diff options
Diffstat (limited to 'drivers/md')
44 files changed, 1559 insertions, 2516 deletions
diff --git a/drivers/md/.gitignore b/drivers/md/.gitignore deleted file mode 100644 index a7afec6b19c..00000000000 --- a/drivers/md/.gitignore +++ /dev/null @@ -1,4 +0,0 @@ -mktables -raid6altivec*.c -raid6int*.c -raid6tables.c diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 4a6feac8c94..bf1a95e3155 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -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 diff --git a/drivers/md/Makefile b/drivers/md/Makefile index e355e7f6a53..5e3aac41919 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -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) diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 1742435ce3a..ed4900ade93 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -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 */ + /* 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: + bitmap->bp[page].map = mappage; + bitmap->missing_pages--; + } 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; - } - - page = filemap_get_page(bitmap, chunk); - if (!page) return; - bit = file_page_offset(bitmap, chunk); + struct dm_dirty_log *log = bitmap->mddev->bitmap_info.log; + if (log) + log->type->mark_region(log, chunk); + } else { - /* 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) { @@ -1536,6 +1552,7 @@ 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 +1569,9 @@ 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 +1680,17 @@ 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 +1704,8 @@ 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 +1739,9 @@ 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 +1761,11 @@ 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 +1774,69 @@ 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 +1925,7 @@ 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 +2107,3 @@ 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); diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h index 3797dea4723..e872a7bad6b 100644 --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -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); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 3bdbb611570..368e8e98f70 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -107,11 +107,10 @@ struct crypt_config { struct workqueue_struct *io_queue; struct workqueue_struct *crypt_queue; - /* - * crypto related data - */ + char *cipher; + char *cipher_mode; + struct crypt_iv_operations *iv_gen_ops; - char *iv_mode; union { struct iv_essiv_private essiv; struct iv_benbi_private benbi; @@ -135,8 +134,6 @@ struct crypt_config { unsigned int dmreq_start; struct ablkcipher_request *req; - char cipher[CRYPTO_MAX_ALG_NAME]; - char chainmode[CRYPTO_MAX_ALG_NAME]; struct crypto_ablkcipher *tfm; unsigned long flags; unsigned int key_size; @@ -999,82 +996,135 @@ static int crypt_wipe_key(struct crypt_config *cc) return crypto_ablkcipher_setkey(cc->tfm, cc->key, cc->key_size); } -/* - * Construct an encryption mapping: - * <cipher> <key> <iv_offset> <dev_path> <start> - */ -static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) +static void crypt_dtr(struct dm_target *ti) { - struct crypt_config *cc; - struct crypto_ablkcipher *tfm; - char *tmp; - char *cipher; - char *chainmode; - char *ivmode; - char *ivopts; - unsigned int key_size; - unsigned long long tmpll; + struct crypt_config *cc = ti->private; - if (argc != 5) { - ti->error = "Not enough arguments"; + ti->private = NULL; + + if (!cc) + return; + + if (cc->io_queue) + destroy_workqueue(cc->io_queue); + if (cc->crypt_queue) + destroy_workqueue(cc->crypt_queue); + + if (cc->bs) + bioset_free(cc->bs); + + if (cc->page_pool) + mempool_destroy(cc->page_pool); + if (cc->req_pool) + mempool_destroy(cc->req_pool); + if (cc->io_pool) + mempool_destroy(cc->io_pool); + + if (cc->iv_gen_ops && cc->iv_gen_ops->dtr) + cc->iv_gen_ops->dtr(cc); + + if (cc->tfm && !IS_ERR(cc->tfm)) + crypto_free_ablkcipher(cc->tfm); + + if (cc->dev) + dm_put_device(ti, cc->dev); + + kzfree(cc->cipher); + kzfree(cc->cipher_mode); + + /* Must zero key material before freeing */ + kzfree(cc); +} + +static int crypt_ctr_cipher(struct dm_target *ti, + char *cipher_in, char *key) +{ + struct crypt_config *cc = ti->private; + char *tmp, *cipher, *chainmode, *ivmode, *ivopts; + char *cipher_api = NULL; + int ret = -EINVAL; + + /* Convert to crypto api definition? */ + if (strchr(cipher_in, '(')) { + ti->error = "Bad cipher specification"; return -EINVAL; } - tmp = argv[0]; + /* + * Legacy dm-crypt cipher specification + * cipher-mode-iv:ivopts + */ + tmp = cipher_in; cipher = strsep(&tmp, "-"); + + cc->cipher = kstrdup(cipher, GFP_KERNEL); + if (!cc->cipher) + goto bad_mem; + + if (tmp) { + cc->cipher_mode = kstrdup(tmp, GFP_KERNEL); + if (!cc->cipher_mode) + goto bad_mem; + } + chainmode = strsep(&tmp, "-"); ivopts = strsep(&tmp, "-"); ivmode = strsep(&ivopts, ":"); if (tmp) - DMWARN("Unexpected additional cipher options"); - - key_size = strlen(argv[1]) >> 1; - - cc = kzalloc(sizeof(*cc) + key_size * sizeof(u8), GFP_KERNEL); - if (cc == NULL) { - ti->error = - "Cannot allocate transparent encryption context"; - return -ENOMEM; - } + DMWARN("Ignoring unexpected additional cipher options"); - /* Compatibility mode for old dm-crypt cipher strings */ - if (!chainmode || (strcmp(chainmode, "plain") == 0 && !ivmode)) { + /* Compatibility mode for old dm-crypt mappings */ + if (!chainmode || (!strcmp(chainmode, "plain") && !ivmode)) { + kfree(cc->cipher_mode); + cc->cipher_mode = kstrdup("cbc-plain", GFP_KERNEL); chainmode = "cbc"; ivmode = "plain"; } if (strcmp(chainmode, "ecb") && !ivmode) { - ti->error = "This chaining mode requires an IV mechanism"; - goto bad_cipher; + ti->error = "IV mechanism required"; + return -EINVAL; } - if (snprintf(cc->cipher, CRYPTO_MAX_ALG_NAME, "%s(%s)", - chainmode, cipher) >= CRYPTO_MAX_ALG_NAME) { - ti->error = "Chain mode + cipher name is too long"; - goto bad_cipher; + cipher_api = kmalloc(CRYPTO_MAX_ALG_NAME, GFP_KERNEL); + if (!cipher_api) + goto bad_mem; + + ret = snprintf(cipher_api, CRYPTO_MAX_ALG_NAME, + "%s(%s)", chainmode, cipher); + if (ret < 0) { + kfree(cipher_api); + goto bad_mem; } - tfm = crypto_alloc_ablkcipher(cc->cipher, 0, 0); - if (IS_ERR(tfm)) { + /* Allocate cipher */ + cc->tfm = crypto_alloc_ablkcipher(cipher_api, 0, 0); + if (IS_ERR(cc->tfm)) { + ret = PTR_ERR(cc->tfm); ti->error = "Error allocating crypto tfm"; - goto bad_cipher; + goto bad; } - strcpy(cc->cipher, cipher); - strcpy(cc->chainmode, chainmode); - cc->tfm = tfm; - - if (crypt_set_key(cc, argv[1]) < 0) { + /* Initialize and set key */ + ret = crypt_set_key(cc, key); + if (ret < 0) { ti->error = "Error decoding and setting key"; - goto bad_ivmode; + goto bad; } - /* - * Choose ivmode. Valid modes: "plain", "essiv:<esshash>", "benbi". - * See comments at iv code - */ + /* Initialize IV */ + cc->iv_size = crypto_ablkcipher_ivsize(cc->tfm); + if (cc->iv_size) + /* at least a 64 bit sector number should fit in our buffer */ + cc->iv_size = max(cc->iv_size, + (unsigned int)(sizeof(u64) / sizeof(u8))); + else if (ivmode) { + DMWARN("Selected cipher does not support IVs"); + ivmode = NULL; + } + /* Choose ivmode, see comments at iv code. */ if (ivmode == NULL) cc->iv_gen_ops = NULL; else if (strcmp(ivmode, "plain") == 0) @@ -1088,159 +1138,138 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) else if (strcmp(ivmode, "null") == 0) cc->iv_gen_ops = &crypt_iv_null_ops; else { + ret = -EINVAL; ti->error = "Invalid IV mode"; - goto bad_ivmode; + goto bad; } - if (cc->iv_gen_ops && cc->iv_gen_ops->ctr && - cc->iv_gen_ops->ctr(cc, ti, ivopts) < 0) - goto bad_ivmode; - - if (cc->iv_gen_ops && cc->iv_gen_ops->init && - cc->iv_gen_ops->init(cc) < 0) { - ti->error = "Error initialising IV"; - goto bad_slab_pool; + /* Allocate IV */ + if (cc->iv_gen_ops && cc->iv_gen_ops->ctr) { + ret = cc->iv_gen_ops->ctr(cc, ti, ivopts); + if (ret < 0) { + ti->error = "Error creating IV"; + goto bad; + } } - cc->iv_size = crypto_ablkcipher_ivsize(tfm); - if (cc->iv_size) - /* at least a 64 bit sector number should fit in our buffer */ - cc->iv_size = max(cc->iv_size, - (unsigned int)(sizeof(u64) / sizeof(u8))); - else { - if (cc->iv_gen_ops) { - DMWARN("Selected cipher does not support IVs"); - if (cc->iv_gen_ops->dtr) - cc->iv_gen_ops->dtr(cc); - cc->iv_gen_ops = NULL; + /* Initialize IV (set keys for ESSIV etc) */ + if (cc->iv_gen_ops && cc->iv_gen_ops->init) { + ret = cc->iv_gen_ops->init(cc); + if (ret < 0) { + ti->error = "Error initialising IV"; + goto bad; } } + ret = 0; +bad: + kfree(cipher_api); + return ret; + +bad_mem: + ti->error = "Cannot allocate cipher strings"; + return -ENOMEM; +} + +/* + * Construct an encryption mapping: + * <cipher> <key> <iv_offset> <dev_path> <start> + */ +static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) +{ + struct crypt_config *cc; + unsigned int key_size; + unsigned long long tmpll; + int ret; + + if (argc != 5) { + ti->error = "Not enough arguments"; + return -EINVAL; + } + + key_size = strlen(argv[1]) >> 1; + + cc = kzalloc(sizeof(*cc) + key_size * sizeof(u8), GFP_KERNEL); + if (!cc) { + ti->error = "Cannot allocate encryption context"; + return -ENOMEM; + } + + ti->private = cc; + ret = crypt_ctr_cipher(ti, argv[0], argv[1]); + if (ret < 0) + goto bad; + + ret = -ENOMEM; cc->io_pool = mempool_create_slab_pool(MIN_IOS, _crypt_io_pool); if (!cc->io_pool) { ti->error = "Cannot allocate crypt io mempool"; - goto bad_slab_pool; + goto bad; } cc->dmreq_start = sizeof(struct ablkcipher_request); - cc->dmreq_start += crypto_ablkcipher_reqsize(tfm); + cc->dmreq_start += crypto_ablkcipher_reqsize(cc->tfm); cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment()); - cc->dmreq_start += crypto_ablkcipher_alignmask(tfm) & + cc->dmreq_start += crypto_ablkcipher_alignmask(cc->tfm) & ~(crypto_tfm_ctx_alignment() - 1); cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start + sizeof(struct dm_crypt_request) + cc->iv_size); if (!cc->req_pool) { ti->error = "Cannot allocate crypt request mempool"; - goto bad_req_pool; + goto bad; } cc->req = NULL; cc->page_pool = mempool_create_page_pool(MIN_POOL_PAGES, 0); if (!cc->page_pool) { ti->error = "Cannot allocate page mempool"; - goto bad_page_pool; + goto bad; } cc->bs = bioset_create(MIN_IOS, 0); if (!cc->bs) { ti->error = "Cannot allocate crypt bioset"; - goto bad_bs; + goto bad; } + ret = -EINVAL; if (sscanf(argv[2], "%llu", &tmpll) != 1) { ti->error = "Invalid iv_offset sector"; - goto bad_device; + goto bad; } cc->iv_offset = tmpll; - if (sscanf(argv[4], "%llu", &tmpll) != 1) { - ti->error = "Invalid device sector"; - goto bad_device; - } - cc->start = tmpll; - if (dm_get_device(ti, argv[3], dm_table_get_mode(ti->table), &cc->dev)) { ti->error = "Device lookup failed"; - goto bad_device; + goto bad; } - if (ivmode && cc->iv_gen_ops) { - if (ivopts) - *(ivopts - 1) = ':'; - cc->iv_mode = kmalloc(strlen(ivmode) + 1, GFP_KERNEL); - if (!cc->iv_mode) { - ti->error = "Error kmallocing iv_mode string"; - goto bad_ivmode_string; - } - strcpy(cc->iv_mode, ivmode); - } else - cc->iv_mode = NULL; + if (sscanf(argv[4], "%llu", &tmpll) != 1) { + ti->error = "Invalid device sector"; + goto bad; + } + cc->start = tmpll; + ret = -ENOMEM; cc->io_queue = create_singlethread_workqueue("kcryptd_io"); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; - goto bad_io_queue; + goto bad; } cc->crypt_queue = create_singlethread_workqueue("kcryptd"); if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; - goto bad_crypt_queue; + goto bad; } ti->num_flush_requests = 1; - ti->private = cc; return 0; -bad_crypt_queue: - destroy_workqueue(cc->io_queue); -bad_io_queue: - kfree(cc->iv_mode); -bad_ivmode_string: - dm_put_device(ti, cc->dev); -bad_device: - bioset_free(cc->bs); -bad_bs: - mempool_destroy(cc->page_pool); -bad_page_pool: - mempool_destroy(cc->req_pool); -bad_req_pool: - mempool_destroy(cc->io_pool); -bad_slab_pool: - if (cc->iv_gen_ops && cc->iv_gen_ops->dtr) - cc->iv_gen_ops->dtr(cc); -bad_ivmode: - crypto_free_ablkcipher(tfm); -bad_cipher: - /* Must zero key material before freeing */ - kzfree(cc); - return -EINVAL; -} - -static void crypt_dtr(struct dm_target *ti) -{ - struct crypt_config *cc = (struct crypt_config *) ti->private; - - destroy_workqueue(cc->io_queue); - destroy_workqueue(cc->crypt_queue); - - if (cc->req) - mempool_free(cc->req, cc->req_pool); - - bioset_free(cc->bs); - mempool_destroy(cc->page_pool); - mempool_destroy(cc->req_pool); - mempool_destroy(cc->io_pool); - - kfree(cc->iv_mode); - if (cc->iv_gen_ops && cc->iv_gen_ops->dtr) - cc->iv_gen_ops->dtr(cc); - crypto_free_ablkcipher(cc->tfm); - dm_put_device(ti, cc->dev); - - /* Must zero key material before freeing */ - kzfree(cc); +bad: + crypt_dtr(ti); + return ret; } static int crypt_map(struct dm_target *ti, struct bio *bio, @@ -1255,7 +1284,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio, return DM_MAPIO_REMAPPED; } - io = crypt_io_alloc(ti, bio, bio->bi_sector - ti->begin); + io = crypt_io_alloc(ti, bio, dm_target_offset(ti, bio->bi_sector)); if (bio_data_dir(io->base_bio) == READ) kcryptd_queue_io(io); @@ -1268,7 +1297,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio, static int crypt_status(struct dm_target *ti, status_type_t type, char *result, unsigned int maxlen) { - struct crypt_config *cc = (struct crypt_config *) ti->private; + struct crypt_config *cc = ti->private; unsigned int sz = 0; switch (type) { @@ -1277,11 +1306,10 @@ static int crypt_status(struct dm_target *ti, status_type_t type, break; case STATUSTYPE_TABLE: - if (cc->iv_mode) - DMEMIT("%s-%s-%s ", cc->cipher, cc->chainmode, - cc->iv_mode); + if (cc->cipher_mode) + DMEMIT("%s-%s ", cc->cipher, cc->cipher_mode); else - DMEMIT("%s-%s ", cc->cipher, cc->chainmode); + DMEMIT("%s ", cc->cipher); if (cc->key_size > 0) { if ((maxlen - sz) < ((cc->key_size << 1) + 1)) @@ -1378,7 +1406,7 @@ static int crypt_merge(struct dm_target *ti, struct bvec_merge_data *bvm, return max_size; bvm->bi_bdev = cc->dev->bdev; - bvm->bi_sector = cc->start + bvm->bi_sector - ti->begin; + bvm->bi_sector = cc->start + dm_target_offset(ti, bvm->bi_sector); return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); } diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 852052880d7..baa11912cc9 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -198,6 +198,7 @@ out: atomic_set(&dc->may_delay, 1); ti->num_flush_requests = 1; + ti->num_discard_requests = 1; ti->private = dc; return 0; @@ -281,14 +282,13 @@ static int delay_map(struct dm_target *ti, struct bio *bio, bio->bi_bdev = dc->dev_write->bdev; if (bio_sectors(bio)) bio->bi_sector = dc->start_write + - (bio->bi_sector - ti->begin); + dm_target_offset(ti, bio->bi_sector); return delay_bio(dc, dc->write_delay, bio); } bio->bi_bdev = dc->dev_read->bdev; - bio->bi_sector = dc->start_read + - (bio->bi_sector - ti->begin); + bio->bi_sector = dc->start_read + dm_target_offset(ti, bio->bi_sector); return delay_bio(dc, dc->read_delay, bio); } diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c index 2b7907b6dd0..0bdb201c2c2 100644 --- a/drivers/md/dm-exception-store.c +++ b/drivers/md/dm-exception-store.c @@ -173,7 +173,9 @@ int dm_exception_store_set_chunk_size(struct dm_exception_store *store, /* Validate the chunk size against the device block size */ if (chunk_size % - (bdev_logical_block_size(dm_snap_cow(store->snap)->bdev) >> 9)) { + (bdev_logical_block_size(dm_snap_cow(store->snap)->bdev) >> 9) || + chunk_size % + (bdev_logical_block_size(dm_snap_origin(store->snap)->bdev) >> 9)) { *error = "Chunk size is not a multiple of device blocksize"; return -EINVAL; } diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index e8dfa06af3b..0b2536247cf 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -126,8 +126,9 @@ struct dm_exception_store { }; /* - * Obtain the cow device used by a given snapshot. + * Obtain the origin or cow device used by a given snapshot. */ +struct dm_dev *dm_snap_origin(struct dm_snapshot *snap); struct dm_dev *dm_snap_cow(struct dm_snapshot *snap); /* diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 10f457ca6af..0590c75b0ab 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -356,7 +356,7 @@ static void dispatch_io(int rw, unsigned int num_regions, BUG_ON(num_regions > DM_IO_MAX_REGIONS); if (sync) - rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); + rw |= REQ_SYNC | REQ_UNPLUG; /* * For multiple regions we need to be careful to rewind @@ -364,7 +364,7 @@ static void dispatch_io(int rw, unsigned int num_regions, */ for (i = 0; i < num_regions; i++) { *dp = old_pages; - if (where[i].count || (rw & (1 << BIO_RW_BARRIER))) + if (where[i].count || (rw & REQ_HARDBARRIER)) do_region(rw, i, where + i, dp, io); } @@ -412,8 +412,8 @@ retry: } set_current_state(TASK_RUNNING); - if (io->eopnotsupp_bits && (rw & (1 << BIO_RW_BARRIER))) { - rw &= ~(1 << BIO_RW_BARRIER); + if (io->eopnotsupp_bits && (rw & REQ_HARDBARRIER)) { + rw &= ~REQ_HARDBARRIER; goto retry; } @@ -479,8 +479,8 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp) * New collapsed (a)synchronous interface. * * If the IO is asynchronous (i.e. it has notify.fn), you must either unplug - * the queue with blk_unplug() some time later or set the BIO_RW_SYNC bit in - * io_req->bi_rw. If you fail to do one of these, the IO will be submitted to + * the queue with blk_unplug() some time later or set REQ_SYNC in +io_req->bi_rw. If you fail to do one of these, the IO will be submitted to * the disk after q->unplug_delay, which defaults to 3ms in blk-settings.c. */ int dm_io(struct dm_io_request *io_req, unsigned num_regions, diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index d7500e1c26f..3e39193e503 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -249,55 +249,66 @@ static void __hash_remove(struct hash_cell *hc) static void dm_hash_remove_all(int keep_open_devices) { - int i, dev_skipped, dev_removed; + int i, dev_skipped; struct hash_cell *hc; - struct list_head *tmp, *n; + struct mapped_device *md; + +retry: + dev_skipped = 0; down_write(&_hash_lock); -retry: - dev_skipped = dev_removed = 0; for (i = 0; i < NUM_BUCKETS; i++) { - list_for_each_safe (tmp, n, _name_buckets + i) { - hc = list_entry(tmp, struct hash_cell, name_list); + list_for_each_entry(hc, _name_buckets + i, name_list) { + md = hc->md; + dm_get(md); - if (keep_open_devices && - dm_lock_for_deletion(hc->md)) { + if (keep_open_devices && dm_lock_for_deletion(md)) { + dm_put(md); dev_skipped++; continue; } + __hash_remove(hc); - dev_removed = 1; - } - } - /* - * Some mapped devices may be using other mapped devices, so if any - * still exist, repeat until we make no further progress. - */ - if (dev_skipped) { - if (dev_removed) - goto retry; + up_write(&_hash_lock); - DMWARN("remove_all left %d open device(s)", dev_skipped); + dm_put(md); + if (likely(keep_open_devices)) + dm_destroy(md); + else + dm_destroy_immediate(md); + + /* + * Some mapped devices may be using other mapped + * devices, so repeat until we make no further + * progress. If a new mapped device is created + * here it will also get removed. + */ + goto retry; + } } up_write(&_hash_lock); + + if (dev_skipped) + DMWARN("remove_all left %d open device(s)", dev_skipped); } -static int dm_hash_rename(uint32_t cookie, uint32_t *flags, const char *old, - const char *new) +static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, + const char *new) { char *new_name, *old_name; struct hash_cell *hc; struct dm_table *table; + struct mapped_device *md; /* * duplicate new. */ new_name = kstrdup(new, GFP_KERNEL); if (!new_name) - return -ENOMEM; + return ERR_PTR(-ENOMEM); down_write(&_hash_lock); @@ -306,24 +317,24 @@ static int dm_hash_rename(uint32_t cookie, uint32_t *flags, const char *old, */ hc = __get_name_cell(new); if (hc) { - DMWARN("asked to rename to an already existing name %s -> %s", - old, new); + DMWARN("asked to rename to an already-existing name %s -> %s", + param->name, new); dm_put(hc->md); up_write(&_hash_lock); kfree(new_name); - return -EBUSY; + return ERR_PTR(-EBUSY); } /* * Is there such a device as 'old' ? */ - hc = __get_name_cell(old); + hc = __get_name_cell(param->name); if (!hc) { - DMWARN("asked to rename a non existent device %s -> %s", - old, new); + DMWARN("asked to rename a non-existent device %s -> %s", + param->name, new); up_write(&_hash_lock); kfree(new_name); - return -ENXIO; + return ERR_PTR(-ENXIO); } /* @@ -345,13 +356,14 @@ static int dm_hash_rename(uint32_t cookie, uint32_t *flags, const char *old, dm_table_put(table); } - if (!dm_kobject_uevent(hc->md, KOBJ_CHANGE, cookie)) - *flags |= DM_UEVENT_GENERATED_FLAG; + if (!dm_kobject_uevent(hc->md, KOBJ_CHANGE, param->event_nr)) + param->flags |= DM_UEVENT_GENERATED_FLAG; - dm_put(hc->md); + md = hc->md; up_write(&_hash_lock); kfree(old_name); - return 0; + + return md; } /*----------------------------------------------------------------- @@ -573,7 +585,7 @@ static struct dm_table *dm_get_live_or_inactive_table(struct mapped_device *md, * Fills in a dm_ioctl structure, ready for sending back to * userland. */ -static int __dev_status(struct mapped_device *md, struct dm_ioctl *param) +static void __dev_status(struct mapped_device *md, struct dm_ioctl *param) { struct gendisk *disk = dm_disk(md); struct dm_table *table; @@ -617,8 +629,6 @@ static int __dev_status(struct mapped_device *md, struct dm_ioctl *param) dm_table_put(table); } } - - return 0; } static int dev_create(struct dm_ioctl *param, size_t param_size) @@ -640,15 +650,17 @@ static int dev_create(struct dm_ioctl *param, size_t param_size) r = dm_hash_insert(param->name, *param->uuid ? param->uuid : NULL, md); if (r) { dm_put(md); + dm_destroy(md); return r; } param->flags &= ~DM_INACTIVE_PRESENT_FLAG; - r = __dev_status(md, param); + __dev_status(md, param); + dm_put(md); - return r; + return 0; } /* @@ -742,6 +754,7 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size) param->flags |= DM_UEVENT_GENERATED_FLAG; dm_put(md); + dm_destroy(md); return 0; } @@ -762,6 +775,7 @@ static int dev_rename(struct dm_ioctl *param, size_t param_size) { int r; char *new_name = (char *) param + param->data_start; + struct mapped_device *md; if (new_name < param->data || invalid_str(new_name, (void *) param + param_size) || @@ -774,10 +788,14 @@ static int dev_rename(struct dm_ioctl *param, size_t param_size) if (r) return r; - param->data_size = 0; + md = dm_hash_rename(param, new_name); + if (IS_ERR(md)) + return PTR_ERR(md); + + __dev_status(md, param); + dm_put(md); - return dm_hash_rename(param->event_nr, ¶m->flags, param->name, - new_name); + return 0; } static int dev_set_geometry(struct dm_ioctl *param, size_t param_size) @@ -818,8 +836,6 @@ static int dev_set_geometry(struct dm_ioctl *param, size_t param_size) geometry.start = indata[3]; r = dm_set_geometry(md, &geometry); - if (!r) - r = __dev_status(md, param); param->data_size = 0; @@ -843,13 +859,17 @@ static int do_suspend(struct dm_ioctl *param) if (param->flags & DM_NOFLUSH_FLAG) suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG; - if (!dm_suspended_md(md)) + if (!dm_suspended_md(md)) { r = dm_suspend(md, suspend_flags); + if (r) + goto out; + } - if (!r) - r = __dev_status(md, param); + __dev_status(md, param); +out: dm_put(md); + return r; } @@ -911,7 +931,7 @@ static int do_resume(struct dm_ioctl *param) dm_table_destroy(old_map); if (!r) - r = __dev_status(md, param); + __dev_status(md, param); dm_put(md); return r; @@ -935,16 +955,16 @@ static int dev_suspend(struct dm_ioctl *param, size_t param_size) */ static int dev_status(struct dm_ioctl *param, size_t param_size) { - int r; struct mapped_device *md; md = find_device(param); if (!md) return -ENXIO; - r = __dev_status(md, param); + __dev_status(md, param); dm_put(md); - return r; + + return 0; } /* @@ -1019,7 +1039,7 @@ static void retrieve_status(struct dm_table *table, */ static int dev_wait(struct dm_ioctl *param, size_t param_size) { - int r; + int r = 0; struct mapped_device *md; struct dm_table *table; @@ -1040,9 +1060,7 @@ static int dev_wait(struct dm_ioctl *param, size_t param_size) * changed to trigger the event, so we may as well tell * him and save an ioctl. */ - r = __dev_status(md, param); - if (r) - goto out; + __dev_status(md, param); table = dm_get_live_or_inactive_table(md, param); if (table) { @@ -1050,8 +1068,9 @@ static int dev_wait(struct dm_ioctl *param, size_t param_size) dm_table_put(table); } - out: +out: dm_put(md); + return r; } @@ -1112,28 +1131,9 @@ static int populate_table(struct dm_table *table, next = spec->next; } - r = dm_table_set_type(table); - if (r) { - DMWARN("unable to set table type"); - return r; - } - return dm_table_complete(table); } -static int table_prealloc_integrity(struct dm_table *t, - struct mapped_device *md) -{ - struct list_head *devices = dm_table_get_devices(t); - struct dm_dev_internal *dd; - - list_for_each_entry(dd, devices, list) - if (bdev_get_integrity(dd->dm_dev.bdev)) - return blk_integrity_register(dm_disk(md), NULL); - - return 0; -} - static int table_load(struct dm_ioctl *param, size_t param_size) { int r; @@ -1155,21 +1155,30 @@ static int table_load(struct dm_ioctl *param, size_t param_size) goto out; } - r = table_prealloc_integrity(t, md); - if (r) { - DMERR("%s: could not register integrity profile.", - dm_device_name(md)); + /* Protect md->type and md->queue against concurrent table loads. */ + dm_lock_md_type(md); + if (dm_get_md_type(md) == DM_TYPE_NONE) + /* Initial table load: acquire type of table. */ + dm_set_md_type(md, dm_table_get_type(t)); + else if (dm_get_md_type(md) != dm_table_get_type(t)) { + DMWARN("can't change device type after initial table load."); dm_table_destroy(t); + dm_unlock_md_type(md); + r = -EINVAL; goto out; } - r = dm_table_alloc_md_mempools(t); + /* setup md->queue to reflect md's type (may block) */ + r = dm_setup_md_queue(md); if (r) { - DMWARN("unable to allocate mempools for this table"); + DMWARN("unable to set up device queue for new table."); dm_table_destroy(t); + dm_unlock_md_type(md); goto out; } + dm_unlock_md_type(md); + /* stage inactive table */ down_write(&_hash_lock); hc = dm_get_mdptr(md); if (!hc || hc->md != md) { @@ -1186,7 +1195,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size) up_write(&_hash_lock); param->flags |= DM_INACTIVE_PRESENT_FLAG; - r = __dev_status(md, param); + __dev_status(md, param); out: dm_put(md); @@ -1196,7 +1205,6 @@ out: static int table_clear(struct dm_ioctl *param, size_t param_size) { - int r; struct hash_cell *hc; struct mapped_device *md; @@ -1216,11 +1224,12 @@ static int table_clear(struct dm_ioctl *param, size_t param_size) param->flags &= ~DM_INACTIVE_PRESENT_FLAG; - r = __dev_status(hc->md, param); + __dev_status(hc->md, param); md = hc->md; up_write(&_hash_lock); dm_put(md); - return r; + + return 0; } /* @@ -1265,7 +1274,6 @@ static void retrieve_deps(struct dm_table *table, static int table_deps(struct dm_ioctl *param, size_t param_size) { - int r = 0; struct mapped_device *md; struct dm_table *table; @@ -1273,9 +1281,7 @@ static int table_deps(struct dm_ioctl *param, size_t param_size) if (!md) return -ENXIO; - r = __dev_status(md, param); - if (r) - goto out; + __dev_status(md, param); table = dm_get_live_or_inactive_table(md, param); if (table) { @@ -1283,9 +1289,9 @@ static int table_deps(struct dm_ioctl *param, size_t param_size) dm_table_put(table); } - out: dm_put(md); - return r; + + return 0; } /* @@ -1294,7 +1300,6 @@ static int table_deps(struct dm_ioctl *param, size_t param_size) */ static int table_status(struct dm_ioctl *param, size_t param_size) { - int r; struct mapped_device *md; struct dm_table *table; @@ -1302,9 +1307,7 @@ static int table_status(struct dm_ioctl *param, size_t param_size) if (!md) return -ENXIO; - r = __dev_status(md, param); - if (r) - goto out; + __dev_status(md, param); table = dm_get_live_or_inactive_table(md, param); if (table) { @@ -1312,9 +1315,9 @@ static int table_status(struct dm_ioctl *param, size_t param_size) dm_table_put(table); } -out: dm_put(md); - return r; + + return 0; } /* @@ -1333,10 +1336,6 @@ static int target_message(struct dm_ioctl *param, size_t param_size) if (!md) return -ENXIO; - r = __dev_status(md, param); - if (r) - goto out; - if (tmsg < (struct dm_target_msg *) param->data || invalid_str(tmsg->message, (void *) param + param_size)) { DMWARN("Invalid target message parameters."); @@ -1593,18 +1592,22 @@ static long dm_compat_ctl_ioctl(struct file *file, uint command, ulong u) #endif static const struct file_operations _ctl_fops = { + .open = nonseekable_open, .unlocked_ioctl = dm_ctl_ioctl, .compat_ioctl = dm_compat_ctl_ioctl, .owner = THIS_MODULE, }; static struct miscdevice _dm_misc = { - .minor = MISC_DYNAMIC_MINOR, + .minor = MAPPER_CTRL_MINOR, .name = DM_NAME, - .nodename = "mapper/control", + .nodename = DM_DIR "/" DM_CONTROL_NODE, .fops = &_ctl_fops }; +MODULE_ALIAS_MISCDEV(MAPPER_CTRL_MINOR); +MODULE_ALIAS("devname:" DM_DIR "/" DM_CONTROL_NODE); + /* * Create misc character device and link to DM_DIR/control. */ diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index addf8347504..d8587bac568 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -345,7 +345,7 @@ static int run_io_job(struct kcopyd_job *job) { int r; struct dm_io_request io_req = { - .bi_rw = job->rw | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG), + .bi_rw = job->rw | REQ_SYNC | REQ_UNPLUG, .mem.type = DM_IO_PAGE_LIST, .mem.ptr.pl = job->pages, .mem.offset = job->offset, diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 9200dbf2391..3921e3bb43c 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -53,6 +53,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv) } ti->num_flush_requests = 1; + ti->num_discard_requests = 1; ti->private = lc; return 0; @@ -73,7 +74,7 @@ static sector_t linear_map_sector(struct dm_target *ti, sector_t bi_sector) { struct linear_c *lc = ti->private; - return lc->start + (bi_sector - ti->begin); + return lc->start + dm_target_offset(ti, bi_sector); } static void linear_map_bio(struct dm_target *ti, struct bio *bio) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 826bce7343b..487ecda90ad 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -706,6 +706,7 @@ static struct priority_group *parse_priority_group(struct arg_set *as, if (as->argc < nr_params) { ti->error = "not enough path parameters"; + r = -EINVAL; goto bad; } @@ -892,6 +893,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc, } ti->num_flush_requests = 1; + ti->num_discard_requests = 1; return 0; @@ -1271,6 +1273,15 @@ static int do_end_io(struct multipath *m, struct request *clone, if (error == -EOPNOTSUPP) return error; + if (clone->cmd_flags & REQ_DISCARD) + /* + * Pass all discard request failures up. + * FIXME: only fail_path if the discard failed due to a + * transport problem. This requires precise understanding + * of the underlying failure (e.g. the SCSI sense). + */ + return error; + if (mpio->pgpath) fail_path(mpio->pgpath); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index ddda531723d..7c081bcbc3c 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -445,7 +445,7 @@ static sector_t map_sector(struct mirror *m, struct bio *bio) { if (unlikely(!bio->bi_size)) return 0; - return m->offset + (bio->bi_sector - m->ms->ti->begin); + return m->offset + dm_target_offset(m->ms->ti, bio->bi_sector); } static void map_bio(struct mirror *m, struct bio *bio) @@ -1211,7 +1211,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, if (error == -EOPNOTSUPP) goto out; - if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD)) + if ((error == -EWOULDBLOCK) && (bio->bi_rw & REQ_RAHEAD)) goto out; if (unlikely(error)) { diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index c097d8a4823..cc2bdb83f9a 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -266,7 +266,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw, */ static chunk_t area_location(struct pstore *ps, chunk_t area) { - return 1 + ((ps->exceptions_per_area + 1) * area); + return NUM_SNAPSHOT_HDR_CHUNKS + ((ps->exceptions_per_area + 1) * area); } /* @@ -780,8 +780,8 @@ static int persistent_commit_merge(struct dm_exception_store *store, * ps->current_area does not get reduced by prepare_merge() until * after commit_merge() has removed the nr_merged previous exceptions. */ - ps->next_free = (area_location(ps, ps->current_area) - 1) + - (ps->current_committed + 1) + NUM_SNAPSHOT_HDR_CHUNKS; + ps->next_free = area_location(ps, ps->current_area) + + ps->current_committed + 1; return 0; } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 54853773510..5974d3094d9 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -148,6 +148,12 @@ struct dm_snapshot { #define RUNNING_MERGE 0 #define SHUTDOWN_MERGE 1 +struct dm_dev *dm_snap_origin(struct dm_snapshot *s) +{ + return s->origin; +} +EXPORT_SYMBOL(dm_snap_origin); + struct dm_dev *dm_snap_cow(struct dm_snapshot *s) { return s->cow; @@ -1065,10 +1071,6 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) origin_mode = FMODE_WRITE; } - origin_path = argv[0]; - argv++; - argc--; - s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) { ti->error = "Cannot allocate snapshot context private " @@ -1077,6 +1079,16 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } + origin_path = argv[0]; + argv++; + argc--; + + r = dm_get_device(ti, origin_path, origin_mode, &s->origin); + if (r) { + ti->error = "Cannot get origin device"; + goto bad_origin; + } + cow_path = argv[0]; argv++; argc--; @@ -1097,12 +1109,6 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) argv += args_used; argc -= args_used; - r = dm_get_device(ti, origin_path, origin_mode, &s->origin); - if (r) { - ti->error = "Cannot get origin device"; - goto bad_origin; - } - s->ti = ti; s->valid = 1; s->active = 0; @@ -1212,15 +1218,15 @@ bad_kcopyd: dm_exception_table_exit(&s->complete, exception_cache); bad_hash_tables: - dm_put_device(ti, s->origin); - -bad_origin: dm_exception_store_destroy(s->store); bad_store: dm_put_device(ti, s->cow); bad_cow: + dm_put_device(ti, s->origin); + +bad_origin: kfree(s); bad: @@ -1314,12 +1320,12 @@ static void snapshot_dtr(struct dm_target *ti) mempool_destroy(s->pending_pool); - dm_put_device(ti, s->origin); - dm_exception_store_destroy(s->store); dm_put_device(ti, s->cow); + dm_put_device(ti, s->origin); + kfree(s); } @@ -1686,7 +1692,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio, chunk_t chunk; if (unlikely(bio_empty_barrier(bio))) { - if (!map_context->flush_request) + if (!map_context->target_request_nr) bio->bi_bdev = s->origin->bdev; else bio->bi_bdev = s->cow->bdev; @@ -1899,8 +1905,14 @@ static int snapshot_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct dm_snapshot *snap = ti->private; + int r; + + r = fn(ti, snap->origin, 0, ti->len, data); + + if (!r) + r = fn(ti, snap->cow, 0, get_dev_size(snap->cow->bdev), data); - return fn(ti, snap->origin, 0, ti->len, data); + return r; } @@ -2159,6 +2171,21 @@ static int origin_status(struct dm_target *ti, status_type_t type, char *result, return 0; } +static int origin_merge(struct dm_target *ti, struct bvec_merge_data *bvm, + struct bio_vec *biovec, int max_size) +{ + struct dm_dev *dev = ti->private; + struct request_queue *q = bdev_get_queue(dev->bdev); + + if (!q->merge_bvec_fn) + return max_size; + + bvm->bi_bdev = dev->bdev; + bvm->bi_sector = bvm->bi_sector; + + return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); +} + static int origin_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { @@ -2176,6 +2203,7 @@ static struct target_type origin_target = { .map = origin_map, .resume = origin_resume, .status = origin_status, + .merge = origin_merge, .iterate_devices = origin_iterate_devices, }; diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index e610725db76..c297f6da91e 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -25,6 +25,8 @@ struct stripe { struct stripe_c { uint32_t stripes; + int stripes_shift; + sector_t stripes_mask; /* The size of this target / num. stripes */ sector_t stripe_width; @@ -162,16 +164,22 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv) /* Set pointer to dm target; used in trigger_event */ sc->ti = ti; - sc->stripes = stripes; sc->stripe_width = width; + + if (stripes & (stripes - 1)) + sc->stripes_shift = -1; + else { + sc->stripes_shift = ffs(stripes) - 1; + sc->stripes_mask = ((sector_t) stripes) - 1; + } + ti->split_io = chunk_size; ti->num_flush_requests = stripes; + ti->num_discard_requests = stripes; + sc->chunk_shift = ffs(chunk_size) - 1; sc->chunk_mask = ((sector_t) chunk_size) - 1; - for (sc->chunk_shift = 0; chunk_size; sc->chunk_shift++) - chunk_size >>= 1; - sc->chunk_shift--; /* * Get the stripe destinations. @@ -207,26 +215,79 @@ static void stripe_dtr(struct dm_target *ti) kfree(sc); } +static void stripe_map_sector(struct stripe_c *sc, sector_t sector, + uint32_t *stripe, sector_t *result) +{ + sector_t offset = dm_target_offset(sc->ti, sector); + sector_t chunk = offset >> sc->chunk_shift; + + if (sc->stripes_shift < 0) + *stripe = sector_div(chunk, sc->stripes); + else { + *stripe = chunk & sc->stripes_mask; + chunk >>= sc->stripes_shift; + } + + *result = (chunk << sc->chunk_shift) | (offset & sc->chunk_mask); +} + +static void stripe_map_range_sector(struct stripe_c *sc, sector_t sector, + uint32_t target_stripe, sector_t *result) +{ + uint32_t stripe; + + stripe_map_sector(sc, sector, &stripe, result); + if (stripe == target_stripe) + return; + *result &= ~sc->chunk_mask; /* round down */ + if (target_stripe < stripe) + *result += sc->chunk_mask + 1; /* next chunk */ +} + +static int stripe_map_discard(struct stripe_c *sc, struct bio *bio, + uint32_t target_stripe) +{ + sector_t begin, end; + + stripe_map_range_sector(sc, bio->bi_sector, target_stripe, &begin); + stripe_map_range_sector(sc, bio->bi_sector + bio_sectors(bio), + target_stripe, &end); + if (begin < end) { + bio->bi_bdev = sc->stripe[target_stripe].dev->bdev; + bio->bi_sector = begin + sc->stripe[target_stripe].physical_start; + bio->bi_size = to_bytes(end - begin); + return DM_MAPIO_REMAPPED; + } else { + /* The range doesn't map to the target stripe */ + bio_endio(bio, 0); + return DM_MAPIO_SUBMITTED; + } +} + static int stripe_map(struct dm_target *ti, struct bio *bio, union map_info *map_context) { - struct stripe_c *sc = (struct stripe_c *) ti->private; - sector_t offset, chunk; + struct stripe_c *sc = ti->private; uint32_t stripe; + unsigned target_request_nr; if (unlikely(bio_empty_barrier(bio))) { - BUG_ON(map_context->flush_request >= sc->stripes); - bio->bi_bdev = sc->stripe[map_context->flush_request].dev->bdev; + target_request_nr = map_context->target_request_nr; + BUG_ON(target_request_nr >= sc->stripes); + bio->bi_bdev = sc->stripe[target_request_nr].dev->bdev; return DM_MAPIO_REMAPPED; } + if (unlikely(bio->bi_rw & REQ_DISCARD)) { + target_request_nr = map_context->target_request_nr; + BUG_ON(target_request_nr >= sc->stripes); + return stripe_map_discard(sc, bio, target_request_nr); + } - offset = bio->bi_sector - ti->begin; - chunk = offset >> sc->chunk_shift; - stripe = sector_div(chunk, sc->stripes); + stripe_map_sector(sc, bio->bi_sector, &stripe, &bio->bi_sector); + bio->bi_sector += sc->stripe[stripe].physical_start; bio->bi_bdev = sc->stripe[stripe].dev->bdev; - bio->bi_sector = sc->stripe[stripe].physical_start + - (chunk << sc->chunk_shift) + (offset & sc->chunk_mask); + return DM_MAPIO_REMAPPED; } @@ -284,7 +345,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio, if (!error) return 0; /* I/O complete */ - if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD)) + if ((error == -EWOULDBLOCK) && (bio->bi_rw & REQ_RAHEAD)) return error; if (error == -EOPNOTSUPP) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 9924ea23032..f9fc07d7a4b 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -54,6 +54,8 @@ struct dm_table { sector_t *highs; struct dm_target *targets; + unsigned discards_supported:1; + /* * Indicates the rw permissions for the new logical * device. This should be a combination of FMODE_READ @@ -203,6 +205,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode, INIT_LIST_HEAD(&t->devices); atomic_set(&t->holders, 0); + t->discards_supported = 1; if (!num_targets) num_targets = KEYS_PER_NODE; @@ -245,7 +248,7 @@ void dm_table_destroy(struct dm_table *t) msleep(1); smp_mb(); - /* free the indexes (see dm_table_complete) */ + /* free the indexes */ if (t->depth >= 2) vfree(t->index[t->depth - 2]); @@ -770,6 +773,9 @@ int dm_table_add_target(struct dm_table *t, const char *type, t->highs[t->num_targets++] = tgt->begin + tgt->len - 1; + if (!tgt->num_discard_requests) + t->discards_supported = 0; + return 0; bad: @@ -778,7 +784,7 @@ int dm_table_add_target(struct dm_table *t, const char *type, return r; } -int dm_table_set_type(struct dm_table *t) +static int dm_table_set_type(struct dm_table *t) { unsigned i; unsigned bio_based = 0, request_based = 0; @@ -900,7 +906,7 @@ static int setup_indexes(struct dm_table *t) /* * Builds the btree to index the map. */ -int dm_table_complete(struct dm_table *t) +static int dm_table_build_index(struct dm_table *t) { int r = 0; unsigned int leaf_nodes; @@ -919,6 +925,55 @@ int dm_table_complete(struct dm_table *t) return r; } +/* + * Register the mapped device for blk_integrity support if + * the underlying devices support it. + */ +static int dm_table_prealloc_integrity(struct dm_table *t, struct mapped_device *md) +{ + struct list_head *devices = dm_table_get_devices(t); + struct dm_dev_internal *dd; + + list_for_each_entry(dd, devices, list) + if (bdev_get_integrity(dd->dm_dev.bdev)) + return blk_integrity_register(dm_disk(md), NULL); + + return 0; +} + +/* + * Prepares the table for use by building the indices, + * setting the type, and allocating mempools. + */ +int dm_table_complete(struct dm_table *t) +{ + int r; + + r = dm_table_set_type(t); + if (r) { + DMERR("unable to set table type"); + return r; + } + + r = dm_table_build_index(t); + if (r) { + DMERR("unable to build btrees"); + return r; + } + + r = dm_table_prealloc_integrity(t, t->md); + if (r) { + DMERR("could not register integrity profile."); + return r; + } + + r = dm_table_alloc_md_mempools(t); + if (r) + DMERR("unable to allocate mempools"); + + return r; +} + static DEFINE_MUTEX(_event_lock); void dm_table_event_callback(struct dm_table *t, void (*fn)(void *), void *context) @@ -1086,6 +1141,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, else queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, q); + if (!dm_table_supports_discards(t)) + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); + else + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); + dm_table_set_integrity(t); /* @@ -1232,6 +1292,39 @@ struct mapped_device *dm_table_get_md(struct dm_table *t) return t->md; } +static int device_discard_capable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + + return q && blk_queue_discard(q); +} + +bool dm_table_supports_discards(struct dm_table *t) +{ + struct dm_target *ti; + unsigned i = 0; + + if (!t->discards_supported) + return 0; + + /* + * Ensure that at least one underlying device supports discards. + * t->devices includes internal dm devices such as mirror logs + * so we need to use iterate_devices here, which targets + * supporting discard must provide. + */ + while (i < dm_table_get_num_targets(t)) { + ti = dm_table_get_target(t, i++); + + if (ti->type->iterate_devices && + ti->type->iterate_devices(ti, device_discard_capable, NULL)) + return 1; + } + + return 0; +} + EXPORT_SYMBOL(dm_vcalloc); EXPORT_SYMBOL(dm_get_device); EXPORT_SYMBOL(dm_put_device); diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index 11dea11dc0b..8da366cf381 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -113,6 +113,11 @@ void dm_unregister_target(struct target_type *tt) */ static int io_err_ctr(struct dm_target *tt, unsigned int argc, char **args) { + /* + * Return error for discards instead of -EOPNOTSUPP + */ + tt->num_discard_requests = 1; + return 0; } diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c index bbc97030c0c..cc2b3cb8194 100644 --- a/drivers/md/dm-zero.c +++ b/drivers/md/dm-zero.c @@ -22,6 +22,11 @@ static int zero_ctr(struct dm_target *ti, unsigned int argc, char **argv) return -EINVAL; } + /* + * Silently drop discards, avoiding -EOPNOTSUPP. + */ + ti->num_discard_requests = 1; + return 0; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index d21e1284604..ac384b2a6a3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -15,10 +15,12 @@ #include <linux/blkpg.h> #include <linux/bio.h> #include <linux/buffer_head.h> +#include <linux/smp_lock.h> #include <linux/mempool.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/hdreg.h> +#include <linux/delay.h> #include <trace/events/block.h> @@ -123,6 +125,10 @@ struct mapped_device { unsigned long flags; struct request_queue *queue; + unsigned type; + /* Protect queue and type against concurrent access. */ + struct mutex type_lock; + struct gendisk *disk; char name[16]; @@ -338,6 +344,7 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode) { struct mapped_device *md; + lock_kernel(); spin_lock(&_minor_lock); md = bdev->bd_disk->private_data; @@ -355,6 +362,7 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode) out: spin_unlock(&_minor_lock); + unlock_kernel(); return md ? 0 : -ENXIO; } @@ -362,8 +370,12 @@ out: static int dm_blk_close(struct gendisk *disk, fmode_t mode) { struct mapped_device *md = disk->private_data; + + lock_kernel(); atomic_dec(&md->open_count); dm_put(md); + unlock_kernel(); + return 0; } @@ -614,7 +626,7 @@ static void dec_pending(struct dm_io *io, int error) */ spin_lock_irqsave(&md->deferred_lock, flags); if (__noflush_suspending(md)) { - if (!bio_rw_flagged(io->bio, BIO_RW_BARRIER)) + if (!(io->bio->bi_rw & REQ_HARDBARRIER)) bio_list_add_head(&md->deferred, io->bio); } else @@ -626,13 +638,19 @@ static void dec_pending(struct dm_io *io, int error) io_error = io->error; bio = io->bio; - if (bio_rw_flagged(bio, BIO_RW_BARRIER)) { + if (bio->bi_rw & REQ_HARDBARRIER) { /* * There can be just one barrier request so we use * a per-device variable for error reporting. * Note that you can't touch the bio after end_io_acct + * + * We ignore -EOPNOTSUPP for empty flush reported by + * underlying devices. We assume that if the device + * doesn't support empty barriers, it doesn't need + * cache flushing commands. */ - if (!md->barrier_error && io_error != -EOPNOTSUPP) + if (!md->barrier_error && + !(bio_empty_barrier(bio) && io_error == -EOPNOTSUPP)) md->barrier_error = io_error; end_io_acct(io); free_io(md, io); @@ -792,12 +810,12 @@ static void dm_end_request(struct request *clone, int error) { int rw = rq_data_dir(clone); int run_queue = 1; - bool is_barrier = blk_barrier_rq(clone); + bool is_barrier = clone->cmd_flags & REQ_HARDBARRIER; struct dm_rq_target_io *tio = clone->end_io_data; struct mapped_device *md = tio->md; struct request *rq = tio->orig; - if (blk_pc_request(rq) && !is_barrier) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !is_barrier) { rq->errors = clone->errors; rq->resid_len = clone->resid_len; @@ -844,7 +862,7 @@ void dm_requeue_unmapped_request(struct request *clone) struct request_queue *q = rq->q; unsigned long flags; - if (unlikely(blk_barrier_rq(clone))) { + if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) { /* * Barrier clones share an original request. * Leave it to dm_end_request(), which handles this special @@ -943,7 +961,7 @@ static void dm_complete_request(struct request *clone, int error) struct dm_rq_target_io *tio = clone->end_io_data; struct request *rq = tio->orig; - if (unlikely(blk_barrier_rq(clone))) { + if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) { /* * Barrier clones share an original request. So can't use * softirq_done with the original. @@ -972,7 +990,7 @@ void dm_kill_unmapped_request(struct request *clone, int error) struct dm_rq_target_io *tio = clone->end_io_data; struct request *rq = tio->orig; - if (unlikely(blk_barrier_rq(clone))) { + if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) { /* * Barrier clones share an original request. * Leave it to dm_end_request(), which handles this special @@ -1012,17 +1030,27 @@ static void end_clone_request(struct request *clone, int error) dm_complete_request(clone, error); } -static sector_t max_io_len(struct mapped_device *md, - sector_t sector, struct dm_target *ti) +/* + * Return maximum size of I/O possible at the supplied sector up to the current + * target boundary. + */ +static sector_t max_io_len_target_boundary(sector_t sector, struct dm_target *ti) { - sector_t offset = sector - ti->begin; - sector_t len = ti->len - offset; + sector_t target_offset = dm_target_offset(ti, sector); + + return ti->len - target_offset; +} + +static sector_t max_io_len(sector_t sector, struct dm_target *ti) +{ + sector_t len = max_io_len_target_boundary(sector, ti); /* * Does the target need to split even further ? */ if (ti->split_io) { sector_t boundary; + sector_t offset = dm_target_offset(ti, sector); boundary = ((offset + ti->split_io) & ~(ti->split_io - 1)) - offset; if (len > boundary) @@ -1106,7 +1134,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector, clone->bi_sector = sector; clone->bi_bdev = bio->bi_bdev; - clone->bi_rw = bio->bi_rw & ~(1 << BIO_RW_BARRIER); + clone->bi_rw = bio->bi_rw & ~REQ_HARDBARRIER; clone->bi_vcnt = 1; clone->bi_size = to_bytes(len); clone->bi_io_vec->bv_offset = offset; @@ -1133,7 +1161,7 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector, clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs); __bio_clone(clone, bio); - clone->bi_rw &= ~(1 << BIO_RW_BARRIER); + clone->bi_rw &= ~REQ_HARDBARRIER; clone->bi_destructor = dm_bio_destructor; clone->bi_sector = sector; clone->bi_idx = idx; @@ -1164,36 +1192,96 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci, return tio; } -static void __flush_target(struct clone_info *ci, struct dm_target *ti, - unsigned flush_nr) +static void __issue_target_request(struct clone_info *ci, struct dm_target *ti, + unsigned request_nr, sector_t len) { struct dm_target_io *tio = alloc_tio(ci, ti); struct bio *clone; - tio->info.flush_request = flush_nr; + tio->info.target_request_nr = request_nr; - clone = bio_alloc_bioset(GFP_NOIO, 0, ci->md->bs); + /* + * Discard requests require the bio's inline iovecs be initialized. + * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush + * and discard, so no need for concern about wasted bvec allocations. + */ + clone = bio_alloc_bioset(GFP_NOIO, ci->bio->bi_max_vecs, ci->md->bs); __bio_clone(clone, ci->bio); clone->bi_destructor = dm_bio_destructor; + if (len) { + clone->bi_sector = ci->sector; + clone->bi_size = to_bytes(len); + } __map_bio(ti, clone, tio); } +static void __issue_target_requests(struct clone_info *ci, struct dm_target *ti, + unsigned num_requests, sector_t len) +{ + unsigned request_nr; + + for (request_nr = 0; request_nr < num_requests; request_nr++) + __issue_target_request(ci, ti, request_nr, len); +} + static int __clone_and_map_empty_barrier(struct clone_info *ci) { - unsigned target_nr = 0, flush_nr; + unsigned target_nr = 0; struct dm_target *ti; while ((ti = dm_table_get_target(ci->map, target_nr++))) - for (flush_nr = 0; flush_nr < ti->num_flush_requests; - flush_nr++) - __flush_target(ci, ti, flush_nr); + __issue_target_requests(ci, ti, ti->num_flush_requests, 0); ci->sector_count = 0; return 0; } +/* + * Perform all io with a single clone. + */ +static void __clone_and_map_simple(struct clone_info *ci, struct dm_target *ti) +{ + struct bio *clone, *bio = ci->bio; + struct dm_target_io *tio; + + tio = alloc_tio(ci, ti); + clone = clone_bio(bio, ci->sector, ci->idx, + bio->bi_vcnt - ci->idx, ci->sector_count, + ci->md->bs); + __map_bio(ti, clone, tio); + ci->sector_count = 0; +} + +static int __clone_and_map_discard(struct clone_info *ci) +{ + struct dm_target *ti; + sector_t len; + + do { + ti = dm_table_find_target(ci->map, ci->sector); + if (!dm_target_is_valid(ti)) + return -EIO; + + /* + * Even though the device advertised discard support, + * reconfiguration might have changed that since the + * check was performed. + */ + if (!ti->num_discard_requests) + return -EOPNOTSUPP; + + len = min(ci->sector_count, max_io_len_target_boundary(ci->sector, ti)); + + __issue_target_requests(ci, ti, ti->num_discard_requests, len); + + ci->sector += len; + } while (ci->sector_count -= len); + + return 0; +} + static int __clone_and_map(struct clone_info *ci) { struct bio *clone, *bio = ci->bio; @@ -1204,27 +1292,21 @@ static int __clone_and_map(struct clone_info *ci) if (unlikely(bio_empty_barrier(bio))) return __clone_and_map_empty_barrier(ci); + if (unlikely(bio->bi_rw & REQ_DISCARD)) + return __clone_and_map_discard(ci); + ti = dm_table_find_target(ci->map, ci->sector); if (!dm_target_is_valid(ti)) return -EIO; - max = max_io_len(ci->md, ci->sector, ti); - - /* - * Allocate a target io object. - */ - tio = alloc_tio(ci, ti); + max = max_io_len(ci->sector, ti); if (ci->sector_count <= max) { /* * Optimise for the simple case where we can do all of * the remaining io with a single clone. */ - clone = clone_bio(bio, ci->sector, ci->idx, - bio->bi_vcnt - ci->idx, ci->sector_count, - ci->md->bs); - __map_bio(ti, clone, tio); - ci->sector_count = 0; + __clone_and_map_simple(ci, ti); } else if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) { /* @@ -1245,6 +1327,7 @@ static int __clone_and_map(struct clone_info *ci) len += bv_len; } + tio = alloc_tio(ci, ti); clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len, ci->md->bs); __map_bio(ti, clone, tio); @@ -1267,13 +1350,12 @@ static int __clone_and_map(struct clone_info *ci) if (!dm_target_is_valid(ti)) return -EIO; - max = max_io_len(ci->md, ci->sector, ti); - - tio = alloc_tio(ci, ti); + max = max_io_len(ci->sector, ti); } len = min(remaining, max); + tio = alloc_tio(ci, ti); clone = split_bvec(bio, ci->sector, ci->idx, bv->bv_offset + offset, len, ci->md->bs); @@ -1301,7 +1383,7 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio) ci.map = dm_get_live_table(md); if (unlikely(!ci.map)) { - if (!bio_rw_flagged(bio, BIO_RW_BARRIER)) + if (!(bio->bi_rw & REQ_HARDBARRIER)) bio_io_error(bio); else if (!md->barrier_error) @@ -1355,7 +1437,7 @@ static int dm_merge_bvec(struct request_queue *q, /* * Find maximum amount of I/O that won't need splitting */ - max_sectors = min(max_io_len(md, bvm->bi_sector, ti), + max_sectors = min(max_io_len(bvm->bi_sector, ti), (sector_t) BIO_MAX_SECTORS); max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size; if (max_size < 0) @@ -1414,7 +1496,7 @@ static int _dm_request(struct request_queue *q, struct bio *bio) * we have to queue this io for later. */ if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) || - unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + unlikely(bio->bi_rw & REQ_HARDBARRIER)) { up_read(&md->io_lock); if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) && @@ -1455,20 +1537,9 @@ static int dm_request(struct request_queue *q, struct bio *bio) return _dm_request(q, bio); } -/* - * Mark this request as flush request, so that dm_request_fn() can - * recognize. - */ -static void dm_rq_prepare_flush(struct request_queue *q, struct request *rq) -{ - rq->cmd_type = REQ_TYPE_LINUX_BLOCK; - rq->cmd[0] = REQ_LB_OP_FLUSH; -} - static bool dm_rq_is_flush_request(struct request *rq) { - if (rq->cmd_type == REQ_TYPE_LINUX_BLOCK && - rq->cmd[0] == REQ_LB_OP_FLUSH) + if (rq->cmd_flags & REQ_FLUSH) return true; else return false; @@ -1849,6 +1920,28 @@ static const struct block_device_operations dm_blk_dops; static void dm_wq_work(struct work_struct *work); static void dm_rq_barrier_work(struct work_struct *work); +static void dm_init_md_queue(struct mapped_device *md) +{ + /* + * Request-based dm devices cannot be stacked on top of bio-based dm + * devices. The type of this dm device has not been decided yet. + * The type is decided at the first table loading time. + * To prevent problematic device stacking, clear the queue flag + * for request stacking support until then. + * + * This queue is new, so no concurrency on the queue_flags. + */ + queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, md->queue); + + md->queue->queuedata = md; + md->queue->backing_dev_info.congested_fn = dm_any_congested; + md->queue->backing_dev_info.congested_data = md; + blk_queue_make_request(md->queue, dm_request); + blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY); + md->queue->unplug_fn = dm_unplug_all; + blk_queue_merge_bvec(md->queue, dm_merge_bvec); +} + /* * Allocate and initialise a blank device with a given minor. */ @@ -1874,8 +1967,10 @@ static struct mapped_device *alloc_dev(int minor) if (r < 0) goto bad_minor; + md->type = DM_TYPE_NONE; init_rwsem(&md->io_lock); mutex_init(&md->suspend_lock); + mutex_init(&md->type_lock); spin_lock_init(&md->deferred_lock); spin_lock_init(&md->barrier_error_lock); rwlock_init(&md->map_lock); @@ -1886,34 +1981,11 @@ static struct mapped_device *alloc_dev(int minor) INIT_LIST_HEAD(&md->uevent_list); spin_lock_init(&md->uevent_lock); - md->queue = blk_init_queue(dm_request_fn, NULL); + md->queue = blk_alloc_queue(GFP_KERNEL); if (!md->queue) goto bad_queue; - /* - * Request-based dm devices cannot be stacked on top of bio-based dm - * devices. The type of this dm device has not been decided yet, - * although we initialized the queue using blk_init_queue(). - * The type is decided at the first table loading time. - * To prevent problematic device stacking, clear the queue flag - * for request stacking support until then. - * - * This queue is new, so no concurrency on the queue_flags. - */ - queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, md->queue); - md->saved_make_request_fn = md->queue->make_request_fn; - md->queue->queuedata = md; - md->queue->backing_dev_info.congested_fn = dm_any_congested; - md->queue->backing_dev_info.congested_data = md; - blk_queue_make_request(md->queue, dm_request); - blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY); - md->queue->unplug_fn = dm_unplug_all; - blk_queue_merge_bvec(md->queue, dm_merge_bvec); - blk_queue_softirq_done(md->queue, dm_softirq_done); - blk_queue_prep_rq(md->queue, dm_prep_fn); - blk_queue_lld_busy(md->queue, dm_lld_busy); - blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH, - dm_rq_prepare_flush); + dm_init_md_queue(md); md->disk = alloc_disk(1); if (!md->disk) @@ -2128,6 +2200,72 @@ int dm_create(int minor, struct mapped_device **result) return 0; } +/* + * Functions to manage md->type. + * All are required to hold md->type_lock. + */ +void dm_lock_md_type(struct mapped_device *md) +{ + mutex_lock(&md->type_lock); +} + +void dm_unlock_md_type(struct mapped_device *md) +{ + mutex_unlock(&md->type_lock); +} + +void dm_set_md_type(struct mapped_device *md, unsigned type) +{ + md->type = type; +} + +unsigned dm_get_md_type(struct mapped_device *md) +{ + return md->type; +} + +/* + * Fully initialize a request-based queue (->elevator, ->request_fn, etc). + */ +static int dm_init_request_based_queue(struct mapped_device *md) +{ + struct request_queue *q = NULL; + + if (md->queue->elevator) + return 1; + + /* Fully initialize the queue */ + q = blk_init_allocated_queue(md->queue, dm_request_fn, NULL); + if (!q) + return 0; + + md->queue = q; + md->saved_make_request_fn = md->queue->make_request_fn; + dm_init_md_queue(md); + blk_queue_softirq_done(md->queue, dm_softirq_done); + blk_queue_prep_rq(md->queue, dm_prep_fn); + blk_queue_lld_busy(md->queue, dm_lld_busy); + blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH); + + elv_register_queue(md->queue); + + return 1; +} + +/* + * Setup the DM device's queue based on md's type + */ +int dm_setup_md_queue(struct mapped_device *md) +{ + if ((dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) && + !dm_init_request_based_queue(md)) { + DMWARN("Cannot initialize queue for request-based mapped device"); + return -EINVAL; + } + + return 0; +} + static struct mapped_device *dm_find_md(dev_t dev) { struct mapped_device *md; @@ -2141,6 +2279,7 @@ static struct mapped_device *dm_find_md(dev_t dev) md = idr_find(&_minor_idr, minor); if (md && (md == MINOR_ALLOCED || (MINOR(disk_devt(dm_disk(md))) != minor) || + dm_deleting_md(md) || test_bit(DMF_FREEING, &md->flags))) { md = NULL; goto out; @@ -2175,6 +2314,7 @@ void dm_set_mdptr(struct mapped_device *md, void *ptr) void dm_get(struct mapped_device *md) { atomic_inc(&md->holders); + BUG_ON(test_bit(DMF_FREEING, &md->flags)); } const char *dm_device_name(struct mapped_device *md) @@ -2183,27 +2323,55 @@ const char *dm_device_name(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_device_name); -void dm_put(struct mapped_device *md) +static void __dm_destroy(struct mapped_device *md, bool wait) { struct dm_table *map; - BUG_ON(test_bit(DMF_FREEING, &md->flags)); + might_sleep(); - if (atomic_dec_and_lock(&md->holders, &_minor_lock)) { - map = dm_get_live_table(md); - idr_replace(&_minor_idr, MINOR_ALLOCED, - MINOR(disk_devt(dm_disk(md)))); - set_bit(DMF_FREEING, &md->flags); - spin_unlock(&_minor_lock); - if (!dm_suspended_md(md)) { - dm_table_presuspend_targets(map); - dm_table_postsuspend_targets(map); - } - dm_sysfs_exit(md); - dm_table_put(map); - dm_table_destroy(__unbind(md)); - free_dev(md); + spin_lock(&_minor_lock); + map = dm_get_live_table(md); + idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md)))); + set_bit(DMF_FREEING, &md->flags); + spin_unlock(&_minor_lock); + + if (!dm_suspended_md(md)) { + dm_table_presuspend_targets(map); + dm_table_postsuspend_targets(map); } + + /* + * Rare, but there may be I/O requests still going to complete, + * for example. Wait for all references to disappear. + * No one should increment the reference count of the mapped_device, + * after the mapped_device state becomes DMF_FREEING. + */ + if (wait) + while (atomic_read(&md->holders)) + msleep(1); + else if (atomic_read(&md->holders)) + DMWARN("%s: Forcibly removing mapped_device still in use! (%d users)", + dm_device_name(md), atomic_read(&md->holders)); + + dm_sysfs_exit(md); + dm_table_put(map); + dm_table_destroy(__unbind(md)); + free_dev(md); +} + +void dm_destroy(struct mapped_device *md) +{ + __dm_destroy(md, true); +} + +void dm_destroy_immediate(struct mapped_device *md) +{ + __dm_destroy(md, false); +} + +void dm_put(struct mapped_device *md) +{ + atomic_dec(&md->holders); } EXPORT_SYMBOL_GPL(dm_put); @@ -2258,7 +2426,12 @@ static void process_barrier(struct mapped_device *md, struct bio *bio) if (!bio_empty_barrier(bio)) { __split_and_process_bio(md, bio); - dm_flush(md); + /* + * If the request isn't supported, don't waste time with + * the second flush. + */ + if (md->barrier_error != -EOPNOTSUPP) + dm_flush(md); } if (md->barrier_error != DM_ENDIO_REQUEUE) @@ -2296,7 +2469,7 @@ static void dm_wq_work(struct work_struct *work) if (dm_request_based(md)) generic_make_request(c); else { - if (bio_rw_flagged(c, BIO_RW_BARRIER)) + if (c->bi_rw & REQ_HARDBARRIER) process_barrier(md, c); else __split_and_process_bio(md, c); @@ -2315,11 +2488,11 @@ static void dm_queue_flush(struct mapped_device *md) queue_work(md->wq, &md->work); } -static void dm_rq_set_flush_nr(struct request *clone, unsigned flush_nr) +static void dm_rq_set_target_request_nr(struct request *clone, unsigned request_nr) { struct dm_rq_target_io *tio = clone->end_io_data; - tio->info.flush_request = flush_nr; + tio->info.target_request_nr = request_nr; } /* Issue barrier requests to targets and wait for their completion. */ @@ -2337,7 +2510,7 @@ static int dm_rq_barrier(struct mapped_device *md) ti = dm_table_get_target(map, i); for (j = 0; j < ti->num_flush_requests; j++) { clone = clone_rq(md->flush_request, md, GFP_NOIO); - dm_rq_set_flush_nr(clone, j); + dm_rq_set_target_request_nr(clone, j); atomic_inc(&md->pending[rq_data_dir(clone)]); map_request(ti, clone, md); } @@ -2403,13 +2576,6 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) goto out; } - /* cannot change the device type, once a table is bound */ - if (md->map && - (dm_table_get_type(md->map) != dm_table_get_type(table))) { - DMWARN("can't change the device type after a table is bound"); - goto out; - } - map = __bind(md, table, &limits); out: diff --git a/drivers/md/dm.h b/drivers/md/dm.h index bad1724d486..0c2dd5f4af7 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -59,13 +59,20 @@ void dm_table_postsuspend_targets(struct dm_table *t); int dm_table_resume_targets(struct dm_table *t); int dm_table_any_congested(struct dm_table *t, int bdi_bits); int dm_table_any_busy_target(struct dm_table *t); -int dm_table_set_type(struct dm_table *t); unsigned dm_table_get_type(struct dm_table *t); bool dm_table_request_based(struct dm_table *t); +bool dm_table_supports_discards(struct dm_table *t); int dm_table_alloc_md_mempools(struct dm_table *t); void dm_table_free_md_mempools(struct dm_table *t); struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t); +void dm_lock_md_type(struct mapped_device *md); +void dm_unlock_md_type(struct mapped_device *md); +void dm_set_md_type(struct mapped_device *md, unsigned type); +unsigned dm_get_md_type(struct mapped_device *md); + +int dm_setup_md_queue(struct mapped_device *md); + /* * To check the return value from dm_table_find_target(). */ @@ -122,6 +129,11 @@ void dm_linear_exit(void); int dm_stripe_init(void); void dm_stripe_exit(void); +/* + * mapped_device operations + */ +void dm_destroy(struct mapped_device *md); +void dm_destroy_immediate(struct mapped_device *md); int dm_open_count(struct mapped_device *md); int dm_lock_for_deletion(struct mapped_device *md); diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 7e0e057db9a..ba19060bcf3 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -294,7 +294,7 @@ static int linear_make_request (mddev_t *mddev, struct bio *bio) dev_info_t *tmp_dev; sector_t start_sector; - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { md_barrier_request(mddev, bio); return 0; } diff --git a/drivers/md/md.c b/drivers/md/md.c index cb20d0b0555..43cf9cc9c1d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -36,6 +36,7 @@ #include <linux/blkdev.h> #include <linux/sysctl.h> #include <linux/seq_file.h> +#include <linux/smp_lock.h> #include <linux/buffer_head.h> /* for invalidate_bdev */ #include <linux/poll.h> #include <linux/ctype.h> @@ -261,7 +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; @@ -269,13 +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) { @@ -353,7 +356,7 @@ static void md_submit_barrier(struct work_struct *ws) /* an empty barrier - all done */ bio_endio(bio, 0); else { - bio->bi_rw &= ~(1<<BIO_RW_BARRIER); + bio->bi_rw &= ~REQ_HARDBARRIER; if (mddev->pers->make_request(mddev, bio)) generic_make_request(bio); mddev->barrier = POST_REQUEST_BARRIER; @@ -384,6 +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); @@ -416,7 +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); @@ -436,6 +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) { @@ -532,25 +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); @@ -675,11 +730,11 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, * if zero is reached. * If an error occurred, call md_error * - * As we might need to resubmit the request if BIO_RW_BARRIER + * As we might need to resubmit the request if REQ_HARDBARRIER * causes ENOTSUPP, we allocate a spare bio... */ struct bio *bio = bio_alloc(GFP_NOIO, 1); - int rw = (1<<BIO_RW) | (1<<BIO_RW_SYNCIO) | (1<<BIO_RW_UNPLUG); + int rw = REQ_WRITE | REQ_SYNC | REQ_UNPLUG; bio->bi_bdev = rdev->bdev; bio->bi_sector = sector; @@ -691,7 +746,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, atomic_inc(&mddev->pending_writes); if (!test_bit(BarriersNotsupp, &rdev->flags)) { struct bio *rbio; - rw |= (1<<BIO_RW_BARRIER); + rw |= REQ_HARDBARRIER; rbio = bio_clone(bio, GFP_NOIO); rbio->bi_private = bio; rbio->bi_end_io = super_written_barrier; @@ -736,7 +791,7 @@ int sync_page_io(struct block_device *bdev, sector_t sector, int size, struct completion event; int ret; - rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); + rw |= REQ_SYNC | REQ_UNPLUG; bio->bi_bdev = bdev; bio->bi_sector = sector; @@ -1811,11 +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); @@ -2083,16 +2136,6 @@ static void sync_sbs(mddev_t * mddev, int nospares) * with the rest of the array) */ mdk_rdev_t *rdev; - - /* First make sure individual recovery_offsets are correct */ - list_for_each_entry(rdev, &mddev->disks, same_set) { - if (rdev->raid_disk >= 0 && - mddev->delta_disks >= 0 && - !test_bit(In_sync, &rdev->flags) && - mddev->curr_resync_completed > rdev->recovery_offset) - rdev->recovery_offset = mddev->curr_resync_completed; - - } list_for_each_entry(rdev, &mddev->disks, same_set) { if (rdev->sb_events == mddev->events || (nospares && @@ -2114,13 +2157,27 @@ static void md_update_sb(mddev_t * mddev, int force_change) int sync_req; int nospares = 0; - mddev->utime = get_seconds(); - if (mddev->external) - return; repeat: + /* First make sure individual recovery_offsets are correct */ + list_for_each_entry(rdev, &mddev->disks, same_set) { + if (rdev->raid_disk >= 0 && + mddev->delta_disks >= 0 && + !test_bit(In_sync, &rdev->flags) && + mddev->curr_resync_completed > rdev->recovery_offset) + rdev->recovery_offset = mddev->curr_resync_completed; + + } + if (!mddev->persistent) { + clear_bit(MD_CHANGE_CLEAN, &mddev->flags); + clear_bit(MD_CHANGE_DEVS, &mddev->flags); + wake_up(&mddev->sb_wait); + return; + } + spin_lock_irq(&mddev->write_lock); - set_bit(MD_CHANGE_PENDING, &mddev->flags); + mddev->utime = get_seconds(); + if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags)) force_change = 1; if (test_and_clear_bit(MD_CHANGE_CLEAN, &mddev->flags)) @@ -2168,19 +2225,6 @@ repeat: MD_BUG(); mddev->events --; } - - /* - * do not write anything to disk if using - * nonpersistent superblocks - */ - if (!mddev->persistent) { - if (!mddev->external) - clear_bit(MD_CHANGE_PENDING, &mddev->flags); - - spin_unlock_irq(&mddev->write_lock); - wake_up(&mddev->sb_wait); - return; - } sync_sbs(mddev, nospares); spin_unlock_irq(&mddev->write_lock); @@ -2334,8 +2378,8 @@ 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 = @@ -2430,14 +2474,10 @@ 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) @@ -2447,7 +2487,7 @@ 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; } @@ -2695,6 +2735,24 @@ 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 * @@ -2718,6 +2776,7 @@ 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; @@ -2727,18 +2786,6 @@ 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 @@ -2767,9 +2814,6 @@ 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: @@ -2960,7 +3004,9 @@ 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) { @@ -3324,7 +3370,7 @@ array_state_show(mddev_t *mddev, char *page) case 0: if (mddev->in_sync) st = clean; - else if (test_bit(MD_CHANGE_CLEAN, &mddev->flags)) + else if (test_bit(MD_CHANGE_PENDING, &mddev->flags)) st = write_pending; else if (mddev->safemode) st = active_idle; @@ -3405,9 +3451,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len) mddev->in_sync = 1; if (mddev->safemode == 1) mddev->safemode = 0; - if (mddev->persistent) - set_bit(MD_CHANGE_CLEAN, - &mddev->flags); + set_bit(MD_CHANGE_CLEAN, &mddev->flags); } err = 0; } else @@ -3419,8 +3463,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len) case active: if (mddev->pers) { restart_array(mddev); - if (mddev->external) - clear_bit(MD_CHANGE_CLEAN, &mddev->flags); + clear_bit(MD_CHANGE_PENDING, &mddev->flags); wake_up(&mddev->sb_wait); err = 0; } else { @@ -3437,7 +3480,7 @@ 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; } } @@ -3735,7 +3778,7 @@ 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; } @@ -4281,13 +4324,14 @@ 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; @@ -4325,14 +4369,14 @@ 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; @@ -4344,13 +4388,9 @@ 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) @@ -4397,7 +4437,7 @@ 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); @@ -4496,11 +4536,12 @@ 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; @@ -4518,8 +4559,7 @@ 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); @@ -4531,12 +4571,12 @@ 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) { @@ -4545,7 +4585,11 @@ 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); @@ -4573,7 +4617,7 @@ 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; } @@ -4644,9 +4688,10 @@ 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); @@ -4666,11 +4711,10 @@ 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; @@ -4678,6 +4722,7 @@ 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) { @@ -4697,7 +4742,7 @@ 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: @@ -4711,26 +4756,29 @@ 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) { @@ -4740,21 +4788,17 @@ 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); @@ -4771,13 +4815,11 @@ 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 @@ -5138,7 +5180,7 @@ 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) @@ -5331,8 +5373,11 @@ 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 */ @@ -5581,6 +5626,8 @@ 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); @@ -5813,7 +5860,7 @@ 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 { @@ -5902,6 +5949,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) mddev_t *mddev = mddev_find(bdev->bd_dev); int err; + lock_kernel(); if (mddev->gendisk != bdev->bd_disk) { /* we are racing with mddev_put which is discarding this * bd_disk. @@ -5910,6 +5958,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) /* Wait until bdev->bd_disk is definitely gone */ flush_scheduled_work(); /* Then retry the open from the top */ + unlock_kernel(); return -ERESTARTSYS; } BUG_ON(mddev != bdev->bd_disk->private_data); @@ -5923,6 +5972,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) check_disk_size_change(mddev->gendisk, bdev); out: + unlock_kernel(); return err; } @@ -5931,8 +5981,10 @@ static int md_release(struct gendisk *disk, fmode_t mode) mddev_t *mddev = disk->private_data; BUG_ON(!mddev); + lock_kernel(); atomic_dec(&mddev->openers); mddev_put(mddev); + unlock_kernel(); return 0; } @@ -6059,10 +6111,12 @@ 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); } @@ -6514,15 +6568,15 @@ void md_write_start(mddev_t *mddev, struct bio *bi) if (mddev->in_sync) { mddev->in_sync = 0; set_bit(MD_CHANGE_CLEAN, &mddev->flags); + set_bit(MD_CHANGE_PENDING, &mddev->flags); md_wakeup_thread(mddev->thread); did_change = 1; } 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)); } @@ -6558,22 +6612,31 @@ int md_allow_write(mddev_t *mddev) if (mddev->in_sync) { mddev->in_sync = 0; set_bit(MD_CHANGE_CLEAN, &mddev->flags); + set_bit(MD_CHANGE_PENDING, &mddev->flags); if (mddev->safemode_delay && mddev->safemode == 0) 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); - if (test_bit(MD_CHANGE_CLEAN, &mddev->flags)) + if (test_bit(MD_CHANGE_PENDING, &mddev->flags)) return -EAGAIN; else return 0; } 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) @@ -6752,7 +6815,7 @@ 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 = @@ -6829,7 +6892,7 @@ 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 @@ -6848,7 +6911,7 @@ 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)); @@ -6950,10 +7013,7 @@ 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); @@ -7039,14 +7099,13 @@ void md_check_recovery(mddev_t *mddev) mddev->recovery_cp == MaxSector) { mddev->in_sync = 1; did_change = 1; - if (mddev->persistent) - set_bit(MD_CHANGE_CLEAN, &mddev->flags); + set_bit(MD_CHANGE_CLEAN, &mddev->flags); } if (mddev->safemode == 1) 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) @@ -7085,7 +7144,7 @@ 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; } @@ -7147,7 +7206,7 @@ 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: @@ -7156,7 +7215,7 @@ 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); } @@ -7164,7 +7223,7 @@ 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)); diff --git a/drivers/md/md.h b/drivers/md/md.h index 10597bfec00..3931299788d 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -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 */ @@ -67,7 +87,7 @@ struct mdk_rdev_s #define Faulty 1 /* device is known to have a fault */ #define In_sync 2 /* device is in_sync with rest of array */ #define WriteMostly 4 /* Avoid reading if at all possible */ -#define BarriersNotsupp 5 /* BIO_RW_BARRIER is not supported */ +#define BarriersNotsupp 5 /* REQ_HARDBARRIER is not supported */ #define AllReserved 6 /* If whole device is reserved for * one array */ #define AutoDetected 7 /* added by auto-detect */ @@ -120,11 +140,15 @@ struct mddev_s unsigned long flags; #define MD_CHANGE_DEVS 0 /* Some device status has changed */ #define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */ -#define MD_CHANGE_PENDING 2 /* superblock update in progress */ +#define MD_CHANGE_PENDING 2 /* switch from 'clean' to 'active' in progress */ 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; @@ -254,7 +278,7 @@ struct mddev_s * fails. Only supported */ struct bio *biolist; /* bios that need to be retried - * because BIO_RW_BARRIER is not supported + * because REQ_HARDBARRIER is not supported */ atomic_t recovery_active; /* blocks scheduled, but not written */ @@ -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 */ diff --git a/drivers/md/mktables.c b/drivers/md/mktables.c deleted file mode 100644 index 3b1500843bb..00000000000 --- a/drivers/md/mktables.c +++ /dev/null @@ -1,132 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2002-2007 H. Peter Anvin - All Rights Reserved - * - * This file is part of the Linux kernel, and is made available under - * the terms of the GNU General Public License version 2 or (at your - * option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * mktables.c - * - * Make RAID-6 tables. This is a host user space program to be run at - * compile time. - */ - -#include <stdio.h> -#include <string.h> -#include <inttypes.h> -#include <stdlib.h> -#include <time.h> - -static uint8_t gfmul(uint8_t a, uint8_t b) -{ - uint8_t v = 0; - - while (b) { - if (b & 1) - v ^= a; - a = (a << 1) ^ (a & 0x80 ? 0x1d : 0); - b >>= 1; - } - - return v; -} - -static uint8_t gfpow(uint8_t a, int b) -{ - uint8_t v = 1; - - b %= 255; - if (b < 0) - b += 255; - - while (b) { - if (b & 1) - v = gfmul(v, a); - a = gfmul(a, a); - b >>= 1; - } - - return v; -} - -int main(int argc, char *argv[]) -{ - int i, j, k; - uint8_t v; - uint8_t exptbl[256], invtbl[256]; - - printf("#include <linux/raid/pq.h>\n"); - - /* Compute multiplication table */ - printf("\nconst u8 __attribute__((aligned(256)))\n" - "raid6_gfmul[256][256] =\n" - "{\n"); - for (i = 0; i < 256; i++) { - printf("\t{\n"); - for (j = 0; j < 256; j += 8) { - printf("\t\t"); - for (k = 0; k < 8; k++) - printf("0x%02x,%c", gfmul(i, j + k), - (k == 7) ? '\n' : ' '); - } - printf("\t},\n"); - } - printf("};\n"); - printf("#ifdef __KERNEL__\n"); - printf("EXPORT_SYMBOL(raid6_gfmul);\n"); - printf("#endif\n"); - - /* Compute power-of-2 table (exponent) */ - v = 1; - printf("\nconst u8 __attribute__((aligned(256)))\n" - "raid6_gfexp[256] =\n" "{\n"); - for (i = 0; i < 256; i += 8) { - printf("\t"); - for (j = 0; j < 8; j++) { - exptbl[i + j] = v; - printf("0x%02x,%c", v, (j == 7) ? '\n' : ' '); - v = gfmul(v, 2); - if (v == 1) - v = 0; /* For entry 255, not a real entry */ - } - } - printf("};\n"); - printf("#ifdef __KERNEL__\n"); - printf("EXPORT_SYMBOL(raid6_gfexp);\n"); - printf("#endif\n"); - - /* Compute inverse table x^-1 == x^254 */ - printf("\nconst u8 __attribute__((aligned(256)))\n" - "raid6_gfinv[256] =\n" "{\n"); - for (i = 0; i < 256; i += 8) { - printf("\t"); - for (j = 0; j < 8; j++) { - invtbl[i + j] = v = gfpow(i + j, 254); - printf("0x%02x,%c", v, (j == 7) ? '\n' : ' '); - } - } - printf("};\n"); - printf("#ifdef __KERNEL__\n"); - printf("EXPORT_SYMBOL(raid6_gfinv);\n"); - printf("#endif\n"); - - /* Compute inv(2^x + 1) (exponent-xor-inverse) table */ - printf("\nconst u8 __attribute__((aligned(256)))\n" - "raid6_gfexi[256] =\n" "{\n"); - for (i = 0; i < 256; i += 8) { - printf("\t"); - for (j = 0; j < 8; j++) - printf("0x%02x,%c", invtbl[exptbl[i + j] ^ 1], - (j == 7) ? '\n' : ' '); - } - printf("};\n"); - printf("#ifdef __KERNEL__\n"); - printf("EXPORT_SYMBOL(raid6_gfexi);\n"); - printf("#endif\n"); - - return 0; -} diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 410fb60699a..0307d217e7a 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -91,7 +91,7 @@ static void multipath_end_request(struct bio *bio, int error) if (uptodate) multipath_end_bh_io(mp_bh, 0); - else if (!bio_rw_flagged(bio, BIO_RW_AHEAD)) { + else if (!(bio->bi_rw & REQ_RAHEAD)) { /* * oops, IO error: */ @@ -142,7 +142,7 @@ static int multipath_make_request(mddev_t *mddev, struct bio * bio) struct multipath_bh * mp_bh; struct multipath_info *multipath; - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { md_barrier_request(mddev, bio); return 0; } @@ -163,7 +163,7 @@ static int multipath_make_request(mddev_t *mddev, struct bio * bio) mp_bh->bio = *bio; mp_bh->bio.bi_sector += multipath->rdev->data_offset; mp_bh->bio.bi_bdev = multipath->rdev->bdev; - mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT); + mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT; mp_bh->bio.bi_end_io = multipath_end_request; mp_bh->bio.bi_private = mp_bh; generic_make_request(&mp_bh->bio); @@ -398,7 +398,7 @@ static void multipathd (mddev_t *mddev) *bio = *(mp_bh->master_bio); bio->bi_sector += conf->multipaths[mp_bh->path].rdev->data_offset; bio->bi_bdev = conf->multipaths[mp_bh->path].rdev->bdev; - bio->bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT); + bio->bi_rw |= REQ_FAILFAST_TRANSPORT; bio->bi_end_io = multipath_end_request; bio->bi_private = mp_bh; generic_make_request(bio); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 563abed5a2c..6f7af46d623 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -483,7 +483,7 @@ static int raid0_make_request(mddev_t *mddev, struct bio *bio) struct strip_zone *zone; mdk_rdev_t *tmp_dev; - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { md_barrier_request(mddev, bio); return 0; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a948da8012d..ad83a4dcadc 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -787,8 +787,8 @@ static int make_request(mddev_t *mddev, struct bio * bio) struct bio_list bl; struct page **behind_pages = NULL; const int rw = bio_data_dir(bio); - const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); - bool do_barriers; + const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); + unsigned long do_barriers; mdk_rdev_t *blocked_rdev; /* @@ -822,7 +822,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) finish_wait(&conf->wait_barrier, &w); } if (unlikely(!mddev->barriers_work && - bio_rw_flagged(bio, BIO_RW_BARRIER))) { + (bio->bi_rw & REQ_HARDBARRIER))) { if (rw == WRITE) md_write_end(mddev); bio_endio(bio, -EOPNOTSUPP); @@ -877,7 +877,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset; read_bio->bi_bdev = mirror->rdev->bdev; read_bio->bi_end_io = raid1_end_read_request; - read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO); + read_bio->bi_rw = READ | do_sync; read_bio->bi_private = r1_bio; generic_make_request(read_bio); @@ -959,7 +959,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) atomic_set(&r1_bio->remaining, 0); atomic_set(&r1_bio->behind_remaining, 0); - do_barriers = bio_rw_flagged(bio, BIO_RW_BARRIER); + do_barriers = bio->bi_rw & REQ_HARDBARRIER; if (do_barriers) set_bit(R1BIO_Barrier, &r1_bio->state); @@ -975,8 +975,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) mbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset; mbio->bi_bdev = conf->mirrors[i].rdev->bdev; mbio->bi_end_io = raid1_end_write_request; - mbio->bi_rw = WRITE | (do_barriers << BIO_RW_BARRIER) | - (do_sync << BIO_RW_SYNCIO); + mbio->bi_rw = WRITE | do_barriers | do_sync; mbio->bi_private = r1_bio; if (behind_pages) { @@ -1121,6 +1120,8 @@ static int raid1_spare_active(mddev_t *mddev) { int i; conf_t *conf = mddev->private; + int count = 0; + unsigned long flags; /* * Find all failed disks within the RAID1 configuration @@ -1132,15 +1133,16 @@ static int raid1_spare_active(mddev_t *mddev) if (rdev && !test_bit(Faulty, &rdev->flags) && !test_and_set_bit(In_sync, &rdev->flags)) { - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded--; - spin_unlock_irqrestore(&conf->device_lock, flags); + count++; + sysfs_notify_dirent(rdev->sysfs_state); } } + spin_lock_irqsave(&conf->device_lock, flags); + mddev->degraded -= count; + spin_unlock_irqrestore(&conf->device_lock, flags); print_conf(conf); - return 0; + return count; } @@ -1633,7 +1635,7 @@ static void raid1d(mddev_t *mddev) sync_request_write(mddev, r1_bio); unplug = 1; } else if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) { - /* some requests in the r1bio were BIO_RW_BARRIER + /* some requests in the r1bio were REQ_HARDBARRIER * requests which failed with -EOPNOTSUPP. Hohumm.. * Better resubmit without the barrier. * We know which devices to resubmit for, because @@ -1641,7 +1643,7 @@ static void raid1d(mddev_t *mddev) * We already have a nr_pending reference on these rdevs. */ int i; - const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO); + const unsigned long do_sync = (r1_bio->master_bio->bi_rw & REQ_SYNC); clear_bit(R1BIO_BarrierRetry, &r1_bio->state); clear_bit(R1BIO_Barrier, &r1_bio->state); for (i=0; i < conf->raid_disks; i++) @@ -1662,8 +1664,7 @@ static void raid1d(mddev_t *mddev) conf->mirrors[i].rdev->data_offset; bio->bi_bdev = conf->mirrors[i].rdev->bdev; bio->bi_end_io = raid1_end_write_request; - bio->bi_rw = WRITE | - (do_sync << BIO_RW_SYNCIO); + bio->bi_rw = WRITE | do_sync; bio->bi_private = r1_bio; r1_bio->bios[i] = bio; generic_make_request(bio); @@ -1698,7 +1699,7 @@ static void raid1d(mddev_t *mddev) (unsigned long long)r1_bio->sector); raid_end_bio_io(r1_bio); } else { - const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO); + const unsigned long do_sync = r1_bio->master_bio->bi_rw & REQ_SYNC; r1_bio->bios[r1_bio->read_disk] = mddev->ro ? IO_BLOCKED : NULL; r1_bio->read_disk = disk; @@ -1715,7 +1716,7 @@ static void raid1d(mddev_t *mddev) bio->bi_sector = r1_bio->sector + rdev->data_offset; bio->bi_bdev = rdev->bdev; bio->bi_end_io = raid1_end_read_request; - bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO); + bio->bi_rw = READ | do_sync; bio->bi_private = r1_bio; unplug = 1; generic_make_request(bio); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 42e64e4e5e2..84718383124 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -799,12 +799,12 @@ static int make_request(mddev_t *mddev, struct bio * bio) int i; int chunk_sects = conf->chunk_mask + 1; const int rw = bio_data_dir(bio); - const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); + const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); struct bio_list bl; unsigned long flags; mdk_rdev_t *blocked_rdev; - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { md_barrier_request(mddev, bio); return 0; } @@ -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: @@ -879,7 +897,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) mirror->rdev->data_offset; read_bio->bi_bdev = mirror->rdev->bdev; read_bio->bi_end_io = raid10_end_read_request; - read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO); + read_bio->bi_rw = READ | do_sync; read_bio->bi_private = r10_bio; generic_make_request(read_bio); @@ -947,7 +965,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) conf->mirrors[d].rdev->data_offset; mbio->bi_bdev = conf->mirrors[d].rdev->bdev; mbio->bi_end_io = raid10_end_write_request; - mbio->bi_rw = WRITE | (do_sync << BIO_RW_SYNCIO); + mbio->bi_rw = WRITE | do_sync; mbio->bi_private = r10_bio; atomic_inc(&r10_bio->remaining); @@ -1098,6 +1116,8 @@ static int raid10_spare_active(mddev_t *mddev) int i; conf_t *conf = mddev->private; mirror_info_t *tmp; + int count = 0; + unsigned long flags; /* * Find all non-in_sync disks within the RAID10 configuration @@ -1108,15 +1128,16 @@ static int raid10_spare_active(mddev_t *mddev) if (tmp->rdev && !test_bit(Faulty, &tmp->rdev->flags) && !test_and_set_bit(In_sync, &tmp->rdev->flags)) { - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded--; - spin_unlock_irqrestore(&conf->device_lock, flags); + count++; + sysfs_notify_dirent(tmp->rdev->sysfs_state); } } + spin_lock_irqsave(&conf->device_lock, flags); + mddev->degraded -= count; + spin_unlock_irqrestore(&conf->device_lock, flags); print_conf(conf); - return 0; + return count; } @@ -1716,7 +1737,7 @@ static void raid10d(mddev_t *mddev) raid_end_bio_io(r10_bio); bio_put(bio); } else { - const bool do_sync = bio_rw_flagged(r10_bio->master_bio, BIO_RW_SYNCIO); + const unsigned long do_sync = (r10_bio->master_bio->bi_rw & REQ_SYNC); bio_put(bio); rdev = conf->mirrors[mirror].rdev; if (printk_ratelimit()) @@ -1730,7 +1751,7 @@ static void raid10d(mddev_t *mddev) bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr + rdev->data_offset; bio->bi_bdev = rdev->bdev; - bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO); + bio->bi_rw = READ | do_sync; bio->bi_private = r10_bio; bio->bi_end_io = raid10_end_read_request; unplug = 1; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 96c690279fc..69b0a169e43 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -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 int raid5_congested(void *data, int bits) +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 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. @@ -3958,7 +3978,7 @@ static int make_request(mddev_t *mddev, struct bio * bi) const int rw = bio_data_dir(bi); int remaining; - if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) { + if (unlikely(bi->bi_rw & REQ_HARDBARRIER)) { /* Drain all pending writes. We only really need * to ensure they have been submitted, but this is * easier. @@ -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; @@ -4566,23 +4586,15 @@ raid5_show_stripe_cache_size(mddev_t *mddev, char *page) return 0; } -static ssize_t -raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len) +int +raid5_set_cache_size(mddev_t *mddev, int size) { raid5_conf_t *conf = mddev->private; - unsigned long new; int err; - if (len >= PAGE_SIZE) + if (size <= 16 || size > 32768) return -EINVAL; - if (!conf) - return -ENODEV; - - if (strict_strtoul(page, 10, &new)) - return -EINVAL; - if (new <= 16 || new > 32768) - return -EINVAL; - while (new < conf->max_nr_stripes) { + while (size < conf->max_nr_stripes) { if (drop_one_stripe(conf)) conf->max_nr_stripes--; else @@ -4591,11 +4603,32 @@ raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len) err = md_allow_write(mddev); if (err) return err; - while (new > conf->max_nr_stripes) { + 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) +{ + raid5_conf_t *conf = mddev->private; + unsigned long new; + int err; + + if (len >= PAGE_SIZE) + return -EINVAL; + if (!conf) + return -ENODEV; + + if (strict_strtoul(page, 10, &new)) + return -EINVAL; + err = raid5_set_cache_size(mddev, new); + if (err) + return err; 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; @@ -5144,42 +5177,47 @@ 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 - */ - { - 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; - } /* 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)) + else if (mddev->kobj.sd && + sysfs_create_group(&mddev->kobj, &raid5_attrs_group)) printk(KERN_WARNING - "md/raid:%s: failed to create sysfs attributes.\n", + "raid5: failed to create sysfs attributes for %s\n", mdname(mddev)); + md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); - mddev->queue->queue_lock = &conf->device_lock; + 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; - mddev->queue->unplug_fn = raid5_unplug_device; - mddev->queue->backing_dev_info.congested_data = mddev; - mddev->queue->backing_dev_info.congested_fn = raid5_congested; + blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec); - md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); + 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; - 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)); + 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); + list_for_each_entry(rdev, &mddev->disks, same_set) + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + } return 0; abort: @@ -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; @@ -5291,6 +5330,8 @@ static int raid5_spare_active(mddev_t *mddev) int i; raid5_conf_t *conf = mddev->private; struct disk_info *tmp; + int count = 0; + unsigned long flags; for (i = 0; i < conf->raid_disks; i++) { tmp = conf->disks + i; @@ -5298,14 +5339,15 @@ static int raid5_spare_active(mddev_t *mddev) && tmp->rdev->recovery_offset == MaxSector && !test_bit(Faulty, &tmp->rdev->flags) && !test_and_set_bit(In_sync, &tmp->rdev->flags)) { - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); - mddev->degraded--; - spin_unlock_irqrestore(&conf->device_lock, flags); + count++; + sysfs_notify_dirent(tmp->rdev->sysfs_state); } } + spin_lock_irqsave(&conf->device_lock, flags); + mddev->degraded -= count; + spin_unlock_irqrestore(&conf->device_lock, flags); print_raid5_conf(conf); - return 0; + return count; } static int raid5_remove_disk(mddev_t *mddev, int number) @@ -5545,10 +5587,7 @@ 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 +5642,7 @@ 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); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 0f86f5e3672..36eaed5dfd6 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -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 diff --git a/drivers/md/raid6algos.c b/drivers/md/raid6algos.c deleted file mode 100644 index 1f8784bfd44..00000000000 --- a/drivers/md/raid6algos.c +++ /dev/null @@ -1,154 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2002 H. Peter Anvin - All Rights Reserved - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 53 Temple Place Ste 330, - * Boston MA 02111-1307, USA; either version 2 of the License, or - * (at your option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * raid6algos.c - * - * Algorithm list and algorithm selection for RAID-6 - */ - -#include <linux/raid/pq.h> -#include <linux/gfp.h> -#ifndef __KERNEL__ -#include <sys/mman.h> -#include <stdio.h> -#else -#if !RAID6_USE_EMPTY_ZERO_PAGE -/* In .bss so it's zeroed */ -const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256))); -EXPORT_SYMBOL(raid6_empty_zero_page); -#endif -#endif - -struct raid6_calls raid6_call; -EXPORT_SYMBOL_GPL(raid6_call); - -const struct raid6_calls * const raid6_algos[] = { - &raid6_intx1, - &raid6_intx2, - &raid6_intx4, - &raid6_intx8, -#if defined(__ia64__) - &raid6_intx16, - &raid6_intx32, -#endif -#if defined(__i386__) && !defined(__arch_um__) - &raid6_mmxx1, - &raid6_mmxx2, - &raid6_sse1x1, - &raid6_sse1x2, - &raid6_sse2x1, - &raid6_sse2x2, -#endif -#if defined(__x86_64__) && !defined(__arch_um__) - &raid6_sse2x1, - &raid6_sse2x2, - &raid6_sse2x4, -#endif -#ifdef CONFIG_ALTIVEC - &raid6_altivec1, - &raid6_altivec2, - &raid6_altivec4, - &raid6_altivec8, -#endif - NULL -}; - -#ifdef __KERNEL__ -#define RAID6_TIME_JIFFIES_LG2 4 -#else -/* Need more time to be stable in userspace */ -#define RAID6_TIME_JIFFIES_LG2 9 -#define time_before(x, y) ((x) < (y)) -#endif - -/* Try to pick the best algorithm */ -/* This code uses the gfmul table as convenient data set to abuse */ - -int __init raid6_select_algo(void) -{ - const struct raid6_calls * const * algo; - const struct raid6_calls * best; - char *syndromes; - void *dptrs[(65536/PAGE_SIZE)+2]; - int i, disks; - unsigned long perf, bestperf; - int bestprefer; - unsigned long j0, j1; - - disks = (65536/PAGE_SIZE)+2; - for ( i = 0 ; i < disks-2 ; i++ ) { - dptrs[i] = ((char *)raid6_gfmul) + PAGE_SIZE*i; - } - - /* Normal code - use a 2-page allocation to avoid D$ conflict */ - syndromes = (void *) __get_free_pages(GFP_KERNEL, 1); - - if ( !syndromes ) { - printk("raid6: Yikes! No memory available.\n"); - return -ENOMEM; - } - - dptrs[disks-2] = syndromes; - dptrs[disks-1] = syndromes + PAGE_SIZE; - - bestperf = 0; bestprefer = 0; best = NULL; - - for ( algo = raid6_algos ; *algo ; algo++ ) { - if ( !(*algo)->valid || (*algo)->valid() ) { - perf = 0; - - preempt_disable(); - j0 = jiffies; - while ( (j1 = jiffies) == j0 ) - cpu_relax(); - while (time_before(jiffies, - j1 + (1<<RAID6_TIME_JIFFIES_LG2))) { - (*algo)->gen_syndrome(disks, PAGE_SIZE, dptrs); - perf++; - } - preempt_enable(); - - if ( (*algo)->prefer > bestprefer || - ((*algo)->prefer == bestprefer && - perf > bestperf) ) { - best = *algo; - bestprefer = best->prefer; - bestperf = perf; - } - printk("raid6: %-8s %5ld MB/s\n", (*algo)->name, - (perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2)); - } - } - - if (best) { - printk("raid6: using algorithm %s (%ld MB/s)\n", - best->name, - (bestperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2)); - raid6_call = *best; - } else - printk("raid6: Yikes! No algorithm found!\n"); - - free_pages((unsigned long)syndromes, 1); - - return best ? 0 : -EINVAL; -} - -static void raid6_exit(void) -{ - do { } while (0); -} - -subsys_initcall(raid6_select_algo); -module_exit(raid6_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("RAID6 Q-syndrome calculations"); diff --git a/drivers/md/raid6altivec.uc b/drivers/md/raid6altivec.uc deleted file mode 100644 index 2654d5c854b..00000000000 --- a/drivers/md/raid6altivec.uc +++ /dev/null @@ -1,130 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2002-2004 H. Peter Anvin - All Rights Reserved - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 53 Temple Place Ste 330, - * Boston MA 02111-1307, USA; either version 2 of the License, or - * (at your option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * raid6altivec$#.c - * - * $#-way unrolled portable integer math RAID-6 instruction set - * - * This file is postprocessed using unroll.awk - * - * <benh> hpa: in process, - * you can just "steal" the vec unit with enable_kernel_altivec() (but - * bracked this with preempt_disable/enable or in a lock) - */ - -#include <linux/raid/pq.h> - -#ifdef CONFIG_ALTIVEC - -#include <altivec.h> -#ifdef __KERNEL__ -# include <asm/system.h> -# include <asm/cputable.h> -#endif - -/* - * This is the C data type to use. We use a vector of - * signed char so vec_cmpgt() will generate the right - * instruction. - */ - -typedef vector signed char unative_t; - -#define NBYTES(x) ((vector signed char) {x,x,x,x, x,x,x,x, x,x,x,x, x,x,x,x}) -#define NSIZE sizeof(unative_t) - -/* - * The SHLBYTE() operation shifts each byte left by 1, *not* - * rolling over into the next byte - */ -static inline __attribute_const__ unative_t SHLBYTE(unative_t v) -{ - return vec_add(v,v); -} - -/* - * The MASK() operation returns 0xFF in any byte for which the high - * bit is 1, 0x00 for any byte for which the high bit is 0. - */ -static inline __attribute_const__ unative_t MASK(unative_t v) -{ - unative_t zv = NBYTES(0); - - /* vec_cmpgt returns a vector bool char; thus the need for the cast */ - return (unative_t)vec_cmpgt(zv, v); -} - - -/* This is noinline to make damned sure that gcc doesn't move any of the - Altivec code around the enable/disable code */ -static void noinline -raid6_altivec$#_gen_syndrome_real(int disks, size_t bytes, void **ptrs) -{ - u8 **dptr = (u8 **)ptrs; - u8 *p, *q; - int d, z, z0; - - unative_t wd$$, wq$$, wp$$, w1$$, w2$$; - unative_t x1d = NBYTES(0x1d); - - z0 = disks - 3; /* Highest data disk */ - p = dptr[z0+1]; /* XOR parity */ - q = dptr[z0+2]; /* RS syndrome */ - - for ( d = 0 ; d < bytes ; d += NSIZE*$# ) { - wq$$ = wp$$ = *(unative_t *)&dptr[z0][d+$$*NSIZE]; - for ( z = z0-1 ; z >= 0 ; z-- ) { - wd$$ = *(unative_t *)&dptr[z][d+$$*NSIZE]; - wp$$ = vec_xor(wp$$, wd$$); - w2$$ = MASK(wq$$); - w1$$ = SHLBYTE(wq$$); - w2$$ = vec_and(w2$$, x1d); - w1$$ = vec_xor(w1$$, w2$$); - wq$$ = vec_xor(w1$$, wd$$); - } - *(unative_t *)&p[d+NSIZE*$$] = wp$$; - *(unative_t *)&q[d+NSIZE*$$] = wq$$; - } -} - -static void raid6_altivec$#_gen_syndrome(int disks, size_t bytes, void **ptrs) -{ - preempt_disable(); - enable_kernel_altivec(); - - raid6_altivec$#_gen_syndrome_real(disks, bytes, ptrs); - - preempt_enable(); -} - -int raid6_have_altivec(void); -#if $# == 1 -int raid6_have_altivec(void) -{ - /* This assumes either all CPUs have Altivec or none does */ -# ifdef __KERNEL__ - return cpu_has_feature(CPU_FTR_ALTIVEC); -# else - return 1; -# endif -} -#endif - -const struct raid6_calls raid6_altivec$# = { - raid6_altivec$#_gen_syndrome, - raid6_have_altivec, - "altivecx$#", - 0 -}; - -#endif /* CONFIG_ALTIVEC */ diff --git a/drivers/md/raid6int.uc b/drivers/md/raid6int.uc deleted file mode 100644 index d1e276a14fa..00000000000 --- a/drivers/md/raid6int.uc +++ /dev/null @@ -1,117 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2002-2004 H. Peter Anvin - All Rights Reserved - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 53 Temple Place Ste 330, - * Boston MA 02111-1307, USA; either version 2 of the License, or - * (at your option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * raid6int$#.c - * - * $#-way unrolled portable integer math RAID-6 instruction set - * - * This file is postprocessed using unroll.awk - */ - -#include <linux/raid/pq.h> - -/* - * This is the C data type to use - */ - -/* Change this from BITS_PER_LONG if there is something better... */ -#if BITS_PER_LONG == 64 -# define NBYTES(x) ((x) * 0x0101010101010101UL) -# define NSIZE 8 -# define NSHIFT 3 -# define NSTRING "64" -typedef u64 unative_t; -#else -# define NBYTES(x) ((x) * 0x01010101U) -# define NSIZE 4 -# define NSHIFT 2 -# define NSTRING "32" -typedef u32 unative_t; -#endif - - - -/* - * IA-64 wants insane amounts of unrolling. On other architectures that - * is just a waste of space. - */ -#if ($# <= 8) || defined(__ia64__) - - -/* - * These sub-operations are separate inlines since they can sometimes be - * specially optimized using architecture-specific hacks. - */ - -/* - * The SHLBYTE() operation shifts each byte left by 1, *not* - * rolling over into the next byte - */ -static inline __attribute_const__ unative_t SHLBYTE(unative_t v) -{ - unative_t vv; - - vv = (v << 1) & NBYTES(0xfe); - return vv; -} - -/* - * The MASK() operation returns 0xFF in any byte for which the high - * bit is 1, 0x00 for any byte for which the high bit is 0. - */ -static inline __attribute_const__ unative_t MASK(unative_t v) -{ - unative_t vv; - - vv = v & NBYTES(0x80); - vv = (vv << 1) - (vv >> 7); /* Overflow on the top bit is OK */ - return vv; -} - - -static void raid6_int$#_gen_syndrome(int disks, size_t bytes, void **ptrs) -{ - u8 **dptr = (u8 **)ptrs; - u8 *p, *q; - int d, z, z0; - - unative_t wd$$, wq$$, wp$$, w1$$, w2$$; - - z0 = disks - 3; /* Highest data disk */ - p = dptr[z0+1]; /* XOR parity */ - q = dptr[z0+2]; /* RS syndrome */ - - for ( d = 0 ; d < bytes ; d += NSIZE*$# ) { - wq$$ = wp$$ = *(unative_t *)&dptr[z0][d+$$*NSIZE]; - for ( z = z0-1 ; z >= 0 ; z-- ) { - wd$$ = *(unative_t *)&dptr[z][d+$$*NSIZE]; - wp$$ ^= wd$$; - w2$$ = MASK(wq$$); - w1$$ = SHLBYTE(wq$$); - w2$$ &= NBYTES(0x1d); - w1$$ ^= w2$$; - wq$$ = w1$$ ^ wd$$; - } - *(unative_t *)&p[d+NSIZE*$$] = wp$$; - *(unative_t *)&q[d+NSIZE*$$] = wq$$; - } -} - -const struct raid6_calls raid6_intx$# = { - raid6_int$#_gen_syndrome, - NULL, /* always valid */ - "int" NSTRING "x$#", - 0 -}; - -#endif diff --git a/drivers/md/raid6mmx.c b/drivers/md/raid6mmx.c deleted file mode 100644 index e7f6c13132b..00000000000 --- a/drivers/md/raid6mmx.c +++ /dev/null @@ -1,142 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2002 H. Peter Anvin - All Rights Reserved - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 53 Temple Place Ste 330, - * Boston MA 02111-1307, USA; either version 2 of the License, or - * (at your option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * raid6mmx.c - * - * MMX implementation of RAID-6 syndrome functions - */ - -#if defined(__i386__) && !defined(__arch_um__) - -#include <linux/raid/pq.h> -#include "raid6x86.h" - -/* Shared with raid6sse1.c */ -const struct raid6_mmx_constants { - u64 x1d; -} raid6_mmx_constants = { - 0x1d1d1d1d1d1d1d1dULL, -}; - -static int raid6_have_mmx(void) -{ - /* Not really "boot_cpu" but "all_cpus" */ - return boot_cpu_has(X86_FEATURE_MMX); -} - -/* - * Plain MMX implementation - */ -static void raid6_mmx1_gen_syndrome(int disks, size_t bytes, void **ptrs) -{ - u8 **dptr = (u8 **)ptrs; - u8 *p, *q; - int d, z, z0; - - z0 = disks - 3; /* Highest data disk */ - p = dptr[z0+1]; /* XOR parity */ - q = dptr[z0+2]; /* RS syndrome */ - - kernel_fpu_begin(); - - asm volatile("movq %0,%%mm0" : : "m" (raid6_mmx_constants.x1d)); - asm volatile("pxor %mm5,%mm5"); /* Zero temp */ - - for ( d = 0 ; d < bytes ; d += 8 ) { - asm volatile("movq %0,%%mm2" : : "m" (dptr[z0][d])); /* P[0] */ - asm volatile("movq %mm2,%mm4"); /* Q[0] */ - for ( z = z0-1 ; z >= 0 ; z-- ) { - asm volatile("movq %0,%%mm6" : : "m" (dptr[z][d])); - asm volatile("pcmpgtb %mm4,%mm5"); - asm volatile("paddb %mm4,%mm4"); - asm volatile("pand %mm0,%mm5"); - asm volatile("pxor %mm5,%mm4"); - asm volatile("pxor %mm5,%mm5"); - asm volatile("pxor %mm6,%mm2"); - asm volatile("pxor %mm6,%mm4"); - } - asm volatile("movq %%mm2,%0" : "=m" (p[d])); - asm volatile("pxor %mm2,%mm2"); - asm volatile("movq %%mm4,%0" : "=m" (q[d])); - asm volatile("pxor %mm4,%mm4"); - } - - kernel_fpu_end(); -} - -const struct raid6_calls raid6_mmxx1 = { - raid6_mmx1_gen_syndrome, - raid6_have_mmx, - "mmxx1", - 0 -}; - -/* - * Unrolled-by-2 MMX implementation - */ -static void raid6_mmx2_gen_syndrome(int disks, size_t bytes, void **ptrs) -{ - u8 **dptr = (u8 **)ptrs; - u8 *p, *q; - int d, z, z0; - - z0 = disks - 3; /* Highest data disk */ - p = dptr[z0+1]; /* XOR parity */ - q = dptr[z0+2]; /* RS syndrome */ - - kernel_fpu_begin(); - - asm volatile("movq %0,%%mm0" : : "m" (raid6_mmx_constants.x1d)); - asm volatile("pxor %mm5,%mm5"); /* Zero temp */ - asm volatile("pxor %mm7,%mm7"); /* Zero temp */ - - for ( d = 0 ; d < bytes ; d += 16 ) { - asm volatile("movq %0,%%mm2" : : "m" (dptr[z0][d])); /* P[0] */ - asm volatile("movq %0,%%mm3" : : "m" (dptr[z0][d+8])); - asm volatile("movq %mm2,%mm4"); /* Q[0] */ - asm volatile("movq %mm3,%mm6"); /* Q[1] */ - for ( z = z0-1 ; z >= 0 ; z-- ) { - asm volatile("pcmpgtb %mm4,%mm5"); - asm volatile("pcmpgtb %mm6,%mm7"); - asm volatile("paddb %mm4,%mm4"); - asm volatile("paddb %mm6,%mm6"); - asm volatile("pand %mm0,%mm5"); - asm volatile("pand %mm0,%mm7"); - asm volatile("pxor %mm5,%mm4"); - asm volatile("pxor %mm7,%mm6"); - asm volatile("movq %0,%%mm5" : : "m" (dptr[z][d])); - asm volatile("movq %0,%%mm7" : : "m" (dptr[z][d+8])); - asm volatile("pxor %mm5,%mm2"); - asm volatile("pxor %mm7,%mm3"); - asm volatile("pxor %mm5,%mm4"); - asm volatile("pxor %mm7,%mm6"); - asm volatile("pxor %mm5,%mm5"); - asm volatile("pxor %mm7,%mm7"); - } - asm volatile("movq %%mm2,%0" : "=m" (p[d])); - asm volatile("movq %%mm3,%0" : "=m" (p[d+8])); - asm volatile("movq %%mm4,%0" : "=m" (q[d])); - asm volatile("movq %%mm6,%0" : "=m" (q[d+8])); - } - - kernel_fpu_end(); -} - -const struct raid6_calls raid6_mmxx2 = { - raid6_mmx2_gen_syndrome, - raid6_have_mmx, - "mmxx2", - 0 -}; - -#endif diff --git a/drivers/md/raid6recov.c b/drivers/md/raid6recov.c deleted file mode 100644 index 2609f00e0d6..00000000000 --- a/drivers/md/raid6recov.c +++ /dev/null @@ -1,132 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2002 H. Peter Anvin - All Rights Reserved - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 53 Temple Place Ste 330, - * Boston MA 02111-1307, USA; either version 2 of the License, or - * (at your option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * raid6recov.c - * - * RAID-6 data recovery in dual failure mode. In single failure mode, - * use the RAID-5 algorithm (or, in the case of Q failure, just reconstruct - * the syndrome.) - */ - -#include <linux/raid/pq.h> - -/* Recover two failed data blocks. */ -void raid6_2data_recov(int disks, size_t bytes, int faila, int failb, - void **ptrs) -{ - u8 *p, *q, *dp, *dq; - u8 px, qx, db; - const u8 *pbmul; /* P multiplier table for B data */ - const u8 *qmul; /* Q multiplier table (for both) */ - - p = (u8 *)ptrs[disks-2]; - q = (u8 *)ptrs[disks-1]; - - /* Compute syndrome with zero for the missing data pages - Use the dead data pages as temporary storage for - delta p and delta q */ - dp = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; - ptrs[disks-2] = dp; - dq = (u8 *)ptrs[failb]; - ptrs[failb] = (void *)raid6_empty_zero_page; - ptrs[disks-1] = dq; - - raid6_call.gen_syndrome(disks, bytes, ptrs); - - /* Restore pointer table */ - ptrs[faila] = dp; - ptrs[failb] = dq; - ptrs[disks-2] = p; - ptrs[disks-1] = q; - - /* Now, pick the proper data tables */ - pbmul = raid6_gfmul[raid6_gfexi[failb-faila]]; - qmul = raid6_gfmul[raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]]]; - - /* Now do it... */ - while ( bytes-- ) { - px = *p ^ *dp; - qx = qmul[*q ^ *dq]; - *dq++ = db = pbmul[px] ^ qx; /* Reconstructed B */ - *dp++ = db ^ px; /* Reconstructed A */ - p++; q++; - } -} -EXPORT_SYMBOL_GPL(raid6_2data_recov); - -/* Recover failure of one data block plus the P block */ -void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs) -{ - u8 *p, *q, *dq; - const u8 *qmul; /* Q multiplier table */ - - p = (u8 *)ptrs[disks-2]; - q = (u8 *)ptrs[disks-1]; - - /* Compute syndrome with zero for the missing data page - Use the dead data page as temporary storage for delta q */ - dq = (u8 *)ptrs[faila]; - ptrs[faila] = (void *)raid6_empty_zero_page; - ptrs[disks-1] = dq; - - raid6_call.gen_syndrome(disks, bytes, ptrs); - - /* Restore pointer table */ - ptrs[faila] = dq; - ptrs[disks-1] = q; - - /* Now, pick the proper data tables */ - qmul = raid6_gfmul[raid6_gfinv[raid6_gfexp[faila]]]; - - /* Now do it... */ - while ( bytes-- ) { - *p++ ^= *dq = qmul[*q ^ *dq]; - q++; dq++; - } -} -EXPORT_SYMBOL_GPL(raid6_datap_recov); - -#ifndef __KERNEL__ -/* Testing only */ - -/* Recover two failed blocks. */ -void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, void **ptrs) -{ - if ( faila > failb ) { - int tmp = faila; - faila = failb; - failb = tmp; - } - - if ( failb == disks-1 ) { - if ( faila == disks-2 ) { - /* P+Q failure. Just rebuild the syndrome. */ - raid6_call.gen_syndrome(disks, bytes, ptrs); - } else { - /* data+Q failure. Reconstruct data from P, - then rebuild syndrome. */ - /* NOT IMPLEMENTED - equivalent to RAID-5 */ - } - } else { - if ( failb == disks-2 ) { - /* data+P failure. */ - raid6_datap_recov(disks, bytes, faila, ptrs); - } else { - /* data+data failure. */ - raid6_2data_recov(disks, bytes, faila, failb, ptrs); - } - } -} - -#endif diff --git a/drivers/md/raid6sse1.c b/drivers/md/raid6sse1.c deleted file mode 100644 index b274dd5eab8..00000000000 --- a/drivers/md/raid6sse1.c +++ /dev/null @@ -1,162 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2002 H. Peter Anvin - All Rights Reserved - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 53 Temple Place Ste 330, - * Boston MA 02111-1307, USA; either version 2 of the License, or - * (at your option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * raid6sse1.c - * - * SSE-1/MMXEXT implementation of RAID-6 syndrome functions - * - * This is really an MMX implementation, but it requires SSE-1 or - * AMD MMXEXT for prefetch support and a few other features. The - * support for nontemporal memory accesses is enough to make this - * worthwhile as a separate implementation. - */ - -#if defined(__i386__) && !defined(__arch_um__) - -#include <linux/raid/pq.h> -#include "raid6x86.h" - -/* Defined in raid6mmx.c */ -extern const struct raid6_mmx_constants { - u64 x1d; -} raid6_mmx_constants; - -static int raid6_have_sse1_or_mmxext(void) -{ - /* Not really boot_cpu but "all_cpus" */ - return boot_cpu_has(X86_FEATURE_MMX) && - (boot_cpu_has(X86_FEATURE_XMM) || - boot_cpu_has(X86_FEATURE_MMXEXT)); -} - -/* - * Plain SSE1 implementation - */ -static void raid6_sse11_gen_syndrome(int disks, size_t bytes, void **ptrs) -{ - u8 **dptr = (u8 **)ptrs; - u8 *p, *q; - int d, z, z0; - - z0 = disks - 3; /* Highest data disk */ - p = dptr[z0+1]; /* XOR parity */ - q = dptr[z0+2]; /* RS syndrome */ - - kernel_fpu_begin(); - - asm volatile("movq %0,%%mm0" : : "m" (raid6_mmx_constants.x1d)); - asm volatile("pxor %mm5,%mm5"); /* Zero temp */ - - for ( d = 0 ; d < bytes ; d += 8 ) { - asm volatile("prefetchnta %0" : : "m" (dptr[z0][d])); - asm volatile("movq %0,%%mm2" : : "m" (dptr[z0][d])); /* P[0] */ - asm volatile("prefetchnta %0" : : "m" (dptr[z0-1][d])); - asm volatile("movq %mm2,%mm4"); /* Q[0] */ - asm volatile("movq %0,%%mm6" : : "m" (dptr[z0-1][d])); - for ( z = z0-2 ; z >= 0 ; z-- ) { - asm volatile("prefetchnta %0" : : "m" (dptr[z][d])); - asm volatile("pcmpgtb %mm4,%mm5"); - asm volatile("paddb %mm4,%mm4"); - asm volatile("pand %mm0,%mm5"); - asm volatile("pxor %mm5,%mm4"); - asm volatile("pxor %mm5,%mm5"); - asm volatile("pxor %mm6,%mm2"); - asm volatile("pxor %mm6,%mm4"); - asm volatile("movq %0,%%mm6" : : "m" (dptr[z][d])); - } - asm volatile("pcmpgtb %mm4,%mm5"); - asm volatile("paddb %mm4,%mm4"); - asm volatile("pand %mm0,%mm5"); - asm volatile("pxor %mm5,%mm4"); - asm volatile("pxor %mm5,%mm5"); - asm volatile("pxor %mm6,%mm2"); - asm volatile("pxor %mm6,%mm4"); - - asm volatile("movntq %%mm2,%0" : "=m" (p[d])); - asm volatile("movntq %%mm4,%0" : "=m" (q[d])); - } - - asm volatile("sfence" : : : "memory"); - kernel_fpu_end(); -} - -const struct raid6_calls raid6_sse1x1 = { - raid6_sse11_gen_syndrome, - raid6_have_sse1_or_mmxext, - "sse1x1", - 1 /* Has cache hints */ -}; - -/* - * Unrolled-by-2 SSE1 implementation - */ -static void raid6_sse12_gen_syndrome(int disks, size_t bytes, void **ptrs) -{ - u8 **dptr = (u8 **)ptrs; - u8 *p, *q; - int d, z, z0; - - z0 = disks - 3; /* Highest data disk */ - p = dptr[z0+1]; /* XOR parity */ - q = dptr[z0+2]; /* RS syndrome */ - - kernel_fpu_begin(); - - asm volatile("movq %0,%%mm0" : : "m" (raid6_mmx_constants.x1d)); - asm volatile("pxor %mm5,%mm5"); /* Zero temp */ - asm volatile("pxor %mm7,%mm7"); /* Zero temp */ - - /* We uniformly assume a single prefetch covers at least 16 bytes */ - for ( d = 0 ; d < bytes ; d += 16 ) { - asm volatile("prefetchnta %0" : : "m" (dptr[z0][d])); - asm volatile("movq %0,%%mm2" : : "m" (dptr[z0][d])); /* P[0] */ - asm volatile("movq %0,%%mm3" : : "m" (dptr[z0][d+8])); /* P[1] */ - asm volatile("movq %mm2,%mm4"); /* Q[0] */ - asm volatile("movq %mm3,%mm6"); /* Q[1] */ - for ( z = z0-1 ; z >= 0 ; z-- ) { - asm volatile("prefetchnta %0" : : "m" (dptr[z][d])); - asm volatile("pcmpgtb %mm4,%mm5"); - asm volatile("pcmpgtb %mm6,%mm7"); - asm volatile("paddb %mm4,%mm4"); - asm volatile("paddb %mm6,%mm6"); - asm volatile("pand %mm0,%mm5"); - asm volatile("pand %mm0,%mm7"); - asm volatile("pxor %mm5,%mm4"); - asm volatile("pxor %mm7,%mm6"); - asm volatile("movq %0,%%mm5" : : "m" (dptr[z][d])); - asm volatile("movq %0,%%mm7" : : "m" (dptr[z][d+8])); - asm volatile("pxor %mm5,%mm2"); - asm volatile("pxor %mm7,%mm3"); - asm volatile("pxor %mm5,%mm4"); - asm volatile("pxor %mm7,%mm6"); - asm volatile("pxor %mm5,%mm5"); - asm volatile("pxor %mm7,%mm7"); - } - asm volatile("movntq %%mm2,%0" : "=m" (p[d])); - asm volatile("movntq %%mm3,%0" : "=m" (p[d+8])); - asm volatile("movntq %%mm4,%0" : "=m" (q[d])); - asm volatile("movntq %%mm6,%0" : "=m" (q[d+8])); - } - - asm volatile("sfence" : :: "memory"); - kernel_fpu_end(); -} - -const struct raid6_calls raid6_sse1x2 = { - raid6_sse12_gen_syndrome, - raid6_have_sse1_or_mmxext, - "sse1x2", - 1 /* Has cache hints */ -}; - -#endif diff --git a/drivers/md/raid6sse2.c b/drivers/md/raid6sse2.c deleted file mode 100644 index 6ed6c6c0389..00000000000 --- a/drivers/md/raid6sse2.c +++ /dev/null @@ -1,262 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2002 H. Peter Anvin - All Rights Reserved - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 53 Temple Place Ste 330, - * Boston MA 02111-1307, USA; either version 2 of the License, or - * (at your option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * raid6sse2.c - * - * SSE-2 implementation of RAID-6 syndrome functions - * - */ - -#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__) - -#include <linux/raid/pq.h> -#include "raid6x86.h" - -static const struct raid6_sse_constants { - u64 x1d[2]; -} raid6_sse_constants __attribute__((aligned(16))) = { - { 0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL }, -}; - -static int raid6_have_sse2(void) -{ - /* Not really boot_cpu but "all_cpus" */ - return boot_cpu_has(X86_FEATURE_MMX) && - boot_cpu_has(X86_FEATURE_FXSR) && - boot_cpu_has(X86_FEATURE_XMM) && - boot_cpu_has(X86_FEATURE_XMM2); -} - -/* - * Plain SSE2 implementation - */ -static void raid6_sse21_gen_syndrome(int disks, size_t bytes, void **ptrs) -{ - u8 **dptr = (u8 **)ptrs; - u8 *p, *q; - int d, z, z0; - - z0 = disks - 3; /* Highest data disk */ - p = dptr[z0+1]; /* XOR parity */ - q = dptr[z0+2]; /* RS syndrome */ - - kernel_fpu_begin(); - - asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0])); - asm volatile("pxor %xmm5,%xmm5"); /* Zero temp */ - - for ( d = 0 ; d < bytes ; d += 16 ) { - asm volatile("prefetchnta %0" : : "m" (dptr[z0][d])); - asm volatile("movdqa %0,%%xmm2" : : "m" (dptr[z0][d])); /* P[0] */ - asm volatile("prefetchnta %0" : : "m" (dptr[z0-1][d])); - asm volatile("movdqa %xmm2,%xmm4"); /* Q[0] */ - asm volatile("movdqa %0,%%xmm6" : : "m" (dptr[z0-1][d])); - for ( z = z0-2 ; z >= 0 ; z-- ) { - asm volatile("prefetchnta %0" : : "m" (dptr[z][d])); - asm volatile("pcmpgtb %xmm4,%xmm5"); - asm volatile("paddb %xmm4,%xmm4"); - asm volatile("pand %xmm0,%xmm5"); - asm volatile("pxor %xmm5,%xmm4"); - asm volatile("pxor %xmm5,%xmm5"); - asm volatile("pxor %xmm6,%xmm2"); - asm volatile("pxor %xmm6,%xmm4"); - asm volatile("movdqa %0,%%xmm6" : : "m" (dptr[z][d])); - } - asm volatile("pcmpgtb %xmm4,%xmm5"); - asm volatile("paddb %xmm4,%xmm4"); - asm volatile("pand %xmm0,%xmm5"); - asm volatile("pxor %xmm5,%xmm4"); - asm volatile("pxor %xmm5,%xmm5"); - asm volatile("pxor %xmm6,%xmm2"); - asm volatile("pxor %xmm6,%xmm4"); - - asm volatile("movntdq %%xmm2,%0" : "=m" (p[d])); - asm volatile("pxor %xmm2,%xmm2"); - asm volatile("movntdq %%xmm4,%0" : "=m" (q[d])); - asm volatile("pxor %xmm4,%xmm4"); - } - - asm volatile("sfence" : : : "memory"); - kernel_fpu_end(); -} - -const struct raid6_calls raid6_sse2x1 = { - raid6_sse21_gen_syndrome, - raid6_have_sse2, - "sse2x1", - 1 /* Has cache hints */ -}; - -/* - * Unrolled-by-2 SSE2 implementation - */ -static void raid6_sse22_gen_syndrome(int disks, size_t bytes, void **ptrs) -{ - u8 **dptr = (u8 **)ptrs; - u8 *p, *q; - int d, z, z0; - - z0 = disks - 3; /* Highest data disk */ - p = dptr[z0+1]; /* XOR parity */ - q = dptr[z0+2]; /* RS syndrome */ - - kernel_fpu_begin(); - - asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0])); - asm volatile("pxor %xmm5,%xmm5"); /* Zero temp */ - asm volatile("pxor %xmm7,%xmm7"); /* Zero temp */ - - /* We uniformly assume a single prefetch covers at least 32 bytes */ - for ( d = 0 ; d < bytes ; d += 32 ) { - asm volatile("prefetchnta %0" : : "m" (dptr[z0][d])); - asm volatile("movdqa %0,%%xmm2" : : "m" (dptr[z0][d])); /* P[0] */ - asm volatile("movdqa %0,%%xmm3" : : "m" (dptr[z0][d+16])); /* P[1] */ - asm volatile("movdqa %xmm2,%xmm4"); /* Q[0] */ - asm volatile("movdqa %xmm3,%xmm6"); /* Q[1] */ - for ( z = z0-1 ; z >= 0 ; z-- ) { - asm volatile("prefetchnta %0" : : "m" (dptr[z][d])); - asm volatile("pcmpgtb %xmm4,%xmm5"); - asm volatile("pcmpgtb %xmm6,%xmm7"); - asm volatile("paddb %xmm4,%xmm4"); - asm volatile("paddb %xmm6,%xmm6"); - asm volatile("pand %xmm0,%xmm5"); - asm volatile("pand %xmm0,%xmm7"); - asm volatile("pxor %xmm5,%xmm4"); - asm volatile("pxor %xmm7,%xmm6"); - asm volatile("movdqa %0,%%xmm5" : : "m" (dptr[z][d])); - asm volatile("movdqa %0,%%xmm7" : : "m" (dptr[z][d+16])); - asm volatile("pxor %xmm5,%xmm2"); - asm volatile("pxor %xmm7,%xmm3"); - asm volatile("pxor %xmm5,%xmm4"); - asm volatile("pxor %xmm7,%xmm6"); - asm volatile("pxor %xmm5,%xmm5"); - asm volatile("pxor %xmm7,%xmm7"); - } - asm volatile("movntdq %%xmm2,%0" : "=m" (p[d])); - asm volatile("movntdq %%xmm3,%0" : "=m" (p[d+16])); - asm volatile("movntdq %%xmm4,%0" : "=m" (q[d])); - asm volatile("movntdq %%xmm6,%0" : "=m" (q[d+16])); - } - - asm volatile("sfence" : : : "memory"); - kernel_fpu_end(); -} - -const struct raid6_calls raid6_sse2x2 = { - raid6_sse22_gen_syndrome, - raid6_have_sse2, - "sse2x2", - 1 /* Has cache hints */ -}; - -#endif - -#if defined(__x86_64__) && !defined(__arch_um__) - -/* - * Unrolled-by-4 SSE2 implementation - */ -static void raid6_sse24_gen_syndrome(int disks, size_t bytes, void **ptrs) -{ - u8 **dptr = (u8 **)ptrs; - u8 *p, *q; - int d, z, z0; - - z0 = disks - 3; /* Highest data disk */ - p = dptr[z0+1]; /* XOR parity */ - q = dptr[z0+2]; /* RS syndrome */ - - kernel_fpu_begin(); - - asm volatile("movdqa %0,%%xmm0" :: "m" (raid6_sse_constants.x1d[0])); - asm volatile("pxor %xmm2,%xmm2"); /* P[0] */ - asm volatile("pxor %xmm3,%xmm3"); /* P[1] */ - asm volatile("pxor %xmm4,%xmm4"); /* Q[0] */ - asm volatile("pxor %xmm5,%xmm5"); /* Zero temp */ - asm volatile("pxor %xmm6,%xmm6"); /* Q[1] */ - asm volatile("pxor %xmm7,%xmm7"); /* Zero temp */ - asm volatile("pxor %xmm10,%xmm10"); /* P[2] */ - asm volatile("pxor %xmm11,%xmm11"); /* P[3] */ - asm volatile("pxor %xmm12,%xmm12"); /* Q[2] */ - asm volatile("pxor %xmm13,%xmm13"); /* Zero temp */ - asm volatile("pxor %xmm14,%xmm14"); /* Q[3] */ - asm volatile("pxor %xmm15,%xmm15"); /* Zero temp */ - - for ( d = 0 ; d < bytes ; d += 64 ) { - for ( z = z0 ; z >= 0 ; z-- ) { - /* The second prefetch seems to improve performance... */ - asm volatile("prefetchnta %0" :: "m" (dptr[z][d])); - asm volatile("prefetchnta %0" :: "m" (dptr[z][d+32])); - asm volatile("pcmpgtb %xmm4,%xmm5"); - asm volatile("pcmpgtb %xmm6,%xmm7"); - asm volatile("pcmpgtb %xmm12,%xmm13"); - asm volatile("pcmpgtb %xmm14,%xmm15"); - asm volatile("paddb %xmm4,%xmm4"); - asm volatile("paddb %xmm6,%xmm6"); - asm volatile("paddb %xmm12,%xmm12"); - asm volatile("paddb %xmm14,%xmm14"); - asm volatile("pand %xmm0,%xmm5"); - asm volatile("pand %xmm0,%xmm7"); - asm volatile("pand %xmm0,%xmm13"); - asm volatile("pand %xmm0,%xmm15"); - asm volatile("pxor %xmm5,%xmm4"); - asm volatile("pxor %xmm7,%xmm6"); - asm volatile("pxor %xmm13,%xmm12"); - asm volatile("pxor %xmm15,%xmm14"); - asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d])); - asm volatile("movdqa %0,%%xmm7" :: "m" (dptr[z][d+16])); - asm volatile("movdqa %0,%%xmm13" :: "m" (dptr[z][d+32])); - asm volatile("movdqa %0,%%xmm15" :: "m" (dptr[z][d+48])); - asm volatile("pxor %xmm5,%xmm2"); - asm volatile("pxor %xmm7,%xmm3"); - asm volatile("pxor %xmm13,%xmm10"); - asm volatile("pxor %xmm15,%xmm11"); - asm volatile("pxor %xmm5,%xmm4"); - asm volatile("pxor %xmm7,%xmm6"); - asm volatile("pxor %xmm13,%xmm12"); - asm volatile("pxor %xmm15,%xmm14"); - asm volatile("pxor %xmm5,%xmm5"); - asm volatile("pxor %xmm7,%xmm7"); - asm volatile("pxor %xmm13,%xmm13"); - asm volatile("pxor %xmm15,%xmm15"); - } - asm volatile("movntdq %%xmm2,%0" : "=m" (p[d])); - asm volatile("pxor %xmm2,%xmm2"); - asm volatile("movntdq %%xmm3,%0" : "=m" (p[d+16])); - asm volatile("pxor %xmm3,%xmm3"); - asm volatile("movntdq %%xmm10,%0" : "=m" (p[d+32])); - asm volatile("pxor %xmm10,%xmm10"); - asm volatile("movntdq %%xmm11,%0" : "=m" (p[d+48])); - asm volatile("pxor %xmm11,%xmm11"); - asm volatile("movntdq %%xmm4,%0" : "=m" (q[d])); - asm volatile("pxor %xmm4,%xmm4"); - asm volatile("movntdq %%xmm6,%0" : "=m" (q[d+16])); - asm volatile("pxor %xmm6,%xmm6"); - asm volatile("movntdq %%xmm12,%0" : "=m" (q[d+32])); - asm volatile("pxor %xmm12,%xmm12"); - asm volatile("movntdq %%xmm14,%0" : "=m" (q[d+48])); - asm volatile("pxor %xmm14,%xmm14"); - } - - asm volatile("sfence" : : : "memory"); - kernel_fpu_end(); -} - -const struct raid6_calls raid6_sse2x4 = { - raid6_sse24_gen_syndrome, - raid6_have_sse2, - "sse2x4", - 1 /* Has cache hints */ -}; - -#endif diff --git a/drivers/md/raid6test/Makefile b/drivers/md/raid6test/Makefile deleted file mode 100644 index 2874cbef529..00000000000 --- a/drivers/md/raid6test/Makefile +++ /dev/null @@ -1,75 +0,0 @@ -# -# This is a simple Makefile to test some of the RAID-6 code -# from userspace. -# - -CC = gcc -OPTFLAGS = -O2 # Adjust as desired -CFLAGS = -I.. -I ../../../include -g $(OPTFLAGS) -LD = ld -AWK = awk -AR = ar -RANLIB = ranlib - -.c.o: - $(CC) $(CFLAGS) -c -o $@ $< - -%.c: ../%.c - cp -f $< $@ - -%.uc: ../%.uc - cp -f $< $@ - -all: raid6.a raid6test - -raid6.a: raid6int1.o raid6int2.o raid6int4.o raid6int8.o raid6int16.o \ - raid6int32.o \ - raid6mmx.o raid6sse1.o raid6sse2.o \ - raid6altivec1.o raid6altivec2.o raid6altivec4.o raid6altivec8.o \ - raid6recov.o raid6algos.o \ - raid6tables.o - rm -f $@ - $(AR) cq $@ $^ - $(RANLIB) $@ - -raid6test: test.c raid6.a - $(CC) $(CFLAGS) -o raid6test $^ - -raid6altivec1.c: raid6altivec.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=1 < raid6altivec.uc > $@ - -raid6altivec2.c: raid6altivec.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=2 < raid6altivec.uc > $@ - -raid6altivec4.c: raid6altivec.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=4 < raid6altivec.uc > $@ - -raid6altivec8.c: raid6altivec.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=8 < raid6altivec.uc > $@ - -raid6int1.c: raid6int.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=1 < raid6int.uc > $@ - -raid6int2.c: raid6int.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=2 < raid6int.uc > $@ - -raid6int4.c: raid6int.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=4 < raid6int.uc > $@ - -raid6int8.c: raid6int.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=8 < raid6int.uc > $@ - -raid6int16.c: raid6int.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=16 < raid6int.uc > $@ - -raid6int32.c: raid6int.uc ../unroll.awk - $(AWK) ../unroll.awk -vN=32 < raid6int.uc > $@ - -raid6tables.c: mktables - ./mktables > raid6tables.c - -clean: - rm -f *.o *.a mktables mktables.c raid6int.uc raid6*.c raid6test - -spotless: clean - rm -f *~ diff --git a/drivers/md/raid6test/test.c b/drivers/md/raid6test/test.c deleted file mode 100644 index 7a930318b17..00000000000 --- a/drivers/md/raid6test/test.c +++ /dev/null @@ -1,124 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2002-2007 H. Peter Anvin - All Rights Reserved - * - * This file is part of the Linux kernel, and is made available under - * the terms of the GNU General Public License version 2 or (at your - * option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * raid6test.c - * - * Test RAID-6 recovery with various algorithms - */ - -#include <stdlib.h> -#include <stdio.h> -#include <string.h> -#include <linux/raid/pq.h> - -#define NDISKS 16 /* Including P and Q */ - -const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256))); -struct raid6_calls raid6_call; - -char *dataptrs[NDISKS]; -char data[NDISKS][PAGE_SIZE]; -char recovi[PAGE_SIZE], recovj[PAGE_SIZE]; - -static void makedata(void) -{ - int i, j; - - for (i = 0; i < NDISKS; i++) { - for (j = 0; j < PAGE_SIZE; j++) - data[i][j] = rand(); - - dataptrs[i] = data[i]; - } -} - -static char disk_type(int d) -{ - switch (d) { - case NDISKS-2: - return 'P'; - case NDISKS-1: - return 'Q'; - default: - return 'D'; - } -} - -static int test_disks(int i, int j) -{ - int erra, errb; - - memset(recovi, 0xf0, PAGE_SIZE); - memset(recovj, 0xba, PAGE_SIZE); - - dataptrs[i] = recovi; - dataptrs[j] = recovj; - - raid6_dual_recov(NDISKS, PAGE_SIZE, i, j, (void **)&dataptrs); - - erra = memcmp(data[i], recovi, PAGE_SIZE); - errb = memcmp(data[j], recovj, PAGE_SIZE); - - if (i < NDISKS-2 && j == NDISKS-1) { - /* We don't implement the DQ failure scenario, since it's - equivalent to a RAID-5 failure (XOR, then recompute Q) */ - erra = errb = 0; - } else { - printf("algo=%-8s faila=%3d(%c) failb=%3d(%c) %s\n", - raid6_call.name, - i, disk_type(i), - j, disk_type(j), - (!erra && !errb) ? "OK" : - !erra ? "ERRB" : - !errb ? "ERRA" : "ERRAB"); - } - - dataptrs[i] = data[i]; - dataptrs[j] = data[j]; - - return erra || errb; -} - -int main(int argc, char *argv[]) -{ - const struct raid6_calls *const *algo; - int i, j; - int err = 0; - - makedata(); - - for (algo = raid6_algos; *algo; algo++) { - if (!(*algo)->valid || (*algo)->valid()) { - raid6_call = **algo; - - /* Nuke syndromes */ - memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE); - - /* Generate assumed good syndrome */ - raid6_call.gen_syndrome(NDISKS, PAGE_SIZE, - (void **)&dataptrs); - - for (i = 0; i < NDISKS-1; i++) - for (j = i+1; j < NDISKS; j++) - err += test_disks(i, j); - } - printf("\n"); - } - - printf("\n"); - /* Pick the best algorithm test */ - raid6_select_algo(); - - if (err) - printf("\n*** ERRORS FOUND ***\n"); - - return err; -} diff --git a/drivers/md/raid6x86.h b/drivers/md/raid6x86.h deleted file mode 100644 index 4c22c156855..00000000000 --- a/drivers/md/raid6x86.h +++ /dev/null @@ -1,61 +0,0 @@ -/* ----------------------------------------------------------------------- * - * - * Copyright 2002-2004 H. Peter Anvin - All Rights Reserved - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 53 Temple Place Ste 330, - * Boston MA 02111-1307, USA; either version 2 of the License, or - * (at your option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * raid6x86.h - * - * Definitions common to x86 and x86-64 RAID-6 code only - */ - -#ifndef LINUX_RAID_RAID6X86_H -#define LINUX_RAID_RAID6X86_H - -#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__) - -#ifdef __KERNEL__ /* Real code */ - -#include <asm/i387.h> - -#else /* Dummy code for user space testing */ - -static inline void kernel_fpu_begin(void) -{ -} - -static inline void kernel_fpu_end(void) -{ -} - -#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */ -#define X86_FEATURE_FXSR (0*32+24) /* FXSAVE and FXRSTOR instructions - * (fast save and restore) */ -#define X86_FEATURE_XMM (0*32+25) /* Streaming SIMD Extensions */ -#define X86_FEATURE_XMM2 (0*32+26) /* Streaming SIMD Extensions-2 */ -#define X86_FEATURE_MMXEXT (1*32+22) /* AMD MMX extensions */ - -/* Should work well enough on modern CPUs for testing */ -static inline int boot_cpu_has(int flag) -{ - u32 eax = (flag >> 5) ? 0x80000001 : 1; - u32 edx; - - asm volatile("cpuid" - : "+a" (eax), "=d" (edx) - : : "ecx", "ebx"); - - return (edx >> (flag & 31)) & 1; -} - -#endif /* ndef __KERNEL__ */ - -#endif -#endif diff --git a/drivers/md/unroll.awk b/drivers/md/unroll.awk deleted file mode 100644 index c6aa03631df..00000000000 --- a/drivers/md/unroll.awk +++ /dev/null @@ -1,20 +0,0 @@ - -# This filter requires one command line option of form -vN=n -# where n must be a decimal number. -# -# Repeat each input line containing $$ n times, replacing $$ with 0...n-1. -# Replace each $# with n, and each $* with a single $. - -BEGIN { - n = N + 0 -} -{ - if (/\$\$/) { rep = n } else { rep = 1 } - for (i = 0; i < rep; ++i) { - tmp = $0 - gsub(/\$\$/, i, tmp) - gsub(/\$\#/, n, tmp) - gsub(/\$\*/, "$", tmp) - print tmp - } -} |