summaryrefslogtreecommitdiff
path: root/io_uring/io_uring.c
diff options
context:
space:
mode:
Diffstat (limited to 'io_uring/io_uring.c')
-rw-r--r--io_uring/io_uring.c49
1 files changed, 31 insertions, 18 deletions
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ff2bbac1a10f..2ac1cd8d23ea 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -677,16 +677,20 @@ static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx)
io_cq_unlock_post(ctx);
}
+static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx)
+{
+ /* iopoll syncs against uring_lock, not completion_lock */
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_lock(&ctx->uring_lock);
+ __io_cqring_overflow_flush(ctx);
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_unlock(&ctx->uring_lock);
+}
+
static void io_cqring_overflow_flush(struct io_ring_ctx *ctx)
{
- if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
- /* iopoll syncs against uring_lock, not completion_lock */
- if (ctx->flags & IORING_SETUP_IOPOLL)
- mutex_lock(&ctx->uring_lock);
- __io_cqring_overflow_flush(ctx);
- if (ctx->flags & IORING_SETUP_IOPOLL)
- mutex_unlock(&ctx->uring_lock);
- }
+ if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
+ io_cqring_do_overflow_flush(ctx);
}
void __io_put_task(struct task_struct *task, int nr)
@@ -727,6 +731,8 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
size_t ocq_size = sizeof(struct io_overflow_cqe);
bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
+ lockdep_assert_held(&ctx->completion_lock);
+
if (is_cqe32)
ocq_size += sizeof(struct io_uring_cqe);
@@ -816,9 +822,6 @@ static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res,
{
struct io_uring_cqe *cqe;
- if (!ctx->task_complete)
- lockdep_assert_held(&ctx->completion_lock);
-
ctx->cq_extra++;
/*
@@ -1232,13 +1235,18 @@ static void io_req_local_work_add(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
- if (!llist_add(&req->io_task_work.node, &ctx->work_llist))
+ percpu_ref_get(&ctx->refs);
+
+ if (!llist_add(&req->io_task_work.node, &ctx->work_llist)) {
+ percpu_ref_put(&ctx->refs);
return;
+ }
/* need it for the following io_cqring_wake() */
smp_mb__after_atomic();
if (unlikely(atomic_read(&req->task->io_uring->in_idle))) {
io_move_task_work_from_local(ctx);
+ percpu_ref_put(&ctx->refs);
return;
}
@@ -1248,6 +1256,7 @@ static void io_req_local_work_add(struct io_kiocb *req)
if (ctx->has_evfd)
io_eventfd_signal(ctx);
__io_cqring_wake(ctx);
+ percpu_ref_put(&ctx->refs);
}
void __io_req_task_work_add(struct io_kiocb *req, bool allow_local)
@@ -2461,7 +2470,7 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx)
/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq,
- ktime_t timeout)
+ ktime_t *timeout)
{
int ret;
unsigned long check_cq;
@@ -2479,7 +2488,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
return -EBADR;
}
- if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
+ if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
return -ETIME;
/*
@@ -2549,10 +2558,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
trace_io_uring_cqring_wait(ctx, min_events);
do {
- io_cqring_overflow_flush(ctx);
+ if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
+ finish_wait(&ctx->cq_wait, &iowq.wq);
+ io_cqring_do_overflow_flush(ctx);
+ }
prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
TASK_INTERRUPTIBLE);
- ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
+ ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
if (__io_cqring_events_user(ctx) >= min_events)
break;
cond_resched();
@@ -4013,8 +4025,6 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
return -EEXIST;
if (ctx->restricted) {
- if (opcode >= IORING_REGISTER_LAST)
- return -EINVAL;
opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
if (!test_bit(opcode, ctx->restrictions.register_op))
return -EACCES;
@@ -4170,6 +4180,9 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
long ret = -EBADF;
struct fd f;
+ if (opcode >= IORING_REGISTER_LAST)
+ return -EINVAL;
+
f = fdget(fd);
if (!f.file)
return -EBADF;