Merge: dm: sync with upstream v6.17

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/7535

JIRA: https://issues.redhat.com/browse/RHEL-119009
Upstream Status: kernel/git/torvalds/linux.git

Pull in various dm changes from upstream.

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>

Approved-by: Matthew Sakai <msakai@redhat.com>
Approved-by: Mikuláš Patočka <mpatocka@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

Author: CKI KWF Bot

Documentation/admin-guide/device-mapper/dm-integrity.rst

@@ -92,6 +92,11 @@ Target arguments:
 		allowed. This mode is useful for data recovery if the
 		device cannot be activated in any of the other standard
 		modes.
+	I - inline mode - in this mode, dm-integrity will store integrity
+		data directly in the underlying device sectors.
+		The underlying device must have an integrity profile that
+		allows storing user integrity data and provides enough
+		space for the selected integrity tag.
 
 5. the number of additional arguments
 

Documentation/admin-guide/device-mapper/thin-provisioning.rst

@@ -80,11 +80,11 @@ less sharing than average you'll need a larger-than-average metadata device.
 
 As a guide, we suggest you calculate the number of bytes to use in the
 metadata device as 48 * $data_dev_size / $data_block_size but round it up
-to 2MB if the answer is smaller.  If you're creating large numbers of
+to 2MiB if the answer is smaller.  If you're creating large numbers of
 snapshots which are recording large amounts of change, you may find you
 need to increase this.
 
-The largest size supported is 16GB: If the device is larger,
+The largest size supported is 16GiB: If the device is larger,
 a warning will be issued and the excess space will not be used.
 
 Reloading a pool table
@@ -107,13 +107,13 @@ Using an existing pool device
 
 $data_block_size gives the smallest unit of disk space that can be
 allocated at a time expressed in units of 512-byte sectors.
-$data_block_size must be between 128 (64KB) and 2097152 (1GB) and a
-multiple of 128 (64KB).  $data_block_size cannot be changed after the
+$data_block_size must be between 128 (64KiB) and 2097152 (1GiB) and a
+multiple of 128 (64KiB).  $data_block_size cannot be changed after the
 thin-pool is created.  People primarily interested in thin provisioning
-may want to use a value such as 1024 (512KB).  People doing lots of
-snapshotting may want a smaller value such as 128 (64KB).  If you are
+may want to use a value such as 1024 (512KiB).  People doing lots of
+snapshotting may want a smaller value such as 128 (64KiB).  If you are
 not zeroing newly-allocated data, a larger $data_block_size in the
-region of 256000 (128MB) is suggested.
+region of 262144 (128MiB) is suggested.
 
 $low_water_mark is expressed in blocks of size $data_block_size.  If
 free space on the data device drops below this level then a dm event
@@ -291,7 +291,7 @@ i) Constructor
       error_if_no_space:
 	Error IOs, instead of queueing, if no space.
 
-    Data block size must be between 64KB (128 sectors) and 1GB
+    Data block size must be between 64KiB (128 sectors) and 1GiB
     (2097152 sectors) inclusive.
 
 

Documentation/admin-guide/device-mapper/verity.rst

@@ -87,6 +87,15 @@ panic_on_corruption
     Panic the device when a corrupted block is discovered. This option is
     not compatible with ignore_corruption and restart_on_corruption.
 
+restart_on_error
+    Restart the system when an I/O error is detected.
+    This option can be combined with the restart_on_corruption option.
+
+panic_on_error
+    Panic the device when an I/O error is detected. This option is
+    not compatible with the restart_on_error option but can be combined
+    with the panic_on_corruption option.
+
 ignore_zero_blocks
     Do not verify blocks that are expected to contain zeroes and always return
     zeroes instead. This may be useful if the partition contains unused blocks
@@ -142,8 +151,15 @@ root_hash_sig_key_desc <key_description>
     already in the secondary trusted keyring.
 
 try_verify_in_tasklet
-    If verity hashes are in cache, verify data blocks in kernel tasklet instead
-    of workqueue. This option can reduce IO latency.
+    If verity hashes are in cache and the IO size does not exceed the limit,
+    verify data blocks in bottom half instead of workqueue. This option can
+    reduce IO latency. The size limits can be configured via
+    /sys/module/dm_verity/parameters/use_bh_bytes. The four parameters
+    correspond to limits for IOPRIO_CLASS_NONE, IOPRIO_CLASS_RT,
+    IOPRIO_CLASS_BE and IOPRIO_CLASS_IDLE in turn.
+    For example:
+    <none>,<rt>,<be>,<idle>
+    4096,4096,4096,4096
 
 Theory of operation
 ===================

drivers/md/Kconfig

@@ -284,6 +284,7 @@ config DM_CRYPT
 	depends on BLK_DEV_DM
 	depends on (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n)
 	depends on (TRUSTED_KEYS || TRUSTED_KEYS=n)
+	select CRC32
 	select CRYPTO
 	select CRYPTO_CBC
 	select CRYPTO_ESSIV

drivers/md/dm-bufio.c

@@ -40,16 +40,6 @@
 #define DM_BUFIO_WRITEBACK_RATIO	3
 #define DM_BUFIO_LOW_WATERMARK_RATIO	16
 
-/*
- * Check buffer ages in this interval (seconds)
- */
-#define DM_BUFIO_WORK_TIMER_SECS	30
-
-/*
- * Free buffers when they are older than this (seconds)
- */
-#define DM_BUFIO_DEFAULT_AGE_SECS	300
-
 /*
  * The nr of bytes of cached data to keep around.
  */
@@ -1057,10 +1047,8 @@ static unsigned long dm_bufio_cache_size_latch;
 
 static DEFINE_SPINLOCK(global_spinlock);
 
-/*
- * Buffers are freed after this timeout
- */
-static unsigned int dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS;
+static unsigned int dm_bufio_max_age; /* No longer does anything */
+
 static unsigned long dm_bufio_retain_bytes = DM_BUFIO_DEFAULT_RETAIN_BYTES;
 
 static unsigned long dm_bufio_peak_allocated;
@@ -1088,7 +1076,6 @@ static LIST_HEAD(dm_bufio_all_clients);
 static DEFINE_MUTEX(dm_bufio_clients_lock);
 
 static struct workqueue_struct *dm_bufio_wq;
-static struct delayed_work dm_bufio_cleanup_old_work;
 static struct work_struct dm_bufio_replacement_work;
 
 
@@ -2236,7 +2223,7 @@ int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t c
 }
 EXPORT_SYMBOL_GPL(dm_bufio_issue_discard);
 
-static bool forget_buffer(struct dm_bufio_client *c, sector_t block)
+static void forget_buffer(struct dm_bufio_client *c, sector_t block)
 {
 	struct dm_buffer *b;
 
@@ -2251,8 +2238,6 @@ static bool forget_buffer(struct dm_bufio_client *c, sector_t block)
 			cache_put_and_wake(c, b);
 		}
 	}
-
-	return b ? true : false;
 }
 
 /*
@@ -2682,130 +2667,6 @@ EXPORT_SYMBOL_GPL(dm_bufio_set_sector_offset);
 
 /*--------------------------------------------------------------*/
 
-static unsigned int get_max_age_hz(void)
-{
-	unsigned int max_age = READ_ONCE(dm_bufio_max_age);
-
-	if (max_age > UINT_MAX / HZ)
-		max_age = UINT_MAX / HZ;
-
-	return max_age * HZ;
-}
-
-static bool older_than(struct dm_buffer *b, unsigned long age_hz)
-{
-	return time_after_eq(jiffies, READ_ONCE(b->last_accessed) + age_hz);
-}
-
-struct evict_params {
-	gfp_t gfp;
-	unsigned long age_hz;
-
-	/*
-	 * This gets updated with the largest last_accessed (ie. most
-	 * recently used) of the evicted buffers.  It will not be reinitialised
-	 * by __evict_many(), so you can use it across multiple invocations.
-	 */
-	unsigned long last_accessed;
-};
-
-/*
- * We may not be able to evict this buffer if IO pending or the client
- * is still using it.
- *
- * And if GFP_NOFS is used, we must not do any I/O because we hold
- * dm_bufio_clients_lock and we would risk deadlock if the I/O gets
- * rerouted to different bufio client.
- */
-static enum evict_result select_for_evict(struct dm_buffer *b, void *context)
-{
-	struct evict_params *params = context;
-
-	if (!(params->gfp & __GFP_FS) ||
-	    (static_branch_unlikely(&no_sleep_enabled) && b->c->no_sleep)) {
-		if (test_bit_acquire(B_READING, &b->state) ||
-		    test_bit(B_WRITING, &b->state) ||
-		    test_bit(B_DIRTY, &b->state))
-			return ER_DONT_EVICT;
-	}
-
-	return older_than(b, params->age_hz) ? ER_EVICT : ER_STOP;
-}
-
-static unsigned long __evict_many(struct dm_bufio_client *c,
-				  struct evict_params *params,
-				  int list_mode, unsigned long max_count)
-{
-	unsigned long count;
-	unsigned long last_accessed;
-	struct dm_buffer *b;
-
-	for (count = 0; count < max_count; count++) {
-		b = cache_evict(&c->cache, list_mode, select_for_evict, params);
-		if (!b)
-			break;
-
-		last_accessed = READ_ONCE(b->last_accessed);
-		if (time_after_eq(params->last_accessed, last_accessed))
-			params->last_accessed = last_accessed;
-
-		__make_buffer_clean(b);
-		__free_buffer_wake(b);
-
-		cond_resched();
-	}
-
-	return count;
-}
-
-static void evict_old_buffers(struct dm_bufio_client *c, unsigned long age_hz)
-{
-	struct evict_params params = {.gfp = 0, .age_hz = age_hz, .last_accessed = 0};
-	unsigned long retain = get_retain_buffers(c);
-	unsigned long count;
-	LIST_HEAD(write_list);
-
-	dm_bufio_lock(c);
-
-	__check_watermark(c, &write_list);
-	if (unlikely(!list_empty(&write_list))) {
-		dm_bufio_unlock(c);
-		__flush_write_list(&write_list);
-		dm_bufio_lock(c);
-	}
-
-	count = cache_total(&c->cache);
-	if (count > retain)
-		__evict_many(c, &params, LIST_CLEAN, count - retain);
-
-	dm_bufio_unlock(c);
-}
-
-static void cleanup_old_buffers(void)
-{
-	unsigned long max_age_hz = get_max_age_hz();
-	struct dm_bufio_client *c;
-
-	mutex_lock(&dm_bufio_clients_lock);
-
-	__cache_size_refresh();
-
-	list_for_each_entry(c, &dm_bufio_all_clients, client_list)
-		evict_old_buffers(c, max_age_hz);
-
-	mutex_unlock(&dm_bufio_clients_lock);
-}
-
-static void work_fn(struct work_struct *w)
-{
-	cleanup_old_buffers();
-
-	queue_delayed_work(dm_bufio_wq, &dm_bufio_cleanup_old_work,
-			   DM_BUFIO_WORK_TIMER_SECS * HZ);
-}
-
-/*--------------------------------------------------------------*/
-
 /*
  * Global cleanup tries to evict the oldest buffers from across _all_
  * the clients.  It does this by repeatedly evicting a few buffers from
@@ -2843,27 +2704,55 @@ static void __insert_client(struct dm_bufio_client *new_client)
 	list_add_tail(&new_client->client_list, h);
 }
 
+static enum evict_result select_for_evict(struct dm_buffer *b, void *context)
+{
+	/* In no-sleep mode, we cannot wait on IO. */
+	if (static_branch_unlikely(&no_sleep_enabled) && b->c->no_sleep) {
+		if (test_bit_acquire(B_READING, &b->state) ||
+		    test_bit(B_WRITING, &b->state) ||
+		    test_bit(B_DIRTY, &b->state))
+			return ER_DONT_EVICT;
+	}
+	return ER_EVICT;
+}
+
 static unsigned long __evict_a_few(unsigned long nr_buffers)
 {
-	unsigned long count;
 	struct dm_bufio_client *c;
-	struct evict_params params = {
-		.gfp = GFP_KERNEL,
-		.age_hz = 0,
-		/* set to jiffies in case there are no buffers in this client */
-		.last_accessed = jiffies
-	};
+	unsigned long oldest_buffer = jiffies;
+	unsigned long last_accessed;
+	unsigned long count;
+	struct dm_buffer *b;
 
 	c = __pop_client();
 	if (!c)
 		return 0;
 
 	dm_bufio_lock(c);
-	count = __evict_many(c, &params, LIST_CLEAN, nr_buffers);
+
+	for (count = 0; count < nr_buffers; count++) {
+		b = cache_evict(&c->cache, LIST_CLEAN, select_for_evict, NULL);
+		if (!b)
+			break;
+
+		last_accessed = READ_ONCE(b->last_accessed);
+		if (time_after_eq(oldest_buffer, last_accessed))
+			oldest_buffer = last_accessed;
+
+		__make_buffer_clean(b);
+		__free_buffer_wake(b);
+
+		if (need_resched()) {
+			dm_bufio_unlock(c);
+			cond_resched();
+			dm_bufio_lock(c);
+		}
+	}
+
 	dm_bufio_unlock(c);
 
 	if (count)
-		c->oldest_buffer = params.last_accessed;
+		c->oldest_buffer = oldest_buffer;
 	__insert_client(c);
 
 	return count;
@@ -2946,10 +2835,7 @@ static int __init dm_bufio_init(void)
 	if (!dm_bufio_wq)
 		return -ENOMEM;
 
-	INIT_DELAYED_WORK(&dm_bufio_cleanup_old_work, work_fn);
 	INIT_WORK(&dm_bufio_replacement_work, do_global_cleanup);
-	queue_delayed_work(dm_bufio_wq, &dm_bufio_cleanup_old_work,
-			   DM_BUFIO_WORK_TIMER_SECS * HZ);
 
 	return 0;
 }
@@ -2961,7 +2847,6 @@ static void __exit dm_bufio_exit(void)
 {
 	int bug = 0;
 
-	cancel_delayed_work_sync(&dm_bufio_cleanup_old_work);
 	destroy_workqueue(dm_bufio_wq);
 
 	if (dm_bufio_client_count) {
@@ -2998,7 +2883,7 @@ module_param_named(max_cache_size_bytes, dm_bufio_cache_size, ulong, 0644);
 MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache");
 
 module_param_named(max_age_seconds, dm_bufio_max_age, uint, 0644);
-MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds");
+MODULE_PARM_DESC(max_age_seconds, "No longer does anything");
 
 module_param_named(retain_bytes, dm_bufio_retain_bytes, ulong, 0644);
 MODULE_PARM_DESC(retain_bytes, "Try to keep at least this many bytes cached in memory");

drivers/md/dm-core.h

@@ -141,6 +141,7 @@ struct mapped_device {
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int nr_zones;
 	void *zone_revalidate_map;
+	struct task_struct *revalidate_map_task;
 #endif
 
 #ifdef CONFIG_IMA
@@ -161,9 +162,7 @@ struct mapped_device {
 #define DMF_SUSPENDED_INTERNALLY 7
 #define DMF_POST_SUSPENDING 8
 #define DMF_EMULATE_ZONE_APPEND 9
-
-void disable_discard(struct mapped_device *md);
-void disable_write_zeroes(struct mapped_device *md);
+#define DMF_QUEUE_STOPPED 10
 
 static inline sector_t dm_get_size(struct mapped_device *md)
 {