diff options
199 files changed, 2308 insertions, 1163 deletions
diff --git a/Documentation/input/event-codes.txt b/Documentation/input/event-codes.txt new file mode 100644 index 00000000000..23fcb05175b --- /dev/null +++ b/Documentation/input/event-codes.txt @@ -0,0 +1,262 @@ +The input protocol uses a map of types and codes to express input device values +to userspace. This document describes the types and codes and how and when they +may be used. + +A single hardware event generates multiple input events. Each input event +contains the new value of a single data item. A special event type, EV_SYN, is +used to separate input events into packets of input data changes occurring at +the same moment in time. In the following, the term "event" refers to a single +input event encompassing a type, code, and value. + +The input protocol is a stateful protocol. Events are emitted only when values +of event codes have changed. However, the state is maintained within the Linux +input subsystem; drivers do not need to maintain the state and may attempt to +emit unchanged values without harm. Userspace may obtain the current state of +event code values using the EVIOCG* ioctls defined in linux/input.h. The event +reports supported by a device are also provided by sysfs in +class/input/event*/device/capabilities/, and the properties of a device are +provided in class/input/event*/device/properties. + +Types: +========== +Types are groupings of codes under a logical input construct. Each type has a +set of applicable codes to be used in generating events. See the Codes section +for details on valid codes for each type. + +* EV_SYN: + - Used as markers to separate events. Events may be separated in time or in + space, such as with the multitouch protocol. + +* EV_KEY: + - Used to describe state changes of keyboards, buttons, or other key-like + devices. + +* EV_REL: + - Used to describe relative axis value changes, e.g. moving the mouse 5 units + to the left. + +* EV_ABS: + - Used to describe absolute axis value changes, e.g. describing the + coordinates of a touch on a touchscreen. + +* EV_MSC: + - Used to describe miscellaneous input data that do not fit into other types. + +* EV_SW: + - Used to describe binary state input switches. + +* EV_LED: + - Used to turn LEDs on devices on and off. + +* EV_SND: + - Used to output sound to devices. + +* EV_REP: + - Used for autorepeating devices. + +* EV_FF: + - Used to send force feedback commands to an input device. + +* EV_PWR: + - A special type for power button and switch input. + +* EV_FF_STATUS: + - Used to receive force feedback device status. + +Codes: +========== +Codes define the precise type of event. + +EV_SYN: +---------- +EV_SYN event values are undefined. Their usage is defined only by when they are +sent in the evdev event stream. + +* SYN_REPORT: + - Used to synchronize and separate events into packets of input data changes + occurring at the same moment in time. For example, motion of a mouse may set + the REL_X and REL_Y values for one motion, then emit a SYN_REPORT. The next + motion will emit more REL_X and REL_Y values and send another SYN_REPORT. + +* SYN_CONFIG: + - TBD + +* SYN_MT_REPORT: + - Used to synchronize and separate touch events. See the + multi-touch-protocol.txt document for more information. + +* SYN_DROPPED: + - Used to indicate buffer overrun in the evdev client's event queue. + Client should ignore all events up to and including next SYN_REPORT + event and query the device (using EVIOCG* ioctls) to obtain its + current state. + +EV_KEY: +---------- +EV_KEY events take the form KEY_<name> or BTN_<name>. For example, KEY_A is used +to represent the 'A' key on a keyboard. When a key is depressed, an event with +the key's code is emitted with value 1. When the key is released, an event is +emitted with value 0. Some hardware send events when a key is repeated. These +events have a value of 2. In general, KEY_<name> is used for keyboard keys, and +BTN_<name> is used for other types of momentary switch events. + +A few EV_KEY codes have special meanings: + +* BTN_TOOL_<name>: + - These codes are used in conjunction with input trackpads, tablets, and + touchscreens. These devices may be used with fingers, pens, or other tools. + When an event occurs and a tool is used, the corresponding BTN_TOOL_<name> + code should be set to a value of 1. When the tool is no longer interacting + with the input device, the BTN_TOOL_<name> code should be reset to 0. All + trackpads, tablets, and touchscreens should use at least one BTN_TOOL_<name> + code when events are generated. + +* BTN_TOUCH: + BTN_TOUCH is used for touch contact. While an input tool is determined to be + within meaningful physical contact, the value of this property must be set + to 1. Meaningful physical contact may mean any contact, or it may mean + contact conditioned by an implementation defined property. For example, a + touchpad may set the value to 1 only when the touch pressure rises above a + certain value. BTN_TOUCH may be combined with BTN_TOOL_<name> codes. For + example, a pen tablet may set BTN_TOOL_PEN to 1 and BTN_TOUCH to 0 while the + pen is hovering over but not touching the tablet surface. + +Note: For appropriate function of the legacy mousedev emulation driver, +BTN_TOUCH must be the first evdev code emitted in a synchronization frame. + +Note: Historically a touch device with BTN_TOOL_FINGER and BTN_TOUCH was +interpreted as a touchpad by userspace, while a similar device without +BTN_TOOL_FINGER was interpreted as a touchscreen. For backwards compatibility +with current userspace it is recommended to follow this distinction. In the +future, this distinction will be deprecated and the device properties ioctl +EVIOCGPROP, defined in linux/input.h, will be used to convey the device type. + +* BTN_TOOL_FINGER, BTN_TOOL_DOUBLETAP, BTN_TOOL_TRIPLETAP, BTN_TOOL_QUADTAP: + - These codes denote one, two, three, and four finger interaction on a + trackpad or touchscreen. For example, if the user uses two fingers and moves + them on the touchpad in an effort to scroll content on screen, + BTN_TOOL_DOUBLETAP should be set to value 1 for the duration of the motion. + Note that all BTN_TOOL_<name> codes and the BTN_TOUCH code are orthogonal in + purpose. A trackpad event generated by finger touches should generate events + for one code from each group. At most only one of these BTN_TOOL_<name> + codes should have a value of 1 during any synchronization frame. + +Note: Historically some drivers emitted multiple of the finger count codes with +a value of 1 in the same synchronization frame. This usage is deprecated. + +Note: In multitouch drivers, the input_mt_report_finger_count() function should +be used to emit these codes. Please see multi-touch-protocol.txt for details. + +EV_REL: +---------- +EV_REL events describe relative changes in a property. For example, a mouse may +move to the left by a certain number of units, but its absolute position in +space is unknown. If the absolute position is known, EV_ABS codes should be used +instead of EV_REL codes. + +A few EV_REL codes have special meanings: + +* REL_WHEEL, REL_HWHEEL: + - These codes are used for vertical and horizontal scroll wheels, + respectively. + +EV_ABS: +---------- +EV_ABS events describe absolute changes in a property. For example, a touchpad +may emit coordinates for a touch location. + +A few EV_ABS codes have special meanings: + +* ABS_DISTANCE: + - Used to describe the distance of a tool from an interaction surface. This + event should only be emitted while the tool is hovering, meaning in close + proximity of the device and while the value of the BTN_TOUCH code is 0. If + the input device may be used freely in three dimensions, consider ABS_Z + instead. + +* ABS_MT_<name>: + - Used to describe multitouch input events. Please see + multi-touch-protocol.txt for details. + +EV_SW: +---------- +EV_SW events describe stateful binary switches. For example, the SW_LID code is +used to denote when a laptop lid is closed. + +Upon binding to a device or resuming from suspend, a driver must report +the current switch state. This ensures that the device, kernel, and userspace +state is in sync. + +Upon resume, if the switch state is the same as before suspend, then the input +subsystem will filter out the duplicate switch state reports. The driver does +not need to keep the state of the switch at any time. + +EV_MSC: +---------- +EV_MSC events are used for input and output events that do not fall under other +categories. + +EV_LED: +---------- +EV_LED events are used for input and output to set and query the state of +various LEDs on devices. + +EV_REP: +---------- +EV_REP events are used for specifying autorepeating events. + +EV_SND: +---------- +EV_SND events are used for sending sound commands to simple sound output +devices. + +EV_FF: +---------- +EV_FF events are used to initialize a force feedback capable device and to cause +such device to feedback. + +EV_PWR: +---------- +EV_PWR events are a special type of event used specifically for power +mangement. Its usage is not well defined. To be addressed later. + +Guidelines: +========== +The guidelines below ensure proper single-touch and multi-finger functionality. +For multi-touch functionality, see the multi-touch-protocol.txt document for +more information. + +Mice: +---------- +REL_{X,Y} must be reported when the mouse moves. BTN_LEFT must be used to report +the primary button press. BTN_{MIDDLE,RIGHT,4,5,etc.} should be used to report +further buttons of the device. REL_WHEEL and REL_HWHEEL should be used to report +scroll wheel events where available. + +Touchscreens: +---------- +ABS_{X,Y} must be reported with the location of the touch. BTN_TOUCH must be +used to report when a touch is active on the screen. +BTN_{MOUSE,LEFT,MIDDLE,RIGHT} must not be reported as the result of touch +contact. BTN_TOOL_<name> events should be reported where possible. + +Trackpads: +---------- +Legacy trackpads that only provide relative position information must report +events like mice described above. + +Trackpads that provide absolute touch position must report ABS_{X,Y} for the +location of the touch. BTN_TOUCH should be used to report when a touch is active +on the trackpad. Where multi-finger support is available, BTN_TOOL_<name> should +be used to report the number of touches active on the trackpad. + +Tablets: +---------- +BTN_TOOL_<name> events must be reported when a stylus or other tool is active on +the tablet. ABS_{X,Y} must be reported with the location of the tool. BTN_TOUCH +should be used to report when the tool is in contact with the tablet. +BTN_{STYLUS,STYLUS2} should be used to report buttons on the tool itself. Any +button may be used for buttons on the tablet except BTN_{MOUSE,LEFT}. +BTN_{0,1,2,etc} are good generic codes for unlabeled buttons. Do not use +meaningful buttons, like BTN_FORWARD, unless the button is labeled for that +purpose on the device. diff --git a/MAINTAINERS b/MAINTAINERS index 649600cb8ec..ec360030628 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -184,10 +184,9 @@ F: Documentation/filesystems/9p.txt F: fs/9p/ A2232 SERIAL BOARD DRIVER -M: Enver Haase <A2232@gmx.net> L: linux-m68k@lists.linux-m68k.org -S: Maintained -F: drivers/char/ser_a2232* +S: Orphan +F: drivers/staging/generic_serial/ser_a2232* AACRAID SCSI RAID DRIVER M: Adaptec OEM Raid Solutions <aacraid@adaptec.com> @@ -877,6 +876,13 @@ F: arch/arm/mach-mv78xx0/ F: arch/arm/mach-orion5x/ F: arch/arm/plat-orion/ +ARM/Orion SoC/Technologic Systems TS-78xx platform support +M: Alexander Clouter <alex@digriz.org.uk> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +W: http://www.digriz.org.uk/ts78xx/kernel +S: Maintained +F: arch/arm/mach-orion5x/ts78xx-* + ARM/MIOA701 MACHINE SUPPORT M: Robert Jarzmik <robert.jarzmik@free.fr> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -1063,7 +1069,7 @@ F: arch/arm/mach-shmobile/ F: drivers/sh/ ARM/TELECHIPS ARM ARCHITECTURE -M: "Hans J. Koch" <hjk@linutronix.de> +M: "Hans J. Koch" <hjk@hansjkoch.de> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/plat-tcc/ @@ -1823,11 +1829,10 @@ S: Maintained F: drivers/platform/x86/compal-laptop.c COMPUTONE INTELLIPORT MULTIPORT CARD -M: "Michael H. Warfield" <mhw@wittsend.com> W: http://www.wittsend.com/computone.html -S: Maintained +S: Orphan F: Documentation/serial/computone.txt -F: drivers/char/ip2/ +F: drivers/staging/tty/ip2/ CONEXANT ACCESSRUNNER USB DRIVER M: Simon Arlott <cxacru@fire.lp0.eu> @@ -2010,7 +2015,7 @@ F: drivers/net/wan/cycx* CYCLADES ASYNC MUX DRIVER W: http://www.cyclades.com/ S: Orphan -F: drivers/char/cyclades.c +F: drivers/tty/cyclades.c F: include/linux/cyclades.h CYCLADES PC300 DRIVER @@ -2124,8 +2129,8 @@ L: Eng.Linux@digi.com W: http://www.digi.com S: Orphan F: Documentation/serial/digiepca.txt -F: drivers/char/epca* -F: drivers/char/digi* +F: drivers/staging/tty/epca* +F: drivers/staging/tty/digi* DIOLAN U2C-12 I2C DRIVER M: Guenter Roeck <guenter.roeck@ericsson.com> @@ -4077,7 +4082,7 @@ F: drivers/video/matrox/matroxfb_* F: include/linux/matroxfb.h MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER -M: "Hans J. Koch" <hjk@linutronix.de> +M: "Hans J. Koch" <hjk@hansjkoch.de> L: lm-sensors@lm-sensors.org S: Maintained F: Documentation/hwmon/max6650 @@ -4192,7 +4197,7 @@ MOXA SMARTIO/INDUSTIO/INTELLIO SERIAL CARD M: Jiri Slaby <jirislaby@gmail.com> S: Maintained F: Documentation/serial/moxa-smartio -F: drivers/char/mxser.* +F: drivers/tty/mxser.* MSI LAPTOP SUPPORT M: "Lee, Chun-Yi" <jlee@novell.com> @@ -4234,7 +4239,7 @@ F: sound/oss/msnd* MULTITECH MULTIPORT CARD (ISICOM) S: Orphan -F: drivers/char/isicom.c +F: drivers/tty/isicom.c F: include/linux/isicom.h MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER @@ -5273,14 +5278,14 @@ F: drivers/memstick/host/r592.* RISCOM8 DRIVER S: Orphan F: Documentation/serial/riscom8.txt -F: drivers/char/riscom8* +F: drivers/staging/tty/riscom8* ROCKETPORT DRIVER P: Comtrol Corp. W: http://www.comtrol.com S: Maintained F: Documentation/serial/rocket.txt -F: drivers/char/rocket* +F: drivers/tty/rocket* ROSE NETWORK LAYER M: Ralf Baechle <ralf@linux-mips.org> @@ -5916,10 +5921,9 @@ F: arch/arm/mach-spear6xx/spear600.c F: arch/arm/mach-spear6xx/spear600_evb.c SPECIALIX IO8+ MULTIPORT SERIAL CARD DRIVER -M: Roger Wolff <R.E.Wolff@BitWizard.nl> -S: Supported +S: Orphan F: Documentation/serial/specialix.txt -F: drivers/char/specialix* +F: drivers/staging/tty/specialix* SPI SUBSYSTEM M: David Brownell <dbrownell@users.sourceforge.net> @@ -5964,7 +5968,6 @@ F: arch/alpha/kernel/srm_env.c STABLE BRANCH M: Greg Kroah-Hartman <greg@kroah.com> -M: Chris Wright <chrisw@sous-sol.org> L: stable@kernel.org S: Maintained @@ -6248,7 +6251,8 @@ M: Greg Ungerer <gerg@uclinux.org> W: http://www.uclinux.org/ L: uclinux-dev@uclinux.org (subscribers-only) S: Maintained -F: arch/m68knommu/ +F: arch/m68k/*/*_no.* +F: arch/m68k/include/asm/*_no.* UCLINUX FOR RENESAS H8/300 (H8300) M: Yoshinori Sato <ysato@users.sourceforge.jp> @@ -6618,7 +6622,7 @@ F: fs/hostfs/ F: fs/hppfs/ USERSPACE I/O (UIO) -M: "Hans J. Koch" <hjk@linutronix.de> +M: "Hans J. Koch" <hjk@hansjkoch.de> M: Greg Kroah-Hartman <gregkh@suse.de> S: Maintained F: Documentation/DocBook/uio-howto.tmpl @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 39 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Flesh-Eating Bats with Fangs # *DOCUMENTATION* diff --git a/arch/alpha/kernel/Makefile b/arch/alpha/kernel/Makefile index 9bb7b858ed2..7a6d908bb86 100644 --- a/arch/alpha/kernel/Makefile +++ b/arch/alpha/kernel/Makefile @@ -4,7 +4,7 @@ extra-y := head.o vmlinux.lds asflags-y := $(KBUILD_CFLAGS) -ccflags-y := -Werror -Wno-sign-compare +ccflags-y := -Wno-sign-compare obj-y := entry.o traps.o process.o init_task.o osf_sys.o irq.o \ irq_alpha.o signal.o setup.o ptrace.o time.o \ diff --git a/arch/alpha/kernel/core_mcpcia.c b/arch/alpha/kernel/core_mcpcia.c index 381fec0af52..da7bcc372f1 100644 --- a/arch/alpha/kernel/core_mcpcia.c +++ b/arch/alpha/kernel/core_mcpcia.c @@ -88,7 +88,7 @@ conf_read(unsigned long addr, unsigned char type1, { unsigned long flags; unsigned long mid = MCPCIA_HOSE2MID(hose->index); - unsigned int stat0, value, temp, cpu; + unsigned int stat0, value, cpu; cpu = smp_processor_id(); @@ -101,7 +101,7 @@ conf_read(unsigned long addr, unsigned char type1, stat0 = *(vuip)MCPCIA_CAP_ERR(mid); *(vuip)MCPCIA_CAP_ERR(mid) = stat0; mb(); - temp = *(vuip)MCPCIA_CAP_ERR(mid); + *(vuip)MCPCIA_CAP_ERR(mid); DBG_CFG(("conf_read: MCPCIA_CAP_ERR(%d) was 0x%x\n", mid, stat0)); mb(); @@ -136,7 +136,7 @@ conf_write(unsigned long addr, unsigned int value, unsigned char type1, { unsigned long flags; unsigned long mid = MCPCIA_HOSE2MID(hose->index); - unsigned int stat0, temp, cpu; + unsigned int stat0, cpu; cpu = smp_processor_id(); @@ -145,7 +145,7 @@ conf_write(unsigned long addr, unsigned int value, unsigned char type1, /* Reset status register to avoid losing errors. */ stat0 = *(vuip)MCPCIA_CAP_ERR(mid); *(vuip)MCPCIA_CAP_ERR(mid) = stat0; mb(); - temp = *(vuip)MCPCIA_CAP_ERR(mid); + *(vuip)MCPCIA_CAP_ERR(mid); DBG_CFG(("conf_write: MCPCIA CAP_ERR(%d) was 0x%x\n", mid, stat0)); draina(); @@ -157,7 +157,7 @@ conf_write(unsigned long addr, unsigned int value, unsigned char type1, *((vuip)addr) = value; mb(); mb(); /* magic */ - temp = *(vuip)MCPCIA_CAP_ERR(mid); /* read to force the write */ + *(vuip)MCPCIA_CAP_ERR(mid); /* read to force the write */ mcheck_expected(cpu) = 0; mb(); @@ -572,12 +572,10 @@ mcpcia_print_system_area(unsigned long la_ptr) void mcpcia_machine_check(unsigned long vector, unsigned long la_ptr) { - struct el_common *mchk_header; struct el_MCPCIA_uncorrected_frame_mcheck *mchk_logout; unsigned int cpu = smp_processor_id(); int expected; - mchk_header = (struct el_common *)la_ptr; mchk_logout = (struct el_MCPCIA_uncorrected_frame_mcheck *)la_ptr; expected = mcheck_expected(cpu); diff --git a/arch/alpha/kernel/err_titan.c b/arch/alpha/kernel/err_titan.c index c3b3781a03d..14b26c466c8 100644 --- a/arch/alpha/kernel/err_titan.c +++ b/arch/alpha/kernel/err_titan.c @@ -533,8 +533,6 @@ static struct el_subpacket_annotation el_titan_annotations[] = { static struct el_subpacket * el_process_regatta_subpacket(struct el_subpacket *header) { - int status; - if (header->class != EL_CLASS__REGATTA_FAMILY) { printk("%s ** Unexpected header CLASS %d TYPE %d, aborting\n", err_print_prefix, @@ -551,7 +549,7 @@ el_process_regatta_subpacket(struct el_subpacket *header) printk("%s ** Occurred on CPU %d:\n", err_print_prefix, (int)header->by_type.regatta_frame.cpuid); - status = privateer_process_logout_frame((struct el_common *) + privateer_process_logout_frame((struct el_common *) header->by_type.regatta_frame.data_start, 1); break; default: diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 1479dc6ebd9..51b7fbd9e4c 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -228,7 +228,7 @@ struct irqaction timer_irqaction = { void __init init_rtc_irq(void) { - irq_set_chip_and_handler_name(RTC_IRQ, &no_irq_chip, + irq_set_chip_and_handler_name(RTC_IRQ, &dummy_irq_chip, handle_simple_irq, "RTC"); setup_irq(RTC_IRQ, &timer_irqaction); } diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index d2634e4476b..edbddcbd5bc 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -1404,8 +1404,6 @@ determine_cpu_caches (unsigned int cpu_type) case PCA56_CPU: case PCA57_CPU: { - unsigned long cbox_config, size; - if (cpu_type == PCA56_CPU) { L1I = CSHAPE(16*1024, 6, 1); L1D = CSHAPE(8*1024, 5, 1); @@ -1415,10 +1413,12 @@ determine_cpu_caches (unsigned int cpu_type) } L3 = -1; +#if 0 + unsigned long cbox_config, size; + cbox_config = *(vulp) phys_to_virt (0xfffff00008UL); size = 512*1024 * (1 << ((cbox_config >> 12) & 3)); -#if 0 L2 = ((cbox_config >> 31) & 1 ? CSHAPE (size, 6, 1) : -1); #else L2 = external_cache_probe(512*1024, 6); diff --git a/arch/alpha/kernel/smc37c93x.c b/arch/alpha/kernel/smc37c93x.c index 3e6a2893af9..6886b834f48 100644 --- a/arch/alpha/kernel/smc37c93x.c +++ b/arch/alpha/kernel/smc37c93x.c @@ -79,7 +79,6 @@ static unsigned long __init SMCConfigState(unsigned long baseAddr) { unsigned char devId; - unsigned char devRev; unsigned long configPort; unsigned long indexPort; @@ -100,7 +99,7 @@ static unsigned long __init SMCConfigState(unsigned long baseAddr) devId = inb(dataPort); if (devId == VALID_DEVICE_ID) { outb(DEVICE_REV, indexPort); - devRev = inb(dataPort); + /* unsigned char devRev = */ inb(dataPort); break; } else diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c index d3cb28bb8eb..d92cdc715c6 100644 --- a/arch/alpha/kernel/sys_wildfire.c +++ b/arch/alpha/kernel/sys_wildfire.c @@ -156,7 +156,6 @@ static void __init wildfire_init_irq_per_pca(int qbbno, int pcano) { int i, irq_bias; - unsigned long io_bias; static struct irqaction isa_enable = { .handler = no_action, .name = "isa_enable", @@ -165,10 +164,12 @@ wildfire_init_irq_per_pca(int qbbno, int pcano) irq_bias = qbbno * (WILDFIRE_PCA_PER_QBB * WILDFIRE_IRQ_PER_PCA) + pcano * WILDFIRE_IRQ_PER_PCA; +#if 0 + unsigned long io_bias; + /* Only need the following for first PCI bus per PCA. */ io_bias = WILDFIRE_IO(qbbno, pcano<<1) - WILDFIRE_IO_BIAS; -#if 0 outb(0, DMA1_RESET_REG + io_bias); outb(0, DMA2_RESET_REG + io_bias); outb(DMA_MODE_CASCADE, DMA2_MODE_REG + io_bias); diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index a58e84f1a63..918e8e0b72f 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -153,6 +153,7 @@ void read_persistent_clock(struct timespec *ts) year += 100; ts->tv_sec = mktime(year, mon, day, hour, min, sec); + ts->tv_nsec = 0; } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index fdc9d4dbf85..377a7a595b0 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1540,7 +1540,6 @@ config HIGHMEM config HIGHPTE bool "Allocate 2nd-level pagetables from highmem" depends on HIGHMEM - depends on !OUTER_CACHE config HW_PERF_EVENTS bool "Enable hardware performance counter support for perf events" @@ -2012,6 +2011,8 @@ source "kernel/power/Kconfig" config ARCH_SUSPEND_POSSIBLE depends on !ARCH_S5P64X0 && !ARCH_S5P6442 + depends on CPU_ARM920T || CPU_ARM926T || CPU_SA1100 || \ + CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE def_bool y endmenu diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 494224a9b45..03d01d783e3 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -63,17 +63,6 @@ config DEBUG_USER 8 - SIGSEGV faults 16 - SIGBUS faults -config DEBUG_ERRORS - bool "Verbose kernel error messages" - depends on DEBUG_KERNEL - help - This option controls verbose debugging information which can be - printed when the kernel detects an internal error. This debugging - information is useful to kernel hackers when tracking down problems, - but mostly meaningless to other people. It's safe to say Y unless - you are concerned with the code size or don't want to see these - messages. - config DEBUG_STACK_USAGE bool "Enable stack utilization instrumentation" depends on DEBUG_KERNEL diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile index e7521bca2c3..6ea9b6f3607 100644 --- a/arch/arm/common/Makefile +++ b/arch/arm/common/Makefile @@ -16,5 +16,4 @@ obj-$(CONFIG_SHARP_SCOOP) += scoop.o obj-$(CONFIG_ARCH_IXP2000) += uengine.o obj-$(CONFIG_ARCH_IXP23XX) += uengine.o obj-$(CONFIG_PCI_HOST_ITE8152) += it8152.o -obj-$(CONFIG_COMMON_CLKDEV) += clkdev.o obj-$(CONFIG_ARM_TIMER_SP804) += timer-sp.o diff --git a/arch/arm/include/asm/thread_notify.h b/arch/arm/include/asm/thread_notify.h index c4391ba2035..1dc98067589 100644 --- a/arch/arm/include/asm/thread_notify.h +++ b/arch/arm/include/asm/thread_notify.h @@ -43,6 +43,7 @@ static inline void thread_notify(unsigned long rc, struct thread_info *thread) #define THREAD_NOTIFY_FLUSH 0 #define THREAD_NOTIFY_EXIT 1 #define THREAD_NOTIFY_SWITCH 2 +#define THREAD_NOTIFY_COPY 3 #endif #endif diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 74554f1742d..8d95446150a 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -29,7 +29,7 @@ obj-$(CONFIG_MODULES) += armksyms.o module.o obj-$(CONFIG_ARTHUR) += arthur.o obj-$(CONFIG_ISA_DMA) += dma-isa.o obj-$(CONFIG_PCI) += bios32.o isa.o -obj-$(CONFIG_PM) += sleep.o +obj-$(CONFIG_PM_SLEEP) += sleep.o obj-$(CONFIG_HAVE_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_SMP) += smp.o smp_tlb.o obj-$(CONFIG_HAVE_ARM_SCU) += smp_scu.o diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c index d4a0da1e48f..9b05c6a0dce 100644 --- a/arch/arm/kernel/elf.c +++ b/arch/arm/kernel/elf.c @@ -40,15 +40,22 @@ EXPORT_SYMBOL(elf_check_arch); void elf_set_personality(const struct elf32_hdr *x) { unsigned int eflags = x->e_flags; - unsigned int personality = PER_LINUX_32BIT; + unsigned int personality = current->personality & ~PER_MASK; + + /* + * We only support Linux ELF executables, so always set the + * personality to LINUX. + */ + personality |= PER_LINUX; /* * APCS-26 is only valid for OABI executables */ - if ((eflags & EF_ARM_EABI_MASK) == EF_ARM_EABI_UNKNOWN) { - if (eflags & EF_ARM_APCS_26) - personality = PER_LINUX; - } + if ((eflags & EF_ARM_EABI_MASK) == EF_ARM_EABI_UNKNOWN && + (eflags & EF_ARM_APCS_26)) + personality &= ~ADDR_LIMIT_32BIT; + else + personality |= ADDR_LIMIT_32BIT; set_personality(personality); diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 8dbc126f715..87acc25d7a3 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -868,6 +868,13 @@ static void reset_ctrl_regs(void *info) */ asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0)); isb(); + + /* + * Clear any configured vector-catch events before + * enabling monitor mode. + */ + asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0)); + isb(); } if (enable_monitor_mode()) diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 69cfee0fe00..979da3947f4 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -221,7 +221,7 @@ again: prev_raw_count &= armpmu->max_period; if (overflow) - delta = armpmu->max_period - prev_raw_count + new_raw_count; + delta = armpmu->max_period - prev_raw_count + new_raw_count + 1; else delta = new_raw_count - prev_raw_count; diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 94bbedbed63..5e1e5419722 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -372,6 +372,8 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start, if (clone_flags & CLONE_SETTLS) thread->tp_value = regs->ARM_r3; + thread_notify(THREAD_NOTIFY_COPY, thread); + return 0; } diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index f0000e188c8..3b54ad19d48 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -410,8 +410,7 @@ static int bad_syscall(int n, struct pt_regs *regs) struct thread_info *thread = current_thread_info(); siginfo_t info; - if (current->personality != PER_LINUX && - current->personality != PER_LINUX_32BIT && + if ((current->personality & PER_MASK) != PER_LINUX && thread->exec_domain->handler) { thread->exec_domain->handler(n, regs); return regs->ARM_r0; diff --git a/arch/arm/mach-mmp/include/mach/gpio.h b/arch/arm/mach-mmp/include/mach/gpio.h index ee8b02ed801..7bfb827f3fe 100644 --- a/arch/arm/mach-mmp/include/mach/gpio.h +++ b/arch/arm/mach-mmp/include/mach/gpio.h @@ -10,7 +10,7 @@ #define BANK_OFF(n) (((n) < 3) ? (n) << 2 : 0x100 + (((n) - 3) << 2)) #define GPIO_REG(x) (*((volatile u32 *)(GPIO_REGS_VIRT + (x)))) -#define NR_BUILTIN_GPIO (192) +#define NR_BUILTIN_GPIO IRQ_GPIO_NUM #define gpio_to_bank(gpio) ((gpio) >> 5) #define gpio_to_irq(gpio) (IRQ_GPIO_START + (gpio)) diff --git a/arch/arm/mach-mmp/include/mach/mfp-pxa168.h b/arch/arm/mach-mmp/include/mach/mfp-pxa168.h index 4621067c772..713be155a44 100644 --- a/arch/arm/mach-mmp/include/mach/mfp-pxa168.h +++ b/arch/arm/mach-mmp/include/mach/mfp-pxa168.h @@ -8,6 +8,15 @@ #define MFP_DRIVE_MEDIUM (0x2 << 13) #define MFP_DRIVE_FAST (0x3 << 13) +#undef MFP_CFG +#undef MFP_CFG_DRV + +#define MFP_CFG(pin, af) \ + (MFP_LPM_INPUT | MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_DRIVE_MEDIUM) + +#define MFP_CFG_DRV(pin, af, drv) \ + (MFP_LPM_INPUT | MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_DRIVE_##drv) + /* GPIO */ #define GPIO0_GPIO MFP_CFG(GPIO0, AF5) #define GPIO1_GPIO MFP_CFG(GPIO1, AF5) diff --git a/arch/arm/mach-msm/board-qsd8x50.c b/arch/arm/mach-msm/board-qsd8x50.c index 7f568611547..6a96911b0ad 100644 --- a/arch/arm/mach-msm/board-qsd8x50.c +++ b/arch/arm/mach-msm/board-qsd8x50.c @@ -160,10 +160,7 @@ static struct msm_mmc_platform_data qsd8x50_sdc1_data = { static void __init qsd8x50_init_mmc(void) { - if (machine_is_qsd8x50_ffa() || machine_is_qsd8x50a_ffa()) - vreg_mmc = vreg_get(NULL, "gp6"); - else - vreg_mmc = vreg_get(NULL, "gp5"); + vreg_mmc = vreg_get(NULL, "gp5"); if (IS_ERR(vreg_mmc)) { pr_err("vreg get for vreg_mmc failed (%ld)\n", diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c index 56f920c55b6..38b95e949d1 100644 --- a/arch/arm/mach-msm/timer.c +++ b/arch/arm/mach-msm/timer.c @@ -269,7 +269,7 @@ int __cpuinit local_timer_setup(struct clock_event_device *evt) /* Use existing clock_event for cpu 0 */ if (!smp_processor_id()) - return; + return 0; writel(DGT_CLK_CTL_DIV_4, MSM_TMR_BASE + DGT_CLK_CTL); diff --git a/arch/arm/mach-pxa/include/mach/gpio.h b/arch/arm/mach-pxa/include/mach/gpio.h index b024a8b3743..c4639502efc 100644 --- a/arch/arm/mach-pxa/include/mach/gpio.h +++ b/arch/arm/mach-pxa/include/mach/gpio.h @@ -99,11 +99,24 @@ #define GAFR(x) GPIO_REG(0x54 + (((x) & 0x70) >> 2)) -#define NR_BUILTIN_GPIO 128 +#define NR_BUILTIN_GPIO PXA_GPIO_IRQ_NUM #define gpio_to_bank(gpio) ((gpio) >> 5) #define gpio_to_irq(gpio) IRQ_GPIO(gpio) -#define irq_to_gpio(irq) IRQ_TO_GPIO(irq) + +static inline int irq_to_gpio(unsigned int irq) +{ + int gpio; + + if (irq == IRQ_GPIO0 || irq == IRQ_GPIO1) + return irq - IRQ_GPIO0; + + gpio = irq - PXA_GPIO_IRQ_BASE; + if (gpio >= 2 && gpio < NR_BUILTIN_GPIO) + return gpio; + + return -1; +} #ifdef CONFIG_CPU_PXA26x /* GPIO86/87/88/89 on PXA26x have their direction bits in GPDR2 inverted, diff --git a/arch/arm/mach-pxa/include/mach/irqs.h b/arch/arm/mach-pxa/include/mach/irqs.h index a4285fc0087..038402404e3 100644 --- a/arch/arm/mach-pxa/include/mach/irqs.h +++ b/arch/arm/mach-pxa/include/mach/irqs.h @@ -93,9 +93,6 @@ #define GPIO_2_x_TO_IRQ(x) (PXA_GPIO_IRQ_BASE + (x)) #define IRQ_GPIO(x) (((x) < 2) ? (IRQ_GPIO0 + (x)) : GPIO_2_x_TO_IRQ(x)) -#define IRQ_TO_GPIO_2_x(i) ((i) - PXA_GPIO_IRQ_BASE) -#define IRQ_TO_GPIO(i) (((i) < IRQ_GPIO(2)) ? ((i) - IRQ_GPIO0) : IRQ_TO_GPIO_2_x(i)) - /* * The following interrupts are for board specific purposes. Since * the kernel can only run on one machine at a time, we can re-use diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c index 6bde5956358..a4af8c52d7e 100644 --- a/arch/arm/mach-pxa/pxa25x.c +++ b/arch/arm/mach-pxa/pxa25x.c @@ -285,7 +285,7 @@ static inline void pxa25x_init_pm(void) {} static int pxa25x_set_wake(struct irq_data *d, unsigned int on) { - int gpio = IRQ_TO_GPIO(d->irq); + int gpio = irq_to_gpio(d->irq); uint32_t mask = 0; if (gpio >= 0 && gpio < 85) diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c index 1cb5d0f9723..909756eaf4b 100644 --- a/arch/arm/mach-pxa/pxa27x.c +++ b/arch/arm/mach-pxa/pxa27x.c @@ -345,7 +345,7 @@ static inline void pxa27x_init_pm(void) {} */ static int pxa27x_set_wake(struct irq_data *d, unsigned int on) { - int gpio = IRQ_TO_GPIO(d->irq); + int gpio = irq_to_gpio(d->irq); uint32_t mask; if (gpio >= 0 && gpio < 128) diff --git a/arch/arm/mach-tegra/gpio.c b/arch/arm/mach-tegra/gpio.c index 76a3f654220..65a1aba6823 100644 --- a/arch/arm/mach-tegra/gpio.c +++ b/arch/arm/mach-tegra/gpio.c @@ -257,7 +257,8 @@ static void tegra_gpio_irq_handler(unsigned int irq, struct irq_desc *desc) void tegra_gpio_resume(void) { unsigned long flags; - int b, p, i; + int b; + int p; local_irq_save(flags); @@ -280,7 +281,8 @@ void tegra_gpio_resume(void) void tegra_gpio_suspend(void) { unsigned long flags; - int b, p, i; + int b; + int p; local_irq_save(flags); for (b = 0; b < ARRAY_SIZE(tegra_gpio_banks); b++) { diff --git a/arch/arm/mach-tegra/tegra2_clocks.c b/arch/arm/mach-tegra/tegra2_clocks.c index 6d7c4eea4dc..4459470c052 100644 --- a/arch/arm/mach-tegra/tegra2_clocks.c +++ b/arch/arm/mach-tegra/tegra2_clocks.c @@ -1362,14 +1362,15 @@ static int tegra_clk_shared_bus_set_rate(struct clk *c, unsigned long rate) { unsigned long flags; int ret; + long new_rate = rate; - rate = clk_round_rate(c->parent, rate); - if (rate < 0) - return rate; + new_rate = clk_round_rate(c->parent, new_rate); + if (new_rate < 0) + return new_rate; spin_lock_irqsave(&c->parent->spinlock, flags); - c->u.shared_bus_user.rate = rate; + c->u.shared_bus_user.rate = new_rate; ret = tegra_clk_shared_bus_update(c->parent); spin_unlock_irqrestore(&c->parent->spinlock, flags); diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index afe209e1e1f..74be05f3e03 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -7,6 +7,7 @@ #include <linux/shm.h> #include <linux/sched.h> #include <linux/io.h> +#include <linux/personality.h> #include <linux/random.h> #include <asm/cputype.h> #include <asm/system.h> @@ -82,7 +83,8 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, mm->cached_hole_size = 0; } /* 8 bits of randomness in 20 address space bits */ - if (current->flags & PF_RANDOMIZE) + if ((current->flags & PF_RANDOMIZE) && + !(current->personality & ADDR_NO_RANDOMIZE)) addr += (get_random_int() % (1 << 8)) << PAGE_SHIFT; full_search: diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index b46eb21f05c..bf8a1d1cccb 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -390,7 +390,7 @@ ENTRY(cpu_arm920_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size .equ cpu_arm920_suspend_size, 4 * 3 -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP ENTRY(cpu_arm920_do_suspend) stmfd sp!, {r4 - r7, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index 6a4bdb2c94a..0ed85d930c0 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -404,7 +404,7 @@ ENTRY(cpu_arm926_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size .equ cpu_arm926_suspend_size, 4 * 3 -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP ENTRY(cpu_arm926_do_suspend) stmfd sp!, {r4 - r7, lr} mrc p15, 0, r4, c13, c0, 0 @ PID diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 74483d1977f..184a9c997e3 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -171,7 +171,7 @@ ENTRY(cpu_sa1100_set_pte_ext) .globl cpu_sa1100_suspend_size .equ cpu_sa1100_suspend_size, 4*4 -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP ENTRY(cpu_sa1100_do_suspend) stmfd sp!, {r4 - r7, lr} mrc p15, 0, r4, c3, c0, 0 @ domain ID diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index bfa0c9f611c..7c99cb4c8e4 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -124,7 +124,7 @@ ENTRY(cpu_v6_set_pte_ext) /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size .equ cpu_v6_suspend_size, 4 * 8 -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP ENTRY(cpu_v6_do_suspend) stmfd sp!, {r4 - r11, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index c35618e42f6..babfba09c89 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -211,7 +211,7 @@ cpu_v7_name: /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */ .globl cpu_v7_suspend_size .equ cpu_v7_suspend_size, 4 * 8 -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP ENTRY(cpu_v7_do_suspend) stmfd sp!, {r4 - r11, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index 63d8b2044e8..596213699f3 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -417,7 +417,7 @@ ENTRY(cpu_xsc3_set_pte_ext) .globl cpu_xsc3_suspend_size .equ cpu_xsc3_suspend_size, 4 * 8 -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP ENTRY(cpu_xsc3_do_suspend) stmfd sp!, {r4 - r10, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index 086038cd86a..ce233bcbf50 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -518,7 +518,7 @@ ENTRY(cpu_xscale_set_pte_ext) .globl cpu_xscale_suspend_size .equ cpu_xscale_suspend_size, 4 * 7 -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP ENTRY(cpu_xscale_do_suspend) stmfd sp!, {r4 - r10, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode diff --git a/arch/arm/plat-s5p/pm.c b/arch/arm/plat-s5p/pm.c index d592b6304b4..d15dc47b0e3 100644 --- a/arch/arm/plat-s5p/pm.c +++ b/arch/arm/plat-s5p/pm.c @@ -19,17 +19,6 @@ #define PFX "s5p pm: " -/* s3c_pm_check_resume_pin - * - * check to see if the pin is configured correctly for sleep mode, and - * make any necessary adjustments if it is not -*/ - -static void s3c_pm_check_resume_pin(unsigned int pin, unsigned int irqoffs) -{ - /* nothing here yet */ -} - /* s3c_pm_configure_extint * * configure all external interrupt pins diff --git a/arch/arm/plat-samsung/pm-check.c b/arch/arm/plat-samsung/pm-check.c index e4baf76f374..6b733fafe7c 100644 --- a/arch/arm/plat-samsung/pm-check.c +++ b/arch/arm/plat-samsung/pm-check.c @@ -164,7 +164,6 @@ static inline int in_region(void *ptr, int size, void *what, size_t whatsz) */ static u32 *s3c_pm_runcheck(struct resource *res, u32 *val) { - void *save_at = phys_to_virt(s3c_sleep_save_phys); unsigned long addr; unsigned long left; void *stkpage; @@ -192,11 +191,6 @@ static u32 *s3c_pm_runcheck(struct resource *res, u32 *val) goto skip_check; } - if (in_region(ptr, left, save_at, 32*4 )) { - S3C_PMDBG("skipping %08lx, has save block in\n", addr); - goto skip_check; - } - /* calculate and check the checksum */ calc = crc32_le(~0, ptr, left); diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c index d5b58d31903..5c0a440d6e1 100644 --- a/arch/arm/plat-samsung/pm.c +++ b/arch/arm/plat-samsung/pm.c @@ -214,8 +214,9 @@ void s3c_pm_do_restore_core(struct sleep_save *ptr, int count) * * print any IRQs asserted at resume time (ie, we woke from) */ -static void s3c_pm_show_resume_irqs(int start, unsigned long which, - unsigned long mask) +static void __maybe_unused s3c_pm_show_resume_irqs(int start, + unsigned long which, + unsigned long mask) { int i; diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index bbf3da012af..f74695075e6 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -78,6 +78,14 @@ static void vfp_thread_exit(struct thread_info *thread) put_cpu(); } +static void vfp_thread_copy(struct thread_info *thread) +{ + struct thread_info *parent = current_thread_info(); + + vfp_sync_hwstate(parent); + thread->vfpstate = parent->vfpstate; +} + /* * When this function is called with the following 'cmd's, the following * is true while this function is being run: @@ -104,12 +112,17 @@ static void vfp_thread_exit(struct thread_info *thread) static int vfp_notifier(struct notifier_block *self, unsigned long cmd, void *v) { struct thread_info *thread = v; + u32 fpexc; +#ifdef CONFIG_SMP + unsigned int cpu; +#endif - if (likely(cmd == THREAD_NOTIFY_SWITCH)) { - u32 fpexc = fmrx(FPEXC); + switch (cmd) { + case THREAD_NOTIFY_SWITCH: + fpexc = fmrx(FPEXC); #ifdef CONFIG_SMP - unsigned int cpu = thread->cpu; + cpu = thread->cpu; /* * On SMP, if VFP is enabled, save the old state in @@ -134,13 +147,20 @@ static int vfp_notifier(struct notifier_block *self, unsigned long cmd, void *v) * old state. */ fmxr(FPEXC, fpexc & ~FPEXC_EN); - return NOTIFY_DONE; - } + break; - if (cmd == THREAD_NOTIFY_FLUSH) + case THREAD_NOTIFY_FLUSH: vfp_thread_flush(thread); - else + break; + + case THREAD_NOTIFY_EXIT: vfp_thread_exit(thread); + break; + + case THREAD_NOTIFY_COPY: + vfp_thread_copy(thread); + break; + } return NOTIFY_DONE; } diff --git a/arch/blackfin/include/asm/system.h b/arch/blackfin/include/asm/system.h index 19e2c7c3e63..44bd0cced72 100644 --- a/arch/blackfin/include/asm/system.h +++ b/arch/blackfin/include/asm/system.h @@ -19,11 +19,11 @@ * Force strict CPU ordering. */ #define nop() __asm__ __volatile__ ("nop;\n\t" : : ) -#define mb() __asm__ __volatile__ ("" : : : "memory") -#define rmb() __asm__ __volatile__ ("" : : : "memory") -#define wmb() __asm__ __volatile__ ("" : : : "memory") -#define set_mb(var, value) do { (void) xchg(&var, value); } while (0) -#define read_barrier_depends() do { } while(0) +#define smp_mb() mb() +#define smp_rmb() rmb() +#define smp_wmb() wmb() +#define set_mb(var, value) do { var = value; mb(); } while (0) +#define smp_read_barrier_depends() read_barrier_depends() #ifdef CONFIG_SMP asmlinkage unsigned long __raw_xchg_1_asm(volatile void *ptr, unsigned long value); @@ -37,16 +37,16 @@ asmlinkage unsigned long __raw_cmpxchg_4_asm(volatile void *ptr, unsigned long new, unsigned long old); #ifdef __ARCH_SYNC_CORE_DCACHE -# define smp_mb() do { barrier(); smp_check_barrier(); smp_mark_barrier(); } while (0) -# define smp_rmb() do { barrier(); smp_check_barrier(); } while (0) -# define smp_wmb() do { barrier(); smp_mark_barrier(); } while (0) -#define smp_read_barrier_depends() do { barrier(); smp_check_barrier(); } while (0) - +/* Force Core data cache coherence */ +# define mb() do { barrier(); smp_check_barrier(); smp_mark_barrier(); } while (0) +# define rmb() do { barrier(); smp_check_barrier(); } while (0) +# define wmb() do { barrier(); smp_mark_barrier(); } while (0) +# define read_barrier_depends() do { barrier(); smp_check_barrier(); } while (0) #else -# define smp_mb() barrier() -# define smp_rmb() barrier() -# define smp_wmb() barrier() -#define smp_read_barrier_depends() barrier() +# define mb() barrier() +# define rmb() barrier() +# define wmb() barrier() +# define read_barrier_depends() do { } while (0) #endif static inline unsigned long __xchg(unsigned long x, volatile void *ptr, @@ -99,10 +99,10 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, #else /* !CONFIG_SMP */ -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define smp_read_barrier_depends() do { } while(0) +#define mb() barrier() +#define rmb() barrier() +#define wmb() barrier() +#define read_barrier_depends() do { } while (0) struct __xchg_dummy { unsigned long a[100]; diff --git a/arch/blackfin/kernel/gptimers.c b/arch/blackfin/kernel/gptimers.c index cdbe075de1d..8b81dc04488 100644 --- a/arch/blackfin/kernel/gptimers.c +++ b/arch/blackfin/kernel/gptimers.c @@ -268,7 +268,7 @@ void disable_gptimers(uint16_t mask) _disable_gptimers(mask); for (i = 0; i < MAX_BLACKFIN_GPTIMERS; ++i) if (mask & (1 << i)) - group_regs[BFIN_TIMER_OCTET(i)]->status |= trun_mask[i]; + group_regs[BFIN_TIMER_OCTET(i)]->status = trun_mask[i]; SSYNC(); } EXPORT_SYMBOL(disable_gptimers); diff --git a/arch/blackfin/kernel/time-ts.c b/arch/blackfin/kernel/time-ts.c index 8c9a43daf80..cdb4beb6bc8 100644 --- a/arch/blackfin/kernel/time-ts.c +++ b/arch/blackfin/kernel/time-ts.c @@ -206,8 +206,14 @@ irqreturn_t bfin_gptmr0_interrupt(int irq, void *dev_id) { struct clock_event_device *evt = dev_id; smp_mb(); - evt->event_handler(evt); + /* + * We want to ACK before we handle so that we can handle smaller timer + * intervals. This way if the timer expires again while we're handling + * things, we're more likely to see that 2nd int rather than swallowing + * it by ACKing the int at the end of this handler. + */ bfin_gptmr0_ack(); + evt->event_handler(evt); return IRQ_HANDLED; } diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 326bb86f4d2..1fbd94c4445 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -109,10 +109,23 @@ static void ipi_flush_icache(void *info) struct blackfin_flush_data *fdata = info; /* Invalidate the memory holding the bounds of the flushed region. */ - invalidate_dcache_range((unsigned long)fdata, - (unsigned long)fdata + sizeof(*fdata)); + blackfin_dcache_invalidate_range((unsigned long)fdata, + (unsigned long)fdata + sizeof(*fdata)); + + /* Make sure all write buffers in the data side of the core + * are flushed before trying to invalidate the icache. This + * needs to be after the data flush and before the icache + * flush so that the SSYNC does the right thing in preventing + * the instruction prefetcher from hitting things in cached + * memory at the wrong time -- it runs much further ahead than + * the pipeline. + */ + SSYNC(); - flush_icache_range(fdata->start, fdata->end); + /* ipi_flaush_icache is invoked by generic flush_icache_range, + * so call blackfin arch icache flush directly here. + */ + blackfin_icache_flush_range(fdata->start, fdata->end); } static void ipi_call_function(unsigned int cpu, struct ipi_message *msg) diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 851b3bf6e96..eccdefe70d4 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -6,7 +6,6 @@ config MICROBLAZE select HAVE_FUNCTION_GRAPH_TRACER select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD - select USB_ARCH_HAS_EHCI select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_OPROFILE select HAVE_ARCH_KGDB diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index b6ff882f695..8f4d50b0adf 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -209,7 +209,7 @@ config ARCH_HIBERNATION_POSSIBLE config ARCH_SUSPEND_POSSIBLE def_bool y depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx || \ - PPC_85xx || PPC_86xx || PPC_PSERIES || 44x || 40x + (PPC_85xx && !SMP) || PPC_86xx || PPC_PSERIES || 44x || 40x config PPC_DCR_NATIVE bool diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index be3cdf9134c..1833d1a07e7 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -382,10 +382,12 @@ extern const char *powerpc_base_platform; #define CPU_FTRS_E500_2 (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \ CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE) -#define CPU_FTRS_E500MC (CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_USE_TB | \ - CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NODSISRALIGN | \ +#define CPU_FTRS_E500MC (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \ CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \ CPU_FTR_DBELL) +#define CPU_FTRS_E5500 (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \ + CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \ + CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD) #define CPU_FTRS_GENERIC_32 (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN) /* 64-bit CPUs */ @@ -435,11 +437,15 @@ extern const char *powerpc_base_platform; #define CPU_FTRS_COMPATIBLE (CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2) #ifdef __powerpc64__ +#ifdef CONFIG_PPC_BOOK3E +#define CPU_FTRS_POSSIBLE (CPU_FTRS_E5500) +#else #define CPU_FTRS_POSSIBLE \ (CPU_FTRS_POWER3 | CPU_FTRS_RS64 | CPU_FTRS_POWER4 | \ CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | CPU_FTRS_POWER6 | \ CPU_FTRS_POWER7 | CPU_FTRS_CELL | CPU_FTRS_PA6T | \ CPU_FTR_1T_SEGMENT | CPU_FTR_VSX) +#endif #else enum { CPU_FTRS_POSSIBLE = @@ -473,16 +479,21 @@ enum { #endif #ifdef CONFIG_E500 CPU_FTRS_E500 | CPU_FTRS_E500_2 | CPU_FTRS_E500MC | + CPU_FTRS_E5500 | #endif 0, }; #endif /* __powerpc64__ */ #ifdef __powerpc64__ +#ifdef CONFIG_PPC_BOOK3E +#define CPU_FTRS_ALWAYS (CPU_FTRS_E5500) +#else #define CPU_FTRS_ALWAYS \ (CPU_FTRS_POWER3 & CPU_FTRS_RS64 & CPU_FTRS_POWER4 & \ CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & CPU_FTRS_POWER6 & \ CPU_FTRS_POWER7 & CPU_FTRS_CELL & CPU_FTRS_PA6T & CPU_FTRS_POSSIBLE) +#endif #else enum { CPU_FTRS_ALWAYS = @@ -513,6 +524,7 @@ enum { #endif #ifdef CONFIG_E500 CPU_FTRS_E500 & CPU_FTRS_E500_2 & CPU_FTRS_E500MC & + CPU_FTRS_E5500 & #endif CPU_FTRS_POSSIBLE, }; diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h index 811f04ac366..8d1569c2904 100644 --- a/arch/powerpc/include/asm/pte-common.h +++ b/arch/powerpc/include/asm/pte-common.h @@ -162,7 +162,7 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void); * on platforms where such control is possible. */ #if defined(CONFIG_KGDB) || defined(CONFIG_XMON) || defined(CONFIG_BDI_SWITCH) ||\ - defined(CONFIG_KPROBES) + defined(CONFIG_KPROBES) || defined(CONFIG_DYNAMIC_FTRACE) #define PAGE_KERNEL_TEXT PAGE_KERNEL_X #else #define PAGE_KERNEL_TEXT PAGE_KERNEL_ROX diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index c9b68d07ac4..b9602ee06de 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1973,7 +1973,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .pvr_mask = 0xffff0000, .pvr_value = 0x80240000, .cpu_name = "e5500", - .cpu_features = CPU_FTRS_E500MC, + .cpu_features = CPU_FTRS_E5500, .cpu_user_features = COMMON_USER_BOOKE, .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 3d3d416339d..5b5e1f002a8 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -163,7 +163,7 @@ static void crash_kexec_prepare_cpus(int cpu) } /* wait for all the CPUs to hit real mode but timeout if they don't come in */ -#if defined(CONFIG_PPC_STD_MMU_64) && defined(CONFIG_SMP) +#ifdef CONFIG_PPC_STD_MMU_64 static void crash_kexec_wait_realmode(int cpu) { unsigned int msecs; @@ -188,9 +188,7 @@ static void crash_kexec_wait_realmode(int cpu) } mb(); } -#else -static inline void crash_kexec_wait_realmode(int cpu) {} -#endif +#endif /* CONFIG_PPC_STD_MMU_64 */ /* * This function will be called by secondary cpus or by kexec cpu @@ -235,7 +233,9 @@ void crash_kexec_secondary(struct pt_regs *regs) crash_ipi_callback(regs); } -#else +#else /* ! CONFIG_SMP */ +static inline void crash_kexec_wait_realmode(int cpu) {} + static void crash_kexec_prepare_cpus(int cpu) { /* @@ -255,7 +255,7 @@ void crash_kexec_secondary(struct pt_regs *regs) { cpus_in_sr = CPU_MASK_NONE; } -#endif +#endif /* CONFIG_SMP */ /* * Register a function to be called on shutdown. Only use this if you diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index c834757bebc..2b97b80d6d7 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -330,9 +330,11 @@ void __init find_legacy_serial_ports(void) if (!parent) continue; if (of_match_node(legacy_serial_parents, parent) != NULL) { - index = add_legacy_soc_port(np, np); - if (index >= 0 && np == stdout) - legacy_serial_console = index; + if (of_device_is_available(np)) { + index = add_legacy_soc_port(np, np); + if (index >= 0 && np == stdout) + legacy_serial_console = index; + } } of_node_put(parent); } diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index c4063b7f49a..822f63008ae 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -398,6 +398,25 @@ static int check_excludes(struct perf_event **ctrs, unsigned int cflags[], return 0; } +static u64 check_and_compute_delta(u64 prev, u64 val) +{ + u64 delta = (val - prev) & 0xfffffffful; + + /* + * POWER7 can roll back counter values, if the new value is smaller + * than the previous value it will cause the delta and the counter to + * have bogus values unless we rolled a counter over. If a coutner is + * rolled back, it will be smaller, but within 256, which is the maximum + * number of events to rollback at once. If we dectect a rollback + * return 0. This can lead to a small lack of precision in the + * counters. + */ + if (prev > val && (prev - val) < 256) + delta = 0; + + return delta; +} + static void power_pmu_read(struct perf_event *event) { s64 val, delta, prev; @@ -416,10 +435,11 @@ static void power_pmu_read(struct perf_event *event) prev = local64_read(&event->hw.prev_count); barrier(); val = read_pmc(event->hw.idx); + delta = check_and_compute_delta(prev, val); + if (!delta) + return; } while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev); - /* The counters are only 32 bits wide */ - delta = (val - prev) & 0xfffffffful; local64_add(delta, &event->count); local64_sub(delta, &event->hw.period_left); } @@ -449,8 +469,9 @@ static void freeze_limited_counters(struct cpu_hw_events *cpuhw, val = (event->hw.idx == 5) ? pmc5 : pmc6; prev = local64_read(&event->hw.prev_count); event->hw.idx = 0; - delta = (val - prev) & 0xfffffffful; - local64_add(delta, &event->count); + delta = check_and_compute_delta(prev, val); + if (delta) + local64_add(delta, &event->count); } } @@ -458,14 +479,16 @@ static void thaw_limited_counters(struct cpu_hw_events *cpuhw, unsigned long pmc5, unsigned long pmc6) { struct perf_event *event; - u64 val; + u64 val, prev; int i; for (i = 0; i < cpuhw->n_limited; ++i) { event = cpuhw->limited_counter[i]; event->hw.idx = cpuhw->limited_hwidx[i]; val = (event->hw.idx == 5) ? pmc5 : pmc6; - local64_set(&event->hw.prev_count, val); + prev = local64_read(&event->hw.prev_count); + if (check_and_compute_delta(prev, val)) + local64_set(&event->hw.prev_count, val); perf_event_update_userpage(event); } } @@ -1197,7 +1220,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, /* we don't have to worry about interrupts here */ prev = local64_read(&event->hw.prev_count); - delta = (val - prev) & 0xfffffffful; + delta = check_and_compute_delta(prev, val); local64_add(delta, &event->count); /* diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 375480c56eb..f33acfd872a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -229,6 +229,9 @@ static u64 scan_dispatch_log(u64 stop_tb) u64 stolen = 0; u64 dtb; + if (!dtl) + return 0; + if (i == vpa->dtl_idx) return 0; while (i < vpa->dtl_idx) { diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index a830c5e8065..bc5f0dc6ae1 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -842,6 +842,7 @@ static void __devinit smp_core99_setup_cpu(int cpu_nr) mpic_setup_this_cpu(); } +#ifdef CONFIG_PPC64 #ifdef CONFIG_HOTPLUG_CPU static int smp_core99_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) @@ -879,7 +880,6 @@ static struct notifier_block __cpuinitdata smp_core99_cpu_nb = { static void __init smp_core99_bringup_done(void) { -#ifdef CONFIG_PPC64 extern void g5_phy_disable_cpu1(void); /* Close i2c bus if it was used for tb sync */ @@ -894,14 +894,14 @@ static void __init smp_core99_bringup_done(void) set_cpu_present(1, false); g5_phy_disable_cpu1(); } -#endif /* CONFIG_PPC64 */ - #ifdef CONFIG_HOTPLUG_CPU register_cpu_notifier(&smp_core99_cpu_nb); #endif + if (ppc_md.progress) ppc_md.progress("smp_core99_bringup_done", 0x349); } +#endif /* CONFIG_PPC64 */ #ifdef CONFIG_HOTPLUG_CPU @@ -975,7 +975,9 @@ static void pmac_cpu_die(void) struct smp_ops_t core99_smp_ops = { .message_pass = smp_mpic_message_pass, .probe = smp_core99_probe, +#ifdef CONFIG_PPC64 .bringup_done = smp_core99_bringup_done, +#endif .kick_cpu = smp_core99_kick_cpu, .setup_cpu = smp_core99_setup_cpu, .give_timebase = smp_core99_give_timebase, diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 00072414908..6c42cfde841 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -287,14 +287,22 @@ static int alloc_dispatch_logs(void) int cpu, ret; struct paca_struct *pp; struct dtl_entry *dtl; + struct kmem_cache *dtl_cache; if (!firmware_has_feature(FW_FEATURE_SPLPAR)) return 0; + dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES, + DISPATCH_LOG_BYTES, 0, NULL); + if (!dtl_cache) { + pr_warn("Failed to create dispatch trace log buffer cache\n"); + pr_warn("Stolen time statistics will be unreliable\n"); + return 0; + } + for_each_possible_cpu(cpu) { pp = &paca[cpu]; - dtl = kmalloc_node(DISPATCH_LOG_BYTES, GFP_KERNEL, - cpu_to_node(cpu)); + dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL); if (!dtl) { pr_warn("Failed to allocate dispatch trace log for cpu %d\n", cpu); diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index f8f7f28c634..68ca9290df9 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -324,6 +324,11 @@ int __init fsl_add_bridge(struct device_node *dev, int is_primary) struct resource rsrc; const int *bus_range; + if (!of_device_is_available(dev)) { + pr_warning("%s: disabled\n", dev->full_name); + return -ENODEV; + } + pr_debug("Adding PCI host bridge %s\n", dev->full_name); /* Fetch host bridge registers address */ diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 14232d57369..49798532b47 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -1457,7 +1457,6 @@ int fsl_rio_setup(struct platform_device *dev) port->ops = ops; port->priv = priv; port->phys_efptr = 0x100; - rio_register_mport(port); priv->regs_win = ioremap(regs.start, regs.end - regs.start + 1); rio_regs_win = priv->regs_win; @@ -1504,6 +1503,9 @@ int fsl_rio_setup(struct platform_device *dev) dev_info(&dev->dev, "RapidIO Common Transport System size: %d\n", port->sys_size ? 65536 : 256); + if (rio_register_mport(port)) + goto err; + if (port->host_deviceid >= 0) out_be32(priv->regs_win + RIO_GCCSR, RIO_PORT_GEN_HOST | RIO_PORT_GEN_MASTER | RIO_PORT_GEN_DISCOVERED); diff --git a/arch/um/Kconfig.x86 b/arch/um/Kconfig.x86 index 02fb017fed4..a9da516a527 100644 --- a/arch/um/Kconfig.x86 +++ b/arch/um/Kconfig.x86 @@ -4,6 +4,10 @@ menu "UML-specific options" menu "Host processor type and features" +config CMPXCHG_LOCAL + bool + default n + source "arch/x86/Kconfig.cpu" endmenu diff --git a/arch/um/include/asm/bug.h b/arch/um/include/asm/bug.h new file mode 100644 index 00000000000..9e33b864c35 --- /dev/null +++ b/arch/um/include/asm/bug.h @@ -0,0 +1,6 @@ +#ifndef __UM_BUG_H +#define __UM_BUG_H + +#include <asm-generic/bug.h> + +#endif diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index fd5a1f365c9..3cce71413d0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -96,11 +96,15 @@ #define MSR_IA32_MC0_ADDR 0x00000402 #define MSR_IA32_MC0_MISC 0x00000403 +#define MSR_AMD64_MC0_MASK 0xc0010044 + #define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x)) #define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x)) #define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x)) #define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x)) +#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x)) + /* These are consecutive and not in the normal 4er MCE bank block */ #define MSR_IA32_MC0_CTL2 0x00000280 #define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x)) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 3ecece0217e..3532d3bf810 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -615,6 +615,25 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) /* As a rule processors have APIC timer running in deep C states */ if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400)) set_cpu_cap(c, X86_FEATURE_ARAT); + + /* + * Disable GART TLB Walk Errors on Fam10h. We do this here + * because this is always needed when GART is enabled, even in a + * kernel which has no MCE support built in. + */ + if (c->x86 == 0x10) { + /* + * BIOS should disable GartTlbWlk Errors themself. If + * it doesn't do it here as suggested by the BKDG. + * + * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 + */ + u64 mask; + + rdmsrl(MSR_AMD64_MCx_MASK(4), mask); + mask |= (1 << 10); + wrmsrl(MSR_AMD64_MCx_MASK(4), mask); + } } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c2871d3c71b..8ed8908cc9f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -312,6 +312,26 @@ void __cpuinit smp_store_cpu_info(int id) identify_secondary_cpu(c); } +static void __cpuinit check_cpu_siblings_on_same_node(int cpu1, int cpu2) +{ + int node1 = early_cpu_to_node(cpu1); + int node2 = early_cpu_to_node(cpu2); + + /* + * Our CPU scheduler assumes all logical cpus in the same physical cpu + * share the same node. But, buggy ACPI or NUMA emulation might assign + * them to different node. Fix it. + */ + if (node1 != node2) { + pr_warning("CPU %d in node %d and CPU %d in node %d are in the same physical CPU. forcing same node %d\n", + cpu1, node1, cpu2, node2, node2); + + numa_remove_cpu(cpu1); + numa_set_node(cpu1, node2); + numa_add_cpu(cpu1); + } +} + static void __cpuinit link_thread_siblings(int cpu1, int cpu2) { cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2)); @@ -320,6 +340,7 @@ static void __cpuinit link_thread_siblings(int cpu1, int cpu2) cpumask_set_cpu(cpu2, cpu_core_mask(cpu1)); cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2)); cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1)); + check_cpu_siblings_on_same_node(cpu1, cpu2); } @@ -361,10 +382,12 @@ void __cpuinit set_cpu_sibling_map(int cpu) per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { cpumask_set_cpu(i, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(i)); + check_cpu_siblings_on_same_node(cpu, i); } if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(i)); + check_cpu_siblings_on_same_node(cpu, i); /* * Does this new cpu bringup a new core? */ diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts index dc701ea5854..2d6d226f2b1 100644 --- a/arch/x86/platform/ce4100/falconfalls.dts +++ b/arch/x86/platform/ce4100/falconfalls.dts @@ -74,6 +74,7 @@ compatible = "intel,ce4100-pci", "pci"; device_type = "pci"; bus-range = <1 1>; + reg = <0x0800 0x0 0x0 0x0 0x0>; ranges = <0x2000000 0 0xdffe0000 0x2000000 0 0xdffe0000 0 0x1000>; interrupt-parent = <&ioapic2>; @@ -412,6 +413,7 @@ #address-cells = <2>; #size-cells = <1>; compatible = "isa"; + reg = <0xf800 0x0 0x0 0x0 0x0>; ranges = <1 0 0 0 0 0x100>; rtc@70 { diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index 5c0207bf959..275dbc19e2c 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -97,11 +97,11 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table) pentry->freq_hz, pentry->irq); if (!pentry->irq) continue; - mp_irq.type = MP_IOAPIC; + mp_irq.type = MP_INTSRC; mp_irq.irqtype = mp_INT; /* triggering mode edge bit 2-3, active high polarity bit 0-1 */ mp_irq.irqflag = 5; - mp_irq.srcbus = 0; + mp_irq.srcbus = MP_BUS_ISA; mp_irq.srcbusirq = pentry->irq; /* IRQ */ mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; @@ -168,10 +168,10 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) { pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n", totallen, (u32)pentry->phys_addr, pentry->irq); - mp_irq.type = MP_IOAPIC; + mp_irq.type = MP_INTSRC; mp_irq.irqtype = mp_INT; mp_irq.irqflag = 0xf; /* level trigger and active low */ - mp_irq.srcbus = 0; + mp_irq.srcbus = MP_BUS_ISA; mp_irq.srcbusirq = pentry->irq; /* IRQ */ mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; @@ -282,7 +282,7 @@ void __init x86_mrst_early_setup(void) /* Avoid searching for BIOS MP tables */ x86_init.mpparse.find_smp_config = x86_init_noop; x86_init.mpparse.get_smp_config = x86_init_uint_noop; - + set_bit(MP_BUS_ISA, mp_bus_not_pci); } /* diff --git a/block/blk-core.c b/block/blk-core.c index 90f22cc3079..5fa3dd2705c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -198,26 +198,13 @@ void blk_dump_rq_flags(struct request *rq, char *msg) } EXPORT_SYMBOL(blk_dump_rq_flags); -/* - * Make sure that plugs that were pending when this function was entered, - * are now complete and requests pushed to the queue. -*/ -static inline void queue_sync_plugs(struct request_queue *q) -{ - /* - * If the current process is plugged and has barriers submitted, - * we will livelock if we don't unplug first. - */ - blk_flush_plug(current); -} - static void blk_delay_work(struct work_struct *work) { struct request_queue *q; q = container_of(work, struct request_queue, delay_work.work); spin_lock_irq(q->queue_lock); - __blk_run_queue(q, false); + __blk_run_queue(q); spin_unlock_irq(q->queue_lock); } @@ -233,7 +220,8 @@ static void blk_delay_work(struct work_struct *work) */ void blk_delay_queue(struct request_queue *q, unsigned long msecs) { - schedule_delayed_work(&q->delay_work, msecs_to_jiffies(msecs)); + queue_delayed_work(kblockd_workqueue, &q->delay_work, + msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_delay_queue); @@ -251,7 +239,7 @@ void blk_start_queue(struct request_queue *q) WARN_ON(!irqs_disabled()); queue_flag_clear(QUEUE_FLAG_STOPPED, q); - __blk_run_queue(q, false); + __blk_run_queue(q); } EXPORT_SYMBOL(blk_start_queue); @@ -298,7 +286,6 @@ void blk_sync_queue(struct request_queue *q) { del_timer_sync(&q->timeout); cancel_delayed_work_sync(&q->delay_work); - queue_sync_plugs(q); } EXPORT_SYMBOL(blk_sync_queue); @@ -310,9 +297,8 @@ EXPORT_SYMBOL(blk_sync_queue); * Description: * See @blk_run_queue. This variant must be called with the queue lock * held and interrupts disabled. - * */ -void __blk_run_queue(struct request_queue *q, bool force_kblockd) +void __blk_run_queue(struct request_queue *q) { if (unlikely(blk_queue_stopped(q))) return; @@ -321,7 +307,7 @@ void __blk_run_queue(struct request_queue *q, bool force_kblockd) * Only recurse once to avoid overrunning the stack, let the unplug * handling reinvoke the handler shortly if we already got there. */ - if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) { + if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) { q->request_fn(q); queue_flag_clear(QUEUE_FLAG_REENTER, q); } else @@ -330,6 +316,20 @@ void __blk_run_queue(struct request_queue *q, bool force_kblockd) EXPORT_SYMBOL(__blk_run_queue); /** + * blk_run_queue_async - run a single device queue in workqueue context + * @q: The queue to run + * + * Description: + * Tells kblockd to perform the equivalent of @blk_run_queue on behalf + * of us. + */ +void blk_run_queue_async(struct request_queue *q) +{ + if (likely(!blk_queue_stopped(q))) + queue_delayed_work(kblockd_workqueue, &q->delay_work, 0); +} + +/** * blk_run_queue - run a single device queue * @q: The queue to run * @@ -342,7 +342,7 @@ void blk_run_queue(struct request_queue *q) unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); - __blk_run_queue(q, false); + __blk_run_queue(q); spin_unlock_irqrestore(q->queue_lock, flags); } EXPORT_SYMBOL(blk_run_queue); @@ -991,7 +991,7 @@ void blk_insert_request(struct request_queue *q, struct request *rq, blk_queue_end_tag(q, rq); add_acct_request(q, rq, where); - __blk_run_queue(q, false); + __blk_run_queue(q); spin_unlock_irqrestore(q->queue_lock, flags); } EXPORT_SYMBOL(blk_insert_request); @@ -1311,7 +1311,15 @@ get_rq: plug = current->plug; if (plug) { - if (!plug->should_sort && !list_empty(&plug->list)) { + /* + * If this is the first request added after a plug, fire + * of a plug trace. If others have been added before, check + * if we have multiple devices in this plug. If so, make a + * note to sort the list before dispatch. + */ + if (list_empty(&plug->list)) + trace_block_plug(q); + else if (!plug->should_sort) { struct request *__rq; __rq = list_entry_rq(plug->list.prev); @@ -1327,7 +1335,7 @@ get_rq: } else { spin_lock_irq(q->queue_lock); add_acct_request(q, req, where); - __blk_run_queue(q, false); + __blk_run_queue(q); out_unlock: spin_unlock_irq(q->queue_lock); } @@ -2644,6 +2652,7 @@ void blk_start_plug(struct blk_plug *plug) plug->magic = PLUG_MAGIC; INIT_LIST_HEAD(&plug->list); + INIT_LIST_HEAD(&plug->cb_list); plug->should_sort = 0; /* @@ -2668,33 +2677,93 @@ static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b) return !(rqa->q <= rqb->q); } -static void flush_plug_list(struct blk_plug *plug) +/* + * If 'from_schedule' is true, then postpone the dispatch of requests + * until a safe kblockd context. We due this to avoid accidental big + * additional stack usage in driver dispatch, in places where the originally + * plugger did not intend it. + */ +static void queue_unplugged(struct request_queue *q, unsigned int depth, + bool from_schedule) + __releases(q->queue_lock) +{ + trace_block_unplug(q, depth, !from_schedule); + + /* + * If we are punting this to kblockd, then we can safely drop + * the queue_lock before waking kblockd (which needs to take + * this lock). + */ + if (from_schedule) { + spin_unlock(q->queue_lock); + blk_run_queue_async(q); + } else { + __blk_run_queue(q); + spin_unlock(q->queue_lock); + } + +} + +static void flush_plug_callbacks(struct blk_plug *plug) +{ + LIST_HEAD(callbacks); + + if (list_empty(&plug->cb_list)) + return; + + list_splice_init(&plug->cb_list, &callbacks); + + while (!list_empty(&callbacks)) { + struct blk_plug_cb *cb = list_first_entry(&callbacks, + struct blk_plug_cb, + list); + list_del(&cb->list); + cb->callback(cb); + } +} + +void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) { struct request_queue *q; unsigned long flags; struct request *rq; + LIST_HEAD(list); + unsigned int depth; BUG_ON(plug->magic != PLUG_MAGIC); + flush_plug_callbacks(plug); if (list_empty(&plug->list)) return; - if (plug->should_sort) - list_sort(NULL, &plug->list, plug_rq_cmp); + list_splice_init(&plug->list, &list); + + if (plug->should_sort) { + list_sort(NULL, &list, plug_rq_cmp); + plug->should_sort = 0; + } q = NULL; + depth = 0; + + /* + * Save and disable interrupts here, to avoid doing it for every + * queue lock we have to take. + */ local_irq_save(flags); - while (!list_empty(&plug->list)) { - rq = list_entry_rq(plug->list.next); + while (!list_empty(&list)) { + rq = list_entry_rq(list.next); list_del_init(&rq->queuelist); BUG_ON(!(rq->cmd_flags & REQ_ON_PLUG)); BUG_ON(!rq->q); if (rq->q != q) { - if (q) { - __blk_run_queue(q, false); - spin_unlock(q->queue_lock); - } + /* + * This drops the queue lock + */ + if (q) + queue_unplugged(q, depth, from_schedule); q = rq->q; + depth = 0; spin_lock(q->queue_lock); } rq->cmd_flags &= ~REQ_ON_PLUG; @@ -2706,38 +2775,28 @@ static void flush_plug_list(struct blk_plug *plug) __elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH); else __elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE); - } - if (q) { - __blk_run_queue(q, false); - spin_unlock(q->queue_lock); + depth++; } - BUG_ON(!list_empty(&plug->list)); - local_irq_restore(flags); -} - -static void __blk_finish_plug(struct task_struct *tsk, struct blk_plug *plug) -{ - flush_plug_list(plug); + /* + * This drops the queue lock + */ + if (q) + queue_unplugged(q, depth, from_schedule); - if (plug == tsk->plug) - tsk->plug = NULL; + local_irq_restore(flags); } +EXPORT_SYMBOL(blk_flush_plug_list); void blk_finish_plug(struct blk_plug *plug) { - if (plug) - __blk_finish_plug(current, plug); -} -EXPORT_SYMBOL(blk_finish_plug); + blk_flush_plug_list(plug, false); -void __blk_flush_plug(struct task_struct *tsk, struct blk_plug *plug) -{ - __blk_finish_plug(tsk, plug); - tsk->plug = plug; + if (plug == current->plug) + current->plug = NULL; } -EXPORT_SYMBOL(__blk_flush_plug); +EXPORT_SYMBOL(blk_finish_plug); int __init blk_dev_init(void) { diff --git a/block/blk-exec.c b/block/blk-exec.c index 7482b7fa863..81e31819a59 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -55,7 +55,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, WARN_ON(irqs_disabled()); spin_lock_irq(q->queue_lock); __elv_add_request(q, rq, where); - __blk_run_queue(q, false); + __blk_run_queue(q); /* the queue is stopped so it won't be plugged+unplugged */ if (rq->cmd_type == REQ_TYPE_PM_RESUME) q->request_fn(q); diff --git a/block/blk-flush.c b/block/blk-flush.c index eba4a2790c6..6c9b5e189e6 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -218,7 +218,7 @@ static void flush_end_io(struct request *flush_rq, int error) * request_fn may confuse the driver. Always use kblockd. */ if (queued) - __blk_run_queue(q, true); + blk_run_queue_async(q); } /** @@ -274,7 +274,7 @@ static void flush_data_end_io(struct request *rq, int error) * the comment in flush_end_io(). */ if (blk_flush_complete_seq(rq, REQ_FSEQ_DATA, error)) - __blk_run_queue(q, true); + blk_run_queue_async(q); } /** diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 261c75c665a..6d735122bc5 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -498,7 +498,6 @@ int blk_register_queue(struct gendisk *disk) { int ret; struct device *dev = disk_to_dev(disk); - struct request_queue *q = disk->queue; if (WARN_ON(!q)) @@ -521,7 +520,7 @@ int blk_register_queue(struct gendisk *disk) if (ret) { kobject_uevent(&q->kobj, KOBJ_REMOVE); kobject_del(&q->kobj); - blk_trace_remove_sysfs(disk_to_dev(disk)); + blk_trace_remove_sysfs(dev); kobject_put(&dev->kobj); return ret; } diff --git a/block/blk.h b/block/blk.h index 61263463e38..c9df8fc3c99 100644 --- a/block/blk.h +++ b/block/blk.h @@ -22,6 +22,7 @@ void blk_rq_timed_out_timer(unsigned long data); void blk_delete_timer(struct request *); void blk_add_timer(struct request *); void __generic_unplug_device(struct request_queue *); +void blk_run_queue_async(struct request_queue *q); /* * Internal atomic flags for request handling diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 3be881ec95a..46b0a1d1d92 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3368,7 +3368,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfqd->busy_queues > 1) { cfq_del_timer(cfqd, cfqq); cfq_clear_cfqq_wait_request(cfqq); - __blk_run_queue(cfqd->queue, false); + __blk_run_queue(cfqd->queue); } else { cfq_blkiocg_update_idle_time_stats( &cfqq->cfqg->blkg); @@ -3383,7 +3383,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, * this new queue is RT and the current one is BE */ cfq_preempt_queue(cfqd, cfqq); - __blk_run_queue(cfqd->queue, false); + __blk_run_queue(cfqd->queue); } } @@ -3743,7 +3743,7 @@ static void cfq_kick_queue(struct work_struct *work) struct request_queue *q = cfqd->queue; spin_lock_irq(q->queue_lock); - __blk_run_queue(cfqd->queue, false); + __blk_run_queue(cfqd->queue); spin_unlock_irq(q->queue_lock); } diff --git a/block/elevator.c b/block/elevator.c index 0cdb4e7ebab..6f6abc08bb5 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -642,7 +642,7 @@ void elv_quiesce_start(struct request_queue *q) */ elv_drain_elevator(q); while (q->rq.elvpriv) { - __blk_run_queue(q, false); + __blk_run_queue(q); spin_unlock_irq(q->queue_lock); msleep(10); spin_lock_irq(q->queue_lock); @@ -695,7 +695,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where) * with anything. There's no point in delaying queue * processing. */ - __blk_run_queue(q, false); + __blk_run_queue(q); break; case ELEVATOR_INSERT_SORT_MERGE: diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c index 38319a69bd0..d6d58684712 100644 --- a/drivers/i2c/algos/i2c-algo-bit.c +++ b/drivers/i2c/algos/i2c-algo-bit.c @@ -232,9 +232,17 @@ static int i2c_inb(struct i2c_adapter *i2c_adap) * Sanity check for the adapter hardware - check the reaction of * the bus lines only if it seems to be idle. */ -static int test_bus(struct i2c_algo_bit_data *adap, char *name) +static int test_bus(struct i2c_adapter *i2c_adap) { - int scl, sda; + struct i2c_algo_bit_data *adap = i2c_adap->algo_data; + const char *name = i2c_adap->name; + int scl, sda, ret; + + if (adap->pre_xfer) { + ret = adap->pre_xfer(i2c_adap); + if (ret < 0) + return -ENODEV; + } if (adap->getscl == NULL) pr_info("%s: Testing SDA only, SCL is not readable\n", name); @@ -297,11 +305,19 @@ static int test_bus(struct i2c_algo_bit_data *adap, char *name) "while pulling SCL high!\n", name); goto bailout; } + + if (adap->post_xfer) + adap->post_xfer(i2c_adap); + pr_info("%s: Test OK\n", name); return 0; bailout: sdahi(adap); sclhi(adap); + + if (adap->post_xfer) + adap->post_xfer(i2c_adap); + return -ENODEV; } @@ -607,7 +623,7 @@ static int __i2c_bit_add_bus(struct i2c_adapter *adap, int ret; if (bit_test) { - ret = test_bus(bit_adap, adap->name); + ret = test_bus(adap); if (ret < 0) return -ENODEV; } diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 70c30e6bce0..9a58994ff7e 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -797,7 +797,8 @@ static int i2c_do_add_adapter(struct i2c_driver *driver, /* Let legacy drivers scan this bus for matching devices */ if (driver->attach_adapter) { - dev_warn(&adap->dev, "attach_adapter method is deprecated\n"); + dev_warn(&adap->dev, "%s: attach_adapter method is deprecated\n", + driver->driver.name); dev_warn(&adap->dev, "Please use another way to instantiate " "your i2c_client\n"); /* We ignore the return code; if it fails, too bad */ @@ -984,7 +985,8 @@ static int i2c_do_del_adapter(struct i2c_driver *driver, if (!driver->detach_adapter) return 0; - dev_warn(&adapter->dev, "detach_adapter method is deprecated\n"); + dev_warn(&adapter->dev, "%s: detach_adapter method is deprecated\n", + driver->driver.name); res = driver->detach_adapter(adapter); if (res) dev_err(&adapter->dev, "detach_adapter failed (%d) " diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 7f42d3a454d..88d8e4cb419 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -39,13 +39,13 @@ struct evdev { }; struct evdev_client { - int head; - int tail; + unsigned int head; + unsigned int tail; spinlock_t buffer_lock; /* protects access to buffer, head and tail */ struct fasync_struct *fasync; struct evdev *evdev; struct list_head node; - int bufsize; + unsigned int bufsize; struct input_event buffer[]; }; @@ -55,16 +55,25 @@ static DEFINE_MUTEX(evdev_table_mutex); static void evdev_pass_event(struct evdev_client *client, struct input_event *event) { - /* - * Interrupts are disabled, just acquire the lock. - * Make sure we don't leave with the client buffer - * "empty" by having client->head == client->tail. - */ + /* Interrupts are disabled, just acquire the lock. */ spin_lock(&client->buffer_lock); - do { - client->buffer[client->head++] = *event; - client->head &= client->bufsize - 1; - } while (client->head == client->tail); + + client->buffer[client->head++] = *event; + client->head &= client->bufsize - 1; + + if (unlikely(client->head == client->tail)) { + /* + * This effectively "drops" all unconsumed events, leaving + * EV_SYN/SYN_DROPPED plus the newest event in the queue. + */ + client->tail = (client->head - 2) & (client->bufsize - 1); + + client->buffer[client->tail].time = event->time; + client->buffer[client->tail].type = EV_SYN; + client->buffer[client->tail].code = SYN_DROPPED; + client->buffer[client->tail].value = 0; + } + spin_unlock(&client->buffer_lock); if (event->type == EV_SYN) diff --git a/drivers/input/input.c b/drivers/input/input.c index d6e8bd8a851..ebbceedc92f 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1746,6 +1746,42 @@ void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int } EXPORT_SYMBOL(input_set_capability); +static unsigned int input_estimate_events_per_packet(struct input_dev *dev) +{ + int mt_slots; + int i; + unsigned int events; + + if (dev->mtsize) { + mt_slots = dev->mtsize; + } else if (test_bit(ABS_MT_TRACKING_ID, dev->absbit)) { + mt_slots = dev->absinfo[ABS_MT_TRACKING_ID].maximum - + dev->absinfo[ABS_MT_TRACKING_ID].minimum + 1, + clamp(mt_slots, 2, 32); + } else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) { + mt_slots = 2; + } else { + mt_slots = 0; + } + + events = mt_slots + 1; /* count SYN_MT_REPORT and SYN_REPORT */ + + for (i = 0; i < ABS_CNT; i++) { + if (test_bit(i, dev->absbit)) { + if (input_is_mt_axis(i)) + events += mt_slots; + else + events++; + } + } + + for (i = 0; i < REL_CNT; i++) + if (test_bit(i, dev->relbit)) + events++; + + return events; +} + #define INPUT_CLEANSE_BITMASK(dev, type, bits) \ do { \ if (!test_bit(EV_##type, dev->evbit)) \ @@ -1793,6 +1829,10 @@ int input_register_device(struct input_dev *dev) /* Make sure that bitmasks not mentioned in dev->evbit are clean. */ input_cleanse_bitmasks(dev); + if (!dev->hint_events_per_packet) + dev->hint_events_per_packet = + input_estimate_events_per_packet(dev); + /* * If delay and period are pre-set by the driver, then autorepeating * is handled by the driver itself and we don't do it in input.c. diff --git a/drivers/input/keyboard/twl4030_keypad.c b/drivers/input/keyboard/twl4030_keypad.c index 09bef79d9da..a26922cf0e8 100644 --- a/drivers/input/keyboard/twl4030_keypad.c +++ b/drivers/input/keyboard/twl4030_keypad.c @@ -332,18 +332,20 @@ static int __devinit twl4030_kp_program(struct twl4030_keypad *kp) static int __devinit twl4030_kp_probe(struct platform_device *pdev) { struct twl4030_keypad_data *pdata = pdev->dev.platform_data; - const struct matrix_keymap_data *keymap_data = pdata->keymap_data; + const struct matrix_keymap_data *keymap_data; struct twl4030_keypad *kp; struct input_dev *input; u8 reg; int error; - if (!pdata || !pdata->rows || !pdata->cols || + if (!pdata || !pdata->rows || !pdata->cols || !pdata->keymap_data || pdata->rows > TWL4030_MAX_ROWS || pdata->cols > TWL4030_MAX_COLS) { dev_err(&pdev->dev, "Invalid platform_data\n"); return -EINVAL; } + keymap_data = pdata->keymap_data; + kp = kzalloc(sizeof(*kp), GFP_KERNEL); input = input_allocate_device(); if (!kp || !input) { diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c index 7077f9bf5ea..62bae99424e 100644 --- a/drivers/input/misc/xen-kbdfront.c +++ b/drivers/input/misc/xen-kbdfront.c @@ -303,7 +303,7 @@ static void xenkbd_backend_changed(struct xenbus_device *dev, enum xenbus_state backend_state) { struct xenkbd_info *info = dev_get_drvdata(&dev->dev); - int val; + int ret, val; switch (backend_state) { case XenbusStateInitialising: @@ -316,6 +316,17 @@ static void xenkbd_backend_changed(struct xenbus_device *dev, case XenbusStateInitWait: InitWait: + ret = xenbus_scanf(XBT_NIL, info->xbdev->otherend, + "feature-abs-pointer", "%d", &val); + if (ret < 0) + val = 0; + if (val) { + ret = xenbus_printf(XBT_NIL, info->xbdev->nodename, + "request-abs-pointer", "1"); + if (ret) + pr_warning("xenkbd: can't request abs-pointer"); + } + xenbus_switch_state(dev, XenbusStateConnected); break; diff --git a/drivers/input/touchscreen/h3600_ts_input.c b/drivers/input/touchscreen/h3600_ts_input.c index efa06882de0..45f93d0f559 100644 --- a/drivers/input/touchscreen/h3600_ts_input.c +++ b/drivers/input/touchscreen/h3600_ts_input.c @@ -399,31 +399,34 @@ static int h3600ts_connect(struct serio *serio, struct serio_driver *drv) IRQF_SHARED | IRQF_DISABLED, "h3600_action", &ts->dev)) { printk(KERN_ERR "h3600ts.c: Could not allocate Action Button IRQ!\n"); err = -EBUSY; - goto fail2; + goto fail1; } if (request_irq(IRQ_GPIO_BITSY_NPOWER_BUTTON, npower_button_handler, IRQF_SHARED | IRQF_DISABLED, "h3600_suspend", &ts->dev)) { printk(KERN_ERR "h3600ts.c: Could not allocate Power Button IRQ!\n"); err = -EBUSY; - goto fail3; + goto fail2; } serio_set_drvdata(serio, ts); err = serio_open(serio, drv); if (err) - return err; + goto fail3; //h3600_flite_control(1, 25); /* default brightness */ - input_register_device(ts->dev); + err = input_register_device(ts->dev); + if (err) + goto fail4; return 0; -fail3: free_irq(IRQ_GPIO_BITSY_NPOWER_BUTTON, ts->dev); +fail4: serio_close(serio); +fail3: serio_set_drvdata(serio, NULL); + free_irq(IRQ_GPIO_BITSY_NPOWER_BUTTON, ts->dev); fail2: free_irq(IRQ_GPIO_BITSY_ACTION_BUTTON, ts->dev); -fail1: serio_set_drvdata(serio, NULL); - input_free_device(input_dev); +fail1: input_free_device(input_dev); kfree(ts); return err; } diff --git a/drivers/leds/leds-regulator.c b/drivers/leds/leds-regulator.c index 3790816643b..8497f56f8e4 100644 --- a/drivers/leds/leds-regulator.c +++ b/drivers/leds/leds-regulator.c @@ -178,6 +178,10 @@ static int __devinit regulator_led_probe(struct platform_device *pdev) led->cdev.flags |= LED_CORE_SUSPENDRESUME; led->vcc = vcc; + /* to handle correctly an already enabled regulator */ + if (regulator_is_enabled(led->vcc)) + led->enabled = 1; + mutex_init(&led->mutex); INIT_WORK(&led->work, led_work); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5ef136cdba9..e5d8904fc8f 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -390,13 +390,6 @@ static int raid_is_congested(struct dm_target_callbacks *cb, int bits) return md_raid5_congested(&rs->md, bits); } -static void raid_unplug(struct dm_target_callbacks *cb) -{ - struct raid_set *rs = container_of(cb, struct raid_set, callbacks); - - md_raid5_kick_device(rs->md.private); -} - /* * Construct a RAID4/5/6 mapping: * Args: @@ -487,7 +480,6 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv) } rs->callbacks.congested_fn = raid_is_congested; - rs->callbacks.unplug_fn = raid_unplug; dm_table_add_target_callbacks(ti->table, &rs->callbacks); return 0; diff --git a/drivers/md/md.c b/drivers/md/md.c index b12b3776c0c..6e853c61d87 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -447,48 +447,59 @@ EXPORT_SYMBOL(md_flush_request); /* Support for plugging. * This mirrors the plugging support in request_queue, but does not - * require having a whole queue + * require having a whole queue or request structures. + * We allocate an md_plug_cb for each md device and each thread it gets + * plugged on. This links tot the private plug_handle structure in the + * personality data where we keep a count of the number of outstanding + * plugs so other code can see if a plug is active. */ -static void plugger_work(struct work_struct *work) -{ - struct plug_handle *plug = - container_of(work, struct plug_handle, unplug_work); - plug->unplug_fn(plug); -} -static void plugger_timeout(unsigned long data) -{ - struct plug_handle *plug = (void *)data; - kblockd_schedule_work(NULL, &plug->unplug_work); -} -void plugger_init(struct plug_handle *plug, - void (*unplug_fn)(struct plug_handle *)) -{ - plug->unplug_flag = 0; - plug->unplug_fn = unplug_fn; - init_timer(&plug->unplug_timer); - plug->unplug_timer.function = plugger_timeout; - plug->unplug_timer.data = (unsigned long)plug; - INIT_WORK(&plug->unplug_work, plugger_work); -} -EXPORT_SYMBOL_GPL(plugger_init); +struct md_plug_cb { + struct blk_plug_cb cb; + mddev_t *mddev; +}; -void plugger_set_plug(struct plug_handle *plug) +static void plugger_unplug(struct blk_plug_cb *cb) { - if (!test_and_set_bit(PLUGGED_FLAG, &plug->unplug_flag)) - mod_timer(&plug->unplug_timer, jiffies + msecs_to_jiffies(3)+1); + struct md_plug_cb *mdcb = container_of(cb, struct md_plug_cb, cb); + if (atomic_dec_and_test(&mdcb->mddev->plug_cnt)) + md_wakeup_thread(mdcb->mddev->thread); + kfree(mdcb); } -EXPORT_SYMBOL_GPL(plugger_set_plug); -int plugger_remove_plug(struct plug_handle *plug) +/* Check that an unplug wakeup will come shortly. + * If not, wakeup the md thread immediately + */ +int mddev_check_plugged(mddev_t *mddev) { - if (test_and_clear_bit(PLUGGED_FLAG, &plug->unplug_flag)) { - del_timer(&plug->unplug_timer); - return 1; - } else + struct blk_plug *plug = current->plug; + struct md_plug_cb *mdcb; + + if (!plug) + return 0; + + list_for_each_entry(mdcb, &plug->cb_list, cb.list) { + if (mdcb->cb.callback == plugger_unplug && + mdcb->mddev == mddev) { + /* Already on the list, move to top */ + if (mdcb != list_first_entry(&plug->cb_list, + struct md_plug_cb, + cb.list)) + list_move(&mdcb->cb.list, &plug->cb_list); + return 1; + } + } + /* Not currently on the callback list */ + mdcb = kmalloc(sizeof(*mdcb), GFP_ATOMIC); + if (!mdcb) return 0; -} -EXPORT_SYMBOL_GPL(plugger_remove_plug); + mdcb->mddev = mddev; + mdcb->cb.callback = plugger_unplug; + atomic_inc(&mddev->plug_cnt); + list_add(&mdcb->cb.list, &plug->cb_list); + return 1; +} +EXPORT_SYMBOL_GPL(mddev_check_plugged); static inline mddev_t *mddev_get(mddev_t *mddev) { @@ -538,6 +549,7 @@ void mddev_init(mddev_t *mddev) atomic_set(&mddev->active, 1); atomic_set(&mddev->openers, 0); atomic_set(&mddev->active_io, 0); + atomic_set(&mddev->plug_cnt, 0); spin_lock_init(&mddev->write_lock); atomic_set(&mddev->flush_pending, 0); init_waitqueue_head(&mddev->sb_wait); @@ -4723,7 +4735,6 @@ static void md_clean(mddev_t *mddev) mddev->bitmap_info.chunksize = 0; mddev->bitmap_info.daemon_sleep = 0; mddev->bitmap_info.max_write_behind = 0; - mddev->plug = NULL; } static void __md_stop_writes(mddev_t *mddev) @@ -6688,12 +6699,6 @@ int md_allow_write(mddev_t *mddev) } EXPORT_SYMBOL_GPL(md_allow_write); -void md_unplug(mddev_t *mddev) -{ - if (mddev->plug) - mddev->plug->unplug_fn(mddev->plug); -} - #define SYNC_MARKS 10 #define SYNC_MARK_STEP (3*HZ) void md_do_sync(mddev_t *mddev) diff --git a/drivers/md/md.h b/drivers/md/md.h index 52b407369e1..0b1fd3f1d85 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -29,26 +29,6 @@ typedef struct mddev_s mddev_t; typedef struct mdk_rdev_s mdk_rdev_t; -/* generic plugging support - like that provided with request_queue, - * but does not require a request_queue - */ -struct plug_handle { - void (*unplug_fn)(struct plug_handle *); - struct timer_list unplug_timer; - struct work_struct unplug_work; - unsigned long unplug_flag; -}; -#define PLUGGED_FLAG 1 -void plugger_init(struct plug_handle *plug, - void (*unplug_fn)(struct plug_handle *)); -void plugger_set_plug(struct plug_handle *plug); -int plugger_remove_plug(struct plug_handle *plug); -static inline void plugger_flush(struct plug_handle *plug) -{ - del_timer_sync(&plug->unplug_timer); - cancel_work_sync(&plug->unplug_work); -} - /* * MD's 'extended' device */ @@ -199,6 +179,9 @@ struct mddev_s int delta_disks, new_level, new_layout; int new_chunk_sectors; + atomic_t plug_cnt; /* If device is expecting + * more bios soon. + */ struct mdk_thread_s *thread; /* management thread */ struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */ sector_t curr_resync; /* last block scheduled */ @@ -336,7 +319,6 @@ struct mddev_s struct list_head all_mddevs; struct attribute_group *to_remove; - struct plug_handle *plug; /* if used by personality */ struct bio_set *bio_set; @@ -516,7 +498,6 @@ extern int md_integrity_register(mddev_t *mddev); extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); extern void restore_bitmap_write_access(struct file *file); -extern void md_unplug(mddev_t *mddev); extern void mddev_init(mddev_t *mddev); extern int md_run(mddev_t *mddev); @@ -530,4 +511,5 @@ extern struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask, mddev_t *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, mddev_t *mddev); +extern int mddev_check_plugged(mddev_t *mddev); #endif /* _MD_MD_H */ diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index c2a21ae56d9..2b7a7ff401d 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -565,12 +565,6 @@ static void flush_pending_writes(conf_t *conf) spin_unlock_irq(&conf->device_lock); } -static void md_kick_device(mddev_t *mddev) -{ - blk_flush_plug(current); - md_wakeup_thread(mddev->thread); -} - /* Barriers.... * Sometimes we need to suspend IO while we do something else, * either some resync/recovery, or reconfigure the array. @@ -600,7 +594,7 @@ static void raise_barrier(conf_t *conf) /* Wait until no block IO is waiting */ wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting, - conf->resync_lock, md_kick_device(conf->mddev)); + conf->resync_lock, ); /* block any new IO from starting */ conf->barrier++; @@ -608,7 +602,7 @@ static void raise_barrier(conf_t *conf) /* Now wait for all pending IO to complete */ wait_event_lock_irq(conf->wait_barrier, !conf->nr_pending && conf->barrier < RESYNC_DEPTH, - conf->resync_lock, md_kick_device(conf->mddev)); + conf->resync_lock, ); spin_unlock_irq(&conf->resync_lock); } @@ -630,7 +624,7 @@ static void wait_barrier(conf_t *conf) conf->nr_waiting++; wait_event_lock_irq(conf->wait_barrier, !conf->barrier, conf->resync_lock, - md_kick_device(conf->mddev)); + ); conf->nr_waiting--; } conf->nr_pending++; @@ -666,8 +660,7 @@ static void freeze_array(conf_t *conf) wait_event_lock_irq(conf->wait_barrier, conf->nr_pending == conf->nr_queued+1, conf->resync_lock, - ({ flush_pending_writes(conf); - md_kick_device(conf->mddev); })); + flush_pending_writes(conf)); spin_unlock_irq(&conf->resync_lock); } static void unfreeze_array(conf_t *conf) @@ -729,6 +722,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA)); mdk_rdev_t *blocked_rdev; + int plugged; /* * Register the new request and wait if the reconstruction @@ -820,6 +814,8 @@ static int make_request(mddev_t *mddev, struct bio * bio) * inc refcount on their rdev. Record them by setting * bios[x] to bio */ + plugged = mddev_check_plugged(mddev); + disks = conf->raid_disks; retry_write: blocked_rdev = NULL; @@ -925,7 +921,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) /* In case raid1d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - if (do_sync || !bitmap) + if (do_sync || !bitmap || !plugged) md_wakeup_thread(mddev->thread); return 0; @@ -1516,13 +1512,16 @@ static void raid1d(mddev_t *mddev) conf_t *conf = mddev->private; struct list_head *head = &conf->retry_list; mdk_rdev_t *rdev; + struct blk_plug plug; md_check_recovery(mddev); - + + blk_start_plug(&plug); for (;;) { char b[BDEVNAME_SIZE]; - flush_pending_writes(conf); + if (atomic_read(&mddev->plug_cnt) == 0) + flush_pending_writes(conf); spin_lock_irqsave(&conf->device_lock, flags); if (list_empty(head)) { @@ -1593,6 +1592,7 @@ static void raid1d(mddev_t *mddev) } cond_resched(); } + blk_finish_plug(&plug); } @@ -2039,7 +2039,6 @@ static int stop(mddev_t *mddev) md_unregister_thread(mddev->thread); mddev->thread = NULL; - blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/ if (conf->r1bio_pool) mempool_destroy(conf->r1bio_pool); kfree(conf->mirrors); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 2da83d56659..8e9462626ec 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -634,12 +634,6 @@ static void flush_pending_writes(conf_t *conf) spin_unlock_irq(&conf->device_lock); } -static void md_kick_device(mddev_t *mddev) -{ - blk_flush_plug(current); - md_wakeup_thread(mddev->thread); -} - /* Barriers.... * Sometimes we need to suspend IO while we do something else, * either some resync/recovery, or reconfigure the array. @@ -669,15 +663,15 @@ static void raise_barrier(conf_t *conf, int force) /* Wait until no block IO is waiting (unless 'force') */ wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting, - conf->resync_lock, md_kick_device(conf->mddev)); + conf->resync_lock, ); /* block any new IO from starting */ conf->barrier++; - /* No wait for all pending IO to complete */ + /* Now wait for all pending IO to complete */ wait_event_lock_irq(conf->wait_barrier, !conf->nr_pending && conf->barrier < RESYNC_DEPTH, - conf->resync_lock, md_kick_device(conf->mddev)); + conf->resync_lock, ); spin_unlock_irq(&conf->resync_lock); } @@ -698,7 +692,7 @@ static void wait_barrier(conf_t *conf) conf->nr_waiting++; wait_event_lock_irq(conf->wait_barrier, !conf->barrier, conf->resync_lock, - md_kick_device(conf->mddev)); + ); conf->nr_waiting--; } conf->nr_pending++; @@ -734,8 +728,8 @@ static void freeze_array(conf_t *conf) wait_event_lock_irq(conf->wait_barrier, conf->nr_pending == conf->nr_queued+1, conf->resync_lock, - ({ flush_pending_writes(conf); - md_kick_device(conf->mddev); })); + flush_pending_writes(conf)); + spin_unlock_irq(&conf->resync_lock); } @@ -762,6 +756,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) const unsigned long do_fua = (bio->bi_rw & REQ_FUA); unsigned long flags; mdk_rdev_t *blocked_rdev; + int plugged; if (unlikely(bio->bi_rw & REQ_FLUSH)) { md_flush_request(mddev, bio); @@ -870,6 +865,8 @@ static int make_request(mddev_t *mddev, struct bio * bio) * inc refcount on their rdev. Record them by setting * bios[x] to bio */ + plugged = mddev_check_plugged(mddev); + raid10_find_phys(conf, r10_bio); retry_write: blocked_rdev = NULL; @@ -946,9 +943,8 @@ static int make_request(mddev_t *mddev, struct bio * bio) /* In case raid10d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - if (do_sync || !mddev->bitmap) + if (do_sync || !mddev->bitmap || !plugged) md_wakeup_thread(mddev->thread); - return 0; } @@ -1640,9 +1636,11 @@ static void raid10d(mddev_t *mddev) conf_t *conf = mddev->private; struct list_head *head = &conf->retry_list; mdk_rdev_t *rdev; + struct blk_plug plug; md_check_recovery(mddev); + blk_start_plug(&plug); for (;;) { char b[BDEVNAME_SIZE]; @@ -1716,6 +1714,7 @@ static void raid10d(mddev_t *mddev) } cond_resched(); } + blk_finish_plug(&plug); } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e867ee42b15..f301e6ae220 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -27,12 +27,12 @@ * * We group bitmap updates into batches. Each batch has a number. * We may write out several batches at once, but that isn't very important. - * conf->bm_write is the number of the last batch successfully written. - * conf->bm_flush is the number of the last batch that was closed to + * conf->seq_write is the number of the last batch successfully written. + * conf->seq_flush is the number of the last batch that was closed to * new additions. * When we discover that we will need to write to any block in a stripe * (in add_stripe_bio) we update the in-memory bitmap and record in sh->bm_seq - * the number of the batch it will be in. This is bm_flush+1. + * the number of the batch it will be in. This is seq_flush+1. * When we are ready to do a write, if that batch hasn't been written yet, * we plug the array and queue the stripe for later. * When an unplug happens, we increment bm_flush, thus closing the current @@ -199,14 +199,12 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh) BUG_ON(!list_empty(&sh->lru)); BUG_ON(atomic_read(&conf->active_stripes)==0); if (test_bit(STRIPE_HANDLE, &sh->state)) { - if (test_bit(STRIPE_DELAYED, &sh->state)) { + if (test_bit(STRIPE_DELAYED, &sh->state)) list_add_tail(&sh->lru, &conf->delayed_list); - plugger_set_plug(&conf->plug); - } else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && - sh->bm_seq - conf->seq_write > 0) { + else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && + sh->bm_seq - conf->seq_write > 0) list_add_tail(&sh->lru, &conf->bitmap_list); - plugger_set_plug(&conf->plug); - } else { + else { clear_bit(STRIPE_BIT_DELAY, &sh->state); list_add_tail(&sh->lru, &conf->handle_list); } @@ -461,7 +459,7 @@ get_active_stripe(raid5_conf_t *conf, sector_t sector, < (conf->max_nr_stripes *3/4) || !conf->inactive_blocked), conf->device_lock, - md_raid5_kick_device(conf)); + ); conf->inactive_blocked = 0; } else init_stripe(sh, sector, previous); @@ -1470,7 +1468,7 @@ static int resize_stripes(raid5_conf_t *conf, int newsize) wait_event_lock_irq(conf->wait_for_stripe, !list_empty(&conf->inactive_list), conf->device_lock, - blk_flush_plug(current)); + ); osh = get_free_stripe(conf); spin_unlock_irq(&conf->device_lock); atomic_set(&nsh->count, 1); @@ -3623,8 +3621,7 @@ static void raid5_activate_delayed(raid5_conf_t *conf) atomic_inc(&conf->preread_active_stripes); list_add_tail(&sh->lru, &conf->hold_list); } - } else - plugger_set_plug(&conf->plug); + } } static void activate_bit_delay(raid5_conf_t *conf) @@ -3641,21 +3638,6 @@ static void activate_bit_delay(raid5_conf_t *conf) } } -void md_raid5_kick_device(raid5_conf_t *conf) -{ - blk_flush_plug(current); - raid5_activate_delayed(conf); - md_wakeup_thread(conf->mddev->thread); -} -EXPORT_SYMBOL_GPL(md_raid5_kick_device); - -static void raid5_unplug(struct plug_handle *plug) -{ - raid5_conf_t *conf = container_of(plug, raid5_conf_t, plug); - - md_raid5_kick_device(conf); -} - int md_raid5_congested(mddev_t *mddev, int bits) { raid5_conf_t *conf = mddev->private; @@ -3945,6 +3927,7 @@ static int make_request(mddev_t *mddev, struct bio * bi) struct stripe_head *sh; const int rw = bio_data_dir(bi); int remaining; + int plugged; if (unlikely(bi->bi_rw & REQ_FLUSH)) { md_flush_request(mddev, bi); @@ -3963,6 +3946,7 @@ static int make_request(mddev_t *mddev, struct bio * bi) bi->bi_next = NULL; bi->bi_phys_segments = 1; /* over-loaded to count active stripes */ + plugged = mddev_check_plugged(mddev); for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) { DEFINE_WAIT(w); int disks, data_disks; @@ -4057,7 +4041,7 @@ static int make_request(mddev_t *mddev, struct bio * bi) * add failed due to overlap. Flush everything * and wait a while */ - md_raid5_kick_device(conf); + md_wakeup_thread(mddev->thread); release_stripe(sh); schedule(); goto retry; @@ -4077,6 +4061,9 @@ static int make_request(mddev_t *mddev, struct bio * bi) } } + if (!plugged) + md_wakeup_thread(mddev->thread); + spin_lock_irq(&conf->device_lock); remaining = raid5_dec_bi_phys_segments(bi); spin_unlock_irq(&conf->device_lock); @@ -4478,24 +4465,30 @@ static void raid5d(mddev_t *mddev) struct stripe_head *sh; raid5_conf_t *conf = mddev->private; int handled; + struct blk_plug plug; pr_debug("+++ raid5d active\n"); md_check_recovery(mddev); + blk_start_plug(&plug); handled = 0; spin_lock_irq(&conf->device_lock); while (1) { struct bio *bio; - if (conf->seq_flush != conf->seq_write) { - int seq = conf->seq_flush; + if (atomic_read(&mddev->plug_cnt) == 0 && + !list_empty(&conf->bitmap_list)) { + /* Now is a good time to flush some bitmap updates */ + conf->seq_flush++; spin_unlock_irq(&conf->device_lock); bitmap_unplug(mddev->bitmap); spin_lock_irq(&conf->device_lock); - conf->seq_write = seq; + conf->seq_write = conf->seq_flush; activate_bit_delay(conf); } + if (atomic_read(&mddev->plug_cnt) == 0) + raid5_activate_delayed(conf); while ((bio = remove_bio_from_retry(conf))) { int ok; @@ -4525,6 +4518,7 @@ static void raid5d(mddev_t *mddev) spin_unlock_irq(&conf->device_lock); async_tx_issue_pending_all(); + blk_finish_plug(&plug); pr_debug("--- raid5d inactive\n"); } @@ -5141,8 +5135,6 @@ static int run(mddev_t *mddev) mdname(mddev)); md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); - plugger_init(&conf->plug, raid5_unplug); - mddev->plug = &conf->plug; if (mddev->queue) { int chunk_size; /* read-ahead size must cover two whole stripes, which @@ -5192,7 +5184,6 @@ static int stop(mddev_t *mddev) mddev->thread = NULL; if (mddev->queue) mddev->queue->backing_dev_info.congested_fn = NULL; - plugger_flush(&conf->plug); /* the unplug fn references 'conf'*/ free_conf(conf); mddev->private = NULL; mddev->to_remove = &raid5_attrs_group; diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 8d563a4f022..3ca77a2613b 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -400,8 +400,6 @@ struct raid5_private_data { * Cleared when a sync completes. */ - struct plug_handle plug; - /* per cpu variables */ struct raid5_percpu { struct page *spare_page; /* Used when checking P/Q in raid6 */ diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index 20e4e9395b6..ecafa4ba238 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -348,15 +348,15 @@ static unsigned long gru_chiplet_cpu_to_mmr(int chiplet, int cpu, int *corep) static int gru_irq_count[GRU_CHIPLETS_PER_BLADE]; -static void gru_noop(unsigned int irq) +static void gru_noop(struct irq_data *d) { } static struct irq_chip gru_chip[GRU_CHIPLETS_PER_BLADE] = { [0 ... GRU_CHIPLETS_PER_BLADE - 1] { - .mask = gru_noop, - .unmask = gru_noop, - .ack = gru_noop + .irq_mask = gru_noop, + .irq_unmask = gru_noop, + .irq_ack = gru_noop } }; diff --git a/drivers/pcmcia/pxa2xx_balloon3.c b/drivers/pcmcia/pxa2xx_balloon3.c index 453c54c9761..4c3e94c0ae8 100644 --- a/drivers/pcmcia/pxa2xx_balloon3.c +++ b/drivers/pcmcia/pxa2xx_balloon3.c @@ -25,6 +25,8 @@ #include <mach/balloon3.h> +#include <asm/mach-types.h> + #include "soc_common.h" /* @@ -127,6 +129,9 @@ static int __init balloon3_pcmcia_init(void) { int ret; + if (!machine_is_balloon3()) + return -ENODEV; + balloon3_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1); if (!balloon3_pcmcia_device) return -ENOMEM; diff --git a/drivers/pcmcia/pxa2xx_trizeps4.c b/drivers/pcmcia/pxa2xx_trizeps4.c index b7e596620db..b829e655457 100644 --- a/drivers/pcmcia/pxa2xx_trizeps4.c +++ b/drivers/pcmcia/pxa2xx_trizeps4.c @@ -69,15 +69,15 @@ static int trizeps_pcmcia_hw_init(struct soc_pcmcia_socket *skt) for (i = 0; i < ARRAY_SIZE(irqs); i++) { if (irqs[i].sock != skt->nr) continue; - if (gpio_request(IRQ_TO_GPIO(irqs[i].irq), irqs[i].str) < 0) { + if (gpio_request(irq_to_gpio(irqs[i].irq), irqs[i].str) < 0) { pr_err("%s: sock %d unable to request gpio %d\n", - __func__, skt->nr, IRQ_TO_GPIO(irqs[i].irq)); + __func__, skt->nr, irq_to_gpio(irqs[i].irq)); ret = -EBUSY; goto error; } - if (gpio_direction_input(IRQ_TO_GPIO(irqs[i].irq)) < 0) { + if (gpio_direction_input(irq_to_gpio(irqs[i].irq)) < 0) { pr_err("%s: sock %d unable to set input gpio %d\n", - __func__, skt->nr, IRQ_TO_GPIO(irqs[i].irq)); + __func__, skt->nr, irq_to_gpio(irqs[i].irq)); ret = -EINVAL; goto error; } @@ -86,7 +86,7 @@ static int trizeps_pcmcia_hw_init(struct soc_pcmcia_socket *skt) error: for (; i >= 0; i--) { - gpio_free(IRQ_TO_GPIO(irqs[i].irq)); + gpio_free(irq_to_gpio(irqs[i].irq)); } return (ret); } @@ -97,7 +97,7 @@ static void trizeps_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt) /* free allocated gpio's */ gpio_free(GPIO_PRDY); for (i = 0; i < ARRAY_SIZE(irqs); i++) - gpio_free(IRQ_TO_GPIO(irqs[i].irq)); + gpio_free(irq_to_gpio(irqs[i].irq)); } static unsigned long trizeps_pcmcia_status[2]; @@ -226,6 +226,9 @@ static int __init trizeps_pcmcia_init(void) { int ret; + if (!machine_is_trizeps4() && !machine_is_trizeps4wl()) + return -ENODEV; + trizeps_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1); if (!trizeps_pcmcia_device) return -ENOMEM; diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c index c29719cacbc..86c9a091a2f 100644 --- a/drivers/rapidio/rio.c +++ b/drivers/rapidio/rio.c @@ -1171,16 +1171,17 @@ static int rio_hdid_setup(char *str) __setup("riohdid=", rio_hdid_setup); -void rio_register_mport(struct rio_mport *port) +int rio_register_mport(struct rio_mport *port) { if (next_portid >= RIO_MAX_MPORTS) { pr_err("RIO: reached specified max number of mports\n"); - return; + return 1; } port->id = next_portid++; port->host_deviceid = rio_get_hdid(port->id); list_add_tail(&port->node, &rio_mports); + return 0; } EXPORT_SYMBOL_GPL(rio_local_get_device_id); diff --git a/drivers/rapidio/switches/idt_gen2.c b/drivers/rapidio/switches/idt_gen2.c index 095016a9dec..ac2701b22e7 100644 --- a/drivers/rapidio/switches/idt_gen2.c +++ b/drivers/rapidio/switches/idt_gen2.c @@ -418,3 +418,4 @@ DECLARE_RIO_SWITCH_INIT(RIO_VID_IDT, RIO_DID_IDTCPS1848, idtg2_switch_init); DECLARE_RIO_SWITCH_INIT(RIO_VID_IDT, RIO_DID_IDTCPS1616, idtg2_switch_init); DECLARE_RIO_SWITCH_INIT(RIO_VID_IDT, RIO_DID_IDTVPS1616, idtg2_switch_init); DECLARE_RIO_SWITCH_INIT(RIO_VID_IDT, RIO_DID_IDTSPS1616, idtg2_switch_init); +DECLARE_RIO_SWITCH_INIT(RIO_VID_IDT, RIO_DID_IDTCPS1432, idtg2_switch_init); diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 09b4437b3e6..39013867cbd 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -171,7 +171,7 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev, err = __rtc_read_alarm(rtc, &alrm); if (!err && !rtc_valid_tm(&alrm.time)) - rtc_set_alarm(rtc, &alrm); + rtc_initialize_alarm(rtc, &alrm); strlcpy(rtc->name, name, RTC_DEVICE_NAME_SIZE); dev_set_name(&rtc->dev, "rtc%d", id); diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 23719f0acbf..ef6316acec4 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -375,6 +375,32 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) } EXPORT_SYMBOL_GPL(rtc_set_alarm); +/* Called once per device from rtc_device_register */ +int rtc_initialize_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) +{ + int err; + + err = rtc_valid_tm(&alarm->time); + if (err != 0) + return err; + + err = mutex_lock_interruptible(&rtc->ops_lock); + if (err) + return err; + + rtc->aie_timer.node.expires = rtc_tm_to_ktime(alarm->time); + rtc->aie_timer.period = ktime_set(0, 0); + if (alarm->enabled) { + rtc->aie_timer.enabled = 1; + timerqueue_add(&rtc->timerqueue, &rtc->aie_timer.node); + } + mutex_unlock(&rtc->ops_lock); + return err; +} +EXPORT_SYMBOL_GPL(rtc_initialize_alarm); + + + int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled) { int err = mutex_lock_interruptible(&rtc->ops_lock); diff --git a/drivers/rtc/rtc-bfin.c b/drivers/rtc/rtc-bfin.c index a0fc4cf42ab..90d866272c8 100644 --- a/drivers/rtc/rtc-bfin.c +++ b/drivers/rtc/rtc-bfin.c @@ -250,6 +250,8 @@ static int bfin_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) bfin_rtc_int_set_alarm(rtc); else bfin_rtc_int_clear(~(RTC_ISTAT_ALARM | RTC_ISTAT_ALARM_DAY)); + + return 0; } static int bfin_rtc_read_time(struct device *dev, struct rtc_time *tm) diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c index c4200646955..c5ac03793e7 100644 --- a/drivers/rtc/rtc-mc13xxx.c +++ b/drivers/rtc/rtc-mc13xxx.c @@ -401,6 +401,7 @@ const struct platform_device_id mc13xxx_rtc_idtable[] = { }, { .name = "mc13892-rtc", }, + { } }; static struct platform_driver mc13xxx_rtc_driver = { diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 714964913e5..b3466c491cd 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -336,7 +336,6 @@ static void s3c_rtc_release(struct device *dev) /* do not clear AIE here, it may be needed for wake */ - s3c_rtc_setpie(dev, 0); free_irq(s3c_rtc_alarmno, rtc_dev); free_irq(s3c_rtc_tickno, rtc_dev); } @@ -408,7 +407,6 @@ static int __devexit s3c_rtc_remove(struct platform_device *dev) platform_set_drvdata(dev, NULL); rtc_device_unregister(rtc); - s3c_rtc_setpie(&dev->dev, 0); s3c_rtc_setaie(&dev->dev, 0); clk_disable(rtc_clk); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 6d5c7ff43f5..ab55c2fa7ce 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -443,7 +443,7 @@ static void scsi_run_queue(struct request_queue *q) &sdev->request_queue->queue_flags); if (flagset) queue_flag_set(QUEUE_FLAG_REENTER, sdev->request_queue); - __blk_run_queue(sdev->request_queue, false); + __blk_run_queue(sdev->request_queue); if (flagset) queue_flag_clear(QUEUE_FLAG_REENTER, sdev->request_queue); spin_unlock(sdev->request_queue->queue_lock); diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index fdf3fa63905..28c33506e4a 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -3829,7 +3829,7 @@ fc_bsg_goose_queue(struct fc_rport *rport) !test_bit(QUEUE_FLAG_REENTER, &rport->rqst_q->queue_flags); if (flagset) queue_flag_set(QUEUE_FLAG_REENTER, rport->rqst_q); - __blk_run_queue(rport->rqst_q, false); + __blk_run_queue(rport->rqst_q); if (flagset) queue_flag_clear(QUEUE_FLAG_REENTER, rport->rqst_q); spin_unlock_irqrestore(rport->rqst_q->queue_lock, flags); diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig index 41b6e51188e..006489d82dc 100644 --- a/drivers/usb/Kconfig +++ b/drivers/usb/Kconfig @@ -66,6 +66,7 @@ config USB_ARCH_HAS_EHCI default y if ARCH_VT8500 default y if PLAT_SPEAR default y if ARCH_MSM + default y if MICROBLAZE default PCI # ARM SA1111 chips have a non-PCI based "OHCI-compatible" USB host interface. diff --git a/drivers/usb/core/devices.c b/drivers/usb/core/devices.c index a3d2e239965..96fdfb815f8 100644 --- a/drivers/usb/core/devices.c +++ b/drivers/usb/core/devices.c @@ -221,7 +221,7 @@ static char *usb_dump_endpoint_descriptor(int speed, char *start, char *end, break; case USB_ENDPOINT_XFER_INT: type = "Int."; - if (speed == USB_SPEED_HIGH) + if (speed == USB_SPEED_HIGH || speed == USB_SPEED_SUPER) interval = 1 << (desc->bInterval - 1); else interval = desc->bInterval; @@ -229,7 +229,8 @@ static char *usb_dump_endpoint_descriptor(int speed, char *start, char *end, default: /* "can't happen" */ return start; } - interval *= (speed == USB_SPEED_HIGH) ? 125 : 1000; + interval *= (speed == USB_SPEED_HIGH || + speed == USB_SPEED_SUPER) ? 125 : 1000; if (interval % 1000) unit = 'u'; else { @@ -542,8 +543,9 @@ static ssize_t usb_device_dump(char __user **buffer, size_t *nbytes, if (level == 0) { int max; - /* high speed reserves 80%, full/low reserves 90% */ - if (usbdev->speed == USB_SPEED_HIGH) + /* super/high speed reserves 80%, full/low reserves 90% */ + if (usbdev->speed == USB_SPEED_HIGH || + usbdev->speed == USB_SPEED_SUPER) max = 800; else max = FRAME_TIME_MAX_USECS_ALLOC; diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 8eed05d2383..77a7faec8d7 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1908,7 +1908,7 @@ void usb_free_streams(struct usb_interface *interface, /* Streams only apply to bulk endpoints. */ for (i = 0; i < num_eps; i++) - if (!usb_endpoint_xfer_bulk(&eps[i]->desc)) + if (!eps[i] || !usb_endpoint_xfer_bulk(&eps[i]->desc)) return; hcd->driver->free_streams(hcd, dev, eps, num_eps, mem_flags); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 8fb754916c6..93720bdc9ef 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2285,7 +2285,17 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg) } /* see 7.1.7.6 */ - status = set_port_feature(hub->hdev, port1, USB_PORT_FEAT_SUSPEND); + /* Clear PORT_POWER if it's a USB3.0 device connected to USB 3.0 + * external hub. + * FIXME: this is a temporary workaround to make the system able + * to suspend/resume. + */ + if ((hub->hdev->parent != NULL) && hub_is_superspeed(hub->hdev)) + status = clear_port_feature(hub->hdev, port1, + USB_PORT_FEAT_POWER); + else + status = set_port_feature(hub->hdev, port1, + USB_PORT_FEAT_SUSPEND); if (status) { dev_dbg(hub->intfdev, "can't suspend port %d, status %d\n", port1, status); diff --git a/drivers/usb/gadget/f_audio.c b/drivers/usb/gadget/f_audio.c index 9abecfddb27..0111f8a9cf7 100644 --- a/drivers/usb/gadget/f_audio.c +++ b/drivers/usb/gadget/f_audio.c @@ -706,6 +706,7 @@ f_audio_unbind(struct usb_configuration *c, struct usb_function *f) struct f_audio *audio = func_to_audio(f); usb_free_descriptors(f->descriptors); + usb_free_descriptors(f->hs_descriptors); kfree(audio); } diff --git a/drivers/usb/gadget/f_eem.c b/drivers/usb/gadget/f_eem.c index 95dd4662d6a..b3c30429015 100644 --- a/drivers/usb/gadget/f_eem.c +++ b/drivers/usb/gadget/f_eem.c @@ -314,6 +314,9 @@ eem_unbind(struct usb_configuration *c, struct usb_function *f) static void eem_cmd_complete(struct usb_ep *ep, struct usb_request *req) { + struct sk_buff *skb = (struct sk_buff *)req->context; + + dev_kfree_skb_any(skb); } /* @@ -428,10 +431,11 @@ static int eem_unwrap(struct gether *port, skb_trim(skb2, len); put_unaligned_le16(BIT(15) | BIT(11) | len, skb_push(skb2, 2)); - skb_copy_bits(skb, 0, req->buf, skb->len); - req->length = skb->len; + skb_copy_bits(skb2, 0, req->buf, skb2->len); + req->length = skb2->len; req->complete = eem_cmd_complete; req->zero = 1; + req->context = skb2; if (usb_ep_queue(port->in_ep, req, GFP_ATOMIC)) DBG(cdev, "echo response queue fail\n"); break; diff --git a/drivers/usb/gadget/fsl_qe_udc.c b/drivers/usb/gadget/fsl_qe_udc.c index aee7e3c53c3..36613b37c50 100644 --- a/drivers/usb/gadget/fsl_qe_udc.c +++ b/drivers/usb/gadget/fsl_qe_udc.c @@ -1148,6 +1148,12 @@ static int qe_ep_tx(struct qe_ep *ep, struct qe_frame *frame) static int txcomplete(struct qe_ep *ep, unsigned char restart) { if (ep->tx_req != NULL) { + struct qe_req *req = ep->tx_req; + unsigned zlp = 0, last_len = 0; + + last_len = min_t(unsigned, req->req.length - ep->sent, + ep->ep.maxpacket); + if (!restart) { int asent = ep->last; ep->sent += asent; @@ -1156,9 +1162,18 @@ static int txcomplete(struct qe_ep *ep, unsigned char restart) ep->last = 0; } + /* zlp needed when req->re.zero is set */ + if (req->req.zero) { + if (last_len == 0 || + (req->req.length % ep->ep.maxpacket) != 0) + zlp = 0; + else + zlp = 1; + } else + zlp = 0; + /* a request already were transmitted completely */ - if ((ep->tx_req->req.length - ep->sent) <= 0) { - ep->tx_req->req.actual = (unsigned int)ep->sent; + if (((ep->tx_req->req.length - ep->sent) <= 0) && !zlp) { done(ep, ep->tx_req, 0); ep->tx_req = NULL; ep->last = 0; @@ -1191,6 +1206,7 @@ static int qe_usb_senddata(struct qe_ep *ep, struct qe_frame *frame) buf = (u8 *)ep->tx_req->req.buf + ep->sent; if (buf && size) { ep->last = size; + ep->tx_req->req.actual += size; frame_set_data(frame, buf); frame_set_length(frame, size); frame_set_status(frame, FRAME_OK); diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c index 3ed73f49cf1..a01383f71f3 100644 --- a/drivers/usb/gadget/inode.c +++ b/drivers/usb/gadget/inode.c @@ -386,8 +386,10 @@ ep_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) /* halt any endpoint by doing a "wrong direction" i/o call */ if (usb_endpoint_dir_in(&data->desc)) { - if (usb_endpoint_xfer_isoc(&data->desc)) + if (usb_endpoint_xfer_isoc(&data->desc)) { + mutex_unlock(&data->lock); return -EINVAL; + } DBG (data->dev, "%s halt\n", data->name); spin_lock_irq (&data->dev->lock); if (likely (data->ep != NULL)) diff --git a/drivers/usb/gadget/pch_udc.c b/drivers/usb/gadget/pch_udc.c index 3e4b35e50c2..68dbcc3e4cc 100644 --- a/drivers/usb/gadget/pch_udc.c +++ b/drivers/usb/gadget/pch_udc.c @@ -1608,7 +1608,7 @@ static int pch_udc_pcd_queue(struct usb_ep *usbep, struct usb_request *usbreq, return -EINVAL; if (!dev->driver || (dev->gadget.speed == USB_SPEED_UNKNOWN)) return -ESHUTDOWN; - spin_lock_irqsave(&ep->dev->lock, iflags); + spin_lock_irqsave(&dev->lock, iflags); /* map the buffer for dma */ if (usbreq->length && ((usbreq->dma == DMA_ADDR_INVALID) || !usbreq->dma)) { @@ -1625,8 +1625,10 @@ static int pch_udc_pcd_queue(struct usb_ep *usbep, struct usb_request *usbreq, DMA_FROM_DEVICE); } else { req->buf = kzalloc(usbreq->length, GFP_ATOMIC); - if (!req->buf) - return -ENOMEM; + if (!req->buf) { + retval = -ENOMEM; + goto probe_end; + } if (ep->in) { memcpy(req->buf, usbreq->buf, usbreq->length); req->dma = dma_map_single(&dev->pdev->dev, diff --git a/drivers/usb/gadget/r8a66597-udc.c b/drivers/usb/gadget/r8a66597-udc.c index 015118535f7..6dcc1f68fa6 100644 --- a/drivers/usb/gadget/r8a66597-udc.c +++ b/drivers/usb/gadget/r8a66597-udc.c @@ -1083,7 +1083,9 @@ static void irq_device_state(struct r8a66597 *r8a66597) if (dvsq == DS_DFLT) { /* bus reset */ + spin_unlock(&r8a66597->lock); r8a66597->driver->disconnect(&r8a66597->gadget); + spin_lock(&r8a66597->lock); r8a66597_update_usb_speed(r8a66597); } if (r8a66597->old_dvsq == DS_CNFG && dvsq != DS_CNFG) diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index 98ded66e8d3..42abd0f603b 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -1247,24 +1247,27 @@ static void start_unlink_async (struct ehci_hcd *ehci, struct ehci_qh *qh) static void scan_async (struct ehci_hcd *ehci) { + bool stopped; struct ehci_qh *qh; enum ehci_timer_action action = TIMER_IO_WATCHDOG; ehci->stamp = ehci_readl(ehci, &ehci->regs->frame_index); timer_action_done (ehci, TIMER_ASYNC_SHRINK); rescan: + stopped = !HC_IS_RUNNING(ehci_to_hcd(ehci)->state); qh = ehci->async->qh_next.qh; if (likely (qh != NULL)) { do { /* clean any finished work for this qh */ - if (!list_empty (&qh->qtd_list) - && qh->stamp != ehci->stamp) { + if (!list_empty(&qh->qtd_list) && (stopped || + qh->stamp != ehci->stamp)) { int temp; /* unlinks could happen here; completion * reporting drops the lock. rescan using * the latest schedule, but don't rescan - * qhs we already finished (no looping). + * qhs we already finished (no looping) + * unless the controller is stopped. */ qh = qh_get (qh); qh->stamp = ehci->stamp; @@ -1285,9 +1288,9 @@ rescan: */ if (list_empty(&qh->qtd_list) && qh->qh_state == QH_STATE_LINKED) { - if (!ehci->reclaim - && ((ehci->stamp - qh->stamp) & 0x1fff) - >= (EHCI_SHRINK_FRAMES * 8)) + if (!ehci->reclaim && (stopped || + ((ehci->stamp - qh->stamp) & 0x1fff) + >= EHCI_SHRINK_FRAMES * 8)) start_unlink_async(ehci, qh); else action = TIMER_ASYNC_SHRINK; diff --git a/drivers/usb/host/isp1760-hcd.c b/drivers/usb/host/isp1760-hcd.c index f50e84ac570..795345ad45e 100644 --- a/drivers/usb/host/isp1760-hcd.c +++ b/drivers/usb/host/isp1760-hcd.c @@ -295,7 +295,7 @@ static void alloc_mem(struct usb_hcd *hcd, struct isp1760_qtd *qtd) } dev_err(hcd->self.controller, - "%s: Can not allocate %lu bytes of memory\n" + "%s: Cannot allocate %zu bytes of memory\n" "Current memory map:\n", __func__, qtd->length); for (i = 0; i < BLOCKS; i++) { diff --git a/drivers/usb/host/ohci-au1xxx.c b/drivers/usb/host/ohci-au1xxx.c index 17a6043c1fa..958d985f295 100644 --- a/drivers/usb/host/ohci-au1xxx.c +++ b/drivers/usb/host/ohci-au1xxx.c @@ -33,7 +33,7 @@ #ifdef __LITTLE_ENDIAN #define USBH_ENABLE_INIT (USBH_ENABLE_CE | USBH_ENABLE_E | USBH_ENABLE_C) -#elif __BIG_ENDIAN +#elif defined(__BIG_ENDIAN) #define USBH_ENABLE_INIT (USBH_ENABLE_CE | USBH_ENABLE_E | USBH_ENABLE_C | \ USBH_ENABLE_BE) #else diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 1d586d4f7b5..9b166d70ae9 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -84,65 +84,92 @@ int usb_amd_find_chipset_info(void) { u8 rev = 0; unsigned long flags; + struct amd_chipset_info info; + int ret; spin_lock_irqsave(&amd_lock, flags); - amd_chipset.probe_count++; /* probe only once */ - if (amd_chipset.probe_count > 1) { + if (amd_chipset.probe_count > 0) { + amd_chipset.probe_count++; spin_unlock_irqrestore(&amd_lock, flags); return amd_chipset.probe_result; } + memset(&info, 0, sizeof(info)); + spin_unlock_irqrestore(&amd_lock, flags); - amd_chipset.smbus_dev = pci_get_device(PCI_VENDOR_ID_ATI, 0x4385, NULL); - if (amd_chipset.smbus_dev) { - rev = amd_chipset.smbus_dev->revision; + info.smbus_dev = pci_get_device(PCI_VENDOR_ID_ATI, 0x4385, NULL); + if (info.smbus_dev) { + rev = info.smbus_dev->revision; if (rev >= 0x40) - amd_chipset.sb_type = 1; + info.sb_type = 1; else if (rev >= 0x30 && rev <= 0x3b) - amd_chipset.sb_type = 3; + info.sb_type = 3; } else { - amd_chipset.smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD, - 0x780b, NULL); - if (!amd_chipset.smbus_dev) { - spin_unlock_irqrestore(&amd_lock, flags); - return 0; + info.smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD, + 0x780b, NULL); + if (!info.smbus_dev) { + ret = 0; + goto commit; } - rev = amd_chipset.smbus_dev->revision; + + rev = info.smbus_dev->revision; if (rev >= 0x11 && rev <= 0x18) - amd_chipset.sb_type = 2; + info.sb_type = 2; } - if (amd_chipset.sb_type == 0) { - if (amd_chipset.smbus_dev) { - pci_dev_put(amd_chipset.smbus_dev); - amd_chipset.smbus_dev = NULL; + if (info.sb_type == 0) { + if (info.smbus_dev) { + pci_dev_put(info.smbus_dev); + info.smbus_dev = NULL; } - spin_unlock_irqrestore(&amd_lock, flags); - return 0; + ret = 0; + goto commit; } - amd_chipset.nb_dev = pci_get_device(PCI_VENDOR_ID_AMD, 0x9601, NULL); - if (amd_chipset.nb_dev) { - amd_chipset.nb_type = 1; + info.nb_dev = pci_get_device(PCI_VENDOR_ID_AMD, 0x9601, NULL); + if (info.nb_dev) { + info.nb_type = 1; } else { - amd_chipset.nb_dev = pci_get_device(PCI_VENDOR_ID_AMD, - 0x1510, NULL); - if (amd_chipset.nb_dev) { - amd_chipset.nb_type = 2; - } else { - amd_chipset.nb_dev = pci_get_device(PCI_VENDOR_ID_AMD, - 0x9600, NULL); - if (amd_chipset.nb_dev) - amd_chipset.nb_type = 3; + info.nb_dev = pci_get_device(PCI_VENDOR_ID_AMD, 0x1510, NULL); + if (info.nb_dev) { + info.nb_type = 2; + } else { + info.nb_dev = pci_get_device(PCI_VENDOR_ID_AMD, + 0x9600, NULL); + if (info.nb_dev) + info.nb_type = 3; } } - amd_chipset.probe_result = 1; + ret = info.probe_result = 1; printk(KERN_DEBUG "QUIRK: Enable AMD PLL fix\n"); - spin_unlock_irqrestore(&amd_lock, flags); - return amd_chipset.probe_result; +commit: + + spin_lock_irqsave(&amd_lock, flags); + if (amd_chipset.probe_count > 0) { + /* race - someone else was faster - drop devices */ + + /* Mark that we where here */ + amd_chipset.probe_count++; + ret = amd_chipset.probe_result; + + spin_unlock_irqrestore(&amd_lock, flags); + + if (info.nb_dev) + pci_dev_put(info.nb_dev); + if (info.smbus_dev) + pci_dev_put(info.smbus_dev); + + } else { + /* no race - commit the result */ + info.probe_count++; + amd_chipset = info; + spin_unlock_irqrestore(&amd_lock, flags); + } + + return ret; } EXPORT_SYMBOL_GPL(usb_amd_find_chipset_info); @@ -284,6 +311,7 @@ EXPORT_SYMBOL_GPL(usb_amd_quirk_pll_enable); void usb_amd_dev_put(void) { + struct pci_dev *nb, *smbus; unsigned long flags; spin_lock_irqsave(&amd_lock, flags); @@ -294,20 +322,23 @@ void usb_amd_dev_put(void) return; } - if (amd_chipset.nb_dev) { - pci_dev_put(amd_chipset.nb_dev); - amd_chipset.nb_dev = NULL; - } - if (amd_chipset.smbus_dev) { - pci_dev_put(amd_chipset.smbus_dev); - amd_chipset.smbus_dev = NULL; - } + /* save them to pci_dev_put outside of spinlock */ + nb = amd_chipset.nb_dev; + smbus = amd_chipset.smbus_dev; + + amd_chipset.nb_dev = NULL; + amd_chipset.smbus_dev = NULL; amd_chipset.nb_type = 0; amd_chipset.sb_type = 0; amd_chipset.isoc_reqs = 0; amd_chipset.probe_result = 0; spin_unlock_irqrestore(&amd_lock, flags); + + if (nb) + pci_dev_put(nb); + if (smbus) + pci_dev_put(smbus); } EXPORT_SYMBOL_GPL(usb_amd_dev_put); diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index a003e79aacd..627f3438028 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -846,7 +846,7 @@ static u32 xhci_find_real_port_number(struct xhci_hcd *xhci, * Skip ports that don't have known speeds, or have duplicate * Extended Capabilities port speed entries. */ - if (port_speed == 0 || port_speed == -1) + if (port_speed == 0 || port_speed == DUPLICATE_ENTRY) continue; /* @@ -974,6 +974,47 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud return 0; } +/* + * Convert interval expressed as 2^(bInterval - 1) == interval into + * straight exponent value 2^n == interval. + * + */ +static unsigned int xhci_parse_exponent_interval(struct usb_device *udev, + struct usb_host_endpoint *ep) +{ + unsigned int interval; + + interval = clamp_val(ep->desc.bInterval, 1, 16) - 1; + if (interval != ep->desc.bInterval - 1) + dev_warn(&udev->dev, + "ep %#x - rounding interval to %d microframes\n", + ep->desc.bEndpointAddress, + 1 << interval); + + return interval; +} + +/* + * Convert bInterval expressed in frames (in 1-255 range) to exponent of + * microframes, rounded down to nearest power of 2. + */ +static unsigned int xhci_parse_frame_interval(struct usb_device *udev, + struct usb_host_endpoint *ep) +{ + unsigned int interval; + + interval = fls(8 * ep->desc.bInterval) - 1; + interval = clamp_val(interval, 3, 10); + if ((1 << interval) != 8 * ep->desc.bInterval) + dev_warn(&udev->dev, + "ep %#x - rounding interval to %d microframes, ep desc says %d microframes\n", + ep->desc.bEndpointAddress, + 1 << interval, + 8 * ep->desc.bInterval); + + return interval; +} + /* Return the polling or NAK interval. * * The polling interval is expressed in "microframes". If xHCI's Interval field @@ -982,7 +1023,7 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud * The NAK interval is one NAK per 1 to 255 microframes, or no NAKs if interval * is set to 0. */ -static inline unsigned int xhci_get_endpoint_interval(struct usb_device *udev, +static unsigned int xhci_get_endpoint_interval(struct usb_device *udev, struct usb_host_endpoint *ep) { unsigned int interval = 0; @@ -991,45 +1032,38 @@ static inline unsigned int xhci_get_endpoint_interval(struct usb_device *udev, case USB_SPEED_HIGH: /* Max NAK rate */ if (usb_endpoint_xfer_control(&ep->desc) || - usb_endpoint_xfer_bulk(&ep->desc)) + usb_endpoint_xfer_bulk(&ep->desc)) { interval = ep->desc.bInterval; + break; + } /* Fall through - SS and HS isoc/int have same decoding */ + case USB_SPEED_SUPER: if (usb_endpoint_xfer_int(&ep->desc) || - usb_endpoint_xfer_isoc(&ep->desc)) { - if (ep->desc.bInterval == 0) - interval = 0; - else - interval = ep->desc.bInterval - 1; - if (interval > 15) - interval = 15; - if (interval != ep->desc.bInterval + 1) - dev_warn(&udev->dev, "ep %#x - rounding interval to %d microframes\n", - ep->desc.bEndpointAddress, 1 << interval); + usb_endpoint_xfer_isoc(&ep->desc)) { + interval = xhci_parse_exponent_interval(udev, ep); } break; - /* Convert bInterval (in 1-255 frames) to microframes and round down to - * nearest power of 2. - */ + case USB_SPEED_FULL: + if (usb_endpoint_xfer_int(&ep->desc)) { + interval = xhci_parse_exponent_interval(udev, ep); + break; + } + /* + * Fall through for isochronous endpoint interval decoding + * since it uses the same rules as low speed interrupt + * endpoints. + */ + case USB_SPEED_LOW: if (usb_endpoint_xfer_int(&ep->desc) || - usb_endpoint_xfer_isoc(&ep->desc)) { - interval = fls(8*ep->desc.bInterval) - 1; - if (interval > 10) - interval = 10; - if (interval < 3) - interval = 3; - if ((1 << interval) != 8*ep->desc.bInterval) - dev_warn(&udev->dev, - "ep %#x - rounding interval" - " to %d microframes, " - "ep desc says %d microframes\n", - ep->desc.bEndpointAddress, - 1 << interval, - 8*ep->desc.bInterval); + usb_endpoint_xfer_isoc(&ep->desc)) { + + interval = xhci_parse_frame_interval(udev, ep); } break; + default: BUG(); } @@ -1041,7 +1075,7 @@ static inline unsigned int xhci_get_endpoint_interval(struct usb_device *udev, * transaction opportunities per microframe", but that goes in the Max Burst * endpoint context field. */ -static inline u32 xhci_get_endpoint_mult(struct usb_device *udev, +static u32 xhci_get_endpoint_mult(struct usb_device *udev, struct usb_host_endpoint *ep) { if (udev->speed != USB_SPEED_SUPER || @@ -1050,7 +1084,7 @@ static inline u32 xhci_get_endpoint_mult(struct usb_device *udev, return ep->ss_ep_comp.bmAttributes; } -static inline u32 xhci_get_endpoint_type(struct usb_device *udev, +static u32 xhci_get_endpoint_type(struct usb_device *udev, struct usb_host_endpoint *ep) { int in; @@ -1084,7 +1118,7 @@ static inline u32 xhci_get_endpoint_type(struct usb_device *udev, * Basically, this is the maxpacket size, multiplied by the burst size * and mult size. */ -static inline u32 xhci_get_max_esit_payload(struct xhci_hcd *xhci, +static u32 xhci_get_max_esit_payload(struct xhci_hcd *xhci, struct usb_device *udev, struct usb_host_endpoint *ep) { @@ -1727,12 +1761,12 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, * found a similar duplicate. */ if (xhci->port_array[i] != major_revision && - xhci->port_array[i] != (u8) -1) { + xhci->port_array[i] != DUPLICATE_ENTRY) { if (xhci->port_array[i] == 0x03) xhci->num_usb3_ports--; else xhci->num_usb2_ports--; - xhci->port_array[i] = (u8) -1; + xhci->port_array[i] = DUPLICATE_ENTRY; } /* FIXME: Should we disable the port? */ continue; @@ -1831,7 +1865,7 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags) for (i = 0; i < num_ports; i++) { if (xhci->port_array[i] == 0x03 || xhci->port_array[i] == 0 || - xhci->port_array[i] == -1) + xhci->port_array[i] == DUPLICATE_ENTRY) continue; xhci->usb2_ports[port_index] = diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ceea9f33491..a10494c2f3c 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -114,6 +114,10 @@ static int xhci_pci_setup(struct usb_hcd *hcd) if (pdev->vendor == PCI_VENDOR_ID_NEC) xhci->quirks |= XHCI_NEC_HOST; + /* AMD PLL quirk */ + if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info()) + xhci->quirks |= XHCI_AMD_PLL_FIX; + /* Make sure the HC is halted. */ retval = xhci_halt(xhci); if (retval) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index cfc1ad92473..7437386a9a5 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -93,7 +93,7 @@ dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg, /* Does this link TRB point to the first segment in a ring, * or was the previous TRB the last TRB on the last segment in the ERST? */ -static inline bool last_trb_on_last_seg(struct xhci_hcd *xhci, struct xhci_ring *ring, +static bool last_trb_on_last_seg(struct xhci_hcd *xhci, struct xhci_ring *ring, struct xhci_segment *seg, union xhci_trb *trb) { if (ring == xhci->event_ring) @@ -107,7 +107,7 @@ static inline bool last_trb_on_last_seg(struct xhci_hcd *xhci, struct xhci_ring * segment? I.e. would the updated event TRB pointer step off the end of the * event seg? */ -static inline int last_trb(struct xhci_hcd *xhci, struct xhci_ring *ring, +static int last_trb(struct xhci_hcd *xhci, struct xhci_ring *ring, struct xhci_segment *seg, union xhci_trb *trb) { if (ring == xhci->event_ring) @@ -116,7 +116,7 @@ static inline int last_trb(struct xhci_hcd *xhci, struct xhci_ring *ring, return (trb->link.control & TRB_TYPE_BITMASK) == TRB_TYPE(TRB_LINK); } -static inline int enqueue_is_link_trb(struct xhci_ring *ring) +static int enqueue_is_link_trb(struct xhci_ring *ring) { struct xhci_link_trb *link = &ring->enqueue->link; return ((link->control & TRB_TYPE_BITMASK) == TRB_TYPE(TRB_LINK)); @@ -592,7 +592,7 @@ void xhci_queue_new_dequeue_state(struct xhci_hcd *xhci, ep->ep_state |= SET_DEQ_PENDING; } -static inline void xhci_stop_watchdog_timer_in_irq(struct xhci_hcd *xhci, +static void xhci_stop_watchdog_timer_in_irq(struct xhci_hcd *xhci, struct xhci_virt_ep *ep) { ep->ep_state &= ~EP_HALT_PENDING; @@ -619,6 +619,13 @@ static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci, /* Only giveback urb when this is the last td in urb */ if (urb_priv->td_cnt == urb_priv->length) { + if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) { + xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs--; + if (xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs == 0) { + if (xhci->quirks & XHCI_AMD_PLL_FIX) + usb_amd_quirk_pll_enable(); + } + } usb_hcd_unlink_urb_from_ep(hcd, urb); xhci_dbg(xhci, "Giveback %s URB %p\n", adjective, urb); @@ -1209,7 +1216,7 @@ static unsigned int find_faked_portnum_from_hw_portnum(struct usb_hcd *hcd, * Skip ports that don't have known speeds, or have duplicate * Extended Capabilities port speed entries. */ - if (port_speed == 0 || port_speed == -1) + if (port_speed == 0 || port_speed == DUPLICATE_ENTRY) continue; /* @@ -1235,6 +1242,7 @@ static void handle_port_status(struct xhci_hcd *xhci, u8 major_revision; struct xhci_bus_state *bus_state; u32 __iomem **port_array; + bool bogus_port_status = false; /* Port status change events always have a successful completion code */ if (GET_COMP_CODE(event->generic.field[2]) != COMP_SUCCESS) { @@ -1247,6 +1255,7 @@ static void handle_port_status(struct xhci_hcd *xhci, max_ports = HCS_MAX_PORTS(xhci->hcs_params1); if ((port_id <= 0) || (port_id > max_ports)) { xhci_warn(xhci, "Invalid port id %d\n", port_id); + bogus_port_status = true; goto cleanup; } @@ -1258,12 +1267,14 @@ static void handle_port_status(struct xhci_hcd *xhci, xhci_warn(xhci, "Event for port %u not in " "Extended Capabilities, ignoring.\n", port_id); + bogus_port_status = true; goto cleanup; } - if (major_revision == (u8) -1) { + if (major_revision == DUPLICATE_ENTRY) { xhci_warn(xhci, "Event for port %u duplicated in" "Extended Capabilities, ignoring.\n", port_id); + bogus_port_status = true; goto cleanup; } @@ -1335,6 +1346,13 @@ cleanup: /* Update event ring dequeue pointer before dropping the lock */ inc_deq(xhci, xhci->event_ring, true); + /* Don't make the USB core poll the roothub if we got a bad port status + * change event. Besides, at that point we can't tell which roothub + * (USB 2.0 or USB 3.0) to kick. + */ + if (bogus_port_status) + return; + spin_unlock(&xhci->lock); /* Pass this up to the core */ usb_hcd_poll_rh_status(hcd); @@ -1554,8 +1572,17 @@ td_cleanup: urb_priv->td_cnt++; /* Giveback the urb when all the tds are completed */ - if (urb_priv->td_cnt == urb_priv->length) + if (urb_priv->td_cnt == urb_priv->length) { ret = 1; + if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) { + xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs--; + if (xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs + == 0) { + if (xhci->quirks & XHCI_AMD_PLL_FIX) + usb_amd_quirk_pll_enable(); + } + } + } } return ret; @@ -1675,71 +1702,52 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, struct urb_priv *urb_priv; int idx; int len = 0; - int skip_td = 0; union xhci_trb *cur_trb; struct xhci_segment *cur_seg; + struct usb_iso_packet_descriptor *frame; u32 trb_comp_code; + bool skip_td = false; ep_ring = xhci_dma_to_transfer_ring(ep, event->buffer); trb_comp_code = GET_COMP_CODE(event->transfer_len); urb_priv = td->urb->hcpriv; idx = urb_priv->td_cnt; + frame = &td->urb->iso_frame_desc[idx]; - if (ep->skip) { - /* The transfer is partly done */ - *status = -EXDEV; - td->urb->iso_frame_desc[idx].status = -EXDEV; - } else { - /* handle completion code */ - switch (trb_comp_code) { - case COMP_SUCCESS: - td->urb->iso_frame_desc[idx].status = 0; - xhci_dbg(xhci, "Successful isoc transfer!\n"); - break; - case COMP_SHORT_TX: - if (td->urb->transfer_flags & URB_SHORT_NOT_OK) - td->urb->iso_frame_desc[idx].status = - -EREMOTEIO; - else - td->urb->iso_frame_desc[idx].status = 0; - break; - case COMP_BW_OVER: - td->urb->iso_frame_desc[idx].status = -ECOMM; - skip_td = 1; - break; - case COMP_BUFF_OVER: - case COMP_BABBLE: - td->urb->iso_frame_desc[idx].status = -EOVERFLOW; - skip_td = 1; - break; - case COMP_STALL: - td->urb->iso_frame_desc[idx].status = -EPROTO; - skip_td = 1; - break; - case COMP_STOP: - case COMP_STOP_INVAL: - break; - default: - td->urb->iso_frame_desc[idx].status = -1; - break; - } - } - - /* calc actual length */ - if (ep->skip) { - td->urb->iso_frame_desc[idx].actual_length = 0; - /* Update ring dequeue pointer */ - while (ep_ring->dequeue != td->last_trb) - inc_deq(xhci, ep_ring, false); - inc_deq(xhci, ep_ring, false); - return finish_td(xhci, td, event_trb, event, ep, status, true); + /* handle completion code */ + switch (trb_comp_code) { + case COMP_SUCCESS: + frame->status = 0; + xhci_dbg(xhci, "Successful isoc transfer!\n"); + break; + case COMP_SHORT_TX: + frame->status = td->urb->transfer_flags & URB_SHORT_NOT_OK ? + -EREMOTEIO : 0; + break; + case COMP_BW_OVER: + frame->status = -ECOMM; + skip_td = true; + break; + case COMP_BUFF_OVER: + case COMP_BABBLE: + frame->status = -EOVERFLOW; + skip_td = true; + break; + case COMP_STALL: + frame->status = -EPROTO; + skip_td = true; + break; + case COMP_STOP: + case COMP_STOP_INVAL: + break; + default: + frame->status = -1; + break; } - if (trb_comp_code == COMP_SUCCESS || skip_td == 1) { - td->urb->iso_frame_desc[idx].actual_length = - td->urb->iso_frame_desc[idx].length; - td->urb->actual_length += - td->urb->iso_frame_desc[idx].length; + if (trb_comp_code == COMP_SUCCESS || skip_td) { + frame->actual_length = frame->length; + td->urb->actual_length += frame->length; } else { for (cur_trb = ep_ring->dequeue, cur_seg = ep_ring->deq_seg; cur_trb != event_trb; @@ -1755,7 +1763,7 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, TRB_LEN(event->transfer_len); if (trb_comp_code != COMP_STOP_INVAL) { - td->urb->iso_frame_desc[idx].actual_length = len; + frame->actual_length = len; td->urb->actual_length += len; } } @@ -1766,6 +1774,35 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, return finish_td(xhci, td, event_trb, event, ep, status, false); } +static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, + struct xhci_transfer_event *event, + struct xhci_virt_ep *ep, int *status) +{ + struct xhci_ring *ep_ring; + struct urb_priv *urb_priv; + struct usb_iso_packet_descriptor *frame; + int idx; + + ep_ring = xhci_dma_to_transfer_ring(ep, event->buffer); + urb_priv = td->urb->hcpriv; + idx = urb_priv->td_cnt; + frame = &td->urb->iso_frame_desc[idx]; + + /* The transfer is partly done */ + *status = -EXDEV; + frame->status = -EXDEV; + + /* calc actual length */ + frame->actual_length = 0; + + /* Update ring dequeue pointer */ + while (ep_ring->dequeue != td->last_trb) + inc_deq(xhci, ep_ring, false); + inc_deq(xhci, ep_ring, false); + + return finish_td(xhci, td, NULL, event, ep, status, true); +} + /* * Process bulk and interrupt tds, update urb status and actual_length. */ @@ -2024,36 +2061,42 @@ static int handle_tx_event(struct xhci_hcd *xhci, } td = list_entry(ep_ring->td_list.next, struct xhci_td, td_list); + /* Is this a TRB in the currently executing TD? */ event_seg = trb_in_td(ep_ring->deq_seg, ep_ring->dequeue, td->last_trb, event_dma); - if (event_seg && ep->skip) { + if (!event_seg) { + if (!ep->skip || + !usb_endpoint_xfer_isoc(&td->urb->ep->desc)) { + /* HC is busted, give up! */ + xhci_err(xhci, + "ERROR Transfer event TRB DMA ptr not " + "part of current TD\n"); + return -ESHUTDOWN; + } + + ret = skip_isoc_td(xhci, td, event, ep, &status); + goto cleanup; + } + + if (ep->skip) { xhci_dbg(xhci, "Found td. Clear skip flag.\n"); ep->skip = false; } - if (!event_seg && - (!ep->skip || !usb_endpoint_xfer_isoc(&td->urb->ep->desc))) { - /* HC is busted, give up! */ - xhci_err(xhci, "ERROR Transfer event TRB DMA ptr not " - "part of current TD\n"); - return -ESHUTDOWN; - } - if (event_seg) { - event_trb = &event_seg->trbs[(event_dma - - event_seg->dma) / sizeof(*event_trb)]; - /* - * No-op TRB should not trigger interrupts. - * If event_trb is a no-op TRB, it means the - * corresponding TD has been cancelled. Just ignore - * the TD. - */ - if ((event_trb->generic.field[3] & TRB_TYPE_BITMASK) - == TRB_TYPE(TRB_TR_NOOP)) { - xhci_dbg(xhci, "event_trb is a no-op TRB. " - "Skip it\n"); - goto cleanup; - } + event_trb = &event_seg->trbs[(event_dma - event_seg->dma) / + sizeof(*event_trb)]; + /* + * No-op TRB should not trigger interrupts. + * If event_trb is a no-op TRB, it means the + * corresponding TD has been cancelled. Just ignore + * the TD. + */ + if ((event_trb->generic.field[3] & TRB_TYPE_BITMASK) + == TRB_TYPE(TRB_TR_NOOP)) { + xhci_dbg(xhci, + "event_trb is a no-op TRB. Skip it\n"); + goto cleanup; } /* Now update the urb's actual_length and give back to @@ -3126,6 +3169,12 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, } } + if (xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs == 0) { + if (xhci->quirks & XHCI_AMD_PLL_FIX) + usb_amd_quirk_pll_disable(); + } + xhci_to_hcd(xhci)->self.bandwidth_isoc_reqs++; + giveback_first_trb(xhci, slot_id, ep_index, urb->stream_id, start_cycle, start_trb); return 0; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 196e0181b2e..81b976e4588 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -550,6 +550,9 @@ void xhci_stop(struct usb_hcd *hcd) del_timer_sync(&xhci->event_ring_timer); #endif + if (xhci->quirks & XHCI_AMD_PLL_FIX) + usb_amd_dev_put(); + xhci_dbg(xhci, "// Disabling event ring interrupts\n"); temp = xhci_readl(xhci, &xhci->op_regs->status); xhci_writel(xhci, temp & ~STS_EINT, &xhci->op_regs->status); @@ -771,7 +774,9 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) /* If restore operation fails, re-initialize the HC during resume */ if ((temp & STS_SRE) || hibernated) { - usb_root_hub_lost_power(hcd->self.root_hub); + /* Let the USB core know _both_ roothubs lost power. */ + usb_root_hub_lost_power(xhci->main_hcd->self.root_hub); + usb_root_hub_lost_power(xhci->shared_hcd->self.root_hub); xhci_dbg(xhci, "Stop HCD\n"); xhci_halt(xhci); @@ -2386,10 +2391,18 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev) /* Everything but endpoint 0 is disabled, so free or cache the rings. */ last_freed_endpoint = 1; for (i = 1; i < 31; ++i) { - if (!virt_dev->eps[i].ring) - continue; - xhci_free_or_cache_endpoint_ring(xhci, virt_dev, i); - last_freed_endpoint = i; + struct xhci_virt_ep *ep = &virt_dev->eps[i]; + + if (ep->ep_state & EP_HAS_STREAMS) { + xhci_free_stream_info(xhci, ep->stream_info); + ep->stream_info = NULL; + ep->ep_state &= ~EP_HAS_STREAMS; + } + + if (ep->ring) { + xhci_free_or_cache_endpoint_ring(xhci, virt_dev, i); + last_freed_endpoint = i; + } } xhci_dbg(xhci, "Output context after successful reset device cmd:\n"); xhci_dbg_ctx(xhci, virt_dev->out_ctx, last_freed_endpoint); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 07e263063e3..ba1be6b7cc6 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -30,6 +30,7 @@ /* Code sharing between pci-quirks and xhci hcd */ #include "xhci-ext-caps.h" +#include "pci-quirks.h" /* xHCI PCI Configuration Registers */ #define XHCI_SBRN_OFFSET (0x60) @@ -232,7 +233,7 @@ struct xhci_op_regs { * notification type that matches a bit set in this bit field. */ #define DEV_NOTE_MASK (0xffff) -#define ENABLE_DEV_NOTE(x) (1 << x) +#define ENABLE_DEV_NOTE(x) (1 << (x)) /* Most of the device notification types should only be used for debug. * SW does need to pay attention to function wake notifications. */ @@ -348,6 +349,9 @@ struct xhci_op_regs { /* Initiate a warm port reset - complete when PORT_WRC is '1' */ #define PORT_WR (1 << 31) +/* We mark duplicate entries with -1 */ +#define DUPLICATE_ENTRY ((u8)(-1)) + /* Port Power Management Status and Control - port_power_base bitmasks */ /* Inactivity timer value for transitions into U1, in microseconds. * Timeout can be up to 127us. 0xFF means an infinite timeout. @@ -601,11 +605,11 @@ struct xhci_ep_ctx { #define EP_STATE_STOPPED 3 #define EP_STATE_ERROR 4 /* Mult - Max number of burtst within an interval, in EP companion desc. */ -#define EP_MULT(p) ((p & 0x3) << 8) +#define EP_MULT(p) (((p) & 0x3) << 8) /* bits 10:14 are Max Primary Streams */ /* bit 15 is Linear Stream Array */ /* Interval - period between requests to an endpoint - 125u increments. */ -#define EP_INTERVAL(p) ((p & 0xff) << 16) +#define EP_INTERVAL(p) (((p) & 0xff) << 16) #define EP_INTERVAL_TO_UFRAMES(p) (1 << (((p) >> 16) & 0xff)) #define EP_MAXPSTREAMS_MASK (0x1f << 10) #define EP_MAXPSTREAMS(p) (((p) << 10) & EP_MAXPSTREAMS_MASK) @@ -1276,6 +1280,7 @@ struct xhci_hcd { #define XHCI_LINK_TRB_QUIRK (1 << 0) #define XHCI_RESET_EP_QUIRK (1 << 1) #define XHCI_NEC_HOST (1 << 2) +#define XHCI_AMD_PLL_FIX (1 << 3) /* There are two roothubs to keep track of bus suspend info for */ struct xhci_bus_state bus_state[2]; /* Is each xHCI roothub port a USB 3.0, USB 2.0, or USB 1.1 port? */ diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig index 4cbb7e4b368..74073b363c3 100644 --- a/drivers/usb/musb/Kconfig +++ b/drivers/usb/musb/Kconfig @@ -14,7 +14,7 @@ config USB_MUSB_HDRC select TWL4030_USB if MACH_OMAP_3430SDP select TWL6030_USB if MACH_OMAP_4430SDP || MACH_OMAP4_PANDA select USB_OTG_UTILS - tristate 'Inventra Highspeed Dual Role Controller (TI, ADI, ...)' + bool 'Inventra Highspeed Dual Role Controller (TI, ADI, ...)' help Say Y here if your system has a dual role high speed USB controller based on the Mentor Graphics silicon IP. Then @@ -30,8 +30,8 @@ config USB_MUSB_HDRC If you do not know what this is, please say N. - To compile this driver as a module, choose M here; the - module will be called "musb-hdrc". +# To compile this driver as a module, choose M here; the +# module will be called "musb-hdrc". choice prompt "Platform Glue Layer" diff --git a/drivers/usb/musb/blackfin.c b/drivers/usb/musb/blackfin.c index 52312e8af21..8e2a1ff8a35 100644 --- a/drivers/usb/musb/blackfin.c +++ b/drivers/usb/musb/blackfin.c @@ -21,6 +21,7 @@ #include <asm/cacheflush.h> #include "musb_core.h" +#include "musbhsdma.h" #include "blackfin.h" struct bfin_glue { @@ -332,6 +333,27 @@ static int bfin_musb_set_mode(struct musb *musb, u8 musb_mode) return -EIO; } +static int bfin_musb_adjust_channel_params(struct dma_channel *channel, + u16 packet_sz, u8 *mode, + dma_addr_t *dma_addr, u32 *len) +{ + struct musb_dma_channel *musb_channel = channel->private_data; + + /* + * Anomaly 05000450 might cause data corruption when using DMA + * MODE 1 transmits with short packet. So to work around this, + * we truncate all MODE 1 transfers down to a multiple of the + * max packet size, and then do the last short packet transfer + * (if there is any) using MODE 0. + */ + if (ANOMALY_05000450) { + if (musb_channel->transmit && *mode == 1) + *len = *len - (*len % packet_sz); + } + + return 0; +} + static void bfin_musb_reg_init(struct musb *musb) { if (ANOMALY_05000346) { @@ -430,6 +452,8 @@ static const struct musb_platform_ops bfin_ops = { .vbus_status = bfin_musb_vbus_status, .set_vbus = bfin_musb_set_vbus, + + .adjust_channel_params = bfin_musb_adjust_channel_params, }; static u64 bfin_dmamask = DMA_BIT_MASK(32); diff --git a/drivers/usb/musb/cppi_dma.c b/drivers/usb/musb/cppi_dma.c index de55a3c3259..ab434fbd8c3 100644 --- a/drivers/usb/musb/cppi_dma.c +++ b/drivers/usb/musb/cppi_dma.c @@ -597,12 +597,12 @@ cppi_next_tx_segment(struct musb *musb, struct cppi_channel *tx) length = min(n_bds * maxpacket, length); } - DBG(4, "TX DMA%d, pktSz %d %s bds %d dma 0x%x len %u\n", + DBG(4, "TX DMA%d, pktSz %d %s bds %d dma 0x%llx len %u\n", tx->index, maxpacket, rndis ? "rndis" : "transparent", n_bds, - addr, length); + (unsigned long long)addr, length); cppi_rndis_update(tx, 0, musb->ctrl_base, rndis); @@ -820,7 +820,7 @@ cppi_next_rx_segment(struct musb *musb, struct cppi_channel *rx, int onepacket) length = min(n_bds * maxpacket, length); DBG(4, "RX DMA%d seg, maxp %d %s bds %d (cnt %d) " - "dma 0x%x len %u %u/%u\n", + "dma 0x%llx len %u %u/%u\n", rx->index, maxpacket, onepacket ? (is_rndis ? "rndis" : "onepacket") @@ -829,7 +829,8 @@ cppi_next_rx_segment(struct musb *musb, struct cppi_channel *rx, int onepacket) musb_readl(tibase, DAVINCI_RXCPPI_BUFCNT0_REG + (rx->index * 4)) & 0xffff, - addr, length, rx->channel.actual_len, rx->buf_len); + (unsigned long long)addr, length, + rx->channel.actual_len, rx->buf_len); /* only queue one segment at a time, since the hardware prevents * correct queue shutdown after unexpected short packets @@ -1039,9 +1040,9 @@ static bool cppi_rx_scan(struct cppi *cppi, unsigned ch) if (!completed && (bd->hw_options & CPPI_OWN_SET)) break; - DBG(5, "C/RXBD %08x: nxt %08x buf %08x " + DBG(5, "C/RXBD %llx: nxt %08x buf %08x " "off.len %08x opt.len %08x (%d)\n", - bd->dma, bd->hw_next, bd->hw_bufp, + (unsigned long long)bd->dma, bd->hw_next, bd->hw_bufp, bd->hw_off_len, bd->hw_options, rx->channel.actual_len); @@ -1111,11 +1112,12 @@ static bool cppi_rx_scan(struct cppi *cppi, unsigned ch) musb_ep_select(cppi->mregs, rx->index + 1); csr = musb_readw(regs, MUSB_RXCSR); if (csr & MUSB_RXCSR_DMAENAB) { - DBG(4, "list%d %p/%p, last %08x%s, csr %04x\n", + DBG(4, "list%d %p/%p, last %llx%s, csr %04x\n", rx->index, rx->head, rx->tail, rx->last_processed - ? rx->last_processed->dma + ? (unsigned long long) + rx->last_processed->dma : 0, completed ? ", completed" : "", csr); @@ -1167,8 +1169,11 @@ irqreturn_t cppi_interrupt(int irq, void *dev_id) tx = musb_readl(tibase, DAVINCI_TXCPPI_MASKED_REG); rx = musb_readl(tibase, DAVINCI_RXCPPI_MASKED_REG); - if (!tx && !rx) + if (!tx && !rx) { + if (cppi->irq) + spin_unlock_irqrestore(&musb->lock, flags); return IRQ_NONE; + } DBG(4, "CPPI IRQ Tx%x Rx%x\n", tx, rx); @@ -1199,7 +1204,7 @@ irqreturn_t cppi_interrupt(int irq, void *dev_id) */ if (NULL == bd) { DBG(1, "null BD\n"); - tx_ram->tx_complete = 0; + musb_writel(&tx_ram->tx_complete, 0, 0); continue; } @@ -1452,7 +1457,7 @@ static int cppi_channel_abort(struct dma_channel *channel) * compare mode by writing 1 to the tx_complete register. */ cppi_reset_tx(tx_ram, 1); - cppi_ch->head = 0; + cppi_ch->head = NULL; musb_writel(&tx_ram->tx_complete, 0, 1); cppi_dump_tx(5, cppi_ch, " (done teardown)"); diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 630ae7f3cd4..f10ff00ca09 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -1030,6 +1030,7 @@ static void musb_shutdown(struct platform_device *pdev) struct musb *musb = dev_to_musb(&pdev->dev); unsigned long flags; + pm_runtime_get_sync(musb->controller); spin_lock_irqsave(&musb->lock, flags); musb_platform_disable(musb); musb_generic_disable(musb); @@ -1040,6 +1041,7 @@ static void musb_shutdown(struct platform_device *pdev) musb_writeb(musb->mregs, MUSB_DEVCTL, 0); musb_platform_exit(musb); + pm_runtime_put(musb->controller); /* FIXME power down */ } diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h index 4bd9e2145ee..0e053b58796 100644 --- a/drivers/usb/musb/musb_core.h +++ b/drivers/usb/musb/musb_core.h @@ -261,6 +261,7 @@ enum musb_g_ep0_state { * @try_ilde: tries to idle the IP * @vbus_status: returns vbus status if possible * @set_vbus: forces vbus status + * @channel_program: pre check for standard dma channel_program func */ struct musb_platform_ops { int (*init)(struct musb *musb); @@ -274,6 +275,10 @@ struct musb_platform_ops { int (*vbus_status)(struct musb *musb); void (*set_vbus)(struct musb *musb, int on); + + int (*adjust_channel_params)(struct dma_channel *channel, + u16 packet_sz, u8 *mode, + dma_addr_t *dma_addr, u32 *len); }; /* diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 98519c5d8b5..6dfbf9ffd7a 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -535,7 +535,7 @@ void musb_g_tx(struct musb *musb, u8 epnum) is_dma = 1; csr |= MUSB_TXCSR_P_WZC_BITS; csr &= ~(MUSB_TXCSR_DMAENAB | MUSB_TXCSR_P_UNDERRUN | - MUSB_TXCSR_TXPKTRDY); + MUSB_TXCSR_TXPKTRDY | MUSB_TXCSR_AUTOSET); musb_writew(epio, MUSB_TXCSR, csr); /* Ensure writebuffer is empty. */ csr = musb_readw(epio, MUSB_TXCSR); @@ -1296,7 +1296,7 @@ static int musb_gadget_dequeue(struct usb_ep *ep, struct usb_request *request) } /* if the hardware doesn't have the request, easy ... */ - if (musb_ep->req_list.next != &request->list || musb_ep->busy) + if (musb_ep->req_list.next != &req->list || musb_ep->busy) musb_g_giveback(musb_ep, request, -ECONNRESET); /* ... else abort the dma transfer ... */ diff --git a/drivers/usb/musb/musbhsdma.c b/drivers/usb/musb/musbhsdma.c index 0144a2d481f..d281792db05 100644 --- a/drivers/usb/musb/musbhsdma.c +++ b/drivers/usb/musb/musbhsdma.c @@ -169,6 +169,14 @@ static int dma_channel_program(struct dma_channel *channel, BUG_ON(channel->status == MUSB_DMA_STATUS_UNKNOWN || channel->status == MUSB_DMA_STATUS_BUSY); + /* Let targets check/tweak the arguments */ + if (musb->ops->adjust_channel_params) { + int ret = musb->ops->adjust_channel_params(channel, + packet_sz, &mode, &dma_addr, &len); + if (ret) + return ret; + } + /* * The DMA engine in RTL1.8 and above cannot handle * DMA addresses that are not aligned to a 4 byte boundary. diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index 25cb8b0003b..57a27fa954b 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -259,9 +259,10 @@ static int musb_otg_notifications(struct notifier_block *nb, case USB_EVENT_VBUS: DBG(4, "VBUS Connect\n"); +#ifdef CONFIG_USB_GADGET_MUSB_HDRC if (musb->gadget_driver) pm_runtime_get_sync(musb->controller); - +#endif otg_init(musb->xceiv); break; diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c index d6384e4aeef..f7e04bf34a1 100644 --- a/drivers/usb/musb/ux500.c +++ b/drivers/usb/musb/ux500.c @@ -93,6 +93,8 @@ static int __init ux500_probe(struct platform_device *pdev) } musb->dev.parent = &pdev->dev; + musb->dev.dma_mask = pdev->dev.dma_mask; + musb->dev.coherent_dma_mask = pdev->dev.coherent_dma_mask; glue->dev = &pdev->dev; glue->musb = musb; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index a973c7a29d6..4de6ef0ae52 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -151,6 +151,8 @@ static struct ftdi_sio_quirk ftdi_stmclite_quirk = { * /sys/bus/usb/ftdi_sio/new_id, then send patch/report! */ static struct usb_device_id id_table_combined [] = { + { USB_DEVICE(FTDI_VID, FTDI_CTI_MINI_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_CTI_NANO_PID) }, { USB_DEVICE(FTDI_VID, FTDI_AMC232_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) }, @@ -525,6 +527,7 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(SEALEVEL_VID, SEALEVEL_2803_8_PID) }, { USB_DEVICE(IDTECH_VID, IDTECH_IDT1221U_PID) }, { USB_DEVICE(OCT_VID, OCT_US101_PID) }, + { USB_DEVICE(OCT_VID, OCT_DK201_PID) }, { USB_DEVICE(FTDI_VID, FTDI_HE_TIRA1_PID), .driver_info = (kernel_ulong_t)&ftdi_HE_TIRA1_quirk }, { USB_DEVICE(FTDI_VID, FTDI_USB_UIRT_PID), @@ -787,6 +790,8 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(FTDI_VID, MARVELL_OPENRD_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, HAMEG_HO820_PID) }, + { USB_DEVICE(FTDI_VID, HAMEG_HO720_PID) }, + { USB_DEVICE(FTDI_VID, HAMEG_HO730_PID) }, { USB_DEVICE(FTDI_VID, HAMEG_HO870_PID) }, { USB_DEVICE(FTDI_VID, MJSG_GENERIC_PID) }, { USB_DEVICE(FTDI_VID, MJSG_SR_RADIO_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index c543e55bafb..efffc23723b 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -300,6 +300,8 @@ * Hameg HO820 and HO870 interface (using VID 0x0403) */ #define HAMEG_HO820_PID 0xed74 +#define HAMEG_HO730_PID 0xed73 +#define HAMEG_HO720_PID 0xed72 #define HAMEG_HO870_PID 0xed71 /* @@ -572,6 +574,7 @@ /* Note: OCT US101 is also rebadged as Dick Smith Electronics (NZ) XH6381 */ /* Also rebadged as Dick Smith Electronics (Aus) XH6451 */ /* Also rebadged as SIIG Inc. model US2308 hardware version 1 */ +#define OCT_DK201_PID 0x0103 /* OCT DK201 USB docking station */ #define OCT_US101_PID 0x0421 /* OCT US101 USB to RS-232 */ /* @@ -1141,3 +1144,12 @@ #define QIHARDWARE_VID 0x20B7 #define MILKYMISTONE_JTAGSERIAL_PID 0x0713 +/* + * CTI GmbH RS485 Converter http://www.cti-lean.com/ + */ +/* USB-485-Mini*/ +#define FTDI_CTI_MINI_PID 0xF608 +/* USB-Nano-485*/ +#define FTDI_CTI_NANO_PID 0xF60B + + diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 75c7f456eed..d77ff043589 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -407,6 +407,10 @@ static void option_instat_callback(struct urb *urb); /* ONDA MT825UP HSDPA 14.2 modem */ #define ONDA_MT825UP 0x000b +/* Samsung products */ +#define SAMSUNG_VENDOR_ID 0x04e8 +#define SAMSUNG_PRODUCT_GT_B3730 0x6889 + /* some devices interfaces need special handling due to a number of reasons */ enum option_blacklist_reason { OPTION_BLACKLIST_NONE = 0, @@ -968,6 +972,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) }, { USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */ { USB_DEVICE(ONDA_VENDOR_ID, ONDA_MT825UP) }, /* ONDA MT825UP modem */ + { USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_GT_B3730, USB_CLASS_CDC_DATA, 0x00, 0x00) }, /* Samsung GT-B3730/GT-B3710 LTE USB modem.*/ { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 8858201eb1d..54a9dab1f33 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -111,7 +111,7 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) ifnum = intf->desc.bInterfaceNumber; dbg("This Interface = %d", ifnum); - data = serial->private = kzalloc(sizeof(struct usb_wwan_intf_private), + data = kzalloc(sizeof(struct usb_wwan_intf_private), GFP_KERNEL); if (!data) return -ENOMEM; @@ -134,8 +134,10 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) usb_endpoint_is_bulk_out(&intf->endpoint[1].desc)) { dbg("QDL port found"); - if (serial->interface->num_altsetting == 1) - return 0; + if (serial->interface->num_altsetting == 1) { + retval = 0; /* Success */ + break; + } retval = usb_set_interface(serial->dev, ifnum, 1); if (retval < 0) { @@ -145,7 +147,6 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) retval = -ENODEV; kfree(data); } - return retval; } break; @@ -166,6 +167,7 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) "Could not set interface, error %d\n", retval); retval = -ENODEV; + kfree(data); } } else if (ifnum == 2) { dbg("Modem port found"); @@ -177,7 +179,6 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) retval = -ENODEV; kfree(data); } - return retval; } else if (ifnum==3) { /* * NMEA (serial line 9600 8N1) @@ -191,6 +192,7 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) "Could not set interface, error %d\n", retval); retval = -ENODEV; + kfree(data); } } break; @@ -199,12 +201,27 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) dev_err(&serial->dev->dev, "unknown number of interfaces: %d\n", nintf); kfree(data); - return -ENODEV; + retval = -ENODEV; } + /* Set serial->private if not returning -ENODEV */ + if (retval != -ENODEV) + usb_set_serial_data(serial, data); return retval; } +static void qc_release(struct usb_serial *serial) +{ + struct usb_wwan_intf_private *priv = usb_get_serial_data(serial); + + dbg("%s", __func__); + + /* Call usb_wwan release & free the private data allocated in qcprobe */ + usb_wwan_release(serial); + usb_set_serial_data(serial, NULL); + kfree(priv); +} + static struct usb_serial_driver qcdevice = { .driver = { .owner = THIS_MODULE, @@ -222,7 +239,7 @@ static struct usb_serial_driver qcdevice = { .chars_in_buffer = usb_wwan_chars_in_buffer, .attach = usb_wwan_startup, .disconnect = usb_wwan_disconnect, - .release = usb_wwan_release, + .release = qc_release, #ifdef CONFIG_PM .suspend = usb_wwan_suspend, .resume = usb_wwan_resume, diff --git a/drivers/video/pxafb.c b/drivers/video/pxafb.c index a2e5b5100ab..0f4e8c942f9 100644 --- a/drivers/video/pxafb.c +++ b/drivers/video/pxafb.c @@ -1648,7 +1648,9 @@ pxafb_freq_transition(struct notifier_block *nb, unsigned long val, void *data) switch (val) { case CPUFREQ_PRECHANGE: - if (!fbi->overlay[0].usage && !fbi->overlay[1].usage) +#ifdef CONFIG_FB_PXA_OVERLAY + if (!(fbi->overlay[0].usage || fbi->overlay[1].usage)) +#endif set_ctrlr_state(fbi, C_DISABLE_CLKCHANGE); break; diff --git a/fs/9p/fid.c b/fs/9p/fid.c index 0ee594569dc..85b67ffa2a4 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -286,11 +286,9 @@ static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, uid_t uid) struct p9_fid *v9fs_writeback_fid(struct dentry *dentry) { - int err, flags; + int err; struct p9_fid *fid; - struct v9fs_session_info *v9ses; - v9ses = v9fs_dentry2v9ses(dentry); fid = v9fs_fid_clone_with_uid(dentry, 0); if (IS_ERR(fid)) goto error_out; @@ -299,17 +297,8 @@ struct p9_fid *v9fs_writeback_fid(struct dentry *dentry) * dirty pages. We always request for the open fid in read-write * mode so that a partial page write which result in page * read can work. - * - * we don't have a tsyncfs operation for older version - * of protocol. So make sure the write back fid is - * opened in O_SYNC mode. */ - if (!v9fs_proto_dotl(v9ses)) - flags = O_RDWR | O_SYNC; - else - flags = O_RDWR; - - err = p9_client_open(fid, flags); + err = p9_client_open(fid, O_RDWR); if (err < 0) { p9_client_clunk(fid); fid = ERR_PTR(err); diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 9665c2b840e..e5ebedfc5ed 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -116,7 +116,6 @@ struct v9fs_session_info { struct list_head slist; /* list of sessions registered with v9fs */ struct backing_dev_info bdi; struct rw_semaphore rename_sem; - struct p9_fid *root_fid; /* Used for file system sync */ }; /* cache_validity flags */ diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index b6a3b9f7fe4..e022890c6f4 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -126,7 +126,9 @@ static int v9fs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) retval = v9fs_refresh_inode_dotl(fid, inode); else retval = v9fs_refresh_inode(fid, inode); - if (retval <= 0) + if (retval == -ENOENT) + return 0; + if (retval < 0) return retval; } out_valid: diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index ffbb113d5f3..82a7c38ddad 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -811,7 +811,7 @@ v9fs_vfs_follow_link_dotl(struct dentry *dentry, struct nameidata *nd) fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) { __putname(link); - link = ERR_PTR(PTR_ERR(fid)); + link = ERR_CAST(fid); goto ndset; } retval = p9_client_readlink(fid, &target); diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index f3eed3383e4..feef6cdc1fd 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -154,6 +154,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, retval = PTR_ERR(inode); goto release_sb; } + root = d_alloc_root(inode); if (!root) { iput(inode); @@ -185,21 +186,10 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, p9stat_free(st); kfree(st); } - v9fs_fid_add(root, fid); retval = v9fs_get_acl(inode, fid); if (retval) goto release_sb; - /* - * Add the root fid to session info. This is used - * for file system sync. We want a cloned fid here - * so that we can do a sync_filesystem after a - * shrink_dcache_for_umount - */ - v9ses->root_fid = v9fs_fid_clone(root); - if (IS_ERR(v9ses->root_fid)) { - retval = PTR_ERR(v9ses->root_fid); - goto release_sb; - } + v9fs_fid_add(root, fid); P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n"); return dget(sb->s_root); @@ -210,11 +200,15 @@ close_session: v9fs_session_close(v9ses); kfree(v9ses); return ERR_PTR(retval); + release_sb: /* - * we will do the session_close and root dentry - * release in the below call. + * we will do the session_close and root dentry release + * in the below call. But we need to clunk fid, because we haven't + * attached the fid to dentry so it won't get clunked + * automatically. */ + p9_client_clunk(fid); deactivate_locked_super(sb); return ERR_PTR(retval); } @@ -232,7 +226,7 @@ static void v9fs_kill_super(struct super_block *s) P9_DPRINTK(P9_DEBUG_VFS, " %p\n", s); kill_anon_super(s); - p9_client_clunk(v9ses->root_fid); + v9fs_session_cancel(v9ses); v9fs_session_close(v9ses); kfree(v9ses); @@ -285,14 +279,6 @@ done: return res; } -static int v9fs_sync_fs(struct super_block *sb, int wait) -{ - struct v9fs_session_info *v9ses = sb->s_fs_info; - - P9_DPRINTK(P9_DEBUG_VFS, "v9fs_sync_fs: super_block %p\n", sb); - return p9_client_sync_fs(v9ses->root_fid); -} - static int v9fs_drop_inode(struct inode *inode) { struct v9fs_session_info *v9ses; @@ -307,6 +293,51 @@ static int v9fs_drop_inode(struct inode *inode) return 1; } +static int v9fs_write_inode(struct inode *inode, + struct writeback_control *wbc) +{ + int ret; + struct p9_wstat wstat; + struct v9fs_inode *v9inode; + /* + * send an fsync request to server irrespective of + * wbc->sync_mode. + */ + P9_DPRINTK(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode); + v9inode = V9FS_I(inode); + if (!v9inode->writeback_fid) + return 0; + v9fs_blank_wstat(&wstat); + + ret = p9_client_wstat(v9inode->writeback_fid, &wstat); + if (ret < 0) { + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + return ret; + } + return 0; +} + +static int v9fs_write_inode_dotl(struct inode *inode, + struct writeback_control *wbc) +{ + int ret; + struct v9fs_inode *v9inode; + /* + * send an fsync request to server irrespective of + * wbc->sync_mode. + */ + P9_DPRINTK(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode); + v9inode = V9FS_I(inode); + if (!v9inode->writeback_fid) + return 0; + ret = p9_client_fsync(v9inode->writeback_fid, 0); + if (ret < 0) { + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + return ret; + } + return 0; +} + static const struct super_operations v9fs_super_ops = { .alloc_inode = v9fs_alloc_inode, .destroy_inode = v9fs_destroy_inode, @@ -314,17 +345,18 @@ static const struct super_operations v9fs_super_ops = { .evict_inode = v9fs_evict_inode, .show_options = generic_show_options, .umount_begin = v9fs_umount_begin, + .write_inode = v9fs_write_inode, }; static const struct super_operations v9fs_super_ops_dotl = { .alloc_inode = v9fs_alloc_inode, .destroy_inode = v9fs_destroy_inode, - .sync_fs = v9fs_sync_fs, .statfs = v9fs_statfs, .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, .show_options = generic_show_options, .umount_begin = v9fs_umount_begin, + .write_inode = v9fs_write_inode_dotl, }; struct file_system_type v9fs_fs_type = { diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index f34078d702d..303983fabfd 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -941,9 +941,13 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) current->mm->start_stack = bprm->p; #ifdef arch_randomize_brk - if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) + if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) { current->mm->brk = current->mm->start_brk = arch_randomize_brk(current->mm); +#ifdef CONFIG_COMPAT_BRK + current->brk_randomized = 1; +#endif + } #endif if (current->personality & MMAP_PAGE_ZERO) { diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index de34bfad9ec..5d505aaa72f 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -178,16 +178,17 @@ static int btrfs_xattr_acl_set(struct dentry *dentry, const char *name, if (value) { acl = posix_acl_from_xattr(value, size); - if (acl == NULL) { - value = NULL; - size = 0; + if (acl) { + ret = posix_acl_valid(acl); + if (ret) + goto out; } else if (IS_ERR(acl)) { return PTR_ERR(acl); } } ret = btrfs_set_acl(NULL, dentry->d_inode, acl, type); - +out: posix_acl_release(acl); return ret; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3458b572554..2e61fe1b6b8 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -740,8 +740,10 @@ struct btrfs_space_info { */ unsigned long reservation_progress; - int full; /* indicates that we cannot allocate any more + int full:1; /* indicates that we cannot allocate any more chunks for this space */ + int chunk_alloc:1; /* set if we are allocating a chunk */ + int force_alloc; /* set if we need to force a chunk alloc for this space */ @@ -2576,6 +2578,11 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode, int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, struct inode *inode, u64 start, u64 end); int btrfs_release_file(struct inode *inode, struct file *file); +void btrfs_drop_pages(struct page **pages, size_t num_pages); +int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode, + struct page **pages, size_t num_pages, + loff_t pos, size_t write_bytes, + struct extent_state **cached); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8f1d44ba332..68c84c8c24b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3057,7 +3057,7 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root) btrfs_destroy_pinned_extent(root, root->fs_info->pinned_extents); - t->use_count = 0; + atomic_set(&t->use_count, 0); list_del_init(&t->list); memset(t, 0, sizeof(*t)); kmem_cache_free(btrfs_transaction_cachep, t); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f619c3cb13b..31f33ba56fe 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -33,6 +33,25 @@ #include "locking.h" #include "free-space-cache.h" +/* control flags for do_chunk_alloc's force field + * CHUNK_ALLOC_NO_FORCE means to only allocate a chunk + * if we really need one. + * + * CHUNK_ALLOC_FORCE means it must try to allocate one + * + * CHUNK_ALLOC_LIMITED means to only try and allocate one + * if we have very few chunks already allocated. This is + * used as part of the clustering code to help make sure + * we have a good pool of storage to cluster in, without + * filling the FS with empty chunks + * + */ +enum { + CHUNK_ALLOC_NO_FORCE = 0, + CHUNK_ALLOC_FORCE = 1, + CHUNK_ALLOC_LIMITED = 2, +}; + static int update_block_group(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, int alloc); @@ -3019,7 +3038,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, found->bytes_readonly = 0; found->bytes_may_use = 0; found->full = 0; - found->force_alloc = 0; + found->force_alloc = CHUNK_ALLOC_NO_FORCE; + found->chunk_alloc = 0; *space_info = found; list_add_rcu(&found->list, &info->space_info); atomic_set(&found->caching_threads, 0); @@ -3150,7 +3170,7 @@ again: if (!data_sinfo->full && alloc_chunk) { u64 alloc_target; - data_sinfo->force_alloc = 1; + data_sinfo->force_alloc = CHUNK_ALLOC_FORCE; spin_unlock(&data_sinfo->lock); alloc: alloc_target = btrfs_get_alloc_profile(root, 1); @@ -3160,7 +3180,8 @@ alloc: ret = do_chunk_alloc(trans, root->fs_info->extent_root, bytes + 2 * 1024 * 1024, - alloc_target, 0); + alloc_target, + CHUNK_ALLOC_NO_FORCE); btrfs_end_transaction(trans, root); if (ret < 0) { if (ret != -ENOSPC) @@ -3239,31 +3260,56 @@ static void force_metadata_allocation(struct btrfs_fs_info *info) rcu_read_lock(); list_for_each_entry_rcu(found, head, list) { if (found->flags & BTRFS_BLOCK_GROUP_METADATA) - found->force_alloc = 1; + found->force_alloc = CHUNK_ALLOC_FORCE; } rcu_read_unlock(); } static int should_alloc_chunk(struct btrfs_root *root, - struct btrfs_space_info *sinfo, u64 alloc_bytes) + struct btrfs_space_info *sinfo, u64 alloc_bytes, + int force) { u64 num_bytes = sinfo->total_bytes - sinfo->bytes_readonly; + u64 num_allocated = sinfo->bytes_used + sinfo->bytes_reserved; u64 thresh; - if (sinfo->bytes_used + sinfo->bytes_reserved + - alloc_bytes + 256 * 1024 * 1024 < num_bytes) + if (force == CHUNK_ALLOC_FORCE) + return 1; + + /* + * in limited mode, we want to have some free space up to + * about 1% of the FS size. + */ + if (force == CHUNK_ALLOC_LIMITED) { + thresh = btrfs_super_total_bytes(&root->fs_info->super_copy); + thresh = max_t(u64, 64 * 1024 * 1024, + div_factor_fine(thresh, 1)); + + if (num_bytes - num_allocated < thresh) + return 1; + } + + /* + * we have two similar checks here, one based on percentage + * and once based on a hard number of 256MB. The idea + * is that if we have a good amount of free + * room, don't allocate a chunk. A good mount is + * less than 80% utilized of the chunks we have allocated, + * or more than 256MB free + */ + if (num_allocated + alloc_bytes + 256 * 1024 * 1024 < num_bytes) return 0; - if (sinfo->bytes_used + sinfo->bytes_reserved + - alloc_bytes < div_factor(num_bytes, 8)) + if (num_allocated + alloc_bytes < div_factor(num_bytes, 8)) return 0; thresh = btrfs_super_total_bytes(&root->fs_info->super_copy); + + /* 256MB or 5% of the FS */ thresh = max_t(u64, 256 * 1024 * 1024, div_factor_fine(thresh, 5)); if (num_bytes > thresh && sinfo->bytes_used < div_factor(num_bytes, 3)) return 0; - return 1; } @@ -3273,10 +3319,9 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, { struct btrfs_space_info *space_info; struct btrfs_fs_info *fs_info = extent_root->fs_info; + int wait_for_alloc = 0; int ret = 0; - mutex_lock(&fs_info->chunk_mutex); - flags = btrfs_reduce_alloc_profile(extent_root, flags); space_info = __find_space_info(extent_root->fs_info, flags); @@ -3287,21 +3332,40 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, } BUG_ON(!space_info); +again: spin_lock(&space_info->lock); if (space_info->force_alloc) - force = 1; + force = space_info->force_alloc; if (space_info->full) { spin_unlock(&space_info->lock); - goto out; + return 0; } - if (!force && !should_alloc_chunk(extent_root, space_info, - alloc_bytes)) { + if (!should_alloc_chunk(extent_root, space_info, alloc_bytes, force)) { spin_unlock(&space_info->lock); - goto out; + return 0; + } else if (space_info->chunk_alloc) { + wait_for_alloc = 1; + } else { + space_info->chunk_alloc = 1; } + spin_unlock(&space_info->lock); + mutex_lock(&fs_info->chunk_mutex); + + /* + * The chunk_mutex is held throughout the entirety of a chunk + * allocation, so once we've acquired the chunk_mutex we know that the + * other guy is done and we need to recheck and see if we should + * allocate. + */ + if (wait_for_alloc) { + mutex_unlock(&fs_info->chunk_mutex); + wait_for_alloc = 0; + goto again; + } + /* * If we have mixed data/metadata chunks we want to make sure we keep * allocating mixed chunks instead of individual chunks. @@ -3327,9 +3391,10 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, space_info->full = 1; else ret = 1; - space_info->force_alloc = 0; + + space_info->force_alloc = CHUNK_ALLOC_NO_FORCE; + space_info->chunk_alloc = 0; spin_unlock(&space_info->lock); -out: mutex_unlock(&extent_root->fs_info->chunk_mutex); return ret; } @@ -5303,11 +5368,13 @@ loop: if (allowed_chunk_alloc) { ret = do_chunk_alloc(trans, root, num_bytes + - 2 * 1024 * 1024, data, 1); + 2 * 1024 * 1024, data, + CHUNK_ALLOC_LIMITED); allowed_chunk_alloc = 0; done_chunk_alloc = 1; - } else if (!done_chunk_alloc) { - space_info->force_alloc = 1; + } else if (!done_chunk_alloc && + space_info->force_alloc == CHUNK_ALLOC_NO_FORCE) { + space_info->force_alloc = CHUNK_ALLOC_LIMITED; } if (loop < LOOP_NO_EMPTY_SIZE) { @@ -5393,7 +5460,8 @@ again: */ if (empty_size || root->ref_cows) ret = do_chunk_alloc(trans, root->fs_info->extent_root, - num_bytes + 2 * 1024 * 1024, data, 0); + num_bytes + 2 * 1024 * 1024, data, + CHUNK_ALLOC_NO_FORCE); WARN_ON(num_bytes < root->sectorsize); ret = find_free_extent(trans, root, num_bytes, empty_size, @@ -5405,7 +5473,7 @@ again: num_bytes = num_bytes & ~(root->sectorsize - 1); num_bytes = max(num_bytes, min_alloc_size); do_chunk_alloc(trans, root->fs_info->extent_root, - num_bytes, data, 1); + num_bytes, data, CHUNK_ALLOC_FORCE); goto again; } if (ret == -ENOSPC && btrfs_test_opt(root, ENOSPC_DEBUG)) { @@ -8109,13 +8177,15 @@ int btrfs_set_block_group_ro(struct btrfs_root *root, alloc_flags = update_block_group_flags(root, cache->flags); if (alloc_flags != cache->flags) - do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1); + do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, + CHUNK_ALLOC_FORCE); ret = set_block_group_ro(cache); if (!ret) goto out; alloc_flags = get_alloc_profile(root, cache->space_info->flags); - ret = do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1); + ret = do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, + CHUNK_ALLOC_FORCE); if (ret < 0) goto out; ret = set_block_group_ro(cache); @@ -8128,7 +8198,8 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 type) { u64 alloc_flags = get_alloc_profile(root, type); - return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1); + return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, + CHUNK_ALLOC_FORCE); } /* diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 20ddb28602a..31513860508 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -690,6 +690,15 @@ static void cache_state(struct extent_state *state, } } +static void uncache_state(struct extent_state **cached_ptr) +{ + if (cached_ptr && (*cached_ptr)) { + struct extent_state *state = *cached_ptr; + *cached_ptr = NULL; + free_extent_state(state); + } +} + /* * set some bits on a range in the tree. This may require allocations or * sleeping, so the gfp mask is used to indicate what is allowed. @@ -940,10 +949,10 @@ static int clear_extent_new(struct extent_io_tree *tree, u64 start, u64 end, } int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, - gfp_t mask) + struct extent_state **cached_state, gfp_t mask) { - return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, NULL, - NULL, mask); + return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, + NULL, cached_state, mask); } static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, @@ -1012,8 +1021,7 @@ int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end, mask); } -int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, - gfp_t mask) +int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask) { return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL, mask); @@ -1735,6 +1743,9 @@ static void end_bio_extent_readpage(struct bio *bio, int err) do { struct page *page = bvec->bv_page; + struct extent_state *cached = NULL; + struct extent_state *state; + tree = &BTRFS_I(page->mapping->host)->io_tree; start = ((u64)page->index << PAGE_CACHE_SHIFT) + @@ -1749,9 +1760,20 @@ static void end_bio_extent_readpage(struct bio *bio, int err) if (++bvec <= bvec_end) prefetchw(&bvec->bv_page->flags); + spin_lock(&tree->lock); + state = find_first_extent_bit_state(tree, start, EXTENT_LOCKED); + if (state && state->start == start) { + /* + * take a reference on the state, unlock will drop + * the ref + */ + cache_state(state, &cached); + } + spin_unlock(&tree->lock); + if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) { ret = tree->ops->readpage_end_io_hook(page, start, end, - NULL); + state); if (ret) uptodate = 0; } @@ -1764,15 +1786,16 @@ static void end_bio_extent_readpage(struct bio *bio, int err) test_bit(BIO_UPTODATE, &bio->bi_flags); if (err) uptodate = 0; + uncache_state(&cached); continue; } } if (uptodate) { - set_extent_uptodate(tree, start, end, + set_extent_uptodate(tree, start, end, &cached, GFP_ATOMIC); } - unlock_extent(tree, start, end, GFP_ATOMIC); + unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC); if (whole_page) { if (uptodate) { @@ -1811,6 +1834,7 @@ static void end_bio_extent_preparewrite(struct bio *bio, int err) do { struct page *page = bvec->bv_page; + struct extent_state *cached = NULL; tree = &BTRFS_I(page->mapping->host)->io_tree; start = ((u64)page->index << PAGE_CACHE_SHIFT) + @@ -1821,13 +1845,14 @@ static void end_bio_extent_preparewrite(struct bio *bio, int err) prefetchw(&bvec->bv_page->flags); if (uptodate) { - set_extent_uptodate(tree, start, end, GFP_ATOMIC); + set_extent_uptodate(tree, start, end, &cached, + GFP_ATOMIC); } else { ClearPageUptodate(page); SetPageError(page); } - unlock_extent(tree, start, end, GFP_ATOMIC); + unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC); } while (bvec >= bio->bi_io_vec); @@ -2016,14 +2041,17 @@ static int __extent_read_full_page(struct extent_io_tree *tree, while (cur <= end) { if (cur >= last_byte) { char *userpage; + struct extent_state *cached = NULL; + iosize = PAGE_CACHE_SIZE - page_offset; userpage = kmap_atomic(page, KM_USER0); memset(userpage + page_offset, 0, iosize); flush_dcache_page(page); kunmap_atomic(userpage, KM_USER0); set_extent_uptodate(tree, cur, cur + iosize - 1, - GFP_NOFS); - unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS); + &cached, GFP_NOFS); + unlock_extent_cached(tree, cur, cur + iosize - 1, + &cached, GFP_NOFS); break; } em = get_extent(inode, page, page_offset, cur, @@ -2063,14 +2091,17 @@ static int __extent_read_full_page(struct extent_io_tree *tree, /* we've found a hole, just zero and go on */ if (block_start == EXTENT_MAP_HOLE) { char *userpage; + struct extent_state *cached = NULL; + userpage = kmap_atomic(page, KM_USER0); memset(userpage + page_offset, 0, iosize); flush_dcache_page(page); kunmap_atomic(userpage, KM_USER0); set_extent_uptodate(tree, cur, cur + iosize - 1, - GFP_NOFS); - unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS); + &cached, GFP_NOFS); + unlock_extent_cached(tree, cur, cur + iosize - 1, + &cached, GFP_NOFS); cur = cur + iosize; page_offset += iosize; continue; @@ -2789,9 +2820,12 @@ int extent_prepare_write(struct extent_io_tree *tree, iocount++; block_start = block_start + iosize; } else { - set_extent_uptodate(tree, block_start, cur_end, + struct extent_state *cached = NULL; + + set_extent_uptodate(tree, block_start, cur_end, &cached, GFP_NOFS); - unlock_extent(tree, block_start, cur_end, GFP_NOFS); + unlock_extent_cached(tree, block_start, cur_end, + &cached, GFP_NOFS); block_start = cur_end + 1; } page_offset = block_start & (PAGE_CACHE_SIZE - 1); @@ -3457,7 +3491,7 @@ int set_extent_buffer_uptodate(struct extent_io_tree *tree, num_pages = num_extent_pages(eb->start, eb->len); set_extent_uptodate(tree, eb->start, eb->start + eb->len - 1, - GFP_NOFS); + NULL, GFP_NOFS); for (i = 0; i < num_pages; i++) { page = extent_buffer_page(eb, i); if ((i == 0 && (eb->start & (PAGE_CACHE_SIZE - 1))) || @@ -3885,6 +3919,12 @@ static void move_pages(struct page *dst_page, struct page *src_page, kunmap_atomic(dst_kaddr, KM_USER0); } +static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned long len) +{ + unsigned long distance = (src > dst) ? src - dst : dst - src; + return distance < len; +} + static void copy_pages(struct page *dst_page, struct page *src_page, unsigned long dst_off, unsigned long src_off, unsigned long len) @@ -3892,10 +3932,12 @@ static void copy_pages(struct page *dst_page, struct page *src_page, char *dst_kaddr = kmap_atomic(dst_page, KM_USER0); char *src_kaddr; - if (dst_page != src_page) + if (dst_page != src_page) { src_kaddr = kmap_atomic(src_page, KM_USER1); - else + } else { src_kaddr = dst_kaddr; + BUG_ON(areas_overlap(src_off, dst_off, len)); + } memcpy(dst_kaddr + dst_off, src_kaddr + src_off, len); kunmap_atomic(dst_kaddr, KM_USER0); @@ -3970,7 +4012,7 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, "len %lu len %lu\n", dst_offset, len, dst->len); BUG_ON(1); } - if (dst_offset < src_offset) { + if (!areas_overlap(src_offset, dst_offset, len)) { memcpy_extent_buffer(dst, dst_offset, src_offset, len); return; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index f62c5442835..af2d7179c37 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -208,7 +208,7 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int bits, int exclusive_bits, u64 *failed_start, struct extent_state **cached_state, gfp_t mask); int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, - gfp_t mask); + struct extent_state **cached_state, gfp_t mask); int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask); int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e621ea54a3f..75899a01dde 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -104,7 +104,7 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, /* * unlocks pages after btrfs_file_write is done with them */ -static noinline void btrfs_drop_pages(struct page **pages, size_t num_pages) +void btrfs_drop_pages(struct page **pages, size_t num_pages) { size_t i; for (i = 0; i < num_pages; i++) { @@ -127,16 +127,13 @@ static noinline void btrfs_drop_pages(struct page **pages, size_t num_pages) * this also makes the decision about creating an inline extent vs * doing real data extents, marking pages dirty and delalloc as required. */ -static noinline int dirty_and_release_pages(struct btrfs_root *root, - struct file *file, - struct page **pages, - size_t num_pages, - loff_t pos, - size_t write_bytes) +int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode, + struct page **pages, size_t num_pages, + loff_t pos, size_t write_bytes, + struct extent_state **cached) { int err = 0; int i; - struct inode *inode = fdentry(file)->d_inode; u64 num_bytes; u64 start_pos; u64 end_of_last_block; @@ -149,7 +146,7 @@ static noinline int dirty_and_release_pages(struct btrfs_root *root, end_of_last_block = start_pos + num_bytes - 1; err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, - NULL); + cached); if (err) return err; @@ -992,9 +989,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, } if (copied > 0) { - ret = dirty_and_release_pages(root, file, pages, - dirty_pages, pos, - copied); + ret = btrfs_dirty_pages(root, inode, pages, + dirty_pages, pos, copied, + NULL); if (ret) { btrfs_delalloc_release_space(inode, dirty_pages << PAGE_CACHE_SHIFT); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index f561c953205..11d2e9cea09 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -508,6 +508,7 @@ int btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode; struct rb_node *node; struct list_head *pos, *n; + struct page **pages; struct page *page; struct extent_state *cached_state = NULL; struct btrfs_free_cluster *cluster = NULL; @@ -517,13 +518,13 @@ int btrfs_write_out_cache(struct btrfs_root *root, u64 start, end, len; u64 bytes = 0; u32 *crc, *checksums; - pgoff_t index = 0, last_index = 0; unsigned long first_page_offset; - int num_checksums; + int index = 0, num_pages = 0; int entries = 0; int bitmaps = 0; int ret = 0; bool next_page = false; + bool out_of_space = false; root = root->fs_info->tree_root; @@ -551,24 +552,31 @@ int btrfs_write_out_cache(struct btrfs_root *root, return 0; } - last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; + num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; filemap_write_and_wait(inode->i_mapping); btrfs_wait_ordered_range(inode, inode->i_size & ~(root->sectorsize - 1), (u64)-1); /* We need a checksum per page. */ - num_checksums = i_size_read(inode) / PAGE_CACHE_SIZE; - crc = checksums = kzalloc(sizeof(u32) * num_checksums, GFP_NOFS); + crc = checksums = kzalloc(sizeof(u32) * num_pages, GFP_NOFS); if (!crc) { iput(inode); return 0; } + pages = kzalloc(sizeof(struct page *) * num_pages, GFP_NOFS); + if (!pages) { + kfree(crc); + iput(inode); + return 0; + } + /* Since the first page has all of our checksums and our generation we * need to calculate the offset into the page that we can start writing * our entries. */ - first_page_offset = (sizeof(u32) * num_checksums) + sizeof(u64); + first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64); /* Get the cluster for this block_group if it exists */ if (!list_empty(&block_group->cluster_list)) @@ -590,20 +598,18 @@ int btrfs_write_out_cache(struct btrfs_root *root, * after find_get_page at this point. Just putting this here so people * know and don't freak out. */ - while (index <= last_index) { + while (index < num_pages) { page = grab_cache_page(inode->i_mapping, index); if (!page) { - pgoff_t i = 0; + int i; - while (i < index) { - page = find_get_page(inode->i_mapping, i); - unlock_page(page); - page_cache_release(page); - page_cache_release(page); - i++; + for (i = 0; i < num_pages; i++) { + unlock_page(pages[i]); + page_cache_release(pages[i]); } goto out_free; } + pages[index] = page; index++; } @@ -631,7 +637,12 @@ int btrfs_write_out_cache(struct btrfs_root *root, offset = start_offset; } - page = find_get_page(inode->i_mapping, index); + if (index >= num_pages) { + out_of_space = true; + break; + } + + page = pages[index]; addr = kmap(page); entry = addr + start_offset; @@ -708,23 +719,6 @@ int btrfs_write_out_cache(struct btrfs_root *root, bytes += PAGE_CACHE_SIZE; - ClearPageChecked(page); - set_page_extent_mapped(page); - SetPageUptodate(page); - set_page_dirty(page); - - /* - * We need to release our reference we got for grab_cache_page, - * except for the first page which will hold our checksums, we - * do that below. - */ - if (index != 0) { - unlock_page(page); - page_cache_release(page); - } - - page_cache_release(page); - index++; } while (node || next_page); @@ -734,7 +728,11 @@ int btrfs_write_out_cache(struct btrfs_root *root, struct btrfs_free_space *entry = list_entry(pos, struct btrfs_free_space, list); - page = find_get_page(inode->i_mapping, index); + if (index >= num_pages) { + out_of_space = true; + break; + } + page = pages[index]; addr = kmap(page); memcpy(addr, entry->bitmap, PAGE_CACHE_SIZE); @@ -745,64 +743,58 @@ int btrfs_write_out_cache(struct btrfs_root *root, crc++; bytes += PAGE_CACHE_SIZE; - ClearPageChecked(page); - set_page_extent_mapped(page); - SetPageUptodate(page); - set_page_dirty(page); - unlock_page(page); - page_cache_release(page); - page_cache_release(page); list_del_init(&entry->list); index++; } + if (out_of_space) { + btrfs_drop_pages(pages, num_pages); + unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, + i_size_read(inode) - 1, &cached_state, + GFP_NOFS); + ret = 0; + goto out_free; + } + /* Zero out the rest of the pages just to make sure */ - while (index <= last_index) { + while (index < num_pages) { void *addr; - page = find_get_page(inode->i_mapping, index); - + page = pages[index]; addr = kmap(page); memset(addr, 0, PAGE_CACHE_SIZE); kunmap(page); - ClearPageChecked(page); - set_page_extent_mapped(page); - SetPageUptodate(page); - set_page_dirty(page); - unlock_page(page); - page_cache_release(page); - page_cache_release(page); bytes += PAGE_CACHE_SIZE; index++; } - btrfs_set_extent_delalloc(inode, 0, bytes - 1, &cached_state); - /* Write the checksums and trans id to the first page */ { void *addr; u64 *gen; - page = find_get_page(inode->i_mapping, 0); + page = pages[0]; addr = kmap(page); - memcpy(addr, checksums, sizeof(u32) * num_checksums); - gen = addr + (sizeof(u32) * num_checksums); + memcpy(addr, checksums, sizeof(u32) * num_pages); + gen = addr + (sizeof(u32) * num_pages); *gen = trans->transid; kunmap(page); - ClearPageChecked(page); - set_page_extent_mapped(page); - SetPageUptodate(page); - set_page_dirty(page); - unlock_page(page); - page_cache_release(page); - page_cache_release(page); } - BTRFS_I(inode)->generation = trans->transid; + ret = btrfs_dirty_pages(root, inode, pages, num_pages, 0, + bytes, &cached_state); + btrfs_drop_pages(pages, num_pages); unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, &cached_state, GFP_NOFS); + if (ret) { + ret = 0; + goto out_free; + } + + BTRFS_I(inode)->generation = trans->transid; + filemap_write_and_wait(inode->i_mapping); key.objectid = BTRFS_FREE_SPACE_OBJECTID; @@ -853,6 +845,7 @@ out_free: BTRFS_I(inode)->generation = 0; } kfree(checksums); + kfree(pages); btrfs_update_inode(trans, root, inode); iput(inode); return ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5cc64ab9c48..fcd66b6a808 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1770,9 +1770,12 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) add_pending_csums(trans, inode, ordered_extent->file_offset, &ordered_extent->list); - btrfs_ordered_update_i_size(inode, 0, ordered_extent); - ret = btrfs_update_inode(trans, root, inode); - BUG_ON(ret); + ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent); + if (!ret) { + ret = btrfs_update_inode(trans, root, inode); + BUG_ON(ret); + } + ret = 0; out: if (nolock) { if (trans) @@ -2590,6 +2593,13 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, struct btrfs_inode_item *item, struct inode *inode) { + if (!leaf->map_token) + map_private_extent_buffer(leaf, (unsigned long)item, + sizeof(struct btrfs_inode_item), + &leaf->map_token, &leaf->kaddr, + &leaf->map_start, &leaf->map_len, + KM_USER1); + btrfs_set_inode_uid(leaf, item, inode->i_uid); btrfs_set_inode_gid(leaf, item, inode->i_gid); btrfs_set_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size); @@ -2618,6 +2628,11 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, btrfs_set_inode_rdev(leaf, item, inode->i_rdev); btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags); btrfs_set_inode_block_group(leaf, item, BTRFS_I(inode)->block_group); + + if (leaf->map_token) { + unmap_extent_buffer(leaf, leaf->map_token, KM_USER1); + leaf->map_token = NULL; + } } /* @@ -4207,10 +4222,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, struct btrfs_key found_key; struct btrfs_path *path; int ret; - u32 nritems; struct extent_buffer *leaf; int slot; - int advance; unsigned char d_type; int over = 0; u32 di_cur; @@ -4253,27 +4266,19 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto err; - advance = 0; while (1) { leaf = path->nodes[0]; - nritems = btrfs_header_nritems(leaf); slot = path->slots[0]; - if (advance || slot >= nritems) { - if (slot >= nritems - 1) { - ret = btrfs_next_leaf(root, path); - if (ret) - break; - leaf = path->nodes[0]; - nritems = btrfs_header_nritems(leaf); - slot = path->slots[0]; - } else { - slot++; - path->slots[0]++; - } + if (slot >= btrfs_header_nritems(leaf)) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto err; + else if (ret > 0) + break; + continue; } - advance = 1; item = btrfs_item_nr(leaf, slot); btrfs_item_key_to_cpu(leaf, &found_key, slot); @@ -4282,7 +4287,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, if (btrfs_key_type(&found_key) != key_type) break; if (found_key.offset < filp->f_pos) - continue; + goto next; filp->f_pos = found_key.offset; @@ -4335,6 +4340,8 @@ skip: di_cur += di_len; di = (struct btrfs_dir_item *)((char *)di + di_len); } +next: + path->slots[0]++; } /* Reached end of directory/root. Bump pos past the last item. */ @@ -4527,14 +4534,17 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, BUG_ON(!path); inode = new_inode(root->fs_info->sb); - if (!inode) + if (!inode) { + btrfs_free_path(path); return ERR_PTR(-ENOMEM); + } if (dir) { trace_btrfs_inode_request(dir); ret = btrfs_set_inode_index(dir, index); if (ret) { + btrfs_free_path(path); iput(inode); return ERR_PTR(ret); } @@ -4834,9 +4844,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, if (inode->i_nlink == ~0U) return -EMLINK; - btrfs_inc_nlink(inode); - inode->i_ctime = CURRENT_TIME; - err = btrfs_set_inode_index(dir, &index); if (err) goto fail; @@ -4852,6 +4859,9 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, goto fail; } + btrfs_inc_nlink(inode); + inode->i_ctime = CURRENT_TIME; + btrfs_set_trans_block_group(trans, dir); ihold(inode); @@ -5221,7 +5231,7 @@ again: btrfs_mark_buffer_dirty(leaf); } set_extent_uptodate(io_tree, em->start, - extent_map_end(em) - 1, GFP_NOFS); + extent_map_end(em) - 1, NULL, GFP_NOFS); goto insert; } else { printk(KERN_ERR "btrfs unknown found_type %d\n", found_type); @@ -5428,17 +5438,30 @@ out: } static struct extent_map *btrfs_new_extent_direct(struct inode *inode, + struct extent_map *em, u64 start, u64 len) { struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; - struct extent_map *em; struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; struct btrfs_key ins; u64 alloc_hint; int ret; + bool insert = false; - btrfs_drop_extent_cache(inode, start, start + len - 1, 0); + /* + * Ok if the extent map we looked up is a hole and is for the exact + * range we want, there is no reason to allocate a new one, however if + * it is not right then we need to free this one and drop the cache for + * our range. + */ + if (em->block_start != EXTENT_MAP_HOLE || em->start != start || + em->len != len) { + free_extent_map(em); + em = NULL; + insert = true; + btrfs_drop_extent_cache(inode, start, start + len - 1, 0); + } trans = btrfs_join_transaction(root, 0); if (IS_ERR(trans)) @@ -5454,10 +5477,12 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, goto out; } - em = alloc_extent_map(GFP_NOFS); if (!em) { - em = ERR_PTR(-ENOMEM); - goto out; + em = alloc_extent_map(GFP_NOFS); + if (!em) { + em = ERR_PTR(-ENOMEM); + goto out; + } } em->start = start; @@ -5467,9 +5492,15 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, em->block_start = ins.objectid; em->block_len = ins.offset; em->bdev = root->fs_info->fs_devices->latest_bdev; + + /* + * We need to do this because if we're using the original em we searched + * for, we could have EXTENT_FLAG_VACANCY set, and we don't want that. + */ + em->flags = 0; set_bit(EXTENT_FLAG_PINNED, &em->flags); - while (1) { + while (insert) { write_lock(&em_tree->lock); ret = add_extent_mapping(em_tree, em); write_unlock(&em_tree->lock); @@ -5687,8 +5718,7 @@ must_cow: * it above */ len = bh_result->b_size; - free_extent_map(em); - em = btrfs_new_extent_direct(inode, start, len); + em = btrfs_new_extent_direct(inode, em, start, len); if (IS_ERR(em)) return PTR_ERR(em); len = min(len, em->len - (start - em->start)); @@ -5851,8 +5881,10 @@ again: } add_pending_csums(trans, inode, ordered->file_offset, &ordered->list); - btrfs_ordered_update_i_size(inode, 0, ordered); - btrfs_update_inode(trans, root, inode); + ret = btrfs_ordered_update_i_size(inode, 0, ordered); + if (!ret) + btrfs_update_inode(trans, root, inode); + ret = 0; out_unlock: unlock_extent_cached(&BTRFS_I(inode)->io_tree, ordered->file_offset, ordered->file_offset + ordered->len - 1, @@ -5938,7 +5970,7 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, int rw, u64 file_offset, int skip_sum, - u32 *csums) + u32 *csums, int async_submit) { int write = rw & REQ_WRITE; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -5949,13 +5981,24 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, if (ret) goto err; - if (write && !skip_sum) { + if (skip_sum) + goto map; + + if (write && async_submit) { ret = btrfs_wq_submit_bio(root->fs_info, inode, rw, bio, 0, 0, file_offset, __btrfs_submit_bio_start_direct_io, __btrfs_submit_bio_done); goto err; + } else if (write) { + /* + * If we aren't doing async submit, calculate the csum of the + * bio now. + */ + ret = btrfs_csum_one_bio(root, inode, bio, file_offset, 1); + if (ret) + goto err; } else if (!skip_sum) { ret = btrfs_lookup_bio_sums_dio(root, inode, bio, file_offset, csums); @@ -5963,7 +6006,8 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, goto err; } - ret = btrfs_map_bio(root, rw, bio, 0, 1); +map: + ret = btrfs_map_bio(root, rw, bio, 0, async_submit); err: bio_put(bio); return ret; @@ -5985,15 +6029,9 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, int nr_pages = 0; u32 *csums = dip->csums; int ret = 0; + int async_submit = 0; int write = rw & REQ_WRITE; - bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS); - if (!bio) - return -ENOMEM; - bio->bi_private = dip; - bio->bi_end_io = btrfs_end_dio_bio; - atomic_inc(&dip->pending_bios); - map_length = orig_bio->bi_size; ret = btrfs_map_block(map_tree, READ, start_sector << 9, &map_length, NULL, 0); @@ -6002,6 +6040,19 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, return -EIO; } + if (map_length >= orig_bio->bi_size) { + bio = orig_bio; + goto submit; + } + + async_submit = 1; + bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS); + if (!bio) + return -ENOMEM; + bio->bi_private = dip; + bio->bi_end_io = btrfs_end_dio_bio; + atomic_inc(&dip->pending_bios); + while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) { if (unlikely(map_length < submit_len + bvec->bv_len || bio_add_page(bio, bvec->bv_page, bvec->bv_len, @@ -6015,7 +6066,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, atomic_inc(&dip->pending_bios); ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum, - csums); + csums, async_submit); if (ret) { bio_put(bio); atomic_dec(&dip->pending_bios); @@ -6052,8 +6103,9 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, } } +submit: ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum, - csums); + csums, async_submit); if (!ret) return 0; @@ -6148,6 +6200,7 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io unsigned long nr_segs) { int seg; + int i; size_t size; unsigned long addr; unsigned blocksize_mask = root->sectorsize - 1; @@ -6162,8 +6215,22 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io addr = (unsigned long)iov[seg].iov_base; size = iov[seg].iov_len; end += size; - if ((addr & blocksize_mask) || (size & blocksize_mask)) + if ((addr & blocksize_mask) || (size & blocksize_mask)) goto out; + + /* If this is a write we don't need to check anymore */ + if (rw & WRITE) + continue; + + /* + * Check to make sure we don't have duplicate iov_base's in this + * iovec, if so return EINVAL, otherwise we'll get csum errors + * when reading back. + */ + for (i = seg + 1; i < nr_segs; i++) { + if (iov[seg].iov_base == iov[i].iov_base) + goto out; + } } retval = 0; out: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index cfc264fefdb..ffb48d6c543 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2287,7 +2287,7 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) struct btrfs_ioctl_space_info space; struct btrfs_ioctl_space_info *dest; struct btrfs_ioctl_space_info *dest_orig; - struct btrfs_ioctl_space_info *user_dest; + struct btrfs_ioctl_space_info __user *user_dest; struct btrfs_space_info *info; u64 types[] = {BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_SYSTEM, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 58e7de9cc90..0ac712efcdf 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -159,7 +159,7 @@ enum { Opt_compress_type, Opt_compress_force, Opt_compress_force_type, Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard, Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, - Opt_enospc_debug, Opt_err, + Opt_enospc_debug, Opt_subvolrootid, Opt_err, }; static match_table_t tokens = { @@ -189,6 +189,7 @@ static match_table_t tokens = { {Opt_clear_cache, "clear_cache"}, {Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"}, {Opt_enospc_debug, "enospc_debug"}, + {Opt_subvolrootid, "subvolrootid=%d"}, {Opt_err, NULL}, }; @@ -232,6 +233,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) break; case Opt_subvol: case Opt_subvolid: + case Opt_subvolrootid: case Opt_device: /* * These are parsed by btrfs_parse_early_options @@ -388,7 +390,7 @@ out: */ static int btrfs_parse_early_options(const char *options, fmode_t flags, void *holder, char **subvol_name, u64 *subvol_objectid, - struct btrfs_fs_devices **fs_devices) + u64 *subvol_rootid, struct btrfs_fs_devices **fs_devices) { substring_t args[MAX_OPT_ARGS]; char *opts, *orig, *p; @@ -429,6 +431,18 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags, *subvol_objectid = intarg; } break; + case Opt_subvolrootid: + intarg = 0; + error = match_int(&args[0], &intarg); + if (!error) { + /* we want the original fs_tree */ + if (!intarg) + *subvol_rootid = + BTRFS_FS_TREE_OBJECTID; + else + *subvol_rootid = intarg; + } + break; case Opt_device: error = btrfs_scan_one_device(match_strdup(&args[0]), flags, holder, fs_devices); @@ -736,6 +750,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, fmode_t mode = FMODE_READ; char *subvol_name = NULL; u64 subvol_objectid = 0; + u64 subvol_rootid = 0; int error = 0; if (!(flags & MS_RDONLY)) @@ -743,7 +758,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, error = btrfs_parse_early_options(data, mode, fs_type, &subvol_name, &subvol_objectid, - &fs_devices); + &subvol_rootid, &fs_devices); if (error) return ERR_PTR(error); @@ -807,15 +822,17 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, s->s_flags |= MS_ACTIVE; } - root = get_default_root(s, subvol_objectid); - if (IS_ERR(root)) { - error = PTR_ERR(root); - deactivate_locked_super(s); - goto error_free_subvol_name; - } /* if they gave us a subvolume name bind mount into that */ if (strcmp(subvol_name, ".")) { struct dentry *new_root; + + root = get_default_root(s, subvol_rootid); + if (IS_ERR(root)) { + error = PTR_ERR(root); + deactivate_locked_super(s); + goto error_free_subvol_name; + } + mutex_lock(&root->d_inode->i_mutex); new_root = lookup_one_len(subvol_name, root, strlen(subvol_name)); @@ -836,6 +853,13 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } dput(root); root = new_root; + } else { + root = get_default_root(s, subvol_objectid); + if (IS_ERR(root)) { + error = PTR_ERR(root); + deactivate_locked_super(s); + goto error_free_subvol_name; + } } kfree(subvol_name); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 5b158da7e0b..c571734d5e5 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -32,10 +32,8 @@ static noinline void put_transaction(struct btrfs_transaction *transaction) { - WARN_ON(transaction->use_count == 0); - transaction->use_count--; - if (transaction->use_count == 0) { - list_del_init(&transaction->list); + WARN_ON(atomic_read(&transaction->use_count) == 0); + if (atomic_dec_and_test(&transaction->use_count)) { memset(transaction, 0, sizeof(*transaction)); kmem_cache_free(btrfs_transaction_cachep, transaction); } @@ -60,14 +58,14 @@ static noinline int join_transaction(struct btrfs_root *root) if (!cur_trans) return -ENOMEM; root->fs_info->generation++; - cur_trans->num_writers = 1; + atomic_set(&cur_trans->num_writers, 1); cur_trans->num_joined = 0; cur_trans->transid = root->fs_info->generation; init_waitqueue_head(&cur_trans->writer_wait); init_waitqueue_head(&cur_trans->commit_wait); cur_trans->in_commit = 0; cur_trans->blocked = 0; - cur_trans->use_count = 1; + atomic_set(&cur_trans->use_count, 1); cur_trans->commit_done = 0; cur_trans->start_time = get_seconds(); @@ -88,7 +86,7 @@ static noinline int join_transaction(struct btrfs_root *root) root->fs_info->running_transaction = cur_trans; spin_unlock(&root->fs_info->new_trans_lock); } else { - cur_trans->num_writers++; + atomic_inc(&cur_trans->num_writers); cur_trans->num_joined++; } @@ -145,7 +143,7 @@ static void wait_current_trans(struct btrfs_root *root) cur_trans = root->fs_info->running_transaction; if (cur_trans && cur_trans->blocked) { DEFINE_WAIT(wait); - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); while (1) { prepare_to_wait(&root->fs_info->transaction_wait, &wait, TASK_UNINTERRUPTIBLE); @@ -181,6 +179,7 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root, { struct btrfs_trans_handle *h; struct btrfs_transaction *cur_trans; + int retries = 0; int ret; if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) @@ -204,7 +203,7 @@ again: } cur_trans = root->fs_info->running_transaction; - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); if (type != TRANS_JOIN_NOLOCK) mutex_unlock(&root->fs_info->trans_mutex); @@ -224,10 +223,18 @@ again: if (num_items > 0) { ret = btrfs_trans_reserve_metadata(h, root, num_items); - if (ret == -EAGAIN) { + if (ret == -EAGAIN && !retries) { + retries++; btrfs_commit_transaction(h, root); goto again; + } else if (ret == -EAGAIN) { + /* + * We have already retried and got EAGAIN, so really we + * don't have space, so set ret to -ENOSPC. + */ + ret = -ENOSPC; } + if (ret < 0) { btrfs_end_transaction(h, root); return ERR_PTR(ret); @@ -327,7 +334,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) goto out_unlock; /* nothing committing|committed */ } - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); mutex_unlock(&root->fs_info->trans_mutex); wait_for_commit(root, cur_trans); @@ -457,18 +464,14 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, wake_up_process(info->transaction_kthread); } - if (lock) - mutex_lock(&info->trans_mutex); WARN_ON(cur_trans != info->running_transaction); - WARN_ON(cur_trans->num_writers < 1); - cur_trans->num_writers--; + WARN_ON(atomic_read(&cur_trans->num_writers) < 1); + atomic_dec(&cur_trans->num_writers); smp_mb(); if (waitqueue_active(&cur_trans->writer_wait)) wake_up(&cur_trans->writer_wait); put_transaction(cur_trans); - if (lock) - mutex_unlock(&info->trans_mutex); if (current->journal_info == trans) current->journal_info = NULL; @@ -1178,7 +1181,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, /* take transaction reference */ mutex_lock(&root->fs_info->trans_mutex); cur_trans = trans->transaction; - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); mutex_unlock(&root->fs_info->trans_mutex); btrfs_end_transaction(trans, root); @@ -1237,7 +1240,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, mutex_lock(&root->fs_info->trans_mutex); if (cur_trans->in_commit) { - cur_trans->use_count++; + atomic_inc(&cur_trans->use_count); mutex_unlock(&root->fs_info->trans_mutex); btrfs_end_transaction(trans, root); @@ -1259,7 +1262,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, prev_trans = list_entry(cur_trans->list.prev, struct btrfs_transaction, list); if (!prev_trans->commit_done) { - prev_trans->use_count++; + atomic_inc(&prev_trans->use_count); mutex_unlock(&root->fs_info->trans_mutex); wait_for_commit(root, prev_trans); @@ -1300,14 +1303,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, TASK_UNINTERRUPTIBLE); smp_mb(); - if (cur_trans->num_writers > 1) + if (atomic_read(&cur_trans->num_writers) > 1) schedule_timeout(MAX_SCHEDULE_TIMEOUT); else if (should_grow) schedule_timeout(1); mutex_lock(&root->fs_info->trans_mutex); finish_wait(&cur_trans->writer_wait, &wait); - } while (cur_trans->num_writers > 1 || + } while (atomic_read(&cur_trans->num_writers) > 1 || (should_grow && cur_trans->num_joined != joined)); ret = create_pending_snapshots(trans, root->fs_info); @@ -1394,6 +1397,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, wake_up(&cur_trans->commit_wait); + list_del_init(&cur_trans->list); put_transaction(cur_trans); put_transaction(cur_trans); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 229a594cacd..e441acc6c58 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -27,11 +27,11 @@ struct btrfs_transaction { * total writers in this transaction, it must be zero before the * transaction can end */ - unsigned long num_writers; + atomic_t num_writers; unsigned long num_joined; int in_commit; - int use_count; + atomic_t use_count; int commit_done; int blocked; struct list_head list; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index a5303b871b1..cfd660550de 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -180,11 +180,10 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) struct btrfs_path *path; struct extent_buffer *leaf; struct btrfs_dir_item *di; - int ret = 0, slot, advance; + int ret = 0, slot; size_t total_size = 0, size_left = size; unsigned long name_ptr; size_t name_len; - u32 nritems; /* * ok we want all objects associated with this id. @@ -204,34 +203,24 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto err; - advance = 0; + while (1) { leaf = path->nodes[0]; - nritems = btrfs_header_nritems(leaf); slot = path->slots[0]; /* this is where we start walking through the path */ - if (advance || slot >= nritems) { + if (slot >= btrfs_header_nritems(leaf)) { /* * if we've reached the last slot in this leaf we need * to go to the next leaf and reset everything */ - if (slot >= nritems-1) { - ret = btrfs_next_leaf(root, path); - if (ret) - break; - leaf = path->nodes[0]; - nritems = btrfs_header_nritems(leaf); - slot = path->slots[0]; - } else { - /* - * just walking through the slots on this leaf - */ - slot++; - path->slots[0]++; - } + ret = btrfs_next_leaf(root, path); + if (ret < 0) + goto err; + else if (ret > 0) + break; + continue; } - advance = 1; btrfs_item_key_to_cpu(leaf, &found_key, slot); @@ -250,7 +239,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) /* we are just looking for how big our buffer needs to be */ if (!size) - continue; + goto next; if (!buffer || (name_len + 1) > size_left) { ret = -ERANGE; @@ -263,6 +252,8 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) size_left -= name_len + 1; buffer += name_len + 1; +next: + path->slots[0]++; } ret = total_size; diff --git a/fs/dcache.c b/fs/dcache.c index ad25c4cec7d..129a3573099 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2131,7 +2131,7 @@ EXPORT_SYMBOL(d_rehash); */ void dentry_update_name_case(struct dentry *dentry, struct qstr *name) { - BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); + BUG_ON(!mutex_is_locked(&dentry->d_parent->d_inode->i_mutex)); BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */ spin_lock(&dentry->d_lock); diff --git a/fs/fhandle.c b/fs/fhandle.c index bf93ad2bee0..6b088641f5b 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -7,6 +7,7 @@ #include <linux/exportfs.h> #include <linux/fs_struct.h> #include <linux/fsnotify.h> +#include <linux/personality.h> #include <asm/uaccess.h> #include "internal.h" diff --git a/fs/filesystems.c b/fs/filesystems.c index 751d6b255a1..0845f84f2a5 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -110,14 +110,13 @@ int unregister_filesystem(struct file_system_type * fs) *tmp = fs->next; fs->next = NULL; write_unlock(&file_systems_lock); + synchronize_rcu(); return 0; } tmp = &(*tmp)->next; } write_unlock(&file_systems_lock); - synchronize_rcu(); - return -EINVAL; } diff --git a/fs/namei.c b/fs/namei.c index e6cd6113872..54fc993e302 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -697,6 +697,7 @@ static __always_inline void set_root_rcu(struct nameidata *nd) do { seq = read_seqcount_begin(&fs->seq); nd->root = fs->root; + nd->seq = __read_seqcount_begin(&nd->root.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } } diff --git a/fs/partitions/ldm.c b/fs/partitions/ldm.c index b10e3540d5b..ce4f6244042 100644 --- a/fs/partitions/ldm.c +++ b/fs/partitions/ldm.c @@ -1299,6 +1299,11 @@ static bool ldm_frag_add (const u8 *data, int size, struct list_head *frags) BUG_ON (!data || !frags); + if (size < 2 * VBLK_SIZE_HEAD) { + ldm_error("Value of size is to small."); + return false; + } + group = get_unaligned_be32(data + 0x08); rec = get_unaligned_be16(data + 0x0C); num = get_unaligned_be16(data + 0x0E); @@ -1306,6 +1311,10 @@ static bool ldm_frag_add (const u8 *data, int size, struct list_head *frags) ldm_error ("A VBLK claims to have %d parts.", num); return false; } + if (rec >= num) { + ldm_error("REC value (%d) exceeds NUM value (%d)", rec, num); + return false; + } list_for_each (item, frags) { f = list_entry (item, struct frag, list); @@ -1334,10 +1343,9 @@ found: f->map |= (1 << rec); - if (num > 0) { - data += VBLK_SIZE_HEAD; - size -= VBLK_SIZE_HEAD; - } + data += VBLK_SIZE_HEAD; + size -= VBLK_SIZE_HEAD; + memcpy (f->data+rec*(size-VBLK_SIZE_HEAD)+VBLK_SIZE_HEAD, data, size); return true; diff --git a/fs/proc/base.c b/fs/proc/base.c index dd6628d3ba4..dfa532730e5 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3124,11 +3124,16 @@ static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldi /* for the /proc/ directory itself, after non-process stuff has been done */ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) { - unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY; - struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode); + unsigned int nr; + struct task_struct *reaper; struct tgid_iter iter; struct pid_namespace *ns; + if (filp->f_pos >= PID_MAX_LIMIT + TGID_OFFSET) + goto out_no_task; + nr = filp->f_pos - FIRST_PROCESS_ENTRY; + + reaper = get_proc_task(filp->f_path.dentry->d_inode); if (!reaper) goto out_no_task; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 9eead2c796b..fbb0b478a34 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -112,6 +112,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) SetPageDirty(page); unlock_page(page); + put_page(page); } return 0; diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index 919f0de29d8..e6493cac193 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -23,6 +23,12 @@ #ifndef __UBIFS_DEBUG_H__ #define __UBIFS_DEBUG_H__ +/* Checking helper functions */ +typedef int (*dbg_leaf_callback)(struct ubifs_info *c, + struct ubifs_zbranch *zbr, void *priv); +typedef int (*dbg_znode_callback)(struct ubifs_info *c, + struct ubifs_znode *znode, void *priv); + #ifdef CONFIG_UBIFS_FS_DEBUG /** @@ -270,11 +276,6 @@ void dbg_dump_tnc(struct ubifs_info *c); void dbg_dump_index(struct ubifs_info *c); void dbg_dump_lpt_lebs(const struct ubifs_info *c); -/* Checking helper functions */ -typedef int (*dbg_leaf_callback)(struct ubifs_info *c, - struct ubifs_zbranch *zbr, void *priv); -typedef int (*dbg_znode_callback)(struct ubifs_info *c, - struct ubifs_znode *znode, void *priv); int dbg_walk_index(struct ubifs_info *c, dbg_leaf_callback leaf_cb, dbg_znode_callback znode_cb, void *priv); @@ -295,7 +296,6 @@ int dbg_check_idx_size(struct ubifs_info *c, long long idx_size); int dbg_check_filesystem(struct ubifs_info *c); void dbg_check_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat, int add_pos); -int dbg_check_lprops(struct ubifs_info *c); int dbg_check_lpt_nodes(struct ubifs_info *c, struct ubifs_cnode *cnode, int row, int col); int dbg_check_inode_size(struct ubifs_info *c, const struct inode *inode, @@ -401,58 +401,94 @@ void dbg_debugfs_exit_fs(struct ubifs_info *c); #define DBGKEY(key) ((char *)(key)) #define DBGKEY1(key) ((char *)(key)) -#define ubifs_debugging_init(c) 0 -#define ubifs_debugging_exit(c) ({}) - -#define dbg_ntype(type) "" -#define dbg_cstate(cmt_state) "" -#define dbg_jhead(jhead) "" -#define dbg_get_key_dump(c, key) ({}) -#define dbg_dump_inode(c, inode) ({}) -#define dbg_dump_node(c, node) ({}) -#define dbg_dump_lpt_node(c, node, lnum, offs) ({}) -#define dbg_dump_budget_req(req) ({}) -#define dbg_dump_lstats(lst) ({}) -#define dbg_dump_budg(c) ({}) -#define dbg_dump_lprop(c, lp) ({}) -#define dbg_dump_lprops(c) ({}) -#define dbg_dump_lpt_info(c) ({}) -#define dbg_dump_leb(c, lnum) ({}) -#define dbg_dump_znode(c, znode) ({}) -#define dbg_dump_heap(c, heap, cat) ({}) -#define dbg_dump_pnode(c, pnode, parent, iip) ({}) -#define dbg_dump_tnc(c) ({}) -#define dbg_dump_index(c) ({}) -#define dbg_dump_lpt_lebs(c) ({}) - -#define dbg_walk_index(c, leaf_cb, znode_cb, priv) 0 -#define dbg_old_index_check_init(c, zroot) 0 -#define dbg_save_space_info(c) ({}) -#define dbg_check_space_info(c) 0 -#define dbg_check_old_index(c, zroot) 0 -#define dbg_check_cats(c) 0 -#define dbg_check_ltab(c) 0 -#define dbg_chk_lpt_free_spc(c) 0 -#define dbg_chk_lpt_sz(c, action, len) 0 -#define dbg_check_synced_i_size(inode) 0 -#define dbg_check_dir_size(c, dir) 0 -#define dbg_check_tnc(c, x) 0 -#define dbg_check_idx_size(c, idx_size) 0 -#define dbg_check_filesystem(c) 0 -#define dbg_check_heap(c, heap, cat, add_pos) ({}) -#define dbg_check_lprops(c) 0 -#define dbg_check_lpt_nodes(c, cnode, row, col) 0 -#define dbg_check_inode_size(c, inode, size) 0 -#define dbg_check_data_nodes_order(c, head) 0 -#define dbg_check_nondata_nodes_order(c, head) 0 -#define dbg_force_in_the_gaps_enabled 0 -#define dbg_force_in_the_gaps() 0 -#define dbg_failure_mode 0 - -#define dbg_debugfs_init() 0 -#define dbg_debugfs_exit() -#define dbg_debugfs_init_fs(c) 0 -#define dbg_debugfs_exit_fs(c) 0 +static inline int ubifs_debugging_init(struct ubifs_info *c) { return 0; } +static inline void ubifs_debugging_exit(struct ubifs_info *c) { return; } +static inline const char *dbg_ntype(int type) { return ""; } +static inline const char *dbg_cstate(int cmt_state) { return ""; } +static inline const char *dbg_jhead(int jhead) { return ""; } +static inline const char * +dbg_get_key_dump(const struct ubifs_info *c, + const union ubifs_key *key) { return ""; } +static inline void dbg_dump_inode(const struct ubifs_info *c, + const struct inode *inode) { return; } +static inline void dbg_dump_node(const struct ubifs_info *c, + const void *node) { return; } +static inline void dbg_dump_lpt_node(const struct ubifs_info *c, + void *node, int lnum, + int offs) { return; } +static inline void +dbg_dump_budget_req(const struct ubifs_budget_req *req) { return; } +static inline void +dbg_dump_lstats(const struct ubifs_lp_stats *lst) { return; } +static inline void dbg_dump_budg(struct ubifs_info *c) { return; } +static inline void dbg_dump_lprop(const struct ubifs_info *c, + const struct ubifs_lprops *lp) { return; } +static inline void dbg_dump_lprops(struct ubifs_info *c) { return; } +static inline void dbg_dump_lpt_info(struct ubifs_info *c) { return; } +static inline void dbg_dump_leb(const struct ubifs_info *c, + int lnum) { return; } +static inline void +dbg_dump_znode(const struct ubifs_info *c, + const struct ubifs_znode *znode) { return; } +static inline void dbg_dump_heap(struct ubifs_info *c, + struct ubifs_lpt_heap *heap, + int cat) { return; } +static inline void dbg_dump_pnode(struct ubifs_info *c, + struct ubifs_pnode *pnode, + struct ubifs_nnode *parent, + int iip) { return; } +static inline void dbg_dump_tnc(struct ubifs_info *c) { return; } +static inline void dbg_dump_index(struct ubifs_info *c) { return; } +static inline void dbg_dump_lpt_lebs(const struct ubifs_info *c) { return; } + +static inline int dbg_walk_index(struct ubifs_info *c, + dbg_leaf_callback leaf_cb, + dbg_znode_callback znode_cb, + void *priv) { return 0; } +static inline void dbg_save_space_info(struct ubifs_info *c) { return; } +static inline int dbg_check_space_info(struct ubifs_info *c) { return 0; } +static inline int dbg_check_lprops(struct ubifs_info *c) { return 0; } +static inline int +dbg_old_index_check_init(struct ubifs_info *c, + struct ubifs_zbranch *zroot) { return 0; } +static inline int +dbg_check_old_index(struct ubifs_info *c, + struct ubifs_zbranch *zroot) { return 0; } +static inline int dbg_check_cats(struct ubifs_info *c) { return 0; } +static inline int dbg_check_ltab(struct ubifs_info *c) { return 0; } +static inline int dbg_chk_lpt_free_spc(struct ubifs_info *c) { return 0; } +static inline int dbg_chk_lpt_sz(struct ubifs_info *c, + int action, int len) { return 0; } +static inline int dbg_check_synced_i_size(struct inode *inode) { return 0; } +static inline int dbg_check_dir_size(struct ubifs_info *c, + const struct inode *dir) { return 0; } +static inline int dbg_check_tnc(struct ubifs_info *c, int extra) { return 0; } +static inline int dbg_check_idx_size(struct ubifs_info *c, + long long idx_size) { return 0; } +static inline int dbg_check_filesystem(struct ubifs_info *c) { return 0; } +static inline void dbg_check_heap(struct ubifs_info *c, + struct ubifs_lpt_heap *heap, + int cat, int add_pos) { return; } +static inline int dbg_check_lpt_nodes(struct ubifs_info *c, + struct ubifs_cnode *cnode, int row, int col) { return 0; } +static inline int dbg_check_inode_size(struct ubifs_info *c, + const struct inode *inode, + loff_t size) { return 0; } +static inline int +dbg_check_data_nodes_order(struct ubifs_info *c, + struct list_head *head) { return 0; } +static inline int +dbg_check_nondata_nodes_order(struct ubifs_info *c, + struct list_head *head) { return 0; } + +static inline int dbg_force_in_the_gaps(void) { return 0; } +#define dbg_force_in_the_gaps_enabled 0 +#define dbg_failure_mode 0 + +static inline int dbg_debugfs_init(void) { return 0; } +static inline void dbg_debugfs_exit(void) { return; } +static inline int dbg_debugfs_init_fs(struct ubifs_info *c) { return 0; } +static inline int dbg_debugfs_exit_fs(struct ubifs_info *c) { return 0; } #endif /* !CONFIG_UBIFS_FS_DEBUG */ #endif /* !__UBIFS_DEBUG_H__ */ diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 28be1e6a65e..b286db79c68 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1312,6 +1312,9 @@ int ubifs_fsync(struct file *file, int datasync) dbg_gen("syncing inode %lu", inode->i_ino); + if (inode->i_sb->s_flags & MS_RDONLY) + return 0; + /* * VFS has already synchronized dirty pages for this inode. Synchronize * the inode unless this is a 'datasync()' call. diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 32176cc8e71..cbbfd98ad4a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -697,7 +697,7 @@ extern void blk_start_queue(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(struct request_queue *q); -extern void __blk_run_queue(struct request_queue *q, bool force_kblockd); +extern void __blk_run_queue(struct request_queue *q); extern void blk_run_queue(struct request_queue *); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, @@ -857,26 +857,39 @@ extern void blk_put_queue(struct request_queue *); struct blk_plug { unsigned long magic; struct list_head list; + struct list_head cb_list; unsigned int should_sort; }; +struct blk_plug_cb { + struct list_head list; + void (*callback)(struct blk_plug_cb *); +}; extern void blk_start_plug(struct blk_plug *); extern void blk_finish_plug(struct blk_plug *); -extern void __blk_flush_plug(struct task_struct *, struct blk_plug *); +extern void blk_flush_plug_list(struct blk_plug *, bool); static inline void blk_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; - if (unlikely(plug)) - __blk_flush_plug(tsk, plug); + if (plug) + blk_flush_plug_list(plug, false); +} + +static inline void blk_schedule_flush_plug(struct task_struct *tsk) +{ + struct blk_plug *plug = tsk->plug; + + if (plug) + blk_flush_plug_list(plug, true); } static inline bool blk_needs_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; - return plug && !list_empty(&plug->list); + return plug && (!list_empty(&plug->list) || !list_empty(&plug->cb_list)); } /* @@ -1314,6 +1327,11 @@ static inline void blk_flush_plug(struct task_struct *task) { } +static inline void blk_schedule_flush_plug(struct task_struct *task) +{ +} + + static inline bool blk_needs_flush_plug(struct task_struct *tsk) { return false; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index e2768834f39..32a4423710f 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -197,7 +197,6 @@ struct dm_target { struct dm_target_callbacks { struct list_head list; int (*congested_fn) (struct dm_target_callbacks *, int); - void (*unplug_fn)(struct dm_target_callbacks *); }; int dm_register_target(struct target_type *t); diff --git a/include/linux/input.h b/include/linux/input.h index f3a7794a18c..771d6d85667 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -167,6 +167,7 @@ struct input_keymap_entry { #define SYN_REPORT 0 #define SYN_CONFIG 1 #define SYN_MT_REPORT 2 +#define SYN_DROPPED 3 /* * Keys and buttons @@ -553,8 +554,8 @@ struct input_keymap_entry { #define KEY_DVD 0x185 /* Media Select DVD */ #define KEY_AUX 0x186 #define KEY_MP3 0x187 -#define KEY_AUDIO 0x188 -#define KEY_VIDEO 0x189 +#define KEY_AUDIO 0x188 /* AL Audio Browser */ +#define KEY_VIDEO 0x189 /* AL Movie Browser */ #define KEY_DIRECTORY 0x18a #define KEY_LIST 0x18b #define KEY_MEMO 0x18c /* Media Select Messages */ @@ -603,8 +604,9 @@ struct input_keymap_entry { #define KEY_FRAMEFORWARD 0x1b5 #define KEY_CONTEXT_MENU 0x1b6 /* GenDesc - system context menu */ #define KEY_MEDIA_REPEAT 0x1b7 /* Consumer - transport control */ -#define KEY_10CHANNELSUP 0x1b8 /* 10 channels up (10+) */ -#define KEY_10CHANNELSDOWN 0x1b9 /* 10 channels down (10-) */ +#define KEY_10CHANNELSUP 0x1b8 /* 10 channels up (10+) */ +#define KEY_10CHANNELSDOWN 0x1b9 /* 10 channels down (10-) */ +#define KEY_IMAGES 0x1ba /* AL Image Browser */ #define KEY_DEL_EOL 0x1c0 #define KEY_DEL_EOS 0x1c1 diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h index b3ac06a4435..318bb82325a 100644 --- a/include/linux/input/mt.h +++ b/include/linux/input/mt.h @@ -48,6 +48,12 @@ static inline void input_mt_slot(struct input_dev *dev, int slot) input_event(dev, EV_ABS, ABS_MT_SLOT, slot); } +static inline bool input_is_mt_axis(int axis) +{ + return axis == ABS_MT_SLOT || + (axis >= ABS_MT_FIRST && axis <= ABS_MT_LAST); +} + void input_mt_report_slot_state(struct input_dev *dev, unsigned int tool_type, bool active); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5a5ce705583..5e9840f5098 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -216,7 +216,7 @@ static inline void mem_cgroup_del_lru_list(struct page *page, int lru) return ; } -static inline inline void mem_cgroup_rotate_reclaimable_page(struct page *page) +static inline void mem_cgroup_rotate_reclaimable_page(struct page *page) { return ; } diff --git a/include/linux/pid.h b/include/linux/pid.h index 31afb7ecbe1..cdced84261d 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -117,7 +117,7 @@ extern struct pid *find_vpid(int nr); */ extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); -int next_pidmap(struct pid_namespace *pid_ns, int last); +int next_pidmap(struct pid_namespace *pid_ns, unsigned int last); extern struct pid *alloc_pid(struct pid_namespace *ns); extern void free_pid(struct pid *pid); diff --git a/include/linux/rio.h b/include/linux/rio.h index 4e37a7cfa72..4d50611112b 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -396,7 +396,7 @@ union rio_pw_msg { }; /* Architecture and hardware-specific functions */ -extern void rio_register_mport(struct rio_mport *); +extern int rio_register_mport(struct rio_mport *); extern int rio_open_inb_mbox(struct rio_mport *, void *, int, int); extern void rio_close_inb_mbox(struct rio_mport *, int); extern int rio_open_outb_mbox(struct rio_mport *, void *, int, int); diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h index 7410d3365e2..0cee0152aca 100644 --- a/include/linux/rio_ids.h +++ b/include/linux/rio_ids.h @@ -35,6 +35,7 @@ #define RIO_DID_IDTCPS6Q 0x035f #define RIO_DID_IDTCPS10Q 0x035e #define RIO_DID_IDTCPS1848 0x0374 +#define RIO_DID_IDTCPS1432 0x0375 #define RIO_DID_IDTCPS1616 0x0379 #define RIO_DID_IDTVPS1616 0x0377 #define RIO_DID_IDTSPS1616 0x0378 diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 2ca7e8a7806..877ece45426 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -228,6 +228,8 @@ extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); extern int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); +extern int rtc_initialize_alarm(struct rtc_device *rtc, + struct rtc_wkalrm *alrm); extern void rtc_update_irq(struct rtc_device *rtc, unsigned long num, unsigned long events); diff --git a/include/linux/sched.h b/include/linux/sched.h index d9ca3aa511f..171ba24b08a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1247,6 +1247,9 @@ struct task_struct { #endif struct mm_struct *mm, *active_mm; +#ifdef CONFIG_COMPAT_BRK + unsigned brk_randomized:1; +#endif #if defined(SPLIT_RSS_COUNTING) struct task_rss_stat rss_stat; #endif diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 461c0119664..2b3831b58aa 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -58,6 +58,13 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, UNEVICTABLE_PGCLEARED, /* on COW, page truncate */ UNEVICTABLE_PGSTRANDED, /* unable to isolate on unlock */ UNEVICTABLE_MLOCKFREED, +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + THP_FAULT_ALLOC, + THP_FAULT_FALLBACK, + THP_COLLAPSE_ALLOC, + THP_COLLAPSE_ALLOC_FAILED, + THP_SPLIT, +#endif NR_VM_EVENT_ITEMS }; diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h index cdf2e8ac430..d2df55b0c21 100644 --- a/include/net/9p/9p.h +++ b/include/net/9p/9p.h @@ -139,8 +139,6 @@ do { \ */ enum p9_msg_t { - P9_TSYNCFS = 0, - P9_RSYNCFS, P9_TLERROR = 6, P9_RLERROR, P9_TSTATFS = 8, diff --git a/include/net/9p/client.h b/include/net/9p/client.h index 85c1413f054..051a99f7976 100644 --- a/include/net/9p/client.h +++ b/include/net/9p/client.h @@ -218,8 +218,8 @@ void p9_client_disconnect(struct p9_client *clnt); void p9_client_begin_disconnect(struct p9_client *clnt); struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, char *uname, u32 n_uname, char *aname); -struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, - int clone); +struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, + char **wnames, int clone); int p9_client_open(struct p9_fid *fid, int mode); int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode, char *extension); @@ -230,7 +230,6 @@ int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode, gid_t gid, struct p9_qid *qid); int p9_client_clunk(struct p9_fid *fid); int p9_client_fsync(struct p9_fid *fid, int datasync); -int p9_client_sync_fs(struct p9_fid *fid); int p9_client_remove(struct p9_fid *fid); int p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset, u32 count); diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 78f18adb49c..bf366547da2 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -401,9 +401,9 @@ TRACE_EVENT(block_plug, DECLARE_EVENT_CLASS(block_unplug, - TP_PROTO(struct request_queue *q), + TP_PROTO(struct request_queue *q, unsigned int depth, bool explicit), - TP_ARGS(q), + TP_ARGS(q, depth, explicit), TP_STRUCT__entry( __field( int, nr_rq ) @@ -411,7 +411,7 @@ DECLARE_EVENT_CLASS(block_unplug, ), TP_fast_assign( - __entry->nr_rq = q->rq.count[READ] + q->rq.count[WRITE]; + __entry->nr_rq = depth; memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -419,31 +419,19 @@ DECLARE_EVENT_CLASS(block_unplug, ); /** - * block_unplug_timer - timed release of operations requests in queue to device driver - * @q: request queue to unplug - * - * Unplug the request queue @q because a timer expired and allow block - * operation requests to be sent to the device driver. - */ -DEFINE_EVENT(block_unplug, block_unplug_timer, - - TP_PROTO(struct request_queue *q), - - TP_ARGS(q) -); - -/** - * block_unplug_io - release of operations requests in request queue + * block_unplug - release of operations requests in request queue * @q: request queue to unplug + * @depth: number of requests just added to the queue + * @explicit: whether this was an explicit unplug, or one from schedule() * * Unplug request queue @q because device driver is scheduled to work * on elements in the request queue. */ -DEFINE_EVENT(block_unplug, block_unplug_io, +DEFINE_EVENT(block_unplug, block_unplug, - TP_PROTO(struct request_queue *q), + TP_PROTO(struct request_queue *q, unsigned int depth, bool explicit), - TP_ARGS(q) + TP_ARGS(q, depth, explicit) ); /** diff --git a/kernel/futex.c b/kernel/futex.c index dfb924ffe65..fe28dc282ea 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1886,7 +1886,7 @@ retry: restart->futex.val = val; restart->futex.time = abs_time->tv64; restart->futex.bitset = bitset; - restart->futex.flags = flags; + restart->futex.flags = flags | FLAGS_HAS_TIMEOUT; ret = -ERESTART_RESTARTBLOCK; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 27960f114ef..8e81a9860a0 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -364,6 +364,7 @@ void perf_cgroup_switch(struct task_struct *task, int mode) } if (mode & PERF_CGROUP_SWIN) { + WARN_ON_ONCE(cpuctx->cgrp); /* set cgrp before ctxsw in to * allow event_filter_match() to not * have to pass task around @@ -2423,6 +2424,14 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) if (!ctx || !ctx->nr_events) goto out; + /* + * We must ctxsw out cgroup events to avoid conflict + * when invoking perf_task_event_sched_in() later on + * in this function. Otherwise we end up trying to + * ctxswin cgroup events which are already scheduled + * in. + */ + perf_cgroup_sched_out(current); task_ctx_sched_out(ctx, EVENT_ALL); raw_spin_lock(&ctx->lock); @@ -2447,6 +2456,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) raw_spin_unlock(&ctx->lock); + /* + * Also calls ctxswin for cgroup events, if any: + */ perf_event_context_sched_in(ctx, ctx->task); out: local_irq_restore(flags); diff --git a/kernel/pid.c b/kernel/pid.c index 02f22127426..57a8346a270 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -217,11 +217,14 @@ static int alloc_pidmap(struct pid_namespace *pid_ns) return -1; } -int next_pidmap(struct pid_namespace *pid_ns, int last) +int next_pidmap(struct pid_namespace *pid_ns, unsigned int last) { int offset; struct pidmap *map, *end; + if (last >= PID_MAX_LIMIT) + return -1; + offset = (last + 1) & BITS_PER_PAGE_MASK; map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE]; end = &pid_ns->pidmap[PIDMAP_ENTRIES]; diff --git a/kernel/sched.c b/kernel/sched.c index 27d3e73a2af..30a29ad46eb 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4218,7 +4218,7 @@ need_resched: */ if (blk_needs_flush_plug(prev)) { raw_spin_unlock(&rq->lock); - blk_flush_plug(prev); + blk_schedule_flush_plug(prev); raw_spin_lock(&rq->lock); } } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7aa40f8e182..6957aa298df 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -850,29 +850,21 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q) __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL); } -static void blk_add_trace_unplug_io(void *ignore, struct request_queue *q) +static void blk_add_trace_unplug(void *ignore, struct request_queue *q, + unsigned int depth, bool explicit) { struct blk_trace *bt = q->blk_trace; if (bt) { - unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE]; - __be64 rpdu = cpu_to_be64(pdu); + __be64 rpdu = cpu_to_be64(depth); + u32 what; - __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_IO, 0, - sizeof(rpdu), &rpdu); - } -} - -static void blk_add_trace_unplug_timer(void *ignore, struct request_queue *q) -{ - struct blk_trace *bt = q->blk_trace; - - if (bt) { - unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE]; - __be64 rpdu = cpu_to_be64(pdu); + if (explicit) + what = BLK_TA_UNPLUG_IO; + else + what = BLK_TA_UNPLUG_TIMER; - __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_TIMER, 0, - sizeof(rpdu), &rpdu); + __blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu); } } @@ -1015,9 +1007,7 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_plug(blk_add_trace_plug, NULL); WARN_ON(ret); - ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL); - WARN_ON(ret); - ret = register_trace_block_unplug_io(blk_add_trace_unplug_io, NULL); + ret = register_trace_block_unplug(blk_add_trace_unplug, NULL); WARN_ON(ret); ret = register_trace_block_split(blk_add_trace_split, NULL); WARN_ON(ret); @@ -1032,8 +1022,7 @@ static void blk_unregister_tracepoints(void) unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL); unregister_trace_block_bio_remap(blk_add_trace_bio_remap, NULL); unregister_trace_block_split(blk_add_trace_split, NULL); - unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL); - unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL); + unregister_trace_block_unplug(blk_add_trace_unplug, NULL); unregister_trace_block_plug(blk_add_trace_plug, NULL); unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); unregister_trace_block_getrq(blk_add_trace_getrq, NULL); diff --git a/lib/kstrtox.c b/lib/kstrtox.c index 05672e819f8..a235f3cc471 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -49,12 +49,9 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) val = *s - '0'; else if ('a' <= _tolower(*s) && _tolower(*s) <= 'f') val = _tolower(*s) - 'a' + 10; - else if (*s == '\n') { - if (*(s + 1) == '\0') - break; - else - return -EINVAL; - } else + else if (*s == '\n' && *(s + 1) == '\0') + break; + else return -EINVAL; if (val >= base) diff --git a/lib/test-kstrtox.c b/lib/test-kstrtox.c index 325c2f9eceb..d55769d63cb 100644 --- a/lib/test-kstrtox.c +++ b/lib/test-kstrtox.c @@ -315,12 +315,12 @@ static void __init test_kstrtou64_ok(void) {"65537", 10, 65537}, {"2147483646", 10, 2147483646}, {"2147483647", 10, 2147483647}, - {"2147483648", 10, 2147483648}, - {"2147483649", 10, 2147483649}, - {"4294967294", 10, 4294967294}, - {"4294967295", 10, 4294967295}, - {"4294967296", 10, 4294967296}, - {"4294967297", 10, 4294967297}, + {"2147483648", 10, 2147483648ULL}, + {"2147483649", 10, 2147483649ULL}, + {"4294967294", 10, 4294967294ULL}, + {"4294967295", 10, 4294967295ULL}, + {"4294967296", 10, 4294967296ULL}, + {"4294967297", 10, 4294967297ULL}, {"9223372036854775806", 10, 9223372036854775806ULL}, {"9223372036854775807", 10, 9223372036854775807ULL}, {"9223372036854775808", 10, 9223372036854775808ULL}, @@ -369,12 +369,12 @@ static void __init test_kstrtos64_ok(void) {"65537", 10, 65537}, {"2147483646", 10, 2147483646}, {"2147483647", 10, 2147483647}, - {"2147483648", 10, 2147483648}, - {"2147483649", 10, 2147483649}, - {"4294967294", 10, 4294967294}, - {"4294967295", 10, 4294967295}, - {"4294967296", 10, 4294967296}, - {"4294967297", 10, 4294967297}, + {"2147483648", 10, 2147483648LL}, + {"2147483649", 10, 2147483649LL}, + {"4294967294", 10, 4294967294LL}, + {"4294967295", 10, 4294967295LL}, + {"4294967296", 10, 4294967296LL}, + {"4294967297", 10, 4294967297LL}, {"9223372036854775806", 10, 9223372036854775806LL}, {"9223372036854775807", 10, 9223372036854775807LL}, }; @@ -418,10 +418,10 @@ static void __init test_kstrtou32_ok(void) {"65537", 10, 65537}, {"2147483646", 10, 2147483646}, {"2147483647", 10, 2147483647}, - {"2147483648", 10, 2147483648}, - {"2147483649", 10, 2147483649}, - {"4294967294", 10, 4294967294}, - {"4294967295", 10, 4294967295}, + {"2147483648", 10, 2147483648U}, + {"2147483649", 10, 2147483649U}, + {"4294967294", 10, 4294967294U}, + {"4294967295", 10, 4294967295U}, }; TEST_OK(kstrtou32, u32, "%u", test_u32_ok); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 0a619e0e2e0..470dcda10ad 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -244,24 +244,28 @@ static ssize_t single_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag) { - if (test_bit(flag, &transparent_hugepage_flags)) - return sprintf(buf, "[yes] no\n"); - else - return sprintf(buf, "yes [no]\n"); + return sprintf(buf, "%d\n", + !!test_bit(flag, &transparent_hugepage_flags)); } + static ssize_t single_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag) { - if (!memcmp("yes", buf, - min(sizeof("yes")-1, count))) { + unsigned long value; + int ret; + + ret = kstrtoul(buf, 10, &value); + if (ret < 0) + return ret; + if (value > 1) + return -EINVAL; + + if (value) set_bit(flag, &transparent_hugepage_flags); - } else if (!memcmp("no", buf, - min(sizeof("no")-1, count))) { + else clear_bit(flag, &transparent_hugepage_flags); - } else - return -EINVAL; return count; } @@ -680,8 +684,11 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_OOM; page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), vma, haddr, numa_node_id(), 0); - if (unlikely(!page)) + if (unlikely(!page)) { + count_vm_event(THP_FAULT_FALLBACK); goto out; + } + count_vm_event(THP_FAULT_ALLOC); if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { put_page(page); goto out; @@ -909,11 +916,13 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, new_page = NULL; if (unlikely(!new_page)) { + count_vm_event(THP_FAULT_FALLBACK); ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); put_page(page); goto out; } + count_vm_event(THP_FAULT_ALLOC); if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { put_page(new_page); @@ -1390,6 +1399,7 @@ int split_huge_page(struct page *page) BUG_ON(!PageSwapBacked(page)); __split_huge_page(page, anon_vma); + count_vm_event(THP_SPLIT); BUG_ON(PageCompound(page)); out_unlock: @@ -1784,9 +1794,11 @@ static void collapse_huge_page(struct mm_struct *mm, node, __GFP_OTHER_NODE); if (unlikely(!new_page)) { up_read(&mm->mmap_sem); + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); *hpage = ERR_PTR(-ENOMEM); return; } + count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { up_read(&mm->mmap_sem); put_page(new_page); @@ -2151,8 +2163,11 @@ static void khugepaged_do_scan(struct page **hpage) #ifndef CONFIG_NUMA if (!*hpage) { *hpage = alloc_hugepage(khugepaged_defrag()); - if (unlikely(!*hpage)) + if (unlikely(!*hpage)) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); break; + } + count_vm_event(THP_COLLAPSE_ALLOC); } #else if (IS_ERR(*hpage)) @@ -2192,8 +2207,11 @@ static struct page *khugepaged_alloc_hugepage(void) do { hpage = alloc_hugepage(khugepaged_defrag()); - if (!hpage) + if (!hpage) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); khugepaged_alloc_sleep(); + } else + count_vm_event(THP_COLLAPSE_ALLOC); } while (unlikely(!hpage) && likely(khugepaged_enabled())); return hpage; @@ -2210,8 +2228,11 @@ static void khugepaged_loop(void) while (likely(khugepaged_enabled())) { #ifndef CONFIG_NUMA hpage = khugepaged_alloc_hugepage(); - if (unlikely(!hpage)) + if (unlikely(!hpage)) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); break; + } + count_vm_event(THP_COLLAPSE_ALLOC); #else if (IS_ERR(hpage)) { khugepaged_alloc_sleep(); diff --git a/mm/memory.c b/mm/memory.c index b623a249918..ce22a250926 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3688,7 +3688,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, */ #ifdef CONFIG_HAVE_IOREMAP_PROT vma = find_vma(mm, addr); - if (!vma) + if (!vma || vma->vm_start > addr) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a2acaf820fe..9ca1d604f7c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -375,7 +375,7 @@ void online_page(struct page *page) #endif #ifdef CONFIG_FLATMEM - max_mapnr = max(page_to_pfn(page), max_mapnr); + max_mapnr = max(pfn, max_mapnr); #endif ClearPageReserved(page); diff --git a/mm/mmap.c b/mm/mmap.c index 8c05e5b43b6..e27e0cf0de0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -259,7 +259,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ - if (mm->start_brk > PAGE_ALIGN(mm->end_data)) + if (current->brk_randomized) min_brk = mm->start_brk; else min_brk = mm->end_data; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 6a819d1b2c7..83fb72c108b 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -84,24 +84,6 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk, #endif /* CONFIG_NUMA */ /* - * If this is a system OOM (not a memcg OOM) and the task selected to be - * killed is not already running at high (RT) priorities, speed up the - * recovery by boosting the dying task to the lowest FIFO priority. - * That helps with the recovery and avoids interfering with RT tasks. - */ -static void boost_dying_task_prio(struct task_struct *p, - struct mem_cgroup *mem) -{ - struct sched_param param = { .sched_priority = 1 }; - - if (mem) - return; - - if (!rt_task(p)) - sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); -} - -/* * The process p may have detached its own ->mm while exiting or through * use_mm(), but one or more of its subthreads may still have a valid * pointer. Return p, or any of its subthreads with a valid ->mm, with @@ -452,13 +434,6 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem) set_tsk_thread_flag(p, TIF_MEMDIE); force_sig(SIGKILL, p); - /* - * We give our sacrificial lamb high priority and access to - * all the memory it needs. That way it should be able to - * exit() and clear out its resources quickly... - */ - boost_dying_task_prio(p, mem); - return 0; } #undef K @@ -482,7 +457,6 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, */ if (p->flags & PF_EXITING) { set_tsk_thread_flag(p, TIF_MEMDIE); - boost_dying_task_prio(p, mem); return 0; } @@ -556,7 +530,6 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask) */ if (fatal_signal_pending(current)) { set_thread_flag(TIF_MEMDIE); - boost_dying_task_prio(current, NULL); return; } @@ -712,7 +685,6 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, */ if (fatal_signal_pending(current)) { set_thread_flag(TIF_MEMDIE); - boost_dying_task_prio(current, NULL); return; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2747f5e5abc..9f8a97b9a35 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3176,7 +3176,7 @@ static __init_refok int __build_all_zonelists(void *data) * Called with zonelists_mutex held always * unless system_state == SYSTEM_BOOTING. */ -void build_all_zonelists(void *data) +void __ref build_all_zonelists(void *data) { set_zonelist_order(); diff --git a/mm/shmem.c b/mm/shmem.c index 58da7c150ba..8fa27e4e582 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -421,7 +421,8 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long * a waste to allocate index if we cannot allocate data. */ if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, (sbinfo->max_blocks - 1)) > 0) + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks - 1) >= 0) return ERR_PTR(-ENOSPC); percpu_counter_inc(&sbinfo->used_blocks); spin_lock(&inode->i_lock); @@ -1397,7 +1398,8 @@ repeat: shmem_swp_unmap(entry); sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) { - if ((percpu_counter_compare(&sbinfo->used_blocks, sbinfo->max_blocks) > 0) || + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks) >= 0 || shmem_acct_block(info->flags)) { spin_unlock(&info->lock); error = -ENOSPC; diff --git a/mm/vmscan.c b/mm/vmscan.c index c7f5a6d4b75..f6b435c8007 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -41,6 +41,7 @@ #include <linux/memcontrol.h> #include <linux/delayacct.h> #include <linux/sysctl.h> +#include <linux/oom.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -1988,17 +1989,12 @@ static bool zone_reclaimable(struct zone *zone) return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; } -/* - * As hibernation is going on, kswapd is freezed so that it can't mark - * the zone into all_unreclaimable. It can't handle OOM during hibernation. - * So let's check zone's unreclaimable in direct reclaim as well as kswapd. - */ +/* All zones in zonelist are unreclaimable? */ static bool all_unreclaimable(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; - bool all_unreclaimable = true; for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { @@ -2006,13 +2002,11 @@ static bool all_unreclaimable(struct zonelist *zonelist, continue; if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; - if (zone_reclaimable(zone)) { - all_unreclaimable = false; - break; - } + if (!zone->all_unreclaimable) + return false; } - return all_unreclaimable; + return true; } /* @@ -2108,6 +2102,14 @@ out: if (sc->nr_reclaimed) return sc->nr_reclaimed; + /* + * As hibernation is going on, kswapd is freezed so that it can't mark + * the zone into all_unreclaimable. Thus bypassing all_unreclaimable + * check. + */ + if (oom_killer_disabled) + return 0; + /* top priority shrink_zones still had more to do? don't OOM, then */ if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc)) return 1; diff --git a/mm/vmstat.c b/mm/vmstat.c index 772b39b87d9..897ea9e8823 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -321,9 +321,12 @@ static inline void mod_state(struct zone *zone, /* * The fetching of the stat_threshold is racy. We may apply * a counter threshold to the wrong the cpu if we get - * rescheduled while executing here. However, the following - * will apply the threshold again and therefore bring the - * counter under the threshold. + * rescheduled while executing here. However, the next + * counter update will apply the threshold again and + * therefore bring the counter under the threshold again. + * + * Most of the time the thresholds are the same anyways + * for all cpus in a zone. */ t = this_cpu_read(pcp->stat_threshold); @@ -945,7 +948,16 @@ static const char * const vmstat_text[] = { "unevictable_pgs_cleared", "unevictable_pgs_stranded", "unevictable_pgs_mlockfreed", + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + "thp_fault_alloc", + "thp_fault_fallback", + "thp_collapse_alloc", + "thp_collapse_alloc_failed", + "thp_split", #endif + +#endif /* CONFIG_VM_EVENTS_COUNTERS */ }; static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, diff --git a/net/9p/client.c b/net/9p/client.c index 48b8e084e71..77367745be9 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -929,15 +929,15 @@ error: } EXPORT_SYMBOL(p9_client_attach); -struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, - int clone) +struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, + char **wnames, int clone) { int err; struct p9_client *clnt; struct p9_fid *fid; struct p9_qid *wqids; struct p9_req_t *req; - int16_t nwqids, count; + uint16_t nwqids, count; err = 0; wqids = NULL; @@ -955,7 +955,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, fid = oldfid; - P9_DPRINTK(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %d wname[0] %s\n", + P9_DPRINTK(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n", oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL); req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid, @@ -1220,27 +1220,6 @@ error: } EXPORT_SYMBOL(p9_client_fsync); -int p9_client_sync_fs(struct p9_fid *fid) -{ - int err = 0; - struct p9_req_t *req; - struct p9_client *clnt; - - P9_DPRINTK(P9_DEBUG_9P, ">>> TSYNC_FS fid %d\n", fid->fid); - - clnt = fid->clnt; - req = p9_client_rpc(clnt, P9_TSYNCFS, "d", fid->fid); - if (IS_ERR(req)) { - err = PTR_ERR(req); - goto error; - } - P9_DPRINTK(P9_DEBUG_9P, "<<< RSYNCFS fid %d\n", fid->fid); - p9_free_req(clnt, req); -error: - return err; -} -EXPORT_SYMBOL(p9_client_sync_fs); - int p9_client_clunk(struct p9_fid *fid) { int err; diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 8a4084fa8b5..b58a501cf3d 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -265,7 +265,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'T':{ - int16_t *nwname = va_arg(ap, int16_t *); + uint16_t *nwname = va_arg(ap, uint16_t *); char ***wnames = va_arg(ap, char ***); errcode = p9pdu_readf(pdu, proto_version, @@ -468,7 +468,8 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, case 'E':{ int32_t cnt = va_arg(ap, int32_t); const char *k = va_arg(ap, const void *); - const char *u = va_arg(ap, const void *); + const char __user *u = va_arg(ap, + const void __user *); errcode = p9pdu_writef(pdu, proto_version, "d", cnt); if (!errcode && pdu_write_urw(pdu, k, u, cnt)) @@ -495,7 +496,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, } break; case 'T':{ - int16_t nwname = va_arg(ap, int); + uint16_t nwname = va_arg(ap, int); const char **wnames = va_arg(ap, const char **); errcode = p9pdu_writef(pdu, proto_version, "w", diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index d47880e971d..e883172f9aa 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -66,7 +66,7 @@ p9_payload_gup(struct p9_req_t *req, size_t *pdata_off, int *pdata_len, uint32_t pdata_mapped_pages; struct trans_rpage_info *rpinfo; - *pdata_off = (size_t)req->tc->pubuf & (PAGE_SIZE-1); + *pdata_off = (__force size_t)req->tc->pubuf & (PAGE_SIZE-1); if (*pdata_off) first_page_bytes = min(((size_t)PAGE_SIZE - *pdata_off), diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index e8f046b0718..244e7074218 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -326,8 +326,11 @@ req_retry_pinned: outp = pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM, pdata_off, rpinfo->rp_data, pdata_len); } else { - char *pbuf = req->tc->pubuf ? req->tc->pubuf : - req->tc->pkbuf; + char *pbuf; + if (req->tc->pubuf) + pbuf = (__force char *) req->tc->pubuf; + else + pbuf = req->tc->pkbuf; outp = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, pbuf, req->tc->pbuf_size); } @@ -352,8 +355,12 @@ req_retry_pinned: in = pack_sg_list_p(chan->sg, out+inp, VIRTQUEUE_NUM, pdata_off, rpinfo->rp_data, pdata_len); } else { - char *pbuf = req->tc->pubuf ? req->tc->pubuf : - req->tc->pkbuf; + char *pbuf; + if (req->tc->pubuf) + pbuf = (__force char *) req->tc->pubuf; + else + pbuf = req->tc->pkbuf; + in = pack_sg_list(chan->sg, out+inp, VIRTQUEUE_NUM, pbuf, req->tc->pbuf_size); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 50af02737a3..5a80f41c0cb 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -579,9 +579,15 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc, list_for_each_entry_safe(req, nreq, &osd->o_linger_requests, r_linger_osd) { - __unregister_linger_request(osdc, req); + /* + * reregister request prior to unregistering linger so + * that r_osd is preserved. + */ + BUG_ON(!list_empty(&req->r_req_lru_item)); __register_request(osdc, req); - list_move(&req->r_req_lru_item, &osdc->req_unsent); + list_add(&req->r_req_lru_item, &osdc->req_unsent); + list_add(&req->r_osd_item, &req->r_osd->o_requests); + __unregister_linger_request(osdc, req); dout("requeued lingering %p tid %llu osd%d\n", req, req->r_tid, osd->o_osd); } @@ -798,7 +804,7 @@ static void __register_request(struct ceph_osd_client *osdc, req->r_request->hdr.tid = cpu_to_le64(req->r_tid); INIT_LIST_HEAD(&req->r_req_lru_item); - dout("register_request %p tid %lld\n", req, req->r_tid); + dout("__register_request %p tid %lld\n", req, req->r_tid); __insert_request(osdc, req); ceph_osdc_get_request(req); osdc->num_requests++; diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 9fea7553522..96bee5c4600 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -13,7 +13,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) { FILE *fp; char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1]; - char *token, *saved_ptr; + char *token, *saved_ptr = NULL; int found = 0; fp = fopen("/proc/mounts", "r"); |