summaryrefslogtreecommitdiff
path: root/fs/eventfd.c
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2021-07-29 14:01:59 +0300
committerThomas Gleixner <tglx@linutronix.de>2021-08-28 02:33:02 +0300
commitb542e383d8c005f06a131e2b40d5889b812f19c6 (patch)
tree14a6c55f5366f44df978f27c4b8a92f0a30b0689 /fs/eventfd.c
parent366e7ad6ba5f4cb2ffd0b7316e404d6ee9c0f401 (diff)
downloadlinux-b542e383d8c005f06a131e2b40d5889b812f19c6.tar.xz
eventfd: Make signal recursion protection a task bit
The recursion protection for eventfd_signal() is based on a per CPU variable and relies on the !RT semantics of spin_lock_irqsave() for protecting this per CPU variable. On RT kernels spin_lock_irqsave() neither disables preemption nor interrupts which allows the spin lock held section to be preempted. If the preempting task invokes eventfd_signal() as well, then the recursion warning triggers. Paolo suggested to protect the per CPU variable with a local lock, but that's heavyweight and actually not necessary. The goal of this protection is to prevent the task stack from overflowing, which can be achieved with a per task recursion protection as well. Replace the per CPU variable with a per task bit similar to other recursion protection bits like task_struct::in_page_owner. This works on both !RT and RT kernels and removes as a side effect the extra per CPU storage. No functional change for !RT kernels. Reported-by: Daniel Bristot de Oliveira <bristot@redhat.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Tested-by: Daniel Bristot de Oliveira <bristot@redhat.com> Acked-by: Jason Wang <jasowang@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Link: https://lore.kernel.org/r/87wnp9idso.ffs@tglx
Diffstat (limited to 'fs/eventfd.c')
-rw-r--r--fs/eventfd.c12
1 files changed, 5 insertions, 7 deletions
diff --git a/fs/eventfd.c b/fs/eventfd.c
index e265b6dd4f34..3627dd7d25db 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -25,8 +25,6 @@
#include <linux/idr.h>
#include <linux/uio.h>
-DEFINE_PER_CPU(int, eventfd_wake_count);
-
static DEFINE_IDA(eventfd_ida);
struct eventfd_ctx {
@@ -67,21 +65,21 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
* Deadlock or stack overflow issues can happen if we recurse here
* through waitqueue wakeup handlers. If the caller users potentially
* nested waitqueues with custom wakeup handlers, then it should
- * check eventfd_signal_count() before calling this function. If
- * it returns true, the eventfd_signal() call should be deferred to a
+ * check eventfd_signal_allowed() before calling this function. If
+ * it returns false, the eventfd_signal() call should be deferred to a
* safe context.
*/
- if (WARN_ON_ONCE(this_cpu_read(eventfd_wake_count)))
+ if (WARN_ON_ONCE(current->in_eventfd_signal))
return 0;
spin_lock_irqsave(&ctx->wqh.lock, flags);
- this_cpu_inc(eventfd_wake_count);
+ current->in_eventfd_signal = 1;
if (ULLONG_MAX - ctx->count < n)
n = ULLONG_MAX - ctx->count;
ctx->count += n;
if (waitqueue_active(&ctx->wqh))
wake_up_locked_poll(&ctx->wqh, EPOLLIN);
- this_cpu_dec(eventfd_wake_count);
+ current->in_eventfd_signal = 0;
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
return n;