It can be quite beneficial to mark appropriate functions with
__attribute__((hot)), it mostly helps to rearrange functions so they are
cached better. E.g. nops test showed 31->32 MIOPS improvement with it.
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
fs/io_uring.c | 34 ++++++++++++++++++----------------
1 file changed, 18 insertions(+), 16 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 62dc128e9b6b..e35569df7f80 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -114,6 +114,8 @@
#define IO_TCTX_REFS_CACHE_NR (1U << 10)
+#define __hot __attribute__((__hot__))
+
struct io_uring {
u32 head ____cacheline_aligned_in_smp;
u32 tail ____cacheline_aligned_in_smp;
@@ -1816,8 +1818,8 @@ static void io_req_complete_post(struct io_kiocb *req, s32 res,
io_cqring_ev_posted(ctx);
}
-static inline void io_req_complete_state(struct io_kiocb *req, s32 res,
- u32 cflags)
+static inline __hot void io_req_complete_state(struct io_kiocb *req,
+ s32 res, u32 cflags)
{
req->result = res;
req->cflags = cflags;
@@ -2260,8 +2262,8 @@ static void io_free_req_work(struct io_kiocb *req, bool *locked)
io_free_req(req);
}
-static void io_free_batch_list(struct io_ring_ctx *ctx,
- struct io_wq_work_node *node)
+static __hot void io_free_batch_list(struct io_ring_ctx *ctx,
+ struct io_wq_work_node *node)
__must_hold(&ctx->uring_lock)
{
struct task_struct *task = NULL;
@@ -2294,7 +2296,7 @@ static void io_free_batch_list(struct io_ring_ctx *ctx,
io_put_task(task, task_refs);
}
-static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
+static __hot void __io_submit_flush_completions(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
struct io_wq_work_node *node, *prev;
@@ -2389,7 +2391,7 @@ static inline bool io_run_task_work(void)
return false;
}
-static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
+static __hot int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
{
struct io_wq_work_node *pos, *start, *prev;
int nr_events = 0;
@@ -2479,7 +2481,7 @@ static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
mutex_unlock(&ctx->uring_lock);
}
-static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
+static __hot int io_iopoll_check(struct io_ring_ctx *ctx, long min)
{
unsigned int nr_events = 0;
int ret = 0;
@@ -6541,7 +6543,7 @@ static void io_clean_op(struct io_kiocb *req)
req->flags &= ~IO_REQ_CLEAN_FLAGS;
}
-static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
+static __hot int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
const struct cred *creds = NULL;
@@ -6882,7 +6884,7 @@ static void io_queue_sqe_arm_apoll(struct io_kiocb *req)
io_queue_linked_timeout(linked_timeout);
}
-static inline void __io_queue_sqe(struct io_kiocb *req)
+static inline __hot void __io_queue_sqe(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
struct io_kiocb *linked_timeout;
@@ -6926,7 +6928,7 @@ static void io_queue_sqe_fallback(struct io_kiocb *req)
}
}
-static inline void io_queue_sqe(struct io_kiocb *req)
+static inline __hot void io_queue_sqe(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL))))
@@ -6977,8 +6979,8 @@ static void io_init_req_drain(struct io_kiocb *req)
}
}
-static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
+static __hot int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
__must_hold(&ctx->uring_lock)
{
struct io_submit_state *state;
@@ -7050,8 +7052,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
return io_req_prep(req, sqe);
}
-static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
+static __hot int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
__must_hold(&ctx->uring_lock)
{
struct io_submit_link *link = &ctx->submit_state.link;
@@ -7174,7 +7176,7 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
* used, it's important that those reads are done through READ_ONCE() to
* prevent a re-load down the line.
*/
-static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx)
+static inline const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx)
{
unsigned head, mask = ctx->sq_entries - 1;
unsigned sq_idx = ctx->cached_sq_head++ & mask;
@@ -7198,7 +7200,7 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx)
return NULL;
}
-static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
+static __hot int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
__must_hold(&ctx->uring_lock)
{
unsigned int entries = io_sqring_entries(ctx);
--
2.33.0
