diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/Kconfig | 43 | ||||
-rw-r--r-- | drivers/md/Makefile | 2 | ||||
-rw-r--r-- | drivers/md/bitmap.c | 189 | ||||
-rw-r--r-- | drivers/md/bitmap.h | 10 | ||||
-rw-r--r-- | drivers/md/dm-cache-policy-mq.c | 251 | ||||
-rw-r--r-- | drivers/md/dm-crypt.c | 13 | ||||
-rw-r--r-- | drivers/md/dm-delay.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-io.c | 15 | ||||
-rw-r--r-- | drivers/md/dm-ioctl.c | 17 | ||||
-rw-r--r-- | drivers/md/dm-log-userspace-base.c | 91 | ||||
-rw-r--r-- | drivers/md/dm-log-userspace-transfer.c | 5 | ||||
-rw-r--r-- | drivers/md/dm-log-writes.c | 825 | ||||
-rw-r--r-- | drivers/md/dm-mpath.c | 6 | ||||
-rw-r--r-- | drivers/md/dm-snap.c | 120 | ||||
-rw-r--r-- | drivers/md/dm-sysfs.c | 43 | ||||
-rw-r--r-- | drivers/md/dm-table.c | 71 | ||||
-rw-r--r-- | drivers/md/dm-thin.c | 11 | ||||
-rw-r--r-- | drivers/md/dm-verity.c | 147 | ||||
-rw-r--r-- | drivers/md/dm.c | 618 | ||||
-rw-r--r-- | drivers/md/dm.h | 10 | ||||
-rw-r--r-- | drivers/md/md-cluster.c | 965 | ||||
-rw-r--r-- | drivers/md/md-cluster.h | 29 | ||||
-rw-r--r-- | drivers/md/md.c | 409 | ||||
-rw-r--r-- | drivers/md/md.h | 26 | ||||
-rw-r--r-- | drivers/md/raid0.c | 53 | ||||
-rw-r--r-- | drivers/md/raid1.c | 34 | ||||
-rw-r--r-- | drivers/md/raid10.c | 8 | ||||
-rw-r--r-- | drivers/md/raid5.c | 839 | ||||
-rw-r--r-- | drivers/md/raid5.h | 59 |
29 files changed, 4246 insertions, 665 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 63e05e32b462..edcf4ab66e00 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -175,6 +175,22 @@ config MD_FAULTY In unsure, say N. + +config MD_CLUSTER + tristate "Cluster Support for MD (EXPERIMENTAL)" + depends on BLK_DEV_MD + depends on DLM + default n + ---help--- + Clustering support for MD devices. This enables locking and + synchronization across multiple systems on the cluster, so all + nodes in the cluster can access the MD devices simultaneously. + + This brings the redundancy (and uptime) of RAID levels across the + nodes of the cluster. + + If unsure, say N. + source "drivers/md/bcache/Kconfig" config BLK_DEV_DM_BUILTIN @@ -196,6 +212,17 @@ config BLK_DEV_DM If unsure, say N. +config DM_MQ_DEFAULT + bool "request-based DM: use blk-mq I/O path by default" + depends on BLK_DEV_DM + ---help--- + This option enables the blk-mq based I/O path for request-based + DM devices by default. With the option the dm_mod.use_blk_mq + module/boot option defaults to Y, without it to N, but it can + still be overriden either way. + + If unsure say N. + config DM_DEBUG bool "Device mapper debugging support" depends on BLK_DEV_DM @@ -432,4 +459,20 @@ config DM_SWITCH If unsure, say N. +config DM_LOG_WRITES + tristate "Log writes target support" + depends on BLK_DEV_DM + ---help--- + This device-mapper target takes two devices, one device to use + normally, one to log all write operations done to the first device. + This is for use by file system developers wishing to verify that + their fs is writing a consitent file system at all times by allowing + them to replay the log in a variety of ways and to check the + contents. + + To compile this code as a module, choose M here: the module will + be called dm-log-writes. + + If unsure, say N. + endif # MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index a2da532b1c2b..dba4db5985fb 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_MD_RAID10) += raid10.o obj-$(CONFIG_MD_RAID456) += raid456.o obj-$(CONFIG_MD_MULTIPATH) += multipath.o obj-$(CONFIG_MD_FAULTY) += faulty.o +obj-$(CONFIG_MD_CLUSTER) += md-cluster.o obj-$(CONFIG_BCACHE) += bcache/ obj-$(CONFIG_BLK_DEV_MD) += md-mod.o obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o @@ -55,6 +56,7 @@ obj-$(CONFIG_DM_CACHE) += dm-cache.o obj-$(CONFIG_DM_CACHE_MQ) += dm-cache-mq.o obj-$(CONFIG_DM_CACHE_CLEANER) += dm-cache-cleaner.o obj-$(CONFIG_DM_ERA) += dm-era.o +obj-$(CONFIG_DM_LOG_WRITES) += dm-log-writes.o ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 3a5767968ba0..2bc56e2a3526 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -205,6 +205,10 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait) struct block_device *bdev; struct mddev *mddev = bitmap->mddev; struct bitmap_storage *store = &bitmap->storage; + int node_offset = 0; + + if (mddev_is_clustered(bitmap->mddev)) + node_offset = bitmap->cluster_slot * store->file_pages; while ((rdev = next_active_rdev(rdev, mddev)) != NULL) { int size = PAGE_SIZE; @@ -433,6 +437,7 @@ void bitmap_update_sb(struct bitmap *bitmap) /* This might have been changed by a reshape */ sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors); sb->chunksize = cpu_to_le32(bitmap->mddev->bitmap_info.chunksize); + sb->nodes = cpu_to_le32(bitmap->mddev->bitmap_info.nodes); sb->sectors_reserved = cpu_to_le32(bitmap->mddev-> bitmap_info.space); kunmap_atomic(sb); @@ -544,6 +549,7 @@ static int bitmap_read_sb(struct bitmap *bitmap) bitmap_super_t *sb; unsigned long chunksize, daemon_sleep, write_behind; unsigned long long events; + int nodes = 0; unsigned long sectors_reserved = 0; int err = -EINVAL; struct page *sb_page; @@ -562,6 +568,22 @@ static int bitmap_read_sb(struct bitmap *bitmap) return -ENOMEM; bitmap->storage.sb_page = sb_page; +re_read: + /* If cluster_slot is set, the cluster is setup */ + if (bitmap->cluster_slot >= 0) { + sector_t bm_blocks = bitmap->mddev->resync_max_sectors; + + sector_div(bm_blocks, + bitmap->mddev->bitmap_info.chunksize >> 9); + /* bits to bytes */ + bm_blocks = ((bm_blocks+7) >> 3) + sizeof(bitmap_super_t); + /* to 4k blocks */ + bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks, 4096); + bitmap->mddev->bitmap_info.offset += bitmap->cluster_slot * (bm_blocks << 3); + pr_info("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__, + bitmap->cluster_slot, (unsigned long long)bitmap->mddev->bitmap_info.offset); + } + if (bitmap->storage.file) { loff_t isize = i_size_read(bitmap->storage.file->f_mapping->host); int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize; @@ -577,12 +599,15 @@ static int bitmap_read_sb(struct bitmap *bitmap) if (err) return err; + err = -EINVAL; sb = kmap_atomic(sb_page); chunksize = le32_to_cpu(sb->chunksize); daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ; write_behind = le32_to_cpu(sb->write_behind); sectors_reserved = le32_to_cpu(sb->sectors_reserved); + nodes = le32_to_cpu(sb->nodes); + strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64); /* verify that the bitmap-specific fields are valid */ if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) @@ -619,7 +644,7 @@ static int bitmap_read_sb(struct bitmap *bitmap) goto out; } events = le64_to_cpu(sb->events); - if (events < bitmap->mddev->events) { + if (!nodes && (events < bitmap->mddev->events)) { printk(KERN_INFO "%s: bitmap file is out of date (%llu < %llu) " "-- forcing full recovery\n", @@ -634,20 +659,40 @@ static int bitmap_read_sb(struct bitmap *bitmap) if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN) set_bit(BITMAP_HOSTENDIAN, &bitmap->flags); bitmap->events_cleared = le64_to_cpu(sb->events_cleared); + strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64); err = 0; + out: kunmap_atomic(sb); + /* Assiging chunksize is required for "re_read" */ + bitmap->mddev->bitmap_info.chunksize = chunksize; + if (nodes && (bitmap->cluster_slot < 0)) { + err = md_setup_cluster(bitmap->mddev, nodes); + if (err) { + pr_err("%s: Could not setup cluster service (%d)\n", + bmname(bitmap), err); + goto out_no_sb; + } + bitmap->cluster_slot = md_cluster_ops->slot_number(bitmap->mddev); + goto re_read; + } + + out_no_sb: if (test_bit(BITMAP_STALE, &bitmap->flags)) bitmap->events_cleared = bitmap->mddev->events; bitmap->mddev->bitmap_info.chunksize = chunksize; bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep; bitmap->mddev->bitmap_info.max_write_behind = write_behind; + bitmap->mddev->bitmap_info.nodes = nodes; if (bitmap->mddev->bitmap_info.space == 0 || bitmap->mddev->bitmap_info.space > sectors_reserved) bitmap->mddev->bitmap_info.space = sectors_reserved; - if (err) + if (err) { bitmap_print_sb(bitmap); + if (bitmap->cluster_slot < 0) + md_cluster_stop(bitmap->mddev); + } return err; } @@ -692,9 +737,10 @@ static inline struct page *filemap_get_page(struct bitmap_storage *store, } static int bitmap_storage_alloc(struct bitmap_storage *store, - unsigned long chunks, int with_super) + unsigned long chunks, int with_super, + int slot_number) { - int pnum; + int pnum, offset = 0; unsigned long num_pages; unsigned long bytes; @@ -703,6 +749,7 @@ static int bitmap_storage_alloc(struct bitmap_storage *store, bytes += sizeof(bitmap_super_t); num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE); + offset = slot_number * (num_pages - 1); store->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL); @@ -713,20 +760,22 @@ static int bitmap_storage_alloc(struct bitmap_storage *store, store->sb_page = alloc_page(GFP_KERNEL|__GFP_ZERO); if (store->sb_page == NULL) return -ENOMEM; - store->sb_page->index = 0; } + pnum = 0; if (store->sb_page) { store->filemap[0] = store->sb_page; pnum = 1; + store->sb_page->index = offset; } + for ( ; pnum < num_pages; pnum++) { store->filemap[pnum] = alloc_page(GFP_KERNEL|__GFP_ZERO); if (!store->filemap[pnum]) { store->file_pages = pnum; return -ENOMEM; } - store->filemap[pnum]->index = pnum; + store->filemap[pnum]->index = pnum + offset; } store->file_pages = pnum; @@ -885,6 +934,28 @@ static void bitmap_file_clear_bit(struct bitmap *bitmap, sector_t block) } } +static int bitmap_file_test_bit(struct bitmap *bitmap, sector_t block) +{ + unsigned long bit; + struct page *page; + void *paddr; + unsigned long chunk = block >> bitmap->counts.chunkshift; + int set = 0; + + page = filemap_get_page(&bitmap->storage, chunk); + if (!page) + return -EINVAL; + bit = file_page_offset(&bitmap->storage, chunk); + paddr = kmap_atomic(page); + if (test_bit(BITMAP_HOSTENDIAN, &bitmap->flags)) + set = test_bit(bit, paddr); + else + set = test_bit_le(bit, paddr); + kunmap_atomic(paddr); + return set; +} + + /* this gets called when the md device is ready to unplug its underlying * (slave) device queues -- before we let any writes go down, we need to * sync the dirty pages of the bitmap file to disk */ @@ -935,7 +1006,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n */ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) { - unsigned long i, chunks, index, oldindex, bit; + unsigned long i, chunks, index, oldindex, bit, node_offset = 0; struct page *page = NULL; unsigned long bit_cnt = 0; struct file *file; @@ -981,6 +1052,9 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) if (!bitmap->mddev->bitmap_info.external) offset = sizeof(bitmap_super_t); + if (mddev_is_clustered(bitmap->mddev)) + node_offset = bitmap->cluster_slot * (DIV_ROUND_UP(store->bytes, PAGE_SIZE)); + for (i = 0; i < chunks; i++) { int b; index = file_page_index(&bitmap->storage, i); @@ -1001,7 +1075,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) bitmap->mddev, bitmap->mddev->bitmap_info.offset, page, - index, count); + index + node_offset, count); if (ret) goto err; @@ -1207,7 +1281,6 @@ void bitmap_daemon_work(struct mddev *mddev) j < bitmap->storage.file_pages && !test_bit(BITMAP_STALE, &bitmap->flags); j++) { - if (test_page_attr(bitmap, j, BITMAP_PAGE_DIRTY)) /* bitmap_unplug will handle the rest */ @@ -1530,11 +1603,13 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n return; } if (!*bmc) { - *bmc = 2 | (needed ? NEEDED_MASK : 0); + *bmc = 2; bitmap_count_page(&bitmap->counts, offset, 1); bitmap_set_pending(&bitmap->counts, offset); bitmap->allclean = 0; } + if (needed) + *bmc |= NEEDED_MASK; spin_unlock_irq(&bitmap->counts.lock); } @@ -1591,6 +1666,10 @@ static void bitmap_free(struct bitmap *bitmap) if (!bitmap) /* there was no bitmap */ return; + if (mddev_is_clustered(bitmap->mddev) && bitmap->mddev->cluster_info && + bitmap->cluster_slot == md_cluster_ops->slot_number(bitmap->mddev)) + md_cluster_stop(bitmap->mddev); + /* Shouldn't be needed - but just in case.... */ wait_event(bitmap->write_wait, atomic_read(&bitmap->pending_writes) == 0); @@ -1636,7 +1715,7 @@ void bitmap_destroy(struct mddev *mddev) * initialize the bitmap structure * if this returns an error, bitmap_destroy must be called to do clean up */ -int bitmap_create(struct mddev *mddev) +struct bitmap *bitmap_create(struct mddev *mddev, int slot) { struct bitmap *bitmap; sector_t blocks = mddev->resync_max_sectors; @@ -1650,7 +1729,7 @@ int bitmap_create(struct mddev *mddev) bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL); if (!bitmap) - return -ENOMEM; + return ERR_PTR(-ENOMEM); spin_lock_init(&bitmap->counts.lock); atomic_set(&bitmap->pending_writes, 0); @@ -1659,6 +1738,7 @@ int bitmap_create(struct mddev *mddev) init_waitqueue_head(&bitmap->behind_wait); bitmap->mddev = mddev; + bitmap->cluster_slot = slot; if (mddev->kobj.sd) bm = sysfs_get_dirent(mddev->kobj.sd, "bitmap"); @@ -1706,12 +1786,14 @@ int bitmap_create(struct mddev *mddev) printk(KERN_INFO "created bitmap (%lu pages) for device %s\n", bitmap->counts.pages, bmname(bitmap)); - mddev->bitmap = bitmap; - return test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0; + err = test_bit(BITMAP_WRITE_ERROR, &bitmap->flags) ? -EIO : 0; + if (err) + goto error; + return bitmap; error: bitmap_free(bitmap); - return err; + return ERR_PTR(err); } int bitmap_load(struct mddev *mddev) @@ -1765,6 +1847,60 @@ out: } EXPORT_SYMBOL_GPL(bitmap_load); +/* Loads the bitmap associated with slot and copies the resync information + * to our bitmap + */ +int bitmap_copy_from_slot(struct mddev *mddev, int slot, + sector_t *low, sector_t *high, bool clear_bits) +{ + int rv = 0, i, j; + sector_t block, lo = 0, hi = 0; + struct bitmap_counts *counts; + struct bitmap *bitmap = bitmap_create(mddev, slot); + + if (IS_ERR(bitmap)) + return PTR_ERR(bitmap); + + rv = bitmap_read_sb(bitmap); + if (rv) + goto err; + + rv = bitmap_init_from_disk(bitmap, 0); + if (rv) + goto err; + + counts = &bitmap->counts; + for (j = 0; j < counts->chunks; j++) { + block = (sector_t)j << counts->chunkshift; + if (bitmap_file_test_bit(bitmap, block)) { + if (!lo) + lo = block; + hi = block; + bitmap_file_clear_bit(bitmap, block); + bitmap_set_memory_bits(mddev->bitmap, block, 1); + bitmap_file_set_bit(mddev->bitmap, block); + } + } + + if (clear_bits) { + bitmap_update_sb(bitmap); + /* Setting this for the ev_page should be enough. + * And we do not require both write_all and PAGE_DIRT either + */ + for (i = 0; i < bitmap->storage.file_pages; i++) + set_page_attr(bitmap, i, BITMAP_PAGE_DIRTY); + bitmap_write_all(bitmap); + bitmap_unplug(bitmap); + } + *low = lo; + *high = hi; +err: + bitmap_free(bitmap); + return rv; +} +EXPORT_SYMBOL_GPL(bitmap_copy_from_slot); + + void bitmap_status(struct seq_file *seq, struct bitmap *bitmap) { unsigned long chunk_kb; @@ -1849,7 +1985,8 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks, memset(&store, 0, sizeof(store)); if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file) ret = bitmap_storage_alloc(&store, chunks, - !bitmap->mddev->bitmap_info.external); + !bitmap->mddev->bitmap_info.external, + bitmap->cluster_slot); if (ret) goto err; @@ -2021,13 +2158,18 @@ location_store(struct mddev *mddev, const char *buf, size_t len) return -EINVAL; mddev->bitmap_info.offset = offset; if (mddev->pers) { + struct bitmap *bitmap; mddev->pers->quiesce(mddev, 1); - rv = bitmap_create(mddev); - if (!rv) + bitmap = bitmap_create(mddev, -1); + if (IS_ERR(bitmap)) + rv = PTR_ERR(bitmap); + else { + mddev->bitmap = bitmap; rv = bitmap_load(mddev); - if (rv) { - bitmap_destroy(mddev); - mddev->bitmap_info.offset = 0; + if (rv) { + bitmap_destroy(mddev); + mddev->bitmap_info.offset = 0; + } } mddev->pers->quiesce(mddev, 0); if (rv) @@ -2186,6 +2328,8 @@ __ATTR(chunksize, S_IRUGO|S_IWUSR, chunksize_show, chunksize_store); static ssize_t metadata_show(struct mddev *mddev, char *page) { + if (mddev_is_clustered(mddev)) + return sprintf(page, "clustered\n"); return sprintf(page, "%s\n", (mddev->bitmap_info.external ? "external" : "internal")); } @@ -2198,7 +2342,8 @@ static ssize_t metadata_store(struct mddev *mddev, const char *buf, size_t len) return -EBUSY; if (strncmp(buf, "external", 8) == 0) mddev->bitmap_info.external = 1; - else if (strncmp(buf, "internal", 8) == 0) + else if ((strncmp(buf, "internal", 8) == 0) || + (strncmp(buf, "clustered", 9) == 0)) mddev->bitmap_info.external = 0; else return -EINVAL; diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h index 30210b9c4ef9..f1f4dd01090d 100644 --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -130,8 +130,9 @@ typedef struct bitmap_super_s { __le32 write_behind; /* 60 number of outstanding write-behind writes */ __le32 sectors_reserved; /* 64 number of 512-byte sectors that are * reserved for the bitmap. */ - - __u8 pad[256 - 68]; /* set to zero */ + __le32 nodes; /* 68 the maximum number of nodes in cluster. */ + __u8 cluster_name[64]; /* 72 cluster name to which this md belongs */ + __u8 pad[256 - 136]; /* set to zero */ } bitmap_super_t; /* notes: @@ -226,12 +227,13 @@ struct bitmap { wait_queue_head_t behind_wait; struct kernfs_node *sysfs_can_clear; + int cluster_slot; /* Slot offset for clustered env */ }; /* the bitmap API */ /* these are used only by md/bitmap */ -int bitmap_create(struct mddev *mddev); +struct bitmap *bitmap_create(struct mddev *mddev, int slot); int bitmap_load(struct mddev *mddev); void bitmap_flush(struct mddev *mddev); void bitmap_destroy(struct mddev *mddev); @@ -260,6 +262,8 @@ void bitmap_daemon_work(struct mddev *mddev); int bitmap_resize(struct bitmap *bitmap, sector_t blocks, int chunksize, int init); +int bitmap_copy_from_slot(struct mddev *mddev, int slot, + sector_t *lo, sector_t *hi, bool clear_bits); #endif #endif diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c index 13f547a4eeb6..3ddd1162334d 100644 --- a/drivers/md/dm-cache-policy-mq.c +++ b/drivers/md/dm-cache-policy-mq.c @@ -8,6 +8,7 @@ #include "dm.h" #include <linux/hash.h> +#include <linux/jiffies.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> @@ -124,32 +125,41 @@ static void iot_examine_bio(struct io_tracker *t, struct bio *bio) * sorted queue. */ #define NR_QUEUE_LEVELS 16u +#define NR_SENTINELS NR_QUEUE_LEVELS * 3 + +#define WRITEBACK_PERIOD HZ struct queue { + unsigned nr_elts; + bool current_writeback_sentinels; + unsigned long next_writeback; struct list_head qs[NR_QUEUE_LEVELS]; + struct list_head sentinels[NR_SENTINELS]; }; static void queue_init(struct queue *q) { unsigned i; - for (i = 0; i < NR_QUEUE_LEVELS; i++) + q->nr_elts = 0; + q->current_writeback_sentinels = false; + q->next_writeback = 0; + for (i = 0; i < NR_QUEUE_LEVELS; i++) { INIT_LIST_HEAD(q->qs + i); + INIT_LIST_HEAD(q->sentinels + i); + INIT_LIST_HEAD(q->sentinels + NR_QUEUE_LEVELS + i); + INIT_LIST_HEAD(q->sentinels + (2 * NR_QUEUE_LEVELS) + i); + } } -/* - * Checks to see if the queue is empty. - * FIXME: reduce cpu usage. - */ -static bool queue_empty(struct queue *q) +static unsigned queue_size(struct queue *q) { - unsigned i; - - for (i = 0; i < NR_QUEUE_LEVELS; i++) - if (!list_empty(q->qs + i)) - return false; + return q->nr_elts; +} - return true; +static bool queue_empty(struct queue *q) +{ + return q->nr_elts == 0; } /* @@ -157,24 +167,19 @@ static bool queue_empty(struct queue *q) */ static void queue_push(struct queue *q, unsigned level, struct list_head *elt) { + q->nr_elts++; list_add_tail(elt, q->qs + level); } -static void queue_remove(struct list_head *elt) +static void queue_remove(struct queue *q, struct list_head *elt) { + q->nr_elts--; list_del(elt); } -/* - * Shifts all regions down one level. This has no effect on the order of - * the queue. - */ -static void queue_shift_down(struct queue *q) +static bool is_sentinel(struct queue *q, struct list_head *h) { - unsigned level; - - for (level = 1; level < NR_QUEUE_LEVELS; level++) - list_splice_init(q->qs + level, q->qs + level - 1); + return (h >= q->sentinels) && (h < (q->sentinels + NR_SENTINELS)); } /* @@ -184,10 +189,12 @@ static void queue_shift_down(struct queue *q) static struct list_head *queue_peek(struct queue *q) { unsigned level; + struct list_head *h; for (level = 0; level < NR_QUEUE_LEVELS; level++) - if (!list_empty(q->qs + level)) - return q->qs[level].next; + list_for_each(h, q->qs + level) + if (!is_sentinel(q, h)) + return h; return NULL; } @@ -197,16 +204,34 @@ static struct list_head *queue_pop(struct queue *q) struct list_head *r = queue_peek(q); if (r) { + q->nr_elts--; list_del(r); - - /* have we just emptied the bottom level? */ - if (list_empty(q->qs)) - queue_shift_down(q); } return r; } +/* + * Pops an entry from a level that is not past a sentinel. + */ +static struct list_head *queue_pop_old(struct queue *q) +{ + unsigned level; + struct list_head *h; + + for (level = 0; level < NR_QUEUE_LEVELS; level++) + list_for_each(h, q->qs + level) { + if (is_sentinel(q, h)) + break; + + q->nr_elts--; + list_del(h); + return h; + } + + return NULL; +} + static struct list_head *list_pop(struct list_head *lh) { struct list_head *r = lh->next; @@ -217,6 +242,62 @@ static struct list_head *list_pop(struct list_head *lh) return r; } +static struct list_head *writeback_sentinel(struct queue *q, unsigned level) +{ + if (q->current_writeback_sentinels) + return q->sentinels + NR_QUEUE_LEVELS + level; + else + return q->sentinels + 2 * NR_QUEUE_LEVELS + level; +} + +static void queue_update_writeback_sentinels(struct queue *q) +{ + unsigned i; + struct list_head *h; + + if (time_after(jiffies, q->next_writeback)) { + for (i = 0; i < NR_QUEUE_LEVELS; i++) { + h = writeback_sentinel(q, i); + list_del(h); + list_add_tail(h, q->qs + i); + } + + q->next_writeback = jiffies + WRITEBACK_PERIOD; + q->current_writeback_sentinels = !q->current_writeback_sentinels; + } +} + +/* + * Sometimes we want to iterate through entries that have been pushed since + * a certain event. We use sentinel entries on the queues to delimit these + * 'tick' events. + */ +static void queue_tick(struct queue *q) +{ + unsigned i; + + for (i = 0; i < NR_QUEUE_LEVELS; i++) { + list_del(q->sentinels + i); + list_add_tail(q->sentinels + i, q->qs + i); + } +} + +typedef void (*iter_fn)(struct list_head *, void *); +static void queue_iterate_tick(struct queue *q, iter_fn fn, void *context) +{ + unsigned i; + struct list_head *h; + + for (i = 0; i < NR_QUEUE_LEVELS; i++) { + list_for_each_prev(h, q->qs + i) { + if (is_sentinel(q, h)) + break; + + fn(h, context); + } + } +} + /*----------------------------------------------------------------*/ /* @@ -232,8 +313,6 @@ struct entry { */ bool dirty:1; unsigned hit_count; - unsigned generation; - unsigned tick; }; /* @@ -481,7 +560,6 @@ static bool in_cache(struct mq_policy *mq, struct entry *e) */ static void push(struct mq_policy *mq, struct entry *e) { - e->tick = mq->tick; hash_insert(mq, e); if (in_cache(mq, e)) @@ -496,7 +574,11 @@ static void push(struct mq_policy *mq, struct entry *e) */ static void del(struct mq_policy *mq, struct entry *e) { - queue_remove(&e->list); + if (in_cache(mq, e)) + queue_remove(e->dirty ? &mq->cache_dirty : &mq->cache_clean, &e->list); + else + queue_remove(&mq->pre_cache, &e->list); + hash_remove(e); } @@ -518,18 +600,24 @@ static struct entry *pop(struct mq_policy *mq, struct queue *q) return e; } -static struct entry *peek(struct queue *q) +static struct entry *pop_old(struct mq_policy *mq, struct queue *q) { - struct list_head *h = queue_peek(q); - return h ? container_of(h, struct entry, list) : NULL; + struct entry *e; + struct list_head *h = queue_pop_old(q); + + if (!h) + return NULL; + + e = container_of(h, struct entry, list); + hash_remove(e); + + return e; } -/* - * Has this entry already been updated? - */ -static bool updated_this_tick(struct mq_policy *mq, struct entry *e) +static struct entry *peek(struct queue *q) { - return mq->tick == e->tick; + struct list_head *h = queue_peek(q); + return h ? container_of(h, struct entry, list) : NULL; } /* @@ -583,20 +671,9 @@ static void check_generation(struct mq_policy *mq) * Whenever we use an entry we bump up it's hit counter, and push it to the * back to it's current level. */ -static void requeue_and_update_tick(struct mq_policy *mq, struct entry *e) +static void requeue(struct mq_policy *mq, struct entry *e) { - if (updated_this_tick(mq, e)) - return; - - e->hit_count++; - mq->hit_count++; check_generation(mq); - - /* generation adjustment, to stop the counts increasing forever. */ - /* FIXME: divide? */ - /* e->hit_count -= min(e->hit_count - 1, mq->generation - e->generation); */ - e->generation = mq->generation; - del(mq, e); push(mq, e); } @@ -703,7 +780,7 @@ static int cache_entry_found(struct mq_policy *mq, struct entry *e, struct policy_result *result) { - requeue_and_update_tick(mq, e); + requeue(mq, e); if (in_cache(mq, e)) { result->op = POLICY_HIT; @@ -740,8 +817,6 @@ static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e, new_e->oblock = e->oblock; new_e->dirty = false; new_e->hit_count = e->hit_count; - new_e->generation = e->generation; - new_e->tick = e->tick; del(mq, e); free_entry(&mq->pre_cache_pool, e); @@ -757,18 +832,16 @@ static int pre_cache_entry_found(struct mq_policy *mq, struct entry *e, int data_dir, struct policy_result *result) { int r = 0; - bool updated = updated_this_tick(mq, e); - if ((!discarded_oblock && updated) || - !should_promote(mq, e, discarded_oblock, data_dir)) { - requeue_and_update_tick(mq, e); + if (!should_promote(mq, e, discarded_oblock, data_dir)) { + requeue(mq, e); result->op = POLICY_MISS; } else if (!can_migrate) r = -EWOULDBLOCK; else { - requeue_and_update_tick(mq, e); + requeue(mq, e); r = pre_cache_to_cache(mq, e, result); } @@ -795,7 +868,6 @@ static void insert_in_pre_cache(struct mq_policy *mq, e->dirty = false; e->oblock = oblock; e->hit_count = 1; - e->generation = mq->generation; push(mq, e); } @@ -828,7 +900,6 @@ static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock, e->oblock = oblock; e->dirty = false; e->hit_count = 1; - e->generation = mq->generation; push(mq, e); result->cblock = infer_cblock(&mq->cache_pool, e); @@ -905,12 +976,37 @@ static void mq_destroy(struct dm_cache_policy *p) kfree(mq); } +static void update_pre_cache_hits(struct list_head *h, void *context) +{ + struct entry *e = container_of(h, struct entry, list); + e->hit_count++; +} + +static void update_cache_hits(struct list_head *h, void *context) +{ + struct mq_policy *mq = context; + struct entry *e = container_of(h, struct entry, list); + e->hit_count++; + mq->hit_count++; +} + static void copy_tick(struct mq_policy *mq) { - unsigned long flags; + unsigned long flags, tick; spin_lock_irqsave(&mq->tick_lock, flags); - mq->tick = mq->tick_protected; + tick = mq->tick_protected; + if (tick != mq->tick) { + queue_iterate_tick(&mq->pre_cache, update_pre_cache_hits, mq); + queue_iterate_tick(&mq->cache_dirty, update_cache_hits, mq); + queue_iterate_tick(&mq->cache_clean, update_cache_hits, mq); + mq->tick = tick; + } + + queue_tick(&mq->pre_cache); + queue_tick(&mq->cache_dirty); + queue_tick(&mq->cache_clean); + queue_update_writeback_sentinels(&mq->cache_dirty); spin_unlock_irqrestore(&mq->tick_lock, flags); } @@ -1001,7 +1097,6 @@ static int mq_load_mapping(struct dm_cache_policy *p, e->oblock = oblock; e->dirty = false; /* this gets corrected in a minute */ e->hit_count = hint_valid ? hint : 1; - e->generation = mq->generation; push(mq, e); return 0; @@ -1012,10 +1107,15 @@ static int mq_save_hints(struct mq_policy *mq, struct queue *q, { int r; unsigned level; + struct list_head *h; struct entry *e; for (level = 0; level < NR_QUEUE_LEVELS; level++) - list_for_each_entry(e, q->qs + level, list) { + list_for_each(h, q->qs + level) { + if (is_sentinel(q, h)) + continue; + + e = container_of(h, struct entry, list); r = fn(context, infer_cblock(&mq->cache_pool, e), e->oblock, e->hit_count); if (r) @@ -1087,10 +1187,27 @@ static int mq_remove_cblock(struct dm_cache_policy *p, dm_cblock_t cblock) return r; } +#define CLEAN_TARGET_PERCENTAGE 25 + +static bool clean_target_met(struct mq_policy *mq) +{ + /* + * Cache entries may not be populated. So we're cannot rely on the + * size of the clean queue. + */ + unsigned nr_clean = from_cblock(mq->cache_size) - queue_size(&mq->cache_dirty); + unsigned target = from_cblock(mq->cache_size) * CLEAN_TARGET_PERCENTAGE / 100; + + return nr_clean >= target; +} + static int __mq_writeback_work(struct mq_policy *mq, dm_oblock_t *oblock, dm_cblock_t *cblock) { - struct entry *e = pop(mq, &mq->cache_dirty); + struct entry *e = pop_old(mq, &mq->cache_dirty); + + if (!e && !clean_target_met(mq)) + e = pop(mq, &mq->cache_dirty); if (!e) return -ENODATA; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 713a96237a80..5503e43e5f28 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -228,7 +228,7 @@ static struct crypto_ablkcipher *any_tfm(struct crypt_config *cc) * * tcw: Compatible implementation of the block chaining mode used * by the TrueCrypt device encryption system (prior to version 4.1). - * For more info see: http://www.truecrypt.org + * For more info see: https://gitlab.com/cryptsetup/cryptsetup/wikis/TrueCryptOnDiskFormat * It operates on full 512 byte sectors and uses CBC * with an IV derived from initial key and the sector number. * In addition, whitening value is applied on every sector, whitening @@ -1124,15 +1124,15 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone) static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) { struct crypt_config *cc = io->cc; - struct bio *base_bio = io->base_bio; struct bio *clone; /* - * The block layer might modify the bvec array, so always - * copy the required bvecs because we need the original - * one in order to decrypt the whole bio data *afterwards*. + * We need the original biovec array in order to decrypt + * the whole bio data *afterwards* -- thanks to immutable + * biovecs we don't need to worry about the block layer + * modifying the biovec array; so leverage bio_clone_fast(). */ - clone = bio_clone_bioset(base_bio, gfp, cc->bs); + clone = bio_clone_fast(io->base_bio, gfp, cc->bs); if (!clone) return 1; @@ -1816,6 +1816,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (ret) goto bad; + ret = -EINVAL; while (opt_params--) { opt_string = dm_shift_arg(&as); if (!opt_string) { diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 42c3a27a14cc..57b6a1901c91 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -236,7 +236,7 @@ static int delay_bio(struct delay_c *dc, int delay, struct bio *bio) delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info)); delayed->context = dc; - delayed->expires = expires = jiffies + (delay * HZ / 1000); + delayed->expires = expires = jiffies + msecs_to_jiffies(delay); mutex_lock(&delayed_bios_lock); diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 37de0173b6d2..74adcd2c967e 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -289,9 +289,16 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, struct request_queue *q = bdev_get_queue(where->bdev); unsigned short logical_block_size = queue_logical_block_size(q); sector_t num_sectors; + unsigned int uninitialized_var(special_cmd_max_sectors); - /* Reject unsupported discard requests */ - if ((rw & REQ_DISCARD) && !blk_queue_discard(q)) { + /* + * Reject unsupported discard and write same requests. + */ + if (rw & REQ_DISCARD) + special_cmd_max_sectors = q->limits.max_discard_sectors; + else if (rw & REQ_WRITE_SAME) + special_cmd_max_sectors = q->limits.max_write_same_sectors; + if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) { dec_count(io, region, -EOPNOTSUPP); return; } @@ -317,7 +324,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, store_io_and_region_in_bio(bio, io, region); if (rw & REQ_DISCARD) { - num_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining); + num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; remaining -= num_sectors; } else if (rw & REQ_WRITE_SAME) { @@ -326,7 +333,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where, */ dp->get_page(dp, &page, &len, &offset); bio_add_page(bio, page, logical_block_size, offset); - num_sectors = min_t(sector_t, q->limits.max_write_same_sectors, remaining); + num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining); bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT; offset = 0; diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index c8a18e4ee9dc..720ceeb7fa9b 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1298,21 +1298,22 @@ static int table_load(struct dm_ioctl *param, size_t param_size) goto err_unlock_md_type; } - if (dm_get_md_type(md) == DM_TYPE_NONE) + 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)) { + + /* setup md->queue to reflect md's type (may block) */ + r = dm_setup_md_queue(md); + if (r) { + DMWARN("unable to set up device queue for new table."); + goto err_unlock_md_type; + } + } else if (dm_get_md_type(md) != dm_table_get_type(t)) { DMWARN("can't change device type after initial table load."); r = -EINVAL; goto err_unlock_md_type; } - /* setup md->queue to reflect md's type (may block) */ - r = dm_setup_md_queue(md); - if (r) { - DMWARN("unable to set up device queue for new table."); - goto err_unlock_md_type; - } dm_unlock_md_type(md); /* stage inactive table */ diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 03177ca0b009..058256d2eeea 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -17,7 +17,9 @@ #define DM_LOG_USERSPACE_VSN "1.3.0" -struct flush_entry { +#define FLUSH_ENTRY_POOL_SIZE 16 + +struct dm_dirty_log_flush_entry { int type; region_t region; struct list_head list; @@ -34,22 +36,14 @@ struct flush_entry { struct log_c { struct dm_target *ti; struct dm_dev *log_dev; - uint32_t region_size; - region_t region_count; - uint64_t luid; - char uuid[DM_UUID_LEN]; char *usr_argv_str; uint32_t usr_argc; - /* - * in_sync_hint gets set when doing is_remote_recovering. It - * represents the first region that needs recovery. IOW, the - * first zero bit of sync_bits. This can be useful for to limit - * traffic for calls like is_remote_recovering and get_resync_work, - * but be take care in its use for anything else. - */ - uint64_t in_sync_hint; + uint32_t region_size; + region_t region_count; + uint64_t luid; + char uuid[DM_UUID_LEN]; /* * Mark and clear requests are held until a flush is issued @@ -62,6 +56,15 @@ struct log_c { struct list_head clear_list; /* + * in_sync_hint gets set when doing is_remote_recovering. It + * represents the first region that needs recovery. IOW, the + * first zero bit of sync_bits. This can be useful for to limit + * traffic for calls like is_remote_recovering and get_resync_work, + * but be take care in its use for anything else. + */ + uint64_t in_sync_hint; + + /* * Workqueue for flush of clear region requests. */ struct workqueue_struct *dmlog_wq; @@ -72,19 +75,11 @@ struct log_c { * Combine userspace flush and mark requests for efficiency. */ uint32_t integrated_flush; -}; - -static mempool_t *flush_entry_pool; -static void *flush_entry_alloc(gfp_t gfp_mask, void *pool_data) -{ - return kmalloc(sizeof(struct flush_entry), gfp_mask); -} + mempool_t *flush_entry_pool; +}; -static void flush_entry_free(void *element, void *pool_data) -{ - kfree(element); -} +static struct kmem_cache *_flush_entry_cache; static int userspace_do_request(struct log_c *lc, const char *uuid, int request_type, char *data, size_t data_size, @@ -254,6 +249,14 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, goto out; } + lc->flush_entry_pool = mempool_create_slab_pool(FLUSH_ENTRY_POOL_SIZE, + _flush_entry_cache); + if (!lc->flush_entry_pool) { + DMERR("Failed to create flush_entry_pool"); + r = -ENOMEM; + goto out; + } + /* * Send table string and get back any opened device. */ @@ -310,6 +313,8 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, out: kfree(devices_rdata); if (r) { + if (lc->flush_entry_pool) + mempool_destroy(lc->flush_entry_pool); kfree(lc); kfree(ctr_str); } else { @@ -338,6 +343,8 @@ static void userspace_dtr(struct dm_dirty_log *log) if (lc->log_dev) dm_put_device(lc->ti, lc->log_dev); + mempool_destroy(lc->flush_entry_pool); + kfree(lc->usr_argv_str); kfree(lc); @@ -461,7 +468,7 @@ static int userspace_in_sync(struct dm_dirty_log *log, region_t region, static int flush_one_by_one(struct log_c *lc, struct list_head *flush_list) { int r = 0; - struct flush_entry *fe; + struct dm_dirty_log_flush_entry *fe; list_for_each_entry(fe, flush_list, list) { r = userspace_do_request(lc, lc->uuid, fe->type, @@ -481,7 +488,7 @@ static int flush_by_group(struct log_c *lc, struct list_head *flush_list, int r = 0; int count; uint32_t type = 0; - struct flush_entry *fe, *tmp_fe; + struct dm_dirty_log_flush_entry *fe, *tmp_fe; LIST_HEAD(tmp_list); uint64_t group[MAX_FLUSH_GROUP_COUNT]; @@ -563,7 +570,8 @@ static int userspace_flush(struct dm_dirty_log *log) LIST_HEAD(clear_list); int mark_list_is_empty; int clear_list_is_empty; - struct flush_entry *fe, *tmp_fe; + struct dm_dirty_log_flush_entry *fe, *tmp_fe; + mempool_t *flush_entry_pool = lc->flush_entry_pool; spin_lock_irqsave(&lc->flush_lock, flags); list_splice_init(&lc->mark_list, &mark_list); @@ -643,10 +651,10 @@ static void userspace_mark_region(struct dm_dirty_log *log, region_t region) { unsigned long flags; struct log_c *lc = log->context; - struct flush_entry *fe; + struct dm_dirty_log_flush_entry *fe; /* Wait for an allocation, but _never_ fail */ - fe = mempool_alloc(flush_entry_pool, GFP_NOIO); + fe = mempool_alloc(lc->flush_entry_pool, GFP_NOIO); BUG_ON(!fe); spin_lock_irqsave(&lc->flush_lock, flags); @@ -672,7 +680,7 @@ static void userspace_clear_region(struct dm_dirty_log *log, region_t region) { unsigned long flags; struct log_c *lc = log->context; - struct flush_entry *fe; + struct dm_dirty_log_flush_entry *fe; /* * If we fail to allocate, we skip the clearing of @@ -680,7 +688,7 @@ static void userspace_clear_region(struct dm_dirty_log *log, region_t region) * to cause the region to be resync'ed when the * device is activated next time. */ - fe = mempool_alloc(flush_entry_pool, GFP_ATOMIC); + fe = mempool_alloc(lc->flush_entry_pool, GFP_ATOMIC); if (!fe) { DMERR("Failed to allocate memory to clear region."); return; @@ -733,7 +741,6 @@ static int userspace_get_resync_work(struct dm_dirty_log *log, region_t *region) static void userspace_set_region_sync(struct dm_dirty_log *log, region_t region, int in_sync) { - int r; struct log_c *lc = log->context; struct { region_t r; @@ -743,12 +750,12 @@ static void userspace_set_region_sync(struct dm_dirty_log *log, pkg.r = region; pkg.i = (int64_t)in_sync; - r = userspace_do_request(lc, lc->uuid, DM_ULOG_SET_REGION_SYNC, - (char *)&pkg, sizeof(pkg), NULL, NULL); + (void) userspace_do_request(lc, lc->uuid, DM_ULOG_SET_REGION_SYNC, + (char *)&pkg, sizeof(pkg), NULL, NULL); /* * It would be nice to be able to report failures. - * However, it is easy emough to detect and resolve. + * However, it is easy enough to detect and resolve. */ return; } @@ -886,18 +893,16 @@ static int __init userspace_dirty_log_init(void) { int r = 0; - flush_entry_pool = mempool_create(100, flush_entry_alloc, - flush_entry_free, NULL); - - if (!flush_entry_pool) { - DMWARN("Unable to create flush_entry_pool: No memory."); + _flush_entry_cache = KMEM_CACHE(dm_dirty_log_flush_entry, 0); + if (!_flush_entry_cache) { + DMWARN("Unable to create flush_entry_cache: No memory."); return -ENOMEM; } r = dm_ulog_tfr_init(); if (r) { DMWARN("Unable to initialize userspace log communications"); - mempool_destroy(flush_entry_pool); + kmem_cache_destroy(_flush_entry_cache); return r; } @@ -905,7 +910,7 @@ static int __init userspace_dirty_log_init(void) if (r) { DMWARN("Couldn't register userspace dirty log type"); dm_ulog_tfr_exit(); - mempool_destroy(flush_entry_pool); + kmem_cache_destroy(_flush_entry_cache); return r; } @@ -917,7 +922,7 @@ static void __exit userspace_dirty_log_exit(void) { dm_dirty_log_type_unregister(&_userspace_type); dm_ulog_tfr_exit(); - mempool_destroy(flush_entry_pool); + kmem_cache_destroy(_flush_entry_cache); DMINFO("version " DM_LOG_USERSPACE_VSN " unloaded"); return; diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c index 39ad9664d397..fdf8ec304f8d 100644 --- a/drivers/md/dm-log-userspace-transfer.c +++ b/drivers/md/dm-log-userspace-transfer.c @@ -172,6 +172,7 @@ int dm_consult_userspace(const char *uuid, uint64_t luid, int request_type, char *rdata, size_t *rdata_size) { int r = 0; + unsigned long tmo; size_t dummy = 0; int overhead_size = sizeof(struct dm_ulog_request) + sizeof(struct cn_msg); struct dm_ulog_request *tfr = prealloced_ulog_tfr; @@ -236,11 +237,11 @@ resend: goto out; } - r = wait_for_completion_timeout(&(pkg.complete), DM_ULOG_RETRY_TIMEOUT); + tmo = wait_for_completion_timeout(&(pkg.complete), DM_ULOG_RETRY_TIMEOUT); spin_lock(&receiving_list_lock); list_del_init(&(pkg.list)); spin_unlock(&receiving_list_lock); - if (!r) { + if (!tmo) { DMWARN("[%s] Request timed out: [%u/%u] - retrying", (strlen(uuid) > 8) ? (uuid + (strlen(uuid) - 8)) : (uuid), diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c new file mode 100644 index 000000000000..93e08446a87d --- /dev/null +++ b/drivers/md/dm-log-writes.c @@ -0,0 +1,825 @@ +/* + * Copyright (C) 2014 Facebook. All rights reserved. + * + * This file is released under the GPL. + */ + +#include <linux/device-mapper.h> + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/blkdev.h> +#include <linux/bio.h> +#include <linux/slab.h> +#include <linux/kthread.h> +#include <linux/freezer.h> + +#define DM_MSG_PREFIX "log-writes" + +/* + * This target will sequentially log all writes to the target device onto the + * log device. This is helpful for replaying writes to check for fs consistency + * at all times. This target provides a mechanism to mark specific events to + * check data at a later time. So for example you would: + * + * write data + * fsync + * dmsetup message /dev/whatever mark mymark + * unmount /mnt/test + * + * Then replay the log up to mymark and check the contents of the replay to + * verify it matches what was written. + * + * We log writes only after they have been flushed, this makes the log describe + * close to the order in which the data hits the actual disk, not its cache. So + * for example the following sequence (W means write, C means complete) + * + * Wa,Wb,Wc,Cc,Ca,FLUSH,FUAd,Cb,CFLUSH,CFUAd + * + * Would result in the log looking like this: + * + * c,a,flush,fuad,b,<other writes>,<next flush> + * + * This is meant to help expose problems where file systems do not properly wait + * on data being written before invoking a FLUSH. FUA bypasses cache so once it + * completes it is added to the log as it should be on disk. + * + * We treat DISCARDs as if they don't bypass cache so that they are logged in + * order of completion along with the normal writes. If we didn't do it this + * way we would process all the discards first and then write all the data, when + * in fact we want to do the data and the discard in the order that they + * completed. + */ +#define LOG_FLUSH_FLAG (1 << 0) +#define LOG_FUA_FLAG (1 << 1) +#define LOG_DISCARD_FLAG (1 << 2) +#define LOG_MARK_FLAG (1 << 3) + +#define WRITE_LOG_VERSION 1 +#define WRITE_LOG_MAGIC 0x6a736677736872 + +/* + * The disk format for this is braindead simple. + * + * At byte 0 we have our super, followed by the following sequence for + * nr_entries: + * + * [ 1 sector ][ entry->nr_sectors ] + * [log_write_entry][ data written ] + * + * The log_write_entry takes up a full sector so we can have arbitrary length + * marks and it leaves us room for extra content in the future. + */ + +/* + * Basic info about the log for userspace. + */ +struct log_write_super { + __le64 magic; + __le64 version; + __le64 nr_entries; + __le32 sectorsize; +}; + +/* + * sector - the sector we wrote. + * nr_sectors - the number of sectors we wrote. + * flags - flags for this log entry. + * data_len - the size of the data in this log entry, this is for private log + * entry stuff, the MARK data provided by userspace for example. + */ +struct log_write_entry { + __le64 sector; + __le64 nr_sectors; + __le64 flags; + __le64 data_len; +}; + +struct log_writes_c { + struct dm_dev *dev; + struct dm_dev *logdev; + u64 logged_entries; + u32 sectorsize; + atomic_t io_blocks; + atomic_t pending_blocks; + sector_t next_sector; + sector_t end_sector; + bool logging_enabled; + bool device_supports_discard; + spinlock_t blocks_lock; + struct list_head unflushed_blocks; + struct list_head logging_blocks; + wait_queue_head_t wait; + struct task_struct *log_kthread; +}; + +struct pending_block { + int vec_cnt; + u64 flags; + sector_t sector; + sector_t nr_sectors; + char *data; + u32 datalen; + struct list_head list; + struct bio_vec vecs[0]; +}; + +struct per_bio_data { + struct pending_block *block; +}; + +static void put_pending_block(struct log_writes_c *lc) +{ + if (atomic_dec_and_test(&lc->pending_blocks)) { + smp_mb__after_atomic(); + if (waitqueue_active(&lc->wait)) + wake_up(&lc->wait); + } +} + +static void put_io_block(struct log_writes_c *lc) +{ + if (atomic_dec_and_test(&lc->io_blocks)) { + smp_mb__after_atomic(); + if (waitqueue_active(&lc->wait)) + wake_up(&lc->wait); + } +} + +static void log_end_io(struct bio *bio, int err) +{ + struct log_writes_c *lc = bio->bi_private; + struct bio_vec *bvec; + int i; + + if (err) { + unsigned long flags; + + DMERR("Error writing log block, error=%d", err); + spin_lock_irqsave(&lc->blocks_lock, flags); + lc->logging_enabled = false; + spin_unlock_irqrestore(&lc->blocks_lock, flags); + } + + bio_for_each_segment_all(bvec, bio, i) + __free_page(bvec->bv_page); + + put_io_block(lc); + bio_put(bio); +} + +/* + * Meant to be called if there is an error, it will free all the pages + * associated with the block. + */ +static void free_pending_block(struct log_writes_c *lc, + struct pending_block *block) +{ + int i; + + for (i = 0; i < block->vec_cnt; i++) { + if (block->vecs[i].bv_page) + __free_page(block->vecs[i].bv_page); + } + kfree(block->data); + kfree(block); + put_pending_block(lc); +} + +static int write_metadata(struct log_writes_c *lc, void *entry, + size_t entrylen, void *data, size_t datalen, + sector_t sector) +{ + struct bio *bio; + struct page *page; + void *ptr; + size_t ret; + + bio = bio_alloc(GFP_KERNEL, 1); + if (!bio) { + DMERR("Couldn't alloc log bio"); + goto error; + } + bio->bi_iter.bi_size = 0; + bio->bi_iter.bi_sector = sector; + bio->bi_bdev = lc->logdev->bdev; + bio->bi_end_io = log_end_io; + bio->bi_private = lc; + set_bit(BIO_UPTODATE, &bio->bi_flags); + + page = alloc_page(GFP_KERNEL); + if (!page) { + DMERR("Couldn't alloc log page"); + bio_put(bio); + goto error; + } + + ptr = kmap_atomic(page); + memcpy(ptr, entry, entrylen); + if (datalen) + memcpy(ptr + entrylen, data, datalen); + memset(ptr + entrylen + datalen, 0, + lc->sectorsize - entrylen - datalen); + kunmap_atomic(ptr); + + ret = bio_add_page(bio, page, lc->sectorsize, 0); + if (ret != lc->sectorsize) { + DMERR("Couldn't add page to the log block"); + goto error_bio; + } + submit_bio(WRITE, bio); + return 0; +error_bio: + bio_put(bio); + __free_page(page); +error: + put_io_block(lc); + return -1; +} + +static int log_one_block(struct log_writes_c *lc, + struct pending_block *block, sector_t sector) +{ + struct bio *bio; + struct log_write_entry entry; + size_t ret; + int i; + + entry.sector = cpu_to_le64(block->sector); + entry.nr_sectors = cpu_to_le64(block->nr_sectors); + entry.flags = cpu_to_le64(block->flags); + entry.data_len = cpu_to_le64(block->datalen); + if (write_metadata(lc, &entry, sizeof(entry), block->data, + block->datalen, sector)) { + free_pending_block(lc, block); + return -1; + } + + if (!block->vec_cnt) + goto out; + sector++; + + bio = bio_alloc(GFP_KERNEL, block->vec_cnt); + if (!bio) { + DMERR("Couldn't alloc log bio"); + goto error; + } + atomic_inc(&lc->io_blocks); + bio->bi_iter.bi_size = 0; + bio->bi_iter.bi_sector = sector; + bio->bi_bdev = lc->logdev->bdev; + bio->bi_end_io = log_end_io; + bio->bi_private = lc; + set_bit(BIO_UPTODATE, &bio->bi_flags); + + for (i = 0; i < block->vec_cnt; i++) { + /* + * The page offset is always 0 because we allocate a new page + * for every bvec in the original bio for simplicity sake. + */ + ret = bio_add_page(bio, block->vecs[i].bv_page, + block->vecs[i].bv_len, 0); + if (ret != block->vecs[i].bv_len) { + atomic_inc(&lc->io_blocks); + submit_bio(WRITE, bio); + bio = bio_alloc(GFP_KERNEL, block->vec_cnt - i); + if (!bio) { + DMERR("Couldn't alloc log bio"); + goto error; + } + bio->bi_iter.bi_size = 0; + bio->bi_iter.bi_sector = sector; + bio->bi_bdev = lc->logdev->bdev; + bio->bi_end_io = log_end_io; + bio->bi_private = lc; + set_bit(BIO_UPTODATE, &bio->bi_flags); + + ret = bio_add_page(bio, block->vecs[i].bv_page, + block->vecs[i].bv_len, 0); + if (ret != block->vecs[i].bv_len) { + DMERR("Couldn't add page on new bio?"); + bio_put(bio); + goto error; + } + } + sector += block->vecs[i].bv_len >> SECTOR_SHIFT; + } + submit_bio(WRITE, bio); +out: + kfree(block->data); + kfree(block); + put_pending_block(lc); + return 0; +error: + free_pending_block(lc, block); + put_io_block(lc); + return -1; +} + +static int log_super(struct log_writes_c *lc) +{ + struct log_write_super super; + + super.magic = cpu_to_le64(WRITE_LOG_MAGIC); + super.version = cpu_to_le64(WRITE_LOG_VERSION); + super.nr_entries = cpu_to_le64(lc->logged_entries); + super.sectorsize = cpu_to_le32(lc->sectorsize); + + if (write_metadata(lc, &super, sizeof(super), NULL, 0, 0)) { + DMERR("Couldn't write super"); + return -1; + } + + return 0; +} + +static inline sector_t logdev_last_sector(struct log_writes_c *lc) +{ + return i_size_read(lc->logdev->bdev->bd_inode) >> SECTOR_SHIFT; +} + +static int log_writes_kthread(void *arg) +{ + struct log_writes_c *lc = (struct log_writes_c *)arg; + sector_t sector = 0; + + while (!kthread_should_stop()) { + bool super = false; + bool logging_enabled; + struct pending_block *block = NULL; + int ret; + + spin_lock_irq(&lc->blocks_lock); + if (!list_empty(&lc->logging_blocks)) { + block = list_first_entry(&lc->logging_blocks, + struct pending_block, list); + list_del_init(&block->list); + if (!lc->logging_enabled) + goto next; + + sector = lc->next_sector; + if (block->flags & LOG_DISCARD_FLAG) + lc->next_sector++; + else + lc->next_sector += block->nr_sectors + 1; + + /* + * Apparently the size of the device may not be known + * right away, so handle this properly. + */ + if (!lc->end_sector) + lc->end_sector = logdev_last_sector(lc); + if (lc->end_sector && + lc->next_sector >= lc->end_sector) { + DMERR("Ran out of space on the logdev"); + lc->logging_enabled = false; + goto next; + } + lc->logged_entries++; + atomic_inc(&lc->io_blocks); + + super = (block->flags & (LOG_FUA_FLAG | LOG_MARK_FLAG)); + if (super) + atomic_inc(&lc->io_blocks); + } +next: + logging_enabled = lc->logging_enabled; + spin_unlock_irq(&lc->blocks_lock); + if (block) { + if (logging_enabled) { + ret = log_one_block(lc, block, sector); + if (!ret && super) + ret = log_super(lc); + if (ret) { + spin_lock_irq(&lc->blocks_lock); + lc->logging_enabled = false; + spin_unlock_irq(&lc->blocks_lock); + } + } else + free_pending_block(lc, block); + continue; + } + + if (!try_to_freeze()) { + set_current_state(TASK_INTERRUPTIBLE); + if (!kthread_should_stop() && + !atomic_read(&lc->pending_blocks)) + schedule(); + __set_current_state(TASK_RUNNING); + } + } + return 0; +} + +/* + * Construct a log-writes mapping: + * log-writes <dev_path> <log_dev_path> + */ +static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) +{ + struct log_writes_c *lc; + struct dm_arg_set as; + const char *devname, *logdevname; + + as.argc = argc; + as.argv = argv; + + if (argc < 2) { + ti->error = "Invalid argument count"; + return -EINVAL; + } + + lc = kzalloc(sizeof(struct log_writes_c), GFP_KERNEL); + if (!lc) { + ti->error = "Cannot allocate context"; + return -ENOMEM; + } + spin_lock_init(&lc->blocks_lock); + INIT_LIST_HEAD(&lc->unflushed_blocks); + INIT_LIST_HEAD(&lc->logging_blocks); + init_waitqueue_head(&lc->wait); + lc->sectorsize = 1 << SECTOR_SHIFT; + atomic_set(&lc->io_blocks, 0); + atomic_set(&lc->pending_blocks, 0); + + devname = dm_shift_arg(&as); + if (dm_get_device(ti, devname, dm_table_get_mode(ti->table), &lc->dev)) { + ti->error = "Device lookup failed"; + goto bad; + } + + logdevname = dm_shift_arg(&as); + if (dm_get_device(ti, logdevname, dm_table_get_mode(ti->table), &lc->logdev)) { + ti->error = "Log device lookup failed"; + dm_put_device(ti, lc->dev); + goto bad; + } + + lc->log_kthread = kthread_run(log_writes_kthread, lc, "log-write"); + if (!lc->log_kthread) { + ti->error = "Couldn't alloc kthread"; + dm_put_device(ti, lc->dev); + dm_put_device(ti, lc->logdev); + goto bad; + } + + /* We put the super at sector 0, start logging at sector 1 */ + lc->next_sector = 1; + lc->logging_enabled = true; + lc->end_sector = logdev_last_sector(lc); + lc->device_supports_discard = true; + + ti->num_flush_bios = 1; + ti->flush_supported = true; + ti->num_discard_bios = 1; + ti->discards_supported = true; + ti->per_bio_data_size = sizeof(struct per_bio_data); + ti->private = lc; + return 0; + +bad: + kfree(lc); + return -EINVAL; +} + +static int log_mark(struct log_writes_c *lc, char *data) +{ + struct pending_block *block; + size_t maxsize = lc->sectorsize - sizeof(struct log_write_entry); + + block = kzalloc(sizeof(struct pending_block), GFP_KERNEL); + if (!block) { + DMERR("Error allocating pending block"); + return -ENOMEM; + } + + block->data = kstrndup(data, maxsize, GFP_KERNEL); + if (!block->data) { + DMERR("Error copying mark data"); + kfree(block); + return -ENOMEM; + } + atomic_inc(&lc->pending_blocks); + block->datalen = strlen(block->data); + block->flags |= LOG_MARK_FLAG; + spin_lock_irq(&lc->blocks_lock); + list_add_tail(&block->list, &lc->logging_blocks); + spin_unlock_irq(&lc->blocks_lock); + wake_up_process(lc->log_kthread); + return 0; +} + +static void log_writes_dtr(struct dm_target *ti) +{ + struct log_writes_c *lc = ti->private; + + spin_lock_irq(&lc->blocks_lock); + list_splice_init(&lc->unflushed_blocks, &lc->logging_blocks); + spin_unlock_irq(&lc->blocks_lock); + + /* + * This is just nice to have since it'll update the super to include the + * unflushed blocks, if it fails we don't really care. + */ + log_mark(lc, "dm-log-writes-end"); + wake_up_process(lc->log_kthread); + wait_event(lc->wait, !atomic_read(&lc->io_blocks) && + !atomic_read(&lc->pending_blocks)); + kthread_stop(lc->log_kthread); + + WARN_ON(!list_empty(&lc->logging_blocks)); + WARN_ON(!list_empty(&lc->unflushed_blocks)); + dm_put_device(ti, lc->dev); + dm_put_device(ti, lc->logdev); + kfree(lc); +} + +static void normal_map_bio(struct dm_target *ti, struct bio *bio) +{ + struct log_writes_c *lc = ti->private; + + bio->bi_bdev = lc->dev->bdev; +} + +static int log_writes_map(struct dm_target *ti, struct bio *bio) +{ + struct log_writes_c *lc = ti->private; + struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); + struct pending_block *block; + struct bvec_iter iter; + struct bio_vec bv; + size_t alloc_size; + int i = 0; + bool flush_bio = (bio->bi_rw & REQ_FLUSH); + bool fua_bio = (bio->bi_rw & REQ_FUA); + bool discard_bio = (bio->bi_rw & REQ_DISCARD); + + pb->block = NULL; + + /* Don't bother doing anything if logging has been disabled */ + if (!lc->logging_enabled) + goto map_bio; + + /* + * Map reads as normal. + */ + if (bio_data_dir(bio) == READ) + goto map_bio; + + /* No sectors and not a flush? Don't care */ + if (!bio_sectors(bio) && !flush_bio) + goto map_bio; + + /* + * Discards will have bi_size set but there's no actual data, so just + * allocate the size of the pending block. + */ + if (discard_bio) + alloc_size = sizeof(struct pending_block); + else + alloc_size = sizeof(struct pending_block) + sizeof(struct bio_vec) * bio_segments(bio); + + block = kzalloc(alloc_size, GFP_NOIO); + if (!block) { + DMERR("Error allocating pending block"); + spin_lock_irq(&lc->blocks_lock); + lc->logging_enabled = false; + spin_unlock_irq(&lc->blocks_lock); + return -ENOMEM; + } + INIT_LIST_HEAD(&block->list); + pb->block = block; + atomic_inc(&lc->pending_blocks); + + if (flush_bio) + block->flags |= LOG_FLUSH_FLAG; + if (fua_bio) + block->flags |= LOG_FUA_FLAG; + if (discard_bio) + block->flags |= LOG_DISCARD_FLAG; + + block->sector = bio->bi_iter.bi_sector; + block->nr_sectors = bio_sectors(bio); + + /* We don't need the data, just submit */ + if (discard_bio) { + WARN_ON(flush_bio || fua_bio); + if (lc->device_supports_discard) + goto map_bio; + bio_endio(bio, 0); + return DM_MAPIO_SUBMITTED; + } + + /* Flush bio, splice the unflushed blocks onto this list and submit */ + if (flush_bio && !bio_sectors(bio)) { + spin_lock_irq(&lc->blocks_lock); + list_splice_init(&lc->unflushed_blocks, &block->list); + spin_unlock_irq(&lc->blocks_lock); + goto map_bio; + } + + /* + * We will write this bio somewhere else way later so we need to copy + * the actual contents into new pages so we know the data will always be + * there. + * + * We do this because this could be a bio from O_DIRECT in which case we + * can't just hold onto the page until some later point, we have to + * manually copy the contents. + */ + bio_for_each_segment(bv, bio, iter) { + struct page *page; + void *src, *dst; + + page = alloc_page(GFP_NOIO); + if (!page) { + DMERR("Error allocing page"); + free_pending_block(lc, block); + spin_lock_irq(&lc->blocks_lock); + lc->logging_enabled = false; + spin_unlock_irq(&lc->blocks_lock); + return -ENOMEM; + } + + src = kmap_atomic(bv.bv_page); + dst = kmap_atomic(page); + memcpy(dst, src + bv.bv_offset, bv.bv_len); + kunmap_atomic(dst); + kunmap_atomic(src); + block->vecs[i].bv_page = page; + block->vecs[i].bv_len = bv.bv_len; + block->vec_cnt++; + i++; + } + + /* Had a flush with data in it, weird */ + if (flush_bio) { + spin_lock_irq(&lc->blocks_lock); + list_splice_init(&lc->unflushed_blocks, &block->list); + spin_unlock_irq(&lc->blocks_lock); + } +map_bio: + normal_map_bio(ti, bio); + return DM_MAPIO_REMAPPED; +} + +static int normal_end_io(struct dm_target *ti, struct bio *bio, int error) +{ + struct log_writes_c *lc = ti->private; + struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); + + if (bio_data_dir(bio) == WRITE && pb->block) { + struct pending_block *block = pb->block; + unsigned long flags; + + spin_lock_irqsave(&lc->blocks_lock, flags); + if (block->flags & LOG_FLUSH_FLAG) { + list_splice_tail_init(&block->list, &lc->logging_blocks); + list_add_tail(&block->list, &lc->logging_blocks); + wake_up_process(lc->log_kthread); + } else if (block->flags & LOG_FUA_FLAG) { + list_add_tail(&block->list, &lc->logging_blocks); + wake_up_process(lc->log_kthread); + } else + list_add_tail(&block->list, &lc->unflushed_blocks); + spin_unlock_irqrestore(&lc->blocks_lock, flags); + } + + return error; +} + +/* + * INFO format: <logged entries> <highest allocated sector> + */ +static void log_writes_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, + unsigned maxlen) +{ + unsigned sz = 0; + struct log_writes_c *lc = ti->private; + + switch (type) { + case STATUSTYPE_INFO: + DMEMIT("%llu %llu", lc->logged_entries, + (unsigned long long)lc->next_sector - 1); + if (!lc->logging_enabled) + DMEMIT(" logging_disabled"); + break; + + case STATUSTYPE_TABLE: + DMEMIT("%s %s", lc->dev->name, lc->logdev->name); + break; + } +} + +static int log_writes_ioctl(struct dm_target *ti, unsigned int cmd, + unsigned long arg) +{ + struct log_writes_c *lc = ti->private; + struct dm_dev *dev = lc->dev; + int r = 0; + + /* + * Only pass ioctls through if the device sizes match exactly. + */ + if (ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT) + r = scsi_verify_blk_ioctl(NULL, cmd); + + return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg); +} + +static int log_writes_merge(struct dm_target *ti, struct bvec_merge_data *bvm, + struct bio_vec *biovec, int max_size) +{ + struct log_writes_c *lc = ti->private; + struct request_queue *q = bdev_get_queue(lc->dev->bdev); + + if (!q->merge_bvec_fn) + return max_size; + + bvm->bi_bdev = lc->dev->bdev; + bvm->bi_sector = dm_target_offset(ti, bvm->bi_sector); + + return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); +} + +static int log_writes_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, + void *data) +{ + struct log_writes_c *lc = ti->private; + + return fn(ti, lc->dev, 0, ti->len, data); +} + +/* + * Messages supported: + * mark <mark data> - specify the marked data. + */ +static int log_writes_message(struct dm_target *ti, unsigned argc, char **argv) +{ + int r = -EINVAL; + struct log_writes_c *lc = ti->private; + + if (argc != 2) { + DMWARN("Invalid log-writes message arguments, expect 2 arguments, got %d", argc); + return r; + } + + if (!strcasecmp(argv[0], "mark")) + r = log_mark(lc, argv[1]); + else + DMWARN("Unrecognised log writes target message received: %s", argv[0]); + + return r; +} + +static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limits) +{ + struct log_writes_c *lc = ti->private; + struct request_queue *q = bdev_get_queue(lc->dev->bdev); + + if (!q || !blk_queue_discard(q)) { + lc->device_supports_discard = false; + limits->discard_granularity = 1 << SECTOR_SHIFT; + limits->max_discard_sectors = (UINT_MAX >> SECTOR_SHIFT); + } +} + +static struct target_type log_writes_target = { + .name = "log-writes", + .version = {1, 0, 0}, + .module = THIS_MODULE, + .ctr = log_writes_ctr, + .dtr = log_writes_dtr, + .map = log_writes_map, + .end_io = normal_end_io, + .status = log_writes_status, + .ioctl = log_writes_ioctl, + .merge = log_writes_merge, + .message = log_writes_message, + .iterate_devices = log_writes_iterate_devices, + .io_hints = log_writes_io_hints, +}; + +static int __init dm_log_writes_init(void) +{ + int r = dm_register_target(&log_writes_target); + + if (r < 0) + DMERR("register failed %d", r); + + return r; +} + +static void __exit dm_log_writes_exit(void) +{ + dm_unregister_target(&log_writes_target); +} + +module_init(dm_log_writes_init); +module_exit(dm_log_writes_exit); + +MODULE_DESCRIPTION(DM_NAME " log writes target"); +MODULE_AUTHOR("Josef Bacik <jbacik@fb.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index d376dc87716e..63953477a07c 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -428,7 +428,7 @@ static int __multipath_map(struct dm_target *ti, struct request *clone, } else { /* blk-mq request-based interface */ *__clone = blk_get_request(bdev_get_queue(bdev), - rq_data_dir(rq), GFP_KERNEL); + rq_data_dir(rq), GFP_ATOMIC); if (IS_ERR(*__clone)) /* ENOMEM, requeue */ return r; @@ -1627,7 +1627,7 @@ static int __pgpath_busy(struct pgpath *pgpath) { struct request_queue *q = bdev_get_queue(pgpath->path.dev->bdev); - return dm_underlying_device_busy(q); + return blk_lld_busy(q); } /* @@ -1703,7 +1703,7 @@ out: *---------------------------------------------------------------*/ static struct target_type multipath_target = { .name = "multipath", - .version = {1, 8, 0}, + .version = {1, 9, 0}, .module = THIS_MODULE, .ctr = multipath_ctr, .dtr = multipath_dtr, diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 8b204ae216ab..f83a0f3fc365 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -20,6 +20,8 @@ #include <linux/log2.h> #include <linux/dm-kcopyd.h> +#include "dm.h" + #include "dm-exception-store.h" #define DM_MSG_PREFIX "snapshots" @@ -291,12 +293,23 @@ struct origin { }; /* + * This structure is allocated for each origin target + */ +struct dm_origin { + struct dm_dev *dev; + struct dm_target *ti; + unsigned split_boundary; + struct list_head hash_list; +}; + +/* * Size of the hash table for origin volumes. If we make this * the size of the minors list then it should be nearly perfect */ #define ORIGIN_HASH_SIZE 256 #define ORIGIN_MASK 0xFF static struct list_head *_origins; +static struct list_head *_dm_origins; static struct rw_semaphore _origins_lock; static DECLARE_WAIT_QUEUE_HEAD(_pending_exceptions_done); @@ -310,12 +323,22 @@ static int init_origin_hash(void) _origins = kmalloc(ORIGIN_HASH_SIZE * sizeof(struct list_head), GFP_KERNEL); if (!_origins) { - DMERR("unable to allocate memory"); + DMERR("unable to allocate memory for _origins"); return -ENOMEM; } - for (i = 0; i < ORIGIN_HASH_SIZE; i++) INIT_LIST_HEAD(_origins + i); + + _dm_origins = kmalloc(ORIGIN_HASH_SIZE * sizeof(struct list_head), + GFP_KERNEL); + if (!_dm_origins) { + DMERR("unable to allocate memory for _dm_origins"); + kfree(_origins); + return -ENOMEM; + } + for (i = 0; i < ORIGIN_HASH_SIZE; i++) + INIT_LIST_HEAD(_dm_origins + i); + init_rwsem(&_origins_lock); return 0; @@ -324,6 +347,7 @@ static int init_origin_hash(void) static void exit_origin_hash(void) { kfree(_origins); + kfree(_dm_origins); } static unsigned origin_hash(struct block_device *bdev) @@ -350,6 +374,30 @@ static void __insert_origin(struct origin *o) list_add_tail(&o->hash_list, sl); } +static struct dm_origin *__lookup_dm_origin(struct block_device *origin) +{ + struct list_head *ol; + struct dm_origin *o; + + ol = &_dm_origins[origin_hash(origin)]; + list_for_each_entry (o, ol, hash_list) + if (bdev_equal(o->dev->bdev, origin)) + return o; + + return NULL; +} + +static void __insert_dm_origin(struct dm_origin *o) +{ + struct list_head *sl = &_dm_origins[origin_hash(o->dev->bdev)]; + list_add_tail(&o->hash_list, sl); +} + +static void __remove_dm_origin(struct dm_origin *o) +{ + list_del(&o->hash_list); +} + /* * _origins_lock must be held when calling this function. * Returns number of snapshots registered using the supplied cow device, plus: @@ -1840,9 +1888,40 @@ static int snapshot_preresume(struct dm_target *ti) static void snapshot_resume(struct dm_target *ti) { struct dm_snapshot *s = ti->private; - struct dm_snapshot *snap_src = NULL, *snap_dest = NULL; + struct dm_snapshot *snap_src = NULL, *snap_dest = NULL, *snap_merging = NULL; + struct dm_origin *o; + struct mapped_device *origin_md = NULL; + bool must_restart_merging = false; down_read(&_origins_lock); + + o = __lookup_dm_origin(s->origin->bdev); + if (o) + origin_md = dm_table_get_md(o->ti->table); + if (!origin_md) { + (void) __find_snapshots_sharing_cow(s, NULL, NULL, &snap_merging); + if (snap_merging) + origin_md = dm_table_get_md(snap_merging->ti->table); + } + if (origin_md == dm_table_get_md(ti->table)) + origin_md = NULL; + if (origin_md) { + if (dm_hold(origin_md)) + origin_md = NULL; + } + + up_read(&_origins_lock); + + if (origin_md) { + dm_internal_suspend_fast(origin_md); + if (snap_merging && test_bit(RUNNING_MERGE, &snap_merging->state_bits)) { + must_restart_merging = true; + stop_merge(snap_merging); + } + } + + down_read(&_origins_lock); + (void) __find_snapshots_sharing_cow(s, &snap_src, &snap_dest, NULL); if (snap_src && snap_dest) { down_write(&snap_src->lock); @@ -1851,8 +1930,16 @@ static void snapshot_resume(struct dm_target *ti) up_write(&snap_dest->lock); up_write(&snap_src->lock); } + up_read(&_origins_lock); + if (origin_md) { + if (must_restart_merging) + start_merge(snap_merging); + dm_internal_resume_fast(origin_md); + dm_put(origin_md); + } + /* Now we have correct chunk size, reregister */ reregister_snapshot(s); @@ -2133,11 +2220,6 @@ static int origin_write_extent(struct dm_snapshot *merging_snap, * Origin: maps a linear range of a device, with hooks for snapshotting. */ -struct dm_origin { - struct dm_dev *dev; - unsigned split_boundary; -}; - /* * Construct an origin mapping: <dev_path> * The context for an origin is merely a 'struct dm_dev *' @@ -2166,6 +2248,7 @@ static int origin_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_open; } + o->ti = ti; ti->private = o; ti->num_flush_bios = 1; @@ -2180,6 +2263,7 @@ bad_alloc: static void origin_dtr(struct dm_target *ti) { struct dm_origin *o = ti->private; + dm_put_device(ti, o->dev); kfree(o); } @@ -2216,6 +2300,19 @@ static void origin_resume(struct dm_target *ti) struct dm_origin *o = ti->private; o->split_boundary = get_origin_minimum_chunksize(o->dev->bdev); + + down_write(&_origins_lock); + __insert_dm_origin(o); + up_write(&_origins_lock); +} + +static void origin_postsuspend(struct dm_target *ti) +{ + struct dm_origin *o = ti->private; + + down_write(&_origins_lock); + __remove_dm_origin(o); + up_write(&_origins_lock); } static void origin_status(struct dm_target *ti, status_type_t type, @@ -2258,12 +2355,13 @@ static int origin_iterate_devices(struct dm_target *ti, static struct target_type origin_target = { .name = "snapshot-origin", - .version = {1, 8, 1}, + .version = {1, 9, 0}, .module = THIS_MODULE, .ctr = origin_ctr, .dtr = origin_dtr, .map = origin_map, .resume = origin_resume, + .postsuspend = origin_postsuspend, .status = origin_status, .merge = origin_merge, .iterate_devices = origin_iterate_devices, @@ -2271,7 +2369,7 @@ static struct target_type origin_target = { static struct target_type snapshot_target = { .name = "snapshot", - .version = {1, 12, 0}, + .version = {1, 13, 0}, .module = THIS_MODULE, .ctr = snapshot_ctr, .dtr = snapshot_dtr, @@ -2285,7 +2383,7 @@ static struct target_type snapshot_target = { static struct target_type merge_target = { .name = dm_snapshot_merge_target_name, - .version = {1, 2, 0}, + .version = {1, 3, 0}, .module = THIS_MODULE, .ctr = snapshot_ctr, .dtr = snapshot_dtr, diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c index c62c5ab6aed5..7e818f5f1dc4 100644 --- a/drivers/md/dm-sysfs.c +++ b/drivers/md/dm-sysfs.c @@ -11,7 +11,7 @@ struct dm_sysfs_attr { struct attribute attr; ssize_t (*show)(struct mapped_device *, char *); - ssize_t (*store)(struct mapped_device *, char *); + ssize_t (*store)(struct mapped_device *, const char *, size_t count); }; #define DM_ATTR_RO(_name) \ @@ -39,6 +39,31 @@ static ssize_t dm_attr_show(struct kobject *kobj, struct attribute *attr, return ret; } +#define DM_ATTR_RW(_name) \ +struct dm_sysfs_attr dm_attr_##_name = \ + __ATTR(_name, S_IRUGO | S_IWUSR, dm_attr_##_name##_show, dm_attr_##_name##_store) + +static ssize_t dm_attr_store(struct kobject *kobj, struct attribute *attr, + const char *page, size_t count) +{ + struct dm_sysfs_attr *dm_attr; + struct mapped_device *md; + ssize_t ret; + + dm_attr = container_of(attr, struct dm_sysfs_attr, attr); + if (!dm_attr->store) + return -EIO; + + md = dm_get_from_kobject(kobj); + if (!md) + return -EINVAL; + + ret = dm_attr->store(md, page, count); + dm_put(md); + + return ret; +} + static ssize_t dm_attr_name_show(struct mapped_device *md, char *buf) { if (dm_copy_name_and_uuid(md, buf, NULL)) @@ -64,25 +89,33 @@ static ssize_t dm_attr_suspended_show(struct mapped_device *md, char *buf) return strlen(buf); } +static ssize_t dm_attr_use_blk_mq_show(struct mapped_device *md, char *buf) +{ + sprintf(buf, "%d\n", dm_use_blk_mq(md)); + + return strlen(buf); +} + static DM_ATTR_RO(name); static DM_ATTR_RO(uuid); static DM_ATTR_RO(suspended); +static DM_ATTR_RO(use_blk_mq); +static DM_ATTR_RW(rq_based_seq_io_merge_deadline); static struct attribute *dm_attrs[] = { &dm_attr_name.attr, &dm_attr_uuid.attr, &dm_attr_suspended.attr, + &dm_attr_use_blk_mq.attr, + &dm_attr_rq_based_seq_io_merge_deadline.attr, NULL, }; static const struct sysfs_ops dm_sysfs_ops = { .show = dm_attr_show, + .store = dm_attr_store, }; -/* - * dm kobject is embedded in mapped_device structure - * no need to define release function here - */ static struct kobj_type dm_ktype = { .sysfs_ops = &dm_sysfs_ops, .default_attrs = dm_attrs, diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 6554d9148927..d9b00b8565c6 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -18,6 +18,8 @@ #include <linux/mutex.h> #include <linux/delay.h> #include <linux/atomic.h> +#include <linux/blk-mq.h> +#include <linux/mount.h> #define DM_MSG_PREFIX "table" @@ -372,23 +374,18 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, int r; dev_t uninitialized_var(dev); struct dm_dev_internal *dd; - unsigned int major, minor; struct dm_table *t = ti->table; - char dummy; + struct block_device *bdev; BUG_ON(!t); - if (sscanf(path, "%u:%u%c", &major, &minor, &dummy) == 2) { - /* Extract the major/minor numbers */ - dev = MKDEV(major, minor); - if (MAJOR(dev) != major || MINOR(dev) != minor) - return -EOVERFLOW; + /* convert the path to a device */ + bdev = lookup_bdev(path); + if (IS_ERR(bdev)) { + dev = name_to_dev_t(path); + if (!dev) + return -ENODEV; } else { - /* convert the path to a device */ - struct block_device *bdev = lookup_bdev(path); - - if (IS_ERR(bdev)) - return PTR_ERR(bdev); dev = bdev->bd_dev; bdput(bdev); } @@ -939,7 +936,7 @@ bool dm_table_mq_request_based(struct dm_table *t) return dm_table_get_type(t) == DM_TYPE_MQ_REQUEST_BASED; } -static int dm_table_alloc_md_mempools(struct dm_table *t) +static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md) { unsigned type = dm_table_get_type(t); unsigned per_bio_data_size = 0; @@ -957,7 +954,7 @@ static int dm_table_alloc_md_mempools(struct dm_table *t) per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size); } - t->mempools = dm_alloc_md_mempools(type, t->integrity_supported, per_bio_data_size); + t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported, per_bio_data_size); if (!t->mempools) return -ENOMEM; @@ -1127,7 +1124,7 @@ int dm_table_complete(struct dm_table *t) return r; } - r = dm_table_alloc_md_mempools(t); + r = dm_table_alloc_md_mempools(t, t->md); if (r) DMERR("unable to allocate mempools"); @@ -1339,14 +1336,14 @@ static bool dm_table_supports_flush(struct dm_table *t, unsigned flush) continue; if (ti->flush_supported) - return 1; + return true; if (ti->type->iterate_devices && ti->type->iterate_devices(ti, device_flush_capable, &flush)) - return 1; + return true; } - return 0; + return false; } static bool dm_table_discard_zeroes_data(struct dm_table *t) @@ -1359,10 +1356,10 @@ static bool dm_table_discard_zeroes_data(struct dm_table *t) ti = dm_table_get_target(t, i++); if (ti->discard_zeroes_data_unsupported) - return 0; + return false; } - return 1; + return true; } static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev, @@ -1408,10 +1405,10 @@ static bool dm_table_all_devices_attribute(struct dm_table *t, if (!ti->type->iterate_devices || !ti->type->iterate_devices(ti, func, NULL)) - return 0; + return false; } - return 1; + return true; } static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev, @@ -1468,14 +1465,14 @@ static bool dm_table_supports_discards(struct dm_table *t) continue; if (ti->discards_supported) - return 1; + return true; if (ti->type->iterate_devices && ti->type->iterate_devices(ti, device_discard_capable, NULL)) - return 1; + return true; } - return 0; + return false; } void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, @@ -1677,20 +1674,6 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits) return r; } -int dm_table_any_busy_target(struct dm_table *t) -{ - unsigned i; - struct dm_target *ti; - - for (i = 0; i < t->num_targets; i++) { - ti = t->targets + i; - if (ti->type->busy && ti->type->busy(ti)) - return 1; - } - - return 0; -} - struct mapped_device *dm_table_get_md(struct dm_table *t) { return t->md; @@ -1709,9 +1692,13 @@ void dm_table_run_md_queue_async(struct dm_table *t) md = dm_table_get_md(t); queue = dm_get_md_queue(md); if (queue) { - spin_lock_irqsave(queue->queue_lock, flags); - blk_run_queue_async(queue); - spin_unlock_irqrestore(queue->queue_lock, flags); + if (queue->mq_ops) + blk_mq_run_hw_queues(queue, true); + else { + spin_lock_irqsave(queue->queue_lock, flags); + blk_run_queue_async(queue); + spin_unlock_irqrestore(queue->queue_lock, flags); + } } } EXPORT_SYMBOL(dm_table_run_md_queue_async); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 654773cb1eee..921aafd12aee 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2358,17 +2358,6 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; case -ENODATA: - if (get_pool_mode(tc->pool) == PM_READ_ONLY) { - /* - * This block isn't provisioned, and we have no way - * of doing so. - */ - handle_unserviceable_bio(tc->pool, bio); - cell_defer_no_holder(tc, virt_cell); - return DM_MAPIO_SUBMITTED; - } - /* fall through */ - case -EWOULDBLOCK: thin_defer_cell(tc, virt_cell); return DM_MAPIO_SUBMITTED; diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c index 7a7bab8947ae..66616db33e6f 100644 --- a/drivers/md/dm-verity.c +++ b/drivers/md/dm-verity.c @@ -18,20 +18,39 @@ #include <linux/module.h> #include <linux/device-mapper.h> +#include <linux/reboot.h> #include <crypto/hash.h> #define DM_MSG_PREFIX "verity" +#define DM_VERITY_ENV_LENGTH 42 +#define DM_VERITY_ENV_VAR_NAME "DM_VERITY_ERR_BLOCK_NR" + #define DM_VERITY_IO_VEC_INLINE 16 #define DM_VERITY_MEMPOOL_SIZE 4 #define DM_VERITY_DEFAULT_PREFETCH_SIZE 262144 #define DM_VERITY_MAX_LEVELS 63 +#define DM_VERITY_MAX_CORRUPTED_ERRS 100 + +#define DM_VERITY_OPT_LOGGING "ignore_corruption" +#define DM_VERITY_OPT_RESTART "restart_on_corruption" static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR); +enum verity_mode { + DM_VERITY_MODE_EIO, + DM_VERITY_MODE_LOGGING, + DM_VERITY_MODE_RESTART +}; + +enum verity_block_type { + DM_VERITY_BLOCK_TYPE_DATA, + DM_VERITY_BLOCK_TYPE_METADATA +}; + struct dm_verity { struct dm_dev *data_dev; struct dm_dev *hash_dev; @@ -54,6 +73,8 @@ struct dm_verity { unsigned digest_size; /* digest size for the current hash algorithm */ unsigned shash_descsize;/* the size of temporary space for crypto */ int hash_failed; /* set to 1 if hash of any block failed */ + enum verity_mode mode; /* mode for handling verification errors */ + unsigned corrupted_errs;/* Number of errors for corrupted blocks */ mempool_t *vec_mempool; /* mempool of bio vector */ @@ -175,6 +196,57 @@ static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level, } /* + * Handle verification errors. + */ +static int verity_handle_err(struct dm_verity *v, enum verity_block_type type, + unsigned long long block) +{ + char verity_env[DM_VERITY_ENV_LENGTH]; + char *envp[] = { verity_env, NULL }; + const char *type_str = ""; + struct mapped_device *md = dm_table_get_md(v->ti->table); + + /* Corruption should be visible in device status in all modes */ + v->hash_failed = 1; + + if (v->corrupted_errs >= DM_VERITY_MAX_CORRUPTED_ERRS) + goto out; + + v->corrupted_errs++; + + switch (type) { + case DM_VERITY_BLOCK_TYPE_DATA: + type_str = "data"; + break; + case DM_VERITY_BLOCK_TYPE_METADATA: + type_str = "metadata"; + break; + default: + BUG(); + } + + DMERR("%s: %s block %llu is corrupted", v->data_dev->name, type_str, + block); + + if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS) + DMERR("%s: reached maximum errors", v->data_dev->name); + + snprintf(verity_env, DM_VERITY_ENV_LENGTH, "%s=%d,%llu", + DM_VERITY_ENV_VAR_NAME, type, block); + + kobject_uevent_env(&disk_to_dev(dm_disk(md))->kobj, KOBJ_CHANGE, envp); + +out: + if (v->mode == DM_VERITY_MODE_LOGGING) + return 0; + + if (v->mode == DM_VERITY_MODE_RESTART) + kernel_restart("dm-verity device corrupted"); + + return 1; +} + +/* * Verify hash of a metadata block pertaining to the specified data block * ("block" argument) at a specified level ("level" argument). * @@ -251,11 +323,11 @@ static int verity_verify_level(struct dm_verity_io *io, sector_t block, goto release_ret_r; } if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - DMERR_LIMIT("metadata block %llu is corrupted", - (unsigned long long)hash_block); - v->hash_failed = 1; - r = -EIO; - goto release_ret_r; + if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_METADATA, + hash_block)) { + r = -EIO; + goto release_ret_r; + } } else aux->hash_verified = 1; } @@ -367,10 +439,9 @@ test_block_hash: return r; } if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - DMERR_LIMIT("data block %llu is corrupted", - (unsigned long long)(io->block + b)); - v->hash_failed = 1; - return -EIO; + if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, + io->block + b)) + return -EIO; } } @@ -546,6 +617,19 @@ static void verity_status(struct dm_target *ti, status_type_t type, else for (x = 0; x < v->salt_size; x++) DMEMIT("%02x", v->salt[x]); + if (v->mode != DM_VERITY_MODE_EIO) { + DMEMIT(" 1 "); + switch (v->mode) { + case DM_VERITY_MODE_LOGGING: + DMEMIT(DM_VERITY_OPT_LOGGING); + break; + case DM_VERITY_MODE_RESTART: + DMEMIT(DM_VERITY_OPT_RESTART); + break; + default: + BUG(); + } + } break; } } @@ -647,13 +731,19 @@ static void verity_dtr(struct dm_target *ti) static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) { struct dm_verity *v; - unsigned num; + struct dm_arg_set as; + const char *opt_string; + unsigned int num, opt_params; unsigned long long num_ll; int r; int i; sector_t hash_position; char dummy; + static struct dm_arg _args[] = { + {0, 1, "Invalid number of feature args"}, + }; + v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL); if (!v) { ti->error = "Cannot allocate verity structure"; @@ -668,8 +758,8 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } - if (argc != 10) { - ti->error = "Invalid argument count: exactly 10 arguments required"; + if (argc < 10) { + ti->error = "Not enough arguments"; r = -EINVAL; goto bad; } @@ -790,6 +880,39 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) } } + argv += 10; + argc -= 10; + + /* Optional parameters */ + if (argc) { + as.argc = argc; + as.argv = argv; + + r = dm_read_arg_group(_args, &as, &opt_params, &ti->error); + if (r) + goto bad; + + while (opt_params) { + opt_params--; + opt_string = dm_shift_arg(&as); + if (!opt_string) { + ti->error = "Not enough feature arguments"; + r = -EINVAL; + goto bad; + } + + if (!strcasecmp(opt_string, DM_VERITY_OPT_LOGGING)) + v->mode = DM_VERITY_MODE_LOGGING; + else if (!strcasecmp(opt_string, DM_VERITY_OPT_RESTART)) + v->mode = DM_VERITY_MODE_RESTART; + else { + ti->error = "Invalid feature arguments"; + r = -EINVAL; + goto bad; + } + } + } + v->hash_per_block_bits = __fls((1 << v->hash_dev_block_bits) / v->digest_size); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 73f28802dc7a..a930b72314ac 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -21,6 +21,9 @@ #include <linux/delay.h> #include <linux/wait.h> #include <linux/kthread.h> +#include <linux/ktime.h> +#include <linux/elevator.h> /* for rq_end_sector() */ +#include <linux/blk-mq.h> #include <trace/events/block.h> @@ -216,8 +219,29 @@ struct mapped_device { struct kthread_worker kworker; struct task_struct *kworker_task; + + /* for request-based merge heuristic in dm_request_fn() */ + unsigned seq_rq_merge_deadline_usecs; + int last_rq_rw; + sector_t last_rq_pos; + ktime_t last_rq_start_time; + + /* for blk-mq request-based DM support */ + struct blk_mq_tag_set tag_set; + bool use_blk_mq; }; +#ifdef CONFIG_DM_MQ_DEFAULT +static bool use_blk_mq = true; +#else +static bool use_blk_mq = false; +#endif + +bool dm_use_blk_mq(struct mapped_device *md) +{ + return md->use_blk_mq; +} + /* * For mempools pre-allocation at the table loading time. */ @@ -250,35 +274,35 @@ static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS; */ static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS; -static unsigned __dm_get_reserved_ios(unsigned *reserved_ios, +static unsigned __dm_get_module_param(unsigned *module_param, unsigned def, unsigned max) { - unsigned ios = ACCESS_ONCE(*reserved_ios); - unsigned modified_ios = 0; + unsigned param = ACCESS_ONCE(*module_param); + unsigned modified_param = 0; - if (!ios) - modified_ios = def; - else if (ios > max) - modified_ios = max; + if (!param) + modified_param = def; + else if (param > max) + modified_param = max; - if (modified_ios) { - (void)cmpxchg(reserved_ios, ios, modified_ios); - ios = modified_ios; + if (modified_param) { + (void)cmpxchg(module_param, param, modified_param); + param = modified_param; } - return ios; + return param; } unsigned dm_get_reserved_bio_based_ios(void) { - return __dm_get_reserved_ios(&reserved_bio_based_ios, + return __dm_get_module_param(&reserved_bio_based_ios, RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS); } EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios); unsigned dm_get_reserved_rq_based_ios(void) { - return __dm_get_reserved_ios(&reserved_rq_based_ios, + return __dm_get_module_param(&reserved_rq_based_ios, RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS); } EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios); @@ -433,7 +457,6 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode) dm_get(md); atomic_inc(&md->open_count); - out: spin_unlock(&_minor_lock); @@ -442,16 +465,20 @@ out: static void dm_blk_close(struct gendisk *disk, fmode_t mode) { - struct mapped_device *md = disk->private_data; + struct mapped_device *md; spin_lock(&_minor_lock); + md = disk->private_data; + if (WARN_ON(!md)) + goto out; + if (atomic_dec_and_test(&md->open_count) && (test_bit(DMF_DEFERRED_REMOVE, &md->flags))) queue_work(deferred_remove_workqueue, &deferred_remove_work); dm_put(md); - +out: spin_unlock(&_minor_lock); } @@ -1014,6 +1041,11 @@ static void end_clone_bio(struct bio *clone, int error) blk_update_request(tio->orig, 0, nr_bytes); } +static struct dm_rq_target_io *tio_from_request(struct request *rq) +{ + return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special); +} + /* * Don't touch any member of the md after calling this function because * the md may be freed in dm_put() at the end of this function. @@ -1021,10 +1053,13 @@ static void end_clone_bio(struct bio *clone, int error) */ static void rq_completed(struct mapped_device *md, int rw, bool run_queue) { + int nr_requests_pending; + atomic_dec(&md->pending[rw]); /* nudge anyone waiting on suspend queue */ - if (!md_in_flight(md)) + nr_requests_pending = md_in_flight(md); + if (!nr_requests_pending) wake_up(&md->wait); /* @@ -1033,8 +1068,13 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue) * back into ->request_fn() could deadlock attempting to grab the * queue lock again. */ - if (run_queue) - blk_run_queue_async(md->queue); + if (run_queue) { + if (md->queue->mq_ops) + blk_mq_run_hw_queues(md->queue, true); + else if (!nr_requests_pending || + (nr_requests_pending >= md->queue->nr_congestion_on)) + blk_run_queue_async(md->queue); + } /* * dm_put() must be at the end of this function. See the comment above @@ -1042,16 +1082,29 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue) dm_put(md); } -static void free_rq_clone(struct request *clone) +static void free_rq_clone(struct request *clone, bool must_be_mapped) { struct dm_rq_target_io *tio = clone->end_io_data; + struct mapped_device *md = tio->md; + + WARN_ON_ONCE(must_be_mapped && !clone->q); blk_rq_unprep_clone(clone); - if (clone->q && clone->q->mq_ops) + + if (md->type == DM_TYPE_MQ_REQUEST_BASED) + /* stacked on blk-mq queue(s) */ tio->ti->type->release_clone_rq(clone); - else - free_clone_request(tio->md, clone); - free_rq_tio(tio); + else if (!md->queue->mq_ops) + /* request_fn queue stacked on request_fn queue(s) */ + free_clone_request(md, clone); + /* + * NOTE: for the blk-mq queue stacked on request_fn queue(s) case: + * no need to call free_clone_request() because we leverage blk-mq by + * allocating the clone at the end of the blk-mq pdu (see: clone_rq) + */ + + if (!md->queue->mq_ops) + free_rq_tio(tio); } /* @@ -1079,38 +1132,54 @@ static void dm_end_request(struct request *clone, int error) rq->sense_len = clone->sense_len; } - free_rq_clone(clone); - blk_end_request_all(rq, error); + free_rq_clone(clone, true); + if (!rq->q->mq_ops) + blk_end_request_all(rq, error); + else + blk_mq_end_request(rq, error); rq_completed(md, rw, true); } static void dm_unprep_request(struct request *rq) { - struct dm_rq_target_io *tio = rq->special; + struct dm_rq_target_io *tio = tio_from_request(rq); struct request *clone = tio->clone; - rq->special = NULL; - rq->cmd_flags &= ~REQ_DONTPREP; + if (!rq->q->mq_ops) { + rq->special = NULL; + rq->cmd_flags &= ~REQ_DONTPREP; + } if (clone) - free_rq_clone(clone); + free_rq_clone(clone, false); } /* * Requeue the original request of a clone. */ -static void dm_requeue_unmapped_original_request(struct mapped_device *md, - struct request *rq) +static void old_requeue_request(struct request *rq) { - int rw = rq_data_dir(rq); struct request_queue *q = rq->q; unsigned long flags; - dm_unprep_request(rq); - spin_lock_irqsave(q->queue_lock, flags); blk_requeue_request(q, rq); spin_unlock_irqrestore(q->queue_lock, flags); +} + +static void dm_requeue_unmapped_original_request(struct mapped_device *md, + struct request *rq) +{ + int rw = rq_data_dir(rq); + + dm_unprep_request(rq); + + if (!rq->q->mq_ops) + old_requeue_request(rq); + else { + blk_mq_requeue_request(rq); + blk_mq_kick_requeue_list(rq->q); + } rq_completed(md, rw, false); } @@ -1122,35 +1191,44 @@ static void dm_requeue_unmapped_request(struct request *clone) dm_requeue_unmapped_original_request(tio->md, tio->orig); } -static void __stop_queue(struct request_queue *q) -{ - blk_stop_queue(q); -} - -static void stop_queue(struct request_queue *q) +static void old_stop_queue(struct request_queue *q) { unsigned long flags; + if (blk_queue_stopped(q)) + return; + spin_lock_irqsave(q->queue_lock, flags); - __stop_queue(q); + blk_stop_queue(q); spin_unlock_irqrestore(q->queue_lock, flags); } -static void __start_queue(struct request_queue *q) +static void stop_queue(struct request_queue *q) { - if (blk_queue_stopped(q)) - blk_start_queue(q); + if (!q->mq_ops) + old_stop_queue(q); + else + blk_mq_stop_hw_queues(q); } -static void start_queue(struct request_queue *q) +static void old_start_queue(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); - __start_queue(q); + if (blk_queue_stopped(q)) + blk_start_queue(q); spin_unlock_irqrestore(q->queue_lock, flags); } +static void start_queue(struct request_queue *q) +{ + if (!q->mq_ops) + old_start_queue(q); + else + blk_mq_start_stopped_hw_queues(q, true); +} + static void dm_done(struct request *clone, int error, bool mapped) { int r = error; @@ -1189,13 +1267,20 @@ static void dm_done(struct request *clone, int error, bool mapped) static void dm_softirq_done(struct request *rq) { bool mapped = true; - struct dm_rq_target_io *tio = rq->special; + struct dm_rq_target_io *tio = tio_from_request(rq); struct request *clone = tio->clone; + int rw; if (!clone) { - blk_end_request_all(rq, tio->error); - rq_completed(tio->md, rq_data_dir(rq), false); - free_rq_tio(tio); + rw = rq_data_dir(rq); + if (!rq->q->mq_ops) { + blk_end_request_all(rq, tio->error); + rq_completed(tio->md, rw, false); + free_rq_tio(tio); + } else { + blk_mq_end_request(rq, tio->error); + rq_completed(tio->md, rw, false); + } return; } @@ -1211,7 +1296,7 @@ static void dm_softirq_done(struct request *rq) */ static void dm_complete_request(struct request *rq, int error) { - struct dm_rq_target_io *tio = rq->special; + struct dm_rq_target_io *tio = tio_from_request(rq); tio->error = error; blk_complete_request(rq); @@ -1230,7 +1315,7 @@ static void dm_kill_unmapped_request(struct request *rq, int error) } /* - * Called with the clone's queue lock held + * Called with the clone's queue lock held (for non-blk-mq) */ static void end_clone_request(struct request *clone, int error) { @@ -1690,7 +1775,7 @@ out: * The request function that just remaps the bio built up by * dm_merge_bvec. */ -static void _dm_request(struct request_queue *q, struct bio *bio) +static void dm_make_request(struct request_queue *q, struct bio *bio) { int rw = bio_data_dir(bio); struct mapped_device *md = q->queuedata; @@ -1722,16 +1807,6 @@ int dm_request_based(struct mapped_device *md) return blk_queue_stackable(md->queue); } -static void dm_request(struct request_queue *q, struct bio *bio) -{ - struct mapped_device *md = q->queuedata; - - if (dm_request_based(md)) - blk_queue_bio(q, bio); - else - _dm_request(q, bio); -} - static void dm_dispatch_clone_request(struct request *clone, struct request *rq) { int r; @@ -1784,15 +1859,25 @@ static int setup_clone(struct request *clone, struct request *rq, static struct request *clone_rq(struct request *rq, struct mapped_device *md, struct dm_rq_target_io *tio, gfp_t gfp_mask) { - struct request *clone = alloc_clone_request(md, gfp_mask); + /* + * Do not allocate a clone if tio->clone was already set + * (see: dm_mq_queue_rq). + */ + bool alloc_clone = !tio->clone; + struct request *clone; - if (!clone) - return NULL; + if (alloc_clone) { + clone = alloc_clone_request(md, gfp_mask); + if (!clone) + return NULL; + } else + clone = tio->clone; blk_rq_init(NULL, clone); if (setup_clone(clone, rq, tio, gfp_mask)) { /* -ENOMEM */ - free_clone_request(md, clone); + if (alloc_clone) + free_clone_request(md, clone); return NULL; } @@ -1801,6 +1886,19 @@ static struct request *clone_rq(struct request *rq, struct mapped_device *md, static void map_tio_request(struct kthread_work *work); +static void init_tio(struct dm_rq_target_io *tio, struct request *rq, + struct mapped_device *md) +{ + tio->md = md; + tio->ti = NULL; + tio->clone = NULL; + tio->orig = rq; + tio->error = 0; + memset(&tio->info, 0, sizeof(tio->info)); + if (md->kworker_task) + init_kthread_work(&tio->work, map_tio_request); +} + static struct dm_rq_target_io *prep_tio(struct request *rq, struct mapped_device *md, gfp_t gfp_mask) { @@ -1812,13 +1910,7 @@ static struct dm_rq_target_io *prep_tio(struct request *rq, if (!tio) return NULL; - tio->md = md; - tio->ti = NULL; - tio->clone = NULL; - tio->orig = rq; - tio->error = 0; - memset(&tio->info, 0, sizeof(tio->info)); - init_kthread_work(&tio->work, map_tio_request); + init_tio(tio, rq, md); table = dm_get_live_table(md, &srcu_idx); if (!dm_table_mq_request_based(table)) { @@ -1862,11 +1954,11 @@ static int dm_prep_fn(struct request_queue *q, struct request *rq) * DM_MAPIO_REQUEUE : the original request needs to be requeued * < 0 : the request was completed due to failure */ -static int map_request(struct dm_target *ti, struct request *rq, +static int map_request(struct dm_rq_target_io *tio, struct request *rq, struct mapped_device *md) { int r; - struct dm_rq_target_io *tio = rq->special; + struct dm_target *ti = tio->ti; struct request *clone = NULL; if (tio->clone) { @@ -1881,7 +1973,7 @@ static int map_request(struct dm_target *ti, struct request *rq, } if (IS_ERR(clone)) return DM_MAPIO_REQUEUE; - if (setup_clone(clone, rq, tio, GFP_KERNEL)) { + if (setup_clone(clone, rq, tio, GFP_ATOMIC)) { /* -ENOMEM */ ti->type->release_clone_rq(clone); return DM_MAPIO_REQUEUE; @@ -1922,15 +2014,24 @@ static void map_tio_request(struct kthread_work *work) struct request *rq = tio->orig; struct mapped_device *md = tio->md; - if (map_request(tio->ti, rq, md) == DM_MAPIO_REQUEUE) + if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) dm_requeue_unmapped_original_request(md, rq); } static void dm_start_request(struct mapped_device *md, struct request *orig) { - blk_start_request(orig); + if (!orig->q->mq_ops) + blk_start_request(orig); + else + blk_mq_start_request(orig); atomic_inc(&md->pending[rq_data_dir(orig)]); + if (md->seq_rq_merge_deadline_usecs) { + md->last_rq_pos = rq_end_sector(orig); + md->last_rq_rw = rq_data_dir(orig); + md->last_rq_start_time = ktime_get(); + } + /* * Hold the md reference here for the in-flight I/O. * We can't rely on the reference count by device opener, @@ -1941,6 +2042,45 @@ static void dm_start_request(struct mapped_device *md, struct request *orig) dm_get(md); } +#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000 + +ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf) +{ + return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs); +} + +ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md, + const char *buf, size_t count) +{ + unsigned deadline; + + if (!dm_request_based(md) || md->use_blk_mq) + return count; + + if (kstrtouint(buf, 10, &deadline)) + return -EINVAL; + + if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS) + deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS; + + md->seq_rq_merge_deadline_usecs = deadline; + + return count; +} + +static bool dm_request_peeked_before_merge_deadline(struct mapped_device *md) +{ + ktime_t kt_deadline; + + if (!md->seq_rq_merge_deadline_usecs) + return false; + + kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC); + kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline); + + return !ktime_after(ktime_get(), kt_deadline); +} + /* * q->request_fn for request-based dm. * Called with the queue lock held. @@ -1964,7 +2104,7 @@ static void dm_request_fn(struct request_queue *q) while (!blk_queue_stopped(q)) { rq = blk_peek_request(q); if (!rq) - goto delay_and_out; + goto out; /* always use block 0 to find the target for flushes for now */ pos = 0; @@ -1983,12 +2123,17 @@ static void dm_request_fn(struct request_queue *q) continue; } + if (dm_request_peeked_before_merge_deadline(md) && + md_in_flight(md) && rq->bio && rq->bio->bi_vcnt == 1 && + md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) + goto delay_and_out; + if (ti->type->busy && ti->type->busy(ti)) goto delay_and_out; dm_start_request(md, rq); - tio = rq->special; + tio = tio_from_request(rq); /* Establish tio->ti before queuing work (map_tio_request) */ tio->ti = ti; queue_kthread_work(&md->kworker, &tio->work); @@ -1998,33 +2143,11 @@ static void dm_request_fn(struct request_queue *q) goto out; delay_and_out: - blk_delay_queue(q, HZ / 10); + blk_delay_queue(q, HZ / 100); out: dm_put_live_table(md, srcu_idx); } -int dm_underlying_device_busy(struct request_queue *q) -{ - return blk_lld_busy(q); -} -EXPORT_SYMBOL_GPL(dm_underlying_device_busy); - -static int dm_lld_busy(struct request_queue *q) -{ - int r; - struct mapped_device *md = q->queuedata; - struct dm_table *map = dm_get_live_table_fast(md); - - if (!map || test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) - r = 1; - else - r = dm_table_any_busy_target(map); - - dm_put_live_table_fast(md); - - return r; -} - static int dm_any_congested(void *congested_data, int bdi_bits) { int r = bdi_bits; @@ -2107,7 +2230,7 @@ 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. + * devices. The type of this dm device may not have 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. @@ -2115,13 +2238,21 @@ static void dm_init_md_queue(struct mapped_device *md) * This queue is new, so no concurrency on the queue_flags. */ queue_flag_clear_unlocked(QUEUE_FLAG_STACKABLE, md->queue); +} +static void dm_init_old_md_queue(struct mapped_device *md) +{ + md->use_blk_mq = false; + dm_init_md_queue(md); + + /* + * Initialize aspects of queue that aren't relevant for blk-mq + */ 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); - blk_queue_merge_bvec(md->queue, dm_merge_bvec); } /* @@ -2153,6 +2284,7 @@ static struct mapped_device *alloc_dev(int minor) if (r < 0) goto bad_io_barrier; + md->use_blk_mq = use_blk_mq; md->type = DM_TYPE_NONE; mutex_init(&md->suspend_lock); mutex_init(&md->type_lock); @@ -2241,7 +2373,6 @@ static void free_dev(struct mapped_device *md) int minor = MINOR(disk_devt(md->disk)); unlock_fs(md); - bdput(md->bdev); destroy_workqueue(md->wq); if (md->kworker_task) @@ -2252,19 +2383,24 @@ static void free_dev(struct mapped_device *md) mempool_destroy(md->rq_pool); if (md->bs) bioset_free(md->bs); - blk_integrity_unregister(md->disk); - del_gendisk(md->disk); + cleanup_srcu_struct(&md->io_barrier); free_table_devices(&md->table_devices); - free_minor(minor); + dm_stats_cleanup(&md->stats); spin_lock(&_minor_lock); md->disk->private_data = NULL; spin_unlock(&_minor_lock); - + if (blk_get_integrity(md->disk)) + blk_integrity_unregister(md->disk); + del_gendisk(md->disk); put_disk(md->disk); blk_cleanup_queue(md->queue); - dm_stats_cleanup(&md->stats); + if (md->use_blk_mq) + blk_mq_free_tag_set(&md->tag_set); + bdput(md->bdev); + free_minor(minor); + module_put(THIS_MODULE); kfree(md); } @@ -2273,7 +2409,7 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t) { struct dm_md_mempools *p = dm_table_get_md_mempools(t); - if (md->io_pool && md->bs) { + if (md->bs) { /* The md already has necessary mempools. */ if (dm_table_get_type(t) == DM_TYPE_BIO_BASED) { /* @@ -2305,7 +2441,7 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t) p->bs = NULL; out: - /* mempool bind completed, now no need any mempools in the table */ + /* mempool bind completed, no longer need any mempools in the table */ dm_table_free_md_mempools(t); } @@ -2352,7 +2488,7 @@ int dm_queue_merge_is_compulsory(struct request_queue *q) if (!q->merge_bvec_fn) return 0; - if (q->make_request_fn == dm_request) { + if (q->make_request_fn == dm_make_request) { dev_md = q->queuedata; if (test_bit(DMF_MERGE_IS_OPTIONAL, &dev_md->flags)) return 0; @@ -2421,7 +2557,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, * This must be done before setting the queue restrictions, * because request-based dm may be run just after the setting. */ - if (dm_table_request_based(t) && !blk_queue_stopped(q)) + if (dm_table_request_based(t)) stop_queue(q); __bind_mempools(md, t); @@ -2503,14 +2639,6 @@ unsigned dm_get_md_type(struct mapped_device *md) return md->type; } -static bool dm_md_type_request_based(struct mapped_device *md) -{ - unsigned table_type = dm_get_md_type(md); - - return (table_type == DM_TYPE_REQUEST_BASED || - table_type == DM_TYPE_MQ_REQUEST_BASED); -} - struct target_type *dm_get_immutable_target_type(struct mapped_device *md) { return md->immutable_target_type; @@ -2527,6 +2655,14 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_get_queue_limits); +static void init_rq_based_worker_thread(struct mapped_device *md) +{ + /* Initialize the request-based DM worker thread */ + init_kthread_worker(&md->kworker); + md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker, + "kdmwork-%s", dm_device_name(md)); +} + /* * Fully initialize a request-based queue (->elevator, ->request_fn, etc). */ @@ -2534,28 +2670,158 @@ 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; + return -EINVAL; + + /* disable dm_request_fn's merge heuristic by default */ + md->seq_rq_merge_deadline_usecs = 0; md->queue = q; - dm_init_md_queue(md); + dm_init_old_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); - /* Also initialize the request-based DM worker thread */ - init_kthread_worker(&md->kworker); - md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker, - "kdmwork-%s", dm_device_name(md)); + init_rq_based_worker_thread(md); elv_register_queue(md->queue); - return 1; + return 0; +} + +static int dm_mq_init_request(void *data, struct request *rq, + unsigned int hctx_idx, unsigned int request_idx, + unsigned int numa_node) +{ + struct mapped_device *md = data; + struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq); + + /* + * Must initialize md member of tio, otherwise it won't + * be available in dm_mq_queue_rq. + */ + tio->md = md; + + return 0; +} + +static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + struct request *rq = bd->rq; + struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq); + struct mapped_device *md = tio->md; + int srcu_idx; + struct dm_table *map = dm_get_live_table(md, &srcu_idx); + struct dm_target *ti; + sector_t pos; + + /* always use block 0 to find the target for flushes for now */ + pos = 0; + if (!(rq->cmd_flags & REQ_FLUSH)) + pos = blk_rq_pos(rq); + + ti = dm_table_find_target(map, pos); + if (!dm_target_is_valid(ti)) { + dm_put_live_table(md, srcu_idx); + DMERR_LIMIT("request attempted access beyond the end of device"); + /* + * Must perform setup, that rq_completed() requires, + * before returning BLK_MQ_RQ_QUEUE_ERROR + */ + dm_start_request(md, rq); + return BLK_MQ_RQ_QUEUE_ERROR; + } + dm_put_live_table(md, srcu_idx); + + if (ti->type->busy && ti->type->busy(ti)) + return BLK_MQ_RQ_QUEUE_BUSY; + + dm_start_request(md, rq); + + /* Init tio using md established in .init_request */ + init_tio(tio, rq, md); + + /* + * Establish tio->ti before queuing work (map_tio_request) + * or making direct call to map_request(). + */ + tio->ti = ti; + + /* Clone the request if underlying devices aren't blk-mq */ + if (dm_table_get_type(map) == DM_TYPE_REQUEST_BASED) { + /* clone request is allocated at the end of the pdu */ + tio->clone = (void *)blk_mq_rq_to_pdu(rq) + sizeof(struct dm_rq_target_io); + if (!clone_rq(rq, md, tio, GFP_ATOMIC)) + return BLK_MQ_RQ_QUEUE_BUSY; + queue_kthread_work(&md->kworker, &tio->work); + } else { + /* Direct call is fine since .queue_rq allows allocations */ + if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) + dm_requeue_unmapped_original_request(md, rq); + } + + return BLK_MQ_RQ_QUEUE_OK; +} + +static struct blk_mq_ops dm_mq_ops = { + .queue_rq = dm_mq_queue_rq, + .map_queue = blk_mq_map_queue, + .complete = dm_softirq_done, + .init_request = dm_mq_init_request, +}; + +static int dm_init_request_based_blk_mq_queue(struct mapped_device *md) +{ + unsigned md_type = dm_get_md_type(md); + struct request_queue *q; + int err; + + memset(&md->tag_set, 0, sizeof(md->tag_set)); + md->tag_set.ops = &dm_mq_ops; + md->tag_set.queue_depth = BLKDEV_MAX_RQ; + md->tag_set.numa_node = NUMA_NO_NODE; + md->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE; + md->tag_set.nr_hw_queues = 1; + if (md_type == DM_TYPE_REQUEST_BASED) { + /* make the memory for non-blk-mq clone part of the pdu */ + md->tag_set.cmd_size = sizeof(struct dm_rq_target_io) + sizeof(struct request); + } else + md->tag_set.cmd_size = sizeof(struct dm_rq_target_io); + md->tag_set.driver_data = md; + + err = blk_mq_alloc_tag_set(&md->tag_set); + if (err) + return err; + + q = blk_mq_init_allocated_queue(&md->tag_set, md->queue); + if (IS_ERR(q)) { + err = PTR_ERR(q); + goto out_tag_set; + } + md->queue = q; + dm_init_md_queue(md); + + /* backfill 'mq' sysfs registration normally done in blk_register_queue */ + blk_mq_register_disk(md->disk); + + if (md_type == DM_TYPE_REQUEST_BASED) + init_rq_based_worker_thread(md); + + return 0; + +out_tag_set: + blk_mq_free_tag_set(&md->tag_set); + return err; +} + +static unsigned filter_md_type(unsigned type, struct mapped_device *md) +{ + if (type == DM_TYPE_BIO_BASED) + return type; + + return !md->use_blk_mq ? DM_TYPE_REQUEST_BASED : DM_TYPE_MQ_REQUEST_BASED; } /* @@ -2563,9 +2829,29 @@ static int dm_init_request_based_queue(struct mapped_device *md) */ int dm_setup_md_queue(struct mapped_device *md) { - if (dm_md_type_request_based(md) && !dm_init_request_based_queue(md)) { - DMWARN("Cannot initialize queue for request-based mapped device"); - return -EINVAL; + int r; + unsigned md_type = filter_md_type(dm_get_md_type(md), md); + + switch (md_type) { + case DM_TYPE_REQUEST_BASED: + r = dm_init_request_based_queue(md); + if (r) { + DMWARN("Cannot initialize queue for request-based mapped device"); + return r; + } + break; + case DM_TYPE_MQ_REQUEST_BASED: + r = dm_init_request_based_blk_mq_queue(md); + if (r) { + DMWARN("Cannot initialize queue for request-based blk-mq mapped device"); + return r; + } + break; + case DM_TYPE_BIO_BASED: + dm_init_old_md_queue(md); + blk_queue_make_request(md->queue, dm_make_request); + blk_queue_merge_bvec(md->queue, dm_merge_bvec); + break; } return 0; @@ -2616,6 +2902,19 @@ void dm_get(struct mapped_device *md) BUG_ON(test_bit(DMF_FREEING, &md->flags)); } +int dm_hold(struct mapped_device *md) +{ + spin_lock(&_minor_lock); + if (test_bit(DMF_FREEING, &md->flags)) { + spin_unlock(&_minor_lock); + return -EBUSY; + } + dm_get(md); + spin_unlock(&_minor_lock); + return 0; +} +EXPORT_SYMBOL_GPL(dm_hold); + const char *dm_device_name(struct mapped_device *md) { return md->name; @@ -2629,19 +2928,26 @@ static void __dm_destroy(struct mapped_device *md, bool wait) might_sleep(); - spin_lock(&_minor_lock); map = dm_get_live_table(md, &srcu_idx); + + spin_lock(&_minor_lock); idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md)))); set_bit(DMF_FREEING, &md->flags); spin_unlock(&_minor_lock); - if (dm_request_based(md)) + if (dm_request_based(md) && md->kworker_task) flush_kthread_worker(&md->kworker); + /* + * Take suspend_lock so that presuspend and postsuspend methods + * do not race with internal suspend. + */ + mutex_lock(&md->suspend_lock); if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); dm_table_postsuspend_targets(map); } + mutex_unlock(&md->suspend_lock); /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ dm_put_live_table(md, srcu_idx); @@ -2883,7 +3189,8 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map, */ if (dm_request_based(md)) { stop_queue(md->queue); - flush_kthread_worker(&md->kworker); + if (md->kworker_task) + flush_kthread_worker(&md->kworker); } flush_workqueue(md->wq); @@ -3115,6 +3422,7 @@ void dm_internal_suspend_fast(struct mapped_device *md) flush_workqueue(md->wq); dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE); } +EXPORT_SYMBOL_GPL(dm_internal_suspend_fast); void dm_internal_resume_fast(struct mapped_device *md) { @@ -3126,6 +3434,7 @@ void dm_internal_resume_fast(struct mapped_device *md) done: mutex_unlock(&md->suspend_lock); } +EXPORT_SYMBOL_GPL(dm_internal_resume_fast); /*----------------------------------------------------------------- * Event notification. @@ -3179,6 +3488,7 @@ struct gendisk *dm_disk(struct mapped_device *md) { return md->disk; } +EXPORT_SYMBOL_GPL(dm_disk); struct kobject *dm_kobject(struct mapped_device *md) { @@ -3226,16 +3536,19 @@ int dm_noflush_suspending(struct dm_target *ti) } EXPORT_SYMBOL_GPL(dm_noflush_suspending); -struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size) +struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type, + unsigned integrity, unsigned per_bio_data_size) { struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL); - struct kmem_cache *cachep; + struct kmem_cache *cachep = NULL; unsigned int pool_size = 0; unsigned int front_pad; if (!pools) return NULL; + type = filter_md_type(type, md); + switch (type) { case DM_TYPE_BIO_BASED: cachep = _io_cache; @@ -3243,13 +3556,13 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone); break; case DM_TYPE_REQUEST_BASED: + cachep = _rq_tio_cache; pool_size = dm_get_reserved_rq_based_ios(); pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache); if (!pools->rq_pool) goto out; /* fall through to setup remaining rq-based pools */ case DM_TYPE_MQ_REQUEST_BASED: - cachep = _rq_tio_cache; if (!pool_size) pool_size = dm_get_reserved_rq_based_ios(); front_pad = offsetof(struct dm_rq_clone_bio_info, clone); @@ -3257,12 +3570,14 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u WARN_ON(per_bio_data_size != 0); break; default: - goto out; + BUG(); } - pools->io_pool = mempool_create_slab_pool(pool_size, cachep); - if (!pools->io_pool) - goto out; + if (cachep) { + pools->io_pool = mempool_create_slab_pool(pool_size, cachep); + if (!pools->io_pool) + goto out; + } pools->bs = bioset_create_nobvec(pool_size, front_pad); if (!pools->bs) @@ -3319,6 +3634,9 @@ MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools"); module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools"); +module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices"); + MODULE_DESCRIPTION(DM_NAME " driver"); MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 59f53e79db82..6123c2bf9150 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -70,7 +70,6 @@ void dm_table_presuspend_undo_targets(struct dm_table *t); 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); unsigned dm_table_get_type(struct dm_table *t); struct target_type *dm_table_get_immutable_target_type(struct dm_table *t); bool dm_table_request_based(struct dm_table *t); @@ -212,6 +211,8 @@ int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action, void dm_internal_suspend(struct mapped_device *md); void dm_internal_resume(struct mapped_device *md); +bool dm_use_blk_mq(struct mapped_device *md); + int dm_io_init(void); void dm_io_exit(void); @@ -221,7 +222,8 @@ void dm_kcopyd_exit(void); /* * Mempool operations */ -struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size); +struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type, + unsigned integrity, unsigned per_bio_data_size); void dm_free_md_mempools(struct dm_md_mempools *pools); /* @@ -235,4 +237,8 @@ static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen return !maxlen || strlen(result) + 1 >= maxlen; } +ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf); +ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md, + const char *buf, size_t count); + #endif diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c new file mode 100644 index 000000000000..fcfc4b9b2672 --- /dev/null +++ b/drivers/md/md-cluster.c @@ -0,0 +1,965 @@ +/* + * Copyright (C) 2015, SUSE + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + */ + + +#include <linux/module.h> +#include <linux/dlm.h> +#include <linux/sched.h> +#include <linux/raid/md_p.h> +#include "md.h" +#include "bitmap.h" +#include "md-cluster.h" + +#define LVB_SIZE 64 +#define NEW_DEV_TIMEOUT 5000 + +struct dlm_lock_resource { + dlm_lockspace_t *ls; + struct dlm_lksb lksb; + char *name; /* lock name. */ + uint32_t flags; /* flags to pass to dlm_lock() */ + struct completion completion; /* completion for synchronized locking */ + void (*bast)(void *arg, int mode); /* blocking AST function pointer*/ + struct mddev *mddev; /* pointing back to mddev. */ +}; + +struct suspend_info { + int slot; + sector_t lo; + sector_t hi; + struct list_head list; +}; + +struct resync_info { + __le64 lo; + __le64 hi; +}; + +/* md_cluster_info flags */ +#define MD_CLUSTER_WAITING_FOR_NEWDISK 1 + + +struct md_cluster_info { + /* dlm lock space and resources for clustered raid. */ + dlm_lockspace_t *lockspace; + int slot_number; + struct completion completion; + struct dlm_lock_resource *sb_lock; + struct mutex sb_mutex; + struct dlm_lock_resource *bitmap_lockres; + struct list_head suspend_list; + spinlock_t suspend_lock; + struct md_thread *recovery_thread; + unsigned long recovery_map; + /* communication loc resources */ + struct dlm_lock_resource *ack_lockres; + struct dlm_lock_resource *message_lockres; + struct dlm_lock_resource *token_lockres; + struct dlm_lock_resource *no_new_dev_lockres; + struct md_thread *recv_thread; + struct completion newdisk_completion; + unsigned long state; +}; + +enum msg_type { + METADATA_UPDATED = 0, + RESYNCING, + NEWDISK, + REMOVE, + RE_ADD, +}; + +struct cluster_msg { + int type; + int slot; + /* TODO: Unionize this for smaller footprint */ + sector_t low; + sector_t high; + char uuid[16]; + int raid_slot; +}; + +static void sync_ast(void *arg) +{ + struct dlm_lock_resource *res; + + res = (struct dlm_lock_resource *) arg; + complete(&res->completion); +} + +static int dlm_lock_sync(struct dlm_lock_resource *res, int mode) +{ + int ret = 0; + + init_completion(&res->completion); + ret = dlm_lock(res->ls, mode, &res->lksb, + res->flags, res->name, strlen(res->name), + 0, sync_ast, res, res->bast); + if (ret) + return ret; + wait_for_completion(&res->completion); + return res->lksb.sb_status; +} + +static int dlm_unlock_sync(struct dlm_lock_resource *res) +{ + return dlm_lock_sync(res, DLM_LOCK_NL); +} + +static struct dlm_lock_resource *lockres_init(struct mddev *mddev, + char *name, void (*bastfn)(void *arg, int mode), int with_lvb) +{ + struct dlm_lock_resource *res = NULL; + int ret, namelen; + struct md_cluster_info *cinfo = mddev->cluster_info; + + res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL); + if (!res) + return NULL; + res->ls = cinfo->lockspace; + res->mddev = mddev; + namelen = strlen(name); + res->name = kzalloc(namelen + 1, GFP_KERNEL); + if (!res->name) { + pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name); + goto out_err; + } + strlcpy(res->name, name, namelen + 1); + if (with_lvb) { + res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL); + if (!res->lksb.sb_lvbptr) { + pr_err("md-cluster: Unable to allocate LVB for resource %s\n", name); + goto out_err; + } + res->flags = DLM_LKF_VALBLK; + } + + if (bastfn) + res->bast = bastfn; + + res->flags |= DLM_LKF_EXPEDITE; + + ret = dlm_lock_sync(res, DLM_LOCK_NL); + if (ret) { + pr_err("md-cluster: Unable to lock NL on new lock resource %s\n", name); + goto out_err; + } + res->flags &= ~DLM_LKF_EXPEDITE; + res->flags |= DLM_LKF_CONVERT; + + return res; +out_err: + kfree(res->lksb.sb_lvbptr); + kfree(res->name); + kfree(res); + return NULL; +} + +static void lockres_free(struct dlm_lock_resource *res) +{ + if (!res) + return; + + init_completion(&res->completion); + dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res); + wait_for_completion(&res->completion); + + kfree(res->name); + kfree(res->lksb.sb_lvbptr); + kfree(res); +} + +static char *pretty_uuid(char *dest, char *src) +{ + int i, len = 0; + + for (i = 0; i < 16; i++) { + if (i == 4 || i == 6 || i == 8 || i == 10) + len += sprintf(dest + len, "-"); + len += sprintf(dest + len, "%02x", (__u8)src[i]); + } + return dest; +} + +static void add_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres, + sector_t lo, sector_t hi) +{ + struct resync_info *ri; + + ri = (struct resync_info *)lockres->lksb.sb_lvbptr; + ri->lo = cpu_to_le64(lo); + ri->hi = cpu_to_le64(hi); +} + +static struct suspend_info *read_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres) +{ + struct resync_info ri; + struct suspend_info *s = NULL; + sector_t hi = 0; + + dlm_lock_sync(lockres, DLM_LOCK_CR); + memcpy(&ri, lockres->lksb.sb_lvbptr, sizeof(struct resync_info)); + hi = le64_to_cpu(ri.hi); + if (ri.hi > 0) { + s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL); + if (!s) + goto out; + s->hi = hi; + s->lo = le64_to_cpu(ri.lo); + } + dlm_unlock_sync(lockres); +out: + return s; +} + +static void recover_bitmaps(struct md_thread *thread) +{ + struct mddev *mddev = thread->mddev; + struct md_cluster_info *cinfo = mddev->cluster_info; + struct dlm_lock_resource *bm_lockres; + char str[64]; + int slot, ret; + struct suspend_info *s, *tmp; + sector_t lo, hi; + + while (cinfo->recovery_map) { + slot = fls64((u64)cinfo->recovery_map) - 1; + + /* Clear suspend_area associated with the bitmap */ + spin_lock_irq(&cinfo->suspend_lock); + list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list) + if (slot == s->slot) { + list_del(&s->list); + kfree(s); + } + spin_unlock_irq(&cinfo->suspend_lock); + + snprintf(str, 64, "bitmap%04d", slot); + bm_lockres = lockres_init(mddev, str, NULL, 1); + if (!bm_lockres) { + pr_err("md-cluster: Cannot initialize bitmaps\n"); + goto clear_bit; + } + + ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW); + if (ret) { + pr_err("md-cluster: Could not DLM lock %s: %d\n", + str, ret); + goto clear_bit; + } + ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi, true); + if (ret) { + pr_err("md-cluster: Could not copy data from bitmap %d\n", slot); + goto dlm_unlock; + } + if (hi > 0) { + /* TODO:Wait for current resync to get over */ + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + if (lo < mddev->recovery_cp) + mddev->recovery_cp = lo; + md_check_recovery(mddev); + } +dlm_unlock: + dlm_unlock_sync(bm_lockres); +clear_bit: + clear_bit(slot, &cinfo->recovery_map); + } +} + +static void recover_prep(void *arg) +{ +} + +static void recover_slot(void *arg, struct dlm_slot *slot) +{ + struct mddev *mddev = arg; + struct md_cluster_info *cinfo = mddev->cluster_info; + + pr_info("md-cluster: %s Node %d/%d down. My slot: %d. Initiating recovery.\n", + mddev->bitmap_info.cluster_name, + slot->nodeid, slot->slot, + cinfo->slot_number); + set_bit(slot->slot - 1, &cinfo->recovery_map); + if (!cinfo->recovery_thread) { + cinfo->recovery_thread = md_register_thread(recover_bitmaps, + mddev, "recover"); + if (!cinfo->recovery_thread) { + pr_warn("md-cluster: Could not create recovery thread\n"); + return; + } + } + md_wakeup_thread(cinfo->recovery_thread); +} + +static void recover_done(void *arg, struct dlm_slot *slots, + int num_slots, int our_slot, + uint32_t generation) +{ + struct mddev *mddev = arg; + struct md_cluster_info *cinfo = mddev->cluster_info; + + cinfo->slot_number = our_slot; + complete(&cinfo->completion); +} + +static const struct dlm_lockspace_ops md_ls_ops = { + .recover_prep = recover_prep, + .recover_slot = recover_slot, + .recover_done = recover_done, +}; + +/* + * The BAST function for the ack lock resource + * This function wakes up the receive thread in + * order to receive and process the message. + */ +static void ack_bast(void *arg, int mode) +{ + struct dlm_lock_resource *res = (struct dlm_lock_resource *)arg; + struct md_cluster_info *cinfo = res->mddev->cluster_info; + + if (mode == DLM_LOCK_EX) + md_wakeup_thread(cinfo->recv_thread); +} + +static void __remove_suspend_info(struct md_cluster_info *cinfo, int slot) +{ + struct suspend_info *s, *tmp; + + list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list) + if (slot == s->slot) { + pr_info("%s:%d Deleting suspend_info: %d\n", + __func__, __LINE__, slot); + list_del(&s->list); + kfree(s); + break; + } +} + +static void remove_suspend_info(struct md_cluster_info *cinfo, int slot) +{ + spin_lock_irq(&cinfo->suspend_lock); + __remove_suspend_info(cinfo, slot); + spin_unlock_irq(&cinfo->suspend_lock); +} + + +static void process_suspend_info(struct md_cluster_info *cinfo, + int slot, sector_t lo, sector_t hi) +{ + struct suspend_info *s; + + if (!hi) { + remove_suspend_info(cinfo, slot); + return; + } + s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL); + if (!s) + return; + s->slot = slot; + s->lo = lo; + s->hi = hi; + spin_lock_irq(&cinfo->suspend_lock); + /* Remove existing entry (if exists) before adding */ + __remove_suspend_info(cinfo, slot); + list_add(&s->list, &cinfo->suspend_list); + spin_unlock_irq(&cinfo->suspend_lock); +} + +static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg) +{ + char disk_uuid[64]; + struct md_cluster_info *cinfo = mddev->cluster_info; + char event_name[] = "EVENT=ADD_DEVICE"; + char raid_slot[16]; + char *envp[] = {event_name, disk_uuid, raid_slot, NULL}; + int len; + + len = snprintf(disk_uuid, 64, "DEVICE_UUID="); + pretty_uuid(disk_uuid + len, cmsg->uuid); + snprintf(raid_slot, 16, "RAID_DISK=%d", cmsg->raid_slot); + pr_info("%s:%d Sending kobject change with %s and %s\n", __func__, __LINE__, disk_uuid, raid_slot); + init_completion(&cinfo->newdisk_completion); + set_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state); + kobject_uevent_env(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE, envp); + wait_for_completion_timeout(&cinfo->newdisk_completion, + NEW_DEV_TIMEOUT); + clear_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state); +} + + +static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + md_reload_sb(mddev); + dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR); +} + +static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg) +{ + struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot); + + if (rdev) + md_kick_rdev_from_array(rdev); + else + pr_warn("%s: %d Could not find disk(%d) to REMOVE\n", __func__, __LINE__, msg->raid_slot); +} + +static void process_readd_disk(struct mddev *mddev, struct cluster_msg *msg) +{ + struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot); + + if (rdev && test_bit(Faulty, &rdev->flags)) + clear_bit(Faulty, &rdev->flags); + else + pr_warn("%s: %d Could not find disk(%d) which is faulty", __func__, __LINE__, msg->raid_slot); +} + +static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg) +{ + switch (msg->type) { + case METADATA_UPDATED: + pr_info("%s: %d Received message: METADATA_UPDATE from %d\n", + __func__, __LINE__, msg->slot); + process_metadata_update(mddev, msg); + break; + case RESYNCING: + pr_info("%s: %d Received message: RESYNCING from %d\n", + __func__, __LINE__, msg->slot); + process_suspend_info(mddev->cluster_info, msg->slot, + msg->low, msg->high); + break; + case NEWDISK: + pr_info("%s: %d Received message: NEWDISK from %d\n", + __func__, __LINE__, msg->slot); + process_add_new_disk(mddev, msg); + break; + case REMOVE: + pr_info("%s: %d Received REMOVE from %d\n", + __func__, __LINE__, msg->slot); + process_remove_disk(mddev, msg); + break; + case RE_ADD: + pr_info("%s: %d Received RE_ADD from %d\n", + __func__, __LINE__, msg->slot); + process_readd_disk(mddev, msg); + break; + default: + pr_warn("%s:%d Received unknown message from %d\n", + __func__, __LINE__, msg->slot); + } +} + +/* + * thread for receiving message + */ +static void recv_daemon(struct md_thread *thread) +{ + struct md_cluster_info *cinfo = thread->mddev->cluster_info; + struct dlm_lock_resource *ack_lockres = cinfo->ack_lockres; + struct dlm_lock_resource *message_lockres = cinfo->message_lockres; + struct cluster_msg msg; + + /*get CR on Message*/ + if (dlm_lock_sync(message_lockres, DLM_LOCK_CR)) { + pr_err("md/raid1:failed to get CR on MESSAGE\n"); + return; + } + + /* read lvb and wake up thread to process this message_lockres */ + memcpy(&msg, message_lockres->lksb.sb_lvbptr, sizeof(struct cluster_msg)); + process_recvd_msg(thread->mddev, &msg); + + /*release CR on ack_lockres*/ + dlm_unlock_sync(ack_lockres); + /*up-convert to EX on message_lockres*/ + dlm_lock_sync(message_lockres, DLM_LOCK_EX); + /*get CR on ack_lockres again*/ + dlm_lock_sync(ack_lockres, DLM_LOCK_CR); + /*release CR on message_lockres*/ + dlm_unlock_sync(message_lockres); +} + +/* lock_comm() + * Takes the lock on the TOKEN lock resource so no other + * node can communicate while the operation is underway. + */ +static int lock_comm(struct md_cluster_info *cinfo) +{ + int error; + + error = dlm_lock_sync(cinfo->token_lockres, DLM_LOCK_EX); + if (error) + pr_err("md-cluster(%s:%d): failed to get EX on TOKEN (%d)\n", + __func__, __LINE__, error); + return error; +} + +static void unlock_comm(struct md_cluster_info *cinfo) +{ + dlm_unlock_sync(cinfo->token_lockres); +} + +/* __sendmsg() + * This function performs the actual sending of the message. This function is + * usually called after performing the encompassing operation + * The function: + * 1. Grabs the message lockresource in EX mode + * 2. Copies the message to the message LVB + * 3. Downconverts message lockresource to CR + * 4. Upconverts ack lock resource from CR to EX. This forces the BAST on other nodes + * and the other nodes read the message. The thread will wait here until all other + * nodes have released ack lock resource. + * 5. Downconvert ack lockresource to CR + */ +static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg) +{ + int error; + int slot = cinfo->slot_number - 1; + + cmsg->slot = cpu_to_le32(slot); + /*get EX on Message*/ + error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_EX); + if (error) { + pr_err("md-cluster: failed to get EX on MESSAGE (%d)\n", error); + goto failed_message; + } + + memcpy(cinfo->message_lockres->lksb.sb_lvbptr, (void *)cmsg, + sizeof(struct cluster_msg)); + /*down-convert EX to CR on Message*/ + error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_CR); + if (error) { + pr_err("md-cluster: failed to convert EX to CR on MESSAGE(%d)\n", + error); + goto failed_message; + } + + /*up-convert CR to EX on Ack*/ + error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_EX); + if (error) { + pr_err("md-cluster: failed to convert CR to EX on ACK(%d)\n", + error); + goto failed_ack; + } + + /*down-convert EX to CR on Ack*/ + error = dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR); + if (error) { + pr_err("md-cluster: failed to convert EX to CR on ACK(%d)\n", + error); + goto failed_ack; + } + +failed_ack: + dlm_unlock_sync(cinfo->message_lockres); +failed_message: + return error; +} + +static int sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg) +{ + int ret; + + lock_comm(cinfo); + ret = __sendmsg(cinfo, cmsg); + unlock_comm(cinfo); + return ret; +} + +static int gather_all_resync_info(struct mddev *mddev, int total_slots) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + int i, ret = 0; + struct dlm_lock_resource *bm_lockres; + struct suspend_info *s; + char str[64]; + + + for (i = 0; i < total_slots; i++) { + memset(str, '\0', 64); + snprintf(str, 64, "bitmap%04d", i); + bm_lockres = lockres_init(mddev, str, NULL, 1); + if (!bm_lockres) + return -ENOMEM; + if (i == (cinfo->slot_number - 1)) + continue; + + bm_lockres->flags |= DLM_LKF_NOQUEUE; + ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW); + if (ret == -EAGAIN) { + memset(bm_lockres->lksb.sb_lvbptr, '\0', LVB_SIZE); + s = read_resync_info(mddev, bm_lockres); + if (s) { + pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n", + __func__, __LINE__, + (unsigned long long) s->lo, + (unsigned long long) s->hi, i); + spin_lock_irq(&cinfo->suspend_lock); + s->slot = i; + list_add(&s->list, &cinfo->suspend_list); + spin_unlock_irq(&cinfo->suspend_lock); + } + ret = 0; + lockres_free(bm_lockres); + continue; + } + if (ret) + goto out; + /* TODO: Read the disk bitmap sb and check if it needs recovery */ + dlm_unlock_sync(bm_lockres); + lockres_free(bm_lockres); + } +out: + return ret; +} + +static int join(struct mddev *mddev, int nodes) +{ + struct md_cluster_info *cinfo; + int ret, ops_rv; + char str[64]; + + if (!try_module_get(THIS_MODULE)) + return -ENOENT; + + cinfo = kzalloc(sizeof(struct md_cluster_info), GFP_KERNEL); + if (!cinfo) + return -ENOMEM; + + init_completion(&cinfo->completion); + + mutex_init(&cinfo->sb_mutex); + mddev->cluster_info = cinfo; + + memset(str, 0, 64); + pretty_uuid(str, mddev->uuid); + ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name, + DLM_LSFL_FS, LVB_SIZE, + &md_ls_ops, mddev, &ops_rv, &cinfo->lockspace); + if (ret) + goto err; + wait_for_completion(&cinfo->completion); + if (nodes < cinfo->slot_number) { + pr_err("md-cluster: Slot allotted(%d) is greater than available slots(%d).", + cinfo->slot_number, nodes); + ret = -ERANGE; + goto err; + } + cinfo->sb_lock = lockres_init(mddev, "cmd-super", + NULL, 0); + if (!cinfo->sb_lock) { + ret = -ENOMEM; + goto err; + } + /* Initiate the communication resources */ + ret = -ENOMEM; + cinfo->recv_thread = md_register_thread(recv_daemon, mddev, "cluster_recv"); + if (!cinfo->recv_thread) { + pr_err("md-cluster: cannot allocate memory for recv_thread!\n"); + goto err; + } + cinfo->message_lockres = lockres_init(mddev, "message", NULL, 1); + if (!cinfo->message_lockres) + goto err; + cinfo->token_lockres = lockres_init(mddev, "token", NULL, 0); + if (!cinfo->token_lockres) + goto err; + cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0); + if (!cinfo->ack_lockres) + goto err; + cinfo->no_new_dev_lockres = lockres_init(mddev, "no-new-dev", NULL, 0); + if (!cinfo->no_new_dev_lockres) + goto err; + + /* get sync CR lock on ACK. */ + if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR)) + pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n", + ret); + /* get sync CR lock on no-new-dev. */ + if (dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR)) + pr_err("md-cluster: failed to get a sync CR lock on no-new-dev!(%d)\n", ret); + + + pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number); + snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1); + cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1); + if (!cinfo->bitmap_lockres) + goto err; + if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) { + pr_err("Failed to get bitmap lock\n"); + ret = -EINVAL; + goto err; + } + + INIT_LIST_HEAD(&cinfo->suspend_list); + spin_lock_init(&cinfo->suspend_lock); + + ret = gather_all_resync_info(mddev, nodes); + if (ret) + goto err; + + return 0; +err: + lockres_free(cinfo->message_lockres); + lockres_free(cinfo->token_lockres); + lockres_free(cinfo->ack_lockres); + lockres_free(cinfo->no_new_dev_lockres); + lockres_free(cinfo->bitmap_lockres); + lockres_free(cinfo->sb_lock); + if (cinfo->lockspace) + dlm_release_lockspace(cinfo->lockspace, 2); + mddev->cluster_info = NULL; + kfree(cinfo); + module_put(THIS_MODULE); + return ret; +} + +static int leave(struct mddev *mddev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + if (!cinfo) + return 0; + md_unregister_thread(&cinfo->recovery_thread); + md_unregister_thread(&cinfo->recv_thread); + lockres_free(cinfo->message_lockres); + lockres_free(cinfo->token_lockres); + lockres_free(cinfo->ack_lockres); + lockres_free(cinfo->no_new_dev_lockres); + lockres_free(cinfo->sb_lock); + lockres_free(cinfo->bitmap_lockres); + dlm_release_lockspace(cinfo->lockspace, 2); + return 0; +} + +/* slot_number(): Returns the MD slot number to use + * DLM starts the slot numbers from 1, wheras cluster-md + * wants the number to be from zero, so we deduct one + */ +static int slot_number(struct mddev *mddev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + return cinfo->slot_number - 1; +} + +static void resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + add_resync_info(mddev, cinfo->bitmap_lockres, lo, hi); + /* Re-acquire the lock to refresh LVB */ + dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW); +} + +static int metadata_update_start(struct mddev *mddev) +{ + return lock_comm(mddev->cluster_info); +} + +static int metadata_update_finish(struct mddev *mddev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + struct cluster_msg cmsg; + int ret; + + memset(&cmsg, 0, sizeof(cmsg)); + cmsg.type = cpu_to_le32(METADATA_UPDATED); + ret = __sendmsg(cinfo, &cmsg); + unlock_comm(cinfo); + return ret; +} + +static int metadata_update_cancel(struct mddev *mddev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + return dlm_unlock_sync(cinfo->token_lockres); +} + +static int resync_send(struct mddev *mddev, enum msg_type type, + sector_t lo, sector_t hi) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + struct cluster_msg cmsg; + int slot = cinfo->slot_number - 1; + + pr_info("%s:%d lo: %llu hi: %llu\n", __func__, __LINE__, + (unsigned long long)lo, + (unsigned long long)hi); + resync_info_update(mddev, lo, hi); + cmsg.type = cpu_to_le32(type); + cmsg.slot = cpu_to_le32(slot); + cmsg.low = cpu_to_le64(lo); + cmsg.high = cpu_to_le64(hi); + return sendmsg(cinfo, &cmsg); +} + +static int resync_start(struct mddev *mddev, sector_t lo, sector_t hi) +{ + pr_info("%s:%d\n", __func__, __LINE__); + return resync_send(mddev, RESYNCING, lo, hi); +} + +static void resync_finish(struct mddev *mddev) +{ + pr_info("%s:%d\n", __func__, __LINE__); + resync_send(mddev, RESYNCING, 0, 0); +} + +static int area_resyncing(struct mddev *mddev, sector_t lo, sector_t hi) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + int ret = 0; + struct suspend_info *s; + + spin_lock_irq(&cinfo->suspend_lock); + if (list_empty(&cinfo->suspend_list)) + goto out; + list_for_each_entry(s, &cinfo->suspend_list, list) + if (hi > s->lo && lo < s->hi) { + ret = 1; + break; + } +out: + spin_unlock_irq(&cinfo->suspend_lock); + return ret; +} + +static int add_new_disk_start(struct mddev *mddev, struct md_rdev *rdev) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + struct cluster_msg cmsg; + int ret = 0; + struct mdp_superblock_1 *sb = page_address(rdev->sb_page); + char *uuid = sb->device_uuid; + + memset(&cmsg, 0, sizeof(cmsg)); + cmsg.type = cpu_to_le32(NEWDISK); + memcpy(cmsg.uuid, uuid, 16); + cmsg.raid_slot = rdev->desc_nr; + lock_comm(cinfo); + ret = __sendmsg(cinfo, &cmsg); + if (ret) + return ret; + cinfo->no_new_dev_lockres->flags |= DLM_LKF_NOQUEUE; + ret = dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_EX); + cinfo->no_new_dev_lockres->flags &= ~DLM_LKF_NOQUEUE; + /* Some node does not "see" the device */ + if (ret == -EAGAIN) + ret = -ENOENT; + else + dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR); + return ret; +} + +static int add_new_disk_finish(struct mddev *mddev) +{ + struct cluster_msg cmsg; + struct md_cluster_info *cinfo = mddev->cluster_info; + int ret; + /* Write sb and inform others */ + md_update_sb(mddev, 1); + cmsg.type = METADATA_UPDATED; + ret = __sendmsg(cinfo, &cmsg); + unlock_comm(cinfo); + return ret; +} + +static int new_disk_ack(struct mddev *mddev, bool ack) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + if (!test_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state)) { + pr_warn("md-cluster(%s): Spurious cluster confirmation\n", mdname(mddev)); + return -EINVAL; + } + + if (ack) + dlm_unlock_sync(cinfo->no_new_dev_lockres); + complete(&cinfo->newdisk_completion); + return 0; +} + +static int remove_disk(struct mddev *mddev, struct md_rdev *rdev) +{ + struct cluster_msg cmsg; + struct md_cluster_info *cinfo = mddev->cluster_info; + cmsg.type = REMOVE; + cmsg.raid_slot = rdev->desc_nr; + return __sendmsg(cinfo, &cmsg); +} + +static int gather_bitmaps(struct md_rdev *rdev) +{ + int sn, err; + sector_t lo, hi; + struct cluster_msg cmsg; + struct mddev *mddev = rdev->mddev; + struct md_cluster_info *cinfo = mddev->cluster_info; + + cmsg.type = RE_ADD; + cmsg.raid_slot = rdev->desc_nr; + err = sendmsg(cinfo, &cmsg); + if (err) + goto out; + + for (sn = 0; sn < mddev->bitmap_info.nodes; sn++) { + if (sn == (cinfo->slot_number - 1)) + continue; + err = bitmap_copy_from_slot(mddev, sn, &lo, &hi, false); + if (err) { + pr_warn("md-cluster: Could not gather bitmaps from slot %d", sn); + goto out; + } + if ((hi > 0) && (lo < mddev->recovery_cp)) + mddev->recovery_cp = lo; + } +out: + return err; +} + +static struct md_cluster_operations cluster_ops = { + .join = join, + .leave = leave, + .slot_number = slot_number, + .resync_info_update = resync_info_update, + .resync_start = resync_start, + .resync_finish = resync_finish, + .metadata_update_start = metadata_update_start, + .metadata_update_finish = metadata_update_finish, + .metadata_update_cancel = metadata_update_cancel, + .area_resyncing = area_resyncing, + .add_new_disk_start = add_new_disk_start, + .add_new_disk_finish = add_new_disk_finish, + .new_disk_ack = new_disk_ack, + .remove_disk = remove_disk, + .gather_bitmaps = gather_bitmaps, +}; + +static int __init cluster_init(void) +{ + pr_warn("md-cluster: EXPERIMENTAL. Use with caution\n"); + pr_info("Registering Cluster MD functions\n"); + register_md_cluster_operations(&cluster_ops, THIS_MODULE); + return 0; +} + +static void cluster_exit(void) +{ + unregister_md_cluster_operations(); +} + +module_init(cluster_init); +module_exit(cluster_exit); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Clustering support for MD"); diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h new file mode 100644 index 000000000000..6817ee00e053 --- /dev/null +++ b/drivers/md/md-cluster.h @@ -0,0 +1,29 @@ + + +#ifndef _MD_CLUSTER_H +#define _MD_CLUSTER_H + +#include "md.h" + +struct mddev; +struct md_rdev; + +struct md_cluster_operations { + int (*join)(struct mddev *mddev, int nodes); + int (*leave)(struct mddev *mddev); + int (*slot_number)(struct mddev *mddev); + void (*resync_info_update)(struct mddev *mddev, sector_t lo, sector_t hi); + int (*resync_start)(struct mddev *mddev, sector_t lo, sector_t hi); + void (*resync_finish)(struct mddev *mddev); + int (*metadata_update_start)(struct mddev *mddev); + int (*metadata_update_finish)(struct mddev *mddev); + int (*metadata_update_cancel)(struct mddev *mddev); + int (*area_resyncing)(struct mddev *mddev, sector_t lo, sector_t hi); + int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev); + int (*add_new_disk_finish)(struct mddev *mddev); + int (*new_disk_ack)(struct mddev *mddev, bool ack); + int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev); + int (*gather_bitmaps)(struct md_rdev *rdev); +}; + +#endif /* _MD_CLUSTER_H */ diff --git a/drivers/md/md.c b/drivers/md/md.c index c8d2bac4e28b..593a02476c78 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -53,6 +53,7 @@ #include <linux/slab.h> #include "md.h" #include "bitmap.h" +#include "md-cluster.h" #ifndef MODULE static void autostart_arrays(int part); @@ -66,6 +67,11 @@ static void autostart_arrays(int part); static LIST_HEAD(pers_list); static DEFINE_SPINLOCK(pers_lock); +struct md_cluster_operations *md_cluster_ops; +EXPORT_SYMBOL(md_cluster_ops); +struct module *md_cluster_mod; +EXPORT_SYMBOL(md_cluster_mod); + static DECLARE_WAIT_QUEUE_HEAD(resync_wait); static struct workqueue_struct *md_wq; static struct workqueue_struct *md_misc_wq; @@ -249,6 +255,7 @@ static void md_make_request(struct request_queue *q, struct bio *bio) const int rw = bio_data_dir(bio); struct mddev *mddev = q->queuedata; unsigned int sectors; + int cpu; if (mddev == NULL || mddev->pers == NULL || !mddev->ready) { @@ -284,7 +291,10 @@ static void md_make_request(struct request_queue *q, struct bio *bio) sectors = bio_sectors(bio); mddev->pers->make_request(mddev, bio); - generic_start_io_acct(rw, sectors, &mddev->gendisk->part0); + cpu = part_stat_lock(); + part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); + part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); + part_stat_unlock(); if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) wake_up(&mddev->sb_wait); @@ -636,7 +646,7 @@ void mddev_unlock(struct mddev *mddev) } EXPORT_SYMBOL_GPL(mddev_unlock); -static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr) +struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr) { struct md_rdev *rdev; @@ -646,6 +656,7 @@ static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr) return NULL; } +EXPORT_SYMBOL_GPL(md_find_rdev_nr_rcu); static struct md_rdev *find_rdev(struct mddev *mddev, dev_t dev) { @@ -2043,11 +2054,11 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) int choice = 0; if (mddev->pers) choice = mddev->raid_disks; - while (find_rdev_nr_rcu(mddev, choice)) + while (md_find_rdev_nr_rcu(mddev, choice)) choice++; rdev->desc_nr = choice; } else { - if (find_rdev_nr_rcu(mddev, rdev->desc_nr)) { + if (md_find_rdev_nr_rcu(mddev, rdev->desc_nr)) { rcu_read_unlock(); return -EBUSY; } @@ -2162,11 +2173,12 @@ static void export_rdev(struct md_rdev *rdev) kobject_put(&rdev->kobj); } -static void kick_rdev_from_array(struct md_rdev *rdev) +void md_kick_rdev_from_array(struct md_rdev *rdev) { unbind_rdev_from_array(rdev); export_rdev(rdev); } +EXPORT_SYMBOL_GPL(md_kick_rdev_from_array); static void export_array(struct mddev *mddev) { @@ -2175,7 +2187,7 @@ static void export_array(struct mddev *mddev) while (!list_empty(&mddev->disks)) { rdev = list_first_entry(&mddev->disks, struct md_rdev, same_set); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); } mddev->raid_disks = 0; mddev->major_version = 0; @@ -2204,7 +2216,7 @@ static void sync_sbs(struct mddev *mddev, int nospares) } } -static void md_update_sb(struct mddev *mddev, int force_change) +void md_update_sb(struct mddev *mddev, int force_change) { struct md_rdev *rdev; int sync_req; @@ -2365,6 +2377,37 @@ repeat: wake_up(&rdev->blocked_wait); } } +EXPORT_SYMBOL(md_update_sb); + +static int add_bound_rdev(struct md_rdev *rdev) +{ + struct mddev *mddev = rdev->mddev; + int err = 0; + + if (!mddev->pers->hot_remove_disk) { + /* If there is hot_add_disk but no hot_remove_disk + * then added disks for geometry changes, + * and should be added immediately. + */ + super_types[mddev->major_version]. + validate_super(mddev, rdev); + err = mddev->pers->hot_add_disk(mddev, rdev); + if (err) { + unbind_rdev_from_array(rdev); + export_rdev(rdev); + return err; + } + } + sysfs_notify_dirent_safe(rdev->sysfs_state); + + set_bit(MD_CHANGE_DEVS, &mddev->flags); + if (mddev->degraded) + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_new_event(mddev); + md_wakeup_thread(mddev->thread); + return 0; +} /* words written to sysfs files may, or may not, be \n terminated. * We want to accept with case. For this we use cmd_match. @@ -2467,10 +2510,16 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) err = -EBUSY; else { struct mddev *mddev = rdev->mddev; - kick_rdev_from_array(rdev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->remove_disk(mddev, rdev); + md_kick_rdev_from_array(rdev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); if (mddev->pers) md_update_sb(mddev, 1); md_new_event(mddev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); err = 0; } } else if (cmd_match(buf, "writemostly")) { @@ -2549,13 +2598,28 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) clear_bit(Replacement, &rdev->flags); err = 0; } + } else if (cmd_match(buf, "re-add")) { + if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1)) { + /* clear_bit is performed _after_ all the devices + * have their local Faulty bit cleared. If any writes + * happen in the meantime in the local node, they + * will land in the local bitmap, which will be synced + * by this node eventually + */ + if (!mddev_is_clustered(rdev->mddev) || + (err = md_cluster_ops->gather_bitmaps(rdev)) == 0) { + clear_bit(Faulty, &rdev->flags); + err = add_bound_rdev(rdev); + } + } else + err = -EBUSY; } if (!err) sysfs_notify_dirent_safe(rdev->sysfs_state); return err ? err : len; } static struct rdev_sysfs_entry rdev_state = -__ATTR(state, S_IRUGO|S_IWUSR, state_show, state_store); +__ATTR_PREALLOC(state, S_IRUGO|S_IWUSR, state_show, state_store); static ssize_t errors_show(struct md_rdev *rdev, char *page) @@ -3123,7 +3187,7 @@ static void analyze_sbs(struct mddev *mddev) "md: fatal superblock inconsistency in %s" " -- removing from array\n", bdevname(rdev->bdev,b)); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); } super_types[mddev->major_version]. @@ -3138,18 +3202,27 @@ static void analyze_sbs(struct mddev *mddev) "md: %s: %s: only %d devices permitted\n", mdname(mddev), bdevname(rdev->bdev, b), mddev->max_disks); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); continue; } - if (rdev != freshest) + if (rdev != freshest) { if (super_types[mddev->major_version]. validate_super(mddev, rdev)) { printk(KERN_WARNING "md: kicking non-fresh %s" " from array!\n", bdevname(rdev->bdev,b)); - kick_rdev_from_array(rdev); + md_kick_rdev_from_array(rdev); continue; } + /* No device should have a Candidate flag + * when reading devices + */ + if (test_bit(Candidate, &rdev->flags)) { + pr_info("md: kicking Cluster Candidate %s from array!\n", + bdevname(rdev->bdev, b)); + md_kick_rdev_from_array(rdev); + } + } if (mddev->level == LEVEL_MULTIPATH) { rdev->desc_nr = i++; rdev->raid_disk = rdev->desc_nr; @@ -3638,7 +3711,8 @@ resync_start_store(struct mddev *mddev, const char *buf, size_t len) return err ?: len; } static struct md_sysfs_entry md_resync_start = -__ATTR(resync_start, S_IRUGO|S_IWUSR, resync_start_show, resync_start_store); +__ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR, + resync_start_show, resync_start_store); /* * The array state can be: @@ -3851,7 +3925,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) return err ?: len; } static struct md_sysfs_entry md_array_state = -__ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store); +__ATTR_PREALLOC(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store); static ssize_t max_corrected_read_errors_show(struct mddev *mddev, char *page) { @@ -4003,8 +4077,12 @@ size_store(struct mddev *mddev, const char *buf, size_t len) if (err) return err; if (mddev->pers) { + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); err = update_size(mddev, sectors); md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); } else { if (mddev->dev_sectors == 0 || mddev->dev_sectors > sectors) @@ -4101,7 +4179,7 @@ out_unlock: } static struct md_sysfs_entry md_metadata = -__ATTR(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store); +__ATTR_PREALLOC(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store); static ssize_t action_show(struct mddev *mddev, char *page) @@ -4189,7 +4267,7 @@ action_store(struct mddev *mddev, const char *page, size_t len) } static struct md_sysfs_entry md_scan_mode = -__ATTR(sync_action, S_IRUGO|S_IWUSR, action_show, action_store); +__ATTR_PREALLOC(sync_action, S_IRUGO|S_IWUSR, action_show, action_store); static ssize_t last_sync_action_show(struct mddev *mddev, char *page) @@ -4335,7 +4413,8 @@ sync_completed_show(struct mddev *mddev, char *page) return sprintf(page, "%llu / %llu\n", resync, max_sectors); } -static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed); +static struct md_sysfs_entry md_sync_completed = + __ATTR_PREALLOC(sync_completed, S_IRUGO, sync_completed_show, NULL); static ssize_t min_sync_show(struct mddev *mddev, char *page) @@ -4348,7 +4427,6 @@ min_sync_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long long min; int err; - int chunk; if (kstrtoull(buf, 10, &min)) return -EINVAL; @@ -4362,16 +4440,8 @@ min_sync_store(struct mddev *mddev, const char *buf, size_t len) if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) goto out_unlock; - /* Must be a multiple of chunk_size */ - chunk = mddev->chunk_sectors; - if (chunk) { - sector_t temp = min; - - err = -EINVAL; - if (sector_div(temp, chunk)) - goto out_unlock; - } - mddev->resync_min = min; + /* Round down to multiple of 4K for safety */ + mddev->resync_min = round_down(min, 8); err = 0; out_unlock: @@ -4748,12 +4818,12 @@ static void md_free(struct kobject *ko) if (mddev->sysfs_state) sysfs_put(mddev->sysfs_state); + if (mddev->queue) + blk_cleanup_queue(mddev->queue); if (mddev->gendisk) { del_gendisk(mddev->gendisk); put_disk(mddev->gendisk); } - if (mddev->queue) - blk_cleanup_queue(mddev->queue); kfree(mddev); } @@ -5071,14 +5141,21 @@ int md_run(struct mddev *mddev) } if (err == 0 && pers->sync_request && (mddev->bitmap_info.file || mddev->bitmap_info.offset)) { - err = bitmap_create(mddev); - if (err) + struct bitmap *bitmap; + + bitmap = bitmap_create(mddev, -1); + if (IS_ERR(bitmap)) { + err = PTR_ERR(bitmap); printk(KERN_ERR "%s: failed to create bitmap (%d)\n", mdname(mddev), err); + } else + mddev->bitmap = bitmap; + } if (err) { mddev_detach(mddev); - pers->free(mddev, mddev->private); + if (mddev->private) + pers->free(mddev, mddev->private); module_put(pers->owner); bitmap_destroy(mddev); return err; @@ -5225,6 +5302,8 @@ static void md_clean(struct mddev *mddev) static void __md_stop_writes(struct mddev *mddev) { + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); flush_workqueue(md_misc_wq); if (mddev->sync_thread) { @@ -5243,6 +5322,8 @@ static void __md_stop_writes(struct mddev *mddev) mddev->in_sync = 1; md_update_sb(mddev, 1); } + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); } void md_stop_writes(struct mddev *mddev) @@ -5629,6 +5710,8 @@ static int get_array_info(struct mddev *mddev, void __user *arg) info.state = (1<<MD_SB_CLEAN); if (mddev->bitmap && mddev->bitmap_info.offset) info.state |= (1<<MD_SB_BITMAP_PRESENT); + if (mddev_is_clustered(mddev)) + info.state |= (1<<MD_SB_CLUSTERED); info.active_disks = insync; info.working_disks = working; info.failed_disks = failed; @@ -5684,7 +5767,7 @@ static int get_disk_info(struct mddev *mddev, void __user * arg) return -EFAULT; rcu_read_lock(); - rdev = find_rdev_nr_rcu(mddev, info.number); + rdev = md_find_rdev_nr_rcu(mddev, info.number); if (rdev) { info.major = MAJOR(rdev->bdev->bd_dev); info.minor = MINOR(rdev->bdev->bd_dev); @@ -5717,6 +5800,13 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) struct md_rdev *rdev; dev_t dev = MKDEV(info->major,info->minor); + if (mddev_is_clustered(mddev) && + !(info->state & ((1 << MD_DISK_CLUSTER_ADD) | (1 << MD_DISK_CANDIDATE)))) { + pr_err("%s: Cannot add to clustered mddev.\n", + mdname(mddev)); + return -EINVAL; + } + if (info->major != MAJOR(dev) || info->minor != MINOR(dev)) return -EOVERFLOW; @@ -5803,31 +5893,38 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) else clear_bit(WriteMostly, &rdev->flags); + /* + * check whether the device shows up in other nodes + */ + if (mddev_is_clustered(mddev)) { + if (info->state & (1 << MD_DISK_CANDIDATE)) { + /* Through --cluster-confirm */ + set_bit(Candidate, &rdev->flags); + err = md_cluster_ops->new_disk_ack(mddev, true); + if (err) { + export_rdev(rdev); + return err; + } + } else if (info->state & (1 << MD_DISK_CLUSTER_ADD)) { + /* --add initiated by this node */ + err = md_cluster_ops->add_new_disk_start(mddev, rdev); + if (err) { + md_cluster_ops->add_new_disk_finish(mddev); + export_rdev(rdev); + return err; + } + } + } + rdev->raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); - if (!err && !mddev->pers->hot_remove_disk) { - /* If there is hot_add_disk but no hot_remove_disk - * then added disks for geometry changes, - * and should be added immediately. - */ - super_types[mddev->major_version]. - validate_super(mddev, rdev); - err = mddev->pers->hot_add_disk(mddev, rdev); - if (err) - unbind_rdev_from_array(rdev); - } if (err) export_rdev(rdev); else - sysfs_notify_dirent_safe(rdev->sysfs_state); - - set_bit(MD_CHANGE_DEVS, &mddev->flags); - if (mddev->degraded) - set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - if (!err) - md_new_event(mddev); - md_wakeup_thread(mddev->thread); + err = add_bound_rdev(rdev); + if (mddev_is_clustered(mddev) && + (info->state & (1 << MD_DISK_CLUSTER_ADD))) + md_cluster_ops->add_new_disk_finish(mddev); return err; } @@ -5888,18 +5985,29 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev) if (!rdev) return -ENXIO; + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); + clear_bit(Blocked, &rdev->flags); remove_and_add_spares(mddev, rdev); if (rdev->raid_disk >= 0) goto busy; - kick_rdev_from_array(rdev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->remove_disk(mddev, rdev); + + md_kick_rdev_from_array(rdev); md_update_sb(mddev, 1); md_new_event(mddev); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); + return 0; busy: + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_cancel(mddev); printk(KERN_WARNING "md: cannot remove active disk %s from %s ...\n", bdevname(rdev->bdev,b), mdname(mddev)); return -EBUSY; @@ -5949,12 +6057,15 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) err = -EINVAL; goto abort_export; } + + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); clear_bit(In_sync, &rdev->flags); rdev->desc_nr = -1; rdev->saved_raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); if (err) - goto abort_export; + goto abort_clustered; /* * The rest should better be atomic, we can have disk failures @@ -5965,6 +6076,8 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); /* * Kick recovery, maybe this spare has to be added to the * array immediately. @@ -5974,6 +6087,9 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) md_new_event(mddev); return 0; +abort_clustered: + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_cancel(mddev); abort_export: export_rdev(rdev); return err; @@ -6031,9 +6147,14 @@ static int set_bitmap_file(struct mddev *mddev, int fd) if (mddev->pers) { mddev->pers->quiesce(mddev, 1); if (fd >= 0) { - err = bitmap_create(mddev); - if (!err) + struct bitmap *bitmap; + + bitmap = bitmap_create(mddev, -1); + if (!IS_ERR(bitmap)) { + mddev->bitmap = bitmap; err = bitmap_load(mddev); + } else + err = PTR_ERR(bitmap); } if (fd < 0 || err) { bitmap_destroy(mddev); @@ -6286,6 +6407,8 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) return rv; } } + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); if (info->size >= 0 && mddev->dev_sectors / 2 != info->size) rv = update_size(mddev, (sector_t)info->size * 2); @@ -6293,33 +6416,49 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) rv = update_raid_disks(mddev, info->raid_disks); if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) { - if (mddev->pers->quiesce == NULL || mddev->thread == NULL) - return -EINVAL; - if (mddev->recovery || mddev->sync_thread) - return -EBUSY; + if (mddev->pers->quiesce == NULL || mddev->thread == NULL) { + rv = -EINVAL; + goto err; + } + if (mddev->recovery || mddev->sync_thread) { + rv = -EBUSY; + goto err; + } if (info->state & (1<<MD_SB_BITMAP_PRESENT)) { + struct bitmap *bitmap; /* add the bitmap */ - if (mddev->bitmap) - return -EEXIST; - if (mddev->bitmap_info.default_offset == 0) - return -EINVAL; + if (mddev->bitmap) { + rv = -EEXIST; + goto err; + } + if (mddev->bitmap_info.default_offset == 0) { + rv = -EINVAL; + goto err; + } mddev->bitmap_info.offset = mddev->bitmap_info.default_offset; mddev->bitmap_info.space = mddev->bitmap_info.default_space; mddev->pers->quiesce(mddev, 1); - rv = bitmap_create(mddev); - if (!rv) + bitmap = bitmap_create(mddev, -1); + if (!IS_ERR(bitmap)) { + mddev->bitmap = bitmap; rv = bitmap_load(mddev); + } else + rv = PTR_ERR(bitmap); if (rv) bitmap_destroy(mddev); mddev->pers->quiesce(mddev, 0); } else { /* remove the bitmap */ - if (!mddev->bitmap) - return -ENOENT; - if (mddev->bitmap->storage.file) - return -EINVAL; + if (!mddev->bitmap) { + rv = -ENOENT; + goto err; + } + if (mddev->bitmap->storage.file) { + rv = -EINVAL; + goto err; + } mddev->pers->quiesce(mddev, 1); bitmap_destroy(mddev); mddev->pers->quiesce(mddev, 0); @@ -6327,6 +6466,12 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) } } md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); + return rv; +err: + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_cancel(mddev); return rv; } @@ -6386,6 +6531,7 @@ static inline bool md_ioctl_valid(unsigned int cmd) case SET_DISK_FAULTY: case STOP_ARRAY: case STOP_ARRAY_RO: + case CLUSTERED_DISK_NACK: return true; default: return false; @@ -6658,6 +6804,13 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto unlock; } + case CLUSTERED_DISK_NACK: + if (mddev_is_clustered(mddev)) + md_cluster_ops->new_disk_ack(mddev, false); + else + err = -EINVAL; + goto unlock; + case HOT_ADD_DISK: err = hot_add_disk(mddev, new_decode_dev(arg)); goto unlock; @@ -7231,6 +7384,55 @@ int unregister_md_personality(struct md_personality *p) } EXPORT_SYMBOL(unregister_md_personality); +int register_md_cluster_operations(struct md_cluster_operations *ops, struct module *module) +{ + if (md_cluster_ops != NULL) + return -EALREADY; + spin_lock(&pers_lock); + md_cluster_ops = ops; + md_cluster_mod = module; + spin_unlock(&pers_lock); + return 0; +} +EXPORT_SYMBOL(register_md_cluster_operations); + +int unregister_md_cluster_operations(void) +{ + spin_lock(&pers_lock); + md_cluster_ops = NULL; + spin_unlock(&pers_lock); + return 0; +} +EXPORT_SYMBOL(unregister_md_cluster_operations); + +int md_setup_cluster(struct mddev *mddev, int nodes) +{ + int err; + + err = request_module("md-cluster"); + if (err) { + pr_err("md-cluster module not found.\n"); + return err; + } + + spin_lock(&pers_lock); + if (!md_cluster_ops || !try_module_get(md_cluster_mod)) { + spin_unlock(&pers_lock); + return -ENOENT; + } + spin_unlock(&pers_lock); + + return md_cluster_ops->join(mddev, nodes); +} + +void md_cluster_stop(struct mddev *mddev) +{ + if (!md_cluster_ops) + return; + md_cluster_ops->leave(mddev); + module_put(md_cluster_mod); +} + static int is_mddev_idle(struct mddev *mddev, int init) { struct md_rdev *rdev; @@ -7368,7 +7570,11 @@ int md_allow_write(struct mddev *mddev) mddev->safemode == 0) mddev->safemode = 1; spin_unlock(&mddev->lock); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); md_update_sb(mddev, 0); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); sysfs_notify_dirent_safe(mddev->sysfs_state); } else spin_unlock(&mddev->lock); @@ -7569,6 +7775,9 @@ void md_do_sync(struct md_thread *thread) md_new_event(mddev); update_time = jiffies; + if (mddev_is_clustered(mddev)) + md_cluster_ops->resync_start(mddev, j, max_sectors); + blk_start_plug(&plug); while (j < max_sectors) { sector_t sectors; @@ -7611,8 +7820,7 @@ void md_do_sync(struct md_thread *thread) if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; - sectors = mddev->pers->sync_request(mddev, j, &skipped, - currspeed < speed_min(mddev)); + sectors = mddev->pers->sync_request(mddev, j, &skipped); if (sectors == 0) { set_bit(MD_RECOVERY_INTR, &mddev->recovery); break; @@ -7629,6 +7837,8 @@ void md_do_sync(struct md_thread *thread) j += sectors; if (j > 2) mddev->curr_resync = j; + if (mddev_is_clustered(mddev)) + md_cluster_ops->resync_info_update(mddev, j, max_sectors); mddev->curr_mark_cnt = io_sectors; if (last_check == 0) /* this is the earliest that rebuild will be @@ -7670,11 +7880,18 @@ void md_do_sync(struct md_thread *thread) /((jiffies-mddev->resync_mark)/HZ +1) +1; if (currspeed > speed_min(mddev)) { - if ((currspeed > speed_max(mddev)) || - !is_mddev_idle(mddev, 0)) { + if (currspeed > speed_max(mddev)) { msleep(500); goto repeat; } + if (!is_mddev_idle(mddev, 0)) { + /* + * Give other IO more of a chance. + * The faster the devices, the less we wait. + */ + wait_event(mddev->recovery_wait, + !atomic_read(&mddev->recovery_active)); + } } } printk(KERN_INFO "md: %s: %s %s.\n",mdname(mddev), desc, @@ -7687,7 +7904,10 @@ void md_do_sync(struct md_thread *thread) wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ - mddev->pers->sync_request(mddev, max_sectors, &skipped, 1); + mddev->pers->sync_request(mddev, max_sectors, &skipped); + + if (mddev_is_clustered(mddev)) + md_cluster_ops->resync_finish(mddev); if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) && mddev->curr_resync > 2) { @@ -7918,8 +8138,13 @@ void md_check_recovery(struct mddev *mddev) sysfs_notify_dirent_safe(mddev->sysfs_state); } - if (mddev->flags & MD_UPDATE_SB_FLAGS) + if (mddev->flags & MD_UPDATE_SB_FLAGS) { + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); md_update_sb(mddev, 0); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); + } if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) { @@ -8017,6 +8242,8 @@ void md_reap_sync_thread(struct mddev *mddev) set_bit(MD_CHANGE_DEVS, &mddev->flags); } } + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_start(mddev); if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && mddev->pers->finish_reshape) mddev->pers->finish_reshape(mddev); @@ -8029,6 +8256,8 @@ void md_reap_sync_thread(struct mddev *mddev) rdev->saved_raid_disk = -1; md_update_sb(mddev, 1); + if (mddev_is_clustered(mddev)) + md_cluster_ops->metadata_update_finish(mddev); clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); @@ -8649,6 +8878,28 @@ err_wq: return ret; } +void md_reload_sb(struct mddev *mddev) +{ + struct md_rdev *rdev, *tmp; + + rdev_for_each_safe(rdev, tmp, mddev) { + rdev->sb_loaded = 0; + ClearPageUptodate(rdev->sb_page); + } + mddev->raid_disks = 0; + analyze_sbs(mddev); + rdev_for_each_safe(rdev, tmp, mddev) { + struct mdp_superblock_1 *sb = page_address(rdev->sb_page); + /* since we don't write to faulty devices, we figure out if the + * disk is faulty by comparing events + */ + if (mddev->events > sb->events) + set_bit(Faulty, &rdev->flags); + } + +} +EXPORT_SYMBOL(md_reload_sb); + #ifndef MODULE /* diff --git a/drivers/md/md.h b/drivers/md/md.h index 318ca8fd430f..4046a6c6f223 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -23,6 +23,7 @@ #include <linux/timer.h> #include <linux/wait.h> #include <linux/workqueue.h> +#include "md-cluster.h" #define MaxSector (~(sector_t)0) @@ -170,6 +171,10 @@ enum flag_bits { * a want_replacement device with same * raid_disk number. */ + Candidate, /* For clustered environments only: + * This device is seen locally but not + * by the whole cluster + */ }; #define BB_LEN_MASK (0x00000000000001FFULL) @@ -202,6 +207,8 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); extern void md_ack_all_badblocks(struct badblocks *bb); +struct md_cluster_info; + struct mddev { void *private; struct md_personality *pers; @@ -430,6 +437,8 @@ struct mddev { unsigned long daemon_sleep; /* how many jiffies between updates? */ unsigned long max_write_behind; /* write-behind mode */ int external; + int nodes; /* Maximum number of nodes in the cluster */ + char cluster_name[64]; /* Name of the cluster */ } bitmap_info; atomic_t max_corr_read_errors; /* max read retries */ @@ -448,6 +457,7 @@ struct mddev { struct work_struct flush_work; struct work_struct event_work; /* used by dm to report failure event */ void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); + struct md_cluster_info *cluster_info; }; static inline int __must_check mddev_lock(struct mddev *mddev) @@ -496,7 +506,7 @@ struct md_personality int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*spare_active) (struct mddev *mddev); - sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster); + sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped); int (*resize) (struct mddev *mddev, sector_t sectors); sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks); int (*check_reshape) (struct mddev *mddev); @@ -608,6 +618,11 @@ static inline void safe_put_page(struct page *p) extern int register_md_personality(struct md_personality *p); extern int unregister_md_personality(struct md_personality *p); +extern int register_md_cluster_operations(struct md_cluster_operations *ops, + struct module *module); +extern int unregister_md_cluster_operations(void); +extern int md_setup_cluster(struct mddev *mddev, int nodes); +extern void md_cluster_stop(struct mddev *mddev); extern struct md_thread *md_register_thread( void (*run)(struct md_thread *thread), struct mddev *mddev, @@ -654,6 +669,10 @@ extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, struct mddev *mddev); extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule); +extern void md_reload_sb(struct mddev *mddev); +extern void md_update_sb(struct mddev *mddev, int force); +extern void md_kick_rdev_from_array(struct md_rdev * rdev); +struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr); static inline int mddev_check_plugged(struct mddev *mddev) { return !!blk_check_plugged(md_unplug, mddev, @@ -669,4 +688,9 @@ static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev) } } +extern struct md_cluster_operations *md_cluster_ops; +static inline int mddev_is_clustered(struct mddev *mddev) +{ + return mddev->cluster_info && mddev->bitmap_info.nodes > 1; +} #endif /* _MD_MD_H */ diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index a13f738a7b39..2cb59a641cd2 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -271,14 +271,16 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) goto abort; } - blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); - blk_queue_io_opt(mddev->queue, - (mddev->chunk_sectors << 9) * mddev->raid_disks); - - if (!discard_supported) - queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); - else - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + if (mddev->queue) { + blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); + blk_queue_io_opt(mddev->queue, + (mddev->chunk_sectors << 9) * mddev->raid_disks); + + if (!discard_supported) + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + else + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + } pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; @@ -313,7 +315,7 @@ static struct strip_zone *find_zone(struct r0conf *conf, /* * remaps the bio to the target device. we separate two flows. - * power 2 flow and a general flow for the sake of perfromance + * power 2 flow and a general flow for the sake of performance */ static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone, sector_t sector, sector_t *sector_offset) @@ -429,9 +431,12 @@ static int raid0_run(struct mddev *mddev) } if (md_check_no_bitmap(mddev)) return -EINVAL; - blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); + + if (mddev->queue) { + blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); + } /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { @@ -448,16 +453,17 @@ static int raid0_run(struct mddev *mddev) printk(KERN_INFO "md/raid0:%s: md_size is %llu sectors.\n", mdname(mddev), (unsigned long long)mddev->array_sectors); - /* calculate the max read-ahead size. - * For read-ahead of large files to be effective, we need to - * readahead at least twice a whole stripe. i.e. number of devices - * multiplied by chunk size times 2. - * If an individual device has an ra_pages greater than the - * chunk size, then we will not drive that device as hard as it - * wants. We consider this a configuration error: a larger - * chunksize should be used in that case. - */ - { + + if (mddev->queue) { + /* calculate the max read-ahead size. + * For read-ahead of large files to be effective, we need to + * readahead at least twice a whole stripe. i.e. number of devices + * multiplied by chunk size times 2. + * If an individual device has an ra_pages greater than the + * chunk size, then we will not drive that device as hard as it + * wants. We consider this a configuration error: a larger + * chunksize should be used in that case. + */ int stripe = mddev->raid_disks * (mddev->chunk_sectors << 9) / PAGE_SIZE; if (mddev->queue->backing_dev_info.ra_pages < 2* stripe) @@ -467,8 +473,6 @@ static int raid0_run(struct mddev *mddev) dump_zones(mddev); ret = md_integrity_register(mddev); - if (ret) - raid0_free(mddev, conf); return ret; } @@ -526,6 +530,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) split = bio; } + sector = bio->bi_iter.bi_sector; zone = find_zone(mddev->private, §or); tmp_dev = map_sector(mddev, zone, sector, §or); split->bi_bdev = tmp_dev->bdev; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 4153da5d4011..9157a29c8dbf 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -539,7 +539,13 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect has_nonrot_disk = 0; choose_next_idle = 0; - choose_first = (conf->mddev->recovery_cp < this_sector + sectors); + if ((conf->mddev->recovery_cp < this_sector + sectors) || + (mddev_is_clustered(conf->mddev) && + md_cluster_ops->area_resyncing(conf->mddev, this_sector, + this_sector + sectors))) + choose_first = 1; + else + choose_first = 0; for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { sector_t dist; @@ -560,7 +566,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect if (test_bit(WriteMostly, &rdev->flags)) { /* Don't balance among write-mostly, just * use the first as a last resort */ - if (best_disk < 0) { + if (best_dist_disk < 0) { if (is_badblock(rdev, this_sector, sectors, &first_bad, &bad_sectors)) { if (first_bad < this_sector) @@ -569,7 +575,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect best_good_sectors = first_bad - this_sector; } else best_good_sectors = sectors; - best_disk = disk; + best_dist_disk = disk; + best_pending_disk = disk; } continue; } @@ -1101,8 +1108,10 @@ static void make_request(struct mddev *mddev, struct bio * bio) md_write_start(mddev, bio); /* wait on superblock update early */ if (bio_data_dir(bio) == WRITE && - bio_end_sector(bio) > mddev->suspend_lo && - bio->bi_iter.bi_sector < mddev->suspend_hi) { + ((bio_end_sector(bio) > mddev->suspend_lo && + bio->bi_iter.bi_sector < mddev->suspend_hi) || + (mddev_is_clustered(mddev) && + md_cluster_ops->area_resyncing(mddev, bio->bi_iter.bi_sector, bio_end_sector(bio))))) { /* As the suspend_* range is controlled by * userspace, we want an interruptible * wait. @@ -1113,7 +1122,10 @@ static void make_request(struct mddev *mddev, struct bio * bio) prepare_to_wait(&conf->wait_barrier, &w, TASK_INTERRUPTIBLE); if (bio_end_sector(bio) <= mddev->suspend_lo || - bio->bi_iter.bi_sector >= mddev->suspend_hi) + bio->bi_iter.bi_sector >= mddev->suspend_hi || + (mddev_is_clustered(mddev) && + !md_cluster_ops->area_resyncing(mddev, + bio->bi_iter.bi_sector, bio_end_sector(bio)))) break; schedule(); } @@ -1560,6 +1572,7 @@ static int raid1_spare_active(struct mddev *mddev) struct md_rdev *rdev = conf->mirrors[i].rdev; struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev; if (repl + && !test_bit(Candidate, &repl->flags) && repl->recovery_offset == MaxSector && !test_bit(Faulty, &repl->flags) && !test_and_set_bit(In_sync, &repl->flags)) { @@ -2467,7 +2480,7 @@ static int init_resync(struct r1conf *conf) * that can be installed to exclude normal IO requests. */ -static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster) +static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped) { struct r1conf *conf = mddev->private; struct r1bio *r1_bio; @@ -2520,13 +2533,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp *skipped = 1; return sync_blocks; } - /* - * If there is non-resync activity waiting for a turn, - * and resync is going fast enough, - * then let it though before starting on this new sync request. - */ - if (!go_faster && conf->nr_waiting) - msleep_interruptible(1000); bitmap_cond_end_sync(mddev->bitmap, sector_nr); r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index a7196c49d15d..e793ab6b3570 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2889,7 +2889,7 @@ static int init_resync(struct r10conf *conf) */ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, - int *skipped, int go_faster) + int *skipped) { struct r10conf *conf = mddev->private; struct r10bio *r10_bio; @@ -2994,12 +2994,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, if (conf->geo.near_copies < conf->geo.raid_disks && max_sector > (sector_nr | chunk_mask)) max_sector = (sector_nr | chunk_mask) + 1; - /* - * If there is non-resync activity waiting for us then - * put in a delay to throttle resync. - */ - if (!go_faster && conf->nr_waiting) - msleep_interruptible(1000); /* Again, very different code for resync and recovery. * Both must result in an r10bio with a list of bios that diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e75d48c0421a..77dfd720aaa0 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -54,6 +54,7 @@ #include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/nodemask.h> +#include <linux/flex_array.h> #include <trace/events/block.h> #include "md.h" @@ -496,7 +497,7 @@ static void shrink_buffers(struct stripe_head *sh) } } -static int grow_buffers(struct stripe_head *sh) +static int grow_buffers(struct stripe_head *sh, gfp_t gfp) { int i; int num = sh->raid_conf->pool_size; @@ -504,7 +505,7 @@ static int grow_buffers(struct stripe_head *sh) for (i = 0; i < num; i++) { struct page *page; - if (!(page = alloc_page(GFP_KERNEL))) { + if (!(page = alloc_page(gfp))) { return 1; } sh->dev[i].page = page; @@ -525,6 +526,7 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) BUG_ON(atomic_read(&sh->count) != 0); BUG_ON(test_bit(STRIPE_HANDLE, &sh->state)); BUG_ON(stripe_operations_active(sh)); + BUG_ON(sh->batch_head); pr_debug("init_stripe called, stripe %llu\n", (unsigned long long)sector); @@ -552,8 +554,10 @@ retry: } if (read_seqcount_retry(&conf->gen_lock, seq)) goto retry; + sh->overwrite_disks = 0; insert_hash(conf, sh); sh->cpu = smp_processor_id(); + set_bit(STRIPE_BATCH_READY, &sh->state); } static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, @@ -668,20 +672,28 @@ get_active_stripe(struct r5conf *conf, sector_t sector, *(conf->hash_locks + hash)); sh = __find_stripe(conf, sector, conf->generation - previous); if (!sh) { - if (!conf->inactive_blocked) + if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) { sh = get_free_stripe(conf, hash); + if (!sh && llist_empty(&conf->released_stripes) && + !test_bit(R5_DID_ALLOC, &conf->cache_state)) + set_bit(R5_ALLOC_MORE, + &conf->cache_state); + } if (noblock && sh == NULL) break; if (!sh) { - conf->inactive_blocked = 1; + set_bit(R5_INACTIVE_BLOCKED, + &conf->cache_state); wait_event_lock_irq( conf->wait_for_stripe, !list_empty(conf->inactive_list + hash) && (atomic_read(&conf->active_stripes) < (conf->max_nr_stripes * 3 / 4) - || !conf->inactive_blocked), + || !test_bit(R5_INACTIVE_BLOCKED, + &conf->cache_state)), *(conf->hash_locks + hash)); - conf->inactive_blocked = 0; + clear_bit(R5_INACTIVE_BLOCKED, + &conf->cache_state); } else { init_stripe(sh, sector, previous); atomic_inc(&sh->count); @@ -708,6 +720,130 @@ get_active_stripe(struct r5conf *conf, sector_t sector, return sh; } +static bool is_full_stripe_write(struct stripe_head *sh) +{ + BUG_ON(sh->overwrite_disks > (sh->disks - sh->raid_conf->max_degraded)); + return sh->overwrite_disks == (sh->disks - sh->raid_conf->max_degraded); +} + +static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) +{ + local_irq_disable(); + if (sh1 > sh2) { + spin_lock(&sh2->stripe_lock); + spin_lock_nested(&sh1->stripe_lock, 1); + } else { + spin_lock(&sh1->stripe_lock); + spin_lock_nested(&sh2->stripe_lock, 1); + } +} + +static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) +{ + spin_unlock(&sh1->stripe_lock); + spin_unlock(&sh2->stripe_lock); + local_irq_enable(); +} + +/* Only freshly new full stripe normal write stripe can be added to a batch list */ +static bool stripe_can_batch(struct stripe_head *sh) +{ + return test_bit(STRIPE_BATCH_READY, &sh->state) && + is_full_stripe_write(sh); +} + +/* we only do back search */ +static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh) +{ + struct stripe_head *head; + sector_t head_sector, tmp_sec; + int hash; + int dd_idx; + + if (!stripe_can_batch(sh)) + return; + /* Don't cross chunks, so stripe pd_idx/qd_idx is the same */ + tmp_sec = sh->sector; + if (!sector_div(tmp_sec, conf->chunk_sectors)) + return; + head_sector = sh->sector - STRIPE_SECTORS; + + hash = stripe_hash_locks_hash(head_sector); + spin_lock_irq(conf->hash_locks + hash); + head = __find_stripe(conf, head_sector, conf->generation); + if (head && !atomic_inc_not_zero(&head->count)) { + spin_lock(&conf->device_lock); + if (!atomic_read(&head->count)) { + if (!test_bit(STRIPE_HANDLE, &head->state)) + atomic_inc(&conf->active_stripes); + BUG_ON(list_empty(&head->lru) && + !test_bit(STRIPE_EXPANDING, &head->state)); + list_del_init(&head->lru); + if (head->group) { + head->group->stripes_cnt--; + head->group = NULL; + } + } + atomic_inc(&head->count); + spin_unlock(&conf->device_lock); + } + spin_unlock_irq(conf->hash_locks + hash); + + if (!head) + return; + if (!stripe_can_batch(head)) + goto out; + + lock_two_stripes(head, sh); + /* clear_batch_ready clear the flag */ + if (!stripe_can_batch(head) || !stripe_can_batch(sh)) + goto unlock_out; + + if (sh->batch_head) + goto unlock_out; + + dd_idx = 0; + while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx) + dd_idx++; + if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw) + goto unlock_out; + + if (head->batch_head) { + spin_lock(&head->batch_head->batch_lock); + /* This batch list is already running */ + if (!stripe_can_batch(head)) { + spin_unlock(&head->batch_head->batch_lock); + goto unlock_out; + } + + /* + * at this point, head's BATCH_READY could be cleared, but we + * can still add the stripe to batch list + */ + list_add(&sh->batch_list, &head->batch_list); + spin_unlock(&head->batch_head->batch_lock); + + sh->batch_head = head->batch_head; + } else { + head->batch_head = head; + sh->batch_head = head->batch_head; + spin_lock(&head->batch_lock); + list_add_tail(&sh->batch_list, &head->batch_list); + spin_unlock(&head->batch_lock); + } + + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + if (atomic_dec_return(&conf->preread_active_stripes) + < IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + + atomic_inc(&sh->count); +unlock_out: + unlock_two_stripes(head, sh); +out: + release_stripe(head); +} + /* Determine if 'data_offset' or 'new_data_offset' should be used * in this stripe_head. */ @@ -738,6 +874,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) { struct r5conf *conf = sh->raid_conf; int i, disks = sh->disks; + struct stripe_head *head_sh = sh; might_sleep(); @@ -746,6 +883,8 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) int replace_only = 0; struct bio *bi, *rbi; struct md_rdev *rdev, *rrdev = NULL; + + sh = head_sh; if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) { if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags)) rw = WRITE_FUA; @@ -764,6 +903,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags)) rw |= REQ_SYNC; +again: bi = &sh->dev[i].req; rbi = &sh->dev[i].rreq; /* For writing to replacement */ @@ -782,7 +922,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) /* We raced and saw duplicates */ rrdev = NULL; } else { - if (test_bit(R5_ReadRepl, &sh->dev[i].flags) && rrdev) + if (test_bit(R5_ReadRepl, &head_sh->dev[i].flags) && rrdev) rdev = rrdev; rrdev = NULL; } @@ -853,13 +993,15 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) __func__, (unsigned long long)sh->sector, bi->bi_rw, i); atomic_inc(&sh->count); + if (sh != head_sh) + atomic_inc(&head_sh->count); if (use_new_offset(conf, sh)) bi->bi_iter.bi_sector = (sh->sector + rdev->new_data_offset); else bi->bi_iter.bi_sector = (sh->sector + rdev->data_offset); - if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) + if (test_bit(R5_ReadNoMerge, &head_sh->dev[i].flags)) bi->bi_rw |= REQ_NOMERGE; if (test_bit(R5_SkipCopy, &sh->dev[i].flags)) @@ -903,6 +1045,8 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) __func__, (unsigned long long)sh->sector, rbi->bi_rw, i); atomic_inc(&sh->count); + if (sh != head_sh) + atomic_inc(&head_sh->count); if (use_new_offset(conf, sh)) rbi->bi_iter.bi_sector = (sh->sector + rrdev->new_data_offset); @@ -934,8 +1078,18 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) pr_debug("skip op %ld on disc %d for sector %llu\n", bi->bi_rw, i, (unsigned long long)sh->sector); clear_bit(R5_LOCKED, &sh->dev[i].flags); + if (sh->batch_head) + set_bit(STRIPE_BATCH_ERR, + &sh->batch_head->state); set_bit(STRIPE_HANDLE, &sh->state); } + + if (!head_sh->batch_head) + continue; + sh = list_first_entry(&sh->batch_list, struct stripe_head, + batch_list); + if (sh != head_sh) + goto again; } } @@ -1051,6 +1205,7 @@ static void ops_run_biofill(struct stripe_head *sh) struct async_submit_ctl submit; int i; + BUG_ON(sh->batch_head); pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -1109,16 +1264,28 @@ static void ops_complete_compute(void *stripe_head_ref) /* return a pointer to the address conversion region of the scribble buffer */ static addr_conv_t *to_addr_conv(struct stripe_head *sh, - struct raid5_percpu *percpu) + struct raid5_percpu *percpu, int i) { - return percpu->scribble + sizeof(struct page *) * (sh->disks + 2); + void *addr; + + addr = flex_array_get(percpu->scribble, i); + return addr + sizeof(struct page *) * (sh->disks + 2); +} + +/* return a pointer to the address conversion region of the scribble buffer */ +static struct page **to_addr_page(struct raid5_percpu *percpu, int i) +{ + void *addr; + + addr = flex_array_get(percpu->scribble, i); + return addr; } static struct dma_async_tx_descriptor * ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) { int disks = sh->disks; - struct page **xor_srcs = percpu->scribble; + struct page **xor_srcs = to_addr_page(percpu, 0); int target = sh->ops.target; struct r5dev *tgt = &sh->dev[target]; struct page *xor_dest = tgt->page; @@ -1127,6 +1294,8 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) struct async_submit_ctl submit; int i; + BUG_ON(sh->batch_head); + pr_debug("%s: stripe %llu block: %d\n", __func__, (unsigned long long)sh->sector, target); BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags)); @@ -1138,7 +1307,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) atomic_inc(&sh->count); init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL, - ops_complete_compute, sh, to_addr_conv(sh, percpu)); + ops_complete_compute, sh, to_addr_conv(sh, percpu, 0)); if (unlikely(count == 1)) tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit); else @@ -1156,7 +1325,9 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu) * destination buffer is recorded in srcs[count] and the Q destination * is recorded in srcs[count+1]]. */ -static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh) +static int set_syndrome_sources(struct page **srcs, + struct stripe_head *sh, + int srctype) { int disks = sh->disks; int syndrome_disks = sh->ddf_layout ? disks : (disks - 2); @@ -1171,8 +1342,15 @@ static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh) i = d0_idx; do { int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks); + struct r5dev *dev = &sh->dev[i]; - srcs[slot] = sh->dev[i].page; + if (i == sh->qd_idx || i == sh->pd_idx || + (srctype == SYNDROME_SRC_ALL) || + (srctype == SYNDROME_SRC_WANT_DRAIN && + test_bit(R5_Wantdrain, &dev->flags)) || + (srctype == SYNDROME_SRC_WRITTEN && + dev->written)) + srcs[slot] = sh->dev[i].page; i = raid6_next_disk(i, disks); } while (i != d0_idx); @@ -1183,7 +1361,7 @@ static struct dma_async_tx_descriptor * ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) { int disks = sh->disks; - struct page **blocks = percpu->scribble; + struct page **blocks = to_addr_page(percpu, 0); int target; int qd_idx = sh->qd_idx; struct dma_async_tx_descriptor *tx; @@ -1193,6 +1371,7 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) int i; int count; + BUG_ON(sh->batch_head); if (sh->ops.target < 0) target = sh->ops.target2; else if (sh->ops.target2 < 0) @@ -1211,12 +1390,12 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) atomic_inc(&sh->count); if (target == qd_idx) { - count = set_syndrome_sources(blocks, sh); + count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL); blocks[count] = NULL; /* regenerating p is not necessary */ BUG_ON(blocks[count+1] != dest); /* q should already be set */ init_async_submit(&submit, ASYNC_TX_FENCE, NULL, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); } else { /* Compute any data- or p-drive using XOR */ @@ -1229,7 +1408,7 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu) init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit); } @@ -1248,9 +1427,10 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu) struct r5dev *tgt = &sh->dev[target]; struct r5dev *tgt2 = &sh->dev[target2]; struct dma_async_tx_descriptor *tx; - struct page **blocks = percpu->scribble; + struct page **blocks = to_addr_page(percpu, 0); struct async_submit_ctl submit; + BUG_ON(sh->batch_head); pr_debug("%s: stripe %llu block1: %d block2: %d\n", __func__, (unsigned long long)sh->sector, target, target2); BUG_ON(target < 0 || target2 < 0); @@ -1290,7 +1470,7 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu) /* Missing P+Q, just recompute */ init_async_submit(&submit, ASYNC_TX_FENCE, NULL, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); return async_gen_syndrome(blocks, 0, syndrome_disks+2, STRIPE_SIZE, &submit); } else { @@ -1314,21 +1494,21 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu) init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL, NULL, NULL, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit); - count = set_syndrome_sources(blocks, sh); + count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL); init_async_submit(&submit, ASYNC_TX_FENCE, tx, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); return async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); } } else { init_async_submit(&submit, ASYNC_TX_FENCE, NULL, ops_complete_compute, sh, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); if (failb == syndrome_disks) { /* We're missing D+P. */ return async_raid6_datap_recov(syndrome_disks+2, @@ -1352,17 +1532,18 @@ static void ops_complete_prexor(void *stripe_head_ref) } static struct dma_async_tx_descriptor * -ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu, - struct dma_async_tx_descriptor *tx) +ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu, + struct dma_async_tx_descriptor *tx) { int disks = sh->disks; - struct page **xor_srcs = percpu->scribble; + struct page **xor_srcs = to_addr_page(percpu, 0); int count = 0, pd_idx = sh->pd_idx, i; struct async_submit_ctl submit; /* existing parity data subtracted */ struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; + BUG_ON(sh->batch_head); pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -1374,31 +1555,56 @@ ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu, } init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx, - ops_complete_prexor, sh, to_addr_conv(sh, percpu)); + ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0)); tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); return tx; } static struct dma_async_tx_descriptor * +ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu, + struct dma_async_tx_descriptor *tx) +{ + struct page **blocks = to_addr_page(percpu, 0); + int count; + struct async_submit_ctl submit; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_WANT_DRAIN); + + init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_PQ_XOR_DST, tx, + ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0)); + tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); + + return tx; +} + +static struct dma_async_tx_descriptor * ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) { int disks = sh->disks; int i; + struct stripe_head *head_sh = sh; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); for (i = disks; i--; ) { - struct r5dev *dev = &sh->dev[i]; + struct r5dev *dev; struct bio *chosen; - if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) { + sh = head_sh; + if (test_and_clear_bit(R5_Wantdrain, &head_sh->dev[i].flags)) { struct bio *wbi; +again: + dev = &sh->dev[i]; spin_lock_irq(&sh->stripe_lock); chosen = dev->towrite; dev->towrite = NULL; + sh->overwrite_disks = 0; BUG_ON(dev->written); wbi = dev->written = chosen; spin_unlock_irq(&sh->stripe_lock); @@ -1423,6 +1629,15 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) } wbi = r5_next_bio(wbi, dev->sector); } + + if (head_sh->batch_head) { + sh = list_first_entry(&sh->batch_list, + struct stripe_head, + batch_list); + if (sh == head_sh) + continue; + goto again; + } } } @@ -1478,12 +1693,15 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu, struct dma_async_tx_descriptor *tx) { int disks = sh->disks; - struct page **xor_srcs = percpu->scribble; + struct page **xor_srcs; struct async_submit_ctl submit; - int count = 0, pd_idx = sh->pd_idx, i; + int count, pd_idx = sh->pd_idx, i; struct page *xor_dest; int prexor = 0; unsigned long flags; + int j = 0; + struct stripe_head *head_sh = sh; + int last_stripe; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -1500,15 +1718,18 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu, ops_complete_reconstruct(sh); return; } +again: + count = 0; + xor_srcs = to_addr_page(percpu, j); /* check if prexor is active which means only process blocks * that are part of a read-modify-write (written) */ - if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) { + if (head_sh->reconstruct_state == reconstruct_state_prexor_drain_run) { prexor = 1; xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if (dev->written) + if (head_sh->dev[i].written) xor_srcs[count++] = dev->page; } } else { @@ -1525,17 +1746,32 @@ ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu, * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST * for the synchronous xor case */ - flags = ASYNC_TX_ACK | - (prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST); - - atomic_inc(&sh->count); + last_stripe = !head_sh->batch_head || + list_first_entry(&sh->batch_list, + struct stripe_head, batch_list) == head_sh; + if (last_stripe) { + flags = ASYNC_TX_ACK | + (prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST); + + atomic_inc(&head_sh->count); + init_async_submit(&submit, flags, tx, ops_complete_reconstruct, head_sh, + to_addr_conv(sh, percpu, j)); + } else { + flags = prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST; + init_async_submit(&submit, flags, tx, NULL, NULL, + to_addr_conv(sh, percpu, j)); + } - init_async_submit(&submit, flags, tx, ops_complete_reconstruct, sh, - to_addr_conv(sh, percpu)); if (unlikely(count == 1)) tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit); else tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit); + if (!last_stripe) { + j++; + sh = list_first_entry(&sh->batch_list, struct stripe_head, + batch_list); + goto again; + } } static void @@ -1543,8 +1779,12 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu, struct dma_async_tx_descriptor *tx) { struct async_submit_ctl submit; - struct page **blocks = percpu->scribble; - int count, i; + struct page **blocks; + int count, i, j = 0; + struct stripe_head *head_sh = sh; + int last_stripe; + int synflags; + unsigned long txflags; pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); @@ -1562,13 +1802,36 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu, return; } - count = set_syndrome_sources(blocks, sh); +again: + blocks = to_addr_page(percpu, j); - atomic_inc(&sh->count); + if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) { + synflags = SYNDROME_SRC_WRITTEN; + txflags = ASYNC_TX_ACK | ASYNC_TX_PQ_XOR_DST; + } else { + synflags = SYNDROME_SRC_ALL; + txflags = ASYNC_TX_ACK; + } + + count = set_syndrome_sources(blocks, sh, synflags); + last_stripe = !head_sh->batch_head || + list_first_entry(&sh->batch_list, + struct stripe_head, batch_list) == head_sh; - init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_reconstruct, - sh, to_addr_conv(sh, percpu)); + if (last_stripe) { + atomic_inc(&head_sh->count); + init_async_submit(&submit, txflags, tx, ops_complete_reconstruct, + head_sh, to_addr_conv(sh, percpu, j)); + } else + init_async_submit(&submit, 0, tx, NULL, NULL, + to_addr_conv(sh, percpu, j)); async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit); + if (!last_stripe) { + j++; + sh = list_first_entry(&sh->batch_list, struct stripe_head, + batch_list); + goto again; + } } static void ops_complete_check(void *stripe_head_ref) @@ -1589,7 +1852,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu) int pd_idx = sh->pd_idx; int qd_idx = sh->qd_idx; struct page *xor_dest; - struct page **xor_srcs = percpu->scribble; + struct page **xor_srcs = to_addr_page(percpu, 0); struct dma_async_tx_descriptor *tx; struct async_submit_ctl submit; int count; @@ -1598,6 +1861,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu) pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector); + BUG_ON(sh->batch_head); count = 0; xor_dest = sh->dev[pd_idx].page; xor_srcs[count++] = xor_dest; @@ -1608,7 +1872,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu) } init_async_submit(&submit, 0, NULL, NULL, NULL, - to_addr_conv(sh, percpu)); + to_addr_conv(sh, percpu, 0)); tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &sh->ops.zero_sum_result, &submit); @@ -1619,20 +1883,21 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu) static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp) { - struct page **srcs = percpu->scribble; + struct page **srcs = to_addr_page(percpu, 0); struct async_submit_ctl submit; int count; pr_debug("%s: stripe %llu checkp: %d\n", __func__, (unsigned long long)sh->sector, checkp); - count = set_syndrome_sources(srcs, sh); + BUG_ON(sh->batch_head); + count = set_syndrome_sources(srcs, sh, SYNDROME_SRC_ALL); if (!checkp) srcs[count] = NULL; atomic_inc(&sh->count); init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check, - sh, to_addr_conv(sh, percpu)); + sh, to_addr_conv(sh, percpu, 0)); async_syndrome_val(srcs, 0, count+2, STRIPE_SIZE, &sh->ops.zero_sum_result, percpu->spare_page, &submit); } @@ -1667,8 +1932,12 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) async_tx_ack(tx); } - if (test_bit(STRIPE_OP_PREXOR, &ops_request)) - tx = ops_run_prexor(sh, percpu, tx); + if (test_bit(STRIPE_OP_PREXOR, &ops_request)) { + if (level < 6) + tx = ops_run_prexor5(sh, percpu, tx); + else + tx = ops_run_prexor6(sh, percpu, tx); + } if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) { tx = ops_run_biodrain(sh, tx); @@ -1693,7 +1962,7 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) BUG(); } - if (overlap_clear) + if (overlap_clear && !sh->batch_head) for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; if (test_and_clear_bit(R5_Overlap, &dev->flags)) @@ -1702,10 +1971,10 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) put_cpu(); } -static int grow_one_stripe(struct r5conf *conf, int hash) +static int grow_one_stripe(struct r5conf *conf, gfp_t gfp) { struct stripe_head *sh; - sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL); + sh = kmem_cache_zalloc(conf->slab_cache, gfp); if (!sh) return 0; @@ -1713,17 +1982,23 @@ static int grow_one_stripe(struct r5conf *conf, int hash) spin_lock_init(&sh->stripe_lock); - if (grow_buffers(sh)) { + if (grow_buffers(sh, gfp)) { shrink_buffers(sh); kmem_cache_free(conf->slab_cache, sh); return 0; } - sh->hash_lock_index = hash; + sh->hash_lock_index = + conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; /* we just created an active stripe so... */ atomic_set(&sh->count, 1); atomic_inc(&conf->active_stripes); INIT_LIST_HEAD(&sh->lru); + + spin_lock_init(&sh->batch_lock); + INIT_LIST_HEAD(&sh->batch_list); + sh->batch_head = NULL; release_stripe(sh); + conf->max_nr_stripes++; return 1; } @@ -1731,7 +2006,6 @@ static int grow_stripes(struct r5conf *conf, int num) { struct kmem_cache *sc; int devs = max(conf->raid_disks, conf->previous_raid_disks); - int hash; if (conf->mddev->gendisk) sprintf(conf->cache_name[0], @@ -1749,13 +2023,10 @@ static int grow_stripes(struct r5conf *conf, int num) return 1; conf->slab_cache = sc; conf->pool_size = devs; - hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; - while (num--) { - if (!grow_one_stripe(conf, hash)) + while (num--) + if (!grow_one_stripe(conf, GFP_KERNEL)) return 1; - conf->max_nr_stripes++; - hash = (hash + 1) % NR_STRIPE_HASH_LOCKS; - } + return 0; } @@ -1772,13 +2043,21 @@ static int grow_stripes(struct r5conf *conf, int num) * calculate over all devices (not just the data blocks), using zeros in place * of the P and Q blocks. */ -static size_t scribble_len(int num) +static struct flex_array *scribble_alloc(int num, int cnt, gfp_t flags) { + struct flex_array *ret; size_t len; len = sizeof(struct page *) * (num+2) + sizeof(addr_conv_t) * (num+2); - - return len; + ret = flex_array_alloc(len, cnt, flags); + if (!ret) + return NULL; + /* always prealloc all elements, so no locking is required */ + if (flex_array_prealloc(ret, 0, cnt, flags)) { + flex_array_free(ret); + return NULL; + } + return ret; } static int resize_stripes(struct r5conf *conf, int newsize) @@ -1896,16 +2175,16 @@ static int resize_stripes(struct r5conf *conf, int newsize) err = -ENOMEM; get_online_cpus(); - conf->scribble_len = scribble_len(newsize); for_each_present_cpu(cpu) { struct raid5_percpu *percpu; - void *scribble; + struct flex_array *scribble; percpu = per_cpu_ptr(conf->percpu, cpu); - scribble = kmalloc(conf->scribble_len, GFP_NOIO); + scribble = scribble_alloc(newsize, conf->chunk_sectors / + STRIPE_SECTORS, GFP_NOIO); if (scribble) { - kfree(percpu->scribble); + flex_array_free(percpu->scribble); percpu->scribble = scribble; } else { err = -ENOMEM; @@ -1937,9 +2216,10 @@ static int resize_stripes(struct r5conf *conf, int newsize) return err; } -static int drop_one_stripe(struct r5conf *conf, int hash) +static int drop_one_stripe(struct r5conf *conf) { struct stripe_head *sh; + int hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS; spin_lock_irq(conf->hash_locks + hash); sh = get_free_stripe(conf, hash); @@ -1950,15 +2230,15 @@ static int drop_one_stripe(struct r5conf *conf, int hash) shrink_buffers(sh); kmem_cache_free(conf->slab_cache, sh); atomic_dec(&conf->active_stripes); + conf->max_nr_stripes--; return 1; } static void shrink_stripes(struct r5conf *conf) { - int hash; - for (hash = 0; hash < NR_STRIPE_HASH_LOCKS; hash++) - while (drop_one_stripe(conf, hash)) - ; + while (conf->max_nr_stripes && + drop_one_stripe(conf)) + ; if (conf->slab_cache) kmem_cache_destroy(conf->slab_cache); @@ -2154,10 +2434,16 @@ static void raid5_end_write_request(struct bio *bi, int error) } rdev_dec_pending(rdev, conf->mddev); + if (sh->batch_head && !uptodate) + set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state); + if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags)) clear_bit(R5_LOCKED, &sh->dev[i].flags); set_bit(STRIPE_HANDLE, &sh->state); release_stripe(sh); + + if (sh->batch_head && sh != sh->batch_head) + release_stripe(sh->batch_head); } static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous); @@ -2535,7 +2821,7 @@ static void schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, int rcw, int expand) { - int i, pd_idx = sh->pd_idx, disks = sh->disks; + int i, pd_idx = sh->pd_idx, qd_idx = sh->qd_idx, disks = sh->disks; struct r5conf *conf = sh->raid_conf; int level = conf->level; @@ -2571,13 +2857,15 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state)) atomic_inc(&conf->pending_full_writes); } else { - BUG_ON(level == 6); BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) || test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags))); + BUG_ON(level == 6 && + (!(test_bit(R5_UPTODATE, &sh->dev[qd_idx].flags) || + test_bit(R5_Wantcompute, &sh->dev[qd_idx].flags)))); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if (i == pd_idx) + if (i == pd_idx || i == qd_idx) continue; if (dev->towrite && @@ -2624,7 +2912,8 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, * toread/towrite point to the first in a chain. * The bi_next chain must be in order. */ -static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite) +static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, + int forwrite, int previous) { struct bio **bip; struct r5conf *conf = sh->raid_conf; @@ -2643,6 +2932,9 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in * protect it. */ spin_lock_irq(&sh->stripe_lock); + /* Don't allow new IO added to stripes in batch list */ + if (sh->batch_head) + goto overlap; if (forwrite) { bip = &sh->dev[dd_idx].towrite; if (*bip == NULL) @@ -2657,6 +2949,9 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi)) goto overlap; + if (!forwrite || previous) + clear_bit(STRIPE_BATCH_READY, &sh->state); + BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next); if (*bip) bi->bi_next = *bip; @@ -2674,7 +2969,8 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in sector = bio_end_sector(bi); } if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS) - set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags); + if (!test_and_set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags)) + sh->overwrite_disks++; } pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n", @@ -2688,6 +2984,9 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in sh->bm_seq = conf->seq_flush+1; set_bit(STRIPE_BIT_DELAY, &sh->state); } + + if (stripe_can_batch(sh)) + stripe_add_to_batch_list(conf, sh); return 1; overlap: @@ -2720,6 +3019,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, struct bio **return_bi) { int i; + BUG_ON(sh->batch_head); for (i = disks; i--; ) { struct bio *bi; int bitmap_end = 0; @@ -2746,6 +3046,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, /* fail all writes first */ bi = sh->dev[i].towrite; sh->dev[i].towrite = NULL; + sh->overwrite_disks = 0; spin_unlock_irq(&sh->stripe_lock); if (bi) bitmap_end = 1; @@ -2834,6 +3135,7 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh, int abort = 0; int i; + BUG_ON(sh->batch_head); clear_bit(STRIPE_SYNCING, &sh->state); if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags)) wake_up(&conf->wait_for_overlap); @@ -3064,6 +3366,7 @@ static void handle_stripe_fill(struct stripe_head *sh, { int i; + BUG_ON(sh->batch_head); /* look for blocks to read/compute, skip this if a compute * is already in flight, or if the stripe contents are in the * midst of changing due to a write @@ -3087,6 +3390,9 @@ static void handle_stripe_clean_event(struct r5conf *conf, int i; struct r5dev *dev; int discard_pending = 0; + struct stripe_head *head_sh = sh; + bool do_endio = false; + int wakeup_nr = 0; for (i = disks; i--; ) if (sh->dev[i].written) { @@ -3102,8 +3408,11 @@ static void handle_stripe_clean_event(struct r5conf *conf, clear_bit(R5_UPTODATE, &dev->flags); if (test_and_clear_bit(R5_SkipCopy, &dev->flags)) { WARN_ON(test_bit(R5_UPTODATE, &dev->flags)); - dev->page = dev->orig_page; } + do_endio = true; + +returnbi: + dev->page = dev->orig_page; wbi = dev->written; dev->written = NULL; while (wbi && wbi->bi_iter.bi_sector < @@ -3120,6 +3429,17 @@ static void handle_stripe_clean_event(struct r5conf *conf, STRIPE_SECTORS, !test_bit(STRIPE_DEGRADED, &sh->state), 0); + if (head_sh->batch_head) { + sh = list_first_entry(&sh->batch_list, + struct stripe_head, + batch_list); + if (sh != head_sh) { + dev = &sh->dev[i]; + goto returnbi; + } + } + sh = head_sh; + dev = &sh->dev[i]; } else if (test_bit(R5_Discard, &dev->flags)) discard_pending = 1; WARN_ON(test_bit(R5_SkipCopy, &dev->flags)); @@ -3141,8 +3461,17 @@ static void handle_stripe_clean_event(struct r5conf *conf, * will be reinitialized */ spin_lock_irq(&conf->device_lock); +unhash: remove_hash(sh); + if (head_sh->batch_head) { + sh = list_first_entry(&sh->batch_list, + struct stripe_head, batch_list); + if (sh != head_sh) + goto unhash; + } spin_unlock_irq(&conf->device_lock); + sh = head_sh; + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) set_bit(STRIPE_HANDLE, &sh->state); @@ -3151,6 +3480,45 @@ static void handle_stripe_clean_event(struct r5conf *conf, if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state)) if (atomic_dec_and_test(&conf->pending_full_writes)) md_wakeup_thread(conf->mddev->thread); + + if (!head_sh->batch_head || !do_endio) + return; + for (i = 0; i < head_sh->disks; i++) { + if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags)) + wakeup_nr++; + } + while (!list_empty(&head_sh->batch_list)) { + int i; + sh = list_first_entry(&head_sh->batch_list, + struct stripe_head, batch_list); + list_del_init(&sh->batch_list); + + set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG, + head_sh->state & ~((1 << STRIPE_ACTIVE) | + (1 << STRIPE_PREREAD_ACTIVE) | + STRIPE_EXPAND_SYNC_FLAG)); + sh->check_state = head_sh->check_state; + sh->reconstruct_state = head_sh->reconstruct_state; + for (i = 0; i < sh->disks; i++) { + if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) + wakeup_nr++; + sh->dev[i].flags = head_sh->dev[i].flags; + } + + spin_lock_irq(&sh->stripe_lock); + sh->batch_head = NULL; + spin_unlock_irq(&sh->stripe_lock); + if (sh->state & STRIPE_EXPAND_SYNC_FLAG) + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); + } + + spin_lock_irq(&head_sh->stripe_lock); + head_sh->batch_head = NULL; + spin_unlock_irq(&head_sh->stripe_lock); + wake_up_nr(&conf->wait_for_overlap, wakeup_nr); + if (head_sh->state & STRIPE_EXPAND_SYNC_FLAG) + set_bit(STRIPE_HANDLE, &head_sh->state); } static void handle_stripe_dirtying(struct r5conf *conf, @@ -3161,28 +3529,27 @@ static void handle_stripe_dirtying(struct r5conf *conf, int rmw = 0, rcw = 0, i; sector_t recovery_cp = conf->mddev->recovery_cp; - /* RAID6 requires 'rcw' in current implementation. - * Otherwise, check whether resync is now happening or should start. + /* Check whether resync is now happening or should start. * If yes, then the array is dirty (after unclean shutdown or * initial creation), so parity in some stripes might be inconsistent. * In this case, we need to always do reconstruct-write, to ensure * that in case of drive failure or read-error correction, we * generate correct data from the parity. */ - if (conf->max_degraded == 2 || + if (conf->rmw_level == PARITY_DISABLE_RMW || (recovery_cp < MaxSector && sh->sector >= recovery_cp && s->failed == 0)) { /* Calculate the real rcw later - for now make it * look like rcw is cheaper */ rcw = 1; rmw = 2; - pr_debug("force RCW max_degraded=%u, recovery_cp=%llu sh->sector=%llu\n", - conf->max_degraded, (unsigned long long)recovery_cp, + pr_debug("force RCW rmw_level=%u, recovery_cp=%llu sh->sector=%llu\n", + conf->rmw_level, (unsigned long long)recovery_cp, (unsigned long long)sh->sector); } else for (i = disks; i--; ) { /* would I have to read this buffer for read_modify_write */ struct r5dev *dev = &sh->dev[i]; - if ((dev->towrite || i == sh->pd_idx) && + if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx) && !test_bit(R5_LOCKED, &dev->flags) && !(test_bit(R5_UPTODATE, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags))) { @@ -3192,7 +3559,8 @@ static void handle_stripe_dirtying(struct r5conf *conf, rmw += 2*disks; /* cannot read it */ } /* Would I have to read this buffer for reconstruct_write */ - if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx && + if (!test_bit(R5_OVERWRITE, &dev->flags) && + i != sh->pd_idx && i != sh->qd_idx && !test_bit(R5_LOCKED, &dev->flags) && !(test_bit(R5_UPTODATE, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags))) { @@ -3205,7 +3573,7 @@ static void handle_stripe_dirtying(struct r5conf *conf, pr_debug("for sector %llu, rmw=%d rcw=%d\n", (unsigned long long)sh->sector, rmw, rcw); set_bit(STRIPE_HANDLE, &sh->state); - if (rmw < rcw && rmw > 0) { + if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_ENABLE_RMW)) && rmw > 0) { /* prefer read-modify-write, but need to get some data */ if (conf->mddev->queue) blk_add_trace_msg(conf->mddev->queue, @@ -3213,7 +3581,7 @@ static void handle_stripe_dirtying(struct r5conf *conf, (unsigned long long)sh->sector, rmw); for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if ((dev->towrite || i == sh->pd_idx) && + if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx) && !test_bit(R5_LOCKED, &dev->flags) && !(test_bit(R5_UPTODATE, &dev->flags) || test_bit(R5_Wantcompute, &dev->flags)) && @@ -3232,7 +3600,7 @@ static void handle_stripe_dirtying(struct r5conf *conf, } } } - if (rcw <= rmw && rcw > 0) { + if ((rcw < rmw || (rcw == rmw && conf->rmw_level != PARITY_ENABLE_RMW)) && rcw > 0) { /* want reconstruct write, but need to get some data */ int qread =0; rcw = 0; @@ -3290,6 +3658,7 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, { struct r5dev *dev = NULL; + BUG_ON(sh->batch_head); set_bit(STRIPE_HANDLE, &sh->state); switch (sh->check_state) { @@ -3380,6 +3749,7 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, int qd_idx = sh->qd_idx; struct r5dev *dev; + BUG_ON(sh->batch_head); set_bit(STRIPE_HANDLE, &sh->state); BUG_ON(s->failed > 2); @@ -3543,6 +3913,7 @@ static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh) * copy some of them into a target stripe for expand. */ struct dma_async_tx_descriptor *tx = NULL; + BUG_ON(sh->batch_head); clear_bit(STRIPE_EXPAND_SOURCE, &sh->state); for (i = 0; i < sh->disks; i++) if (i != sh->pd_idx && i != sh->qd_idx) { @@ -3615,8 +3986,8 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) memset(s, 0, sizeof(*s)); - s->expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state); - s->expanded = test_bit(STRIPE_EXPAND_READY, &sh->state); + s->expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state) && !sh->batch_head; + s->expanded = test_bit(STRIPE_EXPAND_READY, &sh->state) && !sh->batch_head; s->failed_num[0] = -1; s->failed_num[1] = -1; @@ -3786,6 +4157,80 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) rcu_read_unlock(); } +static int clear_batch_ready(struct stripe_head *sh) +{ + struct stripe_head *tmp; + if (!test_and_clear_bit(STRIPE_BATCH_READY, &sh->state)) + return 0; + spin_lock(&sh->stripe_lock); + if (!sh->batch_head) { + spin_unlock(&sh->stripe_lock); + return 0; + } + + /* + * this stripe could be added to a batch list before we check + * BATCH_READY, skips it + */ + if (sh->batch_head != sh) { + spin_unlock(&sh->stripe_lock); + return 1; + } + spin_lock(&sh->batch_lock); + list_for_each_entry(tmp, &sh->batch_list, batch_list) + clear_bit(STRIPE_BATCH_READY, &tmp->state); + spin_unlock(&sh->batch_lock); + spin_unlock(&sh->stripe_lock); + + /* + * BATCH_READY is cleared, no new stripes can be added. + * batch_list can be accessed without lock + */ + return 0; +} + +static void check_break_stripe_batch_list(struct stripe_head *sh) +{ + struct stripe_head *head_sh, *next; + int i; + + if (!test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state)) + return; + + head_sh = sh; + do { + sh = list_first_entry(&sh->batch_list, + struct stripe_head, batch_list); + BUG_ON(sh == head_sh); + } while (!test_bit(STRIPE_DEGRADED, &sh->state)); + + while (sh != head_sh) { + next = list_first_entry(&sh->batch_list, + struct stripe_head, batch_list); + list_del_init(&sh->batch_list); + + set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG, + head_sh->state & ~((1 << STRIPE_ACTIVE) | + (1 << STRIPE_PREREAD_ACTIVE) | + (1 << STRIPE_DEGRADED) | + STRIPE_EXPAND_SYNC_FLAG)); + sh->check_state = head_sh->check_state; + sh->reconstruct_state = head_sh->reconstruct_state; + for (i = 0; i < sh->disks; i++) + sh->dev[i].flags = head_sh->dev[i].flags & + (~((1 << R5_WriteError) | (1 << R5_Overlap))); + + spin_lock_irq(&sh->stripe_lock); + sh->batch_head = NULL; + spin_unlock_irq(&sh->stripe_lock); + + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); + + sh = next; + } +} + static void handle_stripe(struct stripe_head *sh) { struct stripe_head_state s; @@ -3803,7 +4248,14 @@ static void handle_stripe(struct stripe_head *sh) return; } - if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) { + if (clear_batch_ready(sh) ) { + clear_bit_unlock(STRIPE_ACTIVE, &sh->state); + return; + } + + check_break_stripe_batch_list(sh); + + if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) { spin_lock(&sh->stripe_lock); /* Cannot process 'sync' concurrently with 'discard' */ if (!test_bit(STRIPE_DISCARD, &sh->state) && @@ -4158,7 +4610,7 @@ static int raid5_congested(struct mddev *mddev, int bits) * how busy the stripe_cache is */ - if (conf->inactive_blocked) + if (test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) return 1; if (conf->quiesce) return 1; @@ -4180,8 +4632,12 @@ static int raid5_mergeable_bvec(struct mddev *mddev, unsigned int chunk_sectors = mddev->chunk_sectors; unsigned int bio_sectors = bvm->bi_size >> 9; - if ((bvm->bi_rw & 1) == WRITE) - return biovec->bv_len; /* always allow writes to be mergeable */ + /* + * always allow writes to be mergeable, read as well if array + * is degraded as we'll go through stripe cache anyway. + */ + if ((bvm->bi_rw & 1) == WRITE || mddev->degraded) + return biovec->bv_len; if (mddev->new_chunk_sectors < mddev->chunk_sectors) chunk_sectors = mddev->new_chunk_sectors; @@ -4603,12 +5059,14 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) } set_bit(STRIPE_DISCARD, &sh->state); finish_wait(&conf->wait_for_overlap, &w); + sh->overwrite_disks = 0; for (d = 0; d < conf->raid_disks; d++) { if (d == sh->pd_idx || d == sh->qd_idx) continue; sh->dev[d].towrite = bi; set_bit(R5_OVERWRITE, &sh->dev[d].flags); raid5_inc_bi_active_stripes(bi); + sh->overwrite_disks++; } spin_unlock_irq(&sh->stripe_lock); if (conf->mddev->bitmap) { @@ -4656,7 +5114,12 @@ static void make_request(struct mddev *mddev, struct bio * bi) md_write_start(mddev, bi); - if (rw == READ && + /* + * If array is degraded, better not do chunk aligned read because + * later we might have to read it again in order to reconstruct + * data on failed drives. + */ + if (rw == READ && mddev->degraded == 0 && mddev->reshape_position == MaxSector && chunk_aligned_read(mddev,bi)) return; @@ -4772,7 +5235,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) } if (test_bit(STRIPE_EXPANDING, &sh->state) || - !add_stripe_bio(sh, bi, dd_idx, rw)) { + !add_stripe_bio(sh, bi, dd_idx, rw, previous)) { /* Stripe is busy expanding or * add failed due to overlap. Flush everything * and wait a while @@ -4785,7 +5248,8 @@ static void make_request(struct mddev *mddev, struct bio * bi) } set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); - if ((bi->bi_rw & REQ_SYNC) && + if ((!sh->batch_head || sh == sh->batch_head) && + (bi->bi_rw & REQ_SYNC) && !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); release_stripe_plug(mddev, sh); @@ -5050,8 +5514,7 @@ ret: return reshape_sectors; } -/* FIXME go_faster isn't used */ -static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster) +static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped) { struct r5conf *conf = mddev->private; struct stripe_head *sh; @@ -5121,12 +5584,17 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int schedule_timeout_uninterruptible(1); } /* Need to check if array will still be degraded after recovery/resync - * We don't need to check the 'failed' flag as when that gets set, - * recovery aborts. + * Note in case of > 1 drive failures it's possible we're rebuilding + * one drive while leaving another faulty drive in array. */ - for (i = 0; i < conf->raid_disks; i++) - if (conf->disks[i].rdev == NULL) + rcu_read_lock(); + for (i = 0; i < conf->raid_disks; i++) { + struct md_rdev *rdev = ACCESS_ONCE(conf->disks[i].rdev); + + if (rdev == NULL || test_bit(Faulty, &rdev->flags)) still_degraded = 1; + } + rcu_read_unlock(); bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded); @@ -5181,7 +5649,7 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio) return handled; } - if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) { + if (!add_stripe_bio(sh, raid_bio, dd_idx, 0, 0)) { release_stripe(sh); raid5_set_bi_processed_stripes(raid_bio, scnt); conf->retry_read_aligned = raid_bio; @@ -5307,6 +5775,8 @@ static void raid5d(struct md_thread *thread) int batch_size, released; released = release_stripe_list(conf, conf->temp_inactive_list); + if (released) + clear_bit(R5_DID_ALLOC, &conf->cache_state); if ( !list_empty(&conf->bitmap_list)) { @@ -5345,6 +5815,13 @@ static void raid5d(struct md_thread *thread) pr_debug("%d stripes handled\n", handled); spin_unlock_irq(&conf->device_lock); + if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state)) { + grow_one_stripe(conf, __GFP_NOWARN); + /* Set flag even if allocation failed. This helps + * slow down allocation requests when mem is short + */ + set_bit(R5_DID_ALLOC, &conf->cache_state); + } async_tx_issue_pending_all(); blk_finish_plug(&plug); @@ -5360,7 +5837,7 @@ raid5_show_stripe_cache_size(struct mddev *mddev, char *page) spin_lock(&mddev->lock); conf = mddev->private; if (conf) - ret = sprintf(page, "%d\n", conf->max_nr_stripes); + ret = sprintf(page, "%d\n", conf->min_nr_stripes); spin_unlock(&mddev->lock); return ret; } @@ -5370,30 +5847,24 @@ raid5_set_cache_size(struct mddev *mddev, int size) { struct r5conf *conf = mddev->private; int err; - int hash; if (size <= 16 || size > 32768) return -EINVAL; - hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS; - while (size < conf->max_nr_stripes) { - if (drop_one_stripe(conf, hash)) - conf->max_nr_stripes--; - else - break; - hash--; - if (hash < 0) - hash = NR_STRIPE_HASH_LOCKS - 1; - } + + conf->min_nr_stripes = size; + while (size < conf->max_nr_stripes && + drop_one_stripe(conf)) + ; + + err = md_allow_write(mddev); if (err) return err; - hash = conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS; - while (size > conf->max_nr_stripes) { - if (grow_one_stripe(conf, hash)) - conf->max_nr_stripes++; - else break; - hash = (hash + 1) % NR_STRIPE_HASH_LOCKS; - } + + while (size > conf->max_nr_stripes) + if (!grow_one_stripe(conf, GFP_KERNEL)) + break; + return 0; } EXPORT_SYMBOL(raid5_set_cache_size); @@ -5428,6 +5899,49 @@ raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR, raid5_store_stripe_cache_size); static ssize_t +raid5_show_rmw_level(struct mddev *mddev, char *page) +{ + struct r5conf *conf = mddev->private; + if (conf) + return sprintf(page, "%d\n", conf->rmw_level); + else + return 0; +} + +static ssize_t +raid5_store_rmw_level(struct mddev *mddev, const char *page, size_t len) +{ + struct r5conf *conf = mddev->private; + unsigned long new; + + if (!conf) + return -ENODEV; + + if (len >= PAGE_SIZE) + return -EINVAL; + + if (kstrtoul(page, 10, &new)) + return -EINVAL; + + if (new != PARITY_DISABLE_RMW && !raid6_call.xor_syndrome) + return -EINVAL; + + if (new != PARITY_DISABLE_RMW && + new != PARITY_ENABLE_RMW && + new != PARITY_PREFER_RMW) + return -EINVAL; + + conf->rmw_level = new; + return len; +} + +static struct md_sysfs_entry +raid5_rmw_level = __ATTR(rmw_level, S_IRUGO | S_IWUSR, + raid5_show_rmw_level, + raid5_store_rmw_level); + + +static ssize_t raid5_show_preread_threshold(struct mddev *mddev, char *page) { struct r5conf *conf; @@ -5458,7 +5972,7 @@ raid5_store_preread_threshold(struct mddev *mddev, const char *page, size_t len) conf = mddev->private; if (!conf) err = -ENODEV; - else if (new > conf->max_nr_stripes) + else if (new > conf->min_nr_stripes) err = -EINVAL; else conf->bypass_threshold = new; @@ -5613,6 +6127,7 @@ static struct attribute *raid5_attrs[] = { &raid5_preread_bypass_threshold.attr, &raid5_group_thread_cnt.attr, &raid5_skip_copy.attr, + &raid5_rmw_level.attr, NULL, }; static struct attribute_group raid5_attrs_group = { @@ -5694,7 +6209,8 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks) static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) { safe_put_page(percpu->spare_page); - kfree(percpu->scribble); + if (percpu->scribble) + flex_array_free(percpu->scribble); percpu->spare_page = NULL; percpu->scribble = NULL; } @@ -5704,7 +6220,9 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu if (conf->level == 6 && !percpu->spare_page) percpu->spare_page = alloc_page(GFP_KERNEL); if (!percpu->scribble) - percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); + percpu->scribble = scribble_alloc(max(conf->raid_disks, + conf->previous_raid_disks), conf->chunk_sectors / + STRIPE_SECTORS, GFP_KERNEL); if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) { free_scratch_buffer(conf, percpu); @@ -5735,6 +6253,8 @@ static void raid5_free_percpu(struct r5conf *conf) static void free_conf(struct r5conf *conf) { + if (conf->shrinker.seeks) + unregister_shrinker(&conf->shrinker); free_thread_groups(conf); shrink_stripes(conf); raid5_free_percpu(conf); @@ -5802,6 +6322,30 @@ static int raid5_alloc_percpu(struct r5conf *conf) return err; } +static unsigned long raid5_cache_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct r5conf *conf = container_of(shrink, struct r5conf, shrinker); + int ret = 0; + while (ret < sc->nr_to_scan) { + if (drop_one_stripe(conf) == 0) + return SHRINK_STOP; + ret++; + } + return ret; +} + +static unsigned long raid5_cache_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + struct r5conf *conf = container_of(shrink, struct r5conf, shrinker); + + if (conf->max_nr_stripes < conf->min_nr_stripes) + /* unlikely, but not impossible */ + return 0; + return conf->max_nr_stripes - conf->min_nr_stripes; +} + static struct r5conf *setup_conf(struct mddev *mddev) { struct r5conf *conf; @@ -5874,7 +6418,6 @@ static struct r5conf *setup_conf(struct mddev *mddev) else conf->previous_raid_disks = mddev->raid_disks - mddev->delta_disks; max_disks = max(conf->raid_disks, conf->previous_raid_disks); - conf->scribble_len = scribble_len(max_disks); conf->disks = kzalloc(max_disks * sizeof(struct disk_info), GFP_KERNEL); @@ -5902,6 +6445,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) INIT_LIST_HEAD(conf->temp_inactive_list + i); conf->level = mddev->new_level; + conf->chunk_sectors = mddev->new_chunk_sectors; if (raid5_alloc_percpu(conf) != 0) goto abort; @@ -5934,12 +6478,17 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->fullsync = 1; } - conf->chunk_sectors = mddev->new_chunk_sectors; conf->level = mddev->new_level; - if (conf->level == 6) + if (conf->level == 6) { conf->max_degraded = 2; - else + if (raid6_call.xor_syndrome) + conf->rmw_level = PARITY_ENABLE_RMW; + else + conf->rmw_level = PARITY_DISABLE_RMW; + } else { conf->max_degraded = 1; + conf->rmw_level = PARITY_ENABLE_RMW; + } conf->algorithm = mddev->new_layout; conf->reshape_progress = mddev->reshape_position; if (conf->reshape_progress != MaxSector) { @@ -5947,10 +6496,11 @@ static struct r5conf *setup_conf(struct mddev *mddev) conf->prev_algo = mddev->layout; } - memory = conf->max_nr_stripes * (sizeof(struct stripe_head) + + conf->min_nr_stripes = NR_STRIPES; + memory = conf->min_nr_stripes * (sizeof(struct stripe_head) + max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024; atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS); - if (grow_stripes(conf, NR_STRIPES)) { + if (grow_stripes(conf, conf->min_nr_stripes)) { printk(KERN_ERR "md/raid:%s: couldn't allocate %dkB for buffers\n", mdname(mddev), memory); @@ -5958,6 +6508,17 @@ static struct r5conf *setup_conf(struct mddev *mddev) } else printk(KERN_INFO "md/raid:%s: allocated %dkB\n", mdname(mddev), memory); + /* + * Losing a stripe head costs more than the time to refill it, + * it reduces the queue depth and so can hurt throughput. + * So set it rather large, scaled by number of devices. + */ + conf->shrinker.seeks = DEFAULT_SEEKS * conf->raid_disks * 4; + conf->shrinker.scan_objects = raid5_cache_scan; + conf->shrinker.count_objects = raid5_cache_count; + conf->shrinker.batch = 128; + conf->shrinker.flags = 0; + register_shrinker(&conf->shrinker); sprintf(pers_name, "raid%d", mddev->new_level); conf->thread = md_register_thread(raid5d, mddev, pers_name); @@ -6599,9 +7160,9 @@ static int check_stripe_cache(struct mddev *mddev) */ struct r5conf *conf = mddev->private; if (((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4 - > conf->max_nr_stripes || + > conf->min_nr_stripes || ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4 - > conf->max_nr_stripes) { + > conf->min_nr_stripes) { printk(KERN_WARNING "md/raid:%s: reshape: not enough stripes. Needed %lu\n", mdname(mddev), ((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9) diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 983e18a83db1..7dc0dd86074b 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -210,11 +210,19 @@ struct stripe_head { atomic_t count; /* nr of active thread/requests */ int bm_seq; /* sequence number for bitmap flushes */ int disks; /* disks in stripe */ + int overwrite_disks; /* total overwrite disks in stripe, + * this is only checked when stripe + * has STRIPE_BATCH_READY + */ enum check_states check_state; enum reconstruct_states reconstruct_state; spinlock_t stripe_lock; int cpu; struct r5worker_group *group; + + struct stripe_head *batch_head; /* protected by stripe lock */ + spinlock_t batch_lock; /* only header's lock is useful */ + struct list_head batch_list; /* protected by head's batch lock*/ /** * struct stripe_operations * @target - STRIPE_OP_COMPUTE_BLK target @@ -327,8 +335,15 @@ enum { STRIPE_ON_UNPLUG_LIST, STRIPE_DISCARD, STRIPE_ON_RELEASE_LIST, + STRIPE_BATCH_READY, + STRIPE_BATCH_ERR, }; +#define STRIPE_EXPAND_SYNC_FLAG \ + ((1 << STRIPE_EXPAND_SOURCE) |\ + (1 << STRIPE_EXPAND_READY) |\ + (1 << STRIPE_EXPANDING) |\ + (1 << STRIPE_SYNC_REQUESTED)) /* * Operation request flags */ @@ -340,6 +355,24 @@ enum { STRIPE_OP_RECONSTRUCT, STRIPE_OP_CHECK, }; + +/* + * RAID parity calculation preferences + */ +enum { + PARITY_DISABLE_RMW = 0, + PARITY_ENABLE_RMW, + PARITY_PREFER_RMW, +}; + +/* + * Pages requested from set_syndrome_sources() + */ +enum { + SYNDROME_SRC_ALL, + SYNDROME_SRC_WANT_DRAIN, + SYNDROME_SRC_WRITTEN, +}; /* * Plugging: * @@ -396,10 +429,11 @@ struct r5conf { spinlock_t hash_locks[NR_STRIPE_HASH_LOCKS]; struct mddev *mddev; int chunk_sectors; - int level, algorithm; + int level, algorithm, rmw_level; int max_degraded; int raid_disks; int max_nr_stripes; + int min_nr_stripes; /* reshape_progress is the leading edge of a 'reshape' * It has value MaxSector when no reshape is happening @@ -458,15 +492,11 @@ struct r5conf { /* per cpu variables */ struct raid5_percpu { struct page *spare_page; /* Used when checking P/Q in raid6 */ - void *scribble; /* space for constructing buffer + struct flex_array *scribble; /* space for constructing buffer * lists and performing address * conversions */ } __percpu *percpu; - size_t scribble_len; /* size of scribble region must be - * associated with conf to handle - * cpu hotplug while reshaping - */ #ifdef CONFIG_HOTPLUG_CPU struct notifier_block cpu_notify; #endif @@ -480,9 +510,19 @@ struct r5conf { struct llist_head released_stripes; wait_queue_head_t wait_for_stripe; wait_queue_head_t wait_for_overlap; - int inactive_blocked; /* release of inactive stripes blocked, - * waiting for 25% to be free - */ + unsigned long cache_state; +#define R5_INACTIVE_BLOCKED 1 /* release of inactive stripes blocked, + * waiting for 25% to be free + */ +#define R5_ALLOC_MORE 2 /* It might help to allocate another + * stripe. + */ +#define R5_DID_ALLOC 4 /* A stripe was allocated, don't allocate + * more until at least one has been + * released. This avoids flooding + * the cache. + */ + struct shrinker shrinker; int pool_size; /* number of disks in stripeheads in pool */ spinlock_t device_lock; struct disk_info *disks; @@ -497,6 +537,7 @@ struct r5conf { int worker_cnt_per_group; }; + /* * Our supported algorithms */ |