diff options
85 files changed, 10397 insertions, 112 deletions
diff --git a/Documentation/tracers/mmiotrace.txt b/Documentation/tracers/mmiotrace.txt new file mode 100644 index 00000000000..a4afb560a45 --- /dev/null +++ b/Documentation/tracers/mmiotrace.txt @@ -0,0 +1,164 @@ + In-kernel memory-mapped I/O tracing + + +Home page and links to optional user space tools: + + http://nouveau.freedesktop.org/wiki/MmioTrace + +MMIO tracing was originally developed by Intel around 2003 for their Fault +Injection Test Harness. In Dec 2006 - Jan 2007, using the code from Intel, +Jeff Muizelaar created a tool for tracing MMIO accesses with the Nouveau +project in mind. Since then many people have contributed. + +Mmiotrace was built for reverse engineering any memory-mapped IO device with +the Nouveau project as the first real user. Only x86 and x86_64 architectures +are supported. + +Out-of-tree mmiotrace was originally modified for mainline inclusion and +ftrace framework by Pekka Paalanen <pq@iki.fi>. + + +Preparation +----------- + +Mmiotrace feature is compiled in by the CONFIG_MMIOTRACE option. Tracing is +disabled by default, so it is safe to have this set to yes. SMP systems are +supported, but tracing is unreliable and may miss events if more than one CPU +is on-line, therefore mmiotrace takes all but one CPU off-line during run-time +activation. You can re-enable CPUs by hand, but you have been warned, there +is no way to automatically detect if you are losing events due to CPUs racing. + + +Usage Quick Reference +--------------------- + +$ mount -t debugfs debugfs /debug +$ echo mmiotrace > /debug/tracing/current_tracer +$ cat /debug/tracing/trace_pipe > mydump.txt & +Start X or whatever. +$ echo "X is up" > /debug/tracing/marker +$ echo none > /debug/tracing/current_tracer +Check for lost events. + + +Usage +----- + +Make sure debugfs is mounted to /debug. If not, (requires root privileges) +$ mount -t debugfs debugfs /debug + +Check that the driver you are about to trace is not loaded. + +Activate mmiotrace (requires root privileges): +$ echo mmiotrace > /debug/tracing/current_tracer + +Start storing the trace: +$ cat /debug/tracing/trace_pipe > mydump.txt & +The 'cat' process should stay running (sleeping) in the background. + +Load the driver you want to trace and use it. Mmiotrace will only catch MMIO +accesses to areas that are ioremapped while mmiotrace is active. + +[Unimplemented feature:] +During tracing you can place comments (markers) into the trace by +$ echo "X is up" > /debug/tracing/marker +This makes it easier to see which part of the (huge) trace corresponds to +which action. It is recommended to place descriptive markers about what you +do. + +Shut down mmiotrace (requires root privileges): +$ echo none > /debug/tracing/current_tracer +The 'cat' process exits. If it does not, kill it by issuing 'fg' command and +pressing ctrl+c. + +Check that mmiotrace did not lose events due to a buffer filling up. Either +$ grep -i lost mydump.txt +which tells you exactly how many events were lost, or use +$ dmesg +to view your kernel log and look for "mmiotrace has lost events" warning. If +events were lost, the trace is incomplete. You should enlarge the buffers and +try again. Buffers are enlarged by first seeing how large the current buffers +are: +$ cat /debug/tracing/trace_entries +gives you a number. Approximately double this number and write it back, for +instance: +$ echo 128000 > /debug/tracing/trace_entries +Then start again from the top. + +If you are doing a trace for a driver project, e.g. Nouveau, you should also +do the following before sending your results: +$ lspci -vvv > lspci.txt +$ dmesg > dmesg.txt +$ tar zcf pciid-nick-mmiotrace.tar.gz mydump.txt lspci.txt dmesg.txt +and then send the .tar.gz file. The trace compresses considerably. Replace +"pciid" and "nick" with the PCI ID or model name of your piece of hardware +under investigation and your nick name. + + +How Mmiotrace Works +------------------- + +Access to hardware IO-memory is gained by mapping addresses from PCI bus by +calling one of the ioremap_*() functions. Mmiotrace is hooked into the +__ioremap() function and gets called whenever a mapping is created. Mapping is +an event that is recorded into the trace log. Note, that ISA range mappings +are not caught, since the mapping always exists and is returned directly. + +MMIO accesses are recorded via page faults. Just before __ioremap() returns, +the mapped pages are marked as not present. Any access to the pages causes a +fault. The page fault handler calls mmiotrace to handle the fault. Mmiotrace +marks the page present, sets TF flag to achieve single stepping and exits the +fault handler. The instruction that faulted is executed and debug trap is +entered. Here mmiotrace again marks the page as not present. The instruction +is decoded to get the type of operation (read/write), data width and the value +read or written. These are stored to the trace log. + +Setting the page present in the page fault handler has a race condition on SMP +machines. During the single stepping other CPUs may run freely on that page +and events can be missed without a notice. Re-enabling other CPUs during +tracing is discouraged. + + +Trace Log Format +---------------- + +The raw log is text and easily filtered with e.g. grep and awk. One record is +one line in the log. A record starts with a keyword, followed by keyword +dependant arguments. Arguments are separated by a space, or continue until the +end of line. The format for version 20070824 is as follows: + +Explanation Keyword Space separated arguments +--------------------------------------------------------------------------- + +read event R width, timestamp, map id, physical, value, PC, PID +write event W width, timestamp, map id, physical, value, PC, PID +ioremap event MAP timestamp, map id, physical, virtual, length, PC, PID +iounmap event UNMAP timestamp, map id, PC, PID +marker MARK timestamp, text +version VERSION the string "20070824" +info for reader LSPCI one line from lspci -v +PCI address map PCIDEV space separated /proc/bus/pci/devices data +unk. opcode UNKNOWN timestamp, map id, physical, data, PC, PID + +Timestamp is in seconds with decimals. Physical is a PCI bus address, virtual +is a kernel virtual address. Width is the data width in bytes and value is the +data value. Map id is an arbitrary id number identifying the mapping that was +used in an operation. PC is the program counter and PID is process id. PC is +zero if it is not recorded. PID is always zero as tracing MMIO accesses +originating in user space memory is not yet supported. + +For instance, the following awk filter will pass all 32-bit writes that target +physical addresses in the range [0xfb73ce40, 0xfb800000[ + +$ awk '/W 4 / { adr=strtonum($5); if (adr >= 0xfb73ce40 && +adr < 0xfb800000) print; }' + + +Tools for Developers +-------------------- + +The user space tools include utilities for: +- replacing numeric addresses and values with hardware register names +- replaying MMIO logs, i.e., re-executing the recorded writes + + @@ -528,6 +528,10 @@ KBUILD_CFLAGS += -g KBUILD_AFLAGS += -gdwarf-2 endif +ifdef CONFIG_FTRACE +KBUILD_CFLAGS += -pg +endif + # We trigger additional mismatches with less inlining ifdef CONFIG_DEBUG_SECTION_MISMATCH KBUILD_CFLAGS += $(call cc-option, -fno-inline-functions-called-once) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3934e265940..a5e9912e2d3 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -105,11 +105,13 @@ config ARCH_NO_VIRT_TO_BUS config PPC bool default y + select HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE select HAVE_IDE - select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_LMB + select HAVE_OPROFILE config EARLY_PRINTK bool diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 2346d271fbf..f3f5e264143 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -12,6 +12,18 @@ CFLAGS_prom_init.o += -fPIC CFLAGS_btext.o += -fPIC endif +ifdef CONFIG_FTRACE +# Do not trace early boot code +CFLAGS_REMOVE_cputable.o = -pg +CFLAGS_REMOVE_prom_init.o = -pg + +ifdef CONFIG_DYNAMIC_FTRACE +# dynamic ftrace setup. +CFLAGS_REMOVE_ftrace.o = -pg +endif + +endif + obj-y := cputable.o ptrace.o syscalls.o \ irq.o align.o signal_32.o pmc.o vdso.o \ init_task.o process.o systbl.o idle.o \ @@ -78,6 +90,8 @@ obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o + obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o ifneq ($(CONFIG_PPC_INDIRECT_IO),y) diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 0c8614d9875..0e6221889ca 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -1035,3 +1035,133 @@ machine_check_in_rtas: /* XXX load up BATs and panic */ #endif /* CONFIG_PPC_RTAS */ + +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE +_GLOBAL(mcount) +_GLOBAL(_mcount) + stwu r1,-48(r1) + stw r3, 12(r1) + stw r4, 16(r1) + stw r5, 20(r1) + stw r6, 24(r1) + mflr r3 + stw r7, 28(r1) + mfcr r5 + stw r8, 32(r1) + stw r9, 36(r1) + stw r10,40(r1) + stw r3, 44(r1) + stw r5, 8(r1) + .globl mcount_call +mcount_call: + bl ftrace_stub + nop + lwz r6, 8(r1) + lwz r0, 44(r1) + lwz r3, 12(r1) + mtctr r0 + lwz r4, 16(r1) + mtcr r6 + lwz r5, 20(r1) + lwz r6, 24(r1) + lwz r0, 52(r1) + lwz r7, 28(r1) + lwz r8, 32(r1) + mtlr r0 + lwz r9, 36(r1) + lwz r10,40(r1) + addi r1, r1, 48 + bctr + +_GLOBAL(ftrace_caller) + /* Based off of objdump optput from glibc */ + stwu r1,-48(r1) + stw r3, 12(r1) + stw r4, 16(r1) + stw r5, 20(r1) + stw r6, 24(r1) + mflr r3 + lwz r4, 52(r1) + mfcr r5 + stw r7, 28(r1) + stw r8, 32(r1) + stw r9, 36(r1) + stw r10,40(r1) + stw r3, 44(r1) + stw r5, 8(r1) +.globl ftrace_call +ftrace_call: + bl ftrace_stub + nop + lwz r6, 8(r1) + lwz r0, 44(r1) + lwz r3, 12(r1) + mtctr r0 + lwz r4, 16(r1) + mtcr r6 + lwz r5, 20(r1) + lwz r6, 24(r1) + lwz r0, 52(r1) + lwz r7, 28(r1) + lwz r8, 32(r1) + mtlr r0 + lwz r9, 36(r1) + lwz r10,40(r1) + addi r1, r1, 48 + bctr +#else +_GLOBAL(mcount) +_GLOBAL(_mcount) + stwu r1,-48(r1) + stw r3, 12(r1) + stw r4, 16(r1) + stw r5, 20(r1) + stw r6, 24(r1) + mflr r3 + lwz r4, 52(r1) + mfcr r5 + stw r7, 28(r1) + stw r8, 32(r1) + stw r9, 36(r1) + stw r10,40(r1) + stw r3, 44(r1) + stw r5, 8(r1) + + LOAD_REG_ADDR(r5, ftrace_trace_function) +#if 0 + mtctr r3 + mr r1, r5 + bctrl +#endif + lwz r5,0(r5) +#if 1 + mtctr r5 + bctrl +#else + bl ftrace_stub +#endif + nop + + lwz r6, 8(r1) + lwz r0, 44(r1) + lwz r3, 12(r1) + mtctr r0 + lwz r4, 16(r1) + mtcr r6 + lwz r5, 20(r1) + lwz r6, 24(r1) + lwz r0, 52(r1) + lwz r7, 28(r1) + lwz r8, 32(r1) + mtlr r0 + lwz r9, 36(r1) + lwz r10,40(r1) + addi r1, r1, 48 + bctr +#endif + +_GLOBAL(ftrace_stub) + blr + +#endif /* CONFIG_MCOUNT */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index c0db5b769e5..2c4d9e056ea 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -870,3 +870,65 @@ _GLOBAL(enter_prom) ld r0,16(r1) mtlr r0 blr + +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE +_GLOBAL(mcount) +_GLOBAL(_mcount) + /* Taken from output of objdump from lib64/glibc */ + mflr r3 + stdu r1, -112(r1) + std r3, 128(r1) + .globl mcount_call |