diff options
Diffstat (limited to 'drivers/block/drbd')
| -rw-r--r-- | drivers/block/drbd/drbd_actlog.c | 323 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_bitmap.c | 48 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_debugfs.c | 14 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_int.h | 114 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_main.c | 74 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_nl.c | 1361 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_proc.c | 6 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_protocol.h | 2 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_receiver.c | 254 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_req.c | 147 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_req.h | 17 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_state.c | 428 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_state.h | 6 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_state_change.h | 63 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_worker.c | 105 |
15 files changed, 2358 insertions, 604 deletions
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index b3868e7a1..10459a145 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -288,7 +288,162 @@ bool drbd_al_begin_io_prepare(struct drbd_device *device, struct drbd_interval * return need_transaction; } -static int al_write_transaction(struct drbd_device *device); +#if (PAGE_SHIFT + 3) < (AL_EXTENT_SHIFT - BM_BLOCK_SHIFT) +/* Currently BM_BLOCK_SHIFT, BM_EXT_SHIFT and AL_EXTENT_SHIFT + * are still coupled, or assume too much about their relation. + * Code below will not work if this is violated. + * Will be cleaned up with some followup patch. + */ +# error FIXME +#endif + +static unsigned int al_extent_to_bm_page(unsigned int al_enr) +{ + return al_enr >> + /* bit to page */ + ((PAGE_SHIFT + 3) - + /* al extent number to bit */ + (AL_EXTENT_SHIFT - BM_BLOCK_SHIFT)); +} + +static sector_t al_tr_number_to_on_disk_sector(struct drbd_device *device) +{ + const unsigned int stripes = device->ldev->md.al_stripes; + const unsigned int stripe_size_4kB = device->ldev->md.al_stripe_size_4k; + + /* transaction number, modulo on-disk ring buffer wrap around */ + unsigned int t = device->al_tr_number % (device->ldev->md.al_size_4k); + + /* ... to aligned 4k on disk block */ + t = ((t % stripes) * stripe_size_4kB) + t/stripes; + + /* ... to 512 byte sector in activity log */ + t *= 8; + + /* ... plus offset to the on disk position */ + return device->ldev->md.md_offset + device->ldev->md.al_offset + t; +} + +static int __al_write_transaction(struct drbd_device *device, struct al_transaction_on_disk *buffer) +{ + struct lc_element *e; + sector_t sector; + int i, mx; + unsigned extent_nr; + unsigned crc = 0; + int err = 0; + + memset(buffer, 0, sizeof(*buffer)); + buffer->magic = cpu_to_be32(DRBD_AL_MAGIC); + buffer->tr_number = cpu_to_be32(device->al_tr_number); + + i = 0; + + /* Even though no one can start to change this list + * once we set the LC_LOCKED -- from drbd_al_begin_io(), + * lc_try_lock_for_transaction() --, someone may still + * be in the process of changing it. */ + spin_lock_irq(&device->al_lock); + list_for_each_entry(e, &device->act_log->to_be_changed, list) { + if (i == AL_UPDATES_PER_TRANSACTION) { + i++; + break; + } + buffer->update_slot_nr[i] = cpu_to_be16(e->lc_index); + buffer->update_extent_nr[i] = cpu_to_be32(e->lc_new_number); + if (e->lc_number != LC_FREE) + drbd_bm_mark_for_writeout(device, + al_extent_to_bm_page(e->lc_number)); + i++; + } + spin_unlock_irq(&device->al_lock); + BUG_ON(i > AL_UPDATES_PER_TRANSACTION); + + buffer->n_updates = cpu_to_be16(i); + for ( ; i < AL_UPDATES_PER_TRANSACTION; i++) { + buffer->update_slot_nr[i] = cpu_to_be16(-1); + buffer->update_extent_nr[i] = cpu_to_be32(LC_FREE); + } + + buffer->context_size = cpu_to_be16(device->act_log->nr_elements); + buffer->context_start_slot_nr = cpu_to_be16(device->al_tr_cycle); + + mx = min_t(int, AL_CONTEXT_PER_TRANSACTION, + device->act_log->nr_elements - device->al_tr_cycle); + for (i = 0; i < mx; i++) { + unsigned idx = device->al_tr_cycle + i; + extent_nr = lc_element_by_index(device->act_log, idx)->lc_number; + buffer->context[i] = cpu_to_be32(extent_nr); + } + for (; i < AL_CONTEXT_PER_TRANSACTION; i++) + buffer->context[i] = cpu_to_be32(LC_FREE); + + device->al_tr_cycle += AL_CONTEXT_PER_TRANSACTION; + if (device->al_tr_cycle >= device->act_log->nr_elements) + device->al_tr_cycle = 0; + + sector = al_tr_number_to_on_disk_sector(device); + + crc = crc32c(0, buffer, 4096); + buffer->crc32c = cpu_to_be32(crc); + + if (drbd_bm_write_hinted(device)) + err = -EIO; + else { + bool write_al_updates; + rcu_read_lock(); + write_al_updates = rcu_dereference(device->ldev->disk_conf)->al_updates; + rcu_read_unlock(); + if (write_al_updates) { + if (drbd_md_sync_page_io(device, device->ldev, sector, WRITE)) { + err = -EIO; + drbd_chk_io_error(device, 1, DRBD_META_IO_ERROR); + } else { + device->al_tr_number++; + device->al_writ_cnt++; + } + } + } + + return err; +} + +static int al_write_transaction(struct drbd_device *device) +{ + struct al_transaction_on_disk *buffer; + int err; + + if (!get_ldev(device)) { + drbd_err(device, "disk is %s, cannot start al transaction\n", + drbd_disk_str(device->state.disk)); + return -EIO; + } + + /* The bitmap write may have failed, causing a state change. */ + if (device->state.disk < D_INCONSISTENT) { + drbd_err(device, + "disk is %s, cannot write al transaction\n", + drbd_disk_str(device->state.disk)); + put_ldev(device); + return -EIO; + } + + /* protects md_io_buffer, al_tr_cycle, ... */ + buffer = drbd_md_get_buffer(device, __func__); + if (!buffer) { + drbd_err(device, "disk failed while waiting for md_io buffer\n"); + put_ldev(device); + return -ENODEV; + } + + err = __al_write_transaction(device, buffer); + + drbd_md_put_buffer(device); + put_ldev(device); + + return err; +} + void drbd_al_begin_io_commit(struct drbd_device *device) { @@ -420,153 +575,6 @@ void drbd_al_complete_io(struct drbd_device *device, struct drbd_interval *i) wake_up(&device->al_wait); } -#if (PAGE_SHIFT + 3) < (AL_EXTENT_SHIFT - BM_BLOCK_SHIFT) -/* Currently BM_BLOCK_SHIFT, BM_EXT_SHIFT and AL_EXTENT_SHIFT - * are still coupled, or assume too much about their relation. - * Code below will not work if this is violated. - * Will be cleaned up with some followup patch. - */ -# error FIXME -#endif - -static unsigned int al_extent_to_bm_page(unsigned int al_enr) -{ - return al_enr >> - /* bit to page */ - ((PAGE_SHIFT + 3) - - /* al extent number to bit */ - (AL_EXTENT_SHIFT - BM_BLOCK_SHIFT)); -} - -static sector_t al_tr_number_to_on_disk_sector(struct drbd_device *device) -{ - const unsigned int stripes = device->ldev->md.al_stripes; - const unsigned int stripe_size_4kB = device->ldev->md.al_stripe_size_4k; - - /* transaction number, modulo on-disk ring buffer wrap around */ - unsigned int t = device->al_tr_number % (device->ldev->md.al_size_4k); - - /* ... to aligned 4k on disk block */ - t = ((t % stripes) * stripe_size_4kB) + t/stripes; - - /* ... to 512 byte sector in activity log */ - t *= 8; - - /* ... plus offset to the on disk position */ - return device->ldev->md.md_offset + device->ldev->md.al_offset + t; -} - -int al_write_transaction(struct drbd_device *device) -{ - struct al_transaction_on_disk *buffer; - struct lc_element *e; - sector_t sector; - int i, mx; - unsigned extent_nr; - unsigned crc = 0; - int err = 0; - - if (!get_ldev(device)) { - drbd_err(device, "disk is %s, cannot start al transaction\n", - drbd_disk_str(device->state.disk)); - return -EIO; - } - - /* The bitmap write may have failed, causing a state change. */ - if (device->state.disk < D_INCONSISTENT) { - drbd_err(device, - "disk is %s, cannot write al transaction\n", - drbd_disk_str(device->state.disk)); - put_ldev(device); - return -EIO; - } - - /* protects md_io_buffer, al_tr_cycle, ... */ - buffer = drbd_md_get_buffer(device, __func__); - if (!buffer) { - drbd_err(device, "disk failed while waiting for md_io buffer\n"); - put_ldev(device); - return -ENODEV; - } - - memset(buffer, 0, sizeof(*buffer)); - buffer->magic = cpu_to_be32(DRBD_AL_MAGIC); - buffer->tr_number = cpu_to_be32(device->al_tr_number); - - i = 0; - - /* Even though no one can start to change this list - * once we set the LC_LOCKED -- from drbd_al_begin_io(), - * lc_try_lock_for_transaction() --, someone may still - * be in the process of changing it. */ - spin_lock_irq(&device->al_lock); - list_for_each_entry(e, &device->act_log->to_be_changed, list) { - if (i == AL_UPDATES_PER_TRANSACTION) { - i++; - break; - } - buffer->update_slot_nr[i] = cpu_to_be16(e->lc_index); - buffer->update_extent_nr[i] = cpu_to_be32(e->lc_new_number); - if (e->lc_number != LC_FREE) - drbd_bm_mark_for_writeout(device, - al_extent_to_bm_page(e->lc_number)); - i++; - } - spin_unlock_irq(&device->al_lock); - BUG_ON(i > AL_UPDATES_PER_TRANSACTION); - - buffer->n_updates = cpu_to_be16(i); - for ( ; i < AL_UPDATES_PER_TRANSACTION; i++) { - buffer->update_slot_nr[i] = cpu_to_be16(-1); - buffer->update_extent_nr[i] = cpu_to_be32(LC_FREE); - } - - buffer->context_size = cpu_to_be16(device->act_log->nr_elements); - buffer->context_start_slot_nr = cpu_to_be16(device->al_tr_cycle); - - mx = min_t(int, AL_CONTEXT_PER_TRANSACTION, - device->act_log->nr_elements - device->al_tr_cycle); - for (i = 0; i < mx; i++) { - unsigned idx = device->al_tr_cycle + i; - extent_nr = lc_element_by_index(device->act_log, idx)->lc_number; - buffer->context[i] = cpu_to_be32(extent_nr); - } - for (; i < AL_CONTEXT_PER_TRANSACTION; i++) - buffer->context[i] = cpu_to_be32(LC_FREE); - - device->al_tr_cycle += AL_CONTEXT_PER_TRANSACTION; - if (device->al_tr_cycle >= device->act_log->nr_elements) - device->al_tr_cycle = 0; - - sector = al_tr_number_to_on_disk_sector(device); - - crc = crc32c(0, buffer, 4096); - buffer->crc32c = cpu_to_be32(crc); - - if (drbd_bm_write_hinted(device)) - err = -EIO; - else { - bool write_al_updates; - rcu_read_lock(); - write_al_updates = rcu_dereference(device->ldev->disk_conf)->al_updates; - rcu_read_unlock(); - if (write_al_updates) { - if (drbd_md_sync_page_io(device, device->ldev, sector, WRITE)) { - err = -EIO; - drbd_chk_io_error(device, 1, DRBD_META_IO_ERROR); - } else { - device->al_tr_number++; - device->al_writ_cnt++; - } - } - } - - drbd_md_put_buffer(device); - put_ldev(device); - - return err; -} - static int _try_lc_del(struct drbd_device *device, struct lc_element *al_ext) { int rv; @@ -606,21 +614,24 @@ void drbd_al_shrink(struct drbd_device *device) wake_up(&device->al_wait); } -int drbd_initialize_al(struct drbd_device *device, void *buffer) +int drbd_al_initialize(struct drbd_device *device, void *buffer) { struct al_transaction_on_disk *al = buffer; struct drbd_md *md = &device->ldev->md; - sector_t al_base = md->md_offset + md->al_offset; int al_size_4k = md->al_stripes * md->al_stripe_size_4k; int i; - memset(al, 0, 4096); - al->magic = cpu_to_be32(DRBD_AL_MAGIC); - al->transaction_type = cpu_to_be16(AL_TR_INITIALIZED); - al->crc32c = cpu_to_be32(crc32c(0, al, 4096)); + __al_write_transaction(device, al); + /* There may or may not have been a pending transaction. */ + spin_lock_irq(&device->al_lock); + lc_committed(device->act_log); + spin_unlock_irq(&device->al_lock); - for (i = 0; i < al_size_4k; i++) { - int err = drbd_md_sync_page_io(device, device->ldev, al_base + i * 8, WRITE); + /* The rest of the transactions will have an empty "updates" list, and + * are written out only to provide the context, and to initialize the + * on-disk ring buffer. */ + for (i = 1; i < al_size_4k; i++) { + int err = __al_write_transaction(device, al); if (err) return err; } diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 9462d2752..92d6fc020 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -24,7 +24,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/vmalloc.h> #include <linux/string.h> #include <linux/drbd.h> @@ -364,12 +364,9 @@ static void bm_free_pages(struct page **pages, unsigned long number) } } -static void bm_vk_free(void *ptr, int v) +static inline void bm_vk_free(void *ptr) { - if (v) - vfree(ptr); - else - kfree(ptr); + kvfree(ptr); } /* @@ -379,7 +376,7 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want) { struct page **old_pages = b->bm_pages; struct page **new_pages, *page; - unsigned int i, bytes, vmalloced = 0; + unsigned int i, bytes; unsigned long have = b->bm_number_of_pages; BUG_ON(have == 0 && old_pages != NULL); @@ -401,7 +398,6 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want) PAGE_KERNEL); if (!new_pages) return NULL; - vmalloced = 1; } if (want >= have) { @@ -411,7 +407,7 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want) page = alloc_page(GFP_NOIO | __GFP_HIGHMEM); if (!page) { bm_free_pages(new_pages + have, i - have); - bm_vk_free(new_pages, vmalloced); + bm_vk_free(new_pages); return NULL; } /* we want to know which page it is @@ -427,11 +423,6 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want) */ } - if (vmalloced) - b->bm_flags |= BM_P_VMALLOCED; - else - b->bm_flags &= ~BM_P_VMALLOCED; - return new_pages; } @@ -469,7 +460,7 @@ void drbd_bm_cleanup(struct drbd_device *device) if (!expect(device->bitmap)) return; bm_free_pages(device->bitmap->bm_pages, device->bitmap->bm_number_of_pages); - bm_vk_free(device->bitmap->bm_pages, (BM_P_VMALLOCED & device->bitmap->bm_flags)); + bm_vk_free(device->bitmap->bm_pages); kfree(device->bitmap); device->bitmap = NULL; } @@ -479,8 +470,14 @@ void drbd_bm_cleanup(struct drbd_device *device) * this masks out the remaining bits. * Returns the number of bits cleared. */ +#ifndef BITS_PER_PAGE #define BITS_PER_PAGE (1UL << (PAGE_SHIFT + 3)) #define BITS_PER_PAGE_MASK (BITS_PER_PAGE - 1) +#else +# if BITS_PER_PAGE != (1UL << (PAGE_SHIFT + 3)) +# error "ambiguous BITS_PER_PAGE" +# endif +#endif #define BITS_PER_LONG_MASK (BITS_PER_LONG - 1) static int bm_clear_surplus(struct drbd_bitmap *b) { @@ -559,21 +556,19 @@ static unsigned long bm_count_bits(struct drbd_bitmap *b) unsigned long *p_addr; unsigned long bits = 0; unsigned long mask = (1UL << (b->bm_bits & BITS_PER_LONG_MASK)) -1; - int idx, i, last_word; + int idx, last_word; /* all but last page */ for (idx = 0; idx < b->bm_number_of_pages - 1; idx++) { p_addr = __bm_map_pidx(b, idx); - for (i = 0; i < LWPP; i++) - bits += hweight_long(p_addr[i]); + bits += bitmap_weight(p_addr, BITS_PER_PAGE); __bm_unmap(p_addr); cond_resched(); } /* last (or only) page */ last_word = ((b->bm_bits - 1) & BITS_PER_PAGE_MASK) >> LN2_BPL; p_addr = __bm_map_pidx(b, idx); - for (i = 0; i < last_word; i++) - bits += hweight_long(p_addr[i]); + bits += bitmap_weight(p_addr, last_word * BITS_PER_LONG); p_addr[last_word] &= cpu_to_lel(mask); bits += hweight_long(p_addr[last_word]); /* 32bit arch, may have an unused padding long */ @@ -639,7 +634,6 @@ int drbd_bm_resize(struct drbd_device *device, sector_t capacity, int set_new_bi unsigned long want, have, onpages; /* number of pages */ struct page **npages, **opages = NULL; int err = 0, growing; - int opages_vmalloced; if (!expect(b)) return -ENOMEM; @@ -652,8 +646,6 @@ int drbd_bm_resize(struct drbd_device *device, sector_t capacity, int set_new_bi if (capacity == b->bm_dev_capacity) goto out; - opages_vmalloced = (BM_P_VMALLOCED & b->bm_flags); - if (capacity == 0) { spin_lock_irq(&b->bm_lock); opages = b->bm_pages; @@ -667,7 +659,7 @@ int drbd_bm_resize(struct drbd_device *device, sector_t capacity, int set_new_bi b->bm_dev_capacity = 0; spin_unlock_irq(&b->bm_lock); bm_free_pages(opages, onpages); - bm_vk_free(opages, opages_vmalloced); + bm_vk_free(opages); goto out; } bits = BM_SECT_TO_BIT(ALIGN(capacity, BM_SECT_PER_BIT)); @@ -740,7 +732,7 @@ int drbd_bm_resize(struct drbd_device *device, sector_t capacity, int set_new_bi spin_unlock_irq(&b->bm_lock); if (opages != npages) - bm_vk_free(opages, opages_vmalloced); + bm_vk_free(opages); if (!growing) b->bm_set = bm_count_bits(b); drbd_info(device, "resync bitmap: bits=%lu words=%lu pages=%lu\n", bits, words, want); @@ -1419,6 +1411,9 @@ static inline void bm_set_full_words_within_one_page(struct drbd_bitmap *b, int bits; int changed = 0; unsigned long *paddr = kmap_atomic(b->bm_pages[page_nr]); + + /* I think it is more cache line friendly to hweight_long then set to ~0UL, + * than to first bitmap_weight() all words, then bitmap_fill() all words */ for (i = first_word; i < last_word; i++) { bits = hweight_long(paddr[i]); paddr[i] = ~0UL; @@ -1628,8 +1623,7 @@ int drbd_bm_e_weight(struct drbd_device *device, unsigned long enr) int n = e-s; p_addr = bm_map_pidx(b, bm_word_to_page_idx(b, s)); bm = p_addr + MLPP(s); - while (n--) - count += hweight_long(*bm++); + count += bitmap_weight(bm, n * BITS_PER_LONG); bm_unmap(p_addr); } else { drbd_err(device, "start offset (%d) too large in drbd_bm_e_weight\n", s); diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c index 6b88a35fb..4de95bbff 100644 --- a/drivers/block/drbd/drbd_debugfs.c +++ b/drivers/block/drbd/drbd_debugfs.c @@ -434,12 +434,12 @@ static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, vo if (!parent || d_really_is_negative(parent)) goto out; /* serialize with d_delete() */ - mutex_lock(&d_inode(parent)->i_mutex); + inode_lock(d_inode(parent)); /* Make sure the object is still alive */ if (simple_positive(file->f_path.dentry) && kref_get_unless_zero(kref)) ret = 0; - mutex_unlock(&d_inode(parent)->i_mutex); + inode_unlock(d_inode(parent)); if (!ret) { ret = single_open(file, show, data); if (ret) @@ -771,6 +771,13 @@ static int device_data_gen_id_show(struct seq_file *m, void *ignored) return 0; } +static int device_ed_gen_id_show(struct seq_file *m, void *ignored) +{ + struct drbd_device *device = m->private; + seq_printf(m, "0x%016llX\n", (unsigned long long)device->ed_uuid); + return 0; +} + #define drbd_debugfs_device_attr(name) \ static int device_ ## name ## _open(struct inode *inode, struct file *file) \ { \ @@ -796,6 +803,7 @@ drbd_debugfs_device_attr(oldest_requests) drbd_debugfs_device_attr(act_log_extents) drbd_debugfs_device_attr(resync_extents) drbd_debugfs_device_attr(data_gen_id) +drbd_debugfs_device_attr(ed_gen_id) void drbd_debugfs_device_add(struct drbd_device *device) { @@ -839,6 +847,7 @@ void drbd_debugfs_device_add(struct drbd_device *device) DCF(act_log_extents); DCF(resync_extents); DCF(data_gen_id); + DCF(ed_gen_id); #undef DCF return; @@ -854,6 +863,7 @@ void drbd_debugfs_device_cleanup(struct drbd_device *device) drbd_debugfs_remove(&device->debugfs_vol_act_log_extents); drbd_debugfs_remove(&device->debugfs_vol_resync_extents); drbd_debugfs_remove(&device->debugfs_vol_data_gen_id); + drbd_debugfs_remove(&device->debugfs_vol_ed_gen_id); drbd_debugfs_remove(&device->debugfs_vol); } diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index e66d453a5..34bc84efc 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -77,13 +77,6 @@ extern int fault_devs; extern char usermode_helper[]; -/* I don't remember why XCPU ... - * This is used to wake the asender, - * and to interrupt sending the sending task - * on disconnect. - */ -#define DRBD_SIG SIGXCPU - /* This is used to stop/restart our threads. * Cannot use SIGTERM nor SIGKILL, since these * are sent out by init on runlevel changes @@ -292,6 +285,9 @@ struct drbd_device_work { extern int drbd_wait_misc(struct drbd_device *, struct drbd_interval *); +extern void lock_all_resources(void); +extern void unlock_all_resources(void); + struct drbd_request { struct drbd_work w; struct drbd_device *device; @@ -504,7 +500,6 @@ enum { MD_NO_FUA, /* Users wants us to not use FUA/FLUSH on meta data dev */ - SUSPEND_IO, /* suspend application io */ BITMAP_IO, /* suspend application io; once no more io in flight, start bitmap io */ BITMAP_IO_QUEUED, /* Started bitmap IO */ @@ -541,9 +536,6 @@ struct drbd_bitmap; /* opaque for drbd_device */ /* definition of bits in bm_flags to be used in drbd_bm_lock * and drbd_bitmap_io and friends. */ enum bm_flag { - /* do we need to kfree, or vfree bm_pages? */ - BM_P_VMALLOCED = 0x10000, /* internal use only, will be masked out */ - /* currently locked for bulk operation */ BM_LOCKED_MASK = 0xf, @@ -632,12 +624,6 @@ struct bm_io_work { void (*done)(struct drbd_device *device, int rv); }; -enum write_ordering_e { - WO_none, - WO_drain_io, - WO_bdev_flush, -}; - struct fifo_buffer { unsigned int head_index; unsigned int size; @@ -650,8 +636,7 @@ extern struct fifo_buffer *fifo_alloc(int fifo_size); enum { NET_CONGESTED, /* The data socket is congested */ RESOLVE_CONFLICTS, /* Set on one node, cleared on the peer! */ - SEND_PING, /* whether asender should send a ping asap */ - SIGNAL_ASENDER, /* whether asender wants to be interrupted */ + SEND_PING, GOT_PING_ACK, /* set when we receive a ping_ack packet, ping_wait gets woken */ CONN_WD_ST_CHG_REQ, /* A cluster wide state change on the connection is active */ CONN_WD_ST_CHG_OKAY, @@ -670,6 +655,8 @@ enum { DEVICE_WORK_PENDING, /* tell worker that some device has pending work */ }; +enum which_state { NOW, OLD = NOW, NEW }; + struct drbd_resource { char *name; #ifdef CONFIG_DEBUG_FS @@ -755,7 +742,8 @@ struct drbd_connection { unsigned long last_reconnect_jif; struct drbd_thread receiver; struct drbd_thread worker; - struct drbd_thread asender; + struct drbd_thread ack_receiver; + struct workqueue_struct *ack_sender; /* cached pointers, * so we can look up the oldest pending requests more quickly. @@ -774,6 +762,8 @@ struct drbd_connection { struct drbd_thread_timing_details r_timing_details[DRBD_THREAD_DETAILS_HIST]; struct { + unsigned long last_sent_barrier_jif; + /* whether this sender thread * has processed a single write yet. */ bool seen_any_write_yet; @@ -788,6 +778,17 @@ struct drbd_connection { } send; }; +static inline bool has_net_conf(struct drbd_connection *connection) +{ + bool has_net_conf; + + rcu_read_lock(); + has_net_conf = rcu_dereference(connection->net_conf); + rcu_read_unlock(); + + return has_net_conf; +} + void __update_timing_details( struct drbd_thread_timing_details *tdp, unsigned int *cb_nr, @@ -811,6 +812,7 @@ struct drbd_peer_device { struct list_head peer_devices; struct drbd_device *device; struct drbd_connection *connection; + struct work_struct send_acks_work; #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_peer_dev; #endif @@ -829,6 +831,7 @@ struct drbd_device { struct dentry *debugfs_vol_act_log_extents; struct dentry *debugfs_vol_resync_extents; struct dentry *debugfs_vol_data_gen_id; + struct dentry *debugfs_vol_ed_gen_id; #endif unsigned int vnr; /* volume number within the connection */ @@ -873,6 +876,7 @@ struct drbd_device { atomic_t rs_pending_cnt; /* RS request/data packets on the wire */ atomic_t unacked_cnt; /* Need to send replies for */ atomic_t local_cnt; /* Waiting for local completion */ + atomic_t suspend_cnt; /* Interval tree of pending local requests */ struct rb_root read_requests; @@ -1020,6 +1024,12 @@ static inline struct drbd_peer_device *first_peer_device(struct drbd_device *dev return list_first_entry_or_null(&device->peer_devices, struct drbd_peer_device, peer_devices); } +static inline struct drbd_peer_device * +conn_peer_device(struct drbd_connection *connection, int volume_number) +{ + return idr_find(&connection->peer_devices, volume_number); +} + #define for_each_resource(resource, _resources) \ list_for_each_entry(resource, _resources, resources) @@ -1113,7 +1123,7 @@ extern int drbd_send_ov_request(struct drbd_peer_device *, sector_t sector, int extern int drbd_send_bitmap(struct drbd_device *device); extern void drbd_send_sr_reply(struct drbd_peer_device *, enum drbd_state_rv retcode); extern void conn_send_sr_reply(struct drbd_connection *connection, enum drbd_state_rv retcode); -extern void drbd_free_ldev(struct drbd_backing_dev *ldev); +extern void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev); extern void drbd_device_cleanup(struct drbd_device *device); void drbd_print_uuids(struct drbd_device *device, const char *text); @@ -1424,7 +1434,7 @@ extern struct bio_set *drbd_md_io_bio_set; /* to allocate from that set */ extern struct bio *bio_alloc_drbd(gfp_t gfp_mask); -extern rwlock_t global_state_lock; +extern struct mutex resources_mutex; extern int conn_lowest_minor(struct drbd_connection *connection); extern enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsigned int minor); @@ -1454,6 +1464,9 @@ extern int is_valid_ar_handle(struct drbd_request *, sector_t); /* drbd_nl.c */ + +extern struct mutex notification_mutex; + extern void drbd_suspend_io(struct drbd_device *device); extern void drbd_resume_io(struct drbd_device *device); extern char *ppsize(char *buf, unsigned long long size); @@ -1536,7 +1549,9 @@ extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req); /* drbd_receiver.c */ extern int drbd_receiver(struct drbd_thread *thi); -extern int drbd_asender(struct drbd_thread *thi); +extern int drbd_ack_receiver(struct drbd_thread *thi); +extern void drbd_send_ping_wf(struct work_struct *ws); +extern void drbd_send_acks_wf(struct work_struct *ws); extern bool drbd_rs_c_min_rate_throttle(struct drbd_device *device); extern bool drbd_rs_should_slow_down(struct drbd_device *device, sector_t sector, bool throttle_if_app_is_waiting); @@ -1649,7 +1664,7 @@ extern int __drbd_change_sync(struct drbd_device *device, sector_t sector, int s #define drbd_rs_failed_io(device, sector, size) \ __drbd_change_sync(device, sector, size, RECORD_RS_FAILED) extern void drbd_al_shrink(struct drbd_device *device); -extern int drbd_initialize_al(struct drbd_device *, void *); +extern int drbd_al_initialize(struct drbd_device *, void *); /* drbd_nl.c */ /* state info broadcast */ @@ -1668,6 +1683,29 @@ struct sib_info { }; void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib); +extern void notify_resource_state(struct sk_buff *, + unsigned int, + struct drbd_resource *, + struct resource_info *, + enum drbd_notification_type); +extern void notify_device_state(struct sk_buff *, + unsigned int, + struct drbd_device *, + struct device_info *, + enum drbd_notification_type); +extern void notify_connection_state(struct sk_buff *, + unsigned int, + struct drbd_connection *, + struct connection_info *, + enum drbd_notification_type); +extern void notify_peer_device_state(struct sk_buff *, + unsigned int, + struct drbd_peer_device *, + struct peer_device_info *, + enum drbd_notification_type); +extern void notify_helper(enum drbd_notification_type, struct drbd_device *, + struct drbd_connection *, const char *, int); + /* * inline helper functions *************************/ @@ -1694,19 +1732,6 @@ static inline int drbd_peer_req_has_active_page(struct drbd_peer_request *peer_r return 0; } -static inline enum drbd_state_rv -_drbd_set_state(struct drbd_device *device, union drbd_state ns, - enum chg_state_flags flags, struct completion *done) -{ - enum drbd_state_rv rv; - - read_lock(&global_state_lock); - rv = __drbd_set_state(device, ns, flags, done); - read_unlock(&global_state_lock); - - return rv; -} - static inline union drbd_state drbd_read_state(struct drbd_device *device) { struct drbd_resource *resource = device->resource; @@ -1937,16 +1962,21 @@ drbd_device_post_work(struct drbd_device *device, int work_bit) extern void drbd_flush_workqueue(struct drbd_work_queue *work_queue); -static inline void wake_asender(struct drbd_connection *connection) +/* To get the ack_receiver out of the blocking network stack, + * so it can change its sk_rcvtimeo from idle- to ping-timeout, + * and send a ping, we need to send a signal. + * Which signal we send is irrelevant. */ +static inline void wake_ack_receiver(struct drbd_connection *connection) { - if (test_bit(SIGNAL_ASENDER, &connection->flags)) - force_sig(DRBD_SIG, connection->asender.task); + struct task_struct *task = connection->ack_receiver.task; + if (task && get_t_state(&connection->ack_receiver) == RUNNING) + force_sig(SIGXCPU, task); } static inline void request_ping(struct drbd_connection *connection) { set_bit(SEND_PING, &connection->flags); - wake_asender(connection); + wake_ack_receiver(connection); } extern void *conn_prepare_command(struct drbd_connection *, struct drbd_socket *); @@ -2230,7 +2260,7 @@ static inline bool may_inc_ap_bio(struct drbd_device *device) if (drbd_suspended(device)) return false; - if (test_bit(SUSPEND_IO, &device->flags)) + if (atomic_read(&device->suspend_cnt)) return false; /* to avoid potential deadlock or bitmap corruption, diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 74d97f4ba..5b43dfb79 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -117,6 +117,7 @@ module_param_string(usermode_helper, usermode_helper, sizeof(usermode_helper), 0 */ struct idr drbd_devices; struct list_head drbd_resources; +struct mutex resources_mutex; struct kmem_cache *drbd_request_cache; struct kmem_cache *drbd_ee_cache; /* peer requests */ @@ -1435,8 +1436,8 @@ static int we_should_drop_the_connection(struct drbd_connection *connection, str /* long elapsed = (long)(jiffies - device->last_received); */ drop_it = connection->meta.socket == sock - || !connection->asender.task - || get_t_state(&connection->asender) != RUNNING + || !connection->ack_receiver.task + || get_t_state(&connection->ack_receiver) != RUNNING || connection->cstate < C_WF_REPORT_PARAMS; if (drop_it) @@ -1793,15 +1794,6 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock, drbd_update_congested(connection); } do { - /* STRANGE - * tcp_sendmsg does _not_ use its size parameter at all ? - * - * -EAGAIN on timeout, -EINTR on signal. - */ -/* THINK - * do we need to block DRBD_SIG if sock == &meta.socket ?? - * otherwise wake_asender() might interrupt some send_*Ack ! - */ rv = kernel_sendmsg(sock, &msg, &iov, 1, size); if (rv == -EAGAIN) { if (we_should_drop_the_connection(connection, sock)) @@ -2000,7 +1992,7 @@ void drbd_device_cleanup(struct drbd_device *device) drbd_bm_cleanup(device); } - drbd_free_ldev(device->ldev); + drbd_backing_dev_free(device, device->ldev); device->ldev = NULL; clear_bit(AL_SUSPENDED, &device->flags); @@ -2179,7 +2171,7 @@ void drbd_destroy_device(struct kref *kref) if (device->this_bdev) bdput(device->this_bdev); - drbd_free_ldev(device->ldev); + drbd_backing_dev_free(device, device->ldev); device->ldev = NULL; drbd_release_all_peer_reqs(device); @@ -2563,7 +2555,7 @@ int set_resource_options(struct drbd_resource *resource, struct res_opts *res_op cpumask_copy(resource->cpu_mask, new_cpu_mask); for_each_connection_rcu(connection, resource) { connection->receiver.reset_cpu_mask = 1; - connection->asender.reset_cpu_mask = 1; + connection->ack_receiver.reset_cpu_mask = 1; connection->worker.reset_cpu_mask = 1; } } @@ -2590,7 +2582,7 @@ struct drbd_resource *drbd_create_resource(const char *name) kref_init(&resource->kref); idr_init(&resource->devices); INIT_LIST_HEAD(&resource->connections); - resource->write_ordering = WO_bdev_flush; + resource->write_ordering = WO_BDEV_FLUSH; list_add_tail_rcu(&resource->resources, &drbd_resources); mutex_init(&resource->conf_update); mutex_init(&resource->adm_mutex); @@ -2652,8 +2644,8 @@ struct drbd_connection *conn_create(const char *name, struct res_opts *res_opts) connection->receiver.connection = connection; drbd_thread_init(resource, &connection->worker, drbd_worker, "worker"); connection->worker.connection = connection; - drbd_thread_init(resource, &connection->asender, drbd_asender, "asender"); - connection->asender.connection = connection; + drbd_thread_init(resource, &connection->ack_receiver, drbd_ack_receiver, "ack_recv"); + connection->ack_receiver.connection = connection; kref_init(&connection->kref); @@ -2702,8 +2694,8 @@ static int init_submitter(struct drbd_device *device) { /* opencoded create_singlethread_workqueue(), * to be able to say "drbd%d", ..., minor */ - device->submit.wq = alloc_workqueue("drbd%u_submit", - WQ_UNBOUND | WQ_MEM_RECLAIM, 1, device->minor); + device->submit.wq = + alloc_ordered_workqueue("drbd%u_submit", WQ_MEM_RECLAIM, device->minor); if (!device->submit.wq) return -ENOMEM; @@ -2820,6 +2812,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig goto out_idr_remove_from_resource; } kref_get(&connection->kref); + INIT_WORK(&peer_device->send_acks_work, drbd_send_acks_wf); } if (init_submitter(device)) { @@ -2923,7 +2916,7 @@ static int __init drbd_init(void) drbd_proc = NULL; /* play safe for drbd_cleanup */ idr_init(&drbd_devices); - rwlock_init(&global_state_lock); + mutex_init(&resources_mutex); INIT_LIST_HEAD(&drbd_resources); err = drbd_genl_register(); @@ -2971,18 +2964,6 @@ fail: return err; } -void drbd_free_ldev(struct drbd_backing_dev *ldev) -{ - if (ldev == NULL) - return; - - blkdev_put(ldev->backing_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); - blkdev_put(ldev->md_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); - - kfree(ldev->disk_conf); - kfree(ldev); -} - static void drbd_free_one_sock(struct drbd_socket *ds) { struct socket *s; @@ -3277,6 +3258,10 @@ int drbd_md_read(struct drbd_device *device, struct drbd_backing_dev *bdev) * and read it. */ bdev->md.meta_dev_idx = bdev->disk_conf->meta_dev_idx; bdev->md.md_offset = drbd_md_ss(bdev); + /* Even for (flexible or indexed) external meta data, + * initially restrict us to the 4k superblock for now. + * Affects the paranoia out-of-range access check in drbd_md_sync_page_io(). */ + bdev->md.md_size_sect = 8; if (drbd_md_sync_page_io(device, bdev, bdev->md.md_offset, READ)) { /* NOTE: can't do normal error processing here as this is @@ -3578,7 +3563,9 @@ void drbd_queue_bitmap_io(struct drbd_device *device, spin_lock_irq(&device->resource->req_lock); set_bit(BITMAP_IO, &device->flags); - if (atomic_read(&device->ap_bio_cnt) == 0) { + /* don't wait for pending application IO if the caller indicates that + * application IO does not conflict anyways. */ + if (flags == BM_LOCKED_CHANGE_ALLOWED || atomic_read(&device->ap_bio_cnt) == 0) { if (!test_and_set_bit(BITMAP_IO_QUEUED, &device->flags)) drbd_queue_work(&first_peer_device(device)->connection->sender_work, &device->bm_io_work.w); @@ -3746,6 +3733,27 @@ int drbd_wait_misc(struct drbd_device *device, struct drbd_interval *i) return 0; } +void lock_all_resources(void) +{ + struct drbd_resource *resource; + int __maybe_unused i = 0; + + mutex_lock(&resources_mutex); + local_irq_disable(); + for_each_resource(resource, &drbd_resources) + spin_lock_nested(&resource->req_lock, i++); +} + +void unlock_all_resources(void) +{ + struct drbd_resource *resource; + + for_each_resource(resource, &drbd_resources) + spin_unlock(&resource->req_lock); + local_irq_enable(); + mutex_unlock(&resources_mutex); +} + #ifdef CONFIG_DRBD_FAULT_INJECTION /* Fault insertion support including random number generator shamelessly * stolen from kernel/rcutorture.c */ diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index e80cbefbc..c055c5e12 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -36,6 +36,7 @@ #include "drbd_int.h" #include "drbd_protocol.h" #include "drbd_req.h" +#include "drbd_state_change.h" #include <asm/unaligned.h> #include <linux/drbd_limits.h> #include <linux/kthread.h> @@ -75,11 +76,24 @@ int drbd_adm_get_status(struct sk_buff *skb, struct genl_info *info); int drbd_adm_get_timeout_type(struct sk_buff *skb, struct genl_info *info); /* .dumpit */ int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb); +int drbd_adm_dump_resources(struct sk_buff *skb, struct netlink_callback *cb); +int drbd_adm_dump_devices(struct sk_buff *skb, struct netlink_callback *cb); +int drbd_adm_dump_devices_done(struct netlink_callback *cb); +int drbd_adm_dump_connections(struct sk_buff *skb, struct netlink_callback *cb); +int drbd_adm_dump_connections_done(struct netlink_callback *cb); +int drbd_adm_dump_peer_devices(struct sk_buff *skb, struct netlink_callback *cb); +int drbd_adm_dump_peer_devices_done(struct netlink_callback *cb); +int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb); #include <linux/drbd_genl_api.h> #include "drbd_nla.h" #include <linux/genl_magic_func.h> +static atomic_t drbd_genl_seq = ATOMIC_INIT(2); /* two. */ +static atomic_t notify_genl_seq = ATOMIC_INIT(2); /* two. */ + +DEFINE_MUTEX(notification_mutex); + /* used blkdev_get_by_path, to claim our meta data device(s) */ static char *drbd_m_holder = "Hands off! this is DRBD's meta data device."; @@ -349,6 +363,7 @@ int drbd_khelper(struct drbd_device *device, char *cmd) sib.sib_reason = SIB_HELPER_PRE; sib.helper_name = cmd; drbd_bcast_event(device, &sib); + notify_helper(NOTIFY_CALL, device, connection, cmd, 0); ret = call_usermodehelper(usermode_helper, argv, envp, UMH_WAIT_PROC); if (ret) drbd_warn(device, "helper command: %s %s %s exit code %u (0x%x)\n", @@ -361,6 +376,7 @@ int drbd_khelper(struct drbd_device *device, char *cmd) sib.sib_reason = SIB_HELPER_POST; sib.helper_exit_code = ret; drbd_bcast_event(device, &sib); + notify_helper(NOTIFY_RESPONSE, device, connection, cmd, ret); if (current == connection->worker.task) clear_bit(CALLBACK_PENDING, &connection->flags); @@ -388,6 +404,7 @@ static int conn_khelper(struct drbd_connection *connection, char *cmd) drbd_info(connection, "helper command: %s %s %s\n", usermode_helper, cmd, resource_name); /* TODO: conn_bcast_event() ?? */ + notify_helper(NOTIFY_CALL, NULL, connection, cmd, 0); ret = call_usermodehelper(usermode_helper, argv, envp, UMH_WAIT_PROC); if (ret) @@ -399,6 +416,7 @@ static int conn_khelper(struct drbd_connection *connection, char *cmd) usermode_helper, cmd, resource_name, (ret >> 8) & 0xff, ret); /* TODO: conn_bcast_event() ?? */ + notify_helper(NOTIFY_RESPONSE, NULL, connection, cmd, ret); if (ret < 0) /* Ignore any ERRNOs we got. */ ret = 0; @@ -847,9 +865,11 @@ char *ppsize(char *buf, unsigned long long size) * and can be long lived. * This changes an device->flag, is triggered by drbd internals, * and should be short-lived. */ +/* It needs to be a counter, since multiple threads might + independently suspend and resume IO. */ void drbd_suspend_io(struct drbd_device *device) { - set_bit(SUSPEND_IO, &device->flags); + atomic_inc(&device->suspend_cnt); if (drbd_suspended(device)) return; wait_event(device->misc_wait, !atomic_read(&device->ap_bio_cnt)); @@ -857,8 +877,8 @@ void drbd_suspend_io(struct drbd_device *device) void drbd_resume_io(struct drbd_device *device) { - clear_bit(SUSPEND_IO, &device->flags); - wake_up(&device->misc_wait); + if (atomic_dec_and_test(&device->suspend_cnt)) + wake_up(&device->misc_wait); } /** @@ -871,27 +891,32 @@ void drbd_resume_io(struct drbd_device *device) enum determine_dev_size drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct resize_parms *rs) __must_hold(local) { - sector_t prev_first_sect, prev_size; /* previous meta location */ - sector_t la_size_sect, u_size; + struct md_offsets_and_sizes { + u64 last_agreed_sect; + u64 md_offset; + s32 al_offset; + s32 bm_offset; + u32 md_size_sect; + + u32 al_stripes; + u32 al_stripe_size_4k; + } prev; + sector_t u_size, size; struct drbd_md *md = &device->ldev->md; - u32 prev_al_stripe_size_4k; - u32 prev_al_stripes; - sector_t size; char ppb[10]; void *buffer; int md_moved, la_size_changed; enum determine_dev_size rv = DS_UNCHANGED; - /* race: - * application request passes inc_ap_bio, - * but then cannot get an AL-reference. - * this function later may wait on ap_bio_cnt == 0. -> deadlock. + /* We may change the on-disk offsets of our meta data below. Lock out + * anything that may cause meta data IO, to avoid acting on incomplete + * layout changes or scribbling over meta data that is in the process + * of being moved. * - * to avoid that: - * Suspend IO right here. - * still lock the act_log to not trigger ASSERTs there. - */ + * Move is not exactly correct, btw, currently we have all our meta + * data in core memory, to "move" it we just write it all out, there + * are no reads. */ drbd_suspend_io(device); buffer = drbd_md_get_buffer(device, __func__); /* Lock meta-data IO */ if (!buffer) { @@ -899,19 +924,17 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct return DS_ERROR; } - /* no wait necessary anymore, actually we could assert that */ - wait_event(device->al_wait, lc_try_lock(device->act_log)); - - prev_first_sect = drbd_md_first_sector(device->ldev); - prev_size = device->ldev->md.md_size_sect; - la_size_sect = device->ldev->md.la_size_sect; + /* remember current offset and sizes */ + prev.last_agreed_sect = md->la_size_sect; + prev.md_offset = md->md_offset; + prev.al_offset = md->al_offset; + prev.bm_offset = md->bm_offset; + prev.md_size_sect = md->md_size_sect; + prev.al_stripes = md->al_stripes; + prev.al_stripe_size_4k = md->al_stripe_size_4k; if (rs) { /* rs is non NULL if we should change the AL layout only */ - - prev_al_stripes = md->al_stripes; - prev_al_stripe_size_4k = md->al_stripe_size_4k; - md->al_stripes = rs->al_stripes; md->al_stripe_size_4k = rs->al_stripe_size / 4; md->al_size_4k = (u64)rs->al_stripes * rs->al_stripe_size / 4; @@ -924,7 +947,7 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct rcu_read_unlock(); size = drbd_new_dev_size(device, device->ldev, u_size, flags & DDSF_FORCED); - if (size < la_size_sect) { + if (size < prev.last_agreed_sect) { if (rs && u_size == 0) { /* Remove "rs &&" later. This check should always be active, but right now the receiver expects the permissive behavior */ @@ -945,30 +968,29 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct err = drbd_bm_resize(device, size, !(flags & DDSF_NO_RESYNC)); if (unlikely(err)) { /* currently there is only one error: ENOMEM! */ - size = drbd_bm_capacity(device)>>1; + size = drbd_bm_capacity(device); if (size == 0) { drbd_err(device, "OUT OF MEMORY! " "Could not allocate bitmap!\n"); } else { drbd_err(device, "BM resizing failed. " - "Leaving size unchanged at size = %lu KB\n", - (unsigned long)size); + "Leaving size unchanged\n"); } rv = DS_ERROR; } /* racy, see comments above. */ drbd_set_my_capacity(device, size); - device->ldev->md.la_size_sect = size; + md->la_size_sect = size; drbd_info(device, "size = %s (%llu KB)\n", ppsize(ppb, size>>1), (unsigned long long)size>>1); } if (rv <= DS_ERROR) goto err_out; - la_size_changed = (la_size_sect != device->ldev->md.la_size_sect); + la_size_changed = (prev.last_agreed_sect != md->la_size_sect); - md_moved = prev_first_sect != drbd_md_first_sector(device->ldev) - || prev_size != device->ldev->md.md_size_sect; + md_moved = prev.md_offset != md->md_offset + || prev.md_size_sect != md->md_size_sect; if (la_size_changed || md_moved || rs) { u32 prev_flags; @@ -977,20 +999,29 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct * Clear the timer, to avoid scary "timer expired!" messages, * "Superblock" is written out at least twice below, anyways. */ del_timer(&device->md_sync_timer); - drbd_al_shrink(device); /* All extents inactive. */ + /* We won't change the "al-extents" setting, we just may need + * to move the on-disk location of the activity log ringbuffer. + * Lock for transaction is good enough, it may well be "dirty" + * or even "starving". */ + wait_event(device->al_wait, lc_try_lock_for_transaction(device->act_log)); + + /* mark current on-disk bitmap and activity log as unreliable */ prev_flags = md->flags; - md->flags &= ~MDF_PRIMARY_IND; + md->flags |= MDF_FULL_SYNC | MDF_AL_DISABLED; drbd_md_write(device, buffer); + drbd_al_initialize(device, buffer); + drbd_info(device, "Writing the whole bitmap, %s\n", la_size_changed && md_moved ? "size changed and md moved" : la_size_changed ? "size changed" : "md moved"); /* next line implicitly does drbd_suspend_io()+drbd_resume_io() */ drbd_bitmap_io(device, md_moved ? &drbd_bm_write_all : &drbd_bm_write, "size changed", BM_LOCKED_MASK); - drbd_initialize_al(device, buffer); + /* on-disk bitmap and activity log is authoritative again + * (unless there was an IO error meanwhile...) */ md->flags = prev_flags; drbd_md_write(device, buffer); @@ -999,20 +1030,22 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct md->al_stripes, md->al_stripe_size_4k * 4); } - if (size > la_size_sect) - rv = la_size_sect ? DS_GREW : DS_GREW_FROM_ZERO; - if (size < la_size_sect) + if (size > prev.last_agreed_sect) + rv = prev.last_agreed_sect ? DS_GREW : DS_GREW_FROM_ZERO; + if (size < prev.last_agreed_sect) rv = DS_SHRUNK; if (0) { err_out: - if (rs) { - md->al_stripes = prev_al_stripes; - md->al_stripe_size_4k = prev_al_stripe_size_4k; - md->al_size_4k = (u64)prev_al_stripes * prev_al_stripe_size_4k; - - drbd_md_set_sector_offsets(device, device->ldev); - } + /* restore previous offset and sizes */ + md->la_size_sect = prev.last_agreed_sect; + md->md_offset = prev.md_offset; + md->al_offset = prev.al_offset; + md->bm_offset = prev.bm_offset; + md->md_size_sect = prev.md_size_sect; + md->al_stripes = prev.al_stripes; + md->al_stripe_size_4k = prev.al_stripe_size_4k; + md->al_size_4k = (u64)prev.al_stripes * prev.al_stripe_size_4k; } lc_unlock(device->act_log); wake_up(&device->al_wait); @@ -1115,8 +1148,7 @@ static int drbd_check_al_size(struct drbd_device *device, struct disk_conf *dc) lc_destroy(n); return -EBUSY; } else { - if (t) - lc_destroy(t); + lc_destroy(t); } drbd_md_mark_dirty(device); /* we changed device->act_log->nr_elemens */ return 0; @@ -1151,21 +1183,20 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi if (b) { struct drbd_connection *connection = first_peer_device(device)->connection; + blk_queue_max_discard_sectors(q, DRBD_MAX_DISCARD_SECTORS); + if (blk_queue_discard(b) && (connection->cstate < C_CONNECTED || connection->agreed_features & FF_TRIM)) { - /* For now, don't allow more than one activity log extent worth of data - * to be discarded in one go. We may need to rework drbd_al_begin_io() - * to allow for even larger discard ranges */ - blk_queue_max_discard_sectors(q, DRBD_MAX_DISCARD_SECTORS); - + /* We don't care, stacking below should fix it for the local device. + * Whether or not it is a suitable granularity on the remote device + * is not our problem, really. If you care, you need to + * use devices with similar topology on all peers. */ + q->limits.discard_granularity = 512; queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); - /* REALLY? Is stacking secdiscard "legal"? */ - if (blk_queue_secdiscard(b)) - queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q); } else { blk_queue_max_discard_sectors(q, 0); queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); - queue_flag_clear_unlocked(QUEUE_FLAG_SECDISCARD, q); + q->limits.discard_granularity = 0; } blk_queue_stack_limits(q, b); @@ -1177,6 +1208,12 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages; } } + /* To avoid confusion, if this queue does not support discard, clear + * max_discard_sectors, which is what lsblk -D reports to the user. */ + if (!blk_queue_discard(q)) { + blk_queue_max_discard_sectors(q, 0); + q->limits.discard_granularity = 0; + } } void drbd_reconsider_max_bio_size(struct drbd_device *device, struct drbd_backing_dev *bdev) @@ -1241,8 +1278,8 @@ static void conn_reconfig_done(struct drbd_connection *connection) connection->cstate == C_STANDALONE; spin_unlock_irq(&connection->resource->req_lock); if (stop_threads) { - /* asender is implicitly stopped by receiver - * in conn_disconnect() */ + /* ack_receiver thread and ack_sender workqueue are implicitly + * stopped by receiver in conn_disconnect() */ drbd_thread_stop(&connection->receiver); drbd_thread_stop(&connection->worker); } @@ -1389,13 +1426,13 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) goto fail_unlock; } - write_lock_irq(&global_state_lock); + lock_all_resources(); retcode = drbd_resync_after_valid(device, new_disk_conf->resync_after); if (retcode == NO_ERROR) { rcu_assign_pointer(device->ldev->disk_conf, new_disk_conf); drbd_resync_after_changed(device); } - write_unlock_irq(&global_state_lock); + unlock_all_resources(); if (retcode != NO_ERROR) goto fail_unlock; @@ -1418,7 +1455,7 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) set_bit(MD_NO_FUA, &device->flags); if (write_ordering_changed(old_disk_conf, new_disk_conf)) - drbd_bump_write_ordering(device->resource, NULL, WO_bdev_flush); + drbd_bump_write_ordering(device->resource, NULL, WO_BDEV_FLUSH); drbd_md_sync(device); @@ -1449,6 +1486,88 @@ success: return 0; } +static struct block_device *open_backing_dev(struct drbd_device *device, + const char *bdev_path, void *claim_ptr, bool do_bd_link) +{ + struct block_device *bdev; + int err = 0; + + bdev = blkdev_get_by_path(bdev_path, + FMODE_READ | FMODE_WRITE | FMODE_EXCL, claim_ptr); + if (IS_ERR(bdev)) { + drbd_err(device, "open(\"%s\") failed with %ld\n", + bdev_path, PTR_ERR(bdev)); + return bdev; + } + + if (!do_bd_link) + return bdev; + + err = bd_link_disk_holder(bdev, device->vdisk); + if (err) { + blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + drbd_err(device, "bd_link_disk_holder(\"%s\", ...) failed with %d\n", + bdev_path, err); + bdev = ERR_PTR(err); + } + return bdev; +} + +static int open_backing_devices(struct drbd_device *device, + struct disk_conf *new_disk_conf, + struct drbd_backing_dev *nbc) +{ + struct block_device *bdev; + + bdev = open_backing_dev(device, new_disk_conf->backing_dev, device, true); + if (IS_ERR(bdev)) + return ERR_OPEN_DISK; + nbc->backing_bdev = bdev; + + /* + * meta_dev_idx >= 0: external fixed size, possibly multiple + * drbd sharing one meta device. TODO in that case, paranoia + * check that [md_bdev, meta_dev_idx] is not yet used by some + * other drbd minor! (if you use drbd.conf + drbdadm, that + * should check it for you already; but if you don't, or + * someone fooled it, we need to double check here) + */ + bdev = open_backing_dev(device, new_disk_conf->meta_dev, + /* claim ptr: device, if claimed exclusively; shared drbd_m_holder, + * if potentially shared with other drbd minors */ + (new_disk_conf->meta_dev_idx < 0) ? (void*)device : (void*)drbd_m_holder, + /* avoid double bd_claim_by_disk() for the same (source,target) tuple, + * as would happen with internal metadata. */ + (new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_FLEX_INT && + new_disk_conf->meta_dev_idx != DRBD_MD_INDEX_INTERNAL)); + if (IS_ERR(bdev)) + return ERR_OPEN_MD_DISK; + nbc->md_bdev = bdev; + return NO_ERROR; +} + +static void close_backing_dev(struct drbd_device *device, struct block_device *bdev, + bool do_bd_unlink) +{ + if (!bdev) + return; + if (do_bd_unlink) + bd_unlink_disk_holder(bdev, device->vdisk); + blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); +} + +void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev) +{ + if (ldev == NULL) + return; + + close_backing_dev(device, ldev->md_bdev, ldev->md_bdev != ldev->backing_bdev); + close_backing_dev(device, ldev->backing_bdev, true); + + kfree(ldev->disk_conf); + kfree(ldev); +} + int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context adm_ctx; @@ -1462,7 +1581,6 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) sector_t min_md_device_sectors; struct drbd_backing_dev *nbc = NULL; /* new_backing_conf */ struct disk_conf *new_disk_conf = NULL; - struct block_device *bdev; struct lru_cache *resync_lru = NULL; struct fifo_buffer *new_plan = NULL; union drbd_state ns, os; @@ -1478,7 +1596,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) device = adm_ctx.device; mutex_lock(&adm_ctx.resource->adm_mutex); peer_device = first_peer_device(device); - connection = peer_device ? peer_device->connection : NULL; + connection = peer_device->connection; conn_reconfig_start(connection); /* if you want to reconfigure, please tear down first */ @@ -1539,12 +1657,6 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) goto fail; } - write_lock_irq(&global_state_lock); - retcode = drbd_resync_after_valid(device, new_disk_conf->resync_after); - write_unlock_irq(&global_state_lock); - if (retcode != NO_ERROR) - goto fail; - rcu_read_lock(); nc = rcu_dereference(connection->net_conf); if (nc) { @@ -1556,35 +1668,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) } rcu_read_unlock(); - bdev = blkdev_get_by_path(new_disk_conf->backing_dev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, device); - if (IS_ERR(bdev)) { - drbd_err(device, "open(\"%s\") failed with %ld\n", new_disk_conf->backing_dev, - PTR_ERR(bdev)); - retcode = ERR_OPEN_DISK; - goto fail; - } - nbc->backing_bdev = bdev; - - /* - * meta_dev_idx >= 0: external fixed size, possibly multiple - * drbd sharing one meta device. TODO in that case, paranoia - * check that [md_bdev, meta_dev_idx] is not yet used by some - * other drbd minor! (if you use drbd.conf + drbdadm, that - * should check it for you already; but if you don't, or - * someone fooled it, we need to double check here) - */ - bdev = blkdev_get_by_path(new_disk_conf->meta_dev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, - (new_disk_conf->meta_dev_idx < 0) ? - (void *)device : (void *)drbd_m_holder); - if (IS_ERR(bdev)) { - drbd_err(device, "open(\"%s\") failed with %ld\n", new_disk_conf->meta_dev, - PTR_ERR(bdev)); - retcode = ERR_OPEN_MD_DISK; + retcode = open_backing_devices(device, new_disk_conf, nbc); + if (retcode != NO_ERROR) goto fail; - } - nbc->md_bdev = bdev; if ((nbc->backing_bdev == nbc->md_bdev) != (new_disk_conf->meta_dev_idx == DRBD_MD_INDEX_INTERNAL || @@ -1707,6 +1793,13 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) goto force_diskless_dec; } + lock_all_resources(); + retcode = drbd_resync_after_valid(device, new_disk_conf->resync_after); + if (retcode != NO_ERROR) { + unlock_all_resources(); + goto force_diskless_dec; + } + /* Reset the "barriers don't work" bits here, then force meta data to * be written, to ensure we determine if barriers are supported. */ if (new_disk_conf->md_flushes) @@ -1727,7 +1820,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) new_disk_conf = NULL; new_plan = NULL; - drbd_bump_write_ordering(device->resource, device->ldev, WO_bdev_flush); + drbd_resync_after_changed(device); + drbd_bump_write_ordering(device->resource, device->ldev, WO_BDEV_FLUSH); + unlock_all_resources(); if (drbd_md_test_flag(device->ldev, MDF_CRASHED_PRIMARY)) set_bit(CRASHED_PRIMARY, &device->flags); @@ -1875,12 +1970,8 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) fail: conn_reconfig_done(connection); if (nbc) { - if (nbc->backing_bdev) - blkdev_put(nbc->backing_bdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL); - if (nbc->md_bdev) - blkdev_put(nbc->md_bdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL); + close_backing_dev(device, nbc->md_bdev, nbc->md_bdev != nbc->backing_bdev); + close_backing_dev(device, nbc->backing_bdev, true); kfree(nbc); } kfree(new_disk_conf); @@ -1895,6 +1986,7 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) static int adm_detach(struct drbd_device *device, int force) { enum drbd_state_rv retcode; + void *buffer; int ret; if (force) { @@ -1905,13 +1997,16 @@ static int adm_detach(struct drbd_device *device, int force) } drbd_suspend_io(device); /* so no-one is stuck in drbd_al_begin_io */ - drbd_md_get_buffer(device, __func__); /* make sure there is no in-flight meta-data IO */ - retcode = drbd_request_state(device, NS(disk, D_FAILED)); - drbd_md_put_buffer(device); + buffer = drbd_md_get_buffer(device, __func__); /* make sure there is no in-flight meta-data IO */ + if (buffer) { + retcode = drbd_request_state(device, NS(disk, D_FAILED)); + drbd_md_put_buffer(device); + } else /* already <= D_FAILED */ + retcode = SS_NOTHING_TO_DO; /* D_FAILED will transition to DISKLESS. */ + drbd_resume_io(device); ret = wait_event_interruptible(device->misc_wait, device->state.disk != D_FAILED); - drbd_resume_io(device); if ((int)retcode == (int)SS_IS_DISKLESS) retcode = SS_NOTHING_TO_DO; if (ret) @@ -2245,8 +2340,31 @@ int drbd_adm_net_opts(struct sk_buff *skb, struct genl_info *info) return 0; } +static void connection_to_info(struct connection_info *info, + struct drbd_connection *connection) +{ + info->conn_connection_state = connection->cstate; + info->conn_role = conn_highest_peer(connection); +} + +static void peer_device_to_info(struct peer_device_info *info, + struct drbd_peer_device *peer_device) +{ + struct drbd_device *device = peer_device->device; + + info->peer_repl_state = + max_t(enum drbd_conns, C_WF_REPORT_PARAMS, device->state.conn); + info->peer_disk_state = device->state.pdsk; + info->peer_resync_susp_user = device->state.user_isp; + info->peer_resync_susp_peer = device->state.peer_isp; + info->peer_resync_susp_dependency = device->state.aftr_isp; +} + int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) { + struct connection_info connection_info; + enum drbd_notification_type flags; + unsigned int peer_devices = 0; struct drbd_config_context adm_ctx; struct drbd_peer_device *peer_device; struct net_conf *old_net_conf, *new_net_conf = NULL; @@ -2347,6 +2465,22 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info) connection->peer_addr_len = nla_len(adm_ctx.peer_addr); memcpy(&connection->peer_addr, nla_data(adm_ctx.peer_addr), connection->peer_addr_len); + idr_for_each_entry(&connection->peer_devices, peer_device, i) { + peer_devices++; + } + + connection_to_info(&connection_info, connection); + flags = (peer_devices--) ? NOTIFY_CONTINUES : 0; + mutex_lock(¬ification_mutex); + notify_connection_state(NULL, 0, connection, &connection_info, NOTIFY_CREATE | flags); + idr_for_each_entry(&connection->peer_devices, peer_device, i) { + struct peer_device_info peer_device_info; + + peer_device_to_info(&peer_device_info, peer_device); + flags = (peer_devices--) ? NOTIFY_CONTINUES : 0; + notify_peer_device_state(NULL, 0, peer_device, &peer_device_info, NOTIFY_CREATE | flags); + } + mutex_unlock(¬ification_mutex); mutex_unlock(&adm_ctx.resource->conf_update); rcu_read_lock(); @@ -2428,6 +2562,8 @@ static enum drbd_state_rv conn_try_disconnect(struct drbd_connection *connection drbd_err(connection, "unexpected rv2=%d in conn_try_disconnect()\n", rv2); + /* Unlike in DRBD 9, the state engine has generated + * NOTIFY_DESTROY events before clearing connection->net_conf. */ } return rv; } @@ -2585,6 +2721,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info) mutex_unlock(&device->resource->conf_update); synchronize_rcu(); kfree(old_disk_conf); + new_disk_conf = NULL; } ddsf = (rs.resize_force ? DDSF_FORCED : 0) | (rs.no_resync ? DDSF_NO_RESYNC : 0); @@ -2618,6 +2755,7 @@ int drbd_adm_resize(struct sk_buff *skb, struct genl_info *info) fail_ldev: put_ldev(device); + kfree(new_disk_conf); goto fail; } @@ -2855,7 +2993,30 @@ int drbd_adm_resume_io(struct sk_buff *skb, struct genl_info *info) mutex_lock(&adm_ctx.resource->adm_mutex); device = adm_ctx.device; if (test_bit(NEW_CUR_UUID, &device->flags)) { - drbd_uuid_new_current(device); + if (get_ldev_if_state(device, D_ATTACHING)) { + drbd_uuid_new_current(device); + put_ldev(device); + } else { + /* This is effectively a multi-stage "forced down". + * The NEW_CUR_UUID bit is supposedly only set, if we + * lost the replication connection, and are configured + * to freeze IO and wait for some fence-peer handler. + * So we still don't have a replication connection. + * And now we don't have a local disk either. After + * resume, we will fail all pending and new IO, because + * we don't have any data anymore. Which means we will + * eventually be able to terminate all users of this + * device, and then take it down. By bumping the + * "effective" data uuid, we make sure that you really + * need to tear down before you reconfigure, we will + * the refuse to re-connect or re-attach (because no + * matching real data uuid exists). + */ + u64 val; + get_random_bytes(&val, sizeof(u64)); + drbd_set_ed_uuid(device, val); + drbd_warn(device, "Resumed without access to data; please tear down before attempting to re-configure.\n"); + } clear_bit(NEW_CUR_UUID, &device->flags); } drbd_suspend_io(device); @@ -2910,6 +3071,486 @@ nla_put_failure: } /* + * The generic netlink dump callbacks are called outside the genl_lock(), so + * they cannot use the simple attribute parsing code which uses global + * attribute tables. + */ +static struct nlattr *find_cfg_context_attr(const struct nlmsghdr *nlh, int attr) +{ + const unsigned hdrlen = GENL_HDRLEN + GENL_MAGIC_FAMILY_HDRSZ; + const int maxtype = ARRAY_SIZE(drbd_cfg_context_nl_policy) - 1; + struct nlattr *nla; + + nla = nla_find(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), + DRBD_NLA_CFG_CONTEXT); + if (!nla) + return NULL; + return drbd_nla_find_nested(maxtype, nla, __nla_type(attr)); +} + +static void resource_to_info(struct resource_info *, struct drbd_resource *); + +int drbd_adm_dump_resources(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct drbd_genlmsghdr *dh; + struct drbd_resource *resource; + struct resource_info resource_info; + struct resource_statistics resource_statistics; + int err; + + rcu_read_lock(); + if (cb->args[0]) { + for_each_resource_rcu(resource, &drbd_resources) + if (resource == (struct drbd_resource *)cb->args[0]) + goto found_resource; + err = 0; /* resource was probably deleted */ + goto out; + } + resource = list_entry(&drbd_resources, + struct drbd_resource, resources); + +found_resource: + list_for_each_entry_continue_rcu(resource, &drbd_resources, resources) { + goto put_result; + } + err = 0; + goto out; + +put_result: + dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &drbd_genl_family, + NLM_F_MULTI, DRBD_ADM_GET_RESOURCES); + err = -ENOMEM; + if (!dh) + goto out; + dh->minor = -1U; + dh->ret_code = NO_ERROR; + err = nla_put_drbd_cfg_context(skb, resource, NULL, NULL); + if (err) + goto out; + err = res_opts_to_skb(skb, &resource->res_opts, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + resource_to_info(&resource_info, resource); + err = resource_info_to_skb(skb, &resource_info, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + resource_statistics.res_stat_write_ordering = resource->write_ordering; + err = resource_statistics_to_skb(skb, &resource_statistics, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + cb->args[0] = (long)resource; + genlmsg_end(skb, dh); + err = 0; + +out: + rcu_read_unlock(); + if (err) + return err; + return skb->len; +} + +static void device_to_statistics(struct device_statistics *s, + struct drbd_device *device) +{ + memset(s, 0, sizeof(*s)); + s->dev_upper_blocked = !may_inc_ap_bio(device); + if (get_ldev(device)) { + struct drbd_md *md = &device->ldev->md; + u64 *history_uuids = (u64 *)s->history_uuids; + struct request_queue *q; + int n; + + spin_lock_irq(&md->uuid_lock); + s->dev_current_uuid = md->uuid[UI_CURRENT]; + BUILD_BUG_ON(sizeof(s->history_uuids) < UI_HISTORY_END - UI_HISTORY_START + 1); + for (n = 0; n < UI_HISTORY_END - UI_HISTORY_START + 1; n++) + history_uuids[n] = md->uuid[UI_HISTORY_START + n]; + for (; n < HISTORY_UUIDS; n++) + history_uuids[n] = 0; + s->history_uuids_len = HISTORY_UUIDS; + spin_unlock_irq(&md->uuid_lock); + + s->dev_disk_flags = md->flags; + q = bdev_get_queue(device->ldev->backing_bdev); + s->dev_lower_blocked = + bdi_congested(&q->backing_dev_info, + (1 << WB_async_congested) | + (1 << WB_sync_congested)); + put_ldev(device); + } + s->dev_size = drbd_get_capacity(device->this_bdev); + s->dev_read = device->read_cnt; + s->dev_write = device->writ_cnt; + s->dev_al_writes = device->al_writ_cnt; + s->dev_bm_writes = device->bm_writ_cnt; + s->dev_upper_pending = atomic_read(&device->ap_bio_cnt); + s->dev_lower_pending = atomic_read(&device->local_cnt); + s->dev_al_suspended = test_bit(AL_SUSPENDED, &device->flags); + s->dev_exposed_data_uuid = device->ed_uuid; +} + +static int put_resource_in_arg0(struct netlink_callback *cb, int holder_nr) +{ + if (cb->args[0]) { + struct drbd_resource *resource = + (struct drbd_resource *)cb->args[0]; + kref_put(&resource->kref, drbd_destroy_resource); + } + + return 0; +} + +int drbd_adm_dump_devices_done(struct netlink_callback *cb) { + return put_resource_in_arg0(cb, 7); +} + +static void device_to_info(struct device_info *, struct drbd_device *); + +int drbd_adm_dump_devices(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nlattr *resource_filter; + struct drbd_resource *resource; + struct drbd_device *uninitialized_var(device); + int minor, err, retcode; + struct drbd_genlmsghdr *dh; + struct device_info device_info; + struct device_statistics device_statistics; + struct idr *idr_to_search; + + resource = (struct drbd_resource *)cb->args[0]; + if (!cb->args[0] && !cb->args[1]) { + resource_filter = find_cfg_context_attr(cb->nlh, T_ctx_resource_name); + if (resource_filter) { + retcode = ERR_RES_NOT_KNOWN; + resource = drbd_find_resource(nla_data(resource_filter)); + if (!resource) + goto put_result; + cb->args[0] = (long)resource; + } + } + + rcu_read_lock(); + minor = cb->args[1]; + idr_to_search = resource ? &resource->devices : &drbd_devices; + device = idr_get_next(idr_to_search, &minor); + if (!device) { + err = 0; + goto out; + } + idr_for_each_entry_continue(idr_to_search, device, minor) { + retcode = NO_ERROR; + goto put_result; /* only one iteration */ + } + err = 0; + goto out; /* no more devices */ + +put_result: + dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &drbd_genl_family, + NLM_F_MULTI, DRBD_ADM_GET_DEVICES); + err = -ENOMEM; + if (!dh) + goto out; + dh->ret_code = retcode; + dh->minor = -1U; + if (retcode == NO_ERROR) { + dh->minor = device->minor; + err = nla_put_drbd_cfg_context(skb, device->resource, NULL, device); + if (err) + goto out; + if (get_ldev(device)) { + struct disk_conf *disk_conf = + rcu_dereference(device->ldev->disk_conf); + + err = disk_conf_to_skb(skb, disk_conf, !capable(CAP_SYS_ADMIN)); + put_ldev(device); + if (err) + goto out; + } + device_to_info(&device_info, device); + err = device_info_to_skb(skb, &device_info, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + + device_to_statistics(&device_statistics, device); + err = device_statistics_to_skb(skb, &device_statistics, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + cb->args[1] = minor + 1; + } + genlmsg_end(skb, dh); + err = 0; + +out: + rcu_read_unlock(); + if (err) + return err; + return skb->len; +} + +int drbd_adm_dump_connections_done(struct netlink_callback *cb) +{ + return put_resource_in_arg0(cb, 6); +} + +enum { SINGLE_RESOURCE, ITERATE_RESOURCES }; + +int drbd_adm_dump_connections(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nlattr *resource_filter; + struct drbd_resource *resource = NULL, *next_resource; + struct drbd_connection *uninitialized_var(connection); + int err = 0, retcode; + struct drbd_genlmsghdr *dh; + struct connection_info connection_info; + struct connection_statistics connection_statistics; + + rcu_read_lock(); + resource = (struct drbd_resource *)cb->args[0]; + if (!cb->args[0]) { + resource_filter = find_cfg_context_attr(cb->nlh, T_ctx_resource_name); + if (resource_filter) { + retcode = ERR_RES_NOT_KNOWN; + resource = drbd_find_resource(nla_data(resource_filter)); + if (!resource) + goto put_result; + cb->args[0] = (long)resource; + cb->args[1] = SINGLE_RESOURCE; + } + } + if (!resource) { + if (list_empty(&drbd_resources)) + goto out; + resource = list_first_entry(&drbd_resources, struct drbd_resource, resources); + kref_get(&resource->kref); + cb->args[0] = (long)resource; + cb->args[1] = ITERATE_RESOURCES; + } + + next_resource: + rcu_read_unlock(); + mutex_lock(&resource->conf_update); + rcu_read_lock(); + if (cb->args[2]) { + for_each_connection_rcu(connection, resource) + if (connection == (struct drbd_connection *)cb->args[2]) + goto found_connection; + /* connection was probably deleted */ + goto no_more_connections; + } + connection = list_entry(&resource->connections, struct drbd_connection, connections); + +found_connection: + list_for_each_entry_continue_rcu(connection, &resource->connections, connections) { + if (!has_net_conf(connection)) + continue; + retcode = NO_ERROR; + goto put_result; /* only one iteration */ + } + +no_more_connections: + if (cb->args[1] == ITERATE_RESOURCES) { + for_each_resource_rcu(next_resource, &drbd_resources) { + if (next_resource == resource) + goto found_resource; + } + /* resource was probably deleted */ + } + goto out; + +found_resource: + list_for_each_entry_continue_rcu(next_resource, &drbd_resources, resources) { + mutex_unlock(&resource->conf_update); + kref_put(&resource->kref, drbd_destroy_resource); + resource = next_resource; + kref_get(&resource->kref); + cb->args[0] = (long)resource; + cb->args[2] = 0; + goto next_resource; + } + goto out; /* no more resources */ + +put_result: + dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &drbd_genl_family, + NLM_F_MULTI, DRBD_ADM_GET_CONNECTIONS); + err = -ENOMEM; + if (!dh) + goto out; + dh->ret_code = retcode; + dh->minor = -1U; + if (retcode == NO_ERROR) { + struct net_conf *net_conf; + + err = nla_put_drbd_cfg_context(skb, resource, connection, NULL); + if (err) + goto out; + net_conf = rcu_dereference(connection->net_conf); + if (net_conf) { + err = net_conf_to_skb(skb, net_conf, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + } + connection_to_info(&connection_info, connection); + err = connection_info_to_skb(skb, &connection_info, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + connection_statistics.conn_congested = test_bit(NET_CONGESTED, &connection->flags); + err = connection_statistics_to_skb(skb, &connection_statistics, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + cb->args[2] = (long)connection; + } + genlmsg_end(skb, dh); + err = 0; + +out: + rcu_read_unlock(); + if (resource) + mutex_unlock(&resource->conf_update); + if (err) + return err; + return skb->len; +} + +enum mdf_peer_flag { + MDF_PEER_CONNECTED = 1 << 0, + MDF_PEER_OUTDATED = 1 << 1, + MDF_PEER_FENCING = 1 << 2, + MDF_PEER_FULL_SYNC = 1 << 3, +}; + +static void peer_device_to_statistics(struct peer_device_statistics *s, + struct drbd_peer_device *peer_device) +{ + struct drbd_device *device = peer_device->device; + + memset(s, 0, sizeof(*s)); + s->peer_dev_received = device->recv_cnt; + s->peer_dev_sent = device->send_cnt; + s->peer_dev_pending = atomic_read(&device->ap_pending_cnt) + + atomic_read(&device->rs_pending_cnt); + s->peer_dev_unacked = atomic_read(&device->unacked_cnt); + s->peer_dev_out_of_sync = drbd_bm_total_weight(device) << (BM_BLOCK_SHIFT - 9); + s->peer_dev_resync_failed = device->rs_failed << (BM_BLOCK_SHIFT - 9); + if (get_ldev(device)) { + struct drbd_md *md = &device->ldev->md; + + spin_lock_irq(&md->uuid_lock); + s->peer_dev_bitmap_uuid = md->uuid[UI_BITMAP]; + spin_unlock_irq(&md->uuid_lock); + s->peer_dev_flags = + (drbd_md_test_flag(device->ldev, MDF_CONNECTED_IND) ? + MDF_PEER_CONNECTED : 0) + + (drbd_md_test_flag(device->ldev, MDF_CONSISTENT) && + !drbd_md_test_flag(device->ldev, MDF_WAS_UP_TO_DATE) ? + MDF_PEER_OUTDATED : 0) + + /* FIXME: MDF_PEER_FENCING? */ + (drbd_md_test_flag(device->ldev, MDF_FULL_SYNC) ? + MDF_PEER_FULL_SYNC : 0); + put_ldev(device); + } +} + +int drbd_adm_dump_peer_devices_done(struct netlink_callback *cb) +{ + return put_resource_in_arg0(cb, 9); +} + +int drbd_adm_dump_peer_devices(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nlattr *resource_filter; + struct drbd_resource *resource; + struct drbd_device *uninitialized_var(device); + struct drbd_peer_device *peer_device = NULL; + int minor, err, retcode; + struct drbd_genlmsghdr *dh; + struct idr *idr_to_search; + + resource = (struct drbd_resource *)cb->args[0]; + if (!cb->args[0] && !cb->args[1]) { + resource_filter = find_cfg_context_attr(cb->nlh, T_ctx_resource_name); + if (resource_filter) { + retcode = ERR_RES_NOT_KNOWN; + resource = drbd_find_resource(nla_data(resource_filter)); + if (!resource) + goto put_result; + } + cb->args[0] = (long)resource; + } + + rcu_read_lock(); + minor = cb->args[1]; + idr_to_search = resource ? &resource->devices : &drbd_devices; + device = idr_find(idr_to_search, minor); + if (!device) { +next_device: + minor++; + cb->args[2] = 0; + device = idr_get_next(idr_to_search, &minor); + if (!device) { + err = 0; + goto out; + } + } + if (cb->args[2]) { + for_each_peer_device(peer_device, device) + if (peer_device == (struct drbd_peer_device *)cb->args[2]) + goto found_peer_device; + /* peer device was probably deleted */ + goto next_device; + } + /* Make peer_device point to the list head (not the first entry). */ + peer_device = list_entry(&device->peer_devices, struct drbd_peer_device, peer_devices); + +found_peer_device: + list_for_each_entry_continue_rcu(peer_device, &device->peer_devices, peer_devices) { + if (!has_net_conf(peer_device->connection)) + continue; + retcode = NO_ERROR; + goto put_result; /* only one iteration */ + } + goto next_device; + +put_result: + dh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &drbd_genl_family, + NLM_F_MULTI, DRBD_ADM_GET_PEER_DEVICES); + err = -ENOMEM; + if (!dh) + goto out; + dh->ret_code = retcode; + dh->minor = -1U; + if (retcode == NO_ERROR) { + struct peer_device_info peer_device_info; + struct peer_device_statistics peer_device_statistics; + + dh->minor = minor; + err = nla_put_drbd_cfg_context(skb, device->resource, peer_device->connection, device); + if (err) + goto out; + peer_device_to_info(&peer_device_info, peer_device); + err = peer_device_info_to_skb(skb, &peer_device_info, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + peer_device_to_statistics(&peer_device_statistics, peer_device); + err = peer_device_statistics_to_skb(skb, &peer_device_statistics, !capable(CAP_SYS_ADMIN)); + if (err) + goto out; + cb->args[1] = minor; + cb->args[2] = (long)peer_device; + } + genlmsg_end(skb, dh); + err = 0; + +out: + rcu_read_unlock(); + if (err) + return err; + return skb->len; +} +/* * Return the connection of @resource if @resource has exactly one connection. */ static struct drbd_connection *the_only_connection(struct drbd_resource *resource) @@ -3414,8 +4055,18 @@ drbd_check_resource_name(struct drbd_config_context *adm_ctx) return NO_ERROR; } +static void resource_to_info(struct resource_info *info, + struct drbd_resource *resource) +{ + info->res_role = conn_highest_role(first_connection(resource)); + info->res_susp = resource->susp; + info->res_susp_nod = resource->susp_nod; + info->res_susp_fen = resource->susp_fen; +} + int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info) { + struct drbd_connection *connection; struct drbd_config_context adm_ctx; enum drbd_ret_code retcode; struct res_opts res_opts; @@ -3449,13 +4100,33 @@ int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info) } /* not yet safe for genl_family.parallel_ops */ - if (!conn_create(adm_ctx.resource_name, &res_opts)) + mutex_lock(&resources_mutex); + connection = conn_create(adm_ctx.resource_name, &res_opts); + mutex_unlock(&resources_mutex); + + if (connection) { + struct resource_info resource_info; + + mutex_lock(¬ification_mutex); + resource_to_info(&resource_info, connection->resource); + notify_resource_state(NULL, 0, connection->resource, + &resource_info, NOTIFY_CREATE); + mutex_unlock(¬ification_mutex); + } else retcode = ERR_NOMEM; + out: drbd_adm_finish(&adm_ctx, info, retcode); return 0; } +static void device_to_info(struct device_info *info, + struct drbd_device *device) +{ + info->dev_disk_state = device->state.disk; +} + + int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context adm_ctx; @@ -3490,6 +4161,36 @@ int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info) mutex_lock(&adm_ctx.resource->adm_mutex); retcode = drbd_create_device(&adm_ctx, dh->minor); + if (retcode == NO_ERROR) { + struct drbd_device *device; + struct drbd_peer_device *peer_device; + struct device_info info; + unsigned int peer_devices = 0; + enum drbd_notification_type flags; + + device = minor_to_device(dh->minor); + for_each_peer_device(peer_device, device) { + if (!has_net_conf(peer_device->connection)) + continue; + peer_devices++; + } + + device_to_info(&info, device); + mutex_lock(¬ification_mutex); + flags = (peer_devices--) ? NOTIFY_CONTINUES : 0; + notify_device_state(NULL, 0, device, &info, NOTIFY_CREATE | flags); + for_each_peer_device(peer_device, device) { + struct peer_device_info peer_device_info; + + if (!has_net_conf(peer_device->connection)) + continue; + peer_device_to_info(&peer_device_info, peer_device); + flags = (peer_devices--) ? NOTIFY_CONTINUES : 0; + notify_peer_device_state(NULL, 0, peer_device, &peer_device_info, + NOTIFY_CREATE | flags); + } + mutex_unlock(¬ification_mutex); + } mutex_unlock(&adm_ctx.resource->adm_mutex); out: drbd_adm_finish(&adm_ctx, info, retcode); @@ -3498,13 +4199,35 @@ out: static enum drbd_ret_code adm_del_minor(struct drbd_device *device) { + struct drbd_peer_device *peer_device; + if (device->state.disk == D_DISKLESS && /* no need to be device->state.conn == C_STANDALONE && * we may want to delete a minor from a live replication group. */ device->state.role == R_SECONDARY) { + struct drbd_connection *connection = + first_connection(device->resource); + _drbd_request_state(device, NS(conn, C_WF_REPORT_PARAMS), CS_VERBOSE + CS_WAIT_COMPLETE); + + /* If the state engine hasn't stopped the sender thread yet, we + * need to flush the sender work queue before generating the + * DESTROY events here. */ + if (get_t_state(&connection->worker) == RUNNING) + drbd_flush_workqueue(&connection->sender_work); + + mutex_lock(¬ification_mutex); + for_each_peer_device(peer_device, device) { + if (!has_net_conf(peer_device->connection)) + continue; + notify_peer_device_state(NULL, 0, peer_device, NULL, + NOTIFY_DESTROY | NOTIFY_CONTINUES); + } + notify_device_state(NULL, 0, device, NULL, NOTIFY_DESTROY); + mutex_unlock(¬ification_mutex); + drbd_delete_device(device); return NO_ERROR; } else @@ -3541,7 +4264,16 @@ static int adm_del_resource(struct drbd_resource *resource) if (!idr_is_empty(&resource->devices)) return ERR_RES_IN_USE; + /* The state engine has stopped the sender thread, so we don't + * need to flush the sender work queue before generating the + * DESTROY event here. */ + mutex_lock(¬ification_mutex); + notify_resource_state(NULL, 0, resource, NULL, NOTIFY_DESTROY); + mutex_unlock(¬ification_mutex); + + mutex_lock(&resources_mutex); list_del_rcu(&resource->resources); + mutex_unlock(&resources_mutex); /* Make sure all threads have actually stopped: state handling only * does drbd_thread_stop_nowait(). */ list_for_each_entry(connection, &resource->connections, connections) @@ -3637,7 +4369,6 @@ finish: void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib) { - static atomic_t drbd_genl_seq = ATOMIC_INIT(2); /* two. */ struct sk_buff *msg; struct drbd_genlmsghdr *d_out; unsigned seq; @@ -3658,7 +4389,7 @@ void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib) if (nla_put_status_info(msg, device, sib)) goto nla_put_failure; genlmsg_end(msg, d_out); - err = drbd_genl_multicast_events(msg, 0); + err = drbd_genl_multicast_events(msg, GFP_NOWAIT); /* msg has been consumed or freed in netlink_broadcast() */ if (err && err != -ESRCH) goto failed; @@ -3672,3 +4403,405 @@ failed: "Event seq:%u sib_reason:%u\n", err, seq, sib->sib_reason); } + +static int nla_put_notification_header(struct sk_buff *msg, + enum drbd_notification_type type) +{ + struct drbd_notification_header nh = { + .nh_type = type, + }; + + return drbd_notification_header_to_skb(msg, &nh, true); +} + +void notify_resource_state(struct sk_buff *skb, + unsigned int seq, + struct drbd_resource *resource, + struct resource_info *resource_info, + enum drbd_notification_type type) +{ + struct resource_statistics resource_statistics; + struct drbd_genlmsghdr *dh; + bool multicast = false; + int err; + + if (!skb) { + seq = atomic_inc_return(¬ify_genl_seq); + skb = genlmsg_new(NLMSG_GOODSIZE, GFP_NOIO); + err = -ENOMEM; + if (!skb) + goto failed; + multicast = true; + } + + err = -EMSGSIZE; + dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_RESOURCE_STATE); + if (!dh) + goto nla_put_failure; + dh->minor = -1U; + dh->ret_code = NO_ERROR; + if (nla_put_drbd_cfg_context(skb, resource, NULL, NULL) || + nla_put_notification_header(skb, type) || + ((type & ~NOTIFY_FLAGS) != NOTIFY_DESTROY && + resource_info_to_skb(skb, resource_info, true))) + goto nla_put_failure; + resource_statistics.res_stat_write_ordering = resource->write_ordering; + err = resource_statistics_to_skb(skb, &resource_statistics, !capable(CAP_SYS_ADMIN)); + if (err) + goto nla_put_failure; + genlmsg_end(skb, dh); + if (multicast) { + err = drbd_genl_multicast_events(skb, GFP_NOWAIT); + /* skb has been consumed or freed in netlink_broadcast() */ + if (err && err != -ESRCH) + goto failed; + } + return; + +nla_put_failure: + nlmsg_free(skb); +failed: + drbd_err(resource, "Error %d while broadcasting event. Event seq:%u\n", + err, seq); +} + +void notify_device_state(struct sk_buff *skb, + unsigned int seq, + struct drbd_device *device, + struct device_info *device_info, + enum drbd_notification_type type) +{ + struct device_statistics device_statistics; + struct drbd_genlmsghdr *dh; + bool multicast = false; + int err; + + if (!skb) { + seq = atomic_inc_return(¬ify_genl_seq); + skb = genlmsg_new(NLMSG_GOODSIZE, GFP_NOIO); + err = -ENOMEM; + if (!skb) + goto failed; + multicast = true; + } + + err = -EMSGSIZE; + dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_DEVICE_STATE); + if (!dh) + goto nla_put_failure; + dh->minor = device->minor; + dh->ret_code = NO_ERROR; + if (nla_put_drbd_cfg_context(skb, device->resource, NULL, device) || + nla_put_notification_header(skb, type) || + ((type & ~NOTIFY_FLAGS) != NOTIFY_DESTROY && + device_info_to_skb(skb, device_info, true))) + goto nla_put_failure; + device_to_statistics(&device_statistics, device); + device_statistics_to_skb(skb, &device_statistics, !capable(CAP_SYS_ADMIN)); + genlmsg_end(skb, dh); + if (multicast) { + err = drbd_genl_multicast_events(skb, GFP_NOWAIT); + /* skb has been consumed or freed in netlink_broadcast() */ + if (err && err != -ESRCH) + goto failed; + } + return; + +nla_put_failure: + nlmsg_free(skb); +failed: + drbd_err(device, "Error %d while broadcasting event. Event seq:%u\n", + err, seq); +} + +void notify_connection_state(struct sk_buff *skb, + unsigned int seq, + struct drbd_connection *connection, + struct connection_info *connection_info, + enum drbd_notification_type type) +{ + struct connection_statistics connection_statistics; + struct drbd_genlmsghdr *dh; + bool multicast = false; + int err; + + if (!skb) { + seq = atomic_inc_return(¬ify_genl_seq); + skb = genlmsg_new(NLMSG_GOODSIZE, GFP_NOIO); + err = -ENOMEM; + if (!skb) + goto failed; + multicast = true; + } + + err = -EMSGSIZE; + dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_CONNECTION_STATE); + if (!dh) + goto nla_put_failure; + dh->minor = -1U; + dh->ret_code = NO_ERROR; + if (nla_put_drbd_cfg_context(skb, connection->resource, connection, NULL) || + nla_put_notification_header(skb, type) || + ((type & ~NOTIFY_FLAGS) != NOTIFY_DESTROY && + connection_info_to_skb(skb, connection_info, true))) + goto nla_put_failure; + connection_statistics.conn_congested = test_bit(NET_CONGESTED, &connection->flags); + connection_statistics_to_skb(skb, &connection_statistics, !capable(CAP_SYS_ADMIN)); + genlmsg_end(skb, dh); + if (multicast) { + err = drbd_genl_multicast_events(skb, GFP_NOWAIT); + /* skb has been consumed or freed in netlink_broadcast() */ + if (err && err != -ESRCH) + goto failed; + } + return; + +nla_put_failure: + nlmsg_free(skb); +failed: + drbd_err(connection, "Error %d while broadcasting event. Event seq:%u\n", + err, seq); +} + +void notify_peer_device_state(struct sk_buff *skb, + unsigned int seq, + struct drbd_peer_device *peer_device, + struct peer_device_info *peer_device_info, + enum drbd_notification_type type) +{ + struct peer_device_statistics peer_device_statistics; + struct drbd_resource *resource = peer_device->device->resource; + struct drbd_genlmsghdr *dh; + bool multicast = false; + int err; + + if (!skb) { + seq = atomic_inc_return(¬ify_genl_seq); + skb = genlmsg_new(NLMSG_GOODSIZE, GFP_NOIO); + err = -ENOMEM; + if (!skb) + goto failed; + multicast = true; + } + + err = -EMSGSIZE; + dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_PEER_DEVICE_STATE); + if (!dh) + goto nla_put_failure; + dh->minor = -1U; + dh->ret_code = NO_ERROR; + if (nla_put_drbd_cfg_context(skb, resource, peer_device->connection, peer_device->device) || + nla_put_notification_header(skb, type) || + ((type & ~NOTIFY_FLAGS) != NOTIFY_DESTROY && + peer_device_info_to_skb(skb, peer_device_info, true))) + goto nla_put_failure; + peer_device_to_statistics(&peer_device_statistics, peer_device); + peer_device_statistics_to_skb(skb, &peer_device_statistics, !capable(CAP_SYS_ADMIN)); + genlmsg_end(skb, dh); + if (multicast) { + err = drbd_genl_multicast_events(skb, GFP_NOWAIT); + /* skb has been consumed or freed in netlink_broadcast() */ + if (err && err != -ESRCH) + goto failed; + } + return; + +nla_put_failure: + nlmsg_free(skb); +failed: + drbd_err(peer_device, "Error %d while broadcasting event. Event seq:%u\n", + err, seq); +} + +void notify_helper(enum drbd_notification_type type, + struct drbd_device *device, struct drbd_connection *connection, + const char *name, int status) +{ + struct drbd_resource *resource = device ? device->resource : connection->resource; + struct drbd_helper_info helper_info; + unsigned int seq = atomic_inc_return(¬ify_genl_seq); + struct sk_buff *skb = NULL; + struct drbd_genlmsghdr *dh; + int err; + + strlcpy(helper_info.helper_name, name, sizeof(helper_info.helper_name)); + helper_info.helper_name_len = min(strlen(name), sizeof(helper_info.helper_name)); + helper_info.helper_status = status; + + skb = genlmsg_new(NLMSG_GOODSIZE, GFP_NOIO); + err = -ENOMEM; + if (!skb) + goto fail; + + err = -EMSGSIZE; + dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_HELPER); + if (!dh) + goto fail; + dh->minor = device ? device->minor : -1; + dh->ret_code = NO_ERROR; + mutex_lock(¬ification_mutex); + if (nla_put_drbd_cfg_context(skb, resource, connection, device) || + nla_put_notification_header(skb, type) || + drbd_helper_info_to_skb(skb, &helper_info, true)) + goto unlock_fail; + genlmsg_end(skb, dh); + err = drbd_genl_multicast_events(skb, GFP_NOWAIT); + skb = NULL; + /* skb has been consumed or freed in netlink_broadcast() */ + if (err && err != -ESRCH) + goto unlock_fail; + mutex_unlock(¬ification_mutex); + return; + +unlock_fail: + mutex_unlock(¬ification_mutex); +fail: + nlmsg_free(skb); + drbd_err(resource, "Error %d while broadcasting event. Event seq:%u\n", + err, seq); +} + +static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) +{ + struct drbd_genlmsghdr *dh; + int err; + + err = -EMSGSIZE; + dh = genlmsg_put(skb, 0, seq, &drbd_genl_family, 0, DRBD_INITIAL_STATE_DONE); + if (!dh) + goto nla_put_failure; + dh->minor = -1U; + dh->ret_code = NO_ERROR; + if (nla_put_notification_header(skb, NOTIFY_EXISTS)) + goto nla_put_failure; + genlmsg_end(skb, dh); + return; + +nla_put_failure: + nlmsg_free(skb); + pr_err("Error %d sending event. Event seq:%u\n", err, seq); +} + +static void free_state_changes(struct list_head *list) +{ + while (!list_empty(list)) { + struct drbd_state_change *state_change = + list_first_entry(list, struct drbd_state_change, list); + list_del(&state_change->list); + forget_state_change(state_change); + } +} + +static unsigned int notifications_for_state_change(struct drbd_state_change *state_change) +{ + return 1 + + state_change->n_connections + + state_change->n_devices + + state_change->n_devices * state_change->n_connections; +} + +static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct drbd_state_change *state_change = (struct drbd_state_change *)cb->args[0]; + unsigned int seq = cb->args[2]; + unsigned int n; + enum drbd_notification_type flags = 0; + + /* There is no need for taking notification_mutex here: it doesn't + matter if the initial state events mix with later state chage + events; we can always tell the events apart by the NOTIFY_EXISTS + flag. */ + + cb->args[5]--; + if (cb->args[5] == 1) { + notify_initial_state_done(skb, seq); + goto out; + } + n = cb->args[4]++; + if (cb->args[4] < cb->args[3]) + flags |= NOTIFY_CONTINUES; + if (n < 1) { + notify_resource_state_change(skb, seq, state_change->resource, + NOTIFY_EXISTS | flags); + goto next; + } + n--; + if (n < state_change->n_connections) { + notify_connection_state_change(skb, seq, &state_change->connections[n], + NOTIFY_EXISTS | flags); + goto next; + } + n -= state_change->n_connections; + if (n < state_change->n_devices) { + notify_device_state_change(skb, seq, &state_change->devices[n], + NOTIFY_EXISTS | flags); + goto next; + } + n -= state_change->n_devices; + if (n < state_change->n_devices * state_change->n_connections) { + notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], + NOTIFY_EXISTS | flags); + goto next; + } + +next: + if (cb->args[4] == cb->args[3]) { + struct drbd_state_change *next_state_change = + list_entry(state_change->list.next, + struct drbd_state_change, list); + cb->args[0] = (long)next_state_change; + cb->args[3] = notifications_for_state_change(next_state_change); + cb->args[4] = 0; + } +out: + return skb->len; +} + +int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct drbd_resource *resource; + LIST_HEAD(head); + + if (cb->args[5] >= 1) { + if (cb->args[5] > 1) + return get_initial_state(skb, cb); + if (cb->args[0]) { + struct drbd_state_change *state_change = + (struct drbd_state_change *)cb->args[0]; + + /* connect list to head */ + list_add(&head, &state_change->list); + free_state_changes(&head); + } + return 0; + } + + cb->args[5] = 2; /* number of iterations */ + mutex_lock(&resources_mutex); + for_each_resource(resource, &drbd_resources) { + struct drbd_state_change *state_change; + + state_change = remember_old_state(resource, GFP_KERNEL); + if (!state_change) { + if (!list_empty(&head)) + free_state_changes(&head); + mutex_unlock(&resources_mutex); + return -ENOMEM; + } + copy_old_to_new_state_change(state_change); + list_add_tail(&state_change->list, &head); + cb->args[5] += notifications_for_state_change(state_change); + } + mutex_unlock(&resources_mutex); + + if (!list_empty(&head)) { + struct drbd_state_change *state_change = + list_entry(head.next, struct drbd_state_change, list); + cb->args[0] = (long)state_change; + cb->args[3] = notifications_for_state_change(state_change); + list_del(&head); /* detach list from head */ + } + + cb->args[2] = cb->nlh->nlmsg_seq; + return get_initial_state(skb, cb); +} diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c index 3b10fa6cb..6537b25db 100644 --- a/drivers/block/drbd/drbd_proc.c +++ b/drivers/block/drbd/drbd_proc.c @@ -245,9 +245,9 @@ static int drbd_seq_show(struct seq_file *seq, void *v) char wp; static char write_ordering_chars[] = { - [WO_none] = 'n', - [WO_drain_io] = 'd', - [WO_bdev_flush] = 'f', + [WO_NONE] = 'n', + [WO_DRAIN_IO] = 'd', + [WO_BDEV_FLUSH] = 'f', }; seq_printf(seq, "version: " REL_VERSION " (api:%d/proto:%d-%d)\n%s\n", diff --git a/drivers/block/drbd/drbd_protocol.h b/drivers/block/drbd/drbd_protocol.h index 2da9104a3..ef9245363 100644 --- a/drivers/block/drbd/drbd_protocol.h +++ b/drivers/block/drbd/drbd_protocol.h @@ -23,7 +23,7 @@ enum drbd_packet { P_AUTH_RESPONSE = 0x11, P_STATE_CHG_REQ = 0x12, - /* asender (meta socket */ + /* (meta socket) */ P_PING = 0x13, P_PING_ACK = 0x14, P_RECV_ACK = 0x15, /* Used in protocol B */ diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index b4b5680ac..1957fe860 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -215,7 +215,7 @@ static void reclaim_finished_net_peer_reqs(struct drbd_device *device, } } -static void drbd_kick_lo_and_reclaim_net(struct drbd_device *device) +static void drbd_reclaim_net_peer_reqs(struct drbd_device *device) { LIST_HEAD(reclaimed); struct drbd_peer_request *peer_req, *t; @@ -223,11 +223,30 @@ static void drbd_kick_lo_and_reclaim_net(struct drbd_device *device) spin_lock_irq(&device->resource->req_lock); reclaim_finished_net_peer_reqs(device, &reclaimed); spin_unlock_irq(&device->resource->req_lock); - list_for_each_entry_safe(peer_req, t, &reclaimed, w.list) drbd_free_net_peer_req(device, peer_req); } +static void conn_reclaim_net_peer_reqs(struct drbd_connection *connection) +{ + struct drbd_peer_device *peer_device; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { + struct drbd_device *device = peer_device->device; + if (!atomic_read(&device->pp_in_use_by_net)) + continue; + + kref_get(&device->kref); + rcu_read_unlock(); + drbd_reclaim_net_peer_reqs(device); + kref_put(&device->kref, drbd_destroy_device); + rcu_read_lock(); + } + rcu_read_unlock(); +} + /** * drbd_alloc_pages() - Returns @number pages, retries forever (or until signalled) * @device: DRBD device. @@ -265,10 +284,15 @@ struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int if (atomic_read(&device->pp_in_use) < mxb) page = __drbd_alloc_pages(device, number); + /* Try to keep the fast path fast, but occasionally we need + * to reclaim the pages we lended to the network stack. */ + if (page && atomic_read(&device->pp_in_use_by_net) > 512) + drbd_reclaim_net_peer_reqs(device); + while (page == NULL) { prepare_to_wait(&drbd_pp_wait, &wait, TASK_INTERRUPTIBLE); - drbd_kick_lo_and_reclaim_net(device); + drbd_reclaim_net_peer_reqs(device); if (atomic_read(&device->pp_in_use) < mxb) { page = __drbd_alloc_pages(device, number); @@ -1099,7 +1123,15 @@ randomize: return 0; } - drbd_thread_start(&connection->asender); + drbd_thread_start(&connection->ack_receiver); + /* opencoded create_singlethread_workqueue(), + * to be able to use format string arguments */ + connection->ack_sender = + alloc_ordered_workqueue("drbd_as_%s", WQ_MEM_RECLAIM, connection->resource->name); + if (!connection->ack_sender) { + drbd_err(connection, "Failed to create workqueue ack_sender\n"); + return 0; + } mutex_lock(&connection->resource->conf_update); /* The discard_my_data flag is a single-shot modifier to the next @@ -1178,7 +1210,7 @@ static void drbd_flush(struct drbd_connection *connection) struct drbd_peer_device *peer_device; int vnr; - if (connection->resource->write_ordering >= WO_bdev_flush) { + if (connection->resource->write_ordering >= WO_BDEV_FLUSH) { rcu_read_lock(); idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { struct drbd_device *device = peer_device->device; @@ -1203,7 +1235,7 @@ static void drbd_flush(struct drbd_connection *connection) /* would rather check on EOPNOTSUPP, but that is not reliable. * don't try again for ANY return value != 0 * if (rv == -EOPNOTSUPP) */ - drbd_bump_write_ordering(connection->resource, NULL, WO_drain_io); + drbd_bump_write_ordering(connection->resource, NULL, WO_DRAIN_IO); } put_ldev(device); kref_put(&device->kref, drbd_destroy_device); @@ -1299,10 +1331,10 @@ max_allowed_wo(struct drbd_backing_dev *bdev, enum write_ordering_e wo) dc = rcu_dereference(bdev->disk_conf); - if (wo == WO_bdev_flush && !dc->disk_flushes) - wo = WO_drain_io; - if (wo == WO_drain_io && !dc->disk_drain) - wo = WO_none; + if (wo == WO_BDEV_FLUSH && !dc->disk_flushes) + wo = WO_DRAIN_IO; + if (wo == WO_DRAIN_IO && !dc->disk_drain) + wo = WO_NONE; return wo; } @@ -1319,13 +1351,13 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin enum write_ordering_e pwo; int vnr; static char *write_ordering_str[] = { - [WO_none] = "none", - [WO_drain_io] = "drain", - [WO_bdev_flush] = "flush", + [WO_NONE] = "none", + [WO_DRAIN_IO] = "drain", + [WO_BDEV_FLUSH] = "flush", }; pwo = resource->write_ordering; - if (wo != WO_bdev_flush) + if (wo != WO_BDEV_FLUSH) wo = min(pwo, wo); rcu_read_lock(); idr_for_each_entry(&resource->devices, device, vnr) { @@ -1343,7 +1375,7 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin rcu_read_unlock(); resource->write_ordering = wo; - if (pwo != resource->write_ordering || wo == WO_bdev_flush) + if (pwo != resource->write_ordering || wo == WO_BDEV_FLUSH) drbd_info(resource, "Method to ensure write ordering: %s\n", write_ordering_str[resource->write_ordering]); } @@ -1380,7 +1412,7 @@ int drbd_submit_peer_request(struct drbd_device *device, if (peer_req->flags & EE_IS_TRIM_USE_ZEROOUT) { /* wait for all pending IO completions, before we start * zeroing things out. */ - conn_wait_active_ee_empty(first_peer_device(device)->connection); + conn_wait_active_ee_empty(peer_req->peer_device->connection); /* add it to the active list now, * so we can find it to present it in debugfs */ peer_req->submit_jif = jiffies; @@ -1508,12 +1540,6 @@ static void conn_wait_active_ee_empty(struct drbd_connection *connection) rcu_read_unlock(); } -static struct drbd_peer_device * -conn_peer_device(struct drbd_connection *connection, int volume_number) -{ - return idr_find(&connection->peer_devices, volume_number); -} - static int receive_Barrier(struct drbd_connection *connection, struct packet_info *pi) { int rv; @@ -1533,7 +1559,7 @@ static int receive_Barrier(struct drbd_connection *connection, struct packet_inf * Therefore we must send the barrier_ack after the barrier request was * completed. */ switch (connection->resource->write_ordering) { - case WO_none: + case WO_NONE: if (rv == FE_RECYCLED) return 0; @@ -1546,8 +1572,8 @@ static int receive_Barrier(struct drbd_connection *connection, struct packet_inf drbd_warn(connection, "Allocation of an epoch failed, slowing down\n"); /* Fall through */ - case WO_bdev_flush: - case WO_drain_io: + case WO_BDEV_FLUSH: + case WO_DRAIN_IO: conn_wait_active_ee_empty(connection); drbd_flush(connection); @@ -1752,7 +1778,7 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req } /* - * e_end_resync_block() is called in asender context via + * e_end_resync_block() is called in ack_sender context via * drbd_finish_peer_reqs(). */ static int e_end_resync_block(struct drbd_work *w, int unused) @@ -1926,7 +1952,7 @@ static void restart_conflicting_writes(struct drbd_device *device, } /* - * e_end_block() is called in asender context via drbd_finish_peer_reqs(). + * e_end_block() is called in ack_sender context via drbd_finish_peer_reqs(). */ static int e_end_block(struct drbd_work *w, int cancel) { @@ -1966,7 +1992,7 @@ static int e_end_block(struct drbd_work *w, int cancel) } else D_ASSERT(device, drbd_interval_empty(&peer_req->i)); - drbd_may_finish_epoch(first_peer_device(device)->connection, peer_req->epoch, EV_PUT + (cancel ? EV_CLEANUP : 0)); + drbd_may_finish_epoch(peer_device->connection, peer_req->epoch, EV_PUT + (cancel ? EV_CLEANUP : 0)); return err; } @@ -2098,7 +2124,7 @@ static int wait_for_and_update_peer_seq(struct drbd_peer_device *peer_device, co } rcu_read_lock(); - tp = rcu_dereference(first_peer_device(device)->connection->net_conf)->two_primaries; + tp = rcu_dereference(peer_device->connection->net_conf)->two_primaries; rcu_read_unlock(); if (!tp) @@ -2217,7 +2243,7 @@ static int handle_write_conflicts(struct drbd_device *device, peer_req->w.cb = superseded ? e_send_superseded : e_send_retry_write; list_add_tail(&peer_req->w.list, &device->done_ee); - wake_asender(connection); + queue_work(connection->ack_sender, &peer_req->peer_device->send_acks_work); err = -ENOENT; goto out; @@ -2364,7 +2390,7 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info * if (dp_flags & DP_SEND_RECEIVE_ACK) { /* I really don't like it that the receiver thread * sends on the msock, but anyways */ - drbd_send_ack(first_peer_device(device), P_RECV_ACK, peer_req); + drbd_send_ack(peer_device, P_RECV_ACK, peer_req); } if (tp) { @@ -4056,7 +4082,7 @@ static int receive_state(struct drbd_connection *connection, struct packet_info os = ns = drbd_read_state(device); spin_unlock_irq(&device->resource->req_lock); - /* If some other part of the code (asender thread, timeout) + /* If some other part of the code (ack_receiver thread, timeout) * already decided to close the connection again, * we must not "re-establish" it here. */ if (os.conn <= C_TEAR_DOWN) @@ -4661,8 +4687,12 @@ static void conn_disconnect(struct drbd_connection *connection) */ conn_request_state(connection, NS(conn, C_NETWORK_FAILURE), CS_HARD); - /* asender does not clean up anything. it must not interfere, either */ - drbd_thread_stop(&connection->asender); + /* ack_receiver does not clean up anything. it must not interfere, either */ + drbd_thread_stop(&connection->ack_receiver); + if (connection->ack_sender) { + destroy_workqueue(connection->ack_sender); + connection->ack_sender = NULL; + } drbd_free_sock(connection); rcu_read_lock(); @@ -5431,49 +5461,39 @@ static int got_skip(struct drbd_connection *connection, struct packet_info *pi) return 0; } -static int connection_finish_peer_reqs(struct drbd_connection *connection) +struct meta_sock_cmd { + size_t pkt_size; + int (*fn)(struct drbd_connection *connection, struct packet_info *); +}; + +static void set_rcvtimeo(struct drbd_connection *connection, bool ping_timeout) { - struct drbd_peer_device *peer_device; - int vnr, not_empty = 0; + long t; + struct net_conf *nc; - do { - clear_bit(SIGNAL_ASENDER, &connection->flags); - flush_signals(current); + rcu_read_lock(); + nc = rcu_dereference(connection->net_conf); + t = ping_timeout ? nc->ping_timeo : nc->ping_int; + rcu_read_unlock(); - rcu_read_lock(); - idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { - struct drbd_device *device = peer_device->device; - kref_get(&device->kref); - rcu_read_unlock(); - if (drbd_finish_peer_reqs(device)) { - kref_put(&device->kref, drbd_destroy_device); - return 1; - } - kref_put(&device->kref, drbd_destroy_device); - rcu_read_lock(); - } - set_bit(SIGNAL_ASENDER, &connection->flags); + t *= HZ; + if (ping_timeout) + t /= 10; - spin_lock_irq(&connection->resource->req_lock); - idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { - struct drbd_device *device = peer_device->device; - not_empty = !list_empty(&device->done_ee); - if (not_empty) - break; - } - spin_unlock_irq(&connection->resource->req_lock); - rcu_read_unlock(); - } while (not_empty); + connection->meta.socket->sk->sk_rcvtimeo = t; +} - return 0; +static void set_ping_timeout(struct drbd_connection *connection) +{ + set_rcvtimeo(connection, 1); } -struct asender_cmd { - size_t pkt_size; - int (*fn)(struct drbd_connection *connection, struct packet_info *); -}; +static void set_idle_timeout(struct drbd_connection *connection) +{ + set_rcvtimeo(connection, 0); +} -static struct asender_cmd asender_tbl[] = { +static struct meta_sock_cmd ack_receiver_tbl[] = { [P_PING] = { 0, got_Ping }, [P_PING_ACK] = { 0, got_PingAck }, [P_RECV_ACK] = { sizeof(struct p_block_ack), got_BlockAck }, @@ -5493,64 +5513,40 @@ static struct asender_cmd asender_tbl[] = { [P_RETRY_WRITE] = { sizeof(struct p_block_ack), got_BlockAck }, }; -int drbd_asender(struct drbd_thread *thi) +int drbd_ack_receiver(struct drbd_thread *thi) { struct drbd_connection *connection = thi->connection; - struct asender_cmd *cmd = NULL; + struct meta_sock_cmd *cmd = NULL; struct packet_info pi; + unsigned long pre_recv_jif; int rv; void *buf = connection->meta.rbuf; int received = 0; unsigned int header_size = drbd_header_size(connection); int expect = header_size; bool ping_timeout_active = false; - struct net_conf *nc; - int ping_timeo, tcp_cork, ping_int; struct sched_param param = { .sched_priority = 2 }; rv = sched_setscheduler(current, SCHED_RR, ¶m); if (rv < 0) - drbd_err(connection, "drbd_asender: ERROR set priority, ret=%d\n", rv); + drbd_err(connection, "drbd_ack_receiver: ERROR set priority, ret=%d\n", rv); while (get_t_state(thi) == RUNNING) { drbd_thread_current_set_cpu(thi); - rcu_read_lock(); - nc = rcu_dereference(connection->net_conf); - ping_timeo = nc->ping_timeo; - tcp_cork = nc->tcp_cork; - ping_int = nc->ping_int; - rcu_read_unlock(); + conn_reclaim_net_peer_reqs(connection); if (test_and_clear_bit(SEND_PING, &connection->flags)) { if (drbd_send_ping(connection)) { drbd_err(connection, "drbd_send_ping has failed\n"); goto reconnect; } - connection->meta.socket->sk->sk_rcvtimeo = ping_timeo * HZ / 10; + set_ping_timeout(connection); ping_timeout_active = true; } - /* TODO: conditionally cork; it may hurt latency if we cork without - much to send */ - if (tcp_cork) - drbd_tcp_cork(connection->meta.socket); - if (connection_finish_peer_reqs(connection)) { - drbd_err(connection, "connection_finish_peer_reqs() failed\n"); - goto reconnect; - } - /* but unconditionally uncork unless disabled */ - if (tcp_cork) - drbd_tcp_uncork(connection->meta.socket); - - /* short circuit, recv_msg would return EINTR anyways. */ - if (signal_pending(current)) - continue; - + pre_recv_jif = jiffies; rv = drbd_recv_short(connection->meta.socket, buf, expect-received, 0); - clear_bit(SIGNAL_ASENDER, &connection->flags); - - flush_signals(current); /* Note: * -EINTR (on meta) we got a signal @@ -5562,7 +5558,6 @@ int drbd_asender(struct drbd_thread *thi) * rv < expected: "woken" by signal during receive * rv == 0 : "connection shut down by peer" */ -received_more: if (likely(rv > 0)) { received += rv; buf += rv; @@ -5584,8 +5579,7 @@ received_more: } else if (rv == -EAGAIN) { /* If the data socket received something meanwhile, * that is good enough: peer is still alive. */ - if (time_after(connection->last_received, - jiffies - connection->meta.socket->sk->sk_rcvtimeo)) + if (time_after(connection->last_received, pre_recv_jif)) continue; if (ping_timeout_active) { drbd_err(connection, "PingAck did not arrive in time.\n"); @@ -5594,6 +5588,10 @@ received_more: set_bit(SEND_PING, &connection->flags); continue; } else if (rv == -EINTR) { + /* maybe drbd_thread_stop(): the while condition will notice. + * maybe woken for send_ping: we'll send a ping above, + * and change the rcvtimeo */ + flush_signals(current); continue; } else { drbd_err(connection, "sock_recvmsg returned %d\n", rv); @@ -5603,8 +5601,8 @@ received_more: if (received == expect && cmd == NULL) { if (decode_header(connection, connection->meta.rbuf, &pi)) goto reconnect; - cmd = &asender_tbl[pi.cmd]; - if (pi.cmd >= ARRAY_SIZE(asender_tbl) || !cmd->fn) { + cmd = &ack_receiver_tbl[pi.cmd]; + if (pi.cmd >= ARRAY_SIZE(ack_receiver_tbl) || !cmd->fn) { drbd_err(connection, "Unexpected meta packet %s (0x%04x)\n", cmdname(pi.cmd), pi.cmd); goto disconnect; @@ -5627,9 +5625,8 @@ received_more: connection->last_received = jiffies; - if (cmd == &asender_tbl[P_PING_ACK]) { - /* restore idle timeout */ - connection->meta.socket->sk->sk_rcvtimeo = ping_int * HZ; + if (cmd == &ack_receiver_tbl[P_PING_ACK]) { + set_idle_timeout(connection); ping_timeout_active = false; } @@ -5638,11 +5635,6 @@ received_more: expect = header_size; cmd = NULL; } - if (test_bit(SEND_PING, &connection->flags)) - continue; - rv = drbd_recv_short(connection->meta.socket, buf, expect-received, MSG_DONTWAIT); - if (rv > 0) - goto received_more; } if (0) { @@ -5654,9 +5646,41 @@ reconnect: disconnect: conn_request_state(connection, NS(conn, C_DISCONNECTING), CS_HARD); } - clear_bit(SIGNAL_ASENDER, &connection->flags); - drbd_info(connection, "asender terminated\n"); + drbd_info(connection, "ack_receiver terminated\n"); return 0; } + +void drbd_send_acks_wf(struct work_struct *ws) +{ + struct drbd_peer_device *peer_device = + container_of(ws, struct drbd_peer_device, send_acks_work); + struct drbd_connection *connection = peer_device->connection; + struct drbd_device *device = peer_device->device; + struct net_conf *nc; + int tcp_cork, err; + + rcu_read_lock(); + nc = rcu_dereference(connection->net_conf); + tcp_cork = nc->tcp_cork; + rcu_read_unlock(); + + if (tcp_cork) + drbd_tcp_cork(connection->meta.socket); + + err = drbd_finish_peer_reqs(device); + kref_put(&device->kref, drbd_destroy_device); + /* get is in drbd_endio_write_sec_final(). That is necessary to keep the + struct work_struct send_acks_work alive, which is in the peer_device object */ + + if (err) { + conn_request_state(connection, NS(conn, C_NETWORK_FAILURE), CS_HARD); + return; + } + + if (tcp_cork) + drbd_tcp_uncork(connection->meta.socket); + + return; +} diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 3ae2c0086..2255dcfeb 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -453,12 +453,12 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m, kref_get(&req->kref); /* wait for the DONE */ if (!(s & RQ_NET_SENT) && (set & RQ_NET_SENT)) { - /* potentially already completed in the asender thread */ + /* potentially already completed in the ack_receiver thread */ if (!(s & RQ_NET_DONE)) { atomic_add(req->i.size >> 9, &device->ap_in_flight); set_if_null_req_not_net_done(peer_device, req); } - if (s & RQ_NET_PENDING) + if (req->rq_state & RQ_NET_PENDING) set_if_null_req_ack_pending(peer_device, req); } @@ -1095,6 +1095,24 @@ static bool do_remote_read(struct drbd_request *req) return false; } +bool drbd_should_do_remote(union drbd_dev_state s) +{ + return s.pdsk == D_UP_TO_DATE || + (s.pdsk >= D_INCONSISTENT && + s.conn >= C_WF_BITMAP_T && + s.conn < C_AHEAD); + /* Before proto 96 that was >= CONNECTED instead of >= C_WF_BITMAP_T. + That is equivalent since before 96 IO was frozen in the C_WF_BITMAP* + states. */ +} + +static bool drbd_should_send_out_of_sync(union drbd_dev_state s) +{ + return s.conn == C_AHEAD || s.conn == C_WF_BITMAP_S; + /* pdsk = D_INCONSISTENT as a consequence. Protocol 96 check not necessary + since we enter state C_AHEAD only if proto >= 96 */ +} + /* returns number of connections (== 1, for drbd 8.4) * expected to actually write this data, * which does NOT include those that we are L_AHEAD for. */ @@ -1149,7 +1167,6 @@ drbd_submit_req_private_bio(struct drbd_request *req) * stable storage, and this is a WRITE, we may not even submit * this bio. */ if (get_ldev(device)) { - req->pre_submit_jif = jiffies; if (drbd_insert_fault(device, rw == WRITE ? DRBD_FAULT_DT_WR : rw == READ ? DRBD_FAULT_DT_RD @@ -1293,6 +1310,7 @@ static void drbd_send_and_submit(struct drbd_device *device, struct drbd_request &device->pending_master_completion[rw == WRITE]); if (req->private_bio) { /* needs to be marked within the same spinlock */ + req->pre_submit_jif = jiffies; list_add_tail(&req->req_pending_local, &device->pending_completion[rw == WRITE]); _req_mod(req, TO_BE_SUBMITTED); @@ -1513,6 +1531,78 @@ blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio) return BLK_QC_T_NONE; } +static bool net_timeout_reached(struct drbd_request *net_req, + struct drbd_connection *connection, + unsigned long now, unsigned long ent, + unsigned int ko_count, unsigned int timeout) +{ + struct drbd_device *device = net_req->device; + + if (!time_after(now, net_req->pre_send_jif + ent)) + return false; + + if (time_in_range(now, connection->last_reconnect_jif, connection->last_reconnect_jif + ent)) + return false; + + if (net_req->rq_state & RQ_NET_PENDING) { + drbd_warn(device, "Remote failed to finish a request within %ums > ko-count (%u) * timeout (%u * 0.1s)\n", + jiffies_to_msecs(now - net_req->pre_send_jif), ko_count, timeout); + return true; + } + + /* We received an ACK already (or are using protocol A), + * but are waiting for the epoch closing barrier ack. + * Check if we sent the barrier already. We should not blame the peer + * for being unresponsive, if we did not even ask it yet. */ + if (net_req->epoch == connection->send.current_epoch_nr) { + drbd_warn(device, + "We did not send a P_BARRIER for %ums > ko-count (%u) * timeout (%u * 0.1s); drbd kernel thread blocked?\n", + jiffies_to_msecs(now - net_req->pre_send_jif), ko_count, timeout); + return false; + } + + /* Worst case: we may have been blocked for whatever reason, then + * suddenly are able to send a lot of requests (and epoch separating + * barriers) in quick succession. + * The timestamp of the net_req may be much too old and not correspond + * to the sending time of the relevant unack'ed barrier packet, so + * would trigger a spurious timeout. The latest barrier packet may + * have a too recent timestamp to trigger the timeout, potentially miss + * a timeout. Right now we don't have a place to conveniently store + * these timestamps. + * But in this particular situation, the application requests are still + * completed to upper layers, DRBD should still "feel" responsive. + * No need yet to kill this connection, it may still recover. + * If not, eventually we will have queued enough into the network for + * us to block. From that point of view, the timestamp of the last sent + * barrier packet is relevant enough. + */ + if (time_after(now, connection->send.last_sent_barrier_jif + ent)) { + drbd_warn(device, "Remote failed to answer a P_BARRIER (sent at %lu jif; now=%lu jif) within %ums > ko-count (%u) * timeout (%u * 0.1s)\n", + connection->send.last_sent_barrier_jif, now, + jiffies_to_msecs(now - connection->send.last_sent_barrier_jif), ko_count, timeout); + return true; + } + return false; +} + +/* A request is considered timed out, if + * - we have some effective timeout from the configuration, + * with some state restrictions applied, + * - the oldest request is waiting for a response from the network + * resp. the local disk, + * - the oldest request is in fact older than the effective timeout, + * - the connection was established (resp. disk was attached) + * for longer than the timeout already. + * Note that for 32bit jiffies and very stable connections/disks, + * we may have a wrap around, which is catched by + * !time_in_range(now, last_..._jif, last_..._jif + timeout). + * + * Side effect: once per 32bit wrap-around interval, which means every + * ~198 days with 250 HZ, we have a window where the timeout would need + * to expire twice (worst case) to become effective. Good enough. + */ + void request_timer_fn(unsigned long data) { struct drbd_device *device = (struct drbd_device *) data; @@ -1522,11 +1612,14 @@ void request_timer_fn(unsigned long data) unsigned long oldest_submit_jif; unsigned long ent = 0, dt = 0, et, nt; /* effective timeout = ko_count * timeout */ unsigned long now; + unsigned int ko_count = 0, timeout = 0; rcu_read_lock(); nc = rcu_dereference(connection->net_conf); - if (nc && device->state.conn >= C_WF_REPORT_PARAMS) - ent = nc->timeout * HZ/10 * nc->ko_count; + if (nc && device->state.conn >= C_WF_REPORT_PARAMS) { + ko_count = nc->ko_count; + timeout = nc->timeout; + } if (get_ldev(device)) { /* implicit state.disk >= D_INCONSISTENT */ dt = rcu_dereference(device->ldev->disk_conf)->disk_timeout * HZ / 10; @@ -1534,6 +1627,8 @@ void request_timer_fn(unsigned long data) } rcu_read_unlock(); + + ent = timeout * HZ/10 * ko_count; et = min_not_zero(dt, ent); if (!et) @@ -1545,11 +1640,22 @@ void request_timer_fn(unsigned long data) spin_lock_irq(&device->resource->req_lock); req_read = list_first_entry_or_null(&device->pending_completion[0], struct drbd_request, req_pending_local); req_write = list_first_entry_or_null(&device->pending_completion[1], struct drbd_request, req_pending_local); - req_peer = connection->req_not_net_done; + /* maybe the oldest request waiting for the peer is in fact still - * blocking in tcp sendmsg */ - if (!req_peer && connection->req_next && connection->req_next->pre_send_jif) - req_peer = connection->req_next; + * blocking in tcp sendmsg. That's ok, though, that's handled via the + * socket send timeout, requesting a ping, and bumping ko-count in + * we_should_drop_the_connection(). + */ + + /* check the oldest request we did successfully sent, + * but which is still waiting for an ACK. */ + req_peer = connection->req_ack_pending; + + /* if we don't have such request (e.g. protocoll A) + * check the oldest requests which is still waiting on its epoch + * closing barrier ack. */ + if (!req_peer) + req_peer = connection->req_not_net_done; /* evaluate the oldest peer request only in one timer! */ if (req_peer && req_peer->device != device) @@ -1566,28 +1672,9 @@ void request_timer_fn(unsigned long data) : req_write ? req_write->pre_submit_jif : req_read ? req_read->pre_submit_jif : now; - /* The request is considered timed out, if - * - we have some effective timeout from the configuration, - * with above state restrictions applied, - * - the oldest request is waiting for a response from the network - * resp. the local disk, - * - the oldest request is in fact older than the effective timeout, - * - the connection was established (resp. disk was attached) - * for longer than the timeout already. - * Note that for 32bit jiffies and very stable connections/disks, - * we may have a wrap around, which is catched by - * !time_in_range(now, last_..._jif, last_..._jif + timeout). - * - * Side effect: once per 32bit wrap-around interval, which means every - * ~198 days with 250 HZ, we have a window where the timeout would need - * to expire twice (worst case) to become effective. Good enough. - */ - if (ent && req_peer && - time_after(now, req_peer->pre_send_jif + ent) && - !time_in_range(now, connection->last_reconnect_jif, connection->last_reconnect_jif + ent)) { - drbd_warn(device, "Remote failed to finish a request within ko-count * timeout\n"); + if (ent && req_peer && net_timeout_reached(req_peer, connection, now, ent, ko_count, timeout)) _conn_request_state(connection, NS(conn, C_TIMEOUT), CS_VERBOSE | CS_HARD); - } + if (dt && oldest_submit_jif != now && time_after(now, oldest_submit_jif + dt) && !time_in_range(now, device->last_reattach_jif, device->last_reattach_jif + dt)) { diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h index 9f6a04080..bb2ef7816 100644 --- a/drivers/block/drbd/drbd_req.h +++ b/drivers/block/drbd/drbd_req.h @@ -331,21 +331,6 @@ static inline int req_mod(struct drbd_request *req, return rv; } -static inline bool drbd_should_do_remote(union drbd_dev_state s) -{ - return s.pdsk == D_UP_TO_DATE || - (s.pdsk >= D_INCONSISTENT && - s.conn >= C_WF_BITMAP_T && - s.conn < C_AHEAD); - /* Before proto 96 that was >= CONNECTED instead of >= C_WF_BITMAP_T. - That is equivalent since before 96 IO was frozen in the C_WF_BITMAP* - states. */ -} -static inline bool drbd_should_send_out_of_sync(union drbd_dev_state s) -{ - return s.conn == C_AHEAD || s.conn == C_WF_BITMAP_S; - /* pdsk = D_INCONSISTENT as a consequence. Protocol 96 check not necessary - since we enter state C_AHEAD only if proto >= 96 */ -} +extern bool drbd_should_do_remote(union drbd_dev_state); #endif diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 2d7dd269b..5a7ef7873 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -29,6 +29,7 @@ #include "drbd_int.h" #include "drbd_protocol.h" #include "drbd_req.h" +#include "drbd_state_change.h" struct after_state_chg_work { struct drbd_work w; @@ -37,6 +38,7 @@ struct after_state_chg_work { union drbd_state ns; enum chg_state_flags flags; struct completion *done; + struct drbd_state_change *state_change; }; enum sanitize_state_warnings { @@ -48,9 +50,248 @@ enum sanitize_state_warnings { IMPLICITLY_UPGRADED_PDSK, }; +static void count_objects(struct drbd_resource *resource, + unsigned int *n_devices, + unsigned int *n_connections) +{ + struct drbd_device *device; + struct drbd_connection *connection; + int vnr; + + *n_devices = 0; + *n_connections = 0; + + idr_for_each_entry(&resource->devices, device, vnr) + (*n_devices)++; + for_each_connection(connection, resource) + (*n_connections)++; +} + +static struct drbd_state_change *alloc_state_change(unsigned int n_devices, unsigned int n_connections, gfp_t gfp) +{ + struct drbd_state_change *state_change; + unsigned int size, n; + + size = sizeof(struct drbd_state_change) + + n_devices * sizeof(struct drbd_device_state_change) + + n_connections * sizeof(struct drbd_connection_state_change) + + n_devices * n_connections * sizeof(struct drbd_peer_device_state_change); + state_change = kmalloc(size, gfp); + if (!state_change) + return NULL; + state_change->n_devices = n_devices; + state_change->n_connections = n_connections; + state_change->devices = (void *)(state_change + 1); + state_change->connections = (void *)&state_change->devices[n_devices]; + state_change->peer_devices = (void *)&state_change->connections[n_connections]; + state_change->resource->resource = NULL; + for (n = 0; n < n_devices; n++) + state_change->devices[n].device = NULL; + for (n = 0; n < n_connections; n++) + state_change->connections[n].connection = NULL; + return state_change; +} + +struct drbd_state_change *remember_old_state(struct drbd_resource *resource, gfp_t gfp) +{ + struct drbd_state_change *state_change; + struct drbd_device *device; + unsigned int n_devices; + struct drbd_connection *connection; + unsigned int n_connections; + int vnr; + + struct drbd_device_state_change *device_state_change; + struct drbd_peer_device_state_change *peer_device_state_change; + struct drbd_connection_state_change *connection_state_change; + + /* Caller holds req_lock spinlock. + * No state, no device IDR, no connections lists can change. */ + count_objects(resource, &n_devices, &n_connections); + state_change = alloc_state_change(n_devices, n_connections, gfp); + if (!state_change) + return NULL; + + kref_get(&resource->kref); + state_change->resource->resource = resource; + state_change->resource->role[OLD] = + conn_highest_role(first_connection(resource)); + state_change->resource->susp[OLD] = resource->susp; + state_change->resource->susp_nod[OLD] = resource->susp_nod; + state_change->resource->susp_fen[OLD] = resource->susp_fen; + + connection_state_change = state_change->connections; + for_each_connection(connection, resource) { + kref_get(&connection->kref); + connection_state_change->connection = connection; + connection_state_change->cstate[OLD] = + connection->cstate; + connection_state_change->peer_role[OLD] = + conn_highest_peer(connection); + connection_state_change++; + } + + device_state_change = state_change->devices; + peer_device_state_change = state_change->peer_devices; + idr_for_each_entry(&resource->devices, device, vnr) { + kref_get(&device->kref); + device_state_change->device = device; + device_state_change->disk_state[OLD] = device->state.disk; + + /* The peer_devices for each device have to be enumerated in + the order of the connections. We may not use for_each_peer_device() here. */ + for_each_connection(connection, resource) { + struct drbd_peer_device *peer_device; + + peer_device = conn_peer_device(connection, device->vnr); + peer_device_state_change->peer_device = peer_device; + peer_device_state_change->disk_state[OLD] = + device->state.pdsk; + peer_device_state_change->repl_state[OLD] = + max_t(enum drbd_conns, + C_WF_REPORT_PARAMS, device->state.conn); + peer_device_state_change->resync_susp_user[OLD] = + device->state.user_isp; + peer_device_state_change->resync_susp_peer[OLD] = + device->state.peer_isp; + peer_device_state_change->resync_susp_dependency[OLD] = + device->state.aftr_isp; + peer_device_state_change++; + } + device_state_change++; + } + + return state_change; +} + +static void remember_new_state(struct drbd_state_change *state_change) +{ + struct drbd_resource_state_change *resource_state_change; + struct drbd_resource *resource; + unsigned int n; + + if (!state_change) + return; + + resource_state_change = &state_change->resource[0]; + resource = resource_state_change->resource; + + resource_state_change->role[NEW] = + conn_highest_role(first_connection(resource)); + resource_state_change->susp[NEW] = resource->susp; + resource_state_change->susp_nod[NEW] = resource->susp_nod; + resource_state_change->susp_fen[NEW] = resource->susp_fen; + + for (n = 0; n < state_change->n_devices; n++) { + struct drbd_device_state_change *device_state_change = + &state_change->devices[n]; + struct drbd_device *device = device_state_change->device; + + device_state_change->disk_state[NEW] = device->state.disk; + } + + for (n = 0; n < state_change->n_connections; n++) { + struct drbd_connection_state_change *connection_state_change = + &state_change->connections[n]; + struct drbd_connection *connection = + connection_state_change->connection; + + connection_state_change->cstate[NEW] = connection->cstate; + connection_state_change->peer_role[NEW] = + conn_highest_peer(connection); + } + + for (n = 0; n < state_change->n_devices * state_change->n_connections; n++) { + struct drbd_peer_device_state_change *peer_device_state_change = + &state_change->peer_devices[n]; + struct drbd_device *device = + peer_device_state_change->peer_device->device; + union drbd_dev_state state = device->state; + + peer_device_state_change->disk_state[NEW] = state.pdsk; + peer_device_state_change->repl_state[NEW] = + max_t(enum drbd_conns, C_WF_REPORT_PARAMS, state.conn); + peer_device_state_change->resync_susp_user[NEW] = + state.user_isp; + peer_device_state_change->resync_susp_peer[NEW] = + state.peer_isp; + peer_device_state_change->resync_susp_dependency[NEW] = + state.aftr_isp; + } +} + +void copy_old_to_new_state_change(struct drbd_state_change *state_change) +{ + struct drbd_resource_state_change *resource_state_change = &state_change->resource[0]; + unsigned int n_device, n_connection, n_peer_device, n_peer_devices; + +#define OLD_TO_NEW(x) \ + (x[NEW] = x[OLD]) + + OLD_TO_NEW(resource_state_change->role); + OLD_TO_NEW(resource_state_change->susp); + OLD_TO_NEW(resource_state_change->susp_nod); + OLD_TO_NEW(resource_state_change->susp_fen); + + for (n_connection = 0; n_connection < state_change->n_connections; n_connection++) { + struct drbd_connection_state_change *connection_state_change = + &state_change->connections[n_connection]; + + OLD_TO_NEW(connection_state_change->peer_role); + OLD_TO_NEW(connection_state_change->cstate); + } + + for (n_device = 0; n_device < state_change->n_devices; n_device++) { + struct drbd_device_state_change *device_state_change = + &state_change->devices[n_device]; + + OLD_TO_NEW(device_state_change->disk_state); + } + + n_peer_devices = state_change->n_devices * state_change->n_connections; + for (n_peer_device = 0; n_peer_device < n_peer_devices; n_peer_device++) { + struct drbd_peer_device_state_change *p = + &state_change->peer_devices[n_peer_device]; + + OLD_TO_NEW(p->disk_state); + OLD_TO_NEW(p->repl_state); + OLD_TO_NEW(p->resync_susp_user); + OLD_TO_NEW(p->resync_susp_peer); + OLD_TO_NEW(p->resync_susp_dependency); + } + +#undef OLD_TO_NEW +} + +void forget_state_change(struct drbd_state_change *state_change) +{ + unsigned int n; + + if (!state_change) + return; + + if (state_change->resource->resource) + kref_put(&state_change->resource->resource->kref, drbd_destroy_resource); + for (n = 0; n < state_change->n_devices; n++) { + struct drbd_device *device = state_change->devices[n].device; + + if (device) + kref_put(&device->kref, drbd_destroy_device); + } + for (n = 0; n < state_change->n_connections; n++) { + struct drbd_connection *connection = + state_change->connections[n].connection; + + if (connection) + kref_put(&connection->kref, drbd_destroy_connection); + } + kfree(state_change); +} + static int w_after_state_ch(struct drbd_work *w, int unused); static void after_state_ch(struct drbd_device *device, union drbd_state os, - union drbd_state ns, enum chg_state_flags flags); + union drbd_state ns, enum chg_state_flags flags, + struct drbd_state_change *); static enum drbd_state_rv is_valid_state(struct drbd_device *, union drbd_state); static enum drbd_state_rv is_valid_soft_transition(union drbd_state, union drbd_state, struct drbd_connection *); static enum drbd_state_rv is_valid_transition(union drbd_state os, union drbd_state ns); @@ -93,6 +334,7 @@ static enum drbd_role max_role(enum drbd_role role1, enum drbd_role role2) return R_SECONDARY; return R_UNKNOWN; } + static enum drbd_role min_role(enum drbd_role role1, enum drbd_role role2) { if (role1 == R_UNKNOWN || role2 == R_UNKNOWN) @@ -937,7 +1179,7 @@ void drbd_resume_al(struct drbd_device *device) drbd_info(device, "Resumed AL updates\n"); } -/* helper for __drbd_set_state */ +/* helper for _drbd_set_state */ static void set_ov_position(struct drbd_device *device, enum drbd_conns cs) { if (first_peer_device(device)->connection->agreed_pro_version < 90) @@ -965,17 +1207,17 @@ static void set_ov_position(struct drbd_device *device, enum drbd_conns cs) } /** - * __drbd_set_state() - Set a new DRBD state + * _drbd_set_state() - Set a new DRBD state * @device: DRBD device. * @ns: new state. * @flags: Flags * @done: Optional completion, that will get completed after the after_state_ch() finished * - * Caller needs to hold req_lock, and global_state_lock. Do not call directly. + * Caller needs to hold req_lock. Do not call directly. */ enum drbd_state_rv -__drbd_set_state(struct drbd_device *device, union drbd_state ns, - enum chg_state_flags flags, struct completion *done) +_drbd_set_state(struct drbd_device *device, union drbd_state ns, + enum chg_state_flags flags, struct completion *done) { struct drbd_peer_device *peer_device = first_peer_device(device); struct drbd_connection *connection = peer_device ? peer_device->connection : NULL; @@ -983,6 +1225,7 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns, enum drbd_state_rv rv = SS_SUCCESS; enum sanitize_state_warnings ssw; struct after_state_chg_work *ascw; + struct drbd_state_change *state_change; os = drbd_read_state(device); @@ -1037,6 +1280,9 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns, if (!is_sync_state(os.conn) && is_sync_state(ns.conn)) clear_bit(RS_DONE, &device->flags); + /* FIXME: Have any flags been set earlier in this function already? */ + state_change = remember_old_state(device->resource, GFP_ATOMIC); + /* changes to local_cnt and device flags should be visible before * changes to state, which again should be visible before anything else * depending on that change happens. */ @@ -1047,6 +1293,8 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns, device->resource->susp_fen = ns.susp_fen; smp_wmb(); + remember_new_state(state_change); + /* put replicated vs not-replicated requests in seperate epochs */ if (drbd_should_do_remote((union drbd_dev_state)os.i) != drbd_should_do_remote((union drbd_dev_state)ns.i)) @@ -1184,6 +1432,7 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns, ascw->w.cb = w_after_state_ch; ascw->device = device; ascw->done = done; + ascw->state_change = state_change; drbd_queue_work(&connection->sender_work, &ascw->w); } else { @@ -1199,7 +1448,8 @@ static int w_after_state_ch(struct drbd_work *w, int unused) container_of(w, struct after_state_chg_work, w); struct drbd_device *device = ascw->device; - after_state_ch(device, ascw->os, ascw->ns, ascw->flags); + after_state_ch(device, ascw->os, ascw->ns, ascw->flags, ascw->state_change); + forget_state_change(ascw->state_change); if (ascw->flags & CS_WAIT_COMPLETE) complete(ascw->done); kfree(ascw); @@ -1234,7 +1484,7 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device, D_ASSERT(device, current == first_peer_device(device)->connection->worker.task); /* open coded non-blocking drbd_suspend_io(device); */ - set_bit(SUSPEND_IO, &device->flags); + atomic_inc(&device->suspend_cnt); drbd_bm_lock(device, why, flags); rv = io_fn(device); @@ -1245,6 +1495,139 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device, return rv; } +void notify_resource_state_change(struct sk_buff *skb, + unsigned int seq, + struct drbd_resource_state_change *resource_state_change, + enum drbd_notification_type type) +{ + struct drbd_resource *resource = resource_state_change->resource; + struct resource_info resource_info = { + .res_role = resource_state_change->role[NEW], + .res_susp = resource_state_change->susp[NEW], + .res_susp_nod = resource_state_change->susp_nod[NEW], + .res_susp_fen = resource_state_change->susp_fen[NEW], + }; + + notify_resource_state(skb, seq, resource, &resource_info, type); +} + +void notify_connection_state_change(struct sk_buff *skb, + unsigned int seq, + struct drbd_connection_state_change *connection_state_change, + enum drbd_notification_type type) +{ + struct drbd_connection *connection = connection_state_change->connection; + struct connection_info connection_info = { + .conn_connection_state = connection_state_change->cstate[NEW], + .conn_role = connection_state_change->peer_role[NEW], + }; + + notify_connection_state(skb, seq, connection, &connection_info, type); +} + +void notify_device_state_change(struct sk_buff *skb, + unsigned int seq, + struct drbd_device_state_change *device_state_change, + enum drbd_notification_type type) +{ + struct drbd_device *device = device_state_change->device; + struct device_info device_info = { + .dev_disk_state = device_state_change->disk_state[NEW], + }; + + notify_device_state(skb, seq, device, &device_info, type); +} + +void notify_peer_device_state_change(struct sk_buff *skb, + unsigned int seq, + struct drbd_peer_device_state_change *p, + enum drbd_notification_type type) +{ + struct drbd_peer_device *peer_device = p->peer_device; + struct peer_device_info peer_device_info = { + .peer_repl_state = p->repl_state[NEW], + .peer_disk_state = p->disk_state[NEW], + .peer_resync_susp_user = p->resync_susp_user[NEW], + .peer_resync_susp_peer = p->resync_susp_peer[NEW], + .peer_resync_susp_dependency = p->resync_susp_dependency[NEW], + }; + + notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); +} + +static void broadcast_state_change(struct drbd_state_change *state_change) +{ + struct drbd_resource_state_change *resource_state_change = &state_change->resource[0]; + bool resource_state_has_changed; + unsigned int n_device, n_connection, n_peer_device, n_peer_devices; + void (*last_func)(struct sk_buff *, unsigned int, void *, + enum drbd_notification_type) = NULL; + void *uninitialized_var(last_arg); + +#define HAS_CHANGED(state) ((state)[OLD] != (state)[NEW]) +#define FINAL_STATE_CHANGE(type) \ + ({ if (last_func) \ + last_func(NULL, 0, last_arg, type); \ + }) +#define REMEMBER_STATE_CHANGE(func, arg, type) \ + ({ FINAL_STATE_CHANGE(type | NOTIFY_CONTINUES); \ + last_func = (typeof(last_func))func; \ + last_arg = arg; \ + }) + + mutex_lock(¬ification_mutex); + + resource_state_has_changed = + HAS_CHANGED(resource_state_change->role) || + HAS_CHANGED(resource_state_change->susp) || + HAS_CHANGED(resource_state_change->susp_nod) || + HAS_CHANGED(resource_state_change->susp_fen); + + if (resource_state_has_changed) + REMEMBER_STATE_CHANGE(notify_resource_state_change, + resource_state_change, NOTIFY_CHANGE); + + for (n_connection = 0; n_connection < state_change->n_connections; n_connection++) { + struct drbd_connection_state_change *connection_state_change = + &state_change->connections[n_connection]; + + if (HAS_CHANGED(connection_state_change->peer_role) || + HAS_CHANGED(connection_state_change->cstate)) + REMEMBER_STATE_CHANGE(notify_connection_state_change, + connection_state_change, NOTIFY_CHANGE); + } + + for (n_device = 0; n_device < state_change->n_devices; n_device++) { + struct drbd_device_state_change *device_state_change = + &state_change->devices[n_device]; + + if (HAS_CHANGED(device_state_change->disk_state)) + REMEMBER_STATE_CHANGE(notify_device_state_change, + device_state_change, NOTIFY_CHANGE); + } + + n_peer_devices = state_change->n_devices * state_change->n_connections; + for (n_peer_device = 0; n_peer_device < n_peer_devices; n_peer_device++) { + struct drbd_peer_device_state_change *p = + &state_change->peer_devices[n_peer_device]; + + if (HAS_CHANGED(p->disk_state) || + HAS_CHANGED(p->repl_state) || + HAS_CHANGED(p->resync_susp_user) || + HAS_CHANGED(p->resync_susp_peer) || + HAS_CHANGED(p->resync_susp_dependency)) + REMEMBER_STATE_CHANGE(notify_peer_device_state_change, + p, NOTIFY_CHANGE); + } + + FINAL_STATE_CHANGE(NOTIFY_CHANGE); + mutex_unlock(¬ification_mutex); + +#undef HAS_CHANGED +#undef FINAL_STATE_CHANGE +#undef REMEMBER_STATE_CHANGE +} + /** * after_state_ch() - Perform after state change actions that may sleep * @device: DRBD device. @@ -1253,13 +1636,16 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device, * @flags: Flags */ static void after_state_ch(struct drbd_device *device, union drbd_state os, - union drbd_state ns, enum chg_state_flags flags) + union drbd_state ns, enum chg_state_flags flags, + struct drbd_state_change *state_change) { struct drbd_resource *resource = device->resource; struct drbd_peer_device *peer_device = first_peer_device(device); struct drbd_connection *connection = peer_device ? peer_device->connection : NULL; struct sib_info sib; + broadcast_state_change(state_change); + sib.sib_reason = SIB_STATE_CHANGE; sib.os = os; sib.ns = ns; @@ -1377,7 +1763,7 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os, } if (ns.pdsk < D_INCONSISTENT && get_ldev(device)) { - if (os.peer == R_SECONDARY && ns.peer == R_PRIMARY && + if (os.peer != R_PRIMARY && ns.peer == R_PRIMARY && device->ldev->md.uuid[UI_BITMAP] == 0 && ns.disk >= D_UP_TO_DATE) { drbd_uuid_new_current(device); drbd_send_uuids(peer_device); @@ -1444,7 +1830,7 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os, if (os.disk != D_FAILED && ns.disk == D_FAILED) { enum drbd_io_error_p eh = EP_PASS_ON; int was_io_error = 0; - /* corresponding get_ldev was in __drbd_set_state, to serialize + /* corresponding get_ldev was in _drbd_set_state, to serialize * our cleanup here with the transition to D_DISKLESS. * But is is still not save to dreference ldev here, since * we might come from an failed Attach before ldev was set. */ @@ -1455,6 +1841,10 @@ static void after_state_ch(struct drbd_device *device, union drbd_state os, was_io_error = test_and_clear_bit(WAS_IO_ERROR, &device->flags); + /* Intentionally call this handler first, before drbd_send_state(). + * See: 2932204 drbd: call local-io-error handler early + * People may chose to hard-reset the box from this handler. + * It is useful if this looks like a "regular node crash". */ if (was_io_error && eh == EP_CALL_HELPER) drbd_khelper(device, "local-io-error"); @@ -1572,6 +1962,7 @@ struct after_conn_state_chg_work { union drbd_state ns_max; /* new, max state, over all devices */ enum chg_state_flags flags; struct drbd_connection *connection; + struct drbd_state_change *state_change; }; static int w_after_conn_state_ch(struct drbd_work *w, int unused) @@ -1584,6 +1975,8 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused) struct drbd_peer_device *peer_device; int vnr; + broadcast_state_change(acscw->state_change); + forget_state_change(acscw->state_change); kfree(acscw); /* Upon network configuration, we need to start the receiver */ @@ -1593,6 +1986,13 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused) if (oc == C_DISCONNECTING && ns_max.conn == C_STANDALONE) { struct net_conf *old_conf; + mutex_lock(¬ification_mutex); + idr_for_each_entry(&connection->peer_devices, peer_device, vnr) + notify_peer_device_state(NULL, 0, peer_device, NULL, + NOTIFY_DESTROY | NOTIFY_CONTINUES); + notify_connection_state(NULL, 0, connection, NULL, NOTIFY_DESTROY); + mutex_unlock(¬ification_mutex); + mutex_lock(&connection->resource->conf_update); old_conf = connection->net_conf; connection->my_addr_len = 0; @@ -1759,7 +2159,7 @@ conn_set_state(struct drbd_connection *connection, union drbd_state mask, union if (flags & CS_IGN_OUTD_FAIL && ns.disk == D_OUTDATED && os.disk < D_OUTDATED) ns.disk = os.disk; - rv = __drbd_set_state(device, ns, flags, NULL); + rv = _drbd_set_state(device, ns, flags, NULL); if (rv < SS_SUCCESS) BUG(); @@ -1823,6 +2223,7 @@ _conn_request_state(struct drbd_connection *connection, union drbd_state mask, u enum drbd_conns oc = connection->cstate; union drbd_state ns_max, ns_min, os; bool have_mutex = false; + struct drbd_state_change *state_change; if (mask.conn) { rv = is_valid_conn_transition(oc, val.conn); @@ -1868,10 +2269,12 @@ _conn_request_state(struct drbd_connection *connection, union drbd_state mask, u goto abort; } + state_change = remember_old_state(connection->resource, GFP_ATOMIC); conn_old_common_state(connection, &os, &flags); flags |= CS_DC_SUSP; conn_set_state(connection, mask, val, &ns_min, &ns_max, flags); conn_pr_state_change(connection, os, ns_max, flags); + remember_new_state(state_change); acscw = kmalloc(sizeof(*acscw), GFP_ATOMIC); if (acscw) { @@ -1882,6 +2285,7 @@ _conn_request_state(struct drbd_connection *connection, union drbd_state mask, u acscw->w.cb = w_after_conn_state_ch; kref_get(&connection->kref); acscw->connection = connection; + acscw->state_change = state_change; drbd_queue_work(&connection->sender_work, &acscw->w); } else { drbd_err(connection, "Could not kmalloc an acscw\n"); diff --git a/drivers/block/drbd/drbd_state.h b/drivers/block/drbd/drbd_state.h index 7f53c4082..bd989536f 100644 --- a/drivers/block/drbd/drbd_state.h +++ b/drivers/block/drbd/drbd_state.h @@ -122,9 +122,9 @@ extern enum drbd_state_rv _drbd_request_state_holding_state_mutex(struct drbd_device *, union drbd_state, union drbd_state, enum chg_state_flags); -extern enum drbd_state_rv __drbd_set_state(struct drbd_device *, union drbd_state, - enum chg_state_flags, - struct completion *done); +extern enum drbd_state_rv _drbd_set_state(struct drbd_device *, union drbd_state, + enum chg_state_flags, + struct completion *done); extern void print_st_err(struct drbd_device *, union drbd_state, union drbd_state, int); diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h new file mode 100644 index 000000000..9e503a1a0 --- /dev/null +++ b/drivers/block/drbd/drbd_state_change.h @@ -0,0 +1,63 @@ +#ifndef DRBD_STATE_CHANGE_H +#define DRBD_STATE_CHANGE_H + +struct drbd_resource_state_change { + struct drbd_resource *resource; + enum drbd_role role[2]; + bool susp[2]; + bool susp_nod[2]; + bool susp_fen[2]; +}; + +struct drbd_device_state_change { + struct drbd_device *device; + enum drbd_disk_state disk_state[2]; +}; + +struct drbd_connection_state_change { + struct drbd_connection *connection; + enum drbd_conns cstate[2]; /* drbd9: enum drbd_conn_state */ + enum drbd_role peer_role[2]; +}; + +struct drbd_peer_device_state_change { + struct drbd_peer_device *peer_device; + enum drbd_disk_state disk_state[2]; + enum drbd_conns repl_state[2]; /* drbd9: enum drbd_repl_state */ + bool resync_susp_user[2]; + bool resync_susp_peer[2]; + bool resync_susp_dependency[2]; +}; + +struct drbd_state_change { + struct list_head list; + unsigned int n_devices; + unsigned int n_connections; + struct drbd_resource_state_change resource[1]; + struct drbd_device_state_change *devices; + struct drbd_connection_state_change *connections; + struct drbd_peer_device_state_change *peer_devices; +}; + +extern struct drbd_state_change *remember_old_state(struct drbd_resource *, gfp_t); +extern void copy_old_to_new_state_change(struct drbd_state_change *); +extern void forget_state_change(struct drbd_state_change *); + +extern void notify_resource_state_change(struct sk_buff *, + unsigned int, + struct drbd_resource_state_change *, + enum drbd_notification_type type); +extern void notify_connection_state_change(struct sk_buff *, + unsigned int, + struct drbd_connection_state_change *, + enum drbd_notification_type type); +extern void notify_device_state_change(struct sk_buff *, + unsigned int, + struct drbd_device_state_change *, + enum drbd_notification_type type); +extern void notify_peer_device_state_change(struct sk_buff *, + unsigned int, + struct drbd_peer_device_state_change *, + enum drbd_notification_type type); + +#endif /* DRBD_STATE_CHANGE_H */ diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 5578c1477..eff716c27 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -55,13 +55,6 @@ static int make_resync_request(struct drbd_device *, int); * */ - -/* About the global_state_lock - Each state transition on an device holds a read lock. In case we have - to evaluate the resync after dependencies, we grab a write lock, because - we need stable states on all devices for that. */ -rwlock_t global_state_lock; - /* used for synchronous meta data and bitmap IO * submitted by drbd_md_sync_page_io() */ @@ -120,6 +113,7 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l unsigned long flags = 0; struct drbd_peer_device *peer_device = peer_req->peer_device; struct drbd_device *device = peer_device->device; + struct drbd_connection *connection = peer_device->connection; struct drbd_interval i; int do_wake; u64 block_id; @@ -152,6 +146,12 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l * ((peer_req->flags & (EE_WAS_ERROR|EE_IS_TRIM)) == EE_WAS_ERROR) */ if (peer_req->flags & EE_WAS_ERROR) __drbd_chk_io_error(device, DRBD_WRITE_ERROR); + + if (connection->cstate >= C_WF_REPORT_PARAMS) { + kref_get(&device->kref); /* put is in drbd_send_acks_wf() */ + if (!queue_work(connection->ack_sender, &peer_device->send_acks_work)) + kref_put(&device->kref, drbd_destroy_device); + } spin_unlock_irqrestore(&device->resource->req_lock, flags); if (block_id == ID_SYNCER) @@ -163,7 +163,6 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l if (do_al_complete_io) drbd_al_complete_io(device, &i); - wake_asender(peer_device->connection); put_ldev(device); } @@ -195,6 +194,12 @@ void drbd_peer_request_endio(struct bio *bio) } } +void drbd_panic_after_delayed_completion_of_aborted_request(struct drbd_device *device) +{ + panic("drbd%u %s/%u potential random memory corruption caused by delayed completion of aborted local request\n", + device->minor, device->resource->name, device->vnr); +} + /* read, readA or write requests on R_PRIMARY coming from drbd_make_request */ void drbd_request_endio(struct bio *bio) @@ -238,7 +243,7 @@ void drbd_request_endio(struct bio *bio) drbd_emerg(device, "delayed completion of aborted local request; disk-timeout may be too aggressive\n"); if (!bio->bi_error) - panic("possible random memory corruption caused by delayed completion of aborted local request\n"); + drbd_panic_after_delayed_completion_of_aborted_request(device); } /* to avoid recursion in __req_mod */ @@ -1291,6 +1296,7 @@ static int drbd_send_barrier(struct drbd_connection *connection) p->barrier = connection->send.current_epoch_nr; p->pad = 0; connection->send.current_epoch_writes = 0; + connection->send.last_sent_barrier_jif = jiffies; return conn_send_command(connection, sock, P_BARRIER, sizeof(*p), NULL, 0); } @@ -1315,6 +1321,7 @@ static void re_init_if_first_write(struct drbd_connection *connection, unsigned connection->send.seen_any_write_yet = true; connection->send.current_epoch_nr = epoch; connection->send.current_epoch_writes = 0; + connection->send.last_sent_barrier_jif = jiffies; } } @@ -1456,70 +1463,73 @@ static int _drbd_may_sync_now(struct drbd_device *device) } /** - * _drbd_pause_after() - Pause resync on all devices that may not resync now + * drbd_pause_after() - Pause resync on all devices that may not resync now * @device: DRBD device. * * Called from process context only (admin command and after_state_ch). */ -static int _drbd_pause_after(struct drbd_device *device) +static bool drbd_pause_after(struct drbd_device *device) { + bool changed = false; struct drbd_device *odev; - int i, rv = 0; + int i; rcu_read_lock(); idr_for_each_entry(&drbd_devices, odev, i) { if (odev->state.conn == C_STANDALONE && odev->state.disk == D_DISKLESS) continue; - if (!_drbd_may_sync_now(odev)) - rv |= (__drbd_set_state(_NS(odev, aftr_isp, 1), CS_HARD, NULL) - != SS_NOTHING_TO_DO); + if (!_drbd_may_sync_now(odev) && + _drbd_set_state(_NS(odev, aftr_isp, 1), + CS_HARD, NULL) != SS_NOTHING_TO_DO) + changed = true; } rcu_read_unlock(); - return rv; + return changed; } /** - * _drbd_resume_next() - Resume resync on all devices that may resync now + * drbd_resume_next() - Resume resync on all devices that may resync now * @device: DRBD device. * * Called from process context only (admin command and worker). */ -static int _drbd_resume_next(struct drbd_device *device) +static bool drbd_resume_next(struct drbd_device *device) { + bool changed = false; struct drbd_device *odev; - int i, rv = 0; + int i; rcu_read_lock(); idr_for_each_entry(&drbd_devices, odev, i) { if (odev->state.conn == C_STANDALONE && odev->state.disk == D_DISKLESS) continue; if (odev->state.aftr_isp) { - if (_drbd_may_sync_now(odev)) - rv |= (__drbd_set_state(_NS(odev, aftr_isp, 0), - CS_HARD, NULL) - != SS_NOTHING_TO_DO) ; + if (_drbd_may_sync_now(odev) && + _drbd_set_state(_NS(odev, aftr_isp, 0), + CS_HARD, NULL) != SS_NOTHING_TO_DO) + changed = true; } } rcu_read_unlock(); - return rv; + return changed; } void resume_next_sg(struct drbd_device *device) { - write_lock_irq(&global_state_lock); - _drbd_resume_next(device); - write_unlock_irq(&global_state_lock); + lock_all_resources(); + drbd_resume_next(device); + unlock_all_resources(); } void suspend_other_sg(struct drbd_device *device) { - write_lock_irq(&global_state_lock); - _drbd_pause_after(device); - write_unlock_irq(&global_state_lock); + lock_all_resources(); + drbd_pause_after(device); + unlock_all_resources(); } -/* caller must hold global_state_lock */ +/* caller must lock_all_resources() */ enum drbd_ret_code drbd_resync_after_valid(struct drbd_device *device, int o_minor) { struct drbd_device *odev; @@ -1557,15 +1567,15 @@ enum drbd_ret_code drbd_resync_after_valid(struct drbd_device *device, int o_min } } -/* caller must hold global_state_lock */ +/* caller must lock_all_resources() */ void drbd_resync_after_changed(struct drbd_device *device) { - int changes; + int changed; do { - changes = _drbd_pause_after(device); - changes |= _drbd_resume_next(device); - } while (changes); + changed = drbd_pause_after(device); + changed |= drbd_resume_next(device); + } while (changed); } void drbd_rs_controller_reset(struct drbd_device *device) @@ -1685,19 +1695,14 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side) } else { mutex_lock(device->state_mutex); } - clear_bit(B_RS_H_DONE, &device->flags); - /* req_lock: serialize with drbd_send_and_submit() and others - * global_state_lock: for stable sync-after dependencies */ - spin_lock_irq(&device->resource->req_lock); - write_lock(&global_state_lock); + lock_all_resources(); + clear_bit(B_RS_H_DONE, &device->flags); /* Did some connection breakage or IO error race with us? */ if (device->state.conn < C_CONNECTED || !get_ldev_if_state(device, D_NEGOTIATING)) { - write_unlock(&global_state_lock); - spin_unlock_irq(&device->resource->req_lock); - mutex_unlock(device->state_mutex); - return; + unlock_all_resources(); + goto out; } ns = drbd_read_state(device); @@ -1711,7 +1716,7 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side) else /* side == C_SYNC_SOURCE */ ns.pdsk = D_INCONSISTENT; - r = __drbd_set_state(device, ns, CS_VERBOSE, NULL); + r = _drbd_set_state(device, ns, CS_VERBOSE, NULL); ns = drbd_read_state(device); if (ns.conn < C_CONNECTED) @@ -1732,7 +1737,7 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side) device->rs_mark_left[i] = tw; device->rs_mark_time[i] = now; } - _drbd_pause_after(device); + drbd_pause_after(device); /* Forget potentially stale cached per resync extent bit-counts. * Open coded drbd_rs_cancel_all(device), we already have IRQs * disabled, and know the disk state is ok. */ @@ -1742,8 +1747,7 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side) device->resync_wenr = LC_FREE; spin_unlock(&device->al_lock); } - write_unlock(&global_state_lock); - spin_unlock_irq(&device->resource->req_lock); + unlock_all_resources(); if (r == SS_SUCCESS) { wake_up(&device->al_wait); /* for lc_reset() above */ @@ -1807,6 +1811,7 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side) drbd_md_sync(device); } put_ldev(device); +out: mutex_unlock(device->state_mutex); } @@ -1836,7 +1841,7 @@ static void drbd_ldev_destroy(struct drbd_device *device) device->act_log = NULL; __acquire(local); - drbd_free_ldev(device->ldev); + drbd_backing_dev_free(device, device->ldev); device->ldev = NULL; __release(local); |