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

Pull perf fixes from Ingo Molnar:
 "Misc fixes:

   - counter freezing related regression fix

   - uprobes race fix

   - Intel PMU unusual event combination fix

   - .. and diverse tooling fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  uprobes: Fix handle_swbp() vs. unregister() + register() race once more
  perf/x86/intel: Disallow precise_ip on BTS events
  perf/x86/intel: Add generic branch tracing check to intel_pmu_has_bts()
  perf/x86/intel: Move branch tracing setup to the Intel-specific source file
  perf/x86/intel: Fix regression by default disabling perfmon v4 interrupt handling
  perf tools beauty ioctl: Support new ISO7816 commands
  tools uapi asm-generic: Synchronize ioctls.h
  tools arch x86: Update tools's copy of cpufeatures.h
  tools headers uapi: Synchronize i915_drm.h
  perf tools: Restore proper cwd on return from mnt namespace
  tools build feature: Check if get_current_dir_name() is available
  perf tools: Fix crash on synthesizing the unit

Documentation/admin-guide/kernel-parameters.txt

@@ -856,7 +856,8 @@
 			causing system reset or hang due to sending
 			INIT from AP to BSP.
 
-	disable_counter_freezing [HW]
+	perf_v4_pmi=	[X86,INTEL]
+			Format: <bool>
 			Disable Intel PMU counter freezing feature.
 			The feature only exists starting from
 			Arch Perfmon v4 (Skylake and newer).

arch/x86/events/core.c

@@ -438,26 +438,6 @@ int x86_setup_perfctr(struct perf_event *event)
 	if (config == -1LL)
 		return -EINVAL;
 
-	/*
-	 * Branch tracing:
-	 */
-	if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
-	    !attr->freq && hwc->sample_period == 1) {
-		/* BTS is not supported by this architecture. */
-		if (!x86_pmu.bts_active)
-			return -EOPNOTSUPP;
-
-		/* BTS is currently only allowed for user-mode. */
-		if (!attr->exclude_kernel)
-			return -EOPNOTSUPP;
-
-		/* disallow bts if conflicting events are present */
-		if (x86_add_exclusive(x86_lbr_exclusive_lbr))
-			return -EBUSY;
-
-		event->destroy = hw_perf_lbr_event_destroy;
-	}
-
 	hwc->config |= config;
 
 	return 0;

arch/x86/events/intel/core.c

@@ -2306,14 +2306,18 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	return handled;
 }
 
-static bool disable_counter_freezing;
+static bool disable_counter_freezing = true;
 static int __init intel_perf_counter_freezing_setup(char *s)
 {
-	disable_counter_freezing = true;
+	bool res;
-	pr_info("Intel PMU Counter freezing feature disabled\n");
+
+	if (kstrtobool(s, &res))
+		return -EINVAL;
+
+	disable_counter_freezing = !res;
 	return 1;
 }
-__setup("disable_counter_freezing", intel_perf_counter_freezing_setup);
+__setup("perf_v4_pmi=", intel_perf_counter_freezing_setup);
 
 /*
  * Simplified handler for Arch Perfmon v4:
@@ -2470,16 +2474,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 static struct event_constraint *
 intel_bts_constraints(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
+	if (unlikely(intel_pmu_has_bts(event)))
-	unsigned int hw_event, bts_event;
-
-	if (event->attr.freq)
-		return NULL;
-
-	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
-	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
-
-	if (unlikely(hw_event == bts_event && hwc->sample_period == 1))
 		return &bts_constraint;
 
 	return NULL;
@@ -3098,10 +3093,51 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 	return flags;
 }
 
+static int intel_pmu_bts_config(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+
+	if (unlikely(intel_pmu_has_bts(event))) {
+		/* BTS is not supported by this architecture. */
+		if (!x86_pmu.bts_active)
+			return -EOPNOTSUPP;
+
+		/* BTS is currently only allowed for user-mode. */
+		if (!attr->exclude_kernel)
+			return -EOPNOTSUPP;
+
+		/* BTS is not allowed for precise events. */
+		if (attr->precise_ip)
+			return -EOPNOTSUPP;
+
+		/* disallow bts if conflicting events are present */
+		if (x86_add_exclusive(x86_lbr_exclusive_lbr))
+			return -EBUSY;
+
+		event->destroy = hw_perf_lbr_event_destroy;
+	}
+
+	return 0;
+}
+
+static int core_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	return intel_pmu_bts_config(event);
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
 
+	if (ret)
+		return ret;
+
+	ret = intel_pmu_bts_config(event);
 	if (ret)
 		return ret;
 
@@ -3127,7 +3163,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		/*
 		 * BTS is set up earlier in this path, so don't account twice
 		 */
-		if (!intel_pmu_has_bts(event)) {
+		if (!unlikely(intel_pmu_has_bts(event))) {
 			/* disallow lbr if conflicting events are present */
 			if (x86_add_exclusive(x86_lbr_exclusive_lbr))
 				return -EBUSY;
@@ -3596,7 +3632,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.enable_all		= core_pmu_enable_all,
 	.enable			= core_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
+	.hw_config		= core_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,

arch/x86/events/perf_event.h

@@ -859,11 +859,16 @@ static inline int amd_pmu_init(void)
 
 static inline bool intel_pmu_has_bts(struct perf_event *event)
 {
-	if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
+	struct hw_perf_event *hwc = &event->hw;
-	    !event->attr.freq && event->hw.sample_period == 1)
+	unsigned int hw_event, bts_event;
-		return true;
 
-	return false;
+	if (event->attr.freq)
+		return false;
+
+	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
+	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
+
+	return hw_event == bts_event && hwc->sample_period == 1;
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);

kernel/events/uprobes.c

@@ -829,7 +829,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 	BUG_ON((uprobe->offset & ~PAGE_MASK) +
 			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
 
-	smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
+	smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
 	set_bit(UPROBE_COPY_INSN, &uprobe->flags);
 
  out:
@@ -2178,10 +2178,18 @@ static void handle_swbp(struct pt_regs *regs)
 	 * After we hit the bp, _unregister + _register can install the
 	 * new and not-yet-analyzed uprobe at the same address, restart.
 	 */
-	smp_rmb(); /* pairs with wmb() in install_breakpoint() */
 	if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
 		goto out;
 
+	/*
+	 * Pairs with the smp_wmb() in prepare_uprobe().
+	 *
+	 * Guarantees that if we see the UPROBE_COPY_INSN bit set, then
+	 * we must also see the stores to &uprobe->arch performed by the
+	 * prepare_uprobe() call.
+	 */
+	smp_rmb();
+
 	/* Tracing handlers use ->utask to communicate with fetch methods */
 	if (!get_utask())
 		goto out;

tools/arch/x86/include/asm/cpufeatures.h

@@ -331,6 +331,8 @@
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
 #define X86_FEATURE_CLDEMOTE		(16*32+25) /* CLDEMOTE instruction */
+#define X86_FEATURE_MOVDIRI		(16*32+27) /* MOVDIRI instruction */
+#define X86_FEATURE_MOVDIR64B		(16*32+28) /* MOVDIR64B instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */

tools/build/Makefile.feature

@@ -33,6 +33,7 @@ FEATURE_TESTS_BASIC :=                  \
         dwarf_getlocations              \
         fortify-source                  \
         sync-compare-and-swap           \
+        get_current_dir_name            \
         glibc                           \
         gtk2                            \
         gtk2-infobar                    \

tools/build/feature/Makefile

@@ -7,6 +7,7 @@ FILES=                                          \
          test-dwarf_getlocations.bin            \
          test-fortify-source.bin                \
          test-sync-compare-and-swap.bin         \
+         test-get_current_dir_name.bin          \
          test-glibc.bin                         \
          test-gtk2.bin                          \
          test-gtk2-infobar.bin                  \
@@ -101,6 +102,9 @@ $(OUTPUT)test-bionic.bin:
 $(OUTPUT)test-libelf.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-get_current_dir_name.bin:
+	$(BUILD)
+
 $(OUTPUT)test-glibc.bin:
 	$(BUILD)
 

tools/build/feature/test-all.c

@@ -34,6 +34,10 @@
 # include "test-libelf-mmap.c"
 #undef main
 
+#define main main_test_get_current_dir_name
+# include "test-get_current_dir_name.c"
+#undef main
+
 #define main main_test_glibc
 # include "test-glibc.c"
 #undef main
@@ -174,6 +178,7 @@ int main(int argc, char *argv[])
 	main_test_hello();
 	main_test_libelf();
 	main_test_libelf_mmap();
+	main_test_get_current_dir_name();
 	main_test_glibc();
 	main_test_dwarf();
 	main_test_dwarf_getlocations();

tools/build/feature/test-get_current_dir_name.c

@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <stdlib.h>
+
+int main(void)
+{
+	free(get_current_dir_name());
+	return 0;
+}

tools/include/uapi/asm-generic/ioctls.h

@@ -79,6 +79,8 @@
 #define TIOCGPTLCK	_IOR('T', 0x39, int) /* Get Pty lock state */
 #define TIOCGEXCL	_IOR('T', 0x40, int) /* Get exclusive mode state */
 #define TIOCGPTPEER	_IO('T', 0x41) /* Safely open the slave */
+#define TIOCGISO7816	_IOR('T', 0x42, struct serial_iso7816)
+#define TIOCSISO7816	_IOWR('T', 0x43, struct serial_iso7816)
 
 #define FIONCLEX	0x5450
 #define FIOCLEX		0x5451

tools/include/uapi/drm/i915_drm.h

@@ -529,6 +529,28 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
 
+/*
+ * Once upon a time we supposed that writes through the GGTT would be
+ * immediately in physical memory (once flushed out of the CPU path). However,
+ * on a few different processors and chipsets, this is not necessarily the case
+ * as the writes appear to be buffered internally. Thus a read of the backing
+ * storage (physical memory) via a different path (with different physical tags
+ * to the indirect write via the GGTT) will see stale values from before
+ * the GGTT write. Inside the kernel, we can for the most part keep track of
+ * the different read/write domains in use (e.g. set-domain), but the assumption
+ * of coherency is baked into the ABI, hence reporting its true state in this
+ * parameter.
+ *
+ * Reports true when writes via mmap_gtt are immediately visible following an
+ * lfence to flush the WCB.
+ *
+ * Reports false when writes via mmap_gtt are indeterminately delayed in an in
+ * internal buffer and are _not_ immediately visible to third parties accessing
+ * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC
+ * communications channel when reporting false is strongly disadvised.
+ */
+#define I915_PARAM_MMAP_GTT_COHERENT	52
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*

tools/perf/Makefile.config

@@ -299,6 +299,11 @@ ifndef NO_BIONIC
   endif
 endif
 
+ifeq ($(feature-get_current_dir_name), 1)
+  CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME
+endif
+
+
 ifdef NO_LIBELF
   NO_DWARF := 1
   NO_DEMANGLE := 1

tools/perf/tests/attr/base-record

@@ -9,7 +9,7 @@ size=112
 config=0
 sample_period=*
 sample_type=263
-read_format=0
+read_format=0|4
 disabled=1
 inherit=1
 pinned=0

tools/perf/trace/beauty/ioctl.c

@@ -31,6 +31,7 @@ static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size)
 	"TCSETSW2", "TCSETSF2", "TIOCGRS48", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
 	"TIOCGDEV", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", "TIOCVHANGUP", "TIOCGPKT",
 	"TIOCGPTLCK", [_IOC_NR(TIOCGEXCL)] = "TIOCGEXCL", "TIOCGPTPEER",
+	"TIOCGISO7816", "TIOCSISO7816",
 	[_IOC_NR(FIONCLEX)] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
 	"TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
 	"TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",

tools/perf/util/Build

@@ -10,6 +10,7 @@ libperf-y += evlist.o
 libperf-y += evsel.o
 libperf-y += evsel_fprintf.o
 libperf-y += find_bit.o
+libperf-y += get_current_dir_name.o
 libperf-y += kallsyms.o
 libperf-y += levenshtein.o
 libperf-y += llvm-utils.o

tools/perf/util/evsel.c

@@ -1092,7 +1092,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->exclude_user   = 1;
 	}
 
-	if (evsel->own_cpus)
+	if (evsel->own_cpus || evsel->unit)
 		evsel->attr.read_format |= PERF_FORMAT_ID;
 
 	/*

tools/perf/util/get_current_dir_name.c

@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+//
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+#include "util.h"
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdlib.h>
+
+/* Android's 'bionic' library, for one, doesn't have this */
+
+char *get_current_dir_name(void)
+{
+	char pwd[PATH_MAX];
+
+	return getcwd(pwd, sizeof(pwd)) == NULL ? NULL : strdup(pwd);
+}
+#endif // HAVE_GET_CURRENT_DIR_NAME

tools/perf/util/namespaces.c

@@ -18,6 +18,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
+#include <asm/bug.h>
 
 struct namespaces *namespaces__new(struct namespaces_event *event)
 {
@@ -186,6 +187,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	char curpath[PATH_MAX];
 	int oldns = -1;
 	int newns = -1;
+	char *oldcwd = NULL;
 
 	if (nc == NULL)
 		return;
@@ -199,9 +201,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
 		return;
 
+	oldcwd = get_current_dir_name();
+	if (!oldcwd)
+		return;
+
 	oldns = open(curpath, O_RDONLY);
 	if (oldns < 0)
-		return;
+		goto errout;
 
 	newns = open(nsi->mntns_path, O_RDONLY);
 	if (newns < 0)
@@ -210,11 +216,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 	if (setns(newns, CLONE_NEWNS) < 0)
 		goto errout;
 
+	nc->oldcwd = oldcwd;
 	nc->oldns = oldns;
 	nc->newns = newns;
 	return;
 
 errout:
+	free(oldcwd);
 	if (oldns > -1)
 		close(oldns);
 	if (newns > -1)
@@ -223,11 +231,16 @@ void nsinfo__mountns_enter(struct nsinfo *nsi,
 
 void nsinfo__mountns_exit(struct nscookie *nc)
 {
-	if (nc == NULL || nc->oldns == -1 || nc->newns == -1)
+	if (nc == NULL || nc->oldns == -1 || nc->newns == -1 || !nc->oldcwd)
 		return;
 
 	setns(nc->oldns, CLONE_NEWNS);
 
+	if (nc->oldcwd) {
+		WARN_ON_ONCE(chdir(nc->oldcwd));
+		zfree(&nc->oldcwd);
+	}
+
 	if (nc->oldns > -1) {
 		close(nc->oldns);
 		nc->oldns = -1;

tools/perf/util/namespaces.h

@@ -38,6 +38,7 @@ struct nsinfo {
 struct nscookie {
 	int			oldns;
 	int			newns;
+	char			*oldcwd;
 };
 
 int nsinfo__init(struct nsinfo *nsi);

tools/perf/util/util.h

@@ -59,6 +59,10 @@ int fetch_kernel_version(unsigned int *puint,
 
 const char *perf_tip(const char *dirpath);
 
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+char *get_current_dir_name(void);
+#endif
+
 #ifndef HAVE_SCHED_GETCPU_SUPPORT
 int sched_getcpu(void);
 #endif