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  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:	Mon, 30 Jun 2014 13:50:56 +0200
From:	Jiri Slaby <jslaby@...e.cz>
To:	stable@...r.kernel.org
Cc:	linux-kernel@...r.kernel.org, Goldwyn Rodrigues <rgoldwyn@...e.de>,
	Srinivas Eeda <srinivas.eeda@...cle.com>,
	Goldwyn Rodrigues <rgoldwyn@...e.com>, Jan Kara <jack@...e.cz>,
	Joel Becker <jlbec@...lplan.org>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Linus Torvalds <torvalds@...ux-foundation.org>,
	Jiri Slaby <jslaby@...e.cz>
Subject: [PATCH 3.12 035/181] ocfs2: revert iput deferring code in ocfs2_drop_dentry_lock

From: Goldwyn Rodrigues <rgoldwyn@...e.de>

3.12-stable review patch.  If anyone has any objections, please let me know.

===============

commit 8ed6b23709b346f7bfc1edab47003a205a6a9f69 upstream.

The following patches are reverted in this patch because these patches
caused performance regression in the remote unlink() calls.

  ea455f8ab683 - ocfs2: Push out dropping of dentry lock to ocfs2_wq
  f7b1aa69be13 - ocfs2: Fix deadlock on umount
  5fd131893793 - ocfs2: Don't oops in ocfs2_kill_sb on a failed mount

Previous patches in this series removed the possible deadlocks from
downconvert thread so the above patches shouldn't be needed anymore.

The regression is caused because these patches delay the iput() in case
of dentry unlocks.  This also delays the unlocking of the open lockres.
The open lockresource is required to test if the inode can be wiped from
disk or not.  When the deleting node does not get the open lock, it
marks it as orphan (even though it is not in use by another
node/process) and causes a journal checkpoint.  This delays operations
following the inode eviction.  This also moves the inode to the orphaned
inode which further causes more I/O and a lot of unneccessary orphans.

The following script can be used to generate the load causing issues:

  declare -a create
  declare -a remove
  declare -a iterations=(1 2 4 8 16 32 64 128 256 512 1024 2048 4096 8192 16384)
  unique="`mktemp -u XXXXX`"
  script="/tmp/idontknow-${unique}.sh"
  cat <<EOF > "${script}"
  for n in {1..8}; do mkdir -p test/dir\${n}
    eval touch test/dir\${n}/foo{1.."\$1"}
  done
  EOF
  chmod 700 "${script}"

  function fcreate ()
  {
    exec 2>&1 /usr/bin/time --format=%E "${script}" "$1"
  }

  function fremove ()
  {
    exec 2>&1 /usr/bin/time --format=%E ssh node2 "cd `pwd`; rm -Rf test*"
  }

  function fcp ()
  {
    exec 2>&1 /usr/bin/time --format=%E ssh node3 "cd `pwd`; cp -R test test.new"
  }

  echo -------------------------------------------------
  echo "| # files | create #s | copy #s | remove #s |"
  echo -------------------------------------------------
  for ((x=0; x < ${#iterations[*]} ; x++)) do
    create[$x]="`fcreate ${iterations[$x]}`"
    copy[$x]="`fcp ${iterations[$x]}`"
    remove[$x]="`fremove`"
    printf "| %8d | %9s | %9s | %9s |\n" ${iterations[$x]} ${create[$x]} ${copy[$x]} ${remove[$x]}
  done
  rm "${script}"
  echo "------------------------"

Signed-off-by: Srinivas Eeda <srinivas.eeda@...cle.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@...e.com>
Signed-off-by: Jan Kara <jack@...e.cz>
Reviewed-by: Mark Fasheh <mfasheh@...e.de>
Cc: Joel Becker <jlbec@...lplan.org>
Signed-off-by: Andrew Morton <akpm@...ux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@...ux-foundation.org>
Signed-off-by: Jiri Slaby <jslaby@...e.cz>
---
 fs/ocfs2/dcache.c | 61 +++----------------------------------------------------
 fs/ocfs2/dcache.h | 12 +----------
 fs/ocfs2/ocfs2.h  | 28 ++++---------------------
 fs/ocfs2/super.c  | 30 +--------------------------
 4 files changed, 9 insertions(+), 122 deletions(-)

diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 0d3a97d2d5f6..e2e05a106beb 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -37,7 +37,6 @@
 #include "dlmglue.h"
 #include "file.h"
 #include "inode.h"
-#include "super.h"
 #include "ocfs2_trace.h"
 
 void ocfs2_dentry_attach_gen(struct dentry *dentry)
@@ -346,52 +345,6 @@ out_attach:
 	return ret;
 }
 
-DEFINE_SPINLOCK(dentry_list_lock);
-
-/* We limit the number of dentry locks to drop in one go. We have
- * this limit so that we don't starve other users of ocfs2_wq. */
-#define DL_INODE_DROP_COUNT 64
-
-/* Drop inode references from dentry locks */
-static void __ocfs2_drop_dl_inodes(struct ocfs2_super *osb, int drop_count)
-{
-	struct ocfs2_dentry_lock *dl;
-
-	spin_lock(&dentry_list_lock);
-	while (osb->dentry_lock_list && (drop_count < 0 || drop_count--)) {
-		dl = osb->dentry_lock_list;
-		osb->dentry_lock_list = dl->dl_next;
-		spin_unlock(&dentry_list_lock);
-		iput(dl->dl_inode);
-		kfree(dl);
-		spin_lock(&dentry_list_lock);
-	}
-	spin_unlock(&dentry_list_lock);
-}
-
-void ocfs2_drop_dl_inodes(struct work_struct *work)
-{
-	struct ocfs2_super *osb = container_of(work, struct ocfs2_super,
-					       dentry_lock_work);
-
-	__ocfs2_drop_dl_inodes(osb, DL_INODE_DROP_COUNT);
-	/*
-	 * Don't queue dropping if umount is in progress. We flush the
-	 * list in ocfs2_dismount_volume
-	 */
-	spin_lock(&dentry_list_lock);
-	if (osb->dentry_lock_list &&
-	    !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED))
-		queue_work(ocfs2_wq, &osb->dentry_lock_work);
-	spin_unlock(&dentry_list_lock);
-}
-
-/* Flush the whole work queue */
-void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb)
-{
-	__ocfs2_drop_dl_inodes(osb, -1);
-}
-
 /*
  * ocfs2_dentry_iput() and friends.
  *
@@ -416,24 +369,16 @@ void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb)
 static void ocfs2_drop_dentry_lock(struct ocfs2_super *osb,
 				   struct ocfs2_dentry_lock *dl)
 {
+	iput(dl->dl_inode);
 	ocfs2_simple_drop_lockres(osb, &dl->dl_lockres);
 	ocfs2_lock_res_free(&dl->dl_lockres);
-
-	/* We leave dropping of inode reference to ocfs2_wq as that can
-	 * possibly lead to inode deletion which gets tricky */
-	spin_lock(&dentry_list_lock);
-	if (!osb->dentry_lock_list &&
-	    !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED))
-		queue_work(ocfs2_wq, &osb->dentry_lock_work);
-	dl->dl_next = osb->dentry_lock_list;
-	osb->dentry_lock_list = dl;
-	spin_unlock(&dentry_list_lock);
+	kfree(dl);
 }
 
 void ocfs2_dentry_lock_put(struct ocfs2_super *osb,
 			   struct ocfs2_dentry_lock *dl)
 {
-	int unlock;
+	int unlock = 0;
 
 	BUG_ON(dl->dl_count == 0);
 
diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h
index b79eff709958..55f58892b153 100644
--- a/fs/ocfs2/dcache.h
+++ b/fs/ocfs2/dcache.h
@@ -29,13 +29,8 @@
 extern const struct dentry_operations ocfs2_dentry_ops;
 
 struct ocfs2_dentry_lock {
-	/* Use count of dentry lock */
 	unsigned int		dl_count;
-	union {
-		/* Linked list of dentry locks to release */
-		struct ocfs2_dentry_lock *dl_next;
-		u64			dl_parent_blkno;
-	};
+	u64			dl_parent_blkno;
 
 	/*
 	 * The ocfs2_dentry_lock keeps an inode reference until
@@ -49,14 +44,9 @@ struct ocfs2_dentry_lock {
 int ocfs2_dentry_attach_lock(struct dentry *dentry, struct inode *inode,
 			     u64 parent_blkno);
 
-extern spinlock_t dentry_list_lock;
-
 void ocfs2_dentry_lock_put(struct ocfs2_super *osb,
 			   struct ocfs2_dentry_lock *dl);
 
-void ocfs2_drop_dl_inodes(struct work_struct *work);
-void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb);
-
 struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno,
 				      int skip_unhashed);
 
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 1f023ae39379..f6134345fe42 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -275,19 +275,16 @@ enum ocfs2_mount_options
 	OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */
 };
 
-#define OCFS2_OSB_SOFT_RO			0x0001
-#define OCFS2_OSB_HARD_RO			0x0002
-#define OCFS2_OSB_ERROR_FS			0x0004
-#define OCFS2_OSB_DROP_DENTRY_LOCK_IMMED	0x0008
-
-#define OCFS2_DEFAULT_ATIME_QUANTUM		60
+#define OCFS2_OSB_SOFT_RO	0x0001
+#define OCFS2_OSB_HARD_RO	0x0002
+#define OCFS2_OSB_ERROR_FS	0x0004
+#define OCFS2_DEFAULT_ATIME_QUANTUM	60
 
 struct ocfs2_journal;
 struct ocfs2_slot_info;
 struct ocfs2_recovery_map;
 struct ocfs2_replay_map;
 struct ocfs2_quota_recovery;
-struct ocfs2_dentry_lock;
 struct ocfs2_super
 {
 	struct task_struct *commit_task;
@@ -414,11 +411,6 @@ struct ocfs2_super
 	struct list_head blocked_lock_list;
 	unsigned long blocked_lock_count;
 
-	/* List of dentry locks to release. Anyone can add locks to
-	 * the list, ocfs2_wq processes the list  */
-	struct ocfs2_dentry_lock *dentry_lock_list;
-	struct work_struct dentry_lock_work;
-
 	/* List of dquot structures to drop last reference to */
 	struct llist_head dquot_drop_list;
 	struct work_struct dquot_drop_work;
@@ -583,18 +575,6 @@ static inline void ocfs2_set_osb_flag(struct ocfs2_super *osb,
 	spin_unlock(&osb->osb_lock);
 }
 
-
-static inline unsigned long  ocfs2_test_osb_flag(struct ocfs2_super *osb,
-						 unsigned long flag)
-{
-	unsigned long ret;
-
-	spin_lock(&osb->osb_lock);
-	ret = osb->osb_flags & flag;
-	spin_unlock(&osb->osb_lock);
-	return ret;
-}
-
 static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb,
 				     int hard)
 {
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index d6adb5b2b3a5..4d13bf18af22 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1238,30 +1238,11 @@ static struct dentry *ocfs2_mount(struct file_system_type *fs_type,
 	return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super);
 }
 
-static void ocfs2_kill_sb(struct super_block *sb)
-{
-	struct ocfs2_super *osb = OCFS2_SB(sb);
-
-	/* Failed mount? */
-	if (!osb || atomic_read(&osb->vol_state) == VOLUME_DISABLED)
-		goto out;
-
-	/* Prevent further queueing of inode drop events */
-	spin_lock(&dentry_list_lock);
-	ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED);
-	spin_unlock(&dentry_list_lock);
-	/* Wait for work to finish and/or remove it */
-	cancel_work_sync(&osb->dentry_lock_work);
-out:
-	kill_block_super(sb);
-}
-
 static struct file_system_type ocfs2_fs_type = {
 	.owner          = THIS_MODULE,
 	.name           = "ocfs2",
 	.mount          = ocfs2_mount,
-	.kill_sb        = ocfs2_kill_sb,
-
+	.kill_sb        = kill_block_super,
 	.fs_flags       = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
 	.next           = NULL
 };
@@ -1934,12 +1915,6 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	debugfs_remove(osb->osb_ctxt);
 
-	/*
-	 * Flush inode dropping work queue so that deletes are
-	 * performed while the filesystem is still working
-	 */
-	ocfs2_drop_all_dl_inodes(osb);
-
 	/* Orphan scan should be stopped as early as possible */
 	ocfs2_orphan_scan_stop(osb);
 
@@ -2277,9 +2252,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
 	journal->j_state = OCFS2_JOURNAL_FREE;
 
-	INIT_WORK(&osb->dentry_lock_work, ocfs2_drop_dl_inodes);
-	osb->dentry_lock_list = NULL;
-
 	INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs);
 	init_llist_head(&osb->dquot_drop_list);
 
-- 
2.0.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists