The patch titled
Subject: aio: kill ki_retry
has been added to the -mm tree. Its filename is
aio-kill-ki_retry.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Kent Overstreet <koverstreet@xxxxxxxxxx>
Subject: aio: kill ki_retry
Thanks to Zach Brown's work to rip out the retry infrastructure, we don't
need this anymore - ki_retry was only called right after the kiocb was
initialized.
This also refactors and trims some duplicated code, as well as cleaning up
the refcounting/error handling a bit.
[akpm@xxxxxxxxxxxxxxxxxxxx: use fmode_t in aio_run_iocb()]
Signed-off-by: Kent Overstreet <koverstreet@xxxxxxxxxx>
Cc: Zach Brown <zab@xxxxxxxxxx>
Cc: Felipe Balbi <balbi@xxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Mark Fasheh <mfasheh@xxxxxxxx>
Cc: Joel Becker <jlbec@xxxxxxxxxxxx>
Cc: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Asai Thambi S P <asamymuthupa@xxxxxxxxxx>
Cc: Selvan Mani <smani@xxxxxxxxxx>
Cc: Sam Bradshaw <sbradshaw@xxxxxxxxxx>
Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Benjamin LaHaise <bcrl@xxxxxxxxx>
Cc: Theodore Ts'o <tytso@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/aio.c | 218 +++++++++++++++---------------------------
include/linux/aio.h | 26 -----
2 files changed, 82 insertions(+), 162 deletions(-)
diff -puN fs/aio.c~aio-kill-ki_retry fs/aio.c
--- a/fs/aio.c~aio-kill-ki_retry
+++ a/fs/aio.c
@@ -1005,24 +1005,15 @@ static void aio_advance_iovec(struct kio
BUG_ON(ret > 0 && iocb->ki_left == 0);
}
-static ssize_t aio_rw_vect_retry(struct kiocb *iocb)
+typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
+ unsigned long, loff_t);
+
+static ssize_t aio_rw_vect_retry(struct kiocb *iocb, int rw, aio_rw_op *rw_op)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
- ssize_t (*rw_op)(struct kiocb *, const struct iovec *,
- unsigned long, loff_t);
ssize_t ret = 0;
- unsigned short opcode;
-
- if ((iocb->ki_opcode == IOCB_CMD_PREADV) ||
- (iocb->ki_opcode == IOCB_CMD_PREAD)) {
- rw_op = file->f_op->aio_read;
- opcode = IOCB_CMD_PREADV;
- } else {
- rw_op = file->f_op->aio_write;
- opcode = IOCB_CMD_PWRITEV;
- }
/* This matches the pread()/pwrite() logic */
if (iocb->ki_pos < 0)
@@ -1038,7 +1029,7 @@ static ssize_t aio_rw_vect_retry(struct
/* retry all partial writes. retry partial reads as long as its a
* regular file. */
} while (ret > 0 && iocb->ki_left > 0 &&
- (opcode == IOCB_CMD_PWRITEV ||
+ (rw == WRITE ||
(!S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode))));
/* This means we must have transferred all that we could */
@@ -1048,7 +1039,7 @@ static ssize_t aio_rw_vect_retry(struct
/* If we managed to write some out we return that, rather than
* the eventual error. */
- if (opcode == IOCB_CMD_PWRITEV
+ if (rw == WRITE
&& ret < 0 && ret != -EIOCBQUEUED
&& iocb->ki_nbytes - iocb->ki_left)
ret = iocb->ki_nbytes - iocb->ki_left;
@@ -1056,73 +1047,41 @@ static ssize_t aio_rw_vect_retry(struct
return ret;
}
-static ssize_t aio_fdsync(struct kiocb *iocb)
-{
- struct file *file = iocb->ki_filp;
- ssize_t ret = -EINVAL;
-
- if (file->f_op->aio_fsync)
- ret = file->f_op->aio_fsync(iocb, 1);
- return ret;
-}
-
-static ssize_t aio_fsync(struct kiocb *iocb)
-{
- struct file *file = iocb->ki_filp;
- ssize_t ret = -EINVAL;
-
- if (file->f_op->aio_fsync)
- ret = file->f_op->aio_fsync(iocb, 0);
- return ret;
-}
-
-static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat)
+static ssize_t aio_setup_vectored_rw(int rw, struct kiocb *kiocb, bool compat)
{
ssize_t ret;
+ kiocb->ki_nr_segs = kiocb->ki_nbytes;
+
#ifdef CONFIG_COMPAT
if (compat)
- ret = compat_rw_copy_check_uvector(type,
+ ret = compat_rw_copy_check_uvector(rw,
(struct compat_iovec __user *)kiocb->ki_buf,
- kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
+ kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
&kiocb->ki_iovec);
else
#endif
- ret = rw_copy_check_uvector(type,
+ ret = rw_copy_check_uvector(rw,
(struct iovec __user *)kiocb->ki_buf,
- kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
+ kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
&kiocb->ki_iovec);
if (ret < 0)
- goto out;
-
- ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret);
- if (ret < 0)
- goto out;
+ return ret;
- kiocb->ki_nr_segs = kiocb->ki_nbytes;
- kiocb->ki_cur_seg = 0;
- /* ki_nbytes/left now reflect bytes instead of segs */
+ /* ki_nbytes now reflect bytes instead of segs */
kiocb->ki_nbytes = ret;
- kiocb->ki_left = ret;
-
- ret = 0;
-out:
- return ret;
+ return 0;
}
-static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb)
+static ssize_t aio_setup_single_vector(int rw, struct kiocb *kiocb)
{
- int bytes;
-
- bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left);
- if (bytes < 0)
- return bytes;
+ if (unlikely(!access_ok(!rw, kiocb->ki_buf, kiocb->ki_nbytes)))
+ return -EFAULT;
kiocb->ki_iovec = &kiocb->ki_inline_vec;
kiocb->ki_iovec->iov_base = kiocb->ki_buf;
- kiocb->ki_iovec->iov_len = bytes;
+ kiocb->ki_iovec->iov_len = kiocb->ki_nbytes;
kiocb->ki_nr_segs = 1;
- kiocb->ki_cur_seg = 0;
return 0;
}
@@ -1131,81 +1090,81 @@ static ssize_t aio_setup_single_vector(i
* Performs the initial checks and aio retry method
* setup for the kiocb at the time of io submission.
*/
-static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
+static ssize_t aio_run_iocb(struct kiocb *req, bool compat)
{
- struct file *file = kiocb->ki_filp;
- ssize_t ret = 0;
+ struct file *file = req->ki_filp;
+ ssize_t ret;
+ int rw;
+ fmode_t mode;
+ aio_rw_op *rw_op;
- switch (kiocb->ki_opcode) {
+ switch (req->ki_opcode) {
case IOCB_CMD_PREAD:
- ret = -EBADF;
- if (unlikely(!(file->f_mode & FMODE_READ)))
- break;
- ret = -EFAULT;
- if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf,
- kiocb->ki_left)))
- break;
- ret = aio_setup_single_vector(READ, file, kiocb);
- if (ret)
- break;
- ret = -EINVAL;
- if (file->f_op->aio_read)
- kiocb->ki_retry = aio_rw_vect_retry;
- break;
- case IOCB_CMD_PWRITE:
- ret = -EBADF;
- if (unlikely(!(file->f_mode & FMODE_WRITE)))
- break;
- ret = -EFAULT;
- if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf,
- kiocb->ki_left)))
- break;
- ret = aio_setup_single_vector(WRITE, file, kiocb);
- if (ret)
- break;
- ret = -EINVAL;
- if (file->f_op->aio_write)
- kiocb->ki_retry = aio_rw_vect_retry;
- break;
case IOCB_CMD_PREADV:
- ret = -EBADF;
- if (unlikely(!(file->f_mode & FMODE_READ)))
- break;
- ret = aio_setup_vectored_rw(READ, kiocb, compat);
- if (ret)
- break;
- ret = -EINVAL;
- if (file->f_op->aio_read)
- kiocb->ki_retry = aio_rw_vect_retry;
- break;
+ mode = FMODE_READ;
+ rw = READ;
+ rw_op = file->f_op->aio_read;
+ goto rw_common;
+
+ case IOCB_CMD_PWRITE:
case IOCB_CMD_PWRITEV:
- ret = -EBADF;
- if (unlikely(!(file->f_mode & FMODE_WRITE)))
- break;
- ret = aio_setup_vectored_rw(WRITE, kiocb, compat);
+ mode = FMODE_WRITE;
+ rw = WRITE;
+ rw_op = file->f_op->aio_write;
+ goto rw_common;
+rw_common:
+ if (unlikely(!(file->f_mode & mode)))
+ return -EBADF;
+
+ if (!rw_op)
+ return -EINVAL;
+
+ ret = (req->ki_opcode == IOCB_CMD_PREADV ||
+ req->ki_opcode == IOCB_CMD_PWRITEV)
+ ? aio_setup_vectored_rw(rw, req, compat)
+ : aio_setup_single_vector(rw, req);
if (ret)
- break;
- ret = -EINVAL;
- if (file->f_op->aio_write)
- kiocb->ki_retry = aio_rw_vect_retry;
+ return ret;
+
+ ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
+ if (ret < 0)
+ return ret;
+
+ req->ki_nbytes = ret;
+ req->ki_left = ret;
+
+ ret = aio_rw_vect_retry(req, rw, rw_op);
break;
+
case IOCB_CMD_FDSYNC:
- ret = -EINVAL;
- if (file->f_op->aio_fsync)
- kiocb->ki_retry = aio_fdsync;
+ if (!file->f_op->aio_fsync)
+ return -EINVAL;
+
+ ret = file->f_op->aio_fsync(req, 1);
break;
+
case IOCB_CMD_FSYNC:
- ret = -EINVAL;
- if (file->f_op->aio_fsync)
- kiocb->ki_retry = aio_fsync;
+ if (!file->f_op->aio_fsync)
+ return -EINVAL;
+
+ ret = file->f_op->aio_fsync(req, 0);
break;
+
default:
pr_debug("EINVAL: no operation provided\n");
- ret = -EINVAL;
+ return -EINVAL;
}
- if (!kiocb->ki_retry)
- return ret;
+ if (ret != -EIOCBQUEUED) {
+ /*
+ * There's no easy way to restart the syscall since other AIO's
+ * may be already running. Just fail this IO with EINTR.
+ */
+ if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
+ ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK))
+ ret = -EINTR;
+ aio_complete(req, ret, 0);
+ }
return 0;
}
@@ -1232,7 +1191,7 @@ static int io_submit_one(struct kioctx *
return -EINVAL;
}
- req = aio_get_req(ctx); /* returns with 2 references to req */
+ req = aio_get_req(ctx);
if (unlikely(!req))
return -EAGAIN;
@@ -1271,25 +1230,12 @@ static int io_submit_one(struct kioctx *
req->ki_left = req->ki_nbytes = iocb->aio_nbytes;
req->ki_opcode = iocb->aio_lio_opcode;
- ret = aio_setup_iocb(req, compat);
+ ret = aio_run_iocb(req, compat);
if (ret)
goto out_put_req;
- ret = req->ki_retry(req);
- if (ret != -EIOCBQUEUED) {
- /*
- * There's no easy way to restart the syscall since other AIO's
- * may be already running. Just fail this IO with EINTR.
- */
- if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
- ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK))
- ret = -EINTR;
- aio_complete(req, ret, 0);
- }
-
aio_put_req(req); /* drop extra ref to req */
return 0;
-
out_put_req:
put_reqs_available(ctx, 1);
aio_put_req(req); /* drop extra ref to req */
diff -puN include/linux/aio.h~aio-kill-ki_retry include/linux/aio.h
--- a/include/linux/aio.h~aio-kill-ki_retry
+++ a/include/linux/aio.h
@@ -29,38 +29,12 @@ struct kiocb;
typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *);
-/* is there a better place to document function pointer methods? */
-/**
- * ki_retry - iocb forward progress callback
- * @kiocb: The kiocb struct to advance by performing an operation.
- *
- * This callback is called when the AIO core wants a given AIO operation
- * to make forward progress. The kiocb argument describes the operation
- * that is to be performed. As the operation proceeds, perhaps partially,
- * ki_retry is expected to update the kiocb with progress made. Typically
- * ki_retry is set in the AIO core and it itself calls file_operations
- * helpers.
- *
- * ki_retry's return value determines when the AIO operation is completed
- * and an event is generated in the AIO event ring. Except the special
- * return values described below, the value that is returned from ki_retry
- * is transferred directly into the completion ring as the operation's
- * resulting status. Once this has happened ki_retry *MUST NOT* reference
- * the kiocb pointer again.
- *
- * If ki_retry returns -EIOCBQUEUED it has made a promise that aio_complete()
- * will be called on the kiocb pointer in the future. The AIO core will
- * not ask the method again -- ki_retry must ensure forward progress.
- * aio_complete() must be called once and only once in the future, multiple
- * calls may result in undefined behaviour.
- */
struct kiocb {
atomic_t ki_users;
struct file *ki_filp;
struct kioctx *ki_ctx; /* NULL for sync ops */
kiocb_cancel_fn *ki_cancel;
- ssize_t (*ki_retry)(struct kiocb *);
void (*ki_dtor)(struct kiocb *);
union {
_
Patches currently in -mm which might be from koverstreet@xxxxxxxxxx are
mm-remove-old-aio-use_mm-comment.patch
aio-remove-dead-code-from-aioh.patch
gadget-remove-only-user-of-aio-retry.patch
aio-remove-retry-based-aio.patch
char-add-aio_readwrite-to-dev-nullzero.patch
aio-kill-return-value-of-aio_complete.patch
aio-add-kiocb_cancel.patch
aio-move-private-stuff-out-of-aioh.patch
aio-dprintk-pr_debug.patch
aio-do-fget-after-aio_get_req.patch
aio-make-aio_put_req-lockless.patch
aio-refcounting-cleanup.patch
wait-add-wait_event_hrtimeout.patch
aio-make-aio_read_evt-more-efficient-convert-to-hrtimers.patch
aio-use-flush_dcache_page.patch
aio-use-cancellation-list-lazily.patch
aio-change-reqs_active-to-include-unreaped-completions.patch
aio-kill-batch-allocation.patch
aio-kill-struct-aio_ring_info.patch
aio-give-shared-kioctx-fields-their-own-cachelines.patch
aio-reqs_active-reqs_available.patch
aio-percpu-reqs_available.patch
generic-dynamic-per-cpu-refcounting.patch
aio-percpu-ioctx-refcount.patch
aio-use-xchg-instead-of-completion_lock.patch
aio-dont-include-aioh-in-schedh.patch
aio-kill-ki_key.patch
aio-kill-ki_retry.patch
block-prep-work-for-batch-completion.patch
block-aio-batch-completion-for-bios-kiocbs.patch
virtio-blk-convert-to-batch-completion.patch
mtip32xx-convert-to-batch-completion.patch
aio-fix-kioctx-not-being-freed-after-cancellation-at-exit-time.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
