Merge tag 'for-6.5/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Update DM crypt to allocate compound pages if possible

 - Fix DM crypt target's crypt_ctr_cipher_new return value on invalid
   AEAD cipher

 - Fix DM flakey testing target's write bio corruption feature to
   corrupt the data of a cloned bio instead of the original

 - Add random_read_corrupt and random_write_corrupt features to DM
   flakey target

 - Fix ABBA deadlock in DM thin metadata by resetting associated bufio
   client rather than destroying and recreating it

 - A couple other small DM thinp cleanups

 - Update DM core to support disabling block core IO stats accounting
   and optimize away code that isn't needed if stats are disabled

 - Other small DM core cleanups

 - Improve DM integrity target to not require so much memory on 32 bit
   systems. Also only allocate the recalculate buffer as needed (and
   increasingly reduce its size on allocation failure)

 - Update DM integrity to use %*ph for printing hexdump of a small
   buffer. Also update DM integrity documentation

 - Various DM core ioctl interface hardening. Now more careful about
   alignment of structures and processing of input passed to the kernel
   from userspace.

   Also disallow the creation of DM devices named "control", "." or ".."

 - Eliminate GFP_NOIO workarounds for __vmalloc and kvmalloc in DM
   core's ioctl and bufio code

* tag 'for-6.5/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (28 commits)
  dm: get rid of GFP_NOIO workarounds for __vmalloc and kvmalloc
  dm integrity: scale down the recalculate buffer if memory allocation fails
  dm integrity: only allocate recalculate buffer when needed
  dm integrity: reduce vmalloc space footprint on 32-bit architectures
  dm ioctl: Refuse to create device named "." or ".."
  dm ioctl: Refuse to create device named "control"
  dm ioctl: Avoid double-fetch of version
  dm ioctl: structs and parameter strings must not overlap
  dm ioctl: Avoid pointer arithmetic overflow
  dm ioctl: Check dm_target_spec is sufficiently aligned
  Documentation: dm-integrity: Document an example of how the tunables relate.
  Documentation: dm-integrity: Document default values.
  Documentation: dm-integrity: Document the meaning of "buffer".
  Documentation: dm-integrity: Fix minor grammatical error.
  dm integrity: Use %*ph for printing hexdump of a small buffer
  dm thin: disable discards for thin-pool if no_discard_passdown
  dm: remove stale/redundant dm_internal_{suspend,resume} prototypes in dm.h
  dm: skip dm-stats work in alloc_io() unless needed
  dm: avoid needless dm_io access if all IO accounting is disabled
  dm: support turning off block-core's io stats accounting
  ...

1 files changed, 38 insertions, 47 deletions

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 63ec502fcb12..3d5c56e0a062 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -34,11 +34,11 @@
 #define DEFAULT_BUFFER_SECTORS		128
 #define DEFAULT_JOURNAL_WATERMARK	50
 #define DEFAULT_SYNC_MSEC		10000
-#define DEFAULT_MAX_JOURNAL_SECTORS	131072
+#define DEFAULT_MAX_JOURNAL_SECTORS	(IS_ENABLED(CONFIG_64BIT) ? 131072 : 8192)
 #define MIN_LOG2_INTERLEAVE_SECTORS	3
 #define MAX_LOG2_INTERLEAVE_SECTORS	31
 #define METADATA_WORKQUEUE_MAX_ACTIVE	16
-#define RECALC_SECTORS			32768
+#define RECALC_SECTORS			(IS_ENABLED(CONFIG_64BIT) ? 32768 : 2048)
 #define RECALC_WRITE_SUPER		16
 #define BITMAP_BLOCK_SIZE		4096	/* don't change it */
 #define BITMAP_FLUSH_INTERVAL		(10 * HZ)
@@ -251,8 +251,6 @@ struct dm_integrity_c {
 
 	struct workqueue_struct *recalc_wq;
 	struct work_struct recalc_work;
-	u8 *recalc_buffer;
-	u8 *recalc_tags;
 
 	struct bio_list flush_bio_list;
 
@@ -342,24 +340,9 @@ static struct kmem_cache *journal_io_cache;
 #define JOURNAL_IO_MEMPOOL	32
 
 #ifdef DEBUG_PRINT
-#define DEBUG_print(x, ...)	printk(KERN_DEBUG x, ##__VA_ARGS__)
-static void __DEBUG_bytes(__u8 *bytes, size_t len, const char *msg, ...)
-{
-	va_list args;
-
-	va_start(args, msg);
-	vprintk(msg, args);
-	va_end(args);
-	if (len)
-		pr_cont(":");
-	while (len) {
-		pr_cont(" %02x", *bytes);
-		bytes++;
-		len--;
-	}
-	pr_cont("\n");
-}
-#define DEBUG_bytes(bytes, len, msg, ...)	__DEBUG_bytes(bytes, len, KERN_DEBUG msg, ##__VA_ARGS__)
+#define DEBUG_print(x, ...)			printk(KERN_DEBUG x, ##__VA_ARGS__)
+#define DEBUG_bytes(bytes, len, msg, ...)	printk(KERN_DEBUG msg "%s%*ph\n", ##__VA_ARGS__, \
+						       len ? ": " : "", len, bytes)
 #else
 #define DEBUG_print(x, ...)			do { } while (0)
 #define DEBUG_bytes(bytes, len, msg, ...)	do { } while (0)
@@ -2661,6 +2644,9 @@ static void recalc_write_super(struct dm_integrity_c *ic)
 static void integrity_recalc(struct work_struct *w)
 {
 	struct dm_integrity_c *ic = container_of(w, struct dm_integrity_c, recalc_work);
+	size_t recalc_tags_size;
+	u8 *recalc_buffer = NULL;
+	u8 *recalc_tags = NULL;
 	struct dm_integrity_range range;
 	struct dm_io_request io_req;
 	struct dm_io_region io_loc;
@@ -2672,6 +2658,26 @@ static void integrity_recalc(struct work_struct *w)
 	unsigned int i;
 	int r;
 	unsigned int super_counter = 0;
+	unsigned recalc_sectors = RECALC_SECTORS;
+
+retry:
+	recalc_buffer = __vmalloc(recalc_sectors << SECTOR_SHIFT, GFP_NOIO);
+	if (!recalc_buffer) {
+oom:
+		recalc_sectors >>= 1;
+		if (recalc_sectors >= 1U << ic->sb->log2_sectors_per_block)
+			goto retry;
+		DMCRIT("out of memory for recalculate buffer - recalculation disabled");
+		goto free_ret;
+	}
+	recalc_tags_size = (recalc_sectors >> ic->sb->log2_sectors_per_block) * ic->tag_size;
+	if (crypto_shash_digestsize(ic->internal_hash) > ic->tag_size)
+		recalc_tags_size += crypto_shash_digestsize(ic->internal_hash) - ic->tag_size;
+	recalc_tags = kvmalloc(recalc_tags_size, GFP_NOIO);
+	if (!recalc_tags) {
+		vfree(recalc_buffer);
+		goto oom;
+	}
 
 	DEBUG_print("start recalculation... (position %llx)\n", le64_to_cpu(ic->sb->recalc_sector));
 
@@ -2693,7 +2699,7 @@ next_chunk:
 	}
 
 	get_area_and_offset(ic, range.logical_sector, &area, &offset);
-	range.n_sectors = min((sector_t)RECALC_SECTORS, ic->provided_data_sectors - range.logical_sector);
+	range.n_sectors = min((sector_t)recalc_sectors, ic->provided_data_sectors - range.logical_sector);
 	if (!ic->meta_dev)
 		range.n_sectors = min(range.n_sectors, ((sector_t)1U << ic->sb->log2_interleave_sectors) - (unsigned int)offset);
 
@@ -2735,7 +2741,7 @@ next_chunk:
 
 	io_req.bi_opf = REQ_OP_READ;
 	io_req.mem.type = DM_IO_VMA;
-	io_req.mem.ptr.addr = ic->recalc_buffer;
+	io_req.mem.ptr.addr = recalc_buffer;
 	io_req.notify.fn = NULL;
 	io_req.client = ic->io;
 	io_loc.bdev = ic->dev->bdev;
@@ -2748,15 +2754,15 @@ next_chunk:
 		goto err;
 	}
 
-	t = ic->recalc_tags;
+	t = recalc_tags;
 	for (i = 0; i < n_sectors; i += ic->sectors_per_block) {
-		integrity_sector_checksum(ic, logical_sector + i, ic->recalc_buffer + (i << SECTOR_SHIFT), t);
+		integrity_sector_checksum(ic, logical_sector + i, recalc_buffer + (i << SECTOR_SHIFT), t);
 		t += ic->tag_size;
 	}
 
 	metadata_block = get_metadata_sector_and_offset(ic, area, offset, &metadata_offset);
 
-	r = dm_integrity_rw_tag(ic, ic->recalc_tags, &metadata_block, &metadata_offset, t - ic->recalc_tags, TAG_WRITE);
+	r = dm_integrity_rw_tag(ic, recalc_tags, &metadata_block, &metadata_offset, t - recalc_tags, TAG_WRITE);
 	if (unlikely(r)) {
 		dm_integrity_io_error(ic, "writing tags", r);
 		goto err;
@@ -2784,12 +2790,16 @@ advance_and_next:
 
 err:
 	remove_range(ic, &range);
-	return;
+	goto free_ret;
 
 unlock_ret:
 	spin_unlock_irq(&ic->endio_wait.lock);
 
 	recalc_write_super(ic);
+
+free_ret:
+	vfree(recalc_buffer);
+	kvfree(recalc_tags);
 }
 
 static void bitmap_block_work(struct work_struct *w)
@@ -4454,8 +4464,6 @@ try_smaller_buffer:
 	}
 
 	if (ic->internal_hash) {
-		size_t recalc_tags_size;
-
 		ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", WQ_MEM_RECLAIM, 1);
 		if (!ic->recalc_wq) {
 			ti->error = "Cannot allocate workqueue";
@@ -4463,21 +4471,6 @@ try_smaller_buffer:
 			goto bad;
 		}
 		INIT_WORK(&ic->recalc_work, integrity_recalc);
-		ic->recalc_buffer = vmalloc(RECALC_SECTORS << SECTOR_SHIFT);
-		if (!ic->recalc_buffer) {
-			ti->error = "Cannot allocate buffer for recalculating";
-			r = -ENOMEM;
-			goto bad;
-		}
-		recalc_tags_size = (RECALC_SECTORS >> ic->sb->log2_sectors_per_block) * ic->tag_size;
-		if (crypto_shash_digestsize(ic->internal_hash) > ic->tag_size)
-			recalc_tags_size += crypto_shash_digestsize(ic->internal_hash) - ic->tag_size;
-		ic->recalc_tags = kvmalloc(recalc_tags_size, GFP_KERNEL);
-		if (!ic->recalc_tags) {
-			ti->error = "Cannot allocate tags for recalculating";
-			r = -ENOMEM;
-			goto bad;
-		}
 	} else {
 		if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
 			ti->error = "Recalculate can only be specified with internal_hash";
@@ -4621,8 +4614,6 @@ static void dm_integrity_dtr(struct dm_target *ti)
 		destroy_workqueue(ic->writer_wq);
 	if (ic->recalc_wq)
 		destroy_workqueue(ic->recalc_wq);
-	vfree(ic->recalc_buffer);
-	kvfree(ic->recalc_tags);
 	kvfree(ic->bbs);
 	if (ic->bufio)
 		dm_bufio_client_destroy(ic->bufio);