BACKPORT: zram: read page from backing device

This patch enables read IO from backing device.  For the feature, it
implements two IO read functions to transfer data from backing storage.

One is asynchronous IO function and other is synchronous one.

A reason I need synchrnous IO is due to partial write which need to
complete read IO before the overwriting partial data.

We can make the partial IO's case asynchronous, too but at the moment, I
don't feel adding more complexity to support such rare use cases so want
to go with simple.

[xieyisheng1@huawei.com: read_from_bdev_async(): return 1 to avoid call page_endio() in zram_rw_page()]
Link: http://lkml.kernel.org/r/1502707447-6944-1-git-send-email-xieyisheng1@huawei.com
Link: http://lkml.kernel.org/r/1498459987-24562-9-git-send-email-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Yisheng Xie <xieyisheng1@huawei.com>
Cc: Juneho Choi <juno.choi@lge.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(cherry picked from commit 8e654f8fbff52ac483fb69957222853d7e2fc588)
Signed-off-by: Peter Kalauskas <peskal@google.com>
Bug: 112488418
Change-Id: Ia82f5fc4697aacc723a336e4dad4e7bc56a1bdb9

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index a0838669b5893b165ec5a51f9b3e558601353926..656495d61998ac1d339e29b70ed81daf6bfc26fc 100644 (file)
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -460,6 +460,95 @@ void zram_page_end_io(struct bio *bio)
        bio_put(bio);
 }
 
+/*
+ * Returns 1 if the submission is successful.
+ */
+static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
+                       unsigned long entry, struct bio *parent)
+{
+       struct bio *bio;
+
+       bio = bio_alloc(GFP_ATOMIC, 1);
+       if (!bio)
+               return -ENOMEM;
+
+       bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
+       bio->bi_bdev = zram->bdev;
+       if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) {
+               bio_put(bio);
+               return -EIO;
+       }
+
+       if (!parent) {
+               bio->bi_rw = 0;
+               bio->bi_end_io = zram_page_end_io;
+       } else {
+               bio->bi_rw = parent->bi_rw;
+               bio_chain(bio, parent);
+       }
+
+       submit_bio(READ, bio);
+       return 1;
+}
+
+struct zram_work {
+       struct work_struct work;
+       struct zram *zram;
+       unsigned long entry;
+       struct bio *bio;
+};
+
+#if PAGE_SIZE != 4096
+static void zram_sync_read(struct work_struct *work)
+{
+       struct bio_vec bvec;
+       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;
+
+       read_from_bdev_async(zram, &bvec, entry, bio);
+}
+
+/*
+ * Block layer want one ->make_request_fn to be active at a time
+ * so if we use chained IO with parent IO in same context,
+ * it's a deadlock. To avoid, it, it uses worker thread context.
+ */
+static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
+                               unsigned long entry, struct bio *bio)
+{
+       struct zram_work work;
+
+       work.zram = zram;
+       work.entry = entry;
+       work.bio = bio;
+
+       INIT_WORK_ONSTACK(&work.work, zram_sync_read);
+       queue_work(system_unbound_wq, &work.work);
+       flush_work(&work.work);
+       destroy_work_on_stack(&work.work);
+
+       return 1;
+}
+#else
+static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
+                               unsigned long entry, struct bio *bio)
+{
+       WARN_ON(1);
+       return -EIO;
+}
+#endif
+
+static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
+                       unsigned long entry, struct bio *parent, bool sync)
+{
+       if (sync)
+               return read_from_bdev_sync(zram, bvec, entry, parent);
+       else
+               return read_from_bdev_async(zram, bvec, entry, parent);
+}
+
 static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
                                        u32 index, struct bio *parent,
                                        unsigned long *pentry)
@@ -520,6 +609,12 @@ static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
 {
        return -EIO;
 }
+
+static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
+                       unsigned long entry, struct bio *parent, bool sync)
+{
+       return -EIO;
+}
 static void zram_wb_clear(struct zram *zram, u32 index) {}
 #endif
 
@@ -779,13 +874,31 @@ static void zram_free_page(struct zram *zram, size_t index)
        zram_set_obj_size(zram, index, 0);
 }
 
-static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index)
+static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
+                               struct bio *bio, bool partial_io)
 {
        int ret;
        unsigned long handle;
        unsigned int size;
        void *src, *dst;
 
+       if (zram_wb_enabled(zram)) {
+               zram_slot_lock(zram, index);
+               if (zram_test_flag(zram, index, ZRAM_WB)) {
+                       struct bio_vec bvec;
+
+                       zram_slot_unlock(zram, index);
+
+                       bvec.bv_page = page;
+                       bvec.bv_len = PAGE_SIZE;
+                       bvec.bv_offset = 0;
+                       return read_from_bdev(zram, &bvec,
+                                       zram_get_element(zram, index),
+                                       bio, partial_io);
+               }
+               zram_slot_unlock(zram, index);
+       }
+
        if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE))
                return 0;
 
@@ -818,7 +931,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index)
 }
 
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
-                               u32 index, int offset)
+                               u32 index, int offset, struct bio *bio)
 {
        int ret;
        struct page *page;
@@ -831,7 +944,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
                        return -ENOMEM;
        }
 
-       ret = __zram_bvec_read(zram, page, index);
+       ret = __zram_bvec_read(zram, page, index, bio, is_partial_io(bvec));
        if (unlikely(ret))
                goto out;
 
@@ -994,7 +1107,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
                if (!page)
                        return -ENOMEM;
 
-               ret = __zram_bvec_read(zram, page, index);
+               ret = __zram_bvec_read(zram, page, index, bio, true);
                if (ret)
                        goto out;
 
@@ -1070,7 +1183,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 
        if (rw == READ) {
                atomic64_inc(&zram->stats.num_reads);
-               ret = zram_bvec_read(zram, bvec, index, offset);
+               ret = zram_bvec_read(zram, bvec, index, offset, bio);
                flush_dcache_page(bvec->bv_page);
        } else {
                atomic64_inc(&zram->stats.num_writes);