lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 23 Nov 2023 20:51:09 +0800
From: Zhang Yi <yi.zhang@...weicloud.com>
To: linux-ext4@...r.kernel.org
Cc: linux-fsdevel@...r.kernel.org,
	tytso@....edu,
	adilger.kernel@...ger.ca,
	jack@...e.cz,
	ritesh.list@...il.com,
	hch@...radead.org,
	djwong@...nel.org,
	yi.zhang@...wei.com,
	yi.zhang@...weicloud.com,
	chengzhihao1@...wei.com,
	yukuai3@...wei.com
Subject: [RFC PATCH 07/18] ext4: allow reserving multi-delayed blocks

From: Zhang Yi <yi.zhang@...wei.com>

Introduce a new helper ext4_insert_delayed_blocks() to support adding
multi-delayed blocks into the extent status tree, it doesn't support
bigalloc feature yet. Also rename ext4_es_insert_delayed_block() to
ext4_es_insert_delayed_extent(), which matches the name style of other
ext4_es_{insert|remove}_extent() helpers.

Signed-off-by: Zhang Yi <yi.zhang@...wei.com>
---
 fs/ext4/extents_status.c    | 20 +++++----
 fs/ext4/extents_status.h    |  4 +-
 fs/ext4/inode.c             | 82 ++++++++++++++++++++++++-------------
 include/trace/events/ext4.h | 12 +++---
 4 files changed, 74 insertions(+), 44 deletions(-)

diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 19a0cc904cd8..c8783b4009ec 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -2043,19 +2043,21 @@ bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk)
 }
 
 /*
- * ext4_es_insert_delayed_block - adds a delayed block to the extents status
- *                                tree, adding a pending reservation where
- *                                needed
+ * ext4_es_insert_delayed_extent - adds delayed blocks to the extents status
+ *                                 tree, adding a pending reservation where
+ *                                 needed
  *
  * @inode - file containing the newly added block
- * @lblk - logical block to be added
+ * @lblk - first logical block to be added
+ * @len - length of blocks to be added
  * @allocated - indicates whether a physical cluster has been allocated for
  *              the logical cluster that contains the block
  */
-void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
-				  bool allocated)
+void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
+				   unsigned int len, bool allocated)
 {
 	struct extent_status newes;
+	ext4_lblk_t end = lblk + len - 1;
 	int err1 = 0;
 	int err2 = 0;
 	struct extent_status *es1 = NULL;
@@ -2068,9 +2070,9 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
 		 lblk, inode->i_ino);
 
 	newes.es_lblk = lblk;
-	newes.es_len = 1;
+	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED);
-	trace_ext4_es_insert_delayed_block(inode, &newes, allocated);
+	trace_ext4_es_insert_delayed_extent(inode, &newes, allocated);
 
 	ext4_es_insert_extent_check(inode, &newes);
 
@@ -2081,7 +2083,7 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
 		es2 = __es_alloc_extent(true);
 	write_lock(&EXT4_I(inode)->i_es_lock);
 
-	err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1);
+	err1 = __es_remove_extent(inode, lblk, end, NULL, es1);
 	if (err1 != 0)
 		goto error;
 	/* Free preallocated extent if it didn't get used. */
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 4f69322dd626..4ccc965a9876 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -251,8 +251,8 @@ extern void ext4_exit_pending(void);
 extern void ext4_init_pending_tree(struct ext4_pending_tree *tree);
 extern void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk);
 extern bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk);
-extern void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
-					 bool allocated);
+extern void ext4_es_insert_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
+					  unsigned int len, bool allocated);
 extern unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk,
 					ext4_lblk_t len);
 extern void ext4_clear_inode_es(struct inode *inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 17fe2bd83617..e92b205b3b24 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1462,7 +1462,7 @@ static int ext4_journalled_write_end(struct file *file,
 /*
  * Reserve space for a single cluster
  */
-static int ext4_da_reserve_space(struct inode *inode)
+static int ext4_da_reserve_space(struct inode *inode, unsigned int len)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -1473,18 +1473,18 @@ static int ext4_da_reserve_space(struct inode *inode)
 	 * us from metadata over-estimation, though we may go over by
 	 * a small amount in the end.  Here we just reserve for data.
 	 */
-	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
+	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, len));
 	if (ret)
 		return ret;
 
 	spin_lock(&ei->i_block_reservation_lock);
-	if (ext4_claim_free_clusters(sbi, 1, 0)) {
+	if (ext4_claim_free_clusters(sbi, len, 0)) {
 		spin_unlock(&ei->i_block_reservation_lock);
-		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
+		dquot_release_reservation_block(inode, EXT4_C2B(sbi, len));
 		return -ENOSPC;
 	}
-	ei->i_reserved_data_blocks++;
-	trace_ext4_da_reserve_space(inode);
+	ei->i_reserved_data_blocks += len;
+	trace_ext4_da_reserve_space(inode, len);
 	spin_unlock(&ei->i_block_reservation_lock);
 
 	return 0;       /* success */
@@ -1630,6 +1630,37 @@ static void ext4_print_free_blocks(struct inode *inode)
 	return;
 }
 
+
+/*
+ * ext4_insert_delayed_blocks - adds multi-delayed blocks to the extents
+ *                              status tree, incrementing the reserved
+ *                              cluster/block count or making a pending
+ *                              reservation where needed.
+ *
+ * @inode - file containing the newly added block
+ * @lblk - start logical block to be added
+ * @len - length of blocks to be added
+ *
+ * Returns 0 on success, negative error code on failure.
+ */
+static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk,
+				      ext4_lblk_t len)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int ret;
+
+	/* TODO: support bigalloc and replace ext4_insert_delayed_block(). */
+	if (sbi->s_cluster_ratio != 1)
+		return -EOPNOTSUPP;
+
+	ret = ext4_da_reserve_space(inode, len);
+	if (ret)   /* ENOSPC */
+		return ret;
+
+	ext4_es_insert_delayed_extent(inode, lblk, len, false);
+	return 0;
+}
+
 /*
  * ext4_insert_delayed_block - adds a delayed block to the extents status
  *                             tree, incrementing the reserved cluster/block
@@ -1647,10 +1678,13 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
 	int ret;
 	bool allocated = false;
 
+	if (sbi->s_cluster_ratio == 1)
+		return ext4_insert_delayed_blocks(inode, lblk, 1);
+
 	/*
-	 * If the cluster containing lblk is shared with a delayed,
-	 * written, or unwritten extent in a bigalloc file system, it's
-	 * already been accounted for and does not need to be reserved.
+	 * For bigalloc, if the cluster containing lblk is shared with a
+	 * delayed, written, or unwritten extent in a bigalloc file system,
+	 * it's already been accounted for and does not need to be reserved.
 	 * A pending reservation must be made for the cluster if it's
 	 * shared with a written or unwritten extent and doesn't already
 	 * have one.  Written and unwritten extents can be purged from the
@@ -1658,32 +1692,24 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
 	 * it's necessary to examine the extent tree if a search of the
 	 * extents status tree doesn't get a match.
 	 */
-	if (sbi->s_cluster_ratio == 1) {
-		ret = ext4_da_reserve_space(inode);
-		if (ret != 0)   /* ENOSPC */
-			return ret;
-	} else {   /* bigalloc */
-		if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
-			if (!ext4_es_scan_clu(inode,
-					      &ext4_es_is_mapped, lblk)) {
-				ret = ext4_clu_mapped(inode,
-						      EXT4_B2C(sbi, lblk));
-				if (ret < 0)
+	if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
+		if (!ext4_es_scan_clu(inode, &ext4_es_is_mapped, lblk)) {
+			ret = ext4_clu_mapped(inode, EXT4_B2C(sbi, lblk));
+			if (ret < 0)
+				return ret;
+			if (ret == 0) {
+				ret = ext4_da_reserve_space(inode, 1);
+				if (ret != 0)   /* ENOSPC */
 					return ret;
-				if (ret == 0) {
-					ret = ext4_da_reserve_space(inode);
-					if (ret != 0)   /* ENOSPC */
-						return ret;
-				} else {
-					allocated = true;
-				}
 			} else {
 				allocated = true;
 			}
+		} else {
+			allocated = true;
 		}
 	}
 
-	ext4_es_insert_delayed_block(inode, lblk, allocated);
+	ext4_es_insert_delayed_extent(inode, lblk, 1, allocated);
 	return 0;
 }
 
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 84421cecec0b..6b871d42b259 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -1249,14 +1249,15 @@ TRACE_EVENT(ext4_da_update_reserve_space,
 );
 
 TRACE_EVENT(ext4_da_reserve_space,
-	TP_PROTO(struct inode *inode),
+	TP_PROTO(struct inode *inode, int reserved_blocks),
 
-	TP_ARGS(inode),
+	TP_ARGS(inode, reserved_blocks),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(	ino_t,	ino			)
 		__field(	__u64,	i_blocks		)
+		__field(	int,	reserved_blocks		)
 		__field(	int,	reserved_data_blocks	)
 		__field(	__u16,  mode			)
 	),
@@ -1265,16 +1266,17 @@ TRACE_EVENT(ext4_da_reserve_space,
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 		__entry->i_blocks = inode->i_blocks;
+		__entry->reserved_blocks = reserved_blocks;
 		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
 		__entry->mode	= inode->i_mode;
 	),
 
-	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu "
+	TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu reserved_blocks %u "
 		  "reserved_data_blocks %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long) __entry->ino,
 		  __entry->mode, __entry->i_blocks,
-		  __entry->reserved_data_blocks)
+		  __entry->reserved_blocks, __entry->reserved_data_blocks)
 );
 
 TRACE_EVENT(ext4_da_release_space,
@@ -2509,7 +2511,7 @@ TRACE_EVENT(ext4_es_shrink,
 		  __entry->scan_time, __entry->nr_skipped, __entry->retried)
 );
 
-TRACE_EVENT(ext4_es_insert_delayed_block,
+TRACE_EVENT(ext4_es_insert_delayed_extent,
 	TP_PROTO(struct inode *inode, struct extent_status *es,
 		 bool allocated),
 
-- 
2.39.2


Powered by blists - more mailing lists