by Daniel Bristot de Oliveira

[permalink] [raw]

On 7/29/21 1:01 PM, Thomas Gleixner wrote:
> 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 <[email protected]>
> Signed-off-by: Thomas Gleixner <[email protected]>

Testing....

Thanks!
-- Daniel

2021-07-29 19:26:11

by Daniel Bristot de Oliveira

[permalink] [raw]

Subject: Re: [PATCH] eventfd: Make signal recursion protection a task bit

2021-08-26 07:05:59

by Jason Wang

[permalink] [raw]

Subject: Re: [PATCH] eventfd: Make signal recursion protection a task bit

?? 2021/7/29 ????7:01, Thomas Gleixner д??:
> 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 <[email protected]>
> Signed-off-by: Thomas Gleixner <[email protected]>

Acked-by: Jason Wang <[email protected]>

Anyone want to pick this patch?

> ---
> fs/aio.c | 2 +-
> fs/eventfd.c | 12 +++++-------
> include/linux/eventfd.h | 11 +++++------
> include/linux/sched.h | 4 ++++
> 4 files changed, 15 insertions(+), 14 deletions(-)
>
> --- a/fs/aio.c
> +++ b/fs/aio.c
> @@ -1695,7 +1695,7 @@ static int aio_poll_wake(struct wait_que
> 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);
> --- 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 @@ struct eventfd_ctx {
> * 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;
> --- a/include/linux/eventfd.h
> +++ b/include/linux/eventfd.h
> @@ -14,6 +14,7 @@
> #include <linux/err.h>
> #include <linux/percpu-defs.h>
> #include <linux/percpu.h>
> +#include <linux/sched.h>
>
> /*
> * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
> @@ -43,11 +44,9 @@ int eventfd_ctx_remove_wait_queue(struct
> __u64 *cnt);
> void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
>
> -DECLARE_PER_CPU(int, eventfd_wake_count);
> -
> -static inline bool eventfd_signal_count(void)
> +static inline bool eventfd_signal_allowed(void)
> {
> - return this_cpu_read(eventfd_wake_count);
> + return !current->in_eventfd_signal;
> }
>
> #else /* CONFIG_EVENTFD */
> @@ -78,9 +77,9 @@ static inline int eventfd_ctx_remove_wai
> return -ENOSYS;
> }
>
> -static inline bool eventfd_signal_count(void)
> +static inline bool eventfd_signal_allowed(void)
> {
> - return false;
> + return true;
> }
>
> static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -863,6 +863,10 @@ struct task_struct {
> /* Used by page_owner=on to detect recursion in page tracking. */
> unsigned in_page_owner:1;
> #endif
> +#ifdef CONFIG_EVENTFD
> + /* Recursion prevention for eventfd_signal() */
> + unsigned in_eventfd_signal:1;
> +#endif
>
> unsigned long atomic_flags; /* Flags requiring atomic access. */
>
>

2021-08-27 23:45:47

by tip-bot2 for Alexey Makhalov

[permalink] [raw]

Subject: [tip: sched/core] eventfd: Make signal recursion protection a task bit

The following commit has been merged into the sched/core branch of tip:

Commit-ID: b542e383d8c005f06a131e2b40d5889b812f19c6
Gitweb: https://git.kernel.org/tip/b542e383d8c005f06a131e2b40d5889b812f19c6
Author: Thomas Gleixner <[email protected]>
AuthorDate: Thu, 29 Jul 2021 13:01:59 +02:00
Committer: Thomas Gleixner <[email protected]>
CommitterDate: Sat, 28 Aug 2021 01:33:02 +02:00

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 <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Tested-by: Daniel Bristot de Oliveira <[email protected]>
Acked-by: Jason Wang <[email protected]>
Cc: Al Viro <[email protected]>
Link: https://lore.kernel.org/r/87wnp9idso.ffs@tglx

---
fs/aio.c | 2 +-
fs/eventfd.c | 12 +++++-------
include/linux/eventfd.h | 11 +++++------
include/linux/sched.h | 4 ++++
4 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 76ce0cc..51b08ab 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 e265b6d..3627dd7 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;
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index fa0a524..305d5f1 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -14,6 +14,7 @@
#include <linux/err.h>
#include <linux/percpu-defs.h>
#include <linux/percpu.h>
+#include <linux/sched.h>

/*
* CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
@@ -43,11 +44,9 @@ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *w
__u64 *cnt);
void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);

-DECLARE_PER_CPU(int, eventfd_wake_count);
-
-static inline bool eventfd_signal_count(void)
+static inline bool eventfd_signal_allowed(void)
{
- return this_cpu_read(eventfd_wake_count);
+ return !current->in_eventfd_signal;
}

#else /* CONFIG_EVENTFD */
@@ -78,9 +77,9 @@ static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx,
return -ENOSYS;
}

-static inline bool eventfd_signal_count(void)
+static inline bool eventfd_signal_allowed(void)
{
- return false;
+ return true;
}

static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3bb9fec..6421a9a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -864,6 +864,10 @@ struct task_struct {
/* Used by page_owner=on to detect recursion in page tracking. */
unsigned in_page_owner:1;
#endif
+#ifdef CONFIG_EVENTFD
+ /* Recursion prevention for eventfd_signal() */
+ unsigned in_eventfd_signal:1;
+#endif

unsigned long atomic_flags; /* Flags requiring atomic access. */