Commit 56201969 authored by Arnaldo Carvalho de Melo's avatar Arnaldo Carvalho de Melo
Browse files

perf: Make perf_event_output() propagate the output() return 



For the original mode of operation it isn't needed, since we report back
errors via PERF_RECORD_LOST records in the ring buffer, but for use in
bpf_perf_event_output() it is convenient to return the errors, basically
-ENOSPC.

Currently bpf_perf_event_output() returns an error indication, the last
thing it does, which is to push it to the ring buffer is that can fail
and if so, this failure won't be reported back to its users, fix it.

Reported-by: default avatarJamal Hadi Salim <jhs@mojatatu.com>
Tested-by: default avatarJamal Hadi Salim <jhs@mojatatu.com>
Acked-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/r/20190118150938.GN5823@kernel.org


Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent 8dabe9c4

include/linux/perf_event.h

+3 −3
Original line number Diff line number Diff line
@@ -978,7 +978,7 @@ extern void perf_event_output_forward(struct perf_event *event, 
extern void perf_event_output_backward(struct perf_event *event,

				       struct perf_sample_data *data,

				       struct pt_regs *regs);

extern void perf_event_output(struct perf_event *event,

extern int perf_event_output(struct perf_event *event,

			     struct perf_sample_data *data,

			     struct pt_regs *regs);

kernel/events/core.c

+7 −4
Original line number Diff line number Diff line
@@ -6489,7 +6489,7 @@ void perf_prepare_sample(struct perf_event_header *header, 
		data->phys_addr = perf_virt_to_phys(data->addr);

}



static __always_inline void

static __always_inline int

__perf_event_output(struct perf_event *event,

		    struct perf_sample_data *data,

		    struct pt_regs *regs,
@@ -6499,13 +6499,15 @@ __perf_event_output(struct perf_event *event, 
{

	struct perf_output_handle handle;

	struct perf_event_header header;

	int err;



	/* protect the callchain buffers */

	rcu_read_lock();



	perf_prepare_sample(&header, data, event, regs);



	if (output_begin(&handle, event, header.size))

	err = output_begin(&handle, event, header.size);

	if (err)

		goto exit;



	perf_output_sample(&handle, &header, data, event);
@@ -6514,6 +6516,7 @@ __perf_event_output(struct perf_event *event, 


exit:

	rcu_read_unlock();

	return err;

}



void
@@ -6532,12 +6535,12 @@ perf_event_output_backward(struct perf_event *event, 
	__perf_event_output(event, data, regs, perf_output_begin_backward);

}



void

int

perf_event_output(struct perf_event *event,

		  struct perf_sample_data *data,

		  struct pt_regs *regs)

{

	__perf_event_output(event, data, regs, perf_output_begin);

	return __perf_event_output(event, data, regs, perf_output_begin);

}



/*

kernel/trace/bpf_trace.c

+1 −2
Original line number Diff line number Diff line
@@ -431,8 +431,7 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, 
	if (unlikely(event->oncpu != cpu))

		return -EOPNOTSUPP;



	perf_event_output(event, sd, regs);

	return 0;

	return perf_event_output(event, sd, regs);

}



BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,

tools/perf/examples/bpf/augmented_raw_syscalls.c

+2 −2
Original line number Diff line number Diff line
@@ -141,8 +141,8 @@ int sys_enter(struct syscall_enter_args *args) 
		len = sizeof(augmented_args.args);

	}



	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);

	return 0;

	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */

	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);

}



SEC("raw_syscalls:sys_exit")

tools/perf/examples/bpf/augmented_syscalls.c

+7 −7
Original line number Diff line number Diff line
@@ -55,9 +55,9 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ 
		len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;	\

		len &= sizeof(augmented_args.filename.value) - 1;				\

	}											\

	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\

	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */	\

	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 		\

				 &augmented_args, len);						\

	return 0;										\

}												\

int syscall_exit(syscall)(struct syscall_exit_args *args)					\

{												\
@@ -125,10 +125,10 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \ 
/*		addrlen = augmented_args.args.addrlen;				     */		\

/*										     */		\

	probe_read(&augmented_args.addr, addrlen, args->addr_ptr); 				\

	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\

	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */	\

	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 		\

				 &augmented_args, 						\

				sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);\

	return 0;										\

}												\

int syscall_exit(syscall)(struct syscall_exit_args *args)					\

{												\

CRA Git | Maintained and supported by SUSTech CRA and CCSE