From: Andi Kleen <andi@firstfloor.org>
To: akpm@linux-foundation.org
Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
viro@zeniv.linux.org.uk, Andi Kleen <ak@linux.intel.com>
Subject: [PATCH 07/11] DIO: Merge direct_io_walker into __blockdev_direct_IO
Date: Mon, 29 Aug 2011 16:23:18 -0700 [thread overview]
Message-ID: <1314660202-661-8-git-send-email-andi@firstfloor.org> (raw)
In-Reply-To: <1314660202-661-1-git-send-email-andi@firstfloor.org>
From: Andi Kleen <ak@linux.intel.com>
This doesn't change anything for the compiler, but hch thought it would
make the code clearer.
I moved the reference counting into its own little inline.
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
fs/direct-io.c | 271 +++++++++++++++++++++++++++-----------------------------
1 files changed, 132 insertions(+), 139 deletions(-)
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 103a6fc..669b667 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1039,136 +1039,10 @@ out:
return ret;
}
-static inline ssize_t
-direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
- const struct iovec *iov, loff_t offset, unsigned long nr_segs,
- unsigned blkbits, get_block_t get_block, dio_iodone_t end_io,
- dio_submit_t submit_io, struct dio *dio, struct dio_submit *sdio)
+static inline int drop_refcount(struct dio *dio)
{
- unsigned long user_addr;
+ int ret2;
unsigned long flags;
- int seg;
- ssize_t ret = 0;
- ssize_t ret2;
- size_t bytes;
- struct buffer_head map_bh = { 0, };
-
- dio->inode = inode;
- dio->rw = rw;
- sdio->blkbits = blkbits;
- sdio->blkfactor = inode->i_blkbits - blkbits;
- sdio->block_in_file = offset >> blkbits;
-
- sdio->get_block = get_block;
- dio->end_io = end_io;
- sdio->submit_io = submit_io;
- sdio->final_block_in_bio = -1;
- sdio->next_block_for_io = -1;
-
- dio->iocb = iocb;
- dio->i_size = i_size_read(inode);
-
- spin_lock_init(&dio->bio_lock);
- dio->refcount = 1;
-
- /*
- * In case of non-aligned buffers, we may need 2 more
- * pages since we need to zero out first and last block.
- */
- if (unlikely(sdio->blkfactor))
- sdio->pages_in_io = 2;
-
- for (seg = 0; seg < nr_segs; seg++) {
- user_addr = (unsigned long)iov[seg].iov_base;
- sdio->pages_in_io +=
- ((user_addr+iov[seg].iov_len +PAGE_SIZE-1)/PAGE_SIZE
- - user_addr/PAGE_SIZE);
- }
-
- for (seg = 0; seg < nr_segs; seg++) {
- user_addr = (unsigned long)iov[seg].iov_base;
- sdio->size += bytes = iov[seg].iov_len;
-
- /* Index into the first page of the first block */
- sdio->first_block_in_page = (user_addr & ~PAGE_MASK) >> blkbits;
- sdio->final_block_in_request = sdio->block_in_file +
- (bytes >> blkbits);
- /* Page fetching state */
- sdio->head = 0;
- sdio->tail = 0;
- sdio->curr_page = 0;
-
- sdio->total_pages = 0;
- if (user_addr & (PAGE_SIZE-1)) {
- sdio->total_pages++;
- bytes -= PAGE_SIZE - (user_addr & (PAGE_SIZE - 1));
- }
- sdio->total_pages += (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
- sdio->curr_user_address = user_addr;
-
- ret = do_direct_IO(dio, sdio, &map_bh);
-
- dio->result += iov[seg].iov_len -
- ((sdio->final_block_in_request - sdio->block_in_file) <<
- blkbits);
-
- if (ret) {
- dio_cleanup(dio, sdio);
- break;
- }
- } /* end iovec loop */
-
- if (ret == -ENOTBLK) {
- /*
- * The remaining part of the request will be
- * be handled by buffered I/O when we return
- */
- ret = 0;
- }
- /*
- * There may be some unwritten disk at the end of a part-written
- * fs-block-sized block. Go zero that now.
- */
- dio_zero_block(dio, sdio, 1, &map_bh);
-
- if (sdio->cur_page) {
- ret2 = dio_send_cur_page(dio, sdio, &map_bh);
- if (ret == 0)
- ret = ret2;
- page_cache_release(sdio->cur_page);
- sdio->cur_page = NULL;
- }
- if (sdio->bio)
- dio_bio_submit(dio, sdio);
-
- /*
- * It is possible that, we return short IO due to end of file.
- * In that case, we need to release all the pages we got hold on.
- */
- dio_cleanup(dio, sdio);
-
- /*
- * All block lookups have been performed. For READ requests
- * we can let i_mutex go now that its achieved its purpose
- * of protecting us from looking up uninitialized blocks.
- */
- if (rw == READ && (dio->flags & DIO_LOCKING))
- mutex_unlock(&dio->inode->i_mutex);
-
- /*
- * The only time we want to leave bios in flight is when a successful
- * partial aio read or full aio write have been setup. In that case
- * bio completion will call aio_complete. The only time it's safe to
- * call aio_complete is when we return -EIOCBQUEUED, so we key on that.
- * This had *better* be the only place that raises -EIOCBQUEUED.
- */
- BUG_ON(ret == -EIOCBQUEUED);
- if (dio->is_async && ret == 0 && dio->result &&
- ((rw & READ) || (dio->result == sdio->size)))
- ret = -EIOCBQUEUED;
-
- if (ret != -EIOCBQUEUED)
- dio_await_completion(dio);
/*
* Sync will always be dropping the final ref and completing the
@@ -1184,14 +1058,7 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
spin_lock_irqsave(&dio->bio_lock, flags);
ret2 = --dio->refcount;
spin_unlock_irqrestore(&dio->bio_lock, flags);
-
- if (ret2 == 0) {
- ret = dio_complete(dio, offset, ret, false);
- kmem_cache_free(dio_cache, dio);
- } else
- BUG_ON(ret != -EIOCBQUEUED);
-
- return ret;
+ return ret2;
}
/*
@@ -1235,6 +1102,9 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
loff_t end = offset;
struct dio *dio;
struct dio_submit sdio = { 0, };
+ unsigned long user_addr;
+ size_t bytes;
+ struct buffer_head map_bh = { 0, };
if (rw & WRITE)
rw = WRITE_ODIRECT;
@@ -1312,9 +1182,132 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
dio->is_async = !is_sync_kiocb(iocb) && !((rw & WRITE) &&
(end > i_size_read(inode)));
- retval = direct_io_worker(rw, iocb, inode, iov, offset,
- nr_segs, blkbits, get_block, end_io,
- submit_io, dio, &sdio);
+ retval = 0;
+
+ dio->inode = inode;
+ dio->rw = rw;
+ sdio.blkbits = blkbits;
+ sdio.blkfactor = inode->i_blkbits - blkbits;
+ sdio.block_in_file = offset >> blkbits;
+
+ sdio.get_block = get_block;
+ dio->end_io = end_io;
+ sdio.submit_io = submit_io;
+ sdio.final_block_in_bio = -1;
+ sdio.next_block_for_io = -1;
+
+ dio->iocb = iocb;
+ dio->i_size = i_size_read(inode);
+
+ spin_lock_init(&dio->bio_lock);
+ dio->refcount = 1;
+
+ /*
+ * In case of non-aligned buffers, we may need 2 more
+ * pages since we need to zero out first and last block.
+ */
+ if (unlikely(sdio.blkfactor))
+ sdio.pages_in_io = 2;
+
+ for (seg = 0; seg < nr_segs; seg++) {
+ user_addr = (unsigned long)iov[seg].iov_base;
+ sdio.pages_in_io +=
+ ((user_addr+iov[seg].iov_len +PAGE_SIZE-1)/PAGE_SIZE
+ - user_addr/PAGE_SIZE);
+ }
+
+ for (seg = 0; seg < nr_segs; seg++) {
+ user_addr = (unsigned long)iov[seg].iov_base;
+ sdio.size += bytes = iov[seg].iov_len;
+
+ /* Index into the first page of the first block */
+ sdio.first_block_in_page = (user_addr & ~PAGE_MASK) >> blkbits;
+ sdio.final_block_in_request = sdio.block_in_file +
+ (bytes >> blkbits);
+ /* Page fetching state */
+ sdio.head = 0;
+ sdio.tail = 0;
+ sdio.curr_page = 0;
+
+ sdio.total_pages = 0;
+ if (user_addr & (PAGE_SIZE-1)) {
+ sdio.total_pages++;
+ bytes -= PAGE_SIZE - (user_addr & (PAGE_SIZE - 1));
+ }
+ sdio.total_pages += (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
+ sdio.curr_user_address = user_addr;
+
+ retval = do_direct_IO(dio, &sdio, &map_bh);
+
+ dio->result += iov[seg].iov_len -
+ ((sdio.final_block_in_request - sdio.block_in_file) <<
+ blkbits);
+
+ if (retval) {
+ dio_cleanup(dio, &sdio);
+ break;
+ }
+ } /* end iovec loop */
+
+ if (retval == -ENOTBLK) {
+ /*
+ * The remaining part of the request will be
+ * be handled by buffered I/O when we return
+ */
+ retval = 0;
+ }
+ /*
+ * There may be some unwritten disk at the end of a part-written
+ * fs-block-sized block. Go zero that now.
+ */
+ dio_zero_block(dio, &sdio, 1, &map_bh);
+
+ if (sdio.cur_page) {
+ ssize_t ret2;
+
+ ret2 = dio_send_cur_page(dio, &sdio, &map_bh);
+ if (retval == 0)
+ retval = ret2;
+ page_cache_release(sdio.cur_page);
+ sdio.cur_page = NULL;
+ }
+ if (sdio.bio)
+ dio_bio_submit(dio, &sdio);
+
+ /*
+ * It is possible that, we return short IO due to end of file.
+ * In that case, we need to release all the pages we got hold on.
+ */
+ dio_cleanup(dio, &sdio);
+
+ /*
+ * All block lookups have been performed. For READ requests
+ * we can let i_mutex go now that its achieved its purpose
+ * of protecting us from looking up uninitialized blocks.
+ */
+ if (rw == READ && (dio->flags & DIO_LOCKING))
+ mutex_unlock(&dio->inode->i_mutex);
+
+ /*
+ * The only time we want to leave bios in flight is when a successful
+ * partial aio read or full aio write have been setup. In that case
+ * bio completion will call aio_complete. The only time it's safe to
+ * call aio_complete is when we return -EIOCBQUEUED, so we key on that.
+ * This had *better* be the only place that raises -EIOCBQUEUED.
+ */
+ BUG_ON(retval == -EIOCBQUEUED);
+ if (dio->is_async && retval == 0 && dio->result &&
+ ((rw & READ) || (dio->result == sdio.size)))
+ retval = -EIOCBQUEUED;
+
+ if (retval != -EIOCBQUEUED)
+ dio_await_completion(dio);
+
+ if (drop_refcount(dio) == 0) {
+ retval = dio_complete(dio, offset, retval, false);
+ kmem_cache_free(dio_cache, dio);
+ } else
+ BUG_ON(retval != -EIOCBQUEUED);
out:
return retval;
--
1.7.4.4
next prev parent reply other threads:[~2011-08-29 23:26 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-08-29 23:23 Updated direct IO optimization patchkit v3 Andi Kleen
2011-08-29 23:23 ` [PATCH 01/11] DIO: Separate fields only used in the submission path from struct dio Andi Kleen
2011-08-29 23:23 ` [PATCH 02/11] DIO: Fix a wrong comment Andi Kleen
2011-08-29 23:23 ` [PATCH 03/11] DIO: Rearrange fields in dio/dio_submit to avoid holes Andi Kleen
2011-08-29 23:23 ` [PATCH 04/11] DIO: Use a slab cache for struct dio Andi Kleen
2011-08-29 23:23 ` [PATCH 05/11] DIO: Separate map_bh from dio v2 Andi Kleen
2011-08-29 23:23 ` [PATCH 06/11] DIO: Inline the complete submission path v2 Andi Kleen
2011-08-29 23:23 ` Andi Kleen [this message]
2011-08-29 23:23 ` [PATCH 08/11] DIO: Remove unnecessary dio argument from dio_pages_present() Andi Kleen
2011-08-29 23:23 ` [PATCH 09/11] DIO: Remove unused dio parameter from dio_bio_add_page Andi Kleen
2011-08-29 23:23 ` [PATCH 10/11] VFS: Cache request_queue in struct block_device Andi Kleen
2011-08-29 23:23 ` [PATCH 11/11] DIO: optimize cache misses in the submission path v2 Andi Kleen
-- strict thread matches above, loose matches on Subject: below --
2011-08-02 4:38 Updated direct IO optimization patchkit v2 Andi Kleen
2011-08-02 4:38 ` [PATCH 07/11] DIO: Merge direct_io_walker into __blockdev_direct_IO Andi Kleen
2011-08-08 18:20 ` Jeff Moyer
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=1314660202-661-8-git-send-email-andi@firstfloor.org \
--to=andi@firstfloor.org \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@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