This patch adds PERF_FLAG_FD_CLOEXEC flag for perf_event_open() syscall. perf_event_open() creates a new file descriptor, but unlike open() syscall, it lack a flag to atomicaly set close-on-exec (O_CLOEXEC).
Not using O_CLOEXEC by default and not letting userspace provide the "open" flags should be avoided: in most case O_CLOEXEC must be used to not leak file descriptor across exec(). Using O_CLOEXEC when creating a file descriptor allows userspace to set latter, using fcntl(), without any risk of race, if the file descriptor is going to be inherited or not across exec(). Link: http://lkml.kernel.org/r/[email protected] Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Yann Droneaud <[email protected]> --- Hi Peter, This patch should replaces "[PATCH v4 6/7] events: use get_unused_fd_flags(0) instead of get_unused_fd()" Please have a look. Regards. include/uapi/linux/perf_event.h | 1 + kernel/events/core.c | 11 ++++++++--- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 009a655..c217765 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -699,6 +699,7 @@ enum perf_callchain_context { #define PERF_FLAG_FD_NO_GROUP (1U << 0) #define PERF_FLAG_FD_OUTPUT (1U << 1) #define PERF_FLAG_PID_CGROUP (1U << 2) /* pid=cgroup id, per-cpu mode only */ +#define PERF_FLAG_FD_CLOEXEC (1U << 3) /* O_CLOEXEC */ union perf_mem_data_src { __u64 val; diff --git a/kernel/events/core.c b/kernel/events/core.c index 953c143..44de88c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -119,7 +119,8 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info) #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ PERF_FLAG_FD_OUTPUT |\ - PERF_FLAG_PID_CGROUP) + PERF_FLAG_PID_CGROUP |\ + PERF_FLAG_FD_CLOEXEC) /* * branch priv levels that need permission checks @@ -6933,6 +6934,7 @@ SYSCALL_DEFINE5(perf_event_open, int event_fd; int move_group = 0; int err; + int fd_flags; /* for future expandability... */ if (flags & ~PERF_FLAG_ALL) @@ -6961,7 +6963,9 @@ SYSCALL_DEFINE5(perf_event_open, if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1)) return -EINVAL; - event_fd = get_unused_fd(); + fd_flags = (flags & PERF_FLAG_FD_CLOEXEC) ? O_CLOEXEC : 0; + + event_fd = get_unused_fd_flags(fd_flags); if (event_fd < 0) return event_fd; @@ -7083,7 +7087,8 @@ SYSCALL_DEFINE5(perf_event_open, goto err_context; } - event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR); + event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, + O_RDWR | fd_flags); if (IS_ERR(event_file)) { err = PTR_ERR(event_file); goto err_context; -- 1.8.1.4 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
