Skip to contentSkip to conversation

Replace io_ring_ctx bitfields with flags

PATCH In review Jens Axboe 2 participants 7 messages Mar 14 – Mar 16 io_uring

lore
Share & tools
lore

Jens Axboe

author maintainer
#0 lore raw

cover Replace io_ring_ctx bitfields with flags

Hi,

No functional changes here, just gets rid of the bitfields in ctx and replaces then with a single int_flags member and a set of flags. This makes it more obvious that these are manipulated and checked together.

 include/linux/io_uring_types.h | 32 +++++++------
 io_uring/eventfd.c             |  4 +-
 io_uring/io_uring.c            | 82 +++++++++++++++++-----------------
 io_uring/io_uring.h            | 10 +++--
 io_uring/msg_ring.c            |  2 +-
 io_uring/register.c            |  8 ++--
 io_uring/rsrc.c                |  8 ++--
 io_uring/tctx.c                |  2 +-
 io_uring/timeout.c             |  4 +-
 io_uring/tw.c                  |  2 +-
 10 files changed, 81 insertions(+), 73 deletions(-)
Signature · 1 line
Jens Axboe
author maintainer
#1 lore raw

PATCH 1/2 io_uring: switch struct io_ring_ctx internal bitfields to flags

Bitfields cannot be set and checked atomically, and this makes it more clear that these are indeed in shared storage and must be checked and set in a sane fashion. This is in preparation for annotating a few of the known racy, but harmless, flags checking.

No intended functional changes in this patch.

---
 include/linux/io_uring_types.h | 32 +++++++------
 io_uring/eventfd.c             |  4 +-
 io_uring/io_uring.c            | 82 +++++++++++++++++-----------------
 io_uring/io_uring.h            |  9 ++--
 io_uring/msg_ring.c            |  2 +-
 io_uring/register.c            |  8 ++--
 io_uring/rsrc.c                |  8 ++--
 io_uring/tctx.c                |  2 +-
 io_uring/timeout.c             |  4 +-
 io_uring/tw.c                  |  2 +-
 10 files changed, 80 insertions(+), 73 deletions(-)
include/linux/io_uring_types.h +18 -14
index dd1420bfcb73..b84576374c7b 100644
@@ -268,24 +268,28 @@ struct io_alloc_cache {
 	unsigned int		init_clear;
 };
 
+enum {
+	IO_RING_F_DRAIN_NEXT		= BIT(0),
+	IO_RING_F_OP_RESTRICTED		= BIT(1),
+	IO_RING_F_REG_RESTRICTED	= BIT(2),
+	IO_RING_F_OFF_TIMEOUT_USED	= BIT(3),
+	IO_RING_F_DRAIN_ACTIVE		= BIT(4),
+	IO_RING_F_HAS_EVFD		= BIT(5),
+	/* all CQEs should be posted only by the submitter task */
+	IO_RING_F_TASK_COMPLETE		= BIT(6),
+	IO_RING_F_LOCKLESS_CQ		= BIT(7),
+	IO_RING_F_SYSCALL_IOPOLL	= BIT(8),
+	IO_RING_F_POLL_ACTIVATED	= BIT(9),
+	IO_RING_F_DRAIN_DISABLED	= BIT(10),
+	IO_RING_F_COMPAT		= BIT(11),
+	IO_RING_F_IOWQ_LIMITS_SET	= BIT(12),
+};
+
 struct io_ring_ctx {
 	/* const or read-mostly hot data */
 	struct {
 		unsigned int		flags;
-		unsigned int		drain_next: 1;
-		unsigned int		op_restricted: 1;
-		unsigned int		reg_restricted: 1;
-		unsigned int		off_timeout_used: 1;
-		unsigned int		drain_active: 1;
-		unsigned int		has_evfd: 1;
-		/* all CQEs should be posted only by the submitter task */
-		unsigned int		task_complete: 1;
-		unsigned int		lockless_cq: 1;
-		unsigned int		syscall_iopoll: 1;
-		unsigned int		poll_activated: 1;
-		unsigned int		drain_disabled: 1;
-		unsigned int		compat: 1;
-		unsigned int		iowq_limits_set : 1;
+		unsigned int		int_flags;
 
 		struct task_struct	*submitter_task;
 		struct io_rings		*rings;
io_uring/eventfd.c +2 -2
index 7482a7dc6b38..3da028500f76 100644
@@ -148,7 +148,7 @@ int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg,
 	spin_unlock(&ctx->completion_lock);
 
 	ev_fd->eventfd_async = eventfd_async;
-	ctx->has_evfd = true;
+	ctx->int_flags |= IO_RING_F_HAS_EVFD;
 	refcount_set(&ev_fd->refs, 1);
 	atomic_set(&ev_fd->ops, 0);
 	rcu_assign_pointer(ctx->io_ev_fd, ev_fd);
@@ -162,7 +162,7 @@ int io_eventfd_unregister(struct io_ring_ctx *ctx)
 	ev_fd = rcu_dereference_protected(ctx->io_ev_fd,
 					lockdep_is_held(&ctx->uring_lock));
 	if (ev_fd) {
-		ctx->has_evfd = false;
+		ctx->int_flags &= ~IO_RING_F_HAS_EVFD;
 		rcu_assign_pointer(ctx->io_ev_fd, NULL);
 		io_eventfd_put(ev_fd);
 		return 0;
io_uring/io_uring.c +42 -40

242 lines not on this page · raw message

io_uring/io_uring.h +5 -4
index 0fa844faf287..5cb1983043cd 100644
@@ -211,7 +211,7 @@ static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx)
 
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		lockdep_assert_held(&ctx->uring_lock);
-	} else if (!ctx->task_complete) {
+	} else if (!(ctx->int_flags & IO_RING_F_TASK_COMPLETE)) {
 		lockdep_assert_held(&ctx->completion_lock);
 	} else if (ctx->submitter_task) {
 		/*
@@ -228,7 +228,7 @@ static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx)
 
 static inline bool io_is_compat(struct io_ring_ctx *ctx)
 {
-	return IS_ENABLED(CONFIG_COMPAT) && unlikely(ctx->compat);
+	return IS_ENABLED(CONFIG_COMPAT) && unlikely(ctx->int_flags & IO_RING_F_COMPAT);
 }
 
 static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
@@ -472,8 +472,9 @@ static inline void io_req_complete_defer(struct io_kiocb *req)
 
 static inline void io_commit_cqring_flush(struct io_ring_ctx *ctx)
 {
-	if (unlikely(ctx->off_timeout_used ||
-		     ctx->has_evfd || ctx->poll_activated))
+	if (unlikely(ctx->int_flags & (IO_RING_F_OFF_TIMEOUT_USED |
+				       IO_RING_F_HAS_EVFD |
+				       IO_RING_F_POLL_ACTIVATED)))
 		__io_commit_cqring_flush(ctx);
 }
 
io_uring/msg_ring.c +1 -1
index 57ad0085869a..3ff9098573db 100644
@@ -67,7 +67,7 @@ void io_msg_ring_cleanup(struct io_kiocb *req)
 
 static inline bool io_msg_need_remote(struct io_ring_ctx *target_ctx)
 {
-	return target_ctx->task_complete;
+	return target_ctx->int_flags & IO_RING_F_TASK_COMPLETE;
 }
 
 static void io_msg_tw_complete(struct io_tw_req tw_req, io_tw_token_t tw)
io_uring/register.c +4 -4
index 0148735f7711..489a6feaf228 100644
@@ -184,9 +184,9 @@ static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
 		return ret;
 	}
 	if (ctx->restrictions.op_registered)
-		ctx->op_restricted = 1;
+		ctx->int_flags |= IO_RING_F_OP_RESTRICTED;
 	if (ctx->restrictions.reg_registered)
-		ctx->reg_restricted = 1;
+		ctx->int_flags |= IO_RING_F_REG_RESTRICTED;
 	return 0;
 }
 
@@ -384,7 +384,7 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
 	for (i = 0; i < ARRAY_SIZE(new_count); i++)
 		if (new_count[i])
 			ctx->iowq_limits[i] = new_count[i];
-	ctx->iowq_limits_set = true;
+	ctx->int_flags |= IO_RING_F_IOWQ_LIMITS_SET;
 
 	if (tctx && tctx->io_wq) {
 		ret = io_wq_max_workers(tctx->io_wq, new_count);
@@ -725,7 +725,7 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 	if (ctx->submitter_task && ctx->submitter_task != current)
 		return -EEXIST;
 
-	if (ctx->reg_restricted && !(ctx->flags & IORING_SETUP_R_DISABLED)) {
+	if ((ctx->int_flags & IO_RING_F_REG_RESTRICTED) && !(ctx->flags & IORING_SETUP_R_DISABLED)) {
 		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
 		if (!test_bit(opcode, ctx->restrictions.register_op))
 			return -EACCES;
io_uring/rsrc.c +4 -4
index 4fa59bf89bba..52554ed89b11 100644
@@ -295,7 +295,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
 		u64 tag = 0;
 
 		uvec = u64_to_user_ptr(user_data);
-		iov = iovec_from_user(uvec, 1, 1, &fast_iov, ctx->compat);
+		iov = iovec_from_user(uvec, 1, 1, &fast_iov, io_is_compat(ctx));
 		if (IS_ERR(iov)) {
 			err = PTR_ERR(iov);
 			break;
@@ -319,7 +319,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
 		i = array_index_nospec(up->offset + done, ctx->buf_table.nr);
 		io_reset_rsrc_node(ctx, &ctx->buf_table, i);
 		ctx->buf_table.nodes[i] = node;
-		if (ctx->compat)
+		if (io_is_compat(ctx))
 			user_data += sizeof(struct compat_iovec);
 		else
 			user_data += sizeof(struct iovec);
@@ -883,12 +883,12 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
 
 		if (arg) {
 			uvec = (struct iovec __user *) arg;
-			iov = iovec_from_user(uvec, 1, 1, &fast_iov, ctx->compat);
+			iov = iovec_from_user(uvec, 1, 1, &fast_iov, io_is_compat(ctx));
 			if (IS_ERR(iov)) {
 				ret = PTR_ERR(iov);
 				break;
 			}
-			if (ctx->compat)
+			if (io_is_compat(ctx))
 				arg += sizeof(struct compat_iovec);
 			else
 				arg += sizeof(struct iovec);
io_uring/tctx.c +1 -1
index 7cbcb82aedfb..143de8e990eb 100644
@@ -121,7 +121,7 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx)
 			return ret;
 
 		tctx = current->io_uring;
-		if (ctx->iowq_limits_set) {
+		if (ctx->int_flags & IO_RING_F_IOWQ_LIMITS_SET) {
 			unsigned int limits[2] = { ctx->iowq_limits[0],
 						   ctx->iowq_limits[1], };
 
io_uring/timeout.c +2 -2
index 8eddf8add7a2..579fdddac71a 100644
@@ -566,8 +566,8 @@ static int __io_timeout_prep(struct io_kiocb *req,
 
 	INIT_LIST_HEAD(&timeout->list);
 	timeout->off = off;
-	if (unlikely(off && !req->ctx->off_timeout_used))
-		req->ctx->off_timeout_used = true;
+	if (unlikely(off && !(req->ctx->int_flags & IO_RING_F_OFF_TIMEOUT_USED)))
+		req->ctx->int_flags |= IO_RING_F_OFF_TIMEOUT_USED;
 	/*
 	 * for multishot reqs w/ fixed nr of repeats, repeats tracks the
 	 * remaining nr
io_uring/tw.c +1 -1
index 2f2b4ac4b126..022fe8753c19 100644
@@ -222,7 +222,7 @@ void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 
 	if (!head) {
 		io_ctx_mark_taskrun(ctx);
-		if (ctx->has_evfd)
+		if (ctx->int_flags & IO_RING_F_HAS_EVFD)
 			io_eventfd_signal(ctx, false);
 	}
 
Signature · 1 line
2.53.0
author maintainer
#6 lore raw

PATCH 2/2 io_uring: mark known and harmless racy ctx->int_flags uses

In reply to Jens Axboe

There are a few of these, where flags are read outside of the uring_lock, yet it's harmless to race on them.

---
 io_uring/io_uring.c | 2 +-
 io_uring/io_uring.h | 7 ++++---
 io_uring/tw.c       | 2 +-
 3 files changed, 6 insertions(+), 5 deletions(-)
io_uring/io_uring.c +1 -1
index bfeb3bc3849d..fb5a263706be 100644
@@ -2242,7 +2242,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	struct io_ring_ctx *ctx = file->private_data;
 	__poll_t mask = 0;
 
-	if (unlikely(!(ctx->int_flags & IO_RING_F_POLL_ACTIVATED)))
+	if (unlikely(!(data_race(ctx->int_flags) & IO_RING_F_POLL_ACTIVATED)))
 		io_activate_pollwq(ctx);
 	/*
 	 * provides mb() which pairs with barrier from wq_has_sleeper
io_uring/io_uring.h +4 -3
index 5cb1983043cd..91cf67b5d85b 100644
@@ -470,11 +470,12 @@ static inline void io_req_complete_defer(struct io_kiocb *req)
 	wq_list_add_tail(&req->comp_list, &state->compl_reqs);
 }
 
+#define SHOULD_FLUSH_MASK	(IO_RING_F_OFF_TIMEOUT_USED | \
+				 IO_RING_F_HAS_EVFD | IO_RING_F_POLL_ACTIVATED)
+
 static inline void io_commit_cqring_flush(struct io_ring_ctx *ctx)
 {
-	if (unlikely(ctx->int_flags & (IO_RING_F_OFF_TIMEOUT_USED |
-				       IO_RING_F_HAS_EVFD |
-				       IO_RING_F_POLL_ACTIVATED)))
+	if (unlikely(data_race(ctx->int_flags) & SHOULD_FLUSH_MASK))
 		__io_commit_cqring_flush(ctx);
 }
 
io_uring/tw.c +1 -1
index 022fe8753c19..fdff81eebc95 100644
@@ -222,7 +222,7 @@ void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 
 	if (!head) {
 		io_ctx_mark_taskrun(ctx);
-		if (ctx->int_flags & IO_RING_F_HAS_EVFD)
+		if (data_race(ctx->int_flags) & IO_RING_F_HAS_EVFD)
 			io_eventfd_signal(ctx, false);
 	}
 
Signature · 1 line
2.53.0
#2 lore raw

Re: [PATCH 1/2] io_uring: switch struct io_ring_ctx internal bitfields to flags

In reply to Jens Axboe
Quoted 55 lines · Jens Axboe

Bitfields cannot be set and checked atomically, and this makes it more clear that these are indeed in shared storage and must be checked and set in a sane fashion. This is in preparation for annotating a few of the known racy, but harmless, flags checking.

No intended functional changes in this patch.

---
 include/linux/io_uring_types.h | 32 +++++++------
 io_uring/eventfd.c             |  4 +-
 io_uring/io_uring.c            | 82 +++++++++++++++++-----------------
 io_uring/io_uring.h            |  9 ++--
 io_uring/msg_ring.c            |  2 +-
 io_uring/register.c            |  8 ++--
 io_uring/rsrc.c                |  8 ++--
 io_uring/tctx.c                |  2 +-
 io_uring/timeout.c             |  4 +-
 io_uring/tw.c                  |  2 +-
 10 files changed, 80 insertions(+), 73 deletions(-)
include/linux/io_uring_types.h +17 -5
index dd1420bfcb73..b84576374c7b 100644
@@ -268,24 +268,28 @@ struct io_alloc_cache {
 	unsigned int		init_clear;
 };
 
+enum {
+	IO_RING_F_DRAIN_NEXT		= BIT(0),
+	IO_RING_F_OP_RESTRICTED		= BIT(1),
+	IO_RING_F_REG_RESTRICTED	= BIT(2),
+	IO_RING_F_OFF_TIMEOUT_USED	= BIT(3),
+	IO_RING_F_DRAIN_ACTIVE		= BIT(4),
+	IO_RING_F_HAS_EVFD		= BIT(5),
+	/* all CQEs should be posted only by the submitter task */
+	IO_RING_F_TASK_COMPLETE		= BIT(6),
+	IO_RING_F_LOCKLESS_CQ		= BIT(7),
+	IO_RING_F_SYSCALL_IOPOLL	= BIT(8),
+	IO_RING_F_POLL_ACTIVATED	= BIT(9),
+	IO_RING_F_DRAIN_DISABLED	= BIT(10),
+	IO_RING_F_COMPAT		= BIT(11),
+	IO_RING_F_IOWQ_LIMITS_SET	= BIT(12),
+};
+
 struct io_ring_ctx {
 	/* const or read-mostly hot data */
 	struct {
 		unsigned int		flags;
-		unsigned int		drain_next: 1;
-		unsigned int		op_restricted: 1;
-		unsigned int		reg_restricted: 1;
-		unsigned int		off_timeout_used: 1;
-		unsigned int		drain_active: 1;

include/linux/io_uring_types.h struct io_alloc_cache { · line 292

Quoted 10 lines
include/linux/io_uring_types.h +1 -9
-		unsigned int		has_evfd: 1;
-		/* all CQEs should be posted only by the submitter task */
-		unsigned int		task_complete: 1;
-		unsigned int		lockless_cq: 1;
-		unsigned int		syscall_iopoll: 1;
-		unsigned int		poll_activated: 1;
-		unsigned int		drain_disabled: 1;
-		unsigned int		compat: 1;
-		unsigned int		iowq_limits_set : 1;
+		unsigned int		int_flags;

Jens,

What does the int prefix means in this context?

Signature · 1 line
Gabriel Krisman Bertazi
author maintainer
#3 lore raw

Re: [PATCH 1/2] io_uring: switch struct io_ring_ctx internal bitfields to flags

Quoted 70 lines · Gabriel Krisman Bertazi
Quoted 55 lines · Jens Axboe

Bitfields cannot be set and checked atomically, and this makes it more clear that these are indeed in shared storage and must be checked and set in a sane fashion. This is in preparation for annotating a few of the known racy, but harmless, flags checking.

No intended functional changes in this patch.

---
 include/linux/io_uring_types.h | 32 +++++++------
 io_uring/eventfd.c             |  4 +-
 io_uring/io_uring.c            | 82 +++++++++++++++++-----------------
 io_uring/io_uring.h            |  9 ++--
 io_uring/msg_ring.c            |  2 +-
 io_uring/register.c            |  8 ++--
 io_uring/rsrc.c                |  8 ++--
 io_uring/tctx.c                |  2 +-
 io_uring/timeout.c             |  4 +-
 io_uring/tw.c                  |  2 +-
 10 files changed, 80 insertions(+), 73 deletions(-)
include/linux/io_uring_types.h +17 -5
index dd1420bfcb73..b84576374c7b 100644
@@ -268,24 +268,28 @@ struct io_alloc_cache {
 	unsigned int		init_clear;
 };
 
+enum {
+	IO_RING_F_DRAIN_NEXT		= BIT(0),
+	IO_RING_F_OP_RESTRICTED		= BIT(1),
+	IO_RING_F_REG_RESTRICTED	= BIT(2),
+	IO_RING_F_OFF_TIMEOUT_USED	= BIT(3),
+	IO_RING_F_DRAIN_ACTIVE		= BIT(4),
+	IO_RING_F_HAS_EVFD		= BIT(5),
+	/* all CQEs should be posted only by the submitter task */
+	IO_RING_F_TASK_COMPLETE		= BIT(6),
+	IO_RING_F_LOCKLESS_CQ		= BIT(7),
+	IO_RING_F_SYSCALL_IOPOLL	= BIT(8),
+	IO_RING_F_POLL_ACTIVATED	= BIT(9),
+	IO_RING_F_DRAIN_DISABLED	= BIT(10),
+	IO_RING_F_COMPAT		= BIT(11),
+	IO_RING_F_IOWQ_LIMITS_SET	= BIT(12),
+};
+
 struct io_ring_ctx {
 	/* const or read-mostly hot data */
 	struct {
 		unsigned int		flags;
-		unsigned int		drain_next: 1;
-		unsigned int		op_restricted: 1;
-		unsigned int		reg_restricted: 1;
-		unsigned int		off_timeout_used: 1;
-		unsigned int		drain_active: 1;

include/linux/io_uring_types.h struct io_alloc_cache { · line 292

Quoted 10 lines
include/linux/io_uring_types.h +1 -9
-		unsigned int		has_evfd: 1;
-		/* all CQEs should be posted only by the submitter task */
-		unsigned int		task_complete: 1;
-		unsigned int		lockless_cq: 1;
-		unsigned int		syscall_iopoll: 1;
-		unsigned int		poll_activated: 1;
-		unsigned int		drain_disabled: 1;
-		unsigned int		compat: 1;
-		unsigned int		iowq_limits_set : 1;
+		unsigned int		int_flags;

Jens,

Quoted 1 line

What does the int prefix means in this context?

It's just short for 'internal'.

Signature · 1 line
Jens Axboe
#4 lore raw

Re: [PATCH 1/2] io_uring: switch struct io_ring_ctx internal bitfields to flags

Quoted 72 lines · Jens Axboe
Quoted 70 lines · Gabriel Krisman Bertazi
Quoted 55 lines · Jens Axboe

Bitfields cannot be set and checked atomically, and this makes it more clear that these are indeed in shared storage and must be checked and set in a sane fashion. This is in preparation for annotating a few of the known racy, but harmless, flags checking.

No intended functional changes in this patch.

---
 include/linux/io_uring_types.h | 32 +++++++------
 io_uring/eventfd.c             |  4 +-
 io_uring/io_uring.c            | 82 +++++++++++++++++-----------------
 io_uring/io_uring.h            |  9 ++--
 io_uring/msg_ring.c            |  2 +-
 io_uring/register.c            |  8 ++--
 io_uring/rsrc.c                |  8 ++--
 io_uring/tctx.c                |  2 +-
 io_uring/timeout.c             |  4 +-
 io_uring/tw.c                  |  2 +-
 10 files changed, 80 insertions(+), 73 deletions(-)
include/linux/io_uring_types.h +17 -5
index dd1420bfcb73..b84576374c7b 100644
@@ -268,24 +268,28 @@ struct io_alloc_cache {
 	unsigned int		init_clear;
 };
 
+enum {
+	IO_RING_F_DRAIN_NEXT		= BIT(0),
+	IO_RING_F_OP_RESTRICTED		= BIT(1),
+	IO_RING_F_REG_RESTRICTED	= BIT(2),
+	IO_RING_F_OFF_TIMEOUT_USED	= BIT(3),
+	IO_RING_F_DRAIN_ACTIVE		= BIT(4),
+	IO_RING_F_HAS_EVFD		= BIT(5),
+	/* all CQEs should be posted only by the submitter task */
+	IO_RING_F_TASK_COMPLETE		= BIT(6),
+	IO_RING_F_LOCKLESS_CQ		= BIT(7),
+	IO_RING_F_SYSCALL_IOPOLL	= BIT(8),
+	IO_RING_F_POLL_ACTIVATED	= BIT(9),
+	IO_RING_F_DRAIN_DISABLED	= BIT(10),
+	IO_RING_F_COMPAT		= BIT(11),
+	IO_RING_F_IOWQ_LIMITS_SET	= BIT(12),
+};
+
 struct io_ring_ctx {
 	/* const or read-mostly hot data */
 	struct {
 		unsigned int		flags;
-		unsigned int		drain_next: 1;
-		unsigned int		op_restricted: 1;
-		unsigned int		reg_restricted: 1;
-		unsigned int		off_timeout_used: 1;
-		unsigned int		drain_active: 1;

include/linux/io_uring_types.h struct io_alloc_cache { · line 292

Quoted 10 lines
include/linux/io_uring_types.h +1 -9
-		unsigned int		has_evfd: 1;
-		/* all CQEs should be posted only by the submitter task */
-		unsigned int		task_complete: 1;
-		unsigned int		lockless_cq: 1;
-		unsigned int		syscall_iopoll: 1;
-		unsigned int		poll_activated: 1;
-		unsigned int		drain_disabled: 1;
-		unsigned int		compat: 1;
-		unsigned int		iowq_limits_set : 1;
+		unsigned int		int_flags;

Jens,

Quoted 3 lines
Quoted 1 line

What does the int prefix means in this context?

It's just short for 'internal'.

ack. Perhaps a comment indicating this is internal would be useful. Otherwise,

Signature · 1 line
Gabriel Krisman Bertazi
author maintainer
#5 lore raw

Re: [PATCH 1/2] io_uring: switch struct io_ring_ctx internal bitfields to flags

Quoted 74 lines · Gabriel Krisman Bertazi
Quoted 72 lines · Jens Axboe
Quoted 70 lines · Gabriel Krisman Bertazi
Quoted 55 lines · Jens Axboe

Bitfields cannot be set and checked atomically, and this makes it more clear that these are indeed in shared storage and must be checked and set in a sane fashion. This is in preparation for annotating a few of the known racy, but harmless, flags checking.

No intended functional changes in this patch.

---
 include/linux/io_uring_types.h | 32 +++++++------
 io_uring/eventfd.c             |  4 +-
 io_uring/io_uring.c            | 82 +++++++++++++++++-----------------
 io_uring/io_uring.h            |  9 ++--
 io_uring/msg_ring.c            |  2 +-
 io_uring/register.c            |  8 ++--
 io_uring/rsrc.c                |  8 ++--
 io_uring/tctx.c                |  2 +-
 io_uring/timeout.c             |  4 +-
 io_uring/tw.c                  |  2 +-
 10 files changed, 80 insertions(+), 73 deletions(-)
include/linux/io_uring_types.h +17 -5
index dd1420bfcb73..b84576374c7b 100644
@@ -268,24 +268,28 @@ struct io_alloc_cache {
 	unsigned int		init_clear;
 };
 
+enum {
+	IO_RING_F_DRAIN_NEXT		= BIT(0),
+	IO_RING_F_OP_RESTRICTED		= BIT(1),
+	IO_RING_F_REG_RESTRICTED	= BIT(2),
+	IO_RING_F_OFF_TIMEOUT_USED	= BIT(3),
+	IO_RING_F_DRAIN_ACTIVE		= BIT(4),
+	IO_RING_F_HAS_EVFD		= BIT(5),
+	/* all CQEs should be posted only by the submitter task */
+	IO_RING_F_TASK_COMPLETE		= BIT(6),
+	IO_RING_F_LOCKLESS_CQ		= BIT(7),
+	IO_RING_F_SYSCALL_IOPOLL	= BIT(8),
+	IO_RING_F_POLL_ACTIVATED	= BIT(9),
+	IO_RING_F_DRAIN_DISABLED	= BIT(10),
+	IO_RING_F_COMPAT		= BIT(11),
+	IO_RING_F_IOWQ_LIMITS_SET	= BIT(12),
+};
+
 struct io_ring_ctx {
 	/* const or read-mostly hot data */
 	struct {
 		unsigned int		flags;
-		unsigned int		drain_next: 1;
-		unsigned int		op_restricted: 1;
-		unsigned int		reg_restricted: 1;
-		unsigned int		off_timeout_used: 1;
-		unsigned int		drain_active: 1;

include/linux/io_uring_types.h struct io_alloc_cache { · line 292

Quoted 10 lines
include/linux/io_uring_types.h +1 -9
-		unsigned int		has_evfd: 1;
-		/* all CQEs should be posted only by the submitter task */
-		unsigned int		task_complete: 1;
-		unsigned int		lockless_cq: 1;
-		unsigned int		syscall_iopoll: 1;
-		unsigned int		poll_activated: 1;
-		unsigned int		drain_disabled: 1;
-		unsigned int		compat: 1;
-		unsigned int		iowq_limits_set : 1;
+		unsigned int		int_flags;

Jens,

Quoted 8 lines
Quoted 3 lines
Quoted 1 line

What does the int prefix means in this context?

It's just short for 'internal'.

ack. Perhaps a comment indicating this is internal would be useful. Otherwise,

Added the comment and your reviewed-by, thanks!

Signature · 1 line
Jens Axboe