The patch titled
md: improve locking around error handling
has been removed from the -mm tree. Its filename is
md-improve-locking-around-error-handling.patch
This patch was dropped because an updated version was merged
------------------------------------------------------
Subject: md: improve locking around error handling
From: NeilBrown <neilb@xxxxxxx>
The error handling routines don't use proper locking, and so two concurrent
errors could trigger a problem.
So:
- use test-and-set and test-and-clear to synchonise
the In_sync bits with the ->degraded count
- use the spinlock to protect updates to the
degraded count (could use an atomic_t but that
would be a bigger change in code, and isn't
really justified)
- remove un-necessary locking in raid5
Signed-off-by: Neil Brown <neilb@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
drivers/md/raid1.c | 16 +++++++++++-----
drivers/md/raid10.c | 12 ++++++++----
drivers/md/raid5.c | 20 ++++++++++++--------
3 files changed, 31 insertions(+), 17 deletions(-)
diff -puN drivers/md/raid1.c~md-improve-locking-around-error-handling drivers/md/raid1.c
--- a/drivers/md/raid1.c~md-improve-locking-around-error-handling
+++ a/drivers/md/raid1.c
@@ -956,14 +956,16 @@ static void error(mddev_t *mddev, mdk_rd
* normal single drive
*/
return;
- if (test_bit(In_sync, &rdev->flags)) {
+ if (test_and_clear_bit(In_sync, &rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded++;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
/*
* if recovery is running, make sure it aborts.
*/
set_bit(MD_RECOVERY_ERR, &mddev->recovery);
}
- clear_bit(In_sync, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT "raid1: Disk failure on %s, disabling device. \n"
@@ -1017,9 +1019,11 @@ static int raid1_spare_active(mddev_t *m
tmp = conf->mirrors + i;
if (tmp->rdev
&& !test_bit(Faulty, &tmp->rdev->flags)
- && !test_bit(In_sync, &tmp->rdev->flags)) {
+ && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded--;
- set_bit(In_sync, &tmp->rdev->flags);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
}
}
@@ -2035,7 +2039,7 @@ static int raid1_reshape(mddev_t *mddev)
mirror_info_t *newmirrors;
conf_t *conf = mddev_to_conf(mddev);
int cnt, raid_disks;
-
+ unsigned long flags;
int d, d2;
/* Cannot change chunk_size, layout, or level */
@@ -2094,7 +2098,9 @@ static int raid1_reshape(mddev_t *mddev)
kfree(conf->poolinfo);
conf->poolinfo = newpoolinfo;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded += (raid_disks - conf->raid_disks);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
conf->raid_disks = mddev->raid_disks = raid_disks;
mddev->delta_disks = 0;
diff -puN drivers/md/raid10.c~md-improve-locking-around-error-handling drivers/md/raid10.c
--- a/drivers/md/raid10.c~md-improve-locking-around-error-handling
+++ a/drivers/md/raid10.c
@@ -950,14 +950,16 @@ static void error(mddev_t *mddev, mdk_rd
* really dead" tests...
*/
return;
- if (test_bit(In_sync, &rdev->flags)) {
+ if (test_and_clear_bit(In_sync, &rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded++;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
/*
* if recovery is running, make sure it aborts.
*/
set_bit(MD_RECOVERY_ERR, &mddev->recovery);
}
- clear_bit(In_sync, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT "raid10: Disk failure on %s, disabling device. \n"
@@ -1033,9 +1035,11 @@ static int raid10_spare_active(mddev_t *
tmp = conf->mirrors + i;
if (tmp->rdev
&& !test_bit(Faulty, &tmp->rdev->flags)
- && !test_bit(In_sync, &tmp->rdev->flags)) {
+ && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded--;
- set_bit(In_sync, &tmp->rdev->flags);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
}
}
diff -puN drivers/md/raid5.c~md-improve-locking-around-error-handling drivers/md/raid5.c
--- a/drivers/md/raid5.c~md-improve-locking-around-error-handling
+++ a/drivers/md/raid5.c
@@ -636,7 +636,6 @@ static int raid5_end_write_request (stru
struct stripe_head *sh = bi->bi_private;
raid5_conf_t *conf = sh->raid_conf;
int disks = sh->disks, i;
- unsigned long flags;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
if (bi->bi_size)
@@ -654,7 +653,6 @@ static int raid5_end_write_request (stru
return 0;
}
- spin_lock_irqsave(&conf->device_lock, flags);
if (!uptodate)
md_error(conf->mddev, conf->disks[i].rdev);
@@ -662,8 +660,7 @@ static int raid5_end_write_request (stru
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
- __release_stripe(conf, sh);
- spin_unlock_irqrestore(&conf->device_lock, flags);
+ release_stripe(sh);
return 0;
}
@@ -697,9 +694,11 @@ static void error(mddev_t *mddev, mdk_rd
if (!test_bit(Faulty, &rdev->flags)) {
set_bit(MD_CHANGE_DEVS, &mddev->flags);
- if (test_bit(In_sync, &rdev->flags)) {
+ if (test_and_clear_bit(In_sync, &rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded++;
- clear_bit(In_sync, &rdev->flags);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
/*
* if recovery was running, make sure it aborts.
*/
@@ -3419,9 +3418,11 @@ static int raid5_spare_active(mddev_t *m
tmp = conf->disks + i;
if (tmp->rdev
&& !test_bit(Faulty, &tmp->rdev->flags)
- && !test_bit(In_sync, &tmp->rdev->flags)) {
+ && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded--;
- set_bit(In_sync, &tmp->rdev->flags);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
}
}
print_raid5_conf(conf);
@@ -3557,6 +3558,7 @@ static int raid5_start_reshape(mddev_t *
struct list_head *rtmp;
int spares = 0;
int added_devices = 0;
+ unsigned long flags;
if (mddev->degraded ||
test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
@@ -3598,7 +3600,9 @@ static int raid5_start_reshape(mddev_t *
break;
}
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded = (conf->raid_disks - conf->previous_raid_disks) - added_devices;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
mddev->raid_disks = conf->raid_disks;
mddev->reshape_position = 0;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
_
Patches currently in -mm which might be from neilb@xxxxxxx are
lockdep-fix-blkdev_open-warning.patch
md-avoid-backward-event-updates-in-md-superblock-when-degraded.patch
md-fix-recent-breakage-of-md-raid1-array-checking.patch
vfs-destroy-the-dentries-contributed-by-a-superblock-on-unmounting.patch
knfsd-knfsd-add-some-missing-newlines-in-printks.patch
knfsd-knfsd-remove-an-unused-variable-from-e_show.patch
knfsd-knfsd-remove-an-unused-variable-from-auth_unix_lookup.patch
knfsd-add-a-callback-for-when-last-rpc-thread-finishes.patch
knfsd-add-a-callback-for-when-last-rpc-thread-finishes-tidy.patch
knfsd-be-more-selective-in-which-sockets-lockd-listens-on.patch
knfsd-remove-nfsd_versbits-as-intermediate-storage-for-desired-versions.patch
knfsd-separate-out-some-parts-of-nfsd_svc-which-start-nfs-servers.patch
knfsd-separate-out-some-parts-of-nfsd_svc-which-start-nfs-servers-tweaks.patch
knfsd-define-new-nfsdfs-file-portlist-contains-list-of-ports.patch
knfsd-define-new-nfsdfs-file-portlist-contains-list-of-ports-tidy.patch
knfsd-define-new-nfsdfs-file-portlist-contains-list-of-ports-fix.patch
knfsd-allow-sockets-to-be-passed-to-nfsd-via-portlist.patch
knfsd-use-seq_start_token-instead-of-hardcoded-magic-void1.patch
knfsd-have-ext2-reject-file-handles-with-bad-inode-numbers-early.patch
knfsd-have-ext2-reject-file-handles-with-bad-inode-numbers-early-tidy.patch
knfsd-make-ext3-reject-filehandles-referring-to-invalid-inode-numbers.patch
knfsd-make-ext3-reject-filehandles-referring-to-invalid-inode-numbers-tidy.patch
knfsd-drop-serv-option-to-svc_recv-and-svc_process.patch
knfsd-drop-serv-option-to-svc_recv-and-svc_process-nfs-callback-fix-nfs-callback-fix.patch
knfsd-check-return-value-of-lockd_up-in-write_ports.patch
knfsd-move-makesock-failed-warning-into-make_socks.patch
knfsd-correctly-handle-error-condition-from-lockd_up.patch
knfsd-move-tempsock-aging-to-a-timer.patch
knfsd-move-tempsock-aging-to-a-timer-tidy.patch
knfsd-convert-sk_inuse-to-atomic_t.patch
knfsd-use-new-lock-for-svc_sock-deferred-list.patch
knfsd-convert-sk_reserved-to-atomic_t.patch
knfsd-test-and-set-sk_busy-atomically.patch
knfsd-split-svc_serv-into-pools.patch
knfsd-split-svc_serv-into-pools-fix.patch
knfsd-add-svc_get.patch
knfsd-add-svc_set_num_threads.patch
knfsd-use-svc_set_num_threads-to-manage-threads-in-knfsd.patch
knfsd-make-rpc-threads-pools-numa-aware.patch
knfsd-make-rpc-threads-pools-numa-aware-fix.patch
knfsd-allow-admin-to-set-nthreads-per-node.patch
nfsd-lockdep-annotation.patch
knfsd-nfsd-lockdep-annotation-fix.patch
knfsd-call-lockd_down-when-closing-a-socket-via-a-write-to-nfsd-portlist.patch
knfsd-protect-update-to-sn_nrthreads-with-lock_kernel.patch
knfsd-fixed-handling-of-lockd-fail-when-adding-nfsd-socket.patch
knfsd-replace-two-page-lists-in-struct-svc_rqst-with-one.patch
knfsd-avoid-excess-stack-usage-in-svc_tcp_recvfrom.patch
knfsd-prepare-knfsd-for-support-of-rsize-wsize-of-up-to-1mb-over-tcp.patch
knfsd-allow-max-size-of-nfsd-payload-to-be-configured.patch
knfsd-make-nfsd-readahead-params-cache-smp-friendly.patch
knfsd-knfsd-cache-ipmap-per-tcp-socket.patch
md-the-scheduled-removal-of-the-start_array-ioctl-for-md.patch
md-fix-a-comment-that-is-wrong-in-raid5h.patch
md-factor-out-part-of-raid10d-into-a-separate-function.patch
md-replace-magic-numbers-in-sb_dirty-with-well-defined-bit-flags.patch
md-remove-the-working_disks-and-failed_disks-from-raid5-state-data.patch
md-remove-working_disks-from-raid10-state.patch
md-improve-locking-around-error-handling.patch
md-new-sysfs-interface-for-setting-bits-in-the-write-intent-bitmap.patch
md-remove-unnecessary-variable-x-in-stripe_to_pdidx.patch
md-dm-reduce-stack-usage-with-stacked-block-devices.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
