Merge tag 'perf-urgent-2020-03-15' of git://git.kernel.org/pub/scm/li…

…nux/kernel/git/tip/tip

Pull perf fixes from Thomas Gleixner:
 "A pile of perf fixes:

  Kernel side:

   - AMD uncore driver: Replace the open coded sanity check with the
     core variant, which provides the correct error code and also leaves
     a hint in dmesg

  Tooling:

   - Fix the stdio input handling with glibc versions >= 2.28

   - Unbreak the futex-wake benchmark which was reduced to 0 test
     threads due to the conversion to cpumaps

   - Initialize sigaction structs before invoking sys_sigactio()

   - Plug the mapfile memory leak in perf jevents

   - Fix off by one relative directory includes

   - Fix an undefined string comparison in perf diff"

* tag 'perf-urgent-2020-03-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/amd/uncore: Replace manual sampling check with CAP_NO_INTERRUPT flag
  tools: Fix off-by 1 relative directory includes
  perf jevents: Fix leak of mapfile memory
  perf bench: Clear struct sigaction before sigaction() syscall
  perf bench futex-wake: Restore thread count default to online CPU count
  perf top: Fix stdio interface input handling with glibc 2.28+
  perf diff: Fix undefined string comparision spotted by clang's -Wstring-compare
  perf symbols: Don't try to find a vmlinux file when looking for kernel modules
  perf bench: Share some global variables to fix build with gcc 10
  perf parse-events: Use asprintf() instead of strncpy() to read tracepoint files
  perf env: Do not return pointers to local variables
  perf tests bp_account: Make global variable static

arch/x86/events/amd/uncore.c

@@ -190,15 +190,12 @@ static int amd_uncore_event_init(struct perf_event *event)
 
 	/*
 	 * NB and Last level cache counters (MSRs) are shared across all cores
-	 * that share the same NB / Last level cache. Interrupts can be directed
-	 * to a single target core, however, event counts generated by processes
-	 * running on other cores cannot be masked out. So we do not support
-	 * sampling and per-thread events.
+	 * that share the same NB / Last level cache.  On family 16h and below,
+	 * Interrupts can be directed to a single target core, however, event
+	 * counts generated by processes running on other cores cannot be masked
+	 * out. So we do not support sampling and per-thread events via
+	 * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts:
 	 */
-	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
-		return -EINVAL;
-
-	/* and we do not enable counter overflow interrupts */
 	hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
 	hwc->idx = -1;
 
@@ -306,7 +303,7 @@ static struct pmu amd_nb_pmu = {
 	.start		= amd_uncore_start,
 	.stop		= amd_uncore_stop,
 	.read		= amd_uncore_read,
-	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
 };
 
 static struct pmu amd_llc_pmu = {
@@ -317,7 +314,7 @@ static struct pmu amd_llc_pmu = {
 	.start		= amd_uncore_start,
 	.stop		= amd_uncore_stop,
 	.read		= amd_uncore_read,
-	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
 };
 
 static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)

tools/include/uapi/asm/errno.h

@@ -1,18 +1,18 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #if defined(__i386__) || defined(__x86_64__)
-#include "../../arch/x86/include/uapi/asm/errno.h"
+#include "../../../arch/x86/include/uapi/asm/errno.h"
 #elif defined(__powerpc__)
-#include "../../arch/powerpc/include/uapi/asm/errno.h"
+#include "../../../arch/powerpc/include/uapi/asm/errno.h"
 #elif defined(__sparc__)
-#include "../../arch/sparc/include/uapi/asm/errno.h"
+#include "../../../arch/sparc/include/uapi/asm/errno.h"
 #elif defined(__alpha__)
-#include "../../arch/alpha/include/uapi/asm/errno.h"
+#include "../../../arch/alpha/include/uapi/asm/errno.h"
 #elif defined(__mips__)
-#include "../../arch/mips/include/uapi/asm/errno.h"
+#include "../../../arch/mips/include/uapi/asm/errno.h"
 #elif defined(__ia64__)
-#include "../../arch/ia64/include/uapi/asm/errno.h"
+#include "../../../arch/ia64/include/uapi/asm/errno.h"
 #elif defined(__xtensa__)
-#include "../../arch/xtensa/include/uapi/asm/errno.h"
+#include "../../../arch/xtensa/include/uapi/asm/errno.h"
 #else
 #include <asm-generic/errno.h>
 #endif

tools/perf/arch/arm64/util/arm-spe.c

@@ -11,17 +11,17 @@
 #include <linux/zalloc.h>
 #include <time.h>
 
-#include "../../util/cpumap.h"
-#include "../../util/event.h"
-#include "../../util/evsel.h"
-#include "../../util/evlist.h"
-#include "../../util/session.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evlist.h"
+#include "../../../util/session.h"
 #include <internal/lib.h> // page_size
-#include "../../util/pmu.h"
-#include "../../util/debug.h"
-#include "../../util/auxtrace.h"
-#include "../../util/record.h"
-#include "../../util/arm-spe.h"
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/record.h"
+#include "../../../util/arm-spe.h"
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)

tools/perf/arch/arm64/util/perf_regs.c

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../../util/perf_regs.h"
+#include "../../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END

tools/perf/arch/powerpc/util/perf_regs.c

@@ -4,8 +4,8 @@
 #include <regex.h>
 #include <linux/zalloc.h>
 
-#include "../../util/perf_regs.h"
-#include "../../util/debug.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/debug.h"
 
 #include <linux/kernel.h>
 

tools/perf/arch/x86/util/auxtrace.c

@@ -7,13 +7,13 @@
 #include <errno.h>
 #include <stdbool.h>
 
-#include "../../util/header.h"
-#include "../../util/debug.h"
-#include "../../util/pmu.h"
-#include "../../util/auxtrace.h"
-#include "../../util/intel-pt.h"
-#include "../../util/intel-bts.h"
-#include "../../util/evlist.h"
+#include "../../../util/header.h"
+#include "../../../util/debug.h"
+#include "../../../util/pmu.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/evlist.h"
 
 static
 struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist,

tools/perf/arch/x86/util/event.c

@@ -3,12 +3,12 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 
-#include "../../util/event.h"
-#include "../../util/synthetic-events.h"
-#include "../../util/machine.h"
-#include "../../util/tool.h"
-#include "../../util/map.h"
-#include "../../util/debug.h"
+#include "../../../util/event.h"
+#include "../../../util/synthetic-events.h"
+#include "../../../util/machine.h"
+#include "../../../util/tool.h"
+#include "../../../util/map.h"
+#include "../../../util/debug.h"
 
 #if defined(__x86_64__)
 

tools/perf/arch/x86/util/header.c

@@ -7,8 +7,8 @@
 #include <string.h>
 #include <regex.h>
 
-#include "../../util/debug.h"
-#include "../../util/header.h"
+#include "../../../util/debug.h"
+#include "../../../util/header.h"
 
 static inline void
 cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,

tools/perf/arch/x86/util/intel-bts.c

@@ -11,18 +11,18 @@
 #include <linux/log2.h>
 #include <linux/zalloc.h>
 
-#include "../../util/cpumap.h"
-#include "../../util/event.h"
-#include "../../util/evsel.h"
-#include "../../util/evlist.h"
-#include "../../util/mmap.h"
-#include "../../util/session.h"
-#include "../../util/pmu.h"
-#include "../../util/debug.h"
-#include "../../util/record.h"
-#include "../../util/tsc.h"
-#include "../../util/auxtrace.h"
-#include "../../util/intel-bts.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evlist.h"
+#include "../../../util/mmap.h"
+#include "../../../util/session.h"
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/record.h"
+#include "../../../util/tsc.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/intel-bts.h"
 #include <internal/lib.h> // page_size
 
 #define KiB(x) ((x) * 1024)

tools/perf/arch/x86/util/intel-pt.c

@@ -13,23 +13,23 @@
 #include <linux/zalloc.h>
 #include <cpuid.h>
 
-#include "../../util/session.h"
-#include "../../util/event.h"
-#include "../../util/evlist.h"
-#include "../../util/evsel.h"
-#include "../../util/evsel_config.h"
-#include "../../util/cpumap.h"
-#include "../../util/mmap.h"
+#include "../../../util/session.h"
+#include "../../../util/event.h"
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "../../../util/evsel_config.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/mmap.h"
 #include <subcmd/parse-options.h>
-#include "../../util/parse-events.h"
-#include "../../util/pmu.h"
-#include "../../util/debug.h"
-#include "../../util/auxtrace.h"
-#include "../../util/record.h"
-#include "../../util/target.h"
-#include "../../util/tsc.h"
+#include "../../../util/parse-events.h"
+#include "../../../util/pmu.h"
+#include "../../../util/debug.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/record.h"
+#include "../../../util/target.h"
+#include "../../../util/tsc.h"
 #include <internal/lib.h> // page_size
-#include "../../util/intel-pt.h"
+#include "../../../util/intel-pt.h"
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)

tools/perf/arch/x86/util/machine.c

@@ -5,9 +5,9 @@
 #include <stdlib.h>
 
 #include <internal/lib.h> // page_size
-#include "../../util/machine.h"
-#include "../../util/map.h"
-#include "../../util/symbol.h"
+#include "../../../util/machine.h"
+#include "../../../util/map.h"
+#include "../../../util/symbol.h"
 #include <linux/ctype.h>
 
 #include <symbol/kallsyms.h>

tools/perf/arch/x86/util/perf_regs.c

@@ -5,10 +5,10 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 
-#include "../../perf-sys.h"
-#include "../../util/perf_regs.h"
-#include "../../util/debug.h"
-#include "../../util/event.h"
+#include "../../../perf-sys.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/debug.h"
+#include "../../../util/event.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(AX, PERF_REG_X86_AX),

tools/perf/arch/x86/util/pmu.c

@@ -4,9 +4,9 @@
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 
-#include "../../util/intel-pt.h"
-#include "../../util/intel-bts.h"
-#include "../../util/pmu.h"
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/pmu.h"
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {

tools/perf/bench/bench.h

@@ -2,6 +2,10 @@
 #ifndef BENCH_H
 #define BENCH_H
 
+#include <sys/time.h>
+
+extern struct timeval bench__start, bench__end, bench__runtime;
+
 /*
  * The madvise transparent hugepage constants were added in glibc
  * 2.13. For compatibility with older versions of glibc, define these

tools/perf/bench/epoll-ctl.c

@@ -35,7 +35,6 @@
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 8;
-struct timeval start, end, runtime;
 static bool done, __verbose, randomize;
 
 /*
@@ -94,8 +93,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void nest_epollfd(void)
@@ -313,6 +312,7 @@ int bench_epoll_ctl(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	memset(&act, 0, sizeof(act));
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
@@ -361,7 +361,7 @@ int bench_epoll_ctl(int argc, const char **argv)
 
 	threads_starting = nthreads;
 
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 
 	do_threads(worker, cpu);
 

tools/perf/bench/epoll-wait.c

@@ -90,7 +90,6 @@
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 8;
-struct timeval start, end, runtime;
 static bool wdone, done, __verbose, randomize, nonblocking;
 
 /*
@@ -276,8 +275,8 @@ static void toggle_done(int sig __maybe_unused,
 {
 	/* inform all threads that we're done for the day */
 	done = true;
-	gettimeofday(&end, NULL);
-	timersub(&end, &start, &runtime);
+	gettimeofday(&bench__end, NULL);
+	timersub(&bench__end, &bench__start, &bench__runtime);
 }
 
 static void print_summary(void)
@@ -287,7 +286,7 @@ static void print_summary(void)
 
 	printf("\nAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
 	       avg, rel_stddev_stats(stddev, avg),
-	       (int) runtime.tv_sec);
+	       (int)bench__runtime.tv_sec);
 }
 
 static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
@@ -427,6 +426,7 @@ int bench_epoll_wait(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	memset(&act, 0, sizeof(act));
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
@@ -479,7 +479,7 @@ int bench_epoll_wait(int argc, const char **argv)
 
 	threads_starting = nthreads;
 
-	gettimeofday(&start, NULL);
+	gettimeofday(&bench__start, NULL);
 
 	do_threads(worker, cpu);
 
@@ -519,7 +519,7 @@ int bench_epoll_wait(int argc, const char **argv)
 		qsort(worker, nthreads, sizeof(struct worker), cmpworker);
 
 	for (i = 0; i < nthreads; i++) {
-		unsigned long t = worker[i].ops/runtime.tv_sec;
+		unsigned long t = worker[i].ops / bench__runtime.tv_sec;
 
 		update_stats(&throughput_stats, t);