On the submission side, add file reference batching to the
aio_submit_state. We get as many references as the number of iocbs we
are submitting, and drop unused ones if we end up switching files. The
assumption here is that we're usually only dealing with one fd, and if
there are multiple, hopefuly they are at least somewhat ordered. Could
trivially be extended to cover multiple fds, if needed.
On the completion side we do the same thing, except this is trivially
done just locally in aio_iopoll_reap().
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
fs/aio.c | 106 +++++++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 91 insertions(+), 15 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index 74afd1ff7fc9..70d96c2e0579 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1329,7 +1329,8 @@ static long aio_iopoll_reap(struct kioctx *ctx, struct io_event __user *evs,
{
void *iocbs[AIO_IOPOLL_BATCH];
struct aio_kiocb *iocb, *n;
- int to_free = 0, ret = 0;
+ int file_count, to_free = 0, ret = 0;
+ struct file *file = NULL;
list_for_each_entry_safe(iocb, n, &ctx->poll_completing, ki_list) {
if (*nr_events == max)
@@ -1342,7 +1343,20 @@ static long aio_iopoll_reap(struct kioctx *ctx, struct io_event __user *evs,
list_del(&iocb->ki_list);
iocbs[to_free++] = iocb;
- fput(iocb->rw.ki_filp);
+ /*
+ * Batched puts of the same file, to avoid dirtying the
+ * file usage count multiple times, if avoidable.
+ */
+ if (!file) {
+ file = iocb->rw.ki_filp;
+ file_count = 1;
+ } else if (file == iocb->rw.ki_filp) {
+ file_count++;
+ } else {
+ fput_many(file, file_count);
+ file = iocb->rw.ki_filp;
+ file_count = 1;
+ }
if (evs && copy_to_user(evs + *nr_events, &iocb->ki_ev,
sizeof(iocb->ki_ev))) {
@@ -1352,6 +1366,9 @@ static long aio_iopoll_reap(struct kioctx *ctx, struct io_event __user *evs,
(*nr_events)++;
}
+ if (file)
+ fput_many(file, file_count);
+
if (to_free)
iocb_put_many(ctx, iocbs, &to_free);
@@ -1746,15 +1763,69 @@ struct aio_submit_state {
*/
struct list_head req_list;
unsigned int req_count;
+
+ /*
+ * File reference cache
+ */
+ struct file *file;
+ unsigned int fd;
+ unsigned int has_refs;
+ unsigned int used_refs;
+ unsigned int ios_left;
};
-static int aio_prep_rw(struct aio_kiocb *kiocb, const struct iocb *iocb)
+static void aio_file_put(struct aio_submit_state *state)
+{
+ if (state->file) {
+ int diff = state->has_refs - state->used_refs;
+
+ if (diff)
+ fput_many(state->file, diff);
+ state->file = NULL;
+ }
+}
+
+/*
+ * Get as many references to a file as we have IOs left in this submission,
+ * assuming most submissions are for one file, or at least that each file
+ * has more than one submission.
+ */
+static struct file *aio_file_get(struct aio_submit_state *state, int fd)
+{
+ if (!state)
+ return fget(fd);
+
+ if (!state->file) {
+get_file:
+ state->file = fget_many(fd, state->ios_left);
+ if (!state->file)
+ return NULL;
+
+ state->fd = fd;
+ state->has_refs = state->ios_left;
+ state->used_refs = 1;
+ state->ios_left--;
+ return state->file;
+ }
+
+ if (state->fd == fd) {
+ state->used_refs++;
+ state->ios_left--;
+ return state->file;
+ }
+
+ aio_file_put(state);
+ goto get_file;
+}
+
+static int aio_prep_rw(struct aio_kiocb *kiocb, const struct iocb *iocb,
+ struct aio_submit_state *state)
{
struct kioctx *ctx = kiocb->ki_ctx;
struct kiocb *req = &kiocb->rw;
int ret;
- req->ki_filp = fget(iocb->aio_fildes);
+ req->ki_filp = aio_file_get(state, iocb->aio_fildes);
if (unlikely(!req->ki_filp))
return -EBADF;
req->ki_pos = iocb->aio_offset;
@@ -1905,7 +1976,8 @@ static void aio_iopoll_iocb_issued(struct aio_submit_state *state,
}
static ssize_t aio_read(struct aio_kiocb *kiocb, const struct iocb *iocb,
- bool vectored, bool compat)
+ struct aio_submit_state *state, bool vectored,
+ bool compat)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *req = &kiocb->rw;
@@ -1913,7 +1985,7 @@ static ssize_t aio_read(struct aio_kiocb *kiocb, const struct iocb *iocb,
struct file *file;
ssize_t ret;
- ret = aio_prep_rw(kiocb, iocb);
+ ret = aio_prep_rw(kiocb, iocb, state);
if (ret)
return ret;
file = req->ki_filp;
@@ -1939,7 +2011,8 @@ static ssize_t aio_read(struct aio_kiocb *kiocb, const struct iocb *iocb,
}
static ssize_t aio_write(struct aio_kiocb *kiocb, const struct iocb *iocb,
- bool vectored, bool compat)
+ struct aio_submit_state *state, bool vectored,
+ bool compat)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *req = &kiocb->rw;
@@ -1947,7 +2020,7 @@ static ssize_t aio_write(struct aio_kiocb *kiocb, const struct iocb *iocb,
struct file *file;
ssize_t ret;
- ret = aio_prep_rw(kiocb, iocb);
+ ret = aio_prep_rw(kiocb, iocb, state);
if (ret)
return ret;
file = req->ki_filp;
@@ -2258,16 +2331,16 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
ret = -EINVAL;
switch (iocb->aio_lio_opcode) {
case IOCB_CMD_PREAD:
- ret = aio_read(req, iocb, false, compat);
+ ret = aio_read(req, iocb, state, false, compat);
break;
case IOCB_CMD_PWRITE:
- ret = aio_write(req, iocb, false, compat);
+ ret = aio_write(req, iocb, state, false, compat);
break;
case IOCB_CMD_PREADV:
- ret = aio_read(req, iocb, true, compat);
+ ret = aio_read(req, iocb, state, true, compat);
break;
case IOCB_CMD_PWRITEV:
- ret = aio_write(req, iocb, true, compat);
+ ret = aio_write(req, iocb, state, true, compat);
break;
case IOCB_CMD_FSYNC:
if (ctx->flags & IOCTX_FLAG_IOPOLL)
@@ -2359,17 +2432,20 @@ 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);
+ aio_file_put(state);
}
/*
* Start submission side cache.
*/
static void aio_submit_state_start(struct aio_submit_state *state,
- struct kioctx *ctx)
+ struct kioctx *ctx, int max_ios)
{
state->ctx = ctx;
INIT_LIST_HEAD(&state->req_list);
state->req_count = 0;
+ state->file = NULL;
+ state->ios_left = max_ios;
#ifdef CONFIG_BLOCK
state->plug_cb.callback = aio_state_unplug;
blk_start_plug(&state->plug);
@@ -2416,7 +2492,7 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
nr = ctx->nr_events;
if (nr > AIO_PLUG_THRESHOLD) {
- aio_submit_state_start(&state, ctx);
+ aio_submit_state_start(&state, ctx, nr);
statep = &state;
}
for (i = 0; i < nr; i++) {
@@ -2460,7 +2536,7 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
nr = ctx->nr_events;
if (nr > AIO_PLUG_THRESHOLD) {
- aio_submit_state_start(&state, ctx);
+ aio_submit_state_start(&state, ctx, nr);
statep = &state;
}
for (i = 0; i < nr; i++) {
--
2.17.1
