Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e4e98f4..223e97a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* raid5.c : Multiple Devices driver for Linux
* Copyright (C) 1996, 1997 Ingo Molnar, Miguel de Icaza, Gadi Oxman
@@ -7,15 +8,6 @@
* RAID-4/5/6 management functions.
* Thanks to Penguin Computing for making the RAID-6 development possible
* by donating a test server!
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * You should have received a copy of the GNU General Public License
- * (for example /usr/src/linux/COPYING); if not, write to the Free
- * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/*
@@ -54,7 +46,6 @@
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/nodemask.h>
-#include <linux/flex_array.h>
#include <trace/events/block.h>
#include <linux/list_sort.h>
@@ -712,6 +703,8 @@
}
static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
+ __acquires(&sh1->stripe_lock)
+ __acquires(&sh2->stripe_lock)
{
if (sh1 > sh2) {
spin_lock_irq(&sh2->stripe_lock);
@@ -723,6 +716,8 @@
}
static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
+ __releases(&sh1->stripe_lock)
+ __releases(&sh2->stripe_lock)
{
spin_unlock(&sh1->stripe_lock);
spin_unlock_irq(&sh2->stripe_lock);
@@ -1394,22 +1389,16 @@
}
/* return a pointer to the address conversion region of the scribble buffer */
-static addr_conv_t *to_addr_conv(struct stripe_head *sh,
- struct raid5_percpu *percpu, int i)
+static struct page **to_addr_page(struct raid5_percpu *percpu, int i)
{
- void *addr;
-
- addr = flex_array_get(percpu->scribble, i);
- return addr + sizeof(struct page *) * (sh->disks + 2);
+ return percpu->scribble + i * percpu->scribble_obj_size;
}
/* return a pointer to the address conversion region of the scribble buffer */
-static struct page **to_addr_page(struct raid5_percpu *percpu, int i)
+static addr_conv_t *to_addr_conv(struct stripe_head *sh,
+ struct raid5_percpu *percpu, int i)
{
- void *addr;
-
- addr = flex_array_get(percpu->scribble, i);
- return addr;
+ return (void *) (to_addr_page(percpu, i) + sh->disks + 2);
}
static struct dma_async_tx_descriptor *
@@ -2238,21 +2227,23 @@
* calculate over all devices (not just the data blocks), using zeros in place
* of the P and Q blocks.
*/
-static struct flex_array *scribble_alloc(int num, int cnt, gfp_t flags)
+static int scribble_alloc(struct raid5_percpu *percpu,
+ int num, int cnt, gfp_t flags)
{
- struct flex_array *ret;
- size_t len;
+ size_t obj_size =
+ sizeof(struct page *) * (num+2) +
+ sizeof(addr_conv_t) * (num+2);
+ void *scribble;
- len = sizeof(struct page *) * (num+2) + sizeof(addr_conv_t) * (num+2);
- ret = flex_array_alloc(len, cnt, flags);
- if (!ret)
- return NULL;
- /* always prealloc all elements, so no locking is required */
- if (flex_array_prealloc(ret, 0, cnt, flags)) {
- flex_array_free(ret);
- return NULL;
- }
- return ret;
+ scribble = kvmalloc_array(cnt, obj_size, flags);
+ if (!scribble)
+ return -ENOMEM;
+
+ kvfree(percpu->scribble);
+
+ percpu->scribble = scribble;
+ percpu->scribble_obj_size = obj_size;
+ return 0;
}
static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
@@ -2270,23 +2261,18 @@
return 0;
mddev_suspend(conf->mddev);
get_online_cpus();
+
for_each_present_cpu(cpu) {
struct raid5_percpu *percpu;
- struct flex_array *scribble;
percpu = per_cpu_ptr(conf->percpu, cpu);
- scribble = scribble_alloc(new_disks,
- new_sectors / STRIPE_SECTORS,
- GFP_NOIO);
-
- if (scribble) {
- flex_array_free(percpu->scribble);
- percpu->scribble = scribble;
- } else {
- err = -ENOMEM;
+ err = scribble_alloc(percpu, new_disks,
+ new_sectors / STRIPE_SECTORS,
+ GFP_NOIO);
+ if (err)
break;
- }
}
+
put_online_cpus();
mddev_resume(conf->mddev);
if (!err) {
@@ -2540,7 +2526,8 @@
int set_bad = 0;
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
- atomic_inc(&rdev->read_errors);
+ if (!(bi->bi_status == BLK_STS_PROTECTION))
+ atomic_inc(&rdev->read_errors);
if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
pr_warn_ratelimited(
"md/raid:%s: read error on replacement device (sector %llu on %s).\n",
@@ -2563,16 +2550,24 @@
(unsigned long long)s,
bdn);
} else if (atomic_read(&rdev->read_errors)
- > conf->max_nr_stripes)
- pr_warn("md/raid:%s: Too many read errors, failing device %s.\n",
- mdname(conf->mddev), bdn);
- else
+ > conf->max_nr_stripes) {
+ if (!test_bit(Faulty, &rdev->flags)) {
+ pr_warn("md/raid:%s: %d read_errors > %d stripes\n",
+ mdname(conf->mddev),
+ atomic_read(&rdev->read_errors),
+ conf->max_nr_stripes);
+ pr_warn("md/raid:%s: Too many read errors, failing device %s.\n",
+ mdname(conf->mddev), bdn);
+ }
+ } else
retry = 1;
if (set_bad && test_bit(In_sync, &rdev->flags)
&& !test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
retry = 1;
if (retry)
- if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
+ if (sh->qd_idx >= 0 && sh->pd_idx == i)
+ set_bit(R5_ReadError, &sh->dev[i].flags);
+ else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
set_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
} else
@@ -2681,6 +2676,18 @@
pr_debug("raid456: error called\n");
spin_lock_irqsave(&conf->device_lock, flags);
+
+ if (test_bit(In_sync, &rdev->flags) &&
+ mddev->degraded == conf->max_degraded) {
+ /*
+ * Don't allow to achieve failed state
+ * Don't try to recover this device
+ */
+ conf->recovery_disabled = mddev->recovery_disabled;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ return;
+ }
+
set_bit(Faulty, &rdev->flags);
clear_bit(In_sync, &rdev->flags);
mddev->degraded = raid5_calc_degraded(conf);
@@ -4185,7 +4192,7 @@
/* now write out any block on a failed drive,
* or P or Q if they were recomputed
*/
- BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */
+ dev = NULL;
if (s->failed == 2) {
dev = &sh->dev[s->failed_num[1]];
s->locked++;
@@ -4210,6 +4217,14 @@
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
}
+ if (WARN_ONCE(dev && !test_bit(R5_UPTODATE, &dev->flags),
+ "%s: disk%td not up to date\n",
+ mdname(conf->mddev),
+ dev - (struct r5dev *) &sh->dev)) {
+ clear_bit(R5_LOCKED, &dev->flags);
+ clear_bit(R5_Wantwrite, &dev->flags);
+ s->locked--;
+ }
clear_bit(STRIPE_DEGRADED, &sh->state);
set_bit(STRIPE_INSYNC, &sh->state);
@@ -4606,7 +4621,6 @@
(1 << STRIPE_FULL_WRITE) |
(1 << STRIPE_BIOFILL_RUN) |
(1 << STRIPE_COMPUTE_RUN) |
- (1 << STRIPE_OPS_REQ_PENDING) |
(1 << STRIPE_DISCARD) |
(1 << STRIPE_BATCH_READY) |
(1 << STRIPE_BATCH_ERR) |
@@ -5245,7 +5259,6 @@
rcu_read_unlock();
raid_bio->bi_next = (void*)rdev;
bio_set_dev(align_bi, rdev->bdev);
- bio_clear_flag(align_bi, BIO_SEG_VALID);
if (is_badblock(rdev, align_bi->bi_iter.bi_sector,
bio_sectors(align_bi),
@@ -5486,7 +5499,7 @@
return;
logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
- last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9);
+ last_sector = bio_end_sector(bi);
bi->bi_next = NULL;
@@ -5713,7 +5726,8 @@
do_flush = false;
}
- set_bit(STRIPE_HANDLE, &sh->state);
+ if (!sh->batch_head)
+ set_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
if ((!sh->batch_head || sh == sh->batch_head) &&
(bi->bi_opf & REQ_SYNC) &&
@@ -6164,6 +6178,8 @@
static int handle_active_stripes(struct r5conf *conf, int group,
struct r5worker *worker,
struct list_head *temp_inactive_list)
+ __releases(&conf->device_lock)
+ __acquires(&conf->device_lock)
{
struct stripe_head *batch[MAX_STRIPE_BATCH], *sh;
int i, batch_size = 0, hash;
@@ -6357,6 +6373,7 @@
int
raid5_set_cache_size(struct mddev *mddev, int size)
{
+ int result = 0;
struct r5conf *conf = mddev->private;
if (size <= 16 || size > 32768)
@@ -6373,11 +6390,14 @@
mutex_lock(&conf->cache_size_mutex);
while (size > conf->max_nr_stripes)
- if (!grow_one_stripe(conf, GFP_KERNEL))
+ if (!grow_one_stripe(conf, GFP_KERNEL)) {
+ conf->min_nr_stripes = conf->max_nr_stripes;
+ result = -ENOMEM;
break;
+ }
mutex_unlock(&conf->cache_size_mutex);
- return 0;
+ return result;
}
EXPORT_SYMBOL(raid5_set_cache_size);
@@ -6644,6 +6664,7 @@
&raid5_skip_copy.attr,
&raid5_rmw_level.attr,
&r5c_journal_mode.attr,
+ &ppl_write_hint.attr,
NULL,
};
static struct attribute_group raid5_attrs_group = {
@@ -6726,25 +6747,26 @@
static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
{
safe_put_page(percpu->spare_page);
- if (percpu->scribble)
- flex_array_free(percpu->scribble);
percpu->spare_page = NULL;
+ kvfree(percpu->scribble);
percpu->scribble = NULL;
}
static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
{
- if (conf->level == 6 && !percpu->spare_page)
+ if (conf->level == 6 && !percpu->spare_page) {
percpu->spare_page = alloc_page(GFP_KERNEL);
- if (!percpu->scribble)
- percpu->scribble = scribble_alloc(max(conf->raid_disks,
- conf->previous_raid_disks),
- max(conf->chunk_sectors,
- conf->prev_chunk_sectors)
- / STRIPE_SECTORS,
- GFP_KERNEL);
+ if (!percpu->spare_page)
+ return -ENOMEM;
+ }
- if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
+ if (scribble_alloc(percpu,
+ max(conf->raid_disks,
+ conf->previous_raid_disks),
+ max(conf->chunk_sectors,
+ conf->prev_chunk_sectors)
+ / STRIPE_SECTORS,
+ GFP_KERNEL)) {
free_scratch_buffer(conf, percpu);
return -ENOMEM;
}
@@ -7386,6 +7408,8 @@
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
mddev->sync_thread = md_register_thread(md_do_sync, mddev,
"reshape");
+ if (!mddev->sync_thread)
+ goto abort;
}
/* Ok, everything is just fine now */
@@ -7656,7 +7680,7 @@
static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
{
struct r5conf *conf = mddev->private;
- int err = -EEXIST;
+ int ret, err = -EEXIST;
int disk;
struct disk_info *p;
int first = 0;
@@ -7671,7 +7695,14 @@
* The array is in readonly mode if journal is missing, so no
* write requests running. We should be safe
*/
- log_init(conf, rdev, false);
+ ret = log_init(conf, rdev, false);
+ if (ret)
+ return ret;
+
+ ret = r5l_start(conf->log);
+ if (ret)
+ return ret;
+
return 0;
}
if (mddev->recovery_disabled == conf->recovery_disabled)