From 9eff26ea48bfbe2885b158742a7512a097ec911b Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 18 Mar 2010 16:05:13 +1100 Subject: powerpc/perf_events: Fix call-graph recording, add perf_arch_fetch_caller_regs This implements a powerpc version of perf_arch_fetch_caller_regs to get correct call-graphs. It's implemented in assembly because that way we can be sure there isn't a stack frame for perf_arch_fetch_caller_regs. If it was in C, gcc might or might not create a stack frame for it, which would affect the number of levels we have to skip. With this, we see results from perf record -e lock:lock_acquire like this: # Samples: 24878 # # Overhead Command Shared Object Symbol # ........ .............. ................. ...... # 14.99% perf [kernel.kallsyms] [k] ._raw_spin_lock | --- ._raw_spin_lock | |--25.00%-- .alloc_fd | (nil) | | | |--50.00%-- .anon_inode_getfd | | .sys_perf_event_open | | syscall_exit | | syscall | | create_counter | | __cmd_record | | run_builtin | | main | | 0xfd2e704 | | 0xfd2e8c0 | | (nil) ... etc. Signed-off-by: Paul Mackerras Acked-by: Benjamin Herrenschmidt Cc: anton@samba.org Cc: linuxppc-dev@ozlabs.org Cc: Peter Zijlstra Cc: Frederic Weisbecker LKML-Reference: <20100318050513.GA6575@drongo> Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/misc.S | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'arch/powerpc/kernel/misc.S') diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 2d29752cbe16..b485a87c94e1 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -127,3 +127,31 @@ _GLOBAL(__setup_cpu_power7) _GLOBAL(__restore_cpu_power7) /* place holder */ blr + +#ifdef CONFIG_EVENT_TRACING +/* + * Get a minimal set of registers for our caller's nth caller. + * r3 = regs pointer, r5 = n. + * + * We only get R1 (stack pointer), NIP (next instruction pointer) + * and LR (link register). These are all we can get in the + * general case without doing complicated stack unwinding, but + * fortunately they are enough to do a stack backtrace, which + * is all we need them for. + */ +_GLOBAL(perf_arch_fetch_caller_regs) + mr r6,r1 + cmpwi r5,0 + mflr r4 + ble 2f + mtctr r5 +1: PPC_LL r6,0(r6) + bdnz 1b + PPC_LL r4,PPC_LR_STKOFF(r6) +2: PPC_LL r7,0(r6) + PPC_LL r7,PPC_LR_STKOFF(r7) + PPC_STL r6,GPR1-STACK_FRAME_OVERHEAD(r3) + PPC_STL r4,_NIP-STACK_FRAME_OVERHEAD(r3) + PPC_STL r7,_LINK-STACK_FRAME_OVERHEAD(r3) + blr +#endif /* CONFIG_EVENT_TRACING */ -- cgit v1.2.3 From 6e03bb5ad363fdbe4e1e227cfb78f7978c662e18 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 3 Apr 2010 12:22:05 +0200 Subject: perf: Always build the powerpc perf_arch_fetch_caller_regs version Now that software events use perf_arch_fetch_caller_regs() too, we need the powerpc version to be always built. Fixes the following build error: (.text+0x3210): undefined reference to `perf_arch_fetch_caller_regs' (.text+0x3324): undefined reference to `perf_arch_fetch_caller_regs' (.text+0x33bc): undefined reference to `perf_arch_fetch_caller_regs' (.text+0x33ec): undefined reference to `perf_arch_fetch_caller_regs' (.text+0xd4a0): undefined reference to `perf_arch_fetch_caller_regs' arch/powerpc/kernel/built-in.o:(.text+0xd528): more undefined references to `perf_arch_fetch_caller_regs' follow make[1]: *** [.tmp_vmlinux1] Error 1 make: *** [sub-make] Error 2 Reported-by: Michael Ellerman Reported-by: Ingo Molnar Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras --- arch/powerpc/kernel/misc.S | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/powerpc/kernel/misc.S') diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index b485a87c94e1..22e507c8a556 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -128,7 +128,6 @@ _GLOBAL(__restore_cpu_power7) /* place holder */ blr -#ifdef CONFIG_EVENT_TRACING /* * Get a minimal set of registers for our caller's nth caller. * r3 = regs pointer, r5 = n. @@ -154,4 +153,3 @@ _GLOBAL(perf_arch_fetch_caller_regs) PPC_STL r4,_NIP-STACK_FRAME_OVERHEAD(r3) PPC_STL r7,_LINK-STACK_FRAME_OVERHEAD(r3) blr -#endif /* CONFIG_EVENT_TRACING */ -- cgit v1.2.3