Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

7 files changed, 92 insertions, 85 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 537803250..30e824866 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2334,7 +2334,7 @@ static int mpage_journal_page_buffers(handle_t *handle,
 
 	if (folio_pos(folio) + len > size &&
 	    !ext4_verity_in_progress(inode))
-		len = size - folio_pos(folio);
+		len = size & (len - 1);
 
 	return ext4_journal_folio_buffers(handle, folio, len);
 }
@@ -2887,9 +2887,6 @@ retry:
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
-	/* In case writeback began while the folio was unlocked */
-	folio_wait_stable(folio);
-
 #ifdef CONFIG_FS_ENCRYPTION
 	ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep);
 #else
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 12b3f1960..66b5a68b0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -831,6 +831,8 @@ static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len)
 		return 0;
 	if (order == MB_NUM_ORDERS(sb))
 		order--;
+	if (WARN_ON_ONCE(order > MB_NUM_ORDERS(sb)))
+		order = MB_NUM_ORDERS(sb) - 1;
 	return order;
 }
 
@@ -1008,6 +1010,8 @@ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context
 	 * goal length.
 	 */
 	order = fls(ac->ac_g_ex.fe_len) - 1;
+	if (WARN_ON_ONCE(order - 1 > MB_NUM_ORDERS(ac->ac_sb)))
+		order = MB_NUM_ORDERS(ac->ac_sb);
 	min_order = order - sbi->s_mb_best_avail_max_trim_order;
 	if (min_order < 0)
 		min_order = 0;
@@ -6113,6 +6117,7 @@ ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp)
 	ext4_mb_mark_bb(sb, block, 1, true);
 	ar->len = 1;
 
+	*errp = 0;
 	return block;
 }
 
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 56938532b..7bfc5fb5a 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -193,8 +193,8 @@ struct ext4_allocation_context {
 	ext4_grpblk_t	ac_orig_goal_len;
 
 	__u32 ac_flags;		/* allocation hints */
+	__u32 ac_groups_linear_remaining;
 	__u16 ac_groups_scanned;
-	__u16 ac_groups_linear_remaining;
 	__u16 ac_found;
 	__u16 ac_cX_found[EXT4_MB_NUM_CRS];
 	__u16 ac_tail;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5e4f65c14..a630b27a4 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2897,7 +2897,7 @@ retry:
 	inode = ext4_new_inode_start_handle(idmap, dir, mode,
 					    NULL, 0, NULL,
 					    EXT4_HT_DIR,
-			EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+			EXT4_MAXQUOTAS_TRANS_BLOCKS(dir->i_sb) +
 			  4 + EXT4_XATTR_TRANS_BLOCKS);
 	handle = ext4_journal_current_handle();
 	err = PTR_ERR(inode);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 044135796..4b368f4db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5551,19 +5551,15 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	if (err)
 		goto failed_mount6;
 
-	err = ext4_register_sysfs(sb);
-	if (err)
-		goto failed_mount7;
-
 	err = ext4_init_orphan_info(sb);
 	if (err)
-		goto failed_mount8;
+		goto failed_mount7;
 #ifdef CONFIG_QUOTA
 	/* Enable quota usage during mount. */
 	if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) {
 		err = ext4_enable_quotas(sb);
 		if (err)
-			goto failed_mount9;
+			goto failed_mount8;
 	}
 #endif  /* CONFIG_QUOTA */
 
@@ -5589,7 +5585,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		ext4_msg(sb, KERN_INFO, "recovery complete");
 		err = ext4_mark_recovery_complete(sb, es);
 		if (err)
-			goto failed_mount10;
+			goto failed_mount9;
 	}
 
 	if (test_opt(sb, DISCARD) && !bdev_max_discard_sectors(sb->s_bdev))
@@ -5606,15 +5602,17 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	atomic_set(&sbi->s_warning_count, 0);
 	atomic_set(&sbi->s_msg_count, 0);
 
+	/* Register sysfs after all initializations are complete. */
+	err = ext4_register_sysfs(sb);
+	if (err)
+		goto failed_mount9;
+
 	return 0;
 
-failed_mount10:
+failed_mount9:
 	ext4_quotas_off(sb, EXT4_MAXQUOTAS);
-failed_mount9: __maybe_unused
+failed_mount8: __maybe_unused
 	ext4_release_orphan_info(sb);
-failed_mount8:
-	ext4_unregister_sysfs(sb);
-	kobject_put(&sbi->s_kobj);
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 6d332dff7..63cbda370 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -29,6 +29,7 @@ typedef enum {
 	attr_trigger_test_error,
 	attr_first_error_time,
 	attr_last_error_time,
+	attr_clusters_in_group,
 	attr_feature,
 	attr_pointer_ui,
 	attr_pointer_ul,
@@ -104,7 +105,7 @@ static ssize_t reserved_clusters_store(struct ext4_sb_info *sbi,
 	int ret;
 
 	ret = kstrtoull(skip_spaces(buf), 0, &val);
-	if (ret || val >= clusters)
+	if (ret || val >= clusters || (s64)val < 0)
 		return -EINVAL;
 
 	atomic64_set(&sbi->s_resv_clusters, val);
@@ -207,13 +208,14 @@ EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444);
 
 EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead,
 		 ext4_sb_info, s_inode_readahead_blks);
+EXT4_ATTR_OFFSET(mb_group_prealloc, 0644, clusters_in_group,
+		 ext4_sb_info, s_mb_group_prealloc);
 EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
 EXT4_RW_ATTR_SBI_UI(mb_stats, s_mb_stats);
 EXT4_RW_ATTR_SBI_UI(mb_max_to_scan, s_mb_max_to_scan);
 EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
 EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
 EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
-EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
 EXT4_RW_ATTR_SBI_UI(mb_max_linear_groups, s_mb_max_linear_groups);
 EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
 EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error);
@@ -392,6 +394,7 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 				(unsigned long long)
 			percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit));
 	case attr_inode_readahead:
+	case attr_clusters_in_group:
 	case attr_pointer_ui:
 		if (!ptr)
 			return 0;
@@ -451,7 +454,8 @@ static ssize_t ext4_attr_store(struct kobject *kobj,
 						s_kobj);
 	struct ext4_attr *a = container_of(attr, struct ext4_attr, attr);
 	void *ptr = calc_ptr(a, sbi);
-	unsigned long t;
+	unsigned int t;
+	unsigned long lt;
 	int ret;
 
 	switch (a->attr_id) {
@@ -460,7 +464,7 @@ static ssize_t ext4_attr_store(struct kobject *kobj,
 	case attr_pointer_ui:
 		if (!ptr)
 			return 0;
-		ret = kstrtoul(skip_spaces(buf), 0, &t);
+		ret = kstrtouint(skip_spaces(buf), 0, &t);
 		if (ret)
 			return ret;
 		if (a->attr_ptr == ptr_ext4_super_block_offset)
@@ -468,13 +472,21 @@ static ssize_t ext4_attr_store(struct kobject *kobj,
 		else
 			*((unsigned int *) ptr) = t;
 		return len;
+	case attr_clusters_in_group:
+		ret = kstrtouint(skip_spaces(buf), 0, &t);
+		if (ret)
+			return ret;
+		if (t > sbi->s_clusters_per_group)
+			return -EINVAL;
+		*((unsigned int *) ptr) = t;
+		return len;
 	case attr_pointer_ul:
 		if (!ptr)
 			return 0;
-		ret = kstrtoul(skip_spaces(buf), 0, &t);
+		ret = kstrtoul(skip_spaces(buf), 0, &lt);
 		if (ret)
 			return ret;
-		*((unsigned long *) ptr) = t;
+		*((unsigned long *) ptr) = lt;
 		return len;
 	case attr_inode_readahead:
 		return inode_readahead_blks_store(sbi, buf, len);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index b67a176bf..78f06f86c 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1619,6 +1619,7 @@ out_err:
 static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 				struct ext4_xattr_search *s,
 				handle_t *handle, struct inode *inode,
+				struct inode *new_ea_inode,
 				bool is_block)
 {
 	struct ext4_xattr_entry *last, *next;
@@ -1626,7 +1627,6 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 	size_t min_offs = s->end - s->base, name_len = strlen(i->name);
 	int in_inode = i->in_inode;
 	struct inode *old_ea_inode = NULL;
-	struct inode *new_ea_inode = NULL;
 	size_t old_size, new_size;
 	int ret;
 
@@ -1711,38 +1711,11 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 			old_ea_inode = NULL;
 			goto out;
 		}
-	}
-	if (i->value && in_inode) {
-		WARN_ON_ONCE(!i->value_len);
-
-		new_ea_inode = ext4_xattr_inode_lookup_create(handle, inode,
-					i->value, i->value_len);
-		if (IS_ERR(new_ea_inode)) {
-			ret = PTR_ERR(new_ea_inode);
-			new_ea_inode = NULL;
-			goto out;
-		}
-	}
 
-	if (old_ea_inode) {
 		/* We are ready to release ref count on the old_ea_inode. */
 		ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode);
-		if (ret) {
-			/* Release newly required ref count on new_ea_inode. */
-			if (new_ea_inode) {
-				int err;
-
-				err = ext4_xattr_inode_dec_ref(handle,
-							       new_ea_inode);
-				if (err)
-					ext4_warning_inode(new_ea_inode,
-						  "dec ref new_ea_inode err=%d",
-						  err);
-				ext4_xattr_inode_free_quota(inode, new_ea_inode,
-							    i->value_len);
-			}
+		if (ret)
 			goto out;
-		}
 
 		ext4_xattr_inode_free_quota(inode, old_ea_inode,
 					    le32_to_cpu(here->e_value_size));
@@ -1866,7 +1839,6 @@ update_hash:
 	ret = 0;
 out:
 	iput(old_ea_inode);
-	iput(new_ea_inode);
 	return ret;
 }
 
@@ -1929,9 +1901,21 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 	size_t old_ea_inode_quota = 0;
 	unsigned int ea_ino;
 
-
 #define header(x) ((struct ext4_xattr_header *)(x))
 
+	/* If we need EA inode, prepare it before locking the buffer */
+	if (i->value && i->in_inode) {
+		WARN_ON_ONCE(!i->value_len);
+
+		ea_inode = ext4_xattr_inode_lookup_create(handle, inode,
+					i->value, i->value_len);
+		if (IS_ERR(ea_inode)) {
+			error = PTR_ERR(ea_inode);
+			ea_inode = NULL;
+			goto cleanup;
+		}
+	}
+
 	if (s->base) {
 		int offset = (char *)s->here - bs->bh->b_data;
 
@@ -1940,6 +1924,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 						      EXT4_JTR_NONE);
 		if (error)
 			goto cleanup;
+
 		lock_buffer(bs->bh);
 
 		if (header(s->base)->h_refcount == cpu_to_le32(1)) {
@@ -1966,7 +1951,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			}
 			ea_bdebug(bs->bh, "modifying in-place");
 			error = ext4_xattr_set_entry(i, s, handle, inode,
-						     true /* is_block */);
+					     ea_inode, true /* is_block */);
 			ext4_xattr_block_csum_set(inode, bs->bh);
 			unlock_buffer(bs->bh);
 			if (error == -EFSCORRUPTED)
@@ -2034,29 +2019,13 @@ clone_block:
 		s->end = s->base + sb->s_blocksize;
 	}
 
-	error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */);
+	error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode,
+				     true /* is_block */);
 	if (error == -EFSCORRUPTED)
 		goto bad_block;
 	if (error)
 		goto cleanup;
 
-	if (i->value && s->here->e_value_inum) {
-		/*
-		 * A ref count on ea_inode has been taken as part of the call to
-		 * ext4_xattr_set_entry() above. We would like to drop this
-		 * extra ref but we have to wait until the xattr block is
-		 * initialized and has its own ref count on the ea_inode.
-		 */
-		ea_ino = le32_to_cpu(s->here->e_value_inum);
-		error = ext4_xattr_inode_iget(inode, ea_ino,
-					      le32_to_cpu(s->here->e_hash),
-					      &ea_inode);
-		if (error) {
-			ea_inode = NULL;
-			goto cleanup;
-		}
-	}
-
 inserted:
 	if (!IS_LAST_ENTRY(s->first)) {
 		new_bh = ext4_xattr_block_cache_find(inode, header(s->base),
@@ -2198,17 +2167,16 @@ getblk_failed:
 
 cleanup:
 	if (ea_inode) {
-		int error2;
-
-		error2 = ext4_xattr_inode_dec_ref(handle, ea_inode);
-		if (error2)
-			ext4_warning_inode(ea_inode, "dec ref error=%d",
-					   error2);
+		if (error) {
+			int error2;
 
-		/* If there was an error, revert the quota charge. */
-		if (error)
+			error2 = ext4_xattr_inode_dec_ref(handle, ea_inode);
+			if (error2)
+				ext4_warning_inode(ea_inode, "dec ref error=%d",
+						   error2);
 			ext4_xattr_inode_free_quota(inode, ea_inode,
 						    i_size_read(ea_inode));
+		}
 		iput(ea_inode);
 	}
 	if (ce)
@@ -2266,14 +2234,38 @@ int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
 {
 	struct ext4_xattr_ibody_header *header;
 	struct ext4_xattr_search *s = &is->s;
+	struct inode *ea_inode = NULL;
 	int error;
 
 	if (!EXT4_INODE_HAS_XATTR_SPACE(inode))
 		return -ENOSPC;
 
-	error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
-	if (error)
+	/* If we need EA inode, prepare it before locking the buffer */
+	if (i->value && i->in_inode) {
+		WARN_ON_ONCE(!i->value_len);
+
+		ea_inode = ext4_xattr_inode_lookup_create(handle, inode,
+					i->value, i->value_len);
+		if (IS_ERR(ea_inode))
+			return PTR_ERR(ea_inode);
+	}
+	error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode,
+				     false /* is_block */);
+	if (error) {
+		if (ea_inode) {
+			int error2;
+
+			error2 = ext4_xattr_inode_dec_ref(handle, ea_inode);
+			if (error2)
+				ext4_warning_inode(ea_inode, "dec ref error=%d",
+						   error2);
+
+			ext4_xattr_inode_free_quota(inode, ea_inode,
+						    i_size_read(ea_inode));
+			iput(ea_inode);
+		}
 		return error;
+	}
 	header = IHDR(inode, ext4_raw_inode(&is->iloc));
 	if (!IS_LAST_ENTRY(s->first)) {
 		header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
@@ -2282,6 +2274,7 @@ int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
 		header->h_magic = cpu_to_le32(0);
 		ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
 	}
+	iput(ea_inode);
 	return 0;
 }
 
@@ -3113,8 +3106,10 @@ ext4_xattr_block_cache_find(struct inode *inode,
 
 		bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO);
 		if (IS_ERR(bh)) {
-			if (PTR_ERR(bh) == -ENOMEM)
+			if (PTR_ERR(bh) == -ENOMEM) {
+				mb_cache_entry_put(ea_block_cache, ce);
 				return NULL;
+			}
 			bh = NULL;
 			EXT4_ERROR_INODE(inode, "block %lu read error",
 					 (unsigned long)ce->e_value);