hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'for-linus' of git://neil.brown.name/md 

* 'for-linus' of git://neil.brown.name/md: (24 commits)
  md: clean up do_md_stop
  md: fix another deadlock with removing sysfs attributes.
  md: move revalidate_disk() back outside open_mutex
  md/raid10: fix deadlock with unaligned read during resync
  md/bitmap:  separate out loading a bitmap from initialising the structures.
  md/bitmap: prepare for storing write-intent-bitmap via dm-dirty-log.
  md/bitmap: optimise scanning of empty bitmaps.
  md/bitmap: clean up plugging calls.
  md/bitmap: reduce dependence on sysfs.
  md/bitmap: white space clean up and similar.
  md/raid5: export raid5 unplugging interface.
  md/plug: optionally use plugger to unplug an array during resync/recovery.
  md/raid5: add simple plugging infrastructure.
  md/raid5: export is_congested test
  raid5: Don't set read-ahead when there is no queue
  md: add support for raising dm events.
  md: export various start/stop interfaces
  md: split out md_rdev_init
  md: be more careful setting MD_CHANGE_CLEAN
  md/raid5: ensure we create a unique name for kmem_cache when mddev has no gendisk
  ...
This commit is contained in:
Linus Torvalds 2010-08-10 15:38:19 -07:00 committed by Chris Metcalf
parent 8cbd84f2dd fd8aa2c181
commit 90a9ed9581
25 changed files with 748 additions and 509 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
crypto/async_tx/Kconfig
View File

@ -22,6 +22,20 @@ config ASYNC_RAID6_RECOV
tristate
select ASYNC_CORE
select ASYNC_PQ
select ASYNC_XOR
config ASYNC_RAID6_TEST
tristate "Self test for hardware accelerated raid6 recovery"
depends on ASYNC_RAID6_RECOV
select ASYNC_MEMCPY
---help---
This is a one-shot self test that permutes through the
recovery of all the possible two disk failure scenarios for a
N-disk array. Recovery is performed with the asynchronous
raid6 recovery routines, and will optionally use an offload
engine if one is available.
If unsure, say N.
config ASYNC_TX_DISABLE_PQ_VAL_DMA
bool

18
drivers/md/Kconfig
View File

@ -121,7 +121,7 @@ config MD_RAID10
config MD_RAID456
tristate "RAID-4/RAID-5/RAID-6 mode"
depends on BLK_DEV_MD
select MD_RAID6_PQ
select RAID6_PQ
select ASYNC_MEMCPY
select ASYNC_XOR
select ASYNC_PQ
@ -165,22 +165,6 @@ config MULTICORE_RAID456
If unsure, say N.
config MD_RAID6_PQ
tristate
config ASYNC_RAID6_TEST
tristate "Self test for hardware accelerated raid6 recovery"
depends on MD_RAID6_PQ
select ASYNC_RAID6_RECOV
---help---
This is a one-shot self test that permutes through the
recovery of all the possible two disk failure scenarios for a
N-disk array. Recovery is performed with the asynchronous
raid6 recovery routines, and will optionally use an offload
engine if one is available.
If unsure, say N.
config MD_MULTIPATH
tristate "Multipath I/O support"
depends on BLK_DEV_MD

77
drivers/md/Makefile
View File

@ -12,13 +12,6 @@ dm-log-userspace-y \
+= dm-log-userspace-base.o dm-log-userspace-transfer.o
md-mod-y += md.o bitmap.o
raid456-y += raid5.o
raid6_pq-y += raid6algos.o raid6recov.o raid6tables.o \
raid6int1.o raid6int2.o raid6int4.o \
raid6int8.o raid6int16.o raid6int32.o \
raid6altivec1.o raid6altivec2.o raid6altivec4.o \
raid6altivec8.o \
raid6mmx.o raid6sse1.o raid6sse2.o
hostprogs-y += mktables
# Note: link order is important. All raid personalities
# and must come before md.o, as they each initialise
@ -29,7 +22,6 @@ obj-$(CONFIG_MD_LINEAR) += linear.o
obj-$(CONFIG_MD_RAID0) += raid0.o
obj-$(CONFIG_MD_RAID1) += raid1.o
obj-$(CONFIG_MD_RAID10) += raid10.o
obj-$(CONFIG_MD_RAID6_PQ) += raid6_pq.o
obj-$(CONFIG_MD_RAID456) += raid456.o
obj-$(CONFIG_MD_MULTIPATH) += multipath.o
obj-$(CONFIG_MD_FAULTY) += faulty.o
@ -45,75 +37,6 @@ obj-$(CONFIG_DM_MIRROR) += dm-mirror.o dm-log.o dm-region-hash.o
obj-$(CONFIG_DM_LOG_USERSPACE) += dm-log-userspace.o
obj-$(CONFIG_DM_ZERO) += dm-zero.o
quiet_cmd_unroll = UNROLL $@
cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$(UNROLL) \
< $< > $@ || ( rm -f $@ && exit 1 )
ifeq ($(CONFIG_ALTIVEC),y)
altivec_flags := -maltivec -mabi=altivec
endif
ifeq ($(CONFIG_DM_UEVENT),y)
dm-mod-objs += dm-uevent.o
endif
targets += raid6int1.c
$(obj)/raid6int1.c: UNROLL := 1
$(obj)/raid6int1.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int2.c
$(obj)/raid6int2.c: UNROLL := 2
$(obj)/raid6int2.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int4.c
$(obj)/raid6int4.c: UNROLL := 4
$(obj)/raid6int4.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int8.c
$(obj)/raid6int8.c: UNROLL := 8
$(obj)/raid6int8.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int16.c
$(obj)/raid6int16.c: UNROLL := 16
$(obj)/raid6int16.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int32.c
$(obj)/raid6int32.c: UNROLL := 32
$(obj)/raid6int32.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
CFLAGS_raid6altivec1.o += $(altivec_flags)
targets += raid6altivec1.c
$(obj)/raid6altivec1.c: UNROLL := 1
$(obj)/raid6altivec1.c: $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
CFLAGS_raid6altivec2.o += $(altivec_flags)
targets += raid6altivec2.c
$(obj)/raid6altivec2.c: UNROLL := 2
$(obj)/raid6altivec2.c: $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
CFLAGS_raid6altivec4.o += $(altivec_flags)
targets += raid6altivec4.c
$(obj)/raid6altivec4.c: UNROLL := 4
$(obj)/raid6altivec4.c: $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
CFLAGS_raid6altivec8.o += $(altivec_flags)
targets += raid6altivec8.c
$(obj)/raid6altivec8.c: UNROLL := 8
$(obj)/raid6altivec8.c: $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
quiet_cmd_mktable = TABLE $@
cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )
targets += raid6tables.c
$(obj)/raid6tables.c: $(obj)/mktables FORCE
$(call if_changed,mktable)

512
drivers/md/bitmap.c
View File

@ -13,7 +13,6 @@
* Still to do:
*
* flush after percent set rather than just time based. (maybe both).
* wait if count gets too high, wake when it drops to half.
*/
#include <linux/blkdev.h>
@ -30,6 +29,7 @@
#include "md.h"
#include "bitmap.h"
#include <linux/dm-dirty-log.h>
/* debug macros */
#define DEBUG 0
@ -51,9 +51,6 @@
#define INJECT_FATAL_FAULT_3 0 /* undef */
#endif
//#define DPRINTK PRINTK /* set this NULL to avoid verbose debug output */
#define DPRINTK(x...) do { } while(0)
#ifndef PRINTK
# if DEBUG > 0
# define PRINTK(x...) printk(KERN_DEBUG x)
@ -62,12 +59,11 @@
# endif
#endif
static inline char * bmname(struct bitmap *bitmap)
static inline char *bmname(struct bitmap *bitmap)
{
return bitmap->mddev ? mdname(bitmap->mddev) : "mdX";
}
/*
* just a placeholder - calls kmalloc for bitmap pages
*/
@ -78,7 +74,7 @@ static unsigned char *bitmap_alloc_page(struct bitmap *bitmap)
#ifdef INJECT_FAULTS_1
page = NULL;
#else
page = kmalloc(PAGE_SIZE, GFP_NOIO);
page = kzalloc(PAGE_SIZE, GFP_NOIO);
#endif
if (!page)
printk("%s: bitmap_alloc_page FAILED\n", bmname(bitmap));
@ -107,7 +103,8 @@ static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page)
* if we find our page, we increment the page's refcount so that it stays
* allocated while we're using it
*/
static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int create)
static int bitmap_checkpage(struct bitmap *bitmap,
unsigned long page, int create)
__releases(bitmap->lock)
__acquires(bitmap->lock)
{
@ -121,7 +118,6 @@ __acquires(bitmap->lock)
return -EINVAL;
}
if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */
return 0;
@ -131,43 +127,34 @@ __acquires(bitmap->lock)
if (!create)
return -ENOENT;
spin_unlock_irq(&bitmap->lock);
/* this page has not been allocated yet */
if ((mappage = bitmap_alloc_page(bitmap)) == NULL) {
spin_unlock_irq(&bitmap->lock);
mappage = bitmap_alloc_page(bitmap);
spin_lock_irq(&bitmap->lock);
if (mappage == NULL) {
PRINTK("%s: bitmap map page allocation failed, hijacking\n",
bmname(bitmap));
/* failed - set the hijacked flag so that we can use the
* pointer as a counter */
spin_lock_irq(&bitmap->lock);
if (!bitmap->bp[page].map)
bitmap->bp[page].hijacked = 1;
goto out;
}
/* got a page */
spin_lock_irq(&bitmap->lock);
/* recheck the page */
if (bitmap->bp[page].map || bitmap->bp[page].hijacked) {
} else if (bitmap->bp[page].map ||
bitmap->bp[page].hijacked) {
/* somebody beat us to getting the page */
bitmap_free_page(bitmap, mappage);
return 0;
} else {
/* no page was in place and we have one, so install it */
bitmap->bp[page].map = mappage;
bitmap->missing_pages--;
}
/* no page was in place and we have one, so install it */
memset(mappage, 0, PAGE_SIZE);
bitmap->bp[page].map = mappage;
bitmap->missing_pages--;
out:
return 0;
}
/* if page is completely empty, put it back on the free list, or dealloc it */
/* if page was hijacked, unmark the flag so it might get alloced next time */
/* Note: lock should be held when calling this */
@ -183,26 +170,15 @@ static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
if (bitmap->bp[page].hijacked) { /* page was hijacked, undo this now */
bitmap->bp[page].hijacked = 0;
bitmap->bp[page].map = NULL;
return;
} else {
/* normal case, free the page */
ptr = bitmap->bp[page].map;
bitmap->bp[page].map = NULL;
bitmap->missing_pages++;
bitmap_free_page(bitmap, ptr);
}
/* normal case, free the page */
#if 0
/* actually ... let's not. We will probably need the page again exactly when
* memory is tight and we are flusing to disk
*/
return;
#else
ptr = bitmap->bp[page].map;
bitmap->bp[page].map = NULL;
bitmap->missing_pages++;
bitmap_free_page(bitmap, ptr);
return;
#endif
}
/*
* bitmap file handling - read and write the bitmap file and its superblock
*/
@ -220,11 +196,14 @@ static struct page *read_sb_page(mddev_t *mddev, loff_t offset,
mdk_rdev_t *rdev;
sector_t target;
int did_alloc = 0;
if (!page)
if (!page) {
page = alloc_page(GFP_KERNEL);
if (!page)
return ERR_PTR(-ENOMEM);
if (!page)
return ERR_PTR(-ENOMEM);
did_alloc = 1;
}
list_for_each_entry(rdev, &mddev->disks, same_set) {
if (! test_bit(In_sync, &rdev->flags)
@ -242,6 +221,8 @@ static struct page *read_sb_page(mddev_t *mddev, loff_t offset,
return page;
}
}
if (did_alloc)
put_page(page);
return ERR_PTR(-EIO);
}
@ -286,49 +267,51 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
mddev_t *mddev = bitmap->mddev;
while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
int size = PAGE_SIZE;
loff_t offset = mddev->bitmap_info.offset;
if (page->index == bitmap->file_pages-1)
size = roundup(bitmap->last_page_size,
bdev_logical_block_size(rdev->bdev));
/* Just make sure we aren't corrupting data or
* metadata
*/
if (mddev->external) {
/* Bitmap could be anywhere. */
if (rdev->sb_start + offset + (page->index *(PAGE_SIZE/512)) >
rdev->data_offset &&
rdev->sb_start + offset <
rdev->data_offset + mddev->dev_sectors +
(PAGE_SIZE/512))
goto bad_alignment;
} else if (offset < 0) {
/* DATA BITMAP METADATA */
if (offset
+ (long)(page->index * (PAGE_SIZE/512))
+ size/512 > 0)
/* bitmap runs in to metadata */
goto bad_alignment;
if (rdev->data_offset + mddev->dev_sectors
> rdev->sb_start + offset)
/* data runs in to bitmap */
goto bad_alignment;
} else if (rdev->sb_start < rdev->data_offset) {
/* METADATA BITMAP DATA */
if (rdev->sb_start
+ offset
+ page->index*(PAGE_SIZE/512) + size/512
> rdev->data_offset)
/* bitmap runs in to data */
goto bad_alignment;
} else {
/* DATA METADATA BITMAP - no problems */
}
md_super_write(mddev, rdev,
rdev->sb_start + offset
+ page->index * (PAGE_SIZE/512),
size,
page);
int size = PAGE_SIZE;
loff_t offset = mddev->bitmap_info.offset;
if (page->index == bitmap->file_pages-1)
size = roundup(bitmap->last_page_size,
bdev_logical_block_size(rdev->bdev));
/* Just make sure we aren't corrupting data or
* metadata
*/
if (mddev->external) {
/* Bitmap could be anywhere. */
if (rdev->sb_start + offset + (page->index
* (PAGE_SIZE/512))
> rdev->data_offset
&&
rdev->sb_start + offset
< (rdev->data_offset + mddev->dev_sectors
+ (PAGE_SIZE/512)))
goto bad_alignment;
} else if (offset < 0) {
/* DATA BITMAP METADATA */
if (offset
+ (long)(page->index * (PAGE_SIZE/512))
+ size/512 > 0)
/* bitmap runs in to metadata */
goto bad_alignment;
if (rdev->data_offset + mddev->dev_sectors
> rdev->sb_start + offset)
/* data runs in to bitmap */
goto bad_alignment;
} else if (rdev->sb_start < rdev->data_offset) {
/* METADATA BITMAP DATA */
if (rdev->sb_start
+ offset
+ page->index*(PAGE_SIZE/512) + size/512
> rdev->data_offset)
/* bitmap runs in to data */
goto bad_alignment;
} else {
/* DATA METADATA BITMAP - no problems */
}
md_super_write(mddev, rdev,
rdev->sb_start + offset
+ page->index * (PAGE_SIZE/512),
size,
page);
}
if (wait)
@ -364,10 +347,9 @@ static void write_page(struct bitmap *bitmap, struct page *page, int wait)
bh = bh->b_this_page;
}
if (wait) {
if (wait)
wait_event(bitmap->write_wait,
atomic_read(&bitmap->pending_writes)==0);
}
}
if (bitmap->flags & BITMAP_WRITE_ERROR)
bitmap_file_kick(bitmap);
@ -424,7 +406,7 @@ static struct page *read_page(struct file *file, unsigned long index,
struct buffer_head *bh;
sector_t block;
PRINTK("read bitmap file (%dB @ %Lu)\n", (int)PAGE_SIZE,
PRINTK("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE,
(unsigned long long)index << PAGE_SHIFT);
page = alloc_page(GFP_KERNEL);
@ -478,7 +460,7 @@ static struct page *read_page(struct file *file, unsigned long index,
}
out:
if (IS_ERR(page))
printk(KERN_ALERT "md: bitmap read error: (%dB @ %Lu): %ld\n",
printk(KERN_ALERT "md: bitmap read error: (%dB @ %llu): %ld\n",
(int)PAGE_SIZE,
(unsigned long long)index << PAGE_SHIFT,
PTR_ERR(page));
@ -664,11 +646,14 @@ static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
sb = kmap_atomic(bitmap->sb_page, KM_USER0);
old = le32_to_cpu(sb->state) & bits;
switch (op) {
case MASK_SET: sb->state |= cpu_to_le32(bits);
break;
case MASK_UNSET: sb->state &= cpu_to_le32(~bits);
break;
default: BUG();
case MASK_SET:
sb->state |= cpu_to_le32(bits);
break;
case MASK_UNSET:
sb->state &= cpu_to_le32(~bits);
break;
default:
BUG();
}
kunmap_atomic(sb, KM_USER0);
return old;
@ -710,12 +695,14 @@ static inline unsigned long file_page_offset(struct bitmap *bitmap, unsigned lon
static inline struct page *filemap_get_page(struct bitmap *bitmap,
unsigned long chunk)
{
if (file_page_index(bitmap, chunk) >= bitmap->file_pages) return NULL;
if (bitmap->filemap == NULL)
return NULL;
if (file_page_index(bitmap, chunk) >= bitmap->file_pages)
return NULL;
return bitmap->filemap[file_page_index(bitmap, chunk)
- file_page_index(bitmap, 0)];
}
static void bitmap_file_unmap(struct bitmap *bitmap)
{
struct page **map, *sb_page;
@ -766,7 +753,6 @@ static void bitmap_file_put(struct bitmap *bitmap)
}
}
/*
* bitmap_file_kick - if an error occurs while manipulating the bitmap file
* then it is no longer reliable, so we stop using it and we mark the file
@ -785,7 +771,6 @@ static void bitmap_file_kick(struct bitmap *bitmap)
ptr = d_path(&bitmap->file->f_path, path,
PAGE_SIZE);
printk(KERN_ALERT
"%s: kicking failed bitmap file %s from array!\n",
bmname(bitmap), IS_ERR(ptr) ? "" : ptr);
@ -803,27 +788,36 @@ static void bitmap_file_kick(struct bitmap *bitmap)
}
enum bitmap_page_attr {
BITMAP_PAGE_DIRTY = 0, // there are set bits that need to be synced
BITMAP_PAGE_CLEAN = 1, // there are bits that might need to be cleared
BITMAP_PAGE_NEEDWRITE=2, // there are cleared bits that need to be synced
BITMAP_PAGE_DIRTY = 0, /* there are set bits that need to be synced */
BITMAP_PAGE_CLEAN = 1, /* there are bits that might need to be cleared */
BITMAP_PAGE_NEEDWRITE = 2, /* there are cleared bits that need to be synced */
};
static inline void set_page_attr(struct bitmap *bitmap, struct page *page,
enum bitmap_page_attr attr)
{
__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
if (page)
__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
else
__set_bit(attr, &bitmap->logattrs);
}
static inline void clear_page_attr(struct bitmap *bitmap, struct page *page,
enum bitmap_page_attr attr)
{
__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
if (page)
__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
else
__clear_bit(attr, &bitmap->logattrs);
}
static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *page,
enum bitmap_page_attr attr)
{
return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
if (page)
return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
else
return test_bit(attr, &bitmap->logattrs);
}
/*
@ -836,30 +830,32 @@ static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *p
static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
{
unsigned long bit;
struct page *page;
struct page *page = NULL;
void *kaddr;
unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);
if (!bitmap->filemap) {
return;
struct dm_dirty_log *log = bitmap->mddev->bitmap_info.log;
if (log)
log->type->mark_region(log, chunk);
} else {
page = filemap_get_page(bitmap, chunk);
if (!page)
return;
bit = file_page_offset(bitmap, chunk);
/* set the bit */
kaddr = kmap_atomic(page, KM_USER0);
if (bitmap->flags & BITMAP_HOSTENDIAN)
set_bit(bit, kaddr);
else
ext2_set_bit(bit, kaddr);
kunmap_atomic(kaddr, KM_USER0);
PRINTK("set file bit %lu page %lu\n", bit, page->index);
}
page = filemap_get_page(bitmap, chunk);
if (!page) return;
bit = file_page_offset(bitmap, chunk);
/* set the bit */
kaddr = kmap_atomic(page, KM_USER0);
if (bitmap->flags & BITMAP_HOSTENDIAN)
set_bit(bit, kaddr);
else
ext2_set_bit(bit, kaddr);
kunmap_atomic(kaddr, KM_USER0);
PRINTK("set file bit %lu page %lu\n", bit, page->index);
/* record page number so it gets flushed to disk when unplug occurs */
set_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
}
/* this gets called when the md device is ready to unplug its underlying
@ -874,6 +870,16 @@ void bitmap_unplug(struct bitmap *bitmap)
if (!bitmap)
return;
if (!bitmap->filemap) {
/* Must be using a dirty_log */
struct dm_dirty_log *log = bitmap->mddev->bitmap_info.log;
dirty = test_and_clear_bit(BITMAP_PAGE_DIRTY, &bitmap->logattrs);
need_write = test_and_clear_bit(BITMAP_PAGE_NEEDWRITE, &bitmap->logattrs);
if (dirty || need_write)
if (log->type->flush(log))
bitmap->flags |= BITMAP_WRITE_ERROR;
goto out;
}
/* look at each page to see if there are any set bits that need to be
* flushed out to disk */
@ -892,7 +898,7 @@ void bitmap_unplug(struct bitmap *bitmap)
wait = 1;
spin_unlock_irqrestore(&bitmap->lock, flags);
if (dirty | need_write)
if (dirty || need_write)
write_page(bitmap, page, 0);
}
if (wait) { /* if any writes were performed, we need to wait on them */
@ -902,9 +908,11 @@ void bitmap_unplug(struct bitmap *bitmap)
else
md_super_wait(bitmap->mddev);
}
out:
if (bitmap->flags & BITMAP_WRITE_ERROR)
bitmap_file_kick(bitmap);
}
EXPORT_SYMBOL(bitmap_unplug);
static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed);
/* * bitmap_init_from_disk -- called at bitmap_create time to initialize
@ -943,12 +951,11 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
printk(KERN_INFO "%s: bitmap file is out of date, doing full "
"recovery\n", bmname(bitmap));
bytes = (chunks + 7) / 8;
bytes = DIV_ROUND_UP(bitmap->chunks, 8);
if (!bitmap->mddev->bitmap_info.external)
bytes += sizeof(bitmap_super_t);
num_pages = (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE);
if (file && i_size_read(file->f_mapping->host) < bytes) {
printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
@ -966,7 +973,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
/* We need 4 bits per page, rounded up to a multiple of sizeof(unsigned long) */
bitmap->filemap_attr = kzalloc(
roundup( DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
roundup(DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
GFP_KERNEL);
if (!bitmap->filemap_attr)
goto err;
@ -1021,7 +1028,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
if (outofdate) {
/*
* if bitmap is out of date, dirty the
* whole page and write it out
* whole page and write it out
*/
paddr = kmap_atomic(page, KM_USER0);
memset(paddr + offset, 0xff,
@ -1052,7 +1059,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
}
}
/* everything went OK */
/* everything went OK */
ret = 0;
bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET);
@ -1080,21 +1087,16 @@ void bitmap_write_all(struct bitmap *bitmap)
*/
int i;
for (i=0; i < bitmap->file_pages; i++)
for (i = 0; i < bitmap->file_pages; i++)
set_page_attr(bitmap, bitmap->filemap[i],
BITMAP_PAGE_NEEDWRITE);
}
static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
{
sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap);
unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
bitmap->bp[page].count += inc;
/*
if (page == 0) printk("count page 0, offset %llu: %d gives %d\n",
(unsigned long long)offset, inc, bitmap->bp[page].count);
*/
bitmap_checkfree(bitmap, page);
}
static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
@ -1114,6 +1116,7 @@ void bitmap_daemon_work(mddev_t *mddev)
struct page *page = NULL, *lastpage = NULL;
int blocks;
void *paddr;
struct dm_dirty_log *log = mddev->bitmap_info.log;
/* Use a mutex to guard daemon_work against
* bitmap_destroy.
@ -1138,11 +1141,12 @@ void bitmap_daemon_work(mddev_t *mddev)
spin_lock_irqsave(&bitmap->lock, flags);
for (j = 0; j < bitmap->chunks; j++) {
bitmap_counter_t *bmc;
if (!bitmap->filemap)
/* error or shutdown */
break;
page = filemap_get_page(bitmap, j);
if (!bitmap->filemap) {
if (!log)
/* error or shutdown */
break;
} else
page = filemap_get_page(bitmap, j);
if (page != lastpage) {
/* skip this page unless it's marked as needing cleaning */
@ -1197,14 +1201,11 @@ void bitmap_daemon_work(mddev_t *mddev)
(sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
&blocks, 0);
if (bmc) {
/*
if (j < 100) printk("bitmap: j=%lu, *bmc = 0x%x\n", j, *bmc);
*/
if (*bmc)
bitmap->allclean = 0;
if (*bmc == 2) {
*bmc=1; /* maybe clear the bit next time */
*bmc = 1; /* maybe clear the bit next time */
set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
} else if (*bmc == 1 && !bitmap->need_sync) {
/* we can clear the bit */
@ -1214,14 +1215,17 @@ void bitmap_daemon_work(mddev_t *mddev)
-1);
/* clear the bit */
paddr = kmap_atomic(page, KM_USER0);
if (bitmap->flags & BITMAP_HOSTENDIAN)
clear_bit(file_page_offset(bitmap, j),
paddr);
else
ext2_clear_bit(file_page_offset(bitmap, j),
paddr);
kunmap_atomic(paddr, KM_USER0);
if (page) {
paddr = kmap_atomic(page, KM_USER0);
if (bitmap->flags & BITMAP_HOSTENDIAN)
clear_bit(file_page_offset(bitmap, j),
paddr);
else
ext2_clear_bit(file_page_offset(bitmap, j),
paddr);
kunmap_atomic(paddr, KM_USER0);
} else
log->type->clear_region(log, j);
}
} else
j |= PAGE_COUNTER_MASK;
@ -1229,12 +1233,16 @@ void bitmap_daemon_work(mddev_t *mddev)
spin_unlock_irqrestore(&bitmap->lock, flags);
/* now sync the final page */
if (lastpage != NULL) {
if (lastpage != NULL || log != NULL) {
spin_lock_irqsave(&bitmap->lock, flags);
if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) {
clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
write_page(bitmap, lastpage, 0);
if (lastpage)
write_page(bitmap, lastpage, 0);
else
if (log->type->flush(log))
bitmap->flags |= BITMAP_WRITE_ERROR;
} else {
set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
spin_unlock_irqrestore(&bitmap->lock, flags);
@ -1243,7 +1251,7 @@ void bitmap_daemon_work(mddev_t *mddev)
done:
if (bitmap->allclean == 0)
bitmap->mddev->thread->timeout =
bitmap->mddev->thread->timeout =
bitmap->mddev->bitmap_info.daemon_sleep;
mutex_unlock(&mddev->bitmap_info.mutex);
}
@ -1262,34 +1270,38 @@ __acquires(bitmap->lock)
unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT;
sector_t csize;
int err;
if (bitmap_checkpage(bitmap, page, create) < 0) {
err = bitmap_checkpage(bitmap, page, create);
if (bitmap->bp[page].hijacked ||
bitmap->bp[page].map == NULL)
csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
PAGE_COUNTER_SHIFT - 1);
else
csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
*blocks = csize - (offset & (csize- 1));
*blocks = csize - (offset & (csize - 1));
if (err < 0)
return NULL;
}
/* now locked ... */
if (bitmap->bp[page].hijacked) { /* hijacked pointer */
/* should we use the first or second counter field
* of the hijacked pointer? */
int hi = (pageoff > PAGE_COUNTER_MASK);
csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
PAGE_COUNTER_SHIFT - 1);
*blocks = csize - (offset & (csize- 1));
return &((bitmap_counter_t *)
&bitmap->bp[page].map)[hi];
} else { /* page is allocated */
csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
*blocks = csize - (offset & (csize- 1));
} else /* page is allocated */
return (bitmap_counter_t *)
&(bitmap->bp[page].map[pageoff]);
}
}
int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind)
{
if (!bitmap) return 0;
if (!bitmap)
return 0;
if (behind) {
int bw;
@ -1322,17 +1334,16 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
prepare_to_wait(&bitmap->overflow_wait, &__wait,
TASK_UNINTERRUPTIBLE);
spin_unlock_irq(&bitmap->lock);
blk_unplug(bitmap->mddev->queue);
md_unplug(bitmap->mddev);
schedule();
finish_wait(&bitmap->overflow_wait, &__wait);
continue;
}
switch(*bmc) {
switch (*bmc) {
case 0:
bitmap_file_set_bit(bitmap, offset);
bitmap_count_page(bitmap,offset, 1);
blk_plug_device_unlocked(bitmap->mddev->queue);
bitmap_count_page(bitmap, offset, 1);
/* fall through */
case 1:
*bmc = 2;
@ -1345,16 +1356,19 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect
offset += blocks;
if (sectors > blocks)
sectors -= blocks;
else sectors = 0;
else
sectors = 0;
}
bitmap->allclean = 0;
return 0;
}
EXPORT_SYMBOL(bitmap_startwrite);
void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
int success, int behind)
{
if (!bitmap) return;
if (!bitmap)
return;
if (behind) {
if (atomic_dec_and_test(&bitmap->behind_writes))
wake_up(&bitmap->behind_wait);
@ -1381,7 +1395,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
bitmap->events_cleared < bitmap->mddev->events) {
bitmap->events_cleared = bitmap->mddev->events;
bitmap->need_sync = 1;
sysfs_notify_dirent(bitmap->sysfs_can_clear);
sysfs_notify_dirent_safe(bitmap->sysfs_can_clear);
}
if (!success && ! (*bmc & NEEDED_MASK))
@ -1391,18 +1405,22 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
wake_up(&bitmap->overflow_wait);
(*bmc)--;
if (*bmc <= 2) {
if (*bmc <= 2)
set_page_attr(bitmap,
filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
filemap_get_page(
bitmap,
offset >> CHUNK_BLOCK_SHIFT(bitmap)),
BITMAP_PAGE_CLEAN);
}
spin_unlock_irqrestore(&bitmap->lock, flags);
offset += blocks;
if (sectors > blocks)
sectors -= blocks;
else sectors = 0;
else
sectors = 0;
}
}
EXPORT_SYMBOL(bitmap_endwrite);
static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
int degraded)
@ -1455,14 +1473,14 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
}
return rv;
}
EXPORT_SYMBOL(bitmap_start_sync);
void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted)
{
bitmap_counter_t *bmc;
unsigned long flags;
/*
if (offset == 0) printk("bitmap_end_sync 0 (%d)\n", aborted);
*/ if (bitmap == NULL) {
if (bitmap == NULL) {
*blocks = 1024;
return;
}
@ -1471,26 +1489,23 @@ void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int ab
if (bmc == NULL)
goto unlock;
/* locked */
/*
if (offset == 0) printk("bitmap_end sync found 0x%x, blocks %d\n", *bmc, *blocks);
*/
if (RESYNC(*bmc)) {
*bmc &= ~RESYNC_MASK;
if (!NEEDED(*bmc) && aborted)
*bmc |= NEEDED_MASK;
else {
if (*bmc <= 2) {
if (*bmc <= 2)
set_page_attr(bitmap,
filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
BITMAP_PAGE_CLEAN);
}
}
}
unlock:
spin_unlock_irqrestore(&bitmap->lock, flags);
bitmap->allclean = 0;
}
EXPORT_SYMBOL(bitmap_end_sync);
void bitmap_close_sync(struct bitmap *bitmap)
{
@ -1507,6 +1522,7 @@ void bitmap_close_sync(struct bitmap *bitmap)
sector += blocks;
}
}
EXPORT_SYMBOL(bitmap_close_sync);
void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
{
@ -1526,7 +1542,8 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
atomic_read(&bitmap->mddev->recovery_active) == 0);
bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync;
set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
if (bitmap->mddev->persistent)
set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
s = 0;
while (s < sector && s < bitmap->mddev->resync_max_sectors) {
@ -1536,6 +1553,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
bitmap->last_end_sync = jiffies;
sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed");
}
EXPORT_SYMBOL(bitmap_cond_end_sync);
static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
{
@ -1552,9 +1570,9 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
spin_unlock_irq(&bitmap->lock);
return;
}
if (! *bmc) {
if (!*bmc) {
struct page *page;
*bmc = 1 | (needed?NEEDED_MASK:0);
*bmc = 1 | (needed ? NEEDED_MASK : 0);
bitmap_count_page(bitmap, offset, 1);
page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap));
set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
@ -1663,15 +1681,17 @@ int bitmap_create(mddev_t *mddev)
unsigned long pages;
struct file *file = mddev->bitmap_info.file;
int err;
sector_t start;
struct sysfs_dirent *bm;
struct sysfs_dirent *bm = NULL;
BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
if (!file && !mddev->bitmap_info.offset) /* bitmap disabled, nothing to do */
if (!file
&& !mddev->bitmap_info.offset
&& !mddev->bitmap_info.log) /* bitmap disabled, nothing to do */
return 0;
BUG_ON(file && mddev->bitmap_info.offset);
BUG_ON(mddev->bitmap_info.offset && mddev->bitmap_info.log);
bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
if (!bitmap)
@ -1685,7 +1705,8 @@ int bitmap_create(mddev_t *mddev)
bitmap->mddev = mddev;
bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap");
if (mddev->kobj.sd)
bm = sysfs_get_dirent(mddev->kobj.sd, NULL, "bitmap");
if (bm) {
bitmap->sysfs_can_clear = sysfs_get_dirent(bm, NULL, "can_clear");
sysfs_put(bm);
@ -1719,9 +1740,9 @@ int bitmap_create(mddev_t *mddev)
bitmap->chunkshift = ffz(~mddev->bitmap_info.chunksize);
/* now that chunksize and chunkshift are set, we can use these macros */
chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
CHUNK_BLOCK_SHIFT(bitmap);
pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;
BUG_ON(!pages);
@ -1741,27 +1762,11 @@ int bitmap_create(mddev_t *mddev)
if (!bitmap->bp)
goto error;
/* now that we have some pages available, initialize the in-memory
* bitmap from the on-disk bitmap */
start = 0;
if (mddev->degraded == 0
|| bitmap->events_cleared == mddev->events)
/* no need to keep dirty bits to optimise a re-add of a missing device */
start = mddev->recovery_cp;
err = bitmap_init_from_disk(bitmap, start);
if (err)
goto error;
printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",
pages, bmname(bitmap));
mddev->bitmap = bitmap;
mddev->thread->timeout = mddev->bitmap_info.daemon_sleep;
md_wakeup_thread(mddev->thread);
bitmap_update_sb(bitmap);
return (bitmap->flags & BITMAP_WRITE_ERROR) ? -EIO : 0;
@ -1770,15 +1775,69 @@ int bitmap_create(mddev_t *mddev)
return err;
}
int bitmap_load(mddev_t *mddev)
{
int err = 0;
sector_t sector = 0;
struct bitmap *bitmap = mddev->bitmap;
if (!bitmap)
goto out;
/* Clear out old bitmap info first: Either there is none, or we
* are resuming after someone else has possibly changed things,
* so we should forget old cached info.
* All chunks should be clean, but some might need_sync.
*/
while (sector < mddev->resync_max_sectors) {
int blocks;
bitmap_start_sync(bitmap, sector, &blocks, 0);
sector += blocks;
}
bitmap_close_sync(bitmap);
if (mddev->bitmap_info.log) {
unsigned long i;
struct dm_dirty_log *log = mddev->bitmap_info.log;
for (i = 0; i < bitmap->chunks; i++)
if (!log->type->in_sync(log, i, 1))
bitmap_set_memory_bits(bitmap,
(sector_t)i << CHUNK_BLOCK_SHIFT(bitmap),
1);
} else {
sector_t start = 0;
if (mddev->degraded == 0
|| bitmap->events_cleared == mddev->events)
/* no need to keep dirty bits to optimise a
* re-add of a missing device */
start = mddev->recovery_cp;
err = bitmap_init_from_disk(bitmap, start);
}
if (err)
goto out;
mddev->thread->timeout = mddev->bitmap_info.daemon_sleep;
md_wakeup_thread(mddev->thread);
bitmap_update_sb(bitmap);
if (bitmap->flags & BITMAP_WRITE_ERROR)
err = -EIO;
out:
return err;
}
EXPORT_SYMBOL_GPL(bitmap_load);
static ssize_t
location_show(mddev_t *mddev, char *page)
{
ssize_t len;
if (mddev->bitmap_info.file) {
if (mddev->bitmap_info.file)
len = sprintf(page, "file");
} else if (mddev->bitmap_info.offset) {
else if (mddev->bitmap_info.offset)
len = sprintf(page, "%+lld", (long long)mddev->bitmap_info.offset);
} else
else
len = sprintf(page, "none");
len += sprintf(page+len, "\n");
return len;
@ -1867,7 +1926,7 @@ timeout_show(mddev_t *mddev, char *page)
ssize_t len;
unsigned long secs = mddev->bitmap_info.daemon_sleep / HZ;
unsigned long jifs = mddev->bitmap_info.daemon_sleep % HZ;
len = sprintf(page, "%lu", secs);
if (jifs)
len += sprintf(page+len, ".%03u", jiffies_to_msecs(jifs));
@ -2049,12 +2108,3 @@ struct attribute_group md_bitmap_group = {
.attrs = md_bitmap_attrs,
};
/* the bitmap API -- for raid personalities */
EXPORT_SYMBOL(bitmap_startwrite);
EXPORT_SYMBOL(bitmap_endwrite);
EXPORT_SYMBOL(bitmap_start_sync);
EXPORT_SYMBOL(bitmap_end_sync);
EXPORT_SYMBOL(bitmap_unplug);
EXPORT_SYMBOL(bitmap_close_sync);
EXPORT_SYMBOL(bitmap_cond_end_sync);

6
drivers/md/bitmap.h
View File

@ -222,6 +222,10 @@ struct bitmap {
unsigned long file_pages; /* number of pages in the file */
int last_page_size; /* bytes in the last page */
unsigned long logattrs; /* used when filemap_attr doesn't exist
* because we are working with a dirty_log
*/
unsigned long flags;
int allclean;
@ -243,12 +247,14 @@ struct bitmap {
wait_queue_head_t behind_wait;
struct sysfs_dirent *sysfs_can_clear;
};
/* the bitmap API */
/* these are used only by md/bitmap */
int bitmap_create(mddev_t *mddev);
int bitmap_load(mddev_t *mddev);
void bitmap_flush(mddev_t *mddev);
void bitmap_destroy(mddev_t *mddev);

286
drivers/md/md.c
View File

@ -262,7 +262,7 @@ static int md_make_request(struct request_queue *q, struct bio *bio)
* Once ->stop is called and completes, the module will be completely
* unused.
*/
static void mddev_suspend(mddev_t *mddev)
void mddev_suspend(mddev_t *mddev)
{
BUG_ON(mddev->suspended);
mddev->suspended = 1;
@ -270,13 +270,15 @@ static void mddev_suspend(mddev_t *mddev)
wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
mddev->pers->quiesce(mddev, 1);
}
EXPORT_SYMBOL_GPL(mddev_suspend);
static void mddev_resume(mddev_t *mddev)
void mddev_resume(mddev_t *mddev)
{
mddev->suspended = 0;
wake_up(&mddev->sb_wait);
mddev->pers->quiesce(mddev, 0);
}
EXPORT_SYMBOL_GPL(mddev_resume);
int mddev_congested(mddev_t *mddev, int bits)
{
@ -385,6 +387,51 @@ void md_barrier_request(mddev_t *mddev, struct bio *bio)
}
EXPORT_SYMBOL(md_barrier_request);
/* Support for plugging.
* This mirrors the plugging support in request_queue, but does not
* require having a whole queue
*/
static void plugger_work(struct work_struct *work)
{
struct plug_handle *plug =
container_of(work, struct plug_handle, unplug_work);
plug->unplug_fn(plug);
}
static void plugger_timeout(unsigned long data)
{
struct plug_handle *plug = (void *)data;
kblockd_schedule_work(NULL, &plug->unplug_work);
}
void plugger_init(struct plug_handle *plug,
void (*unplug_fn)(struct plug_handle *))
{
plug->unplug_flag = 0;
plug->unplug_fn = unplug_fn;
init_timer(&plug->unplug_timer);
plug->unplug_timer.function = plugger_timeout;
plug->unplug_timer.data = (unsigned long)plug;
INIT_WORK(&plug->unplug_work, plugger_work);
}
EXPORT_SYMBOL_GPL(plugger_init);
void plugger_set_plug(struct plug_handle *plug)
{
if (!test_and_set_bit(PLUGGED_FLAG, &plug->unplug_flag))
mod_timer(&plug->unplug_timer, jiffies + msecs_to_jiffies(3)+1);
}
EXPORT_SYMBOL_GPL(plugger_set_plug);
int plugger_remove_plug(struct plug_handle *plug)
{
if (test_and_clear_bit(PLUGGED_FLAG, &plug->unplug_flag)) {
del_timer(&plug->unplug_timer);
return 1;
} else
return 0;
}
EXPORT_SYMBOL_GPL(plugger_remove_plug);
static inline mddev_t *mddev_get(mddev_t *mddev)
{
atomic_inc(&mddev->active);
@ -417,7 +464,7 @@ static void mddev_put(mddev_t *mddev)
spin_unlock(&all_mddevs_lock);
}
static void mddev_init(mddev_t *mddev)
void mddev_init(mddev_t *mddev)
{
mutex_init(&mddev->open_mutex);
mutex_init(&mddev->reconfig_mutex);
@ -437,6 +484,7 @@ static void mddev_init(mddev_t *mddev)
mddev->resync_max = MaxSector;
mddev->level = LEVEL_NONE;
}
EXPORT_SYMBOL_GPL(mddev_init);
static mddev_t * mddev_find(dev_t unit)
{
@ -533,25 +581,31 @@ static void mddev_unlock(mddev_t * mddev)
* an access to the files will try to take reconfig_mutex
* while holding the file unremovable, which leads to
* a deadlock.
* So hold open_mutex instead - we are allowed to take
* it while holding reconfig_mutex, and md_run can
* use it to wait for the remove to complete.
* So hold set sysfs_active while the remove in happeing,
* and anything else which might set ->to_remove or my
* otherwise change the sysfs namespace will fail with
* -EBUSY if sysfs_active is still set.
* We set sysfs_active under reconfig_mutex and elsewhere
* test it under the same mutex to ensure its correct value
* is seen.
*/
struct attribute_group *to_remove = mddev->to_remove;
mddev->to_remove = NULL;
mutex_lock(&mddev->open_mutex);
mddev->sysfs_active = 1;
mutex_unlock(&mddev->reconfig_mutex);
if (to_remove != &md_redundancy_group)
sysfs_remove_group(&mddev->kobj, to_remove);
if (mddev->pers == NULL ||
mddev->pers->sync_request == NULL) {
sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
if (mddev->sysfs_action)
sysfs_put(mddev->sysfs_action);
mddev->sysfs_action = NULL;
if (mddev->kobj.sd) {
if (to_remove != &md_redundancy_group)
sysfs_remove_group(&mddev->kobj, to_remove);
if (mddev->pers == NULL ||
mddev->pers->sync_request == NULL) {
sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
if (mddev->sysfs_action)
sysfs_put(mddev->sysfs_action);
mddev->sysfs_action = NULL;
}
}
mutex_unlock(&mddev->open_mutex);
mddev->sysfs_active = 0;
} else
mutex_unlock(&mddev->reconfig_mutex);
@ -1812,11 +1866,9 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
goto fail;
ko = &part_to_dev(rdev->bdev->bd_part)->kobj;
if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
kobject_del(&rdev->kobj);
goto fail;
}
rdev->sysfs_state = sysfs_get_dirent(rdev->kobj.sd, NULL, "state");
if (sysfs_create_link(&rdev->kobj, ko, "block"))
/* failure here is OK */;
rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
list_add_rcu(&rdev->same_set, &mddev->disks);
bd_claim_by_disk(rdev->bdev, rdev->bdev->bd_holder, mddev->gendisk);
@ -2335,8 +2387,8 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
set_bit(In_sync, &rdev->flags);
err = 0;
}
if (!err && rdev->sysfs_state)
sysfs_notify_dirent(rdev->sysfs_state);
if (!err)
sysfs_notify_dirent_safe(rdev->sysfs_state);
return err ? err : len;
}
static struct rdev_sysfs_entry rdev_state =
@ -2431,14 +2483,10 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
rdev->raid_disk = -1;
return err;
} else
sysfs_notify_dirent(rdev->sysfs_state);
sysfs_notify_dirent_safe(rdev->sysfs_state);
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm))
printk(KERN_WARNING
"md: cannot register "
"%s for %s\n",
nm, mdname(rdev->mddev));
/* failure here is OK */;
/* don't wakeup anyone, leave that to userspace. */
} else {
if (slot >= rdev->mddev->raid_disks)
@ -2448,7 +2496,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len)
clear_bit(Faulty, &rdev->flags);
clear_bit(WriteMostly, &rdev->flags);
set_bit(In_sync, &rdev->flags);
sysfs_notify_dirent(rdev->sysfs_state);
sysfs_notify_dirent_safe(rdev->sysfs_state);
}
return len;
}
@ -2696,6 +2744,24 @@ static struct kobj_type rdev_ktype = {
.default_attrs = rdev_default_attrs,
};
void md_rdev_init(mdk_rdev_t *rdev)
{
rdev->desc_nr = -1;
rdev->saved_raid_disk = -1;
rdev->raid_disk = -1;
rdev->flags = 0;
rdev->data_offset = 0;
rdev->sb_events = 0;
rdev->last_read_error.tv_sec = 0;
rdev->last_read_error.tv_nsec = 0;
atomic_set(&rdev->nr_pending, 0);
atomic_set(&rdev->read_errors, 0);
atomic_set(&rdev->corrected_errors, 0);
INIT_LIST_HEAD(&rdev->same_set);
init_waitqueue_head(&rdev->blocked_wait);
}
EXPORT_SYMBOL_GPL(md_rdev_init);
/*
* Import a device. If 'super_format' >= 0, then sanity check the superblock
*
@ -2719,6 +2785,7 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
return ERR_PTR(-ENOMEM);
}
md_rdev_init(rdev);
if ((err = alloc_disk_sb(rdev)))
goto abort_free;
@ -2728,18 +2795,6 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
kobject_init(&rdev->kobj, &rdev_ktype);
rdev->desc_nr = -1;
rdev->saved_raid_disk = -1;
rdev->raid_disk = -1;
rdev->flags = 0;
rdev->data_offset = 0;
rdev->sb_events = 0;
rdev->last_read_error.tv_sec = 0;
rdev->last_read_error.tv_nsec = 0;
atomic_set(&rdev->nr_pending, 0);
atomic_set(&rdev->read_errors, 0);
atomic_set(&rdev->corrected_errors, 0);
size = rdev->bdev->bd_inode->i_size >> BLOCK_SIZE_BITS;
if (!size) {
printk(KERN_WARNING
@ -2768,9 +2823,6 @@ static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_mi
}
}
INIT_LIST_HEAD(&rdev->same_set);
init_waitqueue_head(&rdev->blocked_wait);
return rdev;
abort_free:
@ -2961,7 +3013,9 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
* - new personality will access other array.
*/
if (mddev->sync_thread || mddev->reshape_position != MaxSector)
if (mddev->sync_thread ||
mddev->reshape_position != MaxSector ||
mddev->sysfs_active)
return -EBUSY;
if (!mddev->pers->quiesce) {
@ -3438,7 +3492,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
if (err)
return err;
else {
sysfs_notify_dirent(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_state);
return len;
}
}
@ -3736,7 +3790,7 @@ action_store(mddev_t *mddev, const char *page, size_t len)
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
sysfs_notify_dirent(mddev->sysfs_action);
sysfs_notify_dirent_safe(mddev->sysfs_action);
return len;
}
@ -4282,13 +4336,14 @@ static int md_alloc(dev_t dev, char *name)
disk->disk_name);
error = 0;
}
if (sysfs_create_group(&mddev->kobj, &md_bitmap_group))
if (mddev->kobj.sd &&
sysfs_create_group(&mddev->kobj, &md_bitmap_group))
printk(KERN_DEBUG "pointless warning\n");
abort:
mutex_unlock(&disks_mutex);
if (!error) {
if (!error && mddev->kobj.sd) {
kobject_uevent(&mddev->kobj, KOBJ_ADD);
mddev->sysfs_state = sysfs_get_dirent(mddev->kobj.sd, NULL, "array_state");
mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
}
mddev_put(mddev);
return error;
@ -4326,14 +4381,14 @@ static void md_safemode_timeout(unsigned long data)
if (!atomic_read(&mddev->writes_pending)) {
mddev->safemode = 1;
if (mddev->external)
sysfs_notify_dirent(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_state);
}
md_wakeup_thread(mddev->thread);
}
static int start_dirty_degraded;
static int md_run(mddev_t *mddev)
int md_run(mddev_t *mddev)
{
int err;
mdk_rdev_t *rdev;
@ -4345,13 +4400,9 @@ static int md_run(mddev_t *mddev)
if (mddev->pers)
return -EBUSY;
/* These two calls synchronise us with the
* sysfs_remove_group calls in mddev_unlock,
* so they must have completed.
*/
mutex_lock(&mddev->open_mutex);
mutex_unlock(&mddev->open_mutex);
/* Cannot run until previous stop completes properly */
if (mddev->sysfs_active)
return -EBUSY;
/*
* Analyze all RAID superblock(s)
@ -4398,7 +4449,7 @@ static int md_run(mddev_t *mddev)
return -EINVAL;
}
}
sysfs_notify_dirent(rdev->sysfs_state);
sysfs_notify_dirent_safe(rdev->sysfs_state);
}
spin_lock(&pers_lock);
@ -4497,11 +4548,12 @@ static int md_run(mddev_t *mddev)
return err;
}
if (mddev->pers->sync_request) {
if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
if (mddev->kobj.sd &&
sysfs_create_group(&mddev->kobj, &md_redundancy_group))
printk(KERN_WARNING
"md: cannot register extra attributes for %s\n",
mdname(mddev));
mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, NULL, "sync_action");
mddev->sysfs_action = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_action");
} else if (mddev->ro == 2) /* auto-readonly not meaningful */
mddev->ro = 0;
@ -4519,8 +4571,7 @@ static int md_run(mddev_t *mddev)
char nm[20];
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
printk("md: cannot register %s for %s\n",
nm, mdname(mddev));
/* failure here is OK */;
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@ -4532,12 +4583,12 @@ static int md_run(mddev_t *mddev)
md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
md_new_event(mddev);
sysfs_notify_dirent(mddev->sysfs_state);
if (mddev->sysfs_action)
sysfs_notify_dirent(mddev->sysfs_action);
sysfs_notify_dirent_safe(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_action);
sysfs_notify(&mddev->kobj, NULL, "degraded");
return 0;
}
EXPORT_SYMBOL_GPL(md_run);
static int do_md_run(mddev_t *mddev)
{
@ -4546,7 +4597,11 @@ static int do_md_run(mddev_t *mddev)
err = md_run(mddev);
if (err)
goto out;
err = bitmap_load(mddev);
if (err) {
bitmap_destroy(mddev);
goto out;
}
set_capacity(mddev->gendisk, mddev->array_sectors);
revalidate_disk(mddev->gendisk);
kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
@ -4574,7 +4629,7 @@ static int restart_array(mddev_t *mddev)
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
md_wakeup_thread(mddev->sync_thread);
sysfs_notify_dirent(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_state);
return 0;
}
@ -4645,9 +4700,10 @@ static void md_clean(mddev_t *mddev)
mddev->bitmap_info.chunksize = 0;
mddev->bitmap_info.daemon_sleep = 0;
mddev->bitmap_info.max_write_behind = 0;
mddev->plug = NULL;
}
static void md_stop_writes(mddev_t *mddev)
void md_stop_writes(mddev_t *mddev)
{
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
@ -4667,11 +4723,10 @@ static void md_stop_writes(mddev_t *mddev)
md_update_sb(mddev, 1);
}
}
EXPORT_SYMBOL_GPL(md_stop_writes);
static void md_stop(mddev_t *mddev)
void md_stop(mddev_t *mddev)
{
md_stop_writes(mddev);
mddev->pers->stop(mddev);
if (mddev->pers->sync_request && mddev->to_remove == NULL)
mddev->to_remove = &md_redundancy_group;
@ -4679,6 +4734,7 @@ static void md_stop(mddev_t *mddev)
mddev->pers = NULL;
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
}
EXPORT_SYMBOL_GPL(md_stop);
static int md_set_readonly(mddev_t *mddev, int is_open)
{
@ -4698,7 +4754,7 @@ static int md_set_readonly(mddev_t *mddev, int is_open)
mddev->ro = 1;
set_disk_ro(mddev->gendisk, 1);
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
sysfs_notify_dirent(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_state);
err = 0;
}
out:
@ -4712,26 +4768,29 @@ out:
*/
static int do_md_stop(mddev_t * mddev, int mode, int is_open)
{
int err = 0;
struct gendisk *disk = mddev->gendisk;
mdk_rdev_t *rdev;
mutex_lock(&mddev->open_mutex);
if (atomic_read(&mddev->openers) > is_open) {
if (atomic_read(&mddev->openers) > is_open ||
mddev->sysfs_active) {
printk("md: %s still in use.\n",mdname(mddev));
err = -EBUSY;
} else if (mddev->pers) {
mutex_unlock(&mddev->open_mutex);
return -EBUSY;
}
if (mddev->pers) {
if (mddev->ro)
set_disk_ro(disk, 0);
md_stop_writes(mddev);
md_stop(mddev);
mddev->queue->merge_bvec_fn = NULL;
mddev->queue->unplug_fn = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
/* tell userspace to handle 'inactive' */
sysfs_notify_dirent(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_state);
list_for_each_entry(rdev, &mddev->disks, same_set)
if (rdev->raid_disk >= 0) {
@ -4741,21 +4800,17 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
}
set_capacity(disk, 0);
mutex_unlock(&mddev->open_mutex);
revalidate_disk(disk);
if (mddev->ro)
mddev->ro = 0;
err = 0;
}
mutex_unlock(&mddev->open_mutex);
if (err)
return err;
} else
mutex_unlock(&mddev->open_mutex);
/*
* Free resources if final stop
*/
if (mode == 0) {
printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
bitmap_destroy(mddev);
@ -4772,13 +4827,11 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
if (mddev->hold_active == UNTIL_STOP)
mddev->hold_active = 0;
}
err = 0;
blk_integrity_unregister(disk);
md_new_event(mddev);
sysfs_notify_dirent(mddev->sysfs_state);
return err;
sysfs_notify_dirent_safe(mddev->sysfs_state);
return 0;
}
#ifndef MODULE
@ -5139,7 +5192,7 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
if (err)
export_rdev(rdev);
else
sysfs_notify_dirent(rdev->sysfs_state);
sysfs_notify_dirent_safe(rdev->sysfs_state);
md_update_sb(mddev, 1);
if (mddev->degraded)
@ -5332,8 +5385,11 @@ static int set_bitmap_file(mddev_t *mddev, int fd)
err = 0;
if (mddev->pers) {
mddev->pers->quiesce(mddev, 1);
if (fd >= 0)
if (fd >= 0) {
err = bitmap_create(mddev);
if (!err)
err = bitmap_load(mddev);
}
if (fd < 0 || err) {
bitmap_destroy(mddev);
fd = -1; /* make sure to put the file */
@ -5582,6 +5638,8 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
mddev->bitmap_info.default_offset;
mddev->pers->quiesce(mddev, 1);
rv = bitmap_create(mddev);
if (!rv)
rv = bitmap_load(mddev);
if (rv)
bitmap_destroy(mddev);
mddev->pers->quiesce(mddev, 0);
@ -5814,7 +5872,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
if (_IOC_TYPE(cmd) == MD_MAJOR && mddev->ro && mddev->pers) {
if (mddev->ro == 2) {
mddev->ro = 0;
sysfs_notify_dirent(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_state);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
} else {
@ -6065,10 +6123,12 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev)
mddev->pers->error_handler(mddev,rdev);
if (mddev->degraded)
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
sysfs_notify_dirent(rdev->sysfs_state);
sysfs_notify_dirent_safe(rdev->sysfs_state);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
if (mddev->event_work.func)
schedule_work(&mddev->event_work);
md_new_event_inintr(mddev);
}
@ -6526,7 +6586,7 @@ void md_write_start(mddev_t *mddev, struct bio *bi)
spin_unlock_irq(&mddev->write_lock);
}
if (did_change)
sysfs_notify_dirent(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_state);
wait_event(mddev->sb_wait,
!test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
!test_bit(MD_CHANGE_PENDING, &mddev->flags));
@ -6569,7 +6629,7 @@ int md_allow_write(mddev_t *mddev)
mddev->safemode = 1;
spin_unlock_irq(&mddev->write_lock);
md_update_sb(mddev, 0);
sysfs_notify_dirent(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_state);
} else
spin_unlock_irq(&mddev->write_lock);
@ -6580,6 +6640,14 @@ int md_allow_write(mddev_t *mddev)
}
EXPORT_SYMBOL_GPL(md_allow_write);
void md_unplug(mddev_t *mddev)
{
if (mddev->queue)
blk_unplug(mddev->queue);
if (mddev->plug)
mddev->plug->unplug_fn(mddev->plug);
}
#define SYNC_MARKS 10
#define SYNC_MARK_STEP (3*HZ)
void md_do_sync(mddev_t *mddev)
@ -6758,12 +6826,13 @@ void md_do_sync(mddev_t *mddev)
>= mddev->resync_max - mddev->curr_resync_completed
)) {
/* time to update curr_resync_completed */
blk_unplug(mddev->queue);
md_unplug(mddev);
wait_event(mddev->recovery_wait,
atomic_read(&mddev->recovery_active) == 0);
mddev->curr_resync_completed =
mddev->curr_resync;
set_bit(MD_CHANGE_CLEAN, &mddev->flags);
if (mddev->persistent)
set_bit(MD_CHANGE_CLEAN, &mddev->flags);
sysfs_notify(&mddev->kobj, NULL, "sync_completed");
}
@ -6835,7 +6904,7 @@ void md_do_sync(mddev_t *mddev)
* about not overloading the IO subsystem. (things like an
* e2fsck being done on the RAID array should execute fast)
*/
blk_unplug(mddev->queue);
md_unplug(mddev);
cond_resched();
currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2
@ -6854,7 +6923,7 @@ void md_do_sync(mddev_t *mddev)
* this also signals 'finished resyncing' to md_stop
*/
out:
blk_unplug(mddev->queue);
md_unplug(mddev);
wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active));
@ -6956,10 +7025,7 @@ static int remove_and_add_spares(mddev_t *mddev)
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&mddev->kobj,
&rdev->kobj, nm))
printk(KERN_WARNING
"md: cannot register "
"%s for %s\n",
nm, mdname(mddev));
/* failure here is OK */;
spares++;
md_new_event(mddev);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
@ -7052,7 +7118,7 @@ void md_check_recovery(mddev_t *mddev)
mddev->safemode = 0;
spin_unlock_irq(&mddev->write_lock);
if (did_change)
sysfs_notify_dirent(mddev->sysfs_state);
sysfs_notify_dirent_safe(mddev->sysfs_state);
}
if (mddev->flags)
@ -7091,7 +7157,7 @@ void md_check_recovery(mddev_t *mddev)
mddev->recovery = 0;
/* flag recovery needed just to double check */
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
sysfs_notify_dirent(mddev->sysfs_action);
sysfs_notify_dirent_safe(mddev->sysfs_action);
md_new_event(mddev);
goto unlock;
}
@ -7153,7 +7219,7 @@ void md_check_recovery(mddev_t *mddev)
mddev->recovery = 0;
} else
md_wakeup_thread(mddev->sync_thread);
sysfs_notify_dirent(mddev->sysfs_action);
sysfs_notify_dirent_safe(mddev->sysfs_action);
md_new_event(mddev);
}
unlock:
@ -7162,7 +7228,7 @@ void md_check_recovery(mddev_t *mddev)
if (test_and_clear_bit(MD_RECOVERY_RECOVER,
&mddev->recovery))
if (mddev->sysfs_action)
sysfs_notify_dirent(mddev->sysfs_action);
sysfs_notify_dirent_safe(mddev->sysfs_action);
}
mddev_unlock(mddev);
}
@ -7170,7 +7236,7 @@ void md_check_recovery(mddev_t *mddev)
void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
{
sysfs_notify_dirent(rdev->sysfs_state);
sysfs_notify_dirent_safe(rdev->sysfs_state);
wait_event_timeout(rdev->blocked_wait,
!test_bit(Blocked, &rdev->flags),
msecs_to_jiffies(5000));

55
drivers/md/md.h
View File

@ -29,6 +29,26 @@
typedef struct mddev_s mddev_t;
typedef struct mdk_rdev_s mdk_rdev_t;
/* generic plugging support - like that provided with request_queue,
* but does not require a request_queue
*/
struct plug_handle {
void (*unplug_fn)(struct plug_handle *);
struct timer_list unplug_timer;
struct work_struct unplug_work;
unsigned long unplug_flag;
};
#define PLUGGED_FLAG 1
void plugger_init(struct plug_handle *plug,
void (*unplug_fn)(struct plug_handle *));
void plugger_set_plug(struct plug_handle *plug);
int plugger_remove_plug(struct plug_handle *plug);
static inline void plugger_flush(struct plug_handle *plug)
{
del_timer_sync(&plug->unplug_timer);
cancel_work_sync(&plug->unplug_work);
}
/*
* MD's 'extended' device
*/
@ -125,6 +145,10 @@ struct mddev_s
int suspended;
atomic_t active_io;
int ro;
int sysfs_active; /* set when sysfs deletes
* are happening, so run/
* takeover/stop are not safe
*/
struct gendisk *gendisk;
@ -297,9 +321,14 @@ struct mddev_s
* hot-adding a bitmap. It should
* eventually be settable by sysfs.
*/
/* When md is serving under dm, it might use a
* dirty_log to store the bits.
*/
struct dm_dirty_log *log;
struct mutex mutex;
unsigned long chunksize;
unsigned long daemon_sleep; /* how many seconds between updates? */
unsigned long daemon_sleep; /* how many jiffies between updates? */
unsigned long max_write_behind; /* write-behind mode */
int external;
} bitmap_info;
@ -308,6 +337,8 @@ struct mddev_s
struct list_head all_mddevs;
struct attribute_group *to_remove;
struct plug_handle *plug; /* if used by personality */
/* Generic barrier handling.
* If there is a pending barrier request, all other
* writes are blocked while the devices are flushed.
@ -318,6 +349,7 @@ struct mddev_s
struct bio *barrier;
atomic_t flush_pending;
struct work_struct barrier_work;
struct work_struct event_work; /* used by dm to report failure event */
};
@ -382,6 +414,18 @@ struct md_sysfs_entry {
};
extern struct attribute_group md_bitmap_group;
static inline struct sysfs_dirent *sysfs_get_dirent_safe(struct sysfs_dirent *sd, char *name)
{
if (sd)
return sysfs_get_dirent(sd, NULL, name);
return sd;
}
static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd)
{
if (sd)
sysfs_notify_dirent(sd);
}
static inline char * mdname (mddev_t * mddev)
{
return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
@ -474,5 +518,14 @@ extern int md_integrity_register(mddev_t *mddev);
extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
extern void restore_bitmap_write_access(struct file *file);
extern void md_unplug(mddev_t *mddev);
extern void mddev_init(mddev_t *mddev);
extern int md_run(mddev_t *mddev);
extern void md_stop(mddev_t *mddev);
extern void md_stop_writes(mddev_t *mddev);
extern void md_rdev_init(mdk_rdev_t *rdev);
extern void mddev_suspend(mddev_t *mddev);
extern void mddev_resume(mddev_t *mddev);
#endif /* _MD_MD_H */

18
drivers/md/raid10.c
View File

@ -825,11 +825,29 @@ static int make_request(mddev_t *mddev, struct bio * bio)
*/
bp = bio_split(bio,
chunk_sects - (bio->bi_sector & (chunk_sects - 1)) );
/* Each of these 'make_request' calls will call 'wait_barrier'.
* If the first succeeds but the second blocks due to the resync
* thread raising the barrier, we will deadlock because the
* IO to the underlying device will be queued in generic_make_request
* and will never complete, so will never reduce nr_pending.
* So increment nr_waiting here so no new raise_barriers will
* succeed, and so the second wait_barrier cannot block.
*/
spin_lock_irq(&conf->resync_lock);
conf->nr_waiting++;
spin_unlock_irq(&conf->resync_lock);
if (make_request(mddev, &bp->bio1))
generic_make_request(&bp->bio1);
if (make_request(mddev, &bp->bio2))
generic_make_request(&bp->bio2);
spin_lock_irq(&conf->resync_lock);
conf->nr_waiting--;
wake_up(&conf->wait_barrier);
spin_unlock_irq(&conf->resync_lock);
bio_pair_release(bp);
return 0;
bad_map:

180
drivers/md/raid5.c
View File

@ -201,11 +201,11 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
if (test_bit(STRIPE_HANDLE, &sh->state)) {
if (test_bit(STRIPE_DELAYED, &sh->state)) {
list_add_tail(&sh->lru, &conf->delayed_list);
blk_plug_device(conf->mddev->queue);
plugger_set_plug(&conf->plug);
} else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
sh->bm_seq - conf->seq_write > 0) {
list_add_tail(&sh->lru, &conf->bitmap_list);
blk_plug_device(conf->mddev->queue);
plugger_set_plug(&conf->plug);
} else {
clear_bit(STRIPE_BIT_DELAY, &sh->state);
list_add_tail(&sh->lru, &conf->handle_list);
@ -434,7 +434,6 @@ static int has_failed(raid5_conf_t *conf)
}
static void unplug_slaves(mddev_t *mddev);
static void raid5_unplug_device(struct request_queue *q);
static struct stripe_head *
get_active_stripe(raid5_conf_t *conf, sector_t sector,
@ -464,7 +463,7 @@ get_active_stripe(raid5_conf_t *conf, sector_t sector,
< (conf->max_nr_stripes *3/4)
|| !conf->inactive_blocked),
conf->device_lock,
raid5_unplug_device(conf->mddev->queue)
md_raid5_unplug_device(conf)
);
conf->inactive_blocked = 0;
} else
@ -1337,10 +1336,14 @@ static int grow_stripes(raid5_conf_t *conf, int num)
struct kmem_cache *sc;
int devs = max(conf->raid_disks, conf->previous_raid_disks);
sprintf(conf->cache_name[0],
"raid%d-%s", conf->level, mdname(conf->mddev));
sprintf(conf->cache_name[1],
"raid%d-%s-alt", conf->level, mdname(conf->mddev));
if (conf->mddev->gendisk)
sprintf(conf->cache_name[0],
"raid%d-%s", conf->level, mdname(conf->mddev));
else
sprintf(conf->cache_name[0],
"raid%d-%p", conf->level, conf->mddev);
sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]);
conf->active_name = 0;
sc = kmem_cache_create(conf->cache_name[conf->active_name],
sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
@ -3614,7 +3617,7 @@ static void raid5_activate_delayed(raid5_conf_t *conf)
list_add_tail(&sh->lru, &conf->hold_list);
}
} else
blk_plug_device(conf->mddev->queue);
plugger_set_plug(&conf->plug);
}
static void activate_bit_delay(raid5_conf_t *conf)
@ -3655,36 +3658,44 @@ static void unplug_slaves(mddev_t *mddev)
rcu_read_unlock();
}
static void raid5_unplug_device(struct request_queue *q)
void md_raid5_unplug_device(raid5_conf_t *conf)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev->private;
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
if (blk_remove_plug(q)) {
if (plugger_remove_plug(&conf->plug)) {
conf->seq_flush++;
raid5_activate_delayed(conf);
}
md_wakeup_thread(mddev->thread);
md_wakeup_thread(conf->mddev->thread);
spin_unlock_irqrestore(&conf->device_lock, flags);
unplug_slaves(mddev);
unplug_slaves(conf->mddev);
}
EXPORT_SYMBOL_GPL(md_raid5_unplug_device);
static void raid5_unplug(struct plug_handle *plug)
{
raid5_conf_t *conf = container_of(plug, raid5_conf_t, plug);
md_raid5_unplug_device(conf);
}
static int raid5_congested(void *data, int bits)
static void raid5_unplug_queue(struct request_queue *q)
{
mddev_t *mddev = q->queuedata;
md_raid5_unplug_device(mddev->private);
}
int md_raid5_congested(mddev_t *mddev, int bits)
{
mddev_t *mddev = data;
raid5_conf_t *conf = mddev->private;
/* No difference between reads and writes. Just check
* how busy the stripe_cache is
*/
if (mddev_congested(mddev, bits))
return 1;
if (conf->inactive_blocked)
return 1;
if (conf->quiesce)
@ -3694,6 +3705,15 @@ static int raid5_congested(void *data, int bits)
return 0;
}
EXPORT_SYMBOL_GPL(md_raid5_congested);
static int raid5_congested(void *data, int bits)
{
mddev_t *mddev = data;
return mddev_congested(mddev, bits) ||
md_raid5_congested(mddev, bits);
}
/* We want read requests to align with chunks where possible,
* but write requests don't need to.
@ -4075,7 +4095,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
* add failed due to overlap. Flush everything
* and wait a while
*/
raid5_unplug_device(mddev->queue);
md_raid5_unplug_device(conf);
release_stripe(sh);
schedule();
goto retry;
@ -4566,6 +4586,32 @@ raid5_show_stripe_cache_size(mddev_t *mddev, char *page)
return 0;
}
int
raid5_set_cache_size(mddev_t *mddev, int size)
{
raid5_conf_t *conf = mddev->private;
int err;
if (size <= 16 || size > 32768)
return -EINVAL;
while (size < conf->max_nr_stripes) {
if (drop_one_stripe(conf))
conf->max_nr_stripes--;
else
break;
}
err = md_allow_write(mddev);
if (err)
return err;
while (size > conf->max_nr_stripes) {
if (grow_one_stripe(conf))
conf->max_nr_stripes++;
else break;
}
return 0;
}
EXPORT_SYMBOL(raid5_set_cache_size);
static ssize_t
raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
{
@ -4580,22 +4626,9 @@ raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
if (strict_strtoul(page, 10, &new))
return -EINVAL;
if (new <= 16 || new > 32768)
return -EINVAL;
while (new < conf->max_nr_stripes) {
if (drop_one_stripe(conf))
conf->max_nr_stripes--;
else
break;
}
err = md_allow_write(mddev);
err = raid5_set_cache_size(mddev, new);
if (err)
return err;
while (new > conf->max_nr_stripes) {
if (grow_one_stripe(conf))
conf->max_nr_stripes++;
else break;
}
return len;
}
@ -4958,7 +4991,7 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
static int run(mddev_t *mddev)
{
raid5_conf_t *conf;
int working_disks = 0, chunk_size;
int working_disks = 0;
int dirty_parity_disks = 0;
mdk_rdev_t *rdev;
sector_t reshape_offset = 0;
@ -5144,43 +5177,48 @@ static int run(mddev_t *mddev)
"reshape");
}
/* read-ahead size must cover two whole stripes, which is
* 2 * (datadisks) * chunksize where 'n' is the number of raid devices
*/
{
/* Ok, everything is just fine now */
if (mddev->to_remove == &raid5_attrs_group)
mddev->to_remove = NULL;
else if (mddev->kobj.sd &&
sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
printk(KERN_WARNING
"raid5: failed to create sysfs attributes for %s\n",
mdname(mddev));
md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
plugger_init(&conf->plug, raid5_unplug);
mddev->plug = &conf->plug;
if (mddev->queue) {
int chunk_size;
/* read-ahead size must cover two whole stripes, which
* is 2 * (datadisks) * chunksize where 'n' is the
* number of raid devices
*/
int data_disks = conf->previous_raid_disks - conf->max_degraded;
int stripe = data_disks *
((mddev->chunk_sectors << 9) / PAGE_SIZE);
if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
mddev->queue->backing_dev_info.congested_data = mddev;
mddev->queue->backing_dev_info.congested_fn = raid5_congested;
mddev->queue->queue_lock = &conf->device_lock;
mddev->queue->unplug_fn = raid5_unplug_queue;
chunk_size = mddev->chunk_sectors << 9;
blk_queue_io_min(mddev->queue, chunk_size);
blk_queue_io_opt(mddev->queue, chunk_size *
(conf->raid_disks - conf->max_degraded));
list_for_each_entry(rdev, &mddev->disks, same_set)
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
}
/* Ok, everything is just fine now */
if (mddev->to_remove == &raid5_attrs_group)
mddev->to_remove = NULL;
else if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
printk(KERN_WARNING
"md/raid:%s: failed to create sysfs attributes.\n",
mdname(mddev));
mddev->queue->queue_lock = &conf->device_lock;
mddev->queue->unplug_fn = raid5_unplug_device;
mddev->queue->backing_dev_info.congested_data = mddev;
mddev->queue->backing_dev_info.congested_fn = raid5_congested;
md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
chunk_size = mddev->chunk_sectors << 9;
blk_queue_io_min(mddev->queue, chunk_size);
blk_queue_io_opt(mddev->queue, chunk_size *
(conf->raid_disks - conf->max_degraded));
list_for_each_entry(rdev, &mddev->disks, same_set)
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
return 0;
abort:
md_unregister_thread(mddev->thread);
@ -5200,8 +5238,9 @@ static int stop(mddev_t *mddev)
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
if (mddev->queue)
mddev->queue->backing_dev_info.congested_fn = NULL;
plugger_flush(&conf->plug); /* the unplug fn references 'conf'*/
free_conf(conf);
mddev->private = NULL;
mddev->to_remove = &raid5_attrs_group;
@ -5545,10 +5584,7 @@ static int raid5_start_reshape(mddev_t *mddev)
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&mddev->kobj,
&rdev->kobj, nm))
printk(KERN_WARNING
"md/raid:%s: failed to create "
" link %s\n",
mdname(mddev), nm);
/* Failure here is OK */;
} else
break;
}
@ -5603,7 +5639,7 @@ static void end_reshape(raid5_conf_t *conf)
/* read-ahead size must cover two whole stripes, which is
* 2 * (datadisks) * chunksize where 'n' is the number of raid devices
*/
{
if (conf->mddev->queue) {
int data_disks = conf->raid_disks - conf->max_degraded;
int stripe = data_disks * ((conf->chunk_sectors << 9)
/ PAGE_SIZE);

9
drivers/md/raid5.h
View File

@ -388,7 +388,7 @@ struct raid5_private_data {
* two caches.
*/
int active_name;
char cache_name[2][20];
char cache_name[2][32];
struct kmem_cache *slab_cache; /* for allocating stripes */
int seq_flush, seq_write;
@ -398,6 +398,9 @@ struct raid5_private_data {
* (fresh device added).
* Cleared when a sync completes.
*/
struct plug_handle plug;
/* per cpu variables */
struct raid5_percpu {
struct page *spare_page; /* Used when checking P/Q in raid6 */
@ -497,4 +500,8 @@ static inline int algorithm_is_DDF(int layout)
{
return layout >= 8 && layout <= 10;
}
extern int md_raid5_congested(mddev_t *mddev, int bits);
extern void md_raid5_unplug_device(raid5_conf_t *conf);
extern int raid5_set_cache_size(mddev_t *mddev, int size);
#endif

3
lib/Kconfig
View File

@ -7,6 +7,9 @@ config BINARY_PRINTF
menu "Library routines"
config RAID6_PQ
tristate
config BITREVERSE
tristate

1
lib/Makefile
View File

@ -69,6 +69,7 @@ obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
obj-$(CONFIG_LZO_COMPRESS) += lzo/
obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
obj-$(CONFIG_RAID6_PQ) += raid6/
lib-$(CONFIG_DECOMPRESS_GZIP) += decompress_inflate.o
lib-$(CONFIG_DECOMPRESS_BZIP2) += decompress_bunzip2.o

78
lib/raid6/Makefile Normal file
View File

@ -0,0 +1,78 @@
obj-$(CONFIG_RAID6_PQ) += raid6_pq.o
raid6_pq-y += raid6algos.o raid6recov.o raid6tables.o \
raid6int1.o raid6int2.o raid6int4.o \
raid6int8.o raid6int16.o raid6int32.o \
raid6altivec1.o raid6altivec2.o raid6altivec4.o \
raid6altivec8.o \
raid6mmx.o raid6sse1.o raid6sse2.o
hostprogs-y += mktables
quiet_cmd_unroll = UNROLL $@
cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$(UNROLL) \
< $< > $@ || ( rm -f $@ && exit 1 )
ifeq ($(CONFIG_ALTIVEC),y)
altivec_flags := -maltivec -mabi=altivec
endif
targets += raid6int1.c
$(obj)/raid6int1.c: UNROLL := 1
$(obj)/raid6int1.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int2.c
$(obj)/raid6int2.c: UNROLL := 2
$(obj)/raid6int2.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int4.c
$(obj)/raid6int4.c: UNROLL := 4
$(obj)/raid6int4.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int8.c
$(obj)/raid6int8.c: UNROLL := 8
$(obj)/raid6int8.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int16.c
$(obj)/raid6int16.c: UNROLL := 16
$(obj)/raid6int16.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
targets += raid6int32.c
$(obj)/raid6int32.c: UNROLL := 32
$(obj)/raid6int32.c: $(src)/raid6int.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
CFLAGS_raid6altivec1.o += $(altivec_flags)
targets += raid6altivec1.c
$(obj)/raid6altivec1.c: UNROLL := 1
$(obj)/raid6altivec1.c: $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
CFLAGS_raid6altivec2.o += $(altivec_flags)
targets += raid6altivec2.c
$(obj)/raid6altivec2.c: UNROLL := 2
$(obj)/raid6altivec2.c: $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
CFLAGS_raid6altivec4.o += $(altivec_flags)
targets += raid6altivec4.c
$(obj)/raid6altivec4.c: UNROLL := 4
$(obj)/raid6altivec4.c: $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
CFLAGS_raid6altivec8.o += $(altivec_flags)
targets += raid6altivec8.c
$(obj)/raid6altivec8.c: UNROLL := 8
$(obj)/raid6altivec8.c: $(src)/raid6altivec.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
quiet_cmd_mktable = TABLE $@
cmd_mktable = $(obj)/mktables > $@ || ( rm -f $@ && exit 1 )
targets += raid6tables.c
$(obj)/raid6tables.c: $(obj)/mktables FORCE
$(call if_changed,mktable)

0
drivers/md/mktables.c → lib/raid6/mktables.c
View File

0
drivers/md/raid6algos.c → lib/raid6/raid6algos.c
View File

0
drivers/md/raid6altivec.uc → lib/raid6/raid6altivec.uc
View File

0
drivers/md/raid6int.uc → lib/raid6/raid6int.uc
View File

0
drivers/md/raid6mmx.c → lib/raid6/raid6mmx.c
View File

0
drivers/md/raid6recov.c → lib/raid6/raid6recov.c
View File

0
drivers/md/raid6sse1.c → lib/raid6/raid6sse1.c
View File

0
drivers/md/raid6sse2.c → lib/raid6/raid6sse2.c
View File

0
drivers/md/raid6test/Makefile → lib/raid6/raid6test/Makefile
View File

0
drivers/md/raid6test/test.c → lib/raid6/raid6test/test.c
View File

0
drivers/md/raid6x86.h → lib/raid6/raid6x86.h
View File

0
drivers/md/unroll.awk → lib/raid6/unroll.awk
View File