diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-26 22:47:20 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-06-26 22:47:20 +0300 |
| commit | a0433f8cae3ac51f59b4b1863032822aaa2d8164 (patch) | |
| tree | 9eb7b096aa9f7fa53921e6ff247488f3a55471f5 | |
| parent | 0aa69d53ac7c30f6184f88f2e310d808b32b35a5 (diff) | |
| parent | fcaa174a9c995cf0af3967e55644a1543ea07e36 (diff) | |
| download | linux-a0433f8cae3ac51f59b4b1863032822aaa2d8164.tar.xz | |
Merge tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux
Pull block updates from Jens Axboe:
- NVMe pull request via Keith:
- Various cleanups all around (Irvin, Chaitanya, Christophe)
- Better struct packing (Christophe JAILLET)
- Reduce controller error logs for optional commands (Keith)
- Support for >=64KiB block sizes (Daniel Gomez)
- Fabrics fixes and code organization (Max, Chaitanya, Daniel
Wagner)
- bcache updates via Coly:
- Fix a race at init time (Mingzhe Zou)
- Misc fixes and cleanups (Andrea, Thomas, Zheng, Ye)
- use page pinning in the block layer for dio (David)
- convert old block dio code to page pinning (David, Christoph)
- cleanups for pktcdvd (Andy)
- cleanups for rnbd (Guoqing)
- use the unchecked __bio_add_page() for the initial single page
additions (Johannes)
- fix overflows in the Amiga partition handling code (Michael)
- improve mq-deadline zoned device support (Bart)
- keep passthrough requests out of the IO schedulers (Christoph, Ming)
- improve support for flush requests, making them less special to deal
with (Christoph)
- add bdev holder ops and shutdown methods (Christoph)
- fix the name_to_dev_t() situation and use cases (Christoph)
- decouple the block open flags from fmode_t (Christoph)
- ublk updates and cleanups, including adding user copy support (Ming)
- BFQ sanity checking (Bart)
- convert brd from radix to xarray (Pankaj)
- constify various structures (Thomas, Ivan)
- more fine grained persistent reservation ioctl capability checks
(Jingbo)
- misc fixes and cleanups (Arnd, Azeem, Demi, Ed, Hengqi, Hou, Jan,
Jordy, Li, Min, Yu, Zhong, Waiman)
* tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux: (266 commits)
scsi/sg: don't grab scsi host module reference
ext4: Fix warning in blkdev_put()
block: don't return -EINVAL for not found names in devt_from_devname
cdrom: Fix spectre-v1 gadget
block: Improve kernel-doc headers
blk-mq: don't insert passthrough request into sw queue
bsg: make bsg_class a static const structure
ublk: make ublk_chr_class a static const structure
aoe: make aoe_class a static const structure
block/rnbd: make all 'class' structures const
block: fix the exclusive open mask in disk_scan_partitions
block: add overflow checks for Amiga partition support
block: change all __u32 annotations to __be32 in affs_hardblocks.h
block: fix signed int overflow in Amiga partition support
block: add capacity validation in bdev_add_partition()
block: fine-granular CAP_SYS_ADMIN for Persistent Reservation
block: disallow Persistent Reservation on partitions
reiserfs: fix blkdev_put() warning from release_journal_dev()
block: fix wrong mode for blkdev_get_by_dev() from disk_scan_partitions()
block: document the holder argument to blkdev_get_by_path
...
218 files changed, 4742 insertions, 3879 deletions
diff --git a/Documentation/admin-guide/bcache.rst b/Documentation/admin-guide/bcache.rst index bb5032a99234..6fdb495ac466 100644 --- a/Documentation/admin-guide/bcache.rst +++ b/Documentation/admin-guide/bcache.rst @@ -508,9 +508,6 @@ cache_miss_collisions cache miss, but raced with a write and data was already present (usually 0 since the synchronization for cache misses was rewritten) -cache_readaheads - Count of times readahead occurred. - Sysfs - cache set ~~~~~~~~~~~~~~~~~ diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index e592a9364473..c63358c38a1d 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -2022,31 +2022,33 @@ that attribute: no-change Do not modify the I/O priority class. - none-to-rt - For requests that do not have an I/O priority class (NONE), - change the I/O priority class into RT. Do not modify - the I/O priority class of other requests. + promote-to-rt + For requests that have a non-RT I/O priority class, change it into RT. + Also change the priority level of these requests to 4. Do not modify + the I/O priority of requests that have priority class RT. restrict-to-be For requests that do not have an I/O priority class or that have I/O - priority class RT, change it into BE. Do not modify the I/O priority - class of requests that have priority class IDLE. + priority class RT, change it into BE. Also change the priority level + of these requests to 0. Do not modify the I/O priority class of + requests that have priority class IDLE. idle Change the I/O priority class of all requests into IDLE, the lowest I/O priority class. + none-to-rt + Deprecated. Just an alias for promote-to-rt. + The following numerical values are associated with the I/O priority policies: -+-------------+---+ -| no-change | 0 | -+-------------+---+ -| none-to-rt | 1 | -+-------------+---+ -| rt-to-be | 2 | -+-------------+---+ -| all-to-idle | 3 | -+-------------+---+ ++----------------+---+ +| no-change | 0 | ++----------------+---+ +| rt-to-be | 2 | ++----------------+---+ +| all-to-idle | 3 | ++----------------+---+ The numerical value that corresponds to each I/O priority class is as follows: @@ -2062,9 +2064,13 @@ The numerical value that corresponds to each I/O priority class is as follows: The algorithm to set the I/O priority class for a request is as follows: -- Translate the I/O priority class policy into a number. -- Change the request I/O priority class into the maximum of the I/O priority - class policy number and the numerical I/O priority class. +- If I/O priority class policy is promote-to-rt, change the request I/O + priority class to IOPRIO_CLASS_RT and change the request I/O priority + level to 4. +- If I/O priorityt class is not promote-to-rt, translate the I/O priority + class policy into a number, then change the request I/O priority class + into the maximum of the I/O priority class policy number and the numerical + I/O priority class. PID --- diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9e5bab29685f..911c54829c7c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5452,7 +5452,12 @@ port and the regular usb controller gets disabled. root= [KNL] Root filesystem - See name_to_dev_t comment in init/do_mounts.c. + Usually this a a block device specifier of some kind, + see the early_lookup_bdev comment in + block/early-lookup.c for details. + Alternatively this can be "ram" for the legacy initial + ramdisk, "nfs" and "cifs" for root on a network file + system, or "mtd" and "ubi" for mounting from raw flash. rootdelay= [KNL] Delay (in seconds) to pause before attempting to mount the root filesystem diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst index 9fb0b1080d3b..d3c1f6d8c0e0 100644 --- a/Documentation/core-api/pin_user_pages.rst +++ b/Documentation/core-api/pin_user_pages.rst @@ -112,6 +112,12 @@ pages: This also leads to limitations: there are only 31-10==21 bits available for a counter that increments 10 bits at a time. +* Because of that limitation, special handling is applied to the zero pages + when using FOLL_PIN. We only pretend to pin a zero page - we don't alter its + refcount or pincount at all (it is permanent, so there's no need). The + unpinning functions also don't do anything to a zero page. This is + transparent to the caller. + * Callers must specifically request "dma-pinned tracking of pages". In other words, just calling get_user_pages() will not suffice; a new set of functions, pin_user_page() and related, must be used. diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 33bf3a627002..b650ff1cb022 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -658,7 +658,7 @@ setup_arch(char **cmdline_p) #endif /* Default root filesystem to sda2. */ - ROOT_DEV = Root_SDA2; + ROOT_DEV = MKDEV(SCSI_DISK0_MAJOR, 2); #ifdef CONFIG_EISA /* FIXME: only set this when we actually have EISA in this box? */ diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index c05728044272..becdb4f33c21 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -627,7 +627,7 @@ setup_arch (char **cmdline_p) * is physical disk 1 partition 1 and the Linux root disk is * physical disk 1 partition 2. */ - ROOT_DEV = Root_SDA2; /* default to second partition on first drive */ + ROOT_DEV = MKDEV(SCSI_DISK0_MAJOR, 2); if (is_uv_system()) uv_setup(cmdline_p); diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 193cc9c39422..0c41f4b005bc 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -76,7 +76,8 @@ int pmac_newworld; static int current_root_goodness = -1; -#define DEFAULT_ROOT_DEVICE Root_SDA1 /* sda1 - slightly silly choice */ +/* sda1 - slightly silly choice */ +#define DEFAULT_ROOT_DEVICE MKDEV(SCSI_DISK0_MAJOR, 1) sys_ctrler_t sys_ctrler = SYS_CTRLER_UNKNOWN; EXPORT_SYMBOL(sys_ctrler); diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index f4c1e6e97ad5..50206feac577 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -108,9 +108,9 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data) static DEFINE_MUTEX(ubd_lock); static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */ -static int ubd_open(struct block_device *bdev, fmode_t mode); -static void ubd_release(struct gendisk *disk, fmode_t mode); -static int ubd_ioctl(struct block_device *bdev, fmode_t mode, +static int ubd_open(struct gendisk *disk, blk_mode_t mode); +static void ubd_release(struct gendisk *disk); +static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo); @@ -1154,9 +1154,8 @@ static int __init ubd_driver_init(void){ device_initcall(ubd_driver_init); -static int ubd_open(struct block_device *bdev, fmode_t mode) +static int ubd_open(struct gendisk *disk, blk_mode_t mode) { - struct gendisk *disk = bdev->bd_disk; struct ubd *ubd_dev = disk->private_data; int err = 0; @@ -1171,19 +1170,12 @@ static int ubd_open(struct block_device *bdev, fmode_t mode) } ubd_dev->count++; set_disk_ro(disk, !ubd_dev->openflags.w); - - /* This should no more be needed. And it didn't work anyway to exclude - * read-write remounting of filesystems.*/ - /*if((mode & FMODE_WRITE) && !ubd_dev->openflags.w){ - if(--ubd_dev->count == 0) ubd_close_dev(ubd_dev); - err = -EROFS; - }*/ out: mutex_unlock(&ubd_mutex); return err; } -static void ubd_release(struct gendisk *disk, fmode_t mode) +static void ubd_release(struct gendisk *disk) { struct ubd *ubd_dev = disk->private_data; @@ -1397,7 +1389,7 @@ static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static int ubd_ioctl(struct block_device *bdev, fmode_t mode, +static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct ubd *ubd_dev = bdev->bd_disk->private_data; diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index f50caaa1c249..178cf96ca10a 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -120,9 +120,9 @@ static void simdisk_submit_bio(struct bio *bio) bio_endio(bio); } -static int simdisk_open(struct block_device *bdev, fmode_t mode) +static int simdisk_open(struct gendisk *disk, blk_mode_t mode) { - struct simdisk *dev = bdev->bd_disk->private_data; + struct simdisk *dev = disk->private_data; spin_lock(&dev->lock); ++dev->users; @@ -130,7 +130,7 @@ static int simdisk_open(struct block_device *bdev, fmode_t mode) return 0; } -static void simdisk_release(struct gendisk *disk, fmode_t mode) +static void simdisk_release(struct gendisk *disk) { struct simdisk *dev = disk->private_data; spin_lock(&dev->lock); diff --git a/block/Makefile b/block/Makefile index b31b05390749..46ada9dc8bbf 100644 --- a/block/Makefile +++ b/block/Makefile @@ -9,7 +9,7 @@ obj-y := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \ genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \ - disk-events.o blk-ia-ranges.o + disk-events.o blk-ia-ranges.o early-lookup.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o diff --git a/block/bdev.c b/block/bdev.c index 21c63bfef323..979e28a46b98 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -93,7 +93,7 @@ EXPORT_SYMBOL(invalidate_bdev); * Drop all buffers & page cache for given bdev range. This function bails * with error if bdev has other exclusive owner (such as filesystem). */ -int truncate_bdev_range(struct block_device *bdev, fmode_t mode, +int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode, loff_t lstart, loff_t lend) { /* @@ -101,14 +101,14 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, * while we discard the buffer cache to avoid discarding buffers * under live filesystem. */ - if (!(mode & FMODE_EXCL)) { - int err = bd_prepare_to_claim(bdev, truncate_bdev_range); + if (!(mode & BLK_OPEN_EXCL)) { + int err = bd_prepare_to_claim(bdev, truncate_bdev_range, NULL); if (err) goto invalidate; } truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend); - if (!(mode & FMODE_EXCL)) + if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, truncate_bdev_range); return 0; @@ -308,7 +308,7 @@ EXPORT_SYMBOL(thaw_bdev); * pseudo-fs */ -static __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock); +static __cacheline_aligned_in_smp DEFINE_MUTEX(bdev_lock); static struct kmem_cache * bdev_cachep __read_mostly; static struct inode *bdev_alloc_inode(struct super_block *sb) @@ -415,6 +415,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) bdev = I_BDEV(inode); mutex_init(&bdev->bd_fsfreeze_mutex); spin_lock_init(&bdev->bd_size_lock); + mutex_init(&bdev->bd_holder_lock); bdev->bd_partno = partno; bdev->bd_inode = inode; bdev->bd_queue = disk->queue; @@ -463,39 +464,48 @@ long nr_blockdev_pages(void) /** * bd_may_claim - test whether a block device can be claimed * @bdev: block device of interest - * @whole: whole block device containing @bdev, may equal @bdev * @holder: holder trying to claim @bdev + * @hops: holder ops * * Test whether @bdev can be claimed by @holder. * - * CONTEXT: - * spin_lock(&bdev_lock). - * * RETURNS: * %true if @bdev can be claimed, %false otherwise. */ -static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, - void *holder) +static bool bd_may_claim(struct block_device *bdev, void *holder, + const struct blk_holder_ops *hops) { - if (bdev->bd_holder == holder) - return true; /* already a holder */ - else if (bdev->bd_holder != NULL) - return false; /* held by someone else */ - else if (whole == bdev) - return true; /* is a whole device which isn't held */ - - else if (whole->bd_holder == bd_may_claim) - return true; /* is a partition of a device that is being partitioned */ - else if (whole->bd_holder != NULL) - return false; /* is a partition of a held device */ - else - return true; /* is a partition of an un-held device */ + struct block_device *whole = bdev_whole(bdev); + + lockdep_assert_held(&bdev_lock); + + if (bdev->bd_holder) { + /* + * The same holder can always re-claim. + */ + if (bdev->bd_holder == holder) { + if (WARN_ON_ONCE(bdev->bd_holder_ops != hops)) + return false; + return true; + } + return false; + } + + /* + * If the whole devices holder is set to bd_may_claim, a partition on + * the device is claimed, but not the whole device. + */ + if (whole != bdev && + whole->bd_holder && whole->bd_holder != bd_may_claim) + return false; + return true; } /** * bd_prepare_to_claim - claim a block device * @bdev: block device of interest * @holder: holder trying to claim @bdev + * @hops: holder ops. * * Claim @bdev. This function fails if @bdev is already claimed by another * holder and waits if another claiming is in progress. return, the caller @@ -504,17 +514,18 @@ 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, void *holder) +int bd_prepare_to_claim(struct block_device *bdev, void *holder, + const struct blk_holder_ops *hops) { struct block_device *whole = bdev_whole(bdev); if (WARN_ON_ONCE(!holder)) return -EINVAL; retry: - spin_lock(&bdev_lock); + mutex_lock(&bdev_lock); /* if someone else claimed, fail */ - if (!bd_may_claim(bdev, whole, holder)) { - spin_unlock(&bdev_lock); + if (!bd_may_claim(bdev, holder, hops)) { + mutex_unlock(&bdev_lock); return -EBUSY; } @@ -524,7 +535,7 @@ retry: DEFINE_WAIT(wait); prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); - spin_unlock(&bdev_lock); + mutex_unlock(&bdev_lock); schedule(); finish_wait(wq, &wait); goto retry; @@ -532,7 +543,7 @@ retry: /* yay, all mine */ whole->bd_claiming = holder; - spin_unlock(&bdev_lock); + mutex_unlock(&bdev_lock); return 0; } EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */ @@ -550,16 +561,18 @@ 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 * @holder: holder that has claimed @bdev + * @hops: block device holder operations * * 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, void *holder) +static void bd_finish_claiming(struct block_device *bdev, void *holder, + const struct blk_holder_ops *hops) { struct block_device *whole = bdev_whole(bdev); - spin_lock(&bdev_lock); - BUG_ON(!bd_may_claim(bdev, whole, holder)); + mutex_lock(&bdev_lock); + BUG_ON(!bd_may_claim(bdev, holder, hops)); /* * Note that for a whole device bd_holders will be incremented twice, * and bd_holder will be set to bd_may_claim before being set to holder @@ -567,9 +580,12 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder) whole->bd_holders++; whole->bd_holder = bd_may_claim; bdev->bd_holders++; + mutex_lock(&bdev->bd_holder_lock); bdev->bd_holder = holder; + bdev->bd_holder_ops = hops; + mutex_unlock(&bdev->bd_holder_lock); bd_clear_claiming(whole, holder); - spin_unlock(&bdev_lock); + mutex_unlock(&bdev_lock); } /** @@ -583,12 +599,47 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder) */ void bd_abort_claiming(struct block_device *bdev, void *holder) { - spin_lock(&bdev_lock); + mutex_lock(&bdev_lock); bd_clear_claiming(bdev_whole(bdev), holder); - spin_unlock(&bdev_lock); + mutex_unlock(&bdev_lock); } EXPORT_SYMBOL(bd_abort_claiming); +static void bd_end_claim(struct block_device *bdev, void *holder) +{ + struct block_device *whole = bdev_whole(bdev); + bool unblock = false; + + /* + * Release a claim on the device. The holder fields are protected with + * bdev_lock. open_mutex is used to synchronize disk_holder unlinking. + */ + mutex_lock(&bdev_lock); + WARN_ON_ONCE(bdev->bd_holder != holder); + WARN_ON_ONCE(--bdev->bd_holders < 0); + WARN_ON_ONCE(--whole->bd_holders < 0); + if (!bdev->bd_holders) { + mutex_lock(&bdev->bd_holder_lock); + bdev->bd_holder = NULL; + bdev->bd_holder_ops = NULL; + mutex_unlock(&bdev->bd_holder_lock); + if (bdev->bd_write_holder) + unblock = true; + } + if (!whole->bd_holders) + whole->bd_holder = NULL; + mutex_unlock(&bdev_lock); + + /* + * If this was the last claim, remove holder link and unblock evpoll if + * it was a write holder. + */ + if (unblock) { + disk_unblock_events(bdev->bd_disk); + bdev->bd_write_holder = false; + } +} + static void blkdev_flush_mapping(struct block_device *bdev) { WARN_ON_ONCE(bdev->bd_holders); @@ -597,13 +648,13 @@ static void blkdev_flush_mapping(struct block_device *bdev) bdev_write_inode(bdev); } -static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) +static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) { struct gendisk *disk = bdev->bd_disk; int ret; if (disk->fops->open) { - ret = disk->fops->open(bdev, mode); + ret = disk->fops->open(disk, mode); if (ret) { /* avoid ghost partitions on a removed medium */ if (ret == -ENOMEDIUM && @@ -621,22 +672,19 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) return 0; } -static void blkdev_put_whole(struct block_device *bdev, fmode_t mode) +static void blkdev_put_whole(struct block_device *bdev) { if (atomic_dec_and_test(&bdev->bd_openers)) blkdev_flush_mapping(bdev); if (bdev->bd_disk->fops->release) - bdev->bd_disk->fops->release(bdev->bd_disk, mode); + bdev->bd_disk->fops->release(bdev->bd_disk); } -static int blkdev_get_part(struct block_device *part, fmode_t mode) +static int blkdev_get_part(struct block_device *part, blk_mode_t mode) { struct gendisk *disk = part->bd_disk; int ret; - if (atomic_read(&part->bd_openers)) - goto done; - ret = blkdev_get_whole(bdev_whole(part), mode); if (ret) return ret; @@ -645,26 +693,27 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode) if (!bdev_nr_sectors(part)) goto out_blkdev_put; - disk->open_partitions++; - set_init_blocksize(part); -done: + if (!atomic_read(&part->bd_openers)) { + disk->open_partitions++; + set_init_blocksize(part); + } atomic_inc(&part->bd_openers); return 0; out_blkdev_put: - blkdev_put_whole(bdev_whole(part), mode); + blkdev_put_whole(bdev_whole(part)); return ret; } -static void blkdev_put_part(struct block_device *part, fmode_t mode) +static void blkdev_put_part(struct block_device *part) { struct block_device *whole = bdev_whole(part); - if (!atomic_dec_and_test(&part->bd_openers)) - return; - blkdev_flush_mapping(part); - whole->bd_disk->open_partitions--; - blkdev_put_whole(whole, mode); + if (atomic_dec_and_test(&part->bd_openers)) { + blkdev_flush_mapping(part); + whole->bd_disk->open_partitions--; + } + blkdev_put_whole(whole); } struct block_device *blkdev_get_no_open(dev_t dev) @@ -695,17 +744,17 @@ void blkdev_put_no_open(struct block_device *bdev) { put_device(&bdev->bd_device); } - + /** * blkdev_get_by_dev - open a block device by device number * @dev: device number of block device to open - * @mode: FMODE_* mask + * @mode: open mode (BLK_OPEN_*) * @holder: exclusive holder identifier + * @hops: holder operations * - * 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. + * Open the block device described by device number @dev. If @holder is not + * %NULL, the block device is opened with exclusive access. Exclusive opens may + * nest for the same @holder. * * 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 @@ -717,7 +766,8 @@ void blkdev_put_no_open(struct block_device *bdev) * RETURNS: * Reference to the 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 *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops) { bool unblock_events = true; struct block_device *bdev; @@ -726,8 +776,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) ret = devcgroup_check_permission(DEVCG_DEV_BLOCK, MAJOR(dev), MINOR(dev), - ((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) | - ((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0)); + ((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) | + ((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0)); if (ret) return ERR_PTR(ret); @@ -736,10 +786,16 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) return ERR_PTR(-ENXIO); disk = bdev->bd_disk; - if (mode & FMODE_EXCL) { - ret = bd_prepare_to_claim(bdev, holder); + if (holder) { + mode |= BLK_OPEN_EXCL; + ret = bd_prepare_to_claim(bdev, holder, hops); if (ret) goto put_blkdev; + } else { + if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL)) { + ret = -EIO; + goto put_blkdev; + } } disk_block_events(disk); @@ -756,8 +812,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) ret = blkdev_get_whole(bdev, mode); if (ret) goto put_module; - if (mode & FMODE_EXCL) { - bd_finish_claiming(bdev, holder); + if (holder) { + bd_finish_claiming(bdev, holder, hops); /* * Block event polling for write claims if requested. Any write @@ -766,7 +822,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) * writeable reference is too fragile given the way @mode is * used in blkdev_get/put(). */ - if ((mode & FMODE_WRITE) && !bdev->bd_write_holder && + if ((mode & BLK_OPEN_WRITE) && !bdev->bd_write_holder && (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) { bdev->bd_write_holder = true; unblock_events = false; @@ -780,7 +836,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) put_module: module_put(disk->fops->owner); abort_claiming: - if (mode & FMODE_EXCL) + if (holder) bd_abort_claiming(bdev, holder); mutex_unlock(&disk->open_mutex); disk_unblock_events(disk); @@ -793,13 +849,13 @@ EXPORT_SYMBOL(blkdev_get_by_dev); /** * blkdev_get_by_path - open a block device by name * @path: path to the block device to open - * @mode: FMODE_* mask + * @mode: open mode (BLK_OPEN_*) * @holder: exclusive holder identifier + * @hops: holder operations * - * 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. + * Open the block device described by the device file at @path. If @holder is + * not %NULL, the block device is opened with exclusive access. Exclusive opens + * may nest for the same @holder. * * CONTEXT: * Might sleep. @@ -807,8 +863,8 @@ EXPORT_SYMBOL(blkdev_get_by_dev); * RETURNS: * 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 *blkdev_get_by_path(const char *path, blk_mode_t mode, + void *holder, const struct blk_holder_ops *hops) { struct block_device *bdev; dev_t dev; @@ -818,9 +874,9 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, if (error) return ERR_PTR(error); - bdev = blkdev_get_by_dev(dev, mode, holder); - if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) { - blkdev_put(bdev, mode); + bdev = blkdev_get_by_dev(dev, mode, holder, hops); + if (!IS_ERR(bdev) && (mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { + blkdev_put(bdev, holder); return ERR_PTR(-EACCES); } @@ -828,7 +884,7 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, } EXPORT_SYMBOL(blkdev_get_by_path); -void blkdev_put(struct block_device *bdev, fmode_t mode) +void blkdev_put(struct block_device *bdev, void *holder) { struct gendisk *disk = bdev->bd_disk; @@ -843,36 +899,8 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) sync_blockdev(bdev); mutex_lock(&disk->open_mutex); - if (mode & FMODE_EXCL) { - struct block_device *whole = bdev_whole(bdev); - bool bdev_free; - - /* - * Release a claim on the device. The holder fields - * are protected with bdev_lock. open_mutex is to - * synchronize disk_holder unlinking. - */ - spin_lock(&bdev_lock); - - WARN_ON_ONCE(--bdev->bd_holders < 0); - WARN_ON_ONCE(--whole->bd_holders < 0); - - if ((bdev_free = !bdev->bd_holders)) - bdev->bd_holder = NULL; - if (!whole->bd_holders) - whole->bd_holder = NULL; - - spin_unlock(&bdev_lock); - - /* - * If this was the last claim, remove holder link and - * unblock evpoll if it was a write holder. - */ - if (bdev_free && bdev->bd_write_holder) { - disk_unblock_events(disk); - bdev->bd_write_holder = false; - } - } + if (holder) + bd_end_claim(bdev, holder); /* * Trigger event checking and tell drivers to flush MEDIA_CHANGE @@ -882,9 +910,9 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE); if (bdev_is_partition(bdev)) - blkdev_put_part(bdev, mode); + blkdev_put_part(bdev); else - blkdev_put_whole(bdev, mode); + blkdev_put_whole(bdev); mutex_unlock(&disk->open_mutex); module_put(disk->fops->owner); diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 3164e3177965..09bbbcf9e049 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5403,6 +5403,10 @@ void bfq_put_queue(struct bfq_queue *bfqq) if (bfqq->bfqd->last_completed_rq_bfqq == bfqq) bfqq->bfqd->last_completed_rq_bfqq = NULL; + WARN_ON_ONCE(!list_empty(&bfqq->fifo)); + WARN_ON_ONCE(!RB_EMPTY_ROOT(&bfqq->sort_list)); + WARN_ON_ONCE(bfqq->dispatched); + kmem_cache_free(bfq_pool, bfqq); bfqg_and_blkg_put(bfqg); } @@ -7135,6 +7139,7 @@ static void bfq_exit_queue(struct elevator_queue *e) { struct bfq_data *bfqd = e->elevator_data; struct bfq_queue *bfqq, *n; + unsigned int actuator; hrtimer_cancel(&bfqd->idle_slice_timer); @@ -7143,6 +7148,10 @@ static void bfq_exit_queue(struct elevator_queue *e) bfq_deactivate_bfqq(bfqd, bfqq, false, false); spin_unlock_irq(&bfqd->lock); + for (actuator = 0; actuator < bfqd->num_actuators; actuator++) + WARN_ON_ONCE(bfqd->rq_in_driver[actuator]); + WARN_ON_ONCE(bfqd->tot_rq_in_driver); + hrtimer_cancel(&bfqd->idle_slice_timer); /* release oom-queue reference to root group */ diff --git a/block/bio.c b/block/bio.c index 043944fd46eb..8672179213b9 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1138,6 +1138,14 @@ int bio_add_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL(bio_add_page); +void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, + size_t off) +{ + WARN_ON_ONCE(len > UINT_MAX); + WARN_ON_ONCE(off > UINT_MAX); + __bio_add_page(bio, &folio->page, len, off); +} + /** * bio_add_folio - Attempt to add part of a folio to a bio. * @bio: BIO to add to. @@ -1169,7 +1177,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty) bio_for_each_segment_all(bvec, bio, iter_all) { if (mark_dirty && !PageCompound(bvec->bv_page)) set_page_dirty_lock(bvec->bv_page); - put_page(bvec->bv_page); + bio_release_page(bio, bvec->bv_page); } } EXPORT_SYMBOL_GPL(__bio_release_pages); @@ -1191,7 +1199,6 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) bio->bi_io_vec = (struct bio_vec *)iter->bvec; bio->bi_iter.bi_bvec_done = iter->iov_offset; bio->bi_iter.bi_size = size; - bio_set_flag(bio, BIO_NO_PAGE_REF); bio_set_flag(bio, BIO_CLONED); } @@ -1206,7 +1213,7 @@ static int bio_iov_add_page(struct bio *bio, struct page *page, } if (same_page) - put_page(page); + bio_release_page(bio, page); return 0; } @@ -1220,7 +1227,7 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page, queue_max_zone_append_sectors(q), &same_page) != len) return -EINVAL; if (same_page) - put_page(page); + bio_release_page(bio, page); return 0; } @@ -1231,10 +1238,10 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page, * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * - * Pins pages from *iter and appends them to @bio's bvec array. The - * pages will have to be released using put_page() when done. - * For multi-segment *iter, this function only adds pages from the - * next non-empty segment of the iov iterator. + * Extracts pages from *iter and appends them to @bio's bvec array. The pages + * will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag. + * For a multi-segment *iter, this function only adds pages from the next + * non-empty segment of the iov iterator. */ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { @@ -1266,9 +1273,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) * result to ensure the bio's total size is correct. The remainder of * the iov data will be picked up in the next bio iteration. */ - size = iov_iter_get_pages(iter, pages, - UINT_MAX - bio->bi_iter.bi_size, - nr_pages, &offset, extraction_flags); + size = iov_iter_extract_pages(iter, &pages, + UINT_MAX - bio->bi_iter.bi_size, + nr_pages, extraction_flags, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; @@ -1301,7 +1308,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) iov_iter_revert(iter, left); out: while (i < nr_pages) - put_page(pages[i++]); + bio_release_page(bio, pages[i++]); return ret; } @@ -1336,6 +1343,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) return 0; } + if (iov_iter_extract_will_pin(iter)) + bio_set_flag(bio, BIO_PAGE_PINNED); do { ret = __bio_iov_iter_get_pages(bio, iter); } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0)); @@ -1489,8 +1498,8 @@ void bio_set_pages_dirty(struct bio *bio) * the BIO and re-dirty the pages in process context. * * It is expected that bio_check_pages_dirty() will wholly own the BIO from - * here on. It will run one put_page() against each page and will run one - * bio_put() against the BIO. + * here on. It will unpin each page and will run one bio_put() against the + * BIO. */ static void bio_dirty_fn(struct work_struct *work); diff --git a/block/blk-cgroup-fc-appid.c b/block/blk-cgroup-fc-appid.c index 842e5e1c0f3c..3ec21333f393 100644 --- a/block/blk-cgroup-fc-appid.c +++ b/block/blk-cgroup-fc-appid.c @@ -34,7 +34,7 @@ int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) * the vmid from the fabric. * Adding the overhead of a lock is not necessary. */ - strlcpy(blkcg->fc_app_id, app_id, app_id_len); + strscpy(blkcg->fc_app_id, app_id, app_id_len); css_put(css); out_cgrp_put: cgroup_put(cgrp); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index dce1548a7a0c..aaf9903ad7b2 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -624,8 +624,13 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct blkg_iostat_set *bis = per_cpu_ptr(blkg->iostat_cpu, cpu); memset(bis, 0, sizeof(*bis)); + + /* Re-initialize the cleared blkg_iostat_set */ + u64_stats_init(&bis->sync); + bis->blkg = blkg; } memset(&blkg->iostat, 0, sizeof(blkg->iostat)); + u64_stats_init(&blkg->iostat.sync); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -762,6 +767,13 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) return -ENODEV; } + mutex_lock(&bdev->bd_queue->rq_qos_mutex); + if (!disk_live(bdev->bd_disk)) { + blkdev_put_no_open(bdev); + mutex_unlock(&bdev->bd_queue->rq_qos_mutex); + return -ENODEV; + } + ctx->body = input; ctx->bdev = bdev; return 0; @@ -906,6 +918,7 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep); */ void blkg_conf_exit(struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_queue->queue_lock) + __releases(&ctx->bdev->bd_queue->rq_qos_mutex) { if (ctx->blkg) { spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock); @@ -913,6 +926,7 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx) } if (ctx->bdev) { + mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); blkdev_put_no_open(ctx->bdev); ctx->body = NULL; ctx->bdev = NULL; diff --git a/block/blk-core.c b/block/blk-core.c index 1da77e7d6289..3fc68b944479 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -420,6 +420,7 @@ struct request_queue *blk_alloc_queue(int node_id) mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); mutex_init(&q->sysfs_dir_lock); + mutex_init(&q->rq_qos_mutex); spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); diff --git a/block/blk-flush.c b/block/blk-flush.c index 04698ed9bcd4..dba392cf22be 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -188,7 +188,9 @@ static void blk_flush_complete_seq(struct request *rq, case REQ_FSEQ_DATA: list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); - blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD); + spin_lock(&q->requeue_lock); + list_add_tail(&rq->queuelist, &q->flush_list); + spin_unlock(&q->requeue_lock); blk_mq_kick_requeue_list(q); break; @@ -346,7 +348,10 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, smp_wmb(); req_ref_set(flush_rq, 1); - blk_mq_add_to_requeue_list(flush_rq, 0); + spin_lock(&q->requeue_lock); + list_add_tail(&flush_rq->queuelist, &q->flush_list); + spin_unlock(&q->requeue_lock); + blk_mq_kick_requeue_list(q); } @@ -376,22 +381,29 @@ static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq, return RQ_END_IO_NONE; } -/** - * blk_insert_flush - insert a new PREFLUSH/FUA request - * @rq: request to insert - * - * To be called from __elv_add_request() for %ELEVATOR_INSERT_FLUSH insertions. - * or __blk_mq_run_hw_queue() to dispatch request. - * @rq is being submitted. Analyze what needs to be done and put it on the - * right queue. +static void blk_rq_init_flush(struct request *rq) +{ + rq->flush.seq = 0; + INIT_LIST_HEAD(&rq->flush.list); + rq->rq_flags |= RQF_FLUSH_SEQ; + rq->flush.saved_end_io = rq->end_io; /* Usually NULL */ + rq->end_io = mq_flush_data_end_io; +} + +/* + * Insert a PREFLUSH/FUA request into the flush state machine. + * Returns true if the request has been consumed by the flush state machine, + * or false if the caller should continue to process it. */ -void blk_insert_flush(struct request *rq) +bool blk_insert_flush(struct request *rq) { struct request_queue *q = rq->q; unsigned long fflags = q->queue_flags; /* may change, cache */ unsigned int policy = blk_flush_policy(fflags, rq); struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx); - struct blk_mq_hw_ctx *hctx = rq->mq_hctx; + + /* FLUSH/FUA request must never be merged */ + WARN_ON_ONCE(rq->bio != rq->biotail); /* * @policy now records what operations need to be done. Adjust @@ -408,45 +420,45 @@ void blk_insert_flush(struct request *rq) */ rq->cmd_flags |= REQ_SYNC; - /* - * An empty flush handed down from a stacking driver may - * translate into nothing if the underlying device does not - * advertise a write-back cache. In this case, simply - * complete the request. - */ - if (!policy) { + switch (policy) { + case 0: + /* + * An empty flush handed down from a stacking driver may + * translate into nothing if the underlying device does not + * advertise a write-back cache. In this case, simply + * complete the request. + */ blk_mq_end_request(rq, 0); - return; - } - - BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */ - - /* - * If there's data but flush is not necessary, the request can be - * processed directly without going through flush machinery. Queue - * for normal execution. - */ - if ((policy & REQ_FSEQ_DATA) && - !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { - blk_mq_request_bypass_insert(rq, 0); - blk_mq_run_hw_queue(hctx, false); - return; + return true; + case REQ_FSEQ_DATA: + /* + * If there's data, but no flush is necessary, the request can + * be processed directly without going through flush machinery. + * Queue for normal execution. + */ + return false; + case REQ_FSEQ_DATA | REQ_FSEQ_POSTFLUSH: + /* + * Initialize the flush fields and completion handler to trigger + * the post flush, and then just pass the command on. + */ + blk_rq_init_flush(rq); + rq->flush.seq |= REQ_FSEQ_POSTFLUSH; + spin_lock_irq(&fq->mq_flush_lock); + list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); + spin_unlock_irq(&fq->mq_flush_lock); + return false; + default: + /* + * Mark the request as part of a flush sequence and submit it + * for further processing to the flush state machine. + */ + blk_rq_init_flush(rq); + spin_lock_irq(&fq->mq_flush_lock); + blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0); + spin_unlock_irq(&fq->mq_flush_lock); + return true; } - - /* - * @rq should go through flush machinery. Mark it part of flush - * sequence and submit for further processing. - */ - memset(&rq->flush, 0, sizeof(rq->flush)); - INIT_LIST_HEAD(&rq->flush.list); - rq->rq_flags |= RQF_FLUSH_SEQ; - rq->flush.saved_end_io = rq->end_io; /* Usually NULL */ - - rq->end_io = mq_flush_data_end_io; - - spin_lock_irq(&fq->mq_flush_lock); - blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0); - spin_unlock_irq(&fq->mq_flush_lock); } /** diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 63fc02042408..25dd4db11121 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -77,6 +77,10 @@ static void ioc_destroy_icq(struct io_cq *icq) struct elevator_type *et = q->elevator->type; lockdep_assert_held(&ioc->lock); + lockdep_assert_held(&q->queue_lock); + + if (icq->flags & ICQ_DESTROYED) + return; radix_tree_delete(&ioc->icq_tree, icq->q->id); hlist_del_init(&icq->ioc_node); @@ -128,12 +132,7 @@ static void ioc_release_fn(struct work_struct *work) spin_lock(&q->queue_lock); spin_lock(&ioc->lock); - /* - * The icq may have been destroyed when the ioc lock - * was released. - */ - if (!(icq->flags & ICQ_DESTROYED)) - ioc_destroy_icq(icq); + ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); rcu_read_unlock(); @@ -171,23 +170,20 @@ static bool ioc_delay_free(struct io_context *ioc) */ void ioc_clear_queue(struct request_queue *q) { - LIST_HEAD(icq_list); - spin_lock_irq(&q->queue_lock); - list_splice_init(&q->icq_list, &icq_list); - spin_unlock_irq(&q->queue_lock); - - rcu_read_lock(); - while (!list_empty(&icq_list)) { + while (!list_empty(&q->icq_list)) { struct io_cq *icq = - list_entry(icq_list.next, struct io_cq, q_node); - - spin_lock_irq(&icq->ioc->lock); - if (!(icq->flags & ICQ_DESTROYED)) - ioc_destroy_icq(icq); - spin_unlock_irq(&icq->ioc->lock); + list_first_entry(&q->icq_list, struct io_cq, q_node); + + /* + * Other context won't hold ioc lock to wait for queue_lock, see + * details in ioc_release_fn(). + */ + spin_lock(&icq->ioc->lock); + ioc_destroy_icq(icq); + spin_unlock(&icq->ioc->lock); } - rcu_read_unlock(); + spin_unlock_irq(&q->queue_lock); } #else /* CONFIG_BLK_ICQ */ static inline void ioc_exit_icqs(struct io_context *ioc) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 285ced3467ab..6084a9519883 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2455,6 +2455,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, u32 hwi, adj_step; s64 margin; u64 cost, new_inuse; + unsigned long flags; current_hweight(iocg, NULL, &hwi); old_hwi = hwi; @@ -2473,11 +2474,11 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, iocg->inuse == iocg->active) return cost; - spin_lock_irq(&ioc->lock); + spin_lock_irqsave(&ioc->lock, flags); /* we own inuse only when @iocg is in the normal active state */ if (iocg->abs_vdebt || list_empty(&iocg->active_list)) { - spin_unlock_irq(&ioc->lock); + spin_unlock_irqrestore(&ioc->lock, flags); return cost; } @@ -2498,7 +2499,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, } while (time_after64(vtime + cost, now->vnow) && iocg->inuse != iocg->active); - spin_unlock_irq(&ioc->lock); + spin_unlock_irqrestore(&ioc->lock, flags); TRACE_IOCG_PATH(inuse_adjust, iocg, now, old_inuse, iocg->inuse, old_hwi, hwi); diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c index 055529b9b92b..4051fada01f1 100644 --- a/block/blk-ioprio.c +++ b/block/blk-ioprio.c @@ -23,25 +23,28 @@ /** * enum prio_policy - I/O priority class policy. * @POLICY_NO_CHANGE: (default) do not modify the I/O priority class. - * @POLICY_NONE_TO_RT: modify IOPRIO_CLASS_NONE into IOPRIO_CLASS_RT. + * @POLICY_PROMOTE_TO_RT: modify no-IOPRIO_CLASS_RT to IOPRIO_CLASS_RT. * @POLICY_RESTRICT_TO_BE: modify IOPRIO_CLASS_NONE and IOPRIO_CLASS_RT into * IOPRIO_CLASS_BE. * @POLICY_ALL_TO_IDLE: change the I/O priority class into IOPRIO_CLASS_IDLE. + * @POLICY_NONE_TO_RT: an alias for POLICY_PROMOTE_TO_RT. * * See also <linux/ioprio.h>. */ enum prio_policy { POLICY_NO_CHANGE = 0, - POLICY_NONE_TO_RT = 1, + POLICY_PROMOTE_TO_RT = 1, POLICY_RESTRICT_TO_BE = 2, POLICY_ALL_TO_IDLE = 3, + POLICY_NONE_TO_RT = 4, }; static const char *policy_name[] = { [POLICY_NO_CHANGE] = "no-change", - [POLICY_NONE_TO_RT] = "none-to-rt", + [POLICY_PROMOTE_TO_RT] = "promote-to-rt", [POLICY_RESTRICT_TO_BE] = "restrict-to-be", [POLICY_ALL_TO_IDLE] = "idle", + [POLICY_NONE_TO_RT] = "none-to-rt", }; static struct blkcg_policy ioprio_policy; @@ -189,6 +192,20 @@ void blkcg_set_ioprio(struct bio *bio) if (!blkcg || blkcg->prio_policy == POLICY_NO_CHANGE) return; + if (blkcg->prio_policy == POLICY_PROMOTE_TO_RT || + blkcg->prio_policy == POLICY_NONE_TO_RT) { + /* + * For RT threads, the default priority level is 4 because + * task_nice is 0. By promoting non-RT io-priority to RT-class + * and default level 4, those requests that are already + * RT-class but need a higher io-priority can use ioprio_set() + * to achieve this. + */ + if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) != IOPRIO_CLASS_RT) + bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 4); + return; + } + /* * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers * correspond to a lower priority. Hence, the max_t() below selects diff --git a/block/blk-map.c b/block/blk-map.c index 46eed2e627c3..44d74a30ddac 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -281,21 +281,21 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (blk_queue_pci_p2pdma(rq->q)) extraction_flags |= ITER_ALLOW_P2PDMA; + if (iov_iter_extract_will_pin(iter)) + bio_set_flag(bio, BIO_PAGE_PINNED); while (iov_iter_count(iter)) { - struct page **pages, *stack_pages[UIO_FASTIOV]; + struct page *stack_pages[UIO_FASTIOV]; + struct page **pages = stack_pages; ssize_t bytes; size_t offs; int npages; - if (nr_vecs <= ARRAY_SIZE(stack_pages)) { - pages = stack_pages; - bytes = iov_iter_get_pages(iter, pages, LONG_MAX, - nr_vecs, &offs, extraction_flags); - } else { - bytes = iov_iter_get_pages_alloc(iter, &pages, - LONG_MAX, &offs, extraction_flags); - } + if (nr_vecs > ARRAY_SIZE(stack_pages)) + pages = NULL; + + bytes = iov_iter_extract_pages(iter, &pages, LONG_MAX, + nr_vecs, extraction_flags, &offs); if (unlikely(bytes <= 0)) { ret = bytes ? bytes : -EFAULT; goto out_unmap; @@ -317,7 +317,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (!bio_add_hw_page(rq->q, bio, page, n, offs, max_sectors, &same_page)) { if (same_page) - put_page(page); + bio_release_page(bio, page); break; } @@ -329,7 +329,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, * release the pages we didn't map into the bio, if any */ while (j < npages) - put_page(pages[j++]); + bio_release_page(bio, pages[j++]); if (pages != stack_pages) kvfree(pages); /* couldn't stuff something into bio? */ diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index d23a8554ec4a..c3b5930106b2 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -88,6 +88,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(IO_STAT), QUEUE_FLAG_NAME(NOXMERGES), QUEUE_FLAG_NAME(ADD_RANDOM), + QUEUE_FLAG_NAME(SYNCHRONOUS), QUEUE_FLAG_NAME(SAME_FORCE), QUEUE_FLAG_NAME(INIT_DONE), QUEUE_FLAG_NAME(STABLE_WRITES), @@ -103,6 +104,8 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(RQ_ALLOC_TIME), QUEUE_FLAG_NAME(HCTX_ACTIVE), QUEUE_FLAG_NAME(NOWAIT), + QUEUE_FLAG_NAME(SQ_SCHED), + QUEUE_FLAG_NAME(SKIP_TAGSET_QUIESCE), }; #undef QUEUE_FLAG_NAME @@ -241,14 +244,14 @@ static const char *const cmd_flag_name[] = { #define RQF_NAME(name) [ilog2((__force u32)RQF_##name)] = #name static const char *const rqf_name[] = { RQF_NAME(STARTED), - RQF_NAME(SOFTBARRIER), RQF_NAME(FLUSH_SEQ), RQF_NAME(MIXED_MERGE), RQF_NAME(MQ_INFLIGHT), RQF_NAME(DONTPREP), + RQF_NAME(SCHED_TAGS), + RQF_NAME(USE_SCHED), RQF_NAME(FAILED), RQF_NAME(QUIET), - RQF_NAME(ELVPRIV), RQF_NAME(IO_STAT), RQF_NAME(PM), RQF_NAME(HASHED), @@ -256,7 +259,6 @@ static const char *const rqf_name[] = { RQF_NAME(SPECIAL_PAYLOAD), RQF_NAME(ZONE_WRITE_LOCKED), RQF_NAME(TIMED_OUT), - RQF_NAME(ELV), RQF_NAME(RESV), }; #undef RQF_NAME @@ -399,7 +401,7 @@ static void blk_mq_debugfs_tags_show(struct seq_file *m, seq_printf(m, "nr_tags=%u\n", tags->nr_tags); seq_printf(m, "nr_reserved_tags=%u\n", tags->nr_reserved_tags); seq_printf(m, "active_queues=%d\n", - atomic_read(&tags->active_queues)); + READ_ONCE(tags->active_queues)); seq_puts(m, "\nbitmap_tags:\n"); sbitmap_queue_show(&tags->bitmap_tags, m); diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 7c3cbad17f30..1326526bb733 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -37,7 +37,7 @@ static inline bool blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq, struct bio *bio) { - if (rq->rq_flags & RQF_ELV) { + if (rq->rq_flags & RQF_USE_SCHED) { struct elevator_queue *e = q->elevator; if (e->type->ops.allow_merge) @@ -48,7 +48,7 @@ blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq, static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) { - if (rq->rq_flags & RQF_ELV) { + if (rq->rq_flags & RQF_USE_SCHED) { struct elevator_queue *e = rq->q->elevator; if (e->type->ops.completed_request) @@ -58,11 +58,11 @@ static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) static inline void blk_mq_sched_requeue_request(struct request *rq) { - if (rq->rq_flags & RQF_ELV) { + if (rq->rq_flags & RQF_USE_SCHED) { struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; - if ((rq->rq_flags & RQF_ELVPRIV) && e->type->ops.requeue_request) + if (e->type->ops.requeue_request) e->type->ops.requeue_request(rq); } } diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index dfd81cab5788..cc57e2dd9a0b 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; + struct blk_mq_tags *tags = hctx->tags; /* * calling test_bit() prior to test_and_set_bit() is intentional, @@ -55,9 +56,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) return; } - users = atomic_inc_return(&hctx->tags->active_queues); - - blk_mq_update_wake_batch(hctx->tags, users); + spin_lock_irq(&tags->lock); + users = tags->active_queues + 1; + WRITE_ONCE(tags->active_queues, users); + blk_mq_update_wake_batch(tags, users); + spin_unlock_irq(&tags->lock); } /* @@ -90,9 +93,11 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) return; } - users = atomic_dec_return(&tags->active_queues); - + spin_lock_irq(&tags->lock); + users = tags->active_queues - 1; + WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); + spin_unlock_irq(&tags->lock); blk_mq_tag_wakeup_all(tags, false); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 850bfb844ed2..decb6ab2d508 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -45,6 +45,8 @@ static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); static void blk_mq_insert_request(struct request *rq, blk_insert_t flags); +static void blk_mq_request_bypass_insert(struct request *rq, + blk_insert_t flags); static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list); @@ -354,12 +356,12 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, data->rq_flags |= RQF_IO_STAT; rq->rq_flags = data->rq_flags; - if (!(data->rq_flags & RQF_ELV)) { - rq->tag = tag; - rq->internal_tag = BLK_MQ_NO_TAG; - } else { + if (data->rq_flags & RQF_SCHED_TAGS) { rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = tag; + } else { + rq->tag = tag; + rq->internal_tag = BLK_MQ_NO_TAG; } rq->timeout = 0; @@ -386,17 +388,14 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, WRITE_ONCE(rq->deadline, 0); req_ref_set(rq, 1); - if (rq->rq_flags & RQF_ELV) { + if (rq->rq_flags & RQF_USE_SCHED) { struct elevator_queue *e = data->q->elevator; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); - if (!op_is_flush(data->cmd_flags) && - e->type->ops.prepare_request) { + if (e->type->ops.prepare_request) e->type->ops.prepare_request(rq); - rq->rq_flags |= RQF_ELVPRIV; - } } return rq; @@ -449,26 +448,32 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) data->flags |= BLK_MQ_REQ_NOWAIT; if (q->elevator) { - struct elevator_queue *e = q->elevator; - - data->rq_flags |= RQF_ELV; + /* + * All requests use scheduler tags when an I/O scheduler is + * enabled for the queue. + */ + data->rq_flags |= RQF_SCHED_TAGS; /* * Flush/passthrough requests are special and go directly to the - * dispatch list. Don't include reserved tags in the - * limiting, as it isn't useful. + * dispatch list. */ - if (!op_is_flush(data->cmd_flags) && - !blk_op_is_passthrough(data->cmd_flags) && - e->type->ops.limit_depth && - !(data->flags & BLK_MQ_REQ_RESERVED)) - e->type->ops.limit_depth(data->cmd_flags, data); + if ((data->cmd_flags & REQ_OP_MASK) != REQ_OP_FLUSH && + !blk_op_is_passthrough(data->cmd_flags)) { + struct elevator_mq_ops *ops = &q->elevator->type->ops; + + WARN_ON_ONCE(data->flags & BLK_MQ_REQ_RESERVED); + + data->rq_flags |= RQF_USE_SCHED; + if (ops->limit_depth) + ops->limit_depth(data->cmd_flags, data); + } } retry: data->ctx = blk_mq_get_ctx(q); data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); - if (!(data->rq_flags & RQF_ELV)) + if (!(data->rq_flags & RQF_SCHED_TAGS)) blk_mq_tag_busy(data->hctx); if (data->flags & BLK_MQ_REQ_RESERVED) @@ -648,10 +653,10 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, goto out_queue_exit; data.ctx = __blk_mq_get_ctx(q, cpu); - if (!q->elevator) - blk_mq_tag_busy(data.hctx); + if (q->elevator) + data.rq_flags |= RQF_SCHED_TAGS; else - data.rq_flags |= RQF_ELV; + blk_mq_tag_busy(data.hctx); if (flags & BLK_MQ_REQ_RESERVED) data.rq_flags |= RQF_RESV; @@ -699,7 +704,7 @@ void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; - if ((rq->rq_flags & RQF_ELVPRIV) && + if ((rq->rq_flags & RQF_USE_SCHED) && q->elevator->type->ops.finish_request) q->elevator->type->ops.finish_request(rq); @@ -957,6 +962,8 @@ EXPORT_SYMBOL_GPL(blk_update_request); static inline void blk_account_io_done(struct request *req, u64 now) { + trace_block_io_done(req); + /* * Account IO completion. flush_rq isn't accounted as a * normal IO on queueing nor completion. Accounting the @@ -976,6 +983,8 @@ static inline void blk_account_io_done(struct request *req, u64 now) static inline void blk_account_io_start(struct request *req) { + trace_block_io_start(req); + if (blk_do_io_stat(req)) { /* * All non-passthrough requests are created from a bio with one @@ -1176,8 +1185,9 @@ bool blk_mq_complete_request_remote(struct request *rq) * or a polled request, always complete locally, * it's pointless to redirect the completion. */ - if (rq->mq_hctx->nr_ctx == 1 || - rq->cmd_flags & REQ_POLLED) + if ((rq->mq_hctx->nr_ctx == 1 && + rq->mq_ctx->cpu == raw_smp_processor_id()) || + rq->cmd_flags & REQ_POLLED) return false; if (blk_mq_complete_need_ipi(rq)) { @@ -1270,7 +1280,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) if (!plug->multiple_queues && last && last->q != rq->q) plug->multiple_queues = true; - if (!plug->has_elevator && (rq->rq_flags & RQF_ELV)) + if (!plug->has_elevator && (rq->rq_flags & RQF_USE_SCHED)) plug->has_elevator = true; rq->rq_next = NULL; rq_list_add(&plug->mq_list, rq); @@ -1411,13 +1421,16 @@ static void __blk_mq_requeue_request(struct request *rq) void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list) { struct request_queue *q = rq->q; + unsigned long flags; __blk_mq_requeue_request(rq); /* this request will be re-inserted to io scheduler queue */ blk_mq_sched_requeue_request(rq); - blk_mq_add_to_requeue_list(rq, BLK_MQ_INSERT_AT_HEAD); + spin_lock_irqsave(&q->requeue_lock, flags); + list_add_tail(&rq->queuelist, &q->requeue_list); + spin_unlock_irqrestore(&q->requeue_lock, flags); if (kick_requeue_list) blk_mq_kick_requeue_list(q); @@ -1429,13 +1442,16 @@ static void blk_mq_requeue_work(struct work_struct *work) struct request_queue *q = container_of(work, struct request_queue, requeue_work.work); LIST_HEAD(rq_list); - struct request *rq, *next; + LIST_HEAD(flush_list); + struct request *rq; spin_lock_irq(&q->requeue_lock); list_splice_init(&q->requeue_list, &rq_list); + list_splice_init(&q->flush_list, &flush_list); spin_unlock_irq(&q->requeue_lock); - list_for_each_entry_safe(rq, next, &rq_list, queuelist) { + while (!list_empty(&rq_list)) { + rq = list_entry(rq_list.next, struct request, queuelist); /* * If RQF_DONTPREP ist set, the request has been started by the * driver already and might have driver-specific data allocated @@ -1443,18 +1459,16 @@ static void blk_mq_requeue_work(struct work_struct *work) * block layer merges for the request. */ if (rq->rq_flags & RQF_DONTPREP) { - rq->rq_flags &= ~RQF_SOFTBARRIER; list_del_init(&rq->queuelist); blk_mq_request_bypass_insert(rq, 0); - } else if (rq->rq_flags & RQF_SOFTBARRIER) { - rq->rq_flags &= ~RQF_SOFTBARRIER; + } else { list_del_init(&rq->queuelist); blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD); } } - while (!list_empty(&rq_list)) { - rq = list_entry(rq_list.next, struct request, queuelist); + while (!list_empty(&flush_list)) { + rq = list_entry(flush_list.next, struct request, queuelist); list_del_init(&rq->queuelist); blk_mq_insert_request(rq, 0); } @@ -1462,27 +1476,6 @@ static void blk_mq_requeue_work(struct work_struct *work) blk_mq_run_hw_queues(q, false); } -void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags) -{ - struct request_queue *q = rq->q; - unsigned long flags; - - /* - * We abuse this flag that is otherwise used by the I/O scheduler to - * request head insertion from the workqueue. - */ - BUG_ON(rq->rq_flags & RQF_SOFTBARRIER); - - spin_lock_irqsave(&q->requeue_lock, flags); - if (insert_flags & BLK_MQ_INSERT_AT_HEAD) { - rq->rq_flags |= RQF_SOFTBARRIER; - list_add(&rq->queuelist, &q->requeue_list); - } else { - list_add_tail(&rq->queuelist, &q->requeue_list); - } - spin_unlock_irqrestore(&q->requeue_lock, flags); -} - void blk_mq_kick_requeue_list(struct request_queue *q) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0); @@ -2427,7 +2420,7 @@ static void blk_mq_run_work_fn(struct work_struct *work) * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ -void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags) +static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; @@ -2492,7 +2485,7 @@ static void blk_mq_insert_request(struct request *rq, blk_insert_t flags) * dispatch it given we prioritize requests in hctx->dispatch. */ blk_mq_request_bypass_insert(rq, flags); - } else if (rq->rq_flags & RQF_FLUSH_SEQ) { + } else if (req_op(rq) == REQ_OP_FLUSH) { /* * Firstly normal IO request is inserted to scheduler queue or * sw queue, meantime we add flush request to dispatch queue( @@ -2622,7 +2615,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, return; } - if ((rq->rq_flags & RQF_ELV) || !blk_mq_get_budget_and_tag(rq)) { + if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, false); return; @@ -2711,6 +2704,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) struct request *requeue_list = NULL; struct request **requeue_lastp = &requeue_list; unsigned int depth = 0; + bool is_passthrough = false; LIST_HEAD(list); do { @@ -2719,7 +2713,9 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) if (!this_hctx) { this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; - } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) { + is_passthrough = blk_rq_is_passthrough(rq); + } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx || + is_passthrough != blk_rq_is_passthrough(rq)) { rq_list_add_tail(&requeue_lastp, rq); continue; } @@ -2731,7 +2727,13 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) trace_block_unplug(this_hctx->queue, depth, !from_sched); percpu_ref_get(&this_hctx->queue->q_usage_counter); - if (this_hctx->queue->elevator) { + /* passthrough requests should never be issued to the I/O scheduler */ + if (is_passthrough) { + spin_lock(&this_hctx->lock); + list_splice_tail_init(&list, &this_hctx->dispatch); + spin_unlock(&this_hctx->lock); + blk_mq_run_hw_queue(this_hctx, from_sched); + } else if (this_hctx->queue->elevator) { this_hctx->queue->elevator->type->ops.insert_requests(this_hctx, &list, 0); blk_mq_run_hw_queue(this_hctx, from_sched); @@ -2970,10 +2972,8 @@ void blk_mq_submit_bio(struct bio *bio) return; } - if (op_is_flush(bio->bi_opf)) { - blk_insert_flush(rq); + if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq)) return; - } if (plug) { blk_add_rq_to_plug(plug, rq); @@ -2981,7 +2981,7 @@ void blk_mq_submit_bio(struct bio *bio) } hctx = rq->mq_hctx; - if ((rq->rq_flags & RQF_ELV) || + if ((rq->rq_flags & RQF_USE_SCHED) || (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, true); @@ -4232,6 +4232,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, blk_mq_update_poll_flag(q); INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); + INIT_LIST_HEAD(&q->flush_list); INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); @@ -4608,9 +4609,6 @@ static bool blk_mq_elv_switch_none(struct list_head *head, { struct blk_mq_qe_pair *qe; - if (!q->elevator) - return true; - qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (!qe) return false; @@ -4618,6 +4616,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head, /* q->elevator needs protection from ->sysfs_lock */ mutex_lock(&q->sysfs_lock); + /* the check has to be done with holding sysfs_lock */ + if (!q->elevator) { + kfree(qe); + goto unlock; + } + INIT_LIST_HEAD(&qe->node); qe->q = q; qe->type = q->elevator->type; @@ -4625,6 +4629,7 @@ static bool blk_mq_elv_switch_none(struct list_head *head, __elevator_get(qe->type); list_add(&qe->node, head); elevator_disable(q); +unlock: mutex_unlock(&q->sysfs_lock); return true; diff --git a/block/blk-mq.h b/block/blk-mq.h index e876584d3516..1743857e0b01 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -47,7 +47,6 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *, unsigned int); -void blk_mq_add_to_requeue_list(struct request *rq, blk_insert_t insert_flags); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); @@ -64,10 +63,6 @@ struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); -/* - * Internal helpers for request insertion into sw queues - */ -void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags); /* * CPU -> queue mappings @@ -226,9 +221,9 @@ static inline bool blk_mq_is_shared_tags(unsigned int flags) static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data) { - if (!(data->rq_flags & RQF_ELV)) - return data->hctx->tags; - return data->hctx->sched_tags; + if (data->rq_flags & RQF_SCHED_TAGS) + return data->hctx->sched_tags; + return data->hctx->tags; } static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx) @@ -417,8 +412,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, return true; } - users = atomic_read(&hctx->tags->active_queues); - + users = READ_ONCE(hctx->tags->active_queues); if (!users) return true; diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index d8cc820a365e..167be74df4ee 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -288,11 +288,13 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, void rq_qos_exit(struct request_queue *q) { + mutex_lock(&q->rq_qos_mutex); while (q->rq_qos) { struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; rqos->ops->exit(rqos); } + mutex_unlock(&q->rq_qos_mutex); } int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, @@ -300,6 +302,8 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, { struct request_queue *q = disk->queue; + lockdep_assert_held(&q->rq_qos_mutex); + rqos->disk = disk; rqos->id = id; rqos->ops = ops; @@ -307,18 +311,13 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, /* * No IO can be in-flight when adding rqos, so freeze queue, which * is fine since we only support rq_qos for blk-mq queue. - * - * Reuse ->queue_lock for protecting against other concurrent - * rq_qos adding/deleting */ blk_mq_freeze_queue(q); - spin_lock_irq(&q->queue_lock); if (rq_qos_id(q, rqos->id)) goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; - spin_unlock_irq(&q->queue_lock); blk_mq_unfreeze_queue(q); @@ -330,7 +329,6 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, return 0; ebusy: - spin_unlock_irq(&q->queue_lock); blk_mq_unfreeze_queue(q); return -EBUSY; } @@ -340,21 +338,15 @@ void rq_qos_del(struct rq_qos *rqos) struct request_queue *q = rqos->disk->queue; struct rq_qos **cur; - /* - * See comment in rq_qos_add() about freezing queue & using - * ->queue_lock. - */ - blk_mq_freeze_queue(q); + lockdep_assert_held(&q->rq_qos_mutex); - spin_lock_irq(&q->queue_lock); + blk_mq_freeze_queue(q); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } - spin_unlock_irq(&q->queue_lock); - blk_mq_unfreeze_queue(q); mutex_lock(&q->debugfs_mutex); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 9ec2a2f1eda3..7a87506ff8e1 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -944,7 +944,9 @@ int wbt_init(struct gendisk *disk) /* * Assign rwb and add the stats callback. */ + mutex_lock(&q->rq_qos_mutex); ret = rq_qos_add(&rwb->rqos, disk, RQ_QOS_WBT, &wbt_rqos_ops); + mutex_unlock(&q->rq_qos_mutex); if (ret) goto err_free; diff --git a/block/blk-zoned.c b/block/blk-zoned.c index fce9082384d6..0f9f97cdddd9 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -57,16 +57,10 @@ EXPORT_SYMBOL_GPL(blk_zone_cond_str); */ bool blk_req_needs_zone_write_lock(struct request *rq) { - if (blk_rq_is_passthrough(rq)) - return false; - if (!rq->q->disk->seq_zones_wlock) return false; - if (bdev_op_is_zoned_write(rq->q->disk->part0, req_op(rq))) - return blk_rq_zone_is_seq(rq); - - return false; + return blk_rq_is_seq_zoned_write(rq); } EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock); @@ -329,8 +323,8 @@ static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx, * BLKREPORTZONE ioctl processing. * Called from blkdev_ioctl. */ -int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) +int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd, + unsigned long arg) { void __user *argp = (void __user *)arg; struct zone_report_args args; @@ -362,8 +356,8 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, return 0; } -static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode, - const struct blk_zone_range *zrange) +static int blkdev_truncate_zone_range(struct block_device *bdev, + blk_mode_t mode, const struct blk_zone_range *zrange) { loff_t start, end; @@ -382,7 +376,7 @@ static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode, * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing. * Called from blkdev_ioctl. */ -int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, +int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -396,7 +390,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, if (!bdev_is_zoned(bdev)) return -ENOTTY; - if (!(mode & FMODE_WRITE)) + if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) diff --git a/block/blk.h b/block/blk.h index 45547bcf1119..608c5dcc516b 100644 --- a/block/blk.h +++ b/block/blk.h @@ -269,7 +269,7 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, */ #define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED) -void blk_insert_flush(struct request *rq); +bool blk_insert_flush(struct request *rq); int elevator_switch(struct request_queue *q, struct elevator_type *new_e); void elevator_disable(struct request_queue *q); @@ -394,10 +394,27 @@ static inline struct bio *blk_queue_bounce(struct bio *bio, #ifdef CONFIG_BLK_DEV_ZONED void disk_free_zone_bitmaps(struct gendisk *disk); void disk_clear_zone_settings(struct gendisk *disk); -#else +int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd, + unsigned long arg); +int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long arg); +#else /* CONFIG_BLK_DEV_ZONED */ static inline void disk_free_zone_bitmaps(struct gendisk *disk) {} static inline void disk_clear_zone_settings(struct gendisk *disk) {} -#endif +static inline int blkdev_report_zones_ioctl(struct block_device *bdev, + unsigned int cmd, unsigned long arg) +{ + return -ENOTTY; +} +static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, + blk_mode_t mode, unsigned int cmd, unsigned long arg) +{ + return -ENOTTY; +} +#endif /* CONFIG_BLK_DEV_ZONED */ + +struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); +void bdev_add(struct block_device *bdev, dev_t dev); int blk_alloc_ext_minor(void); void blk_free_ext_minor(unsigned int minor); @@ -409,7 +426,7 @@ int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, int bdev_del_partition(struct gendisk *disk, int partno); int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, sector_t length); -void blk_drop_partitions(struct gendisk *disk); +void drop_partition(struct block_device *part); void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors); @@ -420,9 +437,19 @@ 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); +/* + * Clean up a page appropriately, where the page may be pinned, may have a + * ref taken on it or neither. + */ +static inline void bio_release_page(struct bio *bio, struct page *page) +{ + if (bio_flagged(bio, BIO_PAGE_PINNED)) + unpin_user_page(page); +} + struct request_queue *blk_alloc_queue(int node_id); -int disk_scan_partitions(struct gendisk *disk, fmode_t mode); +int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode); int disk_alloc_events(struct gendisk *disk); void disk_add_events(struct gendisk *disk); @@ -437,6 +464,9 @@ extern struct device_attribute dev_attr_events_poll_msecs; extern struct attribute_group blk_trace_attr_group; +blk_mode_t file_to_blk_mode(struct file *file); +int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode, + loff_t lstart, loff_t lend); long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 435c32373cd6..b3acdbdb6e7e 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -26,7 +26,7 @@ struct bsg_set { }; static int bsg_transport_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, - fmode_t mode, unsigned int timeout) + bool open_for_write, unsigned int timeout) { struct bsg_job *job; struct request *rq; diff --git a/block/bsg.c b/block/bsg.c index 7eca43f33d7f..1a9396a3b7d7 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -39,7 +39,7 @@ static inline struct bsg_device *to_bsg_device(struct inode *inode) #define BSG_MAX_DEVS 32768 static DEFINE_IDA(bsg_minor_ida); -static struct class *bsg_class; +static const struct class bsg_class; static int bsg_major; static unsigned int bsg_timeout(struct bsg_device *bd, struct sg_io_v4 *hdr) @@ -54,7 +54,8 @@ static unsigned int bsg_timeout(struct bsg_device *bd, struct sg_io_v4 *hdr) return max_t(unsigned int, timeout, BLK_MIN_SG_TIMEOUT); } -static int bsg_sg_io(struct bsg_device *bd, fmode_t mode, void __user *uarg) +static int bsg_sg_io(struct bsg_device *bd, bool open_for_write, + void __user *uarg) { struct sg_io_v4 hdr; int ret; @@ -63,7 +64,8 @@ static int bsg_sg_io(struct bsg_device *bd, fmode_t mode, void __user *uarg) return -EFAULT; if (hdr.guard != 'Q') return -EINVAL; - ret = bd->sg_io_fn(bd->queue, &hdr, mode, bsg_timeout(bd, &hdr)); + ret = bd->sg_io_fn(bd->queue, &hdr, open_for_write, + bsg_timeout(bd, &hdr)); if (!ret && copy_to_user(uarg, &hdr, sizeof(hdr))) return -EFAULT; return ret; @@ -146,7 +148,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case SG_EMULATED_HOST: return put_user(1, intp); case SG_IO: - return bsg_sg_io(bd, file->f_mode, uarg); + return bsg_sg_io(bd, file->f_mode & FMODE_WRITE, uarg); case SCSI_IOCTL_SEND_COMMAND: pr_warn_ratelimited("%s: calling unsupported SCSI_IOCTL_SEND_COMMAND\n", current->comm); @@ -206,7 +208,7 @@ struct bsg_device *bsg_register_queue(struct request_queue *q, return ERR_PTR(ret); } bd->device.devt = MKDEV(bsg_major, ret); - bd->device.class = bsg_class; + bd->device.class = &bsg_class; bd->device.parent = parent; bd->device.release = bsg_device_release; dev_set_name(&bd->device, "%s", name); @@ -240,15 +242,19 @@ static char *bsg_devnode(const struct device *dev, umode_t *mode) return kasprintf(GFP_KERNEL, "bsg/%s", dev_name(dev)); } +static const struct class bsg_class = { + .name = "bsg", + .devnode = bsg_devnode, +}; + static int __init bsg_init(void) { dev_t devid; int ret; - bsg_class = class_create("bsg"); - if (IS_ERR(bsg_class)) - return PTR_ERR(bsg_class); - bsg_class->devnode = bsg_devnode; + ret = class_register(&bsg_class); + if (ret) + return ret; ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg"); if (ret) @@ -260,7 +266,7 @@ static int __init bsg_init(void) return 0; destroy_bsg_class: - class_destroy(bsg_class); + class_unregister(&bsg_class); return ret; } diff --git a/block/disk-events.c b/block/disk-events.c index aee25a7e1ab7..0cfac464e6d1 100644 --- a/block/disk-events.c +++ b/block/disk-events.c @@ -263,31 +263,31 @@ static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) } /** - * bdev_check_media_change - check if a removable media has been changed - * @bdev: block device to check + * disk_check_media_change - check if a removable media has been changed + * @disk: gendisk to check * * Check whether a removable media has been changed, and attempt to free all * dentries and inodes and invalidates all block device page cache entries in * that case. * - * Returns %true if the block device changed, or %false if not. + * Returns %true if the media has changed, or %false if not. */ -bool bdev_check_media_change(struct block_device *bdev) +bool disk_check_media_change(struct gendisk *disk) { unsigned int events; - events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE | + events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST); if (!(events & DISK_EVENT_MEDIA_CHANGE)) return false; - if (__invalidate_device(bdev, true)) + if (__invalidate_device(disk->part0, true)) pr_warn("VFS: busy inodes on changed media %s\n", - bdev->bd_disk->disk_name); - set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + disk->disk_name); + set_bit(GD_NEED_PART_SCAN, &disk->state); return true; } -EXPORT_SYMBOL(bdev_check_media_change); +EXPORT_SYMBOL(disk_check_media_change); /** * disk_force_media_change - force a media change event @@ -307,6 +307,7 @@ bool disk_force_media_change(struct gendisk *disk, unsigned int events) if (!(events & DISK_EVENT_MEDIA_CHANGE)) return false; + inc_diskseq(disk); if (__invalidate_device(disk->part0, true)) pr_warn("VFS: busy inodes on changed media %s\n", disk->disk_name); diff --git a/block/early-lookup.c b/block/early-lookup.c new file mode 100644 index 000000000000..3effbd0d35e9 --- /dev/null +++ b/block/early-lookup.c @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Code for looking up block devices in the early boot code before mounting the + * root file system. + */ +#include <linux/blkdev.h> +#include <linux/ctype.h> + +struct uuidcmp { + const char *uuid; + int len; +}; + +/** + * match_dev_by_uuid - callback for finding a partition using its uuid + * @dev: device passed in by the caller + * @data: opaque pointer to the desired struct uuidcmp to match + * + * Returns 1 if the device matches, and 0 otherwise. + */ +static int __init match_dev_by_uuid(struct device *dev, const void *data) +{ + struct block_device *bdev = dev_to_bdev(dev); + const struct uuidcmp *cmp = data; + + if (!bdev->bd_meta_info || + strncasecmp(cmp->uuid, bdev->bd_meta_info->uuid, cmp->len)) + return 0; + return 1; +} + +/** + * devt_from_partuuid - looks up the dev_t of a partition by its UUID + * @uuid_str: char array containing ascii UUID + * @devt: dev_t result + * + * The function will return the first partition which contains a matching + * UUID value in its partition_meta_info struct. This does not search + * by filesystem UUIDs. + * + * If @uuid_str is followed by a "/PARTNROFF=%d", then the number will be + * extracted and used as an offset from the partition identified by the UUID. + * + * Returns 0 on success or a negative error code on failure. + */ +static int __init devt_from_partuuid(const char *uuid_str, dev_t *devt) +{ + struct uuidcmp cmp; + struct device *dev = NULL; + int offset = 0; + char *slash; + + cmp.uuid = uuid_str; + + slash = strchr(uuid_str, '/'); + /* Check for optional partition number offset attributes. */ + if (slash) { + char c = 0; + + /* Explicitly fail on poor PARTUUID syntax. */ + if (sscanf(slash + 1, "PARTNROFF=%d%c", &offset, &c) != 1) + goto out_invalid; + cmp.len = slash - uuid_str; + } else { + cmp.len = strlen(uuid_str); + } + + if (!cmp.len) + goto out_invalid; + + dev = class_find_device(&block_class, NULL, &cmp, &match_dev_by_uuid); + if (!dev) + return -ENODEV; + + if (offset) { + /* + * Attempt to find the requested partition by adding an offset + * to the partition number found by UUID. + */ + *devt = part_devt(dev_to_disk(dev), + dev_to_bdev(dev)->bd_partno + offset); + } else { + *devt = dev->devt; + } + + put_device(dev); + return 0; + +out_invalid: + pr_err("VFS: PARTUUID= is invalid.\n" + "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n"); + return -EINVAL; +} + +/** + * match_dev_by_label - callback for finding a partition using its label + * @dev: device passed in by the caller + * @data: opaque pointer to the label to match + * + * Returns 1 if the device matches, and 0 otherwise. + */ +static int __init match_dev_by_label(struct device *dev, const void *data) +{ + struct block_device *bdev = dev_to_bdev(dev); + const char *label = data; + + if (!bdev->bd_meta_info || strcmp(label, bdev->bd_meta_info->volname)) + return 0; + return 1; +} + +static int __init devt_from_partlabel(const char *label, dev_t *devt) +{ + struct device *dev; + + dev = class_find_device(&block_class, NULL, label, &match_dev_by_label); + if (!dev) + return -ENODEV; + *devt = dev->devt; + put_device(dev); + return 0; +} + +static dev_t __init blk_lookup_devt(const char *name, int partno) +{ + dev_t devt = MKDEV(0, 0); + struct class_dev_iter iter; + struct device *dev; + + class_dev_iter_init(&iter, &block_class, NULL, &disk_type); + while ((dev = class_dev_iter_next(&iter))) { + struct gendisk *disk = dev_to_disk(dev); + + if (strcmp(dev_name(dev), name)) + continue; + + if (partno < disk->minors) { + /* We need to return the right devno, even + * if the partition doesn't exist yet. + */ + devt = MKDEV(MAJOR(dev->devt), + MINOR(dev->devt) + partno); + } else { + devt = part_devt(disk, partno); + if (devt) + break; + } + } + class_dev_iter_exit(&iter); + return devt; +} + +static int __init devt_from_devname(const char *name, dev_t *devt) +{ + int part; + char s[32]; + char *p; + + if (strlen(name) > 31) + return -EINVAL; + strcpy(s, name); + for (p = s; *p; p++) { + if (*p == '/') + *p = '!'; + } + + *devt = blk_lookup_devt(s, 0); + if (*devt) + return 0; + + /* + * Try non-existent, but valid partition, which may only exist after + * opening the device, like partitioned md devices. + */ + while (p > s && isdigit(p[-1])) + p--; + if (p == s || !*p || *p == '0') + return -ENODEV; + + /* try disk name without <part number> */ + part = simple_strtoul(p, NULL, 10); + *p = '\0'; + *devt = blk_lookup_devt(s, part); + if (*devt) + return 0; + + /* try disk name without p<part number> */ + if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p') + return -ENODEV; + p[-1] = '\0'; + *devt = blk_lookup_devt(s, part); + if (*devt) + return 0; + return -ENODEV; +} + +static int __init devt_from_devnum(const char *name, dev_t *devt) +{ + unsigned maj, min, offset; + char *p, dummy; + + if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 || + sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) { + *devt = MKDEV(maj, min); + if (maj != MAJOR(*devt) || min != MINOR(*devt)) + return -EINVAL; + } else { + *devt = new_decode_dev(simple_strtoul(name, &p, 16)); + if (*p) + return -EINVAL; + } + + return 0; +} + +/* + * Convert a name into device number. We accept the following variants: + * + * 1) <hex_major><hex_minor> device number in hexadecimal represents itself + * no leading 0x, for example b302. + * 3) /dev/<disk_name> represents the device number of disk + * 4) /dev/<disk_name><decimal> represents the device number + * of partition - device number of disk plus the partition number + * 5) /dev/<disk_name>p<decimal> - same as the above, that form is + * used when disk name of partitioned disk ends on a digit. + * 6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the + * unique id of a partition if the partition table provides it. + * The UUID may be either an EFI/GPT UUID, or refer to an MSDOS + * partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero- + * filled hex representation of the 32-bit "NT disk signature", and PP + * is a zero-filled hex representation of the 1-based partition number. + * 7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to + * a partition with a known unique id. + * 8) <major>:<minor> major and minor number of the device separated by + * a colon. + * 9) PARTLABEL=<name> with name being the GPT partition label. + * MSDOS partitions do not support labels! + * + * If name doesn't have fall into the categories above, we return (0,0). + * block_class is used to check if something is a disk name. If the disk + * name contains slashes, the device name has them replaced with + * bangs. + */ +int __init early_lookup_bdev(const char *name, dev_t *devt) +{ + if (strncmp(name, "PARTUUID=", 9) == 0) + return devt_from_partuuid(name + 9, devt); + if (strncmp(name, "PARTLABEL=", 10) == 0) + return devt_from_partlabel(name + 10, devt); + if (strncmp(name, "/dev/", 5) == 0) + return devt_from_devname(name + 5, devt); + return devt_from_devnum(name, devt); +} + +static char __init *bdevt_str(dev_t devt, char *buf) +{ + if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) { + char tbuf[BDEVT_SIZE]; + snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt)); + snprintf(buf, BDEVT_SIZE, "%-9s", tbuf); + } else + snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt)); + + return buf; +} + +/* + * print a full list of all partitions - intended for places where the root + * filesystem can't be mounted and thus to give the victim some idea of what + * went wrong + */ +void __init printk_all_partitions(void) +{ + struct class_dev_iter iter; + struct device *dev; + + class_dev_iter_init(&iter, &block_class, NULL, &disk_type); + while ((dev = class_dev_iter_next(&iter))) { + struct gendisk *disk = dev_to_disk(dev); + struct block_device *part; + char devt_buf[BDEVT_SIZE]; + unsigned long idx; + + /* + * Don't show empty devices or things that have been + * suppressed + */ + if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN)) + continue; + + /* + * Note, unlike /proc/partitions, I am showing the numbers in + * hex - the same format as the root= option takes. + */ + rcu_read_lock(); + xa_for_each(&disk->part_tbl, idx, part) { + if (!bdev_nr_sectors(part)) + continue; + printk("%s%s %10llu %pg %s", + bdev_is_partition(part) ? " " : "", + bdevt_str(part->bd_dev, devt_buf), + bdev_nr_sectors(part) >> 1, part, + part->bd_meta_info ? + part->bd_meta_info->uuid : ""); + if (bdev_is_partition(part)) + printk("\n"); + else if (dev->parent && dev->parent->driver) + printk(" driver: %s\n", + dev->parent->driver->name); + else + printk(" (driver?)\n"); + } + rcu_read_unlock(); + } + class_dev_iter_exit(&iter); +} diff --git a/block/elevator.c b/block/elevator.c index 24909069f872..8400e303fbcb 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -751,7 +751,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *buf, if (!elv_support_iosched(q)) return count; - strlcpy(elevator_name, buf, sizeof(elevator_name)); + strscpy(elevator_name, buf, sizeof(elevator_name)); ret = elevator_change(q, strstrip(elevator_name)); if (!ret) return count; diff --git a/block/fops.c b/block/fops.c index 4faeada05b23..555b1b9ecd2c 100644 --- a/block/fops.c +++ b/block/fops.c @@ -54,7 +54,7 @@ static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos, static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, unsigned int nr_pages) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs; loff_t pos = iocb->ki_pos; bool should_dirty = false; @@ -170,7 +170,7 @@ static void blkdev_bio_end_io(struct bio *bio) static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, unsigned int nr_pages) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); struct blk_plug plug; struct blkdev_dio *dio; struct bio *bio; @@ -310,7 +310,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, struct iov_iter *iter, unsigned int nr_pages) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); bool is_read = iov_iter_rw(iter) == READ; blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb); struct blkdev_dio *dio; @@ -451,7 +451,7 @@ static loff_t blkdev_llseek(struct file *file, loff_t offset, int whence) static int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { - struct block_device *bdev = filp->private_data; + struct block_device *bdev = I_BDEV(filp->f_mapping->host); int error; error = file_write_and_wait_range(filp, start, end); @@ -470,6 +470,30 @@ static int blkdev_fsync(struct file *filp, loff_t start, loff_t end, return error; } +blk_mode_t file_to_blk_mode(struct file *file) +{ + blk_mode_t mode = 0; + + if (file->f_mode & FMODE_READ) + mode |= BLK_OPEN_READ; + if (file->f_mode & FMODE_WRITE) + mode |= BLK_OPEN_WRITE; + if (file->private_data) + mode |= BLK_OPEN_EXCL; + if (file->f_flags & O_NDELAY) + mode |= BLK_OPEN_NDELAY; + + /* + * If all bits in O_ACCMODE set (aka O_RDWR | O_WRONLY), the floppy + * driver has historically allowed ioctls as if the file was opened for + * writing, but does not allow and actual reads or writes. + */ + if ((file->f_flags & O_ACCMODE) == (O_RDWR | O_WRONLY)) + mode |= BLK_OPEN_WRITE_IOCTL; + + return mode; +} + static int blkdev_open(struct inode *inode, struct file *filp) { struct block_device *bdev; @@ -483,31 +507,29 @@ static int blkdev_open(struct inode *inode, struct file *filp) filp->f_flags |= O_LARGEFILE; filp->f_mode |= FMODE_BUF_RASYNC; - if (filp->f_flags & O_NDELAY) - filp->f_mode |= FMODE_NDELAY; + /* + * Use the file private data to store the holder for exclusive openes. + * file_to_blk_mode relies on it being present to set BLK_OPEN_EXCL. + */ if (filp->f_flags & O_EXCL) - filp->f_mode |= FMODE_EXCL; - if ((filp->f_flags & O_ACCMODE) == 3) - filp->f_mode |= FMODE_WRITE_IOCTL; + filp->private_data = filp; - bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp); + bdev = blkdev_get_by_dev(inode->i_rdev, file_to_blk_mode(filp), + filp->private_data, NULL); if (IS_ERR(bdev)) return PTR_ERR(bdev); if (bdev_nowait(bdev)) filp->f_mode |= FMODE_NOWAIT; - filp->private_data = bdev; filp->f_mapping = bdev->bd_inode->i_mapping; filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); return 0; } -static int blkdev_close(struct inode *inode, struct file *filp) +static int blkdev_release(struct inode *inode, struct file *filp) { - struct block_device *bdev = filp->private_data; - - blkdev_put(bdev, filp->f_mode); + blkdev_put(I_BDEV(filp->f_mapping->host), filp->private_data); return 0; } @@ -520,10 +542,9 @@ static int blkdev_close(struct inode *inode, struct file *filp) */ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); struct inode *bd_inode = bdev->bd_inode; loff_t size = bdev_nr_bytes(bdev); - struct blk_plug plug; size_t shorted = 0; ssize_t ret; @@ -548,18 +569,16 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) iov_iter_truncate(from, size); } - blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); if (ret > 0) ret = generic_write_sync(iocb, ret); iov_iter_reexpand(from, iov_iter_count(from) + shorted); - blk_finish_plug(&plug); return ret; } static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct block_device *bdev = iocb->ki_filp->private_data; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); loff_t size = bdev_nr_bytes(bdev); loff_t pos = iocb->ki_pos; size_t shorted = 0; @@ -652,7 +671,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, filemap_invalidate_lock(inode->i_mapping); /* Invalidate the page cache, including dirty pages. */ - error = truncate_bdev_range(bdev, file->f_mode, start, end); + error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end); if (error) goto fail; @@ -693,7 +712,7 @@ static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) const struct file_operations def_blk_fops = { .open = blkdev_open, - .release = blkdev_close, + .release = blkdev_release, .llseek = blkdev_llseek, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, diff --git a/block/genhd.c b/block/genhd.c index 1cb489b927d5..3d287b32d50d 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -25,8 +25,9 @@ #include <linux/pm_runtime.h> #include <linux/badblocks.h> #include <linux/part_stat.h> -#include "blk-throttle.h" +#include <linux/blktrace_api.h> +#include "blk-throttle.h" #include "blk.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" @@ -253,7 +254,7 @@ int __register_blkdev(unsigned int major, const char *name, #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD p->probe = probe; #endif - strlcpy(p->name, name, sizeof(p->name)); + strscpy(p->name, name, sizeof(p->name)); p->next = NULL; index = major_to_index(major); @@ -318,18 +319,6 @@ void blk_free_ext_minor(unsigned int minor) ida_free(&ext_devt_ida, minor); } -static char *bdevt_str(dev_t devt, char *buf) -{ - if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) { - char tbuf[BDEVT_SIZE]; - snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt)); - snprintf(buf, BDEVT_SIZE, "%-9s", tbuf); - } else - snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt)); - - return buf; -} - void disk_uevent(struct gendisk *disk, enum kobject_action action) { struct block_device *part; @@ -351,7 +340,7 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action) } EXPORT_SYMBOL_GPL(disk_uevent); -int disk_scan_partitions(struct gendisk *disk, fmode_t mode) +int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode) { struct block_device *bdev; int ret = 0; @@ -369,18 +358,20 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode) * synchronize with other exclusive openers and other partition * scanners. */ - if (!(mode & FMODE_EXCL)) { - ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions); + if (!(mode & BLK_OPEN_EXCL)) { + ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions, + NULL); if (ret) return ret; } set_bit(GD_NEED_PART_SCAN, &disk->state); - bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL); + bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL, NULL, + NULL); if (IS_ERR(bdev)) ret = PTR_ERR(bdev); else - blkdev_put(bdev, mode & ~FMODE_EXCL); + blkdev_put(bdev, NULL); /* * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set, @@ -388,7 +379,7 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode) * creat partition for underlying disk. */ clear_bit(GD_NEED_PART_SCAN, &disk->state); - if (!(mode & FMODE_EXCL)) + if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(disk->part0, disk_scan_partitions); return ret; } @@ -516,7 +507,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, bdev_add(disk->part0, ddev->devt); if (get_capacity(disk)) - disk_scan_partitions(disk, FMODE_READ); + disk_scan_partitions(disk, BLK_OPEN_READ); /* * Announce the disk and partitions after all partitions are @@ -563,6 +554,28 @@ out_exit_elevator: } EXPORT_SYMBOL(device_add_disk); +static void blk_report_disk_dead(struct gendisk *disk) +{ + struct block_device *bdev; + unsigned long idx; + + rcu_read_lock(); + xa_for_each(&disk->part_tbl, idx, bdev) { + if (!kobject_get_unless_zero(&bdev->bd_device.kobj)) + continue; + rcu_read_unlock(); + + mutex_lock(&bdev->bd_holder_lock); + if (bdev->bd_holder_ops && bdev->bd_holder_ops->mark_dead) + bdev->bd_holder_ops->mark_dead(bdev); + mutex_unlock(&bdev->bd_holder_lock); + + put_device(&bdev->bd_device); + rcu_read_lock(); + } + rcu_read_unlock(); +} + /** * blk_mark_disk_dead - mark a disk as dead * @disk: disk to mark as dead @@ -572,13 +585,26 @@ EXPORT_SYMBOL(device_add_disk); */ void blk_mark_disk_dead(struct gendisk *disk) { - set_bit(GD_DEAD, &disk->state); - blk_queue_start_drain(disk->queue); + /* + * Fail any new I/O. + */ + if (test_and_set_bit(GD_DEAD, &disk->state)) + return; + + if (test_bit(GD_OWNS_QUEUE, &disk->state)) + blk_queue_flag_set(QUEUE_FLAG_DYING, disk->queue); /* * Stop buffered writers from dirtying pages that can't be written out. */ - set_capacity_and_notify(disk, 0); + set_capacity(disk, 0); + + /* + * Prevent new I/O from crossing bio_queue_enter(). + */ + blk_queue_start_drain(disk->queue); + + blk_report_disk_dead(disk); } EXPORT_SYMBOL_GPL(blk_mark_disk_dead); @@ -604,6 +630,8 @@ EXPORT_SYMBOL_GPL(blk_mark_disk_dead); void del_gendisk(struct gendisk *disk) { struct request_queue *q = disk->queue; + struct block_device *part; + unsigned long idx; might_sleep(); @@ -612,26 +640,27 @@ void del_gendisk(struct gendisk *disk) disk_del_events(disk); + /* + * Prevent new openers by unlinked the bdev inode, and write out + * dirty data before marking the disk dead and stopping all I/O. + */ mutex_lock(&disk->open_mutex); - remove_inode_hash(disk->part0->bd_inode); - blk_drop_partitions(disk); + xa_for_each(&disk->part_tbl, idx, part) { + remove_inode_hash(part->bd_inode); + fsync_bdev(part); + __invalidate_device(part, true); + } mutex_unlock(&disk->open_mutex); - fsync_bdev(disk->part0); - __invalidate_device(disk->part0, true); + blk_mark_disk_dead(disk); /* - * Fail any new I/O. + * Drop all partitions now that the disk is marked dead. */ - set_bit(GD_DEAD, &disk->state); - if (test_bit(GD_OWNS_QUEUE, &disk->state)) - blk_queue_flag_set(QUEUE_FLAG_DYING, q); - set_capacity(disk, 0); - - /* - * Prevent new I/O from crossing bio_queue_enter(). - */ - blk_queue_start_drain(q); + mutex_lock(&disk->open_mutex); + xa_for_each_start(&disk->part_tbl, idx, part, 1) + drop_partition(part); + mutex_unlock(&disk->open_mutex); if (!(disk->flags & GENHD_FL_HIDDEN)) { sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); @@ -755,57 +784,6 @@ void blk_request_module(dev_t devt) } #endif /* CONFIG_BLOCK_LEGACY_AUTOLOAD */ -/* - * print a full list of all partitions - intended for places where the root - * filesystem can't be mounted and thus to give the victim some idea of what - * went wrong - */ -void __init printk_all_partitions(void) -{ - struct class_dev_iter iter; - struct device *dev; - - class_dev_iter_init(&iter, &block_class, NULL, &disk_type); - while ((dev = class_dev_iter_next(&iter))) { - struct gendisk *disk = dev_to_disk(dev); - struct block_device *part; - char devt_buf[BDEVT_SIZE]; - unsigned long idx; - - /* - * Don't show empty devices or things that have been - * suppressed - */ - if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN)) - continue; - - /* - * Note, unlike /proc/partitions, I am showing the numbers in - * hex - the same format as the root= option takes. - */ - rcu_read_lock(); - xa_for_each(&disk->part_tbl, idx, part) { - if (!bdev_nr_sectors(part)) - continue; - printk("%s%s %10llu %pg %s", - bdev_is_partition(part) ? " " : "", - bdevt_str(part->bd_dev, devt_buf), - bdev_nr_sectors(part) >> 1, part, - part->bd_meta_info ? - part->bd_meta_info->uuid : ""); - if (bdev_is_partition(part)) - printk("\n"); - else if (dev->parent && dev->parent->driver) - printk(" driver: %s\n", - dev->parent->driver->name); - else - printk(" (driver?)\n"); - } - rcu_read_unlock(); - } - class_dev_iter_exit(&iter); -} - #ifdef CONFIG_PROC_FS /* iterator */ static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos) @@ -1171,6 +1149,8 @@ static void disk_release(struct device *dev) might_sleep(); WARN_ON_ONCE(disk_live(disk)); + blk_trace_remove(disk->queue); + /* * To undo the all initialization from blk_mq_init_allocated_queue in * case of a probe failure where add_disk is never called we have to @@ -1339,35 +1319,6 @@ dev_t part_devt(struct gendisk *disk, u8 partno) return devt; } -dev_t blk_lookup_devt(const char *name, int partno) -{ - dev_t devt = MKDEV(0, 0); - struct class_dev_iter iter; - struct device *dev; - - class_dev_iter_init(&iter, &block_class, NULL, &disk_type); - while ((dev = class_dev_iter_next(&iter))) { - struct gendisk *disk = dev_to_disk(dev); - - if (strcmp(dev_name(dev), name)) - continue; - - if (partno < disk->minors) { - /* We need to return the right devno, even - * if the partition doesn't exist yet. - */ - devt = MKDEV(MAJOR(dev->devt), - MINOR(dev->devt) + partno); - } else { - devt = part_devt(disk, partno); - if (devt) - break; - } - } - class_dev_iter_exit(&iter); - return devt; -} - struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, struct lock_class_key *lkclass) { diff --git a/block/ioctl.c b/block/ioctl.c index 9c5f637ff153..3be11941fb2d 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -82,7 +82,7 @@ static int compat_blkpg_ioctl(struct block_device *bdev, } #endif -static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, +static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { uint64_t range[2]; @@ -90,7 +90,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, struct inode *inode = bdev->bd_inode; int err; - if (!(mode & FMODE_WRITE)) + if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (!bdev_max_discard_sectors(bdev)) @@ -120,14 +120,14 @@ fail: return err; } -static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode, +static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode, void __user *argp) { uint64_t start, len; uint64_t range[2]; int err; - if (!(mode & FMODE_WRITE)) + if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (!bdev_max_secure_erase_sectors(bdev)) return -EOPNOTSUPP; @@ -151,7 +151,7 @@ static int blk_ioctl_secure_erase(struct block_device *bdev, fmode_t mode, } -static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, +static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, unsigned long arg) { uint64_t range[2]; @@ -159,7 +159,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, struct inode *inode = bdev->bd_inode; int err; - if (!(mode & FMODE_WRITE)) + if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (copy_from_user(range, (void __user *)arg, sizeof(range))) @@ -240,7 +240,7 @@ static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val) * drivers that implement only commands that are completely compatible * between 32-bit and 64-bit user space */ -int blkdev_compat_ptr_ioctl(struct block_device *bdev, fmode_t mode, +int blkdev_compat_ptr_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; @@ -254,13 +254,28 @@ int blkdev_compat_ptr_ioctl(struct block_device *bdev, fmode_t mode, EXPORT_SYMBOL(blkdev_compat_ptr_ioctl); #endif -static int blkdev_pr_register(struct block_device *bdev, +static bool blkdev_pr_allowed(struct block_device *bdev, blk_mode_t mode) +{ + /* no sense to make reservations for partitions */ + if (bdev_is_partition(bdev)) + return false; + + if (capable(CAP_SYS_ADMIN)) + return true; + /* + * Only allow unprivileged reservations if the file descriptor is open + * for writing. + */ + return mode & BLK_OPEN_WRITE; +} + +static int blkdev_pr_register(struct block_device *bdev, blk_mode_t mode, struct pr_registration __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_registration reg; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_register) return -EOPNOTSUPP; @@ -272,13 +287,13 @@ static int blkdev_pr_register(struct block_device *bdev, return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags); } -static int blkdev_pr_reserve(struct block_device *bdev, +static int blkdev_pr_reserve(struct block_device *bdev, blk_mode_t mode, struct pr_reservation __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_reserve) return -EOPNOTSUPP; @@ -290,13 +305,13 @@ static int blkdev_pr_reserve(struct block_device *bdev, return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags); } -static int blkdev_pr_release(struct block_device *bdev, +static int blkdev_pr_release(struct block_device *bdev, blk_mode_t mode, struct pr_reservation __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_release) return -EOPNOTSUPP; @@ -308,13 +323,13 @@ static int blkdev_pr_release(struct block_device *bdev, return ops->pr_release(bdev, rsv.key, rsv.type); } -static int blkdev_pr_preempt(struct block_device *bdev, +static int blkdev_pr_preempt(struct block_device *bdev, blk_mode_t mode, struct pr_preempt __user *arg, bool abort) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_preempt p; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_preempt) return -EOPNOTSUPP; @@ -326,13 +341,13 @@ static int blkdev_pr_preempt(struct block_device *bdev, return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort); } -static int blkdev_pr_clear(struct block_device *bdev, +static int blkdev_pr_clear(struct block_device *bdev, blk_mode_t mode, struct pr_clear __user *arg) { const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_clear c; - if (!capable(CAP_SYS_ADMIN)) + if (!blkdev_pr_allowed(bdev, mode)) return -EPERM; if (!ops || !ops->pr_clear) return -EOPNOTSUPP; @@ -344,8 +359,8 @@ static int blkdev_pr_clear(struct block_device *bdev, return ops->pr_clear(bdev, c.key); } -static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, - unsigned cmd, unsigned long arg) +static int blkdev_flushbuf(struct block_device *bdev, unsigned cmd, + unsigned long arg) { if (!capable(CAP_SYS_ADMIN)) return -EACCES; @@ -354,8 +369,8 @@ static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, return 0; } -static int blkdev_roset(struct block_device *bdev, fmode_t mode, - unsigned cmd, unsigned long arg) +static int blkdev_roset(struct block_device *bdev, unsigned cmd, + unsigned long arg) { int ret, n; @@ -439,7 +454,7 @@ static int compat_hdio_getgeo(struct block_device *bdev, #endif /* set the logical block size */ -static int blkdev_bszset(struct block_device *bdev, fmode_t mode, +static int blkdev_bszset(struct block_device *bdev, blk_mode_t mode, int __user *argp) { int ret, n; @@ -451,13 +466,13 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode, if (get_user(n, argp)) return -EFAULT; - if (mode & FMODE_EXCL) + if (mode & BLK_OPEN_EXCL) return set_blocksize(bdev, n); - if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode | FMODE_EXCL, &bdev))) + if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode, &bdev, NULL))) return -EBUSY; ret = set_blocksize(bdev, n); - blkdev_put(bdev, mode | FMODE_EXCL); + blkdev_put(bdev, &bdev); return ret; } @@ -467,7 +482,7 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode, * user space. Note the separate arg/argp parameters that are needed * to deal with the compat_ptr() conversion. */ -static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, +static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg, void __user *argp) { @@ -475,9 +490,9 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, switch (cmd) { case BLKFLSBUF: - return blkdev_flushbuf(bdev, mode, cmd, arg); + return blkdev_flushbuf(bdev, cmd, arg); case BLKROSET: - return blkdev_roset(bdev, mode, cmd, arg); + return blkdev_roset(bdev, cmd, arg); case BLKDISCARD: return blk_ioctl_discard(bdev, mode, arg); case BLKSECDISCARD: @@ -487,7 +502,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, case BLKGETDISKSEQ: return put_u64(argp, bdev->bd_disk->diskseq); case BLKREPORTZONE: - return blkdev_report_zones_ioctl(bdev, mode, cmd, arg); + return blkdev_report_zones_ioctl(bdev, cmd, arg); case BLKRESETZONE: case BLKOPENZONE: case BLKCLOSEZONE: @@ -534,17 +549,17 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); case IOC_PR_REGISTER: - return blkdev_pr_register(bdev, argp); + return blkdev_pr_register(bdev, mode, argp); case IOC_PR_RESERVE: - return blkdev_pr_reserve(bdev, argp); + return blkdev_pr_reserve(bdev, mode, argp); case IOC_PR_RELEASE: - return blkdev_pr_release(bdev, argp); + return blkdev_pr_release(bdev, mode, argp); case IOC_PR_PREEMPT: - return blkdev_pr_preempt(bdev, argp, false); + return blkdev_pr_preempt(bdev, mode, argp, false); case IOC_PR_PREEMPT_ABORT: - return blkdev_pr_preempt(bdev, argp, true); + return blkdev_pr_preempt(bdev, mode, argp, true); case IOC_PR_CLEAR: - return blkdev_pr_clear(bdev, argp); + return blkdev_pr_clear(bdev, mode, argp); default: return -ENOIOCTLCMD; } @@ -560,18 +575,9 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct block_device *bdev = I_BDEV(file->f_mapping->host); void __user *argp = (void __user *)arg; - fmode_t mode = file->f_mode; + blk_mode_t mode = file_to_blk_mode(file); int ret; - /* - * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have - * to updated it before every ioctl. - */ - if (file->f_flags & O_NDELAY) - mode |= FMODE_NDELAY; - else - mode &= ~FMODE_NDELAY; - switch (cmd) { /* These need separate implementations for the data structure */ case HDIO_GETGEO: @@ -630,16 +636,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) void __user *argp = compat_ptr(arg); struct block_device *bdev = I_BDEV(file->f_mapping->host); struct gendisk *disk = bdev->bd_disk; - fmode_t mode = file->f_mode; - - /* - * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have - * to updated it before every ioctl. - */ - if (file->f_flags & O_NDELAY) - mode |= FMODE_NDELAY; - else - mode &= ~FMODE_NDELAY; + blk_mode_t mode = file_to_blk_mode(file); switch (cmd) { /* These need separate implementations for the data structure */ diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 5839a027e0f0..6aa5daf7ae32 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -74,8 +74,8 @@ struct dd_per_prio { struct list_head dispatch; struct rb_root sort_list[DD_DIR_COUNT]; struct list_head fifo_list[DD_DIR_COUNT]; - /* Next request in FIFO order. Read, write or both are NULL. */ - struct request *next_rq[DD_DIR_COUNT]; + /* Position of the most recently dispatched request. */ + sector_t latest_pos[DD_DIR_COUNT]; struct io_stats_per_prio stats; }; @@ -156,6 +156,40 @@ deadline_latter_request(struct request *rq) return NULL; } +/* + * Return the first request for which blk_rq_pos() >= @pos. For zoned devices, + * return the first request after the start of the zone containing @pos. + */ +static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio, + enum dd_data_dir data_dir, sector_t pos) +{ + struct rb_node *node = per_prio->sort_list[data_dir].rb_node; + struct request *rq, *res = NULL; + + if (!node) + return NULL; + + rq = rb_entry_rq(node); + /* + * A zoned write may have been requeued with a starting position that + * is below that of the most recently dispatched request. Hence, for + * zoned writes, start searching from the start of a zone. + */ + if (blk_rq_is_seq_zoned_write(rq)) + pos -= round_down(pos, rq->q->limits.chunk_sectors); + + while (node) { + rq = rb_entry_rq(node); + if (blk_rq_pos(rq) >= pos) { + res = rq; + node = node->rb_left; + } else { + node = node->rb_right; + } + } + return res; +} + static void deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq) { @@ -167,11 +201,6 @@ deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq) static inline void deadline_del_rq_rb(struct dd_per_prio *per_prio, struct request *rq) { - const enum dd_data_dir data_dir = rq_data_dir(rq); - - if (per_prio->next_rq[data_dir] == rq) - per_prio->next_rq[data_dir] = deadline_latter_request(rq); - elv_rb_del(deadline_rb_root(per_prio, rq), rq); } @@ -251,10 +280,6 @@ static void deadline_move_request(struct deadline_data *dd, struct dd_per_prio *per_prio, struct request *rq) { - const enum dd_data_dir data_dir = rq_data_dir(rq); - - per_prio->next_rq[data_dir] = deadline_latter_request(rq); - /* * take it off the sort and fifo list */ @@ -272,21 +297,15 @@ static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio) } /* - * deadline_check_fifo returns 0 if there are no expired requests on the fifo, - * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir]) + * deadline_check_fifo returns true if and only if there are expired requests + * in the FIFO list. Requires !list_empty(&dd->fifo_list[data_dir]). */ -static inline int deadline_check_fifo(struct dd_per_prio *per_prio, - enum dd_data_dir data_dir) +static inline bool deadline_check_fifo(struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) { struct request *rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next); - /* - * rq is expired! - */ - if (time_after_eq(jiffies, (unsigned long)rq->fifo_time)) - return 1; - - return 0; + return time_is_before_eq_jiffies((unsigned long)rq->fifo_time); } /* @@ -310,14 +329,11 @@ static struct request *deadline_skip_seq_writes(struct deadline_data *dd, struct request *rq) { sector_t pos = blk_rq_pos(rq); - sector_t skipped_sectors = 0; - while (rq) { - if (blk_rq_pos(rq) != pos + skipped_sectors) - break; - skipped_sectors += blk_rq_sectors(rq); + do { + pos += blk_rq_sectors(rq); rq = deadline_latter_request(rq); - } + } while (rq && blk_rq_pos(rq) == pos); return rq; } @@ -330,7 +346,7 @@ static struct request * deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio, enum dd_data_dir data_dir) { - struct request *rq; + struct request *rq, *rb_rq, *next; unsigned long flags; if (list_empty(&per_prio->fifo_list[data_dir])) @@ -348,7 +364,12 @@ deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio, * zones and these zones are unlocked. */ spin_lock_irqsave(&dd->zone_lock, flags); - list_for_each_entry(rq, &per_prio->fifo_list[DD_WRITE], queuelist) { + list_for_each_entry_safe(rq, next, &per_prio->fifo_list[DD_WRITE], + queuelist) { + /* Check whether a prior request exists for the same zone. */ + rb_rq = deadline_from_pos(per_prio, data_dir, blk_rq_pos(rq)); + if (rb_rq && blk_rq_pos(rb_rq) < blk_rq_pos(rq)) + rq = rb_rq; if (blk_req_can_dispatch_to_zone(rq) && (blk_queue_nonrot(rq->q) || !deadline_is_seq_write(dd, rq))) @@ -372,7 +393,8 @@ deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio, struct request *rq; unsigned long flags; - rq = per_prio->next_rq[data_dir]; + rq = deadline_from_pos(per_prio, data_dir, + per_prio->latest_pos[data_dir]); if (!rq) return NULL; @@ -435,6 +457,7 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd, if (started_after(dd, rq, latest_start)) return NULL; list_del_init(&rq->queuelist); + data_dir = rq_data_dir(rq); goto done; } @@ -442,9 +465,11 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd, * batches are currently reads XOR writes */ rq = deadline_next_request(dd, per_prio, dd->last_dir); - if (rq && dd->batching < dd->fifo_batch) - /* we have a next request are still entitled to batch */ + if (rq && dd->batching < dd->fifo_batch) { + /* we have a next request and are still entitled to batch */ + data_dir = rq_data_dir(rq); goto dispatch_request; + } /* * at this point we are not running a batch. select the appropriate @@ -522,6 +547,7 @@ dispatch_request: done: ioprio_class = dd_rq_ioclass(rq); prio = ioprio_class_to_prio[ioprio_class]; + dd->per_prio[prio].latest_pos[data_dir] = blk_rq_pos(rq); dd->per_prio[prio].stats.dispatched++; /* * If the request needs its target zone locked, do it. @@ -766,7 +792,7 @@ static bool dd_bio_merge(struct request_queue *q, struct bio *bio, * add rq to rbtree and fifo */ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, - blk_insert_t flags) + blk_insert_t flags, struct list_head *free) { struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; @@ -775,7 +801,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio); struct dd_per_prio *per_prio; enum dd_prio prio; - LIST_HEAD(free); lockdep_assert_held(&dd->lock); @@ -792,10 +817,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, rq->elv.priv[0] = (void *)(uintptr_t)1; } - if (blk_mq_sched_try_insert_merge(q, rq, &free)) { - blk_mq_free_requests(&free); + if (blk_mq_sched_try_insert_merge(q, rq, free)) return; - } trace_block_rq_insert(rq); @@ -803,6 +826,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, list_add(&rq->queuelist, &per_prio->dispatch); rq->fifo_time = jiffies; } else { + struct list_head *insert_before; + deadline_add_rq_rb(per_prio, rq); if (rq_mergeable(rq)) { @@ -815,7 +840,20 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, * set expire time and add to fifo list */ rq->fifo_time = jiffies + dd->fifo_expire[data_dir]; - list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]); + insert_before = &per_prio->fifo_list[data_dir]; +#ifdef CONFIG_BLK_DEV_ZONED + /* + * Insert zoned writes such that requests are sorted by + * position per zone. + */ + if (blk_rq_is_seq_zoned_write(rq)) { + struct request *rq2 = deadline_latter_request(rq); + + if (rq2 && blk_rq_zone_no(rq2) == blk_rq_zone_no(rq)) + insert_before = &rq2->queuelist; + } +#endif + list_add_tail(&rq->queuelist, insert_before); } } @@ -828,6 +866,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, { struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; + LIST_HEAD(free); spin_lock(&dd->lock); while (!list_empty(list)) { @@ -835,9 +874,11 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); - dd_insert_request(hctx, rq, flags); + dd_insert_request(hctx, rq, flags, &free); } spin_unlock(&dd->lock); + + blk_mq_free_requests(&free); } /* Callback from inside blk_mq_rq_ctx_init(). */ @@ -1035,8 +1076,10 @@ static int deadline_##name##_next_rq_show(void *data, \ struct request_queue *q = data; \ struct deadline_data *dd = q->elevator->elevator_data; \ struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ - struct request *rq = per_prio->next_rq[data_dir]; \ + struct request *rq; \ \ + rq = deadline_from_pos(per_prio, data_dir, \ + per_prio->latest_pos[data_dir]); \ if (rq) \ __blk_mq_debugfs_rq_show(m, rq); \ return 0; \ diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c index 5c8624e26a54..ed222b9c901b 100644 --- a/block/partitions/amiga.c +++ b/block/partitions/amiga.c @@ -11,10 +11,18 @@ #define pr_fmt(fmt) fmt #include <linux/types.h> +#include <linux/mm_types.h> +#include <linux/overflow.h> #include <linux/affs_hardblocks.h> #include "check.h" +/* magic offsets in partition DosEnvVec */ +#define NR_HD 3 +#define NR_SECT 5 +#define LO_CYL 9 +#define HI_CYL 10 + static __inline__ u32 checksum_block(__be32 *m, int size) { @@ -31,8 +39,12 @@ int amiga_partition(struct parsed_partitions *state) unsigned char *data; struct RigidDiskBlock *rdb; struct PartitionBlock *pb; - int start_sect, nr_sects, blk, part, res = 0; - int blksize = 1; /* Multiplier for disk block size */ + u64 start_sect, nr_sects; + sector_t blk, end_sect; + u32 cylblk; /* rdb_CylBlocks = nr_heads*sect_per_track */ + u32 nr_hd, nr_sect, lo_cyl, hi_cyl; + int part, res = 0; + unsigned int blksize = 1; /* Multiplier for disk block size */ int slot = 1; for (blk = 0; ; blk++, put_dev_sector(sect)) { @@ -40,7 +52,7 @@ int amiga_partition(struct parsed_partitions *state) goto rdb_done; data = read_part_sector(state, blk, §); if (!data) { - pr_err("Dev %s: unable to read RDB block %d\n", + pr_err("Dev %s: unable to read RDB block %llu\n", state->disk->disk_name, blk); res = -1; goto rdb_done; @@ -57,12 +69,12 @@ int amiga_partition(struct parsed_partitions *state) *(__be32 *)(data+0xdc) = 0; if (checksum_block((__be32 *)data, be32_to_cpu(rdb->rdb_SummedLongs) & 0x7F)==0) { - pr_err("Trashed word at 0xd0 in block %d ignored in checksum calculation\n", + pr_err("Trashed word at 0xd0 in block %llu ignored in checksum calculation\n", blk); break; } - pr_err("Dev %s: RDB in block %d has bad checksum\n", + pr_err("Dev %s: RDB in block %llu has bad checksum\n", state->disk->disk_name, blk); } @@ -79,10 +91,15 @@ int amiga_partition(struct parsed_partitions *state) blk = be32_to_cpu(rdb->rdb_PartitionList); put_dev_sector(sect); for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) { - blk *= blksize; /* Read in terms partition table understands */ + /* Read in terms partition table understands */ + if (check_mul_overflow(blk, (sector_t) blksize, &blk)) { + pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n", + state->disk->disk_name, blk, part); + break; + } data = read_part_sector(state, blk, §); if (!data) { - pr_err("Dev %s: unable to read partition block %d\n", + pr_err("Dev %s: unable to read partition block %llu\n", state->disk->disk_name, blk); res = -1; goto rdb_done; @@ -94,19 +111,70 @@ int amiga_partition(struct parsed_partitions *state) if (checksum_block((__be32 *)pb, be32_to_cpu(pb->pb_SummedLongs) & 0x7F) != 0 ) continue; - /* Tell Kernel about it */ + /* RDB gives us more than enough rope to hang ourselves with, + * many times over (2^128 bytes if all fields max out). + * Some careful checks are in order, so check for potential + * overflows. + * We are multiplying four 32 bit numbers to one sector_t! + */ + + nr_hd = be32_to_cpu(pb->pb_Environment[NR_HD]); + nr_sect = be32_to_cpu(pb->pb_Environment[NR_SECT]); + + /* CylBlocks is total number of blocks per cylinder */ + if (check_mul_overflow(nr_hd, nr_sect, &cylblk)) { + pr_err("Dev %s: heads*sects %u overflows u32, skipping partition!\n", + state->disk->disk_name, cylblk); + continue; + } + + /* check for consistency with RDB defined CylBlocks */ + if (cylblk > be32_to_cpu(rdb->rdb_CylBlocks)) { + pr_warn("Dev %s: cylblk %u > rdb_CylBlocks %u!\n", + state->disk->disk_name, cylblk, + be32_to_cpu(rdb->rdb_CylBlocks)); + } + + /* RDB allows for variable logical block size - + * normalize to 512 byte blocks and check result. + */ + + if (check_mul_overflow(cylblk, blksize, &cylblk)) { + pr_err("Dev %s: partition %u bytes per cyl. overflows u32, skipping partition!\n", + state->disk->disk_name, part); + continue; + } + + /* Calculate partition start and end. Limit of 32 bit on cylblk + * guarantees no overflow occurs if LBD support is enabled. + */ + + lo_cyl = be32_to_cpu(pb->pb_Environment[LO_CYL]); + start_sect = ((u64) lo_cyl * cylblk); + + hi_cyl = be32_to_cpu(pb->pb_Environment[HI_CYL]); + nr_sects = (((u64) hi_cyl - lo_cyl + 1) * cylblk); - nr_sects = (be32_to_cpu(pb->pb_Environment[10]) + 1 - - be32_to_cpu(pb->pb_Environment[9])) * - be32_to_cpu(pb->pb_Environment[3]) * - be32_to_cpu(pb->pb_Environment[5]) * - blksize; if (!nr_sects) continue; - start_sect = be32_to_cpu(pb->pb_Environment[9]) * - be32_to_cpu(pb->pb_Environment[3]) * - be32_to_cpu(pb->pb_Environment[5]) * - blksize; + + /* Warn user if partition end overflows u32 (AmigaDOS limit) */ + + if ((start_sect + nr_sects) > UINT_MAX) { + pr_warn("Dev %s: partition %u (%llu-%llu) needs 64 bit device support!\n", + state->disk->disk_name, part, + start_sect, start_sect + nr_sects); + } + + if (check_add_overflow(start_sect, nr_sects, &end_sect)) { + pr_err("Dev %s: partition %u (%llu-%llu) needs LBD device support, skipping partition!\n", + state->disk->disk_name, part, + start_sect, end_sect); + continue; + } + + /* Tell Kernel about it */ + put_partition(state,slot++,start_sect,nr_sects); { /* Be even more informative to aid mounting */ diff --git a/block/partitions/core.c b/block/partitions/core.c index 49e0496ff23c..13a7341299a9 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -12,7 +12,7 @@ #include <linux/raid/detect.h> #include "check.h" -static int (*check_part[])(struct parsed_partitions *) = { +static int (*const check_part[])(struct parsed_partitions *) = { /* * Probe partition formats with tables at disk address 0 * that also have an ADFS boot block at 0xdc0. @@ -228,7 +228,7 @@ static struct attribute *part_attrs[] = { NULL }; -static struct attribute_group part_attr_group = { +static const struct attribute_group part_attr_group = { .attrs = part_attrs, }; @@ -256,31 +256,36 @@ static int part_uevent(const struct device *dev, struct kobj_uevent_env *env) return 0; } -struct device_type part_type = { +const struct device_type part_type = { .name = "partition", .groups = part_attr_groups, .release = part_release, .uevent = part_uevent, }; -static void delete_partition(struct block_device *part) +void drop_partition(struct block_device *part) { lockdep_assert_held(&part->bd_disk->open_mutex); - fsync_bdev(part); - __invalidate_device(part, true); - xa_erase(&part->bd_disk->part_tbl, part->bd_partno); kobject_put(part->bd_holder_dir); + device_del(&part->bd_device); + put_device(&part->bd_device); +} +static void delete_partition(struct block_device *part) +{ /* * Remove the block device from the inode hash, so that it cannot be * looked up any more even when openers still hold references. */ remove_inode_hash(part->bd_inode); - put_device(&part->bd_device); + fsync_bdev(part); + __invalidate_device(part, true); + + drop_partition(part); } static ssize_t whole_disk_show(struct device *dev, @@ -288,7 +293,7 @@ static ssize_t whole_disk_show(struct device *dev, { return 0; } -static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); +static const DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); /* * Must be called either with open_mutex held, before a disk can be opened or @@ -436,10 +441,21 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start, int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, sector_t length) { + sector_t capacity = get_capacity(disk), end; struct block_device *part; int ret; mutex_lock(&disk->open_mutex); + if (check_add_overflow(start, length, &end)) { + ret = -EINVAL; + goto out; + } + + if (start >= capacity || end > capacity) { + ret = -EINVAL; + goto out; + } + if (!disk_live(disk)) { ret = -ENXIO; goto out; @@ -519,17 +535,6 @@ static bool disk_unlock_native_capacity(struct gendisk *disk) return true; } -void blk_drop_partitions(struct gendisk *disk) -{ - struct block_device *part; - unsigned long idx; - - lockdep_assert_held(&disk->open_mutex); - - xa_for_each_start(&disk->part_tbl, idx, part, 1) - delete_partition(part); -} - static bool blk_add_partition(struct gendisk *disk, struct parsed_partitions *state, int p) { @@ -646,6 +651,8 @@ out_free_state: int bdev_disk_changed(struct gendisk *disk, bool invalidate) { + struct block_device *part; + unsigned long idx; int ret = 0; lockdep_assert_held(&disk->open_mutex); @@ -658,8 +665,9 @@ rescan: return -EBUSY; sync_blockdev(disk->part0); invalidate_bdev(disk->part0); - blk_drop_partitions(disk); + xa_for_each_start(&disk->part_tbl, idx, part, 1) + delete_partition(part); clear_bit(GD_NEED_PART_SCAN, &disk->state); /* diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 9c09ca5c4ab6..878aa7646b37 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -751,14 +751,12 @@ static int really_probe_debug(struct device *dev, struct device_driver *drv) * * Should somehow figure out how to use a semaphore, not an atomic variable... */ -int driver_probe_done(void) +bool __init driver_probe_done(void) { int local_probe_count = atomic_read(&probe_count); pr_debug("%s: probe_count = %d\n", __func__, local_probe_count); - if (local_probe_count) - return -EBUSY; - return 0; + return !local_probe_count; } /** diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 4c8b2ba579ee..e460c9799d9f 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1532,7 +1532,7 @@ static int fd_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { struct amiga_floppy_struct *p = bdev->bd_disk->private_data; @@ -1607,7 +1607,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, return 0; } -static int fd_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { int ret; @@ -1654,10 +1654,10 @@ static void fd_probe(int dev) * /dev/PS0 etc), and disallows simultaneous access to the same * drive with different device numbers. */ -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - int drive = MINOR(bdev->bd_dev) & 3; - int system = (MINOR(bdev->bd_dev) & 4) >> 2; + int drive = disk->first_minor & 3; + int system = (disk->first_minor & 4) >> 2; int old_dev; unsigned long flags; @@ -1673,10 +1673,9 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) mutex_unlock(&amiflop_mutex); return -ENXIO; } - - if (mode & (FMODE_READ|FMODE_WRITE)) { - bdev_check_media_change(bdev); - if (mode & FMODE_WRITE) { + if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) { + disk_check_media_change(disk); + if (mode & BLK_OPEN_WRITE) { int wrprot; get_fdc(drive); @@ -1691,7 +1690,6 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) } } } - local_irq_save(flags); fd_ref[drive]++; fd_device[drive] = system; @@ -1709,7 +1707,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) return 0; } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { struct amiga_floppy_struct *p = disk->private_data; int drive = p - unit; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 128722cf6c3c..cf6883756155 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -204,9 +204,9 @@ aoedisk_rm_debugfs(struct aoedev *d) } static int -aoeblk_open(struct block_device *bdev, fmode_t mode) +aoeblk_open(struct gendisk *disk, blk_mode_t mode) { - struct aoedev *d = bdev->bd_disk->private_data; + struct aoedev *d = disk->private_data; ulong flags; if (!virt_addr_valid(d)) { @@ -232,7 +232,7 @@ aoeblk_open(struct block_device *bdev, fmode_t mode) } static void -aoeblk_release(struct gendisk *disk, fmode_t mode) +aoeblk_release(struct gendisk *disk) { struct aoedev *d = disk->private_data; ulong flags; @@ -285,7 +285,7 @@ aoeblk_getgeo(struct block_device *bdev, struct hd_geometry *geo) } static int -aoeblk_ioctl(struct block_device *bdev, fmode_t mode, uint cmd, ulong arg) +aoeblk_ioctl(struct block_device *bdev, blk_mode_t mode, uint cmd, ulong arg) { struct aoedev *d; diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c index 4c666f72203f..a42c4bcc85ba 100644 --- a/drivers/block/aoe/aoechr.c +++ b/drivers/block/aoe/aoechr.c @@ -49,7 +49,7 @@ static int emsgs_head_idx, emsgs_tail_idx; static struct completion emsgs_comp; static spinlock_t emsgs_lock; static int nblocked_emsgs_readers; -static struct class *aoe_class; + static struct aoe_chardev chardevs[] = { { MINOR_ERR, "err" }, { MINOR_DISCOVER, "discover" }, @@ -58,6 +58,16 @@ static struct aoe_chardev chardevs[] = { { MINOR_FLUSH, "flush" }, }; +static char *aoe_devnode(const struct device *dev, umode_t *mode) +{ + return kasprintf(GFP_KERNEL, "etherd/%s", dev_name(dev)); +} + +static const struct class aoe_class = { + .name = "aoe", + .devnode = aoe_devnode, +}; + static int discover(void) { @@ -273,11 +283,6 @@ static const struct file_operations aoe_fops = { .llseek = noop_llseek, }; -static char *aoe_devnode(const struct device *dev, umode_t *mode) -{ - return kasprintf(GFP_KERNEL, "etherd/%s", dev_name(dev)); -} - int __init aoechr_init(void) { @@ -290,15 +295,14 @@ aoechr_init(void) } init_completion(&emsgs_comp); spin_lock_init(&emsgs_lock); - aoe_class = class_create("aoe"); - if (IS_ERR(aoe_class)) { + n = class_register(&aoe_class); + if (n) { unregister_chrdev(AOE_MAJOR, "aoechr"); - return PTR_ERR(aoe_class); + return n; } - aoe_class->devnode = aoe_devnode; for (i = 0; i < ARRAY_SIZE(chardevs); ++i) - device_create(aoe_class, NULL, + device_create(&aoe_class, NULL, MKDEV(AOE_MAJOR, chardevs[i].minor), NULL, chardevs[i].name); @@ -311,8 +315,8 @@ aoechr_exit(void) int i; for (i = 0; i < ARRAY_SIZE(chardevs); ++i) - device_destroy(aoe_class, MKDEV(AOE_MAJOR, chardevs[i].minor)); - class_destroy(aoe_class); + device_destroy(&aoe_class, MKDEV(AOE_MAJOR, chardevs[i].minor)); + class_unregister(&aoe_class); unregister_chrdev(AOE_MAJOR, "aoechr"); } diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 9deb4df6bdb8..cd738cab725f 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -442,13 +442,13 @@ static void fd_times_out(struct timer_list *unused); static void finish_fdc( void ); static void finish_fdc_done( int dummy ); static void setup_req_params( int drive ); -static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int - cmd, unsigned long param); +static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long param); static void fd_probe( int drive ); static int fd_test_drive_present( int drive ); static void config_types( void ); -static int floppy_open(struct block_device *bdev, fmode_t mode); -static void floppy_release(struct gendisk *disk, fmode_t mode); +static int floppy_open(struct gendisk *disk, blk_mode_t mode); +static void floppy_release(struct gendisk *disk); /************************* End of Prototypes **************************/ @@ -1581,7 +1581,7 @@ out: return BLK_STS_OK; } -static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { struct gendisk *disk = bdev->bd_disk; @@ -1760,15 +1760,15 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* invalidate the buffer track to force a reread */ BufferDrive = -1; set_bit(drive, &fake_change); - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); + if (disk_check_media_change(disk)) + floppy_revalidate(disk); return 0; default: return -EINVAL; } } -static int fd_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { int ret; @@ -1915,32 +1915,31 @@ static void __init config_types( void ) * drive with different device numbers. */ -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - struct atari_floppy_struct *p = bdev->bd_disk->private_data; - int type = MINOR(bdev->bd_dev) >> 2; + struct atari_floppy_struct *p = disk->private_data; + int type = disk->first_minor >> 2; DPRINT(("fd_open: type=%d\n",type)); if (p->ref && p->type != type) return -EBUSY; - if (p->ref == -1 || (p->ref && mode & FMODE_EXCL)) + if (p->ref == -1 || (p->ref && mode & BLK_OPEN_EXCL)) return -EBUSY; - - if (mode & FMODE_EXCL) + if (mode & BLK_OPEN_EXCL) p->ref = -1; else p->ref++; p->type = type; - if (mode & FMODE_NDELAY) + if (mode & BLK_OPEN_NDELAY) return 0; - if (mode & (FMODE_READ|FMODE_WRITE)) { - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); - if (mode & FMODE_WRITE) { + if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) { + if (disk_check_media_change(disk)) + floppy_revalidate(disk); + if (mode & BLK_OPEN_WRITE) { if (p->wpstat) { if (p->ref < 0) p->ref = 0; @@ -1953,18 +1952,18 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) return 0; } -static int floppy_unlocked_open(struct block_device *bdev, fmode_t mode) +static int floppy_unlocked_open(struct gendisk *disk, blk_mode_t mode) { int ret; mutex_lock(&ataflop_mutex); - ret = floppy_open(bdev, mode); + ret = floppy_open(disk, mode); mutex_unlock(&ataflop_mutex); return ret; } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { struct atari_floppy_struct *p = disk->private_data; mutex_lock(&ataflop_mutex); diff --git a/drivers/block/brd.c b/drivers/block/brd.c index bcad9b926b0c..970bd6ff38c4 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -19,7 +19,7 @@ #include <linux/highmem.h> #include <linux/mutex.h> #include <linux/pagemap.h> -#include <linux/radix-tree.h> +#include <linux/xarray.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/backing-dev.h> @@ -28,7 +28,7 @@ #include <linux/uaccess.h> /* - * Each block ramdisk device has a radix_tree brd_pages of pages that stores + * Each block ramdisk device has a xarray brd_pages of pages that stores * the pages containing the block device's contents. A brd page's ->index is * its offset in PAGE_SIZE units. This is similar to, but in no way connected * with, the kernel's pagecache or buffer cache (which sit above our block @@ -40,11 +40,9 @@ struct brd_device { struct list_head brd_list; /* - * Backing store of pages and lock to protect it. This is the contents - * of the block device. + * Backing store of pages. This is the contents of the block device. */ - spinlock_t brd_lock; - struct radix_tree_root brd_pages; + struct xarray brd_pages; u64 brd_nr_pages; }; @@ -56,21 +54,8 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector) pgoff_t idx; struct page *page; - /* - * The page lifetime is protected by the fact that we have opened the - * device node -- brd pages will never be deleted under us, so we - * don't need any further locking or refcounting. - * - * This is strictly true for the radix-tree nodes as well (ie. we - * don't actually need the rcu_read_lock()), however that is not a - * documented feature of the radix-tree API so it is better to be - * safe here (we don't have total exclusion from radix tree updates - * here, only deletes). - */ - rcu_read_lock(); idx = sector >> PAGE_SECTORS_SHIFT; /* sector to page index */ - page = radix_tree_lookup(&brd->brd_pages, idx); - rcu_read_unlock(); + page = xa_load(&brd->brd_pages, idx); BUG_ON(page && page->index != idx); @@ -83,7 +68,7 @@ static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector) static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp) { pgoff_t idx; - struct page *page; + struct page *page, *cur; int ret = 0; page = brd_lookup_page(brd, sector); @@ -94,71 +79,42 @@ static int brd_insert_page(struct brd_device *brd, sector_t sector, gfp_t gfp) if (!page) return -ENOMEM; - if (radix_tree_maybe_preload(gfp)) { - __free_page(page); - return -ENOMEM; - } + xa_lock(&brd->brd_pages); - spin_lock(&brd->brd_lock); idx = sector >> PAGE_SECTORS_SHIFT; page->index = idx; - if (radix_tree_insert(&brd->brd_pages, idx, page)) { + + cur = __xa_cmpxchg(&brd->brd_pages, idx, NULL, page, gfp); + + if (unlikely(cur)) { __free_page(page); - page = radix_tree_lookup(&brd->brd_pages, idx); - if (!page) - ret = -ENOMEM; - else if (page->index != idx) + ret = xa_err(cur); + if (!ret && (cur->index != idx)) ret = -EIO; } else { brd->brd_nr_pages++; } - spin_unlock(&brd->brd_lock); - radix_tree_preload_end(); + xa_unlock(&brd->brd_pages); + return ret; } /* - * Free all backing store pages and radix tree. This must only be called when + * Free all backing store pages and xarray. This must only be called when * there are no other users of the device. */ -#define FREE_BATCH 16 static void brd_free_pages(struct brd_device *brd) { - unsigned long pos = 0; - struct page *pages[FREE_BATCH]; - int nr_pages; - - do { - int i; - - nr_pages = radix_tree_gang_lookup(&brd->brd_pages, - (void **)pages, pos, FREE_BATCH); - - for (i = 0; i < nr_pages; i++) { - void *ret; - - BUG_ON(pages[i]->index < pos); - pos = pages[i]->index; - ret = radix_tree_delete(&brd->brd_pages, pos); - BUG_ON(!ret || ret != pages[i]); - __free_page(pages[i]); - } - - pos++; + struct page *page; + pgoff_t idx; - /* - * It takes 3.4 seconds to remove 80GiB ramdisk. - * So, we need cond_resched to avoid stalling the CPU. - */ + xa_for_each(&brd->brd_pages, idx, page) { + __free_page(page); cond_resched(); + } - /* - * This assumes radix_tree_gang_lookup always returns as - * many pages as possible. If the radix-tree code changes, - * so will this have to. - */ - } while (nr_pages == FREE_BATCH); + xa_destroy(&brd->brd_pages); } /* @@ -372,8 +328,7 @@ static int brd_alloc(int i) brd->brd_number = i; list_add_tail(&brd->brd_list, &brd_devices); - spin_lock_init(&brd->brd_lock); - INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC); + xa_init(&brd->brd_pages); snprintf(buf, DISK_NAME_LEN, "ram%d", i); if (!IS_ERR_OR_NULL(brd_debugfs_dir)) diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 6ac8c54b44c7..85ca000a0564 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -1043,9 +1043,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho bio = bio_alloc_bioset(device->ldev->md_bdev, 1, op, GFP_NOIO, &drbd_md_io_bio_set); bio->bi_iter.bi_sector = on_disk_sector; - /* bio_add_page of a single page to an empty bio will always succeed, - * according to api. Do we want to assert that? */ - bio_add_page(bio, page, len, 0); + __bio_add_page(bio, page, len, 0); bio->bi_private = ctx; bio->bi_end_io = drbd_bm_endio; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 83987e7a5ef2..965f672557f2 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -37,7 +37,6 @@ #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/workqueue.h> -#define __KERNEL_SYSCALLS__ #include <linux/unistd.h> #include <linux/vmalloc.h> #include <linux/sched/signal.h> @@ -50,8 +49,8 @@ #include "drbd_debugfs.h" static DEFINE_MUTEX(drbd_main_mutex); -static int drbd_open(struct block_device *bdev, fmode_t mode); -static void drbd_release(struct gendisk *gd, fmode_t mode); +static int drbd_open(struct gendisk *disk, blk_mode_t mode); +static void drbd_release(struct gendisk *gd); static void md_sync_timer_fn(struct timer_list *t); static int w_bitmap_io(struct drbd_work *w, int unused); @@ -1883,9 +1882,9 @@ int drbd_send_all(struct drbd_connection *connection, struct socket *sock, void return 0; } -static int drbd_open(struct block_device *bdev, fmode_t mode) +static int drbd_open(struct gendisk *disk, blk_mode_t mode) { - struct drbd_device *device = bdev->bd_disk->private_data; + struct drbd_device *device = disk->private_data; unsigned long flags; int rv = 0; @@ -1895,7 +1894,7 @@ static int drbd_open(struct block_device *bdev, fmode_t mode) * and no race with updating open_cnt */ if (device->state.role != R_PRIMARY) { - if (mode & FMODE_WRITE) + if (mode & BLK_OPEN_WRITE) rv = -EROFS; else if (!drbd_allow_oos) rv = -EMEDIUMTYPE; @@ -1909,9 +1908,10 @@ static int drbd_open(struct block_device *bdev, fmode_t mode) return rv; } -static void drbd_release(struct gendisk *gd, fmode_t mode) +static void drbd_release(struct gendisk *gd) { struct drbd_device *device = gd->private_data; + mutex_lock(&drbd_main_mutex); device->open_cnt--; mutex_unlock(&drbd_main_mutex); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 1a5d3d72d91d..cddae6f4b00f 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1640,8 +1640,8 @@ static struct block_device *open_backing_dev(struct drbd_device *device, struct block_device *bdev; int err = 0; - bdev = blkdev_get_by_path(bdev_path, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, claim_ptr); + bdev = blkdev_get_by_path(bdev_path, BLK_OPEN_READ | BLK_OPEN_WRITE, + claim_ptr, NULL); if (IS_ERR(bdev)) { drbd_err(device, "open(\"%s\") failed with %ld\n", bdev_path, PTR_ERR(bdev)); @@ -1653,7 +1653,7 @@ static struct block_device *open_backing_dev(struct drbd_device *device, err = bd_link_disk_holder(bdev, device->vdisk); if (err) { - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, claim_ptr); drbd_err(device, "bd_link_disk_holder(\"%s\", ...) failed with %d\n", bdev_path, err); bdev = ERR_PTR(err); @@ -1695,13 +1695,13 @@ static int open_backing_devices(struct drbd_device *device, } static void close_backing_dev(struct drbd_device *device, struct block_device *bdev, - bool do_bd_unlink) + void *claim_ptr, bool do_bd_unlink) { if (!bdev) return; if (do_bd_unlink) bd_unlink_disk_holder(bdev, device->vdisk); - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, claim_ptr); } void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev *ldev) @@ -1709,8 +1709,11 @@ void drbd_backing_dev_free(struct drbd_device *device, struct drbd_backing_dev * if (ldev == NULL) return; - close_backing_dev(device, ldev->md_bdev, ldev->md_bdev != ldev->backing_bdev); - close_backing_dev(device, ldev->backing_bdev, true); + close_backing_dev(device, ldev->md_bdev, + ldev->md.meta_dev_idx < 0 ? + (void *)device : (void *)drbd_m_holder, + ldev->md_bdev != ldev->backing_bdev); + close_backing_dev(device, ldev->backing_bdev, device, true); kfree(ldev->disk_conf); kfree(ldev); @@ -2126,8 +2129,11 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) fail: conn_reconfig_done(connection); if (nbc) { - close_backing_dev(device, nbc->md_bdev, nbc->md_bdev != nbc->backing_bdev); - close_backing_dev(device, nbc->backing_bdev, true); + close_backing_dev(device, nbc->md_bdev, + nbc->disk_conf->meta_dev_idx < 0 ? + (void *)device : (void *)drbd_m_holder, + nbc->md_bdev != nbc->backing_bdev); + close_backing_dev(device, nbc->backing_bdev, device, true); kfree(nbc); } kfree(new_disk_conf); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 8c2bc47de473..0c9f54197768 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -27,7 +27,6 @@ #include <uapi/linux/sched/types.h> #include <linux/sched/signal.h> #include <linux/pkt_sched.h> -#define __KERNEL_SYSCALLS__ #include <linux/unistd.h> #include <linux/vmalloc.h> #include <linux/random.h> diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index cec2c20f5e59..2db9b186b977 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -402,7 +402,7 @@ 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 blk_mq_tag_set tag_sets[N_DRIVE]; -static struct block_device *opened_bdev[N_DRIVE]; +static struct gendisk *opened_disk[N_DRIVE]; static DEFINE_MUTEX(open_lock); static struct floppy_raw_cmd *raw_cmd, default_raw_cmd; @@ -3210,13 +3210,13 @@ static int floppy_raw_cmd_ioctl(int type, int drive, int cmd, #endif -static int invalidate_drive(struct block_device *bdev) +static int invalidate_drive(struct gendisk *disk) { /* invalidate the buffer track to force a reread */ - set_bit((long)bdev->bd_disk->private_data, &fake_change); + set_bit((long)disk->private_data, &fake_change); process_fd_request(); - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); + if (disk_check_media_change(disk)) + floppy_revalidate(disk); return 0; } @@ -3251,10 +3251,11 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g, floppy_type[type].size + 1; process_fd_request(); for (cnt = 0; cnt < N_DRIVE; cnt++) { - struct block_device *bdev = opened_bdev[cnt]; - if (!bdev || ITYPE(drive_state[cnt].fd_device) != type) + struct gendisk *disk = opened_disk[cnt]; + + if (!disk || ITYPE(drive_state[cnt].fd_device) != type) continue; - __invalidate_device(bdev, true); + __invalidate_device(disk->part0, true); } mutex_unlock(&open_lock); } else { @@ -3287,7 +3288,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g, drive_state[current_drive].maxtrack || ((user_params[drive].sect ^ oldStretch) & (FD_SWAPSIDES | FD_SECTBASEMASK))) - invalidate_drive(bdev); + invalidate_drive(bdev->bd_disk); else process_fd_request(); } @@ -3393,8 +3394,8 @@ static bool valid_floppy_drive_params(const short autodetect[FD_AUTODETECT_SIZE] return true; } -static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, - unsigned long param) +static int fd_locked_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long param) { int drive = (long)bdev->bd_disk->private_data; int type = ITYPE(drive_state[drive].fd_device); @@ -3427,7 +3428,8 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int return ret; /* permission checks */ - if (((cmd & 0x40) && !(mode & (FMODE_WRITE | FMODE_WRITE_IOCTL))) || + if (((cmd & 0x40) && + !(mode & (BLK_OPEN_WRITE | BLK_OPEN_WRITE_IOCTL))) || ((cmd & 0x80) && !capable(CAP_SYS_ADMIN))) return -EPERM; @@ -3464,7 +3466,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int current_type[drive] = NULL; floppy_sizes[drive] = MAX_DISK_SIZE << 1; drive_state[drive].keep_data = 0; - return invalidate_drive(bdev); + return invalidate_drive(bdev->bd_disk); case FDSETPRM: case FDDEFPRM: return set_geometry(cmd, &inparam.g, drive, type, bdev); @@ -3503,7 +3505,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int case FDFLUSH: if (lock_fdc(drive)) return -EINTR; - return invalidate_drive(bdev); + return invalidate_drive(bdev->bd_disk); case FDSETEMSGTRESH: drive_params[drive].max_errors.reporting = (unsigned short)(param & 0x0f); return 0; @@ -3565,7 +3567,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int return 0; } -static int fd_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { int ret; @@ -3653,8 +3655,8 @@ struct compat_floppy_write_errors { #define FDGETFDCSTAT32 _IOR(2, 0x15, struct compat_floppy_fdc_state) #define FDWERRORGET32 _IOR(2, 0x17, struct compat_floppy_write_errors) -static int compat_set_geometry(struct block_device *bdev, fmode_t mode, unsigned int cmd, - struct compat_floppy_struct __user *arg) +static int compat_set_geometry(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, struct compat_floppy_struct __user *arg) { struct floppy_struct v; int drive, type; @@ -3663,7 +3665,7 @@ static int compat_set_geometry(struct block_device *bdev, fmode_t mode, unsigned BUILD_BUG_ON(offsetof(struct floppy_struct, name) != offsetof(struct compat_floppy_struct, name)); - if (!(mode & (FMODE_WRITE | FMODE_WRITE_IOCTL))) + if (!(mode & (BLK_OPEN_WRITE | BLK_OPEN_WRITE_IOCTL))) return -EPERM; memset(&v, 0, sizeof(struct floppy_struct)); @@ -3860,8 +3862,8 @@ static int compat_werrorget(int drive, return 0; } -static int fd_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, - unsigned long param) +static int fd_compat_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long param) { int drive = (long)bdev->bd_disk->private_data; switch (cmd) { @@ -3962,7 +3964,7 @@ static void __init config_types(void) pr_cont("\n"); } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { int drive = (long)disk->private_data; @@ -3973,7 +3975,7 @@ static void floppy_release(struct gendisk *disk, fmode_t mode) drive_state[drive].fd_ref = 0; } if (!drive_state[drive].fd_ref) - opened_bdev[drive] = NULL; + opened_disk[drive] = NULL; mutex_unlock(&open_lock); mutex_unlock(&floppy_mutex); } @@ -3983,9 +3985,9 @@ static void floppy_release(struct gendisk *disk, fmode_t mode) * /dev/PS0 etc), and disallows simultaneous access to the same * drive with different device numbers. */ -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - int drive = (long)bdev->bd_disk->private_data; + int drive = (long)disk->private_data; int old_dev, new_dev; int try; int res = -EBUSY; @@ -3994,7 +3996,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) mutex_lock(&floppy_mutex); mutex_lock(&open_lock); old_dev = drive_state[drive].fd_device; - if (opened_bdev[drive] && opened_bdev[drive] != bdev) + if (opened_disk[drive] && opened_disk[drive] != disk) goto out2; if (!drive_state[drive].fd_ref && (drive_params[drive].flags & FD_BROKEN_DCL)) { @@ -4004,7 +4006,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) drive_state[drive].fd_ref++; - opened_bdev[drive] = bdev; + opened_disk[drive] = disk; res = -ENXIO; @@ -4038,7 +4040,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) } } - new_dev = MINOR(bdev->bd_dev); + new_dev = disk->first_minor; drive_state[drive].fd_device = new_dev; set_capacity(disks[drive][ITYPE(new_dev)], floppy_sizes[new_dev]); if (old_dev != -1 && old_dev != new_dev) { @@ -4048,21 +4050,20 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) if (fdc_state[FDC(drive)].rawcmd == 1) fdc_state[FDC(drive)].rawcmd = 2; - - if (!(mode & FMODE_NDELAY)) { - if (mode & (FMODE_READ|FMODE_WRITE)) { + if (!(mode & BLK_OPEN_NDELAY)) { + if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) { drive_state[drive].last_checked = 0; clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &drive_state[drive].flags); - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); + if (disk_check_media_change(disk)) + floppy_revalidate(disk); if (test_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags)) goto out; if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &drive_state[drive].flags)) goto out; } res = -EROFS; - if ((mode & FMODE_WRITE) && + if ((mode & BLK_OPEN_WRITE) && !test_bit(FD_DISK_WRITABLE_BIT, &drive_state[drive].flags)) goto out; } @@ -4073,7 +4074,7 @@ out: drive_state[drive].fd_ref--; if (!drive_state[drive].fd_ref) - opened_bdev[drive] = NULL; + opened_disk[drive] = NULL; out2: mutex_unlock(&open_lock); mutex_unlock(&floppy_mutex); @@ -4147,7 +4148,7 @@ static int __floppy_read_block_0(struct block_device *bdev, int drive) cbdata.drive = drive; bio_init(&bio, bdev, &bio_vec, 1, REQ_OP_READ); - bio_add_page(&bio, page, block_size(bdev), 0); + __bio_add_page(&bio, page, block_size(bdev), 0); bio.bi_iter.bi_sector = 0; bio.bi_flags |= (1 << BIO_QUIET); @@ -4203,7 +4204,8 @@ static int floppy_revalidate(struct gendisk *disk) drive_state[drive].generation++; if (drive_no_geom(drive)) { /* auto-sensing */ - res = __floppy_read_block_0(opened_bdev[drive], drive); + res = __floppy_read_block_0(opened_disk[drive]->part0, + drive); } else { if (cf) poll_drive(false, FD_RAW_NEED_DISK); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index bc31bb7072a2..37511d2b2caf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -990,7 +990,7 @@ loop_set_status_from_info(struct loop_device *lo, return 0; } -static int loop_configure(struct loop_device *lo, fmode_t mode, +static int loop_configure(struct loop_device *lo, blk_mode_t mode, struct block_device *bdev, const struct loop_config *config) { @@ -1014,8 +1014,8 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. */ - if (!(mode & FMODE_EXCL)) { - error = bd_prepare_to_claim(bdev, loop_configure); + if (!(mode & BLK_OPEN_EXCL)) { + error = bd_prepare_to_claim(bdev, loop_configure, NULL); if (error) goto out_putf; } @@ -1050,7 +1050,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, if (error) goto out_unlock; - if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) || + if (!(file->f_mode & FMODE_WRITE) || !(mode & BLK_OPEN_WRITE) || !file->f_op->write_iter) lo->lo_flags |= LO_FLAGS_READ_ONLY; @@ -1116,7 +1116,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, if (partscan) loop_reread_partitions(lo); - if (!(mode & FMODE_EXCL)) + if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, loop_configure); return 0; @@ -1124,7 +1124,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, out_unlock: loop_global_unlock(lo, is_loop); out_bdev: - if (!(mode & FMODE_EXCL)) + if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, loop_configure); out_putf: fput(file); @@ -1528,7 +1528,7 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, return err; } -static int lo_ioctl(struct block_device *bdev, fmode_t mode, +static int lo_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; @@ -1563,24 +1563,22 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, return loop_clr_fd(lo); case LOOP_SET_STATUS: err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { + if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) err = loop_set_status_old(lo, argp); - } break; case LOOP_GET_STATUS: return loop_get_status_old(lo, argp); case LOOP_SET_STATUS64: err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { + if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) err = loop_set_status64(lo, argp); - } break; case LOOP_GET_STATUS64: return loop_get_status64(lo, argp); case LOOP_SET_CAPACITY: case LOOP_SET_DIRECT_IO: case LOOP_SET_BLOCK_SIZE: - if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN)) + if (!(mode & BLK_OPEN_WRITE) && !capable(CAP_SYS_ADMIN)) return -EPERM; fallthrough; default: @@ -1691,7 +1689,7 @@ loop_get_status_compat(struct loop_device *lo, return err; } -static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, +static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; @@ -1727,7 +1725,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, } #endif -static void lo_release(struct gendisk *disk, fmode_t mode) +static void lo_release(struct gendisk *disk) { struct loop_device *lo = disk->private_data; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 815d77ba6381..b200950e8fb5 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3041,7 +3041,7 @@ static int rssd_disk_name_format(char *prefix, * structure pointer. */ static int mtip_block_ioctl(struct block_device *dev, - fmode_t mode, + blk_mode_t mode, unsigned cmd, unsigned long arg) { @@ -3079,7 +3079,7 @@ static int mtip_block_ioctl(struct block_device *dev, * structure pointer. */ static int mtip_block_compat_ioctl(struct block_device *dev, - fmode_t mode, + blk_mode_t mode, unsigned cmd, unsigned long arg) { diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 65ecde3e2a5b..8576d696c7a2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1502,7 +1502,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, return -ENOTTY; } -static int nbd_ioctl(struct block_device *bdev, fmode_t mode, +static int nbd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct nbd_device *nbd = bdev->bd_disk->private_data; @@ -1553,13 +1553,13 @@ static struct nbd_config *nbd_alloc_config(void) return config; } -static int nbd_open(struct block_device *bdev, fmode_t mode) +static int nbd_open(struct gendisk *disk, blk_mode_t mode) { struct nbd_device *nbd; int ret = 0; mutex_lock(&nbd_index_mutex); - nbd = bdev->bd_disk->private_data; + nbd = disk->private_data; if (!nbd) { ret = -ENXIO; goto out; @@ -1587,17 +1587,17 @@ static int nbd_open(struct block_device *bdev, fmode_t mode) refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); if (max_part) - set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + set_bit(GD_NEED_PART_SCAN, &disk->state); } else if (nbd_disconnected(nbd->config)) { if (max_part) - set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + set_bit(GD_NEED_PART_SCAN, &disk->state); } out: mutex_unlock(&nbd_index_mutex); return ret; } -static void nbd_release(struct gendisk *disk, fmode_t mode) +static void nbd_release(struct gendisk *disk) { struct nbd_device *nbd = disk->private_data; @@ -1776,7 +1776,8 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) if (err == -ENOSPC) err = -EEXIST; } else { - err = idr_alloc(&nbd_index_idr, nbd, 0, 0, GFP_KERNEL); + err = idr_alloc(&nbd_index_idr, nbd, 0, + (MINORMASK >> part_shift) + 1, GFP_KERNEL); if (err >= 0) index = err; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index d5d7884cedd4..a1428538bda5 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -46,47 +46,34 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/pktcdvd.h> -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> +#include <linux/backing-dev.h> #include <linux/compat.h> -#include <linux/kthread.h> +#include <linux/debugfs.h> +#include <linux/device.h> #include <linux/errno.h> -#include <linux/spinlock.h> #include <linux/file.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/miscdevice.h> #include <linux/freezer.h> +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/miscdevice.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/nospec.h> +#include <linux/pktcdvd.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/slab.h> -#include <linux/backing-dev.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/uaccess.h> + +#include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_ioctl.h> -#include <scsi/scsi.h> -#include <linux/debugfs.h> -#include <linux/device.h> -#include <linux/nospec.h> -#include <linux/uaccess.h> -#define DRIVER_NAME "pktcdvd" +#include <asm/unaligned.h> -#define pkt_err(pd, fmt, ...) \ - pr_err("%s: " fmt, pd->name, ##__VA_ARGS__) -#define pkt_notice(pd, fmt, ...) \ - pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__) -#define pkt_info(pd, fmt, ...) \ - pr_info("%s: " fmt, pd->name, ##__VA_ARGS__) - -#define pkt_dbg(level, pd, fmt, ...) \ -do { \ - if (level == 2 && PACKET_DEBUG >= 2) \ - pr_notice("%s: %s():" fmt, \ - pd->name, __func__, ##__VA_ARGS__); \ - else if (level == 1 && PACKET_DEBUG >= 1) \ - pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__); \ -} while (0) +#define DRIVER_NAME "pktcdvd" #define MAX_SPEED 0xffff @@ -107,7 +94,6 @@ static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */ /* forward declaration */ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev); static int pkt_remove_dev(dev_t pkt_dev); -static int pkt_seq_show(struct seq_file *m, void *p); static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd) { @@ -253,15 +239,16 @@ static ssize_t congestion_off_store(struct device *dev, const char *buf, size_t len) { struct pktcdvd_device *pd = dev_get_drvdata(dev); - int val; + int val, ret; - if (sscanf(buf, "%d", &val) == 1) { - spin_lock(&pd->lock); - pd->write_congestion_off = val; - init_write_congestion_marks(&pd->write_congestion_off, - &pd->write_congestion_on); - spin_unlock(&pd->lock); - } + ret = kstrtoint(buf, 10, &val); + if (ret) + return ret; + + spin_lock(&pd->lock); + pd->write_congestion_off = val; + init_write_congestion_marks(&pd->write_congestion_off, &pd->write_congestion_on); + spin_unlock(&pd->lock); return len; } static DEVICE_ATTR_RW(congestion_off); @@ -283,15 +270,16 @@ static ssize_t congestion_on_store(struct device *dev, const char *buf, size_t len) { struct pktcdvd_device *pd = dev_get_drvdata(dev); - int val; + int val, ret; - if (sscanf(buf, "%d", &val) == 1) { - spin_lock(&pd->lock); - pd->write_congestion_on = val; - init_write_congestion_marks(&pd->write_congestion_off, - &pd->write_congestion_on); - spin_unlock(&pd->lock); - } + ret = kstrtoint(buf, 10, &val); + if (ret) + return ret; + + spin_lock(&pd->lock); + pd->write_congestion_on = val; + init_write_congestion_marks(&pd->write_congestion_off, &pd->write_congestion_on); + spin_unlock(&pd->lock); return len; } static DEVICE_ATTR_RW(congestion_on); @@ -319,7 +307,7 @@ static void pkt_sysfs_dev_new(struct pktcdvd_device *pd) if (class_is_registered(&class_pktcdvd)) { pd->dev = device_create_with_groups(&class_pktcdvd, NULL, MKDEV(0, 0), pd, pkt_groups, - "%s", pd->name); + "%s", pd->disk->disk_name); if (IS_ERR(pd->dev)) pd->dev = NULL; } @@ -349,8 +337,8 @@ static ssize_t device_map_show(const struct class *c, const struct class_attribu struct pktcdvd_device *pd = pkt_devs[idx]; if (!pd) continue; - n += sprintf(data+n, "%s %u:%u %u:%u\n", - pd->name, + n += sysfs_emit_at(data, n, "%s %u:%u %u:%u\n", + pd->disk->disk_name, MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev), MAJOR(pd->bdev->bd_dev), MINOR(pd->bdev->bd_dev)); @@ -428,34 +416,92 @@ static void pkt_sysfs_cleanup(void) *******************************************************************/ -static int pkt_debugfs_seq_show(struct seq_file *m, void *p) +static void pkt_count_states(struct pktcdvd_device *pd, int *states) { - return pkt_seq_show(m, p); + struct packet_data *pkt; + int i; + + for (i = 0; i < PACKET_NUM_STATES; i++) + states[i] = 0; + + spin_lock(&pd->cdrw.active_list_lock); + list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { + states[pkt->state]++; + } + spin_unlock(&pd->cdrw.active_list_lock); } -static int pkt_debugfs_fops_open(struct inode *inode, struct file *file) +static int pkt_seq_show(struct seq_file *m, void *p) { - return single_open(file, pkt_debugfs_seq_show, inode->i_private); -} + struct pktcdvd_device *pd = m->private; + char *msg; + int states[PACKET_NUM_STATES]; -static const struct file_operations debug_fops = { - .open = pkt_debugfs_fops_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; + seq_printf(m, "Writer %s mapped to %pg:\n", pd->disk->disk_name, pd->bdev); + + seq_printf(m, "\nSettings:\n"); + seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2); + + if (pd->settings.write_type == 0) + msg = "Packet"; + else + msg = "Unknown"; + seq_printf(m, "\twrite type:\t\t%s\n", msg); + + seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable"); + seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss); + + seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode); + + if (pd->settings.block_mode == PACKET_BLOCK_MODE1) + msg = "Mode 1"; + else if (pd->settings.block_mode == PACKET_BLOCK_MODE2) + msg = "Mode 2"; + else + msg = "Unknown"; + seq_printf(m, "\tblock mode:\t\t%s\n", msg); + + seq_printf(m, "\nStatistics:\n"); + seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started); + seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended); + seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1); + seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1); + seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1); + + seq_printf(m, "\nMisc:\n"); + seq_printf(m, "\treference count:\t%d\n", pd->refcnt); + seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags); + seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed); + seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed); + seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset); + seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset); + + seq_printf(m, "\nQueue state:\n"); + seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size); + seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios)); + seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", pd->current_sector); + + pkt_count_states(pd, states); + seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", + states[0], states[1], states[2], states[3], states[4], states[5]); + + seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n", + pd->write_congestion_off, + pd->write_congestion_on); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(pkt_seq); static void pkt_debugfs_dev_new(struct pktcdvd_device *pd) { if (!pkt_debugfs_root) return; - pd->dfs_d_root = debugfs_create_dir(pd->name, pkt_debugfs_root); + pd->dfs_d_root = debugfs_create_dir(pd->disk->disk_name, pkt_debugfs_root); if (!pd->dfs_d_root) return; - pd->dfs_f_info = debugfs_create_file("info", 0444, - pd->dfs_d_root, pd, &debug_fops); + pd->dfs_f_info = debugfs_create_file("info", 0444, pd->dfs_d_root, + pd, &pkt_seq_fops); } static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd) @@ -484,9 +530,11 @@ static void pkt_debugfs_cleanup(void) static void pkt_bio_finished(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); + BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0); if (atomic_dec_and_test(&pd->cdrw.pending_bios)) { - pkt_dbg(2, pd, "queue empty\n"); + dev_dbg(ddev, "queue empty\n"); atomic_set(&pd->iosched.attention, 1); wake_up(&pd->wqueue); } @@ -717,15 +765,16 @@ static const char *sense_key_string(__u8 index) static void pkt_dump_sense(struct pktcdvd_device *pd, struct packet_command *cgc) { + struct device *ddev = disk_to_dev(pd->disk); struct scsi_sense_hdr *sshdr = cgc->sshdr; if (sshdr) - pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n", + dev_err(ddev, "%*ph - sense %02x.%02x.%02x (%s)\n", CDROM_PACKET_SIZE, cgc->cmd, sshdr->sense_key, sshdr->asc, sshdr->ascq, sense_key_string(sshdr->sense_key)); else - pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd); + dev_err(ddev, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd); } /* @@ -762,10 +811,8 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd, init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); cgc.sshdr = &sshdr; cgc.cmd[0] = GPCMD_SET_SPEED; - cgc.cmd[2] = (read_speed >> 8) & 0xff; - cgc.cmd[3] = read_speed & 0xff; - cgc.cmd[4] = (write_speed >> 8) & 0xff; - cgc.cmd[5] = write_speed & 0xff; + put_unaligned_be16(read_speed, &cgc.cmd[2]); + put_unaligned_be16(write_speed, &cgc.cmd[4]); ret = pkt_generic_packet(pd, &cgc); if (ret) @@ -809,6 +856,7 @@ static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio) */ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); if (atomic_read(&pd->iosched.attention) == 0) return; @@ -836,7 +884,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) need_write_seek = 0; if (need_write_seek && reads_queued) { if (atomic_read(&pd->cdrw.pending_bios) > 0) { - pkt_dbg(2, pd, "write, waiting\n"); + dev_dbg(ddev, "write, waiting\n"); break; } pkt_flush_cache(pd); @@ -845,7 +893,7 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) } else { if (!reads_queued && writes_queued) { if (atomic_read(&pd->cdrw.pending_bios) > 0) { - pkt_dbg(2, pd, "read, waiting\n"); + dev_dbg(ddev, "read, waiting\n"); break; } pd->iosched.writing = 1; @@ -892,25 +940,27 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd) */ static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q) { - if ((pd->settings.size << 9) / CD_FRAMESIZE - <= queue_max_segments(q)) { + struct device *ddev = disk_to_dev(pd->disk); + + if ((pd->settings.size << 9) / CD_FRAMESIZE <= queue_max_segments(q)) { /* * The cdrom device can handle one segment/frame */ clear_bit(PACKET_MERGE_SEGS, &pd->flags); return 0; - } else if ((pd->settings.size << 9) / PAGE_SIZE - <= queue_max_segments(q)) { + } + + if ((pd->settings.size << 9) / PAGE_SIZE <= queue_max_segments(q)) { /* * We can handle this case at the expense of some extra memory * copies during write operations */ set_bit(PACKET_MERGE_SEGS, &pd->flags); return 0; - } else { - pkt_err(pd, "cdrom max_phys_segments too small\n"); - return -EIO; } + + dev_err(ddev, "cdrom max_phys_segments too small\n"); + return -EIO; } static void pkt_end_io_read(struct bio *bio) @@ -919,9 +969,8 @@ static void pkt_end_io_read(struct bio *bio) struct pktcdvd_device *pd = pkt->pd; BUG_ON(!pd); - pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n", - bio, (unsigned long long)pkt->sector, - (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status); + dev_dbg(disk_to_dev(pd->disk), "bio=%p sec0=%llx sec=%llx err=%d\n", + bio, pkt->sector, bio->bi_iter.bi_sector, bio->bi_status); if (bio->bi_status) atomic_inc(&pkt->io_errors); @@ -939,7 +988,7 @@ static void pkt_end_io_packet_write(struct bio *bio) struct pktcdvd_device *pd = pkt->pd; BUG_ON(!pd); - pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status); + dev_dbg(disk_to_dev(pd->disk), "id=%d, err=%d\n", pkt->id, bio->bi_status); pd->stats.pkt_ended++; @@ -955,6 +1004,7 @@ static void pkt_end_io_packet_write(struct bio *bio) */ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) { + struct device *ddev = disk_to_dev(pd->disk); int frames_read = 0; struct bio *bio; int f; @@ -983,8 +1033,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) spin_unlock(&pkt->lock); if (pkt->cache_valid) { - pkt_dbg(2, pd, "zone %llx cached\n", - (unsigned long long)pkt->sector); + dev_dbg(ddev, "zone %llx cached\n", pkt->sector); goto out_account; } @@ -1005,8 +1054,8 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) p = (f * CD_FRAMESIZE) / PAGE_SIZE; offset = (f * CD_FRAMESIZE) % PAGE_SIZE; - pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n", - f, pkt->pages[p], offset); + dev_dbg(ddev, "Adding frame %d, page:%p offs:%d\n", f, + pkt->pages[p], offset); if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset)) BUG(); @@ -1016,8 +1065,7 @@ static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) } out_account: - pkt_dbg(2, pd, "need %d frames for zone %llx\n", - frames_read, (unsigned long long)pkt->sector); + dev_dbg(ddev, "need %d frames for zone %llx\n", frames_read, pkt->sector); pd->stats.pkt_started++; pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9); } @@ -1051,17 +1099,17 @@ static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *p } } -static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state state) +static inline void pkt_set_state(struct device *ddev, struct packet_data *pkt, + enum packet_data_state state) { -#if PACKET_DEBUG > 1 static const char *state_name[] = { "IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED" }; enum packet_data_state old_state = pkt->state; - pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n", - pkt->id, (unsigned long long)pkt->sector, - state_name[old_state], state_name[state]); -#endif + + dev_dbg(ddev, "pkt %2d : s=%6llx %s -> %s\n", + pkt->id, pkt->sector, state_name[old_state], state_name[state]); + pkt->state = state; } @@ -1071,6 +1119,7 @@ static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state */ static int pkt_handle_queue(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_data *pkt, *p; struct bio *bio = NULL; sector_t zone = 0; /* Suppress gcc warning */ @@ -1080,7 +1129,7 @@ static int pkt_handle_queue(struct pktcdvd_device *pd) atomic_set(&pd->scan_queue, 0); if (list_empty(&pd->cdrw.pkt_free_list)) { - pkt_dbg(2, pd, "no pkt\n"); + dev_dbg(ddev, "no pkt\n"); return 0; } @@ -1117,7 +1166,7 @@ try_next_bio: } spin_unlock(&pd->lock); if (!bio) { - pkt_dbg(2, pd, "no bio\n"); + dev_dbg(ddev, "no bio\n"); return 0; } @@ -1133,12 +1182,13 @@ try_next_bio: * to this packet. */ spin_lock(&pd->lock); - pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone); + dev_dbg(ddev, "looking for zone %llx\n", zone); while ((node = pkt_rbtree_find(pd, zone)) != NULL) { + sector_t tmp = get_zone(node->bio->bi_iter.bi_sector, pd); + bio = node->bio; - pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long) - get_zone(bio->bi_iter.bi_sector, pd)); - if (get_zone(bio->bi_iter.bi_sector, pd) != zone) + dev_dbg(ddev, "found zone=%llx\n", tmp); + if (tmp != zone) break; pkt_rbtree_erase(pd, node); spin_lock(&pkt->lock); @@ -1157,7 +1207,7 @@ try_next_bio: spin_unlock(&pd->lock); pkt->sleep_time = max(PACKET_WAIT_TIME, 1); - pkt_set_state(pkt, PACKET_WAITING_STATE); + pkt_set_state(ddev, pkt, PACKET_WAITING_STATE); atomic_set(&pkt->run_sm, 1); spin_lock(&pd->cdrw.active_list_lock); @@ -1209,6 +1259,7 @@ static void bio_list_copy_data(struct bio *dst, struct bio *src) */ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) { + struct device *ddev = disk_to_dev(pd->disk); int f; bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames, @@ -1225,7 +1276,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset)) BUG(); } - pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt); + dev_dbg(ddev, "vcnt=%d\n", pkt->w_bio->bi_vcnt); /* * Fill-in bvec with data from orig_bios. @@ -1233,11 +1284,10 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) spin_lock(&pkt->lock); bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head); - pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE); + pkt_set_state(ddev, pkt, PACKET_WRITE_WAIT_STATE); spin_unlock(&pkt->lock); - pkt_dbg(2, pd, "Writing %d frames for zone %llx\n", - pkt->write_size, (unsigned long long)pkt->sector); + dev_dbg(ddev, "Writing %d frames for zone %llx\n", pkt->write_size, pkt->sector); if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames)) pkt->cache_valid = 1; @@ -1265,7 +1315,9 @@ static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status) static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt) { - pkt_dbg(2, pd, "pkt %d\n", pkt->id); + struct device *ddev = disk_to_dev(pd->disk); + + dev_dbg(ddev, "pkt %d\n", pkt->id); for (;;) { switch (pkt->state) { @@ -1275,7 +1327,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data pkt->sleep_time = 0; pkt_gather_data(pd, pkt); - pkt_set_state(pkt, PACKET_READ_WAIT_STATE); + pkt_set_state(ddev, pkt, PACKET_READ_WAIT_STATE); break; case PACKET_READ_WAIT_STATE: @@ -1283,7 +1335,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data return; if (atomic_read(&pkt->io_errors) > 0) { - pkt_set_state(pkt, PACKET_RECOVERY_STATE); + pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE); } else { pkt_start_write(pd, pkt); } @@ -1294,15 +1346,15 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data return; if (!pkt->w_bio->bi_status) { - pkt_set_state(pkt, PACKET_FINISHED_STATE); + pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE); } else { - pkt_set_state(pkt, PACKET_RECOVERY_STATE); + pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE); } break; case PACKET_RECOVERY_STATE: - pkt_dbg(2, pd, "No recovery possible\n"); - pkt_set_state(pkt, PACKET_FINISHED_STATE); + dev_dbg(ddev, "No recovery possible\n"); + pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE); break; case PACKET_FINISHED_STATE: @@ -1318,6 +1370,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data static void pkt_handle_packets(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_data *pkt, *next; /* @@ -1338,28 +1391,13 @@ static void pkt_handle_packets(struct pktcdvd_device *pd) if (pkt->state == PACKET_FINISHED_STATE) { list_del(&pkt->list); pkt_put_packet_data(pd, pkt); - pkt_set_state(pkt, PACKET_IDLE_STATE); + pkt_set_state(ddev, pkt, PACKET_IDLE_STATE); atomic_set(&pd->scan_queue, 1); } } spin_unlock(&pd->cdrw.active_list_lock); } -static void pkt_count_states(struct pktcdvd_device *pd, int *states) -{ - struct packet_data *pkt; - int i; - - for (i = 0; i < PACKET_NUM_STATES; i++) - states[i] = 0; - - spin_lock(&pd->cdrw.active_list_lock); - list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { - states[pkt->state]++; - } - spin_unlock(&pd->cdrw.active_list_lock); -} - /* * kcdrwd is woken up when writes have been queued for one of our * registered devices @@ -1367,7 +1405,9 @@ static void pkt_count_states(struct pktcdvd_device *pd, int *states) static int kcdrwd(void *foobar) { struct pktcdvd_device *pd = foobar; + struct device *ddev = disk_to_dev(pd->disk); struct packet_data *pkt; + int states[PACKET_NUM_STATES]; long min_sleep_time, residue; set_user_nice(current, MIN_NICE); @@ -1398,13 +1438,9 @@ static int kcdrwd(void *foobar) goto work_to_do; /* Otherwise, go to sleep */ - if (PACKET_DEBUG > 1) { - int states[PACKET_NUM_STATES]; - pkt_count_states(pd, states); - pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", - states[0], states[1], states[2], - states[3], states[4], states[5]); - } + pkt_count_states(pd, states); + dev_dbg(ddev, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", + states[0], states[1], states[2], states[3], states[4], states[5]); min_sleep_time = MAX_SCHEDULE_TIMEOUT; list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { @@ -1412,9 +1448,9 @@ static int kcdrwd(void *foobar) min_sleep_time = pkt->sleep_time; } - pkt_dbg(2, pd, "sleeping\n"); + dev_dbg(ddev, "sleeping\n"); residue = schedule_timeout(min_sleep_time); - pkt_dbg(2, pd, "wake up\n"); + dev_dbg(ddev, "wake up\n"); /* make swsusp happy with our thread */ try_to_freeze(); @@ -1462,7 +1498,7 @@ work_to_do: static void pkt_print_settings(struct pktcdvd_device *pd) { - pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n", + dev_info(disk_to_dev(pd->disk), "%s packets, %u blocks, Mode-%c disc\n", pd->settings.fp ? "Fixed" : "Variable", pd->settings.size >> 2, pd->settings.block_mode == 8 ? '1' : '2'); @@ -1474,8 +1510,7 @@ static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, cgc->cmd[0] = GPCMD_MODE_SENSE_10; cgc->cmd[2] = page_code | (page_control << 6); - cgc->cmd[7] = cgc->buflen >> 8; - cgc->cmd[8] = cgc->buflen & 0xff; + put_unaligned_be16(cgc->buflen, &cgc->cmd[7]); cgc->data_direction = CGC_DATA_READ; return pkt_generic_packet(pd, cgc); } @@ -1486,8 +1521,7 @@ static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc memset(cgc->buffer, 0, 2); cgc->cmd[0] = GPCMD_MODE_SELECT_10; cgc->cmd[1] = 0x10; /* PF */ - cgc->cmd[7] = cgc->buflen >> 8; - cgc->cmd[8] = cgc->buflen & 0xff; + put_unaligned_be16(cgc->buflen, &cgc->cmd[7]); cgc->data_direction = CGC_DATA_WRITE; return pkt_generic_packet(pd, cgc); } @@ -1528,8 +1562,7 @@ static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ); cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO; cgc.cmd[1] = type & 3; - cgc.cmd[4] = (track & 0xff00) >> 8; - cgc.cmd[5] = track & 0xff; + put_unaligned_be16(track, &cgc.cmd[4]); cgc.cmd[8] = 8; cgc.quiet = 1; @@ -1590,6 +1623,7 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd, */ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; write_param_page *wp; @@ -1609,8 +1643,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) return ret; } - size = 2 + ((buffer[0] << 8) | (buffer[1] & 0xff)); - pd->mode_offset = (buffer[6] << 8) | (buffer[7] & 0xff); + size = 2 + get_unaligned_be16(&buffer[0]); + pd->mode_offset = get_unaligned_be16(&buffer[6]); if (size > sizeof(buffer)) size = sizeof(buffer); @@ -1656,7 +1690,7 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) /* * paranoia */ - pkt_err(pd, "write mode wrong %d\n", wp->data_block_type); + dev_err(ddev, "write mode wrong %d\n", wp->data_block_type); return 1; } wp->packet_size = cpu_to_be32(pd->settings.size >> 2); @@ -1677,6 +1711,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) */ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) { + struct device *ddev = disk_to_dev(pd->disk); + switch (pd->mmc3_profile) { case 0x1a: /* DVD+RW */ case 0x12: /* DVD-RAM */ @@ -1701,7 +1737,7 @@ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) if (ti->rt == 1 && ti->blank == 0) return 1; - pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet); + dev_err(ddev, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet); return 0; } @@ -1710,6 +1746,8 @@ static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) */ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) { + struct device *ddev = disk_to_dev(pd->disk); + switch (pd->mmc3_profile) { case 0x0a: /* CD-RW */ case 0xffff: /* MMC3 not supported */ @@ -1719,8 +1757,7 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) case 0x12: /* DVD-RAM */ return 1; default: - pkt_dbg(2, pd, "Wrong disc profile (%x)\n", - pd->mmc3_profile); + dev_dbg(ddev, "Wrong disc profile (%x)\n", pd->mmc3_profile); return 0; } @@ -1729,22 +1766,22 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) * but i'm not sure, should we leave this to user apps? probably. */ if (di->disc_type == 0xff) { - pkt_notice(pd, "unknown disc - no track?\n"); + dev_notice(ddev, "unknown disc - no track?\n"); return 0; } if (di->disc_type != 0x20 && di->disc_type != 0) { - pkt_err(pd, "wrong disc type (%x)\n", di->disc_type); + dev_err(ddev, "wrong disc type (%x)\n", di->disc_type); return 0; } if (di->erasable == 0) { - pkt_notice(pd, "disc not erasable\n"); + dev_err(ddev, "disc not erasable\n"); return 0; } if (di->border_status == PACKET_SESSION_RESERVED) { - pkt_err(pd, "can't write to last track (reserved)\n"); + dev_err(ddev, "can't write to last track (reserved)\n"); return 0; } @@ -1753,6 +1790,7 @@ static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; unsigned char buf[12]; disc_information di; @@ -1763,14 +1801,14 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) cgc.cmd[0] = GPCMD_GET_CONFIGURATION; cgc.cmd[8] = 8; ret = pkt_generic_packet(pd, &cgc); - pd->mmc3_profile = ret ? 0xffff : buf[6] << 8 | buf[7]; + pd->mmc3_profile = ret ? 0xffff : get_unaligned_be16(&buf[6]); memset(&di, 0, sizeof(disc_information)); memset(&ti, 0, sizeof(track_information)); ret = pkt_get_disc_info(pd, &di); if (ret) { - pkt_err(pd, "failed get_disc\n"); + dev_err(ddev, "failed get_disc\n"); return ret; } @@ -1782,12 +1820,12 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */ ret = pkt_get_track_info(pd, track, 1, &ti); if (ret) { - pkt_err(pd, "failed get_track\n"); + dev_err(ddev, "failed get_track\n"); return ret; } if (!pkt_writable_track(pd, &ti)) { - pkt_err(pd, "can't write to this track\n"); + dev_err(ddev, "can't write to this track\n"); return -EROFS; } @@ -1797,11 +1835,11 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) */ pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2; if (pd->settings.size == 0) { - pkt_notice(pd, "detected zero packet size!\n"); + dev_notice(ddev, "detected zero packet size!\n"); return -ENXIO; } if (pd->settings.size > PACKET_MAX_SECTORS) { - pkt_err(pd, "packet size is too big\n"); + dev_err(ddev, "packet size is too big\n"); return -EROFS; } pd->settings.fp = ti.fp; @@ -1843,7 +1881,7 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) pd->settings.block_mode = PACKET_BLOCK_MODE2; break; default: - pkt_err(pd, "unknown data mode\n"); + dev_err(ddev, "unknown data mode\n"); return -EROFS; } return 0; @@ -1854,6 +1892,7 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) */ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; unsigned char buf[64]; @@ -1880,13 +1919,13 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd) */ buf[pd->mode_offset + 10] |= (set << 2); - cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff)); + cgc.buflen = cgc.cmd[8] = 2 + get_unaligned_be16(&buf[0]); ret = pkt_mode_select(pd, &cgc); if (ret) { - pkt_err(pd, "write caching control failed\n"); + dev_err(ddev, "write caching control failed\n"); pkt_dump_sense(pd, &cgc); } else if (!ret && set) - pkt_notice(pd, "enabled write caching\n"); + dev_notice(ddev, "enabled write caching\n"); return ret; } @@ -1935,12 +1974,12 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd, * Speed Performance Descriptor Block", use the information * in the first block. (contains the highest speed) */ - int num_spdb = (cap_buf[30] << 8) + cap_buf[31]; + int num_spdb = get_unaligned_be16(&cap_buf[30]); if (num_spdb > 0) offset = 34; } - *write_speed = (cap_buf[offset] << 8) | cap_buf[offset + 1]; + *write_speed = get_unaligned_be16(&cap_buf[offset]); return 0; } @@ -1967,6 +2006,7 @@ static char us_clv_to_speed[16] = { static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, unsigned *speed) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; unsigned char buf[64]; @@ -1984,7 +2024,7 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, pkt_dump_sense(pd, &cgc); return ret; } - size = ((unsigned int) buf[0]<<8) + buf[1] + 2; + size = 2 + get_unaligned_be16(&buf[0]); if (size > sizeof(buf)) size = sizeof(buf); @@ -2001,11 +2041,11 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, } if (!(buf[6] & 0x40)) { - pkt_notice(pd, "disc type is not CD-RW\n"); + dev_notice(ddev, "disc type is not CD-RW\n"); return 1; } if (!(buf[6] & 0x4)) { - pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n"); + dev_notice(ddev, "A1 values on media are not valid, maybe not CDRW?\n"); return 1; } @@ -2025,25 +2065,26 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, *speed = us_clv_to_speed[sp]; break; default: - pkt_notice(pd, "unknown disc sub-type %d\n", st); + dev_notice(ddev, "unknown disc sub-type %d\n", st); return 1; } if (*speed) { - pkt_info(pd, "maximum media speed: %d\n", *speed); + dev_info(ddev, "maximum media speed: %d\n", *speed); return 0; } else { - pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st); + dev_notice(ddev, "unknown speed %d for sub-type %d\n", sp, st); return 1; } } static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); struct packet_command cgc; struct scsi_sense_hdr sshdr; int ret; - pkt_dbg(2, pd, "Performing OPC\n"); + dev_dbg(ddev, "Performing OPC\n"); init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); cgc.sshdr = &sshdr; @@ -2058,18 +2099,19 @@ static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd) static int pkt_open_write(struct pktcdvd_device *pd) { + struct device *ddev = disk_to_dev(pd->disk); int ret; unsigned int write_speed, media_write_speed, read_speed; ret = pkt_probe_settings(pd); if (ret) { - pkt_dbg(2, pd, "failed probe\n"); + dev_dbg(ddev, "failed probe\n"); return ret; } ret = pkt_set_write_settings(pd); if (ret) { - pkt_dbg(1, pd, "failed saving write settings\n"); + dev_notice(ddev, "failed saving write settings\n"); return -EIO; } @@ -2082,30 +2124,29 @@ static int pkt_open_write(struct pktcdvd_device *pd) case 0x13: /* DVD-RW */ case 0x1a: /* DVD+RW */ case 0x12: /* DVD-RAM */ - pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed); + dev_notice(ddev, "write speed %ukB/s\n", write_speed); break; default: ret = pkt_media_speed(pd, &media_write_speed); if (ret) media_write_speed = 16; write_speed = min(write_speed, media_write_speed * 177); - pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176); + dev_notice(ddev, "write speed %ux\n", write_speed / 176); break; } read_speed = write_speed; ret = pkt_set_speed(pd, write_speed, read_speed); if (ret) { - pkt_dbg(1, pd, "couldn't set write speed\n"); + dev_notice(ddev, "couldn't set write speed\n"); return -EIO; } pd->write_speed = write_speed; pd->read_speed = read_speed; ret = pkt_perform_opc(pd); - if (ret) { - pkt_dbg(1, pd, "Optimum Power Calibration failed\n"); - } + if (ret) + dev_notice(ddev, "Optimum Power Calibration failed\n"); return 0; } @@ -2113,8 +2154,9 @@ static int pkt_open_write(struct pktcdvd_device *pd) /* * called at open time. */ -static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) +static int pkt_open_dev(struct pktcdvd_device *pd, bool write) { + struct device *ddev = disk_to_dev(pd->disk); int ret; long lba; struct request_queue *q; @@ -2125,7 +2167,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) * to read/write from/to it. It is already opened in O_NONBLOCK mode * so open should not fail. */ - bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd); + bdev = blkdev_get_by_dev(pd->bdev->bd_dev, BLK_OPEN_READ, pd, NULL); if (IS_ERR(bdev)) { ret = PTR_ERR(bdev); goto out; @@ -2133,7 +2175,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) ret = pkt_get_last_written(pd, &lba); if (ret) { - pkt_err(pd, "pkt_get_last_written failed\n"); + dev_err(ddev, "pkt_get_last_written failed\n"); goto out_putdev; } @@ -2162,17 +2204,17 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) if (write) { if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) { - pkt_err(pd, "not enough memory for buffers\n"); + dev_err(ddev, "not enough memory for buffers\n"); ret = -ENOMEM; goto out_putdev; } - pkt_info(pd, "%lukB available on disc\n", lba << 1); + dev_info(ddev, "%lukB available on disc\n", lba << 1); } return 0; out_putdev: - blkdev_put(bdev, FMODE_READ | FMODE_EXCL); + blkdev_put(bdev, pd); out: return ret; } @@ -2183,13 +2225,15 @@ out: */ static void pkt_release_dev(struct pktcdvd_device *pd, int flush) { + struct device *ddev = disk_to_dev(pd->disk); + if (flush && pkt_flush_cache(pd)) - pkt_dbg(1, pd, "not flushing cache\n"); + dev_notice(ddev, "not flushing cache\n"); pkt_lock_door(pd, 0); pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); - blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL); + blkdev_put(pd->bdev, pd); pkt_shrink_pktlist(pd); } @@ -2203,14 +2247,14 @@ static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor) return pkt_devs[dev_minor]; } -static int pkt_open(struct block_device *bdev, fmode_t mode) +static int pkt_open(struct gendisk *disk, blk_mode_t mode) { struct pktcdvd_device *pd = NULL; int ret; mutex_lock(&pktcdvd_mutex); mutex_lock(&ctl_mutex); - pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev)); + pd = pkt_find_dev_from_minor(disk->first_minor); if (!pd) { ret = -ENODEV; goto out; @@ -2219,22 +2263,21 @@ static int pkt_open(struct block_device *bdev, fmode_t mode) pd->refcnt++; if (pd->refcnt > 1) { - if ((mode & FMODE_WRITE) && + if ((mode & BLK_OPEN_WRITE) && !test_bit(PACKET_WRITABLE, &pd->flags)) { ret = -EBUSY; goto out_dec; } } else { - ret = pkt_open_dev(pd, mode & FMODE_WRITE); + ret = pkt_open_dev(pd, mode & BLK_OPEN_WRITE); if (ret) goto out_dec; /* * needed here as well, since ext2 (among others) may change * the blocksize at mount time */ - set_blocksize(bdev, CD_FRAMESIZE); + set_blocksize(disk->part0, CD_FRAMESIZE); } - mutex_unlock(&ctl_mutex); mutex_unlock(&pktcdvd_mutex); return 0; @@ -2247,7 +2290,7 @@ out: return ret; } -static void pkt_close(struct gendisk *disk, fmode_t mode) +static void pkt_release(struct gendisk *disk) { struct pktcdvd_device *pd = disk->private_data; @@ -2385,15 +2428,15 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) static void pkt_submit_bio(struct bio *bio) { struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata; + struct device *ddev = disk_to_dev(pd->disk); struct bio *split; bio = bio_split_to_limits(bio); if (!bio) return; - pkt_dbg(2, pd, "start = %6llx stop = %6llx\n", - (unsigned long long)bio->bi_iter.bi_sector, - (unsigned long long)bio_end_sector(bio)); + dev_dbg(ddev, "start = %6llx stop = %6llx\n", + bio->bi_iter.bi_sector, bio_end_sector(bio)); /* * Clone READ bios so we can have our own bi_end_io callback. @@ -2404,13 +2447,12 @@ static void pkt_submit_bio(struct bio *bio) } if (!test_bit(PACKET_WRITABLE, &pd->flags)) { - pkt_notice(pd, "WRITE for ro device (%llu)\n", - (unsigned long long)bio->bi_iter.bi_sector); + dev_notice(ddev, "WRITE for ro device (%llu)\n", bio->bi_iter.bi_sector); goto end_io; } if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) { - pkt_err(pd, "wrong bio size\n"); + dev_err(ddev, "wrong bio size\n"); goto end_io; } @@ -2446,74 +2488,15 @@ static void pkt_init_queue(struct pktcdvd_device *pd) q->queuedata = pd; } -static int pkt_seq_show(struct seq_file *m, void *p) -{ - struct pktcdvd_device *pd = m->private; - char *msg; - int states[PACKET_NUM_STATES]; - - seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev); - - seq_printf(m, "\nSettings:\n"); - seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2); - - if (pd->settings.write_type == 0) - msg = "Packet"; - else - msg = "Unknown"; - seq_printf(m, "\twrite type:\t\t%s\n", msg); - - seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable"); - seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss); - - seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode); - - if (pd->settings.block_mode == PACKET_BLOCK_MODE1) - msg = "Mode 1"; - else if (pd->settings.block_mode == PACKET_BLOCK_MODE2) - msg = "Mode 2"; - else - msg = "Unknown"; - seq_printf(m, "\tblock mode:\t\t%s\n", msg); - - seq_printf(m, "\nStatistics:\n"); - seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started); - seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended); - seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1); - seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1); - seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1); - - seq_printf(m, "\nMisc:\n"); - seq_printf(m, "\treference count:\t%d\n", pd->refcnt); - seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags); - seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed); - seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed); - seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset); - seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset); - - seq_printf(m, "\nQueue state:\n"); - seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size); - seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios)); - seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", (unsigned long long)pd->current_sector); - - pkt_count_states(pd, states); - seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", - states[0], states[1], states[2], states[3], states[4], states[5]); - - seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n", - pd->write_congestion_off, - pd->write_congestion_on); - return 0; -} - static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) { + struct device *ddev = disk_to_dev(pd->disk); int i; struct block_device *bdev; struct scsi_device *sdev; if (pd->pkt_dev == dev) { - pkt_err(pd, "recursive setup not allowed\n"); + dev_err(ddev, "recursive setup not allowed\n"); return -EBUSY; } for (i = 0; i < MAX_WRITERS; i++) { @@ -2521,21 +2504,22 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) if (!pd2) continue; if (pd2->bdev->bd_dev == dev) { - pkt_err(pd, "%pg already setup\n", pd2->bdev); + dev_err(ddev, "%pg already setup\n", pd2->bdev); return -EBUSY; } if (pd2->pkt_dev == dev) { - pkt_err(pd, "can't chain pktcdvd devices\n"); + dev_err(ddev, "can't chain pktcdvd devices\n"); return -EBUSY; } } - bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL); + bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_NDELAY, NULL, + NULL); if (IS_ERR(bdev)) return PTR_ERR(bdev); sdev = scsi_device_from_queue(bdev->bd_disk->queue); if (!sdev) { - blkdev_put(bdev, FMODE_READ | FMODE_NDELAY); + blkdev_put(bdev, NULL); return -EINVAL; } put_device(&sdev->sdev_gendev); @@ -2549,30 +2533,31 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) pkt_init_queue(pd); atomic_set(&pd->cdrw.pending_bios, 0); - pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name); + pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name); if (IS_ERR(pd->cdrw.thread)) { - pkt_err(pd, "can't start kernel thread\n"); + dev_err(ddev, "can't start kernel thread\n"); goto out_mem; } - proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd); - pkt_dbg(1, pd, "writer mapped to %pg\n", bdev); + proc_create_single_data(pd->disk->disk_name, 0, pkt_proc, pkt_seq_show, pd); + dev_notice(ddev, "writer mapped to %pg\n", bdev); return 0; out_mem: - blkdev_put(bdev, FMODE_READ | FMODE_NDELAY); + blkdev_put(bdev, NULL); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return -ENOMEM; } -static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) +static int pkt_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long arg) { struct pktcdvd_device *pd = bdev->bd_disk->private_data; + struct device *ddev = disk_to_dev(pd->disk); int ret; - pkt_dbg(2, pd, "cmd %x, dev %d:%d\n", - cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); + dev_dbg(ddev, "cmd %x, dev %d:%d\n", cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); mutex_lock(&pktcdvd_mutex); switch (cmd) { @@ -2598,7 +2583,7 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); break; default: - pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd); + dev_dbg(ddev, "Unknown ioctl (%x)\n", cmd); ret = -ENOTTY; } mutex_unlock(&pktcdvd_mutex); @@ -2631,7 +2616,7 @@ static const struct block_device_operations pktcdvd_ops = { .owner = THIS_MODULE, .submit_bio = pkt_submit_bio, .open = pkt_open, - .release = pkt_close, + .release = pkt_release, .ioctl = pkt_ioctl, .compat_ioctl = blkdev_compat_ptr_ioctl, .check_events = pkt_check_events, @@ -2676,7 +2661,6 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) spin_lock_init(&pd->iosched.lock); bio_list_init(&pd->iosched.read_queue); bio_list_init(&pd->iosched.write_queue); - sprintf(pd->name, DRIVER_NAME"%d", idx); init_waitqueue_head(&pd->wqueue); pd->bio_queue = RB_ROOT; @@ -2693,7 +2677,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) disk->minors = 1; disk->fops = &pktcdvd_ops; disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART; - strcpy(disk->disk_name, pd->name); + snprintf(disk->disk_name, sizeof(disk->disk_name), DRIVER_NAME"%d", idx); disk->private_data = pd; pd->pkt_dev = MKDEV(pktdev_major, idx); @@ -2735,6 +2719,7 @@ out_mutex: static int pkt_remove_dev(dev_t pkt_dev) { struct pktcdvd_device *pd; + struct device *ddev; int idx; int ret = 0; @@ -2755,6 +2740,9 @@ static int pkt_remove_dev(dev_t pkt_dev) ret = -EBUSY; goto out; } + + ddev = disk_to_dev(pd->disk); + if (!IS_ERR(pd->cdrw.thread)) kthread_stop(pd->cdrw.thread); @@ -2763,10 +2751,10 @@ static int pkt_remove_dev(dev_t pkt_dev) pkt_debugfs_dev_remove(pd); pkt_sysfs_dev_remove(pd); - blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY); + blkdev_put(pd->bdev, NULL); - remove_proc_entry(pd->name, pkt_proc); - pkt_dbg(1, pd, "writer unmapped\n"); + remove_proc_entry(pd->disk->disk_name, pkt_proc); + dev_notice(ddev, "writer unmapped\n"); del_gendisk(pd->disk); put_disk(pd->disk); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 632751ddb287..bd0e075a5d89 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -660,9 +660,9 @@ static bool pending_result_dec(struct pending_result *pending, int *result) return true; } -static int rbd_open(struct block_device *bdev, fmode_t mode) +static int rbd_open(struct gendisk *disk, blk_mode_t mode) { - struct rbd_device *rbd_dev = bdev->bd_disk->private_data; + struct rbd_device *rbd_dev = disk->private_data; bool removing = false; spin_lock_irq(&rbd_dev->lock); @@ -679,7 +679,7 @@ static int rbd_open(struct block_device *bdev, fmode_t mode) return 0; } -static void rbd_release(struct gendisk *disk, fmode_t mode) +static void rbd_release(struct gendisk *disk) { struct rbd_device *rbd_dev = disk->private_data; unsigned long open_count_before; diff --git a/drivers/block/rnbd/Makefile b/drivers/block/rnbd/Makefile index 40b31630822c..208e5f865497 100644 --- a/drivers/block/rnbd/Makefile +++ b/drivers/block/rnbd/Makefile @@ -3,13 +3,11 @@ ccflags-y := -I$(srctree)/drivers/infiniband/ulp/rtrs rnbd-client-y := rnbd-clt.o \ - rnbd-clt-sysfs.o \ - rnbd-common.o + rnbd-clt-sysfs.o CFLAGS_rnbd-srv-trace.o = -I$(src) -rnbd-server-y := rnbd-common.o \ - rnbd-srv.o \ +rnbd-server-y := rnbd-srv.o \ rnbd-srv-sysfs.o \ rnbd-srv-trace.o diff --git a/drivers/block/rnbd/rnbd-clt-sysfs.c b/drivers/block/rnbd/rnbd-clt-sysfs.c index 8c6087949794..c36d8b1ceeed 100644 --- a/drivers/block/rnbd/rnbd-clt-sysfs.c +++ b/drivers/block/rnbd/rnbd-clt-sysfs.c @@ -24,7 +24,9 @@ #include "rnbd-clt.h" static struct device *rnbd_dev; -static struct class *rnbd_dev_class; +static const struct class rnbd_dev_class = { + .name = "rnbd_client", +}; static struct kobject *rnbd_devs_kobj; enum { @@ -278,7 +280,7 @@ static ssize_t access_mode_show(struct kobject *kobj, dev = container_of(kobj, struct rnbd_clt_dev, kobj); - return sysfs_emit(page, "%s\n", rnbd_access_mode_str(dev->access_mode)); + return sysfs_emit(page, "%s\n", rnbd_access_modes[dev->access_mode].str); } static struct kobj_attribute rnbd_clt_access_mode = @@ -596,7 +598,7 @@ static ssize_t rnbd_clt_map_device_store(struct kobject *kobj, pr_info("Mapping device %s on session %s, (access_mode: %s, nr_poll_queues: %d)\n", pathname, sessname, - rnbd_access_mode_str(access_mode), + rnbd_access_modes[access_mode].str, nr_poll_queues); dev = rnbd_clt_map_device(sessname, paths, path_cnt, port_nr, pathname, @@ -646,11 +648,11 @@ int rnbd_clt_create_sysfs_files(void) { int err; - rnbd_dev_class = class_create("rnbd-client"); - if (IS_ERR(rnbd_dev_class)) - return PTR_ERR(rnbd_dev_class); + err = class_register(&rnbd_dev_class); + if (err) + return err; - rnbd_dev = device_create_with_groups(rnbd_dev_class, NULL, + rnbd_dev = device_create_with_groups(&rnbd_dev_class, NULL, MKDEV(0, 0), NULL, default_attr_groups, "ctl"); if (IS_ERR(rnbd_dev)) { @@ -666,9 +668,9 @@ int rnbd_clt_create_sysfs_files(void) return 0; dev_destroy: - device_destroy(rnbd_dev_class, MKDEV(0, 0)); + device_destroy(&rnbd_dev_class, MKDEV(0, 0)); cls_destroy: - class_destroy(rnbd_dev_class); + class_unregister(&rnbd_dev_class); return err; } @@ -678,6 +680,6 @@ void rnbd_clt_destroy_sysfs_files(void) sysfs_remove_group(&rnbd_dev->kobj, &default_attr_group); kobject_del(rnbd_devs_kobj); kobject_put(rnbd_devs_kobj); - device_destroy(rnbd_dev_class, MKDEV(0, 0)); - class_destroy(rnbd_dev_class); + device_destroy(&rnbd_dev_class, MKDEV(0, 0)); + class_unregister(&rnbd_dev_class); } diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 5eb8c7855970..b0550b68645d 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -921,11 +921,11 @@ rnbd_clt_session *find_or_create_sess(const char *sessname, bool *first) return sess; } -static int rnbd_client_open(struct block_device *block_device, fmode_t mode) +static int rnbd_client_open(struct gendisk *disk, blk_mode_t mode) { - struct rnbd_clt_dev *dev = block_device->bd_disk->private_data; + struct rnbd_clt_dev *dev = disk->private_data; - if (get_disk_ro(dev->gd) && (mode & FMODE_WRITE)) + if (get_disk_ro(dev->gd) && (mode & BLK_OPEN_WRITE)) return -EPERM; if (dev->dev_state == DEV_STATE_UNMAPPED || @@ -935,7 +935,7 @@ static int rnbd_client_open(struct block_device *block_device, fmode_t mode) return 0; } -static void rnbd_client_release(struct gendisk *gen, fmode_t mode) +static void rnbd_client_release(struct gendisk *gen) { struct rnbd_clt_dev *dev = gen->private_data; diff --git a/drivers/block/rnbd/rnbd-common.c b/drivers/block/rnbd/rnbd-common.c deleted file mode 100644 index 596c3f732403..000000000000 --- a/drivers/block/rnbd/rnbd-common.c +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RDMA Network Block Driver - * - * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. - * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. - * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. - */ -#include "rnbd-proto.h" - -const char *rnbd_access_mode_str(enum rnbd_access_mode mode) -{ - switch (mode) { - case RNBD_ACCESS_RO: - return "ro"; - case RNBD_ACCESS_RW: - return "rw"; - case RNBD_ACCESS_MIGRATION: - return "migration"; - default: - return "unknown"; - } -} diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h index da1d0542d7e2..e32f8f2c868a 100644 --- a/drivers/block/rnbd/rnbd-proto.h +++ b/drivers/block/rnbd/rnbd-proto.h @@ -61,6 +61,15 @@ enum rnbd_access_mode { RNBD_ACCESS_MIGRATION, }; +static const __maybe_unused struct { + enum rnbd_access_mode mode; + const char *str; +} rnbd_access_modes[] = { + [RNBD_ACCESS_RO] = {RNBD_ACCESS_RO, "ro"}, + [RNBD_ACCESS_RW] = {RNBD_ACCESS_RW, "rw"}, + [RNBD_ACCESS_MIGRATION] = {RNBD_ACCESS_MIGRATION, "migration"}, +}; + /** * struct rnbd_msg_sess_info - initial session info from client to server * @hdr: message header @@ -185,7 +194,6 @@ struct rnbd_msg_io { enum rnbd_io_flags { /* Operations */ - RNBD_OP_READ = 0, RNBD_OP_WRITE = 1, RNBD_OP_FLUSH = 2, @@ -193,15 +201,9 @@ enum rnbd_io_flags { RNBD_OP_SECURE_ERASE = 4, RNBD_OP_WRITE_SAME = 5, - RNBD_OP_LAST, - /* Flags */ - RNBD_F_SYNC = 1<<(RNBD_OP_BITS + 0), RNBD_F_FUA = 1<<(RNBD_OP_BITS + 1), - - RNBD_F_ALL = (RNBD_F_SYNC | RNBD_F_FUA) - }; static inline u32 rnbd_op(u32 flags) @@ -214,21 +216,6 @@ static inline u32 rnbd_flags(u32 flags) return flags & ~RNBD_OP_MASK; } -static inline bool rnbd_flags_supported(u32 flags) -{ - u32 op; - - op = rnbd_op(flags); - flags = rnbd_flags(flags); - - if (op >= RNBD_OP_LAST) - return false; - if (flags & ~RNBD_F_ALL) - return false; - - return true; -} - static inline blk_opf_t rnbd_to_bio_flags(u32 rnbd_opf) { blk_opf_t bio_opf; diff --git a/drivers/block/rnbd/rnbd-srv-sysfs.c b/drivers/block/rnbd/rnbd-srv-sysfs.c index d5d9267e1fa5..cba6ba43c2c2 100644 --- a/drivers/block/rnbd/rnbd-srv-sysfs.c +++ b/drivers/block/rnbd/rnbd-srv-sysfs.c @@ -9,7 +9,6 @@ #undef pr_fmt #define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt -#include <uapi/linux/limits.h> #include <linux/kobject.h> #include <linux/sysfs.h> #include <linux/stat.h> @@ -20,7 +19,9 @@ #include "rnbd-srv.h" static struct device *rnbd_dev; -static struct class *rnbd_dev_class; +static const struct class rnbd_dev_class = { + .name = "rnbd-server", +}; static struct kobject *rnbd_devs_kobj; static void rnbd_srv_dev_release(struct kobject *kobj) @@ -88,8 +89,7 @@ static ssize_t read_only_show(struct kobject *kobj, struct kobj_attribute *attr, sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj); - return sysfs_emit(page, "%d\n", - !(sess_dev->open_flags & FMODE_WRITE)); + return sysfs_emit(page, "%d\n", sess_dev->readonly); } static struct kobj_attribute rnbd_srv_dev_session_ro_attr = @@ -104,7 +104,7 @@ static ssize_t access_mode_show(struct kobject *kobj, sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj); return sysfs_emit(page, "%s\n", - rnbd_access_mode_str(sess_dev->access_mode)); + rnbd_access_modes[sess_dev->access_mode].str); } static struct kobj_attribute rnbd_srv_dev_session_access_mode_attr = @@ -215,12 +215,12 @@ int rnbd_srv_create_sysfs_files(void) { int err; - rnbd_dev_class = class_create("rnbd-server"); - if (IS_ERR(rnbd_dev_class)) - return PTR_ERR(rnbd_dev_class); + err = class_register(&rnbd_dev_class); + if (err) + return err; - rnbd_dev = device_create(rnbd_dev_class, NULL, - MKDEV(0, 0), NULL, "ctl"); + rnbd_dev = device_create(&rnbd_dev_class, NULL, + MKDEV(0, 0), NULL, "ctl"); if (IS_ERR(rnbd_dev)) { err = PTR_ERR(rnbd_dev); goto cls_destroy; @@ -234,9 +234,9 @@ int rnbd_srv_create_sysfs_files(void) return 0; dev_destroy: - device_destroy(rnbd_dev_class, MKDEV(0, 0)); + device_destroy(&rnbd_dev_class, MKDEV(0, 0)); cls_destroy: - class_destroy(rnbd_dev_class); + class_unregister(&rnbd_dev_class); return err; } @@ -245,6 +245,6 @@ void rnbd_srv_destroy_sysfs_files(void) { kobject_del(rnbd_devs_kobj); kobject_put(rnbd_devs_kobj); - device_destroy(rnbd_dev_class, MKDEV(0, 0)); - class_destroy(rnbd_dev_class); + device_destroy(&rnbd_dev_class, MKDEV(0, 0)); + class_unregister(&rnbd_dev_class); } diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 2cfed2e58d64..c186df0ec641 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -96,7 +96,7 @@ rnbd_get_sess_dev(int dev_id, struct rnbd_srv_session *srv_sess) ret = kref_get_unless_zero(&sess_dev->kref); rcu_read_unlock(); - if (!sess_dev || !ret) + if (!ret) return ERR_PTR(-ENXIO); return sess_dev; @@ -180,7 +180,7 @@ static void destroy_device(struct kref *kref) WARN_ONCE(!list_empty(&dev->sess_dev_list), "Device %s is being destroyed but still in use!\n", - dev->id); + dev->name); spin_lock(&dev_lock); list_del(&dev->list); @@ -219,10 +219,10 @@ void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id) rnbd_put_sess_dev(sess_dev); wait_for_completion(&dc); /* wait for inflights to drop to zero */ - blkdev_put(sess_dev->bdev, sess_dev->open_flags); + blkdev_put(sess_dev->bdev, NULL); mutex_lock(&sess_dev->dev->lock); list_del(&sess_dev->dev_list); - if (sess_dev->open_flags & FMODE_WRITE) + if (!sess_dev->readonly) sess_dev->dev->open_write_cnt--; mutex_unlock(&sess_dev->dev->lock); @@ -356,7 +356,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, const void *msg, size_t len, void *data, size_t datalen); -static int process_msg_sess_info(struct rnbd_srv_session *srv_sess, +static void process_msg_sess_info(struct rnbd_srv_session *srv_sess, const void *msg, size_t len, void *data, size_t datalen); @@ -384,8 +384,7 @@ static int rnbd_srv_rdma_ev(void *priv, struct rtrs_srv_op *id, ret = process_msg_open(srv_sess, usr, usrlen, data, datalen); break; case RNBD_MSG_SESS_INFO: - ret = process_msg_sess_info(srv_sess, usr, usrlen, data, - datalen); + process_msg_sess_info(srv_sess, usr, usrlen, data, datalen); break; default: pr_warn("Received unexpected message type %d from session %s\n", @@ -431,7 +430,7 @@ static struct rnbd_srv_dev *rnbd_srv_init_srv_dev(struct block_device *bdev) if (!dev) return ERR_PTR(-ENOMEM); - snprintf(dev->id, sizeof(dev->id), "%pg", bdev); + snprintf(dev->name, sizeof(dev->name), "%pg", bdev); kref_init(&dev->kref); INIT_LIST_HEAD(&dev->sess_dev_list); mutex_init(&dev->lock); @@ -446,7 +445,7 @@ rnbd_srv_find_or_add_srv_dev(struct rnbd_srv_dev *new_dev) spin_lock(&dev_lock); list_for_each_entry(dev, &dev_list, list) { - if (!strncmp(dev->id, new_dev->id, sizeof(dev->id))) { + if (!strncmp(dev->name, new_dev->name, sizeof(dev->name))) { if (!kref_get_unless_zero(&dev->kref)) /* * We lost the race, device is almost dead. @@ -467,39 +466,38 @@ static int rnbd_srv_check_update_open_perm(struct rnbd_srv_dev *srv_dev, struct rnbd_srv_session *srv_sess, enum rnbd_access_mode access_mode) { - int ret = -EPERM; + int ret = 0; mutex_lock(&srv_dev->lock); switch (access_mode) { case RNBD_ACCESS_RO: - ret = 0; break; case RNBD_ACCESS_RW: if (srv_dev->open_write_cnt == 0) { srv_dev->open_write_cnt++; - ret = 0; } else { pr_err("Mapping device '%s' for session %s with RW permissions failed. Device already opened as 'RW' by %d client(s), access mode %s.\n", - srv_dev->id, srv_sess->sessname, + srv_dev->name, srv_sess->sessname, srv_dev->open_write_cnt, - rnbd_access_mode_str(access_mode)); + rnbd_access_modes[access_mode].str); + ret = -EPERM; } break; case RNBD_ACCESS_MIGRATION: if (srv_dev->open_write_cnt < 2) { srv_dev->open_write_cnt++; - ret = 0; } else { pr_err("Mapping device '%s' for session %s with migration permissions failed. Device already opened as 'RW' by %d client(s), access mode %s.\n", - srv_dev->id, srv_sess->sessname, + srv_dev->name, srv_sess->sessname, srv_dev->open_write_cnt, - rnbd_access_mode_str(access_mode)); + rnbd_access_modes[access_mode].str); + ret = -EPERM; } break; default: pr_err("Received mapping request for device '%s' on session %s with invalid access mode: %d\n", - srv_dev->id, srv_sess->sessname, access_mode); + srv_dev->name, srv_sess->sessname, access_mode); ret = -EINVAL; } @@ -561,7 +559,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, static struct rnbd_srv_sess_dev * rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess, const struct rnbd_msg_open *open_msg, - struct block_device *bdev, fmode_t open_flags, + struct block_device *bdev, bool readonly, struct rnbd_srv_dev *srv_dev) { struct rnbd_srv_sess_dev *sdev = rnbd_sess_dev_alloc(srv_sess); @@ -576,7 +574,7 @@ rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess, sdev->bdev = bdev; sdev->sess = srv_sess; sdev->dev = srv_dev; - sdev->open_flags = open_flags; + sdev->readonly = readonly; sdev->access_mode = open_msg->access_mode; return sdev; @@ -631,7 +629,7 @@ static char *rnbd_srv_get_full_path(struct rnbd_srv_session *srv_sess, return full_path; } -static int process_msg_sess_info(struct rnbd_srv_session *srv_sess, +static void process_msg_sess_info(struct rnbd_srv_session *srv_sess, const void *msg, size_t len, void *data, size_t datalen) { @@ -644,8 +642,6 @@ static int process_msg_sess_info(struct rnbd_srv_session *srv_sess, rsp->hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO_RSP); rsp->ver = srv_sess->ver; - - return 0; } /** @@ -681,15 +677,14 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, struct rnbd_srv_sess_dev *srv_sess_dev; const struct rnbd_msg_open *open_msg = msg; struct block_device *bdev; - fmode_t open_flags; + blk_mode_t open_flags = BLK_OPEN_READ; char *full_path; struct rnbd_msg_open_rsp *rsp = data; trace_process_msg_open(srv_sess, open_msg); - open_flags = FMODE_READ; if (open_msg->access_mode != RNBD_ACCESS_RO) - open_flags |= FMODE_WRITE; + open_flags |= BLK_OPEN_WRITE; mutex_lock(&srv_sess->lock); @@ -719,7 +714,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, goto reject; } - bdev = blkdev_get_by_path(full_path, open_flags, THIS_MODULE); + bdev = blkdev_get_by_path(full_path, open_flags, NULL, NULL); if (IS_ERR(bdev)) { ret = PTR_ERR(bdev); pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %d\n", @@ -736,9 +731,9 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, goto blkdev_put; } - srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg, - bdev, open_flags, - srv_dev); + srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg, bdev, + open_msg->access_mode == RNBD_ACCESS_RO, + srv_dev); if (IS_ERR(srv_sess_dev)) { pr_err("Opening device '%s' on session %s failed, creating sess_dev failed, err: %ld\n", full_path, srv_sess->sessname, PTR_ERR(srv_sess_dev)); @@ -774,7 +769,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, list_add(&srv_sess_dev->dev_list, &srv_dev->sess_dev_list); mutex_unlock(&srv_dev->lock); - rnbd_srv_info(srv_sess_dev, "Opened device '%s'\n", srv_dev->id); + rnbd_srv_info(srv_sess_dev, "Opened device '%s'\n", srv_dev->name); kfree(full_path); @@ -795,7 +790,7 @@ srv_dev_put: } rnbd_put_srv_dev(srv_dev); blkdev_put: - blkdev_put(bdev, open_flags); + blkdev_put(bdev, NULL); free_path: kfree(full_path); reject: @@ -808,7 +803,7 @@ static struct rtrs_srv_ctx *rtrs_ctx; static struct rtrs_srv_ops rtrs_ops; static int __init rnbd_srv_init_module(void) { - int err; + int err = 0; BUILD_BUG_ON(sizeof(struct rnbd_msg_hdr) != 4); BUILD_BUG_ON(sizeof(struct rnbd_msg_sess_info) != 36); @@ -822,19 +817,17 @@ static int __init rnbd_srv_init_module(void) }; rtrs_ctx = rtrs_srv_open(&rtrs_ops, port_nr); if (IS_ERR(rtrs_ctx)) { - err = PTR_ERR(rtrs_ctx); pr_err("rtrs_srv_open(), err: %d\n", err); - return err; + return PTR_ERR(rtrs_ctx); } err = rnbd_srv_create_sysfs_files(); if (err) { pr_err("rnbd_srv_create_sysfs_files(), err: %d\n", err); rtrs_srv_close(rtrs_ctx); - return err; } - return 0; + return err; } static void __exit rnbd_srv_cleanup_module(void) diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h index f5962fd31d62..1027656dedb0 100644 --- a/drivers/block/rnbd/rnbd-srv.h +++ b/drivers/block/rnbd/rnbd-srv.h @@ -35,7 +35,7 @@ struct rnbd_srv_dev { struct kobject dev_kobj; struct kobject *dev_sessions_kobj; struct kref kref; - char id[NAME_MAX]; + char name[NAME_MAX]; /* List of rnbd_srv_sess_dev structs */ struct list_head sess_dev_list; struct mutex lock; @@ -52,7 +52,7 @@ struct rnbd_srv_sess_dev { struct kobject kobj; u32 device_id; bool keep_id; - fmode_t open_flags; + bool readonly; struct kref kref; struct completion *destroy_comp; char pathname[NAME_MAX]; diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 9fa821fa76b0..7bf4b48e2282 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -139,7 +139,7 @@ static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo) * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD. * Needed to be able to install inside an ldom from an iso image. */ -static int vdc_ioctl(struct block_device *bdev, fmode_t mode, +static int vdc_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned command, unsigned long argument) { struct vdc_port *port = bdev->bd_disk->private_data; diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 42b4b6828690..f85b6af414b4 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -608,20 +608,18 @@ static void setup_medium(struct floppy_state *fs) } } -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - struct floppy_state *fs = bdev->bd_disk->private_data; + struct floppy_state *fs = disk->private_data; struct swim __iomem *base = fs->swd->base; int err; - if (fs->ref_count == -1 || (fs->ref_count && mode & FMODE_EXCL)) + if (fs->ref_count == -1 || (fs->ref_count && mode & BLK_OPEN_EXCL)) return -EBUSY; - - if (mode & FMODE_EXCL) + if (mode & BLK_OPEN_EXCL) fs->ref_count = -1; else fs->ref_count++; - swim_write(base, setup, S_IBM_DRIVE | S_FCLK_DIV2); udelay(10); swim_drive(base, fs->location); @@ -636,13 +634,13 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) set_capacity(fs->disk, fs->total_secs); - if (mode & FMODE_NDELAY) + if (mode & BLK_OPEN_NDELAY) return 0; - if (mode & (FMODE_READ|FMODE_WRITE)) { - if (bdev_check_media_change(bdev) && fs->disk_in) + if (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE)) { + if (disk_check_media_change(disk) && fs->disk_in) fs->ejected = 0; - if ((mode & FMODE_WRITE) && fs->write_protected) { + if ((mode & BLK_OPEN_WRITE) && fs->write_protected) { err = -EROFS; goto out; } @@ -659,18 +657,18 @@ out: return err; } -static int floppy_unlocked_open(struct block_device *bdev, fmode_t mode) +static int floppy_unlocked_open(struct gendisk *disk, blk_mode_t mode) { int ret; mutex_lock(&swim_mutex); - ret = floppy_open(bdev, mode); + ret = floppy_open(disk, mode); mutex_unlock(&swim_mutex); return ret; } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { struct floppy_state *fs = disk->private_data; struct swim __iomem *base = fs->swd->base; @@ -686,7 +684,7 @@ static void floppy_release(struct gendisk *disk, fmode_t mode) mutex_unlock(&swim_mutex); } -static int floppy_ioctl(struct block_device *bdev, fmode_t mode, +static int floppy_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { struct floppy_state *fs = bdev->bd_disk->private_data; diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index da811a7da03f..dc43a63b3469 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -246,10 +246,9 @@ static int grab_drive(struct floppy_state *fs, enum swim_state state, int interruptible); static void release_drive(struct floppy_state *fs); static int fd_eject(struct floppy_state *fs); -static int floppy_ioctl(struct block_device *bdev, fmode_t mode, +static int floppy_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param); -static int floppy_open(struct block_device *bdev, fmode_t mode); -static void floppy_release(struct gendisk *disk, fmode_t mode); +static int floppy_open(struct gendisk *disk, blk_mode_t mode); static unsigned int floppy_check_events(struct gendisk *disk, unsigned int clearing); static int floppy_revalidate(struct gendisk *disk); @@ -883,7 +882,7 @@ static int fd_eject(struct floppy_state *fs) static struct floppy_struct floppy_type = { 2880,18,2,80,0,0x1B,0x00,0xCF,0x6C,NULL }; /* 7 1.44MB 3.5" */ -static int floppy_locked_ioctl(struct block_device *bdev, fmode_t mode, +static int floppy_locked_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { struct floppy_state *fs = bdev->bd_disk->private_data; @@ -911,7 +910,7 @@ static int floppy_locked_ioctl(struct block_device *bdev, fmode_t mode, return -ENOTTY; } -static int floppy_ioctl(struct block_device *bdev, fmode_t mode, +static int floppy_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long param) { int ret; @@ -923,9 +922,9 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode, return ret; } -static int floppy_open(struct block_device *bdev, fmode_t mode) +static int floppy_open(struct gendisk *disk, blk_mode_t mode) { - struct floppy_state *fs = bdev->bd_disk->private_data; + struct floppy_state *fs = disk->private_data; struct swim3 __iomem *sw = fs->swim3; int n, err = 0; @@ -958,18 +957,18 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) swim3_action(fs, SETMFM); swim3_select(fs, RELAX); - } else if (fs->ref_count == -1 || mode & FMODE_EXCL) + } else if (fs->ref_count == -1 || mode & BLK_OPEN_EXCL) return -EBUSY; - if (err == 0 && (mode & FMODE_NDELAY) == 0 - && (mode & (FMODE_READ|FMODE_WRITE))) { - if (bdev_check_media_change(bdev)) - floppy_revalidate(bdev->bd_disk); + if (err == 0 && !(mode & BLK_OPEN_NDELAY) && + (mode & (BLK_OPEN_READ | BLK_OPEN_WRITE))) { + if (disk_check_media_change(disk)) + floppy_revalidate(disk); if (fs->ejected) err = -ENXIO; } - if (err == 0 && (mode & FMODE_WRITE)) { + if (err == 0 && (mode & BLK_OPEN_WRITE)) { if (fs->write_prot < 0) fs->write_prot = swim3_readbit(fs, WRITE_PROT); if (fs->write_prot) @@ -985,7 +984,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) return err; } - if (mode & FMODE_EXCL) + if (mode & BLK_OPEN_EXCL) fs->ref_count = -1; else ++fs->ref_count; @@ -993,18 +992,18 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) return 0; } -static int floppy_unlocked_open(struct block_device *bdev, fmode_t mode) +static int floppy_unlocked_open(struct gendisk *disk, blk_mode_t mode) { int ret; mutex_lock(&swim3_mutex); - ret = floppy_open(bdev, mode); + ret = floppy_open(disk, mode); mutex_unlock(&swim3_mutex); return ret; } -static void floppy_release(struct gendisk *disk, fmode_t mode) +static void floppy_release(struct gendisk *disk) { struct floppy_state *fs = disk->private_data; struct swim3 __iomem *sw = fs->swim3; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 33d3298a0da1..1c823750c95a 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -43,6 +43,7 @@ #include <asm/page.h> #include <linux/task_work.h> #include <linux/namei.h> +#include <linux/kref.h> #include <uapi/linux/ublk_cmd.h> #define UBLK_MINORS (1U << MINORBITS) @@ -54,7 +55,8 @@ | UBLK_F_USER_RECOVERY \ | UBLK_F_USER_RECOVERY_REISSUE \ | UBLK_F_UNPRIVILEGED_DEV \ - | UBLK_F_CMD_IOCTL_ENCODE) + | UBLK_F_CMD_IOCTL_ENCODE \ + | UBLK_F_USER_COPY) /* All UBLK_PARAM_TYPE_* should be included here */ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | \ @@ -62,7 +64,8 @@ struct ublk_rq_data { struct llist_node node; - struct callback_head work; + + struct kref ref; }; struct ublk_uring_cmd_pdu { @@ -182,8 +185,13 @@ struct ublk_params_header { __u32 types; }; +static inline void __ublk_complete_rq(struct request *req); +static void ublk_complete_rq(struct kref *ref); + static dev_t ublk_chr_devt; -static struct class *ublk_chr_class; +static const struct class ublk_chr_class = { + .name = "ublk-char", +}; static DEFINE_IDR(ublk_index_idr); static DEFINE_SPINLOCK(ublk_idr_lock); @@ -202,6 +210,23 @@ static unsigned int ublks_added; /* protected by ublk_ctl_mutex */ static struct miscdevice ublk_misc; +static inline unsigned ublk_pos_to_hwq(loff_t pos) +{ + return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_QID_OFF) & + UBLK_QID_BITS_MASK; +} + +static inline unsigned ublk_pos_to_buf_off(loff_t pos) +{ + return (pos - UBLKSRV_IO_BUF_OFFSET) & UBLK_IO_BUF_BITS_MASK; +} + +static inline unsigned ublk_pos_to_tag(loff_t pos) +{ + return ((pos - UBLKSRV_IO_BUF_OFFSET) >> UBLK_TAG_OFF) & + UBLK_TAG_BITS_MASK; +} + static void ublk_dev_param_basic_apply(struct ublk_device *ub) { struct request_queue *q = ub->ub_disk->queue; @@ -290,12 +315,52 @@ static int ublk_apply_params(struct ublk_device *ub) return 0; } -static inline bool ublk_can_use_task_work(const struct ublk_queue *ubq) +static inline bool ublk_support_user_copy(const struct ublk_queue *ubq) { - if (IS_BUILTIN(CONFIG_BLK_DEV_UBLK) && - !(ubq->flags & UBLK_F_URING_CMD_COMP_IN_TASK)) - return true; - return false; + return ubq->flags & UBLK_F_USER_COPY; +} + +static inline bool ublk_need_req_ref(const struct ublk_queue *ubq) +{ + /* + * read()/write() is involved in user copy, so request reference + * has to be grabbed + */ + return ublk_support_user_copy(ubq); +} + +static inline void ublk_init_req_ref(const struct ublk_queue *ubq, + struct request *req) +{ + if (ublk_need_req_ref(ubq)) { + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + kref_init(&data->ref); + } +} + +static inline bool ublk_get_req_ref(const struct ublk_queue *ubq, + struct request *req) +{ + if (ublk_need_req_ref(ubq)) { + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + return kref_get_unless_zero(&data->ref); + } + + return true; +} + +static inline void ublk_put_req_ref(const struct ublk_queue *ubq, + struct request *req) +{ + if (ublk_need_req_ref(ubq)) { + struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); + + kref_put(&data->ref, ublk_complete_rq); + } else { + __ublk_complete_rq(req); + } } static inline bool ublk_need_get_data(const struct ublk_queue *ubq) @@ -384,9 +449,9 @@ static void ublk_store_owner_uid_gid(unsigned int *owner_uid, *owner_gid = from_kgid(&init_user_ns, gid); } -static int ublk_open(struct block_device *bdev, fmode_t mode) +static int ublk_open(struct gendisk *disk, blk_mode_t mode) { - struct ublk_device *ub = bdev->bd_disk->private_data; + struct ublk_device *ub = disk->private_data; if (capable(CAP_SYS_ADMIN)) return 0; @@ -421,49 +486,39 @@ static const struct block_device_operations ub_fops = { #define UBLK_MAX_PIN_PAGES 32 -struct ublk_map_data { - const struct request *rq; - unsigned long ubuf; - unsigned int len; -}; - struct ublk_io_iter { struct page *pages[UBLK_MAX_PIN_PAGES]; - unsigned pg_off; /* offset in the 1st page in pages */ - int nr_pages; /* how many page pointers in pages */ struct bio *bio; struct bvec_iter iter; }; -static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data, - unsigned max_bytes, bool to_vm) +/* return how many pages are copied */ +static void ublk_copy_io_pages(struct ublk_io_iter *data, + size_t total, size_t pg_off, int dir) { - const unsigned total = min_t(unsigned, max_bytes, - PAGE_SIZE - data->pg_off + - ((data->nr_pages - 1) << PAGE_SHIFT)); unsigned done = 0; unsigned pg_idx = 0; while (done < total) { struct bio_vec bv = bio_iter_iovec(data->bio, data->iter); - const unsigned int bytes = min3(bv.bv_len, total - done, - (unsigned)(PAGE_SIZE - data->pg_off)); + unsigned int bytes = min3(bv.bv_len, (unsigned)total - done, + (unsigned)(PAGE_SIZE - pg_off)); void *bv_buf = bvec_kmap_local(&bv); void *pg_buf = kmap_local_page(data->pages[pg_idx]); - if (to_vm) - memcpy(pg_buf + data->pg_off, bv_buf, bytes); + if (dir == ITER_DEST) + memcpy(pg_buf + pg_off, bv_buf, bytes); else - memcpy(bv_buf, pg_buf + data->pg_off, bytes); + memcpy(bv_buf, pg_buf + pg_off, bytes); kunmap_local(pg_buf); kunmap_local(bv_buf); /* advance page array */ - data->pg_off += bytes; - if (data->pg_off == PAGE_SIZE) { + pg_off += bytes; + if (pg_off == PAGE_SIZE) { pg_idx += 1; - data->pg_off = 0; + pg_off = 0; } done += bytes; @@ -477,41 +532,58 @@ static inline unsigned ublk_copy_io_pages(struct ublk_io_iter *data, data->iter = data->bio->bi_iter; } } +} - return done; +static bool ublk_advance_io_iter(const struct request *req, + struct ublk_io_iter *iter, unsigned int offset) +{ + struct bio *bio = req->bio; + + for_each_bio(bio) { + if (bio->bi_iter.bi_size > offset) { + iter->bio = bio; + iter->iter = bio->bi_iter; + bio_advance_iter(iter->bio, &iter->iter, offset); + return true; + } + offset -= bio->bi_iter.bi_size; + } + return false; } -static int ublk_copy_user_pages(struct ublk_map_data *data, bool to_vm) +/* + * Copy data between request pages and io_iter, and 'offset' + * is the start point of linear offset of request. + */ +static size_t ublk_copy_user_pages(const struct request *req, + unsigned offset, struct iov_iter *uiter, int dir) { - const unsigned int gup_flags = to_vm ? FOLL_WRITE : 0; - const unsigned long start_vm = data->ubuf; - unsigned int done = 0; - struct ublk_io_iter iter = { - .pg_off = start_vm & (PAGE_SIZE - 1), - .bio = data->rq->bio, - .iter = data->rq->bio->bi_iter, - }; - const unsigned int nr_pages = round_up(data->len + - (start_vm & (PAGE_SIZE - 1)), PAGE_SIZE) >> PAGE_SHIFT; - - while (done < nr_pages) { - const unsigned to_pin = min_t(unsigned, UBLK_MAX_PIN_PAGES, - nr_pages - done); - unsigned i, len; - - iter.nr_pages = get_user_pages_fast(start_vm + - (done << PAGE_SHIFT), to_pin, gup_flags, - iter.pages); - if (iter.nr_pages <= 0) - return done == 0 ? iter.nr_pages : done; - len = ublk_copy_io_pages(&iter, data->len, to_vm); - for (i = 0; i < iter.nr_pages; i++) { - if (to_vm) + struct ublk_io_iter iter; + size_t done = 0; + + if (!ublk_advance_io_iter(req, &iter, offset)) + return 0; + + while (iov_iter_count(uiter) && iter.bio) { + unsigned nr_pages; + ssize_t len; + size_t off; + int i; + + len = iov_iter_get_pages2(uiter, iter.pages, + iov_iter_count(uiter), + UBLK_MAX_PIN_PAGES, &off); + if (len <= 0) + return done; + + ublk_copy_io_pages(&iter, len, off, dir); + nr_pages = DIV_ROUND_UP(len + off, PAGE_SIZE); + for (i = 0; i < nr_pages; i++) { + if (dir == ITER_DEST) set_page_dirty(iter.pages[i]); put_page(iter.pages[i]); } - data->len -= len; - done += iter.nr_pages; + done += len; } return done; @@ -532,21 +604,23 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req, { const unsigned int rq_bytes = blk_rq_bytes(req); + if (ublk_support_user_copy(ubq)) + return rq_bytes; + /* * no zero copy, we delay copy WRITE request data into ublksrv * context and the big benefit is that pinning pages in current * context is pretty fast, see ublk_pin_user_pages */ if (ublk_need_map_req(req)) { - struct ublk_map_data data = { - .rq = req, - .ubuf = io->addr, - .len = rq_bytes, - }; + struct iov_iter iter; + struct iovec iov; + const int dir = ITER_DEST; - ublk_copy_user_pages(&data, true); + import_single_range(dir, u64_to_user_ptr(io->addr), rq_bytes, + &iov, &iter); - return rq_bytes - data.len; + return ublk_copy_user_pages(req, 0, &iter, dir); } return rq_bytes; } @@ -557,18 +631,19 @@ static int ublk_unmap_io(const struct ublk_queue *ubq, { const unsigned int rq_bytes = blk_rq_bytes(req); + if (ublk_support_user_copy(ubq)) + return rq_bytes; + if (ublk_need_unmap_req(req)) { - struct ublk_map_data data = { - .rq = req, - .ubuf = io->addr, - .len = io->res, - }; + struct iov_iter iter; + struct iovec iov; + const int dir = ITER_SOURCE; WARN_ON_ONCE(io->res > rq_bytes); - ublk_copy_user_pages(&data, false); - - return io->res - data.len; + import_single_range(dir, u64_to_user_ptr(io->addr), io->res, + &iov, &iter); + return ublk_copy_user_pages(req, 0, &iter, dir); } return rq_bytes; } @@ -648,13 +723,19 @@ static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq) } /* todo: handle partial completion */ -static void ublk_complete_rq(struct request *req) +static inline void __ublk_complete_rq(struct request *req) { struct ublk_queue *ubq = req->mq_hctx->driver_data; struct ublk_io *io = &ubq->ios[req->tag]; unsigned int unmapped_bytes; blk_status_t res = BLK_STS_OK; + /* called from ublk_abort_queue() code path */ + if (io->flags & UBLK_IO_FLAG_ABORTED) { + res = BLK_STS_IOERR; + goto exit; + } + /* failed read IO if nothing is read */ if (!io->res && req_op(req) == REQ_OP_READ) io->res = -EIO; @@ -694,6 +775,15 @@ exit: blk_mq_end_request(req, res); } +static void ublk_complete_rq(struct kref *ref) +{ + struct ublk_rq_data *data = container_of(ref, struct ublk_rq_data, + ref); + struct request *req = blk_mq_rq_from_pdu(data); + + __ublk_complete_rq(req); +} + /* * Since __ublk_rq_task_work always fails requests immediately during * exiting, __ublk_fail_req() is only called from abort context during @@ -712,7 +802,7 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, if (ublk_queue_can_use_recovery_reissue(ubq)) blk_mq_requeue_request(req, false); else - blk_mq_end_request(req, BLK_STS_IOERR); + ublk_put_req_ref(ubq, req); } } @@ -821,6 +911,7 @@ static inline void __ublk_rq_task_work(struct request *req, mapped_bytes >> 9; } + ublk_init_req_ref(ubq, req); ubq_complete_io_cmd(io, UBLK_IO_RES_OK, issue_flags); } @@ -852,17 +943,6 @@ static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd, unsigned issue_flags) ublk_forward_io_cmds(ubq, issue_flags); } -static void ublk_rq_task_work_fn(struct callback_head *work) -{ - struct ublk_rq_data *data = container_of(work, - struct ublk_rq_data, work); - struct request *req = blk_mq_rq_from_pdu(data); - struct ublk_queue *ubq = req->mq_hctx->driver_data; - unsigned issue_flags = IO_URING_F_UNLOCKED; - - ublk_forward_io_cmds(ubq, issue_flags); -} - static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) { struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); @@ -886,10 +966,6 @@ static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) */ if (unlikely(io->flags & UBLK_IO_FLAG_ABORTED)) { ublk_abort_io_cmds(ubq); - } else if (ublk_can_use_task_work(ubq)) { - if (task_work_add(ubq->ubq_daemon, &data->work, - TWA_SIGNAL_NO_IPI)) - ublk_abort_io_cmds(ubq); } else { struct io_uring_cmd *cmd = io->cmd; struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); @@ -961,19 +1037,9 @@ static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, return 0; } -static int ublk_init_rq(struct blk_mq_tag_set *set, struct request *req, - unsigned int hctx_idx, unsigned int numa_node) -{ - struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); - - init_task_work(&data->work, ublk_rq_task_work_fn); - return 0; -} - static const struct blk_mq_ops ublk_mq_ops = { .queue_rq = ublk_queue_rq, .init_hctx = ublk_init_hctx, - .init_request = ublk_init_rq, .timeout = ublk_timeout, }; @@ -1050,7 +1116,7 @@ static void ublk_commit_completion(struct ublk_device *ub, req = blk_mq_tag_to_rq(ub->tag_set.tags[qid], tag); if (req && likely(!blk_should_fake_timeout(req->q))) - ublk_complete_rq(req); + ublk_put_req_ref(ubq, req); } /* @@ -1295,6 +1361,14 @@ static inline int ublk_check_cmd_op(u32 cmd_op) return 0; } +static inline void ublk_fill_io_cmd(struct ublk_io *io, + struct io_uring_cmd *cmd, unsigned long buf_addr) +{ + io->cmd = cmd; + io->flags |= UBLK_IO_FLAG_ACTIVE; + io->addr = buf_addr; +} + static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags, const struct ublksrv_io_cmd *ub_cmd) @@ -1340,6 +1414,11 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, ^ (_IOC_NR(cmd_op) == UBLK_IO_NEED_GET_DATA)) goto out; + if (ublk_support_user_copy(ubq) && ub_cmd->addr) { + ret = -EINVAL; + goto out; + } + ret = ublk_check_cmd_op(cmd_op); if (ret) goto out; @@ -1358,36 +1437,41 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, */ if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV) goto out; - /* FETCH_RQ has to provide IO buffer if NEED GET DATA is not enabled */ - if (!ub_cmd->addr && !ublk_need_get_data(ubq)) - goto out; - io->cmd = cmd; - io->flags |= UBLK_IO_FLAG_ACTIVE; - io->addr = ub_cmd->addr; + if (!ublk_support_user_copy(ubq)) { + /* + * FETCH_RQ has to provide IO buffer if NEED GET + * DATA is not enabled + */ + if (!ub_cmd->addr && !ublk_need_get_data(ubq)) + goto out; + } + + ublk_fill_io_cmd(io, cmd, ub_cmd->addr); ublk_mark_io_ready(ub, ubq); break; case UBLK_IO_COMMIT_AND_FETCH_REQ: req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag); - /* - * COMMIT_AND_FETCH_REQ has to provide IO buffer if NEED GET DATA is - * not enabled or it is Read IO. - */ - if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || req_op(req) == REQ_OP_READ)) - goto out; + if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)) goto out; - io->addr = ub_cmd->addr; - io->flags |= UBLK_IO_FLAG_ACTIVE; - io->cmd = cmd; + + if (!ublk_support_user_copy(ubq)) { + /* + * COMMIT_AND_FETCH_REQ has to provide IO buffer if + * NEED GET DATA is not enabled or it is Read IO. + */ + if (!ub_cmd->addr && (!ublk_need_get_data(ubq) || + req_op(req) == REQ_OP_READ)) + goto out; + } + ublk_fill_io_cmd(io, cmd, ub_cmd->addr); ublk_commit_completion(ub, ub_cmd); break; case UBLK_IO_NEED_GET_DATA: if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV)) goto out; - io->addr = ub_cmd->addr; - io->cmd = cmd; - io->flags |= UBLK_IO_FLAG_ACTIVE; + ublk_fill_io_cmd(io, cmd, ub_cmd->addr); ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag); break; default: @@ -1402,6 +1486,36 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, return -EIOCBQUEUED; } +static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub, + struct ublk_queue *ubq, int tag, size_t offset) +{ + struct request *req; + + if (!ublk_need_req_ref(ubq)) + return NULL; + + req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag); + if (!req) + return NULL; + + if (!ublk_get_req_ref(ubq, req)) + return NULL; + + if (unlikely(!blk_mq_request_started(req) || req->tag != tag)) + goto fail_put; + + if (!ublk_rq_has_data(req)) + goto fail_put; + + if (offset > blk_rq_bytes(req)) + goto fail_put; + + return req; +fail_put: + ublk_put_req_ref(ubq, req); + return NULL; +} + static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { /* @@ -1419,11 +1533,112 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) return __ublk_ch_uring_cmd(cmd, issue_flags, &ub_cmd); } +static inline bool ublk_check_ubuf_dir(const struct request *req, + int ubuf_dir) +{ + /* copy ubuf to request pages */ + if (req_op(req) == REQ_OP_READ && ubuf_dir == ITER_SOURCE) + return true; + + /* copy request pages to ubuf */ + if (req_op(req) == REQ_OP_WRITE && ubuf_dir == ITER_DEST) + return true; + + return false; +} + +static struct request *ublk_check_and_get_req(struct kiocb *iocb, + struct iov_iter *iter, size_t *off, int dir) +{ + struct ublk_device *ub = iocb->ki_filp->private_data; + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + u16 tag, q_id; + + if (!ub) + return ERR_PTR(-EACCES); + + if (!user_backed_iter(iter)) + return ERR_PTR(-EACCES); + + if (ub->dev_info.state == UBLK_S_DEV_DEAD) + return ERR_PTR(-EACCES); + + tag = ublk_pos_to_tag(iocb->ki_pos); + q_id = ublk_pos_to_hwq(iocb->ki_pos); + buf_off = ublk_pos_to_buf_off(iocb->ki_pos); + + if (q_id >= ub->dev_info.nr_hw_queues) + return ERR_PTR(-EINVAL); + + ubq = ublk_get_queue(ub, q_id); + if (!ubq) + return ERR_PTR(-EINVAL); + + if (tag >= ubq->q_depth) + return ERR_PTR(-EINVAL); + + req = __ublk_check_and_get_req(ub, ubq, tag, buf_off); + if (!req) + return ERR_PTR(-EINVAL); + + if (!req->mq_hctx || !req->mq_hctx->driver_data) + goto fail; + + if (!ublk_check_ubuf_dir(req, dir)) + goto fail; + + *off = buf_off; + return req; +fail: + ublk_put_req_ref(ubq, req); + return ERR_PTR(-EACCES); +} + +static ssize_t ublk_ch_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + size_t ret; + + req = ublk_check_and_get_req(iocb, to, &buf_off, ITER_DEST); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = ublk_copy_user_pages(req, buf_off, to, ITER_DEST); + ubq = req->mq_hctx->driver_data; + ublk_put_req_ref(ubq, req); + + return ret; +} + +static ssize_t ublk_ch_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct ublk_queue *ubq; + struct request *req; + size_t buf_off; + size_t ret; + + req = ublk_check_and_get_req(iocb, from, &buf_off, ITER_SOURCE); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = ublk_copy_user_pages(req, buf_off, from, ITER_SOURCE); + ubq = req->mq_hctx->driver_data; + ublk_put_req_ref(ubq, req); + + return ret; +} + static const struct file_operations ublk_ch_fops = { .owner = THIS_MODULE, .open = ublk_ch_open, .release = ublk_ch_release, .llseek = no_llseek, + .read_iter = ublk_ch_read_iter, + .write_iter = ublk_ch_write_iter, .uring_cmd = ublk_ch_uring_cmd, .mmap = ublk_ch_mmap, }; @@ -1547,7 +1762,7 @@ static int ublk_add_chdev(struct ublk_device *ub) dev->parent = ublk_misc.this_device; dev->devt = MKDEV(MAJOR(ublk_chr_devt), minor); - dev->class = ublk_chr_class; + dev->class = &ublk_chr_class; dev->release = ublk_cdev_rel; device_initialize(dev); @@ -1818,10 +2033,12 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) */ ub->dev_info.flags &= UBLK_F_ALL; - if (!IS_BUILTIN(CONFIG_BLK_DEV_UBLK)) - ub->dev_info.flags |= UBLK_F_URING_CMD_COMP_IN_TASK; + ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE | + UBLK_F_URING_CMD_COMP_IN_TASK; - ub->dev_info.flags |= UBLK_F_CMD_IOCTL_ENCODE; + /* GET_DATA isn't needed any more with USER_COPY */ + if (ub->dev_info.flags & UBLK_F_USER_COPY) + ub->dev_info.flags &= ~UBLK_F_NEED_GET_DATA; /* We are not ready to support zero copy */ ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY; @@ -2133,6 +2350,21 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, return ret; } +static int ublk_ctrl_get_features(struct io_uring_cmd *cmd) +{ + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); + void __user *argp = (void __user *)(unsigned long)header->addr; + u64 features = UBLK_F_ALL & ~UBLK_F_SUPPORT_ZERO_COPY; + + if (header->len != UBLK_FEATURES_LEN || !header->addr) + return -EINVAL; + + if (copy_to_user(argp, &features, UBLK_FEATURES_LEN)) + return -EFAULT; + + return 0; +} + /* * All control commands are sent via /dev/ublk-control, so we have to check * the destination device's permission @@ -2213,6 +2445,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, case UBLK_CMD_GET_DEV_INFO2: case UBLK_CMD_GET_QUEUE_AFFINITY: case UBLK_CMD_GET_PARAMS: + case (_IOC_NR(UBLK_U_CMD_GET_FEATURES)): mask = MAY_READ; break; case UBLK_CMD_START_DEV: @@ -2262,6 +2495,11 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, if (ret) goto out; + if (cmd_op == UBLK_U_CMD_GET_FEATURES) { + ret = ublk_ctrl_get_features(cmd); + goto out; + } + if (_IOC_NR(cmd_op) != UBLK_CMD_ADD_DEV) { ret = -ENODEV; ub = ublk_get_device_from_id(header->dev_id); @@ -2337,6 +2575,9 @@ static int __init ublk_init(void) { int ret; + BUILD_BUG_ON((u64)UBLKSRV_IO_BUF_OFFSET + + UBLKSRV_IO_BUF_TOTAL_SIZE < UBLKSRV_IO_BUF_OFFSET); + init_waitqueue_head(&ublk_idr_wq); ret = misc_register(&ublk_misc); @@ -2347,11 +2588,10 @@ static int __init ublk_init(void) if (ret) goto unregister_mis; - ublk_chr_class = class_create("ublk-char"); - if (IS_ERR(ublk_chr_class)) { - ret = PTR_ERR(ublk_chr_class); + ret = class_register(&ublk_chr_class); + if (ret) goto free_chrdev_region; - } + return 0; free_chrdev_region: @@ -2369,7 +2609,7 @@ static void __exit ublk_exit(void) idr_for_each_entry(&ublk_index_idr, ub, id) ublk_remove(ub); - class_destroy(ublk_chr_class); + class_unregister(&ublk_chr_class); misc_deregister(&ublk_misc); idr_destroy(&ublk_index_idr); diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 4807af1d5805..bb66178c432b 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -473,7 +473,7 @@ static void xenvbd_sysfs_delif(struct xenbus_device *dev) static void xen_vbd_free(struct xen_vbd *vbd) { if (vbd->bdev) - blkdev_put(vbd->bdev, vbd->readonly ? FMODE_READ : FMODE_WRITE); + blkdev_put(vbd->bdev, NULL); vbd->bdev = NULL; } @@ -492,7 +492,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, vbd->pdevice = MKDEV(major, minor); bdev = blkdev_get_by_dev(vbd->pdevice, vbd->readonly ? - FMODE_READ : FMODE_WRITE, NULL); + BLK_OPEN_READ : BLK_OPEN_WRITE, NULL, NULL); if (IS_ERR(bdev)) { pr_warn("xen_vbd_create: device %08x could not be opened\n", diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index c1890c8a9f6e..434fab306777 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -509,7 +509,7 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg) return 0; } -static int blkif_ioctl(struct block_device *bdev, fmode_t mode, +static int blkif_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned command, unsigned long argument) { struct blkfront_info *info = bdev->bd_disk->private_data; diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index c1e85f356e4d..11493167b0a8 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -140,16 +140,14 @@ static void get_chipram(void) return; } -static int z2_open(struct block_device *bdev, fmode_t mode) +static int z2_open(struct gendisk *disk, blk_mode_t mode) { - int device; + int device = disk->first_minor; 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; @@ -290,7 +288,7 @@ err_out: return rc; } -static void z2_release(struct gendisk *disk, fmode_t mode) +static void z2_release(struct gendisk *disk) { mutex_lock(&z2ram_mutex); if (current_device == -1) { diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index f6d90f1ba5cf..1867f378b319 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -420,7 +420,7 @@ static void reset_bdev(struct zram *zram) return; bdev = zram->bdev; - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, zram); /* hope filp_close flush all of IO */ filp_close(zram->backing_dev, NULL); zram->backing_dev = NULL; @@ -507,8 +507,8 @@ static ssize_t backing_dev_store(struct device *dev, goto out; } - bdev = blkdev_get_by_dev(inode->i_rdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram); + bdev = blkdev_get_by_dev(inode->i_rdev, BLK_OPEN_READ | BLK_OPEN_WRITE, + zram, NULL); if (IS_ERR(bdev)) { err = PTR_ERR(bdev); bdev = NULL; @@ -539,7 +539,7 @@ out: kvfree(bitmap); if (bdev) - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, zram); if (backing_dev) filp_close(backing_dev, NULL); @@ -700,7 +700,7 @@ static ssize_t writeback_store(struct device *dev, bio_init(&bio, zram->bdev, &bio_vec, 1, REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); - bio_add_page(&bio, page, PAGE_SIZE, 0); + __bio_add_page(&bio, page, PAGE_SIZE, 0); /* * XXX: A single page IO would be inefficient for write @@ -2097,19 +2097,16 @@ static ssize_t reset_store(struct device *dev, return len; } -static int zram_open(struct block_device *bdev, fmode_t mode) +static int zram_open(struct gendisk *disk, blk_mode_t mode) { - int ret = 0; - struct zram *zram; + struct zram *zram = disk->private_data; - WARN_ON(!mutex_is_locked(&bdev->bd_disk->open_mutex)); + WARN_ON(!mutex_is_locked(&disk->open_mutex)); - zram = bdev->bd_disk->private_data; /* zram was claimed to reset so open request fails */ if (zram->claim) - ret = -EBUSY; - - return ret; + return -EBUSY; + return 0; } static const struct block_device_operations zram_devops = { diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 416f723a2dbb..cc2839805983 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -264,6 +264,7 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/nospec.h> #include <linux/slab.h> #include <linux/cdrom.h> #include <linux/sysctl.h> @@ -978,15 +979,6 @@ static void cdrom_dvd_rw_close_write(struct cdrom_device_info *cdi) cdi->media_written = 0; } -static int cdrom_close_write(struct cdrom_device_info *cdi) -{ -#if 0 - return cdrom_flush_cache(cdi); -#else - return 0; -#endif -} - /* badly broken, I know. Is due for a fixup anytime. */ static void cdrom_count_tracks(struct cdrom_device_info *cdi, tracktype *tracks) { @@ -1155,8 +1147,7 @@ clean_up_and_return: * is in their own interest: device control becomes a lot easier * this way. */ -int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode) +int cdrom_open(struct cdrom_device_info *cdi, blk_mode_t mode) { int ret; @@ -1165,7 +1156,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, /* if this was a O_NONBLOCK open and we should honor the flags, * do a quick open without drive/disc integrity checks. */ cdi->use_count++; - if ((mode & FMODE_NDELAY) && (cdi->options & CDO_USE_FFLAGS)) { + if ((mode & BLK_OPEN_NDELAY) && (cdi->options & CDO_USE_FFLAGS)) { ret = cdi->ops->open(cdi, 1); } else { ret = open_for_data(cdi); @@ -1173,7 +1164,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, goto err; if (CDROM_CAN(CDC_GENERIC_PACKET)) cdrom_mmc3_profile(cdi); - if (mode & FMODE_WRITE) { + if (mode & BLK_OPEN_WRITE) { ret = -EROFS; if (cdrom_open_write(cdi)) goto err_release; @@ -1182,6 +1173,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, ret = 0; cdi->media_written = 0; } + cdi->opened_for_data = true; } if (ret) @@ -1259,10 +1251,9 @@ static int check_for_audio_disc(struct cdrom_device_info *cdi, return 0; } -void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode) +void cdrom_release(struct cdrom_device_info *cdi) { const struct cdrom_device_ops *cdo = cdi->ops; - int opened_for_data; cd_dbg(CD_CLOSE, "entering cdrom_release\n"); @@ -1280,20 +1271,12 @@ void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode) } } - opened_for_data = !(cdi->options & CDO_USE_FFLAGS) || - !(mode & FMODE_NDELAY); - - /* - * flush cache on last write release - */ - if (CDROM_CAN(CDC_RAM) && !cdi->use_count && cdi->for_data) - cdrom_close_write(cdi); - cdo->release(cdi); - if (cdi->use_count == 0) { /* last process that closes dev*/ - if (opened_for_data && - cdi->options & CDO_AUTO_EJECT && CDROM_CAN(CDC_OPEN_TRAY)) + + if (cdi->use_count == 0 && cdi->opened_for_data) { + if (cdi->options & CDO_AUTO_EJECT && CDROM_CAN(CDC_OPEN_TRAY)) cdo->tray_move(cdi, 1); + cdi->opened_for_data = false; } } EXPORT_SYMBOL(cdrom_release); @@ -2329,6 +2312,9 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi, if (arg >= cdi->capacity) return -EINVAL; + /* Prevent arg from speculatively bypassing the length check */ + barrier_nospec(); + info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; @@ -3337,7 +3323,7 @@ static int mmc_ioctl(struct cdrom_device_info *cdi, unsigned int cmd, * ATAPI / SCSI specific code now mainly resides in mmc_ioctl(). */ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode, unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; int ret; diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index ceded5772aac..3a46e27479ff 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -474,19 +474,19 @@ static const struct cdrom_device_ops gdrom_ops = { CDC_RESET | CDC_DRIVE_STATUS | CDC_CD_R, }; -static int gdrom_bdops_open(struct block_device *bdev, fmode_t mode) +static int gdrom_bdops_open(struct gendisk *disk, blk_mode_t mode) { int ret; - bdev_check_media_change(bdev); + disk_check_media_change(disk); mutex_lock(&gdrom_mutex); - ret = cdrom_open(gd.cd_info, bdev, mode); + ret = cdrom_open(gd.cd_info); mutex_unlock(&gdrom_mutex); return ret; } -static void gdrom_bdops_release(struct gendisk *disk, fmode_t mode) +static void gdrom_bdops_release(struct gendisk *disk) { mutex_lock(&gdrom_mutex); cdrom_release(gd.cd_info, mode); @@ -499,13 +499,13 @@ static unsigned int gdrom_bdops_check_events(struct gendisk *disk, return cdrom_check_events(gd.cd_info, clearing); } -static int gdrom_bdops_ioctl(struct block_device *bdev, fmode_t mode, +static int gdrom_bdops_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg) { int ret; mutex_lock(&gdrom_mutex); - ret = cdrom_ioctl(gd.cd_info, bdev, mode, cmd, arg); + ret = cdrom_ioctl(gd.cd_info, bdev, cmd, arg); mutex_unlock(&gdrom_mutex); return ret; diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index aebb7ef10e63..5a79bb3c272f 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -275,7 +275,7 @@ struct bcache_device { int (*cache_miss)(struct btree *b, struct search *s, struct bio *bio, unsigned int sectors); - int (*ioctl)(struct bcache_device *d, fmode_t mode, + int (*ioctl)(struct bcache_device *d, blk_mode_t mode, unsigned int cmd, unsigned long arg); }; @@ -1004,11 +1004,11 @@ extern struct workqueue_struct *bch_flush_wq; extern struct mutex bch_register_lock; extern struct list_head bch_cache_sets; -extern struct kobj_type bch_cached_dev_ktype; -extern struct kobj_type bch_flash_dev_ktype; -extern struct kobj_type bch_cache_set_ktype; -extern struct kobj_type bch_cache_set_internal_ktype; -extern struct kobj_type bch_cache_ktype; +extern const struct kobj_type bch_cached_dev_ktype; +extern const struct kobj_type bch_flash_dev_ktype; +extern const struct kobj_type bch_cache_set_ktype; +extern const struct kobj_type bch_cache_set_internal_ktype; +extern const struct kobj_type bch_cache_ktype; void bch_cached_dev_release(struct kobject *kobj); void bch_flash_dev_release(struct kobject *kobj); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 147c493a989a..68b9d7ca864e 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -885,7 +885,7 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op, * cannibalize_bucket() will take. This means every time we unlock the root of * the btree, we need to release this lock if we have it held. */ -static void bch_cannibalize_unlock(struct cache_set *c) +void bch_cannibalize_unlock(struct cache_set *c) { spin_lock(&c->btree_cannibalize_lock); if (c->btree_cache_alloc_lock == current) { @@ -1090,10 +1090,12 @@ struct btree *__bch_btree_node_alloc(struct cache_set *c, struct btree_op *op, struct btree *parent) { BKEY_PADDED(key) k; - struct btree *b = ERR_PTR(-EAGAIN); + struct btree *b; mutex_lock(&c->bucket_lock); retry: + /* return ERR_PTR(-EAGAIN) when it fails */ + b = ERR_PTR(-EAGAIN); if (__bch_bucket_alloc_set(c, RESERVE_BTREE, &k.key, wait)) goto err; @@ -1138,7 +1140,7 @@ static struct btree *btree_node_alloc_replacement(struct btree *b, { struct btree *n = bch_btree_node_alloc(b->c, op, b->level, b->parent); - if (!IS_ERR_OR_NULL(n)) { + if (!IS_ERR(n)) { mutex_lock(&n->write_lock); bch_btree_sort_into(&b->keys, &n->keys, &b->c->sort); bkey_copy_key(&n->key, &b->key); @@ -1340,7 +1342,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, memset(new_nodes, 0, sizeof(new_nodes)); closure_init_stack(&cl); - while (nodes < GC_MERGE_NODES && !IS_ERR_OR_NULL(r[nodes].b)) + while (nodes < GC_MERGE_NODES && !IS_ERR(r[nodes].b)) keys += r[nodes++].keys; blocks = btree_default_blocks(b->c) * 2 / 3; @@ -1352,7 +1354,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, for (i = 0; i < nodes; i++) { new_nodes[i] = btree_node_alloc_replacement(r[i].b, NULL); - if (IS_ERR_OR_NULL(new_nodes[i])) + if (IS_ERR(new_nodes[i])) goto out_nocoalesce; } @@ -1487,7 +1489,7 @@ out_nocoalesce: bch_keylist_free(&keylist); for (i = 0; i < nodes; i++) - if (!IS_ERR_OR_NULL(new_nodes[i])) { + if (!IS_ERR(new_nodes[i])) { btree_node_free(new_nodes[i]); rw_unlock(true, new_nodes[i]); } @@ -1669,7 +1671,7 @@ static int bch_btree_gc_root(struct btree *b, struct btree_op *op, if (should_rewrite) { n = btree_node_alloc_replacement(b, NULL); - if (!IS_ERR_OR_NULL(n)) { + if (!IS_ERR(n)) { bch_btree_node_write_sync(n); bch_btree_set_root(n); @@ -1968,6 +1970,15 @@ static int bch_btree_check_thread(void *arg) c->gc_stats.nodes++; bch_btree_op_init(&op, 0); ret = bcache_btree(check_recurse, p, c->root, &op); + /* + * The op may be added to cache_set's btree_cache_wait + * in mca_cannibalize(), must ensure it is removed from + * the list and release btree_cache_alloc_lock before + * free op memory. + * Otherwise, the btree_cache_wait will be damaged. + */ + bch_cannibalize_unlock(c); + finish_wait(&c->btree_cache_wait, &(&op)->wait); if (ret) goto out; } diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 1b5fdbc0d83e..a2920bbfcad5 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -282,6 +282,7 @@ void bch_initial_gc_finish(struct cache_set *c); void bch_moving_gc(struct cache_set *c); int bch_btree_check(struct cache_set *c); void bch_initial_mark_key(struct cache_set *c, int level, struct bkey *k); +void bch_cannibalize_unlock(struct cache_set *c); static inline void wake_up_gc(struct cache_set *c) { diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 67a2e29e0b40..a9b1f3896249 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1228,7 +1228,7 @@ void cached_dev_submit_bio(struct bio *bio) detached_dev_do_request(d, bio, orig_bdev, start_time); } -static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, +static int cached_dev_ioctl(struct bcache_device *d, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct cached_dev *dc = container_of(d, struct cached_dev, disk); @@ -1318,7 +1318,7 @@ void flash_dev_submit_bio(struct bio *bio) continue_at(cl, search_free, NULL); } -static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode, +static int flash_dev_ioctl(struct bcache_device *d, blk_mode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h index bd3afc856d53..21b445f8af15 100644 --- a/drivers/md/bcache/stats.h +++ b/drivers/md/bcache/stats.h @@ -18,7 +18,6 @@ struct cache_stats { unsigned long cache_misses; unsigned long cache_bypass_hits; unsigned long cache_bypass_misses; - unsigned long cache_readaheads; unsigned long cache_miss_collisions; unsigned long sectors_bypassed; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 7e9d19fd21dd..e2a803683105 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -732,9 +732,9 @@ out: /* Bcache device */ -static int open_dev(struct block_device *b, fmode_t mode) +static int open_dev(struct gendisk *disk, blk_mode_t mode) { - struct bcache_device *d = b->bd_disk->private_data; + struct bcache_device *d = disk->private_data; if (test_bit(BCACHE_DEV_CLOSING, &d->flags)) return -ENXIO; @@ -743,14 +743,14 @@ static int open_dev(struct block_device *b, fmode_t mode) return 0; } -static void release_dev(struct gendisk *b, fmode_t mode) +static void release_dev(struct gendisk *b) { struct bcache_device *d = b->private_data; closure_put(&d->cl); } -static int ioctl_dev(struct block_device *b, fmode_t mode, +static int ioctl_dev(struct block_device *b, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct bcache_device *d = b->bd_disk->private_data; @@ -1369,7 +1369,7 @@ static void cached_dev_free(struct closure *cl) put_page(virt_to_page(dc->sb_disk)); if (!IS_ERR_OR_NULL(dc->bdev)) - blkdev_put(dc->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(dc->bdev, bcache_kobj); wake_up(&unregister_wait); @@ -1723,7 +1723,7 @@ static void cache_set_flush(struct closure *cl) if (!IS_ERR_OR_NULL(c->gc_thread)) kthread_stop(c->gc_thread); - if (!IS_ERR_OR_NULL(c->root)) + if (!IS_ERR(c->root)) list_add(&c->root->list, &c->btree_cache); /* @@ -2087,7 +2087,7 @@ static int run_cache_set(struct cache_set *c) err = "cannot allocate new btree root"; c->root = __bch_btree_node_alloc(c, NULL, 0, true, NULL); - if (IS_ERR_OR_NULL(c->root)) + if (IS_ERR(c->root)) goto err; mutex_lock(&c->root->write_lock); @@ -2218,7 +2218,7 @@ void bch_cache_release(struct kobject *kobj) put_page(virt_to_page(ca->sb_disk)); if (!IS_ERR_OR_NULL(ca->bdev)) - blkdev_put(ca->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(ca->bdev, bcache_kobj); kfree(ca); module_put(THIS_MODULE); @@ -2359,7 +2359,7 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, * call blkdev_put() to bdev in bch_cache_release(). So we * explicitly call blkdev_put() here. */ - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, bcache_kobj); if (ret == -ENOMEM) err = "cache_alloc(): -ENOMEM"; else if (ret == -EPERM) @@ -2461,7 +2461,7 @@ static void register_bdev_worker(struct work_struct *work) if (!dc) { fail = true; put_page(virt_to_page(args->sb_disk)); - blkdev_put(args->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(args->bdev, bcache_kobj); goto out; } @@ -2491,7 +2491,7 @@ static void register_cache_worker(struct work_struct *work) if (!ca) { fail = true; put_page(virt_to_page(args->sb_disk)); - blkdev_put(args->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(args->bdev, bcache_kobj); goto out; } @@ -2558,9 +2558,8 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, ret = -EINVAL; err = "failed to open device"; - bdev = blkdev_get_by_path(strim(path), - FMODE_READ|FMODE_WRITE|FMODE_EXCL, - sb); + bdev = blkdev_get_by_path(strim(path), BLK_OPEN_READ | BLK_OPEN_WRITE, + bcache_kobj, NULL); if (IS_ERR(bdev)) { if (bdev == ERR_PTR(-EBUSY)) { dev_t dev; @@ -2648,7 +2647,7 @@ async_done: out_put_sb_page: put_page(virt_to_page(sb_disk)); out_blkdev_put: - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, register_bcache); out_free_sb: kfree(sb); out_free_path: diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index c6f677059214..0e2c1880f60b 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -1111,26 +1111,25 @@ SHOW(__bch_cache) vfree(p); - ret = scnprintf(buf, PAGE_SIZE, - "Unused: %zu%%\n" - "Clean: %zu%%\n" - "Dirty: %zu%%\n" - "Metadata: %zu%%\n" - "Average: %llu\n" - "Sectors per Q: %zu\n" - "Quantiles: [", - unused * 100 / (size_t) ca->sb.nbuckets, - available * 100 / (size_t) ca->sb.nbuckets, - dirty * 100 / (size_t) ca->sb.nbuckets, - meta * 100 / (size_t) ca->sb.nbuckets, sum, - n * ca->sb.bucket_size / (ARRAY_SIZE(q) + 1)); + ret = sysfs_emit(buf, + "Unused: %zu%%\n" + "Clean: %zu%%\n" + "Dirty: %zu%%\n" + "Metadata: %zu%%\n" + "Average: %llu\n" + "Sectors per Q: %zu\n" + "Quantiles: [", + unused * 100 / (size_t) ca->sb.nbuckets, + available * 100 / (size_t) ca->sb.nbuckets, + dirty * 100 / (size_t) ca->sb.nbuckets, + meta * 100 / (size_t) ca->sb.nbuckets, sum, + n * ca->sb.bucket_size / (ARRAY_SIZE(q) + 1)); for (i = 0; i < ARRAY_SIZE(q); i++) - ret += scnprintf(buf + ret, PAGE_SIZE - ret, - "%u ", q[i]); + ret += sysfs_emit_at(buf, ret, "%u ", q[i]); ret--; - ret += scnprintf(buf + ret, PAGE_SIZE - ret, "]\n"); + ret += sysfs_emit_at(buf, ret, "]\n"); return ret; } diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h index a2ff6447b699..65b8bd975ab1 100644 --- a/drivers/md/bcache/sysfs.h +++ b/drivers/md/bcache/sysfs.h @@ -3,7 +3,7 @@ #define _BCACHE_SYSFS_H_ #define KTYPE(type) \ -struct kobj_type type ## _ktype = { \ +const struct kobj_type type ## _ktype = { \ .release = type ## _release, \ .sysfs_ops = &((const struct sysfs_ops) { \ .show = type ## _show, \ diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index d4a5fc0650bb..24c049067f61 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -890,6 +890,16 @@ static int bch_root_node_dirty_init(struct cache_set *c, if (ret < 0) pr_warn("sectors dirty init failed, ret=%d!\n", ret); + /* + * The op may be added to cache_set's btree_cache_wait + * in mca_cannibalize(), must ensure it is removed from + * the list and release btree_cache_alloc_lock before + * free op memory. + * Otherwise, the btree_cache_wait will be damaged. + */ + bch_cannibalize_unlock(c); + finish_wait(&c->btree_cache_wait, &(&op.op)->wait); + return ret; } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 872896218550..911f73f7ebba 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -2051,8 +2051,8 @@ static int parse_metadata_dev(struct cache_args *ca, struct dm_arg_set *as, if (!at_least_one_arg(as, error)) return -EINVAL; - r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &ca->metadata_dev); + r = dm_get_device(ca->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &ca->metadata_dev); if (r) { *error = "Error opening metadata device"; return r; @@ -2074,8 +2074,8 @@ static int parse_cache_dev(struct cache_args *ca, struct dm_arg_set *as, if (!at_least_one_arg(as, error)) return -EINVAL; - r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &ca->cache_dev); + r = dm_get_device(ca->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &ca->cache_dev); if (r) { *error = "Error opening cache device"; return r; @@ -2093,8 +2093,8 @@ static int parse_origin_dev(struct cache_args *ca, struct dm_arg_set *as, if (!at_least_one_arg(as, error)) return -EINVAL; - r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &ca->origin_dev); + r = dm_get_device(ca->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &ca->origin_dev); if (r) { *error = "Error opening origin device"; return r; diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index f467cdb5a022..94b2fc33f64b 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -1683,8 +1683,8 @@ static int parse_metadata_dev(struct clone *clone, struct dm_arg_set *as, char * int r; sector_t metadata_dev_size; - r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &clone->metadata_dev); + r = dm_get_device(clone->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &clone->metadata_dev); if (r) { *error = "Error opening metadata device"; return r; @@ -1703,8 +1703,8 @@ static int parse_dest_dev(struct clone *clone, struct dm_arg_set *as, char **err int r; sector_t dest_dev_size; - r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, - &clone->dest_dev); + r = dm_get_device(clone->ti, dm_shift_arg(as), + BLK_OPEN_READ | BLK_OPEN_WRITE, &clone->dest_dev); if (r) { *error = "Error opening destination device"; return r; @@ -1725,7 +1725,7 @@ static int parse_source_dev(struct clone *clone, struct dm_arg_set *as, char **e int r; sector_t source_dev_size; - r = dm_get_device(clone->ti, dm_shift_arg(as), FMODE_READ, + r = dm_get_device(clone->ti, dm_shift_arg(as), BLK_OPEN_READ, &clone->source_dev); if (r) { *error = "Error opening source device"; diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index aecab0c0720f..ce913ad91a52 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -207,11 +207,10 @@ struct dm_table { unsigned integrity_added:1; /* - * Indicates the rw permissions for the new logical - * device. This should be a combination of FMODE_READ - * and FMODE_WRITE. + * Indicates the rw permissions for the new logical device. This + * should be a combination of BLK_OPEN_READ and BLK_OPEN_WRITE. */ - fmode_t mode; + blk_mode_t mode; /* a list of devices used by this table */ struct list_head devices; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 8b47b913ee83..09e37ebf7cc8 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1693,8 +1693,7 @@ retry: len = (remaining_size > PAGE_SIZE) ? PAGE_SIZE : remaining_size; - bio_add_page(clone, page, len, 0); - + __bio_add_page(clone, page, len, 0); remaining_size -= len; } diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 0d70914217ee..6acfa5bf97a4 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1482,14 +1482,16 @@ static int era_ctr(struct dm_target *ti, unsigned int argc, char **argv) era->ti = ti; - r = dm_get_device(ti, argv[0], FMODE_READ | FMODE_WRITE, &era->metadata_dev); + r = dm_get_device(ti, argv[0], BLK_OPEN_READ | BLK_OPEN_WRITE, + &era->metadata_dev); if (r) { ti->error = "Error opening metadata device"; era_destroy(era); return -EINVAL; } - r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &era->origin_dev); + r = dm_get_device(ti, argv[1], BLK_OPEN_READ | BLK_OPEN_WRITE, + &era->origin_dev); if (r) { ti->error = "Error opening data device"; era_destroy(era); diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c index d369457dbed0..2a71bcdba92d 100644 --- a/drivers/md/dm-init.c +++ b/drivers/md/dm-init.c @@ -293,8 +293,10 @@ static int __init dm_init_init(void) for (i = 0; i < ARRAY_SIZE(waitfor); i++) { if (waitfor[i]) { + dev_t dev; + DMINFO("waiting for device %s ...", waitfor[i]); - while (!dm_get_dev_t(waitfor[i])) + while (early_lookup_bdev(waitfor[i], &dev)) fsleep(5000); } } diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 7d5c9c582ed2..6d301019e5e3 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -861,7 +861,7 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param) table = dm_get_inactive_table(md, &srcu_idx); if (table) { - if (!(dm_table_get_mode(table) & FMODE_WRITE)) + if (!(dm_table_get_mode(table) & BLK_OPEN_WRITE)) param->flags |= DM_READONLY_FLAG; param->target_count = table->num_targets; } @@ -1189,7 +1189,7 @@ static int do_resume(struct dm_ioctl *param) if (old_size && new_size && old_size != new_size) need_resize_uevent = true; - if (dm_table_get_mode(new_map) & FMODE_WRITE) + if (dm_table_get_mode(new_map) & BLK_OPEN_WRITE) set_disk_ro(dm_disk(md), 0); else set_disk_ro(dm_disk(md), 1); @@ -1378,12 +1378,12 @@ static int dev_arm_poll(struct file *filp, struct dm_ioctl *param, size_t param_ return 0; } -static inline fmode_t get_mode(struct dm_ioctl *param) +static inline blk_mode_t get_mode(struct dm_ioctl *param) { - fmode_t mode = FMODE_READ | FMODE_WRITE; + blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE; if (param->flags & DM_READONLY_FLAG) - mode = FMODE_READ; + mode = BLK_OPEN_READ; return mode; } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index c8821fcb8299..8846bf510a35 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3750,11 +3750,11 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv, * canceling read-auto mode */ mddev->ro = 0; - if (!mddev->suspended && mddev->sync_thread) + if (!mddev->suspended) md_wakeup_thread(mddev->sync_thread); } set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - if (!mddev->suspended && mddev->thread) + if (!mddev->suspended) md_wakeup_thread(mddev->thread); return 0; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 9c49f53760d0..bf7a574499a3 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1241,9 +1241,8 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) int i; int r = -EINVAL; char *origin_path, *cow_path; - dev_t origin_dev, cow_dev; unsigned int args_used, num_flush_bios = 1; - fmode_t origin_mode = FMODE_READ; + blk_mode_t origin_mode = BLK_OPEN_READ; if (argc < 4) { ti->error = "requires 4 or more arguments"; @@ -1253,7 +1252,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (dm_target_is_snapshot_merge(ti)) { num_flush_bios = 2; - origin_mode = FMODE_WRITE; + origin_mode = BLK_OPEN_WRITE; } s = kzalloc(sizeof(*s), GFP_KERNEL); @@ -1279,24 +1278,21 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->error = "Cannot get origin device"; goto bad_origin; } - origin_dev = s->origin->bdev->bd_dev; cow_path = argv[0]; argv++; argc--; - cow_dev = dm_get_dev_t(cow_path); - if (cow_dev && cow_dev == origin_dev) { - ti->error = "COW device cannot be the same as origin device"; - r = -EINVAL; - goto bad_cow; - } - r = dm_get_device(ti, cow_path, dm_table_get_mode(ti->table), &s->cow); if (r) { ti->error = "Cannot get COW device"; goto bad_cow; } + if (s->cow->bdev && s->cow->bdev == s->origin->bdev) { + ti->error = "COW device cannot be the same as origin device"; + r = -EINVAL; + goto bad_store; + } r = dm_exception_store_create(ti, argc, argv, s, &args_used, &s->store); if (r) { diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 1398f1d6e83e..7d208b2b1a19 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -126,7 +126,7 @@ static int alloc_targets(struct dm_table *t, unsigned int num) return 0; } -int dm_table_create(struct dm_table **result, fmode_t mode, +int dm_table_create(struct dm_table **result, blk_mode_t mode, unsigned int num_targets, struct mapped_device *md) { struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL); @@ -304,7 +304,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * device and not to touch the existing bdev field in case * it is accessed concurrently. */ -static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, +static int upgrade_mode(struct dm_dev_internal *dd, blk_mode_t new_mode, struct mapped_device *md) { int r; @@ -324,23 +324,13 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, } /* - * Convert the path to a device - */ -dev_t dm_get_dev_t(const char *path) -{ - dev_t dev; - - if (lookup_bdev(path, &dev)) - dev = name_to_dev_t(path); - return dev; -} -EXPORT_SYMBOL_GPL(dm_get_dev_t); - -/* * Add a device to the list, or just increment the usage count if * it's already present. + * + * Note: the __ref annotation is because this function can call the __init + * marked early_lookup_bdev when called during early boot code from dm-init.c. */ -int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, +int __ref dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, struct dm_dev **result) { int r; @@ -358,9 +348,13 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, if (MAJOR(dev) != major || MINOR(dev) != minor) return -EOVERFLOW; } else { - dev = dm_get_dev_t(path); - if (!dev) - return -ENODEV; + r = lookup_bdev(path, &dev); +#ifndef MODULE + if (r && system_state < SYSTEM_RUNNING) + r = early_lookup_bdev(path, &dev); +#endif + if (r) + return r; } if (dev == disk_devt(t->md->disk)) return -EINVAL; @@ -668,7 +662,8 @@ int dm_table_add_target(struct dm_table *t, const char *type, t->singleton = true; } - if (dm_target_always_writeable(ti->type) && !(t->mode & FMODE_WRITE)) { + if (dm_target_always_writeable(ti->type) && + !(t->mode & BLK_OPEN_WRITE)) { ti->error = "target type may not be included in a read-only table"; goto bad; } @@ -2039,7 +2034,7 @@ struct list_head *dm_table_get_devices(struct dm_table *t) return &t->devices; } -fmode_t dm_table_get_mode(struct dm_table *t) +blk_mode_t dm_table_get_mode(struct dm_table *t) { return t->mode; } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 39410bf186cf..f1d0dcb9db22 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3300,7 +3300,7 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv) unsigned long block_size; dm_block_t low_water_blocks; struct dm_dev *metadata_dev; - fmode_t metadata_mode; + blk_mode_t metadata_mode; /* * FIXME Remove validation from scope of lock. @@ -3333,7 +3333,8 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) goto out_unlock; - metadata_mode = FMODE_READ | ((pf.mode == PM_READ_ONLY) ? 0 : FMODE_WRITE); + metadata_mode = BLK_OPEN_READ | + ((pf.mode == PM_READ_ONLY) ? 0 : BLK_OPEN_WRITE); r = dm_get_device(ti, argv[0], metadata_mode, &metadata_dev); if (r) { ti->error = "Error opening metadata block device"; @@ -3341,7 +3342,7 @@ static int pool_ctr(struct dm_target *ti, unsigned int argc, char **argv) } warn_if_metadata_device_too_big(metadata_dev->bdev); - r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev); + r = dm_get_device(ti, argv[1], BLK_OPEN_READ | BLK_OPEN_WRITE, &data_dev); if (r) { ti->error = "Error getting data device"; goto out_metadata; @@ -4222,7 +4223,7 @@ static int thin_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_origin_dev; } - r = dm_get_device(ti, argv[2], FMODE_READ, &origin_dev); + r = dm_get_device(ti, argv[2], BLK_OPEN_READ, &origin_dev); if (r) { ti->error = "Error opening origin device"; goto bad_origin_dev; diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index a9ee2faa75a2..3ef9f018da60 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -607,7 +607,7 @@ int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, (*argc)--; if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) { - r = dm_get_device(ti, arg_value, FMODE_READ, &v->fec->dev); + r = dm_get_device(ti, arg_value, BLK_OPEN_READ, &v->fec->dev); if (r) { ti->error = "FEC device lookup failed"; return r; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index e35c16e06d06..26adcfea0302 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1196,7 +1196,7 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) goto bad; - if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) { + if ((dm_table_get_mode(ti->table) & ~BLK_OPEN_READ)) { ti->error = "Device must be readonly"; r = -EINVAL; goto bad; @@ -1225,13 +1225,13 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv) } v->version = num; - r = dm_get_device(ti, argv[1], FMODE_READ, &v->data_dev); + r = dm_get_device(ti, argv[1], BLK_OPEN_READ, &v->data_dev); if (r) { ti->error = "Data device lookup failed"; goto bad; } - r = dm_get_device(ti, argv[2], FMODE_READ, &v->hash_dev); + r = dm_get_device(ti, argv[2], BLK_OPEN_READ, &v->hash_dev); if (r) { ti->error = "Hash device lookup failed"; goto bad; diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 8f0896a6990b..9d3cca8e3dc9 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -577,7 +577,7 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd, bio->bi_iter.bi_sector = dmz_blk2sect(block); bio->bi_private = mblk; bio->bi_end_io = dmz_mblock_bio_end_io; - bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); + __bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); submit_bio(bio); return mblk; @@ -728,7 +728,7 @@ static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, bio->bi_iter.bi_sector = dmz_blk2sect(block); bio->bi_private = mblk; bio->bi_end_io = dmz_mblock_bio_end_io; - bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); + __bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0); submit_bio(bio); return 0; @@ -752,7 +752,7 @@ static int dmz_rdwr_block(struct dmz_dev *dev, enum req_op op, bio = bio_alloc(dev->bdev, 1, op | REQ_SYNC | REQ_META | REQ_PRIO, GFP_NOIO); bio->bi_iter.bi_sector = dmz_blk2sect(block); - bio_add_page(bio, page, DMZ_BLOCK_SIZE, 0); + __bio_add_page(bio, page, DMZ_BLOCK_SIZE, 0); ret = submit_bio_wait(bio); bio_put(bio); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index fffb0cbe2ac8..ae0a88defb41 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -310,13 +310,13 @@ int dm_deleting_md(struct mapped_device *md) return test_bit(DMF_DELETING, &md->flags); } -static int dm_blk_open(struct block_device *bdev, fmode_t mode) +static int dm_blk_open(struct gendisk *disk, blk_mode_t mode) { struct mapped_device *md; spin_lock(&_minor_lock); - md = bdev->bd_disk->private_data; + md = disk->private_data; if (!md) goto out; @@ -334,7 +334,7 @@ out: return md ? 0 : -ENXIO; } -static void dm_blk_close(struct gendisk *disk, fmode_t mode) +static void dm_blk_close(struct gendisk *disk) { struct mapped_device *md; @@ -448,7 +448,7 @@ static void dm_unprepare_ioctl(struct mapped_device *md, int srcu_idx) dm_put_live_table(md, srcu_idx); } -static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, +static int dm_blk_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct mapped_device *md = bdev->bd_disk->private_data; @@ -734,7 +734,7 @@ static char *_dm_claim_ptr = "I belong to device-mapper"; * Open a table device so we can use it as a map destination. */ static struct table_device *open_table_device(struct mapped_device *md, - dev_t dev, fmode_t mode) + dev_t dev, blk_mode_t mode) { struct table_device *td; struct block_device *bdev; @@ -746,7 +746,7 @@ static struct table_device *open_table_device(struct mapped_device *md, return ERR_PTR(-ENOMEM); refcount_set(&td->count, 1); - bdev = blkdev_get_by_dev(dev, mode | FMODE_EXCL, _dm_claim_ptr); + bdev = blkdev_get_by_dev(dev, mode, _dm_claim_ptr, NULL); if (IS_ERR(bdev)) { r = PTR_ERR(bdev); goto out_free_td; @@ -771,7 +771,7 @@ static struct table_device *open_table_device(struct mapped_device *md, return td; out_blkdev_put: - blkdev_put(bdev, mode | FMODE_EXCL); + blkdev_put(bdev, _dm_claim_ptr); out_free_td: kfree(td); return ERR_PTR(r); @@ -784,14 +784,14 @@ static void close_table_device(struct table_device *td, struct mapped_device *md { if (md->disk->slave_dir) bd_unlink_disk_holder(td->dm_dev.bdev, md->disk); - blkdev_put(td->dm_dev.bdev, td->dm_dev.mode | FMODE_EXCL); + blkdev_put(td->dm_dev.bdev, _dm_claim_ptr); put_dax(td->dm_dev.dax_dev); list_del(&td->list); kfree(td); } static struct table_device *find_table_device(struct list_head *l, dev_t dev, - fmode_t mode) + blk_mode_t mode) { struct table_device *td; @@ -802,7 +802,7 @@ static struct table_device *find_table_device(struct list_head *l, dev_t dev, return NULL; } -int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode, +int dm_get_table_device(struct mapped_device *md, dev_t dev, blk_mode_t mode, struct dm_dev **result) { struct table_device *td; diff --git a/drivers/md/dm.h b/drivers/md/dm.h index a856e0aee73b..63d9010d8e61 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -203,7 +203,7 @@ int dm_open_count(struct mapped_device *md); int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred); int dm_cancel_deferred_remove(struct mapped_device *md); int dm_request_based(struct mapped_device *md); -int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode, +int dm_get_table_device(struct mapped_device *md, dev_t dev, blk_mode_t mode, struct dm_dev **result); void dm_put_table_device(struct mapped_device *md, struct dm_dev *d); diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index 91836e6de326..6eaa0eab40f9 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -147,7 +147,8 @@ static void __init md_setup_drive(struct md_setup_args *args) if (p) *p++ = 0; - dev = name_to_dev_t(devname); + if (early_lookup_bdev(devname, &dev)) + dev = 0; if (strncmp(devname, "/dev/", 5) == 0) devname += 5; snprintf(comp_name, 63, "/dev/%s", devname); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index bc8d7565171d..1ff712889a3b 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -54,14 +54,7 @@ __acquires(bitmap->lock) { unsigned char *mappage; - if (page >= bitmap->pages) { - /* This can happen if bitmap_start_sync goes beyond - * End-of-device while looking for a whole page. - * It is harmless. - */ - return -EINVAL; - } - + WARN_ON_ONCE(page >= bitmap->pages); if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */ return 0; @@ -1023,7 +1016,6 @@ static int md_bitmap_file_test_bit(struct bitmap *bitmap, sector_t block) return set; } - /* this gets called when the md device is ready to unplug its underlying * (slave) device queues -- before we let any writes go down, we need to * sync the dirty pages of the bitmap file to disk */ @@ -1033,8 +1025,7 @@ void md_bitmap_unplug(struct bitmap *bitmap) int dirty, need_write; int writing = 0; - if (!bitmap || !bitmap->storage.filemap || - test_bit(BITMAP_STALE, &bitmap->flags)) + if (!md_bitmap_enabled(bitmap)) return; /* look at each page to see if there are any set bits that need to be @@ -1063,6 +1054,35 @@ void md_bitmap_unplug(struct bitmap *bitmap) } EXPORT_SYMBOL(md_bitmap_unplug); +struct bitmap_unplug_work { + struct work_struct work; + struct bitmap *bitmap; + struct completion *done; +}; + +static void md_bitmap_unplug_fn(struct work_struct *work) +{ + struct bitmap_unplug_work *unplug_work = + container_of(work, struct bitmap_unplug_work, work); + + md_bitmap_unplug(unplug_work->bitmap); + complete(unplug_work->done); +} + +void md_bitmap_unplug_async(struct bitmap *bitmap) +{ + DECLARE_COMPLETION_ONSTACK(done); + struct bitmap_unplug_work unplug_work; + + INIT_WORK_ONSTACK(&unplug_work.work, md_bitmap_unplug_fn); + unplug_work.bitmap = bitmap; + unplug_work.done = &done; + + queue_work(md_bitmap_wq, &unplug_work.work); + wait_for_completion(&done); +} +EXPORT_SYMBOL(md_bitmap_unplug_async); + static void md_bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed); /* * bitmap_init_from_disk -- called at bitmap_create time to initialize * the in-memory bitmap from the on-disk bitmap -- also, sets up the @@ -1241,11 +1261,28 @@ static bitmap_counter_t *md_bitmap_get_counter(struct bitmap_counts *bitmap, sector_t offset, sector_t *blocks, int create); +static void mddev_set_timeout(struct mddev *mddev, unsigned long timeout, + bool force) +{ + struct md_thread *thread; + + rcu_read_lock(); + thread = rcu_dereference(mddev->thread); + + if (!thread) + goto out; + + if (force || thread->timeout < MAX_SCHEDULE_TIMEOUT) + thread->timeout = timeout; + +out: + rcu_read_unlock(); +} + /* * bitmap daemon -- periodically wakes up to clean bits and flush pages * out to disk */ - void md_bitmap_daemon_work(struct mddev *mddev) { struct bitmap *bitmap; @@ -1269,7 +1306,7 @@ void md_bitmap_daemon_work(struct mddev *mddev) bitmap->daemon_lastrun = jiffies; if (bitmap->allclean) { - mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + mddev_set_timeout(mddev, MAX_SCHEDULE_TIMEOUT, true); goto done; } bitmap->allclean = 1; @@ -1366,8 +1403,7 @@ void md_bitmap_daemon_work(struct mddev *mddev) done: if (bitmap->allclean == 0) - mddev->thread->timeout = - mddev->bitmap_info.daemon_sleep; + mddev_set_timeout(mddev, mddev->bitmap_info.daemon_sleep, true); mutex_unlock(&mddev->bitmap_info.mutex); } @@ -1387,6 +1423,14 @@ __acquires(bitmap->lock) sector_t csize; int err; + if (page >= bitmap->pages) { + /* + * This can happen if bitmap_start_sync goes beyond + * End-of-device while looking for a whole page or + * user set a huge number to sysfs bitmap_set_bits. + */ + return NULL; + } err = md_bitmap_checkpage(bitmap, page, create, 0); if (bitmap->bp[page].hijacked || @@ -1820,8 +1864,7 @@ void md_bitmap_destroy(struct mddev *mddev) mddev->bitmap = NULL; /* disconnect from the md device */ spin_unlock(&mddev->lock); mutex_unlock(&mddev->bitmap_info.mutex); - if (mddev->thread) - mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT; + mddev_set_timeout(mddev, MAX_SCHEDULE_TIMEOUT, true); md_bitmap_free(bitmap); } @@ -1964,7 +2007,7 @@ int md_bitmap_load(struct mddev *mddev) /* Kick recovery in case any bits were set */ set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery); - mddev->thread->timeout = mddev->bitmap_info.daemon_sleep; + mddev_set_timeout(mddev, mddev->bitmap_info.daemon_sleep, true); md_wakeup_thread(mddev->thread); md_bitmap_update_sb(bitmap); @@ -2469,17 +2512,11 @@ timeout_store(struct mddev *mddev, const char *buf, size_t len) timeout = MAX_SCHEDULE_TIMEOUT-1; if (timeout < 1) timeout = 1; + mddev->bitmap_info.daemon_sleep = timeout; - if (mddev->thread) { - /* if thread->timeout is MAX_SCHEDULE_TIMEOUT, then - * the bitmap is all clean and we don't need to - * adjust the timeout right now - */ - if (mddev->thread->timeout < MAX_SCHEDULE_TIMEOUT) { - mddev->thread->timeout = timeout; - md_wakeup_thread(mddev->thread); - } - } + mddev_set_timeout(mddev, timeout, false); + md_wakeup_thread(mddev->thread); + return len; } diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index cfd7395de8fd..8a3788c9bfef 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -264,6 +264,7 @@ void md_bitmap_sync_with_cluster(struct mddev *mddev, sector_t new_lo, sector_t new_hi); void md_bitmap_unplug(struct bitmap *bitmap); +void md_bitmap_unplug_async(struct bitmap *bitmap); void md_bitmap_daemon_work(struct mddev *mddev); int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks, @@ -273,6 +274,13 @@ int md_bitmap_copy_from_slot(struct mddev *mddev, int slot, sector_t *lo, sector_t *hi, bool clear_bits); void md_bitmap_free(struct bitmap *bitmap); void md_bitmap_wait_behind_writes(struct mddev *mddev); + +static inline bool md_bitmap_enabled(struct bitmap *bitmap) +{ + return bitmap && bitmap->storage.filemap && + !test_bit(BITMAP_STALE, &bitmap->flags); +} + #endif #endif diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 10e0c5381d01..3d9fd74233df 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -75,14 +75,14 @@ struct md_cluster_info { sector_t suspend_hi; int suspend_from; /* the slot which broadcast suspend_lo/hi */ - struct md_thread *recovery_thread; + struct md_thread __rcu *recovery_thread; unsigned long recovery_map; /* communication loc resources */ struct dlm_lock_resource *ack_lockres; struct dlm_lock_resource *message_lockres; struct dlm_lock_resource *token_lockres; struct dlm_lock_resource *no_new_dev_lockres; - struct md_thread *recv_thread; + struct md_thread __rcu *recv_thread; struct completion newdisk_completion; wait_queue_head_t wait; unsigned long state; @@ -362,8 +362,8 @@ static void __recover_slot(struct mddev *mddev, int slot) set_bit(slot, &cinfo->recovery_map); if (!cinfo->recovery_thread) { - cinfo->recovery_thread = md_register_thread(recover_bitmaps, - mddev, "recover"); + rcu_assign_pointer(cinfo->recovery_thread, + md_register_thread(recover_bitmaps, mddev, "recover")); if (!cinfo->recovery_thread) { pr_warn("md-cluster: Could not create recovery thread\n"); return; @@ -526,11 +526,15 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg) static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg) { int got_lock = 0; + struct md_thread *thread; struct md_cluster_info *cinfo = mddev->cluster_info; mddev->good_device_nr = le32_to_cpu(msg->raid_slot); dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR); - wait_event(mddev->thread->wqueue, + + /* daemaon thread must exist */ + thread = rcu_dereference_protected(mddev->thread, true); + wait_event(thread->wqueue, (got_lock = mddev_trylock(mddev)) || test_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state)); md_reload_sb(mddev, mddev->good_device_nr); @@ -889,7 +893,8 @@ static int join(struct mddev *mddev, int nodes) } /* Initiate the communication resources */ ret = -ENOMEM; - cinfo->recv_thread = md_register_thread(recv_daemon, mddev, "cluster_recv"); + rcu_assign_pointer(cinfo->recv_thread, + md_register_thread(recv_daemon, mddev, "cluster_recv")); if (!cinfo->recv_thread) { pr_err("md-cluster: cannot allocate memory for recv_thread!\n"); goto err; diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 66edf5e72bd6..92c45be203d7 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -400,8 +400,8 @@ static int multipath_run (struct mddev *mddev) if (ret) goto out_free_conf; - mddev->thread = md_register_thread(multipathd, mddev, - "multipath"); + rcu_assign_pointer(mddev->thread, + md_register_thread(multipathd, mddev, "multipath")); if (!mddev->thread) goto out_free_conf; diff --git a/drivers/md/md.c b/drivers/md/md.c index 8e344b4b3444..cf3733c90c47 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -70,11 +70,7 @@ #include "md-bitmap.h" #include "md-cluster.h" -/* pers_list is a list of registered personalities protected - * by pers_lock. - * pers_lock does extra service to protect accesses to - * mddev->thread when the mutex cannot be held. - */ +/* pers_list is a list of registered personalities protected by pers_lock. */ static LIST_HEAD(pers_list); static DEFINE_SPINLOCK(pers_lock); @@ -87,23 +83,13 @@ static struct module *md_cluster_mod; static DECLARE_WAIT_QUEUE_HEAD(resync_wait); static struct workqueue_struct *md_wq; static struct workqueue_struct *md_misc_wq; -static struct workqueue_struct *md_rdev_misc_wq; +struct workqueue_struct *md_bitmap_wq; static int remove_and_add_spares(struct mddev *mddev, struct md_rdev *this); static void mddev_detach(struct mddev *mddev); - -enum md_ro_state { - MD_RDWR, - MD_RDONLY, - MD_AUTO_READ, - MD_MAX_STATE -}; - -static bool md_is_rdwr(struct mddev *mddev) -{ - return (mddev->ro == MD_RDWR); -} +static void export_rdev(struct md_rdev *rdev, struct mddev *mddev); +static void md_wakeup_thread_directly(struct md_thread __rcu *thread); /* * Default number of read corrections we'll attempt on an rdev @@ -360,10 +346,6 @@ EXPORT_SYMBOL_GPL(md_new_event); static LIST_HEAD(all_mddevs); static DEFINE_SPINLOCK(all_mddevs_lock); -static bool is_md_suspended(struct mddev *mddev) -{ - return percpu_ref_is_dying(&mddev->active_io); -} /* Rather than calling directly into the personality make_request function, * IO requests come here first so that we can check if the device is * being suspended pending a reconfiguration. @@ -457,13 +439,19 @@ static void md_submit_bio(struct bio *bio) */ void mddev_suspend(struct mddev *mddev) { - WARN_ON_ONCE(mddev->thread && current == mddev->thread->tsk); - lockdep_assert_held(&mddev->reconfig_mutex); + struct md_thread *thread = rcu_dereference_protected(mddev->thread, + lockdep_is_held(&mddev->reconfig_mutex)); + + WARN_ON_ONCE(thread && current == thread->tsk); if (mddev->suspended++) return; wake_up(&mddev->sb_wait); set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags); percpu_ref_kill(&mddev->active_io); + + if (mddev->pers->prepare_suspend) + mddev->pers->prepare_suspend(mddev); + wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io)); mddev->pers->quiesce(mddev, 1); clear_bit_unlock(MD_ALLOW_SB_UPDATE, &mddev->flags); @@ -655,9 +643,11 @@ void mddev_init(struct mddev *mddev) { mutex_init(&mddev->open_mutex); mutex_init(&mddev->reconfig_mutex); + mutex_init(&mddev->delete_mutex); mutex_init(&mddev->bitmap_info.mutex); INIT_LIST_HEAD(&mddev->disks); INIT_LIST_HEAD(&mddev->all_mddevs); + INIT_LIST_HEAD(&mddev->deleting); timer_setup(&mddev->safemode_timer, md_safemode_timeout, 0); atomic_set(&mddev->active, 1); atomic_set(&mddev->openers, 0); @@ -759,6 +749,24 @@ static void mddev_free(struct mddev *mddev) static const struct attribute_group md_redundancy_group; +static void md_free_rdev(struct mddev *mddev) +{ + struct md_rdev *rdev; + struct md_rdev *tmp; + + mutex_lock(&mddev->delete_mutex); + if (list_empty(&mddev->deleting)) + goto out; + + list_for_each_entry_safe(rdev, tmp, &mddev->deleting, same_set) { + list_del_init(&rdev->same_set); + kobject_del(&rdev->kobj); + export_rdev(rdev, mddev); + } +out: + mutex_unlock(&mddev->delete_mutex); +} + void mddev_unlock(struct mddev *mddev) { if (mddev->to_remove) { @@ -800,13 +808,10 @@ void mddev_unlock(struct mddev *mddev) } else mutex_unlock(&mddev->reconfig_mutex); - /* As we've dropped the mutex we need a spinlock to - * make sure the thread doesn't disappear - */ - spin_lock(&pers_lock); + md_free_rdev(mddev); + md_wakeup_thread(mddev->thread); wake_up(&mddev->sb_wait); - spin_unlock(&pers_lock); } EXPORT_SYMBOL_GPL(mddev_unlock); @@ -938,7 +943,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, atomic_inc(&rdev->nr_pending); bio->bi_iter.bi_sector = sector; - bio_add_page(bio, page, size, 0); + __bio_add_page(bio, page, size, 0); bio->bi_private = rdev; bio->bi_end_io = super_written; @@ -979,7 +984,7 @@ int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, bio.bi_iter.bi_sector = sector + rdev->new_data_offset; else bio.bi_iter.bi_sector = sector + rdev->data_offset; - bio_add_page(&bio, page, size, 0); + __bio_add_page(&bio, page, size, 0); submit_bio_wait(&bio); @@ -2440,16 +2445,12 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev) return err; } -static void rdev_delayed_delete(struct work_struct *ws) -{ - struct md_rdev *rdev = container_of(ws, struct md_rdev, del_work); - kobject_del(&rdev->kobj); - kobject_put(&rdev->kobj); -} - void md_autodetect_dev(dev_t dev); -static void export_rdev(struct md_rdev *rdev) +/* just for claiming the bdev */ +static struct md_rdev claim_rdev; + +static void export_rdev(struct md_rdev *rdev, struct mddev *mddev) { pr_debug("md: export_rdev(%pg)\n", rdev->bdev); md_rdev_clear(rdev); @@ -2457,13 +2458,15 @@ static void export_rdev(struct md_rdev *rdev) if (test_bit(AutoDetected, &rdev->flags)) md_autodetect_dev(rdev->bdev->bd_dev); #endif - blkdev_put(rdev->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(rdev->bdev, mddev->major_version == -2 ? &claim_rdev : rdev); rdev->bdev = NULL; kobject_put(&rdev->kobj); } static void md_kick_rdev_from_array(struct md_rdev *rdev) { + struct mddev *mddev = rdev->mddev; + bd_unlink_disk_holder(rdev->bdev, rdev->mddev->gendisk); list_del_rcu(&rdev->same_set); pr_debug("md: unbind<%pg>\n", rdev->bdev); @@ -2477,15 +2480,17 @@ static void md_kick_rdev_from_array(struct md_rdev *rdev) rdev->sysfs_unack_badblocks = NULL; rdev->sysfs_badblocks = NULL; rdev->badblocks.count = 0; - /* We need to delay this, otherwise we can deadlock when - * writing to 'remove' to "dev/state". We also need - * to delay it due to rcu usage. - */ + synchronize_rcu(); - INIT_WORK(&rdev->del_work, rdev_delayed_delete); - kobject_get(&rdev->kobj); - queue_work(md_rdev_misc_wq, &rdev->del_work); - export_rdev(rdev); + + /* + * kobject_del() will wait for all in progress writers to be done, where + * reconfig_mutex is held, hence it can't be called under + * reconfig_mutex and it's delayed to mddev_unlock(). + */ + mutex_lock(&mddev->delete_mutex); + list_add(&rdev->same_set, &mddev->deleting); + mutex_unlock(&mddev->delete_mutex); } static void export_array(struct mddev *mddev) @@ -3553,6 +3558,7 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, { struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr); struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj); + struct kernfs_node *kn = NULL; ssize_t rv; struct mddev *mddev = rdev->mddev; @@ -3560,6 +3566,10 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, return -EIO; if (!capable(CAP_SYS_ADMIN)) return -EACCES; + + if (entry->store == state_store && cmd_match(page, "remove")) + kn = sysfs_break_active_protection(kobj, attr); + rv = mddev ? mddev_lock(mddev) : -ENODEV; if (!rv) { if (rdev->mddev == NULL) @@ -3568,6 +3578,10 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, rv = entry->store(rdev, page, length); mddev_unlock(mddev); } + + if (kn) + sysfs_unbreak_active_protection(kn); + return rv; } @@ -3612,6 +3626,7 @@ int md_rdev_init(struct md_rdev *rdev) return badblocks_init(&rdev->badblocks, 0); } EXPORT_SYMBOL_GPL(md_rdev_init); + /* * Import a device. If 'super_format' >= 0, then sanity check the superblock * @@ -3624,7 +3639,6 @@ EXPORT_SYMBOL_GPL(md_rdev_init); */ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor) { - static struct md_rdev claim_rdev; /* just for claiming the bdev */ struct md_rdev *rdev; sector_t size; int err; @@ -3640,9 +3654,8 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe if (err) goto out_clear_rdev; - rdev->bdev = blkdev_get_by_dev(newdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, - super_format == -2 ? &claim_rdev : rdev); + rdev->bdev = blkdev_get_by_dev(newdev, BLK_OPEN_READ | BLK_OPEN_WRITE, + super_format == -2 ? &claim_rdev : rdev, NULL); if (IS_ERR(rdev->bdev)) { pr_warn("md: could not open device unknown-block(%u,%u).\n", MAJOR(newdev), MINOR(newdev)); @@ -3679,7 +3692,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe return rdev; out_blkdev_put: - blkdev_put(rdev->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(rdev->bdev, super_format == -2 ? &claim_rdev : rdev); out_clear_rdev: md_rdev_clear(rdev); out_free_rdev: @@ -3794,8 +3807,9 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale) static ssize_t safe_delay_show(struct mddev *mddev, char *page) { - int msec = (mddev->safemode_delay*1000)/HZ; - return sprintf(page, "%d.%03d\n", msec/1000, msec%1000); + unsigned int msec = ((unsigned long)mddev->safemode_delay*1000)/HZ; + + return sprintf(page, "%u.%03u\n", msec/1000, msec%1000); } static ssize_t safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len) @@ -3807,7 +3821,7 @@ safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len) return -EINVAL; } - if (strict_strtoul_scaled(cbuf, &msec, 3) < 0) + if (strict_strtoul_scaled(cbuf, &msec, 3) < 0 || msec > UINT_MAX / HZ) return -EINVAL; if (msec == 0) mddev->safemode_delay = 0; @@ -4477,6 +4491,8 @@ max_corrected_read_errors_store(struct mddev *mddev, const char *buf, size_t len rv = kstrtouint(buf, 10, &n); if (rv < 0) return rv; + if (n > INT_MAX) + return -EINVAL; atomic_set(&mddev->max_corr_read_errors, n); return len; } @@ -4491,20 +4507,6 @@ null_show(struct mddev *mddev, char *page) return -EINVAL; } -/* need to ensure rdev_delayed_delete() has completed */ -static void flush_rdev_wq(struct mddev *mddev) -{ - struct md_rdev *rdev; - - rcu_read_lock(); - rdev_for_each_rcu(rdev, mddev) - if (work_pending(&rdev->del_work)) { - flush_workqueue(md_rdev_misc_wq); - break; - } - rcu_read_unlock(); -} - static ssize_t new_dev_store(struct mddev *mddev, const char *buf, size_t len) { @@ -4532,7 +4534,6 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len) minor != MINOR(dev)) return -EOVERFLOW; - flush_rdev_wq(mddev); err = mddev_lock(mddev); if (err) return err; @@ -4560,7 +4561,7 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len) err = bind_rdev_to_array(rdev, mddev); out: if (err) - export_rdev(rdev); + export_rdev(rdev, mddev); mddev_unlock(mddev); if (!err) md_new_event(); @@ -4804,11 +4805,21 @@ action_store(struct mddev *mddev, const char *page, size_t len) return -EINVAL; err = mddev_lock(mddev); if (!err) { - if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { err = -EBUSY; - else { + } else if (mddev->reshape_position == MaxSector || + mddev->pers->check_reshape == NULL || + mddev->pers->check_reshape(mddev)) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); err = mddev->pers->start_reshape(mddev); + } else { + /* + * If reshape is still in progress, and + * md_check_recovery() can continue to reshape, + * don't restart reshape because data can be + * corrupted for raid456. + */ + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } mddev_unlock(mddev); } @@ -5592,7 +5603,6 @@ struct mddev *md_alloc(dev_t dev, char *name) * removed (mddev_delayed_delete). */ flush_workqueue(md_misc_wq); - flush_workqueue(md_rdev_misc_wq); mutex_lock(&disks_mutex); mddev = mddev_alloc(dev); @@ -6269,10 +6279,12 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) } if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) set_bit(MD_RECOVERY_INTR, &mddev->recovery); - if (mddev->sync_thread) - /* Thread might be blocked waiting for metadata update - * which will now never happen */ - wake_up_process(mddev->sync_thread->tsk); + + /* + * Thread might be blocked waiting for metadata update which will now + * never happen + */ + md_wakeup_thread_directly(mddev->sync_thread); if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) return -EBUSY; @@ -6333,10 +6345,12 @@ static int do_md_stop(struct mddev *mddev, int mode, } if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) set_bit(MD_RECOVERY_INTR, &mddev->recovery); - if (mddev->sync_thread) - /* Thread might be blocked waiting for metadata update - * which will now never happen */ - wake_up_process(mddev->sync_thread->tsk); + + /* + * Thread might be blocked waiting for metadata update which will now + * never happen + */ + md_wakeup_thread_directly(mddev->sync_thread); mddev_unlock(mddev); wait_event(resync_wait, (mddev->sync_thread == NULL && @@ -6498,7 +6512,7 @@ static void autorun_devices(int part) rdev_for_each_list(rdev, tmp, &candidates) { list_del_init(&rdev->same_set); if (bind_rdev_to_array(rdev, mddev)) - export_rdev(rdev); + export_rdev(rdev, mddev); } autorun_array(mddev); mddev_unlock(mddev); @@ -6508,7 +6522,7 @@ static void autorun_devices(int part) */ rdev_for_each_list(rdev, tmp, &candidates) { list_del_init(&rdev->same_set); - export_rdev(rdev); + export_rdev(rdev, mddev); } mddev_put(mddev); } @@ -6696,13 +6710,13 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) pr_warn("md: %pg has different UUID to %pg\n", rdev->bdev, rdev0->bdev); - export_rdev(rdev); + export_rdev(rdev, mddev); return -EINVAL; } } err = bind_rdev_to_array(rdev, mddev); if (err) - export_rdev(rdev); + export_rdev(rdev, mddev); return err; } @@ -6733,7 +6747,6 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) if (info->state & (1<<MD_DISK_SYNC) && info->raid_disk < mddev->raid_disks) { rdev->raid_disk = info->raid_disk; - set_bit(In_sync, &rdev->flags); clear_bit(Bitmap_sync, &rdev->flags); } else rdev->raid_disk = -1; @@ -6746,7 +6759,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) /* This was a hot-add request, but events doesn't * match, so reject it. */ - export_rdev(rdev); + export_rdev(rdev, mddev); return -EINVAL; } @@ -6772,7 +6785,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) } } if (has_journal || mddev->bitmap) { - export_rdev(rdev); + export_rdev(rdev, mddev); return -EBUSY; } set_bit(Journal, &rdev->flags); @@ -6787,7 +6800,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) /* --add initiated by this node */ err = md_cluster_ops->add_new_disk(mddev, rdev); if (err) { - export_rdev(rdev); + export_rdev(rdev, mddev); return err; } } @@ -6797,7 +6810,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) err = bind_rdev_to_array(rdev, mddev); if (err) - export_rdev(rdev); + export_rdev(rdev, mddev); if (mddev_is_clustered(mddev)) { if (info->state & (1 << MD_DISK_CANDIDATE)) { @@ -6860,7 +6873,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) err = bind_rdev_to_array(rdev, mddev); if (err) { - export_rdev(rdev); + export_rdev(rdev, mddev); return err; } } @@ -6985,7 +6998,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) return 0; abort_export: - export_rdev(rdev); + export_rdev(rdev, mddev); return err; } @@ -7486,7 +7499,7 @@ static int __md_set_array_info(struct mddev *mddev, void __user *argp) return err; } -static int md_ioctl(struct block_device *bdev, fmode_t mode, +static int md_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { int err = 0; @@ -7555,9 +7568,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, } - if (cmd == ADD_NEW_DISK || cmd == HOT_ADD_DISK) - flush_rdev_wq(mddev); - if (cmd == HOT_REMOVE_DISK) /* need to ensure recovery thread has run */ wait_event_interruptible_timeout(mddev->sb_wait, @@ -7718,7 +7728,7 @@ out: return err; } #ifdef CONFIG_COMPAT -static int md_compat_ioctl(struct block_device *bdev, fmode_t mode, +static int md_compat_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { switch (cmd) { @@ -7767,13 +7777,13 @@ out_unlock: return err; } -static int md_open(struct block_device *bdev, fmode_t mode) +static int md_open(struct gendisk *disk, blk_mode_t mode) { struct mddev *mddev; int err; spin_lock(&all_mddevs_lock); - mddev = mddev_get(bdev->bd_disk->private_data); + mddev = mddev_get(disk->private_data); spin_unlock(&all_mddevs_lock); if (!mddev) return -ENODEV; @@ -7789,7 +7799,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) atomic_inc(&mddev->openers); mutex_unlock(&mddev->open_mutex); - bdev_check_media_change(bdev); + disk_check_media_change(disk); return 0; out_unlock: @@ -7799,7 +7809,7 @@ out: return err; } -static void md_release(struct gendisk *disk, fmode_t mode) +static void md_release(struct gendisk *disk) { struct mddev *mddev = disk->private_data; @@ -7886,13 +7896,29 @@ static int md_thread(void *arg) return 0; } -void md_wakeup_thread(struct md_thread *thread) +static void md_wakeup_thread_directly(struct md_thread __rcu *thread) { - if (thread) { - pr_debug("md: waking up MD thread %s.\n", thread->tsk->comm); - set_bit(THREAD_WAKEUP, &thread->flags); - wake_up(&thread->wqueue); + struct md_thread *t; + + rcu_read_lock(); + t = rcu_dereference(thread); + if (t) + wake_up_process(t->tsk); + rcu_read_unlock(); +} + +void md_wakeup_thread(struct md_thread __rcu *thread) +{ + struct md_thread *t; + + rcu_read_lock(); + t = rcu_dereference(thread); + if (t) { + pr_debug("md: waking up MD thread %s.\n", t->tsk->comm); + set_bit(THREAD_WAKEUP, &t->flags); + wake_up(&t->wqueue); } + rcu_read_unlock(); } EXPORT_SYMBOL(md_wakeup_thread); @@ -7922,22 +7948,15 @@ struct md_thread *md_register_thread(void (*run) (struct md_thread *), } EXPORT_SYMBOL(md_register_thread); -void md_unregister_thread(struct md_thread **threadp) +void md_unregister_thread(struct md_thread __rcu **threadp) { - struct md_thread *thread; + struct md_thread *thread = rcu_dereference_protected(*threadp, true); - /* - * Locking ensures that mddev_unlock does not wake_up a - * non-existent thread - */ - spin_lock(&pers_lock); - thread = *threadp; - if (!thread) { - spin_unlock(&pers_lock); + if (!thread) return; - } - *threadp = NULL; - spin_unlock(&pers_lock); + + rcu_assign_pointer(*threadp, NULL); + synchronize_rcu(); pr_debug("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk)); kthread_stop(thread->tsk); @@ -9100,6 +9119,7 @@ void md_do_sync(struct md_thread *thread) spin_unlock(&mddev->lock); wake_up(&resync_wait); + wake_up(&mddev->sb_wait); md_wakeup_thread(mddev->thread); return; } @@ -9202,9 +9222,8 @@ static void md_start_sync(struct work_struct *ws) { struct mddev *mddev = container_of(ws, struct mddev, del_work); - mddev->sync_thread = md_register_thread(md_do_sync, - mddev, - "resync"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "resync")); if (!mddev->sync_thread) { pr_warn("%s: could not start resync thread...\n", mdname(mddev)); @@ -9619,9 +9638,10 @@ static int __init md_init(void) if (!md_misc_wq) goto err_misc_wq; - md_rdev_misc_wq = alloc_workqueue("md_rdev_misc", 0, 0); - if (!md_rdev_misc_wq) - goto err_rdev_misc_wq; + md_bitmap_wq = alloc_workqueue("md_bitmap", WQ_MEM_RECLAIM | WQ_UNBOUND, + 0); + if (!md_bitmap_wq) + goto err_bitmap_wq; ret = __register_blkdev(MD_MAJOR, "md", md_probe); if (ret < 0) @@ -9641,8 +9661,8 @@ static int __init md_init(void) err_mdp: unregister_blkdev(MD_MAJOR, "md"); err_md: - destroy_workqueue(md_rdev_misc_wq); -err_rdev_misc_wq: + destroy_workqueue(md_bitmap_wq); +err_bitmap_wq: destroy_workqueue(md_misc_wq); err_misc_wq: destroy_workqueue(md_wq); @@ -9938,8 +9958,8 @@ static __exit void md_exit(void) } spin_unlock(&all_mddevs_lock); - destroy_workqueue(md_rdev_misc_wq); destroy_workqueue(md_misc_wq); + destroy_workqueue(md_bitmap_wq); destroy_workqueue(md_wq); } diff --git a/drivers/md/md.h b/drivers/md/md.h index fd8f260ed5f8..bfd2306bc750 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -122,8 +122,6 @@ struct md_rdev { struct serial_in_rdev *serial; /* used for raid1 io serialization */ - struct work_struct del_work; /* used for delayed sysfs removal */ - struct kernfs_node *sysfs_state; /* handle for 'state' * sysfs entry */ /* handle for 'unacknowledged_bad_blocks' sysfs dentry */ @@ -367,8 +365,8 @@ struct mddev { int new_chunk_sectors; int reshape_backwards; - struct md_thread *thread; /* management thread */ - struct md_thread *sync_thread; /* doing resync or reconstruct */ + struct md_thread __rcu *thread; /* management thread */ + struct md_thread __rcu *sync_thread; /* doing resync or reconstruct */ /* 'last_sync_action' is initialized to "none". It is set when a * sync operation (i.e "data-check", "requested-resync", "resync", @@ -531,6 +529,14 @@ struct mddev { unsigned int good_device_nr; /* good device num within cluster raid */ unsigned int noio_flag; /* for memalloc scope API */ + /* + * Temporarily store rdev that will be finally removed when + * reconfig_mutex is unlocked. + */ + struct list_head deleting; + /* Protect the deleting list */ + struct mutex delete_mutex; + bool has_superblocks:1; bool fail_last_dev:1; bool serialize_policy:1; @@ -555,6 +561,23 @@ enum recovery_flags { MD_RESYNCING_REMOTE, /* remote node is running resync thread */ }; +enum md_ro_state { + MD_RDWR, + MD_RDONLY, + MD_AUTO_READ, + MD_MAX_STATE +}; + +static inline bool md_is_rdwr(struct mddev *mddev) +{ + return (mddev->ro == MD_RDWR); +} + +static inline bool is_md_suspended(struct mddev *mddev) +{ + return percpu_ref_is_dying(&mddev->active_io); +} + static inline int __must_check mddev_lock(struct mddev *mddev) { return mutex_lock_interruptible(&mddev->reconfig_mutex); @@ -614,6 +637,7 @@ struct md_personality int (*start_reshape) (struct mddev *mddev); void (*finish_reshape) (struct mddev *mddev); void (*update_reshape_pos) (struct mddev *mddev); + void (*prepare_suspend) (struct mddev *mddev); /* quiesce suspends or resumes internal processing. * 1 - stop new actions and wait for action io to complete * 0 - return to normal behaviour @@ -734,8 +758,8 @@ extern struct md_thread *md_register_thread( void (*run)(struct md_thread *thread), struct mddev *mddev, const char *name); -extern void md_unregister_thread(struct md_thread **threadp); -extern void md_wakeup_thread(struct md_thread *thread); +extern void md_unregister_thread(struct md_thread __rcu **threadp); +extern void md_wakeup_thread(struct md_thread __rcu *thread); extern void md_check_recovery(struct mddev *mddev); extern void md_reap_sync_thread(struct mddev *mddev); extern int mddev_init_writes_pending(struct mddev *mddev); @@ -828,6 +852,7 @@ struct mdu_array_info_s; struct mdu_disk_info_s; extern int mdp_major; +extern struct workqueue_struct *md_bitmap_wq; void md_autostart_arrays(int part); int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info); int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info); diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index e61f6cad4e08..169ebe296f2d 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -21,6 +21,7 @@ #define IO_MADE_GOOD ((struct bio *)2) #define BIO_SPECIAL(bio) ((unsigned long)bio <= 2) +#define MAX_PLUG_BIO 32 /* for managing resync I/O pages */ struct resync_pages { @@ -31,6 +32,7 @@ struct resync_pages { struct raid1_plug_cb { struct blk_plug_cb cb; struct bio_list pending; + unsigned int count; }; static void rbio_pool_free(void *rbio, void *data) @@ -101,11 +103,73 @@ static void md_bio_reset_resync_pages(struct bio *bio, struct resync_pages *rp, struct page *page = resync_fetch_page(rp, idx); int len = min_t(int, size, PAGE_SIZE); - /* - * won't fail because the vec table is big - * enough to hold all these pages - */ - bio_add_page(bio, page, len, 0); + if (WARN_ON(!bio_add_page(bio, page, len, 0))) { + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + return; + } + size -= len; } while (idx++ < RESYNC_PAGES && size > 0); } + + +static inline void raid1_submit_write(struct bio *bio) +{ + struct md_rdev *rdev = (struct md_rdev *)bio->bi_bdev; + + bio->bi_next = NULL; + bio_set_dev(bio, rdev->bdev); + if (test_bit(Faulty, &rdev->flags)) + bio_io_error(bio); + else if (unlikely(bio_op(bio) == REQ_OP_DISCARD && + !bdev_max_discard_sectors(bio->bi_bdev))) + /* Just ignore it */ + bio_endio(bio); + else + submit_bio_noacct(bio); +} + +static inline bool raid1_add_bio_to_plug(struct mddev *mddev, struct bio *bio, + blk_plug_cb_fn unplug, int copies) +{ + struct raid1_plug_cb *plug = NULL; + struct blk_plug_cb *cb; + + /* + * If bitmap is not enabled, it's safe to submit the io directly, and + * this can get optimal performance. + */ + if (!md_bitmap_enabled(mddev->bitmap)) { + raid1_submit_write(bio); + return true; + } + + cb = blk_check_plugged(unplug, mddev, sizeof(*plug)); + if (!cb) + return false; + + plug = container_of(cb, struct raid1_plug_cb, cb); + bio_list_add(&plug->pending, bio); + if (++plug->count / MAX_PLUG_BIO >= copies) { + list_del(&cb->list); + cb->callback(cb, false); + } + + + return true; +} + +/* + * current->bio_list will be set under submit_bio() context, in this case bitmap + * io will be added to the list and wait for current io submission to finish, + * while current io submission must wait for bitmap io to be done. In order to + * avoid such deadlock, submit bitmap io asynchronously. + */ +static inline void raid1_prepare_flush_writes(struct bitmap *bitmap) +{ + if (current->bio_list) + md_bitmap_unplug_async(bitmap); + else + md_bitmap_unplug(bitmap); +} diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 68a9e2d9985b..dd25832eb045 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -794,22 +794,13 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect static void flush_bio_list(struct r1conf *conf, struct bio *bio) { /* flush any pending bitmap writes to disk before proceeding w/ I/O */ - md_bitmap_unplug(conf->mddev->bitmap); + raid1_prepare_flush_writes(conf->mddev->bitmap); wake_up(&conf->wait_barrier); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; - struct md_rdev *rdev = (void *)bio->bi_bdev; - bio->bi_next = NULL; - bio_set_dev(bio, rdev->bdev); - if (test_bit(Faulty, &rdev->flags)) { - bio_io_error(bio); - } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(bio->bi_bdev))) - /* Just ignore it */ - bio_endio(bio); - else - submit_bio_noacct(bio); + + raid1_submit_write(bio); bio = next; cond_resched(); } @@ -1147,7 +1138,10 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio, if (unlikely(!page)) goto free_pages; - bio_add_page(behind_bio, page, len, 0); + if (!bio_add_page(behind_bio, page, len, 0)) { + put_page(page); + goto free_pages; + } size -= len; i++; @@ -1175,7 +1169,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) struct r1conf *conf = mddev->private; struct bio *bio; - if (from_schedule || current->bio_list) { + if (from_schedule) { spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->pending_bio_list, &plug->pending); spin_unlock_irq(&conf->device_lock); @@ -1343,8 +1337,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, struct bitmap *bitmap = mddev->bitmap; unsigned long flags; struct md_rdev *blocked_rdev; - struct blk_plug_cb *cb; - struct raid1_plug_cb *plug = NULL; int first_clone; int max_sectors; bool write_behind = false; @@ -1573,15 +1565,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, r1_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_bdev = (void *)rdev; - - cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug)); - if (cb) - plug = container_of(cb, struct raid1_plug_cb, cb); - else - plug = NULL; - if (plug) { - bio_list_add(&plug->pending, mbio); - } else { + if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) { spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); spin_unlock_irqrestore(&conf->device_lock, flags); @@ -2914,7 +2898,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, * won't fail because the vec table is big * enough to hold all these pages */ - bio_add_page(bio, page, len, 0); + __bio_add_page(bio, page, len, 0); } } nr_sectors += len>>9; @@ -3084,7 +3068,8 @@ static struct r1conf *setup_conf(struct mddev *mddev) } err = -ENOMEM; - conf->thread = md_register_thread(raid1d, mddev, "raid1"); + rcu_assign_pointer(conf->thread, + md_register_thread(raid1d, mddev, "raid1")); if (!conf->thread) goto abort; @@ -3177,8 +3162,8 @@ static int raid1_run(struct mddev *mddev) /* * Ok, everything is just fine now */ - mddev->thread = conf->thread; - conf->thread = NULL; + rcu_assign_pointer(mddev->thread, conf->thread); + rcu_assign_pointer(conf->thread, NULL); mddev->private = conf; set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags); diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index ebb6788820e7..468f189da7a0 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -130,7 +130,7 @@ struct r1conf { /* When taking over an array from a different personality, we store * the new thread here until we fully activate the array. */ - struct md_thread *thread; + struct md_thread __rcu *thread; /* Keep track of cluster resync window to send to other * nodes. diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 4fcfcb350d2b..d0de8c9fb3cf 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -779,8 +779,16 @@ static struct md_rdev *read_balance(struct r10conf *conf, disk = r10_bio->devs[slot].devnum; rdev = rcu_dereference(conf->mirrors[disk].replacement); if (rdev == NULL || test_bit(Faulty, &rdev->flags) || - r10_bio->devs[slot].addr + sectors > rdev->recovery_offset) + r10_bio->devs[slot].addr + sectors > + rdev->recovery_offset) { + /* + * Read replacement first to prevent reading both rdev + * and replacement as NULL during replacement replace + * rdev. + */ + smp_mb(); rdev = rcu_dereference(conf->mirrors[disk].rdev); + } if (rdev == NULL || test_bit(Faulty, &rdev->flags)) continue; @@ -902,25 +910,15 @@ static void flush_pending_writes(struct r10conf *conf) __set_current_state(TASK_RUNNING); blk_start_plug(&plug); - /* flush any pending bitmap writes to disk - * before proceeding w/ I/O */ - md_bitmap_unplug(conf->mddev->bitmap); + raid1_prepare_flush_writes(conf->mddev->bitmap); wake_up(&conf->wait_barrier); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; - struct md_rdev *rdev = (void*)bio->bi_bdev; - bio->bi_next = NULL; - bio_set_dev(bio, rdev->bdev); - if (test_bit(Faulty, &rdev->flags)) { - bio_io_error(bio); - } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(bio->bi_bdev))) - /* Just ignore it */ - bio_endio(bio); - else - submit_bio_noacct(bio); + + raid1_submit_write(bio); bio = next; + cond_resched(); } blk_finish_plug(&plug); } else @@ -982,6 +980,7 @@ static void lower_barrier(struct r10conf *conf) static bool stop_waiting_barrier(struct r10conf *conf) { struct bio_list *bio_list = current->bio_list; + struct md_thread *thread; /* barrier is dropped */ if (!conf->barrier) @@ -997,12 +996,14 @@ static bool stop_waiting_barrier(struct r10conf *conf) (!bio_list_empty(&bio_list[0]) || !bio_list_empty(&bio_list[1]))) return true; + /* daemon thread must exist while handling io */ + thread = rcu_dereference_protected(conf->mddev->thread, true); /* * move on if io is issued from raid10d(), nr_pending is not released * from original io(see handle_read_error()). All raise barrier is * blocked until this io is done. */ - if (conf->mddev->thread->tsk == current) { + if (thread->tsk == current) { WARN_ON_ONCE(atomic_read(&conf->nr_pending) == 0); return true; } @@ -1113,7 +1114,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) struct r10conf *conf = mddev->private; struct bio *bio; - if (from_schedule || current->bio_list) { + if (from_schedule) { spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->pending_bio_list, &plug->pending); spin_unlock_irq(&conf->device_lock); @@ -1125,23 +1126,15 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) /* we aren't scheduling, so we can do the write-out directly. */ bio = bio_list_get(&plug->pending); - md_bitmap_unplug(mddev->bitmap); + raid1_prepare_flush_writes(mddev->bitmap); wake_up(&conf->wait_barrier); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; - struct md_rdev *rdev = (void*)bio->bi_bdev; - bio->bi_next = NULL; - bio_set_dev(bio, rdev->bdev); - if (test_bit(Faulty, &rdev->flags)) { - bio_io_error(bio); - } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(bio->bi_bdev))) - /* Just ignore it */ - bio_endio(bio); - else - submit_bio_noacct(bio); + + raid1_submit_write(bio); bio = next; + cond_resched(); } kfree(plug); } @@ -1282,8 +1275,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC; const blk_opf_t do_fua = bio->bi_opf & REQ_FUA; unsigned long flags; - struct blk_plug_cb *cb; - struct raid1_plug_cb *plug = NULL; struct r10conf *conf = mddev->private; struct md_rdev *rdev; int devnum = r10_bio->devs[n_copy].devnum; @@ -1323,14 +1314,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, atomic_inc(&r10_bio->remaining); - cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug)); - if (cb) - plug = container_of(cb, struct raid1_plug_cb, cb); - else - plug = NULL; - if (plug) { - bio_list_add(&plug->pending, mbio); - } else { + if (!raid1_add_bio_to_plug(mddev, mbio, raid10_unplug, conf->copies)) { spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); spin_unlock_irqrestore(&conf->device_lock, flags); @@ -1479,9 +1463,15 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, for (i = 0; i < conf->copies; i++) { int d = r10_bio->devs[i].devnum; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[d].replacement); + struct md_rdev *rdev, *rrdev; + + rrdev = rcu_dereference(conf->mirrors[d].replacement); + /* + * Read replacement first to prevent reading both rdev and + * replacement as NULL during replacement replace rdev. + */ + smp_mb(); + rdev = rcu_dereference(conf->mirrors[d].rdev); if (rdev == rrdev) rrdev = NULL; if (rdev && (test_bit(Faulty, &rdev->flags))) @@ -2148,9 +2138,10 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) { struct r10conf *conf = mddev->private; int err = -EEXIST; - int mirror; + int mirror, repl_slot = -1; int first = 0; int last = conf->geo.raid_disks - 1; + struct raid10_info *p; if (mddev->recovery_cp < MaxSector) /* only hot-add to in-sync arrays, as recovery is @@ -2173,23 +2164,14 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) else mirror = first; for ( ; mirror <= last ; mirror++) { - struct raid10_info *p = &conf->mirrors[mirror]; + p = &conf->mirrors[mirror]; if (p->recovery_disabled == mddev->recovery_disabled) continue; if (p->rdev) { - if (!test_bit(WantReplacement, &p->rdev->flags) || - p->replacement != NULL) - continue; - clear_bit(In_sync, &rdev->flags); - set_bit(Replacement, &rdev->flags); - rdev->raid_disk = mirror; - err = 0; - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - conf->fullsync = 1; - rcu_assign_pointer(p->replacement, rdev); - break; + if (test_bit(WantReplacement, &p->rdev->flags) && + p->replacement == NULL && repl_slot < 0) + repl_slot = mirror; + continue; } if (mddev->gendisk) @@ -2206,6 +2188,19 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } + if (err && repl_slot >= 0) { + p = &conf->mirrors[repl_slot]; + clear_bit(In_sync, &rdev->flags); + set_bit(Replacement, &rdev->flags); + rdev->raid_disk = repl_slot; + err = 0; + if (mddev->gendisk) + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + conf->fullsync = 1; + rcu_assign_pointer(p->replacement, rdev); + } + print_conf(conf); return err; } @@ -3303,6 +3298,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, int chunks_skipped = 0; sector_t chunk_mask = conf->geo.chunk_mask; int page_idx = 0; + int error_disk = -1; /* * Allow skipping a full rebuild for incremental assembly @@ -3386,8 +3382,21 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, return reshape_request(mddev, sector_nr, skipped); if (chunks_skipped >= conf->geo.raid_disks) { - /* if there has been nothing to do on any drive, - * then there is nothing to do at all.. + pr_err("md/raid10:%s: %s fails\n", mdname(mddev), + test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ? "resync" : "recovery"); + if (error_disk >= 0 && + !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) { + /* + * recovery fails, set mirrors.recovery_disabled, + * device shouldn't be added to there. + */ + conf->mirrors[error_disk].recovery_disabled = + mddev->recovery_disabled; + return 0; + } + /* + * if there has been nothing to do on any drive, + * then there is nothing to do at all. */ *skipped = 1; return (max_sector - sector_nr) + sectors_skipped; @@ -3437,8 +3446,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, sector_t sect; int must_sync; int any_working; - int need_recover = 0; - int need_replace = 0; struct raid10_info *mirror = &conf->mirrors[i]; struct md_rdev *mrdev, *mreplace; @@ -3446,15 +3453,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, mrdev = rcu_dereference(mirror->rdev); mreplace = rcu_dereference(mirror->replacement); - if (mrdev != NULL && - !test_bit(Faulty, &mrdev->flags) && - !test_bit(In_sync, &mrdev->flags)) - need_recover = 1; - if (mreplace != NULL && - !test_bit(Faulty, &mreplace->flags)) - need_replace = 1; + if (mrdev && (test_bit(Faulty, &mrdev->flags) || + test_bit(In_sync, &mrdev->flags))) + mrdev = NULL; + if (mreplace && test_bit(Faulty, &mreplace->flags)) + mreplace = NULL; - if (!need_recover && !need_replace) { + if (!mrdev && !mreplace) { rcu_read_unlock(); continue; } @@ -3470,8 +3475,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, rcu_read_unlock(); continue; } - if (mreplace && test_bit(Faulty, &mreplace->flags)) - mreplace = NULL; /* Unless we are doing a full sync, or a replacement * we only need to recover the block if it is set in * the bitmap @@ -3490,7 +3493,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, rcu_read_unlock(); continue; } - atomic_inc(&mrdev->nr_pending); + if (mrdev) + atomic_inc(&mrdev->nr_pending); if (mreplace) atomic_inc(&mreplace->nr_pending); rcu_read_unlock(); @@ -3577,7 +3581,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, r10_bio->devs[1].devnum = i; r10_bio->devs[1].addr = to_addr; - if (need_recover) { + if (mrdev) { bio = r10_bio->devs[1].bio; bio->bi_next = biolist; biolist = bio; @@ -3594,11 +3598,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r10_bio->devs[1].repl_bio; if (bio) bio->bi_end_io = NULL; - /* Note: if need_replace, then bio + /* Note: if replace is not NULL, then bio * cannot be NULL as r10buf_pool_alloc will * have allocated it. */ - if (!need_replace) + if (!mreplace) break; bio->bi_next = biolist; biolist = bio; @@ -3622,7 +3626,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, for (k = 0; k < conf->copies; k++) if (r10_bio->devs[k].devnum == i) break; - if (!test_bit(In_sync, + if (mrdev && !test_bit(In_sync, &mrdev->flags) && !rdev_set_badblocks( mrdev, @@ -3643,17 +3647,21 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, mdname(mddev)); mirror->recovery_disabled = mddev->recovery_disabled; + } else { + error_disk = i; } put_buf(r10_bio); if (rb2) atomic_dec(&rb2->remaining); r10_bio = rb2; - rdev_dec_pending(mrdev, mddev); + if (mrdev) + rdev_dec_pending(mrdev, mddev); if (mreplace) rdev_dec_pending(mreplace, mddev); break; } - rdev_dec_pending(mrdev, mddev); + if (mrdev) + rdev_dec_pending(mrdev, mddev); if (mreplace) rdev_dec_pending(mreplace, mddev); if (r10_bio->devs[0].bio->bi_opf & MD_FAILFAST) { @@ -3819,11 +3827,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, for (bio= biolist ; bio ; bio=bio->bi_next) { struct resync_pages *rp = get_resync_pages(bio); page = resync_fetch_page(rp, page_idx); - /* - * won't fail because the vec table is big enough - * to hold all these pages - */ - bio_add_page(bio, page, len, 0); + if (WARN_ON(!bio_add_page(bio, page, len, 0))) { + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + goto giveup; + } } nr_sectors += len>>9; sector_nr += len>>9; @@ -4107,7 +4115,8 @@ static struct r10conf *setup_conf(struct mddev *mddev) atomic_set(&conf->nr_pending, 0); err = -ENOMEM; - conf->thread = md_register_thread(raid10d, mddev, "raid10"); + rcu_assign_pointer(conf->thread, + md_register_thread(raid10d, mddev, "raid10")); if (!conf->thread) goto out; @@ -4152,8 +4161,8 @@ static int raid10_run(struct mddev *mddev) if (!conf) goto out; - mddev->thread = conf->thread; - conf->thread = NULL; + rcu_assign_pointer(mddev->thread, conf->thread); + rcu_assign_pointer(conf->thread, NULL); if (mddev_is_clustered(conf->mddev)) { int fc, fo; @@ -4296,8 +4305,8 @@ static int raid10_run(struct mddev *mddev) clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "reshape")); if (!mddev->sync_thread) goto out_free_conf; } @@ -4698,8 +4707,8 @@ out: set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "reshape")); if (!mddev->sync_thread) { ret = -EAGAIN; goto abort; @@ -4997,11 +5006,11 @@ read_more: if (len > PAGE_SIZE) len = PAGE_SIZE; for (bio = blist; bio ; bio = bio->bi_next) { - /* - * won't fail because the vec table is big enough - * to hold all these pages - */ - bio_add_page(bio, page, len, 0); + if (WARN_ON(!bio_add_page(bio, page, len, 0))) { + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + return sectors_done; + } } sector_nr += len >> 9; nr_sectors += len >> 9; diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 8c072ce0bc54..63e48b11b552 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -100,7 +100,7 @@ struct r10conf { /* When taking over an array from a different personality, we store * the new thread here until we fully activate the array. */ - struct md_thread *thread; + struct md_thread __rcu *thread; /* * Keep track of cluster resync window to send to other nodes. diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 46182b955aef..47ba7d9e81e1 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -120,7 +120,7 @@ struct r5l_log { struct bio_set bs; mempool_t meta_pool; - struct md_thread *reclaim_thread; + struct md_thread __rcu *reclaim_thread; unsigned long reclaim_target; /* number of space that need to be * reclaimed. if it's 0, reclaim spaces * used by io_units which are in @@ -792,7 +792,7 @@ static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log) io->current_bio = r5l_bio_alloc(log); io->current_bio->bi_end_io = r5l_log_endio; io->current_bio->bi_private = io; - bio_add_page(io->current_bio, io->meta_page, PAGE_SIZE, 0); + __bio_add_page(io->current_bio, io->meta_page, PAGE_SIZE, 0); r5_reserve_log_entry(log, io); @@ -1576,17 +1576,18 @@ void r5l_wake_reclaim(struct r5l_log *log, sector_t space) void r5l_quiesce(struct r5l_log *log, int quiesce) { - struct mddev *mddev; + struct mddev *mddev = log->rdev->mddev; + struct md_thread *thread = rcu_dereference_protected( + log->reclaim_thread, lockdep_is_held(&mddev->reconfig_mutex)); if (quiesce) { /* make sure r5l_write_super_and_discard_space exits */ - mddev = log->rdev->mddev; wake_up(&mddev->sb_wait); - kthread_park(log->reclaim_thread->tsk); + kthread_park(thread->tsk); r5l_wake_reclaim(log, MaxSector); r5l_do_reclaim(log); } else - kthread_unpark(log->reclaim_thread->tsk); + kthread_unpark(thread->tsk); } bool r5l_log_disk_error(struct r5conf *conf) @@ -3063,6 +3064,7 @@ void r5c_update_on_rdev_error(struct mddev *mddev, struct md_rdev *rdev) int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) { struct r5l_log *log; + struct md_thread *thread; int ret; pr_debug("md/raid:%s: using device %pg as journal\n", @@ -3121,11 +3123,13 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) spin_lock_init(&log->tree_lock); INIT_RADIX_TREE(&log->big_stripe_tree, GFP_NOWAIT | __GFP_NOWARN); - log->reclaim_thread = md_register_thread(r5l_reclaim_thread, - log->rdev->mddev, "reclaim"); - if (!log->reclaim_thread) + thread = md_register_thread(r5l_reclaim_thread, log->rdev->mddev, + "reclaim"); + if (!thread) goto reclaim_thread; - log->reclaim_thread->timeout = R5C_RECLAIM_WAKEUP_INTERVAL; + + thread->timeout = R5C_RECLAIM_WAKEUP_INTERVAL; + rcu_assign_pointer(log->reclaim_thread, thread); init_waitqueue_head(&log->iounit_wait); diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index e495939bb3e0..eaea57aee602 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -465,7 +465,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) bio->bi_end_io = ppl_log_endio; bio->bi_iter.bi_sector = log->next_io_sector; - bio_add_page(bio, io->header_page, PAGE_SIZE, 0); + __bio_add_page(bio, io->header_page, PAGE_SIZE, 0); pr_debug("%s: log->current_io_sector: %llu\n", __func__, (unsigned long long)log->next_io_sector); @@ -496,7 +496,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) prev->bi_opf, GFP_NOIO, &ppl_conf->bs); bio->bi_iter.bi_sector = bio_end_sector(prev); - bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0); + __bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0); bio_chain(bio, prev); ppl_submit_iounit_bio(io, prev); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 9ea285fbc4a6..6615abf54d3f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5966,6 +5966,19 @@ out: return ret; } +static bool reshape_inprogress(struct mddev *mddev) +{ + return test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && + test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && + !test_bit(MD_RECOVERY_DONE, &mddev->recovery) && + !test_bit(MD_RECOVERY_INTR, &mddev->recovery); +} + +static bool reshape_disabled(struct mddev *mddev) +{ + return is_md_suspended(mddev) || !md_is_rdwr(mddev); +} + static enum stripe_result make_stripe_request(struct mddev *mddev, struct r5conf *conf, struct stripe_request_ctx *ctx, sector_t logical_sector, struct bio *bi) @@ -5997,7 +6010,8 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, if (ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) { spin_unlock_irq(&conf->device_lock); - return STRIPE_SCHEDULE_AND_RETRY; + ret = STRIPE_SCHEDULE_AND_RETRY; + goto out; } } spin_unlock_irq(&conf->device_lock); @@ -6076,6 +6090,15 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, out_release: raid5_release_stripe(sh); +out: + if (ret == STRIPE_SCHEDULE_AND_RETRY && !reshape_inprogress(mddev) && + reshape_disabled(mddev)) { + bi->bi_status = BLK_STS_IOERR; + ret = STRIPE_FAIL; + pr_err("md/raid456:%s: io failed across reshape position while reshape can't make progress.\n", + mdname(mddev)); + } + return ret; } @@ -7708,7 +7731,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) } sprintf(pers_name, "raid%d", mddev->new_level); - conf->thread = md_register_thread(raid5d, mddev, pers_name); + rcu_assign_pointer(conf->thread, + md_register_thread(raid5d, mddev, pers_name)); if (!conf->thread) { pr_warn("md/raid:%s: couldn't allocate thread.\n", mdname(mddev)); @@ -7931,8 +7955,8 @@ static int raid5_run(struct mddev *mddev) } conf->min_offset_diff = min_offset_diff; - mddev->thread = conf->thread; - conf->thread = NULL; + rcu_assign_pointer(mddev->thread, conf->thread); + rcu_assign_pointer(conf->thread, NULL); mddev->private = conf; for (i = 0; i < conf->raid_disks && conf->previous_raid_disks; @@ -8029,8 +8053,8 @@ static int raid5_run(struct mddev *mddev) clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "reshape")); if (!mddev->sync_thread) goto abort; } @@ -8377,6 +8401,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) p = conf->disks + disk; tmp = rdev_mdlock_deref(mddev, p->rdev); if (test_bit(WantReplacement, &tmp->flags) && + mddev->reshape_position == MaxSector && p->replacement == NULL) { clear_bit(In_sync, &rdev->flags); set_bit(Replacement, &rdev->flags); @@ -8500,6 +8525,7 @@ static int raid5_start_reshape(struct mddev *mddev) struct r5conf *conf = mddev->private; struct md_rdev *rdev; int spares = 0; + int i; unsigned long flags; if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) @@ -8511,6 +8537,13 @@ static int raid5_start_reshape(struct mddev *mddev) if (has_failed(conf)) return -EINVAL; + /* raid5 can't handle concurrent reshape and recovery */ + if (mddev->recovery_cp < MaxSector) + return -EBUSY; + for (i = 0; i < conf->raid_disks; i++) + if (rdev_mdlock_deref(mddev, conf->disks[i].replacement)) + return -EBUSY; + rdev_for_each(rdev, mddev) { if (!test_bit(In_sync, &rdev->flags) && !test_bit(Faulty, &rdev->flags)) @@ -8607,8 +8640,8 @@ static int raid5_start_reshape(struct mddev *mddev) clear_bit(MD_RECOVERY_DONE, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - mddev->sync_thread = md_register_thread(md_do_sync, mddev, - "reshape"); + rcu_assign_pointer(mddev->sync_thread, + md_register_thread(md_do_sync, mddev, "reshape")); if (!mddev->sync_thread) { mddev->recovery = 0; spin_lock_irq(&conf->device_lock); @@ -9043,6 +9076,22 @@ static int raid5_start(struct mddev *mddev) return r5l_start(conf->log); } +static void raid5_prepare_suspend(struct mddev *mddev) +{ + struct r5conf *conf = mddev->private; + + wait_event(mddev->sb_wait, !reshape_inprogress(mddev) || + percpu_ref_is_zero(&mddev->active_io)); + if (percpu_ref_is_zero(&mddev->active_io)) + return; + + /* + * Reshape is not in progress, and array is suspended, io that is + * waiting for reshpape can never be done. + */ + wake_up(&conf->wait_for_overlap); +} + static struct md_personality raid6_personality = { .name = "raid6", @@ -9063,6 +9112,7 @@ static struct md_personality raid6_personality = .check_reshape = raid6_check_reshape, .start_reshape = raid5_start_reshape, .finish_reshape = raid5_finish_reshape, + .prepare_suspend = raid5_prepare_suspend, .quiesce = raid5_quiesce, .takeover = raid6_takeover, .change_consistency_policy = raid5_change_consistency_policy, @@ -9087,6 +9137,7 @@ static struct md_personality raid5_personality = .check_reshape = raid5_check_reshape, .start_reshape = raid5_start_reshape, .finish_reshape = raid5_finish_reshape, + .prepare_suspend = raid5_prepare_suspend, .quiesce = raid5_quiesce, .takeover = raid5_takeover, .change_consistency_policy = raid5_change_consistency_policy, @@ -9112,6 +9163,7 @@ static struct md_personality raid4_personality = .check_reshape = raid5_check_reshape, .start_reshape = raid5_start_reshape, .finish_reshape = raid5_finish_reshape, + .prepare_suspend = raid5_prepare_suspend, .quiesce = raid5_quiesce, .takeover = raid4_takeover, .change_consistency_policy = raid5_change_consistency_policy, diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index e873938a6125..f19707189a7b 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -679,7 +679,7 @@ struct r5conf { /* When taking over an array from a different personality, we store * the new thread here until we fully activate the array. */ - struct md_thread *thread; + struct md_thread __rcu *thread; struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS]; struct r5worker_group *worker_groups; int group_cnt; diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index d920c4178389..6d01025f1fcf 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -358,15 +358,15 @@ static const struct attribute_group *mmc_disk_attr_groups[] = { NULL, }; -static int mmc_blk_open(struct block_device *bdev, fmode_t mode) +static int mmc_blk_open(struct gendisk *disk, blk_mode_t mode) { - struct mmc_blk_data *md = mmc_blk_get(bdev->bd_disk); + struct mmc_blk_data *md = mmc_blk_get(disk); int ret = -ENXIO; mutex_lock(&block_mutex); if (md) { ret = 0; - if ((mode & FMODE_WRITE) && md->read_only) { + if ((mode & BLK_OPEN_WRITE) && md->read_only) { mmc_blk_put(md); ret = -EROFS; } @@ -376,7 +376,7 @@ static int mmc_blk_open(struct block_device *bdev, fmode_t mode) return ret; } -static void mmc_blk_release(struct gendisk *disk, fmode_t mode) +static void mmc_blk_release(struct gendisk *disk) { struct mmc_blk_data *md = disk->private_data; @@ -757,7 +757,7 @@ static int mmc_blk_check_blkdev(struct block_device *bdev) return 0; } -static int mmc_blk_ioctl(struct block_device *bdev, fmode_t mode, +static int mmc_blk_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct mmc_blk_data *md; @@ -794,7 +794,7 @@ static int mmc_blk_ioctl(struct block_device *bdev, fmode_t mode, } #ifdef CONFIG_COMPAT -static int mmc_blk_compat_ioctl(struct block_device *bdev, fmode_t mode, +static int mmc_blk_compat_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { return mmc_blk_ioctl(bdev, mode, cmd, (unsigned long) compat_ptr(arg)); diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index 4cd37ec45762..be106dc20ff3 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -209,40 +209,34 @@ static void block2mtd_free_device(struct block2mtd_dev *dev) if (dev->blkdev) { invalidate_mapping_pages(dev->blkdev->bd_inode->i_mapping, 0, -1); - blkdev_put(dev->blkdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(dev->blkdev, NULL); } kfree(dev); } - -static struct block2mtd_dev *add_device(char *devname, int erase_size, - char *label, int timeout) +/* + * This function is marked __ref because it calls the __init marked + * early_lookup_bdev when called from the early boot code. + */ +static struct block_device __ref *mdtblock_early_get_bdev(const char *devname, + blk_mode_t mode, int timeout, struct block2mtd_dev *dev) { + struct block_device *bdev = ERR_PTR(-ENODEV); #ifndef MODULE int i; -#endif - const fmode_t mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL; - struct block_device *bdev; - struct block2mtd_dev *dev; - char *name; - if (!devname) - return NULL; - - dev = kzalloc(sizeof(struct block2mtd_dev), GFP_KERNEL); - if (!dev) - return NULL; - - /* Get a handle on the device */ - bdev = blkdev_get_by_path(devname, mode, dev); + /* + * We can't use early_lookup_bdev from a running system. + */ + if (system_state >= SYSTEM_RUNNING) + return bdev; -#ifndef MODULE /* * We might not have the root device mounted at this point. * Try to resolve the device name by other means. */ - for (i = 0; IS_ERR(bdev) && i <= timeout; i++) { + for (i = 0; i <= timeout; i++) { dev_t devt; if (i) @@ -254,13 +248,35 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size, msleep(1000); wait_for_device_probe(); - devt = name_to_dev_t(devname); - if (!devt) - continue; - bdev = blkdev_get_by_dev(devt, mode, dev); + if (!early_lookup_bdev(devname, &devt)) { + bdev = blkdev_get_by_dev(devt, mode, dev, NULL); + if (!IS_ERR(bdev)) + break; + } } #endif + return bdev; +} +static struct block2mtd_dev *add_device(char *devname, int erase_size, + char *label, int timeout) +{ + const blk_mode_t mode = BLK_OPEN_READ | BLK_OPEN_WRITE; + struct block_device *bdev; + struct block2mtd_dev *dev; + char *name; + + if (!devname) + return NULL; + + dev = kzalloc(sizeof(struct block2mtd_dev), GFP_KERNEL); + if (!dev) + return NULL; + + /* Get a handle on the device */ + bdev = blkdev_get_by_path(devname, mode, dev, NULL); + if (IS_ERR(bdev)) + bdev = mdtblock_early_get_bdev(devname, mode, timeout, dev); if (IS_ERR(bdev)) { pr_err("error: cannot open device %s\n", devname); goto err_free_block2mtd; diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 60b222799871..ff18636e0889 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -182,9 +182,9 @@ static blk_status_t mtd_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } -static int blktrans_open(struct block_device *bdev, fmode_t mode) +static int blktrans_open(struct gendisk *disk, blk_mode_t mode) { - struct mtd_blktrans_dev *dev = bdev->bd_disk->private_data; + struct mtd_blktrans_dev *dev = disk->private_data; int ret = 0; kref_get(&dev->ref); @@ -208,7 +208,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode) ret = __get_mtd_device(dev->mtd); if (ret) goto error_release; - dev->file_mode = mode; + dev->writable = mode & BLK_OPEN_WRITE; unlock: dev->open++; @@ -225,7 +225,7 @@ error_put: return ret; } -static void blktrans_release(struct gendisk *disk, fmode_t mode) +static void blktrans_release(struct gendisk *disk) { struct mtd_blktrans_dev *dev = disk->private_data; diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c index a0a1194dc1d9..fa476fb4dffb 100644 --- a/drivers/mtd/mtdblock.c +++ b/drivers/mtd/mtdblock.c @@ -294,7 +294,7 @@ static void mtdblock_release(struct mtd_blktrans_dev *mbd) * It was the last usage. Free the cache, but only sync if * opened for writing. */ - if (mbd->file_mode & FMODE_WRITE) + if (mbd->writable) mtd_sync(mbd->mtd); vfree(mtdblk->cache_data); } diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 3711d7f74600..437c5b83ffe5 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -227,9 +227,9 @@ static blk_status_t ubiblock_read(struct request *req) return BLK_STS_OK; } -static int ubiblock_open(struct block_device *bdev, fmode_t mode) +static int ubiblock_open(struct gendisk *disk, blk_mode_t mode) { - struct ubiblock *dev = bdev->bd_disk->private_data; + struct ubiblock *dev = disk->private_data; int ret; mutex_lock(&dev->dev_mutex); @@ -246,11 +246,10 @@ static int ubiblock_open(struct block_device *bdev, fmode_t mode) * It's just a paranoid check, as write requests will get rejected * in any case. */ - if (mode & FMODE_WRITE) { + if (mode & BLK_OPEN_WRITE) { ret = -EROFS; goto out_unlock; } - dev->desc = ubi_open_volume(dev->ubi_num, dev->vol_id, UBI_READONLY); if (IS_ERR(dev->desc)) { dev_err(disk_to_dev(dev->gd), "failed to open ubi volume %d_%d", @@ -270,7 +269,7 @@ out_unlock: return ret; } -static void ubiblock_release(struct gendisk *gd, fmode_t mode) +static void ubiblock_release(struct gendisk *gd) { struct ubiblock *dev = gd->private_data; diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile index e27202d22c7d..d3fc5063e4be 100644 --- a/drivers/nvme/host/Makefile +++ b/drivers/nvme/host/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_NVME_FC) += nvme-fc.o obj-$(CONFIG_NVME_TCP) += nvme-tcp.o obj-$(CONFIG_NVME_APPLE) += nvme-apple.o -nvme-core-y += core.o ioctl.o +nvme-core-y += core.o ioctl.o sysfs.o nvme-core-$(CONFIG_NVME_VERBOSE_ERRORS) += constants.o nvme-core-$(CONFIG_TRACING) += trace.o nvme-core-$(CONFIG_NVME_MULTIPATH) += multipath.o diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index ea16a0aba679..daf5d144a8ea 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -30,18 +30,18 @@ struct nvme_dhchap_queue_context { u32 s2; u16 transaction; u8 status; + u8 dhgroup_id; u8 hash_id; size_t hash_len; - u8 dhgroup_id; u8 c1[64]; u8 c2[64]; u8 response[64]; u8 *host_response; u8 *ctrl_key; - int ctrl_key_len; u8 *host_key; - int host_key_len; u8 *sess_key; + int ctrl_key_len; + int host_key_len; int sess_key_len; }; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3ec38e2b9173..fdfcf2781c85 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -237,7 +237,7 @@ int nvme_delete_ctrl(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_delete_ctrl); -static void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) +void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) { /* * Keep a reference until nvme_do_delete_ctrl() complete, @@ -1635,12 +1635,12 @@ static void nvme_ns_release(struct nvme_ns *ns) nvme_put_ns(ns); } -static int nvme_open(struct block_device *bdev, fmode_t mode) +static int nvme_open(struct gendisk *disk, blk_mode_t mode) { - return nvme_ns_open(bdev->bd_disk->private_data); + return nvme_ns_open(disk->private_data); } -static void nvme_release(struct gendisk *disk, fmode_t mode) +static void nvme_release(struct gendisk *disk) { nvme_ns_release(disk->private_data); } @@ -1879,7 +1879,7 @@ static void nvme_update_disk_info(struct gendisk *disk, struct nvme_ns *ns, struct nvme_id_ns *id) { sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze)); - unsigned short bs = 1 << ns->lba_shift; + u32 bs = 1U << ns->lba_shift; u32 atomic_bs, phys_bs, io_opt = 0; /* @@ -2300,7 +2300,7 @@ static int nvme_report_zones(struct gendisk *disk, sector_t sector, #define nvme_report_zones NULL #endif /* CONFIG_BLK_DEV_ZONED */ -static const struct block_device_operations nvme_bdev_ops = { +const struct block_device_operations nvme_bdev_ops = { .owner = THIS_MODULE, .ioctl = nvme_ioctl, .compat_ioctl = blkdev_compat_ptr_ioctl, @@ -2835,75 +2835,6 @@ static struct nvme_subsystem *__nvme_find_get_subsystem(const char *subsysnqn) return NULL; } -#define SUBSYS_ATTR_RO(_name, _mode, _show) \ - struct device_attribute subsys_attr_##_name = \ - __ATTR(_name, _mode, _show, NULL) - -static ssize_t nvme_subsys_show_nqn(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_subsystem *subsys = - container_of(dev, struct nvme_subsystem, dev); - - return sysfs_emit(buf, "%s\n", subsys->subnqn); -} -static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn); - -static ssize_t nvme_subsys_show_type(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_subsystem *subsys = - container_of(dev, struct nvme_subsystem, dev); - - switch (subsys->subtype) { - case NVME_NQN_DISC: - return sysfs_emit(buf, "discovery\n"); - case NVME_NQN_NVME: - return sysfs_emit(buf, "nvm\n"); - default: - return sysfs_emit(buf, "reserved\n"); - } -} -static SUBSYS_ATTR_RO(subsystype, S_IRUGO, nvme_subsys_show_type); - -#define nvme_subsys_show_str_function(field) \ -static ssize_t subsys_##field##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct nvme_subsystem *subsys = \ - container_of(dev, struct nvme_subsystem, dev); \ - return sysfs_emit(buf, "%.*s\n", \ - (int)sizeof(subsys->field), subsys->field); \ -} \ -static SUBSYS_ATTR_RO(field, S_IRUGO, subsys_##field##_show); - -nvme_subsys_show_str_function(model); -nvme_subsys_show_str_function(serial); -nvme_subsys_show_str_function(firmware_rev); - -static struct attribute *nvme_subsys_attrs[] = { - &subsys_attr_model.attr, - &subsys_attr_serial.attr, - &subsys_attr_firmware_rev.attr, - &subsys_attr_subsysnqn.attr, - &subsys_attr_subsystype.attr, -#ifdef CONFIG_NVME_MULTIPATH - &subsys_attr_iopolicy.attr, -#endif - NULL, -}; - -static const struct attribute_group nvme_subsys_attrs_group = { - .attrs = nvme_subsys_attrs, -}; - -static const struct attribute_group *nvme_subsys_attrs_groups[] = { - &nvme_subsys_attrs_group, - NULL, -}; - static inline bool nvme_discovery_ctrl(struct nvme_ctrl *ctrl) { return ctrl->opts && ctrl->opts->discovery_nqn; @@ -3108,7 +3039,8 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) ctrl->max_zeroes_sectors = 0; if (ctrl->subsys->subtype != NVME_NQN_NVME || - nvme_ctrl_limited_cns(ctrl)) + nvme_ctrl_limited_cns(ctrl) || + test_bit(NVME_CTRL_SKIP_ID_CNS_CS, &ctrl->flags)) return 0; id = kzalloc(sizeof(*id), GFP_KERNEL); @@ -3130,6 +3062,8 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl); free_data: + if (ret > 0) + set_bit(NVME_CTRL_SKIP_ID_CNS_CS, &ctrl->flags); kfree(id); return ret; } @@ -3437,586 +3371,6 @@ static const struct file_operations nvme_dev_fops = { .uring_cmd = nvme_dev_uring_cmd, }; -static ssize_t nvme_sysfs_reset(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - int ret; - - ret = nvme_reset_ctrl_sync(ctrl); - if (ret < 0) - return ret; - return count; -} -static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset); - -static ssize_t nvme_sysfs_rescan(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - nvme_queue_scan(ctrl); - return count; -} -static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan); - -static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev) -{ - struct gendisk *disk = dev_to_disk(dev); - - if (disk->fops == &nvme_bdev_ops) - return nvme_get_ns_from_dev(dev)->head; - else - return disk->private_data; -} - -static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct nvme_ns_head *head = dev_to_ns_head(dev); - struct nvme_ns_ids *ids = &head->ids; - struct nvme_subsystem *subsys = head->subsys; - int serial_len = sizeof(subsys->serial); - int model_len = sizeof(subsys->model); - - if (!uuid_is_null(&ids->uuid)) - return sysfs_emit(buf, "uuid.%pU\n", &ids->uuid); - - if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - return sysfs_emit(buf, "eui.%16phN\n", ids->nguid); - - if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) - return sysfs_emit(buf, "eui.%8phN\n", ids->eui64); - - while (serial_len > 0 && (subsys->serial[serial_len - 1] == ' ' || - subsys->serial[serial_len - 1] == '\0')) - serial_len--; - while (model_len > 0 && (subsys->model[model_len - 1] == ' ' || - subsys->model[model_len - 1] == '\0')) - model_len--; - - return sysfs_emit(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id, - serial_len, subsys->serial, model_len, subsys->model, - head->ns_id); -} -static DEVICE_ATTR_RO(wwid); - -static ssize_t nguid_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - return sysfs_emit(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid); -} -static DEVICE_ATTR_RO(nguid); - -static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids; - - /* For backward compatibility expose the NGUID to userspace if - * we have no UUID set - */ - if (uuid_is_null(&ids->uuid)) { - dev_warn_ratelimited(dev, - "No UUID available providing old NGUID\n"); - return sysfs_emit(buf, "%pU\n", ids->nguid); - } - return sysfs_emit(buf, "%pU\n", &ids->uuid); -} -static DEVICE_ATTR_RO(uuid); - -static ssize_t eui_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - return sysfs_emit(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64); -} -static DEVICE_ATTR_RO(eui); - -static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - return sysfs_emit(buf, "%d\n", dev_to_ns_head(dev)->ns_id); -} -static DEVICE_ATTR_RO(nsid); - -static struct attribute *nvme_ns_id_attrs[] = { - &dev_attr_wwid.attr, - &dev_attr_uuid.attr, - &dev_attr_nguid.attr, - &dev_attr_eui.attr, - &dev_attr_nsid.attr, -#ifdef CONFIG_NVME_MULTIPATH - &dev_attr_ana_grpid.attr, - &dev_attr_ana_state.attr, -#endif - NULL, -}; - -static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj, - struct attribute *a, int n) -{ - struct device *dev = container_of(kobj, struct device, kobj); - struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids; - - if (a == &dev_attr_uuid.attr) { - if (uuid_is_null(&ids->uuid) && - !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - return 0; - } - if (a == &dev_attr_nguid.attr) { - if (!memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - return 0; - } - if (a == &dev_attr_eui.attr) { - if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) - return 0; - } -#ifdef CONFIG_NVME_MULTIPATH - if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) { - if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */ - return 0; - if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl)) - return 0; - } -#endif - return a->mode; -} - -static const struct attribute_group nvme_ns_id_attr_group = { - .attrs = nvme_ns_id_attrs, - .is_visible = nvme_ns_id_attrs_are_visible, -}; - -const struct attribute_group *nvme_ns_id_attr_groups[] = { - &nvme_ns_id_attr_group, - NULL, -}; - -#define nvme_show_str_function(field) \ -static ssize_t field##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ - return sysfs_emit(buf, "%.*s\n", \ - (int)sizeof(ctrl->subsys->field), ctrl->subsys->field); \ -} \ -static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); - -nvme_show_str_function(model); -nvme_show_str_function(serial); -nvme_show_str_function(firmware_rev); - -#define nvme_show_int_function(field) \ -static ssize_t field##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ - return sysfs_emit(buf, "%d\n", ctrl->field); \ -} \ -static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); - -nvme_show_int_function(cntlid); -nvme_show_int_function(numa_node); -nvme_show_int_function(queue_count); -nvme_show_int_function(sqsize); -nvme_show_int_function(kato); - -static ssize_t nvme_sysfs_delete(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags)) - return -EBUSY; - - if (device_remove_file_self(dev, attr)) - nvme_delete_ctrl_sync(ctrl); - return count; -} -static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete); - -static ssize_t nvme_sysfs_show_transport(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%s\n", ctrl->ops->name); -} -static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL); - -static ssize_t nvme_sysfs_show_state(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - static const char *const state_name[] = { - [NVME_CTRL_NEW] = "new", - [NVME_CTRL_LIVE] = "live", - [NVME_CTRL_RESETTING] = "resetting", - [NVME_CTRL_CONNECTING] = "connecting", - [NVME_CTRL_DELETING] = "deleting", - [NVME_CTRL_DELETING_NOIO]= "deleting (no IO)", - [NVME_CTRL_DEAD] = "dead", - }; - - if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) && - state_name[ctrl->state]) - return sysfs_emit(buf, "%s\n", state_name[ctrl->state]); - - return sysfs_emit(buf, "unknown state\n"); -} - -static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL); - -static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%s\n", ctrl->subsys->subnqn); -} -static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL); - -static ssize_t nvme_sysfs_show_hostnqn(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%s\n", ctrl->opts->host->nqn); -} -static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL); - -static ssize_t nvme_sysfs_show_hostid(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%pU\n", &ctrl->opts->host->id); -} -static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL); - -static ssize_t nvme_sysfs_show_address(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - return ctrl->ops->get_address(ctrl, buf, PAGE_SIZE); -} -static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL); - -static ssize_t nvme_ctrl_loss_tmo_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - - if (ctrl->opts->max_reconnects == -1) - return sysfs_emit(buf, "off\n"); - return sysfs_emit(buf, "%d\n", - opts->max_reconnects * opts->reconnect_delay); -} - -static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - int ctrl_loss_tmo, err; - - err = kstrtoint(buf, 10, &ctrl_loss_tmo); - if (err) - return -EINVAL; - - if (ctrl_loss_tmo < 0) - opts->max_reconnects = -1; - else - opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo, - opts->reconnect_delay); - return count; -} -static DEVICE_ATTR(ctrl_loss_tmo, S_IRUGO | S_IWUSR, - nvme_ctrl_loss_tmo_show, nvme_ctrl_loss_tmo_store); - -static ssize_t nvme_ctrl_reconnect_delay_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (ctrl->opts->reconnect_delay == -1) - return sysfs_emit(buf, "off\n"); - return sysfs_emit(buf, "%d\n", ctrl->opts->reconnect_delay); -} - -static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - unsigned int v; - int err; - - err = kstrtou32(buf, 10, &v); - if (err) - return err; - - ctrl->opts->reconnect_delay = v; - return count; -} -static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR, - nvme_ctrl_reconnect_delay_show, nvme_ctrl_reconnect_delay_store); - -static ssize_t nvme_ctrl_fast_io_fail_tmo_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (ctrl->opts->fast_io_fail_tmo == -1) - return sysfs_emit(buf, "off\n"); - return sysfs_emit(buf, "%d\n", ctrl->opts->fast_io_fail_tmo); -} - -static ssize_t nvme_ctrl_fast_io_fail_tmo_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - int fast_io_fail_tmo, err; - - err = kstrtoint(buf, 10, &fast_io_fail_tmo); - if (err) - return -EINVAL; - - if (fast_io_fail_tmo < 0) - opts->fast_io_fail_tmo = -1; - else - opts->fast_io_fail_tmo = fast_io_fail_tmo; - return count; -} -static DEVICE_ATTR(fast_io_fail_tmo, S_IRUGO | S_IWUSR, - nvme_ctrl_fast_io_fail_tmo_show, nvme_ctrl_fast_io_fail_tmo_store); - -static ssize_t cntrltype_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - static const char * const type[] = { - [NVME_CTRL_IO] = "io\n", - [NVME_CTRL_DISC] = "discovery\n", - [NVME_CTRL_ADMIN] = "admin\n", - }; - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (ctrl->cntrltype > NVME_CTRL_ADMIN || !type[ctrl->cntrltype]) - return sysfs_emit(buf, "reserved\n"); - - return sysfs_emit(buf, type[ctrl->cntrltype]); -} -static DEVICE_ATTR_RO(cntrltype); - -static ssize_t dctype_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - static const char * const type[] = { - [NVME_DCTYPE_NOT_REPORTED] = "none\n", - [NVME_DCTYPE_DDC] = "ddc\n", - [NVME_DCTYPE_CDC] = "cdc\n", - }; - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (ctrl->dctype > NVME_DCTYPE_CDC || !type[ctrl->dctype]) - return sysfs_emit(buf, "reserved\n"); - - return sysfs_emit(buf, type[ctrl->dctype]); -} -static DEVICE_ATTR_RO(dctype); - -#ifdef CONFIG_NVME_AUTH -static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - - if (!opts->dhchap_secret) - return sysfs_emit(buf, "none\n"); - return sysfs_emit(buf, "%s\n", opts->dhchap_secret); -} - -static ssize_t nvme_ctrl_dhchap_secret_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - char *dhchap_secret; - - if (!ctrl->opts->dhchap_secret) - return -EINVAL; - if (count < 7) - return -EINVAL; - if (memcmp(buf, "DHHC-1:", 7)) - return -EINVAL; - - dhchap_secret = kzalloc(count + 1, GFP_KERNEL); - if (!dhchap_secret) - return -ENOMEM; - memcpy(dhchap_secret, buf, count); - nvme_auth_stop(ctrl); - if (strcmp(dhchap_secret, opts->dhchap_secret)) { - struct nvme_dhchap_key *key, *host_key; - int ret; - - ret = nvme_auth_generate_key(dhchap_secret, &key); - if (ret) - return ret; - kfree(opts->dhchap_secret); - opts->dhchap_secret = dhchap_secret; - host_key = ctrl->host_key; - mutex_lock(&ctrl->dhchap_auth_mutex); - ctrl->host_key = key; - mutex_unlock(&ctrl->dhchap_auth_mutex); - nvme_auth_free_key(host_key); - } - /* Start re-authentication */ - dev_info(ctrl->device, "re-authenticating controller\n"); - queue_work(nvme_wq, &ctrl->dhchap_auth_work); - - return count; -} -static DEVICE_ATTR(dhchap_secret, S_IRUGO | S_IWUSR, - nvme_ctrl_dhchap_secret_show, nvme_ctrl_dhchap_secret_store); - -static ssize_t nvme_ctrl_dhchap_ctrl_secret_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - - if (!opts->dhchap_ctrl_secret) - return sysfs_emit(buf, "none\n"); - return sysfs_emit(buf, "%s\n", opts->dhchap_ctrl_secret); -} - -static ssize_t nvme_ctrl_dhchap_ctrl_secret_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - struct nvmf_ctrl_options *opts = ctrl->opts; - char *dhchap_secret; - - if (!ctrl->opts->dhchap_ctrl_secret) - return -EINVAL; - if (count < 7) - return -EINVAL; - if (memcmp(buf, "DHHC-1:", 7)) - return -EINVAL; - - dhchap_secret = kzalloc(count + 1, GFP_KERNEL); - if (!dhchap_secret) - return -ENOMEM; - memcpy(dhchap_secret, buf, count); - nvme_auth_stop(ctrl); - if (strcmp(dhchap_secret, opts->dhchap_ctrl_secret)) { - struct nvme_dhchap_key *key, *ctrl_key; - int ret; - - ret = nvme_auth_generate_key(dhchap_secret, &key); - if (ret) - return ret; - kfree(opts->dhchap_ctrl_secret); - opts->dhchap_ctrl_secret = dhchap_secret; - ctrl_key = ctrl->ctrl_key; - mutex_lock(&ctrl->dhchap_auth_mutex); - ctrl->ctrl_key = key; - mutex_unlock(&ctrl->dhchap_auth_mutex); - nvme_auth_free_key(ctrl_key); - } - /* Start re-authentication */ - dev_info(ctrl->device, "re-authenticating controller\n"); - queue_work(nvme_wq, &ctrl->dhchap_auth_work); - - return count; -} -static DEVICE_ATTR(dhchap_ctrl_secret, S_IRUGO | S_IWUSR, - nvme_ctrl_dhchap_ctrl_secret_show, nvme_ctrl_dhchap_ctrl_secret_store); -#endif - -static struct attribute *nvme_dev_attrs[] = { - &dev_attr_reset_controller.attr, - &dev_attr_rescan_controller.attr, - &dev_attr_model.attr, - &dev_attr_serial.attr, - &dev_attr_firmware_rev.attr, - &dev_attr_cntlid.attr, - &dev_attr_delete_controller.attr, - &dev_attr_transport.attr, - &dev_attr_subsysnqn.attr, - &dev_attr_address.attr, - &dev_attr_state.attr, - &dev_attr_numa_node.attr, - &dev_attr_queue_count.attr, - &dev_attr_sqsize.attr, - &dev_attr_hostnqn.attr, - &dev_attr_hostid.attr, - &dev_attr_ctrl_loss_tmo.attr, - &dev_attr_reconnect_delay.attr, - &dev_attr_fast_io_fail_tmo.attr, - &dev_attr_kato.attr, - &dev_attr_cntrltype.attr, - &dev_attr_dctype.attr, -#ifdef CONFIG_NVME_AUTH - &dev_attr_dhchap_secret.attr, - &dev_attr_dhchap_ctrl_secret.attr, -#endif - NULL -}; - -static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, - struct attribute *a, int n) -{ - struct device *dev = container_of(kobj, struct device, kobj); - struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - - if (a == &dev_attr_delete_controller.attr && !ctrl->ops->delete_ctrl) - return 0; - if (a == &dev_attr_address.attr && !ctrl->ops->get_address) - return 0; - if (a == &dev_attr_hostnqn.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_hostid.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_ctrl_loss_tmo.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_fast_io_fail_tmo.attr && !ctrl->opts) - return 0; -#ifdef CONFIG_NVME_AUTH - if (a == &dev_attr_dhchap_secret.attr && !ctrl->opts) - return 0; - if (a == &dev_attr_dhchap_ctrl_secret.attr && !ctrl->opts) - return 0; -#endif - - return a->mode; -} - -const struct attribute_group nvme_dev_attrs_group = { - .attrs = nvme_dev_attrs, - .is_visible = nvme_dev_attrs_are_visible, -}; -EXPORT_SYMBOL_GPL(nvme_dev_attrs_group); - -static const struct attribute_group *nvme_dev_attr_groups[] = { - &nvme_dev_attrs_group, - NULL, -}; - static struct nvme_ns_head *nvme_find_ns_head(struct nvme_ctrl *ctrl, unsigned nsid) { @@ -4256,7 +3610,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) goto out_put_ns_head; } - if (!multipath && !list_empty(&head->list)) { + if (!multipath) { dev_warn(ctrl->device, "Found shared namespace %d, but multipathing not supported.\n", info->nsid); @@ -4357,7 +3711,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) * instance as shared namespaces will show up as multiple block * devices. */ - if (ns->head->disk) { + if (nvme_ns_head_multipath(ns->head)) { sprintf(disk->disk_name, "nvme%dc%dn%d", ctrl->subsys->instance, ctrl->instance, ns->head->instance); disk->flags |= GENHD_FL_HIDDEN; @@ -5243,6 +4597,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, return 0; out_free_cdev: + nvme_fault_inject_fini(&ctrl->fault_inject); + dev_pm_qos_hide_latency_tolerance(ctrl->device); cdev_device_del(&ctrl->cdev, ctrl->device); out_free_name: nvme_put_ctrl(ctrl); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 0069ebff85df..8175d49f2909 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -21,35 +21,60 @@ static DEFINE_MUTEX(nvmf_hosts_mutex); static struct nvmf_host *nvmf_default_host; -static struct nvmf_host *__nvmf_host_find(const char *hostnqn) +static struct nvmf_host *nvmf_host_alloc(const char *hostnqn, uuid_t *id) { struct nvmf_host *host; - list_for_each_entry(host, &nvmf_hosts, list) { - if (!strcmp(host->nqn, hostnqn)) - return host; - } + host = kmalloc(sizeof(*host), GFP_KERNEL); + if (!host) + return NULL; - return NULL; + kref_init(&host->ref); + uuid_copy(&host->id, id); + strscpy(host->nqn, hostnqn, NVMF_NQN_SIZE); + + return host; } -static struct nvmf_host *nvmf_host_add(const char *hostnqn) +static struct nvmf_host *nvmf_host_add(const char *hostnqn, uuid_t *id) { struct nvmf_host *host; mutex_lock(&nvmf_hosts_mutex); - host = __nvmf_host_find(hostnqn); - if (host) { - kref_get(&host->ref); - goto out_unlock; + + /* + * We have defined a host as how it is perceived by the target. + * Therefore, we don't allow different Host NQNs with the same Host ID. + * Similarly, we do not allow the usage of the same Host NQN with + * different Host IDs. This'll maintain unambiguous host identification. + */ + list_for_each_entry(host, &nvmf_hosts, list) { + bool same_hostnqn = !strcmp(host->nqn, hostnqn); + bool same_hostid = uuid_equal(&host->id, id); + + if (same_hostnqn && same_hostid) { + kref_get(&host->ref); + goto out_unlock; + } + if (same_hostnqn) { + pr_err("found same hostnqn %s but different hostid %pUb\n", + hostnqn, id); + host = ERR_PTR(-EINVAL); + goto out_unlock; + } + if (same_hostid) { + pr_err("found same hostid %pUb but different hostnqn %s\n", + id, hostnqn); + host = ERR_PTR(-EINVAL); + goto out_unlock; + } } - host = kmalloc(sizeof(*host), GFP_KERNEL); - if (!host) + host = nvmf_host_alloc(hostnqn, id); + if (!host) { + host = ERR_PTR(-ENOMEM); goto out_unlock; - - kref_init(&host->ref); - strscpy(host->nqn, hostnqn, NVMF_NQN_SIZE); + } list_add_tail(&host->list, &nvmf_hosts); out_unlock: @@ -60,16 +85,17 @@ out_unlock: static struct nvmf_host *nvmf_host_default(void) { struct nvmf_host *host; + char nqn[NVMF_NQN_SIZE]; + uuid_t id; - host = kmalloc(sizeof(*host), GFP_KERNEL); + uuid_gen(&id); + snprintf(nqn, NVMF_NQN_SIZE, + "nqn.2014-08.org.nvmexpress:uuid:%pUb", &id); + + host = nvmf_host_alloc(nqn, &id); if (!host) return NULL; - kref_init(&host->ref); - uuid_gen(&host->id); - snprintf(host->nqn, NVMF_NQN_SIZE, - "nqn.2014-08.org.nvmexpress:uuid:%pUb", &host->id); - mutex_lock(&nvmf_hosts_mutex); list_add_tail(&host->list, &nvmf_hosts); mutex_unlock(&nvmf_hosts_mutex); @@ -349,6 +375,45 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, } } +static struct nvmf_connect_data *nvmf_connect_data_prep(struct nvme_ctrl *ctrl, + u16 cntlid) +{ + struct nvmf_connect_data *data; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return NULL; + + uuid_copy(&data->hostid, &ctrl->opts->host->id); + data->cntlid = cpu_to_le16(cntlid); + strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); + strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); + + return data; +} + +static void nvmf_connect_cmd_prep(struct nvme_ctrl *ctrl, u16 qid, + struct nvme_command *cmd) +{ + cmd->connect.opcode = nvme_fabrics_command; + cmd->connect.fctype = nvme_fabrics_type_connect; + cmd->connect.qid = cpu_to_le16(qid); + + if (qid) { + cmd->connect.sqsize = cpu_to_le16(ctrl->sqsize); + } else { + cmd->connect.sqsize = cpu_to_le16(NVME_AQ_DEPTH - 1); + + /* + * set keep-alive timeout in seconds granularity (ms * 1000) + */ + cmd->connect.kato = cpu_to_le32(ctrl->kato * 1000); + } + + if (ctrl->opts->disable_sqflow) + cmd->connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW; +} + /** * nvmf_connect_admin_queue() - NVMe Fabrics Admin Queue "Connect" * API function. @@ -377,28 +442,12 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) int ret; u32 result; - cmd.connect.opcode = nvme_fabrics_command; - cmd.connect.fctype = nvme_fabrics_type_connect; - cmd.connect.qid = 0; - cmd.connect.sqsize = cpu_to_le16(NVME_AQ_DEPTH - 1); - - /* - * Set keep-alive timeout in seconds granularity (ms * 1000) - */ - cmd.connect.kato = cpu_to_le32(ctrl->kato * 1000); - - if (ctrl->opts->disable_sqflow) - cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW; + nvmf_connect_cmd_prep(ctrl, 0, &cmd); - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = nvmf_connect_data_prep(ctrl, 0xffff); if (!data) return -ENOMEM; - uuid_copy(&data->hostid, &ctrl->opts->host->id); - data->cntlid = cpu_to_le16(0xffff); - strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); - strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); - ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, data, sizeof(*data), NVME_QID_ANY, 1, BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); @@ -468,23 +517,12 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) int ret; u32 result; - cmd.connect.opcode = nvme_fabrics_command; - cmd.connect.fctype = nvme_fabrics_type_connect; - cmd.connect.qid = cpu_to_le16(qid); - cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize); + nvmf_connect_cmd_prep(ctrl, qid, &cmd); - if (ctrl->opts->disable_sqflow) - cmd.connect.cattr |= NVME_CONNECT_DISABLE_SQFLOW; - - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = nvmf_connect_data_prep(ctrl, ctrl->cntlid); if (!data) return -ENOMEM; - uuid_copy(&data->hostid, &ctrl->opts->host->id); - data->cntlid = cpu_to_le16(ctrl->cntlid); - strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); - strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); - ret = __nvme_submit_sync_cmd(ctrl->connect_q, &cmd, &res, data, sizeof(*data), qid, 1, BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT); @@ -621,6 +659,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, size_t nqnlen = 0; int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO; uuid_t hostid; + char hostnqn[NVMF_NQN_SIZE]; /* Set defaults */ opts->queue_size = NVMF_DEF_QUEUE_SIZE; @@ -637,7 +676,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, if (!options) return -ENOMEM; - uuid_gen(&hostid); + /* use default host if not given by user space */ + uuid_copy(&hostid, &nvmf_default_host->id); + strscpy(hostnqn, nvmf_default_host->nqn, NVMF_NQN_SIZE); while ((p = strsep(&o, ",\n")) != NULL) { if (!*p) @@ -783,12 +824,8 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, ret = -EINVAL; goto out; } - opts->host = nvmf_host_add(p); + strscpy(hostnqn, p, NVMF_NQN_SIZE); kfree(p); - if (!opts->host) { - ret = -ENOMEM; - goto out; - } break; case NVMF_OPT_RECONNECT_DELAY: if (match_int(args, &token)) { @@ -945,18 +982,94 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->fast_io_fail_tmo, ctrl_loss_tmo); } - if (!opts->host) { - kref_get(&nvmf_default_host->ref); - opts->host = nvmf_default_host; + opts->host = nvmf_host_add(hostnqn, &hostid); + if (IS_ERR(opts->host)) { + ret = PTR_ERR(opts->host); + opts->host = NULL; + goto out; } - uuid_copy(&opts->host->id, &hostid); - out: kfree(options); return ret; } +void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues, + u32 io_queues[HCTX_MAX_TYPES]) +{ + if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) { + /* + * separate read/write queues + * hand out dedicated default queues only after we have + * sufficient read queues. + */ + io_queues[HCTX_TYPE_READ] = opts->nr_io_queues; + nr_io_queues -= io_queues[HCTX_TYPE_READ]; + io_queues[HCTX_TYPE_DEFAULT] = + min(opts->nr_write_queues, nr_io_queues); + nr_io_queues -= io_queues[HCTX_TYPE_DEFAULT]; + } else { + /* + * shared read/write queues + * either no write queues were requested, or we don't have + * sufficient queue count to have dedicated default queues. + */ + io_queues[HCTX_TYPE_DEFAULT] = + min(opts->nr_io_queues, nr_io_queues); + nr_io_queues -= io_queues[HCTX_TYPE_DEFAULT]; + } + + if (opts->nr_poll_queues && nr_io_queues) { + /* map dedicated poll queues only if we have queues left */ + io_queues[HCTX_TYPE_POLL] = + min(opts->nr_poll_queues, nr_io_queues); + } +} +EXPORT_SYMBOL_GPL(nvmf_set_io_queues); + +void nvmf_map_queues(struct blk_mq_tag_set *set, struct nvme_ctrl *ctrl, + u32 io_queues[HCTX_MAX_TYPES]) +{ + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (opts->nr_write_queues && io_queues[HCTX_TYPE_READ]) { + /* separate read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; + set->map[HCTX_TYPE_READ].nr_queues = + io_queues[HCTX_TYPE_READ]; + set->map[HCTX_TYPE_READ].queue_offset = + io_queues[HCTX_TYPE_DEFAULT]; + } else { + /* shared read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = + io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; + set->map[HCTX_TYPE_READ].nr_queues = + io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_READ].queue_offset = 0; + } + + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); + if (opts->nr_poll_queues && io_queues[HCTX_TYPE_POLL]) { + /* map dedicated poll queues only if we have queues left */ + set->map[HCTX_TYPE_POLL].nr_queues = io_queues[HCTX_TYPE_POLL]; + set->map[HCTX_TYPE_POLL].queue_offset = + io_queues[HCTX_TYPE_DEFAULT] + + io_queues[HCTX_TYPE_READ]; + blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); + } + + dev_info(ctrl->device, + "mapped %d/%d/%d default/read/poll queues.\n", + io_queues[HCTX_TYPE_DEFAULT], + io_queues[HCTX_TYPE_READ], + io_queues[HCTX_TYPE_POLL]); +} +EXPORT_SYMBOL_GPL(nvmf_map_queues); + static int nvmf_check_required_opts(struct nvmf_ctrl_options *opts, unsigned int required_opts) { diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index dcac3df8a5f7..82e7a27ffbde 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -77,6 +77,9 @@ enum { * with the parsing opts enum. * @mask: Used by the fabrics library to parse through sysfs options * on adding a NVMe controller. + * @max_reconnects: maximum number of allowed reconnect attempts before removing + * the controller, (-1) means reconnect forever, zero means remove + * immediately; * @transport: Holds the fabric transport "technology name" (for a lack of * better description) that will be used by an NVMe controller * being added. @@ -96,9 +99,6 @@ enum { * @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN. * @kato: Keep-alive timeout. * @host: Virtual NVMe host, contains the NQN and Host ID. - * @max_reconnects: maximum number of allowed reconnect attempts before removing - * the controller, (-1) means reconnect forever, zero means remove - * immediately; * @dhchap_secret: DH-HMAC-CHAP secret * @dhchap_ctrl_secret: DH-HMAC-CHAP controller secret for bi-directional * authentication @@ -112,6 +112,7 @@ enum { */ struct nvmf_ctrl_options { unsigned mask; + int max_reconnects; char *transport; char *subsysnqn; char *traddr; @@ -125,7 +126,6 @@ struct nvmf_ctrl_options { bool duplicate_connect; unsigned int kato; struct nvmf_host *host; - int max_reconnects; char *dhchap_secret; char *dhchap_ctrl_secret; bool disable_sqflow; @@ -181,7 +181,7 @@ nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl, ctrl->state == NVME_CTRL_DEAD || strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) || strcmp(opts->host->nqn, ctrl->opts->host->nqn) || - memcmp(&opts->host->id, &ctrl->opts->host->id, sizeof(uuid_t))) + !uuid_equal(&opts->host->id, &ctrl->opts->host->id)) return false; return true; @@ -203,6 +203,13 @@ static inline void nvmf_complete_timed_out_request(struct request *rq) } } +static inline unsigned int nvmf_nr_io_queues(struct nvmf_ctrl_options *opts) +{ + return min(opts->nr_io_queues, num_online_cpus()) + + min(opts->nr_write_queues, num_online_cpus()) + + min(opts->nr_poll_queues, num_online_cpus()); +} + int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val); int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val); int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val); @@ -215,5 +222,9 @@ int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size); bool nvmf_should_reconnect(struct nvme_ctrl *ctrl); bool nvmf_ip_options_match(struct nvme_ctrl *ctrl, struct nvmf_ctrl_options *opts); +void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues, + u32 io_queues[HCTX_MAX_TYPES]); +void nvmf_map_queues(struct blk_mq_tag_set *set, struct nvme_ctrl *ctrl, + u32 io_queues[HCTX_MAX_TYPES]); #endif /* _NVME_FABRICS_H */ diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index b97744e05551..2130ad65b58c 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -14,7 +14,7 @@ enum { }; static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, - unsigned int flags, fmode_t mode) + unsigned int flags, bool open_for_write) { u32 effects; @@ -80,7 +80,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, * writing. */ if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC)) - return mode & FMODE_WRITE; + return open_for_write; return true; } @@ -337,7 +337,7 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl, static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct nvme_passthru_cmd __user *ucmd, unsigned int flags, - fmode_t mode) + bool open_for_write) { struct nvme_passthru_cmd cmd; struct nvme_command c; @@ -365,7 +365,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.cdw14 = cpu_to_le32(cmd.cdw14); c.common.cdw15 = cpu_to_le32(cmd.cdw15); - if (!nvme_cmd_allowed(ns, &c, 0, mode)) + if (!nvme_cmd_allowed(ns, &c, 0, open_for_write)) return -EACCES; if (cmd.timeout_ms) @@ -385,7 +385,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct nvme_passthru_cmd64 __user *ucmd, unsigned int flags, - fmode_t mode) + bool open_for_write) { struct nvme_passthru_cmd64 cmd; struct nvme_command c; @@ -412,7 +412,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.cdw14 = cpu_to_le32(cmd.cdw14); c.common.cdw15 = cpu_to_le32(cmd.cdw15); - if (!nvme_cmd_allowed(ns, &c, flags, mode)) + if (!nvme_cmd_allowed(ns, &c, flags, open_for_write)) return -EACCES; if (cmd.timeout_ms) @@ -583,7 +583,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.cdw14 = cpu_to_le32(READ_ONCE(cmd->cdw14)); c.common.cdw15 = cpu_to_le32(READ_ONCE(cmd->cdw15)); - if (!nvme_cmd_allowed(ns, &c, 0, ioucmd->file->f_mode)) + if (!nvme_cmd_allowed(ns, &c, 0, ioucmd->file->f_mode & FMODE_WRITE)) return -EACCES; d.metadata = READ_ONCE(cmd->metadata); @@ -649,13 +649,13 @@ static bool is_ctrl_ioctl(unsigned int cmd) } static int nvme_ctrl_ioctl(struct nvme_ctrl *ctrl, unsigned int cmd, - void __user *argp, fmode_t mode) + void __user *argp, bool open_for_write) { switch (cmd) { case NVME_IOCTL_ADMIN_CMD: - return nvme_user_cmd(ctrl, NULL, argp, 0, mode); + return nvme_user_cmd(ctrl, NULL, argp, 0, open_for_write); case NVME_IOCTL_ADMIN64_CMD: - return nvme_user_cmd64(ctrl, NULL, argp, 0, mode); + return nvme_user_cmd64(ctrl, NULL, argp, 0, open_for_write); default: return sed_ioctl(ctrl->opal_dev, cmd, argp); } @@ -680,14 +680,14 @@ struct nvme_user_io32 { #endif /* COMPAT_FOR_U64_ALIGNMENT */ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd, - void __user *argp, unsigned int flags, fmode_t mode) + void __user *argp, unsigned int flags, bool open_for_write) { switch (cmd) { case NVME_IOCTL_ID: force_successful_syscall_return(); return ns->head->ns_id; case NVME_IOCTL_IO_CMD: - return nvme_user_cmd(ns->ctrl, ns, argp, flags, mode); + return nvme_user_cmd(ns->ctrl, ns, argp, flags, open_for_write); /* * struct nvme_user_io can have different padding on some 32-bit ABIs. * Just accept the compat version as all fields that are used are the @@ -702,16 +702,18 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd, flags |= NVME_IOCTL_VEC; fallthrough; case NVME_IOCTL_IO64_CMD: - return nvme_user_cmd64(ns->ctrl, ns, argp, flags, mode); + return nvme_user_cmd64(ns->ctrl, ns, argp, flags, + open_for_write); default: return -ENOTTY; } } -int nvme_ioctl(struct block_device *bdev, fmode_t mode, +int nvme_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct nvme_ns *ns = bdev->bd_disk->private_data; + bool open_for_write = mode & BLK_OPEN_WRITE; void __user *argp = (void __user *)arg; unsigned int flags = 0; @@ -719,19 +721,20 @@ int nvme_ioctl(struct block_device *bdev, fmode_t mode, flags |= NVME_IOCTL_PARTITION; if (is_ctrl_ioctl(cmd)) - return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, mode); - return nvme_ns_ioctl(ns, cmd, argp, flags, mode); + return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, open_for_write); + return nvme_ns_ioctl(ns, cmd, argp, flags, open_for_write); } long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct nvme_ns *ns = container_of(file_inode(file)->i_cdev, struct nvme_ns, cdev); + bool open_for_write = file->f_mode & FMODE_WRITE; void __user *argp = (void __user *)arg; if (is_ctrl_ioctl(cmd)) - return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, file->f_mode); - return nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode); + return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, open_for_write); + return nvme_ns_ioctl(ns, cmd, argp, 0, open_for_write); } static int nvme_uring_cmd_checks(unsigned int issue_flags) @@ -800,7 +803,7 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd, #ifdef CONFIG_NVME_MULTIPATH static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *argp, struct nvme_ns_head *head, int srcu_idx, - fmode_t mode) + bool open_for_write) __releases(&head->srcu) { struct nvme_ctrl *ctrl = ns->ctrl; @@ -808,16 +811,17 @@ static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, nvme_get_ctrl(ns->ctrl); srcu_read_unlock(&head->srcu, srcu_idx); - ret = nvme_ctrl_ioctl(ns->ctrl, cmd, argp, mode); + ret = nvme_ctrl_ioctl(ns->ctrl, cmd, argp, open_for_write); nvme_put_ctrl(ctrl); return ret; } -int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, +int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct nvme_ns_head *head = bdev->bd_disk->private_data; + bool open_for_write = mode & BLK_OPEN_WRITE; void __user *argp = (void __user *)arg; struct nvme_ns *ns; int srcu_idx, ret = -EWOULDBLOCK; @@ -838,9 +842,9 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, */ if (is_ctrl_ioctl(cmd)) return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx, - mode); + open_for_write); - ret = nvme_ns_ioctl(ns, cmd, argp, flags, mode); + ret = nvme_ns_ioctl(ns, cmd, argp, flags, open_for_write); out_unlock: srcu_read_unlock(&head->srcu, srcu_idx); return ret; @@ -849,6 +853,7 @@ out_unlock: long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + bool open_for_write = file->f_mode & FMODE_WRITE; struct cdev *cdev = file_inode(file)->i_cdev; struct nvme_ns_head *head = container_of(cdev, struct nvme_ns_head, cdev); @@ -863,9 +868,9 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, if (is_ctrl_ioctl(cmd)) return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx, - file->f_mode); + open_for_write); - ret = nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode); + ret = nvme_ns_ioctl(ns, cmd, argp, 0, open_for_write); out_unlock: srcu_read_unlock(&head->srcu, srcu_idx); return ret; @@ -940,7 +945,7 @@ int nvme_dev_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags) } static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp, - fmode_t mode) + bool open_for_write) { struct nvme_ns *ns; int ret; @@ -964,7 +969,7 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp, kref_get(&ns->kref); up_read(&ctrl->namespaces_rwsem); - ret = nvme_user_cmd(ctrl, ns, argp, 0, mode); + ret = nvme_user_cmd(ctrl, ns, argp, 0, open_for_write); nvme_put_ns(ns); return ret; @@ -976,16 +981,17 @@ out_unlock: long nvme_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + bool open_for_write = file->f_mode & FMODE_WRITE; struct nvme_ctrl *ctrl = file->private_data; void __user *argp = (void __user *)arg; switch (cmd) { case NVME_IOCTL_ADMIN_CMD: - return nvme_user_cmd(ctrl, NULL, argp, 0, file->f_mode); + return nvme_user_cmd(ctrl, NULL, argp, 0, open_for_write); case NVME_IOCTL_ADMIN64_CMD: - return nvme_user_cmd64(ctrl, NULL, argp, 0, file->f_mode); + return nvme_user_cmd64(ctrl, NULL, argp, 0, open_for_write); case NVME_IOCTL_IO_CMD: - return nvme_dev_user_cmd(ctrl, argp, file->f_mode); + return nvme_dev_user_cmd(ctrl, argp, open_for_write); case NVME_IOCTL_RESET: if (!capable(CAP_SYS_ADMIN)) return -EACCES; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 2bc159a318ff..98001eebd275 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -402,14 +402,14 @@ static void nvme_ns_head_submit_bio(struct bio *bio) srcu_read_unlock(&head->srcu, srcu_idx); } -static int nvme_ns_head_open(struct block_device *bdev, fmode_t mode) +static int nvme_ns_head_open(struct gendisk *disk, blk_mode_t mode) { - if (!nvme_tryget_ns_head(bdev->bd_disk->private_data)) + if (!nvme_tryget_ns_head(disk->private_data)) return -ENXIO; return 0; } -static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode) +static void nvme_ns_head_release(struct gendisk *disk) { nvme_put_ns_head(disk->private_data); } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 8657811f8b88..9a98c14c552a 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -247,12 +247,13 @@ enum nvme_ctrl_flags { NVME_CTRL_ADMIN_Q_STOPPED = 1, NVME_CTRL_STARTED_ONCE = 2, NVME_CTRL_STOPPED = 3, + NVME_CTRL_SKIP_ID_CNS_CS = 4, }; struct nvme_ctrl { bool comp_seen; - enum nvme_ctrl_state state; bool identified; + enum nvme_ctrl_state state; spinlock_t lock; struct mutex scan_lock; const struct nvme_ctrl_ops *ops; @@ -284,8 +285,8 @@ struct nvme_ctrl { char name[12]; u16 cntlid; - u32 ctrl_config; u16 mtfa; + u32 ctrl_config; u32 queue_count; u64 cap; @@ -359,10 +360,10 @@ struct nvme_ctrl { bool apst_enabled; /* PCIe only: */ + u16 hmmaxd; u32 hmpre; u32 hmmin; u32 hmminds; - u16 hmmaxd; /* Fabrics only */ u32 ioccsz; @@ -842,10 +843,10 @@ void nvme_put_ns_head(struct nvme_ns_head *head); int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device, const struct file_operations *fops, struct module *owner); void nvme_cdev_del(struct cdev *cdev, struct device *cdev_device); -int nvme_ioctl(struct block_device *bdev, fmode_t mode, +int nvme_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); -int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, +int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg); long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -866,7 +867,11 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[]; extern const struct pr_ops nvme_pr_ops; extern const struct block_device_operations nvme_ns_head_ops; extern const struct attribute_group nvme_dev_attrs_group; +extern const struct attribute_group *nvme_subsys_attrs_groups[]; +extern const struct attribute_group *nvme_dev_attr_groups[]; +extern const struct block_device_operations nvme_bdev_ops; +void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl); struct nvme_ns *nvme_find_path(struct nvme_ns_head *head); #ifdef CONFIG_NVME_MULTIPATH static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 492f319ebdf3..48c60f7fda0b 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -420,10 +420,9 @@ static int nvme_pci_init_request(struct blk_mq_tag_set *set, struct request *req, unsigned int hctx_idx, unsigned int numa_node) { - struct nvme_dev *dev = to_nvme_dev(set->driver_data); struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - nvme_req(req)->ctrl = &dev->ctrl; + nvme_req(req)->ctrl = set->driver_data; nvme_req(req)->cmd = &iod->cmd; return 0; } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 0eb79696fb73..d433b2ec07a6 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -501,7 +501,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue) } ibdev = queue->device->dev; - /* +1 for ib_stop_cq */ + /* +1 for ib_drain_qp */ queue->cq_size = cq_factor * queue->queue_size + 1; ret = nvme_rdma_create_cq(ibdev, queue); @@ -713,18 +713,10 @@ out_stop_queues: static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) { struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; - struct ib_device *ibdev = ctrl->device->dev; - unsigned int nr_io_queues, nr_default_queues; - unsigned int nr_read_queues, nr_poll_queues; + unsigned int nr_io_queues; int i, ret; - nr_read_queues = min_t(unsigned int, ibdev->num_comp_vectors, - min(opts->nr_io_queues, num_online_cpus())); - nr_default_queues = min_t(unsigned int, ibdev->num_comp_vectors, - min(opts->nr_write_queues, num_online_cpus())); - nr_poll_queues = min(opts->nr_poll_queues, num_online_cpus()); - nr_io_queues = nr_read_queues + nr_default_queues + nr_poll_queues; - + nr_io_queues = nvmf_nr_io_queues(opts); ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues); if (ret) return ret; @@ -739,34 +731,7 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n", nr_io_queues); - if (opts->nr_write_queues && nr_read_queues < nr_io_queues) { - /* - * separate read/write queues - * hand out dedicated default queues only after we have - * sufficient read queues. - */ - ctrl->io_queues[HCTX_TYPE_READ] = nr_read_queues; - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ]; - ctrl->io_queues[HCTX_TYPE_DEFAULT] = - min(nr_default_queues, nr_io_queues); - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } else { - /* - * shared read/write queues - * either no write queues were requested, or we don't have - * sufficient queue count to have dedicated default queues. - */ - ctrl->io_queues[HCTX_TYPE_DEFAULT] = - min(nr_read_queues, nr_io_queues); - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } - - if (opts->nr_poll_queues && nr_io_queues) { - /* map dedicated poll queues only if we have queues left */ - ctrl->io_queues[HCTX_TYPE_POLL] = - min(nr_poll_queues, nr_io_queues); - } - + nvmf_set_io_queues(opts, nr_io_queues, ctrl->io_queues); for (i = 1; i < ctrl->ctrl.queue_count; i++) { ret = nvme_rdma_alloc_queue(ctrl, i, ctrl->ctrl.sqsize + 1); @@ -2138,44 +2103,8 @@ static void nvme_rdma_complete_rq(struct request *rq) static void nvme_rdma_map_queues(struct blk_mq_tag_set *set) { struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(set->driver_data); - struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; - if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) { - /* separate read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = - ctrl->io_queues[HCTX_TYPE_READ]; - set->map[HCTX_TYPE_READ].queue_offset = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } else { - /* shared read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_READ].queue_offset = 0; - } - blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); - blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); - - if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) { - /* map dedicated poll queues only if we have queues left */ - set->map[HCTX_TYPE_POLL].nr_queues = - ctrl->io_queues[HCTX_TYPE_POLL]; - set->map[HCTX_TYPE_POLL].queue_offset = - ctrl->io_queues[HCTX_TYPE_DEFAULT] + - ctrl->io_queues[HCTX_TYPE_READ]; - blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); - } - - dev_info(ctrl->ctrl.device, - "mapped %d/%d/%d default/read/poll queues.\n", - ctrl->io_queues[HCTX_TYPE_DEFAULT], - ctrl->io_queues[HCTX_TYPE_READ], - ctrl->io_queues[HCTX_TYPE_POLL]); + nvmf_map_queues(set, &ctrl->ctrl, ctrl->io_queues); } static const struct blk_mq_ops nvme_rdma_mq_ops = { diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c new file mode 100644 index 000000000000..45e91811f905 --- /dev/null +++ b/drivers/nvme/host/sysfs.c @@ -0,0 +1,668 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Sysfs interface for the NVMe core driver. + * + * Copyright (c) 2011-2014, Intel Corporation. + */ + +#include <linux/nvme-auth.h> + +#include "nvme.h" +#include "fabrics.h" + +static ssize_t nvme_sysfs_reset(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + int ret; + + ret = nvme_reset_ctrl_sync(ctrl); + if (ret < 0) + return ret; + return count; +} +static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset); + +static ssize_t nvme_sysfs_rescan(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + nvme_queue_scan(ctrl); + return count; +} +static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan); + +static inline struct nvme_ns_head *dev_to_ns_head(struct device *dev) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (disk->fops == &nvme_bdev_ops) + return nvme_get_ns_from_dev(dev)->head; + else + return disk->private_data; +} + +static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nvme_ns_head *head = dev_to_ns_head(dev); + struct nvme_ns_ids *ids = &head->ids; + struct nvme_subsystem *subsys = head->subsys; + int serial_len = sizeof(subsys->serial); + int model_len = sizeof(subsys->model); + + if (!uuid_is_null(&ids->uuid)) + return sysfs_emit(buf, "uuid.%pU\n", &ids->uuid); + + if (memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + return sysfs_emit(buf, "eui.%16phN\n", ids->nguid); + + if (memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + return sysfs_emit(buf, "eui.%8phN\n", ids->eui64); + + while (serial_len > 0 && (subsys->serial[serial_len - 1] == ' ' || + subsys->serial[serial_len - 1] == '\0')) + serial_len--; + while (model_len > 0 && (subsys->model[model_len - 1] == ' ' || + subsys->model[model_len - 1] == '\0')) + model_len--; + + return sysfs_emit(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id, + serial_len, subsys->serial, model_len, subsys->model, + head->ns_id); +} +static DEVICE_ATTR_RO(wwid); + +static ssize_t nguid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%pU\n", dev_to_ns_head(dev)->ids.nguid); +} +static DEVICE_ATTR_RO(nguid); + +static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids; + + /* For backward compatibility expose the NGUID to userspace if + * we have no UUID set + */ + if (uuid_is_null(&ids->uuid)) { + dev_warn_ratelimited(dev, + "No UUID available providing old NGUID\n"); + return sysfs_emit(buf, "%pU\n", ids->nguid); + } + return sysfs_emit(buf, "%pU\n", &ids->uuid); +} +static DEVICE_ATTR_RO(uuid); + +static ssize_t eui_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%8ph\n", dev_to_ns_head(dev)->ids.eui64); +} +static DEVICE_ATTR_RO(eui); + +static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%d\n", dev_to_ns_head(dev)->ns_id); +} +static DEVICE_ATTR_RO(nsid); + +static struct attribute *nvme_ns_id_attrs[] = { + &dev_attr_wwid.attr, + &dev_attr_uuid.attr, + &dev_attr_nguid.attr, + &dev_attr_eui.attr, + &dev_attr_nsid.attr, +#ifdef CONFIG_NVME_MULTIPATH + &dev_attr_ana_grpid.attr, + &dev_attr_ana_state.attr, +#endif + NULL, +}; + +static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct nvme_ns_ids *ids = &dev_to_ns_head(dev)->ids; + + if (a == &dev_attr_uuid.attr) { + if (uuid_is_null(&ids->uuid) && + !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + return 0; + } + if (a == &dev_attr_nguid.attr) { + if (!memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + return 0; + } + if (a == &dev_attr_eui.attr) { + if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + return 0; + } +#ifdef CONFIG_NVME_MULTIPATH + if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) { + if (dev_to_disk(dev)->fops != &nvme_bdev_ops) /* per-path attr */ + return 0; + if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl)) + return 0; + } +#endif + return a->mode; +} + +static const struct attribute_group nvme_ns_id_attr_group = { + .attrs = nvme_ns_id_attrs, + .is_visible = nvme_ns_id_attrs_are_visible, +}; + +const struct attribute_group *nvme_ns_id_attr_groups[] = { + &nvme_ns_id_attr_group, + NULL, +}; + +#define nvme_show_str_function(field) \ +static ssize_t field##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ + return sysfs_emit(buf, "%.*s\n", \ + (int)sizeof(ctrl->subsys->field), ctrl->subsys->field); \ +} \ +static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); + +nvme_show_str_function(model); +nvme_show_str_function(serial); +nvme_show_str_function(firmware_rev); + +#define nvme_show_int_function(field) \ +static ssize_t field##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ + return sysfs_emit(buf, "%d\n", ctrl->field); \ +} \ +static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); + +nvme_show_int_function(cntlid); +nvme_show_int_function(numa_node); +nvme_show_int_function(queue_count); +nvme_show_int_function(sqsize); +nvme_show_int_function(kato); + +static ssize_t nvme_sysfs_delete(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags)) + return -EBUSY; + + if (device_remove_file_self(dev, attr)) + nvme_delete_ctrl_sync(ctrl); + return count; +} +static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete); + +static ssize_t nvme_sysfs_show_transport(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%s\n", ctrl->ops->name); +} +static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL); + +static ssize_t nvme_sysfs_show_state(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + static const char *const state_name[] = { + [NVME_CTRL_NEW] = "new", + [NVME_CTRL_LIVE] = "live", + [NVME_CTRL_RESETTING] = "resetting", + [NVME_CTRL_CONNECTING] = "connecting", + [NVME_CTRL_DELETING] = "deleting", + [NVME_CTRL_DELETING_NOIO]= "deleting (no IO)", + [NVME_CTRL_DEAD] = "dead", + }; + + if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) && + state_name[ctrl->state]) + return sysfs_emit(buf, "%s\n", state_name[ctrl->state]); + + return sysfs_emit(buf, "unknown state\n"); +} + +static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL); + +static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%s\n", ctrl->subsys->subnqn); +} +static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL); + +static ssize_t nvme_sysfs_show_hostnqn(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%s\n", ctrl->opts->host->nqn); +} +static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL); + +static ssize_t nvme_sysfs_show_hostid(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%pU\n", &ctrl->opts->host->id); +} +static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL); + +static ssize_t nvme_sysfs_show_address(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + return ctrl->ops->get_address(ctrl, buf, PAGE_SIZE); +} +static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL); + +static ssize_t nvme_ctrl_loss_tmo_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (ctrl->opts->max_reconnects == -1) + return sysfs_emit(buf, "off\n"); + return sysfs_emit(buf, "%d\n", + opts->max_reconnects * opts->reconnect_delay); +} + +static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + int ctrl_loss_tmo, err; + + err = kstrtoint(buf, 10, &ctrl_loss_tmo); + if (err) + return -EINVAL; + + if (ctrl_loss_tmo < 0) + opts->max_reconnects = -1; + else + opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo, + opts->reconnect_delay); + return count; +} +static DEVICE_ATTR(ctrl_loss_tmo, S_IRUGO | S_IWUSR, + nvme_ctrl_loss_tmo_show, nvme_ctrl_loss_tmo_store); + +static ssize_t nvme_ctrl_reconnect_delay_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (ctrl->opts->reconnect_delay == -1) + return sysfs_emit(buf, "off\n"); + return sysfs_emit(buf, "%d\n", ctrl->opts->reconnect_delay); +} + +static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + unsigned int v; + int err; + + err = kstrtou32(buf, 10, &v); + if (err) + return err; + + ctrl->opts->reconnect_delay = v; + return count; +} +static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR, + nvme_ctrl_reconnect_delay_show, nvme_ctrl_reconnect_delay_store); + +static ssize_t nvme_ctrl_fast_io_fail_tmo_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (ctrl->opts->fast_io_fail_tmo == -1) + return sysfs_emit(buf, "off\n"); + return sysfs_emit(buf, "%d\n", ctrl->opts->fast_io_fail_tmo); +} + +static ssize_t nvme_ctrl_fast_io_fail_tmo_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + int fast_io_fail_tmo, err; + + err = kstrtoint(buf, 10, &fast_io_fail_tmo); + if (err) + return -EINVAL; + + if (fast_io_fail_tmo < 0) + opts->fast_io_fail_tmo = -1; + else + opts->fast_io_fail_tmo = fast_io_fail_tmo; + return count; +} +static DEVICE_ATTR(fast_io_fail_tmo, S_IRUGO | S_IWUSR, + nvme_ctrl_fast_io_fail_tmo_show, nvme_ctrl_fast_io_fail_tmo_store); + +static ssize_t cntrltype_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + static const char * const type[] = { + [NVME_CTRL_IO] = "io\n", + [NVME_CTRL_DISC] = "discovery\n", + [NVME_CTRL_ADMIN] = "admin\n", + }; + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (ctrl->cntrltype > NVME_CTRL_ADMIN || !type[ctrl->cntrltype]) + return sysfs_emit(buf, "reserved\n"); + + return sysfs_emit(buf, type[ctrl->cntrltype]); +} +static DEVICE_ATTR_RO(cntrltype); + +static ssize_t dctype_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + static const char * const type[] = { + [NVME_DCTYPE_NOT_REPORTED] = "none\n", + [NVME_DCTYPE_DDC] = "ddc\n", + [NVME_DCTYPE_CDC] = "cdc\n", + }; + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (ctrl->dctype > NVME_DCTYPE_CDC || !type[ctrl->dctype]) + return sysfs_emit(buf, "reserved\n"); + + return sysfs_emit(buf, type[ctrl->dctype]); +} +static DEVICE_ATTR_RO(dctype); + +#ifdef CONFIG_NVME_AUTH +static ssize_t nvme_ctrl_dhchap_secret_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (!opts->dhchap_secret) + return sysfs_emit(buf, "none\n"); + return sysfs_emit(buf, "%s\n", opts->dhchap_secret); +} + +static ssize_t nvme_ctrl_dhchap_secret_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + char *dhchap_secret; + + if (!ctrl->opts->dhchap_secret) + return -EINVAL; + if (count < 7) + return -EINVAL; + if (memcmp(buf, "DHHC-1:", 7)) + return -EINVAL; + + dhchap_secret = kzalloc(count + 1, GFP_KERNEL); + if (!dhchap_secret) + return -ENOMEM; + memcpy(dhchap_secret, buf, count); + nvme_auth_stop(ctrl); + if (strcmp(dhchap_secret, opts->dhchap_secret)) { + struct nvme_dhchap_key *key, *host_key; + int ret; + + ret = nvme_auth_generate_key(dhchap_secret, &key); + if (ret) { + kfree(dhchap_secret); + return ret; + } + kfree(opts->dhchap_secret); + opts->dhchap_secret = dhchap_secret; + host_key = ctrl->host_key; + mutex_lock(&ctrl->dhchap_auth_mutex); + ctrl->host_key = key; + mutex_unlock(&ctrl->dhchap_auth_mutex); + nvme_auth_free_key(host_key); + } else + kfree(dhchap_secret); + /* Start re-authentication */ + dev_info(ctrl->device, "re-authenticating controller\n"); + queue_work(nvme_wq, &ctrl->dhchap_auth_work); + + return count; +} + +static DEVICE_ATTR(dhchap_secret, S_IRUGO | S_IWUSR, + nvme_ctrl_dhchap_secret_show, nvme_ctrl_dhchap_secret_store); + +static ssize_t nvme_ctrl_dhchap_ctrl_secret_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + + if (!opts->dhchap_ctrl_secret) + return sysfs_emit(buf, "none\n"); + return sysfs_emit(buf, "%s\n", opts->dhchap_ctrl_secret); +} + +static ssize_t nvme_ctrl_dhchap_ctrl_secret_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + struct nvmf_ctrl_options *opts = ctrl->opts; + char *dhchap_secret; + + if (!ctrl->opts->dhchap_ctrl_secret) + return -EINVAL; + if (count < 7) + return -EINVAL; + if (memcmp(buf, "DHHC-1:", 7)) + return -EINVAL; + + dhchap_secret = kzalloc(count + 1, GFP_KERNEL); + if (!dhchap_secret) + return -ENOMEM; + memcpy(dhchap_secret, buf, count); + nvme_auth_stop(ctrl); + if (strcmp(dhchap_secret, opts->dhchap_ctrl_secret)) { + struct nvme_dhchap_key *key, *ctrl_key; + int ret; + + ret = nvme_auth_generate_key(dhchap_secret, &key); + if (ret) { + kfree(dhchap_secret); + return ret; + } + kfree(opts->dhchap_ctrl_secret); + opts->dhchap_ctrl_secret = dhchap_secret; + ctrl_key = ctrl->ctrl_key; + mutex_lock(&ctrl->dhchap_auth_mutex); + ctrl->ctrl_key = key; + mutex_unlock(&ctrl->dhchap_auth_mutex); + nvme_auth_free_key(ctrl_key); + } else + kfree(dhchap_secret); + /* Start re-authentication */ + dev_info(ctrl->device, "re-authenticating controller\n"); + queue_work(nvme_wq, &ctrl->dhchap_auth_work); + + return count; +} + +static DEVICE_ATTR(dhchap_ctrl_secret, S_IRUGO | S_IWUSR, + nvme_ctrl_dhchap_ctrl_secret_show, nvme_ctrl_dhchap_ctrl_secret_store); +#endif + +static struct attribute *nvme_dev_attrs[] = { + &dev_attr_reset_controller.attr, + &dev_attr_rescan_controller.attr, + &dev_attr_model.attr, + &dev_attr_serial.attr, + &dev_attr_firmware_rev.attr, + &dev_attr_cntlid.attr, + &dev_attr_delete_controller.attr, + &dev_attr_transport.attr, + &dev_attr_subsysnqn.attr, + &dev_attr_address.attr, + &dev_attr_state.attr, + &dev_attr_numa_node.attr, + &dev_attr_queue_count.attr, + &dev_attr_sqsize.attr, + &dev_attr_hostnqn.attr, + &dev_attr_hostid.attr, + &dev_attr_ctrl_loss_tmo.attr, + &dev_attr_reconnect_delay.attr, + &dev_attr_fast_io_fail_tmo.attr, + &dev_attr_kato.attr, + &dev_attr_cntrltype.attr, + &dev_attr_dctype.attr, +#ifdef CONFIG_NVME_AUTH + &dev_attr_dhchap_secret.attr, + &dev_attr_dhchap_ctrl_secret.attr, +#endif + NULL +}; + +static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + + if (a == &dev_attr_delete_controller.attr && !ctrl->ops->delete_ctrl) + return 0; + if (a == &dev_attr_address.attr && !ctrl->ops->get_address) + return 0; + if (a == &dev_attr_hostnqn.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_hostid.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_ctrl_loss_tmo.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_fast_io_fail_tmo.attr && !ctrl->opts) + return 0; +#ifdef CONFIG_NVME_AUTH + if (a == &dev_attr_dhchap_secret.attr && !ctrl->opts) + return 0; + if (a == &dev_attr_dhchap_ctrl_secret.attr && !ctrl->opts) + return 0; +#endif + + return a->mode; +} + +const struct attribute_group nvme_dev_attrs_group = { + .attrs = nvme_dev_attrs, + .is_visible = nvme_dev_attrs_are_visible, +}; +EXPORT_SYMBOL_GPL(nvme_dev_attrs_group); + +const struct attribute_group *nvme_dev_attr_groups[] = { + &nvme_dev_attrs_group, + NULL, +}; + +#define SUBSYS_ATTR_RO(_name, _mode, _show) \ + struct device_attribute subsys_attr_##_name = \ + __ATTR(_name, _mode, _show, NULL) + +static ssize_t nvme_subsys_show_nqn(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + + return sysfs_emit(buf, "%s\n", subsys->subnqn); +} +static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn); + +static ssize_t nvme_subsys_show_type(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + + switch (subsys->subtype) { + case NVME_NQN_DISC: + return sysfs_emit(buf, "discovery\n"); + case NVME_NQN_NVME: + return sysfs_emit(buf, "nvm\n"); + default: + return sysfs_emit(buf, "reserved\n"); + } +} +static SUBSYS_ATTR_RO(subsystype, S_IRUGO, nvme_subsys_show_type); + +#define nvme_subsys_show_str_function(field) \ +static ssize_t subsys_##field##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct nvme_subsystem *subsys = \ + container_of(dev, struct nvme_subsystem, dev); \ + return sysfs_emit(buf, "%.*s\n", \ + (int)sizeof(subsys->field), subsys->field); \ +} \ +static SUBSYS_ATTR_RO(field, S_IRUGO, subsys_##field##_show); + +nvme_subsys_show_str_function(model); +nvme_subsys_show_str_function(serial); +nvme_subsys_show_str_function(firmware_rev); + +static struct attribute *nvme_subsys_attrs[] = { + &subsys_attr_model.attr, + &subsys_attr_serial.attr, + &subsys_attr_firmware_rev.attr, + &subsys_attr_subsysnqn.attr, + &subsys_attr_subsystype.attr, +#ifdef CONFIG_NVME_MULTIPATH + &subsys_attr_iopolicy.attr, +#endif + NULL, +}; + +static const struct attribute_group nvme_subsys_attrs_group = { + .attrs = nvme_subsys_attrs, +}; + +const struct attribute_group *nvme_subsys_attrs_groups[] = { + &nvme_subsys_attrs_group, + NULL, +}; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index bf0230442d57..260b3554d821 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1802,58 +1802,12 @@ out_free_queues: return ret; } -static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl) -{ - unsigned int nr_io_queues; - - nr_io_queues = min(ctrl->opts->nr_io_queues, num_online_cpus()); - nr_io_queues += min(ctrl->opts->nr_write_queues, num_online_cpus()); - nr_io_queues += min(ctrl->opts->nr_poll_queues, num_online_cpus()); - - return nr_io_queues; -} - -static void nvme_tcp_set_io_queues(struct nvme_ctrl *nctrl, - unsigned int nr_io_queues) -{ - struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); - struct nvmf_ctrl_options *opts = nctrl->opts; - - if (opts->nr_write_queues && opts->nr_io_queues < nr_io_queues) { - /* - * separate read/write queues - * hand out dedicated default queues only after we have - * sufficient read queues. - */ - ctrl->io_queues[HCTX_TYPE_READ] = opts->nr_io_queues; - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_READ]; - ctrl->io_queues[HCTX_TYPE_DEFAULT] = - min(opts->nr_write_queues, nr_io_queues); - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } else { - /* - * shared read/write queues - * either no write queues were requested, or we don't have - * sufficient queue count to have dedicated default queues. - */ - ctrl->io_queues[HCTX_TYPE_DEFAULT] = - min(opts->nr_io_queues, nr_io_queues); - nr_io_queues -= ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } - - if (opts->nr_poll_queues && nr_io_queues) { - /* map dedicated poll queues only if we have queues left */ - ctrl->io_queues[HCTX_TYPE_POLL] = - min(opts->nr_poll_queues, nr_io_queues); - } -} - static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) { unsigned int nr_io_queues; int ret; - nr_io_queues = nvme_tcp_nr_io_queues(ctrl); + nr_io_queues = nvmf_nr_io_queues(ctrl->opts); ret = nvme_set_queue_count(ctrl, &nr_io_queues); if (ret) return ret; @@ -1868,8 +1822,8 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) dev_info(ctrl->device, "creating %d I/O queues.\n", nr_io_queues); - nvme_tcp_set_io_queues(ctrl, nr_io_queues); - + nvmf_set_io_queues(ctrl->opts, nr_io_queues, + to_tcp_ctrl(ctrl)->io_queues); return __nvme_tcp_alloc_io_queues(ctrl); } @@ -2449,44 +2403,8 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx, static void nvme_tcp_map_queues(struct blk_mq_tag_set *set) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(set->driver_data); - struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; - - if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) { - /* separate read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = - ctrl->io_queues[HCTX_TYPE_READ]; - set->map[HCTX_TYPE_READ].queue_offset = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - } else { - /* shared read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = - ctrl->io_queues[HCTX_TYPE_DEFAULT]; - set->map[HCTX_TYPE_READ].queue_offset = 0; - } - blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); - blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); - - if (opts->nr_poll_queues && ctrl->io_queues[HCTX_TYPE_POLL]) { - /* map dedicated poll queues only if we have queues left */ - set->map[HCTX_TYPE_POLL].nr_queues = - ctrl->io_queues[HCTX_TYPE_POLL]; - set->map[HCTX_TYPE_POLL].queue_offset = - ctrl->io_queues[HCTX_TYPE_DEFAULT] + - ctrl->io_queues[HCTX_TYPE_READ]; - blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); - } - - dev_info(ctrl->ctrl.device, - "mapped %d/%d/%d default/read/poll queues.\n", - ctrl->io_queues[HCTX_TYPE_DEFAULT], - ctrl->io_queues[HCTX_TYPE_READ], - ctrl->io_queues[HCTX_TYPE_POLL]); + + nvmf_map_queues(set, &ctrl->ctrl, ctrl->io_queues); } static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index 7970a7640e58..586458f765f1 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -295,13 +295,11 @@ void nvmet_execute_auth_send(struct nvmet_req *req) status = 0; } goto done_kfree; - break; case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2: req->sq->authenticated = true; pr_debug("%s: ctrl %d qid %d ctrl authenticated\n", __func__, ctrl->cntlid, req->sq->qid); goto done_kfree; - break; case NVME_AUTH_DHCHAP_MESSAGE_FAILURE2: status = nvmet_auth_failure2(d); if (status) { @@ -312,7 +310,6 @@ void nvmet_execute_auth_send(struct nvmet_req *req) status = 0; } goto done_kfree; - break; default: req->sq->dhchap_status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE; @@ -320,7 +317,6 @@ void nvmet_execute_auth_send(struct nvmet_req *req) NVME_AUTH_DHCHAP_MESSAGE_FAILURE2; req->sq->authenticated = false; goto done_kfree; - break; } done_failure1: req->sq->dhchap_status = NVME_AUTH_DHCHAP_FAILURE_INCORRECT_MESSAGE; @@ -483,15 +479,6 @@ void nvmet_execute_auth_receive(struct nvmet_req *req) status = NVME_SC_INTERNAL; break; } - if (status) { - req->sq->dhchap_status = status; - nvmet_auth_failure1(req, d, al); - pr_warn("ctrl %d qid %d: challenge status (%x)\n", - ctrl->cntlid, req->sq->qid, - req->sq->dhchap_status); - status = 0; - break; - } req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_REPLY; break; case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1: diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index e940a7d37a9d..c65a73433c05 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -645,8 +645,6 @@ fcloop_fcp_recv_work(struct work_struct *work) } if (ret) fcloop_call_host_done(fcpreq, tfcp_req, ret); - - return; } static void @@ -1168,7 +1166,8 @@ __wait_localport_unreg(struct fcloop_lport *lport) ret = nvme_fc_unregister_localport(lport->localport); - wait_for_completion(&lport->unreg_done); + if (!ret) + wait_for_completion(&lport->unreg_done); kfree(lport); diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index c2d6cea0236b..2733e0158585 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -51,7 +51,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) void nvmet_bdev_ns_disable(struct nvmet_ns *ns) { if (ns->bdev) { - blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ); + blkdev_put(ns->bdev, NULL); ns->bdev = NULL; } } @@ -85,7 +85,7 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns) return -ENOTBLK; ns->bdev = blkdev_get_by_path(ns->device_path, - FMODE_READ | FMODE_WRITE, NULL); + BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL); if (IS_ERR(ns->bdev)) { ret = PTR_ERR(ns->bdev); if (ret != -ENOTBLK) { diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index dc60a22646f7..6cf723bc664e 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -109,8 +109,8 @@ struct nvmet_sq { u32 sqhd; bool sqhd_disabled; #ifdef CONFIG_NVME_TARGET_AUTH - struct delayed_work auth_expired_work; bool authenticated; + struct delayed_work auth_expired_work; u16 dhchap_tid; u16 dhchap_status; int dhchap_step; diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 9fbfce735d56..45788955c4e6 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -3234,12 +3234,12 @@ struct blk_mq_ops dasd_mq_ops = { .exit_hctx = dasd_exit_hctx, }; -static int dasd_open(struct block_device *bdev, fmode_t mode) +static int dasd_open(struct gendisk *disk, blk_mode_t mode) { struct dasd_device *base; int rc; - base = dasd_device_from_gendisk(bdev->bd_disk); + base = dasd_device_from_gendisk(disk); if (!base) return -ENODEV; @@ -3268,14 +3268,12 @@ static int dasd_open(struct block_device *bdev, fmode_t mode) rc = -ENODEV; goto out; } - - if ((mode & FMODE_WRITE) && + if ((mode & BLK_OPEN_WRITE) && (test_bit(DASD_FLAG_DEVICE_RO, &base->flags) || (base->features & DASD_FEATURE_READONLY))) { rc = -EROFS; goto out; } - dasd_put_device(base); return 0; @@ -3287,7 +3285,7 @@ unlock: return rc; } -static void dasd_release(struct gendisk *disk, fmode_t mode) +static void dasd_release(struct gendisk *disk) { struct dasd_device *base = dasd_device_from_gendisk(disk); if (base) { diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 998a961e1704..fe5108a1b332 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -130,7 +130,8 @@ int dasd_scan_partitions(struct dasd_block *block) struct block_device *bdev; int rc; - bdev = blkdev_get_by_dev(disk_devt(block->gdp), FMODE_READ, NULL); + bdev = blkdev_get_by_dev(disk_devt(block->gdp), BLK_OPEN_READ, NULL, + NULL); if (IS_ERR(bdev)) { DBF_DEV_EVENT(DBF_ERR, block->base, "scan partitions error, blkdev_get returned %ld", @@ -179,7 +180,7 @@ void dasd_destroy_partitions(struct dasd_block *block) mutex_unlock(&bdev->bd_disk->open_mutex); /* Matching blkdev_put to the blkdev_get in dasd_scan_partitions. */ - blkdev_put(bdev, FMODE_READ); + blkdev_put(bdev, NULL); } int dasd_gendisk_init(void) diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 33f812f0e515..0aa56351da72 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -965,7 +965,8 @@ int dasd_scan_partitions(struct dasd_block *); void dasd_destroy_partitions(struct dasd_block *); /* externals in dasd_ioctl.c */ -int dasd_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); +int dasd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, + unsigned long arg); int dasd_set_read_only(struct block_device *bdev, bool ro); /* externals in dasd_proc.c */ diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 8fca725b3dae..513a7e6eee63 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -612,7 +612,7 @@ static int dasd_ioctl_readall_cmb(struct dasd_block *block, unsigned int cmd, return ret; } -int dasd_ioctl(struct block_device *bdev, fmode_t mode, +int dasd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct dasd_block *block; diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index c09f2e053bf8..200f88f0e451 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -28,8 +28,8 @@ #define DCSSBLK_PARM_LEN 400 #define DCSS_BUS_ID_SIZE 20 -static int dcssblk_open(struct block_device *bdev, fmode_t mode); -static void dcssblk_release(struct gendisk *disk, fmode_t mode); +static int dcssblk_open(struct gendisk *disk, blk_mode_t mode); +static void dcssblk_release(struct gendisk *disk); static void dcssblk_submit_bio(struct bio *bio); static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, @@ -809,12 +809,11 @@ out_buf: } static int -dcssblk_open(struct block_device *bdev, fmode_t mode) +dcssblk_open(struct gendisk *disk, blk_mode_t mode) { - struct dcssblk_dev_info *dev_info; + struct dcssblk_dev_info *dev_info = disk->private_data; int rc; - dev_info = bdev->bd_disk->private_data; if (NULL == dev_info) { rc = -ENODEV; goto out; @@ -826,7 +825,7 @@ out: } static void -dcssblk_release(struct gendisk *disk, fmode_t mode) +dcssblk_release(struct gendisk *disk) { struct dcssblk_dev_info *dev_info = disk->private_data; struct segment_info *entry; diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c index ac648bb8f7e7..cb0a399be1cc 100644 --- a/drivers/scsi/ch.c +++ b/drivers/scsi/ch.c @@ -877,7 +877,8 @@ static long ch_ioctl(struct file *file, } default: - return scsi_ioctl(ch->device, file->f_mode, cmd, argp); + return scsi_ioctl(ch->device, file->f_mode & FMODE_WRITE, cmd, + argp); } } diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index 96ee35256a16..a9a9ec086a7e 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -10,7 +10,7 @@ #define uptr64(val) ((void __user *)(uintptr_t)(val)) static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, - fmode_t mode, unsigned int timeout) + bool open_for_write, unsigned int timeout) { struct scsi_cmnd *scmd; struct request *rq; @@ -42,7 +42,7 @@ static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, if (copy_from_user(scmd->cmnd, uptr64(hdr->request), scmd->cmd_len)) goto out_put_request; ret = -EPERM; - if (!scsi_cmd_allowed(scmd->cmnd, mode)) + if (!scsi_cmd_allowed(scmd->cmnd, open_for_write)) goto out_put_request; ret = 0; diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c index e3b31d32b6a9..6f6c5973c3ea 100644 --- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -248,7 +248,7 @@ static int scsi_send_start_stop(struct scsi_device *sdev, int data) * Only a subset of commands are allowed for unprivileged users. Commands used * to format the media, update the firmware, etc. are not permitted. */ -bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) +bool scsi_cmd_allowed(unsigned char *cmd, bool open_for_write) { /* root can do any command. */ if (capable(CAP_SYS_RAWIO)) @@ -338,7 +338,7 @@ bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) case GPCMD_SET_READ_AHEAD: /* ZBC */ case ZBC_OUT: - return (mode & FMODE_WRITE); + return open_for_write; default: return false; } @@ -346,7 +346,7 @@ bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode) EXPORT_SYMBOL(scsi_cmd_allowed); static int scsi_fill_sghdr_rq(struct scsi_device *sdev, struct request *rq, - struct sg_io_hdr *hdr, fmode_t mode) + struct sg_io_hdr *hdr, bool open_for_write) { struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq); @@ -354,7 +354,7 @@ static int scsi_fill_sghdr_rq(struct scsi_device *sdev, struct request *rq, return -EMSGSIZE; if (copy_from_user(scmd->cmnd, hdr->cmdp, hdr->cmd_len)) return -EFAULT; - if (!scsi_cmd_allowed(scmd->cmnd, mode)) + if (!scsi_cmd_allowed(scmd->cmnd, open_for_write)) return -EPERM; scmd->cmd_len = hdr->cmd_len; @@ -407,7 +407,8 @@ static int scsi_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr, return ret; } -static int sg_io(struct scsi_device *sdev, struct sg_io_hdr *hdr, fmode_t mode) +static int sg_io(struct scsi_device *sdev, struct sg_io_hdr *hdr, + bool open_for_write) { unsigned long start_time; ssize_t ret = 0; @@ -448,7 +449,7 @@ static int sg_io(struct scsi_device *sdev, struct sg_io_hdr *hdr, fmode_t mode) goto out_put_request; } - ret = scsi_fill_sghdr_rq(sdev, rq, hdr, mode); + ret = scsi_fill_sghdr_rq(sdev, rq, hdr, open_for_write); if (ret < 0) goto out_put_request; @@ -477,8 +478,7 @@ out_put_request: /** * sg_scsi_ioctl -- handle deprecated SCSI_IOCTL_SEND_COMMAND ioctl * @q: request queue to send scsi commands down - * @mode: mode used to open the file through which the ioctl has been - * submitted + * @open_for_write: is the file / block device opened for writing? * @sic: userspace structure describing the command to perform * * Send down the scsi command described by @sic to the device below @@ -501,7 +501,7 @@ out_put_request: * Positive numbers returned are the compacted SCSI error codes (4 * bytes in one int) where the lowest byte is the SCSI status. */ -static int sg_scsi_ioctl(struct request_queue *q, fmode_t mode, +static int sg_scsi_ioctl(struct request_queue *q, bool open_for_write, struct scsi_ioctl_command __user *sic) { struct request *rq; @@ -554,7 +554,7 @@ static int sg_scsi_ioctl(struct request_queue *q, fmode_t mode, goto error; err = -EPERM; - if (!scsi_cmd_allowed(scmd->cmnd, mode)) + if (!scsi_cmd_allowed(scmd->cmnd, open_for_write)) goto error; /* default. possible overridden later */ @@ -776,7 +776,7 @@ static int scsi_put_cdrom_generic_arg(const struct cdrom_generic_command *cgc, return 0; } -static int scsi_cdrom_send_packet(struct scsi_device *sdev, fmode_t mode, +static int scsi_cdrom_send_packet(struct scsi_device *sdev, bool open_for_write, void __user *arg) { struct cdrom_generic_command cgc; @@ -817,7 +817,7 @@ static int scsi_cdrom_send_packet(struct scsi_device *sdev, fmode_t mode, hdr.cmdp = ((struct cdrom_generic_command __user *) arg)->cmd; hdr.cmd_len = sizeof(cgc.cmd); - err = sg_io(sdev, &hdr, mode); + err = sg_io(sdev, &hdr, open_for_write); if (err == -EFAULT) return -EFAULT; @@ -832,7 +832,7 @@ static int scsi_cdrom_send_packet(struct scsi_device *sdev, fmode_t mode, return err; } -static int scsi_ioctl_sg_io(struct scsi_device *sdev, fmode_t mode, +static int scsi_ioctl_sg_io(struct scsi_device *sdev, bool open_for_write, void __user *argp) { struct sg_io_hdr hdr; @@ -841,7 +841,7 @@ static int scsi_ioctl_sg_io(struct scsi_device *sdev, fmode_t mode, error = get_sg_io_hdr(&hdr, argp); if (error) return error; - error = sg_io(sdev, &hdr, mode); + error = sg_io(sdev, &hdr, open_for_write); if (error == -EFAULT) return error; if (put_sg_io_hdr(&hdr, argp)) @@ -852,7 +852,7 @@ static int scsi_ioctl_sg_io(struct scsi_device *sdev, fmode_t mode, /** * scsi_ioctl - Dispatch ioctl to scsi device * @sdev: scsi device receiving ioctl - * @mode: mode the block/char device is opened with + * @open_for_write: is the file / block device opened for writing? * @cmd: which ioctl is it * @arg: data associated with ioctl * @@ -860,7 +860,7 @@ static int scsi_ioctl_sg_io(struct scsi_device *sdev, fmode_t mode, * does not take a major/minor number as the dev field. Rather, it takes * a pointer to a &struct scsi_device. */ -int scsi_ioctl(struct scsi_device *sdev, fmode_t mode, int cmd, +int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd, void __user *arg) { struct request_queue *q = sdev->request_queue; @@ -896,11 +896,11 @@ int scsi_ioctl(struct scsi_device *sdev, fmode_t mode, int cmd, case SG_EMULATED_HOST: return sg_emulated_host(q, arg); case SG_IO: - return scsi_ioctl_sg_io(sdev, mode, arg); + return scsi_ioctl_sg_io(sdev, open_for_write, arg); case SCSI_IOCTL_SEND_COMMAND: - return sg_scsi_ioctl(q, mode, arg); + return sg_scsi_ioctl(q, open_for_write, arg); case CDROM_SEND_PACKET: - return scsi_cdrom_send_packet(sdev, mode, arg); + return scsi_cdrom_send_packet(sdev, open_for_write, arg); case CDROMCLOSETRAY: return scsi_send_start_stop(sdev, 3); case CDROMEJECT: diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 1624d528aa1f..ab216976dbdc 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1280,11 +1280,10 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt) mempool_free(rq->special_vec.bv_page, sd_page_pool); } -static bool sd_need_revalidate(struct block_device *bdev, - struct scsi_disk *sdkp) +static bool sd_need_revalidate(struct gendisk *disk, struct scsi_disk *sdkp) { if (sdkp->device->removable || sdkp->write_prot) { - if (bdev_check_media_change(bdev)) + if (disk_check_media_change(disk)) return true; } @@ -1293,13 +1292,13 @@ static bool sd_need_revalidate(struct block_device *bdev, * nothing to do with partitions, BLKRRPART is used to force a full * revalidate after things like a format for historical reasons. */ - return test_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + return test_bit(GD_NEED_PART_SCAN, &disk->state); } /** * sd_open - open a scsi disk device - * @bdev: Block device of the scsi disk to open - * @mode: FMODE_* mask + * @disk: disk to open + * @mode: open mode * * Returns 0 if successful. Returns a negated errno value in case * of error. @@ -1309,11 +1308,11 @@ static bool sd_need_revalidate(struct block_device *bdev, * In the latter case @inode and @filp carry an abridged amount * of information as noted above. * - * Locking: called with bdev->bd_disk->open_mutex held. + * Locking: called with disk->open_mutex held. **/ -static int sd_open(struct block_device *bdev, fmode_t mode) +static int sd_open(struct gendisk *disk, blk_mode_t mode) { - struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); + struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdev = sdkp->device; int retval; @@ -1330,14 +1329,15 @@ static int sd_open(struct block_device *bdev, fmode_t mode) if (!scsi_block_when_processing_errors(sdev)) goto error_out; - if (sd_need_revalidate(bdev, sdkp)) - sd_revalidate_disk(bdev->bd_disk); + if (sd_need_revalidate(disk, sdkp)) + sd_revalidate_disk(disk); /* * If the drive is empty, just let the open fail. */ retval = -ENOMEDIUM; - if (sdev->removable && !sdkp->media_present && !(mode & FMODE_NDELAY)) + if (sdev->removable && !sdkp->media_present && + !(mode & BLK_OPEN_NDELAY)) goto error_out; /* @@ -1345,7 +1345,7 @@ static int sd_open(struct block_device *bdev, fmode_t mode) * if the user expects to be able to write to the thing. */ retval = -EROFS; - if (sdkp->write_prot && (mode & FMODE_WRITE)) + if (sdkp->write_prot && (mode & BLK_OPEN_WRITE)) goto error_out; /* @@ -1374,16 +1374,15 @@ error_out: * sd_release - invoked when the (last) close(2) is called on this * scsi disk. * @disk: disk to release - * @mode: FMODE_* mask * * Returns 0. * * Note: may block (uninterruptible) if error recovery is underway * on this disk. * - * Locking: called with bdev->bd_disk->open_mutex held. + * Locking: called with disk->open_mutex held. **/ -static void sd_release(struct gendisk *disk, fmode_t mode) +static void sd_release(struct gendisk *disk) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdev = sdkp->device; @@ -1426,7 +1425,7 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) /** * sd_ioctl - process an ioctl * @bdev: target block device - * @mode: FMODE_* mask + * @mode: open mode * @cmd: ioctl command number * @arg: this is third argument given to ioctl(2) system call. * Often contains a pointer. @@ -1437,7 +1436,7 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) * Note: most ioctls are forward onto the block subsystem or further * down in the scsi subsystem. **/ -static int sd_ioctl(struct block_device *bdev, fmode_t mode, +static int sd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; @@ -1459,13 +1458,13 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, * access to the device is prohibited. */ error = scsi_ioctl_block_when_processing_errors(sdp, cmd, - (mode & FMODE_NDELAY) != 0); + (mode & BLK_OPEN_NDELAY)); if (error) return error; if (is_sed_ioctl(cmd)) return sed_ioctl(sdkp->opal_dev, cmd, p); - return scsi_ioctl(sdp, mode, cmd, p); + return scsi_ioctl(sdp, mode & BLK_OPEN_WRITE, cmd, p); } static void set_media_not_present(struct scsi_disk *sdkp) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 037f8c98a6d3..dcb73787c29d 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -237,7 +237,7 @@ static int sg_allow_access(struct file *filp, unsigned char *cmd) if (sfp->parentdp->device->type == TYPE_SCANNER) return 0; - if (!scsi_cmd_allowed(cmd, filp->f_mode)) + if (!scsi_cmd_allowed(cmd, filp->f_mode & FMODE_WRITE)) return -EPERM; return 0; } @@ -1103,7 +1103,8 @@ sg_ioctl_common(struct file *filp, Sg_device *sdp, Sg_fd *sfp, case SCSI_IOCTL_SEND_COMMAND: if (atomic_read(&sdp->detaching)) return -ENODEV; - return scsi_ioctl(sdp->device, filp->f_mode, cmd_in, p); + return scsi_ioctl(sdp->device, filp->f_mode & FMODE_WRITE, + cmd_in, p); case SG_SET_DEBUG: result = get_user(val, ip); if (result) @@ -1159,7 +1160,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) ret = sg_ioctl_common(filp, sdp, sfp, cmd_in, p); if (ret != -ENOIOCTLCMD) return ret; - return scsi_ioctl(sdp->device, filp->f_mode, cmd_in, p); + return scsi_ioctl(sdp->device, filp->f_mode & FMODE_WRITE, cmd_in, p); } static __poll_t @@ -1496,6 +1497,10 @@ sg_add_device(struct device *cl_dev) int error; unsigned long iflags; + error = blk_get_queue(scsidp->request_queue); + if (error) + return error; + error = -ENOMEM; cdev = cdev_alloc(); if (!cdev) { @@ -1553,6 +1558,7 @@ cdev_add_err: out: if (cdev) cdev_del(cdev); + blk_put_queue(scsidp->request_queue); return error; } @@ -1560,6 +1566,7 @@ static void sg_device_destroy(struct kref *kref) { struct sg_device *sdp = container_of(kref, struct sg_device, d_ref); + struct request_queue *q = sdp->device->request_queue; unsigned long flags; /* CAUTION! Note that the device can still be found via idr_find() @@ -1567,6 +1574,9 @@ sg_device_destroy(struct kref *kref) * any other cleanup. */ + blk_trace_remove(q); + blk_put_queue(q); + write_lock_irqsave(&sg_index_lock, flags); idr_remove(&sg_index_idr, sdp->index); write_unlock_irqrestore(&sg_index_lock, flags); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 12869e6d4ebd..ce886c8c9dbe 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -484,9 +484,9 @@ static void sr_revalidate_disk(struct scsi_cd *cd) get_sectorsize(cd); } -static int sr_block_open(struct block_device *bdev, fmode_t mode) +static int sr_block_open(struct gendisk *disk, blk_mode_t mode) { - struct scsi_cd *cd = scsi_cd(bdev->bd_disk); + struct scsi_cd *cd = scsi_cd(disk); struct scsi_device *sdev = cd->device; int ret; @@ -494,11 +494,11 @@ static int sr_block_open(struct block_device *bdev, fmode_t mode) return -ENXIO; scsi_autopm_get_device(sdev); - if (bdev_check_media_change(bdev)) + if (disk_check_media_change(disk)) sr_revalidate_disk(cd); mutex_lock(&cd->lock); - ret = cdrom_open(&cd->cdi, bdev, mode); + ret = cdrom_open(&cd->cdi, mode); mutex_unlock(&cd->lock); scsi_autopm_put_device(sdev); @@ -507,19 +507,19 @@ static int sr_block_open(struct block_device *bdev, fmode_t mode) return ret; } -static void sr_block_release(struct gendisk *disk, fmode_t mode) +static void sr_block_release(struct gendisk *disk) { struct scsi_cd *cd = scsi_cd(disk); mutex_lock(&cd->lock); - cdrom_release(&cd->cdi, mode); + cdrom_release(&cd->cdi); mutex_unlock(&cd->lock); scsi_device_put(cd->device); } -static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, - unsigned long arg) +static int sr_block_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned cmd, unsigned long arg) { struct scsi_cd *cd = scsi_cd(bdev->bd_disk); struct scsi_device *sdev = cd->device; @@ -532,18 +532,18 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, mutex_lock(&cd->lock); ret = scsi_ioctl_block_when_processing_errors(sdev, cmd, - (mode & FMODE_NDELAY) != 0); + (mode & BLK_OPEN_NDELAY)); if (ret) goto out; scsi_autopm_get_device(sdev); if (cmd != CDROMCLOSETRAY && cmd != CDROMEJECT) { - ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); + ret = cdrom_ioctl(&cd->cdi, bdev, cmd, arg); if (ret != -ENOSYS) goto put; } - ret = scsi_ioctl(sdev, mode, cmd, argp); + ret = scsi_ioctl(sdev, mode & BLK_OPEN_WRITE, cmd, argp); put: scsi_autopm_put_device(sdev); diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index b90a440e135d..14d7981ddcdd 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -3832,7 +3832,7 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg) break; } - retval = scsi_ioctl(STp->device, file->f_mode, cmd_in, p); + retval = scsi_ioctl(STp->device, file->f_mode & FMODE_WRITE, cmd_in, p); if (!retval && cmd_in == SCSI_IOCTL_STOP_UNIT) { /* unload */ STp->rew_at_close = 0; diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index cc838ffd1294..3c462d69daca 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -90,7 +90,7 @@ static int iblock_configure_device(struct se_device *dev) struct request_queue *q; struct block_device *bd = NULL; struct blk_integrity *bi; - fmode_t mode; + blk_mode_t mode = BLK_OPEN_READ; unsigned int max_write_zeroes_sectors; int ret; @@ -108,13 +108,12 @@ static int iblock_configure_device(struct se_device *dev) pr_debug( "IBLOCK: Claiming struct block_device: %s\n", ib_dev->ibd_udev_path); - mode = FMODE_READ|FMODE_EXCL; if (!ib_dev->ibd_readonly) - mode |= FMODE_WRITE; + mode |= BLK_OPEN_WRITE; else dev->dev_flags |= DF_READ_ONLY; - bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev); + bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev, NULL); if (IS_ERR(bd)) { ret = PTR_ERR(bd); goto out_free_bioset; @@ -175,7 +174,7 @@ static int iblock_configure_device(struct se_device *dev) return 0; out_blkdev_put: - blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); + blkdev_put(ib_dev->ibd_bd, ib_dev); out_free_bioset: bioset_exit(&ib_dev->ibd_bio_set); out: @@ -201,7 +200,7 @@ static void iblock_destroy_device(struct se_device *dev) struct iblock_dev *ib_dev = IBLOCK_DEV(dev); if (ib_dev->ibd_bd != NULL) - blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); + blkdev_put(ib_dev->ibd_bd, ib_dev); bioset_exit(&ib_dev->ibd_bio_set); } diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index e7425549e39c..0d4f09693ef4 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -366,8 +366,8 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd) * Claim exclusive struct block_device access to struct scsi_device * for TYPE_DISK and TYPE_ZBC using supplied udev_path */ - bd = blkdev_get_by_path(dev->udev_path, - FMODE_WRITE|FMODE_READ|FMODE_EXCL, pdv); + bd = blkdev_get_by_path(dev->udev_path, BLK_OPEN_WRITE | BLK_OPEN_READ, + pdv, NULL); if (IS_ERR(bd)) { pr_err("pSCSI: blkdev_get_by_path() failed\n"); scsi_device_put(sd); @@ -377,7 +377,7 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd) ret = pscsi_add_device_to_list(dev, sd); if (ret) { - blkdev_put(pdv->pdv_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); + blkdev_put(pdv->pdv_bd, pdv); scsi_device_put(sd); return ret; } @@ -565,8 +565,7 @@ static void pscsi_destroy_device(struct se_device *dev) */ if ((sd->type == TYPE_DISK || sd->type == TYPE_ZBC) && pdv->pdv_bd) { - blkdev_put(pdv->pdv_bd, - FMODE_WRITE|FMODE_READ|FMODE_EXCL); + blkdev_put(pdv->pdv_bd, pdv); pdv->pdv_bd = NULL; } /* diff --git a/fs/Makefile b/fs/Makefile index 5bfdbf0d7037..e513aaee0603 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -17,14 +17,8 @@ obj-y := open.o read_write.o file_table.o super.o \ fs_types.o fs_context.o fs_parser.o fsopen.o init.o \ kernel_read_file.o mnt_idmapping.o remap_range.o -ifeq ($(CONFIG_BLOCK),y) -obj-y += buffer.o mpage.o -else -obj-y += no-block.o -endif - -obj-$(CONFIG_PROC_FS) += proc_namespace.o - +obj-$(CONFIG_BLOCK) += buffer.o mpage.o +obj-$(CONFIG_PROC_FS) += proc_namespace.o obj-$(CONFIG_LEGACY_DIRECT_IO) += direct-io.o obj-y += notify/ obj-$(CONFIG_EPOLL) += eventpoll.o diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 5e86bea0a950..5f10965fd72b 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -257,8 +257,8 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return -EINVAL; } - bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL, - fs_info->bdev_holder); + bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE, + fs_info->bdev_holder, NULL); if (IS_ERR(bdev)) { btrfs_err(fs_info, "target device %s is invalid!", device_path); return PTR_ERR(bdev); @@ -315,7 +315,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, device->bdev = bdev; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); - device->mode = FMODE_EXCL; + device->holder = fs_info->bdev_holder; device->dev_stats_valid = 1; set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_devices; @@ -334,7 +334,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return 0; error: - blkdev_put(bdev, FMODE_EXCL); + blkdev_put(bdev, fs_info->bdev_holder); return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index edbbd5cf23fc..a895d105464b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2671,7 +2671,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ioctl_vol_args_v2 *vol_args; struct block_device *bdev = NULL; - fmode_t mode; + void *holder; int ret; bool cancel = false; @@ -2708,7 +2708,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) goto err_drop; /* Exclusive operation is now claimed */ - ret = btrfs_rm_device(fs_info, &args, &bdev, &mode); + ret = btrfs_rm_device(fs_info, &args, &bdev, &holder); btrfs_exclop_finish(fs_info); @@ -2723,7 +2723,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) err_drop: mnt_drop_write_file(file); if (bdev) - blkdev_put(bdev, mode); + blkdev_put(bdev, holder); out: btrfs_put_dev_args_from_path(&args); kfree(vol_args); @@ -2737,7 +2737,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ioctl_vol_args *vol_args; struct block_device *bdev = NULL; - fmode_t mode; + void *holder; int ret; bool cancel = false; @@ -2764,7 +2764,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE, cancel); if (ret == 0) { - ret = btrfs_rm_device(fs_info, &args, &bdev, &mode); + ret = btrfs_rm_device(fs_info, &args, &bdev, &holder); if (!ret) btrfs_info(fs_info, "disk deleted %s", vol_args->name); btrfs_exclop_finish(fs_info); @@ -2772,7 +2772,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) mnt_drop_write_file(file); if (bdev) - blkdev_put(bdev, mode); + blkdev_put(bdev, holder); out: btrfs_put_dev_args_from_path(&args); kfree(vol_args); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8b1c1225245e..f1dd172d8d5b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -849,8 +849,7 @@ out: * All other options will be parsed on much later in the mount process and * only when we need to allocate a new super block. */ -static int btrfs_parse_device_options(const char *options, fmode_t flags, - void *holder) +static int btrfs_parse_device_options(const char *options, blk_mode_t flags) { substring_t args[MAX_OPT_ARGS]; char *device_name, *opts, *orig, *p; @@ -884,8 +883,7 @@ static int btrfs_parse_device_options(const char *options, fmode_t flags, error = -ENOMEM; goto out; } - device = btrfs_scan_one_device(device_name, flags, - holder); + device = btrfs_scan_one_device(device_name, flags); kfree(device_name); if (IS_ERR(device)) { error = PTR_ERR(device); @@ -1442,12 +1440,9 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, struct btrfs_fs_devices *fs_devices = NULL; struct btrfs_fs_info *fs_info = NULL; void *new_sec_opts = NULL; - fmode_t mode = FMODE_READ; + blk_mode_t mode = sb_open_mode(flags); int error = 0; - if (!(flags & SB_RDONLY)) - mode |= FMODE_WRITE; - if (data) { error = security_sb_eat_lsm_opts(data, &new_sec_opts); if (error) @@ -1477,13 +1472,13 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, } mutex_lock(&uuid_mutex); - error = btrfs_parse_device_options(data, mode, fs_type); + error = btrfs_parse_device_options(data, mode); if (error) { mutex_unlock(&uuid_mutex); goto error_fs_info; } - device = btrfs_scan_one_device(device_name, mode, fs_type); + device = btrfs_scan_one_device(device_name, mode); if (IS_ERR(device)) { mutex_unlock(&uuid_mutex); error = PTR_ERR(device); @@ -2195,8 +2190,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case BTRFS_IOC_SCAN_DEV: mutex_lock(&uuid_mutex); - device = btrfs_scan_one_device(vol->name, FMODE_READ, - &btrfs_root_fs_type); + device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ); ret = PTR_ERR_OR_ZERO(device); mutex_unlock(&uuid_mutex); break; @@ -2210,8 +2204,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, break; case BTRFS_IOC_DEVICES_READY: mutex_lock(&uuid_mutex); - device = btrfs_scan_one_device(vol->name, FMODE_READ, - &btrfs_root_fs_type); + device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ); if (IS_ERR(device)) { mutex_unlock(&uuid_mutex); ret = PTR_ERR(device); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 4193ace3fb5a..73f9ea7672db 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -510,13 +510,13 @@ static struct btrfs_fs_devices *find_fsid_with_metadata_uuid( static int -btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder, +btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder, int flush, struct block_device **bdev, struct btrfs_super_block **disk_super) { int ret; - *bdev = blkdev_get_by_path(device_path, flags, holder); + *bdev = blkdev_get_by_path(device_path, flags, holder, NULL); if (IS_ERR(*bdev)) { ret = PTR_ERR(*bdev); @@ -527,14 +527,14 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder, sync_blockdev(*bdev); ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE); if (ret) { - blkdev_put(*bdev, flags); + blkdev_put(*bdev, holder); goto error; } invalidate_bdev(*bdev); *disk_super = btrfs_read_dev_super(*bdev); if (IS_ERR(*disk_super)) { ret = PTR_ERR(*disk_super); - blkdev_put(*bdev, flags); + blkdev_put(*bdev, holder); goto error; } @@ -610,7 +610,7 @@ static int btrfs_free_stale_devices(dev_t devt, struct btrfs_device *skip_device * fs_devices->device_list_mutex here. */ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, - struct btrfs_device *device, fmode_t flags, + struct btrfs_device *device, blk_mode_t flags, void *holder) { struct block_device *bdev; @@ -662,7 +662,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, device->bdev = bdev; clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); - device->mode = flags; + device->holder = holder; fs_devices->open_devices++; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && @@ -676,7 +676,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, error_free_page: btrfs_release_disk_super(disk_super); - blkdev_put(bdev, flags); + blkdev_put(bdev, holder); return -EINVAL; } @@ -1067,7 +1067,7 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, continue; if (device->bdev) { - blkdev_put(device->bdev, device->mode); + blkdev_put(device->bdev, device->holder); device->bdev = NULL; fs_devices->open_devices--; } @@ -1113,7 +1113,7 @@ static void btrfs_close_bdev(struct btrfs_device *device) invalidate_bdev(device->bdev); } - blkdev_put(device->bdev, device->mode); + blkdev_put(device->bdev, device->holder); } static void btrfs_close_one_device(struct btrfs_device *device) @@ -1217,14 +1217,12 @@ void btrfs_close_devices(struct btrfs_fs_devices *fs_devices) } static int open_fs_devices(struct btrfs_fs_devices *fs_devices, - fmode_t flags, void *holder) + blk_mode_t flags, void *holder) { struct btrfs_device *device; struct btrfs_device *latest_dev = NULL; struct btrfs_device *tmp_device; - flags |= FMODE_EXCL; - list_for_each_entry_safe(device, tmp_device, &fs_devices->devices, dev_list) { int ret; @@ -1267,7 +1265,7 @@ static int devid_cmp(void *priv, const struct list_head *a, } int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, - fmode_t flags, void *holder) + blk_mode_t flags, void *holder) { int ret; @@ -1358,8 +1356,7 @@ int btrfs_forget_devices(dev_t devt) * and we are not allowed to call set_blocksize during the scan. The superblock * is read via pagecache */ -struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, - void *holder) +struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags) { struct btrfs_super_block *disk_super; bool new_device_added = false; @@ -1378,16 +1375,16 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, */ /* - * Avoid using flag |= FMODE_EXCL here, as the systemd-udev may - * initiate the device scan which may race with the user's mount - * or mkfs command, resulting in failure. - * Since the device scan is solely for reading purposes, there is - * no need for FMODE_EXCL. Additionally, the devices are read again + * Avoid an exclusive open here, as the systemd-udev may initiate the + * device scan which may race with the user's mount or mkfs command, + * resulting in failure. + * Since the device scan is solely for reading purposes, there is no + * need for an exclusive open. Additionally, the devices are read again * during the mount process. It is ok to get some inconsistent * values temporarily, as the device paths of the fsid are the only * required information for assembling the volume. */ - bdev = blkdev_get_by_path(path, flags, holder); + bdev = blkdev_get_by_path(path, flags, NULL, NULL); if (IS_ERR(bdev)) return ERR_CAST(bdev); @@ -1411,7 +1408,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, btrfs_release_disk_super(disk_super); error_bdev_put: - blkdev_put(bdev, flags); + blkdev_put(bdev, NULL); return device; } @@ -2098,7 +2095,7 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, - struct block_device **bdev, fmode_t *mode) + struct block_device **bdev, void **holder) { struct btrfs_trans_handle *trans; struct btrfs_device *device; @@ -2237,7 +2234,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, } *bdev = device->bdev; - *mode = device->mode; + *holder = device->holder; synchronize_rcu(); btrfs_free_device(device); @@ -2391,7 +2388,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, return -ENOMEM; } - ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0, + ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0, &bdev, &disk_super); if (ret) { btrfs_put_dev_args_from_path(args); @@ -2405,7 +2402,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info, else memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE); btrfs_release_disk_super(disk_super); - blkdev_put(bdev, FMODE_READ); + blkdev_put(bdev, NULL); return 0; } @@ -2638,8 +2635,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path if (sb_rdonly(sb) && !fs_devices->seeding) return -EROFS; - bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL, - fs_info->bdev_holder); + bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE, + fs_info->bdev_holder, NULL); if (IS_ERR(bdev)) return PTR_ERR(bdev); @@ -2701,7 +2698,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path device->commit_total_bytes = device->total_bytes; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state); - device->mode = FMODE_EXCL; + device->holder = fs_info->bdev_holder; device->dev_stats_valid = 1; set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); @@ -2859,7 +2856,7 @@ error_free_zone: error_free_device: btrfs_free_device(device); error: - blkdev_put(bdev, FMODE_EXCL); + blkdev_put(bdev, fs_info->bdev_holder); if (locked) { mutex_unlock(&uuid_mutex); up_write(&sb->s_umount); @@ -6898,7 +6895,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info, if (IS_ERR(fs_devices)) return fs_devices; - ret = open_fs_devices(fs_devices, FMODE_READ, fs_info->bdev_holder); + ret = open_fs_devices(fs_devices, BLK_OPEN_READ, fs_info->bdev_holder); if (ret) { free_fs_devices(fs_devices); return ERR_PTR(ret); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index d44cb9d22d63..b8c51f16ba86 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -94,8 +94,8 @@ struct btrfs_device { struct btrfs_zoned_device_info *zone_info; - /* the mode sent to blkdev_get */ - fmode_t mode; + /* block device holder for blkdev_get/put */ + void *holder; /* * Device's major-minor number. Must be set even if the device is not @@ -610,9 +610,8 @@ struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans, u64 type); void btrfs_mapping_tree_free(struct extent_map_tree *tree); int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, - fmode_t flags, void *holder); -struct btrfs_device *btrfs_scan_one_device(const char *path, - fmode_t flags, void *holder); + blk_mode_t flags, void *holder); +struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags); int btrfs_forget_devices(dev_t devt); void btrfs_close_devices(struct btrfs_fs_devices *fs_devices); void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices); @@ -630,7 +629,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args); int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, - struct block_device **bdev, fmode_t *mode); + struct block_device **bdev, void **holder); void __exit btrfs_cleanup_fs_uuids(void); int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len); int btrfs_grow_device(struct btrfs_trans_handle *trans, diff --git a/fs/buffer.c b/fs/buffer.c index fe64356e89b8..93c7446d9221 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2759,8 +2759,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); - BUG_ON(bio->bi_iter.bi_size != bh->b_size); + __bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; diff --git a/fs/direct-io.c b/fs/direct-io.c index 0b380bb8a81e..2ceb378b93c0 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -42,8 +42,8 @@ #include "internal.h" /* - * How many user pages to map in one call to get_user_pages(). This determines - * the size of a structure in the slab cache + * How many user pages to map in one call to iov_iter_extract_pages(). This + * determines the size of a structure in the slab cache */ #define DIO_PAGES 64 @@ -121,12 +121,13 @@ struct dio { struct inode *inode; loff_t i_size; /* i_size when submitted */ dio_iodone_t *end_io; /* IO completion function */ + bool is_pinned; /* T if we have pins on the pages */ void *private; /* copy from map_bh.b_private */ /* BIO completion state */ spinlock_t bio_lock; /* protects BIO fields below */ - int page_errors; /* errno from get_user_pages() */ + int page_errors; /* err from iov_iter_extract_pages() */ int is_async; /* is IO async ? */ bool defer_completion; /* defer AIO completion to workqueue? */ bool should_dirty; /* if pages should be dirtied */ @@ -165,14 +166,14 @@ static inline unsigned dio_pages_present(struct dio_submit *sdio) */ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) { + struct page **pages = dio->pages; const enum req_op dio_op = dio->opf & REQ_OP_MASK; ssize_t ret; - ret = iov_iter_get_pages2(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES, - &sdio->from); + ret = iov_iter_extract_pages(sdio->iter, &pages, LONG_MAX, + DIO_PAGES, 0, &sdio->from); if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) { - struct page *page = ZERO_PAGE(0); /* * A memory fault, but the filesystem has some outstanding * mapped blocks. We need to use those blocks up to avoid @@ -180,8 +181,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) */ if (dio->page_errors == 0) dio->page_errors = ret; - get_page(page); - dio->pages[0] = page; + dio->pages[0] = ZERO_PAGE(0); sdio->head = 0; sdio->tail = 1; sdio->from = 0; @@ -201,9 +201,9 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) /* * Get another userspace page. Returns an ERR_PTR on error. Pages are - * buffered inside the dio so that we can call get_user_pages() against a - * decent number of pages, less frequently. To provide nicer use of the - * L1 cache. + * buffered inside the dio so that we can call iov_iter_extract_pages() + * against a decent number of pages, less frequently. To provide nicer use of + * the L1 cache. */ static inline struct page *dio_get_page(struct dio *dio, struct dio_submit *sdio) @@ -219,6 +219,18 @@ static inline struct page *dio_get_page(struct dio *dio, return dio->pages[sdio->head]; } +static void dio_pin_page(struct dio *dio, struct page *page) +{ + if (dio->is_pinned) + folio_add_pin(page_folio(page)); +} + +static void dio_unpin_page(struct dio *dio, struct page *page) +{ + if (dio->is_pinned) + unpin_user_page(page); +} + /* * dio_complete() - called when all DIO BIO I/O has been completed * @@ -402,6 +414,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, bio->bi_end_io = dio_bio_end_aio; else bio->bi_end_io = dio_bio_end_io; + if (dio->is_pinned) + bio_set_flag(bio, BIO_PAGE_PINNED); sdio->bio = bio; sdio->logical_offset_in_bio = sdio->cur_page_fs_offset; } @@ -442,8 +456,10 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) */ static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio) { - while (sdio->head < sdio->tail) - put_page(dio->pages[sdio->head++]); + if (dio->is_pinned) + unpin_user_pages(dio->pages + sdio->head, + sdio->tail - sdio->head); + sdio->head = sdio->tail; } /* @@ -674,7 +690,7 @@ out: * * Return zero on success. Non-zero means the caller needs to start a new BIO. */ -static inline int dio_bio_add_page(struct dio_submit *sdio) +static inline int dio_bio_add_page(struct dio *dio, struct dio_submit *sdio) { int ret; @@ -686,7 +702,7 @@ static inline int dio_bio_add_page(struct dio_submit *sdio) */ if ((sdio->cur_page_len + sdio->cur_page_offset) == PAGE_SIZE) sdio->pages_in_io--; - get_page(sdio->cur_page); + dio_pin_page(dio, sdio->cur_page); sdio->final_block_in_bio = sdio->cur_page_block + (sdio->cur_page_len >> sdio->blkbits); ret = 0; @@ -741,11 +757,11 @@ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio, goto out; } - if (dio_bio_add_page(sdio) != 0) { + if (dio_bio_add_page(dio, sdio) != 0) { dio_bio_submit(dio, sdio); ret = dio_new_bio(dio, sdio, sdio->cur_page_block, map_bh); if (ret == 0) { - ret = dio_bio_add_page(sdio); + ret = dio_bio_add_page(dio, sdio); BUG_ON(ret != 0); } } @@ -802,13 +818,13 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, */ if (sdio->cur_page) { ret = dio_send_cur_page(dio, sdio, map_bh); - put_page(sdio->cur_page); + dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; if (ret) return ret; } - get_page(page); /* It is in dio */ + dio_pin_page(dio, page); /* It is in dio */ sdio->cur_page = page; sdio->cur_page_offset = offset; sdio->cur_page_len = len; @@ -823,7 +839,7 @@ out: ret = dio_send_cur_page(dio, sdio, map_bh); if (sdio->bio) dio_bio_submit(dio, sdio); - put_page(sdio->cur_page); + dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; } return ret; @@ -924,7 +940,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio, ret = get_more_blocks(dio, sdio, map_bh); if (ret) { - put_page(page); + dio_unpin_page(dio, page); goto out; } if (!buffer_mapped(map_bh)) @@ -969,7 +985,7 @@ do_holes: /* AKPM: eargh, -ENOTBLK is a hack */ if (dio_op == REQ_OP_WRITE) { - put_page(page); + dio_unpin_page(dio, page); return -ENOTBLK; } @@ -982,7 +998,7 @@ do_holes: if (sdio->block_in_file >= i_size_aligned >> blkbits) { /* We hit eof */ - put_page(page); + dio_unpin_page(dio, page); goto out; } zero_user(page, from, 1 << blkbits); @@ -1022,7 +1038,7 @@ do_holes: sdio->next_block_for_io, map_bh); if (ret) { - put_page(page); + dio_unpin_page(dio, page); goto out; } sdio->next_block_for_io += this_chunk_blocks; @@ -1037,8 +1053,8 @@ next_block: break; } - /* Drop the ref which was taken in get_user_pages() */ - put_page(page); + /* Drop the pin which was taken in get_user_pages() */ + dio_unpin_page(dio, page); } out: return ret; @@ -1133,6 +1149,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, /* will be released by direct_io_worker */ inode_lock(inode); } + dio->is_pinned = iov_iter_extract_will_pin(iter); /* Once we sampled i_size check for reads beyond EOF */ dio->i_size = i_size_read(inode); @@ -1257,7 +1274,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, ret2 = dio_send_cur_page(dio, &sdio, &map_bh); if (retval == 0) retval = ret2; - put_page(sdio.cur_page); + dio_unpin_page(dio, sdio.cur_page); sdio.cur_page = NULL; } if (sdio.bio) diff --git a/fs/erofs/super.c b/fs/erofs/super.c index ff18f6b14de5..9d6a3c6158bd 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -19,6 +19,7 @@ #include <trace/events/erofs.h> static struct kmem_cache *erofs_inode_cachep __read_mostly; +struct file_system_type erofs_fs_type; void _erofs_err(struct super_block *sb, const char *function, const char *fmt, ...) @@ -253,8 +254,8 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, return PTR_ERR(fscache); dif->fscache = fscache; } else if (!sbi->devs->flatdev) { - bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL, - sb->s_type); + bdev = blkdev_get_by_path(dif->path, BLK_OPEN_READ, sb->s_type, + NULL); if (IS_ERR(bdev)) return PTR_ERR(bdev); dif->bdev = bdev; @@ -815,7 +816,7 @@ static int erofs_release_device_info(int id, void *ptr, void *data) fs_put_dax(dif->dax_dev, NULL); if (dif->bdev) - blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL); + blkdev_put(dif->bdev, &erofs_fs_type); erofs_fscache_unregister_cookie(dif->fscache); dif->fscache = NULL; kfree(dif->path); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 8104a21b001a..02fa8a64dc3f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2968,6 +2968,7 @@ int ext4_fileattr_set(struct mnt_idmap *idmap, int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); int ext4_update_overhead(struct super_block *sb, bool force); +int ext4_force_shutdown(struct super_block *sb, u32 flags); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index f9a430152063..961284cc9b65 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -793,16 +793,9 @@ static int ext4_ioctl_setproject(struct inode *inode, __u32 projid) } #endif -static int ext4_shutdown(struct super_block *sb, unsigned long arg) +int ext4_force_shutdown(struct super_block *sb, u32 flags) { struct ext4_sb_info *sbi = EXT4_SB(sb); - __u32 flags; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (get_user(flags, (__u32 __user *)arg)) - return -EFAULT; if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH) return -EINVAL; @@ -838,6 +831,19 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg) return 0; } +static int ext4_ioctl_shutdown(struct super_block *sb, unsigned long arg) +{ + u32 flags; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (get_user(flags, (__u32 __user *)arg)) + return -EFAULT; + + return ext4_force_shutdown(sb, flags); +} + struct getfsmap_info { struct super_block *gi_sb; struct fsmap_head __user *gi_data; @@ -1566,7 +1572,7 @@ resizefs_out: return ext4_ioctl_get_es_cache(filp, arg); case EXT4_IOC_SHUTDOWN: - return ext4_shutdown(sb, arg); + return ext4_ioctl_shutdown(sb, arg); case FS_IOC_ENABLE_VERITY: if (!ext4_has_feature_verity(sb)) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 05fcecc36244..eaa5858d5285 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1096,6 +1096,15 @@ void ext4_update_dynamic_rev(struct super_block *sb) */ } +static void ext4_bdev_mark_dead(struct block_device *bdev) +{ + ext4_force_shutdown(bdev->bd_holder, EXT4_GOING_FLAGS_NOLOGFLUSH); +} + +static const struct blk_holder_ops ext4_holder_ops = { + .mark_dead = ext4_bdev_mark_dead, +}; + /* * Open the external journal device */ @@ -1103,7 +1112,8 @@ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb) { struct block_device *bdev; - bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb); + bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb, + &ext4_holder_ops); if (IS_ERR(bdev)) goto fail; return bdev; @@ -1118,17 +1128,12 @@ fail: /* * Release the journal device */ -static void ext4_blkdev_put(struct block_device *bdev) -{ - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); -} - static void ext4_blkdev_remove(struct ext4_sb_info *sbi) { struct block_device *bdev; bdev = sbi->s_journal_bdev; if (bdev) { - ext4_blkdev_put(bdev); + blkdev_put(bdev, sbi->s_sb); sbi->s_journal_bdev = NULL; } } @@ -1449,6 +1454,11 @@ static void ext4_destroy_inode(struct inode *inode) EXT4_I(inode)->i_reserved_data_blocks); } +static void ext4_shutdown(struct super_block *sb) +{ + ext4_force_shutdown(sb, EXT4_GOING_FLAGS_NOLOGFLUSH); +} + static void init_once(void *foo) { struct ext4_inode_info *ei = foo; @@ -1609,6 +1619,7 @@ static const struct super_operations ext4_sops = { .unfreeze_fs = ext4_unfreeze, .statfs = ext4_statfs, .show_options = ext4_show_options, + .shutdown = ext4_shutdown, #ifdef CONFIG_QUOTA .quota_read = ext4_quota_read, .quota_write = ext4_quota_write, @@ -5899,7 +5910,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, out_journal: jbd2_journal_destroy(journal); out_bdev: - ext4_blkdev_put(bdev); + blkdev_put(bdev, sb); return NULL; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 9f15b03037db..e34197a70dc1 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1538,7 +1538,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) int i; for (i = 0; i < sbi->s_ndevs; i++) { - blkdev_put(FDEV(i).bdev, FMODE_EXCL); + blkdev_put(FDEV(i).bdev, sbi->sb->s_type); #ifdef CONFIG_BLK_DEV_ZONED kvfree(FDEV(i).blkz_seq); #endif @@ -3993,6 +3993,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); unsigned int max_devices = MAX_DEVICES; unsigned int logical_blksize; + blk_mode_t mode = sb_open_mode(sbi->sb->s_flags); int i; /* Initialize single device information */ @@ -4024,8 +4025,8 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) if (max_devices == 1) { /* Single zoned block device mount */ FDEV(0).bdev = - blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev, - sbi->sb->s_mode, sbi->sb->s_type); + blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev, mode, + sbi->sb->s_type, NULL); } else { /* Multi-device mount */ memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN); @@ -4043,8 +4044,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) (FDEV(i).total_segments << sbi->log_blocks_per_seg) - 1; } - FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path, - sbi->sb->s_mode, sbi->sb->s_type); + FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path, mode, + sbi->sb->s_type, + NULL); } if (IS_ERR(FDEV(i).bdev)) return PTR_ERR(FDEV(i).bdev); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 9af9ddb61ca0..cd962985b058 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -254,7 +254,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent) bio = bio_alloc(sb->s_bdev, 1, REQ_OP_READ | REQ_META, GFP_NOFS); bio->bi_iter.bi_sector = sector * (sb->s_blocksize >> 9); - bio_add_page(bio, page, PAGE_SIZE, 0); + __bio_add_page(bio, page, PAGE_SIZE, 0); bio->bi_end_io = end_bio_io_page; bio->bi_private = page; diff --git a/fs/inode.c b/fs/inode.c index 53ae3b76d232..d37fad91c8da 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2306,7 +2306,8 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; } else if (S_ISBLK(mode)) { - inode->i_fop = &def_blk_fops; + if (IS_ENABLED(CONFIG_BLOCK)) + inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; } else if (S_ISFIFO(mode)) inode->i_fop = &pipefifo_fops; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 063133ec77f4..0edab9deae2a 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -312,7 +312,7 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter, ctx->bio->bi_opf |= REQ_RAHEAD; ctx->bio->bi_iter.bi_sector = sector; ctx->bio->bi_end_io = iomap_read_end_io; - bio_add_folio(ctx->bio, folio, plen, poff); + bio_add_folio_nofail(ctx->bio, folio, plen, poff); } done: @@ -539,7 +539,7 @@ static int iomap_read_folio_sync(loff_t block_start, struct folio *folio, bio_init(&bio, iomap->bdev, &bvec, 1, REQ_OP_READ); bio.bi_iter.bi_sector = iomap_sector(iomap, block_start); - bio_add_folio(&bio, folio, plen, poff); + bio_add_folio_nofail(&bio, folio, plen, poff); return submit_bio_wait(&bio); } @@ -1582,7 +1582,7 @@ iomap_add_to_ioend(struct inode *inode, loff_t pos, struct folio *folio, if (!bio_add_folio(wpc->ioend->io_bio, folio, len, poff)) { wpc->ioend->io_bio = iomap_chain_bio(wpc->ioend->io_bio); - bio_add_folio(wpc->ioend->io_bio, folio, len, poff); + bio_add_folio_nofail(wpc->ioend->io_bio, folio, len, poff); } if (iop) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 019cc87d0fb3..08873f0627dd 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -203,7 +203,6 @@ static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; - get_page(page); __bio_add_page(bio, page, len, 0); iomap_dio_submit_bio(iter, dio, bio, pos); } diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 695415cbfe98..e855b8fde76c 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1100,8 +1100,8 @@ int lmLogOpen(struct super_block *sb) * file systems to log may have n-to-1 relationship; */ - bdev = blkdev_get_by_dev(sbi->logdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, - log); + bdev = blkdev_get_by_dev(sbi->logdev, BLK_OPEN_READ | BLK_OPEN_WRITE, + log, NULL); if (IS_ERR(bdev)) { rc = PTR_ERR(bdev); goto free; @@ -1141,7 +1141,7 @@ journal_found: lbmLogShutdown(log); close: /* close external log device */ - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, log); free: /* free log descriptor */ mutex_unlock(&jfs_log_mutex); @@ -1485,7 +1485,7 @@ int lmLogClose(struct super_block *sb) bdev = log->bdev; rc = lmLogShutdown(log); - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, log); kfree(log); @@ -1974,7 +1974,7 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp) bio = bio_alloc(log->bdev, 1, REQ_OP_READ, GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); - bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); + __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); bio->bi_end_io = lbmIODone; @@ -2115,7 +2115,7 @@ static void lbmStartIO(struct lbuf * bp) bio = bio_alloc(log->bdev, 1, REQ_OP_WRITE | REQ_SYNC, GFP_NOFS); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); - bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); + __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); bio->bi_end_io = lbmIODone; diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index fea5f8821da5..70f5563a8e81 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -35,7 +35,7 @@ bl_free_device(struct pnfs_block_dev *dev) } if (dev->bdev) - blkdev_put(dev->bdev, FMODE_READ | FMODE_WRITE); + blkdev_put(dev->bdev, NULL); } } @@ -243,7 +243,8 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d, if (!dev) return -EIO; - bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_WRITE, NULL); + bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, + NULL); if (IS_ERR(bdev)) { printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n", MAJOR(dev), MINOR(dev), PTR_ERR(bdev)); @@ -312,7 +313,8 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix) if (!devname) return ERR_PTR(-ENOMEM); - bdev = blkdev_get_by_path(devname, FMODE_READ | FMODE_WRITE, NULL); + bdev = blkdev_get_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, + NULL); if (IS_ERR(bdev)) { pr_warn("pNFS: failed to open device %s (%ld)\n", devname, PTR_ERR(bdev)); @@ -373,7 +375,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, return 0; out_blkdev_put: - blkdev_put(d->bdev, FMODE_READ | FMODE_WRITE); + blkdev_put(d->bdev, NULL); return error; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 9ba4933087af..0ef8c71bde8e 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1299,14 +1299,11 @@ nilfs_mount(struct file_system_type *fs_type, int flags, { struct nilfs_super_data sd; struct super_block *s; - fmode_t mode = FMODE_READ | FMODE_EXCL; struct dentry *root_dentry; int err, s_new = false; - if (!(flags & SB_RDONLY)) - mode |= FMODE_WRITE; - - sd.bdev = blkdev_get_by_path(dev_name, mode, fs_type); + sd.bdev = blkdev_get_by_path(dev_name, sb_open_mode(flags), fs_type, + NULL); if (IS_ERR(sd.bdev)) return ERR_CAST(sd.bdev); @@ -1340,7 +1337,6 @@ nilfs_mount(struct file_system_type *fs_type, int flags, s_new = true; /* New superblock instance created */ - s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev); sb_set_blocksize(s, block_size(sd.bdev)); @@ -1378,7 +1374,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, } if (!s_new) - blkdev_put(sd.bdev, mode); + blkdev_put(sd.bdev, fs_type); return root_dentry; @@ -1387,7 +1383,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, failed: if (!s_new) - blkdev_put(sd.bdev, mode); + blkdev_put(sd.bdev, fs_type); return ERR_PTR(err); } diff --git a/fs/no-block.c b/fs/no-block.c deleted file mode 100644 index 481c0f0ab4bd..000000000000 --- a/fs/no-block.c +++ /dev/null @@ -1,19 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* no-block.c: implementation of routines required for non-BLOCK configuration - * - * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/kernel.h> -#include <linux/fs.h> - -static int no_blkdev_open(struct inode * inode, struct file * filp) -{ - return -ENODEV; -} - -const struct file_operations def_blk_fops = { - .open = no_blkdev_open, - .llseek = noop_llseek, -}; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 60b97c92e2b2..21472e3ed182 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1503,7 +1503,7 @@ static void o2hb_region_release(struct config_item *item) } if (reg->hr_bdev) - blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE); + blkdev_put(reg->hr_bdev, NULL); kfree(reg->hr_slots); @@ -1786,7 +1786,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, goto out2; reg->hr_bdev = blkdev_get_by_dev(f.file->f_mapping->host->i_rdev, - FMODE_WRITE | FMODE_READ, NULL); + BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, + NULL); if (IS_ERR(reg->hr_bdev)) { ret = PTR_ERR(reg->hr_bdev); reg->hr_bdev = NULL; @@ -1893,7 +1894,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item, out3: if (ret < 0) { - blkdev_put(reg->hr_bdev, FMODE_READ | FMODE_WRITE); + blkdev_put(reg->hr_bdev, NULL); reg->hr_bdev = NULL; } out2: diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c index 4ae0cfcd15f2..de8cf5d75f34 100644 --- a/fs/pstore/blk.c +++ b/fs/pstore/blk.c @@ -263,9 +263,9 @@ static __init const char *early_boot_devpath(const char *initial_devname) * same scheme to find the device that we use for mounting * the root file system. */ - dev_t dev = name_to_dev_t(initial_devname); + dev_t dev; - if (!dev) { + if (early_lookup_bdev(initial_devname, &dev)) { pr_err("failed to resolve '%s'!\n", initial_devname); return initial_devname; } diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 4d11d60f493c..479aa4a57602 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2589,7 +2589,12 @@ static void release_journal_dev(struct super_block *super, struct reiserfs_journal *journal) { if (journal->j_dev_bd != NULL) { - blkdev_put(journal->j_dev_bd, journal->j_dev_mode); + void *holder = NULL; + + if (journal->j_dev_bd->bd_dev != super->s_dev) + holder = journal; + + blkdev_put(journal->j_dev_bd, holder); journal->j_dev_bd = NULL; } } @@ -2598,9 +2603,10 @@ static int journal_init_dev(struct super_block *super, struct reiserfs_journal *journal, const char *jdev_name) { + blk_mode_t blkdev_mode = BLK_OPEN_READ; + void *holder = journal; int result; dev_t jdev; - fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL; result = 0; @@ -2608,16 +2614,15 @@ static int journal_init_dev(struct super_block *super, jdev = SB_ONDISK_JOURNAL_DEVICE(super) ? new_decode_dev(SB_ONDISK_JOURNAL_DEVICE(super)) : super->s_dev; - if (bdev_read_only(super->s_bdev)) - blkdev_mode = FMODE_READ; + if (!bdev_read_only(super->s_bdev)) + blkdev_mode |= BLK_OPEN_WRITE; /* there is no "jdev" option and journal is on separate device */ if ((!jdev_name || !jdev_name[0])) { if (jdev == super->s_dev) - blkdev_mode &= ~FMODE_EXCL; - journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode, - journal); - journal->j_dev_mode = blkdev_mode; + holder = NULL; + journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode, holder, + NULL); if (IS_ERR(journal->j_dev_bd)) { result = PTR_ERR(journal->j_dev_bd); journal->j_dev_bd = NULL; @@ -2631,8 +2636,8 @@ static int journal_init_dev(struct super_block *super, return 0; } - journal->j_dev_mode = blkdev_mode; - journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, journal); + journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, holder, + NULL); if (IS_ERR(journal->j_dev_bd)) { result = PTR_ERR(journal->j_dev_bd); journal->j_dev_bd = NULL; diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 1bccf6a2e908..55e85256aae8 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -300,7 +300,6 @@ struct reiserfs_journal { struct reiserfs_journal_cnode *j_first; struct block_device *j_dev_bd; - fmode_t j_dev_mode; /* first block on s_dev of reserved area journal */ int j_1st_reserved_block; diff --git a/fs/splice.c b/fs/splice.c index 2420ead610a7..7a9565d8ec4f 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -368,16 +368,15 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos, if (ret > 0) { keep = DIV_ROUND_UP(ret, PAGE_SIZE); *ppos = kiocb.ki_pos; - file_accessed(in); - } else if (ret < 0) { - /* - * callers of ->splice_read() expect -EAGAIN on - * "can't put anything in there", rather than -EFAULT. - */ - if (ret == -EFAULT) - ret = -EAGAIN; } + /* + * Callers of ->splice_read() expect -EAGAIN on "can't put anything in + * there", rather than -EFAULT. + */ + if (ret == -EFAULT) + ret = -EAGAIN; + /* Free any pages that didn't get touched at all. */ if (keep < npages) release_pages(pages + keep, npages - keep); diff --git a/fs/super.c b/fs/super.c index 48c29954d487..05ff6abddd3c 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1210,6 +1210,22 @@ int get_tree_keyed(struct fs_context *fc, EXPORT_SYMBOL(get_tree_keyed); #ifdef CONFIG_BLOCK +static void fs_mark_dead(struct block_device *bdev) +{ + struct super_block *sb; + + sb = get_super(bdev); + if (!sb) + return; + + if (sb->s_op->shutdown) + sb->s_op->shutdown(sb); + drop_super(sb); +} + +static const struct blk_holder_ops fs_holder_ops = { + .mark_dead = fs_mark_dead, +}; static int set_bdev_super(struct super_block *s, void *data) { @@ -1243,16 +1259,13 @@ int get_tree_bdev(struct fs_context *fc, { struct block_device *bdev; struct super_block *s; - fmode_t mode = FMODE_READ | FMODE_EXCL; int error = 0; - if (!(fc->sb_flags & SB_RDONLY)) - mode |= FMODE_WRITE; - if (!fc->source) return invalf(fc, "No source specified"); - bdev = blkdev_get_by_path(fc->source, mode, fc->fs_type); + bdev = blkdev_get_by_path(fc->source, sb_open_mode(fc->sb_flags), + fc->fs_type, &fs_holder_ops); if (IS_ERR(bdev)) { errorf(fc, "%s: Can't open blockdev", fc->source); return PTR_ERR(bdev); @@ -1266,7 +1279,7 @@ int get_tree_bdev(struct fs_context *fc, if (bdev->bd_fsfreeze_count > 0) { mutex_unlock(&bdev->bd_fsfreeze_mutex); warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); - blkdev_put(bdev, mode); + blkdev_put(bdev, fc->fs_type); return -EBUSY; } @@ -1275,7 +1288,7 @@ int get_tree_bdev(struct fs_context *fc, s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc); mutex_unlock(&bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) { - blkdev_put(bdev, mode); + blkdev_put(bdev, fc->fs_type); return PTR_ERR(s); } @@ -1284,7 +1297,7 @@ int get_tree_bdev(struct fs_context *fc, if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) { warnf(fc, "%pg: Can't mount, would change RO state", bdev); deactivate_locked_super(s); - blkdev_put(bdev, mode); + blkdev_put(bdev, fc->fs_type); return -EBUSY; } @@ -1296,10 +1309,9 @@ int get_tree_bdev(struct fs_context *fc, * holding an active reference. */ up_write(&s->s_umount); - blkdev_put(bdev, mode); + blkdev_put(bdev, fc->fs_type); down_write(&s->s_umount); } else { - s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fc->fs_type->name, s->s_id); @@ -1331,13 +1343,10 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, { struct block_device *bdev; struct super_block *s; - fmode_t mode = FMODE_READ | FMODE_EXCL; int error = 0; - if (!(flags & SB_RDONLY)) - mode |= FMODE_WRITE; - - bdev = blkdev_get_by_path(dev_name, mode, fs_type); + bdev = blkdev_get_by_path(dev_name, sb_open_mode(flags), fs_type, + &fs_holder_ops); if (IS_ERR(bdev)) return ERR_CAST(bdev); @@ -1373,10 +1382,9 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, * holding an active reference. */ up_write(&s->s_umount); - blkdev_put(bdev, mode); + blkdev_put(bdev, fs_type); down_write(&s->s_umount); } else { - s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, s->s_id); @@ -1396,7 +1404,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, error_s: error = PTR_ERR(s); error_bdev: - blkdev_put(bdev, mode); + blkdev_put(bdev, fs_type); error: return ERR_PTR(error); } @@ -1405,13 +1413,11 @@ EXPORT_SYMBOL(mount_bdev); void kill_block_super(struct super_block *sb) { struct block_device *bdev = sb->s_bdev; - fmode_t mode = sb->s_mode; bdev->bd_super = NULL; generic_shutdown_super(sb); sync_blockdev(bdev); - WARN_ON_ONCE(!(mode & FMODE_EXCL)); - blkdev_put(bdev, mode | FMODE_EXCL); + blkdev_put(bdev, sb->s_type); } EXPORT_SYMBOL(kill_block_super); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 13851c0d640b..9ebb8333a308 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -534,6 +534,9 @@ xfs_do_force_shutdown( } else if (flags & SHUTDOWN_CORRUPT_ONDISK) { tag = XFS_PTAG_SHUTDOWN_CORRUPT; why = "Corruption of on-disk metadata"; + } else if (flags & SHUTDOWN_DEVICE_REMOVED) { + tag = XFS_PTAG_SHUTDOWN_IOERROR; + why = "Block device removal"; } else { tag = XFS_PTAG_SHUTDOWN_IOERROR; why = "Metadata I/O Error"; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 6c09f89534d3..e2866e7fa60c 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -458,12 +458,14 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, uint32_t flags, char *fname, #define SHUTDOWN_FORCE_UMOUNT (1u << 2) /* shutdown from a forced unmount */ #define SHUTDOWN_CORRUPT_INCORE (1u << 3) /* corrupt in-memory structures */ #define SHUTDOWN_CORRUPT_ONDISK (1u << 4) /* corrupt metadata on device */ +#define SHUTDOWN_DEVICE_REMOVED (1u << 5) /* device removed underneath us */ #define XFS_SHUTDOWN_STRINGS \ { SHUTDOWN_META_IO_ERROR, "metadata_io" }, \ { SHUTDOWN_LOG_IO_ERROR, "log_io" }, \ { SHUTDOWN_FORCE_UMOUNT, "force_umount" }, \ - { SHUTDOWN_CORRUPT_INCORE, "corruption" } + { SHUTDOWN_CORRUPT_INCORE, "corruption" }, \ + { SHUTDOWN_DEVICE_REMOVED, "device_removed" } /* * Flags for xfs_mountfs diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4120bd1cba90..d910b141d52e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -377,6 +377,17 @@ disable_dax: return 0; } +static void +xfs_bdev_mark_dead( + struct block_device *bdev) +{ + xfs_force_shutdown(bdev->bd_holder, SHUTDOWN_DEVICE_REMOVED); +} + +static const struct blk_holder_ops xfs_holder_ops = { + .mark_dead = xfs_bdev_mark_dead, +}; + STATIC int xfs_blkdev_get( xfs_mount_t *mp, @@ -385,8 +396,8 @@ xfs_blkdev_get( { int error = 0; - *bdevp = blkdev_get_by_path(name, FMODE_READ|FMODE_WRITE|FMODE_EXCL, - mp); + *bdevp = blkdev_get_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE, mp, + &xfs_holder_ops); if (IS_ERR(*bdevp)) { error = PTR_ERR(*bdevp); xfs_warn(mp, "Invalid device [%s], error=%d", name, error); @@ -397,10 +408,11 @@ xfs_blkdev_get( STATIC void xfs_blkdev_put( + struct xfs_mount *mp, struct block_device *bdev) { if (bdev) - blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + blkdev_put(bdev, mp); } STATIC void @@ -411,13 +423,13 @@ xfs_close_devices( struct block_device *logdev = mp->m_logdev_targp->bt_bdev; xfs_free_buftarg(mp->m_logdev_targp); - xfs_blkdev_put(logdev); + xfs_blkdev_put(mp, logdev); } if (mp->m_rtdev_targp) { struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev; xfs_free_buftarg(mp->m_rtdev_targp); - xfs_blkdev_put(rtdev); + xfs_blkdev_put(mp, rtdev); } xfs_free_buftarg(mp->m_ddev_targp); } @@ -492,10 +504,10 @@ xfs_open_devices( out_free_ddev_targ: xfs_free_buftarg(mp->m_ddev_targp); out_close_rtdev: - xfs_blkdev_put(rtdev); + xfs_blkdev_put(mp, rtdev); out_close_logdev: if (logdev && logdev != ddev) - xfs_blkdev_put(logdev); + xfs_blkdev_put(mp, logdev); return error; } @@ -1160,6 +1172,13 @@ xfs_fs_free_cached_objects( return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan); } +static void +xfs_fs_shutdown( + struct super_block *sb) +{ + xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED); +} + static const struct super_operations xfs_super_operations = { .alloc_inode = xfs_fs_alloc_inode, .destroy_inode = xfs_fs_destroy_inode, @@ -1173,6 +1192,7 @@ static const struct super_operations xfs_super_operations = { .show_options = xfs_fs_show_options, .nr_cached_objects = xfs_fs_nr_cached_objects, .free_cached_objects = xfs_fs_free_cached_objects, + .shutdown = xfs_fs_shutdown, }; static int diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 56c00111966a..bbe44a26a8e5 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1128,7 +1128,7 @@ static int zonefs_read_super(struct super_block *sb) bio_init(&bio, sb->s_bdev, &bio_vec, 1, REQ_OP_READ); bio.bi_iter.bi_sector = 0; - bio_add_page(&bio, page, PAGE_SIZE, 0); + __bio_add_page(&bio, page, PAGE_SIZE, 0); ret = submit_bio_wait(&bio); if (ret) diff --git a/include/linux/bio.h b/include/linux/bio.h index b3e7529ff55e..c4f5b5228105 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -229,7 +229,7 @@ static inline void bio_cnt_set(struct bio *bio, unsigned int count) static inline bool bio_flagged(struct bio *bio, unsigned int bit) { - return (bio->bi_flags & (1U << bit)) != 0; + return bio->bi_flags & (1U << bit); } static inline void bio_set_flag(struct bio *bio, unsigned int bit) @@ -465,14 +465,18 @@ extern void bio_uninit(struct bio *); void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf); void bio_chain(struct bio *, struct bio *); -int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off); -bool bio_add_folio(struct bio *, struct folio *, size_t len, size_t off); +int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len, + unsigned off); +bool __must_check bio_add_folio(struct bio *bio, struct folio *folio, + size_t len, size_t off); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); int bio_add_zone_append_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); +void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, + size_t off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter); void __bio_release_pages(struct bio *bio, bool mark_dirty); @@ -488,7 +492,7 @@ void zero_fill_bio(struct bio *bio); static inline void bio_release_pages(struct bio *bio, bool mark_dirty) { - if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + if (bio_flagged(bio, BIO_PAGE_PINNED)) __bio_release_pages(bio, mark_dirty); } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 06caacd77ed6..f401067ac03a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -28,8 +28,6 @@ typedef __u32 __bitwise req_flags_t; /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) -/* may not be passed by ioscheduler */ -#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) /* request for flush sequence */ #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) /* merge of different types, fail separately */ @@ -38,12 +36,14 @@ typedef __u32 __bitwise req_flags_t; #define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) /* don't call prep for this one */ #define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) +/* use hctx->sched_tags */ +#define RQF_SCHED_TAGS ((__force req_flags_t)(1 << 8)) +/* use an I/O scheduler for this request */ +#define RQF_USE_SCHED ((__force req_flags_t)(1 << 9)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ #define RQF_QUIET ((__force req_flags_t)(1 << 11)) -/* elevator private data attached */ -#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) /* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* runtime pm request */ @@ -59,13 +59,11 @@ typedef __u32 __bitwise req_flags_t; #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) -/* queue has elevator attached */ -#define RQF_ELV ((__force req_flags_t)(1 << 22)) -#define RQF_RESV ((__force req_flags_t)(1 << 23)) +#define RQF_RESV ((__force req_flags_t)(1 << 23)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ - (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) + (RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) enum mq_rq_state { MQ_RQ_IDLE = 0, @@ -169,25 +167,20 @@ struct request { void *completion_data; }; - /* * Three pointers are available for the IO schedulers, if they need - * more they have to dynamically allocate it. Flush requests are - * never put on the IO scheduler. So let the flush fields share - * space with the elevator data. + * more they have to dynamically allocate it. */ - union { - struct { - struct io_cq *icq; - void *priv[2]; - } elv; - - struct { - unsigned int seq; - struct list_head list; - rq_end_io_fn *saved_end_io; - } flush; - }; + struct { + struct io_cq *icq; + void *priv[2]; + } elv; + + struct { + unsigned int seq; + struct list_head list; + rq_end_io_fn *saved_end_io; + } flush; union { struct __call_single_data csd; @@ -208,7 +201,7 @@ static inline enum req_op req_op(const struct request *req) static inline bool blk_rq_is_passthrough(struct request *rq) { - return blk_op_is_passthrough(req_op(rq)); + return blk_op_is_passthrough(rq->cmd_flags); } static inline unsigned short req_get_ioprio(struct request *req) @@ -746,8 +739,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, struct blk_mq_tags { unsigned int nr_tags; unsigned int nr_reserved_tags; - - atomic_t active_queues; + unsigned int active_queues; struct sbitmap_queue bitmap_tags; struct sbitmap_queue breserved_tags; @@ -844,7 +836,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib); */ static inline bool blk_mq_need_time_stamp(struct request *rq) { - return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); + return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } static inline bool blk_mq_is_reserved_rq(struct request *rq) @@ -860,7 +852,7 @@ static inline bool blk_mq_add_to_batch(struct request *req, struct io_comp_batch *iob, int ioerror, void (*complete)(struct io_comp_batch *)) { - if (!iob || (req->rq_flags & RQF_ELV) || ioerror || + if (!iob || (req->rq_flags & RQF_USE_SCHED) || ioerror || (req->end_io && !blk_rq_is_passthrough(req))) return false; @@ -1164,6 +1156,18 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq) return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq)); } +/** + * blk_rq_is_seq_zoned_write() - Check if @rq requires write serialization. + * @rq: Request to examine. + * + * Note: REQ_OP_ZONE_APPEND requests do not require serialization. + */ +static inline bool blk_rq_is_seq_zoned_write(struct request *rq) +{ + return op_needs_zoned_write_locking(req_op(rq)) && + blk_rq_zone_is_seq(rq); +} + bool blk_req_needs_zone_write_lock(struct request *rq); bool blk_req_zone_write_trylock(struct request *rq); void __blk_req_zone_write_lock(struct request *rq); @@ -1194,6 +1198,11 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq) return !blk_req_zone_is_write_locked(rq); } #else /* CONFIG_BLK_DEV_ZONED */ +static inline bool blk_rq_is_seq_zoned_write(struct request *rq) +{ + return false; +} + static inline bool blk_req_needs_zone_write_lock(struct request *rq) { return false; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 740afe80f297..752a54e3284b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -55,6 +55,8 @@ struct block_device { struct super_block * bd_super; void * bd_claiming; void * bd_holder; + const struct blk_holder_ops *bd_holder_ops; + struct mutex bd_holder_lock; /* The counter of freeze processes */ int bd_fsfreeze_count; int bd_holders; @@ -323,7 +325,7 @@ struct bio { * bio flags */ enum { - BIO_NO_PAGE_REF, /* don't put release vec pages */ + BIO_PAGE_PINNED, /* Unpin pages in bio_release_pages() */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ BIO_QUIET, /* Make BIO Quiet */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c0ffe203a602..ed44a997f629 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -41,7 +41,7 @@ struct blk_stat_callback; struct blk_crypto_profile; extern const struct device_type disk_type; -extern struct device_type part_type; +extern const struct device_type part_type; extern struct class block_class; /* @@ -112,6 +112,19 @@ struct blk_integrity { unsigned char tag_size; }; +typedef unsigned int __bitwise blk_mode_t; + +/* open for reading */ +#define BLK_OPEN_READ ((__force blk_mode_t)(1 << 0)) +/* open for writing */ +#define BLK_OPEN_WRITE ((__force blk_mode_t)(1 << 1)) +/* open exclusively (vs other exclusive openers */ +#define BLK_OPEN_EXCL ((__force blk_mode_t)(1 << 2)) +/* opened with O_NDELAY */ +#define BLK_OPEN_NDELAY ((__force blk_mode_t)(1 << 3)) +/* open for "writes" only for ioctls (specialy hack for floppy.c) */ +#define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) + struct gendisk { /* * major/first_minor/minors should not be set by any new driver, the @@ -187,6 +200,7 @@ struct gendisk { struct badblocks *bb; struct lockdep_map lockdep_map; u64 diskseq; + blk_mode_t open_mode; /* * Independent sector access ranges. This is always NULL for @@ -318,7 +332,6 @@ typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model); #ifdef CONFIG_BLK_DEV_ZONED - #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); @@ -328,33 +341,11 @@ extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, gfp_t gfp_mask); int blk_revalidate_disk_zones(struct gendisk *disk, void (*update_driver_data)(struct gendisk *disk)); - -extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg); -extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg); - #else /* CONFIG_BLK_DEV_ZONED */ - static inline unsigned int bdev_nr_zones(struct block_device *bdev) { return 0; } - -static inline int blkdev_report_zones_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) -{ - return -ENOTTY; -} - -static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) -{ - return -ENOTTY; -} - #endif /* CONFIG_BLK_DEV_ZONED */ /* @@ -392,6 +383,7 @@ struct request_queue { struct blk_queue_stats *stats; struct rq_qos *rq_qos; + struct mutex rq_qos_mutex; const struct blk_mq_ops *mq_ops; @@ -487,6 +479,7 @@ struct request_queue { * for flush operations */ struct blk_flush_queue *fq; + struct list_head flush_list; struct list_head requeue_list; spinlock_t requeue_lock; @@ -815,7 +808,7 @@ int __register_blkdev(unsigned int major, const char *name, __register_blkdev(major, name, NULL) void unregister_blkdev(unsigned int major, const char *name); -bool bdev_check_media_change(struct block_device *bdev); +bool disk_check_media_change(struct gendisk *disk); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void set_capacity(struct gendisk *disk, sector_t size); @@ -836,7 +829,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, dev_t part_devt(struct gendisk *disk, u8 partno); void inc_diskseq(struct gendisk *disk); -dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); extern int blk_register_queue(struct gendisk *disk); @@ -1281,15 +1273,18 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) return disk_zone_no(bdev->bd_disk, sec); } -static inline bool bdev_op_is_zoned_write(struct block_device *bdev, - blk_opf_t op) +/* Whether write serialization is required for @op on zoned devices. */ +static inline bool op_needs_zoned_write_locking(enum req_op op) { - if (!bdev_is_zoned(bdev)) - return false; - return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES; } +static inline bool bdev_op_is_zoned_write(struct block_device *bdev, + enum req_op op) +{ + return bdev_is_zoned(bdev) && op_needs_zoned_write_locking(op); +} + static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1380,10 +1375,12 @@ struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); - int (*open) (struct block_device *, fmode_t); - void (*release) (struct gendisk *, fmode_t); - int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); + int (*open)(struct gendisk *disk, blk_mode_t mode); + void (*release)(struct gendisk *disk); + int (*ioctl)(struct block_device *bdev, blk_mode_t mode, + unsigned cmd, unsigned long arg); + int (*compat_ioctl)(struct block_device *bdev, blk_mode_t mode, + unsigned cmd, unsigned long arg); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); void (*unlock_native_capacity) (struct gendisk *); @@ -1410,7 +1407,7 @@ struct block_device_operations { }; #ifdef CONFIG_COMPAT -extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, +extern int blkdev_compat_ptr_ioctl(struct block_device *, blk_mode_t, unsigned int, unsigned long); #else #define blkdev_compat_ptr_ioctl NULL @@ -1463,22 +1460,31 @@ void blkdev_show(struct seq_file *seqf, off_t offset); #define BLKDEV_MAJOR_MAX 0 #endif -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, void *holder); +struct blk_holder_ops { + void (*mark_dead)(struct block_device *bdev); +}; + +/* + * Return the correct open flags for blkdev_get_by_* for super block flags + * as stored in sb->s_flags. + */ +#define sb_open_mode(flags) \ + (BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) + +struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops); +struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, + void *holder, const struct blk_holder_ops *hops); +int bd_prepare_to_claim(struct block_device *bdev, void *holder, + const struct blk_holder_ops *hops); void bd_abort_claiming(struct block_device *bdev, void *holder); -void blkdev_put(struct block_device *bdev, fmode_t mode); +void blkdev_put(struct block_device *bdev, void *holder); /* just for blk-cgroup, don't use elsewhere */ struct block_device *blkdev_get_no_open(dev_t dev); void blkdev_put_no_open(struct block_device *bdev); -struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); -void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); -int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, - loff_t lend); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); @@ -1488,6 +1494,7 @@ int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); void printk_all_partitions(void); +int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else static inline void invalidate_bdev(struct block_device *bdev) { @@ -1509,6 +1516,10 @@ static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) static inline void printk_all_partitions(void) { } +static inline int early_lookup_bdev(const char *pathname, dev_t *dev) +{ + return -EINVAL; +} #endif /* CONFIG_BLOCK */ int fsync_bdev(struct block_device *bdev); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index cfbda114348c..122c62e561fc 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -85,10 +85,14 @@ extern int blk_trace_remove(struct request_queue *q); # define blk_add_driver_data(rq, data, len) do {} while (0) # define blk_trace_setup(q, name, dev, bdev, arg) (-ENOTTY) # define blk_trace_startstop(q, start) (-ENOTTY) -# define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) # define blk_add_cgroup_trace_msg(q, cg, fmt, ...) do { } while (0) # define blk_trace_note_message_enabled(q) (false) + +static inline int blk_trace_remove(struct request_queue *q) +{ + return -ENOTTY; +} #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_COMPAT diff --git a/include/linux/bsg.h b/include/linux/bsg.h index 1ac81c809da9..ee2df73edf83 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -9,7 +9,7 @@ struct device; struct request_queue; typedef int (bsg_sg_io_fn)(struct request_queue *, struct sg_io_v4 *hdr, - fmode_t mode, unsigned int timeout); + bool open_for_write, unsigned int timeout); struct bsg_device *bsg_register_queue(struct request_queue *q, struct device *parent, const char *name, diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 67caa909e3e6..98c6fd0b39b6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -13,6 +13,7 @@ #include <linux/fs.h> /* not really needed, later.. */ #include <linux/list.h> +#include <linux/blkdev.h> #include <scsi/scsi_common.h> #include <uapi/linux/cdrom.h> @@ -61,9 +62,9 @@ struct cdrom_device_info { __u8 last_sense; __u8 media_written; /* dirty flag, DVD+RW bookkeeping */ unsigned short mmc3_profile; /* current MMC3 profile */ - int for_data; int (*exit)(struct cdrom_device_info *); int mrw_mode_page; + bool opened_for_data; __s64 last_media_change_ms; }; @@ -101,11 +102,10 @@ int cdrom_read_tocentry(struct cdrom_device_info *cdi, struct cdrom_tocentry *entry); /* the general block_device operations structure: */ -extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode); -extern void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode); -extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode, unsigned int cmd, unsigned long arg); +int cdrom_open(struct cdrom_device_info *cdi, blk_mode_t mode); +void cdrom_release(struct cdrom_device_info *cdi); +int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, + unsigned int cmd, unsigned long arg); extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index a52d2b9a6846..69d0435c7ebb 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -166,17 +166,15 @@ void dm_error(const char *message); struct dm_dev { struct block_device *bdev; struct dax_device *dax_dev; - fmode_t mode; + blk_mode_t mode; char name[16]; }; -dev_t dm_get_dev_t(const char *path); - /* * Constructors should call these functions to ensure destination devices * are opened/closed correctly. */ -int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, +int dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, struct dm_dev **result); void dm_put_device(struct dm_target *ti, struct dm_dev *d); @@ -545,7 +543,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo); /* * First create an empty table. */ -int dm_table_create(struct dm_table **result, fmode_t mode, +int dm_table_create(struct dm_table **result, blk_mode_t mode, unsigned int num_targets, struct mapped_device *md); /* @@ -588,7 +586,7 @@ void dm_sync_table(struct mapped_device *md); * Queries */ sector_t dm_table_get_size(struct dm_table *t); -fmode_t dm_table_get_mode(struct dm_table *t); +blk_mode_t dm_table_get_mode(struct dm_table *t); struct mapped_device *dm_table_get_md(struct dm_table *t); const char *dm_table_device_name(struct dm_table *t); diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index c244267a6744..7738f458995f 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -126,7 +126,7 @@ int __must_check driver_register(struct device_driver *drv); void driver_unregister(struct device_driver *drv); struct device_driver *driver_find(const char *name, const struct bus_type *bus); -int driver_probe_done(void); +bool __init driver_probe_done(void); void wait_for_device_probe(void); void __init wait_for_init_devices_probe(void); diff --git a/include/linux/fs.h b/include/linux/fs.h index 42129a67d98d..ed5b32dc2625 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -119,13 +119,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) -/* File is opened with O_NDELAY (only set for block devices) */ -#define FMODE_NDELAY ((__force fmode_t)0x40) -/* File is opened with O_EXCL (only set for block devices) */ -#define FMODE_EXCL ((__force fmode_t)0x80) -/* File is opened using open(.., 3, ..) and is writeable only for ioctls - (specialy hack for floppy.c) */ -#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */ @@ -1224,7 +1217,6 @@ struct super_block { uuid_t s_uuid; /* UUID */ unsigned int s_max_links; - fmode_t s_mode; /* * The next field is for VFS *only*. No filesystems have any business @@ -1944,6 +1936,7 @@ struct super_operations { struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); + void (*shutdown)(struct super_block *sb); }; /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 27ce77080c79..200068d98686 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1910,6 +1910,28 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, return page_maybe_dma_pinned(page); } +/** + * is_zero_page - Query if a page is a zero page + * @page: The page to query + * + * This returns true if @page is one of the permanent zero pages. + */ +static inline bool is_zero_page(const struct page *page) +{ + return is_zero_pfn(page_to_pfn(page)); +} + +/** + * is_zero_folio - Query if a folio is a zero page + * @folio: The folio to query + * + * This returns true if @folio is one of the permanent zero pages. + */ +static inline bool is_zero_folio(const struct folio *folio) +{ + return is_zero_page(&folio->page); +} + /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION static inline bool is_longterm_pinnable_page(struct page *page) @@ -1920,8 +1942,8 @@ static inline bool is_longterm_pinnable_page(struct page *page) if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif - /* The zero page may always be pinned */ - if (is_zero_pfn(page_to_pfn(page))) + /* The zero page can be "pinned" but gets special handling. */ + if (is_zero_page(page)) return true; /* Coherent device memory must always allow eviction. */ @@ -2383,6 +2405,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); +void folio_add_pin(struct folio *folio); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, diff --git a/include/linux/mount.h b/include/linux/mount.h index 1ea326c368f7..4b81ea90440e 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -107,7 +107,6 @@ extern struct vfsmount *vfs_submount(const struct dentry *mountpoint, extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); -extern dev_t name_to_dev_t(const char *name); extern bool path_is_mountpoint(const struct path *path); extern bool our_mnt(struct vfsmount *mnt); diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index 15cc9b95e32b..6e471436bba5 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -34,7 +34,7 @@ struct mtd_blktrans_dev { struct blk_mq_tag_set *tag_set; spinlock_t queue_lock; void *priv; - fmode_t file_mode; + bool writable; }; struct mtd_blktrans_ops { diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index fa092b9be2fd..4109f1bd6128 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -185,7 +185,6 @@ enum nvmefc_fcp_datadir { * @first_sgl: memory for 1st scatter/gather list segment for payload data * @sg_cnt: number of elements in the scatter/gather list * @io_dir: direction of the FCP request (see NVMEFC_FCP_xxx) - * @sqid: The nvme SQID the command is being issued on * @done: The callback routine the LLDD is to invoke upon completion of * the FCP operation. req argument is the pointer to the original * FCP IO operation. @@ -194,12 +193,13 @@ enum nvmefc_fcp_datadir { * while processing the operation. The length of the buffer * corresponds to the fcprqst_priv_sz value specified in the * nvme_fc_port_template supplied by the LLDD. + * @sqid: The nvme SQID the command is being issued on * * Values set by the LLDD indicating completion status of the FCP operation. * Must be set prior to calling the done() callback. + * @rcv_rsplen: length, in bytes, of the FCP RSP IU received. * @transferred_length: amount of payload data, in bytes, that were * transferred. Should equal payload_length on success. - * @rcv_rsplen: length, in bytes, of the FCP RSP IU received. * @status: Completion status of the FCP operation. must be 0 upon success, * negative errno value upon failure (ex: -EIO). Note: this is * NOT a reflection of the NVME CQE completion status. Only the @@ -219,14 +219,14 @@ struct nvmefc_fcp_req { int sg_cnt; enum nvmefc_fcp_datadir io_dir; - __le16 sqid; - void (*done)(struct nvmefc_fcp_req *req); void *private; - u32 transferred_length; + __le16 sqid; + u16 rcv_rsplen; + u32 transferred_length; u32 status; } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index f9c5ac80d59b..80cb00db42a4 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -156,7 +156,6 @@ struct pktcdvd_device { struct block_device *bdev; /* dev attached */ dev_t pkt_dev; /* our dev */ - char name[20]; struct packet_settings settings; struct packet_stats stats; int refcnt; /* Open count */ diff --git a/include/linux/root_dev.h b/include/linux/root_dev.h index 4e78651371ba..847c9a06101b 100644 --- a/include/linux/root_dev.h +++ b/include/linux/root_dev.h @@ -9,15 +9,8 @@ enum { Root_NFS = MKDEV(UNNAMED_MAJOR, 255), Root_CIFS = MKDEV(UNNAMED_MAJOR, 254), + Root_Generic = MKDEV(UNNAMED_MAJOR, 253), Root_RAM0 = MKDEV(RAMDISK_MAJOR, 0), - Root_RAM1 = MKDEV(RAMDISK_MAJOR, 1), - Root_FD0 = MKDEV(FLOPPY_MAJOR, 0), - Root_HDA1 = MKDEV(IDE0_MAJOR, 1), - Root_HDA2 = MKDEV(IDE0_MAJOR, 2), - Root_SDA1 = MKDEV(SCSI_DISK0_MAJOR, 1), - Root_SDA2 = MKDEV(SCSI_DISK0_MAJOR, 2), - Root_HDC1 = MKDEV(IDE1_MAJOR, 1), - Root_SR0 = MKDEV(SCSI_CDROM_MAJOR, 0), }; extern dev_t ROOT_DEV; diff --git a/include/linux/uio.h b/include/linux/uio.h index 60c342bb7ab8..8e7d2c425340 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -277,14 +277,8 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); -ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, - size_t maxsize, unsigned maxpages, size_t *start, - iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); -ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, - struct page ***pages, size_t maxsize, size_t *start, - iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); diff --git a/include/scsi/scsi_ioctl.h b/include/scsi/scsi_ioctl.h index beac64e38b87..a207c07da9d2 100644 --- a/include/scsi/scsi_ioctl.h +++ b/include/scsi/scsi_ioctl.h @@ -45,11 +45,11 @@ typedef struct scsi_fctargaddress { int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev, int cmd, bool ndelay); -int scsi_ioctl(struct scsi_device *sdev, fmode_t mode, int cmd, +int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd, void __user *arg); int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp); int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp); -bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode); +bool scsi_cmd_allowed(unsigned char *cmd, bool open_for_write); #endif /* __KERNEL__ */ #endif /* _SCSI_IOCTL_H */ diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 7f4dfbdf12a6..40e60c33cc6f 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -246,6 +246,32 @@ DEFINE_EVENT(block_rq, block_rq_merge, ); /** + * block_io_start - insert a request for execution + * @rq: block IO operation request + * + * Called when block operation request @rq is queued for execution + */ +DEFINE_EVENT(block_rq, block_io_start, + + TP_PROTO(struct request *rq), + + TP_ARGS(rq) +); + +/** + * block_io_done - block IO operation request completed + * @rq: block IO operation request + * + * Called when block operation request @rq is completed + */ +DEFINE_EVENT(block_rq, block_io_done, + + TP_PROTO(struct request *rq), + + TP_ARGS(rq) +); + +/** * block_bio_complete - completed all work on the block operation * @q: queue holding the block operation * @bio: block operation completed diff --git a/include/uapi/linux/affs_hardblocks.h b/include/uapi/linux/affs_hardblocks.h index 5e2fb8481252..a5aff2eb5f70 100644 --- a/include/uapi/linux/affs_hardblocks.h +++ b/include/uapi/linux/affs_hardblocks.h @@ -7,42 +7,42 @@ /* Just the needed definitions for the RDB of an Amiga HD. */ struct RigidDiskBlock { - __u32 rdb_ID; + __be32 rdb_ID; __be32 rdb_SummedLongs; - __s32 rdb_ChkSum; - __u32 rdb_HostID; + __be32 rdb_ChkSum; + __be32 rdb_HostID; __be32 rdb_BlockBytes; - __u32 rdb_Flags; - __u32 rdb_BadBlockList; + __be32 rdb_Flags; + __be32 rdb_BadBlockList; __be32 rdb_PartitionList; - __u32 rdb_FileSysHeaderList; - __u32 rdb_DriveInit; - __u32 rdb_Reserved1[6]; - __u32 rdb_Cylinders; - __u32 rdb_Sectors; - __u32 rdb_Heads; - __u32 rdb_Interleave; - __u32 rdb_Park; - __u32 rdb_Reserved2[3]; - __u32 rdb_WritePreComp; - __u32 rdb_ReducedWrite; - __u32 rdb_StepRate; - __u32 rdb_Reserved3[5]; - __u32 rdb_RDBBlocksLo; - __u32 rdb_RDBBlocksHi; - __u32 rdb_LoCylinder; - __u32 rdb_HiCylinder; - __u32 rdb_CylBlocks; - __u32 rdb_AutoParkSeconds; - __u32 rdb_HighRDSKBlock; - __u32 rdb_Reserved4; + __be32 rdb_FileSysHeaderList; + __be32 rdb_DriveInit; + __be32 rdb_Reserved1[6]; + __be32 rdb_Cylinders; + __be32 rdb_Sectors; + __be32 rdb_Heads; + __be32 rdb_Interleave; + __be32 rdb_Park; + __be32 rdb_Reserved2[3]; + __be32 rdb_WritePreComp; + __be32 rdb_ReducedWrite; + __be32 rdb_StepRate; + __be32 rdb_Reserved3[5]; + __be32 rdb_RDBBlocksLo; + __be32 rdb_RDBBlocksHi; + __be32 rdb_LoCylinder; + __be32 rdb_HiCylinder; + __be32 rdb_CylBlocks; + __be32 rdb_AutoParkSeconds; + __be32 rdb_HighRDSKBlock; + __be32 rdb_Reserved4; char rdb_DiskVendor[8]; char rdb_DiskProduct[16]; char rdb_DiskRevision[4]; char rdb_ControllerVendor[8]; char rdb_ControllerProduct[16]; char rdb_ControllerRevision[4]; - __u32 rdb_Reserved5[10]; + __be32 rdb_Reserved5[10]; }; #define IDNAME_RIGIDDISK 0x5244534B /* "RDSK" */ @@ -50,16 +50,16 @@ struct RigidDiskBlock { struct PartitionBlock { __be32 pb_ID; __be32 pb_SummedLongs; - __s32 pb_ChkSum; - __u32 pb_HostID; + __be32 pb_ChkSum; + __be32 pb_HostID; __be32 pb_Next; - __u32 pb_Flags; - __u32 pb_Reserved1[2]; - __u32 pb_DevFlags; + __be32 pb_Flags; + __be32 pb_Reserved1[2]; + __be32 pb_DevFlags; __u8 pb_DriveName[32]; - __u32 pb_Reserved2[15]; + __be32 pb_Reserved2[15]; __be32 pb_Environment[17]; - __u32 pb_EReserved[15]; + __be32 pb_EReserved[15]; }; #define IDNAME_PARTITION 0x50415254 /* "PART" */ diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h index 6a5552dfd6af..987a3022dc5f 100644 --- a/include/uapi/linux/pktcdvd.h +++ b/include/uapi/linux/pktcdvd.h @@ -16,6 +16,7 @@ #include <linux/types.h> /* + * UNUSED: * 1 for normal debug messages, 2 is very verbose. 0 to turn it off. */ #define PACKET_DEBUG 1 diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 640bf687b94a..4b8558db90e1 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -47,6 +47,14 @@ _IOWR('u', UBLK_CMD_END_USER_RECOVERY, struct ublksrv_ctrl_cmd) #define UBLK_U_CMD_GET_DEV_INFO2 \ _IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd) +#define UBLK_U_CMD_GET_FEATURES \ + _IOR('u', 0x13, struct ublksrv_ctrl_cmd) + +/* + * 64bits are enough now, and it should be easy to extend in case of + * running out of feature flags + */ +#define UBLK_FEATURES_LEN 8 /* * IO commands, issued by ublk server, and handled by ublk driver. @@ -93,9 +101,29 @@ #define UBLKSRV_CMD_BUF_OFFSET 0 #define UBLKSRV_IO_BUF_OFFSET 0x80000000 -/* tag bit is 12bit, so at most 4096 IOs for each queue */ +/* tag bit is 16bit, so far limit at most 4096 IOs for each queue */ #define UBLK_MAX_QUEUE_DEPTH 4096 +/* single IO buffer max size is 32MB */ +#define UBLK_IO_BUF_OFF 0 +#define UBLK_IO_BUF_BITS 25 +#define UBLK_IO_BUF_BITS_MASK ((1ULL << UBLK_IO_BUF_BITS) - 1) + +/* so at most 64K IOs for each queue */ +#define UBLK_TAG_OFF UBLK_IO_BUF_BITS +#define UBLK_TAG_BITS 16 +#define UBLK_TAG_BITS_MASK ((1ULL << UBLK_TAG_BITS) - 1) + +/* max 4096 queues */ +#define UBLK_QID_OFF (UBLK_TAG_OFF + UBLK_TAG_BITS) +#define UBLK_QID_BITS 12 +#define UBLK_QID_BITS_MASK ((1ULL << UBLK_QID_BITS) - 1) + +#define UBLK_MAX_NR_QUEUES (1U << UBLK_QID_BITS) + +#define UBLKSRV_IO_BUF_TOTAL_BITS (UBLK_QID_OFF + UBLK_QID_BITS) +#define UBLKSRV_IO_BUF_TOTAL_SIZE (1ULL << UBLKSRV_IO_BUF_TOTAL_BITS) + /* * zero copy requires 4k block size, and can remap ublk driver's io * request into ublksrv's vm space @@ -145,6 +173,9 @@ /* use ioctl encoding for uring command */ #define UBLK_F_CMD_IOCTL_ENCODE (1UL << 6) +/* Copy between request and user buffer by pread()/pwrite() */ +#define UBLK_F_USER_COPY (1UL << 7) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 diff --git a/init/do_mounts.c b/init/do_mounts.c index d67efddf8597..2a970f6ac68f 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -28,7 +28,6 @@ #include "do_mounts.h" int root_mountflags = MS_RDONLY | MS_SILENT; -static char * __initdata root_device_name; static char __initdata saved_root_name[64]; static int root_wait; @@ -60,240 +59,6 @@ static int __init readwrite(char *str) __setup("ro", readonly); __setup("rw", readwrite); -#ifdef CONFIG_BLOCK -struct uuidcmp { - const char *uuid; - int len; -}; - -/** - * match_dev_by_uuid - callback for finding a partition using its uuid - * @dev: device passed in by the caller - * @data: opaque pointer to the desired struct uuidcmp to match - * - * Returns 1 if the device matches, and 0 otherwise. - */ -static int match_dev_by_uuid(struct device *dev, const void *data) -{ - struct block_device *bdev = dev_to_bdev(dev); - const struct uuidcmp *cmp = data; - - if (!bdev->bd_meta_info || - strncasecmp(cmp->uuid, bdev->bd_meta_info->uuid, cmp->len)) - return 0; - return 1; -} - -/** - * devt_from_partuuid - looks up the dev_t of a partition by its UUID - * @uuid_str: char array containing ascii UUID - * - * The function will return the first partition which contains a matching - * UUID value in its partition_meta_info struct. This does not search - * by filesystem UUIDs. - * - * If @uuid_str is followed by a "/PARTNROFF=%d", then the number will be - * extracted and used as an offset from the partition identified by the UUID. - * - * Returns the matching dev_t on success or 0 on failure. - */ -static dev_t devt_from_partuuid(const char *uuid_str) -{ - struct uuidcmp cmp; - struct device *dev = NULL; - dev_t devt = 0; - int offset = 0; - char *slash; - - cmp.uuid = uuid_str; - - slash = strchr(uuid_str, '/'); - /* Check for optional partition number offset attributes. */ - if (slash) { - char c = 0; - - /* Explicitly fail on poor PARTUUID syntax. */ - if (sscanf(slash + 1, "PARTNROFF=%d%c", &offset, &c) != 1) - goto clear_root_wait; - cmp.len = slash - uuid_str; - } else { - cmp.len = strlen(uuid_str); - } - - if (!cmp.len) - goto clear_root_wait; - - dev = class_find_device(&block_class, NULL, &cmp, &match_dev_by_uuid); - if (!dev) - return 0; - - if (offset) { - /* - * Attempt to find the requested partition by adding an offset - * to the partition number found by UUID. - */ - devt = part_devt(dev_to_disk(dev), - dev_to_bdev(dev)->bd_partno + offset); - } else { - devt = dev->devt; - } - - put_device(dev); - return devt; - -clear_root_wait: - pr_err("VFS: PARTUUID= is invalid.\n" - "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n"); - if (root_wait) - pr_err("Disabling rootwait; root= is invalid.\n"); - root_wait = 0; - return 0; -} - -/** - * match_dev_by_label - callback for finding a partition using its label - * @dev: device passed in by the caller - * @data: opaque pointer to the label to match - * - * Returns 1 if the device matches, and 0 otherwise. - */ -static int match_dev_by_label(struct device *dev, const void *data) -{ - struct block_device *bdev = dev_to_bdev(dev); - const char *label = data; - - if (!bdev->bd_meta_info || strcmp(label, bdev->bd_meta_info->volname)) - return 0; - return 1; -} - -static dev_t devt_from_partlabel(const char *label) -{ - struct device *dev; - dev_t devt = 0; - - dev = class_find_device(&block_class, NULL, label, &match_dev_by_label); - if (dev) { - devt = dev->devt; - put_device(dev); - } - - return devt; -} - -static dev_t devt_from_devname(const char *name) -{ - dev_t devt = 0; - int part; - char s[32]; - char *p; - - if (strlen(name) > 31) - return 0; - strcpy(s, name); - for (p = s; *p; p++) { - if (*p == '/') - *p = '!'; - } - - devt = blk_lookup_devt(s, 0); - if (devt) - return devt; - - /* - * Try non-existent, but valid partition, which may only exist after - * opening the device, like partitioned md devices. - */ - while (p > s && isdigit(p[-1])) - p--; - if (p == s || !*p || *p == '0') - return 0; - - /* try disk name without <part number> */ - part = simple_strtoul(p, NULL, 10); - *p = '\0'; - devt = blk_lookup_devt(s, part); - if (devt) - return devt; - - /* try disk name without p<part number> */ - if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p') - return 0; - p[-1] = '\0'; - return blk_lookup_devt(s, part); -} -#endif /* CONFIG_BLOCK */ - -static dev_t devt_from_devnum(const char *name) -{ - unsigned maj, min, offset; - dev_t devt = 0; - char *p, dummy; - - if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 || - sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) { - devt = MKDEV(maj, min); - if (maj != MAJOR(devt) || min != MINOR(devt)) - return 0; - } else { - devt = new_decode_dev(simple_strtoul(name, &p, 16)); - if (*p) - return 0; - } - - return devt; -} - -/* - * Convert a name into device number. We accept the following variants: - * - * 1) <hex_major><hex_minor> device number in hexadecimal represents itself - * no leading 0x, for example b302. - * 2) /dev/nfs represents Root_NFS (0xff) - * 3) /dev/<disk_name> represents the device number of disk - * 4) /dev/<disk_name><decimal> represents the device number - * of partition - device number of disk plus the partition number - * 5) /dev/<disk_name>p<decimal> - same as the above, that form is - * used when disk name of partitioned disk ends on a digit. - * 6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the - * unique id of a partition if the partition table provides it. - * The UUID may be either an EFI/GPT UUID, or refer to an MSDOS - * partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero- - * filled hex representation of the 32-bit "NT disk signature", and PP - * is a zero-filled hex representation of the 1-based partition number. - * 7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to - * a partition with a known unique id. - * 8) <major>:<minor> major and minor number of the device separated by - * a colon. - * 9) PARTLABEL=<name> with name being the GPT partition label. - * MSDOS partitions do not support labels! - * 10) /dev/cifs represents Root_CIFS (0xfe) - * - * If name doesn't have fall into the categories above, we return (0,0). - * block_class is used to check if something is a disk name. If the disk - * name contains slashes, the device name has them replaced with - * bangs. - */ -dev_t name_to_dev_t(const char *name) -{ - if (strcmp(name, "/dev/nfs") == 0) - return Root_NFS; - if (strcmp(name, "/dev/cifs") == 0) - return Root_CIFS; - if (strcmp(name, "/dev/ram") == 0) - return Root_RAM0; -#ifdef CONFIG_BLOCK - if (strncmp(name, "PARTUUID=", 9) == 0) - return devt_from_partuuid(name + 9); - if (strncmp(name, "PARTLABEL=", 10) == 0) - return devt_from_partlabel(name + 10); - if (strncmp(name, "/dev/", 5) == 0) - return devt_from_devname(name + 5); -#endif - return devt_from_devnum(name); -} -EXPORT_SYMBOL_GPL(name_to_dev_t); - static int __init root_dev_setup(char *line) { strscpy(saved_root_name, line, sizeof(saved_root_name)); @@ -391,7 +156,7 @@ out: return ret; } -void __init mount_block_root(char *name, int flags) +void __init mount_root_generic(char *name, char *pretty_name, int flags) { struct page *page = alloc_page(GFP_KERNEL); char *fs_names = page_address(page); @@ -425,7 +190,7 @@ retry: * and give them a list of the available devices */ printk("VFS: Cannot open root device \"%s\" or %s: error %d\n", - root_device_name, b, err); + pretty_name, b, err); printk("Please append a correct \"root=\" boot option; here are the available partitions:\n"); printk_all_partitions(); @@ -453,15 +218,14 @@ out: #define NFSROOT_TIMEOUT_MAX 30 #define NFSROOT_RETRY_MAX 5 -static int __init mount_nfs_root(void) +static void __init mount_nfs_root(void) { char *root_dev, *root_data; unsigned int timeout; - int try, err; + int try; - err = nfs_root_data(&root_dev, &root_data); - if (err != 0) - return 0; + if (nfs_root_data(&root_dev, &root_data)) + goto fail; /* * The server or network may not be ready, so try several @@ -470,10 +234,8 @@ static int __init mount_nfs_root(void) */ timeout = NFSROOT_TIMEOUT_MIN; for (try = 1; ; try++) { - err = do_mount_root(root_dev, "nfs", - root_mountflags, root_data); - if (err == 0) - return 1; + if (!do_mount_root(root_dev, "nfs", root_mountflags, root_data)) + return; if (try > NFSROOT_RETRY_MAX) break; @@ -483,9 +245,14 @@ static int __init mount_nfs_root(void) if (timeout > NFSROOT_TIMEOUT_MAX) timeout = NFSROOT_TIMEOUT_MAX; } - return 0; +fail: + pr_err("VFS: Unable to mount root fs via NFS.\n"); +} +#else +static inline void mount_nfs_root(void) +{ } -#endif +#endif /* CONFIG_ROOT_NFS */ #ifdef CONFIG_CIFS_ROOT @@ -495,22 +262,20 @@ extern int cifs_root_data(char **dev, char **opts); #define CIFSROOT_TIMEOUT_MAX 30 #define CIFSROOT_RETRY_MAX 5 -static int __init mount_cifs_root(void) +static void __init mount_cifs_root(void) { char *root_dev, *root_data; unsigned int timeout; - int try, err; + int try; - err = cifs_root_data(&root_dev, &root_data); - if (err != 0) - return 0; + if (cifs_root_data(&root_dev, &root_data)) + goto fail; timeout = CIFSROOT_TIMEOUT_MIN; for (try = 1; ; try++) { - err = do_mount_root(root_dev, "cifs", root_mountflags, - root_data); - if (err == 0) - return 1; + if (!do_mount_root(root_dev, "cifs", root_mountflags, + root_data)) + return; if (try > CIFSROOT_RETRY_MAX) break; @@ -519,9 +284,14 @@ static int __init mount_cifs_root(void) if (timeout > CIFSROOT_TIMEOUT_MAX) timeout = CIFSROOT_TIMEOUT_MAX; } - return 0; +fail: + pr_err("VFS: Unable to mount root fs via SMB.\n"); } -#endif +#else +static inline void mount_cifs_root(void) +{ +} +#endif /* CONFIG_CIFS_ROOT */ static bool __init fs_is_nodev(char *fstype) { @@ -536,7 +306,7 @@ static bool __init fs_is_nodev(char *fstype) return ret; } -static int __init mount_nodev_root(void) +static int __init mount_nodev_root(char *root_device_name) { char *fs_names, *fstype; int err = -EINVAL; @@ -563,35 +333,84 @@ static int __init mount_nodev_root(void) return err; } -void __init mount_root(void) +#ifdef CONFIG_BLOCK +static void __init mount_block_root(char *root_device_name) { -#ifdef CONFIG_ROOT_NFS - if (ROOT_DEV == Root_NFS) { - if (!mount_nfs_root()) - printk(KERN_ERR "VFS: Unable to mount root fs via NFS.\n"); - return; + int err = create_dev("/dev/root", ROOT_DEV); + + if (err < 0) + pr_emerg("Failed to create /dev/root: %d\n", err); + mount_root_generic("/dev/root", root_device_name, root_mountflags); +} +#else +static inline void mount_block_root(char *root_device_name) +{ +} +#endif /* CONFIG_BLOCK */ + +void __init mount_root(char *root_device_name) +{ + switch (ROOT_DEV) { + case Root_NFS: + mount_nfs_root(); + break; + case Root_CIFS: + mount_cifs_root(); + break; + case Root_Generic: + mount_root_generic(root_device_name, root_device_name, + root_mountflags); + break; + case 0: + if (root_device_name && root_fs_names && + mount_nodev_root(root_device_name) == 0) + break; + fallthrough; + default: + mount_block_root(root_device_name); + break; } -#endif -#ifdef CONFIG_CIFS_ROOT - if (ROOT_DEV == Root_CIFS) { - if (!mount_cifs_root()) - printk(KERN_ERR "VFS: Unable to mount root fs via SMB.\n"); +} + +/* wait for any asynchronous scanning to complete */ +static void __init wait_for_root(char *root_device_name) +{ + if (ROOT_DEV != 0) return; - } -#endif - if (ROOT_DEV == 0 && root_device_name && root_fs_names) { - if (mount_nodev_root() == 0) - return; - } -#ifdef CONFIG_BLOCK - { - int err = create_dev("/dev/root", ROOT_DEV); - if (err < 0) - pr_emerg("Failed to create /dev/root: %d\n", err); - mount_block_root("/dev/root", root_mountflags); + pr_info("Waiting for root device %s...\n", root_device_name); + + while (!driver_probe_done() || + early_lookup_bdev(root_device_name, &ROOT_DEV) < 0) + msleep(5); + async_synchronize_full(); + +} + +static dev_t __init parse_root_device(char *root_device_name) +{ + int error; + dev_t dev; + + if (!strncmp(root_device_name, "mtd", 3) || + !strncmp(root_device_name, "ubi", 3)) + return Root_Generic; + if (strcmp(root_device_name, "/dev/nfs") == 0) + return Root_NFS; + if (strcmp(root_device_name, "/dev/cifs") == 0) + return Root_CIFS; + if (strcmp(root_device_name, "/dev/ram") == 0) + return Root_RAM0; + + error = early_lookup_bdev(root_device_name, &dev); + if (error) { + if (error == -EINVAL && root_wait) { + pr_err("Disabling rootwait; root= is invalid.\n"); + root_wait = 0; + } + return 0; } -#endif + return dev; } /* @@ -616,32 +435,15 @@ void __init prepare_namespace(void) md_run_setup(); - if (saved_root_name[0]) { - root_device_name = saved_root_name; - if (!strncmp(root_device_name, "mtd", 3) || - !strncmp(root_device_name, "ubi", 3)) { - mount_block_root(root_device_name, root_mountflags); - goto out; - } - ROOT_DEV = name_to_dev_t(root_device_name); - if (strncmp(root_device_name, "/dev/", 5) == 0) - root_device_name += 5; - } + if (saved_root_name[0]) + ROOT_DEV = parse_root_device(saved_root_name); - if (initrd_load()) + if (initrd_load(saved_root_name)) goto out; - /* wait for any asynchronous scanning to complete */ - if ((ROOT_DEV == 0) && root_wait) { - printk(KERN_INFO "Waiting for root device %s...\n", - saved_root_name); - while (driver_probe_done() != 0 || - (ROOT_DEV = name_to_dev_t(saved_root_name)) == 0) - msleep(5); - async_synchronize_full(); - } - - mount_root(); + if (root_wait) + wait_for_root(saved_root_name); + mount_root(saved_root_name); out: devtmpfs_mount(); init_mount(".", "/", NULL, MS_MOVE, NULL); diff --git a/init/do_mounts.h b/init/do_mounts.h index 7a29ac3e427b..15e372b00ce7 100644 --- a/init/do_mounts.h +++ b/init/do_mounts.h @@ -10,8 +10,8 @@ #include <linux/root_dev.h> #include <linux/init_syscalls.h> -void mount_block_root(char *name, int flags); -void mount_root(void); +void mount_root_generic(char *name, char *pretty_name, int flags); +void mount_root(char *root_device_name); extern int root_mountflags; static inline __init int create_dev(char *name, dev_t dev) @@ -33,11 +33,11 @@ static inline int rd_load_image(char *from) { return 0; } #endif #ifdef CONFIG_BLK_DEV_INITRD - -bool __init initrd_load(void); - +bool __init initrd_load(char *root_device_name); #else - -static inline bool initrd_load(void) { return false; } +static inline bool initrd_load(char *root_device_name) +{ + return false; + } #endif diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 34731241377d..425f4bcf4b77 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -83,7 +83,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new) return 0; } -static void __init handle_initrd(void) +static void __init handle_initrd(char *root_device_name) { struct subprocess_info *info; static char *argv[] = { "linuxrc", NULL, }; @@ -95,7 +95,8 @@ static void __init handle_initrd(void) real_root_dev = new_encode_dev(ROOT_DEV); create_dev("/dev/root.old", Root_RAM0); /* mount initrd on rootfs' /root */ - mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY); + mount_root_generic("/dev/root.old", root_device_name, + root_mountflags & ~MS_RDONLY); init_mkdir("/old", 0700); init_chdir("/old"); @@ -117,7 +118,7 @@ static void __init handle_initrd(void) init_chdir("/"); ROOT_DEV = new_decode_dev(real_root_dev); - mount_root(); + mount_root(root_device_name); printk(KERN_NOTICE "Trying to move old root to /initrd ... "); error = init_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL); @@ -133,7 +134,7 @@ static void __init handle_initrd(void) } } -bool __init initrd_load(void) +bool __init initrd_load(char *root_device_name) { if (mount_initrd) { create_dev("/dev/ram", Root_RAM0); @@ -145,7 +146,7 @@ bool __init initrd_load(void) */ if (rd_load_image("/initrd.image") && ROOT_DEV != Root_RAM0) { init_unlink("/initrd.image"); - handle_initrd(); + handle_initrd(root_device_name); return true; } } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 30d1274f03f6..f62e89d0d906 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -11,6 +11,7 @@ #define pr_fmt(fmt) "PM: hibernation: " fmt +#include <linux/blkdev.h> #include <linux/export.h> #include <linux/suspend.h> #include <linux/reboot.h> @@ -64,7 +65,6 @@ enum { static int hibernation_mode = HIBERNATION_SHUTDOWN; bool freezer_test_done; -bool snapshot_test; static const struct platform_hibernation_ops *hibernation_ops; @@ -684,26 +684,22 @@ static void power_down(void) cpu_relax(); } -static int load_image_and_restore(void) +static int load_image_and_restore(bool snapshot_test) { int error; unsigned int flags; - fmode_t mode = FMODE_READ; - - if (snapshot_test) - mode |= FMODE_EXCL; pm_pr_dbg("Loading hibernation image.\n"); lock_device_hotplug(); error = create_basic_memory_bitmaps(); if (error) { - swsusp_close(mode); + swsusp_close(snapshot_test); goto Unlock; } error = swsusp_read(&flags); - swsusp_close(mode); + swsusp_close(snapshot_test); if (!error) error = hibernation_restore(flags & SF_PLATFORM_MODE); @@ -721,6 +717,7 @@ static int load_image_and_restore(void) */ int hibernate(void) { + bool snapshot_test = false; unsigned int sleep_flags; int error; @@ -748,9 +745,6 @@ int hibernate(void) if (error) goto Exit; - /* protected by system_transition_mutex */ - snapshot_test = false; - lock_device_hotplug(); /* Allocate memory management structures */ error = create_basic_memory_bitmaps(); @@ -792,9 +786,9 @@ int hibernate(void) unlock_device_hotplug(); if (snapshot_test) { pm_pr_dbg("Checking hibernation image\n"); - error = swsusp_check(); + error = swsusp_check(snapshot_test); if (!error) - error = load_image_and_restore(); + error = load_image_and_restore(snapshot_test); } thaw_processes(); @@ -910,52 +904,10 @@ unlock: } EXPORT_SYMBOL_GPL(hibernate_quiet_exec); -/** - * software_resume - Resume from a saved hibernation image. - * - * This routine is called as a late initcall, when all devices have been - * discovered and initialized already. - * - * The image reading code is called to see if there is a hibernation image - * available for reading. If that is the case, devices are quiesced and the - * contents of memory is restored from the saved image. - * - * If this is successful, control reappears in the restored target kernel in - * hibernation_snapshot() which returns to hibernate(). Otherwise, the routine - * attempts to recover gracefully and make the kernel return to the normal mode - * of operation. - */ -static int software_resume(void) +static int __init find_resume_device(void) { - int error; - - /* - * If the user said "noresume".. bail out early. - */ - if (noresume || !hibernation_available()) - return 0; - - /* - * name_to_dev_t() below takes a sysfs buffer mutex when sysfs - * is configured into the kernel. Since the regular hibernate - * trigger path is via sysfs which takes a buffer mutex before - * calling hibernate functions (which take system_transition_mutex) - * this can cause lockdep to complain about a possible ABBA deadlock - * which cannot happen since we're in the boot code here and - * sysfs can't be invoked yet. Therefore, we use a subclass - * here to avoid lockdep complaining. - */ - mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING); - - snapshot_test = false; - - if (swsusp_resume_device) - goto Check_image; - - if (!strlen(resume_file)) { - error = -ENOENT; - goto Unlock; - } + if (!strlen(resume_file)) + return -ENOENT; pm_pr_dbg("Checking hibernation image partition %s\n", resume_file); @@ -966,40 +918,41 @@ static int software_resume(void) } /* Check if the device is there */ - swsusp_resume_device = name_to_dev_t(resume_file); - if (!swsusp_resume_device) { - /* - * Some device discovery might still be in progress; we need - * to wait for this to finish. - */ - wait_for_device_probe(); - - if (resume_wait) { - while ((swsusp_resume_device = name_to_dev_t(resume_file)) == 0) - msleep(10); - async_synchronize_full(); - } + if (!early_lookup_bdev(resume_file, &swsusp_resume_device)) + return 0; - swsusp_resume_device = name_to_dev_t(resume_file); - if (!swsusp_resume_device) { - error = -ENODEV; - goto Unlock; - } + /* + * Some device discovery might still be in progress; we need to wait for + * this to finish. + */ + wait_for_device_probe(); + if (resume_wait) { + while (early_lookup_bdev(resume_file, &swsusp_resume_device)) + msleep(10); + async_synchronize_full(); } - Check_image: + return early_lookup_bdev(resume_file, &swsusp_resume_device); +} + +static int software_resume(void) +{ + int error; + pm_pr_dbg("Hibernation image partition %d:%d present\n", MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); pm_pr_dbg("Looking for hibernation image.\n"); - error = swsusp_check(); + + mutex_lock(&system_transition_mutex); + error = swsusp_check(false); if (error) goto Unlock; /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; - swsusp_close(FMODE_READ | FMODE_EXCL); + swsusp_close(false); goto Unlock; } @@ -1020,7 +973,7 @@ static int software_resume(void) goto Close_Finish; } - error = load_image_and_restore(); + error = load_image_and_restore(false); thaw_processes(); Finish: pm_notifier_call_chain(PM_POST_RESTORE); @@ -1034,11 +987,43 @@ static int software_resume(void) pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); return error; Close_Finish: - swsusp_close(FMODE_READ | FMODE_EXCL); + swsusp_close(false); goto Finish; } -late_initcall_sync(software_resume); +/** + * software_resume_initcall - Resume from a saved hibernation image. + * + * This routine is called as a late initcall, when all devices have been + * discovered and initialized already. + * + * The image reading code is called to see if there is a hibernation image + * available for reading. If that is the case, devices are quiesced and the + * contents of memory is restored from the saved image. + * + * If this is successful, control reappears in the restored target kernel in + * hibernation_snapshot() which returns to hibernate(). Otherwise, the routine + * attempts to recover gracefully and make the kernel return to the normal mode + * of operation. + */ +static int __init software_resume_initcall(void) +{ + /* + * If the user said "noresume".. bail out early. + */ + if (noresume || !hibernation_available()) + return 0; + + if (!swsusp_resume_device) { + int error = find_resume_device(); + + if (error) + return error; + } + + return software_resume(); +} +late_initcall_sync(software_resume_initcall); static const char * const hibernation_modes[] = { @@ -1177,7 +1162,11 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, unsigned int sleep_flags; int len = n; char *name; - dev_t res; + dev_t dev; + int error; + + if (!hibernation_available()) + return 0; if (len && buf[len-1] == '\n') len--; @@ -1185,13 +1174,29 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, if (!name) return -ENOMEM; - res = name_to_dev_t(name); + error = lookup_bdev(name, &dev); + if (error) { + unsigned maj, min, offset; + char *p, dummy; + + if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 || + sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, + &dummy) == 3) { + dev = MKDEV(maj, min); + if (maj != MAJOR(dev) || min != MINOR(dev)) + error = -EINVAL; + } else { + dev = new_decode_dev(simple_strtoul(name, &p, 16)); + if (*p) + error = -EINVAL; + } + } kfree(name); - if (!res) - return -EINVAL; + if (error) + return error; sleep_flags = lock_system_sleep(); - swsusp_resume_device = res; + swsusp_resume_device = dev; unlock_system_sleep(sleep_flags); pm_pr_dbg("Configured hibernation resume from disk to %u\n", diff --git a/kernel/power/power.h b/kernel/power/power.h index b83c8d5e188d..a8e0c44b804e 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -59,7 +59,6 @@ asmlinkage int swsusp_save(void); /* kernel/power/hibernate.c */ extern bool freezer_test_done; -extern bool snapshot_test; extern int hibernation_snapshot(int platform_mode); extern int hibernation_restore(int platform_mode); @@ -174,11 +173,11 @@ extern int swsusp_swap_in_use(void); #define SF_HW_SIG 8 /* kernel/power/hibernate.c */ -extern int swsusp_check(void); +int swsusp_check(bool snapshot_test); extern void swsusp_free(void); extern int swsusp_read(unsigned int *flags_p); extern int swsusp_write(unsigned int flags); -extern void swsusp_close(fmode_t); +void swsusp_close(bool snapshot_test); #ifdef CONFIG_SUSPEND extern int swsusp_unmark(void); #endif diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 92e41ed292ad..f6ebcd00c410 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -356,14 +356,14 @@ static int swsusp_swap_check(void) return res; root_swap = res; - hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, FMODE_WRITE, - NULL); + hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, + BLK_OPEN_WRITE, NULL, NULL); if (IS_ERR(hib_resume_bdev)) return PTR_ERR(hib_resume_bdev); res = set_blocksize(hib_resume_bdev, PAGE_SIZE); if (res < 0) - blkdev_put(hib_resume_bdev, FMODE_WRITE); + blkdev_put(hib_resume_bdev, NULL); return res; } @@ -443,7 +443,7 @@ static int get_swap_writer(struct swap_map_handle *handle) err_rel: release_swap_writer(handle); err_close: - swsusp_close(FMODE_WRITE); + swsusp_close(false); return ret; } @@ -508,7 +508,7 @@ static int swap_writer_finish(struct swap_map_handle *handle, if (error) free_all_swap_pages(root_swap); release_swap_writer(handle); - swsusp_close(FMODE_WRITE); + swsusp_close(false); return error; } @@ -1510,21 +1510,19 @@ end: return error; } +static void *swsusp_holder; + /** * swsusp_check - Check for swsusp signature in the resume device */ -int swsusp_check(void) +int swsusp_check(bool snapshot_test) { + void *holder = snapshot_test ? &swsusp_holder : NULL; int error; - void *holder; - fmode_t mode = FMODE_READ; - if (snapshot_test) - mode |= FMODE_EXCL; - - hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, - mode, &holder); + hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, BLK_OPEN_READ, + holder, NULL); if (!IS_ERR(hib_resume_bdev)) { set_blocksize(hib_resume_bdev, PAGE_SIZE); clear_page(swsusp_header); @@ -1551,7 +1549,7 @@ int swsusp_check(void) put: if (error) - blkdev_put(hib_resume_bdev, mode); + blkdev_put(hib_resume_bdev, holder); else pr_debug("Image signature found, resuming\n"); } else { @@ -1568,14 +1566,14 @@ put: * swsusp_close - close swap device. */ -void swsusp_close(fmode_t mode) +void swsusp_close(bool snapshot_test) { if (IS_ERR(hib_resume_bdev)) { pr_debug("Image device not initialised\n"); return; } - blkdev_put(hib_resume_bdev, mode); + blkdev_put(hib_resume_bdev, snapshot_test ? &swsusp_holder : NULL); } /** diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f18138e0292a..b667b1e2f688 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1082,8 +1082,7 @@ static struct page *first_bvec_segment(const struct iov_iter *i, static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, - unsigned int maxpages, size_t *start, - iov_iter_extraction_t extraction_flags) + unsigned int maxpages, size_t *start) { unsigned int n, gup_flags = 0; @@ -1093,8 +1092,6 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, return 0; if (maxsize > MAX_RW_COUNT) maxsize = MAX_RW_COUNT; - if (extraction_flags & ITER_ALLOW_P2PDMA) - gup_flags |= FOLL_PCI_P2PDMA; if (likely(user_backed_iter(i))) { unsigned long addr; @@ -1144,49 +1141,31 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, return -EFAULT; } -ssize_t iov_iter_get_pages(struct iov_iter *i, - struct page **pages, size_t maxsize, unsigned maxpages, - size_t *start, iov_iter_extraction_t extraction_flags) +ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, + size_t maxsize, unsigned maxpages, size_t *start) { if (!maxpages) return 0; BUG_ON(!pages); - return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, - start, extraction_flags); -} -EXPORT_SYMBOL_GPL(iov_iter_get_pages); - -ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, - size_t maxsize, unsigned maxpages, size_t *start) -{ - return iov_iter_get_pages(i, pages, maxsize, maxpages, start, 0); + return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, start); } EXPORT_SYMBOL(iov_iter_get_pages2); -ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, - struct page ***pages, size_t maxsize, - size_t *start, iov_iter_extraction_t extraction_flags) +ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, + struct page ***pages, size_t maxsize, size_t *start) { ssize_t len; *pages = NULL; - len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start, - extraction_flags); + len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start); if (len <= 0) { kvfree(*pages); *pages = NULL; } return len; } -EXPORT_SYMBOL_GPL(iov_iter_get_pages_alloc); - -ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, - struct page ***pages, size_t maxsize, size_t *start) -{ - return iov_iter_get_pages_alloc(i, pages, maxsize, start, 0); -} EXPORT_SYMBOL(iov_iter_get_pages_alloc2); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, diff --git a/lib/raid6/neon.h b/lib/raid6/neon.h new file mode 100644 index 000000000000..2ca41ee9b499 --- /dev/null +++ b/lib/raid6/neon.h @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only + +void raid6_neon1_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs); +void raid6_neon1_xor_syndrome_real(int disks, int start, int stop, + unsigned long bytes, void **ptrs); +void raid6_neon2_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs); +void raid6_neon2_xor_syndrome_real(int disks, int start, int stop, + unsigned long bytes, void **ptrs); +void raid6_neon4_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs); +void raid6_neon4_xor_syndrome_real(int disks, int start, int stop, + unsigned long bytes, void **ptrs); +void raid6_neon8_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs); +void raid6_neon8_xor_syndrome_real(int disks, int start, int stop, + unsigned long bytes, void **ptrs); +void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp, + uint8_t *dq, const uint8_t *pbmul, + const uint8_t *qmul); + +void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq, + const uint8_t *qmul); + + diff --git a/lib/raid6/neon.uc b/lib/raid6/neon.uc index b7c68030da4f..355270af0cd6 100644 --- a/lib/raid6/neon.uc +++ b/lib/raid6/neon.uc @@ -25,6 +25,7 @@ */ #include <arm_neon.h> +#include "neon.h" typedef uint8x16_t unative_t; diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c index d6fba8bf8c0a..1bfc14174d4d 100644 --- a/lib/raid6/recov_neon.c +++ b/lib/raid6/recov_neon.c @@ -8,6 +8,7 @@ #ifdef __KERNEL__ #include <asm/neon.h> +#include "neon.h" #else #define kernel_neon_begin() #define kernel_neon_end() @@ -19,13 +20,6 @@ static int raid6_has_neon(void) return cpu_has_neon(); } -void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp, - uint8_t *dq, const uint8_t *pbmul, - const uint8_t *qmul); - -void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq, - const uint8_t *qmul); - static void raid6_2data_recov_neon(int disks, size_t bytes, int faila, int failb, void **ptrs) { diff --git a/lib/raid6/recov_neon_inner.c b/lib/raid6/recov_neon_inner.c index 90eb80d43790..f9e7e8f5a151 100644 --- a/lib/raid6/recov_neon_inner.c +++ b/lib/raid6/recov_neon_inner.c @@ -5,6 +5,7 @@ */ #include <arm_neon.h> +#include "neon.h" #ifdef CONFIG_ARM /* @@ -51,7 +51,8 @@ static inline void sanity_check_pinned_pages(struct page **pages, struct page *page = *pages; struct folio *folio = page_folio(page); - if (!folio_test_anon(folio)) + if (is_zero_page(page) || + !folio_test_anon(folio)) continue; if (!folio_test_large(folio) || folio_test_hugetlb(folio)) VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); @@ -132,6 +133,13 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) struct folio *folio; /* + * Don't take a pin on the zero page - it's not going anywhere + * and it is used in a *lot* of places. + */ + if (is_zero_page(page)) + return page_folio(page); + + /* * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a * right zone, so fail and let the caller fall back to the slow * path. @@ -180,6 +188,8 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { + if (is_zero_folio(folio)) + return; node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) atomic_sub(refs, &folio->_pincount); @@ -225,6 +235,13 @@ int __must_check try_grab_page(struct page *page, unsigned int flags) folio_ref_inc(folio); else if (flags & FOLL_PIN) { /* + * Don't take a pin on the zero page - it's not going anywhere + * and it is used in a *lot* of places. + */ + if (is_zero_page(page)) + return 0; + + /* * Similar to try_grab_folio(): be sure to *also* * increment the normal page refcount field at least once, * so that the page really is pinned. @@ -258,6 +275,33 @@ void unpin_user_page(struct page *page) } EXPORT_SYMBOL(unpin_user_page); +/** + * folio_add_pin - Try to get an additional pin on a pinned folio + * @folio: The folio to be pinned + * + * Get an additional pin on a folio we already have a pin on. Makes no change + * if the folio is a zero_page. + */ +void folio_add_pin(struct folio *folio) +{ + if (is_zero_folio(folio)) + return; + + /* + * Similar to try_grab_folio(): be sure to *also* increment the normal + * page refcount field at least once, so that the page really is + * pinned. + */ + if (folio_test_large(folio)) { + WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1); + folio_ref_inc(folio); + atomic_inc(&folio->_pincount); + } else { + WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS); + folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); + } +} + static inline struct folio *gup_folio_range_next(struct page *start, unsigned long npages, unsigned long i, unsigned int *ntails) { @@ -3079,6 +3123,9 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast); * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for further details. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page() will not remove pins from it. */ int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) @@ -3110,6 +3157,9 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast); * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, @@ -3143,6 +3193,9 @@ EXPORT_SYMBOL(pin_user_pages_remote); * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, @@ -3161,6 +3214,9 @@ EXPORT_SYMBOL(pin_user_pages); * pin_user_pages_unlocked() is the FOLL_PIN variant of * get_user_pages_unlocked(). Behavior is the same, except that this one sets * FOLL_PIN and rejects FOLL_GET. + * + * Note that if a zero_page is amongst the returned pages, it will not have + * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) diff --git a/mm/page_io.c b/mm/page_io.c index 87b682d18850..684cd3c7b59b 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -338,7 +338,7 @@ static void swap_writepage_bdev_sync(struct page *page, bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc)); bio.bi_iter.bi_sector = swap_page_sector(page); - bio_add_page(&bio, page, thp_size(page), 0); + __bio_add_page(&bio, page, thp_size(page), 0); bio_associate_blkg_from_page(&bio, page); count_swpout_vm_event(page); @@ -360,7 +360,7 @@ static void swap_writepage_bdev_async(struct page *page, GFP_NOIO); bio->bi_iter.bi_sector = swap_page_sector(page); bio->bi_end_io = end_swap_bio_write; - bio_add_page(bio, page, thp_size(page), 0); + __bio_add_page(bio, page, thp_size(page), 0); bio_associate_blkg_from_page(bio, page); count_swpout_vm_event(page); @@ -468,7 +468,7 @@ static void swap_readpage_bdev_sync(struct page *page, bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ); bio.bi_iter.bi_sector = swap_page_sector(page); - bio_add_page(&bio, page, thp_size(page), 0); + __bio_add_page(&bio, page, thp_size(page), 0); /* * Keep this task valid during swap readpage because the oom killer may * attempt to access it in the page fault retry time check. @@ -488,7 +488,7 @@ static void swap_readpage_bdev_async(struct page *page, bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL); bio->bi_iter.bi_sector = swap_page_sector(page); bio->bi_end_io = end_swap_bio_read; - bio_add_page(bio, page, thp_size(page), 0); + __bio_add_page(bio, page, thp_size(page), 0); count_vm_event(PSWPIN); submit_bio(bio); } diff --git a/mm/swapfile.c b/mm/swapfile.c index 274bbf797480..6bc83060df9a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2539,7 +2539,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, old_block_size); - blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(bdev, p); } inode_lock(inode); @@ -2770,7 +2770,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) if (S_ISBLK(inode->i_mode)) { p->bdev = blkdev_get_by_dev(inode->i_rdev, - FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); + BLK_OPEN_READ | BLK_OPEN_WRITE, p, NULL); if (IS_ERR(p->bdev)) { error = PTR_ERR(p->bdev); p->bdev = NULL; @@ -3221,7 +3221,7 @@ bad_swap: p->cluster_next_cpu = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); - blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + blkdev_put(p->bdev, p); } inode = NULL; destroy_swap_extents(p); |