From ee6a129dffe10ae30b45b5a744e7c0a056291d13 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 28 Nov 2019 15:48:10 +0100 Subject: compat_ioctl: block: add blkdev_compat_ptr_ioctl A lot of block drivers need only a trivial .compat_ioctl callback. Add a helper function that can be set as the callback pointer to only convert the argument using the compat_ptr() conversion and otherwise assume all input and output data is compatible, or handled using in_compat_syscall() checks. This mirrors the compat_ptr_ioctl() helper function used in character devices. Reviewed-by: Ben Hutchings Signed-off-by: Arnd Bergmann --- include/linux/blkdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 47eb22a3b7f9..3e0408618da7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1711,6 +1711,13 @@ struct block_device_operations { const struct pr_ops *pr_ops; }; +#ifdef CONFIG_COMPAT +extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, + unsigned int, unsigned long); +#else +#define blkdev_compat_ptr_ioctl NULL +#endif + extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); extern int bdev_read_page(struct block_device *, sector_t, struct page *); -- cgit v1.2.3-71-gd317 From ad6bf88a6c19a39fb3b0045d78ea880325dfcf15 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 15 Jan 2020 08:35:25 -0500 Subject: block: fix an integer overflow in logical block size Logical block size has type unsigned short. That means that it can be at most 32768. However, there are architectures that can run with 64k pages (for example arm64) and on these architectures, it may be possible to create block devices with 64k block size. For exmaple (run this on an architecture with 64k pages): Mount will fail with this error because it tries to read the superblock using 2-sector access: device-mapper: writecache: I/O is not aligned, sector 2, size 1024, block size 65536 EXT4-fs (dm-0): unable to read superblock This patch changes the logical block size from unsigned short to unsigned int to avoid the overflow. Cc: stable@vger.kernel.org Reviewed-by: Martin K. Petersen Reviewed-by: Ming Lei Signed-off-by: Mikulas Patocka Signed-off-by: Jens Axboe --- block/blk-settings.c | 2 +- drivers/md/dm-snap-persistent.c | 2 +- drivers/md/raid0.c | 2 +- include/linux/blkdev.h | 8 ++++---- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 5f6dcc7a47bd..c8eda2e7b91e 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -328,7 +328,7 @@ EXPORT_SYMBOL(blk_queue_max_segment_size); * storage device can address. The default of 512 covers most * hardware. **/ -void blk_queue_logical_block_size(struct request_queue *q, unsigned short size) +void blk_queue_logical_block_size(struct request_queue *q, unsigned int size) { q->limits.logical_block_size = size; diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 3c50c4e4da8f..963d3774c93e 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -17,7 +17,7 @@ #include #define DM_MSG_PREFIX "persistent snapshot" -#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32 /* 16KB */ +#define DM_CHUNK_SIZE_DEFAULT_SECTORS 32U /* 16KB */ #define DM_PREFETCH_CHUNKS 12 diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index b7c20979bd19..322386ff5d22 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -87,7 +87,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) char b[BDEVNAME_SIZE]; char b2[BDEVNAME_SIZE]; struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL); - unsigned short blksize = 512; + unsigned blksize = 512; *private_conf = ERR_PTR(-ENOMEM); if (!conf) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 47eb22a3b7f9..4c636c42ad68 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -328,6 +328,7 @@ struct queue_limits { unsigned int max_sectors; unsigned int max_segment_size; unsigned int physical_block_size; + unsigned int logical_block_size; unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; @@ -338,7 +339,6 @@ struct queue_limits { unsigned int discard_granularity; unsigned int discard_alignment; - unsigned short logical_block_size; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; @@ -1077,7 +1077,7 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); -extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); +extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); @@ -1291,7 +1291,7 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned short queue_logical_block_size(const struct request_queue *q) +static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; @@ -1301,7 +1301,7 @@ static inline unsigned short queue_logical_block_size(const struct request_queue return retval; } -static inline unsigned short bdev_logical_block_size(struct block_device *bdev) +static inline unsigned int bdev_logical_block_size(struct block_device *bdev) { return queue_logical_block_size(bdev_get_queue(bdev)); } -- cgit v1.2.3-71-gd317 From c780e86dd48ef6467a1146cf7d0fe1e05a635039 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 6 Feb 2020 15:28:12 +0100 Subject: blktrace: Protect q->blk_trace with RCU KASAN is reporting that __blk_add_trace() has a use-after-free issue when accessing q->blk_trace. Indeed the switching of block tracing (and thus eventual freeing of q->blk_trace) is completely unsynchronized with the currently running tracing and thus it can happen that the blk_trace structure is being freed just while __blk_add_trace() works on it. Protect accesses to q->blk_trace by RCU during tracing and make sure we wait for the end of RCU grace period when shutting down tracing. Luckily that is rare enough event that we can afford that. Note that postponing the freeing of blk_trace to an RCU callback should better be avoided as it could have unexpected user visible side-effects as debugfs files would be still existing for a short while block tracing has been shut down. Link: https://bugzilla.kernel.org/show_bug.cgi?id=205711 CC: stable@vger.kernel.org Reviewed-by: Chaitanya Kulkarni Reviewed-by: Ming Lei Tested-by: Ming Lei Reviewed-by: Bart Van Assche Reported-by: Tristan Madani Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- include/linux/blktrace_api.h | 18 +++++-- kernel/trace/blktrace.c | 114 +++++++++++++++++++++++++++++++------------ 3 files changed, 97 insertions(+), 37 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 053ea4b51988..10455b2bbbb4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -524,7 +524,7 @@ struct request_queue { unsigned int sg_reserved_size; int node; #ifdef CONFIG_BLK_DEV_IO_TRACE - struct blk_trace *blk_trace; + struct blk_trace __rcu *blk_trace; struct mutex blk_trace_mutex; #endif /* diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7bb2d8de9f30..3b6ff5902edc 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -51,9 +51,13 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f **/ #define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ do { \ - struct blk_trace *bt = (q)->blk_trace; \ + struct blk_trace *bt; \ + \ + rcu_read_lock(); \ + bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__) @@ -61,10 +65,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f static inline bool blk_trace_note_message_enabled(struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; - if (likely(!bt)) - return false; - return bt->act_mask & BLK_TC_NOTIFY; + struct blk_trace *bt; + bool ret; + + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + ret = bt && (bt->act_mask & BLK_TC_NOTIFY); + rcu_read_unlock(); + return ret; } extern void blk_add_driver_data(struct request_queue *q, struct request *rq, diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 0735ae8545d8..4560878f0bac 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -335,6 +335,7 @@ static void put_probe_ref(void) static void blk_trace_cleanup(struct blk_trace *bt) { + synchronize_rcu(); blk_trace_free(bt); put_probe_ref(); } @@ -629,8 +630,10 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (bt == NULL) return -EINVAL; @@ -740,8 +743,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) void blk_trace_shutdown(struct request_queue *q) { mutex_lock(&q->blk_trace_mutex); - - if (q->blk_trace) { + if (rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } @@ -752,8 +755,10 @@ void blk_trace_shutdown(struct request_queue *q) #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + /* We don't use the 'bt' value here except as an optimization... */ + bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; @@ -796,10 +801,14 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) static void blk_add_trace_rq(struct request *rq, int error, unsigned int nr_bytes, u32 what, u64 cgid) { - struct blk_trace *bt = rq->q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(rq->q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); @@ -808,6 +817,7 @@ static void blk_add_trace_rq(struct request *rq, int error, __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, error, 0, NULL, cgid); + rcu_read_unlock(); } static void blk_add_trace_rq_insert(void *ignore, @@ -853,14 +863,19 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq, static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, what, error, 0, NULL, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } static void blk_add_trace_bio_bounce(void *ignore, @@ -905,11 +920,14 @@ static void blk_add_trace_getrq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } @@ -921,27 +939,35 @@ static void blk_add_trace_sleeprq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } static void blk_add_trace_plug(void *ignore, struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); + rcu_read_unlock(); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; @@ -953,14 +979,17 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } + rcu_read_unlock(); } static void blk_add_trace_split(void *ignore, struct request_queue *q, struct bio *bio, unsigned int pdu) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu); @@ -969,6 +998,7 @@ static void blk_add_trace_split(void *ignore, BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), &rpdu, blk_trace_bio_get_cgid(q, bio)); } + rcu_read_unlock(); } /** @@ -988,11 +1018,15 @@ static void blk_add_trace_bio_remap(void *ignore, struct request_queue *q, struct bio *bio, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); @@ -1001,6 +1035,7 @@ static void blk_add_trace_bio_remap(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } /** @@ -1021,11 +1056,15 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); @@ -1034,6 +1073,7 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } /** @@ -1051,14 +1091,19 @@ void blk_add_driver_data(struct request_queue *q, struct request *rq, void *data, size_t len) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1597,6 +1642,7 @@ static int blk_trace_remove_queue(struct request_queue *q) return -EINVAL; put_probe_ref(); + synchronize_rcu(); blk_trace_free(bt); return 0; } @@ -1758,6 +1804,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct hd_struct *p = dev_to_part(dev); struct request_queue *q; struct block_device *bdev; + struct blk_trace *bt; ssize_t ret = -ENXIO; bdev = bdget(part_devt(p)); @@ -1770,21 +1817,23 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - ret = sprintf(buf, "%u\n", !!q->blk_trace); + ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; } - if (q->blk_trace == NULL) + if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) - ret = blk_trace_mask2str(buf, q->blk_trace->act_mask); + ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) - ret = sprintf(buf, "%u\n", q->blk_trace->pid); + ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba); + ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); + ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: mutex_unlock(&q->blk_trace_mutex); @@ -1801,6 +1850,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct block_device *bdev; struct request_queue *q; struct hd_struct *p; + struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; @@ -1831,8 +1881,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - if (!!value == !!q->blk_trace) { + if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } @@ -1844,18 +1896,18 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } ret = 0; - if (q->blk_trace == NULL) + if (bt == NULL) ret = blk_trace_setup_queue(q, bdev); if (ret == 0) { if (attr == &dev_attr_act_mask) - q->blk_trace->act_mask = value; + bt->act_mask = value; else if (attr == &dev_attr_pid) - q->blk_trace->pid = value; + bt->pid = value; else if (attr == &dev_attr_start_lba) - q->blk_trace->start_lba = value; + bt->start_lba = value; else if (attr == &dev_attr_end_lba) - q->blk_trace->end_lba = value; + bt->end_lba = value; } out_unlock_bdev: -- cgit v1.2.3-71-gd317 From e959e5405f34aa92d71d0dd162b969c21742061d Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Mon, 2 Mar 2020 14:24:08 +0100 Subject: block: Remove used kblockd_schedule_work_on() Commit ee63cfa7fc19 ("block: add kblockd_schedule_work_on()") introduced the helper in 2016. Remove it because since then no caller was added. Cc: Jens Axboe Signed-off-by: Daniel Wagner Signed-off-by: Jens Axboe --- block/blk-core.c | 6 ------ include/linux/blkdev.h | 1 - 2 files changed, 7 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 089e890ab208..60dc9552ef8d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1663,12 +1663,6 @@ int kblockd_schedule_work(struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); -int kblockd_schedule_work_on(int cpu, struct work_struct *work) -{ - return queue_work_on(cpu, kblockd_workqueue, work); -} -EXPORT_SYMBOL(kblockd_schedule_work_on); - int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 10455b2bbbb4..f629d40c645c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1494,7 +1494,6 @@ static inline void put_dev_sector(Sector p) } int kblockd_schedule_work(struct work_struct *work); -int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ -- cgit v1.2.3-71-gd317