Regression and bug fixes for ext4.

-----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAmUGh1YACgkQ8vlZVpUN
 gaN9lQgAqmMWu3xLwOERgVbK3CYT8WMcv0m9/by+vSwghCoPVDWWENgEgAzo4YpK
 Lsp4q62wHaWs6AzvJEaJ8ryedo7e4FUHxcvp2f6dCuOPadOEZZZTa4G5fAr0kYXS
 TIoaFtv6F2QVnGU6Y5lhtfYzmgLRdLL0B6MfSTYGO2MSREqxapvfxyGBQdkOuXfO
 UEtrUUEqQ2GdDcKp+FRRnaUvNaTPEESY8d5eVwrMmyUhQWUQL/N2BPbFkk1TP6RG
 MLDNsUZpdhZvLs6qLuR7dvO5wa2fshvRJIXlPINM0R0as5LmHqVL/ifCNkCn4W+k
 ZNvdSPhqew68KHHq3sYFtm9rbZ3YOA==
 =DopS
 -----END PGP SIGNATURE-----

Merge tag 'ext4_for_linus-6.6-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "Regression and bug fixes for ext4"

* tag 'ext4_for_linus-6.6-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: fix rec_len verify error
  ext4: do not let fstrim block system suspend
  ext4: move setting of trimmed bit into ext4_try_to_trim_range()
  jbd2: Fix memory leak in journal_init_common()
  jbd2: Remove page size assumptions
  buffer: Make bh_offset() work for compound pages

fs/ext4/mballoc.c

@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/nospec.h>
 #include <linux/backing-dev.h>
+#include <linux/freezer.h>
 #include <trace/events/ext4.h>
 
 /*
@@ -6906,6 +6907,21 @@ __acquires(bitlock)
 	return ret;
 }
 
+static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb,
+					   ext4_group_t grp)
+{
+	if (grp < ext4_get_groups_count(sb))
+		return EXT4_CLUSTERS_PER_GROUP(sb) - 1;
+	return (ext4_blocks_count(EXT4_SB(sb)->s_es) -
+		ext4_group_first_block_no(sb, grp) - 1) >>
+					EXT4_CLUSTER_BITS(sb);
+}
+
+static bool ext4_trim_interrupted(void)
+{
+	return fatal_signal_pending(current) || freezing(current);
+}
+
 static int ext4_try_to_trim_range(struct super_block *sb,
 		struct ext4_buddy *e4b, ext4_grpblk_t start,
 		ext4_grpblk_t max, ext4_grpblk_t minblocks)
@@ -6913,9 +6929,12 @@ __acquires(ext4_group_lock_ptr(sb, e4b->bd_group))
 __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 {
 	ext4_grpblk_t next, count, free_count;
+	bool set_trimmed = false;
 	void *bitmap;
 
 	bitmap = e4b->bd_bitmap;
+	if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group))
+		set_trimmed = true;
 	start = max(e4b->bd_info->bb_first_free, start);
 	count = 0;
 	free_count = 0;
@@ -6930,16 +6949,14 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 			int ret = ext4_trim_extent(sb, start, next - start, e4b);
 
 			if (ret && ret != -EOPNOTSUPP)
-				break;
+				return count;
 			count += next - start;
 		}
 		free_count += next - start;
 		start = next + 1;
 
-		if (fatal_signal_pending(current)) {
-			count = -ERESTARTSYS;
-			break;
-		}
+		if (ext4_trim_interrupted())
+			return count;
 
 		if (need_resched()) {
 			ext4_unlock_group(sb, e4b->bd_group);
@@ -6951,6 +6968,9 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 			break;
 	}
 
+	if (set_trimmed)
+		EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info);
+
 	return count;
 }
 
@@ -6961,7 +6981,6 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
  * @start:		first group block to examine
  * @max:		last group block to examine
  * @minblocks:		minimum extent block count
- * @set_trimmed:	set the trimmed flag if at least one block is trimmed
  *
  * ext4_trim_all_free walks through group's block bitmap searching for free
  * extents. When the free extent is found, mark it as used in group buddy
@@ -6971,7 +6990,7 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 static ext4_grpblk_t
 ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 		   ext4_grpblk_t start, ext4_grpblk_t max,
-		   ext4_grpblk_t minblocks, bool set_trimmed)
+		   ext4_grpblk_t minblocks)
 {
 	struct ext4_buddy e4b;
 	int ret;
@@ -6988,13 +7007,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 	ext4_lock_group(sb, group);
 
 	if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) ||
-	    minblocks < EXT4_SB(sb)->s_last_trim_minblks) {
+	    minblocks < EXT4_SB(sb)->s_last_trim_minblks)
 		ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks);
-		if (ret >= 0 && set_trimmed)
-			EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
-	} else {
+	else
 		ret = 0;
-	}
 
 	ext4_unlock_group(sb, group);
 	ext4_mb_unload_buddy(&e4b);
@@ -7027,7 +7043,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	ext4_fsblk_t first_data_blk =
 			le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
 	ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es);
-	bool whole_group, eof = false;
 	int ret = 0;
 
 	start = range->start >> sb->s_blocksize_bits;
@@ -7046,10 +7061,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		if (minlen > EXT4_CLUSTERS_PER_GROUP(sb))
 			goto out;
 	}
-	if (end >= max_blks - 1) {
+	if (end >= max_blks - 1)
 		end = max_blks - 1;
-		eof = true;
-	}
 	if (end <= first_data_blk)
 		goto out;
 	if (start < first_data_blk)
@@ -7063,9 +7076,10 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 
 	/* end now represents the last cluster to discard in this group */
 	end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
-	whole_group = true;
 
 	for (group = first_group; group <= last_group; group++) {
+		if (ext4_trim_interrupted())
+			break;
 		grp = ext4_get_group_info(sb, group);
 		if (!grp)
 			continue;
@@ -7082,13 +7096,11 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		 * change it for the last group, note that last_cluster is
 		 * already computed earlier by ext4_get_group_no_and_offset()
 		 */
-		if (group == last_group) {
+		if (group == last_group)
 			end = last_cluster;
-			whole_group = eof ? true : end == EXT4_CLUSTERS_PER_GROUP(sb) - 1;
-		}
 		if (grp->bb_free >= minlen) {
 			cnt = ext4_trim_all_free(sb, group, first_cluster,
-						 end, minlen, whole_group);
+						 end, minlen);
 			if (cnt < 0) {
 				ret = cnt;
 				break;

fs/ext4/namei.c

@@ -343,17 +343,17 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
 						   struct buffer_head *bh)
 {
 	struct ext4_dir_entry_tail *t;
+	int blocksize = EXT4_BLOCK_SIZE(inode->i_sb);
 
 #ifdef PARANOID
 	struct ext4_dir_entry *d, *top;
 
 	d = (struct ext4_dir_entry *)bh->b_data;
 	top = (struct ext4_dir_entry *)(bh->b_data +
-		(EXT4_BLOCK_SIZE(inode->i_sb) -
-		 sizeof(struct ext4_dir_entry_tail)));
-	while (d < top && d->rec_len)
+		(blocksize - sizeof(struct ext4_dir_entry_tail)));
+	while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize))
 		d = (struct ext4_dir_entry *)(((void *)d) +
-		    le16_to_cpu(d->rec_len));
+		    ext4_rec_len_from_disk(d->rec_len, blocksize));
 
 	if (d != top)
 		return NULL;
@@ -364,7 +364,8 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
 #endif
 
 	if (t->det_reserved_zero1 ||
-	    le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) ||
+	    (ext4_rec_len_from_disk(t->det_rec_len, blocksize) !=
+	     sizeof(struct ext4_dir_entry_tail)) ||
 	    t->det_reserved_zero2 ||
 	    t->det_reserved_ft != EXT4_FT_DIR_CSUM)
 		return NULL;
@@ -445,13 +446,14 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode,
 	struct ext4_dir_entry *dp;
 	struct dx_root_info *root;
 	int count_offset;
+	int blocksize = EXT4_BLOCK_SIZE(inode->i_sb);
+	unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize);
 
-	if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb))
+	if (rlen == blocksize)
 		count_offset = 8;
-	else if (le16_to_cpu(dirent->rec_len) == 12) {
+	else if (rlen == 12) {
 		dp = (struct ext4_dir_entry *)(((void *)dirent) + 12);
-		if (le16_to_cpu(dp->rec_len) !=
-		    EXT4_BLOCK_SIZE(inode->i_sb) - 12)
+		if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12)
 			return NULL;
 		root = (struct dx_root_info *)(((void *)dp + 12));
 		if (root->reserved_zero ||
@@ -1315,6 +1317,7 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh,
 	unsigned int buflen = bh->b_size;
 	char *base = bh->b_data;
 	struct dx_hash_info h = *hinfo;
+	int blocksize = EXT4_BLOCK_SIZE(dir->i_sb);
 
 	if (ext4_has_metadata_csum(dir->i_sb))
 		buflen -= sizeof(struct ext4_dir_entry_tail);
@@ -1335,11 +1338,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh,
 			map_tail--;
 			map_tail->hash = h.hash;
 			map_tail->offs = ((char *) de - base)>>2;
-			map_tail->size = le16_to_cpu(de->rec_len);
+			map_tail->size = ext4_rec_len_from_disk(de->rec_len,
+								blocksize);
 			count++;
 			cond_resched();
 		}
-		de = ext4_next_entry(de, dir->i_sb->s_blocksize);
+		de = ext4_next_entry(de, blocksize);
 	}
 	return count;
 }

fs/jbd2/commit.c

@@ -298,14 +298,12 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 
 static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
 {
-	struct page *page = bh->b_page;
 	char *addr;
 	__u32 checksum;
 
-	addr = kmap_atomic(page);
-	checksum = crc32_be(crc32_sum,
-		(void *)(addr + offset_in_page(bh->b_data)), bh->b_size);
-	kunmap_atomic(addr);
+	addr = kmap_local_folio(bh->b_folio, bh_offset(bh));
+	checksum = crc32_be(crc32_sum, addr, bh->b_size);
+	kunmap_local(addr);
 
 	return checksum;
 }
@@ -322,7 +320,6 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 				    struct buffer_head *bh, __u32 sequence)
 {
 	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
-	struct page *page = bh->b_page;
 	__u8 *addr;
 	__u32 csum32;
 	__be32 seq;
@@ -331,11 +328,10 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 		return;
 
 	seq = cpu_to_be32(sequence);
-	addr = kmap_atomic(page);
+	addr = kmap_local_folio(bh->b_folio, bh_offset(bh));
 	csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
-	csum32 = jbd2_chksum(j, csum32, addr + offset_in_page(bh->b_data),
-			     bh->b_size);
-	kunmap_atomic(addr);
+	csum32 = jbd2_chksum(j, csum32, addr, bh->b_size);
+	kunmap_local(addr);
 
 	if (jbd2_has_feature_csum3(j))
 		tag3->t_checksum = cpu_to_be32(csum32);

fs/jbd2/journal.c

@@ -1601,6 +1601,8 @@ static journal_t *journal_init_common(struct block_device *bdev,
 
 err_cleanup:
 	percpu_counter_destroy(&journal->j_checkpoint_jh_count);
+	if (journal->j_chksum_driver)
+		crypto_free_shash(journal->j_chksum_driver);
 	kfree(journal->j_wbuf);
 	jbd2_journal_destroy_revoke(journal);
 	journal_fail_superblock(journal);

fs/jbd2/transaction.c

@@ -935,19 +935,15 @@ static void warn_dirty_buffer(struct buffer_head *bh)
 /* Call t_frozen trigger and copy buffer data into jh->b_frozen_data. */
 static void jbd2_freeze_jh_data(struct journal_head *jh)
 {
-	struct page *page;
-	int offset;
 	char *source;
 	struct buffer_head *bh = jh2bh(jh);
 
 	J_EXPECT_JH(jh, buffer_uptodate(bh), "Possible IO failure.\n");
-	page = bh->b_page;
-	offset = offset_in_page(bh->b_data);
-	source = kmap_atomic(page);
+	source = kmap_local_folio(bh->b_folio, bh_offset(bh));
 	/* Fire data frozen trigger just before we copy the data */
-	jbd2_buffer_frozen_trigger(jh, source + offset, jh->b_triggers);
-	memcpy(jh->b_frozen_data, source + offset, bh->b_size);
-	kunmap_atomic(source);
+	jbd2_buffer_frozen_trigger(jh, source, jh->b_triggers);
+	memcpy(jh->b_frozen_data, source, bh->b_size);
+	kunmap_local(source);
 
 	/*
 	 * Now that the frozen data is saved off, we need to store any matching

include/linux/buffer_head.h

@@ -171,7 +171,10 @@ static __always_inline int buffer_uptodate(const struct buffer_head *bh)
 	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
-#define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
+static inline unsigned long bh_offset(const struct buffer_head *bh)
+{
+	return (unsigned long)(bh)->b_data & (page_size(bh->b_page) - 1);
+}
 
 /* If we *know* page->private refers to buffer_heads */
 #define page_buffers(page)					\