summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-08-02 13:27:23 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-08-02 13:27:23 -0700
commit98e247464088a11ce2328a214fdb87d4c06f8db6 (patch)
tree1f876a9b06b189855adfbefd1da6b6753effd1bb /mm
parentb349b1181d24af1c151134a3c39725e94a5619dd (diff)
parent0dd316ba8692c2374fbb82cce57c0b23144f2977 (diff)
Merge tag 'for-5.20/io_uring-buffered-writes-2022-07-29' of git://git.kernel.dk/linux-block
Pull io_uring buffered writes support from Jens Axboe: "This contains support for buffered writes, specifically for XFS. btrfs is in progress, will be coming in the next release. io_uring does support buffered writes on any file type, but since the buffered write path just always -EAGAIN (or -EOPNOTSUPP) any attempt to do so if IOCB_NOWAIT is set, any buffered write will effectively be handled by io-wq offload. This isn't very efficient, and we even have specific code in io-wq to serialize buffered writes to the same inode to avoid further inefficiencies with thread offload. This is particularly sad since most buffered writes don't block, they simply copy data to a page and dirty it. With this pull request, we can handle buffered writes a lot more effiently. If balance_dirty_pages() needs to block, we back off on writes as indicated. This improves buffered write support by 2-3x. Jan Kara helped with the mm bits for this, and Stefan handled the fs/iomap/xfs/io_uring parts of it" * tag 'for-5.20/io_uring-buffered-writes-2022-07-29' of git://git.kernel.dk/linux-block: mm: honor FGP_NOWAIT for page cache page allocation xfs: Add async buffered write support xfs: Specify lockmode when calling xfs_ilock_for_iomap() io_uring: Add tracepoint for short writes io_uring: fix issue with io_write() not always undoing sb_start_write() io_uring: Add support for async buffered writes fs: Add async write file modification handling. fs: Split off inode_needs_update_time and __file_update_time fs: add __remove_file_privs() with flags parameter fs: add a FMODE_BUF_WASYNC flags for f_mode iomap: Return -EAGAIN from iomap_write_iter() iomap: Add async buffered write support iomap: Add flags parameter to iomap_page_create() mm: Add balance_dirty_pages_ratelimited_flags() function mm: Move updates of dirty_exceeded into one place mm: Move starting of background writeback into the main balancing loop
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c4
-rw-r--r--mm/page-writeback.c89
2 files changed, 61 insertions, 32 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index ffdfbc8b0e3c..254931a6e3ed 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1988,6 +1988,10 @@ no_page:
gfp |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
gfp &= ~__GFP_FS;
+ if (fgp_flags & FGP_NOWAIT) {
+ gfp &= ~GFP_KERNEL;
+ gfp |= GFP_NOWAIT | __GFP_NOWARN;
+ }
folio = filemap_alloc_folio(gfp, 0);
if (!folio)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 55c2776ae699..d0d466a5c804 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1554,8 +1554,8 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
* If we're over `background_thresh' then the writeback threads are woken to
* perform some writeout.
*/
-static void balance_dirty_pages(struct bdi_writeback *wb,
- unsigned long pages_dirtied)
+static int balance_dirty_pages(struct bdi_writeback *wb,
+ unsigned long pages_dirtied, unsigned int flags)
{
struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) };
struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) };
@@ -1575,6 +1575,7 @@ static void balance_dirty_pages(struct bdi_writeback *wb,
struct backing_dev_info *bdi = wb->bdi;
bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
unsigned long start_time = jiffies;
+ int ret = 0;
for (;;) {
unsigned long now = jiffies;
@@ -1628,6 +1629,19 @@ static void balance_dirty_pages(struct bdi_writeback *wb,
}
/*
+ * In laptop mode, we wait until hitting the higher threshold
+ * before starting background writeout, and then write out all
+ * the way down to the lower threshold. So slow writers cause
+ * minimal disk activity.
+ *
+ * In normal mode, we start background writeout at the lower
+ * background_thresh, to keep the amount of dirty memory low.
+ */
+ if (!laptop_mode && nr_reclaimable > gdtc->bg_thresh &&
+ !writeback_in_progress(wb))
+ wb_start_background_writeback(wb);
+
+ /*
* Throttle it only when the background writeback cannot
* catch-up. This avoids (excessively) small writeouts
* when the wb limits are ramping up in case of !strictlimit.
@@ -1657,6 +1671,7 @@ free_running:
break;
}
+ /* Start writeback even when in laptop mode */
if (unlikely(!writeback_in_progress(wb)))
wb_start_background_writeback(wb);
@@ -1715,8 +1730,8 @@ free_running:
sdtc = mdtc;
}
- if (dirty_exceeded && !wb->dirty_exceeded)
- wb->dirty_exceeded = 1;
+ if (dirty_exceeded != wb->dirty_exceeded)
+ wb->dirty_exceeded = dirty_exceeded;
if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) +
BANDWIDTH_INTERVAL))
@@ -1789,6 +1804,10 @@ pause:
period,
pause,
start_time);
+ if (flags & BDP_ASYNC) {
+ ret = -EAGAIN;
+ break;
+ }
__set_current_state(TASK_KILLABLE);
wb->dirty_sleep = now;
io_schedule_timeout(pause);
@@ -1820,26 +1839,7 @@ pause:
if (fatal_signal_pending(current))
break;
}
-
- if (!dirty_exceeded && wb->dirty_exceeded)
- wb->dirty_exceeded = 0;
-
- if (writeback_in_progress(wb))
- return;
-
- /*
- * In laptop mode, we wait until hitting the higher threshold before
- * starting background writeout, and then write out all the way down
- * to the lower threshold. So slow writers cause minimal disk activity.
- *
- * In normal mode, we start background writeout at the lower
- * background_thresh, to keep the amount of dirty memory low.
- */
- if (laptop_mode)
- return;
-
- if (nr_reclaimable > gdtc->bg_thresh)
- wb_start_background_writeback(wb);
+ return ret;
}
static DEFINE_PER_CPU(int, bdp_ratelimits);
@@ -1861,27 +1861,34 @@ static DEFINE_PER_CPU(int, bdp_ratelimits);
DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
/**
- * balance_dirty_pages_ratelimited - balance dirty memory state
- * @mapping: address_space which was dirtied
+ * balance_dirty_pages_ratelimited_flags - Balance dirty memory state.
+ * @mapping: address_space which was dirtied.
+ * @flags: BDP flags.
*
* Processes which are dirtying memory should call in here once for each page
* which was newly dirtied. The function will periodically check the system's
* dirty state and will initiate writeback if needed.
*
- * Once we're over the dirty memory limit we decrease the ratelimiting
- * by a lot, to prevent individual processes from overshooting the limit
- * by (ratelimit_pages) each.
+ * See balance_dirty_pages_ratelimited() for details.
+ *
+ * Return: If @flags contains BDP_ASYNC, it may return -EAGAIN to
+ * indicate that memory is out of balance and the caller must wait
+ * for I/O to complete. Otherwise, it will return 0 to indicate
+ * that either memory was already in balance, or it was able to sleep
+ * until the amount of dirty memory returned to balance.
*/
-void balance_dirty_pages_ratelimited(struct address_space *mapping)
+int balance_dirty_pages_ratelimited_flags(struct address_space *mapping,
+ unsigned int flags)
{
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
struct bdi_writeback *wb = NULL;
int ratelimit;
+ int ret = 0;
int *p;
if (!(bdi->capabilities & BDI_CAP_WRITEBACK))
- return;
+ return ret;
if (inode_cgwb_enabled(inode))
wb = wb_get_create_current(bdi, GFP_KERNEL);
@@ -1921,9 +1928,27 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping)
preempt_enable();
if (unlikely(current->nr_dirtied >= ratelimit))
- balance_dirty_pages(wb, current->nr_dirtied);
+ ret = balance_dirty_pages(wb, current->nr_dirtied, flags);
wb_put(wb);
+ return ret;
+}
+
+/**
+ * balance_dirty_pages_ratelimited - balance dirty memory state.
+ * @mapping: address_space which was dirtied.
+ *
+ * Processes which are dirtying memory should call in here once for each page
+ * which was newly dirtied. The function will periodically check the system's
+ * dirty state and will initiate writeback if needed.
+ *
+ * Once we're over the dirty memory limit we decrease the ratelimiting
+ * by a lot, to prevent individual processes from overshooting the limit
+ * by (ratelimit_pages) each.
+ */
+void balance_dirty_pages_ratelimited(struct address_space *mapping)
+{
+ balance_dirty_pages_ratelimited_flags(mapping, 0);
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited);