summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
authorAndi Kleen <ak@linux.intel.com>2015-10-22 22:07:21 (GMT)
committerIngo Molnar <mingo@kernel.org>2015-11-23 08:58:25 (GMT)
commit75925e1ad7f5a4e867bd14ff8e7f114ea1596434 (patch)
treea526761994dbe3c9db832b7e61defd95755669e7 /arch/x86/kernel
parent10013ebb5d7856c243541870f4e62fed68253e88 (diff)
downloadlinux-75925e1ad7f5a4e867bd14ff8e7f114ea1596434.tar.xz
perf/x86: Optimize stack walk user accesses
Change the perf user stack walking to use the new __copy_from_user_nmi(), and split each access into word sized transfer sizes. This allows to inline the complete access and optimize it all into a single load. The main advantage is that this avoids the overhead of double page faults. When normal copy_from_user() fails it reexecutes the copy to compute an accurate number of non copied bytes. This leads to executing the expensive page fault twice. While walking stacks having a fault at some point is relatively common (typically when some part of the program isn't compiled with frame pointers), so this is a large overhead. With the optimized copies we avoid this problem because they only do all accesses once. And of course they're much faster too when the access does not fault because they're just single instructions instead of complex function calls. While profiling a kernel build with -g, the patch brings down the average time of the PMI handler from 966ns to 552ns (-43%). Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Link: http://lkml.kernel.org/r/1445551641-13379-2-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/cpu/perf_event.c22
1 files changed, 19 insertions, 3 deletions
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2bf79d7..9dfbba5 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2250,12 +2250,19 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
ss_base = get_segment_base(regs->ss);
fp = compat_ptr(ss_base + regs->bp);
+ pagefault_disable();
while (entry->nr < PERF_MAX_STACK_DEPTH) {
unsigned long bytes;
frame.next_frame = 0;
frame.return_address = 0;
- bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+ if (!access_ok(VERIFY_READ, fp, 8))
+ break;
+
+ bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
+ if (bytes != 0)
+ break;
+ bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4);
if (bytes != 0)
break;
@@ -2265,6 +2272,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
perf_callchain_store(entry, cs_base + frame.return_address);
fp = compat_ptr(ss_base + frame.next_frame);
}
+ pagefault_enable();
return 1;
}
#else
@@ -2302,12 +2310,19 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
if (perf_callchain_user32(regs, entry))
return;
+ pagefault_disable();
while (entry->nr < PERF_MAX_STACK_DEPTH) {
unsigned long bytes;
frame.next_frame = NULL;
frame.return_address = 0;
- bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+ if (!access_ok(VERIFY_READ, fp, 16))
+ break;
+
+ bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+ if (bytes != 0)
+ break;
+ bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
if (bytes != 0)
break;
@@ -2315,8 +2330,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
break;
perf_callchain_store(entry, frame.return_address);
- fp = frame.next_frame;
+ fp = (void __user *)frame.next_frame;
}
+ pagefault_enable();
}
/*