From b542e383d8c005f06a131e2b40d5889b812f19c6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 29 Jul 2021 13:01:59 +0200 Subject: 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 Signed-off-by: Thomas Gleixner Tested-by: Daniel Bristot de Oliveira Acked-by: Jason Wang Cc: Al Viro Link: https://lore.kernel.org/r/87wnp9idso.ffs@tglx --- fs/aio.c | 2 +- fs/eventfd.c | 12 +++++------- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/aio.c b/fs/aio.c index 76ce0cc3ee4e..51b08ab01dff 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1695,7 +1695,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); req->done = true; - if (iocb->ki_eventfd && eventfd_signal_count()) { + if (iocb->ki_eventfd && eventfd_signal_allowed()) { iocb = NULL; INIT_WORK(&req->work, aio_poll_put_work); schedule_work(&req->work); 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 #include -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; -- cgit v1.2.3