1 files changed, 84 insertions, 27 deletions

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index a68297fb51a2..08d7953ec5f1 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -291,22 +291,16 @@ static ssize_t mem_used_max_store(struct device *dev,
 	return len;
 }
 
-static ssize_t idle_store(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t len)
+/*
+ * Mark all pages which are older than or equal to cutoff as IDLE.
+ * Callers should hold the zram init lock in read mode
+ */
+static void mark_idle(struct zram *zram, ktime_t cutoff)
 {
-	struct zram *zram = dev_to_zram(dev);
+	int is_idle = 1;
 	unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
 	int index;
 
-	if (!sysfs_streq(buf, "all"))
-		return -EINVAL;
-
-	down_read(&zram->init_lock);
-	if (!init_done(zram)) {
-		up_read(&zram->init_lock);
-		return -EINVAL;
-	}
-
 	for (index = 0; index < nr_pages; index++) {
 		/*
 		 * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race.
@@ -314,14 +308,50 @@ static ssize_t idle_store(struct device *dev,
 		 */
 		zram_slot_lock(zram, index);
 		if (zram_allocated(zram, index) &&
-				!zram_test_flag(zram, index, ZRAM_UNDER_WB))
-			zram_set_flag(zram, index, ZRAM_IDLE);
+				!zram_test_flag(zram, index, ZRAM_UNDER_WB)) {
+#ifdef CONFIG_ZRAM_MEMORY_TRACKING
+			is_idle = !cutoff || ktime_after(cutoff, zram->table[index].ac_time);
+#endif
+			if (is_idle)
+				zram_set_flag(zram, index, ZRAM_IDLE);
+		}
 		zram_slot_unlock(zram, index);
 	}
+}
 
-	up_read(&zram->init_lock);
+static ssize_t idle_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct zram *zram = dev_to_zram(dev);
+	ktime_t cutoff_time = 0;
+	ssize_t rv = -EINVAL;
 
-	return len;
+	if (!sysfs_streq(buf, "all")) {
+		/*
+		 * If it did not parse as 'all' try to treat it as an integer when
+		 * we have memory tracking enabled.
+		 */
+		u64 age_sec;
+
+		if (IS_ENABLED(CONFIG_ZRAM_MEMORY_TRACKING) && !kstrtoull(buf, 0, &age_sec))
+			cutoff_time = ktime_sub(ktime_get_boottime(),
+					ns_to_ktime(age_sec * NSEC_PER_SEC));
+		else
+			goto out;
+	}
+
+	down_read(&zram->init_lock);
+	if (!init_done(zram))
+		goto out_unlock;
+
+	/* A cutoff_time of 0 marks everything as idle, this is the "all" behavior */
+	mark_idle(zram, cutoff_time);
+	rv = len;
+
+out_unlock:
+	up_read(&zram->init_lock);
+out:
+	return rv;
 }
 
 #ifdef CONFIG_ZRAM_WRITEBACK
@@ -587,7 +617,7 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
 {
 	struct bio *bio;
 
-	bio = bio_alloc(GFP_ATOMIC, 1);
+	bio = bio_alloc(GFP_NOIO, 1);
 	if (!bio)
 		return -ENOMEM;
 
@@ -910,7 +940,7 @@ static ssize_t read_block_state(struct file *file, char __user *buf,
 			zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.',
 			zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.');
 
-		if (count < copied) {
+		if (count <= copied) {
 			zram_slot_unlock(zram, index);
 			break;
 		}
@@ -1704,12 +1734,13 @@ static void zram_reset_device(struct zram *zram)
 	set_capacity_and_notify(zram->disk, 0);
 	part_stat_set_all(zram->disk->part0, 0);
 
-	up_write(&zram->init_lock);
 	/* I/O operation under all of CPU are done so let's free */
 	zram_meta_free(zram, disksize);
 	memset(&zram->stats, 0, sizeof(zram->stats));
 	zcomp_destroy(comp);
 	reset_bdev(zram);
+
+	up_write(&zram->init_lock);
 }
 
 static ssize_t disksize_store(struct device *dev,
@@ -1789,7 +1820,7 @@ static ssize_t reset_store(struct device *dev,
 	mutex_unlock(&bdev->bd_disk->open_mutex);
 
 	/* Make sure all the pending I/O are finished */
-	fsync_bdev(bdev);
+	sync_blockdev(bdev);
 	zram_reset_device(zram);
 
 	mutex_lock(&bdev->bd_disk->open_mutex);
@@ -1949,7 +1980,9 @@ static int zram_add(void)
 		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
 	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
-	device_add_disk(NULL, zram->disk, zram_disk_attr_groups);
+	ret = device_add_disk(NULL, zram->disk, zram_disk_attr_groups);
+	if (ret)
+		goto out_cleanup_disk;
 
 	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
 
@@ -1957,6 +1990,8 @@ static int zram_add(void)
 	pr_info("Added device: %s\n", zram->disk->disk_name);
 	return device_id;
 
+out_cleanup_disk:
+	blk_cleanup_disk(zram->disk);
 out_free_idr:
 	idr_remove(&zram_index_idr, device_id);
 out_free_dev:
@@ -1967,25 +2002,47 @@ out_free_dev:
 static int zram_remove(struct zram *zram)
 {
 	struct block_device *bdev = zram->disk->part0;
+	bool claimed;
 
 	mutex_lock(&bdev->bd_disk->open_mutex);
-	if (bdev->bd_openers || zram->claim) {
+	if (bdev->bd_openers) {
 		mutex_unlock(&bdev->bd_disk->open_mutex);
 		return -EBUSY;
 	}
 
-	zram->claim = true;
+	claimed = zram->claim;
+	if (!claimed)
+		zram->claim = true;
 	mutex_unlock(&bdev->bd_disk->open_mutex);
 
 	zram_debugfs_unregister(zram);
 
-	/* Make sure all the pending I/O are finished */
-	fsync_bdev(bdev);
-	zram_reset_device(zram);
+	if (claimed) {
+		/*
+		 * If we were claimed by reset_store(), del_gendisk() will
+		 * wait until reset_store() is done, so nothing need to do.
+		 */
+		;
+	} else {
+		/* Make sure all the pending I/O are finished */
+		sync_blockdev(bdev);
+		zram_reset_device(zram);
+	}
 
 	pr_info("Removed device: %s\n", zram->disk->disk_name);
 
 	del_gendisk(zram->disk);
+
+	/* del_gendisk drains pending reset_store */
+	WARN_ON_ONCE(claimed && zram->claim);
+
+	/*
+	 * disksize_store() may be called in between zram_reset_device()
+	 * and del_gendisk(), so run the last reset to avoid leaking
+	 * anything allocated with disksize_store()
+	 */
+	zram_reset_device(zram);
+
 	blk_cleanup_disk(zram->disk);
 	kfree(zram);
 	return 0;
@@ -2062,7 +2119,7 @@ static struct class zram_control_class = {
 
 static int zram_remove_cb(int id, void *ptr, void *data)
 {
-	zram_remove(ptr);
+	WARN_ON_ONCE(zram_remove(ptr));
 	return 0;
 }