From 5151412dd4338b273afdb107c3772528e9e67d92 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 23 Nov 2011 10:59:13 +0100 Subject: block: initialize request_queue's numa node during struct request_queue is allocated with __GFP_ZERO so its "node" field is zero before initialization. This causes an oops if node 0 is offline in the page allocator because its zonelists are not initialized. From Dave Young's dmesg: SRAT: Node 1 PXM 2 0-d0000000 SRAT: Node 1 PXM 2 100000000-330000000 SRAT: Node 0 PXM 1 330000000-630000000 Initmem setup node 1 0000000000000000-000000000affb000 ... Built 1 zonelists in Node order, mobility grouping on. ... BUG: unable to handle kernel paging request at 0000000000001c08 IP: [] __alloc_pages_nodemask+0xb5/0x870 and __alloc_pages_nodemask+0xb5 translates to a NULL pointer on zonelist->_zonerefs. The fix is to initialize q->node at the time of allocation so the correct node is passed to the slab allocator later. Since blk_init_allocated_queue_node() is no longer needed, merge it with blk_init_allocated_queue(). [rientjes@google.com: changelog, initializing q->node] Cc: stable@vger.kernel.org [2.6.37+] Reported-by: Dave Young Signed-off-by: Mike Snitzer Signed-off-by: David Rientjes Tested-by: Dave Young Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c7a6d3b5bc7b..94acd8172b5b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -805,9 +805,6 @@ extern void blk_unprep_request(struct request *); */ extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id); -extern struct request_queue *blk_init_allocated_queue_node(struct request_queue *, - request_fn_proc *, - spinlock_t *, int node_id); extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); extern struct request_queue *blk_init_allocated_queue(struct request_queue *, request_fn_proc *, spinlock_t *); -- cgit v1.2.3 From 1ba64edef6051d2ec79bb2fbd3a0c8f0df00ab55 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:37 +0100 Subject: block, sx8: kill blk_insert_request() The only user left for blk_insert_request() is sx8 and it can be trivially switched to use blk_execute_rq_nowait() - special requests aren't included in io stat and sx8 doesn't use block layer tagging. Switch sx8 and kill blk_insert_requeset(). This patch doesn't introduce any functional difference. Only compile tested. Signed-off-by: Tejun Heo Acked-by: Jeff Garzik Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c7a6d3b5bc7b..8a6b51b13a1c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -660,7 +660,6 @@ extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); extern struct request *blk_make_request(struct request_queue *, struct bio *, gfp_t); -extern void blk_insert_request(struct request_queue *, struct request *, int, void *); extern void blk_requeue_request(struct request_queue *, struct request *); extern void blk_add_request_payload(struct request *rq, struct page *page, unsigned int len); -- cgit v1.2.3 From 34f6055c80285e4efb3f602a9119db75239744dc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:37 +0100 Subject: block: add blk_queue_dead() There are a number of QUEUE_FLAG_DEAD tests. Add blk_queue_dead() macro and use it. This patch doesn't introduce any functional difference. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8a6b51b13a1c..783f97c14d0a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -481,6 +481,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) +#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) -- cgit v1.2.3 From a73f730d013ff2788389fd0c46ad3e5510f124e6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:37 +0100 Subject: block, cfq: move cfqd->cic_index to q->id cfq allocates per-queue id using ida and uses it to index cic radix tree from io_context. Move it to q->id and allocate on queue init and free on queue release. This simplifies cfq a bit and will allow for further improvements of io context life-cycle management. This patch doesn't introduce any functional difference. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 783f97c14d0a..8c8dbc4738ea 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -310,6 +310,12 @@ struct request_queue { */ unsigned long queue_flags; + /* + * ida allocated id for this queue. Used to index queues from + * ioctx. + */ + int id; + /* * queue needs bounce pages for pages above this limit */ -- cgit v1.2.3 From 09ac46c429464c919d04bb737b27edd84d944f02 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:38 +0100 Subject: block: misc updates to blk_get_queue() * blk_get_queue() is peculiar in that it returns 0 on success and 1 on failure instead of 0 / -errno or boolean. Update it such that it returns %true on success and %false on failure. * Make sure the caller checks for the return value. * Separate out __blk_get_queue() which doesn't check whether @q is dead and put it in blk.h. This will be used later. This patch doesn't introduce any functional changes. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8c8dbc4738ea..d1b6f4ed1f96 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -865,7 +865,7 @@ extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatte extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); -int blk_get_queue(struct request_queue *); +bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(gfp_t); struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); -- cgit v1.2.3 From b2efa05265d62bc29f3a64400fad4b44340eedb8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:39 +0100 Subject: block, cfq: unlink cfq_io_context's immediately cic is association between io_context and request_queue. A cic is linked from both ioc and q and should be destroyed when either one goes away. As ioc and q both have their own locks, locking becomes a bit complex - both orders work for removal from one but not from the other. Currently, cfq tries to circumvent this locking order issue with RCU. ioc->lock nests inside queue_lock but the radix tree and cic's are also protected by RCU allowing either side to walk their lists without grabbing lock. This rather unconventional use of RCU quickly devolves into extremely fragile convolution. e.g. The following is from cfqd going away too soon after ioc and q exits raced. general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: [ 88.503444] Pid: 599, comm: hexdump Not tainted 3.1.0-rc10-work+ #158 Bochs Bochs RIP: 0010:[] [] cfq_exit_single_io_context+0x58/0xf0 ... Call Trace: [] call_for_each_cic+0x5a/0x90 [] cfq_exit_io_context+0x15/0x20 [] exit_io_context+0x100/0x140 [] do_exit+0x579/0x850 [] do_group_exit+0x5b/0xd0 [] sys_exit_group+0x17/0x20 [] system_call_fastpath+0x16/0x1b The only real hot path here is cic lookup during request initialization and avoiding extra locking requires very confined use of RCU. This patch makes cic removal from both ioc and request_queue perform double-locking and unlink immediately. * From q side, the change is almost trivial as ioc->lock nests inside queue_lock. It just needs to grab each ioc->lock as it walks cic_list and unlink it. * From ioc side, it's a bit more difficult because of inversed lock order. ioc needs its lock to walk its cic_list but can't grab the matching queue_lock and needs to perform unlock-relock dancing. Unlinking is now wholly done from put_io_context() and fast path is optimized by using the queue_lock the caller already holds, which is by far the most common case. If the ioc accessed multiple devices, it tries with trylock. In unlikely cases of fast path failure, it falls back to full double-locking dance from workqueue. Double-locking isn't the prettiest thing in the world but it's *far* simpler and more understandable than RCU trick without adding any meaningful overhead. This still leaves a lot of now unnecessary RCU logics. Future patches will trim them. -v2: Vivek pointed out that cic->q was being dereferenced after cic->release() was called. Updated to use local variable @this_q instead. Signed-off-by: Tejun Heo Cc: Vivek Goyal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d1b6f4ed1f96..65c2f8c70089 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -393,6 +393,9 @@ struct request_queue { /* Throttle data */ struct throtl_data *td; #endif +#ifdef CONFIG_LOCKDEP + int ioc_release_depth; +#endif }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ -- cgit v1.2.3 From a612fddf0d8090f2877305c9168b6c1a34fb5d90 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 14 Dec 2011 00:33:41 +0100 Subject: block, cfq: move cfqd->icq_list to request_queue and add request->elv.icq Most of icq management is about to be moved out of cfq into blk-ioc. This patch prepares for it. * Move cfqd->icq_list to request_queue->icq_list * Make request explicitly point to icq instead of through elevator private data. ->elevator_private[3] is replaced with sub struct elv which contains icq pointer and priv[2]. cfq is updated accordingly. * Meaningless clearing of ->elevator_private[0] removed from elv_set_request(). At that point in code, the field was guaranteed to be %NULL anyway. This patch doesn't introduce any functional change. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 65c2f8c70089..8bca04873f53 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -111,10 +111,14 @@ struct request { * 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 three elevator_private pointers. + * space with the elevator data. */ union { - void *elevator_private[3]; + struct { + struct io_cq *icq; + void *priv[2]; + } elv; + struct { unsigned int seq; struct list_head list; @@ -357,6 +361,8 @@ struct request_queue { struct timer_list timeout; struct list_head timeout_list; + struct list_head icq_list; + struct queue_limits limits; /* -- cgit v1.2.3 From b1bd055d397e09f99dcef9b138ed104ff1812fcb Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 11 Jan 2012 16:27:11 +0100 Subject: block: Introduce blk_set_stacking_limits function Stacking driver queue limits are typically bounded exclusively by the capabilities of the low level devices, not by the stacking driver itself. This patch introduces blk_set_stacking_limits() which has more liberal metrics than the default queue limits function. This allows us to inherit topology parameters from bottom devices without manually tweaking the default limits in each driver prior to calling the stacking function. Since there is now a clear distinction between stacking and low-level devices, blk_set_default_limits() has been modified to carry the more conservative values that we used to manually set in blk_queue_make_request(). Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8bca04873f53..adc34133a56a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -844,6 +844,7 @@ extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_default_limits(struct queue_limits *lim); +extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev, -- cgit v1.2.3 From fd83240a60ecc59849420df3393e9e6d35c77683 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Thu, 12 Jan 2012 09:17:30 +0100 Subject: blockdev: convert some macros to static inlines We prefer to program in C rather than preprocessor and it fixes this warning when CONFIG_BLK_DEV_INTEGRITY is not set: drivers/md/dm-table.c: In function 'dm_table_set_integrity': drivers/md/dm-table.c:1285:3: warning: statement with no effect [-Wunused-value] Signed-off-by: Stephen Rothwell Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 77 +++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 64 insertions(+), 13 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index adc34133a56a..5cfb9b22627f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1298,19 +1298,70 @@ queue_max_integrity_segments(struct request_queue *q) #else /* CONFIG_BLK_DEV_INTEGRITY */ -#define blk_integrity_rq(rq) (0) -#define blk_rq_count_integrity_sg(a, b) (0) -#define blk_rq_map_integrity_sg(a, b, c) (0) -#define bdev_get_integrity(a) (0) -#define blk_get_integrity(a) (0) -#define blk_integrity_compare(a, b) (0) -#define blk_integrity_register(a, b) (0) -#define blk_integrity_unregister(a) do { } while (0) -#define blk_queue_max_integrity_segments(a, b) do { } while (0) -#define queue_max_integrity_segments(a) (0) -#define blk_integrity_merge_rq(a, b, c) (0) -#define blk_integrity_merge_bio(a, b, c) (0) -#define blk_integrity_is_initialized(a) (0) +struct bio; +struct block_device; +struct gendisk; +struct blk_integrity; + +static inline int blk_integrity_rq(struct request *rq) +{ + return 0; +} +static inline int blk_rq_count_integrity_sg(struct request_queue *q, + struct bio *b) +{ + return 0; +} +static inline int blk_rq_map_integrity_sg(struct request_queue *q, + struct bio *b, + struct scatterlist *s) +{ + return 0; +} +static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) +{ + return 0; +} +static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +{ + return NULL; +} +static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) +{ + return 0; +} +static inline int blk_integrity_register(struct gendisk *d, + struct blk_integrity *b) +{ + return 0; +} +static inline void blk_integrity_unregister(struct gendisk *d) +{ +} +static inline void blk_queue_max_integrity_segments(struct request_queue *q, + unsigned int segs) +{ +} +static inline unsigned short queue_max_integrity_segments(struct request_queue *q) +{ + return 0; +} +static inline int blk_integrity_merge_rq(struct request_queue *rq, + struct request *r1, + struct request *r2) +{ + return 0; +} +static inline int blk_integrity_merge_bio(struct request_queue *rq, + struct request *r, + struct bio *b) +{ + return 0; +} +static inline bool blk_integrity_is_initialized(struct gendisk *g) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_INTEGRITY */ -- cgit v1.2.3 From 577ebb374c78314ac4617242f509e2f5e7156649 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 12 Jan 2012 16:01:27 +0100 Subject: block: add and use scsi_blk_cmd_ioctl Introduce a wrapper around scsi_cmd_ioctl that takes a block device. The function will then be enhanced to detect partition block devices and, in that case, subject the ioctls to whitelisting. Cc: linux-scsi@vger.kernel.org Cc: Jens Axboe Cc: James Bottomley Signed-off-by: Paolo Bonzini Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 94acd8172b5b..ca7b869508c7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -675,6 +675,8 @@ extern int blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern void blk_delay_queue(struct request_queue *, unsigned long); extern void blk_recount_segments(struct request_queue *, struct bio *); +extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, + unsigned int, void __user *); extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, unsigned int, void __user *); extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, -- cgit v1.2.3 From 0bfc96cb77224736dfa35c3c555d37b3646ef35e Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 12 Jan 2012 16:01:28 +0100 Subject: block: fail SCSI passthrough ioctls on partition devices Linux allows executing the SG_IO ioctl on a partition or LVM volume, and will pass the command to the underlying block device. This is well-known, but it is also a large security problem when (via Unix permissions, ACLs, SELinux or a combination thereof) a program or user needs to be granted access only to part of the disk. This patch lets partitions forward a small set of harmless ioctls; others are logged with printk so that we can see which ioctls are actually sent. In my tests only CDROM_GET_CAPABILITY actually occurred. Of course it was being sent to a (partition on a) hard disk, so it would have failed with ENOTTY and the patch isn't changing anything in practice. Still, I'm treating it specially to avoid spamming the logs. In principle, this restriction should include programs running with CAP_SYS_RAWIO. If for example I let a program access /dev/sda2 and /dev/sdb, it still should not be able to read/write outside the boundaries of /dev/sda2 independent of the capabilities. However, for now programs with CAP_SYS_RAWIO will still be allowed to send the ioctls. Their actions will still be logged. This patch does not affect the non-libata IDE driver. That driver however already tests for bd != bd->bd_contains before issuing some ioctl; it could be restricted further to forbid these ioctls even for programs running with CAP_SYS_ADMIN/CAP_SYS_RAWIO. Cc: linux-scsi@vger.kernel.org Cc: Jens Axboe Cc: James Bottomley Signed-off-by: Paolo Bonzini [ Make it also print the command name when warning - Linus ] Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ca7b869508c7..0ed1eb062313 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -675,6 +675,7 @@ extern int blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern void blk_delay_queue(struct request_queue *, unsigned long); extern void blk_recount_segments(struct request_queue *, struct bio *); +extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, unsigned int, void __user *); extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, -- cgit v1.2.3 From 11a3122f6cf2d988a77eb8883d0fc49cd013a6d5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 7 Feb 2012 07:51:30 +0100 Subject: block: strip out locking optimization in put_io_context() put_io_context() performed a complex trylock dancing to avoid deferring ioc release to workqueue. It was also broken on UP because trylock was always assumed to succeed which resulted in unbalanced preemption count. While there are ways to fix the UP breakage, even the most pathological microbench (forced ioc allocation and tight fork/exit loop) fails to show any appreciable performance benefit of the optimization. Strip it out. If there turns out to be workloads which are affected by this change, simpler optimization from the discussion thread can be applied later. Signed-off-by: Tejun Heo LKML-Reference: <1328514611.21268.66.camel@sli10-conroe> Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6c6a1f008065..606cf339bb56 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -399,9 +399,6 @@ struct request_queue { /* Throttle data */ struct throtl_data *td; #endif -#ifdef CONFIG_LOCKDEP - int ioc_release_depth; -#endif }; #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ -- cgit v1.2.3