| 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
| ||
|
Message-Id: <1393276530-26423-3-git-send-email-amadvance@gmail.com>
Date: Mon, 24 Feb 2014 22:15:29 +0100
From: Andrea Mazzoleni <amadvance@...il.com>
To: clm@...com, jbacik@...com, neilb@...e.de
Cc: linux-kernel@...r.kernel.org, linux-raid@...r.kernel.org,
linux-btrfs@...r.kernel.org, amadvance@...il.com
Subject: [PATCH v5 2/3] fs: btrfs: Adds new par3456 modes to support up to six parities
Removes the RAID logic now handled in the new raid_gen() and raid_rec() calls
that hide all the details.
Replaces the faila/failb failure indexes with a fail[] vector that keeps
track of up to six failures.
Replaces the existing BLOCK_GROUP_RAID5/6 with new PAR1/2/3/4/5/6 ones that
handle up to six parities, and updates all the code to use them.
Signed-off-by: Andrea Mazzoleni <amadvance@...il.com>
---
fs/btrfs/Kconfig | 1 +
fs/btrfs/ctree.h | 50 ++++++--
fs/btrfs/disk-io.c | 7 +-
fs/btrfs/extent-tree.c | 67 +++++++----
fs/btrfs/inode.c | 3 +-
fs/btrfs/raid56.c | 273 ++++++++++++++-----------------------------
fs/btrfs/raid56.h | 19 ++-
fs/btrfs/scrub.c | 3 +-
fs/btrfs/volumes.c | 144 +++++++++++++++--------
include/trace/events/btrfs.h | 16 ++-
include/uapi/linux/btrfs.h | 19 ++-
11 files changed, 313 insertions(+), 289 deletions(-)
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index a66768e..fb011b8 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -6,6 +6,7 @@ config BTRFS_FS
select ZLIB_DEFLATE
select LZO_COMPRESS
select LZO_DECOMPRESS
+ select RAID_CAUCHY
select RAID6_PQ
select XOR_BLOCKS
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2c1a42c..7e6d2bf 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -522,6 +522,7 @@ struct btrfs_super_block {
#define BTRFS_FEATURE_INCOMPAT_RAID56 (1ULL << 7)
#define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA (1ULL << 8)
#define BTRFS_FEATURE_INCOMPAT_NO_HOLES (1ULL << 9)
+#define BTRFS_FEATURE_INCOMPAT_PAR3456 (1ULL << 10)
#define BTRFS_FEATURE_COMPAT_SUPP 0ULL
#define BTRFS_FEATURE_COMPAT_SAFE_SET 0ULL
@@ -539,7 +540,8 @@ struct btrfs_super_block {
BTRFS_FEATURE_INCOMPAT_RAID56 | \
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \
BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \
- BTRFS_FEATURE_INCOMPAT_NO_HOLES)
+ BTRFS_FEATURE_INCOMPAT_NO_HOLES | \
+ BTRFS_FEATURE_INCOMPAT_PAR3456)
#define BTRFS_FEATURE_INCOMPAT_SAFE_SET \
(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
@@ -983,8 +985,39 @@ struct btrfs_dev_replace_item {
#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4)
#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5)
#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6)
-#define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7)
-#define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8)
+#define BTRFS_BLOCK_GROUP_PAR1 (1ULL << 7)
+#define BTRFS_BLOCK_GROUP_PAR2 (1ULL << 8)
+#define BTRFS_BLOCK_GROUP_PAR3 (1ULL << 9)
+#define BTRFS_BLOCK_GROUP_PAR4 (1ULL << 10)
+#define BTRFS_BLOCK_GROUP_PAR5 (1ULL << 11)
+#define BTRFS_BLOCK_GROUP_PAR6 (1ULL << 12)
+
+/* tags for all the parity groups */
+#define BTRFS_BLOCK_GROUP_PARX (BTRFS_BLOCK_GROUP_PAR1 | \
+ BTRFS_BLOCK_GROUP_PAR2 | \
+ BTRFS_BLOCK_GROUP_PAR3 | \
+ BTRFS_BLOCK_GROUP_PAR4 | \
+ BTRFS_BLOCK_GROUP_PAR5 | \
+ BTRFS_BLOCK_GROUP_PAR6)
+
+/* gets the parity number from the parity group */
+static inline int btrfs_flags_par(unsigned group)
+{
+ switch (group & BTRFS_BLOCK_GROUP_PARX) {
+ case BTRFS_BLOCK_GROUP_PAR1: return 1;
+ case BTRFS_BLOCK_GROUP_PAR2: return 2;
+ case BTRFS_BLOCK_GROUP_PAR3: return 3;
+ case BTRFS_BLOCK_GROUP_PAR4: return 4;
+ case BTRFS_BLOCK_GROUP_PAR5: return 5;
+ case BTRFS_BLOCK_GROUP_PAR6: return 6;
+ }
+
+ /* ensures that no multiple groups are defined */
+ BUG_ON(group & BTRFS_BLOCK_GROUP_PARX);
+
+ return 0;
+}
+
#define BTRFS_BLOCK_GROUP_RESERVED BTRFS_AVAIL_ALLOC_BIT_SINGLE
enum btrfs_raid_types {
@@ -993,8 +1026,12 @@ enum btrfs_raid_types {
BTRFS_RAID_DUP,
BTRFS_RAID_RAID0,
BTRFS_RAID_SINGLE,
- BTRFS_RAID_RAID5,
- BTRFS_RAID_RAID6,
+ BTRFS_RAID_PAR1,
+ BTRFS_RAID_PAR2,
+ BTRFS_RAID_PAR3,
+ BTRFS_RAID_PAR4,
+ BTRFS_RAID_PAR5,
+ BTRFS_RAID_PAR6,
BTRFS_NR_RAID_TYPES
};
@@ -1004,8 +1041,7 @@ enum btrfs_raid_types {
#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \
BTRFS_BLOCK_GROUP_RAID1 | \
- BTRFS_BLOCK_GROUP_RAID5 | \
- BTRFS_BLOCK_GROUP_RAID6 | \
+ BTRFS_BLOCK_GROUP_PARX | \
BTRFS_BLOCK_GROUP_DUP | \
BTRFS_BLOCK_GROUP_RAID10)
/*
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 81ea553..9931cf3 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3337,12 +3337,11 @@ int btrfs_calc_num_tolerated_disk_barrier_failures(
num_tolerated_disk_barrier_failures = 0;
else if (num_tolerated_disk_barrier_failures > 1) {
if (flags & (BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID5 |
BTRFS_BLOCK_GROUP_RAID10)) {
num_tolerated_disk_barrier_failures = 1;
- } else if (flags &
- BTRFS_BLOCK_GROUP_RAID6) {
- num_tolerated_disk_barrier_failures = 2;
+ } else if (flags & BTRFS_BLOCK_GROUP_PARX) {
+ num_tolerated_disk_barrier_failures
+ = btrfs_flags_par(flags);
}
}
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 32312e0..a5d1f9d 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3516,21 +3516,35 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
/* First, mask out the RAID levels which aren't possible */
if (num_devices == 1)
flags &= ~(BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_BLOCK_GROUP_RAID5);
+ BTRFS_BLOCK_GROUP_PAR1);
if (num_devices < 3)
- flags &= ~BTRFS_BLOCK_GROUP_RAID6;
+ flags &= ~BTRFS_BLOCK_GROUP_PAR2;
if (num_devices < 4)
- flags &= ~BTRFS_BLOCK_GROUP_RAID10;
+ flags &= ~(BTRFS_BLOCK_GROUP_RAID10 | BTRFS_BLOCK_GROUP_PAR3);
+ if (num_devices < 5)
+ flags &= ~BTRFS_BLOCK_GROUP_PAR4;
+ if (num_devices < 6)
+ flags &= ~BTRFS_BLOCK_GROUP_PAR5;
+ if (num_devices < 7)
+ flags &= ~BTRFS_BLOCK_GROUP_PAR6;
tmp = flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6 | BTRFS_BLOCK_GROUP_RAID10);
+ BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_PARX |
+ BTRFS_BLOCK_GROUP_RAID10);
flags &= ~tmp;
- if (tmp & BTRFS_BLOCK_GROUP_RAID6)
- tmp = BTRFS_BLOCK_GROUP_RAID6;
- else if (tmp & BTRFS_BLOCK_GROUP_RAID5)
- tmp = BTRFS_BLOCK_GROUP_RAID5;
+ if (tmp & BTRFS_BLOCK_GROUP_PAR6)
+ tmp = BTRFS_BLOCK_GROUP_PAR6;
+ else if (tmp & BTRFS_BLOCK_GROUP_PAR5)
+ tmp = BTRFS_BLOCK_GROUP_PAR5;
+ else if (tmp & BTRFS_BLOCK_GROUP_PAR4)
+ tmp = BTRFS_BLOCK_GROUP_PAR4;
+ else if (tmp & BTRFS_BLOCK_GROUP_PAR3)
+ tmp = BTRFS_BLOCK_GROUP_PAR3;
+ else if (tmp & BTRFS_BLOCK_GROUP_PAR2)
+ tmp = BTRFS_BLOCK_GROUP_PAR2;
+ else if (tmp & BTRFS_BLOCK_GROUP_PAR1)
+ tmp = BTRFS_BLOCK_GROUP_PAR1;
else if (tmp & BTRFS_BLOCK_GROUP_RAID10)
tmp = BTRFS_BLOCK_GROUP_RAID10;
else if (tmp & BTRFS_BLOCK_GROUP_RAID1)
@@ -3769,8 +3783,7 @@ static u64 get_system_chunk_thresh(struct btrfs_root *root, u64 type)
if (type & (BTRFS_BLOCK_GROUP_RAID10 |
BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6))
+ BTRFS_BLOCK_GROUP_PARX))
num_dev = root->fs_info->fs_devices->rw_devices;
else if (type & BTRFS_BLOCK_GROUP_RAID1)
num_dev = 2;
@@ -6104,10 +6117,18 @@ int __get_raid_index(u64 flags)
return BTRFS_RAID_DUP;
else if (flags & BTRFS_BLOCK_GROUP_RAID0)
return BTRFS_RAID_RAID0;
- else if (flags & BTRFS_BLOCK_GROUP_RAID5)
- return BTRFS_RAID_RAID5;
- else if (flags & BTRFS_BLOCK_GROUP_RAID6)
- return BTRFS_RAID_RAID6;
+ else if (flags & BTRFS_BLOCK_GROUP_PAR1)
+ return BTRFS_RAID_PAR1;
+ else if (flags & BTRFS_BLOCK_GROUP_PAR2)
+ return BTRFS_RAID_PAR2;
+ else if (flags & BTRFS_BLOCK_GROUP_PAR3)
+ return BTRFS_RAID_PAR3;
+ else if (flags & BTRFS_BLOCK_GROUP_PAR4)
+ return BTRFS_RAID_PAR4;
+ else if (flags & BTRFS_BLOCK_GROUP_PAR5)
+ return BTRFS_RAID_PAR5;
+ else if (flags & BTRFS_BLOCK_GROUP_PAR6)
+ return BTRFS_RAID_PAR6;
return BTRFS_RAID_SINGLE; /* BTRFS_BLOCK_GROUP_SINGLE */
}
@@ -6123,8 +6144,12 @@ static const char *btrfs_raid_type_names[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_DUP] = "dup",
[BTRFS_RAID_RAID0] = "raid0",
[BTRFS_RAID_SINGLE] = "single",
- [BTRFS_RAID_RAID5] = "raid5",
- [BTRFS_RAID_RAID6] = "raid6",
+ [BTRFS_RAID_PAR1] = "raid5",
+ [BTRFS_RAID_PAR2] = "raid6",
+ [BTRFS_RAID_PAR3] = "par3",
+ [BTRFS_RAID_PAR4] = "par4",
+ [BTRFS_RAID_PAR5] = "par5",
+ [BTRFS_RAID_PAR6] = "par6",
};
static const char *get_raid_name(enum btrfs_raid_types type)
@@ -6269,8 +6294,7 @@ search:
if (!block_group_bits(block_group, flags)) {
u64 extra = BTRFS_BLOCK_GROUP_DUP |
BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6 |
+ BTRFS_BLOCK_GROUP_PARX |
BTRFS_BLOCK_GROUP_RAID10;
/*
@@ -7856,7 +7880,7 @@ static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
root->fs_info->fs_devices->missing_devices;
stripped = BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6 |
+ BTRFS_BLOCK_GROUP_PARX |
BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
if (num_devices == 1) {
@@ -8539,8 +8563,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
if (!(get_alloc_profile(root, space_info->flags) &
(BTRFS_BLOCK_GROUP_RAID10 |
BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6 |
+ BTRFS_BLOCK_GROUP_PARX |
BTRFS_BLOCK_GROUP_DUP)))
continue;
/*
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d3d4448..46b4b49 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7184,8 +7184,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
}
/* async crcs make it difficult to collect full stripe writes. */
- if (btrfs_get_alloc_profile(root, 1) &
- (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6))
+ if (btrfs_get_alloc_profile(root, 1) & BTRFS_BLOCK_GROUP_PARX)
async_submit = 0;
else
async_submit = 1;
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 9af0b25..c7573dc 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -27,10 +27,10 @@
#include <linux/capability.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
-#include <linux/raid/pq.h>
+#include <linux/raid/raid.h>
+#include <linux/raid/helper.h>
#include <linux/hash.h>
#include <linux/list_sort.h>
-#include <linux/raid/xor.h>
#include <linux/vmalloc.h>
#include <asm/div64.h>
#include "ctree.h"
@@ -125,11 +125,11 @@ struct btrfs_raid_bio {
*/
int read_rebuild;
- /* first bad stripe */
- int faila;
+ /* bad stripes */
+ int fail[RAID_PARITY_MAX];
- /* second bad stripe (for raid6 use) */
- int failb;
+ /* number of bad stripes in fail[] */
+ int nr_fail;
/*
* number of pages needed to represent the full
@@ -496,26 +496,6 @@ static void cache_rbio(struct btrfs_raid_bio *rbio)
}
/*
- * helper function to run the xor_blocks api. It is only
- * able to do MAX_XOR_BLOCKS at a time, so we need to
- * loop through.
- */
-static void run_xor(void **pages, int src_cnt, ssize_t len)
-{
- int src_off = 0;
- int xor_src_cnt = 0;
- void *dest = pages[src_cnt];
-
- while(src_cnt > 0) {
- xor_src_cnt = min(src_cnt, MAX_XOR_BLOCKS);
- xor_blocks(xor_src_cnt, len, dest, pages + src_off);
-
- src_cnt -= xor_src_cnt;
- src_off += xor_src_cnt;
- }
-}
-
-/*
* returns true if the bio list inside this rbio
* covers an entire stripe (no rmw required).
* Must be called with the bio list lock held, or
@@ -587,25 +567,18 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
}
/*
- * helper to index into the pstripe
- */
-static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index)
-{
- index += (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
- return rbio->stripe_pages[index];
-}
-
-/*
- * helper to index into the qstripe, returns null
- * if there is no qstripe
+ * helper to index into the parity stripe
+ * returns null if there is no stripe
*/
-static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
+static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio,
+ int index, int parity)
{
- if (rbio->nr_data + 1 == rbio->bbio->num_stripes)
+ if (rbio->nr_data + parity >= rbio->bbio->num_stripes)
return NULL;
- index += ((rbio->nr_data + 1) * rbio->stripe_len) >>
- PAGE_CACHE_SHIFT;
+ index += ((rbio->nr_data + parity) * rbio->stripe_len)
+ >> PAGE_CACHE_SHIFT;
+
return rbio->stripe_pages[index];
}
@@ -946,8 +919,7 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
rbio->fs_info = root->fs_info;
rbio->stripe_len = stripe_len;
rbio->nr_pages = num_pages;
- rbio->faila = -1;
- rbio->failb = -1;
+ rbio->nr_fail = 0;
atomic_set(&rbio->refs, 1);
/*
@@ -958,10 +930,10 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
rbio->stripe_pages = p;
rbio->bio_pages = p + sizeof(struct page *) * num_pages;
- if (raid_map[bbio->num_stripes - 1] == RAID6_Q_STRIPE)
- nr_data = bbio->num_stripes - 2;
- else
- nr_data = bbio->num_stripes - 1;
+ /* get the number of data stripes removing all the parities */
+ nr_data = bbio->num_stripes;
+ while (nr_data > 0 && is_parity_stripe(raid_map[nr_data - 1]))
+ --nr_data;
rbio->nr_data = nr_data;
return rbio;
@@ -1072,8 +1044,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
*/
static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio)
{
- if (rbio->faila >= 0 || rbio->failb >= 0) {
- BUG_ON(rbio->faila == rbio->bbio->num_stripes - 1);
+ if (rbio->nr_fail > 0) {
__raid56_parity_recover(rbio);
} else {
finish_rmw(rbio);
@@ -1137,10 +1108,10 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
void *pointers[bbio->num_stripes];
int stripe_len = rbio->stripe_len;
int nr_data = rbio->nr_data;
+ int nr_parity;
+ int parity;
int stripe;
int pagenr;
- int p_stripe = -1;
- int q_stripe = -1;
struct bio_list bio_list;
struct bio *bio;
int pages_per_stripe = stripe_len >> PAGE_CACHE_SHIFT;
@@ -1148,14 +1119,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
bio_list_init(&bio_list);
- if (bbio->num_stripes - rbio->nr_data == 1) {
- p_stripe = bbio->num_stripes - 1;
- } else if (bbio->num_stripes - rbio->nr_data == 2) {
- p_stripe = bbio->num_stripes - 2;
- q_stripe = bbio->num_stripes - 1;
- } else {
- BUG();
- }
+ nr_parity = bbio->num_stripes - rbio->nr_data;
/* at this point we either have a full stripe,
* or we've read the full stripe from the drive.
@@ -1194,29 +1158,15 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
pointers[stripe] = kmap(p);
}
- /* then add the parity stripe */
- p = rbio_pstripe_page(rbio, pagenr);
- SetPageUptodate(p);
- pointers[stripe++] = kmap(p);
-
- if (q_stripe != -1) {
-
- /*
- * raid6, add the qstripe and call the
- * library function to fill in our p/q
- */
- p = rbio_qstripe_page(rbio, pagenr);
+ /* then add the parity stripes */
+ for (parity = 0; parity < nr_parity; ++parity) {
+ p = rbio_pstripe_page(rbio, pagenr, parity);
SetPageUptodate(p);
pointers[stripe++] = kmap(p);
-
- raid6_call.gen_syndrome(bbio->num_stripes, PAGE_SIZE,
- pointers);
- } else {
- /* raid5 */
- memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
- run_xor(pointers + 1, nr_data - 1, PAGE_CACHE_SIZE);
}
+ /* compute the parity */
+ raid_gen(rbio->nr_data, nr_parity, PAGE_SIZE, pointers);
for (stripe = 0; stripe < bbio->num_stripes; stripe++)
kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
@@ -1321,24 +1271,25 @@ static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed)
{
unsigned long flags;
int ret = 0;
+ int i;
spin_lock_irqsave(&rbio->bio_list_lock, flags);
/* we already know this stripe is bad, move on */
- if (rbio->faila == failed || rbio->failb == failed)
- goto out;
+ for (i = 0; i < rbio->nr_fail; ++i)
+ if (rbio->fail[i] == failed)
+ goto out;
- if (rbio->faila == -1) {
- /* first failure on this rbio */
- rbio->faila = failed;
- atomic_inc(&rbio->bbio->error);
- } else if (rbio->failb == -1) {
- /* second failure on this rbio */
- rbio->failb = failed;
- atomic_inc(&rbio->bbio->error);
- } else {
+ if (rbio->nr_fail == RAID_PARITY_MAX) {
ret = -EIO;
+ goto out;
}
+
+ /* new failure on this rbio */
+ raid_insert(rbio->nr_fail, rbio->fail, failed);
+ ++rbio->nr_fail;
+ atomic_inc(&rbio->bbio->error);
+
out:
spin_unlock_irqrestore(&rbio->bio_list_lock, flags);
@@ -1724,8 +1675,10 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
{
int pagenr, stripe;
void **pointers;
- int faila = -1, failb = -1;
+ int ifail;
int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ int nr_parity;
+ int nr_fail;
struct page *page;
int err;
int i;
@@ -1737,8 +1690,8 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
goto cleanup_io;
}
- faila = rbio->faila;
- failb = rbio->failb;
+ nr_parity = rbio->bbio->num_stripes - rbio->nr_data;
+ nr_fail = rbio->nr_fail;
if (rbio->read_rebuild) {
spin_lock_irq(&rbio->bio_list_lock);
@@ -1752,98 +1705,30 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
/* setup our array of pointers with pages
* from each stripe
*/
+ ifail = 0;
for (stripe = 0; stripe < rbio->bbio->num_stripes; stripe++) {
/*
* if we're rebuilding a read, we have to use
* pages from the bio list
*/
if (rbio->read_rebuild &&
- (stripe == faila || stripe == failb)) {
+ rbio->fail[ifail] == stripe) {
page = page_in_rbio(rbio, stripe, pagenr, 0);
+ ++ifail;
} else {
page = rbio_stripe_page(rbio, stripe, pagenr);
}
pointers[stripe] = kmap(page);
}
- /* all raid6 handling here */
- if (rbio->raid_map[rbio->bbio->num_stripes - 1] ==
- RAID6_Q_STRIPE) {
-
- /*
- * single failure, rebuild from parity raid5
- * style
- */
- if (failb < 0) {
- if (faila == rbio->nr_data) {
- /*
- * Just the P stripe has failed, without
- * a bad data or Q stripe.
- * TODO, we should redo the xor here.
- */
- err = -EIO;
- goto cleanup;
- }
- /*
- * a single failure in raid6 is rebuilt
- * in the pstripe code below
- */
- goto pstripe;
- }
-
- /* make sure our ps and qs are in order */
- if (faila > failb) {
- int tmp = failb;
- failb = faila;
- faila = tmp;
- }
-
- /* if the q stripe is failed, do a pstripe reconstruction
- * from the xors.
- * If both the q stripe and the P stripe are failed, we're
- * here due to a crc mismatch and we can't give them the
- * data they want
- */
- if (rbio->raid_map[failb] == RAID6_Q_STRIPE) {
- if (rbio->raid_map[faila] == RAID5_P_STRIPE) {
- err = -EIO;
- goto cleanup;
- }
- /*
- * otherwise we have one bad data stripe and
- * a good P stripe. raid5!
- */
- goto pstripe;
- }
-
- if (rbio->raid_map[failb] == RAID5_P_STRIPE) {
- raid6_datap_recov(rbio->bbio->num_stripes,
- PAGE_SIZE, faila, pointers);
- } else {
- raid6_2data_recov(rbio->bbio->num_stripes,
- PAGE_SIZE, faila, failb,
- pointers);
- }
- } else {
- void *p;
-
- /* rebuild from P stripe here (raid5 or raid6) */
- BUG_ON(failb != -1);
-pstripe:
- /* Copy parity block into failed block to start with */
- memcpy(pointers[faila],
- pointers[rbio->nr_data],
- PAGE_CACHE_SIZE);
-
- /* rearrange the pointer array */
- p = pointers[faila];
- for (stripe = faila; stripe < rbio->nr_data - 1; stripe++)
- pointers[stripe] = pointers[stripe + 1];
- pointers[rbio->nr_data - 1] = p;
-
- /* xor in the rest */
- run_xor(pointers, rbio->nr_data - 1, PAGE_CACHE_SIZE);
+ /* if we have too many failure */
+ if (nr_fail > nr_parity) {
+ err = -EIO;
+ goto cleanup;
}
+ raid_rec(nr_fail, rbio->fail, rbio->nr_data, nr_parity,
+ PAGE_SIZE, pointers);
+
/* if we're doing this rebuild as part of an rmw, go through
* and set all of our private rbio pages in the
* failed stripes as uptodate. This way finish_rmw will
@@ -1852,24 +1737,23 @@ pstripe:
*/
if (!rbio->read_rebuild) {
for (i = 0; i < nr_pages; i++) {
- if (faila != -1) {
- page = rbio_stripe_page(rbio, faila, i);
- SetPageUptodate(page);
- }
- if (failb != -1) {
- page = rbio_stripe_page(rbio, failb, i);
+ for (ifail = 0; ifail < nr_fail; ++ifail) {
+ int sfail = rbio->fail[ifail];
+ page = rbio_stripe_page(rbio, sfail, i);
SetPageUptodate(page);
}
}
}
+ ifail = 0;
for (stripe = 0; stripe < rbio->bbio->num_stripes; stripe++) {
/*
* if we're rebuilding a read, we have to use
* pages from the bio list
*/
if (rbio->read_rebuild &&
- (stripe == faila || stripe == failb)) {
+ rbio->fail[ifail] == stripe) {
page = page_in_rbio(rbio, stripe, pagenr, 0);
+ ++ifail;
} else {
page = rbio_stripe_page(rbio, stripe, pagenr);
}
@@ -1891,8 +1775,7 @@ cleanup_io:
rbio_orig_end_io(rbio, err, err == 0);
} else if (err == 0) {
- rbio->faila = -1;
- rbio->failb = -1;
+ rbio->nr_fail = 0;
finish_rmw(rbio);
} else {
rbio_orig_end_io(rbio, err, 0);
@@ -1939,6 +1822,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
int bios_to_read = 0;
struct btrfs_bio *bbio = rbio->bbio;
struct bio_list bio_list;
+ int ifail;
int ret;
int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
int pagenr;
@@ -1958,10 +1842,12 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
* stripe cache, it is possible that some or all of these
* pages are going to be uptodate.
*/
+ ifail = 0;
for (stripe = 0; stripe < bbio->num_stripes; stripe++) {
- if (rbio->faila == stripe ||
- rbio->failb == stripe)
+ if (rbio->fail[ifail] == stripe) {
+ ++ifail;
continue;
+ }
for (pagenr = 0; pagenr < nr_pages; pagenr++) {
struct page *p;
@@ -2037,6 +1923,7 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
{
struct btrfs_raid_bio *rbio;
int ret;
+ int i;
rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
if (IS_ERR(rbio))
@@ -2046,21 +1933,33 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
bio_list_add(&rbio->bio_list, bio);
rbio->bio_list_bytes = bio->bi_iter.bi_size;
- rbio->faila = find_logical_bio_stripe(rbio, bio);
- if (rbio->faila == -1) {
+ rbio->fail[0] = find_logical_bio_stripe(rbio, bio);
+ if (rbio->fail[0] == -1) {
BUG();
kfree(raid_map);
kfree(bbio);
kfree(rbio);
return -EIO;
}
+ rbio->nr_fail = 1;
/*
- * reconstruct from the q stripe if they are
- * asking for mirror 3
+ * Reconstruct from other parity stripes if they are
+ * asking for different mirrors.
+ * For each mirror we disable one extra parity to trigger
+ * a different recovery.
+ * With mirror_num == 2 we disable nothing and we reconstruct
+ * with the first parity, with mirror_num == 3 we disable the
+ * first parity and then we reconstruct with the second,
+ * and so on, up to mirror_num == 7 where we disable the first 5
+ * parity levels and we recover with the 6 one.
*/
- if (mirror_num == 3)
- rbio->failb = bbio->num_stripes - 2;
+ if (mirror_num > 2 && mirror_num - 2 < RAID_PARITY_MAX) {
+ for (i = 0; i < mirror_num - 2; ++i) {
+ raid_insert(rbio->nr_fail, rbio->fail, rbio->nr_data + i);
+ ++rbio->nr_fail;
+ }
+ }
ret = lock_stripe_add(rbio);
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index ea5d73b..b1082b6 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -21,23 +21,22 @@
#define __BTRFS_RAID56__
static inline int nr_parity_stripes(struct map_lookup *map)
{
- if (map->type & BTRFS_BLOCK_GROUP_RAID5)
- return 1;
- else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
- return 2;
- else
- return 0;
+ return btrfs_flags_par(map->type);
}
static inline int nr_data_stripes(struct map_lookup *map)
{
return map->num_stripes - nr_parity_stripes(map);
}
-#define RAID5_P_STRIPE ((u64)-2)
-#define RAID6_Q_STRIPE ((u64)-1)
-#define is_parity_stripe(x) (((x) == RAID5_P_STRIPE) || \
- ((x) == RAID6_Q_STRIPE))
+#define BTRFS_RAID_PAR1_STRIPE ((u64)-6)
+#define BTRFS_RAID_PAR2_STRIPE ((u64)-5)
+#define BTRFS_RAID_PAR3_STRIPE ((u64)-4)
+#define BTRFS_RAID_PAR4_STRIPE ((u64)-3)
+#define BTRFS_RAID_PAR5_STRIPE ((u64)-2)
+#define BTRFS_RAID_PAR6_STRIPE ((u64)-1)
+
+#define is_parity_stripe(x) (((u64)(x) >= BTRFS_RAID_PAR1_STRIPE))
int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
struct btrfs_bio *bbio, u64 *raid_map,
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index efba5d1..495c13e 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2259,8 +2259,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
int extent_mirror_num;
int stop_loop;
- if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6)) {
+ if (map->type & BTRFS_BLOCK_GROUP_PARX) {
if (num >= nr_data_stripes(map)) {
return 0;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bab0b84..acafb50 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1525,17 +1525,41 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
goto out;
}
- if ((all_avail & BTRFS_BLOCK_GROUP_RAID5) &&
+ if ((all_avail & BTRFS_BLOCK_GROUP_PAR1) &&
root->fs_info->fs_devices->rw_devices <= 2) {
ret = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET;
goto out;
}
- if ((all_avail & BTRFS_BLOCK_GROUP_RAID6) &&
+
+ if ((all_avail & BTRFS_BLOCK_GROUP_PAR2) &&
root->fs_info->fs_devices->rw_devices <= 3) {
ret = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET;
goto out;
}
+ if ((all_avail & BTRFS_BLOCK_GROUP_PAR3) &&
+ root->fs_info->fs_devices->rw_devices <= 4) {
+ ret = BTRFS_ERROR_DEV_PAR3_MIN_NOT_MET;
+ goto out;
+ }
+
+ if ((all_avail & BTRFS_BLOCK_GROUP_PAR4) &&
+ root->fs_info->fs_devices->rw_devices <= 5) {
+ ret = BTRFS_ERROR_DEV_PAR4_MIN_NOT_MET;
+ goto out;
+ }
+
+ if ((all_avail & BTRFS_BLOCK_GROUP_PAR5) &&
+ root->fs_info->fs_devices->rw_devices <= 6) {
+ ret = BTRFS_ERROR_DEV_PAR5_MIN_NOT_MET;
+ goto out;
+ }
+
+ if ((all_avail & BTRFS_BLOCK_GROUP_PAR6) &&
+ root->fs_info->fs_devices->rw_devices <= 7) {
+ ret = BTRFS_ERROR_DEV_PAR6_MIN_NOT_MET;
+ goto out;
+ }
if (strcmp(device_path, "missing") == 0) {
struct list_head *devices;
struct btrfs_device *tmp;
@@ -2797,10 +2821,8 @@ static int chunk_drange_filter(struct extent_buffer *leaf,
if (btrfs_chunk_type(leaf, chunk) & (BTRFS_BLOCK_GROUP_DUP |
BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10)) {
factor = num_stripes / 2;
- } else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_RAID5) {
- factor = num_stripes - 1;
- } else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_RAID6) {
- factor = num_stripes - 2;
+ } else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_PARX) {
+ factor = num_stripes - btrfs_flags_par(btrfs_chunk_type(leaf, chunk));
} else {
factor = num_stripes;
}
@@ -3158,10 +3180,18 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
else if (num_devices > 1)
allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
if (num_devices > 2)
- allowed |= BTRFS_BLOCK_GROUP_RAID5;
+ allowed |= BTRFS_BLOCK_GROUP_PAR1;
if (num_devices > 3)
allowed |= (BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_RAID6);
+ BTRFS_BLOCK_GROUP_PAR2);
+ if (num_devices > 4)
+ allowed |= BTRFS_BLOCK_GROUP_PAR3;
+ if (num_devices > 5)
+ allowed |= BTRFS_BLOCK_GROUP_PAR4;
+ if (num_devices > 6)
+ allowed |= BTRFS_BLOCK_GROUP_PAR5;
+ if (num_devices > 7)
+ allowed |= BTRFS_BLOCK_GROUP_PAR6;
if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(!alloc_profile_is_valid(bctl->data.target, 1) ||
(bctl->data.target & ~allowed))) {
@@ -3201,8 +3231,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
/* allow to reduce meta or sys integrity only if force set */
allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6;
+ BTRFS_BLOCK_GROUP_PARX;
do {
seq = read_seqbegin(&fs_info->profiles_lock);
@@ -3940,7 +3969,7 @@ static struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.devs_increment = 1,
.ncopies = 1,
},
- [BTRFS_RAID_RAID5] = {
+ [BTRFS_RAID_PAR1] = {
.sub_stripes = 1,
.dev_stripes = 1,
.devs_max = 0,
@@ -3948,7 +3977,7 @@ static struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.devs_increment = 1,
.ncopies = 2,
},
- [BTRFS_RAID_RAID6] = {
+ [BTRFS_RAID_PAR2] = {
.sub_stripes = 1,
.dev_stripes = 1,
.devs_max = 0,
@@ -3956,6 +3985,38 @@ static struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
.devs_increment = 1,
.ncopies = 3,
},
+ [BTRFS_RAID_PAR3] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 4,
+ .devs_increment = 1,
+ .ncopies = 4,
+ },
+ [BTRFS_RAID_PAR4] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 5,
+ .devs_increment = 1,
+ .ncopies = 5,
+ },
+ [BTRFS_RAID_PAR5] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 6,
+ .devs_increment = 1,
+ .ncopies = 6,
+ },
+ [BTRFS_RAID_PAR6] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 7,
+ .devs_increment = 1,
+ .ncopies = 7,
+ },
};
static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target)
@@ -3966,7 +4027,7 @@ static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target)
static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
{
- if (!(type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)))
+ if (!(type & BTRFS_BLOCK_GROUP_PARX))
return;
btrfs_set_fs_incompat(info, RAID56);
@@ -4134,15 +4195,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
*/
data_stripes = num_stripes / ncopies;
- if (type & BTRFS_BLOCK_GROUP_RAID5) {
- raid_stripe_len = find_raid56_stripe_len(ndevs - 1,
+ if (type & BTRFS_BLOCK_GROUP_PARX) {
+ int nr_par = btrfs_flags_par(type);
+ raid_stripe_len = find_raid56_stripe_len(ndevs - nr_par,
btrfs_super_stripesize(info->super_copy));
- data_stripes = num_stripes - 1;
- }
- if (type & BTRFS_BLOCK_GROUP_RAID6) {
- raid_stripe_len = find_raid56_stripe_len(ndevs - 2,
- btrfs_super_stripesize(info->super_copy));
- data_stripes = num_stripes - 2;
+ data_stripes = num_stripes - nr_par;
}
/*
@@ -4500,10 +4557,8 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
ret = map->num_stripes;
else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
ret = map->sub_stripes;
- else if (map->type & BTRFS_BLOCK_GROUP_RAID5)
- ret = 2;
- else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
- ret = 3;
+ else if (map->type & BTRFS_BLOCK_GROUP_PARX)
+ ret = 1 + btrfs_flags_par(map->type);
else
ret = 1;
free_extent_map(em);
@@ -4532,10 +4587,9 @@ unsigned long btrfs_full_stripe_len(struct btrfs_root *root,
BUG_ON(em->start > logical || em->start + em->len < logical);
map = (struct map_lookup *)em->bdev;
- if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6)) {
+ if (map->type & BTRFS_BLOCK_GROUP_PARX)
len = map->stripe_len * nr_data_stripes(map);
- }
+
free_extent_map(em);
return len;
}
@@ -4555,8 +4609,7 @@ int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
BUG_ON(em->start > logical || em->start + em->len < logical);
map = (struct map_lookup *)em->bdev;
- if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6))
+ if (map->type & BTRFS_BLOCK_GROUP_PARX)
ret = 1;
free_extent_map(em);
return ret;
@@ -4694,7 +4747,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
stripe_offset = offset - stripe_offset;
/* if we're here for raid56, we need to know the stripe aligned start */
- if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)) {
+ if (map->type & BTRFS_BLOCK_GROUP_PARX) {
unsigned long full_stripe_len = stripe_len * nr_data_stripes(map);
raid56_full_stripe_start = offset;
@@ -4707,8 +4760,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
if (rw & REQ_DISCARD) {
/* we don't discard raid56 yet */
- if (map->type &
- (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)) {
+ if (map->type & BTRFS_BLOCK_GROUP_PARX) {
ret = -EOPNOTSUPP;
goto out;
}
@@ -4718,7 +4770,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
/* For writes to RAID[56], allow a full stripeset across all disks.
For other RAID types and for RAID[56] reads, just allow a single
stripe (on a single disk). */
- if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6) &&
+ if (map->type & BTRFS_BLOCK_GROUP_PARX &&
(rw & REQ_WRITE)) {
max_len = stripe_len * nr_data_stripes(map) -
(offset - raid56_full_stripe_start);
@@ -4882,13 +4934,12 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
mirror_num = stripe_index - old_stripe_index + 1;
}
- } else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6)) {
+ } else if (map->type & BTRFS_BLOCK_GROUP_PARX) {
u64 tmp;
if (bbio_ret && ((rw & REQ_WRITE) || mirror_num > 1)
&& raid_map_ret) {
- int i, rot;
+ int i, j, rot;
/* push stripe_nr back to the start of the full stripe */
stripe_nr = raid56_full_stripe_start;
@@ -4917,10 +4968,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
raid_map[(i+rot) % num_stripes] =
em->start + (tmp + i) * map->stripe_len;
- raid_map[(i+rot) % map->num_stripes] = RAID5_P_STRIPE;
- if (map->type & BTRFS_BLOCK_GROUP_RAID6)
- raid_map[(i+rot+1) % num_stripes] =
- RAID6_Q_STRIPE;
+ for (j = 0; j < btrfs_flags_par(map->type); j++)
+ raid_map[(i+rot+j) % num_stripes] = BTRFS_RAID_PAR1_STRIPE + j;
*length = map->stripe_len;
stripe_index = 0;
@@ -4928,8 +4977,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
} else {
/*
* Mirror #0 or #1 means the original data block.
- * Mirror #2 is RAID5 parity block.
- * Mirror #3 is RAID6 Q block.
+ * Mirror #2 is RAID5/PAR1 P block.
+ * Mirror #3 is RAID6/PAR2 Q block.
+ * .. and so on up to PAR6
*/
stripe_index = do_div(stripe_nr, nr_data_stripes(map));
if (mirror_num > 1)
@@ -5049,11 +5099,10 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) {
if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_RAID5 |
BTRFS_BLOCK_GROUP_DUP)) {
max_errors = 1;
- } else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
- max_errors = 2;
+ } else if (map->type & BTRFS_BLOCK_GROUP_PARX) {
+ max_errors = btrfs_flags_par(map->type);
}
}
@@ -5212,8 +5261,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
do_div(length, map->num_stripes / map->sub_stripes);
else if (map->type & BTRFS_BLOCK_GROUP_RAID0)
do_div(length, map->num_stripes);
- else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID6)) {
+ else if (map->type & BTRFS_BLOCK_GROUP_PARX) {
do_div(length, nr_data_stripes(map));
rmap_len = map->stripe_len * nr_data_stripes(map);
}
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 3176cdc..98a9c78 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -58,8 +58,12 @@ struct extent_buffer;
{ BTRFS_BLOCK_GROUP_RAID1, "RAID1"}, \
{ BTRFS_BLOCK_GROUP_DUP, "DUP"}, \
{ BTRFS_BLOCK_GROUP_RAID10, "RAID10"}, \
- { BTRFS_BLOCK_GROUP_RAID5, "RAID5"}, \
- { BTRFS_BLOCK_GROUP_RAID6, "RAID6"}
+ { BTRFS_BLOCK_GROUP_PAR1, "RAID5"}, \
+ { BTRFS_BLOCK_GROUP_PAR2, "RAID6"}, \
+ { BTRFS_BLOCK_GROUP_PAR3, "PAR3"}, \
+ { BTRFS_BLOCK_GROUP_PAR4, "PAR4"}, \
+ { BTRFS_BLOCK_GROUP_PAR5, "PAR5"}, \
+ { BTRFS_BLOCK_GROUP_PAR6, "PAR6"}
#define BTRFS_UUID_SIZE 16
@@ -623,8 +627,12 @@ DEFINE_EVENT(btrfs_delayed_ref_head, run_delayed_ref_head,
{ BTRFS_BLOCK_GROUP_RAID1, "RAID1" }, \
{ BTRFS_BLOCK_GROUP_DUP, "DUP" }, \
{ BTRFS_BLOCK_GROUP_RAID10, "RAID10"}, \
- { BTRFS_BLOCK_GROUP_RAID5, "RAID5" }, \
- { BTRFS_BLOCK_GROUP_RAID6, "RAID6" })
+ { BTRFS_BLOCK_GROUP_PAR1, "RAID5" }, \
+ { BTRFS_BLOCK_GROUP_PAR2, "RAID6" }, \
+ { BTRFS_BLOCK_GROUP_PAR3, "PAR3" }, \
+ { BTRFS_BLOCK_GROUP_PAR4, "PAR4" }, \
+ { BTRFS_BLOCK_GROUP_PAR5, "PAR5" }, \
+ { BTRFS_BLOCK_GROUP_PAR6, "PAR6" })
DECLARE_EVENT_CLASS(btrfs__chunk,
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index b4d6909..ba120ba 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -488,8 +488,13 @@ enum btrfs_err_code {
BTRFS_ERROR_DEV_TGT_REPLACE,
BTRFS_ERROR_DEV_MISSING_NOT_FOUND,
BTRFS_ERROR_DEV_ONLY_WRITABLE,
- BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS
+ BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS,
+ BTRFS_ERROR_DEV_PAR3_MIN_NOT_MET,
+ BTRFS_ERROR_DEV_PAR4_MIN_NOT_MET,
+ BTRFS_ERROR_DEV_PAR5_MIN_NOT_MET,
+ BTRFS_ERROR_DEV_PAR6_MIN_NOT_MET
};
+
/* An error code to error string mapping for the kernel
* error codes
*/
@@ -501,9 +506,9 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code)
case BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET:
return "unable to go below four devices on raid10";
case BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET:
- return "unable to go below two devices on raid5";
+ return "unable to go below two devices on raid5/par1";
case BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET:
- return "unable to go below three devices on raid6";
+ return "unable to go below three devices on raid6/par2";
case BTRFS_ERROR_DEV_TGT_REPLACE:
return "unable to remove the dev_replace target dev";
case BTRFS_ERROR_DEV_MISSING_NOT_FOUND:
@@ -513,6 +518,14 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code)
case BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS:
return "add/delete/balance/replace/resize operation "\
"in progress";
+ case BTRFS_ERROR_DEV_PAR3_MIN_NOT_MET:
+ return "unable to go below four devices on par3";
+ case BTRFS_ERROR_DEV_PAR4_MIN_NOT_MET:
+ return "unable to go below five devices on par4";
+ case BTRFS_ERROR_DEV_PAR5_MIN_NOT_MET:
+ return "unable to go below six devices on par5";
+ case BTRFS_ERROR_DEV_PAR6_MIN_NOT_MET:
+ return "unable to go below seven devices on par5";
default:
return NULL;
}
--
1.7.12.1
--
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