aboutsummaryrefslogtreecommitdiff
path: root/drivers/md/raid5.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/raid5.c')
-rw-r--r--drivers/md/raid5.c135
1 files changed, 86 insertions, 49 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index a35b846af4f8..2332b5ced0dd 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -60,6 +60,10 @@
#include "raid0.h"
#include "bitmap.h"
+static bool devices_handle_discard_safely = false;
+module_param(devices_handle_discard_safely, bool, 0644);
+MODULE_PARM_DESC(devices_handle_discard_safely,
+ "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
/*
* Stripe cache
*/
@@ -668,6 +672,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
+ /*
+ * If this is discard request, set bi_vcnt 0. We don't
+ * want to confuse SCSI because SCSI will replace payload
+ */
+ if (rw & REQ_DISCARD)
+ bi->bi_vcnt = 0;
if (rrdev)
set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
@@ -706,6 +716,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
rbi->bi_io_vec[0].bv_offset = 0;
rbi->bi_size = STRIPE_SIZE;
+ /*
+ * If this is discard request, set bi_vcnt 0. We don't
+ * want to confuse SCSI because SCSI will replace payload
+ */
+ if (rw & REQ_DISCARD)
+ rbi->bi_vcnt = 0;
if (conf->mddev->gendisk)
trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
rbi, disk_devt(conf->mddev->gendisk),
@@ -1881,6 +1897,7 @@ static void raid5_end_write_request(struct bio *bi, int error)
set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
} else {
if (!uptodate) {
+ set_bit(STRIPE_DEGRADED, &sh->state);
set_bit(WriteErrorSeen, &rdev->flags);
set_bit(R5_WriteError, &sh->dev[i].flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
@@ -2800,6 +2817,14 @@ static void handle_stripe_clean_event(struct r5conf *conf,
}
/* now that discard is done we can proceed with any sync */
clear_bit(STRIPE_DISCARD, &sh->state);
+ /*
+ * SCSI discard will change some bio fields and the stripe has
+ * no updated data, so remove it from hash list and the stripe
+ * will be reinitialized
+ */
+ spin_lock_irq(&conf->device_lock);
+ remove_hash(sh);
+ spin_unlock_irq(&conf->device_lock);
if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
set_bit(STRIPE_HANDLE, &sh->state);
@@ -3371,7 +3396,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
*/
set_bit(R5_Insync, &dev->flags);
- if (rdev && test_bit(R5_WriteError, &dev->flags)) {
+ if (test_bit(R5_WriteError, &dev->flags)) {
/* This flag does not apply to '.replacement'
* only to .rdev, so make sure to check that*/
struct md_rdev *rdev2 = rcu_dereference(
@@ -3384,7 +3409,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
} else
clear_bit(R5_WriteError, &dev->flags);
}
- if (rdev && test_bit(R5_MadeGood, &dev->flags)) {
+ if (test_bit(R5_MadeGood, &dev->flags)) {
/* This flag does not apply to '.replacement'
* only to .rdev, so make sure to check that*/
struct md_rdev *rdev2 = rcu_dereference(
@@ -3540,6 +3565,8 @@ static void handle_stripe(struct stripe_head *sh)
set_bit(R5_Wantwrite, &dev->flags);
if (prexor)
continue;
+ if (s.failed > 1)
+ continue;
if (!test_bit(R5_Insync, &dev->flags) ||
((i == sh->pd_idx || i == sh->qd_idx) &&
s.failed == 0))
@@ -5016,23 +5043,43 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks)
return sectors * (raid_disks - conf->max_degraded);
}
+static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+ safe_put_page(percpu->spare_page);
+ kfree(percpu->scribble);
+ percpu->spare_page = NULL;
+ percpu->scribble = NULL;
+}
+
+static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+ if (conf->level == 6 && !percpu->spare_page)
+ percpu->spare_page = alloc_page(GFP_KERNEL);
+ if (!percpu->scribble)
+ percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
+
+ if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
+ free_scratch_buffer(conf, percpu);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
static void raid5_free_percpu(struct r5conf *conf)
{
- struct raid5_percpu *percpu;
unsigned long cpu;
if (!conf->percpu)
return;
- get_online_cpus();
- for_each_possible_cpu(cpu) {
- percpu = per_cpu_ptr(conf->percpu, cpu);
- safe_put_page(percpu->spare_page);
- kfree(percpu->scribble);
- }
#ifdef CONFIG_HOTPLUG_CPU
unregister_cpu_notifier(&conf->cpu_notify);
#endif
+
+ get_online_cpus();
+ for_each_possible_cpu(cpu)
+ free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
put_online_cpus();
free_percpu(conf->percpu);
@@ -5058,15 +5105,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- if (conf->level == 6 && !percpu->spare_page)
- percpu->spare_page = alloc_page(GFP_KERNEL);
- if (!percpu->scribble)
- percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
-
- if (!percpu->scribble ||
- (conf->level == 6 && !percpu->spare_page)) {
- safe_put_page(percpu->spare_page);
- kfree(percpu->scribble);
+ if (alloc_scratch_buffer(conf, percpu)) {
pr_err("%s: failed memory allocation for cpu%ld\n",
__func__, cpu);
return notifier_from_errno(-ENOMEM);
@@ -5074,10 +5113,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- safe_put_page(percpu->spare_page);
- kfree(percpu->scribble);
- percpu->spare_page = NULL;
- percpu->scribble = NULL;
+ free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
break;
default:
break;
@@ -5089,40 +5125,29 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
static int raid5_alloc_percpu(struct r5conf *conf)
{
unsigned long cpu;
- struct page *spare_page;
- struct raid5_percpu __percpu *allcpus;
- void *scribble;
- int err;
+ int err = 0;
- allcpus = alloc_percpu(struct raid5_percpu);
- if (!allcpus)
+ conf->percpu = alloc_percpu(struct raid5_percpu);
+ if (!conf->percpu)
return -ENOMEM;
- conf->percpu = allcpus;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ conf->cpu_notify.notifier_call = raid456_cpu_notify;
+ conf->cpu_notify.priority = 0;
+ err = register_cpu_notifier(&conf->cpu_notify);
+ if (err)
+ return err;
+#endif
get_online_cpus();
- err = 0;
for_each_present_cpu(cpu) {
- if (conf->level == 6) {
- spare_page = alloc_page(GFP_KERNEL);
- if (!spare_page) {
- err = -ENOMEM;
- break;
- }
- per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
- }
- scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
- if (!scribble) {
- err = -ENOMEM;
+ err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
+ if (err) {
+ pr_err("%s: failed memory allocation for cpu%ld\n",
+ __func__, cpu);
break;
}
- per_cpu_ptr(conf->percpu, cpu)->scribble = scribble;
}
-#ifdef CONFIG_HOTPLUG_CPU
- conf->cpu_notify.notifier_call = raid456_cpu_notify;
- conf->cpu_notify.priority = 0;
- if (err == 0)
- err = register_cpu_notifier(&conf->cpu_notify);
-#endif
put_online_cpus();
return err;
@@ -5590,7 +5615,7 @@ static int run(struct mddev *mddev)
mddev->queue->limits.discard_granularity = stripe;
/*
* unaligned part of discard request will be ignored, so can't
- * guarantee discard_zerors_data
+ * guarantee discard_zeroes_data
*/
mddev->queue->limits.discard_zeroes_data = 0;
@@ -5615,6 +5640,18 @@ static int run(struct mddev *mddev)
!bdev_get_queue(rdev->bdev)->
limits.discard_zeroes_data)
discard_supported = false;
+ /* Unfortunately, discard_zeroes_data is not currently
+ * a guarantee - just a hint. So we only allow DISCARD
+ * if the sysadmin has confirmed that only safe devices
+ * are in use by setting a module parameter.
+ */
+ if (!devices_handle_discard_safely) {
+ if (discard_supported) {
+ pr_info("md/raid456: discard support disabled due to uncertainty.\n");
+ pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n");
+ }
+ discard_supported = false;
+ }
}
if (discard_supported &&
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-26 14:48:20 +0000