Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

36db171c · Linus Torvalds <[email protected]> · 2016-05-16 14:08:43 -07:00

Pull perf updates from Ingo Molnar:
 "Bigger kernel side changes:

   - Add backwards writing capability to the perf ring-buffer code,
     which is preparation for future advanced features like robust
     'overwrite support' and snapshot mode.  (Wang Nan)

   - Add pause and resume ioctls for the perf ringbuffer (Wang Nan)

   - x86 Intel cstate code cleanups and reorgnization (Thomas Gleixner)

   - x86 Intel uncore and CPU PMU driver updates (Kan Liang, Peter
     Zijlstra)

   - x86 AUX (Intel PT) related enhancements and updates (Alexander
     Shishkin)

   - x86 MSR PMU driver enhancements and updates (Huang Rui)

   - ... and lots of other changes spread out over 40+ commits.

  Biggest tooling side changes:

   - 'perf trace' features and enhancements.  (Arnaldo Carvalho de Melo)

   - BPF tooling updates (Wang Nan)

   - 'perf sched' updates (Jiri Olsa)

   - 'perf probe' updates (Masami Hiramatsu)

   - ... plus 200+ other enhancements, fixes and cleanups to tools/

  The merge commits, the shortlog and the changelogs contain a lot more
  details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (249 commits)
  perf/core: Disable the event on a truncated AUX record
  perf/x86/intel/pt: Generate PMI in the STOP region as well
  perf buildid-cache: Use lsdir() for looking up buildid caches
  perf symbols: Use lsdir() for the search in kcore cache directory
  perf tools: Use SBUILD_ID_SIZE where applicable
  perf tools: Fix lsdir to set errno correctly
  perf trace: Move seccomp args beautifiers to tools/perf/trace/beauty/
  perf trace: Move flock op beautifier to tools/perf/trace/beauty/
  perf build: Add build-test for debug-frame on arm/arm64
  perf build: Add build-test for libunwind cross-platforms support
  perf script: Fix export of callchains with recursion in db-export
  perf script: Fix callchain addresses in db-export
  perf script: Fix symbol insertion behavior in db-export
  perf symbols: Add dso__insert_symbol function
  perf scripting python: Use Py_FatalError instead of die()
  perf tools: Remove xrealloc and ALLOC_GROW
  perf help: Do not use ALLOC_GROW in add_cmd_list
  perf pmu: Make pmu_formats_string to check return value of strbuf
  perf header: Make topology checkers to check return value of strbuf
  perf tools: Make alias handler to check return value of strbuf
  ...

Commit: 36db171cc733bc7b8c628ef21831467d1919decd
Parents: 3469d261 · 3f56e687

Merge commit. Changes below are compared with the first parent: 3469d261.

Changes

217 files changed · +8328 −2731

File	Status	Add	Del	Content
Documentation/sysctl/kernel.txt	modified	+14	−0	View file
arch/arm/kernel/hw_breakpoint.c	modified	+2	−2	View file
arch/arm/kernel/perf_callchain.c	modified	+1	−1	View file
arch/arm64/kernel/hw_breakpoint.c	modified	+2	−2	View file
arch/arm64/kernel/perf_callchain.c	modified	+2	−2	View file
arch/metag/kernel/perf_callchain.c	modified	+1	−1	View file
arch/mips/kernel/perf_event.c	modified	+2	−2	View file
arch/powerpc/perf/callchain.c	modified	+2	−2	View file
arch/sparc/kernel/perf_event.c	modified	+3	−3	View file
arch/x86/Kconfig	modified	+2	−13	View file
arch/x86/events/Kconfig	added	+36	−0	View file
arch/x86/events/Makefile	modified	+3	−6	View file
arch/x86/events/amd/uncore.c	modified	+2	−0	View file
arch/x86/events/core.c	modified	+8	−2	View file
arch/x86/events/intel/Makefile	added	+9	−0	View file
arch/x86/events/intel/bts.c	modified	+48	−57	View file
arch/x86/events/intel/core.c	modified	+159	−1	View file
arch/x86/events/intel/cstate.c	modified	+256	−291	View file
arch/x86/events/intel/ds.c	modified	+6	−0	View file
arch/x86/events/intel/lbr.c	modified	+30	−1	View file
arch/x86/events/intel/pt.c	modified	+250	−68	View file
arch/x86/events/intel/pt.h	modified	+68	−0	View file
arch/x86/events/intel/rapl.c	modified	+141	−42	View file
arch/x86/events/intel/uncore.c	modified	+126	−90	View file
arch/x86/events/msr.c	modified	+26	−10	View file
arch/x86/events/perf_event.h	modified	+5	−0	View file
arch/x86/include/asm/cpufeatures.h	modified	+2	−0	View file
arch/x86/include/asm/msr-index.h	modified	+15	−20	View file
arch/x86/kernel/uprobes.c	modified	+2	−2	View file
arch/xtensa/kernel/perf_event.c	modified	+2	−2	View file
drivers/perf/arm_pmu.c	modified	+8	−0	View file
drivers/powercap/intel_rapl.c	modified	+69	−0	View file
include/linux/perf_event.h	modified	+135	−4	View file
include/uapi/linux/perf_event.h	modified	+3	−1	View file
kernel/bpf/stackmap.c	modified	+4	−4	View file
kernel/events/callchain.c	modified	+33	−2	View file
kernel/events/core.c	modified	+857	−54	View file
kernel/events/internal.h	modified	+9	−1	View file
kernel/events/ring_buffer.c	modified	+87	−31	View file
kernel/sysctl.c	modified	+12	−0	View file
kernel/trace/trace_event_perf.c	modified	+3	−0	View file
tools/Makefile	modified	+2	−1	View file
tools/build/Makefile.feature	modified	+7	−1	View file
tools/build/feature/Makefile	modified	+23	−0	View file
tools/build/feature/test-bpf.c	modified	+1	−2	View file
tools/build/feature/test-libunwind-aarch64.c	added	+26	−0	View file
tools/build/feature/test-libunwind-arm.c	added	+27	−0	View file
tools/build/feature/test-libunwind-debug-frame-aarch64.c	added	+16	−0	View file
tools/build/feature/test-libunwind-debug-frame-arm.c	added	+16	−0	View file
tools/build/feature/test-libunwind-x86.c	added	+27	−0	View file
tools/build/feature/test-libunwind-x86_64.c	added	+27	−0	View file
tools/lib/api/fs/fs.c	modified	+13	−0	View file
tools/lib/api/fs/fs.h	modified	+2	−0	View file
tools/perf/Documentation/intel-pt.txt	modified	+7	−0	View file
tools/perf/Documentation/itrace.txt	modified	+8	−0	View file
tools/perf/Documentation/perf-annotate.txt	modified	+1	−1	View file
tools/perf/Documentation/perf-diff.txt	modified	+1	−1	View file
tools/perf/Documentation/perf-list.txt	modified	+106	−1	View file
tools/perf/Documentation/perf-mem.txt	modified	+8	−0	View file
tools/perf/Documentation/perf-record.txt	modified	+13	−0	View file
tools/perf/Documentation/perf-report.txt	modified	+2	−2	View file
tools/perf/Documentation/perf-sched.txt	modified	+16	−0	View file
tools/perf/Documentation/perf-script.txt	modified	+14	−0	View file
tools/perf/Documentation/perf-top.txt	modified	+1	−1	View file
tools/perf/Documentation/perf-trace.txt	modified	+32	−0	View file
tools/perf/Makefile.perf	modified	+9	−6	View file
tools/perf/arch/powerpc/Makefile	modified	+1	−0	View file
tools/perf/arch/powerpc/util/dwarf-regs.c	modified	+28	−12	View file
tools/perf/arch/powerpc/util/sym-handling.c	modified	+32	−11	View file
tools/perf/arch/x86/Makefile	modified	+23	−0	View file
tools/perf/arch/x86/entry/syscalls/syscall_64.tbl	added	+376	−0	View file
tools/perf/arch/x86/entry/syscalls/syscalltbl.sh	added	+39	−0	View file
tools/perf/arch/x86/tests/perf-time-to-tsc.c	modified	+1	−1	View file
tools/perf/arch/x86/util/intel-bts.c	modified	+5	−0	View file
tools/perf/arch/x86/util/intel-pt.c	modified	+5	−0	View file
tools/perf/arch/x86/util/tsc.c	modified	+31	−1	View file
tools/perf/arch/x86/util/tsc.h	deleted	+0	−17	View before deletion
tools/perf/bench/futex-lock-pi.c	modified	+1	−1	View file
tools/perf/bench/futex.h	modified	+2	−4	View file
tools/perf/bench/mem-functions.c	modified	+15	−7	View file
tools/perf/builtin-config.c	modified	+32	−7	View file
tools/perf/builtin-diff.c	modified	+2	−2	View file
tools/perf/builtin-help.c	modified	+10	−8	View file
tools/perf/builtin-inject.c	modified	+1	−0	View file
tools/perf/builtin-kmem.c	modified	+1	−1	View file
tools/perf/builtin-kvm.c	modified	+1	−1	View file
tools/perf/builtin-mem.c	modified	+10	−1	View file
tools/perf/builtin-record.c	modified	+220	−47	View file
tools/perf/builtin-report.c	modified	+10	−9	View file
tools/perf/builtin-sched.c	modified	+186	−12	View file
tools/perf/builtin-script.c	modified	+35	−21	View file
tools/perf/builtin-stat.c	modified	+8	−0	View file
tools/perf/builtin-top.c	modified	+19	−20	View file
tools/perf/builtin-trace.c	modified	+416	−669	View file
tools/perf/config/Makefile	modified	+1	−4	View file
tools/perf/jvmti/jvmti_agent.c	modified	+41	−2	View file
tools/perf/perf.c	modified	+11	−5	View file
tools/perf/perf.h	modified	+0	−1	View file
tools/perf/scripts/python/export-to-postgresql.py	modified	+32	−20	View file
tools/perf/tests/Build	modified	+2	−0	View file
tools/perf/tests/backward-ring-buffer.c	added	+151	−0	View file
tools/perf/tests/bpf.c	modified	+1	−1	View file
tools/perf/tests/builtin-test.c	modified	+8	−0	View file
tools/perf/tests/code-reading.c	modified	+1	−1	View file
tools/perf/tests/dso-data.c	modified	+1	−1	View file
tools/perf/tests/event-times.c	added	+236	−0	View file
tools/perf/tests/event_update.c	modified	+1	−1	View file
tools/perf/tests/hists_common.c	modified	+1	−1	View file
tools/perf/tests/hists_cumulate.c	modified	+2	−2	View file
tools/perf/tests/hists_filter.c	modified	+1	−1	View file
tools/perf/tests/hists_link.c	modified	+2	−2	View file
tools/perf/tests/hists_output.c	modified	+2	−2	View file
tools/perf/tests/keep-tracking.c	modified	+1	−1	View file
tools/perf/tests/openat-syscall-tp-fields.c	modified	+1	−1	View file
tools/perf/tests/perf-record.c	modified	+1	−1	View file
tools/perf/tests/switch-tracking.c	modified	+1	−1	View file
tools/perf/tests/tests.h	modified	+2	−0	View file
tools/perf/tests/vmlinux-kallsyms.c	modified	+10	−1	View file
tools/perf/trace/beauty/eventfd.c	added	+38	−0	View file
tools/perf/trace/beauty/flock.c	added	+31	−0	View file
tools/perf/trace/beauty/futex_op.c	added	+44	−0	View file
tools/perf/trace/beauty/mmap.c	added	+158	−0	View file
tools/perf/trace/beauty/mode_t.c	added	+68	−0	View file
tools/perf/trace/beauty/msg_flags.c	added	+62	−0	View file
tools/perf/trace/beauty/open_flags.c	added	+56	−0	View file
tools/perf/trace/beauty/perf_event_open.c	added	+43	−0	View file
tools/perf/trace/beauty/pid.c	added	+21	−0	View file
tools/perf/trace/beauty/sched_policy.c	added	+44	−0	View file
tools/perf/trace/beauty/seccomp.c	added	+52	−0	View file
tools/perf/trace/beauty/signum.c	added	+53	−0	View file
tools/perf/trace/beauty/socket_type.c	added	+60	−0	View file
tools/perf/trace/beauty/waitid_options.c	added	+26	−0	View file
tools/perf/ui/browsers/hists.c	modified	+20	−20	View file
tools/perf/ui/gtk/hists.c	modified	+1	−1	View file
tools/perf/ui/hist.c	modified	+1	−1	View file
tools/perf/ui/stdio/hist.c	modified	+1	−2	View file
tools/perf/util/Build	modified	+5	−3	View file
tools/perf/util/annotate.c	modified	+2	−2	View file
tools/perf/util/auxtrace.c	modified	+7	−0	View file
tools/perf/util/auxtrace.h	modified	+2	−0	View file
tools/perf/util/bpf-loader.c	modified	+143	−0	View file
tools/perf/util/bpf-loader.h	modified	+19	−0	View file
tools/perf/util/build-id.c	modified	+7	−29	View file
tools/perf/util/cache.h	modified	+0	−19	View file
tools/perf/util/call-path.c	added	+122	−0	View file
tools/perf/util/call-path.h	added	+77	−0	View file
tools/perf/util/callchain.c	modified	+6	−3	View file
tools/perf/util/callchain.h	modified	+8	−1	View file
tools/perf/util/config.c	modified	+191	−31	View file
tools/perf/util/config.h	added	+26	−0	View file
tools/perf/util/cpumap.c	modified	+12	−0	View file
tools/perf/util/cpumap.h	modified	+2	−0	View file
tools/perf/util/data.c	modified	+41	−0	View file
tools/perf/util/data.h	modified	+10	−1	View file
tools/perf/util/db-export.c	modified	+87	−2	View file
tools/perf/util/db-export.h	modified	+3	−0	View file
tools/perf/util/dso.c	modified	+2	−2	View file
tools/perf/util/dwarf-aux.c	modified	+24	−28	View file
tools/perf/util/event.c	modified	+1	−0	View file
tools/perf/util/event.h	modified	+9	−0	View file
tools/perf/util/evlist.c	modified	+134	−40	View file
tools/perf/util/evlist.h	modified	+21	−1	View file
tools/perf/util/evsel.c	modified	+38	−101	View file
tools/perf/util/evsel.h	modified	+26	−2	View file
tools/perf/util/evsel_fprintf.c	added	+212	−0	View file
tools/perf/util/header.c	modified	+21	−12	View file
tools/perf/util/help-unknown-cmd.c	modified	+22	−8	View file
tools/perf/util/hist.c	modified	+13	−10	View file
tools/perf/util/hist.h	modified	+10	−2	View file
tools/perf/util/intel-bts.c	modified	+5	−0	View file
tools/perf/util/intel-pt-decoder/intel-pt-decoder.c	modified	+1	−1	View file
tools/perf/util/intel-pt.c	modified	+20	−2	View file
tools/perf/util/jitdump.c	modified	+34	−7	View file
tools/perf/util/jitdump.h	modified	+3	−0	View file
tools/perf/util/machine.c	modified	+73	−32	View file
tools/perf/util/machine.h	modified	+7	−0	View file
tools/perf/util/map.c	modified	+15	−1	View file
tools/perf/util/ordered-events.c	modified	+9	−0	View file
tools/perf/util/ordered-events.h	modified	+1	−0	View file
tools/perf/util/pmu.c	modified	+11	−12	View file
tools/perf/util/probe-event.c	modified	+215	−191	View file
tools/perf/util/probe-event.h	modified	+3	−2	View file
tools/perf/util/probe-file.c	modified	+1	−2	View file
tools/perf/util/probe-finder.c	modified	+21	−15	View file
tools/perf/util/python-ext-sources	modified	+1	−0	View file
tools/perf/util/quote.c	modified	+20	−16	View file
tools/perf/util/quote.h	modified	+1	−1	View file
tools/perf/util/rb_resort.h	added	+149	−0	View file
tools/perf/util/record.c	modified	+3	−2	View file
tools/perf/util/scripting-engines/trace-event-perl.c	modified	+118	−8	View file
tools/perf/util/scripting-engines/trace-event-python.c	modified	+41	−6	View file
tools/perf/util/session.c	modified	+13	−102	View file
tools/perf/util/session.h	modified	+1	−11	View file
tools/perf/util/sort.c	modified	+14	−21	View file
tools/perf/util/sort.h	modified	+0	−7	View file
tools/perf/util/stat.c	modified	+3	−1	View file
tools/perf/util/strbuf.c	modified	+67	−26	View file
tools/perf/util/strbuf.h	modified	+15	−10	View file
tools/perf/util/symbol-elf.c	modified	+7	−13	View file
tools/perf/util/symbol.c	modified	+37	−71	View file
tools/perf/util/symbol.h	modified	+18	−1	View file
tools/perf/util/symbol_fprintf.c	added	+71	−0	View file
tools/perf/util/syscalltbl.c	added	+134	−0	View file
tools/perf/util/syscalltbl.h	added	+20	−0	View file
tools/perf/util/thread-stack.c	modified	+1	−138	View file
tools/perf/util/thread-stack.h	modified	+10	−21	View file
tools/perf/util/thread.c	modified	+20	−1	View file
tools/perf/util/thread.h	modified	+8	−0	View file
tools/perf/util/thread_map.c	modified	+13	−1	View file
tools/perf/util/thread_map.h	modified	+3	−0	View file
tools/perf/util/tool.h	modified	+1	−0	View file
tools/perf/util/trigger.h	added	+94	−0	View file
tools/perf/util/tsc.h	modified	+20	−1	View file
tools/perf/util/unwind-libunwind.c	modified	+9	−16	View file
tools/perf/util/util.c	modified	+36	−2	View file
tools/perf/util/util.h	modified	+9	−6	View file
tools/perf/util/wrapper.c	deleted	+0	−29	View before deletion

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/sysctl/kernel.txt

View file

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index fcddfd5..daabdd7 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -60,6 +60,7 @@ show up in /proc/sys/kernel:
 - panic_on_warn
 - perf_cpu_time_max_percent
 - perf_event_paranoid
+- perf_event_max_stack
 - pid_max
 - powersave-nap               [ PPC only ]
 - printk
@@ -654,6 +655,19 @@ users (without CAP_SYS_ADMIN).  The default value is 2.
 
 ==============================================================
 
+perf_event_max_stack:
+
+Controls maximum number of stack frames to copy for (attr.sample_type &
+PERF_SAMPLE_CALLCHAIN) configured events, for instance, when using
+'perf record -g' or 'perf trace --call-graph fp'.
+
+This can only be done when no events are in use that have callchains
+enabled, otherwise writing to this file will return -EBUSY.
+
+The default value is 127.
+
+==============================================================
+
 pid_max:
 
 PID allocation wrap value.  When the kernel's next PID value

arch/arm/kernel/hw_breakpoint.c

View file

diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 6284779..b8df458 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -631,7 +631,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	info->address &= ~alignment_mask;
 	info->ctrl.len <<= offset;
 
-	if (!bp->overflow_handler) {
+	if (is_default_overflow_handler(bp)) {
 		/*
 		 * Mismatch breakpoints are required for single-stepping
 		 * breakpoints.
@@ -754,7 +754,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 		 * mismatch breakpoint so we can single-step over the
 		 * watchpoint trigger.
 		 */
-		if (!wp->overflow_handler)
+		if (is_default_overflow_handler(wp))
 			enable_single_step(wp, instruction_pointer(regs));
 
 unlock:

arch/arm/kernel/perf_callchain.c

View file

diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
index 4e02ae5..27563be 100644
--- a/arch/arm/kernel/perf_callchain.c
+++ b/arch/arm/kernel/perf_callchain.c
@@ -75,7 +75,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
 
-	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+	while ((entry->nr < sysctl_perf_event_max_stack) &&
 	       tail && !((unsigned long)tail & 0x3))
 		tail = user_backtrace(tail, entry);
 }

arch/arm64/kernel/hw_breakpoint.c

View file

diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index b45c95d..4ef5373 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -616,7 +616,7 @@ static int breakpoint_handler(unsigned long unused, unsigned int esr,
 		perf_bp_event(bp, regs);
 
 		/* Do we need to handle the stepping? */
-		if (!bp->overflow_handler)
+		if (is_default_overflow_handler(bp))
 			step = 1;
 unlock:
 		rcu_read_unlock();
@@ -712,7 +712,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 		perf_bp_event(wp, regs);
 
 		/* Do we need to handle the stepping? */
-		if (!wp->overflow_handler)
+		if (is_default_overflow_handler(wp))
 			step = 1;
 
 unlock:

arch/arm64/kernel/perf_callchain.c

View file

diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index ff46654..32c3c6e 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -122,7 +122,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 
 		tail = (struct frame_tail __user *)regs->regs[29];
 
-		while (entry->nr < PERF_MAX_STACK_DEPTH &&
+		while (entry->nr < sysctl_perf_event_max_stack &&
 		       tail && !((unsigned long)tail & 0xf))
 			tail = user_backtrace(tail, entry);
 	} else {
@@ -132,7 +132,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 
 		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
 
-		while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+		while ((entry->nr < sysctl_perf_event_max_stack) &&
 			tail && !((unsigned long)tail & 0x3))
 			tail = compat_user_backtrace(tail, entry);
 #endif

arch/metag/kernel/perf_callchain.c

View file

diff --git a/arch/metag/kernel/perf_callchain.c b/arch/metag/kernel/perf_callchain.c
index 3156334..252abc1 100644
--- a/arch/metag/kernel/perf_callchain.c
+++ b/arch/metag/kernel/perf_callchain.c
@@ -65,7 +65,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	--frame;
 
-	while ((entry->nr < PERF_MAX_STACK_DEPTH) && frame)
+	while ((entry->nr < sysctl_perf_event_max_stack) && frame)
 		frame = user_backtrace(frame, entry);
 }
 

arch/mips/kernel/perf_event.c

View file

diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c
index c1cf9c6..5021c54 100644
--- a/arch/mips/kernel/perf_event.c
+++ b/arch/mips/kernel/perf_event.c
@@ -35,7 +35,7 @@ static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
 		addr = *sp++;
 		if (__kernel_text_address(addr)) {
 			perf_callchain_store(entry, addr);
-			if (entry->nr >= PERF_MAX_STACK_DEPTH)
+			if (entry->nr >= sysctl_perf_event_max_stack)
 				break;
 		}
 	}
@@ -59,7 +59,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 	}
 	do {
 		perf_callchain_store(entry, pc);
-		if (entry->nr >= PERF_MAX_STACK_DEPTH)
+		if (entry->nr >= sysctl_perf_event_max_stack)
 			break;
 		pc = unwind_stack(current, &sp, pc, &ra);
 	} while (pc);

arch/powerpc/perf/callchain.c

View file

diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index e04a675..22d9015 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -247,7 +247,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
 
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_max_stack) {
 		fp = (unsigned long __user *) sp;
 		if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
 			return;
@@ -453,7 +453,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
 
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_max_stack) {
 		fp = (unsigned int __user *) (unsigned long) sp;
 		if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
 			return;

arch/sparc/kernel/perf_event.c

View file

diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 6596f66..a4b8b5a 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1756,7 +1756,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			}
 		}
 #endif
-	} while (entry->nr < PERF_MAX_STACK_DEPTH);
+	} while (entry->nr < sysctl_perf_event_max_stack);
 }
 
 static inline int
@@ -1790,7 +1790,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 		pc = sf.callers_pc;
 		ufp = (unsigned long)sf.fp + STACK_BIAS;
 		perf_callchain_store(entry, pc);
-	} while (entry->nr < PERF_MAX_STACK_DEPTH);
+	} while (entry->nr < sysctl_perf_event_max_stack);
 }
 
 static void perf_callchain_user_32(struct perf_callchain_entry *entry,
@@ -1822,7 +1822,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 			ufp = (unsigned long)sf.fp;
 		}
 		perf_callchain_store(entry, pc);
-	} while (entry->nr < PERF_MAX_STACK_DEPTH);
+	} while (entry->nr < sysctl_perf_event_max_stack);
 }
 
 void

arch/x86/Kconfig

View file

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2dc1860..a494fa3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -164,10 +164,6 @@ config INSTRUCTION_DECODER
 	def_bool y
 	depends on KPROBES || PERF_EVENTS || UPROBES
 
-config PERF_EVENTS_INTEL_UNCORE
-	def_bool y
-	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
-
 config OUTPUT_FORMAT
 	string
 	default "elf32-i386" if X86_32
@@ -1046,6 +1042,8 @@ config X86_THERMAL_VECTOR
 	def_bool y
 	depends on X86_MCE_INTEL
 
+source "arch/x86/events/Kconfig"
+
 config X86_LEGACY_VM86
 	bool "Legacy VM86 support"
 	default n
@@ -1210,15 +1208,6 @@ config MICROCODE_OLD_INTERFACE
 	def_bool y
 	depends on MICROCODE
 
-config PERF_EVENTS_AMD_POWER
-	depends on PERF_EVENTS && CPU_SUP_AMD
-	tristate "AMD Processor Power Reporting Mechanism"
-	---help---
-	  Provide power reporting mechanism support for AMD processors.
-	  Currently, it leverages X86_FEATURE_ACC_POWER
-	  (CPUID Fn8000_0007_EDX[12]) interface to calculate the
-	  average power consumption on Family 15h processors.
-
 config X86_MSR
 	tristate "/dev/cpu/*/msr - Model-specific register support"
 	---help---

arch/x86/events/Kconfig

View file

diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig
new file mode 100644
index 0000000..98397db
--- /dev/null
+++ b/arch/x86/events/Kconfig
@@ -0,0 +1,36 @@
+menu "Performance monitoring"
+
+config PERF_EVENTS_INTEL_UNCORE
+	tristate "Intel uncore performance events"
+	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+	default y
+	---help---
+	Include support for Intel uncore performance events. These are
+	available on NehalemEX and more modern processors.
+
+config PERF_EVENTS_INTEL_RAPL
+	tristate "Intel rapl performance events"
+	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+	default y
+	---help---
+	Include support for Intel rapl performance events for power
+	monitoring on modern processors.
+
+config PERF_EVENTS_INTEL_CSTATE
+	tristate "Intel cstate performance events"
+	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+	default y
+	---help---
+	Include support for Intel cstate performance events for power
+	monitoring on modern processors.
+
+config PERF_EVENTS_AMD_POWER
+	depends on PERF_EVENTS && CPU_SUP_AMD
+	tristate "AMD Processor Power Reporting Mechanism"
+	---help---
+	  Provide power reporting mechanism support for AMD processors.
+	  Currently, it leverages X86_FEATURE_ACC_POWER
+	  (CPUID Fn8000_0007_EDX[12]) interface to calculate the
+	  average power consumption on Family 15h processors.
+
+endmenu

arch/x86/events/Makefile

View file

diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index f59618a..1d392c3 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -6,9 +6,6 @@ obj-$(CONFIG_X86_LOCAL_APIC)            += amd/ibs.o msr.o
 ifdef CONFIG_AMD_IOMMU
 obj-$(CONFIG_CPU_SUP_AMD)               += amd/iommu.o
 endif
-obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/core.o intel/bts.o intel/cqm.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/cstate.o intel/ds.o intel/knc.o 
-obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/lbr.o intel/p4.o intel/p6.o intel/pt.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/rapl.o msr.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel/uncore.o intel/uncore_nhmex.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel/uncore_snb.o intel/uncore_snbep.o
+
+obj-$(CONFIG_CPU_SUP_INTEL)		+= msr.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/

arch/x86/events/amd/uncore.c

View file

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 3db9569..98ac573 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -263,6 +263,7 @@ static const struct attribute_group *amd_uncore_attr_groups[] = {
 };
 
 static struct pmu amd_nb_pmu = {
+	.task_ctx_nr	= perf_invalid_context,
 	.attr_groups	= amd_uncore_attr_groups,
 	.name		= "amd_nb",
 	.event_init	= amd_uncore_event_init,
@@ -274,6 +275,7 @@ static struct pmu amd_nb_pmu = {
 };
 
 static struct pmu amd_l2_pmu = {
+	.task_ctx_nr	= perf_invalid_context,
 	.attr_groups	= amd_uncore_attr_groups,
 	.name		= "amd_l2",
 	.event_init	= amd_uncore_event_init,

arch/x86/events/core.c

View file

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 041e442..5e5e76a 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -360,6 +360,9 @@ int x86_add_exclusive(unsigned int what)
 {
 	int i;
 
+	if (x86_pmu.lbr_pt_coexist)
+		return 0;
+
 	if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
 		mutex_lock(&pmc_reserve_mutex);
 		for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
@@ -380,6 +383,9 @@ fail_unlock:
 
 void x86_del_exclusive(unsigned int what)
 {
+	if (x86_pmu.lbr_pt_coexist)
+		return;
+
 	atomic_dec(&x86_pmu.lbr_exclusive[what]);
 	atomic_dec(&active_events);
 }
@@ -2277,7 +2283,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 
 	fp = compat_ptr(ss_base + regs->bp);
 	pagefault_disable();
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_max_stack) {
 		unsigned long bytes;
 		frame.next_frame     = 0;
 		frame.return_address = 0;
@@ -2337,7 +2343,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		return;
 
 	pagefault_disable();
-	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+	while (entry->nr < sysctl_perf_event_max_stack) {
 		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;

arch/x86/events/intel/Makefile

View file

diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile
new file mode 100644
index 0000000..3660b2c
--- /dev/null
+++ b/arch/x86/events/intel/Makefile
@@ -0,0 +1,9 @@
+obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o cqm.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl.o
+intel-rapl-objs				:= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
+intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o
+intel-cstate-objs			:= cstate.o

arch/x86/events/intel/bts.c

View file

diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index b99dc92..0a6e393 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -171,18 +171,6 @@ static void bts_buffer_pad_out(struct bts_phys *phys, unsigned long head)
 	memset(page_address(phys->page) + index, 0, phys->size - index);
 }
 
-static bool bts_buffer_is_full(struct bts_buffer *buf, struct bts_ctx *bts)
-{
-	if (buf->snapshot)
-		return false;
-
-	if (local_read(&buf->data_size) >= bts->handle.size ||
-	    bts->handle.size - local_read(&buf->data_size) < BTS_RECORD_SIZE)
-		return true;
-
-	return false;
-}
-
 static void bts_update(struct bts_ctx *bts)
 {
 	int cpu = raw_smp_processor_id();
@@ -213,18 +201,15 @@ static void bts_update(struct bts_ctx *bts)
 	}
 }
 
+static int
+bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
+
 static void __bts_event_start(struct perf_event *event)
 {
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 	struct bts_buffer *buf = perf_get_aux(&bts->handle);
 	u64 config = 0;
 
-	if (!buf || bts_buffer_is_full(buf, bts))
-		return;
-
-	event->hw.itrace_started = 1;
-	event->hw.state = 0;
-
 	if (!buf->snapshot)
 		config |= ARCH_PERFMON_EVENTSEL_INT;
 	if (!event->attr.exclude_kernel)
@@ -241,16 +226,41 @@ static void __bts_event_start(struct perf_event *event)
 	wmb();
 
 	intel_pmu_enable_bts(config);
+
 }
 
 static void bts_event_start(struct perf_event *event, int flags)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_buffer *buf;
+
+	buf = perf_aux_output_begin(&bts->handle, event);
+	if (!buf)
+		goto fail_stop;
+
+	if (bts_buffer_reset(buf, &bts->handle))
+		goto fail_end_stop;
+
+	bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base;
+	bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum;
+	bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold;
+
+	event->hw.itrace_started = 1;
+	event->hw.state = 0;
 
 	__bts_event_start(event);
 
 	/* PMI handler: this counter is running and likely generating PMIs */
 	ACCESS_ONCE(bts->started) = 1;
+
+	return;
+
+fail_end_stop:
+	perf_aux_output_end(&bts->handle, 0, false);
+
+fail_stop:
+	event->hw.state = PERF_HES_STOPPED;
 }
 
 static void __bts_event_stop(struct perf_event *event)
@@ -269,15 +279,32 @@ static void __bts_event_stop(struct perf_event *event)
 
 static void bts_event_stop(struct perf_event *event, int flags)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_buffer *buf = perf_get_aux(&bts->handle);
 
 	/* PMI handler: don't restart this counter */
 	ACCESS_ONCE(bts->started) = 0;
 
 	__bts_event_stop(event);
 
-	if (flags & PERF_EF_UPDATE)
+	if (flags & PERF_EF_UPDATE) {
 		bts_update(bts);
+
+		if (buf) {
+			if (buf->snapshot)
+				bts->handle.head =
+					local_xchg(&buf->data_size,
+						   buf->nr_pages << PAGE_SHIFT);
+			perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
+					    !!local_xchg(&buf->lost, 0));
+		}
+
+		cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
+		cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base;
+		cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum;
+		cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold;
+	}
 }
 
 void intel_bts_enable_local(void)
@@ -417,34 +444,14 @@ int intel_bts_interrupt(void)
 
 static void bts_event_del(struct perf_event *event, int mode)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct bts_buffer *buf = perf_get_aux(&bts->handle);
-
 	bts_event_stop(event, PERF_EF_UPDATE);
-
-	if (buf) {
-		if (buf->snapshot)
-			bts->handle.head =
-				local_xchg(&buf->data_size,
-					   buf->nr_pages << PAGE_SHIFT);
-		perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
-				    !!local_xchg(&buf->lost, 0));
-	}
-
-	cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
-	cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base;
-	cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum;
-	cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold;
 }
 
 static int bts_event_add(struct perf_event *event, int mode)
 {
-	struct bts_buffer *buf;
 	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	int ret = -EBUSY;
 
 	event->hw.state = PERF_HES_STOPPED;
 
@@ -454,26 +461,10 @@ static int bts_event_add(struct perf_event *event, int mode)
 	if (bts->handle.event)
 		return -EBUSY;
 
-	buf = perf_aux_output_begin(&bts->handle, event);
-	if (!buf)
-		return -EINVAL;
-
-	ret = bts_buffer_reset(buf, &bts->handle);
-	if (ret) {
-		perf_aux_output_end(&bts->handle, 0, false);
-		return ret;
-	}
-
-	bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base;
-	bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum;
-	bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold;
-
 	if (mode & PERF_EF_START) {
 		bts_event_start(event, 0);
-		if (hwc->state & PERF_HES_STOPPED) {
-			bts_event_del(event, 0);
-			return -EBUSY;
-		}
+		if (hwc->state & PERF_HES_STOPPED)
+			return -EINVAL;
 	}
 
 	return 0;

arch/x86/events/intel/core.c

View file

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 5210eaa..7c66695 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1465,6 +1465,140 @@ static __initconst const u64 slm_hw_cache_event_ids
  },
 };
 
+static struct extra_reg intel_glm_extra_regs[] __read_mostly = {
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x760005ffbfull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x360005ffbfull, RSP_1),
+	EVENT_EXTRA_END
+};
+
+#define GLM_DEMAND_DATA_RD		BIT_ULL(0)
+#define GLM_DEMAND_RFO			BIT_ULL(1)
+#define GLM_ANY_RESPONSE		BIT_ULL(16)
+#define GLM_SNP_NONE_OR_MISS		BIT_ULL(33)
+#define GLM_DEMAND_READ			GLM_DEMAND_DATA_RD
+#define GLM_DEMAND_WRITE		GLM_DEMAND_RFO
+#define GLM_DEMAND_PREFETCH		(SNB_PF_DATA_RD|SNB_PF_RFO)
+#define GLM_LLC_ACCESS			GLM_ANY_RESPONSE
+#define GLM_SNP_ANY			(GLM_SNP_NONE_OR_MISS|SNB_NO_FWD|SNB_HITM)
+#define GLM_LLC_MISS			(GLM_SNP_ANY|SNB_NON_DRAM)
+
+static __initconst const u64 glm_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= 0x81d0,	/* MEM_UOPS_RETIRED.ALL_LOADS */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= 0x82d0,	/* MEM_UOPS_RETIRED.ALL_STORES */
+			[C(RESULT_MISS)]	= 0x0,
+		},
+		[C(OP_PREFETCH)] = {