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>

1 files changed, 106 insertions, 31 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cb31229a6fa4..29ace107f236 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -150,15 +150,15 @@ static int __init register_array_map(void)
 }
 late_initcall(register_array_map);
 
-static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr)
 {
-	/* only bpf_prog file descriptors can be stored in prog_array map */
+	/* only file descriptors can be stored in this type of map */
 	if (attr->value_size != sizeof(u32))
 		return ERR_PTR(-EINVAL);
 	return array_map_alloc(attr);
 }
 
-static void prog_array_map_free(struct bpf_map *map)
+static void fd_array_map_free(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
@@ -167,21 +167,21 @@ static void prog_array_map_free(struct bpf_map *map)
 
 	/* make sure it's empty */
 	for (i = 0; i < array->map.max_entries; i++)
-		BUG_ON(array->prog[i] != NULL);
+		BUG_ON(array->ptrs[i] != NULL);
 	kvfree(array);
 }
 
-static void *prog_array_map_lookup_elem(struct bpf_map *map, void *key)
+static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	return NULL;
 }
 
 /* only called from syscall */
-static int prog_array_map_update_elem(struct bpf_map *map, void *key,
-				      void *value, u64 map_flags)
+static int fd_array_map_update_elem(struct bpf_map *map, void *key,
+				    void *value, u64 map_flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	struct bpf_prog *prog, *old_prog;
+	void *new_ptr, *old_ptr;
 	u32 index = *(u32 *)key, ufd;
 
 	if (map_flags != BPF_ANY)
@@ -191,57 +191,75 @@ static int prog_array_map_update_elem(struct bpf_map *map, void *key,
 		return -E2BIG;
 
 	ufd = *(u32 *)value;
-	prog = bpf_prog_get(ufd);
-	if (IS_ERR(prog))
-		return PTR_ERR(prog);
-
-	if (!bpf_prog_array_compatible(array, prog)) {
-		bpf_prog_put(prog);
-		return -EINVAL;
-	}
+	new_ptr = map->ops->map_fd_get_ptr(map, ufd);
+	if (IS_ERR(new_ptr))
+		return PTR_ERR(new_ptr);
 
-	old_prog = xchg(array->prog + index, prog);
-	if (old_prog)
-		bpf_prog_put_rcu(old_prog);
+	old_ptr = xchg(array->ptrs + index, new_ptr);
+	if (old_ptr)
+		map->ops->map_fd_put_ptr(old_ptr);
 
 	return 0;
 }
 
-static int prog_array_map_delete_elem(struct bpf_map *map, void *key)
+static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	struct bpf_prog *old_prog;
+	void *old_ptr;
 	u32 index = *(u32 *)key;
 
 	if (index >= array->map.max_entries)
 		return -E2BIG;
 
-	old_prog = xchg(array->prog + index, NULL);
-	if (old_prog) {
-		bpf_prog_put_rcu(old_prog);
+	old_ptr = xchg(array->ptrs + index, NULL);
+	if (old_ptr) {
+		map->ops->map_fd_put_ptr(old_ptr);
 		return 0;
 	} else {
 		return -ENOENT;
 	}
 }
 
+static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_prog *prog = bpf_prog_get(fd);
+	if (IS_ERR(prog))
+		return prog;
+
+	if (!bpf_prog_array_compatible(array, prog)) {
+		bpf_prog_put(prog);
+		return ERR_PTR(-EINVAL);
+	}
+	return prog;
+}
+
+static void prog_fd_array_put_ptr(void *ptr)
+{
+	struct bpf_prog *prog = ptr;
+
+	bpf_prog_put_rcu(prog);
+}
+
 /* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_prog_array_map_clear(struct bpf_map *map)
+void bpf_fd_array_map_clear(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
 	for (i = 0; i < array->map.max_entries; i++)
-		prog_array_map_delete_elem(map, &i);
+		fd_array_map_delete_elem(map, &i);
 }
 
 static const struct bpf_map_ops prog_array_ops = {
-	.map_alloc = prog_array_map_alloc,
-	.map_free = prog_array_map_free,
+	.map_alloc = fd_array_map_alloc,
+	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
-	.map_lookup_elem = prog_array_map_lookup_elem,
-	.map_update_elem = prog_array_map_update_elem,
-	.map_delete_elem = prog_array_map_delete_elem,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_update_elem = fd_array_map_update_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = prog_fd_array_get_ptr,
+	.map_fd_put_ptr = prog_fd_array_put_ptr,
 };
 
 static struct bpf_map_type_list prog_array_type __read_mostly = {
@@ -255,3 +273,60 @@ static int __init register_prog_array_map(void)
 	return 0;
 }
 late_initcall(register_prog_array_map);
+
+static void perf_event_array_map_free(struct bpf_map *map)
+{
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
+static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
+{
+	struct perf_event *event;
+	const struct perf_event_attr *attr;
+
+	event = perf_event_get(fd);
+	if (IS_ERR(event))
+		return event;
+
+	attr = perf_event_attrs(event);
+	if (IS_ERR(attr))
+		return (void *)attr;
+
+	if (attr->type != PERF_TYPE_RAW &&
+	    attr->type != PERF_TYPE_HARDWARE) {
+		perf_event_release_kernel(event);
+		return ERR_PTR(-EINVAL);
+	}
+	return event;
+}
+
+static void perf_event_fd_array_put_ptr(void *ptr)
+{
+	struct perf_event *event = ptr;
+
+	perf_event_release_kernel(event);
+}
+
+static const struct bpf_map_ops perf_event_array_ops = {
+	.map_alloc = fd_array_map_alloc,
+	.map_free = perf_event_array_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_update_elem = fd_array_map_update_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
+	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
+};
+
+static struct bpf_map_type_list perf_event_array_type __read_mostly = {
+	.ops = &perf_event_array_ops,
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+};
+
+static int __init register_perf_event_array_map(void)
+{
+	bpf_register_map_type(&perf_event_array_type);
+	return 0;
+}
+late_initcall(register_perf_event_array_map);