From 34919e3ba23a106e04f042f19348d9e55739b35a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Nov 2020 11:00:12 +0100 Subject: rbd: implement ->set_read_only to hook into BLKROSET processing Implement the ->set_read_only method instead of parsing the actual ioctl command. Signed-off-by: Christoph Hellwig Acked-by: Ilya Dryomov Signed-off-by: Jens Axboe --- drivers/block/rbd.c | 40 ++++------------------------------------ 1 file changed, 4 insertions(+), 36 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index f84128abade3..671733e459cf 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -692,12 +692,9 @@ static void rbd_release(struct gendisk *disk, fmode_t mode) put_device(&rbd_dev->dev); } -static int rbd_ioctl_set_ro(struct rbd_device *rbd_dev, unsigned long arg) +static int rbd_set_read_only(struct block_device *bdev, bool ro) { - int ro; - - if (get_user(ro, (int __user *)arg)) - return -EFAULT; + struct rbd_device *rbd_dev = bdev->bd_disk->private_data; /* * Both images mapped read-only and snapshots can't be marked @@ -710,43 +707,14 @@ static int rbd_ioctl_set_ro(struct rbd_device *rbd_dev, unsigned long arg) rbd_assert(!rbd_is_snap(rbd_dev)); } - /* Let blkdev_roset() handle it */ - return -ENOTTY; -} - -static int rbd_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) -{ - struct rbd_device *rbd_dev = bdev->bd_disk->private_data; - int ret; - - switch (cmd) { - case BLKROSET: - ret = rbd_ioctl_set_ro(rbd_dev, arg); - break; - default: - ret = -ENOTTY; - } - - return ret; -} - -#ifdef CONFIG_COMPAT -static int rbd_compat_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) -{ - return rbd_ioctl(bdev, mode, cmd, arg); + return 0; } -#endif /* CONFIG_COMPAT */ static const struct block_device_operations rbd_bd_ops = { .owner = THIS_MODULE, .open = rbd_open, .release = rbd_release, - .ioctl = rbd_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = rbd_compat_ioctl, -#endif + .set_read_only = rbd_set_read_only, }; /* -- cgit v1.2.3 From 7a2f0ce19f2e2ed93b5ace60375b908392ec8afb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Nov 2020 11:00:16 +0100 Subject: loop: use set_disk_ro Use set_disk_ro instead of set_device_ro to match all other block drivers and to ensure all partitions mirror the read-only flag. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/loop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/block') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a58084c2ed7c..027f5724fe2c 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1138,7 +1138,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, if (error) goto out_unlock; - set_device_ro(bdev, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); + set_disk_ro(lo->lo_disk, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO; lo->lo_device = bdev; -- cgit v1.2.3 From a7cb3d2f09c8405aed59d97a7d02cebea43cd3c7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Nov 2020 11:00:18 +0100 Subject: block: remove __blkdev_driver_ioctl Just open code it in the few callers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/ioctl.c | 25 +++++-------------------- drivers/block/pktcdvd.c | 6 ++++-- drivers/md/bcache/request.c | 5 +++-- drivers/md/dm.c | 5 ++++- include/linux/blkdev.h | 2 -- 5 files changed, 16 insertions(+), 27 deletions(-) (limited to 'drivers/block') diff --git a/block/ioctl.c b/block/ioctl.c index 04255dc5f3bf..6b785181344f 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -219,23 +219,6 @@ static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val) } #endif -int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, - unsigned cmd, unsigned long arg) -{ - struct gendisk *disk = bdev->bd_disk; - - if (disk->fops->ioctl) - return disk->fops->ioctl(bdev, mode, cmd, arg); - - return -ENOTTY; -} -/* - * For the record: _GPL here is only because somebody decided to slap it - * on the previous export. Sheer idiocy, since it wasn't copyrightable - * at all and could be open-coded without any exports by anybody who cares. - */ -EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl); - #ifdef CONFIG_COMPAT /* * This is the equivalent of compat_ptr_ioctl(), to be used by block @@ -594,10 +577,12 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, } ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); - if (ret == -ENOIOCTLCMD) - return __blkdev_driver_ioctl(bdev, mode, cmd, arg); + if (ret != -ENOIOCTLCMD) + return ret; - return ret; + if (!bdev->bd_disk->fops->ioctl) + return -ENOTTY; + return bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); } EXPORT_SYMBOL_GPL(blkdev_ioctl); /* for /dev/raw */ diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 467dbd06b7cd..ef1c1f094ea4 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2584,9 +2584,11 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, case CDROM_LAST_WRITTEN: case CDROM_SEND_PACKET: case SCSI_IOCTL_SEND_COMMAND: - ret = __blkdev_driver_ioctl(pd->bdev, mode, cmd, arg); + if (!bdev->bd_disk->fops->ioctl) + ret = -ENOTTY; + else + ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); break; - default: pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd); ret = -ENOTTY; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 214326383145..afac8d07c1bd 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1230,8 +1230,9 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, if (dc->io_disable) return -EIO; - - return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + if (!dc->bdev->bd_disk->fops->ioctl) + return -ENOTTY; + return dc->bdev->bd_disk->fops->ioctl(dc->bdev, mode, cmd, arg); } void bch_cached_dev_request_init(struct cached_dev *dc) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c18fc2548518..6db395c3d28b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -570,7 +570,10 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, } } - r = __blkdev_driver_ioctl(bdev, mode, cmd, arg); + if (!bdev->bd_disk->fops->ioctl) + r = -ENOTTY; + else + r = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); out: dm_unprepare_ioctl(md, srcu_idx); return r; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c1ba8a8d2bc..05b346a68c2e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1867,8 +1867,6 @@ extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, #define blkdev_compat_ptr_ioctl NULL #endif -extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, - unsigned long); extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); -- cgit v1.2.3 From f9550f1b3981755b0ba9bd385c3c6efdfadd8fe4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Oct 2020 15:58:30 +0100 Subject: swim: don't call blk_register_region The swim driver (unlike various other floppy drivers) doesn't have magic device nodes for certain modes, and already registers a gendisk for each of the floppies supported by a device. Thus the region registered is a no-op and can be removed. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/block/swim.c | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 52dd1efa00f9..cc6a0bc6c005 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -745,18 +745,6 @@ static const struct block_device_operations floppy_fops = { .check_events = floppy_check_events, }; -static struct kobject *floppy_find(dev_t dev, int *part, void *data) -{ - struct swim_priv *swd = data; - int drive = (*part & 3); - - if (drive >= swd->floppy_count) - return NULL; - - *part = 0; - return get_disk_and_module(swd->unit[drive].disk); -} - static int swim_add_floppy(struct swim_priv *swd, enum drive_location location) { struct floppy_state *fs = &swd->unit[swd->floppy_count]; @@ -846,9 +834,6 @@ static int swim_floppy_init(struct swim_priv *swd) add_disk(swd->unit[drive].disk); } - blk_register_region(MKDEV(FLOPPY_MAJOR, 0), 256, THIS_MODULE, - floppy_find, NULL, swd); - return 0; exit_put_disks: @@ -932,8 +917,6 @@ static int swim_remove(struct platform_device *dev) int drive; struct resource *res; - blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256); - for (drive = 0; drive < swd->floppy_count; drive++) { del_gendisk(swd->unit[drive].disk); blk_cleanup_queue(swd->unit[drive].disk->queue); -- cgit v1.2.3 From 7cc178a6b994b7c994f1811c4b9fedc015ee0c9e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Oct 2020 15:58:32 +0100 Subject: brd: use __register_blkdev to allocate devices on demand Use the simpler mechanism attached to major_name to allocate a brd device when a currently unregistered minor is accessed. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/block/brd.c | 39 +++++++++++---------------------------- 1 file changed, 11 insertions(+), 28 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/brd.c b/drivers/block/brd.c index cc49a921339f..c43a6ab4b1f3 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -426,14 +426,15 @@ static void brd_free(struct brd_device *brd) kfree(brd); } -static struct brd_device *brd_init_one(int i, bool *new) +static void brd_probe(dev_t dev) { struct brd_device *brd; + int i = MINOR(dev) / max_part; - *new = false; + mutex_lock(&brd_devices_mutex); list_for_each_entry(brd, &brd_devices, brd_list) { if (brd->brd_number == i) - goto out; + goto out_unlock; } brd = brd_alloc(i); @@ -442,9 +443,9 @@ static struct brd_device *brd_init_one(int i, bool *new) add_disk(brd->brd_disk); list_add_tail(&brd->brd_list, &brd_devices); } - *new = true; -out: - return brd; + +out_unlock: + mutex_unlock(&brd_devices_mutex); } static void brd_del_one(struct brd_device *brd) @@ -454,23 +455,6 @@ static void brd_del_one(struct brd_device *brd) brd_free(brd); } -static struct kobject *brd_probe(dev_t dev, int *part, void *data) -{ - struct brd_device *brd; - struct kobject *kobj; - bool new; - - mutex_lock(&brd_devices_mutex); - brd = brd_init_one(MINOR(dev) / max_part, &new); - kobj = brd ? get_disk_and_module(brd->brd_disk) : NULL; - mutex_unlock(&brd_devices_mutex); - - if (new) - *part = 0; - - return kobj; -} - static inline void brd_check_and_reset_par(void) { if (unlikely(!max_part)) @@ -510,11 +494,12 @@ static int __init brd_init(void) * dynamically. */ - if (register_blkdev(RAMDISK_MAJOR, "ramdisk")) + if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe)) return -EIO; brd_check_and_reset_par(); + mutex_lock(&brd_devices_mutex); for (i = 0; i < rd_nr; i++) { brd = brd_alloc(i); if (!brd) @@ -532,9 +517,7 @@ static int __init brd_init(void) brd->brd_disk->queue = brd->brd_queue; add_disk(brd->brd_disk); } - - blk_register_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS, - THIS_MODULE, brd_probe, NULL, NULL); + mutex_unlock(&brd_devices_mutex); pr_info("brd: module loaded\n"); return 0; @@ -544,6 +527,7 @@ out_free: list_del(&brd->brd_list); brd_free(brd); } + mutex_unlock(&brd_devices_mutex); unregister_blkdev(RAMDISK_MAJOR, "ramdisk"); pr_info("brd: module NOT loaded !!!\n"); @@ -557,7 +541,6 @@ static void __exit brd_exit(void) list_for_each_entry_safe(brd, next, &brd_devices, brd_list) brd_del_one(brd); - blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS); unregister_blkdev(RAMDISK_MAJOR, "ramdisk"); pr_info("brd: module unloaded\n"); -- cgit v1.2.3 From 8410d38c255200f71b67ddb37021c36273e7e78c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Oct 2020 15:58:33 +0100 Subject: loop: use __register_blkdev to allocate devices on demand Use the simpler mechanism attached to major_name to allocate a brd device when a currently unregistered minor is accessed. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/block/loop.c | 30 ++++++++---------------------- 1 file changed, 8 insertions(+), 22 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 027f5724fe2c..22e59410b971 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -2235,24 +2235,18 @@ out: return ret; } -static struct kobject *loop_probe(dev_t dev, int *part, void *data) +static void loop_probe(dev_t dev) { + int idx = MINOR(dev) >> part_shift; struct loop_device *lo; - struct kobject *kobj; - int err; + + if (max_loop && idx >= max_loop) + return; mutex_lock(&loop_ctl_mutex); - err = loop_lookup(&lo, MINOR(dev) >> part_shift); - if (err < 0) - err = loop_add(&lo, MINOR(dev) >> part_shift); - if (err < 0) - kobj = NULL; - else - kobj = get_disk_and_module(lo->lo_disk); + if (loop_lookup(&lo, idx) < 0) + loop_add(&lo, idx); mutex_unlock(&loop_ctl_mutex); - - *part = 0; - return kobj; } static long loop_control_ioctl(struct file *file, unsigned int cmd, @@ -2372,14 +2366,11 @@ static int __init loop_init(void) goto err_out; - if (register_blkdev(LOOP_MAJOR, "loop")) { + if (__register_blkdev(LOOP_MAJOR, "loop", loop_probe)) { err = -EIO; goto misc_out; } - blk_register_region(MKDEV(LOOP_MAJOR, 0), range, - THIS_MODULE, loop_probe, NULL, NULL); - /* pre-create number of devices given by config or max_loop */ mutex_lock(&loop_ctl_mutex); for (i = 0; i < nr; i++) @@ -2405,16 +2396,11 @@ static int loop_exit_cb(int id, void *ptr, void *data) static void __exit loop_exit(void) { - unsigned long range; - - range = max_loop ? max_loop << part_shift : 1UL << MINORBITS; - mutex_lock(&loop_ctl_mutex); idr_for_each(&loop_index_idr, &loop_exit_cb, NULL); idr_destroy(&loop_index_idr); - blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range); unregister_blkdev(LOOP_MAJOR, "loop"); misc_deregister(&loop_misc); -- cgit v1.2.3 From 302cfee150291c6cd85b1ca197d062d0b423d09c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Oct 2020 15:58:36 +0100 Subject: floppy: use a separate gendisk for each media format The floppy driver usually autodetects the media when used with the normal /dev/fd? devices, which also are the only nodes created by udev. But it also supports various aliases that force a given media format. That is currently supported using the blk_register_region framework which finds the floppy gendisk even for a 'mismatched' dev_t. The problem with this (besides the code complexity) is that it creates multiple struct block_device instances for the whole device of a single gendisk, which can lead to interesting issues in code not aware of that fact. To fix this just create a separate gendisk for each of the aliases if they are accessed. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/floppy.c | 154 +++++++++++++++++++++++++++++++------------------ 1 file changed, 97 insertions(+), 57 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 7df79ae6b0a1..dfe1dfc901cc 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -402,7 +402,6 @@ static struct floppy_drive_params drive_params[N_DRIVE]; static struct floppy_drive_struct drive_state[N_DRIVE]; static struct floppy_write_errors write_errors[N_DRIVE]; static struct timer_list motor_off_timer[N_DRIVE]; -static struct gendisk *disks[N_DRIVE]; static struct blk_mq_tag_set tag_sets[N_DRIVE]; static struct block_device *opened_bdev[N_DRIVE]; static DEFINE_MUTEX(open_lock); @@ -477,6 +476,8 @@ static struct floppy_struct floppy_type[32] = { { 3200,20,2,80,0,0x1C,0x00,0xCF,0x2C,"H1600" }, /* 31 1.6MB 3.5" */ }; +static struct gendisk *disks[N_DRIVE][ARRAY_SIZE(floppy_type)]; + #define SECTSIZE (_FD_SECTSIZE(*floppy)) /* Auto-detection: Disk type used until the next media change occurs. */ @@ -4111,7 +4112,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) new_dev = MINOR(bdev->bd_dev); drive_state[drive].fd_device = new_dev; - set_capacity(disks[drive], floppy_sizes[new_dev]); + set_capacity(disks[drive][ITYPE(new_dev)], floppy_sizes[new_dev]); if (old_dev != -1 && old_dev != new_dev) { if (buffer_drive == drive) buffer_track = -1; @@ -4579,15 +4580,58 @@ static bool floppy_available(int drive) return true; } -static struct kobject *floppy_find(dev_t dev, int *part, void *data) +static int floppy_alloc_disk(unsigned int drive, unsigned int type) { - int drive = (*part & 3) | ((*part & 0x80) >> 5); - if (drive >= N_DRIVE || !floppy_available(drive)) - return NULL; - if (((*part >> 2) & 0x1f) >= ARRAY_SIZE(floppy_type)) - return NULL; - *part = 0; - return get_disk_and_module(disks[drive]); + struct gendisk *disk; + int err; + + disk = alloc_disk(1); + if (!disk) + return -ENOMEM; + + disk->queue = blk_mq_init_queue(&tag_sets[drive]); + if (IS_ERR(disk->queue)) { + err = PTR_ERR(disk->queue); + disk->queue = NULL; + put_disk(disk); + return err; + } + + blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); + blk_queue_max_hw_sectors(disk->queue, 64); + disk->major = FLOPPY_MAJOR; + disk->first_minor = TOMINOR(drive) | (type << 2); + disk->fops = &floppy_fops; + disk->events = DISK_EVENT_MEDIA_CHANGE; + if (type) + sprintf(disk->disk_name, "fd%d_type%d", drive, type); + else + sprintf(disk->disk_name, "fd%d", drive); + /* to be cleaned up... */ + disk->private_data = (void *)(long)drive; + disk->flags |= GENHD_FL_REMOVABLE; + + disks[drive][type] = disk; + return 0; +} + +static DEFINE_MUTEX(floppy_probe_lock); + +static void floppy_probe(dev_t dev) +{ + unsigned int drive = (MINOR(dev) & 3) | ((MINOR(dev) & 0x80) >> 5); + unsigned int type = (MINOR(dev) >> 2) & 0x1f; + + if (drive >= N_DRIVE || !floppy_available(drive) || + type >= ARRAY_SIZE(floppy_type)) + return; + + mutex_lock(&floppy_probe_lock); + if (!disks[drive][type]) { + if (floppy_alloc_disk(drive, type) == 0) + add_disk(disks[drive][type]); + } + mutex_unlock(&floppy_probe_lock); } static int __init do_floppy_init(void) @@ -4609,33 +4653,25 @@ static int __init do_floppy_init(void) return -ENOMEM; for (drive = 0; drive < N_DRIVE; drive++) { - disks[drive] = alloc_disk(1); - if (!disks[drive]) { - err = -ENOMEM; + memset(&tag_sets[drive], 0, sizeof(tag_sets[drive])); + tag_sets[drive].ops = &floppy_mq_ops; + tag_sets[drive].nr_hw_queues = 1; + tag_sets[drive].nr_maps = 1; + tag_sets[drive].queue_depth = 2; + tag_sets[drive].numa_node = NUMA_NO_NODE; + tag_sets[drive].flags = BLK_MQ_F_SHOULD_MERGE; + err = blk_mq_alloc_tag_set(&tag_sets[drive]); + if (err) goto out_put_disk; - } - disks[drive]->queue = blk_mq_init_sq_queue(&tag_sets[drive], - &floppy_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(disks[drive]->queue)) { - err = PTR_ERR(disks[drive]->queue); - disks[drive]->queue = NULL; + err = floppy_alloc_disk(drive, 0); + if (err) goto out_put_disk; - } - - blk_queue_bounce_limit(disks[drive]->queue, BLK_BOUNCE_HIGH); - blk_queue_max_hw_sectors(disks[drive]->queue, 64); - disks[drive]->major = FLOPPY_MAJOR; - disks[drive]->first_minor = TOMINOR(drive); - disks[drive]->fops = &floppy_fops; - disks[drive]->events = DISK_EVENT_MEDIA_CHANGE; - sprintf(disks[drive]->disk_name, "fd%d", drive); timer_setup(&motor_off_timer[drive], motor_off_callback, 0); } - err = register_blkdev(FLOPPY_MAJOR, "fd"); + err = __register_blkdev(FLOPPY_MAJOR, "fd", floppy_probe); if (err) goto out_put_disk; @@ -4643,9 +4679,6 @@ static int __init do_floppy_init(void) if (err) goto out_unreg_blkdev; - blk_register_region(MKDEV(FLOPPY_MAJOR, 0), 256, THIS_MODULE, - floppy_find, NULL, NULL); - for (i = 0; i < 256; i++) if (ITYPE(i)) floppy_sizes[i] = floppy_type[ITYPE(i)].size; @@ -4673,7 +4706,7 @@ static int __init do_floppy_init(void) if (fdc_state[0].address == -1) { cancel_delayed_work(&fd_timeout); err = -ENODEV; - goto out_unreg_region; + goto out_unreg_driver; } #if N_FDC > 1 fdc_state[1].address = FDC2; @@ -4684,7 +4717,7 @@ static int __init do_floppy_init(void) if (err) { cancel_delayed_work(&fd_timeout); err = -EBUSY; - goto out_unreg_region; + goto out_unreg_driver; } /* initialise drive state */ @@ -4761,10 +4794,8 @@ static int __init do_floppy_init(void) if (err) goto out_remove_drives; - /* to be cleaned up... */ - disks[drive]->private_data = (void *)(long)drive; - disks[drive]->flags |= GENHD_FL_REMOVABLE; - device_add_disk(&floppy_device[drive].dev, disks[drive], NULL); + device_add_disk(&floppy_device[drive].dev, disks[drive][0], + NULL); } return 0; @@ -4772,30 +4803,27 @@ static int __init do_floppy_init(void) out_remove_drives: while (drive--) { if (floppy_available(drive)) { - del_gendisk(disks[drive]); + del_gendisk(disks[drive][0]); platform_device_unregister(&floppy_device[drive]); } } out_release_dma: if (atomic_read(&usage_count)) floppy_release_irq_and_dma(); -out_unreg_region: - blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256); +out_unreg_driver: platform_driver_unregister(&floppy_driver); out_unreg_blkdev: unregister_blkdev(FLOPPY_MAJOR, "fd"); out_put_disk: destroy_workqueue(floppy_wq); for (drive = 0; drive < N_DRIVE; drive++) { - if (!disks[drive]) + if (!disks[drive][0]) break; - if (disks[drive]->queue) { - del_timer_sync(&motor_off_timer[drive]); - blk_cleanup_queue(disks[drive]->queue); - disks[drive]->queue = NULL; - blk_mq_free_tag_set(&tag_sets[drive]); - } - put_disk(disks[drive]); + del_timer_sync(&motor_off_timer[drive]); + blk_cleanup_queue(disks[drive][0]->queue); + disks[drive][0]->queue = NULL; + blk_mq_free_tag_set(&tag_sets[drive]); + put_disk(disks[drive][0]); } return err; } @@ -5006,9 +5034,8 @@ module_init(floppy_module_init); static void __exit floppy_module_exit(void) { - int drive; + int drive, i; - blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256); unregister_blkdev(FLOPPY_MAJOR, "fd"); platform_driver_unregister(&floppy_driver); @@ -5018,10 +5045,16 @@ static void __exit floppy_module_exit(void) del_timer_sync(&motor_off_timer[drive]); if (floppy_available(drive)) { - del_gendisk(disks[drive]); + for (i = 0; i < ARRAY_SIZE(floppy_type); i++) { + if (disks[drive][i]) + del_gendisk(disks[drive][i]); + } platform_device_unregister(&floppy_device[drive]); } - blk_cleanup_queue(disks[drive]->queue); + for (i = 0; i < ARRAY_SIZE(floppy_type); i++) { + if (disks[drive][i]) + blk_cleanup_queue(disks[drive][i]->queue); + } blk_mq_free_tag_set(&tag_sets[drive]); /* @@ -5029,10 +5062,17 @@ static void __exit floppy_module_exit(void) * queue reference in put_disk(). */ if (!(allowed_drive_mask & (1 << drive)) || - fdc_state[FDC(drive)].version == FDC_NONE) - disks[drive]->queue = NULL; + fdc_state[FDC(drive)].version == FDC_NONE) { + for (i = 0; i < ARRAY_SIZE(floppy_type); i++) { + if (disks[drive][i]) + disks[drive][i]->queue = NULL; + } + } - put_disk(disks[drive]); + for (i = 0; i < ARRAY_SIZE(floppy_type); i++) { + if (disks[drive][i]) + put_disk(disks[drive][i]); + } } cancel_delayed_work_sync(&fd_timeout); -- cgit v1.2.3 From 0033a9b41fc219e1e0d673e0a42179577a7d68ad Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Oct 2020 15:58:37 +0100 Subject: amiflop: use separate gendisks for Amiga vs MS-DOS mode Use separate gendisks (which share a tag_set) for the native Amgiga vs the MS-DOS mode instead of redirecting the gendisk lookup using a probe callback. This avoids potential problems with aliased block_device instances and will eventually allow for removing the blk_register_region framework. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/block/amiflop.c | 98 +++++++++++++++++++++++++++---------------------- 1 file changed, 55 insertions(+), 43 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 71c2b1564558..9e2d0c6a3877 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -201,7 +201,7 @@ struct amiga_floppy_struct { int busy; /* true when drive is active */ int dirty; /* true when trackbuf is not on disk */ int status; /* current error code for unit */ - struct gendisk *gendisk; + struct gendisk *gendisk[2]; struct blk_mq_tag_set tag_set; }; @@ -1669,6 +1669,11 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) return -EBUSY; } + if (unit[drive].type->code == FD_NODRIVE) { + mutex_unlock(&amiflop_mutex); + return -ENXIO; + } + if (mode & (FMODE_READ|FMODE_WRITE)) { bdev_check_media_change(bdev); if (mode & FMODE_WRITE) { @@ -1695,7 +1700,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) unit[drive].dtype=&data_types[system]; unit[drive].blocks=unit[drive].type->heads*unit[drive].type->tracks* data_types[system].sects*unit[drive].type->sect_mult; - set_capacity(unit[drive].gendisk, unit[drive].blocks); + set_capacity(unit[drive].gendisk[system], unit[drive].blocks); printk(KERN_INFO "fd%d: accessing %s-disk with %s-layout\n",drive, unit[drive].type->name, data_types[system].name); @@ -1772,36 +1777,68 @@ static const struct blk_mq_ops amiflop_mq_ops = { .queue_rq = amiflop_queue_rq, }; -static struct gendisk *fd_alloc_disk(int drive) +static int fd_alloc_disk(int drive, int system) { struct gendisk *disk; disk = alloc_disk(1); if (!disk) goto out; - - disk->queue = blk_mq_init_sq_queue(&unit[drive].tag_set, &amiflop_mq_ops, - 2, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(disk->queue)) { - disk->queue = NULL; + disk->queue = blk_mq_init_queue(&unit[drive].tag_set); + if (IS_ERR(disk->queue)) goto out_put_disk; - } + disk->major = FLOPPY_MAJOR; + disk->first_minor = drive + system; + disk->fops = &floppy_fops; + disk->events = DISK_EVENT_MEDIA_CHANGE; + if (system) + sprintf(disk->disk_name, "fd%d_msdos", drive); + else + sprintf(disk->disk_name, "fd%d", drive); + disk->private_data = &unit[drive]; + set_capacity(disk, 880 * 2); + + unit[drive].gendisk[system] = disk; + add_disk(disk); + return 0; + +out_put_disk: + disk->queue = NULL; + put_disk(disk); +out: + return -ENOMEM; +} + +static int fd_alloc_drive(int drive) +{ unit[drive].trackbuf = kmalloc(FLOPPY_MAX_SECTORS * 512, GFP_KERNEL); if (!unit[drive].trackbuf) - goto out_cleanup_queue; + goto out; - return disk; + memset(&unit[drive].tag_set, 0, sizeof(unit[drive].tag_set)); + unit[drive].tag_set.ops = &amiflop_mq_ops; + unit[drive].tag_set.nr_hw_queues = 1; + unit[drive].tag_set.nr_maps = 1; + unit[drive].tag_set.queue_depth = 2; + unit[drive].tag_set.numa_node = NUMA_NO_NODE; + unit[drive].tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + if (blk_mq_alloc_tag_set(&unit[drive].tag_set)) + goto out_cleanup_trackbuf; -out_cleanup_queue: - blk_cleanup_queue(disk->queue); - disk->queue = NULL; + pr_cont(" fd%d", drive); + + if (fd_alloc_disk(drive, 0) || fd_alloc_disk(drive, 1)) + goto out_cleanup_tagset; + return 0; + +out_cleanup_tagset: blk_mq_free_tag_set(&unit[drive].tag_set); -out_put_disk: - put_disk(disk); +out_cleanup_trackbuf: + kfree(unit[drive].trackbuf); out: unit[drive].type->code = FD_NODRIVE; - return NULL; + return -ENOMEM; } static int __init fd_probe_drives(void) @@ -1812,29 +1849,16 @@ static int __init fd_probe_drives(void) drives=0; nomem=0; for(drive=0;drivecode == FD_NODRIVE) continue; - disk = fd_alloc_disk(drive); - if (!disk) { + if (fd_alloc_drive(drive) < 0) { pr_cont(" no mem for fd%d", drive); nomem = 1; continue; } - unit[drive].gendisk = disk; drives++; - - pr_cont(" fd%d",drive); - disk->major = FLOPPY_MAJOR; - disk->first_minor = drive; - disk->fops = &floppy_fops; - disk->events = DISK_EVENT_MEDIA_CHANGE; - sprintf(disk->disk_name, "fd%d", drive); - disk->private_data = &unit[drive]; - set_capacity(disk, 880*2); - add_disk(disk); } if ((drives > 0) || (nomem == 0)) { if (drives == 0) @@ -1846,15 +1870,6 @@ static int __init fd_probe_drives(void) return -ENOMEM; } -static struct kobject *floppy_find(dev_t dev, int *part, void *data) -{ - int drive = *part & 3; - if (unit[drive].type->code == FD_NODRIVE) - return NULL; - *part = 0; - return get_disk_and_module(unit[drive].gendisk); -} - static int __init amiga_floppy_probe(struct platform_device *pdev) { int i, ret; @@ -1884,9 +1899,6 @@ static int __init amiga_floppy_probe(struct platform_device *pdev) if (fd_probe_drives() < 1) /* No usable drives */ goto out_probe; - blk_register_region(MKDEV(FLOPPY_MAJOR, 0), 256, THIS_MODULE, - floppy_find, NULL, NULL); - /* initialize variables */ timer_setup(&motor_on_timer, motor_on_callback, 0); motor_on_timer.expires = 0; -- cgit v1.2.3 From bf9c0538e485b591a2ee02d9adb8a99db4be5a2a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Oct 2020 15:58:38 +0100 Subject: ataflop: use a separate gendisk for each media format The Atari floppy driver usually autodetects the media when used with the ormal /dev/fd? devices, which also are the only nodes created by udev. But it also supports various aliases that force a given media format. That is currently supported using the blk_register_region framework which finds the floppy gendisk even for a 'mismatched' dev_t. The problem with this (besides the code complexity) is that it creates multiple struct block_device instances for the whole device of a single gendisk, which can lead to interesting issues in code not aware of that fact. To fix this just create a separate gendisk for each of the aliases if they are accessed. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/ataflop.c | 135 ++++++++++++++++++++++++++++++------------------ 1 file changed, 86 insertions(+), 49 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 3e881fdb06e0..104b713f4055 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -297,7 +297,7 @@ static struct atari_floppy_struct { unsigned int wpstat; /* current state of WP signal (for disk change detection) */ int flags; /* flags */ - struct gendisk *disk; + struct gendisk *disk[NUM_DISK_MINORS]; int ref; int type; struct blk_mq_tag_set tag_set; @@ -723,12 +723,16 @@ static void fd_error( void ) static int do_format(int drive, int type, struct atari_format_descr *desc) { - struct request_queue *q = unit[drive].disk->queue; + struct request_queue *q; unsigned char *p; int sect, nsect; unsigned long flags; int ret; + if (type) + type--; + + q = unit[drive].disk[type]->queue; blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); @@ -738,7 +742,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) local_irq_restore(flags); if (type) { - if (--type >= NUM_DISK_MINORS || + if (type >= NUM_DISK_MINORS || minor2disktype[type].drive_types > DriveType) { ret = -EINVAL; goto out; @@ -1154,7 +1158,7 @@ static void fd_rwsec_done1(int status) if (SUDT[-1].blocks > ReqBlock) { /* try another disk type */ SUDT--; - set_capacity(unit[SelectedDrive].disk, + set_capacity(unit[SelectedDrive].disk[0], SUDT->blocks); } else Probing = 0; @@ -1169,7 +1173,7 @@ static void fd_rwsec_done1(int status) /* record not found, but not probing. Maybe stretch wrong ? Restart probing */ if (SUD.autoprobe) { SUDT = atari_disk_type + StartDiskType[DriveType]; - set_capacity(unit[SelectedDrive].disk, + set_capacity(unit[SelectedDrive].disk[0], SUDT->blocks); Probing = 1; } @@ -1515,7 +1519,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, if (!UDT) { Probing = 1; UDT = atari_disk_type + StartDiskType[DriveType]; - set_capacity(floppy->disk, UDT->blocks); + set_capacity(bd->rq->rq_disk, UDT->blocks); UD.autoprobe = 1; } } @@ -1533,7 +1537,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, } type = minor2disktype[type].index; UDT = &atari_disk_type[type]; - set_capacity(floppy->disk, UDT->blocks); + set_capacity(bd->rq->rq_disk, UDT->blocks); UD.autoprobe = 0; } @@ -1658,7 +1662,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, printk (KERN_INFO "floppy%d: setting %s %p!\n", drive, dtp->name, dtp); UDT = dtp; - set_capacity(floppy->disk, UDT->blocks); + set_capacity(disk, UDT->blocks); if (cmd == FDDEFPRM) { /* save settings as permanent default type */ @@ -1702,7 +1706,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, return -EINVAL; UDT = dtp; - set_capacity(floppy->disk, UDT->blocks); + set_capacity(disk, UDT->blocks); return 0; case FDMSGON: @@ -1725,7 +1729,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, UDT = NULL; /* MSch: invalidate default_params */ default_params[drive].blocks = 0; - set_capacity(floppy->disk, MAX_DISK_SIZE * 2); + set_capacity(disk, MAX_DISK_SIZE * 2); fallthrough; case FDFMTEND: case FDFLUSH: @@ -1962,14 +1966,50 @@ static const struct blk_mq_ops ataflop_mq_ops = { .commit_rqs = ataflop_commit_rqs, }; -static struct kobject *floppy_find(dev_t dev, int *part, void *data) +static int ataflop_alloc_disk(unsigned int drive, unsigned int type) { - int drive = *part & 3; - int type = *part >> 2; + struct gendisk *disk; + int ret; + + disk = alloc_disk(1); + if (!disk) + return -ENOMEM; + + disk->queue = blk_mq_init_queue(&unit[drive].tag_set); + if (IS_ERR(disk->queue)) { + ret = PTR_ERR(disk->queue); + disk->queue = NULL; + put_disk(disk); + return ret; + } + + disk->major = FLOPPY_MAJOR; + disk->first_minor = drive + (type << 2); + sprintf(disk->disk_name, "fd%d", drive); + disk->fops = &floppy_fops; + disk->events = DISK_EVENT_MEDIA_CHANGE; + disk->private_data = &unit[drive]; + set_capacity(disk, MAX_DISK_SIZE * 2); + + unit[drive].disk[type] = disk; + return 0; +} + +static DEFINE_MUTEX(ataflop_probe_lock); + +static void ataflop_probe(dev_t dev) +{ + int drive = MINOR(dev) & 3; + int type = MINOR(dev) >> 2; + if (drive >= FD_MAX_UNITS || type > NUM_DISK_MINORS) - return NULL; - *part = 0; - return get_disk_and_module(unit[drive].disk); + return; + mutex_lock(&ataflop_probe_lock); + if (!unit[drive].disk[type]) { + if (ataflop_alloc_disk(drive, type) == 0) + add_disk(unit[drive].disk[type]); + } + mutex_unlock(&ataflop_probe_lock); } static int __init atari_floppy_init (void) @@ -1981,23 +2021,26 @@ static int __init atari_floppy_init (void) /* Amiga, Mac, ... don't have Atari-compatible floppy :-) */ return -ENODEV; - if (register_blkdev(FLOPPY_MAJOR,"fd")) - return -EBUSY; + mutex_lock(&ataflop_probe_lock); + ret = __register_blkdev(FLOPPY_MAJOR, "fd", ataflop_probe); + if (ret) + goto out_unlock; for (i = 0; i < FD_MAX_UNITS; i++) { - unit[i].disk = alloc_disk(1); - if (!unit[i].disk) { - ret = -ENOMEM; + memset(&unit[i].tag_set, 0, sizeof(unit[i].tag_set)); + unit[i].tag_set.ops = &ataflop_mq_ops; + unit[i].tag_set.nr_hw_queues = 1; + unit[i].tag_set.nr_maps = 1; + unit[i].tag_set.queue_depth = 2; + unit[i].tag_set.numa_node = NUMA_NO_NODE; + unit[i].tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + ret = blk_mq_alloc_tag_set(&unit[i].tag_set); + if (ret) goto err; - } - unit[i].disk->queue = blk_mq_init_sq_queue(&unit[i].tag_set, - &ataflop_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(unit[i].disk->queue)) { - put_disk(unit[i].disk); - ret = PTR_ERR(unit[i].disk->queue); - unit[i].disk->queue = NULL; + ret = ataflop_alloc_disk(i, 0); + if (ret) { + blk_mq_free_tag_set(&unit[i].tag_set); goto err; } } @@ -2027,19 +2070,9 @@ static int __init atari_floppy_init (void) for (i = 0; i < FD_MAX_UNITS; i++) { unit[i].track = -1; unit[i].flags = 0; - unit[i].disk->major = FLOPPY_MAJOR; - unit[i].disk->first_minor = i; - sprintf(unit[i].disk->disk_name, "fd%d", i); - unit[i].disk->fops = &floppy_fops; - unit[i].disk->events = DISK_EVENT_MEDIA_CHANGE; - unit[i].disk->private_data = &unit[i]; - set_capacity(unit[i].disk, MAX_DISK_SIZE * 2); - add_disk(unit[i].disk); + add_disk(unit[i].disk[0]); } - blk_register_region(MKDEV(FLOPPY_MAJOR, 0), 256, THIS_MODULE, - floppy_find, NULL, NULL); - printk(KERN_INFO "Atari floppy driver: max. %cD, %strack buffering\n", DriveType == 0 ? 'D' : DriveType == 1 ? 'H' : 'E', UseTrackbuffer ? "" : "no "); @@ -2049,14 +2082,14 @@ static int __init atari_floppy_init (void) err: while (--i >= 0) { - struct gendisk *disk = unit[i].disk; - - blk_cleanup_queue(disk->queue); + blk_cleanup_queue(unit[i].disk[0]->queue); + put_disk(unit[i].disk[0]); blk_mq_free_tag_set(&unit[i].tag_set); - put_disk(unit[i].disk); } unregister_blkdev(FLOPPY_MAJOR, "fd"); +out_unlock: + mutex_unlock(&ataflop_probe_lock); return ret; } @@ -2101,13 +2134,17 @@ __setup("floppy=", atari_floppy_setup); static void __exit atari_floppy_exit(void) { - int i; - blk_unregister_region(MKDEV(FLOPPY_MAJOR, 0), 256); + int i, type; + for (i = 0; i < FD_MAX_UNITS; i++) { - del_gendisk(unit[i].disk); - blk_cleanup_queue(unit[i].disk->queue); + for (type = 0; type < NUM_DISK_MINORS; type++) { + if (!unit[i].disk[type]) + continue; + del_gendisk(unit[i].disk[type]); + blk_cleanup_queue(unit[i].disk[type]->queue); + put_disk(unit[i].disk[type]); + } blk_mq_free_tag_set(&unit[i].tag_set); - put_disk(unit[i].disk); } unregister_blkdev(FLOPPY_MAJOR, "fd"); -- cgit v1.2.3 From 6c3a05e127058ed9626a2f39e779c5e595c13a9b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Oct 2020 15:58:39 +0100 Subject: z2ram: reindent reindent the driver using Lident as the code style was far away from normal Linux code. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/block/z2ram.c | 493 ++++++++++++++++++++++++-------------------------- 1 file changed, 236 insertions(+), 257 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index 0e734802ee7c..eafecc9a72b3 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -42,7 +42,6 @@ #include - #define Z2MINOR_COMBINED (0) #define Z2MINOR_Z2ONLY (1) #define Z2MINOR_CHIPONLY (2) @@ -50,17 +49,17 @@ #define Z2MINOR_MEMLIST2 (5) #define Z2MINOR_MEMLIST3 (6) #define Z2MINOR_MEMLIST4 (7) -#define Z2MINOR_COUNT (8) /* Move this down when adding a new minor */ +#define Z2MINOR_COUNT (8) /* Move this down when adding a new minor */ #define Z2RAM_CHUNK1024 ( Z2RAM_CHUNKSIZE >> 10 ) static DEFINE_MUTEX(z2ram_mutex); -static u_long *z2ram_map = NULL; -static u_long z2ram_size = 0; -static int z2_count = 0; -static int chip_count = 0; -static int list_count = 0; -static int current_device = -1; +static u_long *z2ram_map = NULL; +static u_long z2ram_size = 0; +static int z2_count = 0; +static int chip_count = 0; +static int list_count = 0; +static int current_device = -1; static DEFINE_SPINLOCK(z2ram_lock); @@ -71,7 +70,7 @@ static blk_status_t z2_queue_rq(struct blk_mq_hw_ctx *hctx, { struct request *req = bd->rq; unsigned long start = blk_rq_pos(req) << 9; - unsigned long len = blk_rq_cur_bytes(req); + unsigned long len = blk_rq_cur_bytes(req); blk_mq_start_request(req); @@ -92,7 +91,7 @@ static blk_status_t z2_queue_rq(struct blk_mq_hw_ctx *hctx, if (len < size) size = len; - addr += z2ram_map[ start >> Z2RAM_CHUNKSHIFT ]; + addr += z2ram_map[start >> Z2RAM_CHUNKSHIFT]; if (rq_data_dir(req) == READ) memcpy(buffer, (char *)addr, size); else @@ -106,228 +105,214 @@ static blk_status_t z2_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } -static void -get_z2ram( void ) +static void get_z2ram(void) { - int i; - - for ( i = 0; i < Z2RAM_SIZE / Z2RAM_CHUNKSIZE; i++ ) - { - if ( test_bit( i, zorro_unused_z2ram ) ) - { - z2_count++; - z2ram_map[z2ram_size++] = (unsigned long)ZTWO_VADDR(Z2RAM_START) + - (i << Z2RAM_CHUNKSHIFT); - clear_bit( i, zorro_unused_z2ram ); + int i; + + for (i = 0; i < Z2RAM_SIZE / Z2RAM_CHUNKSIZE; i++) { + if (test_bit(i, zorro_unused_z2ram)) { + z2_count++; + z2ram_map[z2ram_size++] = + (unsigned long)ZTWO_VADDR(Z2RAM_START) + + (i << Z2RAM_CHUNKSHIFT); + clear_bit(i, zorro_unused_z2ram); + } } - } - return; + return; } -static void -get_chipram( void ) +static void get_chipram(void) { - while ( amiga_chip_avail() > ( Z2RAM_CHUNKSIZE * 4 ) ) - { - chip_count++; - z2ram_map[ z2ram_size ] = - (u_long)amiga_chip_alloc( Z2RAM_CHUNKSIZE, "z2ram" ); + while (amiga_chip_avail() > (Z2RAM_CHUNKSIZE * 4)) { + chip_count++; + z2ram_map[z2ram_size] = + (u_long) amiga_chip_alloc(Z2RAM_CHUNKSIZE, "z2ram"); - if ( z2ram_map[ z2ram_size ] == 0 ) - { - break; + if (z2ram_map[z2ram_size] == 0) { + break; + } + + z2ram_size++; } - z2ram_size++; - } - - return; + return; } static int z2_open(struct block_device *bdev, fmode_t mode) { - int device; - int max_z2_map = ( Z2RAM_SIZE / Z2RAM_CHUNKSIZE ) * - sizeof( z2ram_map[0] ); - int max_chip_map = ( amiga_chip_size / Z2RAM_CHUNKSIZE ) * - sizeof( z2ram_map[0] ); - int rc = -ENOMEM; - - device = MINOR(bdev->bd_dev); - - mutex_lock(&z2ram_mutex); - if ( current_device != -1 && current_device != device ) - { - rc = -EBUSY; - goto err_out; - } - - if ( current_device == -1 ) - { - z2_count = 0; - chip_count = 0; - list_count = 0; - z2ram_size = 0; - - /* Use a specific list entry. */ - if (device >= Z2MINOR_MEMLIST1 && device <= Z2MINOR_MEMLIST4) { - int index = device - Z2MINOR_MEMLIST1 + 1; - unsigned long size, paddr, vaddr; - - if (index >= m68k_realnum_memory) { - printk( KERN_ERR DEVICE_NAME - ": no such entry in z2ram_map\n" ); - goto err_out; - } - - paddr = m68k_memory[index].addr; - size = m68k_memory[index].size & ~(Z2RAM_CHUNKSIZE-1); - -#ifdef __powerpc__ - /* FIXME: ioremap doesn't build correct memory tables. */ - { - vfree(vmalloc (size)); - } + int device; + int max_z2_map = (Z2RAM_SIZE / Z2RAM_CHUNKSIZE) * sizeof(z2ram_map[0]); + int max_chip_map = (amiga_chip_size / Z2RAM_CHUNKSIZE) * + sizeof(z2ram_map[0]); + int rc = -ENOMEM; - vaddr = (unsigned long)ioremap_wt(paddr, size); + device = MINOR(bdev->bd_dev); -#else - vaddr = (unsigned long)z_remap_nocache_nonser(paddr, size); -#endif - z2ram_map = - kmalloc_array(size / Z2RAM_CHUNKSIZE, - sizeof(z2ram_map[0]), - GFP_KERNEL); - if ( z2ram_map == NULL ) - { - printk( KERN_ERR DEVICE_NAME - ": cannot get mem for z2ram_map\n" ); - goto err_out; - } + mutex_lock(&z2ram_mutex); + if (current_device != -1 && current_device != device) { + rc = -EBUSY; + goto err_out; + } - while (size) { - z2ram_map[ z2ram_size++ ] = vaddr; - size -= Z2RAM_CHUNKSIZE; - vaddr += Z2RAM_CHUNKSIZE; - list_count++; - } + if (current_device == -1) { + z2_count = 0; + chip_count = 0; + list_count = 0; + z2ram_size = 0; - if ( z2ram_size != 0 ) - printk( KERN_INFO DEVICE_NAME - ": using %iK List Entry %d Memory\n", - list_count * Z2RAM_CHUNK1024, index ); - } else - - switch ( device ) - { - case Z2MINOR_COMBINED: - - z2ram_map = kmalloc( max_z2_map + max_chip_map, GFP_KERNEL ); - if ( z2ram_map == NULL ) - { - printk( KERN_ERR DEVICE_NAME - ": cannot get mem for z2ram_map\n" ); - goto err_out; - } + /* Use a specific list entry. */ + if (device >= Z2MINOR_MEMLIST1 && device <= Z2MINOR_MEMLIST4) { + int index = device - Z2MINOR_MEMLIST1 + 1; + unsigned long size, paddr, vaddr; - get_z2ram(); - get_chipram(); - - if ( z2ram_size != 0 ) - printk( KERN_INFO DEVICE_NAME - ": using %iK Zorro II RAM and %iK Chip RAM (Total %dK)\n", - z2_count * Z2RAM_CHUNK1024, - chip_count * Z2RAM_CHUNK1024, - ( z2_count + chip_count ) * Z2RAM_CHUNK1024 ); - - break; - - case Z2MINOR_Z2ONLY: - z2ram_map = kmalloc( max_z2_map, GFP_KERNEL ); - if ( z2ram_map == NULL ) - { - printk( KERN_ERR DEVICE_NAME - ": cannot get mem for z2ram_map\n" ); - goto err_out; - } + if (index >= m68k_realnum_memory) { + printk(KERN_ERR DEVICE_NAME + ": no such entry in z2ram_map\n"); + goto err_out; + } - get_z2ram(); + paddr = m68k_memory[index].addr; + size = m68k_memory[index].size & ~(Z2RAM_CHUNKSIZE - 1); - if ( z2ram_size != 0 ) - printk( KERN_INFO DEVICE_NAME - ": using %iK of Zorro II RAM\n", - z2_count * Z2RAM_CHUNK1024 ); +#ifdef __powerpc__ + /* FIXME: ioremap doesn't build correct memory tables. */ + { + vfree(vmalloc(size)); + } - break; + vaddr = (unsigned long)ioremap_wt(paddr, size); - case Z2MINOR_CHIPONLY: - z2ram_map = kmalloc( max_chip_map, GFP_KERNEL ); - if ( z2ram_map == NULL ) - { - printk( KERN_ERR DEVICE_NAME - ": cannot get mem for z2ram_map\n" ); - goto err_out; +#else + vaddr = + (unsigned long)z_remap_nocache_nonser(paddr, size); +#endif + z2ram_map = + kmalloc_array(size / Z2RAM_CHUNKSIZE, + sizeof(z2ram_map[0]), GFP_KERNEL); + if (z2ram_map == NULL) { + printk(KERN_ERR DEVICE_NAME + ": cannot get mem for z2ram_map\n"); + goto err_out; + } + + while (size) { + z2ram_map[z2ram_size++] = vaddr; + size -= Z2RAM_CHUNKSIZE; + vaddr += Z2RAM_CHUNKSIZE; + list_count++; + } + + if (z2ram_size != 0) + printk(KERN_INFO DEVICE_NAME + ": using %iK List Entry %d Memory\n", + list_count * Z2RAM_CHUNK1024, index); + } else + switch (device) { + case Z2MINOR_COMBINED: + + z2ram_map = + kmalloc(max_z2_map + max_chip_map, + GFP_KERNEL); + if (z2ram_map == NULL) { + printk(KERN_ERR DEVICE_NAME + ": cannot get mem for z2ram_map\n"); + goto err_out; + } + + get_z2ram(); + get_chipram(); + + if (z2ram_size != 0) + printk(KERN_INFO DEVICE_NAME + ": using %iK Zorro II RAM and %iK Chip RAM (Total %dK)\n", + z2_count * Z2RAM_CHUNK1024, + chip_count * Z2RAM_CHUNK1024, + (z2_count + + chip_count) * Z2RAM_CHUNK1024); + + break; + + case Z2MINOR_Z2ONLY: + z2ram_map = kmalloc(max_z2_map, GFP_KERNEL); + if (z2ram_map == NULL) { + printk(KERN_ERR DEVICE_NAME + ": cannot get mem for z2ram_map\n"); + goto err_out; + } + + get_z2ram(); + + if (z2ram_size != 0) + printk(KERN_INFO DEVICE_NAME + ": using %iK of Zorro II RAM\n", + z2_count * Z2RAM_CHUNK1024); + + break; + + case Z2MINOR_CHIPONLY: + z2ram_map = kmalloc(max_chip_map, GFP_KERNEL); + if (z2ram_map == NULL) { + printk(KERN_ERR DEVICE_NAME + ": cannot get mem for z2ram_map\n"); + goto err_out; + } + + get_chipram(); + + if (z2ram_size != 0) + printk(KERN_INFO DEVICE_NAME + ": using %iK Chip RAM\n", + chip_count * Z2RAM_CHUNK1024); + + break; + + default: + rc = -ENODEV; + goto err_out; + + break; + } + + if (z2ram_size == 0) { + printk(KERN_NOTICE DEVICE_NAME + ": no unused ZII/Chip RAM found\n"); + goto err_out_kfree; } - get_chipram(); - - if ( z2ram_size != 0 ) - printk( KERN_INFO DEVICE_NAME - ": using %iK Chip RAM\n", - chip_count * Z2RAM_CHUNK1024 ); - - break; - - default: - rc = -ENODEV; - goto err_out; - - break; + current_device = device; + z2ram_size <<= Z2RAM_CHUNKSHIFT; + set_capacity(z2ram_gendisk, z2ram_size >> 9); } - if ( z2ram_size == 0 ) - { - printk( KERN_NOTICE DEVICE_NAME - ": no unused ZII/Chip RAM found\n" ); - goto err_out_kfree; - } - - current_device = device; - z2ram_size <<= Z2RAM_CHUNKSHIFT; - set_capacity(z2ram_gendisk, z2ram_size >> 9); - } - - mutex_unlock(&z2ram_mutex); - return 0; + mutex_unlock(&z2ram_mutex); + return 0; err_out_kfree: - kfree(z2ram_map); + kfree(z2ram_map); err_out: - mutex_unlock(&z2ram_mutex); - return rc; + mutex_unlock(&z2ram_mutex); + return rc; } -static void -z2_release(struct gendisk *disk, fmode_t mode) +static void z2_release(struct gendisk *disk, fmode_t mode) { - mutex_lock(&z2ram_mutex); - if ( current_device == -1 ) { - mutex_unlock(&z2ram_mutex); - return; - } - mutex_unlock(&z2ram_mutex); - /* - * FIXME: unmap memory - */ + mutex_lock(&z2ram_mutex); + if (current_device == -1) { + mutex_unlock(&z2ram_mutex); + return; + } + mutex_unlock(&z2ram_mutex); + /* + * FIXME: unmap memory + */ } -static const struct block_device_operations z2_fops = -{ - .owner = THIS_MODULE, - .open = z2_open, - .release = z2_release, +static const struct block_device_operations z2_fops = { + .owner = THIS_MODULE, + .open = z2_open, + .release = z2_release, }; static struct kobject *z2_find(dev_t dev, int *part, void *data) @@ -340,89 +325,83 @@ static struct request_queue *z2_queue; static struct blk_mq_tag_set tag_set; static const struct blk_mq_ops z2_mq_ops = { - .queue_rq = z2_queue_rq, + .queue_rq = z2_queue_rq, }; -static int __init -z2_init(void) +static int __init z2_init(void) { - int ret; + int ret; - if (!MACH_IS_AMIGA) - return -ENODEV; + if (!MACH_IS_AMIGA) + return -ENODEV; - ret = -EBUSY; - if (register_blkdev(Z2RAM_MAJOR, DEVICE_NAME)) - goto err; + ret = -EBUSY; + if (register_blkdev(Z2RAM_MAJOR, DEVICE_NAME)) + goto err; - ret = -ENOMEM; - z2ram_gendisk = alloc_disk(1); - if (!z2ram_gendisk) - goto out_disk; + ret = -ENOMEM; + z2ram_gendisk = alloc_disk(1); + if (!z2ram_gendisk) + goto out_disk; - z2_queue = blk_mq_init_sq_queue(&tag_set, &z2_mq_ops, 16, + z2_queue = blk_mq_init_sq_queue(&tag_set, &z2_mq_ops, 16, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(z2_queue)) { - ret = PTR_ERR(z2_queue); - z2_queue = NULL; - goto out_queue; - } + if (IS_ERR(z2_queue)) { + ret = PTR_ERR(z2_queue); + z2_queue = NULL; + goto out_queue; + } - z2ram_gendisk->major = Z2RAM_MAJOR; - z2ram_gendisk->first_minor = 0; - z2ram_gendisk->fops = &z2_fops; - sprintf(z2ram_gendisk->disk_name, "z2ram"); + z2ram_gendisk->major = Z2RAM_MAJOR; + z2ram_gendisk->first_minor = 0; + z2ram_gendisk->fops = &z2_fops; + sprintf(z2ram_gendisk->disk_name, "z2ram"); - z2ram_gendisk->queue = z2_queue; - add_disk(z2ram_gendisk); - blk_register_region(MKDEV(Z2RAM_MAJOR, 0), Z2MINOR_COUNT, THIS_MODULE, - z2_find, NULL, NULL); + z2ram_gendisk->queue = z2_queue; + add_disk(z2ram_gendisk); + blk_register_region(MKDEV(Z2RAM_MAJOR, 0), Z2MINOR_COUNT, THIS_MODULE, + z2_find, NULL, NULL); - return 0; + return 0; out_queue: - put_disk(z2ram_gendisk); + put_disk(z2ram_gendisk); out_disk: - unregister_blkdev(Z2RAM_MAJOR, DEVICE_NAME); + unregister_blkdev(Z2RAM_MAJOR, DEVICE_NAME); err: - return ret; + return ret; } static void __exit z2_exit(void) { - int i, j; - blk_unregister_region(MKDEV(Z2RAM_MAJOR, 0), Z2MINOR_COUNT); - unregister_blkdev(Z2RAM_MAJOR, DEVICE_NAME); - del_gendisk(z2ram_gendisk); - put_disk(z2ram_gendisk); - blk_cleanup_queue(z2_queue); - blk_mq_free_tag_set(&tag_set); - - if ( current_device != -1 ) - { - i = 0; - - for ( j = 0 ; j < z2_count; j++ ) - { - set_bit( i++, zorro_unused_z2ram ); - } + int i, j; + blk_unregister_region(MKDEV(Z2RAM_MAJOR, 0), Z2MINOR_COUNT); + unregister_blkdev(Z2RAM_MAJOR, DEVICE_NAME); + del_gendisk(z2ram_gendisk); + put_disk(z2ram_gendisk); + blk_cleanup_queue(z2_queue); + blk_mq_free_tag_set(&tag_set); + + if (current_device != -1) { + i = 0; + + for (j = 0; j < z2_count; j++) { + set_bit(i++, zorro_unused_z2ram); + } - for ( j = 0 ; j < chip_count; j++ ) - { - if ( z2ram_map[ i ] ) - { - amiga_chip_free( (void *) z2ram_map[ i++ ] ); - } - } + for (j = 0; j < chip_count; j++) { + if (z2ram_map[i]) { + amiga_chip_free((void *)z2ram_map[i++]); + } + } - if ( z2ram_map != NULL ) - { - kfree( z2ram_map ); + if (z2ram_map != NULL) { + kfree(z2ram_map); + } } - } - return; -} + return; +} module_init(z2_init); module_exit(z2_exit); -- cgit v1.2.3 From 76487f0241423497218f6ec505aa93cc29c8ddcd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 29 Oct 2020 15:58:40 +0100 Subject: z2ram: use separate gendisk for the different modes Use separate gendisks (which share a tag_set) for the different operating modes instead of redirecting the gendisk lookup using a probe callback. This avoids potential problems with aliased block_device instances and will eventually allow for removing the blk_register_region framework. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/block/z2ram.c | 100 +++++++++++++++++++++++++++++--------------------- 1 file changed, 58 insertions(+), 42 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index eafecc9a72b3..c1d20818e649 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -63,7 +63,7 @@ static int current_device = -1; static DEFINE_SPINLOCK(z2ram_lock); -static struct gendisk *z2ram_gendisk; +static struct gendisk *z2ram_gendisk[Z2MINOR_COUNT]; static blk_status_t z2_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) @@ -283,7 +283,7 @@ static int z2_open(struct block_device *bdev, fmode_t mode) current_device = device; z2ram_size <<= Z2RAM_CHUNKSHIFT; - set_capacity(z2ram_gendisk, z2ram_size >> 9); + set_capacity(z2ram_gendisk[device], z2ram_size >> 9); } mutex_unlock(&z2ram_mutex); @@ -315,71 +315,87 @@ static const struct block_device_operations z2_fops = { .release = z2_release, }; -static struct kobject *z2_find(dev_t dev, int *part, void *data) -{ - *part = 0; - return get_disk_and_module(z2ram_gendisk); -} - -static struct request_queue *z2_queue; static struct blk_mq_tag_set tag_set; static const struct blk_mq_ops z2_mq_ops = { .queue_rq = z2_queue_rq, }; +static int z2ram_register_disk(int minor) +{ + struct request_queue *q; + struct gendisk *disk; + + disk = alloc_disk(1); + if (!disk) + return -ENOMEM; + + q = blk_mq_init_queue(&tag_set); + if (IS_ERR(q)) { + put_disk(disk); + return PTR_ERR(q); + } + + disk->major = Z2RAM_MAJOR; + disk->first_minor = minor; + disk->fops = &z2_fops; + if (minor) + sprintf(disk->disk_name, "z2ram%d", minor); + else + sprintf(disk->disk_name, "z2ram"); + disk->queue = q; + + z2ram_gendisk[minor] = disk; + add_disk(disk); + return 0; +} + static int __init z2_init(void) { - int ret; + int ret, i; if (!MACH_IS_AMIGA) return -ENODEV; - ret = -EBUSY; if (register_blkdev(Z2RAM_MAJOR, DEVICE_NAME)) - goto err; - - ret = -ENOMEM; - z2ram_gendisk = alloc_disk(1); - if (!z2ram_gendisk) - goto out_disk; - - z2_queue = blk_mq_init_sq_queue(&tag_set, &z2_mq_ops, 16, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(z2_queue)) { - ret = PTR_ERR(z2_queue); - z2_queue = NULL; - goto out_queue; + return -EBUSY; + + tag_set.ops = &z2_mq_ops; + tag_set.nr_hw_queues = 1; + tag_set.nr_maps = 1; + tag_set.queue_depth = 16; + tag_set.numa_node = NUMA_NO_NODE; + tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + ret = blk_mq_alloc_tag_set(&tag_set); + if (ret) + goto out_unregister_blkdev; + + for (i = 0; i < Z2MINOR_COUNT; i++) { + ret = z2ram_register_disk(i); + if (ret && i == 0) + goto out_free_tagset; } - z2ram_gendisk->major = Z2RAM_MAJOR; - z2ram_gendisk->first_minor = 0; - z2ram_gendisk->fops = &z2_fops; - sprintf(z2ram_gendisk->disk_name, "z2ram"); - - z2ram_gendisk->queue = z2_queue; - add_disk(z2ram_gendisk); - blk_register_region(MKDEV(Z2RAM_MAJOR, 0), Z2MINOR_COUNT, THIS_MODULE, - z2_find, NULL, NULL); - return 0; -out_queue: - put_disk(z2ram_gendisk); -out_disk: +out_free_tagset: + blk_mq_free_tag_set(&tag_set); +out_unregister_blkdev: unregister_blkdev(Z2RAM_MAJOR, DEVICE_NAME); -err: return ret; } static void __exit z2_exit(void) { int i, j; - blk_unregister_region(MKDEV(Z2RAM_MAJOR, 0), Z2MINOR_COUNT); + unregister_blkdev(Z2RAM_MAJOR, DEVICE_NAME); - del_gendisk(z2ram_gendisk); - put_disk(z2ram_gendisk); - blk_cleanup_queue(z2_queue); + + for (i = 0; i < Z2MINOR_COUNT; i++) { + del_gendisk(z2ram_gendisk[i]); + blk_cleanup_queue(z2ram_gendisk[i]->queue); + put_disk(z2ram_gendisk[i]); + } blk_mq_free_tag_set(&tag_set); if (current_device != -1) { -- cgit v1.2.3 From 3b4f85d02a4bd85cbea999a064235a47694bbb7b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:56:53 +0100 Subject: loop: let set_capacity_revalidate_and_notify update the bdev size There is no good reason to call revalidate_disk_size separately. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- drivers/block/loop.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 22e59410b971..fcc5e32f0993 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -251,12 +251,8 @@ loop_validate_block_size(unsigned short bsize) */ static void loop_set_size(struct loop_device *lo, loff_t size) { - struct block_device *bdev = lo->lo_device; - - bd_set_nr_sectors(bdev, size); - - if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, false)) - kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); + if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, true)) + kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); } static inline int -- cgit v1.2.3 From 449f4ec9892ebc2f37a7eae6d97db2cf7c65e09a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:56:56 +0100 Subject: block: remove the update_bdev parameter to set_capacity_revalidate_and_notify The update_bdev argument is always set to true, so remove it. Also rename the function to the slighly less verbose set_capacity_and_notify, as propagating the disk size to the block device isn't really revalidation. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Petr Vorel Signed-off-by: Jens Axboe --- block/genhd.c | 13 +++++-------- drivers/block/loop.c | 2 +- drivers/block/virtio_blk.c | 2 +- drivers/block/xen-blkfront.c | 2 +- drivers/nvme/host/core.c | 2 +- drivers/scsi/sd.c | 5 ++--- include/linux/genhd.h | 3 +-- 7 files changed, 12 insertions(+), 17 deletions(-) (limited to 'drivers/block') diff --git a/block/genhd.c b/block/genhd.c index ec2a24799cd9..4e039524f92b 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -47,17 +47,15 @@ static void disk_del_events(struct gendisk *disk); static void disk_release_events(struct gendisk *disk); /* - * Set disk capacity and notify if the size is not currently - * zero and will not be set to zero + * Set disk capacity and notify if the size is not currently zero and will not + * be set to zero. Returns true if a uevent was sent, otherwise false. */ -bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, - bool update_bdev) +bool set_capacity_and_notify(struct gendisk *disk, sector_t size) { sector_t capacity = get_capacity(disk); set_capacity(disk, size); - if (update_bdev) - revalidate_disk_size(disk, true); + revalidate_disk_size(disk, true); if (capacity != size && capacity != 0 && size != 0) { char *envp[] = { "RESIZE=1", NULL }; @@ -68,8 +66,7 @@ bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, return false; } - -EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify); +EXPORT_SYMBOL_GPL(set_capacity_and_notify); /* * Format the device name of the indicated disk into the supplied buffer and diff --git a/drivers/block/loop.c b/drivers/block/loop.c index fcc5e32f0993..9a27d4f1c08a 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -251,7 +251,7 @@ loop_validate_block_size(unsigned short bsize) */ static void loop_set_size(struct loop_device *lo, loff_t size) { - if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, true)) + if (!set_capacity_and_notify(lo->lo_disk, size)) kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index a314b9382442..3e812b4c32e6 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -470,7 +470,7 @@ static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize) cap_str_10, cap_str_2); - set_capacity_revalidate_and_notify(vblk->disk, capacity, true); + set_capacity_and_notify(vblk->disk, capacity); } static void virtblk_config_changed_work(struct work_struct *work) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 48629d3433b4..79521e33d30e 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2370,7 +2370,7 @@ static void blkfront_connect(struct blkfront_info *info) return; printk(KERN_INFO "Setting capacity to %Lu\n", sectors); - set_capacity_revalidate_and_notify(info->gd, sectors, true); + set_capacity_and_notify(info->gd, sectors); return; case BLKIF_STATE_SUSPENDED: diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f6c6479da0e9..6c144e748f8c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2053,7 +2053,7 @@ static void nvme_update_disk_info(struct gendisk *disk, capacity = 0; } - set_capacity_revalidate_and_notify(disk, capacity, true); + set_capacity_and_notify(disk, capacity); nvme_config_discard(disk, ns); nvme_config_write_zeroes(disk, ns); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index e9b898a1a480..679c2c025047 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3261,8 +3261,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sdkp->first_scan = 0; - set_capacity_revalidate_and_notify(disk, - logical_to_sectors(sdp, sdkp->capacity), true); + set_capacity_and_notify(disk, logical_to_sectors(sdp, sdkp->capacity)); sd_config_write_same(sdkp); kfree(buffer); @@ -3272,7 +3271,7 @@ static int sd_revalidate_disk(struct gendisk *disk) * capacity to 0. */ if (sd_zbc_revalidate_zones(sdkp)) - set_capacity_revalidate_and_notify(disk, 0, true); + set_capacity_and_notify(disk, 0); out: return 0; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 3cbc2781ef34..46553d6d6025 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -314,8 +314,7 @@ static inline int get_disk_ro(struct gendisk *disk) extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); -bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, - bool update_bdev); +bool set_capacity_and_notify(struct gendisk *disk, sector_t size); /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; -- cgit v1.2.3 From ee4bf648635055d2b76afadaf34236c8b2d852a7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:56:57 +0100 Subject: nbd: remove the call to set_blocksize Block driver have no business setting the file system concept of a block size. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index aaae9220f3a0..a9a0b49ff161 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -296,7 +296,7 @@ static void nbd_size_clear(struct nbd_device *nbd) } } -static void nbd_size_update(struct nbd_device *nbd, bool start) +static void nbd_size_update(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; struct block_device *bdev = bdget_disk(nbd->disk, 0); @@ -311,11 +311,9 @@ static void nbd_size_update(struct nbd_device *nbd, bool start) blk_queue_physical_block_size(nbd->disk->queue, config->blksize); set_capacity(nbd->disk, nr_sectors); if (bdev) { - if (bdev->bd_disk) { + if (bdev->bd_disk) bd_set_nr_sectors(bdev, nr_sectors); - if (start) - set_blocksize(bdev, config->blksize); - } else + else set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); bdput(bdev); } @@ -329,7 +327,7 @@ static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize, config->blksize = blocksize; config->bytesize = blocksize * nr_blocks; if (nbd->task_recv != NULL) - nbd_size_update(nbd, false); + nbd_size_update(nbd); } static void nbd_complete_rq(struct request *req) @@ -1309,7 +1307,7 @@ static int nbd_start_device(struct nbd_device *nbd) args->index = i; queue_work(nbd->recv_workq, &args->work); } - nbd_size_update(nbd, true); + nbd_size_update(nbd); return error; } -- cgit v1.2.3 From 92f93c3a1bf9dc73181dc6566497d16b690cb576 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:56:58 +0100 Subject: nbd: move the task_recv check into nbd_size_update nbd_size_update is about to acquire a few more callers, so lift the check into the function. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index a9a0b49ff161..48054051e281 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -299,8 +299,11 @@ static void nbd_size_clear(struct nbd_device *nbd) static void nbd_size_update(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; - struct block_device *bdev = bdget_disk(nbd->disk, 0); sector_t nr_sectors = config->bytesize >> 9; + struct block_device *bdev; + + if (!nbd->task_recv) + return; if (config->flags & NBD_FLAG_SEND_TRIM) { nbd->disk->queue->limits.discard_granularity = config->blksize; @@ -309,7 +312,9 @@ static void nbd_size_update(struct nbd_device *nbd) } blk_queue_logical_block_size(nbd->disk->queue, config->blksize); blk_queue_physical_block_size(nbd->disk->queue, config->blksize); + set_capacity(nbd->disk, nr_sectors); + bdev = bdget_disk(nbd->disk, 0); if (bdev) { if (bdev->bd_disk) bd_set_nr_sectors(bdev, nr_sectors); @@ -326,8 +331,7 @@ static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize, struct nbd_config *config = nbd->config; config->blksize = blocksize; config->bytesize = blocksize * nr_blocks; - if (nbd->task_recv != NULL) - nbd_size_update(nbd); + nbd_size_update(nbd); } static void nbd_complete_rq(struct request *req) -- cgit v1.2.3 From 2dc691cc4ac259f8b5bb0bd8670645af894d30eb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:56:59 +0100 Subject: nbd: refactor size updates Merge nbd_size_set and nbd_size_update into a single function that also updates the nbd_config fields. This new function takes the device size in bytes as the first argument, and the blocksize as the second argument, simplifying the calculations required in most callers. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 44 ++++++++++++++++++-------------------------- 1 file changed, 18 insertions(+), 26 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 48054051e281..6e8f2ff715c6 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -296,28 +296,30 @@ static void nbd_size_clear(struct nbd_device *nbd) } } -static void nbd_size_update(struct nbd_device *nbd) +static void nbd_set_size(struct nbd_device *nbd, loff_t bytesize, + loff_t blksize) { - struct nbd_config *config = nbd->config; - sector_t nr_sectors = config->bytesize >> 9; struct block_device *bdev; + nbd->config->bytesize = bytesize; + nbd->config->blksize = blksize; + if (!nbd->task_recv) return; - if (config->flags & NBD_FLAG_SEND_TRIM) { - nbd->disk->queue->limits.discard_granularity = config->blksize; - nbd->disk->queue->limits.discard_alignment = config->blksize; + if (nbd->config->flags & NBD_FLAG_SEND_TRIM) { + nbd->disk->queue->limits.discard_granularity = blksize; + nbd->disk->queue->limits.discard_alignment = blksize; blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); } - blk_queue_logical_block_size(nbd->disk->queue, config->blksize); - blk_queue_physical_block_size(nbd->disk->queue, config->blksize); + blk_queue_logical_block_size(nbd->disk->queue, blksize); + blk_queue_physical_block_size(nbd->disk->queue, blksize); - set_capacity(nbd->disk, nr_sectors); + set_capacity(nbd->disk, bytesize >> 9); bdev = bdget_disk(nbd->disk, 0); if (bdev) { if (bdev->bd_disk) - bd_set_nr_sectors(bdev, nr_sectors); + bd_set_nr_sectors(bdev, bytesize >> 9); else set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); bdput(bdev); @@ -325,15 +327,6 @@ static void nbd_size_update(struct nbd_device *nbd) kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); } -static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize, - loff_t nr_blocks) -{ - struct nbd_config *config = nbd->config; - config->blksize = blocksize; - config->bytesize = blocksize * nr_blocks; - nbd_size_update(nbd); -} - static void nbd_complete_rq(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); @@ -1311,7 +1304,7 @@ static int nbd_start_device(struct nbd_device *nbd) args->index = i; queue_work(nbd->recv_workq, &args->work); } - nbd_size_update(nbd); + nbd_set_size(nbd, config->bytesize, config->blksize); return error; } @@ -1390,15 +1383,14 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, arg = NBD_DEF_BLKSIZE; if (!nbd_is_valid_blksize(arg)) return -EINVAL; - nbd_size_set(nbd, arg, - div_s64(config->bytesize, arg)); + nbd_set_size(nbd, config->bytesize, arg); return 0; case NBD_SET_SIZE: - nbd_size_set(nbd, config->blksize, - div_s64(arg, config->blksize)); + nbd_set_size(nbd, arg, config->blksize); return 0; case NBD_SET_SIZE_BLOCKS: - nbd_size_set(nbd, config->blksize, arg); + nbd_set_size(nbd, arg * config->blksize, + config->blksize); return 0; case NBD_SET_TIMEOUT: nbd_set_cmd_timeout(nbd, arg); @@ -1828,7 +1820,7 @@ static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) } if (bytes != config->bytesize || bsize != config->blksize) - nbd_size_set(nbd, bsize, div64_u64(bytes, bsize)); + nbd_set_size(nbd, bytes, bsize); return 0; } -- cgit v1.2.3 From dcbddf541f18e367ac9cdad8e223d382cd303161 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:00 +0100 Subject: nbd: validate the block size in nbd_set_size Move the validation of the block from the callers into nbd_set_size. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 47 +++++++++++++++-------------------------------- 1 file changed, 15 insertions(+), 32 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 6e8f2ff715c6..7478a5e02bc1 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -296,16 +296,21 @@ static void nbd_size_clear(struct nbd_device *nbd) } } -static void nbd_set_size(struct nbd_device *nbd, loff_t bytesize, +static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { struct block_device *bdev; + if (!blksize) + blksize = NBD_DEF_BLKSIZE; + if (blksize < 512 || blksize > PAGE_SIZE || !is_power_of_2(blksize)) + return -EINVAL; + nbd->config->bytesize = bytesize; nbd->config->blksize = blksize; if (!nbd->task_recv) - return; + return 0; if (nbd->config->flags & NBD_FLAG_SEND_TRIM) { nbd->disk->queue->limits.discard_granularity = blksize; @@ -325,6 +330,7 @@ static void nbd_set_size(struct nbd_device *nbd, loff_t bytesize, bdput(bdev); } kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); + return 0; } static void nbd_complete_rq(struct request *req) @@ -1304,8 +1310,7 @@ static int nbd_start_device(struct nbd_device *nbd) args->index = i; queue_work(nbd->recv_workq, &args->work); } - nbd_set_size(nbd, config->bytesize, config->blksize); - return error; + return nbd_set_size(nbd, config->bytesize, config->blksize); } static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev) @@ -1347,14 +1352,6 @@ static void nbd_clear_sock_ioctl(struct nbd_device *nbd, nbd_config_put(nbd); } -static bool nbd_is_valid_blksize(unsigned long blksize) -{ - if (!blksize || !is_power_of_2(blksize) || blksize < 512 || - blksize > PAGE_SIZE) - return false; - return true; -} - static void nbd_set_cmd_timeout(struct nbd_device *nbd, u64 timeout) { nbd->tag_set.timeout = timeout * HZ; @@ -1379,19 +1376,12 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, case NBD_SET_SOCK: return nbd_add_socket(nbd, arg, false); case NBD_SET_BLKSIZE: - if (!arg) - arg = NBD_DEF_BLKSIZE; - if (!nbd_is_valid_blksize(arg)) - return -EINVAL; - nbd_set_size(nbd, config->bytesize, arg); - return 0; + return nbd_set_size(nbd, config->bytesize, arg); case NBD_SET_SIZE: - nbd_set_size(nbd, arg, config->blksize); - return 0; + return nbd_set_size(nbd, arg, config->blksize); case NBD_SET_SIZE_BLOCKS: - nbd_set_size(nbd, arg * config->blksize, - config->blksize); - return 0; + return nbd_set_size(nbd, arg * config->blksize, + config->blksize); case NBD_SET_TIMEOUT: nbd_set_cmd_timeout(nbd, arg); return 0; @@ -1809,18 +1799,11 @@ static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) if (info->attrs[NBD_ATTR_SIZE_BYTES]) bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]); - if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) { + if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) bsize = nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]); - if (!bsize) - bsize = NBD_DEF_BLKSIZE; - if (!nbd_is_valid_blksize(bsize)) { - printk(KERN_ERR "Invalid block size %llu\n", bsize); - return -EINVAL; - } - } if (bytes != config->bytesize || bsize != config->blksize) - nbd_set_size(nbd, bytes, bsize); + return nbd_set_size(nbd, bytes, bsize); return 0; } -- cgit v1.2.3 From 2ebcabf3dba50f61850efec9a331bd061c6333e0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:01 +0100 Subject: nbd: use set_capacity_and_notify Use set_capacity_and_notify to update the disk and block device sizes and send a RESIZE uevent to userspace. Note that blktests relies on uevents being sent also for updates that did not change the device size, so the explicit kobject_uevent remains for that case. Signed-off-by: Christoph Hellwig Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 7478a5e02bc1..45b0423ef2c5 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -299,8 +299,6 @@ static void nbd_size_clear(struct nbd_device *nbd) static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { - struct block_device *bdev; - if (!blksize) blksize = NBD_DEF_BLKSIZE; if (blksize < 512 || blksize > PAGE_SIZE || !is_power_of_2(blksize)) @@ -320,16 +318,9 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, blk_queue_logical_block_size(nbd->disk->queue, blksize); blk_queue_physical_block_size(nbd->disk->queue, blksize); - set_capacity(nbd->disk, bytesize >> 9); - bdev = bdget_disk(nbd->disk, 0); - if (bdev) { - if (bdev->bd_disk) - bd_set_nr_sectors(bdev, bytesize >> 9); - else - set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); - bdput(bdev); - } - kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); + set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); + if (!set_capacity_and_notify(nbd->disk, bytesize >> 9)) + kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); return 0; } -- cgit v1.2.3 From 8a6f7bbf29d1d61d3ff18f0a0feead9f287c9b14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:02 +0100 Subject: aoe: don't call set_capacity from irq context Updating the block device size from irq context can lead to torn writes of the 64-bit value, and prevents us from using normal process context locking primitives to serialize access to the 64-bit nr_sectors value. Defer the set_capacity to the already existing workqueue handler, where it can be merged with the update of the block device size by using set_capacity_and_notify. As an extra bonus this also adds proper uevent notifications for the resize. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/aoe/aoecmd.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 313f0b946fe2..ac720bdcd983 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -890,19 +890,13 @@ void aoecmd_sleepwork(struct work_struct *work) { struct aoedev *d = container_of(work, struct aoedev, work); - struct block_device *bd; - u64 ssize; if (d->flags & DEVFL_GDALLOC) aoeblk_gdalloc(d); if (d->flags & DEVFL_NEWSIZE) { - ssize = get_capacity(d->gd); - bd = bdget_disk(d->gd, 0); - if (bd) { - bd_set_nr_sectors(bd, ssize); - bdput(bd); - } + set_capacity_and_notify(d->gd, d->ssize); + spin_lock_irq(&d->lock); d->flags |= DEVFL_UP; d->flags &= ~DEVFL_NEWSIZE; @@ -971,10 +965,9 @@ ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id) d->geo.start = 0; if (d->flags & (DEVFL_GDALLOC|DEVFL_NEWSIZE)) return; - if (d->gd != NULL) { - set_capacity(d->gd, ssize); + if (d->gd != NULL) d->flags |= DEVFL_NEWSIZE; - } else + else d->flags |= DEVFL_GDALLOC; schedule_work(&d->work); } -- cgit v1.2.3 From 657985f857c0027db6f17fa4af7e8818038e0b15 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:04 +0100 Subject: pktcdvd: use set_capacity_and_notify Use set_capacity_and_notify to set the size of both the disk and block device. This also gets the uevent notifications for the resize for free. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/pktcdvd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index ef1c1f094ea4..b8bb8ec7538d 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2130,8 +2130,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) } set_capacity(pd->disk, lba << 2); - set_capacity(pd->bdev->bd_disk, lba << 2); - bd_set_nr_sectors(pd->bdev, lba << 2); + set_capacity_and_notify(pd->bdev->bd_disk, lba << 2); q = bdev_get_queue(pd->bdev); if (write) { -- cgit v1.2.3 From bc254eb44f9dfce278b53b714fb7bb963253789d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:06 +0100 Subject: drbd: use set_capacity_and_notify Use set_capacity_and_notify to set the size of both the disk and block device. This also gets the uevent notifications for the resize for free. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_main.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 65b95aef8dbc..1c8c18b2a25f 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2036,8 +2036,7 @@ void drbd_set_my_capacity(struct drbd_device *device, sector_t size) { char ppb[10]; - set_capacity(device->vdisk, size); - revalidate_disk_size(device->vdisk, false); + set_capacity_and_notify(device->vdisk, size); drbd_info(device, "size = %s (%llu KB)\n", ppsize(ppb, size>>1), (unsigned long long)size>>1); @@ -2068,8 +2067,7 @@ void drbd_device_cleanup(struct drbd_device *device) } D_ASSERT(device, first_peer_device(device)->connection->net_conf == NULL); - set_capacity(device->vdisk, 0); - revalidate_disk_size(device->vdisk, false); + set_capacity_and_notify(device->vdisk, 0); if (device->bitmap) { /* maybe never allocated. */ drbd_bm_resize(device, 0, 1); -- cgit v1.2.3 From e864e49af3a85797b51b36876087591602de2eb4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:07 +0100 Subject: rbd: use set_capacity_and_notify Use set_capacity_and_notify to set the size of both the disk and block device. This also gets the uevent notifications for the resize for free. Signed-off-by: Christoph Hellwig Acked-by: Ilya Dryomov Signed-off-by: Jens Axboe --- drivers/block/rbd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 671733e459cf..2ed79b09439a 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4888,8 +4888,7 @@ static void rbd_dev_update_size(struct rbd_device *rbd_dev) !test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags)) { size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE; dout("setting size to %llu sectors", (unsigned long long)size); - set_capacity(rbd_dev->disk, size); - revalidate_disk_size(rbd_dev->disk, true); + set_capacity_and_notify(rbd_dev->disk, size); } } -- cgit v1.2.3 From 230272b4f809d51c8b21d46dcec99f265b0842ec Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:08 +0100 Subject: rnbd: use set_capacity_and_notify Use set_capacity_and_notify to set the size of both the disk and block device. This also gets the uevent notifications for the resize for free. Signed-off-by: Christoph Hellwig Acked-by: Jack Wang Signed-off-by: Jens Axboe --- drivers/block/rnbd/rnbd-clt.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 8b2411ccbda9..bb13d7dd195a 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -100,8 +100,7 @@ static int rnbd_clt_change_capacity(struct rnbd_clt_dev *dev, rnbd_clt_info(dev, "Device size changed from %zu to %zu sectors\n", dev->nsectors, new_nsectors); dev->nsectors = new_nsectors; - set_capacity(dev->gd, dev->nsectors); - revalidate_disk_size(dev->gd, true); + set_capacity_and_notify(dev->gd, dev->nsectors); return 0; } -- cgit v1.2.3 From 6e017a3931d7722260e3656a6fc9b02de5fb3c5d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:09 +0100 Subject: zram: use set_capacity_and_notify Use set_capacity_and_notify to set the size of both the disk and block device. This also gets the uevent notifications for the resize for free. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/zram/zram_drv.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 1b697208d661..6d15d51cee2b 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1695,7 +1695,7 @@ static void zram_reset_device(struct zram *zram) disksize = zram->disksize; zram->disksize = 0; - set_capacity(zram->disk, 0); + set_capacity_and_notify(zram->disk, 0); part_stat_set_all(&zram->disk->part0, 0); up_write(&zram->init_lock); @@ -1741,9 +1741,7 @@ static ssize_t disksize_store(struct device *dev, zram->comp = comp; zram->disksize = disksize; - set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT); - - revalidate_disk_size(zram->disk, true); + set_capacity_and_notify(zram->disk, zram->disksize >> SECTOR_SHIFT); up_write(&zram->init_lock); return len; @@ -1790,7 +1788,6 @@ static ssize_t reset_store(struct device *dev, /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - revalidate_disk_size(zram->disk, true); bdput(bdev); mutex_lock(&bdev->bd_mutex); -- cgit v1.2.3 From ddff331a14eb7d5af08e63579ba28c289db26e20 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:57:13 +0100 Subject: virtio-blk: remove a spurious call to revalidate_disk_size revalidate_disk_size just updates the block device size from the disk size. Thus calling it from virtblk_update_cache_mode doesn't actually do anything. Signed-off-by: Christoph Hellwig Acked-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: Jens Axboe --- drivers/block/virtio_blk.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/block') diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 3e812b4c32e6..145606dc52db 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -598,7 +598,6 @@ static void virtblk_update_cache_mode(struct virtio_device *vdev) struct virtio_blk *vblk = vdev->priv; blk_queue_write_cache(vblk->disk->queue, writeback, false); - revalidate_disk_size(vblk->disk, true); } static const char *const virtblk_cache_types[] = { -- cgit v1.2.3 From a6419fd810c6b3b060f75b69b09d25ea2ac1f200 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 30 Jun 2020 16:33:54 +0200 Subject: mtip32xx: remove the call to fsync_bdev on removal del_gendisk already calls fsync_bdev for every partition, no need to do this twice. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- drivers/block/mtip32xx/mtip32xx.c | 15 --------------- drivers/block/mtip32xx/mtip32xx.h | 2 -- 2 files changed, 17 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 153e2cdecb4d..53ac59d19ae5 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3687,7 +3687,6 @@ skip_create_disk: /* Enable the block device and add it to /dev */ device_add_disk(&dd->pdev->dev, dd->disk, NULL); - dd->bdev = bdget_disk(dd->disk, 0); /* * Now that the disk is active, initialize any sysfs attributes * managed by the protocol layer. @@ -3721,9 +3720,6 @@ start_service_thread: return rv; kthread_run_error: - bdput(dd->bdev); - dd->bdev = NULL; - /* Delete our gendisk. This also removes the device from /dev */ del_gendisk(dd->disk); @@ -3804,14 +3800,6 @@ static int mtip_block_remove(struct driver_data *dd) blk_mq_tagset_busy_iter(&dd->tags, mtip_no_dev_cleanup, dd); blk_mq_unquiesce_queue(dd->queue); - /* - * Delete our gendisk structure. This also removes the device - * from /dev - */ - if (dd->bdev) { - bdput(dd->bdev); - dd->bdev = NULL; - } if (dd->disk) { if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag)) del_gendisk(dd->disk); @@ -4206,9 +4194,6 @@ static void mtip_pci_remove(struct pci_dev *pdev) } while (atomic_read(&dd->irq_workers_active) != 0 && time_before(jiffies, to)); - if (!dd->sr) - fsync_bdev(dd->bdev); - if (atomic_read(&dd->irq_workers_active) != 0) { dev_warn(&dd->pdev->dev, "Completion workers still active!\n"); diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index e22a7f0523bf..88f4206310e4 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -463,8 +463,6 @@ struct driver_data { int isr_binding; - struct block_device *bdev; - struct list_head online_list; /* linkage for online list */ struct list_head remove_list; /* linkage for removing list */ -- cgit v1.2.3 From ee763e2143e79fa41d2818e620e1e8ff69af87bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:43:46 +0100 Subject: zram: do not call set_blocksize set_blocksize is used by file systems to use their preferred buffer cache block size. Block drivers should not set it. Signed-off-by: Christoph Hellwig Acked-by: Minchan Kim Signed-off-by: Jens Axboe --- drivers/block/zram/zram_drv.c | 11 +---------- drivers/block/zram/zram_drv.h | 1 - 2 files changed, 1 insertion(+), 11 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 6d15d51cee2b..b5f68951c9d2 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -403,13 +403,10 @@ static void reset_bdev(struct zram *zram) return; bdev = zram->bdev; - if (zram->old_block_size) - set_blocksize(bdev, zram->old_block_size); blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); /* hope filp_close flush all of IO */ filp_close(zram->backing_dev, NULL); zram->backing_dev = NULL; - zram->old_block_size = 0; zram->bdev = NULL; zram->disk->fops = &zram_devops; kvfree(zram->bitmap); @@ -454,7 +451,7 @@ static ssize_t backing_dev_store(struct device *dev, struct file *backing_dev = NULL; struct inode *inode; struct address_space *mapping; - unsigned int bitmap_sz, old_block_size = 0; + unsigned int bitmap_sz; unsigned long nr_pages, *bitmap = NULL; struct block_device *bdev = NULL; int err; @@ -509,14 +506,8 @@ static ssize_t backing_dev_store(struct device *dev, goto out; } - old_block_size = block_size(bdev); - err = set_blocksize(bdev, PAGE_SIZE); - if (err) - goto out; - reset_bdev(zram); - zram->old_block_size = old_block_size; zram->bdev = bdev; zram->backing_dev = backing_dev; zram->bitmap = bitmap; diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index f2fd46daa760..712354a4207c 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -118,7 +118,6 @@ struct zram { bool wb_limit_enable; u64 bd_wb_limit; struct block_device *bdev; - unsigned int old_block_size; unsigned long *bitmap; unsigned long nr_pages; #endif -- cgit v1.2.3 From f46f2a3198017cff1f3f8f71de74ff7abee3aa16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 Nov 2020 15:38:30 +0100 Subject: loop: do not call set_blocksize set_blocksize is used by file systems to use their preferred buffer cache block size. Block drivers should not set it. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- drivers/block/loop.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 9a27d4f1c08a..b42c728620c9 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1164,9 +1164,6 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, size = get_loop_size(lo, file); loop_set_size(lo, size); - set_blocksize(bdev, S_ISBLK(inode->i_mode) ? - block_size(inode->i_bdev) : PAGE_SIZE); - lo->lo_state = Lo_bound; if (part_shift) lo->lo_flags |= LO_FLAGS_PARTSCAN; -- cgit v1.2.3 From 4e7b5671c6a883d94b5428e1a9c141bbd56cb2a6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 23 Nov 2020 13:38:40 +0100 Subject: block: remove i_bdev Switch the block device lookup interfaces to directly work with a dev_t so that struct block_device references are only acquired by the blkdev_get variants (and the blk-cgroup special case). This means that we now don't need an extra reference in the inode and can generally simplify handling of struct block_device to keep the lookups contained in the core block layer code. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Tejun Heo Acked-by: Coly Li [bcache] Signed-off-by: Jens Axboe --- block/ioctl.c | 3 +- drivers/block/loop.c | 8 +- drivers/md/bcache/super.c | 20 +-- drivers/md/dm-table.c | 9 +- drivers/mtd/mtdsuper.c | 17 +-- drivers/target/target_core_file.c | 6 +- drivers/usb/gadget/function/storage_common.c | 8 +- fs/block_dev.c | 196 +++++++-------------------- fs/btrfs/volumes.c | 13 +- fs/inode.c | 3 - fs/internal.h | 7 +- fs/io_uring.c | 10 +- fs/pipe.c | 5 +- fs/quota/quota.c | 19 ++- fs/statfs.c | 2 +- fs/super.c | 44 +++--- include/linux/blkdev.h | 2 +- include/linux/fs.h | 1 - 18 files changed, 121 insertions(+), 252 deletions(-) (limited to 'drivers/block') diff --git a/block/ioctl.c b/block/ioctl.c index 0c09bb7a6ff3..a6d8171221c7 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -590,8 +590,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret; void __user *argp = compat_ptr(arg); - struct inode *inode = file->f_mapping->host; - struct block_device *bdev = inode->i_bdev; + struct block_device *bdev = I_BDEV(file->f_mapping->host); struct gendisk *disk = bdev->bd_disk; fmode_t mode = file->f_mode; loff_t size; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index b42c728620c9..26c7aafba7c5 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -675,10 +675,10 @@ static int loop_validate_file(struct file *file, struct block_device *bdev) while (is_loop_device(f)) { struct loop_device *l; - if (f->f_mapping->host->i_bdev == bdev) + if (f->f_mapping->host->i_rdev == bdev->bd_dev) return -EBADF; - l = f->f_mapping->host->i_bdev->bd_disk->private_data; + l = I_BDEV(f->f_mapping->host)->bd_disk->private_data; if (l->lo_state != Lo_bound) { return -EINVAL; } @@ -885,9 +885,7 @@ static void loop_config_discard(struct loop_device *lo) * file-backed loop devices: discarded regions read back as zero. */ if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) { - struct request_queue *backingq; - - backingq = bdev_get_queue(inode->i_bdev); + struct request_queue *backingq = bdev_get_queue(I_BDEV(inode)); max_discard_sectors = backingq->limits.max_write_zeroes_sectors; granularity = backingq->limits.discard_granularity ?: diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index a6a5e21e4fd1..c55d3c58a7ef 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -2380,38 +2380,38 @@ kobj_attribute_write(register, register_bcache); kobj_attribute_write(register_quiet, register_bcache); kobj_attribute_write(pendings_cleanup, bch_pending_bdevs_cleanup); -static bool bch_is_open_backing(struct block_device *bdev) +static bool bch_is_open_backing(dev_t dev) { struct cache_set *c, *tc; struct cached_dev *dc, *t; list_for_each_entry_safe(c, tc, &bch_cache_sets, list) list_for_each_entry_safe(dc, t, &c->cached_devs, list) - if (dc->bdev == bdev) + if (dc->bdev->bd_dev == dev) return true; list_for_each_entry_safe(dc, t, &uncached_devices, list) - if (dc->bdev == bdev) + if (dc->bdev->bd_dev == dev) return true; return false; } -static bool bch_is_open_cache(struct block_device *bdev) +static bool bch_is_open_cache(dev_t dev) { struct cache_set *c, *tc; list_for_each_entry_safe(c, tc, &bch_cache_sets, list) { struct cache *ca = c->cache; - if (ca->bdev == bdev) + if (ca->bdev->bd_dev == dev) return true; } return false; } -static bool bch_is_open(struct block_device *bdev) +static bool bch_is_open(dev_t dev) { - return bch_is_open_cache(bdev) || bch_is_open_backing(bdev); + return bch_is_open_cache(dev) || bch_is_open_backing(dev); } struct async_reg_args { @@ -2535,9 +2535,11 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, sb); if (IS_ERR(bdev)) { if (bdev == ERR_PTR(-EBUSY)) { - bdev = lookup_bdev(strim(path)); + dev_t dev; + mutex_lock(&bch_register_lock); - if (!IS_ERR(bdev) && bch_is_open(bdev)) + if (lookup_bdev(strim(path), &dev) == 0 && + bch_is_open(dev)) err = "device already registered"; else err = "device busy"; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index ce543b761be7..dea677721710 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -348,16 +348,9 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, dev_t dm_get_dev_t(const char *path) { dev_t dev; - struct block_device *bdev; - bdev = lookup_bdev(path); - if (IS_ERR(bdev)) + if (lookup_bdev(path, &dev)) dev = name_to_dev_t(path); - else { - dev = bdev->bd_dev; - bdput(bdev); - } - return dev; } EXPORT_SYMBOL_GPL(dm_get_dev_t); diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c index c3e2098372f2..38b6aa849c63 100644 --- a/drivers/mtd/mtdsuper.c +++ b/drivers/mtd/mtdsuper.c @@ -120,8 +120,8 @@ int get_tree_mtd(struct fs_context *fc, struct fs_context *fc)) { #ifdef CONFIG_BLOCK - struct block_device *bdev; - int ret, major; + dev_t dev; + int ret; #endif int mtdnr; @@ -169,20 +169,15 @@ int get_tree_mtd(struct fs_context *fc, /* try the old way - the hack where we allowed users to mount * /dev/mtdblock$(n) but didn't actually _use_ the blockdev */ - bdev = lookup_bdev(fc->source); - if (IS_ERR(bdev)) { - ret = PTR_ERR(bdev); + ret = lookup_bdev(fc->source, &dev); + if (ret) { errorf(fc, "MTD: Couldn't look up '%s': %d", fc->source, ret); return ret; } pr_debug("MTDSB: lookup_bdev() returned 0\n"); - major = MAJOR(bdev->bd_dev); - mtdnr = MINOR(bdev->bd_dev); - bdput(bdev); - - if (major == MTD_BLOCK_MAJOR) - return mtd_get_sb_by_nr(fc, mtdnr, fill_super); + if (MAJOR(dev) == MTD_BLOCK_MAJOR) + return mtd_get_sb_by_nr(fc, MINOR(dev), fill_super); #endif /* CONFIG_BLOCK */ diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 7143d03f0e02..b0cb5b95e892 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -133,10 +133,10 @@ static int fd_configure_device(struct se_device *dev) */ inode = file->f_mapping->host; if (S_ISBLK(inode->i_mode)) { - struct request_queue *q = bdev_get_queue(inode->i_bdev); + struct request_queue *q = bdev_get_queue(I_BDEV(inode)); unsigned long long dev_size; - fd_dev->fd_block_size = bdev_logical_block_size(inode->i_bdev); + fd_dev->fd_block_size = bdev_logical_block_size(I_BDEV(inode)); /* * Determine the number of bytes from i_size_read() minus * one (1) logical sector from underlying struct block_device @@ -559,7 +559,7 @@ fd_execute_unmap(struct se_cmd *cmd, sector_t lba, sector_t nolb) if (S_ISBLK(inode->i_mode)) { /* The backend is block device, use discard */ - struct block_device *bdev = inode->i_bdev; + struct block_device *bdev = I_BDEV(inode); struct se_device *dev = cmd->se_dev; ret = blkdev_issue_discard(bdev, diff --git a/drivers/usb/gadget/function/storage_common.c b/drivers/usb/gadget/function/storage_common.c index f7e6c42558eb..b859a158a414 100644 --- a/drivers/usb/gadget/function/storage_common.c +++ b/drivers/usb/gadget/function/storage_common.c @@ -204,7 +204,7 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename) if (!(filp->f_mode & FMODE_WRITE)) ro = 1; - inode = file_inode(filp); + inode = filp->f_mapping->host; if ((!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))) { LINFO(curlun, "invalid file type: %s\n", filename); goto out; @@ -221,7 +221,7 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename) if (!(filp->f_mode & FMODE_CAN_WRITE)) ro = 1; - size = i_size_read(inode->i_mapping->host); + size = i_size_read(inode); if (size < 0) { LINFO(curlun, "unable to find file size: %s\n", filename); rc = (int) size; @@ -231,8 +231,8 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename) if (curlun->cdrom) { blksize = 2048; blkbits = 11; - } else if (inode->i_bdev) { - blksize = bdev_logical_block_size(inode->i_bdev); + } else if (S_ISBLK(inode->i_mode)) { + blksize = bdev_logical_block_size(I_BDEV(inode)); blkbits = blksize_bits(blksize); } else { blksize = 512; diff --git a/fs/block_dev.c b/fs/block_dev.c index 2b8c0586314f..6d6e4d50834c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -883,7 +883,6 @@ static struct block_device *bdget(dev_t dev) bdev->bd_dev = dev; inode->i_mode = S_IFBLK; inode->i_rdev = dev; - inode->i_bdev = bdev; inode->i_data.a_ops = &def_blk_aops; mapping_set_gfp_mask(&inode->i_data, GFP_USER); unlock_new_inode(inode); @@ -928,67 +927,8 @@ void bdput(struct block_device *bdev) { iput(bdev->bd_inode); } - EXPORT_SYMBOL(bdput); -static struct block_device *bd_acquire(struct inode *inode) -{ - struct block_device *bdev; - - spin_lock(&bdev_lock); - bdev = inode->i_bdev; - if (bdev && !inode_unhashed(bdev->bd_inode)) { - bdgrab(bdev); - spin_unlock(&bdev_lock); - return bdev; - } - spin_unlock(&bdev_lock); - - /* - * i_bdev references block device inode that was already shut down - * (corresponding device got removed). Remove the reference and look - * up block device inode again just in case new device got - * reestablished under the same device number. - */ - if (bdev) - bd_forget(inode); - - bdev = bdget(inode->i_rdev); - if (bdev) { - spin_lock(&bdev_lock); - if (!inode->i_bdev) { - /* - * We take an additional reference to bd_inode, - * and it's released in clear_inode() of inode. - * So, we can access it via ->i_mapping always - * without igrab(). - */ - bdgrab(bdev); - inode->i_bdev = bdev; - inode->i_mapping = bdev->bd_inode->i_mapping; - } - spin_unlock(&bdev_lock); - } - return bdev; -} - -/* Call when you free inode */ - -void bd_forget(struct inode *inode) -{ - struct block_device *bdev = NULL; - - spin_lock(&bdev_lock); - if (!sb_is_blkdev_sb(inode->i_sb)) - bdev = inode->i_bdev; - inode->i_bdev = NULL; - inode->i_mapping = &inode->i_data; - spin_unlock(&bdev_lock); - - if (bdev) - bdput(bdev); -} - /** * bd_may_claim - test whether a block device can be claimed * @bdev: block device of interest @@ -1497,38 +1437,45 @@ static int __blkdev_get(struct block_device *bdev, struct gendisk *disk, } /** - * blkdev_get - open a block device - * @bdev: block_device to open + * blkdev_get_by_dev - open a block device by device number + * @dev: device number of block device to open * @mode: FMODE_* mask * @holder: exclusive holder identifier * - * Open @bdev with @mode. If @mode includes %FMODE_EXCL, @bdev is - * open with exclusive access. Specifying %FMODE_EXCL with %NULL - * @holder is invalid. Exclusive opens may nest for the same @holder. + * Open the block device described by device number @dev. If @mode includes + * %FMODE_EXCL, the block device is opened with exclusive access. Specifying + * %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may nest for + * the same @holder. * - * On success, the reference count of @bdev is unchanged. On failure, - * @bdev is put. + * Use this interface ONLY if you really do not have anything better - i.e. when + * you are behind a truly sucky interface and all you are given is a device + * number. Everything else should use blkdev_get_by_path(). * * CONTEXT: * Might sleep. * * RETURNS: - * 0 on success, -errno on failure. + * Reference to the block_device on success, ERR_PTR(-errno) on failure. */ -static int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) +struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) { struct block_device *claiming; bool unblock_events = true; + struct block_device *bdev; struct gendisk *disk; int partno; int ret; ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, - imajor(bdev->bd_inode), iminor(bdev->bd_inode), + MAJOR(dev), MINOR(dev), ((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) | ((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0)); if (ret) - goto bdput; + return ERR_PTR(ret); + + bdev = bdget(dev); + if (!bdev) + return ERR_PTR(-ENOMEM); /* * If we lost a race with 'disk' being deleted, try again. See md.c. @@ -1589,10 +1536,13 @@ put_disk: if (ret == -ERESTARTSYS) goto retry; bdput: - if (ret) + if (ret) { bdput(bdev); - return ret; + return ERR_PTR(ret); + } + return bdev; } +EXPORT_SYMBOL(blkdev_get_by_dev); /** * blkdev_get_by_path - open a block device by name @@ -1600,32 +1550,30 @@ bdput: * @mode: FMODE_* mask * @holder: exclusive holder identifier * - * Open the blockdevice described by the device file at @path. @mode - * and @holder are identical to blkdev_get(). - * - * On success, the returned block_device has reference count of one. + * Open the block device described by the device file at @path. If @mode + * includes %FMODE_EXCL, the block device is opened with exclusive access. + * Specifying %FMODE_EXCL with a %NULL @holder is invalid. Exclusive opens may + * nest for the same @holder. * * CONTEXT: * Might sleep. * * RETURNS: - * Pointer to block_device on success, ERR_PTR(-errno) on failure. + * Reference to the block_device on success, ERR_PTR(-errno) on failure. */ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder) { struct block_device *bdev; - int err; - - bdev = lookup_bdev(path); - if (IS_ERR(bdev)) - return bdev; + dev_t dev; + int error; - err = blkdev_get(bdev, mode, holder); - if (err) - return ERR_PTR(err); + error = lookup_bdev(path, &dev); + if (error) + return ERR_PTR(error); - if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) { + bdev = blkdev_get_by_dev(dev, mode, holder); + if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) { blkdev_put(bdev, mode); return ERR_PTR(-EACCES); } @@ -1634,45 +1582,6 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, } EXPORT_SYMBOL(blkdev_get_by_path); -/** - * blkdev_get_by_dev - open a block device by device number - * @dev: device number of block device to open - * @mode: FMODE_* mask - * @holder: exclusive holder identifier - * - * Open the blockdevice described by device number @dev. @mode and - * @holder are identical to blkdev_get(). - * - * Use it ONLY if you really do not have anything better - i.e. when - * you are behind a truly sucky interface and all you are given is a - * device number. _Never_ to be used for internal purposes. If you - * ever need it - reconsider your API. - * - * On success, the returned block_device has reference count of one. - * - * CONTEXT: - * Might sleep. - * - * RETURNS: - * Pointer to block_device on success, ERR_PTR(-errno) on failure. - */ -struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) -{ - struct block_device *bdev; - int err; - - bdev = bdget(dev); - if (!bdev) - return ERR_PTR(-ENOMEM); - - err = blkdev_get(bdev, mode, holder); - if (err) - return ERR_PTR(err); - - return bdev; -} -EXPORT_SYMBOL(blkdev_get_by_dev); - static int blkdev_open(struct inode * inode, struct file * filp) { struct block_device *bdev; @@ -1694,14 +1603,12 @@ static int blkdev_open(struct inode * inode, struct file * filp) if ((filp->f_flags & O_ACCMODE) == 3) filp->f_mode |= FMODE_WRITE_IOCTL; - bdev = bd_acquire(inode); - if (bdev == NULL) - return -ENOMEM; - + bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp); + if (IS_ERR(bdev)) + return PTR_ERR(bdev); filp->f_mapping = bdev->bd_inode->i_mapping; filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); - - return blkdev_get(bdev, filp->f_mode, filp); + return 0; } static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) @@ -2010,37 +1917,32 @@ const struct file_operations def_blk_fops = { * namespace if possible and return it. Return ERR_PTR(error) * otherwise. */ -struct block_device *lookup_bdev(const char *pathname) +int lookup_bdev(const char *pathname, dev_t *dev) { - struct block_device *bdev; struct inode *inode; struct path path; int error; if (!pathname || !*pathname) - return ERR_PTR(-EINVAL); + return -EINVAL; error = kern_path(pathname, LOOKUP_FOLLOW, &path); if (error) - return ERR_PTR(error); + return error; inode = d_backing_inode(path.dentry); error = -ENOTBLK; if (!S_ISBLK(inode->i_mode)) - goto fail; + goto out_path_put; error = -EACCES; if (!may_open_dev(&path)) - goto fail; - error = -ENOMEM; - bdev = bd_acquire(inode); - if (!bdev) - goto fail; -out: + goto out_path_put; + + *dev = inode->i_rdev; + error = 0; +out_path_put: path_put(&path); - return bdev; -fail: - bdev = ERR_PTR(error); - goto out; + return error; } EXPORT_SYMBOL(lookup_bdev); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a6406b3b8c2b..fbc4b58228f7 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -929,16 +929,16 @@ static noinline struct btrfs_device *device_list_add(const char *path, * make sure it's the same device if the device is mounted */ if (device->bdev) { - struct block_device *path_bdev; + int error; + dev_t path_dev; - path_bdev = lookup_bdev(path); - if (IS_ERR(path_bdev)) { + error = lookup_bdev(path, &path_dev); + if (error) { mutex_unlock(&fs_devices->device_list_mutex); - return ERR_CAST(path_bdev); + return ERR_PTR(error); } - if (device->bdev != path_bdev) { - bdput(path_bdev); + if (device->bdev->bd_dev != path_dev) { mutex_unlock(&fs_devices->device_list_mutex); btrfs_warn_in_rcu(device->fs_info, "duplicate device %s devid %llu generation %llu scanned by %s (%d)", @@ -947,7 +947,6 @@ static noinline struct btrfs_device *device_list_add(const char *path, task_pid_nr(current)); return ERR_PTR(-EEXIST); } - bdput(path_bdev); btrfs_info_in_rcu(device->fs_info, "devid %llu device path %s changed to %s scanned by %s (%d)", devid, rcu_str_deref(device->name), diff --git a/fs/inode.c b/fs/inode.c index 9d78c37b00b8..cb008acf0efd 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -155,7 +155,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_bytes = 0; inode->i_generation = 0; inode->i_pipe = NULL; - inode->i_bdev = NULL; inode->i_cdev = NULL; inode->i_link = NULL; inode->i_dir_seq = 0; @@ -580,8 +579,6 @@ static void evict(struct inode *inode) truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } - if (S_ISBLK(inode->i_mode) && inode->i_bdev) - bd_forget(inode); if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); diff --git a/fs/internal.h b/fs/internal.h index 47be21dfeebe..53f890446e75 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -25,7 +25,6 @@ extern void __init bdev_cache_init(void); extern int __sync_blockdev(struct block_device *bdev, int wait); void iterate_bdevs(void (*)(struct block_device *, void *), void *); void emergency_thaw_bdev(struct super_block *sb); -void bd_forget(struct inode *inode); #else static inline void bdev_cache_init(void) { @@ -43,9 +42,6 @@ static inline int emergency_thaw_bdev(struct super_block *sb) { return 0; } -static inline void bd_forget(struct inode *inode) -{ -} #endif /* CONFIG_BLOCK */ /* @@ -114,8 +110,7 @@ extern struct file *alloc_empty_file_noaccount(int, const struct cred *); */ extern int reconfigure_super(struct fs_context *); extern bool trylock_super(struct super_block *sb); -struct super_block *__get_super(struct block_device *bdev, bool excl); -extern struct super_block *user_get_super(dev_t); +struct super_block *user_get_super(dev_t, bool excl); void put_super(struct super_block *sb); extern bool mount_capable(struct fs_context *); diff --git a/fs/io_uring.c b/fs/io_uring.c index 4ead291b2976..8f13c0417f94 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2716,11 +2716,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd) static bool io_bdev_nowait(struct block_device *bdev) { -#ifdef CONFIG_BLOCK return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); -#else - return true; -#endif } /* @@ -2733,14 +2729,16 @@ static bool io_file_supports_async(struct file *file, int rw) umode_t mode = file_inode(file)->i_mode; if (S_ISBLK(mode)) { - if (io_bdev_nowait(file->f_inode->i_bdev)) + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(I_BDEV(file->f_mapping->host))) return true; return false; } if (S_ISCHR(mode) || S_ISSOCK(mode)) return true; if (S_ISREG(mode)) { - if (io_bdev_nowait(file->f_inode->i_sb->s_bdev) && + if (IS_ENABLED(CONFIG_BLOCK) && + io_bdev_nowait(file->f_inode->i_sb->s_bdev) && file->f_op != &io_uring_fops) return true; return false; diff --git a/fs/pipe.c b/fs/pipe.c index 0ac197658a2d..c5989cfd564d 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1342,9 +1342,8 @@ out_revert_acct: } /* - * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same - * location, so checking ->i_pipe is not enough to verify that this is a - * pipe. + * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is + * not enough to verify that this is a pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { diff --git a/fs/quota/quota.c b/fs/quota/quota.c index f3d32b0d9008..6d16b2be5ac4 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -866,17 +866,18 @@ static bool quotactl_cmd_onoff(int cmd) static struct super_block *quotactl_block(const char __user *special, int cmd) { #ifdef CONFIG_BLOCK - struct block_device *bdev; struct super_block *sb; struct filename *tmp = getname(special); bool excl = false, thawed = false; + int error; + dev_t dev; if (IS_ERR(tmp)) return ERR_CAST(tmp); - bdev = lookup_bdev(tmp->name); + error = lookup_bdev(tmp->name, &dev); putname(tmp); - if (IS_ERR(bdev)) - return ERR_CAST(bdev); + if (error) + return ERR_PTR(error); if (quotactl_cmd_onoff(cmd)) { excl = true; @@ -886,8 +887,10 @@ static struct super_block *quotactl_block(const char __user *special, int cmd) } retry: - sb = __get_super(bdev, excl); - if (thawed && sb && sb->s_writers.frozen != SB_UNFROZEN) { + sb = user_get_super(dev, excl); + if (!sb) + return ERR_PTR(-ENODEV); + if (thawed && sb->s_writers.frozen != SB_UNFROZEN) { if (excl) up_write(&sb->s_umount); else @@ -897,10 +900,6 @@ retry: put_super(sb); goto retry; } - - bdput(bdev); - if (!sb) - return ERR_PTR(-ENODEV); return sb; #else diff --git a/fs/statfs.c b/fs/statfs.c index 59f33752c131..68cb07788750 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -235,7 +235,7 @@ SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user static int vfs_ustat(dev_t dev, struct kstatfs *sbuf) { - struct super_block *s = user_get_super(dev); + struct super_block *s = user_get_super(dev, false); int err; if (!s) return -EINVAL; diff --git a/fs/super.c b/fs/super.c index 343e5c1e538d..2c6cdea2ab2d 100644 --- a/fs/super.c +++ b/fs/super.c @@ -740,7 +740,14 @@ void iterate_supers_type(struct file_system_type *type, EXPORT_SYMBOL(iterate_supers_type); -struct super_block *__get_super(struct block_device *bdev, bool excl) +/** + * get_super - get the superblock of a device + * @bdev: device to get the superblock for + * + * Scans the superblock list and finds the superblock of the file system + * mounted on the device given. %NULL is returned if no match is found. + */ +struct super_block *get_super(struct block_device *bdev) { struct super_block *sb; @@ -755,17 +762,11 @@ rescan: if (sb->s_bdev == bdev) { sb->s_count++; spin_unlock(&sb_lock); - if (!excl) - down_read(&sb->s_umount); - else - down_write(&sb->s_umount); + down_read(&sb->s_umount); /* still alive? */ if (sb->s_root && (sb->s_flags & SB_BORN)) return sb; - if (!excl) - up_read(&sb->s_umount); - else - up_write(&sb->s_umount); + up_read(&sb->s_umount); /* nope, got unmounted */ spin_lock(&sb_lock); __put_super(sb); @@ -776,19 +777,6 @@ rescan: return NULL; } -/** - * get_super - get the superblock of a device - * @bdev: device to get the superblock for - * - * Scans the superblock list and finds the superblock of the file system - * mounted on the device given. %NULL is returned if no match is found. - */ -struct super_block *get_super(struct block_device *bdev) -{ - return __get_super(bdev, false); -} -EXPORT_SYMBOL(get_super); - /** * get_active_super - get an active reference to the superblock of a device * @bdev: device to get the superblock for @@ -820,7 +808,7 @@ restart: return NULL; } -struct super_block *user_get_super(dev_t dev) +struct super_block *user_get_super(dev_t dev, bool excl) { struct super_block *sb; @@ -832,11 +820,17 @@ rescan: if (sb->s_dev == dev) { sb->s_count++; spin_unlock(&sb_lock); - down_read(&sb->s_umount); + if (excl) + down_write(&sb->s_umount); + else + down_read(&sb->s_umount); /* still alive? */ if (sb->s_root && (sb->s_flags & SB_BORN)) return sb; - up_read(&sb->s_umount); + if (excl) + up_write(&sb->s_umount); + else + up_read(&sb->s_umount); /* nope, got unmounted */ spin_lock(&sb_lock); __put_super(sb); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 12810a19edeb..bdd7339bcda4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1973,7 +1973,7 @@ int bdev_read_only(struct block_device *bdev); int set_blocksize(struct block_device *bdev, int size); const char *bdevname(struct block_device *bdev, char *buffer); -struct block_device *lookup_bdev(const char *); +int lookup_bdev(const char *pathname, dev_t *dev); void blkdev_show(struct seq_file *seqf, off_t offset); diff --git a/include/linux/fs.h b/include/linux/fs.h index a61df0dd4f19..b0b358309657 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -696,7 +696,6 @@ struct inode { struct list_head i_devices; union { struct pipe_inode_info *i_pipe; - struct block_device *i_bdev; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; -- cgit v1.2.3 From a954ea812018a84d350b316c39a2be3edc4b7ca8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 23 Nov 2020 13:29:55 +0100 Subject: block: remove ->bd_contains Now that each hd_struct has a reference to the corresponding block_device, there is no need for the bd_contains pointer. Add a bdev_whole() helper to look up the whole device block_device struture instead. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- drivers/block/loop.c | 2 +- drivers/scsi/scsicam.c | 2 +- fs/block_dev.c | 22 ++++++++-------------- include/linux/blk_types.h | 4 +++- 4 files changed, 13 insertions(+), 17 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 26c7aafba7c5..c0df88b3300c 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1088,7 +1088,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, * here to avoid changing device under exclusive owner. */ if (!(mode & FMODE_EXCL)) { - claimed_bdev = bdev->bd_contains; + claimed_bdev = bdev_whole(bdev); error = bd_prepare_to_claim(bdev, claimed_bdev, loop_configure); if (error) goto out_putf; diff --git a/drivers/scsi/scsicam.c b/drivers/scsi/scsicam.c index 682cf08ab041..f1553a453616 100644 --- a/drivers/scsi/scsicam.c +++ b/drivers/scsi/scsicam.c @@ -32,7 +32,7 @@ */ unsigned char *scsi_bios_ptable(struct block_device *dev) { - struct address_space *mapping = dev->bd_contains->bd_inode->i_mapping; + struct address_space *mapping = bdev_whole(dev)->bd_inode->i_mapping; unsigned char *res = NULL; struct page *page; diff --git a/fs/block_dev.c b/fs/block_dev.c index b350ed3af83b..94baee369d26 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -119,7 +119,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, * under live filesystem. */ if (!(mode & FMODE_EXCL)) { - claimed_bdev = bdev->bd_contains; + claimed_bdev = bdev_whole(bdev); err = bd_prepare_to_claim(bdev, claimed_bdev, truncate_bdev_range); if (err) @@ -880,7 +880,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) spin_lock_init(&bdev->bd_size_lock); bdev->bd_disk = disk; bdev->bd_partno = partno; - bdev->bd_contains = NULL; bdev->bd_super = NULL; bdev->bd_inode = inode; bdev->bd_part_count = 0; @@ -1347,9 +1346,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) int ret; if (!bdev->bd_openers) { - bdev->bd_contains = bdev; - - if (!bdev->bd_partno) { + if (!bdev_is_partition(bdev)) { ret = -ENXIO; bdev->bd_part = disk_get_part(disk, 0); if (!bdev->bd_part) @@ -1389,7 +1386,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) whole->bd_part_count++; mutex_unlock(&whole->bd_mutex); - bdev->bd_contains = whole; bdev->bd_part = disk_get_part(disk, bdev->bd_partno); if (!(disk->flags & GENHD_FL_UP) || !bdev->bd_part || !bdev->bd_part->nr_sects) { @@ -1405,7 +1401,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) if (bdev->bd_bdi == &noop_backing_dev_info) bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); } else { - if (bdev->bd_contains == bdev) { + if (!bdev_is_partition(bdev)) { ret = 0; if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); @@ -1423,7 +1419,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) out_clear: disk_put_part(bdev->bd_part); bdev->bd_part = NULL; - bdev->bd_contains = NULL; return ret; } @@ -1670,8 +1665,7 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) disk_put_part(bdev->bd_part); bdev->bd_part = NULL; if (bdev_is_partition(bdev)) - victim = bdev->bd_contains; - bdev->bd_contains = NULL; + victim = bdev_whole(bdev); } else { if (!bdev_is_partition(bdev) && disk->fops->release) disk->fops->release(disk, mode); @@ -1690,6 +1684,7 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) mutex_lock(&bdev->bd_mutex); if (mode & FMODE_EXCL) { + struct block_device *whole = bdev_whole(bdev); bool bdev_free; /* @@ -1700,13 +1695,12 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) spin_lock(&bdev_lock); WARN_ON_ONCE(--bdev->bd_holders < 0); - WARN_ON_ONCE(--bdev->bd_contains->bd_holders < 0); + WARN_ON_ONCE(--whole->bd_holders < 0); - /* bd_contains might point to self, check in a separate step */ if ((bdev_free = !bdev->bd_holders)) bdev->bd_holder = NULL; - if (!bdev->bd_contains->bd_holders) - bdev->bd_contains->bd_holder = NULL; + if (!whole->bd_holders) + whole->bd_holder = NULL; spin_unlock(&bdev_lock); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 9698f459cc65..2e0a9bd9688d 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -32,7 +32,6 @@ struct block_device { #ifdef CONFIG_SYSFS struct list_head bd_holder_disks; #endif - struct block_device * bd_contains; u8 bd_partno; struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ @@ -49,6 +48,9 @@ struct block_device { struct super_block *bd_fsfreeze_sb; } __randomize_layout; +#define bdev_whole(_bdev) \ + ((_bdev)->bd_disk->part0.bdev) + #define bdev_kobj(_bdev) \ (&part_to_dev((_bdev)->bd_part)->kobj) -- cgit v1.2.3 From 37c3fc9abb25cd767ad5b048358336ac89488c16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 25 Nov 2020 21:20:08 +0100 Subject: block: simplify the block device claiming interface Stop passing the whole device as a separate argument given that it can be trivially deducted and cleanup the !holder debug check. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- drivers/block/loop.c | 12 +++++------- fs/block_dev.c | 51 ++++++++++++++++++-------------------------------- include/linux/blkdev.h | 6 ++---- 3 files changed, 25 insertions(+), 44 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index c0df88b3300c..d643c67be6ac 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1069,7 +1069,6 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, struct file *file; struct inode *inode; struct address_space *mapping; - struct block_device *claimed_bdev = NULL; int error; loff_t size; bool partscan; @@ -1088,8 +1087,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, * here to avoid changing device under exclusive owner. */ if (!(mode & FMODE_EXCL)) { - claimed_bdev = bdev_whole(bdev); - error = bd_prepare_to_claim(bdev, claimed_bdev, loop_configure); + error = bd_prepare_to_claim(bdev, loop_configure); if (error) goto out_putf; } @@ -1176,15 +1174,15 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, mutex_unlock(&loop_ctl_mutex); if (partscan) loop_reread_partitions(lo, bdev); - if (claimed_bdev) - bd_abort_claiming(bdev, claimed_bdev, loop_configure); + if (!(mode & FMODE_EXCL)) + bd_abort_claiming(bdev, loop_configure); return 0; out_unlock: mutex_unlock(&loop_ctl_mutex); out_bdev: - if (claimed_bdev) - bd_abort_claiming(bdev, claimed_bdev, loop_configure); + if (!(mode & FMODE_EXCL)) + bd_abort_claiming(bdev, loop_configure); out_putf: fput(file); out: diff --git a/fs/block_dev.c b/fs/block_dev.c index 94baee369d26..0569f5ebeb6f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -110,24 +110,20 @@ EXPORT_SYMBOL(invalidate_bdev); int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, loff_t lend) { - struct block_device *claimed_bdev = NULL; - int err; - /* * If we don't hold exclusive handle for the device, upgrade to it * while we discard the buffer cache to avoid discarding buffers * under live filesystem. */ if (!(mode & FMODE_EXCL)) { - claimed_bdev = bdev_whole(bdev); - err = bd_prepare_to_claim(bdev, claimed_bdev, - truncate_bdev_range); + int err = bd_prepare_to_claim(bdev, truncate_bdev_range); if (err) return err; } + truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend); - if (claimed_bdev) - bd_abort_claiming(bdev, claimed_bdev, truncate_bdev_range); + if (!(mode & FMODE_EXCL)) + bd_abort_claiming(bdev, truncate_bdev_range); return 0; } EXPORT_SYMBOL(truncate_bdev_range); @@ -978,7 +974,6 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, /** * bd_prepare_to_claim - claim a block device * @bdev: block device of interest - * @whole: the whole device containing @bdev, may equal @bdev * @holder: holder trying to claim @bdev * * Claim @bdev. This function fails if @bdev is already claimed by another @@ -988,9 +983,12 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, * RETURNS: * 0 if @bdev can be claimed, -EBUSY otherwise. */ -int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, - void *holder) +int bd_prepare_to_claim(struct block_device *bdev, void *holder) { + struct block_device *whole = bdev_whole(bdev); + + if (WARN_ON_ONCE(!holder)) + return -EINVAL; retry: spin_lock(&bdev_lock); /* if someone else claimed, fail */ @@ -1030,15 +1028,15 @@ static void bd_clear_claiming(struct block_device *whole, void *holder) /** * bd_finish_claiming - finish claiming of a block device * @bdev: block device of interest - * @whole: whole block device * @holder: holder that has claimed @bdev * * Finish exclusive open of a block device. Mark the device as exlusively * open by the holder and wake up all waiters for exclusive open to finish. */ -static void bd_finish_claiming(struct block_device *bdev, - struct block_device *whole, void *holder) +static void bd_finish_claiming(struct block_device *bdev, void *holder) { + struct block_device *whole = bdev_whole(bdev); + spin_lock(&bdev_lock); BUG_ON(!bd_may_claim(bdev, whole, holder)); /* @@ -1063,11 +1061,10 @@ static void bd_finish_claiming(struct block_device *bdev, * also used when exclusive open is not actually desired and we just needed * to block other exclusive openers for a while. */ -void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, - void *holder) +void bd_abort_claiming(struct block_device *bdev, void *holder) { spin_lock(&bdev_lock); - bd_clear_claiming(whole, holder); + bd_clear_claiming(bdev_whole(bdev), holder); spin_unlock(&bdev_lock); } EXPORT_SYMBOL(bd_abort_claiming); @@ -1487,7 +1484,6 @@ void blkdev_put_no_open(struct block_device *bdev) */ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) { - struct block_device *claiming; bool unblock_events = true; struct block_device *bdev; struct gendisk *disk; @@ -1510,15 +1506,9 @@ retry: disk = bdev->bd_disk; if (mode & FMODE_EXCL) { - WARN_ON_ONCE(!holder); - - ret = -ENOMEM; - claiming = bdget_disk(disk, 0); - if (!claiming) - goto put_blkdev; - ret = bd_prepare_to_claim(bdev, claiming, holder); + ret = bd_prepare_to_claim(bdev, holder); if (ret) - goto put_claiming; + goto put_blkdev; } disk_block_events(disk); @@ -1528,7 +1518,7 @@ retry: if (ret) goto abort_claiming; if (mode & FMODE_EXCL) { - bd_finish_claiming(bdev, claiming, holder); + bd_finish_claiming(bdev, holder); /* * Block event polling for write claims if requested. Any write @@ -1547,18 +1537,13 @@ retry: if (unblock_events) disk_unblock_events(disk); - if (mode & FMODE_EXCL) - bdput(claiming); return bdev; abort_claiming: if (mode & FMODE_EXCL) - bd_abort_claiming(bdev, claiming, holder); + bd_abort_claiming(bdev, holder); mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); -put_claiming: - if (mode & FMODE_EXCL) - bdput(claiming); put_blkdev: blkdev_put_no_open(bdev); if (ret == -ERESTARTSYS) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5d48b92f5e43..43a25d855e04 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1988,10 +1988,8 @@ void blkdev_show(struct seq_file *seqf, off_t offset); struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, - void *holder); -void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, - void *holder); +int bd_prepare_to_claim(struct block_device *bdev, void *holder); +void bd_abort_claiming(struct block_device *bdev, void *holder); void blkdev_put(struct block_device *bdev, fmode_t mode); /* just for blk-cgroup, don't use elsewhere */ -- cgit v1.2.3 From a782483cc1f875355690625d8253a232f2581418 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Nov 2020 18:43:37 +0100 Subject: block: remove the nr_sects field in struct hd_struct Now that the hd_struct always has a block device attached to it, there is no need for having two size field that just get out of sync. Additionally the field in hd_struct did not use proper serialization, possibly allowing for torn writes. By only using the block_device field this problem also gets fixed. Signed-off-by: Christoph Hellwig Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Coly Li [bcache] Acked-by: Chao Yu [f2fs] Signed-off-by: Jens Axboe --- block/bio.c | 4 +-- block/blk-core.c | 2 +- block/blk.h | 53 --------------------------- block/genhd.c | 59 +++++++++++++++++------------- block/partitions/core.c | 17 +++++---- drivers/block/loop.c | 1 - drivers/block/nbd.c | 2 +- drivers/block/xen-blkback/common.h | 4 +-- drivers/md/bcache/super.c | 2 +- drivers/s390/block/dasd_ioctl.c | 4 +-- drivers/target/target_core_pscsi.c | 5 ++- fs/block_dev.c | 73 ++------------------------------------ fs/f2fs/super.c | 2 +- fs/pstore/blk.c | 2 +- include/linux/genhd.h | 29 ++++----------- kernel/trace/blktrace.c | 2 +- 16 files changed, 67 insertions(+), 194 deletions(-) (limited to 'drivers/block') diff --git a/block/bio.c b/block/bio.c index fa01bef35bb1..669bb47a3198 100644 --- a/block/bio.c +++ b/block/bio.c @@ -613,8 +613,8 @@ void guard_bio_eod(struct bio *bio) rcu_read_lock(); part = __disk_get_part(bio->bi_disk, bio->bi_partno); if (part) - maxsector = part_nr_sects_read(part); - else + maxsector = bdev_nr_sectors(part->bdev); + else maxsector = get_capacity(bio->bi_disk); rcu_read_unlock(); diff --git a/block/blk-core.c b/block/blk-core.c index 2db8bda43b6e..988f45094a38 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -755,7 +755,7 @@ static inline int blk_partition_remap(struct bio *bio) goto out; if (bio_sectors(bio)) { - if (bio_check_eod(bio, part_nr_sects_read(p))) + if (bio_check_eod(bio, bdev_nr_sectors(p->bdev))) goto out; bio->bi_iter.bi_sector += p->start_sect; trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p), diff --git a/block/blk.h b/block/blk.h index c4839abcfa27..09cee7024fb4 100644 --- a/block/blk.h +++ b/block/blk.h @@ -387,59 +387,6 @@ static inline void hd_free_part(struct hd_struct *part) percpu_ref_exit(&part->ref); } -/* - * Any access of part->nr_sects which is not protected by partition - * bd_mutex or gendisk bdev bd_mutex, should be done using this - * accessor function. - * - * Code written along the lines of i_size_read() and i_size_write(). - * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption - * on. - */ -static inline sector_t part_nr_sects_read(struct hd_struct *part) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - sector_t nr_sects; - unsigned seq; - do { - seq = read_seqcount_begin(&part->nr_sects_seq); - nr_sects = part->nr_sects; - } while (read_seqcount_retry(&part->nr_sects_seq, seq)); - return nr_sects; -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) - sector_t nr_sects; - - preempt_disable(); - nr_sects = part->nr_sects; - preempt_enable(); - return nr_sects; -#else - return part->nr_sects; -#endif -} - -/* - * Should be called with mutex lock held (typically bd_mutex) of partition - * to provide mutual exlusion among writers otherwise seqcount might be - * left in wrong state leaving the readers spinning infinitely. - */ -static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - preempt_disable(); - write_seqcount_begin(&part->nr_sects_seq); - part->nr_sects = size; - write_seqcount_end(&part->nr_sects_seq); - preempt_enable(); -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) - preempt_disable(); - part->nr_sects = size; - preempt_enable(); -#else - part->nr_sects = size; -#endif -} - int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); diff --git a/block/genhd.c b/block/genhd.c index bf8fa82f135f..c65f485b9db5 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -40,6 +40,16 @@ static void disk_add_events(struct gendisk *disk); static void disk_del_events(struct gendisk *disk); static void disk_release_events(struct gendisk *disk); +void set_capacity(struct gendisk *disk, sector_t sectors) +{ + struct block_device *bdev = disk->part0.bdev; + + spin_lock(&bdev->bd_size_lock); + i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); + spin_unlock(&bdev->bd_size_lock); +} +EXPORT_SYMBOL(set_capacity); + /* * Set disk capacity and notify if the size is not currently zero and will not * be set to zero. Returns true if a uevent was sent, otherwise false. @@ -47,18 +57,30 @@ static void disk_release_events(struct gendisk *disk); bool set_capacity_and_notify(struct gendisk *disk, sector_t size) { sector_t capacity = get_capacity(disk); + char *envp[] = { "RESIZE=1", NULL }; set_capacity(disk, size); - revalidate_disk_size(disk, true); - if (capacity != size && capacity != 0 && size != 0) { - char *envp[] = { "RESIZE=1", NULL }; + /* + * Only print a message and send a uevent if the gendisk is user visible + * and alive. This avoids spamming the log and udev when setting the + * initial capacity during probing. + */ + if (size == capacity || + (disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP) + return false; - kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); - return true; - } + pr_info("%s: detected capacity change from %lld to %lld\n", + disk->disk_name, size, capacity); - return false; + /* + * Historically we did not send a uevent for changes to/from an empty + * device. + */ + if (!capacity || !size) + return false; + kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); + return true; } EXPORT_SYMBOL_GPL(set_capacity_and_notify); @@ -247,7 +269,7 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) part = rcu_dereference(ptbl->part[piter->idx]); if (!part) continue; - if (!part_nr_sects_read(part) && + if (!bdev_nr_sectors(part->bdev) && !(piter->flags & DISK_PITER_INCL_EMPTY) && !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 && piter->idx == 0)) @@ -284,7 +306,7 @@ EXPORT_SYMBOL_GPL(disk_part_iter_exit); static inline int sector_in_part(struct hd_struct *part, sector_t sector) { return part->start_sect <= sector && - sector < part->start_sect + part_nr_sects_read(part); + sector < part->start_sect + bdev_nr_sectors(part->bdev); } /** @@ -986,8 +1008,8 @@ void __init printk_all_partitions(void) printk("%s%s %10llu %s %s", is_part0 ? "" : " ", bdevt_str(part_devt(part), devt_buf), - (unsigned long long)part_nr_sects_read(part) >> 1 - , disk_name(disk, part->partno, name_buf), + bdev_nr_sectors(part->bdev) >> 1, + disk_name(disk, part->partno, name_buf), part->info ? part->info->uuid : ""); if (is_part0) { if (dev->parent && dev->parent->driver) @@ -1079,7 +1101,7 @@ static int show_partition(struct seq_file *seqf, void *v) while ((part = disk_part_iter_next(&piter))) seq_printf(seqf, "%4d %7d %10llu %s\n", MAJOR(part_devt(part)), MINOR(part_devt(part)), - (unsigned long long)part_nr_sects_read(part) >> 1, + bdev_nr_sectors(part->bdev) >> 1, disk_name(sgp, part->partno, buf)); disk_part_iter_exit(&piter); @@ -1161,8 +1183,7 @@ ssize_t part_size_show(struct device *dev, { struct hd_struct *p = dev_to_part(dev); - return sprintf(buf, "%llu\n", - (unsigned long long)part_nr_sects_read(p)); + return sprintf(buf, "%llu\n", bdev_nr_sectors(p->bdev)); } ssize_t part_stat_show(struct device *dev, @@ -1618,16 +1639,6 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) ptbl = rcu_dereference_protected(disk->part_tbl, 1); rcu_assign_pointer(ptbl->part[0], &disk->part0); - /* - * set_capacity() and get_capacity() currently don't use - * seqcounter to read/update the part0->nr_sects. Still init - * the counter as we can read the sectors in IO submission - * patch using seqence counters. - * - * TODO: Ideally set_capacity() and get_capacity() should be - * converted to make use of bd_mutex and sequence counters. - */ - hd_sects_seq_init(&disk->part0); if (hd_ref_init(&disk->part0)) goto out_free_bdstats; diff --git a/block/partitions/core.c b/block/partitions/core.c index 696bd9ff63c6..bcfa8215bd5e 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -85,6 +85,13 @@ static int (*check_part[])(struct parsed_partitions *) = { NULL }; +static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) +{ + spin_lock(&bdev->bd_size_lock); + i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); + spin_unlock(&bdev->bd_size_lock); +} + static struct parsed_partitions *allocate_partitions(struct gendisk *hd) { struct parsed_partitions *state; @@ -295,7 +302,7 @@ static void hd_struct_free_work(struct work_struct *work) put_device(disk_to_dev(disk)); part->start_sect = 0; - part->nr_sects = 0; + bdev_set_nr_sectors(part->bdev, 0); part_stat_set_all(part, 0); put_device(part_to_dev(part)); } @@ -412,11 +419,10 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, goto out_free_stats; p->bdev = bdev; - hd_sects_seq_init(p); pdev = part_to_dev(p); p->start_sect = start; - p->nr_sects = len; + bdev_set_nr_sectors(bdev, len); p->partno = partno; p->policy = get_disk_ro(disk); @@ -509,7 +515,7 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start, disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY); while ((part = disk_part_iter_next(&piter))) { if (part->partno == skip_partno || - start >= part->start_sect + part->nr_sects || + start >= part->start_sect + bdev_nr_sectors(part->bdev) || start + length <= part->start_sect) continue; overlap = true; @@ -600,8 +606,7 @@ int bdev_resize_partition(struct block_device *bdev, int partno, if (partition_overlaps(bdev->bd_disk, start, length, partno)) goto out_unlock; - part_nr_sects_write(part, length); - bd_set_nr_sectors(bdevp, length); + bdev_set_nr_sectors(bdevp, length); ret = 0; out_unlock: diff --git a/drivers/block/loop.c b/drivers/block/loop.c index d643c67be6ac..d2ce1ddc192d 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1241,7 +1241,6 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) set_capacity(lo->lo_disk, 0); loop_sysfs_exit(lo); if (bdev) { - bd_set_nr_sectors(bdev, 0); /* let user-space know about this change */ kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 45b0423ef2c5..014683968ce1 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1132,7 +1132,7 @@ static void nbd_bdev_reset(struct block_device *bdev) { if (bdev->bd_openers > 1) return; - bd_set_nr_sectors(bdev, 0); + set_capacity(bdev->bd_disk, 0); } static void nbd_parse_flags(struct nbd_device *nbd) diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index c6ea5d38c509..0762db247b41 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -358,9 +358,7 @@ struct pending_req { }; -#define vbd_sz(_v) ((_v)->bdev->bd_part ? \ - (_v)->bdev->bd_part->nr_sects : \ - get_capacity((_v)->bdev->bd_disk)) +#define vbd_sz(_v) bdev_nr_sectors((_v)->bdev) #define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt)) #define xen_blkif_put(_b) \ diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index c55d3c58a7ef..04fa40868fbe 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1408,7 +1408,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) q->limits.raid_partial_stripes_expensive; ret = bcache_device_init(&dc->disk, block_size, - dc->bdev->bd_part->nr_sects - dc->sb.data_offset, + bdev_nr_sectors(dc->bdev) - dc->sb.data_offset, dc->bdev, &bcache_cached_ops); if (ret) return ret; diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 3359559517bf..304eba1acf16 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -54,8 +54,6 @@ dasd_ioctl_enable(struct block_device *bdev) return -ENODEV; dasd_enable_device(base); - /* Formatting the dasd device can change the capacity. */ - bd_set_nr_sectors(bdev, get_capacity(base->block->gdp)); dasd_put_device(base); return 0; } @@ -88,7 +86,7 @@ dasd_ioctl_disable(struct block_device *bdev) * Set i_size to zero, since read, write, etc. check against this * value. */ - bd_set_nr_sectors(bdev, 0); + set_capacity(bdev->bd_disk, 0); dasd_put_device(base); return 0; } diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 4e37fa9b409d..7994f27e4527 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1029,9 +1029,8 @@ static sector_t pscsi_get_blocks(struct se_device *dev) { struct pscsi_dev_virt *pdv = PSCSI_DEV(dev); - if (pdv->pdv_bd && pdv->pdv_bd->bd_part) - return pdv->pdv_bd->bd_part->nr_sects; - + if (pdv->pdv_bd) + return bdev_nr_sectors(pdv->pdv_bd); return 0; } diff --git a/fs/block_dev.c b/fs/block_dev.c index a5b6955a841f..31ee5a857f71 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1208,70 +1208,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); #endif -/** - * check_disk_size_change - checks for disk size change and adjusts bdev size. - * @disk: struct gendisk to check - * @bdev: struct bdev to adjust. - * @verbose: if %true log a message about a size change if there is any - * - * This routine checks to see if the bdev size does not match the disk size - * and adjusts it if it differs. When shrinking the bdev size, its all caches - * are freed. - */ -static void check_disk_size_change(struct gendisk *disk, - struct block_device *bdev, bool verbose) -{ - loff_t disk_size, bdev_size; - - spin_lock(&bdev->bd_size_lock); - disk_size = (loff_t)get_capacity(disk) << 9; - bdev_size = i_size_read(bdev->bd_inode); - if (disk_size != bdev_size) { - if (verbose) { - printk(KERN_INFO - "%s: detected capacity change from %lld to %lld\n", - disk->disk_name, bdev_size, disk_size); - } - i_size_write(bdev->bd_inode, disk_size); - } - spin_unlock(&bdev->bd_size_lock); -} - -/** - * revalidate_disk_size - checks for disk size change and adjusts bdev size. - * @disk: struct gendisk to check - * @verbose: if %true log a message about a size change if there is any - * - * This routine checks to see if the bdev size does not match the disk size - * and adjusts it if it differs. When shrinking the bdev size, its all caches - * are freed. - */ -void revalidate_disk_size(struct gendisk *disk, bool verbose) -{ - struct block_device *bdev; - - /* - * Hidden disks don't have associated bdev so there's no point in - * revalidating them. - */ - if (disk->flags & GENHD_FL_HIDDEN) - return; - - bdev = bdget_disk(disk, 0); - if (bdev) { - check_disk_size_change(disk, bdev, verbose); - bdput(bdev); - } -} - -void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors) -{ - spin_lock(&bdev->bd_size_lock); - i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); - spin_unlock(&bdev->bd_size_lock); -} -EXPORT_SYMBOL(bd_set_nr_sectors); - static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); int bdev_disk_changed(struct block_device *bdev, bool invalidate) @@ -1305,8 +1241,6 @@ rescan: disk->fops->revalidate_disk(disk); } - check_disk_size_change(disk, bdev, !invalidate); - if (get_capacity(disk)) { ret = blk_add_partitions(disk, bdev); if (ret == -EAGAIN) @@ -1349,10 +1283,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) if (disk->fops->open) ret = disk->fops->open(bdev, mode); - if (!ret) { - bd_set_nr_sectors(bdev, get_capacity(disk)); + if (!ret) set_init_blocksize(bdev); - } /* * If the device is invalidated, rescan partition @@ -1381,13 +1313,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) bdev->bd_part = disk_get_part(disk, bdev->bd_partno); if (!(disk->flags & GENHD_FL_UP) || - !bdev->bd_part || !bdev->bd_part->nr_sects) { + !bdev->bd_part || !bdev_nr_sectors(bdev)) { __blkdev_put(whole, mode, 1); bdput(whole); ret = -ENXIO; goto out_clear; } - bd_set_nr_sectors(bdev, bdev->bd_part->nr_sects); set_init_blocksize(bdev); } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 00eff2f51807..d4e7fab352ba 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3151,7 +3151,7 @@ static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx, static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) { struct block_device *bdev = FDEV(devi).bdev; - sector_t nr_sectors = bdev->bd_part->nr_sects; + sector_t nr_sectors = bdev_nr_sectors(bdev); struct f2fs_report_zones_args rep_zone_arg; int ret; diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c index fcd5563dde06..777a26f7bbe2 100644 --- a/fs/pstore/blk.c +++ b/fs/pstore/blk.c @@ -245,7 +245,7 @@ static struct block_device *psblk_get_bdev(void *holder, return bdev; } - nr_sects = part_nr_sects_read(bdev->bd_part); + nr_sects = bdev_nr_sectors(bdev); if (!nr_sects) { pr_err("not enough space for '%s'\n", blkdev); blkdev_put(bdev, mode); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6ba91ee54cb2..30d4785b7df8 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -52,15 +52,6 @@ struct partition_meta_info { struct hd_struct { sector_t start_sect; - /* - * nr_sects is protected by sequence counter. One might extend a - * partition while IO is happening to it and update of nr_sects - * can be non-atomic on 32bit machines with 64bit sector_t. - */ - sector_t nr_sects; -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - seqcount_t nr_sects_seq; -#endif unsigned long stamp; struct disk_stats __percpu *dkstats; struct percpu_ref ref; @@ -254,13 +245,6 @@ static inline void disk_put_part(struct hd_struct *part) put_device(part_to_dev(part)); } -static inline void hd_sects_seq_init(struct hd_struct *p) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - seqcount_init(&p->nr_sects_seq); -#endif -} - /* * Smarter partition iterator without context limits. */ @@ -318,13 +302,15 @@ static inline sector_t get_start_sect(struct block_device *bdev) { return bdev->bd_part->start_sect; } -static inline sector_t get_capacity(struct gendisk *disk) + +static inline sector_t bdev_nr_sectors(struct block_device *bdev) { - return disk->part0.nr_sects; + return i_size_read(bdev->bd_inode) >> 9; } -static inline void set_capacity(struct gendisk *disk, sector_t size) + +static inline sector_t get_capacity(struct gendisk *disk) { - disk->part0.nr_sects = size; + return bdev_nr_sectors(disk->part0.bdev); } int bdev_disk_changed(struct block_device *bdev, bool invalidate); @@ -358,10 +344,9 @@ int __register_blkdev(unsigned int major, const char *name, __register_blkdev(major, name, NULL) void unregister_blkdev(unsigned int major, const char *name); -void revalidate_disk_size(struct gendisk *disk, bool verbose); bool bdev_check_media_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); -void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors); +void set_capacity(struct gendisk *disk, sector_t size); /* for drivers/char/raw.c: */ int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index f1022945e346..7076d588a50d 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -465,7 +465,7 @@ static void blk_trace_setup_lba(struct blk_trace *bt, if (part) { bt->start_lba = part->start_sect; - bt->end_lba = part->start_sect + part->nr_sects; + bt->end_lba = part->start_sect + bdev_nr_sectors(bdev); } else { bt->start_lba = 0; bt->end_lba = -1ULL; -- cgit v1.2.3 From cb8432d650fe3be58bb962bc8e602dc405510327 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Nov 2020 18:47:17 +0100 Subject: block: allocate struct hd_struct as part of struct bdev_inode Allocate hd_struct together with struct block_device to pre-load the lifetime rule changes in preparation of merging the two structures. Note that part0 was previously embedded into struct gendisk, but is a separate allocation now, and already points to the block_device instead of the hd_struct. The lifetime of struct gendisk is still controlled by the struct device embedded in the part0 hd_struct. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-core.c | 16 ++++----- block/blk-flush.c | 2 +- block/blk-merge.c | 2 -- block/blk.h | 21 ------------ block/genhd.c | 50 +++++++++++----------------- block/partitions/core.c | 67 ++++---------------------------------- drivers/block/drbd/drbd_receiver.c | 2 +- drivers/block/drbd/drbd_worker.c | 3 +- drivers/block/zram/zram_drv.c | 2 +- drivers/md/dm.c | 4 +-- drivers/md/md.c | 2 +- fs/block_dev.c | 39 +++++++--------------- include/linux/blk_types.h | 2 +- include/linux/genhd.h | 14 ++++---- include/linux/part_stat.h | 4 +-- 15 files changed, 61 insertions(+), 169 deletions(-) (limited to 'drivers/block') diff --git a/block/blk-core.c b/block/blk-core.c index d64ffcb6f9ae..9ea70275fc1c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -714,7 +714,8 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) static noinline int should_fail_bio(struct bio *bio) { - if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size)) + if (should_fail_request(bio->bi_disk->part0->bd_part, + bio->bi_iter.bi_size)) return -EIO; return 0; } @@ -831,7 +832,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio) if (unlikely(blk_partition_remap(bio))) goto end_io; } else { - if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0))) + if (unlikely(bio_check_ro(bio, bio->bi_disk->part0->bd_part))) goto end_io; if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk)))) goto end_io; @@ -1203,7 +1204,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * return ret; if (rq->rq_disk && - should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) + should_fail_request(rq->rq_disk->part0->bd_part, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) @@ -1272,7 +1273,7 @@ again: __part_stat_add(part, io_ticks, end ? now - stamp : 1); } if (part->partno) { - part = &part_to_disk(part)->part0; + part = part_to_disk(part)->part0->bd_part; goto again; } } @@ -1309,8 +1310,6 @@ void blk_account_io_done(struct request *req, u64 now) part_stat_inc(part, ios[sgrp]); part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); - - hd_struct_put(part); } } @@ -1354,7 +1353,7 @@ EXPORT_SYMBOL_GPL(part_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { - return __part_start_io_acct(&disk->part0, sectors, op); + return __part_start_io_acct(disk->part0->bd_part, sectors, op); } EXPORT_SYMBOL(disk_start_io_acct); @@ -1376,14 +1375,13 @@ void part_end_io_acct(struct hd_struct *part, struct bio *bio, unsigned long start_time) { __part_end_io_acct(part, bio_op(bio), start_time); - hd_struct_put(part); } EXPORT_SYMBOL_GPL(part_end_io_acct); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time) { - __part_end_io_acct(&disk->part0, op, start_time); + __part_end_io_acct(disk->part0->bd_part, op, start_time); } EXPORT_SYMBOL(disk_end_io_acct); diff --git a/block/blk-flush.c b/block/blk-flush.c index e32958f0b687..fcd0a60574df 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -139,7 +139,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front) static void blk_account_io_flush(struct request *rq) { - struct hd_struct *part = &rq->rq_disk->part0; + struct hd_struct *part = rq->rq_disk->part0->bd_part; part_stat_lock(); part_stat_inc(part, ios[STAT_FLUSH]); diff --git a/block/blk-merge.c b/block/blk-merge.c index bcf5e4580603..cb351ab9b77d 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -683,8 +683,6 @@ static void blk_account_io_merge_request(struct request *req) part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); - - hd_struct_put(req->part); } } diff --git a/block/blk.h b/block/blk.h index 0bd4b58bcbaf..32ac41f7557f 100644 --- a/block/blk.h +++ b/block/blk.h @@ -363,27 +363,6 @@ int bdev_del_partition(struct block_device *bdev, int partno); int bdev_resize_partition(struct block_device *bdev, int partno, sector_t start, sector_t length); int disk_expand_part_tbl(struct gendisk *disk, int target); -int hd_ref_init(struct hd_struct *part); - -/* no need to get/put refcount of part0 */ -static inline int hd_struct_try_get(struct hd_struct *part) -{ - if (part->partno) - return percpu_ref_tryget_live(&part->ref); - return 1; -} - -static inline void hd_struct_put(struct hd_struct *part) -{ - if (part->partno) - percpu_ref_put(&part->ref); -} - -static inline void hd_free_part(struct hd_struct *part) -{ - bdput(part->bdev); - percpu_ref_exit(&part->ref); -} int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, diff --git a/block/genhd.c b/block/genhd.c index 2db1204920a9..c35b03dac5e5 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -42,7 +42,7 @@ static void disk_release_events(struct gendisk *disk); void set_capacity(struct gendisk *disk, sector_t sectors) { - struct block_device *bdev = disk->part0.bdev; + struct block_device *bdev = disk->part0; spin_lock(&bdev->bd_size_lock); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); @@ -318,9 +318,7 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector) * primarily used for stats accounting. * * CONTEXT: - * RCU read locked. The returned partition pointer is always valid - * because its refcount is grabbed except for part0, which lifetime - * is same with the disk. + * RCU read locked. * * RETURNS: * Found partition on success, part0 is returned if no partition matches @@ -336,26 +334,19 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) ptbl = rcu_dereference(disk->part_tbl); part = rcu_dereference(ptbl->last_lookup); - if (part && sector_in_part(part, sector) && hd_struct_try_get(part)) + if (part && sector_in_part(part, sector)) goto out_unlock; for (i = 1; i < ptbl->len; i++) { part = rcu_dereference(ptbl->part[i]); if (part && sector_in_part(part, sector)) { - /* - * only live partition can be cached for lookup, - * so use-after-free on cached & deleting partition - * can be avoided - */ - if (!hd_struct_try_get(part)) - break; rcu_assign_pointer(ptbl->last_lookup, part); goto out_unlock; } } - part = &disk->part0; + part = disk->part0->bd_part; out_unlock: rcu_read_unlock(); return part; @@ -681,8 +672,8 @@ static void register_disk(struct device *parent, struct gendisk *disk, */ pm_runtime_set_memalloc_noio(ddev, true); - disk->part0.bdev->bd_holder_dir = - kobject_create_and_add("holders", &ddev->kobj); + disk->part0->bd_holder_dir = + kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); if (disk->flags & GENHD_FL_HIDDEN) { @@ -748,7 +739,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, disk->flags |= GENHD_FL_UP; - retval = blk_alloc_devt(&disk->part0, &devt); + retval = blk_alloc_devt(disk->part0->bd_part, &devt); if (retval) { WARN_ON(1); return; @@ -775,7 +766,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt)); WARN_ON(ret); bdi_set_owner(bdi, dev); - bdev_add(disk->part0.bdev, devt); + bdev_add(disk->part0, devt); } register_disk(parent, disk, groups); if (register_queue) @@ -888,11 +879,11 @@ void del_gendisk(struct gendisk *disk) blk_unregister_queue(disk); - kobject_put(disk->part0.bdev->bd_holder_dir); + kobject_put(disk->part0->bd_holder_dir); kobject_put(disk->slave_dir); - part_stat_set_all(&disk->part0, 0); - disk->part0.bdev->bd_stamp = 0; + part_stat_set_all(disk->part0->bd_part, 0); + disk->part0->bd_stamp = 0; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); @@ -1005,7 +996,7 @@ void __init printk_all_partitions(void) */ disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0); while ((part = disk_part_iter_next(&piter))) { - bool is_part0 = part == &disk->part0; + bool is_part0 = part == disk->part0->bd_part; printk("%s%s %10llu %s %s", is_part0 ? "" : " ", bdevt_str(part_devt(part), devt_buf), @@ -1460,7 +1451,7 @@ static void disk_release(struct device *dev) disk_release_events(disk); kfree(disk->random); disk_replace_part_tbl(disk, NULL); - hd_free_part(&disk->part0); + bdput(disk->part0); if (disk->queue) blk_put_queue(disk->queue); kfree(disk); @@ -1626,8 +1617,8 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) if (!disk) return NULL; - disk->part0.bdev = bdev_alloc(disk, 0); - if (!disk->part0.bdev) + disk->part0 = bdev_alloc(disk, 0); + if (!disk->part0) goto out_free_disk; disk->node_id = node_id; @@ -1635,10 +1626,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) goto out_bdput; ptbl = rcu_dereference_protected(disk->part_tbl, 1); - rcu_assign_pointer(ptbl->part[0], &disk->part0); - - if (hd_ref_init(&disk->part0)) - goto out_bdput; + rcu_assign_pointer(ptbl->part[0], disk->part0->bd_part); disk->minors = minors; rand_initialize_disk(disk); @@ -1648,7 +1636,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) return disk; out_bdput: - bdput(disk->part0.bdev); + bdput(disk->part0); out_free_disk: kfree(disk); return NULL; @@ -1687,9 +1675,9 @@ void set_disk_ro(struct gendisk *disk, int flag) struct disk_part_iter piter; struct hd_struct *part; - if (disk->part0.bdev->bd_read_only != flag) { + if (disk->part0->bd_read_only != flag) { set_disk_ro_uevent(disk, flag); - disk->part0.bdev->bd_read_only = flag; + disk->part0->bd_read_only = flag; } disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY); diff --git a/block/partitions/core.c b/block/partitions/core.c index 060c1be13cd8..6d1fca193cbd 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -265,9 +265,9 @@ static const struct attribute_group *part_attr_groups[] = { static void part_release(struct device *dev) { struct hd_struct *p = dev_to_part(dev); + blk_free_devt(dev->devt); - hd_free_part(p); - kfree(p); + bdput(p->bdev); } static int part_uevent(struct device *dev, struct kobj_uevent_env *env) @@ -288,46 +288,6 @@ struct device_type part_type = { .uevent = part_uevent, }; -static void hd_struct_free_work(struct work_struct *work) -{ - struct hd_struct *part = - container_of(to_rcu_work(work), struct hd_struct, rcu_work); - struct gendisk *disk = part_to_disk(part); - - /* - * Release the disk reference acquired in delete_partition here. - * We can't release it in hd_struct_free because the final put_device - * needs process context and thus can't be run directly from a - * percpu_ref ->release handler. - */ - put_device(disk_to_dev(disk)); - - part->bdev->bd_start_sect = 0; - bdev_set_nr_sectors(part->bdev, 0); - part_stat_set_all(part, 0); - put_device(part_to_dev(part)); -} - -static void hd_struct_free(struct percpu_ref *ref) -{ - struct hd_struct *part = container_of(ref, struct hd_struct, ref); - struct gendisk *disk = part_to_disk(part); - struct disk_part_tbl *ptbl = - rcu_dereference_protected(disk->part_tbl, 1); - - rcu_assign_pointer(ptbl->last_lookup, NULL); - - INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work); - queue_rcu_work(system_wq, &part->rcu_work); -} - -int hd_ref_init(struct hd_struct *part) -{ - if (percpu_ref_init(&part->ref, hd_struct_free, 0, GFP_KERNEL)) - return -ENOMEM; - return 0; -} - /* * Must be called either with bd_mutex held, before a disk can be opened or * after all disk users are gone. @@ -342,8 +302,8 @@ void delete_partition(struct hd_struct *part) * ->part_tbl is referenced in this part's release handler, so * we have to hold the disk device */ - get_device(disk_to_dev(disk)); rcu_assign_pointer(ptbl->part[part->partno], NULL); + rcu_assign_pointer(ptbl->last_lookup, NULL); kobject_put(part->bdev->bd_holder_dir); device_del(part_to_dev(part)); @@ -353,7 +313,7 @@ void delete_partition(struct hd_struct *part) */ remove_inode_hash(part->bdev->bd_inode); - percpu_ref_kill(&part->ref); + put_device(part_to_dev(part)); } static ssize_t whole_disk_show(struct device *dev, @@ -406,15 +366,11 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, if (ptbl->part[partno]) return ERR_PTR(-EBUSY); - p = kzalloc(sizeof(*p), GFP_KERNEL); - if (!p) - return ERR_PTR(-EBUSY); - bdev = bdev_alloc(disk, partno); if (!bdev) - goto out_free; - p->bdev = bdev; + return ERR_PTR(-ENOMEM); + p = bdev->bd_part; pdev = part_to_dev(p); bdev->bd_start_sect = start; @@ -463,13 +419,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, goto out_del; } - err = hd_ref_init(p); - if (err) { - if (flags & ADDPART_FLAG_WHOLEDISK) - goto out_remove_file; - goto out_del; - } - /* everything is up and running, commence */ bdev_add(bdev, devt); rcu_assign_pointer(ptbl->part[partno], p); @@ -481,11 +430,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, out_bdput: bdput(bdev); -out_free: - kfree(p); return ERR_PTR(err); -out_remove_file: - device_remove_file(pdev, &dev_attr_whole_disk); out_del: kobject_put(bdev->bd_holder_dir); device_del(pdev); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index dc333dbe5232..9e5c2fdfda36 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -2802,7 +2802,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device) if (c_min_rate == 0) return false; - curr_events = (int)part_stat_read_accum(&disk->part0, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - atomic_read(&device->rs_sect_ev); if (atomic_read(&device->ap_actlog_cnt) diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index ba56f3f05312..343f56b86bb7 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1678,7 +1678,8 @@ void drbd_rs_controller_reset(struct drbd_device *device) atomic_set(&device->rs_sect_in, 0); atomic_set(&device->rs_sect_ev, 0); device->rs_in_flight = 0; - device->rs_last_events = (int)part_stat_read_accum(&disk->part0, sectors); + device->rs_last_events = + (int)part_stat_read_accum(disk->part0->bd_part, sectors); /* Updating the RCU protected object in place is necessary since this function gets called from atomic context. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index b5f68951c9d2..6d84876a9cd0 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1687,7 +1687,7 @@ static void zram_reset_device(struct zram *zram) zram->disksize = 0; set_capacity_and_notify(zram->disk, 0); - part_stat_set_all(&zram->disk->part0, 0); + part_stat_set_all(zram->disk->part0->bd_part, 0); up_write(&zram->init_lock); /* I/O operation under all of CPU are done so let's free */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 48051db006f3..1b2db4d530ea 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1607,7 +1607,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, * (by eliminating DM's splitting and just using bio_split) */ part_stat_lock(); - __dm_part_stat_sub(&dm_disk(md)->part0, + __dm_part_stat_sub(dm_disk(md)->part0->bd_part, sectors[op_stat_group(bio_op(bio))], ci.sector_count); part_stat_unlock(); @@ -2242,7 +2242,7 @@ EXPORT_SYMBOL_GPL(dm_put); static bool md_in_flight_bios(struct mapped_device *md) { int cpu; - struct hd_struct *part = &dm_disk(md)->part0; + struct hd_struct *part = dm_disk(md)->part0->bd_part; long sum = 0; for_each_possible_cpu(cpu) { diff --git a/drivers/md/md.c b/drivers/md/md.c index 7ce6047c856e..3696c2d77a4d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8441,7 +8441,7 @@ static int is_mddev_idle(struct mddev *mddev, int init) rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { struct gendisk *disk = rdev->bdev->bd_disk; - curr_events = (int)part_stat_read_accum(&disk->part0, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - atomic_read(&disk->sync_io); /* sync IO will cause sync_io to increase before the disk_stats * as sync_io is counted when a request starts, and diff --git a/fs/block_dev.c b/fs/block_dev.c index 381c22426f43..61cf33b6284f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -39,6 +39,7 @@ struct bdev_inode { struct block_device bdev; + struct hd_struct hd; struct inode vfs_inode; }; @@ -886,6 +887,9 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) iput(inode); return NULL; } + bdev->bd_part = &BDEV_I(inode)->hd; + memset(bdev->bd_part, 0, sizeof(*bdev->bd_part)); + bdev->bd_part->bdev = bdev; return bdev; } @@ -1280,15 +1284,10 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed); static int __blkdev_get(struct block_device *bdev, fmode_t mode) { struct gendisk *disk = bdev->bd_disk; - int ret; + int ret = 0; if (!bdev->bd_openers) { if (!bdev_is_partition(bdev)) { - ret = -ENXIO; - bdev->bd_part = disk_get_part(disk, 0); - if (!bdev->bd_part) - goto out_clear; - ret = 0; if (disk->fops->open) ret = disk->fops->open(bdev, mode); @@ -1307,7 +1306,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) bdev_disk_changed(bdev, ret == -ENOMEDIUM); if (ret) - goto out_clear; + return ret; } else { struct block_device *whole = bdget_disk(disk, 0); @@ -1316,18 +1315,16 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) if (ret) { mutex_unlock(&whole->bd_mutex); bdput(whole); - goto out_clear; + return ret; } whole->bd_part_count++; mutex_unlock(&whole->bd_mutex); - bdev->bd_part = disk_get_part(disk, bdev->bd_partno); if (!(disk->flags & GENHD_FL_UP) || - !bdev->bd_part || !bdev_nr_sectors(bdev)) { + !bdev_nr_sectors(bdev)) { __blkdev_put(whole, mode, 1); bdput(whole); - ret = -ENXIO; - goto out_clear; + return -ENXIO; } set_init_blocksize(bdev); } @@ -1336,7 +1333,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); } else { if (!bdev_is_partition(bdev)) { - ret = 0; if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); /* the same as first opener case, read comment there */ @@ -1349,11 +1345,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) } bdev->bd_openers++; return 0; - - out_clear: - disk_put_part(bdev->bd_part); - bdev->bd_part = NULL; - return ret; } struct block_device *blkdev_get_no_open(dev_t dev) @@ -1580,18 +1571,12 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) sync_blockdev(bdev); kill_bdev(bdev); bdev_write_inode(bdev); - - if (!bdev_is_partition(bdev) && disk->fops->release) - disk->fops->release(disk, mode); - - disk_put_part(bdev->bd_part); - bdev->bd_part = NULL; if (bdev_is_partition(bdev)) victim = bdev_whole(bdev); - } else { - if (!bdev_is_partition(bdev) && disk->fops->release) - disk->fops->release(disk, mode); } + + if (!bdev_is_partition(bdev) && disk->fops->release) + disk->fops->release(disk, mode); mutex_unlock(&bdev->bd_mutex); if (victim) { __blkdev_put(victim, mode, 1); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 758cf71c9aa2..6edea5c16259 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -59,7 +59,7 @@ struct block_device { } __randomize_layout; #define bdev_whole(_bdev) \ - ((_bdev)->bd_disk->part0.bdev) + ((_bdev)->bd_disk->part0) #define bdev_kobj(_bdev) \ (&part_to_dev((_bdev)->bd_part)->kobj) diff --git a/include/linux/genhd.h b/include/linux/genhd.h index dcbf9ef7610e..df7319da013c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -19,11 +19,12 @@ #include #include -#define dev_to_disk(device) container_of((device), struct gendisk, part0.__dev) #define dev_to_part(device) container_of((device), struct hd_struct, __dev) -#define disk_to_dev(disk) (&(disk)->part0.__dev) #define part_to_dev(part) (&((part)->__dev)) +#define dev_to_disk(device) (dev_to_part(device)->bdev->bd_disk) +#define disk_to_dev(disk) (part_to_dev((disk)->part0->bd_part)) + extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class; @@ -51,12 +52,9 @@ struct partition_meta_info { }; struct hd_struct { - struct percpu_ref ref; - struct block_device *bdev; struct device __dev; int partno; - struct rcu_work rcu_work; }; /** @@ -168,7 +166,7 @@ struct gendisk { * helpers. */ struct disk_part_tbl __rcu *part_tbl; - struct hd_struct part0; + struct block_device *part0; const struct block_device_operations *fops; struct request_queue *queue; @@ -278,7 +276,7 @@ extern void set_disk_ro(struct gendisk *disk, int flag); static inline int get_disk_ro(struct gendisk *disk) { - return disk->part0.bdev->bd_read_only; + return disk->part0->bd_read_only; } extern void disk_block_events(struct gendisk *disk); @@ -302,7 +300,7 @@ static inline sector_t bdev_nr_sectors(struct block_device *bdev) static inline sector_t get_capacity(struct gendisk *disk) { - return bdev_nr_sectors(disk->part0.bdev); + return bdev_nr_sectors(disk->part0); } int bdev_disk_changed(struct block_device *bdev, bool invalidate); diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 87ad60106e1d..680de036691e 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -59,8 +59,8 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ if ((part)->partno) \ - __part_stat_add(&part_to_disk((part))->part0, \ - field, addnd); \ + __part_stat_add(part_to_disk((part))->part0->bd_part, \ + field, addnd); \ } while (0) #define part_stat_dec(part, field) \ -- cgit v1.2.3 From 8446fe9255be821cb38ffd306d7e8edc4b9ea662 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Nov 2020 09:36:54 +0100 Subject: block: switch partition lookup to use struct block_device Use struct block_device to lookup partitions on a disk. This removes all usage of struct hd_struct from the I/O path. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Acked-by: Coly Li [bcache] Acked-by: Chao Yu [f2fs] Signed-off-by: Jens Axboe --- block/bio.c | 4 +-- block/blk-core.c | 66 +++++++++++++++++--------------------- block/blk-flush.c | 2 +- block/blk-mq.c | 9 +++--- block/blk-mq.h | 7 ++-- block/blk.h | 4 +-- block/genhd.c | 57 +++++++++++++++++--------------- block/partitions/core.c | 7 ++-- drivers/block/drbd/drbd_receiver.c | 2 +- drivers/block/drbd/drbd_worker.c | 2 +- drivers/block/zram/zram_drv.c | 2 +- drivers/md/bcache/request.c | 4 +-- drivers/md/dm.c | 4 +-- drivers/md/md.c | 4 +-- drivers/nvme/target/admin-cmd.c | 20 ++++++------ fs/ext4/super.c | 18 ++++------- fs/ext4/sysfs.c | 10 ++---- fs/f2fs/f2fs.h | 2 +- fs/f2fs/super.c | 6 ++-- include/linux/blkdev.h | 8 ++--- include/linux/genhd.h | 4 +-- include/linux/part_stat.h | 17 +++++----- 22 files changed, 122 insertions(+), 137 deletions(-) (limited to 'drivers/block') diff --git a/block/bio.c b/block/bio.c index 669bb47a3198..ebb18136b86f 100644 --- a/block/bio.c +++ b/block/bio.c @@ -608,12 +608,12 @@ void bio_truncate(struct bio *bio, unsigned new_size) void guard_bio_eod(struct bio *bio) { sector_t maxsector; - struct hd_struct *part; + struct block_device *part; rcu_read_lock(); part = __disk_get_part(bio->bi_disk, bio->bi_partno); if (part) - maxsector = bdev_nr_sectors(part->bdev); + maxsector = bdev_nr_sectors(part); else maxsector = get_capacity(bio->bi_disk); rcu_read_unlock(); diff --git a/block/blk-core.c b/block/blk-core.c index 9ea70275fc1c..cee568389b7e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -666,10 +666,9 @@ static int __init setup_fail_make_request(char *str) } __setup("fail_make_request=", setup_fail_make_request); -static bool should_fail_request(struct hd_struct *part, unsigned int bytes) +static bool should_fail_request(struct block_device *part, unsigned int bytes) { - return part->bdev->bd_make_it_fail && - should_fail(&fail_make_request, bytes); + return part->bd_make_it_fail && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) @@ -684,7 +683,7 @@ late_initcall(fail_make_request_debugfs); #else /* CONFIG_FAIL_MAKE_REQUEST */ -static inline bool should_fail_request(struct hd_struct *part, +static inline bool should_fail_request(struct block_device *part, unsigned int bytes) { return false; @@ -692,11 +691,11 @@ static inline bool should_fail_request(struct hd_struct *part, #endif /* CONFIG_FAIL_MAKE_REQUEST */ -static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) +static inline bool bio_check_ro(struct bio *bio, struct block_device *part) { const int op = bio_op(bio); - if (part->bdev->bd_read_only && op_is_write(op)) { + if (part->bd_read_only && op_is_write(op)) { char b[BDEVNAME_SIZE]; if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) @@ -704,7 +703,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) WARN_ONCE(1, "Trying to write to read-only block-device %s (partno %d)\n", - bio_devname(bio, b), part->partno); + bio_devname(bio, b), part->bd_partno); /* Older lvm-tools actually trigger this */ return false; } @@ -714,8 +713,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) static noinline int should_fail_bio(struct bio *bio) { - if (should_fail_request(bio->bi_disk->part0->bd_part, - bio->bi_iter.bi_size)) + if (should_fail_request(bio->bi_disk->part0, bio->bi_iter.bi_size)) return -EIO; return 0; } @@ -744,7 +742,7 @@ static inline int bio_check_eod(struct bio *bio, sector_t maxsector) */ static inline int blk_partition_remap(struct bio *bio) { - struct hd_struct *p; + struct block_device *p; int ret = -EIO; rcu_read_lock(); @@ -757,12 +755,12 @@ static inline int blk_partition_remap(struct bio *bio) goto out; if (bio_sectors(bio)) { - if (bio_check_eod(bio, bdev_nr_sectors(p->bdev))) + if (bio_check_eod(bio, bdev_nr_sectors(p))) goto out; - bio->bi_iter.bi_sector += p->bdev->bd_start_sect; - trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p), + bio->bi_iter.bi_sector += p->bd_start_sect; + trace_block_bio_remap(bio->bi_disk->queue, bio, p->bd_dev, bio->bi_iter.bi_sector - - p->bdev->bd_start_sect); + p->bd_start_sect); } bio->bi_partno = 0; ret = 0; @@ -832,7 +830,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio) if (unlikely(blk_partition_remap(bio))) goto end_io; } else { - if (unlikely(bio_check_ro(bio, bio->bi_disk->part0->bd_part))) + if (unlikely(bio_check_ro(bio, bio->bi_disk->part0))) goto end_io; if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk)))) goto end_io; @@ -1204,7 +1202,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * return ret; if (rq->rq_disk && - should_fail_request(rq->rq_disk->part0->bd_part, blk_rq_bytes(rq))) + should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) @@ -1263,17 +1261,18 @@ unsigned int blk_rq_err_bytes(const struct request *rq) } EXPORT_SYMBOL_GPL(blk_rq_err_bytes); -static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) +static void update_io_ticks(struct block_device *part, unsigned long now, + bool end) { unsigned long stamp; again: - stamp = READ_ONCE(part->bdev->bd_stamp); + stamp = READ_ONCE(part->bd_stamp); if (unlikely(stamp != now)) { - if (likely(cmpxchg(&part->bdev->bd_stamp, stamp, now) == stamp)) + if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp)) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } - if (part->partno) { - part = part_to_disk(part)->part0->bd_part; + if (part->bd_partno) { + part = bdev_whole(part); goto again; } } @@ -1282,11 +1281,9 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); - struct hd_struct *part; part_stat_lock(); - part = req->part; - part_stat_add(part, sectors[sgrp], bytes >> 9); + part_stat_add(req->part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } @@ -1301,14 +1298,11 @@ void blk_account_io_done(struct request *req, u64 now) if (req->part && blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { const int sgrp = op_stat_group(req_op(req)); - struct hd_struct *part; part_stat_lock(); - part = req->part; - - update_io_ticks(part, jiffies, true); - part_stat_inc(part, ios[sgrp]); - part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); + update_io_ticks(req->part, jiffies, true); + part_stat_inc(req->part, ios[sgrp]); + part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); } } @@ -1325,7 +1319,7 @@ void blk_account_io_start(struct request *rq) part_stat_unlock(); } -static unsigned long __part_start_io_acct(struct hd_struct *part, +static unsigned long __part_start_io_acct(struct block_device *part, unsigned int sectors, unsigned int op) { const int sgrp = op_stat_group(op); @@ -1341,7 +1335,7 @@ static unsigned long __part_start_io_acct(struct hd_struct *part, return now; } -unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, +unsigned long part_start_io_acct(struct gendisk *disk, struct block_device **part, struct bio *bio) { *part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector); @@ -1353,11 +1347,11 @@ EXPORT_SYMBOL_GPL(part_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { - return __part_start_io_acct(disk->part0->bd_part, sectors, op); + return __part_start_io_acct(disk->part0, sectors, op); } EXPORT_SYMBOL(disk_start_io_acct); -static void __part_end_io_acct(struct hd_struct *part, unsigned int op, +static void __part_end_io_acct(struct block_device *part, unsigned int op, unsigned long start_time) { const int sgrp = op_stat_group(op); @@ -1371,7 +1365,7 @@ static void __part_end_io_acct(struct hd_struct *part, unsigned int op, part_stat_unlock(); } -void part_end_io_acct(struct hd_struct *part, struct bio *bio, +void part_end_io_acct(struct block_device *part, struct bio *bio, unsigned long start_time) { __part_end_io_acct(part, bio_op(bio), start_time); @@ -1381,7 +1375,7 @@ EXPORT_SYMBOL_GPL(part_end_io_acct); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time) { - __part_end_io_acct(disk->part0->bd_part, op, start_time); + __part_end_io_acct(disk->part0, op, start_time); } EXPORT_SYMBOL(disk_end_io_acct); diff --git a/block/blk-flush.c b/block/blk-flush.c index fcd0a60574df..9507dcdd5881 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -139,7 +139,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front) static void blk_account_io_flush(struct request *rq) { - struct hd_struct *part = rq->rq_disk->part0->bd_part; + struct block_device *part = rq->rq_disk->part0; part_stat_lock(); part_stat_inc(part, ios[STAT_FLUSH]); diff --git a/block/blk-mq.c b/block/blk-mq.c index 55bcee5dc032..a2593748fa53 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -95,7 +95,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, } struct mq_inflight { - struct hd_struct *part; + struct block_device *part; unsigned int inflight[2]; }; @@ -111,7 +111,8 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, return true; } -unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) +unsigned int blk_mq_in_flight(struct request_queue *q, + struct block_device *part) { struct mq_inflight mi = { .part = part }; @@ -120,8 +121,8 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part) return mi.inflight[0] + mi.inflight[1]; } -void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, - unsigned int inflight[2]) +void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, + unsigned int inflight[2]) { struct mq_inflight mi = { .part = part }; diff --git a/block/blk-mq.h b/block/blk-mq.h index a52703c98b77..c696515766c7 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -182,9 +182,10 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) return hctx->nr_ctx && hctx->tags; } -unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part); -void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, - unsigned int inflight[2]); +unsigned int blk_mq_in_flight(struct request_queue *q, + struct block_device *part); +void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, + unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct request_queue *q) { diff --git a/block/blk.h b/block/blk.h index 32ac41f7557f..d5bf8f3a0781 100644 --- a/block/blk.h +++ b/block/blk.h @@ -215,7 +215,7 @@ static inline void elevator_exit(struct request_queue *q, __elevator_exit(q, e); } -struct hd_struct *__disk_get_part(struct gendisk *disk, int partno); +struct block_device *__disk_get_part(struct gendisk *disk, int partno); ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); @@ -348,7 +348,7 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q); static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} #endif -struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); +struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); int blk_alloc_devt(struct hd_struct *part, dev_t *devt); void blk_free_devt(dev_t devt); diff --git a/block/genhd.c b/block/genhd.c index c35b03dac5e5..ed06466b305d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -126,7 +126,7 @@ static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat) } } -static unsigned int part_in_flight(struct hd_struct *part) +static unsigned int part_in_flight(struct block_device *part) { unsigned int inflight = 0; int cpu; @@ -141,7 +141,8 @@ static unsigned int part_in_flight(struct hd_struct *part) return inflight; } -static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2]) +static void part_in_flight_rw(struct block_device *part, + unsigned int inflight[2]) { int cpu; @@ -157,7 +158,7 @@ static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2]) inflight[1] = 0; } -struct hd_struct *__disk_get_part(struct gendisk *disk, int partno) +struct block_device *__disk_get_part(struct gendisk *disk, int partno) { struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl); @@ -182,15 +183,21 @@ struct hd_struct *__disk_get_part(struct gendisk *disk, int partno) */ struct hd_struct *disk_get_part(struct gendisk *disk, int partno) { + struct block_device *bdev; struct hd_struct *part; rcu_read_lock(); - part = __disk_get_part(disk, partno); - if (part) - get_device(part_to_dev(part)); + bdev = __disk_get_part(disk, partno); + if (!bdev) + goto fail; + part = bdev->bd_part; + if (!kobject_get_unless_zero(&part_to_dev(part)->kobj)) + goto fail; rcu_read_unlock(); - return part; +fail: + rcu_read_unlock(); + return NULL; } /** @@ -264,19 +271,19 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) /* iterate to the next partition */ for (; piter->idx != end; piter->idx += inc) { - struct hd_struct *part; + struct block_device *part; part = rcu_dereference(ptbl->part[piter->idx]); if (!part) continue; - if (!bdev_nr_sectors(part->bdev) && + if (!bdev_nr_sectors(part) && !(piter->flags & DISK_PITER_INCL_EMPTY) && !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 && piter->idx == 0)) continue; - get_device(part_to_dev(part)); - piter->part = part; + get_device(part_to_dev(part->bd_part)); + piter->part = part->bd_part; piter->idx += inc; break; } @@ -303,10 +310,10 @@ void disk_part_iter_exit(struct disk_part_iter *piter) } EXPORT_SYMBOL_GPL(disk_part_iter_exit); -static inline int sector_in_part(struct hd_struct *part, sector_t sector) +static inline int sector_in_part(struct block_device *part, sector_t sector) { - return part->bdev->bd_start_sect <= sector && - sector < part->bdev->bd_start_sect + bdev_nr_sectors(part->bdev); + return part->bd_start_sect <= sector && + sector < part->bd_start_sect + bdev_nr_sectors(part); } /** @@ -324,10 +331,10 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector) * Found partition on success, part0 is returned if no partition matches * or the matched partition is being deleted. */ -struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) +struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) { struct disk_part_tbl *ptbl; - struct hd_struct *part; + struct block_device *part; int i; rcu_read_lock(); @@ -346,7 +353,7 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) } } - part = disk->part0->bd_part; + part = disk->part0; out_unlock: rcu_read_unlock(); return part; @@ -882,7 +889,7 @@ void del_gendisk(struct gendisk *disk) kobject_put(disk->part0->bd_holder_dir); kobject_put(disk->slave_dir); - part_stat_set_all(disk->part0->bd_part, 0); + part_stat_set_all(disk->part0, 0); disk->part0->bd_stamp = 0; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); @@ -1189,9 +1196,9 @@ ssize_t part_stat_show(struct device *dev, part_stat_read_all(p, &stat); if (queue_is_mq(q)) - inflight = blk_mq_in_flight(q, p); + inflight = blk_mq_in_flight(q, p->bdev); else - inflight = part_in_flight(p); + inflight = part_in_flight(p->bdev); return sprintf(buf, "%8lu %8lu %8llu %8u " @@ -1231,9 +1238,9 @@ ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, unsigned int inflight[2]; if (queue_is_mq(q)) - blk_mq_in_flight_rw(q, p, inflight); + blk_mq_in_flight_rw(q, p->bdev, inflight); else - part_in_flight_rw(p, inflight); + part_in_flight_rw(p->bdev, inflight); return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]); } @@ -1506,9 +1513,9 @@ static int diskstats_show(struct seq_file *seqf, void *v) while ((hd = disk_part_iter_next(&piter))) { part_stat_read_all(hd, &stat); if (queue_is_mq(gp->queue)) - inflight = blk_mq_in_flight(gp->queue, hd); + inflight = blk_mq_in_flight(gp->queue, hd->bdev); else - inflight = part_in_flight(hd); + inflight = part_in_flight(hd->bdev); seq_printf(seqf, "%4d %7d %s " "%lu %lu %lu %u " @@ -1626,7 +1633,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) goto out_bdput; ptbl = rcu_dereference_protected(disk->part_tbl, 1); - rcu_assign_pointer(ptbl->part[0], disk->part0->bd_part); + rcu_assign_pointer(ptbl->part[0], disk->part0); disk->minors = minors; rand_initialize_disk(disk); diff --git a/block/partitions/core.c b/block/partitions/core.c index 6d1fca193cbd..c2f6721633b8 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -298,12 +298,9 @@ void delete_partition(struct hd_struct *part) struct disk_part_tbl *ptbl = rcu_dereference_protected(disk->part_tbl, 1); - /* - * ->part_tbl is referenced in this part's release handler, so - * we have to hold the disk device - */ rcu_assign_pointer(ptbl->part[part->partno], NULL); rcu_assign_pointer(ptbl->last_lookup, NULL); + kobject_put(part->bdev->bd_holder_dir); device_del(part_to_dev(part)); @@ -421,7 +418,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno, /* everything is up and running, commence */ bdev_add(bdev, devt); - rcu_assign_pointer(ptbl->part[partno], p); + rcu_assign_pointer(ptbl->part[partno], bdev); /* suppress uevent if the disk suppresses it */ if (!dev_get_uevent_suppress(ddev)) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 9e5c2fdfda36..09c86ef3f0fd 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -2802,7 +2802,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device) if (c_min_rate == 0) return false; - curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0, sectors) - atomic_read(&device->rs_sect_ev); if (atomic_read(&device->ap_actlog_cnt) diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 343f56b86bb7..02044ab7f767 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1679,7 +1679,7 @@ void drbd_rs_controller_reset(struct drbd_device *device) atomic_set(&device->rs_sect_ev, 0); device->rs_in_flight = 0; device->rs_last_events = - (int)part_stat_read_accum(disk->part0->bd_part, sectors); + (int)part_stat_read_accum(disk->part0, sectors); /* Updating the RCU protected object in place is necessary since this function gets called from atomic context. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 6d84876a9cd0..dc8957d173d3 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1687,7 +1687,7 @@ static void zram_reset_device(struct zram *zram) zram->disksize = 0; set_capacity_and_notify(zram->disk, 0); - part_stat_set_all(zram->disk->part0->bd_part, 0); + part_stat_set_all(zram->disk->part0, 0); up_write(&zram->init_lock); /* I/O operation under all of CPU are done so let's free */ diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index afac8d07c1bd..85b1f2a9b72d 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -475,7 +475,7 @@ struct search { unsigned int read_dirty_data:1; unsigned int cache_missed:1; - struct hd_struct *part; + struct block_device *part; unsigned long start_time; struct btree_op op; @@ -1073,7 +1073,7 @@ struct detached_dev_io_private { unsigned long start_time; bio_end_io_t *bi_end_io; void *bi_private; - struct hd_struct *part; + struct block_device *part; }; static void detached_dev_end_io(struct bio *bio) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1b2db4d530ea..176adcff56b3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1607,7 +1607,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, * (by eliminating DM's splitting and just using bio_split) */ part_stat_lock(); - __dm_part_stat_sub(dm_disk(md)->part0->bd_part, + __dm_part_stat_sub(dm_disk(md)->part0, sectors[op_stat_group(bio_op(bio))], ci.sector_count); part_stat_unlock(); @@ -2242,7 +2242,7 @@ EXPORT_SYMBOL_GPL(dm_put); static bool md_in_flight_bios(struct mapped_device *md) { int cpu; - struct hd_struct *part = dm_disk(md)->part0->bd_part; + struct block_device *part = dm_disk(md)->part0; long sum = 0; for_each_possible_cpu(cpu) { diff --git a/drivers/md/md.c b/drivers/md/md.c index 3696c2d77a4d..0065736f05b4 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -464,7 +464,7 @@ struct md_io { bio_end_io_t *orig_bi_end_io; void *orig_bi_private; unsigned long start_time; - struct hd_struct *part; + struct block_device *part; }; static void md_end_io(struct bio *bio) @@ -8441,7 +8441,7 @@ static int is_mddev_idle(struct mddev *mddev, int init) rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) { struct gendisk *disk = rdev->bdev->bd_disk; - curr_events = (int)part_stat_read_accum(disk->part0->bd_part, sectors) - + curr_events = (int)part_stat_read_accum(disk->part0, sectors) - atomic_read(&disk->sync_io); /* sync IO will cause sync_io to increase before the disk_stats * as sync_io is counted when a request starts, and diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index dca34489a1dc..8d90235e4fcc 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -89,12 +89,12 @@ static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req, if (!ns->bdev) goto out; - host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]); - data_units_read = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part, - sectors[READ]), 1000); - host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]); - data_units_written = DIV_ROUND_UP(part_stat_read(ns->bdev->bd_part, - sectors[WRITE]), 1000); + host_reads = part_stat_read(ns->bdev, ios[READ]); + data_units_read = + DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[READ]), 1000); + host_writes = part_stat_read(ns->bdev, ios[WRITE]); + data_units_written = + DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[WRITE]), 1000); put_unaligned_le64(host_reads, &slog->host_reads[0]); put_unaligned_le64(data_units_read, &slog->data_units_read[0]); @@ -120,12 +120,12 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req, /* we don't have the right data for file backed ns */ if (!ns->bdev) continue; - host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]); + host_reads += part_stat_read(ns->bdev, ios[READ]); data_units_read += DIV_ROUND_UP( - part_stat_read(ns->bdev->bd_part, sectors[READ]), 1000); - host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]); + part_stat_read(ns->bdev, sectors[READ]), 1000); + host_writes += part_stat_read(ns->bdev, ios[WRITE]); data_units_written += DIV_ROUND_UP( - part_stat_read(ns->bdev->bd_part, sectors[WRITE]), 1000); + part_stat_read(ns->bdev, sectors[WRITE]), 1000); } put_unaligned_le64(host_reads, &slog->host_reads[0]); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6633b20224d5..c303a0ff0b17 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4048,9 +4048,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_sb = sb; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sb_block = sb_block; - if (sb->s_bdev->bd_part) - sbi->s_sectors_written_start = - part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]); + sbi->s_sectors_written_start = + part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); /* Cleanup superblock name */ strreplace(sb->s_id, '/', '!'); @@ -5509,15 +5508,10 @@ static int ext4_commit_super(struct super_block *sb, int sync) */ if (!(sb->s_flags & SB_RDONLY)) ext4_update_tstamp(es, s_wtime); - if (sb->s_bdev->bd_part) - es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + - ((part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]) - - EXT4_SB(sb)->s_sectors_written_start) >> 1)); - else - es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written); + es->s_kbytes_written = + cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - + EXT4_SB(sb)->s_sectors_written_start) >> 1)); if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter)) ext4_free_blocks_count_set(es, EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive( diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 4e27fe6ed3ae..075aa3a19ff5 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -62,11 +62,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) { struct super_block *sb = sbi->s_buddy_cache->i_sb; - if (!sb->s_bdev->bd_part) - return snprintf(buf, PAGE_SIZE, "0\n"); return snprintf(buf, PAGE_SIZE, "%lu\n", - (part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]) - + (part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - sbi->s_sectors_written_start) >> 1); } @@ -74,12 +71,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf) { struct super_block *sb = sbi->s_buddy_cache->i_sb; - if (!sb->s_bdev->bd_part) - return snprintf(buf, PAGE_SIZE, "0\n"); return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long)(sbi->s_kbytes_written + - ((part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]) - + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - EXT4_SB(sb)->s_sectors_written_start) >> 1))); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cb700d797296..49681a8d2b14 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1675,7 +1675,7 @@ static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) * and the return value is in kbytes. s is of struct f2fs_sb_info. */ #define BD_PART_WRITTEN(s) \ -(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) - \ + (((u64)part_stat_read((s)->sb->s_bdev, sectors[STAT_WRITE]) - \ (s)->sectors_written_start) >> 1) static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d4e7fab352ba..af9f449da64b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3700,10 +3700,8 @@ try_onemore: } /* For write statistics */ - if (sb->s_bdev->bd_part) - sbi->sectors_written_start = - (u64)part_stat_read(sb->s_bdev->bd_part, - sectors[STAT_WRITE]); + sbi->sectors_written_start = + (u64)part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); /* Read accumulated write IO statistics if exists */ seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 619adea57098..1d4be1fc6007 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -191,7 +191,7 @@ struct request { }; struct gendisk *rq_disk; - struct hd_struct *part; + struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ u64 alloc_time_ns; @@ -1943,9 +1943,9 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); -unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, - struct bio *bio); -void part_end_io_acct(struct hd_struct *part, struct bio *bio, +unsigned long part_start_io_acct(struct gendisk *disk, + struct block_device **part, struct bio *bio); +void part_end_io_acct(struct block_device *part, struct bio *bio, unsigned long start_time); /** diff --git a/include/linux/genhd.h b/include/linux/genhd.h index df7319da013c..fe6fee77e2b9 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -131,8 +131,8 @@ enum { struct disk_part_tbl { struct rcu_head rcu_head; int len; - struct hd_struct __rcu *last_lookup; - struct hd_struct __rcu *part[]; + struct block_device __rcu *last_lookup; + struct block_device __rcu *part[]; }; struct disk_events; diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 680de036691e..d2558121d48c 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -25,26 +25,26 @@ struct disk_stats { #define part_stat_unlock() preempt_enable() #define part_stat_get_cpu(part, field, cpu) \ - (per_cpu_ptr((part)->bdev->bd_stats, (cpu))->field) + (per_cpu_ptr((part)->bd_stats, (cpu))->field) #define part_stat_get(part, field) \ part_stat_get_cpu(part, field, smp_processor_id()) #define part_stat_read(part, field) \ ({ \ - typeof((part)->bdev->bd_stats->field) res = 0; \ + typeof((part)->bd_stats->field) res = 0; \ unsigned int _cpu; \ for_each_possible_cpu(_cpu) \ - res += per_cpu_ptr((part)->bdev->bd_stats, _cpu)->field; \ + res += per_cpu_ptr((part)->bd_stats, _cpu)->field; \ res; \ }) -static inline void part_stat_set_all(struct hd_struct *part, int value) +static inline void part_stat_set_all(struct block_device *part, int value) { int i; for_each_possible_cpu(i) - memset(per_cpu_ptr(part->bdev->bd_stats, i), value, + memset(per_cpu_ptr(part->bd_stats, i), value, sizeof(struct disk_stats)); } @@ -54,13 +54,12 @@ static inline void part_stat_set_all(struct hd_struct *part, int value) part_stat_read(part, field[STAT_DISCARD])) #define __part_stat_add(part, field, addnd) \ - __this_cpu_add((part)->bdev->bd_stats->field, addnd) + __this_cpu_add((part)->bd_stats->field, addnd) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ - if ((part)->partno) \ - __part_stat_add(part_to_disk((part))->part0->bd_part, \ - field, addnd); \ + if ((part)->bd_partno) \ + __part_stat_add(bdev_whole(part), field, addnd); \ } while (0) #define part_stat_dec(part, field) \ -- cgit v1.2.3 From 977115c0f664e016a6b2774d4f97116ade23d732 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 26 Nov 2020 10:41:07 +0100 Subject: block: stop using bdget_disk for partition 0 We can just dereference the point in struct gendisk instead. Also remove the now unused export. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/genhd.c | 1 - drivers/block/nbd.c | 4 +--- drivers/block/xen-blkfront.c | 20 +++++--------------- drivers/block/zram/zram_drv.c | 14 ++------------ drivers/md/dm.c | 16 ++-------------- drivers/s390/block/dasd_ioctl.c | 5 ++--- fs/block_dev.c | 2 +- 7 files changed, 13 insertions(+), 49 deletions(-) (limited to 'drivers/block') diff --git a/block/genhd.c b/block/genhd.c index 0fabfc90b8e4..b84b8671e627 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -930,7 +930,6 @@ struct block_device *bdget_disk(struct gendisk *disk, int partno) return bdev; } -EXPORT_SYMBOL(bdget_disk); /* * print a full list of all partitions - intended for places where the root diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 014683968ce1..92f84ed0ba9e 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1488,12 +1488,10 @@ out: static void nbd_release(struct gendisk *disk, fmode_t mode) { struct nbd_device *nbd = disk->private_data; - struct block_device *bdev = bdget_disk(disk, 0); if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && - bdev->bd_openers == 0) + disk->part0->bd_openers == 0) nbd_disconnect_and_put(nbd); - bdput(bdev); nbd_config_put(nbd); nbd_put(nbd); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 79521e33d30e..188e0b47534b 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2153,7 +2153,7 @@ static void blkfront_closing(struct blkfront_info *info) } if (info->gd) - bdev = bdget_disk(info->gd, 0); + bdev = bdgrab(info->gd->part0); mutex_unlock(&info->mutex); @@ -2518,7 +2518,7 @@ static int blkfront_remove(struct xenbus_device *xbdev) disk = info->gd; if (disk) - bdev = bdget_disk(disk, 0); + bdev = bdgrab(disk->part0); info->xbdev = NULL; mutex_unlock(&info->mutex); @@ -2595,19 +2595,11 @@ out: static void blkif_release(struct gendisk *disk, fmode_t mode) { struct blkfront_info *info = disk->private_data; - struct block_device *bdev; struct xenbus_device *xbdev; mutex_lock(&blkfront_mutex); - - bdev = bdget_disk(disk, 0); - - if (!bdev) { - WARN(1, "Block device %s yanked out from us!\n", disk->disk_name); + if (disk->part0->bd_openers) goto out_mutex; - } - if (bdev->bd_openers) - goto out; /* * Check if we have been instructed to close. We will have @@ -2619,7 +2611,7 @@ static void blkif_release(struct gendisk *disk, fmode_t mode) if (xbdev && xbdev->state == XenbusStateClosing) { /* pending switch to state closed */ - dev_info(disk_to_dev(bdev->bd_disk), "releasing disk\n"); + dev_info(disk_to_dev(disk), "releasing disk\n"); xlvbd_release_gendisk(info); xenbus_frontend_closed(info->xbdev); } @@ -2628,14 +2620,12 @@ static void blkif_release(struct gendisk *disk, fmode_t mode) if (!xbdev) { /* sudden device removal */ - dev_info(disk_to_dev(bdev->bd_disk), "releasing disk\n"); + dev_info(disk_to_dev(disk), "releasing disk\n"); xlvbd_release_gendisk(info); disk->private_data = NULL; free_info(info); } -out: - bdput(bdev); out_mutex: mutex_unlock(&blkfront_mutex); } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index dc8957d173d3..b0701bae6e98 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1760,15 +1760,12 @@ static ssize_t reset_store(struct device *dev, return -EINVAL; zram = dev_to_zram(dev); - bdev = bdget_disk(zram->disk, 0); - if (!bdev) - return -ENOMEM; + bdev = zram->disk->part0; mutex_lock(&bdev->bd_mutex); /* Do not reset an active device or claimed device */ if (bdev->bd_openers || zram->claim) { mutex_unlock(&bdev->bd_mutex); - bdput(bdev); return -EBUSY; } @@ -1779,7 +1776,6 @@ static ssize_t reset_store(struct device *dev, /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - bdput(bdev); mutex_lock(&bdev->bd_mutex); zram->claim = false; @@ -1965,16 +1961,11 @@ out_free_dev: static int zram_remove(struct zram *zram) { - struct block_device *bdev; - - bdev = bdget_disk(zram->disk, 0); - if (!bdev) - return -ENOMEM; + struct block_device *bdev = zram->disk->part0; mutex_lock(&bdev->bd_mutex); if (bdev->bd_openers || zram->claim) { mutex_unlock(&bdev->bd_mutex); - bdput(bdev); return -EBUSY; } @@ -1986,7 +1977,6 @@ static int zram_remove(struct zram *zram) /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - bdput(bdev); pr_info("Removed device: %s\n", zram->disk->disk_name); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 176adcff56b3..ed7e836efbcd 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2375,16 +2375,11 @@ out: */ static int lock_fs(struct mapped_device *md) { - struct block_device *bdev; int r; WARN_ON(test_bit(DMF_FROZEN, &md->flags)); - bdev = bdget_disk(md->disk, 0); - if (!bdev) - return -ENOMEM; - r = freeze_bdev(bdev); - bdput(bdev); + r = freeze_bdev(md->disk->part0); if (!r) set_bit(DMF_FROZEN, &md->flags); return r; @@ -2392,16 +2387,9 @@ static int lock_fs(struct mapped_device *md) static void unlock_fs(struct mapped_device *md) { - struct block_device *bdev; - if (!test_bit(DMF_FROZEN, &md->flags)) return; - - bdev = bdget_disk(md->disk, 0); - if (!bdev) - return; - thaw_bdev(bdev); - bdput(bdev); + thaw_bdev(md->disk->part0); clear_bit(DMF_FROZEN, &md->flags); } diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 304eba1acf16..9f6424408946 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -220,9 +220,8 @@ dasd_format(struct dasd_block *block, struct format_data_t *fdata) * enabling the device later. */ if (fdata->start_unit == 0) { - struct block_device *bdev = bdget_disk(block->gdp, 0); - bdev->bd_inode->i_blkbits = blksize_bits(fdata->blksize); - bdput(bdev); + block->gdp->part0->bd_inode->i_blkbits = + blksize_bits(fdata->blksize); } rc = base->discipline->format_device(base, fdata, 1); diff --git a/fs/block_dev.c b/fs/block_dev.c index a9905d8fd02b..9e56ee1f2652 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1299,7 +1299,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) if (ret) return ret; } else { - struct block_device *whole = bdget_disk(disk, 0); + struct block_device *whole = bdgrab(disk->part0); mutex_lock_nested(&whole->bd_mutex, 1); ret = __blkdev_get(whole, mode); -- cgit v1.2.3