The patch titled
Subject: zram: fix synchronous reads
has been added to the -mm mm-unstable branch. Its filename is
zram-fix-synchronous-reads.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/zram-fix-synchronous-reads.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Christoph Hellwig <hch@xxxxxx>
Subject: zram: fix synchronous reads
Date: Thu, 6 Apr 2023 16:41:01 +0200
Currently nothing waits for the synchronous reads before accessing the
data. Switch them to an on-stack bio and submit_bio_wait to make sure the
I/O has actually completed when the work item has been flushed. This also
removes the call to page_endio that would unlock a page that has never
been locked.
Drop the partial_io/sync flag, as chaining only makes sense for the
asynchronous reads of the entire page.
Link: https://lkml.kernel.org/r/20230406144102.149231-16-hch@xxxxxx
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: Sergey Senozhatsky <senozhatsky@xxxxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/block/zram/zram_drv.c | 64 ++++++++++++--------------------
1 file changed, 24 insertions(+), 40 deletions(-)
--- a/drivers/block/zram/zram_drv.c~zram-fix-synchronous-reads
+++ a/drivers/block/zram/zram_drv.c
@@ -55,7 +55,7 @@ static const struct block_device_operati
static void zram_free_page(struct zram *zram, size_t index);
static int zram_read_page(struct zram *zram, struct page *page, u32 index,
- struct bio *bio, bool partial_io);
+ struct bio *parent);
static int zram_slot_trylock(struct zram *zram, u32 index)
{
@@ -575,31 +575,15 @@ static void free_block_bdev(struct zram
atomic64_dec(&zram->stats.bd_count);
}
-static void zram_page_end_io(struct bio *bio)
-{
- struct page *page = bio_first_page_all(bio);
-
- page_endio(page, op_is_write(bio_op(bio)),
- blk_status_to_errno(bio->bi_status));
- bio_put(bio);
-}
-
static void read_from_bdev_async(struct zram *zram, struct page *page,
unsigned long entry, struct bio *parent)
{
struct bio *bio;
- bio = bio_alloc(zram->bdev, 1, parent ? parent->bi_opf : REQ_OP_READ,
- GFP_NOIO);
-
+ bio = bio_alloc(zram->bdev, 1, parent->bi_opf, GFP_NOIO);
bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
__bio_add_page(bio, page, PAGE_SIZE, 0);
-
- if (!parent)
- bio->bi_end_io = zram_page_end_io;
- else
- bio_chain(bio, parent);
-
+ bio_chain(bio, parent);
submit_bio(bio);
}
@@ -704,7 +688,7 @@ static ssize_t writeback_store(struct de
/* Need for hugepage writeback racing */
zram_set_flag(zram, index, ZRAM_IDLE);
zram_slot_unlock(zram, index);
- if (zram_read_page(zram, page, index, NULL, false)) {
+ if (zram_read_page(zram, page, index, NULL)) {
zram_slot_lock(zram, index);
zram_clear_flag(zram, index, ZRAM_UNDER_WB);
zram_clear_flag(zram, index, ZRAM_IDLE);
@@ -780,23 +764,24 @@ release_init_lock:
return ret;
}
+#if PAGE_SIZE != 4096
struct zram_work {
struct work_struct work;
struct zram *zram;
unsigned long entry;
- struct bio *bio;
struct page *page;
};
-#if PAGE_SIZE != 4096
static void zram_sync_read(struct work_struct *work)
{
struct zram_work *zw = container_of(work, struct zram_work, work);
- struct zram *zram = zw->zram;
- unsigned long entry = zw->entry;
- struct bio *bio = zw->bio;
+ struct bio_bvec bv;
+ struct bio bio;
- read_from_bdev_async(zram, zw->page, entry, bio);
+ bio_init(&bio, zw->zram->bdev, &bv, 1, REQ_OP_READ);
+ bio.bi_iter.bi_sector = zw->entry * (PAGE_SIZE >> 9);
+ __bio_add_page(&bio, zw->page, PAGE_SIZE, 0);
+ submit_bio_wait(&bio);
}
/*
@@ -805,14 +790,13 @@ static void zram_sync_read(struct work_s
* use a worker thread context.
*/
static int read_from_bdev_sync(struct zram *zram, struct page *page,
- unsigned long entry, struct bio *bio)
+ unsigned long entry)
{
struct zram_work work;
work.page = page;
work.zram = zram;
work.entry = entry;
- work.bio = bio;
INIT_WORK_ONSTACK(&work.work, zram_sync_read);
queue_work(system_unbound_wq, &work.work);
@@ -823,7 +807,7 @@ static int read_from_bdev_sync(struct zr
}
#else
static int read_from_bdev_sync(struct zram *zram, struct page *page,
- unsigned long entry, struct bio *bio)
+ unsigned long entry)
{
WARN_ON(1);
return -EIO;
@@ -831,18 +815,18 @@ static int read_from_bdev_sync(struct zr
#endif
static int read_from_bdev(struct zram *zram, struct page *page,
- unsigned long entry, struct bio *parent, bool sync)
+ unsigned long entry, struct bio *parent)
{
atomic64_inc(&zram->stats.bd_reads);
- if (sync)
- return read_from_bdev_sync(zram, page, entry, parent);
+ if (!parent)
+ return read_from_bdev_sync(zram, page, entry);
read_from_bdev_async(zram, page, entry, parent);
return 1;
}
#else
static inline void reset_bdev(struct zram *zram) {};
static int read_from_bdev(struct zram *zram, struct page *page,
- unsigned long entry, struct bio *parent, bool sync)
+ unsigned long entry, struct bio *parent)
{
return -EIO;
}
@@ -1375,7 +1359,7 @@ static int zram_read_from_zspool(struct
}
static int zram_read_page(struct zram *zram, struct page *page, u32 index,
- struct bio *bio, bool partial_io)
+ struct bio *parent)
{
int ret;
@@ -1392,7 +1376,7 @@ static int zram_read_page(struct zram *z
zram_slot_unlock(zram, index);
ret = read_from_bdev(zram, page, zram_get_element(zram, index),
- bio, partial_io);
+ parent);
}
/* Should NEVER happen. Return bio error if it does. */
@@ -1407,14 +1391,14 @@ static int zram_read_page(struct zram *z
* always expects a full page for the output.
*/
static int zram_bvec_read_partial(struct zram *zram, struct bio_vec *bvec,
- u32 index, int offset, struct bio *bio)
+ u32 index, int offset)
{
struct page *page = alloc_page(GFP_NOIO);
int ret;
if (!page)
return -ENOMEM;
- ret = zram_read_page(zram, page, index, bio, true);
+ ret = zram_read_page(zram, page, index, NULL);
if (likely(!ret))
memcpy_to_bvec(bvec, page_address(page) + offset);
__free_page(page);
@@ -1425,8 +1409,8 @@ static int zram_bvec_read(struct zram *z
u32 index, int offset, struct bio *bio)
{
if (is_partial_io(bvec))
- return zram_bvec_read_partial(zram, bvec, index, offset, bio);
- return zram_read_page(zram, bvec->bv_page, index, bio, false);
+ return zram_bvec_read_partial(zram, bvec, index, offset);
+ return zram_read_page(zram, bvec->bv_page, index, bio);
}
static int zram_write_page(struct zram *zram, struct page *page, u32 index)
@@ -1566,7 +1550,7 @@ static int zram_bvec_write_partial(struc
if (!page)
return -ENOMEM;
- ret = zram_read_page(zram, page, index, bio, true);
+ ret = zram_read_page(zram, page, index, bio);
if (!ret) {
memcpy_from_bvec(page_address(page) + offset, bvec);
ret = zram_write_page(zram, page, index);
_
Patches currently in -mm which might be from hch@xxxxxx are
zram-remove-valid_io_request.patch
zram-make-zram_bio_discard-more-self-contained.patch
zram-simplify-bvec-iteration-in-__zram_make_request.patch
zram-move-discard-handling-to-zram_submit_bio.patch
zram-return-early-on-error-in-zram_bvec_rw.patch
zram-refactor-highlevel-read-and-write-handling.patch
zram-dont-use-highmem-for-the-bounce-buffer-in-zram_bvec_readwrite.patch
zram-rename-__zram_bvec_read-to-zram_read_page.patch
zram-directly-call-zram_read_page-in-writeback_store.patch
zram-refactor-zram_bdev_read.patch
zram-dont-pass-a-bvec-to-__zram_bvec_write.patch
zram-refactor-zram_bdev_write.patch
zram-pass-a-page-to-read_from_bdev.patch
zram-dont-return-errors-from-read_from_bdev_async.patch
zram-fix-synchronous-reads.patch
zram-return-errors-from-read_from_bdev_sync.patch
