diff options
823 files changed, 25806 insertions, 16201 deletions
diff --git a/Documentation/ABI/testing/debugfs-kmemtrace b/Documentation/ABI/testing/debugfs-kmemtrace deleted file mode 100644 index 5e6a92a02d8..00000000000 --- a/Documentation/ABI/testing/debugfs-kmemtrace +++ /dev/null @@ -1,71 +0,0 @@ -What: /sys/kernel/debug/kmemtrace/ -Date: July 2008 -Contact: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> -Description: - -In kmemtrace-enabled kernels, the following files are created: - -/sys/kernel/debug/kmemtrace/ - cpu<n> (0400) Per-CPU tracing data, see below. (binary) - total_overruns (0400) Total number of bytes which were dropped from - cpu<n> files because of full buffer condition, - non-binary. (text) - abi_version (0400) Kernel's kmemtrace ABI version. (text) - -Each per-CPU file should be read according to the relay interface. That is, -the reader should set affinity to that specific CPU and, as currently done by -the userspace application (though there are other methods), use poll() with -an infinite timeout before every read(). Otherwise, erroneous data may be -read. The binary data has the following _core_ format: - - Event ID (1 byte) Unsigned integer, one of: - 0 - represents an allocation (KMEMTRACE_EVENT_ALLOC) - 1 - represents a freeing of previously allocated memory - (KMEMTRACE_EVENT_FREE) - Type ID (1 byte) Unsigned integer, one of: - 0 - this is a kmalloc() / kfree() - 1 - this is a kmem_cache_alloc() / kmem_cache_free() - 2 - this is a __get_free_pages() et al. - Event size (2 bytes) Unsigned integer representing the - size of this event. Used to extend - kmemtrace. Discard the bytes you - don't know about. - Sequence number (4 bytes) Signed integer used to reorder data - logged on SMP machines. Wraparound - must be taken into account, although - it is unlikely. - Caller address (8 bytes) Return address to the caller. - Pointer to mem (8 bytes) Pointer to target memory area. Can be - NULL, but not all such calls might be - recorded. - -In case of KMEMTRACE_EVENT_ALLOC events, the next fields follow: - - Requested bytes (8 bytes) Total number of requested bytes, - unsigned, must not be zero. - Allocated bytes (8 bytes) Total number of actually allocated - bytes, unsigned, must not be lower - than requested bytes. - Requested flags (4 bytes) GFP flags supplied by the caller. - Target CPU (4 bytes) Signed integer, valid for event id 1. - If equal to -1, target CPU is the same - as origin CPU, but the reverse might - not be true. - -The data is made available in the same endianness the machine has. - -Other event ids and type ids may be defined and added. Other fields may be -added by increasing event size, but see below for details. -Every modification to the ABI, including new id definitions, are followed -by bumping the ABI version by one. - -Adding new data to the packet (features) is done at the end of the mandatory -data: - Feature size (2 byte) - Feature ID (1 byte) - Feature data (Feature size - 3 bytes) - - -Users: - kmemtrace-user - git://repo.or.cz/kmemtrace-user.git - diff --git a/Documentation/DocBook/kgdb.tmpl b/Documentation/DocBook/kgdb.tmpl index 55f12ac37ac..490d862c5f0 100644 --- a/Documentation/DocBook/kgdb.tmpl +++ b/Documentation/DocBook/kgdb.tmpl @@ -199,10 +199,33 @@ may be configured as a kernel built-in or a kernel loadable module. You can only make use of <constant>kgdbwait</constant> and early debugging if you build kgdboc into the kernel as a built-in. + <para>Optionally you can elect to activate kms (Kernel Mode + Setting) integration. When you use kms with kgdboc and you have a + video driver that has atomic mode setting hooks, it is possible to + enter the debugger on the graphics console. When the kernel + execution is resumed, the previous graphics mode will be restored. + This integration can serve as a useful tool to aid in diagnosing + crashes or doing analysis of memory with kdb while allowing the + full graphics console applications to run. + </para> </para> <sect2 id="kgdbocArgs"> <title>kgdboc arguments</title> - <para>Usage: <constant>kgdboc=[kbd][[,]serial_device][,baud]</constant></para> + <para>Usage: <constant>kgdboc=[kms][[,]kbd][[,]serial_device][,baud]</constant></para> + <para>The order listed above must be observed if you use any of the + optional configurations together. + </para> + <para>Abbreviations: + <itemizedlist> + <listitem><para>kms = Kernel Mode Setting</para></listitem> + <listitem><para>kbd = Keyboard</para></listitem> + </itemizedlist> + </para> + <para>You can configure kgdboc to use the keyboard, and or a serial + device depending on if you are using kdb and or kgdb, in one of the + following scenarios. The order listed above must be observed if + you use any of the optional configurations together. Using kms + + only gdb is generally not a useful combination.</para> <sect3 id="kgdbocArgs1"> <title>Using loadable module or built-in</title> <para> @@ -212,7 +235,7 @@ <listitem> <para>As a kernel loadable module:</para> <para>Use the command: <constant>modprobe kgdboc kgdboc=<tty-device>,[baud]</constant></para> - <para>Here are two examples of how you might formate the kgdboc + <para>Here are two examples of how you might format the kgdboc string. The first is for an x86 target using the first serial port. The second example is for the ARM Versatile AB using the second serial port. @@ -240,6 +263,9 @@ </sect3> <sect3 id="kgdbocArgs3"> <title>More examples</title> + <para>You can configure kgdboc to use the keyboard, and or a serial + device depending on if you are using kdb and or kgdb, in one of the + following scenarios.</para> <para>You can configure kgdboc to use the keyboard, and or a serial device depending on if you are using kdb and or kgdb, in one of the following scenarios. @@ -255,6 +281,12 @@ <listitem><para>kdb with a keyboard</para> <para><constant>kgdboc=kbd</constant></para> </listitem> + <listitem><para>kdb with kernel mode setting</para> + <para><constant>kgdboc=kms,kbd</constant></para> + </listitem> + <listitem><para>kdb with kernel mode setting and kgdb over a serial port</para> + <para><constant>kgdboc=kms,kbd,ttyS0,115200</constant></para> + </listitem> </orderedlist> </para> </sect3> @@ -637,6 +669,8 @@ Task Addr Pid Parent [*] cpu State Thread Command <listitem><para>The logic to perform safe memory reads and writes to memory while using the debugger</para></listitem> <listitem><para>A full implementation for software breakpoints unless overridden by the arch</para></listitem> <listitem><para>The API to invoke either the kdb or kgdb frontend to the debug core.</para></listitem> + <listitem><para>The structures and callback API for atomic kernel mode setting.</para> + <para>NOTE: kgdboc is where the kms callbacks are invoked.</para></listitem> </itemizedlist> </para> </listitem> @@ -747,6 +781,8 @@ Task Addr Pid Parent [*] cpu State Thread Command </sect1> <sect1 id="kgdbocDesign"> <title>kgdboc internals</title> + <sect2> + <title>kgdboc and uarts</title> <para> The kgdboc driver is actually a very thin driver that relies on the underlying low level to the hardware driver having "polling hooks" @@ -754,11 +790,8 @@ Task Addr Pid Parent [*] cpu State Thread Command implementation of kgdboc it the serial_core was changed to expose a low level UART hook for doing polled mode reading and writing of a single character while in an atomic context. When kgdb makes an I/O - request to the debugger, kgdboc invokes a call back in the serial - core which in turn uses the call back in the UART driver. It is - certainly possible to extend kgdboc to work with non-UART based - consoles in the future. - </para> + request to the debugger, kgdboc invokes a callback in the serial + core which in turn uses the callback in the UART driver.</para> <para> When using kgdboc with a UART, the UART driver must implement two callbacks in the <constant>struct uart_ops</constant>. Example from drivers/8250.c:<programlisting> #ifdef CONFIG_CONSOLE_POLL @@ -772,9 +805,68 @@ Task Addr Pid Parent [*] cpu State Thread Command that they can be called from an atomic context and have to restore the state of the UART chip on return such that the system can return to normal when the debugger detaches. You need to be very careful - with any kind of lock you consider, because failing here is most + with any kind of lock you consider, because failing here is most likely going to mean pressing the reset button. </para> + </sect2> + <sect2 id="kgdbocKbd"> + <title>kgdboc and keyboards</title> + <para>The kgdboc driver contains logic to configure communications + with an attached keyboard. The keyboard infrastructure is only + compiled into the kernel when CONFIG_KDB_KEYBOARD=y is set in the + kernel configuration.</para> + <para>The core polled keyboard driver driver for PS/2 type keyboards + is in drivers/char/kdb_keyboard.c. This driver is hooked into the + debug core when kgdboc populates the callback in the array + called <constant>kdb_poll_funcs[]</constant>. The + kdb_get_kbd_char() is the top-level function which polls hardware + for single character input. + </para> + </sect2> + <sect2 id="kgdbocKms"> + <title>kgdboc and kms</title> + <para>The kgdboc driver contains logic to request the graphics + display to switch to a text context when you are using + "kgdboc=kms,kbd", provided that you have a video driver which has a + frame buffer console and atomic kernel mode setting support.</para> + <para> + Every time the kernel + debugger is entered it calls kgdboc_pre_exp_handler() which in turn + calls con_debug_enter() in the virtual console layer. On resuming kernel + execution, the kernel debugger calls kgdboc_post_exp_handler() which + in turn calls con_debug_leave().</para> + <para>Any video driver that wants to be compatible with the kernel + debugger and the atomic kms callbacks must implement the + mode_set_base_atomic, fb_debug_enter and fb_debug_leave operations. + For the fb_debug_enter and fb_debug_leave the option exists to use + the generic drm fb helper functions or implement something custom for + the hardware. The following example shows the initialization of the + .mode_set_base_atomic operation in + drivers/gpu/drm/i915/intel_display.c: + <informalexample> + <programlisting> +static const struct drm_crtc_helper_funcs intel_helper_funcs = { +[...] + .mode_set_base_atomic = intel_pipe_set_base_atomic, +[...] +}; + </programlisting> + </informalexample> + </para> + <para>Here is an example of how the i915 driver initializes the fb_debug_enter and fb_debug_leave functions to use the generic drm helpers in + drivers/gpu/drm/i915/intel_fb.c: + <informalexample> + <programlisting> +static struct fb_ops intelfb_ops = { +[...] + .fb_debug_enter = drm_fb_helper_debug_enter, + .fb_debug_leave = drm_fb_helper_debug_leave, +[...] +}; + </programlisting> + </informalexample> + </para> + </sect2> </sect1> </chapter> <chapter id="credits"> diff --git a/Documentation/DocBook/stylesheet.xsl b/Documentation/DocBook/stylesheet.xsl index 254c1d5d2e5..85b25275196 100644 --- a/Documentation/DocBook/stylesheet.xsl +++ b/Documentation/DocBook/stylesheet.xsl @@ -6,4 +6,5 @@ <param name="callout.graphics">0</param> <!-- <param name="paper.type">A4</param> --> <param name="generate.section.toc.level">2</param> +<param name="use.id.as.filename">1</param> </stylesheet> diff --git a/Documentation/coccinelle.txt b/Documentation/coccinelle.txt new file mode 100644 index 00000000000..cd2b0283706 --- /dev/null +++ b/Documentation/coccinelle.txt @@ -0,0 +1,258 @@ +Copyright 2010 Nicolas Palix <npalix@diku.dk> +Copyright 2010 Julia Lawall <julia@diku.dk> +Copyright 2010 Gilles Muller <Gilles.Muller@lip6.fr> + + + Getting Coccinelle +~~~~~~~~~~~~~~~~~~~~ + +The semantic patches included in the kernel use the 'virtual rule' +feature which was introduced in Coccinelle version 0.1.11. + +Coccinelle (>=0.2.0) is available through the package manager +of many distributions, e.g. : + + - Debian (>=squeeze) + - Fedora (>=13) + - Ubuntu (>=10.04 Lucid Lynx) + - OpenSUSE + - Arch Linux + - NetBSD + - FreeBSD + + +You can get the latest version released from the Coccinelle homepage at +http://coccinelle.lip6.fr/ + +Once you have it, run the following command: + + ./configure + make + +as a regular user, and install it with + + sudo make install + + + Using Coccinelle on the Linux kernel +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +A Coccinelle-specific target is defined in the top level +Makefile. This target is named 'coccicheck' and calls the 'coccicheck' +front-end in the 'scripts' directory. + +Four modes are defined: report, patch, context, and org. The mode to +use is specified by setting the MODE variable with 'MODE=<mode>'. + +'report' generates a list in the following format: + file:line:column-column: message + +'patch' proposes a fix, when possible. + +'context' highlights lines of interest and their context in a +diff-like style.Lines of interest are indicated with '-'. + +'org' generates a report in the Org mode format of Emacs. + +Note that not all semantic patches implement all modes. + +To make a report for every semantic patch, run the following command: + + make coccicheck MODE=report + +NB: The 'report' mode is the default one. + +To produce patches, run: + + make coccicheck MODE=patch + + +The coccicheck target applies every semantic patch available in the +subdirectories of 'scripts/coccinelle' to the entire Linux kernel. + +For each semantic patch, a changelog message is proposed. It gives a +description of the problem being checked by the semantic patch, and +includes a reference to Coccinelle. + +As any static code analyzer, Coccinelle produces false +positives. Thus, reports must be carefully checked, and patches +reviewed. + + + Using Coccinelle with a single semantic patch +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The optional make variable COCCI can be used to check a single +semantic patch. In that case, the variable must be initialized with +the name of the semantic patch to apply. + +For instance: + + make coccicheck COCCI=<my_SP.cocci> MODE=patch +or + make coccicheck COCCI=<my_SP.cocci> MODE=report + + + Proposing new semantic patches +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +New semantic patches can be proposed and submitted by kernel +developers. For sake of clarity, they should be organized in the +subdirectories of 'scripts/coccinelle/'. + + + Detailed description of the 'report' mode +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +'report' generates a list in the following format: + file:line:column-column: message + +Example: + +Running + + make coccicheck MODE=report COCCI=scripts/coccinelle/err_cast.cocci + +will execute the following part of the SmPL script. + +<smpl> +@r depends on !context && !patch && (org || report)@ +expression x; +position p; +@@ + + ERR_PTR@p(PTR_ERR(x)) + +@script:python depends on report@ +p << r.p; +x << r.x; +@@ + +msg="ERR_CAST can be used with %s" % (x) +coccilib.report.print_report(p[0], msg) +</smpl> + +This SmPL excerpt generates entries on the standard output, as +illustrated below: + +/home/user/linux/crypto/ctr.c:188:9-16: ERR_CAST can be used with alg +/home/user/linux/crypto/authenc.c:619:9-16: ERR_CAST can be used with auth +/home/user/linux/crypto/xts.c:227:9-16: ERR_CAST can be used with alg + + + Detailed description of the 'patch' mode +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +When the 'patch' mode is available, it proposes a fix for each problem +identified. + +Example: + +Running + make coccicheck MODE=patch COCCI=scripts/coccinelle/err_cast.cocci + +will execute the following part of the SmPL script. + +<smpl> +@ depends on !context && patch && !org && !report @ +expression x; +@@ + +- ERR_PTR(PTR_ERR(x)) ++ ERR_CAST(x) +</smpl> + +This SmPL excerpt generates patch hunks on the standard output, as +illustrated below: + +diff -u -p a/crypto/ctr.c b/crypto/ctr.c +--- a/crypto/ctr.c 2010-05-26 10:49:38.000000000 +0200 ++++ b/crypto/ctr.c 2010-06-03 23:44:49.000000000 +0200 +@@ -185,7 +185,7 @@ static struct crypto_instance *crypto_ct + alg = crypto_attr_alg(tb[1], CRYPTO_ALG_TYPE_CIPHER, + CRYPTO_ALG_TYPE_MASK); + if (IS_ERR(alg)) +- return ERR_PTR(PTR_ERR(alg)); ++ return ERR_CAST(alg); + + /* Block size must be >= 4 bytes. */ + err = -EINVAL; + + Detailed description of the 'context' mode +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +'context' highlights lines of interest and their context +in a diff-like style. + +NOTE: The diff-like output generated is NOT an applicable patch. The + intent of the 'context' mode is to highlight the important lines + (annotated with minus, '-') and gives some surrounding context + lines around. This output can be used with the diff mode of + Emacs to review the code. + +Example: + +Running + make coccicheck MODE=context COCCI=scripts/coccinelle/err_cast.cocci + +will execute the following part of the SmPL script. + +<smpl> +@ depends on context && !patch && !org && !report@ +expression x; +@@ + +* ERR_PTR(PTR_ERR(x)) +</smpl> + +This SmPL excerpt generates diff hunks on the standard output, as +illustrated below: + +diff -u -p /home/user/linux/crypto/ctr.c /tmp/nothing +--- /home/user/linux/crypto/ctr.c 2010-05-26 10:49:38.000000000 +0200 ++++ /tmp/nothing +@@ -185,7 +185,6 @@ static struct crypto_instance *crypto_ct + alg = crypto_attr_alg(tb[1], CRYPTO_ALG_TYPE_CIPHER, + CRYPTO_ALG_TYPE_MASK); + if (IS_ERR(alg)) +- return ERR_PTR(PTR_ERR(alg)); + + /* Block size must be >= 4 bytes. */ + err = -EINVAL; + + Detailed description of the 'org' mode +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +'org' generates a report in the Org mode format of Emacs. + +Example: + +Running + make coccicheck MODE=org COCCI=scripts/coccinelle/err_cast.cocci + +will execute the following part of the SmPL script. + +<smpl> +@r depends on !context && !patch && (org || report)@ +expression x; +position p; +@@ + + ERR_PTR@p(PTR_ERR(x)) + +@script:python depends on org@ +p << r.p; +x << r.x; +@@ + +msg="ERR_CAST can be used with %s" % (x) +msg_safe=msg.replace("[","@(").replace("]",")") +coccilib.org.print_todo(p[0], msg_safe) +</smpl> + +This SmPL excerpt generates Org entries on the standard output, as +illustrated below: + +* TODO [[view:/home/user/linux/crypto/ctr.c::face=ovl-face1::linb=188::colb=9::cole=16][ERR_CAST can be used with alg]] +* TODO [[view:/home/user/linux/crypto/authenc.c::face=ovl-face1::linb=619::colb=9::cole=16][ERR_CAST can be used with auth]] +* TODO [[view:/home/user/linux/crypto/xts.c::face=ovl-face1::linb=227::colb=9::cole=16][ERR_CAST can be used with alg]] diff --git a/Documentation/hwmon/pkgtemp b/Documentation/hwmon/pkgtemp new file mode 100644 index 00000000000..c8e1fb0fadd --- /dev/null +++ b/Documentation/hwmon/pkgtemp @@ -0,0 +1,36 @@ +Kernel driver pkgtemp +====================== + +Supported chips: + * Intel family + Prefix: 'pkgtemp' + CPUID: + Datasheet: Intel 64 and IA-32 Architectures Software Developer's Manual + Volume 3A: System Programming Guide + +Author: Fenghua Yu + +Description +----------- + +This driver permits reading package level temperature sensor embedded inside +Intel CPU package. The sensors can be in core, uncore, memory controller, or +other components in a package. The feature is first implemented in Intel Sandy +Bridge platform. + +Temperature is measured in degrees Celsius and measurement resolution is +1 degree C. Valid temperatures are from 0 to TjMax degrees C, because the actual +value of temperature register is in fact a delta from TjMax. + +Temperature known as TjMax is the maximum junction temperature of package. +We get this from MSR_IA32_TEMPERATURE_TARGET. If the MSR is not accessible, +we define TjMax as 100 degrees Celsius. At this temperature, protection +mechanism will perform actions to forcibly cool down the package. Alarm +may be raised, if the temperature grows enough (more than TjMax) to trigger +the Out-Of-Spec bit. Following table summarizes the exported sysfs files: + +temp1_input - Package temperature (in millidegrees Celsius). +temp1_max - All cooling devices should be turned on. +temp1_crit - Maximum junction temperature (in millidegrees Celsius). +temp1_crit_alarm - Set when Out-of-spec bit is set, never clears. + Correct CPU operation is no longer guaranteed. diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt index 634c625da8c..1e5165aa9e4 100644 --- a/Documentation/kbuild/kbuild.txt +++ b/Documentation/kbuild/kbuild.txt @@ -22,11 +22,33 @@ building C files and assembler files. KAFLAGS -------------------------------------------------- -Additional options to the assembler. +Additional options to the assembler (for built-in and modules). + +AFLAGS_MODULE +-------------------------------------------------- +Addtional module specific options to use for $(AS). + +AFLAGS_KERNEL +-------------------------------------------------- +Addtional options for $(AS) when used for assembler +code for code that is compiled as built-in. KCFLAGS -------------------------------------------------- -Additional options to the C compiler. +Additional options to the C compiler (for built-in and modules). + +CFLAGS_KERNEL +-------------------------------------------------- +Addtional options for $(CC) when used to compile +code that is compiled as built-in. + +CFLAGS_MODULE +-------------------------------------------------- +Addtional module specific options to use for $(CC). + +LDFLAGS_MODULE +-------------------------------------------------- +Additional options used for $(LD) when linking modules. KBUILD_VERBOSE -------------------------------------------------- @@ -40,15 +62,15 @@ Set the directory to look for the kernel source when building external modules. The directory can be specified in several ways: 1) Use "M=..." on the command line -2) Environmnet variable KBUILD_EXTMOD -3) Environmnet variable SUBDIRS +2) Environment variable KBUILD_EXTMOD +3) Environment variable SUBDIRS The possibilities are listed in the order they take precedence. Using "M=..." will always override the others. KBUILD_OUTPUT -------------------------------------------------- Specify the output directory when building the kernel. -The output directory can also be specificed using "O=...". +The output directory can also be specified using "O=...". Setting "O=..." takes precedence over KBUILD_OUTPUT. ARCH @@ -90,7 +112,7 @@ The script will be called with the following arguments: $3 - kernel map file $4 - default install path (use root directory if blank) -The implmentation of "make install" is architecture specific +The implementation of "make install" is architecture specific and it may differ from the above. INSTALLKERNEL is provided to enable the possibility to diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt index b2cb16ebcb1..cca46b1a0f6 100644 --- a/Documentation/kbuild/kconfig.txt +++ b/Documentation/kbuild/kconfig.txt @@ -65,7 +65,7 @@ also use the environment variable KCONFIG_ALLCONFIG as a flag or a filename that contains config symbols that the user requires to be set to a specific value. If KCONFIG_ALLCONFIG is used without a filename, "make *config" checks for a file named -"all{yes/mod/no/random}.config" (corresponding to the *config command +"all{yes/mod/no/def/random}.config" (corresponding to the *config command that was used) for symbol values that are to be forced. If this file is not found, it checks for a file named "all.config" to contain forced values. diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt index 71c602d6168..c375313cb12 100644 --- a/Documentation/kbuild/makefiles.txt +++ b/Documentation/kbuild/makefiles.txt @@ -168,7 +168,7 @@ more details, with real examples. #drivers/isdn/i4l/Makefile # Makefile for the kernel ISDN subsystem and device drivers. # Each configuration option enables a list of files. - obj-$(CONFIG_ISDN) += isdn.o + obj-$(CONFIG_ISDN_I4L) += isdn.o obj-$(CONFIG_ISDN_PPP_BSDCOMP) += isdn_bsdcomp.o --- 3.3 Loadable module goals - obj-m @@ -187,34 +187,35 @@ more details, with real examples. Note: In this example $(CONFIG_ISDN_PPP_BSDCOMP) evaluates to 'm' If a kernel module is built from several source files, you specify - that you want to build a module in the same way as above. - - Kbuild needs to know which the parts that you want to build your - module from, so you have to tell it by setting an - $(<module_name>-objs) variable. + that you want to build a module in the same way as above; however, + kbuild needs to know which object files you want to build your + module from, so you have to tell it by setting a $(<module_name>-y) + variable. Example: #drivers/isdn/i4l/Makefile - obj-$(CONFIG_ISDN) += isdn.o - isdn-objs := isdn_net_lib.o isdn_v110.o isdn_common.o + obj-$(CONFIG_ISDN_I4L) += isdn.o + isdn-y := isdn_net_lib.o isdn_v110.o isdn_common.o In this example, the module name will be isdn.o. Kbuild will - compile the objects listed in $(isdn-objs) and then run + compile the objects listed in $(isdn-y) and then run "$(LD) -r" on the list of these files to generate isdn.o. - Kbuild recognises objects used for composite objects by the suffix - -objs, and the suffix -y. This allows the Makefiles to use - the value of a CONFIG_ symbol to determine if an object is part - of a composite object. + Due to kbuild recognizing $(<module_name>-y) for composite objects, + you can use the value of a CONFIG_ symbol to optionally include an + object file as part of a composite object. Example: #fs/ext2/Makefile - obj-$(CONFIG_EXT2_FS) += ext2.o - ext2-y := balloc.o bitmap.o - ext2-$(CONFIG_EXT2_FS_XATTR) += xattr.o + obj-$(CONFIG_EXT2_FS) += ext2.o + ext2-y := balloc.o dir.o file.o ialloc.o inode.o ioctl.o \ + namei.o super.o symlink.o + ext2-$(CONFIG_EXT2_FS_XATTR) += xattr.o xattr_user.o \ + xattr_trusted.o - In this example, xattr.o is only part of the composite object - ext2.o if $(CONFIG_EXT2_FS_XATTR) evaluates to 'y'. + In this example, xattr.o, xattr_user.o and xattr_trusted.o are only + part of the composite object ext2.o if $(CONFIG_EXT2_FS_XATTR) + evaluates to 'y'. Note: Of course, when you are building objects into the kernel, the syntax above will also work. So, if you have CONFIG_EXT2_FS=y, @@ -244,12 +245,12 @@ more details, with real examples. may contain both a built-in.o and a lib.a file. Example: - #arch/i386/lib/Makefile - lib-y := checksum.o delay.o + #arch/x86/lib/Makefile + lib-y := delay.o - This will create a library lib.a based on checksum.o and delay.o. - For kbuild to actually recognize that there is a lib.a being built, - the directory shall be listed in libs-y. + This will create a library lib.a based on delay.o. For kbuild to + actually recognize that there is a lib.a being built, the directory + shall be listed in libs-y. See also "6.3 List directories to visit when descending". Use of lib-y is normally restricted to lib/ and arch/*/lib. @@ -284,43 +285,40 @@ more details, with real examples. --- 3.7 Compilation flags ccflags-y, asflags-y and ldflags-y - The three flags listed above applies only to the kbuild makefile - where they are assigned. They are used for all the normal - cc, as and ld invocation happenign during a recursive build. + These three flags apply only to the kbuild makefile in which they + are assigned. They are used for all the normal cc, as and ld + invocations happening during a recursive build. Note: Flags with the same behaviour were previously named: EXTRA_CFLAGS, EXTRA_AFLAGS and EXTRA_LDFLAGS. - They are yet supported but their use are deprecated. + They are still supported but their usage is deprecated. - ccflags-y specifies options for compiling C files with $(CC). + ccflags-y specifies options for compiling with $(CC). Example: - # drivers/sound/emu10k1/Makefile - ccflags-y += -I$(obj) - ccflags-$(DEBUG) += -DEMU10K1_DEBUG - + # drivers/acpi/Makefile + ccflags-y := -Os + ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT This variable is necessary because the top Makefile owns the variable $(KBUILD_CFLAGS) and uses it for compilation flags for the entire tree. - asflags-y is a similar string for per-directory options - when compiling assembly language source. + asflags-y specifies options for assembling with $(AS). Example: - #arch/x86_64/kernel/Makefile - asflags-y := -traditional - + #arch/sparc/kernel/Makefile + asflags-y := -ansi - ldflags-y is a string for per-directory options to $(LD). + ldflags-y specifies options for linking with $(LD). Example: - #arch/m68k/fpsp040/Makefile - ldflags-y := -x + #arch/cris/boot/compressed/Makefile + ldflags-y += -T $(srctree)/$(src)/decompress_$(arch-y).lds subdir-ccflags-y, subdir-asflags-y - The two flags listed above are similar to ccflags-y and as-falgs-y. - The difference is that the subdir- variants has effect for the kbuild - file where tey are present and all subdirectories. + The two flags listed above are similar to ccflags-y and asflags-y. + The difference is that the subdir- variants have effect for the kbuild + file where they are present and all subdirectories. Options specified using subdir-* are added to the commandline before the options specified using the non-subdir variants. @@ -340,18 +338,18 @@ more details, with real examples. CFLAGS_aha152x.o = -DAHA152X_STAT -DAUTOCONF CFLAGS_gdth.o = # -DDEBUG_GDTH=2 -D__SERIAL__ -D__COM2__ \ -DGDTH_STATISTICS - CFLAGS_seagate.o = -DARBITRATE -DPARITY -DSEAGATE_USE_ASM - These three lines specify compilation flags for aha152x.o, - gdth.o, and seagate.o + These two lines specify compilation flags for aha152x.o and gdth.o. $(AFLAGS_$@) is a similar feature for source files in assembly languages. Example: # arch/arm/kernel/Makefile - AFLAGS_head-armv.o := -DTEXTADDR=$(TEXTADDR) -traditional - AFLAGS_head-armo.o := -DTEXTADDR=$(TEXTADDR) -traditional + AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) + AFLAGS_crunch-bits.o := -Wa,-mcpu=ep9312 + AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt + --- 3.9 Dependency tracking @@ -923,16 +921,33 @@ When kbuild executes, the following steps are followed (roughly): The first example utilises the trick that a config option expands to 'y' when selected. - CFLAGS_KERNEL $(CC) options specific for built-in + KBUILD_AFLAGS_KERNEL $(AS) options specific for built-in + + $(KBUILD_AFLAGS_KERNEL) contains extra C compiler flags used to compile + resident kernel code. + + KBUILD_AFLAGS_MODULE Options for $(AS) when building modules + + $(KBUILD_AFLAGS_MODULE) is used to add arch specific options that + are used for $(AS). + From commandline AFLAGS_MODULE shall be used (see kbuild.txt). - $(CFLAGS_KERNEL) contains extra C compiler flags used to compile + KBUILD_CFLAGS_KERNEL $(CC) options specific for built-in + + $(KBUILD_CFLAGS_KERNEL) contains extra C compiler flags used to compile resident kernel code. - CFLAGS_MODULE $(CC) options specific for modules + KBUILD_CFLAGS_MODULE Options for $(CC) when building modules + + $(KBUILD_CFLAGS_MODULE) is used to add arch specific options that + are used for $(CC). + From commandline CFLAGS_MODULE shall be used (see kbuild.txt). - $(CFLAGS_MODULE) contains extra C compiler flags used to compile code - for loadable kernel modules. + KBUILD_LDFLAGS_MODULE Options for $(LD) when linking modules + $(KBUILD_LDFLAGS_MODULE) is used to add arch specific options + used when linking modules. This is often a linker script. + From commandline LDFLAGS_MODULE shall be used (see kbuild.txt). --- 6.2 Add prerequisites to archprepare: @@ -1176,14 +1191,14 @@ When kbuild executes, the following steps are followed (roughly): === 7 Kbuild syntax for exported headers The kernel include a set of headers that is exported to userspace. -Many headers can be exported as-is but other headers requires a +Many headers can be exported as-is but other headers require a minimal pre-processing before they are ready for user-space. The pre-processing does: - drop kernel specific annotations - drop include of compiler.h -- drop all sections that is kernel internat (guarded by ifdef __KERNEL__) +- drop all sections that are kernel internal (guarded by ifdef __KERNEL__) -Each relevant directory contain a file name "Kbuild" which specify the +Each relevant directory contains a file name "Kbuild" which specifies the headers to be exported. See subsequent chapter for the syntax of the Kbuild file. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index d9239d5f3ad..f20c7abc032 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -116,6 +116,7 @@ parameter is applicable: More X86-64 boot options can be found in Documentation/x86/x86_64/boot-options.txt . X86 Either 32bit or 64bit x86 (same as X86-32+X86-64) + XEN Xen support is enabled In addition, the following text indicates that the option: @@ -1144,9 +1145,12 @@ and is between 256 and 4096 characters. It is defined in the file kgdboc= [KGDB,HW] kgdb over consoles. Requires a tty driver that supports console polling, or a supported polling keyboard driver (non-usb). - Serial only format: <serial_device>[,baud] - keyboard only format: kbd - keyboard and serial format: kbd,<serial_device>[,baud] + Serial only format: <serial_device>[,baud] + keyboard only format: kbd + keyboard and serial format: kbd,<serial_device>[,baud] + Optional Kernel mode setting: + kms, kbd format: kms,kbd + kms, kbd and serial format: kms,kbd,<ser_dev>[,baud] kgdbwait [KGDB] Stop kernel execution and enter the kernel debugger at the earliest opportunity. @@ -1812,6 +1816,8 @@ and is between 256 and 4096 characters. It is defined in the file nousb [USB] Disable the USB subsystem + nowatchdog [KNL] Disable the lockup detector. + nowb [ARM] nox2apic [X86-64,APIC] Do not enable x2APIC mode. @@ -2886,6 +2892,16 @@ and is between 256 and 4096 characters. It is defined in the file xd= [HW,XT] Original XT pre-IDE (RLL encoded) disks. xd_geo= See header of drivers/block/xd.c. + xen_emul_unplug= [HW,X86,XEN] + Unplug Xen emulated devices + Format: [unplug0,][unplug1] + ide-disks -- unplug primary master IDE devices + aux-ide-disks -- unplug non-primary-master IDE devices + nics -- unplug network devices + all -- unplug all emulated devices (NICs and IDE disks) + ignore -- continue loading the Xen platform PCI driver even + if the version check failed + xirc2ps_cs= [NET,PCMCIA] Format: <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt index f1f81afee8a..dc52bd442c9 100644 --- a/Documentation/trace/ftrace-design.txt +++ b/Documentation/trace/ftrace-design.txt @@ -13,6 +13,9 @@ Note that this focuses on architecture implementation details only. If you want more explanation of a feature in terms of common code, review the common ftrace.txt file. +Ideally, everyone who wishes to retain performance while supporting tracing in +their kernel should make it all the way to dynamic ftrace support. + Prerequisites ------------- @@ -215,7 +218,7 @@ An arch may pass in a unique value (frame pointer) to both the entering and exiting of a function. On exit, the value is compared and if it does not match, then it will panic the kernel. This is largely a sanity check for bad code generation with gcc. If gcc for your port sanely updates the frame -pointer under different opitmization levels, then ignore this option. +pointer under different optimization levels, then ignore this option. However, adding support for it isn't terribly difficult. In your assembly code that calls prepare_ftrace_return(), pass the frame pointer as the 3rd argument. @@ -234,7 +237,7 @@ If you can't trace NMI functions, then skip this option. HAVE_SYSCALL_TRACEPOINTS ---------------------- +------------------------ You need very few things to get the syscalls tracing in an arch. @@ -250,12 +253,152 @@ You need very few things to get the syscalls tracing in an arch. HAVE_FTRACE_MCOUNT_RECORD ------------------------- -See scripts/recordmcount.pl for more info. +See scripts/recordmcount.pl for more info. Just fill in the arch-specific +details for how to locate the addresses of mcount call sites via objdump. +This option doesn't make much sense without also implementing dynamic ftrace. + +HAVE_DYNAMIC_FTRACE +------------------- + +You will first need HAVE_FTRACE_MCOUNT_RECORD and HAVE_FUNCTION_TRACER, so +scroll your reader back up if you got over eager. + +Once those are out of the way, you will need to implement: + - asm/ftrace.h: + - MCOUNT_ADDR + - ftrace_call_adjust() + - struct dyn_arch_ftrace{} + - asm code: + - mcount() (new stub) + - ftrace_caller() + - ftrace_call() + - ftrace_stub() + - C code: + - ftrace_dyn_arch_init() + - ftrace_make_nop() + - ftrace_make_call() + - ftrace_update_ftrace_func() + +First you will need to fill out some arch details in your asm/ftrace.h. + +Define MCOUNT_ADDR as the address of your mcount symbol similar to: + #define MCOUNT_ADDR ((unsigned long)mcount) +Since no one else will have a decl for that function, you will need to: + extern void mcount(void); + +You will also need the helper function ftrace_call_adjust(). Most people +will be able to stub it out like so: + static inline unsigned long ftrace_call_adjust(unsigned long addr) + { + return addr; + } <details to be filled> +Lastly you will need the custom dyn_arch_ftrace structure. If you need +some extra state when runtime patching arbitrary call sites, this is the +place. For now though, create an empty struct: + struct dyn_arch_ftrace { + /* No extra data needed */ + }; + +With the header out of the way, we can fill out the assembly code. While we +did already create a mcount() function earlier, dynamic ftrace only wants a +stub function. This is because the mcount() will only be used during boot +and then all references to it will be patched out never to return. Instead, +the guts of the old mcount() will be used to create a new ftrace_caller() +function. Because the two are hard to merge, it will most likely be a lot +easier to have two separate definitions split up by #ifdefs. Same goes for +the ftrace_stub() as that will now be inlined in ftrace_caller(). + +Before we get confused anymore, let's check out some pseudo code so you can +implement your own stuff in assembly: -HAVE_DYNAMIC_FTRACE ---------------------- +void mcount(void) +{ + return; +} + +void ftrace_caller(void) +{ + /* implement HAVE_FUNCTION_TRACE_MCOUNT_TEST if you desire */ + + /* save all state needed by the ABI (see paragraph above) */ + + unsigned long frompc = ...; + unsigned long selfpc = <return address> - MCOUNT_INSN_SIZE; + +ftrace_call: + ftrace_stub(frompc, selfpc); + + /* restore all state needed by the ABI */ + +ftrace_stub: + return; +} + +This might look a little odd at first, but keep in mind that we will be runtime +patching multiple things. First, only functions that we actually want to trace +will be patched to call ftrace_caller(). Second, since we only have one tracer +active at a time, we will patch the ftrace_caller() function itself to call the +specific tracer in question. That is the point of the ftrace_call label. + +With that in mind, let's move on to the C code that will actually be doing the +runtime patching. You'll need a little knowledge of your arch's opcodes in +order to make it through the next section. + +Every arch has an init callback function. If you need to do something early on +to initialize some state, this is the time to do that. Otherwise, this simple +function below should be sufficient for most people: + +int __init ftrace_dyn_arch_init(void *data) +{ + /* return value is done indirectly via data */ + *(unsigned long *)data = 0; + + return 0; +} + +There are two functions that are used to do runtime patching of arbitrary +functions. The first is used to turn the mcount call site into a nop (which +is what helps us retain runtime performance when not tracing). The second is +used to turn the mcount call site into a call to an arbitrary location (but +typically that is ftracer_caller()). See the general function definition in +linux/ftrace.h for the functions: + ftrace_make_nop() + ftrace_make_call() +The rec->ip value is the address of the mcount call site that was collected +by the scripts/recordmcount.pl during build time. + +The last function is used to do runtime patching of the active tracer. This +will be modifying the assembly code at the location of the ftrace_call symbol +inside of the ftrace_caller() function. So you should have sufficient padding +at that location to support the new function calls you'll be inserting. Some +people will be using a "call" type instruction while others will be using a +"branch" type instruction. Specifically, the function is: + ftrace_update_ftrace_func() + + +HAVE_DYNAMIC_FTRACE + HAVE_FUNCTION_GRAPH_TRACER +------------------------------------------------ + +The function grapher needs a few tweaks in order to work with dynamic ftrace. +Basically, you will need to: + - update: + - ftrace_caller() + - ftrace_graph_call() + - ftrace_graph_caller() + - implement: + - ftrace_enable_ftrace_graph_caller() + - ftrace_disable_ftrace_graph_caller() <details to be filled> +Quick notes: + - add a nop stub after the ftrace_call location named ftrace_graph_call; + stub needs to be large enough to support a call to ftrace_graph_caller() + - update ftrace_graph_caller() to work with being called by the new + ftrace_caller() since some semantics may have changed + - ftrace_enable_ftrace_graph_caller() will runtime patch the + ftrace_graph_call location with a call to ftrace_graph_caller() + - ftrace_disable_ftrace_graph_caller() will runtime patch the + ftrace_graph_call location with nops diff --git a/Documentation/trace/kmemtrace.txt b/Documentation/trace/kmemtrace.txt deleted file mode 100644 index 6308735e58c..00000000000 --- a/Documentation/trace/kmemtrace.txt +++ /dev/null @@ -1,126 +0,0 @@ - kmemtrace - Kernel Memory Tracer - - by Eduard - Gabriel Munteanu - <eduard.munteanu@linux360.ro> - -I. Introduction -=============== - -kmemtrace helps kernel developers figure out two things: -1) how different allocators (SLAB, SLUB etc.) perform -2) how kernel code allocates memory and how much - -To do this, we trace every allocation and export information to the userspace -through the relay interface. We export things such as the number of requested -bytes, the number of bytes actually allocated (i.e. including internal -fragmentation), whether this is a slab allocation or a plain kmalloc() and so -on. - -The actual analysis is performed by a userspace tool (see section III for -details on where to get it from). It logs the data exported by the kernel, -processes it and (as of writing this) can provide the following information: -- the total amount of memory allocated and fragmentation per call-site -- the amount of memory allocated and fragmentation per allocation -- total memory allocated and fragmentation in the collected dataset -- number of cross-CPU allocation and frees (makes sense in NUMA environments) - -Moreover, it can potentially find inconsistent and erroneous behavior in -kernel code, such as using slab free functions on kmalloc'ed memory or -allocating less memory than requested (but not truly failed allocations). - -kmemtrace also makes provisions for tracing on some arch and analysing the -data on another. - -II. Design and goals -==================== - -kmemtrace was designed to handle rather large amounts of data. Thus, it uses -the relay interface to export whatever is logged to userspace, which then -stores it. Analysis and reporting is done asynchronously, that is, after the -data is collected and stored. By design, it allows one to log and analyse -on different machines and different arches. - -As of writing this, the ABI is not considered stable, though it might not -change much. However, no guarantees are made about compatibility yet. When -deemed stable, the ABI should still allow easy extension while maintaining -backward compatibility. This is described further in Documentation/ABI. - -Summary of design goals: - - allow logging and analysis to be done across different machines - - be fast and anticipate usage in high-load environments (*) - - be reasonably extensible - - make it possible for GNU/Linux distributions to have kmemtrace - included in their repositories - -(*) - one of the reasons Pekka Enberg's original userspace data analysis - tool's code was rewritten from Perl to C (although this is more than a - simple conversion) - - -III. Quick usage guide -====================== - -1) Get a kernel that supports kmemtrace and build it accordingly (i.e. enable -CONFIG_KMEMTRACE). - -2) Get the userspace tool and build it: -$ git clone git://repo.or.cz/kmemtrace-user.git # current repository -$ cd kmemtrace-user/ -$ ./autogen.sh -$ ./configure -$ make - -3) Boot the kmemtrace-enabled kernel if you haven't, preferably in the -'single' runlevel (so that relay buffers don't fill up easily), and run -kmemtrace: -# '$' does not mean user, but root here. -$ mount -t debugfs none /sys/kernel/debug -$ mount -t proc none /proc -$ cd path/to/kmemtrace-user/ -$ ./kmemtraced -Wait a bit, then stop it with CTRL+C. -$ cat /sys/kernel/debug/kmemtrace/total_overruns # Check if we didn't - # overrun, should - # be zero. -$ (Optionally) [Run kmemtrace_check separately on each cpu[0-9]*.out file to - check its correctness] -$ ./kmemtrace-report - -Now you should have a nice and short summary of how the allocator performs. - -IV. FAQ and known issues -======================== - -Q: 'cat /sys/kernel/debug/kmemtrace/total_overruns' is non-zero, how do I fix -this? Should I worry? -A: If it's non-zero, this affects kmemtrace's accuracy, depending on how -large the number is. You can fix it by supplying a higher -'kmemtrace.subbufs=N' kernel parameter. ---- - -Q: kmemtrace_check reports errors, how do I fix this? Should I worry? -A: This is a bug and should be reported. It can occur for a variety of -reasons: - - possible bugs in relay code - - possible misuse of relay by kmemtrace - - timestamps being collected unorderly -Or you may fix it yourself and send us a patch. ---- - -Q: kmemtrace_report shows many errors, how do I fix this? Should I worry? -A: This is a known issue and I'm working on it. These might be true errors -in kernel code, which may have inconsistent behavior (e.g. allocating memory -with kmem_cache_alloc() and freeing it with kfree()). Pekka Enberg pointed -out this behavior may work with SLAB, but may fail with other allocators. - -It may also be due to lack of tracing in some unusual allocator functions. - -We don't want bug reports regarding this issue yet. ---- - -V. See also -=========== - -Documentation/kernel-parameters.txt -Documentation/ABI/testing/debugfs-kmemtrace - diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt index ec94748ae65..5f77d94598d 100644 --- a/Documentation/trace/kprobetrace.txt +++ b/Documentation/trace/kprobetrace.txt @@ -42,7 +42,7 @@ Synopsis of kprobe_events +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**) NAME=FETCHARG : Set NAME as the argument name of FETCHARG. FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types - (u8/u16/u32/u64/s8/s16/s32/s64) are supported. + (u8/u16/u32/u64/s8/s16/s32/s64) and string are supported. (*) only for return probe. (**) this is useful for fetching a field of data structures. diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c index 66e9358e214..ccd951fa94e 100644 --- a/Documentation/vm/page-types.c +++ b/Documentation/vm/page-types.c @@ -694,7 +694,7 @@ static void usage(void) #endif " -l|--list Show page details in ranges\n" " -L|--list-each Show page details one by one\n" -" -N|--no-summary Don't show summay info\n" +" -N|--no-summary Don't show summary info\n" " -X|--hwpoison hwpoison pages\n" " -x|--unpoison unpoison pages\n" " -h|--help Show this usage message\n" diff --git a/MAINTAINERS b/MAINTAINERS index 05741e0da46..100a3f535c9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1569,6 +1569,16 @@ L: platform-driver-x86@vger.kernel.org S: Supported F: drivers/platform/x86/classmate-laptop.c +COCCINELLE/Semantic Patches (SmPL) +M: Julia Lawall <julia@diku.dk> +M: Gilles Muller <Gilles.Muller@lip6.fr> +M: Nicolas Palix <npalix@diku.dk> +L: cocci@diku.dk (moderated for non-subscribers) +W: http://coccinelle.lip6.fr/ +S: Supported +F: scripts/coccinelle/ +F: scripts/coccicheck + CODA FILE SYSTEM M: Jan Harkes <jaharkes@cs.cmu.edu> M: coda@cs.cmu.edu @@ -3266,8 +3276,8 @@ F: fs/autofs4/ KERNEL BUILD + files below scripts/ (unless maintained elsewhere) M: Michal Marek <mmarek@suse.cz> -T: git git://repo.or.cz/linux-kbuild.git for-next -T: git git://repo.or.cz/linux-kbuild.git for-linus +T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6.git for-next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6.git rc-fixes L: linux-kbuild@vger.kernel.org S: Maintained F: Documentation/kbuild/ @@ -3393,13 +3403,6 @@ F: include/linux/kmemleak.h F: mm/kmemleak.c F: mm/kmemleak-test.c -KMEMTRACE -M: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> -S: Maintained -F: Documentation/trace/kmemtrace.txt -F: include/linux/kmemtrace.h -F: kernel/trace/kmemtrace.c - KPROBES M: Ananth N Mavinakayanahalli <ananth@in.ibm.com> M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> @@ -5675,7 +5678,7 @@ TRACING M: Steven Rostedt <rostedt@goodmis.org> M: Frederic Weisbecker <fweisbec@gmail.com> M: Ingo Molnar <mingo@redhat.com> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git tracing/core +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf/core S: Maintained F: Documentation/trace/ftrace.txt F: arch/*/*/*/ftrace.h @@ -332,10 +332,9 @@ CHECK = sparse CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \ -Wbitwise -Wno-return-void $(CF) -MODFLAGS = -DMODULE -CFLAGS_MODULE = $(MODFLAGS) -AFLAGS_MODULE = $(MODFLAGS) -LDFLAGS_MODULE = -T $(srctree)/scripts/module-common.lds +CFLAGS_MODULE = +AFLAGS_MODULE = +LDFLAGS_MODULE = CFLAGS_KERNEL = AFLAGS_KERNEL = CFLAGS_GCOV = -fprofile-arcs -ftest-coverage @@ -354,7 +353,12 @@ KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -Werror-implicit-function-declaration \ -Wno-format-security \ -fno-delete-null-pointer-checks +KBUILD_AFLAGS_KERNEL := +KBUILD_CFLAGS_KERNEL := KBUILD_AFLAGS := -D__ASSEMBLY__ +KBUILD_AFLAGS_MODULE := -DMODULE +KBUILD_CFLAGS_MODULE := -DMODULE +KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds # Read KERNELRELEASE from include/config/kernel.release (if it exists) KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null) @@ -369,6 +373,8 @@ export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_GCOV export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE +export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE +export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL # When compiling out-of-tree modules, put MODVERDIR in the module # tree rather than in the kernel tree. The kernel tree might @@ -412,9 +418,9 @@ endif # of make so .config is not included in this case either (for *config). no-dot-config-targets := clean mrproper distclean \ - cscope TAGS tags help %docs check% \ + cscope TAGS tags help %docs check% coccicheck \ include/linux/version.h headers_% \ - kernelrelease kernelversion + kernelversion %src-pkg config-targets := 0 mixed-targets := 0 @@ -526,7 +532,7 @@ endif # $(dot-config) # The all: target is the default when no target is given on the # command line. # This allow a user to issue only 'make' to build a kernel including modules -# Defaults vmlinux but it is usually overridden in the arch makefile +# Defaults to vmlinux, but the arch makefile usually adds further targets all: vmlinux ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE @@ -557,6 +563,10 @@ KBUILD_CFLAGS += -g KBUILD_AFLAGS += -gdwarf-2 endif +ifdef CONFIG_DEBUG_INFO_REDUCED +KBUILD_CFLAGS += $(call cc-option, -femit-struct-debug-baseonly) +endif + ifdef CONFIG_FUNCTION_TRACER KBUILD_CFLAGS += -pg endif @@ -603,7 +613,7 @@ endif # Use --build-id when available. LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\ $(call cc-ldoption, -Wl$(comma)--build-id,)) -LDFLAGS_MODULE += $(LDFLAGS_BUILD_ID) +KBUILD_LDFLAGS_MODULE += $(LDFLAGS_BUILD_ID) LDFLAGS_vmlinux += $(LDFLAGS_BUILD_ID) ifeq ($(CONFIG_STRIP_ASM_SYMS),y) @@ -1158,6 +1168,8 @@ distclean: mrproper # rpm target kept for backward compatibility package-dir := $(srctree)/scripts/package +%src-pkg: FORCE + $(Q)$(MAKE) $(build)=$(package-dir) $@ %pkg: include/config/kernel.release FORCE $(Q)$(MAKE) $(build)=$(package-dir) $@ rpm: include/config/kernel.release FORCE @@ -1209,8 +1221,9 @@ help: @echo ' includecheck - Check for duplicate included header files' @echo ' export_report - List the usages of all exported symbols' @echo ' headers_check - Sanity check on exported headers' - @echo ' headerdep - Detect inclusion cycles in headers'; \ - echo '' + @echo ' headerdep - Detect inclusion cycles in headers' + @$(MAKE) -f $(srctree)/scripts/Makefile.help checker-help + @echo '' @echo 'Kernel packaging:' @$(MAKE) $(build)=$(package-dir) help @echo '' @@ -1369,6 +1382,9 @@ versioncheck: -name '*.[hcS]' -type f -print | sort \ | xargs $(PERL) -w $(srctree)/scripts/checkversion.pl +coccicheck: + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/$@ + namespacecheck: $(PERL) $(srctree)/scripts/namespace.pl @@ -1393,9 +1409,9 @@ checkstack: $(OBJDUMP) -d vmlinux $$(find . -name '*.ko') | \ $(PERL) $(src)/scripts/checkstack.pl $(CHECKSTACK_ARCH) -kernelrelease: - $(if $(wildcard include/config/kernel.release), $(Q)echo $(KERNELRELEASE), \ - $(error kernelrelease not valid - run 'make prepare' to update it)) +kernelrelease: include/config/kernel.release + @echo $(KERNELRELEASE) + kernelversion: @echo $(KERNELVERSION) @@ -1472,6 +1488,7 @@ cmd_crmodverdir = $(Q)mkdir -p $(MODVERDIR) \ $(if $(KBUILD_MODULES),; rm -f $(MODVERDIR)/*) a_flags = -Wp,-MD,$(depfile) $(KBUILD_AFLAGS) $(AFLAGS_KERNEL) \ + $(KBUILD_AFLAGS_KERNEL) \ $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(KBUILD_CPPFLAGS) \ $(modkern_aflags) $(EXTRA_AFLAGS) $(AFLAGS_$(basetarget).o) diff --git a/arch/Kconfig b/arch/Kconfig index acda512da2e..4877a8c8ee1 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -151,4 +151,11 @@ config HAVE_MIXED_BREAKPOINTS_REGS config HAVE_USER_RETURN_NOTIFIER bool +config HAVE_PERF_EVENTS_NMI + bool + help + System hardware can generate an NMI using the perf event + subsystem. Also has support for calculating CPU cycle events + to determine how many clock cycles in a given period. + source "kernel/gcov/Kconfig" diff --git a/arch/alpha/include/asm/local64.h b/arch/alpha/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/alpha/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h index 67af4b84198..08265993227 100644 --- a/arch/arm/include/asm/kgdb.h +++ b/arch/arm/include/asm/kgdb.h @@ -70,11 +70,11 @@ extern int kgdb_fault_expected; #define _GP_REGS 16 #define _FP_REGS 8 #define _EXTRA_REGS 2 -#define GDB_MAX_REGS (_GP_REGS + (_FP_REGS * 3) + _EXTRA_REGS) +#define DBG_MAX_REG_NUM (_GP_REGS + (_FP_REGS * 3) + _EXTRA_REGS) #define KGDB_MAX_NO_CPUS 1 #define BUFMAX 400 -#define NUMREGBYTES (GDB_MAX_REGS << 2) +#define NUMREGBYTES (DBG_MAX_REG_NUM << 2) #define NUMCRITREGBYTES (32 << 2) #define _R0 0 @@ -93,7 +93,7 @@ extern int kgdb_fault_expected; #define _SPT 13 #define _LR 14 #define _PC 15 -#define _CPSR (GDB_MAX_REGS - 1) +#define _CPSR (DBG_MAX_REG_NUM - 1) /* * So that we can denote the end of a frame for tracing, diff --git a/arch/arm/include/asm/local64.h b/arch/arm/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/arm/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index c868a886411..778c2f7024f 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -10,57 +10,62 @@ * Deepak Saxena <dsaxena@plexity.net> */ #include <linux/irq.h> +#include <linux/kdebug.h> #include <linux/kgdb.h> #include <asm/traps.h> -/* Make a local copy of the registers passed into the handler (bletch) */ -void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs) +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { - int regno; - - /* Initialize all to zero. */ - for (regno = 0; regno < GDB_MAX_REGS; regno++) - gdb_regs[regno] = 0; + { "r0", 4, offsetof(struct pt_regs, ARM_r0)}, + { "r1", 4, offsetof(struct pt_regs, ARM_r1)}, + { "r2", 4, offsetof(struct pt_regs, ARM_r2)}, + { "r3", 4, offsetof(struct pt_regs, ARM_r3)}, + { "r4", 4, offsetof(struct pt_regs, ARM_r4)}, + { "r5", 4, offsetof(struct pt_regs, ARM_r5)}, + { "r6", 4, offsetof(struct pt_regs, ARM_r6)}, + { "r7", 4, offsetof(struct pt_regs, ARM_r7)}, + { "r8", 4, offsetof(struct pt_regs, ARM_r8)}, + { "r9", 4, offsetof(struct pt_regs, ARM_r9)}, + { "r10", 4, offsetof(struct pt_regs, ARM_r10)}, + { "fp", 4, offsetof(struct pt_regs, ARM_fp)}, + { "ip", 4, offsetof(struct pt_regs, ARM_ip)}, + { "sp", 4, offsetof(struct pt_regs, ARM_sp)}, + { "lr", 4, offsetof(struct pt_regs, ARM_lr)}, + { "pc", 4, offsetof(struct pt_regs, ARM_pc)}, + { "f0", 12, -1 }, + { "f1", 12, -1 }, + { "f2", 12, -1 }, + { "f3", 12, -1 }, + { "f4", 12, -1 }, + { "f5", 12, -1 }, + { "f6", 12, -1 }, + { "f7", 12, -1 }, + { "fps", 4, -1 }, + { "cpsr", 4, offsetof(struct pt_regs, ARM_cpsr)}, +}; - gdb_regs[_R0] = kernel_regs->ARM_r0; - gdb_regs[_R1] = kernel_regs->ARM_r1; - gdb_regs[_R2] = kernel_regs->ARM_r2; - gdb_regs[_R3] = kernel_regs->ARM_r3; - gdb_regs[_R4] = kernel_regs->ARM_r4; - gdb_regs[_R5] = kernel_regs->ARM_r5; - gdb_regs[_R6] = kernel_regs->ARM_r6; - gdb_regs[_R7] = kernel_regs->ARM_r7; - gdb_regs[_R8] = kernel_regs->ARM_r8; - gdb_regs[_R9] = kernel_regs->ARM_r9; - gdb_regs[_R10] = kernel_regs->ARM_r10; - gdb_regs[_FP] = kernel_regs->ARM_fp; - gdb_regs[_IP] = kernel_regs->ARM_ip; - gdb_regs[_SPT] = kernel_regs->ARM_sp; - gdb_regs[_LR] = kernel_regs->ARM_lr; - gdb_regs[_PC] = kernel_regs->ARM_pc; - gdb_regs[_CPSR] = kernel_regs->ARM_cpsr; +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1) + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + else + memset(mem, 0, dbg_reg_def[regno].size); + return dbg_reg_def[regno].name; } -/* Copy local gdb registers back to kgdb regs, for later copy to kernel */ -void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *kernel_regs) +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) { - kernel_regs->ARM_r0 = gdb_regs[_R0]; - kernel_regs->ARM_r1 = gdb_regs[_R1]; - kernel_regs->ARM_r2 = gdb_regs[_R2]; - kernel_regs->ARM_r3 = gdb_regs[_R3]; - kernel_regs->ARM_r4 = gdb_regs[_R4]; - kernel_regs->ARM_r5 = gdb_regs[_R5]; - kernel_regs->ARM_r6 = gdb_regs[_R6]; - kernel_regs->ARM_r7 = gdb_regs[_R7]; - kernel_regs->ARM_r8 = gdb_regs[_R8]; - kernel_regs->ARM_r9 = gdb_regs[_R9]; - kernel_regs->ARM_r10 = gdb_regs[_R10]; - kernel_regs->ARM_fp = gdb_regs[_FP]; - kernel_regs->ARM_ip = gdb_regs[_IP]; - kernel_regs->ARM_sp = gdb_regs[_SPT]; - kernel_regs->ARM_lr = gdb_regs[_LR]; - kernel_regs->ARM_pc = gdb_regs[_PC]; - kernel_regs->ARM_cpsr = gdb_regs[_CPSR]; + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return -EINVAL; + + if (dbg_reg_def[regno].offset != -1) + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + return 0; } void @@ -176,6 +181,33 @@ void kgdb_roundup_cpus(unsigned long flags) local_irq_disable(); } +static int __kgdb_notify(struct die_args *args, unsigned long cmd) +{ + struct pt_regs *regs = args->regs; + + if (kgdb_handle_exception(1, args->signr, cmd, regs)) + return NOTIFY_DONE; + return NOTIFY_STOP; +} +static int +kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = __kgdb_notify(ptr, cmd); + local_irq_restore(flags); + + return ret; +} + +static struct notifier_block kgdb_notifier = { + .notifier_call = kgdb_notify, + .priority = -INT_MAX, +}; + + /** * kgdb_arch_init - Perform any architecture specific initalization. * @@ -184,6 +216,11 @@ void kgdb_roundup_cpus(unsigned long flags) */ int kgdb_arch_init(void) { + int ret = register_die_notifier(&kgdb_notifier); + + if (ret != 0) + return ret; + register_undef_hook(&kgdb_brkpt_hook); register_undef_hook(&kgdb_compiled_brkpt_hook); @@ -200,6 +237,7 @@ void kgdb_arch_exit(void) { unregister_undef_hook(&kgdb_brkpt_hook); unregister_undef_hook(&kgdb_compiled_brkpt_hook); + unregister_die_notifier(&kgdb_notifier); } /* diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index de12536d687..417c392ddf1 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -164,20 +164,20 @@ armpmu_event_set_period(struct perf_event *event, struct hw_perf_event *hwc, int idx) { - s64 left = atomic64_read(&hwc->period_left); + s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0; if (unlikely(left <= -period)) { left = period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } @@ -185,7 +185,7 @@ armpmu_event_set_period(struct perf_event *event, if (left > (s64)armpmu->max_period) left = armpmu->max_period; - atomic64_set(&hwc->prev_count, (u64)-left); + local64_set(&hwc->prev_count, (u64)-left); armpmu->write_counter(idx, (u64)(-left) & 0xffffffff); @@ -204,18 +204,18 @@ armpmu_event_update(struct perf_event *event, u64 delta; again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); new_raw_count = armpmu->read_counter(idx); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &hwc->period_left); + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); return new_raw_count; } @@ -478,7 +478,7 @@ __hw_perf_event_init(struct perf_event *event) if (!hwc->sample_period) { hwc->sample_period = armpmu->max_period; hwc->last_period = hwc->sample_period; - atomic64_set(&hwc->period_left, hwc->sample_period); + local64_set(&hwc->period_left, hwc->sample_period); } err = 0; diff --git a/arch/avr32/Makefile b/arch/avr32/Makefile index ead8a75203a..22fb66590dc 100644 --- a/arch/avr32/Makefile +++ b/arch/avr32/Makefile @@ -13,7 +13,7 @@ KBUILD_DEFCONFIG := atstk1002_defconfig KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic KBUILD_AFLAGS += -mrelax -mno-pic -CFLAGS_MODULE += -mno-relax +KBUILD_CFLAGS_MODULE += -mno-relax LDFLAGS_vmlinux += --relax cpuflags-$(CONFIG_PLATFORM_AT32AP) += -march=ap diff --git a/arch/avr32/include/asm/local64.h b/arch/avr32/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/avr32/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/blackfin/Makefile b/arch/blackfin/Makefile index 5a97a31d4bb..9d5ffaf5492 100644 --- a/arch/blackfin/Makefile +++ b/arch/blackfin/Makefile @@ -18,8 +18,8 @@ ifeq ($(CONFIG_ROMKERNEL),y) KBUILD_CFLAGS += -mlong-calls endif KBUILD_AFLAGS += $(call cc-option,-mno-fdpic) -CFLAGS_MODULE += -mlong-calls -LDFLAGS_MODULE += -m elf32bfin +KBUILD_CFLAGS_MODULE += -mlong-calls +KBUILD_LDFLAGS_MODULE += -m elf32bfin KALLSYMS += --symbol-prefix=_ KBUILD_DEFCONFIG := BF537-STAMP_defconfig diff --git a/arch/blackfin/include/asm/local64.h b/arch/blackfin/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/blackfin/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/cris/include/asm/local64.h b/arch/cris/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/cris/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/frv/Makefile b/arch/frv/Makefile index 310c47a663f..7ff84575b18 100644 --- a/arch/frv/Makefile +++ b/arch/frv/Makefile @@ -23,20 +23,14 @@ # Copyright (C) 1994 by Hamish Macdonald # -CCSPECS := $(shell $(CC) -v 2>&1 | grep "^Reading specs from " | head -1 | cut -c20-) -CCDIR := $(strip $(patsubst %/specs,%,$(CCSPECS))) -CPUCLASS := fr400 - -# test for cross compiling -COMPILE_ARCH = $(shell uname -m) - ifdef CONFIG_MMU UTS_SYSNAME = -DUTS_SYSNAME=\"Linux\" else UTS_SYSNAME = -DUTS_SYSNAME=\"uClinux\" endif -ARCHMODFLAGS += -G0 -mlong-calls +KBUILD_AFLAGS_MODULE += -G0 -mlong-calls +KBUILD_CFLAGS_MODULE += -G0 -mlong-calls ifdef CONFIG_GPREL_DATA_8 KBUILD_CFLAGS += -G8 @@ -54,7 +48,6 @@ endif ifdef CONFIG_GC_SECTIONS KBUILD_CFLAGS += -ffunction-sections -fdata-sections -LINKFLAGS += --gc-sections endif ifndef CONFIG_FRAME_POINTER @@ -64,16 +57,13 @@ endif ifdef CONFIG_CPU_FR451_COMPILE KBUILD_CFLAGS += -mcpu=fr450 KBUILD_AFLAGS += -mcpu=fr450 -ASFLAGS += -mcpu=fr450 else ifdef CONFIG_CPU_FR551_COMPILE KBUILD_CFLAGS += -mcpu=fr550 KBUILD_AFLAGS += -mcpu=fr550 -ASFLAGS += -mcpu=fr550 else KBUILD_CFLAGS += -mcpu=fr400 KBUILD_AFLAGS += -mcpu=fr400 -ASFLAGS += -mcpu=fr400 endif endif @@ -83,14 +73,12 @@ endif KBUILD_CFLAGS += -mno-fdpic -mgpr-32 -msoft-float -mno-media KBUILD_CFLAGS += -ffixed-fcc3 -ffixed-cc3 -ffixed-gr15 -ffixed-icc2 KBUILD_AFLAGS += -mno-fdpic -ASFLAGS += -mno-fdpic # make sure the .S files get compiled with debug info # and disable optimisations that are unhelpful whilst debugging ifdef CONFIG_DEBUG_INFO #KBUILD_CFLAGS += -O1 KBUILD_AFLAGS += -Wa,--gdwarf2 -ASFLAGS += -Wa,--gdwarf2 endif head-y := arch/frv/kernel/head.o arch/frv/kernel/init_task.o @@ -105,11 +93,5 @@ all: Image Image: vmlinux $(Q)$(MAKE) $(build)=arch/frv/boot $@ -bootstrap: - $(Q)$(MAKEBOOT) bootstrap - archclean: $(Q)$(MAKE) $(clean)=arch/frv/boot - -archdep: scripts/mkdep symlinks - $(Q)$(MAKE) $(build)=arch/frv/boot dep diff --git a/arch/frv/include/asm/local64.h b/arch/frv/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/frv/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/frv/kernel/local64.h b/arch/frv/kernel/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/frv/kernel/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/h8300/include/asm/local64.h b/arch/h8300/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/h8300/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index 8ae0d2604ce..be7bfa12b70 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -22,13 +22,13 @@ CHECKFLAGS += -m64 -D__ia64=1 -D__ia64__=1 -D_LP64 -D__LP64__ OBJCOPYFLAGS := --strip-all LDFLAGS_vmlinux := -static -LDFLAGS_MODULE += -T $(srctree)/arch/ia64/module.lds -AFLAGS_KERNEL := -mconstant-gp +KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/ia64/module.lds +KBUILD_AFLAGS_KERNEL := -mconstant-gp EXTRA := cflags-y := -pipe $(EXTRA) -ffixed-r13 -mfixed-range=f12-f15,f32-f127 \ -falign-functions=32 -frename-registers -fno-optimize-sibling-calls -CFLAGS_KERNEL := -mconstant-gp +KBUILD_CFLAGS_KERNEL := -mconstant-gp GAS_STATUS = $(shell $(srctree)/arch/ia64/scripts/check-gas "$(CC)" "$(OBJDUMP)") KBUILD_CPPFLAGS += $(shell $(srctree)/arch/ia64/scripts/toolchain-flags "$(CC)" "$(OBJDUMP)" "$(READELF)") diff --git a/arch/ia64/include/asm/local64.h b/arch/ia64/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/ia64/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/m32r/Makefile b/arch/m32r/Makefile index 469766b24e2..8ff5ba0ea26 100644 --- a/arch/m32r/Makefile +++ b/arch/m32r/Makefile @@ -12,8 +12,8 @@ OBJCOPYFLAGS := -O binary -R .note -R .comment -S LDFLAGS_vmlinux := KBUILD_CFLAGS += -pipe -fno-schedule-insns -CFLAGS_KERNEL += -mmodel=medium -CFLAGS_MODULE += -mmodel=large +KBUILD_CFLAGS_KERNEL += -mmodel=medium +KBUILD_CFLAGS_MODULE += -mmodel=large ifdef CONFIG_CHIP_VDEC2 cflags-$(CONFIG_ISA_M32R2) += -DNO_FPU -Wa,-bitinst diff --git a/arch/m32r/include/asm/local64.h b/arch/m32r/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/m32r/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile index 570d85c3f97..b06a7e3cbcd 100644 --- a/arch/m68k/Makefile +++ b/arch/m68k/Makefile @@ -18,7 +18,7 @@ KBUILD_DEFCONFIG := multi_defconfig # override top level makefile AS += -m68020 LDFLAGS := -m m68kelf -LDFLAGS_MODULE += -T $(srctree)/arch/m68k/kernel/module.lds +KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/m68k/kernel/module.lds ifneq ($(SUBARCH),$(ARCH)) ifeq ($(CROSS_COMPILE),) CROSS_COMPILE := $(call cc-cross-prefix, \ diff --git a/arch/m68k/include/asm/local64.h b/arch/m68k/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/m68k/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index be3855250db..9bd64b4b2b0 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -18,6 +18,8 @@ config MICROBLAZE select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG select TRACING_SUPPORT + select OF + select OF_FLATTREE config SWAP def_bool n @@ -76,9 +78,6 @@ config LOCKDEP_SUPPORT config HAVE_LATENCYTOP_SUPPORT def_bool y -config DTC - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" @@ -125,18 +124,6 @@ config CMDLINE_FORCE Set this to have arguments from the default kernel command string override those passed by the boot loader. -config OF - def_bool y - select OF_FLATTREE - -config PROC_DEVICETREE - bool "Support for device tree in /proc" - depends on PROC_FS - help - This option adds a device-tree directory under /proc which contains - an image of the device tree that the kernel copies from Open - Firmware or other boot firmware. If unsure, say Y here. - endmenu menu "Advanced setup" diff --git a/arch/microblaze/include/asm/irq.h b/arch/microblaze/include/asm/irq.h index 31a35c33df6..ec5583d6111 100644 --- a/arch/microblaze/include/asm/irq.h +++ b/arch/microblaze/include/asm/irq.h @@ -27,17 +27,6 @@ extern unsigned int nr_irq; struct pt_regs; extern void do_IRQ(struct pt_regs *regs); -/** - * irq_of_parse_and_map - Parse and Map an interrupt into linux virq space - * @device: Device node of the device whose interrupt is to be mapped - * @index: Index of the interrupt to map - * - * This function is a wrapper that chains of_irq_map_one() and - * irq_create_of_mapping() to make things easier to callers - */ -struct device_node; -extern unsigned int irq_of_parse_and_map(struct device_node *dev, int index); - /** FIXME - not implement * irq_dispose_mapping - Unmap an interrupt * @virq: linux virq number of the interrupt to unmap @@ -62,17 +51,4 @@ struct irq_host; extern unsigned int irq_create_mapping(struct irq_host *host, irq_hw_number_t hwirq); -/** - * irq_create_of_mapping - Map a hardware interrupt into linux virq space - * @controller: Device node of the interrupt controller - * @inspec: Interrupt specifier from the device-tree - * @intsize: Size of the interrupt specifier from the device-tree - * - * This function is identical to irq_create_mapping except that it takes - * as input informations straight from the device-tree (typically the results - * of the of_irq_map_*() functions. - */ -extern unsigned int irq_create_of_mapping(struct device_node *controller, - u32 *intspec, unsigned int intsize); - #endif /* _ASM_MICROBLAZE_IRQ_H */ diff --git a/arch/microblaze/include/asm/local64.h b/arch/microblaze/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/microblaze/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/microblaze/include/asm/of_device.h b/arch/microblaze/include/asm/of_device.h deleted file mode 100644 index 73cb9804098..00000000000 --- a/arch/microblaze/include/asm/of_device.h +++ /dev/null @@ -1,44 +0,0 @@ -/* - * Copyright (C) 2007-2008 Michal Simek <monstr@monstr.eu> - * - * based on PowerPC of_device.h - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#ifndef _ASM_MICROBLAZE_OF_DEVICE_H -#define _ASM_MICROBLAZE_OF_DEVICE_H -#ifdef __KERNEL__ - -#include <linux/device.h> -#include <linux/of.h> - -/* - * The of_device is a kind of "base class" that is a superset of - * struct device for use by devices attached to an OF node and - * probed using OF properties. - */ -struct of_device { - struct device dev; /* Generic device interface */ - struct pdev_archdata archdata; -}; - -extern ssize_t of_device_get_modalias(struct of_device *ofdev, - char *str, ssize_t len); - -extern struct of_device *of_device_alloc(struct device_node *np, - const char *bus_id, - struct device *parent); - -extern int of_device_uevent(struct device *dev, - struct kobj_uevent_env *env); - -extern void of_device_make_bus_id(struct of_device *dev); - -/* This is just here during the transition */ -#include <linux/of_device.h> - -#endif /* __KERNEL__ */ -#endif /* _ASM_MICROBLAZE_OF_DEVICE_H */ diff --git a/arch/microblaze/include/asm/of_platform.h b/arch/microblaze/include/asm/of_platform.h deleted file mode 100644 index 37491276c6c..00000000000 --- a/arch/microblaze/include/asm/of_platform.h +++ /dev/null @@ -1,54 +0,0 @@ -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _ASM_MICROBLAZE_OF_PLATFORM_H -#define _ASM_MICROBLAZE_OF_PLATFORM_H - -/* This is just here during the transition */ -#include <linux/of_platform.h> - -/* - * The list of OF IDs below is used for matching bus types in the - * system whose devices are to be exposed as of_platform_devices. - * - * This is the default list valid for most platforms. This file provides - * functions who can take an explicit list if necessary though - * - * The search is always performed recursively looking for children of - * the provided device_node and recursively if such a children matches - * a bus type in the list - */ - -static const struct of_device_id of_default_bus_ids[] = { - { .type = "soc", }, - { .compatible = "soc", }, - { .type = "plb5", }, - { .type = "plb4", }, - { .type = "opb", }, - { .type = "simple", }, - {}, -}; - -/* Platform devices and busses creation */ -extern struct of_device *of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent); -/* pseudo "matches" value to not do deep probe */ -#define OF_NO_DEEP_PROBE ((struct of_device_id *)-1) - -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); - -extern struct of_device *of_find_device_by_phandle(phandle ph); - -extern void of_instantiate_rtc(void); - -#endif /* _ASM_MICROBLAZE_OF_PLATFORM_H */ diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h index c12c6dfafd9..4f268faa012 100644 --- a/arch/microblaze/include/asm/page.h +++ b/arch/microblaze/include/asm/page.h @@ -47,13 +47,6 @@ #define PAGE_UP(addr) (((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1))) #define PAGE_DOWN(addr) ((addr)&(~((PAGE_SIZE)-1))) -/* align addr on a size boundary - adjust address up/down if needed */ -#define _ALIGN_UP(addr, size) (((addr)+((size)-1))&(~((size)-1))) -#define _ALIGN_DOWN(addr, size) ((addr)&(~((size)-1))) - -/* align addr on a size boundary - adjust address up if needed */ -#define _ALIGN(addr, size) _ALIGN_UP(addr, size) - #ifndef CONFIG_MMU /* * PAGE_OFFSET -- the first address of the first page of memory. When not diff --git a/arch/microblaze/include/asm/pci-bridge.h b/arch/microblaze/include/asm/pci-bridge.h index 0c77cda9f5d..0c68764ab54 100644 --- a/arch/microblaze/include/asm/pci-bridge.h +++ b/arch/microblaze/include/asm/pci-bridge.h @@ -172,13 +172,8 @@ static inline int pci_has_flag(int flag) extern struct list_head hose_list; -extern unsigned long pci_address_to_pio(phys_addr_t address); extern int pcibios_vaddr_is_ioport(void __iomem *address); #else -static inline unsigned long pci_address_to_pio(phys_addr_t address) -{ - return (unsigned long)-1; -} static inline int pcibios_vaddr_is_ioport(void __iomem *address) { return 0; diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h index e7d67a329bd..101fa098f62 100644 --- a/arch/microblaze/include/asm/prom.h +++ b/arch/microblaze/include/asm/prom.h @@ -20,9 +20,6 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> -#include <linux/of_fdt.h> -#include <linux/proc_fs.h> -#include <linux/platform_device.h> #include <asm/irq.h> #include <asm/atomic.h> @@ -50,29 +47,10 @@ extern void pci_create_OF_bus_map(void); * OF address retreival & translation */ -/* Translate an OF address block into a CPU physical address - */ -extern u64 of_translate_address(struct device_node *np, const u32 *addr); - -/* Extract an address from a device, returns the region size and - * the address space flags too. The PCI version uses a BAR number - * instead of an absolute index - */ -extern const u32 *of_get_address(struct device_node *dev, int index, - u64 *size, unsigned int *flags); -extern const u32 *of_get_pci_address(struct device_node *dev, int bar_no, - u64 *size, unsigned int *flags); - -/* Get an address as a resource. Note that if your address is - * a PIO address, the conversion will fail if the physical address - * can't be internally converted to an IO token with - * pci_address_to_pio(), that is because it's either called to early - * or it can't be matched to any host bridge IO space - */ -extern int of_address_to_resource(struct device_node *dev, int index, - struct resource *r); -extern int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r); +#ifdef CONFIG_PCI +extern unsigned long pci_address_to_pio(phys_addr_t address); +#define pci_address_to_pio pci_address_to_pio +#endif /* CONFIG_PCI */ /* Parse the ibm,dma-window property of an OF node into the busno, phys and * size parameters. @@ -88,69 +66,6 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); /* Get the MAC address */ extern const void *of_get_mac_address(struct device_node *np); -/* - * OF interrupt mapping - */ - -/* This structure is returned when an interrupt is mapped. The controller - * field needs to be put() after use - */ - -#define OF_MAX_IRQ_SPEC 4 /* We handle specifiers of at most 4 cells */ - -struct of_irq { - struct device_node *controller; /* Interrupt controller node */ - u32 size; /* Specifier size */ - u32 specifier[OF_MAX_IRQ_SPEC]; /* Specifier copy */ -}; - -/** - * of_irq_map_init - Initialize the irq remapper - * @flags: flags defining workarounds to enable - * - * Some machines have bugs in the device-tree which require certain workarounds - * to be applied. Call this before any interrupt mapping attempts to enable - * those workarounds. - */ -#define OF_IMAP_OLDWORLD_MAC 0x00000001 -#define OF_IMAP_NO_PHANDLE 0x00000002 - -extern void of_irq_map_init(unsigned int flags); - -/** - * of_irq_map_raw - Low level interrupt tree parsing - * @parent: the device interrupt parent - * @intspec: interrupt specifier ("interrupts" property of the device) - * @ointsize: size of the passed in interrupt specifier - * @addr: address specifier (start of "reg" property of the device) - * @out_irq: structure of_irq filled by this function - * - * Returns 0 on success and a negative number on error - * - * This function is a low-level interrupt tree walking function. It - * can be used to do a partial walk with synthetized reg and interrupts - * properties, for example when resolving PCI interrupts when no device - * node exist for the parent. - * - */ - -extern int of_irq_map_raw(struct device_node *parent, const u32 *intspec, - u32 ointsize, const u32 *addr, - struct of_irq *out_irq); - -/** - * of_irq_map_one - Resolve an interrupt for a device - * @device: the device whose interrupt is to be resolved - * @index: index of the interrupt to resolve - * @out_irq: structure of_irq filled by this function - * - * This function resolves an interrupt, walking the tree, for a given - * device-tree node. It's the high level pendant to of_irq_map_raw(). - * It also implements the workarounds for OldWolrd Macs. - */ -extern int of_irq_map_one(struct device_node *device, int index, - struct of_irq *out_irq); - /** * of_irq_map_pci - Resolve the interrupt for a PCI device * @pdev: the device whose interrupt is to be resolved @@ -163,20 +78,18 @@ extern int of_irq_map_one(struct device_node *device, int index, * resolving using the OF tree walking. */ struct pci_dev; +struct of_irq; extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq); -extern int of_irq_to_resource(struct device_node *dev, int index, - struct resource *r); - -/** - * of_iomap - Maps the memory mapped IO for a given device_node - * @device: the device whose io range will be mapped - * @index: index of the io range - * - * Returns a pointer to the mapped memory - */ -extern void __iomem *of_iomap(struct device_node *device, int index); - #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ + +/* These includes are put at the bottom because they may contain things + * that are overridden by this file. Ideally they shouldn't be included + * by this file, but there are a bunch of .c files that currently depend + * on it. Eventually they will be cleaned up. */ +#include <linux/of_fdt.h> +#include <linux/of_irq.h> +#include <linux/platform_device.h> + #endif /* _ASM_MICROBLAZE_PROM_H */ diff --git a/arch/microblaze/include/asm/topology.h b/arch/microblaze/include/asm/topology.h index 96bcea5a992..5428f333a02 100644 --- a/arch/microblaze/include/asm/topology.h +++ b/arch/microblaze/include/asm/topology.h @@ -1,11 +1 @@ #include <asm-generic/topology.h> - -#ifndef _ASM_MICROBLAZE_TOPOLOGY_H -#define _ASM_MICROBLAZE_TOPOLOGY_H - -struct device_node; -static inline int of_node_to_nid(struct device_node *device) -{ - return 0; -} -#endif /* _ASM_MICROBLAZE_TOPOLOGY_H */ diff --git a/arch/microblaze/kernel/Makefile b/arch/microblaze/kernel/Makefile index 5eecc9f1fbd..f0cb5c26c81 100644 --- a/arch/microblaze/kernel/Makefile +++ b/arch/microblaze/kernel/Makefile @@ -15,8 +15,8 @@ endif extra-y := head.o vmlinux.lds obj-y += dma.o exceptions.o \ - hw_exception_handler.o init_task.o intc.o irq.o of_device.o \ - of_platform.o process.o prom.o prom_parse.o ptrace.o \ + hw_exception_handler.o init_task.o intc.o irq.o \ + process.o prom.o prom_parse.o ptrace.o \ reset.o setup.o signal.o sys_microblaze.o timer.o traps.o unwind.o obj-y += cpu/ diff --git a/arch/microblaze/kernel/irq.c b/arch/microblaze/kernel/irq.c index 598f1fd61c8..a9345fb4906 100644 --- a/arch/microblaze/kernel/irq.c +++ b/arch/microblaze/kernel/irq.c @@ -17,20 +17,10 @@ #include <linux/seq_file.h> #include <linux/kernel_stat.h> #include <linux/irq.h> +#include <linux/of_irq.h> #include <asm/prom.h> -unsigned int irq_of_parse_and_map(struct device_node *dev, int index) -{ - struct of_irq oirq; - - if (of_irq_map_one(dev, index, &oirq)) - return NO_IRQ; - - return oirq.specifier[0]; -} -EXPORT_SYMBOL_GPL(irq_of_parse_and_map); - static u32 concurrent_irq; void __irq_entry do_IRQ(struct pt_regs *regs) @@ -106,7 +96,7 @@ unsigned int irq_create_mapping(struct irq_host *host, irq_hw_number_t hwirq) EXPORT_SYMBOL_GPL(irq_create_mapping); unsigned int irq_create_of_mapping(struct device_node *controller, - u32 *intspec, unsigned int intsize) + const u32 *intspec, unsigned int intsize) { return intspec[0]; } diff --git a/arch/microblaze/kernel/of_device.c b/arch/microblaze/kernel/of_device.c deleted file mode 100644 index b372787886e..00000000000 --- a/arch/microblaze/kernel/of_device.c +++ /dev/null @@ -1,112 +0,0 @@ -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/mod_devicetable.h> -#include <linux/slab.h> -#include <linux/of_device.h> - -#include <linux/errno.h> - -void of_device_make_bus_id(struct of_device *dev) -{ - static atomic_t bus_no_reg_magic; - struct device_node *node = dev->dev.of_node; - const u32 *reg; - u64 addr; - int magic; - - /* - * For MMIO, get the physical address - */ - reg = of_get_property(node, "reg", NULL); - if (reg) { - addr = of_translate_address(node, reg); - if (addr != OF_BAD_ADDR) { - dev_set_name(&dev->dev, "%llx.%s", - (unsigned long long)addr, node->name); - return; - } - } - - /* - * No BusID, use the node name and add a globally incremented - * counter (and pray...) - */ - magic = atomic_add_return(1, &bus_no_reg_magic); - dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1); -} -EXPORT_SYMBOL(of_device_make_bus_id); - -struct of_device *of_device_alloc(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - struct of_device *dev; - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return NULL; - - dev->dev.of_node = of_node_get(np); - dev->dev.dma_mask = &dev->archdata.dma_mask; - dev->dev.parent = parent; - dev->dev.release = of_release_dev; - - if (bus_id) - dev_set_name(&dev->dev, bus_id); - else - of_device_make_bus_id(dev); - - return dev; -} -EXPORT_SYMBOL(of_device_alloc); - -int of_device_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - struct of_device *ofdev; - const char *compat; - int seen = 0, cplen, sl; - - if (!dev) - return -ENODEV; - - ofdev = to_of_device(dev); - - if (add_uevent_var(env, "OF_NAME=%s", ofdev->dev.of_node->name)) - return -ENOMEM; - - if (add_uevent_var(env, "OF_TYPE=%s", ofdev->dev.of_node->type)) - return -ENOMEM; - - /* Since the compatible field can contain pretty much anything - * it's not really legal to split it out with commas. We split it - * up using a number of environment variables instead. */ - - compat = of_get_property(ofdev->dev.of_node, "compatible", &cplen); - while (compat && *compat && cplen > 0) { - if (add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat)) - return -ENOMEM; - - sl = strlen(compat) + 1; - compat += sl; - cplen -= sl; - seen++; - } - - if (add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen)) - return -ENOMEM; - - /* modalias is trickier, we add it in 2 steps */ - if (add_uevent_var(env, "MODALIAS=")) - return -ENOMEM; - sl = of_device_get_modalias(ofdev, &env->buf[env->buflen-1], - sizeof(env->buf) - env->buflen); - if (sl >= (sizeof(env->buf) - env->buflen)) - return -ENOMEM; - env->buflen += sl; - - return 0; -} -EXPORT_SYMBOL(of_device_uevent); diff --git a/arch/microblaze/kernel/of_platform.c b/arch/microblaze/kernel/of_platform.c deleted file mode 100644 index ccf6f4257f4..00000000000 --- a/arch/microblaze/kernel/of_platform.c +++ /dev/null @@ -1,200 +0,0 @@ -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * and Arnd Bergmann, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#undef DEBUG - -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/mod_devicetable.h> -#include <linux/pci.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/of_platform.h> - -#include <linux/errno.h> -#include <linux/topology.h> -#include <asm/atomic.h> - -struct bus_type of_platform_bus_type = { - .uevent = of_device_uevent, -}; -EXPORT_SYMBOL(of_platform_bus_type); - -static int __init of_bus_driver_init(void) -{ - return of_bus_type_init(&of_platform_bus_type, "of_platform"); -} -postcore_initcall(of_bus_driver_init); - -struct of_device *of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - struct of_device *dev; - - dev = of_device_alloc(np, bus_id, parent); - if (!dev) - return NULL; - - dev->archdata.dma_mask = 0xffffffffUL; - dev->dev.bus = &of_platform_bus_type; - - /* We do not fill the DMA ops for platform devices by default. - * This is currently the responsibility of the platform code - * to do such, possibly using a device notifier - */ - - if (of_device_register(dev) != 0) { - of_device_free(dev); - return NULL; - } - - return dev; -} -EXPORT_SYMBOL(of_platform_device_create); - -/** - * of_platform_bus_create - Create an OF device for a bus node and all its - * children. Optionally recursively instanciate matching busses. - * @bus: device node of the bus to instanciate - * @matches: match table, NULL to use the default, OF_NO_DEEP_PROBE to - * disallow recursive creation of child busses - */ -static int of_platform_bus_create(const struct device_node *bus, - const struct of_device_id *matches, - struct device *parent) -{ - struct device_node *child; - struct of_device *dev; - int rc = 0; - - for_each_child_of_node(bus, child) { - pr_debug(" create child: %s\n", child->full_name); - dev = of_platform_device_create(child, NULL, parent); - if (dev == NULL) - rc = -ENOMEM; - else if (!of_match_node(matches, child)) - continue; - if (rc == 0) { - pr_debug(" and sub busses\n"); - rc = of_platform_bus_create(child, matches, &dev->dev); - } - if (rc) { - of_node_put(child); - break; - } - } - return rc; -} - - -/** - * of_platform_bus_probe - Probe the device-tree for platform busses - * @root: parent of the first level to probe or NULL for the root of the tree - * @matches: match table, NULL to use the default - * @parent: parent to hook devices from, NULL for toplevel - * - * Note that children of the provided root are not instanciated as devices - * unless the specified root itself matches the bus list and is not NULL. - */ - -int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent) -{ - struct device_node *child; - struct of_device *dev; - int rc = 0; - - if (matches == NULL) - matches = of_default_bus_ids; - if (matches == OF_NO_DEEP_PROBE) - return -EINVAL; - if (root == NULL) - root = of_find_node_by_path("/"); - else - of_node_get(root); - - pr_debug("of_platform_bus_probe()\n"); - pr_debug(" starting at: %s\n", root->full_name); - - /* Do a self check of bus type, if there's a match, create - * children - */ - if (of_match_node(matches, root)) { - pr_debug(" root match, create all sub devices\n"); - dev = of_platform_device_create(root, NULL, parent); - if (dev == NULL) { - rc = -ENOMEM; - goto bail; - } - pr_debug(" create all sub busses\n"); - rc = of_platform_bus_create(root, matches, &dev->dev); - goto bail; - } - for_each_child_of_node(root, child) { - if (!of_match_node(matches, child)) - continue; - - pr_debug(" match: %s\n", child->full_name); - dev = of_platform_device_create(child, NULL, parent); - if (dev == NULL) - rc = -ENOMEM; - else - rc = of_platform_bus_create(child, matches, &dev->dev); - if (rc) { - of_node_put(child); - break; - } - } - bail: - of_node_put(root); - return rc; -} -EXPORT_SYMBOL(of_platform_bus_probe); - -static int of_dev_node_match(struct device *dev, void *data) -{ - return to_of_device(dev)->dev.of_node == data; -} - -struct of_device *of_find_device_by_node(struct device_node *np) -{ - struct device *dev; - - dev = bus_find_device(&of_platform_bus_type, - NULL, np, of_dev_node_match); - if (dev) - return to_of_device(dev); - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_node); - -static int of_dev_phandle_match(struct device *dev, void *data) -{ - phandle *ph = data; - return to_of_device(dev)->dev.of_node->phandle == *ph; -} - -struct of_device *of_find_device_by_phandle(phandle ph) -{ - struct device *dev; - - dev = bus_find_device(&of_platform_bus_type, - NULL, &ph, of_dev_phandle_match); - if (dev) - return to_of_device(dev); - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_phandle); diff --git a/arch/microblaze/kernel/prom_parse.c b/arch/microblaze/kernel/prom_parse.c index bf7e6c27e31..d33ba17601f 100644 --- a/arch/microblaze/kernel/prom_parse.c +++ b/arch/microblaze/kernel/prom_parse.c @@ -6,219 +6,11 @@ #include <linux/module.h> #include <linux/ioport.h> #include <linux/etherdevice.h> +#include <linux/of_address.h> #include <asm/prom.h> #include <asm/pci-bridge.h> -#define PRu64 "%llx" - -/* Max address size we deal with */ -#define OF_MAX_ADDR_CELLS 4 -#define OF_CHECK_COUNTS(na, ns) ((na) > 0 && (na) <= OF_MAX_ADDR_CELLS && \ - (ns) > 0) - -static struct of_bus *of_match_bus(struct device_node *np); -static int __of_address_to_resource(struct device_node *dev, - const u32 *addrp, u64 size, unsigned int flags, - struct resource *r); - -/* Debug utility */ -#ifdef DEBUG -static void of_dump_addr(const char *s, const u32 *addr, int na) -{ - printk(KERN_INFO "%s", s); - while (na--) - printk(KERN_INFO " %08x", *(addr++)); - printk(KERN_INFO "\n"); -} -#else -static void of_dump_addr(const char *s, const u32 *addr, int na) { } -#endif - -/* Callbacks for bus specific translators */ -struct of_bus { - const char *name; - const char *addresses; - int (*match)(struct device_node *parent); - void (*count_cells)(struct device_node *child, - int *addrc, int *sizec); - u64 (*map)(u32 *addr, const u32 *range, - int na, int ns, int pna); - int (*translate)(u32 *addr, u64 offset, int na); - unsigned int (*get_flags)(const u32 *addr); -}; - -/* - * Default translator (generic bus) - */ - -static void of_bus_default_count_cells(struct device_node *dev, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = of_n_addr_cells(dev); - if (sizec) - *sizec = of_n_size_cells(dev); -} - -static u64 of_bus_default_map(u32 *addr, const u32 *range, - int na, int ns, int pna) -{ - u64 cp, s, da; - - cp = of_read_number(range, na); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr, na); - - pr_debug("OF: default map, cp="PRu64", s="PRu64", da="PRu64"\n", - cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_default_translate(u32 *addr, u64 offset, int na) -{ - u64 a = of_read_number(addr, na); - memset(addr, 0, na * 4); - a += offset; - if (na > 1) - addr[na - 2] = a >> 32; - addr[na - 1] = a & 0xffffffffu; - - return 0; -} - -static unsigned int of_bus_default_get_flags(const u32 *addr) -{ - return IORESOURCE_MEM; -} - #ifdef CONFIG_PCI -/* - * PCI bus specific translator - */ - -static int of_bus_pci_match(struct device_node *np) -{ - /* "vci" is for the /chaos bridge on 1st-gen PCI powermacs */ - return !strcmp(np->type, "pci") || !strcmp(np->type, "vci"); -} - -static void of_bus_pci_count_cells(struct device_node *np, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = 3; - if (sizec) - *sizec = 2; -} - -static u64 of_bus_pci_map(u32 *addr, const u32 *range, int na, int ns, int pna) -{ - u64 cp, s, da; - - /* Check address type match */ - if ((addr[0] ^ range[0]) & 0x03000000) - return OF_BAD_ADDR; - - /* Read address values, skipping high cell */ - cp = of_read_number(range + 1, na - 1); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr + 1, na - 1); - - pr_debug("OF: PCI map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_pci_translate(u32 *addr, u64 offset, int na) -{ - return of_bus_default_translate(addr + 1, offset, na - 1); -} - -static unsigned int of_bus_pci_get_flags(const u32 *addr) -{ - unsigned int flags = 0; - u32 w = addr[0]; - - switch ((w >> 24) & 0x03) { - case 0x01: - flags |= IORESOURCE_IO; - break; - case 0x02: /* 32 bits */ - case 0x03: /* 64 bits */ - flags |= IORESOURCE_MEM; - break; - } - if (w & 0x40000000) - flags |= IORESOURCE_PREFETCH; - return flags; -} - -const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, - unsigned int *flags) -{ - const u32 *prop; - unsigned int psize; - struct device_node *parent; - struct of_bus *bus; - int onesize, i, na, ns; - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - return NULL; - bus = of_match_bus(parent); - if (strcmp(bus->name, "pci")) { - of_node_put(parent); - return NULL; - } - bus->count_cells(dev, &na, &ns); - of_node_put(parent); - if (!OF_CHECK_COUNTS(na, ns)) - return NULL; - - /* Get "reg" or "assigned-addresses" property */ - prop = of_get_property(dev, bus->addresses, &psize); - if (prop == NULL) - return NULL; - psize /= 4; - - onesize = na + ns; - for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) - if ((prop[0] & 0xff) == ((bar_no * 4) + PCI_BASE_ADDRESS_0)) { - if (size) - *size = of_read_number(prop + na, ns); - if (flags) - *flags = bus->get_flags(prop); - return prop; - } - return NULL; -} -EXPORT_SYMBOL(of_get_pci_address); - -int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r) -{ - const u32 *addrp; - u64 size; - unsigned int flags; - - addrp = of_get_pci_address(dev, bar, &size, &flags); - if (addrp == NULL) - return -EINVAL; - return __of_address_to_resource(dev, addrp, size, flags, r); -} -EXPORT_SYMBOL_GPL(of_pci_address_to_resource); - -static u8 of_irq_pci_swizzle(u8 slot, u8 pin) -{ - return (((pin - 1) + slot) % 4) + 1; -} - int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) { struct device_node *dn, *ppnode; @@ -293,331 +85,6 @@ int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) EXPORT_SYMBOL_GPL(of_irq_map_pci); #endif /* CONFIG_PCI */ -/* - * ISA bus specific translator - */ - -static int of_bus_isa_match(struct device_node *np) -{ - return !strcmp(np->name, "isa"); -} - -static void of_bus_isa_count_cells(struct device_node *child, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = 2; - if (sizec) - *sizec = 1; -} - -static u64 of_bus_isa_map(u32 *addr, const u32 *range, int na, int ns, int pna) -{ - u64 cp, s, da; - - /* Check address type match */ - if ((addr[0] ^ range[0]) & 0x00000001) - return OF_BAD_ADDR; - - /* Read address values, skipping high cell */ - cp = of_read_number(range + 1, na - 1); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr + 1, na - 1); - - pr_debug("OF: ISA map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_isa_translate(u32 *addr, u64 offset, int na) -{ - return of_bus_default_translate(addr + 1, offset, na - 1); -} - -static unsigned int of_bus_isa_get_flags(const u32 *addr) -{ - unsigned int flags = 0; - u32 w = addr[0]; - - if (w & 1) - flags |= IORESOURCE_IO; - else - flags |= IORESOURCE_MEM; - return flags; -} - -/* - * Array of bus specific translators - */ - -static struct of_bus of_busses[] = { -#ifdef CONFIG_PCI - /* PCI */ - { - .name = "pci", - .addresses = "assigned-addresses", - .match = of_bus_pci_match, - .count_cells = of_bus_pci_count_cells, - .map = of_bus_pci_map, - .translate = of_bus_pci_translate, - .get_flags = of_bus_pci_get_flags, - }, -#endif /* CONFIG_PCI */ - /* ISA */ - { - .name = "isa", - .addresses = "reg", - .match = of_bus_isa_match, - .count_cells = of_bus_isa_count_cells, - .map = of_bus_isa_map, - .translate = of_bus_isa_translate, - .get_flags = of_bus_isa_get_flags, - }, - /* Default */ - { - .name = "default", - .addresses = "reg", - .match = NULL, - .count_cells = of_bus_default_count_cells, - .map = of_bus_default_map, - .translate = of_bus_default_translate, - .get_flags = of_bus_default_get_flags, - }, -}; - -static struct of_bus *of_match_bus(struct device_node *np) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(of_busses); i++) - if (!of_busses[i].match || of_busses[i].match(np)) - return &of_busses[i]; - BUG(); - return NULL; -} - -static int of_translate_one(struct device_node *parent, struct of_bus *bus, - struct of_bus *pbus, u32 *addr, - int na, int ns, int pna) -{ - const u32 *ranges; - unsigned int rlen; - int rone; - u64 offset = OF_BAD_ADDR; - - /* Normally, an absence of a "ranges" property means we are - * crossing a non-translatable boundary, and thus the addresses - * below the current not cannot be converted to CPU physical ones. - * Unfortunately, while this is very clear in the spec, it's not - * what Apple understood, and they do have things like /uni-n or - * /ht nodes with no "ranges" property and a lot of perfectly - * useable mapped devices below them. Thus we treat the absence of - * "ranges" as equivalent to an empty "ranges" property which means - * a 1:1 translation at that level. It's up to the caller not to try - * to translate addresses that aren't supposed to be translated in - * the first place. --BenH. - */ - ranges = of_get_property(parent, "ranges", (int *) &rlen); - if (ranges == NULL || rlen == 0) { - offset = of_read_number(addr, na); - memset(addr, 0, pna * 4); - pr_debug("OF: no ranges, 1:1 translation\n"); - goto finish; - } - - pr_debug("OF: walking ranges...\n"); - - /* Now walk through the ranges */ - rlen /= 4; - rone = na + pna + ns; - for (; rlen >= rone; rlen -= rone, ranges += rone) { - offset = bus->map(addr, ranges, na, ns, pna); - if (offset != OF_BAD_ADDR) - break; - } - if (offset == OF_BAD_ADDR) { - pr_debug("OF: not found !\n"); - return 1; - } - memcpy(addr, ranges + na, 4 * pna); - - finish: - of_dump_addr("OF: parent translation for:", addr, pna); - pr_debug("OF: with offset: "PRu64"\n", offset); - - /* Translate it into parent bus space */ - return pbus->translate(addr, offset, pna); -} - -/* - * Translate an address from the device-tree into a CPU physical address, - * this walks up the tree and applies the various bus mappings on the - * way. - * - * Note: We consider that crossing any level with #size-cells == 0 to mean - * that translation is impossible (that is we are not dealing with a value - * that can be mapped to a cpu physical address). This is not really specified - * that way, but this is traditionally the way IBM at least do things - */ -u64 of_translate_address(struct device_node *dev, const u32 *in_addr) -{ - struct device_node *parent = NULL; - struct of_bus *bus, *pbus; - u32 addr[OF_MAX_ADDR_CELLS]; - int na, ns, pna, pns; - u64 result = OF_BAD_ADDR; - - pr_debug("OF: ** translation for device %s **\n", dev->full_name); - - /* Increase refcount at current level */ - of_node_get(dev); - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - goto bail; - bus = of_match_bus(parent); - - /* Cound address cells & copy address locally */ - bus->count_cells(dev, &na, &ns); - if (!OF_CHECK_COUNTS(na, ns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", - dev->full_name); - goto bail; - } - memcpy(addr, in_addr, na * 4); - - pr_debug("OF: bus is %s (na=%d, ns=%d) on %s\n", - bus->name, na, ns, parent->full_name); - of_dump_addr("OF: translating address:", addr, na); - - /* Translate */ - for (;;) { - /* Switch to parent bus */ - of_node_put(dev); - dev = parent; - parent = of_get_parent(dev); - - /* If root, we have finished */ - if (parent == NULL) { - pr_debug("OF: reached root node\n"); - result = of_read_number(addr, na); - break; - } - - /* Get new parent bus and counts */ - pbus = of_match_bus(parent); - pbus->count_cells(dev, &pna, &pns); - if (!OF_CHECK_COUNTS(pna, pns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", - dev->full_name); - break; - } - - pr_debug("OF: parent bus is %s (na=%d, ns=%d) on %s\n", - pbus->name, pna, pns, parent->full_name); - - /* Apply bus translation */ - if (of_translate_one(dev, bus, pbus, addr, na, ns, pna)) - break; - - /* Complete the move up one level */ - na = pna; - ns = pns; - bus = pbus; - - of_dump_addr("OF: one level translation:", addr, na); - } - bail: - of_node_put(parent); - of_node_put(dev); - - return result; -} -EXPORT_SYMBOL(of_translate_address); - -const u32 *of_get_address(struct device_node *dev, int index, u64 *size, - unsigned int *flags) -{ - const u32 *prop; - unsigned int psize; - struct device_node *parent; - struct of_bus *bus; - int onesize, i, na, ns; - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - return NULL; - bus = of_match_bus(parent); - bus->count_cells(dev, &na, &ns); - of_node_put(parent); - if (!OF_CHECK_COUNTS(na, ns)) - return NULL; - - /* Get "reg" or "assigned-addresses" property */ - prop = of_get_property(dev, bus->addresses, (int *) &psize); - if (prop == NULL) - return NULL; - psize /= 4; - - onesize = na + ns; - for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) - if (i == index) { - if (size) - *size = of_read_number(prop + na, ns); - if (flags) - *flags = bus->get_flags(prop); - return prop; - } - return NULL; -} -EXPORT_SYMBOL(of_get_address); - -static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, - u64 size, unsigned int flags, - struct resource *r) -{ - u64 taddr; - - if ((flags & (IORESOURCE_IO | IORESOURCE_MEM)) == 0) - return -EINVAL; - taddr = of_translate_address(dev, addrp); - if (taddr == OF_BAD_ADDR) - return -EINVAL; - memset(r, 0, sizeof(struct resource)); - if (flags & IORESOURCE_IO) { - unsigned long port; - port = -1; /* pci_address_to_pio(taddr); */ - if (port == (unsigned long)-1) - return -EINVAL; - r->start = port; - r->end = port + size - 1; - } else { - r->start = taddr; - r->end = taddr + size - 1; - } - r->flags = flags; - r->name = dev->name; - return 0; -} - -int of_address_to_resource(struct device_node *dev, int index, - struct resource *r) -{ - const u32 *addrp; - u64 size; - unsigned int flags; - - addrp = of_get_address(dev, index, &size, &flags); - if (addrp == NULL) - return -EINVAL; - return __of_address_to_resource(dev, addrp, size, flags, r); -} -EXPORT_SYMBOL_GPL(of_address_to_resource); - void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, unsigned long *busno, unsigned long *phys, unsigned long *size) { @@ -644,308 +111,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, *size = of_read_number(dma_window, cells); } -/* - * Interrupt remapper - */ - -static unsigned int of_irq_workarounds; -static struct device_node *of_irq_dflt_pic; - -static struct device_node *of_irq_find_parent(struct device_node *child) -{ - struct device_node *p; - const phandle *parp; - - if (!of_node_get(child)) - return NULL; - - do { - parp = of_get_property(child, "interrupt-parent", NULL); - if (parp == NULL) - p = of_get_parent(child); - else { - if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) - p = of_node_get(of_irq_dflt_pic); - else - p = of_find_node_by_phandle(*parp); - } - of_node_put(child); - child = p; - } while (p && of_get_property(p, "#interrupt-cells", NULL) == NULL); - - return p; -} - -/* This doesn't need to be called if you don't have any special workaround - * flags to pass - */ -void of_irq_map_init(unsigned int flags) -{ - of_irq_workarounds = flags; - - /* OldWorld, don't bother looking at other things */ - if (flags & OF_IMAP_OLDWORLD_MAC) - return; - - /* If we don't have phandles, let's try to locate a default interrupt - * controller (happens when booting with BootX). We do a first match - * here, hopefully, that only ever happens on machines with one - * controller. - */ - if (flags & OF_IMAP_NO_PHANDLE) { - struct device_node *np; - - for (np = NULL; (np = of_find_all_nodes(np)) != NULL;) { - if (of_get_property(np, "interrupt-controller", NULL) - == NULL) - continue; - /* Skip /chosen/interrupt-controller */ - if (strcmp(np->name, "chosen") == 0) - continue; - /* It seems like at least one person on this planet - * wants to use BootX on a machine with an AppleKiwi - * controller which happens to pretend to be an - * interrupt controller too. - */ - if (strcmp(np->name, "AppleKiwi") == 0) - continue; - /* I think we found one ! */ - of_irq_dflt_pic = np; - break; - } - } - -} - -int of_irq_map_raw(struct device_node *parent, const u32 *intspec, u32 ointsize, - const u32 *addr, struct of_irq *out_irq) -{ - struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL; - const u32 *tmp, *imap, *imask; - u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0; - int imaplen, match, i; - - pr_debug("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...]," - "ointsize=%d\n", - parent->full_name, intspec[0], intspec[1], ointsize); - - ipar = of_node_get(parent); - - /* First get the #interrupt-cells property of the current cursor - * that tells us how to interpret the passed-in intspec. If there - * is none, we are nice and just walk up the tree - */ - do { - tmp = of_get_property(ipar, "#interrupt-cells", NULL); - if (tmp != NULL) { - intsize = *tmp; - break; - } - tnode = ipar; - ipar = of_irq_find_parent(ipar); - of_node_put(tnode); - } while (ipar); - if (ipar == NULL) { - pr_debug(" -> no parent found !\n"); - goto fail; - } - - pr_debug("of_irq_map_raw: ipar=%s, size=%d\n", - ipar->full_name, intsize); - - if (ointsize != intsize) - return -EINVAL; - - /* Look for this #address-cells. We have to implement the old linux - * trick of looking for the parent here as some device-trees rely on it - */ - old = of_node_get(ipar); - do { - tmp = of_get_property(old, "#address-cells", NULL); - tnode = of_get_parent(old); - of_node_put(old); - old = tnode; - } while (old && tmp == NULL); - of_node_put(old); - old = NULL; - addrsize = (tmp == NULL) ? 2 : *tmp; - - pr_debug(" -> addrsize=%d\n", addrsize); - - /* Now start the actual "proper" walk of the interrupt tree */ - while (ipar != NULL) { - /* Now check if cursor is an interrupt-controller and if it is - * then we are done - */ - if (of_get_property(ipar, "interrupt-controller", NULL) != - NULL) { - pr_debug(" -> got it !\n"); - memcpy(out_irq->specifier, intspec, - intsize * sizeof(u32)); - out_irq->size = intsize; - out_irq->controller = ipar; - of_node_put(old); - return 0; - } - - /* Now look for an interrupt-map */ - imap = of_get_property(ipar, "interrupt-map", &imaplen); - /* No interrupt map, check for an interrupt parent */ - if (imap == NULL) { - pr_debug(" -> no map, getting parent\n"); - newpar = of_irq_find_parent(ipar); - goto skiplevel; - } - imaplen /= sizeof(u32); - - /* Look for a mask */ - imask = of_get_property(ipar, "interrupt-map-mask", NULL); - - /* If we were passed no "reg" property and we attempt to parse - * an interrupt-map, then #address-cells must be 0. - * Fail if it's not. - */ - if (addr == NULL && addrsize != 0) { - pr_debug(" -> no reg passed in when needed !\n"); - goto fail; - } - - /* Parse interrupt-map */ - match = 0; - while (imaplen > (addrsize + intsize + 1) && !match) { - /* Compare specifiers */ - match = 1; - for (i = 0; i < addrsize && match; ++i) { - u32 mask = imask ? imask[i] : 0xffffffffu; - match = ((addr[i] ^ imap[i]) & mask) == 0; - } - for (; i < (addrsize + intsize) && match; ++i) { - u32 mask = imask ? imask[i] : 0xffffffffu; - match = - ((intspec[i-addrsize] ^ imap[i]) - & mask) == 0; - } - imap += addrsize + intsize; - imaplen -= addrsize + intsize; - - pr_debug(" -> match=%d (imaplen=%d)\n", match, imaplen); - - /* Get the interrupt parent */ - if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) - newpar = of_node_get(of_irq_dflt_pic); - else - newpar = - of_find_node_by_phandle((phandle)*imap); - imap++; - --imaplen; - - /* Check if not found */ - if (newpar == NULL) { - pr_debug(" -> imap parent not found !\n"); - goto fail; - } - - /* Get #interrupt-cells and #address-cells of new - * parent - */ - tmp = of_get_property(newpar, "#interrupt-cells", NULL); - if (tmp == NULL) { - pr_debug(" -> parent lacks " - "#interrupt-cells!\n"); - goto fail; - } - newintsize = *tmp; - tmp = of_get_property(newpar, "#address-cells", NULL); - newaddrsize = (tmp == NULL) ? 0 : *tmp; - - pr_debug(" -> newintsize=%d, newaddrsize=%d\n", - newintsize, newaddrsize); - - /* Check for malformed properties */ - if (imaplen < (newaddrsize + newintsize)) - goto fail; - - imap += newaddrsize + newintsize; - imaplen -= newaddrsize + newintsize; - - pr_debug(" -> imaplen=%d\n", imaplen); - } - if (!match) - goto fail; - - of_node_put(old); - old = of_node_get(newpar); - addrsize = newaddrsize; - intsize = newintsize; - intspec = imap - intsize; - addr = intspec - addrsize; - -skiplevel: - /* Iterate again with new parent */ - pr_debug(" -> new parent: %s\n", - newpar ? newpar->full_name : "<>"); - of_node_put(ipar); - ipar = newpar; - newpar = NULL; - } -fail: - of_node_put(ipar); - of_node_put(old); - of_node_put(newpar); - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(of_irq_map_raw); - -int of_irq_map_one(struct device_node *device, - int index, struct of_irq *out_irq) -{ - struct device_node *p; - const u32 *intspec, *tmp, *addr; - u32 intsize, intlen; - int res; - - pr_debug("of_irq_map_one: dev=%s, index=%d\n", - device->full_name, index); - - /* Get the interrupts property */ - intspec = of_get_property(device, "interrupts", (int *) &intlen); - if (intspec == NULL) - return -EINVAL; - intlen /= sizeof(u32); - - pr_debug(" intspec=%d intlen=%d\n", *intspec, intlen); - - /* Get the reg property (if any) */ - addr = of_get_property(device, "reg", NULL); - - /* Look for the interrupt parent. */ - p = of_irq_find_parent(device); - if (p == NULL) - return -EINVAL; - - /* Get size of interrupt specifier */ - tmp = of_get_property(p, "#interrupt-cells", NULL); - if (tmp == NULL) { - of_node_put(p); - return -EINVAL; - } - intsize = *tmp; - - pr_debug(" intsize=%d intlen=%d\n", intsize, intlen); - - /* Check index */ - if ((index + 1) * intsize > intlen) - return -EINVAL; - - /* Get new specifier and map it */ - res = of_irq_map_raw(p, intspec + index * intsize, intsize, - addr, out_irq); - of_node_put(p); - return res; -} -EXPORT_SYMBOL_GPL(of_irq_map_one); - /** * Search the device tree for the best MAC address to use. 'mac-address' is * checked first, because that is supposed to contain to "most recent" MAC @@ -983,43 +148,3 @@ const void *of_get_mac_address(struct device_node *np) return NULL; } EXPORT_SYMBOL(of_get_mac_address); - -int of_irq_to_resource(struct device_node *dev, int index, struct resource *r) -{ - struct of_irq out_irq; - int irq; - int res; - - res = of_irq_map_one(dev, index, &out_irq); - - /* Get irq for the device */ - if (res) { - pr_debug("IRQ not found... code = %d", res); - return NO_IRQ; - } - /* Assuming single interrupt controller... */ - irq = out_irq.specifier[0]; - - pr_debug("IRQ found = %d", irq); - - /* Only dereference the resource if both the - * resource and the irq are valid. */ - if (r && irq != NO_IRQ) { - r->start = r->end = irq; - r->flags = IORESOURCE_IRQ; - } - - return irq; -} -EXPORT_SYMBOL_GPL(of_irq_to_resource); - -void __iomem *of_iomap(struct device_node *np, int index) -{ - struct resource res; - - if (of_address_to_resource(np, index, &res)) - return NULL; - - return ioremap(res.start, 1 + res.end - res.start); -} -EXPORT_SYMBOL(of_iomap); diff --git a/arch/microblaze/kernel/reset.c b/arch/microblaze/kernel/reset.c index a1721a33042..bd8ccab5cef 100644 --- a/arch/microblaze/kernel/reset.c +++ b/arch/microblaze/kernel/reset.c @@ -24,8 +24,8 @@ static int of_reset_gpio_handle(void) int ret; /* variable which stored handle reset gpio pin */ struct device_node *root; /* root node */ struct device_node *gpio; /* gpio node */ - struct of_gpio_chip *of_gc = NULL; - enum of_gpio_flags flags ; + struct gpio_chip *gc; + u32 flags; const void *gpio_spec; /* find out root node */ @@ -39,19 +39,19 @@ static int of_reset_gpio_handle(void) goto err0; } - of_gc = gpio->data; - if (!of_gc) { + gc = of_node_to_gpiochip(gpio); + if (!gc) { pr_debug("%s: gpio controller %s isn't registered\n", root->full_name, gpio->full_name); ret = -ENODEV; goto err1; } - ret = of_gc->xlate(of_gc, root, gpio_spec, &flags); + ret = gc->of_xlate(gc, root, gpio_spec, &flags); if (ret < 0) goto err1; - ret += of_gc->gc.base; + ret += gc->base; err1: of_node_put(gpio); err0: diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c index 17c98dbcec8..f5f76884235 100644 --- a/arch/microblaze/kernel/setup.c +++ b/arch/microblaze/kernel/setup.c @@ -213,15 +213,9 @@ static struct notifier_block dflt_plat_bus_notifier = { .priority = INT_MAX, }; -static struct notifier_block dflt_of_bus_notifier = { - .notifier_call = dflt_bus_notify, - .priority = INT_MAX, -}; - static int __init setup_bus_notifier(void) { bus_register_notifier(&platform_bus_type, &dflt_plat_bus_notifier); - bus_register_notifier(&of_platform_bus_type, &dflt_of_bus_notifier); return 0; } diff --git a/arch/mips/Makefile b/arch/mips/Makefile index f0d196090e9..f4a4b663ebb 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -93,7 +93,8 @@ all-$(CONFIG_SYS_SUPPORTS_ZBOOT)+= vmlinuz cflags-y += -G 0 -mno-abicalls -fno-pic -pipe cflags-y += -msoft-float LDFLAGS_vmlinux += -G 0 -static -n -nostdlib -MODFLAGS += -mlong-calls +KBUILD_AFLAGS_MODULE += -mlong-calls +KBUILD_CFLAGS_MODULE += -mlong-calls cflags-y += -ffreestanding @@ -165,7 +166,8 @@ cflags-$(CONFIG_CPU_DADDI_WORKAROUNDS) += $(call cc-option,-mno-daddi,) ifdef CONFIG_CPU_SB1 ifdef CONFIG_SB1_PASS_1_WORKAROUNDS -MODFLAGS += -msb1-pass1-workarounds +KBUILD_AFLAGS_MODULE += -msb1-pass1-workarounds +KBUILD_CFLAGS_MODULE += -msb1-pass1-workarounds endif endif diff --git a/arch/mips/include/asm/kgdb.h b/arch/mips/include/asm/kgdb.h index 19002d605ac..e6c0b0e14cc 100644 --- a/arch/mips/include/asm/kgdb.h +++ b/arch/mips/include/asm/kgdb.h @@ -8,28 +8,27 @@ #if (_MIPS_ISA == _MIPS_ISA_MIPS1) || (_MIPS_ISA == _MIPS_ISA_MIPS2) || \ (_MIPS_ISA == _MIPS_ISA_MIPS32) -#define KGDB_GDB_REG_SIZE 32 +#define KGDB_GDB_REG_SIZE 32 +#define GDB_SIZEOF_REG sizeof(u32) #elif (_MIPS_ISA == _MIPS_ISA_MIPS3) || (_MIPS_ISA == _MIPS_ISA_MIPS4) || \ (_MIPS_ISA == _MIPS_ISA_MIPS64) #ifdef CONFIG_32BIT -#define KGDB_GDB_REG_SIZE 32 +#define KGDB_GDB_REG_SIZE 32 +#define GDB_SIZEOF_REG sizeof(u32) #else /* CONFIG_CPU_32BIT */ -#define KGDB_GDB_REG_SIZE 64 +#define KGDB_GDB_REG_SIZE 64 +#define GDB_SIZEOF_REG sizeof(u64) #endif #else #error "Need to set KGDB_GDB_REG_SIZE for MIPS ISA" #endif /* _MIPS_ISA */ #define BUFMAX 2048 -#if (KGDB_GDB_REG_SIZE == 32) -#define NUMREGBYTES (90*sizeof(u32)) -#define NUMCRITREGBYTES (12*sizeof(u32)) -#else -#define NUMREGBYTES (90*sizeof(u64)) -#define NUMCRITREGBYTES (12*sizeof(u64)) -#endif +#define DBG_MAX_REG_NUM 72 +#define NUMREGBYTES (DBG_MAX_REG_NUM * sizeof(GDB_SIZEOF_REG)) +#define NUMCRITREGBYTES (12 * sizeof(GDB_SIZEOF_REG)) #define BREAK_INSTR_SIZE 4 #define CACHE_FLUSH_IS_SAFE 0 diff --git a/arch/mips/include/asm/local64.h b/arch/mips/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/mips/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c index 9b78ff6e9b8..1f4e2fa6414 100644 --- a/arch/mips/kernel/kgdb.c +++ b/arch/mips/kernel/kgdb.c @@ -50,6 +50,151 @@ static struct hard_trap_info { { 0, 0} /* Must be last */ }; +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = +{ + { "zero", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[0]) }, + { "at", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[1]) }, + { "v0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[2]) }, + { "v1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[3]) }, + { "a0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[4]) }, + { "a1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[5]) }, + { "a2", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[6]) }, + { "a3", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[7]) }, + { "t0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[8]) }, + { "t1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[9]) }, + { "t2", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[10]) }, + { "t3", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[11]) }, + { "t4", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[12]) }, + { "t5", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[13]) }, + { "t6", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[14]) }, + { "t7", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[15]) }, + { "s0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[16]) }, + { "s1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[17]) }, + { "s2", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[18]) }, + { "s3", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[19]) }, + { "s4", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[20]) }, + { "s5", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[21]) }, + { "s6", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[22]) }, + { "s7", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[23]) }, + { "t8", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[24]) }, + { "t9", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[25]) }, + { "k0", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[26]) }, + { "k1", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[27]) }, + { "gp", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[28]) }, + { "sp", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[29]) }, + { "s8", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[30]) }, + { "ra", GDB_SIZEOF_REG, offsetof(struct pt_regs, regs[31]) }, + { "sr", GDB_SIZEOF_REG, offsetof(struct pt_regs, cp0_status) }, + { "lo", GDB_SIZEOF_REG, offsetof(struct pt_regs, lo) }, + { "hi", GDB_SIZEOF_REG, offsetof(struct pt_regs, hi) }, + { "bad", GDB_SIZEOF_REG, offsetof(struct pt_regs, cp0_badvaddr) }, + { "cause", GDB_SIZEOF_REG, offsetof(struct pt_regs, cp0_cause) }, + { "pc", GDB_SIZEOF_REG, offsetof(struct pt_regs, cp0_epc) }, + { "f0", GDB_SIZEOF_REG, 0 }, + { "f1", GDB_SIZEOF_REG, 1 }, + { "f2", GDB_SIZEOF_REG, 2 }, + { "f3", GDB_SIZEOF_REG, 3 }, + { "f4", GDB_SIZEOF_REG, 4 }, + { "f5", GDB_SIZEOF_REG, 5 }, + { "f6", GDB_SIZEOF_REG, 6 }, + { "f7", GDB_SIZEOF_REG, 7 }, + { "f8", GDB_SIZEOF_REG, 8 }, + { "f9", GDB_SIZEOF_REG, 9 }, + { "f10", GDB_SIZEOF_REG, 10 }, + { "f11", GDB_SIZEOF_REG, 11 }, + { "f12", GDB_SIZEOF_REG, 12 }, + { "f13", GDB_SIZEOF_REG, 13 }, + { "f14", GDB_SIZEOF_REG, 14 }, + { "f15", GDB_SIZEOF_REG, 15 }, + { "f16", GDB_SIZEOF_REG, 16 }, + { "f17", GDB_SIZEOF_REG, 17 }, + { "f18", GDB_SIZEOF_REG, 18 }, + { "f19", GDB_SIZEOF_REG, 19 }, + { "f20", GDB_SIZEOF_REG, 20 }, + { "f21", GDB_SIZEOF_REG, 21 }, + { "f22", GDB_SIZEOF_REG, 22 }, + { "f23", GDB_SIZEOF_REG, 23 }, + { "f24", GDB_SIZEOF_REG, 24 }, + { "f25", GDB_SIZEOF_REG, 25 }, + { "f26", GDB_SIZEOF_REG, 26 }, + { "f27", GDB_SIZEOF_REG, 27 }, + { "f28", GDB_SIZEOF_REG, 28 }, + { "f29", GDB_SIZEOF_REG, 29 }, + { "f30", GDB_SIZEOF_REG, 30 }, + { "f31", GDB_SIZEOF_REG, 31 }, + { "fsr", GDB_SIZEOF_REG, 0 }, + { "fir", GDB_SIZEOF_REG, 0 }, +}; + +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) +{ + int fp_reg; + + if (regno < 0 || regno >= DBG_MAX_REG_NUM) + return -EINVAL; + + if (dbg_reg_def[regno].offset != -1 && regno < 38) { + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + } else if (current && dbg_reg_def[regno].offset != -1 && regno < 72) { + /* FP registers 38 -> 69 */ + if (!(regs->cp0_status & ST0_CU1)) + return 0; + if (regno == 70) { + /* Process the fcr31/fsr (register 70) */ + memcpy((void *)¤t->thread.fpu.fcr31, mem, + dbg_reg_def[regno].size); + goto out_save; + } else if (regno == 71) { + /* Ignore the fir (register 71) */ + goto out_save; + } + fp_reg = dbg_reg_def[regno].offset; + memcpy((void *)¤t->thread.fpu.fpr[fp_reg], mem, + dbg_reg_def[regno].size); +out_save: + restore_fp(current); + } + + return 0; +} + +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + int fp_reg; + + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1 && regno < 38) { + /* First 38 registers */ + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + } else if (current && dbg_reg_def[regno].offset != -1 && regno < 72) { + /* FP registers 38 -> 69 */ + if (!(regs->cp0_status & ST0_CU1)) + goto out; + save_fp(current); + if (regno == 70) { + /* Process the fcr31/fsr (register 70) */ + memcpy(mem, (void *)¤t->thread.fpu.fcr31, + dbg_reg_def[regno].size); + goto out; + } else if (regno == 71) { + /* Ignore the fir (register 71) */ + memset(mem, 0, dbg_reg_def[regno].size); + goto out; + } + fp_reg = dbg_reg_def[regno].offset; + memcpy(mem, (void *)¤t->thread.fpu.fpr[fp_reg], + dbg_reg_def[regno].size); + } + +out: + return dbg_reg_def[regno].name; + +} + void arch_kgdb_breakpoint(void) { __asm__ __volatile__( @@ -84,64 +229,6 @@ static int compute_signal(int tt) return SIGHUP; /* default for things we don't know about */ } -void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) -{ - int reg; - -#if (KGDB_GDB_REG_SIZE == 32) - u32 *ptr = (u32 *)gdb_regs; -#else - u64 *ptr = (u64 *)gdb_regs; -#endif - - for (reg = 0; reg < 32; reg++) - *(ptr++) = regs->regs[reg]; - - *(ptr++) = regs->cp0_status; - *(ptr++) = regs->lo; - *(ptr++) = regs->hi; - *(ptr++) = regs->cp0_badvaddr; - *(ptr++) = regs->cp0_cause; - *(ptr++) = regs->cp0_epc; - - /* FP REGS */ - if (!(current && (regs->cp0_status & ST0_CU1))) - return; - - save_fp(current); - for (reg = 0; reg < 32; reg++) - *(ptr++) = current->thread.fpu.fpr[reg]; -} - -void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) -{ - int reg; - -#if (KGDB_GDB_REG_SIZE == 32) - const u32 *ptr = (u32 *)gdb_regs; -#else - const u64 *ptr = (u64 *)gdb_regs; -#endif - - for (reg = 0; reg < 32; reg++) - regs->regs[reg] = *(ptr++); - - regs->cp0_status = *(ptr++); - regs->lo = *(ptr++); - regs->hi = *(ptr++); - regs->cp0_badvaddr = *(ptr++); - regs->cp0_cause = *(ptr++); - regs->cp0_epc = *(ptr++); - - /* FP REGS from current */ - if (!(current && (regs->cp0_status & ST0_CU1))) - return; - - for (reg = 0; reg < 32; reg++) - current->thread.fpu.fpr[reg] = *(ptr++); - restore_fp(current); -} - /* * Similar to regs_to_gdb_regs() except that process is sleeping and so * we may not be able to get all the info. @@ -242,7 +329,7 @@ static struct notifier_block kgdb_notifier = { }; /* - * Handle the 's' and 'c' commands + * Handle the 'c' command */ int kgdb_arch_handle_exception(int vector, int signo, int err_code, char *remcom_in_buffer, char *remcom_out_buffer, @@ -250,20 +337,14 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code, { char *ptr; unsigned long address; - int cpu = smp_processor_id(); switch (remcom_in_buffer[0]) { - case 's': case 'c': /* handle the optional parameter */ ptr = &remcom_in_buffer[1]; if (kgdb_hex2long(&ptr, &address)) regs->cp0_epc = address; - atomic_set(&kgdb_cpu_doing_single_step, -1); - if (remcom_in_buffer[0] == 's') - atomic_set(&kgdb_cpu_doing_single_step, cpu); - return 0; } diff --git a/arch/mn10300/include/asm/local64.h b/arch/mn10300/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/mn10300/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/parisc/include/asm/local64.h b/arch/parisc/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/parisc/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 9877372ffdb..5beb97bafbb 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -82,7 +82,7 @@ unsigned long ftrace_return_to_handler(unsigned long retval0, unsigned long ret; pop_return_trace(&trace, &ret); - trace.rettime = cpu_clock(raw_smp_processor_id()); + trace.rettime = local_clock(); ftrace_graph_return(&trace); if (unlikely(!ret)) { @@ -126,7 +126,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - calltime = cpu_clock(raw_smp_processor_id()); + calltime = local_clock(); if (push_return_trace(old, calltime, self_addr, &trace.depth) == -EBUSY) { diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e4545f85ee9..e2bf40a2ce5 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -120,6 +120,8 @@ config ARCH_NO_VIRT_TO_BUS config PPC bool default y + select OF + select OF_FLATTREE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER @@ -173,10 +175,6 @@ config ARCH_MAY_HAVE_PC_FDC config PPC_OF def_bool y -config OF - def_bool y - select OF_FLATTREE - config PPC_UDBG_16550 bool default n @@ -199,10 +197,6 @@ config SYS_SUPPORTS_APM_EMULATION default y if PMAC_APM_EMU bool -config DTC - bool - default y - config DEFAULT_UIMAGE bool help @@ -579,14 +573,6 @@ config SCHED_SMT when dealing with POWER5 cpus at a cost of slightly increased overhead in some places. If unsure say N here. -config PROC_DEVICETREE - bool "Support for device tree in /proc" - depends on PROC_FS - help - This option adds a device-tree directory under /proc which contains - an image of the device tree that the kernel copies from Open - Firmware or other boot firmware. If unsure, say Y here. - config CMDLINE_BOOL bool "Default bootloader kernel arguments" diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 77cfe7a29e2..5d42f5eae70 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -94,7 +94,7 @@ else endif endif -LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o +KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o ifeq ($(CONFIG_TUNE_CELL),y) KBUILD_CFLAGS += $(call cc-option,-mtune=cell) diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 5e2e2cfcc81..3a40a992e59 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -197,6 +197,7 @@ extern const char *powerpc_base_platform; #define CPU_FTR_SAO LONG_ASM_CONST(0x0020000000000000) #define CPU_FTR_CP_USE_DCBTZ LONG_ASM_CONST(0x0040000000000000) #define CPU_FTR_UNALIGNED_LD_STD LONG_ASM_CONST(0x0080000000000000) +#define CPU_FTR_ASYM_SMT LONG_ASM_CONST(0x0100000000000000) #ifndef __ASSEMBLY__ @@ -412,7 +413,7 @@ extern const char *powerpc_base_platform; CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | CPU_FTR_SAO) + CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT) #define CPU_FTRS_CELL (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index ecba37a9174..67ab5fb7d15 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -300,34 +300,6 @@ extern unsigned int irq_alloc_virt(struct irq_host *host, */ extern void irq_free_virt(unsigned int virq, unsigned int count); - -/* -- OF helpers -- */ - -/** - * irq_create_of_mapping - Map a hardware interrupt into linux virq space - * @controller: Device node of the interrupt controller - * @inspec: Interrupt specifier from the device-tree - * @intsize: Size of the interrupt specifier from the device-tree - * - * This function is identical to irq_create_mapping except that it takes - * as input informations straight from the device-tree (typically the results - * of the of_irq_map_*() functions. - */ -extern unsigned int irq_create_of_mapping(struct device_node *controller, - const u32 *intspec, unsigned int intsize); - -/** - * irq_of_parse_and_map - Parse and Map an interrupt into linux virq space - * @device: Device node of the device whose interrupt is to be mapped - * @index: Index of the interrupt to map - * - * This function is a wrapper that chains of_irq_map_one() and - * irq_create_of_mapping() to make things easier to callers - */ -extern unsigned int irq_of_parse_and_map(struct device_node *dev, int index); - -/* -- End OF helpers -- */ - /** * irq_early_init - Init irq remapping subsystem */ diff --git a/arch/powerpc/include/asm/local64.h b/arch/powerpc/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/powerpc/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h index 675e159b5ef..7ab82c825a0 100644 --- a/arch/powerpc/include/asm/macio.h +++ b/arch/powerpc/include/asm/macio.h @@ -38,7 +38,7 @@ struct macio_dev { struct macio_bus *bus; /* macio bus this device is on */ struct macio_dev *media_bay; /* Device is part of a media bay */ - struct of_device ofdev; + struct platform_device ofdev; struct device_dma_parameters dma_parms; /* ide needs that */ int n_resources; struct resource resource[MACIO_DEV_COUNT_RESOURCES]; diff --git a/arch/powerpc/include/asm/of_device.h b/arch/powerpc/include/asm/of_device.h deleted file mode 100644 index 444e97e2982..00000000000 --- a/arch/powerpc/include/asm/of_device.h +++ /dev/null @@ -1,27 +0,0 @@ -#ifndef _ASM_POWERPC_OF_DEVICE_H -#define _ASM_POWERPC_OF_DEVICE_H -#ifdef __KERNEL__ - -#include <linux/device.h> -#include <linux/of.h> - -/* - * The of_device is a kind of "base class" that is a superset of - * struct device for use by devices attached to an OF node and - * probed using OF properties. - */ -struct of_device -{ - struct device dev; /* Generic device interface */ - struct pdev_archdata archdata; -}; - -extern struct of_device *of_device_alloc(struct device_node *np, - const char *bus_id, - struct device *parent); - -extern int of_device_uevent(struct device *dev, - struct kobj_uevent_env *env); - -#endif /* __KERNEL__ */ -#endif /* _ASM_POWERPC_OF_DEVICE_H */ diff --git a/arch/powerpc/include/asm/of_platform.h b/arch/powerpc/include/asm/of_platform.h deleted file mode 100644 index d4aaa348944..00000000000 --- a/arch/powerpc/include/asm/of_platform.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef _ASM_POWERPC_OF_PLATFORM_H -#define _ASM_POWERPC_OF_PLATFORM_H -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -/* Platform devices and busses creation */ -extern struct of_device *of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent); -/* pseudo "matches" value to not do deep probe */ -#define OF_NO_DEEP_PROBE ((struct of_device_id *)-1) - -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); - -extern struct of_device *of_find_device_by_phandle(phandle ph); - -extern void of_instantiate_rtc(void); - -#endif /* _ASM_POWERPC_OF_PLATFORM_H */ diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 76e1f313a58..51e9e6f90d1 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -303,13 +303,8 @@ extern void pcibios_free_controller(struct pci_controller *phb); extern void pcibios_setup_phb_resources(struct pci_controller *hose); #ifdef CONFIG_PCI -extern unsigned long pci_address_to_pio(phys_addr_t address); extern int pcibios_vaddr_is_ioport(void __iomem *address); #else -static inline unsigned long pci_address_to_pio(phys_addr_t address) -{ - return (unsigned long)-1; -} static inline int pcibios_vaddr_is_ioport(void __iomem *address) { return 0; diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index e6d4ce69b12..5c16b891d50 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -21,3 +21,15 @@ #ifdef CONFIG_FSL_EMB_PERF_EVENT #include <asm/perf_event_fsl_emb.h> #endif + +#ifdef CONFIG_PERF_EVENTS +#include <asm/ptrace.h> +#include <asm/reg.h> + +#define perf_arch_fetch_caller_regs(regs, __ip) \ + do { \ + (regs)->nip = __ip; \ + (regs)->gpr[1] = *(unsigned long *)__get_SP(); \ + asm volatile("mfmsr %0" : "=r" ((regs)->msr)); \ + } while (0) +#endif diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index ddd408a93b5..ae26f2efd08 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -17,9 +17,6 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/types.h> -#include <linux/of_fdt.h> -#include <linux/proc_fs.h> -#include <linux/platform_device.h> #include <asm/irq.h> #include <asm/atomic.h> @@ -43,49 +40,14 @@ extern void pci_create_OF_bus_map(void); * OF address retreival & translation */ -/* Translate an OF address block into a CPU physical address - */ -extern u64 of_translate_address(struct device_node *np, const u32 *addr); - /* Translate a DMA address from device space to CPU space */ extern u64 of_translate_dma_address(struct device_node *dev, const u32 *in_addr); -/* Extract an address from a device, returns the region size and - * the address space flags too. The PCI version uses a BAR number - * instead of an absolute index - */ -extern const u32 *of_get_address(struct device_node *dev, int index, - u64 *size, unsigned int *flags); #ifdef CONFIG_PCI -extern const u32 *of_get_pci_address(struct device_node *dev, int bar_no, - u64 *size, unsigned int *flags); -#else -static inline const u32 *of_get_pci_address(struct device_node *dev, - int bar_no, u64 *size, unsigned int *flags) -{ - return NULL; -} -#endif /* CONFIG_PCI */ - -/* Get an address as a resource. Note that if your address is - * a PIO address, the conversion will fail if the physical address - * can't be internally converted to an IO token with - * pci_address_to_pio(), that is because it's either called to early - * or it can't be matched to any host bridge IO space - */ -extern int of_address_to_resource(struct device_node *dev, int index, - struct resource *r); -#ifdef CONFIG_PCI -extern int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r); -#else -static inline int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r) -{ - return -ENOSYS; -} -#endif /* CONFIG_PCI */ +extern unsigned long pci_address_to_pio(phys_addr_t address); +#define pci_address_to_pio pci_address_to_pio +#endif /* CONFIG_PCI */ /* Parse the ibm,dma-window property of an OF node into the busno, phys and * size parameters. @@ -104,69 +66,12 @@ struct device_node *of_find_next_cache_node(struct device_node *np); /* Get the MAC address */ extern const void *of_get_mac_address(struct device_node *np); -/* - * OF interrupt mapping - */ - -/* This structure is returned when an interrupt is mapped. The controller - * field needs to be put() after use - */ - -#define OF_MAX_IRQ_SPEC 4 /* We handle specifiers of at most 4 cells */ - -struct of_irq { - struct device_node *controller; /* Interrupt controller node */ - u32 size; /* Specifier size */ - u32 specifier[OF_MAX_IRQ_SPEC]; /* Specifier copy */ -}; - -/** - * of_irq_map_init - Initialize the irq remapper - * @flags: flags defining workarounds to enable - * - * Some machines have bugs in the device-tree which require certain workarounds - * to be applied. Call this before any interrupt mapping attempts to enable - * those workarounds. - */ -#define OF_IMAP_OLDWORLD_MAC 0x00000001 -#define OF_IMAP_NO_PHANDLE 0x00000002 - -extern void of_irq_map_init(unsigned int flags); - -/** - * of_irq_map_raw - Low level interrupt tree parsing - * @parent: the device interrupt parent - * @intspec: interrupt specifier ("interrupts" property of the device) - * @ointsize: size of the passed in interrupt specifier - * @addr: address specifier (start of "reg" property of the device) - * @out_irq: structure of_irq filled by this function - * - * Returns 0 on success and a negative number on error - * - * This function is a low-level interrupt tree walking function. It - * can be used to do a partial walk with synthetized reg and interrupts - * properties, for example when resolving PCI interrupts when no device - * node exist for the parent. - * - */ - -extern int of_irq_map_raw(struct device_node *parent, const u32 *intspec, - u32 ointsize, const u32 *addr, - struct of_irq *out_irq); - - -/** - * of_irq_map_one - Resolve an interrupt for a device - * @device: the device whose interrupt is to be resolved - * @index: index of the interrupt to resolve - * @out_irq: structure of_irq filled by this function - * - * This function resolves an interrupt, walking the tree, for a given - * device-tree node. It's the high level pendant to of_irq_map_raw(). - * It also implements the workarounds for OldWolrd Macs. - */ -extern int of_irq_map_one(struct device_node *device, int index, - struct of_irq *out_irq); +#ifdef CONFIG_NUMA +extern int of_node_to_nid(struct device_node *device); +#else +static inline int of_node_to_nid(struct device_node *device) { return 0; } +#endif +#define of_node_to_nid of_node_to_nid /** * of_irq_map_pci - Resolve the interrupt for a PCI device @@ -180,19 +85,19 @@ extern int of_irq_map_one(struct device_node *device, int index, * resolving using the OF tree walking. */ struct pci_dev; +struct of_irq; extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq); -extern int of_irq_to_resource(struct device_node *dev, int index, - struct resource *r); +extern void of_instantiate_rtc(void); -/** - * of_iomap - Maps the memory mapped IO for a given device_node - * @device: the device whose io range will be mapped - * @index: index of the io range - * - * Returns a pointer to the mapped memory - */ -extern void __iomem *of_iomap(struct device_node *device, int index); +/* These includes are put at the bottom because they may contain things + * that are overridden by this file. Ideally they shouldn't be included + * by this file, but there are a bunch of .c files that currently depend + * on it. Eventually they will be cleaned up. */ +#include <linux/of_fdt.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/platform_device.h> #endif /* __KERNEL__ */ #endif /* _POWERPC_PROM_H */ diff --git a/arch/powerpc/include/asm/smu.h b/arch/powerpc/include/asm/smu.h index 7ae2753da56..e3bdada8c54 100644 --- a/arch/powerpc/include/asm/smu.h +++ b/arch/powerpc/include/asm/smu.h @@ -457,8 +457,8 @@ extern void smu_poll(void); */ extern int smu_init(void); extern int smu_present(void); -struct of_device; -extern struct of_device *smu_get_ofdev(void); +struct platform_device; +extern struct platform_device *smu_get_ofdev(void); /* diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 3033c1b3074..afe4aaa65c3 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -41,8 +41,6 @@ static inline int cpu_to_node(int cpu) cpu_all_mask : \ node_to_cpumask_map[node]) -int of_node_to_nid(struct device_node *device); - struct pci_bus; #ifdef CONFIG_PCI extern int pcibus_to_node(struct pci_bus *bus); @@ -97,11 +95,6 @@ extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid); #else -static inline int of_node_to_nid(struct device_node *device) -{ - return 0; -} - static inline void dump_numa_cpu_topology(void) {} static inline int sysfs_add_device_to_node(struct sys_device *dev, int nid) diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 77d831a1cc3..1dda7012914 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -41,7 +41,7 @@ obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_970_NAP) += idle_power4.o -obj-$(CONFIG_PPC_OF) += of_device.o of_platform.o prom_parse.o +obj-$(CONFIG_PPC_OF) += of_platform.o prom_parse.o obj-$(CONFIG_PPC_CLOCK) += clock.o procfs-y := proc_powerpc.o obj-$(CONFIG_PROC_FS) += $(procfs-y) diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 02f724f3675..4295e0b94b2 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -82,17 +82,9 @@ static struct notifier_block ppc_swiotlb_plat_bus_notifier = { .priority = 0, }; -static struct notifier_block ppc_swiotlb_of_bus_notifier = { - .notifier_call = ppc_swiotlb_bus_notify, - .priority = 0, -}; - int __init swiotlb_setup_bus_notifier(void) { bus_register_notifier(&platform_bus_type, &ppc_swiotlb_plat_bus_notifier); - bus_register_notifier(&of_platform_bus_type, - &ppc_swiotlb_of_bus_notifier); - return 0; } diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c index 21266abfbda..9b626cfffce 100644 --- a/arch/powerpc/kernel/ibmebus.c +++ b/arch/powerpc/kernel/ibmebus.c @@ -140,19 +140,19 @@ static struct dma_map_ops ibmebus_dma_ops = { static int ibmebus_match_path(struct device *dev, void *data) { - struct device_node *dn = to_of_device(dev)->dev.of_node; + struct device_node *dn = to_platform_device(dev)->dev.of_node; return (dn->full_name && (strcasecmp((char *)data, dn->full_name) == 0)); } static int ibmebus_match_node(struct device *dev, void *data) { - return to_of_device(dev)->dev.of_node == data; + return to_platform_device(dev)->dev.of_node == data; } static int ibmebus_create_device(struct device_node *dn) { - struct of_device *dev; + struct platform_device *dev; int ret; dev = of_device_alloc(dn, NULL, &ibmebus_bus_device); @@ -298,7 +298,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus, if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path, ibmebus_match_path))) { - of_device_unregister(to_of_device(dev)); + of_device_unregister(to_platform_device(dev)); kfree(path); return count; diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 8f96d319890..d3ce67cf03b 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -53,6 +53,8 @@ #include <linux/bootmem.h> #include <linux/pci.h> #include <linux/debugfs.h> +#include <linux/of.h> +#include <linux/of_irq.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -820,18 +822,6 @@ unsigned int irq_create_of_mapping(struct device_node *controller, } EXPORT_SYMBOL_GPL(irq_create_of_mapping); -unsigned int irq_of_parse_and_map(struct device_node *dev, int index) -{ - struct of_irq oirq; - - if (of_irq_map_one(dev, index, &oirq)) - return NO_IRQ; - - return irq_create_of_mapping(oirq.controller, oirq.specifier, - oirq.size); -} -EXPORT_SYMBOL_GPL(irq_of_parse_and_map); - void irq_dispose_mapping(unsigned int virq) { struct irq_host *host; diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 82a7b228c81..7f61a3ac787 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -129,7 +129,7 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs) return 0; if (*(u32 *) (regs->nip) == *(u32 *) (&arch_kgdb_ops.gdb_bpt_instr)) - regs->nip += 4; + regs->nip += BREAK_INSTR_SIZE; return 1; } diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 035ada5443e..c1fd0f9658f 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -4,6 +4,7 @@ #include <linux/serial_core.h> #include <linux/console.h> #include <linux/pci.h> +#include <linux/of_address.h> #include <linux/of_device.h> #include <asm/io.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 22e507c8a55..2d29752cbe1 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -127,29 +127,3 @@ _GLOBAL(__setup_cpu_power7) _GLOBAL(__restore_cpu_power7) /* place holder */ blr - -/* - * Get a minimal set of registers for our caller's nth caller. - * r3 = regs pointer, r5 = n. - * - * We only get R1 (stack pointer), NIP (next instruction pointer) - * and LR (link register). These are all we can get in the - * general case without doing complicated stack unwinding, but - * fortunately they are enough to do a stack backtrace, which - * is all we need them for. - */ -_GLOBAL(perf_arch_fetch_caller_regs) - mr r6,r1 - cmpwi r5,0 - mflr r4 - ble 2f - mtctr r5 -1: PPC_LL r6,0(r6) - bdnz 1b - PPC_LL r4,PPC_LR_STKOFF(r6) -2: PPC_LL r7,0(r6) - PPC_LL r7,PPC_LR_STKOFF(r7) - PPC_STL r6,GPR1-STACK_FRAME_OVERHEAD(r3) - PPC_STL r4,_NIP-STACK_FRAME_OVERHEAD(r3) - PPC_STL r7,_LINK-STACK_FRAME_OVERHEAD(r3) - blr diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c deleted file mode 100644 index df78e0236a0..00000000000 --- a/arch/powerpc/kernel/of_device.c +++ /dev/null @@ -1,133 +0,0 @@ -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/mod_devicetable.h> -#include <linux/slab.h> -#include <linux/of_device.h> - -#include <asm/errno.h> -#include <asm/dcr.h> - -static void of_device_make_bus_id(struct of_device *dev) -{ - static atomic_t bus_no_reg_magic; - struct device_node *node = dev->dev.of_node; - const u32 *reg; - u64 addr; - int magic; - - /* - * If it's a DCR based device, use 'd' for native DCRs - * and 'D' for MMIO DCRs. - */ -#ifdef CONFIG_PPC_DCR - reg = of_get_property(node, "dcr-reg", NULL); - if (reg) { -#ifdef CONFIG_PPC_DCR_NATIVE - dev_set_name(&dev->dev, "d%x.%s", *reg, node->name); -#else /* CONFIG_PPC_DCR_NATIVE */ - addr = of_translate_dcr_address(node, *reg, NULL); - if (addr != OF_BAD_ADDR) { - dev_set_name(&dev->dev, "D%llx.%s", - (unsigned long long)addr, node->name); - return; - } -#endif /* !CONFIG_PPC_DCR_NATIVE */ - } -#endif /* CONFIG_PPC_DCR */ - - /* - * For MMIO, get the physical address - */ - reg = of_get_property(node, "reg", NULL); - if (reg) { - addr = of_translate_address(node, reg); - if (addr != OF_BAD_ADDR) { - dev_set_name(&dev->dev, "%llx.%s", - (unsigned long long)addr, node->name); - return; - } - } - - /* - * No BusID, use the node name and add a globally incremented - * counter (and pray...) - */ - magic = atomic_add_return(1, &bus_no_reg_magic); - dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1); -} - -struct of_device *of_device_alloc(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - struct of_device *dev; - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return NULL; - - dev->dev.of_node = of_node_get(np); - dev->dev.dma_mask = &dev->archdata.dma_mask; - dev->dev.parent = parent; - dev->dev.release = of_release_dev; - - if (bus_id) - dev_set_name(&dev->dev, "%s", bus_id); - else - of_device_make_bus_id(dev); - - return dev; -} -EXPORT_SYMBOL(of_device_alloc); - -int of_device_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - struct of_device *ofdev; - const char *compat; - int seen = 0, cplen, sl; - - if (!dev) - return -ENODEV; - - ofdev = to_of_device(dev); - - if (add_uevent_var(env, "OF_NAME=%s", ofdev->dev.of_node->name)) - return -ENOMEM; - - if (add_uevent_var(env, "OF_TYPE=%s", ofdev->dev.of_node->type)) - return -ENOMEM; - - /* Since the compatible field can contain pretty much anything - * it's not really legal to split it out with commas. We split it - * up using a number of environment variables instead. */ - - compat = of_get_property(ofdev->dev.of_node, "compatible", &cplen); - while (compat && *compat && cplen > 0) { - if (add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat)) - return -ENOMEM; - - sl = strlen (compat) + 1; - compat += sl; - cplen -= sl; - seen++; - } - - if (add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen)) - return -ENOMEM; - - /* modalias is trickier, we add it in 2 steps */ - if (add_uevent_var(env, "MODALIAS=")) - return -ENOMEM; - sl = of_device_get_modalias(ofdev, &env->buf[env->buflen-1], - sizeof(env->buf) - env->buflen); - if (sl >= (sizeof(env->buf) - env->buflen)) - return -ENOMEM; - env->buflen += sl; - - return 0; -} -EXPORT_SYMBOL(of_device_uevent); -EXPORT_SYMBOL(of_device_get_modalias); diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index 487a98851ba..b2c363ef38a 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -28,207 +28,6 @@ #include <asm/ppc-pci.h> #include <asm/atomic.h> -/* - * The list of OF IDs below is used for matching bus types in the - * system whose devices are to be exposed as of_platform_devices. - * - * This is the default list valid for most platforms. This file provides - * functions who can take an explicit list if necessary though - * - * The search is always performed recursively looking for children of - * the provided device_node and recursively if such a children matches - * a bus type in the list - */ - -static const struct of_device_id of_default_bus_ids[] = { - { .type = "soc", }, - { .compatible = "soc", }, - { .type = "spider", }, - { .type = "axon", }, - { .type = "plb5", }, - { .type = "plb4", }, - { .type = "opb", }, - { .type = "ebc", }, - {}, -}; - -struct bus_type of_platform_bus_type = { - .uevent = of_device_uevent, -}; -EXPORT_SYMBOL(of_platform_bus_type); - -static int __init of_bus_driver_init(void) -{ - return of_bus_type_init(&of_platform_bus_type, "of_platform"); -} - -postcore_initcall(of_bus_driver_init); - -struct of_device* of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - struct of_device *dev; - - dev = of_device_alloc(np, bus_id, parent); - if (!dev) - return NULL; - - dev->archdata.dma_mask = 0xffffffffUL; - dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - - dev->dev.bus = &of_platform_bus_type; - - /* We do not fill the DMA ops for platform devices by default. - * This is currently the responsibility of the platform code - * to do such, possibly using a device notifier - */ - - if (of_device_register(dev) != 0) { - of_device_free(dev); - return NULL; - } - - return dev; -} -EXPORT_SYMBOL(of_platform_device_create); - - - -/** - * of_platform_bus_create - Create an OF device for a bus node and all its - * children. Optionally recursively instanciate matching busses. - * @bus: device node of the bus to instanciate - * @matches: match table, NULL to use the default, OF_NO_DEEP_PROBE to - * disallow recursive creation of child busses - */ -static int of_platform_bus_create(const struct device_node *bus, - const struct of_device_id *matches, - struct device *parent) -{ - struct device_node *child; - struct of_device *dev; - int rc = 0; - - for_each_child_of_node(bus, child) { - pr_debug(" create child: %s\n", child->full_name); - dev = of_platform_device_create(child, NULL, parent); - if (dev == NULL) - rc = -ENOMEM; - else if (!of_match_node(matches, child)) - continue; - if (rc == 0) { - pr_debug(" and sub busses\n"); - rc = of_platform_bus_create(child, matches, &dev->dev); - } if (rc) { - of_node_put(child); - break; - } - } - return rc; -} - -/** - * of_platform_bus_probe - Probe the device-tree for platform busses - * @root: parent of the first level to probe or NULL for the root of the tree - * @matches: match table, NULL to use the default - * @parent: parent to hook devices from, NULL for toplevel - * - * Note that children of the provided root are not instanciated as devices - * unless the specified root itself matches the bus list and is not NULL. - */ - -int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent) -{ - struct device_node *child; - struct of_device *dev; - int rc = 0; - - if (matches == NULL) - matches = of_default_bus_ids; - if (matches == OF_NO_DEEP_PROBE) - return -EINVAL; - if (root == NULL) - root = of_find_node_by_path("/"); - else - of_node_get(root); - - pr_debug("of_platform_bus_probe()\n"); - pr_debug(" starting at: %s\n", root->full_name); - - /* Do a self check of bus type, if there's a match, create - * children - */ - if (of_match_node(matches, root)) { - pr_debug(" root match, create all sub devices\n"); - dev = of_platform_device_create(root, NULL, parent); - if (dev == NULL) { - rc = -ENOMEM; - goto bail; - } - pr_debug(" create all sub busses\n"); - rc = of_platform_bus_create(root, matches, &dev->dev); - goto bail; - } - for_each_child_of_node(root, child) { - if (!of_match_node(matches, child)) - continue; - - pr_debug(" match: %s\n", child->full_name); - dev = of_platform_device_create(child, NULL, parent); - if (dev == NULL) - rc = -ENOMEM; - else - rc = of_platform_bus_create(child, matches, &dev->dev); - if (rc) { - of_node_put(child); - break; - } - } - bail: - of_node_put(root); - return rc; -} -EXPORT_SYMBOL(of_platform_bus_probe); - -static int of_dev_node_match(struct device *dev, void *data) -{ - return to_of_device(dev)->dev.of_node == data; -} - -struct of_device *of_find_device_by_node(struct device_node *np) -{ - struct device *dev; - - dev = bus_find_device(&of_platform_bus_type, - NULL, np, of_dev_node_match); - if (dev) - return to_of_device(dev); - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_node); - -static int of_dev_phandle_match(struct device *dev, void *data) -{ - phandle *ph = data; - return to_of_device(dev)->dev.of_node->phandle == *ph; -} - -struct of_device *of_find_device_by_phandle(phandle ph) -{ - struct device *dev; - - dev = bus_find_device(&of_platform_bus_type, - NULL, &ph, of_dev_phandle_match); - if (dev) - return to_of_device(dev); - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_phandle); - - #ifdef CONFIG_PPC_OF_PLATFORM_PCI /* The probing of PCI controllers from of_platform is currently @@ -237,7 +36,7 @@ EXPORT_SYMBOL(of_find_device_by_phandle); * lacking some bits needed here. */ -static int __devinit of_pci_phb_probe(struct of_device *dev, +static int __devinit of_pci_phb_probe(struct platform_device *dev, const struct of_device_id *match) { struct pci_controller *phb; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 5b38f6ae2b2..9021c4ad4bb 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/of_address.h> #include <linux/mm.h> #include <linux/list.h> #include <linux/syscalls.h> diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index 5c14ffe5125..d301a30445e 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -410,15 +410,15 @@ static void power_pmu_read(struct perf_event *event) * Therefore we treat them like NMIs. */ do { - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); barrier(); val = read_pmc(event->hw.idx); - } while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev); + } while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev); /* The counters are only 32 bits wide */ delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &event->hw.period_left); + local64_add(delta, &event->count); + local64_sub(delta, &event->hw.period_left); } /* @@ -444,10 +444,10 @@ static void freeze_limited_counters(struct cpu_hw_events *cpuhw, if (!event->hw.idx) continue; val = (event->hw.idx == 5) ? pmc5 : pmc6; - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); event->hw.idx = 0; delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); + local64_add(delta, &event->count); } } @@ -462,7 +462,7 @@ static void thaw_limited_counters(struct cpu_hw_events *cpuhw, event = cpuhw->limited_counter[i]; event->hw.idx = cpuhw->limited_hwidx[i]; val = (event->hw.idx == 5) ? pmc5 : pmc6; - atomic64_set(&event->hw.prev_count, val); + local64_set(&event->hw.prev_count, val); perf_event_update_userpage(event); } } @@ -666,11 +666,11 @@ void hw_perf_enable(void) } val = 0; if (event->hw.sample_period) { - left = atomic64_read(&event->hw.period_left); + left = local64_read(&event->hw.period_left); if (left < 0x80000000L) val = 0x80000000L - left; } - atomic64_set(&event->hw.prev_count, val); + local64_set(&event->hw.prev_count, val); event->hw.idx = idx; write_pmc(idx, val); perf_event_update_userpage(event); @@ -754,7 +754,7 @@ static int power_pmu_enable(struct perf_event *event) * skip the schedulability test here, it will be peformed * at commit time(->commit_txn) as a whole */ - if (cpuhw->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuhw->group_flag & PERF_EVENT_TXN) goto nocheck; if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1)) @@ -845,8 +845,8 @@ static void power_pmu_unthrottle(struct perf_event *event) if (left < 0x80000000L) val = 0x80000000L - left; write_pmc(event->hw.idx, val); - atomic64_set(&event->hw.prev_count, val); - atomic64_set(&event->hw.period_left, left); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); perf_event_update_userpage(event); perf_enable(); local_irq_restore(flags); @@ -861,7 +861,7 @@ void power_pmu_start_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - cpuhw->group_flag |= PERF_EVENT_TXN_STARTED; + cpuhw->group_flag |= PERF_EVENT_TXN; cpuhw->n_txn_start = cpuhw->n_events; } @@ -874,7 +874,7 @@ void power_pmu_cancel_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED; + cpuhw->group_flag &= ~PERF_EVENT_TXN; } /* @@ -900,6 +900,7 @@ int power_pmu_commit_txn(const struct pmu *pmu) for (i = cpuhw->n_txn_start; i < n; ++i) cpuhw->event[i]->hw.config = cpuhw->events[i]; + cpuhw->group_flag &= ~PERF_EVENT_TXN; return 0; } @@ -1111,7 +1112,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) event->hw.config = events[n]; event->hw.event_base = cflags[n]; event->hw.last_period = event->hw.sample_period; - atomic64_set(&event->hw.period_left, event->hw.last_period); + local64_set(&event->hw.period_left, event->hw.last_period); /* * See if we need to reserve the PMU. @@ -1149,16 +1150,16 @@ static void record_and_restart(struct perf_event *event, unsigned long val, int record = 0; /* we don't have to worry about interrupts here */ - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); + local64_add(delta, &event->count); /* * See if the total period for this event has expired, * and update for the next period. */ val = 0; - left = atomic64_read(&event->hw.period_left) - delta; + left = local64_read(&event->hw.period_left) - delta; if (period) { if (left <= 0) { left += period; @@ -1196,8 +1197,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val, } write_pmc(event->hw.idx, val); - atomic64_set(&event->hw.prev_count, val); - atomic64_set(&event->hw.period_left, left); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); perf_event_update_userpage(event); } diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c index babcceecd2e..1ba45471ae4 100644 --- a/arch/powerpc/kernel/perf_event_fsl_emb.c +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -162,15 +162,15 @@ static void fsl_emb_pmu_read(struct perf_event *event) * Therefore we treat them like NMIs. */ do { - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); barrier(); val = read_pmc(event->hw.idx); - } while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev); + } while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev); /* The counters are only 32 bits wide */ delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &event->hw.period_left); + local64_add(delta, &event->count); + local64_sub(delta, &event->hw.period_left); } /* @@ -296,11 +296,11 @@ static int fsl_emb_pmu_enable(struct perf_event *event) val = 0; if (event->hw.sample_period) { - s64 left = atomic64_read(&event->hw.period_left); + s64 left = local64_read(&event->hw.period_left); if (left < 0x80000000L) val = 0x80000000L - left; } - atomic64_set(&event->hw.prev_count, val); + local64_set(&event->hw.prev_count, val); write_pmc(i, val); perf_event_update_userpage(event); @@ -371,8 +371,8 @@ static void fsl_emb_pmu_unthrottle(struct perf_event *event) if (left < 0x80000000L) val = 0x80000000L - left; write_pmc(event->hw.idx, val); - atomic64_set(&event->hw.prev_count, val); - atomic64_set(&event->hw.period_left, left); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); perf_event_update_userpage(event); perf_enable(); local_irq_restore(flags); @@ -500,7 +500,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) return ERR_PTR(-ENOTSUPP); event->hw.last_period = event->hw.sample_period; - atomic64_set(&event->hw.period_left, event->hw.last_period); + local64_set(&event->hw.period_left, event->hw.last_period); /* * See if we need to reserve the PMU. @@ -541,16 +541,16 @@ static void record_and_restart(struct perf_event *event, unsigned long val, int record = 0; /* we don't have to worry about interrupts here */ - prev = atomic64_read(&event->hw.prev_count); + prev = local64_read(&event->hw.prev_count); delta = (val - prev) & 0xfffffffful; - atomic64_add(delta, &event->count); + local64_add(delta, &event->count); /* * See if the total period for this event has expired, * and update for the next period. */ val = 0; - left = atomic64_read(&event->hw.period_left) - delta; + left = local64_read(&event->hw.period_left) - delta; if (period) { if (left <= 0) { left += period; @@ -569,6 +569,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, struct perf_sample_data data; perf_sample_data_init(&data, 0); + data.period = event->hw.last_period; if (perf_event_overflow(event, nmi, &data, regs)) { /* @@ -584,8 +585,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val, } write_pmc(event->hw.idx, val); - atomic64_set(&event->hw.prev_count, val); - atomic64_set(&event->hw.period_left, left); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); perf_event_update_userpage(event); } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 551f6713ff4..e78a5add7f1 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1299,3 +1299,14 @@ unsigned long randomize_et_dyn(unsigned long base) return ret; } + +#ifdef CONFIG_SMP +int arch_sd_sibling_asym_packing(void) +{ + if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { + printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); + return SD_ASYM_PACKING; + } + return 0; +} +#endif diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index 8362620c9e6..88334af038e 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -6,232 +6,11 @@ #include <linux/module.h> #include <linux/ioport.h> #include <linux/etherdevice.h> +#include <linux/of_address.h> #include <asm/prom.h> #include <asm/pci-bridge.h> -#ifdef DEBUG -#define DBG(fmt...) do { printk(fmt); } while(0) -#else -#define DBG(fmt...) do { } while(0) -#endif - -#ifdef CONFIG_PPC64 -#define PRu64 "%lx" -#else -#define PRu64 "%llx" -#endif - -/* Max address size we deal with */ -#define OF_MAX_ADDR_CELLS 4 -#define OF_CHECK_COUNTS(na, ns) ((na) > 0 && (na) <= OF_MAX_ADDR_CELLS && \ - (ns) > 0) - -static struct of_bus *of_match_bus(struct device_node *np); -static int __of_address_to_resource(struct device_node *dev, - const u32 *addrp, u64 size, unsigned int flags, - struct resource *r); - - -/* Debug utility */ -#ifdef DEBUG -static void of_dump_addr(const char *s, const u32 *addr, int na) -{ - printk("%s", s); - while(na--) - printk(" %08x", *(addr++)); - printk("\n"); -} -#else -static void of_dump_addr(const char *s, const u32 *addr, int na) { } -#endif - - -/* Callbacks for bus specific translators */ -struct of_bus { - const char *name; - const char *addresses; - int (*match)(struct device_node *parent); - void (*count_cells)(struct device_node *child, - int *addrc, int *sizec); - u64 (*map)(u32 *addr, const u32 *range, - int na, int ns, int pna); - int (*translate)(u32 *addr, u64 offset, int na); - unsigned int (*get_flags)(const u32 *addr); -}; - - -/* - * Default translator (generic bus) - */ - -static void of_bus_default_count_cells(struct device_node *dev, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = of_n_addr_cells(dev); - if (sizec) - *sizec = of_n_size_cells(dev); -} - -static u64 of_bus_default_map(u32 *addr, const u32 *range, - int na, int ns, int pna) -{ - u64 cp, s, da; - - cp = of_read_number(range, na); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr, na); - - DBG("OF: default map, cp="PRu64", s="PRu64", da="PRu64"\n", - cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_default_translate(u32 *addr, u64 offset, int na) -{ - u64 a = of_read_number(addr, na); - memset(addr, 0, na * 4); - a += offset; - if (na > 1) - addr[na - 2] = a >> 32; - addr[na - 1] = a & 0xffffffffu; - - return 0; -} - -static unsigned int of_bus_default_get_flags(const u32 *addr) -{ - return IORESOURCE_MEM; -} - - #ifdef CONFIG_PCI -/* - * PCI bus specific translator - */ - -static int of_bus_pci_match(struct device_node *np) -{ - /* "vci" is for the /chaos bridge on 1st-gen PCI powermacs */ - return !strcmp(np->type, "pci") || !strcmp(np->type, "vci"); -} - -static void of_bus_pci_count_cells(struct device_node *np, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = 3; - if (sizec) - *sizec = 2; -} - -static unsigned int of_bus_pci_get_flags(const u32 *addr) -{ - unsigned int flags = 0; - u32 w = addr[0]; - - switch((w >> 24) & 0x03) { - case 0x01: - flags |= IORESOURCE_IO; - break; - case 0x02: /* 32 bits */ - case 0x03: /* 64 bits */ - flags |= IORESOURCE_MEM; - break; - } - if (w & 0x40000000) - flags |= IORESOURCE_PREFETCH; - return flags; -} - -static u64 of_bus_pci_map(u32 *addr, const u32 *range, int na, int ns, int pna) -{ - u64 cp, s, da; - unsigned int af, rf; - - af = of_bus_pci_get_flags(addr); - rf = of_bus_pci_get_flags(range); - - /* Check address type match */ - if ((af ^ rf) & (IORESOURCE_MEM | IORESOURCE_IO)) - return OF_BAD_ADDR; - - /* Read address values, skipping high cell */ - cp = of_read_number(range + 1, na - 1); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr + 1, na - 1); - - DBG("OF: PCI map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_pci_translate(u32 *addr, u64 offset, int na) -{ - return of_bus_default_translate(addr + 1, offset, na - 1); -} - -const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, - unsigned int *flags) -{ - const u32 *prop; - unsigned int psize; - struct device_node *parent; - struct of_bus *bus; - int onesize, i, na, ns; - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - return NULL; - bus = of_match_bus(parent); - if (strcmp(bus->name, "pci")) { - of_node_put(parent); - return NULL; - } - bus->count_cells(dev, &na, &ns); - of_node_put(parent); - if (!OF_CHECK_COUNTS(na, ns)) - return NULL; - - /* Get "reg" or "assigned-addresses" property */ - prop = of_get_property(dev, bus->addresses, &psize); - if (prop == NULL) - return NULL; - psize /= 4; - - onesize = na + ns; - for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) - if ((prop[0] & 0xff) == ((bar_no * 4) + PCI_BASE_ADDRESS_0)) { - if (size) - *size = of_read_number(prop + na, ns); - if (flags) - *flags = bus->get_flags(prop); - return prop; - } - return NULL; -} -EXPORT_SYMBOL(of_get_pci_address); - -int of_pci_address_to_resource(struct device_node *dev, int bar, - struct resource *r) -{ - const u32 *addrp; - u64 size; - unsigned int flags; - - addrp = of_get_pci_address(dev, bar, &size, &flags); - if (addrp == NULL) - return -EINVAL; - return __of_address_to_resource(dev, addrp, size, flags, r); -} -EXPORT_SYMBOL_GPL(of_pci_address_to_resource); - int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) { struct device_node *dn, *ppnode; @@ -313,345 +92,6 @@ int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) EXPORT_SYMBOL_GPL(of_irq_map_pci); #endif /* CONFIG_PCI */ -/* - * ISA bus specific translator - */ - -static int of_bus_isa_match(struct device_node *np) -{ - return !strcmp(np->name, "isa"); -} - -static void of_bus_isa_count_cells(struct device_node *child, - int *addrc, int *sizec) -{ - if (addrc) - *addrc = 2; - if (sizec) - *sizec = 1; -} - -static u64 of_bus_isa_map(u32 *addr, const u32 *range, int na, int ns, int pna) -{ - u64 cp, s, da; - - /* Check address type match */ - if ((addr[0] ^ range[0]) & 0x00000001) - return OF_BAD_ADDR; - - /* Read address values, skipping high cell */ - cp = of_read_number(range + 1, na - 1); - s = of_read_number(range + na + pna, ns); - da = of_read_number(addr + 1, na - 1); - - DBG("OF: ISA map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da); - - if (da < cp || da >= (cp + s)) - return OF_BAD_ADDR; - return da - cp; -} - -static int of_bus_isa_translate(u32 *addr, u64 offset, int na) -{ - return of_bus_default_translate(addr + 1, offset, na - 1); -} - -static unsigned int of_bus_isa_get_flags(const u32 *addr) -{ - unsigned int flags = 0; - u32 w = addr[0]; - - if (w & 1) - flags |= IORESOURCE_IO; - else - flags |= IORESOURCE_MEM; - return flags; -} - - -/* - * Array of bus specific translators - */ - -static struct of_bus of_busses[] = { -#ifdef CONFIG_PCI - /* PCI */ - { - .name = "pci", - .addresses = "assigned-addresses", - .match = of_bus_pci_match, - .count_cells = of_bus_pci_count_cells, - .map = of_bus_pci_map, - .translate = of_bus_pci_translate, - .get_flags = of_bus_pci_get_flags, - }, -#endif /* CONFIG_PCI */ - /* ISA */ - { - .name = "isa", - .addresses = "reg", - .match = of_bus_isa_match, - .count_cells = of_bus_isa_count_cells, - .map = of_bus_isa_map, - .translate = of_bus_isa_translate, - .get_flags = of_bus_isa_get_flags, - }, - /* Default */ - { - .name = "default", - .addresses = "reg", - .match = NULL, - .count_cells = of_bus_default_count_cells, - .map = of_bus_default_map, - .translate = of_bus_default_translate, - .get_flags = of_bus_default_get_flags, - }, -}; - -static struct of_bus *of_match_bus(struct device_node *np) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(of_busses); i ++) - if (!of_busses[i].match || of_busses[i].match(np)) - return &of_busses[i]; - BUG(); - return NULL; -} - -static int of_translate_one(struct device_node *parent, struct of_bus *bus, - struct of_bus *pbus, u32 *addr, - int na, int ns, int pna, const char *rprop) -{ - const u32 *ranges; - unsigned int rlen; - int rone; - u64 offset = OF_BAD_ADDR; - - /* Normally, an absence of a "ranges" property means we are - * crossing a non-translatable boundary, and thus the addresses - * below the current not cannot be converted to CPU physical ones. - * Unfortunately, while this is very clear in the spec, it's not - * what Apple understood, and they do have things like /uni-n or - * /ht nodes with no "ranges" property and a lot of perfectly - * useable mapped devices below them. Thus we treat the absence of - * "ranges" as equivalent to an empty "ranges" property which means - * a 1:1 translation at that level. It's up to the caller not to try - * to translate addresses that aren't supposed to be translated in - * the first place. --BenH. - */ - ranges = of_get_property(parent, rprop, &rlen); - if (ranges == NULL || rlen == 0) { - offset = of_read_number(addr, na); - memset(addr, 0, pna * 4); - DBG("OF: no ranges, 1:1 translation\n"); - goto finish; - } - - DBG("OF: walking ranges...\n"); - - /* Now walk through the ranges */ - rlen /= 4; - rone = na + pna + ns; - for (; rlen >= rone; rlen -= rone, ranges += rone) { - offset = bus->map(addr, ranges, na, ns, pna); - if (offset != OF_BAD_ADDR) - break; - } - if (offset == OF_BAD_ADDR) { - DBG("OF: not found !\n"); - return 1; - } - memcpy(addr, ranges + na, 4 * pna); - - finish: - of_dump_addr("OF: parent translation for:", addr, pna); - DBG("OF: with offset: "PRu64"\n", offset); - - /* Translate it into parent bus space */ - return pbus->translate(addr, offset, pna); -} - - -/* - * Translate an address from the device-tree into a CPU physical address, - * this walks up the tree and applies the various bus mappings on the - * way. - * - * Note: We consider that crossing any level with #size-cells == 0 to mean - * that translation is impossible (that is we are not dealing with a value - * that can be mapped to a cpu physical address). This is not really specified - * that way, but this is traditionally the way IBM at least do things - */ -u64 __of_translate_address(struct device_node *dev, const u32 *in_addr, - const char *rprop) -{ - struct device_node *parent = NULL; - struct of_bus *bus, *pbus; - u32 addr[OF_MAX_ADDR_CELLS]; - int na, ns, pna, pns; - u64 result = OF_BAD_ADDR; - - DBG("OF: ** translation for device %s **\n", dev->full_name); - - /* Increase refcount at current level */ - of_node_get(dev); - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - goto bail; - bus = of_match_bus(parent); - - /* Cound address cells & copy address locally */ - bus->count_cells(dev, &na, &ns); - if (!OF_CHECK_COUNTS(na, ns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", - dev->full_name); - goto bail; - } - memcpy(addr, in_addr, na * 4); - - DBG("OF: bus is %s (na=%d, ns=%d) on %s\n", - bus->name, na, ns, parent->full_name); - of_dump_addr("OF: translating address:", addr, na); - - /* Translate */ - for (;;) { - /* Switch to parent bus */ - of_node_put(dev); - dev = parent; - parent = of_get_parent(dev); - - /* If root, we have finished */ - if (parent == NULL) { - DBG("OF: reached root node\n"); - result = of_read_number(addr, na); - break; - } - - /* Get new parent bus and counts */ - pbus = of_match_bus(parent); - pbus->count_cells(dev, &pna, &pns); - if (!OF_CHECK_COUNTS(pna, pns)) { - printk(KERN_ERR "prom_parse: Bad cell count for %s\n", - dev->full_name); - break; - } - - DBG("OF: parent bus is %s (na=%d, ns=%d) on %s\n", - pbus->name, pna, pns, parent->full_name); - - /* Apply bus translation */ - if (of_translate_one(dev, bus, pbus, addr, na, ns, pna, rprop)) - break; - - /* Complete the move up one level */ - na = pna; - ns = pns; - bus = pbus; - - of_dump_addr("OF: one level translation:", addr, na); - } - bail: - of_node_put(parent); - of_node_put(dev); - - return result; -} - -u64 of_translate_address(struct device_node *dev, const u32 *in_addr) -{ - return __of_translate_address(dev, in_addr, "ranges"); -} -EXPORT_SYMBOL(of_translate_address); - -u64 of_translate_dma_address(struct device_node *dev, const u32 *in_addr) -{ - return __of_translate_address(dev, in_addr, "dma-ranges"); -} -EXPORT_SYMBOL(of_translate_dma_address); - -const u32 *of_get_address(struct device_node *dev, int index, u64 *size, - unsigned int *flags) -{ - const u32 *prop; - unsigned int psize; - struct device_node *parent; - struct of_bus *bus; - int onesize, i, na, ns; - - /* Get parent & match bus type */ - parent = of_get_parent(dev); - if (parent == NULL) - return NULL; - bus = of_match_bus(parent); - bus->count_cells(dev, &na, &ns); - of_node_put(parent); - if (!OF_CHECK_COUNTS(na, ns)) - return NULL; - - /* Get "reg" or "assigned-addresses" property */ - prop = of_get_property(dev, bus->addresses, &psize); - if (prop == NULL) - return NULL; - psize /= 4; - - onesize = na + ns; - for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) - if (i == index) { - if (size) - *size = of_read_number(prop + na, ns); - if (flags) - *flags = bus->get_flags(prop); - return prop; - } - return NULL; -} -EXPORT_SYMBOL(of_get_address); - -static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, - u64 size, unsigned int flags, - struct resource *r) -{ - u64 taddr; - - if ((flags & (IORESOURCE_IO | IORESOURCE_MEM)) == 0) - return -EINVAL; - taddr = of_translate_address(dev, addrp); - if (taddr == OF_BAD_ADDR) - return -EINVAL; - memset(r, 0, sizeof(struct resource)); - if (flags & IORESOURCE_IO) { - unsigned long port; - port = pci_address_to_pio(taddr); - if (port == (unsigned long)-1) - return -EINVAL; - r->start = port; - r->end = port + size - 1; - } else { - r->start = taddr; - r->end = taddr + size - 1; - } - r->flags = flags; - r->name = dev->name; - return 0; -} - -int of_address_to_resource(struct device_node *dev, int index, - struct resource *r) -{ - const u32 *addrp; - u64 size; - unsigned int flags; - - addrp = of_get_address(dev, index, &size, &flags); - if (addrp == NULL) - return -EINVAL; - return __of_address_to_resource(dev, addrp, size, flags, r); -} -EXPORT_SYMBOL_GPL(of_address_to_resource); - void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, unsigned long *busno, unsigned long *phys, unsigned long *size) { @@ -678,342 +118,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, *size = of_read_number(dma_window, cells); } -/* - * Interrupt remapper - */ - -static unsigned int of_irq_workarounds; -static struct device_node *of_irq_dflt_pic; - -static struct device_node *of_irq_find_parent(struct device_node *child) -{ - struct device_node *p; - const phandle *parp; - - if (!of_node_get(child)) - return NULL; - - do { - parp = of_get_property(child, "interrupt-parent", NULL); - if (parp == NULL) - p = of_get_parent(child); - else { - if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) - p = of_node_get(of_irq_dflt_pic); - else - p = of_find_node_by_phandle(*parp); - } - of_node_put(child); - child = p; - } while (p && of_get_property(p, "#interrupt-cells", NULL) == NULL); - - return p; -} - -/* This doesn't need to be called if you don't have any special workaround - * flags to pass - */ -void of_irq_map_init(unsigned int flags) -{ - of_irq_workarounds = flags; - - /* OldWorld, don't bother looking at other things */ - if (flags & OF_IMAP_OLDWORLD_MAC) - return; - - /* If we don't have phandles, let's try to locate a default interrupt - * controller (happens when booting with BootX). We do a first match - * here, hopefully, that only ever happens on machines with one - * controller. - */ - if (flags & OF_IMAP_NO_PHANDLE) { - struct device_node *np; - - for_each_node_with_property(np, "interrupt-controller") { - /* Skip /chosen/interrupt-controller */ - if (strcmp(np->name, "chosen") == 0) - continue; - /* It seems like at least one person on this planet wants - * to use BootX on a machine with an AppleKiwi controller - * which happens to pretend to be an interrupt - * controller too. - */ - if (strcmp(np->name, "AppleKiwi") == 0) - continue; - /* I think we found one ! */ - of_irq_dflt_pic = np; - break; - } - } - -} - -int of_irq_map_raw(struct device_node *parent, const u32 *intspec, u32 ointsize, - const u32 *addr, struct of_irq *out_irq) -{ - struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL; - const u32 *tmp, *imap, *imask; - u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0; - int imaplen, match, i; - - DBG("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n", - parent->full_name, intspec[0], intspec[1], ointsize); - - ipar = of_node_get(parent); - - /* First get the #interrupt-cells property of the current cursor - * that tells us how to interpret the passed-in intspec. If there - * is none, we are nice and just walk up the tree - */ - do { - tmp = of_get_property(ipar, "#interrupt-cells", NULL); - if (tmp != NULL) { - intsize = *tmp; - break; - } - tnode = ipar; - ipar = of_irq_find_parent(ipar); - of_node_put(tnode); - } while (ipar); - if (ipar == NULL) { - DBG(" -> no parent found !\n"); - goto fail; - } - - DBG("of_irq_map_raw: ipar=%s, size=%d\n", ipar->full_name, intsize); - - if (ointsize != intsize) - return -EINVAL; - - /* Look for this #address-cells. We have to implement the old linux - * trick of looking for the parent here as some device-trees rely on it - */ - old = of_node_get(ipar); - do { - tmp = of_get_property(old, "#address-cells", NULL); - tnode = of_get_parent(old); - of_node_put(old); - old = tnode; - } while(old && tmp == NULL); - of_node_put(old); - old = NULL; - addrsize = (tmp == NULL) ? 2 : *tmp; - - DBG(" -> addrsize=%d\n", addrsize); - - /* Now start the actual "proper" walk of the interrupt tree */ - while (ipar != NULL) { - /* Now check if cursor is an interrupt-controller and if it is - * then we are done - */ - if (of_get_property(ipar, "interrupt-controller", NULL) != - NULL) { - DBG(" -> got it !\n"); - memcpy(out_irq->specifier, intspec, - intsize * sizeof(u32)); - out_irq->size = intsize; - out_irq->controller = ipar; - of_node_put(old); - return 0; - } - - /* Now look for an interrupt-map */ - imap = of_get_property(ipar, "interrupt-map", &imaplen); - /* No interrupt map, check for an interrupt parent */ - if (imap == NULL) { - DBG(" -> no map, getting parent\n"); - newpar = of_irq_find_parent(ipar); - goto skiplevel; - } - imaplen /= sizeof(u32); - - /* Look for a mask */ - imask = of_get_property(ipar, "interrupt-map-mask", NULL); - - /* If we were passed no "reg" property and we attempt to parse - * an interrupt-map, then #address-cells must be 0. - * Fail if it's not. - */ - if (addr == NULL && addrsize != 0) { - DBG(" -> no reg passed in when needed !\n"); - goto fail; - } - - /* Parse interrupt-map */ - match = 0; - while (imaplen > (addrsize + intsize + 1) && !match) { - /* Compare specifiers */ - match = 1; - for (i = 0; i < addrsize && match; ++i) { - u32 mask = imask ? imask[i] : 0xffffffffu; - match = ((addr[i] ^ imap[i]) & mask) == 0; - } - for (; i < (addrsize + intsize) && match; ++i) { - u32 mask = imask ? imask[i] : 0xffffffffu; - match = - ((intspec[i-addrsize] ^ imap[i]) & mask) == 0; - } - imap += addrsize + intsize; - imaplen -= addrsize + intsize; - - DBG(" -> match=%d (imaplen=%d)\n", match, imaplen); - - /* Get the interrupt parent */ - if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) - newpar = of_node_get(of_irq_dflt_pic); - else - newpar = of_find_node_by_phandle((phandle)*imap); - imap++; - --imaplen; - - /* Check if not found */ - if (newpar == NULL) { - DBG(" -> imap parent not found !\n"); - goto fail; - } - - /* Get #interrupt-cells and #address-cells of new - * parent - */ - tmp = of_get_property(newpar, "#interrupt-cells", NULL); - if (tmp == NULL) { - DBG(" -> parent lacks #interrupt-cells !\n"); - goto fail; - } - newintsize = *tmp; - tmp = of_get_property(newpar, "#address-cells", NULL); - newaddrsize = (tmp == NULL) ? 0 : *tmp; - - DBG(" -> newintsize=%d, newaddrsize=%d\n", - newintsize, newaddrsize); - - /* Check for malformed properties */ - if (imaplen < (newaddrsize + newintsize)) - goto fail; - - imap += newaddrsize + newintsize; - imaplen -= newaddrsize + newintsize; - - DBG(" -> imaplen=%d\n", imaplen); - } - if (!match) - goto fail; - - of_node_put(old); - old = of_node_get(newpar); - addrsize = newaddrsize; - intsize = newintsize; - intspec = imap - intsize; - addr = intspec - addrsize; - - skiplevel: - /* Iterate again with new parent */ - DBG(" -> new parent: %s\n", newpar ? newpar->full_name : "<>"); - of_node_put(ipar); - ipar = newpar; - newpar = NULL; - } - fail: - of_node_put(ipar); - of_node_put(old); - of_node_put(newpar); - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(of_irq_map_raw); - -#if defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32) -static int of_irq_map_oldworld(struct device_node *device, int index, - struct of_irq *out_irq) -{ - const u32 *ints = NULL; - int intlen; - - /* - * Old machines just have a list of interrupt numbers - * and no interrupt-controller nodes. We also have dodgy - * cases where the APPL,interrupts property is completely - * missing behind pci-pci bridges and we have to get it - * from the parent (the bridge itself, as apple just wired - * everything together on these) - */ - while (device) { - ints = of_get_property(device, "AAPL,interrupts", &intlen); - if (ints != NULL) - break; - device = device->parent; - if (device && strcmp(device->type, "pci") != 0) - break; - } - if (ints == NULL) - return -EINVAL; - intlen /= sizeof(u32); - - if (index >= intlen) - return -EINVAL; - - out_irq->controller = NULL; - out_irq->specifier[0] = ints[index]; - out_irq->size = 1; - - return 0; -} -#else /* defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32) */ -static int of_irq_map_oldworld(struct device_node *device, int index, - struct of_irq *out_irq) -{ - return -EINVAL; -} -#endif /* !(defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32)) */ - -int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq) -{ - struct device_node *p; - const u32 *intspec, *tmp, *addr; - u32 intsize, intlen; - int res = -EINVAL; - - DBG("of_irq_map_one: dev=%s, index=%d\n", device->full_name, index); - - /* OldWorld mac stuff is "special", handle out of line */ - if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) - return of_irq_map_oldworld(device, index, out_irq); - - /* Get the interrupts property */ - intspec = of_get_property(device, "interrupts", &intlen); - if (intspec == NULL) - return -EINVAL; - intlen /= sizeof(u32); - - /* Get the reg property (if any) */ - addr = of_get_property(device, "reg", NULL); - - /* Look for the interrupt parent. */ - p = of_irq_find_parent(device); - if (p == NULL) - return -EINVAL; - - /* Get size of interrupt specifier */ - tmp = of_get_property(p, "#interrupt-cells", NULL); - if (tmp == NULL) - goto out; - intsize = *tmp; - - DBG(" intsize=%d intlen=%d\n", intsize, intlen); - - /* Check index */ - if ((index + 1) * intsize > intlen) - goto out; - - /* Get new specifier and map it */ - res = of_irq_map_raw(p, intspec + index * intsize, intsize, - addr, out_irq); -out: - of_node_put(p); - return res; -} -EXPORT_SYMBOL_GPL(of_irq_map_one); - /** * Search the device tree for the best MAC address to use. 'mac-address' is * checked first, because that is supposed to contain to "most recent" MAC @@ -1051,29 +155,3 @@ const void *of_get_mac_address(struct device_node *np) return NULL; } EXPORT_SYMBOL(of_get_mac_address); - -int of_irq_to_resource(struct device_node *dev, int index, struct resource *r) -{ - int irq = irq_of_parse_and_map(dev, index); - - /* Only dereference the resource if both the - * resource and the irq are valid. */ - if (r && irq != NO_IRQ) { - r->start = r->end = irq; - r->flags = IORESOURCE_IRQ; - } - - return irq; -} -EXPORT_SYMBOL_GPL(of_irq_to_resource); - -void __iomem *of_iomap(struct device_node *np, int index) -{ - struct resource res; - - if (of_address_to_resource(np, index, &res)) - return NULL; - - return ioremap(res.start, 1 + res.end - res.start); -} -EXPORT_SYMBOL(of_iomap); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 70decd8068c..15ade0d7bbb 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -714,16 +714,9 @@ static struct notifier_block ppc_dflt_plat_bus_notifier = { .priority = INT_MAX, }; -static struct notifier_block ppc_dflt_of_bus_notifier = { - .notifier_call = ppc_dflt_bus_notify, - .priority = INT_MAX, -}; - static int __init setup_bus_notifier(void) { bus_register_notifier(&platform_bus_type, &ppc_dflt_plat_bus_notifier); - bus_register_notifier(&of_platform_bus_type, &ppc_dflt_of_bus_notifier); - return 0; } diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c index e1c5cd6650b..5b243bd3eb3 100644 --- a/arch/powerpc/platforms/512x/clock.c +++ b/arch/powerpc/platforms/512x/clock.c @@ -678,7 +678,7 @@ static void psc_clks_init(void) { struct device_node *np; const u32 *cell_index; - struct of_device *ofdev; + struct platform_device *ofdev; for_each_compatible_node(np, NULL, "fsl,mpc5121-psc") { cell_index = of_get_property(np, "cell-index", NULL); diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c index 6d584f4e3c9..de55bc0584b 100644 --- a/arch/powerpc/platforms/52xx/lite5200.c +++ b/arch/powerpc/platforms/52xx/lite5200.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/root_dev.h> #include <linux/initrd.h> #include <asm/time.h> diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c b/arch/powerpc/platforms/52xx/mpc52xx_gpio.c index ca5305a5bd6..0dad9a935eb 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpio.c @@ -147,26 +147,25 @@ mpc52xx_wkup_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) return 0; } -static int __devinit mpc52xx_wkup_gpiochip_probe(struct of_device *ofdev, +static int __devinit mpc52xx_wkup_gpiochip_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct mpc52xx_gpiochip *chip; struct mpc52xx_gpio_wkup __iomem *regs; - struct of_gpio_chip *ofchip; + struct gpio_chip *gc; int ret; chip = kzalloc(sizeof(*chip), GFP_KERNEL); if (!chip) return -ENOMEM; - ofchip = &chip->mmchip.of_gc; + gc = &chip->mmchip.gc; - ofchip->gpio_cells = 2; - ofchip->gc.ngpio = 8; - ofchip->gc.direction_input = mpc52xx_wkup_gpio_dir_in; - ofchip->gc.direction_output = mpc52xx_wkup_gpio_dir_out; - ofchip->gc.get = mpc52xx_wkup_gpio_get; - ofchip->gc.set = mpc52xx_wkup_gpio_set; + gc->ngpio = 8; + gc->direction_input = mpc52xx_wkup_gpio_dir_in; + gc->direction_output = mpc52xx_wkup_gpio_dir_out; + gc->get = mpc52xx_wkup_gpio_get; + gc->set = mpc52xx_wkup_gpio_set; ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); if (ret) @@ -180,7 +179,7 @@ static int __devinit mpc52xx_wkup_gpiochip_probe(struct of_device *ofdev, return 0; } -static int mpc52xx_gpiochip_remove(struct of_device *ofdev) +static int mpc52xx_gpiochip_remove(struct platform_device *ofdev) { return -EBUSY; } @@ -311,11 +310,11 @@ mpc52xx_simple_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) return 0; } -static int __devinit mpc52xx_simple_gpiochip_probe(struct of_device *ofdev, +static int __devinit mpc52xx_simple_gpiochip_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct mpc52xx_gpiochip *chip; - struct of_gpio_chip *ofchip; + struct gpio_chip *gc; struct mpc52xx_gpio __iomem *regs; int ret; @@ -323,14 +322,13 @@ static int __devinit mpc52xx_simple_gpiochip_probe(struct of_device *ofdev, if (!chip) return -ENOMEM; - ofchip = &chip->mmchip.of_gc; + gc = &chip->mmchip.gc; - ofchip->gpio_cells = 2; - ofchip->gc.ngpio = 32; - ofchip->gc.direction_input = mpc52xx_simple_gpio_dir_in; - ofchip->gc.direction_output = mpc52xx_simple_gpio_dir_out; - ofchip->gc.get = mpc52xx_simple_gpio_get; - ofchip->gc.set = mpc52xx_simple_gpio_set; + gc->ngpio = 32; + gc->direction_input = mpc52xx_simple_gpio_dir_in; + gc->direction_output = mpc52xx_simple_gpio_dir_out; + gc->get = mpc52xx_simple_gpio_get; + gc->set = mpc52xx_simple_gpio_set; ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); if (ret) diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index 46c93578cbf..fea833e18ad 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -78,7 +78,7 @@ MODULE_LICENSE("GPL"); * @dev: pointer to device structure * @regs: virtual address of GPT registers * @lock: spinlock to coordinate between different functions. - * @of_gc: of_gpio_chip instance structure; used when GPIO is enabled + * @gc: gpio_chip instance structure; used when GPIO is enabled * @irqhost: Pointer to irq_host instance; used when IRQ mode is supported * @wdt_mode: only relevant for gpt0: bit 0 (MPC52xx_GPT_CAN_WDT) indicates * if the gpt may be used as wdt, bit 1 (MPC52xx_GPT_IS_WDT) indicates @@ -94,7 +94,7 @@ struct mpc52xx_gpt_priv { u8 wdt_mode; #if defined(CONFIG_GPIOLIB) - struct of_gpio_chip of_gc; + struct gpio_chip gc; #endif }; @@ -280,7 +280,7 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) #if defined(CONFIG_GPIOLIB) static inline struct mpc52xx_gpt_priv *gc_to_mpc52xx_gpt(struct gpio_chip *gc) { - return container_of(to_of_gpio_chip(gc), struct mpc52xx_gpt_priv,of_gc); + return container_of(gc, struct mpc52xx_gpt_priv, gc); } static int mpc52xx_gpt_gpio_get(struct gpio_chip *gc, unsigned int gpio) @@ -336,28 +336,25 @@ mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) if (!of_find_property(node, "gpio-controller", NULL)) return; - gpt->of_gc.gc.label = kstrdup(node->full_name, GFP_KERNEL); - if (!gpt->of_gc.gc.label) { + gpt->gc.label = kstrdup(node->full_name, GFP_KERNEL); + if (!gpt->gc.label) { dev_err(gpt->dev, "out of memory\n"); return; } - gpt->of_gc.gpio_cells = 2; - gpt->of_gc.gc.ngpio = 1; - gpt->of_gc.gc.direction_input = mpc52xx_gpt_gpio_dir_in; - gpt->of_gc.gc.direction_output = mpc52xx_gpt_gpio_dir_out; - gpt->of_gc.gc.get = mpc52xx_gpt_gpio_get; - gpt->of_gc.gc.set = mpc52xx_gpt_gpio_set; - gpt->of_gc.gc.base = -1; - gpt->of_gc.xlate = of_gpio_simple_xlate; - node->data = &gpt->of_gc; - of_node_get(node); + gpt->gc.ngpio = 1; + gpt->gc.direction_input = mpc52xx_gpt_gpio_dir_in; + gpt->gc.direction_output = mpc52xx_gpt_gpio_dir_out; + gpt->gc.get = mpc52xx_gpt_gpio_get; + gpt->gc.set = mpc52xx_gpt_gpio_set; + gpt->gc.base = -1; + gpt->gc.of_node = node; /* Setup external pin in GPIO mode */ clrsetbits_be32(&gpt->regs->mode, MPC52xx_GPT_MODE_MS_MASK, MPC52xx_GPT_MODE_MS_GPIO); - rc = gpiochip_add(&gpt->of_gc.gc); + rc = gpiochip_add(&gpt->gc); if (rc) dev_err(gpt->dev, "gpiochip_add() failed; rc=%i\n", rc); @@ -723,7 +720,7 @@ static inline int mpc52xx_gpt_wdt_setup(struct mpc52xx_gpt_priv *gpt, /* --------------------------------------------------------------------- * of_platform bus binding code */ -static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev, +static int __devinit mpc52xx_gpt_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct mpc52xx_gpt_priv *gpt; @@ -769,7 +766,7 @@ static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev, return 0; } -static int mpc52xx_gpt_remove(struct of_device *ofdev) +static int mpc52xx_gpt_remove(struct platform_device *ofdev) { return -EBUSY; } diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c index e86aec64450..f4ac213c89c 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c @@ -436,8 +436,8 @@ void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req) } EXPORT_SYMBOL(mpc52xx_lpbfifo_abort); -static int __devinit -mpc52xx_lpbfifo_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit mpc52xx_lpbfifo_probe(struct platform_device *op, + const struct of_device_id *match) { struct resource res; int rc = -ENOMEM; @@ -507,7 +507,7 @@ mpc52xx_lpbfifo_probe(struct of_device *op, const struct of_device_id *match) } -static int __devexit mpc52xx_lpbfifo_remove(struct of_device *op) +static int __devexit mpc52xx_lpbfifo_remove(struct platform_device *op) { if (lpbfifo.dev != &op->dev) return 0; diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c index 9f2e52b36f9..1565e0446dc 100644 --- a/arch/powerpc/platforms/82xx/ep8248e.c +++ b/arch/powerpc/platforms/82xx/ep8248e.c @@ -111,7 +111,7 @@ static struct mdiobb_ctrl ep8248e_mdio_ctrl = { .ops = &ep8248e_mdio_ops, }; -static int __devinit ep8248e_mdio_probe(struct of_device *ofdev, +static int __devinit ep8248e_mdio_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct mii_bus *bus; @@ -154,7 +154,7 @@ err_free_bus: return ret; } -static int ep8248e_mdio_remove(struct of_device *ofdev) +static int ep8248e_mdio_remove(struct platform_device *ofdev) { BUG(); return 0; diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index d119a7c1c17..70798ac911e 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -35,9 +35,8 @@ struct mcu { struct mutex lock; - struct device_node *np; struct i2c_client *client; - struct of_gpio_chip of_gc; + struct gpio_chip gc; u8 reg_ctrl; }; @@ -56,8 +55,7 @@ static void mcu_power_off(void) static void mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) { - struct of_gpio_chip *of_gc = to_of_gpio_chip(gc); - struct mcu *mcu = container_of(of_gc, struct mcu, of_gc); + struct mcu *mcu = container_of(gc, struct mcu, gc); u8 bit = 1 << (4 + gpio); mutex_lock(&mcu->lock); @@ -79,9 +77,7 @@ static int mcu_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) static int mcu_gpiochip_add(struct mcu *mcu) { struct device_node *np; - struct of_gpio_chip *of_gc = &mcu->of_gc; - struct gpio_chip *gc = &of_gc->gc; - int ret; + struct gpio_chip *gc = &mcu->gc; np = of_find_compatible_node(NULL, NULL, "fsl,mcu-mpc8349emitx"); if (!np) @@ -94,32 +90,14 @@ static int mcu_gpiochip_add(struct mcu *mcu) gc->base = -1; gc->set = mcu_gpio_set; gc->direction_output = mcu_gpio_dir_out; - of_gc->gpio_cells = 2; - of_gc->xlate = of_gpio_simple_xlate; + gc->of_node = np; - np->data = of_gc; - mcu->np = np; - - /* - * We don't want to lose the node, its ->data and ->full_name... - * So, if succeeded, we don't put the node here. - */ - ret = gpiochip_add(gc); - if (ret) - of_node_put(np); - return ret; + return gpiochip_add(gc); } static int mcu_gpiochip_remove(struct mcu *mcu) { - int ret; - - ret = gpiochip_remove(&mcu->of_gc.gc); - if (ret) - return ret; - of_node_put(mcu->np); - - return 0; + return gpiochip_remove(&mcu->gc); } static int __devinit mcu_probe(struct i2c_client *client, @@ -182,10 +160,16 @@ static const struct i2c_device_id mcu_ids[] = { }; MODULE_DEVICE_TABLE(i2c, mcu_ids); +static struct of_device_id mcu_of_match_table[] __devinitdata = { + { .compatible = "fsl,mcu-mpc8349emitx", }, + { }, +}; + static struct i2c_driver mcu_driver = { .driver = { .name = "mcu-mpc8349emitx", .owner = THIS_MODULE, + .of_match_table = mcu_of_match_table, }, .probe = mcu_probe, .remove = __devexit_p(mcu_remove), diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index ebe6c353720..75ae77f1af6 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -99,7 +99,7 @@ struct pmc_type { int has_deep_sleep; }; -static struct of_device *pmc_dev; +static struct platform_device *pmc_dev; static int has_deep_sleep, deep_sleeping; static int pmc_irq; static struct mpc83xx_pmc __iomem *pmc_regs; @@ -318,7 +318,7 @@ static struct platform_suspend_ops mpc83xx_suspend_ops = { .end = mpc83xx_suspend_end, }; -static int pmc_probe(struct of_device *ofdev, +static int pmc_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct device_node *np = ofdev->dev.of_node; @@ -396,7 +396,7 @@ out: return ret; } -static int pmc_remove(struct of_device *ofdev) +static int pmc_remove(struct platform_device *ofdev) { return -EPERM; }; diff --git a/arch/powerpc/platforms/86xx/gef_gpio.c b/arch/powerpc/platforms/86xx/gef_gpio.c index b8cb08dbd89..4ff7b1e7bba 100644 --- a/arch/powerpc/platforms/86xx/gef_gpio.c +++ b/arch/powerpc/platforms/86xx/gef_gpio.c @@ -118,12 +118,12 @@ static int __init gef_gpio_init(void) } /* Setup pointers to chip functions */ - gef_gpio_chip->of_gc.gpio_cells = 2; - gef_gpio_chip->of_gc.gc.ngpio = 19; - gef_gpio_chip->of_gc.gc.direction_input = gef_gpio_dir_in; - gef_gpio_chip->of_gc.gc.direction_output = gef_gpio_dir_out; - gef_gpio_chip->of_gc.gc.get = gef_gpio_get; - gef_gpio_chip->of_gc.gc.set = gef_gpio_set; + gef_gpio_chip->gc.of_gpio_n_cells = 2; + gef_gpio_chip->gc.ngpio = 19; + gef_gpio_chip->gc.direction_input = gef_gpio_dir_in; + gef_gpio_chip->gc.direction_output = gef_gpio_dir_out; + gef_gpio_chip->gc.get = gef_gpio_get; + gef_gpio_chip->gc.set = gef_gpio_set; /* This function adds a memory mapped GPIO chip */ retval = of_mm_gpiochip_add(np, gef_gpio_chip); @@ -146,12 +146,12 @@ static int __init gef_gpio_init(void) } /* Setup pointers to chip functions */ - gef_gpio_chip->of_gc.gpio_cells = 2; - gef_gpio_chip->of_gc.gc.ngpio = 6; - gef_gpio_chip->of_gc.gc.direction_input = gef_gpio_dir_in; - gef_gpio_chip->of_gc.gc.direction_output = gef_gpio_dir_out; - gef_gpio_chip->of_gc.gc.get = gef_gpio_get; - gef_gpio_chip->of_gc.gc.set = gef_gpio_set; + gef_gpio_chip->gc.of_gpio_n_cells = 2; + gef_gpio_chip->gc.ngpio = 6; + gef_gpio_chip->gc.direction_input = gef_gpio_dir_in; + gef_gpio_chip->gc.direction_output = gef_gpio_dir_out; + gef_gpio_chip->gc.get = gef_gpio_get; + gef_gpio_chip->gc.set = gef_gpio_set; /* This function adds a memory mapped GPIO chip */ retval = of_mm_gpiochip_add(np, gef_gpio_chip); diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c index fb4eb0df054..03aabc0e16a 100644 --- a/arch/powerpc/platforms/amigaone/setup.c +++ b/arch/powerpc/platforms/amigaone/setup.c @@ -13,12 +13,13 @@ */ #include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/seq_file.h> #include <generated/utsrelease.h> #include <asm/machdep.h> #include <asm/cputable.h> -#include <asm/prom.h> #include <asm/pci-bridge.h> #include <asm/i8259.h> #include <asm/time.h> diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 6257e537861..97085530aa6 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -328,7 +328,7 @@ static struct irq_host_ops msic_host_ops = { .map = msic_host_map, }; -static int axon_msi_shutdown(struct of_device *device) +static int axon_msi_shutdown(struct platform_device *device) { struct axon_msic *msic = dev_get_drvdata(&device->dev); u32 tmp; @@ -342,7 +342,7 @@ static int axon_msi_shutdown(struct of_device *device) return 0; } -static int axon_msi_probe(struct of_device *device, +static int axon_msi_probe(struct platform_device *device, const struct of_device_id *device_id) { struct device_node *dn = device->dev.of_node; diff --git a/arch/powerpc/platforms/cell/beat_iommu.c b/arch/powerpc/platforms/cell/beat_iommu.c index 39d361c5c6d..beec405eb6f 100644 --- a/arch/powerpc/platforms/cell/beat_iommu.c +++ b/arch/powerpc/platforms/cell/beat_iommu.c @@ -108,7 +108,7 @@ static int __init celleb_init_iommu(void) celleb_init_direct_mapping(); set_pci_dma_ops(&dma_direct_ops); ppc_md.pci_dma_dev_setup = celleb_pci_dma_dev_setup; - bus_register_notifier(&of_platform_bus_type, &celleb_of_bus_notifier); + bus_register_notifier(&platform_bus_type, &celleb_of_bus_notifier); return 0; } diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 3712900471b..58b13ce3847 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -1204,7 +1204,7 @@ static int __init cell_iommu_init(void) /* Register callbacks on OF platform device addition/removal * to handle linking them to the right DMA operations */ - bus_register_notifier(&of_platform_bus_type, &cell_of_bus_notifier); + bus_register_notifier(&platform_bus_type, &cell_of_bus_notifier); return 0; } diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c index c5ce02e84c8..1b574904275 100644 --- a/arch/powerpc/platforms/cell/qpace_setup.c +++ b/arch/powerpc/platforms/cell/qpace_setup.c @@ -61,12 +61,24 @@ static void qpace_progress(char *s, unsigned short hex) printk("*** %04x : %s\n", hex, s ? s : ""); } +static const struct of_device_id qpace_bus_ids[] __initdata = { + { .type = "soc", }, + { .compatible = "soc", }, + { .type = "spider", }, + { .type = "axon", }, + { .type = "plb5", }, + { .type = "plb4", }, + { .type = "opb", }, + { .type = "ebc", }, + {}, +}; + static int __init qpace_publish_devices(void) { int node; /* Publish OF platform devices for southbridge IOs */ - of_platform_bus_probe(NULL, NULL, NULL); + of_platform_bus_probe(NULL, qpace_bus_ids, NULL); /* There is no device for the MIC memory controller, thus we create * a platform device for it to attach the EDAC driver to. diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index 50385db586b..691995761b3 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -141,6 +141,18 @@ static int __devinit cell_setup_phb(struct pci_controller *phb) return 0; } +static const struct of_device_id cell_bus_ids[] __initdata = { + { .type = "soc", }, + { .compatible = "soc", }, + { .type = "spider", }, + { .type = "axon", }, + { .type = "plb5", }, + { .type = "plb4", }, + { .type = "opb", }, + { .type = "ebc", }, + {}, +}; + static int __init cell_publish_devices(void) { struct device_node *root = of_find_node_by_path("/"); @@ -148,7 +160,7 @@ static int __init cell_publish_devices(void) int node; /* Publish OF platform devices for southbridge IOs */ - of_platform_bus_probe(NULL, NULL, NULL); + of_platform_bus_probe(NULL, cell_bus_ids, NULL); /* On spider based blades, we need to manually create the OF * platform devices for the PCI host bridges diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c index d2c1d497846..33e5fc7334f 100644 --- a/arch/powerpc/platforms/iseries/mf.c +++ b/arch/powerpc/platforms/iseries/mf.c @@ -30,6 +30,7 @@ #include <linux/init.h> #include <linux/completion.h> #include <linux/delay.h> +#include <linux/proc_fs.h> #include <linux/dma-mapping.h> #include <linux/bcd.h> #include <linux/rtc.h> diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c index 627ee089e75..a5d907b5a4c 100644 --- a/arch/powerpc/platforms/pasemi/gpio_mdio.c +++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c @@ -216,7 +216,7 @@ static int gpio_mdio_reset(struct mii_bus *bus) } -static int __devinit gpio_mdio_probe(struct of_device *ofdev, +static int __devinit gpio_mdio_probe(struct platform_device *ofdev, const struct of_device_id *match) { struct device *dev = &ofdev->dev; @@ -275,7 +275,7 @@ out: } -static int gpio_mdio_remove(struct of_device *dev) +static int gpio_mdio_remove(struct platform_device *dev) { struct mii_bus *bus = dev_get_drvdata(&dev->dev); diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index 79bd3e89dba..39df6ab1735 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -21,6 +21,8 @@ #include <linux/delay.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/spinlock.h> #include <linux/adb.h> #include <linux/pmu.h> diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 630a533d0e5..890d5f72b19 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -46,6 +46,10 @@ struct pmac_irq_hw { unsigned int level; }; +/* Workaround flags for 32bit powermac machines */ +unsigned int of_irq_workarounds; +struct device_node *of_irq_dflt_pic; + /* Default addresses */ static volatile struct pmac_irq_hw __iomem *pmac_irq_hw[4]; @@ -428,6 +432,42 @@ static void __init pmac_pic_probe_oldstyle(void) setup_irq(irq_create_mapping(NULL, 20), &xmon_action); #endif } + +int of_irq_map_oldworld(struct device_node *device, int index, + struct of_irq *out_irq) +{ + const u32 *ints = NULL; + int intlen; + + /* + * Old machines just have a list of interrupt numbers + * and no interrupt-controller nodes. We also have dodgy + * cases where the APPL,interrupts property is completely + * missing behind pci-pci bridges and we have to get it + * from the parent (the bridge itself, as apple just wired + * everything together on these) + */ + while (device) { + ints = of_get_property(device, "AAPL,interrupts", &intlen); + if (ints != NULL) + break; + device = device->parent; + if (device && strcmp(device->type, "pci") != 0) + break; + } + if (ints == NULL) + return -EINVAL; + intlen /= sizeof(u32); + + if (index >= intlen) + return -EINVAL; + + out_irq->controller = NULL; + out_irq->specifier[0] = ints[index]; + out_irq->size = 1; + + return 0; +} #endif /* CONFIG_PPC32 */ static void pmac_u3_cascade(unsigned int irq, struct irq_desc *desc) @@ -559,19 +599,39 @@ static int __init pmac_pic_probe_mpic(void) void __init pmac_pic_init(void) { - unsigned int flags = 0; - /* We configure the OF parsing based on our oldworld vs. newworld * platform type and wether we were booted by BootX. */ #ifdef CONFIG_PPC32 if (!pmac_newworld) - flags |= OF_IMAP_OLDWORLD_MAC; + of_irq_workarounds |= OF_IMAP_OLDWORLD_MAC; if (of_get_property(of_chosen, "linux,bootx", NULL) != NULL) - flags |= OF_IMAP_NO_PHANDLE; -#endif /* CONFIG_PPC_32 */ + of_irq_workarounds |= OF_IMAP_NO_PHANDLE; - of_irq_map_init(flags); + /* If we don't have phandles on a newworld, then try to locate a + * default interrupt controller (happens when booting with BootX). + * We do a first match here, hopefully, that only ever happens on + * machines with one controller. + */ + if (pmac_newworld && (of_irq_workarounds & OF_IMAP_NO_PHANDLE)) { + struct device_node *np; + + for_each_node_with_property(np, "interrupt-controller") { + /* Skip /chosen/interrupt-controller */ + if (strcmp(np->name, "chosen") == 0) + continue; + /* It seems like at least one person wants + * to use BootX on a machine with an AppleKiwi + * controller which happens to pretend to be an + * interrupt controller too. */ + if (strcmp(np->name, "AppleKiwi") == 0) + continue; + /* I think we found one ! */ + of_irq_dflt_pic = np; + break; + } + } +#endif /* CONFIG_PPC32 */ /* We first try to detect Apple's new Core99 chipset, since mac-io * is quite different on those machines and contains an IBM MPIC2. diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 402d2212162..2659a60bd7b 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -60,7 +60,7 @@ static int azfs_major, azfs_minor; struct axon_ram_bank { - struct of_device *device; + struct platform_device *device; struct gendisk *disk; unsigned int irq_id; unsigned long ph_addr; @@ -72,7 +72,7 @@ struct axon_ram_bank { static ssize_t axon_ram_sysfs_ecc(struct device *dev, struct device_attribute *attr, char *buf) { - struct of_device *device = to_of_device(dev); + struct platform_device *device = to_platform_device(dev); struct axon_ram_bank *bank = device->dev.platform_data; BUG_ON(!bank); @@ -90,7 +90,7 @@ static DEVICE_ATTR(ecc, S_IRUGO, axon_ram_sysfs_ecc, NULL); static irqreturn_t axon_ram_irq_handler(int irq, void *dev) { - struct of_device *device = dev; + struct platform_device *device = dev; struct axon_ram_bank *bank = device->dev.platform_data; BUG_ON(!bank); @@ -174,8 +174,8 @@ static const struct block_device_operations axon_ram_devops = { * axon_ram_probe - probe() method for platform driver * @device, @device_id: see of_platform_driver method */ -static int -axon_ram_probe(struct of_device *device, const struct of_device_id *device_id) +static int axon_ram_probe(struct platform_device *device, + const struct of_device_id *device_id) { static int axon_ram_bank_id = -1; struct axon_ram_bank *bank; @@ -304,7 +304,7 @@ failed: * @device: see of_platform_driver method */ static int -axon_ram_remove(struct of_device *device) +axon_ram_remove(struct platform_device *device) { struct axon_ram_bank *bank = device->dev.platform_data; diff --git a/arch/powerpc/sysdev/bestcomm/bestcomm.c b/arch/powerpc/sysdev/bestcomm/bestcomm.c index a7c5c470af1..65025611506 100644 --- a/arch/powerpc/sysdev/bestcomm/bestcomm.c +++ b/arch/powerpc/sysdev/bestcomm/bestcomm.c @@ -365,8 +365,8 @@ bcom_engine_cleanup(void) /* OF platform driver */ /* ======================================================================== */ -static int __devinit -mpc52xx_bcom_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit mpc52xx_bcom_probe(struct platform_device *op, + const struct of_device_id *match) { struct device_node *ofn_sram; struct resource res_bcom; @@ -461,8 +461,7 @@ error_ofput: } -static int -mpc52xx_bcom_remove(struct of_device *op) +static int mpc52xx_bcom_remove(struct platform_device *op) { /* Clean up the engine */ bcom_engine_cleanup(); diff --git a/arch/powerpc/sysdev/bestcomm/sram.c b/arch/powerpc/sysdev/bestcomm/sram.c index 5d74ef7a651..1225012a681 100644 --- a/arch/powerpc/sysdev/bestcomm/sram.c +++ b/arch/powerpc/sysdev/bestcomm/sram.c @@ -11,6 +11,7 @@ * kind, whether express or implied. */ +#include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c index 8d103ca6d6a..00852124ff4 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/sysdev/cpm1.c @@ -621,7 +621,6 @@ int cpm1_gpiochip_add16(struct device_node *np) { struct cpm1_gpio16_chip *cpm1_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL); @@ -631,11 +630,9 @@ int cpm1_gpiochip_add16(struct device_node *np) spin_lock_init(&cpm1_gc->lock); mm_gc = &cpm1_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = cpm1_gpio16_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = 16; gc->direction_input = cpm1_gpio16_dir_in; gc->direction_output = cpm1_gpio16_dir_out; @@ -745,7 +742,6 @@ int cpm1_gpiochip_add32(struct device_node *np) { struct cpm1_gpio32_chip *cpm1_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL); @@ -755,11 +751,9 @@ int cpm1_gpiochip_add32(struct device_node *np) spin_lock_init(&cpm1_gc->lock); mm_gc = &cpm1_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = cpm1_gpio32_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = 32; gc->direction_input = cpm1_gpio32_dir_in; gc->direction_output = cpm1_gpio32_dir_out; diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c index 88b9812c854..2b69aa0315b 100644 --- a/arch/powerpc/sysdev/cpm_common.c +++ b/arch/powerpc/sysdev/cpm_common.c @@ -325,7 +325,6 @@ int cpm2_gpiochip_add32(struct device_node *np) { struct cpm2_gpio32_chip *cpm2_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; cpm2_gc = kzalloc(sizeof(*cpm2_gc), GFP_KERNEL); @@ -335,11 +334,9 @@ int cpm2_gpiochip_add32(struct device_node *np) spin_lock_init(&cpm2_gc->lock); mm_gc = &cpm2_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = cpm2_gpio32_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = 32; gc->direction_input = cpm2_gpio32_dir_in; gc->direction_output = cpm2_gpio32_dir_out; diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c index eca4545dd52..7dd2885321a 100644 --- a/arch/powerpc/sysdev/fsl_gtm.c +++ b/arch/powerpc/sysdev/fsl_gtm.c @@ -14,6 +14,7 @@ */ #include <linux/kernel.h> +#include <linux/err.h> #include <linux/errno.h> #include <linux/list.h> #include <linux/io.h> diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 962c2d8dd8d..87991d3abba 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -250,7 +250,7 @@ unlock: raw_spin_unlock(&desc->lock); } -static int fsl_of_msi_remove(struct of_device *ofdev) +static int fsl_of_msi_remove(struct platform_device *ofdev) { struct fsl_msi *msi = ofdev->dev.platform_data; int virq, i; @@ -274,7 +274,7 @@ static int fsl_of_msi_remove(struct of_device *ofdev) return 0; } -static int __devinit fsl_of_msi_probe(struct of_device *dev, +static int __devinit fsl_of_msi_probe(struct platform_device *dev, const struct of_device_id *match) { struct fsl_msi *msi; diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c index 9082eb921ad..44de8559c97 100644 --- a/arch/powerpc/sysdev/fsl_pmc.c +++ b/arch/powerpc/sysdev/fsl_pmc.c @@ -58,7 +58,8 @@ static struct platform_suspend_ops pmc_suspend_ops = { .enter = pmc_suspend_enter, }; -static int pmc_probe(struct of_device *ofdev, const struct of_device_id *id) +static int pmc_probe(struct platform_device *ofdev, + const struct of_device_id *id) { pmc_regs = of_iomap(ofdev->dev.of_node, 0); if (!pmc_regs) diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 30e1626b2e8..8bd86530ee2 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -1338,7 +1338,7 @@ static inline void fsl_rio_info(struct device *dev, u32 ccsr) * master port with system-specific info, and registers the * master port with the RapidIO subsystem. */ -int fsl_rio_setup(struct of_device *dev) +int fsl_rio_setup(struct platform_device *dev) { struct rio_ops *ops; struct rio_mport *port; @@ -1536,7 +1536,7 @@ err_ops: /* The probe function for RapidIO peer-to-peer network. */ -static int __devinit fsl_of_rio_rpn_probe(struct of_device *dev, +static int __devinit fsl_of_rio_rpn_probe(struct platform_device *dev, const struct of_device_id *match) { int rc; diff --git a/arch/powerpc/sysdev/mpc8xxx_gpio.c b/arch/powerpc/sysdev/mpc8xxx_gpio.c index 83f519655fa..2b69084d0f0 100644 --- a/arch/powerpc/sysdev/mpc8xxx_gpio.c +++ b/arch/powerpc/sysdev/mpc8xxx_gpio.c @@ -257,7 +257,6 @@ static void __init mpc8xxx_add_controller(struct device_node *np) { struct mpc8xxx_gpio_chip *mpc8xxx_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; unsigned hwirq; int ret; @@ -271,11 +270,9 @@ static void __init mpc8xxx_add_controller(struct device_node *np) spin_lock_init(&mpc8xxx_gc->lock); mm_gc = &mpc8xxx_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = mpc8xxx_gpio_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = MPC8XXX_GPIO_PINS; gc->direction_input = mpc8xxx_gpio_dir_in; gc->direction_output = mpc8xxx_gpio_dir_out; diff --git a/arch/powerpc/sysdev/mv64x60_dev.c b/arch/powerpc/sysdev/mv64x60_dev.c index 31acd3b1718..1398bc45499 100644 --- a/arch/powerpc/sysdev/mv64x60_dev.c +++ b/arch/powerpc/sysdev/mv64x60_dev.c @@ -20,12 +20,7 @@ #include <asm/prom.h> -/* - * These functions provide the necessary setup for the mv64x60 drivers. - * These drivers are unusual in that they work on both the MIPS and PowerPC - * architectures. Because of that, the drivers do not support the normal - * PowerPC of_platform_bus_type. They support platform_bus_type instead. - */ +/* These functions provide the necessary setup for the mv64x60 drivers. */ static struct of_device_id __initdata of_mv64x60_devices[] = { { .compatible = "marvell,mv64306-devctrl", }, diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c index d07137a07d7..24a0bb955b1 100644 --- a/arch/powerpc/sysdev/pmi.c +++ b/arch/powerpc/sysdev/pmi.c @@ -43,7 +43,7 @@ struct pmi_data { struct mutex msg_mutex; pmi_message_t msg; struct completion *completion; - struct of_device *dev; + struct platform_device *dev; int irq; u8 __iomem *pmi_reg; struct work_struct work; @@ -121,7 +121,7 @@ static void pmi_notify_handlers(struct work_struct *work) spin_unlock(&data->handler_spinlock); } -static int pmi_of_probe(struct of_device *dev, +static int pmi_of_probe(struct platform_device *dev, const struct of_device_id *match) { struct device_node *np = dev->dev.of_node; @@ -185,7 +185,7 @@ out: return rc; } -static int pmi_of_remove(struct of_device *dev) +static int pmi_of_remove(struct platform_device *dev) { struct pmi_handler *handler, *tmp; diff --git a/arch/powerpc/sysdev/ppc4xx_gpio.c b/arch/powerpc/sysdev/ppc4xx_gpio.c index 3812fc366be..fc65ad1b329 100644 --- a/arch/powerpc/sysdev/ppc4xx_gpio.c +++ b/arch/powerpc/sysdev/ppc4xx_gpio.c @@ -181,7 +181,6 @@ static int __init ppc4xx_add_gpiochips(void) int ret; struct ppc4xx_gpio_chip *ppc4xx_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; ppc4xx_gc = kzalloc(sizeof(*ppc4xx_gc), GFP_KERNEL); @@ -193,10 +192,8 @@ static int __init ppc4xx_add_gpiochips(void) spin_lock_init(&ppc4xx_gc->lock); mm_gc = &ppc4xx_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; - of_gc->gpio_cells = 2; gc->ngpio = 32; gc->direction_input = ppc4xx_gpio_dir_in; gc->direction_output = ppc4xx_gpio_dir_out; diff --git a/arch/powerpc/sysdev/qe_lib/gpio.c b/arch/powerpc/sysdev/qe_lib/gpio.c index dc8f8d61807..36bf845df12 100644 --- a/arch/powerpc/sysdev/qe_lib/gpio.c +++ b/arch/powerpc/sysdev/qe_lib/gpio.c @@ -138,8 +138,8 @@ struct qe_pin { struct qe_pin *qe_pin_request(struct device_node *np, int index) { struct qe_pin *qe_pin; - struct device_node *gc; - struct of_gpio_chip *of_gc = NULL; + struct device_node *gpio_np; + struct gpio_chip *gc; struct of_mm_gpio_chip *mm_gc; struct qe_gpio_chip *qe_gc; int err; @@ -155,40 +155,40 @@ struct qe_pin *qe_pin_request(struct device_node *np, int index) } err = of_parse_phandles_with_args(np, "gpios", "#gpio-cells", index, - &gc, &gpio_spec); + &gpio_np, &gpio_spec); if (err) { pr_debug("%s: can't parse gpios property\n", __func__); goto err0; } - if (!of_device_is_compatible(gc, "fsl,mpc8323-qe-pario-bank")) { + if (!of_device_is_compatible(gpio_np, "fsl,mpc8323-qe-pario-bank")) { pr_debug("%s: tried to get a non-qe pin\n", __func__); err = -EINVAL; goto err1; } - of_gc = gc->data; - if (!of_gc) { + gc = of_node_to_gpiochip(gpio_np); + if (!gc) { pr_debug("%s: gpio controller %s isn't registered\n", - np->full_name, gc->full_name); + np->full_name, gpio_np->full_name); err = -ENODEV; goto err1; } - gpio_cells = of_get_property(gc, "#gpio-cells", &size); + gpio_cells = of_get_property(gpio_np, "#gpio-cells", &size); if (!gpio_cells || size != sizeof(*gpio_cells) || - *gpio_cells != of_gc->gpio_cells) { + *gpio_cells != gc->of_gpio_n_cells) { pr_debug("%s: wrong #gpio-cells for %s\n", - np->full_name, gc->full_name); + np->full_name, gpio_np->full_name); err = -EINVAL; goto err1; } - err = of_gc->xlate(of_gc, np, gpio_spec, NULL); + err = gc->of_xlate(gc, np, gpio_spec, NULL); if (err < 0) goto err1; - mm_gc = to_of_mm_gpio_chip(&of_gc->gc); + mm_gc = to_of_mm_gpio_chip(gc); qe_gc = to_qe_gpio_chip(mm_gc); spin_lock_irqsave(&qe_gc->lock, flags); @@ -206,7 +206,7 @@ struct qe_pin *qe_pin_request(struct device_node *np, int index) if (!err) return qe_pin; err1: - of_node_put(gc); + of_node_put(gpio_np); err0: kfree(qe_pin); pr_debug("%s failed with status %d\n", __func__, err); @@ -307,7 +307,6 @@ static int __init qe_add_gpiochips(void) int ret; struct qe_gpio_chip *qe_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; qe_gc = kzalloc(sizeof(*qe_gc), GFP_KERNEL); @@ -319,11 +318,9 @@ static int __init qe_add_gpiochips(void) spin_lock_init(&qe_gc->lock); mm_gc = &qe_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = qe_gpio_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = QE_PIO_PINS; gc->direction_input = qe_gpio_dir_in; gc->direction_output = qe_gpio_dir_out; diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c index 093e0ae1a94..3da8014931c 100644 --- a/arch/powerpc/sysdev/qe_lib/qe.c +++ b/arch/powerpc/sysdev/qe_lib/qe.c @@ -651,14 +651,15 @@ unsigned int qe_get_num_of_snums(void) EXPORT_SYMBOL(qe_get_num_of_snums); #if defined(CONFIG_SUSPEND) && defined(CONFIG_PPC_85xx) -static int qe_resume(struct of_device *ofdev) +static int qe_resume(struct platform_device *ofdev) { if (!qe_alive_during_sleep()) qe_reset(); return 0; } -static int qe_probe(struct of_device *ofdev, const struct of_device_id *id) +static int qe_probe(struct platform_device *ofdev, + const struct of_device_id *id) { return 0; } diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c index d5fb173e588..b6defda5ccc 100644 --- a/arch/powerpc/sysdev/simple_gpio.c +++ b/arch/powerpc/sysdev/simple_gpio.c @@ -91,7 +91,6 @@ static int __init u8_simple_gpiochip_add(struct device_node *np) int ret; struct u8_gpio_chip *u8_gc; struct of_mm_gpio_chip *mm_gc; - struct of_gpio_chip *of_gc; struct gpio_chip *gc; u8_gc = kzalloc(sizeof(*u8_gc), GFP_KERNEL); @@ -101,11 +100,9 @@ static int __init u8_simple_gpiochip_add(struct device_node *np) spin_lock_init(&u8_gc->lock); mm_gc = &u8_gc->mm_gc; - of_gc = &mm_gc->of_gc; - gc = &of_gc->gc; + gc = &mm_gc->gc; mm_gc->save_regs = u8_gpio_save_regs; - of_gc->gpio_cells = 2; gc->ngpio = 8; gc->direction_input = u8_gpio_dir_in; gc->direction_output = u8_gpio_dir_out; diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 30c5f01f93b..0c9e6c6d2a6 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -24,7 +24,8 @@ CHECKFLAGS += -D__s390__ -msize-long else LD_BFD := elf64-s390 LDFLAGS := -m elf64_s390 -MODFLAGS += -fpic -D__PIC__ +KBUILD_AFLAGS_MODULE += -fpic -D__PIC__ +KBUILD_CFLAGS_MODULE += -fpic -D__PIC__ KBUILD_CFLAGS += -m64 KBUILD_AFLAGS += -m64 UTS_MACHINE := s390x diff --git a/arch/s390/include/asm/local64.h b/arch/s390/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/s390/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/score/Makefile b/arch/score/Makefile index 68e0cd06d5c..d77dc639d8e 100644 --- a/arch/score/Makefile +++ b/arch/score/Makefile @@ -20,7 +20,8 @@ cflags-y += -G0 -pipe -mel -mnhwloop -D__SCOREEL__ \ # KBUILD_AFLAGS += $(cflags-y) KBUILD_CFLAGS += $(cflags-y) -MODFLAGS += -mlong-calls +KBUILD_AFLAGS_MODULE += -mlong-calls +KBUILD_CFLAGS_MODULE += -mlong-calls LDFLAGS += --oformat elf32-littlescore LDFLAGS_vmlinux += -G0 -static -nostdlib diff --git a/arch/score/include/asm/local64.h b/arch/score/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/score/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/sh/include/asm/local64.h b/arch/sh/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/sh/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 81b6de41ae5..7a3dc356725 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -185,10 +185,10 @@ static void sh_perf_event_update(struct perf_event *event, * this is the simplest approach for maintaining consistency. */ again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); new_raw_count = sh_pmu->read(idx); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; @@ -203,7 +203,7 @@ again: delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - atomic64_add(delta, &event->count); + local64_add(delta, &event->count); } static void sh_pmu_disable(struct perf_event *event) diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c0015db247b..ba068c833e5 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -18,6 +18,7 @@ config 64BIT config SPARC bool default y + select OF select HAVE_IDE select HAVE_OPROFILE select HAVE_ARCH_KGDB if !SMP || SPARC64 @@ -148,9 +149,6 @@ config GENERIC_GPIO config ARCH_NO_VIRT_TO_BUS def_bool y -config OF - def_bool y - config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y if SPARC64 diff --git a/arch/sparc/include/asm/device.h b/arch/sparc/include/asm/device.h index d4c45214741..daa6a8a5e9c 100644 --- a/arch/sparc/include/asm/device.h +++ b/arch/sparc/include/asm/device.h @@ -6,18 +6,25 @@ #ifndef _ASM_SPARC_DEVICE_H #define _ASM_SPARC_DEVICE_H +#include <asm/openprom.h> + struct device_node; -struct of_device; +struct platform_device; struct dev_archdata { void *iommu; void *stc; void *host_controller; - struct of_device *op; + struct platform_device *op; int numa_node; }; +extern void of_propagate_archdata(struct platform_device *bus); + struct pdev_archdata { + struct resource resource[PROMREG_MAX]; + unsigned int irqs[PROMINTR_MAX]; + int num_irqs; }; #endif /* _ASM_SPARC_DEVICE_H */ diff --git a/arch/sparc/include/asm/floppy_64.h b/arch/sparc/include/asm/floppy_64.h index 8fac3ab22f3..6597ce874d7 100644 --- a/arch/sparc/include/asm/floppy_64.h +++ b/arch/sparc/include/asm/floppy_64.h @@ -43,7 +43,7 @@ struct sun_flpy_controller { /* You'll only ever find one controller on an Ultra anyways. */ static struct sun_flpy_controller *sun_fdc = (struct sun_flpy_controller *)-1; unsigned long fdc_status; -static struct of_device *floppy_op = NULL; +static struct platform_device *floppy_op = NULL; struct sun_floppy_ops { unsigned char (*fd_inb) (unsigned long port); @@ -548,7 +548,7 @@ static unsigned long __init sun_floppy_init(void) { static int initialized = 0; struct device_node *dp; - struct of_device *op; + struct platform_device *op; const char *prop; char state[128]; @@ -567,7 +567,7 @@ static unsigned long __init sun_floppy_init(void) } if (op) { floppy_op = op; - FLOPPY_IRQ = op->irqs[0]; + FLOPPY_IRQ = op->archdata.irqs[0]; } else { struct device_node *ebus_dp; void __iomem *auxio_reg; @@ -593,7 +593,7 @@ static unsigned long __init sun_floppy_init(void) if (state_prop && !strncmp(state_prop, "disabled", 8)) return 0; - FLOPPY_IRQ = op->irqs[0]; + FLOPPY_IRQ = op->archdata.irqs[0]; /* Make sure the high density bit is set, some systems * (most notably Ultra5/Ultra10) come up with it clear. @@ -661,7 +661,7 @@ static unsigned long __init sun_floppy_init(void) config = 0; for (dp = ebus_dp->child; dp; dp = dp->sibling) { if (!strcmp(dp->name, "ecpp")) { - struct of_device *ecpp_op; + struct platform_device *ecpp_op; ecpp_op = of_find_device_by_node(dp); if (ecpp_op) diff --git a/arch/sparc/include/asm/local64.h b/arch/sparc/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/sparc/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/sparc/include/asm/of_device.h b/arch/sparc/include/asm/of_device.h deleted file mode 100644 index f320246a058..00000000000 --- a/arch/sparc/include/asm/of_device.h +++ /dev/null @@ -1,38 +0,0 @@ -#ifndef _ASM_SPARC_OF_DEVICE_H -#define _ASM_SPARC_OF_DEVICE_H -#ifdef __KERNEL__ - -#include <linux/device.h> -#include <linux/of.h> -#include <linux/mod_devicetable.h> -#include <asm/openprom.h> - -/* - * The of_device is a kind of "base class" that is a superset of - * struct device for use by devices attached to an OF node and - * probed using OF properties. - */ -struct of_device -{ - struct device dev; - struct resource resource[PROMREG_MAX]; - unsigned int irqs[PROMINTR_MAX]; - int num_irqs; - - void *sysdata; - - int slot; - int portid; - int clock_freq; -}; - -extern void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name); -extern void of_iounmap(struct resource *res, void __iomem *base, unsigned long size); - -extern void of_propagate_archdata(struct of_device *bus); - -/* This is just here during the transition */ -#include <linux/of_platform.h> - -#endif /* __KERNEL__ */ -#endif /* _ASM_SPARC_OF_DEVICE_H */ diff --git a/arch/sparc/include/asm/of_platform.h b/arch/sparc/include/asm/of_platform.h deleted file mode 100644 index 90da99059f8..00000000000 --- a/arch/sparc/include/asm/of_platform.h +++ /dev/null @@ -1,18 +0,0 @@ -#ifndef ___ASM_SPARC_OF_PLATFORM_H -#define ___ASM_SPARC_OF_PLATFORM_H -/* - * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corp. - * <benh@kernel.crashing.org> - * Modified for Sparc by merging parts of asm/of_device.h - * by Stephen Rothwell - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#define of_bus_type of_platform_bus_type /* for compatibility */ - -#endif diff --git a/arch/sparc/include/asm/parport.h b/arch/sparc/include/asm/parport.h index c333b8d0949..4f7afa01b2a 100644 --- a/arch/sparc/include/asm/parport.h +++ b/arch/sparc/include/asm/parport.h @@ -103,7 +103,7 @@ static inline unsigned int get_dma_residue(unsigned int dmanr) return ebus_dma_residue(&sparc_ebus_dmas[dmanr].info); } -static int __devinit ecpp_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit ecpp_probe(struct platform_device *op, const struct of_device_id *match) { unsigned long base = op->resource[0].start; unsigned long config = op->resource[1].start; @@ -116,7 +116,7 @@ static int __devinit ecpp_probe(struct of_device *op, const struct of_device_id parent = op->dev.of_node->parent; if (!strcmp(parent->name, "dma")) { p = parport_pc_probe_port(base, base + 0x400, - op->irqs[0], PARPORT_DMA_NOFIFO, + op->archdata.irqs[0], PARPORT_DMA_NOFIFO, op->dev.parent->parent, 0); if (!p) return -ENOMEM; @@ -166,7 +166,7 @@ static int __devinit ecpp_probe(struct of_device *op, const struct of_device_id 0, PTR_LPT_REG_DIR); p = parport_pc_probe_port(base, base + 0x400, - op->irqs[0], + op->archdata.irqs[0], slot, op->dev.parent, 0); @@ -192,7 +192,7 @@ out_err: return err; } -static int __devexit ecpp_remove(struct of_device *op) +static int __devexit ecpp_remove(struct platform_device *op) { struct parport *p = dev_get_drvdata(&op->dev); int slot = p->dma; @@ -243,9 +243,7 @@ static struct of_platform_driver ecpp_driver = { static int parport_pc_find_nonpci_ports(int autoirq, int autodma) { - of_register_driver(&ecpp_driver, &of_bus_type); - - return 0; + return of_register_platform_driver(&ecpp_driver); } #endif /* !(_ASM_SPARC64_PARPORT_H */ diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h index 7e2669894ce..74c4e0cd889 100644 --- a/arch/sparc/include/asm/perf_event.h +++ b/arch/sparc/include/asm/perf_event.h @@ -6,7 +6,15 @@ extern void set_perf_event_pending(void); #define PERF_EVENT_INDEX_OFFSET 0 #ifdef CONFIG_PERF_EVENTS +#include <asm/ptrace.h> + extern void init_hw_perf_events(void); + +extern void +__perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); + +#define perf_arch_fetch_caller_regs(pt_regs, ip) \ + __perf_arch_fetch_caller_regs(pt_regs, ip, 1); #else static inline void init_hw_perf_events(void) { } #endif diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h index f845828ca4c..291f12575ed 100644 --- a/arch/sparc/include/asm/prom.h +++ b/arch/sparc/include/asm/prom.h @@ -43,20 +43,22 @@ extern int of_getintprop_default(struct device_node *np, extern int of_find_in_proplist(const char *list, const char *match, int len); #ifdef CONFIG_NUMA extern int of_node_to_nid(struct device_node *dp); -#else -#define of_node_to_nid(dp) (-1) +#define of_node_to_nid of_node_to_nid #endif extern void prom_build_devicetree(void); extern void of_populate_present_mask(void); extern void of_fill_in_cpu_data(void); +struct resource; +extern void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name); +extern void of_iounmap(struct resource *res, void __iomem *base, unsigned long size); + /* These routines are here to provide compatibility with how powerpc * handles IRQ mapping for OF device nodes. We precompute and permanently - * register them in the of_device objects, whereas powerpc computes them + * register them in the platform_device objects, whereas powerpc computes them * on request. */ -extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); static inline void irq_dispose_mapping(unsigned int virq) { } diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c index b27476caa13..2c0046ecc71 100644 --- a/arch/sparc/kernel/apc.c +++ b/arch/sparc/kernel/apc.c @@ -68,7 +68,7 @@ static void apc_swift_idle(void) #endif } -static inline void apc_free(struct of_device *op) +static inline void apc_free(struct platform_device *op) { of_iounmap(&op->resource[0], regs, resource_size(&op->resource[0])); } @@ -136,7 +136,7 @@ static const struct file_operations apc_fops = { static struct miscdevice apc_miscdev = { APC_MINOR, APC_DEVNAME, &apc_fops }; -static int __devinit apc_probe(struct of_device *op, +static int __devinit apc_probe(struct platform_device *op, const struct of_device_id *match) { int err; @@ -184,7 +184,7 @@ static struct of_platform_driver apc_driver = { static int __init apc_init(void) { - return of_register_driver(&apc_driver, &of_bus_type); + return of_register_platform_driver(&apc_driver); } /* This driver is not critical to the boot process diff --git a/arch/sparc/kernel/auxio_64.c b/arch/sparc/kernel/auxio_64.c index ddc84128b3c..3efd3c5af6a 100644 --- a/arch/sparc/kernel/auxio_64.c +++ b/arch/sparc/kernel/auxio_64.c @@ -102,7 +102,8 @@ static struct of_device_id __initdata auxio_match[] = { MODULE_DEVICE_TABLE(of, auxio_match); -static int __devinit auxio_probe(struct of_device *dev, const struct of_device_id *match) +static int __devinit auxio_probe(struct platform_device *dev, + const struct of_device_id *match) { struct device_node *dp = dev->dev.of_node; unsigned long size; @@ -142,7 +143,7 @@ static struct of_platform_driver auxio_driver = { static int __init auxio_init(void) { - return of_register_driver(&auxio_driver, &of_platform_bus_type); + return of_register_platform_driver(&auxio_driver); } /* Must be after subsys_initcall() so that busses are probed. Must diff --git a/arch/sparc/kernel/central.c b/arch/sparc/kernel/central.c index 434335f6582..cfa2624c533 100644 --- a/arch/sparc/kernel/central.c +++ b/arch/sparc/kernel/central.c @@ -59,7 +59,7 @@ static int __devinit clock_board_calc_nslots(struct clock_board *p) } } -static int __devinit clock_board_probe(struct of_device *op, +static int __devinit clock_board_probe(struct platform_device *op, const struct of_device_id *match) { struct clock_board *p = kzalloc(sizeof(*p), GFP_KERNEL); @@ -157,7 +157,7 @@ static struct of_platform_driver clock_board_driver = { }, }; -static int __devinit fhc_probe(struct of_device *op, +static int __devinit fhc_probe(struct platform_device *op, const struct of_device_id *match) { struct fhc *p = kzalloc(sizeof(*p), GFP_KERNEL); @@ -265,8 +265,8 @@ static struct of_platform_driver fhc_driver = { static int __init sunfire_init(void) { - (void) of_register_driver(&fhc_driver, &of_platform_bus_type); - (void) of_register_driver(&clock_board_driver, &of_platform_bus_type); + (void) of_register_platform_driver(&fhc_driver); + (void) of_register_platform_driver(&clock_board_driver); return 0; } diff --git a/arch/sparc/kernel/chmc.c b/arch/sparc/kernel/chmc.c index 870cb65b3f2..08c466ebb32 100644 --- a/arch/sparc/kernel/chmc.c +++ b/arch/sparc/kernel/chmc.c @@ -392,7 +392,7 @@ static void __devinit jbusmc_construct_dimm_groups(struct jbusmc *p, } } -static int __devinit jbusmc_probe(struct of_device *op, +static int __devinit jbusmc_probe(struct platform_device *op, const struct of_device_id *match) { const struct linux_prom64_registers *mem_regs; @@ -690,7 +690,7 @@ static void chmc_fetch_decode_regs(struct chmc *p) chmc_read_mcreg(p, CHMCTRL_DECODE4)); } -static int __devinit chmc_probe(struct of_device *op, +static int __devinit chmc_probe(struct platform_device *op, const struct of_device_id *match) { struct device_node *dp = op->dev.of_node; @@ -765,7 +765,7 @@ out_free: goto out; } -static int __devinit us3mc_probe(struct of_device *op, +static int __devinit us3mc_probe(struct platform_device *op, const struct of_device_id *match) { if (mc_type == MC_TYPE_SAFARI) @@ -775,21 +775,21 @@ static int __devinit us3mc_probe(struct of_device *op, return -ENODEV; } -static void __devexit chmc_destroy(struct of_device *op, struct chmc *p) +static void __devexit chmc_destroy(struct platform_device *op, struct chmc *p) { list_del(&p->list); of_iounmap(&op->resource[0], p->regs, 0x48); kfree(p); } -static void __devexit jbusmc_destroy(struct of_device *op, struct jbusmc *p) +static void __devexit jbusmc_destroy(struct platform_device *op, struct jbusmc *p) { mc_list_del(&p->list); of_iounmap(&op->resource[0], p->regs, JBUSMC_REGS_SIZE); kfree(p); } -static int __devexit us3mc_remove(struct of_device *op) +static int __devexit us3mc_remove(struct platform_device *op) { void *p = dev_get_drvdata(&op->dev); @@ -848,7 +848,7 @@ static int __init us3mc_init(void) ret = register_dimm_printer(us3mc_dimm_printer); if (!ret) { - ret = of_register_driver(&us3mc_driver, &of_bus_type); + ret = of_register_platform_driver(&us3mc_driver); if (ret) unregister_dimm_printer(us3mc_dimm_printer); } @@ -859,7 +859,7 @@ static void __exit us3mc_cleanup(void) { if (us3mc_platform()) { unregister_dimm_printer(us3mc_dimm_printer); - of_unregister_driver(&us3mc_driver); + of_unregister_platform_driver(&us3mc_driver); } } diff --git a/arch/sparc/kernel/helpers.S b/arch/sparc/kernel/helpers.S index 92090cc9e82..682fee06a16 100644 --- a/arch/sparc/kernel/helpers.S +++ b/arch/sparc/kernel/helpers.S @@ -47,9 +47,9 @@ stack_trace_flush: .size stack_trace_flush,.-stack_trace_flush #ifdef CONFIG_PERF_EVENTS - .globl perf_arch_fetch_caller_regs - .type perf_arch_fetch_caller_regs,#function -perf_arch_fetch_caller_regs: + .globl __perf_arch_fetch_caller_regs + .type __perf_arch_fetch_caller_regs,#function +__perf_arch_fetch_caller_regs: /* We always read the %pstate into %o5 since we will use * that to construct a fake %tstate to store into the regs. */ diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 703e4aa9bc3..41f7e4e0f72 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -253,7 +253,7 @@ EXPORT_SYMBOL(sbus_set_sbus64); static void *sbus_alloc_coherent(struct device *dev, size_t len, dma_addr_t *dma_addrp, gfp_t gfp) { - struct of_device *op = to_of_device(dev); + struct platform_device *op = to_platform_device(dev); unsigned long len_total = (len + PAGE_SIZE-1) & PAGE_MASK; unsigned long va; struct resource *res; diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c index 47e63f1e719..2d055a1e9cc 100644 --- a/arch/sparc/kernel/of_device_32.c +++ b/arch/sparc/kernel/of_device_32.c @@ -241,10 +241,10 @@ static int __init use_1to1_mapping(struct device_node *pp) static int of_resource_verbose; -static void __init build_device_resources(struct of_device *op, +static void __init build_device_resources(struct platform_device *op, struct device *parent) { - struct of_device *p_op; + struct platform_device *p_op; struct of_bus *bus; int na, ns; int index, num_reg; @@ -253,7 +253,7 @@ static void __init build_device_resources(struct of_device *op, if (!parent) return; - p_op = to_of_device(parent); + p_op = to_platform_device(parent); bus = of_match_bus(p_op->dev.of_node); bus->count_cells(op->dev.of_node, &na, &ns); @@ -267,6 +267,8 @@ static void __init build_device_resources(struct of_device *op, /* Conver to num-entries. */ num_reg /= na + ns; + op->resource = op->archdata.resource; + op->num_resources = num_reg; for (index = 0; index < num_reg; index++) { struct resource *r = &op->resource[index]; u32 addr[OF_MAX_ADDR_CELLS]; @@ -333,10 +335,10 @@ static void __init build_device_resources(struct of_device *op, } } -static struct of_device * __init scan_one_device(struct device_node *dp, +static struct platform_device * __init scan_one_device(struct device_node *dp, struct device *parent) { - struct of_device *op = kzalloc(sizeof(*op), GFP_KERNEL); + struct platform_device *op = kzalloc(sizeof(*op), GFP_KERNEL); const struct linux_prom_irqs *intr; struct dev_archdata *sd; int len, i; @@ -349,27 +351,21 @@ static struct of_device * __init scan_one_device(struct device_node *dp, op->dev.of_node = dp; - op->clock_freq = of_getintprop_default(dp, "clock-frequency", - (25*1000*1000)); - op->portid = of_getintprop_default(dp, "upa-portid", -1); - if (op->portid == -1) - op->portid = of_getintprop_default(dp, "portid", -1); - intr = of_get_property(dp, "intr", &len); if (intr) { - op->num_irqs = len / sizeof(struct linux_prom_irqs); - for (i = 0; i < op->num_irqs; i++) - op->irqs[i] = intr[i].pri; + op->archdata.num_irqs = len / sizeof(struct linux_prom_irqs); + for (i = 0; i < op->archdata.num_irqs; i++) + op->archdata.irqs[i] = intr[i].pri; } else { const unsigned int *irq = of_get_property(dp, "interrupts", &len); if (irq) { - op->num_irqs = len / sizeof(unsigned int); - for (i = 0; i < op->num_irqs; i++) - op->irqs[i] = irq[i]; + op->archdata.num_irqs = len / sizeof(unsigned int); + for (i = 0; i < op->archdata.num_irqs; i++) + op->archdata.irqs[i] = irq[i]; } else { - op->num_irqs = 0; + op->archdata.num_irqs = 0; } } if (sparc_cpu_model == sun4d) { @@ -411,8 +407,8 @@ static struct of_device * __init scan_one_device(struct device_node *dp, goto build_resources; } - for (i = 0; i < op->num_irqs; i++) { - int this_irq = op->irqs[i]; + for (i = 0; i < op->archdata.num_irqs; i++) { + int this_irq = op->archdata.irqs[i]; int sbusl = pil_to_sbus[this_irq]; if (sbusl) @@ -420,7 +416,7 @@ static struct of_device * __init scan_one_device(struct device_node *dp, (sbusl << 2) + slot); - op->irqs[i] = this_irq; + op->archdata.irqs[i] = this_irq; } } @@ -428,7 +424,7 @@ build_resources: build_device_resources(op, parent); op->dev.parent = parent; - op->dev.bus = &of_platform_bus_type; + op->dev.bus = &platform_bus_type; if (!parent) dev_set_name(&op->dev, "root"); else @@ -447,7 +443,7 @@ build_resources: static void __init scan_tree(struct device_node *dp, struct device *parent) { while (dp) { - struct of_device *op = scan_one_device(dp, parent); + struct platform_device *op = scan_one_device(dp, parent); if (op) scan_tree(dp->child, &op->dev); @@ -456,30 +452,19 @@ static void __init scan_tree(struct device_node *dp, struct device *parent) } } -static void __init scan_of_devices(void) +static int __init scan_of_devices(void) { struct device_node *root = of_find_node_by_path("/"); - struct of_device *parent; + struct platform_device *parent; parent = scan_one_device(root, NULL); if (!parent) - return; + return 0; scan_tree(root->child, &parent->dev); + return 0; } - -static int __init of_bus_driver_init(void) -{ - int err; - - err = of_bus_type_init(&of_platform_bus_type, "of"); - if (!err) - scan_of_devices(); - - return err; -} - -postcore_initcall(of_bus_driver_init); +postcore_initcall(scan_of_devices); static int __init of_debug(char *str) { diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c index 1dae8079f72..63cd4e5d47c 100644 --- a/arch/sparc/kernel/of_device_64.c +++ b/arch/sparc/kernel/of_device_64.c @@ -310,10 +310,10 @@ static int __init use_1to1_mapping(struct device_node *pp) static int of_resource_verbose; -static void __init build_device_resources(struct of_device *op, +static void __init build_device_resources(struct platform_device *op, struct device *parent) { - struct of_device *p_op; + struct platform_device *p_op; struct of_bus *bus; int na, ns; int index, num_reg; @@ -322,7 +322,7 @@ static void __init build_device_resources(struct of_device *op, if (!parent) return; - p_op = to_of_device(parent); + p_op = to_platform_device(parent); bus = of_match_bus(p_op->dev.of_node); bus->count_cells(op->dev.of_node, &na, &ns); @@ -344,6 +344,8 @@ static void __init build_device_resources(struct of_device *op, num_reg = PROMREG_MAX; } + op->resource = op->archdata.resource; + op->num_resources = num_reg; for (index = 0; index < num_reg; index++) { struct resource *r = &op->resource[index]; u32 addr[OF_MAX_ADDR_CELLS]; @@ -526,7 +528,7 @@ static unsigned int __init pci_irq_swizzle(struct device_node *dp, static int of_irq_verbose; -static unsigned int __init build_one_device_irq(struct of_device *op, +static unsigned int __init build_one_device_irq(struct platform_device *op, struct device *parent, unsigned int irq) { @@ -628,10 +630,10 @@ out: return irq; } -static struct of_device * __init scan_one_device(struct device_node *dp, +static struct platform_device * __init scan_one_device(struct device_node *dp, struct device *parent) { - struct of_device *op = kzalloc(sizeof(*op), GFP_KERNEL); + struct platform_device *op = kzalloc(sizeof(*op), GFP_KERNEL); const unsigned int *irq; struct dev_archdata *sd; int len, i; @@ -644,34 +646,28 @@ static struct of_device * __init scan_one_device(struct device_node *dp, op->dev.of_node = dp; - op->clock_freq = of_getintprop_default(dp, "clock-frequency", - (25*1000*1000)); - op->portid = of_getintprop_default(dp, "upa-portid", -1); - if (op->portid == -1) - op->portid = of_getintprop_default(dp, "portid", -1); - irq = of_get_property(dp, "interrupts", &len); if (irq) { - op->num_irqs = len / 4; + op->archdata.num_irqs = len / 4; /* Prevent overrunning the op->irqs[] array. */ - if (op->num_irqs > PROMINTR_MAX) { + if (op->archdata.num_irqs > PROMINTR_MAX) { printk(KERN_WARNING "%s: Too many irqs (%d), " "limiting to %d.\n", - dp->full_name, op->num_irqs, PROMINTR_MAX); - op->num_irqs = PROMINTR_MAX; + dp->full_name, op->archdata.num_irqs, PROMINTR_MAX); + op->archdata.num_irqs = PROMINTR_MAX; } - memcpy(op->irqs, irq, op->num_irqs * 4); + memcpy(op->archdata.irqs, irq, op->archdata.num_irqs * 4); } else { - op->num_irqs = 0; + op->archdata.num_irqs = 0; } build_device_resources(op, parent); - for (i = 0; i < op->num_irqs; i++) - op->irqs[i] = build_one_device_irq(op, parent, op->irqs[i]); + for (i = 0; i < op->archdata.num_irqs; i++) + op->archdata.irqs[i] = build_one_device_irq(op, parent, op->archdata.irqs[i]); op->dev.parent = parent; - op->dev.bus = &of_platform_bus_type; + op->dev.bus = &platform_bus_type; if (!parent) dev_set_name(&op->dev, "root"); else @@ -690,7 +686,7 @@ static struct of_device * __init scan_one_device(struct device_node *dp, static void __init scan_tree(struct device_node *dp, struct device *parent) { while (dp) { - struct of_device *op = scan_one_device(dp, parent); + struct platform_device *op = scan_one_device(dp, parent); if (op) scan_tree(dp->child, &op->dev); @@ -699,30 +695,19 @@ static void __init scan_tree(struct device_node *dp, struct device *parent) } } -static void __init scan_of_devices(void) +static int __init scan_of_devices(void) { struct device_node *root = of_find_node_by_path("/"); - struct of_device *parent; + struct platform_device *parent; parent = scan_one_device(root, NULL); if (!parent) - return; + return 0; scan_tree(root->child, &parent->dev); + return 0; } - -static int __init of_bus_driver_init(void) -{ - int err; - - err = of_bus_type_init(&of_platform_bus_type, "of"); - if (!err) - scan_of_devices(); - - return err; -} - -postcore_initcall(of_bus_driver_init); +postcore_initcall(scan_of_devices); static int __init of_debug(char *str) { diff --git a/arch/sparc/kernel/of_device_common.c b/arch/sparc/kernel/of_device_common.c index 10c6c36a6e7..49ddff56cb0 100644 --- a/arch/sparc/kernel/of_device_common.c +++ b/arch/sparc/kernel/of_device_common.c @@ -11,48 +11,28 @@ #include "of_device_common.h" -static int node_match(struct device *dev, void *data) -{ - struct of_device *op = to_of_device(dev); - struct device_node *dp = data; - - return (op->dev.of_node == dp); -} - -struct of_device *of_find_device_by_node(struct device_node *dp) -{ - struct device *dev = bus_find_device(&of_platform_bus_type, NULL, - dp, node_match); - - if (dev) - return to_of_device(dev); - - return NULL; -} -EXPORT_SYMBOL(of_find_device_by_node); - unsigned int irq_of_parse_and_map(struct device_node *node, int index) { - struct of_device *op = of_find_device_by_node(node); + struct platform_device *op = of_find_device_by_node(node); - if (!op || index >= op->num_irqs) + if (!op || index >= op->archdata.num_irqs) return 0; - return op->irqs[index]; + return op->archdata.irqs[index]; } EXPORT_SYMBOL(irq_of_parse_and_map); /* Take the archdata values for IOMMU, STC, and HOSTDATA found in - * BUS and propagate to all child of_device objects. + * BUS and propagate to all child platform_device objects. */ -void of_propagate_archdata(struct of_device *bus) +void of_propagate_archdata(struct platform_device *bus) { struct dev_archdata *bus_sd = &bus->dev.archdata; struct device_node *bus_dp = bus->dev.of_node; struct device_node *dp; for (dp = bus_dp->child; dp; dp = dp->sibling) { - struct of_device *op = of_find_device_by_node(dp); + struct platform_device *op = of_find_device_by_node(dp); op->dev.archdata.iommu = bus_sd->iommu; op->dev.archdata.stc = bus_sd->stc; @@ -64,9 +44,6 @@ void of_propagate_archdata(struct of_device *bus) } } -struct bus_type of_platform_bus_type; -EXPORT_SYMBOL(of_platform_bus_type); - static void get_cells(struct device_node *dp, int *addrc, int *sizec) { if (addrc) diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 8a8363adb8b..4137579d9ad 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -198,7 +198,7 @@ static unsigned long pci_parse_of_flags(u32 addr0) * into physical address resources, we only have to figure out the register * mapping. */ -static void pci_parse_of_addrs(struct of_device *op, +static void pci_parse_of_addrs(struct platform_device *op, struct device_node *node, struct pci_dev *dev) { @@ -248,7 +248,7 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, { struct dev_archdata *sd; struct pci_slot *slot; - struct of_device *op; + struct platform_device *op; struct pci_dev *dev; const char *type; u32 class; @@ -340,7 +340,7 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, dev->hdr_type = PCI_HEADER_TYPE_NORMAL; dev->rom_base_reg = PCI_ROM_ADDRESS; - dev->irq = sd->op->irqs[0]; + dev->irq = sd->op->archdata.irqs[0]; if (dev->irq == 0xffffffff) dev->irq = PCI_IRQ_NONE; } diff --git a/arch/sparc/kernel/pci_fire.c b/arch/sparc/kernel/pci_fire.c index 51cfa09e392..efb896d6875 100644 --- a/arch/sparc/kernel/pci_fire.c +++ b/arch/sparc/kernel/pci_fire.c @@ -410,7 +410,7 @@ static void pci_fire_hw_init(struct pci_pbm_info *pbm) } static int __devinit pci_fire_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op, u32 portid) + struct platform_device *op, u32 portid) { const struct linux_prom64_registers *regs; struct device_node *dp = op->dev.of_node; @@ -455,7 +455,7 @@ static int __devinit pci_fire_pbm_init(struct pci_pbm_info *pbm, return 0; } -static int __devinit fire_probe(struct of_device *op, +static int __devinit fire_probe(struct platform_device *op, const struct of_device_id *match) { struct device_node *dp = op->dev.of_node; @@ -518,7 +518,7 @@ static struct of_platform_driver fire_driver = { static int __init fire_init(void) { - return of_register_driver(&fire_driver, &of_bus_type); + return of_register_platform_driver(&fire_driver); } subsys_initcall(fire_init); diff --git a/arch/sparc/kernel/pci_impl.h b/arch/sparc/kernel/pci_impl.h index 03186824327..e20ed5f06e9 100644 --- a/arch/sparc/kernel/pci_impl.h +++ b/arch/sparc/kernel/pci_impl.h @@ -91,7 +91,7 @@ struct pci_pbm_info { char *name; /* OBP specific information. */ - struct of_device *op; + struct platform_device *op; u64 ino_bitmap; /* PBM I/O and Memory space resources. */ diff --git a/arch/sparc/kernel/pci_psycho.c b/arch/sparc/kernel/pci_psycho.c index 558a7051282..22eab7cf3b1 100644 --- a/arch/sparc/kernel/pci_psycho.c +++ b/arch/sparc/kernel/pci_psycho.c @@ -285,7 +285,7 @@ static irqreturn_t psycho_ce_intr(int irq, void *dev_id) #define PSYCHO_ECCCTRL_CE 0x2000000000000000UL /* Enable CE INterrupts */ static void psycho_register_error_handlers(struct pci_pbm_info *pbm) { - struct of_device *op = of_find_device_by_node(pbm->op->dev.of_node); + struct platform_device *op = of_find_device_by_node(pbm->op->dev.of_node); unsigned long base = pbm->controller_regs; u64 tmp; int err; @@ -302,23 +302,23 @@ static void psycho_register_error_handlers(struct pci_pbm_info *pbm) * 5: POWER MANAGEMENT */ - if (op->num_irqs < 6) + if (op->archdata.num_irqs < 6) return; /* We really mean to ignore the return result here. Two * PCI controller share the same interrupt numbers and * drive the same front-end hardware. */ - err = request_irq(op->irqs[1], psycho_ue_intr, IRQF_SHARED, + err = request_irq(op->archdata.irqs[1], psycho_ue_intr, IRQF_SHARED, "PSYCHO_UE", pbm); - err = request_irq(op->irqs[2], psycho_ce_intr, IRQF_SHARED, + err = request_irq(op->archdata.irqs[2], psycho_ce_intr, IRQF_SHARED, "PSYCHO_CE", pbm); /* This one, however, ought not to fail. We can just warn * about it since the system can still operate properly even * if this fails. */ - err = request_irq(op->irqs[0], psycho_pcierr_intr, IRQF_SHARED, + err = request_irq(op->archdata.irqs[0], psycho_pcierr_intr, IRQF_SHARED, "PSYCHO_PCIERR", pbm); if (err) printk(KERN_WARNING "%s: Could not register PCIERR, " @@ -483,7 +483,7 @@ static void psycho_pbm_strbuf_init(struct pci_pbm_info *pbm, #define PSYCHO_MEMSPACE_SIZE 0x07fffffffUL static void __devinit psycho_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op, int is_pbm_a) + struct platform_device *op, int is_pbm_a) { psycho_pbm_init_common(pbm, op, "PSYCHO", PBM_CHIP_TYPE_PSYCHO); psycho_pbm_strbuf_init(pbm, is_pbm_a); @@ -503,7 +503,7 @@ static struct pci_pbm_info * __devinit psycho_find_sibling(u32 upa_portid) #define PSYCHO_CONFIGSPACE 0x001000000UL -static int __devinit psycho_probe(struct of_device *op, +static int __devinit psycho_probe(struct platform_device *op, const struct of_device_id *match) { const struct linux_prom64_registers *pr_regs; @@ -612,7 +612,7 @@ static struct of_platform_driver psycho_driver = { static int __init psycho_init(void) { - return of_register_driver(&psycho_driver, &of_bus_type); + return of_register_platform_driver(&psycho_driver); } subsys_initcall(psycho_init); diff --git a/arch/sparc/kernel/pci_sabre.c b/arch/sparc/kernel/pci_sabre.c index 6dad8e3b750..5c3f5ec4cab 100644 --- a/arch/sparc/kernel/pci_sabre.c +++ b/arch/sparc/kernel/pci_sabre.c @@ -311,7 +311,7 @@ static irqreturn_t sabre_ce_intr(int irq, void *dev_id) static void sabre_register_error_handlers(struct pci_pbm_info *pbm) { struct device_node *dp = pbm->op->dev.of_node; - struct of_device *op; + struct platform_device *op; unsigned long base = pbm->controller_regs; u64 tmp; int err; @@ -329,7 +329,7 @@ static void sabre_register_error_handlers(struct pci_pbm_info *pbm) * 2: CE ERR * 3: POWER FAIL */ - if (op->num_irqs < 4) + if (op->archdata.num_irqs < 4) return; /* We clear the error bits in the appropriate AFSR before @@ -341,7 +341,7 @@ static void sabre_register_error_handlers(struct pci_pbm_info *pbm) SABRE_UEAFSR_SDTE | SABRE_UEAFSR_PDTE), base + SABRE_UE_AFSR); - err = request_irq(op->irqs[1], sabre_ue_intr, 0, "SABRE_UE", pbm); + err = request_irq(op->archdata.irqs[1], sabre_ue_intr, 0, "SABRE_UE", pbm); if (err) printk(KERN_WARNING "%s: Couldn't register UE, err=%d.\n", pbm->name, err); @@ -351,11 +351,11 @@ static void sabre_register_error_handlers(struct pci_pbm_info *pbm) base + SABRE_CE_AFSR); - err = request_irq(op->irqs[2], sabre_ce_intr, 0, "SABRE_CE", pbm); + err = request_irq(op->archdata.irqs[2], sabre_ce_intr, 0, "SABRE_CE", pbm); if (err) printk(KERN_WARNING "%s: Couldn't register CE, err=%d.\n", pbm->name, err); - err = request_irq(op->irqs[0], psycho_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], psycho_pcierr_intr, 0, "SABRE_PCIERR", pbm); if (err) printk(KERN_WARNING "%s: Couldn't register PCIERR, err=%d.\n", @@ -443,7 +443,7 @@ static void __devinit sabre_scan_bus(struct pci_pbm_info *pbm, } static void __devinit sabre_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op) + struct platform_device *op) { psycho_pbm_init_common(pbm, op, "SABRE", PBM_CHIP_TYPE_SABRE); pbm->pci_afsr = pbm->controller_regs + SABRE_PIOAFSR; @@ -452,7 +452,7 @@ static void __devinit sabre_pbm_init(struct pci_pbm_info *pbm, sabre_scan_bus(pbm, &op->dev); } -static int __devinit sabre_probe(struct of_device *op, +static int __devinit sabre_probe(struct platform_device *op, const struct of_device_id *match) { const struct linux_prom64_registers *pr_regs; @@ -606,7 +606,7 @@ static struct of_platform_driver sabre_driver = { static int __init sabre_init(void) { - return of_register_driver(&sabre_driver, &of_bus_type); + return of_register_platform_driver(&sabre_driver); } subsys_initcall(sabre_init); diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index 97a1ae2e1c0..445a47a2fb3 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -844,7 +844,7 @@ static int pbm_routes_this_ino(struct pci_pbm_info *pbm, u32 ino) */ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) { - struct of_device *op = of_find_device_by_node(pbm->op->dev.of_node); + struct platform_device *op = of_find_device_by_node(pbm->op->dev.of_node); u64 tmp, err_mask, err_no_mask; int err; @@ -857,14 +857,14 @@ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) */ if (pbm_routes_this_ino(pbm, SCHIZO_UE_INO)) { - err = request_irq(op->irqs[1], schizo_ue_intr, 0, + err = request_irq(op->archdata.irqs[1], schizo_ue_intr, 0, "TOMATILLO_UE", pbm); if (err) printk(KERN_WARNING "%s: Could not register UE, " "err=%d\n", pbm->name, err); } if (pbm_routes_this_ino(pbm, SCHIZO_CE_INO)) { - err = request_irq(op->irqs[2], schizo_ce_intr, 0, + err = request_irq(op->archdata.irqs[2], schizo_ce_intr, 0, "TOMATILLO_CE", pbm); if (err) printk(KERN_WARNING "%s: Could not register CE, " @@ -872,10 +872,10 @@ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) } err = 0; if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_A_INO)) { - err = request_irq(op->irqs[0], schizo_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0, "TOMATILLO_PCIERR", pbm); } else if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_B_INO)) { - err = request_irq(op->irqs[0], schizo_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0, "TOMATILLO_PCIERR", pbm); } if (err) @@ -883,7 +883,7 @@ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) "err=%d\n", pbm->name, err); if (pbm_routes_this_ino(pbm, SCHIZO_SERR_INO)) { - err = request_irq(op->irqs[3], schizo_safarierr_intr, 0, + err = request_irq(op->archdata.irqs[3], schizo_safarierr_intr, 0, "TOMATILLO_SERR", pbm); if (err) printk(KERN_WARNING "%s: Could not register SERR, " @@ -939,7 +939,7 @@ static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm) static void schizo_register_error_handlers(struct pci_pbm_info *pbm) { - struct of_device *op = of_find_device_by_node(pbm->op->dev.of_node); + struct platform_device *op = of_find_device_by_node(pbm->op->dev.of_node); u64 tmp, err_mask, err_no_mask; int err; @@ -952,14 +952,14 @@ static void schizo_register_error_handlers(struct pci_pbm_info *pbm) */ if (pbm_routes_this_ino(pbm, SCHIZO_UE_INO)) { - err = request_irq(op->irqs[1], schizo_ue_intr, 0, + err = request_irq(op->archdata.irqs[1], schizo_ue_intr, 0, "SCHIZO_UE", pbm); if (err) printk(KERN_WARNING "%s: Could not register UE, " "err=%d\n", pbm->name, err); } if (pbm_routes_this_ino(pbm, SCHIZO_CE_INO)) { - err = request_irq(op->irqs[2], schizo_ce_intr, 0, + err = request_irq(op->archdata.irqs[2], schizo_ce_intr, 0, "SCHIZO_CE", pbm); if (err) printk(KERN_WARNING "%s: Could not register CE, " @@ -967,10 +967,10 @@ static void schizo_register_error_handlers(struct pci_pbm_info *pbm) } err = 0; if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_A_INO)) { - err = request_irq(op->irqs[0], schizo_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0, "SCHIZO_PCIERR", pbm); } else if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_B_INO)) { - err = request_irq(op->irqs[0], schizo_pcierr_intr, 0, + err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0, "SCHIZO_PCIERR", pbm); } if (err) @@ -978,7 +978,7 @@ static void schizo_register_error_handlers(struct pci_pbm_info *pbm) "err=%d\n", pbm->name, err); if (pbm_routes_this_ino(pbm, SCHIZO_SERR_INO)) { - err = request_irq(op->irqs[3], schizo_safarierr_intr, 0, + err = request_irq(op->archdata.irqs[3], schizo_safarierr_intr, 0, "SCHIZO_SERR", pbm); if (err) printk(KERN_WARNING "%s: Could not register SERR, " @@ -1307,7 +1307,7 @@ static void schizo_pbm_hw_init(struct pci_pbm_info *pbm) } static int __devinit schizo_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op, u32 portid, + struct platform_device *op, u32 portid, int chip_type) { const struct linux_prom64_registers *regs; @@ -1413,7 +1413,7 @@ static struct pci_pbm_info * __devinit schizo_find_sibling(u32 portid, return NULL; } -static int __devinit __schizo_init(struct of_device *op, unsigned long chip_type) +static int __devinit __schizo_init(struct platform_device *op, unsigned long chip_type) { struct device_node *dp = op->dev.of_node; struct pci_pbm_info *pbm; @@ -1460,7 +1460,7 @@ out_err: return err; } -static int __devinit schizo_probe(struct of_device *op, +static int __devinit schizo_probe(struct platform_device *op, const struct of_device_id *match) { return __schizo_init(op, (unsigned long) match->data); @@ -1501,7 +1501,7 @@ static struct of_platform_driver schizo_driver = { static int __init schizo_init(void) { - return of_register_driver(&schizo_driver, &of_bus_type); + return of_register_platform_driver(&schizo_driver); } subsys_initcall(schizo_init); diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index a24af6f7e17..743344aa6d8 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -879,7 +879,7 @@ static void pci_sun4v_msi_init(struct pci_pbm_info *pbm) #endif /* !(CONFIG_PCI_MSI) */ static int __devinit pci_sun4v_pbm_init(struct pci_pbm_info *pbm, - struct of_device *op, u32 devhandle) + struct platform_device *op, u32 devhandle) { struct device_node *dp = op->dev.of_node; int err; @@ -918,7 +918,7 @@ static int __devinit pci_sun4v_pbm_init(struct pci_pbm_info *pbm, return 0; } -static int __devinit pci_sun4v_probe(struct of_device *op, +static int __devinit pci_sun4v_probe(struct platform_device *op, const struct of_device_id *match) { const struct linux_prom64_registers *regs; @@ -1019,7 +1019,7 @@ static struct of_platform_driver pci_sun4v_driver = { static int __init pci_sun4v_init(void) { - return of_register_driver(&pci_sun4v_driver, &of_bus_type); + return of_register_platform_driver(&pci_sun4v_driver); } subsys_initcall(pci_sun4v_init); diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 44faabc3c02..357ced3c33f 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -572,18 +572,18 @@ static u64 sparc_perf_event_update(struct perf_event *event, s64 delta; again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); new_raw_count = read_pmc(idx); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &hwc->period_left); + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); return new_raw_count; } @@ -591,27 +591,27 @@ again: static int sparc_perf_event_set_period(struct perf_event *event, struct hw_perf_event *hwc, int idx) { - s64 left = atomic64_read(&hwc->period_left); + s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0; if (unlikely(left <= -period)) { left = period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (left > MAX_PERIOD) left = MAX_PERIOD; - atomic64_set(&hwc->prev_count, (u64)-left); + local64_set(&hwc->prev_count, (u64)-left); write_pmc(idx, (u64)(-left) & 0xffffffff); @@ -1006,7 +1006,7 @@ static int sparc_pmu_enable(struct perf_event *event) * skip the schedulability test here, it will be peformed * at commit time(->commit_txn) as a whole */ - if (cpuc->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuc->group_flag & PERF_EVENT_TXN) goto nocheck; if (check_excludes(cpuc->event, n0, 1)) @@ -1088,7 +1088,7 @@ static int __hw_perf_event_init(struct perf_event *event) if (!hwc->sample_period) { hwc->sample_period = MAX_PERIOD; hwc->last_period = hwc->sample_period; - atomic64_set(&hwc->period_left, hwc->sample_period); + local64_set(&hwc->period_left, hwc->sample_period); } return 0; @@ -1103,7 +1103,7 @@ static void sparc_pmu_start_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - cpuhw->group_flag |= PERF_EVENT_TXN_STARTED; + cpuhw->group_flag |= PERF_EVENT_TXN; } /* @@ -1115,7 +1115,7 @@ static void sparc_pmu_cancel_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); - cpuhw->group_flag &= ~PERF_EVENT_TXN_STARTED; + cpuhw->group_flag &= ~PERF_EVENT_TXN; } /* @@ -1138,6 +1138,7 @@ static int sparc_pmu_commit_txn(const struct pmu *pmu) if (sparc_check_constraints(cpuc->event, cpuc->events, n)) return -EAGAIN; + cpuc->group_flag &= ~PERF_EVENT_TXN; return 0; } diff --git a/arch/sparc/kernel/pmc.c b/arch/sparc/kernel/pmc.c index 9589d8b9b0c..94536a85f16 100644 --- a/arch/sparc/kernel/pmc.c +++ b/arch/sparc/kernel/pmc.c @@ -51,7 +51,7 @@ static void pmc_swift_idle(void) #endif } -static int __devinit pmc_probe(struct of_device *op, +static int __devinit pmc_probe(struct platform_device *op, const struct of_device_id *match) { regs = of_ioremap(&op->resource[0], 0, @@ -89,7 +89,7 @@ static struct of_platform_driver pmc_driver = { static int __init pmc_init(void) { - return of_register_driver(&pmc_driver, &of_bus_type); + return of_register_platform_driver(&pmc_driver); } /* This driver is not critical to the boot process diff --git a/arch/sparc/kernel/power.c b/arch/sparc/kernel/power.c index 168d4cb63f5..2c59f4d387d 100644 --- a/arch/sparc/kernel/power.c +++ b/arch/sparc/kernel/power.c @@ -33,10 +33,10 @@ static int __devinit has_button_interrupt(unsigned int irq, struct device_node * return 1; } -static int __devinit power_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit power_probe(struct platform_device *op, const struct of_device_id *match) { struct resource *res = &op->resource[0]; - unsigned int irq= op->irqs[0]; + unsigned int irq = op->archdata.irqs[0]; power_reg = of_ioremap(res, 0, 0x4, "power"); @@ -70,7 +70,7 @@ static struct of_platform_driver power_driver = { static int __init power_init(void) { - return of_register_driver(&power_driver, &of_platform_bus_type); + return of_register_platform_driver(&power_driver); } device_initcall(power_init); diff --git a/arch/sparc/kernel/prom.h b/arch/sparc/kernel/prom.h index a8591ef2636..eeb04a782ec 100644 --- a/arch/sparc/kernel/prom.h +++ b/arch/sparc/kernel/prom.h @@ -9,14 +9,6 @@ extern void irq_trans_init(struct device_node *dp); extern unsigned int prom_unique_id; -static inline int is_root_node(const struct device_node *dp) -{ - if (!dp) - return 0; - - return (dp->parent == NULL); -} - extern char *build_path_component(struct device_node *dp); extern void of_console_init(void); diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index 466a32763ea..86597d9867f 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -21,7 +21,7 @@ #include <linux/mm.h> #include <linux/module.h> #include <linux/memblock.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <asm/prom.h> #include <asm/oplib.h> @@ -81,7 +81,7 @@ static void __init sun4v_path_component(struct device_node *dp, char *tmp_buf) return; regs = rprop->value; - if (!is_root_node(dp->parent)) { + if (!of_node_is_root(dp->parent)) { sprintf(tmp_buf, "%s@%x,%x", dp->name, (unsigned int) (regs->phys_addr >> 32UL), @@ -121,7 +121,7 @@ static void __init sun4u_path_component(struct device_node *dp, char *tmp_buf) return; regs = prop->value; - if (!is_root_node(dp->parent)) { + if (!of_node_is_root(dp->parent)) { sprintf(tmp_buf, "%s@%x,%x", dp->name, (unsigned int) (regs->phys_addr >> 32UL), diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c index 57ac9e28be0..1f830da2ddf 100644 --- a/arch/sparc/kernel/prom_common.c +++ b/arch/sparc/kernel/prom_common.c @@ -244,7 +244,7 @@ char * __init build_full_name(struct device_node *dp) n = prom_early_alloc(len); strcpy(n, dp->parent->full_name); - if (!is_root_node(dp->parent)) { + if (!of_node_is_root(dp->parent)) { strcpy(n + plen, "/"); plen++; } diff --git a/arch/sparc/kernel/prom_irqtrans.c b/arch/sparc/kernel/prom_irqtrans.c index 5702ad4710c..ce651147fab 100644 --- a/arch/sparc/kernel/prom_irqtrans.c +++ b/arch/sparc/kernel/prom_irqtrans.c @@ -719,7 +719,7 @@ static unsigned int central_build_irq(struct device_node *dp, void *_data) { struct device_node *central_dp = _data; - struct of_device *central_op = of_find_device_by_node(central_dp); + struct platform_device *central_op = of_find_device_by_node(central_dp); struct resource *res; unsigned long imap, iclr; u32 tmp; diff --git a/arch/sparc/kernel/psycho_common.c b/arch/sparc/kernel/psycho_common.c index 3f34ac85393..fe2af66bb19 100644 --- a/arch/sparc/kernel/psycho_common.c +++ b/arch/sparc/kernel/psycho_common.c @@ -447,7 +447,7 @@ int psycho_iommu_init(struct pci_pbm_info *pbm, int tsbsize, } -void psycho_pbm_init_common(struct pci_pbm_info *pbm, struct of_device *op, +void psycho_pbm_init_common(struct pci_pbm_info *pbm, struct platform_device *op, const char *chip_name, int chip_type) { struct device_node *dp = op->dev.of_node; diff --git a/arch/sparc/kernel/psycho_common.h b/arch/sparc/kernel/psycho_common.h index 092c278ef28..590b4ed8ab5 100644 --- a/arch/sparc/kernel/psycho_common.h +++ b/arch/sparc/kernel/psycho_common.h @@ -42,7 +42,7 @@ extern int psycho_iommu_init(struct pci_pbm_info *pbm, int tsbsize, unsigned long write_complete_offset); extern void psycho_pbm_init_common(struct pci_pbm_info *pbm, - struct of_device *op, + struct platform_device *op, const char *chip_name, int chip_type); #endif /* _PSYCHO_COMMON_H */ diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c index cfeaf04b9cd..2ca32d13abc 100644 --- a/arch/sparc/kernel/sbus.c +++ b/arch/sparc/kernel/sbus.c @@ -57,7 +57,7 @@ void sbus_set_sbus64(struct device *dev, int bursts) { struct iommu *iommu = dev->archdata.iommu; - struct of_device *op = to_of_device(dev); + struct platform_device *op = to_platform_device(dev); const struct linux_prom_registers *regs; unsigned long cfg_reg; int slot; @@ -204,7 +204,7 @@ static unsigned long sysio_imap_to_iclr(unsigned long imap) return imap + diff; } -static unsigned int sbus_build_irq(struct of_device *op, unsigned int ino) +static unsigned int sbus_build_irq(struct platform_device *op, unsigned int ino) { struct iommu *iommu = op->dev.archdata.iommu; unsigned long reg_base = iommu->write_complete_reg - 0x2000UL; @@ -267,7 +267,7 @@ static unsigned int sbus_build_irq(struct of_device *op, unsigned int ino) #define SYSIO_UEAFSR_RESV2 0x0000001fffffffffUL /* Reserved */ static irqreturn_t sysio_ue_handler(int irq, void *dev_id) { - struct of_device *op = dev_id; + struct platform_device *op = dev_id; struct iommu *iommu = op->dev.archdata.iommu; unsigned long reg_base = iommu->write_complete_reg - 0x2000UL; unsigned long afsr_reg, afar_reg; @@ -341,7 +341,7 @@ static irqreturn_t sysio_ue_handler(int irq, void *dev_id) #define SYSIO_CEAFSR_RESV2 0x0000001fffffffffUL /* Reserved */ static irqreturn_t sysio_ce_handler(int irq, void *dev_id) { - struct of_device *op = dev_id; + struct platform_device *op = dev_id; struct iommu *iommu = op->dev.archdata.iommu; unsigned long reg_base = iommu->write_complete_reg - 0x2000UL; unsigned long afsr_reg, afar_reg; @@ -420,7 +420,7 @@ static irqreturn_t sysio_ce_handler(int irq, void *dev_id) #define SYSIO_SBAFSR_RESV3 0x0000001fffffffffUL /* Reserved */ static irqreturn_t sysio_sbus_error_handler(int irq, void *dev_id) { - struct of_device *op = dev_id; + struct platform_device *op = dev_id; struct iommu *iommu = op->dev.archdata.iommu; unsigned long afsr_reg, afar_reg, reg_base; unsigned long afsr, afar, error_bits; @@ -488,7 +488,7 @@ static irqreturn_t sysio_sbus_error_handler(int irq, void *dev_id) #define SYSIO_CE_INO 0x35 #define SYSIO_SBUSERR_INO 0x36 -static void __init sysio_register_error_handlers(struct of_device *op) +static void __init sysio_register_error_handlers(struct platform_device *op) { struct iommu *iommu = op->dev.archdata.iommu; unsigned long reg_base = iommu->write_complete_reg - 0x2000UL; @@ -534,7 +534,7 @@ static void __init sysio_register_error_handlers(struct of_device *op) } /* Boot time initialization. */ -static void __init sbus_iommu_init(struct of_device *op) +static void __init sbus_iommu_init(struct platform_device *op) { const struct linux_prom64_registers *pr; struct device_node *dp = op->dev.of_node; @@ -663,7 +663,7 @@ static int __init sbus_init(void) struct device_node *dp; for_each_node_by_name(dp, "sbus") { - struct of_device *op = of_find_device_by_node(dp); + struct platform_device *op = of_find_device_by_node(dp); sbus_iommu_init(op); of_propagate_archdata(op); diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c index e404b063be2..9c743b1886f 100644 --- a/arch/sparc/kernel/time_32.c +++ b/arch/sparc/kernel/time_32.c @@ -142,7 +142,7 @@ static struct platform_device m48t59_rtc = { }, }; -static int __devinit clock_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit clock_probe(struct platform_device *op, const struct of_device_id *match) { struct device_node *dp = op->dev.of_node; const char *model = of_get_property(dp, "model", NULL); @@ -189,7 +189,7 @@ static struct of_platform_driver clock_driver = { /* Probe for the mostek real time clock chip. */ static int __init clock_init(void) { - return of_register_driver(&clock_driver, &of_platform_bus_type); + return of_register_platform_driver(&clock_driver); } /* Must be after subsys_initcall() so that busses are probed. Must * be before device_initcall() because things like the RTC driver diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 21e9fcae066..3bc9c9979b9 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -419,7 +419,7 @@ static struct platform_device rtc_cmos_device = { .num_resources = 1, }; -static int __devinit rtc_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit rtc_probe(struct platform_device *op, const struct of_device_id *match) { struct resource *r; @@ -477,7 +477,7 @@ static struct platform_device rtc_bq4802_device = { .num_resources = 1, }; -static int __devinit bq4802_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit bq4802_probe(struct platform_device *op, const struct of_device_id *match) { printk(KERN_INFO "%s: BQ4802 regs at 0x%llx\n", @@ -534,7 +534,7 @@ static struct platform_device m48t59_rtc = { }, }; -static int __devinit mostek_probe(struct of_device *op, const struct of_device_id *match) +static int __devinit mostek_probe(struct platform_device *op, const struct of_device_id *match) { struct device_node *dp = op->dev.of_node; @@ -586,9 +586,9 @@ static int __init clock_init(void) if (tlb_type == hypervisor) return platform_device_register(&rtc_sun4v_device); - (void) of_register_driver(&rtc_driver, &of_platform_bus_type); - (void) of_register_driver(&mostek_driver, &of_platform_bus_type); - (void) of_register_driver(&bq4802_driver, &of_platform_bus_type); + (void) of_register_platform_driver(&rtc_driver); + (void) of_register_platform_driver(&mostek_driver); + (void) of_register_platform_driver(&bq4802_driver); return 0; } diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c index 005e758a4db..fc58c3e917d 100644 --- a/arch/sparc/mm/io-unit.c +++ b/arch/sparc/mm/io-unit.c @@ -35,7 +35,7 @@ #define IOPERM (IOUPTE_CACHE | IOUPTE_WRITE | IOUPTE_VALID) #define MKIOPTE(phys) __iopte((((phys)>>4) & IOUPTE_PAGE) | IOPERM) -static void __init iounit_iommu_init(struct of_device *op) +static void __init iounit_iommu_init(struct platform_device *op) { struct iounit_struct *iounit; iopte_t *xpt, *xptend; @@ -74,7 +74,7 @@ static int __init iounit_init(void) struct device_node *dp; for_each_node_by_name(dp, "sbi") { - struct of_device *op = of_find_device_by_node(dp); + struct platform_device *op = of_find_device_by_node(dp); iounit_iommu_init(op); of_propagate_archdata(op); diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 0e8ae298b3c..07fc6a65d9b 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -56,7 +56,7 @@ static pgprot_t dvma_prot; /* Consistent mapping pte flags */ #define IOPERM (IOPTE_CACHE | IOPTE_WRITE | IOPTE_VALID) #define MKIOPTE(pfn, perm) (((((pfn)<<8) & IOPTE_PAGE) | (perm)) & ~IOPTE_WAZ) -static void __init sbus_iommu_init(struct of_device *op) +static void __init sbus_iommu_init(struct platform_device *op) { struct iommu_struct *iommu; unsigned int impl, vers; @@ -132,7 +132,7 @@ static int __init iommu_init(void) struct device_node *dp; for_each_node_by_name(dp, "iommu") { - struct of_device *op = of_find_device_by_node(dp); + struct platform_device *op = of_find_device_by_node(dp); sbus_iommu_init(op); of_propagate_archdata(op); diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h index 084de4a9fc7..0032f9212e7 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-3level.h @@ -60,7 +60,7 @@ set_pud(pud, __pud(_PAGE_TABLE + __pa(pmd))) #ifdef CONFIG_64BIT -#define set_pud(pudptr, pudval) set_64bit((phys_t *) (pudptr), pud_val(pudval)) +#define set_pud(pudptr, pudval) set_64bit((u64 *) (pudptr), pud_val(pudval)) #else #define set_pud(pudptr, pudval) (*(pudptr) = (pudval)) #endif @@ -73,7 +73,7 @@ static inline int pgd_newpage(pgd_t pgd) static inline void pgd_mkuptodate(pgd_t pgd) { pgd_val(pgd) &= ~_PAGE_NEWPAGE; } #ifdef CONFIG_64BIT -#define set_pmd(pmdptr, pmdval) set_64bit((phys_t *) (pmdptr), pmd_val(pmdval)) +#define set_pmd(pmdptr, pmdval) set_64bit((u64 *) (pmdptr), pmd_val(pmdval)) #else #define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) #endif diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dcb0593b4a6..6f77afa6bca 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -55,6 +55,7 @@ config X86 select HAVE_HW_BREAKPOINT select HAVE_MIXED_BREAKPOINTS_REGS select PERF_EVENTS + select HAVE_PERF_EVENTS_NMI select ANON_INODES select HAVE_ARCH_KMEMCHECK select HAVE_USER_RETURN_NOTIFIER diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index ec749c2bfdd..f7cb086b4ad 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -26,10 +26,10 @@ targets := vmlinux.bin setup.bin setup.elf bzImage targets += fdimage fdimage144 fdimage288 image.iso mtools.conf subdir- := compressed -setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o edd.o -setup-y += header.o main.o mca.o memory.o pm.o pmjump.o -setup-y += printf.o regs.o string.o tty.o video.o video-mode.o -setup-y += version.o +setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o +setup-y += early_serial_console.o edd.o header.o main.o mca.o memory.o +setup-y += pm.o pmjump.o printf.o regs.o string.o tty.o video.o +setup-y += video-mode.o version.o setup-$(CONFIG_X86_APM_BOOT) += apm.o # The link order of the video-*.o modules can matter. In particular, diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 98239d2658f..c7093bd9f2d 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -28,6 +28,7 @@ #include "bitops.h" #include <asm/cpufeature.h> #include <asm/processor-flags.h> +#include "ctype.h" /* Useful macros */ #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) @@ -37,6 +38,8 @@ extern struct setup_header hdr; extern struct boot_params boot_params; +#define cpu_relax() asm volatile("rep; nop") + /* Basic port I/O */ static inline void outb(u8 v, u16 port) { @@ -198,11 +201,6 @@ static inline int memcmp_gs(const void *s1, addr_t s2, size_t len) return diff; } -static inline int isdigit(int ch) -{ - return (ch >= '0') && (ch <= '9'); -} - /* Heap -- available for dynamic lists. */ extern char _end[]; extern char *HEAP; @@ -287,8 +285,18 @@ struct biosregs { void intcall(u8 int_no, const struct biosregs *ireg, struct biosregs *oreg); /* cmdline.c */ -int cmdline_find_option(const char *option, char *buffer, int bufsize); -int cmdline_find_option_bool(const char *option); +int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int bufsize); +int __cmdline_find_option_bool(u32 cmdline_ptr, const char *option); +static inline int cmdline_find_option(const char *option, char *buffer, int bufsize) +{ + return __cmdline_find_option(boot_params.hdr.cmd_line_ptr, option, buffer, bufsize); +} + +static inline int cmdline_find_option_bool(const char *option) +{ + return __cmdline_find_option_bool(boot_params.hdr.cmd_line_ptr, option); +} + /* cpu.c, cpucheck.c */ struct cpu_features { @@ -300,6 +308,10 @@ extern struct cpu_features cpu; int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr); int validate_cpu(void); +/* early_serial_console.c */ +extern int early_serial_base; +void console_init(void); + /* edd.c */ void query_edd(void); @@ -329,8 +341,10 @@ void initregs(struct biosregs *regs); /* string.c */ int strcmp(const char *str1, const char *str2); +int strncmp(const char *cs, const char *ct, size_t count); size_t strnlen(const char *s, size_t maxlen); unsigned int atou(const char *s); +unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base); /* tty.c */ void puts(const char *); diff --git a/arch/x86/boot/cmdline.c b/arch/x86/boot/cmdline.c index a1d35634bce..6b3b6f708c0 100644 --- a/arch/x86/boot/cmdline.c +++ b/arch/x86/boot/cmdline.c @@ -27,9 +27,8 @@ static inline int myisspace(u8 c) * Returns the length of the argument (regardless of if it was * truncated to fit in the buffer), or -1 on not found. */ -int cmdline_find_option(const char *option, char *buffer, int bufsize) +int __cmdline_find_option(u32 cmdline_ptr, const char *option, char *buffer, int bufsize) { - u32 cmdline_ptr = boot_params.hdr.cmd_line_ptr; addr_t cptr; char c; int len = -1; @@ -100,9 +99,8 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize) * Returns the position of that option (starts counting with 1) * or 0 on not found */ -int cmdline_find_option_bool(const char *option) +int __cmdline_find_option_bool(u32 cmdline_ptr, const char *option) { - u32 cmdline_ptr = boot_params.hdr.cmd_line_ptr; addr_t cptr; char c; int pos = 0, wstart = 0; diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index fbb47daf245..0c229551eea 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -4,7 +4,7 @@ # create a compressed vmlinux image from the original vmlinux # -targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(BITS).o misc.o piggy.o +targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC @@ -23,7 +23,7 @@ LDFLAGS_vmlinux := -T hostprogs-y := mkpiggy -$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/piggy.o FORCE +$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o $(obj)/piggy.o FORCE $(call if_changed,ld) @: diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c new file mode 100644 index 00000000000..cb62f786990 --- /dev/null +++ b/arch/x86/boot/compressed/cmdline.c @@ -0,0 +1,21 @@ +#include "misc.h" + +static unsigned long fs; +static inline void set_fs(unsigned long seg) +{ + fs = seg << 4; /* shift it back */ +} +typedef unsigned long addr_t; +static inline char rdfs8(addr_t addr) +{ + return *((char *)(fs + addr)); +} +#include "../cmdline.c" +int cmdline_find_option(const char *option, char *buffer, int bufsize) +{ + return __cmdline_find_option(real_mode->hdr.cmd_line_ptr, option, buffer, bufsize); +} +int cmdline_find_option_bool(const char *option) +{ + return __cmdline_find_option_bool(real_mode->hdr.cmd_line_ptr, option); +} diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c new file mode 100644 index 00000000000..261e81fb958 --- /dev/null +++ b/arch/x86/boot/compressed/early_serial_console.c @@ -0,0 +1,5 @@ +#include "misc.h" + +int early_serial_base; + +#include "../early_serial_console.c" diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index f543b70ffae..67a655a39ce 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -124,6 +124,19 @@ relocated: rep stosl /* + * Adjust our own GOT + */ + leal _got(%ebx), %edx + leal _egot(%ebx), %ecx +1: + cmpl %ecx, %edx + jae 2f + addl %ebx, (%edx) + addl $4, %edx + jmp 1b +2: + +/* * Do the decompression, and jump to the new kernel.. */ leal z_extract_offset_negative(%ebx), %ebp diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index faff0dc9c06..52f85a196fa 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -280,6 +280,19 @@ relocated: rep stosq /* + * Adjust our own GOT + */ + leaq _got(%rip), %rdx + leaq _egot(%rip), %rcx +1: + cmpq %rcx, %rdx + jae 2f + addq %rbx, (%rdx) + addq $8, %rdx + jmp 1b +2: + +/* * Do the decompression, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 51e240779a4..8f7bef8e9ff 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -9,23 +9,7 @@ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996 */ -/* - * we have to be careful, because no indirections are allowed here, and - * paravirt_ops is a kind of one. As it will only run in baremetal anyway, - * we just keep it from happening - */ -#undef CONFIG_PARAVIRT -#ifdef CONFIG_X86_32 -#define _ASM_X86_DESC_H 1 -#endif - -#include <linux/linkage.h> -#include <linux/screen_info.h> -#include <linux/elf.h> -#include <linux/io.h> -#include <asm/page.h> -#include <asm/boot.h> -#include <asm/bootparam.h> +#include "misc.h" /* WARNING!! * This code is compiled with -fPIC and it is relocated dynamically @@ -123,15 +107,13 @@ static void error(char *m); /* * This is set up by the setup-routine at boot-time */ -static struct boot_params *real_mode; /* Pointer to real-mode data */ +struct boot_params *real_mode; /* Pointer to real-mode data */ static int quiet; +static int debug; void *memset(void *s, int c, size_t n); void *memcpy(void *dest, const void *src, size_t n); -static void __putstr(int, const char *); -#define putstr(__x) __putstr(0, __x) - #ifdef CONFIG_X86_64 #define memptr long #else @@ -170,7 +152,21 @@ static void scroll(void) vidmem[i] = ' '; } -static void __putstr(int error, const char *s) +#define XMTRDY 0x20 + +#define TXR 0 /* Transmit register (WRITE) */ +#define LSR 5 /* Line Status */ +static void serial_putchar(int ch) +{ + unsigned timeout = 0xffff; + + while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout) + cpu_relax(); + + outb(ch, early_serial_base + TXR); +} + +void __putstr(int error, const char *s) { int x, y, pos; char c; @@ -179,6 +175,14 @@ static void __putstr(int error, const char *s) if (!error) return; #endif + if (early_serial_base) { + const char *str = s; + while (*str) { + if (*str == '\n') + serial_putchar('\r'); + serial_putchar(*str++); + } + } if (real_mode->screen_info.orig_video_mode == 0 && lines == 0 && cols == 0) @@ -305,8 +309,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, { real_mode = rmode; - if (real_mode->hdr.loadflags & QUIET_FLAG) + if (cmdline_find_option_bool("quiet")) quiet = 1; + if (cmdline_find_option_bool("debug")) + debug = 1; if (real_mode->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; @@ -319,6 +325,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, lines = real_mode->screen_info.orig_video_lines; cols = real_mode->screen_info.orig_video_cols; + console_init(); + if (debug) + putstr("early console in decompress_kernel\n"); + free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h new file mode 100644 index 00000000000..3f19c81a620 --- /dev/null +++ b/arch/x86/boot/compressed/misc.h @@ -0,0 +1,39 @@ +#ifndef BOOT_COMPRESSED_MISC_H +#define BOOT_COMPRESSED_MISC_H + +/* + * we have to be careful, because no indirections are allowed here, and + * paravirt_ops is a kind of one. As it will only run in baremetal anyway, + * we just keep it from happening + */ +#undef CONFIG_PARAVIRT +#ifdef CONFIG_X86_32 +#define _ASM_X86_DESC_H 1 +#endif + +#include <linux/linkage.h> +#include <linux/screen_info.h> +#include <linux/elf.h> +#include <linux/io.h> +#include <asm/page.h> +#include <asm/boot.h> +#include <asm/bootparam.h> + +#define BOOT_BOOT_H +#include "../ctype.h" + +/* misc.c */ +extern struct boot_params *real_mode; /* Pointer to real-mode data */ +void __putstr(int error, const char *s); +#define putstr(__x) __putstr(0, __x) +#define puts(__x) __putstr(0, __x) + +/* cmdline.c */ +int cmdline_find_option(const char *option, char *buffer, int bufsize); +int cmdline_find_option_bool(const char *option); + +/* early_serial_console.c */ +extern int early_serial_base; +void console_init(void); + +#endif diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c new file mode 100644 index 00000000000..19b3e693cd7 --- /dev/null +++ b/arch/x86/boot/compressed/string.c @@ -0,0 +1,2 @@ +#include "misc.h" +#include "../string.c" diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index 5ddabceee12..34d047c9828 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -41,6 +41,12 @@ SECTIONS *(.rodata.*) _erodata = . ; } + .got : { + _got = .; + KEEP(*(.got.plt)) + KEEP(*(.got)) + _egot = .; + } .data : { _data = . ; *(.data) diff --git a/arch/x86/boot/ctype.h b/arch/x86/boot/ctype.h new file mode 100644 index 00000000000..25e13403193 --- /dev/null +++ b/arch/x86/boot/ctype.h @@ -0,0 +1,21 @@ +#ifndef BOOT_ISDIGIT_H + +#define BOOT_ISDIGIT_H + +static inline int isdigit(int ch) +{ + return (ch >= '0') && (ch <= '9'); +} + +static inline int isxdigit(int ch) +{ + if (isdigit(ch)) + return true; + + if ((ch >= 'a') && (ch <= 'f')) + return true; + + return (ch >= 'A') && (ch <= 'F'); +} + +#endif diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c new file mode 100644 index 00000000000..030f4b93e25 --- /dev/null +++ b/arch/x86/boot/early_serial_console.c @@ -0,0 +1,139 @@ +#include "boot.h" + +#define DEFAULT_SERIAL_PORT 0x3f8 /* ttyS0 */ + +#define XMTRDY 0x20 + +#define DLAB 0x80 + +#define TXR 0 /* Transmit register (WRITE) */ +#define RXR 0 /* Receive register (READ) */ +#define IER 1 /* Interrupt Enable */ +#define IIR 2 /* Interrupt ID */ +#define FCR 2 /* FIFO control */ +#define LCR 3 /* Line control */ +#define MCR 4 /* Modem control */ +#define LSR 5 /* Line Status */ +#define MSR 6 /* Modem Status */ +#define DLL 0 /* Divisor Latch Low */ +#define DLH 1 /* Divisor latch High */ + +#define DEFAULT_BAUD 9600 + +static void early_serial_init(int port, int baud) +{ + unsigned char c; + unsigned divisor; + + outb(0x3, port + LCR); /* 8n1 */ + outb(0, port + IER); /* no interrupt */ + outb(0, port + FCR); /* no fifo */ + outb(0x3, port + MCR); /* DTR + RTS */ + + divisor = 115200 / baud; + c = inb(port + LCR); + outb(c | DLAB, port + LCR); + outb(divisor & 0xff, port + DLL); + outb((divisor >> 8) & 0xff, port + DLH); + outb(c & ~DLAB, port + LCR); + + early_serial_base = port; +} + +static void parse_earlyprintk(void) +{ + int baud = DEFAULT_BAUD; + char arg[32]; + int pos = 0; + int port = 0; + + if (cmdline_find_option("earlyprintk", arg, sizeof arg) > 0) { + char *e; + + if (!strncmp(arg, "serial", 6)) { + port = DEFAULT_SERIAL_PORT; + pos += 6; + } + + if (arg[pos] == ',') + pos++; + + if (!strncmp(arg, "ttyS", 4)) { + static const int bases[] = { 0x3f8, 0x2f8 }; + int idx = 0; + + if (!strncmp(arg + pos, "ttyS", 4)) + pos += 4; + + if (arg[pos++] == '1') + idx = 1; + + port = bases[idx]; + } + + if (arg[pos] == ',') + pos++; + + baud = simple_strtoull(arg + pos, &e, 0); + if (baud == 0 || arg + pos == e) + baud = DEFAULT_BAUD; + } + + if (port) + early_serial_init(port, baud); +} + +#define BASE_BAUD (1843200/16) +static unsigned int probe_baud(int port) +{ + unsigned char lcr, dll, dlh; + unsigned int quot; + + lcr = inb(port + LCR); + outb(lcr | DLAB, port + LCR); + dll = inb(port + DLL); + dlh = inb(port + DLH); + outb(lcr, port + LCR); + quot = (dlh << 8) | dll; + + return BASE_BAUD / quot; +} + +static void parse_console_uart8250(void) +{ + char optstr[64], *options; + int baud = DEFAULT_BAUD; + int port = 0; + + /* + * console=uart8250,io,0x3f8,115200n8 + * need to make sure it is last one console ! + */ + if (cmdline_find_option("console", optstr, sizeof optstr) <= 0) + return; + + options = optstr; + + if (!strncmp(options, "uart8250,io,", 12)) + port = simple_strtoull(options + 12, &options, 0); + else if (!strncmp(options, "uart,io,", 8)) + port = simple_strtoull(options + 8, &options, 0); + else + return; + + if (options && (options[0] == ',')) + baud = simple_strtoull(options + 1, &options, 0); + else + baud = probe_baud(port); + + if (port) + early_serial_init(port, baud); +} + +void console_init(void) +{ + parse_earlyprintk(); + + if (!early_serial_base) + parse_console_uart8250(); +} diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index 140172b895b..40358c8905b 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -130,6 +130,11 @@ void main(void) /* First, copy the boot header into the "zeropage" */ copy_boot_params(); + /* Initialize the early-boot console */ + console_init(); + if (cmdline_find_option_bool("debug")) + puts("early console in setup code\n"); + /* End of heap check */ init_heap(); @@ -168,10 +173,6 @@ void main(void) /* Set the video mode */ set_video(); - /* Parse command line for 'quiet' and pass it to decompressor. */ - if (cmdline_find_option_bool("quiet")) - boot_params.hdr.loadflags |= QUIET_FLAG; - /* Do the last things and invoke protected mode */ go_to_protected_mode(); } diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c index 50e47cdbddd..cdac91ca55d 100644 --- a/arch/x86/boot/printf.c +++ b/arch/x86/boot/printf.c @@ -34,7 +34,7 @@ static int skip_atoi(const char **s) #define SMALL 32 /* Must be 32 == 0x20 */ #define SPECIAL 64 /* 0x */ -#define do_div(n,base) ({ \ +#define __do_div(n, base) ({ \ int __res; \ __res = ((unsigned long) n) % (unsigned) base; \ n = ((unsigned long) n) / (unsigned) base; \ @@ -83,7 +83,7 @@ static char *number(char *str, long num, int base, int size, int precision, tmp[i++] = '0'; else while (num != 0) - tmp[i++] = (digits[do_div(num, base)] | locase); + tmp[i++] = (digits[__do_div(num, base)] | locase); if (i > precision) precision = i; size -= precision; diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index f94b7a0c2ab..3cbc4058dd2 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -30,6 +30,22 @@ int strcmp(const char *str1, const char *str2) return 0; } +int strncmp(const char *cs, const char *ct, size_t count) +{ + unsigned char c1, c2; + + while (count) { + c1 = *cs++; + c2 = *ct++; + if (c1 != c2) + return c1 < c2 ? -1 : 1; + if (!c1) + break; + count--; + } + return 0; +} + size_t strnlen(const char *s, size_t maxlen) { const char *es = s; @@ -48,3 +64,50 @@ unsigned int atou(const char *s) i = i * 10 + (*s++ - '0'); return i; } + +/* Works only for digits and letters, but small and fast */ +#define TOLOWER(x) ((x) | 0x20) + +static unsigned int simple_guess_base(const char *cp) +{ + if (cp[0] == '0') { + if (TOLOWER(cp[1]) == 'x' && isxdigit(cp[2])) + return 16; + else + return 8; + } else { + return 10; + } +} + +/** + * simple_strtoull - convert a string to an unsigned long long + * @cp: The start of the string + * @endp: A pointer to the end of the parsed string will be placed here + * @base: The number base to use + */ + +unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) +{ + unsigned long long result = 0; + + if (!base) + base = simple_guess_base(cp); + + if (base == 16 && cp[0] == '0' && TOLOWER(cp[1]) == 'x') + cp += 2; + + while (isxdigit(*cp)) { + unsigned int value; + + value = isdigit(*cp) ? *cp - '0' : TOLOWER(*cp) - 'a' + 10; + if (value >= base) + break; + result = result * base + value; + cp++; + } + if (endp) + *endp = (char *)cp; + + return result; +} diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c index 01ec69c901c..def2451f46a 100644 --- a/arch/x86/boot/tty.c +++ b/arch/x86/boot/tty.c @@ -10,23 +10,36 @@ * ----------------------------------------------------------------------- */ /* - * Very simple screen I/O - * XXX: Probably should add very simple serial I/O? + * Very simple screen and serial I/O */ #include "boot.h" +int early_serial_base; + +#define XMTRDY 0x20 + +#define TXR 0 /* Transmit register (WRITE) */ +#define LSR 5 /* Line Status */ + /* * These functions are in .inittext so they can be used to signal * error during initialization. */ -void __attribute__((section(".inittext"))) putchar(int ch) +static void __attribute__((section(".inittext"))) serial_putchar(int ch) { - struct biosregs ireg; + unsigned timeout = 0xffff; - if (ch == '\n') - putchar('\r'); /* \n -> \r\n */ + while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout) + cpu_relax(); + + outb(ch, early_serial_base + TXR); +} + +static void __attribute__((section(".inittext"))) bios_putchar(int ch) +{ + struct biosregs ireg; initregs(&ireg); ireg.bx = 0x0007; @@ -36,6 +49,17 @@ void __attribute__((section(".inittext"))) putchar(int ch) intcall(0x10, &ireg, NULL); } +void __attribute__((section(".inittext"))) putchar(int ch) +{ + if (ch == '\n') + putchar('\r'); /* \n -> \r\n */ + + bios_putchar(ch); + + if (early_serial_base != 0) + serial_putchar(ch); +} + void __attribute__((section(".inittext"))) puts(const char *str) { while (*str) @@ -112,3 +136,4 @@ int getchar_timeout(void) return 0; /* Timeout! */ } + diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index d28fad19654..e3a32431ca1 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1471,6 +1471,7 @@ CONFIG_HWMON=y # CONFIG_SENSORS_GL518SM is not set # CONFIG_SENSORS_GL520SM is not set # CONFIG_SENSORS_CORETEMP is not set +# CONFIG_SENSORS_PKGTEMP is not set # CONFIG_SENSORS_IT87 is not set # CONFIG_SENSORS_LM63 is not set # CONFIG_SENSORS_LM75 is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 6c86acd847a..4251f837205 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -1456,6 +1456,7 @@ CONFIG_HWMON=y # CONFIG_SENSORS_GL518SM is not set # CONFIG_SENSORS_GL520SM is not set # CONFIG_SENSORS_CORETEMP is not set +# CONFIG_SENSORS_PKGTEMP is not set # CONFIG_SENSORS_IT87 is not set # CONFIG_SENSORS_LM63 is not set # CONFIG_SENSORS_LM75 is not set diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index aa2c39d968f..92091de1111 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -134,7 +134,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) boot_cpu_data.x86_model <= 0x05 && boot_cpu_data.x86_mask < 0x0A) return 1; - else if (boot_cpu_has(X86_FEATURE_AMDC1E)) + else if (c1e_detected) return 1; else return max_cstate; diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h index c74a2eebe57..a69b1ac9eaf 100644 --- a/arch/x86/include/asm/apb_timer.h +++ b/arch/x86/include/asm/apb_timer.h @@ -55,7 +55,6 @@ extern unsigned long apbt_quick_calibrate(void); extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu); extern void apbt_setup_secondary_clock(void); extern unsigned int boot_cpu_id; -extern int disable_apbt_percpu; extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint); extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr); diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 8859e12dd3c..284a6e8f7ce 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -11,38 +11,42 @@ extern void __xchg_wrong_size(void); /* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. */ - -struct __xchg_dummy { - unsigned long a[100]; -}; -#define __xg(x) ((struct __xchg_dummy *)(x)) - #define __xchg(x, ptr, size) \ ({ \ __typeof(*(ptr)) __x = (x); \ switch (size) { \ case 1: \ - asm volatile("xchgb %b0,%1" \ - : "=q" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile("xchgb %0,%1" \ + : "=q" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile("xchgw %w0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile("xchgw %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 4: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ asm volatile("xchgl %0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ default: \ __xchg_wrong_size(); \ } \ @@ -53,60 +57,33 @@ struct __xchg_dummy { __xchg((v), (ptr), sizeof(*ptr)) /* - * The semantics of XCHGCMP8B are a bit strange, this is why - * there is a loop and the loading of %%eax and %%edx has to - * be inside. This inlines well in most cases, the cached - * cost is around ~38 cycles. (in the future we might want - * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that - * might have an implicit FPU-save as a cost, so it's not - * clear which path to go.) + * CMPXCHG8B only writes to the target if we had the previous + * value in registers, otherwise it acts as a read and gives us the + * "new previous" value. That is why there is a loop. Preloading + * EDX:EAX is a performance optimization: in the common case it means + * we need only one locked operation. * - * cmpxchg8b must be used with the lock prefix here to allow - * the instruction to be executed atomically, see page 3-102 - * of the instruction set reference 24319102.pdf. We need - * the reader side to see the coherent 64bit value. + * A SIMD/3DNOW!/MMX/FPU 64-bit store here would require at the very + * least an FPU save and/or %cr0.ts manipulation. + * + * cmpxchg8b must be used with the lock prefix here to allow the + * instruction to be executed atomically. We need to have the reader + * side to see the coherent 64bit value. */ -static inline void __set_64bit(unsigned long long *ptr, - unsigned int low, unsigned int high) +static inline void set_64bit(volatile u64 *ptr, u64 value) { + u32 low = value; + u32 high = value >> 32; + u64 prev = *ptr; + asm volatile("\n1:\t" - "movl (%0), %%eax\n\t" - "movl 4(%0), %%edx\n\t" - LOCK_PREFIX "cmpxchg8b (%0)\n\t" + LOCK_PREFIX "cmpxchg8b %0\n\t" "jnz 1b" - : /* no outputs */ - : "D"(ptr), - "b"(low), - "c"(high) - : "ax", "dx", "memory"); -} - -static inline void __set_64bit_constant(unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr, (unsigned int)value, (unsigned int)(value >> 32)); -} - -#define ll_low(x) *(((unsigned int *)&(x)) + 0) -#define ll_high(x) *(((unsigned int *)&(x)) + 1) - -static inline void __set_64bit_var(unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr, ll_low(value), ll_high(value)); + : "=m" (*ptr), "+A" (prev) + : "b" (low), "c" (high) + : "memory"); } -#define set_64bit(ptr, value) \ - (__builtin_constant_p((value)) \ - ? __set_64bit_constant((ptr), (value)) \ - : __set_64bit_var((ptr), (value))) - -#define _set_64bit(ptr, value) \ - (__builtin_constant_p(value) \ - ? __set_64bit(ptr, (unsigned int)(value), \ - (unsigned int)((value) >> 32)) \ - : __set_64bit(ptr, ll_low((value)), ll_high((value)))) - extern void __cmpxchg_wrong_size(void); /* @@ -121,23 +98,32 @@ extern void __cmpxchg_wrong_size(void); __typeof__(*(ptr)) __new = (new); \ switch (size) { \ case 1: \ - asm volatile(lock "cmpxchgb %b1,%2" \ - : "=a"(__ret) \ - : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile(lock "cmpxchgw %w1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile(lock "cmpxchgl %1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ default: \ __cmpxchg_wrong_size(); \ } \ @@ -175,32 +161,28 @@ extern void __cmpxchg_wrong_size(void); (unsigned long long)(n))) #endif -static inline unsigned long long __cmpxchg64(volatile void *ptr, - unsigned long long old, - unsigned long long new) +static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new) { - unsigned long long prev; - asm volatile(LOCK_PREFIX "cmpxchg8b %3" - : "=A"(prev) - : "b"((unsigned long)new), - "c"((unsigned long)(new >> 32)), - "m"(*__xg(ptr)), - "0"(old) + u64 prev; + asm volatile(LOCK_PREFIX "cmpxchg8b %1" + : "=A" (prev), + "+m" (*ptr) + : "b" ((u32)new), + "c" ((u32)(new >> 32)), + "0" (old) : "memory"); return prev; } -static inline unsigned long long __cmpxchg64_local(volatile void *ptr, - unsigned long long old, - unsigned long long new) +static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) { - unsigned long long prev; - asm volatile("cmpxchg8b %3" - : "=A"(prev) - : "b"((unsigned long)new), - "c"((unsigned long)(new >> 32)), - "m"(*__xg(ptr)), - "0"(old) + u64 prev; + asm volatile("cmpxchg8b %1" + : "=A" (prev), + "+m" (*ptr) + : "b" ((u32)new), + "c" ((u32)(new >> 32)), + "0" (old) : "memory"); return prev; } @@ -264,8 +246,6 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old, * to simulate the cmpxchg8b on the 80386 and 80486 CPU. */ -extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64); - #define cmpxchg64(ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ @@ -283,20 +263,20 @@ extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64); __ret; }) - -#define cmpxchg64_local(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - if (likely(boot_cpu_data.x86 > 4)) \ - __ret = (__typeof__(*(ptr)))__cmpxchg64_local((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - else \ - __ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - __ret; \ -}) +#define cmpxchg64_local(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (o); \ + __typeof__(*(ptr)) __new = (n); \ + alternative_io("call cmpxchg8b_emu", \ + "cmpxchg8b (%%esi)" , \ + X86_FEATURE_CX8, \ + "=A" (__ret), \ + "S" ((ptr)), "0" (__old), \ + "b" ((unsigned int)__new), \ + "c" ((unsigned int)(__new>>32)) \ + : "memory"); \ + __ret; }) #endif diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 485ae415fae..423ae58aa02 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -3,51 +3,60 @@ #include <asm/alternative.h> /* Provides LOCK_PREFIX */ -#define __xg(x) ((volatile long *)(x)) - -static inline void set_64bit(volatile unsigned long *ptr, unsigned long val) +static inline void set_64bit(volatile u64 *ptr, u64 val) { *ptr = val; } -#define _set_64bit set_64bit - extern void __xchg_wrong_size(void); extern void __cmpxchg_wrong_size(void); /* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. */ #define __xchg(x, ptr, size) \ ({ \ __typeof(*(ptr)) __x = (x); \ switch (size) { \ case 1: \ - asm volatile("xchgb %b0,%1" \ - : "=q" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile("xchgb %0,%1" \ + : "=q" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile("xchgw %w0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile("xchgw %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile("xchgl %k0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile("xchgl %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 8: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ asm volatile("xchgq %0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ default: \ __xchg_wrong_size(); \ } \ @@ -71,29 +80,41 @@ extern void __cmpxchg_wrong_size(void); __typeof__(*(ptr)) __new = (new); \ switch (size) { \ case 1: \ - asm volatile(lock "cmpxchgb %b1,%2" \ - : "=a"(__ret) \ - : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile(lock "cmpxchgw %w1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile(lock "cmpxchgl %k1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 8: \ - asm volatile(lock "cmpxchgq %1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + asm volatile(lock "cmpxchgq %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ default: \ __cmpxchg_wrong_size(); \ } \ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 46814591438..0b205b8a430 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -6,7 +6,7 @@ #include <asm/required-features.h> -#define NCAPINTS 9 /* N 32-bit words worth of info */ +#define NCAPINTS 10 /* N 32-bit words worth of info */ /* * Note: If the comment begins with a quoted string, that string is used @@ -89,7 +89,7 @@ #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */ #define X86_FEATURE_11AP (3*32+19) /* "" Bad local APIC aka 11AP */ #define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_AMDC1E (3*32+21) /* AMD C1E detected */ + /* 21 available, was AMD_C1E */ #define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */ @@ -124,6 +124,8 @@ #define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ #define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */ #define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */ +#define X86_FEATURE_F16C (4*32+29) /* 16-bit fp conversions */ +#define X86_FEATURE_RDRND (4*32+30) /* The RDRAND instruction */ #define X86_FEATURE_HYPERVISOR (4*32+31) /* Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ @@ -157,22 +159,29 @@ /* * Auxiliary flags: Linux defined - For features scattered in various - * CPUID levels like 0x6, 0xA etc + * CPUID levels like 0x6, 0xA etc, word 7 */ #define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */ #define X86_FEATURE_ARAT (7*32+ 1) /* Always Running APIC Timer */ #define X86_FEATURE_CPB (7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB (7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ +#define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ -/* Virtualization flags: Linux defined */ +/* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ #define X86_FEATURE_VNMI (8*32+ 1) /* Intel Virtual NMI */ #define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */ #define X86_FEATURE_EPT (8*32+ 3) /* Intel Extended Page Table */ #define X86_FEATURE_VPID (8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_NPT (8*32+5) /* AMD Nested Page Table support */ -#define X86_FEATURE_LBRV (8*32+6) /* AMD LBR Virtualization support */ -#define X86_FEATURE_SVML (8*32+7) /* "svm_lock" AMD SVM locking MSR */ -#define X86_FEATURE_NRIPS (8*32+8) /* "nrip_save" AMD SVM next_rip save */ +#define X86_FEATURE_NPT (8*32+ 5) /* AMD Nested Page Table support */ +#define X86_FEATURE_LBRV (8*32+ 6) /* AMD LBR Virtualization support */ +#define X86_FEATURE_SVML (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ +#define X86_FEATURE_NRIPS (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ +#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) @@ -194,7 +203,9 @@ extern const char * const x86_power_flags[32]; (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) || \ (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) || \ (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) || \ - (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ) \ + (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) || \ + (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \ + (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) ) \ ? 1 : \ test_cpu_cap(c, bit)) diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 942255310e6..528a11e8d3e 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -20,10 +20,10 @@ struct arch_hw_breakpoint { #include <linux/list.h> /* Available HW breakpoint length encodings */ +#define X86_BREAKPOINT_LEN_X 0x00 #define X86_BREAKPOINT_LEN_1 0x40 #define X86_BREAKPOINT_LEN_2 0x44 #define X86_BREAKPOINT_LEN_4 0x4c -#define X86_BREAKPOINT_LEN_EXECUTE 0x40 #ifdef CONFIG_X86_64 #define X86_BREAKPOINT_LEN_8 0x48 diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 70abda7058c..ff2546ce717 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -45,5 +45,6 @@ extern const struct hypervisor_x86 *x86_hyper; /* Recognized hypervisors */ extern const struct hypervisor_x86 x86_hyper_vmware; extern const struct hypervisor_x86 x86_hyper_ms_hyperv; +extern const struct hypervisor_x86 x86_hyper_xen_hvm; #endif diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 8767d99c4f6..e2ca3009255 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -125,6 +125,9 @@ */ #define MCE_SELF_VECTOR 0xeb +/* Xen vector callback to receive events in a HVM domain */ +#define XEN_HVM_EVTCHN_CALLBACK 0xe9 + #define NR_VECTORS 256 #define FPU_IRQ 13 diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 006da3687cd..396f5b5fc4d 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -39,9 +39,11 @@ enum regnames { GDB_FS, /* 14 */ GDB_GS, /* 15 */ }; +#define GDB_ORIG_AX 41 +#define DBG_MAX_REG_NUM 16 #define NUMREGBYTES ((GDB_GS+1)*4) #else /* ! CONFIG_X86_32 */ -enum regnames64 { +enum regnames { GDB_AX, /* 0 */ GDB_BX, /* 1 */ GDB_CX, /* 2 */ @@ -59,15 +61,15 @@ enum regnames64 { GDB_R14, /* 14 */ GDB_R15, /* 15 */ GDB_PC, /* 16 */ + GDB_PS, /* 17 */ + GDB_CS, /* 18 */ + GDB_SS, /* 19 */ }; - -enum regnames32 { - GDB_PS = 34, - GDB_CS, - GDB_SS, -}; -#define NUMREGBYTES ((GDB_SS+1)*4) -#endif /* CONFIG_X86_32 */ +#define GDB_ORIG_AX 57 +#define DBG_MAX_REG_NUM 20 +/* 17 64 bit regs and 3 32 bit regs */ +#define NUMREGBYTES ((17 * 8) + (3 * 4)) +#endif /* ! CONFIG_X86_32 */ static inline void arch_kgdb_breakpoint(void) { diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/x86/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 451d30e7f62..16350740edf 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -13,6 +13,32 @@ extern int pci_mrst_init(void); int __init sfi_parse_mrtc(struct sfi_table_header *table); +/* + * Medfield is the follow-up of Moorestown, it combines two chip solution into + * one. Other than that it also added always-on and constant tsc and lapic + * timers. Medfield is the platform name, and the chip name is called Penwell + * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be + * identified via MSRs. + */ +enum mrst_cpu_type { + MRST_CPU_CHIP_LINCROFT = 1, + MRST_CPU_CHIP_PENWELL, +}; + +extern enum mrst_cpu_type __mrst_cpu_chip; +static enum mrst_cpu_type mrst_identify_cpu(void) +{ + return __mrst_cpu_chip; +} + +enum mrst_timer_options { + MRST_TIMER_DEFAULT, + MRST_TIMER_APBT_ONLY, + MRST_TIMER_LAPIC_APBT, +}; + +extern enum mrst_timer_options mrst_timer_options; + #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 509a42187dc..65bbec2093a 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -161,8 +161,6 @@ #define MSR_K7_FID_VID_STATUS 0xc0010042 /* K6 MSRs */ -#define MSR_K6_EFER 0xc0000080 -#define MSR_K6_STAR 0xc0000081 #define MSR_K6_WHCR 0xc0000082 #define MSR_K6_UWCCR 0xc0000085 #define MSR_K6_EPMR 0xc0000086 @@ -226,12 +224,14 @@ #define MSR_IA32_THERM_CONTROL 0x0000019a #define MSR_IA32_THERM_INTERRUPT 0x0000019b -#define THERM_INT_LOW_ENABLE (1 << 0) -#define THERM_INT_HIGH_ENABLE (1 << 1) +#define THERM_INT_HIGH_ENABLE (1 << 0) +#define THERM_INT_LOW_ENABLE (1 << 1) +#define THERM_INT_PLN_ENABLE (1 << 24) #define MSR_IA32_THERM_STATUS 0x0000019c #define THERM_STATUS_PROCHOT (1 << 0) +#define THERM_STATUS_POWER_LIMIT (1 << 10) #define MSR_THERM2_CTL 0x0000019d @@ -241,6 +241,19 @@ #define MSR_IA32_TEMPERATURE_TARGET 0x000001a2 +#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 + +#define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1 + +#define PACKAGE_THERM_STATUS_PROCHOT (1 << 0) +#define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10) + +#define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2 + +#define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0) +#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1) +#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24) + /* MISC_ENABLE bits: architectural */ #define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << 0) #define MSR_IA32_MISC_ENABLE_TCC (1ULL << 1) diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index c5bc4c2d33f..084ef95274c 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -148,8 +148,8 @@ static inline unsigned long long native_read_pmc(int counter) #define rdmsr(msr, val1, val2) \ do { \ u64 __val = native_read_msr((msr)); \ - (val1) = (u32)__val; \ - (val2) = (u32)(__val >> 32); \ + (void)((val1) = (u32)__val); \ + (void)((val2) = (u32)(__val >> 32)); \ } while (0) static inline void wrmsr(unsigned msr, unsigned low, unsigned high) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 93da9c3f334..932f0f86b4b 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -17,7 +17,9 @@ int do_nmi_callback(struct pt_regs *regs, int cpu); extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int check_nmi_watchdog(void); +#if !defined(CONFIG_LOCKUP_DETECTOR) extern int nmi_watchdog_enabled; +#endif extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 254883d0c7e..6e742cc4251 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -68,8 +68,9 @@ union cpuid10_eax { union cpuid10_edx { struct { - unsigned int num_counters_fixed:4; - unsigned int reserved:28; + unsigned int num_counters_fixed:5; + unsigned int bit_width_fixed:8; + unsigned int reserved:19; } split; unsigned int full; }; @@ -140,6 +141,19 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) +#include <asm/stacktrace.h> + +/* + * We abuse bit 3 from flags to pass exact information, see perf_misc_flags + * and the comment with PERF_EFLAGS_EXACT. + */ +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->ip = (__ip); \ + (regs)->bp = caller_frame_pointer(); \ + (regs)->cs = __KERNEL_CS; \ + regs->flags = 0; \ +} + #else static inline void init_hw_perf_events(void) { } static inline void perf_events_lapic_init(void) { } diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 64a8ebff06f..def500776b1 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -19,7 +19,6 @@ #define ARCH_P4_RESERVED_ESCR (2) /* IQ_ESCR(0,1) not always present */ #define ARCH_P4_MAX_ESCR (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR) #define ARCH_P4_MAX_CCCR (18) -#define ARCH_P4_MAX_COUNTER (ARCH_P4_MAX_CCCR / 2) #define P4_ESCR_EVENT_MASK 0x7e000000U #define P4_ESCR_EVENT_SHIFT 25 @@ -71,10 +70,6 @@ #define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) #define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) -/* Custom bits in reerved CCCR area */ -#define P4_CCCR_CACHE_OPS_MASK 0x0000003fU - - /* Non HT mask */ #define P4_CCCR_MASK \ (P4_CCCR_OVF | \ @@ -106,8 +101,7 @@ * ESCR and CCCR but rather an only packed value should * be unpacked and written to a proper addresses * - * the base idea is to pack as much info as - * possible + * the base idea is to pack as much info as possible */ #define p4_config_pack_escr(v) (((u64)(v)) << 32) #define p4_config_pack_cccr(v) (((u64)(v)) & 0xffffffffULL) @@ -130,8 +124,6 @@ t; \ }) -#define p4_config_unpack_cache_event(v) (((u64)(v)) & P4_CCCR_CACHE_OPS_MASK) - #define P4_CONFIG_HT_SHIFT 63 #define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) @@ -214,6 +206,12 @@ static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr) return escr; } +/* + * This are the events which should be used in "Event Select" + * field of ESCR register, they are like unique keys which allow + * the kernel to determinate which CCCR and COUNTER should be + * used to track an event + */ enum P4_EVENTS { P4_EVENT_TC_DELIVER_MODE, P4_EVENT_BPU_FETCH_REQUEST, @@ -561,7 +559,7 @@ enum P4_EVENT_OPCODES { * a caller should use P4_ESCR_EMASK_NAME helper to * pick the EventMask needed, for example * - * P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD) + * P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD) */ enum P4_ESCR_EMASKS { P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0), @@ -753,43 +751,50 @@ enum P4_ESCR_EMASKS { P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1), }; -/* P4 PEBS: stale for a while */ -#define P4_PEBS_METRIC_MASK 0x00001fffU -#define P4_PEBS_UOB_TAG 0x01000000U -#define P4_PEBS_ENABLE 0x02000000U - -/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */ -#define P4_PEBS__1stl_cache_load_miss_retired 0x3000001 -#define P4_PEBS__2ndl_cache_load_miss_retired 0x3000002 -#define P4_PEBS__dtlb_load_miss_retired 0x3000004 -#define P4_PEBS__dtlb_store_miss_retired 0x3000004 -#define P4_PEBS__dtlb_all_miss_retired 0x3000004 -#define P4_PEBS__tagged_mispred_branch 0x3018000 -#define P4_PEBS__mob_load_replay_retired 0x3000200 -#define P4_PEBS__split_load_retired 0x3000400 -#define P4_PEBS__split_store_retired 0x3000400 - -#define P4_VERT__1stl_cache_load_miss_retired 0x0000001 -#define P4_VERT__2ndl_cache_load_miss_retired 0x0000001 -#define P4_VERT__dtlb_load_miss_retired 0x0000001 -#define P4_VERT__dtlb_store_miss_retired 0x0000002 -#define P4_VERT__dtlb_all_miss_retired 0x0000003 -#define P4_VERT__tagged_mispred_branch 0x0000010 -#define P4_VERT__mob_load_replay_retired 0x0000001 -#define P4_VERT__split_load_retired 0x0000001 -#define P4_VERT__split_store_retired 0x0000002 - -enum P4_CACHE_EVENTS { - P4_CACHE__NONE, - - P4_CACHE__1stl_cache_load_miss_retired, - P4_CACHE__2ndl_cache_load_miss_retired, - P4_CACHE__dtlb_load_miss_retired, - P4_CACHE__dtlb_store_miss_retired, - P4_CACHE__itlb_reference_hit, - P4_CACHE__itlb_reference_miss, - - P4_CACHE__MAX +/* + * P4 PEBS specifics (Replay Event only) + * + * Format (bits): + * 0-6: metric from P4_PEBS_METRIC enum + * 7 : reserved + * 8 : reserved + * 9-11 : reserved + * + * Note we have UOP and PEBS bits reserved for now + * just in case if we will need them once + */ +#define P4_PEBS_CONFIG_ENABLE (1 << 7) +#define P4_PEBS_CONFIG_UOP_TAG (1 << 8) +#define P4_PEBS_CONFIG_METRIC_MASK 0x3f +#define P4_PEBS_CONFIG_MASK 0xff + +/* + * mem: Only counters MSR_IQ_COUNTER4 (16) and + * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling + */ +#define P4_PEBS_ENABLE 0x02000000U +#define P4_PEBS_ENABLE_UOP_TAG 0x01000000U + +#define p4_config_unpack_metric(v) (((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK) +#define p4_config_unpack_pebs(v) (((u64)(v)) & P4_PEBS_CONFIG_MASK) + +#define p4_config_pebs_has(v, mask) (p4_config_unpack_pebs(v) & (mask)) + +enum P4_PEBS_METRIC { + P4_PEBS_METRIC__none, + + P4_PEBS_METRIC__1stl_cache_load_miss_retired, + P4_PEBS_METRIC__2ndl_cache_load_miss_retired, + P4_PEBS_METRIC__dtlb_load_miss_retired, + P4_PEBS_METRIC__dtlb_store_miss_retired, + P4_PEBS_METRIC__dtlb_all_miss_retired, + P4_PEBS_METRIC__tagged_mispred_branch, + P4_PEBS_METRIC__mob_load_replay_retired, + P4_PEBS_METRIC__split_load_retired, + P4_PEBS_METRIC__split_store_retired, + + P4_PEBS_METRIC__max }; #endif /* PERF_EVENT_P4_H */ + diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7e5c6a60b8e..325b7bdbeba 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -762,6 +762,7 @@ extern void init_c1e_mask(void); extern unsigned long boot_option_idle_override; extern unsigned long idle_halt; extern unsigned long idle_nomwait; +extern bool c1e_detected; /* * on systems with caches, caches must be flashed as the absolute @@ -1025,4 +1026,24 @@ unsigned long calc_aperfmperf_ratio(struct aperfmperf *old, return ratio; } +/* + * AMD errata checking + */ +#ifdef CONFIG_CPU_SUP_AMD +extern const int amd_erratum_383[]; +extern const int amd_erratum_400[]; +extern bool cpu_has_amd_erratum(const int *); + +#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } +#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } +#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ + ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) +#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) +#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) +#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) + +#else +#define cpu_has_amd_erratum(x) (false) +#endif /* CONFIG_CPU_SUP_AMD */ + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 64cf2d24fad..6c7fc25f2c3 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -84,5 +84,7 @@ #define REQUIRED_MASK5 0 #define REQUIRED_MASK6 0 #define REQUIRED_MASK7 0 +#define REQUIRED_MASK8 0 +#define REQUIRED_MASK9 0 #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index 606ede12697..d1e41b0f9b6 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -118,7 +118,7 @@ static inline void __down_read(struct rw_semaphore *sem) { asm volatile("# beginning down_read\n\t" LOCK_PREFIX _ASM_INC "(%1)\n\t" - /* adds 0x00000001, returns the old value */ + /* adds 0x00000001 */ " jns 1f\n" " call call_rwsem_down_read_failed\n" "1:\n\t" @@ -156,11 +156,9 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) { rwsem_count_t tmp; - - tmp = RWSEM_ACTIVE_WRITE_BIAS; asm volatile("# beginning down_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" - /* subtract 0x0000ffff, returns the old value */ + /* adds 0xffff0001, returns the old value */ " test %1,%1\n\t" /* was the count 0 before? */ " jz 1f\n" @@ -168,7 +166,7 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) "1:\n" "# ending down_write" : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (tmp) + : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) : "memory", "cc"); } @@ -195,16 +193,16 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) */ static inline void __up_read(struct rw_semaphore *sem) { - rwsem_count_t tmp = -RWSEM_ACTIVE_READ_BIAS; + rwsem_count_t tmp; asm volatile("# beginning __up_read\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* subtracts 1, returns the old value */ " jns 1f\n\t" - " call call_rwsem_wake\n" + " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n" "# ending __up_read\n" : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (tmp) + : "a" (sem), "1" (-RWSEM_ACTIVE_READ_BIAS) : "memory", "cc"); } @@ -216,10 +214,9 @@ static inline void __up_write(struct rw_semaphore *sem) rwsem_count_t tmp; asm volatile("# beginning __up_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" - /* tries to transition - 0xffff0001 -> 0x00000000 */ - " jz 1f\n" - " call call_rwsem_wake\n" + /* subtracts 0xffff0001, returns the old value */ + " jns 1f\n\t" + " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n\t" "# ending __up_write\n" : "+m" (sem->count), "=d" (tmp) diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 86b1506f417..ef292c792d7 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -82,7 +82,7 @@ void *extend_brk(size_t size, size_t align); * executable.) */ #define RESERVE_BRK(name,sz) \ - static void __section(.discard) __used \ + static void __section(.discard.text) __used \ __brk_reservation_fn_##name##__(void) { \ asm volatile ( \ ".pushsection .brk_reservation,\"aw\",@nobits;" \ diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 4dab78edbad..2b16a2ad23d 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -1,6 +1,13 @@ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + */ + #ifndef _ASM_X86_STACKTRACE_H #define _ASM_X86_STACKTRACE_H +#include <linux/uaccess.h> + extern int kstack_depth_to_print; struct thread_info; @@ -42,4 +49,46 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data); +#ifdef CONFIG_X86_32 +#define STACKSLOTS_PER_LINE 8 +#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) +#else +#define STACKSLOTS_PER_LINE 4 +#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) +#endif + +extern void +show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, char *log_lvl); + +extern void +show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, unsigned long bp, char *log_lvl); + +extern unsigned int code_bytes; + +/* The form of the top of the frame on the stack */ +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +struct stack_frame_ia32 { + u32 next_frame; + u32 return_address; +}; + +static inline unsigned long caller_frame_pointer(void) +{ + struct stack_frame *frame; + + get_bp(frame); + +#ifdef CONFIG_FRAME_POINTER + frame = frame->next_frame; +#endif + + return (unsigned long)frame; +} + #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 9c371e4a9fa..7fda040a76c 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -417,6 +417,12 @@ HYPERVISOR_nmi_op(unsigned long op, unsigned long arg) return _hypercall2(int, nmi_op, op, arg); } +static inline unsigned long __must_check +HYPERVISOR_hvm_op(int op, void *arg) +{ + return _hypercall2(unsigned long, hvm_op, op, arg); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S index 580b4e29601..28595d6df47 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.S +++ b/arch/x86/kernel/acpi/realmode/wakeup.S @@ -104,7 +104,7 @@ _start: movl %eax, %ecx orl %edx, %ecx jz 1f - movl $0xc0000080, %ecx + movl $MSR_EFER, %ecx wrmsr 1: diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 0d20286d78c..fa044e1e30a 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -2572,6 +2572,11 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, static int amd_iommu_domain_has_cap(struct iommu_domain *domain, unsigned long cap) { + switch (cap) { + case IOMMU_CAP_CACHE_COHERENCY: + return 1; + } + return 0; } @@ -2609,8 +2614,7 @@ int __init amd_iommu_init_passthrough(void) pt_domain->mode |= PAGE_MODE_NONE; - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - + for_each_pci_dev(dev) { if (!check_device(&dev->dev)) continue; diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index a35347501d3..8dd77800ff5 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -43,10 +43,11 @@ #include <asm/fixmap.h> #include <asm/apb_timer.h> +#include <asm/mrst.h> #define APBT_MASK CLOCKSOURCE_MASK(32) #define APBT_SHIFT 22 -#define APBT_CLOCKEVENT_RATING 150 +#define APBT_CLOCKEVENT_RATING 110 #define APBT_CLOCKSOURCE_RATING 250 #define APBT_MIN_DELTA_USEC 200 @@ -83,8 +84,6 @@ struct apbt_dev { char name[10]; }; -int disable_apbt_percpu __cpuinitdata; - static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev); #ifdef CONFIG_SMP @@ -195,29 +194,6 @@ static struct clock_event_device apbt_clockevent = { }; /* - * if user does not want to use per CPU apb timer, just give it a lower rating - * than local apic timer and skip the late per cpu timer init. - */ -static inline int __init setup_x86_mrst_timer(char *arg) -{ - if (!arg) - return -EINVAL; - - if (strcmp("apbt_only", arg) == 0) - disable_apbt_percpu = 0; - else if (strcmp("lapic_and_apbt", arg) == 0) - disable_apbt_percpu = 1; - else { - pr_warning("X86 MRST timer option %s not recognised" - " use x86_mrst_timer=apbt_only or lapic_and_apbt\n", - arg); - return -EINVAL; - } - return 0; -} -__setup("x86_mrst_timer=", setup_x86_mrst_timer); - -/* * start count down from 0xffff_ffff. this is done by toggling the enable bit * then load initial load count to ~0. */ @@ -335,7 +311,7 @@ static int __init apbt_clockevent_register(void) adev->num = smp_processor_id(); memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device)); - if (disable_apbt_percpu) { + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100; global_clock_event = &adev->evt; printk(KERN_DEBUG "%s clockevent registered as global\n", @@ -429,7 +405,8 @@ static int apbt_cpuhp_notify(struct notifier_block *n, static __init int apbt_late_init(void) { - if (disable_apbt_percpu || !apb_timer_block_enabled) + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT || + !apb_timer_block_enabled) return 0; /* This notifier should be called after workqueue is ready */ hotcpu_notifier(apbt_cpuhp_notify, -20); @@ -450,6 +427,8 @@ static void apbt_set_mode(enum clock_event_mode mode, int timer_num; struct apbt_dev *adev = EVT_TO_APBT_DEV(evt); + BUG_ON(!apbt_virt_address); + timer_num = adev->num; pr_debug("%s CPU %d timer %d mode=%d\n", __func__, first_cpu(*evt->cpumask), timer_num, mode); @@ -676,7 +655,7 @@ void __init apbt_time_init(void) } #ifdef CONFIG_SMP /* kernel cmdline disable apb timer, so we will use lapic timers */ - if (disable_apbt_percpu) { + if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { printk(KERN_INFO "apbt: disabled per cpu timer\n"); return; } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index b5d8b0bcf23..a2e0caf26e1 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -280,7 +280,7 @@ void __init early_gart_iommu_check(void) * or BIOS forget to put that in reserved. * try to update e820 to make that region as reserved. */ - u32 agp_aper_base = 0, agp_aper_order = 0; + u32 agp_aper_order = 0; int i, fix, slot, valid_agp = 0; u32 ctl; u32 aper_size = 0, aper_order = 0, last_aper_order = 0; @@ -291,7 +291,7 @@ void __init early_gart_iommu_check(void) return; /* This is mostly duplicate of iommu_hole_init */ - agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp); + search_agp_bridge(&agp_aper_order, &valid_agp); fix = 0; for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 565c1bfc507..910f20b457c 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -2,7 +2,12 @@ # Makefile for local APIC drivers and for the IO-APIC code # -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o nmi.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o +ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y) +obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o +endif +obj-$(CONFIG_HARDLOCKUP_DETECTOR) += hw_nmi.o + obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_SMP) += ipi.o diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c new file mode 100644 index 00000000000..cefd6942f0e --- /dev/null +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -0,0 +1,107 @@ +/* + * HW NMI watchdog support + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * Arch specific calls to support NMI watchdog + * + * Bits copied from original nmi.c file + * + */ +#include <asm/apic.h> + +#include <linux/cpumask.h> +#include <linux/kdebug.h> +#include <linux/notifier.h> +#include <linux/kprobes.h> +#include <linux/nmi.h> +#include <linux/module.h> + +/* For reliability, we're prepared to waste bits here. */ +static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; + +u64 hw_nmi_get_sample_period(void) +{ + return (u64)(cpu_khz) * 1000 * 60; +} + +#ifdef ARCH_HAS_NMI_WATCHDOG +void arch_trigger_all_cpu_backtrace(void) +{ + int i; + + cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); + + printk(KERN_INFO "sending NMI to all CPUs:\n"); + apic->send_IPI_all(NMI_VECTOR); + + /* Wait for up to 10 seconds for all CPUs to do the backtrace */ + for (i = 0; i < 10 * 1000; i++) { + if (cpumask_empty(to_cpumask(backtrace_mask))) + break; + mdelay(1); + } +} + +static int __kprobes +arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, + unsigned long cmd, void *__args) +{ + struct die_args *args = __args; + struct pt_regs *regs; + int cpu = smp_processor_id(); + + switch (cmd) { + case DIE_NMI: + case DIE_NMI_IPI: + break; + + default: + return NOTIFY_DONE; + } + + regs = args->regs; + + if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { + static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; + + arch_spin_lock(&lock); + printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); + show_regs(regs); + dump_stack(); + arch_spin_unlock(&lock); + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); + return NOTIFY_STOP; + } + + return NOTIFY_DONE; +} + +static __read_mostly struct notifier_block backtrace_notifier = { + .notifier_call = arch_trigger_all_cpu_backtrace_handler, + .next = NULL, + .priority = 1 +}; + +static int __init register_trigger_all_cpu_backtrace(void) +{ + register_die_notifier(&backtrace_notifier); + return 0; +} +early_initcall(register_trigger_all_cpu_backtrace); +#endif + +/* STUB calls to mimic old nmi_watchdog behaviour */ +#if defined(CONFIG_X86_LOCAL_APIC) +unsigned int nmi_watchdog = NMI_NONE; +EXPORT_SYMBOL(nmi_watchdog); +void acpi_nmi_enable(void) { return; } +void acpi_nmi_disable(void) { return; } +#endif +atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */ +EXPORT_SYMBOL(nmi_active); +int unknown_nmi_panic; +void cpu_nmi_set_wd_enabled(void) { return; } +void stop_apic_nmi_watchdog(void *unused) { return; } +void setup_apic_nmi_watchdog(void *unused) { return; } +int __init check_nmi_watchdog(void) { return 0; } diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index 1edaf15c0b8..a43f71cb30f 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -401,13 +401,6 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) int cpu = smp_processor_id(); int rc = 0; - /* check for other users first */ - if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) - == NOTIFY_STOP) { - rc = 1; - touched = 1; - } - sum = get_timer_irqs(cpu); if (__get_cpu_var(nmi_touch)) { diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 3a785da34b6..3f0ebe429a0 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -12,11 +12,11 @@ endif nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_common.o := $(nostackp) -obj-y := intel_cacheinfo.o addon_cpuid_features.o +obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o obj-y += vmware.o hypervisor.o sched.o mshyperv.o -obj-$(CONFIG_X86_32) += bugs.o cmpxchg.o +obj-$(CONFIG_X86_32) += bugs.o obj-$(CONFIG_X86_64) += bugs_64.o obj-$(CONFIG_CPU_SUP_INTEL) += intel.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e485825130d..60a57b13082 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -466,7 +466,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) } } - if (c->x86 == 0x10 || c->x86 == 0x11) + if (c->x86 >= 0x10) set_cpu_cap(c, X86_FEATURE_REP_GOOD); /* get apicid instead of initial apic id from cpuid */ @@ -529,7 +529,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) num_cache_leaves = 3; } - if (c->x86 >= 0xf && c->x86 <= 0x11) + if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has_xmm2) { @@ -546,7 +546,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) fam10h_check_enable_mmcfg(); } - if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) { + if (c == &boot_cpu_data && c->x86 >= 0xf) { unsigned long long tseg; /* @@ -609,3 +609,74 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = { }; cpu_dev_register(amd_cpu_dev); + +/* + * AMD errata checking + * + * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or + * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that + * have an OSVW id assigned, which it takes as first argument. Both take a + * variable number of family-specific model-stepping ranges created by + * AMD_MODEL_RANGE(). Each erratum also has to be declared as extern const + * int[] in arch/x86/include/asm/processor.h. + * + * Example: + * + * const int amd_erratum_319[] = + * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2), + * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0), + * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); + */ + +const int amd_erratum_400[] = + AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), + AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); +EXPORT_SYMBOL_GPL(amd_erratum_400); + +const int amd_erratum_383[] = + AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); +EXPORT_SYMBOL_GPL(amd_erratum_383); + +bool cpu_has_amd_erratum(const int *erratum) +{ + struct cpuinfo_x86 *cpu = ¤t_cpu_data; + int osvw_id = *erratum++; + u32 range; + u32 ms; + + /* + * If called early enough that current_cpu_data hasn't been initialized + * yet, fall back to boot_cpu_data. + */ + if (cpu->x86 == 0) + cpu = &boot_cpu_data; + + if (cpu->x86_vendor != X86_VENDOR_AMD) + return false; + + if (osvw_id >= 0 && osvw_id < 65536 && + cpu_has(cpu, X86_FEATURE_OSVW)) { + u64 osvw_len; + + rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len); + if (osvw_id < osvw_len) { + u64 osvw_bits; + + rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6), + osvw_bits); + return osvw_bits & (1ULL << (osvw_id & 0x3f)); + } + } + + /* OSVW unavailable or ID unknown, match family-model-stepping range */ + ms = (cpu->x86_model << 8) | cpu->x86_mask; + while ((range = *erratum++)) + if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && + (ms >= AMD_MODEL_RANGE_START(range)) && + (ms <= AMD_MODEL_RANGE_END(range))) + return true; + + return false; +} + +EXPORT_SYMBOL_GPL(cpu_has_amd_erratum); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 68e4a6f2211..f1027313838 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -551,6 +551,16 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[4] = excap; } + /* Additional Intel-defined flags: level 0x00000007 */ + if (c->cpuid_level >= 0x00000007) { + u32 eax, ebx, ecx, edx; + + cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); + + if (eax > 0) + c->x86_capability[9] = ebx; + } + /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); c->extended_cpuid_level = xlvl; @@ -576,6 +586,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + init_scattered_cpuid_features(c); } static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -731,7 +742,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ - init_scattered_cpuid_features(c); detect_nopl(c); } diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index dd531cc56a8..8095f8611f8 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -34,6 +34,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = { &x86_hyper_vmware, &x86_hyper_ms_hyperv, +#ifdef CONFIG_XEN_PVHVM + &x86_hyper_xen_hvm, +#endif }; const struct hypervisor_x86 *x86_hyper; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 33eae2062cf..898c2f4eab8 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -347,8 +347,8 @@ static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node) return l3; } -static void __cpuinit -amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) +static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, + int index) { int node; @@ -396,20 +396,39 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) this_leaf->l3 = l3_caches[node]; } +/* + * check whether a slot used for disabling an L3 index is occupied. + * @l3: L3 cache descriptor + * @slot: slot number (0..1) + * + * @returns: the disabled index if used or negative value if slot free. + */ +int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot) +{ + unsigned int reg = 0; + + pci_read_config_dword(l3->dev, 0x1BC + slot * 4, ®); + + /* check whether this slot is activated already */ + if (reg & (3UL << 30)) + return reg & 0xfff; + + return -1; +} + static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, unsigned int slot) { - struct pci_dev *dev = this_leaf->l3->dev; - unsigned int reg = 0; + int index; if (!this_leaf->l3 || !this_leaf->l3->can_disable) return -EINVAL; - if (!dev) - return -EINVAL; + index = amd_get_l3_disable_slot(this_leaf->l3, slot); + if (index >= 0) + return sprintf(buf, "%d\n", index); - pci_read_config_dword(dev, 0x1BC + slot * 4, ®); - return sprintf(buf, "0x%08x\n", reg); + return sprintf(buf, "FREE\n"); } #define SHOW_CACHE_DISABLE(slot) \ @@ -451,37 +470,74 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu, } } - -static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, - const char *buf, size_t count, - unsigned int slot) +/* + * disable a L3 cache index by using a disable-slot + * + * @l3: L3 cache descriptor + * @cpu: A CPU on the node containing the L3 cache + * @slot: slot number (0..1) + * @index: index to disable + * + * @return: 0 on success, error status on failure + */ +int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot, + unsigned long index) { - struct pci_dev *dev = this_leaf->l3->dev; - int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - unsigned long val = 0; + int ret = 0; #define SUBCACHE_MASK (3UL << 20) #define SUBCACHE_INDEX 0xfff - if (!this_leaf->l3 || !this_leaf->l3->can_disable) + /* + * check whether this slot is already used or + * the index is already disabled + */ + ret = amd_get_l3_disable_slot(l3, slot); + if (ret >= 0) return -EINVAL; + /* + * check whether the other slot has disabled the + * same index already + */ + if (index == amd_get_l3_disable_slot(l3, !slot)) + return -EINVAL; + + /* do not allow writes outside of allowed bits */ + if ((index & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) || + ((index & SUBCACHE_INDEX) > l3->indices)) + return -EINVAL; + + amd_l3_disable_index(l3, cpu, slot, index); + + return 0; +} + +static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, + const char *buf, size_t count, + unsigned int slot) +{ + unsigned long val = 0; + int cpu, err = 0; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!dev) + if (!this_leaf->l3 || !this_leaf->l3->can_disable) return -EINVAL; - if (strict_strtoul(buf, 10, &val) < 0) - return -EINVAL; + cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); - /* do not allow writes outside of allowed bits */ - if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) || - ((val & SUBCACHE_INDEX) > this_leaf->l3->indices)) + if (strict_strtoul(buf, 10, &val) < 0) return -EINVAL; - amd_l3_disable_index(this_leaf->l3, cpu, slot, val); - + err = amd_set_l3_disable_slot(this_leaf->l3, cpu, slot, val); + if (err) { + if (err == -EEXIST) + printk(KERN_WARNING "L3 disable slot %d in use!\n", + slot); + return err; + } return count; } @@ -502,7 +558,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, #else /* CONFIG_CPU_SUP_AMD */ static void __cpuinit -amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf) +amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index) { }; #endif /* CONFIG_CPU_SUP_AMD */ @@ -518,7 +574,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index, if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { amd_cpuid4(index, &eax, &ebx, &ecx); - amd_check_l3_disable(index, this_leaf); + amd_check_l3_disable(this_leaf, index); } else { cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 1970ef911c9..e1269d62c56 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -51,7 +51,7 @@ static DEFINE_MUTEX(mce_read_mutex); #define rcu_dereference_check_mce(p) \ - rcu_dereference_check((p), \ + rcu_dereference_index_check((p), \ rcu_read_lock_sched_held() || \ lockdep_is_held(&mce_read_mutex)) diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index e1a0a3bf971..c2a8b26d4fe 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -34,15 +34,25 @@ /* How long to wait between reporting thermal events */ #define CHECK_INTERVAL (300 * HZ) +#define THERMAL_THROTTLING_EVENT 0 +#define POWER_LIMIT_EVENT 1 + /* - * Current thermal throttling state: + * Current thermal event state: */ -struct thermal_state { - bool is_throttled; - +struct _thermal_state { + bool new_event; + int event; u64 next_check; - unsigned long throttle_count; - unsigned long last_throttle_count; + unsigned long count; + unsigned long last_count; +}; + +struct thermal_state { + struct _thermal_state core_throttle; + struct _thermal_state core_power_limit; + struct _thermal_state package_throttle; + struct _thermal_state package_power_limit; }; static DEFINE_PER_CPU(struct thermal_state, thermal_state); @@ -53,11 +63,13 @@ static u32 lvtthmr_init __read_mostly; #ifdef CONFIG_SYSFS #define define_therm_throt_sysdev_one_ro(_name) \ - static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL) + static SYSDEV_ATTR(_name, 0444, \ + therm_throt_sysdev_show_##_name, \ + NULL) \ -#define define_therm_throt_sysdev_show_func(name) \ +#define define_therm_throt_sysdev_show_func(event, name) \ \ -static ssize_t therm_throt_sysdev_show_##name( \ +static ssize_t therm_throt_sysdev_show_##event##_##name( \ struct sys_device *dev, \ struct sysdev_attribute *attr, \ char *buf) \ @@ -66,30 +78,42 @@ static ssize_t therm_throt_sysdev_show_##name( \ ssize_t ret; \ \ preempt_disable(); /* CPU hotplug */ \ - if (cpu_online(cpu)) \ + if (cpu_online(cpu)) { \ ret = sprintf(buf, "%lu\n", \ - per_cpu(thermal_state, cpu).name); \ - else \ + per_cpu(thermal_state, cpu).event.name); \ + } else \ ret = 0; \ preempt_enable(); \ \ return ret; \ } -define_therm_throt_sysdev_show_func(throttle_count); -define_therm_throt_sysdev_one_ro(throttle_count); +define_therm_throt_sysdev_show_func(core_throttle, count); +define_therm_throt_sysdev_one_ro(core_throttle_count); + +define_therm_throt_sysdev_show_func(core_power_limit, count); +define_therm_throt_sysdev_one_ro(core_power_limit_count); + +define_therm_throt_sysdev_show_func(package_throttle, count); +define_therm_throt_sysdev_one_ro(package_throttle_count); + +define_therm_throt_sysdev_show_func(package_power_limit, count); +define_therm_throt_sysdev_one_ro(package_power_limit_count); static struct attribute *thermal_throttle_attrs[] = { - &attr_throttle_count.attr, + &attr_core_throttle_count.attr, NULL }; -static struct attribute_group thermal_throttle_attr_group = { +static struct attribute_group thermal_attr_group = { .attrs = thermal_throttle_attrs, .name = "thermal_throttle" }; #endif /* CONFIG_SYSFS */ +#define CORE_LEVEL 0 +#define PACKAGE_LEVEL 1 + /*** * therm_throt_process - Process thermal throttling event from interrupt * @curr: Whether the condition is current or not (boolean), since the @@ -106,39 +130,70 @@ static struct attribute_group thermal_throttle_attr_group = { * 1 : Event should be logged further, and a message has been * printed to the syslog. */ -static int therm_throt_process(bool is_throttled) +static int therm_throt_process(bool new_event, int event, int level) { - struct thermal_state *state; - unsigned int this_cpu; - bool was_throttled; + struct _thermal_state *state; + unsigned int this_cpu = smp_processor_id(); + bool old_event; u64 now; + struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); - this_cpu = smp_processor_id(); now = get_jiffies_64(); - state = &per_cpu(thermal_state, this_cpu); + if (level == CORE_LEVEL) { + if (event == THERMAL_THROTTLING_EVENT) + state = &pstate->core_throttle; + else if (event == POWER_LIMIT_EVENT) + state = &pstate->core_power_limit; + else + return 0; + } else if (level == PACKAGE_LEVEL) { + if (event == THERMAL_THROTTLING_EVENT) + state = &pstate->package_throttle; + else if (event == POWER_LIMIT_EVENT) + state = &pstate->package_power_limit; + else + return 0; + } else + return 0; - was_throttled = state->is_throttled; - state->is_throttled = is_throttled; + old_event = state->new_event; + state->new_event = new_event; - if (is_throttled) - state->throttle_count++; + if (new_event) + state->count++; if (time_before64(now, state->next_check) && - state->throttle_count != state->last_throttle_count) + state->count != state->last_count) return 0; state->next_check = now + CHECK_INTERVAL; - state->last_throttle_count = state->throttle_count; + state->last_count = state->count; /* if we just entered the thermal event */ - if (is_throttled) { - printk(KERN_CRIT "CPU%d: Temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, state->throttle_count); + if (new_event) { + if (event == THERMAL_THROTTLING_EVENT) + printk(KERN_CRIT "CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package", + state->count); + else + printk(KERN_CRIT "CPU%d: %s power limit notification (total events = %lu)\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package", + state->count); add_taint(TAINT_MACHINE_CHECK); return 1; } - if (was_throttled) { - printk(KERN_INFO "CPU%d: Temperature/speed normal\n", this_cpu); + if (old_event) { + if (event == THERMAL_THROTTLING_EVENT) + printk(KERN_INFO "CPU%d: %s temperature/speed normal\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package"); + else + printk(KERN_INFO "CPU%d: %s power limit normal\n", + this_cpu, + level == CORE_LEVEL ? "Core" : "Package"); return 1; } @@ -149,13 +204,32 @@ static int therm_throt_process(bool is_throttled) /* Add/Remove thermal_throttle interface for CPU device: */ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev) { - return sysfs_create_group(&sys_dev->kobj, - &thermal_throttle_attr_group); + int err; + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + + err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group); + if (err) + return err; + + if (cpu_has(c, X86_FEATURE_PLN)) + err = sysfs_add_file_to_group(&sys_dev->kobj, + &attr_core_power_limit_count.attr, + thermal_attr_group.name); + if (cpu_has(c, X86_FEATURE_PTS)) + err = sysfs_add_file_to_group(&sys_dev->kobj, + &attr_package_throttle_count.attr, + thermal_attr_group.name); + if (cpu_has(c, X86_FEATURE_PLN)) + err = sysfs_add_file_to_group(&sys_dev->kobj, + &attr_package_power_limit_count.attr, + thermal_attr_group.name); + + return err; } static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev) { - sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group); + sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group); } /* Mutex protecting device creation against CPU hotplug: */ @@ -226,14 +300,50 @@ device_initcall(thermal_throttle_init_device); #endif /* CONFIG_SYSFS */ +/* + * Set up the most two significant bit to notify mce log that this thermal + * event type. + * This is a temp solution. May be changed in the future with mce log + * infrasture. + */ +#define CORE_THROTTLED (0) +#define CORE_POWER_LIMIT ((__u64)1 << 62) +#define PACKAGE_THROTTLED ((__u64)2 << 62) +#define PACKAGE_POWER_LIMIT ((__u64)3 << 62) + /* Thermal transition interrupt handler */ static void intel_thermal_interrupt(void) { __u64 msr_val; + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); rdmsrl(MSR_IA32_THERM_STATUS, msr_val); - if (therm_throt_process((msr_val & THERM_STATUS_PROCHOT) != 0)) - mce_log_therm_throt_event(msr_val); + + if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + CORE_LEVEL) != 0) + mce_log_therm_throt_event(CORE_THROTTLED | msr_val); + + if (cpu_has(c, X86_FEATURE_PLN)) + if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, + POWER_LIMIT_EVENT, + CORE_LEVEL) != 0) + mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val); + + if (cpu_has(c, X86_FEATURE_PTS)) { + rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); + if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + PACKAGE_LEVEL) != 0) + mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val); + if (cpu_has(c, X86_FEATURE_PLN)) + if (therm_throt_process(msr_val & + PACKAGE_THERM_STATUS_POWER_LIMIT, + POWER_LIMIT_EVENT, + PACKAGE_LEVEL) != 0) + mce_log_therm_throt_event(PACKAGE_POWER_LIMIT + | msr_val); + } } static void unexpected_thermal_interrupt(void) @@ -335,8 +445,26 @@ void intel_init_thermal(struct cpuinfo_x86 *c) apic_write(APIC_LVTTHMR, h); rdmsr(MSR_IA32_THERM_INTERRUPT, l, h); - wrmsr(MSR_IA32_THERM_INTERRUPT, - l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h); + if (cpu_has(c, X86_FEATURE_PLN)) + wrmsr(MSR_IA32_THERM_INTERRUPT, + l | (THERM_INT_LOW_ENABLE + | THERM_INT_HIGH_ENABLE | THERM_INT_PLN_ENABLE), h); + else + wrmsr(MSR_IA32_THERM_INTERRUPT, + l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h); + + if (cpu_has(c, X86_FEATURE_PTS)) { + rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); + if (cpu_has(c, X86_FEATURE_PLN)) + wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, + l | (PACKAGE_THERM_INT_LOW_ENABLE + | PACKAGE_THERM_INT_HIGH_ENABLE + | PACKAGE_THERM_INT_PLN_ENABLE), h); + else + wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, + l | (PACKAGE_THERM_INT_LOW_ENABLE + | PACKAGE_THERM_INT_HIGH_ENABLE), h); + } smp_thermal_vector = intel_thermal_interrupt; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fd31a441c61..7d28d7d0388 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -433,13 +433,12 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, { unsigned int mask_lo, mask_hi, base_lo, base_hi; unsigned int tmp, hi; - int cpu; /* * get_mtrr doesn't need to update mtrr_state, also it could be called * from any cpu, so try to print it out directly. */ - cpu = get_cpu(); + get_cpu(); rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5db5b7d65a1..f2da20fda02 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -220,6 +220,7 @@ struct x86_pmu { struct perf_event *event); struct event_constraint *event_constraints; void (*quirks)(void); + int perfctr_second_write; int (*cpu_prepare)(int cpu); void (*cpu_starting)(int cpu); @@ -295,10 +296,10 @@ x86_perf_event_update(struct perf_event *event) * count to the generic event atomically: */ again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); rdmsrl(hwc->event_base + idx, new_raw_count); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; @@ -313,8 +314,8 @@ again: delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - atomic64_add(delta, &event->count); - atomic64_sub(delta, &hwc->period_left); + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); return new_raw_count; } @@ -438,7 +439,7 @@ static int x86_setup_perfctr(struct perf_event *event) if (!hwc->sample_period) { hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; - atomic64_set(&hwc->period_left, hwc->sample_period); + local64_set(&hwc->period_left, hwc->sample_period); } else { /* * If we have a PMU initialized but no APIC @@ -885,7 +886,7 @@ static int x86_perf_event_set_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - s64 left = atomic64_read(&hwc->period_left); + s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0, idx = hwc->idx; @@ -897,14 +898,14 @@ x86_perf_event_set_period(struct perf_event *event) */ if (unlikely(left <= -period)) { left = period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } @@ -923,10 +924,19 @@ x86_perf_event_set_period(struct perf_event *event) * The hw event starts counting from this event offset, * mark it to be able to extra future deltas: */ - atomic64_set(&hwc->prev_count, (u64)-left); + local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base + idx, + wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask); + + /* + * Due to erratum on certan cpu we need + * a second write to be sure the register + * is updated properly + */ + if (x86_pmu.perfctr_second_write) { + wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask); + } perf_event_update_userpage(event); @@ -969,7 +979,7 @@ static int x86_pmu_enable(struct perf_event *event) * skip the schedulability test here, it will be peformed * at commit time(->commit_txn) as a whole */ - if (cpuc->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuc->group_flag & PERF_EVENT_TXN) goto out; ret = x86_pmu.schedule_events(cpuc, n, assign); @@ -1096,7 +1106,7 @@ static void x86_pmu_disable(struct perf_event *event) * The events never got scheduled and ->cancel_txn will truncate * the event_list. */ - if (cpuc->group_flag & PERF_EVENT_TXN_STARTED) + if (cpuc->group_flag & PERF_EVENT_TXN) return; x86_pmu_stop(event); @@ -1388,7 +1398,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - cpuc->group_flag |= PERF_EVENT_TXN_STARTED; + cpuc->group_flag |= PERF_EVENT_TXN; cpuc->n_txn = 0; } @@ -1401,7 +1411,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED; + cpuc->group_flag &= ~PERF_EVENT_TXN; /* * Truncate the collected events. */ @@ -1435,11 +1445,7 @@ static int x86_pmu_commit_txn(const struct pmu *pmu) */ memcpy(cpuc->assign, assign, n*sizeof(int)); - /* - * Clear out the txn count so that ->cancel_txn() which gets - * run after ->commit_txn() doesn't undo things. - */ - cpuc->n_txn = 0; + cpuc->group_flag &= ~PERF_EVENT_TXN; return 0; } @@ -1607,8 +1613,6 @@ static const struct stacktrace_ops backtrace_ops = { .walk_stack = print_context_stack_bp, }; -#include "../dumpstack.h" - static void perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) { @@ -1730,22 +1734,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } -void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) -{ - regs->ip = ip; - /* - * perf_arch_fetch_caller_regs adds another call, we need to increment - * the skip level - */ - regs->bp = rewind_frame_pointer(skip + 1); - regs->cs = __KERNEL_CS; - /* - * We abuse bit 3 to pass exact information, see perf_misc_flags - * and the comment with PERF_EFLAGS_EXACT. - */ - regs->flags = 0; -} - unsigned long perf_instruction_pointer(struct pt_regs *regs) { unsigned long ip; diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index ae85d69644d..107711bf0ee 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -21,22 +21,36 @@ struct p4_event_bind { char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on abscence */ }; -struct p4_cache_event_bind { +struct p4_pebs_bind { unsigned int metric_pebs; unsigned int metric_vert; }; -#define P4_GEN_CACHE_EVENT_BIND(name) \ - [P4_CACHE__##name] = { \ - .metric_pebs = P4_PEBS__##name, \ - .metric_vert = P4_VERT__##name, \ +/* it sets P4_PEBS_ENABLE_UOP_TAG as well */ +#define P4_GEN_PEBS_BIND(name, pebs, vert) \ + [P4_PEBS_METRIC__##name] = { \ + .metric_pebs = pebs | P4_PEBS_ENABLE_UOP_TAG, \ + .metric_vert = vert, \ } -static struct p4_cache_event_bind p4_cache_event_bind_map[] = { - P4_GEN_CACHE_EVENT_BIND(1stl_cache_load_miss_retired), - P4_GEN_CACHE_EVENT_BIND(2ndl_cache_load_miss_retired), - P4_GEN_CACHE_EVENT_BIND(dtlb_load_miss_retired), - P4_GEN_CACHE_EVENT_BIND(dtlb_store_miss_retired), +/* + * note we have P4_PEBS_ENABLE_UOP_TAG always set here + * + * it's needed for mapping P4_PEBS_CONFIG_METRIC_MASK bits of + * event configuration to find out which values are to be + * written into MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT + * resgisters + */ +static struct p4_pebs_bind p4_pebs_bind_map[] = { + P4_GEN_PEBS_BIND(1stl_cache_load_miss_retired, 0x0000001, 0x0000001), + P4_GEN_PEBS_BIND(2ndl_cache_load_miss_retired, 0x0000002, 0x0000001), + P4_GEN_PEBS_BIND(dtlb_load_miss_retired, 0x0000004, 0x0000001), + P4_GEN_PEBS_BIND(dtlb_store_miss_retired, 0x0000004, 0x0000002), + P4_GEN_PEBS_BIND(dtlb_all_miss_retired, 0x0000004, 0x0000003), + P4_GEN_PEBS_BIND(tagged_mispred_branch, 0x0018000, 0x0000010), + P4_GEN_PEBS_BIND(mob_load_replay_retired, 0x0000200, 0x0000001), + P4_GEN_PEBS_BIND(split_load_retired, 0x0000400, 0x0000001), + P4_GEN_PEBS_BIND(split_store_retired, 0x0000400, 0x0000002), }; /* @@ -281,10 +295,10 @@ static struct p4_event_bind p4_event_bind_map[] = { }, }; -#define P4_GEN_CACHE_EVENT(event, bit, cache_event) \ +#define P4_GEN_CACHE_EVENT(event, bit, metric) \ p4_config_pack_escr(P4_ESCR_EVENT(event) | \ P4_ESCR_EMASK_BIT(event, bit)) | \ - p4_config_pack_cccr(cache_event | \ + p4_config_pack_cccr(metric | \ P4_CCCR_ESEL(P4_OPCODE_ESEL(P4_OPCODE(event)))) static __initconst const u64 p4_hw_cache_event_ids @@ -296,34 +310,34 @@ static __initconst const u64 p4_hw_cache_event_ids [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0, [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, - P4_CACHE__1stl_cache_load_miss_retired), + P4_PEBS_METRIC__1stl_cache_load_miss_retired), }, }, [ C(LL ) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0, [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, - P4_CACHE__2ndl_cache_load_miss_retired), + P4_PEBS_METRIC__2ndl_cache_load_miss_retired), }, }, [ C(DTLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0, [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, - P4_CACHE__dtlb_load_miss_retired), + P4_PEBS_METRIC__dtlb_load_miss_retired), }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = 0x0, [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS, - P4_CACHE__dtlb_store_miss_retired), + P4_PEBS_METRIC__dtlb_store_miss_retired), }, }, [ C(ITLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, HIT, - P4_CACHE__itlb_reference_hit), + P4_PEBS_METRIC__none), [ C(RESULT_MISS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, MISS, - P4_CACHE__itlb_reference_miss), + P4_PEBS_METRIC__none), }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = -1, @@ -414,11 +428,37 @@ static u64 p4_pmu_event_map(int hw_event) return config; } +static int p4_validate_raw_event(struct perf_event *event) +{ + unsigned int v; + + /* user data may have out-of-bound event index */ + v = p4_config_unpack_event(event->attr.config); + if (v >= ARRAY_SIZE(p4_event_bind_map)) { + pr_warning("P4 PMU: Unknown event code: %d\n", v); + return -EINVAL; + } + + /* + * it may have some screwed PEBS bits + */ + if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE)) { + pr_warning("P4 PMU: PEBS are not supported yet\n"); + return -EINVAL; + } + v = p4_config_unpack_metric(event->attr.config); + if (v >= ARRAY_SIZE(p4_pebs_bind_map)) { + pr_warning("P4 PMU: Unknown metric code: %d\n", v); + return -EINVAL; + } + + return 0; +} + static int p4_hw_config(struct perf_event *event) { int cpu = get_cpu(); int rc = 0; - unsigned int evnt; u32 escr, cccr; /* @@ -438,12 +478,9 @@ static int p4_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) { - /* user data may have out-of-bound event index */ - evnt = p4_config_unpack_event(event->attr.config); - if (evnt >= ARRAY_SIZE(p4_event_bind_map)) { - rc = -EINVAL; + rc = p4_validate_raw_event(event); + if (rc) goto out; - } /* * We don't control raw events so it's up to the caller @@ -451,12 +488,15 @@ static int p4_hw_config(struct perf_event *event) * on HT machine but allow HT-compatible specifics to be * passed on) * + * Note that for RAW events we allow user to use P4_CCCR_RESERVED + * bits since we keep additional info here (for cache events and etc) + * * XXX: HT wide things should check perf_paranoid_cpu() && * CAP_SYS_ADMIN */ event->hw.config |= event->attr.config & (p4_config_pack_escr(P4_ESCR_MASK_HT) | - p4_config_pack_cccr(P4_CCCR_MASK_HT)); + p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED)); } rc = x86_setup_perfctr(event); @@ -482,6 +522,29 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc) return overflow; } +static void p4_pmu_disable_pebs(void) +{ + /* + * FIXME + * + * It's still allowed that two threads setup same cache + * events so we can't simply clear metrics until we knew + * noone is depending on us, so we need kind of counter + * for "ReplayEvent" users. + * + * What is more complex -- RAW events, if user (for some + * reason) will pass some cache event metric with improper + * event opcode -- it's fine from hardware point of view + * but completely nonsence from "meaning" of such action. + * + * So at moment let leave metrics turned on forever -- it's + * ok for now but need to be revisited! + * + * (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)0); + * (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)0); + */ +} + static inline void p4_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -507,6 +570,26 @@ static void p4_pmu_disable_all(void) continue; p4_pmu_disable_event(event); } + + p4_pmu_disable_pebs(); +} + +/* configuration must be valid */ +static void p4_pmu_enable_pebs(u64 config) +{ + struct p4_pebs_bind *bind; + unsigned int idx; + + BUILD_BUG_ON(P4_PEBS_METRIC__max > P4_PEBS_CONFIG_METRIC_MASK); + + idx = p4_config_unpack_metric(config); + if (idx == P4_PEBS_METRIC__none) + return; + + bind = &p4_pebs_bind_map[idx]; + + (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs); + (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert); } static void p4_pmu_enable_event(struct perf_event *event) @@ -515,9 +598,7 @@ static void p4_pmu_enable_event(struct perf_event *event) int thread = p4_ht_config_thread(hwc->config); u64 escr_conf = p4_config_unpack_escr(p4_clear_ht_bit(hwc->config)); unsigned int idx = p4_config_unpack_event(hwc->config); - unsigned int idx_cache = p4_config_unpack_cache_event(hwc->config); struct p4_event_bind *bind; - struct p4_cache_event_bind *bind_cache; u64 escr_addr, cccr; bind = &p4_event_bind_map[idx]; @@ -537,16 +618,10 @@ static void p4_pmu_enable_event(struct perf_event *event) cccr = p4_config_unpack_cccr(hwc->config); /* - * it could be Cache event so that we need to - * set metrics into additional MSRs + * it could be Cache event so we need to write metrics + * into additional MSRs */ - BUILD_BUG_ON(P4_CACHE__MAX > P4_CCCR_CACHE_OPS_MASK); - if (idx_cache > P4_CACHE__NONE && - idx_cache < ARRAY_SIZE(p4_cache_event_bind_map)) { - bind_cache = &p4_cache_event_bind_map[idx_cache]; - (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind_cache->metric_pebs); - (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind_cache->metric_vert); - } + p4_pmu_enable_pebs(hwc->config); (void)checking_wrmsrl(escr_addr, escr_conf); (void)checking_wrmsrl(hwc->config_base + hwc->idx, @@ -829,6 +904,15 @@ static __initconst const struct x86_pmu p4_pmu = { .max_period = (1ULL << 39) - 1, .hw_config = p4_hw_config, .schedule_events = p4_pmu_schedule_events, + /* + * This handles erratum N15 in intel doc 249199-029, + * the counter may not be updated correctly on write + * so we need a second write operation to do the trick + * (the official workaround didn't work) + * + * the former idea is taken from OProfile code + */ + .perfctr_second_write = 1, }; static __init int p4_pmu_init(void) diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c new file mode 100644 index 00000000000..34b4dad6f0b --- /dev/null +++ b/arch/x86/kernel/cpu/scattered.c @@ -0,0 +1,63 @@ +/* + * Routines to indentify additional cpu features that are scattered in + * cpuid space. + */ +#include <linux/cpu.h> + +#include <asm/pat.h> +#include <asm/processor.h> + +#include <asm/apic.h> + +struct cpuid_bit { + u16 feature; + u8 reg; + u8 bit; + u32 level; + u32 sub_leaf; +}; + +enum cpuid_regs { + CR_EAX = 0, + CR_ECX, + CR_EDX, + CR_EBX +}; + +void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) +{ + u32 max_level; + u32 regs[4]; + const struct cpuid_bit *cb; + + static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { + { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, + { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, + { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, + { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, + { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, + { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 }, + { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a, 0 }, + { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, + { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, + { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a, 0 }, + { 0, 0, 0, 0, 0 } + }; + + for (cb = cpuid_bits; cb->feature; cb++) { + + /* Verify that the level is valid */ + max_level = cpuid_eax(cb->level & 0xffff0000); + if (max_level < cb->level || + max_level > (cb->level | 0xffff)) + continue; + + cpuid_count(cb->level, cb->sub_leaf, ®s[CR_EAX], + ®s[CR_EBX], ®s[CR_ECX], ®s[CR_EDX]); + + if (regs[cb->reg] & (1 << cb->bit)) + set_cpu_cap(c, cb->feature); + } +} diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/topology.c index 10fa5684a66..4397e987a1c 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/topology.c @@ -1,62 +1,14 @@ /* - * Routines to indentify additional cpu features that are scattered in - * cpuid space. + * Check for extended topology enumeration cpuid leaf 0xb and if it + * exists, use it for populating initial_apicid and cpu topology + * detection. */ -#include <linux/cpu.h> +#include <linux/cpu.h> +#include <asm/apic.h> #include <asm/pat.h> #include <asm/processor.h> -#include <asm/apic.h> - -struct cpuid_bit { - u16 feature; - u8 reg; - u8 bit; - u32 level; -}; - -enum cpuid_regs { - CR_EAX = 0, - CR_ECX, - CR_EDX, - CR_EBX -}; - -void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) -{ - u32 max_level; - u32 regs[4]; - const struct cpuid_bit *cb; - - static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { - { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 }, - { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 }, - { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006 }, - { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007 }, - { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a }, - { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a }, - { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a }, - { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a }, - { 0, 0, 0, 0 } - }; - - for (cb = cpuid_bits; cb->feature; cb++) { - - /* Verify that the level is valid */ - max_level = cpuid_eax(cb->level & 0xffff0000); - if (max_level < cb->level || - max_level > (cb->level | 0xffff)) - continue; - - cpuid(cb->level, ®s[CR_EAX], ®s[CR_EBX], - ®s[CR_ECX], ®s[CR_EDX]); - - if (regs[cb->reg] & (1 << cb->bit)) - set_cpu_cap(c, cb->feature); - } -} - /* leaf 0xb SMT level */ #define SMT_LEVEL 0 diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index c89a386930b..6e8752c1bd5 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -18,7 +18,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" int panic_on_unrecovered_nmi; int panic_on_io_nmi; diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h deleted file mode 100644 index e1a93be4fd4..00000000000 --- a/arch/x86/kernel/dumpstack.h +++ /dev/null @@ -1,56 +0,0 @@ -/* - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs - */ - -#ifndef DUMPSTACK_H -#define DUMPSTACK_H - -#ifdef CONFIG_X86_32 -#define STACKSLOTS_PER_LINE 8 -#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) -#else -#define STACKSLOTS_PER_LINE 4 -#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) -#endif - -#include <linux/uaccess.h> - -extern void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl); - -extern void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl); - -extern unsigned int code_bytes; - -/* The form of the top of the frame on the stack */ -struct stack_frame { - struct stack_frame *next_frame; - unsigned long return_address; -}; - -struct stack_frame_ia32 { - u32 next_frame; - u32 return_address; -}; - -static inline unsigned long rewind_frame_pointer(int n) -{ - struct stack_frame *frame; - - get_bp(frame); - -#ifdef CONFIG_FRAME_POINTER - while (n--) { - if (probe_kernel_address(&frame->next_frame, frame)) - break; - } -#endif - - return (unsigned long)frame; -} - -#endif /* DUMPSTACK_H */ diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 11540a189d9..0f6376ffa2d 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -16,8 +16,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" - void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 272c9f1f05f..57a21f11c79 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -16,7 +16,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" #define N_EXCEPTION_STACKS_END \ (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index cd49141cf15..258e93fa263 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -611,14 +611,14 @@ ldt_ss: * compensating for the offset by changing to the ESPFIX segment with * a base address that matches for the difference. */ +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) mov %esp, %edx /* load kernel esp */ mov PT_OLDESP(%esp), %eax /* load userspace esp */ mov %dx, %ax /* eax: new kernel esp */ sub %eax, %edx /* offset (low word is 0) */ - PER_CPU(gdt_page, %ebx) shr $16, %edx - mov %dl, GDT_ENTRY_ESPFIX_SS * 8 + 4(%ebx) /* bits 16..23 */ - mov %dh, GDT_ENTRY_ESPFIX_SS * 8 + 7(%ebx) /* bits 24..31 */ + mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ + mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ pushl $__ESPFIX_SS CFI_ADJUST_CFA_OFFSET 4 push %eax /* new kernel esp */ @@ -791,9 +791,8 @@ ptregs_clone: * normal stack and adjusts ESP with the matching offset. */ /* fixup the stack */ - PER_CPU(gdt_page, %ebx) - mov GDT_ENTRY_ESPFIX_SS * 8 + 4(%ebx), %al /* bits 16..23 */ - mov GDT_ENTRY_ESPFIX_SS * 8 + 7(%ebx), %ah /* bits 24..31 */ + mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ + mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ shl $16, %eax addl %esp, %eax /* the adjusted stack pointer */ pushl $__KERNEL_DS @@ -1166,6 +1165,9 @@ ENTRY(xen_failsafe_callback) .previous ENDPROC(xen_failsafe_callback) +BUILD_INTERRUPT3(xen_hvm_callback_vector, XEN_HVM_EVTCHN_CALLBACK, + xen_evtchn_do_upcall) + #endif /* CONFIG_XEN */ #ifdef CONFIG_FUNCTION_TRACER diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 4db7c4d12ff..c5ea5cdbe7b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1065,6 +1065,7 @@ ENTRY(\sym) END(\sym) .endm +#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) .macro paranoidzeroentry_ist sym do_sym ist ENTRY(\sym) INTR_FRAME @@ -1076,10 +1077,9 @@ ENTRY(\sym) TRACE_IRQS_OFF movq %rsp,%rdi /* pt_regs pointer */ xorl %esi,%esi /* no error code */ - PER_CPU(init_tss, %r12) - subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12) + subq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) call \do_sym - addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%r12) + addq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) jmp paranoid_exit /* %ebx: no swapgs flag */ CFI_ENDPROC END(\sym) @@ -1329,6 +1329,9 @@ ENTRY(xen_failsafe_callback) CFI_ENDPROC END(xen_failsafe_callback) +apicinterrupt XEN_HVM_EVTCHN_CALLBACK \ + xen_hvm_callback_vector xen_evtchn_do_upcall + #endif /* CONFIG_XEN */ /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 3d1e6f16b7a..239046bd447 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -234,9 +234,8 @@ ENTRY(secondary_startup_64) * init data section till per cpu areas are set up. */ movl $MSR_GS_BASE,%ecx - movq initial_gs(%rip),%rax - movq %rax,%rdx - shrq $32,%rdx + movl initial_gs(%rip),%eax + movl initial_gs+4(%rip),%edx wrmsr /* esi is pointer to real mode structure with interesting info. diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index a8f1b803d2f..a474ec37c32 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -208,6 +208,9 @@ int arch_bp_generic_fields(int x86_len, int x86_type, { /* Len */ switch (x86_len) { + case X86_BREAKPOINT_LEN_X: + *gen_len = sizeof(long); + break; case X86_BREAKPOINT_LEN_1: *gen_len = HW_BREAKPOINT_LEN_1; break; @@ -251,6 +254,29 @@ static int arch_build_bp_info(struct perf_event *bp) info->address = bp->attr.bp_addr; + /* Type */ + switch (bp->attr.bp_type) { + case HW_BREAKPOINT_W: + info->type = X86_BREAKPOINT_WRITE; + break; + case HW_BREAKPOINT_W | HW_BREAKPOINT_R: + info->type = X86_BREAKPOINT_RW; + break; + case HW_BREAKPOINT_X: + info->type = X86_BREAKPOINT_EXECUTE; + /* + * x86 inst breakpoints need to have a specific undefined len. + * But we still need to check userspace is not trying to setup + * an unsupported length, to get a range breakpoint for example. + */ + if (bp->attr.bp_len == sizeof(long)) { + info->len = X86_BREAKPOINT_LEN_X; + return 0; + } + default: + return -EINVAL; + } + /* Len */ switch (bp->attr.bp_len) { case HW_BREAKPOINT_LEN_1: @@ -271,21 +297,6 @@ static int arch_build_bp_info(struct perf_event *bp) return -EINVAL; } - /* Type */ - switch (bp->attr.bp_type) { - case HW_BREAKPOINT_W: - info->type = X86_BREAKPOINT_WRITE; - break; - case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - info->type = X86_BREAKPOINT_RW; - break; - case HW_BREAKPOINT_X: - info->type = X86_BREAKPOINT_EXECUTE; - break; - default: - return -EINVAL; - } - return 0; } /* @@ -305,6 +316,9 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) ret = -EINVAL; switch (info->len) { + case X86_BREAKPOINT_LEN_X: + align = sizeof(long) -1; + break; case X86_BREAKPOINT_LEN_1: align = 0; break; @@ -466,6 +480,13 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) perf_bp_event(bp, args->regs); + /* + * Set up resume flag to avoid breakpoint recursion when + * returning back to origin. + */ + if (bp->hw.info.type == X86_BREAKPOINT_EXECUTE) + args->regs->flags |= X86_EFLAGS_RF; + rcu_read_unlock(); } /* diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 01ab17ae2ae..ef10940e1af 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -49,55 +49,94 @@ #include <asm/system.h> #include <asm/apic.h> -/** - * pt_regs_to_gdb_regs - Convert ptrace regs to GDB regs - * @gdb_regs: A pointer to hold the registers in the order GDB wants. - * @regs: The &struct pt_regs of the current process. - * - * Convert the pt_regs in @regs into the format for registers that - * GDB expects, stored in @gdb_regs. - */ -void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { -#ifndef CONFIG_X86_32 - u32 *gdb_regs32 = (u32 *)gdb_regs; +#ifdef CONFIG_X86_32 + { "ax", 4, offsetof(struct pt_regs, ax) }, + { "cx", 4, offsetof(struct pt_regs, cx) }, + { "dx", 4, offsetof(struct pt_regs, dx) }, + { "bx", 4, offsetof(struct pt_regs, bx) }, + { "sp", 4, offsetof(struct pt_regs, sp) }, + { "bp", 4, offsetof(struct pt_regs, bp) }, + { "si", 4, offsetof(struct pt_regs, si) }, + { "di", 4, offsetof(struct pt_regs, di) }, + { "ip", 4, offsetof(struct pt_regs, ip) }, + { "flags", 4, offsetof(struct pt_regs, flags) }, + { "cs", 4, offsetof(struct pt_regs, cs) }, + { "ss", 4, offsetof(struct pt_regs, ss) }, + { "ds", 4, offsetof(struct pt_regs, ds) }, + { "es", 4, offsetof(struct pt_regs, es) }, + { "fs", 4, -1 }, + { "gs", 4, -1 }, +#else + { "ax", 8, offsetof(struct pt_regs, ax) }, + { "bx", 8, offsetof(struct pt_regs, bx) }, + { "cx", 8, offsetof(struct pt_regs, cx) }, + { "dx", 8, offsetof(struct pt_regs, dx) }, + { "si", 8, offsetof(struct pt_regs, dx) }, + { "di", 8, offsetof(struct pt_regs, di) }, + { "bp", 8, offsetof(struct pt_regs, bp) }, + { "sp", 8, offsetof(struct pt_regs, sp) }, + { "r8", 8, offsetof(struct pt_regs, r8) }, + { "r9", 8, offsetof(struct pt_regs, r9) }, + { "r10", 8, offsetof(struct pt_regs, r10) }, + { "r11", 8, offsetof(struct pt_regs, r11) }, + { "r12", 8, offsetof(struct pt_regs, r12) }, + { "r13", 8, offsetof(struct pt_regs, r13) }, + { "r14", 8, offsetof(struct pt_regs, r14) }, + { "r15", 8, offsetof(struct pt_regs, r15) }, + { "ip", 8, offsetof(struct pt_regs, ip) }, + { "flags", 4, offsetof(struct pt_regs, flags) }, + { "cs", 4, offsetof(struct pt_regs, cs) }, + { "ss", 4, offsetof(struct pt_regs, ss) }, #endif - gdb_regs[GDB_AX] = regs->ax; - gdb_regs[GDB_BX] = regs->bx; - gdb_regs[GDB_CX] = regs->cx; - gdb_regs[GDB_DX] = regs->dx; - gdb_regs[GDB_SI] = regs->si; - gdb_regs[GDB_DI] = regs->di; - gdb_regs[GDB_BP] = regs->bp; - gdb_regs[GDB_PC] = regs->ip; +}; + +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) +{ + if ( #ifdef CONFIG_X86_32 - gdb_regs[GDB_PS] = regs->flags; - gdb_regs[GDB_DS] = regs->ds; - gdb_regs[GDB_ES] = regs->es; - gdb_regs[GDB_CS] = regs->cs; - gdb_regs[GDB_FS] = 0xFFFF; - gdb_regs[GDB_GS] = 0xFFFF; - if (user_mode_vm(regs)) { - gdb_regs[GDB_SS] = regs->ss; - gdb_regs[GDB_SP] = regs->sp; - } else { - gdb_regs[GDB_SS] = __KERNEL_DS; - gdb_regs[GDB_SP] = kernel_stack_pointer(regs); + regno == GDB_SS || regno == GDB_FS || regno == GDB_GS || +#endif + regno == GDB_SP || regno == GDB_ORIG_AX) + return 0; + + if (dbg_reg_def[regno].offset != -1) + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + return 0; +} + +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno == GDB_ORIG_AX) { + memcpy(mem, ®s->orig_ax, sizeof(regs->orig_ax)); + return "orig_ax"; } -#else - gdb_regs[GDB_R8] = regs->r8; - gdb_regs[GDB_R9] = regs->r9; - gdb_regs[GDB_R10] = regs->r10; - gdb_regs[GDB_R11] = regs->r11; - gdb_regs[GDB_R12] = regs->r12; - gdb_regs[GDB_R13] = regs->r13; - gdb_regs[GDB_R14] = regs->r14; - gdb_regs[GDB_R15] = regs->r15; - gdb_regs32[GDB_PS] = regs->flags; - gdb_regs32[GDB_CS] = regs->cs; - gdb_regs32[GDB_SS] = regs->ss; - gdb_regs[GDB_SP] = kernel_stack_pointer(regs); + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1) + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + + switch (regno) { +#ifdef CONFIG_X86_32 + case GDB_SS: + if (!user_mode_vm(regs)) + *(unsigned long *)mem = __KERNEL_DS; + break; + case GDB_SP: + if (!user_mode_vm(regs)) + *(unsigned long *)mem = kernel_stack_pointer(regs); + break; + case GDB_GS: + case GDB_FS: + *(unsigned long *)mem = 0xFFFF; + break; #endif + } + return dbg_reg_def[regno].name; } /** @@ -150,54 +189,13 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) gdb_regs[GDB_SP] = p->thread.sp; } -/** - * gdb_regs_to_pt_regs - Convert GDB regs to ptrace regs. - * @gdb_regs: A pointer to hold the registers we've received from GDB. - * @regs: A pointer to a &struct pt_regs to hold these values in. - * - * Convert the GDB regs in @gdb_regs into the pt_regs, and store them - * in @regs. - */ -void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) -{ -#ifndef CONFIG_X86_32 - u32 *gdb_regs32 = (u32 *)gdb_regs; -#endif - regs->ax = gdb_regs[GDB_AX]; - regs->bx = gdb_regs[GDB_BX]; - regs->cx = gdb_regs[GDB_CX]; - regs->dx = gdb_regs[GDB_DX]; - regs->si = gdb_regs[GDB_SI]; - regs->di = gdb_regs[GDB_DI]; - regs->bp = gdb_regs[GDB_BP]; - regs->ip = gdb_regs[GDB_PC]; -#ifdef CONFIG_X86_32 - regs->flags = gdb_regs[GDB_PS]; - regs->ds = gdb_regs[GDB_DS]; - regs->es = gdb_regs[GDB_ES]; - regs->cs = gdb_regs[GDB_CS]; -#else - regs->r8 = gdb_regs[GDB_R8]; - regs->r9 = gdb_regs[GDB_R9]; - regs->r10 = gdb_regs[GDB_R10]; - regs->r11 = gdb_regs[GDB_R11]; - regs->r12 = gdb_regs[GDB_R12]; - regs->r13 = gdb_regs[GDB_R13]; - regs->r14 = gdb_regs[GDB_R14]; - regs->r15 = gdb_regs[GDB_R15]; - regs->flags = gdb_regs32[GDB_PS]; - regs->cs = gdb_regs32[GDB_CS]; - regs->ss = gdb_regs32[GDB_SS]; -#endif -} - static struct hw_breakpoint { unsigned enabled; unsigned long addr; int len; int type; struct perf_event **pev; -} breakinfo[4]; +} breakinfo[HBP_NUM]; static unsigned long early_dr7; @@ -205,7 +203,7 @@ static void kgdb_correct_hw_break(void) { int breakno; - for (breakno = 0; breakno < 4; breakno++) { + for (breakno = 0; breakno < HBP_NUM; breakno++) { struct perf_event *bp; struct arch_hw_breakpoint *info; int val; @@ -292,10 +290,10 @@ kgdb_remove_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) { int i; - for (i = 0; i < 4; i++) + for (i = 0; i < HBP_NUM; i++) if (breakinfo[i].addr == addr && breakinfo[i].enabled) break; - if (i == 4) + if (i == HBP_NUM) return -1; if (hw_break_release_slot(i)) { @@ -313,7 +311,7 @@ static void kgdb_remove_all_hw_break(void) int cpu = raw_smp_processor_id(); struct perf_event *bp; - for (i = 0; i < 4; i++) { + for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; bp = *per_cpu_ptr(breakinfo[i].pev, cpu); @@ -333,10 +331,10 @@ kgdb_set_hw_break(unsigned long addr, int len, enum kgdb_bptype bptype) { int i; - for (i = 0; i < 4; i++) + for (i = 0; i < HBP_NUM; i++) if (!breakinfo[i].enabled) break; - if (i == 4) + if (i == HBP_NUM) return -1; switch (bptype) { @@ -397,7 +395,7 @@ void kgdb_disable_hw_debug(struct pt_regs *regs) /* Disable hardware debugging while we are in kgdb: */ set_debugreg(0UL, 7); - for (i = 0; i < 4; i++) { + for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; if (dbg_is_early) { @@ -458,7 +456,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, { unsigned long addr; char *ptr; - int newPC; switch (remcomInBuffer[0]) { case 'c': @@ -469,8 +466,6 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, linux_regs->ip = addr; case 'D': case 'k': - newPC = linux_regs->ip; - /* clear the trace bit */ linux_regs->flags &= ~X86_EFLAGS_TF; atomic_set(&kgdb_cpu_doing_single_step, -1); @@ -645,7 +640,7 @@ void kgdb_arch_late(void) attr.bp_len = HW_BREAKPOINT_LEN_1; attr.bp_type = HW_BREAKPOINT_W; attr.disabled = 1; - for (i = 0; i < 4; i++) { + for (i = 0; i < HBP_NUM; i++) { if (breakinfo[i].pev) continue; breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL); diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 675879b65ce..1bfb6cf4dd5 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -126,16 +126,22 @@ static void __kprobes synthesize_reljump(void *from, void *to) } /* - * Check for the REX prefix which can only exist on X86_64 - * X86_32 always returns 0 + * Skip the prefixes of the instruction. */ -static int __kprobes is_REX_prefix(kprobe_opcode_t *insn) +static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) { + insn_attr_t attr; + + attr = inat_get_opcode_attribute((insn_byte_t)*insn); + while (inat_is_legacy_prefix(attr)) { + insn++; + attr = inat_get_opcode_attribute((insn_byte_t)*insn); + } #ifdef CONFIG_X86_64 - if ((*insn & 0xf0) == 0x40) - return 1; + if (inat_is_rex_prefix(attr)) + insn++; #endif - return 0; + return insn; } /* @@ -272,6 +278,9 @@ static int __kprobes can_probe(unsigned long paddr) */ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) { + /* Skip prefixes */ + insn = skip_prefixes(insn); + switch (*insn) { case 0xfa: /* cli */ case 0xfb: /* sti */ @@ -280,13 +289,6 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) return 1; } - /* - * on X86_64, 0x40-0x4f are REX prefixes so we need to look - * at the next byte instead.. but of course not recurse infinitely - */ - if (is_REX_prefix(insn)) - return is_IF_modifier(++insn); - return 0; } @@ -803,9 +805,8 @@ static void __kprobes resume_execution(struct kprobe *p, unsigned long orig_ip = (unsigned long)p->addr; kprobe_opcode_t *insn = p->ainsn.insn; - /*skip the REX prefix*/ - if (is_REX_prefix(insn)) - insn++; + /* Skip prefixes */ + insn = skip_prefixes(insn); regs->flags &= ~X86_EFLAGS_TF; switch (*insn) { diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c index 5915e0b3330..79ae68154e8 100644 --- a/arch/x86/kernel/mrst.c +++ b/arch/x86/kernel/mrst.c @@ -25,8 +25,34 @@ #include <asm/i8259.h> #include <asm/apb_timer.h> +/* + * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock, + * cmdline option x86_mrst_timer can be used to override the configuration + * to prefer one or the other. + * at runtime, there are basically three timer configurations: + * 1. per cpu apbt clock only + * 2. per cpu always-on lapic clocks only, this is Penwell/Medfield only + * 3. per cpu lapic clock (C3STOP) and one apbt clock, with broadcast. + * + * by default (without cmdline option), platform code first detects cpu type + * to see if we are on lincroft or penwell, then set up both lapic or apbt + * clocks accordingly. + * i.e. by default, medfield uses configuration #2, moorestown uses #1. + * config #3 is supported but not recommended on medfield. + * + * rating and feature summary: + * lapic (with C3STOP) --------- 100 + * apbt (always-on) ------------ 110 + * lapic (always-on,ARAT) ------ 150 + */ + +__cpuinitdata enum mrst_timer_options mrst_timer_options; + static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM]; static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM]; +enum mrst_cpu_type __mrst_cpu_chip; +EXPORT_SYMBOL_GPL(__mrst_cpu_chip); + int sfi_mtimer_num; struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX]; @@ -167,18 +193,6 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) return 0; } -/* - * the secondary clock in Moorestown can be APBT or LAPIC clock, default to - * APBT but cmdline option can also override it. - */ -static void __cpuinit mrst_setup_secondary_clock(void) -{ - /* restore default lapic clock if disabled by cmdline */ - if (disable_apbt_percpu) - return setup_secondary_APIC_clock(); - apbt_setup_secondary_clock(); -} - static unsigned long __init mrst_calibrate_tsc(void) { unsigned long flags, fast_calibrate; @@ -195,6 +209,21 @@ static unsigned long __init mrst_calibrate_tsc(void) void __init mrst_time_init(void) { + switch (mrst_timer_options) { + case MRST_TIMER_APBT_ONLY: + break; + case MRST_TIMER_LAPIC_APBT: + x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; + break; + default: + if (!boot_cpu_has(X86_FEATURE_ARAT)) + break; + x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; + return; + } + /* we need at least one APB timer */ sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr); pre_init_apic_IRQ0(); apbt_time_init(); @@ -205,16 +234,21 @@ void __init mrst_rtc_init(void) sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc); } -/* - * if we use per cpu apb timer, the bootclock already setup. if we use lapic - * timer and one apbt timer for broadcast, we need to set up lapic boot clock. - */ -static void __init mrst_setup_boot_clock(void) +void __cpuinit mrst_arch_setup(void) { - pr_info("%s: per cpu apbt flag %d \n", __func__, disable_apbt_percpu); - if (disable_apbt_percpu) - setup_boot_APIC_clock(); -}; + if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27) + __mrst_cpu_chip = MRST_CPU_CHIP_PENWELL; + else if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x26) + __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + else { + pr_err("Unknown Moorestown CPU (%d:%d), default to Lincroft\n", + boot_cpu_data.x86, boot_cpu_data.x86_model); + __mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT; + } + pr_debug("Moorestown CPU %s identified\n", + (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) ? + "Lincroft" : "Penwell"); +} /* MID systems don't have i8042 controller */ static int mrst_i8042_detect(void) @@ -232,11 +266,13 @@ void __init x86_mrst_early_setup(void) x86_init.resources.reserve_resources = x86_init_noop; x86_init.timers.timer_init = mrst_time_init; - x86_init.timers.setup_percpu_clockev = mrst_setup_boot_clock; + x86_init.timers.setup_percpu_clockev = x86_init_noop; x86_init.irqs.pre_vector_init = x86_init_noop; - x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock; + x86_init.oem.arch_setup = mrst_arch_setup; + + x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock; x86_platform.calibrate_tsc = mrst_calibrate_tsc; x86_platform.i8042_detect = mrst_i8042_detect; @@ -250,3 +286,26 @@ void __init x86_mrst_early_setup(void) x86_init.mpparse.get_smp_config = x86_init_uint_noop; } + +/* + * if user does not want to use per CPU apb timer, just give it a lower rating + * than local apic timer and skip the late per cpu timer init. + */ +static inline int __init setup_x86_mrst_timer(char *arg) +{ + if (!arg) + return -EINVAL; + + if (strcmp("apbt_only", arg) == 0) + mrst_timer_options = MRST_TIMER_APBT_ONLY; + else if (strcmp("lapic_and_apbt", arg) == 0) + mrst_timer_options = MRST_TIMER_LAPIC_APBT; + else { + pr_warning("X86 MRST timer option %s not recognised" + " use x86_mrst_timer=apbt_only or lapic_and_apbt\n", + arg); + return -EINVAL; + } + return 0; +} +__setup("x86_mrst_timer=", setup_x86_mrst_timer); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index cbcf013a0ec..d401f1d2d06 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -526,44 +526,10 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) return (edx & MWAIT_EDX_C1); } -/* - * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e. - * For more information see - * - Erratum #400 for NPT family 0xf and family 0x10 CPUs - * - Erratum #365 for family 0x11 (not affected because C1e not in use) - */ -static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c) -{ - u64 val; - if (c->x86_vendor != X86_VENDOR_AMD) - goto no_c1e_idle; - - /* Family 0x0f models < rev F do not have C1E */ - if (c->x86 == 0x0F && c->x86_model >= 0x40) - return 1; - - if (c->x86 == 0x10) { - /* - * check OSVW bit for CPUs that are not affected - * by erratum #400 - */ - if (cpu_has(c, X86_FEATURE_OSVW)) { - rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val); - if (val >= 2) { - rdmsrl(MSR_AMD64_OSVW_STATUS, val); - if (!(val & BIT(1))) - goto no_c1e_idle; - } - } - return 1; - } - -no_c1e_idle: - return 0; -} +bool c1e_detected; +EXPORT_SYMBOL(c1e_detected); static cpumask_var_t c1e_mask; -static int c1e_detected; void c1e_remove_cpu(int cpu) { @@ -585,12 +551,12 @@ static void c1e_idle(void) u32 lo, hi; rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi); + if (lo & K8_INTP_C1E_ACTIVE_MASK) { - c1e_detected = 1; + c1e_detected = true; if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); printk(KERN_INFO "System has AMD C1E enabled\n"); - set_cpu_cap(&boot_cpu_data, X86_FEATURE_AMDC1E); } } @@ -639,7 +605,8 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) */ printk(KERN_INFO "using mwait in idle threads.\n"); pm_idle = mwait_idle; - } else if (check_c1e_idle(c)) { + } else if (cpu_has_amd_erratum(amd_erratum_400)) { + /* E400: APIC timer interrupt does not wake up CPU from C1e */ printk(KERN_INFO "using C1E aware idle routine\n"); pm_idle = c1e_idle; } else diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 8d128783af4..96586c3cbbb 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -57,6 +57,8 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <trace/events/power.h> + asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); /* @@ -111,6 +113,8 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); + + trace_power_end(smp_processor_id()); } tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3c2422a99f1..3d9ea531ddd 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -51,6 +51,8 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <trace/events/power.h> + asmlinkage extern void ret_from_fork(void); DEFINE_PER_CPU(unsigned long, old_rsp); @@ -138,6 +140,9 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); + + trace_power_end(smp_processor_id()); + /* In many cases the interrupt that ended idle has already called exit_idle. But some idle loops can be woken up without interrupt. */ diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 922eefbb3f6..b53c525368a 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -23,11 +23,16 @@ static int save_stack_stack(void *data, char *name) return 0; } -static void save_stack_address(void *data, unsigned long addr, int reliable) +static void +__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) { struct stack_trace *trace = data; +#ifdef CONFIG_FRAME_POINTER if (!reliable) return; +#endif + if (nosched && in_sched_functions(addr)) + return; if (trace->skip > 0) { trace->skip--; return; @@ -36,20 +41,15 @@ static void save_stack_address(void *data, unsigned long addr, int reliable) trace->entries[trace->nr_entries++] = addr; } +static void save_stack_address(void *data, unsigned long addr, int reliable) +{ + return __save_stack_address(data, addr, reliable, false); +} + static void save_stack_address_nosched(void *data, unsigned long addr, int reliable) { - struct stack_trace *trace = (struct stack_trace *)data; - if (!reliable) - return; - if (in_sched_functions(addr)) - return; - if (trace->skip > 0) { - trace->skip--; - return; - } - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = addr; + return __save_stack_address(data, addr, reliable, true); } static const struct stacktrace_ops save_stack_ops = { @@ -96,12 +96,13 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk); /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */ -struct stack_frame { +struct stack_frame_user { const void __user *next_fp; unsigned long ret_addr; }; -static int copy_stack_frame(const void __user *fp, struct stack_frame *frame) +static int +copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) { int ret; @@ -126,7 +127,7 @@ static inline void __save_stack_trace_user(struct stack_trace *trace) trace->entries[trace->nr_entries++] = regs->ip; while (trace->nr_entries < trace->max_entries) { - struct stack_frame frame; + struct stack_frame_user frame; frame.next_fp = NULL; frame.ret_addr = 0; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 725ef4d17cd..60788dee0f8 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -392,7 +392,13 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; + #ifdef CONFIG_X86_LOCAL_APIC + if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) + == NOTIFY_STOP) + return; + +#ifndef CONFIG_LOCKUP_DETECTOR /* * Ok, so this is none of the documented NMI sources, * so it must be the NMI watchdog. @@ -400,6 +406,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (nmi_watchdog_tick(regs, reason)) return; if (!do_nmi_callback(regs, cpu)) +#endif /* !CONFIG_LOCKUP_DETECTOR */ unknown_nmi_error(reason, regs); #else unknown_nmi_error(reason, regs); diff --git a/arch/x86/kernel/verify_cpu_64.S b/arch/x86/kernel/verify_cpu_64.S index 45b6f8a975a..56a8c2a867d 100644 --- a/arch/x86/kernel/verify_cpu_64.S +++ b/arch/x86/kernel/verify_cpu_64.S @@ -31,6 +31,7 @@ */ #include <asm/cpufeature.h> +#include <asm/msr-index.h> verify_cpu: pushfl # Save caller passed flags @@ -88,7 +89,7 @@ verify_cpu_sse_test: je verify_cpu_sse_ok test %di,%di jz verify_cpu_no_longmode # only try to force SSE on AMD - movl $0xc0010015,%ecx # HWCR + movl $MSR_K7_HWCR,%ecx rdmsr btr $15,%eax # enable SSE wrmsr diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 37e68fc5e24..980149867a1 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -36,15 +36,14 @@ int check_for_xstate(struct i387_fxsave_struct __user *buf, err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0], sizeof(struct _fpx_sw_bytes)); - if (err) - return err; + return -EFAULT; /* * First Magic check failed. */ if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1) - return -1; + return -EINVAL; /* * Check for error scenarios. @@ -52,19 +51,21 @@ int check_for_xstate(struct i387_fxsave_struct __user *buf, if (fx_sw_user->xstate_size < min_xstate_size || fx_sw_user->xstate_size > xstate_size || fx_sw_user->xstate_size > fx_sw_user->extended_size) - return -1; + return -EINVAL; err = __get_user(magic2, (__u32 *) (((void *)fpstate) + fx_sw_user->extended_size - FP_XSTATE_MAGIC2_SIZE)); + if (err) + return err; /* * Check for the presence of second magic word at the end of memory * layout. This detects the case where the user just copied the legacy * fpstate layout with out copying the extended state information * in the memory layout. */ - if (err || magic2 != FP_XSTATE_MAGIC2) - return -1; + if (magic2 != FP_XSTATE_MAGIC2) + return -EFAULT; return 0; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 56c9b6bd765..bc5b9b8d4a3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -131,7 +131,7 @@ static struct svm_direct_access_msrs { u32 index; /* Index of the MSR */ bool always; /* True if intercept is always on */ } direct_access_msrs[] = { - { .index = MSR_K6_STAR, .always = true }, + { .index = MSR_STAR, .always = true }, { .index = MSR_IA32_SYSENTER_CS, .always = true }, #ifdef CONFIG_X86_64 { .index = MSR_GS_BASE, .always = true }, @@ -384,8 +384,7 @@ static void svm_init_erratum_383(void) int err; u64 val; - /* Only Fam10h is affected */ - if (boot_cpu_data.x86 != 0x10) + if (!cpu_has_amd_erratum(amd_erratum_383)) return; /* Use _safe variants to not break nested virtualization */ @@ -2433,7 +2432,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) *data = tsc_offset + native_read_tsc(); break; } - case MSR_K6_STAR: + case MSR_STAR: *data = svm->vmcb->save.star; break; #ifdef CONFIG_X86_64 @@ -2557,7 +2556,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) break; } - case MSR_K6_STAR: + case MSR_STAR: svm->vmcb->save.star = data; break; #ifdef CONFIG_X86_64 diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 27a0222c294..49b25eee25a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -240,14 +240,14 @@ static u64 host_efer; static void ept_save_pdptrs(struct kvm_vcpu *vcpu); /* - * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it + * Keep MSR_STAR at the end, as setup_msrs() will try to optimize it * away by decrementing the array size. */ static const u32 vmx_msr_index[] = { #ifdef CONFIG_X86_64 MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif - MSR_EFER, MSR_TSC_AUX, MSR_K6_STAR, + MSR_EFER, MSR_TSC_AUX, MSR_STAR, }; #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) @@ -1117,10 +1117,10 @@ static void setup_msrs(struct vcpu_vmx *vmx) if (index >= 0 && vmx->rdtscp_enabled) move_msr_up(vmx, index, save_nmsrs++); /* - * MSR_K6_STAR is only needed on long mode guests, and only + * MSR_STAR is only needed on long mode guests, and only * if efer.sce is enabled. */ - index = __find_msr_index(vmx, MSR_K6_STAR); + index = __find_msr_index(vmx, MSR_STAR); if ((index >= 0) && (vmx->vcpu.arch.efer & EFER_SCE)) move_msr_up(vmx, index, save_nmsrs++); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 97aab036dab..25f19078b32 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -733,7 +733,7 @@ static u32 msrs_to_save[] = { HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_APIC_ASSIST_PAGE, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_K6_STAR, + MSR_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f871e04b696..e10cf070ede 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -30,6 +30,7 @@ ifeq ($(CONFIG_X86_32),y) lib-y += checksum_32.o lib-y += strstr_32.o lib-y += semaphore_32.o string_32.o + lib-y += cmpxchg.o ifneq ($(CONFIG_X86_CMPXCHG64),y) lib-y += cmpxchg8b_emu.o atomic64_386_32.o endif diff --git a/arch/x86/kernel/cpu/cmpxchg.c b/arch/x86/lib/cmpxchg.c index 2056ccf572c..5d619f6df3e 100644 --- a/arch/x86/kernel/cpu/cmpxchg.c +++ b/arch/x86/lib/cmpxchg.c @@ -52,21 +52,3 @@ unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new) } EXPORT_SYMBOL(cmpxchg_386_u32); #endif - -#ifndef CONFIG_X86_CMPXCHG64 -unsigned long long cmpxchg_486_u64(volatile void *ptr, u64 old, u64 new) -{ - u64 prev; - unsigned long flags; - - /* Poor man's cmpxchg8b for 386 and 486. Unsuitable for SMP */ - local_irq_save(flags); - prev = *(u64 *)ptr; - if (prev == old) - *(u64 *)ptr = new; - local_irq_restore(flags); - return prev; -} -EXPORT_SYMBOL(cmpxchg_486_u64); -#endif - diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index a725b7f760a..0002a3a3308 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -37,6 +37,28 @@ struct addr_marker { const char *name; }; +/* indices for address_markers; keep sync'd w/ address_markers below */ +enum address_markers_idx { + USER_SPACE_NR = 0, +#ifdef CONFIG_X86_64 + KERNEL_SPACE_NR, + LOW_KERNEL_NR, + VMALLOC_START_NR, + VMEMMAP_START_NR, + HIGH_KERNEL_NR, + MODULES_VADDR_NR, + MODULES_END_NR, +#else + KERNEL_SPACE_NR, + VMALLOC_START_NR, + VMALLOC_END_NR, +# ifdef CONFIG_HIGHMEM + PKMAP_BASE_NR, +# endif + FIXADDR_START_NR, +#endif +}; + /* Address space markers hints */ static struct addr_marker address_markers[] = { { 0, "User Space" }, @@ -331,14 +353,12 @@ static int pt_dump_init(void) #ifdef CONFIG_X86_32 /* Not a compile-time constant on x86-32 */ - address_markers[2].start_address = VMALLOC_START; - address_markers[3].start_address = VMALLOC_END; + address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; + address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; # ifdef CONFIG_HIGHMEM - address_markers[4].start_address = PKMAP_BASE; - address_markers[5].start_address = FIXADDR_START; -# else - address_markers[4].start_address = FIXADDR_START; + address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE; # endif + address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; #endif pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 12e4d2d3c11..3ba6e0608c5 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -62,8 +62,8 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, static void __iomem *__ioremap_caller(resource_size_t phys_addr, unsigned long size, unsigned long prot_val, void *caller) { - unsigned long pfn, offset, vaddr; - resource_size_t last_addr; + unsigned long offset, vaddr; + resource_size_t pfn, last_pfn, last_addr; const resource_size_t unaligned_phys_addr = phys_addr; const unsigned long unaligned_size = size; struct vm_struct *area; @@ -100,10 +100,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ - for (pfn = phys_addr >> PAGE_SHIFT; - (pfn << PAGE_SHIFT) < (last_addr & PAGE_MASK); - pfn++) { - + last_pfn = last_addr >> PAGE_SHIFT; + for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) { int is_ram = page_is_ram(pfn); if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) @@ -115,7 +113,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, * Mappings have to be page-aligned */ offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; + phys_addr &= PHYSICAL_PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; retval = reserve_memtype(phys_addr, (u64)phys_addr + size, @@ -613,7 +611,7 @@ void __init early_iounmap(void __iomem *addr, unsigned long size) return; } offset = virt_addr & ~PAGE_MASK; - nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT; + nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT; idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; while (nrpages > 0) { diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 5d0e67fff1a..e5d5e2ce9f7 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -45,6 +45,8 @@ struct kmmio_fault_page { * Protected by kmmio_lock, when linked into kmmio_page_table. */ int count; + + bool scheduled_for_release; }; struct kmmio_delayed_release { @@ -398,8 +400,11 @@ static void release_kmmio_fault_page(unsigned long page, BUG_ON(f->count < 0); if (!f->count) { disarm_kmmio_fault_page(f); - f->release_next = *release_list; - *release_list = f; + if (!f->scheduled_for_release) { + f->release_next = *release_list; + *release_list = f; + f->scheduled_for_release = true; + } } } @@ -471,8 +476,10 @@ static void remove_kmmio_fault_pages(struct rcu_head *head) prevp = &f->release_next; } else { *prevp = f->release_next; + f->release_next = NULL; + f->scheduled_for_release = false; } - f = f->release_next; + f = *prevp; } spin_unlock_irqrestore(&kmmio_lock, flags); @@ -510,6 +517,9 @@ void unregister_kmmio_probe(struct kmmio_probe *p) kmmio_count--; spin_unlock_irqrestore(&kmmio_lock, flags); + if (!release_list) + return; + drelease = kmalloc(sizeof(*drelease), GFP_ATOMIC); if (!drelease) { pr_crit("leaking kmmio_fault_page objects.\n"); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 64121a18b8c..f6ff57b7efa 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -158,7 +158,7 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) return req_type; } -static int pat_pagerange_is_ram(unsigned long start, unsigned long end) +static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end) { int ram_page = 0, not_rampage = 0; unsigned long page_nr; diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c index 308e32570d8..38e6d174c49 100644 --- a/arch/x86/mm/pf_in.c +++ b/arch/x86/mm/pf_in.c @@ -40,16 +40,16 @@ static unsigned char prefix_codes[] = { static unsigned int reg_rop[] = { 0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F }; -static unsigned int reg_wop[] = { 0x88, 0x89 }; +static unsigned int reg_wop[] = { 0x88, 0x89, 0xAA, 0xAB }; static unsigned int imm_wop[] = { 0xC6, 0xC7 }; /* IA32 Manual 3, 3-432*/ -static unsigned int rw8[] = { 0x88, 0x8A, 0xC6 }; +static unsigned int rw8[] = { 0x88, 0x8A, 0xC6, 0xAA }; static unsigned int rw32[] = { - 0x89, 0x8B, 0xC7, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F + 0x89, 0x8B, 0xC7, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F, 0xAB }; -static unsigned int mw8[] = { 0x88, 0x8A, 0xC6, 0xB60F, 0xBE0F }; +static unsigned int mw8[] = { 0x88, 0x8A, 0xC6, 0xB60F, 0xBE0F, 0xAA }; static unsigned int mw16[] = { 0xB70F, 0xBF0F }; -static unsigned int mw32[] = { 0x89, 0x8B, 0xC7 }; +static unsigned int mw32[] = { 0x89, 0x8B, 0xC7, 0xAB }; static unsigned int mw64[] = {}; #else /* not __i386__ */ static unsigned char prefix_codes[] = { @@ -63,20 +63,20 @@ static unsigned char prefix_codes[] = { static unsigned int reg_rop[] = { 0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F }; -static unsigned int reg_wop[] = { 0x88, 0x89 }; +static unsigned int reg_wop[] = { 0x88, 0x89, 0xAA, 0xAB }; static unsigned int imm_wop[] = { 0xC6, 0xC7 }; -static unsigned int rw8[] = { 0xC6, 0x88, 0x8A }; +static unsigned int rw8[] = { 0xC6, 0x88, 0x8A, 0xAA }; static unsigned int rw32[] = { - 0xC7, 0x89, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F + 0xC7, 0x89, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F, 0xAB }; /* 8 bit only */ -static unsigned int mw8[] = { 0xC6, 0x88, 0x8A, 0xB60F, 0xBE0F }; +static unsigned int mw8[] = { 0xC6, 0x88, 0x8A, 0xB60F, 0xBE0F, 0xAA }; /* 16 bit only */ static unsigned int mw16[] = { 0xB70F, 0xBF0F }; /* 16 or 32 bit */ static unsigned int mw32[] = { 0xC7 }; /* 16, 32 or 64 bit */ -static unsigned int mw64[] = { 0x89, 0x8B }; +static unsigned int mw64[] = { 0x89, 0x8B, 0xAB }; #endif /* not __i386__ */ struct prefix_bits { @@ -410,7 +410,6 @@ static unsigned long *get_reg_w32(int no, struct pt_regs *regs) unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs) { unsigned int opcode; - unsigned char mod_rm; int reg; unsigned char *p; struct prefix_bits prf; @@ -437,8 +436,13 @@ unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs) goto err; do_work: - mod_rm = *p; - reg = ((mod_rm >> 3) & 0x7) | (prf.rexr << 3); + /* for STOS, source register is fixed */ + if (opcode == 0xAA || opcode == 0xAB) { + reg = arg_AX; + } else { + unsigned char mod_rm = *p; + reg = ((mod_rm >> 3) & 0x7) | (prf.rexr << 3); + } switch (get_ins_reg_width(ins_addr)) { case 1: return *get_reg_w8(reg, prf.rex, regs); diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index 8565d944f7c..38868adf07e 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -90,6 +90,27 @@ static void do_test(unsigned long size) iounmap(p); } +/* + * Tests how mmiotrace behaves in face of multiple ioremap / iounmaps in + * a short time. We had a bug in deferred freeing procedure which tried + * to free this region multiple times (ioremap can reuse the same address + * for many mappings). + */ +static void do_test_bulk_ioremapping(void) +{ + void __iomem *p; + int i; + + for (i = 0; i < 10; ++i) { + p = ioremap_nocache(mmio_address, PAGE_SIZE); + if (p) + iounmap(p); + } + + /* Force freeing. If it will crash we will know why. */ + synchronize_rcu(); +} + static int __init init(void) { unsigned long size = (read_far) ? (8 << 20) : (16 << 10); @@ -104,6 +125,7 @@ static int __init init(void) "and writing 16 kB of rubbish in there.\n", size >> 10, mmio_address); do_test(size); + do_test_bulk_ioremapping(); pr_info("All done.\n"); return 0; } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 426f3a1a64d..c03f14ab666 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -278,11 +278,9 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) static void do_flush_tlb_all(void *info) { - unsigned long cpu = smp_processor_id(); - __flush_tlb_all(); if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) - leave_mm(cpu); + leave_mm(smp_processor_id()); } void flush_tlb_all(void) diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index b28d2f1253b..1ba67dc8006 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -634,6 +634,18 @@ static int __init ppro_init(char **cpu_type) if (force_arch_perfmon && cpu_has_arch_perfmon) return 0; + /* + * Documentation on identifying Intel processors by CPU family + * and model can be found in the Intel Software Developer's + * Manuals (SDM): + * + * http://www.intel.com/products/processor/manuals/ + * + * As of May 2010 the documentation for this was in the: + * "Intel 64 and IA-32 Architectures Software Developer's + * Manual Volume 3B: System Programming Guide", "Table B-1 + * CPUID Signature Values of DisplayFamily_DisplayModel". + */ switch (cpu_model) { case 0 ... 2: *cpu_type = "i386/ppro"; @@ -655,12 +667,12 @@ static int __init ppro_init(char **cpu_type) case 15: case 23: *cpu_type = "i386/core_2"; break; + case 0x1a: case 0x2e: - case 26: spec = &op_arch_perfmon_spec; *cpu_type = "i386/core_i7"; break; - case 28: + case 0x1c: *cpu_type = "i386/atom"; break; default: diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 6b4ffedb93c..4a2afa1bac5 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -120,7 +120,8 @@ $(obj)/vdso32-syms.lds: $(vdso32.so-y:%=$(obj)/vdso32-%-syms.lds) FORCE quiet_cmd_vdso = VDSO $@ cmd_vdso = $(CC) -nostdlib -o $@ \ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \ - -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) + -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ + sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) GCOV_PROFILE := n diff --git a/arch/x86/vdso/checkundef.sh b/arch/x86/vdso/checkundef.sh new file mode 100755 index 00000000000..7ee90a9b549 --- /dev/null +++ b/arch/x86/vdso/checkundef.sh @@ -0,0 +1,10 @@ +#!/bin/sh +nm="$1" +file="$2" +$nm "$file" | grep '^ *U' > /dev/null 2>&1 +if [ $? -eq 1 ]; then + exit 0 +else + echo "$file: undefined symbols found" >&2 + exit 1 +fi diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 02b442e9200..36df991985b 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -374,7 +374,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) #ifdef CONFIG_X86_64 -__initcall(sysenter_setup); +subsys_initcall(sysenter_setup); #ifdef CONFIG_SYSCTL /* Register vsyscall32 into the ABI table */ diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index ac74869b814..43456ee1769 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -74,7 +74,7 @@ static int __init init_vdso_vars(void) vdso_enabled = 0; return -ENOMEM; } -__initcall(init_vdso_vars); +subsys_initcall(init_vdso_vars); struct linux_binprm; diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index b83e119fbeb..68128a1b401 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -13,6 +13,11 @@ config XEN kernel to boot in a paravirtualized environment under the Xen hypervisor. +config XEN_PVHVM + def_bool y + depends on XEN + depends on X86_LOCAL_APIC + config XEN_MAX_DOMAIN_MEMORY int "Maximum allowed size of a domain in gigabytes" default 8 if X86_32 diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3bb4fc21f4f..93095468598 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -12,7 +12,7 @@ CFLAGS_mmu.o := $(nostackp) obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ - grant-table.o suspend.o + grant-table.o suspend.o platform-pci-unplug.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 65d8d79b46a..d4ff5e83621 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -11,6 +11,7 @@ * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/smp.h> @@ -35,8 +36,10 @@ #include <xen/interface/version.h> #include <xen/interface/physdev.h> #include <xen/interface/vcpu.h> +#include <xen/interface/memory.h> #include <xen/features.h> #include <xen/page.h> +#include <xen/hvm.h> #include <xen/hvc-console.h> #include <asm/paravirt.h> @@ -55,7 +58,9 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/reboot.h> +#include <asm/setup.h> #include <asm/stackprotector.h> +#include <asm/hypervisor.h> #include "xen-ops.h" #include "mmu.h" @@ -76,6 +81,10 @@ struct shared_info xen_dummy_shared_info; void *xen_initial_gdt; +RESERVE_BRK(shared_info_page_brk, PAGE_SIZE); +__read_mostly int xen_have_vector_callback; +EXPORT_SYMBOL_GPL(xen_have_vector_callback); + /* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. @@ -97,6 +106,14 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; */ static int have_vcpu_info_placement = 1; +static void clamp_max_cpus(void) +{ +#ifdef CONFIG_SMP + if (setup_max_cpus > MAX_VIRT_CPUS) + setup_max_cpus = MAX_VIRT_CPUS; +#endif +} + static void xen_vcpu_setup(int cpu) { struct vcpu_register_vcpu_info info; @@ -104,13 +121,17 @@ static void xen_vcpu_setup(int cpu) struct vcpu_info *vcpup; BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); - per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; - if (!have_vcpu_info_placement) - return; /* already tested, not available */ + if (cpu < MAX_VIRT_CPUS) + per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; - vcpup = &per_cpu(xen_vcpu_info, cpu); + if (!have_vcpu_info_placement) { + if (cpu >= MAX_VIRT_CPUS) + clamp_max_cpus(); + return; + } + vcpup = &per_cpu(xen_vcpu_info, cpu); info.mfn = arbitrary_virt_to_mfn(vcpup); info.offset = offset_in_page(vcpup); @@ -125,6 +146,7 @@ static void xen_vcpu_setup(int cpu) if (err) { printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err); have_vcpu_info_placement = 0; + clamp_max_cpus(); } else { /* This cpu is using the registered vcpu info, even if later ones fail to. */ @@ -731,7 +753,6 @@ static void set_xen_basic_apic_ops(void) #endif - static void xen_clts(void) { struct multicall_space mcs; @@ -926,10 +947,6 @@ static const struct pv_init_ops xen_init_ops __initdata = { .patch = xen_patch, }; -static const struct pv_time_ops xen_time_ops __initdata = { - .sched_clock = xen_sched_clock, -}; - static const struct pv_cpu_ops xen_cpu_ops __initdata = { .cpuid = xen_cpuid, @@ -1028,6 +1045,23 @@ static void xen_crash_shutdown(struct pt_regs *regs) xen_reboot(SHUTDOWN_crash); } +static int +xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) +{ + xen_reboot(SHUTDOWN_crash); + return NOTIFY_DONE; +} + +static struct notifier_block xen_panic_block = { + .notifier_call= xen_panic_event, +}; + +int xen_panic_handler_init(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, &xen_panic_block); + return 0; +} + static const struct machine_ops __initdata xen_machine_ops = { .restart = xen_restart, .halt = xen_machine_halt, @@ -1067,7 +1101,6 @@ asmlinkage void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; pv_init_ops = xen_init_ops; - pv_time_ops = xen_time_ops; pv_cpu_ops = xen_cpu_ops; pv_apic_ops = xen_apic_ops; @@ -1075,13 +1108,7 @@ asmlinkage void __init xen_start_kernel(void) x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; - x86_init.timers.timer_init = xen_time_init; - x86_init.timers.setup_percpu_clockev = x86_init_noop; - x86_cpuinit.setup_percpu_clockev = x86_init_noop; - - x86_platform.calibrate_tsc = xen_tsc_khz; - x86_platform.get_wallclock = xen_get_wallclock; - x86_platform.set_wallclock = xen_set_wallclock; + xen_init_time_ops(); /* * Set up some pagetable state before starting to set any ptes. @@ -1206,3 +1233,139 @@ asmlinkage void __init xen_start_kernel(void) x86_64_start_reservations((char *)__pa_symbol(&boot_params)); #endif } + +static uint32_t xen_cpuid_base(void) +{ + uint32_t base, eax, ebx, ecx, edx; + char signature[13]; + + for (base = 0x40000000; base < 0x40010000; base += 0x100) { + cpuid(base, &eax, &ebx, &ecx, &edx); + *(uint32_t *)(signature + 0) = ebx; + *(uint32_t *)(signature + 4) = ecx; + *(uint32_t *)(signature + 8) = edx; + signature[12] = 0; + + if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2)) + return base; + } + + return 0; +} + +static int init_hvm_pv_info(int *major, int *minor) +{ + uint32_t eax, ebx, ecx, edx, pages, msr, base; + u64 pfn; + + base = xen_cpuid_base(); + cpuid(base + 1, &eax, &ebx, &ecx, &edx); + + *major = eax >> 16; + *minor = eax & 0xffff; + printk(KERN_INFO "Xen version %d.%d.\n", *major, *minor); + + cpuid(base + 2, &pages, &msr, &ecx, &edx); + + pfn = __pa(hypercall_page); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + + xen_setup_features(); + + pv_info = xen_info; + pv_info.kernel_rpl = 0; + + xen_domain_type = XEN_HVM_DOMAIN; + + return 0; +} + +void xen_hvm_init_shared_info(void) +{ + int cpu; + struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + + if (!shared_info_page) + shared_info_page = (struct shared_info *) + extend_brk(PAGE_SIZE, PAGE_SIZE); + xatp.domid = DOMID_SELF; + xatp.idx = 0; + xatp.space = XENMAPSPACE_shared_info; + xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; + if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) + BUG(); + + HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; + + /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info + * page, we use it in the event channel upcall and in some pvclock + * related functions. We don't need the vcpu_info placement + * optimizations because we don't use any pv_mmu or pv_irq op on + * HVM. + * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_init_shared_info is run at resume time too and + * in that case multiple vcpus might be online. */ + for_each_online_cpu(cpu) { + per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + } +} + +#ifdef CONFIG_XEN_PVHVM +static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + int cpu = (long)hcpu; + switch (action) { + case CPU_UP_PREPARE: + per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata xen_hvm_cpu_notifier = { + .notifier_call = xen_hvm_cpu_notify, +}; + +static void __init xen_hvm_guest_init(void) +{ + int r; + int major, minor; + + r = init_hvm_pv_info(&major, &minor); + if (r < 0) + return; + + xen_hvm_init_shared_info(); + + if (xen_feature(XENFEAT_hvm_callback_vector)) + xen_have_vector_callback = 1; + register_cpu_notifier(&xen_hvm_cpu_notifier); + xen_unplug_emulated_devices(); + have_vcpu_info_placement = 0; + x86_init.irqs.intr_init = xen_init_IRQ; + xen_hvm_init_time_ops(); + xen_hvm_init_mmu_ops(); +} + +static bool __init xen_hvm_platform(void) +{ + if (xen_pv_domain()) + return false; + + if (!xen_cpuid_base()) + return false; + + return true; +} + +const __refconst struct hypervisor_x86 x86_hyper_xen_hvm = { + .name = "Xen HVM", + .detect = xen_hvm_platform, + .init_platform = xen_hvm_guest_init, +}; +EXPORT_SYMBOL(x86_hyper_xen_hvm); +#endif diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 914f04695ce..413b19b3d0f 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -58,6 +58,7 @@ #include <xen/page.h> #include <xen/interface/xen.h> +#include <xen/interface/hvm/hvm_op.h> #include <xen/interface/version.h> #include <xen/hvc-console.h> @@ -1941,6 +1942,40 @@ void __init xen_init_mmu_ops(void) pv_mmu_ops = xen_mmu_ops; } +#ifdef CONFIG_XEN_PVHVM +static void xen_hvm_exit_mmap(struct mm_struct *mm) +{ + struct xen_hvm_pagetable_dying a; + int rc; + + a.domid = DOMID_SELF; + a.gpa = __pa(mm->pgd); + rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a); + WARN_ON_ONCE(rc < 0); +} + +static int is_pagetable_dying_supported(void) +{ + struct xen_hvm_pagetable_dying a; + int rc = 0; + + a.domid = DOMID_SELF; + a.gpa = 0x00; + rc = HYPERVISOR_hvm_op(HVMOP_pagetable_dying, &a); + if (rc < 0) { + printk(KERN_DEBUG "HVMOP_pagetable_dying not supported\n"); + return 0; + } + return 1; +} + +void __init xen_hvm_init_mmu_ops(void) +{ + if (is_pagetable_dying_supported()) + pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap; +} +#endif + #ifdef CONFIG_XEN_DEBUG_FS static struct dentry *d_mmu_debug; diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 5fe6bc7f5ec..fa938c4aa2f 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -60,4 +60,5 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, unsigned long xen_read_cr2_direct(void); extern void xen_init_mmu_ops(void); +extern void xen_hvm_init_mmu_ops(void); #endif /* _XEN_MMU_H */ diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c new file mode 100644 index 00000000000..554c002a1e1 --- /dev/null +++ b/arch/x86/xen/platform-pci-unplug.c @@ -0,0 +1,137 @@ +/****************************************************************************** + * platform-pci-unplug.c + * + * Xen platform PCI device driver + * Copyright (c) 2010, Citrix + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> + +#include <xen/platform_pci.h> + +#define XEN_PLATFORM_ERR_MAGIC -1 +#define XEN_PLATFORM_ERR_PROTOCOL -2 +#define XEN_PLATFORM_ERR_BLACKLIST -3 + +/* store the value of xen_emul_unplug after the unplug is done */ +int xen_platform_pci_unplug; +EXPORT_SYMBOL_GPL(xen_platform_pci_unplug); +#ifdef CONFIG_XEN_PVHVM +static int xen_emul_unplug; + +static int __init check_platform_magic(void) +{ + short magic; + char protocol; + + magic = inw(XEN_IOPORT_MAGIC); + if (magic != XEN_IOPORT_MAGIC_VAL) { + printk(KERN_ERR "Xen Platform PCI: unrecognised magic value\n"); + return XEN_PLATFORM_ERR_MAGIC; + } + + protocol = inb(XEN_IOPORT_PROTOVER); + + printk(KERN_DEBUG "Xen Platform PCI: I/O protocol version %d\n", + protocol); + + switch (protocol) { + case 1: + outw(XEN_IOPORT_LINUX_PRODNUM, XEN_IOPORT_PRODNUM); + outl(XEN_IOPORT_LINUX_DRVVER, XEN_IOPORT_DRVVER); + if (inw(XEN_IOPORT_MAGIC) != XEN_IOPORT_MAGIC_VAL) { + printk(KERN_ERR "Xen Platform: blacklisted by host\n"); + return XEN_PLATFORM_ERR_BLACKLIST; + } + break; + default: + printk(KERN_WARNING "Xen Platform PCI: unknown I/O protocol version"); + return XEN_PLATFORM_ERR_PROTOCOL; + } + + return 0; +} + +void __init xen_unplug_emulated_devices(void) +{ + int r; + + /* check the version of the xen platform PCI device */ + r = check_platform_magic(); + /* If the version matches enable the Xen platform PCI driver. + * Also enable the Xen platform PCI driver if the version is really old + * and the user told us to ignore it. */ + if (r && !(r == XEN_PLATFORM_ERR_MAGIC && + (xen_emul_unplug & XEN_UNPLUG_IGNORE))) + return; + /* Set the default value of xen_emul_unplug depending on whether or + * not the Xen PV frontends and the Xen platform PCI driver have + * been compiled for this kernel (modules or built-in are both OK). */ + if (!xen_emul_unplug) { + if (xen_must_unplug_nics()) { + printk(KERN_INFO "Netfront and the Xen platform PCI driver have " + "been compiled for this kernel: unplug emulated NICs.\n"); + xen_emul_unplug |= XEN_UNPLUG_ALL_NICS; + } + if (xen_must_unplug_disks()) { + printk(KERN_INFO "Blkfront and the Xen platform PCI driver have " + "been compiled for this kernel: unplug emulated disks.\n" + "You might have to change the root device\n" + "from /dev/hd[a-d] to /dev/xvd[a-d]\n" + "in your root= kernel command line option\n"); + xen_emul_unplug |= XEN_UNPLUG_ALL_IDE_DISKS; + } + } + /* Now unplug the emulated devices */ + if (!(xen_emul_unplug & XEN_UNPLUG_IGNORE)) + outw(xen_emul_unplug, XEN_IOPORT_UNPLUG); + xen_platform_pci_unplug = xen_emul_unplug; +} + +static int __init parse_xen_emul_unplug(char *arg) +{ + char *p, *q; + int l; + + for (p = arg; p; p = q) { + q = strchr(p, ','); + if (q) { + l = q - p; + q++; + } else { + l = strlen(p); + } + if (!strncmp(p, "all", l)) + xen_emul_unplug |= XEN_UNPLUG_ALL; + else if (!strncmp(p, "ide-disks", l)) + xen_emul_unplug |= XEN_UNPLUG_ALL_IDE_DISKS; + else if (!strncmp(p, "aux-ide-disks", l)) + xen_emul_unplug |= XEN_UNPLUG_AUX_IDE_DISKS; + else if (!strncmp(p, "nics", l)) + xen_emul_unplug |= XEN_UNPLUG_ALL_NICS; + else if (!strncmp(p, "ignore", l)) + xen_emul_unplug |= XEN_UNPLUG_IGNORE; + else + printk(KERN_WARNING "unrecognised option '%s' " + "in parameter 'xen_emul_unplug'\n", p); + } + return 0; +} +early_param("xen_emul_unplug", parse_xen_emul_unplug); +#endif diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ad0047f47cd..328b0030542 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -20,6 +20,7 @@ #include <xen/page.h> #include <xen/interface/callback.h> #include <xen/interface/physdev.h> +#include <xen/interface/memory.h> #include <xen/features.h> #include "xen-ops.h" @@ -32,6 +33,73 @@ extern void xen_sysenter_target(void); extern void xen_syscall_target(void); extern void xen_syscall32_target(void); +static unsigned long __init xen_release_chunk(phys_addr_t start_addr, + phys_addr_t end_addr) +{ + struct xen_memory_reservation reservation = { + .address_bits = 0, + .extent_order = 0, + .domid = DOMID_SELF + }; + unsigned long start, end; + unsigned long len = 0; + unsigned long pfn; + int ret; + + start = PFN_UP(start_addr); + end = PFN_DOWN(end_addr); + + if (end <= start) + return 0; + + printk(KERN_INFO "xen_release_chunk: looking at area pfn %lx-%lx: ", + start, end); + for(pfn = start; pfn < end; pfn++) { + unsigned long mfn = pfn_to_mfn(pfn); + + /* Make sure pfn exists to start with */ + if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn) + continue; + + set_xen_guest_handle(reservation.extent_start, &mfn); + reservation.nr_extents = 1; + + ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, + &reservation); + WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n", + start, end, ret); + if (ret == 1) { + set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + len++; + } + } + printk(KERN_CONT "%ld pages freed\n", len); + + return len; +} + +static unsigned long __init xen_return_unused_memory(unsigned long max_pfn, + const struct e820map *e820) +{ + phys_addr_t max_addr = PFN_PHYS(max_pfn); + phys_addr_t last_end = 0; + unsigned long released = 0; + int i; + + for (i = 0; i < e820->nr_map && last_end < max_addr; i++) { + phys_addr_t end = e820->map[i].addr; + end = min(max_addr, end); + + released += xen_release_chunk(last_end, end); + last_end = e820->map[i].addr + e820->map[i].size; + } + + if (last_end < max_addr) + released += xen_release_chunk(last_end, max_addr); + + printk(KERN_INFO "released %ld pages of unused memory\n", released); + return released; +} /** * machine_specific_memory_setup - Hook for machine specific memory setup. @@ -67,6 +135,8 @@ char * __init xen_memory_setup(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + xen_return_unused_memory(xen_start_info->nr_pages, &e820); + return "Xen"; } @@ -156,6 +226,8 @@ void __init xen_arch_setup(void) struct physdev_set_iopl set_iopl; int rc; + xen_panic_handler_init(); + HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_writable_pagetables); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index a29693fd313..25f232b18a8 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -394,6 +394,8 @@ static void stop_self(void *v) load_cr3(swapper_pg_dir); /* should set up a minimal gdt */ + set_cpu_online(cpu, false); + HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL); BUG(); } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index a9c66110803..1d789d56877 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -26,6 +26,18 @@ void xen_pre_suspend(void) BUG(); } +void xen_hvm_post_suspend(int suspend_cancelled) +{ + int cpu; + xen_hvm_init_shared_info(); + xen_callback_vector(); + if (xen_feature(XENFEAT_hvm_safe_pvclock)) { + for_each_online_cpu(cpu) { + xen_setup_runstate_info(cpu); + } + } +} + void xen_post_suspend(int suspend_cancelled) { xen_build_mfn_list_list(); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index b3c6c59ed30..1a5353a753f 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -20,6 +20,7 @@ #include <asm/xen/hypercall.h> #include <xen/events.h> +#include <xen/features.h> #include <xen/interface/xen.h> #include <xen/interface/vcpu.h> @@ -155,47 +156,8 @@ static void do_stolen_accounting(void) account_idle_ticks(ticks); } -/* - * Xen sched_clock implementation. Returns the number of unstolen - * nanoseconds, which is nanoseconds the VCPU spent in RUNNING+BLOCKED - * states. - */ -unsigned long long xen_sched_clock(void) -{ - struct vcpu_runstate_info state; - cycle_t now; - u64 ret; - s64 offset; - - /* - * Ideally sched_clock should be called on a per-cpu basis - * anyway, so preempt should already be disabled, but that's - * not current practice at the moment. - */ - preempt_disable(); - - now = xen_clocksource_read(); - - get_runstate_snapshot(&state); - - WARN_ON(state.state != RUNSTATE_running); - - offset = now - state.state_entry_time; - if (offset < 0) - offset = 0; - - ret = state.time[RUNSTATE_blocked] + - state.time[RUNSTATE_running] + - offset; - - preempt_enable(); - - return ret; -} - - /* Get the TSC speed from Xen */ -unsigned long xen_tsc_khz(void) +static unsigned long xen_tsc_khz(void) { struct pvclock_vcpu_time_info *info = &HYPERVISOR_shared_info->vcpu_info[0].time; @@ -230,7 +192,7 @@ static void xen_read_wallclock(struct timespec *ts) put_cpu_var(xen_vcpu); } -unsigned long xen_get_wallclock(void) +static unsigned long xen_get_wallclock(void) { struct timespec ts; @@ -238,7 +200,7 @@ unsigned long xen_get_wallclock(void) return ts.tv_sec; } -int xen_set_wallclock(unsigned long now) +static int xen_set_wallclock(unsigned long now) { /* do nothing for domU */ return -1; @@ -473,7 +435,11 @@ void xen_timer_resume(void) } } -__init void xen_time_init(void) +static const struct pv_time_ops xen_time_ops __initdata = { + .sched_clock = xen_clocksource_read, +}; + +static __init void xen_time_init(void) { int cpu = smp_processor_id(); struct timespec tp; @@ -497,3 +463,47 @@ __init void xen_time_init(void) xen_setup_timer(cpu); xen_setup_cpu_clockevents(); } + +__init void xen_init_time_ops(void) +{ + pv_time_ops = xen_time_ops; + + x86_init.timers.timer_init = xen_time_init; + x86_init.timers.setup_percpu_clockev = x86_init_noop; + x86_cpuinit.setup_percpu_clockev = x86_init_noop; + + x86_platform.calibrate_tsc = xen_tsc_khz; + x86_platform.get_wallclock = xen_get_wallclock; + x86_platform.set_wallclock = xen_set_wallclock; +} + +#ifdef CONFIG_XEN_PVHVM +static void xen_hvm_setup_cpu_clockevents(void) +{ + int cpu = smp_processor_id(); + xen_setup_runstate_info(cpu); + xen_setup_timer(cpu); + xen_setup_cpu_clockevents(); +} + +__init void xen_hvm_init_time_ops(void) +{ + /* vector callback is needed otherwise we cannot receive interrupts + * on cpu > 0 */ + if (!xen_have_vector_callback && num_present_cpus() > 1) + return; + if (!xen_feature(XENFEAT_hvm_safe_pvclock)) { + printk(KERN_INFO "Xen doesn't support pvclock on HVM," + "disable pv timer\n"); + return; + } + + pv_time_ops = xen_time_ops; + x86_init.timers.setup_percpu_clockev = xen_time_init; + x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents; + + x86_platform.calibrate_tsc = xen_tsc_khz; + x86_platform.get_wallclock = xen_get_wallclock; + x86_platform.set_wallclock = xen_set_wallclock; +} +#endif diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index f9153a300bc..7c8ab86163e 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -38,6 +38,10 @@ void xen_enable_sysenter(void); void xen_enable_syscall(void); void xen_vcpu_restore(void); +void xen_callback_vector(void); +void xen_hvm_init_shared_info(void); +void __init xen_unplug_emulated_devices(void); + void __init xen_build_dynamic_phys_to_machine(void); void xen_init_irq_ops(void); @@ -46,11 +50,8 @@ void xen_setup_runstate_info(int cpu); void xen_teardown_timer(int cpu); cycle_t xen_clocksource_read(void); void xen_setup_cpu_clockevents(void); -unsigned long xen_tsc_khz(void); -void __init xen_time_init(void); -unsigned long xen_get_wallclock(void); -int xen_set_wallclock(unsigned long time); -unsigned long long xen_sched_clock(void); +void __init xen_init_time_ops(void); +void __init xen_hvm_init_time_ops(void); irqreturn_t xen_debug_interrupt(int irq, void *dev_id); @@ -101,4 +102,6 @@ void xen_sysret32(void); void xen_sysret64(void); void xen_adjust_exception_frame(void); +extern int xen_panic_handler_init(void); + #endif /* XEN_OPS_H */ diff --git a/arch/xtensa/include/asm/local64.h b/arch/xtensa/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/xtensa/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index e9a8026d39f..eead3f581fb 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -164,7 +164,7 @@ static void lapic_timer_check_state(int state, struct acpi_processor *pr, if (cpu_has(&cpu_data(pr->id), X86_FEATURE_ARAT)) return; - if (boot_cpu_has(X86_FEATURE_AMDC1E)) + if (c1e_detected) type = ACPI_STATE_C1; /* diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index aa85a98d3a4..8fae6afd6a3 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -187,6 +187,15 @@ config ATA_PIIX If unsure, say N. +config SATA_DWC + tristate "DesignWare Cores SATA support" + depends on 460EX + help + This option enables support for the on-chip SATA controller of the + AppliedMicro processor 460EX. + + If unsure, say N. + config SATA_MV tristate "Marvell SATA support" help @@ -796,6 +805,15 @@ config PATA_RZ1000 If unsure, say N. +config PATA_SAMSUNG_CF + tristate "Samsung SoC PATA support" + depends on SAMSUNG_DEV_IDE + help + This option enables basic support for Samsung's S3C/S5P board + PATA controllers via the new ATA layer + + If unsure, say N. + config PATA_WINBOND_VLB tristate "Winbond W83759A VLB PATA support (Experimental)" depends on ISA && EXPERIMENTAL diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile index 7ef89d73df6..6540632bda0 100644 --- a/drivers/ata/Makefile +++ b/drivers/ata/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_SATA_AHCI_PLATFORM) += ahci_platform.o libahci.o obj-$(CONFIG_SATA_FSL) += sata_fsl.o obj-$(CONFIG_SATA_INIC162X) += sata_inic162x.o obj-$(CONFIG_SATA_SIL24) += sata_sil24.o +obj-$(CONFIG_SATA_DWC) += sata_dwc_460ex.o # SFF w/ custom DMA obj-$(CONFIG_PDC_ADMA) += pdc_adma.o @@ -87,6 +88,7 @@ obj-$(CONFIG_PATA_OF_PLATFORM) += pata_of_platform.o obj-$(CONFIG_PATA_QDI) += pata_qdi.o obj-$(CONFIG_PATA_RB532) += pata_rb532_cf.o obj-$(CONFIG_PATA_RZ1000) += pata_rz1000.o +obj-$(CONFIG_PATA_SAMSUNG_CF) += pata_samsung_cf.o obj-$(CONFIG_PATA_WINBOND_VLB) += pata_winbond.o # Should be last but two libata driver diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index f2522534ae6..fe75d8befc3 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1042,7 +1042,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) VPRINTK("ENTER\n"); - WARN_ON(ATA_MAX_QUEUE > AHCI_MAX_CMDS); + WARN_ON((int)ATA_MAX_QUEUE > AHCI_MAX_CMDS); if (!printed_version++) dev_printk(KERN_DEBUG, &pdev->dev, "version " DRV_VERSION "\n"); diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 5e11b160f24..4e97f33cca4 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -54,19 +54,13 @@ static int __init ahci_probe(struct platform_device *pdev) return -EINVAL; } - if (pdata && pdata->init) { - rc = pdata->init(dev); - if (rc) - return rc; - } - if (pdata && pdata->ata_port_info) pi = *pdata->ata_port_info; hpriv = devm_kzalloc(dev, sizeof(*hpriv), GFP_KERNEL); if (!hpriv) { - rc = -ENOMEM; - goto err0; + dev_err(dev, "can't alloc ahci_host_priv\n"); + return -ENOMEM; } hpriv->flags |= (unsigned long)pi.private_data; @@ -74,8 +68,19 @@ static int __init ahci_probe(struct platform_device *pdev) hpriv->mmio = devm_ioremap(dev, mem->start, resource_size(mem)); if (!hpriv->mmio) { dev_err(dev, "can't map %pR\n", mem); - rc = -ENOMEM; - goto err0; + return -ENOMEM; + } + + /* + * Some platforms might need to prepare for mmio region access, + * which could be done in the following init call. So, the mmio + * region shouldn't be accessed before init (if provided) has + * returned successfully. + */ + if (pdata && pdata->init) { + rc = pdata->init(dev, hpriv->mmio); + if (rc) + return rc; } ahci_save_initial_config(dev, hpriv, @@ -166,7 +171,6 @@ static int __devexit ahci_remove(struct platform_device *pdev) } static struct platform_driver ahci_driver = { - .probe = ahci_probe, .remove = __devexit_p(ahci_remove), .driver = { .name = "ahci", diff --git a/drivers/ata/ata_generic.c b/drivers/ata/ata_generic.c index 7107a6929de..cc5f7726bde 100644 --- a/drivers/ata/ata_generic.c +++ b/drivers/ata/ata_generic.c @@ -54,7 +54,6 @@ static int generic_set_mode(struct ata_link *link, struct ata_device **unused) const struct pci_device_id *id = ap->host->private_data; int dma_enabled = 0; struct ata_device *dev; - struct pci_dev *pdev = to_pci_dev(ap->host->dev); if (id->driver_data & ATA_GEN_FORCE_DMA) { dma_enabled = 0xff; @@ -63,9 +62,6 @@ static int generic_set_mode(struct ata_link *link, struct ata_device **unused) dma_enabled = ioread8(ap->ioaddr.bmdma_addr + ATA_DMA_STATUS); } - if (pdev->vendor == PCI_VENDOR_ID_CENATEK) - dma_enabled = 0xFF; - ata_for_each_dev(dev, link, ENABLED) { /* We don't really care */ dev->pio_mode = XFER_PIO_0; diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 7409f98d2ae..3971bc0a483 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -158,6 +158,7 @@ struct piix_map_db { struct piix_host_priv { const int *map; u32 saved_iocfg; + spinlock_t sidpr_lock; /* FIXME: remove once locking in EH is fixed */ void __iomem *sidpr; }; @@ -951,12 +952,15 @@ static int piix_sidpr_scr_read(struct ata_link *link, unsigned int reg, u32 *val) { struct piix_host_priv *hpriv = link->ap->host->private_data; + unsigned long flags; if (reg >= ARRAY_SIZE(piix_sidx_map)) return -EINVAL; + spin_lock_irqsave(&hpriv->sidpr_lock, flags); piix_sidpr_sel(link, reg); *val = ioread32(hpriv->sidpr + PIIX_SIDPR_DATA); + spin_unlock_irqrestore(&hpriv->sidpr_lock, flags); return 0; } @@ -964,12 +968,15 @@ static int piix_sidpr_scr_write(struct ata_link *link, unsigned int reg, u32 val) { struct piix_host_priv *hpriv = link->ap->host->private_data; + unsigned long flags; if (reg >= ARRAY_SIZE(piix_sidx_map)) return -EINVAL; + spin_lock_irqsave(&hpriv->sidpr_lock, flags); piix_sidpr_sel(link, reg); iowrite32(val, hpriv->sidpr + PIIX_SIDPR_DATA); + spin_unlock_irqrestore(&hpriv->sidpr_lock, flags); return 0; } @@ -1566,6 +1573,7 @@ static int __devinit piix_init_one(struct pci_dev *pdev, hpriv = devm_kzalloc(dev, sizeof(*hpriv), GFP_KERNEL); if (!hpriv) return -ENOMEM; + spin_lock_init(&hpriv->sidpr_lock); /* Save IOCFG, this will be used for cable detection, quirk * detection and restoration on detach. This is necessary diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index ddf8e486278..a0a4d696840 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4167,15 +4167,13 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "WDC AC23200L", "21.10N21", ATA_HORKAGE_NODMA }, { "Compaq CRD-8241B", NULL, ATA_HORKAGE_NODMA }, { "CRD-8400B", NULL, ATA_HORKAGE_NODMA }, - { "CRD-8480B", NULL, ATA_HORKAGE_NODMA }, - { "CRD-8482B", NULL, ATA_HORKAGE_NODMA }, + { "CRD-848[02]B", NULL, ATA_HORKAGE_NODMA }, { "CRD-84", NULL, ATA_HORKAGE_NODMA }, { "SanDisk SDP3B", NULL, ATA_HORKAGE_NODMA }, { "SanDisk SDP3B-64", NULL, ATA_HORKAGE_NODMA }, { "SANYO CD-ROM CRD", NULL, ATA_HORKAGE_NODMA }, { "HITACHI CDR-8", NULL, ATA_HORKAGE_NODMA }, - { "HITACHI CDR-8335", NULL, ATA_HORKAGE_NODMA }, - { "HITACHI CDR-8435", NULL, ATA_HORKAGE_NODMA }, + { "HITACHI CDR-8[34]35",NULL, ATA_HORKAGE_NODMA }, { "Toshiba CD-ROM XM-6202B", NULL, ATA_HORKAGE_NODMA }, { "TOSHIBA CD-ROM XM-1702BC", NULL, ATA_HORKAGE_NODMA }, { "CD-532E-A", NULL, ATA_HORKAGE_NODMA }, @@ -4211,70 +4209,16 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "OCZ CORE_SSD", "02.10104", ATA_HORKAGE_NONCQ }, /* Seagate NCQ + FLUSH CACHE firmware bug */ - { "ST31500341AS", "SD15", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST31500341AS", "SD16", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST31500341AS", "SD17", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST31500341AS", "SD18", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST31500341AS", "SD19", ATA_HORKAGE_NONCQ | + { "ST31500341AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, - { "ST31000333AS", "SD15", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST31000333AS", "SD16", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST31000333AS", "SD17", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST31000333AS", "SD18", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST31000333AS", "SD19", ATA_HORKAGE_NONCQ | + { "ST31000333AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640623AS", "SD15", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640623AS", "SD16", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640623AS", "SD17", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640623AS", "SD18", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640623AS", "SD19", ATA_HORKAGE_NONCQ | + { "ST3640[36]23AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640323AS", "SD15", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640323AS", "SD16", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640323AS", "SD17", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640323AS", "SD18", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3640323AS", "SD19", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - - { "ST3320813AS", "SD15", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3320813AS", "SD16", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3320813AS", "SD17", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3320813AS", "SD18", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3320813AS", "SD19", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - - { "ST3320613AS", "SD15", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3320613AS", "SD16", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3320613AS", "SD17", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3320613AS", "SD18", ATA_HORKAGE_NONCQ | - ATA_HORKAGE_FIRMWARE_WARN }, - { "ST3320613AS", "SD19", ATA_HORKAGE_NONCQ | + { "ST3320[68]13AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, /* Blacklist entries taken from Silicon Image 3124/3132 @@ -4303,12 +4247,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* Devices which get the IVB wrong */ { "QUANTUM FIREBALLlct10 05", "A03.0900", ATA_HORKAGE_IVB, }, /* Maybe we should just blacklist TSSTcorp... */ - { "TSSTcorp CDDVDW SH-S202H", "SB00", ATA_HORKAGE_IVB, }, - { "TSSTcorp CDDVDW SH-S202H", "SB01", ATA_HORKAGE_IVB, }, - { "TSSTcorp CDDVDW SH-S202J", "SB00", ATA_HORKAGE_IVB, }, - { "TSSTcorp CDDVDW SH-S202J", "SB01", ATA_HORKAGE_IVB, }, - { "TSSTcorp CDDVDW SH-S202N", "SB00", ATA_HORKAGE_IVB, }, - { "TSSTcorp CDDVDW SH-S202N", "SB01", ATA_HORKAGE_IVB, }, + { "TSSTcorp CDDVDW SH-S202[HJN]", "SB0[01]", ATA_HORKAGE_IVB, }, /* Devices that do not need bridging limits applied */ { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK, }, @@ -4326,29 +4265,73 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { } }; -static int strn_pattern_cmp(const char *patt, const char *name, int wildchar) +/** + * glob_match - match a text string against a glob-style pattern + * @text: the string to be examined + * @pattern: the glob-style pattern to be matched against + * + * Either/both of text and pattern can be empty strings. + * + * Match text against a glob-style pattern, with wildcards and simple sets: + * + * ? matches any single character. + * * matches any run of characters. + * [xyz] matches a single character from the set: x, y, or z. + * [a-d] matches a single character from the range: a, b, c, or d. + * [a-d0-9] matches a single character from either range. + * + * The special characters ?, [, -, or *, can be matched using a set, eg. [*] + * Behaviour with malformed patterns is undefined, though generally reasonable. + * + * Example patterns: "SD1?", "SD1[0-5]", "*R0", SD*1?[012]*xx" + * + * This function uses one level of recursion per '*' in pattern. + * Since it calls _nothing_ else, and has _no_ explicit local variables, + * this will not cause stack problems for any reasonable use here. + * + * RETURNS: + * 0 on match, 1 otherwise. + */ +static int glob_match (const char *text, const char *pattern) { - const char *p; - int len; - - /* - * check for trailing wildcard: *\0 - */ - p = strchr(patt, wildchar); - if (p && ((*(p + 1)) == 0)) - len = p - patt; - else { - len = strlen(name); - if (!len) { - if (!*patt) - return 0; - return -1; + do { + /* Match single character or a '?' wildcard */ + if (*text == *pattern || *pattern == '?') { + if (!*pattern++) + return 0; /* End of both strings: match */ + } else { + /* Match single char against a '[' bracketed ']' pattern set */ + if (!*text || *pattern != '[') + break; /* Not a pattern set */ + while (*++pattern && *pattern != ']' && *text != *pattern) { + if (*pattern == '-' && *(pattern - 1) != '[') + if (*text > *(pattern - 1) && *text < *(pattern + 1)) { + ++pattern; + break; + } + } + if (!*pattern || *pattern == ']') + return 1; /* No match */ + while (*pattern && *pattern++ != ']'); + } + } while (*++text && *pattern); + + /* Match any run of chars against a '*' wildcard */ + if (*pattern == '*') { + if (!*++pattern) + return 0; /* Match: avoid recursion at end of pattern */ + /* Loop to handle additional pattern chars after the wildcard */ + while (*text) { + if (glob_match(text, pattern) == 0) + return 0; /* Remainder matched */ + ++text; /* Absorb (match) this char and try again */ } } - - return strncmp(patt, name, len); + if (!*text && !*pattern) + return 0; /* End of both strings: match */ + return 1; /* No match */ } - + static unsigned long ata_dev_blacklisted(const struct ata_device *dev) { unsigned char model_num[ATA_ID_PROD_LEN + 1]; @@ -4359,10 +4342,10 @@ static unsigned long ata_dev_blacklisted(const struct ata_device *dev) ata_id_c_string(dev->id, model_rev, ATA_ID_FW_REV, sizeof(model_rev)); while (ad->model_num) { - if (!strn_pattern_cmp(ad->model_num, model_num, '*')) { + if (!glob_match(model_num, ad->model_num)) { if (ad->model_rev == NULL) return ad->horkage; - if (!strn_pattern_cmp(ad->model_rev, model_rev, '*')) + if (!glob_match(model_rev, ad->model_rev)) return ad->horkage; } ad++; diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index f77a67303f8..697474b625b 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -2214,6 +2214,7 @@ const char *ata_get_cmd_descript(u8 command) { ATA_CMD_SMART, "SMART" }, { ATA_CMD_MEDIA_LOCK, "DOOR LOCK" }, { ATA_CMD_MEDIA_UNLOCK, "DOOR UNLOCK" }, + { ATA_CMD_DSM, "DATA SET MANAGEMENT" }, { ATA_CMD_CHK_MED_CRD_TYP, "CHECK MEDIA CARD TYPE" }, { ATA_CMD_CFA_REQ_EXT_ERR, "CFA REQUEST EXTENDED ERROR" }, { ATA_CMD_CFA_WRITE_NE, "CFA WRITE SECTORS WITHOUT ERASE" }, diff --git a/drivers/ata/pata_samsung_cf.c b/drivers/ata/pata_samsung_cf.c new file mode 100644 index 00000000000..6f9cfb24b75 --- /dev/null +++ b/drivers/ata/pata_samsung_cf.c @@ -0,0 +1,683 @@ +/* + * Copyright (c) 2010 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * PATA driver for Samsung SoCs. + * Supports CF Interface in True IDE mode. Currently only PIO mode has been + * implemented; UDMA support has to be added. + * + * Based on: + * PATA driver for AT91SAM9260 Static Memory Controller + * PATA driver for Toshiba SCC controller + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. +*/ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/clk.h> +#include <linux/libata.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include <plat/ata.h> +#include <plat/regs-ata.h> + +#define DRV_NAME "pata_samsung_cf" +#define DRV_VERSION "0.1" + +enum s3c_cpu_type { + TYPE_S3C64XX, + TYPE_S5PC100, + TYPE_S5PV210, +}; + +/* + * struct s3c_ide_info - S3C PATA instance. + * @clk: The clock resource for this controller. + * @ide_addr: The area mapped for the hardware registers. + * @sfr_addr: The area mapped for the special function registers. + * @irq: The IRQ number we are using. + * @cpu_type: The exact type of this controller. + * @fifo_status_reg: The ATA_FIFO_STATUS register offset. + */ +struct s3c_ide_info { + struct clk *clk; + void __iomem *ide_addr; + void __iomem *sfr_addr; + unsigned int irq; + enum s3c_cpu_type cpu_type; + unsigned int fifo_status_reg; +}; + +static void pata_s3c_set_endian(void __iomem *s3c_ide_regbase, u8 mode) +{ + u32 reg = readl(s3c_ide_regbase + S3C_ATA_CFG); + reg = mode ? (reg & ~S3C_ATA_CFG_SWAP) : (reg | S3C_ATA_CFG_SWAP); + writel(reg, s3c_ide_regbase + S3C_ATA_CFG); +} + +static void pata_s3c_cfg_mode(void __iomem *s3c_ide_sfrbase) +{ + /* Select true-ide as the internal operating mode */ + writel(readl(s3c_ide_sfrbase + S3C_CFATA_MUX) | S3C_CFATA_MUX_TRUEIDE, + s3c_ide_sfrbase + S3C_CFATA_MUX); +} + +static unsigned long +pata_s3c_setup_timing(struct s3c_ide_info *info, const struct ata_timing *ata) +{ + int t1 = ata->setup; + int t2 = ata->act8b; + int t2i = ata->rec8b; + ulong piotime; + + piotime = ((t2i & 0xff) << 12) | ((t2 & 0xff) << 4) | (t1 & 0xf); + + return piotime; +} + +static void pata_s3c_set_piomode(struct ata_port *ap, struct ata_device *adev) +{ + struct s3c_ide_info *info = ap->host->private_data; + struct ata_timing timing; + int cycle_time; + ulong ata_cfg = readl(info->ide_addr + S3C_ATA_CFG); + ulong piotime; + + /* Enables IORDY if mode requires it */ + if (ata_pio_need_iordy(adev)) + ata_cfg |= S3C_ATA_CFG_IORDYEN; + else + ata_cfg &= ~S3C_ATA_CFG_IORDYEN; + + cycle_time = (int)(1000000000UL / clk_get_rate(info->clk)); + + ata_timing_compute(adev, adev->pio_mode, &timing, + cycle_time * 1000, 0); + + piotime = pata_s3c_setup_timing(info, &timing); + + writel(ata_cfg, info->ide_addr + S3C_ATA_CFG); + writel(piotime, info->ide_addr + S3C_ATA_PIO_TIME); +} + +/* + * Waits until the IDE controller is able to perform next read/write + * operation to the disk. Needed for 64XX series boards only. + */ +static int wait_for_host_ready(struct s3c_ide_info *info) +{ + ulong timeout; + void __iomem *fifo_reg = info->ide_addr + info->fifo_status_reg; + + /* wait for maximum of 20 msec */ + timeout = jiffies + msecs_to_jiffies(20); + while (time_before(jiffies, timeout)) { + if ((readl(fifo_reg) >> 28) == 0) + return 0; + } + return -EBUSY; +} + +/* + * Writes to one of the task file registers. + */ +static void ata_outb(struct ata_host *host, u8 addr, void __iomem *reg) +{ + struct s3c_ide_info *info = host->private_data; + + wait_for_host_ready(info); + writeb(addr, reg); +} + +/* + * Reads from one of the task file registers. + */ +static u8 ata_inb(struct ata_host *host, void __iomem *reg) +{ + struct s3c_ide_info *info = host->private_data; + u8 temp; + + wait_for_host_ready(info); + (void) readb(reg); + wait_for_host_ready(info); + temp = readb(info->ide_addr + S3C_ATA_PIO_RDATA); + return temp; +} + +/* + * pata_s3c_tf_load - send taskfile registers to host controller + */ +static void pata_s3c_tf_load(struct ata_port *ap, + const struct ata_taskfile *tf) +{ + struct ata_ioports *ioaddr = &ap->ioaddr; + unsigned int is_addr = tf->flags & ATA_TFLAG_ISADDR; + + if (tf->ctl != ap->last_ctl) { + ata_outb(ap->host, tf->ctl, ioaddr->ctl_addr); + ap->last_ctl = tf->ctl; + ata_wait_idle(ap); + } + + if (is_addr && (tf->flags & ATA_TFLAG_LBA48)) { + ata_outb(ap->host, tf->hob_feature, ioaddr->feature_addr); + ata_outb(ap->host, tf->hob_nsect, ioaddr->nsect_addr); + ata_outb(ap->host, tf->hob_lbal, ioaddr->lbal_addr); + ata_outb(ap->host, tf->hob_lbam, ioaddr->lbam_addr); + ata_outb(ap->host, tf->hob_lbah, ioaddr->lbah_addr); + } + + if (is_addr) { + ata_outb(ap->host, tf->feature, ioaddr->feature_addr); + ata_outb(ap->host, tf->nsect, ioaddr->nsect_addr); + ata_outb(ap->host, tf->lbal, ioaddr->lbal_addr); + ata_outb(ap->host, tf->lbam, ioaddr->lbam_addr); + ata_outb(ap->host, tf->lbah, ioaddr->lbah_addr); + } + + if (tf->flags & ATA_TFLAG_DEVICE) + ata_outb(ap->host, tf->device, ioaddr->device_addr); + + ata_wait_idle(ap); +} + +/* + * pata_s3c_tf_read - input device's ATA taskfile shadow registers + */ +static void pata_s3c_tf_read(struct ata_port *ap, struct ata_taskfile *tf) +{ + struct ata_ioports *ioaddr = &ap->ioaddr; + + tf->feature = ata_inb(ap->host, ioaddr->error_addr); + tf->nsect = ata_inb(ap->host, ioaddr->nsect_addr); + tf->lbal = ata_inb(ap->host, ioaddr->lbal_addr); + tf->lbam = ata_inb(ap->host, ioaddr->lbam_addr); + tf->lbah = ata_inb(ap->host, ioaddr->lbah_addr); + tf->device = ata_inb(ap->host, ioaddr->device_addr); + + if (tf->flags & ATA_TFLAG_LBA48) { + ata_outb(ap->host, tf->ctl | ATA_HOB, ioaddr->ctl_addr); + tf->hob_feature = ata_inb(ap->host, ioaddr->error_addr); + tf->hob_nsect = ata_inb(ap->host, ioaddr->nsect_addr); + tf->hob_lbal = ata_inb(ap->host, ioaddr->lbal_addr); + tf->hob_lbam = ata_inb(ap->host, ioaddr->lbam_addr); + tf->hob_lbah = ata_inb(ap->host, ioaddr->lbah_addr); + ata_outb(ap->host, tf->ctl, ioaddr->ctl_addr); + ap->last_ctl = tf->ctl; + } +} + +/* + * pata_s3c_exec_command - issue ATA command to host controller + */ +static void pata_s3c_exec_command(struct ata_port *ap, + const struct ata_taskfile *tf) +{ + ata_outb(ap->host, tf->command, ap->ioaddr.command_addr); + ata_sff_pause(ap); +} + +/* + * pata_s3c_check_status - Read device status register + */ +static u8 pata_s3c_check_status(struct ata_port *ap) +{ + return ata_inb(ap->host, ap->ioaddr.status_addr); +} + +/* + * pata_s3c_check_altstatus - Read alternate device status register + */ +static u8 pata_s3c_check_altstatus(struct ata_port *ap) +{ + return ata_inb(ap->host, ap->ioaddr.altstatus_addr); +} + +/* + * pata_s3c_data_xfer - Transfer data by PIO + */ +unsigned int pata_s3c_data_xfer(struct ata_device *dev, unsigned char *buf, + unsigned int buflen, int rw) +{ + struct ata_port *ap = dev->link->ap; + struct s3c_ide_info *info = ap->host->private_data; + void __iomem *data_addr = ap->ioaddr.data_addr; + unsigned int words = buflen >> 1, i; + u16 *data_ptr = (u16 *)buf; + + /* Requires wait same as in ata_inb/ata_outb */ + if (rw == READ) + for (i = 0; i < words; i++, data_ptr++) { + wait_for_host_ready(info); + (void) readw(data_addr); + wait_for_host_ready(info); + *data_ptr = readw(info->ide_addr + + S3C_ATA_PIO_RDATA); + } + else + for (i = 0; i < words; i++, data_ptr++) { + wait_for_host_ready(info); + writew(*data_ptr, data_addr); + } + + if (buflen & 0x01) + dev_err(ap->dev, "unexpected trailing data\n"); + + return words << 1; +} + +/* + * pata_s3c_dev_select - Select device on ATA bus + */ +static void pata_s3c_dev_select(struct ata_port *ap, unsigned int device) +{ + u8 tmp = ATA_DEVICE_OBS; + + if (device != 0) + tmp |= ATA_DEV1; + + ata_outb(ap->host, tmp, ap->ioaddr.device_addr); + ata_sff_pause(ap); +} + +/* + * pata_s3c_devchk - PATA device presence detection + */ +static unsigned int pata_s3c_devchk(struct ata_port *ap, + unsigned int device) +{ + struct ata_ioports *ioaddr = &ap->ioaddr; + u8 nsect, lbal; + + pata_s3c_dev_select(ap, device); + + ata_outb(ap->host, 0x55, ioaddr->nsect_addr); + ata_outb(ap->host, 0xaa, ioaddr->lbal_addr); + + ata_outb(ap->host, 0xaa, ioaddr->nsect_addr); + ata_outb(ap->host, 0x55, ioaddr->lbal_addr); + + ata_outb(ap->host, 0x55, ioaddr->nsect_addr); + ata_outb(ap->host, 0xaa, ioaddr->lbal_addr); + + nsect = ata_inb(ap->host, ioaddr->nsect_addr); + lbal = ata_inb(ap->host, ioaddr->lbal_addr); + + if ((nsect == 0x55) && (lbal == 0xaa)) + return 1; /* we found a device */ + + return 0; /* nothing found */ +} + +/* + * pata_s3c_wait_after_reset - wait for devices to become ready after reset + */ +static int pata_s3c_wait_after_reset(struct ata_link *link, + unsigned long deadline) +{ + int rc; + + msleep(ATA_WAIT_AFTER_RESET); + + /* always check readiness of the master device */ + rc = ata_sff_wait_ready(link, deadline); + /* -ENODEV means the odd clown forgot the D7 pulldown resistor + * and TF status is 0xff, bail out on it too. + */ + if (rc) + return rc; + + return 0; +} + +/* + * pata_s3c_bus_softreset - PATA device software reset + */ +static unsigned int pata_s3c_bus_softreset(struct ata_port *ap, + unsigned long deadline) +{ + struct ata_ioports *ioaddr = &ap->ioaddr; + + /* software reset. causes dev0 to be selected */ + ata_outb(ap->host, ap->ctl, ioaddr->ctl_addr); + udelay(20); + ata_outb(ap->host, ap->ctl | ATA_SRST, ioaddr->ctl_addr); + udelay(20); + ata_outb(ap->host, ap->ctl, ioaddr->ctl_addr); + ap->last_ctl = ap->ctl; + + return pata_s3c_wait_after_reset(&ap->link, deadline); +} + +/* + * pata_s3c_softreset - reset host port via ATA SRST + */ +static int pata_s3c_softreset(struct ata_link *link, unsigned int *classes, + unsigned long deadline) +{ + struct ata_port *ap = link->ap; + unsigned int devmask = 0; + int rc; + u8 err; + + /* determine if device 0 is present */ + if (pata_s3c_devchk(ap, 0)) + devmask |= (1 << 0); + + /* select device 0 again */ + pata_s3c_dev_select(ap, 0); + + /* issue bus reset */ + rc = pata_s3c_bus_softreset(ap, deadline); + /* if link is occupied, -ENODEV too is an error */ + if (rc && rc != -ENODEV) { + ata_link_printk(link, KERN_ERR, "SRST failed (errno=%d)\n", rc); + return rc; + } + + /* determine by signature whether we have ATA or ATAPI devices */ + classes[0] = ata_sff_dev_classify(&ap->link.device[0], + devmask & (1 << 0), &err); + + return 0; +} + +/* + * pata_s3c_set_devctl - Write device control register + */ +static void pata_s3c_set_devctl(struct ata_port *ap, u8 ctl) +{ + ata_outb(ap->host, ctl, ap->ioaddr.ctl_addr); +} + +static struct scsi_host_template pata_s3c_sht = { + ATA_PIO_SHT(DRV_NAME), +}; + +static struct ata_port_operations pata_s3c_port_ops = { + .inherits = &ata_sff_port_ops, + .sff_check_status = pata_s3c_check_status, + .sff_check_altstatus = pata_s3c_check_altstatus, + .sff_tf_load = pata_s3c_tf_load, + .sff_tf_read = pata_s3c_tf_read, + .sff_data_xfer = pata_s3c_data_xfer, + .sff_exec_command = pata_s3c_exec_command, + .sff_dev_select = pata_s3c_dev_select, + .sff_set_devctl = pata_s3c_set_devctl, + .softreset = pata_s3c_softreset, + .set_piomode = pata_s3c_set_piomode, +}; + +static struct ata_port_operations pata_s5p_port_ops = { + .inherits = &ata_sff_port_ops, + .set_piomode = pata_s3c_set_piomode, +}; + +static void pata_s3c_enable(void *s3c_ide_regbase, bool state) +{ + u32 temp = readl(s3c_ide_regbase + S3C_ATA_CTRL); + temp = state ? (temp | 1) : (temp & ~1); + writel(temp, s3c_ide_regbase + S3C_ATA_CTRL); +} + +static irqreturn_t pata_s3c_irq(int irq, void *dev_instance) +{ + struct ata_host *host = dev_instance; + struct s3c_ide_info *info = host->private_data; + u32 reg; + + reg = readl(info->ide_addr + S3C_ATA_IRQ); + writel(reg, info->ide_addr + S3C_ATA_IRQ); + + return ata_sff_interrupt(irq, dev_instance); +} + +static void pata_s3c_hwinit(struct s3c_ide_info *info, + struct s3c_ide_platdata *pdata) +{ + switch (info->cpu_type) { + case TYPE_S3C64XX: + /* Configure as big endian */ + pata_s3c_cfg_mode(info->sfr_addr); + pata_s3c_set_endian(info->ide_addr, 1); + pata_s3c_enable(info->ide_addr, true); + msleep(100); + + /* Remove IRQ Status */ + writel(0x1f, info->ide_addr + S3C_ATA_IRQ); + writel(0x1b, info->ide_addr + S3C_ATA_IRQ_MSK); + break; + + case TYPE_S5PC100: + pata_s3c_cfg_mode(info->sfr_addr); + /* FALLTHROUGH */ + + case TYPE_S5PV210: + /* Configure as little endian */ + pata_s3c_set_endian(info->ide_addr, 0); + pata_s3c_enable(info->ide_addr, true); + msleep(100); + + /* Remove IRQ Status */ + writel(0x3f, info->ide_addr + S3C_ATA_IRQ); + writel(0x3f, info->ide_addr + S3C_ATA_IRQ_MSK); + break; + + default: + BUG(); + } +} + +static int __init pata_s3c_probe(struct platform_device *pdev) +{ + struct s3c_ide_platdata *pdata = pdev->dev.platform_data; + struct device *dev = &pdev->dev; + struct s3c_ide_info *info; + struct resource *res; + struct ata_port *ap; + struct ata_host *host; + enum s3c_cpu_type cpu_type; + int ret; + + cpu_type = platform_get_device_id(pdev)->driver_data; + + info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL); + if (!info) { + dev_err(dev, "failed to allocate memory for device data\n"); + return -ENOMEM; + } + + info->irq = platform_get_irq(pdev, 0); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (res == NULL) { + dev_err(dev, "failed to get mem resource\n"); + return -EINVAL; + } + + if (!devm_request_mem_region(dev, res->start, + resource_size(res), DRV_NAME)) { + dev_err(dev, "error requesting register region\n"); + return -EBUSY; + } + + info->ide_addr = devm_ioremap(dev, res->start, resource_size(res)); + if (!info->ide_addr) { + dev_err(dev, "failed to map IO base address\n"); + return -ENOMEM; + } + + info->clk = clk_get(&pdev->dev, "cfcon"); + if (IS_ERR(info->clk)) { + dev_err(dev, "failed to get access to cf controller clock\n"); + ret = PTR_ERR(info->clk); + info->clk = NULL; + return ret; + } + + clk_enable(info->clk); + + /* init ata host */ + host = ata_host_alloc(dev, 1); + if (!host) { + dev_err(dev, "failed to allocate ide host\n"); + ret = -ENOMEM; + goto stop_clk; + } + + ap = host->ports[0]; + ap->flags |= ATA_FLAG_MMIO; + ap->pio_mask = ATA_PIO4; + + if (cpu_type == TYPE_S3C64XX) { + ap->ops = &pata_s3c_port_ops; + info->sfr_addr = info->ide_addr + 0x1800; + info->ide_addr += 0x1900; + info->fifo_status_reg = 0x94; + } else if (cpu_type == TYPE_S5PC100) { + ap->ops = &pata_s5p_port_ops; + info->sfr_addr = info->ide_addr + 0x1800; + info->ide_addr += 0x1900; + info->fifo_status_reg = 0x84; + } else { + ap->ops = &pata_s5p_port_ops; + info->fifo_status_reg = 0x84; + } + + info->cpu_type = cpu_type; + + if (info->irq <= 0) { + ap->flags |= ATA_FLAG_PIO_POLLING; + info->irq = 0; + ata_port_desc(ap, "no IRQ, using PIO polling\n"); + } + + ap->ioaddr.cmd_addr = info->ide_addr + S3C_ATA_CMD; + ap->ioaddr.data_addr = info->ide_addr + S3C_ATA_PIO_DTR; + ap->ioaddr.error_addr = info->ide_addr + S3C_ATA_PIO_FED; + ap->ioaddr.feature_addr = info->ide_addr + S3C_ATA_PIO_FED; + ap->ioaddr.nsect_addr = info->ide_addr + S3C_ATA_PIO_SCR; + ap->ioaddr.lbal_addr = info->ide_addr + S3C_ATA_PIO_LLR; + ap->ioaddr.lbam_addr = info->ide_addr + S3C_ATA_PIO_LMR; + ap->ioaddr.lbah_addr = info->ide_addr + S3C_ATA_PIO_LHR; + ap->ioaddr.device_addr = info->ide_addr + S3C_ATA_PIO_DVR; + ap->ioaddr.status_addr = info->ide_addr + S3C_ATA_PIO_CSD; + ap->ioaddr.command_addr = info->ide_addr + S3C_ATA_PIO_CSD; + ap->ioaddr.altstatus_addr = info->ide_addr + S3C_ATA_PIO_DAD; + ap->ioaddr.ctl_addr = info->ide_addr + S3C_ATA_PIO_DAD; + + ata_port_desc(ap, "mmio cmd 0x%llx ", + (unsigned long long)res->start); + + host->private_data = info; + + if (pdata && pdata->setup_gpio) + pdata->setup_gpio(); + + /* Set endianness and enable the interface */ + pata_s3c_hwinit(info, pdata); + + platform_set_drvdata(pdev, host); + + return ata_host_activate(host, info->irq, + info->irq ? pata_s3c_irq : NULL, + 0, &pata_s3c_sht); + +stop_clk: + clk_disable(info->clk); + clk_put(info->clk); + return ret; +} + +static int __exit pata_s3c_remove(struct platform_device *pdev) +{ + struct ata_host *host = platform_get_drvdata(pdev); + struct s3c_ide_info *info = host->private_data; + + ata_host_detach(host); + + clk_disable(info->clk); + clk_put(info->clk); + + return 0; +} + +#ifdef CONFIG_PM +static int pata_s3c_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct ata_host *host = platform_get_drvdata(pdev); + + return ata_host_suspend(host, PMSG_SUSPEND); +} + +static int pata_s3c_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct ata_host *host = platform_get_drvdata(pdev); + struct s3c_ide_platdata *pdata = pdev->dev.platform_data; + struct s3c_ide_info *info = host->private_data; + + pata_s3c_hwinit(info, pdata); + ata_host_resume(host); + + return 0; +} + +static const struct dev_pm_ops pata_s3c_pm_ops = { + .suspend = pata_s3c_suspend, + .resume = pata_s3c_resume, +}; +#endif + +/* driver device registration */ +static struct platform_device_id pata_s3c_driver_ids[] = { + { + .name = "s3c64xx-pata", + .driver_data = TYPE_S3C64XX, + }, { + .name = "s5pc100-pata", + .driver_data = TYPE_S5PC100, + }, { + .name = "s5pv210-pata", + .driver_data = TYPE_S5PV210, + }, + { } +}; + +MODULE_DEVICE_TABLE(platform, pata_s3c_driver_ids); + +static struct platform_driver pata_s3c_driver = { + .remove = __exit_p(pata_s3c_remove), + .id_table = pata_s3c_driver_ids, + .driver = { + .name = DRV_NAME, + .owner = THIS_MODULE, +#ifdef CONFIG_PM + .pm = &pata_s3c_pm_ops, +#endif + }, +}; + +static int __init pata_s3c_init(void) +{ + return platform_driver_probe(&pata_s3c_driver, pata_s3c_probe); +} + +static void __exit pata_s3c_exit(void) +{ + platform_driver_unregister(&pata_s3c_driver); +} + +module_init(pata_s3c_init); +module_exit(pata_s3c_exit); + +MODULE_AUTHOR("Abhilash Kesavan, <a.kesavan@samsung.com>"); +MODULE_DESCRIPTION("low-level driver for Samsung PATA controller"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(DRV_VERSION); diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c index d9db3f8d60e..fe36966f7e3 100644 --- a/drivers/ata/pata_scc.c +++ b/drivers/ata/pata_scc.c @@ -168,8 +168,7 @@ static const unsigned long JCACTSELtbl[2][7] = { }; static const struct pci_device_id scc_pci_tbl[] = { - {PCI_VENDOR_ID_TOSHIBA_2, PCI_DEVICE_ID_TOSHIBA_SCC_ATA, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, + { PCI_VDEVICE(TOSHIBA_2, PCI_DEVICE_ID_TOSHIBA_SCC_ATA), 0}, { } /* terminate list */ }; diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c new file mode 100644 index 00000000000..ea24c1e51be --- /dev/null +++ b/drivers/ata/sata_dwc_460ex.c @@ -0,0 +1,1756 @@ +/* + * drivers/ata/sata_dwc_460ex.c + * + * Synopsys DesignWare Cores (DWC) SATA host driver + * + * Author: Mark Miesfeld <mmiesfeld@amcc.com> + * + * Ported from 2.6.19.2 to 2.6.25/26 by Stefan Roese <sr@denx.de> + * Copyright 2008 DENX Software Engineering + * + * Based on versions provided by AMCC and Synopsys which are: + * Copyright 2006 Applied Micro Circuits Corporation + * COPYRIGHT (C) 2005 SYNOPSYS, INC. ALL RIGHTS RESERVED + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifdef CONFIG_SATA_DWC_DEBUG +#define DEBUG +#endif + +#ifdef CONFIG_SATA_DWC_VDEBUG +#define VERBOSE_DEBUG +#define DEBUG_NCQ +#endif + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/device.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/libata.h> +#include <linux/slab.h> +#include "libata.h" + +#include <scsi/scsi_host.h> +#include <scsi/scsi_cmnd.h> + +#define DRV_NAME "sata-dwc" +#define DRV_VERSION "1.0" + +/* SATA DMA driver Globals */ +#define DMA_NUM_CHANS 1 +#define DMA_NUM_CHAN_REGS 8 + +/* SATA DMA Register definitions */ +#define AHB_DMA_BRST_DFLT 64 /* 16 data items burst length*/ + +struct dmareg { + u32 low; /* Low bits 0-31 */ + u32 high; /* High bits 32-63 */ +}; + +/* DMA Per Channel registers */ +struct dma_chan_regs { + struct dmareg sar; /* Source Address */ + struct dmareg dar; /* Destination address */ + struct dmareg llp; /* Linked List Pointer */ + struct dmareg ctl; /* Control */ + struct dmareg sstat; /* Source Status not implemented in core */ + struct dmareg dstat; /* Destination Status not implemented in core*/ + struct dmareg sstatar; /* Source Status Address not impl in core */ + struct dmareg dstatar; /* Destination Status Address not implemente */ + struct dmareg cfg; /* Config */ + struct dmareg sgr; /* Source Gather */ + struct dmareg dsr; /* Destination Scatter */ +}; + +/* Generic Interrupt Registers */ +struct dma_interrupt_regs { + struct dmareg tfr; /* Transfer Interrupt */ + struct dmareg block; /* Block Interrupt */ + struct dmareg srctran; /* Source Transfer Interrupt */ + struct dmareg dsttran; /* Dest Transfer Interrupt */ + struct dmareg error; /* Error */ +}; + +struct ahb_dma_regs { + struct dma_chan_regs chan_regs[DMA_NUM_CHAN_REGS]; + struct dma_interrupt_regs interrupt_raw; /* Raw Interrupt */ + struct dma_interrupt_regs interrupt_status; /* Interrupt Status */ + struct dma_interrupt_regs interrupt_mask; /* Interrupt Mask */ + struct dma_interrupt_regs interrupt_clear; /* Interrupt Clear */ + struct dmareg statusInt; /* Interrupt combined*/ + struct dmareg rq_srcreg; /* Src Trans Req */ + struct dmareg rq_dstreg; /* Dst Trans Req */ + struct dmareg rq_sgl_srcreg; /* Sngl Src Trans Req*/ + struct dmareg rq_sgl_dstreg; /* Sngl Dst Trans Req*/ + struct dmareg rq_lst_srcreg; /* Last Src Trans Req*/ + struct dmareg rq_lst_dstreg; /* Last Dst Trans Req*/ + struct dmareg dma_cfg; /* DMA Config */ + struct dmareg dma_chan_en; /* DMA Channel Enable*/ + struct dmareg dma_id; /* DMA ID */ + struct dmareg dma_test; /* DMA Test */ + struct dmareg res1; /* reserved */ + struct dmareg res2; /* reserved */ + /* + * DMA Comp Params + * Param 6 = dma_param[0], Param 5 = dma_param[1], + * Param 4 = dma_param[2] ... + */ + struct dmareg dma_params[6]; +}; + +/* Data structure for linked list item */ +struct lli { + u32 sar; /* Source Address */ + u32 dar; /* Destination address */ + u32 llp; /* Linked List Pointer */ + struct dmareg ctl; /* Control */ + struct dmareg dstat; /* Destination Status */ +}; + +enum { + SATA_DWC_DMAC_LLI_SZ = (sizeof(struct lli)), + SATA_DWC_DMAC_LLI_NUM = 256, + SATA_DWC_DMAC_LLI_TBL_SZ = (SATA_DWC_DMAC_LLI_SZ * \ + SATA_DWC_DMAC_LLI_NUM), + SATA_DWC_DMAC_TWIDTH_BYTES = 4, + SATA_DWC_DMAC_CTRL_TSIZE_MAX = (0x00000800 * \ + SATA_DWC_DMAC_TWIDTH_BYTES), +}; + +/* DMA Register Operation Bits */ +enum { + DMA_EN = 0x00000001, /* Enable AHB DMA */ + DMA_CTL_LLP_SRCEN = 0x10000000, /* Blk chain enable Src */ + DMA_CTL_LLP_DSTEN = 0x08000000, /* Blk chain enable Dst */ +}; + +#define DMA_CTL_BLK_TS(size) ((size) & 0x000000FFF) /* Blk Transfer size */ +#define DMA_CHANNEL(ch) (0x00000001 << (ch)) /* Select channel */ + /* Enable channel */ +#define DMA_ENABLE_CHAN(ch) ((0x00000001 << (ch)) | \ + ((0x000000001 << (ch)) << 8)) + /* Disable channel */ +#define DMA_DISABLE_CHAN(ch) (0x00000000 | ((0x000000001 << (ch)) << 8)) + /* Transfer Type & Flow Controller */ +#define DMA_CTL_TTFC(type) (((type) & 0x7) << 20) +#define DMA_CTL_SMS(num) (((num) & 0x3) << 25) /* Src Master Select */ +#define DMA_CTL_DMS(num) (((num) & 0x3) << 23)/* Dst Master Select */ + /* Src Burst Transaction Length */ +#define DMA_CTL_SRC_MSIZE(size) (((size) & 0x7) << 14) + /* Dst Burst Transaction Length */ +#define DMA_CTL_DST_MSIZE(size) (((size) & 0x7) << 11) + /* Source Transfer Width */ +#define DMA_CTL_SRC_TRWID(size) (((size) & 0x7) << 4) + /* Destination Transfer Width */ +#define DMA_CTL_DST_TRWID(size) (((size) & 0x7) << 1) + +/* Assign HW handshaking interface (x) to destination / source peripheral */ +#define DMA_CFG_HW_HS_DEST(int_num) (((int_num) & 0xF) << 11) +#define DMA_CFG_HW_HS_SRC(int_num) (((int_num) & 0xF) << 7) +#define DMA_LLP_LMS(addr, master) (((addr) & 0xfffffffc) | (master)) + +/* + * This define is used to set block chaining disabled in the control low + * register. It is already in little endian format so it can be &'d dirctly. + * It is essentially: cpu_to_le32(~(DMA_CTL_LLP_SRCEN | DMA_CTL_LLP_DSTEN)) + */ +enum { + DMA_CTL_LLP_DISABLE_LE32 = 0xffffffe7, + DMA_CTL_TTFC_P2M_DMAC = 0x00000002, /* Per to mem, DMAC cntr */ + DMA_CTL_TTFC_M2P_PER = 0x00000003, /* Mem to per, peripheral cntr */ + DMA_CTL_SINC_INC = 0x00000000, /* Source Address Increment */ + DMA_CTL_SINC_DEC = 0x00000200, + DMA_CTL_SINC_NOCHANGE = 0x00000400, + DMA_CTL_DINC_INC = 0x00000000, /* Destination Address Increment */ + DMA_CTL_DINC_DEC = 0x00000080, + DMA_CTL_DINC_NOCHANGE = 0x00000100, + DMA_CTL_INT_EN = 0x00000001, /* Interrupt Enable */ + +/* Channel Configuration Register high bits */ + DMA_CFG_FCMOD_REQ = 0x00000001, /* Flow Control - request based */ + DMA_CFG_PROTCTL = (0x00000003 << 2),/* Protection Control */ + +/* Channel Configuration Register low bits */ + DMA_CFG_RELD_DST = 0x80000000, /* Reload Dest / Src Addr */ + DMA_CFG_RELD_SRC = 0x40000000, + DMA_CFG_HS_SELSRC = 0x00000800, /* Software handshake Src/ Dest */ + DMA_CFG_HS_SELDST = 0x00000400, + DMA_CFG_FIFOEMPTY = (0x00000001 << 9), /* FIFO Empty bit */ + +/* Channel Linked List Pointer Register */ + DMA_LLP_AHBMASTER1 = 0, /* List Master Select */ + DMA_LLP_AHBMASTER2 = 1, + + SATA_DWC_MAX_PORTS = 1, + + SATA_DWC_SCR_OFFSET = 0x24, + SATA_DWC_REG_OFFSET = 0x64, +}; + +/* DWC SATA Registers */ +struct sata_dwc_regs { + u32 fptagr; /* 1st party DMA tag */ + u32 fpbor; /* 1st party DMA buffer offset */ + u32 fptcr; /* 1st party DMA Xfr count */ + u32 dmacr; /* DMA Control */ + u32 dbtsr; /* DMA Burst Transac size */ + u32 intpr; /* Interrupt Pending */ + u32 intmr; /* Interrupt Mask */ + u32 errmr; /* Error Mask */ + u32 llcr; /* Link Layer Control */ + u32 phycr; /* PHY Control */ + u32 physr; /* PHY Status */ + u32 rxbistpd; /* Recvd BIST pattern def register */ + u32 rxbistpd1; /* Recvd BIST data dword1 */ + u32 rxbistpd2; /* Recvd BIST pattern data dword2 */ + u32 txbistpd; /* Trans BIST pattern def register */ + u32 txbistpd1; /* Trans BIST data dword1 */ + u32 txbistpd2; /* Trans BIST data dword2 */ + u32 bistcr; /* BIST Control Register */ + u32 bistfctr; /* BIST FIS Count Register */ + u32 bistsr; /* BIST Status Register */ + u32 bistdecr; /* BIST Dword Error count register */ + u32 res[15]; /* Reserved locations */ + u32 testr; /* Test Register */ + u32 versionr; /* Version Register */ + u32 idr; /* ID Register */ + u32 unimpl[192]; /* Unimplemented */ + u32 dmadr[256]; /* FIFO Locations in DMA Mode */ +}; + +enum { + SCR_SCONTROL_DET_ENABLE = 0x00000001, + SCR_SSTATUS_DET_PRESENT = 0x00000001, + SCR_SERROR_DIAG_X = 0x04000000, +/* DWC SATA Register Operations */ + SATA_DWC_TXFIFO_DEPTH = 0x01FF, + SATA_DWC_RXFIFO_DEPTH = 0x01FF, + SATA_DWC_DMACR_TMOD_TXCHEN = 0x00000004, + SATA_DWC_DMACR_TXCHEN = (0x00000001 | SATA_DWC_DMACR_TMOD_TXCHEN), + SATA_DWC_DMACR_RXCHEN = (0x00000002 | SATA_DWC_DMACR_TMOD_TXCHEN), + SATA_DWC_DMACR_TXRXCH_CLEAR = SATA_DWC_DMACR_TMOD_TXCHEN, + SATA_DWC_INTPR_DMAT = 0x00000001, + SATA_DWC_INTPR_NEWFP = 0x00000002, + SATA_DWC_INTPR_PMABRT = 0x00000004, + SATA_DWC_INTPR_ERR = 0x00000008, + SATA_DWC_INTPR_NEWBIST = 0x00000010, + SATA_DWC_INTPR_IPF = 0x10000000, + SATA_DWC_INTMR_DMATM = 0x00000001, + SATA_DWC_INTMR_NEWFPM = 0x00000002, + SATA_DWC_INTMR_PMABRTM = 0x00000004, + SATA_DWC_INTMR_ERRM = 0x00000008, + SATA_DWC_INTMR_NEWBISTM = 0x00000010, + SATA_DWC_LLCR_SCRAMEN = 0x00000001, + SATA_DWC_LLCR_DESCRAMEN = 0x00000002, + SATA_DWC_LLCR_RPDEN = 0x00000004, +/* This is all error bits, zero's are reserved fields. */ + SATA_DWC_SERROR_ERR_BITS = 0x0FFF0F03 +}; + +#define SATA_DWC_SCR0_SPD_GET(v) (((v) >> 4) & 0x0000000F) +#define SATA_DWC_DMACR_TX_CLEAR(v) (((v) & ~SATA_DWC_DMACR_TXCHEN) |\ + SATA_DWC_DMACR_TMOD_TXCHEN) +#define SATA_DWC_DMACR_RX_CLEAR(v) (((v) & ~SATA_DWC_DMACR_RXCHEN) |\ + SATA_DWC_DMACR_TMOD_TXCHEN) +#define SATA_DWC_DBTSR_MWR(size) (((size)/4) & SATA_DWC_TXFIFO_DEPTH) +#define SATA_DWC_DBTSR_MRD(size) ((((size)/4) & SATA_DWC_RXFIFO_DEPTH)\ + << 16) +struct sata_dwc_device { + struct device *dev; /* generic device struct */ + struct ata_probe_ent *pe; /* ptr to probe-ent */ + struct ata_host *host; + u8 *reg_base; + struct sata_dwc_regs *sata_dwc_regs; /* DW Synopsys SATA specific */ + int irq_dma; +}; + +#define SATA_DWC_QCMD_MAX 32 + +struct sata_dwc_device_port { + struct sata_dwc_device *hsdev; + int cmd_issued[SATA_DWC_QCMD_MAX]; + struct lli *llit[SATA_DWC_QCMD_MAX]; /* DMA LLI table */ + dma_addr_t llit_dma[SATA_DWC_QCMD_MAX]; + u32 dma_chan[SATA_DWC_QCMD_MAX]; + int dma_pending[SATA_DWC_QCMD_MAX]; +}; + +/* + * Commonly used DWC SATA driver Macros + */ +#define HSDEV_FROM_HOST(host) ((struct sata_dwc_device *)\ + (host)->private_data) +#define HSDEV_FROM_AP(ap) ((struct sata_dwc_device *)\ + (ap)->host->private_data) +#define HSDEVP_FROM_AP(ap) ((struct sata_dwc_device_port *)\ + (ap)->private_data) +#define HSDEV_FROM_QC(qc) ((struct sata_dwc_device *)\ + (qc)->ap->host->private_data) +#define HSDEV_FROM_HSDEVP(p) ((struct sata_dwc_device *)\ + (hsdevp)->hsdev) + +enum { + SATA_DWC_CMD_ISSUED_NOT = 0, + SATA_DWC_CMD_ISSUED_PEND = 1, + SATA_DWC_CMD_ISSUED_EXEC = 2, + SATA_DWC_CMD_ISSUED_NODATA = 3, + + SATA_DWC_DMA_PENDING_NONE = 0, + SATA_DWC_DMA_PENDING_TX = 1, + SATA_DWC_DMA_PENDING_RX = 2, +}; + +struct sata_dwc_host_priv { + void __iomem *scr_addr_sstatus; + u32 sata_dwc_sactive_issued ; + u32 sata_dwc_sactive_queued ; + u32 dma_interrupt_count; + struct ahb_dma_regs *sata_dma_regs; + struct device *dwc_dev; +}; +struct sata_dwc_host_priv host_pvt; +/* + * Prototypes + */ +static void sata_dwc_bmdma_start_by_tag(struct ata_queued_cmd *qc, u8 tag); +static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc, + u32 check_status); +static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status); +static void sata_dwc_port_stop(struct ata_port *ap); +static void sata_dwc_clear_dmacr(struct sata_dwc_device_port *hsdevp, u8 tag); +static int dma_dwc_init(struct sata_dwc_device *hsdev, int irq); +static void dma_dwc_exit(struct sata_dwc_device *hsdev); +static int dma_dwc_xfer_setup(struct scatterlist *sg, int num_elems, + struct lli *lli, dma_addr_t dma_lli, + void __iomem *addr, int dir); +static void dma_dwc_xfer_start(int dma_ch); + +static void sata_dwc_tf_dump(struct ata_taskfile *tf) +{ + dev_vdbg(host_pvt.dwc_dev, "taskfile cmd: 0x%02x protocol: %s flags:" + "0x%lx device: %x\n", tf->command, ata_get_cmd_descript\ + (tf->protocol), tf->flags, tf->device); + dev_vdbg(host_pvt.dwc_dev, "feature: 0x%02x nsect: 0x%x lbal: 0x%x " + "lbam: 0x%x lbah: 0x%x\n", tf->feature, tf->nsect, tf->lbal, + tf->lbam, tf->lbah); + dev_vdbg(host_pvt.dwc_dev, "hob_feature: 0x%02x hob_nsect: 0x%x " + "hob_lbal: 0x%x hob_lbam: 0x%x hob_lbah: 0x%x\n", + tf->hob_feature, tf->hob_nsect, tf->hob_lbal, tf->hob_lbam, + tf->hob_lbah); +} + +/* + * Function: get_burst_length_encode + * arguments: datalength: length in bytes of data + * returns value to be programmed in register corrresponding to data length + * This value is effectively the log(base 2) of the length + */ +static int get_burst_length_encode(int datalength) +{ + int items = datalength >> 2; /* div by 4 to get lword count */ + + if (items >= 64) + return 5; + + if (items >= 32) + return 4; + + if (items >= 16) + return 3; + + if (items >= 8) + return 2; + + if (items >= 4) + return 1; + + return 0; +} + +static void clear_chan_interrupts(int c) +{ + out_le32(&(host_pvt.sata_dma_regs->interrupt_clear.tfr.low), + DMA_CHANNEL(c)); + out_le32(&(host_pvt.sata_dma_regs->interrupt_clear.block.low), + DMA_CHANNEL(c)); + out_le32(&(host_pvt.sata_dma_regs->interrupt_clear.srctran.low), + DMA_CHANNEL(c)); + out_le32(&(host_pvt.sata_dma_regs->interrupt_clear.dsttran.low), + DMA_CHANNEL(c)); + out_le32(&(host_pvt.sata_dma_regs->interrupt_clear.error.low), + DMA_CHANNEL(c)); +} + +/* + * Function: dma_request_channel + * arguments: None + * returns channel number if available else -1 + * This function assigns the next available DMA channel from the list to the + * requester + */ +static int dma_request_channel(void) +{ + int i; + + for (i = 0; i < DMA_NUM_CHANS; i++) { + if (!(in_le32(&(host_pvt.sata_dma_regs->dma_chan_en.low)) &\ + DMA_CHANNEL(i))) + return i; + } + dev_err(host_pvt.dwc_dev, "%s NO channel chan_en: 0x%08x\n", __func__, + in_le32(&(host_pvt.sata_dma_regs->dma_chan_en.low))); + return -1; +} + +/* + * Function: dma_dwc_interrupt + * arguments: irq, dev_id, pt_regs + * returns channel number if available else -1 + * Interrupt Handler for DW AHB SATA DMA + */ +static irqreturn_t dma_dwc_interrupt(int irq, void *hsdev_instance) +{ + int chan; + u32 tfr_reg, err_reg; + unsigned long flags; + struct sata_dwc_device *hsdev = + (struct sata_dwc_device *)hsdev_instance; + struct ata_host *host = (struct ata_host *)hsdev->host; + struct ata_port *ap; + struct sata_dwc_device_port *hsdevp; + u8 tag = 0; + unsigned int port = 0; + + spin_lock_irqsave(&host->lock, flags); + ap = host->ports[port]; + hsdevp = HSDEVP_FROM_AP(ap); + tag = ap->link.active_tag; + + tfr_reg = in_le32(&(host_pvt.sata_dma_regs->interrupt_status.tfr\ + .low)); + err_reg = in_le32(&(host_pvt.sata_dma_regs->interrupt_status.error\ + .low)); + + dev_dbg(ap->dev, "eot=0x%08x err=0x%08x pending=%d active port=%d\n", + tfr_reg, err_reg, hsdevp->dma_pending[tag], port); + + for (chan = 0; chan < DMA_NUM_CHANS; chan++) { + /* Check for end-of-transfer interrupt. */ + if (tfr_reg & DMA_CHANNEL(chan)) { + /* + * Each DMA command produces 2 interrupts. Only + * complete the command after both interrupts have been + * seen. (See sata_dwc_isr()) + */ + host_pvt.dma_interrupt_count++; + sata_dwc_clear_dmacr(hsdevp, tag); + + if (hsdevp->dma_pending[tag] == + SATA_DWC_DMA_PENDING_NONE) { + dev_err(ap->dev, "DMA not pending eot=0x%08x " + "err=0x%08x tag=0x%02x pending=%d\n", + tfr_reg, err_reg, tag, + hsdevp->dma_pending[tag]); + } + + if ((host_pvt.dma_interrupt_count % 2) == 0) + sata_dwc_dma_xfer_complete(ap, 1); + + /* Clear the interrupt */ + out_le32(&(host_pvt.sata_dma_regs->interrupt_clear\ + .tfr.low), + DMA_CHANNEL(chan)); + } + + /* Check for error interrupt. */ + if (err_reg & DMA_CHANNEL(chan)) { + /* TODO Need error handler ! */ + dev_err(ap->dev, "error interrupt err_reg=0x%08x\n", + err_reg); + + /* Clear the interrupt. */ + out_le32(&(host_pvt.sata_dma_regs->interrupt_clear\ + .error.low), + DMA_CHANNEL(chan)); + } + } + spin_unlock_irqrestore(&host->lock, flags); + return IRQ_HANDLED; +} + +/* + * Function: dma_request_interrupts + * arguments: hsdev + * returns status + * This function registers ISR for a particular DMA channel interrupt + */ +static int dma_request_interrupts(struct sata_dwc_device *hsdev, int irq) +{ + int retval = 0; + int chan; + + for (chan = 0; chan < DMA_NUM_CHANS; chan++) { + /* Unmask error interrupt */ + out_le32(&(host_pvt.sata_dma_regs)->interrupt_mask.error.low, + DMA_ENABLE_CHAN(chan)); + + /* Unmask end-of-transfer interrupt */ + out_le32(&(host_pvt.sata_dma_regs)->interrupt_mask.tfr.low, + DMA_ENABLE_CHAN(chan)); + } + + retval = request_irq(irq, dma_dwc_interrupt, 0, "SATA DMA", hsdev); + if (retval) { + dev_err(host_pvt.dwc_dev, "%s: could not get IRQ %d\n", + __func__, irq); + return -ENODEV; + } + + /* Mark this interrupt as requested */ + hsdev->irq_dma = irq; + return 0; +} + +/* + * Function: map_sg_to_lli + * The Synopsis driver has a comment proposing that better performance + * is possible by only enabling interrupts on the last item in the linked list. + * However, it seems that could be a problem if an error happened on one of the + * first items. The transfer would halt, but no error interrupt would occur. + * Currently this function sets interrupts enabled for each linked list item: + * DMA_CTL_INT_EN. + */ +static int map_sg_to_lli(struct scatterlist *sg, int num_elems, + struct lli *lli, dma_addr_t dma_lli, + void __iomem *dmadr_addr, int dir) +{ + int i, idx = 0; + int fis_len = 0; + dma_addr_t next_llp; + int bl; + + dev_dbg(host_pvt.dwc_dev, "%s: sg=%p nelem=%d lli=%p dma_lli=0x%08x" + " dmadr=0x%08x\n", __func__, sg, num_elems, lli, (u32)dma_lli, + (u32)dmadr_addr); + + bl = get_burst_length_encode(AHB_DMA_BRST_DFLT); + + for (i = 0; i < num_elems; i++, sg++) { + u32 addr, offset; + u32 sg_len, len; + + addr = (u32) sg_dma_address(sg); + sg_len = sg_dma_len(sg); + + dev_dbg(host_pvt.dwc_dev, "%s: elem=%d sg_addr=0x%x sg_len" + "=%d\n", __func__, i, addr, sg_len); + + while (sg_len) { + if (idx >= SATA_DWC_DMAC_LLI_NUM) { + /* The LLI table is not large enough. */ + dev_err(host_pvt.dwc_dev, "LLI table overrun " + "(idx=%d)\n", idx); + break; + } + len = (sg_len > SATA_DWC_DMAC_CTRL_TSIZE_MAX) ? + SATA_DWC_DMAC_CTRL_TSIZE_MAX : sg_len; + + offset = addr & 0xffff; + if ((offset + sg_len) > 0x10000) + len = 0x10000 - offset; + + /* + * Make sure a LLI block is not created that will span + * 8K max FIS boundary. If the block spans such a FIS + * boundary, there is a chance that a DMA burst will + * cross that boundary -- this results in an error in + * the host controller. + */ + if (fis_len + len > 8192) { + dev_dbg(host_pvt.dwc_dev, "SPLITTING: fis_len=" + "%d(0x%x) len=%d(0x%x)\n", fis_len, + fis_len, len, len); + len = 8192 - fis_len; + fis_len = 0; + } else { + fis_len += len; + } + if (fis_len == 8192) + fis_len = 0; + + /* + * Set DMA addresses and lower half of control register + * based on direction. + */ + if (dir == DMA_FROM_DEVICE) { + lli[idx].dar = cpu_to_le32(addr); + lli[idx].sar = cpu_to_le32((u32)dmadr_addr); + + lli[idx].ctl.low = cpu_to_le32( + DMA_CTL_TTFC(DMA_CTL_TTFC_P2M_DMAC) | + DMA_CTL_SMS(0) | + DMA_CTL_DMS(1) | + DMA_CTL_SRC_MSIZE(bl) | + DMA_CTL_DST_MSIZE(bl) | + DMA_CTL_SINC_NOCHANGE | + DMA_CTL_SRC_TRWID(2) | + DMA_CTL_DST_TRWID(2) | + DMA_CTL_INT_EN | + DMA_CTL_LLP_SRCEN | + DMA_CTL_LLP_DSTEN); + } else { /* DMA_TO_DEVICE */ + lli[idx].sar = cpu_to_le32(addr); + lli[idx].dar = cpu_to_le32((u32)dmadr_addr); + + lli[idx].ctl.low = cpu_to_le32( + DMA_CTL_TTFC(DMA_CTL_TTFC_M2P_PER) | + DMA_CTL_SMS(1) | + DMA_CTL_DMS(0) | + DMA_CTL_SRC_MSIZE(bl) | + DMA_CTL_DST_MSIZE(bl) | + DMA_CTL_DINC_NOCHANGE | + DMA_CTL_SRC_TRWID(2) | + DMA_CTL_DST_TRWID(2) | + DMA_CTL_INT_EN | + DMA_CTL_LLP_SRCEN | + DMA_CTL_LLP_DSTEN); + } + + dev_dbg(host_pvt.dwc_dev, "%s setting ctl.high len: " + "0x%08x val: 0x%08x\n", __func__, + len, DMA_CTL_BLK_TS(len / 4)); + + /* Program the LLI CTL high register */ + lli[idx].ctl.high = cpu_to_le32(DMA_CTL_BLK_TS\ + (len / 4)); + + /* Program the next pointer. The next pointer must be + * the physical address, not the virtual address. + */ + next_llp = (dma_lli + ((idx + 1) * sizeof(struct \ + lli))); + + /* The last 2 bits encode the list master select. */ + next_llp = DMA_LLP_LMS(next_llp, DMA_LLP_AHBMASTER2); + + lli[idx].llp = cpu_to_le32(next_llp); + idx++; + sg_len -= len; + addr += len; + } + } + + /* + * The last next ptr has to be zero and the last control low register + * has to have LLP_SRC_EN and LLP_DST_EN (linked list pointer source + * and destination enable) set back to 0 (disabled.) This is what tells + * the core that this is the last item in the linked list. + */ + if (idx) { + lli[idx-1].llp = 0x00000000; + lli[idx-1].ctl.low &= DMA_CTL_LLP_DISABLE_LE32; + + /* Flush cache to memory */ + dma_cache_sync(NULL, lli, (sizeof(struct lli) * idx), + DMA_BIDIRECTIONAL); + } + + return idx; +} + +/* + * Function: dma_dwc_xfer_start + * arguments: Channel number + * Return : None + * Enables the DMA channel + */ +static void dma_dwc_xfer_start(int dma_ch) +{ + /* Enable the DMA channel */ + out_le32(&(host_pvt.sata_dma_regs->dma_chan_en.low), + in_le32(&(host_pvt.sata_dma_regs->dma_chan_en.low)) | + DMA_ENABLE_CHAN(dma_ch)); +} + +static int dma_dwc_xfer_setup(struct scatterlist *sg, int num_elems, + struct lli *lli, dma_addr_t dma_lli, + void __iomem *addr, int dir) +{ + int dma_ch; + int num_lli; + /* Acquire DMA channel */ + dma_ch = dma_request_channel(); + if (dma_ch == -1) { + dev_err(host_pvt.dwc_dev, "%s: dma channel unavailable\n", + __func__); + return -EAGAIN; + } + + /* Convert SG list to linked list of items (LLIs) for AHB DMA */ + num_lli = map_sg_to_lli(sg, num_elems, lli, dma_lli, addr, dir); + + dev_dbg(host_pvt.dwc_dev, "%s sg: 0x%p, count: %d lli: %p dma_lli:" + " 0x%0xlx addr: %p lli count: %d\n", __func__, sg, num_elems, + lli, (u32)dma_lli, addr, num_lli); + + clear_chan_interrupts(dma_ch); + + /* Program the CFG register. */ + out_le32(&(host_pvt.sata_dma_regs->chan_regs[dma_ch].cfg.high), + DMA_CFG_PROTCTL | DMA_CFG_FCMOD_REQ); + out_le32(&(host_pvt.sata_dma_regs->chan_regs[dma_ch].cfg.low), 0); + + /* Program the address of the linked list */ + out_le32(&(host_pvt.sata_dma_regs->chan_regs[dma_ch].llp.low), + DMA_LLP_LMS(dma_lli, DMA_LLP_AHBMASTER2)); + + /* Program the CTL register with src enable / dst enable */ + out_le32(&(host_pvt.sata_dma_regs->chan_regs[dma_ch].ctl.low), + DMA_CTL_LLP_SRCEN | DMA_CTL_LLP_DSTEN); + return 0; +} + +/* + * Function: dma_dwc_exit + * arguments: None + * returns status + * This function exits the SATA DMA driver + */ +static void dma_dwc_exit(struct sata_dwc_device *hsdev) +{ + dev_dbg(host_pvt.dwc_dev, "%s:\n", __func__); + if (host_pvt.sata_dma_regs) + iounmap(host_pvt.sata_dma_regs); + + if (hsdev->irq_dma) + free_irq(hsdev->irq_dma, hsdev); +} + +/* + * Function: dma_dwc_init + * arguments: hsdev + * returns status + * This function initializes the SATA DMA driver + */ +static int dma_dwc_init(struct sata_dwc_device *hsdev, int irq) +{ + int err; + + err = dma_request_interrupts(hsdev, irq); + if (err) { + dev_err(host_pvt.dwc_dev, "%s: dma_request_interrupts returns" + " %d\n", __func__, err); + goto error_out; + } + + /* Enabe DMA */ + out_le32(&(host_pvt.sata_dma_regs->dma_cfg.low), DMA_EN); + + dev_notice(host_pvt.dwc_dev, "DMA initialized\n"); + dev_dbg(host_pvt.dwc_dev, "SATA DMA registers=0x%p\n", host_pvt.\ + sata_dma_regs); + + return 0; + +error_out: + dma_dwc_exit(hsdev); + + return err; +} + +static int sata_dwc_scr_read(struct ata_link *link, unsigned int scr, u32 *val) +{ + if (scr > SCR_NOTIFICATION) { + dev_err(link->ap->dev, "%s: Incorrect SCR offset 0x%02x\n", + __func__, scr); + return -EINVAL; + } + + *val = in_le32((void *)link->ap->ioaddr.scr_addr + (scr * 4)); + dev_dbg(link->ap->dev, "%s: id=%d reg=%d val=val=0x%08x\n", + __func__, link->ap->print_id, scr, *val); + + return 0; +} + +static int sata_dwc_scr_write(struct ata_link *link, unsigned int scr, u32 val) +{ + dev_dbg(link->ap->dev, "%s: id=%d reg=%d val=val=0x%08x\n", + __func__, link->ap->print_id, scr, val); + if (scr > SCR_NOTIFICATION) { + dev_err(link->ap->dev, "%s: Incorrect SCR offset 0x%02x\n", + __func__, scr); + return -EINVAL; + } + out_le32((void *)link->ap->ioaddr.scr_addr + (scr * 4), val); + + return 0; +} + +static u32 core_scr_read(unsigned int scr) +{ + return in_le32((void __iomem *)(host_pvt.scr_addr_sstatus) +\ + (scr * 4)); +} + +static void core_scr_write(unsigned int scr, u32 val) +{ + out_le32((void __iomem *)(host_pvt.scr_addr_sstatus) + (scr * 4), + val); +} + +static void clear_serror(void) +{ + u32 val; + val = core_scr_read(SCR_ERROR); + core_scr_write(SCR_ERROR, val); + +} + +static void clear_interrupt_bit(struct sata_dwc_device *hsdev, u32 bit) +{ + out_le32(&hsdev->sata_dwc_regs->intpr, + in_le32(&hsdev->sata_dwc_regs->intpr)); +} + +static u32 qcmd_tag_to_mask(u8 tag) +{ + return 0x00000001 << (tag & 0x1f); +} + +/* See ahci.c */ +static void sata_dwc_error_intr(struct ata_port *ap, + struct sata_dwc_device *hsdev, uint intpr) +{ + struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); + struct ata_eh_info *ehi = &ap->link.eh_info; + unsigned int err_mask = 0, action = 0; + struct ata_queued_cmd *qc; + u32 serror; + u8 status, tag; + u32 err_reg; + + ata_ehi_clear_desc(ehi); + + serror = core_scr_read(SCR_ERROR); + status = ap->ops->sff_check_status(ap); + + err_reg = in_le32(&(host_pvt.sata_dma_regs->interrupt_status.error.\ + low)); + tag = ap->link.active_tag; + + dev_err(ap->dev, "%s SCR_ERROR=0x%08x intpr=0x%08x status=0x%08x " + "dma_intp=%d pending=%d issued=%d dma_err_status=0x%08x\n", + __func__, serror, intpr, status, host_pvt.dma_interrupt_count, + hsdevp->dma_pending[tag], hsdevp->cmd_issued[tag], err_reg); + + /* Clear error register and interrupt bit */ + clear_serror(); + clear_interrupt_bit(hsdev, SATA_DWC_INTPR_ERR); + + /* This is the only error happening now. TODO check for exact error */ + + err_mask |= AC_ERR_HOST_BUS; + action |= ATA_EH_RESET; + + /* Pass this on to EH */ + ehi->serror |= serror; + ehi->action |= action; + + qc = ata_qc_from_tag(ap, tag); + if (qc) + qc->err_mask |= err_mask; + else + ehi->err_mask |= err_mask; + + ata_port_abort(ap); +} + +/* + * Function : sata_dwc_isr + * arguments : irq, void *dev_instance, struct pt_regs *regs + * Return value : irqreturn_t - status of IRQ + * This Interrupt handler called via port ops registered function. + * .irq_handler = sata_dwc_isr + */ +static irqreturn_t sata_dwc_isr(int irq, void *dev_instance) +{ + struct ata_host *host = (struct ata_host *)dev_instance; + struct sata_dwc_device *hsdev = HSDEV_FROM_HOST(host); + struct ata_port *ap; + struct ata_queued_cmd *qc; + unsigned long flags; + u8 status, tag; + int handled, num_processed, port = 0; + uint intpr, sactive, sactive2, tag_mask; + struct sata_dwc_device_port *hsdevp; + host_pvt.sata_dwc_sactive_issued = 0; + + spin_lock_irqsave(&host->lock, flags); + + /* Read the interrupt register */ + intpr = in_le32(&hsdev->sata_dwc_regs->intpr); + + ap = host->ports[port]; + hsdevp = HSDEVP_FROM_AP(ap); + + dev_dbg(ap->dev, "%s intpr=0x%08x active_tag=%d\n", __func__, intpr, + ap->link.active_tag); + + /* Check for error interrupt */ + if (intpr & SATA_DWC_INTPR_ERR) { + sata_dwc_error_intr(ap, hsdev, intpr); + handled = 1; + goto DONE; + } + + /* Check for DMA SETUP FIS (FP DMA) interrupt */ + if (intpr & SATA_DWC_INTPR_NEWFP) { + clear_interrupt_bit(hsdev, SATA_DWC_INTPR_NEWFP); + + tag = (u8)(in_le32(&hsdev->sata_dwc_regs->fptagr)); + dev_dbg(ap->dev, "%s: NEWFP tag=%d\n", __func__, tag); + if (hsdevp->cmd_issued[tag] != SATA_DWC_CMD_ISSUED_PEND) + dev_warn(ap->dev, "CMD tag=%d not pending?\n", tag); + + host_pvt.sata_dwc_sactive_issued |= qcmd_tag_to_mask(tag); + + qc = ata_qc_from_tag(ap, tag); + /* + * Start FP DMA for NCQ command. At this point the tag is the + * active tag. It is the tag that matches the command about to + * be completed. + */ + qc->ap->link.active_tag = tag; + sata_dwc_bmdma_start_by_tag(qc, tag); + + handled = 1; + goto DONE; + } + sactive = core_scr_read(SCR_ACTIVE); + tag_mask = (host_pvt.sata_dwc_sactive_issued | sactive) ^ sactive; + + /* If no sactive issued and tag_mask is zero then this is not NCQ */ + if (host_pvt.sata_dwc_sactive_issued == 0 && tag_mask == 0) { + if (ap->link.active_tag == ATA_TAG_POISON) + tag = 0; + else + tag = ap->link.active_tag; + qc = ata_qc_from_tag(ap, tag); + + /* DEV interrupt w/ no active qc? */ + if (unlikely(!qc || (qc->tf.flags & ATA_TFLAG_POLLING))) { + dev_err(ap->dev, "%s interrupt with no active qc " + "qc=%p\n", __func__, qc); + ap->ops->sff_check_status(ap); + handled = 1; + goto DONE; + } + status = ap->ops->sff_check_status(ap); + + qc->ap->link.active_tag = tag; + hsdevp->cmd_issued[tag] = SATA_DWC_CMD_ISSUED_NOT; + + if (status & ATA_ERR) { + dev_dbg(ap->dev, "interrupt ATA_ERR (0x%x)\n", status); + sata_dwc_qc_complete(ap, qc, 1); + handled = 1; + goto DONE; + } + + dev_dbg(ap->dev, "%s non-NCQ cmd interrupt, protocol: %s\n", + __func__, ata_get_cmd_descript(qc->tf.protocol)); +DRVSTILLBUSY: + if (ata_is_dma(qc->tf.protocol)) { + /* + * Each DMA transaction produces 2 interrupts. The DMAC + * transfer complete interrupt and the SATA controller + * operation done interrupt. The command should be + * completed only after both interrupts are seen. + */ + host_pvt.dma_interrupt_count++; + if (hsdevp->dma_pending[tag] == \ + SATA_DWC_DMA_PENDING_NONE) { + dev_err(ap->dev, "%s: DMA not pending " + "intpr=0x%08x status=0x%08x pending" + "=%d\n", __func__, intpr, status, + hsdevp->dma_pending[tag]); + } + + if ((host_pvt.dma_interrupt_count % 2) == 0) + sata_dwc_dma_xfer_complete(ap, 1); + } else if (ata_is_pio(qc->tf.protocol)) { + ata_sff_hsm_move(ap, qc, status, 0); + handled = 1; + goto DONE; + } else { + if (unlikely(sata_dwc_qc_complete(ap, qc, 1))) + goto DRVSTILLBUSY; + } + + handled = 1; + goto DONE; + } + + /* + * This is a NCQ command. At this point we need to figure out for which + * tags we have gotten a completion interrupt. One interrupt may serve + * as completion for more than one operation when commands are queued + * (NCQ). We need to process each completed command. + */ + + /* process completed commands */ + sactive = core_scr_read(SCR_ACTIVE); + tag_mask = (host_pvt.sata_dwc_sactive_issued | sactive) ^ sactive; + + if (sactive != 0 || (host_pvt.sata_dwc_sactive_issued) > 1 || \ + tag_mask > 1) { + dev_dbg(ap->dev, "%s NCQ:sactive=0x%08x sactive_issued=0x%08x" + "tag_mask=0x%08x\n", __func__, sactive, + host_pvt.sata_dwc_sactive_issued, tag_mask); + } + + if ((tag_mask | (host_pvt.sata_dwc_sactive_issued)) != \ + (host_pvt.sata_dwc_sactive_issued)) { + dev_warn(ap->dev, "Bad tag mask? sactive=0x%08x " + "(host_pvt.sata_dwc_sactive_issued)=0x%08x tag_mask" + "=0x%08x\n", sactive, host_pvt.sata_dwc_sactive_issued, + tag_mask); + } + + /* read just to clear ... not bad if currently still busy */ + status = ap->ops->sff_check_status(ap); + dev_dbg(ap->dev, "%s ATA status register=0x%x\n", __func__, status); + + tag = 0; + num_processed = 0; + while (tag_mask) { + num_processed++; + while (!(tag_mask & 0x00000001)) { + tag++; + tag_mask <<= 1; + } + + tag_mask &= (~0x00000001); + qc = ata_qc_from_tag(ap, tag); + + /* To be picked up by completion functions */ + qc->ap->link.active_tag = tag; + hsdevp->cmd_issued[tag] = SATA_DWC_CMD_ISSUED_NOT; + + /* Let libata/scsi layers handle error */ + if (status & ATA_ERR) { + dev_dbg(ap->dev, "%s ATA_ERR (0x%x)\n", __func__, + status); + sata_dwc_qc_complete(ap, qc, 1); + handled = 1; + goto DONE; + } + + /* Process completed command */ + dev_dbg(ap->dev, "%s NCQ command, protocol: %s\n", __func__, + ata_get_cmd_descript(qc->tf.protocol)); + if (ata_is_dma(qc->tf.protocol)) { + host_pvt.dma_interrupt_count++; + if (hsdevp->dma_pending[tag] == \ + SATA_DWC_DMA_PENDING_NONE) + dev_warn(ap->dev, "%s: DMA not pending?\n", + __func__); + if ((host_pvt.dma_interrupt_count % 2) == 0) + sata_dwc_dma_xfer_complete(ap, 1); + } else { + if (unlikely(sata_dwc_qc_complete(ap, qc, 1))) + goto STILLBUSY; + } + continue; + +STILLBUSY: + ap->stats.idle_irq++; + dev_warn(ap->dev, "STILL BUSY IRQ ata%d: irq trap\n", + ap->print_id); + } /* while tag_mask */ + + /* + * Check to see if any commands completed while we were processing our + * initial set of completed commands (read status clears interrupts, + * so we might miss a completed command interrupt if one came in while + * we were processing --we read status as part of processing a completed + * command). + */ + sactive2 = core_scr_read(SCR_ACTIVE); + if (sactive2 != sactive) { + dev_dbg(ap->dev, "More completed - sactive=0x%x sactive2" + "=0x%x\n", sactive, sactive2); + } + handled = 1; + +DONE: + spin_unlock_irqrestore(&host->lock, flags); + return IRQ_RETVAL(handled); +} + +static void sata_dwc_clear_dmacr(struct sata_dwc_device_port *hsdevp, u8 tag) +{ + struct sata_dwc_device *hsdev = HSDEV_FROM_HSDEVP(hsdevp); + + if (hsdevp->dma_pending[tag] == SATA_DWC_DMA_PENDING_RX) { + out_le32(&(hsdev->sata_dwc_regs->dmacr), + SATA_DWC_DMACR_RX_CLEAR( + in_le32(&(hsdev->sata_dwc_regs->dmacr)))); + } else if (hsdevp->dma_pending[tag] == SATA_DWC_DMA_PENDING_TX) { + out_le32(&(hsdev->sata_dwc_regs->dmacr), + SATA_DWC_DMACR_TX_CLEAR( + in_le32(&(hsdev->sata_dwc_regs->dmacr)))); + } else { + /* + * This should not happen, it indicates the driver is out of + * sync. If it does happen, clear dmacr anyway. + */ + dev_err(host_pvt.dwc_dev, "%s DMA protocol RX and" + "TX DMA not pending tag=0x%02x pending=%d" + " dmacr: 0x%08x\n", __func__, tag, + hsdevp->dma_pending[tag], + in_le32(&(hsdev->sata_dwc_regs->dmacr))); + out_le32(&(hsdev->sata_dwc_regs->dmacr), + SATA_DWC_DMACR_TXRXCH_CLEAR); + } +} + +static void sata_dwc_dma_xfer_complete(struct ata_port *ap, u32 check_status) +{ + struct ata_queued_cmd *qc; + struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); + struct sata_dwc_device *hsdev = HSDEV_FROM_AP(ap); + u8 tag = 0; + + tag = ap->link.active_tag; + qc = ata_qc_from_tag(ap, tag); + if (!qc) { + dev_err(ap->dev, "failed to get qc"); + return; + } + +#ifdef DEBUG_NCQ + if (tag > 0) { + dev_info(ap->dev, "%s tag=%u cmd=0x%02x dma dir=%s proto=%s " + "dmacr=0x%08x\n", __func__, qc->tag, qc->tf.command, + ata_get_cmd_descript(qc->dma_dir), + ata_get_cmd_descript(qc->tf.protocol), + in_le32(&(hsdev->sata_dwc_regs->dmacr))); + } +#endif + + if (ata_is_dma(qc->tf.protocol)) { + if (hsdevp->dma_pending[tag] == SATA_DWC_DMA_PENDING_NONE) { + dev_err(ap->dev, "%s DMA protocol RX and TX DMA not " + "pending dmacr: 0x%08x\n", __func__, + in_le32(&(hsdev->sata_dwc_regs->dmacr))); + } + + hsdevp->dma_pending[tag] = SATA_DWC_DMA_PENDING_NONE; + sata_dwc_qc_complete(ap, qc, check_status); + ap->link.active_tag = ATA_TAG_POISON; + } else { + sata_dwc_qc_complete(ap, qc, check_status); + } +} + +static int sata_dwc_qc_complete(struct ata_port *ap, struct ata_queued_cmd *qc, + u32 check_status) +{ + u8 status = 0; + u32 mask = 0x0; + u8 tag = qc->tag; + struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); + host_pvt.sata_dwc_sactive_queued = 0; + dev_dbg(ap->dev, "%s checkstatus? %x\n", __func__, check_status); + + if (hsdevp->dma_pending[tag] == SATA_DWC_DMA_PENDING_TX) + dev_err(ap->dev, "TX DMA PENDING\n"); + else if (hsdevp->dma_pending[tag] == SATA_DWC_DMA_PENDING_RX) + dev_err(ap->dev, "RX DMA PENDING\n"); + dev_dbg(ap->dev, "QC complete cmd=0x%02x status=0x%02x ata%u:" + " protocol=%d\n", qc->tf.command, status, ap->print_id, + qc->tf.protocol); + + /* clear active bit */ + mask = (~(qcmd_tag_to_mask(tag))); + host_pvt.sata_dwc_sactive_queued = (host_pvt.sata_dwc_sactive_queued) \ + & mask; + host_pvt.sata_dwc_sactive_issued = (host_pvt.sata_dwc_sactive_issued) \ + & mask; + ata_qc_complete(qc); + return 0; +} + +static void sata_dwc_enable_interrupts(struct sata_dwc_device *hsdev) +{ + /* Enable selective interrupts by setting the interrupt maskregister*/ + out_le32(&hsdev->sata_dwc_regs->intmr, + SATA_DWC_INTMR_ERRM | + SATA_DWC_INTMR_NEWFPM | + SATA_DWC_INTMR_PMABRTM | + SATA_DWC_INTMR_DMATM); + /* + * Unmask the error bits that should trigger an error interrupt by + * setting the error mask register. + */ + out_le32(&hsdev->sata_dwc_regs->errmr, SATA_DWC_SERROR_ERR_BITS); + + dev_dbg(host_pvt.dwc_dev, "%s: INTMR = 0x%08x, ERRMR = 0x%08x\n", + __func__, in_le32(&hsdev->sata_dwc_regs->intmr), + in_le32(&hsdev->sata_dwc_regs->errmr)); +} + +static void sata_dwc_setup_port(struct ata_ioports *port, unsigned long base) +{ + port->cmd_addr = (void *)base + 0x00; + port->data_addr = (void *)base + 0x00; + + port->error_addr = (void *)base + 0x04; + port->feature_addr = (void *)base + 0x04; + + port->nsect_addr = (void *)base + 0x08; + + port->lbal_addr = (void *)base + 0x0c; + port->lbam_addr = (void *)base + 0x10; + port->lbah_addr = (void *)base + 0x14; + + port->device_addr = (void *)base + 0x18; + port->command_addr = (void *)base + 0x1c; + port->status_addr = (void *)base + 0x1c; + + port->altstatus_addr = (void *)base + 0x20; + port->ctl_addr = (void *)base + 0x20; +} + +/* + * Function : sata_dwc_port_start + * arguments : struct ata_ioports *port + * Return value : returns 0 if success, error code otherwise + * This function allocates the scatter gather LLI table for AHB DMA + */ +static int sata_dwc_port_start(struct ata_port *ap) +{ + int err = 0; + struct sata_dwc_device *hsdev; + struct sata_dwc_device_port *hsdevp = NULL; + struct device *pdev; + int i; + + hsdev = HSDEV_FROM_AP(ap); + + dev_dbg(ap->dev, "%s: port_no=%d\n", __func__, ap->port_no); + + hsdev->host = ap->host; + pdev = ap->host->dev; + if (!pdev) { + dev_err(ap->dev, "%s: no ap->host->dev\n", __func__); + err = -ENODEV; + goto CLEANUP; + } + + /* Allocate Port Struct */ + hsdevp = kzalloc(sizeof(*hsdevp), GFP_KERNEL); + if (!hsdevp) { + dev_err(ap->dev, "%s: kmalloc failed for hsdevp\n", __func__); + err = -ENOMEM; + goto CLEANUP; + } + hsdevp->hsdev = hsdev; + + for (i = 0; i < SATA_DWC_QCMD_MAX; i++) + hsdevp->cmd_issued[i] = SATA_DWC_CMD_ISSUED_NOT; + + ap->bmdma_prd = 0; /* set these so libata doesn't use them */ + ap->bmdma_prd_dma = 0; + + /* + * DMA - Assign scatter gather LLI table. We can't use the libata + * version since it's PRD is IDE PCI specific. + */ + for (i = 0; i < SATA_DWC_QCMD_MAX; i++) { + hsdevp->llit[i] = dma_alloc_coherent(pdev, + SATA_DWC_DMAC_LLI_TBL_SZ, + &(hsdevp->llit_dma[i]), + GFP_ATOMIC); + if (!hsdevp->llit[i]) { + dev_err(ap->dev, "%s: dma_alloc_coherent failed\n", + __func__); + err = -ENOMEM; + goto CLEANUP; + } + } + + if (ap->port_no == 0) { + dev_dbg(ap->dev, "%s: clearing TXCHEN, RXCHEN in DMAC\n", + __func__); + out_le32(&hsdev->sata_dwc_regs->dmacr, + SATA_DWC_DMACR_TXRXCH_CLEAR); + + dev_dbg(ap->dev, "%s: setting burst size in DBTSR\n", + __func__); + out_le32(&hsdev->sata_dwc_regs->dbtsr, + (SATA_DWC_DBTSR_MWR(AHB_DMA_BRST_DFLT) | + SATA_DWC_DBTSR_MRD(AHB_DMA_BRST_DFLT))); + } + + /* Clear any error bits before libata starts issuing commands */ + clear_serror(); + ap->private_data = hsdevp; + +CLEANUP: + if (err) { + sata_dwc_port_stop(ap); + dev_dbg(ap->dev, "%s: fail\n", __func__); + } else { + dev_dbg(ap->dev, "%s: done\n", __func__); + } + + return err; +} + +static void sata_dwc_port_stop(struct ata_port *ap) +{ + int i; + struct sata_dwc_device *hsdev = HSDEV_FROM_AP(ap); + struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); + + dev_dbg(ap->dev, "%s: ap->id = %d\n", __func__, ap->print_id); + + if (hsdevp && hsdev) { + /* deallocate LLI table */ + for (i = 0; i < SATA_DWC_QCMD_MAX; i++) { + dma_free_coherent(ap->host->dev, + SATA_DWC_DMAC_LLI_TBL_SZ, + hsdevp->llit[i], hsdevp->llit_dma[i]); + } + + kfree(hsdevp); + } + ap->private_data = NULL; +} + +/* + * Function : sata_dwc_exec_command_by_tag + * arguments : ata_port *ap, ata_taskfile *tf, u8 tag, u32 cmd_issued + * Return value : None + * This function keeps track of individual command tag ids and calls + * ata_exec_command in libata + */ +static void sata_dwc_exec_command_by_tag(struct ata_port *ap, + struct ata_taskfile *tf, + u8 tag, u32 cmd_issued) +{ + unsigned long flags; + struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); + + dev_dbg(ap->dev, "%s cmd(0x%02x): %s tag=%d\n", __func__, tf->command, + ata_get_cmd_descript(tf), tag); + + spin_lock_irqsave(&ap->host->lock, flags); + hsdevp->cmd_issued[tag] = cmd_issued; + spin_unlock_irqrestore(&ap->host->lock, flags); + /* + * Clear SError before executing a new command. + * sata_dwc_scr_write and read can not be used here. Clearing the PM + * managed SError register for the disk needs to be done before the + * task file is loaded. + */ + clear_serror(); + ata_sff_exec_command(ap, tf); +} + +static void sata_dwc_bmdma_setup_by_tag(struct ata_queued_cmd *qc, u8 tag) +{ + sata_dwc_exec_command_by_tag(qc->ap, &qc->tf, tag, + SATA_DWC_CMD_ISSUED_PEND); +} + +static void sata_dwc_bmdma_setup(struct ata_queued_cmd *qc) +{ + u8 tag = qc->tag; + + if (ata_is_ncq(qc->tf.protocol)) { + dev_dbg(qc->ap->dev, "%s: ap->link.sactive=0x%08x tag=%d\n", + __func__, qc->ap->link.sactive, tag); + } else { + tag = 0; + } + sata_dwc_bmdma_setup_by_tag(qc, tag); +} + +static void sata_dwc_bmdma_start_by_tag(struct ata_queued_cmd *qc, u8 tag) +{ + int start_dma; + u32 reg, dma_chan; + struct sata_dwc_device *hsdev = HSDEV_FROM_QC(qc); + struct ata_port *ap = qc->ap; + struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); + int dir = qc->dma_dir; + dma_chan = hsdevp->dma_chan[tag]; + + if (hsdevp->cmd_issued[tag] != SATA_DWC_CMD_ISSUED_NOT) { + start_dma = 1; + if (dir == DMA_TO_DEVICE) + hsdevp->dma_pending[tag] = SATA_DWC_DMA_PENDING_TX; + else + hsdevp->dma_pending[tag] = SATA_DWC_DMA_PENDING_RX; + } else { + dev_err(ap->dev, "%s: Command not pending cmd_issued=%d " + "(tag=%d) DMA NOT started\n", __func__, + hsdevp->cmd_issued[tag], tag); + start_dma = 0; + } + + dev_dbg(ap->dev, "%s qc=%p tag: %x cmd: 0x%02x dma_dir: %s " + "start_dma? %x\n", __func__, qc, tag, qc->tf.command, + ata_get_cmd_descript(qc->dma_dir), start_dma); + sata_dwc_tf_dump(&(qc->tf)); + + if (start_dma) { + reg = core_scr_read(SCR_ERROR); + if (reg & SATA_DWC_SERROR_ERR_BITS) { + dev_err(ap->dev, "%s: ****** SError=0x%08x ******\n", + __func__, reg); + } + + if (dir == DMA_TO_DEVICE) + out_le32(&hsdev->sata_dwc_regs->dmacr, + SATA_DWC_DMACR_TXCHEN); + else + out_le32(&hsdev->sata_dwc_regs->dmacr, + SATA_DWC_DMACR_RXCHEN); + + /* Enable AHB DMA transfer on the specified channel */ + dma_dwc_xfer_start(dma_chan); + } +} + +static void sata_dwc_bmdma_start(struct ata_queued_cmd *qc) +{ + u8 tag = qc->tag; + + if (ata_is_ncq(qc->tf.protocol)) { + dev_dbg(qc->ap->dev, "%s: ap->link.sactive=0x%08x tag=%d\n", + __func__, qc->ap->link.sactive, tag); + } else { + tag = 0; + } + dev_dbg(qc->ap->dev, "%s\n", __func__); + sata_dwc_bmdma_start_by_tag(qc, tag); +} + +/* + * Function : sata_dwc_qc_prep_by_tag + * arguments : ata_queued_cmd *qc, u8 tag + * Return value : None + * qc_prep for a particular queued command based on tag + */ +static void sata_dwc_qc_prep_by_tag(struct ata_queued_cmd *qc, u8 tag) +{ + struct scatterlist *sg = qc->sg; + struct ata_port *ap = qc->ap; + u32 dma_chan; + struct sata_dwc_device *hsdev = HSDEV_FROM_AP(ap); + struct sata_dwc_device_port *hsdevp = HSDEVP_FROM_AP(ap); + int err; + + dev_dbg(ap->dev, "%s: port=%d dma dir=%s n_elem=%d\n", + __func__, ap->port_no, ata_get_cmd_descript(qc->dma_dir), + qc->n_elem); + + dma_chan = dma_dwc_xfer_setup(sg, qc->n_elem, hsdevp->llit[tag], + hsdevp->llit_dma[tag], + (void *__iomem)(&hsdev->sata_dwc_regs->\ + dmadr), qc->dma_dir); + if (dma_chan < 0) { + dev_err(ap->dev, "%s: dma_dwc_xfer_setup returns err %d\n", + __func__, err); + return; + } + hsdevp->dma_chan[tag] = dma_chan; +} + +static unsigned int sata_dwc_qc_issue(struct ata_queued_cmd *qc) +{ + u32 sactive; + u8 tag = qc->tag; + struct ata_port *ap = qc->ap; + +#ifdef DEBUG_NCQ + if (qc->tag > 0 || ap->link.sactive > 1) + dev_info(ap->dev, "%s ap id=%d cmd(0x%02x)=%s qc tag=%d " + "prot=%s ap active_tag=0x%08x ap sactive=0x%08x\n", + __func__, ap->print_id, qc->tf.command, + ata_get_cmd_descript(&qc->tf), + qc->tag, ata_get_cmd_descript(qc->tf.protocol), + ap->link.active_tag, ap->link.sactive); +#endif + + if (!ata_is_ncq(qc->tf.protocol)) + tag = 0; + sata_dwc_qc_prep_by_tag(qc, tag); + + if (ata_is_ncq(qc->tf.protocol)) { + sactive = core_scr_read(SCR_ACTIVE); + sactive |= (0x00000001 << tag); + core_scr_write(SCR_ACTIVE, sactive); + + dev_dbg(qc->ap->dev, "%s: tag=%d ap->link.sactive = 0x%08x " + "sactive=0x%08x\n", __func__, tag, qc->ap->link.sactive, + sactive); + + ap->ops->sff_tf_load(ap, &qc->tf); + sata_dwc_exec_command_by_tag(ap, &qc->tf, qc->tag, + SATA_DWC_CMD_ISSUED_PEND); + } else { + ata_sff_qc_issue(qc); + } + return 0; +} + +/* + * Function : sata_dwc_qc_prep + * arguments : ata_queued_cmd *qc + * Return value : None + * qc_prep for a particular queued command + */ + +static void sata_dwc_qc_prep(struct ata_queued_cmd *qc) +{ + if ((qc->dma_dir == DMA_NONE) || (qc->tf.protocol == ATA_PROT_PIO)) + return; + +#ifdef DEBUG_NCQ + if (qc->tag > 0) + dev_info(qc->ap->dev, "%s: qc->tag=%d ap->active_tag=0x%08x\n", + __func__, tag, qc->ap->link.active_tag); + + return ; +#endif +} + +static void sata_dwc_error_handler(struct ata_port *ap) +{ + ap->link.flags |= ATA_LFLAG_NO_HRST; + ata_sff_error_handler(ap); +} + +/* + * scsi mid-layer and libata interface structures + */ +static struct scsi_host_template sata_dwc_sht = { + ATA_NCQ_SHT(DRV_NAME), + /* + * test-only: Currently this driver doesn't handle NCQ + * correctly. We enable NCQ but set the queue depth to a + * max of 1. This will get fixed in in a future release. + */ + .sg_tablesize = LIBATA_MAX_PRD, + .can_queue = ATA_DEF_QUEUE, /* ATA_MAX_QUEUE */ + .dma_boundary = ATA_DMA_BOUNDARY, +}; + +static struct ata_port_operations sata_dwc_ops = { + .inherits = &ata_sff_port_ops, + + .error_handler = sata_dwc_error_handler, + + .qc_prep = sata_dwc_qc_prep, + .qc_issue = sata_dwc_qc_issue, + + .scr_read = sata_dwc_scr_read, + .scr_write = sata_dwc_scr_write, + + .port_start = sata_dwc_port_start, + .port_stop = sata_dwc_port_stop, + + .bmdma_setup = sata_dwc_bmdma_setup, + .bmdma_start = sata_dwc_bmdma_start, +}; + +static const struct ata_port_info sata_dwc_port_info[] = { + { + .flags = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | + ATA_FLAG_MMIO | ATA_FLAG_NCQ, + .pio_mask = 0x1f, /* pio 0-4 */ + .udma_mask = ATA_UDMA6, + .port_ops = &sata_dwc_ops, + }, +}; + +static int sata_dwc_probe(struct of_device *ofdev, + const struct of_device_id *match) +{ + struct sata_dwc_device *hsdev; + u32 idr, versionr; + char *ver = (char *)&versionr; + u8 *base = NULL; + int err = 0; + int irq, rc; + struct ata_host *host; + struct ata_port_info pi = sata_dwc_port_info[0]; + const struct ata_port_info *ppi[] = { &pi, NULL }; + + /* Allocate DWC SATA device */ + hsdev = kmalloc(sizeof(*hsdev), GFP_KERNEL); + if (hsdev == NULL) { + dev_err(&ofdev->dev, "kmalloc failed for hsdev\n"); + err = -ENOMEM; + goto error_out; + } + memset(hsdev, 0, sizeof(*hsdev)); + + /* Ioremap SATA registers */ + base = of_iomap(ofdev->dev.of_node, 0); + if (!base) { + dev_err(&ofdev->dev, "ioremap failed for SATA register" + " address\n"); + err = -ENODEV; + goto error_out; + } + hsdev->reg_base = base; + dev_dbg(&ofdev->dev, "ioremap done for SATA register address\n"); + + /* Synopsys DWC SATA specific Registers */ + hsdev->sata_dwc_regs = (void *__iomem)(base + SATA_DWC_REG_OFFSET); + + /* Allocate and fill host */ + host = ata_host_alloc_pinfo(&ofdev->dev, ppi, SATA_DWC_MAX_PORTS); + if (!host) { + dev_err(&ofdev->dev, "ata_host_alloc_pinfo failed\n"); + err = -ENOMEM; + goto error_out; + } + + host->private_data = hsdev; + + /* Setup port */ + host->ports[0]->ioaddr.cmd_addr = base; + host->ports[0]->ioaddr.scr_addr = base + SATA_DWC_SCR_OFFSET; + host_pvt.scr_addr_sstatus = base + SATA_DWC_SCR_OFFSET; + sata_dwc_setup_port(&host->ports[0]->ioaddr, (unsigned long)base); + + /* Read the ID and Version Registers */ + idr = in_le32(&hsdev->sata_dwc_regs->idr); + versionr = in_le32(&hsdev->sata_dwc_regs->versionr); + dev_notice(&ofdev->dev, "id %d, controller version %c.%c%c\n", + idr, ver[0], ver[1], ver[2]); + + /* Get SATA DMA interrupt number */ + irq = irq_of_parse_and_map(ofdev->dev.of_node, 1); + if (irq == NO_IRQ) { + dev_err(&ofdev->dev, "no SATA DMA irq\n"); + err = -ENODEV; + goto error_out; + } + + /* Get physical SATA DMA register base address */ + host_pvt.sata_dma_regs = of_iomap(ofdev->dev.of_node, 1); + if (!(host_pvt.sata_dma_regs)) { + dev_err(&ofdev->dev, "ioremap failed for AHBDMA register" + " address\n"); + err = -ENODEV; + goto error_out; + } + + /* Save dev for later use in dev_xxx() routines */ + host_pvt.dwc_dev = &ofdev->dev; + + /* Initialize AHB DMAC */ + dma_dwc_init(hsdev, irq); + + /* Enable SATA Interrupts */ + sata_dwc_enable_interrupts(hsdev); + + /* Get SATA interrupt number */ + irq = irq_of_parse_and_map(ofdev->dev.of_node, 0); + if (irq == NO_IRQ) { + dev_err(&ofdev->dev, "no SATA DMA irq\n"); + err = -ENODEV; + goto error_out; + } + + /* + * Now, register with libATA core, this will also initiate the + * device discovery process, invoking our port_start() handler & + * error_handler() to execute a dummy Softreset EH session + */ + rc = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht); + + if (rc != 0) + dev_err(&ofdev->dev, "failed to activate host"); + + dev_set_drvdata(&ofdev->dev, host); + return 0; + +error_out: + /* Free SATA DMA resources */ + dma_dwc_exit(hsdev); + + if (base) + iounmap(base); + return err; +} + +static int sata_dwc_remove(struct of_device *ofdev) +{ + struct device *dev = &ofdev->dev; + struct ata_host *host = dev_get_drvdata(dev); + struct sata_dwc_device *hsdev = host->private_data; + + ata_host_detach(host); + dev_set_drvdata(dev, NULL); + + /* Free SATA DMA resources */ + dma_dwc_exit(hsdev); + + iounmap(hsdev->reg_base); + kfree(hsdev); + kfree(host); + dev_dbg(&ofdev->dev, "done\n"); + return 0; +} + +static const struct of_device_id sata_dwc_match[] = { + { .compatible = "amcc,sata-460ex", }, + {} +}; +MODULE_DEVICE_TABLE(of, sata_dwc_match); + +static struct of_platform_driver sata_dwc_driver = { + .driver = { + .name = DRV_NAME, + .owner = THIS_MODULE, + .of_match_table = sata_dwc_match, + }, + .probe = sata_dwc_probe, + .remove = sata_dwc_remove, +}; + +static int __init sata_dwc_init(void) +{ + return of_register_platform_driver(&sata_dwc_driver); +} + +static void __exit sata_dwc_exit(void) +{ + of_unregister_platform_driver(&sata_dwc_driver); +} + +module_init(sata_dwc_init); +module_exit(sata_dwc_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Mark Miesfeld <mmiesfeld@amcc.com>"); +MODULE_DESCRIPTION("DesignWare Cores SATA controller low lever driver"); +MODULE_VERSION(DRV_VERSION); diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 61c89b54ea2..18c986dbb7f 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1096,7 +1096,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) { struct sata_fsl_host_priv *host_priv = ap->host->private_data; void __iomem *hcr_base = host_priv->hcr_base; - u32 hstatus, qc_active = 0; + u32 hstatus, done_mask = 0; struct ata_queued_cmd *qc; u32 SError; @@ -1116,28 +1116,28 @@ static void sata_fsl_host_intr(struct ata_port *ap) } /* Read command completed register */ - qc_active = ioread32(hcr_base + CC); + done_mask = ioread32(hcr_base + CC); VPRINTK("Status of all queues :\n"); - VPRINTK("qc_active/CC = 0x%x, CA = 0x%x, CE=0x%x,CQ=0x%x,apqa=0x%x\n", - qc_active, + VPRINTK("done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x,CQ=0x%x,apqa=0x%x\n", + done_mask, ioread32(hcr_base + CA), ioread32(hcr_base + CE), ioread32(hcr_base + CQ), ap->qc_active); - if (qc_active & ap->qc_active) { + if (done_mask & ap->qc_active) { int i; /* clear CC bit, this will also complete the interrupt */ - iowrite32(qc_active, hcr_base + CC); + iowrite32(done_mask, hcr_base + CC); DPRINTK("Status of all queues :\n"); - DPRINTK("qc_active/CC = 0x%x, CA = 0x%x, CE=0x%x\n", - qc_active, ioread32(hcr_base + CA), + DPRINTK("done_mask/CC = 0x%x, CA = 0x%x, CE=0x%x\n", + done_mask, ioread32(hcr_base + CA), ioread32(hcr_base + CE)); for (i = 0; i < SATA_FSL_QUEUE_DEPTH; i++) { - if (qc_active & (1 << i)) { + if (done_mask & (1 << i)) { qc = ata_qc_from_tag(ap, i); if (qc) { ata_qc_complete(qc); @@ -1164,7 +1164,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) /* Spurious Interrupt!! */ DPRINTK("spurious interrupt!!, CC = 0x%x\n", ioread32(hcr_base + CC)); - iowrite32(qc_active, hcr_base + CC); + iowrite32(done_mask, hcr_base + CC); return; } } diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index a476cd99b95..9463c71dd38 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -2716,34 +2716,35 @@ static void mv_err_intr(struct ata_port *ap) static void mv_process_crpb_response(struct ata_port *ap, struct mv_crpb *response, unsigned int tag, int ncq_enabled) { + u8 ata_status; + u16 edma_status = le16_to_cpu(response->flags); struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag); - if (qc) { - u8 ata_status; - u16 edma_status = le16_to_cpu(response->flags); - /* - * edma_status from a response queue entry: - * LSB is from EDMA_ERR_IRQ_CAUSE (non-NCQ only). - * MSB is saved ATA status from command completion. - */ - if (!ncq_enabled) { - u8 err_cause = edma_status & 0xff & ~EDMA_ERR_DEV; - if (err_cause) { - /* - * Error will be seen/handled by mv_err_intr(). - * So do nothing at all here. - */ - return; - } - } - ata_status = edma_status >> CRPB_FLAG_STATUS_SHIFT; - if (!ac_err_mask(ata_status)) - ata_qc_complete(qc); - /* else: leave it for mv_err_intr() */ - } else { + if (unlikely(!qc)) { ata_port_printk(ap, KERN_ERR, "%s: no qc for tag=%d\n", __func__, tag); + return; + } + + /* + * edma_status from a response queue entry: + * LSB is from EDMA_ERR_IRQ_CAUSE (non-NCQ only). + * MSB is saved ATA status from command completion. + */ + if (!ncq_enabled) { + u8 err_cause = edma_status & 0xff & ~EDMA_ERR_DEV; + if (err_cause) { + /* + * Error will be seen/handled by + * mv_err_intr(). So do nothing at all here. + */ + return; + } } + ata_status = edma_status >> CRPB_FLAG_STATUS_SHIFT; + if (!ac_err_mask(ata_status)) + ata_qc_complete(qc); + /* else: leave it for mv_err_intr() */ } static void mv_process_crpb_entries(struct ata_port *ap, struct mv_port_priv *pp) diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 21161136cad..cb89ef8d99d 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -1018,7 +1018,7 @@ static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance) NV_ADMA_STAT_CPBERR | NV_ADMA_STAT_CMD_COMPLETE)) { u32 check_commands = notifier_clears[i]; - int pos, error = 0; + int pos, rc; if (status & NV_ADMA_STAT_CPBERR) { /* check all active commands */ @@ -1030,10 +1030,12 @@ static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance) } /* check CPBs for completed commands */ - while ((pos = ffs(check_commands)) && !error) { + while ((pos = ffs(check_commands))) { pos--; - error = nv_adma_check_cpb(ap, pos, + rc = nv_adma_check_cpb(ap, pos, notifier_error & (1 << pos)); + if (unlikely(rc)) + check_commands = 0; check_commands &= ~(1 << pos); } } @@ -2129,7 +2131,6 @@ static int nv_swncq_sdbfis(struct ata_port *ap) struct nv_swncq_port_priv *pp = ap->private_data; struct ata_eh_info *ehi = &ap->link.eh_info; u32 sactive; - int nr_done = 0; u32 done_mask; int i; u8 host_stat; @@ -2170,22 +2171,21 @@ static int nv_swncq_sdbfis(struct ata_port *ap) pp->dhfis_bits &= ~(1 << i); pp->dmafis_bits &= ~(1 << i); pp->sdbfis_bits |= (1 << i); - nr_done++; } } if (!ap->qc_active) { DPRINTK("over\n"); nv_swncq_pp_reinit(ap); - return nr_done; + return 0; } if (pp->qc_active & pp->dhfis_bits) - return nr_done; + return 0; if ((pp->ncq_flags & ncq_saw_backout) || (pp->qc_active ^ pp->dhfis_bits)) - /* if the controller cann't get a device to host register FIS, + /* if the controller can't get a device to host register FIS, * The driver needs to reissue the new command. */ lack_dhfis = 1; @@ -2202,7 +2202,7 @@ static int nv_swncq_sdbfis(struct ata_port *ap) if (lack_dhfis) { qc = ata_qc_from_tag(ap, pp->last_issue_tag); nv_swncq_issue_atacmd(ap, qc); - return nr_done; + return 0; } if (pp->defer_queue.defer_bits) { @@ -2212,7 +2212,7 @@ static int nv_swncq_sdbfis(struct ata_port *ap) nv_swncq_issue_atacmd(ap, qc); } - return nr_done; + return 0; } static inline u32 nv_swncq_tag(struct ata_port *ap) @@ -2224,7 +2224,7 @@ static inline u32 nv_swncq_tag(struct ata_port *ap) return (tag & 0x1f); } -static int nv_swncq_dmafis(struct ata_port *ap) +static void nv_swncq_dmafis(struct ata_port *ap) { struct ata_queued_cmd *qc; unsigned int rw; @@ -2239,7 +2239,7 @@ static int nv_swncq_dmafis(struct ata_port *ap) qc = ata_qc_from_tag(ap, tag); if (unlikely(!qc)) - return 0; + return; rw = qc->tf.flags & ATA_TFLAG_WRITE; @@ -2254,8 +2254,6 @@ static int nv_swncq_dmafis(struct ata_port *ap) dmactl |= ATA_DMA_WR; iowrite8(dmactl | ATA_DMA_START, ap->ioaddr.bmdma_addr + ATA_DMA_CMD); - - return 1; } static void nv_swncq_host_interrupt(struct ata_port *ap, u16 fis) @@ -2265,7 +2263,6 @@ static void nv_swncq_host_interrupt(struct ata_port *ap, u16 fis) struct ata_eh_info *ehi = &ap->link.eh_info; u32 serror; u8 ata_stat; - int rc = 0; ata_stat = ap->ops->sff_check_status(ap); nv_swncq_irq_clear(ap, fis); @@ -2310,8 +2307,7 @@ static void nv_swncq_host_interrupt(struct ata_port *ap, u16 fis) "dhfis 0x%X dmafis 0x%X sactive 0x%X\n", ap->print_id, pp->qc_active, pp->dhfis_bits, pp->dmafis_bits, readl(pp->sactive_block)); - rc = nv_swncq_sdbfis(ap); - if (rc < 0) + if (nv_swncq_sdbfis(ap) < 0) goto irq_error; } @@ -2348,7 +2344,7 @@ static void nv_swncq_host_interrupt(struct ata_port *ap, u16 fis) */ pp->dmafis_bits |= (0x1 << nv_swncq_tag(ap)); pp->ncq_flags |= ncq_saw_dmas; - rc = nv_swncq_dmafis(ap); + nv_swncq_dmafis(ap); } irq_exit: diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index da8f176c051..b7385e07771 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -2657,7 +2657,7 @@ static int __devinit fore200e_sba_probe(struct of_device *op, fore200e->bus = bus; fore200e->bus_dev = op; - fore200e->irq = op->irqs[0]; + fore200e->irq = op->archdata.irqs[0]; fore200e->phys_base = op->resource[0].start; sprintf(fore200e->name, "%s-%d", bus->model_name, index); @@ -2795,7 +2795,7 @@ static int __init fore200e_module_init(void) printk(FORE200E "FORE Systems 200E-series ATM driver - version " FORE200E_VERSION "\n"); #ifdef CONFIG_SBUS - err = of_register_driver(&fore200e_sba_driver, &of_bus_type); + err = of_register_platform_driver(&fore200e_sba_driver); if (err) return err; #endif @@ -2806,7 +2806,7 @@ static int __init fore200e_module_init(void) #ifdef CONFIG_SBUS if (err) - of_unregister_driver(&fore200e_sba_driver); + of_unregister_platform_driver(&fore200e_sba_driver); #endif return err; @@ -2818,7 +2818,7 @@ static void __exit fore200e_module_cleanup(void) pci_unregister_driver(&fore200e_pca_driver); #endif #ifdef CONFIG_SBUS - of_unregister_driver(&fore200e_sba_driver); + of_unregister_platform_driver(&fore200e_sba_driver); #endif } diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 1bb8faaa443..c6c933f5810 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/platform_device.h> +#include <linux/of_device.h> #include <linux/module.h> #include <linux/init.h> #include <linux/dma-mapping.h> @@ -583,6 +584,12 @@ static struct device_attribute platform_dev_attrs[] = { static int platform_uevent(struct device *dev, struct kobj_uevent_env *env) { struct platform_device *pdev = to_platform_device(dev); + int rc; + + /* Some devices have extra OF data and an OF-style MODALIAS */ + rc = of_device_uevent(dev,env); + if (rc != -ENODEV) + return rc; add_uevent_var(env, "MODALIAS=%s%s", PLATFORM_MODULE_PREFIX, (pdev->id_entry) ? pdev->id_entry->name : pdev->name); @@ -621,7 +628,11 @@ static int platform_match(struct device *dev, struct device_driver *drv) struct platform_device *pdev = to_platform_device(dev); struct platform_driver *pdrv = to_platform_driver(drv); - /* match against the id table first */ + /* Attempt an OF style match first */ + if (of_driver_match_device(dev, drv)) + return 1; + + /* Then try to match against the id table */ if (pdrv->id_table) return platform_match_id(pdrv->id_table, pdev) != NULL; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 258bc2ae288..23b7c48df84 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -225,16 +225,6 @@ static int virtblk_ioctl(struct block_device *bdev, fmode_t mode, struct gendisk *disk = bdev->bd_disk; struct virtio_blk *vblk = disk->private_data; - if (cmd == 0x56424944) { /* 'VBID' */ - void __user *usr_data = (void __user *)data; - char id_str[VIRTIO_BLK_ID_BYTES]; - int err; - - err = virtblk_get_id(disk, id_str); - if (!err && copy_to_user(usr_data, id_str, VIRTIO_BLK_ID_BYTES)) - err = -EFAULT; - return err; - } /* * Only allow the generic SCSI ioctls if the host can support it. */ @@ -281,6 +271,27 @@ static int index_to_minor(int index) return index << PART_BITS; } +static ssize_t virtblk_serial_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + int err; + + /* sysfs gives us a PAGE_SIZE buffer */ + BUILD_BUG_ON(PAGE_SIZE < VIRTIO_BLK_ID_BYTES); + + buf[VIRTIO_BLK_ID_BYTES] = '\0'; + err = virtblk_get_id(disk, buf); + if (!err) + return strlen(buf); + + if (err == -EIO) /* Unsupported? Make it empty. */ + return 0; + + return err; +} +DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL); + static int __devinit virtblk_probe(struct virtio_device *vdev) { struct virtio_blk *vblk; @@ -366,12 +377,32 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) vblk->disk->driverfs_dev = &vdev->dev; index++; - /* If barriers are supported, tell block layer that queue is ordered */ - if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH)) + if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH)) { + /* + * If the FLUSH feature is supported we do have support for + * flushing a volatile write cache on the host. Use that + * to implement write barrier support. + */ blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH, virtblk_prepare_flush); - else if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER)) + } else if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER)) { + /* + * If the BARRIER feature is supported the host expects us + * to order request by tags. This implies there is not + * volatile write cache on the host, and that the host + * never re-orders outstanding I/O. This feature is not + * useful for real life scenarious and deprecated. + */ blk_queue_ordered(q, QUEUE_ORDERED_TAG, NULL); + } else { + /* + * If the FLUSH feature is not supported we must assume that + * the host does not perform any kind of volatile write + * caching. We still need to drain the queue to provider + * proper barrier semantics. + */ + blk_queue_ordered(q, QUEUE_ORDERED_DRAIN, NULL); + } /* If disk is read-only in the host, the guest should obey */ if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO)) @@ -445,8 +476,15 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) add_disk(vblk->disk); + err = device_create_file(disk_to_dev(vblk->disk), &dev_attr_serial); + if (err) + goto out_del_disk; + return 0; +out_del_disk: + del_gendisk(vblk->disk); + blk_cleanup_queue(vblk->disk->queue); out_put_disk: put_disk(vblk->disk); out_mempool: diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 82ed403147c..f63ac3d1f8a 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -48,6 +48,7 @@ #include <xen/grant_table.h> #include <xen/events.h> #include <xen/page.h> +#include <xen/platform_pci.h> #include <xen/interface/grant_table.h> #include <xen/interface/io/blkif.h> @@ -737,6 +738,35 @@ static int blkfront_probe(struct xenbus_device *dev, } } + if (xen_hvm_domain()) { + char *type; + int len; + /* no unplug has been done: do not hook devices != xen vbds */ + if (xen_platform_pci_unplug & XEN_UNPLUG_IGNORE) { + int major; + + if (!VDEV_IS_EXTENDED(vdevice)) + major = BLKIF_MAJOR(vdevice); + else + major = XENVBD_MAJOR; + + if (major != XENVBD_MAJOR) { + printk(KERN_INFO + "%s: HVM does not support vbd %d as xen block device\n", + __FUNCTION__, vdevice); + return -ENODEV; + } + } + /* do not create a PV cdrom device if we are an HVM guest */ + type = xenbus_read(XBT_NIL, dev->nodename, "device-type", &len); + if (IS_ERR(type)) + return -ENODEV; + if (strncmp(type, "cdrom", 5) == 0) { + kfree(type); + return -ENODEV; + } + kfree(type); + } info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { xenbus_dev_fatal(dev, -ENOMEM, "allocating info structure"); diff --git a/drivers/char/agp/efficeon-agp.c b/drivers/char/agp/efficeon-agp.c index aa109cbe0e6..d607f53d8af 100644 --- a/drivers/char/agp/efficeon-agp.c +++ b/drivers/char/agp/efficeon-agp.c @@ -372,6 +372,17 @@ static int __devinit agp_efficeon_probe(struct pci_dev *pdev, bridge->capndx = cap_ptr; /* + * If the device has not been properly setup, the following will catch + * the problem and should stop the system from crashing. + * 20030610 - hamish@zot.org + */ + if (pci_enable_device(pdev)) { + printk(KERN_ERR PFX "Unable to Enable PCI device\n"); + agp_put_bridge(bridge); + return -ENODEV; + } + + /* * The following fixes the case where the BIOS has "forgotten" to * provide an address range for the GART. * 20030610 - hamish@zot.org @@ -385,17 +396,6 @@ static int __devinit agp_efficeon_probe(struct pci_dev *pdev, } } - /* - * If the device has not been properly setup, the following will catch - * the problem and should stop the system from crashing. - * 20030610 - hamish@zot.org - */ - if (pci_enable_device(pdev)) { - printk(KERN_ERR PFX "Unable to Enable PCI device\n"); - agp_put_bridge(bridge); - return -ENODEV; - } - /* Fill in the mode register */ if (cap_ptr) { pci_read_config_dword(pdev, diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index d836a71bf06..ddf5def1b0d 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -816,9 +816,9 @@ static const struct intel_driver_description { { PCI_DEVICE_ID_INTEL_IRONLAKE_MC2_HB, PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG, "HD Graphics", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_IG, - "Sandybridge", NULL, &intel_i965_driver }, + "Sandybridge", NULL, &intel_gen6_driver }, { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_IG, - "Sandybridge", NULL, &intel_i965_driver }, + "Sandybridge", NULL, &intel_gen6_driver }, { 0, 0, NULL, NULL, NULL } }; @@ -908,6 +908,17 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, dev_info(&pdev->dev, "Intel %s Chipset\n", intel_agp_chipsets[i].name); /* + * If the device has not been properly setup, the following will catch + * the problem and should stop the system from crashing. + * 20030610 - hamish@zot.org + */ + if (pci_enable_device(pdev)) { + dev_err(&pdev->dev, "can't enable PCI device\n"); + agp_put_bridge(bridge); + return -ENODEV; + } + + /* * The following fixes the case where the BIOS has "forgotten" to * provide an address range for the GART. * 20030610 - hamish@zot.org @@ -921,17 +932,6 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, } } - /* - * If the device has not been properly setup, the following will catch - * the problem and should stop the system from crashing. - * 20030610 - hamish@zot.org - */ - if (pci_enable_device(pdev)) { - dev_err(&pdev->dev, "can't enable PCI device\n"); - agp_put_bridge(bridge); - return -ENODEV; - } - /* Fill in the mode register */ if (cap_ptr) { pci_read_config_dword(pdev, diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h index 2547465d465..c05e3e51826 100644 --- a/drivers/char/agp/intel-agp.h +++ b/drivers/char/agp/intel-agp.h @@ -60,6 +60,12 @@ #define I810_PTE_LOCAL 0x00000002 #define I810_PTE_VALID 0x00000001 #define I830_PTE_SYSTEM_CACHED 0x00000006 +/* GT PTE cache control fields */ +#define GEN6_PTE_UNCACHED 0x00000002 +#define GEN6_PTE_LLC 0x00000004 +#define GEN6_PTE_LLC_MLC 0x00000006 +#define GEN6_PTE_GFDT 0x00000008 + #define I810_SMRAM_MISCC 0x70 #define I810_GFX_MEM_WIN_SIZE 0x00010000 #define I810_GFX_MEM_WIN_32M 0x00010000 diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index a7547150a70..d22ffb811bf 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/drivers/char/agp/intel-gtt.c @@ -25,6 +25,10 @@ #define USE_PCI_DMA_API 1 #endif +/* Max amount of stolen space, anything above will be returned to Linux */ +int intel_max_stolen = 32 * 1024 * 1024; +EXPORT_SYMBOL(intel_max_stolen); + static const struct aper_size_info_fixed intel_i810_sizes[] = { {64, 16384, 4}, @@ -104,7 +108,7 @@ static int intel_agp_map_memory(struct agp_memory *mem) DBG("try mapping %lu pages\n", (unsigned long)mem->page_count); if (sg_alloc_table(&st, mem->page_count, GFP_KERNEL)) - return -ENOMEM; + goto err; mem->sg_list = sg = st.sgl; @@ -113,11 +117,14 @@ static int intel_agp_map_memory(struct agp_memory *mem) mem->num_sg = pci_map_sg(intel_private.pcidev, mem->sg_list, mem->page_count, PCI_DMA_BIDIRECTIONAL); - if (unlikely(!mem->num_sg)) { - intel_agp_free_sglist(mem); - return -ENOMEM; - } + if (unlikely(!mem->num_sg)) + goto err; + return 0; + +err: + sg_free_table(&st); + return -ENOMEM; } static void intel_agp_unmap_memory(struct agp_memory *mem) @@ -176,7 +183,7 @@ static void intel_agp_insert_sg_entries(struct agp_memory *mem, if (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB || agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB) { - cache_bits = I830_PTE_SYSTEM_CACHED; + cache_bits = GEN6_PTE_LLC_MLC; } for (i = 0, j = pg_start; i < mem->page_count; i++, j++) { @@ -710,7 +717,12 @@ static void intel_i830_init_gtt_entries(void) break; } } - if (gtt_entries > 0) { + if (!local && gtt_entries > intel_max_stolen) { + dev_info(&agp_bridge->dev->dev, + "detected %dK stolen memory, trimming to %dK\n", + gtt_entries / KB(1), intel_max_stolen / KB(1)); + gtt_entries = intel_max_stolen / KB(4); + } else if (gtt_entries > 0) { dev_info(&agp_bridge->dev->dev, "detected %dK %s memory\n", gtt_entries / KB(1), local ? "local" : "stolen"); gtt_entries /= KB(4); @@ -797,6 +809,10 @@ static int intel_i830_create_gatt_table(struct agp_bridge_data *bridge) /* we have to call this as early as possible after the MMIO base address is known */ intel_i830_init_gtt_entries(); + if (intel_private.gtt_entries == 0) { + iounmap(intel_private.registers); + return -ENOMEM; + } agp_bridge->gatt_table = NULL; @@ -1282,6 +1298,11 @@ static int intel_i915_create_gatt_table(struct agp_bridge_data *bridge) /* we have to call this as early as possible after the MMIO base address is known */ intel_i830_init_gtt_entries(); + if (intel_private.gtt_entries == 0) { + iounmap(intel_private.gtt); + iounmap(intel_private.registers); + return -ENOMEM; + } agp_bridge->gatt_table = NULL; @@ -1309,6 +1330,16 @@ static unsigned long intel_i965_mask_memory(struct agp_bridge_data *bridge, return addr | bridge->driver->masks[type].mask; } +static unsigned long intel_gen6_mask_memory(struct agp_bridge_data *bridge, + dma_addr_t addr, int type) +{ + /* Shift high bits down */ + addr |= (addr >> 28) & 0xff; + + /* Type checking must be done elsewhere */ + return addr | bridge->driver->masks[type].mask; +} + static void intel_i965_get_gtt_range(int *gtt_offset, int *gtt_size) { u16 snb_gmch_ctl; @@ -1390,6 +1421,11 @@ static int intel_i965_create_gatt_table(struct agp_bridge_data *bridge) /* we have to call this as early as possible after the MMIO base address is known */ intel_i830_init_gtt_entries(); + if (intel_private.gtt_entries == 0) { + iounmap(intel_private.gtt); + iounmap(intel_private.registers); + return -ENOMEM; + } agp_bridge->gatt_table = NULL; @@ -1517,6 +1553,39 @@ static const struct agp_bridge_driver intel_i965_driver = { #endif }; +static const struct agp_bridge_driver intel_gen6_driver = { + .owner = THIS_MODULE, + .aperture_sizes = intel_i830_sizes, + .size_type = FIXED_APER_SIZE, + .num_aperture_sizes = 4, + .needs_scratch_page = true, + .configure = intel_i9xx_configure, + .fetch_size = intel_i9xx_fetch_size, + .cleanup = intel_i915_cleanup, + .mask_memory = intel_gen6_mask_memory, + .masks = intel_i810_masks, + .agp_enable = intel_i810_agp_enable, + .cache_flush = global_cache_flush, + .create_gatt_table = intel_i965_create_gatt_table, + .free_gatt_table = intel_i830_free_gatt_table, + .insert_memory = intel_i915_insert_entries, + .remove_memory = intel_i915_remove_entries, + .alloc_by_type = intel_i830_alloc_by_type, + .free_by_type = intel_i810_free_by_type, + .agp_alloc_page = agp_generic_alloc_page, + .agp_alloc_pages = agp_generic_alloc_pages, + .agp_destroy_page = agp_generic_destroy_page, + .agp_destroy_pages = agp_generic_destroy_pages, + .agp_type_to_mask_type = intel_i830_type_to_mask_type, + .chipset_flush = intel_i915_chipset_flush, +#ifdef USE_PCI_DMA_API + .agp_map_page = intel_agp_map_page, + .agp_unmap_page = intel_agp_unmap_page, + .agp_map_memory = intel_agp_map_memory, + .agp_unmap_memory = intel_agp_unmap_memory, +#endif +}; + static const struct agp_bridge_driver intel_g33_driver = { .owner = THIS_MODULE, .aperture_sizes = intel_i830_sizes, diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c index 89d871ef8c2..91917133ae0 100644 --- a/drivers/char/bsr.c +++ b/drivers/char/bsr.c @@ -23,6 +23,7 @@ #include <linux/of.h> #include <linux/of_device.h> #include <linux/of_platform.h> +#include <linux/fs.h> #include <linux/module.h> #include <linux/cdev.h> #include <linux/list.h> diff --git a/drivers/char/hw_random/n2-drv.c b/drivers/char/hw_random/n2-drv.c index 101d5f23554..7a4f080f835 100644 --- a/drivers/char/hw_random/n2-drv.c +++ b/drivers/char/hw_random/n2-drv.c @@ -762,12 +762,12 @@ static struct of_platform_driver n2rng_driver = { static int __init n2rng_init(void) { - return of_register_driver(&n2rng_driver, &of_bus_type); + return of_register_platform_driver(&n2rng_driver); } static void __exit n2rng_exit(void) { - of_unregister_driver(&n2rng_driver); + of_unregister_platform_driver(&n2rng_driver); } module_init(n2rng_init); diff --git a/drivers/char/mem.c b/drivers/char/mem.c index f54dab8acdc..a398ecdbd75 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -916,7 +916,7 @@ static int __init chr_dev_init(void) NULL, devlist[minor].name); } - return 0; + return tty_init(); } fs_initcall(chr_dev_init); diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c index d71f0fc34b4..507441ac6ed 100644 --- a/drivers/char/tty_io.c +++ b/drivers/char/tty_io.c @@ -3128,7 +3128,7 @@ static struct cdev tty_cdev, console_cdev; * Ok, now we can initialize the rest of the tty devices and can count * on memory allocations, interrupts etc.. */ -static int __init tty_init(void) +int __init tty_init(void) { cdev_init(&tty_cdev, &tty_fops); if (cdev_add(&tty_cdev, MKDEV(TTYAUX_MAJOR, 0), 1) || @@ -3149,4 +3149,4 @@ static int __init tty_init(void) #endif return 0; } -module_init(tty_init); + diff --git a/drivers/char/vt.c b/drivers/char/vt.c index 7cdb6ee569c..4a9eb3044e5 100644 --- a/drivers/char/vt.c +++ b/drivers/char/vt.c @@ -104,6 +104,7 @@ #include <linux/io.h> #include <asm/system.h> #include <linux/uaccess.h> +#include <linux/kdb.h> #define MAX_NR_CON_DRIVER 16 @@ -187,10 +188,15 @@ static DECLARE_WORK(console_work, console_callback); * fg_console is the current virtual console, * last_console is the last used one, * want_console is the console we want to switch to, + * saved_* variants are for save/restore around kernel debugger enter/leave */ int fg_console; int last_console; int want_console = -1; +int saved_fg_console; +int saved_last_console; +int saved_want_console; +int saved_vc_mode; /* * For each existing display, we have a pointer to console currently visible @@ -3414,6 +3420,78 @@ int con_is_bound(const struct consw *csw) EXPORT_SYMBOL(con_is_bound); /** + * con_debug_enter - prepare the console for the kernel debugger + * @sw: console driver + * + * Called when the console is taken over by the kernel debugger, this + * function needs to save the current console state, then put the console + * into a state suitable for the kernel debugger. + * + * RETURNS: + * Zero on success, nonzero if a failure occurred when trying to prepare + * the console for the debugger. + */ +int con_debug_enter(struct vc_data *vc) +{ + int ret = 0; + + saved_fg_console = fg_console; + saved_last_console = last_console; + saved_want_console = want_console; + saved_vc_mode = vc->vc_mode; + vc->vc_mode = KD_TEXT; + console_blanked = 0; + if (vc->vc_sw->con_debug_enter) + ret = vc->vc_sw->con_debug_enter(vc); +#ifdef CONFIG_KGDB_KDB + /* Set the initial LINES variable if it is not already set */ + if (vc->vc_rows < 999) { + int linecount; + char lns[4]; + const char *setargs[3] = { + "set", + "LINES", + lns, + }; + if (kdbgetintenv(setargs[0], &linecount)) { + snprintf(lns, 4, "%i", vc->vc_rows); + kdb_set(2, setargs); + } + } +#endif /* CONFIG_KGDB_KDB */ + return ret; +} +EXPORT_SYMBOL_GPL(con_debug_enter); + +/** + * con_debug_leave - restore console state + * @sw: console driver + * + * Restore the console state to what it was before the kernel debugger + * was invoked. + * + * RETURNS: + * Zero on success, nonzero if a failure occurred when trying to restore + * the console. + */ +int con_debug_leave(void) +{ + struct vc_data *vc; + int ret = 0; + + fg_console = saved_fg_console; + last_console = saved_last_console; + want_console = saved_want_console; + vc_cons[fg_console].d->vc_mode = saved_vc_mode; + + vc = vc_cons[fg_console].d; + if (vc->vc_sw->con_debug_leave) + ret = vc->vc_sw->con_debug_leave(vc); + return ret; +} +EXPORT_SYMBOL_GPL(con_debug_leave); + +/** * register_con_driver - register console driver to console layer * @csw: console driver * @first: the first console to take over, minimum value is 0 diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c index b99c38f23d6..26af2dd5d83 100644 --- a/drivers/crypto/n2_core.c +++ b/drivers/crypto/n2_core.c @@ -2247,20 +2247,20 @@ static struct of_platform_driver n2_mau_driver = { static int __init n2_init(void) { - int err = of_register_driver(&n2_crypto_driver, &of_bus_type); + int err = of_register_platform_driver(&n2_crypto_driver); if (!err) { - err = of_register_driver(&n2_mau_driver, &of_bus_type); + err = of_register_platform_driver(&n2_mau_driver); if (err) - of_unregister_driver(&n2_crypto_driver); + of_unregister_platform_driver(&n2_crypto_driver); } return err; } static void __exit n2_exit(void) { - of_unregister_driver(&n2_mau_driver); - of_unregister_driver(&n2_crypto_driver); + of_unregister_platform_driver(&n2_mau_driver); + of_unregister_platform_driver(&n2_crypto_driver); } module_init(n2_init); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 4e51fe3c1fc..6a6bd569e1f 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -8,6 +8,7 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/gpio.h> +#include <linux/of_gpio.h> #include <linux/idr.h> #include <linux/slab.h> @@ -1100,16 +1101,24 @@ int gpiochip_add(struct gpio_chip *chip) } } + of_gpiochip_add(chip); + unlock: spin_unlock_irqrestore(&gpio_lock, flags); - if (status == 0) - status = gpiochip_export(chip); + + if (status) + goto fail; + + status = gpiochip_export(chip); + if (status) + goto fail; + + return 0; fail: /* failures here can mean systems won't boot... */ - if (status) - pr_err("gpiochip_add: gpios %d..%d (%s) failed to register\n", - chip->base, chip->base + chip->ngpio - 1, - chip->label ? : "generic"); + pr_err("gpiochip_add: gpios %d..%d (%s) failed to register\n", + chip->base, chip->base + chip->ngpio - 1, + chip->label ? : "generic"); return status; } EXPORT_SYMBOL_GPL(gpiochip_add); @@ -1128,6 +1137,8 @@ int gpiochip_remove(struct gpio_chip *chip) spin_lock_irqsave(&gpio_lock, flags); + of_gpiochip_remove(chip); + for (id = chip->base; id < chip->base + chip->ngpio; id++) { if (test_bit(FLAG_REQUESTED, &gpio_desc[id].flags)) { status = -EBUSY; @@ -1148,6 +1159,38 @@ int gpiochip_remove(struct gpio_chip *chip) } EXPORT_SYMBOL_GPL(gpiochip_remove); +/** + * gpiochip_find() - iterator for locating a specific gpio_chip + * @data: data to pass to match function + * @callback: Callback function to check gpio_chip + * + * Similar to bus_find_device. It returns a reference to a gpio_chip as + * determined by a user supplied @match callback. The callback should return + * 0 if the device doesn't match and non-zero if it does. If the callback is + * non-zero, this function will return to the caller and not iterate over any + * more gpio_chips. + */ +struct gpio_chip *gpiochip_find(void *data, + int (*match)(struct gpio_chip *chip, void *data)) +{ + struct gpio_chip *chip = NULL; + unsigned long flags; + int i; + + spin_lock_irqsave(&gpio_lock, flags); + for (i = 0; i < ARCH_NR_GPIOS; i++) { + if (!gpio_desc[i].chip) + continue; + + if (match(gpio_desc[i].chip, data)) { + chip = gpio_desc[i].chip; + break; + } + } + spin_unlock_irqrestore(&gpio_lock, flags); + + return chip; +} /* These "optional" allocation calls help prevent drivers from stomping * on each other, and help provide better diagnostics in debugfs. diff --git a/drivers/gpio/xilinx_gpio.c b/drivers/gpio/xilinx_gpio.c index b8fa65b5bfc..709690995d0 100644 --- a/drivers/gpio/xilinx_gpio.c +++ b/drivers/gpio/xilinx_gpio.c @@ -161,14 +161,12 @@ static void xgpio_save_regs(struct of_mm_gpio_chip *mm_gc) static int __devinit xgpio_of_probe(struct device_node *np) { struct xgpio_instance *chip; - struct of_gpio_chip *ofchip; int status = 0; const u32 *tree_info; chip = kzalloc(sizeof(*chip), GFP_KERNEL); if (!chip) return -ENOMEM; - ofchip = &chip->mmchip.of_gc; /* Update GPIO state shadow register with default value */ tree_info = of_get_property(np, "xlnx,dout-default", NULL); @@ -182,21 +180,20 @@ static int __devinit xgpio_of_probe(struct device_node *np) chip->gpio_dir = *tree_info; /* Check device node and parent device node for device width */ - ofchip->gc.ngpio = 32; /* By default assume full GPIO controller */ + chip->mmchip.gc.ngpio = 32; /* By default assume full GPIO controller */ tree_info = of_get_property(np, "xlnx,gpio-width", NULL); if (!tree_info) tree_info = of_get_property(np->parent, "xlnx,gpio-width", NULL); if (tree_info) - ofchip->gc.ngpio = *tree_info; + chip->mmchip.gc.ngpio = *tree_info; spin_lock_init(&chip->gpio_lock); - ofchip->gpio_cells = 2; - ofchip->gc.direction_input = xgpio_dir_in; - ofchip->gc.direction_output = xgpio_dir_out; - ofchip->gc.get = xgpio_get; - ofchip->gc.set = xgpio_set; + chip->mmchip.gc.direction_input = xgpio_dir_in; + chip->mmchip.gc.direction_output = xgpio_dir_out; + chip->mmchip.gc.get = xgpio_get; + chip->mmchip.gc.set = xgpio_set; chip->mmchip.save_regs = xgpio_save_regs; diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 88910e5a2c7..4cab0c6397e 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -6,7 +6,7 @@ # menuconfig DRM tristate "Direct Rendering Manager (XFree86 4.1.0 and higher DRI support)" - depends on (AGP || AGP=n) && PCI && !EMULATED_CMPXCHG && MMU + depends on (AGP || AGP=n) && !EMULATED_CMPXCHG && MMU select I2C select I2C_ALGOBIT select SLOW_WORK @@ -17,7 +17,7 @@ menuconfig DRM These modules provide support for synchronization, security, and DMA transfers. Please see <http://dri.sourceforge.net/> for more details. You should also select and configure AGP - (/dev/agpgart) support. + (/dev/agpgart) support if it is available for your platform. config DRM_KMS_HELPER tristate @@ -61,6 +61,7 @@ config DRM_RADEON select DRM_KMS_HELPER select DRM_TTM select POWER_SUPPLY + select HWMON help Choose this option if you have an ATI Radeon graphics card. There are both PCI and AGP versions. You don't need to choose this to @@ -130,7 +131,7 @@ endchoice config DRM_MGA tristate "Matrox g200/g400" - depends on DRM + depends on DRM && PCI select FW_LOADER help Choose this option if you have a Matrox G200, G400 or G450 graphics @@ -148,14 +149,14 @@ config DRM_SIS config DRM_VIA tristate "Via unichrome video cards" - depends on DRM + depends on DRM && PCI help Choose this option if you have a Via unichrome or compatible video chipset. If M is selected the module will be called via. config DRM_SAVAGE tristate "Savage video cards" - depends on DRM + depends on DRM && PCI help Choose this option if you have a Savage3D/4/SuperSavage/Pro/Twister chipset. If M is selected the module will be called savage. diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index abe3f446ca4..f3a23a329f4 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -9,9 +9,10 @@ drm-y := drm_auth.o drm_buffer.o drm_bufs.o drm_cache.o \ drm_drv.o drm_fops.o drm_gem.o drm_ioctl.o drm_irq.o \ drm_lock.o drm_memory.o drm_proc.o drm_stub.o drm_vm.o \ drm_agpsupport.o drm_scatter.o ati_pcigart.o drm_pci.o \ - drm_sysfs.o drm_hashtab.o drm_sman.o drm_mm.o \ + drm_platform.o drm_sysfs.o drm_hashtab.o drm_sman.o drm_mm.o \ drm_crtc.o drm_modes.o drm_edid.o \ - drm_info.o drm_debugfs.o drm_encoder_slave.o + drm_info.o drm_debugfs.o drm_encoder_slave.o \ + drm_trace_points.o drm_global.o drm-$(CONFIG_COMPAT) += drm_ioc32.o @@ -19,6 +20,8 @@ drm_kms_helper-y := drm_fb_helper.o drm_crtc_helper.o drm_dp_i2c_helper.o obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o +CFLAGS_drm_trace_points.o := -I$(src) + obj-$(CONFIG_DRM) += drm.o obj-$(CONFIG_DRM_TTM) += ttm/ obj-$(CONFIG_DRM_TDFX) += tdfx/ diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c index 2092e7bb788..a5c9ce93bbc 100644 --- a/drivers/gpu/drm/drm_bufs.c +++ b/drivers/gpu/drm/drm_bufs.c @@ -39,19 +39,6 @@ #include <asm/shmparam.h> #include "drmP.h" -resource_size_t drm_get_resource_start(struct drm_device *dev, unsigned int resource) -{ - return pci_resource_start(dev->pdev, resource); -} -EXPORT_SYMBOL(drm_get_resource_start); - -resource_size_t drm_get_resource_len(struct drm_device *dev, unsigned int resource) -{ - return pci_resource_len(dev->pdev, resource); -} - -EXPORT_SYMBOL(drm_get_resource_len); - static struct drm_map_list *drm_find_matching_map(struct drm_device *dev, struct drm_local_map *map) { @@ -189,7 +176,7 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset, switch (map->type) { case _DRM_REGISTERS: case _DRM_FRAME_BUFFER: -#if !defined(__sparc__) && !defined(__alpha__) && !defined(__ia64__) && !defined(__powerpc64__) && !defined(__x86_64__) +#if !defined(__sparc__) && !defined(__alpha__) && !defined(__ia64__) && !defined(__powerpc64__) && !defined(__x86_64__) && !defined(__arm__) if (map->offset + (map->size-1) < map->offset || map->offset < virt_to_phys(high_memory)) { kfree(map); diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 57cea01c4ff..4c68f76993d 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -80,6 +80,7 @@ static struct drm_prop_enum_list drm_dithering_mode_enum_list[] = { { DRM_MODE_DITHERING_OFF, "Off" }, { DRM_MODE_DITHERING_ON, "On" }, + { DRM_MODE_DITHERING_AUTO, "Automatic" }, }; /* @@ -1126,7 +1127,7 @@ int drm_mode_getresources(struct drm_device *dev, void *data, if (file_priv->master->minor->type == DRM_MINOR_CONTROL) { list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - DRM_DEBUG_KMS("CRTC ID is %d\n", crtc->base.id); + DRM_DEBUG_KMS("[CRTC:%d]\n", crtc->base.id); if (put_user(crtc->base.id, crtc_id + copied)) { ret = -EFAULT; goto out; @@ -1154,8 +1155,8 @@ int drm_mode_getresources(struct drm_device *dev, void *data, list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { - DRM_DEBUG_KMS("ENCODER ID is %d\n", - encoder->base.id); + DRM_DEBUG_KMS("[ENCODER:%d:%s]\n", encoder->base.id, + drm_get_encoder_name(encoder)); if (put_user(encoder->base.id, encoder_id + copied)) { ret = -EFAULT; @@ -1185,8 +1186,9 @@ int drm_mode_getresources(struct drm_device *dev, void *data, list_for_each_entry(connector, &dev->mode_config.connector_list, head) { - DRM_DEBUG_KMS("CONNECTOR ID is %d\n", - connector->base.id); + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", + connector->base.id, + drm_get_connector_name(connector)); if (put_user(connector->base.id, connector_id + copied)) { ret = -EFAULT; @@ -1209,7 +1211,7 @@ int drm_mode_getresources(struct drm_device *dev, void *data, } card_res->count_connectors = connector_count; - DRM_DEBUG_KMS("Counted %d %d %d\n", card_res->count_crtcs, + DRM_DEBUG_KMS("CRTC[%d] CONNECTORS[%d] ENCODERS[%d]\n", card_res->count_crtcs, card_res->count_connectors, card_res->count_encoders); out: @@ -1312,7 +1314,7 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, memset(&u_mode, 0, sizeof(struct drm_mode_modeinfo)); - DRM_DEBUG_KMS("connector id %d:\n", out_resp->connector_id); + DRM_DEBUG_KMS("[CONNECTOR:%d:?]\n", out_resp->connector_id); mutex_lock(&dev->mode_config.mutex); @@ -1493,6 +1495,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, goto out; } crtc = obj_to_crtc(obj); + DRM_DEBUG_KMS("[CRTC:%d]\n", crtc->base.id); if (crtc_req->mode_valid) { /* If we have a mode we need a framebuffer. */ @@ -1569,6 +1572,9 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, goto out; } connector = obj_to_connector(obj); + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", + connector->base.id, + drm_get_connector_name(connector)); connector_set[i] = connector; } @@ -1684,6 +1690,7 @@ int drm_mode_addfb(struct drm_device *dev, r->fb_id = fb->base.id; list_add(&fb->filp_head, &file_priv->fbs); + DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id); out: mutex_unlock(&dev->mode_config.mutex); @@ -2610,6 +2617,15 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, goto out; crtc = obj_to_crtc(obj); + if (crtc->fb == NULL) { + /* The framebuffer is currently unbound, presumably + * due to a hotplug event, that userspace has not + * yet discovered. + */ + ret = -EBUSY; + goto out; + } + if (crtc->funcs->page_flip == NULL) goto out; diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c index 9b2a54117c9..11fe9c870d1 100644 --- a/drivers/gpu/drm/drm_crtc_helper.c +++ b/drivers/gpu/drm/drm_crtc_helper.c @@ -86,7 +86,8 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, int count = 0; int mode_flags = 0; - DRM_DEBUG_KMS("%s\n", drm_get_connector_name(connector)); + DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, + drm_get_connector_name(connector)); /* set all modes to the unverified state */ list_for_each_entry_safe(mode, t, &connector->modes, head) mode->status = MODE_UNVERIFIED; @@ -102,8 +103,8 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector, connector->status = connector->funcs->detect(connector); if (connector->status == connector_status_disconnected) { - DRM_DEBUG_KMS("%s is disconnected\n", - drm_get_connector_name(connector)); + DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n", + connector->base.id, drm_get_connector_name(connector)); drm_mode_connector_update_edid_property(connector, NULL); goto prune; } @@ -141,8 +142,8 @@ prune: drm_mode_sort(&connector->modes); - DRM_DEBUG_KMS("Probed modes for %s\n", - drm_get_connector_name(connector)); + DRM_DEBUG_KMS("[CONNECTOR:%d:%s] probed modes :\n", connector->base.id, + drm_get_connector_name(connector)); list_for_each_entry_safe(mode, t, &connector->modes, head) { mode->vrefresh = drm_mode_vrefresh(mode); @@ -201,6 +202,17 @@ bool drm_helper_crtc_in_use(struct drm_crtc *crtc) } EXPORT_SYMBOL(drm_helper_crtc_in_use); +static void +drm_encoder_disable(struct drm_encoder *encoder) +{ + struct drm_encoder_helper_funcs *encoder_funcs = encoder->helper_private; + + if (encoder_funcs->disable) + (*encoder_funcs->disable)(encoder); + else + (*encoder_funcs->dpms)(encoder, DRM_MODE_DPMS_OFF); +} + /** * drm_helper_disable_unused_functions - disable unused objects * @dev: DRM device @@ -215,7 +227,6 @@ void drm_helper_disable_unused_functions(struct drm_device *dev) { struct drm_encoder *encoder; struct drm_connector *connector; - struct drm_encoder_helper_funcs *encoder_funcs; struct drm_crtc *crtc; list_for_each_entry(connector, &dev->mode_config.connector_list, head) { @@ -226,12 +237,8 @@ void drm_helper_disable_unused_functions(struct drm_device *dev) } list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { - encoder_funcs = encoder->helper_private; if (!drm_helper_encoder_in_use(encoder)) { - if (encoder_funcs->disable) - (*encoder_funcs->disable)(encoder); - else - (*encoder_funcs->dpms)(encoder, DRM_MODE_DPMS_OFF); + drm_encoder_disable(encoder); /* disconnector encoder from any connector */ encoder->crtc = NULL; } @@ -241,7 +248,10 @@ void drm_helper_disable_unused_functions(struct drm_device *dev) struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private; crtc->enabled = drm_helper_crtc_in_use(crtc); if (!crtc->enabled) { - crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF); + if (crtc_funcs->disable) + (*crtc_funcs->disable)(crtc); + else + (*crtc_funcs->dpms)(crtc, DRM_MODE_DPMS_OFF); crtc->fb = NULL; } } @@ -292,11 +302,11 @@ drm_crtc_prepare_encoders(struct drm_device *dev) encoder_funcs = encoder->helper_private; /* Disable unused encoders */ if (encoder->crtc == NULL) - (*encoder_funcs->dpms)(encoder, DRM_MODE_DPMS_OFF); + drm_encoder_disable(encoder); /* Disable encoders whose CRTC is about to change */ if (encoder_funcs->get_crtc && encoder->crtc != (*encoder_funcs->get_crtc)(encoder)) - (*encoder_funcs->dpms)(encoder, DRM_MODE_DPMS_OFF); + drm_encoder_disable(encoder); } } @@ -365,6 +375,7 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc, if (!(ret = crtc_funcs->mode_fixup(crtc, mode, adjusted_mode))) { goto done; } + DRM_DEBUG_KMS("[CRTC:%d]\n", crtc->base.id); /* Prepare the encoders and CRTCs before setting the mode. */ list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { @@ -392,8 +403,9 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc, if (encoder->crtc != crtc) continue; - DRM_DEBUG("%s: set mode %s %x\n", drm_get_encoder_name(encoder), - mode->name, mode->base.id); + DRM_DEBUG_KMS("[ENCODER:%d:%s] set [MODE:%d:%s]\n", + encoder->base.id, drm_get_encoder_name(encoder), + mode->base.id, mode->name); encoder_funcs = encoder->helper_private; encoder_funcs->mode_set(encoder, mode, adjusted_mode); } @@ -469,10 +481,15 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) crtc_funcs = set->crtc->helper_private; - DRM_DEBUG_KMS("crtc: %p %d fb: %p connectors: %p num_connectors:" - " %d (x, y) (%i, %i)\n", - set->crtc, set->crtc->base.id, set->fb, set->connectors, - (int)set->num_connectors, set->x, set->y); + if (set->fb) { + DRM_DEBUG_KMS("[CRTC:%d] [FB:%d] #connectors=%d (x y) (%i %i)\n", + set->crtc->base.id, set->fb->base.id, + (int)set->num_connectors, set->x, set->y); + } else { + DRM_DEBUG_KMS("[CRTC:%d] [NOFB] #connectors=%d (x y) (%i %i)\n", + set->crtc->base.id, (int)set->num_connectors, + set->x, set->y); + } dev = set->crtc->dev; @@ -601,8 +618,14 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) mode_changed = true; connector->encoder->crtc = new_crtc; } - DRM_DEBUG_KMS("setting connector %d crtc to %p\n", - connector->base.id, new_crtc); + if (new_crtc) { + DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [CRTC:%d]\n", + connector->base.id, drm_get_connector_name(connector), + new_crtc->base.id); + } else { + DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [NOCRTC]\n", + connector->base.id, drm_get_connector_name(connector)); + } } /* mode_set_base is not a required function */ @@ -620,8 +643,8 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) if (!drm_crtc_helper_set_mode(set->crtc, set->mode, set->x, set->y, old_fb)) { - DRM_ERROR("failed to set mode on crtc %p\n", - set->crtc); + DRM_ERROR("failed to set mode on [CRTC:%d]\n", + set->crtc->base.id); ret = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 4a66201edae..90288ec7c28 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -243,47 +243,20 @@ int drm_lastclose(struct drm_device * dev) * * Initializes an array of drm_device structures, and attempts to * initialize all available devices, using consecutive minors, registering the - * stubs and initializing the AGP device. + * stubs and initializing the device. * * Expands the \c DRIVER_PREINIT and \c DRIVER_POST_INIT macros before and * after the initialization for driver customization. */ int drm_init(struct drm_driver *driver) { - struct pci_dev *pdev = NULL; - const struct pci_device_id *pid; - int i; - DRM_DEBUG("\n"); - INIT_LIST_HEAD(&driver->device_list); - if (driver->driver_features & DRIVER_MODESET) - return pci_register_driver(&driver->pci_driver); - - /* If not using KMS, fall back to stealth mode manual scanning. */ - for (i = 0; driver->pci_driver.id_table[i].vendor != 0; i++) { - pid = &driver->pci_driver.id_table[i]; - - /* Loop around setting up a DRM device for each PCI device - * matching our ID and device class. If we had the internal - * function that pci_get_subsys and pci_get_class used, we'd - * be able to just pass pid in instead of doing a two-stage - * thing. - */ - pdev = NULL; - while ((pdev = - pci_get_subsys(pid->vendor, pid->device, pid->subvendor, - pid->subdevice, pdev)) != NULL) { - if ((pdev->class & pid->class_mask) != pid->class) - continue; - - /* stealth mode requires a manual probe */ - pci_dev_get(pdev); - drm_get_dev(pdev, pid, driver); - } - } - return 0; + if (driver->driver_features & DRIVER_USE_PLATFORM_DEVICE) + return drm_platform_init(driver); + else + return drm_pci_init(driver); } EXPORT_SYMBOL(drm_init); @@ -315,6 +288,7 @@ static int __init drm_core_init(void) { int ret = -ENOMEM; + drm_global_init(); idr_init(&drm_minors_idr); if (register_chrdev(DRM_MAJOR, "drm", &drm_stub_fops)) @@ -362,6 +336,7 @@ static void __exit drm_core_exit(void) unregister_chrdev(DRM_MAJOR, "drm"); + idr_remove_all(&drm_minors_idr); idr_destroy(&drm_minors_idr); } @@ -506,9 +481,9 @@ long drm_ioctl(struct file *filp, if (ioctl->flags & DRM_UNLOCKED) retcode = func(dev, kdata, file_priv); else { - lock_kernel(); + mutex_lock(&drm_global_mutex); retcode = func(dev, kdata, file_priv); - unlock_kernel(); + mutex_unlock(&drm_global_mutex); } if (cmd & IOC_OUT) { diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 9585e531ac6..dce5c4a97f8 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -282,7 +282,7 @@ drm_do_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter) return block; carp: - dev_warn(&connector->dev->pdev->dev, "%s: EDID block %d invalid.\n", + dev_warn(connector->dev->dev, "%s: EDID block %d invalid.\n", drm_get_connector_name(connector), j); out: @@ -1623,7 +1623,7 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) return 0; } if (!drm_edid_is_valid(edid)) { - dev_warn(&connector->dev->pdev->dev, "%s: EDID invalid.\n", + dev_warn(connector->dev->dev, "%s: EDID invalid.\n", drm_get_connector_name(connector)); return 0; } diff --git a/drivers/gpu/drm/drm_encoder_slave.c b/drivers/gpu/drm/drm_encoder_slave.c index f0184696edf..d62c064fbaa 100644 --- a/drivers/gpu/drm/drm_encoder_slave.c +++ b/drivers/gpu/drm/drm_encoder_slave.c @@ -41,6 +41,9 @@ * &drm_encoder_slave. The @slave_funcs field will be initialized with * the hooks provided by the slave driver. * + * If @info->platform_data is non-NULL it will be used as the initial + * slave config. + * * Returns 0 on success or a negative errno on failure, in particular, * -ENODEV is returned when no matching driver is found. */ @@ -85,6 +88,10 @@ int drm_i2c_encoder_init(struct drm_device *dev, if (err) goto fail_unregister; + if (info->platform_data) + encoder->slave_funcs->set_config(&encoder->base, + info->platform_data); + return 0; fail_unregister: diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 719662034bb..de82e201d68 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -241,6 +241,80 @@ static int drm_fb_helper_parse_command_line(struct drm_fb_helper *fb_helper) return 0; } +int drm_fb_helper_debug_enter(struct fb_info *info) +{ + struct drm_fb_helper *helper = info->par; + struct drm_crtc_helper_funcs *funcs; + int i; + + if (list_empty(&kernel_fb_helper_list)) + return false; + + list_for_each_entry(helper, &kernel_fb_helper_list, kernel_fb_list) { + for (i = 0; i < helper->crtc_count; i++) { + struct drm_mode_set *mode_set = + &helper->crtc_info[i].mode_set; + + if (!mode_set->crtc->enabled) + continue; + + funcs = mode_set->crtc->helper_private; + funcs->mode_set_base_atomic(mode_set->crtc, + mode_set->fb, + mode_set->x, + mode_set->y); + + } + } + + return 0; +} +EXPORT_SYMBOL(drm_fb_helper_debug_enter); + +/* Find the real fb for a given fb helper CRTC */ +static struct drm_framebuffer *drm_mode_config_fb(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_crtc *c; + + list_for_each_entry(c, &dev->mode_config.crtc_list, head) { + if (crtc->base.id == c->base.id) + return c->fb; + } + + return NULL; +} + +int drm_fb_helper_debug_leave(struct fb_info *info) +{ + struct drm_fb_helper *helper = info->par; + struct drm_crtc *crtc; + struct drm_crtc_helper_funcs *funcs; + struct drm_framebuffer *fb; + int i; + + for (i = 0; i < helper->crtc_count; i++) { + struct drm_mode_set *mode_set = &helper->crtc_info[i].mode_set; + crtc = mode_set->crtc; + funcs = crtc->helper_private; + fb = drm_mode_config_fb(crtc); + + if (!crtc->enabled) + continue; + + if (!fb) { + DRM_ERROR("no fb to restore??\n"); + continue; + } + + funcs->mode_set_base_atomic(mode_set->crtc, fb, crtc->x, + crtc->y); + } + + return 0; +} +EXPORT_SYMBOL(drm_fb_helper_debug_leave); + bool drm_fb_helper_force_kernel_mode(void) { int i = 0; @@ -611,7 +685,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, struct drm_framebuffer *fb = fb_helper->fb; int depth; - if (var->pixclock != 0) + if (var->pixclock != 0 || in_dbg_master()) return -EINVAL; /* Need to resize the fb object !!! */ diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c index e7aace20981..2ca8df8b610 100644 --- a/drivers/gpu/drm/drm_fops.c +++ b/drivers/gpu/drm/drm_fops.c @@ -39,6 +39,9 @@ #include <linux/slab.h> #include <linux/smp_lock.h> +/* from BKL pushdown: note that nothing else serializes idr_find() */ +DEFINE_MUTEX(drm_global_mutex); + static int drm_open_helper(struct inode *inode, struct file *filp, struct drm_device * dev); @@ -175,8 +178,7 @@ int drm_stub_open(struct inode *inode, struct file *filp) DRM_DEBUG("\n"); - /* BKL pushdown: note that nothing else serializes idr_find() */ - lock_kernel(); + mutex_lock(&drm_global_mutex); minor = idr_find(&drm_minors_idr, minor_id); if (!minor) goto out; @@ -197,7 +199,7 @@ int drm_stub_open(struct inode *inode, struct file *filp) fops_put(old_fops); out: - unlock_kernel(); + mutex_unlock(&drm_global_mutex); return err; } @@ -472,7 +474,7 @@ int drm_release(struct inode *inode, struct file *filp) struct drm_device *dev = file_priv->minor->dev; int retcode = 0; - lock_kernel(); + mutex_lock(&drm_global_mutex); DRM_DEBUG("open_count = %d\n", dev->open_count); @@ -573,17 +575,14 @@ int drm_release(struct inode *inode, struct file *filp) if (atomic_read(&dev->ioctl_count)) { DRM_ERROR("Device busy: %d\n", atomic_read(&dev->ioctl_count)); - spin_unlock(&dev->count_lock); - unlock_kernel(); - return -EBUSY; + retcode = -EBUSY; + goto out; } - spin_unlock(&dev->count_lock); - unlock_kernel(); - return drm_lastclose(dev); + retcode = drm_lastclose(dev); } +out: spin_unlock(&dev->count_lock); - - unlock_kernel(); + mutex_unlock(&drm_global_mutex); return retcode; } diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 33dad3fa604..4f1b8671448 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -68,8 +68,18 @@ * We make up offsets for buffer objects so we can recognize them at * mmap time. */ + +/* pgoff in mmap is an unsigned long, so we need to make sure that + * the faked up offset will fit + */ + +#if BITS_PER_LONG == 64 #define DRM_FILE_PAGE_OFFSET_START ((0xFFFFFFFFUL >> PAGE_SHIFT) + 1) #define DRM_FILE_PAGE_OFFSET_SIZE ((0xFFFFFFFFUL >> PAGE_SHIFT) * 16) +#else +#define DRM_FILE_PAGE_OFFSET_START ((0xFFFFFFFUL >> PAGE_SHIFT) + 1) +#define DRM_FILE_PAGE_OFFSET_SIZE ((0xFFFFFFFUL >> PAGE_SHIFT) * 16) +#endif /** * Initialize the GEM device fields @@ -419,6 +429,7 @@ drm_gem_release(struct drm_device *dev, struct drm_file *file_private) idr_for_each(&file_private->object_idr, &drm_gem_object_release_handle, NULL); + idr_remove_all(&file_private->object_idr); idr_destroy(&file_private->object_idr); } diff --git a/drivers/gpu/drm/ttm/ttm_global.c b/drivers/gpu/drm/drm_global.c index b17007178a3..c87dc96444d 100644 --- a/drivers/gpu/drm/ttm/ttm_global.c +++ b/drivers/gpu/drm/drm_global.c @@ -28,45 +28,45 @@ * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> */ -#include "ttm/ttm_module.h" #include <linux/mutex.h> #include <linux/slab.h> #include <linux/module.h> +#include "drm_global.h" -struct ttm_global_item { +struct drm_global_item { struct mutex mutex; void *object; int refcount; }; -static struct ttm_global_item glob[TTM_GLOBAL_NUM]; +static struct drm_global_item glob[DRM_GLOBAL_NUM]; -void ttm_global_init(void) +void drm_global_init(void) { int i; - for (i = 0; i < TTM_GLOBAL_NUM; ++i) { - struct ttm_global_item *item = &glob[i]; + for (i = 0; i < DRM_GLOBAL_NUM; ++i) { + struct drm_global_item *item = &glob[i]; mutex_init(&item->mutex); item->object = NULL; item->refcount = 0; } } -void ttm_global_release(void) +void drm_global_release(void) { int i; - for (i = 0; i < TTM_GLOBAL_NUM; ++i) { - struct ttm_global_item *item = &glob[i]; + for (i = 0; i < DRM_GLOBAL_NUM; ++i) { + struct drm_global_item *item = &glob[i]; BUG_ON(item->object != NULL); BUG_ON(item->refcount != 0); } } -int ttm_global_item_ref(struct ttm_global_reference *ref) +int drm_global_item_ref(struct drm_global_reference *ref) { int ret; - struct ttm_global_item *item = &glob[ref->global_type]; + struct drm_global_item *item = &glob[ref->global_type]; void *object; mutex_lock(&item->mutex); @@ -93,11 +93,11 @@ out_err: item->object = NULL; return ret; } -EXPORT_SYMBOL(ttm_global_item_ref); +EXPORT_SYMBOL(drm_global_item_ref); -void ttm_global_item_unref(struct ttm_global_reference *ref) +void drm_global_item_unref(struct drm_global_reference *ref) { - struct ttm_global_item *item = &glob[ref->global_type]; + struct drm_global_item *item = &glob[ref->global_type]; mutex_lock(&item->mutex); BUG_ON(item->refcount == 0); @@ -108,5 +108,5 @@ void ttm_global_item_unref(struct ttm_global_reference *ref) } mutex_unlock(&item->mutex); } -EXPORT_SYMBOL(ttm_global_item_unref); +EXPORT_SYMBOL(drm_global_item_unref); diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c index f0f6c6b93f3..2ef2c782724 100644 --- a/drivers/gpu/drm/drm_info.c +++ b/drivers/gpu/drm/drm_info.c @@ -51,13 +51,24 @@ int drm_name_info(struct seq_file *m, void *data) if (!master) return 0; - if (master->unique) { - seq_printf(m, "%s %s %s\n", - dev->driver->pci_driver.name, - pci_name(dev->pdev), master->unique); + if (drm_core_check_feature(dev, DRIVER_USE_PLATFORM_DEVICE)) { + if (master->unique) { + seq_printf(m, "%s %s %s\n", + dev->driver->platform_device->name, + dev_name(dev->dev), master->unique); + } else { + seq_printf(m, "%s\n", + dev->driver->platform_device->name); + } } else { - seq_printf(m, "%s %s\n", dev->driver->pci_driver.name, - pci_name(dev->pdev)); + if (master->unique) { + seq_printf(m, "%s %s %s\n", + dev->driver->pci_driver.name, + dev_name(dev->dev), master->unique); + } else { + seq_printf(m, "%s %s\n", dev->driver->pci_driver.name, + dev_name(dev->dev)); + } } return 0; diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 9b9ff46c237..7b03b197fc0 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -64,6 +64,19 @@ int drm_getunique(struct drm_device *dev, void *data, return 0; } +static void +drm_unset_busid(struct drm_device *dev, + struct drm_master *master) +{ + kfree(dev->devname); + dev->devname = NULL; + + kfree(master->unique); + master->unique = NULL; + master->unique_len = 0; + master->unique_size = 0; +} + /** * Set the bus id. * @@ -94,17 +107,24 @@ int drm_setunique(struct drm_device *dev, void *data, master->unique_len = u->unique_len; master->unique_size = u->unique_len + 1; master->unique = kmalloc(master->unique_size, GFP_KERNEL); - if (!master->unique) - return -ENOMEM; - if (copy_from_user(master->unique, u->unique, master->unique_len)) - return -EFAULT; + if (!master->unique) { + ret = -ENOMEM; + goto err; + } + + if (copy_from_user(master->unique, u->unique, master->unique_len)) { + ret = -EFAULT; + goto err; + } master->unique[master->unique_len] = '\0'; dev->devname = kmalloc(strlen(dev->driver->pci_driver.name) + strlen(master->unique) + 2, GFP_KERNEL); - if (!dev->devname) - return -ENOMEM; + if (!dev->devname) { + ret = -ENOMEM; + goto err; + } sprintf(dev->devname, "%s@%s", dev->driver->pci_driver.name, master->unique); @@ -113,53 +133,103 @@ int drm_setunique(struct drm_device *dev, void *data, * busid. */ ret = sscanf(master->unique, "PCI:%d:%d:%d", &bus, &slot, &func); - if (ret != 3) - return -EINVAL; + if (ret != 3) { + ret = -EINVAL; + goto err; + } + domain = bus >> 8; bus &= 0xff; if ((domain != drm_get_pci_domain(dev)) || (bus != dev->pdev->bus->number) || (slot != PCI_SLOT(dev->pdev->devfn)) || - (func != PCI_FUNC(dev->pdev->devfn))) - return -EINVAL; + (func != PCI_FUNC(dev->pdev->devfn))) { + ret = -EINVAL; + goto err; + } return 0; + +err: + drm_unset_busid(dev, master); + return ret; } static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv) { struct drm_master *master = file_priv->master; - int len; + int len, ret; if (master->unique != NULL) - return -EBUSY; + drm_unset_busid(dev, master); - master->unique_len = 40; - master->unique_size = master->unique_len; - master->unique = kmalloc(master->unique_size, GFP_KERNEL); - if (master->unique == NULL) - return -ENOMEM; - - len = snprintf(master->unique, master->unique_len, "pci:%04x:%02x:%02x.%d", - drm_get_pci_domain(dev), - dev->pdev->bus->number, - PCI_SLOT(dev->pdev->devfn), - PCI_FUNC(dev->pdev->devfn)); - if (len >= master->unique_len) - DRM_ERROR("buffer overflow"); - else - master->unique_len = len; + if (drm_core_check_feature(dev, DRIVER_USE_PLATFORM_DEVICE)) { + master->unique_len = 10 + strlen(dev->platformdev->name); + master->unique = kmalloc(master->unique_len + 1, GFP_KERNEL); - dev->devname = kmalloc(strlen(dev->driver->pci_driver.name) + - master->unique_len + 2, GFP_KERNEL); - if (dev->devname == NULL) - return -ENOMEM; + if (master->unique == NULL) + return -ENOMEM; - sprintf(dev->devname, "%s@%s", dev->driver->pci_driver.name, - master->unique); + len = snprintf(master->unique, master->unique_len, + "platform:%s", dev->platformdev->name); + + if (len > master->unique_len) { + DRM_ERROR("Unique buffer overflowed\n"); + ret = -EINVAL; + goto err; + } + + dev->devname = + kmalloc(strlen(dev->platformdev->name) + + master->unique_len + 2, GFP_KERNEL); + + if (dev->devname == NULL) { + ret = -ENOMEM; + goto err; + } + + sprintf(dev->devname, "%s@%s", dev->platformdev->name, + master->unique); + + } else { + master->unique_len = 40; + master->unique_size = master->unique_len; + master->unique = kmalloc(master->unique_size, GFP_KERNEL); + if (master->unique == NULL) + return -ENOMEM; + + len = snprintf(master->unique, master->unique_len, + "pci:%04x:%02x:%02x.%d", + drm_get_pci_domain(dev), + dev->pdev->bus->number, + PCI_SLOT(dev->pdev->devfn), + PCI_FUNC(dev->pdev->devfn)); + if (len >= master->unique_len) { + DRM_ERROR("buffer overflow"); + ret = -EINVAL; + goto err; + } else + master->unique_len = len; + + dev->devname = + kmalloc(strlen(dev->driver->pci_driver.name) + + master->unique_len + 2, GFP_KERNEL); + + if (dev->devname == NULL) { + ret = -ENOMEM; + goto err; + } + + sprintf(dev->devname, "%s@%s", dev->driver->pci_driver.name, + master->unique); + } return 0; + +err: + drm_unset_busid(dev, master); + return ret; } /** @@ -323,7 +393,9 @@ int drm_setversion(struct drm_device *dev, void *data, struct drm_file *file_pri /* * Version 1.1 includes tying of DRM to specific device */ - drm_set_busid(dev, file_priv); + retcode = drm_set_busid(dev, file_priv); + if (retcode) + goto done; } } diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index a263b7070fc..9d3a5030b6e 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -34,6 +34,7 @@ */ #include "drmP.h" +#include "drm_trace.h" #include <linux/interrupt.h> /* For task queue support */ #include <linux/slab.h> @@ -57,6 +58,9 @@ int drm_irq_by_busid(struct drm_device *dev, void *data, { struct drm_irq_busid *p = data; + if (drm_core_check_feature(dev, DRIVER_USE_PLATFORM_DEVICE)) + return -EINVAL; + if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) return -EINVAL; @@ -211,7 +215,7 @@ int drm_irq_install(struct drm_device *dev) if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ)) return -EINVAL; - if (dev->pdev->irq == 0) + if (drm_dev_to_irq(dev) == 0) return -EINVAL; mutex_lock(&dev->struct_mutex); @@ -229,7 +233,7 @@ int drm_irq_install(struct drm_device *dev) dev->irq_enabled = 1; mutex_unlock(&dev->struct_mutex); - DRM_DEBUG("irq=%d\n", dev->pdev->irq); + DRM_DEBUG("irq=%d\n", drm_dev_to_irq(dev)); /* Before installing handler */ dev->driver->irq_preinstall(dev); @@ -302,14 +306,14 @@ int drm_irq_uninstall(struct drm_device * dev) if (!irq_enabled) return -EINVAL; - DRM_DEBUG("irq=%d\n", dev->pdev->irq); + DRM_DEBUG("irq=%d\n", drm_dev_to_irq(dev)); if (!drm_core_check_feature(dev, DRIVER_MODESET)) vga_client_register(dev->pdev, NULL, NULL, NULL); dev->driver->irq_uninstall(dev); - free_irq(dev->pdev->irq, dev); + free_irq(drm_dev_to_irq(dev), dev); return 0; } @@ -341,7 +345,7 @@ int drm_control(struct drm_device *dev, void *data, if (drm_core_check_feature(dev, DRIVER_MODESET)) return 0; if (dev->if_version < DRM_IF_VERSION(1, 2) && - ctl->irq != dev->pdev->irq) + ctl->irq != drm_dev_to_irq(dev)) return -EINVAL; return drm_irq_install(dev); case DRM_UNINST_HANDLER: @@ -587,6 +591,7 @@ static int drm_queue_vblank_event(struct drm_device *dev, int pipe, return -ENOMEM; e->pipe = pipe; + e->base.pid = current->pid; e->event.base.type = DRM_EVENT_VBLANK; e->event.base.length = sizeof e->event; e->event.user_data = vblwait->request.signal; @@ -614,6 +619,9 @@ static int drm_queue_vblank_event(struct drm_device *dev, int pipe, DRM_DEBUG("event on vblank count %d, current %d, crtc %d\n", vblwait->request.sequence, seq, pipe); + trace_drm_vblank_event_queued(current->pid, pipe, + vblwait->request.sequence); + e->event.sequence = vblwait->request.sequence; if ((seq - vblwait->request.sequence) <= (1 << 23)) { e->event.tv_sec = now.tv_sec; @@ -621,6 +629,8 @@ static int drm_queue_vblank_event(struct drm_device *dev, int pipe, drm_vblank_put(dev, e->pipe); list_add_tail(&e->base.link, &e->base.file_priv->event_list); wake_up_interruptible(&e->base.file_priv->event_wait); + trace_drm_vblank_event_delivered(current->pid, pipe, + vblwait->request.sequence); } else { list_add_tail(&e->base.link, &dev->vblank_event_list); } @@ -651,7 +661,7 @@ int drm_wait_vblank(struct drm_device *dev, void *data, int ret = 0; unsigned int flags, seq, crtc; - if ((!dev->pdev->irq) || (!dev->irq_enabled)) + if ((!drm_dev_to_irq(dev)) || (!dev->irq_enabled)) return -EINVAL; if (vblwait->request.type & _DRM_VBLANK_SIGNAL) @@ -751,9 +761,13 @@ void drm_handle_vblank_events(struct drm_device *dev, int crtc) drm_vblank_put(dev, e->pipe); list_move_tail(&e->base.link, &e->base.file_priv->event_list); wake_up_interruptible(&e->base.file_priv->event_wait); + trace_drm_vblank_event_delivered(e->base.pid, e->pipe, + e->event.sequence); } spin_unlock_irqrestore(&dev->event_lock, flags); + + trace_drm_vblank_event(crtc, seq); } /** diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 2ac074c8f5d..da99edc5088 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -48,44 +48,14 @@ #define MM_UNUSED_TARGET 4 -unsigned long drm_mm_tail_space(struct drm_mm *mm) -{ - struct list_head *tail_node; - struct drm_mm_node *entry; - - tail_node = mm->ml_entry.prev; - entry = list_entry(tail_node, struct drm_mm_node, ml_entry); - if (!entry->free) - return 0; - - return entry->size; -} - -int drm_mm_remove_space_from_tail(struct drm_mm *mm, unsigned long size) -{ - struct list_head *tail_node; - struct drm_mm_node *entry; - - tail_node = mm->ml_entry.prev; - entry = list_entry(tail_node, struct drm_mm_node, ml_entry); - if (!entry->free) - return -ENOMEM; - - if (entry->size <= size) - return -ENOMEM; - - entry->size -= size; - return 0; -} - static struct drm_mm_node *drm_mm_kmalloc(struct drm_mm *mm, int atomic) { struct drm_mm_node *child; if (atomic) - child = kmalloc(sizeof(*child), GFP_ATOMIC); + child = kzalloc(sizeof(*child), GFP_ATOMIC); else - child = kmalloc(sizeof(*child), GFP_KERNEL); + child = kzalloc(sizeof(*child), GFP_KERNEL); if (unlikely(child == NULL)) { spin_lock(&mm->unused_lock); @@ -94,8 +64,8 @@ static struct drm_mm_node *drm_mm_kmalloc(struct drm_mm *mm, int atomic) else { child = list_entry(mm->unused_nodes.next, - struct drm_mm_node, fl_entry); - list_del(&child->fl_entry); + struct drm_mm_node, free_stack); + list_del(&child->free_stack); --mm->num_unused; } spin_unlock(&mm->unused_lock); @@ -115,7 +85,7 @@ int drm_mm_pre_get(struct drm_mm *mm) spin_lock(&mm->unused_lock); while (mm->num_unused < MM_UNUSED_TARGET) { spin_unlock(&mm->unused_lock); - node = kmalloc(sizeof(*node), GFP_KERNEL); + node = kzalloc(sizeof(*node), GFP_KERNEL); spin_lock(&mm->unused_lock); if (unlikely(node == NULL)) { @@ -124,7 +94,7 @@ int drm_mm_pre_get(struct drm_mm *mm) return ret; } ++mm->num_unused; - list_add_tail(&node->fl_entry, &mm->unused_nodes); + list_add_tail(&node->free_stack, &mm->unused_nodes); } spin_unlock(&mm->unused_lock); return 0; @@ -146,27 +116,12 @@ static int drm_mm_create_tail_node(struct drm_mm *mm, child->start = start; child->mm = mm; - list_add_tail(&child->ml_entry, &mm->ml_entry); - list_add_tail(&child->fl_entry, &mm->fl_entry); + list_add_tail(&child->node_list, &mm->node_list); + list_add_tail(&child->free_stack, &mm->free_stack); return 0; } -int drm_mm_add_space_to_tail(struct drm_mm *mm, unsigned long size, int atomic) -{ - struct list_head *tail_node; - struct drm_mm_node *entry; - - tail_node = mm->ml_entry.prev; - entry = list_entry(tail_node, struct drm_mm_node, ml_entry); - if (!entry->free) { - return drm_mm_create_tail_node(mm, entry->start + entry->size, - size, atomic); - } - entry->size += size; - return 0; -} - static struct drm_mm_node *drm_mm_split_at_start(struct drm_mm_node *parent, unsigned long size, int atomic) @@ -177,15 +132,14 @@ static struct drm_mm_node *drm_mm_split_at_start(struct drm_mm_node *parent, if (unlikely(child == NULL)) return NULL; - INIT_LIST_HEAD(&child->fl_entry); + INIT_LIST_HEAD(&child->free_stack); - child->free = 0; child->size = size; child->start = parent->start; child->mm = parent->mm; - list_add_tail(&child->ml_entry, &parent->ml_entry); - INIT_LIST_HEAD(&child->fl_entry); + list_add_tail(&child->node_list, &parent->node_list); + INIT_LIST_HEAD(&child->free_stack); parent->size -= size; parent->start += size; @@ -213,7 +167,7 @@ struct drm_mm_node *drm_mm_get_block_generic(struct drm_mm_node *node, } if (node->size == size) { - list_del_init(&node->fl_entry); + list_del_init(&node->free_stack); node->free = 0; } else { node = drm_mm_split_at_start(node, size, atomic); @@ -251,7 +205,7 @@ struct drm_mm_node *drm_mm_get_block_range_generic(struct drm_mm_node *node, } if (node->size == size) { - list_del_init(&node->fl_entry); + list_del_init(&node->free_stack); node->free = 0; } else { node = drm_mm_split_at_start(node, size, atomic); @@ -273,16 +227,19 @@ void drm_mm_put_block(struct drm_mm_node *cur) { struct drm_mm *mm = cur->mm; - struct list_head *cur_head = &cur->ml_entry; - struct list_head *root_head = &mm->ml_entry; + struct list_head *cur_head = &cur->node_list; + struct list_head *root_head = &mm->node_list; struct drm_mm_node *prev_node = NULL; struct drm_mm_node *next_node; int merged = 0; + BUG_ON(cur->scanned_block || cur->scanned_prev_free + || cur->scanned_next_free); + if (cur_head->prev != root_head) { prev_node = - list_entry(cur_head->prev, struct drm_mm_node, ml_entry); + list_entry(cur_head->prev, struct drm_mm_node, node_list); if (prev_node->free) { prev_node->size += cur->size; merged = 1; @@ -290,15 +247,15 @@ void drm_mm_put_block(struct drm_mm_node *cur) } if (cur_head->next != root_head) { next_node = - list_entry(cur_head->next, struct drm_mm_node, ml_entry); + list_entry(cur_head->next, struct drm_mm_node, node_list); if (next_node->free) { if (merged) { prev_node->size += next_node->size; - list_del(&next_node->ml_entry); - list_del(&next_node->fl_entry); + list_del(&next_node->node_list); + list_del(&next_node->free_stack); spin_lock(&mm->unused_lock); if (mm->num_unused < MM_UNUSED_TARGET) { - list_add(&next_node->fl_entry, + list_add(&next_node->free_stack, &mm->unused_nodes); ++mm->num_unused; } else @@ -313,12 +270,12 @@ void drm_mm_put_block(struct drm_mm_node *cur) } if (!merged) { cur->free = 1; - list_add(&cur->fl_entry, &mm->fl_entry); + list_add(&cur->free_stack, &mm->free_stack); } else { - list_del(&cur->ml_entry); + list_del(&cur->node_list); spin_lock(&mm->unused_lock); if (mm->num_unused < MM_UNUSED_TARGET) { - list_add(&cur->fl_entry, &mm->unused_nodes); + list_add(&cur->free_stack, &mm->unused_nodes); ++mm->num_unused; } else kfree(cur); @@ -328,40 +285,50 @@ void drm_mm_put_block(struct drm_mm_node *cur) EXPORT_SYMBOL(drm_mm_put_block); +static int check_free_mm_node(struct drm_mm_node *entry, unsigned long size, + unsigned alignment) +{ + unsigned wasted = 0; + + if (entry->size < size) + return 0; + + if (alignment) { + register unsigned tmp = entry->start % alignment; + if (tmp) + wasted = alignment - tmp; + } + + if (entry->size >= size + wasted) { + return 1; + } + + return 0; +} + struct drm_mm_node *drm_mm_search_free(const struct drm_mm *mm, unsigned long size, unsigned alignment, int best_match) { - struct list_head *list; - const struct list_head *free_stack = &mm->fl_entry; struct drm_mm_node *entry; struct drm_mm_node *best; unsigned long best_size; - unsigned wasted; + + BUG_ON(mm->scanned_blocks); best = NULL; best_size = ~0UL; - list_for_each(list, free_stack) { - entry = list_entry(list, struct drm_mm_node, fl_entry); - wasted = 0; - - if (entry->size < size) + list_for_each_entry(entry, &mm->free_stack, free_stack) { + if (!check_free_mm_node(entry, size, alignment)) continue; - if (alignment) { - register unsigned tmp = entry->start % alignment; - if (tmp) - wasted += alignment - tmp; - } + if (!best_match) + return entry; - if (entry->size >= size + wasted) { - if (!best_match) - return entry; - if (entry->size < best_size) { - best = entry; - best_size = entry->size; - } + if (entry->size < best_size) { + best = entry; + best_size = entry->size; } } @@ -376,43 +343,28 @@ struct drm_mm_node *drm_mm_search_free_in_range(const struct drm_mm *mm, unsigned long end, int best_match) { - struct list_head *list; - const struct list_head *free_stack = &mm->fl_entry; struct drm_mm_node *entry; struct drm_mm_node *best; unsigned long best_size; - unsigned wasted; + + BUG_ON(mm->scanned_blocks); best = NULL; best_size = ~0UL; - list_for_each(list, free_stack) { - entry = list_entry(list, struct drm_mm_node, fl_entry); - wasted = 0; - - if (entry->size < size) - continue; - + list_for_each_entry(entry, &mm->free_stack, free_stack) { if (entry->start > end || (entry->start+entry->size) < start) continue; - if (entry->start < start) - wasted += start - entry->start; + if (!check_free_mm_node(entry, size, alignment)) + continue; - if (alignment) { - register unsigned tmp = (entry->start + wasted) % alignment; - if (tmp) - wasted += alignment - tmp; - } + if (!best_match) + return entry; - if (entry->size >= size + wasted && - (entry->start + wasted + size) <= end) { - if (!best_match) - return entry; - if (entry->size < best_size) { - best = entry; - best_size = entry->size; - } + if (entry->size < best_size) { + best = entry; + best_size = entry->size; } } @@ -420,9 +372,161 @@ struct drm_mm_node *drm_mm_search_free_in_range(const struct drm_mm *mm, } EXPORT_SYMBOL(drm_mm_search_free_in_range); +/** + * Initializa lru scanning. + * + * This simply sets up the scanning routines with the parameters for the desired + * hole. + * + * Warning: As long as the scan list is non-empty, no other operations than + * adding/removing nodes to/from the scan list are allowed. + */ +void drm_mm_init_scan(struct drm_mm *mm, unsigned long size, + unsigned alignment) +{ + mm->scan_alignment = alignment; + mm->scan_size = size; + mm->scanned_blocks = 0; + mm->scan_hit_start = 0; + mm->scan_hit_size = 0; +} +EXPORT_SYMBOL(drm_mm_init_scan); + +/** + * Add a node to the scan list that might be freed to make space for the desired + * hole. + * + * Returns non-zero, if a hole has been found, zero otherwise. + */ +int drm_mm_scan_add_block(struct drm_mm_node *node) +{ + struct drm_mm *mm = node->mm; + struct list_head *prev_free, *next_free; + struct drm_mm_node *prev_node, *next_node; + + mm->scanned_blocks++; + + prev_free = next_free = NULL; + + BUG_ON(node->free); + node->scanned_block = 1; + node->free = 1; + + if (node->node_list.prev != &mm->node_list) { + prev_node = list_entry(node->node_list.prev, struct drm_mm_node, + node_list); + + if (prev_node->free) { + list_del(&prev_node->node_list); + + node->start = prev_node->start; + node->size += prev_node->size; + + prev_node->scanned_prev_free = 1; + + prev_free = &prev_node->free_stack; + } + } + + if (node->node_list.next != &mm->node_list) { + next_node = list_entry(node->node_list.next, struct drm_mm_node, + node_list); + + if (next_node->free) { + list_del(&next_node->node_list); + + node->size += next_node->size; + + next_node->scanned_next_free = 1; + + next_free = &next_node->free_stack; + } + } + + /* The free_stack list is not used for allocated objects, so these two + * pointers can be abused (as long as no allocations in this memory + * manager happens). */ + node->free_stack.prev = prev_free; + node->free_stack.next = next_free; + + if (check_free_mm_node(node, mm->scan_size, mm->scan_alignment)) { + mm->scan_hit_start = node->start; + mm->scan_hit_size = node->size; + + return 1; + } + + return 0; +} +EXPORT_SYMBOL(drm_mm_scan_add_block); + +/** + * Remove a node from the scan list. + * + * Nodes _must_ be removed in the exact same order from the scan list as they + * have been added, otherwise the internal state of the memory manager will be + * corrupted. + * + * When the scan list is empty, the selected memory nodes can be freed. An + * immediatly following drm_mm_search_free with best_match = 0 will then return + * the just freed block (because its at the top of the free_stack list). + * + * Returns one if this block should be evicted, zero otherwise. Will always + * return zero when no hole has been found. + */ +int drm_mm_scan_remove_block(struct drm_mm_node *node) +{ + struct drm_mm *mm = node->mm; + struct drm_mm_node *prev_node, *next_node; + + mm->scanned_blocks--; + + BUG_ON(!node->scanned_block); + node->scanned_block = 0; + node->free = 0; + + prev_node = list_entry(node->free_stack.prev, struct drm_mm_node, + free_stack); + next_node = list_entry(node->free_stack.next, struct drm_mm_node, + free_stack); + + if (prev_node) { + BUG_ON(!prev_node->scanned_prev_free); + prev_node->scanned_prev_free = 0; + + list_add_tail(&prev_node->node_list, &node->node_list); + + node->start = prev_node->start + prev_node->size; + node->size -= prev_node->size; + } + + if (next_node) { + BUG_ON(!next_node->scanned_next_free); + next_node->scanned_next_free = 0; + + list_add(&next_node->node_list, &node->node_list); + + node->size -= next_node->size; + } + + INIT_LIST_HEAD(&node->free_stack); + + /* Only need to check for containement because start&size for the + * complete resulting free block (not just the desired part) is + * stored. */ + if (node->start >= mm->scan_hit_start && + node->start + node->size + <= mm->scan_hit_start + mm->scan_hit_size) { + return 1; + } + + return 0; +} +EXPORT_SYMBOL(drm_mm_scan_remove_block); + int drm_mm_clean(struct drm_mm * mm) { - struct list_head *head = &mm->ml_entry; + struct list_head *head = &mm->node_list; return (head->next->next == head); } @@ -430,10 +534,11 @@ EXPORT_SYMBOL(drm_mm_clean); int drm_mm_init(struct drm_mm * mm, unsigned long start, unsigned long size) { - INIT_LIST_HEAD(&mm->ml_entry); - INIT_LIST_HEAD(&mm->fl_entry); + INIT_LIST_HEAD(&mm->node_list); + INIT_LIST_HEAD(&mm->free_stack); INIT_LIST_HEAD(&mm->unused_nodes); mm->num_unused = 0; + mm->scanned_blocks = 0; spin_lock_init(&mm->unused_lock); return drm_mm_create_tail_node(mm, start, size, 0); @@ -442,25 +547,25 @@ EXPORT_SYMBOL(drm_mm_init); void drm_mm_takedown(struct drm_mm * mm) { - struct list_head *bnode = mm->fl_entry.next; + struct list_head *bnode = mm->free_stack.next; struct drm_mm_node *entry; struct drm_mm_node *next; - entry = list_entry(bnode, struct drm_mm_node, fl_entry); + entry = list_entry(bnode, struct drm_mm_node, free_stack); - if (entry->ml_entry.next != &mm->ml_entry || - entry->fl_entry.next != &mm->fl_entry) { + if (entry->node_list.next != &mm->node_list || + entry->free_stack.next != &mm->free_stack) { DRM_ERROR("Memory manager not clean. Delaying takedown\n"); return; } - list_del(&entry->fl_entry); - list_del(&entry->ml_entry); + list_del(&entry->free_stack); + list_del(&entry->node_list); kfree(entry); spin_lock(&mm->unused_lock); - list_for_each_entry_safe(entry, next, &mm->unused_nodes, fl_entry) { - list_del(&entry->fl_entry); + list_for_each_entry_safe(entry, next, &mm->unused_nodes, free_stack) { + list_del(&entry->free_stack); kfree(entry); --mm->num_unused; } @@ -475,7 +580,7 @@ void drm_mm_debug_table(struct drm_mm *mm, const char *prefix) struct drm_mm_node *entry; int total_used = 0, total_free = 0, total = 0; - list_for_each_entry(entry, &mm->ml_entry, ml_entry) { + list_for_each_entry(entry, &mm->node_list, node_list) { printk(KERN_DEBUG "%s 0x%08lx-0x%08lx: %8ld: %s\n", prefix, entry->start, entry->start + entry->size, entry->size, entry->free ? "free" : "used"); @@ -496,7 +601,7 @@ int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm) struct drm_mm_node *entry; int total_used = 0, total_free = 0, total = 0; - list_for_each_entry(entry, &mm->ml_entry, ml_entry) { + list_for_each_entry(entry, &mm->node_list, node_list) { seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: %s\n", entry->start, entry->start + entry->size, entry->size, entry->free ? "free" : "used"); total += entry->size; if (entry->free) diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c index 2ea9ad4a8d6..e20f78b542a 100644 --- a/drivers/gpu/drm/drm_pci.c +++ b/drivers/gpu/drm/drm_pci.c @@ -124,4 +124,147 @@ void drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah) EXPORT_SYMBOL(drm_pci_free); +#ifdef CONFIG_PCI +/** + * Register. + * + * \param pdev - PCI device structure + * \param ent entry from the PCI ID table with device type flags + * \return zero on success or a negative number on failure. + * + * Attempt to gets inter module "drm" information. If we are first + * then register the character device and inter module information. + * Try and register, if we fail to register, backout previous work. + */ +int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent, + struct drm_driver *driver) +{ + struct drm_device *dev; + int ret; + + DRM_DEBUG("\n"); + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + ret = pci_enable_device(pdev); + if (ret) + goto err_g1; + + pci_set_master(pdev); + + dev->pdev = pdev; + dev->dev = &pdev->dev; + + dev->pci_device = pdev->device; + dev->pci_vendor = pdev->vendor; + +#ifdef __alpha__ + dev->hose = pdev->sysdata; +#endif + + if ((ret = drm_fill_in_dev(dev, ent, driver))) { + printk(KERN_ERR "DRM: Fill_in_dev failed.\n"); + goto err_g2; + } + + if (drm_core_check_feature(dev, DRIVER_MODESET)) { + pci_set_drvdata(pdev, dev); + ret = drm_get_minor(dev, &dev->control, DRM_MINOR_CONTROL); + if (ret) + goto err_g2; + } + + if ((ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY))) + goto err_g3; + + if (dev->driver->load) { + ret = dev->driver->load(dev, ent->driver_data); + if (ret) + goto err_g4; + } + + /* setup the grouping for the legacy output */ + if (drm_core_check_feature(dev, DRIVER_MODESET)) { + ret = drm_mode_group_init_legacy_group(dev, + &dev->primary->mode_group); + if (ret) + goto err_g4; + } + + list_add_tail(&dev->driver_item, &driver->device_list); + + DRM_INFO("Initialized %s %d.%d.%d %s for %s on minor %d\n", + driver->name, driver->major, driver->minor, driver->patchlevel, + driver->date, pci_name(pdev), dev->primary->index); + + return 0; + +err_g4: + drm_put_minor(&dev->primary); +err_g3: + if (drm_core_check_feature(dev, DRIVER_MODESET)) + drm_put_minor(&dev->control); +err_g2: + pci_disable_device(pdev); +err_g1: + kfree(dev); + return ret; +} +EXPORT_SYMBOL(drm_get_pci_dev); + +/** + * PCI device initialization. Called via drm_init at module load time, + * + * \return zero on success or a negative number on failure. + * + * Initializes a drm_device structures,registering the + * stubs and initializing the AGP device. + * + * Expands the \c DRIVER_PREINIT and \c DRIVER_POST_INIT macros before and + * after the initialization for driver customization. + */ +int drm_pci_init(struct drm_driver *driver) +{ + struct pci_dev *pdev = NULL; + const struct pci_device_id *pid; + int i; + + if (driver->driver_features & DRIVER_MODESET) + return pci_register_driver(&driver->pci_driver); + + /* If not using KMS, fall back to stealth mode manual scanning. */ + for (i = 0; driver->pci_driver.id_table[i].vendor != 0; i++) { + pid = &driver->pci_driver.id_table[i]; + + /* Loop around setting up a DRM device for each PCI device + * matching our ID and device class. If we had the internal + * function that pci_get_subsys and pci_get_class used, we'd + * be able to just pass pid in instead of doing a two-stage + * thing. + */ + pdev = NULL; + while ((pdev = + pci_get_subsys(pid->vendor, pid->device, pid->subvendor, + pid->subdevice, pdev)) != NULL) { + if ((pdev->class & pid->class_mask) != pid->class) + continue; + + /* stealth mode requires a manual probe */ + pci_dev_get(pdev); + drm_get_pci_dev(pdev, pid, driver); + } + } + return 0; +} + +#else + +int drm_pci_init(struct drm_driver *driver) +{ + return -1; +} + +#endif /*@}*/ diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c new file mode 100644 index 00000000000..460e9a3afa8 --- /dev/null +++ b/drivers/gpu/drm/drm_platform.c @@ -0,0 +1,122 @@ +/* + * Derived from drm_pci.c + * + * Copyright 2003 José Fonseca. + * Copyright 2003 Leif Delgass. + * Copyright (c) 2009, Code Aurora Forum. + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION + * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + */ + +#include "drmP.h" + +/** + * Register. + * + * \param platdev - Platform device struture + * \return zero on success or a negative number on failure. + * + * Attempt to gets inter module "drm" information. If we are first + * then register the character device and inter module information. + * Try and register, if we fail to register, backout previous work. + */ + +int drm_get_platform_dev(struct platform_device *platdev, + struct drm_driver *driver) +{ + struct drm_device *dev; + int ret; + + DRM_DEBUG("\n"); + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + dev->platformdev = platdev; + dev->dev = &platdev->dev; + + ret = drm_fill_in_dev(dev, NULL, driver); + + if (ret) { + printk(KERN_ERR "DRM: Fill_in_dev failed.\n"); + goto err_g1; + } + + if (drm_core_check_feature(dev, DRIVER_MODESET)) { + dev_set_drvdata(&platdev->dev, dev); + ret = drm_get_minor(dev, &dev->control, DRM_MINOR_CONTROL); + if (ret) + goto err_g1; + } + + ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY); + if (ret) + goto err_g2; + + if (dev->driver->load) { + ret = dev->driver->load(dev, 0); + if (ret) + goto err_g3; + } + + /* setup the grouping for the legacy output */ + if (drm_core_check_feature(dev, DRIVER_MODESET)) { + ret = drm_mode_group_init_legacy_group(dev, + &dev->primary->mode_group); + if (ret) + goto err_g3; + } + + list_add_tail(&dev->driver_item, &driver->device_list); + + DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n", + driver->name, driver->major, driver->minor, driver->patchlevel, + driver->date, dev->primary->index); + + return 0; + +err_g3: + drm_put_minor(&dev->primary); +err_g2: + if (drm_core_check_feature(dev, DRIVER_MODESET)) + drm_put_minor(&dev->control); +err_g1: + kfree(dev); + return ret; +} +EXPORT_SYMBOL(drm_get_platform_dev); + +/** + * Platform device initialization. Called via drm_init at module load time, + * + * \return zero on success or a negative number on failure. + * + * Initializes a drm_device structures,registering the + * stubs + * + * Expands the \c DRIVER_PREINIT and \c DRIVER_POST_INIT macros before and + * after the initialization for driver customization. + */ + +int drm_platform_init(struct drm_driver *driver) +{ + return drm_get_platform_dev(driver->platform_device, driver); +} diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c index a0c365f2e52..d1ad57450df 100644 --- a/drivers/gpu/drm/drm_stub.c +++ b/drivers/gpu/drm/drm_stub.c @@ -156,6 +156,9 @@ static void drm_master_destroy(struct kref *kref) master->unique_len = 0; } + kfree(dev->devname); + dev->devname = NULL; + list_for_each_entry_safe(pt, next, &master->magicfree, head) { list_del(&pt->head); drm_ht_remove_item(&master->magiclist, &pt->hash_item); @@ -224,7 +227,7 @@ int drm_dropmaster_ioctl(struct drm_device *dev, void *data, return 0; } -static int drm_fill_in_dev(struct drm_device * dev, struct pci_dev *pdev, +int drm_fill_in_dev(struct drm_device *dev, const struct pci_device_id *ent, struct drm_driver *driver) { @@ -245,14 +248,6 @@ static int drm_fill_in_dev(struct drm_device * dev, struct pci_dev *pdev, idr_init(&dev->drw_idr); - dev->pdev = pdev; - dev->pci_device = pdev->device; - dev->pci_vendor = pdev->vendor; - -#ifdef __alpha__ - dev->hose = pdev->sysdata; -#endif - if (drm_ht_create(&dev->map_hash, 12)) { return -ENOMEM; } @@ -321,7 +316,7 @@ static int drm_fill_in_dev(struct drm_device * dev, struct pci_dev *pdev, * create the proc init entry via proc_init(). This routines assigns * minor numbers to secondary heads of multi-headed cards */ -static int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type) +int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type) { struct drm_minor *new_minor; int ret; @@ -388,83 +383,6 @@ err_idr: } /** - * Register. - * - * \param pdev - PCI device structure - * \param ent entry from the PCI ID table with device type flags - * \return zero on success or a negative number on failure. - * - * Attempt to gets inter module "drm" information. If we are first - * then register the character device and inter module information. - * Try and register, if we fail to register, backout previous work. - */ -int drm_get_dev(struct pci_dev *pdev, const struct pci_device_id *ent, - struct drm_driver *driver) -{ - struct drm_device *dev; - int ret; - - DRM_DEBUG("\n"); - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return -ENOMEM; - - ret = pci_enable_device(pdev); - if (ret) - goto err_g1; - - pci_set_master(pdev); - if ((ret = drm_fill_in_dev(dev, pdev, ent, driver))) { - printk(KERN_ERR "DRM: Fill_in_dev failed.\n"); - goto err_g2; - } - - if (drm_core_check_feature(dev, DRIVER_MODESET)) { - pci_set_drvdata(pdev, dev); - ret = drm_get_minor(dev, &dev->control, DRM_MINOR_CONTROL); - if (ret) - goto err_g2; - } - - if ((ret = drm_get_minor(dev, &dev->primary, DRM_MINOR_LEGACY))) - goto err_g3; - - if (dev->driver->load) { - ret = dev->driver->load(dev, ent->driver_data); - if (ret) - goto err_g4; - } - - /* setup the grouping for the legacy output */ - if (drm_core_check_feature(dev, DRIVER_MODESET)) { - ret = drm_mode_group_init_legacy_group(dev, &dev->primary->mode_group); - if (ret) - goto err_g4; - } - - list_add_tail(&dev->driver_item, &driver->device_list); - - DRM_INFO("Initialized %s %d.%d.%d %s for %s on minor %d\n", - driver->name, driver->major, driver->minor, driver->patchlevel, - driver->date, pci_name(pdev), dev->primary->index); - - return 0; - -err_g4: - drm_put_minor(&dev->primary); -err_g3: - if (drm_core_check_feature(dev, DRIVER_MODESET)) - drm_put_minor(&dev->control); -err_g2: - pci_disable_device(pdev); -err_g1: - kfree(dev); - return ret; -} -EXPORT_SYMBOL(drm_get_dev); - -/** * Put a secondary minor number. * * \param sec_minor - structure to be released diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c index 101d381e9d8..86118a74223 100644 --- a/drivers/gpu/drm/drm_sysfs.c +++ b/drivers/gpu/drm/drm_sysfs.c @@ -489,7 +489,8 @@ int drm_sysfs_device_add(struct drm_minor *minor) int err; char *minor_str; - minor->kdev.parent = &minor->dev->pdev->dev; + minor->kdev.parent = minor->dev->dev; + minor->kdev.class = drm_class; minor->kdev.release = drm_sysfs_device_release; minor->kdev.devt = minor->device; diff --git a/drivers/gpu/drm/drm_trace.h b/drivers/gpu/drm/drm_trace.h new file mode 100644 index 00000000000..03ea964aa60 --- /dev/null +++ b/drivers/gpu/drm/drm_trace.h @@ -0,0 +1,66 @@ +#if !defined(_DRM_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _DRM_TRACE_H_ + +#include <linux/stringify.h> +#include <linux/types.h> +#include <linux/tracepoint.h> + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM drm +#define TRACE_SYSTEM_STRING __stringify(TRACE_SYSTEM) +#define TRACE_INCLUDE_FILE drm_trace + +TRACE_EVENT(drm_vblank_event, + TP_PROTO(int crtc, unsigned int seq), + TP_ARGS(crtc, seq), + TP_STRUCT__entry( + __field(int, crtc) + __field(unsigned int, seq) + ), + TP_fast_assign( + __entry->crtc = crtc; + __entry->seq = seq; + ), + TP_printk("crtc=%d, seq=%d", __entry->crtc, __entry->seq) +); + +TRACE_EVENT(drm_vblank_event_queued, + TP_PROTO(pid_t pid, int crtc, unsigned int seq), + TP_ARGS(pid, crtc, seq), + TP_STRUCT__entry( + __field(pid_t, pid) + __field(int, crtc) + __field(unsigned int, seq) + ), + TP_fast_assign( + __entry->pid = pid; + __entry->crtc = crtc; + __entry->seq = seq; + ), + TP_printk("pid=%d, crtc=%d, seq=%d", __entry->pid, __entry->crtc, \ + __entry->seq) +); + +TRACE_EVENT(drm_vblank_event_delivered, + TP_PROTO(pid_t pid, int crtc, unsigned int seq), + TP_ARGS(pid, crtc, seq), + TP_STRUCT__entry( + __field(pid_t, pid) + __field(int, crtc) + __field(unsigned int, seq) + ), + TP_fast_assign( + __entry->pid = pid; + __entry->crtc = crtc; + __entry->seq = seq; + ), + TP_printk("pid=%d, crtc=%d, seq=%d", __entry->pid, __entry->crtc, \ + __entry->seq) +); + +#endif /* _DRM_TRACE_H_ */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#include <trace/define_trace.h> diff --git a/drivers/gpu/drm/drm_trace_points.c b/drivers/gpu/drm/drm_trace_points.c new file mode 100644 index 00000000000..0d0eb90864a --- /dev/null +++ b/drivers/gpu/drm/drm_trace_points.c @@ -0,0 +1,4 @@ +#include "drmP.h" + +#define CREATE_TRACE_POINTS +#include "drm_trace.h" diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c index c3b13fb41d0..3778360ecee 100644 --- a/drivers/gpu/drm/drm_vm.c +++ b/drivers/gpu/drm/drm_vm.c @@ -61,7 +61,7 @@ static pgprot_t drm_io_prot(uint32_t map_type, struct vm_area_struct *vma) tmp = pgprot_writecombine(tmp); else tmp = pgprot_noncached(tmp); -#elif defined(__sparc__) +#elif defined(__sparc__) || defined(__arm__) tmp = pgprot_noncached(tmp); #endif return tmp; @@ -601,6 +601,7 @@ int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma) } switch (map->type) { +#if !defined(__arm__) case _DRM_AGP: if (drm_core_has_AGP(dev) && dev->agp->cant_use_aperture) { /* @@ -615,20 +616,31 @@ int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma) break; } /* fall through to _DRM_FRAME_BUFFER... */ +#endif case _DRM_FRAME_BUFFER: case _DRM_REGISTERS: offset = dev->driver->get_reg_ofs(dev); vma->vm_flags |= VM_IO; /* not in core dump */ vma->vm_page_prot = drm_io_prot(map->type, vma); +#if !defined(__arm__) if (io_remap_pfn_range(vma, vma->vm_start, (map->offset + offset) >> PAGE_SHIFT, vma->vm_end - vma->vm_start, vma->vm_page_prot)) return -EAGAIN; +#else + if (remap_pfn_range(vma, vma->vm_start, + (map->offset + offset) >> PAGE_SHIFT, + vma->vm_end - vma->vm_start, + vma->vm_page_prot)) + return -EAGAIN; +#endif + DRM_DEBUG(" Type = %d; start = 0x%lx, end = 0x%lx," " offset = 0x%llx\n", map->type, vma->vm_start, vma->vm_end, (unsigned long long)(map->offset + offset)); + vma->vm_ops = &drm_vm_ops; break; case _DRM_CONSISTENT: diff --git a/drivers/gpu/drm/i2c/Makefile b/drivers/gpu/drm/i2c/Makefile index 6d2abaf35ba..92862563e7e 100644 --- a/drivers/gpu/drm/i2c/Makefile +++ b/drivers/gpu/drm/i2c/Makefile @@ -2,3 +2,6 @@ ccflags-y := -Iinclude/drm ch7006-y := ch7006_drv.o ch7006_mode.o obj-$(CONFIG_DRM_I2C_CH7006) += ch7006.o + +sil164-y := sil164_drv.o +obj-$(CONFIG_DRM_I2C_SIL164) += sil164.o diff --git a/drivers/gpu/drm/i2c/ch7006_drv.c b/drivers/gpu/drm/i2c/ch7006_drv.c index 81681a07a80..833b35f44a7 100644 --- a/drivers/gpu/drm/i2c/ch7006_drv.c +++ b/drivers/gpu/drm/i2c/ch7006_drv.c @@ -33,7 +33,7 @@ static void ch7006_encoder_set_config(struct drm_encoder *encoder, { struct ch7006_priv *priv = to_ch7006_priv(encoder); - priv->params = params; + priv->params = *(struct ch7006_encoder_params *)params; } static void ch7006_encoder_destroy(struct drm_encoder *encoder) @@ -114,7 +114,7 @@ static void ch7006_encoder_mode_set(struct drm_encoder *encoder, { struct i2c_client *client = drm_i2c_encoder_get_client(encoder); struct ch7006_priv *priv = to_ch7006_priv(encoder); - struct ch7006_encoder_params *params = priv->params; + struct ch7006_encoder_params *params = &priv->params; struct ch7006_state *state = &priv->state; uint8_t *regs = state->regs; struct ch7006_mode *mode = priv->mode; @@ -428,6 +428,22 @@ static int ch7006_remove(struct i2c_client *client) return 0; } +static int ch7006_suspend(struct i2c_client *client, pm_message_t mesg) +{ + ch7006_dbg(client, "\n"); + + return 0; +} + +static int ch7006_resume(struct i2c_client *client) +{ + ch7006_dbg(client, "\n"); + + ch7006_write(client, 0x3d, 0x0); + + return 0; +} + static int ch7006_encoder_init(struct i2c_client *client, struct drm_device *dev, struct drm_encoder_slave *encoder) @@ -487,6 +503,8 @@ static struct drm_i2c_encoder_driver ch7006_driver = { .i2c_driver = { .probe = ch7006_probe, .remove = ch7006_remove, + .suspend = ch7006_suspend, + .resume = ch7006_resume, .driver = { .name = "ch7006", diff --git a/drivers/gpu/drm/i2c/ch7006_priv.h b/drivers/gpu/drm/i2c/ch7006_priv.h index b06d3d93d8a..1c6d2e3bd96 100644 --- a/drivers/gpu/drm/i2c/ch7006_priv.h +++ b/drivers/gpu/drm/i2c/ch7006_priv.h @@ -77,7 +77,7 @@ struct ch7006_state { }; struct ch7006_priv { - struct ch7006_encoder_params *params; + struct ch7006_encoder_params params; struct ch7006_mode *mode; struct ch7006_state state; diff --git a/drivers/gpu/drm/i2c/sil164_drv.c b/drivers/gpu/drm/i2c/sil164_drv.c new file mode 100644 index 00000000000..0b6773290c0 --- /dev/null +++ b/drivers/gpu/drm/i2c/sil164_drv.c @@ -0,0 +1,462 @@ +/* + * Copyright (C) 2010 Francisco Jerez. + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining + * a copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sublicense, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial + * portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + * IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE + * LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION + * OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION + * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#include "drmP.h" +#include "drm_crtc_helper.h" +#include "drm_encoder_slave.h" +#include "i2c/sil164.h" + +struct sil164_priv { + struct sil164_encoder_params config; + struct i2c_client *duallink_slave; + + uint8_t saved_state[0x10]; + uint8_t saved_slave_state[0x10]; +}; + +#define to_sil164_priv(x) \ + ((struct sil164_priv *)to_encoder_slave(x)->slave_priv) + +#define sil164_dbg(client, format, ...) do { \ + if (drm_debug & DRM_UT_KMS) \ + dev_printk(KERN_DEBUG, &client->dev, \ + "%s: " format, __func__, ## __VA_ARGS__); \ + } while (0) +#define sil164_info(client, format, ...) \ + dev_info(&client->dev, format, __VA_ARGS__) +#define sil164_err(client, format, ...) \ + dev_err(&client->dev, format, __VA_ARGS__) + +#define SIL164_I2C_ADDR_MASTER 0x38 +#define SIL164_I2C_ADDR_SLAVE 0x39 + +/* HW register definitions */ + +#define SIL164_VENDOR_LO 0x0 +#define SIL164_VENDOR_HI 0x1 +#define SIL164_DEVICE_LO 0x2 +#define SIL164_DEVICE_HI 0x3 +#define SIL164_REVISION 0x4 +#define SIL164_FREQ_MIN 0x6 +#define SIL164_FREQ_MAX 0x7 +#define SIL164_CONTROL0 0x8 +# define SIL164_CONTROL0_POWER_ON 0x01 +# define SIL164_CONTROL0_EDGE_RISING 0x02 +# define SIL164_CONTROL0_INPUT_24BIT 0x04 +# define SIL164_CONTROL0_DUAL_EDGE 0x08 +# define SIL164_CONTROL0_HSYNC_ON 0x10 +# define SIL164_CONTROL0_VSYNC_ON 0x20 +#define SIL164_DETECT 0x9 +# define SIL164_DETECT_INTR_STAT 0x01 +# define SIL164_DETECT_HOTPLUG_STAT 0x02 +# define SIL164_DETECT_RECEIVER_STAT 0x04 +# define SIL164_DETECT_INTR_MODE_RECEIVER 0x00 +# define SIL164_DETECT_INTR_MODE_HOTPLUG 0x08 +# define SIL164_DETECT_OUT_MODE_HIGH 0x00 +# define SIL164_DETECT_OUT_MODE_INTR 0x10 +# define SIL164_DETECT_OUT_MODE_RECEIVER 0x20 +# define SIL164_DETECT_OUT_MODE_HOTPLUG 0x30 +# define SIL164_DETECT_VSWING_STAT 0x80 +#define SIL164_CONTROL1 0xa +# define SIL164_CONTROL1_DESKEW_ENABLE 0x10 +# define SIL164_CONTROL1_DESKEW_INCR_SHIFT 5 +#define SIL164_GPIO 0xb +#define SIL164_CONTROL2 0xc +# define SIL164_CONTROL2_FILTER_ENABLE 0x01 +# define SIL164_CONTROL2_FILTER_SETTING_SHIFT 1 +# define SIL164_CONTROL2_DUALLINK_MASTER 0x40 +# define SIL164_CONTROL2_SYNC_CONT 0x80 +#define SIL164_DUALLINK 0xd +# define SIL164_DUALLINK_ENABLE 0x10 +# define SIL164_DUALLINK_SKEW_SHIFT 5 +#define SIL164_PLLZONE 0xe +# define SIL164_PLLZONE_STAT 0x08 +# define SIL164_PLLZONE_FORCE_ON 0x10 +# define SIL164_PLLZONE_FORCE_HIGH 0x20 + +/* HW access functions */ + +static void +sil164_write(struct i2c_client *client, uint8_t addr, uint8_t val) +{ + uint8_t buf[] = {addr, val}; + int ret; + + ret = i2c_master_send(client, buf, ARRAY_SIZE(buf)); + if (ret < 0) + sil164_err(client, "Error %d writing to subaddress 0x%x\n", + ret, addr); +} + +static uint8_t +sil164_read(struct i2c_client *client, uint8_t addr) +{ + uint8_t val; + int ret; + + ret = i2c_master_send(client, &addr, sizeof(addr)); + if (ret < 0) + goto fail; + + ret = i2c_master_recv(client, &val, sizeof(val)); + if (ret < 0) + goto fail; + + return val; + +fail: + sil164_err(client, "Error %d reading from subaddress 0x%x\n", + ret, addr); + return 0; +} + +static void +sil164_save_state(struct i2c_client *client, uint8_t *state) +{ + int i; + + for (i = 0x8; i <= 0xe; i++) + state[i] = sil164_read(client, i); +} + +static void +sil164_restore_state(struct i2c_client *client, uint8_t *state) +{ + int i; + + for (i = 0x8; i <= 0xe; i++) + sil164_write(client, i, state[i]); +} + +static void +sil164_set_power_state(struct i2c_client *client, bool on) +{ + uint8_t control0 = sil164_read(client, SIL164_CONTROL0); + + if (on) + control0 |= SIL164_CONTROL0_POWER_ON; + else + control0 &= ~SIL164_CONTROL0_POWER_ON; + + sil164_write(client, SIL164_CONTROL0, control0); +} + +static void +sil164_init_state(struct i2c_client *client, + struct sil164_encoder_params *config, + bool duallink) +{ + sil164_write(client, SIL164_CONTROL0, + SIL164_CONTROL0_HSYNC_ON | + SIL164_CONTROL0_VSYNC_ON | + (config->input_edge ? SIL164_CONTROL0_EDGE_RISING : 0) | + (config->input_width ? SIL164_CONTROL0_INPUT_24BIT : 0) | + (config->input_dual ? SIL164_CONTROL0_DUAL_EDGE : 0)); + + sil164_write(client, SIL164_DETECT, + SIL164_DETECT_INTR_STAT | + SIL164_DETECT_OUT_MODE_RECEIVER); + + sil164_write(client, SIL164_CONTROL1, + (config->input_skew ? SIL164_CONTROL1_DESKEW_ENABLE : 0) | + (((config->input_skew + 4) & 0x7) + << SIL164_CONTROL1_DESKEW_INCR_SHIFT)); + + sil164_write(client, SIL164_CONTROL2, + SIL164_CONTROL2_SYNC_CONT | + (config->pll_filter ? 0 : SIL164_CONTROL2_FILTER_ENABLE) | + (4 << SIL164_CONTROL2_FILTER_SETTING_SHIFT)); + + sil164_write(client, SIL164_PLLZONE, 0); + + if (duallink) + sil164_write(client, SIL164_DUALLINK, + SIL164_DUALLINK_ENABLE | + (((config->duallink_skew + 4) & 0x7) + << SIL164_DUALLINK_SKEW_SHIFT)); + else + sil164_write(client, SIL164_DUALLINK, 0); +} + +/* DRM encoder functions */ + +static void +sil164_encoder_set_config(struct drm_encoder *encoder, void *params) +{ + struct sil164_priv *priv = to_sil164_priv(encoder); + + priv->config = *(struct sil164_encoder_params *)params; +} + +static void +sil164_encoder_dpms(struct drm_encoder *encoder, int mode) +{ + struct sil164_priv *priv = to_sil164_priv(encoder); + bool on = (mode == DRM_MODE_DPMS_ON); + bool duallink = (on && encoder->crtc->mode.clock > 165000); + + sil164_set_power_state(drm_i2c_encoder_get_client(encoder), on); + + if (priv->duallink_slave) + sil164_set_power_state(priv->duallink_slave, duallink); +} + +static void +sil164_encoder_save(struct drm_encoder *encoder) +{ + struct sil164_priv *priv = to_sil164_priv(encoder); + + sil164_save_state(drm_i2c_encoder_get_client(encoder), + priv->saved_state); + + if (priv->duallink_slave) + sil164_save_state(priv->duallink_slave, + priv->saved_slave_state); +} + +static void +sil164_encoder_restore(struct drm_encoder *encoder) +{ + struct sil164_priv *priv = to_sil164_priv(encoder); + + sil164_restore_state(drm_i2c_encoder_get_client(encoder), + priv->saved_state); + + if (priv->duallink_slave) + sil164_restore_state(priv->duallink_slave, + priv->saved_slave_state); +} + +static bool +sil164_encoder_mode_fixup(struct drm_encoder *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + return true; +} + +static int +sil164_encoder_mode_valid(struct drm_encoder *encoder, + struct drm_display_mode *mode) +{ + struct sil164_priv *priv = to_sil164_priv(encoder); + + if (mode->clock < 32000) + return MODE_CLOCK_LOW; + + if (mode->clock > 330000 || + (mode->clock > 165000 && !priv->duallink_slave)) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static void +sil164_encoder_mode_set(struct drm_encoder *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + struct sil164_priv *priv = to_sil164_priv(encoder); + bool duallink = adjusted_mode->clock > 165000; + + sil164_init_state(drm_i2c_encoder_get_client(encoder), + &priv->config, duallink); + + if (priv->duallink_slave) + sil164_init_state(priv->duallink_slave, + &priv->config, duallink); + + sil164_encoder_dpms(encoder, DRM_MODE_DPMS_ON); +} + +static enum drm_connector_status +sil164_encoder_detect(struct drm_encoder *encoder, + struct drm_connector *connector) +{ + struct i2c_client *client = drm_i2c_encoder_get_client(encoder); + + if (sil164_read(client, SIL164_DETECT) & SIL164_DETECT_HOTPLUG_STAT) + return connector_status_connected; + else + return connector_status_disconnected; +} + +static int +sil164_encoder_get_modes(struct drm_encoder *encoder, + struct drm_connector *connector) +{ + return 0; +} + +static int +sil164_encoder_create_resources(struct drm_encoder *encoder, + struct drm_connector *connector) +{ + return 0; +} + +static int +sil164_encoder_set_property(struct drm_encoder *encoder, + struct drm_connector *connector, + struct drm_property *property, + uint64_t val) +{ + return 0; +} + +static void +sil164_encoder_destroy(struct drm_encoder *encoder) +{ + struct sil164_priv *priv = to_sil164_priv(encoder); + + if (priv->duallink_slave) + i2c_unregister_device(priv->duallink_slave); + + kfree(priv); + drm_i2c_encoder_destroy(encoder); +} + +static struct drm_encoder_slave_funcs sil164_encoder_funcs = { + .set_config = sil164_encoder_set_config, + .destroy = sil164_encoder_destroy, + .dpms = sil164_encoder_dpms, + .save = sil164_encoder_save, + .restore = sil164_encoder_restore, + .mode_fixup = sil164_encoder_mode_fixup, + .mode_valid = sil164_encoder_mode_valid, + .mode_set = sil164_encoder_mode_set, + .detect = sil164_encoder_detect, + .get_modes = sil164_encoder_get_modes, + .create_resources = sil164_encoder_create_resources, + .set_property = sil164_encoder_set_property, +}; + +/* I2C driver functions */ + +static int +sil164_probe(struct i2c_client *client, const struct i2c_device_id *id) +{ + int vendor = sil164_read(client, SIL164_VENDOR_HI) << 8 | + sil164_read(client, SIL164_VENDOR_LO); + int device = sil164_read(client, SIL164_DEVICE_HI) << 8 | + sil164_read(client, SIL164_DEVICE_LO); + int rev = sil164_read(client, SIL164_REVISION); + + if (vendor != 0x1 || device != 0x6) { + sil164_dbg(client, "Unknown device %x:%x.%x\n", + vendor, device, rev); + return -ENODEV; + } + + sil164_info(client, "Detected device %x:%x.%x\n", + vendor, device, rev); + + return 0; +} + +static int +sil164_remove(struct i2c_client *client) +{ + return 0; +} + +static struct i2c_client * +sil164_detect_slave(struct i2c_client *client) +{ + struct i2c_adapter *adap = client->adapter; + struct i2c_msg msg = { + .addr = SIL164_I2C_ADDR_SLAVE, + .len = 0, + }; + const struct i2c_board_info info = { + I2C_BOARD_INFO("sil164", SIL164_I2C_ADDR_SLAVE) + }; + + if (i2c_transfer(adap, &msg, 1) != 1) { + sil164_dbg(adap, "No dual-link slave found."); + return NULL; + } + + return i2c_new_device(adap, &info); +} + +static int +sil164_encoder_init(struct i2c_client *client, + struct drm_device *dev, + struct drm_encoder_slave *encoder) +{ + struct sil164_priv *priv; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + encoder->slave_priv = priv; + encoder->slave_funcs = &sil164_encoder_funcs; + + priv->duallink_slave = sil164_detect_slave(client); + + return 0; +} + +static struct i2c_device_id sil164_ids[] = { + { "sil164", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, sil164_ids); + +static struct drm_i2c_encoder_driver sil164_driver = { + .i2c_driver = { + .probe = sil164_probe, + .remove = sil164_remove, + .driver = { + .name = "sil164", + }, + .id_table = sil164_ids, + }, + .encoder_init = sil164_encoder_init, +}; + +/* Module initialization */ + +static int __init +sil164_init(void) +{ + return drm_i2c_encoder_register(THIS_MODULE, &sil164_driver); +} + +static void __exit +sil164_exit(void) +{ + drm_i2c_encoder_unregister(&sil164_driver); +} + +MODULE_AUTHOR("Francisco Jerez <currojerez@riseup.net>"); +MODULE_DESCRIPTION("Silicon Image sil164 TMDS transmitter driver"); +MODULE_LICENSE("GPL and additional rights"); + +module_init(sil164_init); +module_exit(sil164_exit); diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c index 997d91707ad..0e6c131313d 100644 --- a/drivers/gpu/drm/i810/i810_dma.c +++ b/drivers/gpu/drm/i810/i810_dma.c @@ -37,6 +37,7 @@ #include <linux/interrupt.h> /* For task queue support */ #include <linux/delay.h> #include <linux/slab.h> +#include <linux/smp_lock.h> #include <linux/pagemap.h> #define I810_BUF_FREE 2 @@ -60,9 +61,8 @@ static struct drm_buf *i810_freelist_get(struct drm_device * dev) /* In use is already a pointer */ used = cmpxchg(buf_priv->in_use, I810_BUF_FREE, I810_BUF_CLIENT); - if (used == I810_BUF_FREE) { + if (used == I810_BUF_FREE) return buf; - } } return NULL; } @@ -71,7 +71,7 @@ static struct drm_buf *i810_freelist_get(struct drm_device * dev) * yet, the hardware updates in use for us once its on the ring buffer. */ -static int i810_freelist_put(struct drm_device * dev, struct drm_buf * buf) +static int i810_freelist_put(struct drm_device *dev, struct drm_buf *buf) { drm_i810_buf_priv_t *buf_priv = buf->dev_private; int used; @@ -121,7 +121,7 @@ static const struct file_operations i810_buffer_fops = { .fasync = drm_fasync, }; -static int i810_map_buffer(struct drm_buf * buf, struct drm_file *file_priv) +static int i810_map_buffer(struct drm_buf *buf, struct drm_file *file_priv) { struct drm_device *dev = file_priv->minor->dev; drm_i810_buf_priv_t *buf_priv = buf->dev_private; @@ -152,7 +152,7 @@ static int i810_map_buffer(struct drm_buf * buf, struct drm_file *file_priv) return retcode; } -static int i810_unmap_buffer(struct drm_buf * buf) +static int i810_unmap_buffer(struct drm_buf *buf) { drm_i810_buf_priv_t *buf_priv = buf->dev_private; int retcode = 0; @@ -172,7 +172,7 @@ static int i810_unmap_buffer(struct drm_buf * buf) return retcode; } -static int i810_dma_get_buffer(struct drm_device * dev, drm_i810_dma_t * d, +static int i810_dma_get_buffer(struct drm_device *dev, drm_i810_dma_t *d, struct drm_file *file_priv) { struct drm_buf *buf; @@ -202,7 +202,7 @@ static int i810_dma_get_buffer(struct drm_device * dev, drm_i810_dma_t * d, return retcode; } -static int i810_dma_cleanup(struct drm_device * dev) +static int i810_dma_cleanup(struct drm_device *dev) { struct drm_device_dma *dma = dev->dma; @@ -218,9 +218,8 @@ static int i810_dma_cleanup(struct drm_device * dev) drm_i810_private_t *dev_priv = (drm_i810_private_t *) dev->dev_private; - if (dev_priv->ring.virtual_start) { + if (dev_priv->ring.virtual_start) drm_core_ioremapfree(&dev_priv->ring.map, dev); - } if (dev_priv->hw_status_page) { pci_free_consistent(dev->pdev, PAGE_SIZE, dev_priv->hw_status_page, @@ -242,7 +241,7 @@ static int i810_dma_cleanup(struct drm_device * dev) return 0; } -static int i810_wait_ring(struct drm_device * dev, int n) +static int i810_wait_ring(struct drm_device *dev, int n) { drm_i810_private_t *dev_priv = dev->dev_private; drm_i810_ring_buffer_t *ring = &(dev_priv->ring); @@ -271,11 +270,11 @@ static int i810_wait_ring(struct drm_device * dev, int n) udelay(1); } - out_wait_ring: +out_wait_ring: return iters; } -static void i810_kernel_lost_context(struct drm_device * dev) +static void i810_kernel_lost_context(struct drm_device *dev) { drm_i810_private_t *dev_priv = dev->dev_private; drm_i810_ring_buffer_t *ring = &(dev_priv->ring); @@ -287,7 +286,7 @@ static void i810_kernel_lost_context(struct drm_device * dev) ring->space += ring->Size; } -static int i810_freelist_init(struct drm_device * dev, drm_i810_private_t * dev_priv) +static int i810_freelist_init(struct drm_device *dev, drm_i810_private_t *dev_priv) { struct drm_device_dma *dma = dev->dma; int my_idx = 24; @@ -322,9 +321,9 @@ static int i810_freelist_init(struct drm_device * dev, drm_i810_private_t * dev_ return 0; } -static int i810_dma_initialize(struct drm_device * dev, - drm_i810_private_t * dev_priv, - drm_i810_init_t * init) +static int i810_dma_initialize(struct drm_device *dev, + drm_i810_private_t *dev_priv, + drm_i810_init_t *init) { struct drm_map_list *r_list; memset(dev_priv, 0, sizeof(drm_i810_private_t)); @@ -462,7 +461,7 @@ static int i810_dma_init(struct drm_device *dev, void *data, * Use 'volatile' & local var tmp to force the emitted values to be * identical to the verified ones. */ -static void i810EmitContextVerified(struct drm_device * dev, +static void i810EmitContextVerified(struct drm_device *dev, volatile unsigned int *code) { drm_i810_private_t *dev_priv = dev->dev_private; @@ -495,7 +494,7 @@ static void i810EmitContextVerified(struct drm_device * dev, ADVANCE_LP_RING(); } -static void i810EmitTexVerified(struct drm_device * dev, volatile unsigned int *code) +static void i810EmitTexVerified(struct drm_device *dev, volatile unsigned int *code) { drm_i810_private_t *dev_priv = dev->dev_private; int i, j = 0; @@ -528,7 +527,7 @@ static void i810EmitTexVerified(struct drm_device * dev, volatile unsigned int * /* Need to do some additional checking when setting the dest buffer. */ -static void i810EmitDestVerified(struct drm_device * dev, +static void i810EmitDestVerified(struct drm_device *dev, volatile unsigned int *code) { drm_i810_private_t *dev_priv = dev->dev_private; @@ -563,7 +562,7 @@ static void i810EmitDestVerified(struct drm_device * dev, ADVANCE_LP_RING(); } -static void i810EmitState(struct drm_device * dev) +static void i810EmitState(struct drm_device *dev) { drm_i810_private_t *dev_priv = dev->dev_private; drm_i810_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -594,7 +593,7 @@ static void i810EmitState(struct drm_device * dev) /* need to verify */ -static void i810_dma_dispatch_clear(struct drm_device * dev, int flags, +static void i810_dma_dispatch_clear(struct drm_device *dev, int flags, unsigned int clear_color, unsigned int clear_zval) { @@ -669,7 +668,7 @@ static void i810_dma_dispatch_clear(struct drm_device * dev, int flags, } } -static void i810_dma_dispatch_swap(struct drm_device * dev) +static void i810_dma_dispatch_swap(struct drm_device *dev) { drm_i810_private_t *dev_priv = dev->dev_private; drm_i810_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -715,8 +714,8 @@ static void i810_dma_dispatch_swap(struct drm_device * dev) } } -static void i810_dma_dispatch_vertex(struct drm_device * dev, - struct drm_buf * buf, int discard, int used) +static void i810_dma_dispatch_vertex(struct drm_device *dev, + struct drm_buf *buf, int discard, int used) { drm_i810_private_t *dev_priv = dev->dev_private; drm_i810_buf_priv_t *buf_priv = buf->dev_private; @@ -795,7 +794,7 @@ static void i810_dma_dispatch_vertex(struct drm_device * dev, } } -static void i810_dma_dispatch_flip(struct drm_device * dev) +static void i810_dma_dispatch_flip(struct drm_device *dev) { drm_i810_private_t *dev_priv = dev->dev_private; int pitch = dev_priv->pitch; @@ -841,7 +840,7 @@ static void i810_dma_dispatch_flip(struct drm_device * dev) } -static void i810_dma_quiescent(struct drm_device * dev) +static void i810_dma_quiescent(struct drm_device *dev) { drm_i810_private_t *dev_priv = dev->dev_private; RING_LOCALS; @@ -858,7 +857,7 @@ static void i810_dma_quiescent(struct drm_device * dev) i810_wait_ring(dev, dev_priv->ring.Size - 8); } -static int i810_flush_queue(struct drm_device * dev) +static int i810_flush_queue(struct drm_device *dev) { drm_i810_private_t *dev_priv = dev->dev_private; struct drm_device_dma *dma = dev->dma; @@ -891,7 +890,7 @@ static int i810_flush_queue(struct drm_device * dev) } /* Must be called with the lock held */ -static void i810_reclaim_buffers(struct drm_device * dev, +static void i810_reclaim_buffers(struct drm_device *dev, struct drm_file *file_priv) { struct drm_device_dma *dma = dev->dma; @@ -969,9 +968,8 @@ static int i810_clear_bufs(struct drm_device *dev, void *data, LOCK_TEST_WITH_RETURN(dev, file_priv); /* GH: Someone's doing nasty things... */ - if (!dev->dev_private) { + if (!dev->dev_private) return -EINVAL; - } i810_dma_dispatch_clear(dev, clear->flags, clear->clear_color, clear->clear_depth); @@ -1039,7 +1037,7 @@ static int i810_docopy(struct drm_device *dev, void *data, return 0; } -static void i810_dma_dispatch_mc(struct drm_device * dev, struct drm_buf * buf, int used, +static void i810_dma_dispatch_mc(struct drm_device *dev, struct drm_buf *buf, int used, unsigned int last_render) { drm_i810_private_t *dev_priv = dev->dev_private; @@ -1053,9 +1051,8 @@ static void i810_dma_dispatch_mc(struct drm_device * dev, struct drm_buf * buf, i810_kernel_lost_context(dev); u = cmpxchg(buf_priv->in_use, I810_BUF_CLIENT, I810_BUF_HARDWARE); - if (u != I810_BUF_CLIENT) { + if (u != I810_BUF_CLIENT) DRM_DEBUG("MC found buffer that isn't mine!\n"); - } if (used > 4 * 1024) used = 0; @@ -1160,7 +1157,7 @@ static int i810_ov0_flip(struct drm_device *dev, void *data, LOCK_TEST_WITH_RETURN(dev, file_priv); - //Tell the overlay to update + /* Tell the overlay to update */ I810_WRITE(0x30000, dev_priv->overlay_physical | 0x80000000); return 0; @@ -1168,7 +1165,7 @@ static int i810_ov0_flip(struct drm_device *dev, void *data, /* Not sure why this isn't set all the time: */ -static void i810_do_init_pageflip(struct drm_device * dev) +static void i810_do_init_pageflip(struct drm_device *dev) { drm_i810_private_t *dev_priv = dev->dev_private; @@ -1178,7 +1175,7 @@ static void i810_do_init_pageflip(struct drm_device * dev) dev_priv->sarea_priv->pf_current_page = dev_priv->current_page; } -static int i810_do_cleanup_pageflip(struct drm_device * dev) +static int i810_do_cleanup_pageflip(struct drm_device *dev) { drm_i810_private_t *dev_priv = dev->dev_private; @@ -1218,49 +1215,61 @@ int i810_driver_load(struct drm_device *dev, unsigned long flags) return 0; } -void i810_driver_lastclose(struct drm_device * dev) +void i810_driver_lastclose(struct drm_device *dev) { i810_dma_cleanup(dev); } -void i810_driver_preclose(struct drm_device * dev, struct drm_file *file_priv) +void i810_driver_preclose(struct drm_device *dev, struct drm_file *file_priv) { if (dev->dev_private) { drm_i810_private_t *dev_priv = dev->dev_private; - if (dev_priv->page_flipping) { + if (dev_priv->page_flipping) i810_do_cleanup_pageflip(dev); - } } } -void i810_driver_reclaim_buffers_locked(struct drm_device * dev, +void i810_driver_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv) { i810_reclaim_buffers(dev, file_priv); } -int i810_driver_dma_quiescent(struct drm_device * dev) +int i810_driver_dma_quiescent(struct drm_device *dev) { i810_dma_quiescent(dev); return 0; } +/* + * call the drm_ioctl under the big kernel lock because + * to lock against the i810_mmap_buffers function. + */ +long i810_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + int ret; + lock_kernel(); + ret = drm_ioctl(file, cmd, arg); + unlock_kernel(); + return ret; +} + struct drm_ioctl_desc i810_ioctls[] = { - DRM_IOCTL_DEF(DRM_I810_INIT, i810_dma_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), - DRM_IOCTL_DEF(DRM_I810_VERTEX, i810_dma_vertex, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_CLEAR, i810_clear_bufs, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_FLUSH, i810_flush_ioctl, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_GETAGE, i810_getage, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_GETBUF, i810_getbuf, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_SWAP, i810_swap_bufs, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_COPY, i810_copybuf, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_DOCOPY, i810_docopy, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_OV0INFO, i810_ov0_info, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_FSTATUS, i810_fstatus, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_OV0FLIP, i810_ov0_flip, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_MC, i810_dma_mc, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), - DRM_IOCTL_DEF(DRM_I810_RSTATUS, i810_rstatus, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I810_FLIP, i810_flip_bufs, DRM_AUTH) + DRM_IOCTL_DEF(DRM_I810_INIT, i810_dma_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_VERTEX, i810_dma_vertex, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_CLEAR, i810_clear_bufs, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_FLUSH, i810_flush_ioctl, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_GETAGE, i810_getage, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_GETBUF, i810_getbuf, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_SWAP, i810_swap_bufs, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_COPY, i810_copybuf, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_DOCOPY, i810_docopy, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_OV0INFO, i810_ov0_info, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_FSTATUS, i810_fstatus, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_OV0FLIP, i810_ov0_flip, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_MC, i810_dma_mc, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_RSTATUS, i810_rstatus, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I810_FLIP, i810_flip_bufs, DRM_AUTH|DRM_UNLOCKED), }; int i810_max_ioctl = DRM_ARRAY_SIZE(i810_ioctls); @@ -1276,7 +1285,7 @@ int i810_max_ioctl = DRM_ARRAY_SIZE(i810_ioctls); * \returns * A value of 1 is always retured to indictate every i810 is AGP. */ -int i810_driver_device_is_agp(struct drm_device * dev) +int i810_driver_device_is_agp(struct drm_device *dev) { return 1; } diff --git a/drivers/gpu/drm/i810/i810_drv.c b/drivers/gpu/drm/i810/i810_drv.c index c1e02752e02..b4250b2cac1 100644 --- a/drivers/gpu/drm/i810/i810_drv.c +++ b/drivers/gpu/drm/i810/i810_drv.c @@ -59,7 +59,7 @@ static struct drm_driver driver = { .owner = THIS_MODULE, .open = drm_open, .release = drm_release, - .unlocked_ioctl = drm_ioctl, + .unlocked_ioctl = i810_ioctl, .mmap = drm_mmap, .poll = drm_poll, .fasync = drm_fasync, diff --git a/drivers/gpu/drm/i810/i810_drv.h b/drivers/gpu/drm/i810/i810_drv.h index 21e2691f28f..c9339f48179 100644 --- a/drivers/gpu/drm/i810/i810_drv.h +++ b/drivers/gpu/drm/i810/i810_drv.h @@ -115,56 +115,59 @@ typedef struct drm_i810_private { } drm_i810_private_t; /* i810_dma.c */ -extern int i810_driver_dma_quiescent(struct drm_device * dev); -extern void i810_driver_reclaim_buffers_locked(struct drm_device * dev, +extern int i810_driver_dma_quiescent(struct drm_device *dev); +extern void i810_driver_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv); extern int i810_driver_load(struct drm_device *, unsigned long flags); -extern void i810_driver_lastclose(struct drm_device * dev); -extern void i810_driver_preclose(struct drm_device * dev, +extern void i810_driver_lastclose(struct drm_device *dev); +extern void i810_driver_preclose(struct drm_device *dev, struct drm_file *file_priv); -extern void i810_driver_reclaim_buffers_locked(struct drm_device * dev, +extern void i810_driver_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv); -extern int i810_driver_device_is_agp(struct drm_device * dev); +extern int i810_driver_device_is_agp(struct drm_device *dev); +extern long i810_ioctl(struct file *file, unsigned int cmd, unsigned long arg); extern struct drm_ioctl_desc i810_ioctls[]; extern int i810_max_ioctl; #define I810_BASE(reg) ((unsigned long) \ dev_priv->mmio_map->handle) #define I810_ADDR(reg) (I810_BASE(reg) + reg) -#define I810_DEREF(reg) *(__volatile__ int *)I810_ADDR(reg) +#define I810_DEREF(reg) (*(__volatile__ int *)I810_ADDR(reg)) #define I810_READ(reg) I810_DEREF(reg) -#define I810_WRITE(reg,val) do { I810_DEREF(reg) = val; } while (0) -#define I810_DEREF16(reg) *(__volatile__ u16 *)I810_ADDR(reg) +#define I810_WRITE(reg, val) do { I810_DEREF(reg) = val; } while (0) +#define I810_DEREF16(reg) (*(__volatile__ u16 *)I810_ADDR(reg)) #define I810_READ16(reg) I810_DEREF16(reg) -#define I810_WRITE16(reg,val) do { I810_DEREF16(reg) = val; } while (0) +#define I810_WRITE16(reg, val) do { I810_DEREF16(reg) = val; } while (0) #define I810_VERBOSE 0 #define RING_LOCALS unsigned int outring, ringmask; \ - volatile char *virt; - -#define BEGIN_LP_RING(n) do { \ - if (I810_VERBOSE) \ - DRM_DEBUG("BEGIN_LP_RING(%d)\n", n); \ - if (dev_priv->ring.space < n*4) \ - i810_wait_ring(dev, n*4); \ - dev_priv->ring.space -= n*4; \ - outring = dev_priv->ring.tail; \ - ringmask = dev_priv->ring.tail_mask; \ - virt = dev_priv->ring.virtual_start; \ + volatile char *virt; + +#define BEGIN_LP_RING(n) do { \ + if (I810_VERBOSE) \ + DRM_DEBUG("BEGIN_LP_RING(%d)\n", n); \ + if (dev_priv->ring.space < n*4) \ + i810_wait_ring(dev, n*4); \ + dev_priv->ring.space -= n*4; \ + outring = dev_priv->ring.tail; \ + ringmask = dev_priv->ring.tail_mask; \ + virt = dev_priv->ring.virtual_start; \ } while (0) -#define ADVANCE_LP_RING() do { \ - if (I810_VERBOSE) DRM_DEBUG("ADVANCE_LP_RING\n"); \ +#define ADVANCE_LP_RING() do { \ + if (I810_VERBOSE) \ + DRM_DEBUG("ADVANCE_LP_RING\n"); \ dev_priv->ring.tail = outring; \ - I810_WRITE(LP_RING + RING_TAIL, outring); \ -} while(0) - -#define OUT_RING(n) do { \ - if (I810_VERBOSE) DRM_DEBUG(" OUT_RING %x\n", (int)(n)); \ - *(volatile unsigned int *)(virt + outring) = n; \ - outring += 4; \ - outring &= ringmask; \ + I810_WRITE(LP_RING + RING_TAIL, outring); \ +} while (0) + +#define OUT_RING(n) do { \ + if (I810_VERBOSE) \ + DRM_DEBUG(" OUT_RING %x\n", (int)(n)); \ + *(volatile unsigned int *)(virt + outring) = n; \ + outring += 4; \ + outring &= ringmask; \ } while (0) #define GFX_OP_USER_INTERRUPT ((0<<29)|(2<<23)) diff --git a/drivers/gpu/drm/i830/i830_dma.c b/drivers/gpu/drm/i830/i830_dma.c index 65759a9a85c..5168862c922 100644 --- a/drivers/gpu/drm/i830/i830_dma.c +++ b/drivers/gpu/drm/i830/i830_dma.c @@ -36,6 +36,7 @@ #include "i830_drm.h" #include "i830_drv.h" #include <linux/interrupt.h> /* For task queue support */ +#include <linux/smp_lock.h> #include <linux/pagemap.h> #include <linux/delay.h> #include <linux/slab.h> @@ -62,9 +63,8 @@ static struct drm_buf *i830_freelist_get(struct drm_device * dev) /* In use is already a pointer */ used = cmpxchg(buf_priv->in_use, I830_BUF_FREE, I830_BUF_CLIENT); - if (used == I830_BUF_FREE) { + if (used == I830_BUF_FREE) return buf; - } } return NULL; } @@ -73,7 +73,7 @@ static struct drm_buf *i830_freelist_get(struct drm_device * dev) * yet, the hardware updates in use for us once its on the ring buffer. */ -static int i830_freelist_put(struct drm_device * dev, struct drm_buf * buf) +static int i830_freelist_put(struct drm_device *dev, struct drm_buf *buf) { drm_i830_buf_priv_t *buf_priv = buf->dev_private; int used; @@ -123,7 +123,7 @@ static const struct file_operations i830_buffer_fops = { .fasync = drm_fasync, }; -static int i830_map_buffer(struct drm_buf * buf, struct drm_file *file_priv) +static int i830_map_buffer(struct drm_buf *buf, struct drm_file *file_priv) { struct drm_device *dev = file_priv->minor->dev; drm_i830_buf_priv_t *buf_priv = buf->dev_private; @@ -156,7 +156,7 @@ static int i830_map_buffer(struct drm_buf * buf, struct drm_file *file_priv) return retcode; } -static int i830_unmap_buffer(struct drm_buf * buf) +static int i830_unmap_buffer(struct drm_buf *buf) { drm_i830_buf_priv_t *buf_priv = buf->dev_private; int retcode = 0; @@ -176,7 +176,7 @@ static int i830_unmap_buffer(struct drm_buf * buf) return retcode; } -static int i830_dma_get_buffer(struct drm_device * dev, drm_i830_dma_t * d, +static int i830_dma_get_buffer(struct drm_device *dev, drm_i830_dma_t *d, struct drm_file *file_priv) { struct drm_buf *buf; @@ -206,7 +206,7 @@ static int i830_dma_get_buffer(struct drm_device * dev, drm_i830_dma_t * d, return retcode; } -static int i830_dma_cleanup(struct drm_device * dev) +static int i830_dma_cleanup(struct drm_device *dev) { struct drm_device_dma *dma = dev->dma; @@ -222,9 +222,8 @@ static int i830_dma_cleanup(struct drm_device * dev) drm_i830_private_t *dev_priv = (drm_i830_private_t *) dev->dev_private; - if (dev_priv->ring.virtual_start) { + if (dev_priv->ring.virtual_start) drm_core_ioremapfree(&dev_priv->ring.map, dev); - } if (dev_priv->hw_status_page) { pci_free_consistent(dev->pdev, PAGE_SIZE, dev_priv->hw_status_page, @@ -246,7 +245,7 @@ static int i830_dma_cleanup(struct drm_device * dev) return 0; } -int i830_wait_ring(struct drm_device * dev, int n, const char *caller) +int i830_wait_ring(struct drm_device *dev, int n, const char *caller) { drm_i830_private_t *dev_priv = dev->dev_private; drm_i830_ring_buffer_t *ring = &(dev_priv->ring); @@ -276,11 +275,11 @@ int i830_wait_ring(struct drm_device * dev, int n, const char *caller) dev_priv->sarea_priv->perf_boxes |= I830_BOX_WAIT; } - out_wait_ring: +out_wait_ring: return iters; } -static void i830_kernel_lost_context(struct drm_device * dev) +static void i830_kernel_lost_context(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; drm_i830_ring_buffer_t *ring = &(dev_priv->ring); @@ -295,7 +294,7 @@ static void i830_kernel_lost_context(struct drm_device * dev) dev_priv->sarea_priv->perf_boxes |= I830_BOX_RING_EMPTY; } -static int i830_freelist_init(struct drm_device * dev, drm_i830_private_t * dev_priv) +static int i830_freelist_init(struct drm_device *dev, drm_i830_private_t *dev_priv) { struct drm_device_dma *dma = dev->dma; int my_idx = 36; @@ -329,9 +328,9 @@ static int i830_freelist_init(struct drm_device * dev, drm_i830_private_t * dev_ return 0; } -static int i830_dma_initialize(struct drm_device * dev, - drm_i830_private_t * dev_priv, - drm_i830_init_t * init) +static int i830_dma_initialize(struct drm_device *dev, + drm_i830_private_t *dev_priv, + drm_i830_init_t *init) { struct drm_map_list *r_list; @@ -482,7 +481,7 @@ static int i830_dma_init(struct drm_device *dev, void *data, /* Most efficient way to verify state for the i830 is as it is * emitted. Non-conformant state is silently dropped. */ -static void i830EmitContextVerified(struct drm_device * dev, unsigned int *code) +static void i830EmitContextVerified(struct drm_device *dev, unsigned int *code) { drm_i830_private_t *dev_priv = dev->dev_private; int i, j = 0; @@ -527,7 +526,7 @@ static void i830EmitContextVerified(struct drm_device * dev, unsigned int *code) ADVANCE_LP_RING(); } -static void i830EmitTexVerified(struct drm_device * dev, unsigned int *code) +static void i830EmitTexVerified(struct drm_device *dev, unsigned int *code) { drm_i830_private_t *dev_priv = dev->dev_private; int i, j = 0; @@ -561,7 +560,7 @@ static void i830EmitTexVerified(struct drm_device * dev, unsigned int *code) printk("rejected packet %x\n", code[0]); } -static void i830EmitTexBlendVerified(struct drm_device * dev, +static void i830EmitTexBlendVerified(struct drm_device *dev, unsigned int *code, unsigned int num) { drm_i830_private_t *dev_priv = dev->dev_private; @@ -586,7 +585,7 @@ static void i830EmitTexBlendVerified(struct drm_device * dev, ADVANCE_LP_RING(); } -static void i830EmitTexPalette(struct drm_device * dev, +static void i830EmitTexPalette(struct drm_device *dev, unsigned int *palette, int number, int is_shared) { drm_i830_private_t *dev_priv = dev->dev_private; @@ -603,9 +602,8 @@ static void i830EmitTexPalette(struct drm_device * dev, } else { OUT_RING(CMD_OP_MAP_PALETTE_LOAD | MAP_PALETTE_NUM(number)); } - for (i = 0; i < 256; i++) { + for (i = 0; i < 256; i++) OUT_RING(palette[i]); - } OUT_RING(0); /* KW: WHERE IS THE ADVANCE_LP_RING? This is effectively a noop! */ @@ -613,7 +611,7 @@ static void i830EmitTexPalette(struct drm_device * dev, /* Need to do some additional checking when setting the dest buffer. */ -static void i830EmitDestVerified(struct drm_device * dev, unsigned int *code) +static void i830EmitDestVerified(struct drm_device *dev, unsigned int *code) { drm_i830_private_t *dev_priv = dev->dev_private; unsigned int tmp; @@ -674,7 +672,7 @@ static void i830EmitDestVerified(struct drm_device * dev, unsigned int *code) ADVANCE_LP_RING(); } -static void i830EmitStippleVerified(struct drm_device * dev, unsigned int *code) +static void i830EmitStippleVerified(struct drm_device *dev, unsigned int *code) { drm_i830_private_t *dev_priv = dev->dev_private; RING_LOCALS; @@ -685,7 +683,7 @@ static void i830EmitStippleVerified(struct drm_device * dev, unsigned int *code) ADVANCE_LP_RING(); } -static void i830EmitState(struct drm_device * dev) +static void i830EmitState(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; drm_i830_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -788,7 +786,7 @@ static void i830EmitState(struct drm_device * dev) * Performance monitoring functions */ -static void i830_fill_box(struct drm_device * dev, +static void i830_fill_box(struct drm_device *dev, int x, int y, int w, int h, int r, int g, int b) { drm_i830_private_t *dev_priv = dev->dev_private; @@ -816,17 +814,16 @@ static void i830_fill_box(struct drm_device * dev, OUT_RING((y << 16) | x); OUT_RING(((y + h) << 16) | (x + w)); - if (dev_priv->current_page == 1) { + if (dev_priv->current_page == 1) OUT_RING(dev_priv->front_offset); - } else { + else OUT_RING(dev_priv->back_offset); - } OUT_RING(color); ADVANCE_LP_RING(); } -static void i830_cp_performance_boxes(struct drm_device * dev) +static void i830_cp_performance_boxes(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; @@ -871,7 +868,7 @@ static void i830_cp_performance_boxes(struct drm_device * dev) dev_priv->sarea_priv->perf_boxes = 0; } -static void i830_dma_dispatch_clear(struct drm_device * dev, int flags, +static void i830_dma_dispatch_clear(struct drm_device *dev, int flags, unsigned int clear_color, unsigned int clear_zval, unsigned int clear_depthmask) @@ -966,7 +963,7 @@ static void i830_dma_dispatch_clear(struct drm_device * dev, int flags, } } -static void i830_dma_dispatch_swap(struct drm_device * dev) +static void i830_dma_dispatch_swap(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; drm_i830_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -1036,7 +1033,7 @@ static void i830_dma_dispatch_swap(struct drm_device * dev) } } -static void i830_dma_dispatch_flip(struct drm_device * dev) +static void i830_dma_dispatch_flip(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; RING_LOCALS; @@ -1079,8 +1076,8 @@ static void i830_dma_dispatch_flip(struct drm_device * dev) dev_priv->sarea_priv->pf_current_page = dev_priv->current_page; } -static void i830_dma_dispatch_vertex(struct drm_device * dev, - struct drm_buf * buf, int discard, int used) +static void i830_dma_dispatch_vertex(struct drm_device *dev, + struct drm_buf *buf, int discard, int used) { drm_i830_private_t *dev_priv = dev->dev_private; drm_i830_buf_priv_t *buf_priv = buf->dev_private; @@ -1100,9 +1097,8 @@ static void i830_dma_dispatch_vertex(struct drm_device * dev, if (discard) { u = cmpxchg(buf_priv->in_use, I830_BUF_CLIENT, I830_BUF_HARDWARE); - if (u != I830_BUF_CLIENT) { + if (u != I830_BUF_CLIENT) DRM_DEBUG("xxxx 2\n"); - } } if (used > 4 * 1023) @@ -1191,7 +1187,7 @@ static void i830_dma_dispatch_vertex(struct drm_device * dev, } } -static void i830_dma_quiescent(struct drm_device * dev) +static void i830_dma_quiescent(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; RING_LOCALS; @@ -1208,7 +1204,7 @@ static void i830_dma_quiescent(struct drm_device * dev) i830_wait_ring(dev, dev_priv->ring.Size - 8, __func__); } -static int i830_flush_queue(struct drm_device * dev) +static int i830_flush_queue(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; struct drm_device_dma *dma = dev->dma; @@ -1241,7 +1237,7 @@ static int i830_flush_queue(struct drm_device * dev) } /* Must be called with the lock held */ -static void i830_reclaim_buffers(struct drm_device * dev, struct drm_file *file_priv) +static void i830_reclaim_buffers(struct drm_device *dev, struct drm_file *file_priv) { struct drm_device_dma *dma = dev->dma; int i; @@ -1316,9 +1312,8 @@ static int i830_clear_bufs(struct drm_device *dev, void *data, LOCK_TEST_WITH_RETURN(dev, file_priv); /* GH: Someone's doing nasty things... */ - if (!dev->dev_private) { + if (!dev->dev_private) return -EINVAL; - } i830_dma_dispatch_clear(dev, clear->flags, clear->clear_color, @@ -1339,7 +1334,7 @@ static int i830_swap_bufs(struct drm_device *dev, void *data, /* Not sure why this isn't set all the time: */ -static void i830_do_init_pageflip(struct drm_device * dev) +static void i830_do_init_pageflip(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; @@ -1349,7 +1344,7 @@ static void i830_do_init_pageflip(struct drm_device * dev) dev_priv->sarea_priv->pf_current_page = dev_priv->current_page; } -static int i830_do_cleanup_pageflip(struct drm_device * dev) +static int i830_do_cleanup_pageflip(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; @@ -1490,47 +1485,59 @@ int i830_driver_load(struct drm_device *dev, unsigned long flags) return 0; } -void i830_driver_lastclose(struct drm_device * dev) +void i830_driver_lastclose(struct drm_device *dev) { i830_dma_cleanup(dev); } -void i830_driver_preclose(struct drm_device * dev, struct drm_file *file_priv) +void i830_driver_preclose(struct drm_device *dev, struct drm_file *file_priv) { if (dev->dev_private) { drm_i830_private_t *dev_priv = dev->dev_private; - if (dev_priv->page_flipping) { + if (dev_priv->page_flipping) i830_do_cleanup_pageflip(dev); - } } } -void i830_driver_reclaim_buffers_locked(struct drm_device * dev, struct drm_file *file_priv) +void i830_driver_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv) { i830_reclaim_buffers(dev, file_priv); } -int i830_driver_dma_quiescent(struct drm_device * dev) +int i830_driver_dma_quiescent(struct drm_device *dev) { i830_dma_quiescent(dev); return 0; } +/* + * call the drm_ioctl under the big kernel lock because + * to lock against the i830_mmap_buffers function. + */ +long i830_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + int ret; + lock_kernel(); + ret = drm_ioctl(file, cmd, arg); + unlock_kernel(); + return ret; +} + struct drm_ioctl_desc i830_ioctls[] = { - DRM_IOCTL_DEF(DRM_I830_INIT, i830_dma_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), - DRM_IOCTL_DEF(DRM_I830_VERTEX, i830_dma_vertex, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_CLEAR, i830_clear_bufs, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_FLUSH, i830_flush_ioctl, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_GETAGE, i830_getage, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_GETBUF, i830_getbuf, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_SWAP, i830_swap_bufs, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_COPY, i830_copybuf, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_DOCOPY, i830_docopy, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_FLIP, i830_flip_bufs, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_IRQ_EMIT, i830_irq_emit, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_IRQ_WAIT, i830_irq_wait, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_GETPARAM, i830_getparam, DRM_AUTH), - DRM_IOCTL_DEF(DRM_I830_SETPARAM, i830_setparam, DRM_AUTH) + DRM_IOCTL_DEF(DRM_I830_INIT, i830_dma_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_VERTEX, i830_dma_vertex, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_CLEAR, i830_clear_bufs, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_FLUSH, i830_flush_ioctl, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_GETAGE, i830_getage, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_GETBUF, i830_getbuf, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_SWAP, i830_swap_bufs, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_COPY, i830_copybuf, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_DOCOPY, i830_docopy, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_FLIP, i830_flip_bufs, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_IRQ_EMIT, i830_irq_emit, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_IRQ_WAIT, i830_irq_wait, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_GETPARAM, i830_getparam, DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_I830_SETPARAM, i830_setparam, DRM_AUTH|DRM_UNLOCKED), }; int i830_max_ioctl = DRM_ARRAY_SIZE(i830_ioctls); @@ -1546,7 +1553,7 @@ int i830_max_ioctl = DRM_ARRAY_SIZE(i830_ioctls); * \returns * A value of 1 is always retured to indictate every i8xx is AGP. */ -int i830_driver_device_is_agp(struct drm_device * dev) +int i830_driver_device_is_agp(struct drm_device *dev) { return 1; } diff --git a/drivers/gpu/drm/i830/i830_drv.c b/drivers/gpu/drm/i830/i830_drv.c index 44f990bed8f..a5c66aa82f0 100644 --- a/drivers/gpu/drm/i830/i830_drv.c +++ b/drivers/gpu/drm/i830/i830_drv.c @@ -70,7 +70,7 @@ static struct drm_driver driver = { .owner = THIS_MODULE, .open = drm_open, .release = drm_release, - .unlocked_ioctl = drm_ioctl, + .unlocked_ioctl = i830_ioctl, .mmap = drm_mmap, .poll = drm_poll, .fasync = drm_fasync, diff --git a/drivers/gpu/drm/i830/i830_drv.h b/drivers/gpu/drm/i830/i830_drv.h index da82afe4ded..0df1c720560 100644 --- a/drivers/gpu/drm/i830/i830_drv.h +++ b/drivers/gpu/drm/i830/i830_drv.h @@ -122,6 +122,7 @@ typedef struct drm_i830_private { } drm_i830_private_t; +long i830_ioctl(struct file *file, unsigned int cmd, unsigned long arg); extern struct drm_ioctl_desc i830_ioctls[]; extern int i830_max_ioctl; @@ -132,33 +133,33 @@ extern int i830_irq_wait(struct drm_device *dev, void *data, struct drm_file *file_priv); extern irqreturn_t i830_driver_irq_handler(DRM_IRQ_ARGS); -extern void i830_driver_irq_preinstall(struct drm_device * dev); -extern void i830_driver_irq_postinstall(struct drm_device * dev); -extern void i830_driver_irq_uninstall(struct drm_device * dev); +extern void i830_driver_irq_preinstall(struct drm_device *dev); +extern void i830_driver_irq_postinstall(struct drm_device *dev); +extern void i830_driver_irq_uninstall(struct drm_device *dev); extern int i830_driver_load(struct drm_device *, unsigned long flags); -extern void i830_driver_preclose(struct drm_device * dev, +extern void i830_driver_preclose(struct drm_device *dev, struct drm_file *file_priv); -extern void i830_driver_lastclose(struct drm_device * dev); -extern void i830_driver_reclaim_buffers_locked(struct drm_device * dev, +extern void i830_driver_lastclose(struct drm_device *dev); +extern void i830_driver_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv); -extern int i830_driver_dma_quiescent(struct drm_device * dev); -extern int i830_driver_device_is_agp(struct drm_device * dev); +extern int i830_driver_dma_quiescent(struct drm_device *dev); +extern int i830_driver_device_is_agp(struct drm_device *dev); -#define I830_READ(reg) DRM_READ32(dev_priv->mmio_map, reg) -#define I830_WRITE(reg,val) DRM_WRITE32(dev_priv->mmio_map, reg, val) -#define I830_READ16(reg) DRM_READ16(dev_priv->mmio_map, reg) -#define I830_WRITE16(reg,val) DRM_WRITE16(dev_priv->mmio_map, reg, val) +#define I830_READ(reg) DRM_READ32(dev_priv->mmio_map, reg) +#define I830_WRITE(reg, val) DRM_WRITE32(dev_priv->mmio_map, reg, val) +#define I830_READ16(reg) DRM_READ16(dev_priv->mmio_map, reg) +#define I830_WRITE16(reg, val) DRM_WRITE16(dev_priv->mmio_map, reg, val) #define I830_VERBOSE 0 #define RING_LOCALS unsigned int outring, ringmask, outcount; \ - volatile char *virt; + volatile char *virt; #define BEGIN_LP_RING(n) do { \ if (I830_VERBOSE) \ printk("BEGIN_LP_RING(%d)\n", (n)); \ if (dev_priv->ring.space < n*4) \ - i830_wait_ring(dev, n*4, __func__); \ + i830_wait_ring(dev, n*4, __func__); \ outcount = 0; \ outring = dev_priv->ring.tail; \ ringmask = dev_priv->ring.tail_mask; \ @@ -166,21 +167,23 @@ extern int i830_driver_device_is_agp(struct drm_device * dev); } while (0) #define OUT_RING(n) do { \ - if (I830_VERBOSE) printk(" OUT_RING %x\n", (int)(n)); \ + if (I830_VERBOSE) \ + printk(" OUT_RING %x\n", (int)(n)); \ *(volatile unsigned int *)(virt + outring) = n; \ - outcount++; \ + outcount++; \ outring += 4; \ outring &= ringmask; \ } while (0) -#define ADVANCE_LP_RING() do { \ - if (I830_VERBOSE) printk("ADVANCE_LP_RING %x\n", outring); \ - dev_priv->ring.tail = outring; \ - dev_priv->ring.space -= outcount * 4; \ - I830_WRITE(LP_RING + RING_TAIL, outring); \ -} while(0) +#define ADVANCE_LP_RING() do { \ + if (I830_VERBOSE) \ + printk("ADVANCE_LP_RING %x\n", outring); \ + dev_priv->ring.tail = outring; \ + dev_priv->ring.space -= outcount * 4; \ + I830_WRITE(LP_RING + RING_TAIL, outring); \ +} while (0) -extern int i830_wait_ring(struct drm_device * dev, int n, const char *caller); +extern int i830_wait_ring(struct drm_device *dev, int n, const char *caller); #define GFX_OP_USER_INTERRUPT ((0<<29)|(2<<23)) #define GFX_OP_BREAKPOINT_INTERRUPT ((0<<29)|(1<<23)) diff --git a/drivers/gpu/drm/i830/i830_irq.c b/drivers/gpu/drm/i830/i830_irq.c index 91ec2bb497e..d1a6b95d631 100644 --- a/drivers/gpu/drm/i830/i830_irq.c +++ b/drivers/gpu/drm/i830/i830_irq.c @@ -53,7 +53,7 @@ irqreturn_t i830_driver_irq_handler(DRM_IRQ_ARGS) return IRQ_HANDLED; } -static int i830_emit_irq(struct drm_device * dev) +static int i830_emit_irq(struct drm_device *dev) { drm_i830_private_t *dev_priv = dev->dev_private; RING_LOCALS; @@ -70,7 +70,7 @@ static int i830_emit_irq(struct drm_device * dev) return atomic_read(&dev_priv->irq_emitted); } -static int i830_wait_irq(struct drm_device * dev, int irq_nr) +static int i830_wait_irq(struct drm_device *dev, int irq_nr) { drm_i830_private_t *dev_priv = (drm_i830_private_t *) dev->dev_private; DECLARE_WAITQUEUE(entry, current); @@ -156,7 +156,7 @@ int i830_irq_wait(struct drm_device *dev, void *data, /* drm_dma.h hooks */ -void i830_driver_irq_preinstall(struct drm_device * dev) +void i830_driver_irq_preinstall(struct drm_device *dev) { drm_i830_private_t *dev_priv = (drm_i830_private_t *) dev->dev_private; @@ -168,14 +168,14 @@ void i830_driver_irq_preinstall(struct drm_device * dev) init_waitqueue_head(&dev_priv->irq_queue); } -void i830_driver_irq_postinstall(struct drm_device * dev) +void i830_driver_irq_postinstall(struct drm_device *dev) { drm_i830_private_t *dev_priv = (drm_i830_private_t *) dev->dev_private; I830_WRITE16(I830REG_INT_ENABLE_R, 0x2); } -void i830_driver_irq_uninstall(struct drm_device * dev) +void i830_driver_irq_uninstall(struct drm_device *dev) { drm_i830_private_t *dev_priv = (drm_i830_private_t *) dev->dev_private; if (!dev_priv) diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 2305a1234f1..f19ffe87af3 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -34,12 +34,15 @@ #include "i915_drm.h" #include "i915_drv.h" #include "i915_trace.h" +#include <linux/pci.h> #include <linux/vgaarb.h> #include <linux/acpi.h> #include <linux/pnp.h> #include <linux/vga_switcheroo.h> #include <linux/slab.h> +extern int intel_max_stolen; /* from AGP driver */ + /** * Sets up the hardware status page for devices that need a physical address * in the register. @@ -1256,7 +1259,7 @@ static void i915_setup_compression(struct drm_device *dev, int size) drm_mm_put_block(compressed_fb); } - if (!IS_GM45(dev)) { + if (!(IS_GM45(dev) || IS_IRONLAKE_M(dev))) { compressed_llb = drm_mm_search_free(&dev_priv->vram, 4096, 4096, 0); if (!compressed_llb) { @@ -1282,8 +1285,9 @@ static void i915_setup_compression(struct drm_device *dev, int size) intel_disable_fbc(dev); dev_priv->compressed_fb = compressed_fb; - - if (IS_GM45(dev)) { + if (IS_IRONLAKE_M(dev)) + I915_WRITE(ILK_DPFC_CB_BASE, compressed_fb->start); + else if (IS_GM45(dev)) { I915_WRITE(DPFC_CB_BASE, compressed_fb->start); } else { I915_WRITE(FBC_CFB_BASE, cfb_base); @@ -1291,7 +1295,7 @@ static void i915_setup_compression(struct drm_device *dev, int size) dev_priv->compressed_llb = compressed_llb; } - DRM_DEBUG("FBC base 0x%08lx, ll base 0x%08lx, size %dM\n", cfb_base, + DRM_DEBUG_KMS("FBC base 0x%08lx, ll base 0x%08lx, size %dM\n", cfb_base, ll_base, size >> 20); } @@ -1354,7 +1358,7 @@ static int i915_load_modeset_init(struct drm_device *dev, int fb_bar = IS_I9XX(dev) ? 2 : 0; int ret = 0; - dev->mode_config.fb_base = drm_get_resource_start(dev, fb_bar) & + dev->mode_config.fb_base = pci_resource_start(dev->pdev, fb_bar) & 0xff000000; /* Basic memrange allocator for stolen space (aka vram) */ @@ -2063,8 +2067,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) /* Add register map (needed for suspend/resume) */ mmio_bar = IS_I9XX(dev) ? 0 : 1; - base = drm_get_resource_start(dev, mmio_bar); - size = drm_get_resource_len(dev, mmio_bar); + base = pci_resource_start(dev->pdev, mmio_bar); + size = pci_resource_len(dev->pdev, mmio_bar); if (i915_get_bridge_dev(dev)) { ret = -EIO; @@ -2104,6 +2108,12 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) if (ret) goto out_iomapfree; + if (prealloc_size > intel_max_stolen) { + DRM_INFO("detected %dM stolen memory, trimming to %dM\n", + prealloc_size >> 20, intel_max_stolen >> 20); + prealloc_size = intel_max_stolen; + } + dev_priv->wq = create_singlethread_workqueue("i915"); if (dev_priv->wq == NULL) { DRM_ERROR("Failed to create our workqueue.\n"); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 423dc90c1e2..5044f653e8e 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -93,11 +93,11 @@ static const struct intel_device_info intel_i945gm_info = { }; static const struct intel_device_info intel_i965g_info = { - .is_i965g = 1, .is_i9xx = 1, .has_hotplug = 1, + .is_broadwater = 1, .is_i965g = 1, .is_i9xx = 1, .has_hotplug = 1, }; static const struct intel_device_info intel_i965gm_info = { - .is_i965g = 1, .is_mobile = 1, .is_i965gm = 1, .is_i9xx = 1, + .is_crestline = 1, .is_i965g = 1, .is_i965gm = 1, .is_i9xx = 1, .is_mobile = 1, .has_fbc = 1, .has_rc6 = 1, .has_hotplug = 1, }; @@ -114,7 +114,7 @@ static const struct intel_device_info intel_g45_info = { }; static const struct intel_device_info intel_gm45_info = { - .is_i965g = 1, .is_mobile = 1, .is_g4x = 1, .is_i9xx = 1, + .is_i965g = 1, .is_g4x = 1, .is_i9xx = 1, .is_mobile = 1, .need_gfx_hws = 1, .has_fbc = 1, .has_rc6 = 1, .has_pipe_cxsr = 1, .has_hotplug = 1, @@ -134,7 +134,7 @@ static const struct intel_device_info intel_ironlake_d_info = { static const struct intel_device_info intel_ironlake_m_info = { .is_ironlake = 1, .is_mobile = 1, .is_i965g = 1, .is_i9xx = 1, - .need_gfx_hws = 1, .has_rc6 = 1, + .need_gfx_hws = 1, .has_fbc = 1, .has_rc6 = 1, .has_hotplug = 1, }; @@ -148,33 +148,33 @@ static const struct intel_device_info intel_sandybridge_m_info = { .has_hotplug = 1, .is_gen6 = 1, }; -static const struct pci_device_id pciidlist[] = { - INTEL_VGA_DEVICE(0x3577, &intel_i830_info), - INTEL_VGA_DEVICE(0x2562, &intel_845g_info), - INTEL_VGA_DEVICE(0x3582, &intel_i85x_info), +static const struct pci_device_id pciidlist[] = { /* aka */ + INTEL_VGA_DEVICE(0x3577, &intel_i830_info), /* I830_M */ + INTEL_VGA_DEVICE(0x2562, &intel_845g_info), /* 845_G */ + INTEL_VGA_DEVICE(0x3582, &intel_i85x_info), /* I855_GM */ INTEL_VGA_DEVICE(0x358e, &intel_i85x_info), - INTEL_VGA_DEVICE(0x2572, &intel_i865g_info), - INTEL_VGA_DEVICE(0x2582, &intel_i915g_info), - INTEL_VGA_DEVICE(0x258a, &intel_i915g_info), - INTEL_VGA_DEVICE(0x2592, &intel_i915gm_info), - INTEL_VGA_DEVICE(0x2772, &intel_i945g_info), - INTEL_VGA_DEVICE(0x27a2, &intel_i945gm_info), - INTEL_VGA_DEVICE(0x27ae, &intel_i945gm_info), - INTEL_VGA_DEVICE(0x2972, &intel_i965g_info), - INTEL_VGA_DEVICE(0x2982, &intel_i965g_info), - INTEL_VGA_DEVICE(0x2992, &intel_i965g_info), - INTEL_VGA_DEVICE(0x29a2, &intel_i965g_info), - INTEL_VGA_DEVICE(0x29b2, &intel_g33_info), - INTEL_VGA_DEVICE(0x29c2, &intel_g33_info), - INTEL_VGA_DEVICE(0x29d2, &intel_g33_info), - INTEL_VGA_DEVICE(0x2a02, &intel_i965gm_info), - INTEL_VGA_DEVICE(0x2a12, &intel_i965gm_info), - INTEL_VGA_DEVICE(0x2a42, &intel_gm45_info), - INTEL_VGA_DEVICE(0x2e02, &intel_g45_info), - INTEL_VGA_DEVICE(0x2e12, &intel_g45_info), - INTEL_VGA_DEVICE(0x2e22, &intel_g45_info), - INTEL_VGA_DEVICE(0x2e32, &intel_g45_info), - INTEL_VGA_DEVICE(0x2e42, &intel_g45_info), + INTEL_VGA_DEVICE(0x2572, &intel_i865g_info), /* I865_G */ + INTEL_VGA_DEVICE(0x2582, &intel_i915g_info), /* I915_G */ + INTEL_VGA_DEVICE(0x258a, &intel_i915g_info), /* E7221_G */ + INTEL_VGA_DEVICE(0x2592, &intel_i915gm_info), /* I915_GM */ + INTEL_VGA_DEVICE(0x2772, &intel_i945g_info), /* I945_G */ + INTEL_VGA_DEVICE(0x27a2, &intel_i945gm_info), /* I945_GM */ + INTEL_VGA_DEVICE(0x27ae, &intel_i945gm_info), /* I945_GME */ + INTEL_VGA_DEVICE(0x2972, &intel_i965g_info), /* I946_GZ */ + INTEL_VGA_DEVICE(0x2982, &intel_i965g_info), /* G35_G */ + INTEL_VGA_DEVICE(0x2992, &intel_i965g_info), /* I965_Q */ + INTEL_VGA_DEVICE(0x29a2, &intel_i965g_info), /* I965_G */ + INTEL_VGA_DEVICE(0x29b2, &intel_g33_info), /* Q35_G */ + INTEL_VGA_DEVICE(0x29c2, &intel_g33_info), /* G33_G */ + INTEL_VGA_DEVICE(0x29d2, &intel_g33_info), /* Q33_G */ + INTEL_VGA_DEVICE(0x2a02, &intel_i965gm_info), /* I965_GM */ + INTEL_VGA_DEVICE(0x2a12, &intel_i965gm_info), /* I965_GME */ + INTEL_VGA_DEVICE(0x2a42, &intel_gm45_info), /* GM45_G */ + INTEL_VGA_DEVICE(0x2e02, &intel_g45_info), /* IGD_E_G */ + INTEL_VGA_DEVICE(0x2e12, &intel_g45_info), /* Q45_G */ + INTEL_VGA_DEVICE(0x2e22, &intel_g45_info), /* G45_G */ + INTEL_VGA_DEVICE(0x2e32, &intel_g45_info), /* G41_G */ + INTEL_VGA_DEVICE(0x2e42, &intel_g45_info), /* B43_G */ INTEL_VGA_DEVICE(0xa001, &intel_pineview_info), INTEL_VGA_DEVICE(0xa011, &intel_pineview_info), INTEL_VGA_DEVICE(0x0042, &intel_ironlake_d_info), @@ -340,7 +340,7 @@ int i965_reset(struct drm_device *dev, u8 flags) /* * Clear request list */ - i915_gem_retire_requests(dev, &dev_priv->render_ring); + i915_gem_retire_requests(dev); if (need_display) i915_save_display(dev); @@ -413,7 +413,7 @@ int i965_reset(struct drm_device *dev, u8 flags) static int __devinit i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - return drm_get_dev(pdev, ent, &driver); + return drm_get_pci_dev(pdev, ent, &driver); } static void @@ -482,7 +482,7 @@ static int i915_pm_poweroff(struct device *dev) return i915_drm_freeze(drm_dev); } -const struct dev_pm_ops i915_pm_ops = { +static const struct dev_pm_ops i915_pm_ops = { .suspend = i915_pm_suspend, .resume = i915_pm_resume, .freeze = i915_pm_freeze, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 2e1744d37ad..906663b9929 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -176,7 +176,8 @@ struct drm_i915_display_funcs { int (*get_display_clock_speed)(struct drm_device *dev); int (*get_fifo_size)(struct drm_device *dev, int plane); void (*update_wm)(struct drm_device *dev, int planea_clock, - int planeb_clock, int sr_hdisplay, int pixel_size); + int planeb_clock, int sr_hdisplay, int sr_htotal, + int pixel_size); /* clock updates for mode set */ /* cursor updates */ /* render clock increase/decrease */ @@ -200,6 +201,8 @@ struct intel_device_info { u8 need_gfx_hws : 1; u8 is_g4x : 1; u8 is_pineview : 1; + u8 is_broadwater : 1; + u8 is_crestline : 1; u8 is_ironlake : 1; u8 is_gen6 : 1; u8 has_fbc : 1; @@ -288,6 +291,8 @@ typedef struct drm_i915_private { struct timer_list hangcheck_timer; int hangcheck_count; uint32_t last_acthd; + uint32_t last_instdone; + uint32_t last_instdone1; struct drm_mm vram; @@ -547,6 +552,14 @@ typedef struct drm_i915_private { struct list_head fence_list; /** + * List of objects currently pending being freed. + * + * These objects are no longer in use, but due to a signal + * we were prevented from freeing them at the appointed time. + */ + struct list_head deferred_free_list; + + /** * We leave the user IRQ off as much as possible, * but this means that requests will finish and never * be retired once the system goes idle. Set a timer to @@ -677,7 +690,7 @@ struct drm_i915_gem_object { * * Size: 4 bits for 16 fences + sign (for FENCE_REG_NONE) */ - int fence_reg : 5; + signed int fence_reg : 5; /** * Used for checking the object doesn't appear more than once @@ -713,7 +726,7 @@ struct drm_i915_gem_object { * * In the worst case this is 1 + 1 + 1 + 2*2 = 7. That would fit into 3 * bits with absolutely no headroom. So use 4 bits. */ - int pin_count : 4; + unsigned int pin_count : 4; #define DRM_I915_GEM_OBJECT_MAX_PIN_COUNT 0xf /** AGP memory structure for our GTT binding. */ @@ -743,7 +756,7 @@ struct drm_i915_gem_object { uint32_t stride; /** Record of address bit 17 of each page at last unbind. */ - long *bit_17; + unsigned long *bit_17; /** AGP mapping type (AGP_USER_MEMORY or AGP_USER_CACHED_MEMORY */ uint32_t agp_type; @@ -955,8 +968,7 @@ uint32_t i915_get_gem_seqno(struct drm_device *dev, bool i915_seqno_passed(uint32_t seq1, uint32_t seq2); int i915_gem_object_get_fence_reg(struct drm_gem_object *obj); int i915_gem_object_put_fence_reg(struct drm_gem_object *obj); -void i915_gem_retire_requests(struct drm_device *dev, - struct intel_ring_buffer *ring); +void i915_gem_retire_requests(struct drm_device *dev); void i915_gem_retire_work_handler(struct work_struct *work); void i915_gem_clflush_object(struct drm_gem_object *obj); int i915_gem_object_set_domain(struct drm_gem_object *obj, @@ -986,7 +998,7 @@ void i915_gem_free_all_phys_object(struct drm_device *dev); int i915_gem_object_get_pages(struct drm_gem_object *obj, gfp_t gfpmask); void i915_gem_object_put_pages(struct drm_gem_object *obj); void i915_gem_release(struct drm_device * dev, struct drm_file *file_priv); -void i915_gem_object_flush_write_domain(struct drm_gem_object *obj); +int i915_gem_object_flush_write_domain(struct drm_gem_object *obj); void i915_gem_shrinker_init(void); void i915_gem_shrinker_exit(void); @@ -1046,6 +1058,7 @@ extern void intel_modeset_cleanup(struct drm_device *dev); extern int intel_modeset_vga_set_state(struct drm_device *dev, bool state); extern void i8xx_disable_fbc(struct drm_device *dev); extern void g4x_disable_fbc(struct drm_device *dev); +extern void ironlake_disable_fbc(struct drm_device *dev); extern void intel_disable_fbc(struct drm_device *dev); extern void intel_enable_fbc(struct drm_crtc *crtc, unsigned long interval); extern bool intel_fbc_enabled(struct drm_device *dev); @@ -1135,6 +1148,8 @@ extern int intel_trans_dp_port_sel (struct drm_crtc *crtc); #define IS_I945GM(dev) (INTEL_INFO(dev)->is_i945gm) #define IS_I965G(dev) (INTEL_INFO(dev)->is_i965g) #define IS_I965GM(dev) (INTEL_INFO(dev)->is_i965gm) +#define IS_BROADWATER(dev) (INTEL_INFO(dev)->is_broadwater) +#define IS_CRESTLINE(dev) (INTEL_INFO(dev)->is_crestline) #define IS_GM45(dev) ((dev)->pci_device == 0x2A42) #define IS_G4X(dev) (INTEL_INFO(dev)->is_g4x) #define IS_PINEVIEW_G(dev) ((dev)->pci_device == 0xa001) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 5aa747fc25a..2a4ed7ca8b4 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -35,7 +35,7 @@ #include <linux/swap.h> #include <linux/pci.h> -static void i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj); +static int i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj); static void i915_gem_object_flush_gtt_write_domain(struct drm_gem_object *obj); static void i915_gem_object_flush_cpu_write_domain(struct drm_gem_object *obj); static int i915_gem_object_set_to_cpu_domain(struct drm_gem_object *obj, @@ -53,6 +53,7 @@ static int i915_gem_evict_from_inactive_list(struct drm_device *dev); static int i915_gem_phys_pwrite(struct drm_device *dev, struct drm_gem_object *obj, struct drm_i915_gem_pwrite *args, struct drm_file *file_priv); +static void i915_gem_free_object_tail(struct drm_gem_object *obj); static LIST_HEAD(shrink_list); static DEFINE_SPINLOCK(shrink_list_lock); @@ -127,8 +128,7 @@ i915_gem_create_ioctl(struct drm_device *dev, void *data, return -ENOMEM; ret = drm_gem_handle_create(file_priv, obj, &handle); - drm_gem_object_handle_unreference_unlocked(obj); - + drm_gem_object_unreference_unlocked(obj); if (ret) return ret; @@ -496,10 +496,10 @@ fast_user_write(struct io_mapping *mapping, char *vaddr_atomic; unsigned long unwritten; - vaddr_atomic = io_mapping_map_atomic_wc(mapping, page_base); + vaddr_atomic = io_mapping_map_atomic_wc(mapping, page_base, KM_USER0); unwritten = __copy_from_user_inatomic_nocache(vaddr_atomic + page_offset, user_data, length); - io_mapping_unmap_atomic(vaddr_atomic); + io_mapping_unmap_atomic(vaddr_atomic, KM_USER0); if (unwritten) return -EFAULT; return 0; @@ -1709,9 +1709,9 @@ i915_get_gem_seqno(struct drm_device *dev, /** * This function clears the request list as sequence numbers are passed. */ -void -i915_gem_retire_requests(struct drm_device *dev, - struct intel_ring_buffer *ring) +static void +i915_gem_retire_requests_ring(struct drm_device *dev, + struct intel_ring_buffer *ring) { drm_i915_private_t *dev_priv = dev->dev_private; uint32_t seqno; @@ -1751,6 +1751,30 @@ i915_gem_retire_requests(struct drm_device *dev, } void +i915_gem_retire_requests(struct drm_device *dev) +{ + drm_i915_private_t *dev_priv = dev->dev_private; + + if (!list_empty(&dev_priv->mm.deferred_free_list)) { + struct drm_i915_gem_object *obj_priv, *tmp; + + /* We must be careful that during unbind() we do not + * accidentally infinitely recurse into retire requests. + * Currently: + * retire -> free -> unbind -> wait -> retire_ring + */ + list_for_each_entry_safe(obj_priv, tmp, + &dev_priv->mm.deferred_free_list, + list) + i915_gem_free_object_tail(&obj_priv->base); + } + + i915_gem_retire_requests_ring(dev, &dev_priv->render_ring); + if (HAS_BSD(dev)) + i915_gem_retire_requests_ring(dev, &dev_priv->bsd_ring); +} + +void i915_gem_retire_work_handler(struct work_struct *work) { drm_i915_private_t *dev_priv; @@ -1761,10 +1785,7 @@ i915_gem_retire_work_handler(struct work_struct *work) dev = dev_priv->dev; mutex_lock(&dev->struct_mutex); - i915_gem_retire_requests(dev, &dev_priv->render_ring); - - if (HAS_BSD(dev)) - i915_gem_retire_requests(dev, &dev_priv->bsd_ring); + i915_gem_retire_requests(dev); if (!dev_priv->mm.suspended && (!list_empty(&dev_priv->render_ring.request_list) || @@ -1832,7 +1853,7 @@ i915_do_wait_request(struct drm_device *dev, uint32_t seqno, * a separate wait queue to handle that. */ if (ret == 0) - i915_gem_retire_requests(dev, ring); + i915_gem_retire_requests_ring(dev, ring); return ret; } @@ -1945,11 +1966,12 @@ i915_gem_object_unbind(struct drm_gem_object *obj) * before we unbind. */ ret = i915_gem_object_set_to_cpu_domain(obj, 1); - if (ret) { - if (ret != -ERESTARTSYS) - DRM_ERROR("set_domain failed: %d\n", ret); + if (ret == -ERESTARTSYS) return ret; - } + /* Continue on if we fail due to EIO, the GPU is hung so we + * should be safe and we need to cleanup or else we might + * cause memory corruption through use-after-free. + */ BUG_ON(obj_priv->active); @@ -1985,7 +2007,7 @@ i915_gem_object_unbind(struct drm_gem_object *obj) trace_i915_gem_object_unbind(obj); - return 0; + return ret; } static struct drm_gem_object * @@ -2107,10 +2129,7 @@ i915_gem_evict_something(struct drm_device *dev, int min_size) struct intel_ring_buffer *render_ring = &dev_priv->render_ring; struct intel_ring_buffer *bsd_ring = &dev_priv->bsd_ring; for (;;) { - i915_gem_retire_requests(dev, render_ring); - - if (HAS_BSD(dev)) - i915_gem_retire_requests(dev, bsd_ring); + i915_gem_retire_requests(dev); /* If there's an inactive buffer available now, grab it * and be done. @@ -2583,7 +2602,10 @@ i915_gem_object_put_fence_reg(struct drm_gem_object *obj) if (!IS_I965G(dev)) { int ret; - i915_gem_object_flush_gpu_write_domain(obj); + ret = i915_gem_object_flush_gpu_write_domain(obj); + if (ret != 0) + return ret; + ret = i915_gem_object_wait_rendering(obj); if (ret != 0) return ret; @@ -2634,10 +2656,8 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment) if (free_space != NULL) { obj_priv->gtt_space = drm_mm_get_block(free_space, obj->size, alignment); - if (obj_priv->gtt_space != NULL) { - obj_priv->gtt_space->private = obj; + if (obj_priv->gtt_space != NULL) obj_priv->gtt_offset = obj_priv->gtt_space->start; - } } if (obj_priv->gtt_space == NULL) { /* If the gtt is empty and we're still having trouble @@ -2733,7 +2753,7 @@ i915_gem_clflush_object(struct drm_gem_object *obj) } /** Flushes any GPU write domain for the object if it's dirty. */ -static void +static int i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; @@ -2741,17 +2761,18 @@ i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj) struct drm_i915_gem_object *obj_priv = to_intel_bo(obj); if ((obj->write_domain & I915_GEM_GPU_DOMAINS) == 0) - return; + return 0; /* Queue the GPU write cache flushing we need. */ old_write_domain = obj->write_domain; i915_gem_flush(dev, 0, obj->write_domain); - (void) i915_add_request(dev, NULL, obj->write_domain, obj_priv->ring); - BUG_ON(obj->write_domain); + if (i915_add_request(dev, NULL, obj->write_domain, obj_priv->ring) == 0) + return -ENOMEM; trace_i915_gem_object_change_domain(obj, obj->read_domains, old_write_domain); + return 0; } /** Flushes the GTT write domain for the object if it's dirty. */ @@ -2795,9 +2816,11 @@ i915_gem_object_flush_cpu_write_domain(struct drm_gem_object *obj) old_write_domain); } -void +int i915_gem_object_flush_write_domain(struct drm_gem_object *obj) { + int ret = 0; + switch (obj->write_domain) { case I915_GEM_DOMAIN_GTT: i915_gem_object_flush_gtt_write_domain(obj); @@ -2806,9 +2829,11 @@ i915_gem_object_flush_write_domain(struct drm_gem_object *obj) i915_gem_object_flush_cpu_write_domain(obj); break; default: - i915_gem_object_flush_gpu_write_domain(obj); + ret = i915_gem_object_flush_gpu_write_domain(obj); break; } + + return ret; } /** @@ -2828,7 +2853,10 @@ i915_gem_object_set_to_gtt_domain(struct drm_gem_object *obj, int write) if (obj_priv->gtt_space == NULL) return -EINVAL; - i915_gem_object_flush_gpu_write_domain(obj); + ret = i915_gem_object_flush_gpu_write_domain(obj); + if (ret != 0) + return ret; + /* Wait on any GPU rendering and flushing to occur. */ ret = i915_gem_object_wait_rendering(obj); if (ret != 0) @@ -2878,7 +2906,9 @@ i915_gem_object_set_to_display_plane(struct drm_gem_object *obj) if (obj_priv->gtt_space == NULL) return -EINVAL; - i915_gem_object_flush_gpu_write_domain(obj); + ret = i915_gem_object_flush_gpu_write_domain(obj); + if (ret) + return ret; /* Wait on any GPU rendering and flushing to occur. */ if (obj_priv->active) { @@ -2926,7 +2956,10 @@ i915_gem_object_set_to_cpu_domain(struct drm_gem_object *obj, int write) uint32_t old_write_domain, old_read_domains; int ret; - i915_gem_object_flush_gpu_write_domain(obj); + ret = i915_gem_object_flush_gpu_write_domain(obj); + if (ret) + return ret; + /* Wait on any GPU rendering and flushing to occur. */ ret = i915_gem_object_wait_rendering(obj); if (ret != 0) @@ -3216,7 +3249,10 @@ i915_gem_object_set_cpu_read_domain_range(struct drm_gem_object *obj, if (offset == 0 && size == obj->size) return i915_gem_object_set_to_cpu_domain(obj, 0); - i915_gem_object_flush_gpu_write_domain(obj); + ret = i915_gem_object_flush_gpu_write_domain(obj); + if (ret) + return ret; + /* Wait on any GPU rendering and flushing to occur. */ ret = i915_gem_object_wait_rendering(obj); if (ret != 0) @@ -3451,7 +3487,8 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj, reloc_offset = obj_priv->gtt_offset + reloc->offset; reloc_page = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, (reloc_offset & - ~(PAGE_SIZE - 1))); + ~(PAGE_SIZE - 1)), + KM_USER0); reloc_entry = (uint32_t __iomem *)(reloc_page + (reloc_offset & (PAGE_SIZE - 1))); reloc_val = target_obj_priv->gtt_offset + reloc->delta; @@ -3462,7 +3499,7 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj, readl(reloc_entry), reloc_val); #endif writel(reloc_val, reloc_entry); - io_mapping_unmap_atomic(reloc_page); + io_mapping_unmap_atomic(reloc_page, KM_USER0); /* The updated presumed offset for this entry will be * copied back out to the user. @@ -4313,7 +4350,6 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, struct drm_i915_gem_busy *args = data; struct drm_gem_object *obj; struct drm_i915_gem_object *obj_priv; - drm_i915_private_t *dev_priv = dev->dev_private; obj = drm_gem_object_lookup(dev, file_priv, args->handle); if (obj == NULL) { @@ -4328,10 +4364,7 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, * actually unmasked, and our working set ends up being larger than * required. */ - i915_gem_retire_requests(dev, &dev_priv->render_ring); - - if (HAS_BSD(dev)) - i915_gem_retire_requests(dev, &dev_priv->bsd_ring); + i915_gem_retire_requests(dev); obj_priv = to_intel_bo(obj); /* Don't count being on the flushing list against the object being @@ -4441,20 +4474,19 @@ int i915_gem_init_object(struct drm_gem_object *obj) return 0; } -void i915_gem_free_object(struct drm_gem_object *obj) +static void i915_gem_free_object_tail(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; + drm_i915_private_t *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj_priv = to_intel_bo(obj); + int ret; - trace_i915_gem_object_destroy(obj); - - while (obj_priv->pin_count > 0) - i915_gem_object_unpin(obj); - - if (obj_priv->phys_obj) - i915_gem_detach_phys_object(dev, obj); - - i915_gem_object_unbind(obj); + ret = i915_gem_object_unbind(obj); + if (ret == -ERESTARTSYS) { + list_move(&obj_priv->list, + &dev_priv->mm.deferred_free_list); + return; + } if (obj_priv->mmap_offset) i915_gem_free_mmap_offset(obj); @@ -4466,6 +4498,22 @@ void i915_gem_free_object(struct drm_gem_object *obj) kfree(obj_priv); } +void i915_gem_free_object(struct drm_gem_object *obj) +{ + struct drm_device *dev = obj->dev; + struct drm_i915_gem_object *obj_priv = to_intel_bo(obj); + + trace_i915_gem_object_destroy(obj); + + while (obj_priv->pin_count > 0) + i915_gem_object_unpin(obj); + + if (obj_priv->phys_obj) + i915_gem_detach_phys_object(dev, obj); + + i915_gem_free_object_tail(obj); +} + /** Unbinds all inactive objects. */ static int i915_gem_evict_from_inactive_list(struct drm_device *dev) @@ -4689,9 +4737,19 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, BUG_ON(HAS_BSD(dev) && !list_empty(&dev_priv->bsd_ring.request_list)); mutex_unlock(&dev->struct_mutex); - drm_irq_install(dev); + ret = drm_irq_install(dev); + if (ret) + goto cleanup_ringbuffer; return 0; + +cleanup_ringbuffer: + mutex_lock(&dev->struct_mutex); + i915_gem_cleanup_ringbuffer(dev); + dev_priv->mm.suspended = 1; + mutex_unlock(&dev->struct_mutex); + + return ret; } int @@ -4729,6 +4787,7 @@ i915_gem_load(struct drm_device *dev) INIT_LIST_HEAD(&dev_priv->mm.gpu_write_list); INIT_LIST_HEAD(&dev_priv->mm.inactive_list); INIT_LIST_HEAD(&dev_priv->mm.fence_list); + INIT_LIST_HEAD(&dev_priv->mm.deferred_free_list); INIT_LIST_HEAD(&dev_priv->render_ring.active_list); INIT_LIST_HEAD(&dev_priv->render_ring.request_list); if (HAS_BSD(dev)) { @@ -5027,10 +5086,7 @@ rescan: continue; spin_unlock(&shrink_list_lock); - i915_gem_retire_requests(dev, &dev_priv->render_ring); - - if (HAS_BSD(dev)) - i915_gem_retire_requests(dev, &dev_priv->bsd_ring); + i915_gem_retire_requests(dev); list_for_each_entry_safe(obj_priv, next_obj, &dev_priv->mm.inactive_list, diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 4b7c49d4257..155719e4d16 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -333,8 +333,6 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, i915_gem_release_mmap(obj); if (ret != 0) { - WARN(ret != -ERESTARTSYS, - "failed to reset object for tiling switch"); args->tiling_mode = obj_priv->tiling_mode; args->stride = obj_priv->stride; goto err; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index dba53d4b9fb..85785a8844e 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -171,10 +171,10 @@ void intel_enable_asle (struct drm_device *dev) ironlake_enable_display_irq(dev_priv, DE_GSE); else { i915_enable_pipestat(dev_priv, 1, - I915_LEGACY_BLC_EVENT_ENABLE); + PIPE_LEGACY_BLC_EVENT_ENABLE); if (IS_I965G(dev)) i915_enable_pipestat(dev_priv, 0, - I915_LEGACY_BLC_EVENT_ENABLE); + PIPE_LEGACY_BLC_EVENT_ENABLE); } } @@ -842,7 +842,6 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) u32 iir, new_iir; u32 pipea_stats, pipeb_stats; u32 vblank_status; - u32 vblank_enable; int vblank = 0; unsigned long irqflags; int irq_received; @@ -856,13 +855,10 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) iir = I915_READ(IIR); - if (IS_I965G(dev)) { - vblank_status = I915_START_VBLANK_INTERRUPT_STATUS; - vblank_enable = PIPE_START_VBLANK_INTERRUPT_ENABLE; - } else { - vblank_status = I915_VBLANK_INTERRUPT_STATUS; - vblank_enable = I915_VBLANK_INTERRUPT_ENABLE; - } + if (IS_I965G(dev)) + vblank_status = PIPE_START_VBLANK_INTERRUPT_STATUS; + else + vblank_status = PIPE_VBLANK_INTERRUPT_STATUS; for (;;) { irq_received = iir != 0; @@ -966,8 +962,8 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) intel_finish_page_flip(dev, 1); } - if ((pipea_stats & I915_LEGACY_BLC_EVENT_STATUS) || - (pipeb_stats & I915_LEGACY_BLC_EVENT_STATUS) || + if ((pipea_stats & PIPE_LEGACY_BLC_EVENT_STATUS) || + (pipeb_stats & PIPE_LEGACY_BLC_EVENT_STATUS) || (iir & I915_ASLE_INTERRUPT)) opregion_asle_intr(dev); @@ -1233,16 +1229,21 @@ void i915_hangcheck_elapsed(unsigned long data) { struct drm_device *dev = (struct drm_device *)data; drm_i915_private_t *dev_priv = dev->dev_private; - uint32_t acthd; + uint32_t acthd, instdone, instdone1; /* No reset support on this chip yet. */ if (IS_GEN6(dev)) return; - if (!IS_I965G(dev)) + if (!IS_I965G(dev)) { acthd = I915_READ(ACTHD); - else + instdone = I915_READ(INSTDONE); + instdone1 = 0; + } else { acthd = I915_READ(ACTHD_I965); + instdone = I915_READ(INSTDONE_I965); + instdone1 = I915_READ(INSTDONE1); + } /* If all work is done then ACTHD clearly hasn't advanced. */ if (list_empty(&dev_priv->render_ring.request_list) || @@ -1253,21 +1254,24 @@ void i915_hangcheck_elapsed(unsigned long data) return; } - if (dev_priv->last_acthd == acthd && dev_priv->hangcheck_count > 0) { - DRM_ERROR("Hangcheck timer elapsed... GPU hung\n"); - i915_handle_error(dev, true); - return; - } + if (dev_priv->last_acthd == acthd && + dev_priv->last_instdone == instdone && + dev_priv->last_instdone1 == instdone1) { + if (dev_priv->hangcheck_count++ > 1) { + DRM_ERROR("Hangcheck timer elapsed... GPU hung\n"); + i915_handle_error(dev, true); + return; + } + } else { + dev_priv->hangcheck_count = 0; + + dev_priv->last_acthd = acthd; + dev_priv->last_instdone = instdone; + dev_priv->last_instdone1 = instdone1; + } /* Reset timer case chip hangs without another request being added */ mod_timer(&dev_priv->hangcheck_timer, jiffies + DRM_I915_HANGCHECK_PERIOD); - - if (acthd != dev_priv->last_acthd) - dev_priv->hangcheck_count = 0; - else - dev_priv->hangcheck_count++; - - dev_priv->last_acthd = acthd; } /* drm_dma.h hooks diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index cf41c672def..281db6e5403 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -442,7 +442,7 @@ #define GEN6_RENDER_IMR 0x20a8 #define GEN6_RENDER_CONTEXT_SWITCH_INTERRUPT (1 << 8) #define GEN6_RENDER_PPGTT_PAGE_FAULT (1 << 7) -#define GEN6_RENDER TIMEOUT_COUNTER_EXPIRED (1 << 6) +#define GEN6_RENDER_TIMEOUT_COUNTER_EXPIRED (1 << 6) #define GEN6_RENDER_L3_PARITY_ERROR (1 << 5) #define GEN6_RENDER_PIPE_CONTROL_NOTIFY_INTERRUPT (1 << 4) #define GEN6_RENDER_COMMAND_PARSER_MASTER_ERROR (1 << 3) @@ -530,6 +530,21 @@ #define DPFC_CHICKEN 0x3224 #define DPFC_HT_MODIFY (1<<31) +/* Framebuffer compression for Ironlake */ +#define ILK_DPFC_CB_BASE 0x43200 +#define ILK_DPFC_CONTROL 0x43208 +/* The bit 28-8 is reserved */ +#define DPFC_RESERVED (0x1FFFFF00) +#define ILK_DPFC_RECOMP_CTL 0x4320c +#define ILK_DPFC_STATUS 0x43210 +#define ILK_DPFC_FENCE_YOFF 0x43218 +#define ILK_DPFC_CHICKEN 0x43224 +#define ILK_FBC_RT_BASE 0x2128 +#define ILK_FBC_RT_VALID (1<<0) + +#define ILK_DISPLAY_CHICKEN1 0x42000 +#define ILK_FBCQ_DIS (1<<22) + /* * GPIO regs */ @@ -595,32 +610,6 @@ #define DPLL_FPA01_P1_POST_DIV_MASK 0x00ff0000 /* i915 */ #define DPLL_FPA01_P1_POST_DIV_MASK_PINEVIEW 0x00ff8000 /* Pineview */ -#define I915_FIFO_UNDERRUN_STATUS (1UL<<31) -#define I915_CRC_ERROR_ENABLE (1UL<<29) -#define I915_CRC_DONE_ENABLE (1UL<<28) -#define I915_GMBUS_EVENT_ENABLE (1UL<<27) -#define I915_VSYNC_INTERRUPT_ENABLE (1UL<<25) -#define I915_DISPLAY_LINE_COMPARE_ENABLE (1UL<<24) -#define I915_DPST_EVENT_ENABLE (1UL<<23) -#define I915_LEGACY_BLC_EVENT_ENABLE (1UL<<22) -#define I915_ODD_FIELD_INTERRUPT_ENABLE (1UL<<21) -#define I915_EVEN_FIELD_INTERRUPT_ENABLE (1UL<<20) -#define I915_START_VBLANK_INTERRUPT_ENABLE (1UL<<18) /* 965 or later */ -#define I915_VBLANK_INTERRUPT_ENABLE (1UL<<17) -#define I915_OVERLAY_UPDATED_ENABLE (1UL<<16) -#define I915_CRC_ERROR_INTERRUPT_STATUS (1UL<<13) -#define I915_CRC_DONE_INTERRUPT_STATUS (1UL<<12) -#define I915_GMBUS_INTERRUPT_STATUS (1UL<<11) -#define I915_VSYNC_INTERRUPT_STATUS (1UL<<9) -#define I915_DISPLAY_LINE_COMPARE_STATUS (1UL<<8) -#define I915_DPST_EVENT_STATUS (1UL<<7) -#define I915_LEGACY_BLC_EVENT_STATUS (1UL<<6) -#define I915_ODD_FIELD_INTERRUPT_STATUS (1UL<<5) -#define I915_EVEN_FIELD_INTERRUPT_STATUS (1UL<<4) -#define I915_START_VBLANK_INTERRUPT_STATUS (1UL<<2) /* 965 or later */ -#define I915_VBLANK_INTERRUPT_STATUS (1UL<<1) -#define I915_OVERLAY_UPDATED_STATUS (1UL<<0) - #define SRX_INDEX 0x3c4 #define SRX_DATA 0x3c5 #define SR01 1 @@ -2166,7 +2155,8 @@ #define I830_FIFO_LINE_SIZE 32 #define G4X_FIFO_SIZE 127 -#define I945_FIFO_SIZE 127 /* 945 & 965 */ +#define I965_FIFO_SIZE 512 +#define I945_FIFO_SIZE 127 #define I915_FIFO_SIZE 95 #define I855GM_FIFO_SIZE 127 /* In cachelines */ #define I830_FIFO_SIZE 95 @@ -2185,6 +2175,9 @@ #define PINEVIEW_CURSOR_DFT_WM 0 #define PINEVIEW_CURSOR_GUARD_WM 5 +#define I965_CURSOR_FIFO 64 +#define I965_CURSOR_MAX_WM 32 +#define I965_CURSOR_DFT_WM 8 /* define the Watermark register on Ironlake */ #define WM0_PIPEA_ILK 0x45100 @@ -2212,6 +2205,9 @@ #define ILK_DISPLAY_FIFO 128 #define ILK_DISPLAY_MAXWM 64 #define ILK_DISPLAY_DFTWM 8 +#define ILK_CURSOR_FIFO 32 +#define ILK_CURSOR_MAXWM 16 +#define ILK_CURSOR_DFTWM 8 #define ILK_DISPLAY_SR_FIFO 512 #define ILK_DISPLAY_MAX_SRWM 0x1ff @@ -2510,6 +2506,10 @@ #define ILK_VSDPFD_FULL (1<<21) #define ILK_DSPCLK_GATE 0x42020 #define ILK_DPARB_CLK_GATE (1<<5) +/* According to spec this bit 7/8/9 of 0x42020 should be set to enable FBC */ +#define ILK_CLK_FBC (1<<7) +#define ILK_DPFC_DIS1 (1<<8) +#define ILK_DPFC_DIS2 (1<<9) #define DISP_ARB_CTL 0x45000 #define DISP_TILE_SURFACE_SWIZZLING (1<<13) diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 60a5800fba6..6e2025274db 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -602,7 +602,9 @@ void i915_save_display(struct drm_device *dev) /* Only save FBC state on the platform that supports FBC */ if (I915_HAS_FBC(dev)) { - if (IS_GM45(dev)) { + if (IS_IRONLAKE_M(dev)) { + dev_priv->saveDPFC_CB_BASE = I915_READ(ILK_DPFC_CB_BASE); + } else if (IS_GM45(dev)) { dev_priv->saveDPFC_CB_BASE = I915_READ(DPFC_CB_BASE); } else { dev_priv->saveFBC_CFB_BASE = I915_READ(FBC_CFB_BASE); @@ -706,7 +708,10 @@ void i915_restore_display(struct drm_device *dev) /* only restore FBC info on the platform that supports FBC*/ if (I915_HAS_FBC(dev)) { - if (IS_GM45(dev)) { + if (IS_IRONLAKE_M(dev)) { + ironlake_disable_fbc(dev); + I915_WRITE(ILK_DPFC_CB_BASE, dev_priv->saveDPFC_CB_BASE); + } else if (IS_GM45(dev)) { g4x_disable_fbc(dev); I915_WRITE(DPFC_CB_BASE, dev_priv->saveDPFC_CB_BASE); } else { diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index fab21760dd5..fea97a21cc1 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -262,6 +262,42 @@ DEFINE_EVENT(i915_ring, i915_ring_wait_end, TP_ARGS(dev) ); +TRACE_EVENT(i915_flip_request, + TP_PROTO(int plane, struct drm_gem_object *obj), + + TP_ARGS(plane, obj), + + TP_STRUCT__entry( + __field(int, plane) + __field(struct drm_gem_object *, obj) + ), + + TP_fast_assign( + __entry->plane = plane; + __entry->obj = obj; + ), + + TP_printk("plane=%d, obj=%p", __entry->plane, __entry->obj) +); + +TRACE_EVENT(i915_flip_complete, + TP_PROTO(int plane, struct drm_gem_object *obj), + + TP_ARGS(plane, obj), + + TP_STRUCT__entry( + __field(int, plane) + __field(struct drm_gem_object *, obj) + ), + + TP_fast_assign( + __entry->plane = plane; + __entry->obj = obj; + ), + + TP_printk("plane=%d, obj=%p", __entry->plane, __entry->obj) +); + #endif /* _I915_TRACE_H_ */ /* This part must be outside protection */ diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 5e21b311982..1e5e0d379fa 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -33,6 +33,7 @@ #include "intel_drv.h" #include "i915_drm.h" #include "i915_drv.h" +#include "i915_trace.h" #include "drm_dp_helper.h" #include "drm_crtc_helper.h" @@ -42,6 +43,7 @@ bool intel_pipe_has_type (struct drm_crtc *crtc, int type); static void intel_update_watermarks(struct drm_device *dev); static void intel_increase_pllclock(struct drm_crtc *crtc, bool schedule); +static void intel_crtc_update_cursor(struct drm_crtc *crtc); typedef struct { /* given values */ @@ -322,6 +324,9 @@ struct intel_limit { #define IRONLAKE_DP_P1_MIN 1 #define IRONLAKE_DP_P1_MAX 2 +/* FDI */ +#define IRONLAKE_FDI_FREQ 2700000 /* in kHz for mode->clock */ + static bool intel_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, int target, int refclk, intel_clock_t *best_clock); @@ -975,7 +980,10 @@ void intel_wait_for_vblank(struct drm_device *dev) { /* Wait for 20ms, i.e. one cycle at 50hz. */ - msleep(20); + if (in_dbg_master()) + mdelay(20); /* The kernel debugger cannot call msleep() */ + else + msleep(20); } /* Parameters have changed, update FBC info */ @@ -1122,6 +1130,67 @@ static bool g4x_fbc_enabled(struct drm_device *dev) return I915_READ(DPFC_CONTROL) & DPFC_CTL_EN; } +static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_framebuffer *fb = crtc->fb; + struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb); + struct drm_i915_gem_object *obj_priv = to_intel_bo(intel_fb->obj); + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + int plane = (intel_crtc->plane == 0) ? DPFC_CTL_PLANEA : + DPFC_CTL_PLANEB; + unsigned long stall_watermark = 200; + u32 dpfc_ctl; + + dev_priv->cfb_pitch = (dev_priv->cfb_pitch / 64) - 1; + dev_priv->cfb_fence = obj_priv->fence_reg; + dev_priv->cfb_plane = intel_crtc->plane; + + dpfc_ctl = I915_READ(ILK_DPFC_CONTROL); + dpfc_ctl &= DPFC_RESERVED; + dpfc_ctl |= (plane | DPFC_CTL_LIMIT_1X); + if (obj_priv->tiling_mode != I915_TILING_NONE) { + dpfc_ctl |= (DPFC_CTL_FENCE_EN | dev_priv->cfb_fence); + I915_WRITE(ILK_DPFC_CHICKEN, DPFC_HT_MODIFY); + } else { + I915_WRITE(ILK_DPFC_CHICKEN, ~DPFC_HT_MODIFY); + } + + I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl); + I915_WRITE(ILK_DPFC_RECOMP_CTL, DPFC_RECOMP_STALL_EN | + (stall_watermark << DPFC_RECOMP_STALL_WM_SHIFT) | + (interval << DPFC_RECOMP_TIMER_COUNT_SHIFT)); + I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->y); + I915_WRITE(ILK_FBC_RT_BASE, obj_priv->gtt_offset | ILK_FBC_RT_VALID); + /* enable it... */ + I915_WRITE(ILK_DPFC_CONTROL, I915_READ(ILK_DPFC_CONTROL) | + DPFC_CTL_EN); + + DRM_DEBUG_KMS("enabled fbc on plane %d\n", intel_crtc->plane); +} + +void ironlake_disable_fbc(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 dpfc_ctl; + + /* Disable compression */ + dpfc_ctl = I915_READ(ILK_DPFC_CONTROL); + dpfc_ctl &= ~DPFC_CTL_EN; + I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl); + intel_wait_for_vblank(dev); + + DRM_DEBUG_KMS("disabled FBC\n"); +} + +static bool ironlake_fbc_enabled(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + return I915_READ(ILK_DPFC_CONTROL) & DPFC_CTL_EN; +} + bool intel_fbc_enabled(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -1248,6 +1317,10 @@ static void intel_update_fbc(struct drm_crtc *crtc, goto out_disable; } + /* If the kernel debugger is active, always disable compression */ + if (in_dbg_master()) + goto out_disable; + if (intel_fbc_enabled(dev)) { /* We can re-enable it in this case, but need to update pitch */ if ((fb->pitch > dev_priv->cfb_pitch) || @@ -1279,7 +1352,12 @@ intel_pin_and_fence_fb_obj(struct drm_device *dev, struct drm_gem_object *obj) switch (obj_priv->tiling_mode) { case I915_TILING_NONE: - alignment = 64 * 1024; + if (IS_BROADWATER(dev) || IS_CRESTLINE(dev)) + alignment = 128 * 1024; + else if (IS_I965G(dev)) + alignment = 4 * 1024; + else + alignment = 64 * 1024; break; case I915_TILING_X: /* pin() will align the object as required by fence */ @@ -1314,6 +1392,98 @@ intel_pin_and_fence_fb_obj(struct drm_device *dev, struct drm_gem_object *obj) return 0; } +/* Assume fb object is pinned & idle & fenced and just update base pointers */ +static int +intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb, + int x, int y) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_framebuffer *intel_fb; + struct drm_i915_gem_object *obj_priv; + struct drm_gem_object *obj; + int plane = intel_crtc->plane; + unsigned long Start, Offset; + int dspbase = (plane == 0 ? DSPAADDR : DSPBADDR); + int dspsurf = (plane == 0 ? DSPASURF : DSPBSURF); + int dspstride = (plane == 0) ? DSPASTRIDE : DSPBSTRIDE; + int dsptileoff = (plane == 0 ? DSPATILEOFF : DSPBTILEOFF); + int dspcntr_reg = (plane == 0) ? DSPACNTR : DSPBCNTR; + u32 dspcntr; + + switch (plane) { + case 0: + case 1: + break; + default: + DRM_ERROR("Can't update plane %d in SAREA\n", plane); + return -EINVAL; + } + + intel_fb = to_intel_framebuffer(fb); + obj = intel_fb->obj; + obj_priv = to_intel_bo(obj); + + dspcntr = I915_READ(dspcntr_reg); + /* Mask out pixel format bits in case we change it */ + dspcntr &= ~DISPPLANE_PIXFORMAT_MASK; + switch (fb->bits_per_pixel) { + case 8: + dspcntr |= DISPPLANE_8BPP; + break; + case 16: + if (fb->depth == 15) + dspcntr |= DISPPLANE_15_16BPP; + else + dspcntr |= DISPPLANE_16BPP; + break; + case 24: + case 32: + dspcntr |= DISPPLANE_32BPP_NO_ALPHA; + break; + default: + DRM_ERROR("Unknown color depth\n"); + return -EINVAL; + } + if (IS_I965G(dev)) { + if (obj_priv->tiling_mode != I915_TILING_NONE) + dspcntr |= DISPPLANE_TILED; + else + dspcntr &= ~DISPPLANE_TILED; + } + + if (IS_IRONLAKE(dev)) + /* must disable */ + dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE; + + I915_WRITE(dspcntr_reg, dspcntr); + + Start = obj_priv->gtt_offset; + Offset = y * fb->pitch + x * (fb->bits_per_pixel / 8); + + DRM_DEBUG("Writing base %08lX %08lX %d %d\n", Start, Offset, x, y); + I915_WRITE(dspstride, fb->pitch); + if (IS_I965G(dev)) { + I915_WRITE(dspbase, Offset); + I915_READ(dspbase); + I915_WRITE(dspsurf, Start); + I915_READ(dspsurf); + I915_WRITE(dsptileoff, (y << 16) | x); + } else { + I915_WRITE(dspbase, Start + Offset); + I915_READ(dspbase); + } + + if ((IS_I965G(dev) || plane == 0)) + intel_update_fbc(crtc, &crtc->mode); + + intel_wait_for_vblank(dev); + intel_increase_pllclock(crtc, true); + + return 0; +} + static int intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, struct drm_framebuffer *old_fb) @@ -1554,6 +1724,15 @@ static void ironlake_fdi_link_train(struct drm_crtc *crtc) int fdi_rx_imr_reg = (pipe == 0) ? FDI_RXA_IMR : FDI_RXB_IMR; u32 temp, tries = 0; + /* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit + for train result */ + temp = I915_READ(fdi_rx_imr_reg); + temp &= ~FDI_RX_SYMBOL_LOCK; + temp &= ~FDI_RX_BIT_LOCK; + I915_WRITE(fdi_rx_imr_reg, temp); + I915_READ(fdi_rx_imr_reg); + udelay(150); + /* enable CPU FDI TX and PCH FDI RX */ temp = I915_READ(fdi_tx_reg); temp |= FDI_TX_ENABLE; @@ -1571,16 +1750,7 @@ static void ironlake_fdi_link_train(struct drm_crtc *crtc) I915_READ(fdi_rx_reg); udelay(150); - /* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit - for train result */ - temp = I915_READ(fdi_rx_imr_reg); - temp &= ~FDI_RX_SYMBOL_LOCK; - temp &= ~FDI_RX_BIT_LOCK; - I915_WRITE(fdi_rx_imr_reg, temp); - I915_READ(fdi_rx_imr_reg); - udelay(150); - - for (;;) { + for (tries = 0; tries < 5; tries++) { temp = I915_READ(fdi_rx_iir_reg); DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp); @@ -1590,14 +1760,9 @@ static void ironlake_fdi_link_train(struct drm_crtc *crtc) temp | FDI_RX_BIT_LOCK); break; } - - tries++; - - if (tries > 5) { - DRM_DEBUG_KMS("FDI train 1 fail!\n"); - break; - } } + if (tries == 5) + DRM_DEBUG_KMS("FDI train 1 fail!\n"); /* Train 2 */ temp = I915_READ(fdi_tx_reg); @@ -1613,7 +1778,7 @@ static void ironlake_fdi_link_train(struct drm_crtc *crtc) tries = 0; - for (;;) { + for (tries = 0; tries < 5; tries++) { temp = I915_READ(fdi_rx_iir_reg); DRM_DEBUG_KMS("FDI_RX_IIR 0x%x\n", temp); @@ -1623,14 +1788,9 @@ static void ironlake_fdi_link_train(struct drm_crtc *crtc) DRM_DEBUG_KMS("FDI train 2 done.\n"); break; } - - tries++; - - if (tries > 5) { - DRM_DEBUG_KMS("FDI train 2 fail!\n"); - break; - } } + if (tries == 5) + DRM_DEBUG_KMS("FDI train 2 fail!\n"); DRM_DEBUG_KMS("FDI train done\n"); } @@ -1655,6 +1815,15 @@ static void gen6_fdi_link_train(struct drm_crtc *crtc) int fdi_rx_imr_reg = (pipe == 0) ? FDI_RXA_IMR : FDI_RXB_IMR; u32 temp, i; + /* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit + for train result */ + temp = I915_READ(fdi_rx_imr_reg); + temp &= ~FDI_RX_SYMBOL_LOCK; + temp &= ~FDI_RX_BIT_LOCK; + I915_WRITE(fdi_rx_imr_reg, temp); + I915_READ(fdi_rx_imr_reg); + udelay(150); + /* enable CPU FDI TX and PCH FDI RX */ temp = I915_READ(fdi_tx_reg); temp |= FDI_TX_ENABLE; @@ -1680,15 +1849,6 @@ static void gen6_fdi_link_train(struct drm_crtc *crtc) I915_READ(fdi_rx_reg); udelay(150); - /* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit - for train result */ - temp = I915_READ(fdi_rx_imr_reg); - temp &= ~FDI_RX_SYMBOL_LOCK; - temp &= ~FDI_RX_BIT_LOCK; - I915_WRITE(fdi_rx_imr_reg, temp); - I915_READ(fdi_rx_imr_reg); - udelay(150); - for (i = 0; i < 4; i++ ) { temp = I915_READ(fdi_tx_reg); temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK; @@ -1843,7 +2003,8 @@ static void ironlake_crtc_dpms(struct drm_crtc *crtc, int mode) } /* Enable panel fitting for LVDS */ - if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) { + if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) + || HAS_eDP || intel_pch_has_edp(crtc)) { temp = I915_READ(pf_ctl_reg); I915_WRITE(pf_ctl_reg, temp | PF_ENABLE | PF_FILTER_MED_3x3); @@ -1938,9 +2099,12 @@ static void ironlake_crtc_dpms(struct drm_crtc *crtc, int mode) reg = I915_READ(trans_dp_ctl); reg &= ~TRANS_DP_PORT_SEL_MASK; reg = TRANS_DP_OUTPUT_ENABLE | - TRANS_DP_ENH_FRAMING | - TRANS_DP_VSYNC_ACTIVE_HIGH | - TRANS_DP_HSYNC_ACTIVE_HIGH; + TRANS_DP_ENH_FRAMING; + + if (crtc->mode.flags & DRM_MODE_FLAG_PHSYNC) + reg |= TRANS_DP_HSYNC_ACTIVE_HIGH; + if (crtc->mode.flags & DRM_MODE_FLAG_PVSYNC) + reg |= TRANS_DP_VSYNC_ACTIVE_HIGH; switch (intel_trans_dp_port_sel(crtc)) { case PCH_DP_B: @@ -1980,6 +2144,8 @@ static void ironlake_crtc_dpms(struct drm_crtc *crtc, int mode) intel_crtc_load_lut(crtc); + intel_update_fbc(crtc, &crtc->mode); + break; case DRM_MODE_DPMS_OFF: DRM_DEBUG_KMS("crtc %d dpms off\n", pipe); @@ -1994,6 +2160,10 @@ static void ironlake_crtc_dpms(struct drm_crtc *crtc, int mode) I915_READ(dspbase_reg); } + if (dev_priv->cfb_plane == plane && + dev_priv->display.disable_fbc) + dev_priv->display.disable_fbc(dev); + i915_disable_vga(dev); /* disable cpu pipe, disable after all planes disabled */ @@ -2373,8 +2543,8 @@ static bool intel_crtc_mode_fixup(struct drm_crtc *crtc, struct drm_device *dev = crtc->dev; if (HAS_PCH_SPLIT(dev)) { /* FDI link clock is fixed at 2.7G */ - if (mode->clock * 3 > 27000 * 4) - return MODE_CLOCK_HIGH; + if (mode->clock * 3 > IRONLAKE_FDI_FREQ * 4) + return false; } return true; } @@ -2556,6 +2726,20 @@ static struct intel_watermark_params g4x_wm_info = { 2, G4X_FIFO_LINE_SIZE, }; +static struct intel_watermark_params g4x_cursor_wm_info = { + I965_CURSOR_FIFO, + I965_CURSOR_MAX_WM, + I965_CURSOR_DFT_WM, + 2, + G4X_FIFO_LINE_SIZE, +}; +static struct intel_watermark_params i965_cursor_wm_info = { + I965_CURSOR_FIFO, + I965_CURSOR_MAX_WM, + I965_CURSOR_DFT_WM, + 2, + I915_FIFO_LINE_SIZE, +}; static struct intel_watermark_params i945_wm_info = { I945_FIFO_SIZE, I915_MAX_WM, @@ -2593,6 +2777,14 @@ static struct intel_watermark_params ironlake_display_wm_info = { ILK_FIFO_LINE_SIZE }; +static struct intel_watermark_params ironlake_cursor_wm_info = { + ILK_CURSOR_FIFO, + ILK_CURSOR_MAXWM, + ILK_CURSOR_DFTWM, + 2, + ILK_FIFO_LINE_SIZE +}; + static struct intel_watermark_params ironlake_display_srwm_info = { ILK_DISPLAY_SR_FIFO, ILK_DISPLAY_MAX_SRWM, @@ -2642,7 +2834,7 @@ static unsigned long intel_calculate_wm(unsigned long clock_in_khz, */ entries_required = ((clock_in_khz / 1000) * pixel_size * latency_ns) / 1000; - entries_required /= wm->cacheline_size; + entries_required = DIV_ROUND_UP(entries_required, wm->cacheline_size); DRM_DEBUG_KMS("FIFO entries required for mode: %d\n", entries_required); @@ -2653,8 +2845,14 @@ static unsigned long intel_calculate_wm(unsigned long clock_in_khz, /* Don't promote wm_size to unsigned... */ if (wm_size > (long)wm->max_wm) wm_size = wm->max_wm; - if (wm_size <= 0) + if (wm_size <= 0) { wm_size = wm->default_wm; + DRM_ERROR("Insufficient FIFO for plane, expect flickering:" + " entries required = %ld, available = %lu.\n", + entries_required + wm->guard_size, + wm->fifo_size); + } + return wm_size; } @@ -2763,11 +2961,9 @@ static int i9xx_get_fifo_size(struct drm_device *dev, int plane) uint32_t dsparb = I915_READ(DSPARB); int size; - if (plane == 0) - size = dsparb & 0x7f; - else - size = ((dsparb >> DSPARB_CSTART_SHIFT) & 0x7f) - - (dsparb & 0x7f); + size = dsparb & 0x7f; + if (plane) + size = ((dsparb >> DSPARB_CSTART_SHIFT) & 0x7f) - size; DRM_DEBUG_KMS("FIFO size - (0x%08x) %s: %d\n", dsparb, plane ? "B" : "A", size); @@ -2781,11 +2977,9 @@ static int i85x_get_fifo_size(struct drm_device *dev, int plane) uint32_t dsparb = I915_READ(DSPARB); int size; - if (plane == 0) - size = dsparb & 0x1ff; - else - size = ((dsparb >> DSPARB_BEND_SHIFT) & 0x1ff) - - (dsparb & 0x1ff); + size = dsparb & 0x1ff; + if (plane) + size = ((dsparb >> DSPARB_BEND_SHIFT) & 0x1ff) - size; size >>= 1; /* Convert to cachelines */ DRM_DEBUG_KMS("FIFO size - (0x%08x) %s: %d\n", dsparb, @@ -2826,7 +3020,8 @@ static int i830_get_fifo_size(struct drm_device *dev, int plane) } static void pineview_update_wm(struct drm_device *dev, int planea_clock, - int planeb_clock, int sr_hdisplay, int pixel_size) + int planeb_clock, int sr_hdisplay, int unused, + int pixel_size) { struct drm_i915_private *dev_priv = dev->dev_private; u32 reg; @@ -2891,7 +3086,8 @@ static void pineview_update_wm(struct drm_device *dev, int planea_clock, } static void g4x_update_wm(struct drm_device *dev, int planea_clock, - int planeb_clock, int sr_hdisplay, int pixel_size) + int planeb_clock, int sr_hdisplay, int sr_htotal, + int pixel_size) { struct drm_i915_private *dev_priv = dev->dev_private; int total_size, cacheline_size; @@ -2915,12 +3111,12 @@ static void g4x_update_wm(struct drm_device *dev, int planea_clock, */ entries_required = ((planea_clock / 1000) * pixel_size * latency_ns) / 1000; - entries_required /= G4X_FIFO_LINE_SIZE; + entries_required = DIV_ROUND_UP(entries_required, G4X_FIFO_LINE_SIZE); planea_wm = entries_required + planea_params.guard_size; entries_required = ((planeb_clock / 1000) * pixel_size * latency_ns) / 1000; - entries_required /= G4X_FIFO_LINE_SIZE; + entries_required = DIV_ROUND_UP(entries_required, G4X_FIFO_LINE_SIZE); planeb_wm = entries_required + planeb_params.guard_size; cursora_wm = cursorb_wm = 16; @@ -2934,13 +3130,24 @@ static void g4x_update_wm(struct drm_device *dev, int planea_clock, static const int sr_latency_ns = 12000; sr_clock = planea_clock ? planea_clock : planeb_clock; - line_time_us = ((sr_hdisplay * 1000) / sr_clock); + line_time_us = ((sr_htotal * 1000) / sr_clock); /* Use ns/us then divide to preserve precision */ - sr_entries = (((sr_latency_ns / line_time_us) + 1) * - pixel_size * sr_hdisplay) / 1000; - sr_entries = roundup(sr_entries / cacheline_size, 1); - DRM_DEBUG("self-refresh entries: %d\n", sr_entries); + sr_entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * + pixel_size * sr_hdisplay; + sr_entries = DIV_ROUND_UP(sr_entries, cacheline_size); + + entries_required = (((sr_latency_ns / line_time_us) + + 1000) / 1000) * pixel_size * 64; + entries_required = DIV_ROUND_UP(entries_required, + g4x_cursor_wm_info.cacheline_size); + cursor_sr = entries_required + g4x_cursor_wm_info.guard_size; + + if (cursor_sr > g4x_cursor_wm_info.max_wm) + cursor_sr = g4x_cursor_wm_info.max_wm; + DRM_DEBUG_KMS("self-refresh watermark: display plane %d " + "cursor %d\n", sr_entries, cursor_sr); + I915_WRITE(FW_BLC_SELF, FW_BLC_SELF_EN); } else { /* Turn off self refresh if both pipes are enabled */ @@ -2965,11 +3172,13 @@ static void g4x_update_wm(struct drm_device *dev, int planea_clock, } static void i965_update_wm(struct drm_device *dev, int planea_clock, - int planeb_clock, int sr_hdisplay, int pixel_size) + int planeb_clock, int sr_hdisplay, int sr_htotal, + int pixel_size) { struct drm_i915_private *dev_priv = dev->dev_private; unsigned long line_time_us; int sr_clock, sr_entries, srwm = 1; + int cursor_sr = 16; /* Calc sr entries for one plane configs */ if (sr_hdisplay && (!planea_clock || !planeb_clock)) { @@ -2977,17 +3186,31 @@ static void i965_update_wm(struct drm_device *dev, int planea_clock, static const int sr_latency_ns = 12000; sr_clock = planea_clock ? planea_clock : planeb_clock; - line_time_us = ((sr_hdisplay * 1000) / sr_clock); + line_time_us = ((sr_htotal * 1000) / sr_clock); /* Use ns/us then divide to preserve precision */ - sr_entries = (((sr_latency_ns / line_time_us) + 1) * - pixel_size * sr_hdisplay) / 1000; - sr_entries = roundup(sr_entries / I915_FIFO_LINE_SIZE, 1); + sr_entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * + pixel_size * sr_hdisplay; + sr_entries = DIV_ROUND_UP(sr_entries, I915_FIFO_LINE_SIZE); DRM_DEBUG("self-refresh entries: %d\n", sr_entries); - srwm = I945_FIFO_SIZE - sr_entries; + srwm = I965_FIFO_SIZE - sr_entries; if (srwm < 0) srwm = 1; - srwm &= 0x3f; + srwm &= 0x1ff; + + sr_entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * + pixel_size * 64; + sr_entries = DIV_ROUND_UP(sr_entries, + i965_cursor_wm_info.cacheline_size); + cursor_sr = i965_cursor_wm_info.fifo_size - + (sr_entries + i965_cursor_wm_info.guard_size); + + if (cursor_sr > i965_cursor_wm_info.max_wm) + cursor_sr = i965_cursor_wm_info.max_wm; + + DRM_DEBUG_KMS("self-refresh watermark: display plane %d " + "cursor %d\n", srwm, cursor_sr); + if (IS_I965GM(dev)) I915_WRITE(FW_BLC_SELF, FW_BLC_SELF_EN); } else { @@ -3004,10 +3227,13 @@ static void i965_update_wm(struct drm_device *dev, int planea_clock, I915_WRITE(DSPFW1, (srwm << DSPFW_SR_SHIFT) | (8 << 16) | (8 << 8) | (8 << 0)); I915_WRITE(DSPFW2, (8 << 8) | (8 << 0)); + /* update cursor SR watermark */ + I915_WRITE(DSPFW3, (cursor_sr << DSPFW_CURSOR_SR_SHIFT)); } static void i9xx_update_wm(struct drm_device *dev, int planea_clock, - int planeb_clock, int sr_hdisplay, int pixel_size) + int planeb_clock, int sr_hdisplay, int sr_htotal, + int pixel_size) { struct drm_i915_private *dev_priv = dev->dev_private; uint32_t fwater_lo; @@ -3052,12 +3278,12 @@ static void i9xx_update_wm(struct drm_device *dev, int planea_clock, static const int sr_latency_ns = 6000; sr_clock = planea_clock ? planea_clock : planeb_clock; - line_time_us = ((sr_hdisplay * 1000) / sr_clock); + line_time_us = ((sr_htotal * 1000) / sr_clock); /* Use ns/us then divide to preserve precision */ - sr_entries = (((sr_latency_ns / line_time_us) + 1) * - pixel_size * sr_hdisplay) / 1000; - sr_entries = roundup(sr_entries / cacheline_size, 1); + sr_entries = (((sr_latency_ns / line_time_us) + 1000) / 1000) * + pixel_size * sr_hdisplay; + sr_entries = DIV_ROUND_UP(sr_entries, cacheline_size); DRM_DEBUG_KMS("self-refresh entries: %d\n", sr_entries); srwm = total_size - sr_entries; if (srwm < 0) @@ -3095,7 +3321,7 @@ static void i9xx_update_wm(struct drm_device *dev, int planea_clock, } static void i830_update_wm(struct drm_device *dev, int planea_clock, int unused, - int unused2, int pixel_size) + int unused2, int unused3, int pixel_size) { struct drm_i915_private *dev_priv = dev->dev_private; uint32_t fwater_lo = I915_READ(FW_BLC) & ~0xfff; @@ -3113,9 +3339,11 @@ static void i830_update_wm(struct drm_device *dev, int planea_clock, int unused, } #define ILK_LP0_PLANE_LATENCY 700 +#define ILK_LP0_CURSOR_LATENCY 1300 static void ironlake_update_wm(struct drm_device *dev, int planea_clock, - int planeb_clock, int sr_hdisplay, int pixel_size) + int planeb_clock, int sr_hdisplay, int sr_htotal, + int pixel_size) { struct drm_i915_private *dev_priv = dev->dev_private; int planea_wm, planeb_wm, cursora_wm, cursorb_wm; @@ -3123,20 +3351,48 @@ static void ironlake_update_wm(struct drm_device *dev, int planea_clock, unsigned long line_time_us; int sr_clock, entries_required; u32 reg_value; + int line_count; + int planea_htotal = 0, planeb_htotal = 0; + struct drm_crtc *crtc; + struct intel_crtc *intel_crtc; + + /* Need htotal for all active display plane */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + intel_crtc = to_intel_crtc(crtc); + if (crtc->enabled) { + if (intel_crtc->plane == 0) + planea_htotal = crtc->mode.htotal; + else + planeb_htotal = crtc->mode.htotal; + } + } /* Calculate and update the watermark for plane A */ if (planea_clock) { entries_required = ((planea_clock / 1000) * pixel_size * ILK_LP0_PLANE_LATENCY) / 1000; entries_required = DIV_ROUND_UP(entries_required, - ironlake_display_wm_info.cacheline_size); + ironlake_display_wm_info.cacheline_size); planea_wm = entries_required + ironlake_display_wm_info.guard_size; if (planea_wm > (int)ironlake_display_wm_info.max_wm) planea_wm = ironlake_display_wm_info.max_wm; - cursora_wm = 16; + /* Use the large buffer method to calculate cursor watermark */ + line_time_us = (planea_htotal * 1000) / planea_clock; + + /* Use ns/us then divide to preserve precision */ + line_count = (ILK_LP0_CURSOR_LATENCY / line_time_us + 1000) / 1000; + + /* calculate the cursor watermark for cursor A */ + entries_required = line_count * 64 * pixel_size; + entries_required = DIV_ROUND_UP(entries_required, + ironlake_cursor_wm_info.cacheline_size); + cursora_wm = entries_required + ironlake_cursor_wm_info.guard_size; + if (cursora_wm > ironlake_cursor_wm_info.max_wm) + cursora_wm = ironlake_cursor_wm_info.max_wm; + reg_value = I915_READ(WM0_PIPEA_ILK); reg_value &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK); reg_value |= (planea_wm << WM0_PIPE_PLANE_SHIFT) | @@ -3150,14 +3406,27 @@ static void ironlake_update_wm(struct drm_device *dev, int planea_clock, entries_required = ((planeb_clock / 1000) * pixel_size * ILK_LP0_PLANE_LATENCY) / 1000; entries_required = DIV_ROUND_UP(entries_required, - ironlake_display_wm_info.cacheline_size); + ironlake_display_wm_info.cacheline_size); planeb_wm = entries_required + ironlake_display_wm_info.guard_size; if (planeb_wm > (int)ironlake_display_wm_info.max_wm) planeb_wm = ironlake_display_wm_info.max_wm; - cursorb_wm = 16; + /* Use the large buffer method to calculate cursor watermark */ + line_time_us = (planeb_htotal * 1000) / planeb_clock; + + /* Use ns/us then divide to preserve precision */ + line_count = (ILK_LP0_CURSOR_LATENCY / line_time_us + 1000) / 1000; + + /* calculate the cursor watermark for cursor B */ + entries_required = line_count * 64 * pixel_size; + entries_required = DIV_ROUND_UP(entries_required, + ironlake_cursor_wm_info.cacheline_size); + cursorb_wm = entries_required + ironlake_cursor_wm_info.guard_size; + if (cursorb_wm > ironlake_cursor_wm_info.max_wm) + cursorb_wm = ironlake_cursor_wm_info.max_wm; + reg_value = I915_READ(WM0_PIPEB_ILK); reg_value &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK); reg_value |= (planeb_wm << WM0_PIPE_PLANE_SHIFT) | @@ -3172,12 +3441,12 @@ static void ironlake_update_wm(struct drm_device *dev, int planea_clock, * display plane is used. */ if (!planea_clock || !planeb_clock) { - int line_count; + /* Read the self-refresh latency. The unit is 0.5us */ int ilk_sr_latency = I915_READ(MLTR_ILK) & ILK_SRLT_MASK; sr_clock = planea_clock ? planea_clock : planeb_clock; - line_time_us = ((sr_hdisplay * 1000) / sr_clock); + line_time_us = ((sr_htotal * 1000) / sr_clock); /* Use ns/us then divide to preserve precision */ line_count = ((ilk_sr_latency * 500) / line_time_us + 1000) @@ -3186,14 +3455,14 @@ static void ironlake_update_wm(struct drm_device *dev, int planea_clock, /* calculate the self-refresh watermark for display plane */ entries_required = line_count * sr_hdisplay * pixel_size; entries_required = DIV_ROUND_UP(entries_required, - ironlake_display_srwm_info.cacheline_size); + ironlake_display_srwm_info.cacheline_size); sr_wm = entries_required + ironlake_display_srwm_info.guard_size; /* calculate the self-refresh watermark for display cursor */ entries_required = line_count * pixel_size * 64; entries_required = DIV_ROUND_UP(entries_required, - ironlake_cursor_srwm_info.cacheline_size); + ironlake_cursor_srwm_info.cacheline_size); cursor_wm = entries_required + ironlake_cursor_srwm_info.guard_size; @@ -3237,6 +3506,7 @@ static void ironlake_update_wm(struct drm_device *dev, int planea_clock, * bytes per pixel * where * line time = htotal / dotclock + * surface width = hdisplay for normal plane and 64 for cursor * and latency is assumed to be high, as above. * * The final value programmed to the register should always be rounded up, @@ -3253,6 +3523,7 @@ static void intel_update_watermarks(struct drm_device *dev) int sr_hdisplay = 0; unsigned long planea_clock = 0, planeb_clock = 0, sr_clock = 0; int enabled = 0, pixel_size = 0; + int sr_htotal = 0; if (!dev_priv->display.update_wm) return; @@ -3273,6 +3544,7 @@ static void intel_update_watermarks(struct drm_device *dev) } sr_hdisplay = crtc->mode.hdisplay; sr_clock = crtc->mode.clock; + sr_htotal = crtc->mode.htotal; if (crtc->fb) pixel_size = crtc->fb->bits_per_pixel / 8; else @@ -3284,7 +3556,7 @@ static void intel_update_watermarks(struct drm_device *dev) return; dev_priv->display.update_wm(dev, planea_clock, planeb_clock, - sr_hdisplay, pixel_size); + sr_hdisplay, sr_htotal, pixel_size); } static int intel_crtc_mode_set(struct drm_crtc *crtc, @@ -3403,6 +3675,9 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, return -EINVAL; } + /* Ensure that the cursor is valid for the new mode before changing... */ + intel_crtc_update_cursor(crtc); + if (is_lvds && dev_priv->lvds_downclock_avail) { has_reduced_clock = limit->find_pll(limit, crtc, dev_priv->lvds_downclock, @@ -3469,7 +3744,7 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, temp |= PIPE_8BPC; else temp |= PIPE_6BPC; - } else if (is_edp) { + } else if (is_edp || (is_dp && intel_pch_has_edp(crtc))) { switch (dev_priv->edp_bpp/3) { case 8: temp |= PIPE_8BPC; @@ -3712,6 +3987,11 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, udelay(150); } + if (HAS_PCH_SPLIT(dev)) { + pipeconf &= ~PIPE_ENABLE_DITHER; + pipeconf &= ~PIPE_DITHER_TYPE_MASK; + } + /* The LVDS pin pair needs to be on before the DPLLs are enabled. * This is an exception to the general rule that mode_set doesn't turn * things on. @@ -3754,16 +4034,13 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, if (dev_priv->lvds_dither) { if (HAS_PCH_SPLIT(dev)) { pipeconf |= PIPE_ENABLE_DITHER; - pipeconf &= ~PIPE_DITHER_TYPE_MASK; pipeconf |= PIPE_DITHER_TYPE_ST01; } else lvds |= LVDS_ENABLE_DITHER; } else { - if (HAS_PCH_SPLIT(dev)) { - pipeconf &= ~PIPE_ENABLE_DITHER; - pipeconf &= ~PIPE_DITHER_TYPE_MASK; - } else + if (!HAS_PCH_SPLIT(dev)) { lvds &= ~LVDS_ENABLE_DITHER; + } } } I915_WRITE(lvds_reg, lvds); @@ -3939,6 +4216,85 @@ void intel_crtc_load_lut(struct drm_crtc *crtc) } } +/* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */ +static void intel_crtc_update_cursor(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + int pipe = intel_crtc->pipe; + int x = intel_crtc->cursor_x; + int y = intel_crtc->cursor_y; + uint32_t base, pos; + bool visible; + + pos = 0; + + if (crtc->fb) { + base = intel_crtc->cursor_addr; + if (x > (int) crtc->fb->width) + base = 0; + + if (y > (int) crtc->fb->height) + base = 0; + } else + base = 0; + + if (x < 0) { + if (x + intel_crtc->cursor_width < 0) + base = 0; + + pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; + x = -x; + } + pos |= x << CURSOR_X_SHIFT; + + if (y < 0) { + if (y + intel_crtc->cursor_height < 0) + base = 0; + + pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; + y = -y; + } + pos |= y << CURSOR_Y_SHIFT; + + visible = base != 0; + if (!visible && !intel_crtc->cursor_visble) + return; + + I915_WRITE(pipe == 0 ? CURAPOS : CURBPOS, pos); + if (intel_crtc->cursor_visble != visible) { + uint32_t cntl = I915_READ(pipe == 0 ? CURACNTR : CURBCNTR); + if (base) { + /* Hooray for CUR*CNTR differences */ + if (IS_MOBILE(dev) || IS_I9XX(dev)) { + cntl &= ~(CURSOR_MODE | MCURSOR_PIPE_SELECT); + cntl |= CURSOR_MODE_64_ARGB_AX | MCURSOR_GAMMA_ENABLE; + cntl |= pipe << 28; /* Connect to correct pipe */ + } else { + cntl &= ~(CURSOR_FORMAT_MASK); + cntl |= CURSOR_ENABLE; + cntl |= CURSOR_FORMAT_ARGB | CURSOR_GAMMA_ENABLE; + } + } else { + if (IS_MOBILE(dev) || IS_I9XX(dev)) { + cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE); + cntl |= CURSOR_MODE_DISABLE; + } else { + cntl &= ~(CURSOR_ENABLE | CURSOR_GAMMA_ENABLE); + } + } + I915_WRITE(pipe == 0 ? CURACNTR : CURBCNTR, cntl); + + intel_crtc->cursor_visble = visible; + } + /* and commit changes on next vblank */ + I915_WRITE(pipe == 0 ? CURABASE : CURBBASE, base); + + if (visible) + intel_mark_busy(dev, to_intel_framebuffer(crtc->fb)->obj); +} + static int intel_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, uint32_t handle, @@ -3949,11 +4305,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc, struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct drm_gem_object *bo; struct drm_i915_gem_object *obj_priv; - int pipe = intel_crtc->pipe; - uint32_t control = (pipe == 0) ? CURACNTR : CURBCNTR; - uint32_t base = (pipe == 0) ? CURABASE : CURBBASE; - uint32_t temp = I915_READ(control); - size_t addr; + uint32_t addr; int ret; DRM_DEBUG_KMS("\n"); @@ -3961,12 +4313,6 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc, /* if we want to turn off the cursor ignore width and height */ if (!handle) { DRM_DEBUG_KMS("cursor off\n"); - if (IS_MOBILE(dev) || IS_I9XX(dev)) { - temp &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE); - temp |= CURSOR_MODE_DISABLE; - } else { - temp &= ~(CURSOR_ENABLE | CURSOR_GAMMA_ENABLE); - } addr = 0; bo = NULL; mutex_lock(&dev->struct_mutex); @@ -4008,7 +4354,8 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc, addr = obj_priv->gtt_offset; } else { - ret = i915_gem_attach_phys_object(dev, bo, (pipe == 0) ? I915_GEM_PHYS_CURSOR_0 : I915_GEM_PHYS_CURSOR_1); + ret = i915_gem_attach_phys_object(dev, bo, + (intel_crtc->pipe == 0) ? I915_GEM_PHYS_CURSOR_0 : I915_GEM_PHYS_CURSOR_1); if (ret) { DRM_ERROR("failed to attach phys object\n"); goto fail_locked; @@ -4019,21 +4366,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc, if (!IS_I9XX(dev)) I915_WRITE(CURSIZE, (height << 12) | width); - /* Hooray for CUR*CNTR differences */ - if (IS_MOBILE(dev) || IS_I9XX(dev)) { - temp &= ~(CURSOR_MODE | MCURSOR_PIPE_SELECT); - temp |= CURSOR_MODE_64_ARGB_AX | MCURSOR_GAMMA_ENABLE; - temp |= (pipe << 28); /* Connect to correct pipe */ - } else { - temp &= ~(CURSOR_FORMAT_MASK); - temp |= CURSOR_ENABLE; - temp |= CURSOR_FORMAT_ARGB | CURSOR_GAMMA_ENABLE; - } - finish: - I915_WRITE(control, temp); - I915_WRITE(base, addr); - if (intel_crtc->cursor_bo) { if (dev_priv->info->cursor_needs_physical) { if (intel_crtc->cursor_bo != bo) @@ -4047,6 +4380,10 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc, intel_crtc->cursor_addr = addr; intel_crtc->cursor_bo = bo; + intel_crtc->cursor_width = width; + intel_crtc->cursor_height = height; + + intel_crtc_update_cursor(crtc); return 0; fail_unpin: @@ -4060,34 +4397,12 @@ fail: static int intel_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_framebuffer *intel_fb; - int pipe = intel_crtc->pipe; - uint32_t temp = 0; - uint32_t adder; - - if (crtc->fb) { - intel_fb = to_intel_framebuffer(crtc->fb); - intel_mark_busy(dev, intel_fb->obj); - } - - if (x < 0) { - temp |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; - x = -x; - } - if (y < 0) { - temp |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; - y = -y; - } - temp |= x << CURSOR_X_SHIFT; - temp |= y << CURSOR_Y_SHIFT; + intel_crtc->cursor_x = x; + intel_crtc->cursor_y = y; - adder = intel_crtc->cursor_addr; - I915_WRITE((pipe == 0) ? CURAPOS : CURBPOS, temp); - I915_WRITE((pipe == 0) ? CURABASE : CURBBASE, adder); + intel_crtc_update_cursor(crtc); return 0; } @@ -4671,6 +4986,8 @@ static void do_intel_finish_page_flip(struct drm_device *dev, atomic_dec_and_test(&obj_priv->pending_flip)) DRM_WAKEUP(&dev_priv->pending_flip_queue); schedule_work(&work->work); + + trace_i915_flip_complete(intel_crtc->plane, work->pending_flip_obj); } void intel_finish_page_flip(struct drm_device *dev, int pipe) @@ -4748,27 +5065,22 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, mutex_lock(&dev->struct_mutex); ret = intel_pin_and_fence_fb_obj(dev, obj); - if (ret != 0) { - mutex_unlock(&dev->struct_mutex); - - spin_lock_irqsave(&dev->event_lock, flags); - intel_crtc->unpin_work = NULL; - spin_unlock_irqrestore(&dev->event_lock, flags); - - kfree(work); - - DRM_DEBUG_DRIVER("flip queue: %p pin & fence failed\n", - to_intel_bo(obj)); - return ret; - } + if (ret) + goto cleanup_work; /* Reference the objects for the scheduled work. */ drm_gem_object_reference(work->old_fb_obj); drm_gem_object_reference(obj); crtc->fb = fb; - i915_gem_object_flush_write_domain(obj); - drm_vblank_get(dev, intel_crtc->pipe); + ret = i915_gem_object_flush_write_domain(obj); + if (ret) + goto cleanup_objs; + + ret = drm_vblank_get(dev, intel_crtc->pipe); + if (ret) + goto cleanup_objs; + obj_priv = to_intel_bo(obj); atomic_inc(&obj_priv->pending_flip); work->pending_flip_obj = obj; @@ -4806,7 +5118,23 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, mutex_unlock(&dev->struct_mutex); + trace_i915_flip_request(intel_crtc->plane, obj); + return 0; + +cleanup_objs: + drm_gem_object_unreference(work->old_fb_obj); + drm_gem_object_unreference(obj); +cleanup_work: + mutex_unlock(&dev->struct_mutex); + + spin_lock_irqsave(&dev->event_lock, flags); + intel_crtc->unpin_work = NULL; + spin_unlock_irqrestore(&dev->event_lock, flags); + + kfree(work); + + return ret; } static const struct drm_crtc_helper_funcs intel_helper_funcs = { @@ -4814,6 +5142,7 @@ static const struct drm_crtc_helper_funcs intel_helper_funcs = { .mode_fixup = intel_crtc_mode_fixup, .mode_set = intel_crtc_mode_set, .mode_set_base = intel_pipe_set_base, + .mode_set_base_atomic = intel_pipe_set_base_atomic, .prepare = intel_crtc_prepare, .commit = intel_crtc_commit, .load_lut = intel_crtc_load_lut, @@ -4932,19 +5261,26 @@ static void intel_setup_outputs(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_encoder *encoder; + bool dpd_is_edp = false; - intel_crt_init(dev); - - /* Set up integrated LVDS */ if (IS_MOBILE(dev) && !IS_I830(dev)) intel_lvds_init(dev); if (HAS_PCH_SPLIT(dev)) { - int found; + dpd_is_edp = intel_dpd_is_edp(dev); if (IS_MOBILE(dev) && (I915_READ(DP_A) & DP_DETECTED)) intel_dp_init(dev, DP_A); + if (dpd_is_edp && (I915_READ(PCH_DP_D) & DP_DETECTED)) + intel_dp_init(dev, PCH_DP_D); + } + + intel_crt_init(dev); + + if (HAS_PCH_SPLIT(dev)) { + int found; + if (I915_READ(HDMIB) & PORT_DETECTED) { /* PCH SDVOB multiplex with HDMIB */ found = intel_sdvo_init(dev, PCH_SDVOB); @@ -4963,7 +5299,7 @@ static void intel_setup_outputs(struct drm_device *dev) if (I915_READ(PCH_DP_C) & DP_DETECTED) intel_dp_init(dev, PCH_DP_C); - if (I915_READ(PCH_DP_D) & DP_DETECTED) + if (!dpd_is_edp && (I915_READ(PCH_DP_D) & DP_DETECTED)) intel_dp_init(dev, PCH_DP_D); } else if (SUPPORTS_DIGITAL_OUTPUTS(dev)) { @@ -5372,6 +5708,26 @@ void intel_init_clock_gating(struct drm_device *dev) (I915_READ(DISP_ARB_CTL) | DISP_FBC_WM_DIS)); } + /* + * Based on the document from hardware guys the following bits + * should be set unconditionally in order to enable FBC. + * The bit 22 of 0x42000 + * The bit 22 of 0x42004 + * The bit 7,8,9 of 0x42020. + */ + if (IS_IRONLAKE_M(dev)) { + I915_WRITE(ILK_DISPLAY_CHICKEN1, + I915_READ(ILK_DISPLAY_CHICKEN1) | + ILK_FBCQ_DIS); + I915_WRITE(ILK_DISPLAY_CHICKEN2, + I915_READ(ILK_DISPLAY_CHICKEN2) | + ILK_DPARB_GATE); + I915_WRITE(ILK_DSPCLK_GATE, + I915_READ(ILK_DSPCLK_GATE) | + ILK_DPFC_DIS1 | + ILK_DPFC_DIS2 | + ILK_CLK_FBC); + } return; } else if (IS_G4X(dev)) { uint32_t dspclk_gate; @@ -5450,7 +5806,11 @@ static void intel_init_display(struct drm_device *dev) dev_priv->display.dpms = i9xx_crtc_dpms; if (I915_HAS_FBC(dev)) { - if (IS_GM45(dev)) { + if (IS_IRONLAKE_M(dev)) { + dev_priv->display.fbc_enabled = ironlake_fbc_enabled; + dev_priv->display.enable_fbc = ironlake_enable_fbc; + dev_priv->display.disable_fbc = ironlake_disable_fbc; + } else if (IS_GM45(dev)) { dev_priv->display.fbc_enabled = g4x_fbc_enabled; dev_priv->display.enable_fbc = g4x_enable_fbc; dev_priv->display.disable_fbc = g4x_disable_fbc; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 5dde80f9e65..40be1fa65be 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -43,6 +43,7 @@ #define DP_LINK_CONFIGURATION_SIZE 9 #define IS_eDP(i) ((i)->type == INTEL_OUTPUT_EDP) +#define IS_PCH_eDP(dp_priv) ((dp_priv)->is_pch_edp) struct intel_dp_priv { uint32_t output_reg; @@ -56,6 +57,7 @@ struct intel_dp_priv { struct intel_encoder *intel_encoder; struct i2c_adapter adapter; struct i2c_algo_dp_aux_data algo; + bool is_pch_edp; }; static void @@ -128,8 +130,9 @@ intel_dp_link_required(struct drm_device *dev, struct intel_encoder *intel_encoder, int pixel_clock) { struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_dp_priv *dp_priv = intel_encoder->dev_priv; - if (IS_eDP(intel_encoder)) + if (IS_eDP(intel_encoder) || IS_PCH_eDP(dp_priv)) return (pixel_clock * dev_priv->edp_bpp) / 8; else return pixel_clock * 3; @@ -147,9 +150,21 @@ intel_dp_mode_valid(struct drm_connector *connector, { struct drm_encoder *encoder = intel_attached_encoder(connector); struct intel_encoder *intel_encoder = enc_to_intel_encoder(encoder); + struct intel_dp_priv *dp_priv = intel_encoder->dev_priv; + struct drm_device *dev = connector->dev; + struct drm_i915_private *dev_priv = dev->dev_private; int max_link_clock = intel_dp_link_clock(intel_dp_max_link_bw(intel_encoder)); int max_lanes = intel_dp_max_lane_count(intel_encoder); + if ((IS_eDP(intel_encoder) || IS_PCH_eDP(dp_priv)) && + dev_priv->panel_fixed_mode) { + if (mode->hdisplay > dev_priv->panel_fixed_mode->hdisplay) + return MODE_PANEL; + + if (mode->vdisplay > dev_priv->panel_fixed_mode->vdisplay) + return MODE_PANEL; + } + /* only refuse the mode on non eDP since we have seen some wierd eDP panels which are outside spec tolerances but somehow work by magic */ if (!IS_eDP(intel_encoder) && @@ -508,11 +523,37 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode, { struct intel_encoder *intel_encoder = enc_to_intel_encoder(encoder); struct intel_dp_priv *dp_priv = intel_encoder->dev_priv; + struct drm_device *dev = encoder->dev; + struct drm_i915_private *dev_priv = dev->dev_private; int lane_count, clock; int max_lane_count = intel_dp_max_lane_count(intel_encoder); int max_clock = intel_dp_max_link_bw(intel_encoder) == DP_LINK_BW_2_7 ? 1 : 0; static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 }; + if ((IS_eDP(intel_encoder) || IS_PCH_eDP(dp_priv)) && + dev_priv->panel_fixed_mode) { + struct drm_display_mode *fixed_mode = dev_priv->panel_fixed_mode; + + adjusted_mode->hdisplay = fixed_mode->hdisplay; + adjusted_mode->hsync_start = fixed_mode->hsync_start; + adjusted_mode->hsync_end = fixed_mode->hsync_end; + adjusted_mode->htotal = fixed_mode->htotal; + + adjusted_mode->vdisplay = fixed_mode->vdisplay; + adjusted_mode->vsync_start = fixed_mode->vsync_start; + adjusted_mode->vsync_end = fixed_mode->vsync_end; + adjusted_mode->vtotal = fixed_mode->vtotal; + + adjusted_mode->clock = fixed_mode->clock; + drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V); + + /* + * the mode->clock is used to calculate the Data&Link M/N + * of the pipe. For the eDP the fixed clock should be used. + */ + mode->clock = dev_priv->panel_fixed_mode->clock; + } + for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) { for (clock = 0; clock <= max_clock; clock++) { int link_avail = intel_dp_max_data_rate(intel_dp_link_clock(bws[clock]), lane_count); @@ -531,7 +572,7 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode, } } - if (IS_eDP(intel_encoder)) { + if (IS_eDP(intel_encoder) || IS_PCH_eDP(dp_priv)) { /* okay we failed just pick the highest */ dp_priv->lane_count = max_lane_count; dp_priv->link_bw = bws[max_clock]; @@ -563,14 +604,14 @@ intel_reduce_ratio(uint32_t *num, uint32_t *den) } static void -intel_dp_compute_m_n(int bytes_per_pixel, +intel_dp_compute_m_n(int bpp, int nlanes, int pixel_clock, int link_clock, struct intel_dp_m_n *m_n) { m_n->tu = 64; - m_n->gmch_m = pixel_clock * bytes_per_pixel; + m_n->gmch_m = (pixel_clock * bpp) >> 3; m_n->gmch_n = link_clock * nlanes; intel_reduce_ratio(&m_n->gmch_m, &m_n->gmch_n); m_n->link_m = pixel_clock; @@ -578,6 +619,28 @@ intel_dp_compute_m_n(int bytes_per_pixel, intel_reduce_ratio(&m_n->link_m, &m_n->link_n); } +bool intel_pch_has_edp(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_encoder *encoder; + + list_for_each_entry(encoder, &mode_config->encoder_list, head) { + struct intel_encoder *intel_encoder; + struct intel_dp_priv *dp_priv; + + if (!encoder || encoder->crtc != crtc) + continue; + + intel_encoder = enc_to_intel_encoder(encoder); + dp_priv = intel_encoder->dev_priv; + + if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT) + return dp_priv->is_pch_edp; + } + return false; +} + void intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) @@ -587,7 +650,7 @@ intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode, struct drm_encoder *encoder; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int lane_count = 4; + int lane_count = 4, bpp = 24; struct intel_dp_m_n m_n; /* @@ -605,6 +668,8 @@ intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode, if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT) { lane_count = dp_priv->lane_count; + if (IS_PCH_eDP(dp_priv)) + bpp = dev_priv->edp_bpp; break; } } @@ -614,7 +679,7 @@ intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode, * the number of bytes_per_pixel post-LUT, which we always * set up for 8-bits of R/G/B, or 3 bytes total. */ - intel_dp_compute_m_n(3, lane_count, + intel_dp_compute_m_n(bpp, lane_count, mode->clock, adjusted_mode->clock, &m_n); if (HAS_PCH_SPLIT(dev)) { @@ -796,7 +861,7 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode) if (mode != DRM_MODE_DPMS_ON) { if (dp_reg & DP_PORT_EN) { intel_dp_link_down(intel_encoder, dp_priv->DP); - if (IS_eDP(intel_encoder)) { + if (IS_eDP(intel_encoder) || IS_PCH_eDP(dp_priv)) { ironlake_edp_backlight_off(dev); ironlake_edp_panel_off(dev); } @@ -804,7 +869,7 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode) } else { if (!(dp_reg & DP_PORT_EN)) { intel_dp_link_train(intel_encoder, dp_priv->DP, dp_priv->link_configuration); - if (IS_eDP(intel_encoder)) { + if (IS_eDP(intel_encoder) || IS_PCH_eDP(dp_priv)) { ironlake_edp_panel_on(dev); ironlake_edp_backlight_on(dev); } @@ -1340,17 +1405,32 @@ static int intel_dp_get_modes(struct drm_connector *connector) struct intel_encoder *intel_encoder = enc_to_intel_encoder(encoder); struct drm_device *dev = intel_encoder->enc.dev; struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_dp_priv *dp_priv = intel_encoder->dev_priv; int ret; /* We should parse the EDID data and find out if it has an audio sink */ ret = intel_ddc_get_modes(connector, intel_encoder->ddc_bus); - if (ret) + if (ret) { + if ((IS_eDP(intel_encoder) || IS_PCH_eDP(dp_priv)) && + !dev_priv->panel_fixed_mode) { + struct drm_display_mode *newmode; + list_for_each_entry(newmode, &connector->probed_modes, + head) { + if (newmode->type & DRM_MODE_TYPE_PREFERRED) { + dev_priv->panel_fixed_mode = + drm_mode_duplicate(dev, newmode); + break; + } + } + } + return ret; + } /* if eDP has no EDID, try to use fixed panel mode from VBT */ - if (IS_eDP(intel_encoder)) { + if (IS_eDP(intel_encoder) || IS_PCH_eDP(dp_priv)) { if (dev_priv->panel_fixed_mode != NULL) { struct drm_display_mode *mode; mode = drm_mode_duplicate(dev, dev_priv->panel_fixed_mode); @@ -1435,6 +1515,26 @@ intel_trans_dp_port_sel (struct drm_crtc *crtc) return -1; } +/* check the VBT to see whether the eDP is on DP-D port */ +bool intel_dpd_is_edp(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct child_device_config *p_child; + int i; + + if (!dev_priv->child_dev_num) + return false; + + for (i = 0; i < dev_priv->child_dev_num; i++) { + p_child = dev_priv->child_dev + i; + + if (p_child->dvo_port == PORT_IDPD && + p_child->device_type == DEVICE_TYPE_eDP) + return true; + } + return false; +} + void intel_dp_init(struct drm_device *dev, int output_reg) { @@ -1444,6 +1544,7 @@ intel_dp_init(struct drm_device *dev, int output_reg) struct intel_connector *intel_connector; struct intel_dp_priv *dp_priv; const char *name = NULL; + int type; intel_encoder = kcalloc(sizeof(struct intel_encoder) + sizeof(struct intel_dp_priv), 1, GFP_KERNEL); @@ -1458,18 +1559,24 @@ intel_dp_init(struct drm_device *dev, int output_reg) dp_priv = (struct intel_dp_priv *)(intel_encoder + 1); + if (HAS_PCH_SPLIT(dev) && (output_reg == PCH_DP_D)) + if (intel_dpd_is_edp(dev)) + dp_priv->is_pch_edp = true; + + if (output_reg == DP_A || IS_PCH_eDP(dp_priv)) { + type = DRM_MODE_CONNECTOR_eDP; + intel_encoder->type = INTEL_OUTPUT_EDP; + } else { + type = DRM_MODE_CONNECTOR_DisplayPort; + intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT; + } + connector = &intel_connector->base; - drm_connector_init(dev, connector, &intel_dp_connector_funcs, - DRM_MODE_CONNECTOR_DisplayPort); + drm_connector_init(dev, connector, &intel_dp_connector_funcs, type); drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs); connector->polled = DRM_CONNECTOR_POLL_HPD; - if (output_reg == DP_A) - intel_encoder->type = INTEL_OUTPUT_EDP; - else - intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT; - if (output_reg == DP_B || output_reg == PCH_DP_B) intel_encoder->clone_mask = (1 << INTEL_DP_B_CLONE_BIT); else if (output_reg == DP_C || output_reg == PCH_DP_C) @@ -1528,7 +1635,7 @@ intel_dp_init(struct drm_device *dev, int output_reg) intel_encoder->ddc_bus = &dp_priv->adapter; intel_encoder->hot_plug = intel_dp_hot_plug; - if (output_reg == DP_A) { + if (output_reg == DP_A || IS_PCH_eDP(dp_priv)) { /* initialize panel mode from VBT if available for eDP */ if (dev_priv->lfp_lvds_vbt_mode) { dev_priv->panel_fixed_mode = diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 2f7970be905..b2190148703 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -143,8 +143,6 @@ struct intel_crtc { struct drm_crtc base; enum pipe pipe; enum plane plane; - struct drm_gem_object *cursor_bo; - uint32_t cursor_addr; u8 lut_r[256], lut_g[256], lut_b[256]; int dpms_mode; bool busy; /* is scanout buffer being updated frequently? */ @@ -153,6 +151,12 @@ struct intel_crtc { struct intel_overlay *overlay; struct intel_unpin_work *unpin_work; int fdi_lanes; + + struct drm_gem_object *cursor_bo; + uint32_t cursor_addr; + int16_t cursor_x, cursor_y; + int16_t cursor_width, cursor_height; + bool cursor_visble; }; #define to_intel_crtc(x) container_of(x, struct intel_crtc, base) @@ -179,6 +183,8 @@ extern void intel_dp_init(struct drm_device *dev, int dp_reg); void intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode); +extern bool intel_pch_has_edp(struct drm_crtc *crtc); +extern bool intel_dpd_is_edp(struct drm_device *dev); extern void intel_edp_link_config (struct intel_encoder *, int *, int *); diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index 3e18c9e7729..54acd8b534d 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -61,6 +61,8 @@ static struct fb_ops intelfb_ops = { .fb_pan_display = drm_fb_helper_pan_display, .fb_blank = drm_fb_helper_blank, .fb_setcmap = drm_fb_helper_setcmap, + .fb_debug_enter = drm_fb_helper_debug_enter, + .fb_debug_leave = drm_fb_helper_debug_leave, }; static int intelfb_create(struct intel_fbdev *ifbdev, diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 83bd764b000..197887ed182 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -54,10 +54,11 @@ static void intel_hdmi_mode_set(struct drm_encoder *encoder, struct intel_hdmi_priv *hdmi_priv = intel_encoder->dev_priv; u32 sdvox; - sdvox = SDVO_ENCODING_HDMI | - SDVO_BORDER_ENABLE | - SDVO_VSYNC_ACTIVE_HIGH | - SDVO_HSYNC_ACTIVE_HIGH; + sdvox = SDVO_ENCODING_HDMI | SDVO_BORDER_ENABLE; + if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) + sdvox |= SDVO_VSYNC_ACTIVE_HIGH; + if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) + sdvox |= SDVO_HSYNC_ACTIVE_HIGH; if (hdmi_priv->has_hdmi_sink) { sdvox |= SDVO_AUDIO_ENABLE; diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 0eab8df5bf7..0a2e60059fb 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -156,31 +156,73 @@ static int intel_lvds_mode_valid(struct drm_connector *connector, return MODE_OK; } +static void +centre_horizontally(struct drm_display_mode *mode, + int width) +{ + u32 border, sync_pos, blank_width, sync_width; + + /* keep the hsync and hblank widths constant */ + sync_width = mode->crtc_hsync_end - mode->crtc_hsync_start; + blank_width = mode->crtc_hblank_end - mode->crtc_hblank_start; + sync_pos = (blank_width - sync_width + 1) / 2; + + border = (mode->hdisplay - width + 1) / 2; + border += border & 1; /* make the border even */ + + mode->crtc_hdisplay = width; + mode->crtc_hblank_start = width + border; + mode->crtc_hblank_end = mode->crtc_hblank_start + blank_width; + + mode->crtc_hsync_start = mode->crtc_hblank_start + sync_pos; + mode->crtc_hsync_end = mode->crtc_hsync_start + sync_width; +} + +static void +centre_vertically(struct drm_display_mode *mode, + int height) +{ + u32 border, sync_pos, blank_width, sync_width; + + /* keep the vsync and vblank widths constant */ + sync_width = mode->crtc_vsync_end - mode->crtc_vsync_start; + blank_width = mode->crtc_vblank_end - mode->crtc_vblank_start; + sync_pos = (blank_width - sync_width + 1) / 2; + + border = (mode->vdisplay - height + 1) / 2; + + mode->crtc_vdisplay = height; + mode->crtc_vblank_start = height + border; + mode->crtc_vblank_end = mode->crtc_vblank_start + blank_width; + + mode->crtc_vsync_start = mode->crtc_vblank_start + sync_pos; + mode->crtc_vsync_end = mode->crtc_vsync_start + sync_width; +} + +static inline u32 panel_fitter_scaling(u32 source, u32 target) +{ + /* + * Floating point operation is not supported. So the FACTOR + * is defined, which can avoid the floating point computation + * when calculating the panel ratio. + */ +#define ACCURACY 12 +#define FACTOR (1 << ACCURACY) + u32 ratio = source * FACTOR / target; + return (FACTOR * ratio + FACTOR/2) / FACTOR; +} + static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) { - /* - * float point operation is not supported . So the PANEL_RATIO_FACTOR - * is defined, which can avoid the float point computation when - * calculating the panel ratio. - */ -#define PANEL_RATIO_FACTOR 8192 struct drm_device *dev = encoder->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); struct drm_encoder *tmp_encoder; struct intel_encoder *intel_encoder = enc_to_intel_encoder(encoder); struct intel_lvds_priv *lvds_priv = intel_encoder->dev_priv; - u32 pfit_control = 0, pfit_pgm_ratios = 0; - int left_border = 0, right_border = 0, top_border = 0; - int bottom_border = 0; - bool border = 0; - int panel_ratio, desired_ratio, vert_scale, horiz_scale; - int horiz_ratio, vert_ratio; - u32 hsync_width, vsync_width; - u32 hblank_width, vblank_width; - u32 hsync_pos, vsync_pos; + u32 pfit_control = 0, pfit_pgm_ratios = 0, border = 0; /* Should never happen!! */ if (!IS_I965G(dev) && intel_crtc->pipe == 0) { @@ -200,27 +242,25 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, if (dev_priv->panel_fixed_mode == NULL) return true; /* - * If we have timings from the BIOS for the panel, put them in + * We have timings from the BIOS for the panel, put them in * to the adjusted mode. The CRTC will be set up for this mode, * with the panel scaling set up to source from the H/VDisplay * of the original mode. */ - if (dev_priv->panel_fixed_mode != NULL) { - adjusted_mode->hdisplay = dev_priv->panel_fixed_mode->hdisplay; - adjusted_mode->hsync_start = - dev_priv->panel_fixed_mode->hsync_start; - adjusted_mode->hsync_end = - dev_priv->panel_fixed_mode->hsync_end; - adjusted_mode->htotal = dev_priv->panel_fixed_mode->htotal; - adjusted_mode->vdisplay = dev_priv->panel_fixed_mode->vdisplay; - adjusted_mode->vsync_start = - dev_priv->panel_fixed_mode->vsync_start; - adjusted_mode->vsync_end = - dev_priv->panel_fixed_mode->vsync_end; - adjusted_mode->vtotal = dev_priv->panel_fixed_mode->vtotal; - adjusted_mode->clock = dev_priv->panel_fixed_mode->clock; - drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V); - } + adjusted_mode->hdisplay = dev_priv->panel_fixed_mode->hdisplay; + adjusted_mode->hsync_start = + dev_priv->panel_fixed_mode->hsync_start; + adjusted_mode->hsync_end = + dev_priv->panel_fixed_mode->hsync_end; + adjusted_mode->htotal = dev_priv->panel_fixed_mode->htotal; + adjusted_mode->vdisplay = dev_priv->panel_fixed_mode->vdisplay; + adjusted_mode->vsync_start = + dev_priv->panel_fixed_mode->vsync_start; + adjusted_mode->vsync_end = + dev_priv->panel_fixed_mode->vsync_end; + adjusted_mode->vtotal = dev_priv->panel_fixed_mode->vtotal; + adjusted_mode->clock = dev_priv->panel_fixed_mode->clock; + drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V); /* Make sure pre-965s set dither correctly */ if (!IS_I965G(dev)) { @@ -230,11 +270,8 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, /* Native modes don't need fitting */ if (adjusted_mode->hdisplay == mode->hdisplay && - adjusted_mode->vdisplay == mode->vdisplay) { - pfit_pgm_ratios = 0; - border = 0; + adjusted_mode->vdisplay == mode->vdisplay) goto out; - } /* full screen scale for now */ if (HAS_PCH_SPLIT(dev)) @@ -242,25 +279,9 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, /* 965+ wants fuzzy fitting */ if (IS_I965G(dev)) - pfit_control |= (intel_crtc->pipe << PFIT_PIPE_SHIFT) | - PFIT_FILTER_FUZZY; - - hsync_width = adjusted_mode->crtc_hsync_end - - adjusted_mode->crtc_hsync_start; - vsync_width = adjusted_mode->crtc_vsync_end - - adjusted_mode->crtc_vsync_start; - hblank_width = adjusted_mode->crtc_hblank_end - - adjusted_mode->crtc_hblank_start; - vblank_width = adjusted_mode->crtc_vblank_end - - adjusted_mode->crtc_vblank_start; - /* - * Deal with panel fitting options. Figure out how to stretch the - * image based on its aspect ratio & the current panel fitting mode. - */ - panel_ratio = adjusted_mode->hdisplay * PANEL_RATIO_FACTOR / - adjusted_mode->vdisplay; - desired_ratio = mode->hdisplay * PANEL_RATIO_FACTOR / - mode->vdisplay; + pfit_control |= ((intel_crtc->pipe << PFIT_PIPE_SHIFT) | + PFIT_FILTER_FUZZY); + /* * Enable automatic panel scaling for non-native modes so that they fill * the screen. Should be enabled before the pipe is enabled, according @@ -278,170 +299,63 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, * For centered modes, we have to calculate border widths & * heights and modify the values programmed into the CRTC. */ - left_border = (adjusted_mode->hdisplay - mode->hdisplay) / 2; - right_border = left_border; - if (mode->hdisplay & 1) - right_border++; - top_border = (adjusted_mode->vdisplay - mode->vdisplay) / 2; - bottom_border = top_border; - if (mode->vdisplay & 1) - bottom_border++; - /* Set active & border values */ - adjusted_mode->crtc_hdisplay = mode->hdisplay; - /* Keep the boder be even */ - if (right_border & 1) - right_border++; - /* use the border directly instead of border minuse one */ - adjusted_mode->crtc_hblank_start = mode->hdisplay + - right_border; - /* keep the blank width constant */ - adjusted_mode->crtc_hblank_end = - adjusted_mode->crtc_hblank_start + hblank_width; - /* get the hsync pos relative to hblank start */ - hsync_pos = (hblank_width - hsync_width) / 2; - /* keep the hsync pos be even */ - if (hsync_pos & 1) - hsync_pos++; - adjusted_mode->crtc_hsync_start = - adjusted_mode->crtc_hblank_start + hsync_pos; - /* keep the hsync width constant */ - adjusted_mode->crtc_hsync_end = - adjusted_mode->crtc_hsync_start + hsync_width; - adjusted_mode->crtc_vdisplay = mode->vdisplay; - /* use the border instead of border minus one */ - adjusted_mode->crtc_vblank_start = mode->vdisplay + - bottom_border; - /* keep the vblank width constant */ - adjusted_mode->crtc_vblank_end = - adjusted_mode->crtc_vblank_start + vblank_width; - /* get the vsync start postion relative to vblank start */ - vsync_pos = (vblank_width - vsync_width) / 2; - adjusted_mode->crtc_vsync_start = - adjusted_mode->crtc_vblank_start + vsync_pos; - /* keep the vsync width constant */ - adjusted_mode->crtc_vsync_end = - adjusted_mode->crtc_vsync_start + vsync_width; - border = 1; + centre_horizontally(adjusted_mode, mode->hdisplay); + centre_vertically(adjusted_mode, mode->vdisplay); + border = LVDS_BORDER_ENABLE; break; + case DRM_MODE_SCALE_ASPECT: - /* Scale but preserve the spect ratio */ - pfit_control |= PFIT_ENABLE; + /* Scale but preserve the aspect ratio */ if (IS_I965G(dev)) { + u32 scaled_width = adjusted_mode->hdisplay * mode->vdisplay; + u32 scaled_height = mode->hdisplay * adjusted_mode->vdisplay; + + pfit_control |= PFIT_ENABLE; /* 965+ is easy, it does everything in hw */ - if (panel_ratio > desired_ratio) + if (scaled_width > scaled_height) pfit_control |= PFIT_SCALING_PILLAR; - else if (panel_ratio < desired_ratio) + else if (scaled_width < scaled_height) pfit_control |= PFIT_SCALING_LETTER; else pfit_control |= PFIT_SCALING_AUTO; } else { + u32 scaled_width = adjusted_mode->hdisplay * mode->vdisplay; + u32 scaled_height = mode->hdisplay * adjusted_mode->vdisplay; /* * For earlier chips we have to calculate the scaling * ratio by hand and program it into the * PFIT_PGM_RATIO register */ - u32 horiz_bits, vert_bits, bits = 12; - horiz_ratio = mode->hdisplay * PANEL_RATIO_FACTOR/ - adjusted_mode->hdisplay; - vert_ratio = mode->vdisplay * PANEL_RATIO_FACTOR/ - adjusted_mode->vdisplay; - horiz_scale = adjusted_mode->hdisplay * - PANEL_RATIO_FACTOR / mode->hdisplay; - vert_scale = adjusted_mode->vdisplay * - PANEL_RATIO_FACTOR / mode->vdisplay; - - /* retain aspect ratio */ - if (panel_ratio > desired_ratio) { /* Pillar */ - u32 scaled_width; - scaled_width = mode->hdisplay * vert_scale / - PANEL_RATIO_FACTOR; - horiz_ratio = vert_ratio; - pfit_control |= (VERT_AUTO_SCALE | - VERT_INTERP_BILINEAR | - HORIZ_INTERP_BILINEAR); - /* Pillar will have left/right borders */ - left_border = (adjusted_mode->hdisplay - - scaled_width) / 2; - right_border = left_border; - if (mode->hdisplay & 1) /* odd resolutions */ - right_border++; - /* keep the border be even */ - if (right_border & 1) - right_border++; - adjusted_mode->crtc_hdisplay = scaled_width; - /* use border instead of border minus one */ - adjusted_mode->crtc_hblank_start = - scaled_width + right_border; - /* keep the hblank width constant */ - adjusted_mode->crtc_hblank_end = - adjusted_mode->crtc_hblank_start + - hblank_width; - /* - * get the hsync start pos relative to - * hblank start - */ - hsync_pos = (hblank_width - hsync_width) / 2; - /* keep the hsync_pos be even */ - if (hsync_pos & 1) - hsync_pos++; - adjusted_mode->crtc_hsync_start = - adjusted_mode->crtc_hblank_start + - hsync_pos; - /* keept hsync width constant */ - adjusted_mode->crtc_hsync_end = - adjusted_mode->crtc_hsync_start + - hsync_width; - border = 1; - } else if (panel_ratio < desired_ratio) { /* letter */ - u32 scaled_height = mode->vdisplay * - horiz_scale / PANEL_RATIO_FACTOR; - vert_ratio = horiz_ratio; - pfit_control |= (HORIZ_AUTO_SCALE | - VERT_INTERP_BILINEAR | - HORIZ_INTERP_BILINEAR); - /* Letterbox will have top/bottom border */ - top_border = (adjusted_mode->vdisplay - - scaled_height) / 2; - bottom_border = top_border; - if (mode->vdisplay & 1) - bottom_border++; - adjusted_mode->crtc_vdisplay = scaled_height; - /* use border instead of border minus one */ - adjusted_mode->crtc_vblank_start = - scaled_height + bottom_border; - /* keep the vblank width constant */ - adjusted_mode->crtc_vblank_end = - adjusted_mode->crtc_vblank_start + - vblank_width; - /* - * get the vsync start pos relative to - * vblank start - */ - vsync_pos = (vblank_width - vsync_width) / 2; - adjusted_mode->crtc_vsync_start = - adjusted_mode->crtc_vblank_start + - vsync_pos; - /* keep the vsync width constant */ - adjusted_mode->crtc_vsync_end = - adjusted_mode->crtc_vsync_start + - vsync_width; - border = 1; - } else { - /* Aspects match, Let hw scale both directions */ - pfit_control |= (VERT_AUTO_SCALE | - HORIZ_AUTO_SCALE | + if (scaled_width > scaled_height) { /* pillar */ + centre_horizontally(adjusted_mode, scaled_height / mode->vdisplay); + + border = LVDS_BORDER_ENABLE; + if (mode->vdisplay != adjusted_mode->vdisplay) { + u32 bits = panel_fitter_scaling(mode->vdisplay, adjusted_mode->vdisplay); + pfit_pgm_ratios |= (bits << PFIT_HORIZ_SCALE_SHIFT | + bits << PFIT_VERT_SCALE_SHIFT); + pfit_control |= (PFIT_ENABLE | + VERT_INTERP_BILINEAR | + HORIZ_INTERP_BILINEAR); + } + } else if (scaled_width < scaled_height) { /* letter */ + centre_vertically(adjusted_mode, scaled_width / mode->hdisplay); + + border = LVDS_BORDER_ENABLE; + if (mode->hdisplay != adjusted_mode->hdisplay) { + u32 bits = panel_fitter_scaling(mode->hdisplay, adjusted_mode->hdisplay); + pfit_pgm_ratios |= (bits << PFIT_HORIZ_SCALE_SHIFT | + bits << PFIT_VERT_SCALE_SHIFT); + pfit_control |= (PFIT_ENABLE | + VERT_INTERP_BILINEAR | + HORIZ_INTERP_BILINEAR); + } + } else + /* Aspects match, Let hw scale both directions */ + pfit_control |= (PFIT_ENABLE | + VERT_AUTO_SCALE | HORIZ_AUTO_SCALE | VERT_INTERP_BILINEAR | HORIZ_INTERP_BILINEAR); - } - horiz_bits = (1 << bits) * horiz_ratio / - PANEL_RATIO_FACTOR; - vert_bits = (1 << bits) * vert_ratio / - PANEL_RATIO_FACTOR; - pfit_pgm_ratios = - ((vert_bits << PFIT_VERT_SCALE_SHIFT) & - PFIT_VERT_SCALE_MASK) | - ((horiz_bits << PFIT_HORIZ_SCALE_SHIFT) & - PFIT_HORIZ_SCALE_MASK); } break; @@ -458,6 +372,7 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, VERT_INTERP_BILINEAR | HORIZ_INTERP_BILINEAR); break; + default: break; } @@ -465,14 +380,8 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, out: lvds_priv->pfit_control = pfit_control; lvds_priv->pfit_pgm_ratios = pfit_pgm_ratios; - /* - * When there exists the border, it means that the LVDS_BORDR - * should be enabled. - */ - if (border) - dev_priv->lvds_border_bits |= LVDS_BORDER_ENABLE; - else - dev_priv->lvds_border_bits &= ~(LVDS_BORDER_ENABLE); + dev_priv->lvds_border_bits = border; + /* * XXX: It would be nice to support lower refresh rates on the * panels to reduce power consumption, and perhaps match the diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index d7ad5139d17..d39aea24eab 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -65,7 +65,7 @@ #define OCMD_YUV_410_PLANAR (0xe<<10) /* also 411 */ #define OCMD_TVSYNCFLIP_PARITY (0x1<<9) #define OCMD_TVSYNCFLIP_ENABLE (0x1<<7) -#define OCMD_BUF_TYPE_MASK (Ox1<<5) +#define OCMD_BUF_TYPE_MASK (0x1<<5) #define OCMD_BUF_TYPE_FRAME (0x0<<5) #define OCMD_BUF_TYPE_FIELD (0x1<<5) #define OCMD_TEST_MODE (0x1<<4) @@ -185,7 +185,8 @@ static struct overlay_registers *intel_overlay_map_regs_atomic(struct intel_over if (OVERLAY_NONPHYSICAL(overlay->dev)) { regs = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, - overlay->reg_bo->gtt_offset); + overlay->reg_bo->gtt_offset, + KM_USER0); if (!regs) { DRM_ERROR("failed to map overlay regs in GTT\n"); @@ -200,7 +201,7 @@ static struct overlay_registers *intel_overlay_map_regs_atomic(struct intel_over static void intel_overlay_unmap_regs_atomic(struct intel_overlay *overlay) { if (OVERLAY_NONPHYSICAL(overlay->dev)) - io_mapping_unmap_atomic(overlay->virt_addr); + io_mapping_unmap_atomic(overlay->virt_addr, KM_USER0); overlay->virt_addr = NULL; @@ -958,7 +959,7 @@ static int check_overlay_src(struct drm_device *dev, || rec->src_width < N_HORIZ_Y_TAPS*4) return -EINVAL; - /* check alingment constrains */ + /* check alignment constraints */ switch (rec->flags & I915_OVERLAY_TYPE_MASK) { case I915_OVERLAY_RGB: /* not implemented */ @@ -990,7 +991,10 @@ static int check_overlay_src(struct drm_device *dev, return -EINVAL; /* stride checking */ - stride_mask = 63; + if (IS_I830(dev) || IS_845G(dev)) + stride_mask = 255; + else + stride_mask = 63; if (rec->stride_Y & stride_mask || rec->stride_UV & stride_mask) return -EINVAL; diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 03c231be227..d9d4d51aa89 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1237,9 +1237,11 @@ static void intel_sdvo_mode_set(struct drm_encoder *encoder, /* Set the SDVO control regs. */ if (IS_I965G(dev)) { - sdvox |= SDVO_BORDER_ENABLE | - SDVO_VSYNC_ACTIVE_HIGH | - SDVO_HSYNC_ACTIVE_HIGH; + sdvox |= SDVO_BORDER_ENABLE; + if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC) + sdvox |= SDVO_VSYNC_ACTIVE_HIGH; + if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) + sdvox |= SDVO_HSYNC_ACTIVE_HIGH; } else { sdvox |= I915_READ(sdvo_priv->sdvo_reg); switch (sdvo_priv->sdvo_reg) { diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index d2d4e4045ca..cc3726a4a1c 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -476,7 +476,7 @@ static const struct tv_mode tv_modes[] = { .vi_end_f1 = 20, .vi_end_f2 = 21, .nbr_end = 240, - .burst_ena = 8, + .burst_ena = true, .hburst_start = 72, .hburst_len = 34, .vburst_start_f1 = 9, .vburst_end_f1 = 240, .vburst_start_f2 = 10, .vburst_end_f2 = 240, @@ -896,8 +896,6 @@ static const struct tv_mode tv_modes[] = { }, }; -#define NUM_TV_MODES sizeof(tv_modes) / sizeof (tv_modes[0]) - static void intel_tv_dpms(struct drm_encoder *encoder, int mode) { @@ -1512,7 +1510,7 @@ intel_tv_set_property(struct drm_connector *connector, struct drm_property *prop tv_priv->margin[TV_MARGIN_BOTTOM] = val; changed = true; } else if (property == dev->mode_config.tv_mode_property) { - if (val >= NUM_TV_MODES) { + if (val >= ARRAY_SIZE(tv_modes)) { ret = -EINVAL; goto out; } @@ -1693,13 +1691,13 @@ intel_tv_init(struct drm_device *dev) connector->doublescan_allowed = false; /* Create TV properties then attach current values */ - tv_format_names = kmalloc(sizeof(char *) * NUM_TV_MODES, + tv_format_names = kmalloc(sizeof(char *) * ARRAY_SIZE(tv_modes), GFP_KERNEL); if (!tv_format_names) goto out; - for (i = 0; i < NUM_TV_MODES; i++) + for (i = 0; i < ARRAY_SIZE(tv_modes); i++) tv_format_names[i] = tv_modes[i].name; - drm_mode_create_tv_properties(dev, NUM_TV_MODES, tv_format_names); + drm_mode_create_tv_properties(dev, ARRAY_SIZE(tv_modes), tv_format_names); drm_connector_attach_property(connector, dev->mode_config.tv_mode_property, initial_mode); diff --git a/drivers/gpu/drm/mga/mga_dma.c b/drivers/gpu/drm/mga/mga_dma.c index 3c917fb3a60..08868ac3048 100644 --- a/drivers/gpu/drm/mga/mga_dma.c +++ b/drivers/gpu/drm/mga/mga_dma.c @@ -52,7 +52,7 @@ static int mga_do_cleanup_dma(struct drm_device *dev, int full_cleanup); * Engine control */ -int mga_do_wait_for_idle(drm_mga_private_t * dev_priv) +int mga_do_wait_for_idle(drm_mga_private_t *dev_priv) { u32 status = 0; int i; @@ -74,7 +74,7 @@ int mga_do_wait_for_idle(drm_mga_private_t * dev_priv) return -EBUSY; } -static int mga_do_dma_reset(drm_mga_private_t * dev_priv) +static int mga_do_dma_reset(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_mga_primary_buffer_t *primary = &dev_priv->prim; @@ -102,7 +102,7 @@ static int mga_do_dma_reset(drm_mga_private_t * dev_priv) * Primary DMA stream */ -void mga_do_dma_flush(drm_mga_private_t * dev_priv) +void mga_do_dma_flush(drm_mga_private_t *dev_priv) { drm_mga_primary_buffer_t *primary = &dev_priv->prim; u32 head, tail; @@ -142,11 +142,10 @@ void mga_do_dma_flush(drm_mga_private_t * dev_priv) head = MGA_READ(MGA_PRIMADDRESS); - if (head <= tail) { + if (head <= tail) primary->space = primary->size - primary->tail; - } else { + else primary->space = head - tail; - } DRM_DEBUG(" head = 0x%06lx\n", (unsigned long)(head - dev_priv->primary->offset)); DRM_DEBUG(" tail = 0x%06lx\n", (unsigned long)(tail - dev_priv->primary->offset)); @@ -158,7 +157,7 @@ void mga_do_dma_flush(drm_mga_private_t * dev_priv) DRM_DEBUG("done.\n"); } -void mga_do_dma_wrap_start(drm_mga_private_t * dev_priv) +void mga_do_dma_wrap_start(drm_mga_private_t *dev_priv) { drm_mga_primary_buffer_t *primary = &dev_priv->prim; u32 head, tail; @@ -181,11 +180,10 @@ void mga_do_dma_wrap_start(drm_mga_private_t * dev_priv) head = MGA_READ(MGA_PRIMADDRESS); - if (head == dev_priv->primary->offset) { + if (head == dev_priv->primary->offset) primary->space = primary->size; - } else { + else primary->space = head - dev_priv->primary->offset; - } DRM_DEBUG(" head = 0x%06lx\n", (unsigned long)(head - dev_priv->primary->offset)); DRM_DEBUG(" tail = 0x%06x\n", primary->tail); @@ -199,7 +197,7 @@ void mga_do_dma_wrap_start(drm_mga_private_t * dev_priv) DRM_DEBUG("done.\n"); } -void mga_do_dma_wrap_end(drm_mga_private_t * dev_priv) +void mga_do_dma_wrap_end(drm_mga_private_t *dev_priv) { drm_mga_primary_buffer_t *primary = &dev_priv->prim; drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -220,11 +218,11 @@ void mga_do_dma_wrap_end(drm_mga_private_t * dev_priv) * Freelist management */ -#define MGA_BUFFER_USED ~0 +#define MGA_BUFFER_USED (~0) #define MGA_BUFFER_FREE 0 #if MGA_FREELIST_DEBUG -static void mga_freelist_print(struct drm_device * dev) +static void mga_freelist_print(struct drm_device *dev) { drm_mga_private_t *dev_priv = dev->dev_private; drm_mga_freelist_t *entry; @@ -245,7 +243,7 @@ static void mga_freelist_print(struct drm_device * dev) } #endif -static int mga_freelist_init(struct drm_device * dev, drm_mga_private_t * dev_priv) +static int mga_freelist_init(struct drm_device *dev, drm_mga_private_t *dev_priv) { struct drm_device_dma *dma = dev->dma; struct drm_buf *buf; @@ -288,7 +286,7 @@ static int mga_freelist_init(struct drm_device * dev, drm_mga_private_t * dev_pr return 0; } -static void mga_freelist_cleanup(struct drm_device * dev) +static void mga_freelist_cleanup(struct drm_device *dev) { drm_mga_private_t *dev_priv = dev->dev_private; drm_mga_freelist_t *entry; @@ -308,7 +306,7 @@ static void mga_freelist_cleanup(struct drm_device * dev) #if 0 /* FIXME: Still needed? */ -static void mga_freelist_reset(struct drm_device * dev) +static void mga_freelist_reset(struct drm_device *dev) { struct drm_device_dma *dma = dev->dma; struct drm_buf *buf; @@ -356,7 +354,7 @@ static struct drm_buf *mga_freelist_get(struct drm_device * dev) return NULL; } -int mga_freelist_put(struct drm_device * dev, struct drm_buf * buf) +int mga_freelist_put(struct drm_device *dev, struct drm_buf *buf) { drm_mga_private_t *dev_priv = dev->dev_private; drm_mga_buf_priv_t *buf_priv = buf->dev_private; @@ -391,7 +389,7 @@ int mga_freelist_put(struct drm_device * dev, struct drm_buf * buf) * DMA initialization, cleanup */ -int mga_driver_load(struct drm_device * dev, unsigned long flags) +int mga_driver_load(struct drm_device *dev, unsigned long flags) { drm_mga_private_t *dev_priv; int ret; @@ -405,8 +403,8 @@ int mga_driver_load(struct drm_device * dev, unsigned long flags) dev_priv->usec_timeout = MGA_DEFAULT_USEC_TIMEOUT; dev_priv->chipset = flags; - dev_priv->mmio_base = drm_get_resource_start(dev, 1); - dev_priv->mmio_size = drm_get_resource_len(dev, 1); + dev_priv->mmio_base = pci_resource_start(dev->pdev, 1); + dev_priv->mmio_size = pci_resource_len(dev->pdev, 1); dev->counters += 3; dev->types[6] = _DRM_STAT_IRQ; @@ -439,8 +437,8 @@ int mga_driver_load(struct drm_device * dev, unsigned long flags) * * \sa mga_do_dma_bootstrap, mga_do_pci_dma_bootstrap */ -static int mga_do_agp_dma_bootstrap(struct drm_device * dev, - drm_mga_dma_bootstrap_t * dma_bs) +static int mga_do_agp_dma_bootstrap(struct drm_device *dev, + drm_mga_dma_bootstrap_t *dma_bs) { drm_mga_private_t *const dev_priv = (drm_mga_private_t *) dev->dev_private; @@ -481,11 +479,10 @@ static int mga_do_agp_dma_bootstrap(struct drm_device * dev, */ if (dev_priv->chipset == MGA_CARD_TYPE_G200) { - if (mode.mode & 0x02) { + if (mode.mode & 0x02) MGA_WRITE(MGA_AGP_PLL, MGA_AGP2XPLL_ENABLE); - } else { + else MGA_WRITE(MGA_AGP_PLL, MGA_AGP2XPLL_DISABLE); - } } /* Allocate and bind AGP memory. */ @@ -593,8 +590,8 @@ static int mga_do_agp_dma_bootstrap(struct drm_device * dev, return 0; } #else -static int mga_do_agp_dma_bootstrap(struct drm_device * dev, - drm_mga_dma_bootstrap_t * dma_bs) +static int mga_do_agp_dma_bootstrap(struct drm_device *dev, + drm_mga_dma_bootstrap_t *dma_bs) { return -EINVAL; } @@ -614,8 +611,8 @@ static int mga_do_agp_dma_bootstrap(struct drm_device * dev, * * \sa mga_do_dma_bootstrap, mga_do_agp_dma_bootstrap */ -static int mga_do_pci_dma_bootstrap(struct drm_device * dev, - drm_mga_dma_bootstrap_t * dma_bs) +static int mga_do_pci_dma_bootstrap(struct drm_device *dev, + drm_mga_dma_bootstrap_t *dma_bs) { drm_mga_private_t *const dev_priv = (drm_mga_private_t *) dev->dev_private; @@ -678,9 +675,8 @@ static int mga_do_pci_dma_bootstrap(struct drm_device * dev, req.size = dma_bs->secondary_bin_size; err = drm_addbufs_pci(dev, &req); - if (!err) { + if (!err) break; - } } if (bin_count == 0) { @@ -704,8 +700,8 @@ static int mga_do_pci_dma_bootstrap(struct drm_device * dev, return 0; } -static int mga_do_dma_bootstrap(struct drm_device * dev, - drm_mga_dma_bootstrap_t * dma_bs) +static int mga_do_dma_bootstrap(struct drm_device *dev, + drm_mga_dma_bootstrap_t *dma_bs) { const int is_agp = (dma_bs->agp_mode != 0) && drm_device_is_agp(dev); int err; @@ -737,17 +733,15 @@ static int mga_do_dma_bootstrap(struct drm_device * dev, * carve off portions of it for internal uses. The remaining memory * is returned to user-mode to be used for AGP textures. */ - if (is_agp) { + if (is_agp) err = mga_do_agp_dma_bootstrap(dev, dma_bs); - } /* If we attempted to initialize the card for AGP DMA but failed, * clean-up any mess that may have been created. */ - if (err) { + if (err) mga_do_cleanup_dma(dev, MINIMAL_CLEANUP); - } /* Not only do we want to try and initialized PCI cards for PCI DMA, * but we also try to initialized AGP cards that could not be @@ -757,9 +751,8 @@ static int mga_do_dma_bootstrap(struct drm_device * dev, * AGP memory, etc. */ - if (!is_agp || err) { + if (!is_agp || err) err = mga_do_pci_dma_bootstrap(dev, dma_bs); - } return err; } @@ -792,7 +785,7 @@ int mga_dma_bootstrap(struct drm_device *dev, void *data, return err; } -static int mga_do_init_dma(struct drm_device * dev, drm_mga_init_t * init) +static int mga_do_init_dma(struct drm_device *dev, drm_mga_init_t *init) { drm_mga_private_t *dev_priv; int ret; @@ -800,11 +793,10 @@ static int mga_do_init_dma(struct drm_device * dev, drm_mga_init_t * init) dev_priv = dev->dev_private; - if (init->sgram) { + if (init->sgram) dev_priv->clear_cmd = MGA_DWGCTL_CLEAR | MGA_ATYPE_BLK; - } else { + else dev_priv->clear_cmd = MGA_DWGCTL_CLEAR | MGA_ATYPE_RSTR; - } dev_priv->maccess = init->maccess; dev_priv->fb_cpp = init->fb_cpp; @@ -975,9 +967,8 @@ static int mga_do_cleanup_dma(struct drm_device *dev, int full_cleanup) dev_priv->agp_handle = 0; } - if ((dev->agp != NULL) && dev->agp->acquired) { + if ((dev->agp != NULL) && dev->agp->acquired) err = drm_agp_release(dev); - } #endif } @@ -998,9 +989,8 @@ static int mga_do_cleanup_dma(struct drm_device *dev, int full_cleanup) memset(dev_priv->warp_pipe_phys, 0, sizeof(dev_priv->warp_pipe_phys)); - if (dev_priv->head != NULL) { + if (dev_priv->head != NULL) mga_freelist_cleanup(dev); - } } return err; @@ -1017,9 +1007,8 @@ int mga_dma_init(struct drm_device *dev, void *data, switch (init->func) { case MGA_INIT_DMA: err = mga_do_init_dma(dev, init); - if (err) { + if (err) (void)mga_do_cleanup_dma(dev, FULL_CLEANUP); - } return err; case MGA_CLEANUP_DMA: return mga_do_cleanup_dma(dev, FULL_CLEANUP); @@ -1047,9 +1036,8 @@ int mga_dma_flush(struct drm_device *dev, void *data, WRAP_WAIT_WITH_RETURN(dev_priv); - if (lock->flags & (_DRM_LOCK_FLUSH | _DRM_LOCK_FLUSH_ALL)) { + if (lock->flags & (_DRM_LOCK_FLUSH | _DRM_LOCK_FLUSH_ALL)) mga_do_dma_flush(dev_priv); - } if (lock->flags & _DRM_LOCK_QUIESCENT) { #if MGA_DMA_DEBUG @@ -1079,8 +1067,8 @@ int mga_dma_reset(struct drm_device *dev, void *data, * DMA buffer management */ -static int mga_dma_get_buffers(struct drm_device * dev, - struct drm_file *file_priv, struct drm_dma * d) +static int mga_dma_get_buffers(struct drm_device *dev, + struct drm_file *file_priv, struct drm_dma *d) { struct drm_buf *buf; int i; @@ -1134,9 +1122,8 @@ int mga_dma_buffers(struct drm_device *dev, void *data, d->granted_count = 0; - if (d->request_count) { + if (d->request_count) ret = mga_dma_get_buffers(dev, file_priv, d); - } return ret; } @@ -1144,7 +1131,7 @@ int mga_dma_buffers(struct drm_device *dev, void *data, /** * Called just before the module is unloaded. */ -int mga_driver_unload(struct drm_device * dev) +int mga_driver_unload(struct drm_device *dev) { kfree(dev->dev_private); dev->dev_private = NULL; @@ -1155,12 +1142,12 @@ int mga_driver_unload(struct drm_device * dev) /** * Called when the last opener of the device is closed. */ -void mga_driver_lastclose(struct drm_device * dev) +void mga_driver_lastclose(struct drm_device *dev) { mga_do_cleanup_dma(dev, FULL_CLEANUP); } -int mga_driver_dma_quiescent(struct drm_device * dev) +int mga_driver_dma_quiescent(struct drm_device *dev) { drm_mga_private_t *dev_priv = dev->dev_private; return mga_do_wait_for_idle(dev_priv); diff --git a/drivers/gpu/drm/mga/mga_drv.c b/drivers/gpu/drm/mga/mga_drv.c index ddfe16197b5..26d0d8ced80 100644 --- a/drivers/gpu/drm/mga/mga_drv.c +++ b/drivers/gpu/drm/mga/mga_drv.c @@ -36,7 +36,7 @@ #include "drm_pciids.h" -static int mga_driver_device_is_agp(struct drm_device * dev); +static int mga_driver_device_is_agp(struct drm_device *dev); static struct pci_device_id pciidlist[] = { mga_PCI_IDS @@ -119,7 +119,7 @@ MODULE_LICENSE("GPL and additional rights"); * \returns * If the device is a PCI G450, zero is returned. Otherwise 2 is returned. */ -static int mga_driver_device_is_agp(struct drm_device * dev) +static int mga_driver_device_is_agp(struct drm_device *dev) { const struct pci_dev *const pdev = dev->pdev; diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h index be6c6b9b0e8..1084fa4d261 100644 --- a/drivers/gpu/drm/mga/mga_drv.h +++ b/drivers/gpu/drm/mga/mga_drv.h @@ -164,59 +164,59 @@ extern int mga_dma_reset(struct drm_device *dev, void *data, extern int mga_dma_buffers(struct drm_device *dev, void *data, struct drm_file *file_priv); extern int mga_driver_load(struct drm_device *dev, unsigned long flags); -extern int mga_driver_unload(struct drm_device * dev); -extern void mga_driver_lastclose(struct drm_device * dev); -extern int mga_driver_dma_quiescent(struct drm_device * dev); +extern int mga_driver_unload(struct drm_device *dev); +extern void mga_driver_lastclose(struct drm_device *dev); +extern int mga_driver_dma_quiescent(struct drm_device *dev); -extern int mga_do_wait_for_idle(drm_mga_private_t * dev_priv); +extern int mga_do_wait_for_idle(drm_mga_private_t *dev_priv); -extern void mga_do_dma_flush(drm_mga_private_t * dev_priv); -extern void mga_do_dma_wrap_start(drm_mga_private_t * dev_priv); -extern void mga_do_dma_wrap_end(drm_mga_private_t * dev_priv); +extern void mga_do_dma_flush(drm_mga_private_t *dev_priv); +extern void mga_do_dma_wrap_start(drm_mga_private_t *dev_priv); +extern void mga_do_dma_wrap_end(drm_mga_private_t *dev_priv); -extern int mga_freelist_put(struct drm_device * dev, struct drm_buf * buf); +extern int mga_freelist_put(struct drm_device *dev, struct drm_buf *buf); /* mga_warp.c */ -extern int mga_warp_install_microcode(drm_mga_private_t * dev_priv); -extern int mga_warp_init(drm_mga_private_t * dev_priv); +extern int mga_warp_install_microcode(drm_mga_private_t *dev_priv); +extern int mga_warp_init(drm_mga_private_t *dev_priv); /* mga_irq.c */ extern int mga_enable_vblank(struct drm_device *dev, int crtc); extern void mga_disable_vblank(struct drm_device *dev, int crtc); extern u32 mga_get_vblank_counter(struct drm_device *dev, int crtc); -extern int mga_driver_fence_wait(struct drm_device * dev, unsigned int *sequence); -extern int mga_driver_vblank_wait(struct drm_device * dev, unsigned int *sequence); +extern int mga_driver_fence_wait(struct drm_device *dev, unsigned int *sequence); +extern int mga_driver_vblank_wait(struct drm_device *dev, unsigned int *sequence); extern irqreturn_t mga_driver_irq_handler(DRM_IRQ_ARGS); -extern void mga_driver_irq_preinstall(struct drm_device * dev); +extern void mga_driver_irq_preinstall(struct drm_device *dev); extern int mga_driver_irq_postinstall(struct drm_device *dev); -extern void mga_driver_irq_uninstall(struct drm_device * dev); +extern void mga_driver_irq_uninstall(struct drm_device *dev); extern long mga_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); #define mga_flush_write_combine() DRM_WRITEMEMORYBARRIER() #if defined(__linux__) && defined(__alpha__) -#define MGA_BASE( reg ) ((unsigned long)(dev_priv->mmio->handle)) -#define MGA_ADDR( reg ) (MGA_BASE(reg) + reg) +#define MGA_BASE(reg) ((unsigned long)(dev_priv->mmio->handle)) +#define MGA_ADDR(reg) (MGA_BASE(reg) + reg) -#define MGA_DEREF( reg ) *(volatile u32 *)MGA_ADDR( reg ) -#define MGA_DEREF8( reg ) *(volatile u8 *)MGA_ADDR( reg ) +#define MGA_DEREF(reg) (*(volatile u32 *)MGA_ADDR(reg)) +#define MGA_DEREF8(reg) (*(volatile u8 *)MGA_ADDR(reg)) -#define MGA_READ( reg ) (_MGA_READ((u32 *)MGA_ADDR(reg))) -#define MGA_READ8( reg ) (_MGA_READ((u8 *)MGA_ADDR(reg))) -#define MGA_WRITE( reg, val ) do { DRM_WRITEMEMORYBARRIER(); MGA_DEREF( reg ) = val; } while (0) -#define MGA_WRITE8( reg, val ) do { DRM_WRITEMEMORYBARRIER(); MGA_DEREF8( reg ) = val; } while (0) +#define MGA_READ(reg) (_MGA_READ((u32 *)MGA_ADDR(reg))) +#define MGA_READ8(reg) (_MGA_READ((u8 *)MGA_ADDR(reg))) +#define MGA_WRITE(reg, val) do { DRM_WRITEMEMORYBARRIER(); MGA_DEREF(reg) = val; } while (0) +#define MGA_WRITE8(reg, val) do { DRM_WRITEMEMORYBARRIER(); MGA_DEREF8(reg) = val; } while (0) -static inline u32 _MGA_READ(u32 * addr) +static inline u32 _MGA_READ(u32 *addr) { DRM_MEMORYBARRIER(); return *(volatile u32 *)addr; } #else -#define MGA_READ8( reg ) DRM_READ8(dev_priv->mmio, (reg)) -#define MGA_READ( reg ) DRM_READ32(dev_priv->mmio, (reg)) -#define MGA_WRITE8( reg, val ) DRM_WRITE8(dev_priv->mmio, (reg), (val)) -#define MGA_WRITE( reg, val ) DRM_WRITE32(dev_priv->mmio, (reg), (val)) +#define MGA_READ8(reg) DRM_READ8(dev_priv->mmio, (reg)) +#define MGA_READ(reg) DRM_READ32(dev_priv->mmio, (reg)) +#define MGA_WRITE8(reg, val) DRM_WRITE8(dev_priv->mmio, (reg), (val)) +#define MGA_WRITE(reg, val) DRM_WRITE32(dev_priv->mmio, (reg), (val)) #endif #define DWGREG0 0x1c00 @@ -233,40 +233,39 @@ static inline u32 _MGA_READ(u32 * addr) * Helper macross... */ -#define MGA_EMIT_STATE( dev_priv, dirty ) \ +#define MGA_EMIT_STATE(dev_priv, dirty) \ do { \ - if ( (dirty) & ~MGA_UPLOAD_CLIPRECTS ) { \ - if ( dev_priv->chipset >= MGA_CARD_TYPE_G400 ) { \ - mga_g400_emit_state( dev_priv ); \ - } else { \ - mga_g200_emit_state( dev_priv ); \ - } \ + if ((dirty) & ~MGA_UPLOAD_CLIPRECTS) { \ + if (dev_priv->chipset >= MGA_CARD_TYPE_G400) \ + mga_g400_emit_state(dev_priv); \ + else \ + mga_g200_emit_state(dev_priv); \ } \ } while (0) -#define WRAP_TEST_WITH_RETURN( dev_priv ) \ +#define WRAP_TEST_WITH_RETURN(dev_priv) \ do { \ - if ( test_bit( 0, &dev_priv->prim.wrapped ) ) { \ - if ( mga_is_idle( dev_priv ) ) { \ - mga_do_dma_wrap_end( dev_priv ); \ - } else if ( dev_priv->prim.space < \ - dev_priv->prim.high_mark ) { \ - if ( MGA_DMA_DEBUG ) \ - DRM_INFO( "wrap...\n"); \ - return -EBUSY; \ + if (test_bit(0, &dev_priv->prim.wrapped)) { \ + if (mga_is_idle(dev_priv)) { \ + mga_do_dma_wrap_end(dev_priv); \ + } else if (dev_priv->prim.space < \ + dev_priv->prim.high_mark) { \ + if (MGA_DMA_DEBUG) \ + DRM_INFO("wrap...\n"); \ + return -EBUSY; \ } \ } \ } while (0) -#define WRAP_WAIT_WITH_RETURN( dev_priv ) \ +#define WRAP_WAIT_WITH_RETURN(dev_priv) \ do { \ - if ( test_bit( 0, &dev_priv->prim.wrapped ) ) { \ - if ( mga_do_wait_for_idle( dev_priv ) < 0 ) { \ - if ( MGA_DMA_DEBUG ) \ - DRM_INFO( "wrap...\n"); \ - return -EBUSY; \ + if (test_bit(0, &dev_priv->prim.wrapped)) { \ + if (mga_do_wait_for_idle(dev_priv) < 0) { \ + if (MGA_DMA_DEBUG) \ + DRM_INFO("wrap...\n"); \ + return -EBUSY; \ } \ - mga_do_dma_wrap_end( dev_priv ); \ + mga_do_dma_wrap_end(dev_priv); \ } \ } while (0) @@ -280,12 +279,12 @@ do { \ #define DMA_BLOCK_SIZE (5 * sizeof(u32)) -#define BEGIN_DMA( n ) \ +#define BEGIN_DMA(n) \ do { \ - if ( MGA_VERBOSE ) { \ - DRM_INFO( "BEGIN_DMA( %d )\n", (n) ); \ - DRM_INFO( " space=0x%x req=0x%Zx\n", \ - dev_priv->prim.space, (n) * DMA_BLOCK_SIZE ); \ + if (MGA_VERBOSE) { \ + DRM_INFO("BEGIN_DMA(%d)\n", (n)); \ + DRM_INFO(" space=0x%x req=0x%Zx\n", \ + dev_priv->prim.space, (n) * DMA_BLOCK_SIZE); \ } \ prim = dev_priv->prim.start; \ write = dev_priv->prim.tail; \ @@ -293,9 +292,9 @@ do { \ #define BEGIN_DMA_WRAP() \ do { \ - if ( MGA_VERBOSE ) { \ - DRM_INFO( "BEGIN_DMA()\n" ); \ - DRM_INFO( " space=0x%x\n", dev_priv->prim.space ); \ + if (MGA_VERBOSE) { \ + DRM_INFO("BEGIN_DMA()\n"); \ + DRM_INFO(" space=0x%x\n", dev_priv->prim.space); \ } \ prim = dev_priv->prim.start; \ write = dev_priv->prim.tail; \ @@ -304,72 +303,68 @@ do { \ #define ADVANCE_DMA() \ do { \ dev_priv->prim.tail = write; \ - if ( MGA_VERBOSE ) { \ - DRM_INFO( "ADVANCE_DMA() tail=0x%05x sp=0x%x\n", \ - write, dev_priv->prim.space ); \ - } \ + if (MGA_VERBOSE) \ + DRM_INFO("ADVANCE_DMA() tail=0x%05x sp=0x%x\n", \ + write, dev_priv->prim.space); \ } while (0) #define FLUSH_DMA() \ do { \ - if ( 0 ) { \ - DRM_INFO( "\n" ); \ - DRM_INFO( " tail=0x%06x head=0x%06lx\n", \ - dev_priv->prim.tail, \ - (unsigned long)(MGA_READ(MGA_PRIMADDRESS) - \ - dev_priv->primary->offset)); \ + if (0) { \ + DRM_INFO("\n"); \ + DRM_INFO(" tail=0x%06x head=0x%06lx\n", \ + dev_priv->prim.tail, \ + (unsigned long)(MGA_READ(MGA_PRIMADDRESS) - \ + dev_priv->primary->offset)); \ } \ - if ( !test_bit( 0, &dev_priv->prim.wrapped ) ) { \ - if ( dev_priv->prim.space < \ - dev_priv->prim.high_mark ) { \ - mga_do_dma_wrap_start( dev_priv ); \ - } else { \ - mga_do_dma_flush( dev_priv ); \ - } \ + if (!test_bit(0, &dev_priv->prim.wrapped)) { \ + if (dev_priv->prim.space < dev_priv->prim.high_mark) \ + mga_do_dma_wrap_start(dev_priv); \ + else \ + mga_do_dma_flush(dev_priv); \ } \ } while (0) /* Never use this, always use DMA_BLOCK(...) for primary DMA output. */ -#define DMA_WRITE( offset, val ) \ +#define DMA_WRITE(offset, val) \ do { \ - if ( MGA_VERBOSE ) { \ - DRM_INFO( " DMA_WRITE( 0x%08x ) at 0x%04Zx\n", \ - (u32)(val), write + (offset) * sizeof(u32) ); \ - } \ + if (MGA_VERBOSE) \ + DRM_INFO(" DMA_WRITE( 0x%08x ) at 0x%04Zx\n", \ + (u32)(val), write + (offset) * sizeof(u32)); \ *(volatile u32 *)(prim + write + (offset) * sizeof(u32)) = val; \ } while (0) -#define DMA_BLOCK( reg0, val0, reg1, val1, reg2, val2, reg3, val3 ) \ +#define DMA_BLOCK(reg0, val0, reg1, val1, reg2, val2, reg3, val3) \ do { \ - DMA_WRITE( 0, ((DMAREG( reg0 ) << 0) | \ - (DMAREG( reg1 ) << 8) | \ - (DMAREG( reg2 ) << 16) | \ - (DMAREG( reg3 ) << 24)) ); \ - DMA_WRITE( 1, val0 ); \ - DMA_WRITE( 2, val1 ); \ - DMA_WRITE( 3, val2 ); \ - DMA_WRITE( 4, val3 ); \ + DMA_WRITE(0, ((DMAREG(reg0) << 0) | \ + (DMAREG(reg1) << 8) | \ + (DMAREG(reg2) << 16) | \ + (DMAREG(reg3) << 24))); \ + DMA_WRITE(1, val0); \ + DMA_WRITE(2, val1); \ + DMA_WRITE(3, val2); \ + DMA_WRITE(4, val3); \ write += DMA_BLOCK_SIZE; \ } while (0) /* Buffer aging via primary DMA stream head pointer. */ -#define SET_AGE( age, h, w ) \ +#define SET_AGE(age, h, w) \ do { \ (age)->head = h; \ (age)->wrap = w; \ } while (0) -#define TEST_AGE( age, h, w ) ( (age)->wrap < w || \ - ( (age)->wrap == w && \ - (age)->head < h ) ) +#define TEST_AGE(age, h, w) ((age)->wrap < w || \ + ((age)->wrap == w && \ + (age)->head < h)) -#define AGE_BUFFER( buf_priv ) \ +#define AGE_BUFFER(buf_priv) \ do { \ drm_mga_freelist_t *entry = (buf_priv)->list_entry; \ - if ( (buf_priv)->dispatched ) { \ + if ((buf_priv)->dispatched) { \ entry->age.head = (dev_priv->prim.tail + \ dev_priv->primary->offset); \ entry->age.wrap = dev_priv->sarea_priv->last_wrap; \ @@ -681,7 +676,7 @@ do { \ /* Simple idle test. */ -static __inline__ int mga_is_idle(drm_mga_private_t * dev_priv) +static __inline__ int mga_is_idle(drm_mga_private_t *dev_priv) { u32 status = MGA_READ(MGA_STATUS) & MGA_ENGINE_IDLE_MASK; return (status == MGA_ENDPRDMASTS); diff --git a/drivers/gpu/drm/mga/mga_irq.c b/drivers/gpu/drm/mga/mga_irq.c index daa6041a483..2581202297e 100644 --- a/drivers/gpu/drm/mga/mga_irq.c +++ b/drivers/gpu/drm/mga/mga_irq.c @@ -76,9 +76,8 @@ irqreturn_t mga_driver_irq_handler(DRM_IRQ_ARGS) /* In addition to clearing the interrupt-pending bit, we * have to write to MGA_PRIMEND to re-start the DMA operation. */ - if ((prim_start & ~0x03) != (prim_end & ~0x03)) { + if ((prim_start & ~0x03) != (prim_end & ~0x03)) MGA_WRITE(MGA_PRIMEND, prim_end); - } atomic_inc(&dev_priv->last_fence_retired); DRM_WAKEUP(&dev_priv->fence_queue); @@ -120,7 +119,7 @@ void mga_disable_vblank(struct drm_device *dev, int crtc) /* MGA_WRITE(MGA_IEN, MGA_VLINEIEN | MGA_SOFTRAPEN); */ } -int mga_driver_fence_wait(struct drm_device * dev, unsigned int *sequence) +int mga_driver_fence_wait(struct drm_device *dev, unsigned int *sequence) { drm_mga_private_t *dev_priv = (drm_mga_private_t *) dev->dev_private; unsigned int cur_fence; @@ -139,7 +138,7 @@ int mga_driver_fence_wait(struct drm_device * dev, unsigned int *sequence) return ret; } -void mga_driver_irq_preinstall(struct drm_device * dev) +void mga_driver_irq_preinstall(struct drm_device *dev) { drm_mga_private_t *dev_priv = (drm_mga_private_t *) dev->dev_private; @@ -162,7 +161,7 @@ int mga_driver_irq_postinstall(struct drm_device *dev) return 0; } -void mga_driver_irq_uninstall(struct drm_device * dev) +void mga_driver_irq_uninstall(struct drm_device *dev) { drm_mga_private_t *dev_priv = (drm_mga_private_t *) dev->dev_private; if (!dev_priv) diff --git a/drivers/gpu/drm/mga/mga_state.c b/drivers/gpu/drm/mga/mga_state.c index a53b848e0f1..fff82045c42 100644 --- a/drivers/gpu/drm/mga/mga_state.c +++ b/drivers/gpu/drm/mga/mga_state.c @@ -41,8 +41,8 @@ * DMA hardware state programming functions */ -static void mga_emit_clip_rect(drm_mga_private_t * dev_priv, - struct drm_clip_rect * box) +static void mga_emit_clip_rect(drm_mga_private_t *dev_priv, + struct drm_clip_rect *box) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_mga_context_regs_t *ctx = &sarea_priv->context_state; @@ -66,7 +66,7 @@ static void mga_emit_clip_rect(drm_mga_private_t * dev_priv, ADVANCE_DMA(); } -static __inline__ void mga_g200_emit_context(drm_mga_private_t * dev_priv) +static __inline__ void mga_g200_emit_context(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_mga_context_regs_t *ctx = &sarea_priv->context_state; @@ -89,7 +89,7 @@ static __inline__ void mga_g200_emit_context(drm_mga_private_t * dev_priv) ADVANCE_DMA(); } -static __inline__ void mga_g400_emit_context(drm_mga_private_t * dev_priv) +static __inline__ void mga_g400_emit_context(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_mga_context_regs_t *ctx = &sarea_priv->context_state; @@ -116,7 +116,7 @@ static __inline__ void mga_g400_emit_context(drm_mga_private_t * dev_priv) ADVANCE_DMA(); } -static __inline__ void mga_g200_emit_tex0(drm_mga_private_t * dev_priv) +static __inline__ void mga_g200_emit_tex0(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_mga_texture_regs_t *tex = &sarea_priv->tex_state[0]; @@ -144,7 +144,7 @@ static __inline__ void mga_g200_emit_tex0(drm_mga_private_t * dev_priv) ADVANCE_DMA(); } -static __inline__ void mga_g400_emit_tex0(drm_mga_private_t * dev_priv) +static __inline__ void mga_g400_emit_tex0(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_mga_texture_regs_t *tex = &sarea_priv->tex_state[0]; @@ -184,7 +184,7 @@ static __inline__ void mga_g400_emit_tex0(drm_mga_private_t * dev_priv) ADVANCE_DMA(); } -static __inline__ void mga_g400_emit_tex1(drm_mga_private_t * dev_priv) +static __inline__ void mga_g400_emit_tex1(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_mga_texture_regs_t *tex = &sarea_priv->tex_state[1]; @@ -223,7 +223,7 @@ static __inline__ void mga_g400_emit_tex1(drm_mga_private_t * dev_priv) ADVANCE_DMA(); } -static __inline__ void mga_g200_emit_pipe(drm_mga_private_t * dev_priv) +static __inline__ void mga_g200_emit_pipe(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; unsigned int pipe = sarea_priv->warp_pipe; @@ -250,7 +250,7 @@ static __inline__ void mga_g200_emit_pipe(drm_mga_private_t * dev_priv) ADVANCE_DMA(); } -static __inline__ void mga_g400_emit_pipe(drm_mga_private_t * dev_priv) +static __inline__ void mga_g400_emit_pipe(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; unsigned int pipe = sarea_priv->warp_pipe; @@ -327,7 +327,7 @@ static __inline__ void mga_g400_emit_pipe(drm_mga_private_t * dev_priv) ADVANCE_DMA(); } -static void mga_g200_emit_state(drm_mga_private_t * dev_priv) +static void mga_g200_emit_state(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; unsigned int dirty = sarea_priv->dirty; @@ -348,7 +348,7 @@ static void mga_g200_emit_state(drm_mga_private_t * dev_priv) } } -static void mga_g400_emit_state(drm_mga_private_t * dev_priv) +static void mga_g400_emit_state(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; unsigned int dirty = sarea_priv->dirty; @@ -381,7 +381,7 @@ static void mga_g400_emit_state(drm_mga_private_t * dev_priv) /* Disallow all write destinations except the front and backbuffer. */ -static int mga_verify_context(drm_mga_private_t * dev_priv) +static int mga_verify_context(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_mga_context_regs_t *ctx = &sarea_priv->context_state; @@ -400,7 +400,7 @@ static int mga_verify_context(drm_mga_private_t * dev_priv) /* Disallow texture reads from PCI space. */ -static int mga_verify_tex(drm_mga_private_t * dev_priv, int unit) +static int mga_verify_tex(drm_mga_private_t *dev_priv, int unit) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_mga_texture_regs_t *tex = &sarea_priv->tex_state[unit]; @@ -417,7 +417,7 @@ static int mga_verify_tex(drm_mga_private_t * dev_priv, int unit) return 0; } -static int mga_verify_state(drm_mga_private_t * dev_priv) +static int mga_verify_state(drm_mga_private_t *dev_priv) { drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; unsigned int dirty = sarea_priv->dirty; @@ -446,7 +446,7 @@ static int mga_verify_state(drm_mga_private_t * dev_priv) return (ret == 0); } -static int mga_verify_iload(drm_mga_private_t * dev_priv, +static int mga_verify_iload(drm_mga_private_t *dev_priv, unsigned int dstorg, unsigned int length) { if (dstorg < dev_priv->texture_offset || @@ -465,7 +465,7 @@ static int mga_verify_iload(drm_mga_private_t * dev_priv, return 0; } -static int mga_verify_blit(drm_mga_private_t * dev_priv, +static int mga_verify_blit(drm_mga_private_t *dev_priv, unsigned int srcorg, unsigned int dstorg) { if ((srcorg & 0x3) == (MGA_SRCACC_PCI | MGA_SRCMAP_SYSMEM) || @@ -480,7 +480,7 @@ static int mga_verify_blit(drm_mga_private_t * dev_priv, * */ -static void mga_dma_dispatch_clear(struct drm_device * dev, drm_mga_clear_t * clear) +static void mga_dma_dispatch_clear(struct drm_device *dev, drm_mga_clear_t *clear) { drm_mga_private_t *dev_priv = dev->dev_private; drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -568,7 +568,7 @@ static void mga_dma_dispatch_clear(struct drm_device * dev, drm_mga_clear_t * cl FLUSH_DMA(); } -static void mga_dma_dispatch_swap(struct drm_device * dev) +static void mga_dma_dispatch_swap(struct drm_device *dev) { drm_mga_private_t *dev_priv = dev->dev_private; drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -622,7 +622,7 @@ static void mga_dma_dispatch_swap(struct drm_device * dev) DRM_DEBUG("... done.\n"); } -static void mga_dma_dispatch_vertex(struct drm_device * dev, struct drm_buf * buf) +static void mga_dma_dispatch_vertex(struct drm_device *dev, struct drm_buf *buf) { drm_mga_private_t *dev_priv = dev->dev_private; drm_mga_buf_priv_t *buf_priv = buf->dev_private; @@ -669,7 +669,7 @@ static void mga_dma_dispatch_vertex(struct drm_device * dev, struct drm_buf * bu FLUSH_DMA(); } -static void mga_dma_dispatch_indices(struct drm_device * dev, struct drm_buf * buf, +static void mga_dma_dispatch_indices(struct drm_device *dev, struct drm_buf *buf, unsigned int start, unsigned int end) { drm_mga_private_t *dev_priv = dev->dev_private; @@ -718,7 +718,7 @@ static void mga_dma_dispatch_indices(struct drm_device * dev, struct drm_buf * b /* This copies a 64 byte aligned agp region to the frambuffer with a * standard blit, the ioctl needs to do checking. */ -static void mga_dma_dispatch_iload(struct drm_device * dev, struct drm_buf * buf, +static void mga_dma_dispatch_iload(struct drm_device *dev, struct drm_buf *buf, unsigned int dstorg, unsigned int length) { drm_mga_private_t *dev_priv = dev->dev_private; @@ -766,7 +766,7 @@ static void mga_dma_dispatch_iload(struct drm_device * dev, struct drm_buf * buf FLUSH_DMA(); } -static void mga_dma_dispatch_blit(struct drm_device * dev, drm_mga_blit_t * blit) +static void mga_dma_dispatch_blit(struct drm_device *dev, drm_mga_blit_t *blit) { drm_mga_private_t *dev_priv = dev->dev_private; drm_mga_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -801,9 +801,8 @@ static void mga_dma_dispatch_blit(struct drm_device * dev, drm_mga_blit_t * blit int w = pbox[i].x2 - pbox[i].x1 - 1; int start; - if (blit->ydir == -1) { + if (blit->ydir == -1) srcy = blit->height - srcy - 1; - } start = srcy * blit->src_pitch + srcx; diff --git a/drivers/gpu/drm/mga/mga_warp.c b/drivers/gpu/drm/mga/mga_warp.c index 9aad4847afd..f172bd5c257 100644 --- a/drivers/gpu/drm/mga/mga_warp.c +++ b/drivers/gpu/drm/mga/mga_warp.c @@ -46,7 +46,7 @@ MODULE_FIRMWARE(FIRMWARE_G400); #define WARP_UCODE_SIZE(size) ALIGN(size, MGA_WARP_CODE_ALIGN) -int mga_warp_install_microcode(drm_mga_private_t * dev_priv) +int mga_warp_install_microcode(drm_mga_private_t *dev_priv) { unsigned char *vcbase = dev_priv->warp->handle; unsigned long pcbase = dev_priv->warp->offset; @@ -133,7 +133,7 @@ out: #define WMISC_EXPECTED (MGA_WUCODECACHE_ENABLE | MGA_WMASTER_ENABLE) -int mga_warp_init(drm_mga_private_t * dev_priv) +int mga_warp_init(drm_mga_private_t *dev_priv) { u32 wmisc; diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig index 1175429da10..d2d28048efb 100644 --- a/drivers/gpu/drm/nouveau/Kconfig +++ b/drivers/gpu/drm/nouveau/Kconfig @@ -1,6 +1,6 @@ config DRM_NOUVEAU tristate "Nouveau (nVidia) cards" - depends on DRM + depends on DRM && PCI select FW_LOADER select DRM_KMS_HELPER select DRM_TTM @@ -41,4 +41,13 @@ config DRM_I2C_CH7006 This driver is currently only useful if you're also using the nouveau driver. + +config DRM_I2C_SIL164 + tristate "Silicon Image sil164 TMDS transmitter" + default m if DRM_NOUVEAU + help + Support for sil164 and similar single-link (or dual-link + when used in pairs) TMDS transmitters, used in some nVidia + video cards. + endmenu diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile index acd31ed861e..2405d5ef0ca 100644 --- a/drivers/gpu/drm/nouveau/Makefile +++ b/drivers/gpu/drm/nouveau/Makefile @@ -9,10 +9,10 @@ nouveau-y := nouveau_drv.o nouveau_state.o nouveau_channel.o nouveau_mem.o \ nouveau_bo.o nouveau_fence.o nouveau_gem.o nouveau_ttm.o \ nouveau_hw.o nouveau_calc.o nouveau_bios.o nouveau_i2c.o \ nouveau_display.o nouveau_connector.o nouveau_fbcon.o \ - nouveau_dp.o nouveau_grctx.o \ + nouveau_dp.o \ nv04_timer.o \ nv04_mc.o nv40_mc.o nv50_mc.o \ - nv04_fb.o nv10_fb.o nv40_fb.o nv50_fb.o \ + nv04_fb.o nv10_fb.o nv30_fb.o nv40_fb.o nv50_fb.o \ nv04_fifo.o nv10_fifo.o nv40_fifo.o nv50_fifo.o \ nv04_graph.o nv10_graph.o nv20_graph.o \ nv40_graph.o nv50_graph.o \ @@ -22,7 +22,7 @@ nouveau-y := nouveau_drv.o nouveau_state.o nouveau_channel.o nouveau_mem.o \ nv50_cursor.o nv50_display.o nv50_fbcon.o \ nv04_dac.o nv04_dfp.o nv04_tv.o nv17_tv.o nv17_tv_modes.o \ nv04_crtc.o nv04_display.o nv04_cursor.o nv04_fbcon.o \ - nv17_gpio.o nv50_gpio.o \ + nv10_gpio.o nv50_gpio.o \ nv50_calc.o nouveau-$(CONFIG_DRM_NOUVEAU_DEBUG) += nouveau_debugfs.o diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index d4bcca8a513..c17a055ee3e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -3,6 +3,7 @@ #include <linux/slab.h> #include <acpi/acpi_drivers.h> #include <acpi/acpi_bus.h> +#include <acpi/video.h> #include "drmP.h" #include "drm.h" @@ -11,6 +12,7 @@ #include "nouveau_drv.h" #include "nouveau_drm.h" #include "nv50_display.h" +#include "nouveau_connector.h" #include <linux/vga_switcheroo.h> @@ -42,7 +44,7 @@ static const char nouveau_dsm_muid[] = { 0xB3, 0x4D, 0x7E, 0x5F, 0xEA, 0x12, 0x9F, 0xD4, }; -static int nouveau_dsm(acpi_handle handle, int func, int arg, int *result) +static int nouveau_dsm(acpi_handle handle, int func, int arg, uint32_t *result) { struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; struct acpi_object_list input; @@ -259,3 +261,37 @@ int nouveau_acpi_get_bios_chunk(uint8_t *bios, int offset, int len) { return nouveau_rom_call(nouveau_dsm_priv.rom_handle, bios, offset, len); } + +int +nouveau_acpi_edid(struct drm_device *dev, struct drm_connector *connector) +{ + struct nouveau_connector *nv_connector = nouveau_connector(connector); + struct acpi_device *acpidev; + acpi_handle handle; + int type, ret; + void *edid; + + switch (connector->connector_type) { + case DRM_MODE_CONNECTOR_LVDS: + case DRM_MODE_CONNECTOR_eDP: + type = ACPI_VIDEO_DISPLAY_LCD; + break; + default: + return -EINVAL; + } + + handle = DEVICE_ACPI_HANDLE(&dev->pdev->dev); + if (!handle) + return -ENODEV; + + ret = acpi_bus_get_device(handle, &acpidev); + if (ret) + return -ENODEV; + + ret = acpi_video_get_edid(acpidev, type, -1, &edid); + if (ret < 0) + return ret; + + nv_connector->edid = edid; + return 0; +} diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index e492919faf4..7369b5e7364 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -28,6 +28,8 @@ #include "nouveau_hw.h" #include "nouveau_encoder.h" +#include <linux/io-mapping.h> + /* these defines are made up */ #define NV_CIO_CRE_44_HEADA 0x0 #define NV_CIO_CRE_44_HEADB 0x3 @@ -209,20 +211,20 @@ static struct methods shadow_methods[] = { { "PCIROM", load_vbios_pci, true }, { "ACPI", load_vbios_acpi, true }, }; +#define NUM_SHADOW_METHODS ARRAY_SIZE(shadow_methods) static bool NVShadowVBIOS(struct drm_device *dev, uint8_t *data) { - const int nr_methods = ARRAY_SIZE(shadow_methods); struct methods *methods = shadow_methods; int testscore = 3; - int scores[nr_methods], i; + int scores[NUM_SHADOW_METHODS], i; if (nouveau_vbios) { - for (i = 0; i < nr_methods; i++) + for (i = 0; i < NUM_SHADOW_METHODS; i++) if (!strcasecmp(nouveau_vbios, methods[i].desc)) break; - if (i < nr_methods) { + if (i < NUM_SHADOW_METHODS) { NV_INFO(dev, "Attempting to use BIOS image from %s\n", methods[i].desc); @@ -234,7 +236,7 @@ static bool NVShadowVBIOS(struct drm_device *dev, uint8_t *data) NV_ERROR(dev, "VBIOS source \'%s\' invalid\n", nouveau_vbios); } - for (i = 0; i < nr_methods; i++) { + for (i = 0; i < NUM_SHADOW_METHODS; i++) { NV_TRACE(dev, "Attempting to load BIOS image from %s\n", methods[i].desc); data[0] = data[1] = 0; /* avoid reuse of previous image */ @@ -245,7 +247,7 @@ static bool NVShadowVBIOS(struct drm_device *dev, uint8_t *data) } while (--testscore > 0) { - for (i = 0; i < nr_methods; i++) { + for (i = 0; i < NUM_SHADOW_METHODS; i++) { if (scores[i] == testscore) { NV_TRACE(dev, "Using BIOS image from %s\n", methods[i].desc); @@ -920,7 +922,7 @@ init_io_restrict_prog(struct nvbios *bios, uint16_t offset, NV_ERROR(bios->dev, "0x%04X: Config 0x%02X exceeds maximal bound 0x%02X\n", offset, config, count); - return -EINVAL; + return len; } configval = ROM32(bios->data[offset + 11 + config * 4]); @@ -1022,7 +1024,7 @@ init_io_restrict_pll(struct nvbios *bios, uint16_t offset, NV_ERROR(bios->dev, "0x%04X: Config 0x%02X exceeds maximal bound 0x%02X\n", offset, config, count); - return -EINVAL; + return len; } freq = ROM16(bios->data[offset + 12 + config * 2]); @@ -1194,7 +1196,7 @@ init_dp_condition(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) dpe = nouveau_bios_dp_table(dev, dcb, &dummy); if (!dpe) { NV_ERROR(dev, "0x%04X: INIT_3A: no encoder table!!\n", offset); - return -EINVAL; + return 3; } switch (cond) { @@ -1218,12 +1220,16 @@ init_dp_condition(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) int ret; auxch = nouveau_i2c_find(dev, bios->display.output->i2c_index); - if (!auxch) - return -ENODEV; + if (!auxch) { + NV_ERROR(dev, "0x%04X: couldn't get auxch\n", offset); + return 3; + } ret = nouveau_dp_auxch(auxch, 9, 0xd, &cond, 1); - if (ret) - return ret; + if (ret) { + NV_ERROR(dev, "0x%04X: auxch rd fail: %d\n", offset, ret); + return 3; + } if (cond & 1) iexec->execute = false; @@ -1392,7 +1398,7 @@ init_io_restrict_pll2(struct nvbios *bios, uint16_t offset, NV_ERROR(bios->dev, "0x%04X: Config 0x%02X exceeds maximal bound 0x%02X\n", offset, config, count); - return -EINVAL; + return len; } freq = ROM32(bios->data[offset + 11 + config * 4]); @@ -1452,6 +1458,7 @@ init_i2c_byte(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) * "mask n" and OR it with "data n" before writing it back to the device */ + struct drm_device *dev = bios->dev; uint8_t i2c_index = bios->data[offset + 1]; uint8_t i2c_address = bios->data[offset + 2] >> 1; uint8_t count = bios->data[offset + 3]; @@ -1466,9 +1473,11 @@ init_i2c_byte(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) "Count: 0x%02X\n", offset, i2c_index, i2c_address, count); - chan = init_i2c_device_find(bios->dev, i2c_index); - if (!chan) - return -ENODEV; + chan = init_i2c_device_find(dev, i2c_index); + if (!chan) { + NV_ERROR(dev, "0x%04X: i2c bus not found\n", offset); + return len; + } for (i = 0; i < count; i++) { uint8_t reg = bios->data[offset + 4 + i * 3]; @@ -1479,8 +1488,10 @@ init_i2c_byte(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) ret = i2c_smbus_xfer(&chan->adapter, i2c_address, 0, I2C_SMBUS_READ, reg, I2C_SMBUS_BYTE_DATA, &val); - if (ret < 0) - return ret; + if (ret < 0) { + NV_ERROR(dev, "0x%04X: i2c rd fail: %d\n", offset, ret); + return len; + } BIOSLOG(bios, "0x%04X: I2CReg: 0x%02X, Value: 0x%02X, " "Mask: 0x%02X, Data: 0x%02X\n", @@ -1494,8 +1505,10 @@ init_i2c_byte(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) ret = i2c_smbus_xfer(&chan->adapter, i2c_address, 0, I2C_SMBUS_WRITE, reg, I2C_SMBUS_BYTE_DATA, &val); - if (ret < 0) - return ret; + if (ret < 0) { + NV_ERROR(dev, "0x%04X: i2c wr fail: %d\n", offset, ret); + return len; + } } return len; @@ -1520,6 +1533,7 @@ init_zm_i2c_byte(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) * "DCB I2C table entry index", set the register to "data n" */ + struct drm_device *dev = bios->dev; uint8_t i2c_index = bios->data[offset + 1]; uint8_t i2c_address = bios->data[offset + 2] >> 1; uint8_t count = bios->data[offset + 3]; @@ -1534,9 +1548,11 @@ init_zm_i2c_byte(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) "Count: 0x%02X\n", offset, i2c_index, i2c_address, count); - chan = init_i2c_device_find(bios->dev, i2c_index); - if (!chan) - return -ENODEV; + chan = init_i2c_device_find(dev, i2c_index); + if (!chan) { + NV_ERROR(dev, "0x%04X: i2c bus not found\n", offset); + return len; + } for (i = 0; i < count; i++) { uint8_t reg = bios->data[offset + 4 + i * 2]; @@ -1553,8 +1569,10 @@ init_zm_i2c_byte(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) ret = i2c_smbus_xfer(&chan->adapter, i2c_address, 0, I2C_SMBUS_WRITE, reg, I2C_SMBUS_BYTE_DATA, &val); - if (ret < 0) - return ret; + if (ret < 0) { + NV_ERROR(dev, "0x%04X: i2c wr fail: %d\n", offset, ret); + return len; + } } return len; @@ -1577,6 +1595,7 @@ init_zm_i2c(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) * address" on the I2C bus given by "DCB I2C table entry index" */ + struct drm_device *dev = bios->dev; uint8_t i2c_index = bios->data[offset + 1]; uint8_t i2c_address = bios->data[offset + 2] >> 1; uint8_t count = bios->data[offset + 3]; @@ -1584,7 +1603,7 @@ init_zm_i2c(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) struct nouveau_i2c_chan *chan; struct i2c_msg msg; uint8_t data[256]; - int i; + int ret, i; if (!iexec->execute) return len; @@ -1593,9 +1612,11 @@ init_zm_i2c(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) "Count: 0x%02X\n", offset, i2c_index, i2c_address, count); - chan = init_i2c_device_find(bios->dev, i2c_index); - if (!chan) - return -ENODEV; + chan = init_i2c_device_find(dev, i2c_index); + if (!chan) { + NV_ERROR(dev, "0x%04X: i2c bus not found\n", offset); + return len; + } for (i = 0; i < count; i++) { data[i] = bios->data[offset + 4 + i]; @@ -1608,8 +1629,11 @@ init_zm_i2c(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) msg.flags = 0; msg.len = count; msg.buf = data; - if (i2c_transfer(&chan->adapter, &msg, 1) != 1) - return -EIO; + ret = i2c_transfer(&chan->adapter, &msg, 1); + if (ret != 1) { + NV_ERROR(dev, "0x%04X: i2c wr fail: %d\n", offset, ret); + return len; + } } return len; @@ -1633,6 +1657,7 @@ init_tmds(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) * used -- see get_tmds_index_reg() */ + struct drm_device *dev = bios->dev; uint8_t mlv = bios->data[offset + 1]; uint32_t tmdsaddr = bios->data[offset + 2]; uint8_t mask = bios->data[offset + 3]; @@ -1647,8 +1672,10 @@ init_tmds(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) offset, mlv, tmdsaddr, mask, data); reg = get_tmds_index_reg(bios->dev, mlv); - if (!reg) - return -EINVAL; + if (!reg) { + NV_ERROR(dev, "0x%04X: no tmds_index_reg\n", offset); + return 5; + } bios_wr32(bios, reg, tmdsaddr | NV_PRAMDAC_FP_TMDS_CONTROL_WRITE_DISABLE); @@ -1678,6 +1705,7 @@ init_zm_tmds_group(struct nvbios *bios, uint16_t offset, * register is used -- see get_tmds_index_reg() */ + struct drm_device *dev = bios->dev; uint8_t mlv = bios->data[offset + 1]; uint8_t count = bios->data[offset + 2]; int len = 3 + count * 2; @@ -1691,8 +1719,10 @@ init_zm_tmds_group(struct nvbios *bios, uint16_t offset, offset, mlv, count); reg = get_tmds_index_reg(bios->dev, mlv); - if (!reg) - return -EINVAL; + if (!reg) { + NV_ERROR(dev, "0x%04X: no tmds_index_reg\n", offset); + return len; + } for (i = 0; i < count; i++) { uint8_t tmdsaddr = bios->data[offset + 3 + i * 2]; @@ -2039,6 +2069,323 @@ init_zm_index_io(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) return 5; } +static inline void +bios_md32(struct nvbios *bios, uint32_t reg, + uint32_t mask, uint32_t val) +{ + bios_wr32(bios, reg, (bios_rd32(bios, reg) & ~mask) | val); +} + +static uint32_t +peek_fb(struct drm_device *dev, struct io_mapping *fb, + uint32_t off) +{ + uint32_t val = 0; + + if (off < pci_resource_len(dev->pdev, 1)) { + uint32_t __iomem *p = io_mapping_map_atomic_wc(fb, off, KM_USER0); + + val = ioread32(p); + + io_mapping_unmap_atomic(p, KM_USER0); + } + + return val; +} + +static void +poke_fb(struct drm_device *dev, struct io_mapping *fb, + uint32_t off, uint32_t val) +{ + if (off < pci_resource_len(dev->pdev, 1)) { + uint32_t __iomem *p = io_mapping_map_atomic_wc(fb, off, KM_USER0); + + iowrite32(val, p); + wmb(); + + io_mapping_unmap_atomic(p, KM_USER0); + } +} + +static inline bool +read_back_fb(struct drm_device *dev, struct io_mapping *fb, + uint32_t off, uint32_t val) +{ + poke_fb(dev, fb, off, val); + return val == peek_fb(dev, fb, off); +} + +static int +nv04_init_compute_mem(struct nvbios *bios) +{ + struct drm_device *dev = bios->dev; + uint32_t patt = 0xdeadbeef; + struct io_mapping *fb; + int i; + + /* Map the framebuffer aperture */ + fb = io_mapping_create_wc(pci_resource_start(dev->pdev, 1), + pci_resource_len(dev->pdev, 1)); + if (!fb) + return -ENOMEM; + + /* Sequencer and refresh off */ + NVWriteVgaSeq(dev, 0, 1, NVReadVgaSeq(dev, 0, 1) | 0x20); + bios_md32(bios, NV04_PFB_DEBUG_0, 0, NV04_PFB_DEBUG_0_REFRESH_OFF); + + bios_md32(bios, NV04_PFB_BOOT_0, ~0, + NV04_PFB_BOOT_0_RAM_AMOUNT_16MB | + NV04_PFB_BOOT_0_RAM_WIDTH_128 | + NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_16MBIT); + + for (i = 0; i < 4; i++) + poke_fb(dev, fb, 4 * i, patt); + + poke_fb(dev, fb, 0x400000, patt + 1); + + if (peek_fb(dev, fb, 0) == patt + 1) { + bios_md32(bios, NV04_PFB_BOOT_0, NV04_PFB_BOOT_0_RAM_TYPE, + NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_16MBIT); + bios_md32(bios, NV04_PFB_DEBUG_0, + NV04_PFB_DEBUG_0_REFRESH_OFF, 0); + + for (i = 0; i < 4; i++) + poke_fb(dev, fb, 4 * i, patt); + + if ((peek_fb(dev, fb, 0xc) & 0xffff) != (patt & 0xffff)) + bios_md32(bios, NV04_PFB_BOOT_0, + NV04_PFB_BOOT_0_RAM_WIDTH_128 | + NV04_PFB_BOOT_0_RAM_AMOUNT, + NV04_PFB_BOOT_0_RAM_AMOUNT_8MB); + + } else if ((peek_fb(dev, fb, 0xc) & 0xffff0000) != + (patt & 0xffff0000)) { + bios_md32(bios, NV04_PFB_BOOT_0, + NV04_PFB_BOOT_0_RAM_WIDTH_128 | + NV04_PFB_BOOT_0_RAM_AMOUNT, + NV04_PFB_BOOT_0_RAM_AMOUNT_4MB); + + } else if (peek_fb(dev, fb, 0) == patt) { + if (read_back_fb(dev, fb, 0x800000, patt)) + bios_md32(bios, NV04_PFB_BOOT_0, + NV04_PFB_BOOT_0_RAM_AMOUNT, + NV04_PFB_BOOT_0_RAM_AMOUNT_8MB); + else + bios_md32(bios, NV04_PFB_BOOT_0, + NV04_PFB_BOOT_0_RAM_AMOUNT, + NV04_PFB_BOOT_0_RAM_AMOUNT_4MB); + + bios_md32(bios, NV04_PFB_BOOT_0, NV04_PFB_BOOT_0_RAM_TYPE, + NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_8MBIT); + + } else if (!read_back_fb(dev, fb, 0x800000, patt)) { + bios_md32(bios, NV04_PFB_BOOT_0, NV04_PFB_BOOT_0_RAM_AMOUNT, + NV04_PFB_BOOT_0_RAM_AMOUNT_8MB); + + } + + /* Refresh on, sequencer on */ + bios_md32(bios, NV04_PFB_DEBUG_0, NV04_PFB_DEBUG_0_REFRESH_OFF, 0); + NVWriteVgaSeq(dev, 0, 1, NVReadVgaSeq(dev, 0, 1) & ~0x20); + + io_mapping_free(fb); + return 0; +} + +static const uint8_t * +nv05_memory_config(struct nvbios *bios) +{ + /* Defaults for BIOSes lacking a memory config table */ + static const uint8_t default_config_tab[][2] = { + { 0x24, 0x00 }, + { 0x28, 0x00 }, + { 0x24, 0x01 }, + { 0x1f, 0x00 }, + { 0x0f, 0x00 }, + { 0x17, 0x00 }, + { 0x06, 0x00 }, + { 0x00, 0x00 } + }; + int i = (bios_rd32(bios, NV_PEXTDEV_BOOT_0) & + NV_PEXTDEV_BOOT_0_RAMCFG) >> 2; + + if (bios->legacy.mem_init_tbl_ptr) + return &bios->data[bios->legacy.mem_init_tbl_ptr + 2 * i]; + else + return default_config_tab[i]; +} + +static int +nv05_init_compute_mem(struct nvbios *bios) +{ + struct drm_device *dev = bios->dev; + const uint8_t *ramcfg = nv05_memory_config(bios); + uint32_t patt = 0xdeadbeef; + struct io_mapping *fb; + int i, v; + + /* Map the framebuffer aperture */ + fb = io_mapping_create_wc(pci_resource_start(dev->pdev, 1), + pci_resource_len(dev->pdev, 1)); + if (!fb) + return -ENOMEM; + + /* Sequencer off */ + NVWriteVgaSeq(dev, 0, 1, NVReadVgaSeq(dev, 0, 1) | 0x20); + + if (bios_rd32(bios, NV04_PFB_BOOT_0) & NV04_PFB_BOOT_0_UMA_ENABLE) + goto out; + + bios_md32(bios, NV04_PFB_DEBUG_0, NV04_PFB_DEBUG_0_REFRESH_OFF, 0); + + /* If present load the hardcoded scrambling table */ + if (bios->legacy.mem_init_tbl_ptr) { + uint32_t *scramble_tab = (uint32_t *)&bios->data[ + bios->legacy.mem_init_tbl_ptr + 0x10]; + + for (i = 0; i < 8; i++) + bios_wr32(bios, NV04_PFB_SCRAMBLE(i), + ROM32(scramble_tab[i])); + } + + /* Set memory type/width/length defaults depending on the straps */ + bios_md32(bios, NV04_PFB_BOOT_0, 0x3f, ramcfg[0]); + + if (ramcfg[1] & 0x80) + bios_md32(bios, NV04_PFB_CFG0, 0, NV04_PFB_CFG0_SCRAMBLE); + + bios_md32(bios, NV04_PFB_CFG1, 0x700001, (ramcfg[1] & 1) << 20); + bios_md32(bios, NV04_PFB_CFG1, 0, 1); + + /* Probe memory bus width */ + for (i = 0; i < 4; i++) + poke_fb(dev, fb, 4 * i, patt); + + if (peek_fb(dev, fb, 0xc) != patt) + bios_md32(bios, NV04_PFB_BOOT_0, + NV04_PFB_BOOT_0_RAM_WIDTH_128, 0); + + /* Probe memory length */ + v = bios_rd32(bios, NV04_PFB_BOOT_0) & NV04_PFB_BOOT_0_RAM_AMOUNT; + + if (v == NV04_PFB_BOOT_0_RAM_AMOUNT_32MB && + (!read_back_fb(dev, fb, 0x1000000, ++patt) || + !read_back_fb(dev, fb, 0, ++patt))) + bios_md32(bios, NV04_PFB_BOOT_0, NV04_PFB_BOOT_0_RAM_AMOUNT, + NV04_PFB_BOOT_0_RAM_AMOUNT_16MB); + + if (v == NV04_PFB_BOOT_0_RAM_AMOUNT_16MB && + !read_back_fb(dev, fb, 0x800000, ++patt)) + bios_md32(bios, NV04_PFB_BOOT_0, NV04_PFB_BOOT_0_RAM_AMOUNT, + NV04_PFB_BOOT_0_RAM_AMOUNT_8MB); + + if (!read_back_fb(dev, fb, 0x400000, ++patt)) + bios_md32(bios, NV04_PFB_BOOT_0, NV04_PFB_BOOT_0_RAM_AMOUNT, + NV04_PFB_BOOT_0_RAM_AMOUNT_4MB); + +out: + /* Sequencer on */ + NVWriteVgaSeq(dev, 0, 1, NVReadVgaSeq(dev, 0, 1) & ~0x20); + + io_mapping_free(fb); + return 0; +} + +static int +nv10_init_compute_mem(struct nvbios *bios) +{ + struct drm_device *dev = bios->dev; + struct drm_nouveau_private *dev_priv = bios->dev->dev_private; + const int mem_width[] = { 0x10, 0x00, 0x20 }; + const int mem_width_count = (dev_priv->chipset >= 0x17 ? 3 : 2); + uint32_t patt = 0xdeadbeef; + struct io_mapping *fb; + int i, j, k; + + /* Map the framebuffer aperture */ + fb = io_mapping_create_wc(pci_resource_start(dev->pdev, 1), + pci_resource_len(dev->pdev, 1)); + if (!fb) + return -ENOMEM; + + bios_wr32(bios, NV10_PFB_REFCTRL, NV10_PFB_REFCTRL_VALID_1); + + /* Probe memory bus width */ + for (i = 0; i < mem_width_count; i++) { + bios_md32(bios, NV04_PFB_CFG0, 0x30, mem_width[i]); + + for (j = 0; j < 4; j++) { + for (k = 0; k < 4; k++) + poke_fb(dev, fb, 0x1c, 0); + + poke_fb(dev, fb, 0x1c, patt); + poke_fb(dev, fb, 0x3c, 0); + + if (peek_fb(dev, fb, 0x1c) == patt) + goto mem_width_found; + } + } + +mem_width_found: + patt <<= 1; + + /* Probe amount of installed memory */ + for (i = 0; i < 4; i++) { + int off = bios_rd32(bios, NV04_PFB_FIFO_DATA) - 0x100000; + + poke_fb(dev, fb, off, patt); + poke_fb(dev, fb, 0, 0); + + peek_fb(dev, fb, 0); + peek_fb(dev, fb, 0); + peek_fb(dev, fb, 0); + peek_fb(dev, fb, 0); + + if (peek_fb(dev, fb, off) == patt) + goto amount_found; + } + + /* IC missing - disable the upper half memory space. */ + bios_md32(bios, NV04_PFB_CFG0, 0x1000, 0); + +amount_found: + io_mapping_free(fb); + return 0; +} + +static int +nv20_init_compute_mem(struct nvbios *bios) +{ + struct drm_device *dev = bios->dev; + struct drm_nouveau_private *dev_priv = bios->dev->dev_private; + uint32_t mask = (dev_priv->chipset >= 0x25 ? 0x300 : 0x900); + uint32_t amount, off; + struct io_mapping *fb; + + /* Map the framebuffer aperture */ + fb = io_mapping_create_wc(pci_resource_start(dev->pdev, 1), + pci_resource_len(dev->pdev, 1)); + if (!fb) + return -ENOMEM; + + bios_wr32(bios, NV10_PFB_REFCTRL, NV10_PFB_REFCTRL_VALID_1); + + /* Allow full addressing */ + bios_md32(bios, NV04_PFB_CFG0, 0, mask); + + amount = bios_rd32(bios, NV04_PFB_FIFO_DATA); + for (off = amount; off > 0x2000000; off -= 0x2000000) + poke_fb(dev, fb, off - 4, off); + + amount = bios_rd32(bios, NV04_PFB_FIFO_DATA); + if (amount != peek_fb(dev, fb, amount - 4)) + /* IC missing - disable the upper half memory space. */ + bios_md32(bios, NV04_PFB_CFG0, mask, 0); + + io_mapping_free(fb); + return 0; +} + static int init_compute_mem(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) { @@ -2047,64 +2394,57 @@ init_compute_mem(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) * * offset (8 bit): opcode * - * This opcode is meant to set NV_PFB_CFG0 (0x100200) appropriately so - * that the hardware can correctly calculate how much VRAM it has - * (and subsequently report that value in NV_PFB_CSTATUS (0x10020C)) + * This opcode is meant to set the PFB memory config registers + * appropriately so that we can correctly calculate how much VRAM it + * has (on nv10 and better chipsets the amount of installed VRAM is + * subsequently reported in NV_PFB_CSTATUS (0x10020C)). * - * The implementation of this opcode in general consists of two parts: - * 1) determination of the memory bus width - * 2) determination of how many of the card's RAM pads have ICs attached + * The implementation of this opcode in general consists of several + * parts: * - * 1) is done by a cunning combination of writes to offsets 0x1c and - * 0x3c in the framebuffer, and seeing whether the written values are - * read back correctly. This then affects bits 4-7 of NV_PFB_CFG0 + * 1) Determination of memory type and density. Only necessary for + * really old chipsets, the memory type reported by the strap bits + * (0x101000) is assumed to be accurate on nv05 and newer. * - * 2) is done by a cunning combination of writes to an offset slightly - * less than the maximum memory reported by NV_PFB_CSTATUS, then seeing - * if the test pattern can be read back. This then affects bits 12-15 of - * NV_PFB_CFG0 + * 2) Determination of the memory bus width. Usually done by a cunning + * combination of writes to offsets 0x1c and 0x3c in the fb, and + * seeing whether the written values are read back correctly. * - * In this context a "cunning combination" may include multiple reads - * and writes to varying locations, often alternating the test pattern - * and 0, doubtless to make sure buffers are filled, residual charges - * on tracks are removed etc. + * Only necessary on nv0x-nv1x and nv34, on the other cards we can + * trust the straps. * - * Unfortunately, the "cunning combination"s mentioned above, and the - * changes to the bits in NV_PFB_CFG0 differ with nearly every bios - * trace I have. + * 3) Determination of how many of the card's RAM pads have ICs + * attached, usually done by a cunning combination of writes to an + * offset slightly less than the maximum memory reported by + * NV_PFB_CSTATUS, then seeing if the test pattern can be read back. * - * Therefore, we cheat and assume the value of NV_PFB_CFG0 with which - * we started was correct, and use that instead + * This appears to be a NOP on IGPs and NV4x or newer chipsets, both io + * logs of the VBIOS and kmmio traces of the binary driver POSTing the + * card show nothing being done for this opcode. Why is it still listed + * in the table?! */ /* no iexec->execute check by design */ - /* - * This appears to be a NOP on G8x chipsets, both io logs of the VBIOS - * and kmmio traces of the binary driver POSTing the card show nothing - * being done for this opcode. why is it still listed in the table?! - */ - struct drm_nouveau_private *dev_priv = bios->dev->dev_private; + int ret; - if (dev_priv->card_type >= NV_40) - return 1; - - /* - * On every card I've seen, this step gets done for us earlier in - * the init scripts - uint8_t crdata = bios_idxprt_rd(dev, NV_VIO_SRX, 0x01); - bios_idxprt_wr(dev, NV_VIO_SRX, 0x01, crdata | 0x20); - */ - - /* - * This also has probably been done in the scripts, but an mmio trace of - * s3 resume shows nvidia doing it anyway (unlike the NV_VIO_SRX write) - */ - bios_wr32(bios, NV_PFB_REFCTRL, NV_PFB_REFCTRL_VALID_1); + if (dev_priv->chipset >= 0x40 || + dev_priv->chipset == 0x1a || + dev_priv->chipset == 0x1f) + ret = 0; + else if (dev_priv->chipset >= 0x20 && + dev_priv->chipset != 0x34) + ret = nv20_init_compute_mem(bios); + else if (dev_priv->chipset >= 0x10) + ret = nv10_init_compute_mem(bios); + else if (dev_priv->chipset >= 0x5) + ret = nv05_init_compute_mem(bios); + else + ret = nv04_init_compute_mem(bios); - /* write back the saved configuration value */ - bios_wr32(bios, NV_PFB_CFG0, bios->state.saved_nv_pfb_cfg0); + if (ret) + return ret; return 1; } @@ -2131,7 +2471,8 @@ init_reset(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) /* no iexec->execute check by design */ pci_nv_19 = bios_rd32(bios, NV_PBUS_PCI_NV_19); - bios_wr32(bios, NV_PBUS_PCI_NV_19, 0); + bios_wr32(bios, NV_PBUS_PCI_NV_19, pci_nv_19 & ~0xf00); + bios_wr32(bios, reg, value1); udelay(10); @@ -2167,7 +2508,7 @@ init_configure_mem(struct nvbios *bios, uint16_t offset, uint32_t reg, data; if (bios->major_version > 2) - return -ENODEV; + return 0; bios_idxprt_wr(bios, NV_VIO_SRX, NV_VIO_SR_CLOCK_INDEX, bios_idxprt_rd( bios, NV_VIO_SRX, NV_VIO_SR_CLOCK_INDEX) | 0x20); @@ -2180,14 +2521,14 @@ init_configure_mem(struct nvbios *bios, uint16_t offset, reg = ROM32(bios->data[seqtbloffs += 4])) { switch (reg) { - case NV_PFB_PRE: - data = NV_PFB_PRE_CMD_PRECHARGE; + case NV04_PFB_PRE: + data = NV04_PFB_PRE_CMD_PRECHARGE; break; - case NV_PFB_PAD: - data = NV_PFB_PAD_CKE_NORMAL; + case NV04_PFB_PAD: + data = NV04_PFB_PAD_CKE_NORMAL; break; - case NV_PFB_REF: - data = NV_PFB_REF_CMD_REFRESH; + case NV04_PFB_REF: + data = NV04_PFB_REF_CMD_REFRESH; break; default: data = ROM32(bios->data[meminitdata]); @@ -2222,7 +2563,7 @@ init_configure_clk(struct nvbios *bios, uint16_t offset, int clock; if (bios->major_version > 2) - return -ENODEV; + return 0; clock = ROM16(bios->data[meminitoffs + 4]) * 10; setPLL(bios, NV_PRAMDAC_NVPLL_COEFF, clock); @@ -2255,7 +2596,7 @@ init_configure_preinit(struct nvbios *bios, uint16_t offset, uint8_t cr3c = ((straps << 2) & 0xf0) | (straps & (1 << 6)); if (bios->major_version > 2) - return -ENODEV; + return 0; bios_idxprt_wr(bios, NV_CIO_CRX__COLOR, NV_CIO_CRE_SCRATCH4__INDEX, cr3c); @@ -2389,7 +2730,7 @@ init_ram_condition(struct nvbios *bios, uint16_t offset, * offset + 1 (8 bit): mask * offset + 2 (8 bit): cmpval * - * Test if (NV_PFB_BOOT_0 & "mask") equals "cmpval". + * Test if (NV04_PFB_BOOT_0 & "mask") equals "cmpval". * If condition not met skip subsequent opcodes until condition is * inverted (INIT_NOT), or we hit INIT_RESUME */ @@ -2401,7 +2742,7 @@ init_ram_condition(struct nvbios *bios, uint16_t offset, if (!iexec->execute) return 3; - data = bios_rd32(bios, NV_PFB_BOOT_0) & mask; + data = bios_rd32(bios, NV04_PFB_BOOT_0) & mask; BIOSLOG(bios, "0x%04X: Checking if 0x%08X equals 0x%08X\n", offset, data, cmpval); @@ -2795,12 +3136,13 @@ init_gpio(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) */ struct drm_nouveau_private *dev_priv = bios->dev->dev_private; + struct nouveau_gpio_engine *pgpio = &dev_priv->engine.gpio; const uint32_t nv50_gpio_ctl[2] = { 0xe100, 0xe28c }; int i; if (dev_priv->card_type != NV_50) { NV_ERROR(bios->dev, "INIT_GPIO on unsupported chipset\n"); - return -ENODEV; + return 1; } if (!iexec->execute) @@ -2815,7 +3157,7 @@ init_gpio(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) BIOSLOG(bios, "0x%04X: set gpio 0x%02x, state %d\n", offset, gpio->tag, gpio->state_default); if (bios->execute) - nv50_gpio_set(bios->dev, gpio->tag, gpio->state_default); + pgpio->set(bios->dev, gpio->tag, gpio->state_default); /* The NVIDIA binary driver doesn't appear to actually do * any of this, my VBIOS does however. @@ -2872,10 +3214,7 @@ init_ram_restrict_zm_reg_group(struct nvbios *bios, uint16_t offset, uint8_t index; int i; - - if (!iexec->execute) - return len; - + /* critical! to know the length of the opcode */; if (!blocklen) { NV_ERROR(bios->dev, "0x%04X: Zero block length - has the M table " @@ -2883,6 +3222,9 @@ init_ram_restrict_zm_reg_group(struct nvbios *bios, uint16_t offset, return -EINVAL; } + if (!iexec->execute) + return len; + strap_ramcfg = (bios_rd32(bios, NV_PEXTDEV_BOOT_0) >> 2) & 0xf; index = bios->data[bios->ram_restrict_tbl_ptr + strap_ramcfg]; @@ -3064,14 +3406,14 @@ init_auxch(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) if (!bios->display.output) { NV_ERROR(dev, "INIT_AUXCH: no active output\n"); - return -EINVAL; + return len; } auxch = init_i2c_device_find(dev, bios->display.output->i2c_index); if (!auxch) { NV_ERROR(dev, "INIT_AUXCH: couldn't get auxch %d\n", bios->display.output->i2c_index); - return -ENODEV; + return len; } if (!iexec->execute) @@ -3084,7 +3426,7 @@ init_auxch(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) ret = nouveau_dp_auxch(auxch, 9, addr, &data, 1); if (ret) { NV_ERROR(dev, "INIT_AUXCH: rd auxch fail %d\n", ret); - return ret; + return len; } data &= bios->data[offset + 0]; @@ -3093,7 +3435,7 @@ init_auxch(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) ret = nouveau_dp_auxch(auxch, 8, addr, &data, 1); if (ret) { NV_ERROR(dev, "INIT_AUXCH: wr auxch fail %d\n", ret); - return ret; + return len; } } @@ -3123,14 +3465,14 @@ init_zm_auxch(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) if (!bios->display.output) { NV_ERROR(dev, "INIT_ZM_AUXCH: no active output\n"); - return -EINVAL; + return len; } auxch = init_i2c_device_find(dev, bios->display.output->i2c_index); if (!auxch) { NV_ERROR(dev, "INIT_ZM_AUXCH: couldn't get auxch %d\n", bios->display.output->i2c_index); - return -ENODEV; + return len; } if (!iexec->execute) @@ -3141,7 +3483,7 @@ init_zm_auxch(struct nvbios *bios, uint16_t offset, struct init_exec *iexec) ret = nouveau_dp_auxch(auxch, 8, addr, &bios->data[offset], 1); if (ret) { NV_ERROR(dev, "INIT_ZM_AUXCH: wr auxch fail %d\n", ret); - return ret; + return len; } } @@ -5151,10 +5493,14 @@ static int parse_bmp_structure(struct drm_device *dev, struct nvbios *bios, unsi bios->legacy.i2c_indices.crt = bios->data[legacy_i2c_offset]; bios->legacy.i2c_indices.tv = bios->data[legacy_i2c_offset + 1]; bios->legacy.i2c_indices.panel = bios->data[legacy_i2c_offset + 2]; - bios->dcb.i2c[0].write = bios->data[legacy_i2c_offset + 4]; - bios->dcb.i2c[0].read = bios->data[legacy_i2c_offset + 5]; - bios->dcb.i2c[1].write = bios->data[legacy_i2c_offset + 6]; - bios->dcb.i2c[1].read = bios->data[legacy_i2c_offset + 7]; + if (bios->data[legacy_i2c_offset + 4]) + bios->dcb.i2c[0].write = bios->data[legacy_i2c_offset + 4]; + if (bios->data[legacy_i2c_offset + 5]) + bios->dcb.i2c[0].read = bios->data[legacy_i2c_offset + 5]; + if (bios->data[legacy_i2c_offset + 6]) + bios->dcb.i2c[1].write = bios->data[legacy_i2c_offset + 6]; + if (bios->data[legacy_i2c_offset + 7]) + bios->dcb.i2c[1].read = bios->data[legacy_i2c_offset + 7]; if (bmplength > 74) { bios->fmaxvco = ROM32(bmp[67]); @@ -5589,9 +5935,12 @@ parse_dcb20_entry(struct drm_device *dev, struct dcb_table *dcb, if (conf & 0x4 || conf & 0x8) entry->lvdsconf.use_power_scripts = true; } else { - mask = ~0x5; + mask = ~0x7; + if (conf & 0x2) + entry->lvdsconf.use_acpi_for_edid = true; if (conf & 0x4) entry->lvdsconf.use_power_scripts = true; + entry->lvdsconf.sor.link = (conf & 0x00000030) >> 4; } if (conf & mask) { /* @@ -5706,13 +6055,6 @@ parse_dcb15_entry(struct drm_device *dev, struct dcb_table *dcb, case OUTPUT_TV: entry->tvconf.has_component_output = false; break; - case OUTPUT_TMDS: - /* - * Invent a DVI-A output, by copying the fields of the DVI-D - * output; reported to work by math_b on an NV20(!). - */ - fabricate_vga_output(dcb, entry->i2c_index, entry->heads); - break; case OUTPUT_LVDS: if ((conn & 0x00003f00) != 0x10) entry->lvdsconf.use_straps_for_mode = true; @@ -5793,6 +6135,31 @@ void merge_like_dcb_entries(struct drm_device *dev, struct dcb_table *dcb) dcb->entries = newentries; } +static bool +apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf) +{ + /* Dell Precision M6300 + * DCB entry 2: 02025312 00000010 + * DCB entry 3: 02026312 00000020 + * + * Identical, except apparently a different connector on a + * different SOR link. Not a clue how we're supposed to know + * which one is in use if it even shares an i2c line... + * + * Ignore the connector on the second SOR link to prevent + * nasty problems until this is sorted (assuming it's not a + * VBIOS bug). + */ + if ((dev->pdev->device == 0x040d) && + (dev->pdev->subsystem_vendor == 0x1028) && + (dev->pdev->subsystem_device == 0x019b)) { + if (*conn == 0x02026312 && *conf == 0x00000020) + return false; + } + + return true; +} + static int parse_dcb_table(struct drm_device *dev, struct nvbios *bios, bool twoHeads) { @@ -5926,6 +6293,9 @@ parse_dcb_table(struct drm_device *dev, struct nvbios *bios, bool twoHeads) if ((connection & 0x0000000f) == 0x0000000f) continue; + if (!apply_dcb_encoder_quirks(dev, i, &connection, &config)) + continue; + NV_TRACEWARN(dev, "Raw DCB entry %d: %08x %08x\n", dcb->entries, connection, config); @@ -6181,9 +6551,8 @@ nouveau_run_vbios_init(struct drm_device *dev) struct nvbios *bios = &dev_priv->vbios; int i, ret = 0; - NVLockVgaCrtcs(dev, false); - if (nv_two_heads(dev)) - NVSetOwner(dev, bios->state.crtchead); + /* Reset the BIOS head to 0. */ + bios->state.crtchead = 0; if (bios->major_version < 5) /* BMP only */ load_nv17_hw_sequencer_ucode(dev, bios); @@ -6216,8 +6585,6 @@ nouveau_run_vbios_init(struct drm_device *dev) } } - NVLockVgaCrtcs(dev, true); - return ret; } @@ -6238,7 +6605,6 @@ static bool nouveau_bios_posted(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; - bool was_locked; unsigned htotal; if (dev_priv->chipset >= NV_50) { @@ -6248,13 +6614,12 @@ nouveau_bios_posted(struct drm_device *dev) return true; } - was_locked = NVLockVgaCrtcs(dev, false); htotal = NVReadVgaCrtc(dev, 0, 0x06); htotal |= (NVReadVgaCrtc(dev, 0, 0x07) & 0x01) << 8; htotal |= (NVReadVgaCrtc(dev, 0, 0x07) & 0x20) << 4; htotal |= (NVReadVgaCrtc(dev, 0, 0x25) & 0x01) << 10; htotal |= (NVReadVgaCrtc(dev, 0, 0x41) & 0x01) << 11; - NVLockVgaCrtcs(dev, was_locked); + return (htotal != 0); } @@ -6263,8 +6628,6 @@ nouveau_bios_init(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; struct nvbios *bios = &dev_priv->vbios; - uint32_t saved_nv_pextdev_boot_0; - bool was_locked; int ret; if (!NVInitVBIOS(dev)) @@ -6284,40 +6647,27 @@ nouveau_bios_init(struct drm_device *dev) if (!bios->major_version) /* we don't run version 0 bios */ return 0; - /* these will need remembering across a suspend */ - saved_nv_pextdev_boot_0 = bios_rd32(bios, NV_PEXTDEV_BOOT_0); - bios->state.saved_nv_pfb_cfg0 = bios_rd32(bios, NV_PFB_CFG0); - /* init script execution disabled */ bios->execute = false; /* ... unless card isn't POSTed already */ if (!nouveau_bios_posted(dev)) { - NV_INFO(dev, "Adaptor not initialised\n"); - if (dev_priv->card_type < NV_40) { - NV_ERROR(dev, "Unable to POST this chipset\n"); - return -ENODEV; - } - - NV_INFO(dev, "Running VBIOS init tables\n"); + NV_INFO(dev, "Adaptor not initialised, " + "running VBIOS init tables.\n"); bios->execute = true; } - bios_wr32(bios, NV_PEXTDEV_BOOT_0, saved_nv_pextdev_boot_0); - ret = nouveau_run_vbios_init(dev); if (ret) return ret; /* feature_byte on BMP is poor, but init always sets CR4B */ - was_locked = NVLockVgaCrtcs(dev, false); if (bios->major_version < 5) bios->is_mobile = NVReadVgaCrtc(dev, 0, NV_CIO_CRE_4B) & 0x40; /* all BIT systems need p_f_m_t for digital_min_front_porch */ if (bios->is_mobile || bios->major_version >= 5) ret = parse_fp_mode_table(dev, bios); - NVLockVgaCrtcs(dev, was_locked); /* allow subsequent scripts to execute */ bios->execute = true; diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.h b/drivers/gpu/drm/nouveau/nouveau_bios.h index adf4ec2d06c..024458a8d06 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.h +++ b/drivers/gpu/drm/nouveau/nouveau_bios.h @@ -81,6 +81,7 @@ struct dcb_connector_table_entry { enum dcb_connector_type type; uint8_t index2; uint8_t gpio_tag; + void *drm; }; struct dcb_connector_table { @@ -117,6 +118,7 @@ struct dcb_entry { struct { struct sor_conf sor; bool use_straps_for_mode; + bool use_acpi_for_edid; bool use_power_scripts; } lvdsconf; struct { @@ -249,8 +251,6 @@ struct nvbios { struct { int crtchead; - /* these need remembering across suspend */ - uint32_t saved_nv_pfb_cfg0; } state; struct { diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 6f3c1952237..3ca8343c15d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -461,9 +461,9 @@ nouveau_bo_move_accel_cleanup(struct nouveau_channel *chan, return ret; ret = ttm_bo_move_accel_cleanup(&nvbo->bo, fence, NULL, - evict, no_wait_reserve, no_wait_gpu, new_mem); - if (nvbo->channel && nvbo->channel != chan) - ret = nouveau_fence_wait(fence, NULL, false, false); + evict || (nvbo->channel && + nvbo->channel != chan), + no_wait_reserve, no_wait_gpu, new_mem); nouveau_fence_unref((void *)&fence); return ret; } @@ -711,8 +711,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, bool intr, return ret; /* Software copy if the card isn't up and running yet. */ - if (dev_priv->init_state != NOUVEAU_CARD_INIT_DONE || - !dev_priv->channel) { + if (!dev_priv->channel) { ret = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem); goto out; } @@ -783,7 +782,7 @@ nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) break; case TTM_PL_VRAM: mem->bus.offset = mem->mm_node->start << PAGE_SHIFT; - mem->bus.base = drm_get_resource_start(dev, 1); + mem->bus.base = pci_resource_start(dev->pdev, 1); mem->bus.is_iomem = true; break; default: diff --git a/drivers/gpu/drm/nouveau/nouveau_calc.c b/drivers/gpu/drm/nouveau/nouveau_calc.c index 88f9bc0941e..ca85da78484 100644 --- a/drivers/gpu/drm/nouveau/nouveau_calc.c +++ b/drivers/gpu/drm/nouveau/nouveau_calc.c @@ -200,7 +200,7 @@ nv04_update_arb(struct drm_device *dev, int VClk, int bpp, struct nv_sim_state sim_data; int MClk = nouveau_hw_get_clock(dev, MPLL); int NVClk = nouveau_hw_get_clock(dev, NVPLL); - uint32_t cfg1 = nvReadFB(dev, NV_PFB_CFG1); + uint32_t cfg1 = nvReadFB(dev, NV04_PFB_CFG1); sim_data.pclk_khz = VClk; sim_data.mclk_khz = MClk; @@ -218,7 +218,7 @@ nv04_update_arb(struct drm_device *dev, int VClk, int bpp, sim_data.mem_latency = 3; sim_data.mem_page_miss = 10; } else { - sim_data.memory_type = nvReadFB(dev, NV_PFB_CFG0) & 0x1; + sim_data.memory_type = nvReadFB(dev, NV04_PFB_CFG0) & 0x1; sim_data.memory_width = (nvReadEXTDEV(dev, NV_PEXTDEV_BOOT_0) & 0x10) ? 128 : 64; sim_data.mem_latency = cfg1 & 0xf; sim_data.mem_page_miss = ((cfg1 >> 4) & 0xf) + ((cfg1 >> 31) & 0x1); diff --git a/drivers/gpu/drm/nouveau/nouveau_channel.c b/drivers/gpu/drm/nouveau/nouveau_channel.c index 1fc57ef5829..90fdcda332b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_channel.c +++ b/drivers/gpu/drm/nouveau/nouveau_channel.c @@ -62,7 +62,8 @@ nouveau_channel_pushbuf_ctxdma_init(struct nouveau_channel *chan) * VRAM. */ ret = nouveau_gpuobj_dma_new(chan, NV_CLASS_DMA_IN_MEMORY, - drm_get_resource_start(dev, 1), + pci_resource_start(dev->pdev, + 1), dev_priv->fb_available_size, NV_DMA_ACCESS_RO, NV_DMA_TARGET_PCI, &pushbuf); @@ -257,9 +258,7 @@ nouveau_channel_free(struct nouveau_channel *chan) nouveau_debugfs_channel_fini(chan); /* Give outstanding push buffers a chance to complete */ - spin_lock_irqsave(&chan->fence.lock, flags); nouveau_fence_update(chan); - spin_unlock_irqrestore(&chan->fence.lock, flags); if (chan->fence.sequence != chan->fence.sequence_ack) { struct nouveau_fence *fence = NULL; @@ -368,8 +367,6 @@ nouveau_ioctl_fifo_alloc(struct drm_device *dev, void *data, struct nouveau_channel *chan; int ret; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; - if (dev_priv->engine.graph.accel_blocked) return -ENODEV; @@ -418,7 +415,6 @@ nouveau_ioctl_fifo_free(struct drm_device *dev, void *data, struct drm_nouveau_channel_free *cfree = data; struct nouveau_channel *chan; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; NOUVEAU_GET_USER_CHANNEL_WITH_RETURN(cfree->channel, file_priv, chan); nouveau_channel_free(chan); diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 149ed224c3c..734e92635e8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -102,63 +102,15 @@ nouveau_connector_destroy(struct drm_connector *drm_connector) kfree(drm_connector); } -static void -nouveau_connector_ddc_prepare(struct drm_connector *connector, int *flags) -{ - struct drm_nouveau_private *dev_priv = connector->dev->dev_private; - - if (dev_priv->card_type >= NV_50) - return; - - *flags = 0; - if (NVLockVgaCrtcs(dev_priv->dev, false)) - *flags |= 1; - if (nv_heads_tied(dev_priv->dev)) - *flags |= 2; - - if (*flags & 2) - NVSetOwner(dev_priv->dev, 0); /* necessary? */ -} - -static void -nouveau_connector_ddc_finish(struct drm_connector *connector, int flags) -{ - struct drm_nouveau_private *dev_priv = connector->dev->dev_private; - - if (dev_priv->card_type >= NV_50) - return; - - if (flags & 2) - NVSetOwner(dev_priv->dev, 4); - if (flags & 1) - NVLockVgaCrtcs(dev_priv->dev, true); -} - static struct nouveau_i2c_chan * nouveau_connector_ddc_detect(struct drm_connector *connector, struct nouveau_encoder **pnv_encoder) { struct drm_device *dev = connector->dev; - uint8_t out_buf[] = { 0x0, 0x0}, buf[2]; - int ret, flags, i; - - struct i2c_msg msgs[] = { - { - .addr = 0x50, - .flags = 0, - .len = 1, - .buf = out_buf, - }, - { - .addr = 0x50, - .flags = I2C_M_RD, - .len = 1, - .buf = buf, - } - }; + int i; for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) { - struct nouveau_i2c_chan *i2c = NULL; + struct nouveau_i2c_chan *i2c; struct nouveau_encoder *nv_encoder; struct drm_mode_object *obj; int id; @@ -171,17 +123,9 @@ nouveau_connector_ddc_detect(struct drm_connector *connector, if (!obj) continue; nv_encoder = nouveau_encoder(obj_to_encoder(obj)); + i2c = nouveau_i2c_find(dev, nv_encoder->dcb->i2c_index); - if (nv_encoder->dcb->i2c_index < 0xf) - i2c = nouveau_i2c_find(dev, nv_encoder->dcb->i2c_index); - if (!i2c) - continue; - - nouveau_connector_ddc_prepare(connector, &flags); - ret = i2c_transfer(&i2c->adapter, msgs, 2); - nouveau_connector_ddc_finish(connector, flags); - - if (ret == 2) { + if (i2c && nouveau_probe_i2c_addr(i2c, 0x50)) { *pnv_encoder = nv_encoder; return i2c; } @@ -234,21 +178,7 @@ nouveau_connector_detect(struct drm_connector *connector) struct nouveau_connector *nv_connector = nouveau_connector(connector); struct nouveau_encoder *nv_encoder = NULL; struct nouveau_i2c_chan *i2c; - int type, flags; - - if (nv_connector->dcb->type == DCB_CONNECTOR_LVDS) - nv_encoder = find_encoder_by_type(connector, OUTPUT_LVDS); - if (nv_encoder && nv_connector->native_mode) { - unsigned status = connector_status_connected; - -#if defined(CONFIG_ACPI_BUTTON) || \ - (defined(CONFIG_ACPI_BUTTON_MODULE) && defined(MODULE)) - if (!nouveau_ignorelid && !acpi_lid_open()) - status = connector_status_unknown; -#endif - nouveau_connector_set_encoder(connector, nv_encoder); - return status; - } + int type; /* Cleanup the previous EDID block. */ if (nv_connector->edid) { @@ -259,9 +189,7 @@ nouveau_connector_detect(struct drm_connector *connector) i2c = nouveau_connector_ddc_detect(connector, &nv_encoder); if (i2c) { - nouveau_connector_ddc_prepare(connector, &flags); nv_connector->edid = drm_get_edid(connector, &i2c->adapter); - nouveau_connector_ddc_finish(connector, flags); drm_mode_connector_update_edid_property(connector, nv_connector->edid); if (!nv_connector->edid) { @@ -321,6 +249,85 @@ detect_analog: return connector_status_disconnected; } +static enum drm_connector_status +nouveau_connector_detect_lvds(struct drm_connector *connector) +{ + struct drm_device *dev = connector->dev; + struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_connector *nv_connector = nouveau_connector(connector); + struct nouveau_encoder *nv_encoder = NULL; + enum drm_connector_status status = connector_status_disconnected; + + /* Cleanup the previous EDID block. */ + if (nv_connector->edid) { + drm_mode_connector_update_edid_property(connector, NULL); + kfree(nv_connector->edid); + nv_connector->edid = NULL; + } + + nv_encoder = find_encoder_by_type(connector, OUTPUT_LVDS); + if (!nv_encoder) + return connector_status_disconnected; + + /* Try retrieving EDID via DDC */ + if (!dev_priv->vbios.fp_no_ddc) { + status = nouveau_connector_detect(connector); + if (status == connector_status_connected) + goto out; + } + + /* On some laptops (Sony, i'm looking at you) there appears to + * be no direct way of accessing the panel's EDID. The only + * option available to us appears to be to ask ACPI for help.. + * + * It's important this check's before trying straps, one of the + * said manufacturer's laptops are configured in such a way + * the nouveau decides an entry in the VBIOS FP mode table is + * valid - it's not (rh#613284) + */ + if (nv_encoder->dcb->lvdsconf.use_acpi_for_edid) { + if (!nouveau_acpi_edid(dev, connector)) { + status = connector_status_connected; + goto out; + } + } + + /* If no EDID found above, and the VBIOS indicates a hardcoded + * modeline is avalilable for the panel, set it as the panel's + * native mode and exit. + */ + if (nouveau_bios_fp_mode(dev, NULL) && (dev_priv->vbios.fp_no_ddc || + nv_encoder->dcb->lvdsconf.use_straps_for_mode)) { + status = connector_status_connected; + goto out; + } + + /* Still nothing, some VBIOS images have a hardcoded EDID block + * stored for the panel stored in them. + */ + if (!dev_priv->vbios.fp_no_ddc) { + struct edid *edid = + (struct edid *)nouveau_bios_embedded_edid(dev); + if (edid) { + nv_connector->edid = kmalloc(EDID_LENGTH, GFP_KERNEL); + *(nv_connector->edid) = *edid; + status = connector_status_connected; + } + } + +out: +#if defined(CONFIG_ACPI_BUTTON) || \ + (defined(CONFIG_ACPI_BUTTON_MODULE) && defined(MODULE)) + if (status == connector_status_connected && + !nouveau_ignorelid && !acpi_lid_open()) + status = connector_status_unknown; +#endif + + drm_mode_connector_update_edid_property(connector, nv_connector->edid); + nouveau_connector_set_encoder(connector, nv_encoder); + return status; +} + static void nouveau_connector_force(struct drm_connector *connector) { @@ -441,7 +448,8 @@ nouveau_connector_native_mode(struct drm_connector *connector) int high_w = 0, high_h = 0, high_v = 0; list_for_each_entry(mode, &nv_connector->base.probed_modes, head) { - if (helper->mode_valid(connector, mode) != MODE_OK) + if (helper->mode_valid(connector, mode) != MODE_OK || + (mode->flags & DRM_MODE_FLAG_INTERLACE)) continue; /* Use preferred mode if there is one.. */ @@ -534,21 +542,27 @@ static int nouveau_connector_get_modes(struct drm_connector *connector) { struct drm_device *dev = connector->dev; + struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_connector *nv_connector = nouveau_connector(connector); struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder; int ret = 0; - /* If we're not LVDS, destroy the previous native mode, the attached - * monitor could have changed. + /* destroy the native mode, the attached monitor could have changed. */ - if (nv_connector->dcb->type != DCB_CONNECTOR_LVDS && - nv_connector->native_mode) { + if (nv_connector->native_mode) { drm_mode_destroy(dev, nv_connector->native_mode); nv_connector->native_mode = NULL; } if (nv_connector->edid) ret = drm_add_edid_modes(connector, nv_connector->edid); + else + if (nv_encoder->dcb->type == OUTPUT_LVDS && + (nv_encoder->dcb->lvdsconf.use_straps_for_mode || + dev_priv->vbios.fp_no_ddc) && nouveau_bios_fp_mode(dev, NULL)) { + nv_connector->native_mode = drm_mode_create(dev); + nouveau_bios_fp_mode(dev, nv_connector->native_mode); + } /* Find the native mode if this is a digital panel, if we didn't * find any modes through DDC previously add the native mode to @@ -569,7 +583,8 @@ nouveau_connector_get_modes(struct drm_connector *connector) ret = get_slave_funcs(nv_encoder)-> get_modes(to_drm_encoder(nv_encoder), connector); - if (nv_encoder->dcb->type == OUTPUT_LVDS) + if (nv_connector->dcb->type == DCB_CONNECTOR_LVDS || + nv_connector->dcb->type == DCB_CONNECTOR_eDP) ret += nouveau_connector_scaler_modes_add(connector); return ret; @@ -643,6 +658,44 @@ nouveau_connector_best_encoder(struct drm_connector *connector) return NULL; } +void +nouveau_connector_set_polling(struct drm_connector *connector) +{ + struct drm_device *dev = connector->dev; + struct drm_nouveau_private *dev_priv = dev->dev_private; + struct drm_crtc *crtc; + bool spare_crtc = false; + + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + spare_crtc |= !crtc->enabled; + + connector->polled = 0; + + switch (connector->connector_type) { + case DRM_MODE_CONNECTOR_VGA: + case DRM_MODE_CONNECTOR_TV: + if (dev_priv->card_type >= NV_50 || + (nv_gf4_disp_arch(dev) && spare_crtc)) + connector->polled = DRM_CONNECTOR_POLL_CONNECT; + break; + + case DRM_MODE_CONNECTOR_DVII: + case DRM_MODE_CONNECTOR_DVID: + case DRM_MODE_CONNECTOR_HDMIA: + case DRM_MODE_CONNECTOR_DisplayPort: + case DRM_MODE_CONNECTOR_eDP: + if (dev_priv->card_type >= NV_50) + connector->polled = DRM_CONNECTOR_POLL_HPD; + else if (connector->connector_type == DRM_MODE_CONNECTOR_DVID || + spare_crtc) + connector->polled = DRM_CONNECTOR_POLL_CONNECT; + break; + + default: + break; + } +} + static const struct drm_connector_helper_funcs nouveau_connector_helper_funcs = { .get_modes = nouveau_connector_get_modes, @@ -662,148 +715,74 @@ nouveau_connector_funcs = { .force = nouveau_connector_force }; -static int -nouveau_connector_create_lvds(struct drm_device *dev, - struct drm_connector *connector) -{ - struct nouveau_connector *nv_connector = nouveau_connector(connector); - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_i2c_chan *i2c = NULL; - struct nouveau_encoder *nv_encoder; - struct drm_display_mode native, *mode, *temp; - bool dummy, if_is_24bit = false; - int ret, flags; - - nv_encoder = find_encoder_by_type(connector, OUTPUT_LVDS); - if (!nv_encoder) - return -ENODEV; - - ret = nouveau_bios_parse_lvds_table(dev, 0, &dummy, &if_is_24bit); - if (ret) { - NV_ERROR(dev, "Error parsing LVDS table, disabling LVDS\n"); - return ret; - } - nv_connector->use_dithering = !if_is_24bit; - - /* Firstly try getting EDID over DDC, if allowed and I2C channel - * is available. - */ - if (!dev_priv->vbios.fp_no_ddc && nv_encoder->dcb->i2c_index < 0xf) - i2c = nouveau_i2c_find(dev, nv_encoder->dcb->i2c_index); - - if (i2c) { - nouveau_connector_ddc_prepare(connector, &flags); - nv_connector->edid = drm_get_edid(connector, &i2c->adapter); - nouveau_connector_ddc_finish(connector, flags); - } - - /* If no EDID found above, and the VBIOS indicates a hardcoded - * modeline is avalilable for the panel, set it as the panel's - * native mode and exit. - */ - if (!nv_connector->edid && nouveau_bios_fp_mode(dev, &native) && - (nv_encoder->dcb->lvdsconf.use_straps_for_mode || - dev_priv->vbios.fp_no_ddc)) { - nv_connector->native_mode = drm_mode_duplicate(dev, &native); - goto out; - } - - /* Still nothing, some VBIOS images have a hardcoded EDID block - * stored for the panel stored in them. - */ - if (!nv_connector->edid && !nv_connector->native_mode && - !dev_priv->vbios.fp_no_ddc) { - struct edid *edid = - (struct edid *)nouveau_bios_embedded_edid(dev); - if (edid) { - nv_connector->edid = kmalloc(EDID_LENGTH, GFP_KERNEL); - *(nv_connector->edid) = *edid; - } - } - - if (!nv_connector->edid) - goto out; - - /* We didn't find/use a panel mode from the VBIOS, so parse the EDID - * block and look for the preferred mode there. - */ - ret = drm_add_edid_modes(connector, nv_connector->edid); - if (ret == 0) - goto out; - nv_connector->detected_encoder = nv_encoder; - nv_connector->native_mode = nouveau_connector_native_mode(connector); - list_for_each_entry_safe(mode, temp, &connector->probed_modes, head) - drm_mode_remove(connector, mode); - -out: - if (!nv_connector->native_mode) { - NV_ERROR(dev, "LVDS present in DCB table, but couldn't " - "determine its native mode. Disabling.\n"); - return -ENODEV; - } - - drm_mode_connector_update_edid_property(connector, nv_connector->edid); - return 0; -} +static const struct drm_connector_funcs +nouveau_connector_funcs_lvds = { + .dpms = drm_helper_connector_dpms, + .save = NULL, + .restore = NULL, + .detect = nouveau_connector_detect_lvds, + .destroy = nouveau_connector_destroy, + .fill_modes = drm_helper_probe_single_connector_modes, + .set_property = nouveau_connector_set_property, + .force = nouveau_connector_force +}; -int -nouveau_connector_create(struct drm_device *dev, - struct dcb_connector_table_entry *dcb) +struct drm_connector * +nouveau_connector_create(struct drm_device *dev, int index) { + const struct drm_connector_funcs *funcs = &nouveau_connector_funcs; struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_connector *nv_connector = NULL; + struct dcb_connector_table_entry *dcb = NULL; struct drm_connector *connector; - struct drm_encoder *encoder; - int ret, type; + int type, ret = 0; NV_DEBUG_KMS(dev, "\n"); + if (index >= dev_priv->vbios.dcb.connector.entries) + return ERR_PTR(-EINVAL); + + dcb = &dev_priv->vbios.dcb.connector.entry[index]; + if (dcb->drm) + return dcb->drm; + switch (dcb->type) { - case DCB_CONNECTOR_NONE: - return 0; case DCB_CONNECTOR_VGA: - NV_INFO(dev, "Detected a VGA connector\n"); type = DRM_MODE_CONNECTOR_VGA; break; case DCB_CONNECTOR_TV_0: case DCB_CONNECTOR_TV_1: case DCB_CONNECTOR_TV_3: - NV_INFO(dev, "Detected a TV connector\n"); type = DRM_MODE_CONNECTOR_TV; break; case DCB_CONNECTOR_DVI_I: - NV_INFO(dev, "Detected a DVI-I connector\n"); type = DRM_MODE_CONNECTOR_DVII; break; case DCB_CONNECTOR_DVI_D: - NV_INFO(dev, "Detected a DVI-D connector\n"); type = DRM_MODE_CONNECTOR_DVID; break; case DCB_CONNECTOR_HDMI_0: case DCB_CONNECTOR_HDMI_1: - NV_INFO(dev, "Detected a HDMI connector\n"); type = DRM_MODE_CONNECTOR_HDMIA; break; case DCB_CONNECTOR_LVDS: - NV_INFO(dev, "Detected a LVDS connector\n"); type = DRM_MODE_CONNECTOR_LVDS; + funcs = &nouveau_connector_funcs_lvds; break; case DCB_CONNECTOR_DP: - NV_INFO(dev, "Detected a DisplayPort connector\n"); type = DRM_MODE_CONNECTOR_DisplayPort; break; case DCB_CONNECTOR_eDP: - NV_INFO(dev, "Detected an eDP connector\n"); type = DRM_MODE_CONNECTOR_eDP; break; default: NV_ERROR(dev, "unknown connector type: 0x%02x!!\n", dcb->type); - return -EINVAL; + return ERR_PTR(-EINVAL); } nv_connector = kzalloc(sizeof(*nv_connector), GFP_KERNEL); if (!nv_connector) - return -ENOMEM; + return ERR_PTR(-ENOMEM); nv_connector->dcb = dcb; connector = &nv_connector->base; @@ -811,27 +790,21 @@ nouveau_connector_create(struct drm_device *dev, connector->interlace_allowed = false; connector->doublescan_allowed = false; - drm_connector_init(dev, connector, &nouveau_connector_funcs, type); + drm_connector_init(dev, connector, funcs, type); drm_connector_helper_add(connector, &nouveau_connector_helper_funcs); - /* attach encoders */ - list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - - if (nv_encoder->dcb->connector != dcb->index) - continue; - - if (get_slave_funcs(nv_encoder)) - get_slave_funcs(nv_encoder)->create_resources(encoder, connector); + /* Check if we need dithering enabled */ + if (dcb->type == DCB_CONNECTOR_LVDS) { + bool dummy, is_24bit = false; - drm_mode_connector_attach_encoder(connector, encoder); - } + ret = nouveau_bios_parse_lvds_table(dev, 0, &dummy, &is_24bit); + if (ret) { + NV_ERROR(dev, "Error parsing LVDS table, disabling " + "LVDS\n"); + goto fail; + } - if (!connector->encoder_ids[0]) { - NV_WARN(dev, " no encoders, ignoring\n"); - drm_connector_cleanup(connector); - kfree(connector); - return 0; + nv_connector->use_dithering = !is_24bit; } /* Init DVI-I specific properties */ @@ -841,12 +814,8 @@ nouveau_connector_create(struct drm_device *dev, drm_connector_attach_property(connector, dev->mode_config.dvi_i_select_subconnector_property, 0); } - if (dcb->type != DCB_CONNECTOR_LVDS) - nv_connector->use_dithering = false; - switch (dcb->type) { case DCB_CONNECTOR_VGA: - connector->polled = DRM_CONNECTOR_POLL_CONNECT; if (dev_priv->card_type >= NV_50) { drm_connector_attach_property(connector, dev->mode_config.scaling_mode_property, @@ -858,17 +827,6 @@ nouveau_connector_create(struct drm_device *dev, case DCB_CONNECTOR_TV_3: nv_connector->scaling_mode = DRM_MODE_SCALE_NONE; break; - case DCB_CONNECTOR_DP: - case DCB_CONNECTOR_eDP: - case DCB_CONNECTOR_HDMI_0: - case DCB_CONNECTOR_HDMI_1: - case DCB_CONNECTOR_DVI_I: - case DCB_CONNECTOR_DVI_D: - if (dev_priv->card_type >= NV_50) - connector->polled = DRM_CONNECTOR_POLL_HPD; - else - connector->polled = DRM_CONNECTOR_POLL_CONNECT; - /* fall-through */ default: nv_connector->scaling_mode = DRM_MODE_SCALE_FULLSCREEN; @@ -882,15 +840,15 @@ nouveau_connector_create(struct drm_device *dev, break; } + nouveau_connector_set_polling(connector); + drm_sysfs_connector_add(connector); + dcb->drm = connector; + return dcb->drm; - if (dcb->type == DCB_CONNECTOR_LVDS) { - ret = nouveau_connector_create_lvds(dev, connector); - if (ret) { - connector->funcs->destroy(connector); - return ret; - } - } +fail: + drm_connector_cleanup(connector); + kfree(connector); + return ERR_PTR(ret); - return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h index 4ef38abc2d9..0d2e668ccfe 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.h +++ b/drivers/gpu/drm/nouveau/nouveau_connector.h @@ -49,7 +49,10 @@ static inline struct nouveau_connector *nouveau_connector( return container_of(con, struct nouveau_connector, base); } -int nouveau_connector_create(struct drm_device *, - struct dcb_connector_table_entry *); +struct drm_connector * +nouveau_connector_create(struct drm_device *, int index); + +void +nouveau_connector_set_polling(struct drm_connector *); #endif /* __NOUVEAU_CONNECTOR_H__ */ diff --git a/drivers/gpu/drm/nouveau/nouveau_dma.c b/drivers/gpu/drm/nouveau/nouveau_dma.c index 65c441a1999..2e3c6caa97e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dma.c +++ b/drivers/gpu/drm/nouveau/nouveau_dma.c @@ -92,11 +92,9 @@ nouveau_dma_init(struct nouveau_channel *chan) return ret; /* Map M2MF notifier object - fbcon. */ - if (drm_core_check_feature(dev, DRIVER_MODESET)) { - ret = nouveau_bo_map(chan->notifier_bo); - if (ret) - return ret; - } + ret = nouveau_bo_map(chan->notifier_bo); + if (ret) + return ret; /* Insert NOPS for NOUVEAU_DMA_SKIPS */ ret = RING_SPACE(chan, NOUVEAU_DMA_SKIPS); diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index deeb21c6865..33742b11188 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -23,8 +23,10 @@ */ #include "drmP.h" + #include "nouveau_drv.h" #include "nouveau_i2c.h" +#include "nouveau_connector.h" #include "nouveau_encoder.h" static int @@ -270,13 +272,39 @@ bool nouveau_dp_link_train(struct drm_encoder *encoder) { struct drm_device *dev = encoder->dev; + struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_gpio_engine *pgpio = &dev_priv->engine.gpio; struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - uint8_t config[4]; - uint8_t status[3]; + struct nouveau_connector *nv_connector; + struct bit_displayport_encoder_table *dpe; + int dpe_headerlen; + uint8_t config[4], status[3]; bool cr_done, cr_max_vs, eq_done; int ret = 0, i, tries, voltage; NV_DEBUG_KMS(dev, "link training!!\n"); + + nv_connector = nouveau_encoder_connector_get(nv_encoder); + if (!nv_connector) + return false; + + dpe = nouveau_bios_dp_table(dev, nv_encoder->dcb, &dpe_headerlen); + if (!dpe) { + NV_ERROR(dev, "SOR-%d: no DP encoder table!\n", nv_encoder->or); + return false; + } + + /* disable hotplug detect, this flips around on some panels during + * link training. + */ + pgpio->irq_enable(dev, nv_connector->dcb->gpio_tag, false); + + if (dpe->script0) { + NV_DEBUG_KMS(dev, "SOR-%d: running DP script 0\n", nv_encoder->or); + nouveau_bios_run_init_table(dev, le16_to_cpu(dpe->script0), + nv_encoder->dcb); + } + train: cr_done = eq_done = false; @@ -403,6 +431,15 @@ stop: } } + if (dpe->script1) { + NV_DEBUG_KMS(dev, "SOR-%d: running DP script 1\n", nv_encoder->or); + nouveau_bios_run_init_table(dev, le16_to_cpu(dpe->script1), + nv_encoder->dcb); + } + + /* re-enable hotplug detect */ + pgpio->irq_enable(dev, nv_connector->dcb->gpio_tag, true); + return eq_done; } diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.c b/drivers/gpu/drm/nouveau/nouveau_drv.c index 27377043229..1de5eb53e01 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.c +++ b/drivers/gpu/drm/nouveau/nouveau_drv.c @@ -35,10 +35,6 @@ #include "drm_pciids.h" -MODULE_PARM_DESC(ctxfw, "Use external firmware blob for grctx init (NV40)"); -int nouveau_ctxfw = 0; -module_param_named(ctxfw, nouveau_ctxfw, int, 0400); - MODULE_PARM_DESC(noagp, "Disable AGP"); int nouveau_noagp; module_param_named(noagp, nouveau_noagp, int, 0400); @@ -56,7 +52,7 @@ int nouveau_vram_pushbuf; module_param_named(vram_pushbuf, nouveau_vram_pushbuf, int, 0400); MODULE_PARM_DESC(vram_notify, "Force DMA notifiers to be in VRAM"); -int nouveau_vram_notify = 1; +int nouveau_vram_notify = 0; module_param_named(vram_notify, nouveau_vram_notify, int, 0400); MODULE_PARM_DESC(duallink, "Allow dual-link TMDS (>=GeForce 8)"); @@ -132,7 +128,7 @@ static struct drm_driver driver; static int __devinit nouveau_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - return drm_get_dev(pdev, ent, &driver); + return drm_get_pci_dev(pdev, ent, &driver); } static void @@ -155,9 +151,6 @@ nouveau_pci_suspend(struct pci_dev *pdev, pm_message_t pm_state) struct drm_crtc *crtc; int ret, i; - if (!drm_core_check_feature(dev, DRIVER_MODESET)) - return -ENODEV; - if (pm_state.event == PM_EVENT_PRETHAW) return 0; @@ -257,9 +250,6 @@ nouveau_pci_resume(struct pci_dev *pdev) struct drm_crtc *crtc; int ret, i; - if (!drm_core_check_feature(dev, DRIVER_MODESET)) - return -ENODEV; - nouveau_fbcon_save_disable_accel(dev); NV_INFO(dev, "We're back, enabling device...\n"); @@ -269,6 +259,13 @@ nouveau_pci_resume(struct pci_dev *pdev) return -1; pci_set_master(dev->pdev); + /* Make sure the AGP controller is in a consistent state */ + if (dev_priv->gart_info.type == NOUVEAU_GART_AGP) + nouveau_mem_reset_agp(dev); + + /* Make the CRTCs accessible */ + engine->display.early_init(dev); + NV_INFO(dev, "POSTing device...\n"); ret = nouveau_run_vbios_init(dev); if (ret) @@ -323,7 +320,6 @@ nouveau_pci_resume(struct pci_dev *pdev) list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); - int ret; ret = nouveau_bo_pin(nv_crtc->cursor.nvbo, TTM_PL_FLAG_VRAM); if (!ret) @@ -332,11 +328,7 @@ nouveau_pci_resume(struct pci_dev *pdev) NV_ERROR(dev, "Could not pin/map cursor.\n"); } - if (dev_priv->card_type < NV_50) { - nv04_display_restore(dev); - NVLockVgaCrtcs(dev, false); - } else - nv50_display_init(dev); + engine->display.init(dev); list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); @@ -371,7 +363,8 @@ nouveau_pci_resume(struct pci_dev *pdev) static struct drm_driver driver = { .driver_features = DRIVER_USE_AGP | DRIVER_PCI_DMA | DRIVER_SG | - DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM, + DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | + DRIVER_MODESET, .load = nouveau_load, .firstopen = nouveau_firstopen, .lastclose = nouveau_lastclose, @@ -438,16 +431,18 @@ static int __init nouveau_init(void) nouveau_modeset = 1; } - if (nouveau_modeset == 1) { - driver.driver_features |= DRIVER_MODESET; - nouveau_register_dsm_handler(); - } + if (!nouveau_modeset) + return 0; + nouveau_register_dsm_handler(); return drm_init(&driver); } static void __exit nouveau_exit(void) { + if (!nouveau_modeset) + return; + drm_exit(&driver); nouveau_unregister_dsm_handler(); } diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index c6971910648..e15db15dca7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -123,14 +123,6 @@ nvbo_kmap_obj_iovirtual(struct nouveau_bo *nvbo) return ioptr; } -struct mem_block { - struct mem_block *next; - struct mem_block *prev; - uint64_t start; - uint64_t size; - struct drm_file *file_priv; /* NULL: free, -1: heap, other: real files */ -}; - enum nouveau_flags { NV_NFORCE = 0x10000000, NV_NFORCE2 = 0x20000000 @@ -149,7 +141,7 @@ struct nouveau_gpuobj { struct list_head list; struct nouveau_channel *im_channel; - struct mem_block *im_pramin; + struct drm_mm_node *im_pramin; struct nouveau_bo *im_backing; uint32_t im_backing_start; uint32_t *im_backing_suspend; @@ -196,7 +188,7 @@ struct nouveau_channel { struct list_head pending; uint32_t sequence; uint32_t sequence_ack; - uint32_t last_sequence_irq; + atomic_t last_sequence_irq; } fence; /* DMA push buffer */ @@ -206,7 +198,7 @@ struct nouveau_channel { /* Notifier memory */ struct nouveau_bo *notifier_bo; - struct mem_block *notifier_heap; + struct drm_mm notifier_heap; /* PFIFO context */ struct nouveau_gpuobj_ref *ramfc; @@ -224,7 +216,7 @@ struct nouveau_channel { /* Objects */ struct nouveau_gpuobj_ref *ramin; /* Private instmem */ - struct mem_block *ramin_heap; /* Private PRAMIN heap */ + struct drm_mm ramin_heap; /* Private PRAMIN heap */ struct nouveau_gpuobj_ref *ramht; /* Hash table */ struct list_head ramht_refs; /* Objects referenced by RAMHT */ @@ -277,8 +269,7 @@ struct nouveau_instmem_engine { void (*clear)(struct drm_device *, struct nouveau_gpuobj *); int (*bind)(struct drm_device *, struct nouveau_gpuobj *); int (*unbind)(struct drm_device *, struct nouveau_gpuobj *); - void (*prepare_access)(struct drm_device *, bool write); - void (*finish_access)(struct drm_device *); + void (*flush)(struct drm_device *); }; struct nouveau_mc_engine { @@ -303,10 +294,11 @@ struct nouveau_fb_engine { }; struct nouveau_fifo_engine { - void *priv; - int channels; + struct nouveau_gpuobj_ref *playlist[2]; + int cur_playlist; + int (*init)(struct drm_device *); void (*takedown)(struct drm_device *); @@ -339,10 +331,11 @@ struct nouveau_pgraph_object_class { struct nouveau_pgraph_engine { struct nouveau_pgraph_object_class *grclass; bool accel_blocked; - void *ctxprog; - void *ctxvals; int grctx_size; + /* NV2x/NV3x context table (0x400780) */ + struct nouveau_gpuobj_ref *ctx_table; + int (*init)(struct drm_device *); void (*takedown)(struct drm_device *); @@ -358,6 +351,24 @@ struct nouveau_pgraph_engine { uint32_t size, uint32_t pitch); }; +struct nouveau_display_engine { + int (*early_init)(struct drm_device *); + void (*late_takedown)(struct drm_device *); + int (*create)(struct drm_device *); + int (*init)(struct drm_device *); + void (*destroy)(struct drm_device *); +}; + +struct nouveau_gpio_engine { + int (*init)(struct drm_device *); + void (*takedown)(struct drm_device *); + + int (*get)(struct drm_device *, enum dcb_gpio_tag); + int (*set)(struct drm_device *, enum dcb_gpio_tag, int state); + + void (*irq_enable)(struct drm_device *, enum dcb_gpio_tag, bool on); +}; + struct nouveau_engine { struct nouveau_instmem_engine instmem; struct nouveau_mc_engine mc; @@ -365,6 +376,8 @@ struct nouveau_engine { struct nouveau_fb_engine fb; struct nouveau_pgraph_engine graph; struct nouveau_fifo_engine fifo; + struct nouveau_display_engine display; + struct nouveau_gpio_engine gpio; }; struct nouveau_pll_vals { @@ -500,11 +513,6 @@ enum nouveau_card_type { struct drm_nouveau_private { struct drm_device *dev; - enum { - NOUVEAU_CARD_INIT_DOWN, - NOUVEAU_CARD_INIT_DONE, - NOUVEAU_CARD_INIT_FAILED - } init_state; /* the card type, takes NV_* as values */ enum nouveau_card_type card_type; @@ -525,7 +533,7 @@ struct drm_nouveau_private { struct list_head vbl_waiting; struct { - struct ttm_global_reference mem_global_ref; + struct drm_global_reference mem_global_ref; struct ttm_bo_global_ref bo_global_ref; struct ttm_bo_device bdev; spinlock_t bo_list_lock; @@ -533,8 +541,6 @@ struct drm_nouveau_private { atomic_t validate_sequence; } ttm; - struct fb_info *fbdev_info; - int fifo_alloc_count; struct nouveau_channel *fifos[NOUVEAU_MAX_CHANNEL_NR]; @@ -595,11 +601,7 @@ struct drm_nouveau_private { struct nouveau_gpuobj *vm_vram_pt[NV50_VM_VRAM_NR]; int vm_vram_pt_nr; - struct mem_block *ramin_heap; - - /* context table pointed to be NV_PGRAPH_CHANNEL_CTX_TABLE (0x400780) */ - uint32_t ctx_table_size; - struct nouveau_gpuobj_ref *ctx_table; + struct drm_mm ramin_heap; struct list_head gpuobj_list; @@ -618,6 +620,11 @@ struct drm_nouveau_private { struct backlight_device *backlight; struct nouveau_channel *evo; + struct { + struct dcb_entry *dcb; + u16 script; + u32 pclk; + } evo_irq; struct { struct dentry *channel_root; @@ -652,14 +659,6 @@ nouveau_bo_ref(struct nouveau_bo *ref, struct nouveau_bo **pnvbo) return 0; } -#define NOUVEAU_CHECK_INITIALISED_WITH_RETURN do { \ - struct drm_nouveau_private *nv = dev->dev_private; \ - if (nv->init_state != NOUVEAU_CARD_INIT_DONE) { \ - NV_ERROR(dev, "called without init\n"); \ - return -EINVAL; \ - } \ -} while (0) - #define NOUVEAU_GET_USER_CHANNEL_WITH_RETURN(id, cl, ch) do { \ struct drm_nouveau_private *nv = dev->dev_private; \ if (!nouveau_channel_owner(dev, (cl), (id))) { \ @@ -682,7 +681,6 @@ extern int nouveau_tv_disable; extern char *nouveau_tv_norm; extern int nouveau_reg_debug; extern char *nouveau_vbios; -extern int nouveau_ctxfw; extern int nouveau_ignorelid; extern int nouveau_nofbaccel; extern int nouveau_noaccel; @@ -707,17 +705,10 @@ extern bool nouveau_wait_for_idle(struct drm_device *); extern int nouveau_card_init(struct drm_device *); /* nouveau_mem.c */ -extern int nouveau_mem_init_heap(struct mem_block **, uint64_t start, - uint64_t size); -extern struct mem_block *nouveau_mem_alloc_block(struct mem_block *, - uint64_t size, int align2, - struct drm_file *, int tail); -extern void nouveau_mem_takedown(struct mem_block **heap); -extern void nouveau_mem_free_block(struct mem_block *); extern int nouveau_mem_detect(struct drm_device *dev); -extern void nouveau_mem_release(struct drm_file *, struct mem_block *heap); extern int nouveau_mem_init(struct drm_device *); extern int nouveau_mem_init_agp(struct drm_device *); +extern int nouveau_mem_reset_agp(struct drm_device *); extern void nouveau_mem_close(struct drm_device *); extern struct nouveau_tile_reg *nv10_mem_set_tiling(struct drm_device *dev, uint32_t addr, @@ -857,11 +848,13 @@ void nouveau_register_dsm_handler(void); void nouveau_unregister_dsm_handler(void); int nouveau_acpi_get_bios_chunk(uint8_t *bios, int offset, int len); bool nouveau_acpi_rom_supported(struct pci_dev *pdev); +int nouveau_acpi_edid(struct drm_device *, struct drm_connector *); #else static inline void nouveau_register_dsm_handler(void) {} static inline void nouveau_unregister_dsm_handler(void) {} static inline bool nouveau_acpi_rom_supported(struct pci_dev *pdev) { return false; } static inline int nouveau_acpi_get_bios_chunk(uint8_t *bios, int offset, int len) { return -EINVAL; } +static inline int nouveau_acpi_edid(struct drm_device *dev, struct drm_connector *connector) { return -EINVAL; } #endif /* nouveau_backlight.c */ @@ -924,6 +917,10 @@ extern void nv10_fb_takedown(struct drm_device *); extern void nv10_fb_set_region_tiling(struct drm_device *, int, uint32_t, uint32_t, uint32_t); +/* nv30_fb.c */ +extern int nv30_fb_init(struct drm_device *); +extern void nv30_fb_takedown(struct drm_device *); + /* nv40_fb.c */ extern int nv40_fb_init(struct drm_device *); extern void nv40_fb_takedown(struct drm_device *); @@ -1035,12 +1032,6 @@ extern int nv50_graph_unload_context(struct drm_device *); extern void nv50_graph_context_switch(struct drm_device *); extern int nv50_grctx_init(struct nouveau_grctx *); -/* nouveau_grctx.c */ -extern int nouveau_grctx_prog_load(struct drm_device *); -extern void nouveau_grctx_vals_load(struct drm_device *, - struct nouveau_gpuobj *); -extern void nouveau_grctx_fini(struct drm_device *); - /* nv04_instmem.c */ extern int nv04_instmem_init(struct drm_device *); extern void nv04_instmem_takedown(struct drm_device *); @@ -1051,8 +1042,7 @@ extern int nv04_instmem_populate(struct drm_device *, struct nouveau_gpuobj *, extern void nv04_instmem_clear(struct drm_device *, struct nouveau_gpuobj *); extern int nv04_instmem_bind(struct drm_device *, struct nouveau_gpuobj *); extern int nv04_instmem_unbind(struct drm_device *, struct nouveau_gpuobj *); -extern void nv04_instmem_prepare_access(struct drm_device *, bool write); -extern void nv04_instmem_finish_access(struct drm_device *); +extern void nv04_instmem_flush(struct drm_device *); /* nv50_instmem.c */ extern int nv50_instmem_init(struct drm_device *); @@ -1064,8 +1054,9 @@ extern int nv50_instmem_populate(struct drm_device *, struct nouveau_gpuobj *, extern void nv50_instmem_clear(struct drm_device *, struct nouveau_gpuobj *); extern int nv50_instmem_bind(struct drm_device *, struct nouveau_gpuobj *); extern int nv50_instmem_unbind(struct drm_device *, struct nouveau_gpuobj *); -extern void nv50_instmem_prepare_access(struct drm_device *, bool write); -extern void nv50_instmem_finish_access(struct drm_device *); +extern void nv50_instmem_flush(struct drm_device *); +extern void nv84_instmem_flush(struct drm_device *); +extern void nv50_vm_flush(struct drm_device *, int engine); /* nv04_mc.c */ extern int nv04_mc_init(struct drm_device *); @@ -1088,13 +1079,14 @@ extern long nouveau_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); /* nv04_dac.c */ -extern int nv04_dac_create(struct drm_device *dev, struct dcb_entry *entry); +extern int nv04_dac_create(struct drm_connector *, struct dcb_entry *); extern uint32_t nv17_dac_sample_load(struct drm_encoder *encoder); extern int nv04_dac_output_offset(struct drm_encoder *encoder); extern void nv04_dac_update_dacclk(struct drm_encoder *encoder, bool enable); +extern bool nv04_dac_in_use(struct drm_encoder *encoder); /* nv04_dfp.c */ -extern int nv04_dfp_create(struct drm_device *dev, struct dcb_entry *entry); +extern int nv04_dfp_create(struct drm_connector *, struct dcb_entry *); extern int nv04_dfp_get_bound_head(struct drm_device *dev, struct dcb_entry *dcbent); extern void nv04_dfp_bind_head(struct drm_device *dev, struct dcb_entry *dcbent, int head, bool dl); @@ -1103,15 +1095,17 @@ extern void nv04_dfp_update_fp_control(struct drm_encoder *encoder, int mode); /* nv04_tv.c */ extern int nv04_tv_identify(struct drm_device *dev, int i2c_index); -extern int nv04_tv_create(struct drm_device *dev, struct dcb_entry *entry); +extern int nv04_tv_create(struct drm_connector *, struct dcb_entry *); /* nv17_tv.c */ -extern int nv17_tv_create(struct drm_device *dev, struct dcb_entry *entry); +extern int nv17_tv_create(struct drm_connector *, struct dcb_entry *); /* nv04_display.c */ +extern int nv04_display_early_init(struct drm_device *); +extern void nv04_display_late_takedown(struct drm_device *); extern int nv04_display_create(struct drm_device *); +extern int nv04_display_init(struct drm_device *); extern void nv04_display_destroy(struct drm_device *); -extern void nv04_display_restore(struct drm_device *); /* nv04_crtc.c */ extern int nv04_crtc_create(struct drm_device *, int index); @@ -1147,7 +1141,6 @@ extern int nouveau_fence_wait(void *obj, void *arg, bool lazy, bool intr); extern int nouveau_fence_flush(void *obj, void *arg); extern void nouveau_fence_unref(void **obj); extern void *nouveau_fence_ref(void *obj); -extern void nouveau_fence_handler(struct drm_device *dev, int channel); /* nouveau_gem.c */ extern int nouveau_gem_new(struct drm_device *, struct nouveau_channel *, @@ -1167,13 +1160,15 @@ extern int nouveau_gem_ioctl_cpu_fini(struct drm_device *, void *, extern int nouveau_gem_ioctl_info(struct drm_device *, void *, struct drm_file *); -/* nv17_gpio.c */ -int nv17_gpio_get(struct drm_device *dev, enum dcb_gpio_tag tag); -int nv17_gpio_set(struct drm_device *dev, enum dcb_gpio_tag tag, int state); +/* nv10_gpio.c */ +int nv10_gpio_get(struct drm_device *dev, enum dcb_gpio_tag tag); +int nv10_gpio_set(struct drm_device *dev, enum dcb_gpio_tag tag, int state); /* nv50_gpio.c */ +int nv50_gpio_init(struct drm_device *dev); int nv50_gpio_get(struct drm_device *dev, enum dcb_gpio_tag tag); int nv50_gpio_set(struct drm_device *dev, enum dcb_gpio_tag tag, int state); +void nv50_gpio_irq_enable(struct drm_device *, enum dcb_gpio_tag, bool on); /* nv50_calc. */ int nv50_calc_pll(struct drm_device *, struct pll_lims *, int clk, @@ -1220,6 +1215,14 @@ static inline void nv_wr32(struct drm_device *dev, unsigned reg, u32 val) iowrite32_native(val, dev_priv->mmio + reg); } +static inline void nv_mask(struct drm_device *dev, u32 reg, u32 mask, u32 val) +{ + u32 tmp = nv_rd32(dev, reg); + tmp &= ~mask; + tmp |= val; + nv_wr32(dev, reg, tmp); +} + static inline u8 nv_rd08(struct drm_device *dev, unsigned reg) { struct drm_nouveau_private *dev_priv = dev->dev_private; diff --git a/drivers/gpu/drm/nouveau/nouveau_encoder.h b/drivers/gpu/drm/nouveau/nouveau_encoder.h index e1df8209cd0..a1a0d48ae70 100644 --- a/drivers/gpu/drm/nouveau/nouveau_encoder.h +++ b/drivers/gpu/drm/nouveau/nouveau_encoder.h @@ -38,13 +38,15 @@ struct nouveau_encoder { struct dcb_entry *dcb; int or; + /* different to drm_encoder.crtc, this reflects what's + * actually programmed on the hw, not the proposed crtc */ + struct drm_crtc *crtc; + struct drm_display_mode mode; int last_dpms; struct nv04_output_reg restore; - void (*disconnect)(struct nouveau_encoder *encoder); - union { struct { int mc_unknown; @@ -71,8 +73,8 @@ static inline struct drm_encoder *to_drm_encoder(struct nouveau_encoder *enc) struct nouveau_connector * nouveau_encoder_connector_get(struct nouveau_encoder *encoder); -int nv50_sor_create(struct drm_device *dev, struct dcb_entry *entry); -int nv50_dac_create(struct drm_device *dev, struct dcb_entry *entry); +int nv50_sor_create(struct drm_connector *, struct dcb_entry *); +int nv50_dac_create(struct drm_connector *, struct dcb_entry *); struct bit_displayport_encoder_table { uint32_t match; diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 257ea130ae1..2fb2444d232 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -333,7 +333,7 @@ nouveau_fbcon_output_poll_changed(struct drm_device *dev) drm_fb_helper_hotplug_event(&dev_priv->nfbdev->helper); } -int +static int nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *nfbdev) { struct nouveau_framebuffer *nouveau_fb = &nfbdev->nouveau_fb; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index faddf53ff9e..6b208ffafa8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -67,12 +67,13 @@ nouveau_fence_update(struct nouveau_channel *chan) if (USE_REFCNT) sequence = nvchan_rd32(chan, 0x48); else - sequence = chan->fence.last_sequence_irq; + sequence = atomic_read(&chan->fence.last_sequence_irq); if (chan->fence.sequence_ack == sequence) return; chan->fence.sequence_ack = sequence; + spin_lock(&chan->fence.lock); list_for_each_safe(entry, tmp, &chan->fence.pending) { fence = list_entry(entry, struct nouveau_fence, entry); @@ -84,6 +85,7 @@ nouveau_fence_update(struct nouveau_channel *chan) if (sequence == chan->fence.sequence_ack) break; } + spin_unlock(&chan->fence.lock); } int @@ -119,7 +121,6 @@ nouveau_fence_emit(struct nouveau_fence *fence) { struct drm_nouveau_private *dev_priv = fence->channel->dev->dev_private; struct nouveau_channel *chan = fence->channel; - unsigned long flags; int ret; ret = RING_SPACE(chan, 2); @@ -127,9 +128,7 @@ nouveau_fence_emit(struct nouveau_fence *fence) return ret; if (unlikely(chan->fence.sequence == chan->fence.sequence_ack - 1)) { - spin_lock_irqsave(&chan->fence.lock, flags); nouveau_fence_update(chan); - spin_unlock_irqrestore(&chan->fence.lock, flags); BUG_ON(chan->fence.sequence == chan->fence.sequence_ack - 1); @@ -138,9 +137,9 @@ nouveau_fence_emit(struct nouveau_fence *fence) fence->sequence = ++chan->fence.sequence; kref_get(&fence->refcount); - spin_lock_irqsave(&chan->fence.lock, flags); + spin_lock(&chan->fence.lock); list_add_tail(&fence->entry, &chan->fence.pending); - spin_unlock_irqrestore(&chan->fence.lock, flags); + spin_unlock(&chan->fence.lock); BEGIN_RING(chan, NvSubSw, USE_REFCNT ? 0x0050 : 0x0150, 1); OUT_RING(chan, fence->sequence); @@ -173,14 +172,11 @@ nouveau_fence_signalled(void *sync_obj, void *sync_arg) { struct nouveau_fence *fence = nouveau_fence(sync_obj); struct nouveau_channel *chan = fence->channel; - unsigned long flags; if (fence->signalled) return true; - spin_lock_irqsave(&chan->fence.lock, flags); nouveau_fence_update(chan); - spin_unlock_irqrestore(&chan->fence.lock, flags); return fence->signalled; } @@ -190,8 +186,6 @@ nouveau_fence_wait(void *sync_obj, void *sync_arg, bool lazy, bool intr) unsigned long timeout = jiffies + (3 * DRM_HZ); int ret = 0; - __set_current_state(intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); - while (1) { if (nouveau_fence_signalled(sync_obj, sync_arg)) break; @@ -201,6 +195,8 @@ nouveau_fence_wait(void *sync_obj, void *sync_arg, bool lazy, bool intr) break; } + __set_current_state(intr ? TASK_INTERRUPTIBLE + : TASK_UNINTERRUPTIBLE); if (lazy) schedule_timeout(1); @@ -221,27 +217,12 @@ nouveau_fence_flush(void *sync_obj, void *sync_arg) return 0; } -void -nouveau_fence_handler(struct drm_device *dev, int channel) -{ - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_channel *chan = NULL; - - if (channel >= 0 && channel < dev_priv->engine.fifo.channels) - chan = dev_priv->fifos[channel]; - - if (chan) { - spin_lock_irq(&chan->fence.lock); - nouveau_fence_update(chan); - spin_unlock_irq(&chan->fence.lock); - } -} - int nouveau_fence_init(struct nouveau_channel *chan) { INIT_LIST_HEAD(&chan->fence.pending); spin_lock_init(&chan->fence.lock); + atomic_set(&chan->fence.last_sequence_irq, 0); return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 69c76cf9340..547f2c24c1e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -137,8 +137,6 @@ nouveau_gem_ioctl_new(struct drm_device *dev, void *data, uint32_t flags = 0; int ret = 0; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; - if (unlikely(dev_priv->ttm.bdev.dev_mapping == NULL)) dev_priv->ttm.bdev.dev_mapping = dev_priv->dev->dev_mapping; @@ -577,10 +575,9 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, struct drm_nouveau_gem_pushbuf_bo *bo; struct nouveau_channel *chan; struct validate_op op; - struct nouveau_fence *fence = 0; + struct nouveau_fence *fence = NULL; int i, j, ret = 0, do_reloc = 0; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; NOUVEAU_GET_USER_CHANNEL_WITH_RETURN(req->channel, file_priv, chan); req->vram_available = dev_priv->fb_aper_free; @@ -760,8 +757,6 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data, bool no_wait = !!(req->flags & NOUVEAU_GEM_CPU_PREP_NOWAIT); int ret = -EINVAL; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; - gem = drm_gem_object_lookup(dev, file_priv, req->handle); if (!gem) return ret; @@ -800,8 +795,6 @@ nouveau_gem_ioctl_cpu_fini(struct drm_device *dev, void *data, struct nouveau_bo *nvbo; int ret = -EINVAL; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; - gem = drm_gem_object_lookup(dev, file_priv, req->handle); if (!gem) return ret; @@ -827,8 +820,6 @@ nouveau_gem_ioctl_info(struct drm_device *dev, void *data, struct drm_gem_object *gem; int ret; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; - gem = drm_gem_object_lookup(dev, file_priv, req->handle); if (!gem) return -EINVAL; diff --git a/drivers/gpu/drm/nouveau/nouveau_grctx.c b/drivers/gpu/drm/nouveau/nouveau_grctx.c deleted file mode 100644 index f731c5f6053..00000000000 --- a/drivers/gpu/drm/nouveau/nouveau_grctx.c +++ /dev/null @@ -1,160 +0,0 @@ -/* - * Copyright 2009 Red Hat Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - * Authors: Ben Skeggs - */ - -#include <linux/firmware.h> -#include <linux/slab.h> - -#include "drmP.h" -#include "nouveau_drv.h" - -struct nouveau_ctxprog { - uint32_t signature; - uint8_t version; - uint16_t length; - uint32_t data[]; -} __attribute__ ((packed)); - -struct nouveau_ctxvals { - uint32_t signature; - uint8_t version; - uint32_t length; - struct { - uint32_t offset; - uint32_t value; - } data[]; -} __attribute__ ((packed)); - -int -nouveau_grctx_prog_load(struct drm_device *dev) -{ - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; - const int chipset = dev_priv->chipset; - const struct firmware *fw; - const struct nouveau_ctxprog *cp; - const struct nouveau_ctxvals *cv; - char name[32]; - int ret, i; - - if (pgraph->accel_blocked) - return -ENODEV; - - if (!pgraph->ctxprog) { - sprintf(name, "nouveau/nv%02x.ctxprog", chipset); - ret = request_firmware(&fw, name, &dev->pdev->dev); - if (ret) { - NV_ERROR(dev, "No ctxprog for NV%02x\n", chipset); - return ret; - } - - pgraph->ctxprog = kmemdup(fw->data, fw->size, GFP_KERNEL); - if (!pgraph->ctxprog) { - NV_ERROR(dev, "OOM copying ctxprog\n"); - release_firmware(fw); - return -ENOMEM; - } - - cp = pgraph->ctxprog; - if (le32_to_cpu(cp->signature) != 0x5043564e || - cp->version != 0 || - le16_to_cpu(cp->length) != ((fw->size - 7) / 4)) { - NV_ERROR(dev, "ctxprog invalid\n"); - release_firmware(fw); - nouveau_grctx_fini(dev); - return -EINVAL; - } - release_firmware(fw); - } - - if (!pgraph->ctxvals) { - sprintf(name, "nouveau/nv%02x.ctxvals", chipset); - ret = request_firmware(&fw, name, &dev->pdev->dev); - if (ret) { - NV_ERROR(dev, "No ctxvals for NV%02x\n", chipset); - nouveau_grctx_fini(dev); - return ret; - } - - pgraph->ctxvals = kmemdup(fw->data, fw->size, GFP_KERNEL); - if (!pgraph->ctxvals) { - NV_ERROR(dev, "OOM copying ctxvals\n"); - release_firmware(fw); - nouveau_grctx_fini(dev); - return -ENOMEM; - } - - cv = (void *)pgraph->ctxvals; - if (le32_to_cpu(cv->signature) != 0x5643564e || - cv->version != 0 || - le32_to_cpu(cv->length) != ((fw->size - 9) / 8)) { - NV_ERROR(dev, "ctxvals invalid\n"); - release_firmware(fw); - nouveau_grctx_fini(dev); - return -EINVAL; - } - release_firmware(fw); - } - - cp = pgraph->ctxprog; - - nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_INDEX, 0); - for (i = 0; i < le16_to_cpu(cp->length); i++) - nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_DATA, - le32_to_cpu(cp->data[i])); - - return 0; -} - -void -nouveau_grctx_fini(struct drm_device *dev) -{ - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; - - if (pgraph->ctxprog) { - kfree(pgraph->ctxprog); - pgraph->ctxprog = NULL; - } - - if (pgraph->ctxvals) { - kfree(pgraph->ctxprog); - pgraph->ctxvals = NULL; - } -} - -void -nouveau_grctx_vals_load(struct drm_device *dev, struct nouveau_gpuobj *ctx) -{ - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; - struct nouveau_ctxvals *cv = pgraph->ctxvals; - int i; - - if (!cv) - return; - - for (i = 0; i < le32_to_cpu(cv->length); i++) - nv_wo32(dev, ctx, le32_to_cpu(cv->data[i].offset), - le32_to_cpu(cv->data[i].value)); -} diff --git a/drivers/gpu/drm/nouveau/nouveau_i2c.c b/drivers/gpu/drm/nouveau/nouveau_i2c.c index 316a3c7e6eb..cb0cb34440c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_i2c.c +++ b/drivers/gpu/drm/nouveau/nouveau_i2c.c @@ -278,3 +278,45 @@ nouveau_i2c_find(struct drm_device *dev, int index) return i2c->chan; } +bool +nouveau_probe_i2c_addr(struct nouveau_i2c_chan *i2c, int addr) +{ + uint8_t buf[] = { 0 }; + struct i2c_msg msgs[] = { + { + .addr = addr, + .flags = 0, + .len = 1, + .buf = buf, + }, + { + .addr = addr, + .flags = I2C_M_RD, + .len = 1, + .buf = buf, + } + }; + + return i2c_transfer(&i2c->adapter, msgs, 2) == 2; +} + +int +nouveau_i2c_identify(struct drm_device *dev, const char *what, + struct i2c_board_info *info, int index) +{ + struct nouveau_i2c_chan *i2c = nouveau_i2c_find(dev, index); + int i; + + NV_DEBUG(dev, "Probing %ss on I2C bus: %d\n", what, index); + + for (i = 0; info[i].addr; i++) { + if (nouveau_probe_i2c_addr(i2c, info[i].addr)) { + NV_INFO(dev, "Detected %s: %s\n", what, info[i].type); + return i; + } + } + + NV_DEBUG(dev, "No devices found.\n"); + + return -ENODEV; +} diff --git a/drivers/gpu/drm/nouveau/nouveau_i2c.h b/drivers/gpu/drm/nouveau/nouveau_i2c.h index c8eaf7a9fcb..6dd2f8713cd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_i2c.h +++ b/drivers/gpu/drm/nouveau/nouveau_i2c.h @@ -45,6 +45,9 @@ struct nouveau_i2c_chan { int nouveau_i2c_init(struct drm_device *, struct dcb_i2c_entry *, int index); void nouveau_i2c_fini(struct drm_device *, struct dcb_i2c_entry *); struct nouveau_i2c_chan *nouveau_i2c_find(struct drm_device *, int index); +bool nouveau_probe_i2c_addr(struct nouveau_i2c_chan *i2c, int addr); +int nouveau_i2c_identify(struct drm_device *dev, const char *what, + struct i2c_board_info *info, int index); int nouveau_dp_i2c_aux_ch(struct i2c_adapter *, int mode, uint8_t write_byte, uint8_t *read_byte); diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index c1fd42b0dad..a9f36ab256b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -35,162 +35,6 @@ #include "drm_sarea.h" #include "nouveau_drv.h" -static struct mem_block * -split_block(struct mem_block *p, uint64_t start, uint64_t size, - struct drm_file *file_priv) -{ - /* Maybe cut off the start of an existing block */ - if (start > p->start) { - struct mem_block *newblock = - kmalloc(sizeof(*newblock), GFP_KERNEL); - if (!newblock) - goto out; - newblock->start = start; - newblock->size = p->size - (start - p->start); - newblock->file_priv = NULL; - newblock->next = p->next; - newblock->prev = p; - p->next->prev = newblock; - p->next = newblock; - p->size -= newblock->size; - p = newblock; - } - - /* Maybe cut off the end of an existing block */ - if (size < p->size) { - struct mem_block *newblock = - kmalloc(sizeof(*newblock), GFP_KERNEL); - if (!newblock) - goto out; - newblock->start = start + size; - newblock->size = p->size - size; - newblock->file_priv = NULL; - newblock->next = p->next; - newblock->prev = p; - p->next->prev = newblock; - p->next = newblock; - p->size = size; - } - -out: - /* Our block is in the middle */ - p->file_priv = file_priv; - return p; -} - -struct mem_block * -nouveau_mem_alloc_block(struct mem_block *heap, uint64_t size, - int align2, struct drm_file *file_priv, int tail) -{ - struct mem_block *p; - uint64_t mask = (1 << align2) - 1; - - if (!heap) - return NULL; - - if (tail) { - list_for_each_prev(p, heap) { - uint64_t start = ((p->start + p->size) - size) & ~mask; - - if (p->file_priv == NULL && start >= p->start && - start + size <= p->start + p->size) - return split_block(p, start, size, file_priv); - } - } else { - list_for_each(p, heap) { - uint64_t start = (p->start + mask) & ~mask; - - if (p->file_priv == NULL && - start + size <= p->start + p->size) - return split_block(p, start, size, file_priv); - } - } - - return NULL; -} - -void nouveau_mem_free_block(struct mem_block *p) -{ - p->file_priv = NULL; - - /* Assumes a single contiguous range. Needs a special file_priv in - * 'heap' to stop it being subsumed. - */ - if (p->next->file_priv == NULL) { - struct mem_block *q = p->next; - p->size += q->size; - p->next = q->next; - p->next->prev = p; - kfree(q); - } - - if (p->prev->file_priv == NULL) { - struct mem_block *q = p->prev; - q->size += p->size; - q->next = p->next; - q->next->prev = q; - kfree(p); - } -} - -/* Initialize. How to check for an uninitialized heap? - */ -int nouveau_mem_init_heap(struct mem_block **heap, uint64_t start, - uint64_t size) -{ - struct mem_block *blocks = kmalloc(sizeof(*blocks), GFP_KERNEL); - - if (!blocks) - return -ENOMEM; - - *heap = kmalloc(sizeof(**heap), GFP_KERNEL); - if (!*heap) { - kfree(blocks); - return -ENOMEM; - } - - blocks->start = start; - blocks->size = size; - blocks->file_priv = NULL; - blocks->next = blocks->prev = *heap; - - memset(*heap, 0, sizeof(**heap)); - (*heap)->file_priv = (struct drm_file *) -1; - (*heap)->next = (*heap)->prev = blocks; - return 0; -} - -/* - * Free all blocks associated with the releasing file_priv - */ -void nouveau_mem_release(struct drm_file *file_priv, struct mem_block *heap) -{ - struct mem_block *p; - - if (!heap || !heap->next) - return; - - list_for_each(p, heap) { - if (p->file_priv == file_priv) - p->file_priv = NULL; - } - - /* Assumes a single contiguous range. Needs a special file_priv in - * 'heap' to stop it being subsumed. - */ - list_for_each(p, heap) { - while ((p->file_priv == NULL) && - (p->next->file_priv == NULL) && - (p->next != heap)) { - struct mem_block *q = p->next; - p->size += q->size; - p->next = q->next; - p->next->prev = p; - kfree(q); - } - } -} - /* * NV10-NV40 tiling helpers */ @@ -299,7 +143,6 @@ nv50_mem_vm_bind_linear(struct drm_device *dev, uint64_t virt, uint32_t size, phys |= 0x30; } - dev_priv->engine.instmem.prepare_access(dev, true); while (size) { unsigned offset_h = upper_32_bits(phys); unsigned offset_l = lower_32_bits(phys); @@ -331,36 +174,12 @@ nv50_mem_vm_bind_linear(struct drm_device *dev, uint64_t virt, uint32_t size, } } } - dev_priv->engine.instmem.finish_access(dev); - - nv_wr32(dev, 0x100c80, 0x00050001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - return -EBUSY; - } - - nv_wr32(dev, 0x100c80, 0x00000001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - return -EBUSY; - } - - nv_wr32(dev, 0x100c80, 0x00040001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - return -EBUSY; - } - - nv_wr32(dev, 0x100c80, 0x00060001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - return -EBUSY; - } + dev_priv->engine.instmem.flush(dev); + nv50_vm_flush(dev, 5); + nv50_vm_flush(dev, 0); + nv50_vm_flush(dev, 4); + nv50_vm_flush(dev, 6); return 0; } @@ -374,7 +193,6 @@ nv50_mem_vm_unbind(struct drm_device *dev, uint64_t virt, uint32_t size) virt -= dev_priv->vm_vram_base; pages = (size >> 16) << 1; - dev_priv->engine.instmem.prepare_access(dev, true); while (pages) { pgt = dev_priv->vm_vram_pt[virt >> 29]; pte = (virt & 0x1ffe0000ULL) >> 15; @@ -388,57 +206,19 @@ nv50_mem_vm_unbind(struct drm_device *dev, uint64_t virt, uint32_t size) while (pte < end) nv_wo32(dev, pgt, pte++, 0); } - dev_priv->engine.instmem.finish_access(dev); - - nv_wr32(dev, 0x100c80, 0x00050001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - return; - } - - nv_wr32(dev, 0x100c80, 0x00000001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - return; - } - - nv_wr32(dev, 0x100c80, 0x00040001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - return; - } + dev_priv->engine.instmem.flush(dev); - nv_wr32(dev, 0x100c80, 0x00060001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - } + nv50_vm_flush(dev, 5); + nv50_vm_flush(dev, 0); + nv50_vm_flush(dev, 4); + nv50_vm_flush(dev, 6); } /* * Cleanup everything */ -void nouveau_mem_takedown(struct mem_block **heap) -{ - struct mem_block *p; - - if (!*heap) - return; - - for (p = (*heap)->next; p != *heap;) { - struct mem_block *q = p; - p = p->next; - kfree(q); - } - - kfree(*heap); - *heap = NULL; -} - -void nouveau_mem_close(struct drm_device *dev) +void +nouveau_mem_close(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; @@ -449,8 +229,7 @@ void nouveau_mem_close(struct drm_device *dev) nouveau_ttm_global_release(dev_priv); - if (drm_core_has_AGP(dev) && dev->agp && - drm_core_check_feature(dev, DRIVER_MODESET)) { + if (drm_core_has_AGP(dev) && dev->agp) { struct drm_agp_mem *entry, *tempe; /* Remove AGP resources, but leave dev->agp @@ -471,28 +250,29 @@ void nouveau_mem_close(struct drm_device *dev) } if (dev_priv->fb_mtrr) { - drm_mtrr_del(dev_priv->fb_mtrr, drm_get_resource_start(dev, 1), - drm_get_resource_len(dev, 1), DRM_MTRR_WC); - dev_priv->fb_mtrr = 0; + drm_mtrr_del(dev_priv->fb_mtrr, + pci_resource_start(dev->pdev, 1), + pci_resource_len(dev->pdev, 1), DRM_MTRR_WC); + dev_priv->fb_mtrr = -1; } } static uint32_t nouveau_mem_detect_nv04(struct drm_device *dev) { - uint32_t boot0 = nv_rd32(dev, NV03_BOOT_0); + uint32_t boot0 = nv_rd32(dev, NV04_PFB_BOOT_0); if (boot0 & 0x00000100) return (((boot0 >> 12) & 0xf) * 2 + 2) * 1024 * 1024; - switch (boot0 & NV03_BOOT_0_RAM_AMOUNT) { - case NV04_BOOT_0_RAM_AMOUNT_32MB: + switch (boot0 & NV04_PFB_BOOT_0_RAM_AMOUNT) { + case NV04_PFB_BOOT_0_RAM_AMOUNT_32MB: return 32 * 1024 * 1024; - case NV04_BOOT_0_RAM_AMOUNT_16MB: + case NV04_PFB_BOOT_0_RAM_AMOUNT_16MB: return 16 * 1024 * 1024; - case NV04_BOOT_0_RAM_AMOUNT_8MB: + case NV04_PFB_BOOT_0_RAM_AMOUNT_8MB: return 8 * 1024 * 1024; - case NV04_BOOT_0_RAM_AMOUNT_4MB: + case NV04_PFB_BOOT_0_RAM_AMOUNT_4MB: return 4 * 1024 * 1024; } @@ -536,12 +316,18 @@ nouveau_mem_detect(struct drm_device *dev) } else if (dev_priv->flags & (NV_NFORCE | NV_NFORCE2)) { dev_priv->vram_size = nouveau_mem_detect_nforce(dev); + } else + if (dev_priv->card_type < NV_50) { + dev_priv->vram_size = nv_rd32(dev, NV04_PFB_FIFO_DATA); + dev_priv->vram_size &= NV10_PFB_FIFO_DATA_RAM_AMOUNT_MB_MASK; } else { - dev_priv->vram_size = nv_rd32(dev, NV04_FIFO_DATA); - dev_priv->vram_size &= NV10_FIFO_DATA_RAM_AMOUNT_MB_MASK; - if (dev_priv->chipset == 0xaa || dev_priv->chipset == 0xac) + dev_priv->vram_size = nv_rd32(dev, NV04_PFB_FIFO_DATA); + dev_priv->vram_size |= (dev_priv->vram_size & 0xff) << 32; + dev_priv->vram_size &= 0xffffffff00ll; + if (dev_priv->chipset == 0xaa || dev_priv->chipset == 0xac) { dev_priv->vram_sys_base = nv_rd32(dev, 0x100e10); dev_priv->vram_sys_base <<= 12; + } } NV_INFO(dev, "Detected %dMiB VRAM\n", (int)(dev_priv->vram_size >> 20)); @@ -555,18 +341,36 @@ nouveau_mem_detect(struct drm_device *dev) return -ENOMEM; } -#if __OS_HAS_AGP -static void nouveau_mem_reset_agp(struct drm_device *dev) +int +nouveau_mem_reset_agp(struct drm_device *dev) { - uint32_t saved_pci_nv_1, saved_pci_nv_19, pmc_enable; +#if __OS_HAS_AGP + uint32_t saved_pci_nv_1, pmc_enable; + int ret; + + /* First of all, disable fast writes, otherwise if it's + * already enabled in the AGP bridge and we disable the card's + * AGP controller we might be locking ourselves out of it. */ + if (dev->agp->acquired) { + struct drm_agp_info info; + struct drm_agp_mode mode; + + ret = drm_agp_info(dev, &info); + if (ret) + return ret; + + mode.mode = info.mode & ~0x10; + ret = drm_agp_enable(dev, mode); + if (ret) + return ret; + } saved_pci_nv_1 = nv_rd32(dev, NV04_PBUS_PCI_NV_1); - saved_pci_nv_19 = nv_rd32(dev, NV04_PBUS_PCI_NV_19); /* clear busmaster bit */ nv_wr32(dev, NV04_PBUS_PCI_NV_1, saved_pci_nv_1 & ~0x4); - /* clear SBA and AGP bits */ - nv_wr32(dev, NV04_PBUS_PCI_NV_19, saved_pci_nv_19 & 0xfffff0ff); + /* disable AGP */ + nv_wr32(dev, NV04_PBUS_PCI_NV_19, 0); /* power cycle pgraph, if enabled */ pmc_enable = nv_rd32(dev, NV03_PMC_ENABLE); @@ -578,11 +382,12 @@ static void nouveau_mem_reset_agp(struct drm_device *dev) } /* and restore (gives effect of resetting AGP) */ - nv_wr32(dev, NV04_PBUS_PCI_NV_19, saved_pci_nv_19); nv_wr32(dev, NV04_PBUS_PCI_NV_1, saved_pci_nv_1); -} #endif + return 0; +} + int nouveau_mem_init_agp(struct drm_device *dev) { @@ -592,11 +397,6 @@ nouveau_mem_init_agp(struct drm_device *dev) struct drm_agp_mode mode; int ret; - if (nouveau_noagp) - return 0; - - nouveau_mem_reset_agp(dev); - if (!dev->agp->acquired) { ret = drm_agp_acquire(dev); if (ret) { @@ -633,7 +433,7 @@ nouveau_mem_init(struct drm_device *dev) struct ttm_bo_device *bdev = &dev_priv->ttm.bdev; int ret, dma_bits = 32; - dev_priv->fb_phys = drm_get_resource_start(dev, 1); + dev_priv->fb_phys = pci_resource_start(dev->pdev, 1); dev_priv->gart_info.type = NOUVEAU_GART_NONE; if (dev_priv->card_type >= NV_50 && @@ -665,8 +465,9 @@ nouveau_mem_init(struct drm_device *dev) dev_priv->fb_available_size = dev_priv->vram_size; dev_priv->fb_mappable_pages = dev_priv->fb_available_size; - if (dev_priv->fb_mappable_pages > drm_get_resource_len(dev, 1)) - dev_priv->fb_mappable_pages = drm_get_resource_len(dev, 1); + if (dev_priv->fb_mappable_pages > pci_resource_len(dev->pdev, 1)) + dev_priv->fb_mappable_pages = + pci_resource_len(dev->pdev, 1); dev_priv->fb_mappable_pages >>= PAGE_SHIFT; /* remove reserved space at end of vram from available amount */ @@ -692,7 +493,8 @@ nouveau_mem_init(struct drm_device *dev) /* GART */ #if !defined(__powerpc__) && !defined(__ia64__) - if (drm_device_is_agp(dev) && dev->agp) { + if (drm_device_is_agp(dev) && dev->agp && !nouveau_noagp) { + nouveau_mem_reset_agp(dev); ret = nouveau_mem_init_agp(dev); if (ret) NV_ERROR(dev, "Error initialising AGP: %d\n", ret); @@ -718,8 +520,8 @@ nouveau_mem_init(struct drm_device *dev) return ret; } - dev_priv->fb_mtrr = drm_mtrr_add(drm_get_resource_start(dev, 1), - drm_get_resource_len(dev, 1), + dev_priv->fb_mtrr = drm_mtrr_add(pci_resource_start(dev->pdev, 1), + pci_resource_len(dev->pdev, 1), DRM_MTRR_WC); return 0; diff --git a/drivers/gpu/drm/nouveau/nouveau_notifier.c b/drivers/gpu/drm/nouveau/nouveau_notifier.c index 9537f3e3011..3ec181ff50c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_notifier.c +++ b/drivers/gpu/drm/nouveau/nouveau_notifier.c @@ -55,7 +55,7 @@ nouveau_notifier_init_channel(struct nouveau_channel *chan) if (ret) goto out_err; - ret = nouveau_mem_init_heap(&chan->notifier_heap, 0, ntfy->bo.mem.size); + ret = drm_mm_init(&chan->notifier_heap, 0, ntfy->bo.mem.size); if (ret) goto out_err; @@ -80,7 +80,7 @@ nouveau_notifier_takedown_channel(struct nouveau_channel *chan) nouveau_bo_unpin(chan->notifier_bo); mutex_unlock(&dev->struct_mutex); drm_gem_object_unreference_unlocked(chan->notifier_bo->gem); - nouveau_mem_takedown(&chan->notifier_heap); + drm_mm_takedown(&chan->notifier_heap); } static void @@ -90,7 +90,7 @@ nouveau_notifier_gpuobj_dtor(struct drm_device *dev, NV_DEBUG(dev, "\n"); if (gpuobj->priv) - nouveau_mem_free_block(gpuobj->priv); + drm_mm_put_block(gpuobj->priv); } int @@ -100,18 +100,13 @@ nouveau_notifier_alloc(struct nouveau_channel *chan, uint32_t handle, struct drm_device *dev = chan->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_gpuobj *nobj = NULL; - struct mem_block *mem; + struct drm_mm_node *mem; uint32_t offset; int target, ret; - if (!chan->notifier_heap) { - NV_ERROR(dev, "Channel %d doesn't have a notifier heap!\n", - chan->id); - return -EINVAL; - } - - mem = nouveau_mem_alloc_block(chan->notifier_heap, size, 0, - (struct drm_file *)-2, 0); + mem = drm_mm_search_free(&chan->notifier_heap, size, 0, 0); + if (mem) + mem = drm_mm_get_block(mem, size, 0); if (!mem) { NV_ERROR(dev, "Channel %d notifier block full\n", chan->id); return -ENOMEM; @@ -144,17 +139,17 @@ nouveau_notifier_alloc(struct nouveau_channel *chan, uint32_t handle, mem->size, NV_DMA_ACCESS_RW, target, &nobj); if (ret) { - nouveau_mem_free_block(mem); + drm_mm_put_block(mem); NV_ERROR(dev, "Error creating notifier ctxdma: %d\n", ret); return ret; } - nobj->dtor = nouveau_notifier_gpuobj_dtor; - nobj->priv = mem; + nobj->dtor = nouveau_notifier_gpuobj_dtor; + nobj->priv = mem; ret = nouveau_gpuobj_ref_add(dev, chan, handle, nobj, NULL); if (ret) { nouveau_gpuobj_del(dev, &nobj); - nouveau_mem_free_block(mem); + drm_mm_put_block(mem); NV_ERROR(dev, "Error referencing notifier ctxdma: %d\n", ret); return ret; } @@ -170,7 +165,7 @@ nouveau_notifier_offset(struct nouveau_gpuobj *nobj, uint32_t *poffset) return -EINVAL; if (poffset) { - struct mem_block *mem = nobj->priv; + struct drm_mm_node *mem = nobj->priv; if (*poffset >= mem->size) return false; @@ -189,7 +184,6 @@ nouveau_ioctl_notifier_alloc(struct drm_device *dev, void *data, struct nouveau_channel *chan; int ret; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; NOUVEAU_GET_USER_CHANNEL_WITH_RETURN(na->channel, file_priv, chan); ret = nouveau_notifier_alloc(chan, na->handle, na->size, &na->offset); diff --git a/drivers/gpu/drm/nouveau/nouveau_object.c b/drivers/gpu/drm/nouveau/nouveau_object.c index e7c100ba63a..b6bcb254f4a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_object.c +++ b/drivers/gpu/drm/nouveau/nouveau_object.c @@ -132,7 +132,6 @@ nouveau_ramht_insert(struct drm_device *dev, struct nouveau_gpuobj_ref *ref) } } - instmem->prepare_access(dev, true); co = ho = nouveau_ramht_hash_handle(dev, chan->id, ref->handle); do { if (!nouveau_ramht_entry_valid(dev, ramht, co)) { @@ -143,7 +142,7 @@ nouveau_ramht_insert(struct drm_device *dev, struct nouveau_gpuobj_ref *ref) nv_wo32(dev, ramht, (co + 4)/4, ctx); list_add_tail(&ref->list, &chan->ramht_refs); - instmem->finish_access(dev); + instmem->flush(dev); return 0; } NV_DEBUG(dev, "collision ch%d 0x%08x: h=0x%08x\n", @@ -153,7 +152,6 @@ nouveau_ramht_insert(struct drm_device *dev, struct nouveau_gpuobj_ref *ref) if (co >= dev_priv->ramht_size) co = 0; } while (co != ho); - instmem->finish_access(dev); NV_ERROR(dev, "RAMHT space exhausted. ch=%d\n", chan->id); return -ENOMEM; @@ -173,7 +171,6 @@ nouveau_ramht_remove(struct drm_device *dev, struct nouveau_gpuobj_ref *ref) return; } - instmem->prepare_access(dev, true); co = ho = nouveau_ramht_hash_handle(dev, chan->id, ref->handle); do { if (nouveau_ramht_entry_valid(dev, ramht, co) && @@ -186,7 +183,7 @@ nouveau_ramht_remove(struct drm_device *dev, struct nouveau_gpuobj_ref *ref) nv_wo32(dev, ramht, (co + 4)/4, 0x00000000); list_del(&ref->list); - instmem->finish_access(dev); + instmem->flush(dev); return; } @@ -195,7 +192,6 @@ nouveau_ramht_remove(struct drm_device *dev, struct nouveau_gpuobj_ref *ref) co = 0; } while (co != ho); list_del(&ref->list); - instmem->finish_access(dev); NV_ERROR(dev, "RAMHT entry not found. ch=%d, handle=0x%08x\n", chan->id, ref->handle); @@ -209,7 +205,7 @@ nouveau_gpuobj_new(struct drm_device *dev, struct nouveau_channel *chan, struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_engine *engine = &dev_priv->engine; struct nouveau_gpuobj *gpuobj; - struct mem_block *pramin = NULL; + struct drm_mm *pramin = NULL; int ret; NV_DEBUG(dev, "ch%d size=%u align=%d flags=0x%08x\n", @@ -233,25 +229,12 @@ nouveau_gpuobj_new(struct drm_device *dev, struct nouveau_channel *chan, * available. */ if (chan) { - if (chan->ramin_heap) { - NV_DEBUG(dev, "private heap\n"); - pramin = chan->ramin_heap; - } else - if (dev_priv->card_type < NV_50) { - NV_DEBUG(dev, "global heap fallback\n"); - pramin = dev_priv->ramin_heap; - } + NV_DEBUG(dev, "channel heap\n"); + pramin = &chan->ramin_heap; } else { NV_DEBUG(dev, "global heap\n"); - pramin = dev_priv->ramin_heap; - } - - if (!pramin) { - NV_ERROR(dev, "No PRAMIN heap!\n"); - return -EINVAL; - } + pramin = &dev_priv->ramin_heap; - if (!chan) { ret = engine->instmem.populate(dev, gpuobj, &size); if (ret) { nouveau_gpuobj_del(dev, &gpuobj); @@ -260,9 +243,10 @@ nouveau_gpuobj_new(struct drm_device *dev, struct nouveau_channel *chan, } /* Allocate a chunk of the PRAMIN aperture */ - gpuobj->im_pramin = nouveau_mem_alloc_block(pramin, size, - drm_order(align), - (struct drm_file *)-2, 0); + gpuobj->im_pramin = drm_mm_search_free(pramin, size, align, 0); + if (gpuobj->im_pramin) + gpuobj->im_pramin = drm_mm_get_block(gpuobj->im_pramin, size, align); + if (!gpuobj->im_pramin) { nouveau_gpuobj_del(dev, &gpuobj); return -ENOMEM; @@ -279,10 +263,9 @@ nouveau_gpuobj_new(struct drm_device *dev, struct nouveau_channel *chan, if (gpuobj->flags & NVOBJ_FLAG_ZERO_ALLOC) { int i; - engine->instmem.prepare_access(dev, true); for (i = 0; i < gpuobj->im_pramin->size; i += 4) nv_wo32(dev, gpuobj, i/4, 0); - engine->instmem.finish_access(dev); + engine->instmem.flush(dev); } *gpuobj_ret = gpuobj; @@ -370,10 +353,9 @@ nouveau_gpuobj_del(struct drm_device *dev, struct nouveau_gpuobj **pgpuobj) } if (gpuobj->im_pramin && (gpuobj->flags & NVOBJ_FLAG_ZERO_FREE)) { - engine->instmem.prepare_access(dev, true); for (i = 0; i < gpuobj->im_pramin->size; i += 4) nv_wo32(dev, gpuobj, i/4, 0); - engine->instmem.finish_access(dev); + engine->instmem.flush(dev); } if (gpuobj->dtor) @@ -386,7 +368,7 @@ nouveau_gpuobj_del(struct drm_device *dev, struct nouveau_gpuobj **pgpuobj) if (gpuobj->flags & NVOBJ_FLAG_FAKE) kfree(gpuobj->im_pramin); else - nouveau_mem_free_block(gpuobj->im_pramin); + drm_mm_put_block(gpuobj->im_pramin); } list_del(&gpuobj->list); @@ -589,7 +571,7 @@ nouveau_gpuobj_new_fake(struct drm_device *dev, uint32_t p_offset, list_add_tail(&gpuobj->list, &dev_priv->gpuobj_list); if (p_offset != ~0) { - gpuobj->im_pramin = kzalloc(sizeof(struct mem_block), + gpuobj->im_pramin = kzalloc(sizeof(struct drm_mm_node), GFP_KERNEL); if (!gpuobj->im_pramin) { nouveau_gpuobj_del(dev, &gpuobj); @@ -605,10 +587,9 @@ nouveau_gpuobj_new_fake(struct drm_device *dev, uint32_t p_offset, } if (gpuobj->flags & NVOBJ_FLAG_ZERO_ALLOC) { - dev_priv->engine.instmem.prepare_access(dev, true); for (i = 0; i < gpuobj->im_pramin->size; i += 4) nv_wo32(dev, gpuobj, i/4, 0); - dev_priv->engine.instmem.finish_access(dev); + dev_priv->engine.instmem.flush(dev); } if (pref) { @@ -696,8 +677,6 @@ nouveau_gpuobj_dma_new(struct nouveau_channel *chan, int class, return ret; } - instmem->prepare_access(dev, true); - if (dev_priv->card_type < NV_50) { uint32_t frame, adjust, pte_flags = 0; @@ -734,7 +713,7 @@ nouveau_gpuobj_dma_new(struct nouveau_channel *chan, int class, nv_wo32(dev, *gpuobj, 5, flags5); } - instmem->finish_access(dev); + instmem->flush(dev); (*gpuobj)->engine = NVOBJ_ENGINE_SW; (*gpuobj)->class = class; @@ -849,7 +828,6 @@ nouveau_gpuobj_gr_new(struct nouveau_channel *chan, int class, return ret; } - dev_priv->engine.instmem.prepare_access(dev, true); if (dev_priv->card_type >= NV_50) { nv_wo32(dev, *gpuobj, 0, class); nv_wo32(dev, *gpuobj, 5, 0x00010000); @@ -874,7 +852,7 @@ nouveau_gpuobj_gr_new(struct nouveau_channel *chan, int class, } } } - dev_priv->engine.instmem.finish_access(dev); + dev_priv->engine.instmem.flush(dev); (*gpuobj)->engine = NVOBJ_ENGINE_GR; (*gpuobj)->class = class; @@ -920,6 +898,7 @@ nouveau_gpuobj_channel_init_pramin(struct nouveau_channel *chan) base = 0; /* PGRAPH context */ + size += dev_priv->engine.graph.grctx_size; if (dev_priv->card_type == NV_50) { /* Various fixed table thingos */ @@ -930,12 +909,8 @@ nouveau_gpuobj_channel_init_pramin(struct nouveau_channel *chan) size += 0x8000; /* RAMFC */ size += 0x1000; - /* PGRAPH context */ - size += 0x70000; } - NV_DEBUG(dev, "ch%d PRAMIN size: 0x%08x bytes, base alloc=0x%08x\n", - chan->id, size, base); ret = nouveau_gpuobj_new_ref(dev, NULL, NULL, 0, size, 0x1000, 0, &chan->ramin); if (ret) { @@ -944,8 +919,7 @@ nouveau_gpuobj_channel_init_pramin(struct nouveau_channel *chan) } pramin = chan->ramin->gpuobj; - ret = nouveau_mem_init_heap(&chan->ramin_heap, - pramin->im_pramin->start + base, size); + ret = drm_mm_init(&chan->ramin_heap, pramin->im_pramin->start + base, size); if (ret) { NV_ERROR(dev, "Error creating PRAMIN heap: %d\n", ret); nouveau_gpuobj_ref_del(dev, &chan->ramin); @@ -969,15 +943,11 @@ nouveau_gpuobj_channel_init(struct nouveau_channel *chan, NV_DEBUG(dev, "ch%d vram=0x%08x tt=0x%08x\n", chan->id, vram_h, tt_h); - /* Reserve a block of PRAMIN for the channel - *XXX: maybe on <NV50 too at some point - */ - if (0 || dev_priv->card_type == NV_50) { - ret = nouveau_gpuobj_channel_init_pramin(chan); - if (ret) { - NV_ERROR(dev, "init pramin\n"); - return ret; - } + /* Allocate a chunk of memory for per-channel object storage */ + ret = nouveau_gpuobj_channel_init_pramin(chan); + if (ret) { + NV_ERROR(dev, "init pramin\n"); + return ret; } /* NV50 VM @@ -988,17 +958,13 @@ nouveau_gpuobj_channel_init(struct nouveau_channel *chan, if (dev_priv->card_type >= NV_50) { uint32_t vm_offset, pde; - instmem->prepare_access(dev, true); - vm_offset = (dev_priv->chipset & 0xf0) == 0x50 ? 0x1400 : 0x200; vm_offset += chan->ramin->gpuobj->im_pramin->start; ret = nouveau_gpuobj_new_fake(dev, vm_offset, ~0, 0x4000, 0, &chan->vm_pd, NULL); - if (ret) { - instmem->finish_access(dev); + if (ret) return ret; - } for (i = 0; i < 0x4000; i += 8) { nv_wo32(dev, chan->vm_pd, (i+0)/4, 0x00000000); nv_wo32(dev, chan->vm_pd, (i+4)/4, 0xdeadcafe); @@ -1008,10 +974,8 @@ nouveau_gpuobj_channel_init(struct nouveau_channel *chan, ret = nouveau_gpuobj_ref_add(dev, NULL, 0, dev_priv->gart_info.sg_ctxdma, &chan->vm_gart_pt); - if (ret) { - instmem->finish_access(dev); + if (ret) return ret; - } nv_wo32(dev, chan->vm_pd, pde++, chan->vm_gart_pt->instance | 0x03); nv_wo32(dev, chan->vm_pd, pde++, 0x00000000); @@ -1021,17 +985,15 @@ nouveau_gpuobj_channel_init(struct nouveau_channel *chan, ret = nouveau_gpuobj_ref_add(dev, NULL, 0, dev_priv->vm_vram_pt[i], &chan->vm_vram_pt[i]); - if (ret) { - instmem->finish_access(dev); + if (ret) return ret; - } nv_wo32(dev, chan->vm_pd, pde++, chan->vm_vram_pt[i]->instance | 0x61); nv_wo32(dev, chan->vm_pd, pde++, 0x00000000); } - instmem->finish_access(dev); + instmem->flush(dev); } /* RAMHT */ @@ -1130,8 +1092,8 @@ nouveau_gpuobj_channel_takedown(struct nouveau_channel *chan) for (i = 0; i < dev_priv->vm_vram_pt_nr; i++) nouveau_gpuobj_ref_del(dev, &chan->vm_vram_pt[i]); - if (chan->ramin_heap) - nouveau_mem_takedown(&chan->ramin_heap); + if (chan->ramin_heap.free_stack.next) + drm_mm_takedown(&chan->ramin_heap); if (chan->ramin) nouveau_gpuobj_ref_del(dev, &chan->ramin); @@ -1164,10 +1126,8 @@ nouveau_gpuobj_suspend(struct drm_device *dev) return -ENOMEM; } - dev_priv->engine.instmem.prepare_access(dev, false); for (i = 0; i < gpuobj->im_pramin->size / 4; i++) gpuobj->im_backing_suspend[i] = nv_ro32(dev, gpuobj, i); - dev_priv->engine.instmem.finish_access(dev); } return 0; @@ -1212,10 +1172,9 @@ nouveau_gpuobj_resume(struct drm_device *dev) if (!gpuobj->im_backing_suspend) continue; - dev_priv->engine.instmem.prepare_access(dev, true); for (i = 0; i < gpuobj->im_pramin->size / 4; i++) nv_wo32(dev, gpuobj, i, gpuobj->im_backing_suspend[i]); - dev_priv->engine.instmem.finish_access(dev); + dev_priv->engine.instmem.flush(dev); } nouveau_gpuobj_suspend_cleanup(dev); @@ -1232,7 +1191,6 @@ int nouveau_ioctl_grobj_alloc(struct drm_device *dev, void *data, struct nouveau_channel *chan; int ret; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; NOUVEAU_GET_USER_CHANNEL_WITH_RETURN(init->channel, file_priv, chan); if (init->handle == ~0) @@ -1283,7 +1241,6 @@ int nouveau_ioctl_gpuobj_free(struct drm_device *dev, void *data, struct nouveau_channel *chan; int ret; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; NOUVEAU_GET_USER_CHANNEL_WITH_RETURN(objfree->channel, file_priv, chan); ret = nouveau_gpuobj_ref_find(chan, objfree->handle, &ref); diff --git a/drivers/gpu/drm/nouveau/nouveau_reg.h b/drivers/gpu/drm/nouveau/nouveau_reg.h index 6ca80a3fe70..9c1056cb8a9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_reg.h +++ b/drivers/gpu/drm/nouveau/nouveau_reg.h @@ -1,19 +1,64 @@ +#define NV04_PFB_BOOT_0 0x00100000 +# define NV04_PFB_BOOT_0_RAM_AMOUNT 0x00000003 +# define NV04_PFB_BOOT_0_RAM_AMOUNT_32MB 0x00000000 +# define NV04_PFB_BOOT_0_RAM_AMOUNT_4MB 0x00000001 +# define NV04_PFB_BOOT_0_RAM_AMOUNT_8MB 0x00000002 +# define NV04_PFB_BOOT_0_RAM_AMOUNT_16MB 0x00000003 +# define NV04_PFB_BOOT_0_RAM_WIDTH_128 0x00000004 +# define NV04_PFB_BOOT_0_RAM_TYPE 0x00000028 +# define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_8MBIT 0x00000000 +# define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_16MBIT 0x00000008 +# define NV04_PFB_BOOT_0_RAM_TYPE_SGRAM_16MBIT_4BANK 0x00000010 +# define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_16MBIT 0x00000018 +# define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_64MBIT 0x00000020 +# define NV04_PFB_BOOT_0_RAM_TYPE_SDRAM_64MBITX16 0x00000028 +# define NV04_PFB_BOOT_0_UMA_ENABLE 0x00000100 +# define NV04_PFB_BOOT_0_UMA_SIZE 0x0000f000 +#define NV04_PFB_DEBUG_0 0x00100080 +# define NV04_PFB_DEBUG_0_PAGE_MODE 0x00000001 +# define NV04_PFB_DEBUG_0_REFRESH_OFF 0x00000010 +# define NV04_PFB_DEBUG_0_REFRESH_COUNTX64 0x00003f00 +# define NV04_PFB_DEBUG_0_REFRESH_SLOW_CLK 0x00004000 +# define NV04_PFB_DEBUG_0_SAFE_MODE 0x00008000 +# define NV04_PFB_DEBUG_0_ALOM_ENABLE 0x00010000 +# define NV04_PFB_DEBUG_0_CASOE 0x00100000 +# define NV04_PFB_DEBUG_0_CKE_INVERT 0x10000000 +# define NV04_PFB_DEBUG_0_REFINC 0x20000000 +# define NV04_PFB_DEBUG_0_SAVE_POWER_OFF 0x40000000 +#define NV04_PFB_CFG0 0x00100200 +# define NV04_PFB_CFG0_SCRAMBLE 0x20000000 +#define NV04_PFB_CFG1 0x00100204 +#define NV04_PFB_FIFO_DATA 0x0010020c +# define NV10_PFB_FIFO_DATA_RAM_AMOUNT_MB_MASK 0xfff00000 +# define NV10_PFB_FIFO_DATA_RAM_AMOUNT_MB_SHIFT 20 +#define NV10_PFB_REFCTRL 0x00100210 +# define NV10_PFB_REFCTRL_VALID_1 (1 << 31) +#define NV04_PFB_PAD 0x0010021c +# define NV04_PFB_PAD_CKE_NORMAL (1 << 0) +#define NV10_PFB_TILE(i) (0x00100240 + (i*16)) +#define NV10_PFB_TILE__SIZE 8 +#define NV10_PFB_TLIMIT(i) (0x00100244 + (i*16)) +#define NV10_PFB_TSIZE(i) (0x00100248 + (i*16)) +#define NV10_PFB_TSTATUS(i) (0x0010024c + (i*16)) +#define NV04_PFB_REF 0x001002d0 +# define NV04_PFB_REF_CMD_REFRESH (1 << 0) +#define NV04_PFB_PRE 0x001002d4 +# define NV04_PFB_PRE_CMD_PRECHARGE (1 << 0) +#define NV10_PFB_CLOSE_PAGE2 0x0010033c +#define NV04_PFB_SCRAMBLE(i) (0x00100400 + 4 * (i)) +#define NV40_PFB_TILE(i) (0x00100600 + (i*16)) +#define NV40_PFB_TILE__SIZE_0 12 +#define NV40_PFB_TILE__SIZE_1 15 +#define NV40_PFB_TLIMIT(i) (0x00100604 + (i*16)) +#define NV40_PFB_TSIZE(i) (0x00100608 + (i*16)) +#define NV40_PFB_TSTATUS(i) (0x0010060c + (i*16)) +#define NV40_PFB_UNK_800 0x00100800 -#define NV03_BOOT_0 0x00100000 -# define NV03_BOOT_0_RAM_AMOUNT 0x00000003 -# define NV03_BOOT_0_RAM_AMOUNT_8MB 0x00000000 -# define NV03_BOOT_0_RAM_AMOUNT_2MB 0x00000001 -# define NV03_BOOT_0_RAM_AMOUNT_4MB 0x00000002 -# define NV03_BOOT_0_RAM_AMOUNT_8MB_SDRAM 0x00000003 -# define NV04_BOOT_0_RAM_AMOUNT_32MB 0x00000000 -# define NV04_BOOT_0_RAM_AMOUNT_4MB 0x00000001 -# define NV04_BOOT_0_RAM_AMOUNT_8MB 0x00000002 -# define NV04_BOOT_0_RAM_AMOUNT_16MB 0x00000003 - -#define NV04_FIFO_DATA 0x0010020c -# define NV10_FIFO_DATA_RAM_AMOUNT_MB_MASK 0xfff00000 -# define NV10_FIFO_DATA_RAM_AMOUNT_MB_SHIFT 20 +#define NV_PEXTDEV_BOOT_0 0x00101000 +#define NV_PEXTDEV_BOOT_0_RAMCFG 0x0000003c +# define NV_PEXTDEV_BOOT_0_STRAP_FP_IFACE_12BIT (8 << 12) +#define NV_PEXTDEV_BOOT_3 0x0010100c #define NV_RAMIN 0x00700000 @@ -131,23 +176,6 @@ #define NV04_PTIMER_TIME_1 0x00009410 #define NV04_PTIMER_ALARM_0 0x00009420 -#define NV04_PFB_CFG0 0x00100200 -#define NV04_PFB_CFG1 0x00100204 -#define NV40_PFB_020C 0x0010020C -#define NV10_PFB_TILE(i) (0x00100240 + (i*16)) -#define NV10_PFB_TILE__SIZE 8 -#define NV10_PFB_TLIMIT(i) (0x00100244 + (i*16)) -#define NV10_PFB_TSIZE(i) (0x00100248 + (i*16)) -#define NV10_PFB_TSTATUS(i) (0x0010024C + (i*16)) -#define NV10_PFB_CLOSE_PAGE2 0x0010033C -#define NV40_PFB_TILE(i) (0x00100600 + (i*16)) -#define NV40_PFB_TILE__SIZE_0 12 -#define NV40_PFB_TILE__SIZE_1 15 -#define NV40_PFB_TLIMIT(i) (0x00100604 + (i*16)) -#define NV40_PFB_TSIZE(i) (0x00100608 + (i*16)) -#define NV40_PFB_TSTATUS(i) (0x0010060C + (i*16)) -#define NV40_PFB_UNK_800 0x00100800 - #define NV04_PGRAPH_DEBUG_0 0x00400080 #define NV04_PGRAPH_DEBUG_1 0x00400084 #define NV04_PGRAPH_DEBUG_2 0x00400088 @@ -814,6 +842,7 @@ #define NV50_PDISPLAY_SOR_BACKLIGHT_ENABLE 0x80000000 #define NV50_PDISPLAY_SOR_BACKLIGHT_LEVEL 0x00000fff #define NV50_SOR_DP_CTRL(i,l) (0x0061c10c + (i) * 0x800 + (l) * 0x80) +#define NV50_SOR_DP_CTRL_ENABLED 0x00000001 #define NV50_SOR_DP_CTRL_ENHANCED_FRAME_ENABLED 0x00004000 #define NV50_SOR_DP_CTRL_LANE_MASK 0x001f0000 #define NV50_SOR_DP_CTRL_LANE_0_ENABLED 0x00010000 diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c index 1d6ee8b5515..491767fe4fc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c +++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c @@ -97,7 +97,6 @@ nouveau_sgdma_bind(struct ttm_backend *be, struct ttm_mem_reg *mem) NV_DEBUG(dev, "pg=0x%lx\n", mem->mm_node->start); - dev_priv->engine.instmem.prepare_access(nvbe->dev, true); pte = nouveau_sgdma_pte(nvbe->dev, mem->mm_node->start << PAGE_SHIFT); nvbe->pte_start = pte; for (i = 0; i < nvbe->nr_pages; i++) { @@ -116,24 +115,11 @@ nouveau_sgdma_bind(struct ttm_backend *be, struct ttm_mem_reg *mem) dma_offset += NV_CTXDMA_PAGE_SIZE; } } - dev_priv->engine.instmem.finish_access(nvbe->dev); + dev_priv->engine.instmem.flush(nvbe->dev); if (dev_priv->card_type == NV_50) { - nv_wr32(dev, 0x100c80, 0x00050001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", - nv_rd32(dev, 0x100c80)); - return -EBUSY; - } - - nv_wr32(dev, 0x100c80, 0x00000001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", - nv_rd32(dev, 0x100c80)); - return -EBUSY; - } + nv50_vm_flush(dev, 5); /* PGRAPH */ + nv50_vm_flush(dev, 0); /* PFIFO */ } nvbe->bound = true; @@ -154,7 +140,6 @@ nouveau_sgdma_unbind(struct ttm_backend *be) if (!nvbe->bound) return 0; - dev_priv->engine.instmem.prepare_access(nvbe->dev, true); pte = nvbe->pte_start; for (i = 0; i < nvbe->nr_pages; i++) { dma_addr_t dma_offset = dev_priv->gart_info.sg_dummy_bus; @@ -170,24 +155,11 @@ nouveau_sgdma_unbind(struct ttm_backend *be) dma_offset += NV_CTXDMA_PAGE_SIZE; } } - dev_priv->engine.instmem.finish_access(nvbe->dev); + dev_priv->engine.instmem.flush(nvbe->dev); if (dev_priv->card_type == NV_50) { - nv_wr32(dev, 0x100c80, 0x00050001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", - nv_rd32(dev, 0x100c80)); - return -EBUSY; - } - - nv_wr32(dev, 0x100c80, 0x00000001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", - nv_rd32(dev, 0x100c80)); - return -EBUSY; - } + nv50_vm_flush(dev, 5); + nv50_vm_flush(dev, 0); } nvbe->bound = false; @@ -272,7 +244,6 @@ nouveau_sgdma_init(struct drm_device *dev) pci_map_page(dev->pdev, dev_priv->gart_info.sg_dummy_page, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - dev_priv->engine.instmem.prepare_access(dev, true); if (dev_priv->card_type < NV_50) { /* Maybe use NV_DMA_TARGET_AGP for PCIE? NVIDIA do this, and * confirmed to work on c51. Perhaps means NV_DMA_TARGET_PCIE @@ -294,7 +265,7 @@ nouveau_sgdma_init(struct drm_device *dev) nv_wo32(dev, gpuobj, (i+4)/4, 0); } } - dev_priv->engine.instmem.finish_access(dev); + dev_priv->engine.instmem.flush(dev); dev_priv->gart_info.type = NOUVEAU_GART_SGDMA; dev_priv->gart_info.aper_base = 0; @@ -325,14 +296,11 @@ nouveau_sgdma_get_page(struct drm_device *dev, uint32_t offset, uint32_t *page) { struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_gpuobj *gpuobj = dev_priv->gart_info.sg_ctxdma; - struct nouveau_instmem_engine *instmem = &dev_priv->engine.instmem; int pte; pte = (offset >> NV_CTXDMA_PAGE_SHIFT); if (dev_priv->card_type < NV_50) { - instmem->prepare_access(dev, false); *page = nv_ro32(dev, gpuobj, (pte + 2)) & ~NV_CTXDMA_PAGE_MASK; - instmem->finish_access(dev); return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c index b02a231d693..ee3729e7823 100644 --- a/drivers/gpu/drm/nouveau/nouveau_state.c +++ b/drivers/gpu/drm/nouveau/nouveau_state.c @@ -38,6 +38,7 @@ #include "nv50_display.h" static void nouveau_stub_takedown(struct drm_device *dev) {} +static int nouveau_stub_init(struct drm_device *dev) { return 0; } static int nouveau_init_engine_ptrs(struct drm_device *dev) { @@ -54,8 +55,7 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->instmem.clear = nv04_instmem_clear; engine->instmem.bind = nv04_instmem_bind; engine->instmem.unbind = nv04_instmem_unbind; - engine->instmem.prepare_access = nv04_instmem_prepare_access; - engine->instmem.finish_access = nv04_instmem_finish_access; + engine->instmem.flush = nv04_instmem_flush; engine->mc.init = nv04_mc_init; engine->mc.takedown = nv04_mc_takedown; engine->timer.init = nv04_timer_init; @@ -85,6 +85,16 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->fifo.destroy_context = nv04_fifo_destroy_context; engine->fifo.load_context = nv04_fifo_load_context; engine->fifo.unload_context = nv04_fifo_unload_context; + engine->display.early_init = nv04_display_early_init; + engine->display.late_takedown = nv04_display_late_takedown; + engine->display.create = nv04_display_create; + engine->display.init = nv04_display_init; + engine->display.destroy = nv04_display_destroy; + engine->gpio.init = nouveau_stub_init; + engine->gpio.takedown = nouveau_stub_takedown; + engine->gpio.get = NULL; + engine->gpio.set = NULL; + engine->gpio.irq_enable = NULL; break; case 0x10: engine->instmem.init = nv04_instmem_init; @@ -95,8 +105,7 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->instmem.clear = nv04_instmem_clear; engine->instmem.bind = nv04_instmem_bind; engine->instmem.unbind = nv04_instmem_unbind; - engine->instmem.prepare_access = nv04_instmem_prepare_access; - engine->instmem.finish_access = nv04_instmem_finish_access; + engine->instmem.flush = nv04_instmem_flush; engine->mc.init = nv04_mc_init; engine->mc.takedown = nv04_mc_takedown; engine->timer.init = nv04_timer_init; @@ -128,6 +137,16 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->fifo.destroy_context = nv10_fifo_destroy_context; engine->fifo.load_context = nv10_fifo_load_context; engine->fifo.unload_context = nv10_fifo_unload_context; + engine->display.early_init = nv04_display_early_init; + engine->display.late_takedown = nv04_display_late_takedown; + engine->display.create = nv04_display_create; + engine->display.init = nv04_display_init; + engine->display.destroy = nv04_display_destroy; + engine->gpio.init = nouveau_stub_init; + engine->gpio.takedown = nouveau_stub_takedown; + engine->gpio.get = nv10_gpio_get; + engine->gpio.set = nv10_gpio_set; + engine->gpio.irq_enable = NULL; break; case 0x20: engine->instmem.init = nv04_instmem_init; @@ -138,8 +157,7 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->instmem.clear = nv04_instmem_clear; engine->instmem.bind = nv04_instmem_bind; engine->instmem.unbind = nv04_instmem_unbind; - engine->instmem.prepare_access = nv04_instmem_prepare_access; - engine->instmem.finish_access = nv04_instmem_finish_access; + engine->instmem.flush = nv04_instmem_flush; engine->mc.init = nv04_mc_init; engine->mc.takedown = nv04_mc_takedown; engine->timer.init = nv04_timer_init; @@ -171,6 +189,16 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->fifo.destroy_context = nv10_fifo_destroy_context; engine->fifo.load_context = nv10_fifo_load_context; engine->fifo.unload_context = nv10_fifo_unload_context; + engine->display.early_init = nv04_display_early_init; + engine->display.late_takedown = nv04_display_late_takedown; + engine->display.create = nv04_display_create; + engine->display.init = nv04_display_init; + engine->display.destroy = nv04_display_destroy; + engine->gpio.init = nouveau_stub_init; + engine->gpio.takedown = nouveau_stub_takedown; + engine->gpio.get = nv10_gpio_get; + engine->gpio.set = nv10_gpio_set; + engine->gpio.irq_enable = NULL; break; case 0x30: engine->instmem.init = nv04_instmem_init; @@ -181,15 +209,14 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->instmem.clear = nv04_instmem_clear; engine->instmem.bind = nv04_instmem_bind; engine->instmem.unbind = nv04_instmem_unbind; - engine->instmem.prepare_access = nv04_instmem_prepare_access; - engine->instmem.finish_access = nv04_instmem_finish_access; + engine->instmem.flush = nv04_instmem_flush; engine->mc.init = nv04_mc_init; engine->mc.takedown = nv04_mc_takedown; engine->timer.init = nv04_timer_init; engine->timer.read = nv04_timer_read; engine->timer.takedown = nv04_timer_takedown; - engine->fb.init = nv10_fb_init; - engine->fb.takedown = nv10_fb_takedown; + engine->fb.init = nv30_fb_init; + engine->fb.takedown = nv30_fb_takedown; engine->fb.set_region_tiling = nv10_fb_set_region_tiling; engine->graph.grclass = nv30_graph_grclass; engine->graph.init = nv30_graph_init; @@ -214,6 +241,16 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->fifo.destroy_context = nv10_fifo_destroy_context; engine->fifo.load_context = nv10_fifo_load_context; engine->fifo.unload_context = nv10_fifo_unload_context; + engine->display.early_init = nv04_display_early_init; + engine->display.late_takedown = nv04_display_late_takedown; + engine->display.create = nv04_display_create; + engine->display.init = nv04_display_init; + engine->display.destroy = nv04_display_destroy; + engine->gpio.init = nouveau_stub_init; + engine->gpio.takedown = nouveau_stub_takedown; + engine->gpio.get = nv10_gpio_get; + engine->gpio.set = nv10_gpio_set; + engine->gpio.irq_enable = NULL; break; case 0x40: case 0x60: @@ -225,8 +262,7 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->instmem.clear = nv04_instmem_clear; engine->instmem.bind = nv04_instmem_bind; engine->instmem.unbind = nv04_instmem_unbind; - engine->instmem.prepare_access = nv04_instmem_prepare_access; - engine->instmem.finish_access = nv04_instmem_finish_access; + engine->instmem.flush = nv04_instmem_flush; engine->mc.init = nv40_mc_init; engine->mc.takedown = nv40_mc_takedown; engine->timer.init = nv04_timer_init; @@ -258,6 +294,16 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->fifo.destroy_context = nv40_fifo_destroy_context; engine->fifo.load_context = nv40_fifo_load_context; engine->fifo.unload_context = nv40_fifo_unload_context; + engine->display.early_init = nv04_display_early_init; + engine->display.late_takedown = nv04_display_late_takedown; + engine->display.create = nv04_display_create; + engine->display.init = nv04_display_init; + engine->display.destroy = nv04_display_destroy; + engine->gpio.init = nouveau_stub_init; + engine->gpio.takedown = nouveau_stub_takedown; + engine->gpio.get = nv10_gpio_get; + engine->gpio.set = nv10_gpio_set; + engine->gpio.irq_enable = NULL; break; case 0x50: case 0x80: /* gotta love NVIDIA's consistency.. */ @@ -271,8 +317,10 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->instmem.clear = nv50_instmem_clear; engine->instmem.bind = nv50_instmem_bind; engine->instmem.unbind = nv50_instmem_unbind; - engine->instmem.prepare_access = nv50_instmem_prepare_access; - engine->instmem.finish_access = nv50_instmem_finish_access; + if (dev_priv->chipset == 0x50) + engine->instmem.flush = nv50_instmem_flush; + else + engine->instmem.flush = nv84_instmem_flush; engine->mc.init = nv50_mc_init; engine->mc.takedown = nv50_mc_takedown; engine->timer.init = nv04_timer_init; @@ -300,6 +348,16 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->fifo.destroy_context = nv50_fifo_destroy_context; engine->fifo.load_context = nv50_fifo_load_context; engine->fifo.unload_context = nv50_fifo_unload_context; + engine->display.early_init = nv50_display_early_init; + engine->display.late_takedown = nv50_display_late_takedown; + engine->display.create = nv50_display_create; + engine->display.init = nv50_display_init; + engine->display.destroy = nv50_display_destroy; + engine->gpio.init = nv50_gpio_init; + engine->gpio.takedown = nouveau_stub_takedown; + engine->gpio.get = nv50_gpio_get; + engine->gpio.set = nv50_gpio_set; + engine->gpio.irq_enable = nv50_gpio_irq_enable; break; default: NV_ERROR(dev, "NV%02x unsupported\n", dev_priv->chipset); @@ -407,11 +465,6 @@ nouveau_card_init(struct drm_device *dev) struct nouveau_engine *engine; int ret; - NV_DEBUG(dev, "prev state = %d\n", dev_priv->init_state); - - if (dev_priv->init_state == NOUVEAU_CARD_INIT_DONE) - return 0; - vga_client_register(dev->pdev, dev, NULL, nouveau_vga_set_decode); vga_switcheroo_register_client(dev->pdev, nouveau_switcheroo_set_state, nouveau_switcheroo_can_switch); @@ -421,15 +474,17 @@ nouveau_card_init(struct drm_device *dev) if (ret) goto out; engine = &dev_priv->engine; - dev_priv->init_state = NOUVEAU_CARD_INIT_FAILED; spin_lock_init(&dev_priv->context_switch_lock); + /* Make the CRTCs and I2C buses accessible */ + ret = engine->display.early_init(dev); + if (ret) + goto out; + /* Parse BIOS tables / Run init tables if card not POSTed */ - if (drm_core_check_feature(dev, DRIVER_MODESET)) { - ret = nouveau_bios_init(dev); - if (ret) - goto out; - } + ret = nouveau_bios_init(dev); + if (ret) + goto out_display_early; ret = nouveau_mem_detect(dev); if (ret) @@ -461,10 +516,15 @@ nouveau_card_init(struct drm_device *dev) if (ret) goto out_gpuobj; + /* PGPIO */ + ret = engine->gpio.init(dev); + if (ret) + goto out_mc; + /* PTIMER */ ret = engine->timer.init(dev); if (ret) - goto out_mc; + goto out_gpio; /* PFB */ ret = engine->fb.init(dev); @@ -485,12 +545,16 @@ nouveau_card_init(struct drm_device *dev) goto out_graph; } + ret = engine->display.create(dev); + if (ret) + goto out_fifo; + /* this call irq_preinstall, register irq handler and * call irq_postinstall */ ret = drm_irq_install(dev); if (ret) - goto out_fifo; + goto out_display; ret = drm_vblank_init(dev, 0); if (ret) @@ -504,35 +568,18 @@ nouveau_card_init(struct drm_device *dev) goto out_irq; } - if (drm_core_check_feature(dev, DRIVER_MODESET)) { - if (dev_priv->card_type >= NV_50) - ret = nv50_display_create(dev); - else - ret = nv04_display_create(dev); - if (ret) - goto out_channel; - } - ret = nouveau_backlight_init(dev); if (ret) NV_ERROR(dev, "Error %d registering backlight\n", ret); - dev_priv->init_state = NOUVEAU_CARD_INIT_DONE; - - if (drm_core_check_feature(dev, DRIVER_MODESET)) { - nouveau_fbcon_init(dev); - drm_kms_helper_poll_init(dev); - } - + nouveau_fbcon_init(dev); + drm_kms_helper_poll_init(dev); return 0; -out_channel: - if (dev_priv->channel) { - nouveau_channel_free(dev_priv->channel); - dev_priv->channel = NULL; - } out_irq: drm_irq_uninstall(dev); +out_display: + engine->display.destroy(dev); out_fifo: if (!nouveau_noaccel) engine->fifo.takedown(dev); @@ -543,6 +590,8 @@ out_fb: engine->fb.takedown(dev); out_timer: engine->timer.takedown(dev); +out_gpio: + engine->gpio.takedown(dev); out_mc: engine->mc.takedown(dev); out_gpuobj: @@ -556,6 +605,8 @@ out_gpuobj_early: nouveau_gpuobj_late_takedown(dev); out_bios: nouveau_bios_takedown(dev); +out_display_early: + engine->display.late_takedown(dev); out: vga_client_register(dev->pdev, NULL, NULL, NULL); return ret; @@ -566,45 +617,39 @@ static void nouveau_card_takedown(struct drm_device *dev) struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_engine *engine = &dev_priv->engine; - NV_DEBUG(dev, "prev state = %d\n", dev_priv->init_state); - - if (dev_priv->init_state != NOUVEAU_CARD_INIT_DOWN) { - - nouveau_backlight_exit(dev); - - if (dev_priv->channel) { - nouveau_channel_free(dev_priv->channel); - dev_priv->channel = NULL; - } + nouveau_backlight_exit(dev); - if (!nouveau_noaccel) { - engine->fifo.takedown(dev); - engine->graph.takedown(dev); - } - engine->fb.takedown(dev); - engine->timer.takedown(dev); - engine->mc.takedown(dev); + if (dev_priv->channel) { + nouveau_channel_free(dev_priv->channel); + dev_priv->channel = NULL; + } - mutex_lock(&dev->struct_mutex); - ttm_bo_clean_mm(&dev_priv->ttm.bdev, TTM_PL_VRAM); - ttm_bo_clean_mm(&dev_priv->ttm.bdev, TTM_PL_TT); - mutex_unlock(&dev->struct_mutex); - nouveau_sgdma_takedown(dev); + if (!nouveau_noaccel) { + engine->fifo.takedown(dev); + engine->graph.takedown(dev); + } + engine->fb.takedown(dev); + engine->timer.takedown(dev); + engine->gpio.takedown(dev); + engine->mc.takedown(dev); + engine->display.late_takedown(dev); - nouveau_gpuobj_takedown(dev); - nouveau_mem_close(dev); - engine->instmem.takedown(dev); + mutex_lock(&dev->struct_mutex); + ttm_bo_clean_mm(&dev_priv->ttm.bdev, TTM_PL_VRAM); + ttm_bo_clean_mm(&dev_priv->ttm.bdev, TTM_PL_TT); + mutex_unlock(&dev->struct_mutex); + nouveau_sgdma_takedown(dev); - if (drm_core_check_feature(dev, DRIVER_MODESET)) - drm_irq_uninstall(dev); + nouveau_gpuobj_takedown(dev); + nouveau_mem_close(dev); + engine->instmem.takedown(dev); - nouveau_gpuobj_late_takedown(dev); - nouveau_bios_takedown(dev); + drm_irq_uninstall(dev); - vga_client_register(dev->pdev, NULL, NULL, NULL); + nouveau_gpuobj_late_takedown(dev); + nouveau_bios_takedown(dev); - dev_priv->init_state = NOUVEAU_CARD_INIT_DOWN; - } + vga_client_register(dev->pdev, NULL, NULL, NULL); } /* here a client dies, release the stuff that was allocated for its @@ -691,6 +736,7 @@ int nouveau_load(struct drm_device *dev, unsigned long flags) struct drm_nouveau_private *dev_priv; uint32_t reg0; resource_size_t mmio_start_offs; + int ret; dev_priv = kzalloc(sizeof(*dev_priv), GFP_KERNEL); if (!dev_priv) @@ -699,7 +745,6 @@ int nouveau_load(struct drm_device *dev, unsigned long flags) dev_priv->dev = dev; dev_priv->flags = flags & NOUVEAU_FLAGS; - dev_priv->init_state = NOUVEAU_CARD_INIT_DOWN; NV_DEBUG(dev, "vendor: 0x%X device: 0x%X class: 0x%X\n", dev->pci_vendor, dev->pci_device, dev->pdev->class); @@ -773,11 +818,9 @@ int nouveau_load(struct drm_device *dev, unsigned long flags) NV_INFO(dev, "Detected an NV%2x generation card (0x%08x)\n", dev_priv->card_type, reg0); - if (drm_core_check_feature(dev, DRIVER_MODESET)) { - int ret = nouveau_remove_conflicting_drivers(dev); - if (ret) - return ret; - } + ret = nouveau_remove_conflicting_drivers(dev); + if (ret) + return ret; /* Map PRAMIN BAR, or on older cards, the aperture withing BAR0 */ if (dev_priv->card_type >= NV_40) { @@ -812,46 +855,26 @@ int nouveau_load(struct drm_device *dev, unsigned long flags) dev_priv->flags |= NV_NFORCE2; /* For kernel modesetting, init card now and bring up fbcon */ - if (drm_core_check_feature(dev, DRIVER_MODESET)) { - int ret = nouveau_card_init(dev); - if (ret) - return ret; - } + ret = nouveau_card_init(dev); + if (ret) + return ret; return 0; } -static void nouveau_close(struct drm_device *dev) -{ - struct drm_nouveau_private *dev_priv = dev->dev_private; - - /* In the case of an error dev_priv may not be allocated yet */ - if (dev_priv) - nouveau_card_takedown(dev); -} - -/* KMS: we need mmio at load time, not when the first drm client opens. */ void nouveau_lastclose(struct drm_device *dev) { - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return; - - nouveau_close(dev); } int nouveau_unload(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_engine *engine = &dev_priv->engine; - if (drm_core_check_feature(dev, DRIVER_MODESET)) { - drm_kms_helper_poll_fini(dev); - nouveau_fbcon_fini(dev); - if (dev_priv->card_type >= NV_50) - nv50_display_destroy(dev); - else - nv04_display_destroy(dev); - nouveau_close(dev); - } + drm_kms_helper_poll_fini(dev); + nouveau_fbcon_fini(dev); + engine->display.destroy(dev); + nouveau_card_takedown(dev); iounmap(dev_priv->mmio); iounmap(dev_priv->ramin); @@ -867,8 +890,6 @@ int nouveau_ioctl_getparam(struct drm_device *dev, void *data, struct drm_nouveau_private *dev_priv = dev->dev_private; struct drm_nouveau_getparam *getparam = data; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; - switch (getparam->param) { case NOUVEAU_GETPARAM_CHIPSET_ID: getparam->value = dev_priv->chipset; @@ -937,8 +958,6 @@ nouveau_ioctl_setparam(struct drm_device *dev, void *data, { struct drm_nouveau_setparam *setparam = data; - NOUVEAU_CHECK_INITIALISED_WITH_RETURN; - switch (setparam->param) { default: NV_ERROR(dev, "unknown parameter %lld\n", setparam->param); diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index c385d50f041..bd35f930568 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -42,13 +42,13 @@ nouveau_ttm_mmap(struct file *filp, struct vm_area_struct *vma) } static int -nouveau_ttm_mem_global_init(struct ttm_global_reference *ref) +nouveau_ttm_mem_global_init(struct drm_global_reference *ref) { return ttm_mem_global_init(ref->object); } static void -nouveau_ttm_mem_global_release(struct ttm_global_reference *ref) +nouveau_ttm_mem_global_release(struct drm_global_reference *ref) { ttm_mem_global_release(ref->object); } @@ -56,16 +56,16 @@ nouveau_ttm_mem_global_release(struct ttm_global_reference *ref) int nouveau_ttm_global_init(struct drm_nouveau_private *dev_priv) { - struct ttm_global_reference *global_ref; + struct drm_global_reference *global_ref; int ret; global_ref = &dev_priv->ttm.mem_global_ref; - global_ref->global_type = TTM_GLOBAL_TTM_MEM; + global_ref->global_type = DRM_GLOBAL_TTM_MEM; global_ref->size = sizeof(struct ttm_mem_global); global_ref->init = &nouveau_ttm_mem_global_init; global_ref->release = &nouveau_ttm_mem_global_release; - ret = ttm_global_item_ref(global_ref); + ret = drm_global_item_ref(global_ref); if (unlikely(ret != 0)) { DRM_ERROR("Failed setting up TTM memory accounting\n"); dev_priv->ttm.mem_global_ref.release = NULL; @@ -74,15 +74,15 @@ nouveau_ttm_global_init(struct drm_nouveau_private *dev_priv) dev_priv->ttm.bo_global_ref.mem_glob = global_ref->object; global_ref = &dev_priv->ttm.bo_global_ref.ref; - global_ref->global_type = TTM_GLOBAL_TTM_BO; + global_ref->global_type = DRM_GLOBAL_TTM_BO; global_ref->size = sizeof(struct ttm_bo_global); global_ref->init = &ttm_bo_global_init; global_ref->release = &ttm_bo_global_release; - ret = ttm_global_item_ref(global_ref); + ret = drm_global_item_ref(global_ref); if (unlikely(ret != 0)) { DRM_ERROR("Failed setting up TTM BO subsystem\n"); - ttm_global_item_unref(&dev_priv->ttm.mem_global_ref); + drm_global_item_unref(&dev_priv->ttm.mem_global_ref); dev_priv->ttm.mem_global_ref.release = NULL; return ret; } @@ -96,8 +96,8 @@ nouveau_ttm_global_release(struct drm_nouveau_private *dev_priv) if (dev_priv->ttm.mem_global_ref.release == NULL) return; - ttm_global_item_unref(&dev_priv->ttm.bo_global_ref.ref); - ttm_global_item_unref(&dev_priv->ttm.mem_global_ref); + drm_global_item_unref(&dev_priv->ttm.bo_global_ref.ref); + drm_global_item_unref(&dev_priv->ttm.mem_global_ref); dev_priv->ttm.mem_global_ref.release = NULL; } diff --git a/drivers/gpu/drm/nouveau/nv04_crtc.c b/drivers/gpu/drm/nouveau/nv04_crtc.c index eba687f1099..1c20c08ce67 100644 --- a/drivers/gpu/drm/nouveau/nv04_crtc.c +++ b/drivers/gpu/drm/nouveau/nv04_crtc.c @@ -157,6 +157,7 @@ nv_crtc_dpms(struct drm_crtc *crtc, int mode) { struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); struct drm_device *dev = crtc->dev; + struct drm_connector *connector; unsigned char seq1 = 0, crtc17 = 0; unsigned char crtc1A; @@ -211,6 +212,10 @@ nv_crtc_dpms(struct drm_crtc *crtc, int mode) NVVgaSeqReset(dev, nv_crtc->index, false); NVWriteVgaCrtc(dev, nv_crtc->index, NV_CIO_CRE_RPC1_INDEX, crtc1A); + + /* Update connector polling modes */ + list_for_each_entry(connector, &dev->mode_config.connector_list, head) + nouveau_connector_set_polling(connector); } static bool diff --git a/drivers/gpu/drm/nouveau/nv04_dac.c b/drivers/gpu/drm/nouveau/nv04_dac.c index 1cb19e3acb5..ea3627041ec 100644 --- a/drivers/gpu/drm/nouveau/nv04_dac.c +++ b/drivers/gpu/drm/nouveau/nv04_dac.c @@ -220,6 +220,7 @@ uint32_t nv17_dac_sample_load(struct drm_encoder *encoder) { struct drm_device *dev = encoder->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_gpio_engine *gpio = &dev_priv->engine.gpio; struct dcb_entry *dcb = nouveau_encoder(encoder)->dcb; uint32_t sample, testval, regoffset = nv04_dac_output_offset(encoder); uint32_t saved_powerctrl_2 = 0, saved_powerctrl_4 = 0, saved_routput, @@ -251,22 +252,21 @@ uint32_t nv17_dac_sample_load(struct drm_encoder *encoder) nvWriteMC(dev, NV_PBUS_POWERCTRL_4, saved_powerctrl_4 & 0xffffffcf); } - saved_gpio1 = nv17_gpio_get(dev, DCB_GPIO_TVDAC1); - saved_gpio0 = nv17_gpio_get(dev, DCB_GPIO_TVDAC0); + saved_gpio1 = gpio->get(dev, DCB_GPIO_TVDAC1); + saved_gpio0 = gpio->get(dev, DCB_GPIO_TVDAC0); - nv17_gpio_set(dev, DCB_GPIO_TVDAC1, dcb->type == OUTPUT_TV); - nv17_gpio_set(dev, DCB_GPIO_TVDAC0, dcb->type == OUTPUT_TV); + gpio->set(dev, DCB_GPIO_TVDAC1, dcb->type == OUTPUT_TV); + gpio->set(dev, DCB_GPIO_TVDAC0, dcb->type == OUTPUT_TV); msleep(4); saved_routput = NVReadRAMDAC(dev, 0, NV_PRAMDAC_DACCLK + regoffset); head = (saved_routput & 0x100) >> 8; -#if 0 - /* if there's a spare crtc, using it will minimise flicker for the case - * where the in-use crtc is in use by an off-chip tmds encoder */ - if (xf86_config->crtc[head]->enabled && !xf86_config->crtc[head ^ 1]->enabled) + + /* if there's a spare crtc, using it will minimise flicker */ + if (!(NVReadVgaCrtc(dev, head, NV_CIO_CRE_RPC1_INDEX) & 0xC0)) head ^= 1; -#endif + /* nv driver and nv31 use 0xfffffeee, nv34 and 6600 use 0xfffffece */ routput = (saved_routput & 0xfffffece) | head << 8; @@ -304,8 +304,8 @@ uint32_t nv17_dac_sample_load(struct drm_encoder *encoder) nvWriteMC(dev, NV_PBUS_POWERCTRL_4, saved_powerctrl_4); nvWriteMC(dev, NV_PBUS_POWERCTRL_2, saved_powerctrl_2); - nv17_gpio_set(dev, DCB_GPIO_TVDAC1, saved_gpio1); - nv17_gpio_set(dev, DCB_GPIO_TVDAC0, saved_gpio0); + gpio->set(dev, DCB_GPIO_TVDAC1, saved_gpio1); + gpio->set(dev, DCB_GPIO_TVDAC0, saved_gpio0); return sample; } @@ -315,9 +315,12 @@ nv17_dac_detect(struct drm_encoder *encoder, struct drm_connector *connector) { struct drm_device *dev = encoder->dev; struct dcb_entry *dcb = nouveau_encoder(encoder)->dcb; - uint32_t sample = nv17_dac_sample_load(encoder); - if (sample & NV_PRAMDAC_TEST_CONTROL_SENSEB_ALLHI) { + if (nv04_dac_in_use(encoder)) + return connector_status_disconnected; + + if (nv17_dac_sample_load(encoder) & + NV_PRAMDAC_TEST_CONTROL_SENSEB_ALLHI) { NV_INFO(dev, "Load detected on output %c\n", '@' + ffs(dcb->or)); return connector_status_connected; @@ -330,6 +333,9 @@ static bool nv04_dac_mode_fixup(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) { + if (nv04_dac_in_use(encoder)) + return false; + return true; } @@ -428,6 +434,17 @@ void nv04_dac_update_dacclk(struct drm_encoder *encoder, bool enable) } } +/* Check if the DAC corresponding to 'encoder' is being used by + * someone else. */ +bool nv04_dac_in_use(struct drm_encoder *encoder) +{ + struct drm_nouveau_private *dev_priv = encoder->dev->dev_private; + struct dcb_entry *dcb = nouveau_encoder(encoder)->dcb; + + return nv_gf4_disp_arch(encoder->dev) && + (dev_priv->dac_users[ffs(dcb->or) - 1] & ~(1 << dcb->index)); +} + static void nv04_dac_dpms(struct drm_encoder *encoder, int mode) { struct drm_device *dev = encoder->dev; @@ -501,11 +518,13 @@ static const struct drm_encoder_funcs nv04_dac_funcs = { .destroy = nv04_dac_destroy, }; -int nv04_dac_create(struct drm_device *dev, struct dcb_entry *entry) +int +nv04_dac_create(struct drm_connector *connector, struct dcb_entry *entry) { const struct drm_encoder_helper_funcs *helper; - struct drm_encoder *encoder; struct nouveau_encoder *nv_encoder = NULL; + struct drm_device *dev = connector->dev; + struct drm_encoder *encoder; nv_encoder = kzalloc(sizeof(*nv_encoder), GFP_KERNEL); if (!nv_encoder) @@ -527,5 +546,6 @@ int nv04_dac_create(struct drm_device *dev, struct dcb_entry *entry) encoder->possible_crtcs = entry->heads; encoder->possible_clones = 0; + drm_mode_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/nouveau/nv04_dfp.c b/drivers/gpu/drm/nouveau/nv04_dfp.c index 41634d4752f..3311f3a8c81 100644 --- a/drivers/gpu/drm/nouveau/nv04_dfp.c +++ b/drivers/gpu/drm/nouveau/nv04_dfp.c @@ -413,10 +413,6 @@ static void nv04_dfp_commit(struct drm_encoder *encoder) struct dcb_entry *dcbe = nv_encoder->dcb; int head = nouveau_crtc(encoder->crtc)->index; - NV_INFO(dev, "Output %s is running on CRTC %d using output %c\n", - drm_get_connector_name(&nouveau_encoder_connector_get(nv_encoder)->base), - nv_crtc->index, '@' + ffs(nv_encoder->dcb->or)); - if (dcbe->type == OUTPUT_TMDS) run_tmds_table(dev, dcbe, head, nv_encoder->mode.clock); else if (dcbe->type == OUTPUT_LVDS) @@ -584,11 +580,12 @@ static const struct drm_encoder_funcs nv04_dfp_funcs = { .destroy = nv04_dfp_destroy, }; -int nv04_dfp_create(struct drm_device *dev, struct dcb_entry *entry) +int +nv04_dfp_create(struct drm_connector *connector, struct dcb_entry *entry) { const struct drm_encoder_helper_funcs *helper; - struct drm_encoder *encoder; struct nouveau_encoder *nv_encoder = NULL; + struct drm_encoder *encoder; int type; switch (entry->type) { @@ -613,11 +610,12 @@ int nv04_dfp_create(struct drm_device *dev, struct dcb_entry *entry) nv_encoder->dcb = entry; nv_encoder->or = ffs(entry->or) - 1; - drm_encoder_init(dev, encoder, &nv04_dfp_funcs, type); + drm_encoder_init(connector->dev, encoder, &nv04_dfp_funcs, type); drm_encoder_helper_add(encoder, helper); encoder->possible_crtcs = entry->heads; encoder->possible_clones = 0; + drm_mode_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/nouveau/nv04_display.c b/drivers/gpu/drm/nouveau/nv04_display.c index c7898b4f6df..9e28cf772e3 100644 --- a/drivers/gpu/drm/nouveau/nv04_display.c +++ b/drivers/gpu/drm/nouveau/nv04_display.c @@ -32,8 +32,6 @@ #include "nouveau_encoder.h" #include "nouveau_connector.h" -#define MULTIPLE_ENCODERS(e) (e & (e - 1)) - static void nv04_display_store_initial_head_owner(struct drm_device *dev) { @@ -41,7 +39,7 @@ nv04_display_store_initial_head_owner(struct drm_device *dev) if (dev_priv->chipset != 0x11) { dev_priv->crtc_owner = NVReadVgaCrtc(dev, 0, NV_CIO_CRE_44); - goto ownerknown; + return; } /* reading CR44 is broken on nv11, so we attempt to infer it */ @@ -52,8 +50,6 @@ nv04_display_store_initial_head_owner(struct drm_device *dev) bool tvA = false; bool tvB = false; - NVLockVgaCrtcs(dev, false); - slaved_on_B = NVReadVgaCrtc(dev, 1, NV_CIO_CRE_PIXEL_INDEX) & 0x80; if (slaved_on_B) @@ -66,8 +62,6 @@ nv04_display_store_initial_head_owner(struct drm_device *dev) tvA = !(NVReadVgaCrtc(dev, 0, NV_CIO_CRE_LCD__INDEX) & MASK(NV_CIO_CRE_LCD_LCD_SELECT)); - NVLockVgaCrtcs(dev, true); - if (slaved_on_A && !tvA) dev_priv->crtc_owner = 0x0; else if (slaved_on_B && !tvB) @@ -79,14 +73,40 @@ nv04_display_store_initial_head_owner(struct drm_device *dev) else dev_priv->crtc_owner = 0x0; } +} + +int +nv04_display_early_init(struct drm_device *dev) +{ + /* Make the I2C buses accessible. */ + if (!nv_gf4_disp_arch(dev)) { + uint32_t pmc_enable = nv_rd32(dev, NV03_PMC_ENABLE); + + if (!(pmc_enable & 1)) + nv_wr32(dev, NV03_PMC_ENABLE, pmc_enable | 1); + } -ownerknown: - NV_INFO(dev, "Initial CRTC_OWNER is %d\n", dev_priv->crtc_owner); + /* Unlock the VGA CRTCs. */ + NVLockVgaCrtcs(dev, false); + + /* Make sure the CRTCs aren't in slaved mode. */ + if (nv_two_heads(dev)) { + nv04_display_store_initial_head_owner(dev); + NVSetOwner(dev, 0); + } + + return 0; +} + +void +nv04_display_late_takedown(struct drm_device *dev) +{ + struct drm_nouveau_private *dev_priv = dev->dev_private; + + if (nv_two_heads(dev)) + NVSetOwner(dev, dev_priv->crtc_owner); - /* we need to ensure the heads are not tied henceforth, or reading any - * 8 bit reg on head B will fail - * setting a single arbitrary head solves that */ - NVSetOwner(dev, 0); + NVLockVgaCrtcs(dev, true); } int @@ -94,14 +114,13 @@ nv04_display_create(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; struct dcb_table *dcb = &dev_priv->vbios.dcb; + struct drm_connector *connector, *ct; struct drm_encoder *encoder; struct drm_crtc *crtc; int i, ret; NV_DEBUG_KMS(dev, "\n"); - if (nv_two_heads(dev)) - nv04_display_store_initial_head_owner(dev); nouveau_hw_save_vga_fonts(dev, 1); drm_mode_config_init(dev); @@ -132,19 +151,23 @@ nv04_display_create(struct drm_device *dev) for (i = 0; i < dcb->entries; i++) { struct dcb_entry *dcbent = &dcb->entry[i]; + connector = nouveau_connector_create(dev, dcbent->connector); + if (IS_ERR(connector)) + continue; + switch (dcbent->type) { case OUTPUT_ANALOG: - ret = nv04_dac_create(dev, dcbent); + ret = nv04_dac_create(connector, dcbent); break; case OUTPUT_LVDS: case OUTPUT_TMDS: - ret = nv04_dfp_create(dev, dcbent); + ret = nv04_dfp_create(connector, dcbent); break; case OUTPUT_TV: if (dcbent->location == DCB_LOC_ON_CHIP) - ret = nv17_tv_create(dev, dcbent); + ret = nv17_tv_create(connector, dcbent); else - ret = nv04_tv_create(dev, dcbent); + ret = nv04_tv_create(connector, dcbent); break; default: NV_WARN(dev, "DCB type %d not known\n", dcbent->type); @@ -155,12 +178,16 @@ nv04_display_create(struct drm_device *dev) continue; } - for (i = 0; i < dcb->connector.entries; i++) - nouveau_connector_create(dev, &dcb->connector.entry[i]); + list_for_each_entry_safe(connector, ct, + &dev->mode_config.connector_list, head) { + if (!connector->encoder_ids[0]) { + NV_WARN(dev, "%s has no encoders, removing\n", + drm_get_connector_name(connector)); + connector->funcs->destroy(connector); + } + } /* Save previous state */ - NVLockVgaCrtcs(dev, false); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) crtc->funcs->save(crtc); @@ -191,8 +218,6 @@ nv04_display_destroy(struct drm_device *dev) } /* Restore state */ - NVLockVgaCrtcs(dev, false); - list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { struct drm_encoder_helper_funcs *func = encoder->helper_private; @@ -207,15 +232,12 @@ nv04_display_destroy(struct drm_device *dev) nouveau_hw_save_vga_fonts(dev, 0); } -void -nv04_display_restore(struct drm_device *dev) +int +nv04_display_init(struct drm_device *dev) { - struct drm_nouveau_private *dev_priv = dev->dev_private; struct drm_encoder *encoder; struct drm_crtc *crtc; - NVLockVgaCrtcs(dev, false); - /* meh.. modeset apparently doesn't setup all the regs and depends * on pre-existing state, for now load the state of the card *before* * nouveau was loaded, and then do a modeset. @@ -233,12 +255,6 @@ nv04_display_restore(struct drm_device *dev) list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) crtc->funcs->restore(crtc); - if (nv_two_heads(dev)) { - NV_INFO(dev, "Restoring CRTC_OWNER to %d.\n", - dev_priv->crtc_owner); - NVSetOwner(dev, dev_priv->crtc_owner); - } - - NVLockVgaCrtcs(dev, true); + return 0; } diff --git a/drivers/gpu/drm/nouveau/nv04_fifo.c b/drivers/gpu/drm/nouveau/nv04_fifo.c index 66fe55983b6..06cedd99c26 100644 --- a/drivers/gpu/drm/nouveau/nv04_fifo.c +++ b/drivers/gpu/drm/nouveau/nv04_fifo.c @@ -112,6 +112,12 @@ nv04_fifo_channel_id(struct drm_device *dev) NV03_PFIFO_CACHE1_PUSH1_CHID_MASK; } +#ifdef __BIG_ENDIAN +#define DMA_FETCH_ENDIANNESS NV_PFIFO_CACHE1_BIG_ENDIAN +#else +#define DMA_FETCH_ENDIANNESS 0 +#endif + int nv04_fifo_create_context(struct nouveau_channel *chan) { @@ -131,18 +137,13 @@ nv04_fifo_create_context(struct nouveau_channel *chan) spin_lock_irqsave(&dev_priv->context_switch_lock, flags); /* Setup initial state */ - dev_priv->engine.instmem.prepare_access(dev, true); RAMFC_WR(DMA_PUT, chan->pushbuf_base); RAMFC_WR(DMA_GET, chan->pushbuf_base); RAMFC_WR(DMA_INSTANCE, chan->pushbuf->instance >> 4); RAMFC_WR(DMA_FETCH, (NV_PFIFO_CACHE1_DMA_FETCH_TRIG_128_BYTES | NV_PFIFO_CACHE1_DMA_FETCH_SIZE_128_BYTES | NV_PFIFO_CACHE1_DMA_FETCH_MAX_REQS_8 | -#ifdef __BIG_ENDIAN - NV_PFIFO_CACHE1_BIG_ENDIAN | -#endif - 0)); - dev_priv->engine.instmem.finish_access(dev); + DMA_FETCH_ENDIANNESS)); /* enable the fifo dma operation */ nv_wr32(dev, NV04_PFIFO_MODE, @@ -169,8 +170,6 @@ nv04_fifo_do_load_context(struct drm_device *dev, int chid) struct drm_nouveau_private *dev_priv = dev->dev_private; uint32_t fc = NV04_RAMFC(chid), tmp; - dev_priv->engine.instmem.prepare_access(dev, false); - nv_wr32(dev, NV04_PFIFO_CACHE1_DMA_PUT, nv_ri32(dev, fc + 0)); nv_wr32(dev, NV04_PFIFO_CACHE1_DMA_GET, nv_ri32(dev, fc + 4)); tmp = nv_ri32(dev, fc + 8); @@ -181,8 +180,6 @@ nv04_fifo_do_load_context(struct drm_device *dev, int chid) nv_wr32(dev, NV04_PFIFO_CACHE1_ENGINE, nv_ri32(dev, fc + 20)); nv_wr32(dev, NV04_PFIFO_CACHE1_PULL1, nv_ri32(dev, fc + 24)); - dev_priv->engine.instmem.finish_access(dev); - nv_wr32(dev, NV03_PFIFO_CACHE1_GET, 0); nv_wr32(dev, NV03_PFIFO_CACHE1_PUT, 0); } @@ -223,7 +220,6 @@ nv04_fifo_unload_context(struct drm_device *dev) return -EINVAL; } - dev_priv->engine.instmem.prepare_access(dev, true); RAMFC_WR(DMA_PUT, nv_rd32(dev, NV04_PFIFO_CACHE1_DMA_PUT)); RAMFC_WR(DMA_GET, nv_rd32(dev, NV04_PFIFO_CACHE1_DMA_GET)); tmp = nv_rd32(dev, NV04_PFIFO_CACHE1_DMA_DCOUNT) << 16; @@ -233,7 +229,6 @@ nv04_fifo_unload_context(struct drm_device *dev) RAMFC_WR(DMA_FETCH, nv_rd32(dev, NV04_PFIFO_CACHE1_DMA_FETCH)); RAMFC_WR(ENGINE, nv_rd32(dev, NV04_PFIFO_CACHE1_ENGINE)); RAMFC_WR(PULL1_ENGINE, nv_rd32(dev, NV04_PFIFO_CACHE1_PULL1)); - dev_priv->engine.instmem.finish_access(dev); nv04_fifo_do_load_context(dev, pfifo->channels - 1); nv_wr32(dev, NV03_PFIFO_CACHE1_PUSH1, pfifo->channels - 1); @@ -297,6 +292,7 @@ nv04_fifo_init(struct drm_device *dev) nv04_fifo_init_intr(dev); pfifo->enable(dev); + pfifo->reassign(dev, true); for (i = 0; i < dev_priv->engine.fifo.channels; i++) { if (dev_priv->fifos[i]) { diff --git a/drivers/gpu/drm/nouveau/nv04_graph.c b/drivers/gpu/drm/nouveau/nv04_graph.c index 618355e9cdd..c8973421b63 100644 --- a/drivers/gpu/drm/nouveau/nv04_graph.c +++ b/drivers/gpu/drm/nouveau/nv04_graph.c @@ -342,7 +342,7 @@ static uint32_t nv04_graph_ctx_regs[] = { }; struct graph_state { - int nv04[ARRAY_SIZE(nv04_graph_ctx_regs)]; + uint32_t nv04[ARRAY_SIZE(nv04_graph_ctx_regs)]; }; struct nouveau_channel * @@ -527,8 +527,7 @@ static int nv04_graph_mthd_set_ref(struct nouveau_channel *chan, int grclass, int mthd, uint32_t data) { - chan->fence.last_sequence_irq = data; - nouveau_fence_handler(chan->dev, chan->id); + atomic_set(&chan->fence.last_sequence_irq, data); return 0; } diff --git a/drivers/gpu/drm/nouveau/nv04_instmem.c b/drivers/gpu/drm/nouveau/nv04_instmem.c index a3b9563a6f6..4408232d33f 100644 --- a/drivers/gpu/drm/nouveau/nv04_instmem.c +++ b/drivers/gpu/drm/nouveau/nv04_instmem.c @@ -49,10 +49,8 @@ nv04_instmem_determine_amount(struct drm_device *dev) NV_DEBUG(dev, "RAMIN size: %dKiB\n", dev_priv->ramin_rsvd_vram >> 10); /* Clear all of it, except the BIOS image that's in the first 64KiB */ - dev_priv->engine.instmem.prepare_access(dev, true); for (i = 64 * 1024; i < dev_priv->ramin_rsvd_vram; i += 4) nv_wi32(dev, i, 0x00000000); - dev_priv->engine.instmem.finish_access(dev); } static void @@ -106,7 +104,7 @@ int nv04_instmem_init(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; uint32_t offset; - int ret = 0; + int ret; nv04_instmem_determine_amount(dev); nv04_instmem_configure_fixed_tables(dev); @@ -129,14 +127,14 @@ int nv04_instmem_init(struct drm_device *dev) offset = 0x40000; } - ret = nouveau_mem_init_heap(&dev_priv->ramin_heap, - offset, dev_priv->ramin_rsvd_vram - offset); + ret = drm_mm_init(&dev_priv->ramin_heap, offset, + dev_priv->ramin_rsvd_vram - offset); if (ret) { - dev_priv->ramin_heap = NULL; - NV_ERROR(dev, "Failed to init RAMIN heap\n"); + NV_ERROR(dev, "Failed to init RAMIN heap: %d\n", ret); + return ret; } - return ret; + return 0; } void @@ -186,12 +184,7 @@ nv04_instmem_unbind(struct drm_device *dev, struct nouveau_gpuobj *gpuobj) } void -nv04_instmem_prepare_access(struct drm_device *dev, bool write) -{ -} - -void -nv04_instmem_finish_access(struct drm_device *dev) +nv04_instmem_flush(struct drm_device *dev) { } diff --git a/drivers/gpu/drm/nouveau/nv04_mc.c b/drivers/gpu/drm/nouveau/nv04_mc.c index 617ed1e0526..2af43a1cb2e 100644 --- a/drivers/gpu/drm/nouveau/nv04_mc.c +++ b/drivers/gpu/drm/nouveau/nv04_mc.c @@ -11,6 +11,10 @@ nv04_mc_init(struct drm_device *dev) */ nv_wr32(dev, NV03_PMC_ENABLE, 0xFFFFFFFF); + + /* Disable PROM access. */ + nv_wr32(dev, NV_PBUS_PCI_NV_20, NV_PBUS_PCI_NV_20_ROM_SHADOW_ENABLED); + return 0; } diff --git a/drivers/gpu/drm/nouveau/nv04_tv.c b/drivers/gpu/drm/nouveau/nv04_tv.c index c4e3404337d..94e299cef0b 100644 --- a/drivers/gpu/drm/nouveau/nv04_tv.c +++ b/drivers/gpu/drm/nouveau/nv04_tv.c @@ -34,69 +34,26 @@ #include "i2c/ch7006.h" -static struct { - struct i2c_board_info board_info; - struct drm_encoder_funcs funcs; - struct drm_encoder_helper_funcs hfuncs; - void *params; - -} nv04_tv_encoder_info[] = { +static struct i2c_board_info nv04_tv_encoder_info[] = { { - .board_info = { I2C_BOARD_INFO("ch7006", 0x75) }, - .params = &(struct ch7006_encoder_params) { + I2C_BOARD_INFO("ch7006", 0x75), + .platform_data = &(struct ch7006_encoder_params) { CH7006_FORMAT_RGB24m12I, CH7006_CLOCK_MASTER, 0, 0, 0, CH7006_SYNC_SLAVE, CH7006_SYNC_SEPARATED, CH7006_POUT_3_3V, CH7006_ACTIVE_HSYNC - }, + } }, + { } }; -static bool probe_i2c_addr(struct i2c_adapter *adapter, int addr) -{ - struct i2c_msg msg = { - .addr = addr, - .len = 0, - }; - - return i2c_transfer(adapter, &msg, 1) == 1; -} - int nv04_tv_identify(struct drm_device *dev, int i2c_index) { - struct nouveau_i2c_chan *i2c; - bool was_locked; - int i, ret; - - NV_TRACE(dev, "Probing TV encoders on I2C bus: %d\n", i2c_index); - - i2c = nouveau_i2c_find(dev, i2c_index); - if (!i2c) - return -ENODEV; - - was_locked = NVLockVgaCrtcs(dev, false); - - for (i = 0; i < ARRAY_SIZE(nv04_tv_encoder_info); i++) { - if (probe_i2c_addr(&i2c->adapter, - nv04_tv_encoder_info[i].board_info.addr)) { - ret = i; - break; - } - } - - if (i < ARRAY_SIZE(nv04_tv_encoder_info)) { - NV_TRACE(dev, "Detected TV encoder: %s\n", - nv04_tv_encoder_info[i].board_info.type); - - } else { - NV_TRACE(dev, "No TV encoders found.\n"); - i = -ENODEV; - } - - NVLockVgaCrtcs(dev, was_locked); - return i; + return nouveau_i2c_identify(dev, "TV encoder", + nv04_tv_encoder_info, i2c_index); } + #define PLLSEL_TV_CRTC1_MASK \ (NV_PRAMDAC_PLL_COEFF_SELECT_TV_VSCLK1 \ | NV_PRAMDAC_PLL_COEFF_SELECT_TV_PCLK1) @@ -214,30 +171,32 @@ static void nv04_tv_commit(struct drm_encoder *encoder) static void nv04_tv_destroy(struct drm_encoder *encoder) { - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - to_encoder_slave(encoder)->slave_funcs->destroy(encoder); drm_encoder_cleanup(encoder); - kfree(nv_encoder); + kfree(encoder->helper_private); + kfree(nouveau_encoder(encoder)); } -int nv04_tv_create(struct drm_device *dev, struct dcb_entry *entry) +static const struct drm_encoder_funcs nv04_tv_funcs = { + .destroy = nv04_tv_destroy, +}; + +int +nv04_tv_create(struct drm_connector *connector, struct dcb_entry *entry) { struct nouveau_encoder *nv_encoder; struct drm_encoder *encoder; - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct i2c_adapter *adap; - struct drm_encoder_funcs *funcs = NULL; - struct drm_encoder_helper_funcs *hfuncs = NULL; - struct drm_encoder_slave_funcs *sfuncs = NULL; - int i2c_index = entry->i2c_index; + struct drm_device *dev = connector->dev; + struct drm_encoder_helper_funcs *hfuncs; + struct drm_encoder_slave_funcs *sfuncs; + struct nouveau_i2c_chan *i2c = + nouveau_i2c_find(dev, entry->i2c_index); int type, ret; - bool was_locked; /* Ensure that we can talk to this encoder */ - type = nv04_tv_identify(dev, i2c_index); + type = nv04_tv_identify(dev, entry->i2c_index); if (type < 0) return type; @@ -246,41 +205,32 @@ int nv04_tv_create(struct drm_device *dev, struct dcb_entry *entry) if (!nv_encoder) return -ENOMEM; + hfuncs = kzalloc(sizeof(*hfuncs), GFP_KERNEL); + if (!hfuncs) { + ret = -ENOMEM; + goto fail_free; + } + /* Initialize the common members */ encoder = to_drm_encoder(nv_encoder); - funcs = &nv04_tv_encoder_info[type].funcs; - hfuncs = &nv04_tv_encoder_info[type].hfuncs; - - drm_encoder_init(dev, encoder, funcs, DRM_MODE_ENCODER_TVDAC); + drm_encoder_init(dev, encoder, &nv04_tv_funcs, DRM_MODE_ENCODER_TVDAC); drm_encoder_helper_add(encoder, hfuncs); encoder->possible_crtcs = entry->heads; encoder->possible_clones = 0; - nv_encoder->dcb = entry; nv_encoder->or = ffs(entry->or) - 1; /* Run the slave-specific initialization */ - adap = &dev_priv->vbios.dcb.i2c[i2c_index].chan->adapter; - - was_locked = NVLockVgaCrtcs(dev, false); - - ret = drm_i2c_encoder_init(encoder->dev, to_encoder_slave(encoder), adap, - &nv04_tv_encoder_info[type].board_info); - - NVLockVgaCrtcs(dev, was_locked); - + ret = drm_i2c_encoder_init(dev, to_encoder_slave(encoder), + &i2c->adapter, &nv04_tv_encoder_info[type]); if (ret < 0) - goto fail; + goto fail_cleanup; /* Fill the function pointers */ sfuncs = to_encoder_slave(encoder)->slave_funcs; - *funcs = (struct drm_encoder_funcs) { - .destroy = nv04_tv_destroy, - }; - *hfuncs = (struct drm_encoder_helper_funcs) { .dpms = nv04_tv_dpms, .save = sfuncs->save, @@ -292,14 +242,17 @@ int nv04_tv_create(struct drm_device *dev, struct dcb_entry *entry) .detect = sfuncs->detect, }; - /* Set the slave encoder configuration */ - sfuncs->set_config(encoder, nv04_tv_encoder_info[type].params); + /* Attach it to the specified connector. */ + sfuncs->set_config(encoder, nv04_tv_encoder_info[type].platform_data); + sfuncs->create_resources(encoder, connector); + drm_mode_connector_attach_encoder(connector, encoder); return 0; -fail: +fail_cleanup: drm_encoder_cleanup(encoder); - + kfree(hfuncs); +fail_free: kfree(nv_encoder); return ret; } diff --git a/drivers/gpu/drm/nouveau/nv10_fifo.c b/drivers/gpu/drm/nouveau/nv10_fifo.c index 7aeabf262bc..7a4069cf5d0 100644 --- a/drivers/gpu/drm/nouveau/nv10_fifo.c +++ b/drivers/gpu/drm/nouveau/nv10_fifo.c @@ -55,7 +55,6 @@ nv10_fifo_create_context(struct nouveau_channel *chan) /* Fill entries that are seen filled in dumps of nvidia driver just * after channel's is put into DMA mode */ - dev_priv->engine.instmem.prepare_access(dev, true); nv_wi32(dev, fc + 0, chan->pushbuf_base); nv_wi32(dev, fc + 4, chan->pushbuf_base); nv_wi32(dev, fc + 12, chan->pushbuf->instance >> 4); @@ -66,7 +65,6 @@ nv10_fifo_create_context(struct nouveau_channel *chan) NV_PFIFO_CACHE1_BIG_ENDIAN | #endif 0); - dev_priv->engine.instmem.finish_access(dev); /* enable the fifo dma operation */ nv_wr32(dev, NV04_PFIFO_MODE, @@ -91,8 +89,6 @@ nv10_fifo_do_load_context(struct drm_device *dev, int chid) struct drm_nouveau_private *dev_priv = dev->dev_private; uint32_t fc = NV10_RAMFC(chid), tmp; - dev_priv->engine.instmem.prepare_access(dev, false); - nv_wr32(dev, NV04_PFIFO_CACHE1_DMA_PUT, nv_ri32(dev, fc + 0)); nv_wr32(dev, NV04_PFIFO_CACHE1_DMA_GET, nv_ri32(dev, fc + 4)); nv_wr32(dev, NV10_PFIFO_CACHE1_REF_CNT, nv_ri32(dev, fc + 8)); @@ -117,8 +113,6 @@ nv10_fifo_do_load_context(struct drm_device *dev, int chid) nv_wr32(dev, NV10_PFIFO_CACHE1_DMA_SUBROUTINE, nv_ri32(dev, fc + 48)); out: - dev_priv->engine.instmem.finish_access(dev); - nv_wr32(dev, NV03_PFIFO_CACHE1_GET, 0); nv_wr32(dev, NV03_PFIFO_CACHE1_PUT, 0); } @@ -155,8 +149,6 @@ nv10_fifo_unload_context(struct drm_device *dev) return 0; fc = NV10_RAMFC(chid); - dev_priv->engine.instmem.prepare_access(dev, true); - nv_wi32(dev, fc + 0, nv_rd32(dev, NV04_PFIFO_CACHE1_DMA_PUT)); nv_wi32(dev, fc + 4, nv_rd32(dev, NV04_PFIFO_CACHE1_DMA_GET)); nv_wi32(dev, fc + 8, nv_rd32(dev, NV10_PFIFO_CACHE1_REF_CNT)); @@ -179,8 +171,6 @@ nv10_fifo_unload_context(struct drm_device *dev) nv_wi32(dev, fc + 48, nv_rd32(dev, NV04_PFIFO_CACHE1_DMA_GET)); out: - dev_priv->engine.instmem.finish_access(dev); - nv10_fifo_do_load_context(dev, pfifo->channels - 1); nv_wr32(dev, NV03_PFIFO_CACHE1_PUSH1, pfifo->channels - 1); return 0; diff --git a/drivers/gpu/drm/nouveau/nv17_gpio.c b/drivers/gpu/drm/nouveau/nv10_gpio.c index 2e58c331e9b..007fc29e2f8 100644 --- a/drivers/gpu/drm/nouveau/nv17_gpio.c +++ b/drivers/gpu/drm/nouveau/nv10_gpio.c @@ -55,7 +55,7 @@ get_gpio_location(struct dcb_gpio_entry *ent, uint32_t *reg, uint32_t *shift, } int -nv17_gpio_get(struct drm_device *dev, enum dcb_gpio_tag tag) +nv10_gpio_get(struct drm_device *dev, enum dcb_gpio_tag tag) { struct dcb_gpio_entry *ent = nouveau_bios_gpio_entry(dev, tag); uint32_t reg, shift, mask, value; @@ -72,7 +72,7 @@ nv17_gpio_get(struct drm_device *dev, enum dcb_gpio_tag tag) } int -nv17_gpio_set(struct drm_device *dev, enum dcb_gpio_tag tag, int state) +nv10_gpio_set(struct drm_device *dev, enum dcb_gpio_tag tag, int state) { struct dcb_gpio_entry *ent = nouveau_bios_gpio_entry(dev, tag); uint32_t reg, shift, mask, value; diff --git a/drivers/gpu/drm/nouveau/nv17_tv.c b/drivers/gpu/drm/nouveau/nv17_tv.c index 74c880374fb..44fefb0c708 100644 --- a/drivers/gpu/drm/nouveau/nv17_tv.c +++ b/drivers/gpu/drm/nouveau/nv17_tv.c @@ -37,6 +37,7 @@ static uint32_t nv42_tv_sample_load(struct drm_encoder *encoder) { struct drm_device *dev = encoder->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_gpio_engine *gpio = &dev_priv->engine.gpio; uint32_t testval, regoffset = nv04_dac_output_offset(encoder); uint32_t gpio0, gpio1, fp_htotal, fp_hsync_start, fp_hsync_end, fp_control, test_ctrl, dacclk, ctv_14, ctv_1c, ctv_6c; @@ -52,8 +53,8 @@ static uint32_t nv42_tv_sample_load(struct drm_encoder *encoder) head = (dacclk & 0x100) >> 8; /* Save the previous state. */ - gpio1 = nv17_gpio_get(dev, DCB_GPIO_TVDAC1); - gpio0 = nv17_gpio_get(dev, DCB_GPIO_TVDAC0); + gpio1 = gpio->get(dev, DCB_GPIO_TVDAC1); + gpio0 = gpio->get(dev, DCB_GPIO_TVDAC0); fp_htotal = NVReadRAMDAC(dev, head, NV_PRAMDAC_FP_HTOTAL); fp_hsync_start = NVReadRAMDAC(dev, head, NV_PRAMDAC_FP_HSYNC_START); fp_hsync_end = NVReadRAMDAC(dev, head, NV_PRAMDAC_FP_HSYNC_END); @@ -64,8 +65,8 @@ static uint32_t nv42_tv_sample_load(struct drm_encoder *encoder) ctv_6c = NVReadRAMDAC(dev, head, 0x680c6c); /* Prepare the DAC for load detection. */ - nv17_gpio_set(dev, DCB_GPIO_TVDAC1, true); - nv17_gpio_set(dev, DCB_GPIO_TVDAC0, true); + gpio->set(dev, DCB_GPIO_TVDAC1, true); + gpio->set(dev, DCB_GPIO_TVDAC0, true); NVWriteRAMDAC(dev, head, NV_PRAMDAC_FP_HTOTAL, 1343); NVWriteRAMDAC(dev, head, NV_PRAMDAC_FP_HSYNC_START, 1047); @@ -110,12 +111,27 @@ static uint32_t nv42_tv_sample_load(struct drm_encoder *encoder) NVWriteRAMDAC(dev, head, NV_PRAMDAC_FP_HSYNC_END, fp_hsync_end); NVWriteRAMDAC(dev, head, NV_PRAMDAC_FP_HSYNC_START, fp_hsync_start); NVWriteRAMDAC(dev, head, NV_PRAMDAC_FP_HTOTAL, fp_htotal); - nv17_gpio_set(dev, DCB_GPIO_TVDAC1, gpio1); - nv17_gpio_set(dev, DCB_GPIO_TVDAC0, gpio0); + gpio->set(dev, DCB_GPIO_TVDAC1, gpio1); + gpio->set(dev, DCB_GPIO_TVDAC0, gpio0); return sample; } +static bool +get_tv_detect_quirks(struct drm_device *dev, uint32_t *pin_mask) +{ + /* Zotac FX5200 */ + if (dev->pdev->device == 0x0322 && + dev->pdev->subsystem_vendor == 0x19da && + (dev->pdev->subsystem_device == 0x1035 || + dev->pdev->subsystem_device == 0x2035)) { + *pin_mask = 0xc; + return false; + } + + return true; +} + static enum drm_connector_status nv17_tv_detect(struct drm_encoder *encoder, struct drm_connector *connector) { @@ -124,12 +140,20 @@ nv17_tv_detect(struct drm_encoder *encoder, struct drm_connector *connector) struct drm_mode_config *conf = &dev->mode_config; struct nv17_tv_encoder *tv_enc = to_tv_enc(encoder); struct dcb_entry *dcb = tv_enc->base.dcb; + bool reliable = get_tv_detect_quirks(dev, &tv_enc->pin_mask); - if (dev_priv->chipset == 0x42 || - dev_priv->chipset == 0x43) - tv_enc->pin_mask = nv42_tv_sample_load(encoder) >> 28 & 0xe; - else - tv_enc->pin_mask = nv17_dac_sample_load(encoder) >> 28 & 0xe; + if (nv04_dac_in_use(encoder)) + return connector_status_disconnected; + + if (reliable) { + if (dev_priv->chipset == 0x42 || + dev_priv->chipset == 0x43) + tv_enc->pin_mask = + nv42_tv_sample_load(encoder) >> 28 & 0xe; + else + tv_enc->pin_mask = + nv17_dac_sample_load(encoder) >> 28 & 0xe; + } switch (tv_enc->pin_mask) { case 0x2: @@ -154,7 +178,9 @@ nv17_tv_detect(struct drm_encoder *encoder, struct drm_connector *connector) conf->tv_subconnector_property, tv_enc->subconnector); - if (tv_enc->subconnector) { + if (!reliable) { + return connector_status_unknown; + } else if (tv_enc->subconnector) { NV_INFO(dev, "Load detected on output %c\n", '@' + ffs(dcb->or)); return connector_status_connected; @@ -296,6 +322,9 @@ static bool nv17_tv_mode_fixup(struct drm_encoder *encoder, { struct nv17_tv_norm_params *tv_norm = get_tv_norm(encoder); + if (nv04_dac_in_use(encoder)) + return false; + if (tv_norm->kind == CTV_ENC_MODE) adjusted_mode->clock = tv_norm->ctv_enc_mode.mode.clock; else @@ -307,6 +336,8 @@ static bool nv17_tv_mode_fixup(struct drm_encoder *encoder, static void nv17_tv_dpms(struct drm_encoder *encoder, int mode) { struct drm_device *dev = encoder->dev; + struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_gpio_engine *gpio = &dev_priv->engine.gpio; struct nv17_tv_state *regs = &to_tv_enc(encoder)->state; struct nv17_tv_norm_params *tv_norm = get_tv_norm(encoder); @@ -331,8 +362,8 @@ static void nv17_tv_dpms(struct drm_encoder *encoder, int mode) nv_load_ptv(dev, regs, 200); - nv17_gpio_set(dev, DCB_GPIO_TVDAC1, mode == DRM_MODE_DPMS_ON); - nv17_gpio_set(dev, DCB_GPIO_TVDAC0, mode == DRM_MODE_DPMS_ON); + gpio->set(dev, DCB_GPIO_TVDAC1, mode == DRM_MODE_DPMS_ON); + gpio->set(dev, DCB_GPIO_TVDAC0, mode == DRM_MODE_DPMS_ON); nv04_dac_update_dacclk(encoder, mode == DRM_MODE_DPMS_ON); } @@ -744,8 +775,10 @@ static struct drm_encoder_funcs nv17_tv_funcs = { .destroy = nv17_tv_destroy, }; -int nv17_tv_create(struct drm_device *dev, struct dcb_entry *entry) +int +nv17_tv_create(struct drm_connector *connector, struct dcb_entry *entry) { + struct drm_device *dev = connector->dev; struct drm_encoder *encoder; struct nv17_tv_encoder *tv_enc = NULL; @@ -774,5 +807,7 @@ int nv17_tv_create(struct drm_device *dev, struct dcb_entry *entry) encoder->possible_crtcs = entry->heads; encoder->possible_clones = 0; + nv17_tv_create_resources(encoder, connector); + drm_mode_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/nouveau/nv20_graph.c b/drivers/gpu/drm/nouveau/nv20_graph.c index d6fc0a82f03..17f309b36c9 100644 --- a/drivers/gpu/drm/nouveau/nv20_graph.c +++ b/drivers/gpu/drm/nouveau/nv20_graph.c @@ -370,68 +370,54 @@ nv20_graph_create_context(struct nouveau_channel *chan) { struct drm_device *dev = chan->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; void (*ctx_init)(struct drm_device *, struct nouveau_gpuobj *); - unsigned int ctx_size; unsigned int idoffs = 0x28/4; int ret; switch (dev_priv->chipset) { case 0x20: - ctx_size = NV20_GRCTX_SIZE; ctx_init = nv20_graph_context_init; idoffs = 0; break; case 0x25: case 0x28: - ctx_size = NV25_GRCTX_SIZE; ctx_init = nv25_graph_context_init; break; case 0x2a: - ctx_size = NV2A_GRCTX_SIZE; ctx_init = nv2a_graph_context_init; idoffs = 0; break; case 0x30: case 0x31: - ctx_size = NV30_31_GRCTX_SIZE; ctx_init = nv30_31_graph_context_init; break; case 0x34: - ctx_size = NV34_GRCTX_SIZE; ctx_init = nv34_graph_context_init; break; case 0x35: case 0x36: - ctx_size = NV35_36_GRCTX_SIZE; ctx_init = nv35_36_graph_context_init; break; default: - ctx_size = 0; - ctx_init = nv35_36_graph_context_init; - NV_ERROR(dev, "Please contact the devs if you want your NV%x" - " card to work\n", dev_priv->chipset); - return -ENOSYS; - break; + BUG_ON(1); } - ret = nouveau_gpuobj_new_ref(dev, chan, NULL, 0, ctx_size, 16, - NVOBJ_FLAG_ZERO_ALLOC, - &chan->ramin_grctx); + ret = nouveau_gpuobj_new_ref(dev, chan, NULL, 0, pgraph->grctx_size, + 16, NVOBJ_FLAG_ZERO_ALLOC, + &chan->ramin_grctx); if (ret) return ret; /* Initialise default context values */ - dev_priv->engine.instmem.prepare_access(dev, true); ctx_init(dev, chan->ramin_grctx->gpuobj); /* nv20: nv_wo32(dev, chan->ramin_grctx->gpuobj, 10, chan->id<<24); */ nv_wo32(dev, chan->ramin_grctx->gpuobj, idoffs, (chan->id << 24) | 0x1); /* CTX_USER */ - nv_wo32(dev, dev_priv->ctx_table->gpuobj, chan->id, - chan->ramin_grctx->instance >> 4); - - dev_priv->engine.instmem.finish_access(dev); + nv_wo32(dev, pgraph->ctx_table->gpuobj, chan->id, + chan->ramin_grctx->instance >> 4); return 0; } @@ -440,13 +426,12 @@ nv20_graph_destroy_context(struct nouveau_channel *chan) { struct drm_device *dev = chan->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; if (chan->ramin_grctx) nouveau_gpuobj_ref_del(dev, &chan->ramin_grctx); - dev_priv->engine.instmem.prepare_access(dev, true); - nv_wo32(dev, dev_priv->ctx_table->gpuobj, chan->id, 0); - dev_priv->engine.instmem.finish_access(dev); + nv_wo32(dev, pgraph->ctx_table->gpuobj, chan->id, 0); } int @@ -538,29 +523,44 @@ nv20_graph_set_region_tiling(struct drm_device *dev, int i, uint32_t addr, int nv20_graph_init(struct drm_device *dev) { - struct drm_nouveau_private *dev_priv = - (struct drm_nouveau_private *)dev->dev_private; + struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; uint32_t tmp, vramsz; int ret, i; + switch (dev_priv->chipset) { + case 0x20: + pgraph->grctx_size = NV20_GRCTX_SIZE; + break; + case 0x25: + case 0x28: + pgraph->grctx_size = NV25_GRCTX_SIZE; + break; + case 0x2a: + pgraph->grctx_size = NV2A_GRCTX_SIZE; + break; + default: + NV_ERROR(dev, "unknown chipset, disabling acceleration\n"); + pgraph->accel_blocked = true; + return 0; + } + nv_wr32(dev, NV03_PMC_ENABLE, nv_rd32(dev, NV03_PMC_ENABLE) & ~NV_PMC_ENABLE_PGRAPH); nv_wr32(dev, NV03_PMC_ENABLE, nv_rd32(dev, NV03_PMC_ENABLE) | NV_PMC_ENABLE_PGRAPH); - if (!dev_priv->ctx_table) { + if (!pgraph->ctx_table) { /* Create Context Pointer Table */ - dev_priv->ctx_table_size = 32 * 4; - ret = nouveau_gpuobj_new_ref(dev, NULL, NULL, 0, - dev_priv->ctx_table_size, 16, + ret = nouveau_gpuobj_new_ref(dev, NULL, NULL, 0, 32 * 4, 16, NVOBJ_FLAG_ZERO_ALLOC, - &dev_priv->ctx_table); + &pgraph->ctx_table); if (ret) return ret; } nv_wr32(dev, NV20_PGRAPH_CHANNEL_CTX_TABLE, - dev_priv->ctx_table->instance >> 4); + pgraph->ctx_table->instance >> 4); nv20_graph_rdi(dev); @@ -616,7 +616,7 @@ nv20_graph_init(struct drm_device *dev) nv_wr32(dev, NV10_PGRAPH_SURFACE, tmp); /* begin RAM config */ - vramsz = drm_get_resource_len(dev, 0) - 1; + vramsz = pci_resource_len(dev->pdev, 0) - 1; nv_wr32(dev, 0x4009A4, nv_rd32(dev, NV04_PFB_CFG0)); nv_wr32(dev, 0x4009A8, nv_rd32(dev, NV04_PFB_CFG1)); nv_wr32(dev, NV10_PGRAPH_RDI_INDEX, 0x00EA0000); @@ -644,34 +644,52 @@ void nv20_graph_takedown(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; - nouveau_gpuobj_ref_del(dev, &dev_priv->ctx_table); + nouveau_gpuobj_ref_del(dev, &pgraph->ctx_table); } int nv30_graph_init(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; int ret, i; + switch (dev_priv->chipset) { + case 0x30: + case 0x31: + pgraph->grctx_size = NV30_31_GRCTX_SIZE; + break; + case 0x34: + pgraph->grctx_size = NV34_GRCTX_SIZE; + break; + case 0x35: + case 0x36: + pgraph->grctx_size = NV35_36_GRCTX_SIZE; + break; + default: + NV_ERROR(dev, "unknown chipset, disabling acceleration\n"); + pgraph->accel_blocked = true; + return 0; + } + nv_wr32(dev, NV03_PMC_ENABLE, nv_rd32(dev, NV03_PMC_ENABLE) & ~NV_PMC_ENABLE_PGRAPH); nv_wr32(dev, NV03_PMC_ENABLE, nv_rd32(dev, NV03_PMC_ENABLE) | NV_PMC_ENABLE_PGRAPH); - if (!dev_priv->ctx_table) { + if (!pgraph->ctx_table) { /* Create Context Pointer Table */ - dev_priv->ctx_table_size = 32 * 4; - ret = nouveau_gpuobj_new_ref(dev, NULL, NULL, 0, - dev_priv->ctx_table_size, 16, + ret = nouveau_gpuobj_new_ref(dev, NULL, NULL, 0, 32 * 4, 16, NVOBJ_FLAG_ZERO_ALLOC, - &dev_priv->ctx_table); + &pgraph->ctx_table); if (ret) return ret; } nv_wr32(dev, NV20_PGRAPH_CHANNEL_CTX_TABLE, - dev_priv->ctx_table->instance >> 4); + pgraph->ctx_table->instance >> 4); nv_wr32(dev, NV03_PGRAPH_INTR , 0xFFFFFFFF); nv_wr32(dev, NV03_PGRAPH_INTR_EN, 0xFFFFFFFF); @@ -717,7 +735,7 @@ nv30_graph_init(struct drm_device *dev) nv_wr32(dev, 0x0040075c , 0x00000001); /* begin RAM config */ - /* vramsz = drm_get_resource_len(dev, 0) - 1; */ + /* vramsz = pci_resource_len(dev->pdev, 0) - 1; */ nv_wr32(dev, 0x4009A4, nv_rd32(dev, NV04_PFB_CFG0)); nv_wr32(dev, 0x4009A8, nv_rd32(dev, NV04_PFB_CFG1)); if (dev_priv->chipset != 0x34) { diff --git a/drivers/gpu/drm/nouveau/nv30_fb.c b/drivers/gpu/drm/nouveau/nv30_fb.c new file mode 100644 index 00000000000..9d35c8b3b83 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nv30_fb.c @@ -0,0 +1,87 @@ +/* + * Copyright (C) 2010 Francisco Jerez. + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining + * a copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sublicense, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial + * portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + * IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE + * LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION + * OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION + * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#include "drmP.h" +#include "drm.h" +#include "nouveau_drv.h" +#include "nouveau_drm.h" + +static int +calc_ref(int b, int l, int i) +{ + int j, x = 0; + + for (j = 0; j < 4; j++) { + int n = (b >> (8 * j) & 0xf); + int m = (l >> (8 * i) & 0xff) + 2 * (n & 0x8 ? n - 0x10 : n); + + x |= (0x80 | (m & 0x1f)) << (8 * j); + } + + return x; +} + +int +nv30_fb_init(struct drm_device *dev) +{ + struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_fb_engine *pfb = &dev_priv->engine.fb; + int i, j; + + pfb->num_tiles = NV10_PFB_TILE__SIZE; + + /* Turn all the tiling regions off. */ + for (i = 0; i < pfb->num_tiles; i++) + pfb->set_region_tiling(dev, i, 0, 0, 0); + + /* Init the memory timing regs at 0x10037c/0x1003ac */ + if (dev_priv->chipset == 0x30 || + dev_priv->chipset == 0x31 || + dev_priv->chipset == 0x35) { + /* Related to ROP count */ + int n = (dev_priv->chipset == 0x31 ? 2 : 4); + int b = (dev_priv->chipset > 0x30 ? + nv_rd32(dev, 0x122c) & 0xf : 0); + int l = nv_rd32(dev, 0x1003d0); + + for (i = 0; i < n; i++) { + for (j = 0; j < 3; j++) + nv_wr32(dev, 0x10037c + 0xc * i + 0x4 * j, + calc_ref(b, l, j)); + + for (j = 0; j < 2; j++) + nv_wr32(dev, 0x1003ac + 0x8 * i + 0x4 * j, + calc_ref(b, l, j)); + } + } + + return 0; +} + +void +nv30_fb_takedown(struct drm_device *dev) +{ +} diff --git a/drivers/gpu/drm/nouveau/nv40_fifo.c b/drivers/gpu/drm/nouveau/nv40_fifo.c index 500ccfd3a0b..2b67f1835c3 100644 --- a/drivers/gpu/drm/nouveau/nv40_fifo.c +++ b/drivers/gpu/drm/nouveau/nv40_fifo.c @@ -48,7 +48,6 @@ nv40_fifo_create_context(struct nouveau_channel *chan) spin_lock_irqsave(&dev_priv->context_switch_lock, flags); - dev_priv->engine.instmem.prepare_access(dev, true); nv_wi32(dev, fc + 0, chan->pushbuf_base); nv_wi32(dev, fc + 4, chan->pushbuf_base); nv_wi32(dev, fc + 12, chan->pushbuf->instance >> 4); @@ -61,7 +60,6 @@ nv40_fifo_create_context(struct nouveau_channel *chan) 0x30000000 /* no idea.. */); nv_wi32(dev, fc + 56, chan->ramin_grctx->instance >> 4); nv_wi32(dev, fc + 60, 0x0001FFFF); - dev_priv->engine.instmem.finish_access(dev); /* enable the fifo dma operation */ nv_wr32(dev, NV04_PFIFO_MODE, @@ -89,8 +87,6 @@ nv40_fifo_do_load_context(struct drm_device *dev, int chid) struct drm_nouveau_private *dev_priv = dev->dev_private; uint32_t fc = NV40_RAMFC(chid), tmp, tmp2; - dev_priv->engine.instmem.prepare_access(dev, false); - nv_wr32(dev, NV04_PFIFO_CACHE1_DMA_PUT, nv_ri32(dev, fc + 0)); nv_wr32(dev, NV04_PFIFO_CACHE1_DMA_GET, nv_ri32(dev, fc + 4)); nv_wr32(dev, NV10_PFIFO_CACHE1_REF_CNT, nv_ri32(dev, fc + 8)); @@ -127,8 +123,6 @@ nv40_fifo_do_load_context(struct drm_device *dev, int chid) nv_wr32(dev, 0x2088, nv_ri32(dev, fc + 76)); nv_wr32(dev, 0x3300, nv_ri32(dev, fc + 80)); - dev_priv->engine.instmem.finish_access(dev); - nv_wr32(dev, NV03_PFIFO_CACHE1_GET, 0); nv_wr32(dev, NV03_PFIFO_CACHE1_PUT, 0); } @@ -166,7 +160,6 @@ nv40_fifo_unload_context(struct drm_device *dev) return 0; fc = NV40_RAMFC(chid); - dev_priv->engine.instmem.prepare_access(dev, true); nv_wi32(dev, fc + 0, nv_rd32(dev, NV04_PFIFO_CACHE1_DMA_PUT)); nv_wi32(dev, fc + 4, nv_rd32(dev, NV04_PFIFO_CACHE1_DMA_GET)); nv_wi32(dev, fc + 8, nv_rd32(dev, NV10_PFIFO_CACHE1_REF_CNT)); @@ -200,7 +193,6 @@ nv40_fifo_unload_context(struct drm_device *dev) tmp |= (nv_rd32(dev, NV04_PFIFO_CACHE1_PUT) << 16); nv_wi32(dev, fc + 72, tmp); #endif - dev_priv->engine.instmem.finish_access(dev); nv40_fifo_do_load_context(dev, pfifo->channels - 1); nv_wr32(dev, NV03_PFIFO_CACHE1_PUSH1, diff --git a/drivers/gpu/drm/nouveau/nv40_graph.c b/drivers/gpu/drm/nouveau/nv40_graph.c index 704a25d04ac..fd7d2b50131 100644 --- a/drivers/gpu/drm/nouveau/nv40_graph.c +++ b/drivers/gpu/drm/nouveau/nv40_graph.c @@ -58,6 +58,7 @@ nv40_graph_create_context(struct nouveau_channel *chan) struct drm_device *dev = chan->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; + struct nouveau_grctx ctx = {}; int ret; ret = nouveau_gpuobj_new_ref(dev, chan, NULL, 0, pgraph->grctx_size, @@ -67,20 +68,13 @@ nv40_graph_create_context(struct nouveau_channel *chan) return ret; /* Initialise default context values */ - dev_priv->engine.instmem.prepare_access(dev, true); - if (!pgraph->ctxprog) { - struct nouveau_grctx ctx = {}; - - ctx.dev = chan->dev; - ctx.mode = NOUVEAU_GRCTX_VALS; - ctx.data = chan->ramin_grctx->gpuobj; - nv40_grctx_init(&ctx); - } else { - nouveau_grctx_vals_load(dev, chan->ramin_grctx->gpuobj); - } + ctx.dev = chan->dev; + ctx.mode = NOUVEAU_GRCTX_VALS; + ctx.data = chan->ramin_grctx->gpuobj; + nv40_grctx_init(&ctx); + nv_wo32(dev, chan->ramin_grctx->gpuobj, 0, chan->ramin_grctx->gpuobj->im_pramin->start); - dev_priv->engine.instmem.finish_access(dev); return 0; } @@ -238,7 +232,8 @@ nv40_graph_init(struct drm_device *dev) struct drm_nouveau_private *dev_priv = (struct drm_nouveau_private *)dev->dev_private; struct nouveau_fb_engine *pfb = &dev_priv->engine.fb; - uint32_t vramsz; + struct nouveau_grctx ctx = {}; + uint32_t vramsz, *cp; int i, j; nv_wr32(dev, NV03_PMC_ENABLE, nv_rd32(dev, NV03_PMC_ENABLE) & @@ -246,32 +241,22 @@ nv40_graph_init(struct drm_device *dev) nv_wr32(dev, NV03_PMC_ENABLE, nv_rd32(dev, NV03_PMC_ENABLE) | NV_PMC_ENABLE_PGRAPH); - if (nouveau_ctxfw) { - nouveau_grctx_prog_load(dev); - dev_priv->engine.graph.grctx_size = 175 * 1024; - } + cp = kmalloc(sizeof(*cp) * 256, GFP_KERNEL); + if (!cp) + return -ENOMEM; - if (!dev_priv->engine.graph.ctxprog) { - struct nouveau_grctx ctx = {}; - uint32_t *cp; + ctx.dev = dev; + ctx.mode = NOUVEAU_GRCTX_PROG; + ctx.data = cp; + ctx.ctxprog_max = 256; + nv40_grctx_init(&ctx); + dev_priv->engine.graph.grctx_size = ctx.ctxvals_pos * 4; - cp = kmalloc(sizeof(*cp) * 256, GFP_KERNEL); - if (!cp) - return -ENOMEM; + nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_INDEX, 0); + for (i = 0; i < ctx.ctxprog_len; i++) + nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_DATA, cp[i]); - ctx.dev = dev; - ctx.mode = NOUVEAU_GRCTX_PROG; - ctx.data = cp; - ctx.ctxprog_max = 256; - nv40_grctx_init(&ctx); - dev_priv->engine.graph.grctx_size = ctx.ctxvals_pos * 4; - - nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_INDEX, 0); - for (i = 0; i < ctx.ctxprog_len; i++) - nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_DATA, cp[i]); - - kfree(cp); - } + kfree(cp); /* No context present currently */ nv_wr32(dev, NV40_PGRAPH_CTXCTL_CUR, 0x00000000); @@ -367,7 +352,7 @@ nv40_graph_init(struct drm_device *dev) nv40_graph_set_region_tiling(dev, i, 0, 0, 0); /* begin RAM config */ - vramsz = drm_get_resource_len(dev, 0) - 1; + vramsz = pci_resource_len(dev->pdev, 0) - 1; switch (dev_priv->chipset) { case 0x40: nv_wr32(dev, 0x4009A4, nv_rd32(dev, NV04_PFB_CFG0)); @@ -407,7 +392,6 @@ nv40_graph_init(struct drm_device *dev) void nv40_graph_takedown(struct drm_device *dev) { - nouveau_grctx_fini(dev); } struct nouveau_pgraph_object_class nv40_graph_grclass[] = { diff --git a/drivers/gpu/drm/nouveau/nv40_mc.c b/drivers/gpu/drm/nouveau/nv40_mc.c index 2a3495e848e..e4e72c12ab6 100644 --- a/drivers/gpu/drm/nouveau/nv40_mc.c +++ b/drivers/gpu/drm/nouveau/nv40_mc.c @@ -19,7 +19,7 @@ nv40_mc_init(struct drm_device *dev) case 0x46: /* G72 */ case 0x4e: case 0x4c: /* C51_G7X */ - tmp = nv_rd32(dev, NV40_PFB_020C); + tmp = nv_rd32(dev, NV04_PFB_FIFO_DATA); nv_wr32(dev, NV40_PMC_1700, tmp); nv_wr32(dev, NV40_PMC_1704, 0); nv_wr32(dev, NV40_PMC_1708, 0); diff --git a/drivers/gpu/drm/nouveau/nv50_crtc.c b/drivers/gpu/drm/nouveau/nv50_crtc.c index b4e4a3b05ea..5d11ea10166 100644 --- a/drivers/gpu/drm/nouveau/nv50_crtc.c +++ b/drivers/gpu/drm/nouveau/nv50_crtc.c @@ -440,47 +440,15 @@ nv50_crtc_prepare(struct drm_crtc *crtc) { struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); struct drm_device *dev = crtc->dev; - struct drm_encoder *encoder; - uint32_t dac = 0, sor = 0; NV_DEBUG_KMS(dev, "index %d\n", nv_crtc->index); - /* Disconnect all unused encoders. */ - list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - - if (!drm_helper_encoder_in_use(encoder)) - continue; - - if (nv_encoder->dcb->type == OUTPUT_ANALOG || - nv_encoder->dcb->type == OUTPUT_TV) - dac |= (1 << nv_encoder->or); - else - sor |= (1 << nv_encoder->or); - } - - list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - - if (nv_encoder->dcb->type == OUTPUT_ANALOG || - nv_encoder->dcb->type == OUTPUT_TV) { - if (dac & (1 << nv_encoder->or)) - continue; - } else { - if (sor & (1 << nv_encoder->or)) - continue; - } - - nv_encoder->disconnect(nv_encoder); - } - nv50_crtc_blank(nv_crtc, true); } static void nv50_crtc_commit(struct drm_crtc *crtc) { - struct drm_crtc *crtc2; struct drm_device *dev = crtc->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_channel *evo = dev_priv->evo; @@ -491,20 +459,14 @@ nv50_crtc_commit(struct drm_crtc *crtc) nv50_crtc_blank(nv_crtc, false); - /* Explicitly blank all unused crtc's. */ - list_for_each_entry(crtc2, &dev->mode_config.crtc_list, head) { - if (!drm_helper_crtc_in_use(crtc2)) - nv50_crtc_blank(nouveau_crtc(crtc2), true); - } - ret = RING_SPACE(evo, 2); if (ret) { NV_ERROR(dev, "no space while committing crtc\n"); return; } BEGIN_RING(evo, 0, NV50_EVO_UPDATE, 1); - OUT_RING(evo, 0); - FIRE_RING(evo); + OUT_RING (evo, 0); + FIRE_RING (evo); } static bool diff --git a/drivers/gpu/drm/nouveau/nv50_dac.c b/drivers/gpu/drm/nouveau/nv50_dac.c index 1fd9537beff..1bc08596294 100644 --- a/drivers/gpu/drm/nouveau/nv50_dac.c +++ b/drivers/gpu/drm/nouveau/nv50_dac.c @@ -37,22 +37,31 @@ #include "nv50_display.h" static void -nv50_dac_disconnect(struct nouveau_encoder *nv_encoder) +nv50_dac_disconnect(struct drm_encoder *encoder) { - struct drm_device *dev = to_drm_encoder(nv_encoder)->dev; + struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); + struct drm_device *dev = encoder->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_channel *evo = dev_priv->evo; int ret; + if (!nv_encoder->crtc) + return; + nv50_crtc_blank(nouveau_crtc(nv_encoder->crtc), true); + NV_DEBUG_KMS(dev, "Disconnecting DAC %d\n", nv_encoder->or); - ret = RING_SPACE(evo, 2); + ret = RING_SPACE(evo, 4); if (ret) { NV_ERROR(dev, "no space while disconnecting DAC\n"); return; } BEGIN_RING(evo, 0, NV50_EVO_DAC(nv_encoder->or, MODE_CTRL), 1); - OUT_RING(evo, 0); + OUT_RING (evo, 0); + BEGIN_RING(evo, 0, NV50_EVO_UPDATE, 1); + OUT_RING (evo, 0); + + nv_encoder->crtc = NULL; } static enum drm_connector_status @@ -213,7 +222,8 @@ nv50_dac_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, uint32_t mode_ctl = 0, mode_ctl2 = 0; int ret; - NV_DEBUG_KMS(dev, "or %d\n", nv_encoder->or); + NV_DEBUG_KMS(dev, "or %d type %d crtc %d\n", + nv_encoder->or, nv_encoder->dcb->type, crtc->index); nv50_dac_dpms(encoder, DRM_MODE_DPMS_ON); @@ -243,6 +253,14 @@ nv50_dac_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, BEGIN_RING(evo, 0, NV50_EVO_DAC(nv_encoder->or, MODE_CTRL), 2); OUT_RING(evo, mode_ctl); OUT_RING(evo, mode_ctl2); + + nv_encoder->crtc = encoder->crtc; +} + +static struct drm_crtc * +nv50_dac_crtc_get(struct drm_encoder *encoder) +{ + return nouveau_encoder(encoder)->crtc; } static const struct drm_encoder_helper_funcs nv50_dac_helper_funcs = { @@ -253,7 +271,9 @@ static const struct drm_encoder_helper_funcs nv50_dac_helper_funcs = { .prepare = nv50_dac_prepare, .commit = nv50_dac_commit, .mode_set = nv50_dac_mode_set, - .detect = nv50_dac_detect + .get_crtc = nv50_dac_crtc_get, + .detect = nv50_dac_detect, + .disable = nv50_dac_disconnect }; static void @@ -275,14 +295,11 @@ static const struct drm_encoder_funcs nv50_dac_encoder_funcs = { }; int -nv50_dac_create(struct drm_device *dev, struct dcb_entry *entry) +nv50_dac_create(struct drm_connector *connector, struct dcb_entry *entry) { struct nouveau_encoder *nv_encoder; struct drm_encoder *encoder; - NV_DEBUG_KMS(dev, "\n"); - NV_INFO(dev, "Detected a DAC output\n"); - nv_encoder = kzalloc(sizeof(*nv_encoder), GFP_KERNEL); if (!nv_encoder) return -ENOMEM; @@ -291,14 +308,14 @@ nv50_dac_create(struct drm_device *dev, struct dcb_entry *entry) nv_encoder->dcb = entry; nv_encoder->or = ffs(entry->or) - 1; - nv_encoder->disconnect = nv50_dac_disconnect; - - drm_encoder_init(dev, encoder, &nv50_dac_encoder_funcs, + drm_encoder_init(connector->dev, encoder, &nv50_dac_encoder_funcs, DRM_MODE_ENCODER_DAC); drm_encoder_helper_add(encoder, &nv50_dac_helper_funcs); encoder->possible_crtcs = entry->heads; encoder->possible_clones = 0; + + drm_mode_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index 580a5d10be9..f13ad0de9c8 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -71,14 +71,13 @@ nv50_evo_dmaobj_new(struct nouveau_channel *evo, uint32_t class, uint32_t name, return ret; } - dev_priv->engine.instmem.prepare_access(dev, true); nv_wo32(dev, obj, 0, (tile_flags << 22) | (magic_flags << 16) | class); nv_wo32(dev, obj, 1, limit); nv_wo32(dev, obj, 2, offset); nv_wo32(dev, obj, 3, 0x00000000); nv_wo32(dev, obj, 4, 0x00000000); nv_wo32(dev, obj, 5, 0x00010000); - dev_priv->engine.instmem.finish_access(dev); + dev_priv->engine.instmem.flush(dev); return 0; } @@ -110,8 +109,8 @@ nv50_evo_channel_new(struct drm_device *dev, struct nouveau_channel **pchan) return ret; } - ret = nouveau_mem_init_heap(&chan->ramin_heap, chan->ramin->gpuobj-> - im_pramin->start, 32768); + ret = drm_mm_init(&chan->ramin_heap, + chan->ramin->gpuobj->im_pramin->start, 32768); if (ret) { NV_ERROR(dev, "Error initialising EVO PRAMIN heap: %d\n", ret); nv50_evo_channel_del(pchan); @@ -179,13 +178,25 @@ nv50_evo_channel_new(struct drm_device *dev, struct nouveau_channel **pchan) } int +nv50_display_early_init(struct drm_device *dev) +{ + return 0; +} + +void +nv50_display_late_takedown(struct drm_device *dev) +{ +} + +int nv50_display_init(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_timer_engine *ptimer = &dev_priv->engine.timer; + struct nouveau_gpio_engine *pgpio = &dev_priv->engine.gpio; struct nouveau_channel *evo = dev_priv->evo; struct drm_connector *connector; - uint32_t val, ram_amount, hpd_en[2]; + uint32_t val, ram_amount; uint64_t start; int ret, i; @@ -366,26 +377,13 @@ nv50_display_init(struct drm_device *dev) NV50_PDISPLAY_INTR_EN_CLK_UNK40)); /* enable hotplug interrupts */ - hpd_en[0] = hpd_en[1] = 0; list_for_each_entry(connector, &dev->mode_config.connector_list, head) { struct nouveau_connector *conn = nouveau_connector(connector); - struct dcb_gpio_entry *gpio; if (conn->dcb->gpio_tag == 0xff) continue; - gpio = nouveau_bios_gpio_entry(dev, conn->dcb->gpio_tag); - if (!gpio) - continue; - - hpd_en[gpio->line >> 4] |= (0x00010001 << (gpio->line & 0xf)); - } - - nv_wr32(dev, 0xe054, 0xffffffff); - nv_wr32(dev, 0xe050, hpd_en[0]); - if (dev_priv->chipset >= 0x90) { - nv_wr32(dev, 0xe074, 0xffffffff); - nv_wr32(dev, 0xe070, hpd_en[1]); + pgpio->irq_enable(dev, conn->dcb->gpio_tag, true); } return 0; @@ -465,6 +463,7 @@ int nv50_display_create(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; struct dcb_table *dcb = &dev_priv->vbios.dcb; + struct drm_connector *connector, *ct; int ret, i; NV_DEBUG_KMS(dev, "\n"); @@ -507,14 +506,18 @@ int nv50_display_create(struct drm_device *dev) continue; } + connector = nouveau_connector_create(dev, entry->connector); + if (IS_ERR(connector)) + continue; + switch (entry->type) { case OUTPUT_TMDS: case OUTPUT_LVDS: case OUTPUT_DP: - nv50_sor_create(dev, entry); + nv50_sor_create(connector, entry); break; case OUTPUT_ANALOG: - nv50_dac_create(dev, entry); + nv50_dac_create(connector, entry); break; default: NV_WARN(dev, "DCB encoder %d unknown\n", entry->type); @@ -522,11 +525,13 @@ int nv50_display_create(struct drm_device *dev) } } - for (i = 0 ; i < dcb->connector.entries; i++) { - if (i != 0 && dcb->connector.entry[i].index2 == - dcb->connector.entry[i - 1].index2) - continue; - nouveau_connector_create(dev, &dcb->connector.entry[i]); + list_for_each_entry_safe(connector, ct, + &dev->mode_config.connector_list, head) { + if (!connector->encoder_ids[0]) { + NV_WARN(dev, "%s has no encoders, removing\n", + drm_get_connector_name(connector)); + connector->funcs->destroy(connector); + } } ret = nv50_display_init(dev); @@ -538,7 +543,8 @@ int nv50_display_create(struct drm_device *dev) return 0; } -int nv50_display_destroy(struct drm_device *dev) +void +nv50_display_destroy(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; @@ -548,135 +554,30 @@ int nv50_display_destroy(struct drm_device *dev) nv50_display_disable(dev); nv50_evo_channel_del(&dev_priv->evo); - - return 0; -} - -static inline uint32_t -nv50_display_mode_ctrl(struct drm_device *dev, bool sor, int or) -{ - struct drm_nouveau_private *dev_priv = dev->dev_private; - uint32_t mc; - - if (sor) { - if (dev_priv->chipset < 0x90 || - dev_priv->chipset == 0x92 || dev_priv->chipset == 0xa0) - mc = nv_rd32(dev, NV50_PDISPLAY_SOR_MODE_CTRL_P(or)); - else - mc = nv_rd32(dev, NV90_PDISPLAY_SOR_MODE_CTRL_P(or)); - } else { - mc = nv_rd32(dev, NV50_PDISPLAY_DAC_MODE_CTRL_P(or)); - } - - return mc; -} - -static int -nv50_display_irq_head(struct drm_device *dev, int *phead, - struct dcb_entry **pdcbent) -{ - struct drm_nouveau_private *dev_priv = dev->dev_private; - uint32_t unk30 = nv_rd32(dev, NV50_PDISPLAY_UNK30_CTRL); - uint32_t dac = 0, sor = 0; - int head, i, or = 0, type = OUTPUT_ANY; - - /* We're assuming that head 0 *or* head 1 will be active here, - * and not both. I'm not sure if the hw will even signal both - * ever, but it definitely shouldn't for us as we commit each - * CRTC separately, and submission will be blocked by the GPU - * until we handle each in turn. - */ - NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30); - head = ffs((unk30 >> 9) & 3) - 1; - if (head < 0) - return -EINVAL; - - /* This assumes CRTCs are never bound to multiple encoders, which - * should be the case. - */ - for (i = 0; i < 3 && type == OUTPUT_ANY; i++) { - uint32_t mc = nv50_display_mode_ctrl(dev, false, i); - if (!(mc & (1 << head))) - continue; - - switch ((mc >> 8) & 0xf) { - case 0: type = OUTPUT_ANALOG; break; - case 1: type = OUTPUT_TV; break; - default: - NV_ERROR(dev, "unknown dac mode_ctrl: 0x%08x\n", dac); - return -1; - } - - or = i; - } - - for (i = 0; i < 4 && type == OUTPUT_ANY; i++) { - uint32_t mc = nv50_display_mode_ctrl(dev, true, i); - if (!(mc & (1 << head))) - continue; - - switch ((mc >> 8) & 0xf) { - case 0: type = OUTPUT_LVDS; break; - case 1: type = OUTPUT_TMDS; break; - case 2: type = OUTPUT_TMDS; break; - case 5: type = OUTPUT_TMDS; break; - case 8: type = OUTPUT_DP; break; - case 9: type = OUTPUT_DP; break; - default: - NV_ERROR(dev, "unknown sor mode_ctrl: 0x%08x\n", sor); - return -1; - } - - or = i; - } - - NV_DEBUG_KMS(dev, "type %d, or %d\n", type, or); - if (type == OUTPUT_ANY) { - NV_ERROR(dev, "unknown encoder!!\n"); - return -1; - } - - for (i = 0; i < dev_priv->vbios.dcb.entries; i++) { - struct dcb_entry *dcbent = &dev_priv->vbios.dcb.entry[i]; - - if (dcbent->type != type) - continue; - - if (!(dcbent->or & (1 << or))) - continue; - - *phead = head; - *pdcbent = dcbent; - return 0; - } - - NV_ERROR(dev, "no DCB entry for %d %d\n", dac != 0, or); - return 0; } -static uint32_t -nv50_display_script_select(struct drm_device *dev, struct dcb_entry *dcbent, - int pxclk) +static u16 +nv50_display_script_select(struct drm_device *dev, struct dcb_entry *dcb, + u32 mc, int pxclk) { struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_connector *nv_connector = NULL; struct drm_encoder *encoder; struct nvbios *bios = &dev_priv->vbios; - uint32_t mc, script = 0, or; + u32 script = 0, or; list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - if (nv_encoder->dcb != dcbent) + if (nv_encoder->dcb != dcb) continue; nv_connector = nouveau_encoder_connector_get(nv_encoder); break; } - or = ffs(dcbent->or) - 1; - mc = nv50_display_mode_ctrl(dev, dcbent->type != OUTPUT_ANALOG, or); - switch (dcbent->type) { + or = ffs(dcb->or) - 1; + switch (dcb->type) { case OUTPUT_LVDS: script = (mc >> 8) & 0xf; if (bios->fp_no_ddc) { @@ -767,17 +668,88 @@ nv50_display_vblank_handler(struct drm_device *dev, uint32_t intr) static void nv50_display_unk10_handler(struct drm_device *dev) { - struct dcb_entry *dcbent; - int head, ret; + struct drm_nouveau_private *dev_priv = dev->dev_private; + u32 unk30 = nv_rd32(dev, 0x610030), mc; + int i, crtc, or, type = OUTPUT_ANY; - ret = nv50_display_irq_head(dev, &head, &dcbent); - if (ret) - goto ack; + NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30); + dev_priv->evo_irq.dcb = NULL; nv_wr32(dev, 0x619494, nv_rd32(dev, 0x619494) & ~8); - nouveau_bios_run_display_table(dev, dcbent, 0, -1); + /* Determine which CRTC we're dealing with, only 1 ever will be + * signalled at the same time with the current nouveau code. + */ + crtc = ffs((unk30 & 0x00000060) >> 5) - 1; + if (crtc < 0) + goto ack; + + /* Nothing needs to be done for the encoder */ + crtc = ffs((unk30 & 0x00000180) >> 7) - 1; + if (crtc < 0) + goto ack; + /* Find which encoder was connected to the CRTC */ + for (i = 0; type == OUTPUT_ANY && i < 3; i++) { + mc = nv_rd32(dev, NV50_PDISPLAY_DAC_MODE_CTRL_C(i)); + NV_DEBUG_KMS(dev, "DAC-%d mc: 0x%08x\n", i, mc); + if (!(mc & (1 << crtc))) + continue; + + switch ((mc & 0x00000f00) >> 8) { + case 0: type = OUTPUT_ANALOG; break; + case 1: type = OUTPUT_TV; break; + default: + NV_ERROR(dev, "invalid mc, DAC-%d: 0x%08x\n", i, mc); + goto ack; + } + + or = i; + } + + for (i = 0; type == OUTPUT_ANY && i < 4; i++) { + if (dev_priv->chipset < 0x90 || + dev_priv->chipset == 0x92 || + dev_priv->chipset == 0xa0) + mc = nv_rd32(dev, NV50_PDISPLAY_SOR_MODE_CTRL_C(i)); + else + mc = nv_rd32(dev, NV90_PDISPLAY_SOR_MODE_CTRL_C(i)); + + NV_DEBUG_KMS(dev, "SOR-%d mc: 0x%08x\n", i, mc); + if (!(mc & (1 << crtc))) + continue; + + switch ((mc & 0x00000f00) >> 8) { + case 0: type = OUTPUT_LVDS; break; + case 1: type = OUTPUT_TMDS; break; + case 2: type = OUTPUT_TMDS; break; + case 5: type = OUTPUT_TMDS; break; + case 8: type = OUTPUT_DP; break; + case 9: type = OUTPUT_DP; break; + default: + NV_ERROR(dev, "invalid mc, SOR-%d: 0x%08x\n", i, mc); + goto ack; + } + + or = i; + } + + /* There was no encoder to disable */ + if (type == OUTPUT_ANY) + goto ack; + + /* Disable the encoder */ + for (i = 0; i < dev_priv->vbios.dcb.entries; i++) { + struct dcb_entry *dcb = &dev_priv->vbios.dcb.entry[i]; + + if (dcb->type == type && (dcb->or & (1 << or))) { + nouveau_bios_run_display_table(dev, dcb, 0, -1); + dev_priv->evo_irq.dcb = dcb; + goto ack; + } + } + + NV_ERROR(dev, "no dcb for %d %d 0x%08x\n", or, type, mc); ack: nv_wr32(dev, NV50_PDISPLAY_INTR_1, NV50_PDISPLAY_INTR_1_CLK_UNK10); nv_wr32(dev, 0x610030, 0x80000000); @@ -817,33 +789,103 @@ nv50_display_unk20_dp_hack(struct drm_device *dev, struct dcb_entry *dcb) static void nv50_display_unk20_handler(struct drm_device *dev) { - struct dcb_entry *dcbent; - uint32_t tmp, pclk, script; - int head, or, ret; + struct drm_nouveau_private *dev_priv = dev->dev_private; + u32 unk30 = nv_rd32(dev, 0x610030), tmp, pclk, script, mc; + struct dcb_entry *dcb; + int i, crtc, or, type = OUTPUT_ANY; - ret = nv50_display_irq_head(dev, &head, &dcbent); - if (ret) + NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30); + dcb = dev_priv->evo_irq.dcb; + if (dcb) { + nouveau_bios_run_display_table(dev, dcb, 0, -2); + dev_priv->evo_irq.dcb = NULL; + } + + /* CRTC clock change requested? */ + crtc = ffs((unk30 & 0x00000600) >> 9) - 1; + if (crtc >= 0) { + pclk = nv_rd32(dev, NV50_PDISPLAY_CRTC_P(crtc, CLOCK)); + pclk &= 0x003fffff; + + nv50_crtc_set_clock(dev, crtc, pclk); + + tmp = nv_rd32(dev, NV50_PDISPLAY_CRTC_CLK_CTRL2(crtc)); + tmp &= ~0x000000f; + nv_wr32(dev, NV50_PDISPLAY_CRTC_CLK_CTRL2(crtc), tmp); + } + + /* Nothing needs to be done for the encoder */ + crtc = ffs((unk30 & 0x00000180) >> 7) - 1; + if (crtc < 0) goto ack; - or = ffs(dcbent->or) - 1; - pclk = nv_rd32(dev, NV50_PDISPLAY_CRTC_P(head, CLOCK)) & 0x3fffff; - script = nv50_display_script_select(dev, dcbent, pclk); + pclk = nv_rd32(dev, NV50_PDISPLAY_CRTC_P(crtc, CLOCK)) & 0x003fffff; - NV_DEBUG_KMS(dev, "head %d pxclk: %dKHz\n", head, pclk); + /* Find which encoder is connected to the CRTC */ + for (i = 0; type == OUTPUT_ANY && i < 3; i++) { + mc = nv_rd32(dev, NV50_PDISPLAY_DAC_MODE_CTRL_P(i)); + NV_DEBUG_KMS(dev, "DAC-%d mc: 0x%08x\n", i, mc); + if (!(mc & (1 << crtc))) + continue; - if (dcbent->type != OUTPUT_DP) - nouveau_bios_run_display_table(dev, dcbent, 0, -2); + switch ((mc & 0x00000f00) >> 8) { + case 0: type = OUTPUT_ANALOG; break; + case 1: type = OUTPUT_TV; break; + default: + NV_ERROR(dev, "invalid mc, DAC-%d: 0x%08x\n", i, mc); + goto ack; + } - nv50_crtc_set_clock(dev, head, pclk); + or = i; + } - nouveau_bios_run_display_table(dev, dcbent, script, pclk); + for (i = 0; type == OUTPUT_ANY && i < 4; i++) { + if (dev_priv->chipset < 0x90 || + dev_priv->chipset == 0x92 || + dev_priv->chipset == 0xa0) + mc = nv_rd32(dev, NV50_PDISPLAY_SOR_MODE_CTRL_P(i)); + else + mc = nv_rd32(dev, NV90_PDISPLAY_SOR_MODE_CTRL_P(i)); - nv50_display_unk20_dp_hack(dev, dcbent); + NV_DEBUG_KMS(dev, "SOR-%d mc: 0x%08x\n", i, mc); + if (!(mc & (1 << crtc))) + continue; + + switch ((mc & 0x00000f00) >> 8) { + case 0: type = OUTPUT_LVDS; break; + case 1: type = OUTPUT_TMDS; break; + case 2: type = OUTPUT_TMDS; break; + case 5: type = OUTPUT_TMDS; break; + case 8: type = OUTPUT_DP; break; + case 9: type = OUTPUT_DP; break; + default: + NV_ERROR(dev, "invalid mc, SOR-%d: 0x%08x\n", i, mc); + goto ack; + } + + or = i; + } + + if (type == OUTPUT_ANY) + goto ack; + + /* Enable the encoder */ + for (i = 0; i < dev_priv->vbios.dcb.entries; i++) { + dcb = &dev_priv->vbios.dcb.entry[i]; + if (dcb->type == type && (dcb->or & (1 << or))) + break; + } + + if (i == dev_priv->vbios.dcb.entries) { + NV_ERROR(dev, "no dcb for %d %d 0x%08x\n", or, type, mc); + goto ack; + } - tmp = nv_rd32(dev, NV50_PDISPLAY_CRTC_CLK_CTRL2(head)); - tmp &= ~0x000000f; - nv_wr32(dev, NV50_PDISPLAY_CRTC_CLK_CTRL2(head), tmp); + script = nv50_display_script_select(dev, dcb, mc, pclk); + nouveau_bios_run_display_table(dev, dcb, script, pclk); - if (dcbent->type != OUTPUT_ANALOG) { + nv50_display_unk20_dp_hack(dev, dcb); + + if (dcb->type != OUTPUT_ANALOG) { tmp = nv_rd32(dev, NV50_PDISPLAY_SOR_CLK_CTRL2(or)); tmp &= ~0x00000f0f; if (script & 0x0100) @@ -853,24 +895,61 @@ nv50_display_unk20_handler(struct drm_device *dev) nv_wr32(dev, NV50_PDISPLAY_DAC_CLK_CTRL2(or), 0); } + dev_priv->evo_irq.dcb = dcb; + dev_priv->evo_irq.pclk = pclk; + dev_priv->evo_irq.script = script; + ack: nv_wr32(dev, NV50_PDISPLAY_INTR_1, NV50_PDISPLAY_INTR_1_CLK_UNK20); nv_wr32(dev, 0x610030, 0x80000000); } +/* If programming a TMDS output on a SOR that can also be configured for + * DisplayPort, make sure NV50_SOR_DP_CTRL_ENABLE is forced off. + * + * It looks like the VBIOS TMDS scripts make an attempt at this, however, + * the VBIOS scripts on at least one board I have only switch it off on + * link 0, causing a blank display if the output has previously been + * programmed for DisplayPort. + */ +static void +nv50_display_unk40_dp_set_tmds(struct drm_device *dev, struct dcb_entry *dcb) +{ + int or = ffs(dcb->or) - 1, link = !(dcb->dpconf.sor.link & 1); + struct drm_encoder *encoder; + u32 tmp; + + if (dcb->type != OUTPUT_TMDS) + return; + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { + struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); + + if (nv_encoder->dcb->type == OUTPUT_DP && + nv_encoder->dcb->or & (1 << or)) { + tmp = nv_rd32(dev, NV50_SOR_DP_CTRL(or, link)); + tmp &= ~NV50_SOR_DP_CTRL_ENABLED; + nv_wr32(dev, NV50_SOR_DP_CTRL(or, link), tmp); + break; + } + } +} + static void nv50_display_unk40_handler(struct drm_device *dev) { - struct dcb_entry *dcbent; - int head, pclk, script, ret; + struct drm_nouveau_private *dev_priv = dev->dev_private; + struct dcb_entry *dcb = dev_priv->evo_irq.dcb; + u16 script = dev_priv->evo_irq.script; + u32 unk30 = nv_rd32(dev, 0x610030), pclk = dev_priv->evo_irq.pclk; - ret = nv50_display_irq_head(dev, &head, &dcbent); - if (ret) + NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30); + dev_priv->evo_irq.dcb = NULL; + if (!dcb) goto ack; - pclk = nv_rd32(dev, NV50_PDISPLAY_CRTC_P(head, CLOCK)) & 0x3fffff; - script = nv50_display_script_select(dev, dcbent, pclk); - nouveau_bios_run_display_table(dev, dcbent, script, -pclk); + nouveau_bios_run_display_table(dev, dcb, script, -pclk); + nv50_display_unk40_dp_set_tmds(dev, dcb); ack: nv_wr32(dev, NV50_PDISPLAY_INTR_1, NV50_PDISPLAY_INTR_1_CLK_UNK40); diff --git a/drivers/gpu/drm/nouveau/nv50_display.h b/drivers/gpu/drm/nouveau/nv50_display.h index 581d405ac01..c551f0b85ee 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.h +++ b/drivers/gpu/drm/nouveau/nv50_display.h @@ -38,9 +38,11 @@ void nv50_display_irq_handler(struct drm_device *dev); void nv50_display_irq_handler_bh(struct work_struct *work); void nv50_display_irq_hotplug_bh(struct work_struct *work); -int nv50_display_init(struct drm_device *dev); +int nv50_display_early_init(struct drm_device *dev); +void nv50_display_late_takedown(struct drm_device *dev); int nv50_display_create(struct drm_device *dev); -int nv50_display_destroy(struct drm_device *dev); +int nv50_display_init(struct drm_device *dev); +void nv50_display_destroy(struct drm_device *dev); int nv50_crtc_blank(struct nouveau_crtc *, bool blank); int nv50_crtc_set_clock(struct drm_device *, int head, int pclk); diff --git a/drivers/gpu/drm/nouveau/nv50_fifo.c b/drivers/gpu/drm/nouveau/nv50_fifo.c index e20c0e2474f..fb0281ae8f9 100644 --- a/drivers/gpu/drm/nouveau/nv50_fifo.c +++ b/drivers/gpu/drm/nouveau/nv50_fifo.c @@ -28,41 +28,33 @@ #include "drm.h" #include "nouveau_drv.h" -struct nv50_fifo_priv { - struct nouveau_gpuobj_ref *thingo[2]; - int cur_thingo; -}; - -#define IS_G80 ((dev_priv->chipset & 0xf0) == 0x50) - static void -nv50_fifo_init_thingo(struct drm_device *dev) +nv50_fifo_playlist_update(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nv50_fifo_priv *priv = dev_priv->engine.fifo.priv; + struct nouveau_fifo_engine *pfifo = &dev_priv->engine.fifo; struct nouveau_gpuobj_ref *cur; int i, nr; NV_DEBUG(dev, "\n"); - cur = priv->thingo[priv->cur_thingo]; - priv->cur_thingo = !priv->cur_thingo; + cur = pfifo->playlist[pfifo->cur_playlist]; + pfifo->cur_playlist = !pfifo->cur_playlist; /* We never schedule channel 0 or 127 */ - dev_priv->engine.instmem.prepare_access(dev, true); for (i = 1, nr = 0; i < 127; i++) { if (dev_priv->fifos[i] && dev_priv->fifos[i]->ramfc) nv_wo32(dev, cur->gpuobj, nr++, i); } - dev_priv->engine.instmem.finish_access(dev); + dev_priv->engine.instmem.flush(dev); nv_wr32(dev, 0x32f4, cur->instance >> 12); nv_wr32(dev, 0x32ec, nr); nv_wr32(dev, 0x2500, 0x101); } -static int -nv50_fifo_channel_enable(struct drm_device *dev, int channel, bool nt) +static void +nv50_fifo_channel_enable(struct drm_device *dev, int channel) { struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_channel *chan = dev_priv->fifos[channel]; @@ -70,37 +62,28 @@ nv50_fifo_channel_enable(struct drm_device *dev, int channel, bool nt) NV_DEBUG(dev, "ch%d\n", channel); - if (!chan->ramfc) - return -EINVAL; - - if (IS_G80) + if (dev_priv->chipset == 0x50) inst = chan->ramfc->instance >> 12; else inst = chan->ramfc->instance >> 8; - nv_wr32(dev, NV50_PFIFO_CTX_TABLE(channel), - inst | NV50_PFIFO_CTX_TABLE_CHANNEL_ENABLED); - if (!nt) - nv50_fifo_init_thingo(dev); - return 0; + nv_wr32(dev, NV50_PFIFO_CTX_TABLE(channel), inst | + NV50_PFIFO_CTX_TABLE_CHANNEL_ENABLED); } static void -nv50_fifo_channel_disable(struct drm_device *dev, int channel, bool nt) +nv50_fifo_channel_disable(struct drm_device *dev, int channel) { struct drm_nouveau_private *dev_priv = dev->dev_private; uint32_t inst; - NV_DEBUG(dev, "ch%d, nt=%d\n", channel, nt); + NV_DEBUG(dev, "ch%d\n", channel); - if (IS_G80) + if (dev_priv->chipset == 0x50) inst = NV50_PFIFO_CTX_TABLE_INSTANCE_MASK_G80; else inst = NV50_PFIFO_CTX_TABLE_INSTANCE_MASK_G84; nv_wr32(dev, NV50_PFIFO_CTX_TABLE(channel), inst); - - if (!nt) - nv50_fifo_init_thingo(dev); } static void @@ -133,12 +116,12 @@ nv50_fifo_init_context_table(struct drm_device *dev) for (i = 0; i < NV50_PFIFO_CTX_TABLE__SIZE; i++) { if (dev_priv->fifos[i]) - nv50_fifo_channel_enable(dev, i, true); + nv50_fifo_channel_enable(dev, i); else - nv50_fifo_channel_disable(dev, i, true); + nv50_fifo_channel_disable(dev, i); } - nv50_fifo_init_thingo(dev); + nv50_fifo_playlist_update(dev); } static void @@ -162,41 +145,38 @@ nv50_fifo_init_regs(struct drm_device *dev) nv_wr32(dev, 0x3270, 0); /* Enable dummy channels setup by nv50_instmem.c */ - nv50_fifo_channel_enable(dev, 0, true); - nv50_fifo_channel_enable(dev, 127, true); + nv50_fifo_channel_enable(dev, 0); + nv50_fifo_channel_enable(dev, 127); } int nv50_fifo_init(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nv50_fifo_priv *priv; + struct nouveau_fifo_engine *pfifo = &dev_priv->engine.fifo; int ret; NV_DEBUG(dev, "\n"); - priv = dev_priv->engine.fifo.priv; - if (priv) { - priv->cur_thingo = !priv->cur_thingo; + if (pfifo->playlist[0]) { + pfifo->cur_playlist = !pfifo->cur_playlist; goto just_reset; } - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - dev_priv->engine.fifo.priv = priv; - ret = nouveau_gpuobj_new_ref(dev, NULL, NULL, 0, 128*4, 0x1000, - NVOBJ_FLAG_ZERO_ALLOC, &priv->thingo[0]); + NVOBJ_FLAG_ZERO_ALLOC, + &pfifo->playlist[0]); if (ret) { - NV_ERROR(dev, "error creating thingo0: %d\n", ret); + NV_ERROR(dev, "error creating playlist 0: %d\n", ret); return ret; } ret = nouveau_gpuobj_new_ref(dev, NULL, NULL, 0, 128*4, 0x1000, - NVOBJ_FLAG_ZERO_ALLOC, &priv->thingo[1]); + NVOBJ_FLAG_ZERO_ALLOC, + &pfifo->playlist[1]); if (ret) { - NV_ERROR(dev, "error creating thingo1: %d\n", ret); + nouveau_gpuobj_ref_del(dev, &pfifo->playlist[0]); + NV_ERROR(dev, "error creating playlist 1: %d\n", ret); return ret; } @@ -216,18 +196,15 @@ void nv50_fifo_takedown(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nv50_fifo_priv *priv = dev_priv->engine.fifo.priv; + struct nouveau_fifo_engine *pfifo = &dev_priv->engine.fifo; NV_DEBUG(dev, "\n"); - if (!priv) + if (!pfifo->playlist[0]) return; - nouveau_gpuobj_ref_del(dev, &priv->thingo[0]); - nouveau_gpuobj_ref_del(dev, &priv->thingo[1]); - - dev_priv->engine.fifo.priv = NULL; - kfree(priv); + nouveau_gpuobj_ref_del(dev, &pfifo->playlist[0]); + nouveau_gpuobj_ref_del(dev, &pfifo->playlist[1]); } int @@ -248,7 +225,7 @@ nv50_fifo_create_context(struct nouveau_channel *chan) NV_DEBUG(dev, "ch%d\n", chan->id); - if (IS_G80) { + if (dev_priv->chipset == 0x50) { uint32_t ramin_poffset = chan->ramin->gpuobj->im_pramin->start; uint32_t ramin_voffset = chan->ramin->gpuobj->im_backing_start; @@ -281,10 +258,10 @@ nv50_fifo_create_context(struct nouveau_channel *chan) spin_lock_irqsave(&dev_priv->context_switch_lock, flags); - dev_priv->engine.instmem.prepare_access(dev, true); - nv_wo32(dev, ramfc, 0x48/4, chan->pushbuf->instance >> 4); - nv_wo32(dev, ramfc, 0x80/4, (0xc << 24) | (chan->ramht->instance >> 4)); + nv_wo32(dev, ramfc, 0x80/4, (0 << 27) /* 4KiB */ | + (4 << 24) /* SEARCH_FULL */ | + (chan->ramht->instance >> 4)); nv_wo32(dev, ramfc, 0x44/4, 0x2101ffff); nv_wo32(dev, ramfc, 0x60/4, 0x7fffffff); nv_wo32(dev, ramfc, 0x40/4, 0x00000000); @@ -295,7 +272,7 @@ nv50_fifo_create_context(struct nouveau_channel *chan) chan->dma.ib_base * 4); nv_wo32(dev, ramfc, 0x54/4, drm_order(chan->dma.ib_max + 1) << 16); - if (!IS_G80) { + if (dev_priv->chipset != 0x50) { nv_wo32(dev, chan->ramin->gpuobj, 0, chan->id); nv_wo32(dev, chan->ramin->gpuobj, 1, chan->ramfc->instance >> 8); @@ -304,16 +281,10 @@ nv50_fifo_create_context(struct nouveau_channel *chan) nv_wo32(dev, ramfc, 0x98/4, chan->ramin->instance >> 12); } - dev_priv->engine.instmem.finish_access(dev); - - ret = nv50_fifo_channel_enable(dev, chan->id, false); - if (ret) { - NV_ERROR(dev, "error enabling ch%d: %d\n", chan->id, ret); - spin_unlock_irqrestore(&dev_priv->context_switch_lock, flags); - nouveau_gpuobj_ref_del(dev, &chan->ramfc); - return ret; - } + dev_priv->engine.instmem.flush(dev); + nv50_fifo_channel_enable(dev, chan->id); + nv50_fifo_playlist_update(dev); spin_unlock_irqrestore(&dev_priv->context_switch_lock, flags); return 0; } @@ -328,11 +299,12 @@ nv50_fifo_destroy_context(struct nouveau_channel *chan) /* This will ensure the channel is seen as disabled. */ chan->ramfc = NULL; - nv50_fifo_channel_disable(dev, chan->id, false); + nv50_fifo_channel_disable(dev, chan->id); /* Dummy channel, also used on ch 127 */ if (chan->id == 0) - nv50_fifo_channel_disable(dev, 127, false); + nv50_fifo_channel_disable(dev, 127); + nv50_fifo_playlist_update(dev); nouveau_gpuobj_ref_del(dev, &ramfc); nouveau_gpuobj_ref_del(dev, &chan->cache); @@ -349,8 +321,6 @@ nv50_fifo_load_context(struct nouveau_channel *chan) NV_DEBUG(dev, "ch%d\n", chan->id); - dev_priv->engine.instmem.prepare_access(dev, false); - nv_wr32(dev, 0x3330, nv_ro32(dev, ramfc, 0x00/4)); nv_wr32(dev, 0x3334, nv_ro32(dev, ramfc, 0x04/4)); nv_wr32(dev, 0x3240, nv_ro32(dev, ramfc, 0x08/4)); @@ -396,7 +366,7 @@ nv50_fifo_load_context(struct nouveau_channel *chan) nv_wr32(dev, NV03_PFIFO_CACHE1_GET, 0); /* guessing that all the 0x34xx regs aren't on NV50 */ - if (!IS_G80) { + if (dev_priv->chipset != 0x50) { nv_wr32(dev, 0x340c, nv_ro32(dev, ramfc, 0x88/4)); nv_wr32(dev, 0x3400, nv_ro32(dev, ramfc, 0x8c/4)); nv_wr32(dev, 0x3404, nv_ro32(dev, ramfc, 0x90/4)); @@ -404,8 +374,6 @@ nv50_fifo_load_context(struct nouveau_channel *chan) nv_wr32(dev, 0x3410, nv_ro32(dev, ramfc, 0x98/4)); } - dev_priv->engine.instmem.finish_access(dev); - nv_wr32(dev, NV03_PFIFO_CACHE1_PUSH1, chan->id | (1<<16)); return 0; } @@ -434,8 +402,6 @@ nv50_fifo_unload_context(struct drm_device *dev) ramfc = chan->ramfc->gpuobj; cache = chan->cache->gpuobj; - dev_priv->engine.instmem.prepare_access(dev, true); - nv_wo32(dev, ramfc, 0x00/4, nv_rd32(dev, 0x3330)); nv_wo32(dev, ramfc, 0x04/4, nv_rd32(dev, 0x3334)); nv_wo32(dev, ramfc, 0x08/4, nv_rd32(dev, 0x3240)); @@ -482,7 +448,7 @@ nv50_fifo_unload_context(struct drm_device *dev) } /* guessing that all the 0x34xx regs aren't on NV50 */ - if (!IS_G80) { + if (dev_priv->chipset != 0x50) { nv_wo32(dev, ramfc, 0x84/4, ptr >> 1); nv_wo32(dev, ramfc, 0x88/4, nv_rd32(dev, 0x340c)); nv_wo32(dev, ramfc, 0x8c/4, nv_rd32(dev, 0x3400)); @@ -491,7 +457,7 @@ nv50_fifo_unload_context(struct drm_device *dev) nv_wo32(dev, ramfc, 0x98/4, nv_rd32(dev, 0x3410)); } - dev_priv->engine.instmem.finish_access(dev); + dev_priv->engine.instmem.flush(dev); /*XXX: probably reload ch127 (NULL) state back too */ nv_wr32(dev, NV03_PFIFO_CACHE1_PUSH1, 127); diff --git a/drivers/gpu/drm/nouveau/nv50_gpio.c b/drivers/gpu/drm/nouveau/nv50_gpio.c index bb47ad73726..b2fab2bf3d6 100644 --- a/drivers/gpu/drm/nouveau/nv50_gpio.c +++ b/drivers/gpu/drm/nouveau/nv50_gpio.c @@ -74,3 +74,38 @@ nv50_gpio_set(struct drm_device *dev, enum dcb_gpio_tag tag, int state) nv_wr32(dev, r, v); return 0; } + +void +nv50_gpio_irq_enable(struct drm_device *dev, enum dcb_gpio_tag tag, bool on) +{ + struct dcb_gpio_entry *gpio; + u32 reg, mask; + + gpio = nouveau_bios_gpio_entry(dev, tag); + if (!gpio) { + NV_ERROR(dev, "gpio tag 0x%02x not found\n", tag); + return; + } + + reg = gpio->line < 16 ? 0xe050 : 0xe070; + mask = 0x00010001 << (gpio->line & 0xf); + + nv_wr32(dev, reg + 4, mask); + nv_mask(dev, reg + 0, mask, on ? mask : 0); +} + +int +nv50_gpio_init(struct drm_device *dev) +{ + struct drm_nouveau_private *dev_priv = dev->dev_private; + + /* disable, and ack any pending gpio interrupts */ + nv_wr32(dev, 0xe050, 0x00000000); + nv_wr32(dev, 0xe054, 0xffffffff); + if (dev_priv->chipset >= 0x90) { + nv_wr32(dev, 0xe070, 0x00000000); + nv_wr32(dev, 0xe074, 0xffffffff); + } + + return 0; +} diff --git a/drivers/gpu/drm/nouveau/nv50_graph.c b/drivers/gpu/drm/nouveau/nv50_graph.c index b203d06f601..1413028e158 100644 --- a/drivers/gpu/drm/nouveau/nv50_graph.c +++ b/drivers/gpu/drm/nouveau/nv50_graph.c @@ -30,8 +30,6 @@ #include "nouveau_grctx.h" -#define IS_G80 ((dev_priv->chipset & 0xf0) == 0x50) - static void nv50_graph_init_reset(struct drm_device *dev) { @@ -103,37 +101,33 @@ static int nv50_graph_init_ctxctl(struct drm_device *dev) { struct drm_nouveau_private *dev_priv = dev->dev_private; + struct nouveau_grctx ctx = {}; + uint32_t *cp; + int i; NV_DEBUG(dev, "\n"); - if (nouveau_ctxfw) { - nouveau_grctx_prog_load(dev); - dev_priv->engine.graph.grctx_size = 0x70000; + cp = kmalloc(512 * 4, GFP_KERNEL); + if (!cp) { + NV_ERROR(dev, "failed to allocate ctxprog\n"); + dev_priv->engine.graph.accel_blocked = true; + return 0; } - if (!dev_priv->engine.graph.ctxprog) { - struct nouveau_grctx ctx = {}; - uint32_t *cp = kmalloc(512 * 4, GFP_KERNEL); - int i; - if (!cp) { - NV_ERROR(dev, "Couldn't alloc ctxprog! Disabling acceleration.\n"); - dev_priv->engine.graph.accel_blocked = true; - return 0; - } - ctx.dev = dev; - ctx.mode = NOUVEAU_GRCTX_PROG; - ctx.data = cp; - ctx.ctxprog_max = 512; - if (!nv50_grctx_init(&ctx)) { - dev_priv->engine.graph.grctx_size = ctx.ctxvals_pos * 4; - - nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_INDEX, 0); - for (i = 0; i < ctx.ctxprog_len; i++) - nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_DATA, cp[i]); - } else { - dev_priv->engine.graph.accel_blocked = true; - } - kfree(cp); + + ctx.dev = dev; + ctx.mode = NOUVEAU_GRCTX_PROG; + ctx.data = cp; + ctx.ctxprog_max = 512; + if (!nv50_grctx_init(&ctx)) { + dev_priv->engine.graph.grctx_size = ctx.ctxvals_pos * 4; + + nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_INDEX, 0); + for (i = 0; i < ctx.ctxprog_len; i++) + nv_wr32(dev, NV40_PGRAPH_CTXCTL_UCODE_DATA, cp[i]); + } else { + dev_priv->engine.graph.accel_blocked = true; } + kfree(cp); nv_wr32(dev, 0x400320, 4); nv_wr32(dev, NV40_PGRAPH_CTXCTL_CUR, 0); @@ -164,7 +158,6 @@ void nv50_graph_takedown(struct drm_device *dev) { NV_DEBUG(dev, "\n"); - nouveau_grctx_fini(dev); } void @@ -212,8 +205,9 @@ nv50_graph_create_context(struct nouveau_channel *chan) struct drm_device *dev = chan->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_gpuobj *ramin = chan->ramin->gpuobj; - struct nouveau_gpuobj *ctx; + struct nouveau_gpuobj *obj; struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph; + struct nouveau_grctx ctx = {}; int hdr, ret; NV_DEBUG(dev, "ch%d\n", chan->id); @@ -223,10 +217,9 @@ nv50_graph_create_context(struct nouveau_channel *chan) NVOBJ_FLAG_ZERO_FREE, &chan->ramin_grctx); if (ret) return ret; - ctx = chan->ramin_grctx->gpuobj; + obj = chan->ramin_grctx->gpuobj; - hdr = IS_G80 ? 0x200 : 0x20; - dev_priv->engine.instmem.prepare_access(dev, true); + hdr = (dev_priv->chipset == 0x50) ? 0x200 : 0x20; nv_wo32(dev, ramin, (hdr + 0x00)/4, 0x00190002); nv_wo32(dev, ramin, (hdr + 0x04)/4, chan->ramin_grctx->instance + pgraph->grctx_size - 1); @@ -234,21 +227,15 @@ nv50_graph_create_context(struct nouveau_channel *chan) nv_wo32(dev, ramin, (hdr + 0x0c)/4, 0); nv_wo32(dev, ramin, (hdr + 0x10)/4, 0); nv_wo32(dev, ramin, (hdr + 0x14)/4, 0x00010000); - dev_priv->engine.instmem.finish_access(dev); - - dev_priv->engine.instmem.prepare_access(dev, true); - if (!pgraph->ctxprog) { - struct nouveau_grctx ctx = {}; - ctx.dev = chan->dev; - ctx.mode = NOUVEAU_GRCTX_VALS; - ctx.data = chan->ramin_grctx->gpuobj; - nv50_grctx_init(&ctx); - } else { - nouveau_grctx_vals_load(dev, ctx); - } - nv_wo32(dev, ctx, 0x00000/4, chan->ramin->instance >> 12); - dev_priv->engine.instmem.finish_access(dev); + ctx.dev = chan->dev; + ctx.mode = NOUVEAU_GRCTX_VALS; + ctx.data = obj; + nv50_grctx_init(&ctx); + + nv_wo32(dev, obj, 0x00000/4, chan->ramin->instance >> 12); + + dev_priv->engine.instmem.flush(dev); return 0; } @@ -257,17 +244,16 @@ nv50_graph_destroy_context(struct nouveau_channel *chan) { struct drm_device *dev = chan->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; - int i, hdr = IS_G80 ? 0x200 : 0x20; + int i, hdr = (dev_priv->chipset == 0x50) ? 0x200 : 0x20; NV_DEBUG(dev, "ch%d\n", chan->id); if (!chan->ramin || !chan->ramin->gpuobj) return; - dev_priv->engine.instmem.prepare_access(dev, true); for (i = hdr; i < hdr + 24; i += 4) nv_wo32(dev, chan->ramin->gpuobj, i/4, 0); - dev_priv->engine.instmem.finish_access(dev); + dev_priv->engine.instmem.flush(dev); nouveau_gpuobj_ref_del(dev, &chan->ramin_grctx); } diff --git a/drivers/gpu/drm/nouveau/nv50_instmem.c b/drivers/gpu/drm/nouveau/nv50_instmem.c index 5f21df31f3a..37c7b48ab24 100644 --- a/drivers/gpu/drm/nouveau/nv50_instmem.c +++ b/drivers/gpu/drm/nouveau/nv50_instmem.c @@ -35,8 +35,6 @@ struct nv50_instmem_priv { struct nouveau_gpuobj_ref *pramin_pt; struct nouveau_gpuobj_ref *pramin_bar; struct nouveau_gpuobj_ref *fb_bar; - - bool last_access_wr; }; #define NV50_INSTMEM_PAGE_SHIFT 12 @@ -147,7 +145,7 @@ nv50_instmem_init(struct drm_device *dev) if (ret) return ret; - if (nouveau_mem_init_heap(&chan->ramin_heap, c_base, c_size - c_base)) + if (drm_mm_init(&chan->ramin_heap, c_base, c_size - c_base)) return -ENOMEM; /* RAMFC + zero channel's PRAMIN up to start of VM pagedir */ @@ -241,7 +239,7 @@ nv50_instmem_init(struct drm_device *dev) return ret; BAR0_WI32(priv->fb_bar->gpuobj, 0x00, 0x7fc00000); BAR0_WI32(priv->fb_bar->gpuobj, 0x04, 0x40000000 + - drm_get_resource_len(dev, 1) - 1); + pci_resource_len(dev->pdev, 1) - 1); BAR0_WI32(priv->fb_bar->gpuobj, 0x08, 0x40000000); BAR0_WI32(priv->fb_bar->gpuobj, 0x0c, 0x00000000); BAR0_WI32(priv->fb_bar->gpuobj, 0x10, 0x00000000); @@ -262,23 +260,18 @@ nv50_instmem_init(struct drm_device *dev) /* Assume that praying isn't enough, check that we can re-read the * entire fake channel back from the PRAMIN BAR */ - dev_priv->engine.instmem.prepare_access(dev, false); for (i = 0; i < c_size; i += 4) { if (nv_rd32(dev, NV_RAMIN + i) != nv_ri32(dev, i)) { NV_ERROR(dev, "Error reading back PRAMIN at 0x%08x\n", i); - dev_priv->engine.instmem.finish_access(dev); return -EINVAL; } } - dev_priv->engine.instmem.finish_access(dev); nv_wr32(dev, NV50_PUNK_BAR0_PRAMIN, save_nv001700); /* Global PRAMIN heap */ - if (nouveau_mem_init_heap(&dev_priv->ramin_heap, - c_size, dev_priv->ramin_size - c_size)) { - dev_priv->ramin_heap = NULL; + if (drm_mm_init(&dev_priv->ramin_heap, c_size, dev_priv->ramin_size - c_size)) { NV_ERROR(dev, "Failed to init RAMIN heap\n"); } @@ -321,7 +314,7 @@ nv50_instmem_takedown(struct drm_device *dev) nouveau_gpuobj_del(dev, &chan->vm_pd); nouveau_gpuobj_ref_del(dev, &chan->ramfc); nouveau_gpuobj_ref_del(dev, &chan->ramin); - nouveau_mem_takedown(&chan->ramin_heap); + drm_mm_takedown(&chan->ramin_heap); dev_priv->fifos[0] = dev_priv->fifos[127] = NULL; kfree(chan); @@ -436,14 +429,14 @@ nv50_instmem_bind(struct drm_device *dev, struct nouveau_gpuobj *gpuobj) if (!gpuobj->im_backing || !gpuobj->im_pramin || gpuobj->im_bound) return -EINVAL; - NV_DEBUG(dev, "st=0x%0llx sz=0x%0llx\n", + NV_DEBUG(dev, "st=0x%lx sz=0x%lx\n", gpuobj->im_pramin->start, gpuobj->im_pramin->size); pte = (gpuobj->im_pramin->start >> 12) << 1; pte_end = ((gpuobj->im_pramin->size >> 12) << 1) + pte; vram = gpuobj->im_backing_start; - NV_DEBUG(dev, "pramin=0x%llx, pte=%d, pte_end=%d\n", + NV_DEBUG(dev, "pramin=0x%lx, pte=%d, pte_end=%d\n", gpuobj->im_pramin->start, pte, pte_end); NV_DEBUG(dev, "first vram page: 0x%08x\n", gpuobj->im_backing_start); @@ -453,27 +446,15 @@ nv50_instmem_bind(struct drm_device *dev, struct nouveau_gpuobj *gpuobj) vram |= 0x30; } - dev_priv->engine.instmem.prepare_access(dev, true); while (pte < pte_end) { nv_wo32(dev, pramin_pt, pte++, lower_32_bits(vram)); nv_wo32(dev, pramin_pt, pte++, upper_32_bits(vram)); vram += NV50_INSTMEM_PAGE_SIZE; } - dev_priv->engine.instmem.finish_access(dev); - - nv_wr32(dev, 0x100c80, 0x00040001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (1)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - return -EBUSY; - } + dev_priv->engine.instmem.flush(dev); - nv_wr32(dev, 0x100c80, 0x00060001); - if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) { - NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n"); - NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80)); - return -EBUSY; - } + nv50_vm_flush(dev, 4); + nv50_vm_flush(dev, 6); gpuobj->im_bound = 1; return 0; @@ -492,36 +473,37 @@ nv50_instmem_unbind(struct drm_device *dev, struct nouveau_gpuobj *gpuobj) pte = (gpuobj->im_pramin->start >> 12) << 1; pte_end = ((gpuobj->im_pramin->size >> 12) << 1) + pte; - dev_priv->engine.instmem.prepare_access(dev, true); while (pte < pte_end) { nv_wo32(dev, priv->pramin_pt->gpuobj, pte++, 0x00000000); nv_wo32(dev, priv->pramin_pt->gpuobj, pte++, 0x00000000); } - dev_priv->engine.instmem.finish_access(dev); + dev_priv->engine.instmem.flush(dev); gpuobj->im_bound = 0; return 0; } void -nv50_instmem_prepare_access(struct drm_device *dev, bool write) +nv50_instmem_flush(struct drm_device *dev) { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nv50_instmem_priv *priv = dev_priv->engine.instmem.priv; - - priv->last_access_wr = write; + nv_wr32(dev, 0x00330c, 0x00000001); + if (!nv_wait(0x00330c, 0x00000002, 0x00000000)) + NV_ERROR(dev, "PRAMIN flush timeout\n"); } void -nv50_instmem_finish_access(struct drm_device *dev) +nv84_instmem_flush(struct drm_device *dev) { - struct drm_nouveau_private *dev_priv = dev->dev_private; - struct nv50_instmem_priv *priv = dev_priv->engine.instmem.priv; + nv_wr32(dev, 0x070000, 0x00000001); + if (!nv_wait(0x070000, 0x00000002, 0x00000000)) + NV_ERROR(dev, "PRAMIN flush timeout\n"); +} - if (priv->last_access_wr) { - nv_wr32(dev, 0x070000, 0x00000001); - if (!nv_wait(0x070000, 0x00000001, 0x00000000)) - NV_ERROR(dev, "PRAMIN flush timeout\n"); - } +void +nv50_vm_flush(struct drm_device *dev, int engine) +{ + nv_wr32(dev, 0x100c80, (engine << 16) | 1); + if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) + NV_ERROR(dev, "vm flush timeout: engine %d\n", engine); } diff --git a/drivers/gpu/drm/nouveau/nv50_sor.c b/drivers/gpu/drm/nouveau/nv50_sor.c index 812778db76a..bcd4cf84a7e 100644 --- a/drivers/gpu/drm/nouveau/nv50_sor.c +++ b/drivers/gpu/drm/nouveau/nv50_sor.c @@ -37,52 +37,32 @@ #include "nv50_display.h" static void -nv50_sor_disconnect(struct nouveau_encoder *nv_encoder) +nv50_sor_disconnect(struct drm_encoder *encoder) { - struct drm_device *dev = to_drm_encoder(nv_encoder)->dev; + struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); + struct drm_device *dev = encoder->dev; struct drm_nouveau_private *dev_priv = dev->dev_private; struct nouveau_channel *evo = dev_priv->evo; int ret; + if (!nv_encoder->crtc) + return; + nv50_crtc_blank(nouveau_crtc(nv_encoder->crtc), true); + NV_DEBUG_KMS(dev, "Disconnecting SOR %d\n", nv_encoder->or); - ret = RING_SPACE(evo, 2); + ret = RING_SPACE(evo, 4); if (ret) { NV_ERROR(dev, "no space while disconnecting SOR\n"); return; } BEGIN_RING(evo, 0, NV50_EVO_SOR(nv_encoder->or, MODE_CTRL), 1); - OUT_RING(evo, 0); -} - -static void -nv50_sor_dp_link_train(struct drm_encoder *encoder) -{ - struct drm_device *dev = encoder->dev; - struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); - struct bit_displayport_encoder_table *dpe; - int dpe_headerlen; - - dpe = nouveau_bios_dp_table(dev, nv_encoder->dcb, &dpe_headerlen); - if (!dpe) { - NV_ERROR(dev, "SOR-%d: no DP encoder table!\n", nv_encoder->or); - return; - } + OUT_RING (evo, 0); + BEGIN_RING(evo, 0, NV50_EVO_UPDATE, 1); + OUT_RING (evo, 0); - if (dpe->script0) { - NV_DEBUG_KMS(dev, "SOR-%d: running DP script 0\n", nv_encoder->or); - nouveau_bios_run_init_table(dev, le16_to_cpu(dpe->script0), - nv_encoder->dcb); - } - - if (!nouveau_dp_link_train(encoder)) - NV_ERROR(dev, "SOR-%d: link training failed\n", nv_encoder->or); - - if (dpe->script1) { - NV_DEBUG_KMS(dev, "SOR-%d: running DP script 1\n", nv_encoder->or); - nouveau_bios_run_init_table(dev, le16_to_cpu(dpe->script1), - nv_encoder->dcb); - } + nv_encoder->crtc = NULL; + nv_encoder->last_dpms = DRM_MODE_DPMS_OFF; } static void @@ -94,14 +74,16 @@ nv50_sor_dpms(struct drm_encoder *encoder, int mode) uint32_t val; int or = nv_encoder->or; - NV_DEBUG_KMS(dev, "or %d mode %d\n", or, mode); + NV_DEBUG_KMS(dev, "or %d type %d mode %d\n", or, nv_encoder->dcb->type, mode); nv_encoder->last_dpms = mode; list_for_each_entry(enc, &dev->mode_config.encoder_list, head) { struct nouveau_encoder *nvenc = nouveau_encoder(enc); if (nvenc == nv_encoder || - nvenc->disconnect != nv50_sor_disconnect || + (nvenc->dcb->type != OUTPUT_TMDS && + nvenc->dcb->type != OUTPUT_LVDS && + nvenc->dcb->type != OUTPUT_DP) || nvenc->dcb->or != nv_encoder->dcb->or) continue; @@ -133,8 +115,22 @@ nv50_sor_dpms(struct drm_encoder *encoder, int mode) nv_rd32(dev, NV50_PDISPLAY_SOR_DPMS_STATE(or))); } - if (nv_encoder->dcb->type == OUTPUT_DP && mode == DRM_MODE_DPMS_ON) - nv50_sor_dp_link_train(encoder); + if (nv_encoder->dcb->type == OUTPUT_DP) { + struct nouveau_i2c_chan *auxch; + + auxch = nouveau_i2c_find(dev, nv_encoder->dcb->i2c_index); + if (!auxch) + return; + + if (mode == DRM_MODE_DPMS_ON) { + u8 status = DP_SET_POWER_D0; + nouveau_dp_auxch(auxch, 8, DP_SET_POWER, &status, 1); + nouveau_dp_link_train(encoder); + } else { + u8 status = DP_SET_POWER_D3; + nouveau_dp_auxch(auxch, 8, DP_SET_POWER, &status, 1); + } + } } static void @@ -196,7 +192,8 @@ nv50_sor_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, uint32_t mode_ctl = 0; int ret; - NV_DEBUG_KMS(dev, "or %d\n", nv_encoder->or); + NV_DEBUG_KMS(dev, "or %d type %d -> crtc %d\n", + nv_encoder->or, nv_encoder->dcb->type, crtc->index); nv50_sor_dpms(encoder, DRM_MODE_DPMS_ON); @@ -239,6 +236,14 @@ nv50_sor_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, } BEGIN_RING(evo, 0, NV50_EVO_SOR(nv_encoder->or, MODE_CTRL), 1); OUT_RING(evo, mode_ctl); + + nv_encoder->crtc = encoder->crtc; +} + +static struct drm_crtc * +nv50_sor_crtc_get(struct drm_encoder *encoder) +{ + return nouveau_encoder(encoder)->crtc; } static const struct drm_encoder_helper_funcs nv50_sor_helper_funcs = { @@ -249,7 +254,9 @@ static const struct drm_encoder_helper_funcs nv50_sor_helper_funcs = { .prepare = nv50_sor_prepare, .commit = nv50_sor_commit, .mode_set = nv50_sor_mode_set, - .detect = NULL + .get_crtc = nv50_sor_crtc_get, + .detect = NULL, + .disable = nv50_sor_disconnect }; static void @@ -272,32 +279,22 @@ static const struct drm_encoder_funcs nv50_sor_encoder_funcs = { }; int -nv50_sor_create(struct drm_device *dev, struct dcb_entry *entry) +nv50_sor_create(struct drm_connector *connector, struct dcb_entry *entry) { struct nouveau_encoder *nv_encoder = NULL; + struct drm_device *dev = connector->dev; struct drm_encoder *encoder; - bool dum; int type; NV_DEBUG_KMS(dev, "\n"); switch (entry->type) { case OUTPUT_TMDS: - NV_INFO(dev, "Detected a TMDS output\n"); + case OUTPUT_DP: type = DRM_MODE_ENCODER_TMDS; break; case OUTPUT_LVDS: - NV_INFO(dev, "Detected a LVDS output\n"); type = DRM_MODE_ENCODER_LVDS; - - if (nouveau_bios_parse_lvds_table(dev, 0, &dum, &dum)) { - NV_ERROR(dev, "Failed parsing LVDS table\n"); - return -EINVAL; - } - break; - case OUTPUT_DP: - NV_INFO(dev, "Detected a DP output\n"); - type = DRM_MODE_ENCODER_TMDS; break; default: return -EINVAL; @@ -310,8 +307,7 @@ nv50_sor_create(struct drm_device *dev, struct dcb_entry *entry) nv_encoder->dcb = entry; nv_encoder->or = ffs(entry->or) - 1; - - nv_encoder->disconnect = nv50_sor_disconnect; + nv_encoder->last_dpms = DRM_MODE_DPMS_OFF; drm_encoder_init(dev, encoder, &nv50_sor_encoder_funcs, type); drm_encoder_helper_add(encoder, &nv50_sor_helper_funcs); @@ -342,5 +338,6 @@ nv50_sor_create(struct drm_device *dev, struct dcb_entry *entry) nv_encoder->dp.mc_unknown = 5; } + drm_mode_connector_attach_encoder(connector, encoder); return 0; } diff --git a/drivers/gpu/drm/nouveau/nvreg.h b/drivers/gpu/drm/nouveau/nvreg.h index 5998c35237b..ad64673ace1 100644 --- a/drivers/gpu/drm/nouveau/nvreg.h +++ b/drivers/gpu/drm/nouveau/nvreg.h @@ -147,28 +147,6 @@ # define NV_VIO_GX_DONT_CARE_INDEX 0x07 # define NV_VIO_GX_BIT_MASK_INDEX 0x08 -#define NV_PFB_BOOT_0 0x00100000 -#define NV_PFB_CFG0 0x00100200 -#define NV_PFB_CFG1 0x00100204 -#define NV_PFB_CSTATUS 0x0010020C -#define NV_PFB_REFCTRL 0x00100210 -# define NV_PFB_REFCTRL_VALID_1 (1 << 31) -#define NV_PFB_PAD 0x0010021C -# define NV_PFB_PAD_CKE_NORMAL (1 << 0) -#define NV_PFB_TILE_NV10 0x00100240 -#define NV_PFB_TILE_SIZE_NV10 0x00100244 -#define NV_PFB_REF 0x001002D0 -# define NV_PFB_REF_CMD_REFRESH (1 << 0) -#define NV_PFB_PRE 0x001002D4 -# define NV_PFB_PRE_CMD_PRECHARGE (1 << 0) -#define NV_PFB_CLOSE_PAGE2 0x0010033C -#define NV_PFB_TILE_NV40 0x00100600 -#define NV_PFB_TILE_SIZE_NV40 0x00100604 - -#define NV_PEXTDEV_BOOT_0 0x00101000 -# define NV_PEXTDEV_BOOT_0_STRAP_FP_IFACE_12BIT (8 << 12) -#define NV_PEXTDEV_BOOT_3 0x0010100c - #define NV_PCRTC_INTR_0 0x00600100 # define NV_PCRTC_INTR_0_VBLANK (1 << 0) #define NV_PCRTC_INTR_EN_0 0x00600140 diff --git a/drivers/gpu/drm/r128/r128_cce.c b/drivers/gpu/drm/r128/r128_cce.c index e671d0e74d4..570e190710b 100644 --- a/drivers/gpu/drm/r128/r128_cce.c +++ b/drivers/gpu/drm/r128/r128_cce.c @@ -44,7 +44,7 @@ MODULE_FIRMWARE(FIRMWARE_NAME); -static int R128_READ_PLL(struct drm_device * dev, int addr) +static int R128_READ_PLL(struct drm_device *dev, int addr) { drm_r128_private_t *dev_priv = dev->dev_private; @@ -53,7 +53,7 @@ static int R128_READ_PLL(struct drm_device * dev, int addr) } #if R128_FIFO_DEBUG -static void r128_status(drm_r128_private_t * dev_priv) +static void r128_status(drm_r128_private_t *dev_priv) { printk("GUI_STAT = 0x%08x\n", (unsigned int)R128_READ(R128_GUI_STAT)); @@ -74,7 +74,7 @@ static void r128_status(drm_r128_private_t * dev_priv) * Engine, FIFO control */ -static int r128_do_pixcache_flush(drm_r128_private_t * dev_priv) +static int r128_do_pixcache_flush(drm_r128_private_t *dev_priv) { u32 tmp; int i; @@ -83,9 +83,8 @@ static int r128_do_pixcache_flush(drm_r128_private_t * dev_priv) R128_WRITE(R128_PC_NGUI_CTLSTAT, tmp); for (i = 0; i < dev_priv->usec_timeout; i++) { - if (!(R128_READ(R128_PC_NGUI_CTLSTAT) & R128_PC_BUSY)) { + if (!(R128_READ(R128_PC_NGUI_CTLSTAT) & R128_PC_BUSY)) return 0; - } DRM_UDELAY(1); } @@ -95,7 +94,7 @@ static int r128_do_pixcache_flush(drm_r128_private_t * dev_priv) return -EBUSY; } -static int r128_do_wait_for_fifo(drm_r128_private_t * dev_priv, int entries) +static int r128_do_wait_for_fifo(drm_r128_private_t *dev_priv, int entries) { int i; @@ -112,7 +111,7 @@ static int r128_do_wait_for_fifo(drm_r128_private_t * dev_priv, int entries) return -EBUSY; } -static int r128_do_wait_for_idle(drm_r128_private_t * dev_priv) +static int r128_do_wait_for_idle(drm_r128_private_t *dev_priv) { int i, ret; @@ -189,7 +188,7 @@ out_release: * prior to a wait for idle, as it informs the engine that the command * stream is ending. */ -static void r128_do_cce_flush(drm_r128_private_t * dev_priv) +static void r128_do_cce_flush(drm_r128_private_t *dev_priv) { u32 tmp; @@ -199,7 +198,7 @@ static void r128_do_cce_flush(drm_r128_private_t * dev_priv) /* Wait for the CCE to go idle. */ -int r128_do_cce_idle(drm_r128_private_t * dev_priv) +int r128_do_cce_idle(drm_r128_private_t *dev_priv) { int i; @@ -225,7 +224,7 @@ int r128_do_cce_idle(drm_r128_private_t * dev_priv) /* Start the Concurrent Command Engine. */ -static void r128_do_cce_start(drm_r128_private_t * dev_priv) +static void r128_do_cce_start(drm_r128_private_t *dev_priv) { r128_do_wait_for_idle(dev_priv); @@ -242,7 +241,7 @@ static void r128_do_cce_start(drm_r128_private_t * dev_priv) * commands, so you must wait for the CCE command stream to complete * before calling this routine. */ -static void r128_do_cce_reset(drm_r128_private_t * dev_priv) +static void r128_do_cce_reset(drm_r128_private_t *dev_priv) { R128_WRITE(R128_PM4_BUFFER_DL_WPTR, 0); R128_WRITE(R128_PM4_BUFFER_DL_RPTR, 0); @@ -253,7 +252,7 @@ static void r128_do_cce_reset(drm_r128_private_t * dev_priv) * commands, so you must flush the command stream and wait for the CCE * to go idle before calling this routine. */ -static void r128_do_cce_stop(drm_r128_private_t * dev_priv) +static void r128_do_cce_stop(drm_r128_private_t *dev_priv) { R128_WRITE(R128_PM4_MICRO_CNTL, 0); R128_WRITE(R128_PM4_BUFFER_CNTL, @@ -264,7 +263,7 @@ static void r128_do_cce_stop(drm_r128_private_t * dev_priv) /* Reset the engine. This will stop the CCE if it is running. */ -static int r128_do_engine_reset(struct drm_device * dev) +static int r128_do_engine_reset(struct drm_device *dev) { drm_r128_private_t *dev_priv = dev->dev_private; u32 clock_cntl_index, mclk_cntl, gen_reset_cntl; @@ -301,8 +300,8 @@ static int r128_do_engine_reset(struct drm_device * dev) return 0; } -static void r128_cce_init_ring_buffer(struct drm_device * dev, - drm_r128_private_t * dev_priv) +static void r128_cce_init_ring_buffer(struct drm_device *dev, + drm_r128_private_t *dev_priv) { u32 ring_start; u32 tmp; @@ -340,7 +339,7 @@ static void r128_cce_init_ring_buffer(struct drm_device * dev, R128_WRITE(R128_BUS_CNTL, tmp); } -static int r128_do_init_cce(struct drm_device * dev, drm_r128_init_t * init) +static int r128_do_init_cce(struct drm_device *dev, drm_r128_init_t *init) { drm_r128_private_t *dev_priv; int rc; @@ -588,7 +587,7 @@ static int r128_do_init_cce(struct drm_device * dev, drm_r128_init_t * init) return rc; } -int r128_do_cleanup_cce(struct drm_device * dev) +int r128_do_cleanup_cce(struct drm_device *dev) { /* Make sure interrupts are disabled here because the uninstall ioctl @@ -682,9 +681,8 @@ int r128_cce_stop(struct drm_device *dev, void *data, struct drm_file *file_priv /* Flush any pending CCE commands. This ensures any outstanding * commands are exectuted by the engine before we turn it off. */ - if (stop->flush) { + if (stop->flush) r128_do_cce_flush(dev_priv); - } /* If we fail to make the engine go idle, we return an error * code so that the DRM ioctl wrapper can try again. @@ -735,9 +733,8 @@ int r128_cce_idle(struct drm_device *dev, void *data, struct drm_file *file_priv DEV_INIT_TEST_WITH_RETURN(dev_priv); - if (dev_priv->cce_running) { + if (dev_priv->cce_running) r128_do_cce_flush(dev_priv); - } return r128_do_cce_idle(dev_priv); } @@ -765,7 +762,7 @@ int r128_fullscreen(struct drm_device *dev, void *data, struct drm_file *file_pr #define R128_BUFFER_FREE 0 #if 0 -static int r128_freelist_init(struct drm_device * dev) +static int r128_freelist_init(struct drm_device *dev) { struct drm_device_dma *dma = dev->dma; drm_r128_private_t *dev_priv = dev->dev_private; @@ -848,7 +845,7 @@ static struct drm_buf *r128_freelist_get(struct drm_device * dev) return NULL; } -void r128_freelist_reset(struct drm_device * dev) +void r128_freelist_reset(struct drm_device *dev) { struct drm_device_dma *dma = dev->dma; int i; @@ -864,7 +861,7 @@ void r128_freelist_reset(struct drm_device * dev) * CCE command submission */ -int r128_wait_ring(drm_r128_private_t * dev_priv, int n) +int r128_wait_ring(drm_r128_private_t *dev_priv, int n) { drm_r128_ring_buffer_t *ring = &dev_priv->ring; int i; @@ -881,9 +878,9 @@ int r128_wait_ring(drm_r128_private_t * dev_priv, int n) return -EBUSY; } -static int r128_cce_get_buffers(struct drm_device * dev, +static int r128_cce_get_buffers(struct drm_device *dev, struct drm_file *file_priv, - struct drm_dma * d) + struct drm_dma *d) { int i; struct drm_buf *buf; @@ -933,9 +930,8 @@ int r128_cce_buffers(struct drm_device *dev, void *data, struct drm_file *file_p d->granted_count = 0; - if (d->request_count) { + if (d->request_count) ret = r128_cce_get_buffers(dev, file_priv, d); - } return ret; } diff --git a/drivers/gpu/drm/r128/r128_drv.c b/drivers/gpu/drm/r128/r128_drv.c index b806fdcc717..1e2971f13aa 100644 --- a/drivers/gpu/drm/r128/r128_drv.c +++ b/drivers/gpu/drm/r128/r128_drv.c @@ -85,7 +85,7 @@ static struct drm_driver driver = { .patchlevel = DRIVER_PATCHLEVEL, }; -int r128_driver_load(struct drm_device * dev, unsigned long flags) +int r128_driver_load(struct drm_device *dev, unsigned long flags) { return drm_vblank_init(dev, 1); } diff --git a/drivers/gpu/drm/r128/r128_drv.h b/drivers/gpu/drm/r128/r128_drv.h index 3c60829d82e..930c71b2fb5 100644 --- a/drivers/gpu/drm/r128/r128_drv.h +++ b/drivers/gpu/drm/r128/r128_drv.h @@ -53,7 +53,7 @@ #define DRIVER_MINOR 5 #define DRIVER_PATCHLEVEL 0 -#define GET_RING_HEAD(dev_priv) R128_READ( R128_PM4_BUFFER_DL_RPTR ) +#define GET_RING_HEAD(dev_priv) R128_READ(R128_PM4_BUFFER_DL_RPTR) typedef struct drm_r128_freelist { unsigned int age; @@ -144,23 +144,23 @@ extern int r128_engine_reset(struct drm_device *dev, void *data, struct drm_file extern int r128_fullscreen(struct drm_device *dev, void *data, struct drm_file *file_priv); extern int r128_cce_buffers(struct drm_device *dev, void *data, struct drm_file *file_priv); -extern void r128_freelist_reset(struct drm_device * dev); +extern void r128_freelist_reset(struct drm_device *dev); -extern int r128_wait_ring(drm_r128_private_t * dev_priv, int n); +extern int r128_wait_ring(drm_r128_private_t *dev_priv, int n); -extern int r128_do_cce_idle(drm_r128_private_t * dev_priv); -extern int r128_do_cleanup_cce(struct drm_device * dev); +extern int r128_do_cce_idle(drm_r128_private_t *dev_priv); +extern int r128_do_cleanup_cce(struct drm_device *dev); extern int r128_enable_vblank(struct drm_device *dev, int crtc); extern void r128_disable_vblank(struct drm_device *dev, int crtc); extern u32 r128_get_vblank_counter(struct drm_device *dev, int crtc); extern irqreturn_t r128_driver_irq_handler(DRM_IRQ_ARGS); -extern void r128_driver_irq_preinstall(struct drm_device * dev); +extern void r128_driver_irq_preinstall(struct drm_device *dev); extern int r128_driver_irq_postinstall(struct drm_device *dev); -extern void r128_driver_irq_uninstall(struct drm_device * dev); -extern void r128_driver_lastclose(struct drm_device * dev); -extern int r128_driver_load(struct drm_device * dev, unsigned long flags); -extern void r128_driver_preclose(struct drm_device * dev, +extern void r128_driver_irq_uninstall(struct drm_device *dev); +extern void r128_driver_lastclose(struct drm_device *dev); +extern int r128_driver_load(struct drm_device *dev, unsigned long flags); +extern void r128_driver_preclose(struct drm_device *dev, struct drm_file *file_priv); extern long r128_compat_ioctl(struct file *filp, unsigned int cmd, @@ -390,27 +390,27 @@ extern long r128_compat_ioctl(struct file *filp, unsigned int cmd, #define R128_PCIGART_TABLE_SIZE 32768 -#define R128_READ(reg) DRM_READ32( dev_priv->mmio, (reg) ) -#define R128_WRITE(reg,val) DRM_WRITE32( dev_priv->mmio, (reg), (val) ) -#define R128_READ8(reg) DRM_READ8( dev_priv->mmio, (reg) ) -#define R128_WRITE8(reg,val) DRM_WRITE8( dev_priv->mmio, (reg), (val) ) +#define R128_READ(reg) DRM_READ32(dev_priv->mmio, (reg)) +#define R128_WRITE(reg, val) DRM_WRITE32(dev_priv->mmio, (reg), (val)) +#define R128_READ8(reg) DRM_READ8(dev_priv->mmio, (reg)) +#define R128_WRITE8(reg, val) DRM_WRITE8(dev_priv->mmio, (reg), (val)) -#define R128_WRITE_PLL(addr,val) \ +#define R128_WRITE_PLL(addr, val) \ do { \ R128_WRITE8(R128_CLOCK_CNTL_INDEX, \ ((addr) & 0x1f) | R128_PLL_WR_EN); \ R128_WRITE(R128_CLOCK_CNTL_DATA, (val)); \ } while (0) -#define CCE_PACKET0( reg, n ) (R128_CCE_PACKET0 | \ +#define CCE_PACKET0(reg, n) (R128_CCE_PACKET0 | \ ((n) << 16) | ((reg) >> 2)) -#define CCE_PACKET1( reg0, reg1 ) (R128_CCE_PACKET1 | \ +#define CCE_PACKET1(reg0, reg1) (R128_CCE_PACKET1 | \ (((reg1) >> 2) << 11) | ((reg0) >> 2)) #define CCE_PACKET2() (R128_CCE_PACKET2) -#define CCE_PACKET3( pkt, n ) (R128_CCE_PACKET3 | \ +#define CCE_PACKET3(pkt, n) (R128_CCE_PACKET3 | \ (pkt) | ((n) << 16)) -static __inline__ void r128_update_ring_snapshot(drm_r128_private_t * dev_priv) +static __inline__ void r128_update_ring_snapshot(drm_r128_private_t *dev_priv) { drm_r128_ring_buffer_t *ring = &dev_priv->ring; ring->space = (GET_RING_HEAD(dev_priv) - ring->tail) * sizeof(u32); @@ -430,37 +430,38 @@ do { \ } \ } while (0) -#define RING_SPACE_TEST_WITH_RETURN( dev_priv ) \ +#define RING_SPACE_TEST_WITH_RETURN(dev_priv) \ do { \ drm_r128_ring_buffer_t *ring = &dev_priv->ring; int i; \ - if ( ring->space < ring->high_mark ) { \ - for ( i = 0 ; i < dev_priv->usec_timeout ; i++ ) { \ - r128_update_ring_snapshot( dev_priv ); \ - if ( ring->space >= ring->high_mark ) \ + if (ring->space < ring->high_mark) { \ + for (i = 0 ; i < dev_priv->usec_timeout ; i++) { \ + r128_update_ring_snapshot(dev_priv); \ + if (ring->space >= ring->high_mark) \ goto __ring_space_done; \ - DRM_UDELAY(1); \ + DRM_UDELAY(1); \ } \ - DRM_ERROR( "ring space check failed!\n" ); \ - return -EBUSY; \ + DRM_ERROR("ring space check failed!\n"); \ + return -EBUSY; \ } \ __ring_space_done: \ ; \ } while (0) -#define VB_AGE_TEST_WITH_RETURN( dev_priv ) \ +#define VB_AGE_TEST_WITH_RETURN(dev_priv) \ do { \ drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; \ - if ( sarea_priv->last_dispatch >= R128_MAX_VB_AGE ) { \ - int __ret = r128_do_cce_idle( dev_priv ); \ - if ( __ret ) return __ret; \ + if (sarea_priv->last_dispatch >= R128_MAX_VB_AGE) { \ + int __ret = r128_do_cce_idle(dev_priv); \ + if (__ret) \ + return __ret; \ sarea_priv->last_dispatch = 0; \ - r128_freelist_reset( dev ); \ + r128_freelist_reset(dev); \ } \ } while (0) #define R128_WAIT_UNTIL_PAGE_FLIPPED() do { \ - OUT_RING( CCE_PACKET0( R128_WAIT_UNTIL, 0 ) ); \ - OUT_RING( R128_EVENT_CRTC_OFFSET ); \ + OUT_RING(CCE_PACKET0(R128_WAIT_UNTIL, 0)); \ + OUT_RING(R128_EVENT_CRTC_OFFSET); \ } while (0) /* ================================================================ @@ -472,13 +473,12 @@ do { \ #define RING_LOCALS \ int write, _nr; unsigned int tail_mask; volatile u32 *ring; -#define BEGIN_RING( n ) do { \ - if ( R128_VERBOSE ) { \ - DRM_INFO( "BEGIN_RING( %d )\n", (n)); \ - } \ - if ( dev_priv->ring.space <= (n) * sizeof(u32) ) { \ +#define BEGIN_RING(n) do { \ + if (R128_VERBOSE) \ + DRM_INFO("BEGIN_RING(%d)\n", (n)); \ + if (dev_priv->ring.space <= (n) * sizeof(u32)) { \ COMMIT_RING(); \ - r128_wait_ring( dev_priv, (n) * sizeof(u32) ); \ + r128_wait_ring(dev_priv, (n) * sizeof(u32)); \ } \ _nr = n; dev_priv->ring.space -= (n) * sizeof(u32); \ ring = dev_priv->ring.start; \ @@ -494,40 +494,36 @@ do { \ #define R128_BROKEN_CCE 1 #define ADVANCE_RING() do { \ - if ( R128_VERBOSE ) { \ - DRM_INFO( "ADVANCE_RING() wr=0x%06x tail=0x%06x\n", \ - write, dev_priv->ring.tail ); \ - } \ - if ( R128_BROKEN_CCE && write < 32 ) { \ - memcpy( dev_priv->ring.end, \ - dev_priv->ring.start, \ - write * sizeof(u32) ); \ - } \ - if (((dev_priv->ring.tail + _nr) & tail_mask) != write) { \ + if (R128_VERBOSE) \ + DRM_INFO("ADVANCE_RING() wr=0x%06x tail=0x%06x\n", \ + write, dev_priv->ring.tail); \ + if (R128_BROKEN_CCE && write < 32) \ + memcpy(dev_priv->ring.end, \ + dev_priv->ring.start, \ + write * sizeof(u32)); \ + if (((dev_priv->ring.tail + _nr) & tail_mask) != write) \ DRM_ERROR( \ "ADVANCE_RING(): mismatch: nr: %x write: %x line: %d\n", \ ((dev_priv->ring.tail + _nr) & tail_mask), \ write, __LINE__); \ - } else \ + else \ dev_priv->ring.tail = write; \ } while (0) #define COMMIT_RING() do { \ - if ( R128_VERBOSE ) { \ - DRM_INFO( "COMMIT_RING() tail=0x%06x\n", \ - dev_priv->ring.tail ); \ - } \ + if (R128_VERBOSE) \ + DRM_INFO("COMMIT_RING() tail=0x%06x\n", \ + dev_priv->ring.tail); \ DRM_MEMORYBARRIER(); \ - R128_WRITE( R128_PM4_BUFFER_DL_WPTR, dev_priv->ring.tail ); \ - R128_READ( R128_PM4_BUFFER_DL_WPTR ); \ + R128_WRITE(R128_PM4_BUFFER_DL_WPTR, dev_priv->ring.tail); \ + R128_READ(R128_PM4_BUFFER_DL_WPTR); \ } while (0) -#define OUT_RING( x ) do { \ - if ( R128_VERBOSE ) { \ - DRM_INFO( " OUT_RING( 0x%08x ) at 0x%x\n", \ - (unsigned int)(x), write ); \ - } \ - ring[write++] = cpu_to_le32( x ); \ +#define OUT_RING(x) do { \ + if (R128_VERBOSE) \ + DRM_INFO(" OUT_RING( 0x%08x ) at 0x%x\n", \ + (unsigned int)(x), write); \ + ring[write++] = cpu_to_le32(x); \ write &= tail_mask; \ } while (0) diff --git a/drivers/gpu/drm/r128/r128_irq.c b/drivers/gpu/drm/r128/r128_irq.c index 69810fb8ac4..429d5a02695 100644 --- a/drivers/gpu/drm/r128/r128_irq.c +++ b/drivers/gpu/drm/r128/r128_irq.c @@ -90,7 +90,7 @@ void r128_disable_vblank(struct drm_device *dev, int crtc) */ } -void r128_driver_irq_preinstall(struct drm_device * dev) +void r128_driver_irq_preinstall(struct drm_device *dev) { drm_r128_private_t *dev_priv = (drm_r128_private_t *) dev->dev_private; @@ -105,7 +105,7 @@ int r128_driver_irq_postinstall(struct drm_device *dev) return 0; } -void r128_driver_irq_uninstall(struct drm_device * dev) +void r128_driver_irq_uninstall(struct drm_device *dev) { drm_r128_private_t *dev_priv = (drm_r128_private_t *) dev->dev_private; if (!dev_priv) diff --git a/drivers/gpu/drm/r128/r128_state.c b/drivers/gpu/drm/r128/r128_state.c index af2665cf471..077af1f2f9b 100644 --- a/drivers/gpu/drm/r128/r128_state.c +++ b/drivers/gpu/drm/r128/r128_state.c @@ -37,8 +37,8 @@ * CCE hardware state programming functions */ -static void r128_emit_clip_rects(drm_r128_private_t * dev_priv, - struct drm_clip_rect * boxes, int count) +static void r128_emit_clip_rects(drm_r128_private_t *dev_priv, + struct drm_clip_rect *boxes, int count) { u32 aux_sc_cntl = 0x00000000; RING_LOCALS; @@ -80,7 +80,7 @@ static void r128_emit_clip_rects(drm_r128_private_t * dev_priv, ADVANCE_RING(); } -static __inline__ void r128_emit_core(drm_r128_private_t * dev_priv) +static __inline__ void r128_emit_core(drm_r128_private_t *dev_priv) { drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_r128_context_regs_t *ctx = &sarea_priv->context_state; @@ -95,7 +95,7 @@ static __inline__ void r128_emit_core(drm_r128_private_t * dev_priv) ADVANCE_RING(); } -static __inline__ void r128_emit_context(drm_r128_private_t * dev_priv) +static __inline__ void r128_emit_context(drm_r128_private_t *dev_priv) { drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_r128_context_regs_t *ctx = &sarea_priv->context_state; @@ -121,7 +121,7 @@ static __inline__ void r128_emit_context(drm_r128_private_t * dev_priv) ADVANCE_RING(); } -static __inline__ void r128_emit_setup(drm_r128_private_t * dev_priv) +static __inline__ void r128_emit_setup(drm_r128_private_t *dev_priv) { drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_r128_context_regs_t *ctx = &sarea_priv->context_state; @@ -137,7 +137,7 @@ static __inline__ void r128_emit_setup(drm_r128_private_t * dev_priv) ADVANCE_RING(); } -static __inline__ void r128_emit_masks(drm_r128_private_t * dev_priv) +static __inline__ void r128_emit_masks(drm_r128_private_t *dev_priv) { drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_r128_context_regs_t *ctx = &sarea_priv->context_state; @@ -156,7 +156,7 @@ static __inline__ void r128_emit_masks(drm_r128_private_t * dev_priv) ADVANCE_RING(); } -static __inline__ void r128_emit_window(drm_r128_private_t * dev_priv) +static __inline__ void r128_emit_window(drm_r128_private_t *dev_priv) { drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_r128_context_regs_t *ctx = &sarea_priv->context_state; @@ -171,7 +171,7 @@ static __inline__ void r128_emit_window(drm_r128_private_t * dev_priv) ADVANCE_RING(); } -static __inline__ void r128_emit_tex0(drm_r128_private_t * dev_priv) +static __inline__ void r128_emit_tex0(drm_r128_private_t *dev_priv) { drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_r128_context_regs_t *ctx = &sarea_priv->context_state; @@ -187,9 +187,8 @@ static __inline__ void r128_emit_tex0(drm_r128_private_t * dev_priv) OUT_RING(tex->tex_cntl); OUT_RING(tex->tex_combine_cntl); OUT_RING(ctx->tex_size_pitch_c); - for (i = 0; i < R128_MAX_TEXTURE_LEVELS; i++) { + for (i = 0; i < R128_MAX_TEXTURE_LEVELS; i++) OUT_RING(tex->tex_offset[i]); - } OUT_RING(CCE_PACKET0(R128_CONSTANT_COLOR_C, 1)); OUT_RING(ctx->constant_color_c); @@ -198,7 +197,7 @@ static __inline__ void r128_emit_tex0(drm_r128_private_t * dev_priv) ADVANCE_RING(); } -static __inline__ void r128_emit_tex1(drm_r128_private_t * dev_priv) +static __inline__ void r128_emit_tex1(drm_r128_private_t *dev_priv) { drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; drm_r128_texture_regs_t *tex = &sarea_priv->tex_state[1]; @@ -211,9 +210,8 @@ static __inline__ void r128_emit_tex1(drm_r128_private_t * dev_priv) OUT_RING(CCE_PACKET0(R128_SEC_TEX_CNTL_C, 1 + R128_MAX_TEXTURE_LEVELS)); OUT_RING(tex->tex_cntl); OUT_RING(tex->tex_combine_cntl); - for (i = 0; i < R128_MAX_TEXTURE_LEVELS; i++) { + for (i = 0; i < R128_MAX_TEXTURE_LEVELS; i++) OUT_RING(tex->tex_offset[i]); - } OUT_RING(CCE_PACKET0(R128_SEC_TEXTURE_BORDER_COLOR_C, 0)); OUT_RING(tex->tex_border_color); @@ -221,7 +219,7 @@ static __inline__ void r128_emit_tex1(drm_r128_private_t * dev_priv) ADVANCE_RING(); } -static void r128_emit_state(drm_r128_private_t * dev_priv) +static void r128_emit_state(drm_r128_private_t *dev_priv) { drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; unsigned int dirty = sarea_priv->dirty; @@ -274,7 +272,7 @@ static void r128_emit_state(drm_r128_private_t * dev_priv) * Performance monitoring functions */ -static void r128_clear_box(drm_r128_private_t * dev_priv, +static void r128_clear_box(drm_r128_private_t *dev_priv, int x, int y, int w, int h, int r, int g, int b) { u32 pitch, offset; @@ -321,13 +319,12 @@ static void r128_clear_box(drm_r128_private_t * dev_priv, ADVANCE_RING(); } -static void r128_cce_performance_boxes(drm_r128_private_t * dev_priv) +static void r128_cce_performance_boxes(drm_r128_private_t *dev_priv) { - if (atomic_read(&dev_priv->idle_count) == 0) { + if (atomic_read(&dev_priv->idle_count) == 0) r128_clear_box(dev_priv, 64, 4, 8, 8, 0, 255, 0); - } else { + else atomic_set(&dev_priv->idle_count, 0); - } } #endif @@ -352,8 +349,8 @@ static void r128_print_dirty(const char *msg, unsigned int flags) (flags & R128_REQUIRE_QUIESCENCE) ? "quiescence, " : ""); } -static void r128_cce_dispatch_clear(struct drm_device * dev, - drm_r128_clear_t * clear) +static void r128_cce_dispatch_clear(struct drm_device *dev, + drm_r128_clear_t *clear) { drm_r128_private_t *dev_priv = dev->dev_private; drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -458,7 +455,7 @@ static void r128_cce_dispatch_clear(struct drm_device * dev, } } -static void r128_cce_dispatch_swap(struct drm_device * dev) +static void r128_cce_dispatch_swap(struct drm_device *dev) { drm_r128_private_t *dev_priv = dev->dev_private; drm_r128_sarea_t *sarea_priv = dev_priv->sarea_priv; @@ -524,7 +521,7 @@ static void r128_cce_dispatch_swap(struct drm_device * dev) ADVANCE_RING(); } -static void r128_cce_dispatch_flip(struct drm_device * dev) +static void r128_cce_dispatch_flip(struct drm_device *dev) { drm_r128_private_t *dev_priv = dev->dev_private; RING_LOCALS; @@ -542,11 +539,10 @@ static void r128_cce_dispatch_flip(struct drm_device * dev) R128_WAIT_UNTIL_PAGE_FLIPPED(); OUT_RING(CCE_PACKET0(R128_CRTC_OFFSET, 0)); - if (dev_priv->current_page == 0) { + if (dev_priv->current_page == 0) OUT_RING(dev_priv->back_offset); - } else { + else OUT_RING(dev_priv->front_offset); - } ADVANCE_RING(); @@ -566,7 +562,7 @@ static void r128_cce_dispatch_flip(struct drm_device * dev) ADVANCE_RING(); } -static void r128_cce_dispatch_vertex(struct drm_device * dev, struct drm_buf * buf) +static void r128_cce_dispatch_vertex(struct drm_device *dev, struct drm_buf *buf) { drm_r128_private_t *dev_priv = dev->dev_private; drm_r128_buf_priv_t *buf_priv = buf->dev_private; @@ -585,9 +581,8 @@ static void r128_cce_dispatch_vertex(struct drm_device * dev, struct drm_buf * b if (buf->used) { buf_priv->dispatched = 1; - if (sarea_priv->dirty & ~R128_UPLOAD_CLIPRECTS) { + if (sarea_priv->dirty & ~R128_UPLOAD_CLIPRECTS) r128_emit_state(dev_priv); - } do { /* Emit the next set of up to three cliprects */ @@ -636,8 +631,8 @@ static void r128_cce_dispatch_vertex(struct drm_device * dev, struct drm_buf * b sarea_priv->nbox = 0; } -static void r128_cce_dispatch_indirect(struct drm_device * dev, - struct drm_buf * buf, int start, int end) +static void r128_cce_dispatch_indirect(struct drm_device *dev, + struct drm_buf *buf, int start, int end) { drm_r128_private_t *dev_priv = dev->dev_private; drm_r128_buf_priv_t *buf_priv = buf->dev_private; @@ -691,8 +686,8 @@ static void r128_cce_dispatch_indirect(struct drm_device * dev, dev_priv->sarea_priv->last_dispatch++; } -static void r128_cce_dispatch_indices(struct drm_device * dev, - struct drm_buf * buf, +static void r128_cce_dispatch_indices(struct drm_device *dev, + struct drm_buf *buf, int start, int end, int count) { drm_r128_private_t *dev_priv = dev->dev_private; @@ -713,9 +708,8 @@ static void r128_cce_dispatch_indices(struct drm_device * dev, if (start != end) { buf_priv->dispatched = 1; - if (sarea_priv->dirty & ~R128_UPLOAD_CLIPRECTS) { + if (sarea_priv->dirty & ~R128_UPLOAD_CLIPRECTS) r128_emit_state(dev_priv); - } dwords = (end - start + 3) / sizeof(u32); @@ -775,9 +769,9 @@ static void r128_cce_dispatch_indices(struct drm_device * dev, sarea_priv->nbox = 0; } -static int r128_cce_dispatch_blit(struct drm_device * dev, +static int r128_cce_dispatch_blit(struct drm_device *dev, struct drm_file *file_priv, - drm_r128_blit_t * blit) + drm_r128_blit_t *blit) { drm_r128_private_t *dev_priv = dev->dev_private; struct drm_device_dma *dma = dev->dma; @@ -887,8 +881,8 @@ static int r128_cce_dispatch_blit(struct drm_device * dev, * have hardware stencil support. */ -static int r128_cce_dispatch_write_span(struct drm_device * dev, - drm_r128_depth_t * depth) +static int r128_cce_dispatch_write_span(struct drm_device *dev, + drm_r128_depth_t *depth) { drm_r128_private_t *dev_priv = dev->dev_private; int count, x, y; @@ -902,12 +896,10 @@ static int r128_cce_dispatch_write_span(struct drm_device * dev, if (count > 4096 || count <= 0) return -EMSGSIZE; - if (DRM_COPY_FROM_USER(&x, depth->x, sizeof(x))) { + if (DRM_COPY_FROM_USER(&x, depth->x, sizeof(x))) return -EFAULT; - } - if (DRM_COPY_FROM_USER(&y, depth->y, sizeof(y))) { + if (DRM_COPY_FROM_USER(&y, depth->y, sizeof(y))) return -EFAULT; - } buffer_size = depth->n * sizeof(u32); buffer = kmalloc(buffer_size, GFP_KERNEL); @@ -983,8 +975,8 @@ static int r128_cce_dispatch_write_span(struct drm_device * dev, return 0; } -static int r128_cce_dispatch_write_pixels(struct drm_device * dev, - drm_r128_depth_t * depth) +static int r128_cce_dispatch_write_pixels(struct drm_device *dev, + drm_r128_depth_t *depth) { drm_r128_private_t *dev_priv = dev->dev_private; int count, *x, *y; @@ -1001,9 +993,8 @@ static int r128_cce_dispatch_write_pixels(struct drm_device * dev, xbuf_size = count * sizeof(*x); ybuf_size = count * sizeof(*y); x = kmalloc(xbuf_size, GFP_KERNEL); - if (x == NULL) { + if (x == NULL) return -ENOMEM; - } y = kmalloc(ybuf_size, GFP_KERNEL); if (y == NULL) { kfree(x); @@ -1105,8 +1096,8 @@ static int r128_cce_dispatch_write_pixels(struct drm_device * dev, return 0; } -static int r128_cce_dispatch_read_span(struct drm_device * dev, - drm_r128_depth_t * depth) +static int r128_cce_dispatch_read_span(struct drm_device *dev, + drm_r128_depth_t *depth) { drm_r128_private_t *dev_priv = dev->dev_private; int count, x, y; @@ -1117,12 +1108,10 @@ static int r128_cce_dispatch_read_span(struct drm_device * dev, if (count > 4096 || count <= 0) return -EMSGSIZE; - if (DRM_COPY_FROM_USER(&x, depth->x, sizeof(x))) { + if (DRM_COPY_FROM_USER(&x, depth->x, sizeof(x))) return -EFAULT; - } - if (DRM_COPY_FROM_USER(&y, depth->y, sizeof(y))) { + if (DRM_COPY_FROM_USER(&y, depth->y, sizeof(y))) return -EFAULT; - } BEGIN_RING(7); @@ -1148,8 +1137,8 @@ static int r128_cce_dispatch_read_span(struct drm_device * dev, return 0; } -static int r128_cce_dispatch_read_pixels(struct drm_device * dev, - drm_r128_depth_t * depth) +static int r128_cce_dispatch_read_pixels(struct drm_device *dev, + drm_r128_depth_t *depth) { drm_r128_private_t *dev_priv = dev->dev_private; int count, *x, *y; @@ -1161,16 +1150,14 @@ static int r128_cce_dispatch_read_pixels(struct drm_device * dev, if (count > 4096 || count <= 0) return -EMSGSIZE; - if (count > dev_priv->depth_pitch) { + if (count > dev_priv->depth_pitch) count = dev_priv->depth_pitch; - } xbuf_size = count * sizeof(*x); ybuf_size = count * sizeof(*y); x = kmalloc(xbuf_size, GFP_KERNEL); - if (x == NULL) { + if (x == NULL) return -ENOMEM; - } y = kmalloc(ybuf_size, GFP_KERNEL); if (y == NULL) { kfree(x); @@ -1220,7 +1207,7 @@ static int r128_cce_dispatch_read_pixels(struct drm_device * dev, * Polygon stipple */ -static void r128_cce_dispatch_stipple(struct drm_device * dev, u32 * stipple) +static void r128_cce_dispatch_stipple(struct drm_device *dev, u32 *stipple) { drm_r128_private_t *dev_priv = dev->dev_private; int i; @@ -1230,9 +1217,8 @@ static void r128_cce_dispatch_stipple(struct drm_device * dev, u32 * stipple) BEGIN_RING(33); OUT_RING(CCE_PACKET0(R128_BRUSH_DATA0, 31)); - for (i = 0; i < 32; i++) { + for (i = 0; i < 32; i++) OUT_RING(stipple[i]); - } ADVANCE_RING(); } @@ -1269,7 +1255,7 @@ static int r128_cce_clear(struct drm_device *dev, void *data, struct drm_file *f return 0; } -static int r128_do_init_pageflip(struct drm_device * dev) +static int r128_do_init_pageflip(struct drm_device *dev) { drm_r128_private_t *dev_priv = dev->dev_private; DRM_DEBUG("\n"); @@ -1288,7 +1274,7 @@ static int r128_do_init_pageflip(struct drm_device * dev) return 0; } -static int r128_do_cleanup_pageflip(struct drm_device * dev) +static int r128_do_cleanup_pageflip(struct drm_device *dev) { drm_r128_private_t *dev_priv = dev->dev_private; DRM_DEBUG("\n"); @@ -1645,17 +1631,16 @@ static int r128_getparam(struct drm_device *dev, void *data, struct drm_file *fi return 0; } -void r128_driver_preclose(struct drm_device * dev, struct drm_file *file_priv) +void r128_driver_preclose(struct drm_device *dev, struct drm_file *file_priv) { if (dev->dev_private) { drm_r128_private_t *dev_priv = dev->dev_private; - if (dev_priv->page_flipping) { + if (dev_priv->page_flipping) r128_do_cleanup_pageflip(dev); - } } } -void r128_driver_lastclose(struct drm_device * dev) +void r128_driver_lastclose(struct drm_device *dev) { r128_do_cleanup_cce(dev); } diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile index 84b1f2729d4..aebe0087504 100644 --- a/drivers/gpu/drm/radeon/Makefile +++ b/drivers/gpu/drm/radeon/Makefile @@ -69,5 +69,6 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \ radeon-$(CONFIG_COMPAT) += radeon_ioc32.o radeon-$(CONFIG_VGA_SWITCHEROO) += radeon_atpx_handler.o +radeon-$(CONFIG_ACPI) += radeon_acpi.o obj-$(CONFIG_DRM_RADEON)+= radeon.o diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c index 1d569830ed9..8e421f644a5 100644 --- a/drivers/gpu/drm/radeon/atom.c +++ b/drivers/gpu/drm/radeon/atom.c @@ -108,12 +108,11 @@ static uint32_t atom_iio_execute(struct atom_context *ctx, int base, base++; break; case ATOM_IIO_READ: - temp = ctx->card->reg_read(ctx->card, CU16(base + 1)); + temp = ctx->card->ioreg_read(ctx->card, CU16(base + 1)); base += 3; break; case ATOM_IIO_WRITE: - (void)ctx->card->reg_read(ctx->card, CU16(base + 1)); - ctx->card->reg_write(ctx->card, CU16(base + 1), temp); + ctx->card->ioreg_write(ctx->card, CU16(base + 1), temp); base += 3; break; case ATOM_IIO_CLEAR: @@ -715,8 +714,8 @@ static void atom_op_jump(atom_exec_context *ctx, int *ptr, int arg) cjiffies = jiffies; if (time_after(cjiffies, ctx->last_jump_jiffies)) { cjiffies -= ctx->last_jump_jiffies; - if ((jiffies_to_msecs(cjiffies) > 1000)) { - DRM_ERROR("atombios stuck in loop for more than 1sec aborting\n"); + if ((jiffies_to_msecs(cjiffies) > 5000)) { + DRM_ERROR("atombios stuck in loop for more than 5secs aborting\n"); ctx->abort = true; } } else { diff --git a/drivers/gpu/drm/radeon/atom.h b/drivers/gpu/drm/radeon/atom.h index cd1b64ab5ca..a589a55b223 100644 --- a/drivers/gpu/drm/radeon/atom.h +++ b/drivers/gpu/drm/radeon/atom.h @@ -113,6 +113,8 @@ struct card_info { struct drm_device *dev; void (* reg_write)(struct card_info *, uint32_t, uint32_t); /* filled by driver */ uint32_t (* reg_read)(struct card_info *, uint32_t); /* filled by driver */ + void (* ioreg_write)(struct card_info *, uint32_t, uint32_t); /* filled by driver */ + uint32_t (* ioreg_read)(struct card_info *, uint32_t); /* filled by driver */ void (* mc_write)(struct card_info *, uint32_t, uint32_t); /* filled by driver */ uint32_t (* mc_read)(struct card_info *, uint32_t); /* filled by driver */ void (* pll_write)(struct card_info *, uint32_t, uint32_t); /* filled by driver */ diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 8c2d6478a22..12ad512bd3d 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -44,10 +44,6 @@ static void atombios_overscan_setup(struct drm_crtc *crtc, memset(&args, 0, sizeof(args)); - args.usOverscanRight = 0; - args.usOverscanLeft = 0; - args.usOverscanBottom = 0; - args.usOverscanTop = 0; args.ucCRTC = radeon_crtc->crtc_id; switch (radeon_crtc->rmx_type) { @@ -56,7 +52,6 @@ static void atombios_overscan_setup(struct drm_crtc *crtc, args.usOverscanBottom = (adjusted_mode->crtc_vdisplay - mode->crtc_vdisplay) / 2; args.usOverscanLeft = (adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2; args.usOverscanRight = (adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2; - atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); break; case RMX_ASPECT: a1 = mode->crtc_vdisplay * adjusted_mode->crtc_hdisplay; @@ -69,17 +64,16 @@ static void atombios_overscan_setup(struct drm_crtc *crtc, args.usOverscanLeft = (adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2; args.usOverscanRight = (adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2; } - atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); break; case RMX_FULL: default: - args.usOverscanRight = 0; - args.usOverscanLeft = 0; - args.usOverscanBottom = 0; - args.usOverscanTop = 0; - atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + args.usOverscanRight = radeon_crtc->h_border; + args.usOverscanLeft = radeon_crtc->h_border; + args.usOverscanBottom = radeon_crtc->v_border; + args.usOverscanTop = radeon_crtc->v_border; break; } + atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); } static void atombios_scaler_setup(struct drm_crtc *crtc) @@ -282,22 +276,22 @@ atombios_set_crtc_dtd_timing(struct drm_crtc *crtc, u16 misc = 0; memset(&args, 0, sizeof(args)); - args.usH_Size = cpu_to_le16(mode->crtc_hdisplay); + args.usH_Size = cpu_to_le16(mode->crtc_hdisplay - (radeon_crtc->h_border * 2)); args.usH_Blanking_Time = - cpu_to_le16(mode->crtc_hblank_end - mode->crtc_hdisplay); - args.usV_Size = cpu_to_le16(mode->crtc_vdisplay); + cpu_to_le16(mode->crtc_hblank_end - mode->crtc_hdisplay + (radeon_crtc->h_border * 2)); + args.usV_Size = cpu_to_le16(mode->crtc_vdisplay - (radeon_crtc->v_border * 2)); args.usV_Blanking_Time = - cpu_to_le16(mode->crtc_vblank_end - mode->crtc_vdisplay); + cpu_to_le16(mode->crtc_vblank_end - mode->crtc_vdisplay + (radeon_crtc->v_border * 2)); args.usH_SyncOffset = - cpu_to_le16(mode->crtc_hsync_start - mode->crtc_hdisplay); + cpu_to_le16(mode->crtc_hsync_start - mode->crtc_hdisplay + radeon_crtc->h_border); args.usH_SyncWidth = cpu_to_le16(mode->crtc_hsync_end - mode->crtc_hsync_start); args.usV_SyncOffset = - cpu_to_le16(mode->crtc_vsync_start - mode->crtc_vdisplay); + cpu_to_le16(mode->crtc_vsync_start - mode->crtc_vdisplay + radeon_crtc->v_border); args.usV_SyncWidth = cpu_to_le16(mode->crtc_vsync_end - mode->crtc_vsync_start); - /*args.ucH_Border = mode->hborder;*/ - /*args.ucV_Border = mode->vborder;*/ + args.ucH_Border = radeon_crtc->h_border; + args.ucV_Border = radeon_crtc->v_border; if (mode->flags & DRM_MODE_FLAG_NVSYNC) misc |= ATOM_VSYNC_POLARITY; @@ -669,56 +663,25 @@ static void atombios_crtc_set_dcpll(struct drm_crtc *crtc) atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); } -static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode *mode) +static void atombios_crtc_program_pll(struct drm_crtc *crtc, + int crtc_id, + int pll_id, + u32 encoder_mode, + u32 encoder_id, + u32 clock, + u32 ref_div, + u32 fb_div, + u32 frac_fb_div, + u32 post_div) { - struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); struct drm_device *dev = crtc->dev; struct radeon_device *rdev = dev->dev_private; - struct drm_encoder *encoder = NULL; - struct radeon_encoder *radeon_encoder = NULL; u8 frev, crev; - int index; + int index = GetIndexIntoMasterTable(COMMAND, SetPixelClock); union set_pixel_clock args; - u32 pll_clock = mode->clock; - u32 ref_div = 0, fb_div = 0, frac_fb_div = 0, post_div = 0; - struct radeon_pll *pll; - u32 adjusted_clock; - int encoder_mode = 0; memset(&args, 0, sizeof(args)); - list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { - if (encoder->crtc == crtc) { - radeon_encoder = to_radeon_encoder(encoder); - encoder_mode = atombios_get_encoder_mode(encoder); - break; - } - } - - if (!radeon_encoder) - return; - - switch (radeon_crtc->pll_id) { - case ATOM_PPLL1: - pll = &rdev->clock.p1pll; - break; - case ATOM_PPLL2: - pll = &rdev->clock.p2pll; - break; - case ATOM_DCPLL: - case ATOM_PPLL_INVALID: - default: - pll = &rdev->clock.dcpll; - break; - } - - /* adjust pixel clock as needed */ - adjusted_clock = atombios_adjust_pll(crtc, mode, pll); - - radeon_compute_pll(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div, - &ref_div, &post_div); - - index = GetIndexIntoMasterTable(COMMAND, SetPixelClock); if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev)) return; @@ -727,47 +690,49 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode case 1: switch (crev) { case 1: - args.v1.usPixelClock = cpu_to_le16(mode->clock / 10); + if (clock == ATOM_DISABLE) + return; + args.v1.usPixelClock = cpu_to_le16(clock / 10); args.v1.usRefDiv = cpu_to_le16(ref_div); args.v1.usFbDiv = cpu_to_le16(fb_div); args.v1.ucFracFbDiv = frac_fb_div; args.v1.ucPostDiv = post_div; - args.v1.ucPpll = radeon_crtc->pll_id; - args.v1.ucCRTC = radeon_crtc->crtc_id; + args.v1.ucPpll = pll_id; + args.v1.ucCRTC = crtc_id; args.v1.ucRefDivSrc = 1; break; case 2: - args.v2.usPixelClock = cpu_to_le16(mode->clock / 10); + args.v2.usPixelClock = cpu_to_le16(clock / 10); args.v2.usRefDiv = cpu_to_le16(ref_div); args.v2.usFbDiv = cpu_to_le16(fb_div); args.v2.ucFracFbDiv = frac_fb_div; args.v2.ucPostDiv = post_div; - args.v2.ucPpll = radeon_crtc->pll_id; - args.v2.ucCRTC = radeon_crtc->crtc_id; + args.v2.ucPpll = pll_id; + args.v2.ucCRTC = crtc_id; args.v2.ucRefDivSrc = 1; break; case 3: - args.v3.usPixelClock = cpu_to_le16(mode->clock / 10); + args.v3.usPixelClock = cpu_to_le16(clock / 10); args.v3.usRefDiv = cpu_to_le16(ref_div); args.v3.usFbDiv = cpu_to_le16(fb_div); args.v3.ucFracFbDiv = frac_fb_div; args.v3.ucPostDiv = post_div; - args.v3.ucPpll = radeon_crtc->pll_id; - args.v3.ucMiscInfo = (radeon_crtc->pll_id << 2); - args.v3.ucTransmitterId = radeon_encoder->encoder_id; + args.v3.ucPpll = pll_id; + args.v3.ucMiscInfo = (pll_id << 2); + args.v3.ucTransmitterId = encoder_id; args.v3.ucEncoderMode = encoder_mode; break; case 5: - args.v5.ucCRTC = radeon_crtc->crtc_id; - args.v5.usPixelClock = cpu_to_le16(mode->clock / 10); + args.v5.ucCRTC = crtc_id; + args.v5.usPixelClock = cpu_to_le16(clock / 10); args.v5.ucRefDiv = ref_div; args.v5.usFbDiv = cpu_to_le16(fb_div); args.v5.ulFbDivDecFrac = cpu_to_le32(frac_fb_div * 100000); args.v5.ucPostDiv = post_div; args.v5.ucMiscInfo = 0; /* HDMI depth, etc. */ - args.v5.ucTransmitterID = radeon_encoder->encoder_id; + args.v5.ucTransmitterID = encoder_id; args.v5.ucEncoderMode = encoder_mode; - args.v5.ucPpll = radeon_crtc->pll_id; + args.v5.ucPpll = pll_id; break; default: DRM_ERROR("Unknown table version %d %d\n", frev, crev); @@ -782,6 +747,56 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); } +static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode *mode) +{ + struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); + struct drm_device *dev = crtc->dev; + struct radeon_device *rdev = dev->dev_private; + struct drm_encoder *encoder = NULL; + struct radeon_encoder *radeon_encoder = NULL; + u32 pll_clock = mode->clock; + u32 ref_div = 0, fb_div = 0, frac_fb_div = 0, post_div = 0; + struct radeon_pll *pll; + u32 adjusted_clock; + int encoder_mode = 0; + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { + if (encoder->crtc == crtc) { + radeon_encoder = to_radeon_encoder(encoder); + encoder_mode = atombios_get_encoder_mode(encoder); + break; + } + } + + if (!radeon_encoder) + return; + + switch (radeon_crtc->pll_id) { + case ATOM_PPLL1: + pll = &rdev->clock.p1pll; + break; + case ATOM_PPLL2: + pll = &rdev->clock.p2pll; + break; + case ATOM_DCPLL: + case ATOM_PPLL_INVALID: + default: + pll = &rdev->clock.dcpll; + break; + } + + /* adjust pixel clock as needed */ + adjusted_clock = atombios_adjust_pll(crtc, mode, pll); + + radeon_compute_pll(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div, + &ref_div, &post_div); + + atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id, + encoder_mode, radeon_encoder->encoder_id, mode->clock, + ref_div, fb_div, frac_fb_div, post_div); + +} + static int evergreen_crtc_set_base(struct drm_crtc *crtc, int x, int y, struct drm_framebuffer *old_fb) { @@ -797,7 +812,7 @@ static int evergreen_crtc_set_base(struct drm_crtc *crtc, int x, int y, /* no fb bound */ if (!crtc->fb) { - DRM_DEBUG("No FB bound\n"); + DRM_DEBUG_KMS("No FB bound\n"); return 0; } @@ -841,6 +856,11 @@ static int evergreen_crtc_set_base(struct drm_crtc *crtc, int x, int y, return -EINVAL; } + if (tiling_flags & RADEON_TILING_MACRO) + fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1); + else if (tiling_flags & RADEON_TILING_MICRO) + fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1); + switch (radeon_crtc->crtc_id) { case 0: WREG32(AVIVO_D1VGA_CONTROL, 0); @@ -931,7 +951,7 @@ static int avivo_crtc_set_base(struct drm_crtc *crtc, int x, int y, /* no fb bound */ if (!crtc->fb) { - DRM_DEBUG("No FB bound\n"); + DRM_DEBUG_KMS("No FB bound\n"); return 0; } @@ -979,11 +999,18 @@ static int avivo_crtc_set_base(struct drm_crtc *crtc, int x, int y, return -EINVAL; } - if (tiling_flags & RADEON_TILING_MACRO) - fb_format |= AVIVO_D1GRPH_MACRO_ADDRESS_MODE; + if (rdev->family >= CHIP_R600) { + if (tiling_flags & RADEON_TILING_MACRO) + fb_format |= R600_D1GRPH_ARRAY_MODE_2D_TILED_THIN1; + else if (tiling_flags & RADEON_TILING_MICRO) + fb_format |= R600_D1GRPH_ARRAY_MODE_1D_TILED_THIN1; + } else { + if (tiling_flags & RADEON_TILING_MACRO) + fb_format |= AVIVO_D1GRPH_MACRO_ADDRESS_MODE; - if (tiling_flags & RADEON_TILING_MICRO) - fb_format |= AVIVO_D1GRPH_TILED; + if (tiling_flags & RADEON_TILING_MICRO) + fb_format |= AVIVO_D1GRPH_TILED; + } if (radeon_crtc->crtc_id == 0) WREG32(AVIVO_D1VGA_CONTROL, 0); @@ -1143,10 +1170,8 @@ int atombios_crtc_mode_set(struct drm_crtc *crtc, atombios_crtc_set_pll(crtc, adjusted_mode); atombios_enable_ss(crtc); - if (ASIC_IS_DCE4(rdev)) + if (ASIC_IS_AVIVO(rdev)) atombios_set_crtc_dtd_timing(crtc, adjusted_mode); - else if (ASIC_IS_AVIVO(rdev)) - atombios_crtc_set_timing(crtc, adjusted_mode); else { atombios_crtc_set_timing(crtc, adjusted_mode); if (radeon_crtc->crtc_id == 0) @@ -1191,6 +1216,24 @@ static void atombios_crtc_commit(struct drm_crtc *crtc) atombios_lock_crtc(crtc, ATOM_DISABLE); } +static void atombios_crtc_disable(struct drm_crtc *crtc) +{ + struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); + atombios_crtc_dpms(crtc, DRM_MODE_DPMS_OFF); + + switch (radeon_crtc->pll_id) { + case ATOM_PPLL1: + case ATOM_PPLL2: + /* disable the ppll */ + atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id, + 0, 0, ATOM_DISABLE, 0, 0, 0, 0); + break; + default: + break; + } + radeon_crtc->pll_id = -1; +} + static const struct drm_crtc_helper_funcs atombios_helper_funcs = { .dpms = atombios_crtc_dpms, .mode_fixup = atombios_crtc_mode_fixup, @@ -1199,6 +1242,7 @@ static const struct drm_crtc_helper_funcs atombios_helper_funcs = { .prepare = atombios_crtc_prepare, .commit = atombios_crtc_commit, .load_lut = radeon_crtc_load_lut, + .disable = atombios_crtc_disable, }; void radeon_atombios_init_crtc(struct drm_device *dev, diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index abffb1499e2..36e0d4b545e 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -296,7 +296,7 @@ static void dp_get_adjust_train(u8 link_status[DP_LINK_STATUS_SIZE], u8 this_v = dp_get_adjust_request_voltage(link_status, lane); u8 this_p = dp_get_adjust_request_pre_emphasis(link_status, lane); - DRM_DEBUG("requested signal parameters: lane %d voltage %s pre_emph %s\n", + DRM_DEBUG_KMS("requested signal parameters: lane %d voltage %s pre_emph %s\n", lane, voltage_names[this_v >> DP_TRAIN_VOLTAGE_SWING_SHIFT], pre_emph_names[this_p >> DP_TRAIN_PRE_EMPHASIS_SHIFT]); @@ -313,7 +313,7 @@ static void dp_get_adjust_train(u8 link_status[DP_LINK_STATUS_SIZE], if (p >= dp_pre_emphasis_max(v)) p = dp_pre_emphasis_max(v) | DP_TRAIN_MAX_PRE_EMPHASIS_REACHED; - DRM_DEBUG("using signal parameters: voltage %s pre_emph %s\n", + DRM_DEBUG_KMS("using signal parameters: voltage %s pre_emph %s\n", voltage_names[(v & DP_TRAIN_VOLTAGE_SWING_MASK) >> DP_TRAIN_VOLTAGE_SWING_SHIFT], pre_emph_names[(p & DP_TRAIN_PRE_EMPHASIS_MASK) >> DP_TRAIN_PRE_EMPHASIS_SHIFT]); @@ -358,7 +358,7 @@ retry: if (args.v1.ucReplyStatus && !args.v1.ucDataOutLen) { if (args.v1.ucReplyStatus == 0x20 && retry_count++ < 10) goto retry; - DRM_DEBUG("failed to get auxch %02x%02x %02x %02x 0x%02x %02x after %d retries\n", + DRM_DEBUG_KMS("failed to get auxch %02x%02x %02x %02x 0x%02x %02x after %d retries\n", req_bytes[1], req_bytes[0], req_bytes[2], req_bytes[3], chan->rec.i2c_id, args.v1.ucReplyStatus, retry_count); return false; @@ -461,10 +461,10 @@ bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector) memcpy(dig_connector->dpcd, msg, 8); { int i; - DRM_DEBUG("DPCD: "); + DRM_DEBUG_KMS("DPCD: "); for (i = 0; i < 8; i++) - DRM_DEBUG("%02x ", msg[i]); - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("%02x ", msg[i]); + DRM_DEBUG_KMS("\n"); } return true; } @@ -512,7 +512,7 @@ static bool atom_dp_get_link_status(struct radeon_connector *radeon_connector, return false; } - DRM_DEBUG("link status %02x %02x %02x %02x %02x %02x\n", + DRM_DEBUG_KMS("link status %02x %02x %02x %02x %02x %02x\n", link_status[0], link_status[1], link_status[2], link_status[3], link_status[4], link_status[5]); return true; @@ -695,7 +695,7 @@ void dp_link_train(struct drm_encoder *encoder, if (!clock_recovery) DRM_ERROR("clock recovery failed\n"); else - DRM_DEBUG("clock recovery at voltage %d pre-emphasis %d\n", + DRM_DEBUG_KMS("clock recovery at voltage %d pre-emphasis %d\n", train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK, (train_set[0] & DP_TRAIN_PRE_EMPHASIS_MASK) >> DP_TRAIN_PRE_EMPHASIS_SHIFT); @@ -739,7 +739,7 @@ void dp_link_train(struct drm_encoder *encoder, if (!channel_eq) DRM_ERROR("channel eq failed\n"); else - DRM_DEBUG("channel eq at voltage %d pre-emphasis %d\n", + DRM_DEBUG_KMS("channel eq at voltage %d pre-emphasis %d\n", train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK, (train_set[0] & DP_TRAIN_PRE_EMPHASIS_MASK) >> DP_TRAIN_PRE_EMPHASIS_SHIFT); diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 1caf625e472..957d5067ad9 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -39,6 +39,23 @@ static void evergreen_gpu_init(struct radeon_device *rdev); void evergreen_fini(struct radeon_device *rdev); +/* get temperature in millidegrees */ +u32 evergreen_get_temp(struct radeon_device *rdev) +{ + u32 temp = (RREG32(CG_MULT_THERMAL_STATUS) & ASIC_T_MASK) >> + ASIC_T_SHIFT; + u32 actual_temp = 0; + + if ((temp >> 10) & 1) + actual_temp = 0; + else if ((temp >> 9) & 1) + actual_temp = 255; + else + actual_temp = (temp >> 1) & 0xff; + + return actual_temp * 1000; +} + void evergreen_pm_misc(struct radeon_device *rdev) { int req_ps_idx = rdev->pm.requested_power_state_index; @@ -1115,6 +1132,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev) rdev->config.evergreen.max_backends) & EVERGREEN_MAX_BACKENDS_MASK)); + rdev->config.evergreen.tile_config = gb_addr_config; WREG32(GB_BACKEND_MAP, gb_backend_map); WREG32(GB_ADDR_CONFIG, gb_addr_config); WREG32(DMIF_ADDR_CONFIG, gb_addr_config); @@ -1334,8 +1352,8 @@ int evergreen_mc_init(struct radeon_device *rdev) } rdev->mc.vram_width = numchan * chansize; /* Could aper size report 0 ? */ - rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0); - rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0); + rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0); + rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0); /* Setup GPU memory space */ /* size in MB on evergreen */ rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024; diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h index e028c1cd9d9..2330f3a36fd 100644 --- a/drivers/gpu/drm/radeon/evergreen_reg.h +++ b/drivers/gpu/drm/radeon/evergreen_reg.h @@ -61,6 +61,11 @@ # define EVERGREEN_GRPH_FORMAT_8B_BGRA1010102 5 # define EVERGREEN_GRPH_FORMAT_RGB111110 6 # define EVERGREEN_GRPH_FORMAT_BGR101111 7 +# define EVERGREEN_GRPH_ARRAY_MODE(x) (((x) & 0x7) << 20) +# define EVERGREEN_GRPH_ARRAY_LINEAR_GENERAL 0 +# define EVERGREEN_GRPH_ARRAY_LINEAR_ALIGNED 1 +# define EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1 2 +# define EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1 4 #define EVERGREEN_GRPH_SWAP_CONTROL 0x680c # define EVERGREEN_GRPH_ENDIAN_SWAP(x) (((x) & 0x3) << 0) # define EVERGREEN_GRPH_ENDIAN_NONE 0 diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index a1cd621780e..9b7532dd30f 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -165,6 +165,11 @@ #define SE_DB_BUSY (1 << 30) #define SE_CB_BUSY (1 << 31) +#define CG_MULT_THERMAL_STATUS 0x740 +#define ASIC_T(x) ((x) << 16) +#define ASIC_T_MASK 0x7FF0000 +#define ASIC_T_SHIFT 16 + #define HDP_HOST_PATH_CNTL 0x2C00 #define HDP_NONSURFACE_BASE 0x2C04 #define HDP_NONSURFACE_INFO 0x2C08 diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index a89a15ab524..e817a0bb5eb 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -141,7 +141,7 @@ void r100_pm_get_dynpm_state(struct radeon_device *rdev) /* only one clock mode per power state */ rdev->pm.requested_clock_mode_index = 0; - DRM_DEBUG("Requested: e: %d m: %d p: %d\n", + DRM_DEBUG_DRIVER("Requested: e: %d m: %d p: %d\n", rdev->pm.power_state[rdev->pm.requested_power_state_index]. clock_info[rdev->pm.requested_clock_mode_index].sclk, rdev->pm.power_state[rdev->pm.requested_power_state_index]. @@ -276,7 +276,7 @@ void r100_pm_misc(struct radeon_device *rdev) rdev->pm.power_state[rdev->pm.current_power_state_index].pcie_lanes)) { radeon_set_pcie_lanes(rdev, ps->pcie_lanes); - DRM_DEBUG("Setting: p: %d\n", ps->pcie_lanes); + DRM_DEBUG_DRIVER("Setting: p: %d\n", ps->pcie_lanes); } } @@ -849,7 +849,7 @@ static int r100_cp_init_microcode(struct radeon_device *rdev) const char *fw_name = NULL; int err; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); pdev = platform_device_register_simple("radeon_cp", 0, NULL, 0); err = IS_ERR(pdev); @@ -1803,6 +1803,11 @@ static int r100_packet3_check(struct radeon_cs_parser *p, return r; break; /* triggers drawing using indices to vertex buffer */ + case PACKET3_3D_CLEAR_HIZ: + case PACKET3_3D_CLEAR_ZMASK: + if (p->rdev->hyperz_filp != p->filp) + return -EINVAL; + break; case PACKET3_NOP: break; default: @@ -2295,8 +2300,8 @@ void r100_vram_init_sizes(struct radeon_device *rdev) u64 config_aper_size; /* work out accessible VRAM */ - rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0); - rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0); + rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0); + rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0); rdev->mc.visible_vram_size = r100_get_accessible_vram(rdev); /* FIXME we don't use the second aperture yet when we could use it */ if (rdev->mc.visible_vram_size > rdev->mc.aper_size) @@ -2364,11 +2369,10 @@ void r100_mc_init(struct radeon_device *rdev) */ void r100_pll_errata_after_index(struct radeon_device *rdev) { - if (!(rdev->pll_errata & CHIP_ERRATA_PLL_DUMMYREADS)) { - return; + if (rdev->pll_errata & CHIP_ERRATA_PLL_DUMMYREADS) { + (void)RREG32(RADEON_CLOCK_CNTL_DATA); + (void)RREG32(RADEON_CRTC_GEN_CNTL); } - (void)RREG32(RADEON_CLOCK_CNTL_DATA); - (void)RREG32(RADEON_CRTC_GEN_CNTL); } static void r100_pll_errata_after_data(struct radeon_device *rdev) @@ -2643,7 +2647,7 @@ int r100_set_surface_reg(struct radeon_device *rdev, int reg, flags |= pitch / 8; - DRM_DEBUG("writing surface %d %d %x %x\n", reg, flags, offset, offset+obj_size-1); + DRM_DEBUG_KMS("writing surface %d %d %x %x\n", reg, flags, offset, offset+obj_size-1); WREG32(RADEON_SURFACE0_INFO + surf_index, flags); WREG32(RADEON_SURFACE0_LOWER_BOUND + surf_index, offset); WREG32(RADEON_SURFACE0_UPPER_BOUND + surf_index, offset + obj_size - 1); @@ -3039,7 +3043,7 @@ void r100_bandwidth_update(struct radeon_device *rdev) } #endif - DRM_DEBUG("GRPH_BUFFER_CNTL from to %x\n", + DRM_DEBUG_KMS("GRPH_BUFFER_CNTL from to %x\n", /* (unsigned int)info->SavedReg->grph_buffer_cntl, */ (unsigned int)RREG32(RADEON_GRPH_BUFFER_CNTL)); } @@ -3135,7 +3139,7 @@ void r100_bandwidth_update(struct radeon_device *rdev) WREG32(RS400_DISP1_REQ_CNTL1, 0x28FBC3AC); } - DRM_DEBUG("GRPH2_BUFFER_CNTL from to %x\n", + DRM_DEBUG_KMS("GRPH2_BUFFER_CNTL from to %x\n", (unsigned int)RREG32(RADEON_GRPH2_BUFFER_CNTL)); } } @@ -3809,6 +3813,31 @@ void r100_fini(struct radeon_device *rdev) rdev->bios = NULL; } +/* + * Due to how kexec works, it can leave the hw fully initialised when it + * boots the new kernel. However doing our init sequence with the CP and + * WB stuff setup causes GPU hangs on the RN50 at least. So at startup + * do some quick sanity checks and restore sane values to avoid this + * problem. + */ +void r100_restore_sanity(struct radeon_device *rdev) +{ + u32 tmp; + + tmp = RREG32(RADEON_CP_CSQ_CNTL); + if (tmp) { + WREG32(RADEON_CP_CSQ_CNTL, 0); + } + tmp = RREG32(RADEON_CP_RB_CNTL); + if (tmp) { + WREG32(RADEON_CP_RB_CNTL, 0); + } + tmp = RREG32(RADEON_SCRATCH_UMSK); + if (tmp) { + WREG32(RADEON_SCRATCH_UMSK, 0); + } +} + int r100_init(struct radeon_device *rdev) { int r; @@ -3821,6 +3850,8 @@ int r100_init(struct radeon_device *rdev) radeon_scratch_init(rdev); /* Initialize surface registers */ radeon_surface_init(rdev); + /* sanity check some register to avoid hangs like after kexec */ + r100_restore_sanity(rdev); /* TODO: disable VGA need to use VGA request */ /* BIOS*/ if (!radeon_get_bios(rdev)) { diff --git a/drivers/gpu/drm/radeon/r100d.h b/drivers/gpu/drm/radeon/r100d.h index d016b16fa11..b121b6c678d 100644 --- a/drivers/gpu/drm/radeon/r100d.h +++ b/drivers/gpu/drm/radeon/r100d.h @@ -48,10 +48,12 @@ #define PACKET3_3D_DRAW_IMMD 0x29 #define PACKET3_3D_DRAW_INDX 0x2A #define PACKET3_3D_LOAD_VBPNTR 0x2F +#define PACKET3_3D_CLEAR_ZMASK 0x32 #define PACKET3_INDX_BUFFER 0x33 #define PACKET3_3D_DRAW_VBUF_2 0x34 #define PACKET3_3D_DRAW_IMMD_2 0x35 #define PACKET3_3D_DRAW_INDX_2 0x36 +#define PACKET3_3D_CLEAR_HIZ 0x37 #define PACKET3_BITBLT_MULTI 0x9B #define PACKET0(reg, n) (CP_PACKET0 | \ diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 19a7ef7ee34..c827738ad7d 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -1048,14 +1048,47 @@ static int r300_packet0_check(struct radeon_cs_parser *p, /* RB3D_COLOR_CHANNEL_MASK */ track->color_channel_mask = idx_value; break; - case 0x4d1c: + case 0x43a4: + /* SC_HYPERZ_EN */ + /* r300c emits this register - we need to disable hyperz for it + * without complaining */ + if (p->rdev->hyperz_filp != p->filp) { + if (idx_value & 0x1) + ib[idx] = idx_value & ~1; + } + break; + case 0x4f1c: /* ZB_BW_CNTL */ track->zb_cb_clear = !!(idx_value & (1 << 5)); + if (p->rdev->hyperz_filp != p->filp) { + if (idx_value & (R300_HIZ_ENABLE | + R300_RD_COMP_ENABLE | + R300_WR_COMP_ENABLE | + R300_FAST_FILL_ENABLE)) + goto fail; + } break; case 0x4e04: /* RB3D_BLENDCNTL */ track->blend_read_enable = !!(idx_value & (1 << 2)); break; + case 0x4f28: /* ZB_DEPTHCLEARVALUE */ + break; + case 0x4f30: /* ZB_MASK_OFFSET */ + case 0x4f34: /* ZB_ZMASK_PITCH */ + case 0x4f44: /* ZB_HIZ_OFFSET */ + case 0x4f54: /* ZB_HIZ_PITCH */ + if (idx_value && (p->rdev->hyperz_filp != p->filp)) + goto fail; + break; + case 0x4028: + if (idx_value && (p->rdev->hyperz_filp != p->filp)) + goto fail; + /* GB_Z_PEQ_CONFIG */ + if (p->rdev->family >= CHIP_RV350) + break; + goto fail; + break; case 0x4be8: /* valid register only on RV530 */ if (p->rdev->family == CHIP_RV530) @@ -1066,8 +1099,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, } return 0; fail: - printk(KERN_ERR "Forbidden register 0x%04X in cs at %d\n", - reg, idx); + printk(KERN_ERR "Forbidden register 0x%04X in cs at %d (val=%08x)\n", + reg, idx, idx_value); return -EINVAL; } @@ -1161,6 +1194,11 @@ static int r300_packet3_check(struct radeon_cs_parser *p, return r; } break; + case PACKET3_3D_CLEAR_HIZ: + case PACKET3_3D_CLEAR_ZMASK: + if (p->rdev->hyperz_filp != p->filp) + return -EINVAL; + break; case PACKET3_NOP: break; default: @@ -1380,6 +1418,8 @@ int r300_init(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); /* TODO: disable VGA need to use VGA request */ + /* restore some register to sane defaults */ + r100_restore_sanity(rdev); /* BIOS*/ if (!radeon_get_bios(rdev)) { if (ASIC_IS_AVIVO(rdev)) diff --git a/drivers/gpu/drm/radeon/r300d.h b/drivers/gpu/drm/radeon/r300d.h index 968a33317fb..0c036c60d9d 100644 --- a/drivers/gpu/drm/radeon/r300d.h +++ b/drivers/gpu/drm/radeon/r300d.h @@ -48,10 +48,12 @@ #define PACKET3_3D_DRAW_IMMD 0x29 #define PACKET3_3D_DRAW_INDX 0x2A #define PACKET3_3D_LOAD_VBPNTR 0x2F +#define PACKET3_3D_CLEAR_ZMASK 0x32 #define PACKET3_INDX_BUFFER 0x33 #define PACKET3_3D_DRAW_VBUF_2 0x34 #define PACKET3_3D_DRAW_IMMD_2 0x35 #define PACKET3_3D_DRAW_INDX_2 0x36 +#define PACKET3_3D_CLEAR_HIZ 0x37 #define PACKET3_BITBLT_MULTI 0x9B #define PACKET0(reg, n) (CP_PACKET0 | \ diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c index e6c89142bb4..59f7bccc5be 100644 --- a/drivers/gpu/drm/radeon/r420.c +++ b/drivers/gpu/drm/radeon/r420.c @@ -343,6 +343,8 @@ int r420_init(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); /* TODO: disable VGA need to use VGA request */ + /* restore some register to sane defaults */ + r100_restore_sanity(rdev); /* BIOS*/ if (!radeon_get_bios(rdev)) { if (ASIC_IS_AVIVO(rdev)) diff --git a/drivers/gpu/drm/radeon/r500_reg.h b/drivers/gpu/drm/radeon/r500_reg.h index 93c9a2bbccf..6ac1f604e29 100644 --- a/drivers/gpu/drm/radeon/r500_reg.h +++ b/drivers/gpu/drm/radeon/r500_reg.h @@ -386,6 +386,11 @@ # define AVIVO_D1GRPH_TILED (1 << 20) # define AVIVO_D1GRPH_MACRO_ADDRESS_MODE (1 << 21) +# define R600_D1GRPH_ARRAY_MODE_LINEAR_GENERAL (0 << 20) +# define R600_D1GRPH_ARRAY_MODE_LINEAR_ALIGNED (1 << 20) +# define R600_D1GRPH_ARRAY_MODE_1D_TILED_THIN1 (2 << 20) +# define R600_D1GRPH_ARRAY_MODE_2D_TILED_THIN1 (4 << 20) + /* The R7xx *_HIGH surface regs are backwards; the D1 regs are in the D2 * block and vice versa. This applies to GRPH, CUR, etc. */ diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c index 694af7cc23a..1458dee902d 100644 --- a/drivers/gpu/drm/radeon/r520.c +++ b/drivers/gpu/drm/radeon/r520.c @@ -231,6 +231,8 @@ int r520_init(struct radeon_device *rdev) radeon_scratch_init(rdev); /* Initialize surface registers */ radeon_surface_init(rdev); + /* restore some register to sane defaults */ + r100_restore_sanity(rdev); /* TODO: disable VGA need to use VGA request */ /* BIOS*/ if (!radeon_get_bios(rdev)) { diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index e100f69faee..d0ebae9dde2 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -92,6 +92,21 @@ void r600_gpu_init(struct radeon_device *rdev); void r600_fini(struct radeon_device *rdev); void r600_irq_disable(struct radeon_device *rdev); +/* get temperature in millidegrees */ +u32 rv6xx_get_temp(struct radeon_device *rdev) +{ + u32 temp = (RREG32(CG_THERMAL_STATUS) & ASIC_T_MASK) >> + ASIC_T_SHIFT; + u32 actual_temp = 0; + + if ((temp >> 7) & 1) + actual_temp = 0; + else + actual_temp = (temp >> 1) & 0xff; + + return actual_temp * 1000; +} + void r600_pm_get_dynpm_state(struct radeon_device *rdev) { int i; @@ -256,7 +271,7 @@ void r600_pm_get_dynpm_state(struct radeon_device *rdev) } } - DRM_DEBUG("Requested: e: %d m: %d p: %d\n", + DRM_DEBUG_DRIVER("Requested: e: %d m: %d p: %d\n", rdev->pm.power_state[rdev->pm.requested_power_state_index]. clock_info[rdev->pm.requested_clock_mode_index].sclk, rdev->pm.power_state[rdev->pm.requested_power_state_index]. @@ -571,7 +586,7 @@ void r600_pm_misc(struct radeon_device *rdev) if (voltage->voltage != rdev->pm.current_vddc) { radeon_atom_set_voltage(rdev, voltage->voltage); rdev->pm.current_vddc = voltage->voltage; - DRM_DEBUG("Setting: v: %d\n", voltage->voltage); + DRM_DEBUG_DRIVER("Setting: v: %d\n", voltage->voltage); } } } @@ -869,7 +884,17 @@ void r600_pcie_gart_tlb_flush(struct radeon_device *rdev) u32 tmp; /* flush hdp cache so updates hit vram */ - WREG32(R_005480_HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1); + if ((rdev->family >= CHIP_RV770) && (rdev->family <= CHIP_RV740)) { + void __iomem *ptr = (void *)rdev->gart.table.vram.ptr; + u32 tmp; + + /* r7xx hw bug. write to HDP_DEBUG1 followed by fb read + * rather than write to HDP_REG_COHERENCY_FLUSH_CNTL + */ + WREG32(HDP_DEBUG1, 0); + tmp = readl((void __iomem *)ptr); + } else + WREG32(R_005480_HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1); WREG32(VM_CONTEXT0_INVALIDATION_LOW_ADDR, rdev->mc.gtt_start >> 12); WREG32(VM_CONTEXT0_INVALIDATION_HIGH_ADDR, (rdev->mc.gtt_end - 1) >> 12); @@ -1217,8 +1242,8 @@ int r600_mc_init(struct radeon_device *rdev) } rdev->mc.vram_width = numchan * chansize; /* Could aper size report 0 ? */ - rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0); - rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0); + rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0); + rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0); /* Setup GPU memory space */ rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE); rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE); @@ -1609,7 +1634,7 @@ void r600_gpu_init(struct radeon_device *rdev) r600_count_pipe_bits((cc_rb_backend_disable & R6XX_MAX_BACKENDS_MASK) >> 16)), (cc_rb_backend_disable >> 16)); - + rdev->config.r600.tile_config = tiling_config; tiling_config |= BACKEND_MAP(backend_map); WREG32(GB_TILING_CONFIG, tiling_config); WREG32(DCP_TILING_CONFIG, tiling_config & 0xffff); @@ -3512,5 +3537,15 @@ int r600_debugfs_mc_info_init(struct radeon_device *rdev) */ void r600_ioctl_wait_idle(struct radeon_device *rdev, struct radeon_bo *bo) { - WREG32(R_005480_HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1); + /* r7xx hw bug. write to HDP_DEBUG1 followed by fb read + * rather than write to HDP_REG_COHERENCY_FLUSH_CNTL + */ + if ((rdev->family >= CHIP_RV770) && (rdev->family <= CHIP_RV740)) { + void __iomem *ptr = (void *)rdev->gart.table.vram.ptr; + u32 tmp; + + WREG32(HDP_DEBUG1, 0); + tmp = readl((void __iomem *)ptr); + } else + WREG32(R_005480_HDP_MEM_COHERENCY_FLUSH_CNTL, 0x1); } diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c index 2b26553c352..b5443fe1c1d 100644 --- a/drivers/gpu/drm/radeon/r600_audio.c +++ b/drivers/gpu/drm/radeon/r600_audio.c @@ -63,7 +63,8 @@ int r600_audio_bits_per_sample(struct radeon_device *rdev) case 0x4: return 32; } - DRM_ERROR("Unknown bits per sample 0x%x using 16 instead.\n", (int)value); + dev_err(rdev->dev, "Unknown bits per sample 0x%x using 16 instead\n", + (int)value); return 16; } @@ -150,7 +151,8 @@ static void r600_audio_update_hdmi(unsigned long param) r600_hdmi_update_audio_settings(encoder); } - if(still_going) r600_audio_schedule_polling(rdev); + if (still_going) + r600_audio_schedule_polling(rdev); } /* @@ -158,8 +160,9 @@ static void r600_audio_update_hdmi(unsigned long param) */ static void r600_audio_engine_enable(struct radeon_device *rdev, bool enable) { - DRM_INFO("%s audio support", enable ? "Enabling" : "Disabling"); + DRM_INFO("%s audio support\n", enable ? "Enabling" : "Disabling"); WREG32_P(R600_AUDIO_ENABLE, enable ? 0x81000000 : 0x0, ~0x81000000); + rdev->audio_enabled = enable; } /* @@ -195,12 +198,14 @@ void r600_audio_enable_polling(struct drm_encoder *encoder) struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); - DRM_DEBUG("r600_audio_enable_polling: %d", radeon_encoder->audio_polling_active); + DRM_DEBUG("r600_audio_enable_polling: %d\n", + radeon_encoder->audio_polling_active); if (radeon_encoder->audio_polling_active) return; radeon_encoder->audio_polling_active = 1; - mod_timer(&rdev->audio_timer, jiffies + 1); + if (rdev->audio_enabled) + mod_timer(&rdev->audio_timer, jiffies + 1); } /* @@ -209,7 +214,8 @@ void r600_audio_enable_polling(struct drm_encoder *encoder) void r600_audio_disable_polling(struct drm_encoder *encoder) { struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); - DRM_DEBUG("r600_audio_disable_polling: %d", radeon_encoder->audio_polling_active); + DRM_DEBUG("r600_audio_disable_polling: %d\n", + radeon_encoder->audio_polling_active); radeon_encoder->audio_polling_active = 0; } @@ -236,7 +242,7 @@ void r600_audio_set_clock(struct drm_encoder *encoder, int clock) WREG32_P(R600_AUDIO_TIMING, 0x100, ~0x301); break; default: - DRM_ERROR("Unsupported encoder type 0x%02X\n", + dev_err(rdev->dev, "Unsupported encoder type 0x%02X\n", radeon_encoder->encoder_id); return; } @@ -266,7 +272,7 @@ void r600_audio_set_clock(struct drm_encoder *encoder, int clock) */ void r600_audio_fini(struct radeon_device *rdev) { - if (!radeon_audio || !r600_audio_chipset_supported(rdev)) + if (!rdev->audio_enabled) return; del_timer(&rdev->audio_timer); diff --git a/drivers/gpu/drm/radeon/r600_blit_shaders.c b/drivers/gpu/drm/radeon/r600_blit_shaders.c index 0271b53fa2d..e8151c1d55b 100644 --- a/drivers/gpu/drm/radeon/r600_blit_shaders.c +++ b/drivers/gpu/drm/radeon/r600_blit_shaders.c @@ -39,37 +39,45 @@ const u32 r6xx_default_state[] = { - 0xc0002400, + 0xc0002400, /* START_3D_CMDBUF */ 0x00000000, - 0xc0012800, + + 0xc0012800, /* CONTEXT_CONTROL */ 0x80000000, 0x80000000, + 0xc0016800, 0x00000010, - 0x00008000, + 0x00008000, /* WAIT_UNTIL */ + 0xc0016800, 0x00000542, - 0x07000003, + 0x07000003, /* TA_CNTL_AUX */ + 0xc0016800, 0x000005c5, - 0x00000000, + 0x00000000, /* VC_ENHANCE */ + 0xc0016800, 0x00000363, - 0x00000000, + 0x00000000, /* SQ_DYN_GPR_CNTL_PS_FLUSH_REQ */ + 0xc0016800, 0x0000060c, - 0x82000000, + 0x82000000, /* DB_DEBUG */ + 0xc0016800, 0x0000060e, - 0x01020204, - 0xc0016f00, - 0x00000000, - 0x00000000, - 0xc0016f00, - 0x00000001, + 0x01020204, /* DB_WATERMARKS */ + + 0xc0026f00, 0x00000000, + 0x00000000, /* SQ_VTX_BASE_VTX_LOC */ + 0x00000000, /* SQ_VTX_START_INST_LOC */ + 0xc0096900, 0x0000022a, + 0x00000000, /* SQ_ESGS_RING_ITEMSIZE */ 0x00000000, 0x00000000, 0x00000000, @@ -78,515 +86,317 @@ const u32 r6xx_default_state[] = 0x00000000, 0x00000000, 0x00000000, - 0x00000000, + 0xc0016900, 0x00000004, - 0x00000000, - 0xc0016900, + 0x00000000, /* DB_DEPTH_INFO */ + + 0xc0026900, 0x0000000a, - 0x00000000, - 0xc0016900, - 0x0000000b, - 0x00000000, - 0xc0016900, - 0x0000010c, - 0x00000000, - 0xc0016900, - 0x0000010d, - 0x00000000, + 0x00000000, /* DB_STENCIL_CLEAR */ + 0x00000000, /* DB_DEPTH_CLEAR */ + 0xc0016900, 0x00000200, - 0x00000000, - 0xc0016900, + 0x00000000, /* DB_DEPTH_CONTROL */ + + 0xc0026900, 0x00000343, - 0x00000060, - 0xc0016900, - 0x00000344, - 0x00000040, + 0x00000060, /* DB_RENDER_CONTROL */ + 0x00000040, /* DB_RENDER_OVERRIDE */ + 0xc0016900, 0x00000351, - 0x0000aa00, - 0xc0016900, - 0x00000104, - 0x00000000, - 0xc0016900, - 0x0000010e, - 0x00000000, - 0xc0046900, - 0x00000105, - 0x00000000, - 0x00000000, + 0x0000aa00, /* DB_ALPHA_TO_MASK */ + + 0xc00f6900, + 0x00000100, + 0x00000800, /* VGT_MAX_VTX_INDX */ + 0x00000000, /* VGT_MIN_VTX_INDX */ + 0x00000000, /* VGT_INDX_OFFSET */ + 0x00000000, /* VGT_MULTI_PRIM_IB_RESET_INDX */ + 0x00000000, /* SX_ALPHA_TEST_CONTROL */ + 0x00000000, /* CB_BLEND_RED */ 0x00000000, 0x00000000, - 0xc0036900, - 0x00000109, 0x00000000, + 0x00000000, /* CB_FOG_RED */ 0x00000000, 0x00000000, + 0x00000000, /* DB_STENCILREFMASK */ + 0x00000000, /* DB_STENCILREFMASK_BF */ + 0x00000000, /* SX_ALPHA_REF */ + 0xc0046900, 0x0000030c, - 0x01000000, + 0x01000000, /* CB_CLRCMP_CNTL */ 0x00000000, 0x00000000, 0x00000000, + 0xc0046900, 0x00000048, - 0x3f800000, + 0x3f800000, /* CB_CLEAR_RED */ 0x00000000, 0x3f800000, 0x3f800000, - 0xc0016900, - 0x0000008e, - 0x0000000f, + 0xc0016900, 0x00000080, - 0x00000000, - 0xc0016900, + 0x00000000, /* PA_SC_WINDOW_OFFSET */ + + 0xc00a6900, 0x00000083, - 0x0000ffff, - 0xc0016900, - 0x00000084, - 0x00000000, - 0xc0016900, - 0x00000085, + 0x0000ffff, /* PA_SC_CLIP_RECT_RULE */ + 0x00000000, /* PA_SC_CLIPRECT_0_TL */ 0x20002000, - 0xc0016900, - 0x00000086, 0x00000000, - 0xc0016900, - 0x00000087, 0x20002000, - 0xc0016900, - 0x00000088, 0x00000000, - 0xc0016900, - 0x00000089, 0x20002000, - 0xc0016900, - 0x0000008a, 0x00000000, - 0xc0016900, - 0x0000008b, 0x20002000, - 0xc0016900, - 0x0000008c, - 0x00000000, - 0xc0016900, + 0x00000000, /* PA_SC_EDGERULE */ + + 0xc0406900, 0x00000094, - 0x80000000, - 0xc0016900, - 0x00000095, + 0x80000000, /* PA_SC_VPORT_SCISSOR_0_TL */ + 0x20002000, /* PA_SC_VPORT_SCISSOR_0_BR */ + 0x80000000, /* PA_SC_VPORT_SCISSOR_1_TL */ 0x20002000, - 0xc0026900, - 0x000000b4, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x00000096, 0x80000000, - 0xc0016900, - 0x00000097, 0x20002000, - 0xc0026900, - 0x000000b6, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x00000098, 0x80000000, - 0xc0016900, - 0x00000099, 0x20002000, - 0xc0026900, - 0x000000b8, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x0000009a, 0x80000000, - 0xc0016900, - 0x0000009b, 0x20002000, - 0xc0026900, - 0x000000ba, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x0000009c, 0x80000000, - 0xc0016900, - 0x0000009d, 0x20002000, - 0xc0026900, - 0x000000bc, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x0000009e, 0x80000000, - 0xc0016900, - 0x0000009f, 0x20002000, - 0xc0026900, - 0x000000be, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a0, 0x80000000, - 0xc0016900, - 0x000000a1, 0x20002000, - 0xc0026900, - 0x000000c0, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a2, 0x80000000, - 0xc0016900, - 0x000000a3, 0x20002000, - 0xc0026900, - 0x000000c2, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a4, 0x80000000, - 0xc0016900, - 0x000000a5, 0x20002000, - 0xc0026900, - 0x000000c4, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a6, 0x80000000, - 0xc0016900, - 0x000000a7, 0x20002000, - 0xc0026900, - 0x000000c6, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a8, 0x80000000, - 0xc0016900, - 0x000000a9, 0x20002000, - 0xc0026900, - 0x000000c8, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000aa, 0x80000000, - 0xc0016900, - 0x000000ab, 0x20002000, - 0xc0026900, - 0x000000ca, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000ac, 0x80000000, - 0xc0016900, - 0x000000ad, 0x20002000, - 0xc0026900, - 0x000000cc, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000ae, 0x80000000, - 0xc0016900, - 0x000000af, 0x20002000, - 0xc0026900, - 0x000000ce, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000b0, 0x80000000, - 0xc0016900, - 0x000000b1, 0x20002000, - 0xc0026900, - 0x000000d0, - 0x00000000, + 0x00000000, /* PA_SC_VPORT_ZMIN_0 */ 0x3f800000, - 0xc0016900, - 0x000000b2, - 0x80000000, - 0xc0016900, - 0x000000b3, - 0x20002000, - 0xc0026900, - 0x000000d2, 0x00000000, 0x3f800000, - 0xc0016900, - 0x00000293, - 0x00004010, - 0xc0016900, - 0x00000300, 0x00000000, - 0xc0016900, - 0x00000301, - 0x00000000, - 0xc0016900, - 0x00000312, - 0xffffffff, - 0xc0016900, - 0x00000307, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000308, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000283, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000292, + 0x3f800000, 0x00000000, - 0xc0066900, - 0x0000010f, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000206, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000207, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000208, + 0x3f800000, 0x00000000, - 0xc0046900, - 0x00000303, 0x3f800000, + + 0xc0026900, + 0x00000292, + 0x00000000, /* PA_SC_MPASS_PS_CNTL */ + 0x00004010, /* PA_SC_MODE_CNTL */ + + 0xc0096900, + 0x00000300, + 0x00000000, /* PA_SC_LINE_CNTL */ + 0x00000000, /* PA_SC_AA_CONFIG */ + 0x0000002d, /* PA_SU_VTX_CNTL */ + 0x3f800000, /* PA_CL_GB_VERT_CLIP_ADJ */ 0x3f800000, 0x3f800000, 0x3f800000, - 0xc0016900, - 0x00000205, - 0x00000004, - 0xc0016900, - 0x00000280, - 0x00000000, - 0xc0016900, - 0x00000281, + 0x00000000, /* PA_SC_SAMPLE_LOCS_MCTX */ 0x00000000, + 0xc0016900, + 0x00000312, + 0xffffffff, /* PA_SC_AA_MASK */ + + 0xc0066900, 0x0000037e, - 0x00000000, - 0xc0016900, - 0x00000382, - 0x00000000, - 0xc0016900, - 0x00000380, - 0x00000000, - 0xc0016900, - 0x00000383, - 0x00000000, - 0xc0016900, - 0x00000381, - 0x00000000, - 0xc0016900, - 0x00000282, - 0x00000008, - 0xc0016900, - 0x00000302, - 0x0000002d, - 0xc0016900, - 0x0000037f, - 0x00000000, - 0xc0016900, - 0x000001b2, - 0x00000000, - 0xc0016900, + 0x00000000, /* PA_SU_POLY_OFFSET_DB_FMT_CNTL */ + 0x00000000, /* PA_SU_POLY_OFFSET_CLAMP */ + 0x00000000, /* PA_SU_POLY_OFFSET_FRONT_SCALE */ + 0x00000000, /* PA_SU_POLY_OFFSET_FRONT_OFFSET */ + 0x00000000, /* PA_SU_POLY_OFFSET_BACK_SCALE */ + 0x00000000, /* PA_SU_POLY_OFFSET_BACK_OFFSET */ + + 0xc0046900, 0x000001b6, - 0x00000000, - 0xc0016900, - 0x000001b7, - 0x00000000, - 0xc0016900, - 0x000001b8, - 0x00000000, - 0xc0016900, - 0x000001b9, - 0x00000000, + 0x00000000, /* SPI_INPUT_Z */ + 0x00000000, /* SPI_FOG_CNTL */ + 0x00000000, /* SPI_FOG_FUNC_SCALE */ + 0x00000000, /* SPI_FOG_FUNC_BIAS */ + 0xc0016900, 0x00000225, - 0x00000000, + 0x00000000, /* SQ_PGM_START_FS */ + 0xc0016900, 0x00000229, - 0x00000000, + 0x00000000, /* SQ_PGM_RESOURCES_FS */ + 0xc0016900, 0x00000237, - 0x00000000, - 0xc0016900, - 0x00000100, - 0x00000800, - 0xc0016900, - 0x00000101, - 0x00000000, - 0xc0016900, - 0x00000102, - 0x00000000, - 0xc0016900, + 0x00000000, /* SQ_PGM_CF_OFFSET_FS */ + + 0xc0026900, 0x000002a8, - 0x00000000, - 0xc0016900, - 0x000002a9, - 0x00000000, - 0xc0016900, - 0x00000103, - 0x00000000, - 0xc0016900, - 0x00000284, - 0x00000000, - 0xc0016900, - 0x00000290, - 0x00000000, - 0xc0016900, - 0x00000285, - 0x00000000, - 0xc0016900, - 0x00000286, - 0x00000000, - 0xc0016900, - 0x00000287, - 0x00000000, - 0xc0016900, - 0x00000288, - 0x00000000, - 0xc0016900, - 0x00000289, - 0x00000000, - 0xc0016900, - 0x0000028a, - 0x00000000, - 0xc0016900, - 0x0000028b, - 0x00000000, - 0xc0016900, - 0x0000028c, - 0x00000000, - 0xc0016900, - 0x0000028d, - 0x00000000, - 0xc0016900, - 0x0000028e, - 0x00000000, - 0xc0016900, - 0x0000028f, - 0x00000000, + 0x00000000, /* VGT_INSTANCE_STEP_RATE_0 */ + 0x00000000, /* VGT_INSTANCE_STEP_RATE_1 */ + + 0xc0116900, + 0x00000280, + 0x00000000, /* PA_SU_POINT_SIZE */ + 0x00000000, /* PA_SU_POINT_MINMAX */ + 0x00000008, /* PA_SU_LINE_CNTL */ + 0x00000000, /* PA_SC_LINE_STIPPLE */ + 0x00000000, /* VGT_OUTPUT_PATH_CNTL */ + 0x00000000, /* VGT_HOS_CNTL */ + 0x00000000, /* VGT_HOS_MAX_TESS_LEVEL */ + 0x00000000, /* VGT_HOS_MIN_TESS_LEVEL */ + 0x00000000, /* VGT_HOS_REUSE_DEPTH */ + 0x00000000, /* VGT_GROUP_PRIM_TYPE */ + 0x00000000, /* VGT_GROUP_FIRST_DECR */ + 0x00000000, /* VGT_GROUP_DECR */ + 0x00000000, /* VGT_GROUP_VECT_0_CNTL */ + 0x00000000, /* VGT_GROUP_VECT_1_CNTL */ + 0x00000000, /* VGT_GROUP_VECT_0_FMT_CNTL */ + 0x00000000, /* VGT_GROUP_VECT_1_FMT_CNTL */ + 0x00000000, /* VGT_GS_MODE */ + 0xc0016900, 0x000002a1, - 0x00000000, + 0x00000000, /* VGT_PRIMITIVEID_EN */ + 0xc0016900, 0x000002a5, - 0x00000000, - 0xc0016900, + 0x00000000, /* VGT_MULTI_PRIM_ID_RESET_EN */ + + 0xc0036900, 0x000002ac, - 0x00000000, - 0xc0016900, - 0x000002ad, - 0x00000000, - 0xc0016900, - 0x000002ae, - 0x00000000, + 0x00000000, /* VGT_STRMOUT_EN */ + 0x00000000, /* VGT_REUSE_OFF */ + 0x00000000, /* VGT_VTX_CNT_EN */ + 0xc0016900, 0x000002c8, - 0x00000000, - 0xc0016900, - 0x00000206, - 0x00000100, - 0xc0016900, - 0x00000204, - 0x00010000, - 0xc0036e00, - 0x00000000, - 0x00000012, - 0x00000000, - 0x00000000, - 0xc0016900, - 0x0000008f, - 0x0000000f, - 0xc0016900, - 0x000001e8, - 0x00000001, - 0xc0016900, + 0x00000000, /* VGT_STRMOUT_BUFFER_EN */ + + 0xc0076900, 0x00000202, - 0x00cc0000, + 0x00cc0000, /* CB_COLOR_CONTROL */ + 0x00000210, /* DB_SHADER_CNTL */ + 0x00010000, /* PA_CL_CLIP_CNTL */ + 0x00000244, /* PA_SU_SC_MODE_CNTL */ + 0x00000100, /* PA_CL_VTE_CNTL */ + 0x00000000, /* PA_CL_VS_OUT_CNTL */ + 0x00000000, /* PA_CL_NANINF_CNTL */ + + 0xc0026900, + 0x0000008e, + 0x0000000f, /* CB_TARGET_MASK */ + 0x0000000f, /* CB_SHADER_MASK */ + 0xc0016900, - 0x00000205, - 0x00000244, + 0x000001e8, + 0x00000001, /* CB_SHADER_CONTROL */ + 0xc0016900, - 0x00000203, - 0x00000210, + 0x00000185, + 0x00000000, /* SPI_VS_OUT_ID_0 */ + 0xc0016900, + 0x00000191, + 0x00000b00, /* SPI_PS_INPUT_CNTL_0 */ + + 0xc0056900, 0x000001b1, + 0x00000000, /* SPI_VS_OUT_CONFIG */ + 0x00000000, /* SPI_THREAD_GROUPING */ + 0x00000001, /* SPI_PS_IN_CONTROL_0 */ + 0x00000000, /* SPI_PS_IN_CONTROL_1 */ + 0x00000000, /* SPI_INTERP_CONTROL_0 */ + + 0xc0036e00, /* SET_SAMPLER */ 0x00000000, - 0xc0016900, - 0x00000185, - 0x00000000, - 0xc0016900, - 0x000001b3, - 0x00000001, - 0xc0016900, - 0x000001b4, + 0x00000012, 0x00000000, - 0xc0016900, - 0x00000191, - 0x00000b00, - 0xc0016900, - 0x000001b5, 0x00000000, }; const u32 r7xx_default_state[] = { - 0xc0012800, + 0xc0012800, /* CONTEXT_CONTROL */ 0x80000000, 0x80000000, + 0xc0016800, 0x00000010, - 0x00008000, + 0x00008000, /* WAIT_UNTIL */ + 0xc0016800, 0x00000542, - 0x07000002, + 0x07000002, /* TA_CNTL_AUX */ + 0xc0016800, 0x000005c5, - 0x00000000, + 0x00000000, /* VC_ENHANCE */ + 0xc0016800, 0x00000363, - 0x00004000, + 0x00004000, /* SQ_DYN_GPR_CNTL_PS_FLUSH_REQ */ + 0xc0016800, 0x0000060c, - 0x00000000, + 0x00000000, /* DB_DEBUG */ + 0xc0016800, 0x0000060e, - 0x00420204, - 0xc0016f00, - 0x00000000, - 0x00000000, - 0xc0016f00, - 0x00000001, + 0x00420204, /* DB_WATERMARKS */ + + 0xc0026f00, 0x00000000, + 0x00000000, /* SQ_VTX_BASE_VTX_LOC */ + 0x00000000, /* SQ_VTX_START_INST_LOC */ + 0xc0096900, 0x0000022a, + 0x00000000, /* SQ_ESGS_RING_ITEMSIZE */ 0x00000000, 0x00000000, 0x00000000, @@ -595,470 +405,269 @@ const u32 r7xx_default_state[] = 0x00000000, 0x00000000, 0x00000000, - 0x00000000, + 0xc0016900, 0x00000004, - 0x00000000, - 0xc0016900, + 0x00000000, /* DB_DEPTH_INFO */ + + 0xc0026900, 0x0000000a, - 0x00000000, - 0xc0016900, - 0x0000000b, - 0x00000000, - 0xc0016900, - 0x0000010c, - 0x00000000, - 0xc0016900, - 0x0000010d, - 0x00000000, + 0x00000000, /* DB_STENCIL_CLEAR */ + 0x00000000, /* DB_DEPTH_CLEAR */ + 0xc0016900, 0x00000200, - 0x00000000, - 0xc0016900, + 0x00000000, /* DB_DEPTH_CONTROL */ + + 0xc0026900, 0x00000343, - 0x00000060, - 0xc0016900, - 0x00000344, - 0x00000000, + 0x00000060, /* DB_RENDER_CONTROL */ + 0x00000000, /* DB_RENDER_OVERRIDE */ + 0xc0016900, 0x00000351, - 0x0000aa00, - 0xc0016900, - 0x00000104, - 0x00000000, - 0xc0016900, - 0x0000010e, - 0x00000000, - 0xc0046900, - 0x00000105, - 0x00000000, + 0x0000aa00, /* DB_ALPHA_TO_MASK */ + + 0xc0096900, + 0x00000100, + 0x00000800, /* VGT_MAX_VTX_INDX */ + 0x00000000, /* VGT_MIN_VTX_INDX */ + 0x00000000, /* VGT_INDX_OFFSET */ + 0x00000000, /* VGT_MULTI_PRIM_IB_RESET_INDX */ + 0x00000000, /* SX_ALPHA_TEST_CONTROL */ + 0x00000000, /* CB_BLEND_RED */ 0x00000000, 0x00000000, 0x00000000, + + 0xc0036900, + 0x0000010c, + 0x00000000, /* DB_STENCILREFMASK */ + 0x00000000, /* DB_STENCILREFMASK_BF */ + 0x00000000, /* SX_ALPHA_REF */ + 0xc0046900, - 0x0000030c, + 0x0000030c, /* CB_CLRCMP_CNTL */ 0x01000000, 0x00000000, 0x00000000, 0x00000000, - 0xc0016900, - 0x0000008e, - 0x0000000f, + 0xc0016900, 0x00000080, - 0x00000000, - 0xc0016900, + 0x00000000, /* PA_SC_WINDOW_OFFSET */ + + 0xc00a6900, 0x00000083, - 0x0000ffff, - 0xc0016900, - 0x00000084, - 0x00000000, - 0xc0016900, - 0x00000085, + 0x0000ffff, /* PA_SC_CLIP_RECT_RULE */ + 0x00000000, /* PA_SC_CLIPRECT_0_TL */ 0x20002000, - 0xc0016900, - 0x00000086, 0x00000000, - 0xc0016900, - 0x00000087, 0x20002000, - 0xc0016900, - 0x00000088, 0x00000000, - 0xc0016900, - 0x00000089, 0x20002000, - 0xc0016900, - 0x0000008a, 0x00000000, - 0xc0016900, - 0x0000008b, 0x20002000, - 0xc0016900, - 0x0000008c, - 0xaaaaaaaa, - 0xc0016900, + 0xaaaaaaaa, /* PA_SC_EDGERULE */ + + 0xc0406900, 0x00000094, - 0x80000000, - 0xc0016900, - 0x00000095, + 0x80000000, /* PA_SC_VPORT_SCISSOR_0_TL */ + 0x20002000, /* PA_SC_VPORT_SCISSOR_0_BR */ + 0x80000000, /* PA_SC_VPORT_SCISSOR_1_TL */ 0x20002000, - 0xc0026900, - 0x000000b4, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x00000096, 0x80000000, - 0xc0016900, - 0x00000097, 0x20002000, - 0xc0026900, - 0x000000b6, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x00000098, 0x80000000, - 0xc0016900, - 0x00000099, 0x20002000, - 0xc0026900, - 0x000000b8, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x0000009a, 0x80000000, - 0xc0016900, - 0x0000009b, 0x20002000, - 0xc0026900, - 0x000000ba, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x0000009c, 0x80000000, - 0xc0016900, - 0x0000009d, 0x20002000, - 0xc0026900, - 0x000000bc, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x0000009e, 0x80000000, - 0xc0016900, - 0x0000009f, 0x20002000, - 0xc0026900, - 0x000000be, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a0, 0x80000000, - 0xc0016900, - 0x000000a1, 0x20002000, - 0xc0026900, - 0x000000c0, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a2, 0x80000000, - 0xc0016900, - 0x000000a3, 0x20002000, - 0xc0026900, - 0x000000c2, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a4, 0x80000000, - 0xc0016900, - 0x000000a5, 0x20002000, - 0xc0026900, - 0x000000c4, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a6, 0x80000000, - 0xc0016900, - 0x000000a7, 0x20002000, - 0xc0026900, - 0x000000c6, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000a8, 0x80000000, - 0xc0016900, - 0x000000a9, 0x20002000, - 0xc0026900, - 0x000000c8, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000aa, 0x80000000, - 0xc0016900, - 0x000000ab, 0x20002000, - 0xc0026900, - 0x000000ca, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000ac, 0x80000000, - 0xc0016900, - 0x000000ad, 0x20002000, - 0xc0026900, - 0x000000cc, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000ae, 0x80000000, - 0xc0016900, - 0x000000af, 0x20002000, - 0xc0026900, - 0x000000ce, - 0x00000000, - 0x3f800000, - 0xc0016900, - 0x000000b0, 0x80000000, - 0xc0016900, - 0x000000b1, 0x20002000, - 0xc0026900, - 0x000000d0, - 0x00000000, + 0x00000000, /* PA_SC_VPORT_ZMIN_0 */ 0x3f800000, - 0xc0016900, - 0x000000b2, - 0x80000000, - 0xc0016900, - 0x000000b3, - 0x20002000, - 0xc0026900, - 0x000000d2, 0x00000000, 0x3f800000, - 0xc0016900, - 0x00000293, - 0x00514000, - 0xc0016900, - 0x00000300, - 0x00000000, - 0xc0016900, - 0x00000301, 0x00000000, - 0xc0016900, - 0x00000312, - 0xffffffff, - 0xc0016900, - 0x00000307, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000308, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000283, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000292, + 0x3f800000, 0x00000000, - 0xc0066900, - 0x0000010f, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000206, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000207, + 0x3f800000, 0x00000000, - 0xc0016900, - 0x00000208, + 0x3f800000, 0x00000000, - 0xc0046900, - 0x00000303, 0x3f800000, + + 0xc0026900, + 0x00000292, + 0x00000000, /* PA_SC_MPASS_PS_CNTL */ + 0x00514000, /* PA_SC_MODE_CNTL */ + + 0xc0096900, + 0x00000300, + 0x00000000, /* PA_SC_LINE_CNTL */ + 0x00000000, /* PA_SC_AA_CONFIG */ + 0x0000002d, /* PA_SU_VTX_CNTL */ + 0x3f800000, /* PA_CL_GB_VERT_CLIP_ADJ */ 0x3f800000, 0x3f800000, 0x3f800000, - 0xc0016900, - 0x00000205, - 0x00000004, - 0xc0016900, - 0x00000280, - 0x00000000, - 0xc0016900, - 0x00000281, + 0x00000000, /* PA_SC_SAMPLE_LOCS_MCTX */ 0x00000000, + 0xc0016900, + 0x00000312, + 0xffffffff, /* PA_SC_AA_MASK */ + + 0xc0066900, 0x0000037e, - 0x00000000, - 0xc0016900, - 0x00000382, - 0x00000000, - 0xc0016900, - 0x00000380, - 0x00000000, - 0xc0016900, - 0x00000383, - 0x00000000, - 0xc0016900, - 0x00000381, - 0x00000000, - 0xc0016900, - 0x00000282, - 0x00000008, - 0xc0016900, - 0x00000302, - 0x0000002d, - 0xc0016900, - 0x0000037f, - 0x00000000, - 0xc0016900, - 0x000001b2, - 0x00000001, - 0xc0016900, + 0x00000000, /* PA_SU_POLY_OFFSET_DB_FMT_CNTL */ + 0x00000000, /* PA_SU_POLY_OFFSET_CLAMP */ + 0x00000000, /* PA_SU_POLY_OFFSET_FRONT_SCALE */ + 0x00000000, /* PA_SU_POLY_OFFSET_FRONT_OFFSET */ + 0x00000000, /* PA_SU_POLY_OFFSET_BACK_SCALE */ + 0x00000000, /* PA_SU_POLY_OFFSET_BACK_OFFSET */ + + 0xc0046900, 0x000001b6, - 0x00000000, - 0xc0016900, - 0x000001b7, - 0x00000000, - 0xc0016900, - 0x000001b8, - 0x00000000, - 0xc0016900, - 0x000001b9, - 0x00000000, + 0x00000000, /* SPI_INPUT_Z */ + 0x00000000, /* SPI_FOG_CNTL */ + 0x00000000, /* SPI_FOG_FUNC_SCALE */ + 0x00000000, /* SPI_FOG_FUNC_BIAS */ + 0xc0016900, 0x00000225, - 0x00000000, + 0x00000000, /* SQ_PGM_START_FS */ + 0xc0016900, 0x00000229, - 0x00000000, + 0x00000000, /* SQ_PGM_RESOURCES_FS */ + 0xc0016900, 0x00000237, - 0x00000000, - 0xc0016900, - 0x00000100, - 0x00000800, - 0xc0016900, - 0x00000101, - 0x00000000, - 0xc0016900, - 0x00000102, - 0x00000000, - 0xc0016900, + 0x00000000, /* SQ_PGM_CF_OFFSET_FS */ + + 0xc0026900, 0x000002a8, - 0x00000000, - 0xc0016900, - 0x000002a9, - 0x00000000, - 0xc0016900, - 0x00000103, - 0x00000000, - 0xc0016900, - 0x00000284, - 0x00000000, - 0xc0016900, - 0x00000290, - 0x00000000, - 0xc0016900, - 0x00000285, - 0x00000000, - 0xc0016900, - 0x00000286, - 0x00000000, - 0xc0016900, - 0x00000287, - 0x00000000, - 0xc0016900, - 0x00000288, - 0x00000000, - 0xc0016900, - 0x00000289, - 0x00000000, - 0xc0016900, - 0x0000028a, - 0x00000000, - 0xc0016900, - 0x0000028b, - 0x00000000, - 0xc0016900, - 0x0000028c, - 0x00000000, - 0xc0016900, - 0x0000028d, - 0x00000000, - 0xc0016900, - 0x0000028e, - 0x00000000, - 0xc0016900, - 0x0000028f, - 0x00000000, + 0x00000000, /* VGT_INSTANCE_STEP_RATE_0 */ + 0x00000000, /* VGT_INSTANCE_STEP_RATE_1 */ + + 0xc0116900, + 0x00000280, + 0x00000000, /* PA_SU_POINT_SIZE */ + 0x00000000, /* PA_SU_POINT_MINMAX */ + 0x00000008, /* PA_SU_LINE_CNTL */ + 0x00000000, /* PA_SC_LINE_STIPPLE */ + 0x00000000, /* VGT_OUTPUT_PATH_CNTL */ + 0x00000000, /* VGT_HOS_CNTL */ + 0x00000000, /* VGT_HOS_MAX_TESS_LEVEL */ + 0x00000000, /* VGT_HOS_MIN_TESS_LEVEL */ + 0x00000000, /* VGT_HOS_REUSE_DEPTH */ + 0x00000000, /* VGT_GROUP_PRIM_TYPE */ + 0x00000000, /* VGT_GROUP_FIRST_DECR */ + 0x00000000, /* VGT_GROUP_DECR */ + 0x00000000, /* VGT_GROUP_VECT_0_CNTL */ + 0x00000000, /* VGT_GROUP_VECT_1_CNTL */ + 0x00000000, /* VGT_GROUP_VECT_0_FMT_CNTL */ + 0x00000000, /* VGT_GROUP_VECT_1_FMT_CNTL */ + 0x00000000, /* VGT_GS_MODE */ + 0xc0016900, 0x000002a1, - 0x00000000, + 0x00000000, /* VGT_PRIMITIVEID_EN */ + 0xc0016900, 0x000002a5, - 0x00000000, - 0xc0016900, + 0x00000000, /* VGT_MULTI_PRIM_ID_RESET_EN */ + + 0xc0036900, 0x000002ac, - 0x00000000, - 0xc0016900, - 0x000002ad, - 0x00000000, - 0xc0016900, - 0x000002ae, - 0x00000000, + 0x00000000, /* VGT_STRMOUT_EN */ + 0x00000000, /* VGT_REUSE_OFF */ + 0x00000000, /* VGT_VTX_CNT_EN */ + 0xc0016900, 0x000002c8, - 0x00000000, - 0xc0016900, - 0x00000206, - 0x00000100, - 0xc0016900, - 0x00000204, - 0x00010000, - 0xc0036e00, - 0x00000000, - 0x00000012, - 0x00000000, - 0x00000000, - 0xc0016900, - 0x0000008f, - 0x0000000f, - 0xc0016900, - 0x000001e8, - 0x00000001, - 0xc0016900, + 0x00000000, /* VGT_STRMOUT_BUFFER_EN */ + + 0xc0076900, 0x00000202, - 0x00cc0000, + 0x00cc0000, /* CB_COLOR_CONTROL */ + 0x00000210, /* DB_SHADER_CNTL */ + 0x00010000, /* PA_CL_CLIP_CNTL */ + 0x00000244, /* PA_SU_SC_MODE_CNTL */ + 0x00000100, /* PA_CL_VTE_CNTL */ + 0x00000000, /* PA_CL_VS_OUT_CNTL */ + 0x00000000, /* PA_CL_NANINF_CNTL */ + + 0xc0026900, + 0x0000008e, + 0x0000000f, /* CB_TARGET_MASK */ + 0x0000000f, /* CB_SHADER_MASK */ + 0xc0016900, - 0x00000205, - 0x00000244, + 0x000001e8, + 0x00000001, /* CB_SHADER_CONTROL */ + 0xc0016900, - 0x00000203, - 0x00000210, + 0x00000185, + 0x00000000, /* SPI_VS_OUT_ID_0 */ + 0xc0016900, + 0x00000191, + 0x00000b00, /* SPI_PS_INPUT_CNTL_0 */ + + 0xc0056900, 0x000001b1, + 0x00000000, /* SPI_VS_OUT_CONFIG */ + 0x00000001, /* SPI_THREAD_GROUPING */ + 0x00000001, /* SPI_PS_IN_CONTROL_0 */ + 0x00000000, /* SPI_PS_IN_CONTROL_1 */ + 0x00000000, /* SPI_INTERP_CONTROL_0 */ + + 0xc0036e00, /* SET_SAMPLER */ 0x00000000, - 0xc0016900, - 0x00000185, - 0x00000000, - 0xc0016900, - 0x000001b3, - 0x00000001, - 0xc0016900, - 0x000001b4, + 0x00000012, 0x00000000, - 0xc0016900, - 0x00000191, - 0x00000b00, - 0xc0016900, - 0x000001b5, 0x00000000, }; diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 144c32d3713..c3ea212e0c3 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -25,6 +25,7 @@ * Alex Deucher * Jerome Glisse */ +#include <linux/kernel.h> #include "drmP.h" #include "radeon.h" #include "r600d.h" @@ -166,7 +167,7 @@ static void r600_cs_track_init(struct r600_cs_track *track) static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) { struct r600_cs_track *track = p->track; - u32 bpe = 0, pitch, slice_tile_max, size, tmp, height; + u32 bpe = 0, pitch, slice_tile_max, size, tmp, height, pitch_align; volatile u32 *ib = p->ib->ptr; if (G_0280A0_TILE_MODE(track->cb_color_info[i])) { @@ -180,56 +181,57 @@ static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) i, track->cb_color_info[i]); return -EINVAL; } - pitch = (G_028060_PITCH_TILE_MAX(track->cb_color_size[i]) + 1) << 3; + /* pitch is the number of 8x8 tiles per row */ + pitch = G_028060_PITCH_TILE_MAX(track->cb_color_size[i]) + 1; slice_tile_max = G_028060_SLICE_TILE_MAX(track->cb_color_size[i]) + 1; - if (!pitch) { - dev_warn(p->dev, "%s:%d cb pitch (%d) for %d invalid (0x%08X)\n", - __func__, __LINE__, pitch, i, track->cb_color_size[i]); - return -EINVAL; - } - height = size / (pitch * bpe); + height = size / (pitch * 8 * bpe); if (height > 8192) height = 8192; + if (height > 7) + height &= ~0x7; switch (G_0280A0_ARRAY_MODE(track->cb_color_info[i])) { case V_0280A0_ARRAY_LINEAR_GENERAL: + /* technically height & 0x7 */ + break; case V_0280A0_ARRAY_LINEAR_ALIGNED: - if (pitch & 0x3f) { - dev_warn(p->dev, "%s:%d cb pitch (%d x %d = %d) invalid\n", - __func__, __LINE__, pitch, bpe, pitch * bpe); + pitch_align = max((u32)64, (u32)(track->group_size / bpe)) / 8; + if (!IS_ALIGNED(pitch, pitch_align)) { + dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n", + __func__, __LINE__, pitch); return -EINVAL; } - if ((pitch * bpe) & (track->group_size - 1)) { - dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n", - __func__, __LINE__, pitch); + if (!IS_ALIGNED(height, 8)) { + dev_warn(p->dev, "%s:%d cb height (%d) invalid\n", + __func__, __LINE__, height); return -EINVAL; } break; case V_0280A0_ARRAY_1D_TILED_THIN1: - if ((pitch * 8 * bpe * track->nsamples) & (track->group_size - 1)) { + pitch_align = max((u32)8, (u32)(track->group_size / (8 * bpe * track->nsamples))) / 8; + if (!IS_ALIGNED(pitch, pitch_align)) { dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n", - __func__, __LINE__, pitch); + __func__, __LINE__, pitch); + return -EINVAL; + } + if (!IS_ALIGNED(height, 8)) { + dev_warn(p->dev, "%s:%d cb height (%d) invalid\n", + __func__, __LINE__, height); return -EINVAL; } - height &= ~0x7; - if (!height) - height = 8; break; case V_0280A0_ARRAY_2D_TILED_THIN1: - if (pitch & ((8 * track->nbanks) - 1)) { + pitch_align = max((u32)track->nbanks, + (u32)(((track->group_size / 8) / (bpe * track->nsamples)) * track->nbanks)); + if (!IS_ALIGNED(pitch, pitch_align)) { dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n", __func__, __LINE__, pitch); return -EINVAL; } - tmp = pitch * 8 * bpe * track->nsamples; - tmp = tmp / track->nbanks; - if (tmp & (track->group_size - 1)) { - dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n", - __func__, __LINE__, pitch); + if (!IS_ALIGNED((height / 8), track->nbanks)) { + dev_warn(p->dev, "%s:%d cb height (%d) invalid\n", + __func__, __LINE__, height); return -EINVAL; } - height &= ~((16 * track->npipes) - 1); - if (!height) - height = 16 * track->npipes; break; default: dev_warn(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__, @@ -238,16 +240,20 @@ static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) return -EINVAL; } /* check offset */ - tmp = height * pitch; + tmp = height * pitch * 8 * bpe; if ((tmp + track->cb_color_bo_offset[i]) > radeon_bo_size(track->cb_color_bo[i])) { - dev_warn(p->dev, "%s offset[%d] %d to big\n", __func__, i, track->cb_color_bo_offset[i]); + dev_warn(p->dev, "%s offset[%d] %d too big\n", __func__, i, track->cb_color_bo_offset[i]); + return -EINVAL; + } + if (!IS_ALIGNED(track->cb_color_bo_offset[i], track->group_size)) { + dev_warn(p->dev, "%s offset[%d] %d not aligned\n", __func__, i, track->cb_color_bo_offset[i]); return -EINVAL; } /* limit max tile */ - tmp = (height * pitch) >> 6; + tmp = (height * pitch * 8) >> 6; if (tmp < slice_tile_max) slice_tile_max = tmp; - tmp = S_028060_PITCH_TILE_MAX((pitch >> 3) - 1) | + tmp = S_028060_PITCH_TILE_MAX(pitch - 1) | S_028060_SLICE_TILE_MAX(slice_tile_max - 1); ib[track->cb_color_size_idx[i]] = tmp; return 0; @@ -289,7 +295,7 @@ static int r600_cs_track_check(struct radeon_cs_parser *p) /* Check depth buffer */ if (G_028800_STENCIL_ENABLE(track->db_depth_control) || G_028800_Z_ENABLE(track->db_depth_control)) { - u32 nviews, bpe, ntiles; + u32 nviews, bpe, ntiles, pitch, pitch_align, height, size; if (track->db_bo == NULL) { dev_warn(p->dev, "z/stencil with no depth buffer\n"); return -EINVAL; @@ -332,6 +338,51 @@ static int r600_cs_track_check(struct radeon_cs_parser *p) } ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF); } else { + size = radeon_bo_size(track->db_bo); + pitch = G_028000_PITCH_TILE_MAX(track->db_depth_size) + 1; + height = size / (pitch * 8 * bpe); + height &= ~0x7; + if (!height) + height = 8; + + switch (G_028010_ARRAY_MODE(track->db_depth_info)) { + case V_028010_ARRAY_1D_TILED_THIN1: + pitch_align = (max((u32)8, (u32)(track->group_size / (8 * bpe))) / 8); + if (!IS_ALIGNED(pitch, pitch_align)) { + dev_warn(p->dev, "%s:%d db pitch (%d) invalid\n", + __func__, __LINE__, pitch); + return -EINVAL; + } + if (!IS_ALIGNED(height, 8)) { + dev_warn(p->dev, "%s:%d db height (%d) invalid\n", + __func__, __LINE__, height); + return -EINVAL; + } + break; + case V_028010_ARRAY_2D_TILED_THIN1: + pitch_align = max((u32)track->nbanks, + (u32)(((track->group_size / 8) / bpe) * track->nbanks)); + if (!IS_ALIGNED(pitch, pitch_align)) { + dev_warn(p->dev, "%s:%d db pitch (%d) invalid\n", + __func__, __LINE__, pitch); + return -EINVAL; + } + if ((height / 8) & (track->nbanks - 1)) { + dev_warn(p->dev, "%s:%d db height (%d) invalid\n", + __func__, __LINE__, height); + return -EINVAL; + } + break; + default: + dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__, + G_028010_ARRAY_MODE(track->db_depth_info), + track->db_depth_info); + return -EINVAL; + } + if (!IS_ALIGNED(track->db_offset, track->group_size)) { + dev_warn(p->dev, "%s offset[%d] %d not aligned\n", __func__, i, track->db_offset); + return -EINVAL; + } ntiles = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1; nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1; tmp = ntiles * bpe * 64 * nviews; @@ -724,7 +775,25 @@ static inline int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx track->db_depth_control = radeon_get_ib_value(p, idx); break; case R_028010_DB_DEPTH_INFO: - track->db_depth_info = radeon_get_ib_value(p, idx); + if (r600_cs_packet_next_is_pkt3_nop(p)) { + r = r600_cs_packet_next_reloc(p, &reloc); + if (r) { + dev_warn(p->dev, "bad SET_CONTEXT_REG " + "0x%04X\n", reg); + return -EINVAL; + } + track->db_depth_info = radeon_get_ib_value(p, idx); + ib[idx] &= C_028010_ARRAY_MODE; + track->db_depth_info &= C_028010_ARRAY_MODE; + if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) { + ib[idx] |= S_028010_ARRAY_MODE(V_028010_ARRAY_2D_TILED_THIN1); + track->db_depth_info |= S_028010_ARRAY_MODE(V_028010_ARRAY_2D_TILED_THIN1); + } else { + ib[idx] |= S_028010_ARRAY_MODE(V_028010_ARRAY_1D_TILED_THIN1); + track->db_depth_info |= S_028010_ARRAY_MODE(V_028010_ARRAY_1D_TILED_THIN1); + } + } else + track->db_depth_info = radeon_get_ib_value(p, idx); break; case R_028004_DB_DEPTH_VIEW: track->db_depth_view = radeon_get_ib_value(p, idx); @@ -757,8 +826,25 @@ static inline int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx case R_0280B4_CB_COLOR5_INFO: case R_0280B8_CB_COLOR6_INFO: case R_0280BC_CB_COLOR7_INFO: - tmp = (reg - R_0280A0_CB_COLOR0_INFO) / 4; - track->cb_color_info[tmp] = radeon_get_ib_value(p, idx); + if (r600_cs_packet_next_is_pkt3_nop(p)) { + r = r600_cs_packet_next_reloc(p, &reloc); + if (r) { + dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg); + return -EINVAL; + } + tmp = (reg - R_0280A0_CB_COLOR0_INFO) / 4; + track->cb_color_info[tmp] = radeon_get_ib_value(p, idx); + if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) { + ib[idx] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_2D_TILED_THIN1); + track->cb_color_info[tmp] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_2D_TILED_THIN1); + } else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) { + ib[idx] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_1D_TILED_THIN1); + track->cb_color_info[tmp] |= S_0280A0_ARRAY_MODE(V_0280A0_ARRAY_1D_TILED_THIN1); + } + } else { + tmp = (reg - R_0280A0_CB_COLOR0_INFO) / 4; + track->cb_color_info[tmp] = radeon_get_ib_value(p, idx); + } break; case R_028060_CB_COLOR0_SIZE: case R_028064_CB_COLOR1_SIZE: @@ -946,8 +1032,9 @@ static inline unsigned minify(unsigned size, unsigned levels) } static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned nlevels, - unsigned w0, unsigned h0, unsigned d0, unsigned bpe, - unsigned *l0_size, unsigned *mipmap_size) + unsigned w0, unsigned h0, unsigned d0, unsigned bpe, + unsigned pitch_align, + unsigned *l0_size, unsigned *mipmap_size) { unsigned offset, i, level, face; unsigned width, height, depth, rowstride, size; @@ -960,13 +1047,13 @@ static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned nlevels height = minify(h0, i); depth = minify(d0, i); for(face = 0; face < nfaces; face++) { - rowstride = ((width * bpe) + 255) & ~255; + rowstride = ALIGN((width * bpe), pitch_align); size = height * rowstride * depth; offset += size; offset = (offset + 0x1f) & ~0x1f; } } - *l0_size = (((w0 * bpe) + 255) & ~255) * h0 * d0; + *l0_size = ALIGN((w0 * bpe), pitch_align) * h0 * d0; *mipmap_size = offset; if (!blevel) *mipmap_size -= *l0_size; @@ -985,16 +1072,23 @@ static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned nlevels * the texture and mipmap bo object are big enough to cover this resource. */ static inline int r600_check_texture_resource(struct radeon_cs_parser *p, u32 idx, - struct radeon_bo *texture, - struct radeon_bo *mipmap) + struct radeon_bo *texture, + struct radeon_bo *mipmap, + u32 tiling_flags) { + struct r600_cs_track *track = p->track; u32 nfaces, nlevels, blevel, w0, h0, d0, bpe = 0; - u32 word0, word1, l0_size, mipmap_size; + u32 word0, word1, l0_size, mipmap_size, pitch, pitch_align; /* on legacy kernel we don't perform advanced check */ if (p->rdev == NULL) return 0; + word0 = radeon_get_ib_value(p, idx + 0); + if (tiling_flags & RADEON_TILING_MACRO) + word0 |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1); + else if (tiling_flags & RADEON_TILING_MICRO) + word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1); word1 = radeon_get_ib_value(p, idx + 1); w0 = G_038000_TEX_WIDTH(word0) + 1; h0 = G_038004_TEX_HEIGHT(word1) + 1; @@ -1021,11 +1115,55 @@ static inline int r600_check_texture_resource(struct radeon_cs_parser *p, u32 i __func__, __LINE__, G_038004_DATA_FORMAT(word1)); return -EINVAL; } + + pitch = G_038000_PITCH(word0) + 1; + switch (G_038000_TILE_MODE(word0)) { + case V_038000_ARRAY_LINEAR_GENERAL: + pitch_align = 1; + /* XXX check height align */ + break; + case V_038000_ARRAY_LINEAR_ALIGNED: + pitch_align = max((u32)64, (u32)(track->group_size / bpe)) / 8; + if (!IS_ALIGNED(pitch, pitch_align)) { + dev_warn(p->dev, "%s:%d tex pitch (%d) invalid\n", + __func__, __LINE__, pitch); + return -EINVAL; + } + /* XXX check height align */ + break; + case V_038000_ARRAY_1D_TILED_THIN1: + pitch_align = max((u32)8, (u32)(track->group_size / (8 * bpe))) / 8; + if (!IS_ALIGNED(pitch, pitch_align)) { + dev_warn(p->dev, "%s:%d tex pitch (%d) invalid\n", + __func__, __LINE__, pitch); + return -EINVAL; + } + /* XXX check height align */ + break; + case V_038000_ARRAY_2D_TILED_THIN1: + pitch_align = max((u32)track->nbanks, + (u32)(((track->group_size / 8) / bpe) * track->nbanks)); + if (!IS_ALIGNED(pitch, pitch_align)) { + dev_warn(p->dev, "%s:%d tex pitch (%d) invalid\n", + __func__, __LINE__, pitch); + return -EINVAL; + } + /* XXX check height align */ + break; + default: + dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__, + G_038000_TILE_MODE(word0), word0); + return -EINVAL; + } + /* XXX check offset align */ + word0 = radeon_get_ib_value(p, idx + 4); word1 = radeon_get_ib_value(p, idx + 5); blevel = G_038010_BASE_LEVEL(word0); nlevels = G_038014_LAST_LEVEL(word1); - r600_texture_size(nfaces, blevel, nlevels, w0, h0, d0, bpe, &l0_size, &mipmap_size); + r600_texture_size(nfaces, blevel, nlevels, w0, h0, d0, bpe, + (pitch_align * bpe), + &l0_size, &mipmap_size); /* using get ib will give us the offset into the texture bo */ word0 = radeon_get_ib_value(p, idx + 2); if ((l0_size + word0) > radeon_bo_size(texture)) { @@ -1239,6 +1377,10 @@ static int r600_packet3_check(struct radeon_cs_parser *p, return -EINVAL; } ib[idx+1+(i*7)+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff); + if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) + ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1); + else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) + ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1); texture = reloc->robj; /* tex mip base */ r = r600_cs_packet_next_reloc(p, &reloc); @@ -1249,7 +1391,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p, ib[idx+1+(i*7)+3] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff); mipmap = reloc->robj; r = r600_check_texture_resource(p, idx+(i*7)+1, - texture, mipmap); + texture, mipmap, reloc->lobj.tiling_flags); if (r) return r; break; diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c index 26b4bc9d89a..e6a58ed48dc 100644 --- a/drivers/gpu/drm/radeon/r600_hdmi.c +++ b/drivers/gpu/drm/radeon/r600_hdmi.c @@ -435,7 +435,8 @@ static int r600_hdmi_find_free_block(struct drm_device *dev) } } - if (rdev->family == CHIP_RS600 || rdev->family == CHIP_RS690) { + if (rdev->family == CHIP_RS600 || rdev->family == CHIP_RS690 || + rdev->family == CHIP_RS740) { return free_blocks[0] ? R600_HDMI_BLOCK1 : 0; } else if (rdev->family >= CHIP_R600) { if (free_blocks[0]) @@ -466,7 +467,8 @@ static void r600_hdmi_assign_block(struct drm_encoder *encoder) if (ASIC_IS_DCE32(rdev)) radeon_encoder->hdmi_config_offset = dig->dig_encoder ? R600_HDMI_CONFIG2 : R600_HDMI_CONFIG1; - } else if (rdev->family >= CHIP_R600) { + } else if (rdev->family >= CHIP_R600 || rdev->family == CHIP_RS600 || + rdev->family == CHIP_RS690 || rdev->family == CHIP_RS740) { radeon_encoder->hdmi_offset = r600_hdmi_find_free_block(dev); } } diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h index 59c1f8793e6..858a1920c0d 100644 --- a/drivers/gpu/drm/radeon/r600d.h +++ b/drivers/gpu/drm/radeon/r600d.h @@ -239,12 +239,18 @@ #define GRBM_SOFT_RESET 0x8020 #define SOFT_RESET_CP (1<<0) +#define CG_THERMAL_STATUS 0x7F4 +#define ASIC_T(x) ((x) << 0) +#define ASIC_T_MASK 0x1FF +#define ASIC_T_SHIFT 0 + #define HDP_HOST_PATH_CNTL 0x2C00 #define HDP_NONSURFACE_BASE 0x2C04 #define HDP_NONSURFACE_INFO 0x2C08 #define HDP_NONSURFACE_SIZE 0x2C0C #define HDP_REG_COHERENCY_FLUSH_CNTL 0x54A0 #define HDP_TILING_CONFIG 0x2F3C +#define HDP_DEBUG1 0x2F34 #define MC_VM_AGP_TOP 0x2184 #define MC_VM_AGP_BOT 0x2188 @@ -1154,6 +1160,10 @@ #define S_038000_TILE_MODE(x) (((x) & 0xF) << 3) #define G_038000_TILE_MODE(x) (((x) >> 3) & 0xF) #define C_038000_TILE_MODE 0xFFFFFF87 +#define V_038000_ARRAY_LINEAR_GENERAL 0x00000000 +#define V_038000_ARRAY_LINEAR_ALIGNED 0x00000001 +#define V_038000_ARRAY_1D_TILED_THIN1 0x00000002 +#define V_038000_ARRAY_2D_TILED_THIN1 0x00000004 #define S_038000_TILE_TYPE(x) (((x) & 0x1) << 7) #define G_038000_TILE_TYPE(x) (((x) >> 7) & 0x1) #define C_038000_TILE_TYPE 0xFFFFFF7F @@ -1357,6 +1367,8 @@ #define S_028010_ARRAY_MODE(x) (((x) & 0xF) << 15) #define G_028010_ARRAY_MODE(x) (((x) >> 15) & 0xF) #define C_028010_ARRAY_MODE 0xFFF87FFF +#define V_028010_ARRAY_1D_TILED_THIN1 0x00000002 +#define V_028010_ARRAY_2D_TILED_THIN1 0x00000004 #define S_028010_TILE_SURFACE_ENABLE(x) (((x) & 0x1) << 25) #define G_028010_TILE_SURFACE_ENABLE(x) (((x) >> 25) & 0x1) #define C_028010_TILE_SURFACE_ENABLE 0xFDFFFFFF diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 2f94dc66c18..3cd1c470b77 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -178,6 +178,9 @@ void radeon_combios_get_power_modes(struct radeon_device *rdev); void radeon_atombios_get_power_modes(struct radeon_device *rdev); void radeon_atom_set_voltage(struct radeon_device *rdev, u16 level); void rs690_pm_info(struct radeon_device *rdev); +extern u32 rv6xx_get_temp(struct radeon_device *rdev); +extern u32 rv770_get_temp(struct radeon_device *rdev); +extern u32 evergreen_get_temp(struct radeon_device *rdev); /* * Fences. @@ -232,7 +235,7 @@ struct radeon_surface_reg { */ struct radeon_mman { struct ttm_bo_global_ref bo_global_ref; - struct ttm_global_reference mem_global_ref; + struct drm_global_reference mem_global_ref; struct ttm_bo_device bdev; bool mem_global_referenced; bool initialized; @@ -671,6 +674,13 @@ struct radeon_pm_profile { int dpms_on_cm_idx; }; +enum radeon_int_thermal_type { + THERMAL_TYPE_NONE, + THERMAL_TYPE_RV6XX, + THERMAL_TYPE_RV770, + THERMAL_TYPE_EVERGREEN, +}; + struct radeon_voltage { enum radeon_voltage_type type; /* gpio voltage */ @@ -766,6 +776,9 @@ struct radeon_pm { enum radeon_pm_profile_type profile; int profile_index; struct radeon_pm_profile profiles[PM_PROFILE_MAX]; + /* internal thermal controller on rv6xx+ */ + enum radeon_int_thermal_type int_thermal_type; + struct device *int_hwmon_dev; }; @@ -902,6 +915,7 @@ struct r600_asic { unsigned tiling_nbanks; unsigned tiling_npipes; unsigned tiling_group_size; + unsigned tile_config; struct r100_gpu_lockup lockup; }; @@ -926,6 +940,7 @@ struct rv770_asic { unsigned tiling_nbanks; unsigned tiling_npipes; unsigned tiling_group_size; + unsigned tile_config; struct r100_gpu_lockup lockup; }; @@ -951,6 +966,7 @@ struct evergreen_asic { unsigned tiling_nbanks; unsigned tiling_npipes; unsigned tiling_group_size; + unsigned tile_config; }; union radeon_asic_config { @@ -1033,6 +1049,9 @@ struct radeon_device { uint32_t pcie_reg_mask; radeon_rreg_t pciep_rreg; radeon_wreg_t pciep_wreg; + /* io port */ + void __iomem *rio_mem; + resource_size_t rio_mem_size; struct radeon_clock clock; struct radeon_mc mc; struct radeon_gart gart; @@ -1069,6 +1088,7 @@ struct radeon_device { struct mutex vram_mutex; /* audio stuff */ + bool audio_enabled; struct timer_list audio_timer; int audio_channels; int audio_rate; @@ -1078,6 +1098,8 @@ struct radeon_device { bool powered_down; struct notifier_block acpi_nb; + /* only one userspace can use Hyperz features at a time */ + struct drm_file *hyperz_filp; }; int radeon_device_init(struct radeon_device *rdev, @@ -1114,6 +1136,26 @@ static inline void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32 } } +static inline u32 r100_io_rreg(struct radeon_device *rdev, u32 reg) +{ + if (reg < rdev->rio_mem_size) + return ioread32(rdev->rio_mem + reg); + else { + iowrite32(reg, rdev->rio_mem + RADEON_MM_INDEX); + return ioread32(rdev->rio_mem + RADEON_MM_DATA); + } +} + +static inline void r100_io_wreg(struct radeon_device *rdev, u32 reg, u32 v) +{ + if (reg < rdev->rio_mem_size) + iowrite32(v, rdev->rio_mem + reg); + else { + iowrite32(reg, rdev->rio_mem + RADEON_MM_INDEX); + iowrite32(v, rdev->rio_mem + RADEON_MM_DATA); + } +} + /* * Cast helper */ @@ -1152,6 +1194,8 @@ static inline void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32 WREG32_PLL(reg, tmp_); \ } while (0) #define DREG32_SYS(sqf, rdev, reg) seq_printf((sqf), #reg " : 0x%08X\n", r100_mm_rreg((rdev), (reg))) +#define RREG32_IO(reg) r100_io_rreg(rdev, (reg)) +#define WREG32_IO(reg, v) r100_io_wreg(rdev, (reg), (v)) /* * Indirect registers accessor @@ -1415,6 +1459,13 @@ extern void r700_cp_fini(struct radeon_device *rdev); extern void evergreen_disable_interrupt_state(struct radeon_device *rdev); extern int evergreen_irq_set(struct radeon_device *rdev); +/* radeon_acpi.c */ +#if defined(CONFIG_ACPI) +extern int radeon_acpi_init(struct radeon_device *rdev); +#else +static inline int radeon_acpi_init(struct radeon_device *rdev) { return 0; } +#endif + /* evergreen */ struct evergreen_mc_save { u32 vga_control[6]; diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c new file mode 100644 index 00000000000..3f6636bb2d7 --- /dev/null +++ b/drivers/gpu/drm/radeon/radeon_acpi.c @@ -0,0 +1,67 @@ +#include <linux/pci.h> +#include <linux/acpi.h> +#include <linux/slab.h> +#include <acpi/acpi_drivers.h> +#include <acpi/acpi_bus.h> + +#include "drmP.h" +#include "drm.h" +#include "drm_sarea.h" +#include "drm_crtc_helper.h" +#include "radeon.h" + +#include <linux/vga_switcheroo.h> + +/* Call the ATIF method + * + * Note: currently we discard the output + */ +static int radeon_atif_call(acpi_handle handle) +{ + acpi_status status; + union acpi_object atif_arg_elements[2]; + struct acpi_object_list atif_arg; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL}; + + atif_arg.count = 2; + atif_arg.pointer = &atif_arg_elements[0]; + + atif_arg_elements[0].type = ACPI_TYPE_INTEGER; + atif_arg_elements[0].integer.value = 0; + atif_arg_elements[1].type = ACPI_TYPE_INTEGER; + atif_arg_elements[1].integer.value = 0; + + status = acpi_evaluate_object(handle, "ATIF", &atif_arg, &buffer); + + /* Fail only if calling the method fails and ATIF is supported */ + if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { + printk(KERN_DEBUG "failed to evaluate ATIF got %s\n", acpi_format_exception(status)); + kfree(buffer.pointer); + return 1; + } + + kfree(buffer.pointer); + return 0; +} + +/* Call all ACPI methods here */ +int radeon_acpi_init(struct radeon_device *rdev) +{ + acpi_handle handle; + int ret; + + /* No need to proceed if we're sure that ATIF is not supported */ + if (!ASIC_IS_AVIVO(rdev) || !rdev->bios) + return 0; + + /* Get the device handle */ + handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev); + + /* Call the ATIF method */ + ret = radeon_atif_call(handle); + if (ret) + return ret; + + return 0; +} + diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index c0bbaa64157..a5aff755f0d 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -113,6 +113,7 @@ void r100_wb_fini(struct radeon_device *rdev); int r100_wb_init(struct radeon_device *rdev); int r100_cp_reset(struct radeon_device *rdev); void r100_vga_render_disable(struct radeon_device *rdev); +void r100_restore_sanity(struct radeon_device *rdev); int r100_cs_track_check_pkt3_indx_buffer(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt, struct radeon_bo *robj); diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 10673ae59cf..3bc2bcdf530 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -723,7 +723,7 @@ bool radeon_get_atom_connector_info_from_supported_devices_table(struct } if (i == ATOM_DEVICE_CV_INDEX) { - DRM_DEBUG("Skipping Component Video\n"); + DRM_DEBUG_KMS("Skipping Component Video\n"); continue; } @@ -1032,21 +1032,18 @@ bool radeon_atombios_sideport_present(struct radeon_device *rdev) u8 frev, crev; u16 data_offset; + /* sideport is AMD only */ + if (rdev->family == CHIP_RS600) + return false; + if (atom_parse_data_header(mode_info->atom_context, index, NULL, &frev, &crev, &data_offset)) { igp_info = (union igp_info *)(mode_info->atom_context->bios + data_offset); switch (crev) { case 1: - /* AMD IGPS */ - if ((rdev->family == CHIP_RS690) || - (rdev->family == CHIP_RS740)) { - if (igp_info->info.ulBootUpMemoryClock) - return true; - } else { - if (igp_info->info.ucMemoryType & 0xf0) - return true; - } + if (igp_info->info.ulBootUpMemoryClock) + return true; break; case 2: if (igp_info->info_2.ucMemoryType & 0x0f) @@ -1095,7 +1092,7 @@ bool radeon_atombios_get_tmds_info(struct radeon_encoder *encoder, (tmds_info->asMiscInfo[i]. ucPLL_VoltageSwing & 0xf) << 16; - DRM_DEBUG("TMDS PLL From ATOMBIOS %u %x\n", + DRM_DEBUG_KMS("TMDS PLL From ATOMBIOS %u %x\n", tmds->tmds_pll[i].freq, tmds->tmds_pll[i].value); @@ -1789,14 +1786,22 @@ void radeon_atombios_get_power_modes(struct radeon_device *rdev) } /* add the i2c bus for thermal/fan chip */ - /* no support for internal controller yet */ if (controller->ucType > 0) { - if ((controller->ucType == ATOM_PP_THERMALCONTROLLER_RV6xx) || - (controller->ucType == ATOM_PP_THERMALCONTROLLER_RV770) || - (controller->ucType == ATOM_PP_THERMALCONTROLLER_EVERGREEN)) { + if (controller->ucType == ATOM_PP_THERMALCONTROLLER_RV6xx) { + DRM_INFO("Internal thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_RV6XX; + } else if (controller->ucType == ATOM_PP_THERMALCONTROLLER_RV770) { + DRM_INFO("Internal thermal controller %s fan control\n", + (controller->ucFanParameters & + ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_RV770; + } else if (controller->ucType == ATOM_PP_THERMALCONTROLLER_EVERGREEN) { DRM_INFO("Internal thermal controller %s fan control\n", (controller->ucFanParameters & ATOM_PP_FANPARAMETERS_NOFAN) ? "without" : "with"); + rdev->pm.int_thermal_type = THERMAL_TYPE_EVERGREEN; } else if ((controller->ucType == ATOM_PP_THERMALCONTROLLER_EXTERNAL_GPIO) || (controller->ucType == @@ -2179,11 +2184,11 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_TV1_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_TV1_SUPPORT)) { if (connected) { - DRM_DEBUG("TV1 connected\n"); + DRM_DEBUG_KMS("TV1 connected\n"); bios_3_scratch |= ATOM_S3_TV1_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_TV1; } else { - DRM_DEBUG("TV1 disconnected\n"); + DRM_DEBUG_KMS("TV1 disconnected\n"); bios_0_scratch &= ~ATOM_S0_TV1_MASK; bios_3_scratch &= ~ATOM_S3_TV1_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_TV1; @@ -2192,11 +2197,11 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_CV_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_CV_SUPPORT)) { if (connected) { - DRM_DEBUG("CV connected\n"); + DRM_DEBUG_KMS("CV connected\n"); bios_3_scratch |= ATOM_S3_CV_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_CV; } else { - DRM_DEBUG("CV disconnected\n"); + DRM_DEBUG_KMS("CV disconnected\n"); bios_0_scratch &= ~ATOM_S0_CV_MASK; bios_3_scratch &= ~ATOM_S3_CV_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_CV; @@ -2205,12 +2210,12 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_LCD1_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_LCD1_SUPPORT)) { if (connected) { - DRM_DEBUG("LCD1 connected\n"); + DRM_DEBUG_KMS("LCD1 connected\n"); bios_0_scratch |= ATOM_S0_LCD1; bios_3_scratch |= ATOM_S3_LCD1_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_LCD1; } else { - DRM_DEBUG("LCD1 disconnected\n"); + DRM_DEBUG_KMS("LCD1 disconnected\n"); bios_0_scratch &= ~ATOM_S0_LCD1; bios_3_scratch &= ~ATOM_S3_LCD1_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_LCD1; @@ -2219,12 +2224,12 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_CRT1_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_CRT1_SUPPORT)) { if (connected) { - DRM_DEBUG("CRT1 connected\n"); + DRM_DEBUG_KMS("CRT1 connected\n"); bios_0_scratch |= ATOM_S0_CRT1_COLOR; bios_3_scratch |= ATOM_S3_CRT1_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_CRT1; } else { - DRM_DEBUG("CRT1 disconnected\n"); + DRM_DEBUG_KMS("CRT1 disconnected\n"); bios_0_scratch &= ~ATOM_S0_CRT1_MASK; bios_3_scratch &= ~ATOM_S3_CRT1_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_CRT1; @@ -2233,12 +2238,12 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_CRT2_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_CRT2_SUPPORT)) { if (connected) { - DRM_DEBUG("CRT2 connected\n"); + DRM_DEBUG_KMS("CRT2 connected\n"); bios_0_scratch |= ATOM_S0_CRT2_COLOR; bios_3_scratch |= ATOM_S3_CRT2_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_CRT2; } else { - DRM_DEBUG("CRT2 disconnected\n"); + DRM_DEBUG_KMS("CRT2 disconnected\n"); bios_0_scratch &= ~ATOM_S0_CRT2_MASK; bios_3_scratch &= ~ATOM_S3_CRT2_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_CRT2; @@ -2247,12 +2252,12 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_DFP1_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_DFP1_SUPPORT)) { if (connected) { - DRM_DEBUG("DFP1 connected\n"); + DRM_DEBUG_KMS("DFP1 connected\n"); bios_0_scratch |= ATOM_S0_DFP1; bios_3_scratch |= ATOM_S3_DFP1_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_DFP1; } else { - DRM_DEBUG("DFP1 disconnected\n"); + DRM_DEBUG_KMS("DFP1 disconnected\n"); bios_0_scratch &= ~ATOM_S0_DFP1; bios_3_scratch &= ~ATOM_S3_DFP1_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_DFP1; @@ -2261,12 +2266,12 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_DFP2_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_DFP2_SUPPORT)) { if (connected) { - DRM_DEBUG("DFP2 connected\n"); + DRM_DEBUG_KMS("DFP2 connected\n"); bios_0_scratch |= ATOM_S0_DFP2; bios_3_scratch |= ATOM_S3_DFP2_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_DFP2; } else { - DRM_DEBUG("DFP2 disconnected\n"); + DRM_DEBUG_KMS("DFP2 disconnected\n"); bios_0_scratch &= ~ATOM_S0_DFP2; bios_3_scratch &= ~ATOM_S3_DFP2_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_DFP2; @@ -2275,12 +2280,12 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_DFP3_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_DFP3_SUPPORT)) { if (connected) { - DRM_DEBUG("DFP3 connected\n"); + DRM_DEBUG_KMS("DFP3 connected\n"); bios_0_scratch |= ATOM_S0_DFP3; bios_3_scratch |= ATOM_S3_DFP3_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_DFP3; } else { - DRM_DEBUG("DFP3 disconnected\n"); + DRM_DEBUG_KMS("DFP3 disconnected\n"); bios_0_scratch &= ~ATOM_S0_DFP3; bios_3_scratch &= ~ATOM_S3_DFP3_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_DFP3; @@ -2289,12 +2294,12 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_DFP4_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_DFP4_SUPPORT)) { if (connected) { - DRM_DEBUG("DFP4 connected\n"); + DRM_DEBUG_KMS("DFP4 connected\n"); bios_0_scratch |= ATOM_S0_DFP4; bios_3_scratch |= ATOM_S3_DFP4_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_DFP4; } else { - DRM_DEBUG("DFP4 disconnected\n"); + DRM_DEBUG_KMS("DFP4 disconnected\n"); bios_0_scratch &= ~ATOM_S0_DFP4; bios_3_scratch &= ~ATOM_S3_DFP4_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_DFP4; @@ -2303,12 +2308,12 @@ radeon_atombios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_DFP5_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_DFP5_SUPPORT)) { if (connected) { - DRM_DEBUG("DFP5 connected\n"); + DRM_DEBUG_KMS("DFP5 connected\n"); bios_0_scratch |= ATOM_S0_DFP5; bios_3_scratch |= ATOM_S3_DFP5_ACTIVE; bios_6_scratch |= ATOM_S6_ACC_REQ_DFP5; } else { - DRM_DEBUG("DFP5 disconnected\n"); + DRM_DEBUG_KMS("DFP5 disconnected\n"); bios_0_scratch &= ~ATOM_S0_DFP5; bios_3_scratch &= ~ATOM_S3_DFP5_ACTIVE; bios_6_scratch &= ~ATOM_S6_ACC_REQ_DFP5; diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index 2c921373999..654787ec43f 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -53,7 +53,7 @@ static bool igp_read_bios_from_vram(struct radeon_device *rdev) return false; rdev->bios = NULL; - vram_base = drm_get_resource_start(rdev->ddev, 0); + vram_base = pci_resource_start(rdev->pdev, 0); bios = ioremap(vram_base, size); if (!bios) { return false; diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index 2417d7b06fd..5e1474cde4b 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -693,6 +693,10 @@ bool radeon_combios_sideport_present(struct radeon_device *rdev) struct drm_device *dev = rdev->ddev; u16 igp_info; + /* sideport is AMD only */ + if (rdev->family == CHIP_RS400) + return false; + igp_info = combios_get_table_offset(dev, COMBIOS_INTEGRATED_SYSTEM_INFO_TABLE); if (igp_info) { @@ -1205,7 +1209,7 @@ bool radeon_legacy_get_tmds_info_from_combios(struct radeon_encoder *encoder, RBIOS32(tmds_info + i * 10 + 0x08); tmds->tmds_pll[i].freq = RBIOS16(tmds_info + i * 10 + 0x10); - DRM_DEBUG("TMDS PLL From COMBIOS %u %x\n", + DRM_DEBUG_KMS("TMDS PLL From COMBIOS %u %x\n", tmds->tmds_pll[i].freq, tmds->tmds_pll[i].value); } @@ -1223,7 +1227,7 @@ bool radeon_legacy_get_tmds_info_from_combios(struct radeon_encoder *encoder, stride += 10; else stride += 6; - DRM_DEBUG("TMDS PLL From COMBIOS %u %x\n", + DRM_DEBUG_KMS("TMDS PLL From COMBIOS %u %x\n", tmds->tmds_pll[i].freq, tmds->tmds_pll[i].value); } @@ -2208,7 +2212,7 @@ bool radeon_get_legacy_connector_info_from_bios(struct drm_device *dev) uint16_t tmds_info = combios_get_table_offset(dev, COMBIOS_DFP_INFO_TABLE); if (tmds_info) { - DRM_DEBUG("Found DFP table, assuming DVI connector\n"); + DRM_DEBUG_KMS("Found DFP table, assuming DVI connector\n"); radeon_add_legacy_encoder(dev, radeon_get_encoder_id(dev, @@ -2234,7 +2238,7 @@ bool radeon_get_legacy_connector_info_from_bios(struct drm_device *dev) } else { uint16_t crt_info = combios_get_table_offset(dev, COMBIOS_CRT_INFO_TABLE); - DRM_DEBUG("Found CRT table, assuming VGA connector\n"); + DRM_DEBUG_KMS("Found CRT table, assuming VGA connector\n"); if (crt_info) { radeon_add_legacy_encoder(dev, radeon_get_encoder_id(dev, @@ -2251,7 +2255,7 @@ bool radeon_get_legacy_connector_info_from_bios(struct drm_device *dev) CONNECTOR_OBJECT_ID_VGA, &hpd); } else { - DRM_DEBUG("No connector info found\n"); + DRM_DEBUG_KMS("No connector info found\n"); return false; } } @@ -2340,7 +2344,7 @@ bool radeon_get_legacy_connector_info_from_bios(struct drm_device *dev) ddc_i2c.valid = false; break; } - DRM_DEBUG("LCD DDC Info Table found!\n"); + DRM_DEBUG_KMS("LCD DDC Info Table found!\n"); } else ddc_i2c.valid = false; @@ -2941,9 +2945,8 @@ static void combios_write_ram_size(struct drm_device *dev) if (rev < 3) { mem_cntl = RBIOS32(offset + 1); mem_size = RBIOS16(offset + 5); - if (((rdev->flags & RADEON_FAMILY_MASK) < CHIP_R200) && - ((dev->pdev->device != 0x515e) - && (dev->pdev->device != 0x5969))) + if ((rdev->family < CHIP_R200) && + !ASIC_IS_RN50(rdev)) WREG32(RADEON_MEM_CNTL, mem_cntl); } } @@ -2954,10 +2957,8 @@ static void combios_write_ram_size(struct drm_device *dev) if (offset) { rev = RBIOS8(offset - 1); if (rev < 1) { - if (((rdev->flags & RADEON_FAMILY_MASK) < - CHIP_R200) - && ((dev->pdev->device != 0x515e) - && (dev->pdev->device != 0x5969))) { + if ((rdev->family < CHIP_R200) + && !ASIC_IS_RN50(rdev)) { int ram = 0; int mem_addr_mapping = 0; @@ -3121,14 +3122,14 @@ radeon_combios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_TV1_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_TV1_SUPPORT)) { if (connected) { - DRM_DEBUG("TV1 connected\n"); + DRM_DEBUG_KMS("TV1 connected\n"); /* fix me */ bios_4_scratch |= RADEON_TV1_ATTACHED_SVIDEO; /*save->bios_4_scratch |= RADEON_TV1_ATTACHED_COMP; */ bios_5_scratch |= RADEON_TV1_ON; bios_5_scratch |= RADEON_ACC_REQ_TV1; } else { - DRM_DEBUG("TV1 disconnected\n"); + DRM_DEBUG_KMS("TV1 disconnected\n"); bios_4_scratch &= ~RADEON_TV1_ATTACHED_MASK; bios_5_scratch &= ~RADEON_TV1_ON; bios_5_scratch &= ~RADEON_ACC_REQ_TV1; @@ -3137,12 +3138,12 @@ radeon_combios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_LCD1_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_LCD1_SUPPORT)) { if (connected) { - DRM_DEBUG("LCD1 connected\n"); + DRM_DEBUG_KMS("LCD1 connected\n"); bios_4_scratch |= RADEON_LCD1_ATTACHED; bios_5_scratch |= RADEON_LCD1_ON; bios_5_scratch |= RADEON_ACC_REQ_LCD1; } else { - DRM_DEBUG("LCD1 disconnected\n"); + DRM_DEBUG_KMS("LCD1 disconnected\n"); bios_4_scratch &= ~RADEON_LCD1_ATTACHED; bios_5_scratch &= ~RADEON_LCD1_ON; bios_5_scratch &= ~RADEON_ACC_REQ_LCD1; @@ -3151,12 +3152,12 @@ radeon_combios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_CRT1_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_CRT1_SUPPORT)) { if (connected) { - DRM_DEBUG("CRT1 connected\n"); + DRM_DEBUG_KMS("CRT1 connected\n"); bios_4_scratch |= RADEON_CRT1_ATTACHED_COLOR; bios_5_scratch |= RADEON_CRT1_ON; bios_5_scratch |= RADEON_ACC_REQ_CRT1; } else { - DRM_DEBUG("CRT1 disconnected\n"); + DRM_DEBUG_KMS("CRT1 disconnected\n"); bios_4_scratch &= ~RADEON_CRT1_ATTACHED_MASK; bios_5_scratch &= ~RADEON_CRT1_ON; bios_5_scratch &= ~RADEON_ACC_REQ_CRT1; @@ -3165,12 +3166,12 @@ radeon_combios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_CRT2_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_CRT2_SUPPORT)) { if (connected) { - DRM_DEBUG("CRT2 connected\n"); + DRM_DEBUG_KMS("CRT2 connected\n"); bios_4_scratch |= RADEON_CRT2_ATTACHED_COLOR; bios_5_scratch |= RADEON_CRT2_ON; bios_5_scratch |= RADEON_ACC_REQ_CRT2; } else { - DRM_DEBUG("CRT2 disconnected\n"); + DRM_DEBUG_KMS("CRT2 disconnected\n"); bios_4_scratch &= ~RADEON_CRT2_ATTACHED_MASK; bios_5_scratch &= ~RADEON_CRT2_ON; bios_5_scratch &= ~RADEON_ACC_REQ_CRT2; @@ -3179,12 +3180,12 @@ radeon_combios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_DFP1_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_DFP1_SUPPORT)) { if (connected) { - DRM_DEBUG("DFP1 connected\n"); + DRM_DEBUG_KMS("DFP1 connected\n"); bios_4_scratch |= RADEON_DFP1_ATTACHED; bios_5_scratch |= RADEON_DFP1_ON; bios_5_scratch |= RADEON_ACC_REQ_DFP1; } else { - DRM_DEBUG("DFP1 disconnected\n"); + DRM_DEBUG_KMS("DFP1 disconnected\n"); bios_4_scratch &= ~RADEON_DFP1_ATTACHED; bios_5_scratch &= ~RADEON_DFP1_ON; bios_5_scratch &= ~RADEON_ACC_REQ_DFP1; @@ -3193,12 +3194,12 @@ radeon_combios_connected_scratch_regs(struct drm_connector *connector, if ((radeon_encoder->devices & ATOM_DEVICE_DFP2_SUPPORT) && (radeon_connector->devices & ATOM_DEVICE_DFP2_SUPPORT)) { if (connected) { - DRM_DEBUG("DFP2 connected\n"); + DRM_DEBUG_KMS("DFP2 connected\n"); bios_4_scratch |= RADEON_DFP2_ATTACHED; bios_5_scratch |= RADEON_DFP2_ON; bios_5_scratch |= RADEON_ACC_REQ_DFP2; } else { - DRM_DEBUG("DFP2 disconnected\n"); + DRM_DEBUG_KMS("DFP2 disconnected\n"); bios_4_scratch &= ~RADEON_DFP2_ATTACHED; bios_5_scratch &= ~RADEON_DFP2_ON; bios_5_scratch &= ~RADEON_ACC_REQ_DFP2; diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index adccbc2c202..2395c8600cf 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -214,7 +214,7 @@ static struct drm_display_mode *radeon_fp_native_mode(struct drm_encoder *encode mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER; drm_mode_set_name(mode); - DRM_DEBUG("Adding native panel mode %s\n", mode->name); + DRM_DEBUG_KMS("Adding native panel mode %s\n", mode->name); } else if (native_mode->hdisplay != 0 && native_mode->vdisplay != 0) { /* mac laptops without an edid */ @@ -226,7 +226,7 @@ static struct drm_display_mode *radeon_fp_native_mode(struct drm_encoder *encode */ mode = drm_cvt_mode(dev, native_mode->hdisplay, native_mode->vdisplay, 60, true, false, false); mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER; - DRM_DEBUG("Adding cvt approximation of native panel mode %s\n", mode->name); + DRM_DEBUG_KMS("Adding cvt approximation of native panel mode %s\n", mode->name); } return mode; } @@ -312,6 +312,20 @@ int radeon_connector_set_property(struct drm_connector *connector, struct drm_pr } } + if (property == rdev->mode_info.underscan_property) { + /* need to find digital encoder on connector */ + encoder = radeon_find_encoder(connector, DRM_MODE_ENCODER_TMDS); + if (!encoder) + return 0; + + radeon_encoder = to_radeon_encoder(encoder); + + if (radeon_encoder->underscan_type != val) { + radeon_encoder->underscan_type = val; + radeon_property_change_mode(&radeon_encoder->base); + } + } + if (property == rdev->mode_info.tv_std_property) { encoder = radeon_find_encoder(connector, DRM_MODE_ENCODER_TVDAC); if (!encoder) { @@ -522,7 +536,7 @@ static int radeon_lvds_set_property(struct drm_connector *connector, struct radeon_encoder *radeon_encoder; enum radeon_rmx_type rmx_type; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); if (property != dev->mode_config.scaling_mode_property) return 0; @@ -1082,6 +1096,8 @@ radeon_add_atom_connector(struct drm_device *dev, drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.load_detect_property, 1); + /* no HPD on analog connectors */ + radeon_connector->hpd.hpd = RADEON_HPD_NONE; connector->polled = DRM_CONNECTOR_POLL_CONNECT; break; case DRM_MODE_CONNECTOR_DVIA: @@ -1096,6 +1112,8 @@ radeon_add_atom_connector(struct drm_device *dev, drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.load_detect_property, 1); + /* no HPD on analog connectors */ + radeon_connector->hpd.hpd = RADEON_HPD_NONE; break; case DRM_MODE_CONNECTOR_DVII: case DRM_MODE_CONNECTOR_DVID: @@ -1116,6 +1134,10 @@ radeon_add_atom_connector(struct drm_device *dev, drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.coherent_mode_property, 1); + if (ASIC_IS_AVIVO(rdev)) + drm_connector_attach_property(&radeon_connector->base, + rdev->mode_info.underscan_property, + UNDERSCAN_AUTO); if (connector_type == DRM_MODE_CONNECTOR_DVII) { radeon_connector->dac_load_detect = true; drm_connector_attach_property(&radeon_connector->base, @@ -1141,6 +1163,10 @@ radeon_add_atom_connector(struct drm_device *dev, drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.coherent_mode_property, 1); + if (ASIC_IS_AVIVO(rdev)) + drm_connector_attach_property(&radeon_connector->base, + rdev->mode_info.underscan_property, + UNDERSCAN_AUTO); subpixel_order = SubPixelHorizontalRGB; break; case DRM_MODE_CONNECTOR_DisplayPort: @@ -1172,6 +1198,10 @@ radeon_add_atom_connector(struct drm_device *dev, drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.coherent_mode_property, 1); + if (ASIC_IS_AVIVO(rdev)) + drm_connector_attach_property(&radeon_connector->base, + rdev->mode_info.underscan_property, + UNDERSCAN_AUTO); break; case DRM_MODE_CONNECTOR_SVIDEO: case DRM_MODE_CONNECTOR_Composite: @@ -1186,6 +1216,8 @@ radeon_add_atom_connector(struct drm_device *dev, drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.tv_std_property, radeon_atombios_get_tv_info(rdev)); + /* no HPD on analog connectors */ + radeon_connector->hpd.hpd = RADEON_HPD_NONE; } break; case DRM_MODE_CONNECTOR_LVDS: @@ -1209,7 +1241,7 @@ radeon_add_atom_connector(struct drm_device *dev, break; } - if (hpd->hpd == RADEON_HPD_NONE) { + if (radeon_connector->hpd.hpd == RADEON_HPD_NONE) { if (i2c_bus->valid) connector->polled = DRM_CONNECTOR_POLL_CONNECT; } else @@ -1276,6 +1308,8 @@ radeon_add_legacy_connector(struct drm_device *dev, drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.load_detect_property, 1); + /* no HPD on analog connectors */ + radeon_connector->hpd.hpd = RADEON_HPD_NONE; connector->polled = DRM_CONNECTOR_POLL_CONNECT; break; case DRM_MODE_CONNECTOR_DVIA: @@ -1290,6 +1324,8 @@ radeon_add_legacy_connector(struct drm_device *dev, drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.load_detect_property, 1); + /* no HPD on analog connectors */ + radeon_connector->hpd.hpd = RADEON_HPD_NONE; break; case DRM_MODE_CONNECTOR_DVII: case DRM_MODE_CONNECTOR_DVID: @@ -1328,6 +1364,8 @@ radeon_add_legacy_connector(struct drm_device *dev, drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.tv_std_property, radeon_combios_get_tv_info(rdev)); + /* no HPD on analog connectors */ + radeon_connector->hpd.hpd = RADEON_HPD_NONE; } break; case DRM_MODE_CONNECTOR_LVDS: @@ -1345,7 +1383,7 @@ radeon_add_legacy_connector(struct drm_device *dev, break; } - if (hpd->hpd == RADEON_HPD_NONE) { + if (radeon_connector->hpd.hpd == RADEON_HPD_NONE) { if (i2c_bus->valid) connector->polled = DRM_CONNECTOR_POLL_CONNECT; } else diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c index 2f042a3c0e6..eb6b9eed734 100644 --- a/drivers/gpu/drm/radeon/radeon_cp.c +++ b/drivers/gpu/drm/radeon/radeon_cp.c @@ -2120,8 +2120,8 @@ int radeon_driver_load(struct drm_device *dev, unsigned long flags) else dev_priv->flags |= RADEON_IS_PCI; - ret = drm_addmap(dev, drm_get_resource_start(dev, 2), - drm_get_resource_len(dev, 2), _DRM_REGISTERS, + ret = drm_addmap(dev, pci_resource_start(dev->pdev, 2), + pci_resource_len(dev->pdev, 2), _DRM_REGISTERS, _DRM_READ_ONLY | _DRM_DRIVER, &dev_priv->mmio); if (ret != 0) return ret; @@ -2194,9 +2194,9 @@ int radeon_driver_firstopen(struct drm_device *dev) dev_priv->gart_info.table_size = RADEON_PCIGART_TABLE_SIZE; - dev_priv->fb_aper_offset = drm_get_resource_start(dev, 0); + dev_priv->fb_aper_offset = pci_resource_start(dev->pdev, 0); ret = drm_addmap(dev, dev_priv->fb_aper_offset, - drm_get_resource_len(dev, 0), _DRM_FRAME_BUFFER, + pci_resource_len(dev->pdev, 0), _DRM_FRAME_BUFFER, _DRM_WRITE_COMBINING, &map); if (ret != 0) return ret; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index dd279da9054..a64811a9451 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -415,6 +415,22 @@ static uint32_t cail_reg_read(struct card_info *info, uint32_t reg) return r; } +static void cail_ioreg_write(struct card_info *info, uint32_t reg, uint32_t val) +{ + struct radeon_device *rdev = info->dev->dev_private; + + WREG32_IO(reg*4, val); +} + +static uint32_t cail_ioreg_read(struct card_info *info, uint32_t reg) +{ + struct radeon_device *rdev = info->dev->dev_private; + uint32_t r; + + r = RREG32_IO(reg*4); + return r; +} + int radeon_atombios_init(struct radeon_device *rdev) { struct card_info *atom_card_info = @@ -427,6 +443,15 @@ int radeon_atombios_init(struct radeon_device *rdev) atom_card_info->dev = rdev->ddev; atom_card_info->reg_read = cail_reg_read; atom_card_info->reg_write = cail_reg_write; + /* needed for iio ops */ + if (rdev->rio_mem) { + atom_card_info->ioreg_read = cail_ioreg_read; + atom_card_info->ioreg_write = cail_ioreg_write; + } else { + DRM_ERROR("Unable to find PCI I/O BAR; using MMIO for ATOM IIO\n"); + atom_card_info->ioreg_read = cail_reg_read; + atom_card_info->ioreg_write = cail_reg_write; + } atom_card_info->mc_read = cail_mc_read; atom_card_info->mc_write = cail_mc_write; atom_card_info->pll_read = cail_pll_read; @@ -573,7 +598,7 @@ int radeon_device_init(struct radeon_device *rdev, struct pci_dev *pdev, uint32_t flags) { - int r; + int r, i; int dma_bits; rdev->shutdown = false; @@ -650,8 +675,8 @@ int radeon_device_init(struct radeon_device *rdev, /* Registers mapping */ /* TODO: block userspace mapping of io register */ - rdev->rmmio_base = drm_get_resource_start(rdev->ddev, 2); - rdev->rmmio_size = drm_get_resource_len(rdev->ddev, 2); + rdev->rmmio_base = pci_resource_start(rdev->pdev, 2); + rdev->rmmio_size = pci_resource_len(rdev->pdev, 2); rdev->rmmio = ioremap(rdev->rmmio_base, rdev->rmmio_size); if (rdev->rmmio == NULL) { return -ENOMEM; @@ -659,6 +684,17 @@ int radeon_device_init(struct radeon_device *rdev, DRM_INFO("register mmio base: 0x%08X\n", (uint32_t)rdev->rmmio_base); DRM_INFO("register mmio size: %u\n", (unsigned)rdev->rmmio_size); + /* io port mapping */ + for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { + if (pci_resource_flags(rdev->pdev, i) & IORESOURCE_IO) { + rdev->rio_mem_size = pci_resource_len(rdev->pdev, i); + rdev->rio_mem = pci_iomap(rdev->pdev, i, rdev->rio_mem_size); + break; + } + } + if (rdev->rio_mem == NULL) + DRM_ERROR("Unable to find PCI I/O BAR\n"); + /* if we have > 1 VGA cards, then disable the radeon VGA resources */ /* this will fail for cards that aren't VGA class devices, just * ignore it */ @@ -701,6 +737,9 @@ void radeon_device_fini(struct radeon_device *rdev) destroy_workqueue(rdev->wq); vga_switcheroo_unregister_client(rdev->pdev); vga_client_register(rdev->pdev, NULL, NULL, NULL); + if (rdev->rio_mem) + pci_iounmap(rdev->pdev, rdev->rio_mem); + rdev->rio_mem = NULL; iounmap(rdev->rmmio); rdev->rmmio = NULL; } diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 8154cdf796e..74dac9635d7 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -42,7 +42,7 @@ static void avivo_crtc_load_lut(struct drm_crtc *crtc) struct radeon_device *rdev = dev->dev_private; int i; - DRM_DEBUG("%d\n", radeon_crtc->crtc_id); + DRM_DEBUG_KMS("%d\n", radeon_crtc->crtc_id); WREG32(AVIVO_DC_LUTA_CONTROL + radeon_crtc->crtc_offset, 0); WREG32(AVIVO_DC_LUTA_BLACK_OFFSET_BLUE + radeon_crtc->crtc_offset, 0); @@ -75,7 +75,7 @@ static void evergreen_crtc_load_lut(struct drm_crtc *crtc) struct radeon_device *rdev = dev->dev_private; int i; - DRM_DEBUG("%d\n", radeon_crtc->crtc_id); + DRM_DEBUG_KMS("%d\n", radeon_crtc->crtc_id); WREG32(EVERGREEN_DC_LUT_CONTROL + radeon_crtc->crtc_offset, 0); WREG32(EVERGREEN_DC_LUT_BLACK_OFFSET_BLUE + radeon_crtc->crtc_offset, 0); @@ -469,7 +469,7 @@ static void radeon_compute_pll_legacy(struct radeon_pll *pll, uint32_t post_div; u32 pll_out_min, pll_out_max; - DRM_DEBUG("PLL freq %llu %u %u\n", freq, pll->min_ref_div, pll->max_ref_div); + DRM_DEBUG_KMS("PLL freq %llu %u %u\n", freq, pll->min_ref_div, pll->max_ref_div); freq = freq * 1000; if (pll->flags & RADEON_PLL_IS_LCD) { @@ -558,15 +558,17 @@ static void radeon_compute_pll_legacy(struct radeon_pll *pll, current_freq = radeon_div(tmp, ref_div * post_div); if (pll->flags & RADEON_PLL_PREFER_CLOSEST_LOWER) { - error = freq - current_freq; - error = error < 0 ? 0xffffffff : error; + if (freq < current_freq) + error = 0xffffffff; + else + error = freq - current_freq; } else error = abs(current_freq - freq); vco_diff = abs(vco - best_vco); if ((best_vco == 0 && error < best_error) || (best_vco != 0 && - (error < best_error - 100 || + ((best_error > 100 && error < best_error - 100) || (abs(error - best_error) < 100 && vco_diff < best_vco_diff)))) { best_post_div = post_div; best_ref_div = ref_div; @@ -803,7 +805,7 @@ done: *ref_div_p = ref_div; *post_div_p = post_div; - DRM_DEBUG("%u %d.%d, %d, %d\n", *dot_clock_p, *fb_div_p, *frac_fb_div_p, *ref_div_p, *post_div_p); + DRM_DEBUG_KMS("%u %d.%d, %d, %d\n", *dot_clock_p, *fb_div_p, *frac_fb_div_p, *ref_div_p, *post_div_p); } void radeon_compute_pll(struct radeon_pll *pll, @@ -919,6 +921,12 @@ static struct drm_prop_enum_list radeon_tv_std_enum_list[] = { TV_STD_SECAM, "secam" }, }; +static struct drm_prop_enum_list radeon_underscan_enum_list[] = +{ { UNDERSCAN_OFF, "off" }, + { UNDERSCAN_ON, "on" }, + { UNDERSCAN_AUTO, "auto" }, +}; + static int radeon_modeset_create_props(struct radeon_device *rdev) { int i, sz; @@ -972,6 +980,18 @@ static int radeon_modeset_create_props(struct radeon_device *rdev) radeon_tv_std_enum_list[i].name); } + sz = ARRAY_SIZE(radeon_underscan_enum_list); + rdev->mode_info.underscan_property = + drm_property_create(rdev->ddev, + DRM_MODE_PROP_ENUM, + "underscan", sz); + for (i = 0; i < sz; i++) { + drm_property_add_enum(rdev->mode_info.underscan_property, + i, + radeon_underscan_enum_list[i].type, + radeon_underscan_enum_list[i].name); + } + return 0; } @@ -1067,15 +1087,26 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc, struct drm_display_mode *adjusted_mode) { struct drm_device *dev = crtc->dev; + struct radeon_device *rdev = dev->dev_private; struct drm_encoder *encoder; struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); struct radeon_encoder *radeon_encoder; + struct drm_connector *connector; + struct radeon_connector *radeon_connector; bool first = true; + u32 src_v = 1, dst_v = 1; + u32 src_h = 1, dst_h = 1; + + radeon_crtc->h_border = 0; + radeon_crtc->v_border = 0; list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { - radeon_encoder = to_radeon_encoder(encoder); if (encoder->crtc != crtc) continue; + radeon_encoder = to_radeon_encoder(encoder); + connector = radeon_get_connector_for_encoder(encoder); + radeon_connector = to_radeon_connector(connector); + if (first) { /* set scaling */ if (radeon_encoder->rmx_type == RMX_OFF) @@ -1085,31 +1116,49 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc, radeon_crtc->rmx_type = radeon_encoder->rmx_type; else radeon_crtc->rmx_type = RMX_OFF; + src_v = crtc->mode.vdisplay; + dst_v = radeon_crtc->native_mode.vdisplay; + src_h = crtc->mode.hdisplay; + dst_h = radeon_crtc->native_mode.vdisplay; /* copy native mode */ memcpy(&radeon_crtc->native_mode, &radeon_encoder->native_mode, sizeof(struct drm_display_mode)); + + /* fix up for overscan on hdmi */ + if (ASIC_IS_AVIVO(rdev) && + ((radeon_encoder->underscan_type == UNDERSCAN_ON) || + ((radeon_encoder->underscan_type == UNDERSCAN_AUTO) && + drm_detect_hdmi_monitor(radeon_connector->edid)))) { + radeon_crtc->h_border = (mode->hdisplay >> 5) + 16; + radeon_crtc->v_border = (mode->vdisplay >> 5) + 16; + radeon_crtc->rmx_type = RMX_FULL; + src_v = crtc->mode.vdisplay; + dst_v = crtc->mode.vdisplay - (radeon_crtc->v_border * 2); + src_h = crtc->mode.hdisplay; + dst_h = crtc->mode.hdisplay - (radeon_crtc->h_border * 2); + } first = false; } else { if (radeon_crtc->rmx_type != radeon_encoder->rmx_type) { /* WARNING: Right now this can't happen but * in the future we need to check that scaling - * are consistent accross different encoder + * are consistent across different encoder * (ie all encoder can work with the same * scaling). */ - DRM_ERROR("Scaling not consistent accross encoder.\n"); + DRM_ERROR("Scaling not consistent across encoder.\n"); return false; } } } if (radeon_crtc->rmx_type != RMX_OFF) { fixed20_12 a, b; - a.full = dfixed_const(crtc->mode.vdisplay); - b.full = dfixed_const(radeon_crtc->native_mode.hdisplay); + a.full = dfixed_const(src_v); + b.full = dfixed_const(dst_v); radeon_crtc->vsc.full = dfixed_div(a, b); - a.full = dfixed_const(crtc->mode.hdisplay); - b.full = dfixed_const(radeon_crtc->native_mode.vdisplay); + a.full = dfixed_const(src_h); + b.full = dfixed_const(dst_h); radeon_crtc->hsc.full = dfixed_div(a, b); } else { radeon_crtc->vsc.full = dfixed_const(1); diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index e166fe4d7c3..795403b0e2c 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -46,9 +46,10 @@ * - 2.3.0 - add MSPOS + 3D texture + r500 VAP regs * - 2.4.0 - add crtc id query * - 2.5.0 - add get accel 2 to work around ddx breakage for evergreen + * - 2.6.0 - add tiling config query (r6xx+), add initial HiZ support (r300->r500) */ #define KMS_DRIVER_MAJOR 2 -#define KMS_DRIVER_MINOR 5 +#define KMS_DRIVER_MINOR 6 #define KMS_DRIVER_PATCHLEVEL 0 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags); int radeon_driver_unload_kms(struct drm_device *dev); @@ -238,7 +239,7 @@ static struct drm_driver kms_driver; static int __devinit radeon_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - return drm_get_dev(pdev, ent, &kms_driver); + return drm_get_pci_dev(pdev, ent, &kms_driver); } static void diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c index e0b30b264c2..263c8098d7d 100644 --- a/drivers/gpu/drm/radeon/radeon_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_encoders.c @@ -205,14 +205,14 @@ void radeon_encoder_set_active_device(struct drm_encoder *encoder) if (connector->encoder == encoder) { struct radeon_connector *radeon_connector = to_radeon_connector(connector); radeon_encoder->active_device = radeon_encoder->devices & radeon_connector->devices; - DRM_DEBUG("setting active device to %08x from %08x %08x for encoder %d\n", + DRM_DEBUG_KMS("setting active device to %08x from %08x %08x for encoder %d\n", radeon_encoder->active_device, radeon_encoder->devices, radeon_connector->devices, encoder->encoder_type); } } } -static struct drm_connector * +struct drm_connector * radeon_get_connector_for_encoder(struct drm_encoder *encoder) { struct drm_device *dev = encoder->dev; @@ -1021,7 +1021,7 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode) memset(&args, 0, sizeof(args)); - DRM_DEBUG("encoder dpms %d to mode %d, devices %08x, active_devices %08x\n", + DRM_DEBUG_KMS("encoder dpms %d to mode %d, devices %08x, active_devices %08x\n", radeon_encoder->encoder_id, mode, radeon_encoder->devices, radeon_encoder->active_device); switch (radeon_encoder->encoder_id) { @@ -1484,7 +1484,7 @@ radeon_atom_dac_detect(struct drm_encoder *encoder, struct drm_connector *connec uint32_t bios_0_scratch; if (!atombios_dac_load_detect(encoder, connector)) { - DRM_DEBUG("detect returned false \n"); + DRM_DEBUG_KMS("detect returned false \n"); return connector_status_unknown; } @@ -1493,7 +1493,7 @@ radeon_atom_dac_detect(struct drm_encoder *encoder, struct drm_connector *connec else bios_0_scratch = RREG32(RADEON_BIOS_0_SCRATCH); - DRM_DEBUG("Bios 0 scratch %x %08x\n", bios_0_scratch, radeon_encoder->devices); + DRM_DEBUG_KMS("Bios 0 scratch %x %08x\n", bios_0_scratch, radeon_encoder->devices); if (radeon_connector->devices & ATOM_DEVICE_CRT1_SUPPORT) { if (bios_0_scratch & ATOM_S0_CRT1_MASK) return connector_status_connected; @@ -1694,6 +1694,7 @@ radeon_add_atom_encoder(struct drm_device *dev, uint32_t encoder_id, uint32_t su radeon_encoder->encoder_id = encoder_id; radeon_encoder->devices = supported_device; radeon_encoder->rmx_type = RMX_OFF; + radeon_encoder->underscan_type = UNDERSCAN_OFF; switch (radeon_encoder->encoder_id) { case ENCODER_OBJECT_ID_INTERNAL_LVDS: @@ -1707,6 +1708,8 @@ radeon_add_atom_encoder(struct drm_device *dev, uint32_t encoder_id, uint32_t su } else { drm_encoder_init(dev, encoder, &radeon_atom_enc_funcs, DRM_MODE_ENCODER_TMDS); radeon_encoder->enc_priv = radeon_atombios_set_dig_info(radeon_encoder); + if (ASIC_IS_AVIVO(rdev)) + radeon_encoder->underscan_type = UNDERSCAN_AUTO; } drm_encoder_helper_add(encoder, &radeon_atom_dig_helper_funcs); break; @@ -1736,6 +1739,8 @@ radeon_add_atom_encoder(struct drm_device *dev, uint32_t encoder_id, uint32_t su } else { drm_encoder_init(dev, encoder, &radeon_atom_enc_funcs, DRM_MODE_ENCODER_TMDS); radeon_encoder->enc_priv = radeon_atombios_set_dig_info(radeon_encoder); + if (ASIC_IS_AVIVO(rdev)) + radeon_encoder->underscan_type = UNDERSCAN_AUTO; } drm_encoder_helper_add(encoder, &radeon_atom_dig_helper_funcs); break; diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index ab389f89fa8..ddcd3b13f15 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -49,7 +49,7 @@ int radeon_driver_unload_kms(struct drm_device *dev) int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags) { struct radeon_device *rdev; - int r; + int r, acpi_status; rdev = kzalloc(sizeof(struct radeon_device), GFP_KERNEL); if (rdev == NULL) { @@ -77,6 +77,12 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags) dev_err(&dev->pdev->dev, "Fatal error during GPU init\n"); goto out; } + + /* Call ACPI methods */ + acpi_status = radeon_acpi_init(rdev); + if (acpi_status) + dev_dbg(&dev->pdev->dev, "Error during ACPI methods call\n"); + /* Again modeset_init should fail only on fatal error * otherwise it should provide enough functionalities * for shadowfb to run @@ -135,15 +141,36 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) } } if (!found) { - DRM_DEBUG("unknown crtc id %d\n", value); + DRM_DEBUG_KMS("unknown crtc id %d\n", value); return -EINVAL; } break; case RADEON_INFO_ACCEL_WORKING2: value = rdev->accel_working; break; + case RADEON_INFO_TILING_CONFIG: + if (rdev->family >= CHIP_CEDAR) + value = rdev->config.evergreen.tile_config; + else if (rdev->family >= CHIP_RV770) + value = rdev->config.rv770.tile_config; + else if (rdev->family >= CHIP_R600) + value = rdev->config.r600.tile_config; + else { + DRM_DEBUG_KMS("tiling config is r6xx+ only!\n"); + return -EINVAL; + } + case RADEON_INFO_WANT_HYPERZ: + mutex_lock(&dev->struct_mutex); + if (rdev->hyperz_filp) + value = 0; + else { + rdev->hyperz_filp = filp; + value = 1; + } + mutex_unlock(&dev->struct_mutex); + break; default: - DRM_DEBUG("Invalid request %d\n", info->request); + DRM_DEBUG_KMS("Invalid request %d\n", info->request); return -EINVAL; } if (DRM_COPY_TO_USER(value_ptr, &value, sizeof(uint32_t))) { @@ -181,9 +208,11 @@ void radeon_driver_postclose_kms(struct drm_device *dev, void radeon_driver_preclose_kms(struct drm_device *dev, struct drm_file *file_priv) { + struct radeon_device *rdev = dev->dev_private; + if (rdev->hyperz_filp == file_priv) + rdev->hyperz_filp = NULL; } - /* * VBlank related functions. */ diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c index e1e5255396a..989df519a1e 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c @@ -362,10 +362,10 @@ int radeon_crtc_set_base(struct drm_crtc *crtc, int x, int y, uint32_t gen_cntl_reg, gen_cntl_val; int r; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); /* no fb bound */ if (!crtc->fb) { - DRM_DEBUG("No FB bound\n"); + DRM_DEBUG_KMS("No FB bound\n"); return 0; } @@ -528,7 +528,7 @@ static bool radeon_set_crtc_timing(struct drm_crtc *crtc, struct drm_display_mod uint32_t crtc_v_sync_strt_wid; bool is_tv = false; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { if (encoder->crtc == crtc) { struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); @@ -757,7 +757,7 @@ static void radeon_set_pll(struct drm_crtc *crtc, struct drm_display_mode *mode) } } - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); if (!use_bios_divs) { radeon_compute_pll(pll, mode->clock, @@ -772,7 +772,7 @@ static void radeon_set_pll(struct drm_crtc *crtc, struct drm_display_mode *mode) if (!post_div->divider) post_div = &post_divs[0]; - DRM_DEBUG("dc=%u, fd=%d, rd=%d, pd=%d\n", + DRM_DEBUG_KMS("dc=%u, fd=%d, rd=%d, pd=%d\n", (unsigned)freq, feedback_div, reference_div, @@ -841,12 +841,12 @@ static void radeon_set_pll(struct drm_crtc *crtc, struct drm_display_mode *mode) | RADEON_P2PLL_SLEEP | RADEON_P2PLL_ATOMIC_UPDATE_EN)); - DRM_DEBUG("Wrote2: 0x%08x 0x%08x 0x%08x (0x%08x)\n", + DRM_DEBUG_KMS("Wrote2: 0x%08x 0x%08x 0x%08x (0x%08x)\n", (unsigned)pll_ref_div, (unsigned)pll_fb_post_div, (unsigned)htotal_cntl, RREG32_PLL(RADEON_P2PLL_CNTL)); - DRM_DEBUG("Wrote2: rd=%u, fd=%u, pd=%u\n", + DRM_DEBUG_KMS("Wrote2: rd=%u, fd=%u, pd=%u\n", (unsigned)pll_ref_div & RADEON_P2PLL_REF_DIV_MASK, (unsigned)pll_fb_post_div & RADEON_P2PLL_FB0_DIV_MASK, (unsigned)((pll_fb_post_div & @@ -947,12 +947,12 @@ static void radeon_set_pll(struct drm_crtc *crtc, struct drm_display_mode *mode) | RADEON_PPLL_ATOMIC_UPDATE_EN | RADEON_PPLL_VGA_ATOMIC_UPDATE_EN)); - DRM_DEBUG("Wrote: 0x%08x 0x%08x 0x%08x (0x%08x)\n", + DRM_DEBUG_KMS("Wrote: 0x%08x 0x%08x 0x%08x (0x%08x)\n", pll_ref_div, pll_fb_post_div, (unsigned)htotal_cntl, RREG32_PLL(RADEON_PPLL_CNTL)); - DRM_DEBUG("Wrote: rd=%d, fd=%d, pd=%d\n", + DRM_DEBUG_KMS("Wrote: rd=%d, fd=%d, pd=%d\n", pll_ref_div & RADEON_PPLL_REF_DIV_MASK, pll_fb_post_div & RADEON_PPLL_FB3_DIV_MASK, (pll_fb_post_div & RADEON_PPLL_POST3_DIV_MASK) >> 16); diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c index 5688a0cf6bb..b8149cbc0c7 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c @@ -47,7 +47,7 @@ static void radeon_legacy_lvds_dpms(struct drm_encoder *encoder, int mode) uint32_t lvds_gen_cntl, lvds_pll_cntl, pixclks_cntl, disp_pwr_man; int panel_pwr_delay = 2000; bool is_mac = false; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); if (radeon_encoder->enc_priv) { if (rdev->is_atom_bios) { @@ -151,7 +151,7 @@ static void radeon_legacy_lvds_mode_set(struct drm_encoder *encoder, struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); uint32_t lvds_pll_cntl, lvds_gen_cntl, lvds_ss_gen_cntl; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); lvds_pll_cntl = RREG32(RADEON_LVDS_PLL_CNTL); lvds_pll_cntl &= ~RADEON_LVDS_PLL_EN; @@ -167,7 +167,7 @@ static void radeon_legacy_lvds_mode_set(struct drm_encoder *encoder, } else { struct radeon_encoder_lvds *lvds = (struct radeon_encoder_lvds *)radeon_encoder->enc_priv; if (lvds) { - DRM_DEBUG("bios LVDS_GEN_CNTL: 0x%x\n", lvds->lvds_gen_cntl); + DRM_DEBUG_KMS("bios LVDS_GEN_CNTL: 0x%x\n", lvds->lvds_gen_cntl); lvds_gen_cntl = lvds->lvds_gen_cntl; lvds_ss_gen_cntl &= ~((0xf << RADEON_LVDS_PWRSEQ_DELAY1_SHIFT) | (0xf << RADEON_LVDS_PWRSEQ_DELAY2_SHIFT)); @@ -250,7 +250,7 @@ static void radeon_legacy_primary_dac_dpms(struct drm_encoder *encoder, int mode uint32_t dac_cntl = RREG32(RADEON_DAC_CNTL); uint32_t dac_macro_cntl = RREG32(RADEON_DAC_MACRO_CNTL); - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); switch (mode) { case DRM_MODE_DPMS_ON: @@ -315,7 +315,7 @@ static void radeon_legacy_primary_dac_mode_set(struct drm_encoder *encoder, struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); uint32_t disp_output_cntl, dac_cntl, dac2_cntl, dac_macro_cntl; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); if (radeon_crtc->crtc_id == 0) { if (rdev->family == CHIP_R200 || ASIC_IS_R300(rdev)) { @@ -446,7 +446,7 @@ static void radeon_legacy_tmds_int_dpms(struct drm_encoder *encoder, int mode) struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; uint32_t fp_gen_cntl = RREG32(RADEON_FP_GEN_CNTL); - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); switch (mode) { case DRM_MODE_DPMS_ON: @@ -502,7 +502,7 @@ static void radeon_legacy_tmds_int_mode_set(struct drm_encoder *encoder, uint32_t tmp, tmds_pll_cntl, tmds_transmitter_cntl, fp_gen_cntl; int i; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); tmp = tmds_pll_cntl = RREG32(RADEON_TMDS_PLL_CNTL); tmp &= 0xfffff; @@ -610,7 +610,7 @@ static void radeon_legacy_tmds_ext_dpms(struct drm_encoder *encoder, int mode) struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; uint32_t fp2_gen_cntl = RREG32(RADEON_FP2_GEN_CNTL); - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); switch (mode) { case DRM_MODE_DPMS_ON: @@ -666,7 +666,7 @@ static void radeon_legacy_tmds_ext_mode_set(struct drm_encoder *encoder, struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); uint32_t fp2_gen_cntl; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); if (rdev->is_atom_bios) { radeon_encoder->pixel_clock = adjusted_mode->clock; @@ -760,7 +760,7 @@ static void radeon_legacy_tv_dac_dpms(struct drm_encoder *encoder, int mode) uint32_t fp2_gen_cntl = 0, crtc2_gen_cntl = 0, tv_dac_cntl = 0; uint32_t tv_master_cntl = 0; bool is_tv; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); is_tv = radeon_encoder->active_device & ATOM_DEVICE_TV_SUPPORT ? true : false; @@ -878,7 +878,7 @@ static void radeon_legacy_tv_dac_mode_set(struct drm_encoder *encoder, uint32_t disp_hw_debug = 0, fp2_gen_cntl = 0, disp_tv_out_cntl = 0; bool is_tv = false; - DRM_DEBUG("\n"); + DRM_DEBUG_KMS("\n"); is_tv = radeon_encoder->active_device & ATOM_DEVICE_TV_SUPPORT ? true : false; @@ -1075,10 +1075,10 @@ static bool r300_legacy_tv_detect(struct drm_encoder *encoder, tmp = RREG32(RADEON_TV_DAC_CNTL); if ((tmp & RADEON_TV_DAC_GDACDET) != 0) { found = true; - DRM_DEBUG("S-video TV connection detected\n"); + DRM_DEBUG_KMS("S-video TV connection detected\n"); } else if ((tmp & RADEON_TV_DAC_BDACDET) != 0) { found = true; - DRM_DEBUG("Composite TV connection detected\n"); + DRM_DEBUG_KMS("Composite TV connection detected\n"); } WREG32(RADEON_TV_DAC_CNTL, tv_dac_cntl); @@ -1141,10 +1141,10 @@ static bool radeon_legacy_tv_detect(struct drm_encoder *encoder, tmp = RREG32(RADEON_TV_DAC_CNTL); if (tmp & RADEON_TV_DAC_GDACDET) { found = true; - DRM_DEBUG("S-video TV connection detected\n"); + DRM_DEBUG_KMS("S-video TV connection detected\n"); } else if ((tmp & RADEON_TV_DAC_BDACDET) != 0) { found = true; - DRM_DEBUG("Composite TV connection detected\n"); + DRM_DEBUG_KMS("Composite TV connection detected\n"); } WREG32(RADEON_TV_PRE_DAC_MUX_CNTL, tv_pre_dac_mux_cntl); diff --git a/drivers/gpu/drm/radeon/radeon_legacy_tv.c b/drivers/gpu/drm/radeon/radeon_legacy_tv.c index 03204039774..c7b6cb428d0 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_tv.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_tv.c @@ -496,7 +496,7 @@ static bool radeon_legacy_tv_init_restarts(struct drm_encoder *encoder) restart -= v_offset + h_offset; - DRM_DEBUG("compute_restarts: def = %u h = %d v = %d, p1 = %04x, p2 = %04x, restart = %d\n", + DRM_DEBUG_KMS("compute_restarts: def = %u h = %d v = %d, p1 = %04x, p2 = %04x, restart = %d\n", const_ptr->def_restart, tv_dac->h_pos, tv_dac->v_pos, p1, p2, restart); tv_dac->tv.hrestart = restart % h_total; @@ -505,7 +505,7 @@ static bool radeon_legacy_tv_init_restarts(struct drm_encoder *encoder) restart /= v_total; tv_dac->tv.frestart = restart % f_total; - DRM_DEBUG("compute_restart: F/H/V=%u,%u,%u\n", + DRM_DEBUG_KMS("compute_restart: F/H/V=%u,%u,%u\n", (unsigned)tv_dac->tv.frestart, (unsigned)tv_dac->tv.vrestart, (unsigned)tv_dac->tv.hrestart); @@ -523,7 +523,7 @@ static bool radeon_legacy_tv_init_restarts(struct drm_encoder *encoder) tv_dac->tv.timing_cntl = (tv_dac->tv.timing_cntl & ~RADEON_H_INC_MASK) | ((u32)h_inc << RADEON_H_INC_SHIFT); - DRM_DEBUG("compute_restart: h_size = %d h_inc = %d\n", tv_dac->h_size, h_inc); + DRM_DEBUG_KMS("compute_restart: h_size = %d h_inc = %d\n", tv_dac->h_size, h_inc); return h_changed; } diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index 95696aa57ac..71aea4037e9 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -66,6 +66,12 @@ enum radeon_tv_std { TV_STD_PAL_N, }; +enum radeon_underscan_type { + UNDERSCAN_OFF, + UNDERSCAN_ON, + UNDERSCAN_AUTO, +}; + enum radeon_hpd_id { RADEON_HPD_1 = 0, RADEON_HPD_2, @@ -226,10 +232,12 @@ struct radeon_mode_info { struct drm_property *coherent_mode_property; /* DAC enable load detect */ struct drm_property *load_detect_property; - /* TV standard load detect */ + /* TV standard */ struct drm_property *tv_std_property; /* legacy TMDS PLL detect */ struct drm_property *tmds_pll_property; + /* underscan */ + struct drm_property *underscan_property; /* hardcoded DFP edid from BIOS */ struct edid *bios_hardcoded_edid; @@ -266,6 +274,8 @@ struct radeon_crtc { uint32_t legacy_display_base_addr; uint32_t legacy_cursor_offset; enum radeon_rmx_type rmx_type; + u8 h_border; + u8 v_border; fixed20_12 vsc; fixed20_12 hsc; struct drm_display_mode native_mode; @@ -354,6 +364,7 @@ struct radeon_encoder { uint32_t flags; uint32_t pixel_clock; enum radeon_rmx_type rmx_type; + enum radeon_underscan_type underscan_type; struct drm_display_mode native_mode; void *enc_priv; int audio_polling_active; @@ -392,7 +403,7 @@ struct radeon_connector { uint32_t connector_id; uint32_t devices; struct radeon_i2c_chan *ddc_bus; - /* some systems have a an hdmi and vga port with a shared ddc line */ + /* some systems have an hdmi and vga port with a shared ddc line */ bool shared_ddc; bool use_digital; /* we need to mind the EDID between detect @@ -414,6 +425,9 @@ radeon_combios_get_tv_info(struct radeon_device *rdev); extern enum radeon_tv_std radeon_atombios_get_tv_info(struct radeon_device *rdev); +extern struct drm_connector * +radeon_get_connector_for_encoder(struct drm_encoder *encoder); + extern void radeon_connector_hotplug(struct drm_connector *connector); extern bool radeon_dp_needs_link_train(struct radeon_connector *radeon_connector); extern int radeon_dp_mode_valid_helper(struct radeon_connector *radeon_connector, diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index d5b9373ce06..0afd1e62347 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -110,6 +110,7 @@ int radeon_bo_create(struct radeon_device *rdev, struct drm_gem_object *gobj, bo->surface_reg = -1; INIT_LIST_HEAD(&bo->list); +retry: radeon_ttm_placement_from_domain(bo, domain); /* Kernel allocation are uninterruptible */ mutex_lock(&rdev->vram_mutex); @@ -118,10 +119,15 @@ int radeon_bo_create(struct radeon_device *rdev, struct drm_gem_object *gobj, &radeon_ttm_bo_destroy); mutex_unlock(&rdev->vram_mutex); if (unlikely(r != 0)) { - if (r != -ERESTARTSYS) + if (r != -ERESTARTSYS) { + if (domain == RADEON_GEM_DOMAIN_VRAM) { + domain |= RADEON_GEM_DOMAIN_GTT; + goto retry; + } dev_err(rdev->dev, "object_init failed for (%lu, 0x%08X)\n", size, domain); + } return r; } *bo_ptr = bo; @@ -321,6 +327,7 @@ int radeon_bo_list_validate(struct list_head *head) { struct radeon_bo_list *lobj; struct radeon_bo *bo; + u32 domain; int r; list_for_each_entry(lobj, head, list) { @@ -333,17 +340,19 @@ int radeon_bo_list_validate(struct list_head *head) list_for_each_entry(lobj, head, list) { bo = lobj->bo; if (!bo->pin_count) { - if (lobj->wdomain) { - radeon_ttm_placement_from_domain(bo, - lobj->wdomain); - } else { - radeon_ttm_placement_from_domain(bo, - lobj->rdomain); - } + domain = lobj->wdomain ? lobj->wdomain : lobj->rdomain; + + retry: + radeon_ttm_placement_from_domain(bo, domain); r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false, false); - if (unlikely(r)) + if (unlikely(r)) { + if (r != -ERESTARTSYS && domain == RADEON_GEM_DOMAIN_VRAM) { + domain |= RADEON_GEM_DOMAIN_GTT; + goto retry; + } return r; + } } lobj->gpu_offset = radeon_bo_gpu_offset(bo); lobj->tiling_flags = bo->tiling_flags; diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 3fa6984d989..95f8b3a3c43 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -27,6 +27,8 @@ #include <linux/acpi.h> #endif #include <linux/power_supply.h> +#include <linux/hwmon.h> +#include <linux/hwmon-sysfs.h> #define RADEON_IDLE_LOOP_MS 100 #define RADEON_RECLOCK_DELAY_MS 200 @@ -60,9 +62,9 @@ static int radeon_acpi_event(struct notifier_block *nb, if (strcmp(entry->device_class, ACPI_AC_CLASS) == 0) { if (power_supply_is_system_supplied() > 0) - DRM_DEBUG("pm: AC\n"); + DRM_DEBUG_DRIVER("pm: AC\n"); else - DRM_DEBUG("pm: DC\n"); + DRM_DEBUG_DRIVER("pm: DC\n"); if (rdev->pm.pm_method == PM_METHOD_PROFILE) { if (rdev->pm.profile == PM_PROFILE_AUTO) { @@ -196,7 +198,7 @@ static void radeon_set_power_state(struct radeon_device *rdev) radeon_set_engine_clock(rdev, sclk); radeon_pm_debug_check_in_vbl(rdev, true); rdev->pm.current_sclk = sclk; - DRM_DEBUG("Setting: e: %d\n", sclk); + DRM_DEBUG_DRIVER("Setting: e: %d\n", sclk); } /* set memory clock */ @@ -205,7 +207,7 @@ static void radeon_set_power_state(struct radeon_device *rdev) radeon_set_memory_clock(rdev, mclk); radeon_pm_debug_check_in_vbl(rdev, true); rdev->pm.current_mclk = mclk; - DRM_DEBUG("Setting: m: %d\n", mclk); + DRM_DEBUG_DRIVER("Setting: m: %d\n", mclk); } if (misc_after) @@ -217,7 +219,7 @@ static void radeon_set_power_state(struct radeon_device *rdev) rdev->pm.current_power_state_index = rdev->pm.requested_power_state_index; rdev->pm.current_clock_mode_index = rdev->pm.requested_clock_mode_index; } else - DRM_DEBUG("pm: GUI not idle!!!\n"); + DRM_DEBUG_DRIVER("pm: GUI not idle!!!\n"); } static void radeon_pm_set_clocks(struct radeon_device *rdev) @@ -292,27 +294,27 @@ static void radeon_pm_print_states(struct radeon_device *rdev) struct radeon_power_state *power_state; struct radeon_pm_clock_info *clock_info; - DRM_DEBUG("%d Power State(s)\n", rdev->pm.num_power_states); + DRM_DEBUG_DRIVER("%d Power State(s)\n", rdev->pm.num_power_states); for (i = 0; i < rdev->pm.num_power_states; i++) { power_state = &rdev->pm.power_state[i]; - DRM_DEBUG("State %d: %s\n", i, + DRM_DEBUG_DRIVER("State %d: %s\n", i, radeon_pm_state_type_name[power_state->type]); if (i == rdev->pm.default_power_state_index) - DRM_DEBUG("\tDefault"); + DRM_DEBUG_DRIVER("\tDefault"); if ((rdev->flags & RADEON_IS_PCIE) && !(rdev->flags & RADEON_IS_IGP)) - DRM_DEBUG("\t%d PCIE Lanes\n", power_state->pcie_lanes); + DRM_DEBUG_DRIVER("\t%d PCIE Lanes\n", power_state->pcie_lanes); if (power_state->flags & RADEON_PM_STATE_SINGLE_DISPLAY_ONLY) - DRM_DEBUG("\tSingle display only\n"); - DRM_DEBUG("\t%d Clock Mode(s)\n", power_state->num_clock_modes); + DRM_DEBUG_DRIVER("\tSingle display only\n"); + DRM_DEBUG_DRIVER("\t%d Clock Mode(s)\n", power_state->num_clock_modes); for (j = 0; j < power_state->num_clock_modes; j++) { clock_info = &(power_state->clock_info[j]); if (rdev->flags & RADEON_IS_IGP) - DRM_DEBUG("\t\t%d e: %d%s\n", + DRM_DEBUG_DRIVER("\t\t%d e: %d%s\n", j, clock_info->sclk * 10, clock_info->flags & RADEON_PM_MODE_NO_DISPLAY ? "\tNo display only" : ""); else - DRM_DEBUG("\t\t%d e: %d\tm: %d\tv: %d%s\n", + DRM_DEBUG_DRIVER("\t\t%d e: %d\tm: %d\tv: %d%s\n", j, clock_info->sclk * 10, clock_info->mclk * 10, @@ -424,6 +426,82 @@ fail: static DEVICE_ATTR(power_profile, S_IRUGO | S_IWUSR, radeon_get_pm_profile, radeon_set_pm_profile); static DEVICE_ATTR(power_method, S_IRUGO | S_IWUSR, radeon_get_pm_method, radeon_set_pm_method); +static ssize_t radeon_hwmon_show_temp(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev)); + struct radeon_device *rdev = ddev->dev_private; + u32 temp; + + switch (rdev->pm.int_thermal_type) { + case THERMAL_TYPE_RV6XX: + temp = rv6xx_get_temp(rdev); + break; + case THERMAL_TYPE_RV770: + temp = rv770_get_temp(rdev); + break; + case THERMAL_TYPE_EVERGREEN: + temp = evergreen_get_temp(rdev); + break; + default: + temp = 0; + break; + } + + return snprintf(buf, PAGE_SIZE, "%d\n", temp); +} + +static ssize_t radeon_hwmon_show_name(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "radeon\n"); +} + +static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, radeon_hwmon_show_temp, NULL, 0); +static SENSOR_DEVICE_ATTR(name, S_IRUGO, radeon_hwmon_show_name, NULL, 0); + +static struct attribute *hwmon_attributes[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + &sensor_dev_attr_name.dev_attr.attr, + NULL +}; + +static const struct attribute_group hwmon_attrgroup = { + .attrs = hwmon_attributes, +}; + +static void radeon_hwmon_init(struct radeon_device *rdev) +{ + int err; + + rdev->pm.int_hwmon_dev = NULL; + + switch (rdev->pm.int_thermal_type) { + case THERMAL_TYPE_RV6XX: + case THERMAL_TYPE_RV770: + case THERMAL_TYPE_EVERGREEN: + rdev->pm.int_hwmon_dev = hwmon_device_register(rdev->dev); + dev_set_drvdata(rdev->pm.int_hwmon_dev, rdev->ddev); + err = sysfs_create_group(&rdev->pm.int_hwmon_dev->kobj, + &hwmon_attrgroup); + if (err) + DRM_ERROR("Unable to create hwmon sysfs file: %d\n", err); + break; + default: + break; + } +} + +static void radeon_hwmon_fini(struct radeon_device *rdev) +{ + if (rdev->pm.int_hwmon_dev) { + sysfs_remove_group(&rdev->pm.int_hwmon_dev->kobj, &hwmon_attrgroup); + hwmon_device_unregister(rdev->pm.int_hwmon_dev); + } +} + void radeon_pm_suspend(struct radeon_device *rdev) { bool flush_wq = false; @@ -471,6 +549,7 @@ int radeon_pm_init(struct radeon_device *rdev) rdev->pm.dynpm_can_downclock = true; rdev->pm.current_sclk = rdev->clock.default_sclk; rdev->pm.current_mclk = rdev->clock.default_mclk; + rdev->pm.int_thermal_type = THERMAL_TYPE_NONE; if (rdev->bios) { if (rdev->is_atom_bios) @@ -481,6 +560,8 @@ int radeon_pm_init(struct radeon_device *rdev) radeon_pm_init_profile(rdev); } + /* set up the internal thermal sensor if applicable */ + radeon_hwmon_init(rdev); if (rdev->pm.num_power_states > 1) { /* where's the best place to put these? */ ret = device_create_file(rdev->dev, &dev_attr_power_profile); @@ -536,6 +617,7 @@ void radeon_pm_fini(struct radeon_device *rdev) #endif } + radeon_hwmon_fini(rdev); if (rdev->pm.i2c_bus) radeon_i2c_destroy(rdev->pm.i2c_bus); } @@ -576,7 +658,7 @@ void radeon_pm_compute_clocks(struct radeon_device *rdev) radeon_pm_get_dynpm_state(rdev); radeon_pm_set_clocks(rdev); - DRM_DEBUG("radeon: dynamic power management deactivated\n"); + DRM_DEBUG_DRIVER("radeon: dynamic power management deactivated\n"); } } else if (rdev->pm.active_crtc_count == 1) { /* TODO: Increase clocks if needed for current mode */ @@ -593,7 +675,7 @@ void radeon_pm_compute_clocks(struct radeon_device *rdev) rdev->pm.dynpm_state = DYNPM_STATE_ACTIVE; queue_delayed_work(rdev->wq, &rdev->pm.dynpm_idle_work, msecs_to_jiffies(RADEON_IDLE_LOOP_MS)); - DRM_DEBUG("radeon: dynamic power management activated\n"); + DRM_DEBUG_DRIVER("radeon: dynamic power management activated\n"); } } else { /* count == 0 */ if (rdev->pm.dynpm_state != DYNPM_STATE_MINIMUM) { @@ -689,7 +771,7 @@ static bool radeon_pm_debug_check_in_vbl(struct radeon_device *rdev, bool finish bool in_vbl = radeon_pm_in_vbl(rdev); if (in_vbl == false) - DRM_DEBUG("not in vbl for pm change %08x at %s\n", stat_crtc, + DRM_DEBUG_DRIVER("not in vbl for pm change %08x at %s\n", stat_crtc, finish ? "exit" : "entry"); return in_vbl; } diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index e9918d88f5b..84c53e41a88 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -59,28 +59,28 @@ static struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev) /* * Global memory. */ -static int radeon_ttm_mem_global_init(struct ttm_global_reference *ref) +static int radeon_ttm_mem_global_init(struct drm_global_reference *ref) { return ttm_mem_global_init(ref->object); } -static void radeon_ttm_mem_global_release(struct ttm_global_reference *ref) +static void radeon_ttm_mem_global_release(struct drm_global_reference *ref) { ttm_mem_global_release(ref->object); } static int radeon_ttm_global_init(struct radeon_device *rdev) { - struct ttm_global_reference *global_ref; + struct drm_global_reference *global_ref; int r; rdev->mman.mem_global_referenced = false; global_ref = &rdev->mman.mem_global_ref; - global_ref->global_type = TTM_GLOBAL_TTM_MEM; + global_ref->global_type = DRM_GLOBAL_TTM_MEM; global_ref->size = sizeof(struct ttm_mem_global); global_ref->init = &radeon_ttm_mem_global_init; global_ref->release = &radeon_ttm_mem_global_release; - r = ttm_global_item_ref(global_ref); + r = drm_global_item_ref(global_ref); if (r != 0) { DRM_ERROR("Failed setting up TTM memory accounting " "subsystem.\n"); @@ -90,14 +90,14 @@ static int radeon_ttm_global_init(struct radeon_device *rdev) rdev->mman.bo_global_ref.mem_glob = rdev->mman.mem_global_ref.object; global_ref = &rdev->mman.bo_global_ref.ref; - global_ref->global_type = TTM_GLOBAL_TTM_BO; + global_ref->global_type = DRM_GLOBAL_TTM_BO; global_ref->size = sizeof(struct ttm_bo_global); global_ref->init = &ttm_bo_global_init; global_ref->release = &ttm_bo_global_release; - r = ttm_global_item_ref(global_ref); + r = drm_global_item_ref(global_ref); if (r != 0) { DRM_ERROR("Failed setting up TTM BO subsystem.\n"); - ttm_global_item_unref(&rdev->mman.mem_global_ref); + drm_global_item_unref(&rdev->mman.mem_global_ref); return r; } @@ -108,8 +108,8 @@ static int radeon_ttm_global_init(struct radeon_device *rdev) static void radeon_ttm_global_fini(struct radeon_device *rdev) { if (rdev->mman.mem_global_referenced) { - ttm_global_item_unref(&rdev->mman.bo_global_ref.ref); - ttm_global_item_unref(&rdev->mman.mem_global_ref); + drm_global_item_unref(&rdev->mman.bo_global_ref.ref); + drm_global_item_unref(&rdev->mman.mem_global_ref); rdev->mman.mem_global_referenced = false; } } diff --git a/drivers/gpu/drm/radeon/reg_srcs/r300 b/drivers/gpu/drm/radeon/reg_srcs/r300 index 1e97b2d129f..b506ec1cab4 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/r300 +++ b/drivers/gpu/drm/radeon/reg_srcs/r300 @@ -187,7 +187,6 @@ r300 0x4f60 0x4364 RS_INST_13 0x4368 RS_INST_14 0x436C RS_INST_15 -0x43A4 SC_HYPERZ_EN 0x43A8 SC_EDGERULE 0x43B0 SC_CLIP_0_A 0x43B4 SC_CLIP_0_B @@ -716,16 +715,4 @@ r300 0x4f60 0x4F08 ZB_STENCILREFMASK 0x4F14 ZB_ZTOP 0x4F18 ZB_ZCACHE_CTLSTAT -0x4F1C ZB_BW_CNTL -0x4F28 ZB_DEPTHCLEARVALUE -0x4F30 ZB_ZMASK_OFFSET -0x4F34 ZB_ZMASK_PITCH -0x4F38 ZB_ZMASK_WRINDEX -0x4F3C ZB_ZMASK_DWORD -0x4F40 ZB_ZMASK_RDINDEX -0x4F44 ZB_HIZ_OFFSET -0x4F48 ZB_HIZ_WRINDEX -0x4F4C ZB_HIZ_DWORD -0x4F50 ZB_HIZ_RDINDEX -0x4F54 ZB_HIZ_PITCH 0x4F58 ZB_ZPASS_DATA diff --git a/drivers/gpu/drm/radeon/reg_srcs/r420 b/drivers/gpu/drm/radeon/reg_srcs/r420 index e958980d00f..8c1214c2390 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/r420 +++ b/drivers/gpu/drm/radeon/reg_srcs/r420 @@ -130,6 +130,7 @@ r420 0x4f60 0x401C GB_SELECT 0x4020 GB_AA_CONFIG 0x4024 GB_FIFO_SIZE +0x4028 GB_Z_PEQ_CONFIG 0x4100 TX_INVALTAGS 0x4200 GA_POINT_S0 0x4204 GA_POINT_T0 @@ -187,7 +188,6 @@ r420 0x4f60 0x4364 RS_INST_13 0x4368 RS_INST_14 0x436C RS_INST_15 -0x43A4 SC_HYPERZ_EN 0x43A8 SC_EDGERULE 0x43B0 SC_CLIP_0_A 0x43B4 SC_CLIP_0_B @@ -782,16 +782,4 @@ r420 0x4f60 0x4F08 ZB_STENCILREFMASK 0x4F14 ZB_ZTOP 0x4F18 ZB_ZCACHE_CTLSTAT -0x4F1C ZB_BW_CNTL -0x4F28 ZB_DEPTHCLEARVALUE -0x4F30 ZB_ZMASK_OFFSET -0x4F34 ZB_ZMASK_PITCH -0x4F38 ZB_ZMASK_WRINDEX -0x4F3C ZB_ZMASK_DWORD -0x4F40 ZB_ZMASK_RDINDEX -0x4F44 ZB_HIZ_OFFSET -0x4F48 ZB_HIZ_WRINDEX -0x4F4C ZB_HIZ_DWORD -0x4F50 ZB_HIZ_RDINDEX -0x4F54 ZB_HIZ_PITCH 0x4F58 ZB_ZPASS_DATA diff --git a/drivers/gpu/drm/radeon/reg_srcs/rs600 b/drivers/gpu/drm/radeon/reg_srcs/rs600 index 83e8bc0c2bb..0828d80396f 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/rs600 +++ b/drivers/gpu/drm/radeon/reg_srcs/rs600 @@ -187,7 +187,6 @@ rs600 0x6d40 0x4364 RS_INST_13 0x4368 RS_INST_14 0x436C RS_INST_15 -0x43A4 SC_HYPERZ_EN 0x43A8 SC_EDGERULE 0x43B0 SC_CLIP_0_A 0x43B4 SC_CLIP_0_B @@ -782,16 +781,4 @@ rs600 0x6d40 0x4F08 ZB_STENCILREFMASK 0x4F14 ZB_ZTOP 0x4F18 ZB_ZCACHE_CTLSTAT -0x4F1C ZB_BW_CNTL -0x4F28 ZB_DEPTHCLEARVALUE -0x4F30 ZB_ZMASK_OFFSET -0x4F34 ZB_ZMASK_PITCH -0x4F38 ZB_ZMASK_WRINDEX -0x4F3C ZB_ZMASK_DWORD -0x4F40 ZB_ZMASK_RDINDEX -0x4F44 ZB_HIZ_OFFSET -0x4F48 ZB_HIZ_WRINDEX -0x4F4C ZB_HIZ_DWORD -0x4F50 ZB_HIZ_RDINDEX -0x4F54 ZB_HIZ_PITCH 0x4F58 ZB_ZPASS_DATA diff --git a/drivers/gpu/drm/radeon/reg_srcs/rv515 b/drivers/gpu/drm/radeon/reg_srcs/rv515 index 1e46233985e..8293855f5f0 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/rv515 +++ b/drivers/gpu/drm/radeon/reg_srcs/rv515 @@ -235,7 +235,6 @@ rv515 0x6d40 0x4354 RS_INST_13 0x4358 RS_INST_14 0x435C RS_INST_15 -0x43A4 SC_HYPERZ_EN 0x43A8 SC_EDGERULE 0x43B0 SC_CLIP_0_A 0x43B4 SC_CLIP_0_B @@ -479,17 +478,5 @@ rv515 0x6d40 0x4F08 ZB_STENCILREFMASK 0x4F14 ZB_ZTOP 0x4F18 ZB_ZCACHE_CTLSTAT -0x4F1C ZB_BW_CNTL -0x4F28 ZB_DEPTHCLEARVALUE -0x4F30 ZB_ZMASK_OFFSET -0x4F34 ZB_ZMASK_PITCH -0x4F38 ZB_ZMASK_WRINDEX -0x4F3C ZB_ZMASK_DWORD -0x4F40 ZB_ZMASK_RDINDEX -0x4F44 ZB_HIZ_OFFSET -0x4F48 ZB_HIZ_WRINDEX -0x4F4C ZB_HIZ_DWORD -0x4F50 ZB_HIZ_RDINDEX -0x4F54 ZB_HIZ_PITCH 0x4F58 ZB_ZPASS_DATA 0x4FD4 ZB_STENCILREFMASK_BF diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c index f454c9a5e7f..ae2b76b9a38 100644 --- a/drivers/gpu/drm/radeon/rs400.c +++ b/drivers/gpu/drm/radeon/rs400.c @@ -55,14 +55,6 @@ void rs400_gart_adjust_size(struct radeon_device *rdev) rdev->mc.gtt_size = 32 * 1024 * 1024; return; } - if (rdev->family == CHIP_RS400 || rdev->family == CHIP_RS480) { - /* FIXME: RS400 & RS480 seems to have issue with GART size - * if 4G of system memory (needs more testing) - */ - /* XXX is this still an issue with proper alignment? */ - rdev->mc.gtt_size = 32 * 1024 * 1024; - DRM_ERROR("Forcing to 32M GART size (because of ASIC bug ?)\n"); - } } void rs400_gart_tlb_flush(struct radeon_device *rdev) @@ -483,6 +475,8 @@ int rs400_init(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); /* TODO: disable VGA need to use VGA request */ + /* restore some register to sane defaults */ + r100_restore_sanity(rdev); /* BIOS*/ if (!radeon_get_bios(rdev)) { if (ASIC_IS_AVIVO(rdev)) diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 6dc15ea8ba3..cc05b230d7e 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -686,8 +686,8 @@ void rs600_mc_init(struct radeon_device *rdev) { u64 base; - rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0); - rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0); + rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0); + rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0); rdev->mc.vram_is_ddr = true; rdev->mc.vram_width = 128; rdev->mc.real_vram_size = RREG32(RADEON_CONFIG_MEMSIZE); @@ -696,7 +696,6 @@ void rs600_mc_init(struct radeon_device *rdev) rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev); base = RREG32_MC(R_000004_MC_FB_LOCATION); base = G_000004_MC_FB_START(base) << 16; - rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev); radeon_vram_location(rdev, &rdev->mc, base); rdev->mc.gtt_base_align = 0; radeon_gtt_location(rdev, &rdev->mc); @@ -813,6 +812,13 @@ static int rs600_startup(struct radeon_device *rdev) dev_err(rdev->dev, "failled initializing IB (%d).\n", r); return r; } + + r = r600_audio_init(rdev); + if (r) { + dev_err(rdev->dev, "failed initializing audio\n"); + return r; + } + return 0; } @@ -839,6 +845,7 @@ int rs600_resume(struct radeon_device *rdev) int rs600_suspend(struct radeon_device *rdev) { + r600_audio_fini(rdev); r100_cp_disable(rdev); r100_wb_disable(rdev); rs600_irq_disable(rdev); @@ -848,6 +855,7 @@ int rs600_suspend(struct radeon_device *rdev) void rs600_fini(struct radeon_device *rdev) { + r600_audio_fini(rdev); r100_cp_fini(rdev); r100_wb_fini(rdev); r100_ib_fini(rdev); @@ -871,6 +879,8 @@ int rs600_init(struct radeon_device *rdev) radeon_scratch_init(rdev); /* Initialize surface registers */ radeon_surface_init(rdev); + /* restore some register to sane defaults */ + r100_restore_sanity(rdev); /* BIOS */ if (!radeon_get_bios(rdev)) { if (ASIC_IS_AVIVO(rdev)) diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index ce4ecbe1081..3e3f75718be 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -154,13 +154,13 @@ void rs690_mc_init(struct radeon_device *rdev) rdev->mc.vram_width = 128; rdev->mc.real_vram_size = RREG32(RADEON_CONFIG_MEMSIZE); rdev->mc.mc_vram_size = rdev->mc.real_vram_size; - rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0); - rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0); + rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0); + rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0); rdev->mc.visible_vram_size = rdev->mc.aper_size; base = RREG32_MC(R_000100_MCCFG_FB_LOCATION); base = G_000100_MC_FB_START(base) << 16; - rs690_pm_info(rdev); rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev); + rs690_pm_info(rdev); radeon_vram_location(rdev, &rdev->mc, base); rdev->mc.gtt_base_align = rdev->mc.gtt_size - 1; radeon_gtt_location(rdev, &rdev->mc); @@ -398,7 +398,9 @@ void rs690_bandwidth_update(struct radeon_device *rdev) struct drm_display_mode *mode1 = NULL; struct rs690_watermark wm0; struct rs690_watermark wm1; - u32 tmp, d1mode_priority_a_cnt, d2mode_priority_a_cnt; + u32 tmp; + u32 d1mode_priority_a_cnt = S_006548_D1MODE_PRIORITY_A_OFF(1); + u32 d2mode_priority_a_cnt = S_006548_D1MODE_PRIORITY_A_OFF(1); fixed20_12 priority_mark02, priority_mark12, fill_rate; fixed20_12 a, b; @@ -495,10 +497,6 @@ void rs690_bandwidth_update(struct radeon_device *rdev) d1mode_priority_a_cnt |= S_006548_D1MODE_PRIORITY_A_ALWAYS_ON(1); d2mode_priority_a_cnt |= S_006D48_D2MODE_PRIORITY_A_ALWAYS_ON(1); } - WREG32(R_006548_D1MODE_PRIORITY_A_CNT, d1mode_priority_a_cnt); - WREG32(R_00654C_D1MODE_PRIORITY_B_CNT, d1mode_priority_a_cnt); - WREG32(R_006D48_D2MODE_PRIORITY_A_CNT, d2mode_priority_a_cnt); - WREG32(R_006D4C_D2MODE_PRIORITY_B_CNT, d2mode_priority_a_cnt); } else if (mode0) { if (dfixed_trunc(wm0.dbpp) > 64) a.full = dfixed_mul(wm0.dbpp, wm0.num_line_pair); @@ -528,13 +526,7 @@ void rs690_bandwidth_update(struct radeon_device *rdev) d1mode_priority_a_cnt = dfixed_trunc(priority_mark02); if (rdev->disp_priority == 2) d1mode_priority_a_cnt |= S_006548_D1MODE_PRIORITY_A_ALWAYS_ON(1); - WREG32(R_006548_D1MODE_PRIORITY_A_CNT, d1mode_priority_a_cnt); - WREG32(R_00654C_D1MODE_PRIORITY_B_CNT, d1mode_priority_a_cnt); - WREG32(R_006D48_D2MODE_PRIORITY_A_CNT, - S_006D48_D2MODE_PRIORITY_A_OFF(1)); - WREG32(R_006D4C_D2MODE_PRIORITY_B_CNT, - S_006D4C_D2MODE_PRIORITY_B_OFF(1)); - } else { + } else if (mode1) { if (dfixed_trunc(wm1.dbpp) > 64) a.full = dfixed_mul(wm1.dbpp, wm1.num_line_pair); else @@ -563,13 +555,12 @@ void rs690_bandwidth_update(struct radeon_device *rdev) d2mode_priority_a_cnt = dfixed_trunc(priority_mark12); if (rdev->disp_priority == 2) d2mode_priority_a_cnt |= S_006D48_D2MODE_PRIORITY_A_ALWAYS_ON(1); - WREG32(R_006548_D1MODE_PRIORITY_A_CNT, - S_006548_D1MODE_PRIORITY_A_OFF(1)); - WREG32(R_00654C_D1MODE_PRIORITY_B_CNT, - S_00654C_D1MODE_PRIORITY_B_OFF(1)); - WREG32(R_006D48_D2MODE_PRIORITY_A_CNT, d2mode_priority_a_cnt); - WREG32(R_006D4C_D2MODE_PRIORITY_B_CNT, d2mode_priority_a_cnt); } + + WREG32(R_006548_D1MODE_PRIORITY_A_CNT, d1mode_priority_a_cnt); + WREG32(R_00654C_D1MODE_PRIORITY_B_CNT, d1mode_priority_a_cnt); + WREG32(R_006D48_D2MODE_PRIORITY_A_CNT, d2mode_priority_a_cnt); + WREG32(R_006D4C_D2MODE_PRIORITY_B_CNT, d2mode_priority_a_cnt); } uint32_t rs690_mc_rreg(struct radeon_device *rdev, uint32_t reg) @@ -641,6 +632,13 @@ static int rs690_startup(struct radeon_device *rdev) dev_err(rdev->dev, "failled initializing IB (%d).\n", r); return r; } + + r = r600_audio_init(rdev); + if (r) { + dev_err(rdev->dev, "failed initializing audio\n"); + return r; + } + return 0; } @@ -667,6 +665,7 @@ int rs690_resume(struct radeon_device *rdev) int rs690_suspend(struct radeon_device *rdev) { + r600_audio_fini(rdev); r100_cp_disable(rdev); r100_wb_disable(rdev); rs600_irq_disable(rdev); @@ -676,6 +675,7 @@ int rs690_suspend(struct radeon_device *rdev) void rs690_fini(struct radeon_device *rdev) { + r600_audio_fini(rdev); r100_cp_fini(rdev); r100_wb_fini(rdev); r100_ib_fini(rdev); @@ -699,6 +699,8 @@ int rs690_init(struct radeon_device *rdev) radeon_scratch_init(rdev); /* Initialize surface registers */ radeon_surface_init(rdev); + /* restore some register to sane defaults */ + r100_restore_sanity(rdev); /* TODO: disable VGA need to use VGA request */ /* BIOS*/ if (!radeon_get_bios(rdev)) { diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 0c9c169a685..4d6e86041a9 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -469,6 +469,8 @@ int rv515_init(struct radeon_device *rdev) /* Initialize surface registers */ radeon_surface_init(rdev); /* TODO: disable VGA need to use VGA request */ + /* restore some register to sane defaults */ + r100_restore_sanity(rdev); /* BIOS*/ if (!radeon_get_bios(rdev)) { if (ASIC_IS_AVIVO(rdev)) @@ -925,7 +927,9 @@ void rv515_bandwidth_avivo_update(struct radeon_device *rdev) struct drm_display_mode *mode1 = NULL; struct rv515_watermark wm0; struct rv515_watermark wm1; - u32 tmp, d1mode_priority_a_cnt, d2mode_priority_a_cnt; + u32 tmp; + u32 d1mode_priority_a_cnt = MODE_PRIORITY_OFF; + u32 d2mode_priority_a_cnt = MODE_PRIORITY_OFF; fixed20_12 priority_mark02, priority_mark12, fill_rate; fixed20_12 a, b; @@ -999,10 +1003,6 @@ void rv515_bandwidth_avivo_update(struct radeon_device *rdev) d1mode_priority_a_cnt |= MODE_PRIORITY_ALWAYS_ON; d2mode_priority_a_cnt |= MODE_PRIORITY_ALWAYS_ON; } - WREG32(D1MODE_PRIORITY_A_CNT, d1mode_priority_a_cnt); - WREG32(D1MODE_PRIORITY_B_CNT, d1mode_priority_a_cnt); - WREG32(D2MODE_PRIORITY_A_CNT, d2mode_priority_a_cnt); - WREG32(D2MODE_PRIORITY_B_CNT, d2mode_priority_a_cnt); } else if (mode0) { if (dfixed_trunc(wm0.dbpp) > 64) a.full = dfixed_div(wm0.dbpp, wm0.num_line_pair); @@ -1032,11 +1032,7 @@ void rv515_bandwidth_avivo_update(struct radeon_device *rdev) d1mode_priority_a_cnt = dfixed_trunc(priority_mark02); if (rdev->disp_priority == 2) d1mode_priority_a_cnt |= MODE_PRIORITY_ALWAYS_ON; - WREG32(D1MODE_PRIORITY_A_CNT, d1mode_priority_a_cnt); - WREG32(D1MODE_PRIORITY_B_CNT, d1mode_priority_a_cnt); - WREG32(D2MODE_PRIORITY_A_CNT, MODE_PRIORITY_OFF); - WREG32(D2MODE_PRIORITY_B_CNT, MODE_PRIORITY_OFF); - } else { + } else if (mode1) { if (dfixed_trunc(wm1.dbpp) > 64) a.full = dfixed_div(wm1.dbpp, wm1.num_line_pair); else @@ -1065,11 +1061,12 @@ void rv515_bandwidth_avivo_update(struct radeon_device *rdev) d2mode_priority_a_cnt = dfixed_trunc(priority_mark12); if (rdev->disp_priority == 2) d2mode_priority_a_cnt |= MODE_PRIORITY_ALWAYS_ON; - WREG32(D1MODE_PRIORITY_A_CNT, MODE_PRIORITY_OFF); - WREG32(D1MODE_PRIORITY_B_CNT, MODE_PRIORITY_OFF); - WREG32(D2MODE_PRIORITY_A_CNT, d2mode_priority_a_cnt); - WREG32(D2MODE_PRIORITY_B_CNT, d2mode_priority_a_cnt); } + + WREG32(D1MODE_PRIORITY_A_CNT, d1mode_priority_a_cnt); + WREG32(D1MODE_PRIORITY_B_CNT, d1mode_priority_a_cnt); + WREG32(D2MODE_PRIORITY_A_CNT, d2mode_priority_a_cnt); + WREG32(D2MODE_PRIORITY_B_CNT, d2mode_priority_a_cnt); } void rv515_bandwidth_update(struct radeon_device *rdev) diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c index b7fd8206492..f1c79681011 100644 --- a/drivers/gpu/drm/radeon/rv770.c +++ b/drivers/gpu/drm/radeon/rv770.c @@ -42,6 +42,21 @@ static void rv770_gpu_init(struct radeon_device *rdev); void rv770_fini(struct radeon_device *rdev); +/* get temperature in millidegrees */ +u32 rv770_get_temp(struct radeon_device *rdev) +{ + u32 temp = (RREG32(CG_MULT_THERMAL_STATUS) & ASIC_T_MASK) >> + ASIC_T_SHIFT; + u32 actual_temp = 0; + + if ((temp >> 9) & 1) + actual_temp = 0; + else + actual_temp = (temp >> 1) & 0xff; + + return actual_temp * 1000; +} + void rv770_pm_misc(struct radeon_device *rdev) { int req_ps_idx = rdev->pm.requested_power_state_index; @@ -189,7 +204,10 @@ static void rv770_mc_program(struct radeon_device *rdev) WREG32((0x2c20 + j), 0x00000000); WREG32((0x2c24 + j), 0x00000000); } - WREG32(HDP_REG_COHERENCY_FLUSH_CNTL, 0); + /* r7xx hw bug. Read from HDP_DEBUG1 rather + * than writing to HDP_REG_COHERENCY_FLUSH_CNTL + */ + tmp = RREG32(HDP_DEBUG1); rv515_mc_stop(rdev, &save); if (r600_mc_wait_for_idle(rdev)) { @@ -659,8 +677,9 @@ static void rv770_gpu_init(struct radeon_device *rdev) r600_count_pipe_bits((cc_rb_backend_disable & R7XX_MAX_BACKENDS_MASK) >> 16)), (cc_rb_backend_disable >> 16)); - gb_tiling_config |= BACKEND_MAP(backend_map); + rdev->config.rv770.tile_config = gb_tiling_config; + gb_tiling_config |= BACKEND_MAP(backend_map); WREG32(GB_TILING_CONFIG, gb_tiling_config); WREG32(DCP_TILING_CONFIG, (gb_tiling_config & 0xffff)); @@ -919,8 +938,8 @@ int rv770_mc_init(struct radeon_device *rdev) } rdev->mc.vram_width = numchan * chansize; /* Could aper size report 0 ? */ - rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0); - rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0); + rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0); + rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0); /* Setup GPU memory space */ rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE); rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE); diff --git a/drivers/gpu/drm/radeon/rv770d.h b/drivers/gpu/drm/radeon/rv770d.h index 9506f8cb99e..b7a5a20e81d 100644 --- a/drivers/gpu/drm/radeon/rv770d.h +++ b/drivers/gpu/drm/radeon/rv770d.h @@ -122,12 +122,18 @@ #define GUI_ACTIVE (1<<31) #define GRBM_STATUS2 0x8014 +#define CG_MULT_THERMAL_STATUS 0x740 +#define ASIC_T(x) ((x) << 16) +#define ASIC_T_MASK 0x3FF0000 +#define ASIC_T_SHIFT 16 + #define HDP_HOST_PATH_CNTL 0x2C00 #define HDP_NONSURFACE_BASE 0x2C04 #define HDP_NONSURFACE_INFO 0x2C08 #define HDP_NONSURFACE_SIZE 0x2C0C #define HDP_REG_COHERENCY_FLUSH_CNTL 0x54A0 #define HDP_TILING_CONFIG 0x2F3C +#define HDP_DEBUG1 0x2F34 #define MC_SHARED_CHMAP 0x2004 #define NOOFCHAN_SHIFT 12 diff --git a/drivers/gpu/drm/savage/savage_bci.c b/drivers/gpu/drm/savage/savage_bci.c index fa05cda8c98..976dc8d2528 100644 --- a/drivers/gpu/drm/savage/savage_bci.c +++ b/drivers/gpu/drm/savage/savage_bci.c @@ -573,13 +573,13 @@ int savage_driver_firstopen(struct drm_device *dev) dev_priv->mtrr[2].handle = -1; if (S3_SAVAGE3D_SERIES(dev_priv->chipset)) { fb_rsrc = 0; - fb_base = drm_get_resource_start(dev, 0); + fb_base = pci_resource_start(dev->pdev, 0); fb_size = SAVAGE_FB_SIZE_S3; mmio_base = fb_base + SAVAGE_FB_SIZE_S3; aper_rsrc = 0; aperture_base = fb_base + SAVAGE_APERTURE_OFFSET; /* this should always be true */ - if (drm_get_resource_len(dev, 0) == 0x08000000) { + if (pci_resource_len(dev->pdev, 0) == 0x08000000) { /* Don't make MMIO write-cobining! We need 3 * MTRRs. */ dev_priv->mtrr[0].base = fb_base; @@ -599,18 +599,19 @@ int savage_driver_firstopen(struct drm_device *dev) dev_priv->mtrr[2].size, DRM_MTRR_WC); } else { DRM_ERROR("strange pci_resource_len %08llx\n", - (unsigned long long)drm_get_resource_len(dev, 0)); + (unsigned long long) + pci_resource_len(dev->pdev, 0)); } } else if (dev_priv->chipset != S3_SUPERSAVAGE && dev_priv->chipset != S3_SAVAGE2000) { - mmio_base = drm_get_resource_start(dev, 0); + mmio_base = pci_resource_start(dev->pdev, 0); fb_rsrc = 1; - fb_base = drm_get_resource_start(dev, 1); + fb_base = pci_resource_start(dev->pdev, 1); fb_size = SAVAGE_FB_SIZE_S4; aper_rsrc = 1; aperture_base = fb_base + SAVAGE_APERTURE_OFFSET; /* this should always be true */ - if (drm_get_resource_len(dev, 1) == 0x08000000) { + if (pci_resource_len(dev->pdev, 1) == 0x08000000) { /* Can use one MTRR to cover both fb and * aperture. */ dev_priv->mtrr[0].base = fb_base; @@ -620,15 +621,16 @@ int savage_driver_firstopen(struct drm_device *dev) dev_priv->mtrr[0].size, DRM_MTRR_WC); } else { DRM_ERROR("strange pci_resource_len %08llx\n", - (unsigned long long)drm_get_resource_len(dev, 1)); + (unsigned long long) + pci_resource_len(dev->pdev, 1)); } } else { - mmio_base = drm_get_resource_start(dev, 0); + mmio_base = pci_resource_start(dev->pdev, 0); fb_rsrc = 1; - fb_base = drm_get_resource_start(dev, 1); - fb_size = drm_get_resource_len(dev, 1); + fb_base = pci_resource_start(dev->pdev, 1); + fb_size = pci_resource_len(dev->pdev, 1); aper_rsrc = 2; - aperture_base = drm_get_resource_start(dev, 2); + aperture_base = pci_resource_start(dev->pdev, 2); /* Automatic MTRR setup will do the right thing. */ } diff --git a/drivers/gpu/drm/sis/sis_drv.c b/drivers/gpu/drm/sis/sis_drv.c index 4fd1f067d38..776bf9e9ea1 100644 --- a/drivers/gpu/drm/sis/sis_drv.c +++ b/drivers/gpu/drm/sis/sis_drv.c @@ -47,9 +47,8 @@ static int sis_driver_load(struct drm_device *dev, unsigned long chipset) dev->dev_private = (void *)dev_priv; dev_priv->chipset = chipset; ret = drm_sman_init(&dev_priv->sman, 2, 12, 8); - if (ret) { + if (ret) kfree(dev_priv); - } return ret; } diff --git a/drivers/gpu/drm/sis/sis_mm.c b/drivers/gpu/drm/sis/sis_mm.c index af22111397d..07d0f2979ca 100644 --- a/drivers/gpu/drm/sis/sis_mm.c +++ b/drivers/gpu/drm/sis/sis_mm.c @@ -78,7 +78,7 @@ static unsigned long sis_sman_mm_offset(void *private, void *ref) #else /* CONFIG_FB_SIS[_MODULE] */ #define SIS_MM_ALIGN_SHIFT 4 -#define SIS_MM_ALIGN_MASK ( (1 << SIS_MM_ALIGN_SHIFT) - 1) +#define SIS_MM_ALIGN_MASK ((1 << SIS_MM_ALIGN_SHIFT) - 1) #endif /* CONFIG_FB_SIS[_MODULE] */ @@ -225,9 +225,8 @@ static drm_local_map_t *sis_reg_init(struct drm_device *dev) map = entry->map; if (!map) continue; - if (map->type == _DRM_REGISTERS) { + if (map->type == _DRM_REGISTERS) return map; - } } return NULL; } @@ -264,10 +263,10 @@ int sis_idle(struct drm_device *dev) end = jiffies + (DRM_HZ * 3); - for (i=0; i<4; ++i) { + for (i = 0; i < 4; ++i) { do { idle_reg = SIS_READ(0x85cc); - } while ( !time_after_eq(jiffies, end) && + } while (!time_after_eq(jiffies, end) && ((idle_reg & 0x80000000) != 0x80000000)); } @@ -301,7 +300,7 @@ void sis_lastclose(struct drm_device *dev) mutex_unlock(&dev->struct_mutex); } -void sis_reclaim_buffers_locked(struct drm_device * dev, +void sis_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv) { drm_sis_private_t *dev_priv = dev->dev_private; @@ -312,9 +311,8 @@ void sis_reclaim_buffers_locked(struct drm_device * dev, return; } - if (dev->driver->dma_quiescent) { + if (dev->driver->dma_quiescent) dev->driver->dma_quiescent(dev); - } drm_sman_owner_cleanup(&dev_priv->sman, (unsigned long)file_priv); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/ttm/Makefile b/drivers/gpu/drm/ttm/Makefile index 4256e200647..b256d4adfaf 100644 --- a/drivers/gpu/drm/ttm/Makefile +++ b/drivers/gpu/drm/ttm/Makefile @@ -3,7 +3,7 @@ ccflags-y := -Iinclude/drm ttm-y := ttm_agp_backend.o ttm_memory.o ttm_tt.o ttm_bo.o \ - ttm_bo_util.o ttm_bo_vm.o ttm_module.o ttm_global.o \ + ttm_bo_util.o ttm_bo_vm.o ttm_module.o \ ttm_object.o ttm_lock.o ttm_execbuf_util.o ttm_page_alloc.o obj-$(CONFIG_DRM_TTM) += ttm.o diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 555ebb12ace..cb4cf7ef4d1 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -476,7 +476,6 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, bool remove_all) ++put_count; } if (bo->mem.mm_node) { - bo->mem.mm_node->private = NULL; drm_mm_put_block(bo->mem.mm_node); bo->mem.mm_node = NULL; } @@ -670,7 +669,6 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible, printk(KERN_ERR TTM_PFX "Buffer eviction failed\n"); spin_lock(&glob->lru_lock); if (evict_mem.mm_node) { - evict_mem.mm_node->private = NULL; drm_mm_put_block(evict_mem.mm_node); evict_mem.mm_node = NULL; } @@ -929,8 +927,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, mem->mm_node = node; mem->mem_type = mem_type; mem->placement = cur_flags; - if (node) - node->private = bo; return 0; } @@ -973,7 +969,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, interruptible, no_wait_reserve, no_wait_gpu); if (ret == 0 && mem->mm_node) { mem->placement = cur_flags; - mem->mm_node->private = bo; return 0; } if (ret == -ERESTARTSYS) @@ -1029,7 +1024,6 @@ int ttm_bo_move_buffer(struct ttm_buffer_object *bo, out_unlock: if (ret && mem.mm_node) { spin_lock(&glob->lru_lock); - mem.mm_node->private = NULL; drm_mm_put_block(mem.mm_node); spin_unlock(&glob->lru_lock); } @@ -1401,7 +1395,7 @@ static void ttm_bo_global_kobj_release(struct kobject *kobj) kfree(glob); } -void ttm_bo_global_release(struct ttm_global_reference *ref) +void ttm_bo_global_release(struct drm_global_reference *ref) { struct ttm_bo_global *glob = ref->object; @@ -1410,7 +1404,7 @@ void ttm_bo_global_release(struct ttm_global_reference *ref) } EXPORT_SYMBOL(ttm_bo_global_release); -int ttm_bo_global_init(struct ttm_global_reference *ref) +int ttm_bo_global_init(struct drm_global_reference *ref) { struct ttm_bo_global_ref *bo_ref = container_of(ref, struct ttm_bo_global_ref, ref); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 13012a1f148..7cffb3e0423 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -353,8 +353,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, fbo->vm_node = NULL; fbo->sync_obj = driver->sync_obj_ref(bo->sync_obj); - if (fbo->mem.mm_node) - fbo->mem.mm_node->private = (void *)fbo; kref_init(&fbo->list_kref); kref_init(&fbo->kref); fbo->destroy = &ttm_transfered_destroy; diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c index 9a6edbfeaa9..902d7cf9fb4 100644 --- a/drivers/gpu/drm/ttm/ttm_module.c +++ b/drivers/gpu/drm/ttm/ttm_module.c @@ -70,8 +70,6 @@ static int __init ttm_init(void) if (unlikely(ret != 0)) return ret; - ttm_global_init(); - atomic_set(&device_released, 0); ret = drm_class_device_register(&ttm_drm_class_device); if (unlikely(ret != 0)) @@ -81,7 +79,6 @@ static int __init ttm_init(void) out_no_dev_reg: atomic_set(&device_released, 1); wake_up_all(&exit_q); - ttm_global_release(); return ret; } @@ -95,7 +92,6 @@ static void __exit ttm_exit(void) */ wait_event(exit_q, atomic_read(&device_released) == 1); - ttm_global_release(); } module_init(ttm_init); diff --git a/drivers/gpu/drm/via/via_dma.c b/drivers/gpu/drm/via/via_dma.c index bfb92d28326..68dda74a50a 100644 --- a/drivers/gpu/drm/via/via_dma.c +++ b/drivers/gpu/drm/via/via_dma.c @@ -58,28 +58,29 @@ *((uint32_t *)(vb)) = ((nReg) >> 2) | HALCYON_HEADER1; \ *((uint32_t *)(vb) + 1) = (nData); \ vb = ((uint32_t *)vb) + 2; \ - dev_priv->dma_low +=8; \ + dev_priv->dma_low += 8; \ } #define via_flush_write_combine() DRM_MEMORYBARRIER() -#define VIA_OUT_RING_QW(w1,w2) \ +#define VIA_OUT_RING_QW(w1, w2) do { \ *vb++ = (w1); \ *vb++ = (w2); \ - dev_priv->dma_low += 8; + dev_priv->dma_low += 8; \ +} while (0) -static void via_cmdbuf_start(drm_via_private_t * dev_priv); -static void via_cmdbuf_pause(drm_via_private_t * dev_priv); -static void via_cmdbuf_reset(drm_via_private_t * dev_priv); -static void via_cmdbuf_rewind(drm_via_private_t * dev_priv); -static int via_wait_idle(drm_via_private_t * dev_priv); -static void via_pad_cache(drm_via_private_t * dev_priv, int qwords); +static void via_cmdbuf_start(drm_via_private_t *dev_priv); +static void via_cmdbuf_pause(drm_via_private_t *dev_priv); +static void via_cmdbuf_reset(drm_via_private_t *dev_priv); +static void via_cmdbuf_rewind(drm_via_private_t *dev_priv); +static int via_wait_idle(drm_via_private_t *dev_priv); +static void via_pad_cache(drm_via_private_t *dev_priv, int qwords); /* * Free space in command buffer. */ -static uint32_t via_cmdbuf_space(drm_via_private_t * dev_priv) +static uint32_t via_cmdbuf_space(drm_via_private_t *dev_priv) { uint32_t agp_base = dev_priv->dma_offset + (uint32_t) dev_priv->agpAddr; uint32_t hw_addr = *(dev_priv->hw_addr_ptr) - agp_base; @@ -93,7 +94,7 @@ static uint32_t via_cmdbuf_space(drm_via_private_t * dev_priv) * How much does the command regulator lag behind? */ -static uint32_t via_cmdbuf_lag(drm_via_private_t * dev_priv) +static uint32_t via_cmdbuf_lag(drm_via_private_t *dev_priv) { uint32_t agp_base = dev_priv->dma_offset + (uint32_t) dev_priv->agpAddr; uint32_t hw_addr = *(dev_priv->hw_addr_ptr) - agp_base; @@ -108,7 +109,7 @@ static uint32_t via_cmdbuf_lag(drm_via_private_t * dev_priv) */ static inline int -via_cmdbuf_wait(drm_via_private_t * dev_priv, unsigned int size) +via_cmdbuf_wait(drm_via_private_t *dev_priv, unsigned int size) { uint32_t agp_base = dev_priv->dma_offset + (uint32_t) dev_priv->agpAddr; uint32_t cur_addr, hw_addr, next_addr; @@ -146,14 +147,13 @@ static inline uint32_t *via_check_dma(drm_via_private_t * dev_priv, dev_priv->dma_high) { via_cmdbuf_rewind(dev_priv); } - if (via_cmdbuf_wait(dev_priv, size) != 0) { + if (via_cmdbuf_wait(dev_priv, size) != 0) return NULL; - } return (uint32_t *) (dev_priv->dma_ptr + dev_priv->dma_low); } -int via_dma_cleanup(struct drm_device * dev) +int via_dma_cleanup(struct drm_device *dev) { if (dev->dev_private) { drm_via_private_t *dev_priv = @@ -171,9 +171,9 @@ int via_dma_cleanup(struct drm_device * dev) return 0; } -static int via_initialize(struct drm_device * dev, - drm_via_private_t * dev_priv, - drm_via_dma_init_t * init) +static int via_initialize(struct drm_device *dev, + drm_via_private_t *dev_priv, + drm_via_dma_init_t *init) { if (!dev_priv || !dev_priv->mmio) { DRM_ERROR("via_dma_init called before via_map_init\n"); @@ -258,7 +258,7 @@ static int via_dma_init(struct drm_device *dev, void *data, struct drm_file *fil return retcode; } -static int via_dispatch_cmdbuffer(struct drm_device * dev, drm_via_cmdbuffer_t * cmd) +static int via_dispatch_cmdbuffer(struct drm_device *dev, drm_via_cmdbuffer_t *cmd) { drm_via_private_t *dev_priv; uint32_t *vb; @@ -271,9 +271,8 @@ static int via_dispatch_cmdbuffer(struct drm_device * dev, drm_via_cmdbuffer_t * return -EFAULT; } - if (cmd->size > VIA_PCI_BUF_SIZE) { + if (cmd->size > VIA_PCI_BUF_SIZE) return -ENOMEM; - } if (DRM_COPY_FROM_USER(dev_priv->pci_buf, cmd->buf, cmd->size)) return -EFAULT; @@ -291,9 +290,8 @@ static int via_dispatch_cmdbuffer(struct drm_device * dev, drm_via_cmdbuffer_t * } vb = via_check_dma(dev_priv, (cmd->size < 0x100) ? 0x102 : cmd->size); - if (vb == NULL) { + if (vb == NULL) return -EAGAIN; - } memcpy(vb, dev_priv->pci_buf, cmd->size); @@ -311,13 +309,12 @@ static int via_dispatch_cmdbuffer(struct drm_device * dev, drm_via_cmdbuffer_t * return 0; } -int via_driver_dma_quiescent(struct drm_device * dev) +int via_driver_dma_quiescent(struct drm_device *dev) { drm_via_private_t *dev_priv = dev->dev_private; - if (!via_wait_idle(dev_priv)) { + if (!via_wait_idle(dev_priv)) return -EBUSY; - } return 0; } @@ -339,22 +336,17 @@ static int via_cmdbuffer(struct drm_device *dev, void *data, struct drm_file *fi DRM_DEBUG("buf %p size %lu\n", cmdbuf->buf, cmdbuf->size); ret = via_dispatch_cmdbuffer(dev, cmdbuf); - if (ret) { - return ret; - } - - return 0; + return ret; } -static int via_dispatch_pci_cmdbuffer(struct drm_device * dev, - drm_via_cmdbuffer_t * cmd) +static int via_dispatch_pci_cmdbuffer(struct drm_device *dev, + drm_via_cmdbuffer_t *cmd) { drm_via_private_t *dev_priv = dev->dev_private; int ret; - if (cmd->size > VIA_PCI_BUF_SIZE) { + if (cmd->size > VIA_PCI_BUF_SIZE) return -ENOMEM; - } if (DRM_COPY_FROM_USER(dev_priv->pci_buf, cmd->buf, cmd->size)) return -EFAULT; @@ -380,19 +372,14 @@ static int via_pci_cmdbuffer(struct drm_device *dev, void *data, struct drm_file DRM_DEBUG("buf %p size %lu\n", cmdbuf->buf, cmdbuf->size); ret = via_dispatch_pci_cmdbuffer(dev, cmdbuf); - if (ret) { - return ret; - } - - return 0; + return ret; } -static inline uint32_t *via_align_buffer(drm_via_private_t * dev_priv, +static inline uint32_t *via_align_buffer(drm_via_private_t *dev_priv, uint32_t * vb, int qw_count) { - for (; qw_count > 0; --qw_count) { + for (; qw_count > 0; --qw_count) VIA_OUT_RING_QW(HC_DUMMY, HC_DUMMY); - } return vb; } @@ -401,7 +388,7 @@ static inline uint32_t *via_align_buffer(drm_via_private_t * dev_priv, * * Returns virtual pointer to ring buffer. */ -static inline uint32_t *via_get_dma(drm_via_private_t * dev_priv) +static inline uint32_t *via_get_dma(drm_via_private_t *dev_priv) { return (uint32_t *) (dev_priv->dma_ptr + dev_priv->dma_low); } @@ -411,18 +398,18 @@ static inline uint32_t *via_get_dma(drm_via_private_t * dev_priv) * modifying the pause address stored in the buffer itself. If * the regulator has already paused, restart it. */ -static int via_hook_segment(drm_via_private_t * dev_priv, +static int via_hook_segment(drm_via_private_t *dev_priv, uint32_t pause_addr_hi, uint32_t pause_addr_lo, int no_pci_fire) { int paused, count; volatile uint32_t *paused_at = dev_priv->last_pause_ptr; - uint32_t reader,ptr; + uint32_t reader, ptr; uint32_t diff; paused = 0; via_flush_write_combine(); - (void) *(volatile uint32_t *)(via_get_dma(dev_priv) -1); + (void) *(volatile uint32_t *)(via_get_dma(dev_priv) - 1); *paused_at = pause_addr_lo; via_flush_write_combine(); @@ -435,7 +422,7 @@ static int via_hook_segment(drm_via_private_t * dev_priv, dev_priv->last_pause_ptr = via_get_dma(dev_priv) - 1; /* - * If there is a possibility that the command reader will + * If there is a possibility that the command reader will * miss the new pause address and pause on the old one, * In that case we need to program the new start address * using PCI. @@ -443,9 +430,9 @@ static int via_hook_segment(drm_via_private_t * dev_priv, diff = (uint32_t) (ptr - reader) - dev_priv->dma_diff; count = 10000000; - while(diff == 0 && count--) { + while (diff == 0 && count--) { paused = (VIA_READ(0x41c) & 0x80000000); - if (paused) + if (paused) break; reader = *(dev_priv->hw_addr_ptr); diff = (uint32_t) (ptr - reader) - dev_priv->dma_diff; @@ -477,7 +464,7 @@ static int via_hook_segment(drm_via_private_t * dev_priv, return paused; } -static int via_wait_idle(drm_via_private_t * dev_priv) +static int via_wait_idle(drm_via_private_t *dev_priv) { int count = 10000000; @@ -491,9 +478,9 @@ static int via_wait_idle(drm_via_private_t * dev_priv) return count; } -static uint32_t *via_align_cmd(drm_via_private_t * dev_priv, uint32_t cmd_type, - uint32_t addr, uint32_t * cmd_addr_hi, - uint32_t * cmd_addr_lo, int skip_wait) +static uint32_t *via_align_cmd(drm_via_private_t *dev_priv, uint32_t cmd_type, + uint32_t addr, uint32_t *cmd_addr_hi, + uint32_t *cmd_addr_lo, int skip_wait) { uint32_t agp_base; uint32_t cmd_addr, addr_lo, addr_hi; @@ -521,7 +508,7 @@ static uint32_t *via_align_cmd(drm_via_private_t * dev_priv, uint32_t cmd_type, return vb; } -static void via_cmdbuf_start(drm_via_private_t * dev_priv) +static void via_cmdbuf_start(drm_via_private_t *dev_priv) { uint32_t pause_addr_lo, pause_addr_hi; uint32_t start_addr, start_addr_lo; @@ -580,7 +567,7 @@ static void via_cmdbuf_start(drm_via_private_t * dev_priv) dev_priv->dma_diff = ptr - reader; } -static void via_pad_cache(drm_via_private_t * dev_priv, int qwords) +static void via_pad_cache(drm_via_private_t *dev_priv, int qwords) { uint32_t *vb; @@ -590,7 +577,7 @@ static void via_pad_cache(drm_via_private_t * dev_priv, int qwords) via_align_buffer(dev_priv, vb, qwords); } -static inline void via_dummy_bitblt(drm_via_private_t * dev_priv) +static inline void via_dummy_bitblt(drm_via_private_t *dev_priv) { uint32_t *vb = via_get_dma(dev_priv); SetReg2DAGP(0x0C, (0 | (0 << 16))); @@ -598,7 +585,7 @@ static inline void via_dummy_bitblt(drm_via_private_t * dev_priv) SetReg2DAGP(0x0, 0x1 | 0x2000 | 0xAA000000); } -static void via_cmdbuf_jump(drm_via_private_t * dev_priv) +static void via_cmdbuf_jump(drm_via_private_t *dev_priv) { uint32_t agp_base; uint32_t pause_addr_lo, pause_addr_hi; @@ -617,9 +604,8 @@ static void via_cmdbuf_jump(drm_via_private_t * dev_priv) */ dev_priv->dma_low = 0; - if (via_cmdbuf_wait(dev_priv, CMDBUF_ALIGNMENT_SIZE) != 0) { + if (via_cmdbuf_wait(dev_priv, CMDBUF_ALIGNMENT_SIZE) != 0) DRM_ERROR("via_cmdbuf_jump failed\n"); - } via_dummy_bitblt(dev_priv); via_dummy_bitblt(dev_priv); @@ -657,12 +643,12 @@ static void via_cmdbuf_jump(drm_via_private_t * dev_priv) } -static void via_cmdbuf_rewind(drm_via_private_t * dev_priv) +static void via_cmdbuf_rewind(drm_via_private_t *dev_priv) { via_cmdbuf_jump(dev_priv); } -static void via_cmdbuf_flush(drm_via_private_t * dev_priv, uint32_t cmd_type) +static void via_cmdbuf_flush(drm_via_private_t *dev_priv, uint32_t cmd_type) { uint32_t pause_addr_lo, pause_addr_hi; @@ -670,12 +656,12 @@ static void via_cmdbuf_flush(drm_via_private_t * dev_priv, uint32_t cmd_type) via_hook_segment(dev_priv, pause_addr_hi, pause_addr_lo, 0); } -static void via_cmdbuf_pause(drm_via_private_t * dev_priv) +static void via_cmdbuf_pause(drm_via_private_t *dev_priv) { via_cmdbuf_flush(dev_priv, HC_HAGPBpID_PAUSE); } -static void via_cmdbuf_reset(drm_via_private_t * dev_priv) +static void via_cmdbuf_reset(drm_via_private_t *dev_priv) { via_cmdbuf_flush(dev_priv, HC_HAGPBpID_STOP); via_wait_idle(dev_priv); @@ -708,9 +694,8 @@ static int via_cmdbuf_size(struct drm_device *dev, void *data, struct drm_file * case VIA_CMDBUF_SPACE: while (((tmp_size = via_cmdbuf_space(dev_priv)) < d_siz->size) && --count) { - if (!d_siz->wait) { + if (!d_siz->wait) break; - } } if (!count) { DRM_ERROR("VIA_CMDBUF_SPACE timed out.\n"); @@ -720,9 +705,8 @@ static int via_cmdbuf_size(struct drm_device *dev, void *data, struct drm_file * case VIA_CMDBUF_LAG: while (((tmp_size = via_cmdbuf_lag(dev_priv)) > d_siz->size) && --count) { - if (!d_siz->wait) { + if (!d_siz->wait) break; - } } if (!count) { DRM_ERROR("VIA_CMDBUF_LAG timed out.\n"); diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c index 4c54f043068..9b5b4d9dd62 100644 --- a/drivers/gpu/drm/via/via_dmablit.c +++ b/drivers/gpu/drm/via/via_dmablit.c @@ -70,7 +70,7 @@ via_unmap_blit_from_device(struct pci_dev *pdev, drm_via_sg_info_t *vsg) descriptor_this_page; dma_addr_t next = vsg->chain_start; - while(num_desc--) { + while (num_desc--) { if (descriptor_this_page-- == 0) { cur_descriptor_page--; descriptor_this_page = vsg->descriptors_per_page - 1; @@ -174,19 +174,19 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg) struct page *page; int i; - switch(vsg->state) { + switch (vsg->state) { case dr_via_device_mapped: via_unmap_blit_from_device(pdev, vsg); case dr_via_desc_pages_alloc: - for (i=0; i<vsg->num_desc_pages; ++i) { + for (i = 0; i < vsg->num_desc_pages; ++i) { if (vsg->desc_pages[i] != NULL) - free_page((unsigned long)vsg->desc_pages[i]); + free_page((unsigned long)vsg->desc_pages[i]); } kfree(vsg->desc_pages); case dr_via_pages_locked: - for (i=0; i<vsg->num_pages; ++i) { - if ( NULL != (page = vsg->pages[i])) { - if (! PageReserved(page) && (DMA_FROM_DEVICE == vsg->direction)) + for (i = 0; i < vsg->num_pages; ++i) { + if (NULL != (page = vsg->pages[i])) { + if (!PageReserved(page) && (DMA_FROM_DEVICE == vsg->direction)) SetPageDirty(page); page_cache_release(page); } @@ -232,7 +232,7 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg, drm_via_dmablit_t *xfer) { int ret; unsigned long first_pfn = VIA_PFN(xfer->mem_addr); - vsg->num_pages = VIA_PFN(xfer->mem_addr + (xfer->num_lines * xfer->mem_stride -1)) - + vsg->num_pages = VIA_PFN(xfer->mem_addr + (xfer->num_lines * xfer->mem_stride - 1)) - first_pfn + 1; if (NULL == (vsg->pages = vmalloc(sizeof(struct page *) * vsg->num_pages))) @@ -268,7 +268,7 @@ via_alloc_desc_pages(drm_via_sg_info_t *vsg) { int i; - vsg->descriptors_per_page = PAGE_SIZE / sizeof( drm_via_descriptor_t); + vsg->descriptors_per_page = PAGE_SIZE / sizeof(drm_via_descriptor_t); vsg->num_desc_pages = (vsg->num_desc + vsg->descriptors_per_page - 1) / vsg->descriptors_per_page; @@ -276,7 +276,7 @@ via_alloc_desc_pages(drm_via_sg_info_t *vsg) return -ENOMEM; vsg->state = dr_via_desc_pages_alloc; - for (i=0; i<vsg->num_desc_pages; ++i) { + for (i = 0; i < vsg->num_desc_pages; ++i) { if (NULL == (vsg->desc_pages[i] = (drm_via_descriptor_t *) __get_free_page(GFP_KERNEL))) return -ENOMEM; @@ -318,21 +318,20 @@ via_dmablit_handler(struct drm_device *dev, int engine, int from_irq) drm_via_blitq_t *blitq = dev_priv->blit_queues + engine; int cur; int done_transfer; - unsigned long irqsave=0; + unsigned long irqsave = 0; uint32_t status = 0; DRM_DEBUG("DMA blit handler called. engine = %d, from_irq = %d, blitq = 0x%lx\n", engine, from_irq, (unsigned long) blitq); - if (from_irq) { + if (from_irq) spin_lock(&blitq->blit_lock); - } else { + else spin_lock_irqsave(&blitq->blit_lock, irqsave); - } done_transfer = blitq->is_active && - (( status = VIA_READ(VIA_PCI_DMA_CSR0 + engine*0x04)) & VIA_DMA_CSR_TD); - done_transfer = done_transfer || ( blitq->aborting && !(status & VIA_DMA_CSR_DE)); + ((status = VIA_READ(VIA_PCI_DMA_CSR0 + engine*0x04)) & VIA_DMA_CSR_TD); + done_transfer = done_transfer || (blitq->aborting && !(status & VIA_DMA_CSR_DE)); cur = blitq->cur; if (done_transfer) { @@ -377,18 +376,16 @@ via_dmablit_handler(struct drm_device *dev, int engine, int from_irq) if (!timer_pending(&blitq->poll_timer)) mod_timer(&blitq->poll_timer, jiffies + 1); } else { - if (timer_pending(&blitq->poll_timer)) { + if (timer_pending(&blitq->poll_timer)) del_timer(&blitq->poll_timer); - } via_dmablit_engine_off(dev, engine); } } - if (from_irq) { + if (from_irq) spin_unlock(&blitq->blit_lock); - } else { + else spin_unlock_irqrestore(&blitq->blit_lock, irqsave); - } } @@ -414,10 +411,9 @@ via_dmablit_active(drm_via_blitq_t *blitq, int engine, uint32_t handle, wait_que ((blitq->cur_blit_handle - handle) <= (1 << 23)); if (queue && active) { - slot = handle - blitq->done_blit_handle + blitq->cur -1; - if (slot >= VIA_NUM_BLIT_SLOTS) { + slot = handle - blitq->done_blit_handle + blitq->cur - 1; + if (slot >= VIA_NUM_BLIT_SLOTS) slot -= VIA_NUM_BLIT_SLOTS; - } *queue = blitq->blit_queue + slot; } @@ -506,12 +502,12 @@ via_dmablit_workqueue(struct work_struct *work) int cur_released; - DRM_DEBUG("Workqueue task called for blit engine %ld\n",(unsigned long) + DRM_DEBUG("Workqueue task called for blit engine %ld\n", (unsigned long) (blitq - ((drm_via_private_t *)dev->dev_private)->blit_queues)); spin_lock_irqsave(&blitq->blit_lock, irqsave); - while(blitq->serviced != blitq->cur) { + while (blitq->serviced != blitq->cur) { cur_released = blitq->serviced++; @@ -545,13 +541,13 @@ via_dmablit_workqueue(struct work_struct *work) void via_init_dmablit(struct drm_device *dev) { - int i,j; + int i, j; drm_via_private_t *dev_priv = (drm_via_private_t *)dev->dev_private; drm_via_blitq_t *blitq; pci_set_master(dev->pdev); - for (i=0; i< VIA_NUM_BLIT_ENGINES; ++i) { + for (i = 0; i < VIA_NUM_BLIT_ENGINES; ++i) { blitq = dev_priv->blit_queues + i; blitq->dev = dev; blitq->cur_blit_handle = 0; @@ -564,9 +560,8 @@ via_init_dmablit(struct drm_device *dev) blitq->is_active = 0; blitq->aborting = 0; spin_lock_init(&blitq->blit_lock); - for (j=0; j<VIA_NUM_BLIT_SLOTS; ++j) { + for (j = 0; j < VIA_NUM_BLIT_SLOTS; ++j) DRM_INIT_WAITQUEUE(blitq->blit_queue + j); - } DRM_INIT_WAITQUEUE(&blitq->busy_queue); INIT_WORK(&blitq->wq, via_dmablit_workqueue); setup_timer(&blitq->poll_timer, via_dmablit_timer, @@ -685,18 +680,17 @@ via_build_sg_info(struct drm_device *dev, drm_via_sg_info_t *vsg, drm_via_dmabli static int via_dmablit_grab_slot(drm_via_blitq_t *blitq, int engine) { - int ret=0; + int ret = 0; unsigned long irqsave; DRM_DEBUG("Num free is %d\n", blitq->num_free); spin_lock_irqsave(&blitq->blit_lock, irqsave); - while(blitq->num_free == 0) { + while (blitq->num_free == 0) { spin_unlock_irqrestore(&blitq->blit_lock, irqsave); DRM_WAIT_ON(ret, blitq->busy_queue, DRM_HZ, blitq->num_free > 0); - if (ret) { + if (ret) return (-EINTR == ret) ? -EAGAIN : ret; - } spin_lock_irqsave(&blitq->blit_lock, irqsave); } @@ -719,7 +713,7 @@ via_dmablit_release_slot(drm_via_blitq_t *blitq) spin_lock_irqsave(&blitq->blit_lock, irqsave); blitq->num_free++; spin_unlock_irqrestore(&blitq->blit_lock, irqsave); - DRM_WAKEUP( &blitq->busy_queue ); + DRM_WAKEUP(&blitq->busy_queue); } /* @@ -744,9 +738,8 @@ via_dmablit(struct drm_device *dev, drm_via_dmablit_t *xfer) engine = (xfer->to_fb) ? 0 : 1; blitq = dev_priv->blit_queues + engine; - if (0 != (ret = via_dmablit_grab_slot(blitq, engine))) { + if (0 != (ret = via_dmablit_grab_slot(blitq, engine))) return ret; - } if (NULL == (vsg = kmalloc(sizeof(*vsg), GFP_KERNEL))) { via_dmablit_release_slot(blitq); return -ENOMEM; @@ -780,7 +773,7 @@ via_dmablit(struct drm_device *dev, drm_via_dmablit_t *xfer) */ int -via_dma_blit_sync( struct drm_device *dev, void *data, struct drm_file *file_priv ) +via_dma_blit_sync(struct drm_device *dev, void *data, struct drm_file *file_priv) { drm_via_blitsync_t *sync = data; int err; @@ -804,7 +797,7 @@ via_dma_blit_sync( struct drm_device *dev, void *data, struct drm_file *file_pri */ int -via_dma_blit( struct drm_device *dev, void *data, struct drm_file *file_priv ) +via_dma_blit(struct drm_device *dev, void *data, struct drm_file *file_priv) { drm_via_dmablit_t *xfer = data; int err; diff --git a/drivers/gpu/drm/via/via_dmablit.h b/drivers/gpu/drm/via/via_dmablit.h index 7408a547a03..9b662a327ce 100644 --- a/drivers/gpu/drm/via/via_dmablit.h +++ b/drivers/gpu/drm/via/via_dmablit.h @@ -45,12 +45,12 @@ typedef struct _drm_via_sg_info { int num_desc; enum dma_data_direction direction; unsigned char *bounce_buffer; - dma_addr_t chain_start; + dma_addr_t chain_start; uint32_t free_on_sequence; - unsigned int descriptors_per_page; + unsigned int descriptors_per_page; int aborted; enum { - dr_via_device_mapped, + dr_via_device_mapped, dr_via_desc_pages_alloc, dr_via_pages_locked, dr_via_pages_alloc, @@ -68,7 +68,7 @@ typedef struct _drm_via_blitq { unsigned num_free; unsigned num_outstanding; unsigned long end; - int aborting; + int aborting; int is_active; drm_via_sg_info_t *blits[VIA_NUM_BLIT_SLOTS]; spinlock_t blit_lock; diff --git a/drivers/gpu/drm/via/via_drv.h b/drivers/gpu/drm/via/via_drv.h index cafcb844a22..9cf87d91232 100644 --- a/drivers/gpu/drm/via/via_drv.h +++ b/drivers/gpu/drm/via/via_drv.h @@ -107,9 +107,9 @@ enum via_family { #define VIA_BASE ((dev_priv->mmio)) #define VIA_READ(reg) DRM_READ32(VIA_BASE, reg) -#define VIA_WRITE(reg,val) DRM_WRITE32(VIA_BASE, reg, val) +#define VIA_WRITE(reg, val) DRM_WRITE32(VIA_BASE, reg, val) #define VIA_READ8(reg) DRM_READ8(VIA_BASE, reg) -#define VIA_WRITE8(reg,val) DRM_WRITE8(VIA_BASE, reg, val) +#define VIA_WRITE8(reg, val) DRM_WRITE8(VIA_BASE, reg, val) extern struct drm_ioctl_desc via_ioctls[]; extern int via_max_ioctl; @@ -121,28 +121,28 @@ extern int via_agp_init(struct drm_device *dev, void *data, struct drm_file *fil extern int via_map_init(struct drm_device *dev, void *data, struct drm_file *file_priv); extern int via_decoder_futex(struct drm_device *dev, void *data, struct drm_file *file_priv); extern int via_wait_irq(struct drm_device *dev, void *data, struct drm_file *file_priv); -extern int via_dma_blit_sync( struct drm_device *dev, void *data, struct drm_file *file_priv ); -extern int via_dma_blit( struct drm_device *dev, void *data, struct drm_file *file_priv ); +extern int via_dma_blit_sync(struct drm_device *dev, void *data, struct drm_file *file_priv); +extern int via_dma_blit(struct drm_device *dev, void *data, struct drm_file *file_priv); extern int via_driver_load(struct drm_device *dev, unsigned long chipset); extern int via_driver_unload(struct drm_device *dev); -extern int via_init_context(struct drm_device * dev, int context); -extern int via_final_context(struct drm_device * dev, int context); +extern int via_init_context(struct drm_device *dev, int context); +extern int via_final_context(struct drm_device *dev, int context); -extern int via_do_cleanup_map(struct drm_device * dev); +extern int via_do_cleanup_map(struct drm_device *dev); extern u32 via_get_vblank_counter(struct drm_device *dev, int crtc); extern int via_enable_vblank(struct drm_device *dev, int crtc); extern void via_disable_vblank(struct drm_device *dev, int crtc); extern irqreturn_t via_driver_irq_handler(DRM_IRQ_ARGS); -extern void via_driver_irq_preinstall(struct drm_device * dev); +extern void via_driver_irq_preinstall(struct drm_device *dev); extern int via_driver_irq_postinstall(struct drm_device *dev); -extern void via_driver_irq_uninstall(struct drm_device * dev); +extern void via_driver_irq_uninstall(struct drm_device *dev); -extern int via_dma_cleanup(struct drm_device * dev); +extern int via_dma_cleanup(struct drm_device *dev); extern void via_init_command_verifier(void); -extern int via_driver_dma_quiescent(struct drm_device * dev); +extern int via_driver_dma_quiescent(struct drm_device *dev); extern void via_init_futex(drm_via_private_t *dev_priv); extern void via_cleanup_futex(drm_via_private_t *dev_priv); extern void via_release_futex(drm_via_private_t *dev_priv, int context); diff --git a/drivers/gpu/drm/via/via_irq.c b/drivers/gpu/drm/via/via_irq.c index 34079f251cd..d391f48ef87 100644 --- a/drivers/gpu/drm/via/via_irq.c +++ b/drivers/gpu/drm/via/via_irq.c @@ -141,11 +141,10 @@ irqreturn_t via_driver_irq_handler(DRM_IRQ_ARGS) atomic_inc(&cur_irq->irq_received); DRM_WAKEUP(&cur_irq->irq_queue); handled = 1; - if (dev_priv->irq_map[drm_via_irq_dma0_td] == i) { + if (dev_priv->irq_map[drm_via_irq_dma0_td] == i) via_dmablit_handler(dev, 0, 1); - } else if (dev_priv->irq_map[drm_via_irq_dma1_td] == i) { + else if (dev_priv->irq_map[drm_via_irq_dma1_td] == i) via_dmablit_handler(dev, 1, 1); - } } cur_irq++; } @@ -160,7 +159,7 @@ irqreturn_t via_driver_irq_handler(DRM_IRQ_ARGS) return IRQ_NONE; } -static __inline__ void viadrv_acknowledge_irqs(drm_via_private_t * dev_priv) +static __inline__ void viadrv_acknowledge_irqs(drm_via_private_t *dev_priv) { u32 status; @@ -207,7 +206,7 @@ void via_disable_vblank(struct drm_device *dev, int crtc) } static int -via_driver_irq_wait(struct drm_device * dev, unsigned int irq, int force_sequence, +via_driver_irq_wait(struct drm_device *dev, unsigned int irq, int force_sequence, unsigned int *sequence) { drm_via_private_t *dev_priv = (drm_via_private_t *) dev->dev_private; @@ -260,7 +259,7 @@ via_driver_irq_wait(struct drm_device * dev, unsigned int irq, int force_sequenc * drm_dma.h hooks */ -void via_driver_irq_preinstall(struct drm_device * dev) +void via_driver_irq_preinstall(struct drm_device *dev) { drm_via_private_t *dev_priv = (drm_via_private_t *) dev->dev_private; u32 status; @@ -329,7 +328,7 @@ int via_driver_irq_postinstall(struct drm_device *dev) return 0; } -void via_driver_irq_uninstall(struct drm_device * dev) +void via_driver_irq_uninstall(struct drm_device *dev) { drm_via_private_t *dev_priv = (drm_via_private_t *) dev->dev_private; u32 status; diff --git a/drivers/gpu/drm/via/via_map.c b/drivers/gpu/drm/via/via_map.c index 6e6f9159163..6cca9a709f7 100644 --- a/drivers/gpu/drm/via/via_map.c +++ b/drivers/gpu/drm/via/via_map.c @@ -25,7 +25,7 @@ #include "via_drm.h" #include "via_drv.h" -static int via_do_init_map(struct drm_device * dev, drm_via_init_t * init) +static int via_do_init_map(struct drm_device *dev, drm_via_init_t *init) { drm_via_private_t *dev_priv = dev->dev_private; @@ -68,7 +68,7 @@ static int via_do_init_map(struct drm_device * dev, drm_via_init_t * init) return 0; } -int via_do_cleanup_map(struct drm_device * dev) +int via_do_cleanup_map(struct drm_device *dev) { via_dma_cleanup(dev); diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c index f694cb5eded..6cc2dadae3e 100644 --- a/drivers/gpu/drm/via/via_mm.c +++ b/drivers/gpu/drm/via/via_mm.c @@ -31,7 +31,7 @@ #include "drm_sman.h" #define VIA_MM_ALIGN_SHIFT 4 -#define VIA_MM_ALIGN_MASK ( (1 << VIA_MM_ALIGN_SHIFT) - 1) +#define VIA_MM_ALIGN_MASK ((1 << VIA_MM_ALIGN_SHIFT) - 1) int via_agp_init(struct drm_device *dev, void *data, struct drm_file *file_priv) { @@ -172,7 +172,7 @@ int via_mem_free(struct drm_device *dev, void *data, struct drm_file *file_priv) } -void via_reclaim_buffers_locked(struct drm_device * dev, +void via_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv) { drm_via_private_t *dev_priv = dev->dev_private; @@ -183,9 +183,8 @@ void via_reclaim_buffers_locked(struct drm_device * dev, return; } - if (dev->driver->dma_quiescent) { + if (dev->driver->dma_quiescent) dev->driver->dma_quiescent(dev); - } drm_sman_owner_cleanup(&dev_priv->sman, (unsigned long)file_priv); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/via/via_verifier.c b/drivers/gpu/drm/via/via_verifier.c index 46a57919874..48957b856d4 100644 --- a/drivers/gpu/drm/via/via_verifier.c +++ b/drivers/gpu/drm/via/via_verifier.c @@ -235,7 +235,7 @@ static hazard_t table2[256]; static hazard_t table3[256]; static __inline__ int -eat_words(const uint32_t ** buf, const uint32_t * buf_end, unsigned num_words) +eat_words(const uint32_t **buf, const uint32_t *buf_end, unsigned num_words) { if ((buf_end - *buf) >= num_words) { *buf += num_words; @@ -252,7 +252,7 @@ eat_words(const uint32_t ** buf, const uint32_t * buf_end, unsigned num_words) static __inline__ drm_local_map_t *via_drm_lookup_agp_map(drm_via_state_t *seq, unsigned long offset, unsigned long size, - struct drm_device * dev) + struct drm_device *dev) { struct drm_map_list *r_list; drm_local_map_t *map = seq->map_cache; @@ -344,7 +344,7 @@ static __inline__ int finish_current_sequence(drm_via_state_t * cur_seq) } static __inline__ int -investigate_hazard(uint32_t cmd, hazard_t hz, drm_via_state_t * cur_seq) +investigate_hazard(uint32_t cmd, hazard_t hz, drm_via_state_t *cur_seq) { register uint32_t tmp, *tmp_addr; @@ -518,7 +518,7 @@ investigate_hazard(uint32_t cmd, hazard_t hz, drm_via_state_t * cur_seq) static __inline__ int via_check_prim_list(uint32_t const **buffer, const uint32_t * buf_end, - drm_via_state_t * cur_seq) + drm_via_state_t *cur_seq) { drm_via_private_t *dev_priv = (drm_via_private_t *) cur_seq->dev->dev_private; @@ -621,8 +621,8 @@ via_check_prim_list(uint32_t const **buffer, const uint32_t * buf_end, } static __inline__ verifier_state_t -via_check_header2(uint32_t const **buffer, const uint32_t * buf_end, - drm_via_state_t * hc_state) +via_check_header2(uint32_t const **buffer, const uint32_t *buf_end, + drm_via_state_t *hc_state) { uint32_t cmd; int hz_mode; @@ -706,16 +706,15 @@ via_check_header2(uint32_t const **buffer, const uint32_t * buf_end, return state_error; } } - if (hc_state->unfinished && finish_current_sequence(hc_state)) { + if (hc_state->unfinished && finish_current_sequence(hc_state)) return state_error; - } *buffer = buf; return state_command; } static __inline__ verifier_state_t -via_parse_header2(drm_via_private_t * dev_priv, uint32_t const **buffer, - const uint32_t * buf_end, int *fire_count) +via_parse_header2(drm_via_private_t *dev_priv, uint32_t const **buffer, + const uint32_t *buf_end, int *fire_count) { uint32_t cmd; const uint32_t *buf = *buffer; @@ -833,8 +832,8 @@ via_check_header1(uint32_t const **buffer, const uint32_t * buf_end) } static __inline__ verifier_state_t -via_parse_header1(drm_via_private_t * dev_priv, uint32_t const **buffer, - const uint32_t * buf_end) +via_parse_header1(drm_via_private_t *dev_priv, uint32_t const **buffer, + const uint32_t *buf_end) { register uint32_t cmd; const uint32_t *buf = *buffer; @@ -851,7 +850,7 @@ via_parse_header1(drm_via_private_t * dev_priv, uint32_t const **buffer, } static __inline__ verifier_state_t -via_check_vheader5(uint32_t const **buffer, const uint32_t * buf_end) +via_check_vheader5(uint32_t const **buffer, const uint32_t *buf_end) { uint32_t data; const uint32_t *buf = *buffer; @@ -884,8 +883,8 @@ via_check_vheader5(uint32_t const **buffer, const uint32_t * buf_end) } static __inline__ verifier_state_t -via_parse_vheader5(drm_via_private_t * dev_priv, uint32_t const **buffer, - const uint32_t * buf_end) +via_parse_vheader5(drm_via_private_t *dev_priv, uint32_t const **buffer, + const uint32_t *buf_end) { uint32_t addr, count, i; const uint32_t *buf = *buffer; @@ -893,9 +892,8 @@ via_parse_vheader5(drm_via_private_t * dev_priv, uint32_t const **buffer, addr = *buf++ & ~VIA_VIDEOMASK; i = count = *buf; buf += 3; - while (i--) { + while (i--) VIA_WRITE(addr, *buf++); - } if (count & 3) buf += 4 - (count & 3); *buffer = buf; @@ -940,8 +938,8 @@ via_check_vheader6(uint32_t const **buffer, const uint32_t * buf_end) } static __inline__ verifier_state_t -via_parse_vheader6(drm_via_private_t * dev_priv, uint32_t const **buffer, - const uint32_t * buf_end) +via_parse_vheader6(drm_via_private_t *dev_priv, uint32_t const **buffer, + const uint32_t *buf_end) { uint32_t addr, count, i; @@ -1037,7 +1035,7 @@ via_verify_command_stream(const uint32_t * buf, unsigned int size, } int -via_parse_command_stream(struct drm_device * dev, const uint32_t * buf, +via_parse_command_stream(struct drm_device *dev, const uint32_t *buf, unsigned int size) { @@ -1085,9 +1083,8 @@ via_parse_command_stream(struct drm_device * dev, const uint32_t * buf, return -EINVAL; } } - if (state == state_error) { + if (state == state_error) return -EINVAL; - } return 0; } @@ -1096,13 +1093,11 @@ setup_hazard_table(hz_init_t init_table[], hazard_t table[], int size) { int i; - for (i = 0; i < 256; ++i) { + for (i = 0; i < 256; ++i) table[i] = forbidden_command; - } - for (i = 0; i < size; ++i) { + for (i = 0; i < size; ++i) table[init_table[i].code] = init_table[i].hz; - } } void via_init_command_verifier(void) diff --git a/drivers/gpu/drm/via/via_verifier.h b/drivers/gpu/drm/via/via_verifier.h index d6f8214b69f..26b6d361ab9 100644 --- a/drivers/gpu/drm/via/via_verifier.h +++ b/drivers/gpu/drm/via/via_verifier.h @@ -54,8 +54,8 @@ typedef struct { const uint32_t *buf_start; } drm_via_state_t; -extern int via_verify_command_stream(const uint32_t * buf, unsigned int size, - struct drm_device * dev, int agp); +extern int via_verify_command_stream(const uint32_t *buf, unsigned int size, + struct drm_device *dev, int agp); extern int via_parse_command_stream(struct drm_device *dev, const uint32_t *buf, unsigned int size); diff --git a/drivers/gpu/drm/via/via_video.c b/drivers/gpu/drm/via/via_video.c index 6efac8117c9..675d311f038 100644 --- a/drivers/gpu/drm/via/via_video.c +++ b/drivers/gpu/drm/via/via_video.c @@ -29,7 +29,7 @@ #include "via_drm.h" #include "via_drv.h" -void via_init_futex(drm_via_private_t * dev_priv) +void via_init_futex(drm_via_private_t *dev_priv) { unsigned int i; @@ -41,11 +41,11 @@ void via_init_futex(drm_via_private_t * dev_priv) } } -void via_cleanup_futex(drm_via_private_t * dev_priv) +void via_cleanup_futex(drm_via_private_t *dev_priv) { } -void via_release_futex(drm_via_private_t * dev_priv, int context) +void via_release_futex(drm_via_private_t *dev_priv, int context) { unsigned int i; volatile int *lock; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index b793c8c9acb..9dd395b9021 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -764,7 +764,7 @@ static struct drm_driver driver = { static int vmw_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { - return drm_get_dev(pdev, ent, &driver); + return drm_get_pci_dev(pdev, ent, &driver); } static int __init vmwgfx_init(void) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index eaad5209533..429f917b60b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -164,7 +164,7 @@ struct vmw_vga_topology_state { struct vmw_private { struct ttm_bo_device bdev; struct ttm_bo_global_ref bo_global_ref; - struct ttm_global_reference mem_global_ref; + struct drm_global_reference mem_global_ref; struct vmw_fifo_state fifo; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index b0866f04ec7..870967a97c1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -528,7 +528,7 @@ int vmw_fb_init(struct vmw_private *vmw_priv) * Dirty & Deferred IO */ par->dirty.x1 = par->dirty.x2 = 0; - par->dirty.y1 = par->dirty.y1 = 0; + par->dirty.y1 = par->dirty.y2 = 0; par->dirty.active = true; spin_lock_init(&par->dirty.lock); info->fbdefio = &vmw_defio; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c index e3df4adfb4d..83123287c60 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c @@ -44,29 +44,29 @@ int vmw_mmap(struct file *filp, struct vm_area_struct *vma) return ttm_bo_mmap(filp, vma, &dev_priv->bdev); } -static int vmw_ttm_mem_global_init(struct ttm_global_reference *ref) +static int vmw_ttm_mem_global_init(struct drm_global_reference *ref) { DRM_INFO("global init.\n"); return ttm_mem_global_init(ref->object); } -static void vmw_ttm_mem_global_release(struct ttm_global_reference *ref) +static void vmw_ttm_mem_global_release(struct drm_global_reference *ref) { ttm_mem_global_release(ref->object); } int vmw_ttm_global_init(struct vmw_private *dev_priv) { - struct ttm_global_reference *global_ref; + struct drm_global_reference *global_ref; int ret; global_ref = &dev_priv->mem_global_ref; - global_ref->global_type = TTM_GLOBAL_TTM_MEM; + global_ref->global_type = DRM_GLOBAL_TTM_MEM; global_ref->size = sizeof(struct ttm_mem_global); global_ref->init = &vmw_ttm_mem_global_init; global_ref->release = &vmw_ttm_mem_global_release; - ret = ttm_global_item_ref(global_ref); + ret = drm_global_item_ref(global_ref); if (unlikely(ret != 0)) { DRM_ERROR("Failed setting up TTM memory accounting.\n"); return ret; @@ -75,11 +75,11 @@ int vmw_ttm_global_init(struct vmw_private *dev_priv) dev_priv->bo_global_ref.mem_glob = dev_priv->mem_global_ref.object; global_ref = &dev_priv->bo_global_ref.ref; - global_ref->global_type = TTM_GLOBAL_TTM_BO; + global_ref->global_type = DRM_GLOBAL_TTM_BO; global_ref->size = sizeof(struct ttm_bo_global); global_ref->init = &ttm_bo_global_init; global_ref->release = &ttm_bo_global_release; - ret = ttm_global_item_ref(global_ref); + ret = drm_global_item_ref(global_ref); if (unlikely(ret != 0)) { DRM_ERROR("Failed setting up TTM buffer objects.\n"); @@ -88,12 +88,12 @@ int vmw_ttm_global_init(struct vmw_private *dev_priv) return 0; out_no_bo: - ttm_global_item_unref(&dev_priv->mem_global_ref); + drm_global_item_unref(&dev_priv->mem_global_ref); return ret; } void vmw_ttm_global_release(struct vmw_private *dev_priv) { - ttm_global_item_unref(&dev_priv->bo_global_ref.ref); - ttm_global_item_unref(&dev_priv->mem_global_ref); + drm_global_item_unref(&dev_priv->bo_global_ref.ref); + drm_global_item_unref(&dev_priv->mem_global_ref); } diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index c57e530d07c..4d382ae5309 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -407,6 +407,13 @@ config SENSORS_CORETEMP sensor inside your CPU. Most of the family 6 CPUs are supported. Check documentation/driver for details. +config SENSORS_PKGTEMP + tristate "Intel processor package temperature sensor" + depends on X86 && PCI && EXPERIMENTAL + help + If you say yes here you get support for the package level temperature + sensor inside your CPU. Check documentation/driver for details. + config SENSORS_IBMAEM tristate "IBM Active Energy Manager temperature/power sensors and control" select IPMI_SI diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index c5057745b06..9103bd6ea73 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -39,6 +39,7 @@ obj-$(CONFIG_SENSORS_AMS) += ams/ obj-$(CONFIG_SENSORS_ASC7621) += asc7621.o obj-$(CONFIG_SENSORS_ATXP1) += atxp1.o obj-$(CONFIG_SENSORS_CORETEMP) += coretemp.o +obj-$(CONFIG_SENSORS_PKGTEMP) += pkgtemp.o obj-$(CONFIG_SENSORS_DME1737) += dme1737.o obj-$(CONFIG_SENSORS_DS1621) += ds1621.o obj-$(CONFIG_SENSORS_EMC1403) += emc1403.o diff --git a/drivers/hwmon/pkgtemp.c b/drivers/hwmon/pkgtemp.c new file mode 100644 index 00000000000..74157fcda6e --- /dev/null +++ b/drivers/hwmon/pkgtemp.c @@ -0,0 +1,456 @@ +/* + * pkgtemp.c - Linux kernel module for processor package hardware monitoring + * + * Copyright (C) 2010 Fenghua Yu <fenghua.yu@intel.com> + * + * Inspired from many hwmon drivers especially coretemp. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301 USA. + */ + +#include <linux/module.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/jiffies.h> +#include <linux/hwmon.h> +#include <linux/sysfs.h> +#include <linux/hwmon-sysfs.h> +#include <linux/err.h> +#include <linux/mutex.h> +#include <linux/list.h> +#include <linux/platform_device.h> +#include <linux/cpu.h> +#include <linux/pci.h> +#include <asm/msr.h> +#include <asm/processor.h> + +#define DRVNAME "pkgtemp" + +enum { SHOW_TEMP, SHOW_TJMAX, SHOW_TTARGET, SHOW_LABEL, SHOW_NAME }; + +/* + * Functions declaration + */ + +static struct pkgtemp_data *pkgtemp_update_device(struct device *dev); + +struct pkgtemp_data { + struct device *hwmon_dev; + struct mutex update_lock; + const char *name; + u32 id; + u16 phys_proc_id; + char valid; /* zero until following fields are valid */ + unsigned long last_updated; /* in jiffies */ + int temp; + int tjmax; + int ttarget; + u8 alarm; +}; + +/* + * Sysfs stuff + */ + +static ssize_t show_name(struct device *dev, struct device_attribute + *devattr, char *buf) +{ + int ret; + struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); + struct pkgtemp_data *data = dev_get_drvdata(dev); + + if (attr->index == SHOW_NAME) + ret = sprintf(buf, "%s\n", data->name); + else /* show label */ + ret = sprintf(buf, "physical id %d\n", + data->phys_proc_id); + return ret; +} + +static ssize_t show_alarm(struct device *dev, struct device_attribute + *devattr, char *buf) +{ + struct pkgtemp_data *data = pkgtemp_update_device(dev); + /* read the Out-of-spec log, never clear */ + return sprintf(buf, "%d\n", data->alarm); +} + +static ssize_t show_temp(struct device *dev, + struct device_attribute *devattr, char *buf) +{ + struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); + struct pkgtemp_data *data = pkgtemp_update_device(dev); + int err = 0; + + if (attr->index == SHOW_TEMP) + err = data->valid ? sprintf(buf, "%d\n", data->temp) : -EAGAIN; + else if (attr->index == SHOW_TJMAX) + err = sprintf(buf, "%d\n", data->tjmax); + else + err = sprintf(buf, "%d\n", data->ttarget); + return err; +} + +static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL, SHOW_TEMP); +static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp, NULL, SHOW_TJMAX); +static SENSOR_DEVICE_ATTR(temp1_max, S_IRUGO, show_temp, NULL, SHOW_TTARGET); +static DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, show_alarm, NULL); +static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, show_name, NULL, SHOW_LABEL); +static SENSOR_DEVICE_ATTR(name, S_IRUGO, show_name, NULL, SHOW_NAME); + +static struct attribute *pkgtemp_attributes[] = { + &sensor_dev_attr_name.dev_attr.attr, + &sensor_dev_attr_temp1_label.dev_attr.attr, + &dev_attr_temp1_crit_alarm.attr, + &sensor_dev_attr_temp1_input.dev_attr.attr, + &sensor_dev_attr_temp1_crit.dev_attr.attr, + NULL +}; + +static const struct attribute_group pkgtemp_group = { + .attrs = pkgtemp_attributes, +}; + +static struct pkgtemp_data *pkgtemp_update_device(struct device *dev) +{ + struct pkgtemp_data *data = dev_get_drvdata(dev); + unsigned int cpu; + int err; + + mutex_lock(&data->update_lock); + + if (!data->valid || time_after(jiffies, data->last_updated + HZ)) { + u32 eax, edx; + + data->valid = 0; + cpu = data->id; + err = rdmsr_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_STATUS, + &eax, &edx); + if (!err) { + data->alarm = (eax >> 5) & 1; + data->temp = data->tjmax - (((eax >> 16) + & 0x7f) * 1000); + data->valid = 1; + } else + dev_dbg(dev, "Temperature data invalid (0x%x)\n", eax); + + data->last_updated = jiffies; + } + + mutex_unlock(&data->update_lock); + return data; +} + +static int get_tjmax(int cpu, struct device *dev) +{ + int default_tjmax = 100000; + int err; + u32 eax, edx; + u32 val; + + /* IA32_TEMPERATURE_TARGET contains the TjMax value */ + err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx); + if (!err) { + val = (eax >> 16) & 0xff; + if ((val > 80) && (val < 120)) { + dev_info(dev, "TjMax is %d C.\n", val); + return val * 1000; + } + } + dev_warn(dev, "Unable to read TjMax from CPU.\n"); + return default_tjmax; +} + +static int __devinit pkgtemp_probe(struct platform_device *pdev) +{ + struct pkgtemp_data *data; + int err; + u32 eax, edx; +#ifdef CONFIG_SMP + struct cpuinfo_x86 *c = &cpu_data(pdev->id); +#endif + + data = kzalloc(sizeof(struct pkgtemp_data), GFP_KERNEL); + if (!data) { + err = -ENOMEM; + dev_err(&pdev->dev, "Out of memory\n"); + goto exit; + } + + data->id = pdev->id; +#ifdef CONFIG_SMP + data->phys_proc_id = c->phys_proc_id; +#endif + data->name = "pkgtemp"; + mutex_init(&data->update_lock); + + /* test if we can access the THERM_STATUS MSR */ + err = rdmsr_safe_on_cpu(data->id, MSR_IA32_PACKAGE_THERM_STATUS, + &eax, &edx); + if (err) { + dev_err(&pdev->dev, + "Unable to access THERM_STATUS MSR, giving up\n"); + goto exit_free; + } + + data->tjmax = get_tjmax(data->id, &pdev->dev); + platform_set_drvdata(pdev, data); + + err = rdmsr_safe_on_cpu(data->id, MSR_IA32_TEMPERATURE_TARGET, + &eax, &edx); + if (err) { + dev_warn(&pdev->dev, "Unable to read" + " IA32_TEMPERATURE_TARGET MSR\n"); + } else { + data->ttarget = data->tjmax - (((eax >> 8) & 0xff) * 1000); + err = device_create_file(&pdev->dev, + &sensor_dev_attr_temp1_max.dev_attr); + if (err) + goto exit_free; + } + + err = sysfs_create_group(&pdev->dev.kobj, &pkgtemp_group); + if (err) + goto exit_free; + + data->hwmon_dev = hwmon_device_register(&pdev->dev); + if (IS_ERR(data->hwmon_dev)) { + err = PTR_ERR(data->hwmon_dev); + dev_err(&pdev->dev, "Class registration failed (%d)\n", + err); + goto exit_class; + } + + return 0; + +exit_class: + sysfs_remove_group(&pdev->dev.kobj, &pkgtemp_group); +exit_free: + kfree(data); +exit: + return err; +} + +static int __devexit pkgtemp_remove(struct platform_device *pdev) +{ + struct pkgtemp_data *data = platform_get_drvdata(pdev); + + hwmon_device_unregister(data->hwmon_dev); + sysfs_remove_group(&pdev->dev.kobj, &pkgtemp_group); + platform_set_drvdata(pdev, NULL); + kfree(data); + return 0; +} + +static struct platform_driver pkgtemp_driver = { + .driver = { + .owner = THIS_MODULE, + .name = DRVNAME, + }, + .probe = pkgtemp_probe, + .remove = __devexit_p(pkgtemp_remove), +}; + +struct pdev_entry { + struct list_head list; + struct platform_device *pdev; + unsigned int cpu; +#ifdef CONFIG_SMP + u16 phys_proc_id; +#endif +}; + +static LIST_HEAD(pdev_list); +static DEFINE_MUTEX(pdev_list_mutex); + +static int __cpuinit pkgtemp_device_add(unsigned int cpu) +{ + int err; + struct platform_device *pdev; + struct pdev_entry *pdev_entry; +#ifdef CONFIG_SMP + struct cpuinfo_x86 *c = &cpu_data(cpu); +#endif + + mutex_lock(&pdev_list_mutex); + +#ifdef CONFIG_SMP + /* Only keep the first entry in each package */ + list_for_each_entry(pdev_entry, &pdev_list, list) { + if (c->phys_proc_id == pdev_entry->phys_proc_id) { + err = 0; /* Not an error */ + goto exit; + } + } +#endif + + pdev = platform_device_alloc(DRVNAME, cpu); + if (!pdev) { + err = -ENOMEM; + printk(KERN_ERR DRVNAME ": Device allocation failed\n"); + goto exit; + } + + pdev_entry = kzalloc(sizeof(struct pdev_entry), GFP_KERNEL); + if (!pdev_entry) { + err = -ENOMEM; + goto exit_device_put; + } + + err = platform_device_add(pdev); + if (err) { + printk(KERN_ERR DRVNAME ": Device addition failed (%d)\n", + err); + goto exit_device_free; + } + +#ifdef CONFIG_SMP + pdev_entry->phys_proc_id = c->phys_proc_id; +#endif + pdev_entry->pdev = pdev; + pdev_entry->cpu = cpu; + list_add_tail(&pdev_entry->list, &pdev_list); + mutex_unlock(&pdev_list_mutex); + + return 0; + +exit_device_free: + kfree(pdev_entry); +exit_device_put: + platform_device_put(pdev); +exit: + mutex_unlock(&pdev_list_mutex); + return err; +} + +#ifdef CONFIG_HOTPLUG_CPU +static void pkgtemp_device_remove(unsigned int cpu) +{ + struct pdev_entry *p, *n; + unsigned int i; + int err; + + mutex_lock(&pdev_list_mutex); + list_for_each_entry_safe(p, n, &pdev_list, list) { + if (p->cpu != cpu) + continue; + + platform_device_unregister(p->pdev); + list_del(&p->list); + kfree(p); + for_each_cpu(i, cpu_core_mask(cpu)) { + if (i != cpu) { + err = pkgtemp_device_add(i); + if (!err) + break; + } + } + break; + } + mutex_unlock(&pdev_list_mutex); +} + +static int __cpuinit pkgtemp_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long) hcpu; + + switch (action) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + pkgtemp_device_add(cpu); + break; + case CPU_DOWN_PREPARE: + pkgtemp_device_remove(cpu); + break; + } + return NOTIFY_OK; +} + +static struct notifier_block pkgtemp_cpu_notifier __refdata = { + .notifier_call = pkgtemp_cpu_callback, +}; +#endif /* !CONFIG_HOTPLUG_CPU */ + +static int __init pkgtemp_init(void) +{ + int i, err = -ENODEV; + struct pdev_entry *p, *n; + + /* quick check if we run Intel */ + if (cpu_data(0).x86_vendor != X86_VENDOR_INTEL) + goto exit; + + err = platform_driver_register(&pkgtemp_driver); + if (err) + goto exit; + + for_each_online_cpu(i) { + struct cpuinfo_x86 *c = &cpu_data(i); + + if (!cpu_has(c, X86_FEATURE_PTS)) + continue; + + err = pkgtemp_device_add(i); + if (err) + goto exit_devices_unreg; + } + if (list_empty(&pdev_list)) { + err = -ENODEV; + goto exit_driver_unreg; + } + +#ifdef CONFIG_HOTPLUG_CPU + register_hotcpu_notifier(&pkgtemp_cpu_notifier); +#endif + return 0; + +exit_devices_unreg: + mutex_lock(&pdev_list_mutex); + list_for_each_entry_safe(p, n, &pdev_list, list) { + platform_device_unregister(p->pdev); + list_del(&p->list); + kfree(p); + } + mutex_unlock(&pdev_list_mutex); +exit_driver_unreg: + platform_driver_unregister(&pkgtemp_driver); +exit: + return err; +} + +static void __exit pkgtemp_exit(void) +{ + struct pdev_entry *p, *n; +#ifdef CONFIG_HOTPLUG_CPU + unregister_hotcpu_notifier(&pkgtemp_cpu_notifier); +#endif + mutex_lock(&pdev_list_mutex); + list_for_each_entry_safe(p, n, &pdev_list, list) { + platform_device_unregister(p->pdev); + list_del(&p->list); + kfree(p); + } + mutex_unlock(&pdev_list_mutex); + platform_driver_unregister(&pkgtemp_driver); +} + +MODULE_AUTHOR("Fenghua Yu <fenghua.yu@intel.com>"); +MODULE_DESCRIPTION("Intel processor package temperature monitor"); +MODULE_LICENSE("GPL"); + +module_init(pkgtemp_init) +module_exit(pkgtemp_exit) diff --git a/drivers/hwmon/ultra45_env.c b/drivers/hwmon/ultra45_env.c index 5da5942cf97..89643261ccd 100644 --- a/drivers/hwmon/ultra45_env.c +++ b/drivers/hwmon/ultra45_env.c @@ -311,12 +311,12 @@ static struct of_platform_driver env_driver = { static int __init env_init(void) { - return of_register_driver(&env_driver, &of_bus_type); + return of_register_platform_driver(&env_driver); } static void __exit env_exit(void) { - of_unregister_driver(&env_driver); + of_unregister_platform_driver(&env_driver); } module_init(env_init); diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c index b02b4533651..e591de1bc70 100644 --- a/drivers/i2c/busses/i2c-cpm.c +++ b/drivers/i2c/busses/i2c-cpm.c @@ -652,6 +652,7 @@ static int __devinit cpm_i2c_probe(struct of_device *ofdev, cpm->adap = cpm_ops; i2c_set_adapdata(&cpm->adap, cpm); cpm->adap.dev.parent = &ofdev->dev; + cpm->adap.dev.of_node = of_node_get(ofdev->dev.of_node); result = cpm_i2c_setup(cpm); if (result) { @@ -676,11 +677,6 @@ static int __devinit cpm_i2c_probe(struct of_device *ofdev, dev_dbg(&ofdev->dev, "hw routines for %s registered.\n", cpm->adap.name); - /* - * register OF I2C devices - */ - of_register_i2c_devices(&cpm->adap, ofdev->dev.of_node); - return 0; out_shut: cpm_i2c_shutdown(cpm); diff --git a/drivers/i2c/busses/i2c-ibm_iic.c b/drivers/i2c/busses/i2c-ibm_iic.c index bf344135647..1168d61418c 100644 --- a/drivers/i2c/busses/i2c-ibm_iic.c +++ b/drivers/i2c/busses/i2c-ibm_iic.c @@ -745,6 +745,7 @@ static int __devinit iic_probe(struct of_device *ofdev, /* Register it with i2c layer */ adap = &dev->adap; adap->dev.parent = &ofdev->dev; + adap->dev.of_node = of_node_get(np); strlcpy(adap->name, "IBM IIC", sizeof(adap->name)); i2c_set_adapdata(adap, dev); adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD; @@ -760,9 +761,6 @@ static int __devinit iic_probe(struct of_device *ofdev, dev_info(&ofdev->dev, "using %s mode\n", dev->fast_mode ? "fast (400 kHz)" : "standard (100 kHz)"); - /* Now register all the child nodes */ - of_register_i2c_devices(adap, np); - return 0; error_cleanup: diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c index 54247d475fc..6545d1c99b6 100644 --- a/drivers/i2c/busses/i2c-mpc.c +++ b/drivers/i2c/busses/i2c-mpc.c @@ -625,13 +625,13 @@ static int __devinit fsl_i2c_probe(struct of_device *op, i2c->adap = mpc_ops; i2c_set_adapdata(&i2c->adap, i2c); i2c->adap.dev.parent = &op->dev; + i2c->adap.dev.of_node = of_node_get(op->dev.of_node); result = i2c_add_adapter(&i2c->adap); if (result < 0) { dev_err(i2c->dev, "failed to add adapter\n"); goto fail_add; } - of_register_i2c_devices(&i2c->adap, op->dev.of_node); return result; diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 0815e10da7c..df937df845e 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -30,6 +30,8 @@ #include <linux/init.h> #include <linux/idr.h> #include <linux/mutex.h> +#include <linux/of_i2c.h> +#include <linux/of_device.h> #include <linux/completion.h> #include <linux/hardirq.h> #include <linux/irqflags.h> @@ -70,6 +72,10 @@ static int i2c_device_match(struct device *dev, struct device_driver *drv) if (!client) return 0; + /* Attempt an OF style match */ + if (of_driver_match_device(dev, drv)) + return 1; + driver = to_i2c_driver(drv); /* match on an id table if there is one */ if (driver->id_table) @@ -790,6 +796,9 @@ static int i2c_register_adapter(struct i2c_adapter *adap) if (adap->nr < __i2c_first_dynamic_bus_num) i2c_scan_static_board_info(adap); + /* Register devices from the device tree */ + of_i2c_register_devices(adap); + /* Notify drivers */ mutex_lock(&core_lock); dummy = bus_for_each_drv(&i2c_bus_type, NULL, adap, diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c index 1dacae4b43f..f3bb92e9755 100644 --- a/drivers/input/misc/sparcspkr.c +++ b/drivers/input/misc/sparcspkr.c @@ -353,14 +353,12 @@ static struct of_platform_driver grover_beep_driver = { static int __init sparcspkr_init(void) { - int err = of_register_driver(&bbc_beep_driver, - &of_platform_bus_type); + int err = of_register_platform_driver(&bbc_beep_driver); if (!err) { - err = of_register_driver(&grover_beep_driver, - &of_platform_bus_type); + err = of_register_platform_driver(&grover_beep_driver); if (err) - of_unregister_driver(&bbc_beep_driver); + of_unregister_platform_driver(&bbc_beep_driver); } return err; @@ -368,8 +366,8 @@ static int __init sparcspkr_init(void) static void __exit sparcspkr_exit(void) { - of_unregister_driver(&bbc_beep_driver); - of_unregister_driver(&grover_beep_driver); + of_unregister_platform_driver(&bbc_beep_driver); + of_unregister_platform_driver(&grover_beep_driver); } module_init(sparcspkr_init); diff --git a/drivers/input/serio/i8042-sparcio.h b/drivers/input/serio/i8042-sparcio.h index 04e32f2d124..cb2a24b9474 100644 --- a/drivers/input/serio/i8042-sparcio.h +++ b/drivers/input/serio/i8042-sparcio.h @@ -58,9 +58,9 @@ static int __devinit sparc_i8042_probe(struct of_device *op, const struct of_dev if (!strcmp(dp->name, OBP_PS2KBD_NAME1) || !strcmp(dp->name, OBP_PS2KBD_NAME2)) { struct of_device *kbd = of_find_device_by_node(dp); - unsigned int irq = kbd->irqs[0]; + unsigned int irq = kbd->archdata.irqs[0]; if (irq == 0xffffffff) - irq = op->irqs[0]; + irq = op->archdata.irqs[0]; i8042_kbd_irq = irq; kbd_iobase = of_ioremap(&kbd->resource[0], 0, 8, "kbd"); @@ -68,9 +68,9 @@ static int __devinit sparc_i8042_probe(struct of_device *op, const struct of_dev } else if (!strcmp(dp->name, OBP_PS2MS_NAME1) || !strcmp(dp->name, OBP_PS2MS_NAME2)) { struct of_device *ms = of_find_device_by_node(dp); - unsigned int irq = ms->irqs[0]; + unsigned int irq = ms->archdata.irqs[0]; if (irq == 0xffffffff) - irq = op->irqs[0]; + irq = op->archdata.irqs[0]; i8042_aux_irq = irq; } @@ -116,8 +116,7 @@ static int __init i8042_platform_init(void) if (!kbd_iobase) return -ENODEV; } else { - int err = of_register_driver(&sparc_i8042_driver, - &of_bus_type); + int err = of_register_platform_driver(&sparc_i8042_driver); if (err) return err; @@ -141,7 +140,7 @@ static inline void i8042_platform_exit(void) struct device_node *root = of_find_node_by_path("/"); if (strcmp(root->name, "SUNW,JavaStation-1")) - of_unregister_driver(&sparc_i8042_driver); + of_unregister_platform_driver(&sparc_i8042_driver); } #else /* !CONFIG_PCI */ diff --git a/drivers/input/xen-kbdfront.c b/drivers/input/xen-kbdfront.c index e14081675bb..ebb11907d40 100644 --- a/drivers/input/xen-kbdfront.c +++ b/drivers/input/xen-kbdfront.c @@ -339,7 +339,7 @@ static struct xenbus_driver xenkbd_driver = { static int __init xenkbd_init(void) { - if (!xen_domain()) + if (!xen_pv_domain()) return -ENODEV; /* Nothing to do if running in dom0. */ diff --git a/drivers/macintosh/macio_sysfs.c b/drivers/macintosh/macio_sysfs.c index 6999ce59fd1..6024038a5b9 100644 --- a/drivers/macintosh/macio_sysfs.c +++ b/drivers/macintosh/macio_sysfs.c @@ -41,10 +41,7 @@ compatible_show (struct device *dev, struct device_attribute *attr, char *buf) static ssize_t modalias_show (struct device *dev, struct device_attribute *attr, char *buf) { - struct of_device *ofdev = to_of_device(dev); - int len; - - len = of_device_get_modalias(ofdev, buf, PAGE_SIZE - 2); + int len = of_device_get_modalias(dev, buf, PAGE_SIZE - 2); buf[len] = '\n'; buf[len+1] = 0; diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index ad847a24a67..7b0f3ef50f9 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1533,12 +1533,20 @@ static int __devexit mmc_spi_remove(struct spi_device *spi) return 0; } +#if defined(CONFIG_OF) +static struct of_device_id mmc_spi_of_match_table[] __devinitdata = { + { .compatible = "mmc-spi-slot", }, +}; +#endif static struct spi_driver mmc_spi_driver = { .driver = { .name = "mmc_spi", .bus = &spi_bus_type, .owner = THIS_MODULE, +#if defined(CONFIG_OF) + .of_match_table = mmc_spi_of_match_table, +#endif }, .probe = mmc_spi_probe, .remove = __devexit_p(mmc_spi_remove), diff --git a/drivers/mtd/maps/sun_uflash.c b/drivers/mtd/maps/sun_uflash.c index 0391c2527bd..8984236a8d0 100644 --- a/drivers/mtd/maps/sun_uflash.c +++ b/drivers/mtd/maps/sun_uflash.c @@ -160,12 +160,12 @@ static struct of_platform_driver uflash_driver = { static int __init uflash_init(void) { - return of_register_driver(&uflash_driver, &of_bus_type); + return of_register_platform_driver(&uflash_driver); } static void __exit uflash_exit(void) { - of_unregister_driver(&uflash_driver); + of_unregister_platform_driver(&uflash_driver); } module_init(uflash_init); diff --git a/drivers/net/fsl_pq_mdio.c b/drivers/net/fsl_pq_mdio.c index b4c41d72c42..f53f850b641 100644 --- a/drivers/net/fsl_pq_mdio.c +++ b/drivers/net/fsl_pq_mdio.c @@ -35,6 +35,7 @@ #include <linux/mii.h> #include <linux/phy.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> diff --git a/drivers/net/ibm_newemac/core.c b/drivers/net/ibm_newemac/core.c index 0f1d4e96cf8..eeec7bc2ce7 100644 --- a/drivers/net/ibm_newemac/core.c +++ b/drivers/net/ibm_newemac/core.c @@ -2339,11 +2339,11 @@ static int __devinit emac_wait_deps(struct emac_instance *dev) deps[EMAC_DEP_MDIO_IDX].phandle = dev->mdio_ph; if (dev->blist && dev->blist > emac_boot_list) deps[EMAC_DEP_PREV_IDX].phandle = 0xffffffffu; - bus_register_notifier(&of_platform_bus_type, &emac_of_bus_notifier); + bus_register_notifier(&platform_bus_type, &emac_of_bus_notifier); wait_event_timeout(emac_probe_wait, emac_check_deps(dev, deps), EMAC_PROBE_DEP_TIMEOUT); - bus_unregister_notifier(&of_platform_bus_type, &emac_of_bus_notifier); + bus_unregister_notifier(&platform_bus_type, &emac_of_bus_notifier); err = emac_check_deps(dev, deps) ? 0 : -ENODEV; for (i = 0; i < EMAC_DEP_COUNT; i++) { if (deps[i].node) diff --git a/drivers/net/myri_sbus.c b/drivers/net/myri_sbus.c index 1a57c3da1f4..04e552aa14e 100644 --- a/drivers/net/myri_sbus.c +++ b/drivers/net/myri_sbus.c @@ -1079,7 +1079,7 @@ static int __devinit myri_sbus_probe(struct of_device *op, const struct of_devic mp->dev = dev; dev->watchdog_timeo = 5*HZ; - dev->irq = op->irqs[0]; + dev->irq = op->archdata.irqs[0]; dev->netdev_ops = &myri_ops; /* Register interrupt handler now. */ @@ -1172,12 +1172,12 @@ static struct of_platform_driver myri_sbus_driver = { static int __init myri_sbus_init(void) { - return of_register_driver(&myri_sbus_driver, &of_bus_type); + return of_register_platform_driver(&myri_sbus_driver); } static void __exit myri_sbus_exit(void) { - of_unregister_driver(&myri_sbus_driver); + of_unregister_platform_driver(&myri_sbus_driver); } module_init(myri_sbus_init); diff --git a/drivers/net/niu.c b/drivers/net/niu.c index b9b950845b0..404f2d55288 100644 --- a/drivers/net/niu.c +++ b/drivers/net/niu.c @@ -28,10 +28,7 @@ #include <linux/slab.h> #include <linux/io.h> - -#ifdef CONFIG_SPARC64 #include <linux/of_device.h> -#endif #include "niu.h" @@ -9114,12 +9111,12 @@ static int __devinit niu_n2_irq_init(struct niu *np, u8 *ldg_num_map) if (!int_prop) return -ENODEV; - for (i = 0; i < op->num_irqs; i++) { + for (i = 0; i < op->archdata.num_irqs; i++) { ldg_num_map[i] = int_prop[i]; - np->ldg[i].irq = op->irqs[i]; + np->ldg[i].irq = op->archdata.irqs[i]; } - np->num_ldg = op->num_irqs; + np->num_ldg = op->archdata.num_irqs; return 0; #else @@ -10249,14 +10246,14 @@ static int __init niu_init(void) niu_debug = netif_msg_init(debug, NIU_MSG_DEFAULT); #ifdef CONFIG_SPARC64 - err = of_register_driver(&niu_of_driver, &of_bus_type); + err = of_register_platform_driver(&niu_of_driver); #endif if (!err) { err = pci_register_driver(&niu_pci_driver); #ifdef CONFIG_SPARC64 if (err) - of_unregister_driver(&niu_of_driver); + of_unregister_platform_driver(&niu_of_driver); #endif } @@ -10267,7 +10264,7 @@ static void __exit niu_exit(void) { pci_unregister_driver(&niu_pci_driver); #ifdef CONFIG_SPARC64 - of_unregister_driver(&niu_of_driver); + of_unregister_platform_driver(&niu_of_driver); #endif } diff --git a/drivers/net/niu.h b/drivers/net/niu.h index d6715465f35..a41fa8ebe05 100644 --- a/drivers/net/niu.h +++ b/drivers/net/niu.h @@ -3236,7 +3236,7 @@ struct niu_phy_ops { int (*link_status)(struct niu *np, int *); }; -struct of_device; +struct platform_device; struct niu { void __iomem *regs; struct net_device *dev; @@ -3297,7 +3297,7 @@ struct niu { struct niu_vpd vpd; u32 eeprom_len; - struct of_device *op; + struct platform_device *op; void __iomem *vir_regs_1; void __iomem *vir_regs_2; }; diff --git a/drivers/net/sunbmac.c b/drivers/net/sunbmac.c index 367e96f317d..09c071bd6ad 100644 --- a/drivers/net/sunbmac.c +++ b/drivers/net/sunbmac.c @@ -1201,7 +1201,7 @@ static int __devinit bigmac_ether_init(struct of_device *op, dev->watchdog_timeo = 5*HZ; /* Finish net device registration. */ - dev->irq = bp->bigmac_op->irqs[0]; + dev->irq = bp->bigmac_op->archdata.irqs[0]; dev->dma = 0; if (register_netdev(dev)) { @@ -1301,12 +1301,12 @@ static struct of_platform_driver bigmac_sbus_driver = { static int __init bigmac_init(void) { - return of_register_driver(&bigmac_sbus_driver, &of_bus_type); + return of_register_platform_driver(&bigmac_sbus_driver); } static void __exit bigmac_exit(void) { - of_unregister_driver(&bigmac_sbus_driver); + of_unregister_platform_driver(&bigmac_sbus_driver); } module_init(bigmac_init); diff --git a/drivers/net/sunhme.c b/drivers/net/sunhme.c index 3d9650b8d38..eec443f6407 100644 --- a/drivers/net/sunhme.c +++ b/drivers/net/sunhme.c @@ -2561,7 +2561,7 @@ static int __init quattro_sbus_register_irqs(void) if (skip) continue; - err = request_irq(op->irqs[0], + err = request_irq(op->archdata.irqs[0], quattro_sbus_interrupt, IRQF_SHARED, "Quattro", qp); @@ -2590,7 +2590,7 @@ static void quattro_sbus_free_irqs(void) if (skip) continue; - free_irq(op->irqs[0], qp); + free_irq(op->archdata.irqs[0], qp); } } #endif /* CONFIG_SBUS */ @@ -2790,7 +2790,7 @@ static int __devinit happy_meal_sbus_probe_one(struct of_device *op, int is_qfe) /* Happy Meal can do it all... */ dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM; - dev->irq = op->irqs[0]; + dev->irq = op->archdata.irqs[0]; #if defined(CONFIG_SBUS) && defined(CONFIG_PCI) /* Hook up SBUS register/descriptor accessors. */ @@ -3304,7 +3304,7 @@ static int __init happy_meal_sbus_init(void) { int err; - err = of_register_driver(&hme_sbus_driver, &of_bus_type); + err = of_register_platform_driver(&hme_sbus_driver); if (!err) err = quattro_sbus_register_irqs(); @@ -3313,7 +3313,7 @@ static int __init happy_meal_sbus_init(void) static void happy_meal_sbus_exit(void) { - of_unregister_driver(&hme_sbus_driver); + of_unregister_platform_driver(&hme_sbus_driver); quattro_sbus_free_irqs(); while (qfe_sbus_list) { diff --git a/drivers/net/sunlance.c b/drivers/net/sunlance.c index 7d9c33dd9d1..ee364fa7563 100644 --- a/drivers/net/sunlance.c +++ b/drivers/net/sunlance.c @@ -1474,7 +1474,7 @@ no_link_test: dev->ethtool_ops = &sparc_lance_ethtool_ops; dev->netdev_ops = &sparc_lance_ops; - dev->irq = op->irqs[0]; + dev->irq = op->archdata.irqs[0]; /* We cannot sleep if the chip is busy during a * multicast list update event, because such events @@ -1558,12 +1558,12 @@ static struct of_platform_driver sunlance_sbus_driver = { /* Find all the lance cards on the system and initialize them */ static int __init sparc_lance_init(void) { - return of_register_driver(&sunlance_sbus_driver, &of_bus_type); + return of_register_platform_driver(&sunlance_sbus_driver); } static void __exit sparc_lance_exit(void) { - of_unregister_driver(&sunlance_sbus_driver); + of_unregister_platform_driver(&sunlance_sbus_driver); } module_init(sparc_lance_init); diff --git a/drivers/net/sunqe.c b/drivers/net/sunqe.c index 72b579c8d81..5f84a5daded 100644 --- a/drivers/net/sunqe.c +++ b/drivers/net/sunqe.c @@ -803,7 +803,7 @@ static struct sunqec * __devinit get_qec(struct of_device *child) qec_init_once(qecp, op); - if (request_irq(op->irqs[0], qec_interrupt, + if (request_irq(op->archdata.irqs[0], qec_interrupt, IRQF_SHARED, "qec", (void *) qecp)) { printk(KERN_ERR "qec: Can't register irq.\n"); goto fail; @@ -901,7 +901,7 @@ static int __devinit qec_ether_init(struct of_device *op) SET_NETDEV_DEV(dev, &op->dev); dev->watchdog_timeo = 5*HZ; - dev->irq = op->irqs[0]; + dev->irq = op->archdata.irqs[0]; dev->dma = 0; dev->ethtool_ops = &qe_ethtool_ops; dev->netdev_ops = &qec_ops; @@ -988,18 +988,18 @@ static struct of_platform_driver qec_sbus_driver = { static int __init qec_init(void) { - return of_register_driver(&qec_sbus_driver, &of_bus_type); + return of_register_platform_driver(&qec_sbus_driver); } static void __exit qec_exit(void) { - of_unregister_driver(&qec_sbus_driver); + of_unregister_platform_driver(&qec_sbus_driver); while (root_qec_dev) { struct sunqec *next = root_qec_dev->next_module; struct of_device *op = root_qec_dev->op; - free_irq(op->irqs[0], (void *) root_qec_dev); + free_irq(op->archdata.irqs[0], (void *) root_qec_dev); of_iounmap(&op->resource[0], root_qec_dev->gregs, GLOB_REG_SIZE); kfree(root_qec_dev); diff --git a/drivers/net/xilinx_emaclite.c b/drivers/net/xilinx_emaclite.c index d04c5b26205..b2c2f391b29 100644 --- a/drivers/net/xilinx_emaclite.c +++ b/drivers/net/xilinx_emaclite.c @@ -20,7 +20,7 @@ #include <linux/skbuff.h> #include <linux/io.h> #include <linux/slab.h> - +#include <linux/of_address.h> #include <linux/of_device.h> #include <linux/of_platform.h> #include <linux/of_mdio.h> diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index 7cecc8fea9b..6acbff389ab 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -1,35 +1,61 @@ -config OF_FLATTREE +config DTC + bool + +config OF bool + +menu "Flattened Device Tree and Open Firmware support" depends on OF +config PROC_DEVICETREE + bool "Support for device tree in /proc" + depends on PROC_FS && !SPARC + help + This option adds a device-tree directory under /proc which contains + an image of the device tree that the kernel copies from Open + Firmware or other boot firmware. If unsure, say Y here. + +config OF_FLATTREE + bool + select DTC + config OF_DYNAMIC def_bool y - depends on OF && PPC_OF + depends on PPC_OF + +config OF_ADDRESS + def_bool y + depends on !SPARC + +config OF_IRQ + def_bool y + depends on !SPARC config OF_DEVICE def_bool y - depends on OF && (SPARC || PPC_OF || MICROBLAZE) config OF_GPIO def_bool y - depends on OF && (PPC_OF || MICROBLAZE) && GPIOLIB + depends on GPIOLIB && !SPARC help OpenFirmware GPIO accessors config OF_I2C def_tristate I2C - depends on (PPC_OF || MICROBLAZE) && I2C + depends on I2C && !SPARC help OpenFirmware I2C accessors config OF_SPI def_tristate SPI - depends on OF && (PPC_OF || MICROBLAZE) && SPI + depends on SPI && !SPARC help OpenFirmware SPI accessors config OF_MDIO def_tristate PHYLIB - depends on OF && PHYLIB + depends on PHYLIB help OpenFirmware MDIO bus (Ethernet PHY) accessors + +endmenu # OF diff --git a/drivers/of/Makefile b/drivers/of/Makefile index f232cc98ce0..0052c405463 100644 --- a/drivers/of/Makefile +++ b/drivers/of/Makefile @@ -1,5 +1,7 @@ obj-y = base.o obj-$(CONFIG_OF_FLATTREE) += fdt.o +obj-$(CONFIG_OF_ADDRESS) += address.o +obj-$(CONFIG_OF_IRQ) += irq.o obj-$(CONFIG_OF_DEVICE) += device.o platform.o obj-$(CONFIG_OF_GPIO) += gpio.o obj-$(CONFIG_OF_I2C) += of_i2c.o diff --git a/drivers/of/address.c b/drivers/of/address.c new file mode 100644 index 00000000000..fcadb726d4f --- /dev/null +++ b/drivers/of/address.c @@ -0,0 +1,595 @@ + +#include <linux/io.h> +#include <linux/ioport.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/pci_regs.h> +#include <linux/string.h> + +/* Max address size we deal with */ +#define OF_MAX_ADDR_CELLS 4 +#define OF_CHECK_COUNTS(na, ns) ((na) > 0 && (na) <= OF_MAX_ADDR_CELLS && \ + (ns) > 0) + +static struct of_bus *of_match_bus(struct device_node *np); +static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, + u64 size, unsigned int flags, + struct resource *r); + +/* Debug utility */ +#ifdef DEBUG +static void of_dump_addr(const char *s, const u32 *addr, int na) +{ + printk(KERN_DEBUG "%s", s); + while (na--) + printk(" %08x", be32_to_cpu(*(addr++))); + printk("\n"); +} +#else +static void of_dump_addr(const char *s, const u32 *addr, int na) { } +#endif + +/* Callbacks for bus specific translators */ +struct of_bus { + const char *name; + const char *addresses; + int (*match)(struct device_node *parent); + void (*count_cells)(struct device_node *child, + int *addrc, int *sizec); + u64 (*map)(u32 *addr, const u32 *range, + int na, int ns, int pna); + int (*translate)(u32 *addr, u64 offset, int na); + unsigned int (*get_flags)(const u32 *addr); +}; + +/* + * Default translator (generic bus) + */ + +static void of_bus_default_count_cells(struct device_node *dev, + int *addrc, int *sizec) +{ + if (addrc) + *addrc = of_n_addr_cells(dev); + if (sizec) + *sizec = of_n_size_cells(dev); +} + +static u64 of_bus_default_map(u32 *addr, const u32 *range, + int na, int ns, int pna) +{ + u64 cp, s, da; + + cp = of_read_number(range, na); + s = of_read_number(range + na + pna, ns); + da = of_read_number(addr, na); + + pr_debug("OF: default map, cp=%llx, s=%llx, da=%llx\n", + (unsigned long long)cp, (unsigned long long)s, + (unsigned long long)da); + + if (da < cp || da >= (cp + s)) + return OF_BAD_ADDR; + return da - cp; +} + +static int of_bus_default_translate(u32 *addr, u64 offset, int na) +{ + u64 a = of_read_number(addr, na); + memset(addr, 0, na * 4); + a += offset; + if (na > 1) + addr[na - 2] = cpu_to_be32(a >> 32); + addr[na - 1] = cpu_to_be32(a & 0xffffffffu); + + return 0; +} + +static unsigned int of_bus_default_get_flags(const u32 *addr) +{ + return IORESOURCE_MEM; +} + +#ifdef CONFIG_PCI +/* + * PCI bus specific translator + */ + +static int of_bus_pci_match(struct device_node *np) +{ + /* "vci" is for the /chaos bridge on 1st-gen PCI powermacs */ + return !strcmp(np->type, "pci") || !strcmp(np->type, "vci"); +} + +static void of_bus_pci_count_cells(struct device_node *np, + int *addrc, int *sizec) +{ + if (addrc) + *addrc = 3; + if (sizec) + *sizec = 2; +} + +static unsigned int of_bus_pci_get_flags(const u32 *addr) +{ + unsigned int flags = 0; + u32 w = addr[0]; + + switch((w >> 24) & 0x03) { + case 0x01: + flags |= IORESOURCE_IO; + break; + case 0x02: /* 32 bits */ + case 0x03: /* 64 bits */ + flags |= IORESOURCE_MEM; + break; + } + if (w & 0x40000000) + flags |= IORESOURCE_PREFETCH; + return flags; +} + +static u64 of_bus_pci_map(u32 *addr, const u32 *range, int na, int ns, int pna) +{ + u64 cp, s, da; + unsigned int af, rf; + + af = of_bus_pci_get_flags(addr); + rf = of_bus_pci_get_flags(range); + + /* Check address type match */ + if ((af ^ rf) & (IORESOURCE_MEM | IORESOURCE_IO)) + return OF_BAD_ADDR; + + /* Read address values, skipping high cell */ + cp = of_read_number(range + 1, na - 1); + s = of_read_number(range + na + pna, ns); + da = of_read_number(addr + 1, na - 1); + + pr_debug("OF: PCI map, cp=%llx, s=%llx, da=%llx\n", + (unsigned long long)cp, (unsigned long long)s, + (unsigned long long)da); + + if (da < cp || da >= (cp + s)) + return OF_BAD_ADDR; + return da - cp; +} + +static int of_bus_pci_translate(u32 *addr, u64 offset, int na) +{ + return of_bus_default_translate(addr + 1, offset, na - 1); +} + +const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, + unsigned int *flags) +{ + const u32 *prop; + unsigned int psize; + struct device_node *parent; + struct of_bus *bus; + int onesize, i, na, ns; + + /* Get parent & match bus type */ + parent = of_get_parent(dev); + if (parent == NULL) + return NULL; + bus = of_match_bus(parent); + if (strcmp(bus->name, "pci")) { + of_node_put(parent); + return NULL; + } + bus->count_cells(dev, &na, &ns); + of_node_put(parent); + if (!OF_CHECK_COUNTS(na, ns)) + return NULL; + + /* Get "reg" or "assigned-addresses" property */ + prop = of_get_property(dev, bus->addresses, &psize); + if (prop == NULL) + return NULL; + psize /= 4; + + onesize = na + ns; + for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) { + u32 val = be32_to_cpu(prop[0]); + if ((val & 0xff) == ((bar_no * 4) + PCI_BASE_ADDRESS_0)) { + if (size) + *size = of_read_number(prop + na, ns); + if (flags) + *flags = bus->get_flags(prop); + return prop; + } + } + return NULL; +} +EXPORT_SYMBOL(of_get_pci_address); + +int of_pci_address_to_resource(struct device_node *dev, int bar, + struct resource *r) +{ + const u32 *addrp; + u64 size; + unsigned int flags; + + addrp = of_get_pci_address(dev, bar, &size, &flags); + if (addrp == NULL) + return -EINVAL; + return __of_address_to_resource(dev, addrp, size, flags, r); +} +EXPORT_SYMBOL_GPL(of_pci_address_to_resource); +#endif /* CONFIG_PCI */ + +/* + * ISA bus specific translator + */ + +static int of_bus_isa_match(struct device_node *np) +{ + return !strcmp(np->name, "isa"); +} + +static void of_bus_isa_count_cells(struct device_node *child, + int *addrc, int *sizec) +{ + if (addrc) + *addrc = 2; + if (sizec) + *sizec = 1; +} + +static u64 of_bus_isa_map(u32 *addr, const u32 *range, int na, int ns, int pna) +{ + u64 cp, s, da; + + /* Check address type match */ + if ((addr[0] ^ range[0]) & 0x00000001) + return OF_BAD_ADDR; + + /* Read address values, skipping high cell */ + cp = of_read_number(range + 1, na - 1); + s = of_read_number(range + na + pna, ns); + da = of_read_number(addr + 1, na - 1); + + pr_debug("OF: ISA map, cp=%llx, s=%llx, da=%llx\n", + (unsigned long long)cp, (unsigned long long)s, + (unsigned long long)da); + + if (da < cp || da >= (cp + s)) + return OF_BAD_ADDR; + return da - cp; +} + +static int of_bus_isa_translate(u32 *addr, u64 offset, int na) +{ + return of_bus_default_translate(addr + 1, offset, na - 1); +} + +static unsigned int of_bus_isa_get_flags(const u32 *addr) +{ + unsigned int flags = 0; + u32 w = addr[0]; + + if (w & 1) + flags |= IORESOURCE_IO; + else + flags |= IORESOURCE_MEM; + return flags; +} + +/* + * Array of bus specific translators + */ + +static struct of_bus of_busses[] = { +#ifdef CONFIG_PCI + /* PCI */ + { + .name = "pci", + .addresses = "assigned-addresses", + .match = of_bus_pci_match, + .count_cells = of_bus_pci_count_cells, + .map = of_bus_pci_map, + .translate = of_bus_pci_translate, + .get_flags = of_bus_pci_get_flags, + }, +#endif /* CONFIG_PCI */ + /* ISA */ + { + .name = "isa", + .addresses = "reg", + .match = of_bus_isa_match, + .count_cells = of_bus_isa_count_cells, + .map = of_bus_isa_map, + .translate = of_bus_isa_translate, + .get_flags = of_bus_isa_get_flags, + }, + /* Default */ + { + .name = "default", + .addresses = "reg", + .match = NULL, + .count_cells = of_bus_default_count_cells, + .map = of_bus_default_map, + .translate = of_bus_default_translate, + .get_flags = of_bus_default_get_flags, + }, +}; + +static struct of_bus *of_match_bus(struct device_node *np) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(of_busses); i++) + if (!of_busses[i].match || of_busses[i].match(np)) + return &of_busses[i]; + BUG(); + return NULL; +} + +static int of_translate_one(struct device_node *parent, struct of_bus *bus, + struct of_bus *pbus, u32 *addr, + int na, int ns, int pna, const char *rprop) +{ + const u32 *ranges; + unsigned int rlen; + int rone; + u64 offset = OF_BAD_ADDR; + + /* Normally, an absence of a "ranges" property means we are + * crossing a non-translatable boundary, and thus the addresses + * below the current not cannot be converted to CPU physical ones. + * Unfortunately, while this is very clear in the spec, it's not + * what Apple understood, and they do have things like /uni-n or + * /ht nodes with no "ranges" property and a lot of perfectly + * useable mapped devices below them. Thus we treat the absence of + * "ranges" as equivalent to an empty "ranges" property which means + * a 1:1 translation at that level. It's up to the caller not to try + * to translate addresses that aren't supposed to be translated in + * the first place. --BenH. + * + * As far as we know, this damage only exists on Apple machines, so + * This code is only enabled on powerpc. --gcl + */ + ranges = of_get_property(parent, rprop, &rlen); +#if !defined(CONFIG_PPC) + if (ranges == NULL) { + pr_err("OF: no ranges; cannot translate\n"); + return 1; + } +#endif /* !defined(CONFIG_PPC) */ + if (ranges == NULL || rlen == 0) { + offset = of_read_number(addr, na); + memset(addr, 0, pna * 4); + pr_debug("OF: empty ranges; 1:1 translation\n"); + goto finish; + } + + pr_debug("OF: walking ranges...\n"); + + /* Now walk through the ranges */ + rlen /= 4; + rone = na + pna + ns; + for (; rlen >= rone; rlen -= rone, ranges += rone) { + offset = bus->map(addr, ranges, na, ns, pna); + if (offset != OF_BAD_ADDR) + break; + } + if (offset == OF_BAD_ADDR) { + pr_debug("OF: not found !\n"); + return 1; + } + memcpy(addr, ranges + na, 4 * pna); + + finish: + of_dump_addr("OF: parent translation for:", addr, pna); + pr_debug("OF: with offset: %llx\n", (unsigned long long)offset); + + /* Translate it into parent bus space */ + return pbus->translate(addr, offset, pna); +} + +/* + * Translate an address from the device-tree into a CPU physical address, + * this walks up the tree and applies the various bus mappings on the + * way. + * + * Note: We consider that crossing any level with #size-cells == 0 to mean + * that translation is impossible (that is we are not dealing with a value + * that can be mapped to a cpu physical address). This is not really specified + * that way, but this is traditionally the way IBM at least do things + */ +u64 __of_translate_address(struct device_node *dev, const u32 *in_addr, + const char *rprop) +{ + struct device_node *parent = NULL; + struct of_bus *bus, *pbus; + u32 addr[OF_MAX_ADDR_CELLS]; + int na, ns, pna, pns; + u64 result = OF_BAD_ADDR; + + pr_debug("OF: ** translation for device %s **\n", dev->full_name); + + /* Increase refcount at current level */ + of_node_get(dev); + + /* Get parent & match bus type */ + parent = of_get_parent(dev); + if (parent == NULL) + goto bail; + bus = of_match_bus(parent); + + /* Cound address cells & copy address locally */ + bus->count_cells(dev, &na, &ns); + if (!OF_CHECK_COUNTS(na, ns)) { + printk(KERN_ERR "prom_parse: Bad cell count for %s\n", + dev->full_name); + goto bail; + } + memcpy(addr, in_addr, na * 4); + + pr_debug("OF: bus is %s (na=%d, ns=%d) on %s\n", + bus->name, na, ns, parent->full_name); + of_dump_addr("OF: translating address:", addr, na); + + /* Translate */ + for (;;) { + /* Switch to parent bus */ + of_node_put(dev); + dev = parent; + parent = of_get_parent(dev); + + /* If root, we have finished */ + if (parent == NULL) { + pr_debug("OF: reached root node\n"); + result = of_read_number(addr, na); + break; + } + + /* Get new parent bus and counts */ + pbus = of_match_bus(parent); + pbus->count_cells(dev, &pna, &pns); + if (!OF_CHECK_COUNTS(pna, pns)) { + printk(KERN_ERR "prom_parse: Bad cell count for %s\n", + dev->full_name); + break; + } + + pr_debug("OF: parent bus is %s (na=%d, ns=%d) on %s\n", + pbus->name, pna, pns, parent->full_name); + + /* Apply bus translation */ + if (of_translate_one(dev, bus, pbus, addr, na, ns, pna, rprop)) + break; + + /* Complete the move up one level */ + na = pna; + ns = pns; + bus = pbus; + + of_dump_addr("OF: one level translation:", addr, na); + } + bail: + of_node_put(parent); + of_node_put(dev); + + return result; +} + +u64 of_translate_address(struct device_node *dev, const u32 *in_addr) +{ + return __of_translate_address(dev, in_addr, "ranges"); +} +EXPORT_SYMBOL(of_translate_address); + +u64 of_translate_dma_address(struct device_node *dev, const u32 *in_addr) +{ + return __of_translate_address(dev, in_addr, "dma-ranges"); +} +EXPORT_SYMBOL(of_translate_dma_address); + +const u32 *of_get_address(struct device_node *dev, int index, u64 *size, + unsigned int *flags) +{ + const u32 *prop; + unsigned int psize; + struct device_node *parent; + struct of_bus *bus; + int onesize, i, na, ns; + + /* Get parent & match bus type */ + parent = of_get_parent(dev); + if (parent == NULL) + return NULL; + bus = of_match_bus(parent); + bus->count_cells(dev, &na, &ns); + of_node_put(parent); + if (!OF_CHECK_COUNTS(na, ns)) + return NULL; + + /* Get "reg" or "assigned-addresses" property */ + prop = of_get_property(dev, bus->addresses, &psize); + if (prop == NULL) + return NULL; + psize /= 4; + + onesize = na + ns; + for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++) + if (i == index) { + if (size) + *size = of_read_number(prop + na, ns); + if (flags) + *flags = bus->get_flags(prop); + return prop; + } + return NULL; +} +EXPORT_SYMBOL(of_get_address); + +static int __of_address_to_resource(struct device_node *dev, const u32 *addrp, + u64 size, unsigned int flags, + struct resource *r) +{ + u64 taddr; + + if ((flags & (IORESOURCE_IO | IORESOURCE_MEM)) == 0) + return -EINVAL; + taddr = of_translate_address(dev, addrp); + if (taddr == OF_BAD_ADDR) + return -EINVAL; + memset(r, 0, sizeof(struct resource)); + if (flags & IORESOURCE_IO) { + unsigned long port; + port = pci_address_to_pio(taddr); + if (port == (unsigned long)-1) + return -EINVAL; + r->start = port; + r->end = port + size - 1; + } else { + r->start = taddr; + r->end = taddr + size - 1; + } + r->flags = flags; + r->name = dev->full_name; + return 0; +} + +/** + * of_address_to_resource - Translate device tree address and return as resource + * + * Note that if your address is a PIO address, the conversion will fail if + * the physical address can't be internally converted to an IO token with + * pci_address_to_pio(), that is because it's either called to early or it + * can't be matched to any host bridge IO space + */ +int of_address_to_resource(struct device_node *dev, int index, + struct resource *r) +{ + const u32 *addrp; + u64 size; + unsigned int flags; + + addrp = of_get_address(dev, index, &size, &flags); + if (addrp == NULL) + return -EINVAL; + return __of_address_to_resource(dev, addrp, size, flags, r); +} +EXPORT_SYMBOL_GPL(of_address_to_resource); + + +/** + * of_iomap - Maps the memory mapped IO for a given device_node + * @device: the device whose io range will be mapped + * @index: index of the io range + * + * Returns a pointer to the mapped memory + */ +void __iomem *of_iomap(struct device_node *np, int index) +{ + struct resource res; + + if (of_address_to_resource(np, index, &res)) + return NULL; + + return ioremap(res.start, 1 + res.end - res.start); +} +EXPORT_SYMBOL(of_iomap); diff --git a/drivers/of/base.c b/drivers/of/base.c index b5ad9740d8b..aa805250de7 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -545,74 +545,28 @@ struct device_node *of_find_matching_node(struct device_node *from, EXPORT_SYMBOL(of_find_matching_node); /** - * of_modalias_table: Table of explicit compatible ==> modalias mappings - * - * This table allows particulare compatible property values to be mapped - * to modalias strings. This is useful for busses which do not directly - * understand the OF device tree but are populated based on data contained - * within the device tree. SPI and I2C are the two current users of this - * table. - * - * In most cases, devices do not need to be listed in this table because - * the modalias value can be derived directly from the compatible table. - * However, if for any reason a value cannot be derived, then this table - * provides a method to override the implicit derivation. - * - * At the moment, a single table is used for all bus types because it is - * assumed that the data size is small and that the compatible values - * should already be distinct enough to differentiate between SPI, I2C - * and other devices. - */ -struct of_modalias_table { - char *of_device; - char *modalias; -}; -static struct of_modalias_table of_modalias_table[] = { - { "fsl,mcu-mpc8349emitx", "mcu-mpc8349emitx" }, - { "mmc-spi-slot", "mmc_spi" }, -}; - -/** * of_modalias_node - Lookup appropriate modalias for a device node * @node: pointer to a device tree node * @modalias: Pointer to buffer that modalias value will be copied into * @len: Length of modalias value * - * Based on the value of the compatible property, this routine will determine - * an appropriate modalias value for a particular device tree node. Two - * separate methods are attempted to derive a modalias value. + * Based on the value of the compatible property, this routine will attempt + * to choose an appropriate modalias value for a particular device tree node. + * It does this by stripping the manufacturer prefix (as delimited by a ',') + * from the first entry in the compatible list property. * - * First method is to lookup the compatible value in of_modalias_table. - * Second is to strip off the manufacturer prefix from the first - * compatible entry and use the remainder as modalias - * - * This routine returns 0 on success + * This routine returns 0 on success, <0 on failure. */ int of_modalias_node(struct device_node *node, char *modalias, int len) { - int i, cplen; - const char *compatible; - const char *p; - - /* 1. search for exception list entry */ - for (i = 0; i < ARRAY_SIZE(of_modalias_table); i++) { - compatible = of_modalias_table[i].of_device; - if (!of_device_is_compatible(node, compatible)) - continue; - strlcpy(modalias, of_modalias_table[i].modalias, len); - return 0; - } + const char *compatible, *p; + int cplen; compatible = of_get_property(node, "compatible", &cplen); - if (!compatible) + if (!compatible || strlen(compatible) > cplen) return -ENODEV; - - /* 2. take first compatible entry and strip manufacturer */ p = strchr(compatible, ','); - if (!p) - return -ENODEV; - p++; - strlcpy(modalias, p, len); + strlcpy(modalias, p ? p + 1 : compatible, len); return 0; } EXPORT_SYMBOL_GPL(of_modalias_node); @@ -651,14 +605,14 @@ EXPORT_SYMBOL(of_find_node_by_phandle); struct device_node * of_parse_phandle(struct device_node *np, const char *phandle_name, int index) { - const phandle *phandle; + const __be32 *phandle; int size; phandle = of_get_property(np, phandle_name, &size); if ((!phandle) || (size < sizeof(*phandle) * (index + 1))) return NULL; - return of_find_node_by_phandle(phandle[index]); + return of_find_node_by_phandle(be32_to_cpup(phandle + index)); } EXPORT_SYMBOL(of_parse_phandle); @@ -714,16 +668,16 @@ int of_parse_phandles_with_args(struct device_node *np, const char *list_name, while (list < list_end) { const __be32 *cells; - const phandle *phandle; + phandle phandle; - phandle = list++; + phandle = be32_to_cpup(list++); args = list; /* one cell hole in the list = <>; */ - if (!*phandle) + if (!phandle) goto next; - node = of_find_node_by_phandle(*phandle); + node = of_find_node_by_phandle(phandle); if (!node) { pr_debug("%s: could not find phandle\n", np->full_name); diff --git a/drivers/of/device.c b/drivers/of/device.c index 7d18f8e0b01..0d8a0644f54 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -20,13 +20,13 @@ const struct of_device_id *of_match_device(const struct of_device_id *matches, const struct device *dev) { - if (!dev->of_node) + if ((!matches) || (!dev->of_node)) return NULL; return of_match_node(matches, dev->of_node); } EXPORT_SYMBOL(of_match_device); -struct of_device *of_dev_get(struct of_device *dev) +struct platform_device *of_dev_get(struct platform_device *dev) { struct device *tmp; @@ -34,13 +34,13 @@ struct of_device *of_dev_get(struct of_device *dev) return NULL; tmp = get_device(&dev->dev); if (tmp) - return to_of_device(tmp); + return to_platform_device(tmp); else return NULL; } EXPORT_SYMBOL(of_dev_get); -void of_dev_put(struct of_device *dev) +void of_dev_put(struct platform_device *dev) { if (dev) put_device(&dev->dev); @@ -50,28 +50,25 @@ EXPORT_SYMBOL(of_dev_put); static ssize_t devspec_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct of_device *ofdev; + struct platform_device *ofdev; - ofdev = to_of_device(dev); + ofdev = to_platform_device(dev); return sprintf(buf, "%s\n", ofdev->dev.of_node->full_name); } static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct of_device *ofdev; + struct platform_device *ofdev; - ofdev = to_of_device(dev); + ofdev = to_platform_device(dev); return sprintf(buf, "%s\n", ofdev->dev.of_node->name); } static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct of_device *ofdev = to_of_device(dev); - ssize_t len = 0; - - len = of_device_get_modalias(ofdev, buf, PAGE_SIZE - 2); + ssize_t len = of_device_get_modalias(dev, buf, PAGE_SIZE - 2); buf[len] = '\n'; buf[len+1] = 0; return len+1; @@ -93,20 +90,25 @@ struct device_attribute of_platform_device_attrs[] = { */ void of_release_dev(struct device *dev) { - struct of_device *ofdev; + struct platform_device *ofdev; - ofdev = to_of_device(dev); + ofdev = to_platform_device(dev); of_node_put(ofdev->dev.of_node); kfree(ofdev); } EXPORT_SYMBOL(of_release_dev); -int of_device_register(struct of_device *ofdev) +int of_device_register(struct platform_device *ofdev) { BUG_ON(ofdev->dev.of_node == NULL); device_initialize(&ofdev->dev); + /* name and id have to be set so that the platform bus doesn't get + * confused on matching */ + ofdev->name = dev_name(&ofdev->dev); + ofdev->id = -1; + /* device_add will assume that this device is on the same node as * the parent. If there is no parent defined, set the node * explicitly */ @@ -117,25 +119,24 @@ int of_device_register(struct of_device *ofdev) } EXPORT_SYMBOL(of_device_register); -void of_device_unregister(struct of_device *ofdev) +void of_device_unregister(struct platform_device *ofdev) { device_unregister(&ofdev->dev); } EXPORT_SYMBOL(of_device_unregister); -ssize_t of_device_get_modalias(struct of_device *ofdev, - char *str, ssize_t len) +ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len) { const char *compat; int cplen, i; ssize_t tsize, csize, repend; /* Name & Type */ - csize = snprintf(str, len, "of:N%sT%s", ofdev->dev.of_node->name, - ofdev->dev.of_node->type); + csize = snprintf(str, len, "of:N%sT%s", dev->of_node->name, + dev->of_node->type); /* Get compatible property if any */ - compat = of_get_property(ofdev->dev.of_node, "compatible", &cplen); + compat = of_get_property(dev->of_node, "compatible", &cplen); if (!compat) return csize; @@ -170,3 +171,51 @@ ssize_t of_device_get_modalias(struct of_device *ofdev, return tsize; } + +/** + * of_device_uevent - Display OF related uevent information + */ +int of_device_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + const char *compat; + int seen = 0, cplen, sl; + + if ((!dev) || (!dev->of_node)) + return -ENODEV; + + if (add_uevent_var(env, "OF_NAME=%s", dev->of_node->name)) + return -ENOMEM; + + if (add_uevent_var(env, "OF_TYPE=%s", dev->of_node->type)) + return -ENOMEM; + + /* Since the compatible field can contain pretty much anything + * it's not really legal to split it out with commas. We split it + * up using a number of environment variables instead. */ + + compat = of_get_property(dev->of_node, "compatible", &cplen); + while (compat && *compat && cplen > 0) { + if (add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat)) + return -ENOMEM; + + sl = strlen(compat) + 1; + compat += sl; + cplen -= sl; + seen++; + } + + if (add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen)) + return -ENOMEM; + + /* modalias is trickier, we add it in 2 steps */ + if (add_uevent_var(env, "MODALIAS=")) + return -ENOMEM; + + sl = of_device_get_modalias(dev, &env->buf[env->buflen-1], + sizeof(env->buf) - env->buflen); + if (sl >= (sizeof(env->buf) - env->buflen)) + return -ENOMEM; + env->buflen += sl; + + return 0; +} diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index b6987bba855..65da5aec755 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -69,9 +69,9 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node, u32 sz = be32_to_cpup((__be32 *)p); p += 8; if (be32_to_cpu(initial_boot_params->version) < 0x10) - p = _ALIGN(p, sz >= 8 ? 8 : 4); + p = ALIGN(p, sz >= 8 ? 8 : 4); p += sz; - p = _ALIGN(p, 4); + p = ALIGN(p, 4); continue; } if (tag != OF_DT_BEGIN_NODE) { @@ -80,7 +80,7 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node, } depth++; pathp = (char *)p; - p = _ALIGN(p + strlen(pathp) + 1, 4); + p = ALIGN(p + strlen(pathp) + 1, 4); if ((*pathp) == '/') { char *lp, *np; for (lp = NULL, np = pathp; *np; np++) @@ -109,7 +109,7 @@ unsigned long __init of_get_flat_dt_root(void) p += 4; BUG_ON(be32_to_cpup((__be32 *)p) != OF_DT_BEGIN_NODE); p += 4; - return _ALIGN(p + strlen((char *)p) + 1, 4); + return ALIGN(p + strlen((char *)p) + 1, 4); } /** @@ -138,7 +138,7 @@ void *__init of_get_flat_dt_prop(unsigned long node, const char *name, noff = be32_to_cpup((__be32 *)(p + 4)); p += 8; if (be32_to_cpu(initial_boot_params->version) < 0x10) - p = _ALIGN(p, sz >= 8 ? 8 : 4); + p = ALIGN(p, sz >= 8 ? 8 : 4); nstr = find_flat_dt_string(noff); if (nstr == NULL) { @@ -151,7 +151,7 @@ void *__init of_get_flat_dt_prop(unsigned long node, const char *name, return (void *)p; } p += sz; - p = _ALIGN(p, 4); + p = ALIGN(p, 4); } while (1); } @@ -169,7 +169,7 @@ int __init of_flat_dt_is_compatible(unsigned long node, const char *compat) if (cp == NULL) return 0; while (cplen > 0) { - if (strncasecmp(cp, compat, strlen(compat)) == 0) + if (of_compat_cmp(cp, compat, strlen(compat)) == 0) return 1; l = strlen(cp) + 1; cp += l; @@ -184,7 +184,7 @@ static void *__init unflatten_dt_alloc(unsigned long *mem, unsigned long size, { void *res; - *mem = _ALIGN(*mem, align); + *mem = ALIGN(*mem, align); res = (void *)*mem; *mem += size; @@ -220,7 +220,7 @@ unsigned long __init unflatten_dt_node(unsigned long mem, *p += 4; pathp = (char *)*p; l = allocl = strlen(pathp) + 1; - *p = _ALIGN(*p + l, 4); + *p = ALIGN(*p + l, 4); /* version 0x10 has a more compact unit name here instead of the full * path. we accumulate the full path size using "fpsize", we'll rebuild @@ -299,7 +299,7 @@ unsigned long __init unflatten_dt_node(unsigned long mem, noff = be32_to_cpup((__be32 *)((*p) + 4)); *p += 8; if (be32_to_cpu(initial_boot_params->version) < 0x10) - *p = _ALIGN(*p, sz >= 8 ? 8 : 4); + *p = ALIGN(*p, sz >= 8 ? 8 : 4); pname = find_flat_dt_string(noff); if (pname == NULL) { @@ -320,20 +320,20 @@ unsigned long __init unflatten_dt_node(unsigned long mem, if ((strcmp(pname, "phandle") == 0) || (strcmp(pname, "linux,phandle") == 0)) { if (np->phandle == 0) - np->phandle = *((u32 *)*p); + np->phandle = be32_to_cpup((__be32*)*p); } /* And we process the "ibm,phandle" property * used in pSeries dynamic device tree * stuff */ if (strcmp(pname, "ibm,phandle") == 0) - np->phandle = *((u32 *)*p); + np->phandle = be32_to_cpup((__be32 *)*p); pp->name = pname; pp->length = sz; pp->value = (void *)*p; *prev_pp = pp; prev_pp = &pp->next; } - *p = _ALIGN((*p) + sz, 4); + *p = ALIGN((*p) + sz, 4); } /* with version 0x10 we may not have the name property, recreate * it here from the unit name if absent diff --git a/drivers/of/gpio.c b/drivers/of/gpio.c index a1b31a4abae..905960338fb 100644 --- a/drivers/of/gpio.c +++ b/drivers/of/gpio.c @@ -11,13 +11,14 @@ * (at your option) any later version. */ -#include <linux/kernel.h> +#include <linux/device.h> #include <linux/errno.h> +#include <linux/module.h> #include <linux/io.h> #include <linux/of.h> -#include <linux/slab.h> +#include <linux/of_address.h> #include <linux/of_gpio.h> -#include <asm/prom.h> +#include <linux/slab.h> /** * of_get_gpio_flags - Get a GPIO number and flags to use with GPIO API @@ -33,32 +34,32 @@ int of_get_gpio_flags(struct device_node *np, int index, enum of_gpio_flags *flags) { int ret; - struct device_node *gc; - struct of_gpio_chip *of_gc = NULL; + struct device_node *gpio_np; + struct gpio_chip *gc; int size; const void *gpio_spec; const __be32 *gpio_cells; ret = of_parse_phandles_with_args(np, "gpios", "#gpio-cells", index, - &gc, &gpio_spec); + &gpio_np, &gpio_spec); if (ret) { pr_debug("%s: can't parse gpios property\n", __func__); goto err0; } - of_gc = gc->data; - if (!of_gc) { + gc = of_node_to_gpiochip(gpio_np); + if (!gc) { pr_debug("%s: gpio controller %s isn't registered\n", - np->full_name, gc->full_name); + np->full_name, gpio_np->full_name); ret = -ENODEV; goto err1; } - gpio_cells = of_get_property(gc, "#gpio-cells", &size); + gpio_cells = of_get_property(gpio_np, "#gpio-cells", &size); if (!gpio_cells || size != sizeof(*gpio_cells) || - be32_to_cpup(gpio_cells) != of_gc->gpio_cells) { + be32_to_cpup(gpio_cells) != gc->of_gpio_n_cells) { pr_debug("%s: wrong #gpio-cells for %s\n", - np->full_name, gc->full_name); + np->full_name, gpio_np->full_name); ret = -EINVAL; goto err1; } @@ -67,13 +68,13 @@ int of_get_gpio_flags(struct device_node *np, int index, if (flags) *flags = 0; - ret = of_gc->xlate(of_gc, np, gpio_spec, flags); + ret = gc->of_xlate(gc, np, gpio_spec, flags); if (ret < 0) goto err1; - ret += of_gc->gc.base; + ret += gc->base; err1: - of_node_put(gc); + of_node_put(gpio_np); err0: pr_debug("%s exited with status %d\n", __func__, ret); return ret; @@ -116,7 +117,7 @@ EXPORT_SYMBOL(of_gpio_count); /** * of_gpio_simple_xlate - translate gpio_spec to the GPIO number and flags - * @of_gc: pointer to the of_gpio_chip structure + * @gc: pointer to the gpio_chip structure * @np: device node of the GPIO chip * @gpio_spec: gpio specifier as found in the device tree * @flags: a flags pointer to fill in @@ -125,8 +126,8 @@ EXPORT_SYMBOL(of_gpio_count); * gpio chips. This function performs only one sanity check: whether gpio * is less than ngpios (that is specified in the gpio_chip). */ -int of_gpio_simple_xlate(struct of_gpio_chip *of_gc, struct device_node *np, - const void *gpio_spec, enum of_gpio_flags *flags) +static int of_gpio_simple_xlate(struct gpio_chip *gc, struct device_node *np, + const void *gpio_spec, u32 *flags) { const __be32 *gpio = gpio_spec; const u32 n = be32_to_cpup(gpio); @@ -137,12 +138,12 @@ int of_gpio_simple_xlate(struct of_gpio_chip *of_gc, struct device_node *np, * number and the flags from a single gpio cell -- this is possible, * but not recommended). */ - if (of_gc->gpio_cells < 2) { + if (gc->of_gpio_n_cells < 2) { WARN_ON(1); return -EINVAL; } - if (n > of_gc->gc.ngpio) + if (n > gc->ngpio) return -EINVAL; if (flags) @@ -150,7 +151,6 @@ int of_gpio_simple_xlate(struct of_gpio_chip *of_gc, struct device_node *np, return n; } -EXPORT_SYMBOL(of_gpio_simple_xlate); /** * of_mm_gpiochip_add - Add memory mapped GPIO chip (bank) @@ -161,10 +161,8 @@ EXPORT_SYMBOL(of_gpio_simple_xlate); * * 1) In the gpio_chip structure: * - all the callbacks - * - * 2) In the of_gpio_chip structure: - * - gpio_cells - * - xlate callback (optional) + * - of_gpio_n_cells + * - of_xlate callback (optional) * * 3) In the of_mm_gpio_chip structure: * - save_regs callback (optional) @@ -177,8 +175,7 @@ int of_mm_gpiochip_add(struct device_node *np, struct of_mm_gpio_chip *mm_gc) { int ret = -ENOMEM; - struct of_gpio_chip *of_gc = &mm_gc->of_gc; - struct gpio_chip *gc = &of_gc->gc; + struct gpio_chip *gc = &mm_gc->gc; gc->label = kstrdup(np->full_name, GFP_KERNEL); if (!gc->label) @@ -190,26 +187,19 @@ int of_mm_gpiochip_add(struct device_node *np, gc->base = -1; - if (!of_gc->xlate) - of_gc->xlate = of_gpio_simple_xlate; - if (mm_gc->save_regs) mm_gc->save_regs(mm_gc); - np->data = of_gc; + mm_gc->gc.of_node = np; ret = gpiochip_add(gc); if (ret) goto err2; - /* We don't want to lose the node and its ->data */ - of_node_get(np); - pr_debug("%s: registered as generic GPIO chip, base is %d\n", np->full_name, gc->base); return 0; err2: - np->data = NULL; iounmap(mm_gc->regs); err1: kfree(gc->label); @@ -219,3 +209,36 @@ err0: return ret; } EXPORT_SYMBOL(of_mm_gpiochip_add); + +void of_gpiochip_add(struct gpio_chip *chip) +{ + if ((!chip->of_node) && (chip->dev)) + chip->of_node = chip->dev->of_node; + + if (!chip->of_node) + return; + + if (!chip->of_xlate) { + chip->of_gpio_n_cells = 2; + chip->of_xlate = of_gpio_simple_xlate; + } + + of_node_get(chip->of_node); +} + +void of_gpiochip_remove(struct gpio_chip *chip) +{ + if (chip->of_node) + of_node_put(chip->of_node); +} + +/* Private function for resolving node pointer to gpio_chip */ +static int of_gpiochip_is_match(struct gpio_chip *chip, void *data) +{ + return chip->of_node == data; +} + +struct gpio_chip *of_node_to_gpiochip(struct device_node *np) +{ + return gpiochip_find(np, of_gpiochip_is_match); +} diff --git a/drivers/of/irq.c b/drivers/of/irq.c new file mode 100644 index 00000000000..6e595e5a397 --- /dev/null +++ b/drivers/of/irq.c @@ -0,0 +1,349 @@ +/* + * Derived from arch/i386/kernel/irq.c + * Copyright (C) 1992 Linus Torvalds + * Adapted from arch/i386 by Gary Thomas + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * Updated and modified by Cort Dougan <cort@fsmlabs.com> + * Copyright (C) 1996-2001 Cort Dougan + * Adapted for Power Macintosh by Paul Mackerras + * Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * This file contains the code used to make IRQ descriptions in the + * device tree to actual irq numbers on an interrupt controller + * driver. + */ + +#include <linux/errno.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_irq.h> +#include <linux/string.h> + +/** + * irq_of_parse_and_map - Parse and map an interrupt into linux virq space + * @device: Device node of the device whose interrupt is to be mapped + * @index: Index of the interrupt to map + * + * This function is a wrapper that chains of_irq_map_one() and + * irq_create_of_mapping() to make things easier to callers + */ +unsigned int irq_of_parse_and_map(struct device_node *dev, int index) +{ + struct of_irq oirq; + + if (of_irq_map_one(dev, index, &oirq)) + return NO_IRQ; + + return irq_create_of_mapping(oirq.controller, oirq.specifier, + oirq.size); +} +EXPORT_SYMBOL_GPL(irq_of_parse_and_map); + +/** + * of_irq_find_parent - Given a device node, find its interrupt parent node + * @child: pointer to device node + * + * Returns a pointer to the interrupt parent node, or NULL if the interrupt + * parent could not be determined. + */ +static struct device_node *of_irq_find_parent(struct device_node *child) +{ + struct device_node *p; + const __be32 *parp; + + if (!of_node_get(child)) + return NULL; + + do { + parp = of_get_property(child, "interrupt-parent", NULL); + if (parp == NULL) + p = of_get_parent(child); + else { + if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) + p = of_node_get(of_irq_dflt_pic); + else + p = of_find_node_by_phandle(be32_to_cpup(parp)); + } + of_node_put(child); + child = p; + } while (p && of_get_property(p, "#interrupt-cells", NULL) == NULL); + + return p; +} + +/** + * of_irq_map_raw - Low level interrupt tree parsing + * @parent: the device interrupt parent + * @intspec: interrupt specifier ("interrupts" property of the device) + * @ointsize: size of the passed in interrupt specifier + * @addr: address specifier (start of "reg" property of the device) + * @out_irq: structure of_irq filled by this function + * + * Returns 0 on success and a negative number on error + * + * This function is a low-level interrupt tree walking function. It + * can be used to do a partial walk with synthetized reg and interrupts + * properties, for example when resolving PCI interrupts when no device + * node exist for the parent. + */ +int of_irq_map_raw(struct device_node *parent, const __be32 *intspec, + u32 ointsize, const __be32 *addr, struct of_irq *out_irq) +{ + struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL; + const __be32 *tmp, *imap, *imask; + u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0; + int imaplen, match, i; + + pr_debug("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n", + parent->full_name, be32_to_cpup(intspec), + be32_to_cpup(intspec + 1), ointsize); + + ipar = of_node_get(parent); + + /* First get the #interrupt-cells property of the current cursor + * that tells us how to interpret the passed-in intspec. If there + * is none, we are nice and just walk up the tree + */ + do { + tmp = of_get_property(ipar, "#interrupt-cells", NULL); + if (tmp != NULL) { + intsize = be32_to_cpu(*tmp); + break; + } + tnode = ipar; + ipar = of_irq_find_parent(ipar); + of_node_put(tnode); + } while (ipar); + if (ipar == NULL) { + pr_debug(" -> no parent found !\n"); + goto fail; + } + + pr_debug("of_irq_map_raw: ipar=%s, size=%d\n", ipar->full_name, intsize); + + if (ointsize != intsize) + return -EINVAL; + + /* Look for this #address-cells. We have to implement the old linux + * trick of looking for the parent here as some device-trees rely on it + */ + old = of_node_get(ipar); + do { + tmp = of_get_property(old, "#address-cells", NULL); + tnode = of_get_parent(old); + of_node_put(old); + old = tnode; + } while (old && tmp == NULL); + of_node_put(old); + old = NULL; + addrsize = (tmp == NULL) ? 2 : be32_to_cpu(*tmp); + + pr_debug(" -> addrsize=%d\n", addrsize); + + /* Now start the actual "proper" walk of the interrupt tree */ + while (ipar != NULL) { + /* Now check if cursor is an interrupt-controller and if it is + * then we are done + */ + if (of_get_property(ipar, "interrupt-controller", NULL) != + NULL) { + pr_debug(" -> got it !\n"); + for (i = 0; i < intsize; i++) + out_irq->specifier[i] = + of_read_number(intspec +i, 1); + out_irq->size = intsize; + out_irq->controller = ipar; + of_node_put(old); + return 0; + } + + /* Now look for an interrupt-map */ + imap = of_get_property(ipar, "interrupt-map", &imaplen); + /* No interrupt map, check for an interrupt parent */ + if (imap == NULL) { + pr_debug(" -> no map, getting parent\n"); + newpar = of_irq_find_parent(ipar); + goto skiplevel; + } + imaplen /= sizeof(u32); + + /* Look for a mask */ + imask = of_get_property(ipar, "interrupt-map-mask", NULL); + + /* If we were passed no "reg" property and we attempt to parse + * an interrupt-map, then #address-cells must be 0. + * Fail if it's not. + */ + if (addr == NULL && addrsize != 0) { + pr_debug(" -> no reg passed in when needed !\n"); + goto fail; + } + + /* Parse interrupt-map */ + match = 0; + while (imaplen > (addrsize + intsize + 1) && !match) { + /* Compare specifiers */ + match = 1; + for (i = 0; i < addrsize && match; ++i) { + u32 mask = imask ? imask[i] : 0xffffffffu; + match = ((addr[i] ^ imap[i]) & mask) == 0; + } + for (; i < (addrsize + intsize) && match; ++i) { + u32 mask = imask ? imask[i] : 0xffffffffu; + match = + ((intspec[i-addrsize] ^ imap[i]) & mask) == 0; + } + imap += addrsize + intsize; + imaplen -= addrsize + intsize; + + pr_debug(" -> match=%d (imaplen=%d)\n", match, imaplen); + + /* Get the interrupt parent */ + if (of_irq_workarounds & OF_IMAP_NO_PHANDLE) + newpar = of_node_get(of_irq_dflt_pic); + else + newpar = of_find_node_by_phandle(be32_to_cpup(imap)); + imap++; + --imaplen; + + /* Check if not found */ + if (newpar == NULL) { + pr_debug(" -> imap parent not found !\n"); + goto fail; + } + + /* Get #interrupt-cells and #address-cells of new + * parent + */ + tmp = of_get_property(newpar, "#interrupt-cells", NULL); + if (tmp == NULL) { + pr_debug(" -> parent lacks #interrupt-cells!\n"); + goto fail; + } + newintsize = be32_to_cpu(*tmp); + tmp = of_get_property(newpar, "#address-cells", NULL); + newaddrsize = (tmp == NULL) ? 0 : be32_to_cpu(*tmp); + + pr_debug(" -> newintsize=%d, newaddrsize=%d\n", + newintsize, newaddrsize); + + /* Check for malformed properties */ + if (imaplen < (newaddrsize + newintsize)) + goto fail; + + imap += newaddrsize + newintsize; + imaplen -= newaddrsize + newintsize; + + pr_debug(" -> imaplen=%d\n", imaplen); + } + if (!match) + goto fail; + + of_node_put(old); + old = of_node_get(newpar); + addrsize = newaddrsize; + intsize = newintsize; + intspec = imap - intsize; + addr = intspec - addrsize; + + skiplevel: + /* Iterate again with new parent */ + pr_debug(" -> new parent: %s\n", newpar ? newpar->full_name : "<>"); + of_node_put(ipar); + ipar = newpar; + newpar = NULL; + } + fail: + of_node_put(ipar); + of_node_put(old); + of_node_put(newpar); + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(of_irq_map_raw); + +/** + * of_irq_map_one - Resolve an interrupt for a device + * @device: the device whose interrupt is to be resolved + * @index: index of the interrupt to resolve + * @out_irq: structure of_irq filled by this function + * + * This function resolves an interrupt, walking the tree, for a given + * device-tree node. It's the high level pendant to of_irq_map_raw(). + */ +int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq) +{ + struct device_node *p; + const __be32 *intspec, *tmp, *addr; + u32 intsize, intlen; + int res = -EINVAL; + + pr_debug("of_irq_map_one: dev=%s, index=%d\n", device->full_name, index); + + /* OldWorld mac stuff is "special", handle out of line */ + if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return of_irq_map_oldworld(device, index, out_irq); + + /* Get the interrupts property */ + intspec = of_get_property(device, "interrupts", &intlen); + if (intspec == NULL) + return -EINVAL; + intlen /= sizeof(*intspec); + + pr_debug(" intspec=%d intlen=%d\n", be32_to_cpup(intspec), intlen); + + /* Get the reg property (if any) */ + addr = of_get_property(device, "reg", NULL); + + /* Look for the interrupt parent. */ + p = of_irq_find_parent(device); + if (p == NULL) + return -EINVAL; + + /* Get size of interrupt specifier */ + tmp = of_get_property(p, "#interrupt-cells", NULL); + if (tmp == NULL) + goto out; + intsize = be32_to_cpu(*tmp); + + pr_debug(" intsize=%d intlen=%d\n", intsize, intlen); + + /* Check index */ + if ((index + 1) * intsize > intlen) + goto out; + + /* Get new specifier and map it */ + res = of_irq_map_raw(p, intspec + index * intsize, intsize, + addr, out_irq); + out: + of_node_put(p); + return res; +} +EXPORT_SYMBOL_GPL(of_irq_map_one); + +/** + * of_irq_to_resource - Decode a node's IRQ and return it as a resource + * @dev: pointer to device tree node + * @index: zero-based index of the irq + * @r: pointer to resource structure to return result into. + */ +int of_irq_to_resource(struct device_node *dev, int index, struct resource *r) +{ + int irq = irq_of_parse_and_map(dev, index); + + /* Only dereference the resource if both the + * resource and the irq are valid. */ + if (r && irq != NO_IRQ) { + r->start = r->end = irq; + r->flags = IORESOURCE_IRQ; + r->name = dev->full_name; + } + + return irq; +} +EXPORT_SYMBOL_GPL(of_irq_to_resource); diff --git a/drivers/of/of_i2c.c b/drivers/of/of_i2c.c index ab6522c8e4f..0a694debd22 100644 --- a/drivers/of/of_i2c.c +++ b/drivers/of/of_i2c.c @@ -14,57 +14,65 @@ #include <linux/i2c.h> #include <linux/of.h> #include <linux/of_i2c.h> +#include <linux/of_irq.h> #include <linux/module.h> -void of_register_i2c_devices(struct i2c_adapter *adap, - struct device_node *adap_node) +void of_i2c_register_devices(struct i2c_adapter *adap) { void *result; struct device_node *node; - for_each_child_of_node(adap_node, node) { + /* Only register child devices if the adapter has a node pointer set */ + if (!adap->dev.of_node) + return; + + dev_dbg(&adap->dev, "of_i2c: walking child nodes\n"); + + for_each_child_of_node(adap->dev.of_node, node) { struct i2c_board_info info = {}; struct dev_archdata dev_ad = {}; const __be32 *addr; int len; - if (of_modalias_node(node, info.type, sizeof(info.type)) < 0) + dev_dbg(&adap->dev, "of_i2c: register %s\n", node->full_name); + + if (of_modalias_node(node, info.type, sizeof(info.type)) < 0) { + dev_err(&adap->dev, "of_i2c: modalias failure on %s\n", + node->full_name); continue; + } addr = of_get_property(node, "reg", &len); - if (!addr || len < sizeof(int) || *addr > (1 << 10) - 1) { - printk(KERN_ERR - "of-i2c: invalid i2c device entry\n"); + if (!addr || (len < sizeof(int))) { + dev_err(&adap->dev, "of_i2c: invalid reg on %s\n", + node->full_name); continue; } - info.irq = irq_of_parse_and_map(node, 0); - info.addr = be32_to_cpup(addr); + if (info.addr > (1 << 10) - 1) { + dev_err(&adap->dev, "of_i2c: invalid addr=%x on %s\n", + info.addr, node->full_name); + continue; + } - info.of_node = node; + info.irq = irq_of_parse_and_map(node, 0); + info.of_node = of_node_get(node); info.archdata = &dev_ad; request_module("%s", info.type); result = i2c_new_device(adap, &info); if (result == NULL) { - printk(KERN_ERR - "of-i2c: Failed to load driver for %s\n", - info.type); + dev_err(&adap->dev, "of_i2c: Failure registering %s\n", + node->full_name); + of_node_put(node); irq_dispose_mapping(info.irq); continue; } - - /* - * Get the node to not lose the dev_archdata->of_node. - * Currently there is no way to put it back, as well as no - * of_unregister_i2c_devices() call. - */ - of_node_get(node); } } -EXPORT_SYMBOL(of_register_i2c_devices); +EXPORT_SYMBOL(of_i2c_register_devices); static int of_dev_node_match(struct device *dev, void *data) { diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 42a6715f8e8..1fce00eb421 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -15,6 +15,7 @@ #include <linux/err.h> #include <linux/phy.h> #include <linux/of.h> +#include <linux/of_irq.h> #include <linux/of_mdio.h> #include <linux/module.h> diff --git a/drivers/of/of_spi.c b/drivers/of/of_spi.c index 5fed7e3c7da..1dbce58a58b 100644 --- a/drivers/of/of_spi.c +++ b/drivers/of/of_spi.c @@ -9,17 +9,17 @@ #include <linux/of.h> #include <linux/device.h> #include <linux/spi/spi.h> +#include <linux/of_irq.h> #include <linux/of_spi.h> /** * of_register_spi_devices - Register child devices onto the SPI bus * @master: Pointer to spi_master device - * @np: parent node of SPI device nodes * - * Registers an spi_device for each child node of 'np' which has a 'reg' + * Registers an spi_device for each child node of master node which has a 'reg' * property. */ -void of_register_spi_devices(struct spi_master *master, struct device_node *np) +void of_register_spi_devices(struct spi_master *master) { struct spi_device *spi; struct device_node *nc; @@ -27,7 +27,10 @@ void of_register_spi_devices(struct spi_master *master, struct device_node *np) int rc; int len; - for_each_child_of_node(np, nc) { + if (!master->dev.of_node) + return; + + for_each_child_of_node(master->dev.of_node, nc) { /* Alloc an spi_device */ spi = spi_alloc_device(master); if (!spi) { diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 7dacc1ebe91..bb72223c22a 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -14,8 +14,105 @@ #include <linux/errno.h> #include <linux/module.h> #include <linux/device.h> +#include <linux/dma-mapping.h> +#include <linux/slab.h> +#include <linux/of_address.h> #include <linux/of_device.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> +#include <linux/platform_device.h> + +static int of_dev_node_match(struct device *dev, void *data) +{ + return dev->of_node == data; +} + +/** + * of_find_device_by_node - Find the platform_device associated with a node + * @np: Pointer to device tree node + * + * Returns platform_device pointer, or NULL if not found + */ +struct platform_device *of_find_device_by_node(struct device_node *np) +{ + struct device *dev; + + dev = bus_find_device(&platform_bus_type, NULL, np, of_dev_node_match); + return dev ? to_platform_device(dev) : NULL; +} +EXPORT_SYMBOL(of_find_device_by_node); + +static int platform_driver_probe_shim(struct platform_device *pdev) +{ + struct platform_driver *pdrv; + struct of_platform_driver *ofpdrv; + const struct of_device_id *match; + + pdrv = container_of(pdev->dev.driver, struct platform_driver, driver); + ofpdrv = container_of(pdrv, struct of_platform_driver, platform_driver); + + /* There is an unlikely chance that an of_platform driver might match + * on a non-OF platform device. If so, then of_match_device() will + * come up empty. Return -EINVAL in this case so other drivers get + * the chance to bind. */ + match = of_match_device(pdev->dev.driver->of_match_table, &pdev->dev); + return match ? ofpdrv->probe(pdev, match) : -EINVAL; +} + +static void platform_driver_shutdown_shim(struct platform_device *pdev) +{ + struct platform_driver *pdrv; + struct of_platform_driver *ofpdrv; + + pdrv = container_of(pdev->dev.driver, struct platform_driver, driver); + ofpdrv = container_of(pdrv, struct of_platform_driver, platform_driver); + ofpdrv->shutdown(pdev); +} + +/** + * of_register_platform_driver + */ +int of_register_platform_driver(struct of_platform_driver *drv) +{ + char *of_name; + + /* setup of_platform_driver to platform_driver adaptors */ + drv->platform_driver.driver = drv->driver; + + /* Prefix the driver name with 'of:' to avoid namespace collisions + * and bogus matches. There are some drivers in the tree that + * register both an of_platform_driver and a platform_driver with + * the same name. This is a temporary measure until they are all + * cleaned up --gcl July 29, 2010 */ + of_name = kmalloc(strlen(drv->driver.name) + 5, GFP_KERNEL); + if (!of_name) + return -ENOMEM; + sprintf(of_name, "of:%s", drv->driver.name); + drv->platform_driver.driver.name = of_name; + + if (drv->probe) + drv->platform_driver.probe = platform_driver_probe_shim; + drv->platform_driver.remove = drv->remove; + if (drv->shutdown) + drv->platform_driver.shutdown = platform_driver_shutdown_shim; + drv->platform_driver.suspend = drv->suspend; + drv->platform_driver.resume = drv->resume; + + return platform_driver_register(&drv->platform_driver); +} +EXPORT_SYMBOL(of_register_platform_driver); + +void of_unregister_platform_driver(struct of_platform_driver *drv) +{ + platform_driver_unregister(&drv->platform_driver); + kfree(drv->platform_driver.driver.name); + drv->platform_driver.driver.name = NULL; +} +EXPORT_SYMBOL(of_unregister_platform_driver); + +#if defined(CONFIG_PPC_DCR) +#include <asm/dcr.h> +#endif extern struct device_attribute of_platform_device_attrs[]; @@ -33,11 +130,11 @@ static int of_platform_device_probe(struct device *dev) { int error = -ENODEV; struct of_platform_driver *drv; - struct of_device *of_dev; + struct platform_device *of_dev; const struct of_device_id *match; drv = to_of_platform_driver(dev->driver); - of_dev = to_of_device(dev); + of_dev = to_platform_device(dev); if (!drv->probe) return error; @@ -55,7 +152,7 @@ static int of_platform_device_probe(struct device *dev) static int of_platform_device_remove(struct device *dev) { - struct of_device *of_dev = to_of_device(dev); + struct platform_device *of_dev = to_platform_device(dev); struct of_platform_driver *drv = to_of_platform_driver(dev->driver); if (dev->driver && drv->remove) @@ -65,7 +162,7 @@ static int of_platform_device_remove(struct device *dev) static void of_platform_device_shutdown(struct device *dev) { - struct of_device *of_dev = to_of_device(dev); + struct platform_device *of_dev = to_platform_device(dev); struct of_platform_driver *drv = to_of_platform_driver(dev->driver); if (dev->driver && drv->shutdown) @@ -76,7 +173,7 @@ static void of_platform_device_shutdown(struct device *dev) static int of_platform_legacy_suspend(struct device *dev, pm_message_t mesg) { - struct of_device *of_dev = to_of_device(dev); + struct platform_device *of_dev = to_platform_device(dev); struct of_platform_driver *drv = to_of_platform_driver(dev->driver); int ret = 0; @@ -87,7 +184,7 @@ static int of_platform_legacy_suspend(struct device *dev, pm_message_t mesg) static int of_platform_legacy_resume(struct device *dev) { - struct of_device *of_dev = to_of_device(dev); + struct platform_device *of_dev = to_platform_device(dev); struct of_platform_driver *drv = to_of_platform_driver(dev->driver); int ret = 0; @@ -384,15 +481,286 @@ int of_bus_type_init(struct bus_type *bus, const char *name) int of_register_driver(struct of_platform_driver *drv, struct bus_type *bus) { - drv->driver.bus = bus; + /* + * Temporary: of_platform_bus used to be distinct from the platform + * bus. It isn't anymore, and so drivers on the platform bus need + * to be registered in a special way. + * + * After all of_platform_bus_type drivers are converted to + * platform_drivers, this exception can be removed. + */ + if (bus == &platform_bus_type) + return of_register_platform_driver(drv); /* register with core */ + drv->driver.bus = bus; return driver_register(&drv->driver); } EXPORT_SYMBOL(of_register_driver); void of_unregister_driver(struct of_platform_driver *drv) { - driver_unregister(&drv->driver); + if (drv->driver.bus == &platform_bus_type) + of_unregister_platform_driver(drv); + else + driver_unregister(&drv->driver); } EXPORT_SYMBOL(of_unregister_driver); + +#if !defined(CONFIG_SPARC) +/* + * The following routines scan a subtree and registers a device for + * each applicable node. + * + * Note: sparc doesn't use these routines because it has a different + * mechanism for creating devices from device tree nodes. + */ + +/** + * of_device_make_bus_id - Use the device node data to assign a unique name + * @dev: pointer to device structure that is linked to a device tree node + * + * This routine will first try using either the dcr-reg or the reg property + * value to derive a unique name. As a last resort it will use the node + * name followed by a unique number. + */ +void of_device_make_bus_id(struct device *dev) +{ + static atomic_t bus_no_reg_magic; + struct device_node *node = dev->of_node; + const u32 *reg; + u64 addr; + int magic; + +#ifdef CONFIG_PPC_DCR + /* + * If it's a DCR based device, use 'd' for native DCRs + * and 'D' for MMIO DCRs. + */ + reg = of_get_property(node, "dcr-reg", NULL); + if (reg) { +#ifdef CONFIG_PPC_DCR_NATIVE + dev_set_name(dev, "d%x.%s", *reg, node->name); +#else /* CONFIG_PPC_DCR_NATIVE */ + u64 addr = of_translate_dcr_address(node, *reg, NULL); + if (addr != OF_BAD_ADDR) { + dev_set_name(dev, "D%llx.%s", + (unsigned long long)addr, node->name); + return; + } +#endif /* !CONFIG_PPC_DCR_NATIVE */ + } +#endif /* CONFIG_PPC_DCR */ + + /* + * For MMIO, get the physical address + */ + reg = of_get_property(node, "reg", NULL); + if (reg) { + addr = of_translate_address(node, reg); + if (addr != OF_BAD_ADDR) { + dev_set_name(dev, "%llx.%s", + (unsigned long long)addr, node->name); + return; + } + } + + /* + * No BusID, use the node name and add a globally incremented + * counter (and pray...) + */ + magic = atomic_add_return(1, &bus_no_reg_magic); + dev_set_name(dev, "%s.%d", node->name, magic - 1); +} + +/** + * of_device_alloc - Allocate and initialize an of_device + * @np: device node to assign to device + * @bus_id: Name to assign to the device. May be null to use default name. + * @parent: Parent device. + */ +struct platform_device *of_device_alloc(struct device_node *np, + const char *bus_id, + struct device *parent) +{ + struct platform_device *dev; + int rc, i, num_reg = 0, num_irq = 0; + struct resource *res, temp_res; + + /* First count how many resources are needed */ + while (of_address_to_resource(np, num_reg, &temp_res) == 0) + num_reg++; + while (of_irq_to_resource(np, num_irq, &temp_res) != NO_IRQ) + num_irq++; + + /* Allocate memory for both the struct device and the resource table */ + dev = kzalloc(sizeof(*dev) + (sizeof(*res) * (num_reg + num_irq)), + GFP_KERNEL); + if (!dev) + return NULL; + res = (struct resource *) &dev[1]; + + /* Populate the resource table */ + if (num_irq || num_reg) { + dev->num_resources = num_reg + num_irq; + dev->resource = res; + for (i = 0; i < num_reg; i++, res++) { + rc = of_address_to_resource(np, i, res); + WARN_ON(rc); + } + for (i = 0; i < num_irq; i++, res++) { + rc = of_irq_to_resource(np, i, res); + WARN_ON(rc == NO_IRQ); + } + } + + dev->dev.of_node = of_node_get(np); +#if defined(CONFIG_PPC) || defined(CONFIG_MICROBLAZE) + dev->dev.dma_mask = &dev->archdata.dma_mask; +#endif + dev->dev.parent = parent; + dev->dev.release = of_release_dev; + + if (bus_id) + dev_set_name(&dev->dev, "%s", bus_id); + else + of_device_make_bus_id(&dev->dev); + + return dev; +} +EXPORT_SYMBOL(of_device_alloc); + +/** + * of_platform_device_create - Alloc, initialize and register an of_device + * @np: pointer to node to create device for + * @bus_id: name to assign device + * @parent: Linux device model parent device. + */ +struct platform_device *of_platform_device_create(struct device_node *np, + const char *bus_id, + struct device *parent) +{ + struct platform_device *dev; + + dev = of_device_alloc(np, bus_id, parent); + if (!dev) + return NULL; + +#if defined(CONFIG_PPC) || defined(CONFIG_MICROBLAZE) + dev->archdata.dma_mask = 0xffffffffUL; +#endif + dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + dev->dev.bus = &platform_bus_type; + + /* We do not fill the DMA ops for platform devices by default. + * This is currently the responsibility of the platform code + * to do such, possibly using a device notifier + */ + + if (of_device_register(dev) != 0) { + of_device_free(dev); + return NULL; + } + + return dev; +} +EXPORT_SYMBOL(of_platform_device_create); + +/** + * of_platform_bus_create - Create an OF device for a bus node and all its + * children. Optionally recursively instantiate matching busses. + * @bus: device node of the bus to instantiate + * @matches: match table, NULL to use the default, OF_NO_DEEP_PROBE to + * disallow recursive creation of child busses + */ +static int of_platform_bus_create(const struct device_node *bus, + const struct of_device_id *matches, + struct device *parent) +{ + struct device_node *child; + struct platform_device *dev; + int rc = 0; + + for_each_child_of_node(bus, child) { + pr_debug(" create child: %s\n", child->full_name); + dev = of_platform_device_create(child, NULL, parent); + if (dev == NULL) + rc = -ENOMEM; + else if (!of_match_node(matches, child)) + continue; + if (rc == 0) { + pr_debug(" and sub busses\n"); + rc = of_platform_bus_create(child, matches, &dev->dev); + } + if (rc) { + of_node_put(child); + break; + } + } + return rc; +} + +/** + * of_platform_bus_probe - Probe the device-tree for platform busses + * @root: parent of the first level to probe or NULL for the root of the tree + * @matches: match table, NULL to use the default + * @parent: parent to hook devices from, NULL for toplevel + * + * Note that children of the provided root are not instantiated as devices + * unless the specified root itself matches the bus list and is not NULL. + */ +int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent) +{ + struct device_node *child; + struct platform_device *dev; + int rc = 0; + + if (WARN_ON(!matches || matches == OF_NO_DEEP_PROBE)) + return -EINVAL; + if (root == NULL) + root = of_find_node_by_path("/"); + else + of_node_get(root); + if (root == NULL) + return -EINVAL; + + pr_debug("of_platform_bus_probe()\n"); + pr_debug(" starting at: %s\n", root->full_name); + + /* Do a self check of bus type, if there's a match, create + * children + */ + if (of_match_node(matches, root)) { + pr_debug(" root match, create all sub devices\n"); + dev = of_platform_device_create(root, NULL, parent); + if (dev == NULL) { + rc = -ENOMEM; + goto bail; + } + pr_debug(" create all sub busses\n"); + rc = of_platform_bus_create(root, matches, &dev->dev); + goto bail; + } + for_each_child_of_node(root, child) { + if (!of_match_node(matches, child)) + continue; + + pr_debug(" match: %s\n", child->full_name); + dev = of_platform_device_create(child, NULL, parent); + if (dev == NULL) + rc = -ENOMEM; + else + rc = of_platform_bus_create(child, matches, &dev->dev); + if (rc) { + of_node_put(child); + break; + } + } + bail: + of_node_put(root); + return rc; +} +EXPORT_SYMBOL(of_platform_bus_probe); +#endif /* !CONFIG_SPARC */ diff --git a/drivers/oprofile/event_buffer.c b/drivers/oprofile/event_buffer.c index 5df60a6b677..dd87e86048b 100644 --- a/drivers/oprofile/event_buffer.c +++ b/drivers/oprofile/event_buffer.c @@ -135,7 +135,7 @@ static int event_buffer_open(struct inode *inode, struct file *file) * echo 1 >/dev/oprofile/enable */ - return 0; + return nonseekable_open(inode, file); fail: dcookie_unregister(file->private_data); @@ -205,4 +205,5 @@ const struct file_operations event_buffer_fops = { .open = event_buffer_open, .release = event_buffer_release, .read = event_buffer_read, + .llseek = no_llseek, }; diff --git a/drivers/parport/parport_sunbpp.c b/drivers/parport/parport_sunbpp.c index 9a5b4b89416..210a6441a06 100644 --- a/drivers/parport/parport_sunbpp.c +++ b/drivers/parport/parport_sunbpp.c @@ -295,7 +295,7 @@ static int __devinit bpp_probe(struct of_device *op, const struct of_device_id * void __iomem *base; struct parport *p; - irq = op->irqs[0]; + irq = op->archdata.irqs[0]; base = of_ioremap(&op->resource[0], 0, resource_size(&op->resource[0]), "sunbpp"); @@ -393,12 +393,12 @@ static struct of_platform_driver bpp_sbus_driver = { static int __init parport_sunbpp_init(void) { - return of_register_driver(&bpp_sbus_driver, &of_bus_type); + return of_register_platform_driver(&bpp_sbus_driver); } static void __exit parport_sunbpp_exit(void) { - of_unregister_driver(&bpp_sbus_driver); + of_unregister_platform_driver(&bpp_sbus_driver); } MODULE_AUTHOR("Derrick J Brashear"); diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index c9171be7456..6a5af18faf6 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -3698,6 +3698,8 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain, if (cap == IOMMU_CAP_CACHE_COHERENCY) return dmar_domain->iommu_snooping; + if (cap == IOMMU_CAP_INTR_REMAP) + return intr_remapping_enabled; return 0; } diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c index 1315ac688aa..1694a0e2845 100644 --- a/drivers/pci/intr_remapping.c +++ b/drivers/pci/intr_remapping.c @@ -311,8 +311,8 @@ int modify_irte(int irq, struct irte *irte_modified) index = irq_iommu->irte_index + irq_iommu->sub_handle; irte = &iommu->ir_table->base[index]; - set_64bit((unsigned long *)&irte->low, irte_modified->low); - set_64bit((unsigned long *)&irte->high, irte_modified->high); + set_64bit(&irte->low, irte_modified->low); + set_64bit(&irte->high, irte_modified->high); __iommu_flush_cache(iommu, irte, sizeof(*irte)); rc = qi_flush_iec(iommu, index, 0); @@ -393,8 +393,8 @@ static int clear_entries(struct irq_2_iommu *irq_iommu) end = start + (1 << irq_iommu->irte_mask); for (entry = start; entry < end; entry++) { - set_64bit((unsigned long *)&entry->low, 0); - set_64bit((unsigned long *)&entry->high, 0); + set_64bit(&entry->low, 0); + set_64bit(&entry->high, 0); } return qi_flush_iec(iommu, index, irq_iommu->irte_mask); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 477345d4164..a0c20d9e839 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -1459,6 +1459,7 @@ static void quirk_jmicron_ata(struct pci_dev *pdev) switch (pdev->device) { case PCI_DEVICE_ID_JMICRON_JMB360: /* SATA single port */ case PCI_DEVICE_ID_JMICRON_JMB362: /* SATA dual ports */ + case PCI_DEVICE_ID_JMICRON_JMB364: /* SATA dual ports */ /* The controller should be in single function ahci mode */ conf1 |= 0x0002A100; /* Set 8, 13, 15, 17 */ break; @@ -1470,6 +1471,7 @@ static void quirk_jmicron_ata(struct pci_dev *pdev) /* Fall through */ case PCI_DEVICE_ID_JMICRON_JMB361: case PCI_DEVICE_ID_JMICRON_JMB363: + case PCI_DEVICE_ID_JMICRON_JMB369: /* Enable dual function mode, AHCI on fn 0, IDE fn1 */ /* Set the class codes correctly and then direct IDE 0 */ conf1 |= 0x00C2A1B3; /* Set 0, 1, 4, 5, 7, 8, 13, 15, 17, 22, 23 */ @@ -1496,16 +1498,20 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB360, qui DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB361, quirk_jmicron_ata); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB362, quirk_jmicron_ata); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB363, quirk_jmicron_ata); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB364, quirk_jmicron_ata); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB365, quirk_jmicron_ata); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB366, quirk_jmicron_ata); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB368, quirk_jmicron_ata); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB369, quirk_jmicron_ata); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB360, quirk_jmicron_ata); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB361, quirk_jmicron_ata); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB362, quirk_jmicron_ata); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB363, quirk_jmicron_ata); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB364, quirk_jmicron_ata); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB365, quirk_jmicron_ata); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB366, quirk_jmicron_ata); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB368, quirk_jmicron_ata); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB369, quirk_jmicron_ata); #endif diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c index 8bfdd63a1fc..3e89c313e98 100644 --- a/drivers/sbus/char/bbc_i2c.c +++ b/drivers/sbus/char/bbc_i2c.c @@ -317,7 +317,7 @@ static struct bbc_i2c_bus * __init attach_one_i2c(struct of_device *op, int inde bp->waiting = 0; init_waitqueue_head(&bp->wq); - if (request_irq(op->irqs[0], bbc_i2c_interrupt, + if (request_irq(op->archdata.irqs[0], bbc_i2c_interrupt, IRQF_SHARED, "bbc_i2c", bp)) goto fail; @@ -373,7 +373,7 @@ static int __devinit bbc_i2c_probe(struct of_device *op, err = bbc_envctrl_init(bp); if (err) { - free_irq(op->irqs[0], bp); + free_irq(op->archdata.irqs[0], bp); if (bp->i2c_bussel_reg) of_iounmap(&op->resource[0], bp->i2c_bussel_reg, 1); if (bp->i2c_control_regs) @@ -392,7 +392,7 @@ static int __devexit bbc_i2c_remove(struct of_device *op) bbc_envctrl_cleanup(bp); - free_irq(op->irqs[0], bp); + free_irq(op->archdata.irqs[0], bp); if (bp->i2c_bussel_reg) of_iounmap(&op->resource[0], bp->i2c_bussel_reg, 1); @@ -425,12 +425,12 @@ static struct of_platform_driver bbc_i2c_driver = { static int __init bbc_i2c_init(void) { - return of_register_driver(&bbc_i2c_driver, &of_bus_type); + return of_register_platform_driver(&bbc_i2c_driver); } static void __exit bbc_i2c_exit(void) { - of_unregister_driver(&bbc_i2c_driver); + of_unregister_platform_driver(&bbc_i2c_driver); } module_init(bbc_i2c_init); diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c index 4ad4d2c9107..47db97583ea 100644 --- a/drivers/sbus/char/display7seg.c +++ b/drivers/sbus/char/display7seg.c @@ -277,12 +277,12 @@ static struct of_platform_driver d7s_driver = { static int __init d7s_init(void) { - return of_register_driver(&d7s_driver, &of_bus_type); + return of_register_platform_driver(&d7s_driver); } static void __exit d7s_exit(void) { - of_unregister_driver(&d7s_driver); + of_unregister_platform_driver(&d7s_driver); } module_init(d7s_init); diff --git a/drivers/sbus/char/envctrl.c b/drivers/sbus/char/envctrl.c index bd0bbc62135..3c27f45e2b6 100644 --- a/drivers/sbus/char/envctrl.c +++ b/drivers/sbus/char/envctrl.c @@ -1140,12 +1140,12 @@ static struct of_platform_driver envctrl_driver = { static int __init envctrl_init(void) { - return of_register_driver(&envctrl_driver, &of_bus_type); + return of_register_platform_driver(&envctrl_driver); } static void __exit envctrl_exit(void) { - of_unregister_driver(&envctrl_driver); + of_unregister_platform_driver(&envctrl_driver); } module_init(envctrl_init); diff --git a/drivers/sbus/char/flash.c b/drivers/sbus/char/flash.c index ed9494e1885..8bb31c584b6 100644 --- a/drivers/sbus/char/flash.c +++ b/drivers/sbus/char/flash.c @@ -219,12 +219,12 @@ static struct of_platform_driver flash_driver = { static int __init flash_init(void) { - return of_register_driver(&flash_driver, &of_bus_type); + return of_register_platform_driver(&flash_driver); } static void __exit flash_cleanup(void) { - of_unregister_driver(&flash_driver); + of_unregister_platform_driver(&flash_driver); } module_init(flash_init); diff --git a/drivers/sbus/char/uctrl.c b/drivers/sbus/char/uctrl.c index 079da4cb45a..41eb6725ff5 100644 --- a/drivers/sbus/char/uctrl.c +++ b/drivers/sbus/char/uctrl.c @@ -368,7 +368,7 @@ static int __devinit uctrl_probe(struct of_device *op, goto out_free; } - p->irq = op->irqs[0]; + p->irq = op->archdata.irqs[0]; err = request_irq(p->irq, uctrl_interrupt, 0, "uctrl", p); if (err) { printk(KERN_ERR "uctrl: Unable to register irq.\n"); @@ -438,12 +438,12 @@ static struct of_platform_driver uctrl_driver = { static int __init uctrl_init(void) { - return of_register_driver(&uctrl_driver, &of_bus_type); + return of_register_platform_driver(&uctrl_driver); } static void __exit uctrl_exit(void) { - of_unregister_driver(&uctrl_driver); + of_unregister_platform_driver(&uctrl_driver); } module_init(uctrl_init); diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c index ca5c15c779c..53d7ed0dc16 100644 --- a/drivers/scsi/qlogicpti.c +++ b/drivers/scsi/qlogicpti.c @@ -729,7 +729,7 @@ static int __devinit qpti_register_irq(struct qlogicpti *qpti) { struct of_device *op = qpti->op; - qpti->qhost->irq = qpti->irq = op->irqs[0]; + qpti->qhost->irq = qpti->irq = op->archdata.irqs[0]; /* We used to try various overly-clever things to * reduce the interrupt processing overhead on @@ -1302,7 +1302,7 @@ static int __devinit qpti_sbus_probe(struct of_device *op, const struct of_devic /* Sometimes Antares cards come up not completely * setup, and we get a report of a zero IRQ. */ - if (op->irqs[0] == 0) + if (op->archdata.irqs[0] == 0) return -ENODEV; host = scsi_host_alloc(tpnt, sizeof(struct qlogicpti)); @@ -1467,12 +1467,12 @@ static struct of_platform_driver qpti_sbus_driver = { static int __init qpti_init(void) { - return of_register_driver(&qpti_sbus_driver, &of_bus_type); + return of_register_platform_driver(&qpti_sbus_driver); } static void __exit qpti_exit(void) { - of_unregister_driver(&qpti_sbus_driver); + of_unregister_platform_driver(&qpti_sbus_driver); } MODULE_DESCRIPTION("QlogicISP SBUS driver"); diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index 026295e2c53..b4056d14f81 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -148,8 +148,6 @@ static inline void scsi_netlink_exit(void) {} /* scsi_pm.c */ #ifdef CONFIG_PM_OPS extern const struct dev_pm_ops scsi_bus_pm_ops; -#else /* CONFIG_PM_OPS */ -#define scsi_bus_pm_ops (*NULL) #endif #ifdef CONFIG_PM_RUNTIME extern void scsi_autopm_get_target(struct scsi_target *); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 562fb3bce26..c3f67373a4f 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -381,7 +381,9 @@ struct bus_type scsi_bus_type = { .name = "scsi", .match = scsi_bus_match, .uevent = scsi_bus_uevent, +#ifdef CONFIG_PM_OPS .pm = &scsi_bus_pm_ops, +#endif }; EXPORT_SYMBOL_GPL(scsi_bus_type); diff --git a/drivers/scsi/sun_esp.c b/drivers/scsi/sun_esp.c index 386dd9d602b..89ba6fe02f8 100644 --- a/drivers/scsi/sun_esp.c +++ b/drivers/scsi/sun_esp.c @@ -116,7 +116,7 @@ static int __devinit esp_sbus_register_irq(struct esp *esp) struct Scsi_Host *host = esp->host; struct of_device *op = esp->dev; - host->irq = op->irqs[0]; + host->irq = op->archdata.irqs[0]; return request_irq(host->irq, scsi_esp_intr, IRQF_SHARED, "ESP", esp); } @@ -644,12 +644,12 @@ static struct of_platform_driver esp_sbus_driver = { static int __init sunesp_init(void) { - return of_register_driver(&esp_sbus_driver, &of_bus_type); + return of_register_platform_driver(&esp_sbus_driver); } static void __exit sunesp_exit(void) { - of_unregister_driver(&esp_sbus_driver); + of_unregister_platform_driver(&esp_sbus_driver); } MODULE_DESCRIPTION("Sun ESP SCSI driver"); diff --git a/drivers/serial/kgdboc.c b/drivers/serial/kgdboc.c index a9a94ae7234..39f9a1adaa7 100644 --- a/drivers/serial/kgdboc.c +++ b/drivers/serial/kgdboc.c @@ -17,6 +17,7 @@ #include <linux/kdb.h> #include <linux/tty.h> #include <linux/console.h> +#include <linux/vt_kern.h> #define MAX_CONFIG_LEN 40 @@ -31,6 +32,7 @@ static struct kparam_string kps = { .maxlen = MAX_CONFIG_LEN, }; +static int kgdboc_use_kms; /* 1 if we use kernel mode switching */ static struct tty_driver *kgdb_tty_driver; static int kgdb_tty_line; @@ -104,6 +106,12 @@ static int configure_kgdboc(void) kgdboc_io_ops.is_console = 0; kgdb_tty_driver = NULL; + kgdboc_use_kms = 0; + if (strncmp(cptr, "kms,", 4) == 0) { + cptr += 4; + kgdboc_use_kms = 1; + } + if (kgdboc_register_kbd(&cptr)) goto do_register; @@ -201,8 +209,14 @@ static int param_set_kgdboc_var(const char *kmessage, struct kernel_param *kp) return configure_kgdboc(); } +static int dbg_restore_graphics; + static void kgdboc_pre_exp_handler(void) { + if (!dbg_restore_graphics && kgdboc_use_kms) { + dbg_restore_graphics = 1; + con_debug_enter(vc_cons[fg_console].d); + } /* Increment the module count when the debugger is active */ if (!kgdb_connected) try_module_get(THIS_MODULE); @@ -213,6 +227,10 @@ static void kgdboc_post_exp_handler(void) /* decrement the module count when the debugger detaches */ if (!kgdb_connected) module_put(THIS_MODULE); + if (kgdboc_use_kms && dbg_restore_graphics) { + dbg_restore_graphics = 0; + con_debug_leave(); + } } static struct kgdb_io kgdboc_io_ops = { diff --git a/drivers/serial/sunhv.c b/drivers/serial/sunhv.c index 890f9174296..a779e22d213 100644 --- a/drivers/serial/sunhv.c +++ b/drivers/serial/sunhv.c @@ -525,7 +525,7 @@ static int __devinit hv_probe(struct of_device *op, const struct of_device_id *m unsigned long minor; int err; - if (op->irqs[0] == 0xffffffff) + if (op->archdata.irqs[0] == 0xffffffff) return -ENODEV; port = kzalloc(sizeof(struct uart_port), GFP_KERNEL); @@ -557,7 +557,7 @@ static int __devinit hv_probe(struct of_device *op, const struct of_device_id *m port->membase = (unsigned char __iomem *) __pa(port); - port->irq = op->irqs[0]; + port->irq = op->archdata.irqs[0]; port->dev = &op->dev; @@ -644,12 +644,12 @@ static int __init sunhv_init(void) if (tlb_type != hypervisor) return -ENODEV; - return of_register_driver(&hv_driver, &of_bus_type); + return of_register_platform_driver(&hv_driver); } static void __exit sunhv_exit(void) { - of_unregister_driver(&hv_driver); + of_unregister_platform_driver(&hv_driver); } module_init(sunhv_init); diff --git a/drivers/serial/sunsab.c b/drivers/serial/sunsab.c index 5e81bc6b48b..9845fb1cfb1 100644 --- a/drivers/serial/sunsab.c +++ b/drivers/serial/sunsab.c @@ -969,7 +969,7 @@ static int __devinit sunsab_init_one(struct uart_sunsab_port *up, return -ENOMEM; up->regs = (union sab82532_async_regs __iomem *) up->port.membase; - up->port.irq = op->irqs[0]; + up->port.irq = op->archdata.irqs[0]; up->port.fifosize = SAB82532_XMIT_FIFO_SIZE; up->port.iotype = UPIO_MEM; @@ -1130,12 +1130,12 @@ static int __init sunsab_init(void) } } - return of_register_driver(&sab_driver, &of_bus_type); + return of_register_platform_driver(&sab_driver); } static void __exit sunsab_exit(void) { - of_unregister_driver(&sab_driver); + of_unregister_platform_driver(&sab_driver); if (sunsab_reg.nr) { sunserial_unregister_minors(&sunsab_reg, sunsab_reg.nr); } diff --git a/drivers/serial/sunsu.c b/drivers/serial/sunsu.c index ffbf4553f66..3cdf74822db 100644 --- a/drivers/serial/sunsu.c +++ b/drivers/serial/sunsu.c @@ -1443,7 +1443,7 @@ static int __devinit su_probe(struct of_device *op, const struct of_device_id *m return -ENOMEM; } - up->port.irq = op->irqs[0]; + up->port.irq = op->archdata.irqs[0]; up->port.dev = &op->dev; @@ -1586,7 +1586,7 @@ static int __init sunsu_init(void) return err; } - err = of_register_driver(&su_driver, &of_bus_type); + err = of_register_platform_driver(&su_driver); if (err && num_uart) sunserial_unregister_minors(&sunsu_reg, num_uart); diff --git a/drivers/serial/sunzilog.c b/drivers/serial/sunzilog.c index f9a24f4ebb3..d1e6bcb5954 100644 --- a/drivers/serial/sunzilog.c +++ b/drivers/serial/sunzilog.c @@ -1426,7 +1426,7 @@ static int __devinit zs_probe(struct of_device *op, const struct of_device_id *m rp = sunzilog_chip_regs[inst]; if (zilog_irq == -1) - zilog_irq = op->irqs[0]; + zilog_irq = op->archdata.irqs[0]; up = &sunzilog_port_table[inst * 2]; @@ -1434,7 +1434,7 @@ static int __devinit zs_probe(struct of_device *op, const struct of_device_id *m up[0].port.mapbase = op->resource[0].start + 0x00; up[0].port.membase = (void __iomem *) &rp->channelA; up[0].port.iotype = UPIO_MEM; - up[0].port.irq = op->irqs[0]; + up[0].port.irq = op->archdata.irqs[0]; up[0].port.uartclk = ZS_CLOCK; up[0].port.fifosize = 1; up[0].port.ops = &sunzilog_pops; @@ -1451,7 +1451,7 @@ static int __devinit zs_probe(struct of_device *op, const struct of_device_id *m up[1].port.mapbase = op->resource[0].start + 0x04; up[1].port.membase = (void __iomem *) &rp->channelB; up[1].port.iotype = UPIO_MEM; - up[1].port.irq = op->irqs[0]; + up[1].port.irq = op->archdata.irqs[0]; up[1].port.uartclk = ZS_CLOCK; up[1].port.fifosize = 1; up[1].port.ops = &sunzilog_pops; @@ -1492,12 +1492,12 @@ static int __devinit zs_probe(struct of_device *op, const struct of_device_id *m "is a %s\n", dev_name(&op->dev), (unsigned long long) up[0].port.mapbase, - op->irqs[0], sunzilog_type(&up[0].port)); + op->archdata.irqs[0], sunzilog_type(&up[0].port)); printk(KERN_INFO "%s: Mouse at MMIO 0x%llx (irq = %d) " "is a %s\n", dev_name(&op->dev), (unsigned long long) up[1].port.mapbase, - op->irqs[0], sunzilog_type(&up[1].port)); + op->archdata.irqs[0], sunzilog_type(&up[1].port)); kbm_inst++; } @@ -1576,7 +1576,7 @@ static int __init sunzilog_init(void) goto out_free_tables; } - err = of_register_driver(&zs_driver, &of_bus_type); + err = of_register_platform_driver(&zs_driver); if (err) goto out_unregister_uart; @@ -1604,7 +1604,7 @@ out: return err; out_unregister_driver: - of_unregister_driver(&zs_driver); + of_unregister_platform_driver(&zs_driver); out_unregister_uart: if (num_sunzilog) { @@ -1619,7 +1619,7 @@ out_free_tables: static void __exit sunzilog_exit(void) { - of_unregister_driver(&zs_driver); + of_unregister_platform_driver(&zs_driver); if (zilog_irq != -1) { struct uart_sunzilog_port *up = sunzilog_irq_chain; diff --git a/drivers/serial/uartlite.c b/drivers/serial/uartlite.c index 8acccd56437..caf085d3a76 100644 --- a/drivers/serial/uartlite.c +++ b/drivers/serial/uartlite.c @@ -21,6 +21,7 @@ #include <asm/io.h> #if defined(CONFIG_OF) && (defined(CONFIG_PPC32) || defined(CONFIG_MICROBLAZE)) #include <linux/of.h> +#include <linux/of_address.h> #include <linux/of_device.h> #include <linux/of_platform.h> diff --git a/drivers/spi/mpc512x_psc_spi.c b/drivers/spi/mpc512x_psc_spi.c index 2534b1ec3ed..10baac3f8ea 100644 --- a/drivers/spi/mpc512x_psc_spi.c +++ b/drivers/spi/mpc512x_psc_spi.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/errno.h> #include <linux/interrupt.h> +#include <linux/of_address.h> #include <linux/of_platform.h> #include <linux/workqueue.h> #include <linux/completion.h> @@ -440,6 +441,7 @@ static int __init mpc512x_psc_spi_do_probe(struct device *dev, u32 regaddr, master->setup = mpc512x_psc_spi_setup; master->transfer = mpc512x_psc_spi_transfer; master->cleanup = mpc512x_psc_spi_cleanup; + master->dev.of_node = dev->of_node; tempp = ioremap(regaddr, size); if (!tempp) { diff --git a/drivers/spi/mpc52xx_psc_spi.c b/drivers/spi/mpc52xx_psc_spi.c index 7104cb739da..66d170147dc 100644 --- a/drivers/spi/mpc52xx_psc_spi.c +++ b/drivers/spi/mpc52xx_psc_spi.c @@ -16,8 +16,8 @@ #include <linux/types.h> #include <linux/errno.h> #include <linux/interrupt.h> +#include <linux/of_address.h> #include <linux/of_platform.h> -#include <linux/of_spi.h> #include <linux/workqueue.h> #include <linux/completion.h> #include <linux/io.h> @@ -398,6 +398,7 @@ static int __init mpc52xx_psc_spi_do_probe(struct device *dev, u32 regaddr, master->setup = mpc52xx_psc_spi_setup; master->transfer = mpc52xx_psc_spi_transfer; master->cleanup = mpc52xx_psc_spi_cleanup; + master->dev.of_node = dev->of_node; mps->psc = ioremap(regaddr, size); if (!mps->psc) { @@ -470,7 +471,6 @@ static int __init mpc52xx_psc_spi_of_probe(struct of_device *op, const u32 *regaddr_p; u64 regaddr64, size64; s16 id = -1; - int rc; regaddr_p = of_get_address(op->dev.of_node, 0, &size64, NULL); if (!regaddr_p) { @@ -491,13 +491,8 @@ static int __init mpc52xx_psc_spi_of_probe(struct of_device *op, id = *psc_nump + 1; } - rc = mpc52xx_psc_spi_do_probe(&op->dev, (u32)regaddr64, (u32)size64, + return mpc52xx_psc_spi_do_probe(&op->dev, (u32)regaddr64, (u32)size64, irq_of_parse_and_map(op->dev.of_node, 0), id); - if (rc == 0) - of_register_spi_devices(dev_get_drvdata(&op->dev), - op->dev.of_node); - - return rc; } static int __exit mpc52xx_psc_spi_of_remove(struct of_device *op) diff --git a/drivers/spi/mpc52xx_spi.c b/drivers/spi/mpc52xx_spi.c index b1a76bff775..56136ff00e0 100644 --- a/drivers/spi/mpc52xx_spi.c +++ b/drivers/spi/mpc52xx_spi.c @@ -18,7 +18,6 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/spi/spi.h> -#include <linux/of_spi.h> #include <linux/io.h> #include <linux/of_gpio.h> #include <linux/slab.h> @@ -439,6 +438,7 @@ static int __devinit mpc52xx_spi_probe(struct of_device *op, master->setup = mpc52xx_spi_setup; master->transfer = mpc52xx_spi_transfer; master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST; + master->dev.of_node = op->dev.of_node; dev_set_drvdata(&op->dev, master); @@ -512,7 +512,6 @@ static int __devinit mpc52xx_spi_probe(struct of_device *op, if (rc) goto err_register; - of_register_spi_devices(master, op->dev.of_node); dev_info(&ms->master->dev, "registered MPC5200 SPI bus\n"); return rc; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index b3a1f9259b6..1bb1b88780c 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -26,6 +26,7 @@ #include <linux/slab.h> #include <linux/mod_devicetable.h> #include <linux/spi/spi.h> +#include <linux/of_spi.h> /* SPI bustype and spi_master class are registered after board init code @@ -540,6 +541,9 @@ int spi_register_master(struct spi_master *master) /* populate children from any spi device tables */ scan_boardinfo(master); status = 0; + + /* Register devices from the device tree */ + of_register_spi_devices(master); done: return status; } diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_mpc8xxx.c index 97ab0a81338..aad9ae1b9c6 100644 --- a/drivers/spi/spi_mpc8xxx.c +++ b/drivers/spi/spi_mpc8xxx.c @@ -38,7 +38,6 @@ #include <linux/of_platform.h> #include <linux/gpio.h> #include <linux/of_gpio.h> -#include <linux/of_spi.h> #include <linux/slab.h> #include <sysdev/fsl_soc.h> @@ -1009,6 +1008,7 @@ mpc8xxx_spi_probe(struct device *dev, struct resource *mem, unsigned int irq) master->setup = mpc8xxx_spi_setup; master->transfer = mpc8xxx_spi_transfer; master->cleanup = mpc8xxx_spi_cleanup; + master->dev.of_node = dev->of_node; mpc8xxx_spi = spi_master_get_devdata(master); mpc8xxx_spi->dev = dev; @@ -1299,8 +1299,6 @@ static int __devinit of_mpc8xxx_spi_probe(struct of_device *ofdev, goto err; } - of_register_spi_devices(master, np); - return 0; err: diff --git a/drivers/spi/spi_ppc4xx.c b/drivers/spi/spi_ppc4xx.c index d53466a249d..0f5fa7e2a55 100644 --- a/drivers/spi/spi_ppc4xx.c +++ b/drivers/spi/spi_ppc4xx.c @@ -407,6 +407,7 @@ static int __init spi_ppc4xx_of_probe(struct of_device *op, master = spi_alloc_master(dev, sizeof *hw); if (master == NULL) return -ENOMEM; + master->dev.of_node = np; dev_set_drvdata(dev, master); hw = spi_master_get_devdata(master); hw->master = spi_master_get(master); @@ -545,7 +546,6 @@ static int __init spi_ppc4xx_of_probe(struct of_device *op, } dev_info(dev, "driver initialized\n"); - of_register_spi_devices(master, np); return 0; diff --git a/drivers/spi/xilinx_spi.c b/drivers/spi/xilinx_spi.c index 1b47363cb73..80f2db5bcfd 100644 --- a/drivers/spi/xilinx_spi.c +++ b/drivers/spi/xilinx_spi.c @@ -390,6 +390,9 @@ struct spi_master *xilinx_spi_init(struct device *dev, struct resource *mem, master->bus_num = bus_num; master->num_chipselect = pdata->num_chipselect; +#ifdef CONFIG_OF + master->dev.of_node = dev->of_node; +#endif xspi->mem = *mem; xspi->irq = irq; diff --git a/drivers/spi/xilinx_spi_of.c b/drivers/spi/xilinx_spi_of.c index 4654805b08d..f53d3f6b9f6 100644 --- a/drivers/spi/xilinx_spi_of.c +++ b/drivers/spi/xilinx_spi_of.c @@ -29,6 +29,7 @@ #include <linux/io.h> #include <linux/slab.h> +#include <linux/of_address.h> #include <linux/of_platform.h> #include <linux/of_device.h> #include <linux/of_spi.h> @@ -80,9 +81,6 @@ static int __devinit xilinx_spi_of_probe(struct of_device *ofdev, dev_set_drvdata(&ofdev->dev, master); - /* Add any subnodes on the SPI bus */ - of_register_spi_devices(master, ofdev->dev.of_node); - return 0; } diff --git a/drivers/usb/gadget/fsl_qe_udc.c b/drivers/usb/gadget/fsl_qe_udc.c index 82506ca297d..9648b75f028 100644 --- a/drivers/usb/gadget/fsl_qe_udc.c +++ b/drivers/usb/gadget/fsl_qe_udc.c @@ -32,6 +32,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/moduleparam.h> +#include <linux/of_address.h> #include <linux/of_platform.h> #include <linux/dma-mapping.h> #include <linux/usb/ch9.h> diff --git a/drivers/video/bw2.c b/drivers/video/bw2.c index 09f1b9b462f..c7796637baf 100644 --- a/drivers/video/bw2.c +++ b/drivers/video/bw2.c @@ -390,12 +390,12 @@ static int __init bw2_init(void) if (fb_get_options("bw2fb", NULL)) return -ENODEV; - return of_register_driver(&bw2_driver, &of_bus_type); + return of_register_platform_driver(&bw2_driver); } static void __exit bw2_exit(void) { - of_unregister_driver(&bw2_driver); + of_unregister_platform_driver(&bw2_driver); } module_init(bw2_init); diff --git a/drivers/video/cg14.c b/drivers/video/cg14.c index e5dc2241194..d09fde8beb6 100644 --- a/drivers/video/cg14.c +++ b/drivers/video/cg14.c @@ -610,12 +610,12 @@ static int __init cg14_init(void) if (fb_get_options("cg14fb", NULL)) return -ENODEV; - return of_register_driver(&cg14_driver, &of_bus_type); + return of_register_platform_driver(&cg14_driver); } static void __exit cg14_exit(void) { - of_unregister_driver(&cg14_driver); + of_unregister_platform_driver(&cg14_driver); } module_init(cg14_init); diff --git a/drivers/video/cg3.c b/drivers/video/cg3.c index 558d73a948a..64aa29809fb 100644 --- a/drivers/video/cg3.c +++ b/drivers/video/cg3.c @@ -477,12 +477,12 @@ static int __init cg3_init(void) if (fb_get_options("cg3fb", NULL)) return -ENODEV; - return of_register_driver(&cg3_driver, &of_bus_type); + return of_register_platform_driver(&cg3_driver); } static void __exit cg3_exit(void) { - of_unregister_driver(&cg3_driver); + of_unregister_platform_driver(&cg3_driver); } module_init(cg3_init); diff --git a/drivers/video/cg6.c b/drivers/video/cg6.c index 480d761a27a..2389a719dcc 100644 --- a/drivers/video/cg6.c +++ b/drivers/video/cg6.c @@ -870,12 +870,12 @@ static int __init cg6_init(void) if (fb_get_options("cg6fb", NULL)) return -ENODEV; - return of_register_driver(&cg6_driver, &of_bus_type); + return of_register_platform_driver(&cg6_driver); } static void __exit cg6_exit(void) { - of_unregister_driver(&cg6_driver); + of_unregister_platform_driver(&cg6_driver); } module_init(cg6_init); diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index b0a3fa00706..3b3f5749af9 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -2342,6 +2342,30 @@ static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch) return 0; } +static int fbcon_debug_enter(struct vc_data *vc) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + + ops->save_graphics = ops->graphics; + ops->graphics = 0; + if (info->fbops->fb_debug_enter) + info->fbops->fb_debug_enter(info); + fbcon_set_palette(vc, color_table); + return 0; +} + +static int fbcon_debug_leave(struct vc_data *vc) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + + ops->graphics = ops->save_graphics; + if (info->fbops->fb_debug_leave) + info->fbops->fb_debug_leave(info); + return 0; +} + static int fbcon_get_font(struct vc_data *vc, struct console_font *font) { u8 *fontdata = vc->vc_font.data; @@ -3276,6 +3300,8 @@ static const struct consw fb_con = { .con_screen_pos = fbcon_screen_pos, .con_getxy = fbcon_getxy, .con_resize = fbcon_resize, + .con_debug_enter = fbcon_debug_enter, + .con_debug_leave = fbcon_debug_leave, }; static struct notifier_block fbcon_event_notifier = { diff --git a/drivers/video/console/fbcon.h b/drivers/video/console/fbcon.h index 89a346880ec..6bd2e0c7f20 100644 --- a/drivers/video/console/fbcon.h +++ b/drivers/video/console/fbcon.h @@ -74,6 +74,7 @@ struct fbcon_ops { int cursor_reset; int blank_state; int graphics; + int save_graphics; /* for debug enter/leave */ int flags; int rotate; int cur_rotate; diff --git a/drivers/video/controlfb.c b/drivers/video/controlfb.c index 49fcbe8f18a..c225dcce89e 100644 --- a/drivers/video/controlfb.c +++ b/drivers/video/controlfb.c @@ -40,6 +40,8 @@ #include <linux/vmalloc.h> #include <linux/delay.h> #include <linux/interrupt.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/fb.h> #include <linux/init.h> #include <linux/pci.h> diff --git a/drivers/video/ffb.c b/drivers/video/ffb.c index 95c0227f47f..f6ecfab296d 100644 --- a/drivers/video/ffb.c +++ b/drivers/video/ffb.c @@ -1067,12 +1067,12 @@ static int __init ffb_init(void) if (fb_get_options("ffb", NULL)) return -ENODEV; - return of_register_driver(&ffb_driver, &of_bus_type); + return of_register_platform_driver(&ffb_driver); } static void __exit ffb_exit(void) { - of_unregister_driver(&ffb_driver); + of_unregister_platform_driver(&ffb_driver); } module_init(ffb_init); diff --git a/drivers/video/leo.c b/drivers/video/leo.c index 9e8bf7d5e24..ad677637ffb 100644 --- a/drivers/video/leo.c +++ b/drivers/video/leo.c @@ -677,12 +677,12 @@ static int __init leo_init(void) if (fb_get_options("leofb", NULL)) return -ENODEV; - return of_register_driver(&leo_driver, &of_bus_type); + return of_register_platform_driver(&leo_driver); } static void __exit leo_exit(void) { - of_unregister_driver(&leo_driver); + of_unregister_platform_driver(&leo_driver); } module_init(leo_init); diff --git a/drivers/video/offb.c b/drivers/video/offb.c index 46dda7d8aae..cb163a5397b 100644 --- a/drivers/video/offb.c +++ b/drivers/video/offb.c @@ -19,13 +19,14 @@ #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/delay.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/interrupt.h> #include <linux/fb.h> #include <linux/init.h> #include <linux/ioport.h> #include <linux/pci.h> #include <asm/io.h> -#include <asm/prom.h> #ifdef CONFIG_PPC64 #include <asm/pci-bridge.h> diff --git a/drivers/video/p9100.c b/drivers/video/p9100.c index 6552751e81a..688b055abab 100644 --- a/drivers/video/p9100.c +++ b/drivers/video/p9100.c @@ -367,12 +367,12 @@ static int __init p9100_init(void) if (fb_get_options("p9100fb", NULL)) return -ENODEV; - return of_register_driver(&p9100_driver, &of_bus_type); + return of_register_platform_driver(&p9100_driver); } static void __exit p9100_exit(void) { - of_unregister_driver(&p9100_driver); + of_unregister_platform_driver(&p9100_driver); } module_init(p9100_init); diff --git a/drivers/video/sunxvr1000.c b/drivers/video/sunxvr1000.c index 489b44e8db8..7288934c0d4 100644 --- a/drivers/video/sunxvr1000.c +++ b/drivers/video/sunxvr1000.c @@ -213,12 +213,12 @@ static int __init gfb_init(void) if (fb_get_options("gfb", NULL)) return -ENODEV; - return of_register_driver(&gfb_driver, &of_bus_type); + return of_register_platform_driver(&gfb_driver); } static void __exit gfb_exit(void) { - of_unregister_driver(&gfb_driver); + of_unregister_platform_driver(&gfb_driver); } module_init(gfb_init); diff --git a/drivers/video/tcx.c b/drivers/video/tcx.c index cc039b33d2d..f375e0db677 100644 --- a/drivers/video/tcx.c +++ b/drivers/video/tcx.c @@ -526,12 +526,12 @@ static int __init tcx_init(void) if (fb_get_options("tcxfb", NULL)) return -ENODEV; - return of_register_driver(&tcx_driver, &of_bus_type); + return of_register_platform_driver(&tcx_driver); } static void __exit tcx_exit(void) { - of_unregister_driver(&tcx_driver); + of_unregister_platform_driver(&tcx_driver); } module_init(tcx_init); diff --git a/drivers/video/xen-fbfront.c b/drivers/video/xen-fbfront.c index fa97d3e7c21..7c7f42a1279 100644 --- a/drivers/video/xen-fbfront.c +++ b/drivers/video/xen-fbfront.c @@ -684,7 +684,7 @@ static struct xenbus_driver xenfb_driver = { static int __init xenfb_init(void) { - if (!xen_domain()) + if (!xen_pv_domain()) return -ENODEV; /* Nothing to do if running in dom0. */ diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index d62b9ce8f77..30a2512fd52 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -545,7 +545,7 @@ static int __devinit cpwd_probe(struct of_device *op, goto out; } - p->irq = op->irqs[0]; + p->irq = op->archdata.irqs[0]; spin_lock_init(&p->lock); @@ -688,12 +688,12 @@ static struct of_platform_driver cpwd_driver = { static int __init cpwd_init(void) { - return of_register_driver(&cpwd_driver, &of_bus_type); + return of_register_platform_driver(&cpwd_driver); } static void __exit cpwd_exit(void) { - of_unregister_driver(&cpwd_driver); + of_unregister_platform_driver(&cpwd_driver); } module_init(cpwd_init); diff --git a/drivers/watchdog/riowd.c b/drivers/watchdog/riowd.c index 5dceeddc885..4082b4ace1f 100644 --- a/drivers/watchdog/riowd.c +++ b/drivers/watchdog/riowd.c @@ -250,12 +250,12 @@ static struct of_platform_driver riowd_driver = { static int __init riowd_init(void) { - return of_register_driver(&riowd_driver, &of_bus_type); + return of_register_platform_driver(&riowd_driver); } static void __exit riowd_exit(void) { - of_unregister_driver(&riowd_driver); + of_unregister_platform_driver(&riowd_driver); } module_init(riowd_init); diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index fad3df2c127..0a882693663 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -62,4 +62,13 @@ config XEN_SYS_HYPERVISOR virtual environment, /sys/hypervisor will still be present, but will have no xen contents. +config XEN_PLATFORM_PCI + tristate "xen platform pci device driver" + depends on XEN_PVHVM + default m + help + Driver for the Xen PCI Platform device: it is responsible for + initializing xenbus and grant_table when running in a Xen HVM + domain. As a consequence this driver is required to run any Xen PV + frontend on Xen HVM. endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 7c284342f30..e392fb776af 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -9,4 +9,5 @@ obj-$(CONFIG_XEN_XENCOMM) += xencomm.o obj-$(CONFIG_XEN_BALLOON) += balloon.o obj-$(CONFIG_XEN_DEV_EVTCHN) += evtchn.o obj-$(CONFIG_XENFS) += xenfs/ -obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o
\ No newline at end of file +obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o +obj-$(CONFIG_XEN_PLATFORM_PCI) += platform-pci.o diff --git a/drivers/xen/events.c b/drivers/xen/events.c index db8f506817f..5e1f34892dc 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -29,6 +29,7 @@ #include <linux/bootmem.h> #include <linux/slab.h> +#include <asm/desc.h> #include <asm/ptrace.h> #include <asm/irq.h> #include <asm/idle.h> @@ -36,10 +37,14 @@ #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> +#include <xen/xen.h> +#include <xen/hvm.h> #include <xen/xen-ops.h> #include <xen/events.h> #include <xen/interface/xen.h> #include <xen/interface/event_channel.h> +#include <xen/interface/hvm/hvm_op.h> +#include <xen/interface/hvm/params.h> /* * This lock protects updates to the following mapping and reference-count @@ -335,9 +340,18 @@ static int find_unbound_irq(void) int irq; struct irq_desc *desc; - for (irq = 0; irq < nr_irqs; irq++) + for (irq = 0; irq < nr_irqs; irq++) { + desc = irq_to_desc(irq); + /* only 0->15 have init'd desc; handle irq > 16 */ + if (desc == NULL) + break; + if (desc->chip == &no_irq_chip) + break; + if (desc->chip != &xen_dynamic_chip) + continue; if (irq_info[irq].type == IRQT_UNBOUND) break; + } if (irq == nr_irqs) panic("No available IRQ to bind to: increase nr_irqs!\n"); @@ -346,7 +360,7 @@ static int find_unbound_irq(void) if (WARN_ON(desc == NULL)) return -1; - dynamic_irq_init(irq); + dynamic_irq_init_keep_chip_data(irq); return irq; } @@ -617,17 +631,13 @@ static DEFINE_PER_CPU(unsigned, xed_nesting_count); * a bitset of words which contain pending event bits. The second * level is a bitset of pending events themselves. */ -void xen_evtchn_do_upcall(struct pt_regs *regs) +static void __xen_evtchn_do_upcall(void) { int cpu = get_cpu(); - struct pt_regs *old_regs = set_irq_regs(regs); struct shared_info *s = HYPERVISOR_shared_info; struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu); unsigned count; - exit_idle(); - irq_enter(); - do { unsigned long pending_words; @@ -664,14 +674,31 @@ void xen_evtchn_do_upcall(struct pt_regs *regs) count = __get_cpu_var(xed_nesting_count); __get_cpu_var(xed_nesting_count) = 0; - } while(count != 1); + } while (count != 1 || vcpu_info->evtchn_upcall_pending); out: + + put_cpu(); +} + +void xen_evtchn_do_upcall(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + exit_idle(); + irq_enter(); + + __xen_evtchn_do_upcall(); + irq_exit(); set_irq_regs(old_regs); +} - put_cpu(); +void xen_hvm_evtchn_do_upcall(void) +{ + __xen_evtchn_do_upcall(); } +EXPORT_SYMBOL_GPL(xen_hvm_evtchn_do_upcall); /* Rebind a new event channel to an existing irq. */ void rebind_evtchn_irq(int evtchn, int irq) @@ -708,7 +735,10 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu) struct evtchn_bind_vcpu bind_vcpu; int evtchn = evtchn_from_irq(irq); - if (!VALID_EVTCHN(evtchn)) + /* events delivered via platform PCI interrupts are always + * routed to vcpu 0 */ + if (!VALID_EVTCHN(evtchn) || + (xen_hvm_domain() && !xen_have_vector_callback)) return -1; /* Send future instances of this interrupt to other vcpu. */ @@ -933,6 +963,44 @@ static struct irq_chip xen_dynamic_chip __read_mostly = { .retrigger = retrigger_dynirq, }; +int xen_set_callback_via(uint64_t via) +{ + struct xen_hvm_param a; + a.domid = DOMID_SELF; + a.index = HVM_PARAM_CALLBACK_IRQ; + a.value = via; + return HYPERVISOR_hvm_op(HVMOP_set_param, &a); +} +EXPORT_SYMBOL_GPL(xen_set_callback_via); + +#ifdef CONFIG_XEN_PVHVM +/* Vector callbacks are better than PCI interrupts to receive event + * channel notifications because we can receive vector callbacks on any + * vcpu and we don't need PCI support or APIC interactions. */ +void xen_callback_vector(void) +{ + int rc; + uint64_t callback_via; + if (xen_have_vector_callback) { + callback_via = HVM_CALLBACK_VECTOR(XEN_HVM_EVTCHN_CALLBACK); + rc = xen_set_callback_via(callback_via); + if (rc) { + printk(KERN_ERR "Request for Xen HVM callback vector" + " failed.\n"); + xen_have_vector_callback = 0; + return; + } + printk(KERN_INFO "Xen HVM callback vector for event delivery is " + "enabled\n"); + /* in the restore case the vector has already been allocated */ + if (!test_bit(XEN_HVM_EVTCHN_CALLBACK, used_vectors)) + alloc_intr_gate(XEN_HVM_EVTCHN_CALLBACK, xen_hvm_callback_vector); + } +} +#else +void xen_callback_vector(void) {} +#endif + void __init xen_init_IRQ(void) { int i; @@ -947,5 +1015,10 @@ void __init xen_init_IRQ(void) for (i = 0; i < NR_EVENT_CHANNELS; i++) mask_evtchn(i); - irq_ctx_init(smp_processor_id()); + if (xen_hvm_domain()) { + xen_callback_vector(); + native_init_IRQ(); + } else { + irq_ctx_init(smp_processor_id()); + } } diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index f66db3b91d6..6c453181649 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -37,11 +37,13 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> +#include <linux/io.h> #include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/page.h> #include <xen/grant_table.h> +#include <xen/interface/memory.h> #include <asm/xen/hypercall.h> #include <asm/pgtable.h> @@ -59,6 +61,8 @@ static unsigned int boot_max_nr_grant_frames; static int gnttab_free_count; static grant_ref_t gnttab_free_head; static DEFINE_SPINLOCK(gnttab_list_lock); +unsigned long xen_hvm_resume_frames; +EXPORT_SYMBOL_GPL(xen_hvm_resume_frames); static struct grant_entry *shared; @@ -433,7 +437,7 @@ static unsigned int __max_nr_grant_frames(void) return query.max_nr_frames; } -static inline unsigned int max_nr_grant_frames(void) +unsigned int gnttab_max_grant_frames(void) { unsigned int xen_max = __max_nr_grant_frames(); @@ -441,6 +445,7 @@ static inline unsigned int max_nr_grant_frames(void) return boot_max_nr_grant_frames; return xen_max; } +EXPORT_SYMBOL_GPL(gnttab_max_grant_frames); static int gnttab_map(unsigned int start_idx, unsigned int end_idx) { @@ -449,6 +454,30 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx) unsigned int nr_gframes = end_idx + 1; int rc; + if (xen_hvm_domain()) { + struct xen_add_to_physmap xatp; + unsigned int i = end_idx; + rc = 0; + /* + * Loop backwards, so that the first hypercall has the largest + * index, ensuring that the table will grow only once. + */ + do { + xatp.domid = DOMID_SELF; + xatp.idx = i; + xatp.space = XENMAPSPACE_grant_table; + xatp.gpfn = (xen_hvm_resume_frames >> PAGE_SHIFT) + i; + rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp); + if (rc != 0) { + printk(KERN_WARNING + "grant table add_to_physmap failed, err=%d\n", rc); + break; + } + } while (i-- > start_idx); + + return rc; + } + frames = kmalloc(nr_gframes * sizeof(unsigned long), GFP_ATOMIC); if (!frames) return -ENOMEM; @@ -465,7 +494,7 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx) BUG_ON(rc || setup.status); - rc = arch_gnttab_map_shared(frames, nr_gframes, max_nr_grant_frames(), + rc = arch_gnttab_map_shared(frames, nr_gframes, gnttab_max_grant_frames(), &shared); BUG_ON(rc); @@ -476,9 +505,27 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx) int gnttab_resume(void) { - if (max_nr_grant_frames() < nr_grant_frames) + unsigned int max_nr_gframes; + + max_nr_gframes = gnttab_max_grant_frames(); + if (max_nr_gframes < nr_grant_frames) return -ENOSYS; - return gnttab_map(0, nr_grant_frames - 1); + + if (xen_pv_domain()) + return gnttab_map(0, nr_grant_frames - 1); + + if (!shared) { + shared = ioremap(xen_hvm_resume_frames, PAGE_SIZE * max_nr_gframes); + if (shared == NULL) { + printk(KERN_WARNING + "Failed to ioremap gnttab share frames!"); + return -ENOMEM; + } + } + + gnttab_map(0, nr_grant_frames - 1); + + return 0; } int gnttab_suspend(void) @@ -495,7 +542,7 @@ static int gnttab_expand(unsigned int req_entries) cur = nr_grant_frames; extra = ((req_entries + (GREFS_PER_GRANT_FRAME-1)) / GREFS_PER_GRANT_FRAME); - if (cur + extra > max_nr_grant_frames()) + if (cur + extra > gnttab_max_grant_frames()) return -ENOSPC; rc = gnttab_map(cur, cur + extra - 1); @@ -505,15 +552,12 @@ static int gnttab_expand(unsigned int req_entries) return rc; } -static int __devinit gnttab_init(void) +int gnttab_init(void) { int i; unsigned int max_nr_glist_frames, nr_glist_frames; unsigned int nr_init_grefs; - if (!xen_domain()) - return -ENODEV; - nr_grant_frames = 1; boot_max_nr_grant_frames = __max_nr_grant_frames(); @@ -556,5 +600,18 @@ static int __devinit gnttab_init(void) kfree(gnttab_list); return -ENOMEM; } +EXPORT_SYMBOL_GPL(gnttab_init); + +static int __devinit __gnttab_init(void) +{ + /* Delay grant-table initialization in the PV on HVM case */ + if (xen_hvm_domain()) + return 0; + + if (!xen_pv_domain()) + return -ENODEV; + + return gnttab_init(); +} -core_initcall(gnttab_init); +core_initcall(__gnttab_init); diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 07e857b0de1..1799bd89031 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -9,6 +9,7 @@ #include <linux/stop_machine.h> #include <linux/freezer.h> +#include <xen/xen.h> #include <xen/xenbus.h> #include <xen/grant_table.h> #include <xen/events.h> @@ -17,6 +18,7 @@ #include <asm/xen/hypercall.h> #include <asm/xen/page.h> +#include <asm/xen/hypervisor.h> enum shutdown_state { SHUTDOWN_INVALID = -1, @@ -33,10 +35,30 @@ enum shutdown_state { static enum shutdown_state shutting_down = SHUTDOWN_INVALID; #ifdef CONFIG_PM_SLEEP -static int xen_suspend(void *data) +static int xen_hvm_suspend(void *data) { + struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; int *cancelled = data; + + BUG_ON(!irqs_disabled()); + + *cancelled = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); + + xen_hvm_post_suspend(*cancelled); + gnttab_resume(); + + if (!*cancelled) { + xen_irq_resume(); + xen_timer_resume(); + } + + return 0; +} + +static int xen_suspend(void *data) +{ int err; + int *cancelled = data; BUG_ON(!irqs_disabled()); @@ -106,7 +128,10 @@ static void do_suspend(void) goto out_resume; } - err = stop_machine(xen_suspend, &cancelled, cpumask_of(0)); + if (xen_hvm_domain()) + err = stop_machine(xen_hvm_suspend, &cancelled, cpumask_of(0)); + else + err = stop_machine(xen_suspend, &cancelled, cpumask_of(0)); dpm_resume_noirq(PMSG_RESUME); @@ -255,7 +280,19 @@ static int shutdown_event(struct notifier_block *notifier, return NOTIFY_DONE; } -static int __init setup_shutdown_event(void) +static int __init __setup_shutdown_event(void) +{ + /* Delay initialization in the PV on HVM case */ + if (xen_hvm_domain()) + return 0; + + if (!xen_pv_domain()) + return -ENODEV; + + return xen_setup_shutdown_event(); +} + +int xen_setup_shutdown_event(void) { static struct notifier_block xenstore_notifier = { .notifier_call = shutdown_event @@ -264,5 +301,6 @@ static int __init setup_shutdown_event(void) return 0; } +EXPORT_SYMBOL_GPL(xen_setup_shutdown_event); -subsys_initcall(setup_shutdown_event); +subsys_initcall(__setup_shutdown_event); diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c new file mode 100644 index 00000000000..c01b5ddce52 --- /dev/null +++ b/drivers/xen/platform-pci.c @@ -0,0 +1,207 @@ +/****************************************************************************** + * platform-pci.c + * + * Xen platform PCI device driver + * Copyright (c) 2005, Intel Corporation. + * Copyright (c) 2007, XenSource Inc. + * Copyright (c) 2010, Citrix + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + */ + + +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/pci.h> + +#include <xen/platform_pci.h> +#include <xen/grant_table.h> +#include <xen/xenbus.h> +#include <xen/events.h> +#include <xen/hvm.h> +#include <xen/xen-ops.h> + +#define DRV_NAME "xen-platform-pci" + +MODULE_AUTHOR("ssmith@xensource.com and stefano.stabellini@eu.citrix.com"); +MODULE_DESCRIPTION("Xen platform PCI device"); +MODULE_LICENSE("GPL"); + +static unsigned long platform_mmio; +static unsigned long platform_mmio_alloc; +static unsigned long platform_mmiolen; +static uint64_t callback_via; + +unsigned long alloc_xen_mmio(unsigned long len) +{ + unsigned long addr; + + addr = platform_mmio + platform_mmio_alloc; + platform_mmio_alloc += len; + BUG_ON(platform_mmio_alloc > platform_mmiolen); + + return addr; +} + +static uint64_t get_callback_via(struct pci_dev *pdev) +{ + u8 pin; + int irq; + + irq = pdev->irq; + if (irq < 16) + return irq; /* ISA IRQ */ + + pin = pdev->pin; + + /* We don't know the GSI. Specify the PCI INTx line instead. */ + return ((uint64_t)0x01 << 56) | /* PCI INTx identifier */ + ((uint64_t)pci_domain_nr(pdev->bus) << 32) | + ((uint64_t)pdev->bus->number << 16) | + ((uint64_t)(pdev->devfn & 0xff) << 8) | + ((uint64_t)(pin - 1) & 3); +} + +static irqreturn_t do_hvm_evtchn_intr(int irq, void *dev_id) +{ + xen_hvm_evtchn_do_upcall(); + return IRQ_HANDLED; +} + +static int xen_allocate_irq(struct pci_dev *pdev) +{ + return request_irq(pdev->irq, do_hvm_evtchn_intr, + IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TRIGGER_RISING, + "xen-platform-pci", pdev); +} + +static int platform_pci_resume(struct pci_dev *pdev) +{ + int err; + if (xen_have_vector_callback) + return 0; + err = xen_set_callback_via(callback_via); + if (err) { + dev_err(&pdev->dev, "platform_pci_resume failure!\n"); + return err; + } + return 0; +} + +static int __devinit platform_pci_init(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + int i, ret; + long ioaddr, iolen; + long mmio_addr, mmio_len; + unsigned int max_nr_gframes; + + i = pci_enable_device(pdev); + if (i) + return i; + + ioaddr = pci_resource_start(pdev, 0); + iolen = pci_resource_len(pdev, 0); + + mmio_addr = pci_resource_start(pdev, 1); + mmio_len = pci_resource_len(pdev, 1); + + if (mmio_addr == 0 || ioaddr == 0) { + dev_err(&pdev->dev, "no resources found\n"); + ret = -ENOENT; + goto pci_out; + } + + if (request_mem_region(mmio_addr, mmio_len, DRV_NAME) == NULL) { + dev_err(&pdev->dev, "MEM I/O resource 0x%lx @ 0x%lx busy\n", + mmio_addr, mmio_len); + ret = -EBUSY; + goto pci_out; + } + + if (request_region(ioaddr, iolen, DRV_NAME) == NULL) { + dev_err(&pdev->dev, "I/O resource 0x%lx @ 0x%lx busy\n", + iolen, ioaddr); + ret = -EBUSY; + goto mem_out; + } + + platform_mmio = mmio_addr; + platform_mmiolen = mmio_len; + + if (!xen_have_vector_callback) { + ret = xen_allocate_irq(pdev); + if (ret) { + dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret); + goto out; + } + callback_via = get_callback_via(pdev); + ret = xen_set_callback_via(callback_via); + if (ret) { + dev_warn(&pdev->dev, "Unable to set the evtchn callback " + "err=%d\n", ret); + goto out; + } + } + + max_nr_gframes = gnttab_max_grant_frames(); + xen_hvm_resume_frames = alloc_xen_mmio(PAGE_SIZE * max_nr_gframes); + ret = gnttab_init(); + if (ret) + goto out; + xenbus_probe(NULL); + ret = xen_setup_shutdown_event(); + if (ret) + goto out; + return 0; + +out: + release_region(ioaddr, iolen); +mem_out: + release_mem_region(mmio_addr, mmio_len); +pci_out: + pci_disable_device(pdev); + return ret; +} + +static struct pci_device_id platform_pci_tbl[] __devinitdata = { + {PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, + {0,} +}; + +MODULE_DEVICE_TABLE(pci, platform_pci_tbl); + +static struct pci_driver platform_driver = { + .name = DRV_NAME, + .probe = platform_pci_init, + .id_table = platform_pci_tbl, +#ifdef CONFIG_PM + .resume_early = platform_pci_resume, +#endif +}; + +static int __init platform_pci_module_init(void) +{ + /* no unplug has been done, IGNORE hasn't been specified: just + * return now */ + if (!xen_platform_pci_unplug) + return -ENODEV; + + return pci_register_driver(&platform_driver); +} + +module_init(platform_pci_module_init); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 3479332113e..29bac511887 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -56,6 +56,9 @@ #include <xen/events.h> #include <xen/page.h> +#include <xen/platform_pci.h> +#include <xen/hvm.h> + #include "xenbus_comms.h" #include "xenbus_probe.h" @@ -752,10 +755,7 @@ int register_xenstore_notifier(struct notifier_block *nb) { int ret = 0; - if (xenstored_ready > 0) - ret = nb->notifier_call(nb, 0, NULL); - else - blocking_notifier_chain_register(&xenstore_chain, nb); + blocking_notifier_chain_register(&xenstore_chain, nb); return ret; } @@ -779,8 +779,23 @@ void xenbus_probe(struct work_struct *unused) /* Notify others that xenstore is up */ blocking_notifier_call_chain(&xenstore_chain, 0, NULL); } +EXPORT_SYMBOL_GPL(xenbus_probe); + +static int __init xenbus_probe_initcall(void) +{ + if (!xen_domain()) + return -ENODEV; + + if (xen_initial_domain() || xen_hvm_domain()) + return 0; + + xenbus_probe(NULL); + return 0; +} + +device_initcall(xenbus_probe_initcall); -static int __init xenbus_probe_init(void) +static int __init xenbus_init(void) { int err = 0; @@ -805,11 +820,24 @@ static int __init xenbus_probe_init(void) if (xen_initial_domain()) { /* dom0 not yet supported */ } else { + if (xen_hvm_domain()) { + uint64_t v = 0; + err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); + if (err) + goto out_error; + xen_store_evtchn = (int)v; + err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); + if (err) + goto out_error; + xen_store_mfn = (unsigned long)v; + xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE); + } else { + xen_store_evtchn = xen_start_info->store_evtchn; + xen_store_mfn = xen_start_info->store_mfn; + xen_store_interface = mfn_to_virt(xen_store_mfn); + } xenstored_ready = 1; - xen_store_evtchn = xen_start_info->store_evtchn; - xen_store_mfn = xen_start_info->store_mfn; } - xen_store_interface = mfn_to_virt(xen_store_mfn); /* Initialize the interface to xenstore. */ err = xs_init(); @@ -819,9 +847,6 @@ static int __init xenbus_probe_init(void) goto out_unreg_back; } - if (!xen_initial_domain()) - xenbus_probe(NULL); - #ifdef CONFIG_XEN_COMPAT_XENFS /* * Create xenfs mountpoint in /proc for compatibility with @@ -842,7 +867,7 @@ static int __init xenbus_probe_init(void) return err; } -postcore_initcall(xenbus_probe_init); +postcore_initcall(xenbus_init); MODULE_LICENSE("GPL"); @@ -950,6 +975,9 @@ static void wait_for_devices(struct xenbus_driver *xendrv) #ifndef MODULE static int __init boot_wait_for_devices(void) { + if (xen_hvm_domain() && !xen_platform_pci_unplug) + return -ENODEV; + ready_to_wait_for_devices = 1; wait_for_devices(NULL); return 0; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 7b547f53f65..5534690075a 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -76,6 +76,14 @@ struct xs_handle { /* * Mutex ordering: transaction_mutex -> watch_mutex -> request_mutex. * response_mutex is never taken simultaneously with the other three. + * + * transaction_mutex must be held before incrementing + * transaction_count. The mutex is held when a suspend is in + * progress to prevent new transactions starting. + * + * When decrementing transaction_count to zero the wait queue + * should be woken up, the suspend code waits for count to + * reach zero. */ /* One request at a time. */ @@ -85,7 +93,9 @@ struct xs_handle { struct mutex response_mutex; /* Protect transactions against save/restore. */ - struct rw_semaphore transaction_mutex; + struct mutex transaction_mutex; + atomic_t transaction_count; + wait_queue_head_t transaction_wq; /* Protect watch (de)register against save/restore. */ struct rw_semaphore watch_mutex; @@ -157,6 +167,31 @@ static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len) return body; } +static void transaction_start(void) +{ + mutex_lock(&xs_state.transaction_mutex); + atomic_inc(&xs_state.transaction_count); + mutex_unlock(&xs_state.transaction_mutex); +} + +static void transaction_end(void) +{ + if (atomic_dec_and_test(&xs_state.transaction_count)) + wake_up(&xs_state.transaction_wq); +} + +static void transaction_suspend(void) +{ + mutex_lock(&xs_state.transaction_mutex); + wait_event(xs_state.transaction_wq, + atomic_read(&xs_state.transaction_count) == 0); +} + +static void transaction_resume(void) +{ + mutex_unlock(&xs_state.transaction_mutex); +} + void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg) { void *ret; @@ -164,7 +199,7 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg) int err; if (req_msg.type == XS_TRANSACTION_START) - down_read(&xs_state.transaction_mutex); + transaction_start(); mutex_lock(&xs_state.request_mutex); @@ -180,7 +215,7 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg) if ((msg->type == XS_TRANSACTION_END) || ((req_msg.type == XS_TRANSACTION_START) && (msg->type == XS_ERROR))) - up_read(&xs_state.transaction_mutex); + transaction_end(); return ret; } @@ -432,11 +467,11 @@ int xenbus_transaction_start(struct xenbus_transaction *t) { char *id_str; - down_read(&xs_state.transaction_mutex); + transaction_start(); id_str = xs_single(XBT_NIL, XS_TRANSACTION_START, "", NULL); if (IS_ERR(id_str)) { - up_read(&xs_state.transaction_mutex); + transaction_end(); return PTR_ERR(id_str); } @@ -461,7 +496,7 @@ int xenbus_transaction_end(struct xenbus_transaction t, int abort) err = xs_error(xs_single(t, XS_TRANSACTION_END, abortstr, NULL)); - up_read(&xs_state.transaction_mutex); + transaction_end(); return err; } @@ -662,7 +697,7 @@ EXPORT_SYMBOL_GPL(unregister_xenbus_watch); void xs_suspend(void) { - down_write(&xs_state.transaction_mutex); + transaction_suspend(); down_write(&xs_state.watch_mutex); mutex_lock(&xs_state.request_mutex); mutex_lock(&xs_state.response_mutex); @@ -677,7 +712,7 @@ void xs_resume(void) mutex_unlock(&xs_state.response_mutex); mutex_unlock(&xs_state.request_mutex); - up_write(&xs_state.transaction_mutex); + transaction_resume(); /* No need for watches_lock: the watch_mutex is sufficient. */ list_for_each_entry(watch, &watches, list) { @@ -693,7 +728,7 @@ void xs_suspend_cancel(void) mutex_unlock(&xs_state.response_mutex); mutex_unlock(&xs_state.request_mutex); up_write(&xs_state.watch_mutex); - up_write(&xs_state.transaction_mutex); + mutex_unlock(&xs_state.transaction_mutex); } static int xenwatch_thread(void *unused) @@ -843,8 +878,10 @@ int xs_init(void) mutex_init(&xs_state.request_mutex); mutex_init(&xs_state.response_mutex); - init_rwsem(&xs_state.transaction_mutex); + mutex_init(&xs_state.transaction_mutex); init_rwsem(&xs_state.watch_mutex); + atomic_set(&xs_state.transaction_count, 0); + init_waitqueue_head(&xs_state.transaction_wq); /* Initialize the shared memory rings to talk to xenstored */ err = xb_init_comms(); diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c index 8924d93136f..78bfab0700b 100644 --- a/drivers/xen/xenfs/super.c +++ b/drivers/xen/xenfs/super.c @@ -65,7 +65,7 @@ static struct file_system_type xenfs_type = { static int __init xenfs_init(void) { - if (xen_pv_domain()) + if (xen_domain()) return register_filesystem(&xenfs_type); printk(KERN_INFO "XENFS: not registering filesystem on non-xen platform\n"); @@ -74,7 +74,7 @@ static int __init xenfs_init(void) static void __exit xenfs_exit(void) { - if (xen_pv_domain()) + if (xen_domain()) unregister_filesystem(&xenfs_type); } diff --git a/drivers/xen/xenfs/xenbus.c b/drivers/xen/xenfs/xenbus.c index f28ece39736..3b39c3752e2 100644 --- a/drivers/xen/xenfs/xenbus.c +++ b/drivers/xen/xenfs/xenbus.c @@ -124,6 +124,9 @@ static ssize_t xenbus_file_read(struct file *filp, mutex_lock(&u->reply_mutex); while (list_empty(&u->read_buffers)) { mutex_unlock(&u->reply_mutex); + if (filp->f_flags & O_NONBLOCK) + return -EAGAIN; + ret = wait_event_interruptible(u->read_waitq, !list_empty(&u->read_buffers)); if (ret) @@ -1277,7 +1277,7 @@ out: /* sys_io_destroy: * Destroy the aio_context specified. May cancel any outstanding * AIOs and block on completion. Will fail with -ENOSYS if not - * implemented. May fail with -EFAULT if the context pointed to + * implemented. May fail with -EINVAL if the context pointed to * is invalid. */ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) @@ -1795,15 +1795,16 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, /* io_getevents: * Attempts to read at least min_nr events and up to nr events from - * the completion queue for the aio_context specified by ctx_id. May - * fail with -EINVAL if ctx_id is invalid, if min_nr is out of range, - * if nr is out of range, if when is out of range. May fail with - * -EFAULT if any of the memory specified to is invalid. May return - * 0 or < min_nr if no events are available and the timeout specified - * by when has elapsed, where when == NULL specifies an infinite - * timeout. Note that the timeout pointed to by when is relative and - * will be updated if not NULL and the operation blocks. Will fail - * with -ENOSYS if not implemented. + * the completion queue for the aio_context specified by ctx_id. If + * it succeeds, the number of read events is returned. May fail with + * -EINVAL if ctx_id is invalid, if min_nr is out of range, if nr is + * out of range, if timeout is out of range. May fail with -EFAULT + * if any of the memory specified is invalid. May return 0 or + * < min_nr if the timeout specified by timeout has elapsed + * before sufficient events are available, where timeout == NULL + * specifies an infinite timeout. Note that the timeout pointed to by + * timeout is relative and will be updated if not NULL and the + * operation blocks. Will fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, long, min_nr, diff --git a/fs/char_dev.c b/fs/char_dev.c index d6db933df2b..f80a4f25123 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -20,6 +20,7 @@ #include <linux/cdev.h> #include <linux/mutex.h> #include <linux/backing-dev.h> +#include <linux/tty.h> #include "internal.h" diff --git a/fs/exec.c b/fs/exec.c index e19de6a8033..97d91a03fb1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -653,6 +653,7 @@ int setup_arg_pages(struct linux_binprm *bprm, else stack_base = vma->vm_start - stack_expand; #endif + current->mm->start_stack = bprm->p; ret = expand_stack(vma, stack_base); if (ret) ret = -EFAULT; diff --git a/fs/file.c b/fs/file.c index 34bb7f71d99..cccaead962c 100644 --- a/fs/file.c +++ b/fs/file.c @@ -178,7 +178,6 @@ static struct fdtable * alloc_fdtable(unsigned int nr) fdt->open_fds = (fd_set *)data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = (fd_set *)data; - INIT_RCU_HEAD(&fdt->rcu); fdt->next = NULL; return fdt; @@ -312,7 +311,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) new_fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init; new_fdt->open_fds = (fd_set *)&newf->open_fds_init; new_fdt->fd = &newf->fd_array[0]; - INIT_RCU_HEAD(&new_fdt->rcu); new_fdt->next = NULL; spin_lock(&oldf->file_lock); @@ -430,7 +428,6 @@ struct files_struct init_files = { .fd = &init_files.fd_array[0], .close_on_exec = (fd_set *)&init_files.close_on_exec_init, .open_fds = (fd_set *)&init_files.open_fds_init, - .rcu = RCU_HEAD_INIT, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock), }; diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 5dcd4b0c553..72c52656dc2 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -459,7 +459,6 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, } /* everything is up and running, commence */ - INIT_RCU_HEAD(&p->rcu_head); rcu_assign_pointer(ptbl->part[partno], p); /* suppress uevent if the disk supresses it */ diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h index 4f3d75e1ad3..c7376bf80b0 100644 --- a/include/asm-generic/gpio.h +++ b/include/asm-generic/gpio.h @@ -31,6 +31,7 @@ static inline int gpio_is_valid(int number) struct device; struct seq_file; struct module; +struct device_node; /** * struct gpio_chip - abstract a GPIO controller @@ -106,6 +107,17 @@ struct gpio_chip { const char *const *names; unsigned can_sleep:1; unsigned exported:1; + +#if defined(CONFIG_OF_GPIO) + /* + * If CONFIG_OF is enabled, then all GPIO controllers described in the + * device tree automatically may have an OF translation + */ + struct device_node *of_node; + int of_gpio_n_cells; + int (*of_xlate)(struct gpio_chip *gc, struct device_node *np, + const void *gpio_spec, u32 *flags); +#endif }; extern const char *gpiochip_is_requested(struct gpio_chip *chip, @@ -115,6 +127,9 @@ extern int __must_check gpiochip_reserve(int start, int ngpio); /* add/remove chips */ extern int gpiochip_add(struct gpio_chip *chip); extern int __must_check gpiochip_remove(struct gpio_chip *chip); +extern struct gpio_chip *gpiochip_find(void *data, + int (*match)(struct gpio_chip *chip, + void *data)); /* Always use the library code for GPIO management calls, diff --git a/include/asm-generic/local64.h b/include/asm-generic/local64.h new file mode 100644 index 00000000000..02ac760c1a8 --- /dev/null +++ b/include/asm-generic/local64.h @@ -0,0 +1,96 @@ +#ifndef _ASM_GENERIC_LOCAL64_H +#define _ASM_GENERIC_LOCAL64_H + +#include <linux/percpu.h> +#include <asm/types.h> + +/* + * A signed long type for operations which are atomic for a single CPU. + * Usually used in combination with per-cpu variables. + * + * This is the default implementation, which uses atomic64_t. Which is + * rather pointless. The whole point behind local64_t is that some processors + * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs + * running on this CPU. local64_t allows exploitation of such capabilities. + */ + +/* Implement in terms of atomics. */ + +#if BITS_PER_LONG == 64 + +#include <asm/local.h> + +typedef struct { + local_t a; +} local64_t; + +#define LOCAL64_INIT(i) { LOCAL_INIT(i) } + +#define local64_read(l) local_read(&(l)->a) +#define local64_set(l,i) local_set((&(l)->a),(i)) +#define local64_inc(l) local_inc(&(l)->a) +#define local64_dec(l) local_dec(&(l)->a) +#define local64_add(i,l) local_add((i),(&(l)->a)) +#define local64_sub(i,l) local_sub((i),(&(l)->a)) + +#define local64_sub_and_test(i, l) local_sub_and_test((i), (&(l)->a)) +#define local64_dec_and_test(l) local_dec_and_test(&(l)->a) +#define local64_inc_and_test(l) local_inc_and_test(&(l)->a) +#define local64_add_negative(i, l) local_add_negative((i), (&(l)->a)) +#define local64_add_return(i, l) local_add_return((i), (&(l)->a)) +#define local64_sub_return(i, l) local_sub_return((i), (&(l)->a)) +#define local64_inc_return(l) local_inc_return(&(l)->a) + +#define local64_cmpxchg(l, o, n) local_cmpxchg((&(l)->a), (o), (n)) +#define local64_xchg(l, n) local_xchg((&(l)->a), (n)) +#define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u)) +#define local64_inc_not_zero(l) local_inc_not_zero(&(l)->a) + +/* Non-atomic variants, ie. preemption disabled and won't be touched + * in interrupt, etc. Some archs can optimize this case well. */ +#define __local64_inc(l) local64_set((l), local64_read(l) + 1) +#define __local64_dec(l) local64_set((l), local64_read(l) - 1) +#define __local64_add(i,l) local64_set((l), local64_read(l) + (i)) +#define __local64_sub(i,l) local64_set((l), local64_read(l) - (i)) + +#else /* BITS_PER_LONG != 64 */ + +#include <asm/atomic.h> + +/* Don't use typedef: don't want them to be mixed with atomic_t's. */ +typedef struct { + atomic64_t a; +} local64_t; + +#define LOCAL64_INIT(i) { ATOMIC_LONG_INIT(i) } + +#define local64_read(l) atomic64_read(&(l)->a) +#define local64_set(l,i) atomic64_set((&(l)->a),(i)) +#define local64_inc(l) atomic64_inc(&(l)->a) +#define local64_dec(l) atomic64_dec(&(l)->a) +#define local64_add(i,l) atomic64_add((i),(&(l)->a)) +#define local64_sub(i,l) atomic64_sub((i),(&(l)->a)) + +#define local64_sub_and_test(i, l) atomic64_sub_and_test((i), (&(l)->a)) +#define local64_dec_and_test(l) atomic64_dec_and_test(&(l)->a) +#define local64_inc_and_test(l) atomic64_inc_and_test(&(l)->a) +#define local64_add_negative(i, l) atomic64_add_negative((i), (&(l)->a)) +#define local64_add_return(i, l) atomic64_add_return((i), (&(l)->a)) +#define local64_sub_return(i, l) atomic64_sub_return((i), (&(l)->a)) +#define local64_inc_return(l) atomic64_inc_return(&(l)->a) + +#define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n)) +#define local64_xchg(l, n) atomic64_xchg((&(l)->a), (n)) +#define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u)) +#define local64_inc_not_zero(l) atomic64_inc_not_zero(&(l)->a) + +/* Non-atomic variants, ie. preemption disabled and won't be touched + * in interrupt, etc. Some archs can optimize this case well. */ +#define __local64_inc(l) local64_set((l), local64_read(l) + 1) +#define __local64_dec(l) local64_set((l), local64_read(l) - 1) +#define __local64_add(i,l) local64_set((l), local64_read(l) + (i)) +#define __local64_sub(i,l) local64_set((l), local64_read(l) - (i)) + +#endif /* BITS_PER_LONG != 64 */ + +#endif /* _ASM_GENERIC_LOCAL64_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 030a954ed29..8a92a170fb7 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -156,10 +156,6 @@ CPU_KEEP(exit.data) \ MEM_KEEP(init.data) \ MEM_KEEP(exit.data) \ - . = ALIGN(8); \ - VMLINUX_SYMBOL(__start___markers) = .; \ - *(__markers) \ - VMLINUX_SYMBOL(__stop___markers) = .; \ . = ALIGN(32); \ VMLINUX_SYMBOL(__start___tracepoints) = .; \ *(__tracepoints) \ @@ -653,6 +649,7 @@ EXIT_DATA \ EXIT_CALL \ *(.discard) \ + *(.discard.*) \ } /** diff --git a/include/drm/drm.h b/include/drm/drm.h index e3f46e0cb7d..e5f70617dec 100644 --- a/include/drm/drm.h +++ b/include/drm/drm.h @@ -663,6 +663,8 @@ struct drm_gem_open { #define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) #define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) +#define DRM_IOCTL_GEM_PRIME_OPEN DRM_IOWR(0x2e, struct drm_gem_open) + #define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) #define DRM_IOCTL_AGP_RELEASE DRM_IO( 0x31) #define DRM_IOCTL_AGP_ENABLE DRM_IOW( 0x32, struct drm_agp_mode) diff --git a/include/drm/drmP.h b/include/drm/drmP.h index c1b987158df..e2a4da7d7fa 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -9,6 +9,7 @@ /* * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas. * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California. + * Copyright (c) 2009-2010, Code Aurora Forum. * All rights reserved. * * Permission is hereby granted, free of charge, to any person obtaining a @@ -48,9 +49,9 @@ #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/file.h> +#include <linux/platform_device.h> #include <linux/pci.h> #include <linux/jiffies.h> -#include <linux/smp_lock.h> /* For (un)lock_kernel */ #include <linux/dma-mapping.h> #include <linux/mm.h> #include <linux/cdev.h> @@ -144,6 +145,7 @@ extern void drm_ut_debug_printk(unsigned int request_level, #define DRIVER_IRQ_VBL2 0x800 #define DRIVER_GEM 0x1000 #define DRIVER_MODESET 0x2000 +#define DRIVER_USE_PLATFORM_DEVICE 0x4000 /***********************************************************************/ /** \name Begin the DRM... */ @@ -403,6 +405,8 @@ struct drm_pending_event { struct drm_event *event; struct list_head link; struct drm_file *file_priv; + pid_t pid; /* pid of requester, no guarantee it's valid by the time + we deliver the event, for tracing only */ void (*destroy)(struct drm_pending_event *event); }; @@ -823,6 +827,7 @@ struct drm_driver { int num_ioctls; struct file_operations fops; struct pci_driver pci_driver; + struct platform_device *platform_device; /* List of devices hanging off this driver */ struct list_head device_list; }; @@ -1015,12 +1020,16 @@ struct drm_device { struct drm_agp_head *agp; /**< AGP data */ + struct device *dev; /**< Device structure */ struct pci_dev *pdev; /**< PCI device structure */ int pci_vendor; /**< PCI vendor id */ int pci_device; /**< PCI device id */ #ifdef __alpha__ struct pci_controller *hose; #endif + + struct platform_device *platformdev; /**< Platform device struture */ + struct drm_sg_mem *sg; /**< Scatter gather memory */ int num_crtcs; /**< Number of CRTCs on this device */ void *dev_private; /**< device private data */ @@ -1060,17 +1069,21 @@ struct drm_device { }; -static inline int drm_dev_to_irq(struct drm_device *dev) -{ - return dev->pdev->irq; -} - static __inline__ int drm_core_check_feature(struct drm_device *dev, int feature) { return ((dev->driver->driver_features & feature) ? 1 : 0); } + +static inline int drm_dev_to_irq(struct drm_device *dev) +{ + if (drm_core_check_feature(dev, DRIVER_USE_PLATFORM_DEVICE)) + return platform_get_irq(dev->platformdev, 0); + else + return dev->pdev->irq; +} + #ifdef __alpha__ #define drm_get_pci_domain(dev) dev->hose->index #else @@ -1138,6 +1151,7 @@ extern long drm_compat_ioctl(struct file *filp, extern int drm_lastclose(struct drm_device *dev); /* Device support (drm_fops.h) */ +extern struct mutex drm_global_mutex; extern int drm_open(struct inode *inode, struct file *filp); extern int drm_stub_open(struct inode *inode, struct file *filp); extern int drm_fasync(int fd, struct file *filp, int on); @@ -1273,10 +1287,6 @@ extern int drm_freebufs(struct drm_device *dev, void *data, extern int drm_mapbufs(struct drm_device *dev, void *data, struct drm_file *file_priv); extern int drm_order(unsigned long size); -extern resource_size_t drm_get_resource_start(struct drm_device *dev, - unsigned int resource); -extern resource_size_t drm_get_resource_len(struct drm_device *dev, - unsigned int resource); /* DMA support (drm_dma.h) */ extern int drm_dma_setup(struct drm_device *dev); @@ -1351,8 +1361,11 @@ extern int drm_dropmaster_ioctl(struct drm_device *dev, void *data, struct drm_master *drm_master_create(struct drm_minor *minor); extern struct drm_master *drm_master_get(struct drm_master *master); extern void drm_master_put(struct drm_master **master); -extern int drm_get_dev(struct pci_dev *pdev, const struct pci_device_id *ent, - struct drm_driver *driver); +extern int drm_get_pci_dev(struct pci_dev *pdev, + const struct pci_device_id *ent, + struct drm_driver *driver); +extern int drm_get_platform_dev(struct platform_device *pdev, + struct drm_driver *driver); extern void drm_put_dev(struct drm_device *dev); extern int drm_put_minor(struct drm_minor **minor); extern unsigned int drm_debug; @@ -1440,6 +1453,8 @@ void drm_gem_vm_open(struct vm_area_struct *vma); void drm_gem_vm_close(struct vm_area_struct *vma); int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma); +#include "drm_global.h" + static inline void drm_gem_object_reference(struct drm_gem_object *obj) { @@ -1529,6 +1544,9 @@ static __inline__ struct drm_local_map *drm_core_findmap(struct drm_device *dev, static __inline__ int drm_device_is_agp(struct drm_device *dev) { + if (drm_core_check_feature(dev, DRIVER_USE_PLATFORM_DEVICE)) + return 0; + if (dev->driver->device_is_agp != NULL) { int err = (*dev->driver->device_is_agp) (dev); @@ -1542,7 +1560,10 @@ static __inline__ int drm_device_is_agp(struct drm_device *dev) static __inline__ int drm_device_is_pcie(struct drm_device *dev) { - return pci_find_capability(dev->pdev, PCI_CAP_ID_EXP); + if (drm_core_check_feature(dev, DRIVER_USE_PLATFORM_DEVICE)) + return 0; + else + return pci_find_capability(dev->pdev, PCI_CAP_ID_EXP); } static __inline__ void drm_core_dropmap(struct drm_local_map *map) @@ -1550,6 +1571,21 @@ static __inline__ void drm_core_dropmap(struct drm_local_map *map) } #include "drm_mem_util.h" + +static inline void *drm_get_device(struct drm_device *dev) +{ + if (drm_core_check_feature(dev, DRIVER_USE_PLATFORM_DEVICE)) + return dev->platformdev; + else + return dev->pdev; +} + +extern int drm_platform_init(struct drm_driver *driver); +extern int drm_pci_init(struct drm_driver *driver); +extern int drm_fill_in_dev(struct drm_device *dev, + const struct pci_device_id *ent, + struct drm_driver *driver); +int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type); /*@}*/ #endif /* __KERNEL__ */ diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h index 1121f7799c6..59b7073b13f 100644 --- a/include/drm/drm_crtc_helper.h +++ b/include/drm/drm_crtc_helper.h @@ -60,9 +60,14 @@ struct drm_crtc_helper_funcs { /* Move the crtc on the current fb to the given position *optional* */ int (*mode_set_base)(struct drm_crtc *crtc, int x, int y, struct drm_framebuffer *old_fb); + int (*mode_set_base_atomic)(struct drm_crtc *crtc, + struct drm_framebuffer *fb, int x, int y); /* reload the current crtc LUT */ void (*load_lut)(struct drm_crtc *crtc); + + /* disable crtc when not in use - more explicit than dpms off */ + void (*disable)(struct drm_crtc *crtc); }; struct drm_encoder_helper_funcs { diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index f0a6afc47e7..f22e7fe4b6d 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -32,6 +32,8 @@ struct drm_fb_helper; +#include <linux/kgdb.h> + struct drm_fb_helper_crtc { uint32_t crtc_id; struct drm_mode_set mode_set; @@ -78,6 +80,7 @@ struct drm_fb_helper_connector { struct drm_fb_helper { struct drm_framebuffer *fb; + struct drm_framebuffer *saved_fb; struct drm_device *dev; struct drm_display_mode *mode; int crtc_count; @@ -126,5 +129,7 @@ int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info); bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper); bool drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper, int bpp_sel); int drm_fb_helper_single_add_all_connectors(struct drm_fb_helper *fb_helper); +int drm_fb_helper_debug_enter(struct fb_info *info); +int drm_fb_helper_debug_leave(struct fb_info *info); #endif diff --git a/include/drm/drm_global.h b/include/drm/drm_global.h new file mode 100644 index 00000000000..a06805eaf64 --- /dev/null +++ b/include/drm/drm_global.h @@ -0,0 +1,53 @@ +/************************************************************************** + * + * Copyright 2008-2009 VMware, Inc., Palo Alto, CA., USA + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ +/* + * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> + */ + +#ifndef _DRM_GLOBAL_H_ +#define _DRM_GLOBAL_H_ +enum drm_global_types { + DRM_GLOBAL_TTM_MEM = 0, + DRM_GLOBAL_TTM_BO, + DRM_GLOBAL_TTM_OBJECT, + DRM_GLOBAL_NUM +}; + +struct drm_global_reference { + enum drm_global_types global_type; + size_t size; + void *object; + int (*init) (struct drm_global_reference *); + void (*release) (struct drm_global_reference *); +}; + +extern void drm_global_init(void); +extern void drm_global_release(void); +extern int drm_global_item_ref(struct drm_global_reference *ref); +extern void drm_global_item_unref(struct drm_global_reference *ref); + +#endif diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h index 4c10be39a43..bf01531193d 100644 --- a/include/drm/drm_mm.h +++ b/include/drm/drm_mm.h @@ -42,21 +42,31 @@ #endif struct drm_mm_node { - struct list_head fl_entry; - struct list_head ml_entry; - int free; + struct list_head free_stack; + struct list_head node_list; + unsigned free : 1; + unsigned scanned_block : 1; + unsigned scanned_prev_free : 1; + unsigned scanned_next_free : 1; unsigned long start; unsigned long size; struct drm_mm *mm; - void *private; }; struct drm_mm { - struct list_head fl_entry; - struct list_head ml_entry; + /* List of free memory blocks, most recently freed ordered. */ + struct list_head free_stack; + /* List of all memory nodes, ordered according to the (increasing) start + * address of the memory node. */ + struct list_head node_list; struct list_head unused_nodes; int num_unused; spinlock_t unused_lock; + unsigned scan_alignment; + unsigned long scan_size; + unsigned long scan_hit_start; + unsigned scan_hit_size; + unsigned scanned_blocks; }; /* @@ -133,6 +143,11 @@ static inline struct drm_mm *drm_get_mm(struct drm_mm_node *block) return block->mm; } +void drm_mm_init_scan(struct drm_mm *mm, unsigned long size, + unsigned alignment); +int drm_mm_scan_add_block(struct drm_mm_node *node); +int drm_mm_scan_remove_block(struct drm_mm_node *node); + extern void drm_mm_debug_table(struct drm_mm *mm, const char *prefix); #ifdef CONFIG_DEBUG_FS int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm); diff --git a/include/drm/drm_mode.h b/include/drm/drm_mode.h index c5ba1636613..0fc7397c8f1 100644 --- a/include/drm/drm_mode.h +++ b/include/drm/drm_mode.h @@ -74,6 +74,7 @@ /* Dithering mode options */ #define DRM_MODE_DITHERING_OFF 0 #define DRM_MODE_DITHERING_ON 1 +#define DRM_MODE_DITHERING_AUTO 2 /* Dirty info options */ #define DRM_MODE_DIRTY_OFF 0 diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 2d428b088cc..3a9940ef728 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -146,6 +146,8 @@ {0x1002, 0x6888, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6889, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x688A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x688C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x688D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6898, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6899, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x689c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_HEMLOCK|RADEON_NEW_MEMMAP}, \ @@ -161,6 +163,7 @@ {0x1002, 0x68be, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_JUNIPER|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68c0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_REDWOOD|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68c1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_REDWOOD|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x68c7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_REDWOOD|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68c8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_REDWOOD|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68c9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_REDWOOD|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68d8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_REDWOOD|RADEON_NEW_MEMMAP}, \ @@ -174,6 +177,7 @@ {0x1002, 0x68e8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68e9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68f1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x68f2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68f8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68f9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \ {0x1002, 0x68fe, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \ @@ -314,6 +318,7 @@ {0x1002, 0x9456, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \ {0x1002, 0x945A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x945B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x945E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9460, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9462, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \ {0x1002, 0x946A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ @@ -324,6 +329,7 @@ {0x1002, 0x9487, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9488, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9489, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x948A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x948F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9490, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9491, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ @@ -366,6 +372,7 @@ {0x1002, 0x9553, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9555, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9557, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x955f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9580, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9581, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9583, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ diff --git a/include/drm/i2c/sil164.h b/include/drm/i2c/sil164.h new file mode 100644 index 00000000000..205e27384c8 --- /dev/null +++ b/include/drm/i2c/sil164.h @@ -0,0 +1,63 @@ +/* + * Copyright (C) 2010 Francisco Jerez. + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining + * a copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sublicense, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial + * portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + * IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE + * LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION + * OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION + * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef __DRM_I2C_SIL164_H__ +#define __DRM_I2C_SIL164_H__ + +/** + * struct sil164_encoder_params + * + * Describes how the sil164 is connected to the GPU. It should be used + * as the @params parameter of its @set_config method. + * + * See "http://www.siliconimage.com/docs/SiI-DS-0021-E-164.pdf". + */ +struct sil164_encoder_params { + enum { + SIL164_INPUT_EDGE_FALLING = 0, + SIL164_INPUT_EDGE_RISING + } input_edge; + + enum { + SIL164_INPUT_WIDTH_12BIT = 0, + SIL164_INPUT_WIDTH_24BIT + } input_width; + + enum { + SIL164_INPUT_SINGLE_EDGE = 0, + SIL164_INPUT_DUAL_EDGE + } input_dual; + + enum { + SIL164_PLL_FILTER_ON = 0, + SIL164_PLL_FILTER_OFF, + } pll_filter; + + int input_skew; /** < Allowed range [-4, 3], use 0 for no de-skew. */ + int duallink_skew; /** < Allowed range [-4, 3]. */ +}; + +#endif diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h index 5347063e9d5..0acaf8f9143 100644 --- a/include/drm/radeon_drm.h +++ b/include/drm/radeon_drm.h @@ -904,6 +904,8 @@ struct drm_radeon_cs { #define RADEON_INFO_ACCEL_WORKING 0x03 #define RADEON_INFO_CRTC_FROM_ID 0x04 #define RADEON_INFO_ACCEL_WORKING2 0x05 +#define RADEON_INFO_TILING_CONFIG 0x06 +#define RADEON_INFO_WANT_HYPERZ 0x07 struct drm_radeon_info { uint32_t request; diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 0ea602da43e..b87504235f1 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -34,6 +34,7 @@ #include "ttm/ttm_memory.h" #include "ttm/ttm_module.h" #include "drm_mm.h" +#include "drm_global.h" #include "linux/workqueue.h" #include "linux/fs.h" #include "linux/spinlock.h" @@ -362,7 +363,7 @@ struct ttm_bo_driver { */ struct ttm_bo_global_ref { - struct ttm_global_reference ref; + struct drm_global_reference ref; struct ttm_mem_global *mem_glob; }; @@ -687,8 +688,8 @@ extern int ttm_mem_io_reserve(struct ttm_bo_device *bdev, extern void ttm_mem_io_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem); -extern void ttm_bo_global_release(struct ttm_global_reference *ref); -extern int ttm_bo_global_init(struct ttm_global_reference *ref); +extern void ttm_bo_global_release(struct drm_global_reference *ref); +extern int ttm_bo_global_init(struct drm_global_reference *ref); extern int ttm_bo_device_release(struct ttm_bo_device *bdev); diff --git a/include/drm/ttm/ttm_module.h b/include/drm/ttm/ttm_module.h index cf416aee19a..45fa318c158 100644 --- a/include/drm/ttm/ttm_module.h +++ b/include/drm/ttm/ttm_module.h @@ -35,26 +35,6 @@ struct kobject; #define TTM_PFX "[TTM] " - -enum ttm_global_types { - TTM_GLOBAL_TTM_MEM = 0, - TTM_GLOBAL_TTM_BO, - TTM_GLOBAL_TTM_OBJECT, - TTM_GLOBAL_NUM -}; - -struct ttm_global_reference { - enum ttm_global_types global_type; - size_t size; - void *object; - int (*init) (struct ttm_global_reference *); - void (*release) (struct ttm_global_reference *); -}; - -extern void ttm_global_init(void); -extern void ttm_global_release(void); -extern int ttm_global_item_ref(struct ttm_global_reference *ref); -extern void ttm_global_item_unref(struct ttm_global_reference *ref); extern struct kobject *ttm_get_kobj(void); #endif /* _TTM_MODULE_H_ */ diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index f7dd576dd5a..be3d9a77d6e 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -15,11 +15,13 @@ #ifndef _AHCI_PLATFORM_H #define _AHCI_PLATFORM_H +#include <linux/compiler.h> + struct device; struct ata_port_info; struct ahci_platform_data { - int (*init)(struct device *dev); + int (*init)(struct device *dev, void __iomem *addr); void (*exit)(struct device *dev); const struct ata_port_info *ata_port_info; unsigned int force_port_map; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index a5a472b1074..c1a62c56a66 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -16,6 +16,7 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) +# define __rcu extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); #else @@ -34,6 +35,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __release(x) (void)0 # define __cond_lock(x,c) (c) # define __percpu +# define __rcu #endif #ifdef __KERNEL__ diff --git a/include/linux/console.h b/include/linux/console.h index dcca5339ceb..f76fc297322 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -55,6 +55,16 @@ struct consw { void (*con_invert_region)(struct vc_data *, u16 *, int); u16 *(*con_screen_pos)(struct vc_data *, int); unsigned long (*con_getxy)(struct vc_data *, unsigned long, int *, int *); + /* + * Prepare the console for the debugger. This includes, but is not + * limited to, unblanking the console, loading an appropriate + * palette, and allowing debugger generated output. + */ + int (*con_debug_enter)(struct vc_data *); + /* + * Restore the console to its pre-debug state as closely as possible. + */ + int (*con_debug_leave)(struct vc_data *); }; extern const struct consw *conswitchp; @@ -69,6 +79,9 @@ int register_con_driver(const struct consw *csw, int first, int last); int unregister_con_driver(const struct consw *csw); int take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); +int con_debug_enter(struct vc_data *vc); +int con_debug_leave(void); + /* scroll */ #define SM_UP (1) #define SM_DOWN (2) diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e287863ac05..de6b1722cdc 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -48,6 +48,31 @@ extern ssize_t arch_cpu_release(const char *, size_t); #endif struct notifier_block; +/* + * CPU notifier priorities. + */ +enum { + /* + * SCHED_ACTIVE marks a cpu which is coming up active during + * CPU_ONLINE and CPU_DOWN_FAILED and must be the first + * notifier. CPUSET_ACTIVE adjusts cpuset according to + * cpu_active mask right after SCHED_ACTIVE. During + * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are + * ordered in the similar way. + * + * This ordering guarantees consistent cpu_active mask and + * migration behavior to all cpu notifiers. + */ + CPU_PRI_SCHED_ACTIVE = INT_MAX, + CPU_PRI_CPUSET_ACTIVE = INT_MAX - 1, + CPU_PRI_SCHED_INACTIVE = INT_MIN + 1, + CPU_PRI_CPUSET_INACTIVE = INT_MIN, + + /* migration should happen before other stuff but after perf */ + CPU_PRI_PERF = 20, + CPU_PRI_MIGRATION = 10, +}; + #ifdef CONFIG_SMP /* Need to know about CPUs going up/down? */ #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 457ed765a11..f20eb8f1602 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -20,6 +20,7 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ extern int cpuset_init(void); extern void cpuset_init_smp(void); +extern void cpuset_update_active_cpus(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern int cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -132,6 +133,11 @@ static inline void set_mems_allowed(nodemask_t nodemask) static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} +static inline void cpuset_update_active_cpus(void) +{ + partition_sched_domains(1, NULL, NULL); +} + static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { diff --git a/include/linux/fb.h b/include/linux/fb.h index e7445df44d6..0c5659c41b0 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -3,6 +3,9 @@ #include <linux/types.h> #include <linux/i2c.h> +#ifdef __KERNEL__ +#include <linux/kgdb.h> +#endif /* __KERNEL__ */ /* Definitions of frame buffers */ @@ -607,6 +610,12 @@ struct fb_deferred_io { * LOCKING NOTE: those functions must _ALL_ be called with the console * semaphore held, this is the only suitable locking mechanism we have * in 2.6. Some may be called at interrupt time at this point though. + * + * The exception to this is the debug related hooks. Putting the fb + * into a debug state (e.g. flipping to the kernel console) and restoring + * it must be done in a lock-free manner, so low level drivers should + * keep track of the initial console (if applicable) and may need to + * perform direct, unlocked hardware writes in these hooks. */ struct fb_ops { @@ -676,6 +685,10 @@ struct fb_ops { /* teardown any resources to do with this framebuffer */ void (*fb_destroy)(struct fb_info *info); + + /* called at KDB enter and leave time to prepare the console */ + int (*fb_debug_enter)(struct fb_info *info); + int (*fb_debug_leave)(struct fb_info *info); }; #ifdef CONFIG_FB_TILEBLITTING diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index d147461bc27..f59ed297b66 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -11,6 +11,7 @@ #include <linux/rcupdate.h> #include <linux/types.h> #include <linux/init.h> +#include <linux/fs.h> #include <asm/atomic.h> diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 41e46330d9b..dcd6a7c3a43 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1,3 +1,8 @@ +/* + * Ftrace header. For implementation details beyond the random comments + * scattered below, see: Documentation/trace/ftrace-design.txt + */ + #ifndef _LINUX_FTRACE_H #define _LINUX_FTRACE_H diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 3167f2df412..02b8b24f8f5 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -11,8 +11,6 @@ struct trace_array; struct tracer; struct dentry; -DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq); - struct trace_print_flags { unsigned long mask; const char *name; @@ -58,6 +56,9 @@ struct trace_iterator { struct ring_buffer_iter *buffer_iter[NR_CPUS]; unsigned long iter_flags; + /* trace_seq for __print_flags() and __print_symbolic() etc. */ + struct trace_seq tmp_seq; + /* The below is zeroed out in pipe_read */ struct trace_seq seq; struct trace_entry *ent; @@ -146,14 +147,19 @@ struct ftrace_event_class { int (*raw_init)(struct ftrace_event_call *); }; +extern int ftrace_event_reg(struct ftrace_event_call *event, + enum trace_reg type); + enum { TRACE_EVENT_FL_ENABLED_BIT, TRACE_EVENT_FL_FILTERED_BIT, + TRACE_EVENT_FL_RECORDED_CMD_BIT, }; enum { - TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), - TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), + TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), + TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), + TRACE_EVENT_FL_RECORDED_CMD = (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT), }; struct ftrace_event_call { @@ -171,6 +177,7 @@ struct ftrace_event_call { * 32 bit flags: * bit 1: enabled * bit 2: filter_active + * bit 3: enabled cmd record * * Changes to flags must hold the event_mutex. * @@ -257,8 +264,7 @@ static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, u64 count, struct pt_regs *regs, void *head) { - perf_tp_event(addr, count, raw_data, size, regs, head); - perf_swevent_put_recursion_context(rctx); + perf_tp_event(addr, count, raw_data, size, regs, head, rctx); } #endif diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 25085ddd955..e0ea40f6c51 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -79,7 +79,9 @@ io_mapping_free(struct io_mapping *mapping) /* Atomic map/unmap */ static inline void * -io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) +io_mapping_map_atomic_wc(struct io_mapping *mapping, + unsigned long offset, + int slot) { resource_size_t phys_addr; unsigned long pfn; @@ -87,13 +89,13 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) BUG_ON(offset >= mapping->size); phys_addr = mapping->base + offset; pfn = (unsigned long) (phys_addr >> PAGE_SHIFT); - return iomap_atomic_prot_pfn(pfn, KM_USER0, mapping->prot); + return iomap_atomic_prot_pfn(pfn, slot, mapping->prot); } static inline void -io_mapping_unmap_atomic(void *vaddr) +io_mapping_unmap_atomic(void *vaddr, int slot) { - iounmap_atomic(vaddr, KM_USER0); + iounmap_atomic(vaddr, slot); } static inline void * @@ -133,13 +135,15 @@ io_mapping_free(struct io_mapping *mapping) /* Atomic map/unmap */ static inline void * -io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) +io_mapping_map_atomic_wc(struct io_mapping *mapping, + unsigned long offset, + int slot) { return ((char *) mapping) + offset; } static inline void -io_mapping_unmap_atomic(void *vaddr) +io_mapping_unmap_atomic(void *vaddr, int slot) { } diff --git a/include/linux/io.h b/include/linux/io.h index 6c7f0ba0d5f..7fd2d2138bf 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -29,10 +29,10 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count); #ifdef CONFIG_MMU int ioremap_page_range(unsigned long addr, unsigned long end, - unsigned long phys_addr, pgprot_t prot); + phys_addr_t phys_addr, pgprot_t prot); #else static inline int ioremap_page_range(unsigned long addr, unsigned long end, - unsigned long phys_addr, pgprot_t prot) + phys_addr_t phys_addr, pgprot_t prot) { return 0; } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index be22ad83689..0a2ba409899 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -30,6 +30,7 @@ struct iommu_domain { }; #define IOMMU_CAP_CACHE_COHERENCY 0x1 +#define IOMMU_CAP_INTR_REMAP 0x2 /* isolates device intrs */ struct iommu_ops { int (*domain_init)(struct iommu_domain *domain); diff --git a/include/linux/kdb.h b/include/linux/kdb.h index ccb2b3ec0fe..ea6e5244ed3 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -114,4 +114,8 @@ enum { KDB_INIT_EARLY, KDB_INIT_FULL, }; + +extern int kdbgetintenv(const char *, int *); +extern int kdb_set(int, const char **); + #endif /* !_KDB_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5de838b0fc1..38e462e0059 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -513,9 +513,6 @@ extern void tracing_start(void); extern void tracing_stop(void); extern void ftrace_off_permanent(void); -extern void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3); - static inline void __attribute__ ((format (printf, 1, 2))) ____trace_printk_check_format(const char *fmt, ...) { @@ -591,8 +588,6 @@ __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap); extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode); #else -static inline void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { } static inline int trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 9340f34d1bb..cc96f0f23e0 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -90,6 +90,19 @@ struct kgdb_bkpt { enum kgdb_bpstate state; }; +struct dbg_reg_def_t { + char *name; + int size; + int offset; +}; + +#ifndef DBG_MAX_REG_NUM +#define DBG_MAX_REG_NUM 0 +#else +extern struct dbg_reg_def_t dbg_reg_def[]; +extern char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs); +extern int dbg_set_reg(int regno, void *mem, struct pt_regs *regs); +#endif #ifndef KGDB_MAX_BREAKPOINTS # define KGDB_MAX_BREAKPOINTS 1000 #endif @@ -281,7 +294,7 @@ extern void kgdb_unregister_io_module(struct kgdb_io *local_kgdb_io_ops); extern struct kgdb_io *dbg_io_ops; extern int kgdb_hex2long(char **ptr, unsigned long *long_val); -extern int kgdb_mem2hex(char *mem, char *buf, int count); +extern char *kgdb_mem2hex(char *mem, char *buf, int count); extern int kgdb_hex2mem(char *buf, char *mem, int count); extern int kgdb_isremovedbreak(unsigned long addr); diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h deleted file mode 100644 index b616d3930c3..00000000000 --- a/include/linux/kmemtrace.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * Copyright (C) 2008 Eduard - Gabriel Munteanu - * - * This file is released under GPL version 2. - */ - -#ifndef _LINUX_KMEMTRACE_H -#define _LINUX_KMEMTRACE_H - -#ifdef __KERNEL__ - -#include <trace/events/kmem.h> - -#ifdef CONFIG_KMEMTRACE -extern void kmemtrace_init(void); -#else -static inline void kmemtrace_init(void) -{ -} -#endif - -#endif /* __KERNEL__ */ - -#endif /* _LINUX_KMEMTRACE_H */ - diff --git a/include/linux/nmi.h b/include/linux/nmi.h index b752e807add..06aab5eee13 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -20,10 +20,14 @@ extern void touch_nmi_watchdog(void); extern void acpi_nmi_disable(void); extern void acpi_nmi_enable(void); #else +#ifndef CONFIG_HARDLOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { touch_softlockup_watchdog(); } +#else +extern void touch_nmi_watchdog(void); +#endif static inline void acpi_nmi_disable(void) { } static inline void acpi_nmi_enable(void) { } #endif @@ -47,4 +51,13 @@ static inline bool trigger_all_cpu_backtrace(void) } #endif +#ifdef CONFIG_LOCKUP_DETECTOR +int hw_nmi_is_cpu_stuck(struct pt_regs *); +u64 hw_nmi_get_sample_period(void); +extern int watchdog_enabled; +struct ctl_table; +extern int proc_dowatchdog_enabled(struct ctl_table *, int , + void __user *, size_t *, loff_t *); +#endif + #endif diff --git a/include/linux/of.h b/include/linux/of.h index a367e19bb3a..cad7cf0ab27 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -70,6 +70,11 @@ extern struct device_node *allnodes; extern struct device_node *of_chosen; extern rwlock_t devtree_lock; +static inline bool of_node_is_root(const struct device_node *node) +{ + return node && (node->parent == NULL); +} + static inline int of_node_check_flag(struct device_node *n, unsigned long flag) { return test_bit(flag, &n->_flags); @@ -141,6 +146,11 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #define OF_BAD_ADDR ((u64)-1) +#ifndef of_node_to_nid +static inline int of_node_to_nid(struct device_node *np) { return -1; } +#define of_node_to_nid of_node_to_nid +#endif + extern struct device_node *of_find_node_by_name(struct device_node *from, const char *name); #define for_each_node_by_name(dn, name) \ diff --git a/include/linux/of_address.h b/include/linux/of_address.h new file mode 100644 index 00000000000..8aea06f0564 --- /dev/null +++ b/include/linux/of_address.h @@ -0,0 +1,44 @@ +#ifndef __OF_ADDRESS_H +#define __OF_ADDRESS_H +#include <linux/ioport.h> +#include <linux/of.h> + +extern u64 of_translate_address(struct device_node *np, const u32 *addr); +extern int of_address_to_resource(struct device_node *dev, int index, + struct resource *r); +extern void __iomem *of_iomap(struct device_node *device, int index); + +/* Extract an address from a device, returns the region size and + * the address space flags too. The PCI version uses a BAR number + * instead of an absolute index + */ +extern const u32 *of_get_address(struct device_node *dev, int index, + u64 *size, unsigned int *flags); + +#ifndef pci_address_to_pio +static inline unsigned long pci_address_to_pio(phys_addr_t addr) { return -1; } +#define pci_address_to_pio pci_address_to_pio +#endif + +#ifdef CONFIG_PCI +extern const u32 *of_get_pci_address(struct device_node *dev, int bar_no, + u64 *size, unsigned int *flags); +extern int of_pci_address_to_resource(struct device_node *dev, int bar, + struct resource *r); +#else /* CONFIG_PCI */ +static inline int of_pci_address_to_resource(struct device_node *dev, int bar, + struct resource *r) +{ + return -ENOSYS; +} + +static inline const u32 *of_get_pci_address(struct device_node *dev, + int bar_no, u64 *size, unsigned int *flags) +{ + return NULL; +} +#endif /* CONFIG_PCI */ + + +#endif /* __OF_ADDRESS_H */ + diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 11651facc5f..35aa44ad9f2 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -1,32 +1,77 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H +/* + * The of_device *was* a kind of "base class" that was a superset of + * struct device for use by devices attached to an OF node and probed + * using OF properties. However, the important bit of OF-style + * probing, namely the device node pointer, has been moved into the + * common struct device when CONFIG_OF is set to make OF-style probing + * available to all bus types. So now, just make of_device and + * platform_device equivalent so that current of_platform bus users + * can be transparently migrated over to using the platform bus. + * + * This line will go away once all references to of_device are removed + * from the kernel. + */ +#define of_device platform_device +#include <linux/platform_device.h> +#include <linux/of_platform.h> /* temporary until merge */ + #ifdef CONFIG_OF_DEVICE #include <linux/device.h> #include <linux/of.h> #include <linux/mod_devicetable.h> -#include <asm/of_device.h> - #define to_of_device(d) container_of(d, struct of_device, dev) extern const struct of_device_id *of_match_device( const struct of_device_id *matches, const struct device *dev); +extern void of_device_make_bus_id(struct device *dev); + +/** + * of_driver_match_device - Tell if a driver's of_match_table matches a device. + * @drv: the device_driver structure to test + * @dev: the device structure to match against + */ +static inline int of_driver_match_device(const struct device *dev, + const struct device_driver *drv) +{ + return of_match_device(drv->of_match_table, dev) != NULL; +} -extern struct of_device *of_dev_get(struct of_device *dev); -extern void of_dev_put(struct of_device *dev); +extern struct platform_device *of_dev_get(struct platform_device *dev); +extern void of_dev_put(struct platform_device *dev); -extern int of_device_register(struct of_device *ofdev); -extern void of_device_unregister(struct of_device *ofdev); +extern int of_device_register(struct platform_device *ofdev); +extern void of_device_unregister(struct platform_device *ofdev); extern void of_release_dev(struct device *dev); -static inline void of_device_free(struct of_device *dev) +static inline void of_device_free(struct platform_device *dev) { of_release_dev(&dev->dev); } -extern ssize_t of_device_get_modalias(struct of_device *ofdev, +extern ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len); + +extern int of_device_uevent(struct device *dev, struct kobj_uevent_env *env); + + +#else /* CONFIG_OF_DEVICE */ + +static inline int of_driver_match_device(struct device *dev, + struct device_driver *drv) +{ + return 0; +} + +static inline int of_device_uevent(struct device *dev, + struct kobj_uevent_env *env) +{ + return -ENODEV; +} + #endif /* CONFIG_OF_DEVICE */ #endif /* _LINUX_OF_DEVICE_H */ diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index fc2472c3c25..6598c04dab0 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -33,34 +33,17 @@ enum of_gpio_flags { #ifdef CONFIG_OF_GPIO /* - * Generic OF GPIO chip - */ -struct of_gpio_chip { - struct gpio_chip gc; - int gpio_cells; - int (*xlate)(struct of_gpio_chip *of_gc, struct device_node *np, - const void *gpio_spec, enum of_gpio_flags *flags); -}; - -static inline struct of_gpio_chip *to_of_gpio_chip(struct gpio_chip *gc) -{ - return container_of(gc, struct of_gpio_chip, gc); -} - -/* * OF GPIO chip for memory mapped banks */ struct of_mm_gpio_chip { - struct of_gpio_chip of_gc; + struct gpio_chip gc; void (*save_regs)(struct of_mm_gpio_chip *mm_gc); void __iomem *regs; }; static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc) { - struct of_gpio_chip *of_gc = to_of_gpio_chip(gc); - - return container_of(of_gc, struct of_mm_gpio_chip, of_gc); + return container_of(gc, struct of_mm_gpio_chip, gc); } extern int of_get_gpio_flags(struct device_node *np, int index, @@ -69,11 +52,12 @@ extern unsigned int of_gpio_count(struct device_node *np); extern int of_mm_gpiochip_add(struct device_node *np, struct of_mm_gpio_chip *mm_gc); -extern int of_gpio_simple_xlate(struct of_gpio_chip *of_gc, - struct device_node *np, - const void *gpio_spec, - enum of_gpio_flags *flags); -#else + +extern void of_gpiochip_add(struct gpio_chip *gc); +extern void of_gpiochip_remove(struct gpio_chip *gc); +extern struct gpio_chip *of_node_to_gpiochip(struct device_node *np); + +#else /* CONFIG_OF_GPIO */ /* Drivers may not strictly depend on the GPIO support, so let them link. */ static inline int of_get_gpio_flags(struct device_node *np, int index, @@ -87,6 +71,9 @@ static inline unsigned int of_gpio_count(struct device_node *np) return 0; } +static inline void of_gpiochip_add(struct gpio_chip *gc) { } +static inline void of_gpiochip_remove(struct gpio_chip *gc) { } + #endif /* CONFIG_OF_GPIO */ /** diff --git a/include/linux/of_i2c.h b/include/linux/of_i2c.h index 34974b5a76f..0efe8d465f5 100644 --- a/include/linux/of_i2c.h +++ b/include/linux/of_i2c.h @@ -12,12 +12,19 @@ #ifndef __LINUX_OF_I2C_H #define __LINUX_OF_I2C_H +#if defined(CONFIG_OF_I2C) || defined(CONFIG_OF_I2C_MODULE) #include <linux/i2c.h> -void of_register_i2c_devices(struct i2c_adapter *adap, - struct device_node *adap_node); +extern void of_i2c_register_devices(struct i2c_adapter *adap); /* must call put_device() when done with returned i2c_client device */ -struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); +extern struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); + +#else +static inline void of_i2c_register_devices(struct i2c_adapter *adap) +{ + return; +} +#endif /* CONFIG_OF_I2C */ #endif /* __LINUX_OF_I2C_H */ diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h new file mode 100644 index 00000000000..5929781c104 --- /dev/null +++ b/include/linux/of_irq.h @@ -0,0 +1,70 @@ +#ifndef __OF_IRQ_H +#define __OF_IRQ_H + +#if defined(CONFIG_OF) +struct of_irq; +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/ioport.h> +#include <linux/of.h> + +/* + * irq_of_parse_and_map() is used ba all OF enabled platforms; but SPARC + * implements it differently. However, the prototype is the same for all, + * so declare it here regardless of the CONFIG_OF_IRQ setting. + */ +extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); + +#if defined(CONFIG_OF_IRQ) +/** + * of_irq - container for device_node/irq_specifier pair for an irq controller + * @controller: pointer to interrupt controller device tree node + * @size: size of interrupt specifier + * @specifier: array of cells @size long specifing the specific interrupt + * + * This structure is returned when an interrupt is mapped. The controller + * field needs to be put() after use + */ +#define OF_MAX_IRQ_SPEC 4 /* We handle specifiers of at most 4 cells */ +struct of_irq { + struct device_node *controller; /* Interrupt controller node */ + u32 size; /* Specifier size */ + u32 specifier[OF_MAX_IRQ_SPEC]; /* Specifier copy */ +}; + +/* + * Workarounds only applied to 32bit powermac machines + */ +#define OF_IMAP_OLDWORLD_MAC 0x00000001 +#define OF_IMAP_NO_PHANDLE 0x00000002 + +#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) +extern unsigned int of_irq_workarounds; +extern struct device_node *of_irq_dflt_pic; +extern int of_irq_map_oldworld(struct device_node *device, int index, + struct of_irq *out_irq); +#else /* CONFIG_PPC32 && CONFIG_PPC_PMAC */ +#define of_irq_workarounds (0) +#define of_irq_dflt_pic (NULL) +static inline int of_irq_map_oldworld(struct device_node *device, int index, + struct of_irq *out_irq) +{ + return -EINVAL; +} +#endif /* CONFIG_PPC32 && CONFIG_PPC_PMAC */ + + +extern int of_irq_map_raw(struct device_node *parent, const u32 *intspec, + u32 ointsize, const u32 *addr, + struct of_irq *out_irq); +extern int of_irq_map_one(struct device_node *device, int index, + struct of_irq *out_irq); +extern unsigned int irq_create_of_mapping(struct device_node *controller, + const u32 *intspec, + unsigned int intsize); +extern int of_irq_to_resource(struct device_node *dev, int index, + struct resource *r); + +#endif /* CONFIG_OF_IRQ */ +#endif /* CONFIG_OF */ +#endif /* __OF_IRQ_H */ diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 1643d3761eb..4e6d989c06d 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -17,29 +17,24 @@ #include <linux/mod_devicetable.h> #include <linux/pm.h> #include <linux/of_device.h> - -/* - * The of_platform_bus_type is a bus type used by drivers that do not - * attach to a macio or similar bus but still use OF probing - * mechanism - */ -extern struct bus_type of_platform_bus_type; +#include <linux/platform_device.h> /* * An of_platform_driver driver is attached to a basic of_device on - * the "platform bus" (of_platform_bus_type). + * the "platform bus" (platform_bus_type). */ struct of_platform_driver { - int (*probe)(struct of_device* dev, + int (*probe)(struct platform_device* dev, const struct of_device_id *match); - int (*remove)(struct of_device* dev); + int (*remove)(struct platform_device* dev); - int (*suspend)(struct of_device* dev, pm_message_t state); - int (*resume)(struct of_device* dev); - int (*shutdown)(struct of_device* dev); + int (*suspend)(struct platform_device* dev, pm_message_t state); + int (*resume)(struct platform_device* dev); + int (*shutdown)(struct platform_device* dev); struct device_driver driver; + struct platform_driver platform_driver; }; #define to_of_platform_driver(drv) \ container_of(drv,struct of_platform_driver, driver) @@ -49,20 +44,30 @@ extern int of_register_driver(struct of_platform_driver *drv, extern void of_unregister_driver(struct of_platform_driver *drv); /* Platform drivers register/unregister */ -static inline int of_register_platform_driver(struct of_platform_driver *drv) -{ - return of_register_driver(drv, &of_platform_bus_type); -} -static inline void of_unregister_platform_driver(struct of_platform_driver *drv) -{ - of_unregister_driver(drv); -} +extern int of_register_platform_driver(struct of_platform_driver *drv); +extern void of_unregister_platform_driver(struct of_platform_driver *drv); -#include <asm/of_platform.h> - -extern struct of_device *of_find_device_by_node(struct device_node *np); +extern struct platform_device *of_device_alloc(struct device_node *np, + const char *bus_id, + struct device *parent); +extern struct platform_device *of_find_device_by_node(struct device_node *np); extern int of_bus_type_init(struct bus_type *bus, const char *name); + +#if !defined(CONFIG_SPARC) /* SPARC has its own device registration method */ +/* Platform devices and busses creation */ +extern struct platform_device *of_platform_device_create(struct device_node *np, + const char *bus_id, + struct device *parent); + +/* pseudo "matches" value to not do deep probe */ +#define OF_NO_DEEP_PROBE ((struct of_device_id *)-1) + +extern int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); +#endif /* !CONFIG_SPARC */ + #endif /* CONFIG_OF_DEVICE */ #endif /* _LINUX_OF_PLATFORM_H */ diff --git a/include/linux/of_spi.h b/include/linux/of_spi.h index 5f71ee8c086..9e3e70f78ae 100644 --- a/include/linux/of_spi.h +++ b/include/linux/of_spi.h @@ -9,10 +9,15 @@ #ifndef __LINUX_OF_SPI_H #define __LINUX_OF_SPI_H -#include <linux/of.h> #include <linux/spi/spi.h> -extern void of_register_spi_devices(struct spi_master *master, - struct device_node *np); +#if defined(CONFIG_OF_SPI) || defined(CONFIG_OF_SPI_MODULE) +extern void of_register_spi_devices(struct spi_master *master); +#else +static inline void of_register_spi_devices(struct spi_master *master) +{ + return; +} +#endif /* CONFIG_OF_SPI */ #endif /* __LINUX_OF_SPI */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 33145408f04..c81eec4d3c3 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2325,9 +2325,11 @@ #define PCI_DEVICE_ID_JMICRON_JMB361 0x2361 #define PCI_DEVICE_ID_JMICRON_JMB362 0x2362 #define PCI_DEVICE_ID_JMICRON_JMB363 0x2363 +#define PCI_DEVICE_ID_JMICRON_JMB364 0x2364 #define PCI_DEVICE_ID_JMICRON_JMB365 0x2365 #define PCI_DEVICE_ID_JMICRON_JMB366 0x2366 #define PCI_DEVICE_ID_JMICRON_JMB368 0x2368 +#define PCI_DEVICE_ID_JMICRON_JMB369 0x2369 #define PCI_DEVICE_ID_JMICRON_JMB38X_SD 0x2381 #define PCI_DEVICE_ID_JMICRON_JMB38X_MMC 0x2382 #define PCI_DEVICE_ID_JMICRON_JMB38X_MS 0x2383 @@ -2773,3 +2775,6 @@ #define PCI_DEVICE_ID_RME_DIGI32 0x9896 #define PCI_DEVICE_ID_RME_DIGI32_PRO 0x9897 #define PCI_DEVICE_ID_RME_DIGI32_8 0x9898 + +#define PCI_VENDOR_ID_XEN 0x5853 +#define PCI_DEVICE_ID_XEN_PLATFORM 0x0001 diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 5d0266d9498..716f99b682c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -214,8 +214,9 @@ struct perf_event_attr { * See also PERF_RECORD_MISC_EXACT_IP */ precise_ip : 2, /* skid constraint */ + mmap_data : 1, /* non-exec mmap data */ - __reserved_1 : 47; + __reserved_1 : 46; union { __u32 wakeup_events; /* wakeup every n events */ @@ -461,6 +462,7 @@ enum perf_callchain_context { #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> +# include <asm/local64.h> #endif struct perf_guest_info_callbacks { @@ -531,14 +533,16 @@ struct hw_perf_event { struct hrtimer hrtimer; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT - /* breakpoint */ - struct arch_hw_breakpoint info; + struct { /* breakpoint */ + struct arch_hw_breakpoint info; + struct list_head bp_list; + }; #endif }; - atomic64_t prev_count; + local64_t prev_count; u64 sample_period; u64 last_period; - atomic64_t period_left; + local64_t period_left; u64 interrupts; u64 freq_time_stamp; @@ -548,7 +552,10 @@ struct hw_perf_event { struct perf_event; -#define PERF_EVENT_TXN_STARTED 1 +/* + * Common implementation detail of pmu::{start,commit,cancel}_txn + */ +#define PERF_EVENT_TXN 0x1 /** * struct pmu - generic performance monitoring unit @@ -562,14 +569,28 @@ struct pmu { void (*unthrottle) (struct perf_event *event); /* - * group events scheduling is treated as a transaction, - * add group events as a whole and perform one schedulability test. - * If test fails, roll back the whole group + * Group events scheduling is treated as a transaction, add group + * events as a whole and perform one schedulability test. If the test + * fails, roll back the whole group */ + /* + * Start the transaction, after this ->enable() doesn't need + * to do schedulability tests. + */ void (*start_txn) (const struct pmu *pmu); - void (*cancel_txn) (const struct pmu *pmu); + /* + * If ->start_txn() disabled the ->enable() schedulability test + * then ->commit_txn() is required to perform one. On success + * the transaction is closed. On error the transaction is kept + * open until ->cancel_txn() is called. + */ int (*commit_txn) (const struct pmu *pmu); + /* + * Will cancel the transaction, assumes ->disable() is called for + * each successfull ->enable() during the transaction. + */ + void (*cancel_txn) (const struct pmu *pmu); }; /** @@ -584,7 +605,9 @@ enum perf_event_active_state { struct file; -struct perf_mmap_data { +#define PERF_BUFFER_WRITABLE 0x01 + +struct perf_buffer { atomic_t refcount; struct rcu_head rcu_head; #ifdef CONFIG_PERF_USE_VMALLOC @@ -650,7 +673,8 @@ struct perf_event { enum perf_event_active_state state; unsigned int attach_state; - atomic64_t count; + local64_t count; + atomic64_t child_count; /* * These are the total time in nanoseconds that the event @@ -709,7 +733,7 @@ struct perf_event { atomic_t mmap_count; int mmap_locked; struct user_struct *mmap_user; - struct perf_mmap_data *data; + struct perf_buffer *buffer; /* poll related */ wait_queue_head_t waitq; @@ -807,7 +831,7 @@ struct perf_cpu_context { struct perf_output_handle { struct perf_event *event; - struct perf_mmap_data *data; + struct perf_buffer *buffer; unsigned long wakeup; unsigned long size; void *addr; @@ -910,8 +934,10 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); -extern void -perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); +#ifndef perf_arch_fetch_caller_regs +static inline void +perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } +#endif /* * Take a snapshot of the regs. Skip ip and frame pointer to @@ -921,31 +947,11 @@ perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); * - bp for callchains * - eflags, for future purposes, just in case */ -static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip) +static inline void perf_fetch_caller_regs(struct pt_regs *regs) { - unsigned long ip; - memset(regs, 0, sizeof(*regs)); - switch (skip) { - case 1 : - ip = CALLER_ADDR0; - break; - case 2 : - ip = CALLER_ADDR1; - break; - case 3 : - ip = CALLER_ADDR2; - break; - case 4: - ip = CALLER_ADDR3; - break; - /* No need to support further for now */ - default: - ip = 0; - } - - return perf_arch_fetch_caller_regs(regs, ip, skip); + perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static inline void @@ -955,21 +961,14 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) struct pt_regs hot_regs; if (!regs) { - perf_fetch_caller_regs(&hot_regs, 1); + perf_fetch_caller_regs(&hot_regs); regs = &hot_regs; } __perf_sw_event(event_id, nr, nmi, regs, addr); } } -extern void __perf_event_mmap(struct vm_area_struct *vma); - -static inline void perf_event_mmap(struct vm_area_struct *vma) -{ - if (vma->vm_flags & VM_EXEC) - __perf_event_mmap(vma); -} - +extern void perf_event_mmap(struct vm_area_struct *vma); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); @@ -1001,7 +1000,7 @@ static inline bool perf_paranoid_kernel(void) extern void perf_event_init(void); extern void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, struct pt_regs *regs, - struct hlist_head *head); + struct hlist_head *head, int rctx); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags @@ -1068,7 +1067,7 @@ static inline void perf_event_disable(struct perf_event *event) { } #define perf_cpu_notifier(fn) \ do { \ static struct notifier_block fn##_nb __cpuinitdata = \ - { .notifier_call = fn, .priority = 20 }; \ + { .notifier_call = fn, .priority = CPU_PRI_PERF }; \ fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ (void *)(unsigned long)smp_processor_id()); \ fn(&fn##_nb, (unsigned long)CPU_STARTING, \ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b653b4aaa8a..9fbc54a2585 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -40,6 +40,7 @@ #include <linux/seqlock.h> #include <linux/lockdep.h> #include <linux/completion.h> +#include <linux/debugobjects.h> #ifdef CONFIG_RCU_TORTURE_TEST extern int rcutorture_runnable; /* for sysctl */ @@ -79,6 +80,16 @@ extern void rcu_init(void); (ptr)->next = NULL; (ptr)->func = NULL; \ } while (0) +/* + * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic + * initialization and destruction of rcu_head on the stack. rcu_head structures + * allocated dynamically in the heap or defined statically don't need any + * initialization. + */ +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +extern void init_rcu_head_on_stack(struct rcu_head *head); +extern void destroy_rcu_head_on_stack(struct rcu_head *head); +#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head_on_stack(struct rcu_head *head) { } @@ -86,6 +97,7 @@ static inline void init_rcu_head_on_stack(struct rcu_head *head) static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } +#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -517,4 +529,74 @@ extern void call_rcu(struct rcu_head *head, extern void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *head)); +/* + * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally + * by call_rcu() and rcu callback execution, and are therefore not part of the + * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. + */ + +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +# define STATE_RCU_HEAD_READY 0 +# define STATE_RCU_HEAD_QUEUED 1 + +extern struct debug_obj_descr rcuhead_debug_descr; + +static inline void debug_rcu_head_queue(struct rcu_head *head) +{ + debug_object_activate(head, &rcuhead_debug_descr); + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_READY, + STATE_RCU_HEAD_QUEUED); +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_QUEUED, + STATE_RCU_HEAD_READY); + debug_object_deactivate(head, &rcuhead_debug_descr); +} +#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +static inline void debug_rcu_head_queue(struct rcu_head *head) +{ +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ +} +#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ + +#ifndef CONFIG_PROVE_RCU +#define __do_rcu_dereference_check(c) do { } while (0) +#endif /* #ifdef CONFIG_PROVE_RCU */ + +#define __rcu_dereference_index_check(p, c) \ + ({ \ + typeof(p) _________p1 = ACCESS_ONCE(p); \ + __do_rcu_dereference_check(c); \ + smp_read_barrier_depends(); \ + (_________p1); \ + }) + +/** + * rcu_dereference_index_check() - rcu_dereference for indices with debug checking + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * Similar to rcu_dereference_check(), but omits the sparse checking. + * This allows rcu_dereference_index_check() to be used on integers, + * which can then be used as array indices. Attempting to use + * rcu_dereference_check() on an integer will give compiler warnings + * because the sparse address-space mechanism relies on dereferencing + * the RCU-protected pointer. Dereferencing integers is not something + * that even gcc will put up with. + * + * Note that this function does not implicitly check for RCU read-side + * critical sections. If this function gains lots of uses, it might + * make sense to provide versions for each flavor of RCU, but it does + * not make sense as of early 2010. + */ +#define rcu_dereference_index_check(p, c) \ + __rcu_dereference_index_check((p), (c)) + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 0478888c689..9591907c4f7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -272,19 +272,10 @@ extern int runqueue_is_locked(int cpu); extern cpumask_var_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) -extern int select_nohz_load_balancer(int cpu); -extern int get_nohz_load_balancer(void); -extern int nohz_ratelimit(int cpu); +extern void select_nohz_load_balancer(int stop_tick); +extern int get_nohz_timer_target(void); #else -static inline int select_nohz_load_balancer(int cpu) -{ - return 0; -} - -static inline int nohz_ratelimit(int cpu) -{ - return 0; -} +static inline void select_nohz_load_balancer(int stop_tick) { } #endif /* @@ -316,20 +307,16 @@ extern void scheduler_tick(void); extern void sched_show_task(struct task_struct *p); -#ifdef CONFIG_DETECT_SOFTLOCKUP -extern void softlockup_tick(void); +#ifdef CONFIG_LOCKUP_DETECTOR extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); -extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); +extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; #else -static inline void softlockup_tick(void) -{ -} static inline void touch_softlockup_watchdog(void) { } @@ -805,7 +792,7 @@ enum cpu_idle_type { #define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */ #define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ - +#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ enum powersavings_balance_level { @@ -840,6 +827,8 @@ static inline int sd_balance_for_package_power(void) return SD_PREFER_SIBLING; } +extern int __weak arch_sd_sibiling_asym_packing(void); + /* * Optimise SD flags for power savings: * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings. @@ -861,7 +850,7 @@ struct sched_group { * CPU power of this group, SCHED_LOAD_SCALE being max power for a * single CPU. */ - unsigned int cpu_power; + unsigned int cpu_power, cpu_power_orig; /* * The CPUs this group covers. @@ -1697,6 +1686,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ @@ -1791,20 +1781,23 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) #endif /* - * Architectures can set this to 1 if they have specified - * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, - * but then during bootup it turns out that sched_clock() - * is reliable after all: + * Do not use outside of architecture code which knows its limitations. + * + * sched_clock() has no promise of monotonicity or bounded drift between + * CPUs, use (which you should not) requires disabling IRQs. + * + * Please use one of the three interfaces below. */ -#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -extern int sched_clock_stable; -#endif - -/* ftrace calls sched_clock() directly */ extern unsigned long long notrace sched_clock(void); +/* + * See the comment in kernel/sched_clock.c + */ +extern u64 cpu_clock(int cpu); +extern u64 local_clock(void); +extern u64 sched_clock_cpu(int cpu); + extern void sched_clock_init(void); -extern u64 sched_clock_cpu(int cpu); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline void sched_clock_tick(void) @@ -1819,17 +1812,19 @@ static inline void sched_clock_idle_wakeup_event(u64 delta_ns) { } #else +/* + * Architectures can set this to 1 if they have specified + * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, + * but then during bootup it turns out that sched_clock() + * is reliable after all: + */ +extern int sched_clock_stable; + extern void sched_clock_tick(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); #endif -/* - * For kernel-internal use: high-speed (but slightly incorrect) per-cpu - * clock constructed from sched_clock(): - */ -extern unsigned long long cpu_clock(int cpu); - extern unsigned long long task_sched_runtime(struct task_struct *task); extern unsigned long long thread_group_sched_runtime(struct task_struct *task); @@ -2435,18 +2430,6 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ -#ifdef CONFIG_TRACING -extern void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3); -#else -static inline void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ -} -#endif - extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 1812dac8c49..1acfa73ce2a 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -14,7 +14,8 @@ #include <asm/page.h> /* kmalloc_sizes.h needs PAGE_SIZE */ #include <asm/cache.h> /* kmalloc_sizes.h needs L1_CACHE_BYTES */ #include <linux/compiler.h> -#include <linux/kmemtrace.h> + +#include <trace/events/kmem.h> #ifndef ARCH_KMALLOC_MINALIGN /* diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 4ba59cfc1f7..6447a723ecb 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -10,9 +10,10 @@ #include <linux/gfp.h> #include <linux/workqueue.h> #include <linux/kobject.h> -#include <linux/kmemtrace.h> #include <linux/kmemleak.h> +#include <trace/events/kmem.h> + enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 13ebb5413a7..a6bfd1367d2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -167,7 +167,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; .enter_event = &event_enter_##sname, \ .exit_event = &event_exit_##sname, \ .enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \ - .exit_fields = LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \ }; #define SYSCALL_DEFINE0(sname) \ @@ -182,7 +181,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; .enter_event = &event_enter__##sname, \ .exit_event = &event_exit__##sname, \ .enter_fields = LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \ - .exit_fields = LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \ }; \ asmlinkage long sys_##sname(void) #else diff --git a/include/linux/topology.h b/include/linux/topology.h index c44df50a05a..b572e432d2f 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -103,6 +103,7 @@ int arch_update_cpu_topology(void); | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ | 0*SD_PREFER_SIBLING \ + | arch_sd_sibling_asym_packing() \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ diff --git a/include/linux/tty.h b/include/linux/tty.h index 931078b7322..7802a243ee1 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -552,6 +552,9 @@ static inline void tty_audit_push_task(struct task_struct *tsk, } #endif +/* tty_io.c */ +extern int __init tty_init(void); + /* tty_ioctl.c */ extern int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 227c2a585e4..de05e96e0a7 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -30,7 +30,7 @@ struct vm_struct { unsigned long flags; struct page **pages; unsigned int nr_pages; - unsigned long phys_addr; + phys_addr_t phys_addr; void *caller; }; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 9466e860d8c..d0f7c817849 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -297,4 +297,8 @@ static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) #else long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ + +#ifdef CONFIG_LOCKDEP +int in_workqueue_context(struct workqueue_struct *wq); +#endif #endif diff --git a/include/trace/boot.h b/include/trace/boot.h deleted file mode 100644 index 088ea089e31..00000000000 --- a/include/trace/boot.h +++ /dev/null @@ -1,60 +0,0 @@ -#ifndef _LINUX_TRACE_BOOT_H -#define _LINUX_TRACE_BOOT_H - -#include <linux/module.h> -#include <linux/kallsyms.h> -#include <linux/init.h> - -/* - * Structure which defines the trace of an initcall - * while it is called. - * You don't have to fill the func field since it is - * only used internally by the tracer. - */ -struct boot_trace_call { - pid_t caller; - char func[KSYM_SYMBOL_LEN]; -}; - -/* - * Structure which defines the trace of an initcall - * while it returns. - */ -struct boot_trace_ret { - char func[KSYM_SYMBOL_LEN]; - int result; - unsigned long long duration; /* nsecs */ -}; - -#ifdef CONFIG_BOOT_TRACER -/* Append the traces on the ring-buffer */ -extern void trace_boot_call(struct boot_trace_call *bt, initcall_t fn); -extern void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn); - -/* Tells the tracer that smp_pre_initcall is finished. - * So we can start the tracing - */ -extern void start_boot_trace(void); - -/* Resume the tracing of other necessary events - * such as sched switches - */ -extern void enable_boot_trace(void); - -/* Suspend this tracing. Actually, only sched_switches tracing have - * to be suspended. Initcalls doesn't need it.) - */ -extern void disable_boot_trace(void); -#else -static inline -void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { } - -static inline -void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { } - -static inline void start_boot_trace(void) { } -static inline void enable_boot_trace(void) { } -static inline void disable_boot_trace(void) { } -#endif /* CONFIG_BOOT_TRACER */ - -#endif /* __LINUX_TRACE_BOOT_H */ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index b9e1dd6c620..9208c92aeab 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -50,31 +50,6 @@ TRACE_EVENT(sched_kthread_stop_ret, ); /* - * Tracepoint for waiting on task to unschedule: - */ -TRACE_EVENT(sched_wait_task, - - TP_PROTO(struct task_struct *p), - - TP_ARGS(p), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - ), - - TP_printk("comm=%s pid=%d prio=%d", - __entry->comm, __entry->pid, __entry->prio) -); - -/* * Tracepoint for waking up a task: */ DECLARE_EVENT_CLASS(sched_wakeup_template, @@ -240,6 +215,13 @@ DEFINE_EVENT(sched_process_template, sched_process_exit, TP_ARGS(p)); /* + * Tracepoint for waiting on task to unschedule: + */ +DEFINE_EVENT(sched_process_template, sched_wait_task, + TP_PROTO(struct task_struct *p), + TP_ARGS(p)); + +/* * Tracepoint for a waiting task: */ TRACE_EVENT(sched_process_wait, diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 9496b965d62..c624126a9c8 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -8,11 +8,7 @@ #include <linux/hrtimer.h> #include <linux/timer.h> -/** - * timer_init - called when the timer is initialized - * @timer: pointer to struct timer_list - */ -TRACE_EVENT(timer_init, +DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), @@ -30,6 +26,17 @@ TRACE_EVENT(timer_init, ); /** + * timer_init - called when the timer is initialized + * @timer: pointer to struct timer_list + */ +DEFINE_EVENT(timer_class, timer_init, + + TP_PROTO(struct timer_list *timer), + + TP_ARGS(timer) +); + +/** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time @@ -94,42 +101,22 @@ TRACE_EVENT(timer_expire_entry, * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ -TRACE_EVENT(timer_expire_exit, +DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), - TP_ARGS(timer), - - TP_STRUCT__entry( - __field(void *, timer ) - ), - - TP_fast_assign( - __entry->timer = timer; - ), - - TP_printk("timer=%p", __entry->timer) + TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ -TRACE_EVENT(timer_cancel, +DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), - TP_ARGS(timer), - - TP_STRUCT__entry( - __field( void *, timer ) - ), - - TP_fast_assign( - __entry->timer = timer; - ), - - TP_printk("timer=%p", __entry->timer) + TP_ARGS(timer) ); /** @@ -224,14 +211,7 @@ TRACE_EVENT(hrtimer_expire_entry, (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->now })) ); -/** - * hrtimer_expire_exit - called immediately after the hrtimer callback returns - * @timer: pointer to struct hrtimer - * - * When used in combination with the hrtimer_expire_entry tracepoint we can - * determine the runtime of the callback function. - */ -TRACE_EVENT(hrtimer_expire_exit, +DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), @@ -249,24 +229,28 @@ TRACE_EVENT(hrtimer_expire_exit, ); /** - * hrtimer_cancel - called when the hrtimer is canceled - * @hrtimer: pointer to struct hrtimer + * hrtimer_expire_exit - called immediately after the hrtimer callback returns + * @timer: pointer to struct hrtimer + * + * When used in combination with the hrtimer_expire_entry tracepoint we can + * determine the runtime of the callback function. */ -TRACE_EVENT(hrtimer_cancel, +DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), - TP_ARGS(hrtimer), + TP_ARGS(hrtimer) +); - TP_STRUCT__entry( - __field( void *, hrtimer ) - ), +/** + * hrtimer_cancel - called when the hrtimer is canceled + * @hrtimer: pointer to struct hrtimer + */ +DEFINE_EVENT(hrtimer_class, hrtimer_cancel, - TP_fast_assign( - __entry->hrtimer = hrtimer; - ), + TP_PROTO(struct hrtimer *hrtimer), - TP_printk("hrtimer=%p", __entry->hrtimer) + TP_ARGS(hrtimer) ); /** diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 5a64905d727..a9377c0083a 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -75,15 +75,12 @@ #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) -#undef __cpparg -#define __cpparg(arg...) arg - /* Callbacks are meaningless to ftrace. */ #undef TRACE_EVENT_FN #define TRACE_EVENT_FN(name, proto, args, tstruct, \ assign, print, reg, unreg) \ - TRACE_EVENT(name, __cpparg(proto), __cpparg(args), \ - __cpparg(tstruct), __cpparg(assign), __cpparg(print)) \ + TRACE_EVENT(name, PARAMS(proto), PARAMS(args), \ + PARAMS(tstruct), PARAMS(assign), PARAMS(print)) \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) @@ -145,7 +142,7 @@ * struct trace_seq *s = &iter->seq; * struct ftrace_raw_<call> *field; <-- defined in stage 1 * struct trace_entry *entry; - * struct trace_seq *p; + * struct trace_seq *p = &iter->tmp_seq; * int ret; * * entry = iter->ent; @@ -157,12 +154,10 @@ * * field = (typeof(field))entry; * - * p = &get_cpu_var(ftrace_event_seq); * trace_seq_init(p); * ret = trace_seq_printf(s, "%s: ", <call>); * if (ret) * ret = trace_seq_printf(s, <TP_printk> "\n"); - * put_cpu(); * if (!ret) * return TRACE_TYPE_PARTIAL_LINE; * @@ -216,7 +211,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ struct trace_seq *s = &iter->seq; \ struct ftrace_raw_##call *field; \ struct trace_entry *entry; \ - struct trace_seq *p; \ + struct trace_seq *p = &iter->tmp_seq; \ int ret; \ \ event = container_of(trace_event, struct ftrace_event_call, \ @@ -231,12 +226,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ \ field = (typeof(field))entry; \ \ - p = &get_cpu_var(ftrace_event_seq); \ trace_seq_init(p); \ ret = trace_seq_printf(s, "%s: ", event->name); \ if (ret) \ ret = trace_seq_printf(s, print); \ - put_cpu(); \ if (!ret) \ return TRACE_TYPE_PARTIAL_LINE; \ \ @@ -255,7 +248,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ struct trace_seq *s = &iter->seq; \ struct ftrace_raw_##template *field; \ struct trace_entry *entry; \ - struct trace_seq *p; \ + struct trace_seq *p = &iter->tmp_seq; \ int ret; \ \ entry = iter->ent; \ @@ -267,12 +260,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ \ field = (typeof(field))entry; \ \ - p = &get_cpu_var(ftrace_event_seq); \ trace_seq_init(p); \ ret = trace_seq_printf(s, "%s: ", #call); \ if (ret) \ ret = trace_seq_printf(s, print); \ - put_cpu(); \ if (!ret) \ return TRACE_TYPE_PARTIAL_LINE; \ \ @@ -439,6 +430,7 @@ static inline notrace int ftrace_get_offsets_##call( \ * .fields = LIST_HEAD_INIT(event_class_##call.fields), * .raw_init = trace_event_raw_init, * .probe = ftrace_raw_event_##call, + * .reg = ftrace_event_reg, * }; * * static struct ftrace_event_call __used @@ -567,6 +559,7 @@ static struct ftrace_event_class __used event_class_##call = { \ .fields = LIST_HEAD_INIT(event_class_##call.fields),\ .raw_init = trace_event_raw_init, \ .probe = ftrace_raw_event_##call, \ + .reg = ftrace_event_reg, \ _TRACE_PERF_INIT(call) \ }; @@ -705,7 +698,7 @@ perf_trace_##call(void *__data, proto) \ int __data_size; \ int rctx; \ \ - perf_fetch_caller_regs(&__regs, 1); \ + perf_fetch_caller_regs(&__regs); \ \ __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\ diff --git a/include/trace/syscall.h b/include/trace/syscall.h index 257e08960d7..31966a4fb8c 100644 --- a/include/trace/syscall.h +++ b/include/trace/syscall.h @@ -26,7 +26,6 @@ struct syscall_metadata { const char **types; const char **args; struct list_head enter_fields; - struct list_head exit_fields; struct ftrace_event_call *enter_event; struct ftrace_event_call *exit_event; diff --git a/include/xen/events.h b/include/xen/events.h index e68d59a90ca..a15d93262e3 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -56,4 +56,11 @@ void xen_poll_irq(int irq); /* Determine the IRQ which is bound to an event channel */ unsigned irq_from_evtchn(unsigned int evtchn); +/* Xen HVM evtchn vector callback */ +extern void xen_hvm_callback_vector(void); +extern int xen_have_vector_callback; +int xen_set_callback_via(uint64_t via); +void xen_evtchn_do_upcall(struct pt_regs *regs); +void xen_hvm_evtchn_do_upcall(void); + #endif /* _XEN_EVENTS_H */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index a40f1cd91be..9a731706a01 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -51,6 +51,7 @@ struct gnttab_free_callback { u16 count; }; +int gnttab_init(void); int gnttab_suspend(void); int gnttab_resume(void); @@ -112,6 +113,9 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, void arch_gnttab_unmap_shared(struct grant_entry *shared, unsigned long nr_gframes); +extern unsigned long xen_hvm_resume_frames; +unsigned int gnttab_max_grant_frames(void); + #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) #endif /* __ASM_GNTTAB_H__ */ diff --git a/include/xen/hvm.h b/include/xen/hvm.h new file mode 100644 index 00000000000..b193fa2f9fd --- /dev/null +++ b/include/xen/hvm.h @@ -0,0 +1,30 @@ +/* Simple wrappers around HVM functions */ +#ifndef XEN_HVM_H__ +#define XEN_HVM_H__ + +#include <xen/interface/hvm/params.h> +#include <asm/xen/hypercall.h> + +static inline int hvm_get_parameter(int idx, uint64_t *value) +{ + struct xen_hvm_param xhv; + int r; + + xhv.domid = DOMID_SELF; + xhv.index = idx; + r = HYPERVISOR_hvm_op(HVMOP_get_param, &xhv); + if (r < 0) { + printk(KERN_ERR "Cannot get hvm parameter %d: %d!\n", + idx, r); + return r; + } + *value = xhv.value; + return r; +} + +#define HVM_CALLBACK_VIA_TYPE_VECTOR 0x2 +#define HVM_CALLBACK_VIA_TYPE_SHIFT 56 +#define HVM_CALLBACK_VECTOR(x) (((uint64_t)HVM_CALLBACK_VIA_TYPE_VECTOR)<<\ + HVM_CALLBACK_VIA_TYPE_SHIFT | (x)) + +#endif /* XEN_HVM_H__ */ diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h index f51b6413b05..70d2563ab16 100644 --- a/include/xen/interface/features.h +++ b/include/xen/interface/features.h @@ -41,6 +41,12 @@ /* x86: Does this Xen host support the MMU_PT_UPDATE_PRESERVE_AD hypercall? */ #define XENFEAT_mmu_pt_update_preserve_ad 5 +/* x86: Does this Xen host support the HVM callback vector type? */ +#define XENFEAT_hvm_callback_vector 8 + +/* x86: pvclock algorithm is safe to use on HVM */ +#define XENFEAT_hvm_safe_pvclock 9 + #define XENFEAT_NR_SUBMAPS 1 #endif /* __XEN_PUBLIC_FEATURES_H__ */ diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h index 39da93c21de..39e571796e3 100644 --- a/include/xen/interface/grant_table.h +++ b/include/xen/interface/grant_table.h @@ -28,6 +28,7 @@ #ifndef __XEN_PUBLIC_GRANT_TABLE_H__ #define __XEN_PUBLIC_GRANT_TABLE_H__ +#include <xen/interface/xen.h> /*********************************** * GRANT TABLE REPRESENTATION diff --git a/include/xen/interface/hvm/hvm_op.h b/include/xen/interface/hvm/hvm_op.h new file mode 100644 index 00000000000..a4827f46ee9 --- /dev/null +++ b/include/xen/interface/hvm/hvm_op.h @@ -0,0 +1,46 @@ +/* + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef __XEN_PUBLIC_HVM_HVM_OP_H__ +#define __XEN_PUBLIC_HVM_HVM_OP_H__ + +/* Get/set subcommands: the second argument of the hypercall is a + * pointer to a xen_hvm_param struct. */ +#define HVMOP_set_param 0 +#define HVMOP_get_param 1 +struct xen_hvm_param { + domid_t domid; /* IN */ + uint32_t index; /* IN */ + uint64_t value; /* IN/OUT */ +}; +DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_param); + +/* Hint from PV drivers for pagetable destruction. */ +#define HVMOP_pagetable_dying 9 +struct xen_hvm_pagetable_dying { + /* Domain with a pagetable about to be destroyed. */ + domid_t domid; + /* guest physical address of the toplevel pagetable dying */ + aligned_u64 gpa; +}; +typedef struct xen_hvm_pagetable_dying xen_hvm_pagetable_dying_t; +DEFINE_GUEST_HANDLE_STRUCT(xen_hvm_pagetable_dying_t); + +#endif /* __XEN_PUBLIC_HVM_HVM_OP_H__ */ diff --git a/include/xen/interface/hvm/params.h b/include/xen/interface/hvm/params.h new file mode 100644 index 00000000000..1888d8c157e --- /dev/null +++ b/include/xen/interface/hvm/params.h @@ -0,0 +1,95 @@ +/* + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef __XEN_PUBLIC_HVM_PARAMS_H__ +#define __XEN_PUBLIC_HVM_PARAMS_H__ + +#include "hvm_op.h" + +/* + * Parameter space for HVMOP_{set,get}_param. + */ + +/* + * How should CPU0 event-channel notifications be delivered? + * val[63:56] == 0: val[55:0] is a delivery GSI (Global System Interrupt). + * val[63:56] == 1: val[55:0] is a delivery PCI INTx line, as follows: + * Domain = val[47:32], Bus = val[31:16], + * DevFn = val[15: 8], IntX = val[ 1: 0] + * val[63:56] == 2: val[7:0] is a vector number. + * If val == 0 then CPU0 event-channel notifications are not delivered. + */ +#define HVM_PARAM_CALLBACK_IRQ 0 + +#define HVM_PARAM_STORE_PFN 1 +#define HVM_PARAM_STORE_EVTCHN 2 + +#define HVM_PARAM_PAE_ENABLED 4 + +#define HVM_PARAM_IOREQ_PFN 5 + +#define HVM_PARAM_BUFIOREQ_PFN 6 + +/* + * Set mode for virtual timers (currently x86 only): + * delay_for_missed_ticks (default): + * Do not advance a vcpu's time beyond the correct delivery time for + * interrupts that have been missed due to preemption. Deliver missed + * interrupts when the vcpu is rescheduled and advance the vcpu's virtual + * time stepwise for each one. + * no_delay_for_missed_ticks: + * As above, missed interrupts are delivered, but guest time always tracks + * wallclock (i.e., real) time while doing so. + * no_missed_ticks_pending: + * No missed interrupts are held pending. Instead, to ensure ticks are + * delivered at some non-zero rate, if we detect missed ticks then the + * internal tick alarm is not disabled if the VCPU is preempted during the + * next tick period. + * one_missed_tick_pending: + * Missed interrupts are collapsed together and delivered as one 'late tick'. + * Guest time always tracks wallclock (i.e., real) time. + */ +#define HVM_PARAM_TIMER_MODE 10 +#define HVMPTM_delay_for_missed_ticks 0 +#define HVMPTM_no_delay_for_missed_ticks 1 +#define HVMPTM_no_missed_ticks_pending 2 +#define HVMPTM_one_missed_tick_pending 3 + +/* Boolean: Enable virtual HPET (high-precision event timer)? (x86-only) */ +#define HVM_PARAM_HPET_ENABLED 11 + +/* Identity-map page directory used by Intel EPT when CR0.PG=0. */ +#define HVM_PARAM_IDENT_PT 12 + +/* Device Model domain, defaults to 0. */ +#define HVM_PARAM_DM_DOMAIN 13 + +/* ACPI S state: currently support S0 and S3 on x86. */ +#define HVM_PARAM_ACPI_S_STATE 14 + +/* TSS used on Intel when CR0.PE=0. */ +#define HVM_PARAM_VM86_TSS 15 + +/* Boolean: Enable aligning all periodic vpts to reduce interrupts */ +#define HVM_PARAM_VPT_ALIGN 16 + +#define HVM_NR_PARAMS 17 + +#endif /* __XEN_PUBLIC_HVM_PARAMS_H__ */ diff --git a/include/xen/platform_pci.h b/include/xen/platform_pci.h new file mode 100644 index 00000000000..ce9d671c636 --- /dev/null +++ b/include/xen/platform_pci.h @@ -0,0 +1,49 @@ +#ifndef _XEN_PLATFORM_PCI_H +#define _XEN_PLATFORM_PCI_H + +#define XEN_IOPORT_MAGIC_VAL 0x49d2 +#define XEN_IOPORT_LINUX_PRODNUM 0x0003 +#define XEN_IOPORT_LINUX_DRVVER 0x0001 + +#define XEN_IOPORT_BASE 0x10 + +#define XEN_IOPORT_PLATFLAGS (XEN_IOPORT_BASE + 0) /* 1 byte access (R/W) */ +#define XEN_IOPORT_MAGIC (XEN_IOPORT_BASE + 0) /* 2 byte access (R) */ +#define XEN_IOPORT_UNPLUG (XEN_IOPORT_BASE + 0) /* 2 byte access (W) */ +#define XEN_IOPORT_DRVVER (XEN_IOPORT_BASE + 0) /* 4 byte access (W) */ + +#define XEN_IOPORT_SYSLOG (XEN_IOPORT_BASE + 2) /* 1 byte access (W) */ +#define XEN_IOPORT_PROTOVER (XEN_IOPORT_BASE + 2) /* 1 byte access (R) */ +#define XEN_IOPORT_PRODNUM (XEN_IOPORT_BASE + 2) /* 2 byte access (W) */ + +#define XEN_UNPLUG_ALL_IDE_DISKS 1 +#define XEN_UNPLUG_ALL_NICS 2 +#define XEN_UNPLUG_AUX_IDE_DISKS 4 +#define XEN_UNPLUG_ALL 7 +#define XEN_UNPLUG_IGNORE 8 + +static inline int xen_must_unplug_nics(void) { +#if (defined(CONFIG_XEN_NETDEV_FRONTEND) || \ + defined(CONFIG_XEN_NETDEV_FRONTEND_MODULE)) && \ + (defined(CONFIG_XEN_PLATFORM_PCI) || \ + defined(CONFIG_XEN_PLATFORM_PCI_MODULE)) + return 1; +#else + return 0; +#endif +} + +static inline int xen_must_unplug_disks(void) { +#if (defined(CONFIG_XEN_BLKDEV_FRONTEND) || \ + defined(CONFIG_XEN_BLKDEV_FRONTEND_MODULE)) && \ + (defined(CONFIG_XEN_PLATFORM_PCI) || \ + defined(CONFIG_XEN_PLATFORM_PCI_MODULE)) + return 1; +#else + return 0; +#endif +} + +extern int xen_platform_pci_unplug; + +#endif /* _XEN_PLATFORM_PCI_H */ diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 883a21bba24..46bc81ef74c 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -7,6 +7,7 @@ DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); void xen_pre_suspend(void); void xen_post_suspend(int suspend_cancelled); +void xen_hvm_post_suspend(int suspend_cancelled); void xen_mm_pin_all(void); void xen_mm_unpin_all(void); @@ -14,4 +15,6 @@ void xen_mm_unpin_all(void); void xen_timer_resume(void); void xen_arch_resume(void); +int xen_setup_shutdown_event(void); + #endif /* INCLUDE_XEN_OPS_H */ diff --git a/init/main.c b/init/main.c index 4ddb53f04f2..b03a4c1f69f 100644 --- a/init/main.c +++ b/init/main.c @@ -66,11 +66,9 @@ #include <linux/ftrace.h> #include <linux/async.h> #include <linux/kmemcheck.h> -#include <linux/kmemtrace.h> #include <linux/sfi.h> #include <linux/shmem_fs.h> #include <linux/slab.h> -#include <trace/boot.h> #include <asm/io.h> #include <asm/bugs.h> @@ -664,7 +662,6 @@ asmlinkage void __init start_kernel(void) #endif page_cgroup_init(); enable_debug_pagealloc(); - kmemtrace_init(); kmemleak_init(); debug_objects_mem_init(); idr_init_cache(); @@ -726,38 +723,33 @@ int initcall_debug; core_param(initcall_debug, initcall_debug, bool, 0644); static char msgbuf[64]; -static struct boot_trace_call call; -static struct boot_trace_ret ret; int do_one_initcall(initcall_t fn) { int count = preempt_count(); ktime_t calltime, delta, rettime; + unsigned long long duration; + int ret; if (initcall_debug) { - call.caller = task_pid_nr(current); - printk("calling %pF @ %i\n", fn, call.caller); + printk("calling %pF @ %i\n", fn, task_pid_nr(current)); calltime = ktime_get(); - trace_boot_call(&call, fn); - enable_boot_trace(); } - ret.result = fn(); + ret = fn(); if (initcall_debug) { - disable_boot_trace(); rettime = ktime_get(); delta = ktime_sub(rettime, calltime); - ret.duration = (unsigned long long) ktime_to_ns(delta) >> 10; - trace_boot_ret(&ret, fn); - printk("initcall %pF returned %d after %Ld usecs\n", fn, - ret.result, ret.duration); + duration = (unsigned long long) ktime_to_ns(delta) >> 10; + printk("initcall %pF returned %d after %lld usecs\n", fn, + ret, duration); } msgbuf[0] = 0; - if (ret.result && ret.result != -ENODEV && initcall_debug) - sprintf(msgbuf, "error code %d ", ret.result); + if (ret && ret != -ENODEV && initcall_debug) + sprintf(msgbuf, "error code %d ", ret); if (preempt_count() != count) { strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf)); @@ -771,7 +763,7 @@ int do_one_initcall(initcall_t fn) printk("initcall %pF returned with %s\n", fn, msgbuf); } - return ret.result; + return ret; } @@ -895,7 +887,6 @@ static int __init kernel_init(void * unused) smp_prepare_cpus(setup_max_cpus); do_pre_smp_initcalls(); - start_boot_trace(); smp_init(); sched_init_smp(); diff --git a/kernel/Makefile b/kernel/Makefile index 057472fbc27..ce53fb2bd1d 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -76,8 +76,8 @@ obj-$(CONFIG_GCOV_KERNEL) += gcov/ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += debug/ -obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o +obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o diff --git a/kernel/cpu.c b/kernel/cpu.c index 97d1b426a4a..f6e726f1849 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -235,11 +235,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) return -EINVAL; cpu_hotplug_begin(); - set_cpu_active(cpu, false); err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); if (err) { - set_cpu_active(cpu, true); - nr_calls--; __cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL); printk("%s: attempt to take down CPU %u failed\n", @@ -249,7 +246,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { - set_cpu_active(cpu, true); /* CPU didn't die: tell everyone. Can't complain. */ cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); @@ -321,8 +317,6 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; BUG_ON(!cpu_online(cpu)); - set_cpu_active(cpu, true); - /* Now call notifier in preparation. */ cpu_notify(CPU_ONLINE | mod, hcpu); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 7cb37d86a00..b23c0979bbe 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2113,31 +2113,17 @@ static void scan_for_empty_cpusets(struct cpuset *root) * but making no active use of cpusets. * * This routine ensures that top_cpuset.cpus_allowed tracks - * cpu_online_map on each CPU hotplug (cpuhp) event. + * cpu_active_mask on each CPU hotplug (cpuhp) event. * * Called within get_online_cpus(). Needs to call cgroup_lock() * before calling generate_sched_domains(). */ -static int cpuset_track_online_cpus(struct notifier_block *unused_nb, - unsigned long phase, void *unused_cpu) +void cpuset_update_active_cpus(void) { struct sched_domain_attr *attr; cpumask_var_t *doms; int ndoms; - switch (phase) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - break; - - default: - return NOTIFY_DONE; - } - cgroup_lock(); mutex_lock(&callback_mutex); cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); @@ -2148,8 +2134,6 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, /* Have scheduler rebuild the domains */ partition_sched_domains(ndoms, doms, attr); - - return NOTIFY_OK; } #ifdef CONFIG_MEMORY_HOTPLUG @@ -2203,7 +2187,6 @@ void __init cpuset_init_smp(void) cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; - hotcpu_notifier(cpuset_track_online_cpus, 0); hotplug_memory_notifier(cpuset_track_online_nodes, 10); cpuset_wq = create_singlethread_workqueue("cpuset"); diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 51d14fe8764..3c2d4972d23 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -605,6 +605,8 @@ cpu_master_loop: if (dbg_kdb_mode) { kgdb_connected = 1; error = kdb_stub(ks); + if (error == -1) + continue; kgdb_connected = 0; } else { error = gdb_serial_stub(ks); diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index 6e81fd59566..481a7bd2dfe 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -52,17 +52,6 @@ static unsigned long gdb_regs[(NUMREGBYTES + * GDB remote protocol parser: */ -static int hex(char ch) -{ - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - if ((ch >= 'A') && (ch <= 'F')) - return ch - 'A' + 10; - return -1; -} - #ifdef CONFIG_KGDB_KDB static int gdbstub_read_wait(void) { @@ -123,8 +112,8 @@ static void get_packet(char *buffer) buffer[count] = 0; if (ch == '#') { - xmitcsum = hex(gdbstub_read_wait()) << 4; - xmitcsum += hex(gdbstub_read_wait()); + xmitcsum = hex_to_bin(gdbstub_read_wait()) << 4; + xmitcsum += hex_to_bin(gdbstub_read_wait()); if (checksum != xmitcsum) /* failed checksum */ @@ -236,7 +225,7 @@ void gdbstub_msg_write(const char *s, int len) * buf. Return a pointer to the last char put in buf (null). May * return an error. */ -int kgdb_mem2hex(char *mem, char *buf, int count) +char *kgdb_mem2hex(char *mem, char *buf, int count) { char *tmp; int err; @@ -248,17 +237,16 @@ int kgdb_mem2hex(char *mem, char *buf, int count) tmp = buf + count; err = probe_kernel_read(tmp, mem, count); - if (!err) { - while (count > 0) { - buf = pack_hex_byte(buf, *tmp); - tmp++; - count--; - } - - *buf = 0; + if (err) + return NULL; + while (count > 0) { + buf = pack_hex_byte(buf, *tmp); + tmp++; + count--; } + *buf = 0; - return err; + return buf; } /* @@ -280,8 +268,8 @@ int kgdb_hex2mem(char *buf, char *mem, int count) tmp_hex = tmp_raw - 1; while (tmp_hex >= buf) { tmp_raw--; - *tmp_raw = hex(*tmp_hex--); - *tmp_raw |= hex(*tmp_hex--) << 4; + *tmp_raw = hex_to_bin(*tmp_hex--); + *tmp_raw |= hex_to_bin(*tmp_hex--) << 4; } return probe_kernel_write(mem, tmp_raw, count); @@ -304,7 +292,7 @@ int kgdb_hex2long(char **ptr, unsigned long *long_val) (*ptr)++; } while (**ptr) { - hex_val = hex(**ptr); + hex_val = hex_to_bin(**ptr); if (hex_val < 0) break; @@ -339,6 +327,32 @@ static int kgdb_ebin2mem(char *buf, char *mem, int count) return probe_kernel_write(mem, c, size); } +#if DBG_MAX_REG_NUM > 0 +void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) +{ + int i; + int idx = 0; + char *ptr = (char *)gdb_regs; + + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + dbg_get_reg(i, ptr + idx, regs); + idx += dbg_reg_def[i].size; + } +} + +void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) +{ + int i; + int idx = 0; + char *ptr = (char *)gdb_regs; + + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + dbg_set_reg(i, ptr + idx, regs); + idx += dbg_reg_def[i].size; + } +} +#endif /* DBG_MAX_REG_NUM > 0 */ + /* Write memory due to an 'M' or 'X' packet. */ static int write_mem_msg(int binary) { @@ -378,28 +392,31 @@ static void error_packet(char *pkt, int error) * remapped to negative TIDs. */ -#define BUF_THREAD_ID_SIZE 16 +#define BUF_THREAD_ID_SIZE 8 static char *pack_threadid(char *pkt, unsigned char *id) { - char *limit; + unsigned char *limit; + int lzero = 1; + + limit = id + (BUF_THREAD_ID_SIZE / 2); + while (id < limit) { + if (!lzero || *id != 0) { + pkt = pack_hex_byte(pkt, *id); + lzero = 0; + } + id++; + } - limit = pkt + BUF_THREAD_ID_SIZE; - while (pkt < limit) - pkt = pack_hex_byte(pkt, *id++); + if (lzero) + pkt = pack_hex_byte(pkt, 0); return pkt; } static void int_to_threadref(unsigned char *id, int value) { - unsigned char *scan; - int i = 4; - - scan = (unsigned char *)id; - while (i--) - *scan++ = 0; - put_unaligned_be32(value, scan); + put_unaligned_be32(value, id); } static struct task_struct *getthread(struct pt_regs *regs, int tid) @@ -463,8 +480,7 @@ static void gdb_cmd_status(struct kgdb_state *ks) pack_hex_byte(&remcom_out_buffer[1], ks->signo); } -/* Handle the 'g' get registers request */ -static void gdb_cmd_getregs(struct kgdb_state *ks) +static void gdb_get_regs_helper(struct kgdb_state *ks) { struct task_struct *thread; void *local_debuggerinfo; @@ -505,6 +521,12 @@ static void gdb_cmd_getregs(struct kgdb_state *ks) */ sleeping_thread_to_gdb_regs(gdb_regs, thread); } +} + +/* Handle the 'g' get registers request */ +static void gdb_cmd_getregs(struct kgdb_state *ks) +{ + gdb_get_regs_helper(ks); kgdb_mem2hex((char *)gdb_regs, remcom_out_buffer, NUMREGBYTES); } @@ -527,13 +549,13 @@ static void gdb_cmd_memread(struct kgdb_state *ks) char *ptr = &remcom_in_buffer[1]; unsigned long length; unsigned long addr; - int err; + char *err; if (kgdb_hex2long(&ptr, &addr) > 0 && *ptr++ == ',' && kgdb_hex2long(&ptr, &length) > 0) { err = kgdb_mem2hex((char *)addr, remcom_out_buffer, length); - if (err) - error_packet(remcom_out_buffer, err); + if (!err) + error_packet(remcom_out_buffer, -EINVAL); } else { error_packet(remcom_out_buffer, -EINVAL); } @@ -550,6 +572,60 @@ static void gdb_cmd_memwrite(struct kgdb_state *ks) strcpy(remcom_out_buffer, "OK"); } +#if DBG_MAX_REG_NUM > 0 +static char *gdb_hex_reg_helper(int regnum, char *out) +{ + int i; + int offset = 0; + + for (i = 0; i < regnum; i++) + offset += dbg_reg_def[i].size; + return kgdb_mem2hex((char *)gdb_regs + offset, out, + dbg_reg_def[i].size); +} + +/* Handle the 'p' individual regster get */ +static void gdb_cmd_reg_get(struct kgdb_state *ks) +{ + unsigned long regnum; + char *ptr = &remcom_in_buffer[1]; + + kgdb_hex2long(&ptr, ®num); + if (regnum >= DBG_MAX_REG_NUM) { + error_packet(remcom_out_buffer, -EINVAL); + return; + } + gdb_get_regs_helper(ks); + gdb_hex_reg_helper(regnum, remcom_out_buffer); +} + +/* Handle the 'P' individual regster set */ +static void gdb_cmd_reg_set(struct kgdb_state *ks) +{ + unsigned long regnum; + char *ptr = &remcom_in_buffer[1]; + int i = 0; + + kgdb_hex2long(&ptr, ®num); + if (*ptr++ != '=' || + !(!kgdb_usethread || kgdb_usethread == current) || + !dbg_get_reg(regnum, gdb_regs, ks->linux_regs)) { + error_packet(remcom_out_buffer, -EINVAL); + return; + } + memset(gdb_regs, 0, sizeof(gdb_regs)); + while (i < sizeof(gdb_regs) * 2) + if (hex_to_bin(ptr[i]) >= 0) + i++; + else + break; + i = i / 2; + kgdb_hex2mem(ptr, (char *)gdb_regs, i); + dbg_set_reg(regnum, gdb_regs, ks->linux_regs); + strcpy(remcom_out_buffer, "OK"); +} +#endif /* DBG_MAX_REG_NUM > 0 */ + /* Handle the 'X' memory binary write bytes */ static void gdb_cmd_binwrite(struct kgdb_state *ks) { @@ -612,7 +688,7 @@ static void gdb_cmd_query(struct kgdb_state *ks) { struct task_struct *g; struct task_struct *p; - unsigned char thref[8]; + unsigned char thref[BUF_THREAD_ID_SIZE]; char *ptr; int i; int cpu; @@ -632,8 +708,7 @@ static void gdb_cmd_query(struct kgdb_state *ks) for_each_online_cpu(cpu) { ks->thr_query = 0; int_to_threadref(thref, -cpu - 2); - pack_threadid(ptr, thref); - ptr += BUF_THREAD_ID_SIZE; + ptr = pack_threadid(ptr, thref); *(ptr++) = ','; i++; } @@ -642,8 +717,7 @@ static void gdb_cmd_query(struct kgdb_state *ks) do_each_thread(g, p) { if (i >= ks->thr_query && !finished) { int_to_threadref(thref, p->pid); - pack_threadid(ptr, thref); - ptr += BUF_THREAD_ID_SIZE; + ptr = pack_threadid(ptr, thref); *(ptr++) = ','; ks->thr_query++; if (ks->thr_query % KGDB_MAX_THREAD_QUERY == 0) @@ -858,11 +932,14 @@ int gdb_serial_stub(struct kgdb_state *ks) int error = 0; int tmp; - /* Clear the out buffer. */ + /* Initialize comm buffer and globals. */ memset(remcom_out_buffer, 0, sizeof(remcom_out_buffer)); + kgdb_usethread = kgdb_info[ks->cpu].task; + ks->kgdb_usethreadid = shadow_pid(kgdb_info[ks->cpu].task->pid); + ks->pass_exception = 0; if (kgdb_connected) { - unsigned char thref[8]; + unsigned char thref[BUF_THREAD_ID_SIZE]; char *ptr; /* Reply to host that an exception has occurred */ @@ -876,10 +953,6 @@ int gdb_serial_stub(struct kgdb_state *ks) put_packet(remcom_out_buffer); } - kgdb_usethread = kgdb_info[ks->cpu].task; - ks->kgdb_usethreadid = shadow_pid(kgdb_info[ks->cpu].task->pid); - ks->pass_exception = 0; - while (1) { error = 0; @@ -904,6 +977,14 @@ int gdb_serial_stub(struct kgdb_state *ks) case 'M': /* MAA..AA,LLLL: Write LLLL bytes at address AA..AA */ gdb_cmd_memwrite(ks); break; +#if DBG_MAX_REG_NUM > 0 + case 'p': /* pXX Return gdb register XX (in hex) */ + gdb_cmd_reg_get(ks); + break; + case 'P': /* PXX=aaaa Set gdb register XX to aaaa (in hex) */ + gdb_cmd_reg_set(ks); + break; +#endif /* DBG_MAX_REG_NUM > 0 */ case 'X': /* XAA..AA,LLLL: Write LLLL bytes at address AA..AA */ gdb_cmd_binwrite(ks); break; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index ebe4a287419..8577e45a9a5 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -312,7 +312,7 @@ int kdbgetularg(const char *arg, unsigned long *value) if (endp == arg) { /* - * Try base 16, for us folks too lazy to type the + * Also try base 16, for us folks too lazy to type the * leading 0x... */ val = simple_strtoul(arg, &endp, 16); @@ -325,6 +325,25 @@ int kdbgetularg(const char *arg, unsigned long *value) return 0; } +int kdbgetu64arg(const char *arg, u64 *value) +{ + char *endp; + u64 val; + + val = simple_strtoull(arg, &endp, 0); + + if (endp == arg) { + + val = simple_strtoull(arg, &endp, 16); + if (endp == arg) + return KDB_BADINT; + } + + *value = val; + + return 0; +} + /* * kdb_set - This function implements the 'set' command. Alter an * existing environment variable or create a new one. @@ -1770,11 +1789,65 @@ static int kdb_go(int argc, const char **argv) */ static int kdb_rd(int argc, const char **argv) { - int diag = kdb_check_regs(); - if (diag) - return diag; + int len = kdb_check_regs(); +#if DBG_MAX_REG_NUM > 0 + int i; + char *rname; + int rsize; + u64 reg64; + u32 reg32; + u16 reg16; + u8 reg8; + + if (len) + return len; + + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + rsize = dbg_reg_def[i].size * 2; + if (rsize > 16) + rsize = 2; + if (len + strlen(dbg_reg_def[i].name) + 4 + rsize > 80) { + len = 0; + kdb_printf("\n"); + } + if (len) + len += kdb_printf(" "); + switch(dbg_reg_def[i].size * 8) { + case 8: + rname = dbg_get_reg(i, ®8, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %02x", rname, reg8); + break; + case 16: + rname = dbg_get_reg(i, ®16, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %04x", rname, reg16); + break; + case 32: + rname = dbg_get_reg(i, ®32, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %08x", rname, reg32); + break; + case 64: + rname = dbg_get_reg(i, ®64, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %016llx", rname, reg64); + break; + default: + len += kdb_printf("%s: ??", dbg_reg_def[i].name); + } + } + kdb_printf("\n"); +#else + if (len) + return len; kdb_dumpregs(kdb_current_regs); +#endif return 0; } @@ -1782,32 +1855,67 @@ static int kdb_rd(int argc, const char **argv) * kdb_rm - This function implements the 'rm' (register modify) command. * rm register-name new-contents * Remarks: - * Currently doesn't allow modification of control or - * debug registers. + * Allows register modification with the same restrictions as gdb */ static int kdb_rm(int argc, const char **argv) { +#if DBG_MAX_REG_NUM > 0 int diag; - int ind = 0; - unsigned long contents; + const char *rname; + int i; + u64 reg64; + u32 reg32; + u16 reg16; + u8 reg8; if (argc != 2) return KDB_ARGCOUNT; /* * Allow presence or absence of leading '%' symbol. */ - if (argv[1][0] == '%') - ind = 1; + rname = argv[1]; + if (*rname == '%') + rname++; - diag = kdbgetularg(argv[2], &contents); + diag = kdbgetu64arg(argv[2], ®64); if (diag) return diag; diag = kdb_check_regs(); if (diag) return diag; + + diag = KDB_BADREG; + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + if (strcmp(rname, dbg_reg_def[i].name) == 0) { + diag = 0; + break; + } + } + if (!diag) { + switch(dbg_reg_def[i].size * 8) { + case 8: + reg8 = reg64; + dbg_set_reg(i, ®8, kdb_current_regs); + break; + case 16: + reg16 = reg64; + dbg_set_reg(i, ®16, kdb_current_regs); + break; + case 32: + reg32 = reg64; + dbg_set_reg(i, ®32, kdb_current_regs); + break; + case 64: + dbg_set_reg(i, ®64, kdb_current_regs); + break; + } + } + return diag; +#else kdb_printf("ERROR: Register set currently not implemented\n"); - return 0; + return 0; +#endif } #if defined(CONFIG_MAGIC_SYSRQ) diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 97d3ba69775..c438f545a32 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -144,9 +144,7 @@ extern int kdb_getword(unsigned long *, unsigned long, size_t); extern int kdb_putword(unsigned long, unsigned long, size_t); extern int kdbgetularg(const char *, unsigned long *); -extern int kdb_set(int, const char **); extern char *kdbgetenv(const char *); -extern int kdbgetintenv(const char *, int *); extern int kdbgetaddrarg(int, const char **, int*, unsigned long *, long *, char **); extern int kdbgetsymval(const char *, kdb_symtab_t *); diff --git a/kernel/fork.c b/kernel/fork.c index b6cce14ba04..a82a65cef74 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -907,7 +907,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p) { unsigned long new_flags = p->flags; - new_flags &= ~PF_SUPERPRIV; + new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); new_flags |= PF_FORKNOEXEC; new_flags |= PF_STARTING; p->flags = new_flags; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 5c69e996bd0..e934339fbbe 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -144,12 +144,8 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, static int hrtimer_get_target(int this_cpu, int pinned) { #ifdef CONFIG_NO_HZ - if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) { - int preferred_cpu = get_nohz_load_balancer(); - - if (preferred_cpu >= 0) - return preferred_cpu; - } + if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) + return get_nohz_timer_target(); #endif return this_cpu; } diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index 71ed3ce29e1..d71a987fd2b 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -41,6 +41,7 @@ #include <linux/sched.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/list.h> #include <linux/cpu.h> #include <linux/smp.h> @@ -62,6 +63,9 @@ static DEFINE_PER_CPU(unsigned int, nr_bp_flexible[TYPE_MAX]); static int nr_slots[TYPE_MAX]; +/* Keep track of the breakpoints attached to tasks */ +static LIST_HEAD(bp_task_head); + static int constraints_initialized; /* Gather the number of total pinned and un-pinned bp in a cpuset */ @@ -103,33 +107,21 @@ static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type) return 0; } -static int task_bp_pinned(struct task_struct *tsk, enum bp_type_idx type) +/* + * Count the number of breakpoints of the same type and same task. + * The given event must be not on the list. + */ +static int task_bp_pinned(struct perf_event *bp, enum bp_type_idx type) { - struct perf_event_context *ctx = tsk->perf_event_ctxp; - struct list_head *list; - struct perf_event *bp; - unsigned long flags; + struct perf_event_context *ctx = bp->ctx; + struct perf_event *iter; int count = 0; - if (WARN_ONCE(!ctx, "No perf context for this task")) - return 0; - - list = &ctx->event_list; - - raw_spin_lock_irqsave(&ctx->lock, flags); - - /* - * The current breakpoint counter is not included in the list - * at the open() callback time - */ - list_for_each_entry(bp, list, event_entry) { - if (bp->attr.type == PERF_TYPE_BREAKPOINT) - if (find_slot_idx(bp) == type) - count += hw_breakpoint_weight(bp); + list_for_each_entry(iter, &bp_task_head, hw.bp_list) { + if (iter->ctx == ctx && find_slot_idx(iter) == type) + count += hw_breakpoint_weight(iter); } - raw_spin_unlock_irqrestore(&ctx->lock, flags); - return count; } @@ -149,7 +141,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp, if (!tsk) slots->pinned += max_task_bp_pinned(cpu, type); else - slots->pinned += task_bp_pinned(tsk, type); + slots->pinned += task_bp_pinned(bp, type); slots->flexible = per_cpu(nr_bp_flexible[type], cpu); return; @@ -162,7 +154,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp, if (!tsk) nr += max_task_bp_pinned(cpu, type); else - nr += task_bp_pinned(tsk, type); + nr += task_bp_pinned(bp, type); if (nr > slots->pinned) slots->pinned = nr; @@ -188,7 +180,7 @@ fetch_this_slot(struct bp_busy_slots *slots, int weight) /* * Add a pinned breakpoint for the given task in our constraint table */ -static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable, +static void toggle_bp_task_slot(struct perf_event *bp, int cpu, bool enable, enum bp_type_idx type, int weight) { unsigned int *tsk_pinned; @@ -196,10 +188,11 @@ static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable, int old_idx = 0; int idx = 0; - old_count = task_bp_pinned(tsk, type); + old_count = task_bp_pinned(bp, type); old_idx = old_count - 1; idx = old_idx + weight; + /* tsk_pinned[n] is the number of tasks having n breakpoints */ tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu); if (enable) { tsk_pinned[idx]++; @@ -222,23 +215,30 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, int cpu = bp->cpu; struct task_struct *tsk = bp->ctx->task; + /* Pinned counter cpu profiling */ + if (!tsk) { + + if (enable) + per_cpu(nr_cpu_bp_pinned[type], bp->cpu) += weight; + else + per_cpu(nr_cpu_bp_pinned[type], bp->cpu) -= weight; + return; + } + /* Pinned counter task profiling */ - if (tsk) { - if (cpu >= 0) { - toggle_bp_task_slot(tsk, cpu, enable, type, weight); - return; - } + if (!enable) + list_del(&bp->hw.bp_list); + + if (cpu >= 0) { + toggle_bp_task_slot(bp, cpu, enable, type, weight); + } else { for_each_online_cpu(cpu) - toggle_bp_task_slot(tsk, cpu, enable, type, weight); - return; + toggle_bp_task_slot(bp, cpu, enable, type, weight); } - /* Pinned counter cpu profiling */ if (enable) - per_cpu(nr_cpu_bp_pinned[type], bp->cpu) += weight; - else - per_cpu(nr_cpu_bp_pinned[type], bp->cpu) -= weight; + list_add_tail(&bp->hw.bp_list, &bp_task_head); } /* @@ -312,6 +312,10 @@ static int __reserve_bp_slot(struct perf_event *bp) weight = hw_breakpoint_weight(bp); fetch_bp_busy_slots(&slots, bp, type); + /* + * Simulate the addition of this breakpoint to the constraints + * and see the result. + */ fetch_this_slot(&slots, weight); /* Flexible counters need to keep at least one slot */ diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 54286798c37..f2852a51023 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -146,7 +146,7 @@ static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], static inline u64 lockstat_clock(void) { - return cpu_clock(smp_processor_id()); + return local_clock(); } static int lock_point(unsigned long points[], unsigned long ip) diff --git a/kernel/module.c b/kernel/module.c index 6c562828c85..d0b5f8db11b 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1,6 +1,6 @@ /* Copyright (C) 2002 Richard Henderson - Copyright (C) 2001 Rusty Russell, 2002 Rusty Russell IBM. + Copyright (C) 2001 Rusty Russell, 2002, 2010 Rusty Russell IBM. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -110,6 +110,20 @@ int unregister_module_notifier(struct notifier_block * nb) } EXPORT_SYMBOL(unregister_module_notifier); +struct load_info { + Elf_Ehdr *hdr; + unsigned long len; + Elf_Shdr *sechdrs; + char *secstrings, *strtab; + unsigned long *strmap; + unsigned long symoffs, stroffs; + struct _ddebug *debug; + unsigned int num_debug; + struct { + unsigned int sym, str, mod, vers, info, pcpu; + } index; +}; + /* We require a truly strong try_module_get(): 0 means failure due to ongoing or failed initialization etc. */ static inline int strong_try_module_get(struct module *mod) @@ -140,42 +154,38 @@ void __module_put_and_exit(struct module *mod, long code) EXPORT_SYMBOL(__module_put_and_exit); /* Find a module section: 0 means not found. */ -static unsigned int find_sec(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings, - const char *name) +static unsigned int find_sec(const struct load_info *info, const char *name) { unsigned int i; - for (i = 1; i < hdr->e_shnum; i++) + for (i = 1; i < info->hdr->e_shnum; i++) { + Elf_Shdr *shdr = &info->sechdrs[i]; /* Alloc bit cleared means "ignore it." */ - if ((sechdrs[i].sh_flags & SHF_ALLOC) - && strcmp(secstrings+sechdrs[i].sh_name, name) == 0) + if ((shdr->sh_flags & SHF_ALLOC) + && strcmp(info->secstrings + shdr->sh_name, name) == 0) return i; + } return 0; } /* Find a module section, or NULL. */ -static void *section_addr(Elf_Ehdr *hdr, Elf_Shdr *shdrs, - const char *secstrings, const char *name) +static void *section_addr(const struct load_info *info, const char *name) { /* Section 0 has sh_addr 0. */ - return (void *)shdrs[find_sec(hdr, shdrs, secstrings, name)].sh_addr; + return (void *)info->sechdrs[find_sec(info, name)].sh_addr; } /* Find a module section, or NULL. Fill in number of "objects" in section. */ -static void *section_objs(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings, +static void *section_objs(const struct load_info *info, const char *name, size_t object_size, unsigned int *num) { - unsigned int sec = find_sec(hdr, sechdrs, secstrings, name); + unsigned int sec = find_sec(info, name); /* Section 0 has sh_addr 0 and sh_size 0. */ - *num = sechdrs[sec].sh_size / object_size; - return (void *)sechdrs[sec].sh_addr; + *num = info->sechdrs[sec].sh_size / object_size; + return (void *)info->sechdrs[sec].sh_addr; } /* Provided by the linker */ @@ -227,7 +237,7 @@ bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, unsigned int symnum, void *data), void *data) { struct module *mod; - const struct symsearch arr[] = { + static const struct symsearch arr[] = { { __start___ksymtab, __stop___ksymtab, __start___kcrctab, NOT_GPL_ONLY, false }, { __start___ksymtab_gpl, __stop___ksymtab_gpl, @@ -392,7 +402,8 @@ static int percpu_modalloc(struct module *mod, mod->percpu = __alloc_reserved_percpu(size, align); if (!mod->percpu) { printk(KERN_WARNING - "Could not allocate %lu bytes percpu data\n", size); + "%s: Could not allocate %lu bytes percpu data\n", + mod->name, size); return -ENOMEM; } mod->percpu_size = size; @@ -404,11 +415,9 @@ static void percpu_modfree(struct module *mod) free_percpu(mod->percpu); } -static unsigned int find_pcpusec(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings) +static unsigned int find_pcpusec(struct load_info *info) { - return find_sec(hdr, sechdrs, secstrings, ".data..percpu"); + return find_sec(info, ".data..percpu"); } static void percpu_modcopy(struct module *mod, @@ -468,9 +477,7 @@ static inline int percpu_modalloc(struct module *mod, static inline void percpu_modfree(struct module *mod) { } -static inline unsigned int find_pcpusec(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings) +static unsigned int find_pcpusec(struct load_info *info) { return 0; } @@ -524,21 +531,21 @@ static char last_unloaded_module[MODULE_NAME_LEN+1]; EXPORT_TRACEPOINT_SYMBOL(module_get); /* Init the unload section of the module. */ -static void module_unload_init(struct module *mod) +static int module_unload_init(struct module *mod) { - int cpu; + mod->refptr = alloc_percpu(struct module_ref); + if (!mod->refptr) + return -ENOMEM; INIT_LIST_HEAD(&mod->source_list); INIT_LIST_HEAD(&mod->target_list); - for_each_possible_cpu(cpu) { - per_cpu_ptr(mod->refptr, cpu)->incs = 0; - per_cpu_ptr(mod->refptr, cpu)->decs = 0; - } /* Hold reference count during initialization. */ __this_cpu_write(mod->refptr->incs, 1); /* Backwards compatibility macros put refcount during init. */ mod->waiter = current; + + return 0; } /* Does a already use b? */ @@ -618,6 +625,8 @@ static void module_unload_free(struct module *mod) kfree(use); } mutex_unlock(&module_mutex); + + free_percpu(mod->refptr); } #ifdef CONFIG_MODULE_FORCE_UNLOAD @@ -891,8 +900,9 @@ int ref_module(struct module *a, struct module *b) } EXPORT_SYMBOL_GPL(ref_module); -static inline void module_unload_init(struct module *mod) +static inline int module_unload_init(struct module *mod) { + return 0; } #endif /* CONFIG_MODULE_UNLOAD */ @@ -1051,10 +1061,9 @@ static inline int same_magic(const char *amagic, const char *bmagic, #endif /* CONFIG_MODVERSIONS */ /* Resolve a symbol for this module. I.e. if we find one, record usage. */ -static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, - unsigned int versindex, +static const struct kernel_symbol *resolve_symbol(struct module *mod, + const struct load_info *info, const char *name, - struct module *mod, char ownername[]) { struct module *owner; @@ -1068,7 +1077,8 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, if (!sym) goto unlock; - if (!check_version(sechdrs, versindex, name, mod, crc, owner)) { + if (!check_version(info->sechdrs, info->index.vers, name, mod, crc, + owner)) { sym = ERR_PTR(-EINVAL); goto getname; } @@ -1087,21 +1097,20 @@ unlock: return sym; } -static const struct kernel_symbol *resolve_symbol_wait(Elf_Shdr *sechdrs, - unsigned int versindex, - const char *name, - struct module *mod) +static const struct kernel_symbol * +resolve_symbol_wait(struct module *mod, + const struct load_info *info, + const char *name) { const struct kernel_symbol *ksym; - char ownername[MODULE_NAME_LEN]; + char owner[MODULE_NAME_LEN]; if (wait_event_interruptible_timeout(module_wq, - !IS_ERR(ksym = resolve_symbol(sechdrs, versindex, name, - mod, ownername)) || - PTR_ERR(ksym) != -EBUSY, + !IS_ERR(ksym = resolve_symbol(mod, info, name, owner)) + || PTR_ERR(ksym) != -EBUSY, 30 * HZ) <= 0) { printk(KERN_WARNING "%s: gave up waiting for init of module %s.\n", - mod->name, ownername); + mod->name, owner); } return ksym; } @@ -1110,8 +1119,9 @@ static const struct kernel_symbol *resolve_symbol_wait(Elf_Shdr *sechdrs, * /sys/module/foo/sections stuff * J. Corbet <corbet@lwn.net> */ -#if defined(CONFIG_KALLSYMS) && defined(CONFIG_SYSFS) +#ifdef CONFIG_SYSFS +#ifdef CONFIG_KALLSYMS static inline bool sect_empty(const Elf_Shdr *sect) { return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0; @@ -1148,8 +1158,7 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs) kfree(sect_attrs); } -static void add_sect_attrs(struct module *mod, unsigned int nsect, - char *secstrings, Elf_Shdr *sechdrs) +static void add_sect_attrs(struct module *mod, const struct load_info *info) { unsigned int nloaded = 0, i, size[2]; struct module_sect_attrs *sect_attrs; @@ -1157,8 +1166,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, struct attribute **gattr; /* Count loaded sections and allocate structures */ - for (i = 0; i < nsect; i++) - if (!sect_empty(&sechdrs[i])) + for (i = 0; i < info->hdr->e_shnum; i++) + if (!sect_empty(&info->sechdrs[i])) nloaded++; size[0] = ALIGN(sizeof(*sect_attrs) + nloaded * sizeof(sect_attrs->attrs[0]), @@ -1175,11 +1184,12 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, sect_attrs->nsections = 0; sattr = §_attrs->attrs[0]; gattr = §_attrs->grp.attrs[0]; - for (i = 0; i < nsect; i++) { - if (sect_empty(&sechdrs[i])) + for (i = 0; i < info->hdr->e_shnum; i++) { + Elf_Shdr *sec = &info->sechdrs[i]; + if (sect_empty(sec)) continue; - sattr->address = sechdrs[i].sh_addr; - sattr->name = kstrdup(secstrings + sechdrs[i].sh_name, + sattr->address = sec->sh_addr; + sattr->name = kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL); if (sattr->name == NULL) goto out; @@ -1247,8 +1257,7 @@ static void free_notes_attrs(struct module_notes_attrs *notes_attrs, kfree(notes_attrs); } -static void add_notes_attrs(struct module *mod, unsigned int nsect, - char *secstrings, Elf_Shdr *sechdrs) +static void add_notes_attrs(struct module *mod, const struct load_info *info) { unsigned int notes, loaded, i; struct module_notes_attrs *notes_attrs; @@ -1260,9 +1269,9 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, /* Count notes sections and allocate structures. */ notes = 0; - for (i = 0; i < nsect; i++) - if (!sect_empty(&sechdrs[i]) && - (sechdrs[i].sh_type == SHT_NOTE)) + for (i = 0; i < info->hdr->e_shnum; i++) + if (!sect_empty(&info->sechdrs[i]) && + (info->sechdrs[i].sh_type == SHT_NOTE)) ++notes; if (notes == 0) @@ -1276,15 +1285,15 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, notes_attrs->notes = notes; nattr = ¬es_attrs->attrs[0]; - for (loaded = i = 0; i < nsect; ++i) { - if (sect_empty(&sechdrs[i])) + for (loaded = i = 0; i < info->hdr->e_shnum; ++i) { + if (sect_empty(&info->sechdrs[i])) continue; - if (sechdrs[i].sh_type == SHT_NOTE) { + if (info->sechdrs[i].sh_type == SHT_NOTE) { sysfs_bin_attr_init(nattr); nattr->attr.name = mod->sect_attrs->attrs[loaded].name; nattr->attr.mode = S_IRUGO; - nattr->size = sechdrs[i].sh_size; - nattr->private = (void *) sechdrs[i].sh_addr; + nattr->size = info->sechdrs[i].sh_size; + nattr->private = (void *) info->sechdrs[i].sh_addr; nattr->read = module_notes_read; ++nattr; } @@ -1315,8 +1324,8 @@ static void remove_notes_attrs(struct module *mod) #else -static inline void add_sect_attrs(struct module *mod, unsigned int nsect, - char *sectstrings, Elf_Shdr *sechdrs) +static inline void add_sect_attrs(struct module *mod, + const struct load_info *info) { } @@ -1324,17 +1333,16 @@ static inline void remove_sect_attrs(struct module *mod) { } -static inline void add_notes_attrs(struct module *mod, unsigned int nsect, - char *sectstrings, Elf_Shdr *sechdrs) +static inline void add_notes_attrs(struct module *mod, + const struct load_info *info) { } static inline void remove_notes_attrs(struct module *mod) { } -#endif +#endif /* CONFIG_KALLSYMS */ -#ifdef CONFIG_SYSFS static void add_usage_links(struct module *mod) { #ifdef CONFIG_MODULE_UNLOAD @@ -1439,6 +1447,7 @@ out: } static int mod_sysfs_setup(struct module *mod, + const struct load_info *info, struct kernel_param *kparam, unsigned int num_params) { @@ -1463,6 +1472,8 @@ static int mod_sysfs_setup(struct module *mod, goto out_unreg_param; add_usage_links(mod); + add_sect_attrs(mod, info); + add_notes_attrs(mod, info); kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD); return 0; @@ -1479,33 +1490,26 @@ out: static void mod_sysfs_fini(struct module *mod) { + remove_notes_attrs(mod); + remove_sect_attrs(mod); kobject_put(&mod->mkobj.kobj); } -#else /* CONFIG_SYSFS */ - -static inline int mod_sysfs_init(struct module *mod) -{ - return 0; -} +#else /* !CONFIG_SYSFS */ -static inline int mod_sysfs_setup(struct module *mod, +static int mod_sysfs_setup(struct module *mod, + const struct load_info *info, struct kernel_param *kparam, unsigned int num_params) { return 0; } -static inline int module_add_modinfo_attrs(struct module *mod) -{ - return 0; -} - -static inline void module_remove_modinfo_attrs(struct module *mod) +static void mod_sysfs_fini(struct module *mod) { } -static void mod_sysfs_fini(struct module *mod) +static void module_remove_modinfo_attrs(struct module *mod) { } @@ -1515,7 +1519,7 @@ static void del_usage_links(struct module *mod) #endif /* CONFIG_SYSFS */ -static void mod_kobject_remove(struct module *mod) +static void mod_sysfs_teardown(struct module *mod) { del_usage_links(mod); module_remove_modinfo_attrs(mod); @@ -1545,9 +1549,7 @@ static void free_module(struct module *mod) mutex_lock(&module_mutex); stop_machine(__unlink_module, mod, NULL); mutex_unlock(&module_mutex); - remove_notes_attrs(mod); - remove_sect_attrs(mod); - mod_kobject_remove(mod); + mod_sysfs_teardown(mod); /* Remove dynamic debug info */ ddebug_remove_module(mod->name); @@ -1565,10 +1567,7 @@ static void free_module(struct module *mod) module_free(mod, mod->module_init); kfree(mod->args); percpu_modfree(mod); -#if defined(CONFIG_MODULE_UNLOAD) - if (mod->refptr) - free_percpu(mod->refptr); -#endif + /* Free lock-classes: */ lockdep_free_key_range(mod->module_core, mod->core_size); @@ -1634,25 +1633,23 @@ static int verify_export_symbols(struct module *mod) } /* Change all symbols so that st_value encodes the pointer directly. */ -static int simplify_symbols(Elf_Shdr *sechdrs, - unsigned int symindex, - const char *strtab, - unsigned int versindex, - unsigned int pcpuindex, - struct module *mod) -{ - Elf_Sym *sym = (void *)sechdrs[symindex].sh_addr; +static int simplify_symbols(struct module *mod, const struct load_info *info) +{ + Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; + Elf_Sym *sym = (void *)symsec->sh_addr; unsigned long secbase; - unsigned int i, n = sechdrs[symindex].sh_size / sizeof(Elf_Sym); + unsigned int i; int ret = 0; const struct kernel_symbol *ksym; - for (i = 1; i < n; i++) { + for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) { + const char *name = info->strtab + sym[i].st_name; + switch (sym[i].st_shndx) { case SHN_COMMON: /* We compiled with -fno-common. These are not supposed to happen. */ - DEBUGP("Common symbol: %s\n", strtab + sym[i].st_name); + DEBUGP("Common symbol: %s\n", name); printk("%s: please compile with -fno-common\n", mod->name); ret = -ENOEXEC; @@ -1665,9 +1662,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs, break; case SHN_UNDEF: - ksym = resolve_symbol_wait(sechdrs, versindex, - strtab + sym[i].st_name, - mod); + ksym = resolve_symbol_wait(mod, info, name); /* Ok if resolved. */ if (ksym && !IS_ERR(ksym)) { sym[i].st_value = ksym->value; @@ -1679,17 +1674,16 @@ static int simplify_symbols(Elf_Shdr *sechdrs, break; printk(KERN_WARNING "%s: Unknown symbol %s (err %li)\n", - mod->name, strtab + sym[i].st_name, - PTR_ERR(ksym)); + mod->name, name, PTR_ERR(ksym)); ret = PTR_ERR(ksym) ?: -ENOENT; break; default: /* Divert to percpu allocation if a percpu var. */ - if (sym[i].st_shndx == pcpuindex) + if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); else - secbase = sechdrs[sym[i].st_shndx].sh_addr; + secbase = info->sechdrs[sym[i].st_shndx].sh_addr; sym[i].st_value += secbase; break; } @@ -1698,6 +1692,35 @@ static int simplify_symbols(Elf_Shdr *sechdrs, return ret; } +static int apply_relocations(struct module *mod, const struct load_info *info) +{ + unsigned int i; + int err = 0; + + /* Now do relocations. */ + for (i = 1; i < info->hdr->e_shnum; i++) { + unsigned int infosec = info->sechdrs[i].sh_info; + + /* Not a valid relocation section? */ + if (infosec >= info->hdr->e_shnum) + continue; + + /* Don't bother with non-allocated sections */ + if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC)) + continue; + + if (info->sechdrs[i].sh_type == SHT_REL) + err = apply_relocate(info->sechdrs, info->strtab, + info->index.sym, i, mod); + else if (info->sechdrs[i].sh_type == SHT_RELA) + err = apply_relocate_add(info->sechdrs, info->strtab, + info->index.sym, i, mod); + if (err < 0) + break; + } + return err; +} + /* Additional bytes needed by arch in front of individual sections */ unsigned int __weak arch_mod_section_prepend(struct module *mod, unsigned int section) @@ -1722,10 +1745,7 @@ static long get_offset(struct module *mod, unsigned int *size, might -- code, read-only data, read-write data, small data. Tally sizes, and place the offsets into sh_entsize fields: high bit means it belongs in init. */ -static void layout_sections(struct module *mod, - const Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings) +static void layout_sections(struct module *mod, struct load_info *info) { static unsigned long const masks[][2] = { /* NOTE: all executable code must be the first section @@ -1738,21 +1758,22 @@ static void layout_sections(struct module *mod, }; unsigned int m, i; - for (i = 0; i < hdr->e_shnum; i++) - sechdrs[i].sh_entsize = ~0UL; + for (i = 0; i < info->hdr->e_shnum; i++) + info->sechdrs[i].sh_entsize = ~0UL; DEBUGP("Core section allocation order:\n"); for (m = 0; m < ARRAY_SIZE(masks); ++m) { - for (i = 0; i < hdr->e_shnum; ++i) { - Elf_Shdr *s = &sechdrs[i]; + for (i = 0; i < info->hdr->e_shnum; ++i) { + Elf_Shdr *s = &info->sechdrs[i]; + const char *sname = info->secstrings + s->sh_name; if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || strstarts(secstrings + s->sh_name, ".init")) + || strstarts(sname, ".init")) continue; s->sh_entsize = get_offset(mod, &mod->core_size, s, i); - DEBUGP("\t%s\n", secstrings + s->sh_name); + DEBUGP("\t%s\n", name); } if (m == 0) mod->core_text_size = mod->core_size; @@ -1760,17 +1781,18 @@ static void layout_sections(struct module *mod, DEBUGP("Init section allocation order:\n"); for (m = 0; m < ARRAY_SIZE(masks); ++m) { - for (i = 0; i < hdr->e_shnum; ++i) { - Elf_Shdr *s = &sechdrs[i]; + for (i = 0; i < info->hdr->e_shnum; ++i) { + Elf_Shdr *s = &info->sechdrs[i]; + const char *sname = info->secstrings + s->sh_name; if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || !strstarts(secstrings + s->sh_name, ".init")) + || !strstarts(sname, ".init")) continue; s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) | INIT_OFFSET_MASK); - DEBUGP("\t%s\n", secstrings + s->sh_name); + DEBUGP("\t%s\n", sname); } if (m == 0) mod->init_text_size = mod->init_size; @@ -1809,33 +1831,28 @@ static char *next_string(char *string, unsigned long *secsize) return string; } -static char *get_modinfo(Elf_Shdr *sechdrs, - unsigned int info, - const char *tag) +static char *get_modinfo(struct load_info *info, const char *tag) { char *p; unsigned int taglen = strlen(tag); - unsigned long size = sechdrs[info].sh_size; + Elf_Shdr *infosec = &info->sechdrs[info->index.info]; + unsigned long size = infosec->sh_size; - for (p = (char *)sechdrs[info].sh_addr; p; p = next_string(p, &size)) { + for (p = (char *)infosec->sh_addr; p; p = next_string(p, &size)) { if (strncmp(p, tag, taglen) == 0 && p[taglen] == '=') return p + taglen + 1; } return NULL; } -static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs, - unsigned int infoindex) +static void setup_modinfo(struct module *mod, struct load_info *info) { struct module_attribute *attr; int i; for (i = 0; (attr = modinfo_attrs[i]); i++) { if (attr->setup) - attr->setup(mod, - get_modinfo(sechdrs, - infoindex, - attr->attr.name)); + attr->setup(mod, get_modinfo(info, attr->attr.name)); } } @@ -1876,11 +1893,10 @@ static int is_exported(const char *name, unsigned long value, } /* As per nm */ -static char elf_type(const Elf_Sym *sym, - Elf_Shdr *sechdrs, - const char *secstrings, - struct module *mod) +static char elf_type(const Elf_Sym *sym, const struct load_info *info) { + const Elf_Shdr *sechdrs = info->sechdrs; + if (ELF_ST_BIND(sym->st_info) == STB_WEAK) { if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT) return 'v'; @@ -1910,8 +1926,10 @@ static char elf_type(const Elf_Sym *sym, else return 'b'; } - if (strstarts(secstrings + sechdrs[sym->st_shndx].sh_name, ".debug")) + if (strstarts(info->secstrings + sechdrs[sym->st_shndx].sh_name, + ".debug")) { return 'n'; + } return '?'; } @@ -1936,127 +1954,96 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, return true; } -static unsigned long layout_symtab(struct module *mod, - Elf_Shdr *sechdrs, - unsigned int symindex, - unsigned int strindex, - const Elf_Ehdr *hdr, - const char *secstrings, - unsigned long *pstroffs, - unsigned long *strmap) +static void layout_symtab(struct module *mod, struct load_info *info) { - unsigned long symoffs; - Elf_Shdr *symsect = sechdrs + symindex; - Elf_Shdr *strsect = sechdrs + strindex; + Elf_Shdr *symsect = info->sechdrs + info->index.sym; + Elf_Shdr *strsect = info->sechdrs + info->index.str; const Elf_Sym *src; - const char *strtab; unsigned int i, nsrc, ndst; /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, - symindex) | INIT_OFFSET_MASK; - DEBUGP("\t%s\n", secstrings + symsect->sh_name); + info->index.sym) | INIT_OFFSET_MASK; + DEBUGP("\t%s\n", info->secstrings + symsect->sh_name); - src = (void *)hdr + symsect->sh_offset; + src = (void *)info->hdr + symsect->sh_offset; nsrc = symsect->sh_size / sizeof(*src); - strtab = (void *)hdr + strsect->sh_offset; for (ndst = i = 1; i < nsrc; ++i, ++src) - if (is_core_symbol(src, sechdrs, hdr->e_shnum)) { + if (is_core_symbol(src, info->sechdrs, info->hdr->e_shnum)) { unsigned int j = src->st_name; - while(!__test_and_set_bit(j, strmap) && strtab[j]) + while (!__test_and_set_bit(j, info->strmap) + && info->strtab[j]) ++j; ++ndst; } /* Append room for core symbols at end of core part. */ - symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); - mod->core_size = symoffs + ndst * sizeof(Elf_Sym); + info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); + mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym); /* Put string table section at end of init part of module. */ strsect->sh_flags |= SHF_ALLOC; strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, - strindex) | INIT_OFFSET_MASK; - DEBUGP("\t%s\n", secstrings + strsect->sh_name); + info->index.str) | INIT_OFFSET_MASK; + DEBUGP("\t%s\n", info->secstrings + strsect->sh_name); /* Append room for core symbols' strings at end of core part. */ - *pstroffs = mod->core_size; - __set_bit(0, strmap); - mod->core_size += bitmap_weight(strmap, strsect->sh_size); - - return symoffs; + info->stroffs = mod->core_size; + __set_bit(0, info->strmap); + mod->core_size += bitmap_weight(info->strmap, strsect->sh_size); } -static void add_kallsyms(struct module *mod, - Elf_Shdr *sechdrs, - unsigned int shnum, - unsigned int symindex, - unsigned int strindex, - unsigned long symoffs, - unsigned long stroffs, - const char *secstrings, - unsigned long *strmap) +static void add_kallsyms(struct module *mod, const struct load_info *info) { unsigned int i, ndst; const Elf_Sym *src; Elf_Sym *dst; char *s; + Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; - mod->symtab = (void *)sechdrs[symindex].sh_addr; - mod->num_symtab = sechdrs[symindex].sh_size / sizeof(Elf_Sym); - mod->strtab = (void *)sechdrs[strindex].sh_addr; + mod->symtab = (void *)symsec->sh_addr; + mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + /* Make sure we get permanent strtab: don't use info->strtab. */ + mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr; /* Set types up while we still have access to sections. */ for (i = 0; i < mod->num_symtab; i++) - mod->symtab[i].st_info - = elf_type(&mod->symtab[i], sechdrs, secstrings, mod); + mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); - mod->core_symtab = dst = mod->module_core + symoffs; + mod->core_symtab = dst = mod->module_core + info->symoffs; src = mod->symtab; *dst = *src; for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) { - if (!is_core_symbol(src, sechdrs, shnum)) + if (!is_core_symbol(src, info->sechdrs, info->hdr->e_shnum)) continue; dst[ndst] = *src; - dst[ndst].st_name = bitmap_weight(strmap, dst[ndst].st_name); + dst[ndst].st_name = bitmap_weight(info->strmap, + dst[ndst].st_name); ++ndst; } mod->core_num_syms = ndst; - mod->core_strtab = s = mod->module_core + stroffs; - for (*s = 0, i = 1; i < sechdrs[strindex].sh_size; ++i) - if (test_bit(i, strmap)) + mod->core_strtab = s = mod->module_core + info->stroffs; + for (*s = 0, i = 1; i < info->sechdrs[info->index.str].sh_size; ++i) + if (test_bit(i, info->strmap)) *++s = mod->strtab[i]; } #else -static inline unsigned long layout_symtab(struct module *mod, - Elf_Shdr *sechdrs, - unsigned int symindex, - unsigned int strindex, - const Elf_Ehdr *hdr, - const char *secstrings, - unsigned long *pstroffs, - unsigned long *strmap) +static inline void layout_symtab(struct module *mod, struct load_info *info) { - return 0; } -static inline void add_kallsyms(struct module *mod, - Elf_Shdr *sechdrs, - unsigned int shnum, - unsigned int symindex, - unsigned int strindex, - unsigned long symoffs, - unsigned long stroffs, - const char *secstrings, - const unsigned long *strmap) +static void add_kallsyms(struct module *mod, struct load_info *info) { } #endif /* CONFIG_KALLSYMS */ static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num) { + if (!debug) + return; #ifdef CONFIG_DYNAMIC_DEBUG if (ddebug_add_module(debug, num, debug->modname)) printk(KERN_ERR "dynamic debug error adding module: %s\n", @@ -2087,65 +2074,47 @@ static void *module_alloc_update_bounds(unsigned long size) } #ifdef CONFIG_DEBUG_KMEMLEAK -static void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, char *secstrings) +static void kmemleak_load_module(const struct module *mod, + const struct load_info *info) { unsigned int i; /* only scan the sections containing data */ kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); - for (i = 1; i < hdr->e_shnum; i++) { - if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + for (i = 1; i < info->hdr->e_shnum; i++) { + const char *name = info->secstrings + info->sechdrs[i].sh_name; + if (!(info->sechdrs[i].sh_flags & SHF_ALLOC)) continue; - if (strncmp(secstrings + sechdrs[i].sh_name, ".data", 5) != 0 - && strncmp(secstrings + sechdrs[i].sh_name, ".bss", 4) != 0) + if (!strstarts(name, ".data") && !strstarts(name, ".bss")) continue; - kmemleak_scan_area((void *)sechdrs[i].sh_addr, - sechdrs[i].sh_size, GFP_KERNEL); + kmemleak_scan_area((void *)info->sechdrs[i].sh_addr, + info->sechdrs[i].sh_size, GFP_KERNEL); } } #else -static inline void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, char *secstrings) +static inline void kmemleak_load_module(const struct module *mod, + const struct load_info *info) { } #endif -/* Allocate and load the module: note that size of section 0 is always - zero, and we rely on this for optional sections. */ -static noinline struct module *load_module(void __user *umod, - unsigned long len, - const char __user *uargs) +/* Sets info->hdr and info->len. */ +static int copy_and_check(struct load_info *info, + const void __user *umod, unsigned long len, + const char __user *uargs) { + int err; Elf_Ehdr *hdr; - Elf_Shdr *sechdrs; - char *secstrings, *args, *modmagic, *strtab = NULL; - char *staging; - unsigned int i; - unsigned int symindex = 0; - unsigned int strindex = 0; - unsigned int modindex, versindex, infoindex, pcpuindex; - struct module *mod; - long err = 0; - void *ptr = NULL; /* Stops spurious gcc warning */ - unsigned long symoffs, stroffs, *strmap; - void __percpu *percpu; - struct _ddebug *debug = NULL; - unsigned int num_debug = 0; - mm_segment_t old_fs; - - DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", - umod, len, uargs); if (len < sizeof(*hdr)) - return ERR_PTR(-ENOEXEC); + return -ENOEXEC; /* Suck in entire file: we'll want most of it. */ /* vmalloc barfs on "unusual" numbers. Check here */ if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL) - return ERR_PTR(-ENOMEM); + return -ENOMEM; if (copy_from_user(hdr, umod, len) != 0) { err = -EFAULT; @@ -2153,135 +2122,225 @@ static noinline struct module *load_module(void __user *umod, } /* Sanity checks against insmoding binaries or wrong arch, - weird elf version */ + weird elf version */ if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0 || hdr->e_type != ET_REL || !elf_check_arch(hdr) - || hdr->e_shentsize != sizeof(*sechdrs)) { + || hdr->e_shentsize != sizeof(Elf_Shdr)) { err = -ENOEXEC; goto free_hdr; } - if (len < hdr->e_shoff + hdr->e_shnum * sizeof(Elf_Shdr)) - goto truncated; + if (len < hdr->e_shoff + hdr->e_shnum * sizeof(Elf_Shdr)) { + err = -ENOEXEC; + goto free_hdr; + } - /* Convenience variables */ - sechdrs = (void *)hdr + hdr->e_shoff; - secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - sechdrs[0].sh_addr = 0; + info->hdr = hdr; + info->len = len; + return 0; - for (i = 1; i < hdr->e_shnum; i++) { - if (sechdrs[i].sh_type != SHT_NOBITS - && len < sechdrs[i].sh_offset + sechdrs[i].sh_size) - goto truncated; +free_hdr: + vfree(hdr); + return err; +} + +static void free_copy(struct load_info *info) +{ + vfree(info->hdr); +} + +static int rewrite_section_headers(struct load_info *info) +{ + unsigned int i; + + /* This should always be true, but let's be sure. */ + info->sechdrs[0].sh_addr = 0; + + for (i = 1; i < info->hdr->e_shnum; i++) { + Elf_Shdr *shdr = &info->sechdrs[i]; + if (shdr->sh_type != SHT_NOBITS + && info->len < shdr->sh_offset + shdr->sh_size) { + printk(KERN_ERR "Module len %lu truncated\n", + info->len); + return -ENOEXEC; + } /* Mark all sections sh_addr with their address in the temporary image. */ - sechdrs[i].sh_addr = (size_t)hdr + sechdrs[i].sh_offset; + shdr->sh_addr = (size_t)info->hdr + shdr->sh_offset; - /* Internal symbols and strings. */ - if (sechdrs[i].sh_type == SHT_SYMTAB) { - symindex = i; - strindex = sechdrs[i].sh_link; - strtab = (char *)hdr + sechdrs[strindex].sh_offset; - } #ifndef CONFIG_MODULE_UNLOAD /* Don't load .exit sections */ - if (strstarts(secstrings+sechdrs[i].sh_name, ".exit")) - sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC; + if (strstarts(info->secstrings+shdr->sh_name, ".exit")) + shdr->sh_flags &= ~(unsigned long)SHF_ALLOC; #endif } - modindex = find_sec(hdr, sechdrs, secstrings, - ".gnu.linkonce.this_module"); - if (!modindex) { + /* Track but don't keep modinfo and version sections. */ + info->index.vers = find_sec(info, "__versions"); + info->index.info = find_sec(info, ".modinfo"); + info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC; + info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC; + return 0; +} + +/* + * Set up our basic convenience variables (pointers to section headers, + * search for module section index etc), and do some basic section + * verification. + * + * Return the temporary module pointer (we'll replace it with the final + * one when we move the module sections around). + */ +static struct module *setup_load_info(struct load_info *info) +{ + unsigned int i; + int err; + struct module *mod; + + /* Set up the convenience variables */ + info->sechdrs = (void *)info->hdr + info->hdr->e_shoff; + info->secstrings = (void *)info->hdr + + info->sechdrs[info->hdr->e_shstrndx].sh_offset; + + err = rewrite_section_headers(info); + if (err) + return ERR_PTR(err); + + /* Find internal symbols and strings. */ + for (i = 1; i < info->hdr->e_shnum; i++) { + if (info->sechdrs[i].sh_type == SHT_SYMTAB) { + info->index.sym = i; + info->index.str = info->sechdrs[i].sh_link; + info->strtab = (char *)info->hdr + + info->sechdrs[info->index.str].sh_offset; + break; + } + } + + info->index.mod = find_sec(info, ".gnu.linkonce.this_module"); + if (!info->index.mod) { printk(KERN_WARNING "No module found in object\n"); - err = -ENOEXEC; - goto free_hdr; + return ERR_PTR(-ENOEXEC); } /* This is temporary: point mod into copy of data. */ - mod = (void *)sechdrs[modindex].sh_addr; + mod = (void *)info->sechdrs[info->index.mod].sh_addr; - if (symindex == 0) { + if (info->index.sym == 0) { printk(KERN_WARNING "%s: module has no symbols (stripped?)\n", mod->name); - err = -ENOEXEC; - goto free_hdr; + return ERR_PTR(-ENOEXEC); } - versindex = find_sec(hdr, sechdrs, secstrings, "__versions"); - infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo"); - pcpuindex = find_pcpusec(hdr, sechdrs, secstrings); - - /* Don't keep modinfo and version sections. */ - sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC; - sechdrs[versindex].sh_flags &= ~(unsigned long)SHF_ALLOC; + info->index.pcpu = find_pcpusec(info); /* Check module struct version now, before we try to use module. */ - if (!check_modstruct_version(sechdrs, versindex, mod)) { - err = -ENOEXEC; - goto free_hdr; - } + if (!check_modstruct_version(info->sechdrs, info->index.vers, mod)) + return ERR_PTR(-ENOEXEC); + + return mod; +} + +static int check_modinfo(struct module *mod, struct load_info *info) +{ + const char *modmagic = get_modinfo(info, "vermagic"); + int err; - modmagic = get_modinfo(sechdrs, infoindex, "vermagic"); /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { err = try_to_force_load(mod, "bad vermagic"); if (err) - goto free_hdr; - } else if (!same_magic(modmagic, vermagic, versindex)) { + return err; + } else if (!same_magic(modmagic, vermagic, info->index.vers)) { printk(KERN_ERR "%s: version magic '%s' should be '%s'\n", mod->name, modmagic, vermagic); - err = -ENOEXEC; - goto free_hdr; + return -ENOEXEC; } - staging = get_modinfo(sechdrs, infoindex, "staging"); - if (staging) { + if (get_modinfo(info, "staging")) { add_taint_module(mod, TAINT_CRAP); printk(KERN_WARNING "%s: module is from the staging directory," " the quality is unknown, you have been warned.\n", mod->name); } - /* Now copy in args */ - args = strndup_user(uargs, ~0UL >> 1); - if (IS_ERR(args)) { - err = PTR_ERR(args); - goto free_hdr; - } + /* Set up license info based on the info section */ + set_license(mod, get_modinfo(info, "license")); - strmap = kzalloc(BITS_TO_LONGS(sechdrs[strindex].sh_size) - * sizeof(long), GFP_KERNEL); - if (!strmap) { - err = -ENOMEM; - goto free_mod; - } + return 0; +} - mod->state = MODULE_STATE_COMING; +static void find_module_sections(struct module *mod, struct load_info *info) +{ + mod->kp = section_objs(info, "__param", + sizeof(*mod->kp), &mod->num_kp); + mod->syms = section_objs(info, "__ksymtab", + sizeof(*mod->syms), &mod->num_syms); + mod->crcs = section_addr(info, "__kcrctab"); + mod->gpl_syms = section_objs(info, "__ksymtab_gpl", + sizeof(*mod->gpl_syms), + &mod->num_gpl_syms); + mod->gpl_crcs = section_addr(info, "__kcrctab_gpl"); + mod->gpl_future_syms = section_objs(info, + "__ksymtab_gpl_future", + sizeof(*mod->gpl_future_syms), + &mod->num_gpl_future_syms); + mod->gpl_future_crcs = section_addr(info, "__kcrctab_gpl_future"); - /* Allow arches to frob section contents and sizes. */ - err = module_frob_arch_sections(hdr, sechdrs, secstrings, mod); - if (err < 0) - goto free_mod; +#ifdef CONFIG_UNUSED_SYMBOLS + mod->unused_syms = section_objs(info, "__ksymtab_unused", + sizeof(*mod->unused_syms), + &mod->num_unused_syms); + mod->unused_crcs = section_addr(info, "__kcrctab_unused"); + mod->unused_gpl_syms = section_objs(info, "__ksymtab_unused_gpl", + sizeof(*mod->unused_gpl_syms), + &mod->num_unused_gpl_syms); + mod->unused_gpl_crcs = section_addr(info, "__kcrctab_unused_gpl"); +#endif +#ifdef CONFIG_CONSTRUCTORS + mod->ctors = section_objs(info, ".ctors", + sizeof(*mod->ctors), &mod->num_ctors); +#endif - if (pcpuindex) { - /* We have a special allocation for this section. */ - err = percpu_modalloc(mod, sechdrs[pcpuindex].sh_size, - sechdrs[pcpuindex].sh_addralign); - if (err) - goto free_mod; - sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC; - } - /* Keep this around for failure path. */ - percpu = mod_percpu(mod); +#ifdef CONFIG_TRACEPOINTS + mod->tracepoints = section_objs(info, "__tracepoints", + sizeof(*mod->tracepoints), + &mod->num_tracepoints); +#endif +#ifdef CONFIG_EVENT_TRACING + mod->trace_events = section_objs(info, "_ftrace_events", + sizeof(*mod->trace_events), + &mod->num_trace_events); + /* + * This section contains pointers to allocated objects in the trace + * code and not scanning it leads to false positives. + */ + kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) * + mod->num_trace_events, GFP_KERNEL); +#endif +#ifdef CONFIG_FTRACE_MCOUNT_RECORD + /* sechdrs[0].sh_size is always zero */ + mod->ftrace_callsites = section_objs(info, "__mcount_loc", + sizeof(*mod->ftrace_callsites), + &mod->num_ftrace_callsites); +#endif - /* Determine total sizes, and put offsets in sh_entsize. For now - this is done generically; there doesn't appear to be any - special cases for the architectures. */ - layout_sections(mod, hdr, sechdrs, secstrings); - symoffs = layout_symtab(mod, sechdrs, symindex, strindex, hdr, - secstrings, &stroffs, strmap); + mod->extable = section_objs(info, "__ex_table", + sizeof(*mod->extable), &mod->num_exentries); + + if (section_addr(info, "__obsparm")) + printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", + mod->name); + + info->debug = section_objs(info, "__verbose", + sizeof(*info->debug), &info->num_debug); +} + +static int move_module(struct module *mod, struct load_info *info) +{ + int i; + void *ptr; /* Do the allocs. */ ptr = module_alloc_update_bounds(mod->core_size); @@ -2291,10 +2350,9 @@ static noinline struct module *load_module(void __user *umod, * leak. */ kmemleak_not_leak(ptr); - if (!ptr) { - err = -ENOMEM; - goto free_percpu; - } + if (!ptr) + return -ENOMEM; + memset(ptr, 0, mod->core_size); mod->module_core = ptr; @@ -2307,50 +2365,40 @@ static noinline struct module *load_module(void __user *umod, */ kmemleak_ignore(ptr); if (!ptr && mod->init_size) { - err = -ENOMEM; - goto free_core; + module_free(mod, mod->module_core); + return -ENOMEM; } memset(ptr, 0, mod->init_size); mod->module_init = ptr; /* Transfer each section which specifies SHF_ALLOC */ DEBUGP("final section addresses:\n"); - for (i = 0; i < hdr->e_shnum; i++) { + for (i = 0; i < info->hdr->e_shnum; i++) { void *dest; + Elf_Shdr *shdr = &info->sechdrs[i]; - if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + if (!(shdr->sh_flags & SHF_ALLOC)) continue; - if (sechdrs[i].sh_entsize & INIT_OFFSET_MASK) + if (shdr->sh_entsize & INIT_OFFSET_MASK) dest = mod->module_init - + (sechdrs[i].sh_entsize & ~INIT_OFFSET_MASK); + + (shdr->sh_entsize & ~INIT_OFFSET_MASK); else - dest = mod->module_core + sechdrs[i].sh_entsize; + dest = mod->module_core + shdr->sh_entsize; - if (sechdrs[i].sh_type != SHT_NOBITS) - memcpy(dest, (void *)sechdrs[i].sh_addr, - sechdrs[i].sh_size); + if (shdr->sh_type != SHT_NOBITS) + memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); /* Update sh_addr to point to copy in image. */ - sechdrs[i].sh_addr = (unsigned long)dest; - DEBUGP("\t0x%lx %s\n", sechdrs[i].sh_addr, secstrings + sechdrs[i].sh_name); - } - /* Module has been moved. */ - mod = (void *)sechdrs[modindex].sh_addr; - kmemleak_load_module(mod, hdr, sechdrs, secstrings); - -#if defined(CONFIG_MODULE_UNLOAD) - mod->refptr = alloc_percpu(struct module_ref); - if (!mod->refptr) { - err = -ENOMEM; - goto free_init; + shdr->sh_addr = (unsigned long)dest; + DEBUGP("\t0x%lx %s\n", + shdr->sh_addr, info->secstrings + shdr->sh_name); } -#endif - /* Now we've moved module, initialize linked lists, etc. */ - module_unload_init(mod); - /* Set up license info based on the info section */ - set_license(mod, get_modinfo(sechdrs, infoindex, "license")); + return 0; +} +static int check_module_license_and_versions(struct module *mod) +{ /* * ndiswrapper is under GPL by itself, but loads proprietary modules. * Don't use add_taint_module(), as it would prevent ndiswrapper from @@ -2363,77 +2411,6 @@ static noinline struct module *load_module(void __user *umod, if (strcmp(mod->name, "driverloader") == 0) add_taint_module(mod, TAINT_PROPRIETARY_MODULE); - /* Set up MODINFO_ATTR fields */ - setup_modinfo(mod, sechdrs, infoindex); - - /* Fix up syms, so that st_value is a pointer to location. */ - err = simplify_symbols(sechdrs, symindex, strtab, versindex, pcpuindex, - mod); - if (err < 0) - goto cleanup; - - /* Now we've got everything in the final locations, we can - * find optional sections. */ - mod->kp = section_objs(hdr, sechdrs, secstrings, "__param", - sizeof(*mod->kp), &mod->num_kp); - mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab", - sizeof(*mod->syms), &mod->num_syms); - mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab"); - mod->gpl_syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab_gpl", - sizeof(*mod->gpl_syms), - &mod->num_gpl_syms); - mod->gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_gpl"); - mod->gpl_future_syms = section_objs(hdr, sechdrs, secstrings, - "__ksymtab_gpl_future", - sizeof(*mod->gpl_future_syms), - &mod->num_gpl_future_syms); - mod->gpl_future_crcs = section_addr(hdr, sechdrs, secstrings, - "__kcrctab_gpl_future"); - -#ifdef CONFIG_UNUSED_SYMBOLS - mod->unused_syms = section_objs(hdr, sechdrs, secstrings, - "__ksymtab_unused", - sizeof(*mod->unused_syms), - &mod->num_unused_syms); - mod->unused_crcs = section_addr(hdr, sechdrs, secstrings, - "__kcrctab_unused"); - mod->unused_gpl_syms = section_objs(hdr, sechdrs, secstrings, - "__ksymtab_unused_gpl", - sizeof(*mod->unused_gpl_syms), - &mod->num_unused_gpl_syms); - mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings, - "__kcrctab_unused_gpl"); -#endif -#ifdef CONFIG_CONSTRUCTORS - mod->ctors = section_objs(hdr, sechdrs, secstrings, ".ctors", - sizeof(*mod->ctors), &mod->num_ctors); -#endif - -#ifdef CONFIG_TRACEPOINTS - mod->tracepoints = section_objs(hdr, sechdrs, secstrings, - "__tracepoints", - sizeof(*mod->tracepoints), - &mod->num_tracepoints); -#endif -#ifdef CONFIG_EVENT_TRACING - mod->trace_events = section_objs(hdr, sechdrs, secstrings, - "_ftrace_events", - sizeof(*mod->trace_events), - &mod->num_trace_events); - /* - * This section contains pointers to allocated objects in the trace - * code and not scanning it leads to false positives. - */ - kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) * - mod->num_trace_events, GFP_KERNEL); -#endif -#ifdef CONFIG_FTRACE_MCOUNT_RECORD - /* sechdrs[0].sh_size is always zero */ - mod->ftrace_callsites = section_objs(hdr, sechdrs, secstrings, - "__mcount_loc", - sizeof(*mod->ftrace_callsites), - &mod->num_ftrace_callsites); -#endif #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || (mod->num_gpl_syms && !mod->gpl_crcs) @@ -2443,56 +2420,16 @@ static noinline struct module *load_module(void __user *umod, || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) #endif ) { - err = try_to_force_load(mod, - "no versions for exported symbols"); - if (err) - goto cleanup; + return try_to_force_load(mod, + "no versions for exported symbols"); } #endif + return 0; +} - /* Now do relocations. */ - for (i = 1; i < hdr->e_shnum; i++) { - const char *strtab = (char *)sechdrs[strindex].sh_addr; - unsigned int info = sechdrs[i].sh_info; - - /* Not a valid relocation section? */ - if (info >= hdr->e_shnum) - continue; - - /* Don't bother with non-allocated sections */ - if (!(sechdrs[info].sh_flags & SHF_ALLOC)) - continue; - - if (sechdrs[i].sh_type == SHT_REL) - err = apply_relocate(sechdrs, strtab, symindex, i,mod); - else if (sechdrs[i].sh_type == SHT_RELA) - err = apply_relocate_add(sechdrs, strtab, symindex, i, - mod); - if (err < 0) - goto cleanup; - } - - /* Set up and sort exception table */ - mod->extable = section_objs(hdr, sechdrs, secstrings, "__ex_table", - sizeof(*mod->extable), &mod->num_exentries); - sort_extable(mod->extable, mod->extable + mod->num_exentries); - - /* Finally, copy percpu area over. */ - percpu_modcopy(mod, (void *)sechdrs[pcpuindex].sh_addr, - sechdrs[pcpuindex].sh_size); - - add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex, - symoffs, stroffs, secstrings, strmap); - kfree(strmap); - strmap = NULL; - - if (!mod->taints) - debug = section_objs(hdr, sechdrs, secstrings, "__verbose", - sizeof(*debug), &num_debug); - - err = module_finalize(hdr, sechdrs, mod); - if (err < 0) - goto cleanup; +static void flush_module_icache(const struct module *mod) +{ + mm_segment_t old_fs; /* flush the icache in correct context */ old_fs = get_fs(); @@ -2511,11 +2448,160 @@ static noinline struct module *load_module(void __user *umod, (unsigned long)mod->module_core + mod->core_size); set_fs(old_fs); +} - mod->args = args; - if (section_addr(hdr, sechdrs, secstrings, "__obsparm")) - printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", - mod->name); +static struct module *layout_and_allocate(struct load_info *info) +{ + /* Module within temporary copy. */ + struct module *mod; + Elf_Shdr *pcpusec; + int err; + + mod = setup_load_info(info); + if (IS_ERR(mod)) + return mod; + + err = check_modinfo(mod, info); + if (err) + return ERR_PTR(err); + + /* Allow arches to frob section contents and sizes. */ + err = module_frob_arch_sections(info->hdr, info->sechdrs, + info->secstrings, mod); + if (err < 0) + goto out; + + pcpusec = &info->sechdrs[info->index.pcpu]; + if (pcpusec->sh_size) { + /* We have a special allocation for this section. */ + err = percpu_modalloc(mod, + pcpusec->sh_size, pcpusec->sh_addralign); + if (err) + goto out; + pcpusec->sh_flags &= ~(unsigned long)SHF_ALLOC; + } + + /* Determine total sizes, and put offsets in sh_entsize. For now + this is done generically; there doesn't appear to be any + special cases for the architectures. */ + layout_sections(mod, info); + + info->strmap = kzalloc(BITS_TO_LONGS(info->sechdrs[info->index.str].sh_size) + * sizeof(long), GFP_KERNEL); + if (!info->strmap) { + err = -ENOMEM; + goto free_percpu; + } + layout_symtab(mod, info); + + /* Allocate and move to the final place */ + err = move_module(mod, info); + if (err) + goto free_strmap; + + /* Module has been copied to its final place now: return it. */ + mod = (void *)info->sechdrs[info->index.mod].sh_addr; + kmemleak_load_module(mod, info); + return mod; + +free_strmap: + kfree(info->strmap); +free_percpu: + percpu_modfree(mod); +out: + return ERR_PTR(err); +} + +/* mod is no longer valid after this! */ +static void module_deallocate(struct module *mod, struct load_info *info) +{ + kfree(info->strmap); + percpu_modfree(mod); + module_free(mod, mod->module_init); + module_free(mod, mod->module_core); +} + +static int post_relocation(struct module *mod, const struct load_info *info) +{ + /* Sort exception table now relocations are done. */ + sort_extable(mod->extable, mod->extable + mod->num_exentries); + + /* Copy relocated percpu area over. */ + percpu_modcopy(mod, (void *)info->sechdrs[info->index.pcpu].sh_addr, + info->sechdrs[info->index.pcpu].sh_size); + + /* Setup kallsyms-specific fields. */ + add_kallsyms(mod, info); + + /* Arch-specific module finalizing. */ + return module_finalize(info->hdr, info->sechdrs, mod); +} + +/* Allocate and load the module: note that size of section 0 is always + zero, and we rely on this for optional sections. */ +static struct module *load_module(void __user *umod, + unsigned long len, + const char __user *uargs) +{ + struct load_info info = { NULL, }; + struct module *mod; + long err; + + DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", + umod, len, uargs); + + /* Copy in the blobs from userspace, check they are vaguely sane. */ + err = copy_and_check(&info, umod, len, uargs); + if (err) + return ERR_PTR(err); + + /* Figure out module layout, and allocate all the memory. */ + mod = layout_and_allocate(&info); + if (IS_ERR(mod)) { + err = PTR_ERR(mod); + goto free_copy; + } + + /* Now module is in final location, initialize linked lists, etc. */ + err = module_unload_init(mod); + if (err) + goto free_module; + + /* Now we've got everything in the final locations, we can + * find optional sections. */ + find_module_sections(mod, &info); + + err = check_module_license_and_versions(mod); + if (err) + goto free_unload; + + /* Set up MODINFO_ATTR fields */ + setup_modinfo(mod, &info); + + /* Fix up syms, so that st_value is a pointer to location. */ + err = simplify_symbols(mod, &info); + if (err < 0) + goto free_modinfo; + + err = apply_relocations(mod, &info); + if (err < 0) + goto free_modinfo; + + err = post_relocation(mod, &info); + if (err < 0) + goto free_modinfo; + + flush_module_icache(mod); + + /* Now copy in args */ + mod->args = strndup_user(uargs, ~0UL >> 1); + if (IS_ERR(mod->args)) { + err = PTR_ERR(mod->args); + goto free_arch_cleanup; + } + + /* Mark state as coming so strong_try_module_get() ignores us. */ + mod->state = MODULE_STATE_COMING; /* Now sew it into the lists so we can get lockdep and oops * info during argument parsing. Noone should access us, since @@ -2530,8 +2616,9 @@ static noinline struct module *load_module(void __user *umod, goto unlock; } - if (debug) - dynamic_debug_setup(debug, num_debug); + /* This has to be done once we're sure module name is unique. */ + if (!mod->taints) + dynamic_debug_setup(info.debug, info.num_debug); /* Find duplicate symbols */ err = verify_export_symbols(mod); @@ -2541,23 +2628,22 @@ static noinline struct module *load_module(void __user *umod, list_add_rcu(&mod->list, &modules); mutex_unlock(&module_mutex); + /* Module is ready to execute: parsing args may do that. */ err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, NULL); if (err < 0) goto unlink; - err = mod_sysfs_setup(mod, mod->kp, mod->num_kp); + /* Link in to syfs. */ + err = mod_sysfs_setup(mod, &info, mod->kp, mod->num_kp); if (err < 0) goto unlink; - add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); - add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs); - - /* Get rid of temporary copy */ - vfree(hdr); - - trace_module_load(mod); + /* Get rid of temporary copy and strmap. */ + kfree(info.strmap); + free_copy(&info); /* Done! */ + trace_module_load(mod); return mod; unlink: @@ -2565,35 +2651,23 @@ static noinline struct module *load_module(void __user *umod, /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); ddebug: - dynamic_debug_remove(debug); + if (!mod->taints) + dynamic_debug_remove(info.debug); unlock: mutex_unlock(&module_mutex); synchronize_sched(); + kfree(mod->args); + free_arch_cleanup: module_arch_cleanup(mod); - cleanup: + free_modinfo: free_modinfo(mod); + free_unload: module_unload_free(mod); -#if defined(CONFIG_MODULE_UNLOAD) - free_percpu(mod->refptr); - free_init: -#endif - module_free(mod, mod->module_init); - free_core: - module_free(mod, mod->module_core); - /* mod will be freed with core. Don't access it beyond this line! */ - free_percpu: - free_percpu(percpu); - free_mod: - kfree(args); - kfree(strmap); - free_hdr: - vfree(hdr); + free_module: + module_deallocate(mod, &info); + free_copy: + free_copy(&info); return ERR_PTR(err); - - truncated: - printk(KERN_ERR "Module len %lu truncated\n", len); - err = -ENOEXEC; - goto free_hdr; } /* Call module constructors. */ diff --git a/kernel/perf_event.c b/kernel/perf_event.c index ff86c558af4..403d1804b19 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -214,7 +214,7 @@ static void perf_unpin_context(struct perf_event_context *ctx) static inline u64 perf_clock(void) { - return cpu_clock(raw_smp_processor_id()); + return local_clock(); } /* @@ -675,7 +675,6 @@ group_sched_in(struct perf_event *group_event, struct perf_event *event, *partial_group = NULL; const struct pmu *pmu = group_event->pmu; bool txn = false; - int ret; if (group_event->state == PERF_EVENT_STATE_OFF) return 0; @@ -703,14 +702,8 @@ group_sched_in(struct perf_event *group_event, } } - if (!txn) - return 0; - - ret = pmu->commit_txn(pmu); - if (!ret) { - pmu->cancel_txn(pmu); + if (!txn || !pmu->commit_txn(pmu)) return 0; - } group_error: /* @@ -1155,9 +1148,9 @@ static void __perf_event_sync_stat(struct perf_event *event, * In order to keep per-task stats reliable we need to flip the event * values when we flip the contexts. */ - value = atomic64_read(&next_event->count); - value = atomic64_xchg(&event->count, value); - atomic64_set(&next_event->count, value); + value = local64_read(&next_event->count); + value = local64_xchg(&event->count, value); + local64_set(&next_event->count, value); swap(event->total_time_enabled, next_event->total_time_enabled); swap(event->total_time_running, next_event->total_time_running); @@ -1547,10 +1540,10 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count) hwc->sample_period = sample_period; - if (atomic64_read(&hwc->period_left) > 8*sample_period) { + if (local64_read(&hwc->period_left) > 8*sample_period) { perf_disable(); perf_event_stop(event); - atomic64_set(&hwc->period_left, 0); + local64_set(&hwc->period_left, 0); perf_event_start(event); perf_enable(); } @@ -1591,7 +1584,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx) perf_disable(); event->pmu->read(event); - now = atomic64_read(&event->count); + now = local64_read(&event->count); delta = now - hwc->freq_count_stamp; hwc->freq_count_stamp = now; @@ -1743,6 +1736,11 @@ static void __perf_event_read(void *info) event->pmu->read(event); } +static inline u64 perf_event_count(struct perf_event *event) +{ + return local64_read(&event->count) + atomic64_read(&event->child_count); +} + static u64 perf_event_read(struct perf_event *event) { /* @@ -1762,7 +1760,7 @@ static u64 perf_event_read(struct perf_event *event) raw_spin_unlock_irqrestore(&ctx->lock, flags); } - return atomic64_read(&event->count); + return perf_event_count(event); } /* @@ -1883,7 +1881,7 @@ static void free_event_rcu(struct rcu_head *head) } static void perf_pending_sync(struct perf_event *event); -static void perf_mmap_data_put(struct perf_mmap_data *data); +static void perf_buffer_put(struct perf_buffer *buffer); static void free_event(struct perf_event *event) { @@ -1891,7 +1889,7 @@ static void free_event(struct perf_event *event) if (!event->parent) { atomic_dec(&nr_events); - if (event->attr.mmap) + if (event->attr.mmap || event->attr.mmap_data) atomic_dec(&nr_mmap_events); if (event->attr.comm) atomic_dec(&nr_comm_events); @@ -1899,9 +1897,9 @@ static void free_event(struct perf_event *event) atomic_dec(&nr_task_events); } - if (event->data) { - perf_mmap_data_put(event->data); - event->data = NULL; + if (event->buffer) { + perf_buffer_put(event->buffer); + event->buffer = NULL; } if (event->destroy) @@ -2126,13 +2124,13 @@ perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) static unsigned int perf_poll(struct file *file, poll_table *wait) { struct perf_event *event = file->private_data; - struct perf_mmap_data *data; + struct perf_buffer *buffer; unsigned int events = POLL_HUP; rcu_read_lock(); - data = rcu_dereference(event->data); - if (data) - events = atomic_xchg(&data->poll, 0); + buffer = rcu_dereference(event->buffer); + if (buffer) + events = atomic_xchg(&buffer->poll, 0); rcu_read_unlock(); poll_wait(file, &event->waitq, wait); @@ -2143,7 +2141,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) static void perf_event_reset(struct perf_event *event) { (void)perf_event_read(event); - atomic64_set(&event->count, 0); + local64_set(&event->count, 0); perf_event_update_userpage(event); } @@ -2342,14 +2340,14 @@ static int perf_event_index(struct perf_event *event) void perf_event_update_userpage(struct perf_event *event) { struct perf_event_mmap_page *userpg; - struct perf_mmap_data *data; + struct perf_buffer *buffer; rcu_read_lock(); - data = rcu_dereference(event->data); - if (!data) + buffer = rcu_dereference(event->buffer); + if (!buffer) goto unlock; - userpg = data->user_page; + userpg = buffer->user_page; /* * Disable preemption so as to not let the corresponding user-space @@ -2359,9 +2357,9 @@ void perf_event_update_userpage(struct perf_event *event) ++userpg->lock; barrier(); userpg->index = perf_event_index(event); - userpg->offset = atomic64_read(&event->count); + userpg->offset = perf_event_count(event); if (event->state == PERF_EVENT_STATE_ACTIVE) - userpg->offset -= atomic64_read(&event->hw.prev_count); + userpg->offset -= local64_read(&event->hw.prev_count); userpg->time_enabled = event->total_time_enabled + atomic64_read(&event->child_total_time_enabled); @@ -2376,6 +2374,25 @@ unlock: rcu_read_unlock(); } +static unsigned long perf_data_size(struct perf_buffer *buffer); + +static void +perf_buffer_init(struct perf_buffer *buffer, long watermark, int flags) +{ + long max_size = perf_data_size(buffer); + + if (watermark) + buffer->watermark = min(max_size, watermark); + + if (!buffer->watermark) + buffer->watermark = max_size / 2; + + if (flags & PERF_BUFFER_WRITABLE) + buffer->writable = 1; + + atomic_set(&buffer->refcount, 1); +} + #ifndef CONFIG_PERF_USE_VMALLOC /* @@ -2383,15 +2400,15 @@ unlock: */ static struct page * -perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff) +perf_mmap_to_page(struct perf_buffer *buffer, unsigned long pgoff) { - if (pgoff > data->nr_pages) + if (pgoff > buffer->nr_pages) return NULL; if (pgoff == 0) - return virt_to_page(data->user_page); + return virt_to_page(buffer->user_page); - return virt_to_page(data->data_pages[pgoff - 1]); + return virt_to_page(buffer->data_pages[pgoff - 1]); } static void *perf_mmap_alloc_page(int cpu) @@ -2407,42 +2424,44 @@ static void *perf_mmap_alloc_page(int cpu) return page_address(page); } -static struct perf_mmap_data * -perf_mmap_data_alloc(struct perf_event *event, int nr_pages) +static struct perf_buffer * +perf_buffer_alloc(int nr_pages, long watermark, int cpu, int flags) { - struct perf_mmap_data *data; + struct perf_buffer *buffer; unsigned long size; int i; - size = sizeof(struct perf_mmap_data); + size = sizeof(struct perf_buffer); size += nr_pages * sizeof(void *); - data = kzalloc(size, GFP_KERNEL); - if (!data) + buffer = kzalloc(size, GFP_KERNEL); + if (!buffer) goto fail; - data->user_page = perf_mmap_alloc_page(event->cpu); - if (!data->user_page) + buffer->user_page = perf_mmap_alloc_page(cpu); + if (!buffer->user_page) goto fail_user_page; for (i = 0; i < nr_pages; i++) { - data->data_pages[i] = perf_mmap_alloc_page(event->cpu); - if (!data->data_pages[i]) + buffer->data_pages[i] = perf_mmap_alloc_page(cpu); + if (!buffer->data_pages[i]) goto fail_data_pages; } - data->nr_pages = nr_pages; + buffer->nr_pages = nr_pages; + + perf_buffer_init(buffer, watermark, flags); - return data; + return buffer; fail_data_pages: for (i--; i >= 0; i--) - free_page((unsigned long)data->data_pages[i]); + free_page((unsigned long)buffer->data_pages[i]); - free_page((unsigned long)data->user_page); + free_page((unsigned long)buffer->user_page); fail_user_page: - kfree(data); + kfree(buffer); fail: return NULL; @@ -2456,17 +2475,17 @@ static void perf_mmap_free_page(unsigned long addr) __free_page(page); } -static void perf_mmap_data_free(struct perf_mmap_data *data) +static void perf_buffer_free(struct perf_buffer *buffer) { int i; - perf_mmap_free_page((unsigned long)data->user_page); - for (i = 0; i < data->nr_pages; i++) - perf_mmap_free_page((unsigned long)data->data_pages[i]); - kfree(data); + perf_mmap_free_page((unsigned long)buffer->user_page); + for (i = 0; i < buffer->nr_pages; i++) + perf_mmap_free_page((unsigned long)buffer->data_pages[i]); + kfree(buffer); } -static inline int page_order(struct perf_mmap_data *data) +static inline int page_order(struct perf_buffer *buffer) { return 0; } @@ -2479,18 +2498,18 @@ static inline int page_order(struct perf_mmap_data *data) * Required for architectures that have d-cache aliasing issues. */ -static inline int page_order(struct perf_mmap_data *data) +static inline int page_order(struct perf_buffer *buffer) { - return data->page_order; + return buffer->page_order; } static struct page * -perf_mmap_to_page(struct perf_mmap_data *data, unsigned long pgoff) +perf_mmap_to_page(struct perf_buffer *buffer, unsigned long pgoff) { - if (pgoff > (1UL << page_order(data))) + if (pgoff > (1UL << page_order(buffer))) return NULL; - return vmalloc_to_page((void *)data->user_page + pgoff * PAGE_SIZE); + return vmalloc_to_page((void *)buffer->user_page + pgoff * PAGE_SIZE); } static void perf_mmap_unmark_page(void *addr) @@ -2500,57 +2519,59 @@ static void perf_mmap_unmark_page(void *addr) page->mapping = NULL; } -static void perf_mmap_data_free_work(struct work_struct *work) +static void perf_buffer_free_work(struct work_struct *work) { - struct perf_mmap_data *data; + struct perf_buffer *buffer; void *base; int i, nr; - data = container_of(work, struct perf_mmap_data, work); - nr = 1 << page_order(data); + buffer = container_of(work, struct perf_buffer, work); + nr = 1 << page_order(buffer); - base = data->user_page; + base = buffer->user_page; for (i = 0; i < nr + 1; i++) perf_mmap_unmark_page(base + (i * PAGE_SIZE)); vfree(base); - kfree(data); + kfree(buffer); } -static void perf_mmap_data_free(struct perf_mmap_data *data) +static void perf_buffer_free(struct perf_buffer *buffer) { - schedule_work(&data->work); + schedule_work(&buffer->work); } -static struct perf_mmap_data * -perf_mmap_data_alloc(struct perf_event *event, int nr_pages) +static struct perf_buffer * +perf_buffer_alloc(int nr_pages, long watermark, int cpu, int flags) { - struct perf_mmap_data *data; + struct perf_buffer *buffer; unsigned long size; void *all_buf; - size = sizeof(struct perf_mmap_data); + size = sizeof(struct perf_buffer); size += sizeof(void *); - data = kzalloc(size, GFP_KERNEL); - if (!data) + buffer = kzalloc(size, GFP_KERNEL); + if (!buffer) goto fail; - INIT_WORK(&data->work, perf_mmap_data_free_work); + INIT_WORK(&buffer->work, perf_buffer_free_work); all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE); if (!all_buf) goto fail_all_buf; - data->user_page = all_buf; - data->data_pages[0] = all_buf + PAGE_SIZE; - data->page_order = ilog2(nr_pages); - data->nr_pages = 1; + buffer->user_page = all_buf; + buffer->data_pages[0] = all_buf + PAGE_SIZE; + buffer->page_order = ilog2(nr_pages); + buffer->nr_pages = 1; + + perf_buffer_init(buffer, watermark, flags); - return data; + return buffer; fail_all_buf: - kfree(data); + kfree(buffer); fail: return NULL; @@ -2558,15 +2579,15 @@ fail: #endif -static unsigned long perf_data_size(struct perf_mmap_data *data) +static unsigned long perf_data_size(struct perf_buffer *buffer) { - return data->nr_pages << (PAGE_SHIFT + page_order(data)); + return buffer->nr_pages << (PAGE_SHIFT + page_order(buffer)); } static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct perf_event *event = vma->vm_file->private_data; - struct perf_mmap_data *data; + struct perf_buffer *buffer; int ret = VM_FAULT_SIGBUS; if (vmf->flags & FAULT_FLAG_MKWRITE) { @@ -2576,14 +2597,14 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } rcu_read_lock(); - data = rcu_dereference(event->data); - if (!data) + buffer = rcu_dereference(event->buffer); + if (!buffer) goto unlock; if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE)) goto unlock; - vmf->page = perf_mmap_to_page(data, vmf->pgoff); + vmf->page = perf_mmap_to_page(buffer, vmf->pgoff); if (!vmf->page) goto unlock; @@ -2598,52 +2619,35 @@ unlock: return ret; } -static void -perf_mmap_data_init(struct perf_event *event, struct perf_mmap_data *data) -{ - long max_size = perf_data_size(data); - - if (event->attr.watermark) { - data->watermark = min_t(long, max_size, - event->attr.wakeup_watermark); - } - - if (!data->watermark) - data->watermark = max_size / 2; - - atomic_set(&data->refcount, 1); - rcu_assign_pointer(event->data, data); -} - -static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head) +static void perf_buffer_free_rcu(struct rcu_head *rcu_head) { - struct perf_mmap_data *data; + struct perf_buffer *buffer; - data = container_of(rcu_head, struct perf_mmap_data, rcu_head); - perf_mmap_data_free(data); + buffer = container_of(rcu_head, struct perf_buffer, rcu_head); + perf_buffer_free(buffer); } -static struct perf_mmap_data *perf_mmap_data_get(struct perf_event *event) +static struct perf_buffer *perf_buffer_get(struct perf_event *event) { - struct perf_mmap_data *data; + struct perf_buffer *buffer; rcu_read_lock(); - data = rcu_dereference(event->data); - if (data) { - if (!atomic_inc_not_zero(&data->refcount)) - data = NULL; + buffer = rcu_dereference(event->buffer); + if (buffer) { + if (!atomic_inc_not_zero(&buffer->refcount)) + buffer = NULL; } rcu_read_unlock(); - return data; + return buffer; } -static void perf_mmap_data_put(struct perf_mmap_data *data) +static void perf_buffer_put(struct perf_buffer *buffer) { - if (!atomic_dec_and_test(&data->refcount)) + if (!atomic_dec_and_test(&buffer->refcount)) return; - call_rcu(&data->rcu_head, perf_mmap_data_free_rcu); + call_rcu(&buffer->rcu_head, perf_buffer_free_rcu); } static void perf_mmap_open(struct vm_area_struct *vma) @@ -2658,16 +2662,16 @@ static void perf_mmap_close(struct vm_area_struct *vma) struct perf_event *event = vma->vm_file->private_data; if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) { - unsigned long size = perf_data_size(event->data); + unsigned long size = perf_data_size(event->buffer); struct user_struct *user = event->mmap_user; - struct perf_mmap_data *data = event->data; + struct perf_buffer *buffer = event->buffer; atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm); vma->vm_mm->locked_vm -= event->mmap_locked; - rcu_assign_pointer(event->data, NULL); + rcu_assign_pointer(event->buffer, NULL); mutex_unlock(&event->mmap_mutex); - perf_mmap_data_put(data); + perf_buffer_put(buffer); free_uid(user); } } @@ -2685,11 +2689,11 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) unsigned long user_locked, user_lock_limit; struct user_struct *user = current_user(); unsigned long locked, lock_limit; - struct perf_mmap_data *data; + struct perf_buffer *buffer; unsigned long vma_size; unsigned long nr_pages; long user_extra, extra; - int ret = 0; + int ret = 0, flags = 0; /* * Don't allow mmap() of inherited per-task counters. This would @@ -2706,7 +2710,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) nr_pages = (vma_size / PAGE_SIZE) - 1; /* - * If we have data pages ensure they're a power-of-two number, so we + * If we have buffer pages ensure they're a power-of-two number, so we * can do bitmasks instead of modulo. */ if (nr_pages != 0 && !is_power_of_2(nr_pages)) @@ -2720,9 +2724,9 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) WARN_ON_ONCE(event->ctx->parent_ctx); mutex_lock(&event->mmap_mutex); - if (event->data) { - if (event->data->nr_pages == nr_pages) - atomic_inc(&event->data->refcount); + if (event->buffer) { + if (event->buffer->nr_pages == nr_pages) + atomic_inc(&event->buffer->refcount); else ret = -EINVAL; goto unlock; @@ -2752,17 +2756,18 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) goto unlock; } - WARN_ON(event->data); + WARN_ON(event->buffer); + + if (vma->vm_flags & VM_WRITE) + flags |= PERF_BUFFER_WRITABLE; - data = perf_mmap_data_alloc(event, nr_pages); - if (!data) { + buffer = perf_buffer_alloc(nr_pages, event->attr.wakeup_watermark, + event->cpu, flags); + if (!buffer) { ret = -ENOMEM; goto unlock; } - - perf_mmap_data_init(event, data); - if (vma->vm_flags & VM_WRITE) - event->data->writable = 1; + rcu_assign_pointer(event->buffer, buffer); atomic_long_add(user_extra, &user->locked_vm); event->mmap_locked = extra; @@ -2941,11 +2946,6 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return NULL; } -__weak -void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) -{ -} - /* * We assume there is only KVM supporting the callbacks. @@ -2971,15 +2971,15 @@ EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); /* * Output */ -static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail, +static bool perf_output_space(struct perf_buffer *buffer, unsigned long tail, unsigned long offset, unsigned long head) { unsigned long mask; - if (!data->writable) + if (!buffer->writable) return true; - mask = perf_data_size(data) - 1; + mask = perf_data_size(buffer) - 1; offset = (offset - tail) & mask; head = (head - tail) & mask; @@ -2992,7 +2992,7 @@ static bool perf_output_space(struct perf_mmap_data *data, unsigned long tail, static void perf_output_wakeup(struct perf_output_handle *handle) { - atomic_set(&handle->data->poll, POLL_IN); + atomic_set(&handle->buffer->poll, POLL_IN); if (handle->nmi) { handle->event->pending_wakeup = 1; @@ -3012,45 +3012,45 @@ static void perf_output_wakeup(struct perf_output_handle *handle) */ static void perf_output_get_handle(struct perf_output_handle *handle) { - struct perf_mmap_data *data = handle->data; + struct perf_buffer *buffer = handle->buffer; preempt_disable(); - local_inc(&data->nest); - handle->wakeup = local_read(&data->wakeup); + local_inc(&buffer->nest); + handle->wakeup = local_read(&buffer->wakeup); } static void perf_output_put_handle(struct perf_output_handle *handle) { - struct perf_mmap_data *data = handle->data; + struct perf_buffer *buffer = handle->buffer; unsigned long head; again: - head = local_read(&data->head); + head = local_read(&buffer->head); /* * IRQ/NMI can happen here, which means we can miss a head update. */ - if (!local_dec_and_test(&data->nest)) + if (!local_dec_and_test(&buffer->nest)) goto out; /* * Publish the known good head. Rely on the full barrier implied - * by atomic_dec_and_test() order the data->head read and this + * by atomic_dec_and_test() order the buffer->head read and this * write. */ - data->user_page->data_head = head; + buffer->user_page->data_head = head; /* * Now check if we missed an update, rely on the (compiler) - * barrier in atomic_dec_and_test() to re-read data->head. + * barrier in atomic_dec_and_test() to re-read buffer->head. */ - if (unlikely(head != local_read(&data->head))) { - local_inc(&data->nest); + if (unlikely(head != local_read(&buffer->head))) { + local_inc(&buffer->nest); goto again; } - if (handle->wakeup != local_read(&data->wakeup)) + if (handle->wakeup != local_read(&buffer->wakeup)) perf_output_wakeup(handle); out: @@ -3070,12 +3070,12 @@ __always_inline void perf_output_copy(struct perf_output_handle *handle, buf += size; handle->size -= size; if (!handle->size) { - struct perf_mmap_data *data = handle->data; + struct perf_buffer *buffer = handle->buffer; handle->page++; - handle->page &= data->nr_pages - 1; - handle->addr = data->data_pages[handle->page]; - handle->size = PAGE_SIZE << page_order(data); + handle->page &= buffer->nr_pages - 1; + handle->addr = buffer->data_pages[handle->page]; + handle->size = PAGE_SIZE << page_order(buffer); } } while (len); } @@ -3084,7 +3084,7 @@ int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size, int nmi, int sample) { - struct perf_mmap_data *data; + struct perf_buffer *buffer; unsigned long tail, offset, head; int have_lost; struct { @@ -3100,19 +3100,19 @@ int perf_output_begin(struct perf_output_handle *handle, if (event->parent) event = event->parent; - data = rcu_dereference(event->data); - if (!data) + buffer = rcu_dereference(event->buffer); + if (!buffer) goto out; - handle->data = data; + handle->buffer = buffer; handle->event = event; handle->nmi = nmi; handle->sample = sample; - if (!data->nr_pages) + if (!buffer->nr_pages) goto out; - have_lost = local_read(&data->lost); + have_lost = local_read(&buffer->lost); if (have_lost) size += sizeof(lost_event); @@ -3124,30 +3124,30 @@ int perf_output_begin(struct perf_output_handle *handle, * tail pointer. So that all reads will be completed before the * write is issued. */ - tail = ACCESS_ONCE(data->user_page->data_tail); + tail = ACCESS_ONCE(buffer->user_page->data_tail); smp_rmb(); - offset = head = local_read(&data->head); + offset = head = local_read(&buffer->head); head += size; - if (unlikely(!perf_output_space(data, tail, offset, head))) + if (unlikely(!perf_output_space(buffer, tail, offset, head))) goto fail; - } while (local_cmpxchg(&data->head, offset, head) != offset); + } while (local_cmpxchg(&buffer->head, offset, head) != offset); - if (head - local_read(&data->wakeup) > data->watermark) - local_add(data->watermark, &data->wakeup); + if (head - local_read(&buffer->wakeup) > buffer->watermark) + local_add(buffer->watermark, &buffer->wakeup); - handle->page = offset >> (PAGE_SHIFT + page_order(data)); - handle->page &= data->nr_pages - 1; - handle->size = offset & ((PAGE_SIZE << page_order(data)) - 1); - handle->addr = data->data_pages[handle->page]; + handle->page = offset >> (PAGE_SHIFT + page_order(buffer)); + handle->page &= buffer->nr_pages - 1; + handle->size = offset & ((PAGE_SIZE << page_order(buffer)) - 1); + handle->addr = buffer->data_pages[handle->page]; handle->addr += handle->size; - handle->size = (PAGE_SIZE << page_order(data)) - handle->size; + handle->size = (PAGE_SIZE << page_order(buffer)) - handle->size; if (have_lost) { lost_event.header.type = PERF_RECORD_LOST; lost_event.header.misc = 0; lost_event.header.size = sizeof(lost_event); lost_event.id = event->id; - lost_event.lost = local_xchg(&data->lost, 0); + lost_event.lost = local_xchg(&buffer->lost, 0); perf_output_put(handle, lost_event); } @@ -3155,7 +3155,7 @@ int perf_output_begin(struct perf_output_handle *handle, return 0; fail: - local_inc(&data->lost); + local_inc(&buffer->lost); perf_output_put_handle(handle); out: rcu_read_unlock(); @@ -3166,15 +3166,15 @@ out: void perf_output_end(struct perf_output_handle *handle) { struct perf_event *event = handle->event; - struct perf_mmap_data *data = handle->data; + struct perf_buffer *buffer = handle->buffer; int wakeup_events = event->attr.wakeup_events; if (handle->sample && wakeup_events) { - int events = local_inc_return(&data->events); + int events = local_inc_return(&buffer->events); if (events >= wakeup_events) { - local_sub(wakeup_events, &data->events); - local_inc(&data->wakeup); + local_sub(wakeup_events, &buffer->events); + local_inc(&buffer->wakeup); } } @@ -3211,7 +3211,7 @@ static void perf_output_read_one(struct perf_output_handle *handle, u64 values[4]; int n = 0; - values[n++] = atomic64_read(&event->count); + values[n++] = perf_event_count(event); if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { values[n++] = event->total_time_enabled + atomic64_read(&event->child_total_time_enabled); @@ -3248,7 +3248,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, if (leader != event) leader->pmu->read(leader); - values[n++] = atomic64_read(&leader->count); + values[n++] = perf_event_count(leader); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); @@ -3260,7 +3260,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, if (sub != event) sub->pmu->read(sub); - values[n++] = atomic64_read(&sub->count); + values[n++] = perf_event_count(sub); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); @@ -3491,7 +3491,7 @@ perf_event_read_event(struct perf_event *event, /* * task tracking -- fork/exit * - * enabled by: attr.comm | attr.mmap | attr.task + * enabled by: attr.comm | attr.mmap | attr.mmap_data | attr.task */ struct perf_task_event { @@ -3541,7 +3541,8 @@ static int perf_event_task_match(struct perf_event *event) if (event->cpu != -1 && event->cpu != smp_processor_id()) return 0; - if (event->attr.comm || event->attr.mmap || event->attr.task) + if (event->attr.comm || event->attr.mmap || + event->attr.mmap_data || event->attr.task) return 1; return 0; @@ -3766,7 +3767,8 @@ static void perf_event_mmap_output(struct perf_event *event, } static int perf_event_mmap_match(struct perf_event *event, - struct perf_mmap_event *mmap_event) + struct perf_mmap_event *mmap_event, + int executable) { if (event->state < PERF_EVENT_STATE_INACTIVE) return 0; @@ -3774,19 +3776,21 @@ static int perf_event_mmap_match(struct perf_event *event, if (event->cpu != -1 && event->cpu != smp_processor_id()) return 0; - if (event->attr.mmap) + if ((!executable && event->attr.mmap_data) || + (executable && event->attr.mmap)) return 1; return 0; } static void perf_event_mmap_ctx(struct perf_event_context *ctx, - struct perf_mmap_event *mmap_event) + struct perf_mmap_event *mmap_event, + int executable) { struct perf_event *event; list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { - if (perf_event_mmap_match(event, mmap_event)) + if (perf_event_mmap_match(event, mmap_event, executable)) perf_event_mmap_output(event, mmap_event); } } @@ -3830,6 +3834,14 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) if (!vma->vm_mm) { name = strncpy(tmp, "[vdso]", sizeof(tmp)); goto got_name; + } else if (vma->vm_start <= vma->vm_mm->start_brk && + vma->vm_end >= vma->vm_mm->brk) { + name = strncpy(tmp, "[heap]", sizeof(tmp)); + goto got_name; + } else if (vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack) { + name = strncpy(tmp, "[stack]", sizeof(tmp)); + goto got_name; } name = strncpy(tmp, "//anon", sizeof(tmp)); @@ -3846,17 +3858,17 @@ got_name: rcu_read_lock(); cpuctx = &get_cpu_var(perf_cpu_context); - perf_event_mmap_ctx(&cpuctx->ctx, mmap_event); + perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, vma->vm_flags & VM_EXEC); ctx = rcu_dereference(current->perf_event_ctxp); if (ctx) - perf_event_mmap_ctx(ctx, mmap_event); + perf_event_mmap_ctx(ctx, mmap_event, vma->vm_flags & VM_EXEC); put_cpu_var(perf_cpu_context); rcu_read_unlock(); kfree(buf); } -void __perf_event_mmap(struct vm_area_struct *vma) +void perf_event_mmap(struct vm_area_struct *vma) { struct perf_mmap_event mmap_event; @@ -4018,14 +4030,14 @@ static u64 perf_swevent_set_period(struct perf_event *event) hwc->last_period = hwc->sample_period; again: - old = val = atomic64_read(&hwc->period_left); + old = val = local64_read(&hwc->period_left); if (val < 0) return 0; nr = div64_u64(period + val, period); offset = nr * period; val -= offset; - if (atomic64_cmpxchg(&hwc->period_left, old, val) != old) + if (local64_cmpxchg(&hwc->period_left, old, val) != old) goto again; return nr; @@ -4064,7 +4076,7 @@ static void perf_swevent_add(struct perf_event *event, u64 nr, { struct hw_perf_event *hwc = &event->hw; - atomic64_add(nr, &event->count); + local64_add(nr, &event->count); if (!regs) return; @@ -4075,7 +4087,7 @@ static void perf_swevent_add(struct perf_event *event, u64 nr, if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq) return perf_swevent_overflow(event, 1, nmi, data, regs); - if (atomic64_add_negative(nr, &hwc->period_left)) + if (local64_add_negative(nr, &hwc->period_left)) return; perf_swevent_overflow(event, 0, nmi, data, regs); @@ -4213,14 +4225,12 @@ int perf_swevent_get_recursion_context(void) } EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context); -void perf_swevent_put_recursion_context(int rctx) +void inline perf_swevent_put_recursion_context(int rctx) { struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context); barrier(); cpuctx->recursion[rctx]--; } -EXPORT_SYMBOL_GPL(perf_swevent_put_recursion_context); - void __perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) @@ -4368,8 +4378,8 @@ static void cpu_clock_perf_event_update(struct perf_event *event) u64 now; now = cpu_clock(cpu); - prev = atomic64_xchg(&event->hw.prev_count, now); - atomic64_add(now - prev, &event->count); + prev = local64_xchg(&event->hw.prev_count, now); + local64_add(now - prev, &event->count); } static int cpu_clock_perf_event_enable(struct perf_event *event) @@ -4377,7 +4387,7 @@ static int cpu_clock_perf_event_enable(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; int cpu = raw_smp_processor_id(); - atomic64_set(&hwc->prev_count, cpu_clock(cpu)); + local64_set(&hwc->prev_count, cpu_clock(cpu)); perf_swevent_start_hrtimer(event); return 0; @@ -4409,9 +4419,9 @@ static void task_clock_perf_event_update(struct perf_event *event, u64 now) u64 prev; s64 delta; - prev = atomic64_xchg(&event->hw.prev_count, now); + prev = local64_xchg(&event->hw.prev_count, now); delta = now - prev; - atomic64_add(delta, &event->count); + local64_add(delta, &event->count); } static int task_clock_perf_event_enable(struct perf_event *event) @@ -4421,7 +4431,7 @@ static int task_clock_perf_event_enable(struct perf_event *event) now = event->ctx->time; - atomic64_set(&hwc->prev_count, now); + local64_set(&hwc->prev_count, now); perf_swevent_start_hrtimer(event); @@ -4601,7 +4611,7 @@ static int perf_tp_event_match(struct perf_event *event, } void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, - struct pt_regs *regs, struct hlist_head *head) + struct pt_regs *regs, struct hlist_head *head, int rctx) { struct perf_sample_data data; struct perf_event *event; @@ -4615,12 +4625,12 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, perf_sample_data_init(&data, addr); data.raw = &raw; - rcu_read_lock(); hlist_for_each_entry_rcu(event, node, head, hlist_entry) { if (perf_tp_event_match(event, &data, regs)) perf_swevent_add(event, count, 1, &data, regs); } - rcu_read_unlock(); + + perf_swevent_put_recursion_context(rctx); } EXPORT_SYMBOL_GPL(perf_tp_event); @@ -4864,7 +4874,7 @@ perf_event_alloc(struct perf_event_attr *attr, hwc->sample_period = 1; hwc->last_period = hwc->sample_period; - atomic64_set(&hwc->period_left, hwc->sample_period); + local64_set(&hwc->period_left, hwc->sample_period); /* * we currently do not support PERF_FORMAT_GROUP on inherited events @@ -4913,7 +4923,7 @@ done: if (!event->parent) { atomic_inc(&nr_events); - if (event->attr.mmap) + if (event->attr.mmap || event->attr.mmap_data) atomic_inc(&nr_mmap_events); if (event->attr.comm) atomic_inc(&nr_comm_events); @@ -5007,7 +5017,7 @@ err_size: static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event) { - struct perf_mmap_data *data = NULL, *old_data = NULL; + struct perf_buffer *buffer = NULL, *old_buffer = NULL; int ret = -EINVAL; if (!output_event) @@ -5037,19 +5047,19 @@ set: if (output_event) { /* get the buffer we want to redirect to */ - data = perf_mmap_data_get(output_event); - if (!data) + buffer = perf_buffer_get(output_event); + if (!buffer) goto unlock; } - old_data = event->data; - rcu_assign_pointer(event->data, data); + old_buffer = event->buffer; + rcu_assign_pointer(event->buffer, buffer); ret = 0; unlock: mutex_unlock(&event->mmap_mutex); - if (old_data) - perf_mmap_data_put(old_data); + if (old_buffer) + perf_buffer_put(old_buffer); out: return ret; } @@ -5298,7 +5308,7 @@ inherit_event(struct perf_event *parent_event, hwc->sample_period = sample_period; hwc->last_period = sample_period; - atomic64_set(&hwc->period_left, sample_period); + local64_set(&hwc->period_left, sample_period); } child_event->overflow_handler = parent_event->overflow_handler; @@ -5359,12 +5369,12 @@ static void sync_child_event(struct perf_event *child_event, if (child_event->attr.inherit_stat) perf_event_read_event(child_event, child); - child_val = atomic64_read(&child_event->count); + child_val = perf_event_count(child_event); /* * Add back the child's count to the parent's count: */ - atomic64_add(child_val, &parent_event->count); + atomic64_add(child_val, &parent_event->child_count); atomic64_add(child_event->total_time_enabled, &parent_event->child_total_time_enabled); atomic64_add(child_event->total_time_running, diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 9829646d399..f66bdd33a6c 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -232,31 +232,24 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) { - struct sighand_struct *sighand; - struct signal_struct *sig; + struct signal_struct *sig = tsk->signal; struct task_struct *t; - *times = INIT_CPUTIME; + times->utime = sig->utime; + times->stime = sig->stime; + times->sum_exec_runtime = sig->sum_sched_runtime; rcu_read_lock(); - sighand = rcu_dereference(tsk->sighand); - if (!sighand) + /* make sure we can trust tsk->thread_group list */ + if (!likely(pid_alive(tsk))) goto out; - sig = tsk->signal; - t = tsk; do { times->utime = cputime_add(times->utime, t->utime); times->stime = cputime_add(times->stime, t->stime); times->sum_exec_runtime += t->se.sum_exec_runtime; - - t = next_thread(t); - } while (t != tsk); - - times->utime = cputime_add(times->utime, sig->utime); - times->stime = cputime_add(times->stime, sig->stime); - times->sum_exec_runtime += sig->sum_sched_runtime; + } while_each_thread(tsk, t); out: rcu_read_unlock(); } @@ -1279,10 +1272,6 @@ static inline int fastpath_timer_check(struct task_struct *tsk) { struct signal_struct *sig; - /* tsk == current, ensure it is safe to use ->signal/sighand */ - if (unlikely(tsk->exit_state)) - return 0; - if (!task_cputime_zero(&tsk->cputime_expires)) { struct task_cputime task_sample = { .utime = tsk->utime, @@ -1298,7 +1287,10 @@ static inline int fastpath_timer_check(struct task_struct *tsk) if (sig->cputimer.running) { struct task_cputime group_sample; - thread_group_cputimer(tsk, &group_sample); + spin_lock(&sig->cputimer.lock); + group_sample = sig->cputimer.cputime; + spin_unlock(&sig->cputimer.lock); + if (task_cputime_expired(&group_sample, &sig->cputime_expires)) return 1; } @@ -1315,6 +1307,7 @@ void run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; + unsigned long flags; BUG_ON(!irqs_disabled()); @@ -1325,7 +1318,8 @@ void run_posix_cpu_timers(struct task_struct *tsk) if (!fastpath_timer_check(tsk)) return; - spin_lock(&tsk->sighand->siglock); + if (!lock_task_sighand(tsk, &flags)) + return; /* * Here we take off tsk->signal->cpu_timers[N] and * tsk->cpu_timers[N] all the timers that are firing, and @@ -1347,7 +1341,7 @@ void run_posix_cpu_timers(struct task_struct *tsk) * that gets the timer lock before we do will give it up and * spin until we've taken care of that timer below. */ - spin_unlock(&tsk->sighand->siglock); + unlock_task_sighand(tsk, &flags); /* * Now that all the timers on our list have the firing flag, diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 72a8dc9567f..4d169835fb3 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -114,3 +114,163 @@ int rcu_my_thread_group_empty(void) } EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty); #endif /* #ifdef CONFIG_PROVE_RCU */ + +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +static inline void debug_init_rcu_head(struct rcu_head *head) +{ + debug_object_init(head, &rcuhead_debug_descr); +} + +static inline void debug_rcu_head_free(struct rcu_head *head) +{ + debug_object_free(head, &rcuhead_debug_descr); +} + +/* + * fixup_init is called when: + * - an active object is initialized + */ +static int rcuhead_fixup_init(void *addr, enum debug_obj_state state) +{ + struct rcu_head *head = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + /* + * Ensure that queued callbacks are all executed. + * If we detect that we are nested in a RCU read-side critical + * section, we should simply fail, otherwise we would deadlock. + */ + if (rcu_preempt_depth() != 0 || preempt_count() != 0 || + irqs_disabled()) { + WARN_ON(1); + return 0; + } + rcu_barrier(); + rcu_barrier_sched(); + rcu_barrier_bh(); + debug_object_init(head, &rcuhead_debug_descr); + return 1; + default: + return 0; + } +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown object is activated (might be a statically initialized object) + * Activation is performed internally by call_rcu(). + */ +static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state) +{ + struct rcu_head *head = addr; + + switch (state) { + + case ODEBUG_STATE_NOTAVAILABLE: + /* + * This is not really a fixup. We just make sure that it is + * tracked in the object tracker. + */ + debug_object_init(head, &rcuhead_debug_descr); + debug_object_activate(head, &rcuhead_debug_descr); + return 0; + + case ODEBUG_STATE_ACTIVE: + /* + * Ensure that queued callbacks are all executed. + * If we detect that we are nested in a RCU read-side critical + * section, we should simply fail, otherwise we would deadlock. + */ + if (rcu_preempt_depth() != 0 || preempt_count() != 0 || + irqs_disabled()) { + WARN_ON(1); + return 0; + } + rcu_barrier(); + rcu_barrier_sched(); + rcu_barrier_bh(); + debug_object_activate(head, &rcuhead_debug_descr); + return 1; + default: + return 0; + } +} + +/* + * fixup_free is called when: + * - an active object is freed + */ +static int rcuhead_fixup_free(void *addr, enum debug_obj_state state) +{ + struct rcu_head *head = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + /* + * Ensure that queued callbacks are all executed. + * If we detect that we are nested in a RCU read-side critical + * section, we should simply fail, otherwise we would deadlock. + */ +#ifndef CONFIG_PREEMPT + WARN_ON(1); + return 0; +#else + if (rcu_preempt_depth() != 0 || preempt_count() != 0 || + irqs_disabled()) { + WARN_ON(1); + return 0; + } + rcu_barrier(); + rcu_barrier_sched(); + rcu_barrier_bh(); + debug_object_free(head, &rcuhead_debug_descr); + return 1; +#endif + default: + return 0; + } +} + +/** + * init_rcu_head_on_stack() - initialize on-stack rcu_head for debugobjects + * @head: pointer to rcu_head structure to be initialized + * + * This function informs debugobjects of a new rcu_head structure that + * has been allocated as an auto variable on the stack. This function + * is not required for rcu_head structures that are statically defined or + * that are dynamically allocated on the heap. This function has no + * effect for !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds. + */ +void init_rcu_head_on_stack(struct rcu_head *head) +{ + debug_object_init_on_stack(head, &rcuhead_debug_descr); +} +EXPORT_SYMBOL_GPL(init_rcu_head_on_stack); + +/** + * destroy_rcu_head_on_stack() - destroy on-stack rcu_head for debugobjects + * @head: pointer to rcu_head structure to be initialized + * + * This function informs debugobjects that an on-stack rcu_head structure + * is about to go out of scope. As with init_rcu_head_on_stack(), this + * function is not required for rcu_head structures that are statically + * defined or that are dynamically allocated on the heap. Also as with + * init_rcu_head_on_stack(), this function has no effect for + * !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds. + */ +void destroy_rcu_head_on_stack(struct rcu_head *head) +{ + debug_object_free(head, &rcuhead_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack); + +struct debug_obj_descr rcuhead_debug_descr = { + .name = "rcu_head", + .fixup_init = rcuhead_fixup_init, + .fixup_activate = rcuhead_fixup_activate, + .fixup_free = rcuhead_fixup_free, +}; +EXPORT_SYMBOL_GPL(rcuhead_debug_descr); +#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 38729d3cd23..196ec02f8be 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -169,6 +169,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) while (list) { next = list->next; prefetch(next); + debug_rcu_head_unqueue(list); list->func(list); list = next; } @@ -211,6 +212,7 @@ static void __call_rcu(struct rcu_head *head, { unsigned long flags; + debug_rcu_head_queue(head); head->func = func; head->next = NULL; diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 6535ac8bc6a..2e2726d790b 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -239,8 +239,7 @@ static unsigned long rcu_random(struct rcu_random_state *rrsp) { if (--rrsp->rrs_count < 0) { - rrsp->rrs_state += - (unsigned long)cpu_clock(raw_smp_processor_id()); + rrsp->rrs_state += (unsigned long)local_clock(); rrsp->rrs_count = RCU_RANDOM_REFRESH; } rrsp->rrs_state = rrsp->rrs_state * RCU_RANDOM_MULT + RCU_RANDOM_ADD; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index d4437345706..d5bc43976c5 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1112,6 +1112,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) while (list) { next = list->next; prefetch(next); + debug_rcu_head_unqueue(list); list->func(list); list = next; if (++count >= rdp->blimit) @@ -1388,6 +1389,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), unsigned long flags; struct rcu_data *rdp; + debug_rcu_head_queue(head); head->func = func; head->next = NULL; diff --git a/kernel/sched.c b/kernel/sched.c index f52a8801b7a..41541d79e3c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -77,6 +77,7 @@ #include <asm/irq_regs.h> #include "sched_cpupri.h" +#include "workqueue_sched.h" #define CREATE_TRACE_POINTS #include <trace/events/sched.h> @@ -456,9 +457,10 @@ struct rq { unsigned long nr_running; #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; + unsigned long last_load_update_tick; #ifdef CONFIG_NO_HZ u64 nohz_stamp; - unsigned char in_nohz_recently; + unsigned char nohz_balance_kick; #endif unsigned int skip_clock_update; @@ -1193,6 +1195,27 @@ static void resched_cpu(int cpu) #ifdef CONFIG_NO_HZ /* + * In the semi idle case, use the nearest busy cpu for migrating timers + * from an idle cpu. This is good for power-savings. + * + * We don't do similar optimization for completely idle system, as + * selecting an idle cpu will add more delays to the timers than intended + * (as that cpu's timer base may not be uptodate wrt jiffies etc). + */ +int get_nohz_timer_target(void) +{ + int cpu = smp_processor_id(); + int i; + struct sched_domain *sd; + + for_each_domain(cpu, sd) { + for_each_cpu(i, sched_domain_span(sd)) + if (!idle_cpu(i)) + return i; + } + return cpu; +} +/* * When add_timer_on() enqueues a timer into the timer wheel of an * idle CPU then this timer might expire before the next timer event * which is scheduled to wake up that CPU. In case of a completely @@ -1232,16 +1255,6 @@ void wake_up_idle_cpu(int cpu) smp_send_reschedule(cpu); } -int nohz_ratelimit(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - u64 diff = rq->clock - rq->nohz_stamp; - - rq->nohz_stamp = rq->clock; - - return diff < (NSEC_PER_SEC / HZ) >> 1; -} - #endif /* CONFIG_NO_HZ */ static u64 sched_avg_period(void) @@ -1652,7 +1665,7 @@ static void update_shares(struct sched_domain *sd) if (root_task_group_empty()) return; - now = cpu_clock(raw_smp_processor_id()); + now = local_clock(); elapsed = now - sd->last_update; if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { @@ -1805,6 +1818,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) static void calc_load_account_idle(struct rq *this_rq); static void update_sysctl(void); static int get_update_sysctl_factor(void); +static void update_cpu_load(struct rq *this_rq); static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) { @@ -2267,11 +2281,55 @@ static void update_avg(u64 *avg, u64 sample) } #endif -/*** +static inline void ttwu_activate(struct task_struct *p, struct rq *rq, + bool is_sync, bool is_migrate, bool is_local, + unsigned long en_flags) +{ + schedstat_inc(p, se.statistics.nr_wakeups); + if (is_sync) + schedstat_inc(p, se.statistics.nr_wakeups_sync); + if (is_migrate) + schedstat_inc(p, se.statistics.nr_wakeups_migrate); + if (is_local) + schedstat_inc(p, se.statistics.nr_wakeups_local); + else + schedstat_inc(p, se.statistics.nr_wakeups_remote); + + activate_task(rq, p, en_flags); +} + +static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, + int wake_flags, bool success) +{ + trace_sched_wakeup(p, success); + check_preempt_curr(rq, p, wake_flags); + + p->state = TASK_RUNNING; +#ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); + + if (unlikely(rq->idle_stamp)) { + u64 delta = rq->clock - rq->idle_stamp; + u64 max = 2*sysctl_sched_migration_cost; + + if (delta > max) + rq->avg_idle = max; + else + update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; + } +#endif + /* if a worker is waking up, notify workqueue */ + if ((p->flags & PF_WQ_WORKER) && success) + wq_worker_waking_up(p, cpu_of(rq)); +} + +/** * try_to_wake_up - wake up a thread - * @p: the to-be-woken-up thread + * @p: the thread to be awakened * @state: the mask of task states that can be woken - * @sync: do a synchronous wakeup? + * @wake_flags: wake modifier flags (WF_*) * * Put it on the run-queue if it's not already there. The "current" * thread is always on the run-queue (except when the actual @@ -2279,7 +2337,8 @@ static void update_avg(u64 *avg, u64 sample) * the simpler "current->state = TASK_RUNNING" to mark yourself * runnable without the overhead of this. * - * returns failure only if the task is already active. + * Returns %true if @p was woken up, %false if it was already running + * or @state didn't match @p's state. */ static int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) @@ -2359,38 +2418,11 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, out_activate: #endif /* CONFIG_SMP */ - schedstat_inc(p, se.statistics.nr_wakeups); - if (wake_flags & WF_SYNC) - schedstat_inc(p, se.statistics.nr_wakeups_sync); - if (orig_cpu != cpu) - schedstat_inc(p, se.statistics.nr_wakeups_migrate); - if (cpu == this_cpu) - schedstat_inc(p, se.statistics.nr_wakeups_local); - else - schedstat_inc(p, se.statistics.nr_wakeups_remote); - activate_task(rq, p, en_flags); + ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu, + cpu == this_cpu, en_flags); success = 1; - out_running: - trace_sched_wakeup(p, success); - check_preempt_curr(rq, p, wake_flags); - - p->state = TASK_RUNNING; -#ifdef CONFIG_SMP - if (p->sched_class->task_woken) - p->sched_class->task_woken(rq, p); - - if (unlikely(rq->idle_stamp)) { - u64 delta = rq->clock - rq->idle_stamp; - u64 max = 2*sysctl_sched_migration_cost; - - if (delta > max) - rq->avg_idle = max; - else - update_avg(&rq->avg_idle, delta); - rq->idle_stamp = 0; - } -#endif + ttwu_post_activation(p, rq, wake_flags, success); out: task_rq_unlock(rq, &flags); put_cpu(); @@ -2399,6 +2431,37 @@ out: } /** + * try_to_wake_up_local - try to wake up a local task with rq lock held + * @p: the thread to be awakened + * + * Put @p on the run-queue if it's not alredy there. The caller must + * ensure that this_rq() is locked, @p is bound to this_rq() and not + * the current task. this_rq() stays locked over invocation. + */ +static void try_to_wake_up_local(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + bool success = false; + + BUG_ON(rq != this_rq()); + BUG_ON(p == current); + lockdep_assert_held(&rq->lock); + + if (!(p->state & TASK_NORMAL)) + return; + + if (!p->se.on_rq) { + if (likely(!task_running(rq, p))) { + schedstat_inc(rq, ttwu_count); + schedstat_inc(rq, ttwu_local); + } + ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP); + success = true; + } + ttwu_post_activation(p, rq, 0, success); +} + +/** * wake_up_process - Wake up a specific process * @p: The process to be woken up. * @@ -3012,23 +3075,102 @@ static void calc_load_account_active(struct rq *this_rq) } /* + * The exact cpuload at various idx values, calculated at every tick would be + * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load + * + * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called + * on nth tick when cpu may be busy, then we have: + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load + * + * decay_load_missed() below does efficient calculation of + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load + * + * The calculation is approximated on a 128 point scale. + * degrade_zero_ticks is the number of ticks after which load at any + * particular idx is approximated to be zero. + * degrade_factor is a precomputed table, a row for each load idx. + * Each column corresponds to degradation factor for a power of two ticks, + * based on 128 point scale. + * Example: + * row 2, col 3 (=12) says that the degradation at load idx 2 after + * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). + * + * With this power of 2 load factors, we can degrade the load n times + * by looking at 1 bits in n and doing as many mult/shift instead of + * n mult/shifts needed by the exact degradation. + */ +#define DEGRADE_SHIFT 7 +static const unsigned char + degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; +static const unsigned char + degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { + {0, 0, 0, 0, 0, 0, 0, 0}, + {64, 32, 8, 0, 0, 0, 0, 0}, + {96, 72, 40, 12, 1, 0, 0}, + {112, 98, 75, 43, 15, 1, 0}, + {120, 112, 98, 76, 45, 16, 2} }; + +/* + * Update cpu_load for any missed ticks, due to tickless idle. The backlog + * would be when CPU is idle and so we just decay the old load without + * adding any new load. + */ +static unsigned long +decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) +{ + int j = 0; + + if (!missed_updates) + return load; + + if (missed_updates >= degrade_zero_ticks[idx]) + return 0; + + if (idx == 1) + return load >> missed_updates; + + while (missed_updates) { + if (missed_updates % 2) + load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; + + missed_updates >>= 1; + j++; + } + return load; +} + +/* * Update rq->cpu_load[] statistics. This function is usually called every - * scheduler tick (TICK_NSEC). + * scheduler tick (TICK_NSEC). With tickless idle this will not be called + * every tick. We fix it up based on jiffies. */ static void update_cpu_load(struct rq *this_rq) { unsigned long this_load = this_rq->load.weight; + unsigned long curr_jiffies = jiffies; + unsigned long pending_updates; int i, scale; this_rq->nr_load_updates++; + /* Avoid repeated calls on same jiffy, when moving in and out of idle */ + if (curr_jiffies == this_rq->last_load_update_tick) + return; + + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + this_rq->last_load_update_tick = curr_jiffies; + /* Update our load: */ - for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { + this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ + for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { unsigned long old_load, new_load; /* scale is effectively 1 << i now, and >> i divides by scale */ old_load = this_rq->cpu_load[i]; + old_load = decay_load_missed(old_load, pending_updates - 1, i); new_load = this_load; /* * Round up the averaging division if load is increasing. This @@ -3036,9 +3178,15 @@ static void update_cpu_load(struct rq *this_rq) * example. */ if (new_load > old_load) - new_load += scale-1; - this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; + new_load += scale - 1; + + this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; } +} + +static void update_cpu_load_active(struct rq *this_rq) +{ + update_cpu_load(this_rq); calc_load_account_active(this_rq); } @@ -3426,7 +3574,7 @@ void scheduler_tick(void) raw_spin_lock(&rq->lock); update_rq_clock(rq); - update_cpu_load(rq); + update_cpu_load_active(rq); curr->sched_class->task_tick(rq, curr, 0); raw_spin_unlock(&rq->lock); @@ -3598,7 +3746,6 @@ need_resched: rq = cpu_rq(cpu); rcu_note_context_switch(cpu); prev = rq->curr; - switch_count = &prev->nivcsw; release_kernel_lock(prev); need_resched_nonpreemptible: @@ -3611,11 +3758,26 @@ need_resched_nonpreemptible: raw_spin_lock_irq(&rq->lock); clear_tsk_need_resched(prev); + switch_count = &prev->nivcsw; if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { - if (unlikely(signal_pending_state(prev->state, prev))) + if (unlikely(signal_pending_state(prev->state, prev))) { prev->state = TASK_RUNNING; - else + } else { + /* + * If a worker is going to sleep, notify and + * ask workqueue whether it wants to wake up a + * task to maintain concurrency. If so, wake + * up the task. + */ + if (prev->flags & PF_WQ_WORKER) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev, cpu); + if (to_wakeup) + try_to_wake_up_local(to_wakeup); + } deactivate_task(rq, prev, DEQUEUE_SLEEP); + } switch_count = &prev->nvcsw; } @@ -3637,8 +3799,10 @@ need_resched_nonpreemptible: context_switch(rq, prev, next); /* unlocks the rq */ /* - * the context switch might have flipped the stack from under - * us, hence refresh the local variables. + * The context switch have flipped the stack from under us + * and restored the local variables which were saved when + * this task called schedule() in the past. prev == current + * is still correct, but it can be moved to another cpu/rq. */ cpu = smp_processor_id(); rq = cpu_rq(cpu); @@ -3647,11 +3811,8 @@ need_resched_nonpreemptible: post_schedule(rq); - if (unlikely(reacquire_kernel_lock(current) < 0)) { - prev = rq->curr; - switch_count = &prev->nivcsw; + if (unlikely(reacquire_kernel_lock(prev))) goto need_resched_nonpreemptible; - } preempt_enable_no_resched(); if (need_resched()) @@ -3726,7 +3887,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) * off of preempt_enable. Kernel preemptions off return from interrupt * occur there and call schedule directly. */ -asmlinkage void __sched preempt_schedule(void) +asmlinkage void __sched notrace preempt_schedule(void) { struct thread_info *ti = current_thread_info(); @@ -3738,9 +3899,9 @@ asmlinkage void __sched preempt_schedule(void) return; do { - add_preempt_count(PREEMPT_ACTIVE); + add_preempt_count_notrace(PREEMPT_ACTIVE); schedule(); - sub_preempt_count(PREEMPT_ACTIVE); + sub_preempt_count_notrace(PREEMPT_ACTIVE); /* * Check again in case we missed a preemption opportunity @@ -4441,12 +4602,8 @@ recheck: */ if (user && !capable(CAP_SYS_NICE)) { if (rt_policy(policy)) { - unsigned long rlim_rtprio; - - if (!lock_task_sighand(p, &flags)) - return -ESRCH; - rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); - unlock_task_sighand(p, &flags); + unsigned long rlim_rtprio = + task_rlimit(p, RLIMIT_RTPRIO); /* can't set/change the rt policy */ if (policy != p->policy && !rlim_rtprio) @@ -5816,20 +5973,49 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) */ static struct notifier_block __cpuinitdata migration_notifier = { .notifier_call = migration_call, - .priority = 10 + .priority = CPU_PRI_MIGRATION, }; +static int __cpuinit sched_cpu_active(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + set_cpu_active((long)hcpu, true); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + set_cpu_active((long)hcpu, false); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + static int __init migration_init(void) { void *cpu = (void *)(long)smp_processor_id(); int err; - /* Start one for the boot CPU: */ + /* Initialize migration for the boot CPU */ err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); BUG_ON(err == NOTIFY_BAD); migration_call(&migration_notifier, CPU_ONLINE, cpu); register_cpu_notifier(&migration_notifier); + /* Register cpu active notifiers */ + cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); + cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); + return 0; } early_initcall(migration_init); @@ -6064,23 +6250,18 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) free_rootdomain(old_rd); } -static int init_rootdomain(struct root_domain *rd, bool bootmem) +static int init_rootdomain(struct root_domain *rd) { - gfp_t gfp = GFP_KERNEL; - memset(rd, 0, sizeof(*rd)); - if (bootmem) - gfp = GFP_NOWAIT; - - if (!alloc_cpumask_var(&rd->span, gfp)) + if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) goto out; - if (!alloc_cpumask_var(&rd->online, gfp)) + if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) goto free_span; - if (!alloc_cpumask_var(&rd->rto_mask, gfp)) + if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) goto free_online; - if (cpupri_init(&rd->cpupri, bootmem) != 0) + if (cpupri_init(&rd->cpupri) != 0) goto free_rto_mask; return 0; @@ -6096,7 +6277,7 @@ out: static void init_defrootdomain(void) { - init_rootdomain(&def_root_domain, true); + init_rootdomain(&def_root_domain); atomic_set(&def_root_domain.refcount, 1); } @@ -6109,7 +6290,7 @@ static struct root_domain *alloc_rootdomain(void) if (!rd) return NULL; - if (init_rootdomain(rd, false) != 0) { + if (init_rootdomain(rd) != 0) { kfree(rd); return NULL; } @@ -7288,29 +7469,35 @@ int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) } #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -#ifndef CONFIG_CPUSETS /* - * Add online and remove offline CPUs from the scheduler domains. - * When cpusets are enabled they take over this function. + * Update cpusets according to cpu_active mask. If cpusets are + * disabled, cpuset_update_active_cpus() becomes a simple wrapper + * around partition_sched_domains(). */ -static int update_sched_domains(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, + void *hcpu) { - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - partition_sched_domains(1, NULL, NULL); + cpuset_update_active_cpus(); return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} +static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + cpuset_update_active_cpus(); + return NOTIFY_OK; default: return NOTIFY_DONE; } } -#endif static int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu) @@ -7356,10 +7543,8 @@ void __init sched_init_smp(void) mutex_unlock(&sched_domains_mutex); put_online_cpus(); -#ifndef CONFIG_CPUSETS - /* XXX: Theoretical race here - CPU may be hotplugged now */ - hotcpu_notifier(update_sched_domains, 0); -#endif + hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); + hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); /* RT runtime code needs to handle some hotplug events */ hotcpu_notifier(update_runtime, 0); @@ -7604,6 +7789,9 @@ void __init sched_init(void) for (j = 0; j < CPU_LOAD_IDX_MAX; j++) rq->cpu_load[j] = 0; + + rq->last_load_update_tick = jiffies; + #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; @@ -7617,6 +7805,10 @@ void __init sched_init(void) rq->idle_stamp = 0; rq->avg_idle = 2*sysctl_sched_migration_cost; rq_attach_root(rq, &def_root_domain); +#ifdef CONFIG_NO_HZ + rq->nohz_balance_kick = 0; + init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i)); +#endif #endif init_rq_hrtick(rq); atomic_set(&rq->nr_iowait, 0); @@ -7661,8 +7853,11 @@ void __init sched_init(void) zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); #ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ - zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); - alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT); + zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); + alloc_cpumask_var(&nohz.grp_idle_mask, GFP_NOWAIT); + atomic_set(&nohz.load_balancer, nr_cpu_ids); + atomic_set(&nohz.first_pick_cpu, nr_cpu_ids); + atomic_set(&nohz.second_pick_cpu, nr_cpu_ids); #endif /* May be allocated at isolcpus cmdline parse time */ if (cpu_isolated_map == NULL) diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index 906a0f718cb..52f1a149bfb 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -10,19 +10,55 @@ * Ingo Molnar <mingo@redhat.com> * Guillaume Chazarain <guichaz@gmail.com> * - * Create a semi stable clock from a mixture of other events, including: - * - gtod + * + * What: + * + * cpu_clock(i) provides a fast (execution time) high resolution + * clock with bounded drift between CPUs. The value of cpu_clock(i) + * is monotonic for constant i. The timestamp returned is in nanoseconds. + * + * ######################### BIG FAT WARNING ########################## + * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # + * # go backwards !! # + * #################################################################### + * + * There is no strict promise about the base, although it tends to start + * at 0 on boot (but people really shouldn't rely on that). + * + * cpu_clock(i) -- can be used from any context, including NMI. + * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI) + * local_clock() -- is cpu_clock() on the current cpu. + * + * How: + * + * The implementation either uses sched_clock() when + * !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK, which means in that case the + * sched_clock() is assumed to provide these properties (mostly it means + * the architecture provides a globally synchronized highres time source). + * + * Otherwise it tries to create a semi stable clock from a mixture of other + * clocks, including: + * + * - GTOD (clock monotomic) * - sched_clock() * - explicit idle events * - * We use gtod as base and the unstable clock deltas. The deltas are filtered, - * making it monotonic and keeping it within an expected window. + * We use GTOD as base and use sched_clock() deltas to improve resolution. The + * deltas are filtered to provide monotonicity and keeping it within an + * expected window. * * Furthermore, explicit sleep and wakeup hooks allow us to account for time * that is otherwise invisible (TSC gets stopped). * - * The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat - * consistent between cpus (never more than 2 jiffies difference). + * + * Notes: + * + * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things + * like cpufreq interrupts that can change the base clock (TSC) multiplier + * and cause funny jumps in time -- although the filtering provided by + * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it + * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on + * sched_clock(). */ #include <linux/spinlock.h> #include <linux/hardirq.h> @@ -170,6 +206,11 @@ again: return val; } +/* + * Similar to cpu_clock(), but requires local IRQs to be disabled. + * + * See cpu_clock(). + */ u64 sched_clock_cpu(int cpu) { struct sched_clock_data *scd; @@ -237,9 +278,19 @@ void sched_clock_idle_wakeup_event(u64 delta_ns) } EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); -unsigned long long cpu_clock(int cpu) +/* + * As outlined at the top, provides a fast, high resolution, nanosecond + * time source that is monotonic per cpu argument and has bounded drift + * between cpus. + * + * ######################### BIG FAT WARNING ########################## + * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # + * # go backwards !! # + * #################################################################### + */ +u64 cpu_clock(int cpu) { - unsigned long long clock; + u64 clock; unsigned long flags; local_irq_save(flags); @@ -249,6 +300,25 @@ unsigned long long cpu_clock(int cpu) return clock; } +/* + * Similar to cpu_clock() for the current cpu. Time will only be observed + * to be monotonic if care is taken to only compare timestampt taken on the + * same CPU. + * + * See cpu_clock(). + */ +u64 local_clock(void) +{ + u64 clock; + unsigned long flags; + + local_irq_save(flags); + clock = sched_clock_cpu(smp_processor_id()); + local_irq_restore(flags); + + return clock; +} + #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ void sched_clock_init(void) @@ -264,12 +334,17 @@ u64 sched_clock_cpu(int cpu) return sched_clock(); } - -unsigned long long cpu_clock(int cpu) +u64 cpu_clock(int cpu) { return sched_clock_cpu(cpu); } +u64 local_clock(void) +{ + return sched_clock_cpu(0); +} + #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ EXPORT_SYMBOL_GPL(cpu_clock); +EXPORT_SYMBOL_GPL(local_clock); diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c index e6871cb3fc8..2722dc1b413 100644 --- a/kernel/sched_cpupri.c +++ b/kernel/sched_cpupri.c @@ -166,14 +166,10 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) * * Returns: -ENOMEM if memory fails. */ -int cpupri_init(struct cpupri *cp, bool bootmem) +int cpupri_init(struct cpupri *cp) { - gfp_t gfp = GFP_KERNEL; int i; - if (bootmem) - gfp = GFP_NOWAIT; - memset(cp, 0, sizeof(*cp)); for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) { @@ -181,7 +177,7 @@ int cpupri_init(struct cpupri *cp, bool bootmem) raw_spin_lock_init(&vec->lock); vec->count = 0; - if (!zalloc_cpumask_var(&vec->mask, gfp)) + if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL)) goto cleanup; } diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h index 7cb5bb6b95b..9fc7d386fea 100644 --- a/kernel/sched_cpupri.h +++ b/kernel/sched_cpupri.h @@ -27,7 +27,7 @@ struct cpupri { int cpupri_find(struct cpupri *cp, struct task_struct *p, struct cpumask *lowest_mask); void cpupri_set(struct cpupri *cp, int cpu, int pri); -int cpupri_init(struct cpupri *cp, bool bootmem); +int cpupri_init(struct cpupri *cp); void cpupri_cleanup(struct cpupri *cp); #else #define cpupri_set(cp, cpu, pri) do { } while (0) diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 35565395d00..2e1b0d17dd9 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -332,7 +332,7 @@ static int sched_debug_show(struct seq_file *m, void *v) PN(sysctl_sched_latency); PN(sysctl_sched_min_granularity); PN(sysctl_sched_wakeup_granularity); - PN(sysctl_sched_child_runs_first); + P(sysctl_sched_child_runs_first); P(sysctl_sched_features); #undef PN #undef P diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a878b5332da..806d1b227a2 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -2287,13 +2287,6 @@ static void update_cpu_power(struct sched_domain *sd, int cpu) unsigned long power = SCHED_LOAD_SCALE; struct sched_group *sdg = sd->groups; - if (sched_feat(ARCH_POWER)) - power *= arch_scale_freq_power(sd, cpu); - else - power *= default_scale_freq_power(sd, cpu); - - power >>= SCHED_LOAD_SHIFT; - if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { if (sched_feat(ARCH_POWER)) power *= arch_scale_smt_power(sd, cpu); @@ -2303,6 +2296,15 @@ static void update_cpu_power(struct sched_domain *sd, int cpu) power >>= SCHED_LOAD_SHIFT; } + sdg->cpu_power_orig = power; + + if (sched_feat(ARCH_POWER)) + power *= arch_scale_freq_power(sd, cpu); + else + power *= default_scale_freq_power(sd, cpu); + + power >>= SCHED_LOAD_SHIFT; + power *= scale_rt_power(cpu); power >>= SCHED_LOAD_SHIFT; @@ -2335,6 +2337,31 @@ static void update_group_power(struct sched_domain *sd, int cpu) sdg->cpu_power = power; } +/* + * Try and fix up capacity for tiny siblings, this is needed when + * things like SD_ASYM_PACKING need f_b_g to select another sibling + * which on its own isn't powerful enough. + * + * See update_sd_pick_busiest() and check_asym_packing(). + */ +static inline int +fix_small_capacity(struct sched_domain *sd, struct sched_group *group) +{ + /* + * Only siblings can have significantly less than SCHED_LOAD_SCALE + */ + if (sd->level != SD_LV_SIBLING) + return 0; + + /* + * If ~90% of the cpu_power is still there, we're good. + */ + if (group->cpu_power * 32 > group->cpu_power_orig * 29) + return 1; + + return 0; +} + /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @sd: The sched_domain whose statistics are to be updated. @@ -2400,14 +2427,14 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, * domains. In the newly idle case, we will allow all the cpu's * to do the newly idle load balance. */ - if (idle != CPU_NEWLY_IDLE && local_group && - balance_cpu != this_cpu) { - *balance = 0; - return; + if (idle != CPU_NEWLY_IDLE && local_group) { + if (balance_cpu != this_cpu) { + *balance = 0; + return; + } + update_group_power(sd, this_cpu); } - update_group_power(sd, this_cpu); - /* Adjust by relative CPU power of the group */ sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power; @@ -2428,6 +2455,51 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); + if (!sgs->group_capacity) + sgs->group_capacity = fix_small_capacity(sd, group); +} + +/** + * update_sd_pick_busiest - return 1 on busiest group + * @sd: sched_domain whose statistics are to be checked + * @sds: sched_domain statistics + * @sg: sched_group candidate to be checked for being the busiest + * @sgs: sched_group statistics + * @this_cpu: the current cpu + * + * Determine if @sg is a busier group than the previously selected + * busiest group. + */ +static bool update_sd_pick_busiest(struct sched_domain *sd, + struct sd_lb_stats *sds, + struct sched_group *sg, + struct sg_lb_stats *sgs, + int this_cpu) +{ + if (sgs->avg_load <= sds->max_load) + return false; + + if (sgs->sum_nr_running > sgs->group_capacity) + return true; + + if (sgs->group_imb) + return true; + + /* + * ASYM_PACKING needs to move all the work to the lowest + * numbered CPUs in the group, therefore mark all groups + * higher than ourself as busy. + */ + if ((sd->flags & SD_ASYM_PACKING) && sgs->sum_nr_running && + this_cpu < group_first_cpu(sg)) { + if (!sds->busiest) + return true; + + if (group_first_cpu(sds->busiest) > group_first_cpu(sg)) + return true; + } + + return false; } /** @@ -2435,7 +2507,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, * @sd: sched_domain whose statistics are to be updated. * @this_cpu: Cpu for which load balance is currently performed. * @idle: Idle status of this_cpu - * @sd_idle: Idle status of the sched_domain containing group. + * @sd_idle: Idle status of the sched_domain containing sg. * @cpus: Set of cpus considered for load balancing. * @balance: Should we balance. * @sds: variable to hold the statistics for this sched_domain. @@ -2446,7 +2518,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, struct sd_lb_stats *sds) { struct sched_domain *child = sd->child; - struct sched_group *group = sd->groups; + struct sched_group *sg = sd->groups; struct sg_lb_stats sgs; int load_idx, prefer_sibling = 0; @@ -2459,21 +2531,20 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, do { int local_group; - local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); + local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg)); memset(&sgs, 0, sizeof(sgs)); - update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle, + update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, sd_idle, local_group, cpus, balance, &sgs); if (local_group && !(*balance)) return; sds->total_load += sgs.group_load; - sds->total_pwr += group->cpu_power; + sds->total_pwr += sg->cpu_power; /* * In case the child domain prefers tasks go to siblings - * first, lower the group capacity to one so that we'll try + * first, lower the sg capacity to one so that we'll try * and move all the excess tasks away. */ if (prefer_sibling) @@ -2481,23 +2552,72 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, if (local_group) { sds->this_load = sgs.avg_load; - sds->this = group; + sds->this = sg; sds->this_nr_running = sgs.sum_nr_running; sds->this_load_per_task = sgs.sum_weighted_load; - } else if (sgs.avg_load > sds->max_load && - (sgs.sum_nr_running > sgs.group_capacity || - sgs.group_imb)) { + } else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) { sds->max_load = sgs.avg_load; - sds->busiest = group; + sds->busiest = sg; sds->busiest_nr_running = sgs.sum_nr_running; sds->busiest_group_capacity = sgs.group_capacity; sds->busiest_load_per_task = sgs.sum_weighted_load; sds->group_imb = sgs.group_imb; } - update_sd_power_savings_stats(group, sds, local_group, &sgs); - group = group->next; - } while (group != sd->groups); + update_sd_power_savings_stats(sg, sds, local_group, &sgs); + sg = sg->next; + } while (sg != sd->groups); +} + +int __weak arch_sd_sibling_asym_packing(void) +{ + return 0*SD_ASYM_PACKING; +} + +/** + * check_asym_packing - Check to see if the group is packed into the + * sched doman. + * + * This is primarily intended to used at the sibling level. Some + * cores like POWER7 prefer to use lower numbered SMT threads. In the + * case of POWER7, it can move to lower SMT modes only when higher + * threads are idle. When in lower SMT modes, the threads will + * perform better since they share less core resources. Hence when we + * have idle threads, we want them to be the higher ones. + * + * This packing function is run on idle threads. It checks to see if + * the busiest CPU in this domain (core in the P7 case) has a higher + * CPU number than the packing function is being run on. Here we are + * assuming lower CPU number will be equivalent to lower a SMT thread + * number. + * + * Returns 1 when packing is required and a task should be moved to + * this CPU. The amount of the imbalance is returned in *imbalance. + * + * @sd: The sched_domain whose packing is to be checked. + * @sds: Statistics of the sched_domain which is to be packed + * @this_cpu: The cpu at whose sched_domain we're performing load-balance. + * @imbalance: returns amount of imbalanced due to packing. + */ +static int check_asym_packing(struct sched_domain *sd, + struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + int busiest_cpu; + + if (!(sd->flags & SD_ASYM_PACKING)) + return 0; + + if (!sds->busiest) + return 0; + + busiest_cpu = group_first_cpu(sds->busiest); + if (this_cpu > busiest_cpu) + return 0; + + *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->cpu_power, + SCHED_LOAD_SCALE); + return 1; } /** @@ -2692,6 +2812,10 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (!(*balance)) goto ret; + if ((idle == CPU_IDLE || idle == CPU_NEWLY_IDLE) && + check_asym_packing(sd, &sds, this_cpu, imbalance)) + return sds.busiest; + if (!sds.busiest || sds.busiest_nr_running == 0) goto out_balanced; @@ -2726,8 +2850,9 @@ ret: * find_busiest_queue - find the busiest runqueue among the cpus in group. */ static struct rq * -find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, - unsigned long imbalance, const struct cpumask *cpus) +find_busiest_queue(struct sched_domain *sd, struct sched_group *group, + enum cpu_idle_type idle, unsigned long imbalance, + const struct cpumask *cpus) { struct rq *busiest = NULL, *rq; unsigned long max_load = 0; @@ -2738,6 +2863,9 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE); unsigned long wl; + if (!capacity) + capacity = fix_small_capacity(sd, group); + if (!cpumask_test_cpu(i, cpus)) continue; @@ -2777,9 +2905,19 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, /* Working cpumask for load_balance and load_balance_newidle. */ static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); -static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle) +static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle, + int busiest_cpu, int this_cpu) { if (idle == CPU_NEWLY_IDLE) { + + /* + * ASYM_PACKING needs to force migrate tasks from busy but + * higher numbered CPUs in order to pack all tasks in the + * lowest numbered CPUs. + */ + if ((sd->flags & SD_ASYM_PACKING) && busiest_cpu > this_cpu) + return 1; + /* * The only task running in a non-idle cpu can be moved to this * cpu in an attempt to completely freeup the other CPU @@ -2854,7 +2992,7 @@ redo: goto out_balanced; } - busiest = find_busiest_queue(group, idle, imbalance, cpus); + busiest = find_busiest_queue(sd, group, idle, imbalance, cpus); if (!busiest) { schedstat_inc(sd, lb_nobusyq[idle]); goto out_balanced; @@ -2898,7 +3036,8 @@ redo: schedstat_inc(sd, lb_failed[idle]); sd->nr_balance_failed++; - if (need_active_balance(sd, sd_idle, idle)) { + if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest), + this_cpu)) { raw_spin_lock_irqsave(&busiest->lock, flags); /* don't kick the active_load_balance_cpu_stop, @@ -3093,13 +3232,40 @@ out_unlock: } #ifdef CONFIG_NO_HZ + +static DEFINE_PER_CPU(struct call_single_data, remote_sched_softirq_cb); + +static void trigger_sched_softirq(void *data) +{ + raise_softirq_irqoff(SCHED_SOFTIRQ); +} + +static inline void init_sched_softirq_csd(struct call_single_data *csd) +{ + csd->func = trigger_sched_softirq; + csd->info = NULL; + csd->flags = 0; + csd->priv = 0; +} + +/* + * idle load balancing details + * - One of the idle CPUs nominates itself as idle load_balancer, while + * entering idle. + * - This idle load balancer CPU will also go into tickless mode when + * it is idle, just like all other idle CPUs + * - When one of the busy CPUs notice that there may be an idle rebalancing + * needed, they will kick the idle load balancer, which then does idle + * load balancing for all the idle CPUs. + */ static struct { atomic_t load_balancer; - cpumask_var_t cpu_mask; - cpumask_var_t ilb_grp_nohz_mask; -} nohz ____cacheline_aligned = { - .load_balancer = ATOMIC_INIT(-1), -}; + atomic_t first_pick_cpu; + atomic_t second_pick_cpu; + cpumask_var_t idle_cpus_mask; + cpumask_var_t grp_idle_mask; + unsigned long next_balance; /* in jiffy units */ +} nohz ____cacheline_aligned; int get_nohz_load_balancer(void) { @@ -3153,17 +3319,17 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) */ static inline int is_semi_idle_group(struct sched_group *ilb_group) { - cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask, + cpumask_and(nohz.grp_idle_mask, nohz.idle_cpus_mask, sched_group_cpus(ilb_group)); /* * A sched_group is semi-idle when it has atleast one busy cpu * and atleast one idle cpu. */ - if (cpumask_empty(nohz.ilb_grp_nohz_mask)) + if (cpumask_empty(nohz.grp_idle_mask)) return 0; - if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group))) + if (cpumask_equal(nohz.grp_idle_mask, sched_group_cpus(ilb_group))) return 0; return 1; @@ -3196,7 +3362,7 @@ static int find_new_ilb(int cpu) * Optimize for the case when we have no idle CPUs or only one * idle CPU. Don't walk the sched_domain hierarchy in such cases */ - if (cpumask_weight(nohz.cpu_mask) < 2) + if (cpumask_weight(nohz.idle_cpus_mask) < 2) goto out_done; for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { @@ -3204,7 +3370,7 @@ static int find_new_ilb(int cpu) do { if (is_semi_idle_group(ilb_group)) - return cpumask_first(nohz.ilb_grp_nohz_mask); + return cpumask_first(nohz.grp_idle_mask); ilb_group = ilb_group->next; @@ -3212,98 +3378,116 @@ static int find_new_ilb(int cpu) } out_done: - return cpumask_first(nohz.cpu_mask); + return nr_cpu_ids; } #else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ static inline int find_new_ilb(int call_cpu) { - return cpumask_first(nohz.cpu_mask); + return nr_cpu_ids; } #endif /* + * Kick a CPU to do the nohz balancing, if it is time for it. We pick the + * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle + * CPU (if there is one). + */ +static void nohz_balancer_kick(int cpu) +{ + int ilb_cpu; + + nohz.next_balance++; + + ilb_cpu = get_nohz_load_balancer(); + + if (ilb_cpu >= nr_cpu_ids) { + ilb_cpu = cpumask_first(nohz.idle_cpus_mask); + if (ilb_cpu >= nr_cpu_ids) + return; + } + + if (!cpu_rq(ilb_cpu)->nohz_balance_kick) { + struct call_single_data *cp; + + cpu_rq(ilb_cpu)->nohz_balance_kick = 1; + cp = &per_cpu(remote_sched_softirq_cb, cpu); + __smp_call_function_single(ilb_cpu, cp, 0); + } + return; +} + +/* * This routine will try to nominate the ilb (idle load balancing) * owner among the cpus whose ticks are stopped. ilb owner will do the idle - * load balancing on behalf of all those cpus. If all the cpus in the system - * go into this tickless mode, then there will be no ilb owner (as there is - * no need for one) and all the cpus will sleep till the next wakeup event - * arrives... - * - * For the ilb owner, tick is not stopped. And this tick will be used - * for idle load balancing. ilb owner will still be part of - * nohz.cpu_mask.. + * load balancing on behalf of all those cpus. * - * While stopping the tick, this cpu will become the ilb owner if there - * is no other owner. And will be the owner till that cpu becomes busy - * or if all cpus in the system stop their ticks at which point - * there is no need for ilb owner. + * When the ilb owner becomes busy, we will not have new ilb owner until some + * idle CPU wakes up and goes back to idle or some busy CPU tries to kick + * idle load balancing by kicking one of the idle CPUs. * - * When the ilb owner becomes busy, it nominates another owner, during the - * next busy scheduler_tick() + * Ticks are stopped for the ilb owner as well, with busy CPU kicking this + * ilb owner CPU in future (when there is a need for idle load balancing on + * behalf of all idle CPUs). */ -int select_nohz_load_balancer(int stop_tick) +void select_nohz_load_balancer(int stop_tick) { int cpu = smp_processor_id(); if (stop_tick) { - cpu_rq(cpu)->in_nohz_recently = 1; - if (!cpu_active(cpu)) { if (atomic_read(&nohz.load_balancer) != cpu) - return 0; + return; /* * If we are going offline and still the leader, * give up! */ - if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) + if (atomic_cmpxchg(&nohz.load_balancer, cpu, + nr_cpu_ids) != cpu) BUG(); - return 0; + return; } - cpumask_set_cpu(cpu, nohz.cpu_mask); + cpumask_set_cpu(cpu, nohz.idle_cpus_mask); - /* time for ilb owner also to sleep */ - if (cpumask_weight(nohz.cpu_mask) == num_active_cpus()) { - if (atomic_read(&nohz.load_balancer) == cpu) - atomic_set(&nohz.load_balancer, -1); - return 0; - } + if (atomic_read(&nohz.first_pick_cpu) == cpu) + atomic_cmpxchg(&nohz.first_pick_cpu, cpu, nr_cpu_ids); + if (atomic_read(&nohz.second_pick_cpu) == cpu) + atomic_cmpxchg(&nohz.second_pick_cpu, cpu, nr_cpu_ids); - if (atomic_read(&nohz.load_balancer) == -1) { - /* make me the ilb owner */ - if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1) - return 1; - } else if (atomic_read(&nohz.load_balancer) == cpu) { + if (atomic_read(&nohz.load_balancer) >= nr_cpu_ids) { int new_ilb; - if (!(sched_smt_power_savings || - sched_mc_power_savings)) - return 1; + /* make me the ilb owner */ + if (atomic_cmpxchg(&nohz.load_balancer, nr_cpu_ids, + cpu) != nr_cpu_ids) + return; + /* * Check to see if there is a more power-efficient * ilb. */ new_ilb = find_new_ilb(cpu); if (new_ilb < nr_cpu_ids && new_ilb != cpu) { - atomic_set(&nohz.load_balancer, -1); + atomic_set(&nohz.load_balancer, nr_cpu_ids); resched_cpu(new_ilb); - return 0; + return; } - return 1; + return; } } else { - if (!cpumask_test_cpu(cpu, nohz.cpu_mask)) - return 0; + if (!cpumask_test_cpu(cpu, nohz.idle_cpus_mask)) + return; - cpumask_clear_cpu(cpu, nohz.cpu_mask); + cpumask_clear_cpu(cpu, nohz.idle_cpus_mask); if (atomic_read(&nohz.load_balancer) == cpu) - if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) + if (atomic_cmpxchg(&nohz.load_balancer, cpu, + nr_cpu_ids) != cpu) BUG(); } - return 0; + return; } #endif @@ -3385,11 +3569,102 @@ out: rq->next_balance = next_balance; } +#ifdef CONFIG_NO_HZ /* - * run_rebalance_domains is triggered when needed from the scheduler tick. - * In CONFIG_NO_HZ case, the idle load balance owner will do the + * In CONFIG_NO_HZ case, the idle balance kickee will do the * rebalancing for all the cpus for whom scheduler ticks are stopped. */ +static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) +{ + struct rq *this_rq = cpu_rq(this_cpu); + struct rq *rq; + int balance_cpu; + + if (idle != CPU_IDLE || !this_rq->nohz_balance_kick) + return; + + for_each_cpu(balance_cpu, nohz.idle_cpus_mask) { + if (balance_cpu == this_cpu) + continue; + + /* + * If this cpu gets work to do, stop the load balancing + * work being done for other cpus. Next load + * balancing owner will pick it up. + */ + if (need_resched()) { + this_rq->nohz_balance_kick = 0; + break; + } + + raw_spin_lock_irq(&this_rq->lock); + update_rq_clock(this_rq); + update_cpu_load(this_rq); + raw_spin_unlock_irq(&this_rq->lock); + + rebalance_domains(balance_cpu, CPU_IDLE); + + rq = cpu_rq(balance_cpu); + if (time_after(this_rq->next_balance, rq->next_balance)) + this_rq->next_balance = rq->next_balance; + } + nohz.next_balance = this_rq->next_balance; + this_rq->nohz_balance_kick = 0; +} + +/* + * Current heuristic for kicking the idle load balancer + * - first_pick_cpu is the one of the busy CPUs. It will kick + * idle load balancer when it has more than one process active. This + * eliminates the need for idle load balancing altogether when we have + * only one running process in the system (common case). + * - If there are more than one busy CPU, idle load balancer may have + * to run for active_load_balance to happen (i.e., two busy CPUs are + * SMT or core siblings and can run better if they move to different + * physical CPUs). So, second_pick_cpu is the second of the busy CPUs + * which will kick idle load balancer as soon as it has any load. + */ +static inline int nohz_kick_needed(struct rq *rq, int cpu) +{ + unsigned long now = jiffies; + int ret; + int first_pick_cpu, second_pick_cpu; + + if (time_before(now, nohz.next_balance)) + return 0; + + if (!rq->nr_running) + return 0; + + first_pick_cpu = atomic_read(&nohz.first_pick_cpu); + second_pick_cpu = atomic_read(&nohz.second_pick_cpu); + + if (first_pick_cpu < nr_cpu_ids && first_pick_cpu != cpu && + second_pick_cpu < nr_cpu_ids && second_pick_cpu != cpu) + return 0; + + ret = atomic_cmpxchg(&nohz.first_pick_cpu, nr_cpu_ids, cpu); + if (ret == nr_cpu_ids || ret == cpu) { + atomic_cmpxchg(&nohz.second_pick_cpu, cpu, nr_cpu_ids); + if (rq->nr_running > 1) + return 1; + } else { + ret = atomic_cmpxchg(&nohz.second_pick_cpu, nr_cpu_ids, cpu); + if (ret == nr_cpu_ids || ret == cpu) { + if (rq->nr_running) + return 1; + } + } + return 0; +} +#else +static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { } +#endif + +/* + * run_rebalance_domains is triggered when needed from the scheduler tick. + * Also triggered for nohz idle balancing (with nohz_balancing_kick set). + */ static void run_rebalance_domains(struct softirq_action *h) { int this_cpu = smp_processor_id(); @@ -3399,37 +3674,12 @@ static void run_rebalance_domains(struct softirq_action *h) rebalance_domains(this_cpu, idle); -#ifdef CONFIG_NO_HZ /* - * If this cpu is the owner for idle load balancing, then do the + * If this cpu has a pending nohz_balance_kick, then do the * balancing on behalf of the other idle cpus whose ticks are * stopped. */ - if (this_rq->idle_at_tick && - atomic_read(&nohz.load_balancer) == this_cpu) { - struct rq *rq; - int balance_cpu; - - for_each_cpu(balance_cpu, nohz.cpu_mask) { - if (balance_cpu == this_cpu) - continue; - - /* - * If this cpu gets work to do, stop the load balancing - * work being done for other cpus. Next load - * balancing owner will pick it up. - */ - if (need_resched()) - break; - - rebalance_domains(balance_cpu, CPU_IDLE); - - rq = cpu_rq(balance_cpu); - if (time_after(this_rq->next_balance, rq->next_balance)) - this_rq->next_balance = rq->next_balance; - } - } -#endif + nohz_idle_balance(this_cpu, idle); } static inline int on_null_domain(int cpu) @@ -3439,57 +3689,17 @@ static inline int on_null_domain(int cpu) /* * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. - * - * In case of CONFIG_NO_HZ, this is the place where we nominate a new - * idle load balancing owner or decide to stop the periodic load balancing, - * if the whole system is idle. */ static inline void trigger_load_balance(struct rq *rq, int cpu) { -#ifdef CONFIG_NO_HZ - /* - * If we were in the nohz mode recently and busy at the current - * scheduler tick, then check if we need to nominate new idle - * load balancer. - */ - if (rq->in_nohz_recently && !rq->idle_at_tick) { - rq->in_nohz_recently = 0; - - if (atomic_read(&nohz.load_balancer) == cpu) { - cpumask_clear_cpu(cpu, nohz.cpu_mask); - atomic_set(&nohz.load_balancer, -1); - } - - if (atomic_read(&nohz.load_balancer) == -1) { - int ilb = find_new_ilb(cpu); - - if (ilb < nr_cpu_ids) - resched_cpu(ilb); - } - } - - /* - * If this cpu is idle and doing idle load balancing for all the - * cpus with ticks stopped, is it time for that to stop? - */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu && - cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { - resched_cpu(cpu); - return; - } - - /* - * If this cpu is idle and the idle load balancing is done by - * someone else, then no need raise the SCHED_SOFTIRQ - */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu && - cpumask_test_cpu(cpu, nohz.cpu_mask)) - return; -#endif /* Don't need to rebalance while attached to NULL domain */ if (time_after_eq(jiffies, rq->next_balance) && likely(!on_null_domain(cpu))) raise_softirq(SCHED_SOFTIRQ); +#ifdef CONFIG_NO_HZ + else if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu))) + nohz_balancer_kick(cpu); +#endif } static void rq_online_fair(struct rq *rq) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 8afb953e31c..d10c80ebb67 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -1663,9 +1663,6 @@ static void watchdog(struct rq *rq, struct task_struct *p) { unsigned long soft, hard; - if (!p->signal) - return; - /* max may change after cur was read, this will be fixed next tick */ soft = task_rlimit(p, RLIMIT_RTTIME); hard = task_rlimit_max(p, RLIMIT_RTTIME); diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 32d2bd4061b..25c2f962f6f 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -295,13 +295,7 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) static inline void account_group_user_time(struct task_struct *tsk, cputime_t cputime) { - struct thread_group_cputimer *cputimer; - - /* tsk == current, ensure it is safe to use ->signal */ - if (unlikely(tsk->exit_state)) - return; - - cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; if (!cputimer->running) return; @@ -325,13 +319,7 @@ static inline void account_group_user_time(struct task_struct *tsk, static inline void account_group_system_time(struct task_struct *tsk, cputime_t cputime) { - struct thread_group_cputimer *cputimer; - - /* tsk == current, ensure it is safe to use ->signal */ - if (unlikely(tsk->exit_state)) - return; - - cputimer = &tsk->signal->cputimer; + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; if (!cputimer->running) return; @@ -355,16 +343,7 @@ static inline void account_group_system_time(struct task_struct *tsk, static inline void account_group_exec_runtime(struct task_struct *tsk, unsigned long long ns) { - struct thread_group_cputimer *cputimer; - struct signal_struct *sig; - - sig = tsk->signal; - /* see __exit_signal()->task_rq_unlock_wait() */ - barrier(); - if (unlikely(!sig)) - return; - - cputimer = &sig->cputimer; + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; if (!cputimer->running) return; diff --git a/kernel/softlockup.c b/kernel/softlockup.c deleted file mode 100644 index 4b493f67dcb..00000000000 --- a/kernel/softlockup.c +++ /dev/null @@ -1,293 +0,0 @@ -/* - * Detect Soft Lockups - * - * started by Ingo Molnar, Copyright (C) 2005, 2006 Red Hat, Inc. - * - * this code detects soft lockups: incidents in where on a CPU - * the kernel does not reschedule for 10 seconds or more. - */ -#include <linux/mm.h> -#include <linux/cpu.h> -#include <linux/nmi.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/freezer.h> -#include <linux/kthread.h> -#include <linux/lockdep.h> -#include <linux/notifier.h> -#include <linux/module.h> -#include <linux/sysctl.h> - -#include <asm/irq_regs.h> - -static DEFINE_SPINLOCK(print_lock); - -static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */ -static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */ -static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); -static DEFINE_PER_CPU(bool, softlock_touch_sync); - -static int __read_mostly did_panic; -int __read_mostly softlockup_thresh = 60; - -/* - * Should we panic (and reboot, if panic_timeout= is set) when a - * soft-lockup occurs: - */ -unsigned int __read_mostly softlockup_panic = - CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; - -static int __init softlockup_panic_setup(char *str) -{ - softlockup_panic = simple_strtoul(str, NULL, 0); - - return 1; -} -__setup("softlockup_panic=", softlockup_panic_setup); - -static int -softlock_panic(struct notifier_block *this, unsigned long event, void *ptr) -{ - did_panic = 1; - - return NOTIFY_DONE; -} - -static struct notifier_block panic_block = { - .notifier_call = softlock_panic, -}; - -/* - * Returns seconds, approximately. We don't need nanosecond - * resolution, and we don't need to waste time with a big divide when - * 2^30ns == 1.074s. - */ -static unsigned long get_timestamp(int this_cpu) -{ - return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */ -} - -static void __touch_softlockup_watchdog(void) -{ - int this_cpu = raw_smp_processor_id(); - - __raw_get_cpu_var(softlockup_touch_ts) = get_timestamp(this_cpu); -} - -void touch_softlockup_watchdog(void) -{ - __raw_get_cpu_var(softlockup_touch_ts) = 0; -} -EXPORT_SYMBOL(touch_softlockup_watchdog); - -void touch_softlockup_watchdog_sync(void) -{ - __raw_get_cpu_var(softlock_touch_sync) = true; - __raw_get_cpu_var(softlockup_touch_ts) = 0; -} - -void touch_all_softlockup_watchdogs(void) -{ - int cpu; - - /* Cause each CPU to re-update its timestamp rather than complain */ - for_each_online_cpu(cpu) - per_cpu(softlockup_touch_ts, cpu) = 0; -} -EXPORT_SYMBOL(touch_all_softlockup_watchdogs); - -int proc_dosoftlockup_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ - touch_all_softlockup_watchdogs(); - return proc_dointvec_minmax(table, write, buffer, lenp, ppos); -} - -/* - * This callback runs from the timer interrupt, and checks - * whether the watchdog thread has hung or not: - */ -void softlockup_tick(void) -{ - int this_cpu = smp_processor_id(); - unsigned long touch_ts = per_cpu(softlockup_touch_ts, this_cpu); - unsigned long print_ts; - struct pt_regs *regs = get_irq_regs(); - unsigned long now; - - /* Is detection switched off? */ - if (!per_cpu(softlockup_watchdog, this_cpu) || softlockup_thresh <= 0) { - /* Be sure we don't false trigger if switched back on */ - if (touch_ts) - per_cpu(softlockup_touch_ts, this_cpu) = 0; - return; - } - - if (touch_ts == 0) { - if (unlikely(per_cpu(softlock_touch_sync, this_cpu))) { - /* - * If the time stamp was touched atomically - * make sure the scheduler tick is up to date. - */ - per_cpu(softlock_touch_sync, this_cpu) = false; - sched_clock_tick(); - } - __touch_softlockup_watchdog(); - return; - } - - print_ts = per_cpu(softlockup_print_ts, this_cpu); - - /* report at most once a second */ - if (print_ts == touch_ts || did_panic) - return; - - /* do not print during early bootup: */ - if (unlikely(system_state != SYSTEM_RUNNING)) { - __touch_softlockup_watchdog(); - return; - } - - now = get_timestamp(this_cpu); - - /* - * Wake up the high-prio watchdog task twice per - * threshold timespan. - */ - if (time_after(now - softlockup_thresh/2, touch_ts)) - wake_up_process(per_cpu(softlockup_watchdog, this_cpu)); - - /* Warn about unreasonable delays: */ - if (time_before_eq(now - softlockup_thresh, touch_ts)) - return; - - per_cpu(softlockup_print_ts, this_cpu) = touch_ts; - - spin_lock(&print_lock); - printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n", - this_cpu, now - touch_ts, - current->comm, task_pid_nr(current)); - print_modules(); - print_irqtrace_events(current); - if (regs) - show_regs(regs); - else - dump_stack(); - spin_unlock(&print_lock); - - if (softlockup_panic) - panic("softlockup: hung tasks"); -} - -/* - * The watchdog thread - runs every second and touches the timestamp. - */ -static int watchdog(void *__bind_cpu) -{ - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; - - sched_setscheduler(current, SCHED_FIFO, ¶m); - - /* initialize timestamp */ - __touch_softlockup_watchdog(); - - set_current_state(TASK_INTERRUPTIBLE); - /* - * Run briefly once per second to reset the softlockup timestamp. - * If this gets delayed for more than 60 seconds then the - * debug-printout triggers in softlockup_tick(). - */ - while (!kthread_should_stop()) { - __touch_softlockup_watchdog(); - schedule(); - - if (kthread_should_stop()) - break; - - set_current_state(TASK_INTERRUPTIBLE); - } - __set_current_state(TASK_RUNNING); - - return 0; -} - -/* - * Create/destroy watchdog threads as CPUs come and go: - */ -static int __cpuinit -cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) -{ - int hotcpu = (unsigned long)hcpu; - struct task_struct *p; - - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - BUG_ON(per_cpu(softlockup_watchdog, hotcpu)); - p = kthread_create(watchdog, hcpu, "watchdog/%d", hotcpu); - if (IS_ERR(p)) { - printk(KERN_ERR "watchdog for %i failed\n", hotcpu); - return NOTIFY_BAD; - } - per_cpu(softlockup_touch_ts, hotcpu) = 0; - per_cpu(softlockup_watchdog, hotcpu) = p; - kthread_bind(p, hotcpu); - break; - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - wake_up_process(per_cpu(softlockup_watchdog, hotcpu)); - break; -#ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - if (!per_cpu(softlockup_watchdog, hotcpu)) - break; - /* Unbind so it can run. Fall thru. */ - kthread_bind(per_cpu(softlockup_watchdog, hotcpu), - cpumask_any(cpu_online_mask)); - case CPU_DEAD: - case CPU_DEAD_FROZEN: - p = per_cpu(softlockup_watchdog, hotcpu); - per_cpu(softlockup_watchdog, hotcpu) = NULL; - kthread_stop(p); - break; -#endif /* CONFIG_HOTPLUG_CPU */ - } - return NOTIFY_OK; -} - -static struct notifier_block __cpuinitdata cpu_nfb = { - .notifier_call = cpu_callback -}; - -static int __initdata nosoftlockup; - -static int __init nosoftlockup_setup(char *str) -{ - nosoftlockup = 1; - return 1; -} -__setup("nosoftlockup", nosoftlockup_setup); - -static int __init spawn_softlockup_task(void) -{ - void *cpu = (void *)(long)smp_processor_id(); - int err; - - if (nosoftlockup) - return 0; - - err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); - if (err == NOTIFY_BAD) { - BUG(); - return 1; - } - cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); - register_cpu_notifier(&cpu_nfb); - - atomic_notifier_chain_register(&panic_notifier_list, &panic_block); - - return 0; -} -early_initcall(spawn_softlockup_task); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f73da1c857e..9acfce0cdfd 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -76,6 +76,10 @@ #include <scsi/sg.h> #endif +#ifdef CONFIG_LOCKUP_DETECTOR +#include <linux/nmi.h> +#endif + #if defined(CONFIG_SYSCTL) @@ -106,7 +110,7 @@ extern int blk_iopoll_enabled; #endif /* Constants used for minimum and maximum */ -#ifdef CONFIG_DETECT_SOFTLOCKUP +#ifdef CONFIG_LOCKUP_DETECTOR static int sixty = 60; static int neg_one = -1; #endif @@ -710,7 +714,34 @@ static struct ctl_table kern_table[] = { .mode = 0444, .proc_handler = proc_dointvec, }, -#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) +#if defined(CONFIG_LOCKUP_DETECTOR) + { + .procname = "watchdog", + .data = &watchdog_enabled, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = proc_dowatchdog_enabled, + }, + { + .procname = "watchdog_thresh", + .data = &softlockup_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dowatchdog_thresh, + .extra1 = &neg_one, + .extra2 = &sixty, + }, + { + .procname = "softlockup_panic", + .data = &softlockup_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR) { .procname = "unknown_nmi_panic", .data = &unknown_nmi_panic, @@ -813,26 +844,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_DETECT_SOFTLOCKUP - { - .procname = "softlockup_panic", - .data = &softlockup_panic, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, - }, - { - .procname = "softlockup_thresh", - .data = &softlockup_thresh, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dosoftlockup_thresh, - .extra1 = &neg_one, - .extra2 = &sixty, - }, -#endif #ifdef CONFIG_DETECT_HUNG_TASK { .procname = "hung_task_panic", diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 813993b5fb6..021d2f878f1 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -325,7 +325,7 @@ void tick_nohz_stop_sched_tick(int inidle) } while (read_seqretry(&xtime_lock, seq)); if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) || - arch_needs_cpu(cpu) || nohz_ratelimit(cpu)) { + arch_needs_cpu(cpu)) { next_jiffies = last_jiffies + 1; delta_jiffies = 1; } else { @@ -405,13 +405,7 @@ void tick_nohz_stop_sched_tick(int inidle) * the scheduler tick in nohz_restart_sched_tick. */ if (!ts->tick_stopped) { - if (select_nohz_load_balancer(1)) { - /* - * sched tick not stopped! - */ - cpumask_clear_cpu(cpu, nohz_cpu_mask); - goto out; - } + select_nohz_load_balancer(1); ts->idle_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; diff --git a/kernel/timer.c b/kernel/timer.c index efde11e197c..d61d16da0b6 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -692,12 +692,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, cpu = smp_processor_id(); #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) - if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) { - int preferred_cpu = get_nohz_load_balancer(); - - if (preferred_cpu >= 0) - cpu = preferred_cpu; - } + if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) + cpu = get_nohz_timer_target(); #endif new_base = per_cpu(tvec_bases, cpu); @@ -1302,7 +1298,6 @@ void run_local_timers(void) { hrtimer_run_queues(); raise_softirq(TIMER_SOFTIRQ); - softlockup_tick(); } /* diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 8b1797c4545..c7683fd8a03 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -194,15 +194,6 @@ config PREEMPT_TRACER enabled. This option and the irqs-off timing option can be used together or separately.) -config SYSPROF_TRACER - bool "Sysprof Tracer" - depends on X86 - select GENERIC_TRACER - select CONTEXT_SWITCH_TRACER - help - This tracer provides the trace needed by the 'Sysprof' userspace - tool. - config SCHED_TRACER bool "Scheduling Latency Tracer" select GENERIC_TRACER @@ -229,23 +220,6 @@ config FTRACE_SYSCALLS help Basic tracer to catch the syscall entry and exit events. -config BOOT_TRACER - bool "Trace boot initcalls" - select GENERIC_TRACER - select CONTEXT_SWITCH_TRACER - help - This tracer helps developers to optimize boot times: it records - the timings of the initcalls and traces key events and the identity - of tasks that can cause boot delays, such as context-switches. - - Its aim is to be parsed by the scripts/bootgraph.pl tool to - produce pretty graphics about boot inefficiencies, giving a visual - representation of the delays during initcalls - but the raw - /debug/tracing/trace text output is readable too. - - You must pass in initcall_debug and ftrace=initcall to the kernel - command line to enable this on bootup. - config TRACE_BRANCH_PROFILING bool select GENERIC_TRACER @@ -325,28 +299,6 @@ config BRANCH_TRACER Say N if unsure. -config KSYM_TRACER - bool "Trace read and write access on kernel memory locations" - depends on HAVE_HW_BREAKPOINT - select TRACING - help - This tracer helps find read and write operations on any given kernel - symbol i.e. /proc/kallsyms. - -config PROFILE_KSYM_TRACER - bool "Profile all kernel memory accesses on 'watched' variables" - depends on KSYM_TRACER - help - This tracer profiles kernel accesses on variables watched through the - ksym tracer ftrace plugin. Depending upon the hardware, all read - and write operations on kernel variables can be monitored for - accesses. - - The results will be displayed in: - /debugfs/tracing/profile_ksym - - Say N if unsure. - config STACK_TRACER bool "Trace max stack" depends on HAVE_FUNCTION_TRACER @@ -371,26 +323,6 @@ config STACK_TRACER Say N if unsure. -config KMEMTRACE - bool "Trace SLAB allocations" - select GENERIC_TRACER - help - kmemtrace provides tracing for slab allocator functions, such as - kmalloc, kfree, kmem_cache_alloc, kmem_cache_free, etc. Collected - data is then fed to the userspace application in order to analyse - allocation hotspots, internal fragmentation and so on, making it - possible to see how well an allocator performs, as well as debug - and profile kernel code. - - This requires an userspace application to use. See - Documentation/trace/kmemtrace.txt for more information. - - Saying Y will make the kernel somewhat larger and slower. However, - if you disable kmemtrace at run-time or boot-time, the performance - impact is minimal (depending on the arch the kernel is built for). - - If unsure, say N. - config WORKQUEUE_TRACER bool "Trace workqueues" select GENERIC_TRACER diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index ffb1a5b0550..53f338190b2 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -30,7 +30,6 @@ obj-$(CONFIG_TRACING) += trace_output.o obj-$(CONFIG_TRACING) += trace_stat.o obj-$(CONFIG_TRACING) += trace_printk.o obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o -obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o @@ -38,10 +37,8 @@ obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o obj-$(CONFIG_NOP_TRACER) += trace_nop.o obj-$(CONFIG_STACK_TRACER) += trace_stack.o obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o -obj-$(CONFIG_BOOT_TRACER) += trace_boot.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o -obj-$(CONFIG_KMEMTRACE) += kmemtrace.o obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o ifeq ($(CONFIG_BLOCK),y) @@ -55,7 +52,9 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o -obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o obj-$(CONFIG_EVENT_TRACING) += power-traces.o +ifeq ($(CONFIG_TRACING),y) +obj-$(CONFIG_KGDB_KDB) += trace_kdb.o +endif libftrace-y := ftrace.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6d2cb14f944..0d88ce9b9fb 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1883,7 +1883,6 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip) struct hlist_head *hhd; struct hlist_node *n; unsigned long key; - int resched; key = hash_long(ip, FTRACE_HASH_BITS); @@ -1897,12 +1896,12 @@ function_trace_probe_call(unsigned long ip, unsigned long parent_ip) * period. This syncs the hash iteration and freeing of items * on the hash. rcu_read_lock is too dangerous here. */ - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); hlist_for_each_entry_rcu(entry, n, hhd, node) { if (entry->ip == ip) entry->ops->func(ip, parent_ip, &entry->data); } - ftrace_preempt_enable(resched); + preempt_enable_notrace(); } static struct ftrace_ops trace_probe_ops __read_mostly = diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c deleted file mode 100644 index bbfc1bb1660..00000000000 --- a/kernel/trace/kmemtrace.c +++ /dev/null @@ -1,529 +0,0 @@ -/* - * Memory allocator tracing - * - * Copyright (C) 2008 Eduard - Gabriel Munteanu - * Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi> - * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> - */ - -#include <linux/tracepoint.h> -#include <linux/seq_file.h> -#include <linux/debugfs.h> -#include <linux/dcache.h> -#include <linux/fs.h> - -#include <linux/kmemtrace.h> - -#include "trace_output.h" -#include "trace.h" - -/* Select an alternative, minimalistic output than the original one */ -#define TRACE_KMEM_OPT_MINIMAL 0x1 - -static struct tracer_opt kmem_opts[] = { - /* Default disable the minimalistic output */ - { TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) }, - { } -}; - -static struct tracer_flags kmem_tracer_flags = { - .val = 0, - .opts = kmem_opts -}; - -static struct trace_array *kmemtrace_array; - -/* Trace allocations */ -static inline void kmemtrace_alloc(enum kmemtrace_type_id type_id, - unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags, - int node) -{ - struct ftrace_event_call *call = &event_kmem_alloc; - struct trace_array *tr = kmemtrace_array; - struct kmemtrace_alloc_entry *entry; - struct ring_buffer_event *event; - - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry)); - if (!event) - return; - - entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, 0); - - entry->ent.type = TRACE_KMEM_ALLOC; - entry->type_id = type_id; - entry->call_site = call_site; - entry->ptr = ptr; - entry->bytes_req = bytes_req; - entry->bytes_alloc = bytes_alloc; - entry->gfp_flags = gfp_flags; - entry->node = node; - - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); - - trace_wake_up(); -} - -static inline void kmemtrace_free(enum kmemtrace_type_id type_id, - unsigned long call_site, - const void *ptr) -{ - struct ftrace_event_call *call = &event_kmem_free; - struct trace_array *tr = kmemtrace_array; - struct kmemtrace_free_entry *entry; - struct ring_buffer_event *event; - - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry)); - if (!event) - return; - entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, 0); - - entry->ent.type = TRACE_KMEM_FREE; - entry->type_id = type_id; - entry->call_site = call_site; - entry->ptr = ptr; - - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); - - trace_wake_up(); -} - -static void kmemtrace_kmalloc(void *ignore, - unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags) -{ - kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr, - bytes_req, bytes_alloc, gfp_flags, -1); -} - -static void kmemtrace_kmem_cache_alloc(void *ignore, - unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags) -{ - kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr, - bytes_req, bytes_alloc, gfp_flags, -1); -} - -static void kmemtrace_kmalloc_node(void *ignore, - unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags, - int node) -{ - kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr, - bytes_req, bytes_alloc, gfp_flags, node); -} - -static void kmemtrace_kmem_cache_alloc_node(void *ignore, - unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags, - int node) -{ - kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr, - bytes_req, bytes_alloc, gfp_flags, node); -} - -static void -kmemtrace_kfree(void *ignore, unsigned long call_site, const void *ptr) -{ - kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr); -} - -static void kmemtrace_kmem_cache_free(void *ignore, - unsigned long call_site, const void *ptr) -{ - kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr); -} - -static int kmemtrace_start_probes(void) -{ - int err; - - err = register_trace_kmalloc(kmemtrace_kmalloc, NULL); - if (err) - return err; - err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL); - if (err) - return err; - err = register_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL); - if (err) - return err; - err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL); - if (err) - return err; - err = register_trace_kfree(kmemtrace_kfree, NULL); - if (err) - return err; - err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL); - - return err; -} - -static void kmemtrace_stop_probes(void) -{ - unregister_trace_kmalloc(kmemtrace_kmalloc, NULL); - unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL); - unregister_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL); - unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL); - unregister_trace_kfree(kmemtrace_kfree, NULL); - unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL); -} - -static int kmem_trace_init(struct trace_array *tr) -{ - kmemtrace_array = tr; - - tracing_reset_online_cpus(tr); - - kmemtrace_start_probes(); - - return 0; -} - -static void kmem_trace_reset(struct trace_array *tr) -{ - kmemtrace_stop_probes(); -} - -static void kmemtrace_headers(struct seq_file *s) -{ - /* Don't need headers for the original kmemtrace output */ - if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)) - return; - - seq_printf(s, "#\n"); - seq_printf(s, "# ALLOC TYPE REQ GIVEN FLAGS " - " POINTER NODE CALLER\n"); - seq_printf(s, "# FREE | | | | " - " | | | |\n"); - seq_printf(s, "# |\n\n"); -} - -/* - * The following functions give the original output from kmemtrace, - * plus the origin CPU, since reordering occurs in-kernel now. - */ - -#define KMEMTRACE_USER_ALLOC 0 -#define KMEMTRACE_USER_FREE 1 - -struct kmemtrace_user_event { - u8 event_id; - u8 type_id; - u16 event_size; - u32 cpu; - u64 timestamp; - unsigned long call_site; - unsigned long ptr; -}; - -struct kmemtrace_user_event_alloc { - size_t bytes_req; - size_t bytes_alloc; - unsigned gfp_flags; - int node; -}; - -static enum print_line_t -kmemtrace_print_alloc(struct trace_iterator *iter, int flags, - struct trace_event *event) -{ - struct trace_seq *s = &iter->seq; - struct kmemtrace_alloc_entry *entry; - int ret; - - trace_assign_type(entry, iter->ent); - - ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu " - "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n", - entry->type_id, (void *)entry->call_site, (unsigned long)entry->ptr, - (unsigned long)entry->bytes_req, (unsigned long)entry->bytes_alloc, - (unsigned long)entry->gfp_flags, entry->node); - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t -kmemtrace_print_free(struct trace_iterator *iter, int flags, - struct trace_event *event) -{ - struct trace_seq *s = &iter->seq; - struct kmemtrace_free_entry *entry; - int ret; - - trace_assign_type(entry, iter->ent); - - ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n", - entry->type_id, (void *)entry->call_site, - (unsigned long)entry->ptr); - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t -kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags, - struct trace_event *event) -{ - struct trace_seq *s = &iter->seq; - struct kmemtrace_alloc_entry *entry; - struct kmemtrace_user_event *ev; - struct kmemtrace_user_event_alloc *ev_alloc; - - trace_assign_type(entry, iter->ent); - - ev = trace_seq_reserve(s, sizeof(*ev)); - if (!ev) - return TRACE_TYPE_PARTIAL_LINE; - - ev->event_id = KMEMTRACE_USER_ALLOC; - ev->type_id = entry->type_id; - ev->event_size = sizeof(*ev) + sizeof(*ev_alloc); - ev->cpu = iter->cpu; - ev->timestamp = iter->ts; - ev->call_site = entry->call_site; - ev->ptr = (unsigned long)entry->ptr; - - ev_alloc = trace_seq_reserve(s, sizeof(*ev_alloc)); - if (!ev_alloc) - return TRACE_TYPE_PARTIAL_LINE; - - ev_alloc->bytes_req = entry->bytes_req; - ev_alloc->bytes_alloc = entry->bytes_alloc; - ev_alloc->gfp_flags = entry->gfp_flags; - ev_alloc->node = entry->node; - - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t -kmemtrace_print_free_user(struct trace_iterator *iter, int flags, - struct trace_event *event) -{ - struct trace_seq *s = &iter->seq; - struct kmemtrace_free_entry *entry; - struct kmemtrace_user_event *ev; - - trace_assign_type(entry, iter->ent); - - ev = trace_seq_reserve(s, sizeof(*ev)); - if (!ev) - return TRACE_TYPE_PARTIAL_LINE; - - ev->event_id = KMEMTRACE_USER_FREE; - ev->type_id = entry->type_id; - ev->event_size = sizeof(*ev); - ev->cpu = iter->cpu; - ev->timestamp = iter->ts; - ev->call_site = entry->call_site; - ev->ptr = (unsigned long)entry->ptr; - - return TRACE_TYPE_HANDLED; -} - -/* The two other following provide a more minimalistic output */ -static enum print_line_t -kmemtrace_print_alloc_compress(struct trace_iterator *iter) -{ - struct kmemtrace_alloc_entry *entry; - struct trace_seq *s = &iter->seq; - int ret; - - trace_assign_type(entry, iter->ent); - - /* Alloc entry */ - ret = trace_seq_printf(s, " + "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Type */ - switch (entry->type_id) { - case KMEMTRACE_TYPE_KMALLOC: - ret = trace_seq_printf(s, "K "); - break; - case KMEMTRACE_TYPE_CACHE: - ret = trace_seq_printf(s, "C "); - break; - case KMEMTRACE_TYPE_PAGES: - ret = trace_seq_printf(s, "P "); - break; - default: - ret = trace_seq_printf(s, "? "); - } - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Requested */ - ret = trace_seq_printf(s, "%4zu ", entry->bytes_req); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Allocated */ - ret = trace_seq_printf(s, "%4zu ", entry->bytes_alloc); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Flags - * TODO: would be better to see the name of the GFP flag names - */ - ret = trace_seq_printf(s, "%08x ", entry->gfp_flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Pointer to allocated */ - ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Node and call site*/ - ret = trace_seq_printf(s, "%4d %pf\n", entry->node, - (void *)entry->call_site); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t -kmemtrace_print_free_compress(struct trace_iterator *iter) -{ - struct kmemtrace_free_entry *entry; - struct trace_seq *s = &iter->seq; - int ret; - - trace_assign_type(entry, iter->ent); - - /* Free entry */ - ret = trace_seq_printf(s, " - "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Type */ - switch (entry->type_id) { - case KMEMTRACE_TYPE_KMALLOC: - ret = trace_seq_printf(s, "K "); - break; - case KMEMTRACE_TYPE_CACHE: - ret = trace_seq_printf(s, "C "); - break; - case KMEMTRACE_TYPE_PAGES: - ret = trace_seq_printf(s, "P "); - break; - default: - ret = trace_seq_printf(s, "? "); - } - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Skip requested/allocated/flags */ - ret = trace_seq_printf(s, " "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Pointer to allocated */ - ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Skip node and print call site*/ - ret = trace_seq_printf(s, " %pf\n", (void *)entry->call_site); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter) -{ - struct trace_entry *entry = iter->ent; - - if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)) - return TRACE_TYPE_UNHANDLED; - - switch (entry->type) { - case TRACE_KMEM_ALLOC: - return kmemtrace_print_alloc_compress(iter); - case TRACE_KMEM_FREE: - return kmemtrace_print_free_compress(iter); - default: - return TRACE_TYPE_UNHANDLED; - } -} - -static struct trace_event_functions kmem_trace_alloc_funcs = { - .trace = kmemtrace_print_alloc, - .binary = kmemtrace_print_alloc_user, -}; - -static struct trace_event kmem_trace_alloc = { - .type = TRACE_KMEM_ALLOC, - .funcs = &kmem_trace_alloc_funcs, -}; - -static struct trace_event_functions kmem_trace_free_funcs = { - .trace = kmemtrace_print_free, - .binary = kmemtrace_print_free_user, -}; - -static struct trace_event kmem_trace_free = { - .type = TRACE_KMEM_FREE, - .funcs = &kmem_trace_free_funcs, -}; - -static struct tracer kmem_tracer __read_mostly = { - .name = "kmemtrace", - .init = kmem_trace_init, - .reset = kmem_trace_reset, - .print_line = kmemtrace_print_line, - .print_header = kmemtrace_headers, - .flags = &kmem_tracer_flags -}; - -void kmemtrace_init(void) -{ - /* earliest opportunity to start kmem tracing */ -} - -static int __init init_kmem_tracer(void) -{ - if (!register_ftrace_event(&kmem_trace_alloc)) { - pr_warning("Warning: could not register kmem events\n"); - return 1; - } - - if (!register_ftrace_event(&kmem_trace_free)) { - pr_warning("Warning: could not register kmem events\n"); - return 1; - } - - if (register_tracer(&kmem_tracer) != 0) { - pr_warning("Warning: could not register the kmem tracer\n"); - return 1; - } - - return 0; -} -device_initcall(init_kmem_tracer); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1da7b6ea8b8..3632ce87674 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -443,6 +443,7 @@ int ring_buffer_print_page_header(struct trace_seq *s) */ struct ring_buffer_per_cpu { int cpu; + atomic_t record_disabled; struct ring_buffer *buffer; spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; @@ -462,7 +463,6 @@ struct ring_buffer_per_cpu { unsigned long read; u64 write_stamp; u64 read_stamp; - atomic_t record_disabled; }; struct ring_buffer { @@ -2242,8 +2242,6 @@ static void trace_recursive_unlock(void) #endif -static DEFINE_PER_CPU(int, rb_need_resched); - /** * ring_buffer_lock_reserve - reserve a part of the buffer * @buffer: the ring buffer to reserve from @@ -2264,13 +2262,13 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; - int cpu, resched; + int cpu; if (ring_buffer_flags != RB_BUFFERS_ON) return NULL; /* If we are tracing schedule, we don't want to recurse */ - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); if (atomic_read(&buffer->record_disabled)) goto out_nocheck; @@ -2295,21 +2293,13 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length) if (!event) goto out; - /* - * Need to store resched state on this cpu. - * Only the first needs to. - */ - - if (preempt_count() == 1) - per_cpu(rb_need_resched, cpu) = resched; - return event; out: trace_recursive_unlock(); out_nocheck: - ftrace_preempt_enable(resched); + preempt_enable_notrace(); return NULL; } EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve); @@ -2355,13 +2345,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer, trace_recursive_unlock(); - /* - * Only the last preempt count needs to restore preemption. - */ - if (preempt_count() == 1) - ftrace_preempt_enable(per_cpu(rb_need_resched, cpu)); - else - preempt_enable_no_resched_notrace(); + preempt_enable_notrace(); return 0; } @@ -2469,13 +2453,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer, trace_recursive_unlock(); - /* - * Only the last preempt count needs to restore preemption. - */ - if (preempt_count() == 1) - ftrace_preempt_enable(per_cpu(rb_need_resched, cpu)); - else - preempt_enable_no_resched_notrace(); + preempt_enable_notrace(); } EXPORT_SYMBOL_GPL(ring_buffer_discard_commit); @@ -2501,12 +2479,12 @@ int ring_buffer_write(struct ring_buffer *buffer, struct ring_buffer_event *event; void *body; int ret = -EBUSY; - int cpu, resched; + int cpu; if (ring_buffer_flags != RB_BUFFERS_ON) return -EBUSY; - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); if (atomic_read(&buffer->record_disabled)) goto out; @@ -2536,7 +2514,7 @@ int ring_buffer_write(struct ring_buffer *buffer, ret = 0; out: - ftrace_preempt_enable(resched); + preempt_enable_notrace(); return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 086d3631680..ed1032d6f81 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -101,10 +101,7 @@ static inline void ftrace_enable_cpu(void) preempt_enable(); } -static cpumask_var_t __read_mostly tracing_buffer_mask; - -#define for_each_tracing_cpu(cpu) \ - for_each_cpu(cpu, tracing_buffer_mask) +cpumask_var_t __read_mostly tracing_buffer_mask; /* * ftrace_dump_on_oops - variable to dump ftrace buffer on oops @@ -344,7 +341,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); /* trace_flags holds trace_options default values */ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | - TRACE_ITER_GRAPH_TIME; + TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD; static int trace_stop_count; static DEFINE_SPINLOCK(tracing_start_lock); @@ -428,6 +425,7 @@ static const char *trace_options[] = { "latency-format", "sleep-time", "graph-time", + "record-cmd", NULL }; @@ -659,6 +657,10 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) return; WARN_ON_ONCE(!irqs_disabled()); + if (!current_trace->use_max_tr) { + WARN_ON_ONCE(1); + return; + } arch_spin_lock(&ftrace_max_lock); tr->buffer = max_tr.buffer; @@ -685,6 +687,11 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) return; WARN_ON_ONCE(!irqs_disabled()); + if (!current_trace->use_max_tr) { + WARN_ON_ONCE(1); + return; + } + arch_spin_lock(&ftrace_max_lock); ftrace_disable_cpu(); @@ -729,7 +736,7 @@ __acquires(kernel_lock) return -1; } - if (strlen(type->name) > MAX_TRACER_SIZE) { + if (strlen(type->name) >= MAX_TRACER_SIZE) { pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE); return -1; } @@ -1331,61 +1338,6 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags) #endif /* CONFIG_STACKTRACE */ -static void -ftrace_trace_special(void *__tr, - unsigned long arg1, unsigned long arg2, unsigned long arg3, - int pc) -{ - struct ftrace_event_call *call = &event_special; - struct ring_buffer_event *event; - struct trace_array *tr = __tr; - struct ring_buffer *buffer = tr->buffer; - struct special_entry *entry; - - event = trace_buffer_lock_reserve(buffer, TRACE_SPECIAL, - sizeof(*entry), 0, pc); - if (!event) - return; - entry = ring_buffer_event_data(event); - entry->arg1 = arg1; - entry->arg2 = arg2; - entry->arg3 = arg3; - - if (!filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(buffer, event, 0, pc); -} - -void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ - ftrace_trace_special(__tr, arg1, arg2, arg3, preempt_count()); -} - -void -ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ - struct trace_array *tr = &global_trace; - struct trace_array_cpu *data; - unsigned long flags; - int cpu; - int pc; - - if (tracing_disabled) - return; - - pc = preempt_count(); - local_irq_save(flags); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - - if (likely(atomic_inc_return(&data->disabled) == 1)) - ftrace_trace_special(tr, arg1, arg2, arg3, pc); - - atomic_dec(&data->disabled); - local_irq_restore(flags); -} - /** * trace_vbprintk - write binary msg to tracing buffer * @@ -1404,7 +1356,6 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) struct bprint_entry *entry; unsigned long flags; int disable; - int resched; int cpu, len = 0, size, pc; if (unlikely(tracing_selftest_running || tracing_disabled)) @@ -1414,7 +1365,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) pause_graph_tracing(); pc = preempt_count(); - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = tr->data[cpu]; @@ -1452,7 +1403,7 @@ out_unlock: out: atomic_dec_return(&data->disabled); - ftrace_preempt_enable(resched); + preempt_enable_notrace(); unpause_graph_tracing(); return len; @@ -1539,11 +1490,6 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args) } EXPORT_SYMBOL_GPL(trace_vprintk); -enum trace_file_type { - TRACE_FILE_LAT_FMT = 1, - TRACE_FILE_ANNOTATE = 2, -}; - static void trace_iterator_increment(struct trace_iterator *iter) { /* Don't allow ftrace to trace into the ring buffers */ @@ -1641,7 +1587,7 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, } /* Find the next real entry, and increment the iterator to the next entry */ -static void *find_next_entry_inc(struct trace_iterator *iter) +void *trace_find_next_entry_inc(struct trace_iterator *iter) { iter->ent = __find_next_entry(iter, &iter->cpu, &iter->lost_events, &iter->ts); @@ -1676,19 +1622,19 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) return NULL; if (iter->idx < 0) - ent = find_next_entry_inc(iter); + ent = trace_find_next_entry_inc(iter); else ent = iter; while (ent && iter->idx < i) - ent = find_next_entry_inc(iter); + ent = trace_find_next_entry_inc(iter); iter->pos = *pos; return ent; } -static void tracing_iter_reset(struct trace_iterator *iter, int cpu) +void tracing_iter_reset(struct trace_iterator *iter, int cpu) { struct trace_array *tr = iter->tr; struct ring_buffer_event *event; @@ -2049,7 +1995,7 @@ int trace_empty(struct trace_iterator *iter) } /* Called with trace_event_read_lock() held. */ -static enum print_line_t print_trace_line(struct trace_iterator *iter) +enum print_line_t print_trace_line(struct trace_iterator *iter) { enum print_line_t ret; @@ -2394,6 +2340,7 @@ static const struct file_operations show_traces_fops = { .open = show_traces_open, .read = seq_read, .release = seq_release, + .llseek = seq_lseek, }; /* @@ -2487,6 +2434,7 @@ static const struct file_operations tracing_cpumask_fops = { .open = tracing_open_generic, .read = tracing_cpumask_read, .write = tracing_cpumask_write, + .llseek = generic_file_llseek, }; static int tracing_trace_options_show(struct seq_file *m, void *v) @@ -2562,6 +2510,9 @@ static void set_tracer_flags(unsigned int mask, int enabled) trace_flags |= mask; else trace_flags &= ~mask; + + if (mask == TRACE_ITER_RECORD_CMD) + trace_event_enable_cmd_record(enabled); } static ssize_t @@ -2653,6 +2604,7 @@ tracing_readme_read(struct file *filp, char __user *ubuf, static const struct file_operations tracing_readme_fops = { .open = tracing_open_generic, .read = tracing_readme_read, + .llseek = generic_file_llseek, }; static ssize_t @@ -2703,6 +2655,7 @@ tracing_saved_cmdlines_read(struct file *file, char __user *ubuf, static const struct file_operations tracing_saved_cmdlines_fops = { .open = tracing_open_generic, .read = tracing_saved_cmdlines_read, + .llseek = generic_file_llseek, }; static ssize_t @@ -2798,6 +2751,9 @@ static int tracing_resize_ring_buffer(unsigned long size) if (ret < 0) return ret; + if (!current_trace->use_max_tr) + goto out; + ret = ring_buffer_resize(max_tr.buffer, size); if (ret < 0) { int r; @@ -2825,11 +2781,14 @@ static int tracing_resize_ring_buffer(unsigned long size) return ret; } + max_tr.entries = size; + out: global_trace.entries = size; return ret; } + /** * tracing_update_buffers - used by tracing facility to expand ring buffers * @@ -2890,12 +2849,26 @@ static int tracing_set_tracer(const char *buf) trace_branch_disable(); if (current_trace && current_trace->reset) current_trace->reset(tr); - + if (current_trace && current_trace->use_max_tr) { + /* + * We don't free the ring buffer. instead, resize it because + * The max_tr ring buffer has some state (e.g. ring->clock) and + * we want preserve it. + */ + ring_buffer_resize(max_tr.buffer, 1); + max_tr.entries = 1; + } destroy_trace_option_files(topts); current_trace = t; topts = create_trace_option_files(current_trace); + if (current_trace->use_max_tr) { + ret = ring_buffer_resize(max_tr.buffer, global_trace.entries); + if (ret < 0) + goto out; + max_tr.entries = global_trace.entries; + } if (t->init) { ret = tracer_init(t, tr); @@ -3032,6 +3005,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) if (iter->trace->pipe_open) iter->trace->pipe_open(iter); + nonseekable_open(inode, filp); out: mutex_unlock(&trace_types_lock); return ret; @@ -3211,7 +3185,7 @@ waitagain: trace_event_read_lock(); trace_access_lock(iter->cpu_file); - while (find_next_entry_inc(iter) != NULL) { + while (trace_find_next_entry_inc(iter) != NULL) { enum print_line_t ret; int len = iter->seq.len; @@ -3294,7 +3268,7 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter) if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(iter); rem -= count; - if (!find_next_entry_inc(iter)) { + if (!trace_find_next_entry_inc(iter)) { rem = 0; iter->ent = NULL; break; @@ -3350,7 +3324,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, if (ret <= 0) goto out_err; - if (!iter->ent && !find_next_entry_inc(iter)) { + if (!iter->ent && !trace_find_next_entry_inc(iter)) { ret = -EFAULT; goto out_err; } @@ -3477,7 +3451,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, } tracing_start(); - max_tr.entries = global_trace.entries; mutex_unlock(&trace_types_lock); return cnt; @@ -3590,18 +3563,21 @@ static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic, .read = tracing_max_lat_read, .write = tracing_max_lat_write, + .llseek = generic_file_llseek, }; static const struct file_operations tracing_ctrl_fops = { .open = tracing_open_generic, .read = tracing_ctrl_read, .write = tracing_ctrl_write, + .llseek = generic_file_llseek, }; static const struct file_operations set_tracer_fops = { .open = tracing_open_generic, .read = tracing_set_trace_read, .write = tracing_set_trace_write, + .llseek = generic_file_llseek, }; static const struct file_operations tracing_pipe_fops = { @@ -3610,17 +3586,20 @@ static const struct file_operations tracing_pipe_fops = { .read = tracing_read_pipe, .splice_read = tracing_splice_read_pipe, .release = tracing_release_pipe, + .llseek = no_llseek, }; static const struct file_operations tracing_entries_fops = { .open = tracing_open_generic, .read = tracing_entries_read, .write = tracing_entries_write, + .llseek = generic_file_llseek, }; static const struct file_operations tracing_mark_fops = { .open = tracing_open_generic, .write = tracing_mark_write, + .llseek = generic_file_llseek, }; static const struct file_operations trace_clock_fops = { @@ -3926,6 +3905,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, static const struct file_operations tracing_stats_fops = { .open = tracing_open_generic, .read = tracing_stats_read, + .llseek = generic_file_llseek, }; #ifdef CONFIG_DYNAMIC_FTRACE @@ -3962,6 +3942,7 @@ tracing_read_dyn_info(struct file *filp, char __user *ubuf, static const struct file_operations tracing_dyn_info_fops = { .open = tracing_open_generic, .read = tracing_read_dyn_info, + .llseek = generic_file_llseek, }; #endif @@ -4115,6 +4096,7 @@ static const struct file_operations trace_options_fops = { .open = tracing_open_generic, .read = trace_options_read, .write = trace_options_write, + .llseek = generic_file_llseek, }; static ssize_t @@ -4166,6 +4148,7 @@ static const struct file_operations trace_options_core_fops = { .open = tracing_open_generic, .read = trace_options_core_read, .write = trace_options_core_write, + .llseek = generic_file_llseek, }; struct dentry *trace_create_file(const char *name, @@ -4355,9 +4338,6 @@ static __init int tracer_init_debugfs(void) trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, &ftrace_update_tot_cnt, &tracing_dyn_info_fops); #endif -#ifdef CONFIG_SYSPROF_TRACER - init_tracer_sysprof_debugfs(d_tracer); -#endif create_trace_options_dir(); @@ -4414,7 +4394,7 @@ static struct notifier_block trace_die_notifier = { */ #define KERN_TRACE KERN_EMERG -static void +void trace_printk_seq(struct trace_seq *s) { /* Probably should print a warning here. */ @@ -4429,6 +4409,13 @@ trace_printk_seq(struct trace_seq *s) trace_seq_init(s); } +void trace_init_global_iter(struct trace_iterator *iter) +{ + iter->tr = &global_trace; + iter->trace = current_trace; + iter->cpu_file = TRACE_PIPE_ALL_CPU; +} + static void __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) { @@ -4454,8 +4441,10 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) if (disable_tracing) ftrace_kill(); + trace_init_global_iter(&iter); + for_each_tracing_cpu(cpu) { - atomic_inc(&global_trace.data[cpu]->disabled); + atomic_inc(&iter.tr->data[cpu]->disabled); } old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ; @@ -4504,7 +4493,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) iter.iter_flags |= TRACE_FILE_LAT_FMT; iter.pos = -1; - if (find_next_entry_inc(&iter) != NULL) { + if (trace_find_next_entry_inc(&iter) != NULL) { int ret; ret = print_trace_line(&iter); @@ -4526,7 +4515,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) trace_flags |= old_userobj; for_each_tracing_cpu(cpu) { - atomic_dec(&global_trace.data[cpu]->disabled); + atomic_dec(&iter.tr->data[cpu]->disabled); } tracing_on(); } @@ -4575,16 +4564,14 @@ __init static int tracer_alloc_buffers(void) #ifdef CONFIG_TRACER_MAX_TRACE - max_tr.buffer = ring_buffer_alloc(ring_buf_size, - TRACE_BUFFER_FLAGS); + max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS); if (!max_tr.buffer) { printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n"); WARN_ON(1); ring_buffer_free(global_trace.buffer); goto out_free_cpumask; } - max_tr.entries = ring_buffer_size(max_tr.buffer); - WARN_ON(max_tr.entries != global_trace.entries); + max_tr.entries = 1; #endif /* Allocate the first page for all buffers */ @@ -4597,9 +4584,6 @@ __init static int tracer_alloc_buffers(void) register_tracer(&nop_trace); current_trace = &nop_trace; -#ifdef CONFIG_BOOT_TRACER - register_tracer(&boot_tracer); -#endif /* All seems OK, enable tracing */ tracing_disabled = 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2cd96399463..d39b3c5454a 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -9,10 +9,7 @@ #include <linux/mmiotrace.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> -#include <trace/boot.h> -#include <linux/kmemtrace.h> #include <linux/hw_breakpoint.h> - #include <linux/trace_seq.h> #include <linux/ftrace_event.h> @@ -25,30 +22,17 @@ enum trace_type { TRACE_STACK, TRACE_PRINT, TRACE_BPRINT, - TRACE_SPECIAL, TRACE_MMIO_RW, TRACE_MMIO_MAP, TRACE_BRANCH, - TRACE_BOOT_CALL, - TRACE_BOOT_RET, TRACE_GRAPH_RET, TRACE_GRAPH_ENT, TRACE_USER_STACK, - TRACE_KMEM_ALLOC, - TRACE_KMEM_FREE, TRACE_BLK, - TRACE_KSYM, __TRACE_LAST_TYPE, }; -enum kmemtrace_type_id { - KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */ - KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */ - KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */ -}; - -extern struct tracer boot_tracer; #undef __field #define __field(type, item) type item; @@ -204,23 +188,15 @@ extern void __ftrace_bad_type(void); IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\ IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \ IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \ - IF_ASSIGN(var, ent, struct special_entry, 0); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \ TRACE_MMIO_RW); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \ TRACE_MMIO_MAP); \ - IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\ - IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\ IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \ IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry, \ TRACE_GRAPH_ENT); \ IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \ TRACE_GRAPH_RET); \ - IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry, \ - TRACE_KMEM_ALLOC); \ - IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \ - TRACE_KMEM_FREE); \ - IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\ __ftrace_bad_type(); \ } while (0) @@ -298,6 +274,7 @@ struct tracer { struct tracer *next; int print_max; struct tracer_flags *flags; + int use_max_tr; }; @@ -318,7 +295,6 @@ struct dentry *trace_create_file(const char *name, const struct file_operations *fops); struct dentry *tracing_init_dentry(void); -void init_tracer_sysprof_debugfs(struct dentry *d_tracer); struct ring_buffer_event; @@ -338,6 +314,14 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts); +int trace_empty(struct trace_iterator *iter); + +void *trace_find_next_entry_inc(struct trace_iterator *iter); + +void trace_init_global_iter(struct trace_iterator *iter); + +void tracing_iter_reset(struct trace_iterator *iter, int cpu); + void default_wait_pipe(struct trace_iterator *iter); void poll_wait_pipe(struct trace_iterator *iter); @@ -355,11 +339,6 @@ void tracing_sched_wakeup_trace(struct trace_array *tr, struct task_struct *wakee, struct task_struct *cur, unsigned long flags, int pc); -void trace_special(struct trace_array *tr, - struct trace_array_cpu *data, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3, int pc); void trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, @@ -380,8 +359,15 @@ void tracing_start_sched_switch_record(void); int register_tracer(struct tracer *type); void unregister_tracer(struct tracer *type); int is_tracing_stopped(void); +enum trace_file_type { + TRACE_FILE_LAT_FMT = 1, + TRACE_FILE_ANNOTATE = 2, +}; + +extern cpumask_var_t __read_mostly tracing_buffer_mask; -extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr); +#define for_each_tracing_cpu(cpu) \ + for_each_cpu(cpu, tracing_buffer_mask) extern unsigned long nsecs_to_usecs(unsigned long nsecs); @@ -452,12 +438,8 @@ extern int trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr); -extern int trace_selftest_startup_sysprof(struct tracer *trace, - struct trace_array *tr); extern int trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr); -extern int trace_selftest_startup_ksym(struct tracer *trace, - struct trace_array *tr); #endif /* CONFIG_FTRACE_STARTUP_TEST */ extern void *head_page(struct trace_array_cpu *data); @@ -471,6 +453,8 @@ trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args); int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...); +void trace_printk_seq(struct trace_seq *s); +enum print_line_t print_trace_line(struct trace_iterator *iter); extern unsigned long trace_flags; @@ -617,6 +601,7 @@ enum trace_iterator_flags { TRACE_ITER_LATENCY_FMT = 0x20000, TRACE_ITER_SLEEP_TIME = 0x40000, TRACE_ITER_GRAPH_TIME = 0x80000, + TRACE_ITER_RECORD_CMD = 0x100000, }; /* @@ -628,54 +613,6 @@ enum trace_iterator_flags { extern struct tracer nop_trace; -/** - * ftrace_preempt_disable - disable preemption scheduler safe - * - * When tracing can happen inside the scheduler, there exists - * cases that the tracing might happen before the need_resched - * flag is checked. If this happens and the tracer calls - * preempt_enable (after a disable), a schedule might take place - * causing an infinite recursion. - * - * To prevent this, we read the need_resched flag before - * disabling preemption. When we want to enable preemption we - * check the flag, if it is set, then we call preempt_enable_no_resched. - * Otherwise, we call preempt_enable. - * - * The rational for doing the above is that if need_resched is set - * and we have yet to reschedule, we are either in an atomic location - * (where we do not need to check for scheduling) or we are inside - * the scheduler and do not want to resched. - */ -static inline int ftrace_preempt_disable(void) -{ - int resched; - - resched = need_resched(); - preempt_disable_notrace(); - - return resched; -} - -/** - * ftrace_preempt_enable - enable preemption scheduler safe - * @resched: the return value from ftrace_preempt_disable - * - * This is a scheduler safe way to enable preemption and not miss - * any preemption checks. The disabled saved the state of preemption. - * If resched is set, then we are either inside an atomic or - * are inside the scheduler (we would have already scheduled - * otherwise). In this case, we do not want to call normal - * preempt_enable, but preempt_enable_no_resched instead. - */ -static inline void ftrace_preempt_enable(int resched) -{ - if (resched) - preempt_enable_no_resched_notrace(); - else - preempt_enable_notrace(); -} - #ifdef CONFIG_BRANCH_TRACER extern int enable_branch_tracing(struct trace_array *tr); extern void disable_branch_tracing(void); @@ -766,6 +703,8 @@ struct filter_pred { int pop_n; }; +extern struct list_head ftrace_common_fields; + extern enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not); extern void print_event_filter(struct ftrace_event_call *call, @@ -795,6 +734,8 @@ filter_check_discard(struct ftrace_event_call *call, void *rec, return 0; } +extern void trace_event_enable_cmd_record(bool enable); + extern struct mutex event_mutex; extern struct list_head ftrace_events; diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c deleted file mode 100644 index c21d5f3956a..00000000000 --- a/kernel/trace/trace_boot.c +++ /dev/null @@ -1,185 +0,0 @@ -/* - * ring buffer based initcalls tracer - * - * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> - * - */ - -#include <linux/init.h> -#include <linux/debugfs.h> -#include <linux/ftrace.h> -#include <linux/kallsyms.h> -#include <linux/time.h> - -#include "trace.h" -#include "trace_output.h" - -static struct trace_array *boot_trace; -static bool pre_initcalls_finished; - -/* Tells the boot tracer that the pre_smp_initcalls are finished. - * So we are ready . - * It doesn't enable sched events tracing however. - * You have to call enable_boot_trace to do so. - */ -void start_boot_trace(void) -{ - pre_initcalls_finished = true; -} - -void enable_boot_trace(void) -{ - if (boot_trace && pre_initcalls_finished) - tracing_start_sched_switch_record(); -} - -void disable_boot_trace(void) -{ - if (boot_trace && pre_initcalls_finished) - tracing_stop_sched_switch_record(); -} - -static int boot_trace_init(struct trace_array *tr) -{ - boot_trace = tr; - - if (!tr) - return 0; - - tracing_reset_online_cpus(tr); - - tracing_sched_switch_assign_trace(tr); - return 0; -} - -static enum print_line_t -initcall_call_print_line(struct trace_iterator *iter) -{ - struct trace_entry *entry = iter->ent; - struct trace_seq *s = &iter->seq; - struct trace_boot_call *field; - struct boot_trace_call *call; - u64 ts; - unsigned long nsec_rem; - int ret; - - trace_assign_type(field, entry); - call = &field->boot_call; - ts = iter->ts; - nsec_rem = do_div(ts, NSEC_PER_SEC); - - ret = trace_seq_printf(s, "[%5ld.%09ld] calling %s @ %i\n", - (unsigned long)ts, nsec_rem, call->func, call->caller); - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - else - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t -initcall_ret_print_line(struct trace_iterator *iter) -{ - struct trace_entry *entry = iter->ent; - struct trace_seq *s = &iter->seq; - struct trace_boot_ret *field; - struct boot_trace_ret *init_ret; - u64 ts; - unsigned long nsec_rem; - int ret; - - trace_assign_type(field, entry); - init_ret = &field->boot_ret; - ts = iter->ts; - nsec_rem = do_div(ts, NSEC_PER_SEC); - - ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s " - "returned %d after %llu msecs\n", - (unsigned long) ts, - nsec_rem, - init_ret->func, init_ret->result, init_ret->duration); - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - else - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t initcall_print_line(struct trace_iterator *iter) -{ - struct trace_entry *entry = iter->ent; - - switch (entry->type) { - case TRACE_BOOT_CALL: - return initcall_call_print_line(iter); - case TRACE_BOOT_RET: - return initcall_ret_print_line(iter); - default: - return TRACE_TYPE_UNHANDLED; - } -} - -struct tracer boot_tracer __read_mostly = -{ - .name = "initcall", - .init = boot_trace_init, - .reset = tracing_reset_online_cpus, - .print_line = initcall_print_line, -}; - -void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) -{ - struct ftrace_event_call *call = &event_boot_call; - struct ring_buffer_event *event; - struct ring_buffer *buffer; - struct trace_boot_call *entry; - struct trace_array *tr = boot_trace; - - if (!tr || !pre_initcalls_finished) - return; - - /* Get its name now since this function could - * disappear because it is in the .init section. - */ - sprint_symbol(bt->func, (unsigned long)fn); - preempt_disable(); - - buffer = tr->buffer; - event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_CALL, - sizeof(*entry), 0, 0); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->boot_call = *bt; - if (!filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(buffer, event, 0, 0); - out: - preempt_enable(); -} - -void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) -{ - struct ftrace_event_call *call = &event_boot_ret; - struct ring_buffer_event *event; - struct ring_buffer *buffer; - struct trace_boot_ret *entry; - struct trace_array *tr = boot_trace; - - if (!tr || !pre_initcalls_finished) - return; - - sprint_symbol(bt->func, (unsigned long)fn); - preempt_disable(); - - buffer = tr->buffer; - event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_RET, - sizeof(*entry), 0, 0); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->boot_ret = *bt; - if (!filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(buffer, event, 0, 0); - out: - preempt_enable(); -} diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index 9d589d8dcd1..685a67d55db 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -32,16 +32,15 @@ u64 notrace trace_clock_local(void) { u64 clock; - int resched; /* * sched_clock() is an architecture implemented, fast, scalable, * lockless clock. It is not guaranteed to be coherent across * CPUs, nor across CPU idle events. */ - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); clock = sched_clock(); - ftrace_preempt_enable(resched); + preempt_enable_notrace(); return clock; } @@ -56,7 +55,7 @@ u64 notrace trace_clock_local(void) */ u64 notrace trace_clock(void) { - return cpu_clock(raw_smp_processor_id()); + return local_clock(); } diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index dc008c1240d..e3dfecaf13e 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -151,23 +151,6 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, ); /* - * Special (free-form) trace entry: - */ -FTRACE_ENTRY(special, special_entry, - - TRACE_SPECIAL, - - F_STRUCT( - __field( unsigned long, arg1 ) - __field( unsigned long, arg2 ) - __field( unsigned long, arg3 ) - ), - - F_printk("(%08lx) (%08lx) (%08lx)", - __entry->arg1, __entry->arg2, __entry->arg3) -); - -/* * Stack-trace entry: */ @@ -271,33 +254,6 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, __entry->map_id, __entry->opcode) ); -FTRACE_ENTRY(boot_call, trace_boot_call, - - TRACE_BOOT_CALL, - - F_STRUCT( - __field_struct( struct boot_trace_call, boot_call ) - __field_desc( pid_t, boot_call, caller ) - __array_desc( char, boot_call, func, KSYM_SYMBOL_LEN) - ), - - F_printk("%d %s", __entry->caller, __entry->func) -); - -FTRACE_ENTRY(boot_ret, trace_boot_ret, - - TRACE_BOOT_RET, - - F_STRUCT( - __field_struct( struct boot_trace_ret, boot_ret ) - __array_desc( char, boot_ret, func, KSYM_SYMBOL_LEN) - __field_desc( int, boot_ret, result ) - __field_desc( unsigned long, boot_ret, duration ) - ), - - F_printk("%s %d %lx", - __entry->func, __entry->result, __entry->duration) -); #define TRACE_FUNC_SIZE 30 #define TRACE_FILE_SIZE 20 @@ -318,53 +274,3 @@ FTRACE_ENTRY(branch, trace_branch, __entry->func, __entry->file, __entry->correct) ); -FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry, - - TRACE_KMEM_ALLOC, - - F_STRUCT( - __field( enum kmemtrace_type_id, type_id ) - __field( unsigned long, call_site ) - __field( const void *, ptr ) - __field( size_t, bytes_req ) - __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) - __field( int, node ) - ), - - F_printk("type:%u call_site:%lx ptr:%p req:%zi alloc:%zi" - " flags:%x node:%d", - __entry->type_id, __entry->call_site, __entry->ptr, - __entry->bytes_req, __entry->bytes_alloc, - __entry->gfp_flags, __entry->node) -); - -FTRACE_ENTRY(kmem_free, kmemtrace_free_entry, - - TRACE_KMEM_FREE, - - F_STRUCT( - __field( enum kmemtrace_type_id, type_id ) - __field( unsigned long, call_site ) - __field( const void *, ptr ) - ), - - F_printk("type:%u call_site:%lx ptr:%p", - __entry->type_id, __entry->call_site, __entry->ptr) -); - -FTRACE_ENTRY(ksym_trace, ksym_trace_entry, - - TRACE_KSYM, - - F_STRUCT( - __field( unsigned long, ip ) - __field( unsigned char, type ) - __array( char , cmd, TASK_COMM_LEN ) - __field( unsigned long, addr ) - ), - - F_printk("ip: %pF type: %d ksym_name: %pS cmd: %s", - (void *)__entry->ip, (unsigned int)__entry->type, - (void *)__entry->addr, __entry->cmd) -); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 8a2b73f7c06..000e6e85b44 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -9,8 +9,6 @@ #include <linux/kprobes.h> #include "trace.h" -EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs); - static char *perf_trace_buf[4]; /* @@ -56,13 +54,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event, } } - if (tp_event->class->reg) - ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER); - else - ret = tracepoint_probe_register(tp_event->name, - tp_event->class->perf_probe, - tp_event); - + ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER); if (ret) goto fail; @@ -96,9 +88,7 @@ int perf_trace_init(struct perf_event *p_event) mutex_lock(&event_mutex); list_for_each_entry(tp_event, &ftrace_events, list) { if (tp_event->event.type == event_id && - tp_event->class && - (tp_event->class->perf_probe || - tp_event->class->reg) && + tp_event->class && tp_event->class->reg && try_module_get(tp_event->mod)) { ret = perf_trace_event_init(tp_event, p_event); break; @@ -138,18 +128,13 @@ void perf_trace_destroy(struct perf_event *p_event) if (--tp_event->perf_refcount > 0) goto out; - if (tp_event->class->reg) - tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER); - else - tracepoint_probe_unregister(tp_event->name, - tp_event->class->perf_probe, - tp_event); + tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER); /* - * Ensure our callback won't be called anymore. See - * tracepoint_probe_unregister() and __DO_TRACE(). + * Ensure our callback won't be called anymore. The buffers + * will be freed after that. */ - synchronize_sched(); + tracepoint_synchronize_unregister(); free_percpu(tp_event->perf_events); tp_event->perf_events = NULL; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 53cffc0b080..09b4fa6e4d3 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -28,6 +28,7 @@ DEFINE_MUTEX(event_mutex); LIST_HEAD(ftrace_events); +LIST_HEAD(ftrace_common_fields); struct list_head * trace_get_fields(struct ftrace_event_call *event_call) @@ -37,15 +38,11 @@ trace_get_fields(struct ftrace_event_call *event_call) return event_call->class->get_fields(event_call); } -int trace_define_field(struct ftrace_event_call *call, const char *type, - const char *name, int offset, int size, int is_signed, - int filter_type) +static int __trace_define_field(struct list_head *head, const char *type, + const char *name, int offset, int size, + int is_signed, int filter_type) { struct ftrace_event_field *field; - struct list_head *head; - - if (WARN_ON(!call->class)) - return 0; field = kzalloc(sizeof(*field), GFP_KERNEL); if (!field) @@ -68,7 +65,6 @@ int trace_define_field(struct ftrace_event_call *call, const char *type, field->size = size; field->is_signed = is_signed; - head = trace_get_fields(call); list_add(&field->link, head); return 0; @@ -80,17 +76,32 @@ err: return -ENOMEM; } + +int trace_define_field(struct ftrace_event_call *call, const char *type, + const char *name, int offset, int size, int is_signed, + int filter_type) +{ + struct list_head *head; + + if (WARN_ON(!call->class)) + return 0; + + head = trace_get_fields(call); + return __trace_define_field(head, type, name, offset, size, + is_signed, filter_type); +} EXPORT_SYMBOL_GPL(trace_define_field); #define __common_field(type, item) \ - ret = trace_define_field(call, #type, "common_" #item, \ - offsetof(typeof(ent), item), \ - sizeof(ent.item), \ - is_signed_type(type), FILTER_OTHER); \ + ret = __trace_define_field(&ftrace_common_fields, #type, \ + "common_" #item, \ + offsetof(typeof(ent), item), \ + sizeof(ent.item), \ + is_signed_type(type), FILTER_OTHER); \ if (ret) \ return ret; -static int trace_define_common_fields(struct ftrace_event_call *call) +static int trace_define_common_fields(void) { int ret; struct trace_entry ent; @@ -130,6 +141,55 @@ int trace_event_raw_init(struct ftrace_event_call *call) } EXPORT_SYMBOL_GPL(trace_event_raw_init); +int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type) +{ + switch (type) { + case TRACE_REG_REGISTER: + return tracepoint_probe_register(call->name, + call->class->probe, + call); + case TRACE_REG_UNREGISTER: + tracepoint_probe_unregister(call->name, + call->class->probe, + call); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return tracepoint_probe_register(call->name, + call->class->perf_probe, + call); + case TRACE_REG_PERF_UNREGISTER: + tracepoint_probe_unregister(call->name, + call->class->perf_probe, + call); + return 0; +#endif + } + return 0; +} +EXPORT_SYMBOL_GPL(ftrace_event_reg); + +void trace_event_enable_cmd_record(bool enable) +{ + struct ftrace_event_call *call; + + mutex_lock(&event_mutex); + list_for_each_entry(call, &ftrace_events, list) { + if (!(call->flags & TRACE_EVENT_FL_ENABLED)) + continue; + + if (enable) { + tracing_start_cmdline_record(); + call->flags |= TRACE_EVENT_FL_RECORDED_CMD; + } else { + tracing_stop_cmdline_record(); + call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD; + } + } + mutex_unlock(&event_mutex); +} + static int ftrace_event_enable_disable(struct ftrace_event_call *call, int enable) { @@ -139,24 +199,20 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, case 0: if (call->flags & TRACE_EVENT_FL_ENABLED) { call->flags &= ~TRACE_EVENT_FL_ENABLED; - tracing_stop_cmdline_record(); - if (call->class->reg) - call->class->reg(call, TRACE_REG_UNREGISTER); - else - tracepoint_probe_unregister(call->name, - call->class->probe, - call); + if (call->flags & TRACE_EVENT_FL_RECORDED_CMD) { + tracing_stop_cmdline_record(); + call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD; + } + call->class->reg(call, TRACE_REG_UNREGISTER); } break; case 1: if (!(call->flags & TRACE_EVENT_FL_ENABLED)) { - tracing_start_cmdline_record(); - if (call->class->reg) - ret = call->class->reg(call, TRACE_REG_REGISTER); - else - ret = tracepoint_probe_register(call->name, - call->class->probe, - call); + if (trace_flags & TRACE_ITER_RECORD_CMD) { + tracing_start_cmdline_record(); + call->flags |= TRACE_EVENT_FL_RECORDED_CMD; + } + ret = call->class->reg(call, TRACE_REG_REGISTER); if (ret) { tracing_stop_cmdline_record(); pr_info("event trace: Could not enable event " @@ -194,8 +250,7 @@ static int __ftrace_set_clr_event(const char *match, const char *sub, mutex_lock(&event_mutex); list_for_each_entry(call, &ftrace_events, list) { - if (!call->name || !call->class || - (!call->class->probe && !call->class->reg)) + if (!call->name || !call->class || !call->class->reg) continue; if (match && @@ -321,7 +376,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ - if (call->class && (call->class->probe || call->class->reg)) + if (call->class && call->class->reg) return call; } @@ -474,8 +529,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); list_for_each_entry(call, &ftrace_events, list) { - if (!call->name || !call->class || - (!call->class->probe && !call->class->reg)) + if (!call->name || !call->class || !call->class->reg) continue; if (system && strcmp(call->class->system, system) != 0) @@ -544,32 +598,10 @@ out: return ret; } -static ssize_t -event_format_read(struct file *filp, char __user *ubuf, size_t cnt, - loff_t *ppos) +static void print_event_fields(struct trace_seq *s, struct list_head *head) { - struct ftrace_event_call *call = filp->private_data; struct ftrace_event_field *field; - struct list_head *head; - struct trace_seq *s; - int common_field_count = 5; - char *buf; - int r = 0; - - if (*ppos) - return 0; - - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; - - trace_seq_init(s); - - trace_seq_printf(s, "name: %s\n", call->name); - trace_seq_printf(s, "ID: %d\n", call->event.type); - trace_seq_printf(s, "format:\n"); - head = trace_get_fields(call); list_for_each_entry_reverse(field, head, link) { /* * Smartly shows the array type(except dynamic array). @@ -584,29 +616,54 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt, array_descriptor = NULL; if (!array_descriptor) { - r = trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;" + trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;" "\tsize:%u;\tsigned:%d;\n", field->type, field->name, field->offset, field->size, !!field->is_signed); } else { - r = trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;" + trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;" "\tsize:%u;\tsigned:%d;\n", (int)(array_descriptor - field->type), field->type, field->name, array_descriptor, field->offset, field->size, !!field->is_signed); } + } +} - if (--common_field_count == 0) - r = trace_seq_printf(s, "\n"); +static ssize_t +event_format_read(struct file *filp, char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct ftrace_event_call *call = filp->private_data; + struct list_head *head; + struct trace_seq *s; + char *buf; + int r; - if (!r) - break; - } + if (*ppos) + return 0; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + trace_seq_init(s); + + trace_seq_printf(s, "name: %s\n", call->name); + trace_seq_printf(s, "ID: %d\n", call->event.type); + trace_seq_printf(s, "format:\n"); + + /* print common fields */ + print_event_fields(s, &ftrace_common_fields); - if (r) - r = trace_seq_printf(s, "\nprint fmt: %s\n", - call->print_fmt); + trace_seq_putc(s, '\n'); + + /* print event specific fields */ + head = trace_get_fields(call); + print_event_fields(s, head); + + r = trace_seq_printf(s, "\nprint fmt: %s\n", call->print_fmt); if (!r) { /* @@ -963,35 +1020,31 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, return -1; } - if (call->class->probe || call->class->reg) + if (call->class->reg) trace_create_file("enable", 0644, call->dir, call, enable); #ifdef CONFIG_PERF_EVENTS - if (call->event.type && (call->class->perf_probe || call->class->reg)) + if (call->event.type && call->class->reg) trace_create_file("id", 0444, call->dir, call, id); #endif - if (call->class->define_fields) { - /* - * Other events may have the same class. Only update - * the fields if they are not already defined. - */ - head = trace_get_fields(call); - if (list_empty(head)) { - ret = trace_define_common_fields(call); - if (!ret) - ret = call->class->define_fields(call); - if (ret < 0) { - pr_warning("Could not initialize trace point" - " events/%s\n", call->name); - return ret; - } + /* + * Other events may have the same class. Only update + * the fields if they are not already defined. + */ + head = trace_get_fields(call); + if (list_empty(head)) { + ret = call->class->define_fields(call); + if (ret < 0) { + pr_warning("Could not initialize trace point" + " events/%s\n", call->name); + return ret; } - trace_create_file("filter", 0644, call->dir, call, - filter); } + trace_create_file("filter", 0644, call->dir, call, + filter); trace_create_file("format", 0444, call->dir, call, format); @@ -999,11 +1052,17 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, return 0; } -static int __trace_add_event_call(struct ftrace_event_call *call) +static int +__trace_add_event_call(struct ftrace_event_call *call, struct module *mod, + const struct file_operations *id, + const struct file_operations *enable, + const struct file_operations *filter, + const struct file_operations *format) { struct dentry *d_events; int ret; + /* The linker may leave blanks */ if (!call->name) return -EINVAL; @@ -1011,8 +1070,8 @@ static int __trace_add_event_call(struct ftrace_event_call *call) ret = call->class->raw_init(call); if (ret < 0) { if (ret != -ENOSYS) - pr_warning("Could not initialize trace " - "events/%s\n", call->name); + pr_warning("Could not initialize trace events/%s\n", + call->name); return ret; } } @@ -1021,11 +1080,10 @@ static int __trace_add_event_call(struct ftrace_event_call *call) if (!d_events) return -ENOENT; - ret = event_create_dir(call, d_events, &ftrace_event_id_fops, - &ftrace_enable_fops, &ftrace_event_filter_fops, - &ftrace_event_format_fops); + ret = event_create_dir(call, d_events, id, enable, filter, format); if (!ret) list_add(&call->list, &ftrace_events); + call->mod = mod; return ret; } @@ -1035,7 +1093,10 @@ int trace_add_event_call(struct ftrace_event_call *call) { int ret; mutex_lock(&event_mutex); - ret = __trace_add_event_call(call); + ret = __trace_add_event_call(call, NULL, &ftrace_event_id_fops, + &ftrace_enable_fops, + &ftrace_event_filter_fops, + &ftrace_event_format_fops); mutex_unlock(&event_mutex); return ret; } @@ -1152,8 +1213,6 @@ static void trace_module_add_events(struct module *mod) { struct ftrace_module_file_ops *file_ops = NULL; struct ftrace_event_call *call, *start, *end; - struct dentry *d_events; - int ret; start = mod->trace_events; end = mod->trace_events + mod->num_trace_events; @@ -1161,38 +1220,14 @@ static void trace_module_add_events(struct module *mod) if (start == end) return; - d_events = event_trace_events_dir(); - if (!d_events) + file_ops = trace_create_file_ops(mod); + if (!file_ops) return; for_each_event(call, start, end) { - /* The linker may leave blanks */ - if (!call->name) - continue; - if (call->class->raw_init) { - ret = call->class->raw_init(call); - if (ret < 0) { - if (ret != -ENOSYS) - pr_warning("Could not initialize trace " - "point events/%s\n", call->name); - continue; - } - } - /* - * This module has events, create file ops for this module - * if not already done. - */ - if (!file_ops) { - file_ops = trace_create_file_ops(mod); - if (!file_ops) - return; - } - call->mod = mod; - ret = event_create_dir(call, d_events, + __trace_add_event_call(call, mod, &file_ops->id, &file_ops->enable, &file_ops->filter, &file_ops->format); - if (!ret) - list_add(&call->list, &ftrace_events); } } @@ -1319,25 +1354,14 @@ static __init int event_trace_init(void) trace_create_file("enable", 0644, d_events, NULL, &ftrace_system_enable_fops); + if (trace_define_common_fields()) + pr_warning("tracing: Failed to allocate common fields"); + for_each_event(call, __start_ftrace_events, __stop_ftrace_events) { - /* The linker may leave blanks */ - if (!call->name) - continue; - if (call->class->raw_init) { - ret = call->class->raw_init(call); - if (ret < 0) { - if (ret != -ENOSYS) - pr_warning("Could not initialize trace " - "point events/%s\n", call->name); - continue; - } - } - ret = event_create_dir(call, d_events, &ftrace_event_id_fops, + __trace_add_event_call(call, NULL, &ftrace_event_id_fops, &ftrace_enable_fops, &ftrace_event_filter_fops, &ftrace_event_format_fops); - if (!ret) - list_add(&call->list, &ftrace_events); } while (true) { @@ -1524,12 +1548,11 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip) struct ftrace_entry *entry; unsigned long flags; long disabled; - int resched; int cpu; int pc; pc = preempt_count(); - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu)); @@ -1551,7 +1574,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip) out: atomic_dec(&per_cpu(ftrace_test_event_disable, cpu)); - ftrace_preempt_enable(resched); + preempt_enable_notrace(); } static struct ftrace_ops trace_ops __initdata = diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 57bb1bb3299..36d40104b17 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -497,12 +497,10 @@ void print_subsystem_event_filter(struct event_subsystem *system, } static struct ftrace_event_field * -find_event_field(struct ftrace_event_call *call, char *name) +__find_event_field(struct list_head *head, char *name) { struct ftrace_event_field *field; - struct list_head *head; - head = trace_get_fields(call); list_for_each_entry(field, head, link) { if (!strcmp(field->name, name)) return field; @@ -511,6 +509,20 @@ find_event_field(struct ftrace_event_call *call, char *name) return NULL; } +static struct ftrace_event_field * +find_event_field(struct ftrace_event_call *call, char *name) +{ + struct ftrace_event_field *field; + struct list_head *head; + + field = __find_event_field(&ftrace_common_fields, name); + if (field) + return field; + + head = trace_get_fields(call); + return __find_event_field(head, name); +} + static void filter_free_pred(struct filter_pred *pred) { if (!pred) @@ -627,9 +639,6 @@ static int init_subsystem_preds(struct event_subsystem *system) int err; list_for_each_entry(call, &ftrace_events, list) { - if (!call->class || !call->class->define_fields) - continue; - if (strcmp(call->class->system, system->name) != 0) continue; @@ -646,9 +655,6 @@ static void filter_free_subsystem_preds(struct event_subsystem *system) struct ftrace_event_call *call; list_for_each_entry(call, &ftrace_events, list) { - if (!call->class || !call->class->define_fields) - continue; - if (strcmp(call->class->system, system->name) != 0) continue; @@ -1251,9 +1257,6 @@ static int replace_system_preds(struct event_subsystem *system, list_for_each_entry(call, &ftrace_events, list) { struct event_filter *filter = call->filter; - if (!call->class || !call->class->define_fields) - continue; - if (strcmp(call->class->system, system->name) != 0) continue; diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 8536e2a6596..4ba44deaac2 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -125,12 +125,6 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \ #include "trace_entries.h" -static int ftrace_raw_init_event(struct ftrace_event_call *call) -{ - INIT_LIST_HEAD(&call->class->fields); - return 0; -} - #undef __entry #define __entry REC @@ -158,7 +152,7 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call) struct ftrace_event_class event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ .define_fields = ftrace_define_fields_##call, \ - .raw_init = ftrace_raw_init_event, \ + .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ }; \ \ struct ftrace_event_call __used \ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index b3f3776b0cd..16aee4d44e8 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -54,14 +54,14 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) struct trace_array_cpu *data; unsigned long flags; long disabled; - int cpu, resched; + int cpu; int pc; if (unlikely(!ftrace_function_enabled)) return; pc = preempt_count(); - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); local_save_flags(flags); cpu = raw_smp_processor_id(); data = tr->data[cpu]; @@ -71,7 +71,7 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) trace_function(tr, ip, parent_ip, flags, pc); atomic_dec(&data->disabled); - ftrace_preempt_enable(resched); + preempt_enable_notrace(); } static void diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 79f4bac99a9..6bff2362578 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -641,7 +641,8 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s) /* Print nsecs (we don't want to exceed 7 numbers) */ if (len < 7) { - snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem); + snprintf(nsecs_str, min(sizeof(nsecs_str), 8UL - len), "%03lu", + nsecs_rem); ret = trace_seq_printf(s, ".%s", nsecs_str); if (!ret) return TRACE_TYPE_PARTIAL_LINE; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 6fd486e0cef..73a6b0601f2 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -649,6 +649,7 @@ static struct tracer irqsoff_tracer __read_mostly = #endif .open = irqsoff_trace_open, .close = irqsoff_trace_close, + .use_max_tr = 1, }; # define register_irqsoff(trace) register_tracer(&trace) #else @@ -681,6 +682,7 @@ static struct tracer preemptoff_tracer __read_mostly = #endif .open = irqsoff_trace_open, .close = irqsoff_trace_close, + .use_max_tr = 1, }; # define register_preemptoff(trace) register_tracer(&trace) #else @@ -715,6 +717,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly = #endif .open = irqsoff_trace_open, .close = irqsoff_trace_close, + .use_max_tr = 1, }; # define register_preemptirqsoff(trace) register_tracer(&trace) diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c new file mode 100644 index 00000000000..7b8ecd751d9 --- /dev/null +++ b/kernel/trace/trace_kdb.c @@ -0,0 +1,136 @@ +/* + * kdb helper for dumping the ftrace buffer + * + * Copyright (C) 2010 Jason Wessel <jason.wessel@windriver.com> + * + * ftrace_dump_buf based on ftrace_dump: + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + */ +#include <linux/init.h> +#include <linux/kgdb.h> +#include <linux/kdb.h> +#include <linux/ftrace.h> + +#include "../debug/kdb/kdb_private.h" +#include "trace.h" +#include "trace_output.h" + +static void ftrace_dump_buf(int skip_lines, long cpu_file) +{ + /* use static because iter can be a bit big for the stack */ + static struct trace_iterator iter; + unsigned int old_userobj; + int cnt = 0, cpu; + + trace_init_global_iter(&iter); + + for_each_tracing_cpu(cpu) { + atomic_inc(&iter.tr->data[cpu]->disabled); + } + + old_userobj = trace_flags; + + /* don't look at user memory in panic mode */ + trace_flags &= ~TRACE_ITER_SYM_USEROBJ; + + kdb_printf("Dumping ftrace buffer:\n"); + + /* reset all but tr, trace, and overruns */ + memset(&iter.seq, 0, + sizeof(struct trace_iterator) - + offsetof(struct trace_iterator, seq)); + iter.iter_flags |= TRACE_FILE_LAT_FMT; + iter.pos = -1; + + if (cpu_file == TRACE_PIPE_ALL_CPU) { + for_each_tracing_cpu(cpu) { + iter.buffer_iter[cpu] = + ring_buffer_read_prepare(iter.tr->buffer, cpu); + ring_buffer_read_start(iter.buffer_iter[cpu]); + tracing_iter_reset(&iter, cpu); + } + } else { + iter.cpu_file = cpu_file; + iter.buffer_iter[cpu_file] = + ring_buffer_read_prepare(iter.tr->buffer, cpu_file); + ring_buffer_read_start(iter.buffer_iter[cpu_file]); + tracing_iter_reset(&iter, cpu_file); + } + if (!trace_empty(&iter)) + trace_find_next_entry_inc(&iter); + while (!trace_empty(&iter)) { + if (!cnt) + kdb_printf("---------------------------------\n"); + cnt++; + + if (trace_find_next_entry_inc(&iter) != NULL && !skip_lines) + print_trace_line(&iter); + if (!skip_lines) + trace_printk_seq(&iter.seq); + else + skip_lines--; + if (KDB_FLAG(CMD_INTERRUPT)) + goto out; + } + + if (!cnt) + kdb_printf(" (ftrace buffer empty)\n"); + else + kdb_printf("---------------------------------\n"); + +out: + trace_flags = old_userobj; + + for_each_tracing_cpu(cpu) { + atomic_dec(&iter.tr->data[cpu]->disabled); + } + + for_each_tracing_cpu(cpu) + if (iter.buffer_iter[cpu]) + ring_buffer_read_finish(iter.buffer_iter[cpu]); +} + +/* + * kdb_ftdump - Dump the ftrace log buffer + */ +static int kdb_ftdump(int argc, const char **argv) +{ + int skip_lines = 0; + long cpu_file; + char *cp; + + if (argc > 2) + return KDB_ARGCOUNT; + + if (argc) { + skip_lines = simple_strtol(argv[1], &cp, 0); + if (*cp) + skip_lines = 0; + } + + if (argc == 2) { + cpu_file = simple_strtol(argv[2], &cp, 0); + if (*cp || cpu_file >= NR_CPUS || cpu_file < 0 || + !cpu_online(cpu_file)) + return KDB_BADINT; + } else { + cpu_file = TRACE_PIPE_ALL_CPU; + } + + kdb_trap_printk++; + ftrace_dump_buf(skip_lines, cpu_file); + kdb_trap_printk--; + + return 0; +} + +static __init int kdb_ftrace_register(void) +{ + kdb_register_repeat("ftdump", kdb_ftdump, "[skip_#lines] [cpu]", + "Dump ftrace log", 0, KDB_REPEAT_NONE); + return 0; +} + +late_initcall(kdb_ftrace_register); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index f52b5f50299..8b27c9849b4 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -30,6 +30,8 @@ #include <linux/ptrace.h> #include <linux/perf_event.h> #include <linux/stringify.h> +#include <linux/limits.h> +#include <linux/uaccess.h> #include <asm/bitsperlong.h> #include "trace.h" @@ -38,6 +40,7 @@ #define MAX_TRACE_ARGS 128 #define MAX_ARGSTR_LEN 63 #define MAX_EVENT_NAME_LEN 64 +#define MAX_STRING_SIZE PATH_MAX #define KPROBE_EVENT_SYSTEM "kprobes" /* Reserved field names */ @@ -58,14 +61,16 @@ const char *reserved_field_names[] = { }; /* Printing function type */ -typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *); +typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *, + void *); #define PRINT_TYPE_FUNC_NAME(type) print_type_##type #define PRINT_TYPE_FMT_NAME(type) print_type_format_##type /* Printing in basic type function template */ #define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast) \ static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \ - const char *name, void *data)\ + const char *name, \ + void *data, void *ent)\ { \ return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\ } \ @@ -80,6 +85,49 @@ DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int) DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long) DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long) +/* data_rloc: data relative location, compatible with u32 */ +#define make_data_rloc(len, roffs) \ + (((u32)(len) << 16) | ((u32)(roffs) & 0xffff)) +#define get_rloc_len(dl) ((u32)(dl) >> 16) +#define get_rloc_offs(dl) ((u32)(dl) & 0xffff) + +static inline void *get_rloc_data(u32 *dl) +{ + return (u8 *)dl + get_rloc_offs(*dl); +} + +/* For data_loc conversion */ +static inline void *get_loc_data(u32 *dl, void *ent) +{ + return (u8 *)ent + get_rloc_offs(*dl); +} + +/* + * Convert data_rloc to data_loc: + * data_rloc stores the offset from data_rloc itself, but data_loc + * stores the offset from event entry. + */ +#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs)) + +/* For defining macros, define string/string_size types */ +typedef u32 string; +typedef u32 string_size; + +/* Print type function for string type */ +static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, + const char *name, + void *data, void *ent) +{ + int len = *(u32 *)data >> 16; + + if (!len) + return trace_seq_printf(s, " %s=(fault)", name); + else + return trace_seq_printf(s, " %s=\"%s\"", name, + (const char *)get_loc_data(data, ent)); +} +static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\""; + /* Data fetch function type */ typedef void (*fetch_func_t)(struct pt_regs *, void *, void *); @@ -94,32 +142,38 @@ static __kprobes void call_fetch(struct fetch_param *fprm, return fprm->fn(regs, fprm->data, dest); } -#define FETCH_FUNC_NAME(kind, type) fetch_##kind##_##type +#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type /* * Define macro for basic types - we don't need to define s* types, because * we have to care only about bitwidth at recording time. */ -#define DEFINE_BASIC_FETCH_FUNCS(kind) \ -DEFINE_FETCH_##kind(u8) \ -DEFINE_FETCH_##kind(u16) \ -DEFINE_FETCH_##kind(u32) \ -DEFINE_FETCH_##kind(u64) - -#define CHECK_BASIC_FETCH_FUNCS(kind, fn) \ - ((FETCH_FUNC_NAME(kind, u8) == fn) || \ - (FETCH_FUNC_NAME(kind, u16) == fn) || \ - (FETCH_FUNC_NAME(kind, u32) == fn) || \ - (FETCH_FUNC_NAME(kind, u64) == fn)) +#define DEFINE_BASIC_FETCH_FUNCS(method) \ +DEFINE_FETCH_##method(u8) \ +DEFINE_FETCH_##method(u16) \ +DEFINE_FETCH_##method(u32) \ +DEFINE_FETCH_##method(u64) + +#define CHECK_FETCH_FUNCS(method, fn) \ + (((FETCH_FUNC_NAME(method, u8) == fn) || \ + (FETCH_FUNC_NAME(method, u16) == fn) || \ + (FETCH_FUNC_NAME(method, u32) == fn) || \ + (FETCH_FUNC_NAME(method, u64) == fn) || \ + (FETCH_FUNC_NAME(method, string) == fn) || \ + (FETCH_FUNC_NAME(method, string_size) == fn)) \ + && (fn != NULL)) /* Data fetch function templates */ #define DEFINE_FETCH_reg(type) \ static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \ - void *offset, void *dest) \ + void *offset, void *dest) \ { \ *(type *)dest = (type)regs_get_register(regs, \ (unsigned int)((unsigned long)offset)); \ } DEFINE_BASIC_FETCH_FUNCS(reg) +/* No string on the register */ +#define fetch_reg_string NULL +#define fetch_reg_string_size NULL #define DEFINE_FETCH_stack(type) \ static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\ @@ -129,6 +183,9 @@ static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\ (unsigned int)((unsigned long)offset)); \ } DEFINE_BASIC_FETCH_FUNCS(stack) +/* No string on the stack entry */ +#define fetch_stack_string NULL +#define fetch_stack_string_size NULL #define DEFINE_FETCH_retval(type) \ static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\ @@ -137,6 +194,9 @@ static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\ *(type *)dest = (type)regs_return_value(regs); \ } DEFINE_BASIC_FETCH_FUNCS(retval) +/* No string on the retval */ +#define fetch_retval_string NULL +#define fetch_retval_string_size NULL #define DEFINE_FETCH_memory(type) \ static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\ @@ -149,6 +209,62 @@ static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\ *(type *)dest = retval; \ } DEFINE_BASIC_FETCH_FUNCS(memory) +/* + * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max + * length and relative data location. + */ +static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs, + void *addr, void *dest) +{ + long ret; + int maxlen = get_rloc_len(*(u32 *)dest); + u8 *dst = get_rloc_data(dest); + u8 *src = addr; + mm_segment_t old_fs = get_fs(); + if (!maxlen) + return; + /* + * Try to get string again, since the string can be changed while + * probing. + */ + set_fs(KERNEL_DS); + pagefault_disable(); + do + ret = __copy_from_user_inatomic(dst++, src++, 1); + while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen); + dst[-1] = '\0'; + pagefault_enable(); + set_fs(old_fs); + + if (ret < 0) { /* Failed to fetch string */ + ((u8 *)get_rloc_data(dest))[0] = '\0'; + *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest)); + } else + *(u32 *)dest = make_data_rloc(src - (u8 *)addr, + get_rloc_offs(*(u32 *)dest)); +} +/* Return the length of string -- including null terminal byte */ +static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs, + void *addr, void *dest) +{ + int ret, len = 0; + u8 c; + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); + pagefault_disable(); + do { + ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1); + len++; + } while (c && ret == 0 && len < MAX_STRING_SIZE); + pagefault_enable(); + set_fs(old_fs); + + if (ret < 0) /* Failed to check the length */ + *(u32 *)dest = 0; + else + *(u32 *)dest = len; +} /* Memory fetching by symbol */ struct symbol_cache { @@ -203,6 +319,8 @@ static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\ *(type *)dest = 0; \ } DEFINE_BASIC_FETCH_FUNCS(symbol) +DEFINE_FETCH_symbol(string) +DEFINE_FETCH_symbol(string_size) /* Dereference memory access function */ struct deref_fetch_param { @@ -224,12 +342,14 @@ static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\ *(type *)dest = 0; \ } DEFINE_BASIC_FETCH_FUNCS(deref) +DEFINE_FETCH_deref(string) +DEFINE_FETCH_deref(string_size) static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data) { - if (CHECK_BASIC_FETCH_FUNCS(deref, data->orig.fn)) + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) free_deref_fetch_param(data->orig.data); - else if (CHECK_BASIC_FETCH_FUNCS(symbol, data->orig.fn)) + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) free_symbol_cache(data->orig.data); kfree(data); } @@ -240,23 +360,43 @@ static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data) #define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG) #define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE) -#define ASSIGN_FETCH_FUNC(kind, type) \ - .kind = FETCH_FUNC_NAME(kind, type) - -#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \ - {.name = #ptype, \ - .size = sizeof(ftype), \ - .is_signed = sign, \ - .print = PRINT_TYPE_FUNC_NAME(ptype), \ - .fmt = PRINT_TYPE_FMT_NAME(ptype), \ -ASSIGN_FETCH_FUNC(reg, ftype), \ -ASSIGN_FETCH_FUNC(stack, ftype), \ -ASSIGN_FETCH_FUNC(retval, ftype), \ -ASSIGN_FETCH_FUNC(memory, ftype), \ -ASSIGN_FETCH_FUNC(symbol, ftype), \ -ASSIGN_FETCH_FUNC(deref, ftype), \ +/* Fetch types */ +enum { + FETCH_MTD_reg = 0, + FETCH_MTD_stack, + FETCH_MTD_retval, + FETCH_MTD_memory, + FETCH_MTD_symbol, + FETCH_MTD_deref, + FETCH_MTD_END, +}; + +#define ASSIGN_FETCH_FUNC(method, type) \ + [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type) + +#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \ + {.name = _name, \ + .size = _size, \ + .is_signed = sign, \ + .print = PRINT_TYPE_FUNC_NAME(ptype), \ + .fmt = PRINT_TYPE_FMT_NAME(ptype), \ + .fmttype = _fmttype, \ + .fetch = { \ +ASSIGN_FETCH_FUNC(reg, ftype), \ +ASSIGN_FETCH_FUNC(stack, ftype), \ +ASSIGN_FETCH_FUNC(retval, ftype), \ +ASSIGN_FETCH_FUNC(memory, ftype), \ +ASSIGN_FETCH_FUNC(symbol, ftype), \ +ASSIGN_FETCH_FUNC(deref, ftype), \ + } \ } +#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \ + __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype) + +#define FETCH_TYPE_STRING 0 +#define FETCH_TYPE_STRSIZE 1 + /* Fetch type information table */ static const struct fetch_type { const char *name; /* Name of type */ @@ -264,14 +404,16 @@ static const struct fetch_type { int is_signed; /* Signed flag */ print_type_func_t print; /* Print functions */ const char *fmt; /* Fromat string */ + const char *fmttype; /* Name in format file */ /* Fetch functions */ - fetch_func_t reg; - fetch_func_t stack; - fetch_func_t retval; - fetch_func_t memory; - fetch_func_t symbol; - fetch_func_t deref; + fetch_func_t fetch[FETCH_MTD_END]; } fetch_type_table[] = { + /* Special types */ + [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string, + sizeof(u32), 1, "__data_loc char[]"), + [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32, + string_size, sizeof(u32), 0, "u32"), + /* Basic types */ ASSIGN_FETCH_TYPE(u8, u8, 0), ASSIGN_FETCH_TYPE(u16, u16, 0), ASSIGN_FETCH_TYPE(u32, u32, 0), @@ -302,12 +444,28 @@ static __kprobes void fetch_stack_address(struct pt_regs *regs, *(unsigned long *)dest = kernel_stack_pointer(regs); } +static fetch_func_t get_fetch_size_function(const struct fetch_type *type, + fetch_func_t orig_fn) +{ + int i; + + if (type != &fetch_type_table[FETCH_TYPE_STRING]) + return NULL; /* Only string type needs size function */ + for (i = 0; i < FETCH_MTD_END; i++) + if (type->fetch[i] == orig_fn) + return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i]; + + WARN_ON(1); /* This should not happen */ + return NULL; +} + /** * Kprobe event core functions */ struct probe_arg { struct fetch_param fetch; + struct fetch_param fetch_size; unsigned int offset; /* Offset from argument entry */ const char *name; /* Name of this argument */ const char *comm; /* Command of this argument */ @@ -429,9 +587,9 @@ error: static void free_probe_arg(struct probe_arg *arg) { - if (CHECK_BASIC_FETCH_FUNCS(deref, arg->fetch.fn)) + if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) free_deref_fetch_param(arg->fetch.data); - else if (CHECK_BASIC_FETCH_FUNCS(symbol, arg->fetch.fn)) + else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) free_symbol_cache(arg->fetch.data); kfree(arg->name); kfree(arg->comm); @@ -548,7 +706,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, if (strcmp(arg, "retval") == 0) { if (is_return) - f->fn = t->retval; + f->fn = t->fetch[FETCH_MTD_retval]; else ret = -EINVAL; } else if (strncmp(arg, "stack", 5) == 0) { @@ -562,7 +720,7 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t, if (ret || param > PARAM_MAX_STACK) ret = -EINVAL; else { - f->fn = t->stack; + f->fn = t->fetch[FETCH_MTD_stack]; f->data = (void *)param; } } else @@ -588,7 +746,7 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t, case '%': /* named register */ ret = regs_query_register_offset(arg + 1); if (ret >= 0) { - f->fn = t->reg; + f->fn = t->fetch[FETCH_MTD_reg]; f->data = (void *)(unsigned long)ret; ret = 0; } @@ -598,7 +756,7 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t, ret = strict_strtoul(arg + 1, 0, ¶m); if (ret) break; - f->fn = t->memory; + f->fn = t->fetch[FETCH_MTD_memory]; f->data = (void *)param; } else { ret = split_symbol_offset(arg + 1, &offset); @@ -606,7 +764,7 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t, break; f->data = alloc_symbol_cache(arg + 1, offset); if (f->data) - f->fn = t->symbol; + f->fn = t->fetch[FETCH_MTD_symbol]; } break; case '+': /* deref memory */ @@ -636,14 +794,17 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t, if (ret) kfree(dprm); else { - f->fn = t->deref; + f->fn = t->fetch[FETCH_MTD_deref]; f->data = (void *)dprm; } } break; } - if (!ret && !f->fn) + if (!ret && !f->fn) { /* Parsed, but do not find fetch method */ + pr_info("%s type has no corresponding fetch method.\n", + t->name); ret = -EINVAL; + } return ret; } @@ -652,6 +813,7 @@ static int parse_probe_arg(char *arg, struct trace_probe *tp, struct probe_arg *parg, int is_return) { const char *t; + int ret; if (strlen(arg) > MAX_ARGSTR_LEN) { pr_info("Argument is too long.: %s\n", arg); @@ -674,7 +836,13 @@ static int parse_probe_arg(char *arg, struct trace_probe *tp, } parg->offset = tp->size; tp->size += parg->type->size; - return __parse_probe_arg(arg, parg->type, &parg->fetch, is_return); + ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return); + if (ret >= 0) { + parg->fetch_size.fn = get_fetch_size_function(parg->type, + parg->fetch.fn); + parg->fetch_size.data = parg->fetch.data; + } + return ret; } /* Return 1 if name is reserved or already used by another argument */ @@ -757,14 +925,17 @@ static int create_trace_probe(int argc, char **argv) pr_info("Delete command needs an event name.\n"); return -EINVAL; } + mutex_lock(&probe_lock); tp = find_probe_event(event, group); if (!tp) { + mutex_unlock(&probe_lock); pr_info("Event %s/%s doesn't exist.\n", group, event); return -ENOENT; } /* delete an event */ unregister_trace_probe(tp); free_trace_probe(tp); + mutex_unlock(&probe_lock); return 0; } @@ -1043,6 +1214,54 @@ static const struct file_operations kprobe_profile_ops = { .release = seq_release, }; +/* Sum up total data length for dynamic arraies (strings) */ +static __kprobes int __get_data_size(struct trace_probe *tp, + struct pt_regs *regs) +{ + int i, ret = 0; + u32 len; + + for (i = 0; i < tp->nr_args; i++) + if (unlikely(tp->args[i].fetch_size.fn)) { + call_fetch(&tp->args[i].fetch_size, regs, &len); + ret += len; + } + + return ret; +} + +/* Store the value of each argument */ +static __kprobes void store_trace_args(int ent_size, struct trace_probe *tp, + struct pt_regs *regs, + u8 *data, int maxlen) +{ + int i; + u32 end = tp->size; + u32 *dl; /* Data (relative) location */ + + for (i = 0; i < tp->nr_args; i++) { + if (unlikely(tp->args[i].fetch_size.fn)) { + /* + * First, we set the relative location and + * maximum data length to *dl + */ + dl = (u32 *)(data + tp->args[i].offset); + *dl = make_data_rloc(maxlen, end - tp->args[i].offset); + /* Then try to fetch string or dynamic array data */ + call_fetch(&tp->args[i].fetch, regs, dl); + /* Reduce maximum length */ + end += get_rloc_len(*dl); + maxlen -= get_rloc_len(*dl); + /* Trick here, convert data_rloc to data_loc */ + *dl = convert_rloc_to_loc(*dl, + ent_size + tp->args[i].offset); + } else + /* Just fetching data normally */ + call_fetch(&tp->args[i].fetch, regs, + data + tp->args[i].offset); + } +} + /* Kprobe handler */ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) { @@ -1050,8 +1269,7 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) struct kprobe_trace_entry_head *entry; struct ring_buffer_event *event; struct ring_buffer *buffer; - u8 *data; - int size, i, pc; + int size, dsize, pc; unsigned long irq_flags; struct ftrace_event_call *call = &tp->call; @@ -1060,7 +1278,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) local_save_flags(irq_flags); pc = preempt_count(); - size = sizeof(*entry) + tp->size; + dsize = __get_data_size(tp, regs); + size = sizeof(*entry) + tp->size + dsize; event = trace_current_buffer_lock_reserve(&buffer, call->event.type, size, irq_flags, pc); @@ -1069,9 +1288,7 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) entry = ring_buffer_event_data(event); entry->ip = (unsigned long)kp->addr; - data = (u8 *)&entry[1]; - for (i = 0; i < tp->nr_args; i++) - call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); + store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); if (!filter_current_check_discard(buffer, call, entry, event)) trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc); @@ -1085,15 +1302,15 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, struct kretprobe_trace_entry_head *entry; struct ring_buffer_event *event; struct ring_buffer *buffer; - u8 *data; - int size, i, pc; + int size, pc, dsize; unsigned long irq_flags; struct ftrace_event_call *call = &tp->call; local_save_flags(irq_flags); pc = preempt_count(); - size = sizeof(*entry) + tp->size; + dsize = __get_data_size(tp, regs); + size = sizeof(*entry) + tp->size + dsize; event = trace_current_buffer_lock_reserve(&buffer, call->event.type, size, irq_flags, pc); @@ -1103,9 +1320,7 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, entry = ring_buffer_event_data(event); entry->func = (unsigned long)tp->rp.kp.addr; entry->ret_ip = (unsigned long)ri->ret_addr; - data = (u8 *)&entry[1]; - for (i = 0; i < tp->nr_args; i++) - call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); + store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); if (!filter_current_check_discard(buffer, call, entry, event)) trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc); @@ -1137,7 +1352,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags, data = (u8 *)&field[1]; for (i = 0; i < tp->nr_args; i++) if (!tp->args[i].type->print(s, tp->args[i].name, - data + tp->args[i].offset)) + data + tp->args[i].offset, field)) goto partial; if (!trace_seq_puts(s, "\n")) @@ -1179,7 +1394,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, data = (u8 *)&field[1]; for (i = 0; i < tp->nr_args; i++) if (!tp->args[i].type->print(s, tp->args[i].name, - data + tp->args[i].offset)) + data + tp->args[i].offset, field)) goto partial; if (!trace_seq_puts(s, "\n")) @@ -1214,11 +1429,6 @@ static void probe_event_disable(struct ftrace_event_call *call) } } -static int probe_event_raw_init(struct ftrace_event_call *event_call) -{ - return 0; -} - #undef DEFINE_FIELD #define DEFINE_FIELD(type, item, name, is_signed) \ do { \ @@ -1239,7 +1449,7 @@ static int kprobe_event_define_fields(struct ftrace_event_call *event_call) DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); /* Set argument names as fields */ for (i = 0; i < tp->nr_args; i++) { - ret = trace_define_field(event_call, tp->args[i].type->name, + ret = trace_define_field(event_call, tp->args[i].type->fmttype, tp->args[i].name, sizeof(field) + tp->args[i].offset, tp->args[i].type->size, @@ -1261,7 +1471,7 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call) DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0); /* Set argument names as fields */ for (i = 0; i < tp->nr_args; i++) { - ret = trace_define_field(event_call, tp->args[i].type->name, + ret = trace_define_field(event_call, tp->args[i].type->fmttype, tp->args[i].name, sizeof(field) + tp->args[i].offset, tp->args[i].type->size, @@ -1301,8 +1511,13 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len) pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); for (i = 0; i < tp->nr_args; i++) { - pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s", - tp->args[i].name); + if (strcmp(tp->args[i].type->name, "string") == 0) + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", __get_str(%s)", + tp->args[i].name); + else + pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s", + tp->args[i].name); } #undef LEN_OR_ZERO @@ -1339,11 +1554,11 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, struct ftrace_event_call *call = &tp->call; struct kprobe_trace_entry_head *entry; struct hlist_head *head; - u8 *data; - int size, __size, i; + int size, __size, dsize; int rctx; - __size = sizeof(*entry) + tp->size; + dsize = __get_data_size(tp, regs); + __size = sizeof(*entry) + tp->size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, @@ -1355,9 +1570,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp, return; entry->ip = (unsigned long)kp->addr; - data = (u8 *)&entry[1]; - for (i = 0; i < tp->nr_args; i++) - call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); + memset(&entry[1], 0, dsize); + store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); head = this_cpu_ptr(call->perf_events); perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head); @@ -1371,11 +1585,11 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, struct ftrace_event_call *call = &tp->call; struct kretprobe_trace_entry_head *entry; struct hlist_head *head; - u8 *data; - int size, __size, i; + int size, __size, dsize; int rctx; - __size = sizeof(*entry) + tp->size; + dsize = __get_data_size(tp, regs); + __size = sizeof(*entry) + tp->size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, @@ -1388,9 +1602,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, entry->func = (unsigned long)tp->rp.kp.addr; entry->ret_ip = (unsigned long)ri->ret_addr; - data = (u8 *)&entry[1]; - for (i = 0; i < tp->nr_args; i++) - call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset); + store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); head = this_cpu_ptr(call->perf_events); perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head); @@ -1486,15 +1698,12 @@ static int register_probe_event(struct trace_probe *tp) int ret; /* Initialize ftrace_event_call */ + INIT_LIST_HEAD(&call->class->fields); if (probe_is_return(tp)) { - INIT_LIST_HEAD(&call->class->fields); call->event.funcs = &kretprobe_funcs; - call->class->raw_init = probe_event_raw_init; call->class->define_fields = kretprobe_event_define_fields; } else { - INIT_LIST_HEAD(&call->class->fields); call->event.funcs = &kprobe_funcs; - call->class->raw_init = probe_event_raw_init; call->class->define_fields = kprobe_event_define_fields; } if (set_print_fmt(tp) < 0) diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c deleted file mode 100644 index 8eaf00749b6..00000000000 --- a/kernel/trace/trace_ksym.c +++ /dev/null @@ -1,508 +0,0 @@ -/* - * trace_ksym.c - Kernel Symbol Tracer - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - * Copyright (C) IBM Corporation, 2009 - */ - -#include <linux/kallsyms.h> -#include <linux/uaccess.h> -#include <linux/debugfs.h> -#include <linux/ftrace.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/fs.h> - -#include "trace_output.h" -#include "trace.h" - -#include <linux/hw_breakpoint.h> -#include <asm/hw_breakpoint.h> - -#include <asm/atomic.h> - -#define KSYM_TRACER_OP_LEN 3 /* rw- */ - -struct trace_ksym { - struct perf_event **ksym_hbp; - struct perf_event_attr attr; -#ifdef CONFIG_PROFILE_KSYM_TRACER - atomic64_t counter; -#endif - struct hlist_node ksym_hlist; -}; - -static struct trace_array *ksym_trace_array; - -static unsigned int ksym_tracing_enabled; - -static HLIST_HEAD(ksym_filter_head); - -static DEFINE_MUTEX(ksym_tracer_mutex); - -#ifdef CONFIG_PROFILE_KSYM_TRACER - -#define MAX_UL_INT 0xffffffff - -void ksym_collect_stats(unsigned long hbp_hit_addr) -{ - struct hlist_node *node; - struct trace_ksym *entry; - - rcu_read_lock(); - hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) { - if (entry->attr.bp_addr == hbp_hit_addr) { - atomic64_inc(&entry->counter); - break; - } - } - rcu_read_unlock(); -} -#endif /* CONFIG_PROFILE_KSYM_TRACER */ - -void ksym_hbp_handler(struct perf_event *hbp, int nmi, - struct perf_sample_data *data, - struct pt_regs *regs) -{ - struct ring_buffer_event *event; - struct ksym_trace_entry *entry; - struct ring_buffer *buffer; - int pc; - - if (!ksym_tracing_enabled) - return; - - buffer = ksym_trace_array->buffer; - - pc = preempt_count(); - - event = trace_buffer_lock_reserve(buffer, TRACE_KSYM, - sizeof(*entry), 0, pc); - if (!event) - return; - - entry = ring_buffer_event_data(event); - entry->ip = instruction_pointer(regs); - entry->type = hw_breakpoint_type(hbp); - entry->addr = hw_breakpoint_addr(hbp); - strlcpy(entry->cmd, current->comm, TASK_COMM_LEN); - -#ifdef CONFIG_PROFILE_KSYM_TRACER - ksym_collect_stats(hw_breakpoint_addr(hbp)); -#endif /* CONFIG_PROFILE_KSYM_TRACER */ - - trace_buffer_unlock_commit(buffer, event, 0, pc); -} - -/* Valid access types are represented as - * - * rw- : Set Read/Write Access Breakpoint - * -w- : Set Write Access Breakpoint - * --- : Clear Breakpoints - * --x : Set Execution Break points (Not available yet) - * - */ -static int ksym_trace_get_access_type(char *str) -{ - int access = 0; - - if (str[0] == 'r') - access |= HW_BREAKPOINT_R; - - if (str[1] == 'w') - access |= HW_BREAKPOINT_W; - - if (str[2] == 'x') - access |= HW_BREAKPOINT_X; - - switch (access) { - case HW_BREAKPOINT_R: - case HW_BREAKPOINT_W: - case HW_BREAKPOINT_W | HW_BREAKPOINT_R: - return access; - default: - return -EINVAL; - } -} - -/* - * There can be several possible malformed requests and we attempt to capture - * all of them. We enumerate some of the rules - * 1. We will not allow kernel symbols with ':' since it is used as a delimiter. - * i.e. multiple ':' symbols disallowed. Possible uses are of the form - * <module>:<ksym_name>:<op>. - * 2. No delimiter symbol ':' in the input string - * 3. Spurious operator symbols or symbols not in their respective positions - * 4. <ksym_name>:--- i.e. clear breakpoint request when ksym_name not in file - * 5. Kernel symbol not a part of /proc/kallsyms - * 6. Duplicate requests - */ -static int parse_ksym_trace_str(char *input_string, char **ksymname, - unsigned long *addr) -{ - int ret; - - *ksymname = strsep(&input_string, ":"); - *addr = kallsyms_lookup_name(*ksymname); - - /* Check for malformed request: (2), (1) and (5) */ - if ((!input_string) || - (strlen(input_string) != KSYM_TRACER_OP_LEN) || - (*addr == 0)) - return -EINVAL;; - - ret = ksym_trace_get_access_type(input_string); - - return ret; -} - -int process_new_ksym_entry(char *ksymname, int op, unsigned long addr) -{ - struct trace_ksym *entry; - int ret = -ENOMEM; - - entry = kzalloc(sizeof(struct trace_ksym), GFP_KERNEL); - if (!entry) - return -ENOMEM; - - hw_breakpoint_init(&entry->attr); - - entry->attr.bp_type = op; - entry->attr.bp_addr = addr; - entry->attr.bp_len = HW_BREAKPOINT_LEN_4; - - entry->ksym_hbp = register_wide_hw_breakpoint(&entry->attr, - ksym_hbp_handler); - - if (IS_ERR(entry->ksym_hbp)) { - ret = PTR_ERR(entry->ksym_hbp); - if (ret == -ENOSPC) { - printk(KERN_ERR "ksym_tracer: Maximum limit reached." - " No new requests for tracing can be accepted now.\n"); - } else { - printk(KERN_INFO "ksym_tracer request failed. Try again" - " later!!\n"); - } - goto err; - } - - hlist_add_head_rcu(&(entry->ksym_hlist), &ksym_filter_head); - - return 0; - -err: - kfree(entry); - - return ret; -} - -static ssize_t ksym_trace_filter_read(struct file *filp, char __user *ubuf, - size_t count, loff_t *ppos) -{ - struct trace_ksym *entry; - struct hlist_node *node; - struct trace_seq *s; - ssize_t cnt = 0; - int ret; - - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; - trace_seq_init(s); - - mutex_lock(&ksym_tracer_mutex); - - hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) { - ret = trace_seq_printf(s, "%pS:", - (void *)(unsigned long)entry->attr.bp_addr); - if (entry->attr.bp_type == HW_BREAKPOINT_R) - ret = trace_seq_puts(s, "r--\n"); - else if (entry->attr.bp_type == HW_BREAKPOINT_W) - ret = trace_seq_puts(s, "-w-\n"); - else if (entry->attr.bp_type == (HW_BREAKPOINT_W | HW_BREAKPOINT_R)) - ret = trace_seq_puts(s, "rw-\n"); - WARN_ON_ONCE(!ret); - } - - cnt = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len); - - mutex_unlock(&ksym_tracer_mutex); - - kfree(s); - - return cnt; -} - -static void __ksym_trace_reset(void) -{ - struct trace_ksym *entry; - struct hlist_node *node, *node1; - - mutex_lock(&ksym_tracer_mutex); - hlist_for_each_entry_safe(entry, node, node1, &ksym_filter_head, - ksym_hlist) { - unregister_wide_hw_breakpoint(entry->ksym_hbp); - hlist_del_rcu(&(entry->ksym_hlist)); - synchronize_rcu(); - kfree(entry); - } - mutex_unlock(&ksym_tracer_mutex); -} - -static ssize_t ksym_trace_filter_write(struct file *file, - const char __user *buffer, - size_t count, loff_t *ppos) -{ - struct trace_ksym *entry; - struct hlist_node *node; - char *buf, *input_string, *ksymname = NULL; - unsigned long ksym_addr = 0; - int ret, op, changed = 0; - - buf = kzalloc(count + 1, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - ret = -EFAULT; - if (copy_from_user(buf, buffer, count)) - goto out; - - buf[count] = '\0'; - input_string = strstrip(buf); - - /* - * Clear all breakpoints if: - * 1: echo > ksym_trace_filter - * 2: echo 0 > ksym_trace_filter - * 3: echo "*:---" > ksym_trace_filter - */ - if (!input_string[0] || !strcmp(input_string, "0") || - !strcmp(input_string, "*:---")) { - __ksym_trace_reset(); - ret = 0; - goto out; - } - - ret = op = parse_ksym_trace_str(input_string, &ksymname, &ksym_addr); - if (ret < 0) - goto out; - - mutex_lock(&ksym_tracer_mutex); - - ret = -EINVAL; - hlist_for_each_entry(entry, node, &ksym_filter_head, ksym_hlist) { - if (entry->attr.bp_addr == ksym_addr) { - /* Check for malformed request: (6) */ - if (entry->attr.bp_type != op) - changed = 1; - else - goto out_unlock; - break; - } - } - if (changed) { - unregister_wide_hw_breakpoint(entry->ksym_hbp); - entry->attr.bp_type = op; - ret = 0; - if (op > 0) { - entry->ksym_hbp = - register_wide_hw_breakpoint(&entry->attr, - ksym_hbp_handler); - if (IS_ERR(entry->ksym_hbp)) - ret = PTR_ERR(entry->ksym_hbp); - else - goto out_unlock; - } - /* Error or "symbol:---" case: drop it */ - hlist_del_rcu(&(entry->ksym_hlist)); - synchronize_rcu(); - kfree(entry); - goto out_unlock; - } else { - /* Check for malformed request: (4) */ - if (op) - ret = process_new_ksym_entry(ksymname, op, ksym_addr); - } -out_unlock: - mutex_unlock(&ksym_tracer_mutex); -out: - kfree(buf); - return !ret ? count : ret; -} - -static const struct file_operations ksym_tracing_fops = { - .open = tracing_open_generic, - .read = ksym_trace_filter_read, - .write = ksym_trace_filter_write, -}; - -static void ksym_trace_reset(struct trace_array *tr) -{ - ksym_tracing_enabled = 0; - __ksym_trace_reset(); -} - -static int ksym_trace_init(struct trace_array *tr) -{ - int cpu, ret = 0; - - for_each_online_cpu(cpu) - tracing_reset(tr, cpu); - ksym_tracing_enabled = 1; - ksym_trace_array = tr; - - return ret; -} - -static void ksym_trace_print_header(struct seq_file *m) -{ - seq_puts(m, - "# TASK-PID CPU# Symbol " - "Type Function\n"); - seq_puts(m, - "# | | | " - " | |\n"); -} - -static enum print_line_t ksym_trace_output(struct trace_iterator *iter) -{ - struct trace_entry *entry = iter->ent; - struct trace_seq *s = &iter->seq; - struct ksym_trace_entry *field; - char str[KSYM_SYMBOL_LEN]; - int ret; - - if (entry->type != TRACE_KSYM) - return TRACE_TYPE_UNHANDLED; - - trace_assign_type(field, entry); - - ret = trace_seq_printf(s, "%11s-%-5d [%03d] %pS", field->cmd, - entry->pid, iter->cpu, (char *)field->addr); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - switch (field->type) { - case HW_BREAKPOINT_R: - ret = trace_seq_printf(s, " R "); - break; - case HW_BREAKPOINT_W: - ret = trace_seq_printf(s, " W "); - break; - case HW_BREAKPOINT_R | HW_BREAKPOINT_W: - ret = trace_seq_printf(s, " RW "); - break; - default: - return TRACE_TYPE_PARTIAL_LINE; - } - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - sprint_symbol(str, field->ip); - ret = trace_seq_printf(s, "%s\n", str); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - return TRACE_TYPE_HANDLED; -} - -struct tracer ksym_tracer __read_mostly = -{ - .name = "ksym_tracer", - .init = ksym_trace_init, - .reset = ksym_trace_reset, -#ifdef CONFIG_FTRACE_SELFTEST - .selftest = trace_selftest_startup_ksym, -#endif - .print_header = ksym_trace_print_header, - .print_line = ksym_trace_output -}; - -#ifdef CONFIG_PROFILE_KSYM_TRACER -static int ksym_profile_show(struct seq_file *m, void *v) -{ - struct hlist_node *node; - struct trace_ksym *entry; - int access_type = 0; - char fn_name[KSYM_NAME_LEN]; - - seq_puts(m, " Access Type "); - seq_puts(m, " Symbol Counter\n"); - seq_puts(m, " ----------- "); - seq_puts(m, " ------ -------\n"); - - rcu_read_lock(); - hlist_for_each_entry_rcu(entry, node, &ksym_filter_head, ksym_hlist) { - - access_type = entry->attr.bp_type; - - switch (access_type) { - case HW_BREAKPOINT_R: - seq_puts(m, " R "); - break; - case HW_BREAKPOINT_W: - seq_puts(m, " W "); - break; - case HW_BREAKPOINT_R | HW_BREAKPOINT_W: - seq_puts(m, " RW "); - break; - default: - seq_puts(m, " NA "); - } - - if (lookup_symbol_name(entry->attr.bp_addr, fn_name) >= 0) - seq_printf(m, " %-36s", fn_name); - else - seq_printf(m, " %-36s", "<NA>"); - seq_printf(m, " %15llu\n", - (unsigned long long)atomic64_read(&entry->counter)); - } - rcu_read_unlock(); - - return 0; -} - -static int ksym_profile_open(struct inode *node, struct file *file) -{ - return single_open(file, ksym_profile_show, NULL); -} - -static const struct file_operations ksym_profile_fops = { - .open = ksym_profile_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif /* CONFIG_PROFILE_KSYM_TRACER */ - -__init static int init_ksym_trace(void) -{ - struct dentry *d_tracer; - - d_tracer = tracing_init_dentry(); - - trace_create_file("ksym_trace_filter", 0644, d_tracer, - NULL, &ksym_tracing_fops); - -#ifdef CONFIG_PROFILE_KSYM_TRACER - trace_create_file("ksym_profile", 0444, d_tracer, - NULL, &ksym_profile_fops); -#endif - - return register_tracer(&ksym_tracer); -} -device_initcall(init_ksym_trace); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 57c1b459647..02272baa220 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -16,9 +16,6 @@ DECLARE_RWSEM(trace_event_mutex); -DEFINE_PER_CPU(struct trace_seq, ftrace_event_seq); -EXPORT_PER_CPU_SYMBOL(ftrace_event_seq); - static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly; static int next_event_type = __TRACE_LAST_TYPE + 1; @@ -1069,65 +1066,6 @@ static struct trace_event trace_wake_event = { .funcs = &trace_wake_funcs, }; -/* TRACE_SPECIAL */ -static enum print_line_t trace_special_print(struct trace_iterator *iter, - int flags, struct trace_event *event) -{ - struct special_entry *field; - - trace_assign_type(field, iter->ent); - - if (!trace_seq_printf(&iter->seq, "# %ld %ld %ld\n", - field->arg1, - field->arg2, - field->arg3)) - return TRACE_TYPE_PARTIAL_LINE; - - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t trace_special_hex(struct trace_iterator *iter, - int flags, struct trace_event *event) -{ - struct special_entry *field; - struct trace_seq *s = &iter->seq; - - trace_assign_type(field, iter->ent); - - SEQ_PUT_HEX_FIELD_RET(s, field->arg1); - SEQ_PUT_HEX_FIELD_RET(s, field->arg2); - SEQ_PUT_HEX_FIELD_RET(s, field->arg3); - - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t trace_special_bin(struct trace_iterator *iter, - int flags, struct trace_event *event) -{ - struct special_entry *field; - struct trace_seq *s = &iter->seq; - - trace_assign_type(field, iter->ent); - - SEQ_PUT_FIELD_RET(s, field->arg1); - SEQ_PUT_FIELD_RET(s, field->arg2); - SEQ_PUT_FIELD_RET(s, field->arg3); - - return TRACE_TYPE_HANDLED; -} - -static struct trace_event_functions trace_special_funcs = { - .trace = trace_special_print, - .raw = trace_special_print, - .hex = trace_special_hex, - .binary = trace_special_bin, -}; - -static struct trace_event trace_special_event = { - .type = TRACE_SPECIAL, - .funcs = &trace_special_funcs, -}; - /* TRACE_STACK */ static enum print_line_t trace_stack_print(struct trace_iterator *iter, @@ -1161,9 +1099,6 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter, static struct trace_event_functions trace_stack_funcs = { .trace = trace_stack_print, - .raw = trace_special_print, - .hex = trace_special_hex, - .binary = trace_special_bin, }; static struct trace_event trace_stack_event = { @@ -1194,9 +1129,6 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter, static struct trace_event_functions trace_user_stack_funcs = { .trace = trace_user_stack_print, - .raw = trace_special_print, - .hex = trace_special_hex, - .binary = trace_special_bin, }; static struct trace_event trace_user_stack_event = { @@ -1314,7 +1246,6 @@ static struct trace_event *events[] __initdata = { &trace_fn_event, &trace_ctx_event, &trace_wake_event, - &trace_special_event, &trace_stack_event, &trace_user_stack_event, &trace_bprint_event, diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 0e73bc2ef8c..4086eae6e81 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -46,7 +46,6 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) struct trace_array_cpu *data; unsigned long flags; long disabled; - int resched; int cpu; int pc; @@ -54,7 +53,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) return; pc = preempt_count(); - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); if (cpu != wakeup_current_cpu) @@ -74,7 +73,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) out: atomic_dec(&data->disabled); out_enable: - ftrace_preempt_enable(resched); + preempt_enable_notrace(); } static struct ftrace_ops trace_ops __read_mostly = @@ -383,6 +382,7 @@ static struct tracer wakeup_tracer __read_mostly = #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif + .use_max_tr = 1, }; static struct tracer wakeup_rt_tracer __read_mostly = @@ -397,6 +397,7 @@ static struct tracer wakeup_rt_tracer __read_mostly = #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif + .use_max_tr = 1, }; __init static int init_wakeup_tracer(void) diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 250e7f9bd2f..155a415b320 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -13,11 +13,9 @@ static inline int trace_valid_entry(struct trace_entry *entry) case TRACE_WAKE: case TRACE_STACK: case TRACE_PRINT: - case TRACE_SPECIAL: case TRACE_BRANCH: case TRACE_GRAPH_ENT: case TRACE_GRAPH_RET: - case TRACE_KSYM: return 1; } return 0; @@ -691,38 +689,6 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr } #endif /* CONFIG_CONTEXT_SWITCH_TRACER */ -#ifdef CONFIG_SYSPROF_TRACER -int -trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr) -{ - unsigned long count; - int ret; - - /* start the tracing */ - ret = tracer_init(trace, tr); - if (ret) { - warn_failed_init_tracer(trace, ret); - return ret; - } - - /* Sleep for a 1/10 of a second */ - msleep(100); - /* stop the tracing. */ - tracing_stop(); - /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); - trace->reset(tr); - tracing_start(); - - if (!ret && !count) { - printk(KERN_CONT ".. no entries found .."); - ret = -1; - } - - return ret; -} -#endif /* CONFIG_SYSPROF_TRACER */ - #ifdef CONFIG_BRANCH_TRACER int trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) @@ -755,56 +721,3 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) } #endif /* CONFIG_BRANCH_TRACER */ -#ifdef CONFIG_KSYM_TRACER -static int ksym_selftest_dummy; - -int -trace_selftest_startup_ksym(struct tracer *trace, struct trace_array *tr) -{ - unsigned long count; - int ret; - - /* start the tracing */ - ret = tracer_init(trace, tr); - if (ret) { - warn_failed_init_tracer(trace, ret); - return ret; - } - - ksym_selftest_dummy = 0; - /* Register the read-write tracing request */ - - ret = process_new_ksym_entry("ksym_selftest_dummy", - HW_BREAKPOINT_R | HW_BREAKPOINT_W, - (unsigned long)(&ksym_selftest_dummy)); - - if (ret < 0) { - printk(KERN_CONT "ksym_trace read-write startup test failed\n"); - goto ret_path; - } - /* Perform a read and a write operation over the dummy variable to - * trigger the tracer - */ - if (ksym_selftest_dummy == 0) - ksym_selftest_dummy++; - - /* stop the tracing. */ - tracing_stop(); - /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); - trace->reset(tr); - tracing_start(); - - /* read & write operations - one each is performed on the dummy variable - * triggering two entries in the trace buffer - */ - if (!ret && count != 2) { - printk(KERN_CONT "Ksym tracer startup test failed"); - ret = -1; - } - -ret_path: - return ret; -} -#endif /* CONFIG_KSYM_TRACER */ - diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index f4bc9b27de5..056468eae7c 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -110,12 +110,12 @@ static inline void check_stack(void) static void stack_trace_call(unsigned long ip, unsigned long parent_ip) { - int cpu, resched; + int cpu; if (unlikely(!ftrace_enabled || stack_trace_disabled)) return; - resched = ftrace_preempt_disable(); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); /* no atomic needed, we only modify this variable by this cpu */ @@ -127,7 +127,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) out: per_cpu(trace_active, cpu)--; /* prevent recursion in schedule */ - ftrace_preempt_enable(resched); + preempt_enable_notrace(); } static struct ftrace_ops trace_ops __read_mostly = diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 34e35804304..bac752f0cfb 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -23,6 +23,9 @@ static int syscall_exit_register(struct ftrace_event_call *event, static int syscall_enter_define_fields(struct ftrace_event_call *call); static int syscall_exit_define_fields(struct ftrace_event_call *call); +/* All syscall exit events have the same fields */ +static LIST_HEAD(syscall_exit_fields); + static struct list_head * syscall_get_enter_fields(struct ftrace_event_call *call) { @@ -34,9 +37,7 @@ syscall_get_enter_fields(struct ftrace_event_call *call) static struct list_head * syscall_get_exit_fields(struct ftrace_event_call *call) { - struct syscall_metadata *entry = call->data; - - return &entry->exit_fields; + return &syscall_exit_fields; } struct trace_event_functions enter_syscall_print_funcs = { diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c deleted file mode 100644 index a7974a552ca..00000000000 --- a/kernel/trace/trace_sysprof.c +++ /dev/null @@ -1,329 +0,0 @@ -/* - * trace stack traces - * - * Copyright (C) 2004-2008, Soeren Sandmann - * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com> - * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> - */ -#include <linux/kallsyms.h> -#include <linux/debugfs.h> -#include <linux/hrtimer.h> -#include <linux/uaccess.h> -#include <linux/ftrace.h> -#include <linux/module.h> -#include <linux/irq.h> -#include <linux/fs.h> - -#include <asm/stacktrace.h> - -#include "trace.h" - -static struct trace_array *sysprof_trace; -static int __read_mostly tracer_enabled; - -/* - * 1 msec sample interval by default: - */ -static unsigned long sample_period = 1000000; -static const unsigned int sample_max_depth = 512; - -static DEFINE_MUTEX(sample_timer_lock); -/* - * Per CPU hrtimers that do the profiling: - */ -static DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer); - -struct stack_frame { - const void __user *next_fp; - unsigned long return_address; -}; - -static int copy_stack_frame(const void __user *fp, struct stack_frame *frame) -{ - int ret; - - if (!access_ok(VERIFY_READ, fp, sizeof(*frame))) - return 0; - - ret = 1; - pagefault_disable(); - if (__copy_from_user_inatomic(frame, fp, sizeof(*frame))) - ret = 0; - pagefault_enable(); - - return ret; -} - -struct backtrace_info { - struct trace_array_cpu *data; - struct trace_array *tr; - int pos; -}; - -static void -backtrace_warning_symbol(void *data, char *msg, unsigned long symbol) -{ - /* Ignore warnings */ -} - -static void backtrace_warning(void *data, char *msg) -{ - /* Ignore warnings */ -} - -static int backtrace_stack(void *data, char *name) -{ - /* Don't bother with IRQ stacks for now */ - return -1; -} - -static void backtrace_address(void *data, unsigned long addr, int reliable) -{ - struct backtrace_info *info = data; - - if (info->pos < sample_max_depth && reliable) { - __trace_special(info->tr, info->data, 1, addr, 0); - - info->pos++; - } -} - -static const struct stacktrace_ops backtrace_ops = { - .warning = backtrace_warning, - .warning_symbol = backtrace_warning_symbol, - .stack = backtrace_stack, - .address = backtrace_address, - .walk_stack = print_context_stack, -}; - -static int -trace_kernel(struct pt_regs *regs, struct trace_array *tr, - struct trace_array_cpu *data) -{ - struct backtrace_info info; - unsigned long bp; - char *stack; - - info.tr = tr; - info.data = data; - info.pos = 1; - - __trace_special(info.tr, info.data, 1, regs->ip, 0); - - stack = ((char *)regs + sizeof(struct pt_regs)); -#ifdef CONFIG_FRAME_POINTER - bp = regs->bp; -#else - bp = 0; -#endif - - dump_trace(NULL, regs, (void *)stack, bp, &backtrace_ops, &info); - - return info.pos; -} - -static void timer_notify(struct pt_regs *regs, int cpu) -{ - struct trace_array_cpu *data; - struct stack_frame frame; - struct trace_array *tr; - const void __user *fp; - int is_user; - int i; - - if (!regs) - return; - - tr = sysprof_trace; - data = tr->data[cpu]; - is_user = user_mode(regs); - - if (!current || current->pid == 0) - return; - - if (is_user && current->state != TASK_RUNNING) - return; - - __trace_special(tr, data, 0, 0, current->pid); - - if (!is_user) - i = trace_kernel(regs, tr, data); - else - i = 0; - - /* - * Trace user stack if we are not a kernel thread - */ - if (current->mm && i < sample_max_depth) { - regs = (struct pt_regs *)current->thread.sp0 - 1; - - fp = (void __user *)regs->bp; - - __trace_special(tr, data, 2, regs->ip, 0); - - while (i < sample_max_depth) { - frame.next_fp = NULL; - frame.return_address = 0; - if (!copy_stack_frame(fp, &frame)) - break; - if ((unsigned long)fp < regs->sp) - break; - - __trace_special(tr, data, 2, frame.return_address, - (unsigned long)fp); - fp = frame.next_fp; - - i++; - } - - } - - /* - * Special trace entry if we overflow the max depth: - */ - if (i == sample_max_depth) - __trace_special(tr, data, -1, -1, -1); - - __trace_special(tr, data, 3, current->pid, i); -} - -static enum hrtimer_restart stack_trace_timer_fn(struct hrtimer *hrtimer) -{ - /* trace here */ - timer_notify(get_irq_regs(), smp_processor_id()); - - hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); - - return HRTIMER_RESTART; -} - -static void start_stack_timer(void *unused) -{ - struct hrtimer *hrtimer = &__get_cpu_var(stack_trace_hrtimer); - - hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hrtimer->function = stack_trace_timer_fn; - - hrtimer_start(hrtimer, ns_to_ktime(sample_period), - HRTIMER_MODE_REL_PINNED); -} - -static void start_stack_timers(void) -{ - on_each_cpu(start_stack_timer, NULL, 1); -} - -static void stop_stack_timer(int cpu) -{ - struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu); - - hrtimer_cancel(hrtimer); -} - -static void stop_stack_timers(void) -{ - int cpu; - - for_each_online_cpu(cpu) - stop_stack_timer(cpu); -} - -static void stop_stack_trace(struct trace_array *tr) -{ - mutex_lock(&sample_timer_lock); - stop_stack_timers(); - tracer_enabled = 0; - mutex_unlock(&sample_timer_lock); -} - -static int stack_trace_init(struct trace_array *tr) -{ - sysprof_trace = tr; - - tracing_start_cmdline_record(); - - mutex_lock(&sample_timer_lock); - start_stack_timers(); - tracer_enabled = 1; - mutex_unlock(&sample_timer_lock); - return 0; -} - -static void stack_trace_reset(struct trace_array *tr) -{ - tracing_stop_cmdline_record(); - stop_stack_trace(tr); -} - -static struct tracer stack_trace __read_mostly = -{ - .name = "sysprof", - .init = stack_trace_init, - .reset = stack_trace_reset, -#ifdef CONFIG_FTRACE_SELFTEST - .selftest = trace_selftest_startup_sysprof, -#endif -}; - -__init static int init_stack_trace(void) -{ - return register_tracer(&stack_trace); -} -device_initcall(init_stack_trace); - -#define MAX_LONG_DIGITS 22 - -static ssize_t -sysprof_sample_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[MAX_LONG_DIGITS]; - int r; - - r = sprintf(buf, "%ld\n", nsecs_to_usecs(sample_period)); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - -static ssize_t -sysprof_sample_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[MAX_LONG_DIGITS]; - unsigned long val; - - if (cnt > MAX_LONG_DIGITS-1) - cnt = MAX_LONG_DIGITS-1; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - val = simple_strtoul(buf, NULL, 10); - /* - * Enforce a minimum sample period of 100 usecs: - */ - if (val < 100) - val = 100; - - mutex_lock(&sample_timer_lock); - stop_stack_timers(); - sample_period = val * 1000; - start_stack_timers(); - mutex_unlock(&sample_timer_lock); - - return cnt; -} - -static const struct file_operations sysprof_sample_fops = { - .read = sysprof_sample_read, - .write = sysprof_sample_write, -}; - -void init_tracer_sysprof_debugfs(struct dentry *d_tracer) -{ - - trace_create_file("sysprof_sample_period", 0644, - d_tracer, NULL, &sysprof_sample_fops); -} diff --git a/kernel/watchdog.c b/kernel/watchdog.c new file mode 100644 index 00000000000..613bc1f0461 --- /dev/null +++ b/kernel/watchdog.c @@ -0,0 +1,567 @@ +/* + * Detect hard and soft lockups on a system + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * this code detects hard lockups: incidents in where on a CPU + * the kernel does not respond to anything except NMI. + * + * Note: Most of this code is borrowed heavily from softlockup.c, + * so thanks to Ingo for the initial implementation. + * Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks + * to those contributors as well. + */ + +#include <linux/mm.h> +#include <linux/cpu.h> +#include <linux/nmi.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/freezer.h> +#include <linux/kthread.h> +#include <linux/lockdep.h> +#include <linux/notifier.h> +#include <linux/module.h> +#include <linux/sysctl.h> + +#include <asm/irq_regs.h> +#include <linux/perf_event.h> + +int watchdog_enabled; +int __read_mostly softlockup_thresh = 60; + +static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); +static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); +static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); +static DEFINE_PER_CPU(bool, softlockup_touch_sync); +static DEFINE_PER_CPU(bool, soft_watchdog_warn); +#ifdef CONFIG_HARDLOCKUP_DETECTOR +static DEFINE_PER_CPU(bool, hard_watchdog_warn); +static DEFINE_PER_CPU(bool, watchdog_nmi_touch); +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); +static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +#endif + +static int __read_mostly did_panic; +static int __initdata no_watchdog; + + +/* boot commands */ +/* + * Should we panic when a soft-lockup or hard-lockup occurs: + */ +#ifdef CONFIG_HARDLOCKUP_DETECTOR +static int hardlockup_panic; + +static int __init hardlockup_panic_setup(char *str) +{ + if (!strncmp(str, "panic", 5)) + hardlockup_panic = 1; + return 1; +} +__setup("nmi_watchdog=", hardlockup_panic_setup); +#endif + +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; + +static int __init softlockup_panic_setup(char *str) +{ + softlockup_panic = simple_strtoul(str, NULL, 0); + + return 1; +} +__setup("softlockup_panic=", softlockup_panic_setup); + +static int __init nowatchdog_setup(char *str) +{ + no_watchdog = 1; + return 1; +} +__setup("nowatchdog", nowatchdog_setup); + +/* deprecated */ +static int __init nosoftlockup_setup(char *str) +{ + no_watchdog = 1; + return 1; +} +__setup("nosoftlockup", nosoftlockup_setup); +/* */ + + +/* + * Returns seconds, approximately. We don't need nanosecond + * resolution, and we don't need to waste time with a big divide when + * 2^30ns == 1.074s. + */ +static unsigned long get_timestamp(int this_cpu) +{ + return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */ +} + +static unsigned long get_sample_period(void) +{ + /* + * convert softlockup_thresh from seconds to ns + * the divide by 5 is to give hrtimer 5 chances to + * increment before the hardlockup detector generates + * a warning + */ + return softlockup_thresh / 5 * NSEC_PER_SEC; +} + +/* Commands for resetting the watchdog */ +static void __touch_watchdog(void) +{ + int this_cpu = smp_processor_id(); + + __get_cpu_var(watchdog_touch_ts) = get_timestamp(this_cpu); +} + +void touch_softlockup_watchdog(void) +{ + __get_cpu_var(watchdog_touch_ts) = 0; +} +EXPORT_SYMBOL(touch_softlockup_watchdog); + +void touch_all_softlockup_watchdogs(void) +{ + int cpu; + + /* + * this is done lockless + * do we care if a 0 races with a timestamp? + * all it means is the softlock check starts one cycle later + */ + for_each_online_cpu(cpu) + per_cpu(watchdog_touch_ts, cpu) = 0; +} + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +void touch_nmi_watchdog(void) +{ + __get_cpu_var(watchdog_nmi_touch) = true; + touch_softlockup_watchdog(); +} +EXPORT_SYMBOL(touch_nmi_watchdog); + +#endif + +void touch_softlockup_watchdog_sync(void) +{ + __raw_get_cpu_var(softlockup_touch_sync) = true; + __raw_get_cpu_var(watchdog_touch_ts) = 0; +} + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +/* watchdog detector functions */ +static int is_hardlockup(void) +{ + unsigned long hrint = __get_cpu_var(hrtimer_interrupts); + + if (__get_cpu_var(hrtimer_interrupts_saved) == hrint) + return 1; + + __get_cpu_var(hrtimer_interrupts_saved) = hrint; + return 0; +} +#endif + +static int is_softlockup(unsigned long touch_ts) +{ + unsigned long now = get_timestamp(smp_processor_id()); + + /* Warn about unreasonable delays: */ + if (time_after(now, touch_ts + softlockup_thresh)) + return now - touch_ts; + + return 0; +} + +static int +watchdog_panic(struct notifier_block *this, unsigned long event, void *ptr) +{ + did_panic = 1; + + return NOTIFY_DONE; +} + +static struct notifier_block panic_block = { + .notifier_call = watchdog_panic, +}; + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +static struct perf_event_attr wd_hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 1, +}; + +/* Callback function for perf event subsystem */ +void watchdog_overflow_callback(struct perf_event *event, int nmi, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + if (__get_cpu_var(watchdog_nmi_touch) == true) { + __get_cpu_var(watchdog_nmi_touch) = false; + return; + } + + /* check for a hardlockup + * This is done by making sure our timer interrupt + * is incrementing. The timer interrupt should have + * fired multiple times before we overflow'd. If it hasn't + * then this is a good indication the cpu is stuck + */ + if (is_hardlockup()) { + int this_cpu = smp_processor_id(); + + /* only print hardlockups once */ + if (__get_cpu_var(hard_watchdog_warn) == true) + return; + + if (hardlockup_panic) + panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu); + else + WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu); + + __get_cpu_var(hard_watchdog_warn) = true; + return; + } + + __get_cpu_var(hard_watchdog_warn) = false; + return; +} +static void watchdog_interrupt_count(void) +{ + __get_cpu_var(hrtimer_interrupts)++; +} +#else +static inline void watchdog_interrupt_count(void) { return; } +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ + +/* watchdog kicker functions */ +static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) +{ + unsigned long touch_ts = __get_cpu_var(watchdog_touch_ts); + struct pt_regs *regs = get_irq_regs(); + int duration; + + /* kick the hardlockup detector */ + watchdog_interrupt_count(); + + /* kick the softlockup detector */ + wake_up_process(__get_cpu_var(softlockup_watchdog)); + + /* .. and repeat */ + hrtimer_forward_now(hrtimer, ns_to_ktime(get_sample_period())); + + if (touch_ts == 0) { + if (unlikely(__get_cpu_var(softlockup_touch_sync))) { + /* + * If the time stamp was touched atomically + * make sure the scheduler tick is up to date. + */ + __get_cpu_var(softlockup_touch_sync) = false; + sched_clock_tick(); + } + __touch_watchdog(); + return HRTIMER_RESTART; + } + + /* check for a softlockup + * This is done by making sure a high priority task is + * being scheduled. The task touches the watchdog to + * indicate it is getting cpu time. If it hasn't then + * this is a good indication some task is hogging the cpu + */ + duration = is_softlockup(touch_ts); + if (unlikely(duration)) { + /* only warn once */ + if (__get_cpu_var(soft_watchdog_warn) == true) + return HRTIMER_RESTART; + + printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", + smp_processor_id(), duration, + current->comm, task_pid_nr(current)); + print_modules(); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else + dump_stack(); + + if (softlockup_panic) + panic("softlockup: hung tasks"); + __get_cpu_var(soft_watchdog_warn) = true; + } else + __get_cpu_var(soft_watchdog_warn) = false; + + return HRTIMER_RESTART; +} + + +/* + * The watchdog thread - touches the timestamp. + */ +static int watchdog(void *unused) +{ + struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; + struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); + + sched_setscheduler(current, SCHED_FIFO, ¶m); + + /* initialize timestamp */ + __touch_watchdog(); + + /* kick off the timer for the hardlockup detector */ + /* done here because hrtimer_start can only pin to smp_processor_id() */ + hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()), + HRTIMER_MODE_REL_PINNED); + + set_current_state(TASK_INTERRUPTIBLE); + /* + * Run briefly once per second to reset the softlockup timestamp. + * If this gets delayed for more than 60 seconds then the + * debug-printout triggers in watchdog_timer_fn(). + */ + while (!kthread_should_stop()) { + __touch_watchdog(); + schedule(); + + if (kthread_should_stop()) + break; + + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + + return 0; +} + + +#ifdef CONFIG_HARDLOCKUP_DETECTOR +static int watchdog_nmi_enable(int cpu) +{ + struct perf_event_attr *wd_attr; + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + /* is it already setup and enabled? */ + if (event && event->state > PERF_EVENT_STATE_OFF) + goto out; + + /* it is setup but not enabled */ + if (event != NULL) + goto out_enable; + + /* Try to register using hardware perf events */ + wd_attr = &wd_hw_attr; + wd_attr->sample_period = hw_nmi_get_sample_period(); + event = perf_event_create_kernel_counter(wd_attr, cpu, -1, watchdog_overflow_callback); + if (!IS_ERR(event)) { + printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n"); + goto out_save; + } + + printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event); + return -1; + + /* success path */ +out_save: + per_cpu(watchdog_ev, cpu) = event; +out_enable: + perf_event_enable(per_cpu(watchdog_ev, cpu)); +out: + return 0; +} + +static void watchdog_nmi_disable(int cpu) +{ + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) { + perf_event_disable(event); + per_cpu(watchdog_ev, cpu) = NULL; + + /* should be in cleanup, but blocks oprofile */ + perf_event_release_kernel(event); + } + return; +} +#else +static int watchdog_nmi_enable(int cpu) { return 0; } +static void watchdog_nmi_disable(int cpu) { return; } +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ + +/* prepare/enable/disable routines */ +static int watchdog_prepare_cpu(int cpu) +{ + struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu); + + WARN_ON(per_cpu(softlockup_watchdog, cpu)); + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; + + return 0; +} + +static int watchdog_enable(int cpu) +{ + struct task_struct *p = per_cpu(softlockup_watchdog, cpu); + + /* enable the perf event */ + if (watchdog_nmi_enable(cpu) != 0) + return -1; + + /* create the watchdog thread */ + if (!p) { + p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu); + if (IS_ERR(p)) { + printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu); + return -1; + } + kthread_bind(p, cpu); + per_cpu(watchdog_touch_ts, cpu) = 0; + per_cpu(softlockup_watchdog, cpu) = p; + wake_up_process(p); + } + + return 0; +} + +static void watchdog_disable(int cpu) +{ + struct task_struct *p = per_cpu(softlockup_watchdog, cpu); + struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu); + + /* + * cancel the timer first to stop incrementing the stats + * and waking up the kthread + */ + hrtimer_cancel(hrtimer); + + /* disable the perf event */ + watchdog_nmi_disable(cpu); + + /* stop the watchdog thread */ + if (p) { + per_cpu(softlockup_watchdog, cpu) = NULL; + kthread_stop(p); + } + + /* if any cpu succeeds, watchdog is considered enabled for the system */ + watchdog_enabled = 1; +} + +static void watchdog_enable_all_cpus(void) +{ + int cpu; + int result = 0; + + for_each_online_cpu(cpu) + result += watchdog_enable(cpu); + + if (result) + printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n"); + +} + +static void watchdog_disable_all_cpus(void) +{ + int cpu; + + for_each_online_cpu(cpu) + watchdog_disable(cpu); + + /* if all watchdogs are disabled, then they are disabled for the system */ + watchdog_enabled = 0; +} + + +/* sysctl functions */ +#ifdef CONFIG_SYSCTL +/* + * proc handler for /proc/sys/kernel/nmi_watchdog + */ + +int proc_dowatchdog_enabled(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + proc_dointvec(table, write, buffer, length, ppos); + + if (watchdog_enabled) + watchdog_enable_all_cpus(); + else + watchdog_disable_all_cpus(); + return 0; +} + +int proc_dowatchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); +} +#endif /* CONFIG_SYSCTL */ + + +/* + * Create/destroy watchdog threads as CPUs come and go: + */ +static int __cpuinit +cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + int hotcpu = (unsigned long)hcpu; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + if (watchdog_prepare_cpu(hotcpu)) + return NOTIFY_BAD; + break; + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + if (watchdog_enable(hotcpu)) + return NOTIFY_BAD; + break; +#ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + watchdog_disable(hotcpu); + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + watchdog_disable(hotcpu); + break; +#endif /* CONFIG_HOTPLUG_CPU */ + } + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata cpu_nfb = { + .notifier_call = cpu_callback +}; + +static int __init spawn_watchdog_task(void) +{ + void *cpu = (void *)(long)smp_processor_id(); + int err; + + if (no_watchdog) + return 0; + + err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); + WARN_ON(err == NOTIFY_BAD); + + cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); + register_cpu_notifier(&cpu_nfb); + + atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + + return 0; +} +early_initcall(spawn_watchdog_task); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 327d2deb445..59fef1531dd 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -68,6 +68,21 @@ struct workqueue_struct { #endif }; +#ifdef CONFIG_LOCKDEP +/** + * in_workqueue_context() - in context of specified workqueue? + * @wq: the workqueue of interest + * + * Checks lockdep state to see if the current task is executing from + * within a workqueue item. This function exists only if lockdep is + * enabled. + */ +int in_workqueue_context(struct workqueue_struct *wq) +{ + return lock_is_held(&wq->lockdep_map); +} +#endif + #ifdef CONFIG_DEBUG_OBJECTS_WORK static struct debug_obj_descr work_debug_descr; diff --git a/kernel/workqueue_sched.h b/kernel/workqueue_sched.h new file mode 100644 index 00000000000..af040babb74 --- /dev/null +++ b/kernel/workqueue_sched.h @@ -0,0 +1,16 @@ +/* + * kernel/workqueue_sched.h + * + * Scheduler hooks for concurrency managed workqueue. Only to be + * included from sched.c and workqueue.c. + */ +static inline void wq_worker_waking_up(struct task_struct *task, + unsigned int cpu) +{ +} + +static inline struct task_struct *wq_worker_sleeping(struct task_struct *task, + unsigned int cpu) +{ + return NULL; +} diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 4608952884d..79e0dff1cdc 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -151,28 +151,33 @@ config DEBUG_SHIRQ Drivers ought to be able to handle interrupts coming in at those points; some don't and need to be caught. -config DETECT_SOFTLOCKUP - bool "Detect Soft Lockups" +config LOCKUP_DETECTOR + bool "Detect Hard and Soft Lockups" depends on DEBUG_KERNEL && !S390 - default y help - Say Y here to enable the kernel to detect "soft lockups", - which are bugs that cause the kernel to loop in kernel + Say Y here to enable the kernel to act as a watchdog to detect + hard and soft lockups. + + Softlockups are bugs that cause the kernel to loop in kernel mode for more than 60 seconds, without giving other tasks a - chance to run. + chance to run. The current stack trace is displayed upon + detection and the system will stay locked up. - When a soft-lockup is detected, the kernel will print the - current stack trace (which you should report), but the - system will stay locked up. This feature has negligible - overhead. + Hardlockups are bugs that cause the CPU to loop in kernel mode + for more than 60 seconds, without letting other interrupts have a + chance to run. The current stack trace is displayed upon detection + and the system will stay locked up. - (Note that "hard lockups" are separate type of bugs that - can be detected via the NMI-watchdog, on platforms that - support it.) + The overhead should be minimal. A periodic hrtimer runs to + generate interrupts and kick the watchdog task every 10-12 seconds. + An NMI is generated every 60 seconds or so to check for hardlockups. + +config HARDLOCKUP_DETECTOR + def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI config BOOTPARAM_SOFTLOCKUP_PANIC bool "Panic (Reboot) On Soft Lockups" - depends on DETECT_SOFTLOCKUP + depends on LOCKUP_DETECTOR help Say Y here to enable the kernel to panic on "soft lockups", which are bugs that cause the kernel to loop in kernel @@ -189,7 +194,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE int - depends on DETECT_SOFTLOCKUP + depends on LOCKUP_DETECTOR range 0 1 default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC default 1 if BOOTPARAM_SOFTLOCKUP_PANIC @@ -306,6 +311,12 @@ config DEBUG_OBJECTS_WORK work queue routines to track the life time of work objects and validate the work operations. +config DEBUG_OBJECTS_RCU_HEAD + bool "Debug RCU callbacks objects" + depends on DEBUG_OBJECTS && PREEMPT + help + Enable this to turn on debugging of RCU list heads (call_rcu() usage). + config DEBUG_OBJECTS_ENABLE_DEFAULT int "debug_objects bootup default value (0-1)" range 0 1 @@ -627,6 +638,19 @@ config DEBUG_INFO If unsure, say N. +config DEBUG_INFO_REDUCED + bool "Reduce debugging information" + depends on DEBUG_INFO + help + If you say Y here gcc is instructed to generate less debugging + information for structure types. This means that tools that + need full debugging information (like kgdb or systemtap) won't + be happy. But if you merely need debugging information to + resolve line numbers there is no loss. Advantage is that + build directory object sizes shrink dramatically over a full + DEBUG_INFO build and compile times are reduced too. + Only works with newer gcc versions. + config DEBUG_VM bool "Debug VM" depends on DEBUG_KERNEL diff --git a/lib/ioremap.c b/lib/ioremap.c index 14c6078f17a..5730ecd3eb6 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -13,10 +13,10 @@ #include <asm/pgtable.h> static int ioremap_pte_range(pmd_t *pmd, unsigned long addr, - unsigned long end, unsigned long phys_addr, pgprot_t prot) + unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { pte_t *pte; - unsigned long pfn; + u64 pfn; pfn = phys_addr >> PAGE_SHIFT; pte = pte_alloc_kernel(pmd, addr); @@ -31,7 +31,7 @@ static int ioremap_pte_range(pmd_t *pmd, unsigned long addr, } static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, - unsigned long end, unsigned long phys_addr, pgprot_t prot) + unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { pmd_t *pmd; unsigned long next; @@ -49,7 +49,7 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, } static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr, - unsigned long end, unsigned long phys_addr, pgprot_t prot) + unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { pud_t *pud; unsigned long next; @@ -67,7 +67,7 @@ static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr, } int ioremap_page_range(unsigned long addr, - unsigned long end, unsigned long phys_addr, pgprot_t prot) + unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { pgd_t *pgd; unsigned long start; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 123bcef13e5..f9fd3dd3916 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -665,7 +665,6 @@ int bdi_init(struct backing_dev_info *bdi) bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; spin_lock_init(&bdi->wb_lock); - INIT_RCU_HEAD(&bdi->rcu_head); INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); INIT_LIST_HEAD(&bdi->work_list); diff --git a/mm/highmem.c b/mm/highmem.c index 66baa20f78f..7a0aa1be499 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -26,6 +26,7 @@ #include <linux/init.h> #include <linux/hash.h> #include <linux/highmem.h> +#include <linux/kgdb.h> #include <asm/tlbflush.h> /* @@ -470,6 +471,12 @@ void debug_kmap_atomic(enum km_type type) warn_count--; } } +#ifdef CONFIG_KGDB_KDB + if (unlikely(type == KM_KDB && atomic_read(&kgdb_active) == -1)) { + WARN_ON(1); + warn_count--; + } +#endif /* CONFIG_KGDB_KDB */ } #endif diff --git a/mm/mmap.c b/mm/mmap.c index 456ec6f2788..e38e910cb75 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1734,8 +1734,10 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) grow = (address - vma->vm_end) >> PAGE_SHIFT; error = acct_stack_growth(vma, size, grow); - if (!error) + if (!error) { vma->vm_end = address; + perf_event_mmap(vma); + } } anon_vma_unlock(vma); return error; @@ -1781,6 +1783,7 @@ static int expand_downwards(struct vm_area_struct *vma, if (!error) { vma->vm_start = address; vma->vm_pgoff -= grow; + perf_event_mmap(vma); } } anon_vma_unlock(vma); @@ -2208,6 +2211,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len) vma->vm_page_prot = vm_get_page_prot(flags); vma_link(mm, vma, prev, rb_link, rb_parent); out: + perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) { if (!mlock_vma_pages_range(vma, addr, addr + len)) diff --git a/mm/slab.c b/mm/slab.c index e49f8f46f46..47360c3e5ab 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -102,7 +102,6 @@ #include <linux/cpu.h> #include <linux/sysctl.h> #include <linux/module.h> -#include <linux/kmemtrace.h> #include <linux/rcupdate.h> #include <linux/string.h> #include <linux/uaccess.h> diff --git a/mm/slob.c b/mm/slob.c index 23631e2bb57..3f19a347dab 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -66,8 +66,10 @@ #include <linux/module.h> #include <linux/rcupdate.h> #include <linux/list.h> -#include <linux/kmemtrace.h> #include <linux/kmemleak.h> + +#include <trace/events/kmem.h> + #include <asm/atomic.h> /* @@ -639,7 +641,6 @@ void kmem_cache_free(struct kmem_cache *c, void *b) if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) { struct slob_rcu *slob_rcu; slob_rcu = b + (c->size - sizeof(struct slob_rcu)); - INIT_RCU_HEAD(&slob_rcu->head); slob_rcu->size = c->size; call_rcu(&slob_rcu->head, kmem_rcu_free); } else { diff --git a/mm/slub.c b/mm/slub.c index 578f68f3c51..7bb7940f4ee 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -17,7 +17,6 @@ #include <linux/slab.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> -#include <linux/kmemtrace.h> #include <linux/kmemcheck.h> #include <linux/cpu.h> #include <linux/cpuset.h> diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ae007462b7f..b7e314b1009 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2403,7 +2403,7 @@ static int s_show(struct seq_file *m, void *p) seq_printf(m, " pages=%d", v->nr_pages); if (v->phys_addr) - seq_printf(m, " phys=%lx", v->phys_addr); + seq_printf(m, " phys=%llx", (unsigned long long)v->phys_addr); if (v->flags & VM_IOREMAP) seq_printf(m, " ioremap"); diff --git a/scripts/Makefile.build b/scripts/Makefile.build index e4deb73e9a8..a1a5cf95a68 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -115,7 +115,10 @@ endif # --------------------------------------------------------------------------- # Default is built-in, unless we know otherwise -modkern_cflags = $(if $(part-of-module), $(CFLAGS_MODULE), $(CFLAGS_KERNEL)) +modkern_cflags = \ + $(if $(part-of-module), \ + $(KBUILD_CFLAGS_MODULE) $(CFLAGS_MODULE), \ + $(KBUILD_CFLAGS_KERNEL) $(CFLAGS_KERNEL)) quiet_modtag := $(empty) $(empty) $(real-objs-m) : part-of-module := y @@ -156,14 +159,14 @@ $(obj)/%.i: $(src)/%.c FORCE cmd_gensymtypes = \ $(CPP) -D__GENKSYMS__ $(c_flags) $< | \ - $(GENKSYMS) -T $@ -a $(ARCH) \ + $(GENKSYMS) $(if $(1), -T $(2)) -a $(ARCH) \ $(if $(KBUILD_PRESERVE),-p) \ - $(if $(1),-r $(firstword $(wildcard $(@:.symtypes=.symref) /dev/null))) + -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null)) quiet_cmd_cc_symtypes_c = SYM $(quiet_modtag) $@ cmd_cc_symtypes_c = \ set -e; \ - $(call cmd_gensymtypes, true) >/dev/null; \ + $(call cmd_gensymtypes,true,$@) >/dev/null; \ test -s $@ || rm -f $@ $(obj)/%.symtypes : $(src)/%.c FORCE @@ -192,16 +195,16 @@ else # the actual value of the checksum generated by genksyms cmd_cc_o_c = $(CC) $(c_flags) -c -o $(@D)/.tmp_$(@F) $< -cmd_modversions = \ - if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \ - $(call cmd_gensymtypes, $(KBUILD_SYMTYPES)) \ - > $(@D)/.tmp_$(@F:.o=.ver); \ - \ - $(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) \ - -T $(@D)/.tmp_$(@F:.o=.ver); \ - rm -f $(@D)/.tmp_$(@F) $(@D)/.tmp_$(@F:.o=.ver); \ - else \ - mv -f $(@D)/.tmp_$(@F) $@; \ +cmd_modversions = \ + if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \ + $(call cmd_gensymtypes,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ + > $(@D)/.tmp_$(@F:.o=.ver); \ + \ + $(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) \ + -T $(@D)/.tmp_$(@F:.o=.ver); \ + rm -f $(@D)/.tmp_$(@F) $(@D)/.tmp_$(@F:.o=.ver); \ + else \ + mv -f $(@D)/.tmp_$(@F) $@; \ fi; endif @@ -248,10 +251,10 @@ $(obj)/%.lst: $(src)/%.c FORCE # Compile assembler sources (.S) # --------------------------------------------------------------------------- -modkern_aflags := $(AFLAGS_KERNEL) +modkern_aflags := $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL) -$(real-objs-m) : modkern_aflags := $(AFLAGS_MODULE) -$(real-objs-m:.o=.s): modkern_aflags := $(AFLAGS_MODULE) +$(real-objs-m) : modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE) +$(real-objs-m:.o=.s): modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE) quiet_cmd_as_s_S = CPP $(quiet_modtag) $@ cmd_as_s_S = $(CPP) $(a_flags) -o $@ $< diff --git a/scripts/Makefile.help b/scripts/Makefile.help new file mode 100644 index 00000000000..d03608f5db0 --- /dev/null +++ b/scripts/Makefile.help @@ -0,0 +1,3 @@ + +checker-help: + @echo ' coccicheck - Check with Coccinelle.' diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 8f14c81abbc..7d22056582c 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -30,7 +30,7 @@ # - See include/linux/module.h for more details # Step 4 is solely used to allow module versioning in external modules, -# where the CRC of each module is retrieved from the Module.symers file. +# where the CRC of each module is retrieved from the Module.symvers file. # KBUILD_MODPOST_WARN can be set to avoid error out in case of undefined # symbols in the final module linking stage @@ -107,7 +107,7 @@ $(modules:.ko=.mod.c): __modpost ; modname = $(notdir $(@:.mod.o=)) quiet_cmd_cc_o_c = CC $@ - cmd_cc_o_c = $(CC) $(c_flags) $(CFLAGS_MODULE) \ + cmd_cc_o_c = $(CC) $(c_flags) $(KBUILD_CFLAGS_MODULE) $(CFLAGS_MODULE) \ -c -o $@ $< $(modules:.ko=.mod.o): %.mod.o: %.mod.c FORCE @@ -117,8 +117,9 @@ targets += $(modules:.ko=.mod.o) # Step 6), final link of the modules quiet_cmd_ld_ko_o = LD [M] $@ - cmd_ld_ko_o = $(LD) -r $(LDFLAGS) $(LDFLAGS_MODULE) -o $@ \ - $(filter-out FORCE,$^) + cmd_ld_ko_o = $(LD) -r $(LDFLAGS) \ + $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \ + -o $@ $(filter-out FORCE,$^) $(modules): %.ko :%.o %.mod.o FORCE $(call if_changed,ld_ko_o) diff --git a/scripts/checkkconfigsymbols.sh b/scripts/checkkconfigsymbols.sh index 46be3c5a62b..2ca49bb31ef 100755 --- a/scripts/checkkconfigsymbols.sh +++ b/scripts/checkkconfigsymbols.sh @@ -14,7 +14,7 @@ find $paths -name '*.[chS]' -o -name 'Makefile' -o -name 'Makefile*[^~]'| while do # Output the bare Kconfig variable and the filename; the _MODULE part at # the end is not removed here (would need perl an not-hungry regexp for that). - sed -ne 's!^.*\<\(UML_\)\?CONFIG_\([0-9A-Z_]\+\).*!\2 '$i'!p' < $i + sed -ne 's!^.*\<\(UML_\)\?CONFIG_\([0-9A-Za-z_]\+\).*!\2 '$i'!p' < $i done | \ # Smart "sort|uniq" implemented in awk and tuned to collect the names of all # files which use a given symbol diff --git a/scripts/coccicheck b/scripts/coccicheck new file mode 100755 index 00000000000..b8bcf1f7bed --- /dev/null +++ b/scripts/coccicheck @@ -0,0 +1,80 @@ +#!/bin/sh + +SPATCH="`which ${SPATCH:=spatch}`" + +if [ "$C" = "1" -o "$C" = "2" ]; then + ONLINE=1 + +# This requires Coccinelle >= 0.2.3 +# FLAGS="-ignore_unknown_options -very_quiet" +# OPTIONS=$* + +# Workaround for Coccinelle < 0.2.3 + FLAGS="-I $srctree/include -very_quiet" + shift $(( $# - 1 )) + OPTIONS=$1 +else + ONLINE=0 + FLAGS="-very_quiet" +fi + +if [ ! -x "$SPATCH" ]; then + echo 'spatch is part of the Coccinelle project and is available at http://coccinelle.lip6.fr/' + exit 1 +fi + +if [ "$MODE" = "" ] ; then + if [ "$ONLINE" = "0" ] ; then + echo 'You have not explicitly specify the mode to use. Fallback to "report".' + echo 'You can specify the mode with "make coccicheck MODE=<mode>"' + echo 'Available modes are: report, patch, context, org' + fi + MODE="report" +fi + +if [ "$ONLINE" = "0" ] ; then + echo '' + echo 'Please check for false positives in the output before submitting a patch.' + echo 'When using "patch" mode, carefully review the patch before submitting it.' + echo '' +fi + +coccinelle () { + COCCI="$1" + + OPT=`grep "Option" $COCCI | cut -d':' -f2` + +# The option '-parse_cocci' can be used to syntaxically check the SmPL files. +# +# $SPATCH -D $MODE $FLAGS -parse_cocci $COCCI $OPT > /dev/null + + if [ "$ONLINE" = "0" ] ; then + + FILE=`echo $COCCI | sed "s|$srctree/||"` + + echo "Processing `basename $COCCI` with option(s) \"$OPT\"" + echo 'Message example to submit a patch:' + + sed -e '/\/\/\//!d' -e 's|^///||' $COCCI + + echo ' The semantic patch that makes this change is available' + echo " in $FILE." + echo '' + echo ' More information about semantic patching is available at' + echo ' http://coccinelle.lip6.fr/' + echo '' + + $SPATCH -D $MODE $FLAGS -sp_file $COCCI $OPT -dir $srctree || exit 1 + else + $SPATCH -D $MODE $FLAGS -sp_file $COCCI $OPT $OPTIONS || exit 1 + fi + +} + +if [ "$COCCI" = "" ] ; then + for f in `find $srctree/scripts/coccinelle/ -name '*.cocci' -type f | sort`; do + coccinelle $f + done +else + coccinelle $COCCI +fi diff --git a/scripts/coccinelle/alloc/drop_kmalloc_cast.cocci b/scripts/coccinelle/alloc/drop_kmalloc_cast.cocci new file mode 100644 index 00000000000..7d4771d449c --- /dev/null +++ b/scripts/coccinelle/alloc/drop_kmalloc_cast.cocci @@ -0,0 +1,67 @@ +/// +/// Casting (void *) value returned by kmalloc is useless +/// as mentioned in Documentation/CodingStyle, Chap 14. +/// +// Confidence: High +// Copyright: 2009,2010 Nicolas Palix, DIKU. GPLv2. +// URL: http://coccinelle.lip6.fr/ +// Options: -no_includes -include_headers +// +// Keywords: kmalloc, kzalloc, kcalloc +// Version min: < 2.6.12 kmalloc +// Version min: < 2.6.12 kcalloc +// Version min: 2.6.14 kzalloc +// + +virtual context +virtual patch +virtual org +virtual report + +//---------------------------------------------------------- +// For context mode +//---------------------------------------------------------- + +@depends on context@ +type T; +@@ + +* (T *) + \(kmalloc\|kzalloc\|kcalloc\)(...) + +//---------------------------------------------------------- +// For patch mode +//---------------------------------------------------------- + +@depends on patch@ +type T; +@@ + +- (T *) + \(kmalloc\|kzalloc\|kcalloc\)(...) + +//---------------------------------------------------------- +// For org and report mode +//---------------------------------------------------------- + +@r depends on org || report@ +type T; +position p; +@@ + + (T@p *)\(kmalloc\|kzalloc\|kcalloc\)(...) + +@script:python depends on org@ +p << r.p; +t << r.T; +@@ + +coccilib.org.print_safe_todo(p[0], t) + +@script:python depends on report@ +p << r.p; +t << r.T; +@@ + +msg="WARNING: casting value returned by k[cmz]alloc to (%s *) is useless." % (t) +coccilib.report.print_report(p[0], msg) diff --git a/scripts/coccinelle/alloc/kzalloc-simple.cocci b/scripts/coccinelle/alloc/kzalloc-simple.cocci new file mode 100644 index 00000000000..2eae828fc65 --- /dev/null +++ b/scripts/coccinelle/alloc/kzalloc-simple.cocci @@ -0,0 +1,82 @@ +/// +/// kzalloc should be used rather than kmalloc followed by memset 0 +/// +// Confidence: High +// Copyright: (C) 2009-2010 Julia Lawall, Nicolas Palix, DIKU. GPLv2. +// Copyright: (C) 2009-2010 Gilles Muller, INRIA/LiP6. GPLv2. +// URL: http://coccinelle.lip6.fr/rules/kzalloc.html +// Options: -no_includes -include_headers +// +// Keywords: kmalloc, kzalloc +// Version min: < 2.6.12 kmalloc +// Version min: 2.6.14 kzalloc +// + +virtual context +virtual patch +virtual org +virtual report + +//---------------------------------------------------------- +// For context mode +//---------------------------------------------------------- + +@depends on context@ +type T, T2; +expression x; +expression E1,E2; +statement S; +@@ + +* x = (T)kmalloc(E1,E2); + if ((x==NULL) || ...) S +* memset((T2)x,0,E1); + +//---------------------------------------------------------- +// For patch mode +//---------------------------------------------------------- + +@depends on patch@ +type T, T2; +expression x; +expression E1,E2; +statement S; +@@ + +- x = (T)kmalloc(E1,E2); ++ x = kzalloc(E1,E2); + if ((x==NULL) || ...) S +- memset((T2)x,0,E1); + +//---------------------------------------------------------- +// For org mode +//---------------------------------------------------------- + +@r depends on org || report@ +type T, T2; +expression x; +expression E1,E2; +statement S; +position p; +@@ + + x = (T)kmalloc@p(E1,E2); + if ((x==NULL) || ...) S + memset((T2)x,0,E1); + +@script:python depends on org@ +p << r.p; +x << r.x; +@@ + +msg="%s" % (x) +msg_safe=msg.replace("[","@(").replace("]",")") +coccilib.org.print_todo(p[0], msg_safe) + +@script:python depends on report@ +p << r.p; +x << r.x; +@@ + +msg="WARNING: kzalloc should be used for %s, instead of kmalloc/memset" % (x) +coccilib.report.print_report(p[0], msg) diff --git a/scripts/coccinelle/deref_null.cocci b/scripts/coccinelle/deref_null.cocci new file mode 100644 index 00000000000..9969d76d0f4 --- /dev/null +++ b/scripts/coccinelle/deref_null.cocci @@ -0,0 +1,293 @@ +/// +/// A variable is dereference under a NULL test. +/// Even though it is know to be NULL. +/// +// Confidence: Moderate +// Copyright: (C) 2010 Nicolas Palix, DIKU. GPLv2. +// Copyright: (C) 2010 Julia Lawall, DIKU. GPLv2. +// Copyright: (C) 2010 Gilles Muller, INRIA/LiP6. GPLv2. +// URL: http://coccinelle.lip6.fr/ +// Comments: -I ... -all_includes can give more complete results +// Options: + +virtual context +virtual patch +virtual org +virtual report + +@initialize:python depends on !context && patch && !org && !report@ + +import sys +print >> sys.stderr, "This semantic patch does not support the 'patch' mode." + +@depends on patch@ +@@ + +this_rule_should_never_matches(); + +@ifm depends on !patch@ +expression *E; +statement S1,S2; +position p1; +@@ + +if@p1 ((E == NULL && ...) || ...) S1 else S2 + +// The following two rules are separate, because both can match a single +// expression in different ways +@pr1 depends on !patch expression@ +expression *ifm.E; +identifier f; +position p1; +@@ + + (E != NULL && ...) ? <+...E->f@p1...+> : ... + +@pr2 depends on !patch expression@ +expression *ifm.E; +identifier f; +position p2; +@@ + +( + (E != NULL) && ... && <+...E->f@p2...+> +| + (E == NULL) || ... || <+...E->f@p2...+> +| + sizeof(<+...E->f@p2...+>) +) + +// For org and report modes + +@r depends on !context && !patch && (org || report) exists@ +expression subE <= ifm.E; +expression *ifm.E; +expression E1,E2; +identifier f; +statement S1,S2,S3,S4; +iterator iter; +position p!={pr1.p1,pr2.p2}; +position ifm.p1; +@@ + +if@p1 ((E == NULL && ...) || ...) +{ + ... when != if (...) S1 else S2 +( + iter(subE,...) S4 // no use +| + list_remove_head(E2,subE,...) +| + subE = E1 +| + for(subE = E1;...;...) S4 +| + subE++ +| + ++subE +| + --subE +| + subE-- +| + &subE +| + E->f@p // bad use +) + ... when any + return ...; +} +else S3 + +@script:python depends on !context && !patch && !org && report@ +p << r.p; +p1 << ifm.p1; +x << ifm.E; +@@ + +msg="ERROR: %s is NULL but dereferenced." % (x) +coccilib.report.print_report(p[0], msg) +cocci.include_match(False) + +@script:python depends on !context && !patch && org && !report@ +p << r.p; +p1 << ifm.p1; +x << ifm.E; +@@ + +msg="ERROR: %s is NULL but dereferenced." % (x) +msg_safe=msg.replace("[","@(").replace("]",")") +cocci.print_main(msg_safe,p) +cocci.include_match(False) + +@s depends on !context && !patch && (org || report) exists@ +expression subE <= ifm.E; +expression *ifm.E; +expression E1,E2; +identifier f; +statement S1,S2,S3,S4; +iterator iter; +position p!={pr1.p1,pr2.p2}; +position ifm.p1; +@@ + +if@p1 ((E == NULL && ...) || ...) +{ + ... when != if (...) S1 else S2 +( + iter(subE,...) S4 // no use +| + list_remove_head(E2,subE,...) +| + subE = E1 +| + for(subE = E1;...;...) S4 +| + subE++ +| + ++subE +| + --subE +| + subE-- +| + &subE +| + E->f@p // bad use +) + ... when any +} +else S3 + +@script:python depends on !context && !patch && !org && report@ +p << s.p; +p1 << ifm.p1; +x << ifm.E; +@@ + +msg="ERROR: %s is NULL but dereferenced." % (x) +coccilib.report.print_report(p[0], msg) + +@script:python depends on !context && !patch && org && !report@ +p << s.p; +p1 << ifm.p1; +x << ifm.E; +@@ + +msg="ERROR: %s is NULL but dereferenced." % (x) +msg_safe=msg.replace("[","@(").replace("]",")") +cocci.print_main(msg_safe,p) + +// For context mode + +@depends on context && !patch && !org && !report exists@ +expression subE <= ifm.E; +expression *ifm.E; +expression E1,E2; +identifier f; +statement S1,S2,S3,S4; +iterator iter; +position p!={pr1.p1,pr2.p2}; +position ifm.p1; +@@ + +if@p1 ((E == NULL && ...) || ...) +{ + ... when != if (...) S1 else S2 +( + iter(subE,...) S4 // no use +| + list_remove_head(E2,subE,...) +| + subE = E1 +| + for(subE = E1;...;...) S4 +| + subE++ +| + ++subE +| + --subE +| + subE-- +| + &subE +| +* E->f@p // bad use +) + ... when any + return ...; +} +else S3 + +// The following three rules are duplicates of ifm, pr1 and pr2 respectively. +// It is need because the previous rule as already made a "change". + +@ifm1 depends on !patch@ +expression *E; +statement S1,S2; +position p1; +@@ + +if@p1 ((E == NULL && ...) || ...) S1 else S2 + +@pr11 depends on !patch expression@ +expression *ifm1.E; +identifier f; +position p1; +@@ + + (E != NULL && ...) ? <+...E->f@p1...+> : ... + +@pr12 depends on !patch expression@ +expression *ifm1.E; +identifier f; +position p2; +@@ + +( + (E != NULL) && ... && <+...E->f@p2...+> +| + (E == NULL) || ... || <+...E->f@p2...+> +| + sizeof(<+...E->f@p2...+>) +) + +@depends on context && !patch && !org && !report exists@ +expression subE <= ifm1.E; +expression *ifm1.E; +expression E1,E2; +identifier f; +statement S1,S2,S3,S4; +iterator iter; +position p!={pr11.p1,pr12.p2}; +position ifm1.p1; +@@ + +if@p1 ((E == NULL && ...) || ...) +{ + ... when != if (...) S1 else S2 +( + iter(subE,...) S4 // no use +| + list_remove_head(E2,subE,...) +| + subE = E1 +| + for(subE = E1;...;...) S4 +| + subE++ +| + ++subE +| + --subE +| + subE-- +| + &subE +| +* E->f@p // bad use +) + ... when any +} +else S3 diff --git a/scripts/coccinelle/err_cast.cocci b/scripts/coccinelle/err_cast.cocci new file mode 100644 index 00000000000..2ce115000af --- /dev/null +++ b/scripts/coccinelle/err_cast.cocci @@ -0,0 +1,56 @@ +/// +/// Use ERR_CAST inlined function instead of ERR_PTR(PTR_ERR(...)) +/// +// Confidence: High +// Copyright: (C) 2009, 2010 Nicolas Palix, DIKU. GPLv2. +// Copyright: (C) 2009, 2010 Julia Lawall, DIKU. GPLv2. +// Copyright: (C) 2009, 2010 Gilles Muller, INRIA/LiP6. GPLv2. +// URL: http://coccinelle.lip6.fr/ +// Options: +// +// Keywords: ERR_PTR, PTR_ERR, ERR_CAST +// Version min: 2.6.25 +// + +virtual context +virtual patch +virtual org +virtual report + + +@ depends on context && !patch && !org && !report@ +expression x; +@@ + +* ERR_PTR(PTR_ERR(x)) + +@ depends on !context && patch && !org && !report @ +expression x; +@@ + +- ERR_PTR(PTR_ERR(x)) ++ ERR_CAST(x) + +@r depends on !context && !patch && (org || report)@ +expression x; +position p; +@@ + + ERR_PTR@p(PTR_ERR(x)) + +@script:python depends on org@ +p << r.p; +x << r.x; +@@ + +msg="WARNING ERR_CAST can be used with %s" % (x) +msg_safe=msg.replace("[","@(").replace("]",")") +coccilib.org.print_todo(p[0], msg_safe) + +@script:python depends on report@ +p << r.p; +x << r.x; +@@ + +msg="WARNING: ERR_CAST can be used with %s" % (x) +coccilib.report.print_report(p[0], msg) diff --git a/scripts/coccinelle/resource_size.cocci b/scripts/coccinelle/resource_size.cocci new file mode 100644 index 00000000000..1935a58b39d --- /dev/null +++ b/scripts/coccinelle/resource_size.cocci @@ -0,0 +1,93 @@ +/// +/// Use resource_size function on resource object +/// instead of explicit computation. +/// +// Confidence: High +// Copyright: (C) 2009, 2010 Nicolas Palix, DIKU. GPLv2. +// Copyright: (C) 2009, 2010 Julia Lawall, DIKU. GPLv2. +// Copyright: (C) 2009, 2010 Gilles Muller, INRIA/LiP6. GPLv2. +// URL: http://coccinelle.lip6.fr/ +// Options: +// +// Keywords: resource_size +// Version min: 2.6.27 resource_size +// + +virtual context +virtual patch +virtual org +virtual report + +//---------------------------------------------------------- +// For context mode +//---------------------------------------------------------- + +@r_context depends on context && !patch && !org@ +struct resource *res; +@@ + +* (res->end - res->start) + 1 + +//---------------------------------------------------------- +// For patch mode +//---------------------------------------------------------- + +@r_patch depends on !context && patch && !org@ +struct resource *res; +@@ + +- (res->end - res->start) + 1 ++ resource_size(res) + +//---------------------------------------------------------- +// For org mode +//---------------------------------------------------------- + + +@r_org depends on !context && !patch && (org || report)@ +struct resource *res; +position p; +@@ + + (res->end@p - res->start) + 1 + +@rbad_org depends on !context && !patch && (org || report)@ +struct resource *res; +position p != r_org.p; +@@ + + res->end@p - res->start + +@script:python depends on org@ +p << r_org.p; +x << r_org.res; +@@ + +msg="ERROR with %s" % (x) +msg_safe=msg.replace("[","@(").replace("]",")") +coccilib.org.print_todo(p[0], msg_safe) + +@script:python depends on report@ +p << r_org.p; +x << r_org.res; +@@ + +msg="ERROR: Missing resource_size with %s" % (x) +coccilib.report.print_report(p[0], msg) + +@script:python depends on org@ +p << rbad_org.p; +x << rbad_org.res; +@@ + +msg="WARNING with %s" % (x) +msg_safe=msg.replace("[","@(").replace("]",")") +coccilib.org.print_todo(p[0], msg_safe) + +@script:python depends on report@ +p << rbad_org.p; +x << rbad_org.res; +@@ + +msg="WARNING: Suspicious code. resource_size is maybe missing with %s" % (x) +coccilib.report.print_report(p[0], msg) diff --git a/scripts/decodecode b/scripts/decodecode index 8b30cc36744..18ba881c341 100755 --- a/scripts/decodecode +++ b/scripts/decodecode @@ -40,7 +40,7 @@ echo $code code=`echo $code | sed -e 's/.*Code: //'` width=`expr index "$code" ' '` -width=$[($width-1)/2] +width=$((($width-1)/2)) case $width in 1) type=byte ;; 2) type=2byte ;; @@ -48,10 +48,10 @@ case $width in esac disas() { - ${CROSS_COMPILE}as $AFLAGS -o $1.o $1.s &> /dev/null + ${CROSS_COMPILE}as $AFLAGS -o $1.o $1.s > /dev/null 2>&1 - if [ "$ARCH" == "arm" ]; then - if [ $width == 2 ]; then + if [ "$ARCH" = "arm" ]; then + if [ $width -eq 2 ]; then OBJDUMPFLAGS="-M force-thumb" fi @@ -59,7 +59,7 @@ disas() { fi ${CROSS_COMPILE}objdump $OBJDUMPFLAGS -S $1.o | \ - grep -v "/tmp\|Disassembly\|\.text\|^$" &> $1.dis + grep -v "/tmp\|Disassembly\|\.text\|^$" > $1.dis 2>&1 } marker=`expr index "$code" "\<"` diff --git a/scripts/dtc/fstree.c b/scripts/dtc/fstree.c index 766b2694d93..8fe1bdf239f 100644 --- a/scripts/dtc/fstree.c +++ b/scripts/dtc/fstree.c @@ -77,6 +77,7 @@ static struct node *read_fstree(const char *dirname) free(tmpnam); } + closedir(d); return tree; } diff --git a/scripts/kconfig/.gitignore b/scripts/kconfig/.gitignore index 6a36a76e660..624f6502e03 100644 --- a/scripts/kconfig/.gitignore +++ b/scripts/kconfig/.gitignore @@ -17,6 +17,7 @@ gconf.glade.h # conf mconf +nconf qconf gconf kxgettext diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 7ea649da194..de934def410 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -21,17 +21,17 @@ menuconfig: $(obj)/mconf $< $(Kconfig) config: $(obj)/conf - $< $(Kconfig) + $< --oldaskconfig $(Kconfig) nconfig: $(obj)/nconf $< $(Kconfig) oldconfig: $(obj)/conf - $< -o $(Kconfig) + $< --$@ $(Kconfig) silentoldconfig: $(obj)/conf $(Q)mkdir -p include/generated - $< -s $(Kconfig) + $< --$@ $(Kconfig) # if no path is given, then use src directory to find file ifdef LSMOD @@ -44,15 +44,15 @@ endif localmodconfig: $(obj)/streamline_config.pl $(obj)/conf $(Q)mkdir -p include/generated $(Q)perl $< $(srctree) $(Kconfig) $(LSMOD_F) > .tmp.config - $(Q)if [ -f .config ]; then \ - cmp -s .tmp.config .config || \ - (mv -f .config .config.old.1; \ - mv -f .tmp.config .config; \ - $(obj)/conf -s $(Kconfig); \ - mv -f .config.old.1 .config.old) \ - else \ - mv -f .tmp.config .config; \ - $(obj)/conf -s $(Kconfig); \ + $(Q)if [ -f .config ]; then \ + cmp -s .tmp.config .config || \ + (mv -f .config .config.old.1; \ + mv -f .tmp.config .config; \ + $(obj)/conf --silentoldconfig $(Kconfig); \ + mv -f .config.old.1 .config.old) \ + else \ + mv -f .tmp.config .config; \ + $(obj)/conf --silentoldconfig $(Kconfig); \ fi $(Q)rm -f .tmp.config @@ -60,15 +60,15 @@ localyesconfig: $(obj)/streamline_config.pl $(obj)/conf $(Q)mkdir -p include/generated $(Q)perl $< $(srctree) $(Kconfig) $(LSMOD_F) > .tmp.config $(Q)sed -i s/=m/=y/ .tmp.config - $(Q)if [ -f .config ]; then \ - cmp -s .tmp.config .config || \ - (mv -f .config .config.old.1; \ - mv -f .tmp.config .config; \ - $(obj)/conf -s $(Kconfig); \ - mv -f .config.old.1 .config.old) \ - else \ - mv -f .tmp.config .config; \ - $(obj)/conf -s $(Kconfig); \ + $(Q)if [ -f .config ]; then \ + cmp -s .tmp.config .config || \ + (mv -f .config .config.old.1; \ + mv -f .tmp.config .config; \ + $(obj)/conf --silentoldconfig $(Kconfig); \ + mv -f .config.old.1 .config.old) \ + else \ + mv -f .tmp.config .config; \ + $(obj)/conf --silentoldconfig $(Kconfig); \ fi $(Q)rm -f .tmp.config @@ -95,30 +95,29 @@ update-po-config: $(obj)/kxgettext $(obj)/gconf.glade.h $(Q)rm -f arch/um/Kconfig.arch $(Q)rm -f $(obj)/config.pot -PHONY += randconfig allyesconfig allnoconfig allmodconfig defconfig +PHONY += allnoconfig allyesconfig allmodconfig alldefconfig randconfig -randconfig: $(obj)/conf - $< -r $(Kconfig) +allnoconfig allyesconfig allmodconfig alldefconfig randconfig: $(obj)/conf + $< --$@ $(Kconfig) -allyesconfig: $(obj)/conf - $< -y $(Kconfig) +PHONY += listnewconfig oldnoconfig savedefconfig defconfig -allnoconfig: $(obj)/conf - $< -n $(Kconfig) +listnewconfig oldnoconfig: $(obj)/conf + $< --$@ $(Kconfig) -allmodconfig: $(obj)/conf - $< -m $(Kconfig) +savedefconfig: $(obj)/conf + $< --$@=defconfig $(Kconfig) defconfig: $(obj)/conf ifeq ($(KBUILD_DEFCONFIG),) - $< -d $(Kconfig) + $< --defconfig $(Kconfig) else @echo "*** Default configuration is based on '$(KBUILD_DEFCONFIG)'" - $(Q)$< -D arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG) $(Kconfig) + $(Q)$< --defconfig=arch/$(SRCARCH)/configs/$(KBUILD_DEFCONFIG) $(Kconfig) endif %_defconfig: $(obj)/conf - $(Q)$< -D arch/$(SRCARCH)/configs/$@ $(Kconfig) + $(Q)$< --defconfig=arch/$(SRCARCH)/configs/$@ $(Kconfig) # Help text used by make help help: @@ -131,11 +130,15 @@ help: @echo ' localmodconfig - Update current config disabling modules not loaded' @echo ' localyesconfig - Update current config converting local mods to core' @echo ' silentoldconfig - Same as oldconfig, but quietly, additionally update deps' - @echo ' randconfig - New config with random answer to all options' - @echo ' defconfig - New config with default answer to all options' - @echo ' allmodconfig - New config selecting modules when possible' - @echo ' allyesconfig - New config where all options are accepted with yes' + @echo ' defconfig - New config with default from ARCH supplied defconfig' + @echo ' savedefconfig - Save current config as ./defconfig (minimal config)' @echo ' allnoconfig - New config where all options are answered with no' + @echo ' allyesconfig - New config where all options are accepted with yes' + @echo ' allmodconfig - New config selecting modules when possible' + @echo ' alldefconfig - New config with all symbols set to default' + @echo ' randconfig - New config with random answer to all options' + @echo ' listnewconfig - List new options' + @echo ' oldnoconfig - Same as silentoldconfig but set new symbols to n (unset)' # lxdialog stuff check-lxdialog := $(srctree)/$(src)/lxdialog/check-lxdialog.sh diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c index 9960d1c303f..274f2716b03 100644 --- a/scripts/kconfig/conf.c +++ b/scripts/kconfig/conf.c @@ -10,6 +10,7 @@ #include <string.h> #include <time.h> #include <unistd.h> +#include <getopt.h> #include <sys/stat.h> #include <sys/time.h> @@ -19,16 +20,21 @@ static void conf(struct menu *menu); static void check_conf(struct menu *menu); -enum { - ask_all, - ask_new, - ask_silent, - set_default, - set_yes, - set_mod, - set_no, - set_random -} input_mode = ask_all; +enum input_mode { + oldaskconfig, + silentoldconfig, + oldconfig, + allnoconfig, + allyesconfig, + allmodconfig, + alldefconfig, + randconfig, + defconfig, + savedefconfig, + listnewconfig, + oldnoconfig, +} input_mode = oldaskconfig; + char *defconfig_file; static int indent = 1; @@ -93,14 +99,14 @@ static int conf_askvalue(struct symbol *sym, const char *def) } switch (input_mode) { - case ask_new: - case ask_silent: + case oldconfig: + case silentoldconfig: if (sym_has_value(sym)) { printf("%s\n", def); return 0; } check_stdin(); - case ask_all: + case oldaskconfig: fflush(stdout); fgets(line, 128, stdin); return 1; @@ -156,14 +162,12 @@ static int conf_string(struct menu *menu) static int conf_sym(struct menu *menu) { struct symbol *sym = menu->sym; - int type; tristate oldval, newval; while (1) { printf("%*s%s ", indent - 1, "", _(menu->prompt->text)); if (sym->name) printf("(%s) ", sym->name); - type = sym_get_type(sym); putchar('['); oldval = sym_get_tristate_value(sym); switch (oldval) { @@ -228,11 +232,9 @@ static int conf_choice(struct menu *menu) { struct symbol *sym, *def_sym; struct menu *child; - int type; bool is_new; sym = menu->sym; - type = sym_get_type(sym); is_new = !sym_has_value(sym); if (sym_is_changable(sym)) { conf_sym(menu); @@ -294,15 +296,15 @@ static int conf_choice(struct menu *menu) printf("?"); printf("]: "); switch (input_mode) { - case ask_new: - case ask_silent: + case oldconfig: + case silentoldconfig: if (!is_new) { cnt = def; printf("%d\n", cnt); break; } check_stdin(); - case ask_all: + case oldaskconfig: fflush(stdout); fgets(line, 128, stdin); strip(line); @@ -360,7 +362,10 @@ static void conf(struct menu *menu) switch (prop->type) { case P_MENU: - if (input_mode == ask_silent && rootEntry != menu) { + if ((input_mode == silentoldconfig || + input_mode == listnewconfig || + input_mode == oldnoconfig) && + rootEntry != menu) { check_conf(menu); return; } @@ -418,10 +423,16 @@ static void check_conf(struct menu *menu) if (sym && !sym_has_value(sym)) { if (sym_is_changable(sym) || (sym_is_choice(sym) && sym_get_tristate_value(sym) == yes)) { - if (!conf_cnt++) - printf(_("*\n* Restart config...\n*\n")); - rootEntry = menu_get_parent_menu(menu); - conf(rootEntry); + if (input_mode == listnewconfig) { + if (sym->name && !sym_is_choice_value(sym)) { + printf("CONFIG_%s\n", sym->name); + } + } else { + if (!conf_cnt++) + printf(_("*\n* Restart config...\n*\n")); + rootEntry = menu_get_parent_menu(menu); + conf(rootEntry); + } } } @@ -429,6 +440,22 @@ static void check_conf(struct menu *menu) check_conf(child); } +static struct option long_opts[] = { + {"oldaskconfig", no_argument, NULL, oldaskconfig}, + {"oldconfig", no_argument, NULL, oldconfig}, + {"silentoldconfig", no_argument, NULL, silentoldconfig}, + {"defconfig", optional_argument, NULL, defconfig}, + {"savedefconfig", required_argument, NULL, savedefconfig}, + {"allnoconfig", no_argument, NULL, allnoconfig}, + {"allyesconfig", no_argument, NULL, allyesconfig}, + {"allmodconfig", no_argument, NULL, allmodconfig}, + {"alldefconfig", no_argument, NULL, alldefconfig}, + {"randconfig", no_argument, NULL, randconfig}, + {"listnewconfig", no_argument, NULL, listnewconfig}, + {"oldnoconfig", no_argument, NULL, oldnoconfig}, + {NULL, 0, NULL, 0} +}; + int main(int ac, char **av) { int opt; @@ -439,32 +466,17 @@ int main(int ac, char **av) bindtextdomain(PACKAGE, LOCALEDIR); textdomain(PACKAGE); - while ((opt = getopt(ac, av, "osdD:nmyrh")) != -1) { + while ((opt = getopt_long_only(ac, av, "", long_opts, NULL)) != -1) { + input_mode = (enum input_mode)opt; switch (opt) { - case 'o': - input_mode = ask_silent; - break; - case 's': - input_mode = ask_silent; + case silentoldconfig: sync_kconfig = 1; break; - case 'd': - input_mode = set_default; - break; - case 'D': - input_mode = set_default; + case defconfig: + case savedefconfig: defconfig_file = optarg; break; - case 'n': - input_mode = set_no; - break; - case 'm': - input_mode = set_mod; - break; - case 'y': - input_mode = set_yes; - break; - case 'r': + case randconfig: { struct timeval now; unsigned int seed; @@ -477,17 +489,12 @@ int main(int ac, char **av) seed = (unsigned int)((now.tv_sec + 1) * (now.tv_usec + 1)); srand(seed); - - input_mode = set_random; break; } - case 'h': - printf(_("See README for usage info\n")); - exit(0); - break; - default: + case '?': fprintf(stderr, _("See README for usage info\n")); exit(1); + break; } } if (ac == optind) { @@ -512,7 +519,7 @@ int main(int ac, char **av) } switch (input_mode) { - case set_default: + case defconfig: if (!defconfig_file) defconfig_file = conf_get_default_confname(); if (conf_read(defconfig_file)) { @@ -522,25 +529,32 @@ int main(int ac, char **av) exit(1); } break; - case ask_silent: - case ask_all: - case ask_new: + case savedefconfig: + conf_read(NULL); + break; + case silentoldconfig: + case oldaskconfig: + case oldconfig: + case listnewconfig: + case oldnoconfig: conf_read(NULL); break; - case set_no: - case set_mod: - case set_yes: - case set_random: + case allnoconfig: + case allyesconfig: + case allmodconfig: + case alldefconfig: + case randconfig: name = getenv("KCONFIG_ALLCONFIG"); if (name && !stat(name, &tmpstat)) { conf_read_simple(name, S_DEF_USER); break; } switch (input_mode) { - case set_no: name = "allno.config"; break; - case set_mod: name = "allmod.config"; break; - case set_yes: name = "allyes.config"; break; - case set_random: name = "allrandom.config"; break; + case allnoconfig: name = "allno.config"; break; + case allyesconfig: name = "allyes.config"; break; + case allmodconfig: name = "allmod.config"; break; + case alldefconfig: name = "alldef.config"; break; + case randconfig: name = "allrandom.config"; break; default: break; } if (!stat(name, &tmpstat)) @@ -565,33 +579,42 @@ int main(int ac, char **av) } switch (input_mode) { - case set_no: + case allnoconfig: conf_set_all_new_symbols(def_no); break; - case set_yes: + case allyesconfig: conf_set_all_new_symbols(def_yes); break; - case set_mod: + case allmodconfig: conf_set_all_new_symbols(def_mod); break; - case set_random: + case alldefconfig: + conf_set_all_new_symbols(def_default); + break; + case randconfig: conf_set_all_new_symbols(def_random); break; - case set_default: + case defconfig: conf_set_all_new_symbols(def_default); break; - case ask_new: - case ask_all: + case savedefconfig: + break; + case oldaskconfig: rootEntry = &rootmenu; conf(&rootmenu); - input_mode = ask_silent; + input_mode = silentoldconfig; /* fall through */ - case ask_silent: + case oldconfig: + case listnewconfig: + case oldnoconfig: + case silentoldconfig: /* Update until a loop caused no more changes */ do { conf_cnt = 0; check_conf(&rootmenu); - } while (conf_cnt); + } while (conf_cnt && + (input_mode != listnewconfig && + input_mode != oldnoconfig)); break; } @@ -607,7 +630,13 @@ int main(int ac, char **av) fprintf(stderr, _("\n*** Error during update of the kernel configuration.\n\n")); return 1; } - } else { + } else if (input_mode == savedefconfig) { + if (conf_write_defconfig(defconfig_file)) { + fprintf(stderr, _("n*** Error while saving defconfig to: %s\n\n"), + defconfig_file); + return 1; + } + } else if (input_mode != listnewconfig) { if (conf_write(NULL)) { fprintf(stderr, _("\n*** Error during writing of the kernel configuration.\n\n")); exit(1); diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index c4dec80cfd8..f81f263b64f 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -170,8 +170,11 @@ int conf_read_simple(const char *name, int def) if (in) goto load; sym_add_change_count(1); - if (!sym_defconfig_list) + if (!sym_defconfig_list) { + if (modules_sym) + sym_calc_value(modules_sym); return 1; + } for_all_defaults(sym_defconfig_list, prop) { if (expr_calc_value(prop->visible.expr) == no || @@ -396,15 +399,149 @@ int conf_read(const char *name) return 0; } +/* Write a S_STRING */ +static void conf_write_string(bool headerfile, const char *name, + const char *str, FILE *out) +{ + int l; + if (headerfile) + fprintf(out, "#define CONFIG_%s \"", name); + else + fprintf(out, "CONFIG_%s=\"", name); + + while (1) { + l = strcspn(str, "\"\\"); + if (l) { + fwrite(str, l, 1, out); + str += l; + } + if (!*str) + break; + fprintf(out, "\\%c", *str++); + } + fputs("\"\n", out); +} + +static void conf_write_symbol(struct symbol *sym, enum symbol_type type, + FILE *out, bool write_no) +{ + const char *str; + + switch (type) { + case S_BOOLEAN: + case S_TRISTATE: + switch (sym_get_tristate_value(sym)) { + case no: + if (write_no) + fprintf(out, "# CONFIG_%s is not set\n", sym->name); + break; + case mod: + fprintf(out, "CONFIG_%s=m\n", sym->name); + break; + case yes: + fprintf(out, "CONFIG_%s=y\n", sym->name); + break; + } + break; + case S_STRING: + conf_write_string(false, sym->name, sym_get_string_value(sym), out); + break; + case S_HEX: + case S_INT: + str = sym_get_string_value(sym); + fprintf(out, "CONFIG_%s=%s\n", sym->name, str); + break; + case S_OTHER: + case S_UNKNOWN: + break; + } +} + +/* + * Write out a minimal config. + * All values that has default values are skipped as this is redundant. + */ +int conf_write_defconfig(const char *filename) +{ + struct symbol *sym; + struct menu *menu; + FILE *out; + + out = fopen(filename, "w"); + if (!out) + return 1; + + sym_clear_all_valid(); + + /* Traverse all menus to find all relevant symbols */ + menu = rootmenu.list; + + while (menu != NULL) + { + sym = menu->sym; + if (sym == NULL) { + if (!menu_is_visible(menu)) + goto next_menu; + } else if (!sym_is_choice(sym)) { + sym_calc_value(sym); + if (!(sym->flags & SYMBOL_WRITE)) + goto next_menu; + sym->flags &= ~SYMBOL_WRITE; + /* If we cannot change the symbol - skip */ + if (!sym_is_changable(sym)) + goto next_menu; + /* If symbol equals to default value - skip */ + if (strcmp(sym_get_string_value(sym), sym_get_string_default(sym)) == 0) + goto next_menu; + + /* + * If symbol is a choice value and equals to the + * default for a choice - skip. + * But only if value equal to "y". + */ + if (sym_is_choice_value(sym)) { + struct symbol *cs; + struct symbol *ds; + + cs = prop_get_symbol(sym_get_choice_prop(sym)); + ds = sym_choice_default(cs); + if (sym == ds) { + if ((sym->type == S_BOOLEAN || + sym->type == S_TRISTATE) && + sym_get_tristate_value(sym) == yes) + goto next_menu; + } + } + conf_write_symbol(sym, sym->type, out, true); + } +next_menu: + if (menu->list != NULL) { + menu = menu->list; + } + else if (menu->next != NULL) { + menu = menu->next; + } else { + while ((menu = menu->parent)) { + if (menu->next != NULL) { + menu = menu->next; + break; + } + } + } + } + fclose(out); + return 0; +} + int conf_write(const char *name) { FILE *out; struct symbol *sym; struct menu *menu; const char *basename; - char dirname[128], tmpname[128], newname[128]; - int type, l; const char *str; + char dirname[128], tmpname[128], newname[128]; + enum symbol_type type; time_t now; int use_timestamp = 1; char *env; @@ -484,50 +621,11 @@ int conf_write(const char *name) if (modules_sym->curr.tri == no) type = S_BOOLEAN; } - switch (type) { - case S_BOOLEAN: - case S_TRISTATE: - switch (sym_get_tristate_value(sym)) { - case no: - fprintf(out, "# CONFIG_%s is not set\n", sym->name); - break; - case mod: - fprintf(out, "CONFIG_%s=m\n", sym->name); - break; - case yes: - fprintf(out, "CONFIG_%s=y\n", sym->name); - break; - } - break; - case S_STRING: - str = sym_get_string_value(sym); - fprintf(out, "CONFIG_%s=\"", sym->name); - while (1) { - l = strcspn(str, "\"\\"); - if (l) { - fwrite(str, l, 1, out); - str += l; - } - if (!*str) - break; - fprintf(out, "\\%c", *str++); - } - fputs("\"\n", out); - break; - case S_HEX: - str = sym_get_string_value(sym); - if (str[0] != '0' || (str[1] != 'x' && str[1] != 'X')) { - fprintf(out, "CONFIG_%s=%s\n", sym->name, str); - break; - } - case S_INT: - str = sym_get_string_value(sym); - fprintf(out, "CONFIG_%s=%s\n", sym->name, str); - break; - } + /* Write config symbol to file */ + conf_write_symbol(sym, type, out, true); } - next: +next: if (menu->list) { menu = menu->list; continue; @@ -679,7 +777,7 @@ int conf_write_autoconf(void) const char *name; FILE *out, *tristate, *out_h; time_t now; - int i, l; + int i; sym_clear_all_valid(); @@ -729,6 +827,11 @@ int conf_write_autoconf(void) sym_calc_value(sym); if (!(sym->flags & SYMBOL_WRITE) || !sym->name) continue; + + /* write symbol to config file */ + conf_write_symbol(sym, sym->type, out, false); + + /* update autoconf and tristate files */ switch (sym->type) { case S_BOOLEAN: case S_TRISTATE: @@ -736,12 +839,10 @@ int conf_write_autoconf(void) case no: break; case mod: - fprintf(out, "CONFIG_%s=m\n", sym->name); fprintf(tristate, "CONFIG_%s=M\n", sym->name); fprintf(out_h, "#define CONFIG_%s_MODULE 1\n", sym->name); break; case yes: - fprintf(out, "CONFIG_%s=y\n", sym->name); if (sym->type == S_TRISTATE) fprintf(tristate, "CONFIG_%s=Y\n", sym->name); @@ -750,35 +851,16 @@ int conf_write_autoconf(void) } break; case S_STRING: - str = sym_get_string_value(sym); - fprintf(out, "CONFIG_%s=\"", sym->name); - fprintf(out_h, "#define CONFIG_%s \"", sym->name); - while (1) { - l = strcspn(str, "\"\\"); - if (l) { - fwrite(str, l, 1, out); - fwrite(str, l, 1, out_h); - str += l; - } - if (!*str) - break; - fprintf(out, "\\%c", *str); - fprintf(out_h, "\\%c", *str); - str++; - } - fputs("\"\n", out); - fputs("\"\n", out_h); + conf_write_string(true, sym->name, sym_get_string_value(sym), out_h); break; case S_HEX: str = sym_get_string_value(sym); if (str[0] != '0' || (str[1] != 'x' && str[1] != 'X')) { - fprintf(out, "CONFIG_%s=%s\n", sym->name, str); fprintf(out_h, "#define CONFIG_%s 0x%s\n", sym->name, str); break; } case S_INT: str = sym_get_string_value(sym); - fprintf(out, "CONFIG_%s=%s\n", sym->name, str); fprintf(out_h, "#define CONFIG_%s %s\n", sym->name, str); break; default: @@ -862,7 +944,8 @@ void conf_set_all_new_symbols(enum conf_def_mode mode) sym->def[S_DEF_USER].tri = no; break; case def_random: - sym->def[S_DEF_USER].tri = (tristate)(rand() % 3); + cnt = sym_get_type(sym) == S_TRISTATE ? 3 : 2; + sym->def[S_DEF_USER].tri = (tristate)(rand() % cnt); break; default: continue; diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c index d83f2322893..8f18e37892c 100644 --- a/scripts/kconfig/expr.c +++ b/scripts/kconfig/expr.c @@ -1121,7 +1121,7 @@ static void expr_print_gstr_helper(void *data, struct symbol *sym, const char *s } str_append(gs, str); - if (sym) + if (sym && sym->type != S_UNKNOWN) str_printf(gs, " [=%s]", sym_str); } diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h index 891cd9ce9ba..6ee2e4fb148 100644 --- a/scripts/kconfig/expr.h +++ b/scripts/kconfig/expr.h @@ -83,6 +83,7 @@ struct symbol { tristate visible; int flags; struct property *prop; + struct expr_value dir_dep; struct expr_value rev_dep; }; @@ -131,6 +132,7 @@ enum prop_type { P_SELECT, /* select BAR */ P_RANGE, /* range 7..100 (for a symbol) */ P_ENV, /* value from environment variable */ + P_SYMBOL, /* where a symbol is defined */ }; struct property { @@ -163,6 +165,7 @@ struct menu { struct symbol *sym; struct property *prompt; struct expr *dep; + struct expr *dir_dep; unsigned int flags; char *help; struct file *file; diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c index bef10411837..d66988265f8 100644 --- a/scripts/kconfig/gconf.c +++ b/scripts/kconfig/gconf.c @@ -1114,7 +1114,7 @@ static gchar **fill_row(struct menu *menu) row[COL_OPTION] = g_strdup_printf("%s %s", _(menu_get_prompt(menu)), - sym && sym_has_value(sym) ? "(NEW)" : ""); + sym && !sym_has_value(sym) ? "(NEW)" : ""); if (opt_mode == OPT_ALL && !menu_is_visible(menu)) row[COL_COLOR] = g_strdup("DarkGray"); @@ -1343,7 +1343,8 @@ static void update_tree(struct menu *src, GtkTreeIter * dst) #endif if ((opt_mode == OPT_NORMAL && !menu_is_visible(child1)) || - (opt_mode == OPT_PROMPT && !menu_has_prompt(child1))) { + (opt_mode == OPT_PROMPT && !menu_has_prompt(child1)) || + (opt_mode == OPT_ALL && !menu_get_prompt(child1))) { /* remove node */ if (gtktree_iter_find_node(dst, menu1) != NULL) { @@ -1425,7 +1426,7 @@ static void display_tree(struct menu *menu) if ((opt_mode == OPT_NORMAL && menu_is_visible(child)) || (opt_mode == OPT_PROMPT && menu_has_prompt(child)) || - (opt_mode == OPT_ALL)) + (opt_mode == OPT_ALL && menu_get_prompt(child))) place_node(child, fill_row(child)); #ifdef DEBUG printf("%*c%s: ", indent, ' ', menu_get_prompt(child)); diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h index ce6549cdacc..76db065ed72 100644 --- a/scripts/kconfig/lkc.h +++ b/scripts/kconfig/lkc.h @@ -126,6 +126,8 @@ void sym_init(void); void sym_clear_all_valid(void); void sym_set_all_changed(void); void sym_set_changed(struct symbol *sym); +struct symbol *sym_choice_default(struct symbol *sym); +const char *sym_get_string_default(struct symbol *sym); struct symbol *sym_check_deps(struct symbol *sym); struct property *prop_alloc(enum prop_type type, struct symbol *sym); struct symbol *prop_get_symbol(struct property *prop); diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h index 7cadcad8233..9a948c9ce44 100644 --- a/scripts/kconfig/lkc_proto.h +++ b/scripts/kconfig/lkc_proto.h @@ -3,6 +3,7 @@ P(conf_parse,void,(const char *name)); P(conf_read,int,(const char *name)); P(conf_read_simple,int,(const char *name, int)); +P(conf_write_defconfig,int,(const char *name)); P(conf_write,int,(const char *name)); P(conf_write_autoconf,int,(void)); P(conf_get_changed,bool,(void)); diff --git a/scripts/kconfig/lxdialog/checklist.c b/scripts/kconfig/lxdialog/checklist.c index bcc6f19c3a3..a2eb80fbc89 100644 --- a/scripts/kconfig/lxdialog/checklist.c +++ b/scripts/kconfig/lxdialog/checklist.c @@ -31,6 +31,10 @@ static int list_width, check_x, item_x; static void print_item(WINDOW * win, int choice, int selected) { int i; + char *list_item = malloc(list_width + 1); + + strncpy(list_item, item_str(), list_width - item_x); + list_item[list_width - item_x] = '\0'; /* Clear 'residue' of last item */ wattrset(win, dlg.menubox.atr); @@ -45,13 +49,14 @@ static void print_item(WINDOW * win, int choice, int selected) wprintw(win, "(%c)", item_is_tag('X') ? 'X' : ' '); wattrset(win, selected ? dlg.tag_selected.atr : dlg.tag.atr); - mvwaddch(win, choice, item_x, item_str()[0]); + mvwaddch(win, choice, item_x, list_item[0]); wattrset(win, selected ? dlg.item_selected.atr : dlg.item.atr); - waddstr(win, (char *)item_str() + 1); + waddstr(win, list_item + 1); if (selected) { wmove(win, choice, check_x + 1); wrefresh(win); } + free(list_item); } /* @@ -175,6 +180,7 @@ do_resize: check_x = 0; item_foreach() check_x = MAX(check_x, strlen(item_str()) + 4); + check_x = MIN(check_x, list_width); check_x = (list_width - check_x) / 2; item_x = check_x + 4; diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c index 2c83d3234d3..d2f6e056c05 100644 --- a/scripts/kconfig/mconf.c +++ b/scripts/kconfig/mconf.c @@ -74,7 +74,7 @@ static const char mconf_readme[] = N_( "\n" " Shortcut: Press <H> or <?>.\n" "\n" -"o To show hidden options, press <Z>.\n" +"o To toggle the display of hidden options, press <Z>.\n" "\n" "\n" "Radiolists (Choice lists)\n" diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index 203632cc30b..4fb590247f3 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -58,6 +58,8 @@ void menu_add_entry(struct symbol *sym) *last_entry_ptr = menu; last_entry_ptr = &menu->next; current_entry = menu; + if (sym) + menu_add_symbol(P_SYMBOL, sym, NULL); } void menu_end_entry(void) @@ -105,6 +107,7 @@ static struct expr *menu_check_dep(struct expr *e) void menu_add_dep(struct expr *dep) { current_entry->dep = expr_alloc_and(current_entry->dep, menu_check_dep(dep)); + current_entry->dir_dep = current_entry->dep; } void menu_set_type(int type) @@ -288,6 +291,10 @@ void menu_finalize(struct menu *parent) for (menu = parent->list; menu; menu = menu->next) menu_finalize(menu); } else if (sym) { + /* ignore inherited dependencies for dir_dep */ + sym->dir_dep.expr = expr_transform(expr_copy(parent->dir_dep)); + sym->dir_dep.expr = expr_eliminate_dups(sym->dir_dep.expr); + basedep = parent->prompt ? parent->prompt->visible.expr : NULL; basedep = expr_trans_compare(basedep, E_UNEQUAL, &symbol_no); basedep = expr_eliminate_dups(expr_transform(basedep)); @@ -419,9 +426,13 @@ bool menu_is_visible(struct menu *menu) if (!sym || sym_get_tristate_value(menu->sym) == no) return false; - for (child = menu->list; child; child = child->next) - if (menu_is_visible(child)) + for (child = menu->list; child; child = child->next) { + if (menu_is_visible(child)) { + if (sym) + sym->flags |= SYMBOL_DEF_USER; return true; + } + } return false; } @@ -501,9 +512,19 @@ void get_symbol_str(struct gstr *r, struct symbol *sym) bool hit; struct property *prop; - if (sym && sym->name) + if (sym && sym->name) { str_printf(r, "Symbol: %s [=%s]\n", sym->name, sym_get_string_value(sym)); + str_printf(r, "Type : %s\n", sym_type_name(sym->type)); + if (sym->type == S_INT || sym->type == S_HEX) { + prop = sym_get_range_prop(sym); + if (prop) { + str_printf(r, "Range : "); + expr_gstr_print(prop->expr, r); + str_append(r, "\n"); + } + } + } for_all_prompts(sym, prop) get_prompt_str(r, prop); hit = false; diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index 00c51507cfc..820df2d1217 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -58,11 +58,10 @@ QValueList<int> ConfigSettings::readSizes(const QString& key, bool *ok) { QValueList<int> result; QStringList entryList = readListEntry(key, ok); - if (ok) { - QStringList::Iterator it; - for (it = entryList.begin(); it != entryList.end(); ++it) - result.push_back((*it).toInt()); - } + QStringList::Iterator it; + + for (it = entryList.begin(); it != entryList.end(); ++it) + result.push_back((*it).toInt()); return result; } @@ -149,7 +148,7 @@ void ConfigItem::updateMenu(void) case S_TRISTATE: char ch; - if (!sym_is_changable(sym) && !list->showAll) { + if (!sym_is_changable(sym) && list->optMode == normalOpt) { setPixmap(promptColIdx, 0); setText(noColIdx, QString::null); setText(modColIdx, QString::null); @@ -320,7 +319,7 @@ ConfigList::ConfigList(ConfigView* p, const char *name) symbolYesPix(xpm_symbol_yes), symbolModPix(xpm_symbol_mod), symbolNoPix(xpm_symbol_no), choiceYesPix(xpm_choice_yes), choiceNoPix(xpm_choice_no), menuPix(xpm_menu), menuInvPix(xpm_menu_inv), menuBackPix(xpm_menuback), voidPix(xpm_void), - showAll(false), showName(false), showRange(false), showData(false), + showName(false), showRange(false), showData(false), optMode(normalOpt), rootEntry(0), headerPopup(0) { int i; @@ -337,10 +336,10 @@ ConfigList::ConfigList(ConfigView* p, const char *name) if (name) { configSettings->beginGroup(name); - showAll = configSettings->readBoolEntry("/showAll", false); showName = configSettings->readBoolEntry("/showName", false); showRange = configSettings->readBoolEntry("/showRange", false); showData = configSettings->readBoolEntry("/showData", false); + optMode = (enum optionMode)configSettings->readNumEntry("/optionMode", false); configSettings->endGroup(); connect(configApp, SIGNAL(aboutToQuit()), SLOT(saveSettings())); } @@ -352,6 +351,17 @@ ConfigList::ConfigList(ConfigView* p, const char *name) reinit(); } +bool ConfigList::menuSkip(struct menu *menu) +{ + if (optMode == normalOpt && menu_is_visible(menu)) + return false; + if (optMode == promptOpt && menu_has_prompt(menu)) + return false; + if (optMode == allOpt) + return false; + return true; +} + void ConfigList::reinit(void) { removeColumn(dataColIdx); @@ -380,7 +390,7 @@ void ConfigList::saveSettings(void) configSettings->writeEntry("/showName", showName); configSettings->writeEntry("/showRange", showRange); configSettings->writeEntry("/showData", showData); - configSettings->writeEntry("/showAll", showAll); + configSettings->writeEntry("/optionMode", (int)optMode); configSettings->endGroup(); } } @@ -606,7 +616,7 @@ void ConfigList::updateMenuList(P* parent, struct menu* menu) } visible = menu_is_visible(child); - if (showAll || visible) { + if (!menuSkip(child)) { if (!child->sym && !child->list && !child->prompt) continue; if (!item || item->menu != child) @@ -835,7 +845,10 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) e->ignore(); } -ConfigView* ConfigView::viewList; +ConfigView*ConfigView::viewList; +QAction *ConfigView::showNormalAction; +QAction *ConfigView::showAllAction; +QAction *ConfigView::showPromptAction; ConfigView::ConfigView(QWidget* parent, const char *name) : Parent(parent, name) @@ -860,13 +873,16 @@ ConfigView::~ConfigView(void) } } -void ConfigView::setShowAll(bool b) +void ConfigView::setOptionMode(QAction *act) { - if (list->showAll != b) { - list->showAll = b; - list->updateListAll(); - emit showAllChanged(b); - } + if (act == showNormalAction) + list->optMode = normalOpt; + else if (act == showAllAction) + list->optMode = allOpt; + else + list->optMode = promptOpt; + + list->updateListAll(); } void ConfigView::setShowName(bool b) @@ -964,34 +980,6 @@ void ConfigInfoView::setInfo(struct menu *m) menuInfo(); } -void ConfigInfoView::setSource(const QString& name) -{ - const char *p = name.latin1(); - - menu = NULL; - sym = NULL; - - switch (p[0]) { - case 'm': - struct menu *m; - - if (sscanf(p, "m%p", &m) == 1 && menu != m) { - menu = m; - menuInfo(); - emit menuSelected(menu); - } - break; - case 's': - struct symbol *s; - - if (sscanf(p, "s%p", &s) == 1 && sym != s) { - sym = s; - symbolInfo(); - } - break; - } -} - void ConfigInfoView::symbolInfo(void) { QString str; @@ -1349,11 +1337,24 @@ ConfigMainWindow::ConfigMainWindow(void) connect(showDataAction, SIGNAL(toggled(bool)), configView, SLOT(setShowData(bool))); connect(configView, SIGNAL(showDataChanged(bool)), showDataAction, SLOT(setOn(bool))); showDataAction->setOn(configList->showData); - QAction *showAllAction = new QAction(NULL, _("Show All Options"), 0, this); - showAllAction->setToggleAction(TRUE); - connect(showAllAction, SIGNAL(toggled(bool)), configView, SLOT(setShowAll(bool))); - connect(showAllAction, SIGNAL(toggled(bool)), menuView, SLOT(setShowAll(bool))); - showAllAction->setOn(configList->showAll); + + QActionGroup *optGroup = new QActionGroup(this); + optGroup->setExclusive(TRUE); + connect(optGroup, SIGNAL(selected(QAction *)), configView, + SLOT(setOptionMode(QAction *))); + connect(optGroup, SIGNAL(selected(QAction *)), menuView, + SLOT(setOptionMode(QAction *))); + + configView->showNormalAction = new QAction(NULL, _("Show Normal Options"), 0, optGroup); + configView->showAllAction = new QAction(NULL, _("Show All Options"), 0, optGroup); + configView->showPromptAction = new QAction(NULL, _("Show Prompt Options"), 0, optGroup); + configView->showNormalAction->setToggleAction(TRUE); + configView->showNormalAction->setOn(configList->optMode == normalOpt); + configView->showAllAction->setToggleAction(TRUE); + configView->showAllAction->setOn(configList->optMode == allOpt); + configView->showPromptAction->setToggleAction(TRUE); + configView->showPromptAction->setOn(configList->optMode == promptOpt); + QAction *showDebugAction = new QAction(NULL, _("Show Debug Info"), 0, this); showDebugAction->setToggleAction(TRUE); connect(showDebugAction, SIGNAL(toggled(bool)), helpText, SLOT(setShowDebug(bool))); @@ -1396,7 +1397,8 @@ ConfigMainWindow::ConfigMainWindow(void) showRangeAction->addTo(optionMenu); showDataAction->addTo(optionMenu); optionMenu->insertSeparator(); - showAllAction->addTo(optionMenu); + optGroup->addTo(optionMenu); + optionMenu->insertSeparator(); showDebugAction->addTo(optionMenu); // create help menu @@ -1491,7 +1493,7 @@ void ConfigMainWindow::setMenuLink(struct menu *menu) ConfigList* list = NULL; ConfigItem* item; - if (!menu_is_visible(menu) && !configView->showAll()) + if (configList->menuSkip(menu)) return; switch (configList->mode) { diff --git a/scripts/kconfig/qconf.h b/scripts/kconfig/qconf.h index b3b5657b6b3..636a74b23bf 100644 --- a/scripts/kconfig/qconf.h +++ b/scripts/kconfig/qconf.h @@ -44,6 +44,9 @@ enum colIdx { enum listMode { singleMode, menuMode, symbolMode, fullMode, listMode }; +enum optionMode { + normalOpt = 0, allOpt, promptOpt +}; class ConfigList : public QListView { Q_OBJECT @@ -115,6 +118,8 @@ public: void setAllOpen(bool open); void setParentMenu(void); + bool menuSkip(struct menu *); + template <class P> void updateMenuList(P*, struct menu*); @@ -124,8 +129,9 @@ public: QPixmap choiceYesPix, choiceNoPix; QPixmap menuPix, menuInvPix, menuBackPix, voidPix; - bool showAll, showName, showRange, showData; + bool showName, showRange, showData; enum listMode mode; + enum optionMode optMode; struct menu *rootEntry; QColorGroup disabledColorGroup; QColorGroup inactivedColorGroup; @@ -222,17 +228,15 @@ public: static void updateList(ConfigItem* item); static void updateListAll(void); - bool showAll(void) const { return list->showAll; } bool showName(void) const { return list->showName; } bool showRange(void) const { return list->showRange; } bool showData(void) const { return list->showData; } public slots: - void setShowAll(bool); void setShowName(bool); void setShowRange(bool); void setShowData(bool); + void setOptionMode(QAction *); signals: - void showAllChanged(bool); void showNameChanged(bool); void showRangeChanged(bool); void showDataChanged(bool); @@ -242,6 +246,10 @@ public: static ConfigView* viewList; ConfigView* nextView; + + static QAction *showNormalAction; + static QAction *showAllAction; + static QAction *showPromptAction; }; class ConfigInfoView : public QTextBrowser { @@ -254,7 +262,6 @@ public: public slots: void setInfo(struct menu *menu); void saveSettings(void); - void setSource(const QString& name); void setShowDebug(bool); signals: diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 2e7a048e0cf..e95718fea35 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -205,6 +205,16 @@ static void sym_calc_visibility(struct symbol *sym) } if (sym_is_choice_value(sym)) return; + /* defaulting to "yes" if no explicit "depends on" are given */ + tri = yes; + if (sym->dir_dep.expr) + tri = expr_calc_value(sym->dir_dep.expr); + if (tri == mod) + tri = yes; + if (sym->dir_dep.tri != tri) { + sym->dir_dep.tri = tri; + sym_set_changed(sym); + } tri = no; if (sym->rev_dep.expr) tri = expr_calc_value(sym->rev_dep.expr); @@ -216,44 +226,63 @@ static void sym_calc_visibility(struct symbol *sym) } } -static struct symbol *sym_calc_choice(struct symbol *sym) +/* + * Find the default symbol for a choice. + * First try the default values for the choice symbol + * Next locate the first visible choice value + * Return NULL if none was found + */ +struct symbol *sym_choice_default(struct symbol *sym) { struct symbol *def_sym; struct property *prop; struct expr *e; - /* is the user choice visible? */ - def_sym = sym->def[S_DEF_USER].val; - if (def_sym) { - sym_calc_visibility(def_sym); - if (def_sym->visible != no) - return def_sym; - } - /* any of the defaults visible? */ for_all_defaults(sym, prop) { prop->visible.tri = expr_calc_value(prop->visible.expr); if (prop->visible.tri == no) continue; def_sym = prop_get_symbol(prop); - sym_calc_visibility(def_sym); if (def_sym->visible != no) return def_sym; } /* just get the first visible value */ prop = sym_get_choice_prop(sym); - expr_list_for_each_sym(prop->expr, e, def_sym) { - sym_calc_visibility(def_sym); + expr_list_for_each_sym(prop->expr, e, def_sym) if (def_sym->visible != no) return def_sym; - } - /* no choice? reset tristate value */ - sym->curr.tri = no; + /* failed to locate any defaults */ return NULL; } +static struct symbol *sym_calc_choice(struct symbol *sym) +{ + struct symbol *def_sym; + struct property *prop; + struct expr *e; + + /* first calculate all choice values' visibilities */ + prop = sym_get_choice_prop(sym); + expr_list_for_each_sym(prop->expr, e, def_sym) + sym_calc_visibility(def_sym); + + /* is the user choice visible? */ + def_sym = sym->def[S_DEF_USER].val; + if (def_sym && def_sym->visible != no) + return def_sym; + + def_sym = sym_choice_default(sym); + + if (def_sym == NULL) + /* no choice? reset tristate value */ + sym->curr.tri = no; + + return def_sym; +} + void sym_calc_value(struct symbol *sym) { struct symbol_value newval, oldval; @@ -321,6 +350,14 @@ void sym_calc_value(struct symbol *sym) } } calc_newval: + if (sym->dir_dep.tri == no && sym->rev_dep.tri != no) { + fprintf(stderr, "warning: ("); + expr_fprint(sym->rev_dep.expr, stderr); + fprintf(stderr, ") selects %s which has unmet direct dependencies (", + sym->name); + expr_fprint(sym->dir_dep.expr, stderr); + fprintf(stderr, ")\n"); + } newval.tri = EXPR_OR(newval.tri, sym->rev_dep.tri); } if (newval.tri == mod && sym_get_type(sym) == S_BOOLEAN) @@ -365,12 +402,13 @@ void sym_calc_value(struct symbol *sym) if (sym_is_choice(sym)) { struct symbol *choice_sym; - int flags = sym->flags & (SYMBOL_CHANGED | SYMBOL_WRITE); prop = sym_get_choice_prop(sym); expr_list_for_each_sym(prop->expr, e, choice_sym) { - choice_sym->flags |= flags; - if (flags & SYMBOL_CHANGED) + if ((sym->flags & SYMBOL_WRITE) && + choice_sym->visible != no) + choice_sym->flags |= SYMBOL_WRITE; + if (sym->flags & SYMBOL_CHANGED) sym_set_changed(choice_sym); } } @@ -623,6 +661,80 @@ bool sym_set_string_value(struct symbol *sym, const char *newval) return true; } +/* + * Find the default value associated to a symbol. + * For tristate symbol handle the modules=n case + * in which case "m" becomes "y". + * If the symbol does not have any default then fallback + * to the fixed default values. + */ +const char *sym_get_string_default(struct symbol *sym) +{ + struct property *prop; + struct symbol *ds; + const char *str; + tristate val; + + sym_calc_visibility(sym); + sym_calc_value(modules_sym); + val = symbol_no.curr.tri; + str = symbol_empty.curr.val; + + /* If symbol has a default value look it up */ + prop = sym_get_default_prop(sym); + if (prop != NULL) { + switch (sym->type) { + case S_BOOLEAN: + case S_TRISTATE: + /* The visibility imay limit the value from yes => mod */ + val = EXPR_AND(expr_calc_value(prop->expr), prop->visible.tri); + break; + default: + /* + * The following fails to handle the situation + * where a default value is further limited by + * the valid range. + */ + ds = prop_get_symbol(prop); + if (ds != NULL) { + sym_calc_value(ds); + str = (const char *)ds->curr.val; + } + } + } + + /* Handle select statements */ + val = EXPR_OR(val, sym->rev_dep.tri); + + /* transpose mod to yes if modules are not enabled */ + if (val == mod) + if (!sym_is_choice_value(sym) && modules_sym->curr.tri == no) + val = yes; + + /* transpose mod to yes if type is bool */ + if (sym->type == S_BOOLEAN && val == mod) + val = yes; + + switch (sym->type) { + case S_BOOLEAN: + case S_TRISTATE: + switch (val) { + case no: return "n"; + case mod: return "m"; + case yes: return "y"; + } + case S_INT: + case S_HEX: + return str; + case S_STRING: + return str; + case S_OTHER: + case S_UNKNOWN: + break; + } + return ""; +} + const char *sym_get_string_value(struct symbol *sym) { tristate val; @@ -765,6 +877,110 @@ struct symbol **sym_re_search(const char *pattern) return sym_arr; } +/* + * When we check for recursive dependencies we use a stack to save + * current state so we can print out relevant info to user. + * The entries are located on the call stack so no need to free memory. + * Note inser() remove() must always match to properly clear the stack. + */ +static struct dep_stack { + struct dep_stack *prev, *next; + struct symbol *sym; + struct property *prop; + struct expr *expr; +} *check_top; + +static void dep_stack_insert(struct dep_stack *stack, struct symbol *sym) +{ + memset(stack, 0, sizeof(*stack)); + if (check_top) + check_top->next = stack; + stack->prev = check_top; + stack->sym = sym; + check_top = stack; +} + +static void dep_stack_remove(void) +{ + check_top = check_top->prev; + if (check_top) + check_top->next = NULL; +} + +/* + * Called when we have detected a recursive dependency. + * check_top point to the top of the stact so we use + * the ->prev pointer to locate the bottom of the stack. + */ +static void sym_check_print_recursive(struct symbol *last_sym) +{ + struct dep_stack *stack; + struct symbol *sym, *next_sym; + struct menu *menu = NULL; + struct property *prop; + struct dep_stack cv_stack; + + if (sym_is_choice_value(last_sym)) { + dep_stack_insert(&cv_stack, last_sym); + last_sym = prop_get_symbol(sym_get_choice_prop(last_sym)); + } + + for (stack = check_top; stack != NULL; stack = stack->prev) + if (stack->sym == last_sym) + break; + if (!stack) { + fprintf(stderr, "unexpected recursive dependency error\n"); + return; + } + + for (; stack; stack = stack->next) { + sym = stack->sym; + next_sym = stack->next ? stack->next->sym : last_sym; + prop = stack->prop; + + /* for choice values find the menu entry (used below) */ + if (sym_is_choice(sym) || sym_is_choice_value(sym)) { + for (prop = sym->prop; prop; prop = prop->next) { + menu = prop->menu; + if (prop->menu) + break; + } + } + if (stack->sym == last_sym) + fprintf(stderr, "%s:%d:error: recursive dependency detected!\n", + prop->file->name, prop->lineno); + if (stack->expr) { + fprintf(stderr, "%s:%d:\tsymbol %s %s value contains %s\n", + prop->file->name, prop->lineno, + sym->name ? sym->name : "<choice>", + prop_get_type_name(prop->type), + next_sym->name ? next_sym->name : "<choice>"); + } else if (stack->prop) { + fprintf(stderr, "%s:%d:\tsymbol %s depends on %s\n", + prop->file->name, prop->lineno, + sym->name ? sym->name : "<choice>", + next_sym->name ? next_sym->name : "<choice>"); + } else if (sym_is_choice(sym)) { + fprintf(stderr, "%s:%d:\tchoice %s contains symbol %s\n", + menu->file->name, menu->lineno, + sym->name ? sym->name : "<choice>", + next_sym->name ? next_sym->name : "<choice>"); + } else if (sym_is_choice_value(sym)) { + fprintf(stderr, "%s:%d:\tsymbol %s is part of choice %s\n", + menu->file->name, menu->lineno, + sym->name ? sym->name : "<choice>", + next_sym->name ? next_sym->name : "<choice>"); + } else { + fprintf(stderr, "%s:%d:\tsymbol %s is selected by %s\n", + prop->file->name, prop->lineno, + sym->name ? sym->name : "<choice>", + next_sym->name ? next_sym->name : "<choice>"); + } + } + + if (check_top == &cv_stack) + dep_stack_remove(); +} static struct symbol *sym_check_expr_deps(struct expr *e) { @@ -801,24 +1017,33 @@ static struct symbol *sym_check_sym_deps(struct symbol *sym) { struct symbol *sym2; struct property *prop; + struct dep_stack stack; + + dep_stack_insert(&stack, sym); sym2 = sym_check_expr_deps(sym->rev_dep.expr); if (sym2) - return sym2; + goto out; for (prop = sym->prop; prop; prop = prop->next) { if (prop->type == P_CHOICE || prop->type == P_SELECT) continue; + stack.prop = prop; sym2 = sym_check_expr_deps(prop->visible.expr); if (sym2) break; if (prop->type != P_DEFAULT || sym_is_choice(sym)) continue; + stack.expr = prop->expr; sym2 = sym_check_expr_deps(prop->expr); if (sym2) break; + stack.expr = NULL; } +out: + dep_stack_remove(); + return sym2; } @@ -827,6 +1052,9 @@ static struct symbol *sym_check_choice_deps(struct symbol *choice) struct symbol *sym, *sym2; struct property *prop; struct expr *e; + struct dep_stack stack; + + dep_stack_insert(&stack, choice); prop = sym_get_choice_prop(choice); expr_list_for_each_sym(prop->expr, e, sym) @@ -840,10 +1068,8 @@ static struct symbol *sym_check_choice_deps(struct symbol *choice) expr_list_for_each_sym(prop->expr, e, sym) { sym2 = sym_check_sym_deps(sym); - if (sym2) { - fprintf(stderr, " -> %s", sym->name); + if (sym2) break; - } } out: expr_list_for_each_sym(prop->expr, e, sym) @@ -853,6 +1079,8 @@ out: prop_get_symbol(sym_get_choice_prop(sym2)) == choice) sym2 = choice; + dep_stack_remove(); + return sym2; } @@ -862,18 +1090,20 @@ struct symbol *sym_check_deps(struct symbol *sym) struct property *prop; if (sym->flags & SYMBOL_CHECK) { - fprintf(stderr, "%s:%d:error: found recursive dependency: %s", - sym->prop->file->name, sym->prop->lineno, - sym->name ? sym->name : "<choice>"); + sym_check_print_recursive(sym); return sym; } if (sym->flags & SYMBOL_CHECKED) return NULL; if (sym_is_choice_value(sym)) { + struct dep_stack stack; + /* for choice groups start the check with main choice symbol */ + dep_stack_insert(&stack, sym); prop = sym_get_choice_prop(sym); sym2 = sym_check_deps(prop_get_symbol(prop)); + dep_stack_remove(); } else if (sym_is_choice(sym)) { sym2 = sym_check_choice_deps(sym); } else { @@ -882,14 +1112,8 @@ struct symbol *sym_check_deps(struct symbol *sym) sym->flags &= ~SYMBOL_CHECK; } - if (sym2) { - fprintf(stderr, " -> %s", sym->name ? sym->name : "<choice>"); - if (sym2 == sym) { - fprintf(stderr, "\n"); - zconfnerrs++; - sym2 = NULL; - } - } + if (sym2 && sym2 == sym) + sym2 = NULL; return sym2; } @@ -943,6 +1167,8 @@ const char *prop_get_type_name(enum prop_type type) return "select"; case P_RANGE: return "range"; + case P_SYMBOL: + return "symbol"; case P_UNKNOWN: break; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 5758aab0d8b..88f3f07205f 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -884,16 +884,16 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, char *zeros = NULL; /* We're looking for a section relative symbol */ - if (!sym->st_shndx || sym->st_shndx >= info->hdr->e_shnum) + if (!sym->st_shndx || get_secindex(info, sym) >= info->num_sections) return; /* Handle all-NULL symbols allocated into .bss */ - if (info->sechdrs[sym->st_shndx].sh_type & SHT_NOBITS) { + if (info->sechdrs[get_secindex(info, sym)].sh_type & SHT_NOBITS) { zeros = calloc(1, sym->st_size); symval = zeros; } else { symval = (void *)info->hdr - + info->sechdrs[sym->st_shndx].sh_offset + + info->sechdrs[get_secindex(info, sym)].sh_offset + sym->st_value; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index f6127b9f5ac..c827309c29c 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -253,7 +253,7 @@ static enum export export_no(const char *s) return export_unknown; } -static enum export export_from_sec(struct elf_info *elf, Elf_Section sec) +static enum export export_from_sec(struct elf_info *elf, unsigned int sec) { if (sec == elf->export_sec) return export_plain; @@ -373,6 +373,8 @@ static int parse_elf(struct elf_info *info, const char *filename) Elf_Ehdr *hdr; Elf_Shdr *sechdrs; Elf_Sym *sym; + const char *secstrings; + unsigned int symtab_idx = ~0U, symtab_shndx_idx = ~0U; hdr = grab_file(filename, &info->size); if (!hdr) { @@ -417,8 +419,27 @@ static int parse_elf(struct elf_info *info, const char *filename) return 0; } + if (hdr->e_shnum == 0) { + /* + * There are more than 64k sections, + * read count from .sh_size. + * note: it doesn't need shndx2secindex() + */ + info->num_sections = TO_NATIVE(sechdrs[0].sh_size); + } + else { + info->num_sections = hdr->e_shnum; + } + if (hdr->e_shstrndx == SHN_XINDEX) { + info->secindex_strings = + shndx2secindex(TO_NATIVE(sechdrs[0].sh_link)); + } + else { + info->secindex_strings = hdr->e_shstrndx; + } + /* Fix endianness in section headers */ - for (i = 0; i < hdr->e_shnum; i++) { + for (i = 0; i < info->num_sections; i++) { sechdrs[i].sh_name = TO_NATIVE(sechdrs[i].sh_name); sechdrs[i].sh_type = TO_NATIVE(sechdrs[i].sh_type); sechdrs[i].sh_flags = TO_NATIVE(sechdrs[i].sh_flags); @@ -431,9 +452,8 @@ static int parse_elf(struct elf_info *info, const char *filename) sechdrs[i].sh_entsize = TO_NATIVE(sechdrs[i].sh_entsize); } /* Find symbol table. */ - for (i = 1; i < hdr->e_shnum; i++) { - const char *secstrings - = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + secstrings = (void *)hdr + sechdrs[info->secindex_strings].sh_offset; + for (i = 1; i < info->num_sections; i++) { const char *secname; int nobits = sechdrs[i].sh_type == SHT_NOBITS; @@ -461,14 +481,26 @@ static int parse_elf(struct elf_info *info, const char *filename) else if (strcmp(secname, "__ksymtab_gpl_future") == 0) info->export_gpl_future_sec = i; - if (sechdrs[i].sh_type != SHT_SYMTAB) - continue; + if (sechdrs[i].sh_type == SHT_SYMTAB) { + unsigned int sh_link_idx; + symtab_idx = i; + info->symtab_start = (void *)hdr + + sechdrs[i].sh_offset; + info->symtab_stop = (void *)hdr + + sechdrs[i].sh_offset + sechdrs[i].sh_size; + sh_link_idx = shndx2secindex(sechdrs[i].sh_link); + info->strtab = (void *)hdr + + sechdrs[sh_link_idx].sh_offset; + } - info->symtab_start = (void *)hdr + sechdrs[i].sh_offset; - info->symtab_stop = (void *)hdr + sechdrs[i].sh_offset - + sechdrs[i].sh_size; - info->strtab = (void *)hdr + - sechdrs[sechdrs[i].sh_link].sh_offset; + /* 32bit section no. table? ("more than 64k sections") */ + if (sechdrs[i].sh_type == SHT_SYMTAB_SHNDX) { + symtab_shndx_idx = i; + info->symtab_shndx_start = (void *)hdr + + sechdrs[i].sh_offset; + info->symtab_shndx_stop = (void *)hdr + + sechdrs[i].sh_offset + sechdrs[i].sh_size; + } } if (!info->symtab_start) fatal("%s has no symtab?\n", filename); @@ -480,6 +512,21 @@ static int parse_elf(struct elf_info *info, const char *filename) sym->st_value = TO_NATIVE(sym->st_value); sym->st_size = TO_NATIVE(sym->st_size); } + + if (symtab_shndx_idx != ~0U) { + Elf32_Word *p; + if (symtab_idx != + shndx2secindex(sechdrs[symtab_shndx_idx].sh_link)) + fatal("%s: SYMTAB_SHNDX has bad sh_link: %u!=%u\n", + filename, + shndx2secindex(sechdrs[symtab_shndx_idx].sh_link), + symtab_idx); + /* Fix endianness */ + for (p = info->symtab_shndx_start; p < info->symtab_shndx_stop; + p++) + *p = TO_NATIVE(*p); + } + return 1; } @@ -519,7 +566,7 @@ static void handle_modversions(struct module *mod, struct elf_info *info, Elf_Sym *sym, const char *symname) { unsigned int crc; - enum export export = export_from_sec(info, sym->st_shndx); + enum export export = export_from_sec(info, get_secindex(info, sym)); switch (sym->st_shndx) { case SHN_COMMON: @@ -661,19 +708,19 @@ static const char *sym_name(struct elf_info *elf, Elf_Sym *sym) return "(unknown)"; } -static const char *sec_name(struct elf_info *elf, int shndx) +static const char *sec_name(struct elf_info *elf, int secindex) { Elf_Shdr *sechdrs = elf->sechdrs; return (void *)elf->hdr + - elf->sechdrs[elf->hdr->e_shstrndx].sh_offset + - sechdrs[shndx].sh_name; + elf->sechdrs[elf->secindex_strings].sh_offset + + sechdrs[secindex].sh_name; } static const char *sech_name(struct elf_info *elf, Elf_Shdr *sechdr) { return (void *)elf->hdr + - elf->sechdrs[elf->hdr->e_shstrndx].sh_offset + - sechdr->sh_name; + elf->sechdrs[elf->secindex_strings].sh_offset + + sechdr->sh_name; } /* if sym is empty or point to a string @@ -1052,11 +1099,14 @@ static Elf_Sym *find_elf_symbol(struct elf_info *elf, Elf64_Sword addr, Elf_Sym *near = NULL; Elf64_Sword distance = 20; Elf64_Sword d; + unsigned int relsym_secindex; if (relsym->st_name != 0) return relsym; + + relsym_secindex = get_secindex(elf, relsym); for (sym = elf->symtab_start; sym < elf->symtab_stop; sym++) { - if (sym->st_shndx != relsym->st_shndx) + if (get_secindex(elf, sym) != relsym_secindex) continue; if (ELF_ST_TYPE(sym->st_info) == STT_SECTION) continue; @@ -1118,9 +1168,9 @@ static Elf_Sym *find_elf_symbol2(struct elf_info *elf, Elf_Addr addr, for (sym = elf->symtab_start; sym < elf->symtab_stop; sym++) { const char *symsec; - if (sym->st_shndx >= SHN_LORESERVE) + if (is_shndx_special(sym->st_shndx)) continue; - symsec = sec_name(elf, sym->st_shndx); + symsec = sec_name(elf, get_secindex(elf, sym)); if (strcmp(symsec, sec) != 0) continue; if (!is_valid_name(elf, sym)) @@ -1316,7 +1366,7 @@ static void check_section_mismatch(const char *modname, struct elf_info *elf, const char *tosec; const struct sectioncheck *mismatch; - tosec = sec_name(elf, sym->st_shndx); + tosec = sec_name(elf, get_secindex(elf, sym)); mismatch = section_mismatch(fromsec, tosec); if (mismatch) { Elf_Sym *to; @@ -1344,7 +1394,7 @@ static unsigned int *reloc_location(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r) { Elf_Shdr *sechdrs = elf->sechdrs; - int section = sechdr->sh_info; + int section = shndx2secindex(sechdr->sh_info); return (void *)elf->hdr + sechdrs[section].sh_offset + r->r_offset - sechdrs[section].sh_addr; @@ -1452,7 +1502,7 @@ static void section_rela(const char *modname, struct elf_info *elf, r.r_addend = TO_NATIVE(rela->r_addend); sym = elf->symtab_start + r_sym; /* Skip special sections */ - if (sym->st_shndx >= SHN_LORESERVE) + if (is_shndx_special(sym->st_shndx)) continue; check_section_mismatch(modname, elf, &r, sym, fromsec); } @@ -1510,7 +1560,7 @@ static void section_rel(const char *modname, struct elf_info *elf, } sym = elf->symtab_start + r_sym; /* Skip special sections */ - if (sym->st_shndx >= SHN_LORESERVE) + if (is_shndx_special(sym->st_shndx)) continue; check_section_mismatch(modname, elf, &r, sym, fromsec); } @@ -1535,7 +1585,7 @@ static void check_sec_ref(struct module *mod, const char *modname, Elf_Shdr *sechdrs = elf->sechdrs; /* Walk through all sections */ - for (i = 0; i < elf->hdr->e_shnum; i++) { + for (i = 0; i < elf->num_sections; i++) { check_section(modname, elf, &elf->sechdrs[i]); /* We want to process only relocation sections and not .init */ if (sechdrs[i].sh_type == SHT_RELA) diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index be987a44f25..0388cfccac8 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -129,8 +129,51 @@ struct elf_info { const char *strtab; char *modinfo; unsigned int modinfo_len; + + /* support for 32bit section numbers */ + + unsigned int num_sections; /* max_secindex + 1 */ + unsigned int secindex_strings; + /* if Nth symbol table entry has .st_shndx = SHN_XINDEX, + * take shndx from symtab_shndx_start[N] instead */ + Elf32_Word *symtab_shndx_start; + Elf32_Word *symtab_shndx_stop; }; +static inline int is_shndx_special(unsigned int i) +{ + return i != SHN_XINDEX && i >= SHN_LORESERVE && i <= SHN_HIRESERVE; +} + +/* shndx is in [0..SHN_LORESERVE) U (SHN_HIRESERVE, 0xfffffff], thus: + * shndx == 0 <=> sechdrs[0] + * ...... + * shndx == SHN_LORESERVE-1 <=> sechdrs[SHN_LORESERVE-1] + * shndx == SHN_HIRESERVE+1 <=> sechdrs[SHN_LORESERVE] + * shndx == SHN_HIRESERVE+2 <=> sechdrs[SHN_LORESERVE+1] + * ...... + * fyi: sym->st_shndx is uint16, SHN_LORESERVE = ff00, SHN_HIRESERVE = ffff, + * so basically we map 0000..feff -> 0000..feff + * ff00..ffff -> (you are a bad boy, dont do it) + * 10000..xxxx -> ff00..(xxxx-0x100) + */ +static inline unsigned int shndx2secindex(unsigned int i) +{ + if (i <= SHN_HIRESERVE) + return i; + return i - (SHN_HIRESERVE + 1 - SHN_LORESERVE); +} + +/* Accessor for sym->st_shndx, hides ugliness of "64k sections" */ +static inline unsigned int get_secindex(const struct elf_info *info, + const Elf_Sym *sym) +{ + if (sym->st_shndx != SHN_XINDEX) + return sym->st_shndx; + return shndx2secindex(info->symtab_shndx_start[sym - + info->symtab_start]); +} + /* file2alias.c */ extern unsigned int cross_build; void handle_moddevtable(struct module *mod, struct elf_info *info, diff --git a/scripts/package/Makefile b/scripts/package/Makefile index d2c29b63add..d0b931b994f 100644 --- a/scripts/package/Makefile +++ b/scripts/package/Makefile @@ -111,13 +111,38 @@ tar%pkg: FORCE clean-dirs += $(objtree)/tar-install/ +# perf-pkg - generate a source tarball with perf source +# --------------------------------------------------------------------------- + +perf-tar=perf-$(KERNELVERSION) + +quiet_cmd_perf_tar = TAR + cmd_perf_tar = \ +git archive --prefix=$(perf-tar)/ HEAD^{tree} \ + $$(cat $(srctree)/tools/perf/MANIFEST) -o $(perf-tar).tar; \ +mkdir -p $(perf-tar); \ +git rev-parse HEAD > $(perf-tar)/HEAD; \ +tar rf $(perf-tar).tar $(perf-tar)/HEAD; \ +rm -r $(perf-tar); \ +$(if $(findstring tar-src,$@),, \ +$(if $(findstring bz2,$@),bzip2, \ +$(if $(findstring gz,$@),gzip, \ +$(error unknown target $@))) \ + -f -9 $(perf-tar).tar) + +perf-%pkg: FORCE + $(call cmd,perf_tar) + # Help text displayed when executing 'make help' # --------------------------------------------------------------------------- help: FORCE - @echo ' rpm-pkg - Build both source and binary RPM kernel packages' - @echo ' binrpm-pkg - Build only the binary kernel package' - @echo ' deb-pkg - Build the kernel as an deb package' - @echo ' tar-pkg - Build the kernel as an uncompressed tarball' - @echo ' targz-pkg - Build the kernel as a gzip compressed tarball' - @echo ' tarbz2-pkg - Build the kernel as a bzip2 compressed tarball' + @echo ' rpm-pkg - Build both source and binary RPM kernel packages' + @echo ' binrpm-pkg - Build only the binary kernel package' + @echo ' deb-pkg - Build the kernel as an deb package' + @echo ' tar-pkg - Build the kernel as an uncompressed tarball' + @echo ' targz-pkg - Build the kernel as a gzip compressed tarball' + @echo ' tarbz2-pkg - Build the kernel as a bzip2 compressed tarball' + @echo ' perf-tar-src-pkg - Build $(perf-tar).tar source tarball' + @echo ' perf-targz-src-pkg - Build $(perf-tar).tar.gz source tarball' + @echo ' perf-tarbz2-src-pkg - Build $(perf-tar).tar.bz2 source tarball' diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 07f2fbde2ab..5f1e2fc7f17 100644 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -148,10 +148,11 @@ EOF # Generate a control file cat <<EOF > debian/control Source: linux-upstream -Section: admin +Section: kernel Priority: optional Maintainer: $maintainer -Standards-Version: 3.8.1 +Standards-Version: 3.8.4 +Homepage: http://www.kernel.org/ EOF if [ "$ARCH" = "um" ]; then diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index f3c9c0a90b9..0171060b5fd 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -326,7 +326,7 @@ if ($arch eq "x86_64") { # 14: R_MIPS_NONE *ABS* # 18: 00020021 nop if ($is_module eq "0") { - $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$"; + $mcount_regex = "^\\s*([0-9a-fA-F]+): R_MIPS_26\\s+_mcount\$"; } else { $mcount_regex = "^\\s*([0-9a-fA-F]+): R_MIPS_HI16\\s+_mcount\$"; } diff --git a/security/apparmor/Kconfig b/security/apparmor/Kconfig index 72555b9ca7d..9b9013b2e32 100644 --- a/security/apparmor/Kconfig +++ b/security/apparmor/Kconfig @@ -1,6 +1,6 @@ config SECURITY_APPARMOR bool "AppArmor support" - depends on SECURITY + depends on SECURITY && NET select AUDIT select SECURITY_PATH select SECURITYFS diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 0d26f689bd7..0088dd8bf68 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -537,6 +537,8 @@ int wait_for_key_construction(struct key *key, bool intr) intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); if (ret < 0) return ret; + if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) + return -ENOKEY; return key_validate(key); } EXPORT_SYMBOL(wait_for_key_construction); diff --git a/sound/sparc/amd7930.c b/sound/sparc/amd7930.c index 71221fd2094..9eb1a4e0363 100644 --- a/sound/sparc/amd7930.c +++ b/sound/sparc/amd7930.c @@ -1010,7 +1010,7 @@ static int __devinit amd7930_sbus_probe(struct of_device *op, const struct of_de struct snd_amd7930 *amd; int err, irq; - irq = op->irqs[0]; + irq = op->archdata.irqs[0]; if (dev_num >= SNDRV_CARDS) return -ENODEV; @@ -1075,7 +1075,7 @@ static struct of_platform_driver amd7930_sbus_driver = { static int __init amd7930_init(void) { - return of_register_driver(&amd7930_sbus_driver, &of_bus_type); + return of_register_platform_driver(&amd7930_sbus_driver); } static void __exit amd7930_exit(void) @@ -1092,7 +1092,7 @@ static void __exit amd7930_exit(void) amd7930_list = NULL; - of_unregister_driver(&amd7930_sbus_driver); + of_unregister_platform_driver(&amd7930_sbus_driver); } module_init(amd7930_init); diff --git a/sound/sparc/cs4231.c b/sound/sparc/cs4231.c index fb4c6f2f29e..68570ee2c9b 100644 --- a/sound/sparc/cs4231.c +++ b/sound/sparc/cs4231.c @@ -1832,14 +1832,14 @@ static int __devinit snd_cs4231_sbus_create(struct snd_card *card, chip->c_dma.request = sbus_dma_request; chip->c_dma.address = sbus_dma_addr; - if (request_irq(op->irqs[0], snd_cs4231_sbus_interrupt, + if (request_irq(op->archdata.irqs[0], snd_cs4231_sbus_interrupt, IRQF_SHARED, "cs4231", chip)) { snd_printdd("cs4231-%d: Unable to grab SBUS IRQ %d\n", - dev, op->irqs[0]); + dev, op->archdata.irqs[0]); snd_cs4231_sbus_free(chip); return -EBUSY; } - chip->irq[0] = op->irqs[0]; + chip->irq[0] = op->archdata.irqs[0]; if (snd_cs4231_probe(chip) < 0) { snd_cs4231_sbus_free(chip); @@ -1870,7 +1870,7 @@ static int __devinit cs4231_sbus_probe(struct of_device *op, const struct of_dev card->shortname, rp->flags & 0xffL, (unsigned long long)rp->start, - op->irqs[0]); + op->archdata.irqs[0]); err = snd_cs4231_sbus_create(card, op, dev); if (err < 0) { @@ -1979,12 +1979,12 @@ static int __devinit snd_cs4231_ebus_create(struct snd_card *card, chip->c_dma.ebus_info.flags = EBUS_DMA_FLAG_USE_EBDMA_HANDLER; chip->c_dma.ebus_info.callback = snd_cs4231_ebus_capture_callback; chip->c_dma.ebus_info.client_cookie = chip; - chip->c_dma.ebus_info.irq = op->irqs[0]; + chip->c_dma.ebus_info.irq = op->archdata.irqs[0]; strcpy(chip->p_dma.ebus_info.name, "cs4231(play)"); chip->p_dma.ebus_info.flags = EBUS_DMA_FLAG_USE_EBDMA_HANDLER; chip->p_dma.ebus_info.callback = snd_cs4231_ebus_play_callback; chip->p_dma.ebus_info.client_cookie = chip; - chip->p_dma.ebus_info.irq = op->irqs[1]; + chip->p_dma.ebus_info.irq = op->archdata.irqs[1]; chip->p_dma.prepare = _ebus_dma_prepare; chip->p_dma.enable = _ebus_dma_enable; @@ -2060,7 +2060,7 @@ static int __devinit cs4231_ebus_probe(struct of_device *op, const struct of_dev sprintf(card->longname, "%s at 0x%llx, irq %d", card->shortname, op->resource[0].start, - op->irqs[0]); + op->archdata.irqs[0]); err = snd_cs4231_ebus_create(card, op, dev); if (err < 0) { @@ -2120,12 +2120,12 @@ static struct of_platform_driver cs4231_driver = { static int __init cs4231_init(void) { - return of_register_driver(&cs4231_driver, &of_bus_type); + return of_register_platform_driver(&cs4231_driver); } static void __exit cs4231_exit(void) { - of_unregister_driver(&cs4231_driver); + of_unregister_platform_driver(&cs4231_driver); } module_init(cs4231_init); diff --git a/sound/sparc/dbri.c b/sound/sparc/dbri.c index 1557bf132e7..c421901c48d 100644 --- a/sound/sparc/dbri.c +++ b/sound/sparc/dbri.c @@ -2608,7 +2608,7 @@ static int __devinit dbri_probe(struct of_device *op, const struct of_device_id return -ENOENT; } - irq = op->irqs[0]; + irq = op->archdata.irqs[0]; if (irq <= 0) { printk(KERN_ERR "DBRI-%d: No IRQ.\n", dev); return -ENODEV; @@ -2699,12 +2699,12 @@ static struct of_platform_driver dbri_sbus_driver = { /* Probe for the dbri chip and then attach the driver. */ static int __init dbri_init(void) { - return of_register_driver(&dbri_sbus_driver, &of_bus_type); + return of_register_platform_driver(&dbri_sbus_driver); } static void __exit dbri_exit(void) { - of_unregister_driver(&dbri_sbus_driver); + of_unregister_platform_driver(&dbri_sbus_driver); } module_init(dbri_init); diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index e1d60d78078..cb43289e447 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -18,3 +18,5 @@ perf-archive tags TAGS cscope* +config.mak +config.mak.autogen diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt index 5d1a9500277..c1057701a7d 100644 --- a/tools/perf/Documentation/perf-buildid-cache.txt +++ b/tools/perf/Documentation/perf-buildid-cache.txt @@ -12,9 +12,9 @@ SYNOPSIS DESCRIPTION ----------- -This command manages the build-id cache. It can add and remove files to the -cache. In the future it should as well purge older entries, set upper limits -for the space used by the cache, etc. +This command manages the build-id cache. It can add and remove files to/from +the cache. In the future it should as well purge older entries, set upper +limits for the space used by the cache, etc. OPTIONS ------- @@ -23,7 +23,7 @@ OPTIONS Add specified file to the cache. -r:: --remove=:: - Remove specified file to the cache. + Remove specified file from the cache. -v:: --verbose:: Be more verbose. diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 94a258c96a4..27d52dae5a4 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -31,6 +31,10 @@ OPTIONS --vmlinux=PATH:: Specify vmlinux path which has debuginfo (Dwarf binary). +-s:: +--source=PATH:: + Specify path to kernel source. + -v:: --verbose:: Be more verbose (show parsed arguments, etc). @@ -90,8 +94,8 @@ Each probe argument follows below syntax. [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE] -'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) -'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. +'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) +'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. LINE SYNTAX ----------- diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 34e255fc3e2..3ee27dccfde 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -103,6 +103,19 @@ OPTIONS --raw-samples:: Collect raw sample records from all opened counters (default for tracepoint counters). +-C:: +--cpu:: +Collect samples only on the list of cpus provided. Multiple CPUs can be provided as a +comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. +In per-thread mode with inheritance mode on (default), samples are captured only when +the thread executes on the designated CPUs. Default is to monitor all CPUs. + +-N:: +--no-buildid-cache:: +Do not update the builid cache. This saves some overhead in situations +where the information in the perf.data file (which includes buildids) +is sufficient. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 909fa766fa1..4b3a2d46b43 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -46,6 +46,13 @@ OPTIONS -B:: print large numbers with thousands' separators according to locale +-C:: +--cpu=:: +Count only on the list of cpus provided. Multiple CPUs can be provided as a +comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. +In per-thread mode, this option is ignored. The -a option is still necessary +to activate system-wide monitoring. Default is to count on all CPUs. + EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 785b9fc32a4..1f9687663f2 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -25,9 +25,11 @@ OPTIONS --count=<count>:: Event period to sample. --C <cpu>:: ---CPU=<cpu>:: - CPU to profile. +-C <cpu-list>:: +--cpu=<cpu>:: +Monitor only on the list of cpus provided. Multiple CPUs can be provided as a +comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. +Default is to monitor all CPUS. -d <seconds>:: --delay=<seconds>:: diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST new file mode 100644 index 00000000000..8c7fc0c8f0b --- /dev/null +++ b/tools/perf/MANIFEST @@ -0,0 +1,12 @@ +tools/perf +include/linux/perf_event.h +include/linux/rbtree.h +include/linux/list.h +include/linux/hash.h +include/linux/stringify.h +lib/rbtree.c +include/linux/swab.h +arch/*/include/asm/unistd*.h +include/linux/poison.h +include/linux/magic.h +include/linux/hw_breakpoint.h diff --git a/tools/perf/Makefile b/tools/perf/Makefile index d75c28a825f..26f626d45a9 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -285,14 +285,10 @@ else QUIET_STDERR = ">/dev/null 2>&1" endif -BITBUCKET = "/dev/null" +-include feature-tests.mak -ifneq ($(shell sh -c "(echo '\#include <stdio.h>'; echo 'int main(void) { return puts(\"hi\"); }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) "$(QUIET_STDERR)" && echo y"), y) - BITBUCKET = .perf.dev.null -endif - -ifeq ($(shell sh -c "echo 'int foo(void) {char X[2]; return 3;}' | $(CC) -x c -c -Werror -fstack-protector-all - -o $(BITBUCKET) "$(QUIET_STDERR)" && echo y"), y) - CFLAGS := $(CFLAGS) -fstack-protector-all +ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y) + CFLAGS := $(CFLAGS) -fstack-protector-all endif @@ -508,7 +504,8 @@ PERFLIBS = $(LIB_FILE) -include config.mak ifndef NO_DWARF -ifneq ($(shell sh -c "(echo '\#include <dwarf.h>'; echo '\#include <libdw.h>'; echo '\#include <version.h>'; echo '\#ifndef _ELFUTILS_PREREQ'; echo '\#error'; echo '\#endif'; echo 'int main(void) { Dwarf *dbg; dbg = dwarf_begin(0, DWARF_C_READ); return (long)dbg; }') | $(CC) -x c - $(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) +FLAGS_DWARF=$(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS) +ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y) msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); NO_DWARF := 1 endif # Dwarf support @@ -536,16 +533,18 @@ ifneq ($(OUTPUT),) BASIC_CFLAGS += -I$(OUTPUT) endif -ifeq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) -ifneq ($(shell sh -c "(echo '\#include <gnu/libc-version.h>'; echo 'int main(void) { const char * version = gnu_get_libc_version(); return (long)version; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) - msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); +FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) +ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF)),y) + FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS) + ifneq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC)),y) + msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static); + else + msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel); + endif endif - ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) - BASIC_CFLAGS += -DLIBELF_NO_MMAP - endif -else - msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel and glibc-dev[el]); +ifneq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_COMMON)),y) + BASIC_CFLAGS += -DLIBELF_NO_MMAP endif ifndef NO_DWARF @@ -561,64 +560,73 @@ endif # NO_DWARF ifdef NO_NEWT BASIC_CFLAGS += -DNO_NEWT_SUPPORT else -ifneq ($(shell sh -c "(echo '\#include <newt.h>'; echo 'int main(void) { newtInit(); newtCls(); return newtFinished(); }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -lnewt -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) "$(QUIET_STDERR)" && echo y"), y) - msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev); - BASIC_CFLAGS += -DNO_NEWT_SUPPORT -else - # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h - BASIC_CFLAGS += -I/usr/include/slang - EXTLIBS += -lnewt -lslang - LIB_OBJS += $(OUTPUT)util/newt.o -endif -endif # NO_NEWT - -ifndef NO_LIBPERL -PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null` -PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` + FLAGS_NEWT=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lnewt + ifneq ($(call try-cc,$(SOURCE_NEWT),$(FLAGS_NEWT)),y) + msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev); + BASIC_CFLAGS += -DNO_NEWT_SUPPORT + else + # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h + BASIC_CFLAGS += -I/usr/include/slang + EXTLIBS += -lnewt -lslang + LIB_OBJS += $(OUTPUT)util/newt.o + endif endif -ifneq ($(shell sh -c "(echo '\#include <EXTERN.h>'; echo '\#include <perl.h>'; echo 'int main(void) { perl_alloc(); return 0; }') | $(CC) -x c - $(PERL_EMBED_CCOPTS) -o $(BITBUCKET) $(PERL_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y) +ifdef NO_LIBPERL BASIC_CFLAGS += -DNO_LIBPERL else - ALL_LDFLAGS += $(PERL_EMBED_LDOPTS) - LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o - LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o -endif + PERL_EMBED_LDOPTS = `perl -MExtUtils::Embed -e ldopts 2>/dev/null` + PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` + FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) -ifndef NO_LIBPYTHON -PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null` -PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null` + ifneq ($(call try-cc,$(SOURCE_PERL_EMBED),$(FLAGS_PERL_EMBED)),y) + BASIC_CFLAGS += -DNO_LIBPERL + else + ALL_LDFLAGS += $(PERL_EMBED_LDOPTS) + LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-perl.o + LIB_OBJS += $(OUTPUT)scripts/perl/Perf-Trace-Util/Context.o + endif endif -ifneq ($(shell sh -c "(echo '\#include <Python.h>'; echo 'int main(void) { Py_Initialize(); return 0; }') | $(CC) -x c - $(PYTHON_EMBED_CCOPTS) -o $(BITBUCKET) $(PYTHON_EMBED_LDOPTS) > /dev/null 2>&1 && echo y"), y) +ifdef NO_LIBPYTHON BASIC_CFLAGS += -DNO_LIBPYTHON else - ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS) - LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o - LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o + PYTHON_EMBED_LDOPTS = `python-config --ldflags 2>/dev/null` + PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null` + FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y) + BASIC_CFLAGS += -DNO_LIBPYTHON + else + ALL_LDFLAGS += $(PYTHON_EMBED_LDOPTS) + LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o + LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o + endif endif ifdef NO_DEMANGLE BASIC_CFLAGS += -DNO_DEMANGLE else - ifdef HAVE_CPLUS_DEMANGLE + ifdef HAVE_CPLUS_DEMANGLE EXTLIBS += -liberty BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE - else - has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y") - + else + FLAGS_BFD=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd + has_bfd := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD)) ifeq ($(has_bfd),y) EXTLIBS += -lbfd else - has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y") + FLAGS_BFD_IBERTY=$(FLAGS_BFD) -liberty + has_bfd_iberty := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY)) ifeq ($(has_bfd_iberty),y) EXTLIBS += -lbfd -liberty else - has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y") + FLAGS_BFD_IBERTY_Z=$(FLAGS_BFD_IBERTY) -lz + has_bfd_iberty_z := $(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD_IBERTY_Z)) ifeq ($(has_bfd_iberty_z),y) EXTLIBS += -lbfd -liberty -lz else - has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y") + FLAGS_CPLUS_DEMANGLE=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -liberty + has_cplus_demangle := $(call try-cc,$(SOURCE_CPLUS_DEMANGLE),$(FLAGS_CPLUS_DEMANGLE)) ifeq ($(has_cplus_demangle),y) EXTLIBS += -liberty BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE @@ -867,7 +875,7 @@ export TAR INSTALL DESTDIR SHELL_PATH SHELL = $(SHELL_PATH) -all:: .perf.dev.null shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS +all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS ifneq (,$X) $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';) endif @@ -1197,11 +1205,6 @@ clean: .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS .PHONY: .FORCE-PERF-BUILD-OPTIONS -.perf.dev.null: - touch .perf.dev.null - -.INTERMEDIATE: .perf.dev.null - ### Make sure built-ins do not have dups and listed in perf.c # check-builtins:: diff --git a/tools/perf/arch/sh/Makefile b/tools/perf/arch/sh/Makefile new file mode 100644 index 00000000000..15130b50dfe --- /dev/null +++ b/tools/perf/arch/sh/Makefile @@ -0,0 +1,4 @@ +ifndef NO_DWARF +PERF_HAVE_DWARF_REGS := 1 +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o +endif diff --git a/tools/perf/arch/sh/util/dwarf-regs.c b/tools/perf/arch/sh/util/dwarf-regs.c new file mode 100644 index 00000000000..a11edb007a6 --- /dev/null +++ b/tools/perf/arch/sh/util/dwarf-regs.c @@ -0,0 +1,55 @@ +/* + * Mapping of DWARF debug register numbers into register names. + * + * Copyright (C) 2010 Matt Fleming <matt@console-pimps.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + */ + +#include <libio.h> +#include <dwarf-regs.h> + +/* + * Generic dwarf analysis helpers + */ + +#define SH_MAX_REGS 18 +const char *sh_regs_table[SH_MAX_REGS] = { + "r0", + "r1", + "r2", + "r3", + "r4", + "r5", + "r6", + "r7", + "r8", + "r9", + "r10", + "r11", + "r12", + "r13", + "r14", + "r15", + "pc", + "pr", +}; + +/* Return architecture dependent register string (for kprobe-tracer) */ +const char *get_arch_regstr(unsigned int n) +{ + return (n <= SH_MAX_REGS) ? sh_regs_table[n] : NULL; +} diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 96db5248e99..fd20670ce98 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -61,11 +61,9 @@ static int hists__add_entry(struct hists *self, struct addr_location *al) static int process_sample_event(event_t *event, struct perf_session *session) { struct addr_location al; + struct sample_data data; - dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc, - event->ip.pid, event->ip.ip); - - if (event__preprocess_sample(event, session, &al, NULL) < 0) { + if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); return -1; diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index f8e3d185202..29ad20e6791 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -78,8 +78,7 @@ static int __cmd_buildid_cache(void) struct str_node *pos; char debugdir[PATH_MAX]; - snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"), - DEBUG_CACHE_DIR); + snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); if (add_name_list_str) { list = strlist__new(true, add_name_list_str); diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 99890728409..44a47e13bd6 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -43,10 +43,8 @@ static int __cmd_buildid_list(void) if (session == NULL) return -1; - if (with_hits) { - symbol_conf.full_paths = true; + if (with_hits) perf_session__process_events(session, &build_id__mark_dso_hit_ops); - } perf_session__fprintf_dsos_buildid(session, stdout, with_hits); diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index a6e2fdc7a04..fca1d440291 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -35,10 +35,7 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi struct addr_location al; struct sample_data data = { .period = 1, }; - dump_printf("(IP, %d): %d: %#Lx\n", event->header.misc, - event->ip.pid, event->ip.ip); - - if (event__preprocess_sample(event, session, &al, NULL) < 0) { + if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); return -1; @@ -47,8 +44,6 @@ static int diff__process_sample_event(event_t *event, struct perf_session *sessi if (al.filtered || al.sym == NULL) return 0; - event__parse_sample(event, session->sample_type, &data); - if (hists__add_entry(&session->hists, &al, data.period)) { pr_warning("problem incrementing symbol period, skipping event\n"); return -1; @@ -185,8 +180,6 @@ static const struct option options[] = { OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules, "load module symbols - WARNING: use only with -k and LIVE kernel"), - OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths, - "Don't shorten the pathnames taking into account the cwd"), OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]", "only consider symbols in these dsos"), OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]", diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index e4a4da32a56..199d5e19554 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -182,6 +182,8 @@ static const struct option options[] = { "Show source code lines.", opt_show_lines), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), + OPT_STRING('s', "source", &symbol_conf.source_prefix, + "directory", "path to kernel source"), #endif OPT__DRY_RUN(&probe_event_dry_run), OPT_INTEGER('\0', "max-probes", ¶ms.max_probe_points, @@ -265,4 +267,3 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) } return 0; } - diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 711745f56bb..ff77b805de7 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -49,7 +49,6 @@ static int group = 0; static int realtime_prio = 0; static bool raw_samples = false; static bool system_wide = false; -static int profile_cpu = -1; static pid_t target_pid = -1; static pid_t target_tid = -1; static pid_t *all_tids = NULL; @@ -61,6 +60,7 @@ static bool call_graph = false; static bool inherit_stat = false; static bool no_samples = false; static bool sample_address = false; +static bool no_buildid = false; static long samples = 0; static u64 bytes_written = 0; @@ -74,6 +74,7 @@ static int file_new = 1; static off_t post_processing_offset; static struct perf_session *session; +static const char *cpu_list; struct mmap_data { int counter; @@ -268,12 +269,17 @@ static void create_counter(int counter, int cpu) if (inherit_stat) attr->inherit_stat = 1; - if (sample_address) + if (sample_address) { attr->sample_type |= PERF_SAMPLE_ADDR; + attr->mmap_data = track; + } if (call_graph) attr->sample_type |= PERF_SAMPLE_CALLCHAIN; + if (system_wide) + attr->sample_type |= PERF_SAMPLE_CPU; + if (raw_samples) { attr->sample_type |= PERF_SAMPLE_TIME; attr->sample_type |= PERF_SAMPLE_RAW; @@ -300,7 +306,7 @@ try_again: die("Permission error - are you root?\n" "\t Consider tweaking" " /proc/sys/kernel/perf_event_paranoid.\n"); - else if (err == ENODEV && profile_cpu != -1) { + else if (err == ENODEV && cpu_list) { die("No such device - did you specify" " an out-of-range profile CPU?\n"); } @@ -433,14 +439,14 @@ static void atexit_header(void) process_buildids(); perf_header__write(&session->header, output, true); + perf_session__delete(session); + symbol__exit(); } } static void event__synthesize_guest_os(struct machine *machine, void *data) { int err; - char *guest_kallsyms; - char path[PATH_MAX]; struct perf_session *psession = data; if (machine__is_host(machine)) @@ -460,13 +466,6 @@ static void event__synthesize_guest_os(struct machine *machine, void *data) pr_err("Couldn't record guest kernel [%d]'s reference" " relocation symbol.\n", machine->pid); - if (machine__is_default_guest(machine)) - guest_kallsyms = (char *) symbol_conf.default_guest_kallsyms; - else { - sprintf(path, "%s/proc/kallsyms", machine->root_dir); - guest_kallsyms = path; - } - /* * We use _stext for guest kernel because guest kernel's /proc/kallsyms * have no _text sometimes. @@ -561,12 +560,15 @@ static int __cmd_record(int argc, const char **argv) if (!file_new) { err = perf_header__read(session, output); if (err < 0) - return err; + goto out_delete_session; } if (have_tracepoints(attrs, nr_counters)) perf_header__set_feat(&session->header, HEADER_TRACE_INFO); + /* + * perf_session__delete(session) will be called at atexit_header() + */ atexit(atexit_header); if (forks) { @@ -622,10 +624,15 @@ static int __cmd_record(int argc, const char **argv) close(child_ready_pipe[0]); } - if ((!system_wide && no_inherit) || profile_cpu != -1) { - open_counters(profile_cpu); + nr_cpus = read_cpu_map(cpu_list); + if (nr_cpus < 1) { + perror("failed to collect number of CPUs\n"); + return -1; + } + + if (!system_wide && no_inherit && !cpu_list) { + open_counters(-1); } else { - nr_cpus = read_cpu_map(); for (i = 0; i < nr_cpus; i++) open_counters(cpumap[i]); } @@ -704,7 +711,7 @@ static int __cmd_record(int argc, const char **argv) if (perf_guest) perf_session__process_machines(session, event__synthesize_guest_os); - if (!system_wide && profile_cpu == -1) + if (!system_wide) event__synthesize_thread(target_tid, process_synthesized_event, session); else @@ -766,6 +773,10 @@ static int __cmd_record(int argc, const char **argv) bytes_written / 24); return 0; + +out_delete_session: + perf_session__delete(session); + return err; } static const char * const record_usage[] = { @@ -794,8 +805,8 @@ static const struct option options[] = { "system-wide collection from all CPUs"), OPT_BOOLEAN('A', "append", &append_file, "append to the output file to do incremental profiling"), - OPT_INTEGER('C', "profile_cpu", &profile_cpu, - "CPU to profile on"), + OPT_STRING('C', "cpu", &cpu_list, "cpu", + "list of cpus to monitor"), OPT_BOOLEAN('f', "force", &force, "overwrite existing data file (deprecated)"), OPT_U64('c', "count", &user_interval, "event period to sample"), @@ -815,17 +826,19 @@ static const struct option options[] = { "Sample addresses"), OPT_BOOLEAN('n', "no-samples", &no_samples, "don't sample"), + OPT_BOOLEAN('N', "no-buildid-cache", &no_buildid, + "do not update the buildid cache"), OPT_END() }; int cmd_record(int argc, const char **argv, const char *prefix __used) { - int i,j; + int i, j, err = -ENOMEM; argc = parse_options(argc, argv, options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc && target_pid == -1 && target_tid == -1 && - !system_wide && profile_cpu == -1) + !system_wide && !cpu_list) usage_with_options(record_usage, options); if (force && append_file) { @@ -839,6 +852,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) } symbol__init(); + if (no_buildid) + disable_buildid_cache(); if (!nr_counters) { nr_counters = 1; @@ -857,7 +872,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) } else { all_tids=malloc(sizeof(pid_t)); if (!all_tids) - return -ENOMEM; + goto out_symbol_exit; all_tids[0] = target_tid; thread_num = 1; @@ -867,13 +882,13 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) for (j = 0; j < MAX_COUNTERS; j++) { fd[i][j] = malloc(sizeof(int)*thread_num); if (!fd[i][j]) - return -ENOMEM; + goto out_free_fd; } } event_array = malloc( sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num); if (!event_array) - return -ENOMEM; + goto out_free_fd; if (user_interval != ULLONG_MAX) default_interval = user_interval; @@ -889,8 +904,22 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) default_interval = freq; } else { fprintf(stderr, "frequency and count are zero, aborting\n"); - exit(EXIT_FAILURE); + err = -EINVAL; + goto out_free_event_array; } - return __cmd_record(argc, argv); + err = __cmd_record(argc, argv); + +out_free_event_array: + free(event_array); +out_free_fd: + for (i = 0; i < MAX_NR_CPUS; i++) { + for (j = 0; j < MAX_COUNTERS; j++) + free(fd[i][j]); + } + free(all_tids); + all_tids = NULL; +out_symbol_exit: + symbol__exit(); + return err; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index fd7407c7205..2f4b92925b2 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -155,30 +155,7 @@ static int process_sample_event(event_t *event, struct perf_session *session) struct addr_location al; struct perf_event_attr *attr; - event__parse_sample(event, session->sample_type, &data); - - dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld\n", event->header.misc, - data.pid, data.tid, data.ip, data.period); - - if (session->sample_type & PERF_SAMPLE_CALLCHAIN) { - unsigned int i; - - dump_printf("... chain: nr:%Lu\n", data.callchain->nr); - - if (!ip_callchain__valid(data.callchain, event)) { - pr_debug("call-chain problem with event, " - "skipping it.\n"); - return 0; - } - - if (dump_trace) { - for (i = 0; i < data.callchain->nr; i++) - dump_printf("..... %2d: %016Lx\n", - i, data.callchain->ips[i]); - } - } - - if (event__preprocess_sample(event, session, &al, NULL) < 0) { + if (event__preprocess_sample(event, session, &al, &data, NULL) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", event->header.type); return -1; @@ -464,8 +441,6 @@ static const struct option options[] = { "pretty printing style key: normal raw"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", "sort by key(s): pid, comm, dso, symbol, parent"), - OPT_BOOLEAN('P', "full-paths", &symbol_conf.full_paths, - "Don't shorten the pathnames taking into account the cwd"), OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 9a39ca3c3ac..a6b4d44f950 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -69,7 +69,7 @@ static struct perf_event_attr default_attrs[] = { }; static bool system_wide = false; -static unsigned int nr_cpus = 0; +static int nr_cpus = 0; static int run_idx = 0; static int run_count = 1; @@ -82,6 +82,7 @@ static int thread_num = 0; static pid_t child_pid = -1; static bool null_run = false; static bool big_num = false; +static const char *cpu_list; static int *fd[MAX_NR_CPUS][MAX_COUNTERS]; @@ -158,7 +159,7 @@ static int create_perf_stat_counter(int counter) PERF_FORMAT_TOTAL_TIME_RUNNING; if (system_wide) { - unsigned int cpu; + int cpu; for (cpu = 0; cpu < nr_cpus; cpu++) { fd[cpu][counter][0] = sys_perf_event_open(attr, @@ -208,7 +209,7 @@ static inline int nsec_counter(int counter) static void read_counter(int counter) { u64 count[3], single_count[3]; - unsigned int cpu; + int cpu; size_t res, nv; int scaled; int i, thread; @@ -542,6 +543,8 @@ static const struct option options[] = { "null run - dont start any counters"), OPT_BOOLEAN('B', "big-num", &big_num, "print large numbers with thousands\' separators"), + OPT_STRING('C', "cpu", &cpu_list, "cpu", + "list of cpus to monitor in system-wide"), OPT_END() }; @@ -566,10 +569,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) } if (system_wide) - nr_cpus = read_cpu_map(); + nr_cpus = read_cpu_map(cpu_list); else nr_cpus = 1; + if (nr_cpus < 1) + usage_with_options(stat_usage, options); + if (target_pid != -1) { target_tid = target_pid; thread_num = find_all_tid(target_pid, &all_tids); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index a66f4272b99..b513e40974f 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -102,6 +102,7 @@ struct sym_entry *sym_filter_entry_sched = NULL; static int sym_pcnt_filter = 5; static int sym_counter = 0; static int display_weighted = -1; +static const char *cpu_list; /* * Symbols @@ -982,6 +983,7 @@ static void event__process_sample(const event_t *self, u64 ip = self->ip.ip; struct sym_entry *syme; struct addr_location al; + struct sample_data data; struct machine *machine; u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; @@ -1024,7 +1026,8 @@ static void event__process_sample(const event_t *self, if (self->header.misc & PERF_RECORD_MISC_EXACT_IP) exact_samples++; - if (event__preprocess_sample(self, session, &al, symbol_filter) < 0 || + if (event__preprocess_sample(self, session, &al, &data, + symbol_filter) < 0 || al.filtered) return; @@ -1079,26 +1082,6 @@ static void event__process_sample(const event_t *self, } } -static int event__process(event_t *event, struct perf_session *session) -{ - switch (event->header.type) { - case PERF_RECORD_COMM: - event__process_comm(event, session); - break; - case PERF_RECORD_MMAP: - event__process_mmap(event, session); - break; - case PERF_RECORD_FORK: - case PERF_RECORD_EXIT: - event__process_task(event, session); - break; - default: - break; - } - - return 0; -} - struct mmap_data { int counter; void *base; @@ -1351,8 +1334,8 @@ static const struct option options[] = { "profile events on existing thread id"), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), - OPT_INTEGER('C', "CPU", &profile_cpu, - "CPU to profile on"), + OPT_STRING('C', "cpu", &cpu_list, "cpu", + "list of cpus to monitor"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols, @@ -1428,10 +1411,10 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) return -ENOMEM; /* CPU and PID are mutually exclusive */ - if (target_tid > 0 && profile_cpu != -1) { + if (target_tid > 0 && cpu_list) { printf("WARNING: PID switch overriding CPU\n"); sleep(1); - profile_cpu = -1; + cpu_list = NULL; } if (!nr_counters) @@ -1469,10 +1452,13 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) attrs[counter].sample_period = default_interval; } - if (target_tid != -1 || profile_cpu != -1) + if (target_tid != -1) nr_cpus = 1; else - nr_cpus = read_cpu_map(); + nr_cpus = read_cpu_map(cpu_list); + + if (nr_cpus < 1) + usage_with_options(top_usage, options); get_term_dimensions(&winsize); if (print_entries == 0) { diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index dddf3f01b5a..294da725a57 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -11,8 +11,9 @@ static char const *script_name; static char const *generate_script_lang; -static bool debug_ordering; +static bool debug_mode; static u64 last_timestamp; +static u64 nr_unordered; static int default_start_script(const char *script __unused, int argc __unused, @@ -91,13 +92,15 @@ static int process_sample_event(event_t *event, struct perf_session *session) } if (session->sample_type & PERF_SAMPLE_RAW) { - if (debug_ordering) { + if (debug_mode) { if (data.time < last_timestamp) { pr_err("Samples misordered, previous: %llu " "this: %llu\n", last_timestamp, data.time); + nr_unordered++; } last_timestamp = data.time; + return 0; } /* * FIXME: better resolve from pid from the struct trace_entry @@ -113,6 +116,15 @@ static int process_sample_event(event_t *event, struct perf_session *session) return 0; } +static u64 nr_lost; + +static int process_lost_event(event_t *event, struct perf_session *session __used) +{ + nr_lost += event->lost.lost; + + return 0; +} + static struct perf_event_ops event_ops = { .sample = process_sample_event, .comm = event__process_comm, @@ -120,6 +132,7 @@ static struct perf_event_ops event_ops = { .event_type = event__process_event_type, .tracing_data = event__process_tracing_data, .build_id = event__process_build_id, + .lost = process_lost_event, .ordered_samples = true, }; @@ -132,9 +145,18 @@ static void sig_handler(int sig __unused) static int __cmd_trace(struct perf_session *session) { + int ret; + signal(SIGINT, sig_handler); - return perf_session__process_events(session, &event_ops); + ret = perf_session__process_events(session, &event_ops); + + if (debug_mode) { + pr_err("Misordered timestamps: %llu\n", nr_unordered); + pr_err("Lost events: %llu\n", nr_lost); + } + + return ret; } struct script_spec { @@ -544,8 +566,8 @@ static const struct option options[] = { "generate perf-trace.xx script in specified language"), OPT_STRING('i', "input", &input_name, "file", "input file name"), - OPT_BOOLEAN('d', "debug-ordering", &debug_ordering, - "check that samples time ordering is monotonic"), + OPT_BOOLEAN('d', "debug-mode", &debug_mode, + "do various checks like samples ordering and lost events"), OPT_END() }; diff --git a/tools/perf/feature-tests.mak b/tools/perf/feature-tests.mak new file mode 100644 index 00000000000..ddb68e601f0 --- /dev/null +++ b/tools/perf/feature-tests.mak @@ -0,0 +1,119 @@ +define SOURCE_HELLO +#include <stdio.h> +int main(void) +{ + return puts(\"hi\"); +} +endef + +ifndef NO_DWARF +define SOURCE_DWARF +#include <dwarf.h> +#include <libdw.h> +#include <version.h> +#ifndef _ELFUTILS_PREREQ +#error +#endif + +int main(void) +{ + Dwarf *dbg = dwarf_begin(0, DWARF_C_READ); + return (long)dbg; +} +endef +endif + +define SOURCE_LIBELF +#include <libelf.h> + +int main(void) +{ + Elf *elf = elf_begin(0, ELF_C_READ, 0); + return (long)elf; +} +endef + +define SOURCE_GLIBC +#include <gnu/libc-version.h> + +int main(void) +{ + const char *version = gnu_get_libc_version(); + return (long)version; +} +endef + +define SOURCE_ELF_MMAP +#include <libelf.h> +int main(void) +{ + Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0); + return (long)elf; +} +endef + +ifndef NO_NEWT +define SOURCE_NEWT +#include <newt.h> + +int main(void) +{ + newtInit(); + newtCls(); + return newtFinished(); +} +endef +endif + +ifndef NO_LIBPERL +define SOURCE_PERL_EMBED +#include <EXTERN.h> +#include <perl.h> + +int main(void) +{ +perl_alloc(); +return 0; +} +endef +endif + +ifndef NO_LIBPYTHON +define SOURCE_PYTHON_EMBED +#include <Python.h> + +int main(void) +{ + Py_Initialize(); + return 0; +} +endef +endif + +define SOURCE_BFD +#include <bfd.h> + +int main(void) +{ + bfd_demangle(0, 0, 0); + return 0; +} +endef + +define SOURCE_CPLUS_DEMANGLE +extern char *cplus_demangle(const char *, int); + +int main(void) +{ + cplus_demangle(0, 0); + return 0; +} +endef + +# try-cc +# Usage: option = $(call try-cc, source-to-build, cc-options) +try-cc = $(shell sh -c \ + 'TMP="$(TMPOUT).$$$$"; \ + echo "$(1)" | \ + $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \ + rm -f "$$TMP"') diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh index 2e7a4f417e2..677e59d62a8 100644 --- a/tools/perf/perf-archive.sh +++ b/tools/perf/perf-archive.sh @@ -7,7 +7,17 @@ if [ $# -ne 0 ] ; then PERF_DATA=$1 fi -DEBUGDIR=~/.debug/ +# +# PERF_BUILDID_DIR environment variable set by perf +# path to buildid directory, default to $HOME/.debug +# +if [ -z $PERF_BUILDID_DIR ]; then + PERF_BUILDID_DIR=~/.debug/ +else + # append / to make substitutions work + PERF_BUILDID_DIR=$PERF_BUILDID_DIR/ +fi + BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX) NOBUILDID=0000000000000000000000000000000000000000 @@ -22,13 +32,13 @@ MANIFEST=$(mktemp /tmp/perf-archive-manifest.XXXXXX) cut -d ' ' -f 1 $BUILDIDS | \ while read build_id ; do - linkname=$DEBUGDIR.build-id/${build_id:0:2}/${build_id:2} + linkname=$PERF_BUILDID_DIR.build-id/${build_id:0:2}/${build_id:2} filename=$(readlink -f $linkname) - echo ${linkname#$DEBUGDIR} >> $MANIFEST - echo ${filename#$DEBUGDIR} >> $MANIFEST + echo ${linkname#$PERF_BUILDID_DIR} >> $MANIFEST + echo ${filename#$PERF_BUILDID_DIR} >> $MANIFEST done -tar cfj $PERF_DATA.tar.bz2 -C $DEBUGDIR -T $MANIFEST +tar cfj $PERF_DATA.tar.bz2 -C $PERF_BUILDID_DIR -T $MANIFEST rm -f $MANIFEST $BUILDIDS echo -e "Now please run:\n" echo -e "$ tar xvf $PERF_DATA.tar.bz2 -C ~/.debug\n" diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 6e487119113..cdd6c03f1e1 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -458,6 +458,8 @@ int main(int argc, const char **argv) handle_options(&argv, &argc, NULL); commit_pager_choice(); set_debugfs_path(); + set_buildid_dir(); + if (argc > 0) { if (!prefixcmp(argv[0], "--")) argv[0] += 2; diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py index 1dc464ee2ca..aad7525bca1 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py @@ -89,3 +89,33 @@ def trace_flag_str(value): value &= ~idx return string + + +def taskState(state): + states = { + 0 : "R", + 1 : "S", + 2 : "D", + 64: "DEAD" + } + + if state not in states: + return "Unknown" + + return states[state] + + +class EventHeaders: + def __init__(self, common_cpu, common_secs, common_nsecs, + common_pid, common_comm): + self.cpu = common_cpu + self.secs = common_secs + self.nsecs = common_nsecs + self.pid = common_pid + self.comm = common_comm + + def ts(self): + return (self.secs * (10 ** 9)) + self.nsecs + + def ts_format(self): + return "%d.%d" % (self.secs, int(self.nsecs / 1000)) diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py new file mode 100644 index 00000000000..ae9a56e43e0 --- /dev/null +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py @@ -0,0 +1,184 @@ +# SchedGui.py - Python extension for perf trace, basic GUI code for +# traces drawing and overview. +# +# Copyright (C) 2010 by Frederic Weisbecker <fweisbec@gmail.com> +# +# This software is distributed under the terms of the GNU General +# Public License ("GPL") version 2 as published by the Free Software +# Foundation. + + +try: + import wx +except ImportError: + raise ImportError, "You need to install the wxpython lib for this script" + + +class RootFrame(wx.Frame): + Y_OFFSET = 100 + RECT_HEIGHT = 100 + RECT_SPACE = 50 + EVENT_MARKING_WIDTH = 5 + + def __init__(self, sched_tracer, title, parent = None, id = -1): + wx.Frame.__init__(self, parent, id, title) + + (self.screen_width, self.screen_height) = wx.GetDisplaySize() + self.screen_width -= 10 + self.screen_height -= 10 + self.zoom = 0.5 + self.scroll_scale = 20 + self.sched_tracer = sched_tracer + self.sched_tracer.set_root_win(self) + (self.ts_start, self.ts_end) = sched_tracer.interval() + self.update_width_virtual() + self.nr_rects = sched_tracer.nr_rectangles() + 1 + self.height_virtual = RootFrame.Y_OFFSET + (self.nr_rects * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)) + + # whole window panel + self.panel = wx.Panel(self, size=(self.screen_width, self.screen_height)) + + # scrollable container + self.scroll = wx.ScrolledWindow(self.panel) + self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, self.width_virtual / self.scroll_scale, self.height_virtual / self.scroll_scale) + self.scroll.EnableScrolling(True, True) + self.scroll.SetFocus() + + # scrollable drawing area + self.scroll_panel = wx.Panel(self.scroll, size=(self.screen_width - 15, self.screen_height / 2)) + self.scroll_panel.Bind(wx.EVT_PAINT, self.on_paint) + self.scroll_panel.Bind(wx.EVT_KEY_DOWN, self.on_key_press) + self.scroll_panel.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down) + self.scroll.Bind(wx.EVT_PAINT, self.on_paint) + self.scroll.Bind(wx.EVT_KEY_DOWN, self.on_key_press) + self.scroll.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down) + + self.scroll.Fit() + self.Fit() + + self.scroll_panel.SetDimensions(-1, -1, self.width_virtual, self.height_virtual, wx.SIZE_USE_EXISTING) + + self.txt = None + + self.Show(True) + + def us_to_px(self, val): + return val / (10 ** 3) * self.zoom + + def px_to_us(self, val): + return (val / self.zoom) * (10 ** 3) + + def scroll_start(self): + (x, y) = self.scroll.GetViewStart() + return (x * self.scroll_scale, y * self.scroll_scale) + + def scroll_start_us(self): + (x, y) = self.scroll_start() + return self.px_to_us(x) + + def paint_rectangle_zone(self, nr, color, top_color, start, end): + offset_px = self.us_to_px(start - self.ts_start) + width_px = self.us_to_px(end - self.ts_start) + + offset_py = RootFrame.Y_OFFSET + (nr * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)) + width_py = RootFrame.RECT_HEIGHT + + dc = self.dc + + if top_color is not None: + (r, g, b) = top_color + top_color = wx.Colour(r, g, b) + brush = wx.Brush(top_color, wx.SOLID) + dc.SetBrush(brush) + dc.DrawRectangle(offset_px, offset_py, width_px, RootFrame.EVENT_MARKING_WIDTH) + width_py -= RootFrame.EVENT_MARKING_WIDTH + offset_py += RootFrame.EVENT_MARKING_WIDTH + + (r ,g, b) = color + color = wx.Colour(r, g, b) + brush = wx.Brush(color, wx.SOLID) + dc.SetBrush(brush) + dc.DrawRectangle(offset_px, offset_py, width_px, width_py) + + def update_rectangles(self, dc, start, end): + start += self.ts_start + end += self.ts_start + self.sched_tracer.fill_zone(start, end) + + def on_paint(self, event): + dc = wx.PaintDC(self.scroll_panel) + self.dc = dc + + width = min(self.width_virtual, self.screen_width) + (x, y) = self.scroll_start() + start = self.px_to_us(x) + end = self.px_to_us(x + width) + self.update_rectangles(dc, start, end) + + def rect_from_ypixel(self, y): + y -= RootFrame.Y_OFFSET + rect = y / (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE) + height = y % (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE) + + if rect < 0 or rect > self.nr_rects - 1 or height > RootFrame.RECT_HEIGHT: + return -1 + + return rect + + def update_summary(self, txt): + if self.txt: + self.txt.Destroy() + self.txt = wx.StaticText(self.panel, -1, txt, (0, (self.screen_height / 2) + 50)) + + + def on_mouse_down(self, event): + (x, y) = event.GetPositionTuple() + rect = self.rect_from_ypixel(y) + if rect == -1: + return + + t = self.px_to_us(x) + self.ts_start + + self.sched_tracer.mouse_down(rect, t) + + + def update_width_virtual(self): + self.width_virtual = self.us_to_px(self.ts_end - self.ts_start) + + def __zoom(self, x): + self.update_width_virtual() + (xpos, ypos) = self.scroll.GetViewStart() + xpos = self.us_to_px(x) / self.scroll_scale + self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, self.width_virtual / self.scroll_scale, self.height_virtual / self.scroll_scale, xpos, ypos) + self.Refresh() + + def zoom_in(self): + x = self.scroll_start_us() + self.zoom *= 2 + self.__zoom(x) + + def zoom_out(self): + x = self.scroll_start_us() + self.zoom /= 2 + self.__zoom(x) + + + def on_key_press(self, event): + key = event.GetRawKeyCode() + if key == ord("+"): + self.zoom_in() + return + if key == ord("-"): + self.zoom_out() + return + + key = event.GetKeyCode() + (x, y) = self.scroll.GetViewStart() + if key == wx.WXK_RIGHT: + self.scroll.Scroll(x + 1, y) + elif key == wx.WXK_LEFT: + self.scroll.Scroll(x - 1, y) + elif key == wx.WXK_DOWN: + self.scroll.Scroll(x, y + 1) + elif key == wx.WXK_UP: + self.scroll.Scroll(x, y - 1) diff --git a/tools/perf/scripts/python/bin/sched-migration-record b/tools/perf/scripts/python/bin/sched-migration-record new file mode 100644 index 00000000000..17a3e9bd9e8 --- /dev/null +++ b/tools/perf/scripts/python/bin/sched-migration-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -m 16384 -a -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@ diff --git a/tools/perf/scripts/python/bin/sched-migration-report b/tools/perf/scripts/python/bin/sched-migration-report new file mode 100644 index 00000000000..61d05f72e44 --- /dev/null +++ b/tools/perf/scripts/python/bin/sched-migration-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: sched migration overview +perf trace $@ -s ~/libexec/perf-core/scripts/python/sched-migration.py diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py new file mode 100644 index 00000000000..b934383c336 --- /dev/null +++ b/tools/perf/scripts/python/sched-migration.py @@ -0,0 +1,461 @@ +#!/usr/bin/python +# +# Cpu task migration overview toy +# +# Copyright (C) 2010 Frederic Weisbecker <fweisbec@gmail.com> +# +# perf trace event handlers have been generated by perf trace -g python +# +# This software is distributed under the terms of the GNU General +# Public License ("GPL") version 2 as published by the Free Software +# Foundation. + + +import os +import sys + +from collections import defaultdict +from UserList import UserList + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') +sys.path.append('scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from SchedGui import * + + +threads = { 0 : "idle"} + +def thread_name(pid): + return "%s:%d" % (threads[pid], pid) + +class RunqueueEventUnknown: + @staticmethod + def color(): + return None + + def __repr__(self): + return "unknown" + +class RunqueueEventSleep: + @staticmethod + def color(): + return (0, 0, 0xff) + + def __init__(self, sleeper): + self.sleeper = sleeper + + def __repr__(self): + return "%s gone to sleep" % thread_name(self.sleeper) + +class RunqueueEventWakeup: + @staticmethod + def color(): + return (0xff, 0xff, 0) + + def __init__(self, wakee): + self.wakee = wakee + + def __repr__(self): + return "%s woke up" % thread_name(self.wakee) + +class RunqueueEventFork: + @staticmethod + def color(): + return (0, 0xff, 0) + + def __init__(self, child): + self.child = child + + def __repr__(self): + return "new forked task %s" % thread_name(self.child) + +class RunqueueMigrateIn: + @staticmethod + def color(): + return (0, 0xf0, 0xff) + + def __init__(self, new): + self.new = new + + def __repr__(self): + return "task migrated in %s" % thread_name(self.new) + +class RunqueueMigrateOut: + @staticmethod + def color(): + return (0xff, 0, 0xff) + + def __init__(self, old): + self.old = old + + def __repr__(self): + return "task migrated out %s" % thread_name(self.old) + +class RunqueueSnapshot: + def __init__(self, tasks = [0], event = RunqueueEventUnknown()): + self.tasks = tuple(tasks) + self.event = event + + def sched_switch(self, prev, prev_state, next): + event = RunqueueEventUnknown() + + if taskState(prev_state) == "R" and next in self.tasks \ + and prev in self.tasks: + return self + + if taskState(prev_state) != "R": + event = RunqueueEventSleep(prev) + + next_tasks = list(self.tasks[:]) + if prev in self.tasks: + if taskState(prev_state) != "R": + next_tasks.remove(prev) + elif taskState(prev_state) == "R": + next_tasks.append(prev) + + if next not in next_tasks: + next_tasks.append(next) + + return RunqueueSnapshot(next_tasks, event) + + def migrate_out(self, old): + if old not in self.tasks: + return self + next_tasks = [task for task in self.tasks if task != old] + + return RunqueueSnapshot(next_tasks, RunqueueMigrateOut(old)) + + def __migrate_in(self, new, event): + if new in self.tasks: + self.event = event + return self + next_tasks = self.tasks[:] + tuple([new]) + + return RunqueueSnapshot(next_tasks, event) + + def migrate_in(self, new): + return self.__migrate_in(new, RunqueueMigrateIn(new)) + + def wake_up(self, new): + return self.__migrate_in(new, RunqueueEventWakeup(new)) + + def wake_up_new(self, new): + return self.__migrate_in(new, RunqueueEventFork(new)) + + def load(self): + """ Provide the number of tasks on the runqueue. + Don't count idle""" + return len(self.tasks) - 1 + + def __repr__(self): + ret = self.tasks.__repr__() + ret += self.origin_tostring() + + return ret + +class TimeSlice: + def __init__(self, start, prev): + self.start = start + self.prev = prev + self.end = start + # cpus that triggered the event + self.event_cpus = [] + if prev is not None: + self.total_load = prev.total_load + self.rqs = prev.rqs.copy() + else: + self.rqs = defaultdict(RunqueueSnapshot) + self.total_load = 0 + + def __update_total_load(self, old_rq, new_rq): + diff = new_rq.load() - old_rq.load() + self.total_load += diff + + def sched_switch(self, ts_list, prev, prev_state, next, cpu): + old_rq = self.prev.rqs[cpu] + new_rq = old_rq.sched_switch(prev, prev_state, next) + + if old_rq is new_rq: + return + + self.rqs[cpu] = new_rq + self.__update_total_load(old_rq, new_rq) + ts_list.append(self) + self.event_cpus = [cpu] + + def migrate(self, ts_list, new, old_cpu, new_cpu): + if old_cpu == new_cpu: + return + old_rq = self.prev.rqs[old_cpu] + out_rq = old_rq.migrate_out(new) + self.rqs[old_cpu] = out_rq + self.__update_total_load(old_rq, out_rq) + + new_rq = self.prev.rqs[new_cpu] + in_rq = new_rq.migrate_in(new) + self.rqs[new_cpu] = in_rq + self.__update_total_load(new_rq, in_rq) + + ts_list.append(self) + + if old_rq is not out_rq: + self.event_cpus.append(old_cpu) + self.event_cpus.append(new_cpu) + + def wake_up(self, ts_list, pid, cpu, fork): + old_rq = self.prev.rqs[cpu] + if fork: + new_rq = old_rq.wake_up_new(pid) + else: + new_rq = old_rq.wake_up(pid) + + if new_rq is old_rq: + return + self.rqs[cpu] = new_rq + self.__update_total_load(old_rq, new_rq) + ts_list.append(self) + self.event_cpus = [cpu] + + def next(self, t): + self.end = t + return TimeSlice(t, self) + +class TimeSliceList(UserList): + def __init__(self, arg = []): + self.data = arg + + def get_time_slice(self, ts): + if len(self.data) == 0: + slice = TimeSlice(ts, TimeSlice(-1, None)) + else: + slice = self.data[-1].next(ts) + return slice + + def find_time_slice(self, ts): + start = 0 + end = len(self.data) + found = -1 + searching = True + while searching: + if start == end or start == end - 1: + searching = False + + i = (end + start) / 2 + if self.data[i].start <= ts and self.data[i].end >= ts: + found = i + end = i + continue + + if self.data[i].end < ts: + start = i + + elif self.data[i].start > ts: + end = i + + return found + + def set_root_win(self, win): + self.root_win = win + + def mouse_down(self, cpu, t): + idx = self.find_time_slice(t) + if idx == -1: + return + + ts = self[idx] + rq = ts.rqs[cpu] + raw = "CPU: %d\n" % cpu + raw += "Last event : %s\n" % rq.event.__repr__() + raw += "Timestamp : %d.%06d\n" % (ts.start / (10 ** 9), (ts.start % (10 ** 9)) / 1000) + raw += "Duration : %6d us\n" % ((ts.end - ts.start) / (10 ** 6)) + raw += "Load = %d\n" % rq.load() + for t in rq.tasks: + raw += "%s \n" % thread_name(t) + + self.root_win.update_summary(raw) + + def update_rectangle_cpu(self, slice, cpu): + rq = slice.rqs[cpu] + + if slice.total_load != 0: + load_rate = rq.load() / float(slice.total_load) + else: + load_rate = 0 + + red_power = int(0xff - (0xff * load_rate)) + color = (0xff, red_power, red_power) + + top_color = None + + if cpu in slice.event_cpus: + top_color = rq.event.color() + + self.root_win.paint_rectangle_zone(cpu, color, top_color, slice.start, slice.end) + + def fill_zone(self, start, end): + i = self.find_time_slice(start) + if i == -1: + return + + for i in xrange(i, len(self.data)): + timeslice = self.data[i] + if timeslice.start > end: + return + + for cpu in timeslice.rqs: + self.update_rectangle_cpu(timeslice, cpu) + + def interval(self): + if len(self.data) == 0: + return (0, 0) + + return (self.data[0].start, self.data[-1].end) + + def nr_rectangles(self): + last_ts = self.data[-1] + max_cpu = 0 + for cpu in last_ts.rqs: + if cpu > max_cpu: + max_cpu = cpu + return max_cpu + + +class SchedEventProxy: + def __init__(self): + self.current_tsk = defaultdict(lambda : -1) + self.timeslices = TimeSliceList() + + def sched_switch(self, headers, prev_comm, prev_pid, prev_prio, prev_state, + next_comm, next_pid, next_prio): + """ Ensure the task we sched out this cpu is really the one + we logged. Otherwise we may have missed traces """ + + on_cpu_task = self.current_tsk[headers.cpu] + + if on_cpu_task != -1 and on_cpu_task != prev_pid: + print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \ + (headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid) + + threads[prev_pid] = prev_comm + threads[next_pid] = next_comm + self.current_tsk[headers.cpu] = next_pid + + ts = self.timeslices.get_time_slice(headers.ts()) + ts.sched_switch(self.timeslices, prev_pid, prev_state, next_pid, headers.cpu) + + def migrate(self, headers, pid, prio, orig_cpu, dest_cpu): + ts = self.timeslices.get_time_slice(headers.ts()) + ts.migrate(self.timeslices, pid, orig_cpu, dest_cpu) + + def wake_up(self, headers, comm, pid, success, target_cpu, fork): + if success == 0: + return + ts = self.timeslices.get_time_slice(headers.ts()) + ts.wake_up(self.timeslices, pid, target_cpu, fork) + + +def trace_begin(): + global parser + parser = SchedEventProxy() + +def trace_end(): + app = wx.App(False) + timeslices = parser.timeslices + frame = RootFrame(timeslices, "Migration") + app.MainLoop() + +def sched__sched_stat_runtime(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, runtime, vruntime): + pass + +def sched__sched_stat_iowait(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, delay): + pass + +def sched__sched_stat_sleep(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, delay): + pass + +def sched__sched_stat_wait(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, delay): + pass + +def sched__sched_process_fork(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + parent_comm, parent_pid, child_comm, child_pid): + pass + +def sched__sched_process_wait(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, prio): + pass + +def sched__sched_process_exit(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, prio): + pass + +def sched__sched_process_free(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, prio): + pass + +def sched__sched_migrate_task(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, prio, orig_cpu, + dest_cpu): + headers = EventHeaders(common_cpu, common_secs, common_nsecs, + common_pid, common_comm) + parser.migrate(headers, pid, prio, orig_cpu, dest_cpu) + +def sched__sched_switch(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + prev_comm, prev_pid, prev_prio, prev_state, + next_comm, next_pid, next_prio): + + headers = EventHeaders(common_cpu, common_secs, common_nsecs, + common_pid, common_comm) + parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state, + next_comm, next_pid, next_prio) + +def sched__sched_wakeup_new(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, prio, success, + target_cpu): + headers = EventHeaders(common_cpu, common_secs, common_nsecs, + common_pid, common_comm) + parser.wake_up(headers, comm, pid, success, target_cpu, 1) + +def sched__sched_wakeup(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, prio, success, + target_cpu): + headers = EventHeaders(common_cpu, common_secs, common_nsecs, + common_pid, common_comm) + parser.wake_up(headers, comm, pid, success, target_cpu, 0) + +def sched__sched_wait_task(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid, prio): + pass + +def sched__sched_kthread_stop_ret(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + ret): + pass + +def sched__sched_kthread_stop(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + comm, pid): + pass + +def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs, + common_pid, common_comm): + pass diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 70c5cf87d02..e437edb7241 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -12,6 +12,7 @@ #include "event.h" #include "symbol.h" #include <linux/kernel.h> +#include "debug.h" static int build_id__mark_dso_hit(event_t *event, struct perf_session *session) { @@ -34,28 +35,43 @@ static int build_id__mark_dso_hit(event_t *event, struct perf_session *session) return 0; } +static int event__exit_del_thread(event_t *self, struct perf_session *session) +{ + struct thread *thread = perf_session__findnew(session, self->fork.tid); + + dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid, + self->fork.ppid, self->fork.ptid); + + if (thread) { + rb_erase(&thread->rb_node, &session->threads); + session->last_match = NULL; + thread__delete(thread); + } + + return 0; +} + struct perf_event_ops build_id__mark_dso_hit_ops = { .sample = build_id__mark_dso_hit, .mmap = event__process_mmap, .fork = event__process_task, + .exit = event__exit_del_thread, }; char *dso__build_id_filename(struct dso *self, char *bf, size_t size) { char build_id_hex[BUILD_ID_SIZE * 2 + 1]; - const char *home; if (!self->has_build_id) return NULL; build_id__sprintf(self->build_id, sizeof(self->build_id), build_id_hex); - home = getenv("HOME"); if (bf == NULL) { - if (asprintf(&bf, "%s/%s/.build-id/%.2s/%s", home, - DEBUG_CACHE_DIR, build_id_hex, build_id_hex + 2) < 0) + if (asprintf(&bf, "%s/.build-id/%.2s/%s", buildid_dir, + build_id_hex, build_id_hex + 2) < 0) return NULL; } else - snprintf(bf, size, "%s/%s/.build-id/%.2s/%s", home, - DEBUG_CACHE_DIR, build_id_hex, build_id_hex + 2); + snprintf(bf, size, "%s/.build-id/%.2s/%s", buildid_dir, + build_id_hex, build_id_hex + 2); return bf; } diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 65fe664fddf..27e9ebe4076 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -23,6 +23,7 @@ extern int perf_config(config_fn_t fn, void *); extern int perf_config_int(const char *, const char *); extern int perf_config_bool(const char *, const char *); extern int config_error_nonbool(const char *); +extern const char *perf_config_dirname(const char *, const char *); /* pager.c */ extern void setup_pager(void); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 52c777e451e..f231f43424d 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -18,7 +18,7 @@ #include "util.h" #include "callchain.h" -bool ip_callchain__valid(struct ip_callchain *chain, event_t *event) +bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event) { unsigned int chain_size = event->header.size; chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index f2e9ee164bd..624a96c636f 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -63,5 +63,5 @@ int register_callchain_param(struct callchain_param *param); int append_chain(struct callchain_node *root, struct ip_callchain *chain, struct map_symbol *syms, u64 period); -bool ip_callchain__valid(struct ip_callchain *chain, event_t *event); +bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event); #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index dabe892d0e5..e02d78cae70 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -11,6 +11,11 @@ #define MAXNAME (256) +#define DEBUG_CACHE_DIR ".debug" + + +char buildid_dir[MAXPATHLEN]; /* root dir for buildid, binary cache */ + static FILE *config_file; static const char *config_file_name; static int config_linenr; @@ -127,7 +132,7 @@ static int get_value(config_fn_t fn, void *data, char *name, unsigned int len) break; if (!iskeychar(c)) break; - name[len++] = tolower(c); + name[len++] = c; if (len >= MAXNAME) return -1; } @@ -327,6 +332,13 @@ int perf_config_bool(const char *name, const char *value) return !!perf_config_bool_or_int(name, value, &discard); } +const char *perf_config_dirname(const char *name, const char *value) +{ + if (!name) + return NULL; + return value; +} + static int perf_default_core_config(const char *var __used, const char *value __used) { /* Add other config variables here and to Documentation/config.txt. */ @@ -428,3 +440,53 @@ int config_error_nonbool(const char *var) { return error("Missing value for '%s'", var); } + +struct buildid_dir_config { + char *dir; +}; + +static int buildid_dir_command_config(const char *var, const char *value, + void *data) +{ + struct buildid_dir_config *c = data; + const char *v; + + /* same dir for all commands */ + if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) { + v = perf_config_dirname(var, value); + if (!v) + return -1; + strncpy(c->dir, v, MAXPATHLEN-1); + c->dir[MAXPATHLEN-1] = '\0'; + } + return 0; +} + +static void check_buildid_dir_config(void) +{ + struct buildid_dir_config c; + c.dir = buildid_dir; + perf_config(buildid_dir_command_config, &c); +} + +void set_buildid_dir(void) +{ + buildid_dir[0] = '\0'; + + /* try config file */ + check_buildid_dir_config(); + + /* default to $HOME/.debug */ + if (buildid_dir[0] == '\0') { + char *v = getenv("HOME"); + if (v) { + snprintf(buildid_dir, MAXPATHLEN-1, "%s/%s", + v, DEBUG_CACHE_DIR); + } else { + strncpy(buildid_dir, DEBUG_CACHE_DIR, MAXPATHLEN-1); + } + buildid_dir[MAXPATHLEN-1] = '\0'; + } + /* for communicating with external commands */ + setenv("PERF_BUILDID_DIR", buildid_dir, 1); +} diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 4e01490e51e..0f9b8d7a7d7 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -20,7 +20,7 @@ static int default_cpu_map(void) return nr_cpus; } -int read_cpu_map(void) +static int read_all_cpu_map(void) { FILE *onlnf; int nr_cpus = 0; @@ -57,3 +57,58 @@ int read_cpu_map(void) return default_cpu_map(); } + +int read_cpu_map(const char *cpu_list) +{ + unsigned long start_cpu, end_cpu = 0; + char *p = NULL; + int i, nr_cpus = 0; + + if (!cpu_list) + return read_all_cpu_map(); + + if (!isdigit(*cpu_list)) + goto invalid; + + while (isdigit(*cpu_list)) { + p = NULL; + start_cpu = strtoul(cpu_list, &p, 0); + if (start_cpu >= INT_MAX + || (*p != '\0' && *p != ',' && *p != '-')) + goto invalid; + + if (*p == '-') { + cpu_list = ++p; + p = NULL; + end_cpu = strtoul(cpu_list, &p, 0); + + if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',')) + goto invalid; + + if (end_cpu < start_cpu) + goto invalid; + } else { + end_cpu = start_cpu; + } + + for (; start_cpu <= end_cpu; start_cpu++) { + /* check for duplicates */ + for (i = 0; i < nr_cpus; i++) + if (cpumap[i] == (int)start_cpu) + goto invalid; + + assert(nr_cpus < MAX_NR_CPUS); + cpumap[nr_cpus++] = (int)start_cpu; + } + if (*p) + ++p; + + cpu_list = p; + } + if (nr_cpus > 0) + return nr_cpus; + + return default_cpu_map(); +invalid: + return -1; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 86c78bb3309..3e60f56e490 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -1,7 +1,7 @@ #ifndef __PERF_CPUMAP_H #define __PERF_CPUMAP_H -extern int read_cpu_map(void); +extern int read_cpu_map(const char *cpu_list); extern int cpumap[]; #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 6cddff2bc97..318dab15d17 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -86,12 +86,10 @@ void trace_event(event_t *event) dump_printf_color(" ", color); for (j = 0; j < 15-(i & 15); j++) dump_printf_color(" ", color); - for (j = 0; j < (i & 15); j++) { - if (isprint(raw_event[i-15+j])) - dump_printf_color("%c", color, - raw_event[i-15+j]); - else - dump_printf_color(".", color); + for (j = i & ~15; j <= i; j++) { + dump_printf_color("%c", color, + isprint(raw_event[j]) ? + raw_event[j] : '.'); } dump_printf_color("\n", color); } diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 2fbf6a463c8..dab9e754a28 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -151,7 +151,6 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, continue; pbf += n + 3; if (*pbf == 'x') { /* vm_exec */ - u64 vm_pgoff; char *execname = strchr(bf, '/'); /* Catch VDSO */ @@ -162,12 +161,7 @@ static int event__synthesize_mmap_events(pid_t pid, pid_t tgid, continue; pbf += 3; - n = hex2u64(pbf, &vm_pgoff); - /* pgoff is in bytes, not pages */ - if (n >= 0) - ev.mmap.pgoff = vm_pgoff << getpagesize(); - else - ev.mmap.pgoff = 0; + n = hex2u64(pbf, &ev.mmap.pgoff); size = strlen(execname); execname[size - 1] = '\0'; /* Remove \n */ @@ -340,30 +334,29 @@ int event__synthesize_kernel_mmap(event__handler_t process, return process(&ev, session); } -static void thread__comm_adjust(struct thread *self) +static void thread__comm_adjust(struct thread *self, struct hists *hists) { char *comm = self->comm; if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep && (!symbol_conf.comm_list || strlist__has_entry(symbol_conf.comm_list, comm))) { - unsigned int slen = strlen(comm); + u16 slen = strlen(comm); - if (slen > comms__col_width) { - comms__col_width = slen; - threads__col_width = slen + 6; - } + if (hists__new_col_len(hists, HISTC_COMM, slen)) + hists__set_col_len(hists, HISTC_THREAD, slen + 6); } } -static int thread__set_comm_adjust(struct thread *self, const char *comm) +static int thread__set_comm_adjust(struct thread *self, const char *comm, + struct hists *hists) { int ret = thread__set_comm(self, comm); if (ret) return ret; - thread__comm_adjust(self); + thread__comm_adjust(self, hists); return 0; } @@ -374,7 +367,8 @@ int event__process_comm(event_t *self, struct perf_session *session) dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid); - if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm)) { + if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm, + &session->hists)) { dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); return -1; } @@ -456,6 +450,7 @@ static int event__process_kernel_mmap(event_t *self, goto out_problem; map->dso->short_name = name; + map->dso->sname_alloc = 1; map->end = map->start + self->mmap.len; } else if (is_kernel_mmap) { const char *symbol_name = (self->mmap.filename + @@ -514,12 +509,13 @@ int event__process_mmap(event_t *self, struct perf_session *session) if (machine == NULL) goto out_problem; thread = perf_session__findnew(session, self->mmap.pid); + if (thread == NULL) + goto out_problem; map = map__new(&machine->user_dsos, self->mmap.start, self->mmap.len, self->mmap.pgoff, self->mmap.pid, self->mmap.filename, - MAP__FUNCTION, session->cwd, session->cwdlen); - - if (thread == NULL || map == NULL) + MAP__FUNCTION); + if (map == NULL) goto out_problem; thread__insert_map(thread, map); @@ -552,6 +548,26 @@ int event__process_task(event_t *self, struct perf_session *session) return 0; } +int event__process(event_t *event, struct perf_session *session) +{ + switch (event->header.type) { + case PERF_RECORD_COMM: + event__process_comm(event, session); + break; + case PERF_RECORD_MMAP: + event__process_mmap(event, session); + break; + case PERF_RECORD_FORK: + case PERF_RECORD_EXIT: + event__process_task(event, session); + break; + default: + break; + } + + return 0; +} + void thread__find_addr_map(struct thread *self, struct perf_session *session, u8 cpumode, enum map_type type, pid_t pid, u64 addr, @@ -641,27 +657,49 @@ void thread__find_addr_location(struct thread *self, al->sym = NULL; } -static void dso__calc_col_width(struct dso *self) +static void dso__calc_col_width(struct dso *self, struct hists *hists) { if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep && (!symbol_conf.dso_list || strlist__has_entry(symbol_conf.dso_list, self->name))) { - u16 slen = self->short_name_len; - if (verbose) - slen = self->long_name_len; - if (dsos__col_width < slen) - dsos__col_width = slen; + u16 slen = dso__name_len(self); + hists__new_col_len(hists, HISTC_DSO, slen); } self->slen_calculated = 1; } int event__preprocess_sample(const event_t *self, struct perf_session *session, - struct addr_location *al, symbol_filter_t filter) + struct addr_location *al, struct sample_data *data, + symbol_filter_t filter) { u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = perf_session__findnew(session, self->ip.pid); + struct thread *thread; + event__parse_sample(self, session->sample_type, data); + + dump_printf("(IP, %d): %d/%d: %#Lx period: %Ld cpu:%d\n", + self->header.misc, data->pid, data->tid, data->ip, + data->period, data->cpu); + + if (session->sample_type & PERF_SAMPLE_CALLCHAIN) { + unsigned int i; + + dump_printf("... chain: nr:%Lu\n", data->callchain->nr); + + if (!ip_callchain__valid(data->callchain, self)) { + pr_debug("call-chain problem with event, " + "skipping it.\n"); + goto out_filtered; + } + + if (dump_trace) { + for (i = 0; i < data->callchain->nr; i++) + dump_printf("..... %2d: %016Lx\n", + i, data->callchain->ips[i]); + } + } + thread = perf_session__findnew(session, self->ip.pid); if (thread == NULL) return -1; @@ -687,6 +725,7 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session, al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); al->sym = NULL; + al->cpu = data->cpu; if (al->map) { if (symbol_conf.dso_list && @@ -703,16 +742,17 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session, * sampled. */ if (!sort_dso.elide && !al->map->dso->slen_calculated) - dso__calc_col_width(al->map->dso); + dso__calc_col_width(al->map->dso, &session->hists); al->sym = map__find_symbol(al->map, al->addr, filter); } else { const unsigned int unresolved_col_width = BITS_PER_LONG / 4; - if (dsos__col_width < unresolved_col_width && + if (hists__col_len(&session->hists, HISTC_DSO) < unresolved_col_width && !symbol_conf.col_width_list_str && !symbol_conf.field_sep && !symbol_conf.dso_list) - dsos__col_width = unresolved_col_width; + hists__set_col_len(&session->hists, HISTC_DSO, + unresolved_col_width); } if (symbol_conf.sym_list && al->sym && @@ -726,9 +766,9 @@ out_filtered: return 0; } -int event__parse_sample(event_t *event, u64 type, struct sample_data *data) +int event__parse_sample(const event_t *event, u64 type, struct sample_data *data) { - u64 *array = event->sample.array; + const u64 *array = event->sample.array; if (type & PERF_SAMPLE_IP) { data->ip = event->ip.ip; @@ -767,7 +807,8 @@ int event__parse_sample(event_t *event, u64 type, struct sample_data *data) u32 *p = (u32 *)array; data->cpu = *p; array++; - } + } else + data->cpu = -1; if (type & PERF_SAMPLE_PERIOD) { data->period = *array; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 8577085db06..8e790dae702 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -154,11 +154,13 @@ int event__process_comm(event_t *self, struct perf_session *session); int event__process_lost(event_t *self, struct perf_session *session); int event__process_mmap(event_t *self, struct perf_session *session); int event__process_task(event_t *self, struct perf_session *session); +int event__process(event_t *event, struct perf_session *session); struct addr_location; int event__preprocess_sample(const event_t *self, struct perf_session *session, - struct addr_location *al, symbol_filter_t filter); -int event__parse_sample(event_t *event, u64 type, struct sample_data *data); + struct addr_location *al, struct sample_data *data, + symbol_filter_t filter); +int event__parse_sample(const event_t *event, u64 type, struct sample_data *data); extern const char *event__name[]; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 1f62435f96c..d7e67b167ea 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -16,6 +16,8 @@ #include "symbol.h" #include "debug.h" +static bool no_buildid_cache = false; + /* * Create new perf.data header attribute: */ @@ -385,8 +387,7 @@ static int perf_session__cache_build_ids(struct perf_session *self) int ret; char debugdir[PATH_MAX]; - snprintf(debugdir, sizeof(debugdir), "%s/%s", getenv("HOME"), - DEBUG_CACHE_DIR); + snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir); if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) return -1; @@ -471,7 +472,8 @@ static int perf_header__adds_write(struct perf_header *self, int fd) } buildid_sec->size = lseek(fd, 0, SEEK_CUR) - buildid_sec->offset; - perf_session__cache_build_ids(session); + if (!no_buildid_cache) + perf_session__cache_build_ids(session); } lseek(fd, sec_start, SEEK_SET); @@ -1190,3 +1192,8 @@ int event__process_build_id(event_t *self, session); return 0; } + +void disable_buildid_cache(void) +{ + no_buildid_cache = true; +} diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 784ee0bdda7..e7263d49bcf 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -5,11 +5,61 @@ #include "sort.h" #include <math.h> +enum hist_filter { + HIST_FILTER__DSO, + HIST_FILTER__THREAD, + HIST_FILTER__PARENT, +}; + struct callchain_param callchain_param = { .mode = CHAIN_GRAPH_REL, .min_percent = 0.5 }; +u16 hists__col_len(struct hists *self, enum hist_column col) +{ + return self->col_len[col]; +} + +void hists__set_col_len(struct hists *self, enum hist_column col, u16 len) +{ + self->col_len[col] = len; +} + +bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len) +{ + if (len > hists__col_len(self, col)) { + hists__set_col_len(self, col, len); + return true; + } + return false; +} + +static void hists__reset_col_len(struct hists *self) +{ + enum hist_column col; + + for (col = 0; col < HISTC_NR_COLS; ++col) + hists__set_col_len(self, col, 0); +} + +static void hists__calc_col_len(struct hists *self, struct hist_entry *h) +{ + u16 len; + + if (h->ms.sym) + hists__new_col_len(self, HISTC_SYMBOL, h->ms.sym->namelen); + + len = thread__comm_len(h->thread); + if (hists__new_col_len(self, HISTC_COMM, len)) + hists__set_col_len(self, HISTC_THREAD, len + 6); + + if (h->ms.map) { + len = dso__name_len(h->ms.map->dso); + hists__new_col_len(self, HISTC_DSO, len); + } +} + static void hist_entry__add_cpumode_period(struct hist_entry *self, unsigned int cpumode, u64 period) { @@ -43,6 +93,8 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) if (self != NULL) { *self = *template; self->nr_events = 1; + if (self->ms.map) + self->ms.map->referenced = true; if (symbol_conf.use_callchain) callchain_init(self->callchain); } @@ -50,11 +102,19 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) return self; } -static void hists__inc_nr_entries(struct hists *self, struct hist_entry *entry) +static void hists__inc_nr_entries(struct hists *self, struct hist_entry *h) { - if (entry->ms.sym && self->max_sym_namelen < entry->ms.sym->namelen) - self->max_sym_namelen = entry->ms.sym->namelen; - ++self->nr_entries; + if (!h->filtered) { + hists__calc_col_len(self, h); + ++self->nr_entries; + } +} + +static u8 symbol__parent_filter(const struct symbol *parent) +{ + if (symbol_conf.exclude_other && parent == NULL) + return 1 << HIST_FILTER__PARENT; + return 0; } struct hist_entry *__hists__add_entry(struct hists *self, @@ -70,10 +130,12 @@ struct hist_entry *__hists__add_entry(struct hists *self, .map = al->map, .sym = al->sym, }, + .cpu = al->cpu, .ip = al->addr, .level = al->level, .period = period, .parent = sym_parent, + .filtered = symbol__parent_filter(sym_parent), }; int cmp; @@ -191,7 +253,7 @@ void hists__collapse_resort(struct hists *self) tmp = RB_ROOT; next = rb_first(&self->entries); self->nr_entries = 0; - self->max_sym_namelen = 0; + hists__reset_col_len(self); while (next) { n = rb_entry(next, struct hist_entry, rb_node); @@ -248,7 +310,7 @@ void hists__output_resort(struct hists *self) next = rb_first(&self->entries); self->nr_entries = 0; - self->max_sym_namelen = 0; + hists__reset_col_len(self); while (next) { n = rb_entry(next, struct hist_entry, rb_node); @@ -515,8 +577,9 @@ static size_t hist_entry_callchain__fprintf(FILE *fp, struct hist_entry *self, } int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, - struct hists *pair_hists, bool show_displacement, - long displacement, bool color, u64 session_total) + struct hists *hists, struct hists *pair_hists, + bool show_displacement, long displacement, + bool color, u64 session_total) { struct sort_entry *se; u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us; @@ -620,29 +683,25 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, ret += snprintf(s + ret, size - ret, "%s", sep ?: " "); ret += se->se_snprintf(self, s + ret, size - ret, - se->se_width ? *se->se_width : 0); + hists__col_len(hists, se->se_width_idx)); } return ret; } -int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists, - bool show_displacement, long displacement, FILE *fp, - u64 session_total) +int hist_entry__fprintf(struct hist_entry *self, struct hists *hists, + struct hists *pair_hists, bool show_displacement, + long displacement, FILE *fp, u64 session_total) { char bf[512]; - int ret; - - ret = hist_entry__snprintf(self, bf, sizeof(bf), pair_hists, - show_displacement, displacement, - true, session_total); - if (!ret) - return 0; - + hist_entry__snprintf(self, bf, sizeof(bf), hists, pair_hists, + show_displacement, displacement, + true, session_total); return fprintf(fp, "%s\n", bf); } -static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp, +static size_t hist_entry__fprintf_callchain(struct hist_entry *self, + struct hists *hists, FILE *fp, u64 session_total) { int left_margin = 0; @@ -650,7 +709,7 @@ static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp, if (sort__first_dimension == SORT_COMM) { struct sort_entry *se = list_first_entry(&hist_entry__sort_list, typeof(*se), list); - left_margin = se->se_width ? *se->se_width : 0; + left_margin = hists__col_len(hists, se->se_width_idx); left_margin -= thread__comm_len(self->thread); } @@ -721,17 +780,17 @@ size_t hists__fprintf(struct hists *self, struct hists *pair, continue; } width = strlen(se->se_header); - if (se->se_width) { - if (symbol_conf.col_width_list_str) { - if (col_width) { - *se->se_width = atoi(col_width); - col_width = strchr(col_width, ','); - if (col_width) - ++col_width; - } + if (symbol_conf.col_width_list_str) { + if (col_width) { + hists__set_col_len(self, se->se_width_idx, + atoi(col_width)); + col_width = strchr(col_width, ','); + if (col_width) + ++col_width; } - width = *se->se_width = max(*se->se_width, width); } + if (!hists__new_col_len(self, se->se_width_idx, width)) + width = hists__col_len(self, se->se_width_idx); fprintf(fp, " %*s", width, se->se_header); } fprintf(fp, "\n"); @@ -754,9 +813,8 @@ size_t hists__fprintf(struct hists *self, struct hists *pair, continue; fprintf(fp, " "); - if (se->se_width) - width = *se->se_width; - else + width = hists__col_len(self, se->se_width_idx); + if (width == 0) width = strlen(se->se_header); for (i = 0; i < width; i++) fprintf(fp, "."); @@ -767,7 +825,6 @@ size_t hists__fprintf(struct hists *self, struct hists *pair, print_entries: for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - int cnt; if (show_displacement) { if (h->pair != NULL) @@ -777,17 +834,12 @@ print_entries: displacement = 0; ++position; } - cnt = hist_entry__fprintf(h, pair, show_displacement, - displacement, fp, self->stats.total_period); - /* Ignore those that didn't match the parent filter */ - if (!cnt) - continue; - - ret += cnt; + ret += hist_entry__fprintf(h, self, pair, show_displacement, + displacement, fp, self->stats.total_period); if (symbol_conf.use_callchain) - ret += hist_entry__fprintf_callchain(h, fp, self->stats.total_period); - + ret += hist_entry__fprintf_callchain(h, self, fp, + self->stats.total_period); if (h->ms.map == NULL && verbose > 1) { __map_groups__fprintf_maps(&h->thread->mg, MAP__FUNCTION, verbose, fp); @@ -800,10 +852,49 @@ print_entries: return ret; } -enum hist_filter { - HIST_FILTER__DSO, - HIST_FILTER__THREAD, -}; +/* + * See hists__fprintf to match the column widths + */ +unsigned int hists__sort_list_width(struct hists *self) +{ + struct sort_entry *se; + int ret = 9; /* total % */ + + if (symbol_conf.show_cpu_utilization) { + ret += 7; /* count_sys % */ + ret += 6; /* count_us % */ + if (perf_guest) { + ret += 13; /* count_guest_sys % */ + ret += 12; /* count_guest_us % */ + } + } + + if (symbol_conf.show_nr_samples) + ret += 11; + + list_for_each_entry(se, &hist_entry__sort_list, list) + if (!se->elide) + ret += 2 + hists__col_len(self, se->se_width_idx); + + return ret; +} + +static void hists__remove_entry_filter(struct hists *self, struct hist_entry *h, + enum hist_filter filter) +{ + h->filtered &= ~(1 << filter); + if (h->filtered) + return; + + ++self->nr_entries; + if (h->ms.unfolded) + self->nr_entries += h->nr_rows; + h->row_offset = 0; + self->stats.total_period += h->period; + self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events; + + hists__calc_col_len(self, h); +} void hists__filter_by_dso(struct hists *self, const struct dso *dso) { @@ -811,7 +902,7 @@ void hists__filter_by_dso(struct hists *self, const struct dso *dso) self->nr_entries = self->stats.total_period = 0; self->stats.nr_events[PERF_RECORD_SAMPLE] = 0; - self->max_sym_namelen = 0; + hists__reset_col_len(self); for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); @@ -824,15 +915,7 @@ void hists__filter_by_dso(struct hists *self, const struct dso *dso) continue; } - h->filtered &= ~(1 << HIST_FILTER__DSO); - if (!h->filtered) { - ++self->nr_entries; - self->stats.total_period += h->period; - self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events; - if (h->ms.sym && - self->max_sym_namelen < h->ms.sym->namelen) - self->max_sym_namelen = h->ms.sym->namelen; - } + hists__remove_entry_filter(self, h, HIST_FILTER__DSO); } } @@ -842,7 +925,7 @@ void hists__filter_by_thread(struct hists *self, const struct thread *thread) self->nr_entries = self->stats.total_period = 0; self->stats.nr_events[PERF_RECORD_SAMPLE] = 0; - self->max_sym_namelen = 0; + hists__reset_col_len(self); for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); @@ -851,15 +934,8 @@ void hists__filter_by_thread(struct hists *self, const struct thread *thread) h->filtered |= (1 << HIST_FILTER__THREAD); continue; } - h->filtered &= ~(1 << HIST_FILTER__THREAD); - if (!h->filtered) { - ++self->nr_entries; - self->stats.total_period += h->period; - self->stats.nr_events[PERF_RECORD_SAMPLE] += h->nr_events; - if (h->ms.sym && - self->max_sym_namelen < h->ms.sym->namelen) - self->max_sym_namelen = h->ms.sym->namelen; - } + + hists__remove_entry_filter(self, h, HIST_FILTER__THREAD); } } @@ -1052,7 +1128,7 @@ fallback: dso, dso->long_name, sym, sym->name); snprintf(command, sizeof(command), - "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s|grep -v %s|expand", + "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS -C %s|grep -v %s|expand", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), filename, filename); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 83fa33a7b38..65a48db46a2 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -56,6 +56,16 @@ struct events_stats { u32 nr_unknown_events; }; +enum hist_column { + HISTC_SYMBOL, + HISTC_DSO, + HISTC_THREAD, + HISTC_COMM, + HISTC_PARENT, + HISTC_CPU, + HISTC_NR_COLS, /* Last entry */ +}; + struct hists { struct rb_node rb_node; struct rb_root entries; @@ -64,7 +74,7 @@ struct hists { u64 config; u64 event_stream; u32 type; - u32 max_sym_namelen; + u16 col_len[HISTC_NR_COLS]; }; struct hist_entry *__hists__add_entry(struct hists *self, @@ -72,12 +82,13 @@ struct hist_entry *__hists__add_entry(struct hists *self, struct symbol *parent, u64 period); extern int64_t hist_entry__cmp(struct hist_entry *, struct hist_entry *); extern int64_t hist_entry__collapse(struct hist_entry *, struct hist_entry *); -int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists, - bool show_displacement, long displacement, FILE *fp, - u64 total); +int hist_entry__fprintf(struct hist_entry *self, struct hists *hists, + struct hists *pair_hists, bool show_displacement, + long displacement, FILE *fp, u64 total); int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size, - struct hists *pair_hists, bool show_displacement, - long displacement, bool color, u64 total); + struct hists *hists, struct hists *pair_hists, + bool show_displacement, long displacement, + bool color, u64 total); void hist_entry__free(struct hist_entry *); void hists__output_resort(struct hists *self); @@ -95,6 +106,10 @@ int hist_entry__annotate(struct hist_entry *self, struct list_head *head); void hists__filter_by_dso(struct hists *self, const struct dso *dso); void hists__filter_by_thread(struct hists *self, const struct thread *thread); +u16 hists__col_len(struct hists *self, enum hist_column col); +void hists__set_col_len(struct hists *self, enum hist_column col, u16 len); +bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len); + #ifdef NO_NEWT_SUPPORT static inline int hists__browse(struct hists *self __used, const char *helpline __used, @@ -126,4 +141,7 @@ int hist_entry__tui_annotate(struct hist_entry *self); int hists__tui_browse_tree(struct rb_root *self, const char *help); #endif + +unsigned int hists__sort_list_width(struct hists *self); + #endif /* __PERF_HIST_H */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index e672f2fef65..3a7eb6ec0ee 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -17,16 +17,6 @@ static inline int is_anon_memory(const char *filename) return strcmp(filename, "//anon") == 0; } -static int strcommon(const char *pathname, char *cwd, int cwdlen) -{ - int n = 0; - - while (n < cwdlen && pathname[n] == cwd[n]) - ++n; - - return n; -} - void map__init(struct map *self, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso) { @@ -39,11 +29,12 @@ void map__init(struct map *self, enum map_type type, self->unmap_ip = map__unmap_ip; RB_CLEAR_NODE(&self->rb_node); self->groups = NULL; + self->referenced = false; } struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, char *filename, - enum map_type type, char *cwd, int cwdlen) + enum map_type type) { struct map *self = malloc(sizeof(*self)); @@ -52,16 +43,6 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, struct dso *dso; int anon; - if (cwd) { - int n = strcommon(filename, cwd, cwdlen); - - if (n == cwdlen) { - snprintf(newfilename, sizeof(newfilename), - ".%s", filename + n); - filename = newfilename; - } - } - anon = is_anon_memory(filename); if (anon) { @@ -248,6 +229,39 @@ void map_groups__init(struct map_groups *self) self->machine = NULL; } +static void maps__delete(struct rb_root *self) +{ + struct rb_node *next = rb_first(self); + + while (next) { + struct map *pos = rb_entry(next, struct map, rb_node); + + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, self); + map__delete(pos); + } +} + +static void maps__delete_removed(struct list_head *self) +{ + struct map *pos, *n; + + list_for_each_entry_safe(pos, n, self, node) { + list_del(&pos->node); + map__delete(pos); + } +} + +void map_groups__exit(struct map_groups *self) +{ + int i; + + for (i = 0; i < MAP__NR_TYPES; ++i) { + maps__delete(&self->maps[i]); + maps__delete_removed(&self->removed_maps[i]); + } +} + void map_groups__flush(struct map_groups *self) { int type; @@ -374,6 +388,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, { struct rb_root *root = &self->maps[map->type]; struct rb_node *next = rb_first(root); + int err = 0; while (next) { struct map *pos = rb_entry(next, struct map, rb_node); @@ -390,20 +405,16 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, rb_erase(&pos->rb_node, root); /* - * We may have references to this map, for instance in some - * hist_entry instances, so just move them to a separate - * list. - */ - list_add_tail(&pos->node, &self->removed_maps[map->type]); - /* * Now check if we need to create new maps for areas not * overlapped by the new map: */ if (map->start > pos->start) { struct map *before = map__clone(pos); - if (before == NULL) - return -ENOMEM; + if (before == NULL) { + err = -ENOMEM; + goto move_map; + } before->end = map->start - 1; map_groups__insert(self, before); @@ -414,14 +425,27 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map, if (map->end < pos->end) { struct map *after = map__clone(pos); - if (after == NULL) - return -ENOMEM; + if (after == NULL) { + err = -ENOMEM; + goto move_map; + } after->start = map->end + 1; map_groups__insert(self, after); if (verbose >= 2) map__fprintf(after, fp); } +move_map: + /* + * If we have references, just move them to a separate list. + */ + if (pos->referenced) + list_add_tail(&pos->node, &self->removed_maps[map->type]); + else + map__delete(pos); + + if (err) + return err; } return 0; @@ -493,6 +517,11 @@ void maps__insert(struct rb_root *maps, struct map *map) rb_insert_color(&map->rb_node, maps); } +void maps__remove(struct rb_root *self, struct map *map) +{ + rb_erase(&map->rb_node, self); +} + struct map *maps__find(struct rb_root *maps, u64 ip) { struct rb_node **p = &maps->rb_node; @@ -526,6 +555,31 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid) return self->root_dir == NULL ? -ENOMEM : 0; } +static void dsos__delete(struct list_head *self) +{ + struct dso *pos, *n; + + list_for_each_entry_safe(pos, n, self, node) { + list_del(&pos->node); + dso__delete(pos); + } +} + +void machine__exit(struct machine *self) +{ + map_groups__exit(&self->kmaps); + dsos__delete(&self->user_dsos); + dsos__delete(&self->kernel_dsos); + free(self->root_dir); + self->root_dir = NULL; +} + +void machine__delete(struct machine *self) +{ + machine__exit(self); + free(self); +} + struct machine *machines__add(struct rb_root *self, pid_t pid, const char *root_dir) { diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index f3913451282..78575796d5f 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -29,7 +29,8 @@ struct map { }; u64 start; u64 end; - enum map_type type; + u8 /* enum map_type */ type; + bool referenced; u32 priv; u64 pgoff; @@ -106,7 +107,7 @@ void map__init(struct map *self, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct list_head *dsos__list, u64 start, u64 len, u64 pgoff, u32 pid, char *filename, - enum map_type type, char *cwd, int cwdlen); + enum map_type type); void map__delete(struct map *self); struct map *map__clone(struct map *self); int map__overlap(struct map *l, struct map *r); @@ -125,8 +126,10 @@ void map__reloc_vmlinux(struct map *self); size_t __map_groups__fprintf_maps(struct map_groups *self, enum map_type type, int verbose, FILE *fp); void maps__insert(struct rb_root *maps, struct map *map); +void maps__remove(struct rb_root *self, struct map *map); struct map *maps__find(struct rb_root *maps, u64 addr); void map_groups__init(struct map_groups *self); +void map_groups__exit(struct map_groups *self); int map_groups__clone(struct map_groups *self, struct map_groups *parent, enum map_type type); size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp); @@ -142,6 +145,8 @@ struct machine *machines__find(struct rb_root *self, pid_t pid); struct machine *machines__findnew(struct rb_root *self, pid_t pid); char *machine__mmap_name(struct machine *self, char *bf, size_t size); int machine__init(struct machine *self, const char *root_dir, pid_t pid); +void machine__exit(struct machine *self); +void machine__delete(struct machine *self); /* * Default guest kernel is defined by parameter --guestkallsyms @@ -163,6 +168,11 @@ static inline void map_groups__insert(struct map_groups *self, struct map *map) map->groups = self; } +static inline void map_groups__remove(struct map_groups *self, struct map *map) +{ + maps__remove(&self->maps[map->type], map); +} + static inline struct map *map_groups__find(struct map_groups *self, enum map_type type, u64 addr) { diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c index 7537ca15900..91de99b5844 100644 --- a/tools/perf/util/newt.c +++ b/tools/perf/util/newt.c @@ -11,6 +11,7 @@ #define HAVE_LONG_LONG __GLIBC_HAVE_LONG_LONG #endif #include <slang.h> +#include <signal.h> #include <stdlib.h> #include <newt.h> #include <sys/ttydefaults.h> @@ -278,9 +279,48 @@ struct ui_browser { void *first_visible_entry, *entries; u16 top, left, width, height; void *priv; + unsigned int (*refresh_entries)(struct ui_browser *self); + void (*seek)(struct ui_browser *self, + off_t offset, int whence); u32 nr_entries; }; +static void ui_browser__list_head_seek(struct ui_browser *self, + off_t offset, int whence) +{ + struct list_head *head = self->entries; + struct list_head *pos; + + switch (whence) { + case SEEK_SET: + pos = head->next; + break; + case SEEK_CUR: + pos = self->first_visible_entry; + break; + case SEEK_END: + pos = head->prev; + break; + default: + return; + } + + if (offset > 0) { + while (offset-- != 0) + pos = pos->next; + } else { + while (offset++ != 0) + pos = pos->prev; + } + + self->first_visible_entry = pos; +} + +static bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row) +{ + return (self->first_visible_entry_idx + row) == self->index; +} + static void ui_browser__refresh_dimensions(struct ui_browser *self) { int cols, rows; @@ -297,8 +337,36 @@ static void ui_browser__refresh_dimensions(struct ui_browser *self) static void ui_browser__reset_index(struct ui_browser *self) { - self->index = self->first_visible_entry_idx = 0; - self->first_visible_entry = NULL; + self->index = self->first_visible_entry_idx = 0; + self->seek(self, 0, SEEK_SET); +} + +static int ui_browser__show(struct ui_browser *self, const char *title) +{ + if (self->form != NULL) { + newtFormDestroy(self->form); + newtPopWindow(); + } + ui_browser__refresh_dimensions(self); + newtCenteredWindow(self->width, self->height, title); + self->form = newt_form__new(); + if (self->form == NULL) + return -1; + + self->sb = newtVerticalScrollbar(self->width, 0, self->height, + HE_COLORSET_NORMAL, + HE_COLORSET_SELECTED); + if (self->sb == NULL) + return -1; + + newtFormAddHotKey(self->form, NEWT_KEY_UP); + newtFormAddHotKey(self->form, NEWT_KEY_DOWN); + newtFormAddHotKey(self->form, NEWT_KEY_PGUP); + newtFormAddHotKey(self->form, NEWT_KEY_PGDN); + newtFormAddHotKey(self->form, NEWT_KEY_HOME); + newtFormAddHotKey(self->form, NEWT_KEY_END); + newtFormAddComponent(self->form, self->sb); + return 0; } static int objdump_line__show(struct objdump_line *self, struct list_head *head, @@ -352,26 +420,10 @@ static int objdump_line__show(struct objdump_line *self, struct list_head *head, static int ui_browser__refresh_entries(struct ui_browser *self) { - struct objdump_line *pos; - struct list_head *head = self->entries; - struct hist_entry *he = self->priv; - int row = 0; - int len = he->ms.sym->end - he->ms.sym->start; - - if (self->first_visible_entry == NULL || self->first_visible_entry == self->entries) - self->first_visible_entry = head->next; - - pos = list_entry(self->first_visible_entry, struct objdump_line, node); - - list_for_each_entry_from(pos, head, node) { - bool current_entry = (self->first_visible_entry_idx + row) == self->index; - SLsmg_gotorc(self->top + row, self->left); - objdump_line__show(pos, head, self->width, - he, len, current_entry); - if (++row == self->height) - break; - } + int row; + newtScrollbarSet(self->sb, self->index, self->nr_entries - 1); + row = self->refresh_entries(self); SLsmg_set_color(HE_COLORSET_NORMAL); SLsmg_fill_region(self->top + row, self->left, self->height - row, self->width, ' '); @@ -379,42 +431,13 @@ static int ui_browser__refresh_entries(struct ui_browser *self) return 0; } -static int ui_browser__run(struct ui_browser *self, const char *title, - struct newtExitStruct *es) +static int ui_browser__run(struct ui_browser *self, struct newtExitStruct *es) { - if (self->form) { - newtFormDestroy(self->form); - newtPopWindow(); - } - - ui_browser__refresh_dimensions(self); - newtCenteredWindow(self->width + 2, self->height, title); - self->form = newt_form__new(); - if (self->form == NULL) - return -1; - - self->sb = newtVerticalScrollbar(self->width + 1, 0, self->height, - HE_COLORSET_NORMAL, - HE_COLORSET_SELECTED); - if (self->sb == NULL) - return -1; - - newtFormAddHotKey(self->form, NEWT_KEY_UP); - newtFormAddHotKey(self->form, NEWT_KEY_DOWN); - newtFormAddHotKey(self->form, NEWT_KEY_PGUP); - newtFormAddHotKey(self->form, NEWT_KEY_PGDN); - newtFormAddHotKey(self->form, ' '); - newtFormAddHotKey(self->form, NEWT_KEY_HOME); - newtFormAddHotKey(self->form, NEWT_KEY_END); - newtFormAddHotKey(self->form, NEWT_KEY_TAB); - newtFormAddHotKey(self->form, NEWT_KEY_RIGHT); - if (ui_browser__refresh_entries(self) < 0) return -1; - newtFormAddComponent(self->form, self->sb); while (1) { - unsigned int offset; + off_t offset; newtFormRun(self->form, es); @@ -428,9 +451,8 @@ static int ui_browser__run(struct ui_browser *self, const char *title, break; ++self->index; if (self->index == self->first_visible_entry_idx + self->height) { - struct list_head *pos = self->first_visible_entry; ++self->first_visible_entry_idx; - self->first_visible_entry = pos->next; + self->seek(self, +1, SEEK_CUR); } break; case NEWT_KEY_UP: @@ -438,9 +460,8 @@ static int ui_browser__run(struct ui_browser *self, const char *title, break; --self->index; if (self->index < self->first_visible_entry_idx) { - struct list_head *pos = self->first_visible_entry; --self->first_visible_entry_idx; - self->first_visible_entry = pos->prev; + self->seek(self, -1, SEEK_CUR); } break; case NEWT_KEY_PGDN: @@ -453,12 +474,7 @@ static int ui_browser__run(struct ui_browser *self, const char *title, offset = self->nr_entries - 1 - self->index; self->index += offset; self->first_visible_entry_idx += offset; - - while (offset--) { - struct list_head *pos = self->first_visible_entry; - self->first_visible_entry = pos->next; - } - + self->seek(self, +offset, SEEK_CUR); break; case NEWT_KEY_PGUP: if (self->first_visible_entry_idx == 0) @@ -471,36 +487,22 @@ static int ui_browser__run(struct ui_browser *self, const char *title, self->index -= offset; self->first_visible_entry_idx -= offset; - - while (offset--) { - struct list_head *pos = self->first_visible_entry; - self->first_visible_entry = pos->prev; - } + self->seek(self, -offset, SEEK_CUR); break; case NEWT_KEY_HOME: ui_browser__reset_index(self); break; - case NEWT_KEY_END: { - struct list_head *head = self->entries; + case NEWT_KEY_END: offset = self->height - 1; + if (offset >= self->nr_entries) + offset = self->nr_entries - 1; - if (offset > self->nr_entries) - offset = self->nr_entries; - - self->index = self->first_visible_entry_idx = self->nr_entries - 1 - offset; - self->first_visible_entry = head->prev; - while (offset-- != 0) { - struct list_head *pos = self->first_visible_entry; - self->first_visible_entry = pos->prev; - } - } + self->index = self->nr_entries - 1; + self->first_visible_entry_idx = self->index - offset; + self->seek(self, -offset, SEEK_END); break; - case NEWT_KEY_RIGHT: - case NEWT_KEY_LEFT: - case NEWT_KEY_TAB: - return es->u.key; default: - continue; + return es->u.key; } if (ui_browser__refresh_entries(self) < 0) return -1; @@ -508,38 +510,6 @@ static int ui_browser__run(struct ui_browser *self, const char *title, return 0; } -/* - * When debugging newt problems it was useful to be able to "unroll" - * the calls to newtCheckBoxTreeAdd{Array,Item}, so that we can generate - * a source file with the sequence of calls to these methods, to then - * tweak the arrays to get the intended results, so I'm keeping this code - * here, may be useful again in the future. - */ -#undef NEWT_DEBUG - -static void newt_checkbox_tree__add(newtComponent tree, const char *str, - void *priv, int *indexes) -{ -#ifdef NEWT_DEBUG - /* Print the newtCheckboxTreeAddArray to tinker with its index arrays */ - int i = 0, len = 40 - strlen(str); - - fprintf(stderr, - "\tnewtCheckboxTreeAddItem(tree, %*.*s\"%s\", (void *)%p, 0, ", - len, len, " ", str, priv); - while (indexes[i] != NEWT_ARG_LAST) { - if (indexes[i] != NEWT_ARG_APPEND) - fprintf(stderr, " %d,", indexes[i]); - else - fprintf(stderr, " %s,", "NEWT_ARG_APPEND"); - ++i; - } - fprintf(stderr, " %s", " NEWT_ARG_LAST);\n"); - fflush(stderr); -#endif - newtCheckboxTreeAddArray(tree, str, priv, 0, indexes); -} - static char *callchain_list__sym_name(struct callchain_list *self, char *bf, size_t bfsize) { @@ -550,144 +520,29 @@ static char *callchain_list__sym_name(struct callchain_list *self, return bf; } -static void __callchain__append_graph_browser(struct callchain_node *self, - newtComponent tree, u64 total, - int *indexes, int depth) +static unsigned int hist_entry__annotate_browser_refresh(struct ui_browser *self) { - struct rb_node *node; - u64 new_total, remaining; - int idx = 0; - - if (callchain_param.mode == CHAIN_GRAPH_REL) - new_total = self->children_hit; - else - new_total = total; - - remaining = new_total; - node = rb_first(&self->rb_root); - while (node) { - struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); - struct rb_node *next = rb_next(node); - u64 cumul = cumul_hits(child); - struct callchain_list *chain; - int first = true, printed = 0; - int chain_idx = -1; - remaining -= cumul; - - indexes[depth] = NEWT_ARG_APPEND; - indexes[depth + 1] = NEWT_ARG_LAST; - - list_for_each_entry(chain, &child->val, list) { - char ipstr[BITS_PER_LONG / 4 + 1], - *alloc_str = NULL; - const char *str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); - - if (first) { - double percent = cumul * 100.0 / new_total; - - first = false; - if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) - str = "Not enough memory!"; - else - str = alloc_str; - } else { - indexes[depth] = idx; - indexes[depth + 1] = NEWT_ARG_APPEND; - indexes[depth + 2] = NEWT_ARG_LAST; - ++chain_idx; - } - newt_checkbox_tree__add(tree, str, &chain->ms, indexes); - free(alloc_str); - ++printed; - } - - indexes[depth] = idx; - if (chain_idx != -1) - indexes[depth + 1] = chain_idx; - if (printed != 0) - ++idx; - __callchain__append_graph_browser(child, tree, new_total, indexes, - depth + (chain_idx != -1 ? 2 : 1)); - node = next; - } -} - -static void callchain__append_graph_browser(struct callchain_node *self, - newtComponent tree, u64 total, - int *indexes, int parent_idx) -{ - struct callchain_list *chain; - int i = 0; - - indexes[1] = NEWT_ARG_APPEND; - indexes[2] = NEWT_ARG_LAST; - - list_for_each_entry(chain, &self->val, list) { - char ipstr[BITS_PER_LONG / 4 + 1], *str; - - if (chain->ip >= PERF_CONTEXT_MAX) - continue; - - if (!i++ && sort__first_dimension == SORT_SYM) - continue; + struct objdump_line *pos; + struct list_head *head = self->entries; + struct hist_entry *he = self->priv; + int row = 0; + int len = he->ms.sym->end - he->ms.sym->start; - str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); - newt_checkbox_tree__add(tree, str, &chain->ms, indexes); - } + if (self->first_visible_entry == NULL || self->first_visible_entry == self->entries) + self->first_visible_entry = head->next; - indexes[1] = parent_idx; - indexes[2] = NEWT_ARG_APPEND; - indexes[3] = NEWT_ARG_LAST; - __callchain__append_graph_browser(self, tree, total, indexes, 2); -} + pos = list_entry(self->first_visible_entry, struct objdump_line, node); -static void hist_entry__append_callchain_browser(struct hist_entry *self, - newtComponent tree, u64 total, int parent_idx) -{ - struct rb_node *rb_node; - int indexes[1024] = { [0] = parent_idx, }; - int idx = 0; - struct callchain_node *chain; - - rb_node = rb_first(&self->sorted_chain); - while (rb_node) { - chain = rb_entry(rb_node, struct callchain_node, rb_node); - switch (callchain_param.mode) { - case CHAIN_FLAT: - break; - case CHAIN_GRAPH_ABS: /* falldown */ - case CHAIN_GRAPH_REL: - callchain__append_graph_browser(chain, tree, total, indexes, idx++); - break; - case CHAIN_NONE: - default: + list_for_each_entry_from(pos, head, node) { + bool current_entry = ui_browser__is_current_entry(self, row); + SLsmg_gotorc(self->top + row, self->left); + objdump_line__show(pos, head, self->width, + he, len, current_entry); + if (++row == self->height) break; - } - rb_node = rb_next(rb_node); } -} - -static size_t hist_entry__append_browser(struct hist_entry *self, - newtComponent tree, u64 total) -{ - char s[256]; - size_t ret; - - if (symbol_conf.exclude_other && !self->parent) - return 0; - ret = hist_entry__snprintf(self, s, sizeof(s), NULL, - false, 0, false, total); - if (symbol_conf.use_callchain) { - int indexes[2]; - - indexes[0] = NEWT_ARG_APPEND; - indexes[1] = NEWT_ARG_LAST; - newt_checkbox_tree__add(tree, s, &self->ms, indexes); - } else - newtListboxAppendEntry(tree, s, &self->ms); - - return ret; + return row; } int hist_entry__tui_annotate(struct hist_entry *self) @@ -712,7 +567,9 @@ int hist_entry__tui_annotate(struct hist_entry *self) ui_helpline__push("Press <- or ESC to exit"); memset(&browser, 0, sizeof(browser)); - browser.entries = &head; + browser.entries = &head; + browser.refresh_entries = hist_entry__annotate_browser_refresh; + browser.seek = ui_browser__list_head_seek; browser.priv = self; list_for_each_entry(pos, &head, node) { size_t line_len = strlen(pos->line); @@ -722,7 +579,9 @@ int hist_entry__tui_annotate(struct hist_entry *self) } browser.width += 18; /* Percentage */ - ret = ui_browser__run(&browser, self->ms.sym->name, &es); + ui_browser__show(&browser, self->ms.sym->name); + newtFormAddHotKey(browser.form, ' '); + ret = ui_browser__run(&browser, &es); newtFormDestroy(browser.form); newtPopWindow(); list_for_each_entry_safe(pos, n, &head, node) { @@ -733,157 +592,48 @@ int hist_entry__tui_annotate(struct hist_entry *self) return ret; } -static const void *newt__symbol_tree_get_current(newtComponent self) -{ - if (symbol_conf.use_callchain) - return newtCheckboxTreeGetCurrent(self); - return newtListboxGetCurrent(self); -} - -static void hist_browser__selection(newtComponent self, void *data) -{ - const struct map_symbol **symbol_ptr = data; - *symbol_ptr = newt__symbol_tree_get_current(self); -} - struct hist_browser { - newtComponent form, tree; - const struct map_symbol *selection; + struct ui_browser b; + struct hists *hists; + struct hist_entry *he_selection; + struct map_symbol *selection; }; -static struct hist_browser *hist_browser__new(void) +static void hist_browser__reset(struct hist_browser *self); +static int hist_browser__run(struct hist_browser *self, const char *title, + struct newtExitStruct *es); +static unsigned int hist_browser__refresh_entries(struct ui_browser *self); +static void ui_browser__hists_seek(struct ui_browser *self, + off_t offset, int whence); + +static struct hist_browser *hist_browser__new(struct hists *hists) { - struct hist_browser *self = malloc(sizeof(*self)); + struct hist_browser *self = zalloc(sizeof(*self)); - if (self != NULL) - self->form = NULL; + if (self) { + self->hists = hists; + self->b.refresh_entries = hist_browser__refresh_entries; + self->b.seek = ui_browser__hists_seek; + } return self; } static void hist_browser__delete(struct hist_browser *self) { - newtFormDestroy(self->form); + newtFormDestroy(self->b.form); newtPopWindow(); free(self); } -static int hist_browser__populate(struct hist_browser *self, struct hists *hists, - const char *title) -{ - int max_len = 0, idx, cols, rows; - struct ui_progress *progress; - struct rb_node *nd; - u64 curr_hist = 0; - char seq[] = ".", unit; - char str[256]; - unsigned long nr_events = hists->stats.nr_events[PERF_RECORD_SAMPLE]; - - if (self->form) { - newtFormDestroy(self->form); - newtPopWindow(); - } - - nr_events = convert_unit(nr_events, &unit); - snprintf(str, sizeof(str), "Events: %lu%c ", - nr_events, unit); - newtDrawRootText(0, 0, str); - - newtGetScreenSize(NULL, &rows); - - if (symbol_conf.use_callchain) - self->tree = newtCheckboxTreeMulti(0, 0, rows - 5, seq, - NEWT_FLAG_SCROLL); - else - self->tree = newtListbox(0, 0, rows - 5, - (NEWT_FLAG_SCROLL | - NEWT_FLAG_RETURNEXIT)); - - newtComponentAddCallback(self->tree, hist_browser__selection, - &self->selection); - - progress = ui_progress__new("Adding entries to the browser...", - hists->nr_entries); - if (progress == NULL) - return -1; - - idx = 0; - for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) { - struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); - int len; - - if (h->filtered) - continue; - - len = hist_entry__append_browser(h, self->tree, hists->stats.total_period); - if (len > max_len) - max_len = len; - if (symbol_conf.use_callchain) - hist_entry__append_callchain_browser(h, self->tree, - hists->stats.total_period, idx++); - ++curr_hist; - if (curr_hist % 5) - ui_progress__update(progress, curr_hist); - } - - ui_progress__delete(progress); - - newtGetScreenSize(&cols, &rows); - - if (max_len > cols) - max_len = cols - 3; - - if (!symbol_conf.use_callchain) - newtListboxSetWidth(self->tree, max_len); - - newtCenteredWindow(max_len + (symbol_conf.use_callchain ? 5 : 0), - rows - 5, title); - self->form = newt_form__new(); - if (self->form == NULL) - return -1; - - newtFormAddHotKey(self->form, 'A'); - newtFormAddHotKey(self->form, 'a'); - newtFormAddHotKey(self->form, 'D'); - newtFormAddHotKey(self->form, 'd'); - newtFormAddHotKey(self->form, 'T'); - newtFormAddHotKey(self->form, 't'); - newtFormAddHotKey(self->form, '?'); - newtFormAddHotKey(self->form, 'H'); - newtFormAddHotKey(self->form, 'h'); - newtFormAddHotKey(self->form, NEWT_KEY_F1); - newtFormAddHotKey(self->form, NEWT_KEY_RIGHT); - newtFormAddHotKey(self->form, NEWT_KEY_TAB); - newtFormAddHotKey(self->form, NEWT_KEY_UNTAB); - newtFormAddComponents(self->form, self->tree, NULL); - self->selection = newt__symbol_tree_get_current(self->tree); - - return 0; -} - static struct hist_entry *hist_browser__selected_entry(struct hist_browser *self) { - int *indexes; - - if (!symbol_conf.use_callchain) - goto out; - - indexes = newtCheckboxTreeFindItem(self->tree, (void *)self->selection); - if (indexes) { - bool is_hist_entry = indexes[1] == NEWT_ARG_LAST; - free(indexes); - if (is_hist_entry) - goto out; - } - return NULL; -out: - return container_of(self->selection, struct hist_entry, ms); + return self->he_selection; } static struct thread *hist_browser__selected_thread(struct hist_browser *self) { - struct hist_entry *he = hist_browser__selected_entry(self); - return he ? he->thread : NULL; + return self->he_selection->thread; } static int hist_browser__title(char *bf, size_t size, const char *ev_name, @@ -905,7 +655,7 @@ static int hist_browser__title(char *bf, size_t size, const char *ev_name, int hists__browse(struct hists *self, const char *helpline, const char *ev_name) { - struct hist_browser *browser = hist_browser__new(); + struct hist_browser *browser = hist_browser__new(self); struct pstack *fstack; const struct thread *thread_filter = NULL; const struct dso *dso_filter = NULL; @@ -924,8 +674,6 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) hist_browser__title(msg, sizeof(msg), ev_name, dso_filter, thread_filter); - if (hist_browser__populate(browser, self, msg) < 0) - goto out_free_stack; while (1) { const struct thread *thread; @@ -934,7 +682,8 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) int nr_options = 0, choice = 0, i, annotate = -2, zoom_dso = -2, zoom_thread = -2; - newtFormRun(browser->form, &es); + if (hist_browser__run(browser, msg, &es)) + break; thread = hist_browser__selected_thread(browser); dso = browser->selection->map ? browser->selection->map->dso : NULL; @@ -1069,8 +818,7 @@ zoom_out_dso: hists__filter_by_dso(self, dso_filter); hist_browser__title(msg, sizeof(msg), ev_name, dso_filter, thread_filter); - if (hist_browser__populate(browser, self, msg) < 0) - goto out; + hist_browser__reset(browser); } else if (choice == zoom_thread) { zoom_thread: if (thread_filter) { @@ -1088,8 +836,7 @@ zoom_out_thread: hists__filter_by_thread(self, thread_filter); hist_browser__title(msg, sizeof(msg), ev_name, dso_filter, thread_filter); - if (hist_browser__populate(browser, self, msg) < 0) - goto out; + hist_browser__reset(browser); } } out_free_stack: @@ -1145,6 +892,13 @@ static struct newtPercentTreeColors { "blue", "lightgray", }; +static void newt_suspend(void *d __used) +{ + newtSuspend(); + raise(SIGTSTP); + newtResume(); +} + void setup_browser(void) { struct newtPercentTreeColors *c = &defaultPercentTreeColors; @@ -1158,6 +912,7 @@ void setup_browser(void) use_browser = 1; newtInit(); newtCls(); + newtSetSuspendCallback(newt_suspend, NULL); ui_helpline__puts(" "); sltt_set_color(HE_COLORSET_TOP, NULL, c->topColorFg, c->topColorBg); sltt_set_color(HE_COLORSET_MEDIUM, NULL, c->mediumColorFg, c->mediumColorBg); @@ -1176,3 +931,638 @@ void exit_browser(bool wait_for_ok) newtFinished(); } } + +static void hist_browser__refresh_dimensions(struct hist_browser *self) +{ + /* 3 == +/- toggle symbol before actual hist_entry rendering */ + self->b.width = 3 + (hists__sort_list_width(self->hists) + + sizeof("[k]")); +} + +static void hist_browser__reset(struct hist_browser *self) +{ + self->b.nr_entries = self->hists->nr_entries; + hist_browser__refresh_dimensions(self); + ui_browser__reset_index(&self->b); +} + +static char tree__folded_sign(bool unfolded) +{ + return unfolded ? '-' : '+'; +} + +static char map_symbol__folded(const struct map_symbol *self) +{ + return self->has_children ? tree__folded_sign(self->unfolded) : ' '; +} + +static char hist_entry__folded(const struct hist_entry *self) +{ + return map_symbol__folded(&self->ms); +} + +static char callchain_list__folded(const struct callchain_list *self) +{ + return map_symbol__folded(&self->ms); +} + +static bool map_symbol__toggle_fold(struct map_symbol *self) +{ + if (!self->has_children) + return false; + + self->unfolded = !self->unfolded; + return true; +} + +#define LEVEL_OFFSET_STEP 3 + +static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self, + struct callchain_node *chain_node, + u64 total, int level, + unsigned short row, + off_t *row_offset, + bool *is_current_entry) +{ + struct rb_node *node; + int first_row = row, width, offset = level * LEVEL_OFFSET_STEP; + u64 new_total, remaining; + + if (callchain_param.mode == CHAIN_GRAPH_REL) + new_total = chain_node->children_hit; + else + new_total = total; + + remaining = new_total; + node = rb_first(&chain_node->rb_root); + while (node) { + struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); + struct rb_node *next = rb_next(node); + u64 cumul = cumul_hits(child); + struct callchain_list *chain; + char folded_sign = ' '; + int first = true; + int extra_offset = 0; + + remaining -= cumul; + + list_for_each_entry(chain, &child->val, list) { + char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str; + const char *str; + int color; + bool was_first = first; + + if (first) { + first = false; + chain->ms.has_children = chain->list.next != &child->val || + rb_first(&child->rb_root) != NULL; + } else { + extra_offset = LEVEL_OFFSET_STEP; + chain->ms.has_children = chain->list.next == &child->val && + rb_first(&child->rb_root) != NULL; + } + + folded_sign = callchain_list__folded(chain); + if (*row_offset != 0) { + --*row_offset; + goto do_next; + } + + alloc_str = NULL; + str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + if (was_first) { + double percent = cumul * 100.0 / new_total; + + if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) + str = "Not enough memory!"; + else + str = alloc_str; + } + + color = HE_COLORSET_NORMAL; + width = self->b.width - (offset + extra_offset + 2); + if (ui_browser__is_current_entry(&self->b, row)) { + self->selection = &chain->ms; + color = HE_COLORSET_SELECTED; + *is_current_entry = true; + } + + SLsmg_set_color(color); + SLsmg_gotorc(self->b.top + row, self->b.left); + slsmg_write_nstring(" ", offset + extra_offset); + slsmg_printf("%c ", folded_sign); + slsmg_write_nstring(str, width); + free(alloc_str); + + if (++row == self->b.height) + goto out; +do_next: + if (folded_sign == '+') + break; + } + + if (folded_sign == '-') { + const int new_level = level + (extra_offset ? 2 : 1); + row += hist_browser__show_callchain_node_rb_tree(self, child, new_total, + new_level, row, row_offset, + is_current_entry); + } + if (row == self->b.height) + goto out; + node = next; + } +out: + return row - first_row; +} + +static int hist_browser__show_callchain_node(struct hist_browser *self, + struct callchain_node *node, + int level, unsigned short row, + off_t *row_offset, + bool *is_current_entry) +{ + struct callchain_list *chain; + int first_row = row, + offset = level * LEVEL_OFFSET_STEP, + width = self->b.width - offset; + char folded_sign = ' '; + + list_for_each_entry(chain, &node->val, list) { + char ipstr[BITS_PER_LONG / 4 + 1], *s; + int color; + /* + * FIXME: This should be moved to somewhere else, + * probably when the callchain is created, so as not to + * traverse it all over again + */ + chain->ms.has_children = rb_first(&node->rb_root) != NULL; + folded_sign = callchain_list__folded(chain); + + if (*row_offset != 0) { + --*row_offset; + continue; + } + + color = HE_COLORSET_NORMAL; + if (ui_browser__is_current_entry(&self->b, row)) { + self->selection = &chain->ms; + color = HE_COLORSET_SELECTED; + *is_current_entry = true; + } + + s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + SLsmg_gotorc(self->b.top + row, self->b.left); + SLsmg_set_color(color); + slsmg_write_nstring(" ", offset); + slsmg_printf("%c ", folded_sign); + slsmg_write_nstring(s, width - 2); + + if (++row == self->b.height) + goto out; + } + + if (folded_sign == '-') + row += hist_browser__show_callchain_node_rb_tree(self, node, + self->hists->stats.total_period, + level + 1, row, + row_offset, + is_current_entry); +out: + return row - first_row; +} + +static int hist_browser__show_callchain(struct hist_browser *self, + struct rb_root *chain, + int level, unsigned short row, + off_t *row_offset, + bool *is_current_entry) +{ + struct rb_node *nd; + int first_row = row; + + for (nd = rb_first(chain); nd; nd = rb_next(nd)) { + struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); + + row += hist_browser__show_callchain_node(self, node, level, + row, row_offset, + is_current_entry); + if (row == self->b.height) + break; + } + + return row - first_row; +} + +static int hist_browser__show_entry(struct hist_browser *self, + struct hist_entry *entry, + unsigned short row) +{ + char s[256]; + double percent; + int printed = 0; + int color, width = self->b.width; + char folded_sign = ' '; + bool current_entry = ui_browser__is_current_entry(&self->b, row); + off_t row_offset = entry->row_offset; + + if (current_entry) { + self->he_selection = entry; + self->selection = &entry->ms; + } + + if (symbol_conf.use_callchain) { + entry->ms.has_children = !RB_EMPTY_ROOT(&entry->sorted_chain); + folded_sign = hist_entry__folded(entry); + } + + if (row_offset == 0) { + hist_entry__snprintf(entry, s, sizeof(s), self->hists, NULL, false, + 0, false, self->hists->stats.total_period); + percent = (entry->period * 100.0) / self->hists->stats.total_period; + + color = HE_COLORSET_SELECTED; + if (!current_entry) { + if (percent >= MIN_RED) + color = HE_COLORSET_TOP; + else if (percent >= MIN_GREEN) + color = HE_COLORSET_MEDIUM; + else + color = HE_COLORSET_NORMAL; + } + + SLsmg_set_color(color); + SLsmg_gotorc(self->b.top + row, self->b.left); + if (symbol_conf.use_callchain) { + slsmg_printf("%c ", folded_sign); + width -= 2; + } + slsmg_write_nstring(s, width); + ++row; + ++printed; + } else + --row_offset; + + if (folded_sign == '-' && row != self->b.height) { + printed += hist_browser__show_callchain(self, &entry->sorted_chain, + 1, row, &row_offset, + ¤t_entry); + if (current_entry) + self->he_selection = entry; + } + + return printed; +} + +static unsigned int hist_browser__refresh_entries(struct ui_browser *self) +{ + unsigned row = 0; + struct rb_node *nd; + struct hist_browser *hb = container_of(self, struct hist_browser, b); + + if (self->first_visible_entry == NULL) + self->first_visible_entry = rb_first(&hb->hists->entries); + + for (nd = self->first_visible_entry; nd; nd = rb_next(nd)) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + + if (h->filtered) + continue; + + row += hist_browser__show_entry(hb, h, row); + if (row == self->height) + break; + } + + return row; +} + +static void callchain_node__init_have_children_rb_tree(struct callchain_node *self) +{ + struct rb_node *nd = rb_first(&self->rb_root); + + for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) { + struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node); + struct callchain_list *chain; + int first = true; + + list_for_each_entry(chain, &child->val, list) { + if (first) { + first = false; + chain->ms.has_children = chain->list.next != &child->val || + rb_first(&child->rb_root) != NULL; + } else + chain->ms.has_children = chain->list.next == &child->val && + rb_first(&child->rb_root) != NULL; + } + + callchain_node__init_have_children_rb_tree(child); + } +} + +static void callchain_node__init_have_children(struct callchain_node *self) +{ + struct callchain_list *chain; + + list_for_each_entry(chain, &self->val, list) + chain->ms.has_children = rb_first(&self->rb_root) != NULL; + + callchain_node__init_have_children_rb_tree(self); +} + +static void callchain__init_have_children(struct rb_root *self) +{ + struct rb_node *nd; + + for (nd = rb_first(self); nd; nd = rb_next(nd)) { + struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); + callchain_node__init_have_children(node); + } +} + +static void hist_entry__init_have_children(struct hist_entry *self) +{ + if (!self->init_have_children) { + callchain__init_have_children(&self->sorted_chain); + self->init_have_children = true; + } +} + +static struct rb_node *hists__filter_entries(struct rb_node *nd) +{ + while (nd != NULL) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + if (!h->filtered) + return nd; + + nd = rb_next(nd); + } + + return NULL; +} + +static struct rb_node *hists__filter_prev_entries(struct rb_node *nd) +{ + while (nd != NULL) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + if (!h->filtered) + return nd; + + nd = rb_prev(nd); + } + + return NULL; +} + +static void ui_browser__hists_seek(struct ui_browser *self, + off_t offset, int whence) +{ + struct hist_entry *h; + struct rb_node *nd; + bool first = true; + + switch (whence) { + case SEEK_SET: + nd = hists__filter_entries(rb_first(self->entries)); + break; + case SEEK_CUR: + nd = self->first_visible_entry; + goto do_offset; + case SEEK_END: + nd = hists__filter_prev_entries(rb_last(self->entries)); + first = false; + break; + default: + return; + } + + /* + * Moves not relative to the first visible entry invalidates its + * row_offset: + */ + h = rb_entry(self->first_visible_entry, struct hist_entry, rb_node); + h->row_offset = 0; + + /* + * Here we have to check if nd is expanded (+), if it is we can't go + * the next top level hist_entry, instead we must compute an offset of + * what _not_ to show and not change the first visible entry. + * + * This offset increments when we are going from top to bottom and + * decreases when we're going from bottom to top. + * + * As we don't have backpointers to the top level in the callchains + * structure, we need to always print the whole hist_entry callchain, + * skipping the first ones that are before the first visible entry + * and stop when we printed enough lines to fill the screen. + */ +do_offset: + if (offset > 0) { + do { + h = rb_entry(nd, struct hist_entry, rb_node); + if (h->ms.unfolded) { + u16 remaining = h->nr_rows - h->row_offset; + if (offset > remaining) { + offset -= remaining; + h->row_offset = 0; + } else { + h->row_offset += offset; + offset = 0; + self->first_visible_entry = nd; + break; + } + } + nd = hists__filter_entries(rb_next(nd)); + if (nd == NULL) + break; + --offset; + self->first_visible_entry = nd; + } while (offset != 0); + } else if (offset < 0) { + while (1) { + h = rb_entry(nd, struct hist_entry, rb_node); + if (h->ms.unfolded) { + if (first) { + if (-offset > h->row_offset) { + offset += h->row_offset; + h->row_offset = 0; + } else { + h->row_offset += offset; + offset = 0; + self->first_visible_entry = nd; + break; + } + } else { + if (-offset > h->nr_rows) { + offset += h->nr_rows; + h->row_offset = 0; + } else { + h->row_offset = h->nr_rows + offset; + offset = 0; + self->first_visible_entry = nd; + break; + } + } + } + + nd = hists__filter_prev_entries(rb_prev(nd)); + if (nd == NULL) + break; + ++offset; + self->first_visible_entry = nd; + if (offset == 0) { + /* + * Last unfiltered hist_entry, check if it is + * unfolded, if it is then we should have + * row_offset at its last entry. + */ + h = rb_entry(nd, struct hist_entry, rb_node); + if (h->ms.unfolded) + h->row_offset = h->nr_rows; + break; + } + first = false; + } + } else { + self->first_visible_entry = nd; + h = rb_entry(nd, struct hist_entry, rb_node); + h->row_offset = 0; + } +} + +static int callchain_node__count_rows_rb_tree(struct callchain_node *self) +{ + int n = 0; + struct rb_node *nd; + + for (nd = rb_first(&self->rb_root); nd; nd = rb_next(nd)) { + struct callchain_node *child = rb_entry(nd, struct callchain_node, rb_node); + struct callchain_list *chain; + char folded_sign = ' '; /* No children */ + + list_for_each_entry(chain, &child->val, list) { + ++n; + /* We need this because we may not have children */ + folded_sign = callchain_list__folded(chain); + if (folded_sign == '+') + break; + } + + if (folded_sign == '-') /* Have children and they're unfolded */ + n += callchain_node__count_rows_rb_tree(child); + } + + return n; +} + +static int callchain_node__count_rows(struct callchain_node *node) +{ + struct callchain_list *chain; + bool unfolded = false; + int n = 0; + + list_for_each_entry(chain, &node->val, list) { + ++n; + unfolded = chain->ms.unfolded; + } + + if (unfolded) + n += callchain_node__count_rows_rb_tree(node); + + return n; +} + +static int callchain__count_rows(struct rb_root *chain) +{ + struct rb_node *nd; + int n = 0; + + for (nd = rb_first(chain); nd; nd = rb_next(nd)) { + struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); + n += callchain_node__count_rows(node); + } + + return n; +} + +static bool hist_browser__toggle_fold(struct hist_browser *self) +{ + if (map_symbol__toggle_fold(self->selection)) { + struct hist_entry *he = self->he_selection; + + hist_entry__init_have_children(he); + self->hists->nr_entries -= he->nr_rows; + + if (he->ms.unfolded) + he->nr_rows = callchain__count_rows(&he->sorted_chain); + else + he->nr_rows = 0; + self->hists->nr_entries += he->nr_rows; + self->b.nr_entries = self->hists->nr_entries; + + return true; + } + + /* If it doesn't have children, no toggling performed */ + return false; +} + +static int hist_browser__run(struct hist_browser *self, const char *title, + struct newtExitStruct *es) +{ + char str[256], unit; + unsigned long nr_events = self->hists->stats.nr_events[PERF_RECORD_SAMPLE]; + + self->b.entries = &self->hists->entries; + self->b.nr_entries = self->hists->nr_entries; + + hist_browser__refresh_dimensions(self); + + nr_events = convert_unit(nr_events, &unit); + snprintf(str, sizeof(str), "Events: %lu%c ", + nr_events, unit); + newtDrawRootText(0, 0, str); + + if (ui_browser__show(&self->b, title) < 0) + return -1; + + newtFormAddHotKey(self->b.form, 'A'); + newtFormAddHotKey(self->b.form, 'a'); + newtFormAddHotKey(self->b.form, '?'); + newtFormAddHotKey(self->b.form, 'h'); + newtFormAddHotKey(self->b.form, 'H'); + newtFormAddHotKey(self->b.form, 'd'); + + newtFormAddHotKey(self->b.form, NEWT_KEY_LEFT); + newtFormAddHotKey(self->b.form, NEWT_KEY_RIGHT); + newtFormAddHotKey(self->b.form, NEWT_KEY_ENTER); + + while (1) { + ui_browser__run(&self->b, es); + + if (es->reason != NEWT_EXIT_HOTKEY) + break; + switch (es->u.key) { + case 'd': { /* Debug */ + static int seq; + struct hist_entry *h = rb_entry(self->b.first_visible_entry, + struct hist_entry, rb_node); + ui_helpline__pop(); + ui_helpline__fpush("%d: nr_ent=(%d,%d), height=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", + seq++, self->b.nr_entries, + self->hists->nr_entries, + self->b.height, + self->b.index, + self->b.first_visible_entry_idx, + h->row_offset, h->nr_rows); + } + continue; + case NEWT_KEY_ENTER: + if (hist_browser__toggle_fold(self)) + break; + /* fall thru */ + default: + return 0; + } + } + return 0; +} diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9bf0f402ca7..4af5bd59cfd 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -602,8 +602,15 @@ parse_breakpoint_event(const char **strp, struct perf_event_attr *attr) return EVT_FAILED; } - /* We should find a nice way to override the access type */ - attr->bp_len = HW_BREAKPOINT_LEN_4; + /* + * We should find a nice way to override the access length + * Provide some defaults for now + */ + if (attr->bp_type == HW_BREAKPOINT_X) + attr->bp_len = sizeof(long); + else + attr->bp_len = HW_BREAKPOINT_LEN_4; + attr->type = PERF_TYPE_BREAKPOINT; return EVT_HANDLED; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 914c67095d9..2e665cb8405 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1,5 +1,5 @@ /* - * probe-event.c : perf-probe definition to kprobe_events format converter + * probe-event.c : perf-probe definition to probe_events format converter * * Written by Masami Hiramatsu <mhiramat@redhat.com> * @@ -120,8 +120,11 @@ static int open_vmlinux(void) return open(machine.vmlinux_maps[MAP__FUNCTION]->dso->long_name, O_RDONLY); } -/* Convert trace point to probe point with debuginfo */ -static int convert_to_perf_probe_point(struct kprobe_trace_point *tp, +/* + * Convert trace point to probe point with debuginfo + * Currently only handles kprobes. + */ +static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, struct perf_probe_point *pp) { struct symbol *sym; @@ -151,8 +154,8 @@ static int convert_to_perf_probe_point(struct kprobe_trace_point *tp, } /* Try to find perf_probe_event with debuginfo */ -static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev, - struct kprobe_trace_event **tevs, +static int try_to_find_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event **tevs, int max_tevs) { bool need_dwarf = perf_probe_event_need_dwarf(pev); @@ -169,11 +172,11 @@ static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev, } /* Searching trace events corresponding to probe event */ - ntevs = find_kprobe_trace_events(fd, pev, tevs, max_tevs); + ntevs = find_probe_trace_events(fd, pev, tevs, max_tevs); close(fd); if (ntevs > 0) { /* Succeeded to find trace events */ - pr_debug("find %d kprobe_trace_events.\n", ntevs); + pr_debug("find %d probe_trace_events.\n", ntevs); return ntevs; } @@ -195,6 +198,65 @@ static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev, return ntevs; } +/* + * Find a src file from a DWARF tag path. Prepend optional source path prefix + * and chop off leading directories that do not exist. Result is passed back as + * a newly allocated path on success. + * Return 0 if file was found and readable, -errno otherwise. + */ +static int get_real_path(const char *raw_path, const char *comp_dir, + char **new_path) +{ + const char *prefix = symbol_conf.source_prefix; + + if (!prefix) { + if (raw_path[0] != '/' && comp_dir) + /* If not an absolute path, try to use comp_dir */ + prefix = comp_dir; + else { + if (access(raw_path, R_OK) == 0) { + *new_path = strdup(raw_path); + return 0; + } else + return -errno; + } + } + + *new_path = malloc((strlen(prefix) + strlen(raw_path) + 2)); + if (!*new_path) + return -ENOMEM; + + for (;;) { + sprintf(*new_path, "%s/%s", prefix, raw_path); + + if (access(*new_path, R_OK) == 0) + return 0; + + if (!symbol_conf.source_prefix) + /* In case of searching comp_dir, don't retry */ + return -errno; + + switch (errno) { + case ENAMETOOLONG: + case ENOENT: + case EROFS: + case EFAULT: + raw_path = strchr(++raw_path, '/'); + if (!raw_path) { + free(*new_path); + *new_path = NULL; + return -ENOENT; + } + continue; + + default: + free(*new_path); + *new_path = NULL; + return -errno; + } + } +} + #define LINEBUF_SIZE 256 #define NR_ADDITIONAL_LINES 2 @@ -244,6 +306,7 @@ int show_line_range(struct line_range *lr) struct line_node *ln; FILE *fp; int fd, ret; + char *tmp; /* Search a line range */ ret = init_vmlinux(); @@ -266,6 +329,15 @@ int show_line_range(struct line_range *lr) return ret; } + /* Convert source file path */ + tmp = lr->path; + ret = get_real_path(tmp, lr->comp_dir, &lr->path); + free(tmp); /* Free old path */ + if (ret < 0) { + pr_warning("Failed to find source file. (%d)\n", ret); + return ret; + } + setup_pager(); if (lr->function) @@ -308,8 +380,8 @@ end: #else /* !DWARF_SUPPORT */ -static int convert_to_perf_probe_point(struct kprobe_trace_point *tp, - struct perf_probe_point *pp) +static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp, + struct perf_probe_point *pp) { pp->function = strdup(tp->symbol); if (pp->function == NULL) @@ -320,8 +392,8 @@ static int convert_to_perf_probe_point(struct kprobe_trace_point *tp, return 0; } -static int try_to_find_kprobe_trace_events(struct perf_probe_event *pev, - struct kprobe_trace_event **tevs __unused, +static int try_to_find_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event **tevs __unused, int max_tevs __unused) { if (perf_probe_event_need_dwarf(pev)) { @@ -557,7 +629,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) /* Parse perf-probe event argument */ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) { - char *tmp; + char *tmp, *goodname; struct perf_probe_arg_field **fieldp; pr_debug("parsing arg: %s into ", str); @@ -580,7 +652,7 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) pr_debug("type:%s ", arg->type); } - tmp = strpbrk(str, "-."); + tmp = strpbrk(str, "-.["); if (!is_c_varname(str) || !tmp) { /* A variable, register, symbol or special value */ arg->var = strdup(str); @@ -590,10 +662,11 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) return 0; } - /* Structure fields */ + /* Structure fields or array element */ arg->var = strndup(str, tmp - str); if (arg->var == NULL) return -ENOMEM; + goodname = arg->var; pr_debug("%s, ", arg->var); fieldp = &arg->field; @@ -601,22 +674,38 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) *fieldp = zalloc(sizeof(struct perf_probe_arg_field)); if (*fieldp == NULL) return -ENOMEM; - if (*tmp == '.') { - str = tmp + 1; - (*fieldp)->ref = false; - } else if (tmp[1] == '>') { - str = tmp + 2; + if (*tmp == '[') { /* Array */ + str = tmp; + (*fieldp)->index = strtol(str + 1, &tmp, 0); (*fieldp)->ref = true; - } else { - semantic_error("Argument parse error: %s\n", str); - return -EINVAL; + if (*tmp != ']' || tmp == str + 1) { + semantic_error("Array index must be a" + " number.\n"); + return -EINVAL; + } + tmp++; + if (*tmp == '\0') + tmp = NULL; + } else { /* Structure */ + if (*tmp == '.') { + str = tmp + 1; + (*fieldp)->ref = false; + } else if (tmp[1] == '>') { + str = tmp + 2; + (*fieldp)->ref = true; + } else { + semantic_error("Argument parse error: %s\n", + str); + return -EINVAL; + } + tmp = strpbrk(str, "-.["); } - - tmp = strpbrk(str, "-."); if (tmp) { (*fieldp)->name = strndup(str, tmp - str); if ((*fieldp)->name == NULL) return -ENOMEM; + if (*str != '[') + goodname = (*fieldp)->name; pr_debug("%s(%d), ", (*fieldp)->name, (*fieldp)->ref); fieldp = &(*fieldp)->next; } @@ -624,11 +713,13 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) (*fieldp)->name = strdup(str); if ((*fieldp)->name == NULL) return -ENOMEM; + if (*str != '[') + goodname = (*fieldp)->name; pr_debug("%s(%d)\n", (*fieldp)->name, (*fieldp)->ref); - /* If no name is specified, set the last field name */ + /* If no name is specified, set the last field name (not array index)*/ if (!arg->name) { - arg->name = strdup((*fieldp)->name); + arg->name = strdup(goodname); if (arg->name == NULL) return -ENOMEM; } @@ -693,16 +784,17 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev) return false; } -/* Parse kprobe_events event into struct probe_point */ -int parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev) +/* Parse probe_events event into struct probe_point */ +static int parse_probe_trace_command(const char *cmd, + struct probe_trace_event *tev) { - struct kprobe_trace_point *tp = &tev->point; + struct probe_trace_point *tp = &tev->point; char pr; char *p; int ret, i, argc; char **argv; - pr_debug("Parsing kprobe_events: %s\n", cmd); + pr_debug("Parsing probe_events: %s\n", cmd); argv = argv_split(cmd, &argc); if (!argv) { pr_debug("Failed to split arguments.\n"); @@ -734,7 +826,7 @@ int parse_kprobe_trace_command(const char *cmd, struct kprobe_trace_event *tev) tp->offset = 0; tev->nargs = argc - 2; - tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs); + tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); if (tev->args == NULL) { ret = -ENOMEM; goto out; @@ -776,8 +868,11 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len) len -= ret; while (field) { - ret = e_snprintf(tmp, len, "%s%s", field->ref ? "->" : ".", - field->name); + if (field->name[0] == '[') + ret = e_snprintf(tmp, len, "%s", field->name); + else + ret = e_snprintf(tmp, len, "%s%s", + field->ref ? "->" : ".", field->name); if (ret <= 0) goto error; tmp += ret; @@ -877,13 +972,13 @@ char *synthesize_perf_probe_command(struct perf_probe_event *pev) } #endif -static int __synthesize_kprobe_trace_arg_ref(struct kprobe_trace_arg_ref *ref, +static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref, char **buf, size_t *buflen, int depth) { int ret; if (ref->next) { - depth = __synthesize_kprobe_trace_arg_ref(ref->next, buf, + depth = __synthesize_probe_trace_arg_ref(ref->next, buf, buflen, depth + 1); if (depth < 0) goto out; @@ -901,9 +996,10 @@ out: } -static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg, +static int synthesize_probe_trace_arg(struct probe_trace_arg *arg, char *buf, size_t buflen) { + struct probe_trace_arg_ref *ref = arg->ref; int ret, depth = 0; char *tmp = buf; @@ -917,16 +1013,24 @@ static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg, buf += ret; buflen -= ret; + /* Special case: @XXX */ + if (arg->value[0] == '@' && arg->ref) + ref = ref->next; + /* Dereferencing arguments */ - if (arg->ref) { - depth = __synthesize_kprobe_trace_arg_ref(arg->ref, &buf, + if (ref) { + depth = __synthesize_probe_trace_arg_ref(ref, &buf, &buflen, 1); if (depth < 0) return depth; } /* Print argument value */ - ret = e_snprintf(buf, buflen, "%s", arg->value); + if (arg->value[0] == '@' && arg->ref) + ret = e_snprintf(buf, buflen, "%s%+ld", arg->value, + arg->ref->offset); + else + ret = e_snprintf(buf, buflen, "%s", arg->value); if (ret < 0) return ret; buf += ret; @@ -951,9 +1055,9 @@ static int synthesize_kprobe_trace_arg(struct kprobe_trace_arg *arg, return buf - tmp; } -char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev) +char *synthesize_probe_trace_command(struct probe_trace_event *tev) { - struct kprobe_trace_point *tp = &tev->point; + struct probe_trace_point *tp = &tev->point; char *buf; int i, len, ret; @@ -969,7 +1073,7 @@ char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev) goto error; for (i = 0; i < tev->nargs; i++) { - ret = synthesize_kprobe_trace_arg(&tev->args[i], buf + len, + ret = synthesize_probe_trace_arg(&tev->args[i], buf + len, MAX_CMDLEN - len); if (ret <= 0) goto error; @@ -982,7 +1086,7 @@ error: return NULL; } -int convert_to_perf_probe_event(struct kprobe_trace_event *tev, +static int convert_to_perf_probe_event(struct probe_trace_event *tev, struct perf_probe_event *pev) { char buf[64] = ""; @@ -995,7 +1099,7 @@ int convert_to_perf_probe_event(struct kprobe_trace_event *tev, return -ENOMEM; /* Convert trace_point to probe_point */ - ret = convert_to_perf_probe_point(&tev->point, &pev->point); + ret = kprobe_convert_to_perf_probe(&tev->point, &pev->point); if (ret < 0) return ret; @@ -1008,7 +1112,7 @@ int convert_to_perf_probe_event(struct kprobe_trace_event *tev, if (tev->args[i].name) pev->args[i].name = strdup(tev->args[i].name); else { - ret = synthesize_kprobe_trace_arg(&tev->args[i], + ret = synthesize_probe_trace_arg(&tev->args[i], buf, 64); pev->args[i].name = strdup(buf); } @@ -1059,9 +1163,9 @@ void clear_perf_probe_event(struct perf_probe_event *pev) memset(pev, 0, sizeof(*pev)); } -void clear_kprobe_trace_event(struct kprobe_trace_event *tev) +static void clear_probe_trace_event(struct probe_trace_event *tev) { - struct kprobe_trace_arg_ref *ref, *next; + struct probe_trace_arg_ref *ref, *next; int i; if (tev->event) @@ -1122,7 +1226,7 @@ static int open_kprobe_events(bool readwrite) } /* Get raw string list of current kprobe_events */ -static struct strlist *get_kprobe_trace_command_rawlist(int fd) +static struct strlist *get_probe_trace_command_rawlist(int fd) { int ret, idx; FILE *fp; @@ -1190,7 +1294,7 @@ static int show_perf_probe_event(struct perf_probe_event *pev) int show_perf_probe_events(void) { int fd, ret; - struct kprobe_trace_event tev; + struct probe_trace_event tev; struct perf_probe_event pev; struct strlist *rawlist; struct str_node *ent; @@ -1207,20 +1311,20 @@ int show_perf_probe_events(void) if (fd < 0) return fd; - rawlist = get_kprobe_trace_command_rawlist(fd); + rawlist = get_probe_trace_command_rawlist(fd); close(fd); if (!rawlist) return -ENOENT; strlist__for_each(ent, rawlist) { - ret = parse_kprobe_trace_command(ent->s, &tev); + ret = parse_probe_trace_command(ent->s, &tev); if (ret >= 0) { ret = convert_to_perf_probe_event(&tev, &pev); if (ret >= 0) ret = show_perf_probe_event(&pev); } clear_perf_probe_event(&pev); - clear_kprobe_trace_event(&tev); + clear_probe_trace_event(&tev); if (ret < 0) break; } @@ -1230,20 +1334,19 @@ int show_perf_probe_events(void) } /* Get current perf-probe event names */ -static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group) +static struct strlist *get_probe_trace_event_names(int fd, bool include_group) { char buf[128]; struct strlist *sl, *rawlist; struct str_node *ent; - struct kprobe_trace_event tev; + struct probe_trace_event tev; int ret = 0; memset(&tev, 0, sizeof(tev)); - - rawlist = get_kprobe_trace_command_rawlist(fd); + rawlist = get_probe_trace_command_rawlist(fd); sl = strlist__new(true, NULL); strlist__for_each(ent, rawlist) { - ret = parse_kprobe_trace_command(ent->s, &tev); + ret = parse_probe_trace_command(ent->s, &tev); if (ret < 0) break; if (include_group) { @@ -1253,7 +1356,7 @@ static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group) ret = strlist__add(sl, buf); } else ret = strlist__add(sl, tev.event); - clear_kprobe_trace_event(&tev); + clear_probe_trace_event(&tev); if (ret < 0) break; } @@ -1266,13 +1369,13 @@ static struct strlist *get_kprobe_trace_event_names(int fd, bool include_group) return sl; } -static int write_kprobe_trace_event(int fd, struct kprobe_trace_event *tev) +static int write_probe_trace_event(int fd, struct probe_trace_event *tev) { int ret = 0; - char *buf = synthesize_kprobe_trace_command(tev); + char *buf = synthesize_probe_trace_command(tev); if (!buf) { - pr_debug("Failed to synthesize kprobe trace event.\n"); + pr_debug("Failed to synthesize probe trace event.\n"); return -EINVAL; } @@ -1325,12 +1428,12 @@ static int get_new_event_name(char *buf, size_t len, const char *base, return ret; } -static int __add_kprobe_trace_events(struct perf_probe_event *pev, - struct kprobe_trace_event *tevs, +static int __add_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event *tevs, int ntevs, bool allow_suffix) { int i, fd, ret; - struct kprobe_trace_event *tev = NULL; + struct probe_trace_event *tev = NULL; char buf[64]; const char *event, *group; struct strlist *namelist; @@ -1339,7 +1442,7 @@ static int __add_kprobe_trace_events(struct perf_probe_event *pev, if (fd < 0) return fd; /* Get current event names */ - namelist = get_kprobe_trace_event_names(fd, false); + namelist = get_probe_trace_event_names(fd, false); if (!namelist) { pr_debug("Failed to get current event list.\n"); return -EIO; @@ -1374,7 +1477,7 @@ static int __add_kprobe_trace_events(struct perf_probe_event *pev, ret = -ENOMEM; break; } - ret = write_kprobe_trace_event(fd, tev); + ret = write_probe_trace_event(fd, tev); if (ret < 0) break; /* Add added event name to namelist */ @@ -1411,21 +1514,21 @@ static int __add_kprobe_trace_events(struct perf_probe_event *pev, return ret; } -static int convert_to_kprobe_trace_events(struct perf_probe_event *pev, - struct kprobe_trace_event **tevs, +static int convert_to_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event **tevs, int max_tevs) { struct symbol *sym; int ret = 0, i; - struct kprobe_trace_event *tev; + struct probe_trace_event *tev; /* Convert perf_probe_event with debuginfo */ - ret = try_to_find_kprobe_trace_events(pev, tevs, max_tevs); + ret = try_to_find_probe_trace_events(pev, tevs, max_tevs); if (ret != 0) return ret; /* Allocate trace event buffer */ - tev = *tevs = zalloc(sizeof(struct kprobe_trace_event)); + tev = *tevs = zalloc(sizeof(struct probe_trace_event)); if (tev == NULL) return -ENOMEM; @@ -1438,7 +1541,7 @@ static int convert_to_kprobe_trace_events(struct perf_probe_event *pev, tev->point.offset = pev->point.offset; tev->nargs = pev->nargs; if (tev->nargs) { - tev->args = zalloc(sizeof(struct kprobe_trace_arg) + tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); if (tev->args == NULL) { ret = -ENOMEM; @@ -1479,7 +1582,7 @@ static int convert_to_kprobe_trace_events(struct perf_probe_event *pev, return 1; error: - clear_kprobe_trace_event(tev); + clear_probe_trace_event(tev); free(tev); *tevs = NULL; return ret; @@ -1487,7 +1590,7 @@ error: struct __event_package { struct perf_probe_event *pev; - struct kprobe_trace_event *tevs; + struct probe_trace_event *tevs; int ntevs; }; @@ -1510,7 +1613,7 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, for (i = 0; i < npevs; i++) { pkgs[i].pev = &pevs[i]; /* Convert with or without debuginfo */ - ret = convert_to_kprobe_trace_events(pkgs[i].pev, + ret = convert_to_probe_trace_events(pkgs[i].pev, &pkgs[i].tevs, max_tevs); if (ret < 0) goto end; @@ -1519,24 +1622,24 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, /* Loop 2: add all events */ for (i = 0; i < npevs && ret >= 0; i++) - ret = __add_kprobe_trace_events(pkgs[i].pev, pkgs[i].tevs, + ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs, pkgs[i].ntevs, force_add); end: /* Loop 3: cleanup trace events */ for (i = 0; i < npevs; i++) for (j = 0; j < pkgs[i].ntevs; j++) - clear_kprobe_trace_event(&pkgs[i].tevs[j]); + clear_probe_trace_event(&pkgs[i].tevs[j]); return ret; } -static int __del_trace_kprobe_event(int fd, struct str_node *ent) +static int __del_trace_probe_event(int fd, struct str_node *ent) { char *p; char buf[128]; int ret; - /* Convert from perf-probe event to trace-kprobe event */ + /* Convert from perf-probe event to trace-probe event */ ret = e_snprintf(buf, 128, "-:%s", ent->s); if (ret < 0) goto error; @@ -1562,7 +1665,7 @@ error: return ret; } -static int del_trace_kprobe_event(int fd, const char *group, +static int del_trace_probe_event(int fd, const char *group, const char *event, struct strlist *namelist) { char buf[128]; @@ -1579,7 +1682,7 @@ static int del_trace_kprobe_event(int fd, const char *group, strlist__for_each_safe(ent, n, namelist) if (strglobmatch(ent->s, buf)) { found++; - ret = __del_trace_kprobe_event(fd, ent); + ret = __del_trace_probe_event(fd, ent); if (ret < 0) break; strlist__remove(namelist, ent); @@ -1588,7 +1691,7 @@ static int del_trace_kprobe_event(int fd, const char *group, ent = strlist__find(namelist, buf); if (ent) { found++; - ret = __del_trace_kprobe_event(fd, ent); + ret = __del_trace_probe_event(fd, ent); if (ret >= 0) strlist__remove(namelist, ent); } @@ -1612,7 +1715,7 @@ int del_perf_probe_events(struct strlist *dellist) return fd; /* Get current event names */ - namelist = get_kprobe_trace_event_names(fd, true); + namelist = get_probe_trace_event_names(fd, true); if (namelist == NULL) return -EINVAL; @@ -1633,7 +1736,7 @@ int del_perf_probe_events(struct strlist *dellist) event = str; } pr_debug("Group: %s, Event: %s\n", group, event); - ret = del_trace_kprobe_event(fd, group, event, namelist); + ret = del_trace_probe_event(fd, group, event, namelist); free(str); if (ret < 0) break; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index e9db1a214ca..5af39243a25 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -7,33 +7,33 @@ extern bool probe_event_dry_run; /* kprobe-tracer tracing point */ -struct kprobe_trace_point { +struct probe_trace_point { char *symbol; /* Base symbol */ unsigned long offset; /* Offset from symbol */ bool retprobe; /* Return probe flag */ }; -/* kprobe-tracer tracing argument referencing offset */ -struct kprobe_trace_arg_ref { - struct kprobe_trace_arg_ref *next; /* Next reference */ +/* probe-tracer tracing argument referencing offset */ +struct probe_trace_arg_ref { + struct probe_trace_arg_ref *next; /* Next reference */ long offset; /* Offset value */ }; /* kprobe-tracer tracing argument */ -struct kprobe_trace_arg { +struct probe_trace_arg { char *name; /* Argument name */ char *value; /* Base value */ char *type; /* Type name */ - struct kprobe_trace_arg_ref *ref; /* Referencing offset */ + struct probe_trace_arg_ref *ref; /* Referencing offset */ }; /* kprobe-tracer tracing event (point + arg) */ -struct kprobe_trace_event { +struct probe_trace_event { char *event; /* Event name */ char *group; /* Group name */ - struct kprobe_trace_point point; /* Trace point */ + struct probe_trace_point point; /* Trace point */ int nargs; /* Number of args */ - struct kprobe_trace_arg *args; /* Arguments */ + struct probe_trace_arg *args; /* Arguments */ }; /* Perf probe probing point */ @@ -50,6 +50,7 @@ struct perf_probe_point { struct perf_probe_arg_field { struct perf_probe_arg_field *next; /* Next field */ char *name; /* Name of the field */ + long index; /* Array index number */ bool ref; /* Referencing flag */ }; @@ -85,31 +86,25 @@ struct line_range { int end; /* End line number */ int offset; /* Start line offset */ char *path; /* Real path name */ + char *comp_dir; /* Compile directory */ struct list_head line_list; /* Visible lines */ }; /* Command string to events */ extern int parse_perf_probe_command(const char *cmd, struct perf_probe_event *pev); -extern int parse_kprobe_trace_command(const char *cmd, - struct kprobe_trace_event *tev); /* Events to command string */ extern char *synthesize_perf_probe_command(struct perf_probe_event *pev); -extern char *synthesize_kprobe_trace_command(struct kprobe_trace_event *tev); +extern char *synthesize_probe_trace_command(struct probe_trace_event *tev); extern int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len); /* Check the perf_probe_event needs debuginfo */ extern bool perf_probe_event_need_dwarf(struct perf_probe_event *pev); -/* Convert from kprobe_trace_event to perf_probe_event */ -extern int convert_to_perf_probe_event(struct kprobe_trace_event *tev, - struct perf_probe_event *pev); - /* Release event contents */ extern void clear_perf_probe_event(struct perf_probe_event *pev); -extern void clear_kprobe_trace_event(struct kprobe_trace_event *tev); /* Command string to line-range */ extern int parse_line_range_desc(const char *cmd, struct line_range *lr); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index d964cb199c6..840f1aabbb7 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -37,6 +37,7 @@ #include "event.h" #include "debug.h" #include "util.h" +#include "symbol.h" #include "probe-finder.h" /* Kprobe tracer basic type is up to u64 */ @@ -143,12 +144,21 @@ static const char *cu_find_realpath(Dwarf_Die *cu_die, const char *fname) return src; } +/* Get DW_AT_comp_dir (should be NULL with older gcc) */ +static const char *cu_get_comp_dir(Dwarf_Die *cu_die) +{ + Dwarf_Attribute attr; + if (dwarf_attr(cu_die, DW_AT_comp_dir, &attr) == NULL) + return NULL; + return dwarf_formstring(&attr); +} + /* Compare diename and tname */ static bool die_compare_name(Dwarf_Die *dw_die, const char *tname) { const char *name; name = dwarf_diename(dw_die); - return name ? strcmp(tname, name) : -1; + return name ? (strcmp(tname, name) == 0) : false; } /* Get type die, but skip qualifiers and typedef */ @@ -319,7 +329,7 @@ static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data) tag = dwarf_tag(die_mem); if ((tag == DW_TAG_formal_parameter || tag == DW_TAG_variable) && - (die_compare_name(die_mem, name) == 0)) + die_compare_name(die_mem, name)) return DIE_FIND_CB_FOUND; return DIE_FIND_CB_CONTINUE; @@ -338,7 +348,7 @@ static int __die_find_member_cb(Dwarf_Die *die_mem, void *data) const char *name = data; if ((dwarf_tag(die_mem) == DW_TAG_member) && - (die_compare_name(die_mem, name) == 0)) + die_compare_name(die_mem, name)) return DIE_FIND_CB_FOUND; return DIE_FIND_CB_SIBLING; @@ -356,14 +366,50 @@ static Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name, * Probe finder related functions */ +static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs) +{ + struct probe_trace_arg_ref *ref; + ref = zalloc(sizeof(struct probe_trace_arg_ref)); + if (ref != NULL) + ref->offset = offs; + return ref; +} + /* Show a location */ -static int convert_location(Dwarf_Op *op, struct probe_finder *pf) +static int convert_variable_location(Dwarf_Die *vr_die, struct probe_finder *pf) { + Dwarf_Attribute attr; + Dwarf_Op *op; + size_t nops; unsigned int regn; Dwarf_Word offs = 0; bool ref = false; const char *regs; - struct kprobe_trace_arg *tvar = pf->tvar; + struct probe_trace_arg *tvar = pf->tvar; + int ret; + + /* TODO: handle more than 1 exprs */ + if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL || + dwarf_getlocation_addr(&attr, pf->addr, &op, &nops, 1) <= 0 || + nops == 0) { + /* TODO: Support const_value */ + pr_err("Failed to find the location of %s at this address.\n" + " Perhaps, it has been optimized out.\n", pf->pvar->var); + return -ENOENT; + } + + if (op->atom == DW_OP_addr) { + /* Static variables on memory (not stack), make @varname */ + ret = strlen(dwarf_diename(vr_die)); + tvar->value = zalloc(ret + 2); + if (tvar->value == NULL) + return -ENOMEM; + snprintf(tvar->value, ret + 2, "@%s", dwarf_diename(vr_die)); + tvar->ref = alloc_trace_arg_ref((long)offs); + if (tvar->ref == NULL) + return -ENOMEM; + return 0; + } /* If this is based on frame buffer, set the offset */ if (op->atom == DW_OP_fbreg) { @@ -405,27 +451,72 @@ static int convert_location(Dwarf_Op *op, struct probe_finder *pf) return -ENOMEM; if (ref) { - tvar->ref = zalloc(sizeof(struct kprobe_trace_arg_ref)); + tvar->ref = alloc_trace_arg_ref((long)offs); if (tvar->ref == NULL) return -ENOMEM; - tvar->ref->offset = (long)offs; } return 0; } static int convert_variable_type(Dwarf_Die *vr_die, - struct kprobe_trace_arg *targ) + struct probe_trace_arg *tvar, + const char *cast) { + struct probe_trace_arg_ref **ref_ptr = &tvar->ref; Dwarf_Die type; char buf[16]; int ret; + /* TODO: check all types */ + if (cast && strcmp(cast, "string") != 0) { + /* Non string type is OK */ + tvar->type = strdup(cast); + return (tvar->type == NULL) ? -ENOMEM : 0; + } + if (die_get_real_type(vr_die, &type) == NULL) { pr_warning("Failed to get a type information of %s.\n", dwarf_diename(vr_die)); return -ENOENT; } + pr_debug("%s type is %s.\n", + dwarf_diename(vr_die), dwarf_diename(&type)); + + if (cast && strcmp(cast, "string") == 0) { /* String type */ + ret = dwarf_tag(&type); + if (ret != DW_TAG_pointer_type && + ret != DW_TAG_array_type) { + pr_warning("Failed to cast into string: " + "%s(%s) is not a pointer nor array.", + dwarf_diename(vr_die), dwarf_diename(&type)); + return -EINVAL; + } + if (ret == DW_TAG_pointer_type) { + if (die_get_real_type(&type, &type) == NULL) { + pr_warning("Failed to get a type information."); + return -ENOENT; + } + while (*ref_ptr) + ref_ptr = &(*ref_ptr)->next; + /* Add new reference with offset +0 */ + *ref_ptr = zalloc(sizeof(struct probe_trace_arg_ref)); + if (*ref_ptr == NULL) { + pr_warning("Out of memory error\n"); + return -ENOMEM; + } + } + if (!die_compare_name(&type, "char") && + !die_compare_name(&type, "unsigned char")) { + pr_warning("Failed to cast into string: " + "%s is not (unsigned) char *.", + dwarf_diename(vr_die)); + return -EINVAL; + } + tvar->type = strdup(cast); + return (tvar->type == NULL) ? -ENOMEM : 0; + } + ret = die_get_byte_size(&type) * 8; if (ret) { /* Check the bitwidth */ @@ -445,8 +536,8 @@ static int convert_variable_type(Dwarf_Die *vr_die, strerror(-ret)); return ret; } - targ->type = strdup(buf); - if (targ->type == NULL) + tvar->type = strdup(buf); + if (tvar->type == NULL) return -ENOMEM; } return 0; @@ -454,22 +545,50 @@ static int convert_variable_type(Dwarf_Die *vr_die, static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, struct perf_probe_arg_field *field, - struct kprobe_trace_arg_ref **ref_ptr, + struct probe_trace_arg_ref **ref_ptr, Dwarf_Die *die_mem) { - struct kprobe_trace_arg_ref *ref = *ref_ptr; + struct probe_trace_arg_ref *ref = *ref_ptr; Dwarf_Die type; Dwarf_Word offs; - int ret; + int ret, tag; pr_debug("converting %s in %s\n", field->name, varname); if (die_get_real_type(vr_die, &type) == NULL) { pr_warning("Failed to get the type of %s.\n", varname); return -ENOENT; } - - /* Check the pointer and dereference */ - if (dwarf_tag(&type) == DW_TAG_pointer_type) { + pr_debug2("Var real type: (%x)\n", (unsigned)dwarf_dieoffset(&type)); + tag = dwarf_tag(&type); + + if (field->name[0] == '[' && + (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)) { + if (field->next) + /* Save original type for next field */ + memcpy(die_mem, &type, sizeof(*die_mem)); + /* Get the type of this array */ + if (die_get_real_type(&type, &type) == NULL) { + pr_warning("Failed to get the type of %s.\n", varname); + return -ENOENT; + } + pr_debug2("Array real type: (%x)\n", + (unsigned)dwarf_dieoffset(&type)); + if (tag == DW_TAG_pointer_type) { + ref = zalloc(sizeof(struct probe_trace_arg_ref)); + if (ref == NULL) + return -ENOMEM; + if (*ref_ptr) + (*ref_ptr)->next = ref; + else + *ref_ptr = ref; + } + ref->offset += die_get_byte_size(&type) * field->index; + if (!field->next) + /* Save vr_die for converting types */ + memcpy(die_mem, vr_die, sizeof(*die_mem)); + goto next; + } else if (tag == DW_TAG_pointer_type) { + /* Check the pointer and dereference */ if (!field->ref) { pr_err("Semantic error: %s must be referred by '->'\n", field->name); @@ -486,7 +605,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, return -EINVAL; } - ref = zalloc(sizeof(struct kprobe_trace_arg_ref)); + ref = zalloc(sizeof(struct probe_trace_arg_ref)); if (ref == NULL) return -ENOMEM; if (*ref_ptr) @@ -495,10 +614,15 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, *ref_ptr = ref; } else { /* Verify it is a data structure */ - if (dwarf_tag(&type) != DW_TAG_structure_type) { + if (tag != DW_TAG_structure_type) { pr_warning("%s is not a data structure.\n", varname); return -EINVAL; } + if (field->name[0] == '[') { + pr_err("Semantic error: %s is not a pointor nor array.", + varname); + return -EINVAL; + } if (field->ref) { pr_err("Semantic error: %s must be referred by '.'\n", field->name); @@ -525,6 +649,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, } ref->offset += (long)offs; +next: /* Converting next field */ if (field->next) return convert_variable_fields(die_mem, field->name, @@ -536,51 +661,32 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, /* Show a variables in kprobe event format */ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) { - Dwarf_Attribute attr; Dwarf_Die die_mem; - Dwarf_Op *expr; - size_t nexpr; int ret; - if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL) - goto error; - /* TODO: handle more than 1 exprs */ - ret = dwarf_getlocation_addr(&attr, pf->addr, &expr, &nexpr, 1); - if (ret <= 0 || nexpr == 0) - goto error; + pr_debug("Converting variable %s into trace event.\n", + dwarf_diename(vr_die)); - ret = convert_location(expr, pf); + ret = convert_variable_location(vr_die, pf); if (ret == 0 && pf->pvar->field) { ret = convert_variable_fields(vr_die, pf->pvar->var, pf->pvar->field, &pf->tvar->ref, &die_mem); vr_die = &die_mem; } - if (ret == 0) { - if (pf->pvar->type) { - pf->tvar->type = strdup(pf->pvar->type); - if (pf->tvar->type == NULL) - ret = -ENOMEM; - } else - ret = convert_variable_type(vr_die, pf->tvar); - } + if (ret == 0) + ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type); /* *expr will be cached in libdw. Don't free it. */ return ret; -error: - /* TODO: Support const_value */ - pr_err("Failed to find the location of %s at this address.\n" - " Perhaps, it has been optimized out.\n", pf->pvar->var); - return -ENOENT; } /* Find a variable in a subprogram die */ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) { - Dwarf_Die vr_die; + Dwarf_Die vr_die, *scopes; char buf[32], *ptr; - int ret; + int ret, nscopes; - /* TODO: Support arrays */ if (pf->pvar->name) pf->tvar->name = strdup(pf->pvar->name); else { @@ -607,18 +713,32 @@ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) pr_debug("Searching '%s' variable in context.\n", pf->pvar->var); /* Search child die for local variables and parameters. */ - if (!die_find_variable(sp_die, pf->pvar->var, &vr_die)) { + if (die_find_variable(sp_die, pf->pvar->var, &vr_die)) + ret = convert_variable(&vr_die, pf); + else { + /* Search upper class */ + nscopes = dwarf_getscopes_die(sp_die, &scopes); + if (nscopes > 0) { + ret = dwarf_getscopevar(scopes, nscopes, pf->pvar->var, + 0, NULL, 0, 0, &vr_die); + if (ret >= 0) + ret = convert_variable(&vr_die, pf); + else + ret = -ENOENT; + free(scopes); + } else + ret = -ENOENT; + } + if (ret < 0) pr_warning("Failed to find '%s' in this function.\n", pf->pvar->var); - return -ENOENT; - } - return convert_variable(&vr_die, pf); + return ret; } /* Show a probe point to output buffer */ static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf) { - struct kprobe_trace_event *tev; + struct probe_trace_event *tev; Dwarf_Addr eaddr; Dwarf_Die die_mem; const char *name; @@ -683,7 +803,7 @@ static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf) /* Find each argument */ tev->nargs = pf->pev->nargs; - tev->args = zalloc(sizeof(struct kprobe_trace_arg) * tev->nargs); + tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); if (tev->args == NULL) return -ENOMEM; for (i = 0; i < pf->pev->nargs; i++) { @@ -897,7 +1017,7 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) /* Check tag and diename */ if (dwarf_tag(sp_die) != DW_TAG_subprogram || - die_compare_name(sp_die, pp->function) != 0) + !die_compare_name(sp_die, pp->function)) return DWARF_CB_OK; pf->fname = dwarf_decl_file(sp_die); @@ -940,9 +1060,9 @@ static int find_probe_point_by_func(struct probe_finder *pf) return _param.retval; } -/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */ -int find_kprobe_trace_events(int fd, struct perf_probe_event *pev, - struct kprobe_trace_event **tevs, int max_tevs) +/* Find probe_trace_events specified by perf_probe_event from debuginfo */ +int find_probe_trace_events(int fd, struct perf_probe_event *pev, + struct probe_trace_event **tevs, int max_tevs) { struct probe_finder pf = {.pev = pev, .max_tevs = max_tevs}; struct perf_probe_point *pp = &pev->point; @@ -952,7 +1072,7 @@ int find_kprobe_trace_events(int fd, struct perf_probe_event *pev, Dwarf *dbg; int ret = 0; - pf.tevs = zalloc(sizeof(struct kprobe_trace_event) * max_tevs); + pf.tevs = zalloc(sizeof(struct probe_trace_event) * max_tevs); if (pf.tevs == NULL) return -ENOMEM; *tevs = pf.tevs; @@ -1096,7 +1216,7 @@ end: static int line_range_add_line(const char *src, unsigned int lineno, struct line_range *lr) { - /* Copy real path */ + /* Copy source path */ if (!lr->path) { lr->path = strdup(src); if (lr->path == NULL) @@ -1220,7 +1340,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) struct line_range *lr = lf->lr; if (dwarf_tag(sp_die) == DW_TAG_subprogram && - die_compare_name(sp_die, lr->function) == 0) { + die_compare_name(sp_die, lr->function)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset); @@ -1263,6 +1383,7 @@ int find_line_range(int fd, struct line_range *lr) size_t cuhl; Dwarf_Die *diep; Dwarf *dbg; + const char *comp_dir; dbg = dwarf_begin(fd, DWARF_C_READ); if (!dbg) { @@ -1298,7 +1419,18 @@ int find_line_range(int fd, struct line_range *lr) } off = noff; } - pr_debug("path: %lx\n", (unsigned long)lr->path); + + /* Store comp_dir */ + if (lf.found) { + comp_dir = cu_get_comp_dir(&lf.cu_die); + if (comp_dir) { + lr->comp_dir = strdup(comp_dir); + if (!lr->comp_dir) + ret = -ENOMEM; + } + } + + pr_debug("path: %s\n", lr->path); dwarf_end(dbg); return (ret < 0) ? ret : lf.found; diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index e1f61dcd18f..4507d519f18 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -16,9 +16,9 @@ static inline int is_c_varname(const char *name) } #ifdef DWARF_SUPPORT -/* Find kprobe_trace_events specified by perf_probe_event from debuginfo */ -extern int find_kprobe_trace_events(int fd, struct perf_probe_event *pev, - struct kprobe_trace_event **tevs, +/* Find probe_trace_events specified by perf_probe_event from debuginfo */ +extern int find_probe_trace_events(int fd, struct perf_probe_event *pev, + struct probe_trace_event **tevs, int max_tevs); /* Find a perf_probe_point from debuginfo */ @@ -33,7 +33,7 @@ extern int find_line_range(int fd, struct line_range *lr); struct probe_finder { struct perf_probe_event *pev; /* Target probe event */ - struct kprobe_trace_event *tevs; /* Result trace events */ + struct probe_trace_event *tevs; /* Result trace events */ int ntevs; /* Number of trace events */ int max_tevs; /* Max number of trace events */ @@ -50,7 +50,7 @@ struct probe_finder { #endif Dwarf_Op *fb_ops; /* Frame base attribute */ struct perf_probe_arg *pvar; /* Current target variable */ - struct kprobe_trace_arg *tvar; /* Current result variable */ + struct probe_trace_arg *tvar; /* Current result variable */ }; struct line_finder { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c422cd67631..fa9d652c2dc 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -27,8 +27,10 @@ static int perf_session__open(struct perf_session *self, bool force) self->fd = open(self->filename, O_RDONLY); if (self->fd < 0) { - pr_err("failed to open file: %s", self->filename); - if (!strcmp(self->filename, "perf.data")) + int err = errno; + + pr_err("failed to open %s: %s", self->filename, strerror(err)); + if (err == ENOENT && !strcmp(self->filename, "perf.data")) pr_err(" (try 'perf record' first)"); pr_err("\n"); return -errno; @@ -77,6 +79,12 @@ int perf_session__create_kernel_maps(struct perf_session *self) return ret; } +static void perf_session__destroy_kernel_maps(struct perf_session *self) +{ + machine__destroy_kernel_maps(&self->host_machine); + machines__destroy_guest_kernel_maps(&self->machines); +} + struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe) { size_t len = filename ? strlen(filename) + 1 : 0; @@ -94,8 +102,6 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc self->hists_tree = RB_ROOT; self->last_match = NULL; self->mmap_window = 32; - self->cwd = NULL; - self->cwdlen = 0; self->machines = RB_ROOT; self->repipe = repipe; INIT_LIST_HEAD(&self->ordered_samples.samples_head); @@ -124,16 +130,43 @@ out_delete: return NULL; } +static void perf_session__delete_dead_threads(struct perf_session *self) +{ + struct thread *n, *t; + + list_for_each_entry_safe(t, n, &self->dead_threads, node) { + list_del(&t->node); + thread__delete(t); + } +} + +static void perf_session__delete_threads(struct perf_session *self) +{ + struct rb_node *nd = rb_first(&self->threads); + + while (nd) { + struct thread *t = rb_entry(nd, struct thread, rb_node); + + rb_erase(&t->rb_node, &self->threads); + nd = rb_next(nd); + thread__delete(t); + } +} + void perf_session__delete(struct perf_session *self) { perf_header__exit(&self->header); + perf_session__destroy_kernel_maps(self); + perf_session__delete_dead_threads(self); + perf_session__delete_threads(self); + machine__exit(&self->host_machine); close(self->fd); - free(self->cwd); free(self); } void perf_session__remove_thread(struct perf_session *self, struct thread *th) { + self->last_match = NULL; rb_erase(&th->rb_node, &self->threads); /* * We may have references to this thread, for instance in some hist_entry @@ -830,23 +863,6 @@ int perf_session__process_events(struct perf_session *self, if (perf_session__register_idle_thread(self) == NULL) return -ENOMEM; - if (!symbol_conf.full_paths) { - char bf[PATH_MAX]; - - if (getcwd(bf, sizeof(bf)) == NULL) { - err = -errno; -out_getcwd_err: - pr_err("failed to get the current directory\n"); - goto out_err; - } - self->cwd = strdup(bf); - if (self->cwd == NULL) { - err = -ENOMEM; - goto out_getcwd_err; - } - self->cwdlen = strlen(self->cwd); - } - if (!self->fd_pipe) err = __perf_session__process_events(self, self->header.data_offset, @@ -854,7 +870,7 @@ out_getcwd_err: self->size, ops); else err = __perf_session__process_pipe_events(self, ops); -out_err: + return err; } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 2316cb5a411..1c61a4f4aa8 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,4 +1,5 @@ #include "sort.h" +#include "hist.h" regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; @@ -10,10 +11,6 @@ int sort__has_parent = 0; enum sort_type sort__first_dimension; -unsigned int dsos__col_width; -unsigned int comms__col_width; -unsigned int threads__col_width; -static unsigned int parent_symbol__col_width; char * field_sep; LIST_HEAD(hist_entry__sort_list); @@ -28,12 +25,14 @@ static int hist_entry__sym_snprintf(struct hist_entry *self, char *bf, size_t size, unsigned int width); static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf, size_t size, unsigned int width); +static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width); struct sort_entry sort_thread = { .se_header = "Command: Pid", .se_cmp = sort__thread_cmp, .se_snprintf = hist_entry__thread_snprintf, - .se_width = &threads__col_width, + .se_width_idx = HISTC_THREAD, }; struct sort_entry sort_comm = { @@ -41,27 +40,35 @@ struct sort_entry sort_comm = { .se_cmp = sort__comm_cmp, .se_collapse = sort__comm_collapse, .se_snprintf = hist_entry__comm_snprintf, - .se_width = &comms__col_width, + .se_width_idx = HISTC_COMM, }; struct sort_entry sort_dso = { .se_header = "Shared Object", .se_cmp = sort__dso_cmp, .se_snprintf = hist_entry__dso_snprintf, - .se_width = &dsos__col_width, + .se_width_idx = HISTC_DSO, }; struct sort_entry sort_sym = { .se_header = "Symbol", .se_cmp = sort__sym_cmp, .se_snprintf = hist_entry__sym_snprintf, + .se_width_idx = HISTC_SYMBOL, }; struct sort_entry sort_parent = { .se_header = "Parent symbol", .se_cmp = sort__parent_cmp, .se_snprintf = hist_entry__parent_snprintf, - .se_width = &parent_symbol__col_width, + .se_width_idx = HISTC_PARENT, +}; + +struct sort_entry sort_cpu = { + .se_header = "CPU", + .se_cmp = sort__cpu_cmp, + .se_snprintf = hist_entry__cpu_snprintf, + .se_width_idx = HISTC_CPU, }; struct sort_dimension { @@ -76,6 +83,7 @@ static struct sort_dimension sort_dimensions[] = { { .name = "dso", .entry = &sort_dso, }, { .name = "symbol", .entry = &sort_sym, }, { .name = "parent", .entry = &sort_parent, }, + { .name = "cpu", .entry = &sort_cpu, }, }; int64_t cmp_null(void *l, void *r) @@ -242,6 +250,20 @@ static int hist_entry__parent_snprintf(struct hist_entry *self, char *bf, self->parent ? self->parent->name : "[other]"); } +/* --sort cpu */ + +int64_t +sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->cpu - left->cpu; +} + +static int hist_entry__cpu_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*d", width, self->cpu); +} + int sort_dimension__add(const char *tok) { unsigned int i; @@ -281,6 +303,8 @@ int sort_dimension__add(const char *tok) sort__first_dimension = SORT_SYM; else if (!strcmp(sd->name, "parent")) sort__first_dimension = SORT_PARENT; + else if (!strcmp(sd->name, "cpu")) + sort__first_dimension = SORT_CPU; } list_add_tail(&sd->entry->list, &hist_entry__sort_list); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 0d61c4082f4..46e531d09e8 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -36,11 +36,14 @@ extern struct sort_entry sort_comm; extern struct sort_entry sort_dso; extern struct sort_entry sort_sym; extern struct sort_entry sort_parent; -extern unsigned int dsos__col_width; -extern unsigned int comms__col_width; -extern unsigned int threads__col_width; extern enum sort_type sort__first_dimension; +/** + * struct hist_entry - histogram entry + * + * @row_offset - offset from the first callchain expanded to appear on screen + * @nr_rows - rows expanded in callchain, recalculated on folding/unfolding + */ struct hist_entry { struct rb_node rb_node; u64 period; @@ -51,7 +54,14 @@ struct hist_entry { struct map_symbol ms; struct thread *thread; u64 ip; + s32 cpu; u32 nr_events; + + /* XXX These two should move to some tree widget lib */ + u16 row_offset; + u16 nr_rows; + + bool init_have_children; char level; u8 filtered; struct symbol *parent; @@ -68,7 +78,8 @@ enum sort_type { SORT_COMM, SORT_DSO, SORT_SYM, - SORT_PARENT + SORT_PARENT, + SORT_CPU, }; /* @@ -84,7 +95,7 @@ struct sort_entry { int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *); int (*se_snprintf)(struct hist_entry *self, char *bf, size_t size, unsigned int width); - unsigned int *se_width; + u8 se_width_idx; bool elide; }; @@ -104,6 +115,7 @@ extern int64_t sort__comm_collapse(struct hist_entry *, struct hist_entry *); extern int64_t sort__dso_cmp(struct hist_entry *, struct hist_entry *); extern int64_t sort__sym_cmp(struct hist_entry *, struct hist_entry *); extern int64_t sort__parent_cmp(struct hist_entry *, struct hist_entry *); +int64_t sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right); extern size_t sort__parent_print(FILE *, struct hist_entry *, unsigned int); extern int sort_dimension__add(const char *); void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list, diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 5b276833e2b..6f0dd90c36c 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -12,6 +12,7 @@ #include <fcntl.h> #include <unistd.h> #include "build-id.h" +#include "debug.h" #include "symbol.h" #include "strlist.h" @@ -25,6 +26,8 @@ #define NT_GNU_BUILD_ID 3 #endif +static bool dso__build_id_equal(const struct dso *self, u8 *build_id); +static int elf_read_build_id(Elf *elf, void *bf, size_t size); static void dsos__add(struct list_head *head, struct dso *dso); static struct map *map__new2(u64 start, struct dso *dso, enum map_type type); static int dso__load_kernel_sym(struct dso *self, struct map *map, @@ -40,6 +43,14 @@ struct symbol_conf symbol_conf = { .try_vmlinux_path = true, }; +int dso__name_len(const struct dso *self) +{ + if (verbose) + return self->long_name_len; + + return self->short_name_len; +} + bool dso__loaded(const struct dso *self, enum map_type type) { return self->loaded & (1 << type); @@ -215,7 +226,9 @@ void dso__delete(struct dso *self) int i; for (i = 0; i < MAP__NR_TYPES; ++i) symbols__delete(&self->symbols[i]); - if (self->long_name != self->name) + if (self->sname_alloc) + free((char *)self->short_name); + if (self->lname_alloc) free(self->long_name); free(self); } @@ -933,8 +946,28 @@ static bool elf_sec__is_a(GElf_Shdr *self, Elf_Data *secstrs, enum map_type type } } +static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr) +{ + Elf_Scn *sec = NULL; + GElf_Shdr shdr; + size_t cnt = 1; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + gelf_getshdr(sec, &shdr); + + if ((addr >= shdr.sh_addr) && + (addr < (shdr.sh_addr + shdr.sh_size))) + return cnt; + + ++cnt; + } + + return -1; +} + static int dso__load_sym(struct dso *self, struct map *map, const char *name, - int fd, symbol_filter_t filter, int kmodule) + int fd, symbol_filter_t filter, int kmodule, + int want_symtab) { struct kmap *kmap = self->kernel ? map__kmap(map) : NULL; struct map *curr_map = map; @@ -944,31 +977,51 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, int err = -1; uint32_t idx; GElf_Ehdr ehdr; - GElf_Shdr shdr; - Elf_Data *syms; + GElf_Shdr shdr, opdshdr; + Elf_Data *syms, *opddata = NULL; GElf_Sym sym; - Elf_Scn *sec, *sec_strndx; + Elf_Scn *sec, *sec_strndx, *opdsec; Elf *elf; int nr = 0; + size_t opdidx = 0; elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); if (elf == NULL) { - pr_err("%s: cannot read %s ELF file.\n", __func__, name); + pr_debug("%s: cannot read %s ELF file.\n", __func__, name); goto out_close; } if (gelf_getehdr(elf, &ehdr) == NULL) { - pr_err("%s: cannot get elf header.\n", __func__); + pr_debug("%s: cannot get elf header.\n", __func__); goto out_elf_end; } + /* Always reject images with a mismatched build-id: */ + if (self->has_build_id) { + u8 build_id[BUILD_ID_SIZE]; + + if (elf_read_build_id(elf, build_id, + BUILD_ID_SIZE) != BUILD_ID_SIZE) + goto out_elf_end; + + if (!dso__build_id_equal(self, build_id)) + goto out_elf_end; + } + sec = elf_section_by_name(elf, &ehdr, &shdr, ".symtab", NULL); if (sec == NULL) { + if (want_symtab) + goto out_elf_end; + sec = elf_section_by_name(elf, &ehdr, &shdr, ".dynsym", NULL); if (sec == NULL) goto out_elf_end; } + opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx); + if (opdsec) + opddata = elf_rawdata(opdsec, NULL); + syms = elf_getdata(sec, NULL); if (syms == NULL) goto out_elf_end; @@ -1013,6 +1066,13 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name, if (!is_label && !elf_sym__is_a(&sym, map->type)) continue; + if (opdsec && sym.st_shndx == opdidx) { + u32 offset = sym.st_value - opdshdr.sh_addr; + u64 *opd = opddata->d_buf + offset; + sym.st_value = *opd; + sym.st_shndx = elf_addr_to_index(elf, sym.st_value); + } + sec = elf_getscn(elf, sym.st_shndx); if (!sec) goto out_elf_end; @@ -1151,37 +1211,26 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) */ #define NOTE_ALIGN(n) (((n) + 3) & -4U) -int filename__read_build_id(const char *filename, void *bf, size_t size) +static int elf_read_build_id(Elf *elf, void *bf, size_t size) { - int fd, err = -1; + int err = -1; GElf_Ehdr ehdr; GElf_Shdr shdr; Elf_Data *data; Elf_Scn *sec; Elf_Kind ek; void *ptr; - Elf *elf; if (size < BUILD_ID_SIZE) goto out; - fd = open(filename, O_RDONLY); - if (fd < 0) - goto out; - - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) { - pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); - goto out_close; - } - ek = elf_kind(elf); if (ek != ELF_K_ELF) - goto out_elf_end; + goto out; if (gelf_getehdr(elf, &ehdr) == NULL) { pr_err("%s: cannot get elf header.\n", __func__); - goto out_elf_end; + goto out; } sec = elf_section_by_name(elf, &ehdr, &shdr, @@ -1190,12 +1239,12 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) sec = elf_section_by_name(elf, &ehdr, &shdr, ".notes", NULL); if (sec == NULL) - goto out_elf_end; + goto out; } data = elf_getdata(sec, NULL); if (data == NULL) - goto out_elf_end; + goto out; ptr = data->d_buf; while (ptr < (data->d_buf + data->d_size)) { @@ -1217,7 +1266,31 @@ int filename__read_build_id(const char *filename, void *bf, size_t size) } ptr += descsz; } -out_elf_end: + +out: + return err; +} + +int filename__read_build_id(const char *filename, void *bf, size_t size) +{ + int fd, err = -1; + Elf *elf; + + if (size < BUILD_ID_SIZE) + goto out; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); + goto out_close; + } + + err = elf_read_build_id(elf, bf, size); + elf_end(elf); out_close: close(fd); @@ -1293,11 +1366,11 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter) { int size = PATH_MAX; char *name; - u8 build_id[BUILD_ID_SIZE]; int ret = -1; int fd; struct machine *machine; const char *root_dir; + int want_symtab; dso__set_loaded(self, map->type); @@ -1324,13 +1397,18 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter) return ret; } - self->origin = DSO__ORIG_BUILD_ID_CACHE; - if (dso__build_id_filename(self, name, size) != NULL) - goto open_file; -more: - do { - self->origin++; + /* Iterate over candidate debug images. + * On the first pass, only load images if they have a full symtab. + * Failing that, do a second pass where we accept .dynsym also + */ + for (self->origin = DSO__ORIG_BUILD_ID_CACHE, want_symtab = 1; + self->origin != DSO__ORIG_NOT_FOUND; + self->origin++) { switch (self->origin) { + case DSO__ORIG_BUILD_ID_CACHE: + if (dso__build_id_filename(self, name, size) == NULL) + continue; + break; case DSO__ORIG_FEDORA: snprintf(name, size, "/usr/lib/debug%s.debug", self->long_name); @@ -1339,21 +1417,20 @@ more: snprintf(name, size, "/usr/lib/debug%s", self->long_name); break; - case DSO__ORIG_BUILDID: - if (filename__read_build_id(self->long_name, build_id, - sizeof(build_id))) { - char build_id_hex[BUILD_ID_SIZE * 2 + 1]; - build_id__sprintf(build_id, sizeof(build_id), - build_id_hex); - snprintf(name, size, - "/usr/lib/debug/.build-id/%.2s/%s.debug", - build_id_hex, build_id_hex + 2); - if (self->has_build_id) - goto compare_build_id; - break; + case DSO__ORIG_BUILDID: { + char build_id_hex[BUILD_ID_SIZE * 2 + 1]; + + if (!self->has_build_id) + continue; + + build_id__sprintf(self->build_id, + sizeof(self->build_id), + build_id_hex); + snprintf(name, size, + "/usr/lib/debug/.build-id/%.2s/%s.debug", + build_id_hex, build_id_hex + 2); } - self->origin++; - /* Fall thru */ + break; case DSO__ORIG_DSO: snprintf(name, size, "%s", self->long_name); break; @@ -1366,36 +1443,41 @@ more: break; default: - goto out; + /* + * If we wanted a full symtab but no image had one, + * relax our requirements and repeat the search. + */ + if (want_symtab) { + want_symtab = 0; + self->origin = DSO__ORIG_BUILD_ID_CACHE; + } else + continue; } - if (self->has_build_id) { - if (filename__read_build_id(name, build_id, - sizeof(build_id)) < 0) - goto more; -compare_build_id: - if (!dso__build_id_equal(self, build_id)) - goto more; - } -open_file: + /* Name is now the name of the next image to try */ fd = open(name, O_RDONLY); - } while (fd < 0); + if (fd < 0) + continue; - ret = dso__load_sym(self, map, name, fd, filter, 0); - close(fd); + ret = dso__load_sym(self, map, name, fd, filter, 0, + want_symtab); + close(fd); - /* - * Some people seem to have debuginfo files _WITHOUT_ debug info!?!? - */ - if (!ret) - goto more; + /* + * Some people seem to have debuginfo files _WITHOUT_ debug + * info!?!? + */ + if (!ret) + continue; - if (ret > 0) { - int nr_plt = dso__synthesize_plt_symbols(self, map, filter); - if (nr_plt > 0) - ret += nr_plt; + if (ret > 0) { + int nr_plt = dso__synthesize_plt_symbols(self, map, filter); + if (nr_plt > 0) + ret += nr_plt; + break; + } } -out: + free(name); if (ret < 0 && strstr(self->name, " (deleted)") != NULL) return 0; @@ -1494,6 +1576,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *self, goto out; } dso__set_long_name(map->dso, long_name); + map->dso->lname_alloc = 1; dso__kernel_module_get_build_id(map->dso, ""); } } @@ -1656,36 +1739,12 @@ static int dso__load_vmlinux(struct dso *self, struct map *map, { int err = -1, fd; - if (self->has_build_id) { - u8 build_id[BUILD_ID_SIZE]; - - if (filename__read_build_id(vmlinux, build_id, - sizeof(build_id)) < 0) { - pr_debug("No build_id in %s, ignoring it\n", vmlinux); - return -1; - } - if (!dso__build_id_equal(self, build_id)) { - char expected_build_id[BUILD_ID_SIZE * 2 + 1], - vmlinux_build_id[BUILD_ID_SIZE * 2 + 1]; - - build_id__sprintf(self->build_id, - sizeof(self->build_id), - expected_build_id); - build_id__sprintf(build_id, sizeof(build_id), - vmlinux_build_id); - pr_debug("build_id in %s is %s while expected is %s, " - "ignoring it\n", vmlinux, vmlinux_build_id, - expected_build_id); - return -1; - } - } - fd = open(vmlinux, O_RDONLY); if (fd < 0) return -1; dso__set_loaded(self, map->type); - err = dso__load_sym(self, map, vmlinux, fd, filter, 0); + err = dso__load_sym(self, map, vmlinux, fd, filter, 0, 0); close(fd); if (err > 0) @@ -2048,6 +2107,36 @@ int __machine__create_kernel_maps(struct machine *self, struct dso *kernel) return 0; } +void machine__destroy_kernel_maps(struct machine *self) +{ + enum map_type type; + + for (type = 0; type < MAP__NR_TYPES; ++type) { + struct kmap *kmap; + + if (self->vmlinux_maps[type] == NULL) + continue; + + kmap = map__kmap(self->vmlinux_maps[type]); + map_groups__remove(&self->kmaps, self->vmlinux_maps[type]); + if (kmap->ref_reloc_sym) { + /* + * ref_reloc_sym is shared among all maps, so free just + * on one of them. + */ + if (type == MAP__FUNCTION) { + free((char *)kmap->ref_reloc_sym->name); + kmap->ref_reloc_sym->name = NULL; + free(kmap->ref_reloc_sym); + } + kmap->ref_reloc_sym = NULL; + } + + map__delete(self->vmlinux_maps[type]); + self->vmlinux_maps[type] = NULL; + } +} + int machine__create_kernel_maps(struct machine *self) { struct dso *kernel = machine__create_kernel(self); @@ -2189,6 +2278,15 @@ out_free_comm_list: return -1; } +void symbol__exit(void) +{ + strlist__delete(symbol_conf.sym_list); + strlist__delete(symbol_conf.dso_list); + strlist__delete(symbol_conf.comm_list); + vmlinux_path__exit(); + symbol_conf.sym_list = symbol_conf.dso_list = symbol_conf.comm_list = NULL; +} + int machines__create_kernel_maps(struct rb_root *self, pid_t pid) { struct machine *machine = machines__findnew(self, pid); @@ -2283,6 +2381,19 @@ failure: return ret; } +void machines__destroy_guest_kernel_maps(struct rb_root *self) +{ + struct rb_node *next = rb_first(self); + + while (next) { + struct machine *pos = rb_entry(next, struct machine, rb_node); + + next = rb_next(&pos->rb_node); + rb_erase(&pos->rb_node, self); + machine__delete(pos); + } +} + int machine__load_kallsyms(struct machine *self, const char *filename, enum map_type type, symbol_filter_t filter) { diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 5e02d2c1715..906be20011d 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -9,8 +9,6 @@ #include <linux/rbtree.h> #include <stdio.h> -#define DEBUG_CACHE_DIR ".debug" - #ifdef HAVE_CPLUS_DEMANGLE extern char *cplus_demangle(const char *, int); @@ -70,9 +68,9 @@ struct symbol_conf { show_nr_samples, use_callchain, exclude_other, - full_paths, show_cpu_utilization; const char *vmlinux_name, + *source_prefix, *field_sep; const char *default_guest_vmlinux_name, *default_guest_kallsyms, @@ -103,6 +101,8 @@ struct ref_reloc_sym { struct map_symbol { struct map *map; struct symbol *sym; + bool unfolded; + bool has_children; }; struct addr_location { @@ -112,7 +112,8 @@ struct addr_location { u64 addr; char level; bool filtered; - unsigned int cpumode; + u8 cpumode; + s32 cpu; }; enum dso_kernel_type { @@ -125,12 +126,14 @@ struct dso { struct list_head node; struct rb_root symbols[MAP__NR_TYPES]; struct rb_root symbol_names[MAP__NR_TYPES]; + enum dso_kernel_type kernel; u8 adjust_symbols:1; u8 slen_calculated:1; u8 has_build_id:1; - enum dso_kernel_type kernel; u8 hit:1; u8 annotate_warned:1; + u8 sname_alloc:1; + u8 lname_alloc:1; unsigned char origin; u8 sorted_by_name; u8 loaded; @@ -146,6 +149,8 @@ struct dso *dso__new(const char *name); struct dso *dso__new_kernel(const char *name); void dso__delete(struct dso *self); +int dso__name_len(const struct dso *self); + bool dso__loaded(const struct dso *self, enum map_type type); bool dso__sorted_by_name(const struct dso *self, enum map_type type); @@ -207,13 +212,16 @@ int kallsyms__parse(const char *filename, void *arg, int (*process_symbol)(void *arg, const char *name, char type, u64 start)); +void machine__destroy_kernel_maps(struct machine *self); int __machine__create_kernel_maps(struct machine *self, struct dso *kernel); int machine__create_kernel_maps(struct machine *self); int machines__create_kernel_maps(struct rb_root *self, pid_t pid); int machines__create_guest_kernel_maps(struct rb_root *self); +void machines__destroy_guest_kernel_maps(struct rb_root *self); int symbol__init(void); +void symbol__exit(void); bool symbol_type__is_a(char symbol_type, enum map_type map_type); size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 9a448b47400..8c72d888e44 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -62,6 +62,13 @@ static struct thread *thread__new(pid_t pid) return self; } +void thread__delete(struct thread *self) +{ + map_groups__exit(&self->mg); + free(self->comm); + free(self); +} + int thread__set_comm(struct thread *self, const char *comm) { int err; diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index ee6bbcf277c..688500ff826 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -20,6 +20,8 @@ struct thread { struct perf_session; +void thread__delete(struct thread *self); + int find_all_tid(int pid, pid_t ** all_tid); int thread__set_comm(struct thread *self, const char *comm); int thread__comm_len(struct thread *self); diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 4e8b6b0c551..f380fed7435 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -89,6 +89,7 @@ extern const char *graph_line; extern const char *graph_dotted_line; +extern char buildid_dir[]; /* On most systems <limits.h> would have given us this, but * not on some systems (e.g. GNU/Hurd). @@ -152,6 +153,8 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2))) extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN); extern int prefixcmp(const char *str, const char *prefix); +extern void set_buildid_dir(void); +extern void disable_buildid_cache(void); static inline const char *skip_prefix(const char *str, const char *prefix) { |