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

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle on the kernel side were:

   - CPU PMU and uncore driver updates to Intel Snow Ridge, IceLake,
     KabyLake, AmberLake and WhiskeyLake CPUs.

   - Rework the MSR probing infrastructure to make it more robust, make
     it work better on virtualized systems and to better expose it on
     sysfs.

   - Rework PMU attributes group support based on the feedback from
     Greg. The core sysfs patch that adds sysfs_update_groups() was
     acked by Greg.

  There's a lot of perf tooling changes as well, all around the place:

   - vendor updates to Intel, cs-etm (ARM), ARM64, s390,

   - various enhancements to Intel PT tooling support:
      - Improve CBR (Core to Bus Ratio) packets support.
      - Export power and ptwrite events to sqlite and postgresql.
      - Add support for decoding PEBS via PT packets.
      - Add support for samples to contain IPC ratio, collecting cycles
        information from CYC packets, showing the IPC info periodically
      - Allow using time ranges

   - lots of updates to perf pmu, perf stat, perf trace, eBPF support,
     perf record, perf diff, etc. - please see the shortlog and Git log
     for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (252 commits)
  tools arch x86: Sync asm/cpufeatures.h with the with the kernel
  tools build: Check if gettid() is available before providing helper
  perf jvmti: Address gcc string overflow warning for strncpy()
  perf python: Remove -fstack-protector-strong if clang doesn't have it
  perf annotate TUI browser: Do not use member from variable within its own initialization
  perf tests: Fix record+probe_libc_inet_pton.sh for powerpc64
  perf evsel: Do not rely on errno values for precise_ip fallback
  perf thread: Allow references to thread objects after machine__exit()
  perf header: Assign proper ff->ph in perf_event__synthesize_features()
  tools arch kvm: Sync kvm headers with the kernel sources
  perf script: Allow specifying the files to process guest samples
  perf tools metric: Don't include duration_time in group
  perf list: Avoid extra : for --raw metrics
  perf vendor events intel: Metric fixes for SKX/CLX
  perf tools: Fix typos / broken sentences
  perf jevents: Add support for Hisi hip08 L3C PMU aliasing
  perf jevents: Add support for Hisi hip08 HHA PMU aliasing
  perf jevents: Add support for Hisi hip08 DDRC PMU aliasing
  perf pmu: Support more complex PMU event aliasing
  perf diff: Documentation -c cycles option
  ...

1 files changed, 91 insertions, 37 deletions

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e059976d9d93..c7fde04400f7 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <asm/bug.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <sys/types.h>
@@ -9,6 +10,8 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <libgen.h>
+#include <bpf/libbpf.h>
+#include "bpf-event.h"
 #include "compress.h"
 #include "namespaces.h"
 #include "path.h"
@@ -392,7 +395,7 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 				return -ENOMEM;
 		}
 
-		strxfrchar(m->name, '-', '_');
+		strreplace(m->name, '-', '_');
 	}
 
 	return 0;
@@ -706,6 +709,44 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 	return false;
 }
 
+static ssize_t bpf_read(struct dso *dso, u64 offset, char *data)
+{
+	struct bpf_prog_info_node *node;
+	ssize_t size = DSO__DATA_CACHE_SIZE;
+	u64 len;
+	u8 *buf;
+
+	node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id);
+	if (!node || !node->info_linear) {
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		return -1;
+	}
+
+	len = node->info_linear->info.jited_prog_len;
+	buf = (u8 *)(uintptr_t)node->info_linear->info.jited_prog_insns;
+
+	if (offset >= len)
+		return -1;
+
+	size = (ssize_t)min(len - offset, (u64)size);
+	memcpy(data, buf + offset, size);
+	return size;
+}
+
+static int bpf_size(struct dso *dso)
+{
+	struct bpf_prog_info_node *node;
+
+	node = perf_env__find_bpf_prog_info(dso->bpf_prog.env, dso->bpf_prog.id);
+	if (!node || !node->info_linear) {
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		return -1;
+	}
+
+	dso->data.file_size = node->info_linear->info.jited_prog_len;
+	return 0;
+}
+
 static void
 dso_cache__free(struct dso *dso)
 {
@@ -794,48 +835,53 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 	return cache_size;
 }
 
-static ssize_t
-dso_cache__read(struct dso *dso, struct machine *machine,
-		u64 offset, u8 *data, ssize_t size)
+static ssize_t file_read(struct dso *dso, struct machine *machine,
+			 u64 offset, char *data)
 {
-	struct dso_cache *cache;
-	struct dso_cache *old;
 	ssize_t ret;
 
-	do {
-		u64 cache_offset;
+	pthread_mutex_lock(&dso__data_open_lock);
 
-		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
-		if (!cache)
-			return -ENOMEM;
+	/*
+	 * dso->data.fd might be closed if other thread opened another
+	 * file (dso) due to open file limit (RLIMIT_NOFILE).
+	 */
+	try_to_open_dso(dso, machine);
 
-		pthread_mutex_lock(&dso__data_open_lock);
+	if (dso->data.fd < 0) {
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		ret = -errno;
+		goto out;
+	}
 
-		/*
-		 * dso->data.fd might be closed if other thread opened another
-		 * file (dso) due to open file limit (RLIMIT_NOFILE).
-		 */
-		try_to_open_dso(dso, machine);
+	ret = pread(dso->data.fd, data, DSO__DATA_CACHE_SIZE, offset);
+out:
+	pthread_mutex_unlock(&dso__data_open_lock);
+	return ret;
+}
 
-		if (dso->data.fd < 0) {
-			ret = -errno;
-			dso->data.status = DSO_DATA_STATUS_ERROR;
-			break;
-		}
+static ssize_t
+dso_cache__read(struct dso *dso, struct machine *machine,
+		u64 offset, u8 *data, ssize_t size)
+{
+	u64 cache_offset = offset & DSO__DATA_CACHE_MASK;
+	struct dso_cache *cache;
+	struct dso_cache *old;
+	ssize_t ret;
 
-		cache_offset = offset & DSO__DATA_CACHE_MASK;
+	cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
+	if (!cache)
+		return -ENOMEM;
 
-		ret = pread(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE, cache_offset);
-		if (ret <= 0)
-			break;
+	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+		ret = bpf_read(dso, cache_offset, cache->data);
+	else
+		ret = file_read(dso, machine, cache_offset, cache->data);
 
+	if (ret > 0) {
 		cache->offset = cache_offset;
 		cache->size   = ret;
-	} while (0);
-
-	pthread_mutex_unlock(&dso__data_open_lock);
 
-	if (ret > 0) {
 		old = dso_cache__insert(dso, cache);
 		if (old) {
 			/* we lose the race */
@@ -898,18 +944,12 @@ static ssize_t cached_read(struct dso *dso, struct machine *machine,
 	return r;
 }
 
-int dso__data_file_size(struct dso *dso, struct machine *machine)
+static int file_size(struct dso *dso, struct machine *machine)
 {
 	int ret = 0;
 	struct stat st;
 	char sbuf[STRERR_BUFSIZE];
 
-	if (dso->data.file_size)
-		return 0;
-
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
-		return -1;
-
 	pthread_mutex_lock(&dso__data_open_lock);
 
 	/*
@@ -938,6 +978,20 @@ out:
 	return ret;
 }
 
+int dso__data_file_size(struct dso *dso, struct machine *machine)
+{
+	if (dso->data.file_size)
+		return 0;
+
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
+	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return bpf_size(dso);
+
+	return file_size(dso, machine);
+}
+
 /**
  * dso__data_size - Return dso data size
  * @dso: dso object