Merge branch 'bpf-perf'

Kaixu Xia says:

====================
bpf: Introduce the new ability of eBPF programs to access hardware PMU counter

This patchset is base on the net-next:
 git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
commit 9dc20a649609c95ce7c5ac4282656ba627b67d49.

Previous patch v6 url:
https://lkml.org/lkml/2015/8/4/188

changes in V7:
 - rebase the whole patch set to net-next tree(9dc20a64);
 - split out the core perf APIs into Patch 1/5;
 - change the return value of function perf_event_attrs()
   from struct perf_event * to const struct perf_event * in
   Patch 1/5;
 - rename the function perf_event_read_internal() to perf_event_
   read_local() and rewrite it in Patch 1/5;
 - rename the function check_func_limit() to check_map_func
   _compatibility() and remove the unnecessary pass pointer to
   a pointer in Patch 4/5;

changes in V6:
 - make the Patch 1/4 commit message more meaning and readable;
 - remove the unnecessary comment in Patch 2/4 and make it clean;
 - declare the function perf_event_release_kernel() in include/
   linux/perf_event.h to fix the build error when CONFIG_PERF_EVENTS
   isn't configured in Patch 2/4;
 - add function perf_event_attrs() to get the struct perf_event_attr
   in Patch 2/4.
 - move the related code from kernel/trace/bpf_trace.c to kernel/
   events/core.c and add function perf_event_read_internal() to
   avoid poking inside of the event outside of perf code in Patch 3/4;
 - generial the func & map match-pair with an array in Patch 3/4;

changes in V5:
 - move struct fd_array_map_ops* fd_ops to bpf_map;
 - move array perf event decrement refcnt function to
   map_free;
 - fix the NULL ptr of perf_event_get();
 - move bpf_perf_event_read() to kernel/bpf/bpf_trace.c;
 - get rid of the remaining struct bpf_prog;
 - move the unnecessay cast on void *;

changes in V4:
 - make the bpf_prog_array_map more generic;
 - fix the bug of event refcnt leak;
 - use more useful errno in bpf_perf_event_read();

changes in V3:
 - collapse V2 patches 1-3 into one;
 - drop the function map->ops->map_traverse_elem() and release
   the struct perf_event in map_free;
 - only allow to access bpf_perf_event_read() from programs;
 - update the perf_event_array_map elem via xchg();
 - pass index directly to bpf_perf_event_read() instead of
   MAP_KEY;

changes in V2:
 - put atomic_long_inc_not_zero() between fdget() and fdput();
 - limit the event type to PERF_TYPE_RAW and PERF_TYPE_HARDWARE;
 - Only read the event counter on current CPU or on current
   process;
 - add new map type BPF_MAP_TYPE_PERF_EVENT_ARRAY to store the
   pointer to the struct perf_event;
 - according to the perf_event_map_fd and key, the function
   bpf_perf_event_read() can get the Hardware PMU counter value;

Patch 5/5 is a simple example and shows how to use this new eBPF
programs ability. The PMU counter data can be found in
/sys/kernel/debug/tracing/trace(trace_pipe).(the cycles PMU
value when 'kprobe/sys_write' sampling)

  $ cat /sys/kernel/debug/tracing/trace_pipe
  $ ./tracex6
       ...
       syslog-ng-548   [000] d..1    76.905673: : CPU-0   681765271
       syslog-ng-548   [000] d..1    76.905690: : CPU-0   681787855
       syslog-ng-548   [000] d..1    76.905707: : CPU-0   681810504
       syslog-ng-548   [000] d..1    76.905725: : CPU-0   681834771
       syslog-ng-548   [000] d..1    76.905745: : CPU-0   681859519
       syslog-ng-548   [000] d..1    76.905766: : CPU-0   681890419
       syslog-ng-548   [000] d..1    76.905783: : CPU-0   681914045
       syslog-ng-548   [000] d..1    76.905800: : CPU-0   681935950
       syslog-ng-548   [000] d..1    76.905816: : CPU-0   681958299
              ls-690   [005] d..1    82.241308: : CPU-5   3138451
              sh-691   [004] d..1    82.244570: : CPU-4   7324988
           <...>-699   [007] d..1    99.961387: : CPU-7   3194027
           <...>-695   [003] d..1    99.961474: : CPU-3   288901
           <...>-695   [003] d..1    99.961541: : CPU-3   383145
           <...>-695   [003] d..1    99.961591: : CPU-3   450365
           <...>-695   [003] d..1    99.961639: : CPU-3   515751
           <...>-695   [003] d..1    99.961686: : CPU-3   579047
       ...

The detail of patches is as follow:

Patch 1/5 add the necessary core perf APIs perf_event_attrs(),
perf_event_get(),perf_event_read_local() when accessing events
counters in eBPF programs

Patch 2/5 rewrites part of the bpf_prog_array map code and make it
more generic;

Patch 3/5 introduces a new bpf map type. This map only stores the
pointer to struct perf_event;

Patch 4/5 implements function bpf_perf_event_read() that get the
selected hardware PMU conuter;

Patch 5/5 gives a simple example.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 100 insertions, 0 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 4450fed91ab4..63e7d50e6a4f 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -12,6 +12,7 @@ hostprogs-y += tracex2
 hostprogs-y += tracex3
 hostprogs-y += tracex4
 hostprogs-y += tracex5
+hostprogs-y += tracex6
 hostprogs-y += lathist
 
 test_verifier-objs := test_verifier.o libbpf.o
@@ -25,6 +26,7 @@ tracex2-objs := bpf_load.o libbpf.o tracex2_user.o
 tracex3-objs := bpf_load.o libbpf.o tracex3_user.o
 tracex4-objs := bpf_load.o libbpf.o tracex4_user.o
 tracex5-objs := bpf_load.o libbpf.o tracex5_user.o
+tracex6-objs := bpf_load.o libbpf.o tracex6_user.o
 lathist-objs := bpf_load.o libbpf.o lathist_user.o
 
 # Tell kbuild to always build the programs
@@ -37,6 +39,7 @@ always += tracex2_kern.o
 always += tracex3_kern.o
 always += tracex4_kern.o
 always += tracex5_kern.o
+always += tracex6_kern.o
 always += tcbpf1_kern.o
 always += lathist_kern.o
 
@@ -51,6 +54,7 @@ HOSTLOADLIBES_tracex2 += -lelf
 HOSTLOADLIBES_tracex3 += -lelf
 HOSTLOADLIBES_tracex4 += -lelf -lrt
 HOSTLOADLIBES_tracex5 += -lelf
+HOSTLOADLIBES_tracex6 += -lelf
 HOSTLOADLIBES_lathist += -lelf
 
 # point this to your LLVM backend with bpf support
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index c77c872fe8ee..3a44d3a272af 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -31,6 +31,8 @@ static unsigned long long (*bpf_get_current_uid_gid)(void) =
 	(void *) BPF_FUNC_get_current_uid_gid;
 static int (*bpf_get_current_comm)(void *buf, int buf_size) =
 	(void *) BPF_FUNC_get_current_comm;
+static int (*bpf_perf_event_read)(void *map, int index) =
+	(void *) BPF_FUNC_perf_event_read;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c
new file mode 100644
index 000000000000..23d1cffaf249
--- /dev/null
+++ b/samples/bpf/tracex6_kern.c
@@ -0,0 +1,26 @@
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") my_map = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(u32),
+	.max_entries = 32,
+};
+
+SEC("kprobe/sys_write")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	u64 count;
+	u32 key = bpf_get_smp_processor_id();
+	char fmt[] = "CPU-%d   %llu\n";
+
+	count = bpf_perf_event_read(&my_map, key);
+	bpf_trace_printk(fmt, sizeof(fmt), key, count);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c
new file mode 100644
index 000000000000..928f05eaa304
--- /dev/null
+++ b/samples/bpf/tracex6_user.c
@@ -0,0 +1,68 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <sys/ioctl.h>
+#include <linux/perf_event.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define SAMPLE_PERIOD  0x7fffffffffffffffULL
+
+static void test_bpf_perf_event(void)
+{
+	int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	int *pmu_fd = malloc(nr_cpus * sizeof(int));
+	unsigned long value;
+	int i;
+
+	struct perf_event_attr attr_insn_pmu = {
+		.freq = 0,
+		.sample_period = SAMPLE_PERIOD,
+		.inherit = 0,
+		.type = PERF_TYPE_HARDWARE,
+		.read_format = 0,
+		.sample_type = 0,
+		.config = 0,/* PMU: cycles */
+	};
+
+	for (i = 0; i < nr_cpus; i++) {
+		pmu_fd[i] = perf_event_open(&attr_insn_pmu, -1/*pid*/, i/*cpu*/, -1/*group_fd*/, 0);
+		if (pmu_fd[i] < 0)
+			printf("event syscall failed\n");
+
+		bpf_update_elem(map_fd[0], &i, &pmu_fd[i], BPF_ANY);
+		ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE, 0);
+	}
+
+	system("ls");
+	system("pwd");
+	system("sleep 2");
+
+	for (i = 0; i < nr_cpus; i++)
+		close(pmu_fd[i]);
+
+	close(map_fd);
+
+	free(pmu_fd);
+}
+
+int main(int argc, char **argv)
+{
+	char filename[256];
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	test_bpf_perf_event();
+
+	return 0;
+}