zram idle page writeback

index 4879595200e1..472027eaed60 100644
@@ -53,6 +53,11 @@ static size_t huge_class_size;
 
 static void zram_free_page(struct zram *zram, size_t index);
 
+static int zram_slot_trylock(struct zram *zram, u32 index)
+{
+	return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].value);
+}
+
 static void zram_slot_lock(struct zram *zram, u32 index)
 {
 	bit_spin_lock(ZRAM_LOCK, &zram->table[index].value);

@@ -443,29 +448,45 @@ static ssize_t backing_dev_store(struct device *dev,
 
 static unsigned long get_entry_bdev(struct zram *zram)
 {
-	unsigned long entry;
+	unsigned long blk_idx;
+	unsigned long ret = 0;
 
-	spin_lock(&zram->bitmap_lock);
 	/* skip 0 bit to confuse zram.handle = 0 */
-	entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1);
-	if (entry == zram->nr_pages) {
-		spin_unlock(&zram->bitmap_lock);
-		return 0;
+	blk_idx = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1);
+	if (blk_idx == zram->nr_pages)
+		goto retry;
+
+	spin_lock_irq(&zram->bitmap_lock);
+	if (test_bit(blk_idx, zram->bitmap)) {
+		spin_unlock_irq(&zram->bitmap_lock);
+		goto retry;
 	}
 
-	set_bit(entry, zram->bitmap);
-	spin_unlock(&zram->bitmap_lock);
+	set_bit(blk_idx, zram->bitmap);
+	ret = blk_idx;
+	goto out;
+retry:
+	spin_lock_irq(&zram->bitmap_lock);
+	blk_idx = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1);
+	if (blk_idx == zram->nr_pages)
+		goto out;
+
+	set_bit(blk_idx, zram->bitmap);
+	ret = blk_idx;
+out:
+	spin_unlock_irq(&zram->bitmap_lock);
 
-	return entry;
+	return ret;
 }
 
 static void put_entry_bdev(struct zram *zram, unsigned long entry)
 {
 	int was_set;
+	unsigned long flags;
 
-	spin_lock(&zram->bitmap_lock);
+	spin_lock_irqsave(&zram->bitmap_lock, flags);
 	was_set = test_and_clear_bit(entry, zram->bitmap);
-	spin_unlock(&zram->bitmap_lock);
+	spin_unlock_irqrestore(&zram->bitmap_lock, flags);
 	WARN_ON_ONCE(!was_set);
 }
 

@@ -886,9 +907,10 @@ static ssize_t debug_stat_show(struct device *dev,
 
 	down_read(&zram->init_lock);
 	ret = scnprintf(buf, PAGE_SIZE,
-			"version: %d\n%8llu\n",
+			"version: %d\n%8llu %8llu\n",
 			version,
-			(u64)atomic64_read(&zram->stats.writestall));
+			(u64)atomic64_read(&zram->stats.writestall),
+			(u64)atomic64_read(&zram->stats.miss_free));
 	up_read(&zram->init_lock);
 
 	return ret;

@@ -1400,10 +1422,14 @@ static void zram_slot_free_notify(struct block_device *bdev,
 
 	zram = bdev->bd_disk->private_data;
 
-	zram_slot_lock(zram, index);
+	atomic64_inc(&zram->stats.notify_free);
+	if (!zram_slot_trylock(zram, index)) {
+		atomic64_inc(&zram->stats.miss_free);
+		return;
+	}
+
 	zram_free_page(zram, index);
 	zram_slot_unlock(zram, index);
-	atomic64_inc(&zram->stats.notify_free);
 }
 
 static int zram_rw_page(struct block_device *bdev, sector_t sector,

index 72c8584b6dff..89da501292ff 100644
@@ -79,6 +79,7 @@ struct zram_stats {
 	atomic64_t pages_stored;	/* no. of pages currently stored */
 	atomic_long_t max_used_pages;	/* no. of maximum pages stored */
 	atomic64_t writestall;		/* no. of write slow paths */
+	atomic64_t miss_free;		/* no. of missed free */
 };
 
 struct zram {

index 472027eaed60..514f5aaf6eff 100644
@@ -387,8 +387,10 @@ static ssize_t backing_dev_store(struct device *dev,
 
 	bdev = bdgrab(I_BDEV(inode));
 	err = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram);
-	if (err < 0)
+	if (err < 0) {
+		bdev = NULL;
 		goto out;
+	}
 
 	nr_pages = i_size_read(inode) >> PAGE_SHIFT;
 	bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long);

index 514f5aaf6eff..fee7e67c750d 100644
@@ -55,17 +55,17 @@ static void zram_free_page(struct zram *zram, size_t index);
 
 static int zram_slot_trylock(struct zram *zram, u32 index)
 {
-	return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].value);
+	return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].flags);
 }
 
 static void zram_slot_lock(struct zram *zram, u32 index)
 {
-	bit_spin_lock(ZRAM_LOCK, &zram->table[index].value);
+	bit_spin_lock(ZRAM_LOCK, &zram->table[index].flags);
 }
 
 static void zram_slot_unlock(struct zram *zram, u32 index)
 {
-	bit_spin_unlock(ZRAM_LOCK, &zram->table[index].value);
+	bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags);
 }
 
 static inline bool init_done(struct zram *zram)

@@ -76,7 +76,7 @@ static inline bool init_done(struct zram *zram)
 static inline bool zram_allocated(struct zram *zram, u32 index)
 {
 
-	return (zram->table[index].value >> (ZRAM_FLAG_SHIFT + 1)) ||
+	return (zram->table[index].flags >> (ZRAM_FLAG_SHIFT + 1)) ||
 					zram->table[index].handle;
 }
 

@@ -99,19 +99,19 @@ static void zram_set_handle(struct zram *zram, u32 index, unsigned long handle)
 static bool zram_test_flag(struct zram *zram, u32 index,
 			enum zram_pageflags flag)
 {
-	return zram->table[index].value & BIT(flag);
+	return zram->table[index].flags & BIT(flag);
 }
 
 static void zram_set_flag(struct zram *zram, u32 index,
 			enum zram_pageflags flag)
 {
-	zram->table[index].value |= BIT(flag);
+	zram->table[index].flags |= BIT(flag);
 }
 
 static void zram_clear_flag(struct zram *zram, u32 index,
 			enum zram_pageflags flag)
 {
-	zram->table[index].value &= ~BIT(flag);
+	zram->table[index].flags &= ~BIT(flag);
 }
 
 static inline void zram_set_element(struct zram *zram, u32 index,

@@ -127,15 +127,15 @@ static unsigned long zram_get_element(struct zram *zram, u32 index)
 
 static size_t zram_get_obj_size(struct zram *zram, u32 index)
 {
-	return zram->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1);
+	return zram->table[index].flags & (BIT(ZRAM_FLAG_SHIFT) - 1);
 }
 
 static void zram_set_obj_size(struct zram *zram,
 					u32 index, size_t size)
 {
-	unsigned long flags = zram->table[index].value >> ZRAM_FLAG_SHIFT;
+	unsigned long flags = zram->table[index].flags >> ZRAM_FLAG_SHIFT;
 
-	zram->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
+	zram->table[index].flags = (flags << ZRAM_FLAG_SHIFT) | size;
 }
 
 #if PAGE_SIZE != 4096

@@ -282,16 +282,11 @@ static ssize_t mem_used_max_store(struct device *dev,
 }
 
 #ifdef CONFIG_ZRAM_WRITEBACK
-static bool zram_wb_enabled(struct zram *zram)
-{
-	return zram->backing_dev;
-}
-
 static void reset_bdev(struct zram *zram)
 {
 	struct block_device *bdev;
 
-	if (!zram_wb_enabled(zram))
+	if (!zram->backing_dev)
 		return;
 
 	bdev = zram->bdev;

@@ -318,7 +313,7 @@ static ssize_t backing_dev_show(struct device *dev,
 	ssize_t ret;
 
 	down_read(&zram->init_lock);
-	if (!zram_wb_enabled(zram)) {
+	if (!zram->backing_dev) {
 		memcpy(buf, "none\n", 5);
 		up_read(&zram->init_lock);
 		return 5;

@@ -448,7 +443,7 @@ static ssize_t backing_dev_store(struct device *dev,
 	return err;
 }
 
-static unsigned long get_entry_bdev(struct zram *zram)
+static unsigned long alloc_block_bdev(struct zram *zram)
 {
 	unsigned long blk_idx;
 	unsigned long ret = 0;

@@ -481,13 +476,13 @@ static unsigned long get_entry_bdev(struct zram *zram)
 	return ret;
 }
 
-static void put_entry_bdev(struct zram *zram, unsigned long entry)
+static void free_block_bdev(struct zram *zram, unsigned long blk_idx)
 {
 	int was_set;
 	unsigned long flags;
 
 	spin_lock_irqsave(&zram->bitmap_lock, flags);
-	was_set = test_and_clear_bit(entry, zram->bitmap);
+	was_set = test_and_clear_bit(blk_idx, zram->bitmap);
 	spin_unlock_irqrestore(&zram->bitmap_lock, flags);
 	WARN_ON_ONCE(!was_set);
 }

@@ -601,7 +596,7 @@ static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
 	if (!bio)
 		return -ENOMEM;
 
-	entry = get_entry_bdev(zram);
+	entry = alloc_block_bdev(zram);
 	if (!entry) {
 		bio_put(bio);
 		return -ENOSPC;

@@ -612,7 +607,7 @@ static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
 	if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len,
 					bvec->bv_offset)) {
 		bio_put(bio);
-		put_entry_bdev(zram, entry);
+		free_block_bdev(zram, entry);
 		return -EIO;
 	}
 

@@ -630,18 +625,7 @@ static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
 	return 0;
 }
 
-static void zram_wb_clear(struct zram *zram, u32 index)
-{
-	unsigned long entry;
-
-	zram_clear_flag(zram, index, ZRAM_WB);
-	entry = zram_get_element(zram, index);
-	zram_set_element(zram, index, 0);
-	put_entry_bdev(zram, entry);
-}
-
 #else
-static bool zram_wb_enabled(struct zram *zram) { return false; }
 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,

@@ -656,7 +640,8 @@ static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
 {
 	return -EIO;
 }
-static void zram_wb_clear(struct zram *zram, u32 index) {}
+
+static void free_block_bdev(struct zram *zram, unsigned long blk_idx) {};
 #endif
 
 #ifdef CONFIG_ZRAM_MEMORY_TRACKING

@@ -678,11 +663,6 @@ static void zram_accessed(struct zram *zram, u32 index)
 	zram->table[index].ac_time = ktime_get_boottime();
 }
 
-static void zram_reset_access(struct zram *zram, u32 index)
-{
-	zram->table[index].ac_time = 0;
-}
-
 static ssize_t read_block_state(struct file *file, char __user *buf,
 				size_t count, loff_t *ppos)
 {

@@ -763,7 +743,6 @@ static void zram_debugfs_unregister(struct zram *zram)
 static void zram_debugfs_create(void) {};
 static void zram_debugfs_destroy(void) {};
 static void zram_accessed(struct zram *zram, u32 index) {};
-static void zram_reset_access(struct zram *zram, u32 index) {};
 static void zram_debugfs_register(struct zram *zram) {};
 static void zram_debugfs_unregister(struct zram *zram) {};
 #endif

@@ -964,17 +943,18 @@ static void zram_free_page(struct zram *zram, size_t index)
 {
 	unsigned long handle;
 
-	zram_reset_access(zram, index);
-
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+	zram->table[index].ac_time = 0;
+#endif
 	if (zram_test_flag(zram, index, ZRAM_HUGE)) {
 		zram_clear_flag(zram, index, ZRAM_HUGE);
 		atomic64_dec(&zram->stats.huge_pages);
 	}
 
-	if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) {
-		zram_wb_clear(zram, index);
-		atomic64_dec(&zram->stats.pages_stored);
-		return;
+	if (zram_test_flag(zram, index, ZRAM_WB)) {
+		zram_clear_flag(zram, index, ZRAM_WB);
+		free_block_bdev(zram, zram_get_element(zram, index));
+		goto out;
 	}
 
 	/*

@@ -983,10 +963,8 @@ static void zram_free_page(struct zram *zram, size_t index)
 	 */
 	if (zram_test_flag(zram, index, ZRAM_SAME)) {
 		zram_clear_flag(zram, index, ZRAM_SAME);
-		zram_set_element(zram, index, 0);
 		atomic64_dec(&zram->stats.same_pages);
-		atomic64_dec(&zram->stats.pages_stored);
-		return;
+		goto out;
 	}
 
 	handle = zram_get_handle(zram, index);

@@ -997,10 +975,11 @@ static void zram_free_page(struct zram *zram, size_t index)
 
 	atomic64_sub(zram_get_obj_size(zram, index),
 			&zram->stats.compr_data_size);
+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));
 }
 
 static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,

@@ -1011,24 +990,20 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 	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);
+	zram_slot_lock(zram, index);
+	if (zram_test_flag(zram, index, ZRAM_WB)) {
+		struct bio_vec bvec;
 
-			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);
+
+		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_lock(zram, index);
 	handle = zram_get_handle(zram, index);
 	if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
 		unsigned long value;

@@ -1140,7 +1115,7 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 
 	if (unlikely(comp_len >= huge_class_size)) {
 		comp_len = PAGE_SIZE;
-		if (zram_wb_enabled(zram) && allow_wb) {
+		if (zram->backing_dev && allow_wb) {
 			zcomp_stream_put(zram->comp);
 			ret = write_to_bdev(zram, bvec, index, bio, &element);
 			if (!ret) {

index 89da501292ff..d75bf190f262 100644
@@ -30,7 +30,7 @@
 
 
 /*
- * The lower ZRAM_FLAG_SHIFT bits of table.value is for
+ * The lower ZRAM_FLAG_SHIFT bits of table.flags is for
  * object size (excluding header), the higher bits is for
  * zram_pageflags.
  *

@@ -41,7 +41,7 @@
  */
 #define ZRAM_FLAG_SHIFT 24
 
-/* Flags for zram pages (table[page_no].value) */
+/* Flags for zram pages (table[page_no].flags) */
 enum zram_pageflags {
 	/* zram slot is locked */
 	ZRAM_LOCK = ZRAM_FLAG_SHIFT,

@@ -60,7 +60,7 @@ struct zram_table_entry {
 		unsigned long handle;
 		unsigned long element;
 	};
-	unsigned long value;
+	unsigned long flags;
 #ifdef CONFIG_ZRAM_MEMORY_TRACKING
 	ktime_t ac_time;
 #endif

@@ -105,8 +105,8 @@ struct zram {
 	 * zram is claimed so open request will be failed
 	 */
 	bool claim; /* Protected by bdev->bd_mutex */
-#ifdef CONFIG_ZRAM_WRITEBACK
 	struct file *backing_dev;
+#ifdef CONFIG_ZRAM_WRITEBACK
 	struct block_device *bdev;
 	unsigned int old_block_size;
 	unsigned long *bitmap;

101 lines not on this page · raw message

index d75bf190f262..214fa4bb46b9 100644
@@ -48,6 +48,7 @@ enum zram_pageflags {
 	ZRAM_SAME,	/* Page consists the same element */
 	ZRAM_WB,	/* page is stored on backing_device */
 	ZRAM_HUGE,	/* Incompressible page */
+	ZRAM_IDLE,	/* not accessed page since last idle marking */
 
 	__NR_ZRAM_PAGEFLAGS,
 };

316 lines not on this page · raw message

index 214fa4bb46b9..07695fe70e17 100644
@@ -47,6 +47,7 @@ enum zram_pageflags {
 	ZRAM_LOCK = ZRAM_FLAG_SHIFT,
 	ZRAM_SAME,	/* Page consists the same element */
 	ZRAM_WB,	/* page is stored on backing_device */
+	ZRAM_UNDER_WB,	/* page is under writeback */
 	ZRAM_HUGE,	/* Incompressible page */
 	ZRAM_IDLE,	/* not accessed page since last idle marking */
 

index 3d069b2328f8..cceaa10301e8 100644
@@ -518,6 +518,8 @@ static unsigned long alloc_block_bdev(struct zram *zram)
 	ret = blk_idx;
 out:
 	spin_unlock_irq(&zram->bitmap_lock);
+	if (ret != 0)
+		atomic64_inc(&zram->stats.bd_count);
 
 	return ret;
 }

@@ -531,6 +533,7 @@ static void free_block_bdev(struct zram *zram, unsigned long blk_idx)
 	was_set = test_and_clear_bit(blk_idx, zram->bitmap);
 	spin_unlock_irqrestore(&zram->bitmap_lock, flags);
 	WARN_ON_ONCE(!was_set);
+	atomic64_dec(&zram->stats.bd_count);
 }
 
 static void zram_page_end_io(struct bio *bio)

@@ -686,6 +689,7 @@ static ssize_t writeback_store(struct device *dev,
 			continue;
 		}
 
+		atomic64_inc(&zram->stats.bd_writes);
 		/*
 		 * 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

@@ -775,6 +779,7 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
 static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
 			unsigned long entry, struct bio *parent, bool sync)
 {
+	atomic64_inc(&zram->stats.bd_reads);
 	if (sync)
 		return read_from_bdev_sync(zram, bvec, entry, parent);
 	else

@@ -1031,6 +1036,25 @@ static ssize_t mm_stat_show(struct device *dev,
 	return ret;
 }
 
+#ifdef CONFIG_ZRAM_WRITEBACK
+static ssize_t bd_stat_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct zram *zram = dev_to_zram(dev);
+	ssize_t ret;
+
+	down_read(&zram->init_lock);
+	ret = scnprintf(buf, PAGE_SIZE,
+			"%8llu %8llu %8llu\n",
+			(u64)atomic64_read(&zram->stats.bd_count),
+			(u64)atomic64_read(&zram->stats.bd_reads),
+			(u64)atomic64_read(&zram->stats.bd_writes));
+	up_read(&zram->init_lock);
+
+	return ret;
+}
+#endif
+
 static ssize_t debug_stat_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {

@@ -1051,6 +1075,9 @@ static ssize_t debug_stat_show(struct device *dev,
 
 static DEVICE_ATTR_RO(io_stat);
 static DEVICE_ATTR_RO(mm_stat);
+#ifdef CONFIG_ZRAM_WRITEBACK
+static DEVICE_ATTR_RO(bd_stat);
+#endif
 static DEVICE_ATTR_RO(debug_stat);
 
 static void zram_meta_free(struct zram *zram, u64 disksize)

@@ -1777,6 +1804,9 @@ static struct attribute *zram_disk_attrs[] = {
 #endif
 	&dev_attr_io_stat.attr,
 	&dev_attr_mm_stat.attr,
+#ifdef CONFIG_ZRAM_WRITEBACK
+	&dev_attr_bd_stat.attr,
+#endif
 	&dev_attr_debug_stat.attr,
 	NULL,
 };

index 07695fe70e17..7cbb134fc0c9 100644
@@ -82,6 +82,11 @@ struct zram_stats {
 	atomic_long_t max_used_pages;	/* no. of maximum pages stored */
 	atomic64_t writestall;		/* no. of write slow paths */
 	atomic64_t miss_free;		/* no. of missed free */
+#ifdef	CONFIG_ZRAM_WRITEBACK
+	atomic64_t bd_count;		/* no. of pages in backing device */
+	atomic64_t bd_reads;		/* no. of reads from backing device */
+	atomic64_t bd_writes;		/* no. of writes from backing device */
+#endif
 };
 
 struct zram {

89 lines not on this page · raw message

index 7cbb134fc0c9..024044e82c9b 100644
@@ -86,6 +86,7 @@ struct zram_stats {
 	atomic64_t bd_count;		/* no. of pages in backing device */
 	atomic64_t bd_reads;		/* no. of reads from backing device */
 	atomic64_t bd_writes;		/* no. of writes from backing device */
+	atomic64_t bd_wb_limit;		/* writeback limit of backing device */
 #endif
 };
 

@@ -113,6 +114,7 @@ struct zram {
 	 */
 	bool claim; /* Protected by bdev->bd_mutex */
 	struct file *backing_dev;
+	bool stop_writeback;
 #ifdef CONFIG_ZRAM_WRITEBACK
 	struct block_device *bdev;
 	unsigned int old_block_size;