From c6e666345e1b79c62ba82339cc7d55a89cb73f88 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 2 Aug 2012 09:48:50 +0200 Subject: block: split discard into aligned requests When a disk has large discard_granularity and small max_discard_sectors, discards are not split with optimal alignment. In the limit case of discard_granularity == max_discard_sectors, no request could be aligned correctly, so in fact you might end up with no discarded logical blocks at all. Another example that helps showing the condition in the patch is with discard_granularity == 64, max_discard_sectors == 128. A request that is submitted for 256 sectors 2..257 will be split in two: 2..129, 130..257. However, only 2 aligned blocks out of 3 are included in the request; 128..191 may be left intact and not discarded. With this patch, the first request will be truncated to ensure good alignment of what's left, and the split will be 2..127, 128..255, 256..257. The patch will also take into account the discard_alignment. At most one extra request will be introduced, because the first request will be reduced by at most granularity-1 sectors, and granularity must be less than max_discard_sectors. Subsequent requests will run on round_down(max_discard_sectors, granularity) sectors, as in the current code. Signed-off-by: Paolo Bonzini Acked-by: Vivek Goyal Tested-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4e72a9d48232..281516ae8b4e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1139,6 +1139,16 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector & (lim->discard_granularity - 1); } +static inline int bdev_discard_alignment(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (bdev != bdev->bd_contains) + return bdev->bd_part->discard_alignment; + + return q->limits.discard_alignment; +} + static inline unsigned int queue_discard_zeroes_data(struct request_queue *q) { if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1) -- cgit v1.2.3 From 85b9f66a41eb8ee3f1dfc95707412705463cdd97 Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 2 Aug 2012 23:42:04 +0200 Subject: block: Add blk_bio_map_sg() helper Add a helper to map a bio to a scatterlist, modelled after blk_rq_map_sg. This helper is useful for any driver that wants to create a scatterlist from its ->make_request_fn method. Changes in v2: - Use __blk_segment_map_sg to avoid duplicated code - Add cocbook style function comment Cc: Rusty Russell Cc: Christoph Hellwig Cc: Tejun Heo Cc: Shaohua Li Cc: "Michael S. Tsirkin" Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Signed-off-by: Christoph Hellwig Signed-off-by: Minchan Kim Signed-off-by: Asias He Signed-off-by: Jens Axboe --- block/blk-merge.c | 37 +++++++++++++++++++++++++++++++++++++ include/linux/blkdev.h | 2 ++ 2 files changed, 39 insertions(+) (limited to 'include/linux') diff --git a/block/blk-merge.c b/block/blk-merge.c index 576b68e79248..e76279e41162 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -209,6 +209,43 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, } EXPORT_SYMBOL(blk_rq_map_sg); +/** + * blk_bio_map_sg - map a bio to a scatterlist + * @q: request_queue in question + * @bio: bio being mapped + * @sglist: scatterlist being mapped + * + * Note: + * Caller must make sure sg can hold bio->bi_phys_segments entries + * + * Will return the number of sg entries setup + */ +int blk_bio_map_sg(struct request_queue *q, struct bio *bio, + struct scatterlist *sglist) +{ + struct bio_vec *bvec, *bvprv; + struct scatterlist *sg; + int nsegs, cluster; + unsigned long i; + + nsegs = 0; + cluster = blk_queue_cluster(q); + + bvprv = NULL; + sg = NULL; + bio_for_each_segment(bvec, bio, i) { + __blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg, + &nsegs, &cluster); + } /* segments in bio */ + + if (sg) + sg_mark_end(sg); + + BUG_ON(bio->bi_phys_segments && nsegs > bio->bi_phys_segments); + return nsegs; +} +EXPORT_SYMBOL(blk_bio_map_sg); + static inline int ll_new_hw_segment(struct request_queue *q, struct request *req, struct bio *bio) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 281516ae8b4e..dc632975d54f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -894,6 +894,8 @@ extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); +extern int blk_bio_map_sg(struct request_queue *q, struct bio *bio, + struct scatterlist *sglist); extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); -- cgit v1.2.3 From 276f0f5d157bb4a816053f4f3a941dbcd4f76556 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 9 Aug 2012 15:20:23 +0200 Subject: block: disable discard request merge temporarily The SCSI discard request merge never worked, and looks no solution for in future, let's disable it temporarily. Signed-off-by: Shaohua Li Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dc632975d54f..4a2ab7c85393 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -601,7 +601,7 @@ static inline void blk_clear_rl_full(struct request_list *rl, bool sync) * it already be started by driver. */ #define RQ_NOMERGE_FLAGS \ - (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA) + (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | REQ_DISCARD) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \ (((rq)->cmd_flags & REQ_DISCARD) || \ -- cgit v1.2.3 From 4e8b14526ca7fb046a81c94002c1c43b6fdf0e9b Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 8 Aug 2012 15:36:20 -0400 Subject: time: Improve sanity checking of timekeeping inputs Unexpected behavior could occur if the time is set to a value large enough to overflow a 64bit ktime_t (which is something larger then the year 2262). Also unexpected behavior could occur if large negative offsets are injected via adjtimex. So this patch improves the sanity check timekeeping inputs by improving the timespec_valid() check, and then makes better use of timespec_valid() to make sure we don't set the time to an invalid negative value or one that overflows ktime_t. Note: This does not protect from setting the time close to overflowing ktime_t and then letting natural accumulation cause the overflow. Reported-by: CAI Qian Reported-by: Sasha Levin Signed-off-by: John Stultz Cc: Peter Zijlstra Cc: Prarit Bhargava Cc: Zhouping Liu Cc: Ingo Molnar Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1344454580-17031-1-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/ktime.h | 7 ------- include/linux/time.h | 22 ++++++++++++++++++++-- kernel/time/timekeeping.c | 26 ++++++++++++++++++++++++-- 3 files changed, 44 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 603bec2913b0..06177ba10a16 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -58,13 +58,6 @@ union ktime { typedef union ktime ktime_t; /* Kill this */ -#define KTIME_MAX ((s64)~((u64)1 << 63)) -#if (BITS_PER_LONG == 64) -# define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) -#else -# define KTIME_SEC_MAX LONG_MAX -#endif - /* * ktime_t definitions when using the 64-bit scalar representation: */ diff --git a/include/linux/time.h b/include/linux/time.h index c81c5e40fcb5..b0bbd8f0130d 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -107,11 +107,29 @@ static inline struct timespec timespec_sub(struct timespec lhs, return ts_delta; } +#define KTIME_MAX ((s64)~((u64)1 << 63)) +#if (BITS_PER_LONG == 64) +# define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) +#else +# define KTIME_SEC_MAX LONG_MAX +#endif + /* * Returns true if the timespec is norm, false if denorm: */ -#define timespec_valid(ts) \ - (((ts)->tv_sec >= 0) && (((unsigned long) (ts)->tv_nsec) < NSEC_PER_SEC)) +static inline bool timespec_valid(const struct timespec *ts) +{ + /* Dates before 1970 are bogus */ + if (ts->tv_sec < 0) + return false; + /* Can't have more nanoseconds then a second */ + if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) + return false; + /* Disallow values that could overflow ktime_t */ + if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) + return false; + return true; +} extern void read_persistent_clock(struct timespec *ts); extern void read_boot_clock(struct timespec *ts); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e16af197a2bc..898bef066a44 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -427,7 +427,7 @@ int do_settimeofday(const struct timespec *tv) struct timespec ts_delta, xt; unsigned long flags; - if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) + if (!timespec_valid(tv)) return -EINVAL; write_seqlock_irqsave(&tk->lock, flags); @@ -463,6 +463,8 @@ int timekeeping_inject_offset(struct timespec *ts) { struct timekeeper *tk = &timekeeper; unsigned long flags; + struct timespec tmp; + int ret = 0; if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; @@ -471,10 +473,17 @@ int timekeeping_inject_offset(struct timespec *ts) timekeeping_forward_now(tk); + /* Make sure the proposed value is valid */ + tmp = timespec_add(tk_xtime(tk), *ts); + if (!timespec_valid(&tmp)) { + ret = -EINVAL; + goto error; + } tk_xtime_add(tk, ts); tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts)); +error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, true); write_sequnlock_irqrestore(&tk->lock, flags); @@ -482,7 +491,7 @@ int timekeeping_inject_offset(struct timespec *ts) /* signal hrtimers about time change */ clock_was_set(); - return 0; + return ret; } EXPORT_SYMBOL(timekeeping_inject_offset); @@ -649,7 +658,20 @@ void __init timekeeping_init(void) struct timespec now, boot, tmp; read_persistent_clock(&now); + if (!timespec_valid(&now)) { + pr_warn("WARNING: Persistent clock returned invalid value!\n" + " Check your CMOS/BIOS settings.\n"); + now.tv_sec = 0; + now.tv_nsec = 0; + } + read_boot_clock(&boot); + if (!timespec_valid(&boot)) { + pr_warn("WARNING: Boot clock returned invalid value!\n" + " Check your CMOS/BIOS settings.\n"); + boot.tv_sec = 0; + boot.tv_nsec = 0; + } seqlock_init(&tk->lock); -- cgit v1.2.3