perf/bpf: Convert perf_event_array to use struct file

Robustify refcounting.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/20160126045947.GA40151@ast-mbp.thefacebook.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 33 insertions, 27 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6612732d8fd0..4f90434b8d64 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -729,7 +729,7 @@ extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
 extern void perf_event_delayed_put(struct task_struct *task);
-extern struct perf_event *perf_event_get(unsigned int fd);
+extern struct file *perf_event_get(unsigned int fd);
 extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event);
 extern void perf_event_print_debug(void);
 extern void perf_pmu_disable(struct pmu *pmu);
@@ -1070,7 +1070,7 @@ static inline int perf_event_init_task(struct task_struct *child)	{ return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)      { }
 static inline void perf_event_free_task(struct task_struct *task)       { }
 static inline void perf_event_delayed_put(struct task_struct *task)     { }
-static inline struct perf_event *perf_event_get(unsigned int fd)        { return ERR_PTR(-EINVAL); }
+static inline struct file *perf_event_get(unsigned int fd)      { return ERR_PTR(-EINVAL); }
 static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
 {
         return ERR_PTR(-EINVAL);
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index b0799bced518..89ebbc4d1164 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -291,10 +291,13 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
 {
         struct perf_event *event;
         const struct perf_event_attr *attr;
+        struct file *file;
 
-        event = perf_event_get(fd);
-        if (IS_ERR(event))
-                return event;
+        file = perf_event_get(fd);
+        if (IS_ERR(file))
+                return file;
+
+        event = file->private_data;
 
         attr = perf_event_attrs(event);
         if (IS_ERR(attr))
@@ -304,24 +307,22 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
                 goto err;
 
         if (attr->type == PERF_TYPE_RAW)
-                return event;
+                return file;
 
         if (attr->type == PERF_TYPE_HARDWARE)
-                return event;
+                return file;
 
         if (attr->type == PERF_TYPE_SOFTWARE &&
             attr->config == PERF_COUNT_SW_BPF_OUTPUT)
-                return event;
+                return file;
 err:
-        perf_event_release_kernel(event);
+        fput(file);
         return ERR_PTR(-EINVAL);
 }
 
 static void perf_event_fd_array_put_ptr(void *ptr)
 {
-        struct perf_event *event = ptr;
-
-        perf_event_release_kernel(event);
+        fput((struct file *)ptr);
 }
 
 static const struct bpf_map_ops perf_event_array_ops = {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fe97f95f204e..eb44730afea5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8916,21 +8916,20 @@ void perf_event_delayed_put(struct task_struct *task)
                 WARN_ON_ONCE(task->perf_event_ctxp[ctxn]);
 }
 
-struct perf_event *perf_event_get(unsigned int fd)
+struct file *perf_event_get(unsigned int fd)
 {
-        int err;
-        struct fd f;
-        struct perf_event *event;
+        struct file *file;
 
-        err = perf_fget_light(fd, &f);
-        if (err)
-                return ERR_PTR(err);
+        file = fget_raw(fd);
+        if (!file)
+                return ERR_PTR(-EBADF);
 
-        event = f.file->private_data;
-        atomic_long_inc(&event->refcount);
-        fdput(f);
+        if (file->f_op != &perf_fops) {
+                fput(file);
+                return ERR_PTR(-EBADF);
+        }
 
-        return event;
+        return file;
 }
 
 const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 45dd798bcd37..326a75e884db 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -191,14 +191,17 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
         struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
         struct bpf_array *array = container_of(map, struct bpf_array, map);
         struct perf_event *event;
+        struct file *file;
 
         if (unlikely(index >= array->map.max_entries))
                 return -E2BIG;
 
-        event = (struct perf_event *)array->ptrs[index];
-        if (!event)
+        file = (struct file *)array->ptrs[index];
+        if (unlikely(!file))
                 return -ENOENT;
 
+        event = file->private_data;
+
         /* make sure event is local and doesn't have pmu::count */
         if (event->oncpu != smp_processor_id() ||
             event->pmu->count)
@@ -228,6 +231,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
         void *data = (void *) (long) r4;
         struct perf_sample_data sample_data;
         struct perf_event *event;
+        struct file *file;
         struct perf_raw_record raw = {
                 .size = size,
                 .data = data,
@@ -236,10 +240,12 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
         if (unlikely(index >= array->map.max_entries))
                 return -E2BIG;
 
-        event = (struct perf_event *)array->ptrs[index];
-        if (unlikely(!event))
+        file = (struct file *)array->ptrs[index];
+        if (unlikely(!file))
                 return -ENOENT;
 
+        event = file->private_data;
+
         if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE ||
                      event->attr.config != PERF_COUNT_SW_BPF_OUTPUT))
                 return -EINVAL;