diff options
author | Stefan Agner <stefan.agner@toradex.com> | 2019-06-18 14:29:35 +0200 |
---|---|---|
committer | Stefan Agner <stefan.agner@toradex.com> | 2019-06-18 14:29:35 +0200 |
commit | d15d0b7a9f89cf5a905ad6802eb23100c8063939 (patch) | |
tree | 84caa660dc73842efa29e116dcb3e32aa81a5cf0 /drivers/block | |
parent | e9dcc568b2e968af848bbdb4267ba6cde5457b9e (diff) | |
parent | 858848641fbecd42437e36adc9291b0ce5db379e (diff) |
Merge tag 'v4.19.50-rt22' into toradex_4.19.y-rt
Linux 4.19.50-rt22
Diffstat (limited to 'drivers/block')
-rw-r--r-- | drivers/block/brd.c | 7 | ||||
-rw-r--r-- | drivers/block/drbd/drbd_nl.c | 15 | ||||
-rw-r--r-- | drivers/block/drbd/drbd_receiver.c | 13 | ||||
-rw-r--r-- | drivers/block/floppy.c | 2 | ||||
-rw-r--r-- | drivers/block/loop.c | 463 | ||||
-rw-r--r-- | drivers/block/loop.h | 1 | ||||
-rw-r--r-- | drivers/block/nbd.c | 5 | ||||
-rw-r--r-- | drivers/block/rbd.c | 9 | ||||
-rw-r--r-- | drivers/block/sunvdc.c | 5 | ||||
-rw-r--r-- | drivers/block/swim3.c | 6 | ||||
-rw-r--r-- | drivers/block/virtio_blk.c | 2 | ||||
-rw-r--r-- | drivers/block/xen-blkfront.c | 38 | ||||
-rw-r--r-- | drivers/block/xsysace.c | 2 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.c | 57 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.h | 2 |
15 files changed, 378 insertions, 249 deletions
diff --git a/drivers/block/brd.c b/drivers/block/brd.c index c18586fccb6f..17defbf4f332 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -96,13 +96,8 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector) /* * Must use NOIO because we don't want to recurse back into the * block or filesystem layers from page reclaim. - * - * Cannot support DAX and highmem, because our ->direct_access - * routine for DAX must return memory that is always addressable. - * If DAX was reworked to use pfns and kmap throughout, this - * restriction might be able to be lifted. */ - gfp_flags = GFP_NOIO | __GFP_ZERO; + gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM; page = alloc_page(gfp_flags); if (!page) return NULL; diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index b4f02768ba47..319fabdd63a3 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -668,14 +668,15 @@ drbd_set_role(struct drbd_device *const device, enum drbd_role new_role, int for if (rv == SS_TWO_PRIMARIES) { /* Maybe the peer is detected as dead very soon... retry at most once more in this case. */ - int timeo; - rcu_read_lock(); - nc = rcu_dereference(connection->net_conf); - timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1; - rcu_read_unlock(); - schedule_timeout_interruptible(timeo); - if (try < max_tries) + if (try < max_tries) { + int timeo; try = max_tries - 1; + rcu_read_lock(); + nc = rcu_dereference(connection->net_conf); + timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1; + rcu_read_unlock(); + schedule_timeout_interruptible(timeo); + } continue; } if (rv < SS_SUCCESS) { diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 75f6b47169e6..cb919b964066 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -3364,7 +3364,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device, enum drbd_conns rv = C_MASK; enum drbd_disk_state mydisk; struct net_conf *nc; - int hg, rule_nr, rr_conflict, tentative; + int hg, rule_nr, rr_conflict, tentative, always_asbp; mydisk = device->state.disk; if (mydisk == D_NEGOTIATING) @@ -3415,8 +3415,12 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device, rcu_read_lock(); nc = rcu_dereference(peer_device->connection->net_conf); + always_asbp = nc->always_asbp; + rr_conflict = nc->rr_conflict; + tentative = nc->tentative; + rcu_read_unlock(); - if (hg == 100 || (hg == -100 && nc->always_asbp)) { + if (hg == 100 || (hg == -100 && always_asbp)) { int pcount = (device->state.role == R_PRIMARY) + (peer_role == R_PRIMARY); int forced = (hg == -100); @@ -3455,9 +3459,6 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device, "Sync from %s node\n", (hg < 0) ? "peer" : "this"); } - rr_conflict = nc->rr_conflict; - tentative = nc->tentative; - rcu_read_unlock(); if (hg == -100) { /* FIXME this log message is not correct if we end up here @@ -4141,7 +4142,7 @@ static int receive_uuids(struct drbd_connection *connection, struct packet_info kfree(device->p_uuid); device->p_uuid = p_uuid; - if (device->state.conn < C_CONNECTED && + if ((device->state.conn < C_CONNECTED || device->state.pdsk == D_DISKLESS) && device->state.disk < D_INCONSISTENT && device->state.role == R_PRIMARY && (device->ed_uuid & ~((u64)1)) != (p_uuid[UI_CURRENT] & ~((u64)1))) { diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index fdabd0b74492..a8de56f1936d 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4084,7 +4084,7 @@ static unsigned int floppy_check_events(struct gendisk *disk, if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) { if (lock_fdc(drive)) - return -EINTR; + return 0; poll_drive(false, 0); process_fd_request(); } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ea9debf59b22..f1e63eb7cbca 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -83,7 +83,7 @@ #include <linux/uaccess.h> static DEFINE_IDR(loop_index_idr); -static DEFINE_MUTEX(loop_index_mutex); +static DEFINE_MUTEX(loop_ctl_mutex); static int max_part; static int part_shift; @@ -631,18 +631,7 @@ static void loop_reread_partitions(struct loop_device *lo, { int rc; - /* - * bd_mutex has been held already in release path, so don't - * acquire it if this function is called in such case. - * - * If the reread partition isn't from release path, lo_refcnt - * must be at least one and it can only become zero when the - * current holder is released. - */ - if (!atomic_read(&lo->lo_refcnt)) - rc = __blkdev_reread_part(bdev); - else - rc = blkdev_reread_part(bdev); + rc = blkdev_reread_part(bdev); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); @@ -668,7 +657,7 @@ static int loop_validate_file(struct file *file, struct block_device *bdev) return -EBADF; l = f->f_mapping->host->i_bdev->bd_disk->private_data; - if (l->lo_state == Lo_unbound) { + if (l->lo_state != Lo_bound) { return -EINVAL; } f = l->lo_backing_file; @@ -689,26 +678,30 @@ static int loop_validate_file(struct file *file, struct block_device *bdev) static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, unsigned int arg) { - struct file *file, *old_file; + struct file *file = NULL, *old_file; int error; + bool partscan; + error = mutex_lock_killable(&loop_ctl_mutex); + if (error) + return error; error = -ENXIO; if (lo->lo_state != Lo_bound) - goto out; + goto out_err; /* the loop device has to be read-only */ error = -EINVAL; if (!(lo->lo_flags & LO_FLAGS_READ_ONLY)) - goto out; + goto out_err; error = -EBADF; file = fget(arg); if (!file) - goto out; + goto out_err; error = loop_validate_file(file, bdev); if (error) - goto out_putf; + goto out_err; old_file = lo->lo_backing_file; @@ -716,7 +709,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, /* size of the new backing store needs to be the same */ if (get_loop_size(lo, file) != get_loop_size(lo, old_file)) - goto out_putf; + goto out_err; /* and ... switch */ blk_mq_freeze_queue(lo->lo_queue); @@ -727,15 +720,22 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue); - + partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; + mutex_unlock(&loop_ctl_mutex); + /* + * We must drop file reference outside of loop_ctl_mutex as dropping + * the file ref can take bd_mutex which creates circular locking + * dependency. + */ fput(old_file); - if (lo->lo_flags & LO_FLAGS_PARTSCAN) + if (partscan) loop_reread_partitions(lo, bdev); return 0; - out_putf: - fput(file); - out: +out_err: + mutex_unlock(&loop_ctl_mutex); + if (file) + fput(file); return error; } @@ -910,6 +910,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, int lo_flags = 0; int error; loff_t size; + bool partscan; /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); @@ -919,13 +920,17 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!file) goto out; + error = mutex_lock_killable(&loop_ctl_mutex); + if (error) + goto out_putf; + error = -EBUSY; if (lo->lo_state != Lo_unbound) - goto out_putf; + goto out_unlock; error = loop_validate_file(file, bdev); if (error) - goto out_putf; + goto out_unlock; mapping = file->f_mapping; inode = mapping->host; @@ -937,10 +942,10 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, error = -EFBIG; size = get_loop_size(lo, file); if ((loff_t)(sector_t)size != size) - goto out_putf; + goto out_unlock; error = loop_prepare_queue(lo); if (error) - goto out_putf; + goto out_unlock; error = 0; @@ -972,18 +977,22 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, lo->lo_state = Lo_bound; if (part_shift) lo->lo_flags |= LO_FLAGS_PARTSCAN; - if (lo->lo_flags & LO_FLAGS_PARTSCAN) - loop_reread_partitions(lo, bdev); + partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; /* Grab the block_device to prevent its destruction after we - * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev). + * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev). */ bdgrab(bdev); + mutex_unlock(&loop_ctl_mutex); + if (partscan) + loop_reread_partitions(lo, bdev); return 0; - out_putf: +out_unlock: + mutex_unlock(&loop_ctl_mutex); +out_putf: fput(file); - out: +out: /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return error; @@ -1026,39 +1035,31 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer, return err; } -static int loop_clr_fd(struct loop_device *lo) +static int __loop_clr_fd(struct loop_device *lo, bool release) { - struct file *filp = lo->lo_backing_file; + struct file *filp = NULL; gfp_t gfp = lo->old_gfp_mask; struct block_device *bdev = lo->lo_device; + int err = 0; + bool partscan = false; + int lo_number; - if (lo->lo_state != Lo_bound) - return -ENXIO; - - /* - * If we've explicitly asked to tear down the loop device, - * and it has an elevated reference count, set it for auto-teardown when - * the last reference goes away. This stops $!~#$@ udev from - * preventing teardown because it decided that it needs to run blkid on - * the loopback device whenever they appear. xfstests is notorious for - * failing tests because blkid via udev races with a losetup - * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d - * command to fail with EBUSY. - */ - if (atomic_read(&lo->lo_refcnt) > 1) { - lo->lo_flags |= LO_FLAGS_AUTOCLEAR; - mutex_unlock(&lo->lo_ctl_mutex); - return 0; + mutex_lock(&loop_ctl_mutex); + if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) { + err = -ENXIO; + goto out_unlock; } - if (filp == NULL) - return -EINVAL; + filp = lo->lo_backing_file; + if (filp == NULL) { + err = -EINVAL; + goto out_unlock; + } /* freeze request queue during the transition */ blk_mq_freeze_queue(lo->lo_queue); spin_lock_irq(&lo->lo_lock); - lo->lo_state = Lo_rundown; lo->lo_backing_file = NULL; spin_unlock_irq(&lo->lo_lock); @@ -1089,26 +1090,92 @@ static int loop_clr_fd(struct loop_device *lo) kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } mapping_set_gfp_mask(filp->f_mapping, gfp); - lo->lo_state = Lo_unbound; /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); blk_mq_unfreeze_queue(lo->lo_queue); - if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev) - loop_reread_partitions(lo, bdev); + partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev; + lo_number = lo->lo_number; + loop_unprepare_queue(lo); +out_unlock: + mutex_unlock(&loop_ctl_mutex); + if (partscan) { + /* + * bd_mutex has been held already in release path, so don't + * acquire it if this function is called in such case. + * + * If the reread partition isn't from release path, lo_refcnt + * must be at least one and it can only become zero when the + * current holder is released. + */ + if (release) + err = __blkdev_reread_part(bdev); + else + err = blkdev_reread_part(bdev); + if (err) + pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", + __func__, lo_number, err); + /* Device is gone, no point in returning error */ + err = 0; + } + + /* + * lo->lo_state is set to Lo_unbound here after above partscan has + * finished. + * + * There cannot be anybody else entering __loop_clr_fd() as + * lo->lo_backing_file is already cleared and Lo_rundown state + * protects us from all the other places trying to change the 'lo' + * device. + */ + mutex_lock(&loop_ctl_mutex); lo->lo_flags = 0; if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; - loop_unprepare_queue(lo); - mutex_unlock(&lo->lo_ctl_mutex); + lo->lo_state = Lo_unbound; + mutex_unlock(&loop_ctl_mutex); + /* - * Need not hold lo_ctl_mutex to fput backing file. - * Calling fput holding lo_ctl_mutex triggers a circular + * Need not hold loop_ctl_mutex to fput backing file. + * Calling fput holding loop_ctl_mutex triggers a circular * lock dependency possibility warning as fput can take - * bd_mutex which is usually taken before lo_ctl_mutex. + * bd_mutex which is usually taken before loop_ctl_mutex. */ - fput(filp); - return 0; + if (filp) + fput(filp); + return err; +} + +static int loop_clr_fd(struct loop_device *lo) +{ + int err; + + err = mutex_lock_killable(&loop_ctl_mutex); + if (err) + return err; + if (lo->lo_state != Lo_bound) { + mutex_unlock(&loop_ctl_mutex); + return -ENXIO; + } + /* + * If we've explicitly asked to tear down the loop device, + * and it has an elevated reference count, set it for auto-teardown when + * the last reference goes away. This stops $!~#$@ udev from + * preventing teardown because it decided that it needs to run blkid on + * the loopback device whenever they appear. xfstests is notorious for + * failing tests because blkid via udev races with a losetup + * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d + * command to fail with EBUSY. + */ + if (atomic_read(&lo->lo_refcnt) > 1) { + lo->lo_flags |= LO_FLAGS_AUTOCLEAR; + mutex_unlock(&loop_ctl_mutex); + return 0; + } + lo->lo_state = Lo_rundown; + mutex_unlock(&loop_ctl_mutex); + + return __loop_clr_fd(lo, false); } static int @@ -1117,47 +1184,72 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) int err; struct loop_func_table *xfer; kuid_t uid = current_uid(); + struct block_device *bdev; + bool partscan = false; + err = mutex_lock_killable(&loop_ctl_mutex); + if (err) + return err; if (lo->lo_encrypt_key_size && !uid_eq(lo->lo_key_owner, uid) && - !capable(CAP_SYS_ADMIN)) - return -EPERM; - if (lo->lo_state != Lo_bound) - return -ENXIO; - if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) - return -EINVAL; + !capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto out_unlock; + } + if (lo->lo_state != Lo_bound) { + err = -ENXIO; + goto out_unlock; + } + if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) { + err = -EINVAL; + goto out_unlock; + } + + if (lo->lo_offset != info->lo_offset || + lo->lo_sizelimit != info->lo_sizelimit) { + sync_blockdev(lo->lo_device); + kill_bdev(lo->lo_device); + } /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue); err = loop_release_xfer(lo); if (err) - goto exit; + goto out_unfreeze; if (info->lo_encrypt_type) { unsigned int type = info->lo_encrypt_type; if (type >= MAX_LO_CRYPT) { err = -EINVAL; - goto exit; + goto out_unfreeze; } xfer = xfer_funcs[type]; if (xfer == NULL) { err = -EINVAL; - goto exit; + goto out_unfreeze; } } else xfer = NULL; err = loop_init_xfer(lo, xfer, info); if (err) - goto exit; + goto out_unfreeze; if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { + /* kill_bdev should have truncated all the pages */ + if (lo->lo_device->bd_inode->i_mapping->nrpages) { + err = -EAGAIN; + pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", + __func__, lo->lo_number, lo->lo_file_name, + lo->lo_device->bd_inode->i_mapping->nrpages); + goto out_unfreeze; + } if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { err = -EFBIG; - goto exit; + goto out_unfreeze; } } @@ -1189,15 +1281,20 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) /* update dio if lo_offset or transfer is changed */ __loop_update_dio(lo, lo->use_dio); - exit: +out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) && !(lo->lo_flags & LO_FLAGS_PARTSCAN)) { lo->lo_flags |= LO_FLAGS_PARTSCAN; lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; - loop_reread_partitions(lo, lo->lo_device); + bdev = lo->lo_device; + partscan = true; } +out_unlock: + mutex_unlock(&loop_ctl_mutex); + if (partscan) + loop_reread_partitions(lo, bdev); return err; } @@ -1205,12 +1302,15 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) static int loop_get_status(struct loop_device *lo, struct loop_info64 *info) { - struct file *file; + struct path path; struct kstat stat; int ret; + ret = mutex_lock_killable(&loop_ctl_mutex); + if (ret) + return ret; if (lo->lo_state != Lo_bound) { - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return -ENXIO; } @@ -1229,17 +1329,17 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) lo->lo_encrypt_key_size); } - /* Drop lo_ctl_mutex while we call into the filesystem. */ - file = get_file(lo->lo_backing_file); - mutex_unlock(&lo->lo_ctl_mutex); - ret = vfs_getattr(&file->f_path, &stat, STATX_INO, - AT_STATX_SYNC_AS_STAT); + /* Drop loop_ctl_mutex while we call into the filesystem. */ + path = lo->lo_backing_file->f_path; + path_get(&path); + mutex_unlock(&loop_ctl_mutex); + ret = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); if (!ret) { info->lo_device = huge_encode_dev(stat.dev); info->lo_inode = stat.ino; info->lo_rdevice = huge_encode_dev(stat.rdev); } - fput(file); + path_put(&path); return ret; } @@ -1323,10 +1423,8 @@ loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) { struct loop_info64 info64; int err; - if (!arg) { - mutex_unlock(&lo->lo_ctl_mutex); + if (!arg) return -EINVAL; - } err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_old(&info64, &info); @@ -1341,10 +1439,8 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { struct loop_info64 info64; int err; - if (!arg) { - mutex_unlock(&lo->lo_ctl_mutex); + if (!arg) return -EINVAL; - } err = loop_get_status(lo, &info64); if (!err && copy_to_user(arg, &info64, sizeof(info64))) err = -EFAULT; @@ -1376,22 +1472,64 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg) static int loop_set_block_size(struct loop_device *lo, unsigned long arg) { + int err = 0; + if (lo->lo_state != Lo_bound) return -ENXIO; if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg)) return -EINVAL; + if (lo->lo_queue->limits.logical_block_size != arg) { + sync_blockdev(lo->lo_device); + kill_bdev(lo->lo_device); + } + blk_mq_freeze_queue(lo->lo_queue); + /* kill_bdev should have truncated all the pages */ + if (lo->lo_queue->limits.logical_block_size != arg && + lo->lo_device->bd_inode->i_mapping->nrpages) { + err = -EAGAIN; + pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", + __func__, lo->lo_number, lo->lo_file_name, + lo->lo_device->bd_inode->i_mapping->nrpages); + goto out_unfreeze; + } + blk_queue_logical_block_size(lo->lo_queue, arg); blk_queue_physical_block_size(lo->lo_queue, arg); blk_queue_io_min(lo->lo_queue, arg); loop_update_dio(lo); - +out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); - return 0; + return err; +} + +static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, + unsigned long arg) +{ + int err; + + err = mutex_lock_killable(&loop_ctl_mutex); + if (err) + return err; + switch (cmd) { + case LOOP_SET_CAPACITY: + err = loop_set_capacity(lo); + break; + case LOOP_SET_DIRECT_IO: + err = loop_set_dio(lo, arg); + break; + case LOOP_SET_BLOCK_SIZE: + err = loop_set_block_size(lo, arg); + break; + default: + err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; + } + mutex_unlock(&loop_ctl_mutex); + return err; } static int lo_ioctl(struct block_device *bdev, fmode_t mode, @@ -1400,64 +1538,42 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, struct loop_device *lo = bdev->bd_disk->private_data; int err; - err = mutex_lock_killable_nested(&lo->lo_ctl_mutex, 1); - if (err) - goto out_unlocked; - switch (cmd) { case LOOP_SET_FD: - err = loop_set_fd(lo, mode, bdev, arg); - break; + return loop_set_fd(lo, mode, bdev, arg); case LOOP_CHANGE_FD: - err = loop_change_fd(lo, bdev, arg); - break; + return loop_change_fd(lo, bdev, arg); case LOOP_CLR_FD: - /* loop_clr_fd would have unlocked lo_ctl_mutex on success */ - err = loop_clr_fd(lo); - if (!err) - goto out_unlocked; - break; + return loop_clr_fd(lo); case LOOP_SET_STATUS: err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) + if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { err = loop_set_status_old(lo, (struct loop_info __user *)arg); + } break; case LOOP_GET_STATUS: - err = loop_get_status_old(lo, (struct loop_info __user *) arg); - /* loop_get_status() unlocks lo_ctl_mutex */ - goto out_unlocked; + return loop_get_status_old(lo, (struct loop_info __user *) arg); case LOOP_SET_STATUS64: err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) + if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { err = loop_set_status64(lo, (struct loop_info64 __user *) arg); + } break; case LOOP_GET_STATUS64: - err = loop_get_status64(lo, (struct loop_info64 __user *) arg); - /* loop_get_status() unlocks lo_ctl_mutex */ - goto out_unlocked; + return loop_get_status64(lo, (struct loop_info64 __user *) arg); case LOOP_SET_CAPACITY: - err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_capacity(lo); - break; case LOOP_SET_DIRECT_IO: - err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_dio(lo, arg); - break; case LOOP_SET_BLOCK_SIZE: - err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_block_size(lo, arg); - break; + if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* Fall through */ default: - err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; + err = lo_simple_ioctl(lo, cmd, arg); + break; } - mutex_unlock(&lo->lo_ctl_mutex); -out_unlocked: return err; } @@ -1571,10 +1687,8 @@ loop_get_status_compat(struct loop_device *lo, struct loop_info64 info64; int err; - if (!arg) { - mutex_unlock(&lo->lo_ctl_mutex); + if (!arg) return -EINVAL; - } err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_compat(&info64, arg); @@ -1589,20 +1703,12 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, switch(cmd) { case LOOP_SET_STATUS: - err = mutex_lock_killable(&lo->lo_ctl_mutex); - if (!err) { - err = loop_set_status_compat(lo, - (const struct compat_loop_info __user *)arg); - mutex_unlock(&lo->lo_ctl_mutex); - } + err = loop_set_status_compat(lo, + (const struct compat_loop_info __user *)arg); break; case LOOP_GET_STATUS: - err = mutex_lock_killable(&lo->lo_ctl_mutex); - if (!err) { - err = loop_get_status_compat(lo, - (struct compat_loop_info __user *)arg); - /* loop_get_status() unlocks lo_ctl_mutex */ - } + err = loop_get_status_compat(lo, + (struct compat_loop_info __user *)arg); break; case LOOP_SET_CAPACITY: case LOOP_CLR_FD: @@ -1626,9 +1732,11 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, static int lo_open(struct block_device *bdev, fmode_t mode) { struct loop_device *lo; - int err = 0; + int err; - mutex_lock(&loop_index_mutex); + err = mutex_lock_killable(&loop_ctl_mutex); + if (err) + return err; lo = bdev->bd_disk->private_data; if (!lo) { err = -ENXIO; @@ -1637,26 +1745,30 @@ static int lo_open(struct block_device *bdev, fmode_t mode) atomic_inc(&lo->lo_refcnt); out: - mutex_unlock(&loop_index_mutex); + mutex_unlock(&loop_ctl_mutex); return err; } -static void __lo_release(struct loop_device *lo) +static void lo_release(struct gendisk *disk, fmode_t mode) { - int err; + struct loop_device *lo; + mutex_lock(&loop_ctl_mutex); + lo = disk->private_data; if (atomic_dec_return(&lo->lo_refcnt)) - return; + goto out_unlock; - mutex_lock(&lo->lo_ctl_mutex); if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { + if (lo->lo_state != Lo_bound) + goto out_unlock; + lo->lo_state = Lo_rundown; + mutex_unlock(&loop_ctl_mutex); /* * In autoclear mode, stop the loop thread * and remove configuration after last close. */ - err = loop_clr_fd(lo); - if (!err) - return; + __loop_clr_fd(lo, true); + return; } else if (lo->lo_state == Lo_bound) { /* * Otherwise keep thread (if running) and config, @@ -1666,14 +1778,8 @@ static void __lo_release(struct loop_device *lo) blk_mq_unfreeze_queue(lo->lo_queue); } - mutex_unlock(&lo->lo_ctl_mutex); -} - -static void lo_release(struct gendisk *disk, fmode_t mode) -{ - mutex_lock(&loop_index_mutex); - __lo_release(disk->private_data); - mutex_unlock(&loop_index_mutex); +out_unlock: + mutex_unlock(&loop_ctl_mutex); } static const struct block_device_operations lo_fops = { @@ -1712,10 +1818,10 @@ static int unregister_transfer_cb(int id, void *ptr, void *data) struct loop_device *lo = ptr; struct loop_func_table *xfer = data; - mutex_lock(&lo->lo_ctl_mutex); + mutex_lock(&loop_ctl_mutex); if (lo->lo_encryption == xfer) loop_release_xfer(lo); - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return 0; } @@ -1896,7 +2002,6 @@ static int loop_add(struct loop_device **l, int i) if (!part_shift) disk->flags |= GENHD_FL_NO_PART_SCAN; disk->flags |= GENHD_FL_EXT_DEVT; - mutex_init(&lo->lo_ctl_mutex); atomic_set(&lo->lo_refcnt, 0); lo->lo_number = i; spin_lock_init(&lo->lo_lock); @@ -1975,7 +2080,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data) struct kobject *kobj; int err; - mutex_lock(&loop_index_mutex); + mutex_lock(&loop_ctl_mutex); err = loop_lookup(&lo, MINOR(dev) >> part_shift); if (err < 0) err = loop_add(&lo, MINOR(dev) >> part_shift); @@ -1983,7 +2088,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data) kobj = NULL; else kobj = get_disk_and_module(lo->lo_disk); - mutex_unlock(&loop_index_mutex); + mutex_unlock(&loop_ctl_mutex); *part = 0; return kobj; @@ -1993,9 +2098,13 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, unsigned long parm) { struct loop_device *lo; - int ret = -ENOSYS; + int ret; + + ret = mutex_lock_killable(&loop_ctl_mutex); + if (ret) + return ret; - mutex_lock(&loop_index_mutex); + ret = -ENOSYS; switch (cmd) { case LOOP_CTL_ADD: ret = loop_lookup(&lo, parm); @@ -2009,21 +2118,15 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, ret = loop_lookup(&lo, parm); if (ret < 0) break; - ret = mutex_lock_killable(&lo->lo_ctl_mutex); - if (ret) - break; if (lo->lo_state != Lo_unbound) { ret = -EBUSY; - mutex_unlock(&lo->lo_ctl_mutex); break; } if (atomic_read(&lo->lo_refcnt) > 0) { ret = -EBUSY; - mutex_unlock(&lo->lo_ctl_mutex); break; } lo->lo_disk->private_data = NULL; - mutex_unlock(&lo->lo_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); loop_remove(lo); break; @@ -2033,7 +2136,7 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, break; ret = loop_add(&lo, -1); } - mutex_unlock(&loop_index_mutex); + mutex_unlock(&loop_ctl_mutex); return ret; } @@ -2117,10 +2220,10 @@ static int __init loop_init(void) THIS_MODULE, loop_probe, NULL, NULL); /* pre-create number of devices given by config or max_loop */ - mutex_lock(&loop_index_mutex); + mutex_lock(&loop_ctl_mutex); for (i = 0; i < nr; i++) loop_add(&lo, i); - mutex_unlock(&loop_index_mutex); + mutex_unlock(&loop_ctl_mutex); printk(KERN_INFO "loop: module loaded\n"); return 0; diff --git a/drivers/block/loop.h b/drivers/block/loop.h index 4d42c7af7de7..af75a5ee4094 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -54,7 +54,6 @@ struct loop_device { spinlock_t lo_lock; int lo_state; - struct mutex lo_ctl_mutex; struct kthread_worker worker; struct task_struct *worker_task; bool use_dio; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 14a51254c3db..c13a6d1796a7 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -288,9 +288,10 @@ static void nbd_size_update(struct nbd_device *nbd) blk_queue_physical_block_size(nbd->disk->queue, config->blksize); set_capacity(nbd->disk, config->bytesize >> 9); if (bdev) { - if (bdev->bd_disk) + if (bdev->bd_disk) { bd_set_size(bdev, config->bytesize); - else + set_blocksize(bdev, config->blksize); + } else bdev->bd_invalidated = 1; bdput(bdev); } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 73ed5f3a862d..585378bc988c 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -5982,7 +5982,6 @@ static ssize_t do_rbd_remove(struct bus_type *bus, struct list_head *tmp; int dev_id; char opt_buf[6]; - bool already = false; bool force = false; int ret; @@ -6015,13 +6014,13 @@ static ssize_t do_rbd_remove(struct bus_type *bus, spin_lock_irq(&rbd_dev->lock); if (rbd_dev->open_count && !force) ret = -EBUSY; - else - already = test_and_set_bit(RBD_DEV_FLAG_REMOVING, - &rbd_dev->flags); + else if (test_and_set_bit(RBD_DEV_FLAG_REMOVING, + &rbd_dev->flags)) + ret = -EINPROGRESS; spin_unlock_irq(&rbd_dev->lock); } spin_unlock(&rbd_dev_list_lock); - if (ret < 0 || already) + if (ret) return ret; if (force) { diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index f68e9baffad7..5d7024057540 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -45,6 +45,8 @@ MODULE_VERSION(DRV_MODULE_VERSION); #define WAITING_FOR_GEN_CMD 0x04 #define WAITING_FOR_ANY -1 +#define VDC_MAX_RETRIES 10 + static struct workqueue_struct *sunvdc_wq; struct vdc_req_entry { @@ -431,6 +433,7 @@ static int __vdc_tx_trigger(struct vdc_port *port) .end_idx = dr->prod, }; int err, delay; + int retries = 0; hdr.seq = dr->snd_nxt; delay = 1; @@ -443,6 +446,8 @@ static int __vdc_tx_trigger(struct vdc_port *port) udelay(delay); if ((delay <<= 1) > 128) delay = 128; + if (retries++ > VDC_MAX_RETRIES) + break; } while (err == -EAGAIN); if (err == -ENOTCONN) diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 469541c1e51e..20907a0a043b 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1026,7 +1026,11 @@ static void floppy_release(struct gendisk *disk, fmode_t mode) struct swim3 __iomem *sw = fs->swim3; mutex_lock(&swim3_mutex); - if (fs->ref_count > 0 && --fs->ref_count == 0) { + if (fs->ref_count > 0) + --fs->ref_count; + else if (fs->ref_count == -1) + fs->ref_count = 0; + if (fs->ref_count == 0) { swim3_action(fs, MOTOR_OFF); out_8(&sw->control_bic, 0xff); swim3_select(fs, RELAX); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 23752dc99b00..dd64f586679e 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -446,6 +446,8 @@ static int init_vq(struct virtio_blk *vblk) if (err) num_vqs = 1; + num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs); + vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL); if (!vblk->vqs) return -ENOMEM; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 3e905da33bcb..5830d9417886 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1310,11 +1310,11 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo) } free_shadow: - kfree(rinfo->shadow[i].grants_used); + kvfree(rinfo->shadow[i].grants_used); rinfo->shadow[i].grants_used = NULL; - kfree(rinfo->shadow[i].indirect_grants); + kvfree(rinfo->shadow[i].indirect_grants); rinfo->shadow[i].indirect_grants = NULL; - kfree(rinfo->shadow[i].sg); + kvfree(rinfo->shadow[i].sg); rinfo->shadow[i].sg = NULL; } @@ -1353,7 +1353,7 @@ static void blkif_free(struct blkfront_info *info, int suspend) for (i = 0; i < info->nr_rings; i++) blkif_free_ring(&info->rinfo[i]); - kfree(info->rinfo); + kvfree(info->rinfo); info->rinfo = NULL; info->nr_rings = 0; } @@ -1914,9 +1914,9 @@ static int negotiate_mq(struct blkfront_info *info) if (!info->nr_rings) info->nr_rings = 1; - info->rinfo = kcalloc(info->nr_rings, - sizeof(struct blkfront_ring_info), - GFP_KERNEL); + info->rinfo = kvcalloc(info->nr_rings, + sizeof(struct blkfront_ring_info), + GFP_KERNEL); if (!info->rinfo) { xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure"); info->nr_rings = 0; @@ -2232,17 +2232,17 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) for (i = 0; i < BLK_RING_SIZE(info); i++) { rinfo->shadow[i].grants_used = - kcalloc(grants, - sizeof(rinfo->shadow[i].grants_used[0]), - GFP_NOIO); - rinfo->shadow[i].sg = kcalloc(psegs, - sizeof(rinfo->shadow[i].sg[0]), - GFP_NOIO); + kvcalloc(grants, + sizeof(rinfo->shadow[i].grants_used[0]), + GFP_NOIO); + rinfo->shadow[i].sg = kvcalloc(psegs, + sizeof(rinfo->shadow[i].sg[0]), + GFP_NOIO); if (info->max_indirect_segments) rinfo->shadow[i].indirect_grants = - kcalloc(INDIRECT_GREFS(grants), - sizeof(rinfo->shadow[i].indirect_grants[0]), - GFP_NOIO); + kvcalloc(INDIRECT_GREFS(grants), + sizeof(rinfo->shadow[i].indirect_grants[0]), + GFP_NOIO); if ((rinfo->shadow[i].grants_used == NULL) || (rinfo->shadow[i].sg == NULL) || (info->max_indirect_segments && @@ -2256,11 +2256,11 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) out_of_memory: for (i = 0; i < BLK_RING_SIZE(info); i++) { - kfree(rinfo->shadow[i].grants_used); + kvfree(rinfo->shadow[i].grants_used); rinfo->shadow[i].grants_used = NULL; - kfree(rinfo->shadow[i].sg); + kvfree(rinfo->shadow[i].sg); rinfo->shadow[i].sg = NULL; - kfree(rinfo->shadow[i].indirect_grants); + kvfree(rinfo->shadow[i].indirect_grants); rinfo->shadow[i].indirect_grants = NULL; } if (!list_empty(&rinfo->indirect_pages)) { diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index c24589414c75..0f36db0cf74a 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -1063,6 +1063,8 @@ static int ace_setup(struct ace_device *ace) return 0; err_read: + /* prevent double queue cleanup */ + ace->gd->queue = NULL; put_disk(ace->gd); err_alloc_disk: blk_cleanup_queue(ace->queue); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 7bc9240be628..ffa3e9d67571 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -62,6 +62,16 @@ static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) spin_lock_init(&zram->table[index].lock); } +static int zram_slot_trylock(struct zram *zram, u32 index) +{ + int ret; + + ret = spin_trylock(&zram->table[index].lock); + if (ret) + __set_bit(ZRAM_LOCK, &zram->table[index].value); + return ret; +} + static void zram_slot_lock(struct zram *zram, u32 index) { spin_lock(&zram->table[index].lock); @@ -77,6 +87,11 @@ static void zram_slot_unlock(struct zram *zram, u32 index) #else static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) { } +static int zram_slot_trylock(struct zram *zram, u32 index) +{ + return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].value); +} + static void zram_slot_lock(struct zram *zram, u32 index) { bit_spin_lock(ZRAM_LOCK, &zram->table[index].value); @@ -407,8 +422,10 @@ static ssize_t backing_dev_store(struct device *dev, bdev = bdgrab(I_BDEV(inode)); err = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram); - if (err < 0) + if (err < 0) { + bdev = NULL; goto out; + } nr_pages = i_size_read(inode) >> PAGE_SHIFT; bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long); @@ -424,7 +441,6 @@ static ssize_t backing_dev_store(struct device *dev, goto out; reset_bdev(zram); - spin_lock_init(&zram->bitmap_lock); zram->old_block_size = old_block_size; zram->bdev = bdev; @@ -468,29 +484,24 @@ out: static unsigned long get_entry_bdev(struct zram *zram) { - unsigned long entry; - - spin_lock(&zram->bitmap_lock); + unsigned long blk_idx = 1; +retry: /* skip 0 bit to confuse zram.handle = 0 */ - entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1); - if (entry == zram->nr_pages) { - spin_unlock(&zram->bitmap_lock); + blk_idx = find_next_zero_bit(zram->bitmap, zram->nr_pages, blk_idx); + if (blk_idx == zram->nr_pages) return 0; - } - set_bit(entry, zram->bitmap); - spin_unlock(&zram->bitmap_lock); + if (test_and_set_bit(blk_idx, zram->bitmap)) + goto retry; - return entry; + return blk_idx; } static void put_entry_bdev(struct zram *zram, unsigned long entry) { int was_set; - spin_lock(&zram->bitmap_lock); was_set = test_and_clear_bit(entry, zram->bitmap); - spin_unlock(&zram->bitmap_lock); WARN_ON_ONCE(!was_set); } @@ -539,18 +550,18 @@ struct zram_work { struct zram *zram; unsigned long entry; struct bio *bio; + struct bio_vec bvec; }; #if PAGE_SIZE != 4096 static void zram_sync_read(struct work_struct *work) { - struct bio_vec bvec; struct zram_work *zw = container_of(work, struct zram_work, work); struct zram *zram = zw->zram; unsigned long entry = zw->entry; struct bio *bio = zw->bio; - read_from_bdev_async(zram, &bvec, entry, bio); + read_from_bdev_async(zram, &zw->bvec, entry, bio); } /* @@ -563,6 +574,7 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, { struct zram_work work; + work.bvec = *bvec; work.zram = zram; work.entry = entry; work.bio = bio; @@ -911,9 +923,10 @@ static ssize_t debug_stat_show(struct device *dev, down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, - "version: %d\n%8llu\n", + "version: %d\n%8llu %8llu\n", version, - (u64)atomic64_read(&zram->stats.writestall)); + (u64)atomic64_read(&zram->stats.writestall), + (u64)atomic64_read(&zram->stats.miss_free)); up_read(&zram->init_lock); return ret; @@ -1429,10 +1442,14 @@ static void zram_slot_free_notify(struct block_device *bdev, zram = bdev->bd_disk->private_data; - zram_slot_lock(zram, index); + atomic64_inc(&zram->stats.notify_free); + if (!zram_slot_trylock(zram, index)) { + atomic64_inc(&zram->stats.miss_free); + return; + } + zram_free_page(zram, index); zram_slot_unlock(zram, index); - atomic64_inc(&zram->stats.notify_free); } static int zram_rw_page(struct block_device *bdev, sector_t sector, diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 1015c7574d54..144e91061df8 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -82,6 +82,7 @@ struct zram_stats { atomic64_t pages_stored; /* no. of pages currently stored */ atomic_long_t max_used_pages; /* no. of maximum pages stored */ atomic64_t writestall; /* no. of write slow paths */ + atomic64_t miss_free; /* no. of missed free */ }; struct zram { @@ -113,7 +114,6 @@ struct zram { unsigned int old_block_size; unsigned long *bitmap; unsigned long nr_pages; - spinlock_t bitmap_lock; #endif #ifdef CONFIG_ZRAM_MEMORY_TRACKING struct dentry *debugfs_dir; |