diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-07 11:59:42 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-07 11:59:42 -0700 |
commit | a0725ab0c7536076d5477264420ef420ebb64501 (patch) | |
tree | 5c972d46c7f58f634ad74c6e4bc7a2bee24e5956 /drivers/block | |
parent | 3ee31b89d9b12c01aa03dda7a923ef07a800eedd (diff) | |
parent | ef13ecbc134d7e0ca4ab4834d08bd20885b53c62 (diff) |
Merge branch 'for-4.14/block' of git://git.kernel.dk/linux-block
Pull block layer updates from Jens Axboe:
"This is the first pull request for 4.14, containing most of the code
changes. It's a quiet series this round, which I think we needed after
the churn of the last few series. This contains:
- Fix for a registration race in loop, from Anton Volkov.
- Overflow complaint fix from Arnd for DAC960.
- Series of drbd changes from the usual suspects.
- Conversion of the stec/skd driver to blk-mq. From Bart.
- A few BFQ improvements/fixes from Paolo.
- CFQ improvement from Ritesh, allowing idling for group idle.
- A few fixes found by Dan's smatch, courtesy of Dan.
- A warning fixup for a race between changing the IO scheduler and
device remova. From David Jeffery.
- A few nbd fixes from Josef.
- Support for cgroup info in blktrace, from Shaohua.
- Also from Shaohua, new features in the null_blk driver to allow it
to actually hold data, among other things.
- Various corner cases and error handling fixes from Weiping Zhang.
- Improvements to the IO stats tracking for blk-mq from me. Can
drastically improve performance for fast devices and/or big
machines.
- Series from Christoph removing bi_bdev as being needed for IO
submission, in preparation for nvme multipathing code.
- Series from Bart, including various cleanups and fixes for switch
fall through case complaints"
* 'for-4.14/block' of git://git.kernel.dk/linux-block: (162 commits)
kernfs: checking for IS_ERR() instead of NULL
drbd: remove BIOSET_NEED_RESCUER flag from drbd_{md_,}io_bio_set
drbd: Fix allyesconfig build, fix recent commit
drbd: switch from kmalloc() to kmalloc_array()
drbd: abort drbd_start_resync if there is no connection
drbd: move global variables to drbd namespace and make some static
drbd: rename "usermode_helper" to "drbd_usermode_helper"
drbd: fix race between handshake and admin disconnect/down
drbd: fix potential deadlock when trying to detach during handshake
drbd: A single dot should be put into a sequence.
drbd: fix rmmod cleanup, remove _all_ debugfs entries
drbd: Use setup_timer() instead of init_timer() to simplify the code.
drbd: fix potential get_ldev/put_ldev refcount imbalance during attach
drbd: new disk-option disable-write-same
drbd: Fix resource role for newly created resources in events2
drbd: mark symbols static where possible
drbd: Send P_NEG_ACK upon write error in protocol != C
drbd: add explicit plugging when submitting batches
drbd: change list_for_each_safe to while(list_first_entry_or_null)
drbd: introduce drbd_recv_header_maybe_unplug
...
Diffstat (limited to 'drivers/block')
28 files changed, 2404 insertions, 2672 deletions
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index 245a879b036e..255591ab3716 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -1678,9 +1678,12 @@ static bool DAC960_V1_ReadControllerConfiguration(DAC960_Controller_T Enquiry2->FirmwareID.FirmwareType = '0'; Enquiry2->FirmwareID.TurnID = 0; } - sprintf(Controller->FirmwareVersion, "%d.%02d-%c-%02d", - Enquiry2->FirmwareID.MajorVersion, Enquiry2->FirmwareID.MinorVersion, - Enquiry2->FirmwareID.FirmwareType, Enquiry2->FirmwareID.TurnID); + snprintf(Controller->FirmwareVersion, sizeof(Controller->FirmwareVersion), + "%d.%02d-%c-%02d", + Enquiry2->FirmwareID.MajorVersion, + Enquiry2->FirmwareID.MinorVersion, + Enquiry2->FirmwareID.FirmwareType, + Enquiry2->FirmwareID.TurnID); if (!((Controller->FirmwareVersion[0] == '5' && strcmp(Controller->FirmwareVersion, "5.06") >= 0) || (Controller->FirmwareVersion[0] == '4' && @@ -6588,7 +6591,8 @@ static void DAC960_CreateProcEntries(DAC960_Controller_T *Controller) &dac960_proc_fops); } - sprintf(Controller->ControllerName, "c%d", Controller->ControllerNumber); + snprintf(Controller->ControllerName, sizeof(Controller->ControllerName), + "c%d", Controller->ControllerNumber); ControllerProcEntry = proc_mkdir(Controller->ControllerName, DAC960_ProcDirectoryEntry); proc_create_data("initial_status", 0, ControllerProcEntry, &dac960_initial_status_proc_fops, Controller); diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 80aaf3420e12..104180e3c55e 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -17,6 +17,7 @@ if BLK_DEV config BLK_DEV_NULL_BLK tristate "Null test block driver" + depends on CONFIGFS_FS config BLK_DEV_FD tristate "Normal floppy disk support" diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 5d9ed0616413..bbd0d186cfc0 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -294,14 +294,13 @@ out: static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio) { - struct block_device *bdev = bio->bi_bdev; - struct brd_device *brd = bdev->bd_disk->private_data; + struct brd_device *brd = bio->bi_disk->private_data; struct bio_vec bvec; sector_t sector; struct bvec_iter iter; sector = bio->bi_iter.bi_sector; - if (bio_end_sector(bio) > get_capacity(bdev->bd_disk)) + if (bio_end_sector(bio) > get_capacity(bio->bi_disk)) goto io_error; bio_for_each_segment(bvec, bio, iter) { diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index e02c45cd3c5a..5f0eaee8c8a7 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -151,7 +151,7 @@ static int _drbd_md_sync_page_io(struct drbd_device *device, op_flags |= REQ_SYNC; bio = bio_alloc_drbd(GFP_NOIO); - bio->bi_bdev = bdev->md_bdev; + bio_set_dev(bio, bdev->md_bdev); bio->bi_iter.bi_sector = sector; err = -EIO; if (bio_add_page(bio, device->md_io.page, size, 0) != size) diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 809fd245c3dc..bd97908c766f 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -1019,7 +1019,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho bm_store_page_idx(page, page_nr); } else page = b->bm_pages[page_nr]; - bio->bi_bdev = device->ldev->md_bdev; + bio_set_dev(bio, device->ldev->md_bdev); bio->bi_iter.bi_sector = on_disk_sector; /* bio_add_page of a single page to an empty bio will always succeed, * according to api. Do we want to assert that? */ diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index d17b6e6393c7..7e8589ce631c 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -63,19 +63,15 @@ # define __must_hold(x) #endif -/* module parameter, defined in drbd_main.c */ -extern unsigned int minor_count; -extern bool disable_sendpage; -extern bool allow_oos; -void tl_abort_disk_io(struct drbd_device *device); - +/* shared module parameters, defined in drbd_main.c */ #ifdef CONFIG_DRBD_FAULT_INJECTION -extern int enable_faults; -extern int fault_rate; -extern int fault_devs; +extern int drbd_enable_faults; +extern int drbd_fault_rate; #endif -extern char usermode_helper[]; +extern unsigned int drbd_minor_count; +extern char drbd_usermode_helper[]; +extern int drbd_proc_details; /* This is used to stop/restart our threads. @@ -181,8 +177,8 @@ _drbd_insert_fault(struct drbd_device *device, unsigned int type); static inline int drbd_insert_fault(struct drbd_device *device, unsigned int type) { #ifdef CONFIG_DRBD_FAULT_INJECTION - return fault_rate && - (enable_faults & (1<<type)) && + return drbd_fault_rate && + (drbd_enable_faults & (1<<type)) && _drbd_insert_fault(device, type); #else return 0; @@ -745,6 +741,8 @@ struct drbd_connection { unsigned current_tle_writes; /* writes seen within this tl epoch */ unsigned long last_reconnect_jif; + /* empty member on older kernels without blk_start_plug() */ + struct blk_plug receiver_plug; struct drbd_thread receiver; struct drbd_thread worker; struct drbd_thread ack_receiver; @@ -1131,7 +1129,8 @@ extern void conn_send_sr_reply(struct drbd_connection *connection, enum drbd_sta extern int drbd_send_rs_deallocated(struct drbd_peer_device *, struct drbd_peer_request *); 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); +extern void drbd_print_uuids(struct drbd_device *device, const char *text); +extern void drbd_queue_unplug(struct drbd_device *device); extern void conn_md_sync(struct drbd_connection *connection); extern void drbd_md_write(struct drbd_device *device, void *buffer); @@ -1463,8 +1462,6 @@ extern struct drbd_resource *drbd_find_resource(const char *name); extern void drbd_destroy_resource(struct kref *kref); extern void conn_free_crypto(struct drbd_connection *connection); -extern int proc_details; - /* drbd_req */ extern void do_submit(struct work_struct *ws); extern void __drbd_make_request(struct drbd_device *, struct bio *, unsigned long); @@ -1628,8 +1625,8 @@ static inline void drbd_generic_make_request(struct drbd_device *device, int fault_type, struct bio *bio) { __release(local); - if (!bio->bi_bdev) { - drbd_err(device, "drbd_generic_make_request: bio->bi_bdev == NULL\n"); + if (!bio->bi_disk) { + drbd_err(device, "drbd_generic_make_request: bio->bi_disk == NULL\n"); bio->bi_status = BLK_STS_IOERR; bio_endio(bio); return; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index e2ed28d45ce1..8cb3791898ae 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -77,41 +77,41 @@ MODULE_PARM_DESC(minor_count, "Approximate number of drbd devices (" MODULE_ALIAS_BLOCKDEV_MAJOR(DRBD_MAJOR); #include <linux/moduleparam.h> -/* allow_open_on_secondary */ -MODULE_PARM_DESC(allow_oos, "DONT USE!"); /* thanks to these macros, if compiled into the kernel (not-module), - * this becomes the boot parameter drbd.minor_count */ -module_param(minor_count, uint, 0444); -module_param(disable_sendpage, bool, 0644); -module_param(allow_oos, bool, 0); -module_param(proc_details, int, 0644); + * these become boot parameters (e.g., drbd.minor_count) */ #ifdef CONFIG_DRBD_FAULT_INJECTION -int enable_faults; -int fault_rate; -static int fault_count; -int fault_devs; +int drbd_enable_faults; +int drbd_fault_rate; +static int drbd_fault_count; +static int drbd_fault_devs; /* bitmap of enabled faults */ -module_param(enable_faults, int, 0664); +module_param_named(enable_faults, drbd_enable_faults, int, 0664); /* fault rate % value - applies to all enabled faults */ -module_param(fault_rate, int, 0664); +module_param_named(fault_rate, drbd_fault_rate, int, 0664); /* count of faults inserted */ -module_param(fault_count, int, 0664); +module_param_named(fault_count, drbd_fault_count, int, 0664); /* bitmap of devices to insert faults on */ -module_param(fault_devs, int, 0644); +module_param_named(fault_devs, drbd_fault_devs, int, 0644); #endif -/* module parameter, defined */ -unsigned int minor_count = DRBD_MINOR_COUNT_DEF; -bool disable_sendpage; -bool allow_oos; -int proc_details; /* Detail level in proc drbd*/ - +/* module parameters we can keep static */ +static bool drbd_allow_oos; /* allow_open_on_secondary */ +static bool drbd_disable_sendpage; +MODULE_PARM_DESC(allow_oos, "DONT USE!"); +module_param_named(allow_oos, drbd_allow_oos, bool, 0); +module_param_named(disable_sendpage, drbd_disable_sendpage, bool, 0644); + +/* module parameters we share */ +int drbd_proc_details; /* Detail level in proc drbd*/ +module_param_named(proc_details, drbd_proc_details, int, 0644); +/* module parameters shared with defaults */ +unsigned int drbd_minor_count = DRBD_MINOR_COUNT_DEF; /* Module parameter for setting the user mode helper program * to run. Default is /sbin/drbdadm */ -char usermode_helper[80] = "/sbin/drbdadm"; - -module_param_string(usermode_helper, usermode_helper, sizeof(usermode_helper), 0644); +char drbd_usermode_helper[80] = "/sbin/drbdadm"; +module_param_named(minor_count, drbd_minor_count, uint, 0444); +module_param_string(usermode_helper, drbd_usermode_helper, sizeof(drbd_usermode_helper), 0644); /* in 2.6.x, our device mapping and config info contains our virtual gendisks * as member "struct gendisk *vdisk;" @@ -923,7 +923,9 @@ void drbd_gen_and_send_sync_uuid(struct drbd_peer_device *peer_device) } /* communicated if (agreed_features & DRBD_FF_WSAME) */ -void assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, struct request_queue *q) +static void +assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, + struct request_queue *q) { if (q) { p->qlim->physical_block_size = cpu_to_be32(queue_physical_block_size(q)); @@ -1560,7 +1562,7 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa * put_page(); and would cause either a VM_BUG directly, or * __page_cache_release a page that would actually still be referenced * by someone, leading to some obscure delayed Oops somewhere else. */ - if (disable_sendpage || (page_count(page) < 1) || PageSlab(page)) + if (drbd_disable_sendpage || (page_count(page) < 1) || PageSlab(page)) return _drbd_no_send_page(peer_device, page, offset, size, msg_flags); msg_flags |= MSG_NOSIGNAL; @@ -1932,7 +1934,7 @@ static int drbd_open(struct block_device *bdev, fmode_t mode) if (device->state.role != R_PRIMARY) { if (mode & FMODE_WRITE) rv = -EROFS; - else if (!allow_oos) + else if (!drbd_allow_oos) rv = -EMEDIUMTYPE; } @@ -1952,6 +1954,19 @@ static void drbd_release(struct gendisk *gd, fmode_t mode) mutex_unlock(&drbd_main_mutex); } +/* need to hold resource->req_lock */ +void drbd_queue_unplug(struct drbd_device *device) +{ + if (device->state.pdsk >= D_INCONSISTENT && device->state.conn >= C_CONNECTED) { + D_ASSERT(device, device->state.role == R_PRIMARY); + if (test_and_clear_bit(UNPLUG_REMOTE, &device->flags)) { + drbd_queue_work_if_unqueued( + &first_peer_device(device)->connection->sender_work, + &device->unplug_work); + } + } +} + static void drbd_set_defaults(struct drbd_device *device) { /* Beware! The actual layout differs @@ -2008,18 +2023,14 @@ void drbd_init_set_defaults(struct drbd_device *device) device->unplug_work.cb = w_send_write_hint; device->bm_io_work.w.cb = w_bitmap_io; - init_timer(&device->resync_timer); - init_timer(&device->md_sync_timer); - init_timer(&device->start_resync_timer); - init_timer(&device->request_timer); - device->resync_timer.function = resync_timer_fn; - device->resync_timer.data = (unsigned long) device; - device->md_sync_timer.function = md_sync_timer_fn; - device->md_sync_timer.data = (unsigned long) device; - device->start_resync_timer.function = start_resync_timer_fn; - device->start_resync_timer.data = (unsigned long) device; - device->request_timer.function = request_timer_fn; - device->request_timer.data = (unsigned long) device; + setup_timer(&device->resync_timer, resync_timer_fn, + (unsigned long)device); + setup_timer(&device->md_sync_timer, md_sync_timer_fn, + (unsigned long)device); + setup_timer(&device->start_resync_timer, start_resync_timer_fn, + (unsigned long)device); + setup_timer(&device->request_timer, request_timer_fn, + (unsigned long)device); init_waitqueue_head(&device->misc_wait); init_waitqueue_head(&device->state_wait); @@ -2131,7 +2142,7 @@ static void drbd_destroy_mempools(void) static int drbd_create_mempools(void) { struct page *page; - const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * minor_count; + const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count; int i; /* prepare our caches and mempools */ @@ -2167,13 +2178,12 @@ static int drbd_create_mempools(void) goto Enomem; /* mempools */ - drbd_io_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_RESCUER); + drbd_io_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0); if (drbd_io_bio_set == NULL) goto Enomem; drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0, - BIOSET_NEED_BVECS | - BIOSET_NEED_RESCUER); + BIOSET_NEED_BVECS); if (drbd_md_io_bio_set == NULL) goto Enomem; @@ -2409,7 +2419,6 @@ static void drbd_cleanup(void) destroy_workqueue(retry.wq); drbd_genl_unregister(); - drbd_debugfs_cleanup(); idr_for_each_entry(&drbd_devices, device, i) drbd_delete_device(device); @@ -2420,6 +2429,8 @@ static void drbd_cleanup(void) drbd_free_resource(resource); } + drbd_debugfs_cleanup(); + drbd_destroy_mempools(); unregister_blkdev(DRBD_MAJOR, "drbd"); @@ -2972,12 +2983,12 @@ static int __init drbd_init(void) { int err; - if (minor_count < DRBD_MINOR_COUNT_MIN || minor_count > DRBD_MINOR_COUNT_MAX) { - pr_err("invalid minor_count (%d)\n", minor_count); + if (drbd_minor_count < DRBD_MINOR_COUNT_MIN || drbd_minor_count > DRBD_MINOR_COUNT_MAX) { + pr_err("invalid minor_count (%d)\n", drbd_minor_count); #ifdef MODULE return -EINVAL; #else - minor_count = DRBD_MINOR_COUNT_DEF; + drbd_minor_count = DRBD_MINOR_COUNT_DEF; #endif } @@ -3900,12 +3911,12 @@ _drbd_insert_fault(struct drbd_device *device, unsigned int type) static struct fault_random_state rrs = {0, 0}; unsigned int ret = ( - (fault_devs == 0 || - ((1 << device_to_minor(device)) & fault_devs) != 0) && - (((_drbd_fault_random(&rrs) % 100) + 1) <= fault_rate)); + (drbd_fault_devs == 0 || + ((1 << device_to_minor(device)) & drbd_fault_devs) != 0) && + (((_drbd_fault_random(&rrs) % 100) + 1) <= drbd_fault_rate)); if (ret) { - fault_count++; + drbd_fault_count++; if (__ratelimit(&drbd_ratelimit_state)) drbd_warn(device, "***Simulating %s failure\n", diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index ad0fcb43e45c..a12f77e6891e 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -344,7 +344,7 @@ int drbd_khelper(struct drbd_device *device, char *cmd) (char[60]) { }, /* address */ NULL }; char mb[14]; - char *argv[] = {usermode_helper, cmd, mb, NULL }; + char *argv[] = {drbd_usermode_helper, cmd, mb, NULL }; struct drbd_connection *connection = first_peer_device(device)->connection; struct sib_info sib; int ret; @@ -359,19 +359,19 @@ int drbd_khelper(struct drbd_device *device, char *cmd) * write out any unsynced meta data changes now */ drbd_md_sync(device); - drbd_info(device, "helper command: %s %s %s\n", usermode_helper, cmd, mb); + drbd_info(device, "helper command: %s %s %s\n", drbd_usermode_helper, cmd, mb); 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); + ret = call_usermodehelper(drbd_usermode_helper, argv, envp, UMH_WAIT_PROC); if (ret) drbd_warn(device, "helper command: %s %s %s exit code %u (0x%x)\n", - usermode_helper, cmd, mb, + drbd_usermode_helper, cmd, mb, (ret >> 8) & 0xff, ret); else drbd_info(device, "helper command: %s %s %s exit code %u (0x%x)\n", - usermode_helper, cmd, mb, + drbd_usermode_helper, cmd, mb, (ret >> 8) & 0xff, ret); sib.sib_reason = SIB_HELPER_POST; sib.helper_exit_code = ret; @@ -396,24 +396,24 @@ enum drbd_peer_state conn_khelper(struct drbd_connection *connection, char *cmd) (char[60]) { }, /* address */ NULL }; char *resource_name = connection->resource->name; - char *argv[] = {usermode_helper, cmd, resource_name, NULL }; + char *argv[] = {drbd_usermode_helper, cmd, resource_name, NULL }; int ret; setup_khelper_env(connection, envp); conn_md_sync(connection); - drbd_info(connection, "helper command: %s %s %s\n", usermode_helper, cmd, resource_name); + drbd_info(connection, "helper command: %s %s %s\n", drbd_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); + ret = call_usermodehelper(drbd_usermode_helper, argv, envp, UMH_WAIT_PROC); if (ret) drbd_warn(connection, "helper command: %s %s %s exit code %u (0x%x)\n", - usermode_helper, cmd, resource_name, + drbd_usermode_helper, cmd, resource_name, (ret >> 8) & 0xff, ret); else drbd_info(connection, "helper command: %s %s %s exit code %u (0x%x)\n", - usermode_helper, cmd, resource_name, + drbd_usermode_helper, cmd, resource_name, (ret >> 8) & 0xff, ret); /* TODO: conn_bcast_event() ?? */ notify_helper(NOTIFY_RESPONSE, NULL, connection, cmd, ret); @@ -1236,12 +1236,18 @@ static void fixup_discard_if_not_supported(struct request_queue *q) static void decide_on_write_same_support(struct drbd_device *device, struct request_queue *q, - struct request_queue *b, struct o_qlim *o) + struct request_queue *b, struct o_qlim *o, + bool disable_write_same) { struct drbd_peer_device *peer_device = first_peer_device(device); struct drbd_connection *connection = peer_device->connection; bool can_do = b ? b->limits.max_write_same_sectors : true; + if (can_do && disable_write_same) { + can_do = false; + drbd_info(peer_device, "WRITE_SAME disabled by config\n"); + } + if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_WSAME)) { can_do = false; drbd_info(peer_device, "peer does not support WRITE_SAME\n"); @@ -1302,6 +1308,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi struct request_queue *b = NULL; struct disk_conf *dc; bool discard_zeroes_if_aligned = true; + bool disable_write_same = false; if (bdev) { b = bdev->backing_bdev->bd_disk->queue; @@ -1311,6 +1318,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi dc = rcu_dereference(device->ldev->disk_conf); max_segments = dc->max_bio_bvecs; discard_zeroes_if_aligned = dc->discard_zeroes_if_aligned; + disable_write_same = dc->disable_write_same; rcu_read_unlock(); blk_set_stacking_limits(&q->limits); @@ -1321,7 +1329,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS); blk_queue_segment_boundary(q, PAGE_SIZE-1); decide_on_discard_support(device, q, b, discard_zeroes_if_aligned); - decide_on_write_same_support(device, q, b, o); + decide_on_write_same_support(device, q, b, o, disable_write_same); if (b) { blk_queue_stack_limits(q, b); @@ -1612,7 +1620,8 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) if (write_ordering_changed(old_disk_conf, new_disk_conf)) drbd_bump_write_ordering(device->resource, NULL, WO_BDEV_FLUSH); - if (old_disk_conf->discard_zeroes_if_aligned != new_disk_conf->discard_zeroes_if_aligned) + if (old_disk_conf->discard_zeroes_if_aligned != new_disk_conf->discard_zeroes_if_aligned + || old_disk_conf->disable_write_same != new_disk_conf->disable_write_same) drbd_reconsider_queue_parameters(device, device->ldev, NULL); drbd_md_sync(device); @@ -2140,34 +2149,13 @@ 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) { set_bit(FORCE_DETACH, &device->flags); drbd_force_state(device, NS(disk, D_FAILED)); - retcode = SS_SUCCESS; - goto out; + return SS_SUCCESS; } - drbd_suspend_io(device); /* so no-one is stuck in drbd_al_begin_io */ - 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); - if ((int)retcode == (int)SS_IS_DISKLESS) - retcode = SS_NOTHING_TO_DO; - if (ret) - retcode = ERR_INTR; -out: - return retcode; + return drbd_request_detach_interruptible(device); } /* Detaching the disk is a process in multiple stages. First we need to lock diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c index 8378142f7a55..582caeb0de86 100644 --- a/drivers/block/drbd/drbd_proc.c +++ b/drivers/block/drbd/drbd_proc.c @@ -127,7 +127,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se seq_putc(seq, '='); seq_putc(seq, '>'); for (i = 0; i < y; i++) - seq_printf(seq, "."); + seq_putc(seq, '.'); seq_puts(seq, "] "); if (state.conn == C_VERIFY_S || state.conn == C_VERIFY_T) @@ -179,7 +179,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se seq_printf_with_thousands_grouping(seq, dbdt); seq_puts(seq, " ("); /* ------------------------- ~3s average ------------------------ */ - if (proc_details >= 1) { + if (drbd_proc_details >= 1) { /* this is what drbd_rs_should_slow_down() uses */ i = (device->rs_last_mark + DRBD_SYNC_MARKS-1) % DRBD_SYNC_MARKS; dt = (jiffies - device->rs_mark_time[i]) / HZ; @@ -209,7 +209,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se } seq_printf(seq, " K/sec%s\n", stalled ? " (stalled)" : ""); - if (proc_details >= 1) { + if (drbd_proc_details >= 1) { /* 64 bit: * we convert to sectors in the display below. */ unsigned long bm_bits = drbd_bm_bits(device); @@ -332,13 +332,13 @@ static int drbd_seq_show(struct seq_file *seq, void *v) state.conn == C_VERIFY_T) drbd_syncer_progress(device, seq, state); - if (proc_details >= 1 && get_ldev_if_state(device, D_FAILED)) { + if (drbd_proc_details >= 1 && get_ldev_if_state(device, D_FAILED)) { lc_seq_printf_stats(seq, device->resync); lc_seq_printf_stats(seq, device->act_log); put_ldev(device); } - if (proc_details >= 2) + if (drbd_proc_details >= 2) seq_printf(seq, "\tblocked on activity log: %d\n", atomic_read(&device->ap_actlog_cnt)); } rcu_read_unlock(); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index c7e95e6380fb..796eaf347dc0 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -332,7 +332,7 @@ static void drbd_free_pages(struct drbd_device *device, struct page *page, int i if (page == NULL) return; - if (drbd_pp_vacant > (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * minor_count) + if (drbd_pp_vacant > (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count) i = page_chain_free(page); else { struct page *tmp; @@ -1100,7 +1100,10 @@ randomize: idr_for_each_entry(&connection->peer_devices, peer_device, vnr) mutex_lock(peer_device->device->state_mutex); + /* avoid a race with conn_request_state( C_DISCONNECTING ) */ + spin_lock_irq(&connection->resource->req_lock); set_bit(STATE_SENT, &connection->flags); + spin_unlock_irq(&connection->resource->req_lock); idr_for_each_entry(&connection->peer_devices, peer_device, vnr) mutex_unlock(peer_device->device->state_mutex); @@ -1194,6 +1197,14 @@ static int decode_header(struct drbd_connection *connection, void *header, struc return 0; } +static void drbd_unplug_all_devices(struct drbd_connection *connection) +{ + if (current->plug == &connection->receiver_plug) { + blk_finish_plug(&connection->receiver_plug); + blk_start_plug(&connection->receiver_plug); + } /* else: maybe just schedule() ?? */ +} + static int drbd_recv_header(struct drbd_connection *connection, struct packet_info *pi) { void *buffer = connection->data.rbuf; @@ -1209,6 +1220,36 @@ static int drbd_recv_header(struct drbd_connection *connection, struct packet_in return err; } +static int drbd_recv_header_maybe_unplug(struct drbd_connection *connection, struct packet_info *pi) +{ + void *buffer = connection->data.rbuf; + unsigned int size = drbd_header_size(connection); + int err; + + err = drbd_recv_short(connection->data.socket, buffer, size, MSG_NOSIGNAL|MSG_DONTWAIT); + if (err != size) { + /* If we have nothing in the receive buffer now, to reduce + * application latency, try to drain the backend queues as + * quickly as possible, and let remote TCP know what we have + * received so far. */ + if (err == -EAGAIN) { + drbd_tcp_quickack(connection->data.socket); + drbd_unplug_all_devices(connection); + } + if (err > 0) { + buffer += err; + size -= err; + } + err = drbd_recv_all_warn(connection, buffer, size); + if (err) + return err; + } + + err = decode_header(connection, connection->data.rbuf, pi); + connection->last_received = jiffies; + + return err; +} /* This is blkdev_issue_flush, but asynchronous. * We want to submit to all component volumes in parallel, * then wait for all completions. @@ -1223,7 +1264,7 @@ struct one_flush_context { struct issue_flush_context *ctx; }; -void one_flush_endio(struct bio *bio) +static void one_flush_endio(struct bio *bio) { struct one_flush_context *octx = bio->bi_private; struct drbd_device *device = octx->device; @@ -1265,7 +1306,7 @@ static void submit_one_flush(struct drbd_device *device, struct issue_flush_cont octx->device = device; octx->ctx = ctx; - bio->bi_bdev = device->ldev->backing_bdev; + bio_set_dev(bio, device->ldev->backing_bdev); bio->bi_private = octx; bio->bi_end_io = one_flush_endio; bio->bi_opf = REQ_OP_FLUSH | REQ_PREFLUSH; @@ -1548,7 +1589,7 @@ next_bio: } /* > peer_req->i.sector, unless this is the first bio */ bio->bi_iter.bi_sector = sector; - bio->bi_bdev = device->ldev->backing_bdev; + bio_set_dev(bio, device->ldev->backing_bdev); bio_set_op_attrs(bio, op, op_flags); bio->bi_private = peer_req; bio->bi_end_io = drbd_peer_req |