IO-Uring Archive on lore.kernel.org
 help / color / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: io-uring@vger.kernel.org
Cc: Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 11/13] io_uring: read opcode and user_data from SQE exactly once
Date: Wed, 18 Dec 2019 10:18:33 -0700
Message-ID: <20191218171835.13315-12-axboe@kernel.dk> (raw)
In-Reply-To: <20191218171835.13315-1-axboe@kernel.dk>

If we defer a request, we can't be reading the opcode again. Ensure that
the user_data and opcode fields are stable. For the user_data we already
have a place for it, for the opcode we can fill a one byte hold and store
that as well. For both of them, assign them when we originally read the
SQE in io_get_sqring(). Any code that uses sqe->opcode or sqe->user_data
is switched to req->opcode and req->user_data.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 45 ++++++++++++++++++++-------------------------
 1 file changed, 20 insertions(+), 25 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index c269229e45ef..9f10f5a9da8d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -384,6 +384,7 @@ struct io_kiocb {
 	bool				has_user;
 	bool				in_async;
 	bool				needs_fixed_file;
+	u8				opcode;
 
 	struct io_ring_ctx	*ctx;
 	union {
@@ -597,12 +598,10 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 	}
 }
 
-static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe)
+static inline bool io_req_needs_user(struct io_kiocb *req)
 {
-	u8 opcode = READ_ONCE(sqe->opcode);
-
-	return !(opcode == IORING_OP_READ_FIXED ||
-		 opcode == IORING_OP_WRITE_FIXED);
+	return !(req->opcode == IORING_OP_READ_FIXED ||
+		 req->opcode == IORING_OP_WRITE_FIXED);
 }
 
 static inline bool io_prep_async_work(struct io_kiocb *req,
@@ -611,7 +610,7 @@ static inline bool io_prep_async_work(struct io_kiocb *req,
 	bool do_hashed = false;
 
 	if (req->sqe) {
-		switch (req->sqe->opcode) {
+		switch (req->opcode) {
 		case IORING_OP_WRITEV:
 		case IORING_OP_WRITE_FIXED:
 			/* only regular files should be hashed for writes */
@@ -634,7 +633,7 @@ static inline bool io_prep_async_work(struct io_kiocb *req,
 				req->work.flags |= IO_WQ_WORK_UNBOUND;
 			break;
 		}
-		if (io_sqe_needs_user(req->sqe))
+		if (io_req_needs_user(req))
 			req->work.flags |= IO_WQ_WORK_NEEDS_USER;
 	}
 
@@ -1005,7 +1004,7 @@ static void io_fail_links(struct io_kiocb *req)
 		trace_io_uring_fail_link(req, link);
 
 		if ((req->flags & REQ_F_LINK_TIMEOUT) &&
-		    link->sqe->opcode == IORING_OP_LINK_TIMEOUT) {
+		    link->opcode == IORING_OP_LINK_TIMEOUT) {
 			io_link_cancel_timeout(link);
 		} else {
 			io_cqring_fill_event(link, -ECANCELED);
@@ -1648,7 +1647,7 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 	 * for that purpose and instead let the caller pass in the read/write
 	 * flag.
 	 */
-	opcode = READ_ONCE(sqe->opcode);
+	opcode = req->opcode;
 	if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
 		*iovec = NULL;
 		return io_import_fixed(req->ctx, rw, sqe, iter);
@@ -3080,7 +3079,7 @@ static int io_req_defer_prep(struct io_kiocb *req)
 	struct iov_iter iter;
 	ssize_t ret;
 
-	switch (io->sqe.opcode) {
+	switch (req->opcode) {
 	case IORING_OP_READV:
 	case IORING_OP_READ_FIXED:
 		/* ensure prep does right import */
@@ -3179,11 +3178,10 @@ __attribute__((nonnull))
 static int io_issue_sqe(struct io_kiocb *req, struct io_kiocb **nxt,
 			bool force_nonblock)
 {
-	int ret, opcode;
 	struct io_ring_ctx *ctx = req->ctx;
+	int ret;
 
-	opcode = READ_ONCE(req->sqe->opcode);
-	switch (opcode) {
+	switch (req->opcode) {
 	case IORING_OP_NOP:
 		ret = io_nop(req);
 		break;
@@ -3320,11 +3318,9 @@ static bool io_req_op_valid(int op)
 	return op >= IORING_OP_NOP && op < IORING_OP_LAST;
 }
 
-static int io_op_needs_file(const struct io_uring_sqe *sqe)
+static int io_req_needs_file(struct io_kiocb *req)
 {
-	int op = READ_ONCE(sqe->opcode);
-
-	switch (op) {
+	switch (req->opcode) {
 	case IORING_OP_NOP:
 	case IORING_OP_POLL_REMOVE:
 	case IORING_OP_TIMEOUT:
@@ -3333,7 +3329,7 @@ static int io_op_needs_file(const struct io_uring_sqe *sqe)
 	case IORING_OP_LINK_TIMEOUT:
 		return 0;
 	default:
-		if (io_req_op_valid(op))
+		if (io_req_op_valid(req->opcode))
 			return 1;
 		return -EINVAL;
 	}
@@ -3360,7 +3356,7 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req)
 	if (flags & IOSQE_IO_DRAIN)
 		req->flags |= REQ_F_IO_DRAIN;
 
-	ret = io_op_needs_file(req->sqe);
+	ret = io_req_needs_file(req);
 	if (ret <= 0)
 		return ret;
 
@@ -3480,7 +3476,7 @@ static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
 
 	nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb,
 					link_list);
-	if (!nxt || nxt->sqe->opcode != IORING_OP_LINK_TIMEOUT)
+	if (!nxt || nxt->opcode != IORING_OP_LINK_TIMEOUT)
 		return NULL;
 
 	req->flags |= REQ_F_LINK_TIMEOUT;
@@ -3582,8 +3578,6 @@ static bool io_submit_sqe(struct io_kiocb *req, struct io_submit_state *state,
 	struct io_ring_ctx *ctx = req->ctx;
 	int ret;
 
-	req->user_data = req->sqe->user_data;
-
 	/* enforce forwards compatibility on users */
 	if (unlikely(req->sqe->flags & ~SQE_VALID_FLAGS)) {
 		ret = -EINVAL;
@@ -3715,6 +3709,8 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req)
 		 */
 		req->sequence = ctx->cached_sq_head;
 		req->sqe = &ctx->sq_sqes[head];
+		req->opcode = READ_ONCE(req->sqe->opcode);
+		req->user_data = READ_ONCE(req->sqe->user_data);
 		ctx->cached_sq_head++;
 		return true;
 	}
@@ -3760,7 +3756,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 			break;
 		}
 
-		if (io_sqe_needs_user(req->sqe) && !*mm) {
+		if (io_req_needs_user(req) && !*mm) {
 			mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm);
 			if (!mm_fault) {
 				use_mm(ctx->sqo_mm);
@@ -3776,8 +3772,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 		req->has_user = *mm != NULL;
 		req->in_async = async;
 		req->needs_fixed_file = async;
-		trace_io_uring_submit_sqe(ctx, req->sqe->user_data,
-					  true, async);
+		trace_io_uring_submit_sqe(ctx, req->user_data, true, async);
 		if (!io_submit_sqe(req, statep, &link))
 			break;
 		/*
-- 
2.24.1


  parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-18 17:18 [PATCHSET v3] io_uring fixes for 5.5-rc3 Jens Axboe
2019-12-18 17:18 ` [PATCH 01/13] io_uring: fix stale comment and a few typos Jens Axboe
2019-12-18 17:18 ` [PATCH 02/13] io_uring: fix sporadic -EFAULT from IORING_OP_RECVMSG Jens Axboe
2019-12-18 17:18 ` [PATCH 03/13] io-wq: re-add io_wq_current_is_worker() Jens Axboe
2019-12-18 17:18 ` [PATCH 04/13] io_uring: fix pre-prepped issue with force_nonblock == true Jens Axboe
2019-12-18 17:18 ` [PATCH 05/13] io_uring: remove 'sqe' parameter to the OP helpers that take it Jens Axboe
2019-12-18 17:18 ` [PATCH 06/13] io_uring: any deferred command must have stable sqe data Jens Axboe
2019-12-18 17:18 ` [PATCH 07/13] io_uring: make HARDLINK imply LINK Jens Axboe
2019-12-18 17:18 ` [PATCH 08/13] io_uring: make IORING_POLL_ADD and IORING_POLL_REMOVE deferrable Jens Axboe
2019-12-18 17:18 ` [PATCH 09/13] io_uring: make IORING_OP_CANCEL_ASYNC deferrable Jens Axboe
2019-12-18 17:18 ` [PATCH 10/13] io_uring: make IORING_OP_TIMEOUT_REMOVE deferrable Jens Axboe
2019-12-18 17:18 ` Jens Axboe [this message]
2019-12-18 17:18 ` [PATCH 12/13] io_uring: warn about unhandled opcode Jens Axboe
2019-12-18 17:18 ` [PATCH 13/13] io_uring: don't wait when under-submitting Jens Axboe

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191218171835.13315-12-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=io-uring@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

IO-Uring Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/io-uring/0 io-uring/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 io-uring io-uring/ https://lore.kernel.org/io-uring \
		io-uring@vger.kernel.org
	public-inbox-index io-uring

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.io-uring


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git