zram: fix synchronous reads

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/20230411171459.567614-17-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 24b31957d9e846413b0ca4ddd3ceede87fb0334b..a2b98100cbda8974f31f4589987c98cab83579ac 100644 (file)
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -55,7 +55,7 @@ static const struct block_device_operations zram_devops;
 
 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)
 {
@@ -576,31 +576,15 @@ static void free_block_bdev(struct zram *zram, unsigned long blk_idx)
        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);
 }
 
@@ -705,7 +689,7 @@ static ssize_t writeback_store(struct device *dev,
                /* 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);
@@ -785,18 +769,19 @@ struct zram_work {
        struct work_struct work;
        struct zram *zram;
        unsigned long entry;
-       struct bio *bio;
        struct page *page;
 };
 
 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_vec 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_struct *work)
  * 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);
@@ -823,13 +807,13 @@ static int read_from_bdev_sync(struct zram *zram, struct page *page,
 }
 
 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) {
+       if (!parent) {
                if (WARN_ON_ONCE(!IS_ENABLED(ZRAM_PARTIAL_IO)))
                        return -EIO;
-               return read_from_bdev_sync(zram, page, entry, parent);
+               return read_from_bdev_sync(zram, page, entry);
        }
        read_from_bdev_async(zram, page, entry, parent);
        return 1;
@@ -837,7 +821,7 @@ static int read_from_bdev(struct zram *zram, struct page *page,
 #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;
 }
@@ -1370,7 +1354,7 @@ static int zram_read_from_zspool(struct zram *zram, struct page *page,
 }
 
 static int zram_read_page(struct zram *zram, struct page *page, u32 index,
-                         struct bio *bio, bool partial_io)
+                         struct bio *parent)
 {
        int ret;
 
@@ -1387,7 +1371,7 @@ static int zram_read_page(struct zram *zram, struct page *page, u32 index,
                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. */
@@ -1402,14 +1386,14 @@ static int zram_read_page(struct zram *zram, struct page *page, u32 index,
  * 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);
@@ -1420,8 +1404,8 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
                          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)
@@ -1561,7 +1545,7 @@ static int zram_bvec_write_partial(struct zram *zram, struct bio_vec *bvec,
        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);