aboutsummaryrefslogtreecommitdiffstats
path: root/fs/io_uring.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/io_uring.c')
-rw-r--r--fs/io_uring.c44
1 files changed, 35 insertions, 9 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c
index d37d7ea5ebe5..74bc4a04befa 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1096,6 +1096,8 @@ static inline void io_prep_async_work(struct io_kiocb *req,
{
const struct io_op_def *def = &io_op_defs[req->opcode];
+ io_req_init_async(req);
+
if (req->flags & REQ_F_ISREG) {
if (def->hash_reg_file)
io_wq_hash_work(&req->work, file_inode(req->file));
@@ -1104,7 +1106,6 @@ static inline void io_prep_async_work(struct io_kiocb *req,
req->work.flags |= IO_WQ_WORK_UNBOUND;
}
- io_req_init_async(req);
io_req_work_grab_env(req, def);
*link = io_prep_linked_timeout(req);
@@ -1274,6 +1275,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
if (cqe) {
clear_bit(0, &ctx->sq_check_overflow);
clear_bit(0, &ctx->cq_check_overflow);
+ ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
}
spin_unlock_irqrestore(&ctx->completion_lock, flags);
io_cqring_ev_posted(ctx);
@@ -1311,6 +1313,7 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
if (list_empty(&ctx->cq_overflow_list)) {
set_bit(0, &ctx->sq_check_overflow);
set_bit(0, &ctx->cq_check_overflow);
+ ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW;
}
req->flags |= REQ_F_OVERFLOW;
refcount_inc(&req->refs);
@@ -3551,6 +3554,7 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (req->flags & REQ_F_NEED_CLEANUP)
return 0;
+ io->msg.msg.msg_name = &io->msg.addr;
io->msg.iov = io->msg.fast_iov;
ret = sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
&io->msg.iov);
@@ -3732,6 +3736,7 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_ctx *io)
{
+ io->msg.msg.msg_name = &io->msg.addr;
io->msg.iov = io->msg.fast_iov;
#ifdef CONFIG_COMPAT
@@ -3840,10 +3845,16 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)
ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.msg,
kmsg->uaddr, flags);
- if (force_nonblock && ret == -EAGAIN)
- return io_setup_async_msg(req, kmsg);
+ if (force_nonblock && ret == -EAGAIN) {
+ ret = io_setup_async_msg(req, kmsg);
+ if (ret != -EAGAIN)
+ kfree(kbuf);
+ return ret;
+ }
if (ret == -ERESTARTSYS)
ret = -EINTR;
+ if (kbuf)
+ kfree(kbuf);
}
if (kmsg && kmsg->iov != kmsg->fast_iov)
@@ -6080,9 +6091,9 @@ static int io_sq_thread(void *data)
}
/* Tell userspace we may need a wakeup call */
+ spin_lock_irq(&ctx->completion_lock);
ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP;
- /* make sure to read SQ tail after writing flags */
- smp_mb();
+ spin_unlock_irq(&ctx->completion_lock);
to_submit = io_sqring_entries(ctx);
if (!to_submit || ret == -EBUSY) {
@@ -6100,13 +6111,17 @@ static int io_sq_thread(void *data)
schedule();
finish_wait(&ctx->sqo_wait, &wait);
+ spin_lock_irq(&ctx->completion_lock);
ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+ spin_unlock_irq(&ctx->completion_lock);
ret = 0;
continue;
}
finish_wait(&ctx->sqo_wait, &wait);
+ spin_lock_irq(&ctx->completion_lock);
ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
+ spin_unlock_irq(&ctx->completion_lock);
}
mutex_lock(&ctx->uring_lock);
@@ -6693,6 +6708,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
for (i = 0; i < nr_tables; i++)
kfree(ctx->file_data->table[i].files);
+ percpu_ref_exit(&ctx->file_data->refs);
kfree(ctx->file_data->table);
kfree(ctx->file_data);
ctx->file_data = NULL;
@@ -6845,8 +6861,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
}
table->files[index] = file;
err = io_sqe_file_register(ctx, file, i);
- if (err)
+ if (err) {
+ fput(file);
break;
+ }
}
nr_args--;
done++;
@@ -7342,9 +7360,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
io_mem_free(ctx->sq_sqes);
percpu_ref_exit(&ctx->refs);
- if (ctx->account_mem)
- io_unaccount_mem(ctx->user,
- ring_pages(ctx->sq_entries, ctx->cq_entries));
free_uid(ctx->user);
put_cred(ctx->creds);
kfree(ctx->cancel_hash);
@@ -7429,6 +7444,16 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
if (ctx->rings)
io_cqring_overflow_flush(ctx, true);
idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
+
+ /*
+ * Do this upfront, so we won't have a grace period where the ring
+ * is closed but resources aren't reaped yet. This can cause
+ * spurious failure in setting up a new ring.
+ */
+ if (ctx->account_mem)
+ io_unaccount_mem(ctx->user,
+ ring_pages(ctx->sq_entries, ctx->cq_entries));
+
INIT_WORK(&ctx->exit_work, io_ring_exit_work);
queue_work(system_wq, &ctx->exit_work);
}
@@ -7488,6 +7513,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
if (list_empty(&ctx->cq_overflow_list)) {
clear_bit(0, &ctx->sq_check_overflow);
clear_bit(0, &ctx->cq_check_overflow);
+ ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
}
spin_unlock_irq(&ctx->completion_lock);