1 files changed, 173 insertions, 74 deletions

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 180613b478a6..6b5a886c8f32 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -52,6 +52,9 @@ static unsigned int num_devices = 1;
 static size_t huge_class_size;
 
 static void zram_free_page(struct zram *zram, size_t index);
+static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
+				u32 index, int offset, struct bio *bio);
+
 
 static int zram_slot_trylock(struct zram *zram, u32 index)
 {
@@ -73,13 +76,6 @@ static inline bool init_done(struct zram *zram)
 	return zram->disksize;
 }
 
-static inline bool zram_allocated(struct zram *zram, u32 index)
-{
-
-	return (zram->table[index].flags >> (ZRAM_FLAG_SHIFT + 1)) ||
-					zram->table[index].handle;
-}
-
 static inline struct zram *dev_to_zram(struct device *dev)
 {
 	return (struct zram *)dev_to_disk(dev)->private_data;
@@ -138,6 +134,13 @@ static void zram_set_obj_size(struct zram *zram,
 	zram->table[index].flags = (flags << ZRAM_FLAG_SHIFT) | size;
 }
 
+static inline bool zram_allocated(struct zram *zram, u32 index)
+{
+	return zram_get_obj_size(zram, index) ||
+			zram_test_flag(zram, index, ZRAM_SAME) ||
+			zram_test_flag(zram, index, ZRAM_WB);
+}
+
 #if PAGE_SIZE != 4096
 static inline bool is_partial_io(struct bio_vec *bvec)
 {
@@ -308,10 +311,14 @@ static ssize_t idle_store(struct device *dev,
 	}
 
 	for (index = 0; index < nr_pages; index++) {
+		/*
+		 * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race.
+		 * See the comment in writeback_store.
+		 */
 		zram_slot_lock(zram, index);
-		if (!zram_allocated(zram, index))
+		if (!zram_allocated(zram, index) ||
+				zram_test_flag(zram, index, ZRAM_UNDER_WB))
 			goto next;
-
 		zram_set_flag(zram, index, ZRAM_IDLE);
 next:
 		zram_slot_unlock(zram, index);
@@ -546,6 +553,158 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
 	return 1;
 }
 
+#define HUGE_WRITEBACK 0x1
+#define IDLE_WRITEBACK 0x2
+
+static ssize_t writeback_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct zram *zram = dev_to_zram(dev);
+	unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
+	unsigned long index;
+	struct bio bio;
+	struct bio_vec bio_vec;
+	struct page *page;
+	ssize_t ret, sz;
+	char mode_buf[8];
+	unsigned long mode = -1UL;
+	unsigned long blk_idx = 0;
+
+	sz = strscpy(mode_buf, buf, sizeof(mode_buf));
+	if (sz <= 0)
+		return -EINVAL;
+
+	/* ignore trailing newline */
+	if (mode_buf[sz - 1] == '\n')
+		mode_buf[sz - 1] = 0x00;
+
+	if (!strcmp(mode_buf, "idle"))
+		mode = IDLE_WRITEBACK;
+	else if (!strcmp(mode_buf, "huge"))
+		mode = HUGE_WRITEBACK;
+
+	if (mode == -1UL)
+		return -EINVAL;
+
+	down_read(&zram->init_lock);
+	if (!init_done(zram)) {
+		ret = -EINVAL;
+		goto release_init_lock;
+	}
+
+	if (!zram->backing_dev) {
+		ret = -ENODEV;
+		goto release_init_lock;
+	}
+
+	page = alloc_page(GFP_KERNEL);
+	if (!page) {
+		ret = -ENOMEM;
+		goto release_init_lock;
+	}
+
+	for (index = 0; index < nr_pages; index++) {
+		struct bio_vec bvec;
+
+		bvec.bv_page = page;
+		bvec.bv_len = PAGE_SIZE;
+		bvec.bv_offset = 0;
+
+		if (!blk_idx) {
+			blk_idx = alloc_block_bdev(zram);
+			if (!blk_idx) {
+				ret = -ENOSPC;
+				break;
+			}
+		}
+
+		zram_slot_lock(zram, index);
+		if (!zram_allocated(zram, index))
+			goto next;
+
+		if (zram_test_flag(zram, index, ZRAM_WB) ||
+				zram_test_flag(zram, index, ZRAM_SAME) ||
+				zram_test_flag(zram, index, ZRAM_UNDER_WB))
+			goto next;
+
+		if ((mode & IDLE_WRITEBACK &&
+			  !zram_test_flag(zram, index, ZRAM_IDLE)) &&
+		    (mode & HUGE_WRITEBACK &&
+			  !zram_test_flag(zram, index, ZRAM_HUGE)))
+			goto next;
+		/*
+		 * Clearing ZRAM_UNDER_WB is duty of caller.
+		 * IOW, zram_free_page never clear it.
+		 */
+		zram_set_flag(zram, index, ZRAM_UNDER_WB);
+		/* Need for hugepage writeback racing */
+		zram_set_flag(zram, index, ZRAM_IDLE);
+		zram_slot_unlock(zram, index);
+		if (zram_bvec_read(zram, &bvec, index, 0, NULL)) {
+			zram_slot_lock(zram, index);
+			zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+			zram_clear_flag(zram, index, ZRAM_IDLE);
+			zram_slot_unlock(zram, index);
+			continue;
+		}
+
+		bio_init(&bio, &bio_vec, 1);
+		bio_set_dev(&bio, zram->bdev);
+		bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9);
+		bio.bi_opf = REQ_OP_WRITE | REQ_SYNC;
+
+		bio_add_page(&bio, bvec.bv_page, bvec.bv_len,
+				bvec.bv_offset);
+		/*
+		 * XXX: A single page IO would be inefficient for write
+		 * but it would be not bad as starter.
+		 */
+		ret = submit_bio_wait(&bio);
+		if (ret) {
+			zram_slot_lock(zram, index);
+			zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+			zram_clear_flag(zram, index, ZRAM_IDLE);
+			zram_slot_unlock(zram, index);
+			continue;
+		}
+
+		/*
+		 * We released zram_slot_lock so need to check if the slot was
+		 * changed. If there is freeing for the slot, we can catch it
+		 * easily by zram_allocated.
+		 * A subtle case is the slot is freed/reallocated/marked as
+		 * ZRAM_IDLE again. To close the race, idle_store doesn't
+		 * mark ZRAM_IDLE once it found the slot was ZRAM_UNDER_WB.
+		 * Thus, we could close the race by checking ZRAM_IDLE bit.
+		 */
+		zram_slot_lock(zram, index);
+		if (!zram_allocated(zram, index) ||
+			  !zram_test_flag(zram, index, ZRAM_IDLE)) {
+			zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+			zram_clear_flag(zram, index, ZRAM_IDLE);
+			goto next;
+		}
+
+		zram_free_page(zram, index);
+		zram_clear_flag(zram, index, ZRAM_UNDER_WB);
+		zram_set_flag(zram, index, ZRAM_WB);
+		zram_set_element(zram, index, blk_idx);
+		blk_idx = 0;
+		atomic64_inc(&zram->stats.pages_stored);
+next:
+		zram_slot_unlock(zram, index);
+	}
+
+	if (blk_idx)
+		free_block_bdev(zram, blk_idx);
+	ret = len;
+	__free_page(page);
+release_init_lock:
+	up_read(&zram->init_lock);
+
+	return ret;
+}
+
 struct zram_work {
 	struct work_struct work;
 	struct zram *zram;
@@ -603,57 +762,8 @@ static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
 	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)
-{
-	struct bio *bio;
-	unsigned long entry;
-
-	bio = bio_alloc(GFP_ATOMIC, 1);
-	if (!bio)
-		return -ENOMEM;
-
-	entry = alloc_block_bdev(zram);
-	if (!entry) {
-		bio_put(bio);
-		return -ENOSPC;
-	}
-
-	bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
-	bio_set_dev(bio, zram->bdev);
-	if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len,
-					bvec->bv_offset)) {
-		bio_put(bio);
-		free_block_bdev(zram, entry);
-		return -EIO;
-	}
-
-	if (!parent) {
-		bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
-		bio->bi_end_io = zram_page_end_io;
-	} else {
-		bio->bi_opf = parent->bi_opf;
-		bio_chain(bio, parent);
-	}
-
-	submit_bio(bio);
-	*pentry = entry;
-
-	return 0;
-}
-
 #else
 static inline void reset_bdev(struct zram *zram) {};
-static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
-					u32 index, struct bio *parent,
-					unsigned long *pentry)
-
-{
-	return -EIO;
-}
-
 static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
 			unsigned long entry, struct bio *parent, bool sync)
 {
@@ -1006,7 +1116,8 @@ out:
 	atomic64_dec(&zram->stats.pages_stored);
 	zram_set_handle(zram, index, 0);
 	zram_set_obj_size(zram, index, 0);
-	WARN_ON_ONCE(zram->table[index].flags & ~(1UL << ZRAM_LOCK));
+	WARN_ON_ONCE(zram->table[index].flags &
+		~(1UL << ZRAM_LOCK | 1UL << ZRAM_UNDER_WB));
 }
 
 static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
@@ -1115,7 +1226,6 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 	struct page *page = bvec->bv_page;
 	unsigned long element = 0;
 	enum zram_pageflags flags = 0;
-	bool allow_wb = true;
 
 	mem = kmap_atomic(page);
 	if (page_same_filled(mem, &element)) {
@@ -1140,21 +1250,8 @@ compress_again:
 		return ret;
 	}
 
-	if (unlikely(comp_len >= huge_class_size)) {
+	if (comp_len >= huge_class_size)
 		comp_len = PAGE_SIZE;
-		if (zram->backing_dev && allow_wb) {
-			zcomp_stream_put(zram->comp);
-			ret = write_to_bdev(zram, bvec, index, bio, &element);
-			if (!ret) {
-				flags = ZRAM_WB;
-				ret = 1;
-				goto out;
-			}
-			allow_wb = false;
-			goto compress_again;
-		}
-	}
-
 	/*
 	 * handle allocation has 2 paths:
 	 * a) fast path is executed with preemption disabled (for
@@ -1643,6 +1740,7 @@ static DEVICE_ATTR_RW(max_comp_streams);
 static DEVICE_ATTR_RW(comp_algorithm);
 #ifdef CONFIG_ZRAM_WRITEBACK
 static DEVICE_ATTR_RW(backing_dev);
+static DEVICE_ATTR_WO(writeback);
 #endif
 
 static struct attribute *zram_disk_attrs[] = {
@@ -1657,6 +1755,7 @@ static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_comp_algorithm.attr,
 #ifdef CONFIG_ZRAM_WRITEBACK
 	&dev_attr_backing_dev.attr,
+	&dev_attr_writeback.attr,
 #endif
 	&dev_attr_io_stat.attr,
 	&dev_attr_mm_stat.attr,