From: Jens Axboe <axboe@kernel.dk>
To: linux-fsdevel@vger.kernel.org, linux-aio@kvack.org,
linux-block@vger.kernel.org
Cc: hch@lst.de, viro@zeniv.linux.org.uk, Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 09/22] aio: add submission side request cache
Date: Fri, 21 Dec 2018 12:22:23 -0700 [thread overview]
Message-ID: <20181221192236.12866-10-axboe@kernel.dk> (raw)
In-Reply-To: <20181221192236.12866-1-axboe@kernel.dk>
We have to add each submitted polled request to the io_context
poll_submitted list, which means we have to grab the poll_lock. We
already use the block plug to batch submissions if we're doing a batch
of IO submissions, extend that to cover the poll requests internally as
well.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/aio.c | 140 +++++++++++++++++++++++++++++++++++++++++++++----------
1 file changed, 115 insertions(+), 25 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index f7992c7123bc..ac296139593f 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -236,6 +236,21 @@ struct aio_kiocb {
};
};
+struct aio_submit_state {
+ struct kioctx *ctx;
+
+ struct blk_plug plug;
+#ifdef CONFIG_BLOCK
+ struct blk_plug_cb plug_cb;
+#endif
+
+ /*
+ * Polled iocbs that have been submitted, but not added to the ctx yet
+ */
+ struct list_head req_list;
+ unsigned int req_count;
+};
+
/*------ sysctl variables----*/
static DEFINE_SPINLOCK(aio_nr_lock);
unsigned long aio_nr; /* current system wide number of aio requests */
@@ -1822,29 +1837,62 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
}
/*
- * After the iocb has been issued, it's safe to be found on the poll list.
- * Adding the kiocb to the list AFTER submission ensures that we don't
- * find it from a io_getevents() thread before the issuer is done accessing
- * the kiocb cookie.
+ * Called either at the end of IO submission, or through a plug callback
+ * because we're going to schedule. Moves out local batch of requests to
+ * the ctx poll list, so they can be found for polling + reaping.
*/
-static void aio_iopoll_iocb_issued(struct aio_kiocb *kiocb)
+static void aio_flush_state_reqs(struct kioctx *ctx,
+ struct aio_submit_state *state)
+{
+ spin_lock(&ctx->poll_lock);
+ list_splice_tail_init(&state->req_list, &ctx->poll_submitted);
+ spin_unlock(&ctx->poll_lock);
+ state->req_count = 0;
+}
+
+static void aio_iopoll_iocb_add_list(struct aio_kiocb *kiocb)
{
+ struct kioctx *ctx = kiocb->ki_ctx;
+
/*
* For fast devices, IO may have already completed. If it has, add
* it to the front so we find it first. We can't add to the poll_done
* list as that's unlocked from the completion side.
*/
- const int front = test_bit(KIOCB_F_POLL_COMPLETED, &kiocb->ki_flags);
- struct kioctx *ctx = kiocb->ki_ctx;
-
spin_lock(&ctx->poll_lock);
- if (front)
+ if (test_bit(KIOCB_F_POLL_COMPLETED, &kiocb->ki_flags))
list_add(&kiocb->ki_list, &ctx->poll_submitted);
else
list_add_tail(&kiocb->ki_list, &ctx->poll_submitted);
spin_unlock(&ctx->poll_lock);
}
+static void aio_iopoll_iocb_add_state(struct aio_submit_state *state,
+ struct aio_kiocb *kiocb)
+{
+ if (test_bit(KIOCB_F_POLL_COMPLETED, &kiocb->ki_flags))
+ list_add(&kiocb->ki_list, &state->req_list);
+ else
+ list_add_tail(&kiocb->ki_list, &state->req_list);
+
+ if (++state->req_count >= AIO_IOPOLL_BATCH)
+ aio_flush_state_reqs(state->ctx, state);
+}
+/*
+ * After the iocb has been issued, it's safe to be found on the poll list.
+ * Adding the kiocb to the list AFTER submission ensures that we don't
+ * find it from a io_getevents() thread before the issuer is done accessing
+ * the kiocb cookie.
+ */
+static void aio_iopoll_iocb_issued(struct aio_submit_state *state,
+ struct aio_kiocb *kiocb)
+{
+ if (!state || !IS_ENABLED(CONFIG_BLOCK))
+ aio_iopoll_iocb_add_list(kiocb);
+ else
+ aio_iopoll_iocb_add_state(state, kiocb);
+}
+
static ssize_t aio_read(struct aio_kiocb *kiocb, const struct iocb *iocb,
bool vectored, bool compat)
{
@@ -2138,7 +2186,8 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
}
static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
- struct iocb __user *user_iocb, bool compat)
+ struct iocb __user *user_iocb,
+ struct aio_submit_state *state, bool compat)
{
struct aio_kiocb *req;
ssize_t ret;
@@ -2241,7 +2290,7 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
ret = -EAGAIN;
goto out_put_req;
}
- aio_iopoll_iocb_issued(req);
+ aio_iopoll_iocb_issued(state, req);
}
return 0;
out_put_req:
@@ -2255,14 +2304,51 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
}
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
- bool compat)
+ struct aio_submit_state *state, bool compat)
{
struct iocb iocb;
if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
return -EFAULT;
- return __io_submit_one(ctx, &iocb, user_iocb, compat);
+ return __io_submit_one(ctx, &iocb, user_iocb, state, compat);
+}
+
+#ifdef CONFIG_BLOCK
+static void aio_state_unplug(struct blk_plug_cb *cb, bool from_schedule)
+{
+ struct aio_submit_state *state;
+
+ state = container_of(cb, struct aio_submit_state, plug_cb);
+ if (!list_empty(&state->req_list))
+ aio_flush_state_reqs(state->ctx, state);
+}
+#endif
+
+/*
+ * Batched submission is done, ensure local IO is flushed out.
+ */
+static void aio_submit_state_end(struct aio_submit_state *state)
+{
+ blk_finish_plug(&state->plug);
+ if (!list_empty(&state->req_list))
+ aio_flush_state_reqs(state->ctx, state);
+}
+
+/*
+ * Start submission side cache.
+ */
+static void aio_submit_state_start(struct aio_submit_state *state,
+ struct kioctx *ctx)
+{
+ state->ctx = ctx;
+ INIT_LIST_HEAD(&state->req_list);
+ state->req_count = 0;
+#ifdef CONFIG_BLOCK
+ state->plug_cb.callback = aio_state_unplug;
+ blk_start_plug(&state->plug);
+ list_add(&state->plug_cb.list, &state->plug.cb_list);
+#endif
}
/* sys_io_submit:
@@ -2280,10 +2366,10 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
struct iocb __user * __user *, iocbpp)
{
+ struct aio_submit_state state, *statep = NULL;
struct kioctx *ctx;
long ret = 0;
int i = 0;
- struct blk_plug plug;
if (unlikely(nr < 0))
return -EINVAL;
@@ -2297,8 +2383,10 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
if (nr > ctx->nr_events)
nr = ctx->nr_events;
- if (nr > AIO_PLUG_THRESHOLD)
- blk_start_plug(&plug);
+ if (nr > AIO_PLUG_THRESHOLD) {
+ aio_submit_state_start(&state, ctx);
+ statep = &state;
+ }
for (i = 0; i < nr; i++) {
struct iocb __user *user_iocb;
@@ -2307,12 +2395,12 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
break;
}
- ret = io_submit_one(ctx, user_iocb, false);
+ ret = io_submit_one(ctx, user_iocb, statep, false);
if (ret)
break;
}
- if (nr > AIO_PLUG_THRESHOLD)
- blk_finish_plug(&plug);
+ if (statep)
+ aio_submit_state_end(statep);
percpu_ref_put(&ctx->users);
return i ? i : ret;
@@ -2322,10 +2410,10 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
int, nr, compat_uptr_t __user *, iocbpp)
{
+ struct aio_submit_state state, *statep = NULL;
struct kioctx *ctx;
long ret = 0;
int i = 0;
- struct blk_plug plug;
if (unlikely(nr < 0))
return -EINVAL;
@@ -2339,8 +2427,10 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
if (nr > ctx->nr_events)
nr = ctx->nr_events;
- if (nr > AIO_PLUG_THRESHOLD)
- blk_start_plug(&plug);
+ if (nr > AIO_PLUG_THRESHOLD) {
+ aio_submit_state_start(&state, ctx);
+ statep = &state;
+ }
for (i = 0; i < nr; i++) {
compat_uptr_t user_iocb;
@@ -2349,12 +2439,12 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
break;
}
- ret = io_submit_one(ctx, compat_ptr(user_iocb), true);
+ ret = io_submit_one(ctx, compat_ptr(user_iocb), statep, true);
if (ret)
break;
}
- if (nr > AIO_PLUG_THRESHOLD)
- blk_finish_plug(&plug);
+ if (statep)
+ aio_submit_state_end(statep);
percpu_ref_put(&ctx->users);
return i ? i : ret;
--
2.17.1
next prev parent reply other threads:[~2018-12-21 19:23 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-21 19:22 [PATCHSET v10] Support for polled and buffered aio (and more) Jens Axboe
2018-12-21 19:22 ` [PATCH 01/22] fs: add an iopoll method to struct file_operations Jens Axboe
2018-12-21 19:22 ` [PATCH 02/22] block: add bio_set_polled() helper Jens Axboe
2018-12-21 19:22 ` [PATCH 03/22] block: wire up block device iopoll method Jens Axboe
2018-12-21 19:22 ` [PATCH 04/22] block: use REQ_HIPRI_ASYNC for non-sync polled IO Jens Axboe
2018-12-21 19:25 ` Jens Axboe
2018-12-27 13:15 ` Christoph Hellwig
2018-12-27 20:22 ` Jens Axboe
2018-12-21 19:22 ` [PATCH 05/22] block: use bio_set_polled() helper for O_DIRECT Jens Axboe
2018-12-21 19:22 ` [PATCH 06/22] iomap: wire up the iopoll method Jens Axboe
2018-12-21 19:22 ` [PATCH 07/22] aio: add io_setup2() system call Jens Axboe
2018-12-27 13:55 ` Christoph Hellwig
2018-12-27 20:27 ` Jens Axboe
2018-12-21 19:22 ` [PATCH 08/22] aio: support for IO polling Jens Axboe
2018-12-27 13:55 ` Christoph Hellwig
2018-12-27 20:29 ` Jens Axboe
2018-12-21 19:22 ` Jens Axboe [this message]
2018-12-27 13:56 ` [PATCH 09/22] aio: add submission side request cache Christoph Hellwig
2018-12-27 20:31 ` Jens Axboe
2018-12-21 19:22 ` [PATCH 10/22] fs: add fget_many() and fput_many() Jens Axboe
2018-12-21 19:22 ` [PATCH 11/22] aio: use fget/fput_many() for file references Jens Axboe
2018-12-21 19:22 ` [PATCH 12/22] aio: split iocb init from allocation Jens Axboe
2018-12-21 19:22 ` [PATCH 13/22] aio: batch aio_kiocb allocation Jens Axboe
2018-12-21 19:22 ` [PATCH 14/22] aio: split old ring complete out from aio_complete() Jens Axboe
2018-12-21 19:22 ` [PATCH 15/22] aio: pass in user index to __io_submit_one() Jens Axboe
2018-12-21 19:22 ` [PATCH 16/22] aio: add support for submission/completion rings Jens Axboe
2018-12-27 13:47 ` Christoph Hellwig
2019-01-02 16:28 ` Jens Axboe
2019-01-02 20:32 ` Jens Axboe
2019-01-02 19:11 ` Jeff Moyer
2018-12-21 19:22 ` [PATCH 17/22] block: implement bio helper to add iter bvec pages to bio Jens Axboe
2018-12-21 19:22 ` [PATCH 18/22] aio: add support for pre-mapped user IO buffers Jens Axboe
2018-12-27 13:57 ` Christoph Hellwig
2018-12-21 19:22 ` [PATCH 19/22] aio: support kernel side submission for aio with SCQRING Jens Axboe
2018-12-27 13:57 ` Christoph Hellwig
2018-12-27 20:34 ` Jens Axboe
2018-12-21 19:22 ` [PATCH 20/22] aio: enable polling for IOCTX_FLAG_SQTHREAD Jens Axboe
2018-12-21 19:22 ` [PATCH 21/22] aio: utilize io_event->res2 for CQ ring Jens Axboe
2018-12-21 19:22 ` [PATCH 22/22] aio: add my copyright Jens Axboe
Reply instructions:
You may reply publicly 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=20181221192236.12866-10-axboe@kernel.dk \
--to=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=linux-aio@kvack.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=viro@zeniv.linux.org.uk \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).