From 1f98a13f623e0ef666690a18c1250335fc6d7ef1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 11 Sep 2009 14:32:04 +0200 Subject: bio: first step in sanitizing the bio->bi_rw flag testing Get rid of any functions that test for these bits and make callers use bio_rw_flagged() directly. Then it is at least directly apparent what variable and flag they check. Signed-off-by: Jens Axboe --- fs/btrfs/volumes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 5dbefd11b4af..5cf405b0828d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -260,7 +260,7 @@ loop_lock: num_run++; batch_run++; - if (bio_sync(cur)) + if (bio_rw_flagged(cur, BIO_RW_SYNCIO)) num_sync_run++; if (need_resched()) { @@ -2903,7 +2903,7 @@ static noinline int schedule_bio(struct btrfs_root *root, bio->bi_rw |= rw; spin_lock(&device->io_lock); - if (bio_sync(bio)) + if (bio_rw_flagged(bio, BIO_RW_SYNCIO)) pending_bios = &device->pending_sync_bios; else pending_bios = &device->pending_bios; -- cgit v1.2.3 From 723590ed52d244b025f10a8e2f54c2f57ed02b4d Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Sat, 15 Aug 2009 08:43:22 +0200 Subject: splice: update mtime and atime on files Splice should update the modification and access times on regular files just like read and write. Not updating mtime will confuse backup tools, etc... This patch only adds the time updates for regular files. For pipes and other special files that splice touches the need for updating the times is less clear. Let's discuss and fix that separately. Signed-off-by: Miklos Szeredi Signed-off-by: Jens Axboe --- fs/splice.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/splice.c b/fs/splice.c index 73766d24f97b..aec4014291be 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -502,8 +502,10 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, len = left; ret = __generic_file_splice_read(in, ppos, pipe, len, flags); - if (ret > 0) + if (ret > 0) { *ppos += ret; + file_accessed(in); + } return ret; } @@ -963,8 +965,10 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD); ret = file_remove_suid(out); - if (!ret) + if (!ret) { + file_update_time(out); ret = splice_from_pipe_feed(pipe, &sd, pipe_to_file); + } mutex_unlock(&inode->i_mutex); } while (ret > 0); splice_from_pipe_end(pipe, &sd); -- cgit v1.2.3 From a9327cac440be4d8333bba975cbbf76045096275 Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Fri, 11 Sep 2009 09:18:54 +0200 Subject: Seperate read and write statistics of in_flight requests Currently, there is a single in_flight counter measuring the number of requests in the request_queue. But some monitoring tools would like to know how many read requests and write requests are in progress. Split the current in_flight counter into two seperate counters for read and write. This information is exported as a sysfs attribute, as changing the currently available stat files would break the existing tools. Signed-off-by: Nikanth Karthikesan Signed-off-by: Jens Axboe --- block/blk-core.c | 6 +++--- block/blk-merge.c | 2 +- block/genhd.c | 4 +++- drivers/md/dm.c | 16 ++++++++++------ fs/partitions/check.c | 12 +++++++++++- include/linux/genhd.h | 21 ++++++++++++++------- 6 files changed, 42 insertions(+), 19 deletions(-) (limited to 'fs') diff --git a/block/blk-core.c b/block/blk-core.c index 982d634e67f9..182ebe3eb9e0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -69,7 +69,7 @@ static void drive_stat_acct(struct request *rq, int new_io) part_stat_inc(cpu, part, merges[rw]); else { part_round_stats(cpu, part); - part_inc_in_flight(part); + part_inc_in_flight(part, rw); } part_stat_unlock(); @@ -1030,7 +1030,7 @@ static void part_round_stats_single(int cpu, struct hd_struct *part, if (part->in_flight) { __part_stat_add(cpu, part, time_in_queue, - part->in_flight * (now - part->stamp)); + part_in_flight(part) * (now - part->stamp)); __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); } part->stamp = now; @@ -1737,7 +1737,7 @@ static void blk_account_io_done(struct request *req) part_stat_inc(cpu, part, ios[rw]); part_stat_add(cpu, part, ticks[rw], duration); part_round_stats(cpu, part); - part_dec_in_flight(part); + part_dec_in_flight(part, rw); part_stat_unlock(); } diff --git a/block/blk-merge.c b/block/blk-merge.c index b0de8574fdc8..99cb5cf1f447 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req) part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_round_stats(cpu, part); - part_dec_in_flight(part); + part_dec_in_flight(part, rq_data_dir(req)); part_stat_unlock(); } diff --git a/block/genhd.c b/block/genhd.c index b89328eceee2..5b76bf55d05c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -869,6 +869,7 @@ static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL); static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); +static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -888,6 +889,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_alignment_offset.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, + &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif @@ -1053,7 +1055,7 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, merges[1]), (unsigned long long)part_stat_read(hd, sectors[1]), jiffies_to_msecs(part_stat_read(hd, ticks[1])), - hd->in_flight, + part_in_flight(hd), jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)) ); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ec012f030240..eee28fac210c 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -130,7 +130,7 @@ struct mapped_device { /* * A list of ios that arrived while we were suspended. */ - atomic_t pending; + atomic_t pending[2]; wait_queue_head_t wait; struct work_struct work; struct bio_list deferred; @@ -453,13 +453,14 @@ static void start_io_acct(struct dm_io *io) { struct mapped_device *md = io->md; int cpu; + int rw = bio_data_dir(io->bio); io->start_time = jiffies; cpu = part_stat_lock(); part_round_stats(cpu, &dm_disk(md)->part0); part_stat_unlock(); - dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending); + dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]); } static void end_io_acct(struct dm_io *io) @@ -479,8 +480,9 @@ static void end_io_acct(struct dm_io *io) * After this is decremented the bio must not be touched if it is * a barrier. */ - dm_disk(md)->part0.in_flight = pending = - atomic_dec_return(&md->pending); + dm_disk(md)->part0.in_flight[rw] = pending = + atomic_dec_return(&md->pending[rw]); + pending += atomic_read(&md->pending[rw^0x1]); /* nudge anyone waiting on suspend queue */ if (!pending) @@ -1785,7 +1787,8 @@ static struct mapped_device *alloc_dev(int minor) if (!md->disk) goto bad_disk; - atomic_set(&md->pending, 0); + atomic_set(&md->pending[0], 0); + atomic_set(&md->pending[1], 0); init_waitqueue_head(&md->wait); INIT_WORK(&md->work, dm_wq_work); init_waitqueue_head(&md->eventq); @@ -2088,7 +2091,8 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) break; } spin_unlock_irqrestore(q->queue_lock, flags); - } else if (!atomic_read(&md->pending)) + } else if (!atomic_read(&md->pending[0]) && + !atomic_read(&md->pending[1])) break; if (interruptible == TASK_INTERRUPTIBLE && diff --git a/fs/partitions/check.c b/fs/partitions/check.c index ea4e6cb29e13..619ba99dfe39 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -248,11 +248,19 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, merges[WRITE]), (unsigned long long)part_stat_read(p, sectors[WRITE]), jiffies_to_msecs(part_stat_read(p, ticks[WRITE])), - p->in_flight, + part_in_flight(p), jiffies_to_msecs(part_stat_read(p, io_ticks)), jiffies_to_msecs(part_stat_read(p, time_in_queue))); } +ssize_t part_inflight_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + + return sprintf(buf, "%8u %8u\n", p->in_flight[0], p->in_flight[1]); +} + #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -281,6 +289,7 @@ static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); +static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -292,6 +301,7 @@ static struct attribute *part_attrs[] = { &dev_attr_size.attr, &dev_attr_alignment_offset.attr, &dev_attr_stat.attr, + &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 45fc320a53c6..44263cb27121 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -98,7 +98,7 @@ struct hd_struct { int make_it_fail; #endif unsigned long stamp; - int in_flight; + int in_flight[2]; #ifdef CONFIG_SMP struct disk_stats *dkstats; #else @@ -322,18 +322,23 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(cpu, gendiskp, field, subnd) \ part_stat_add(cpu, gendiskp, field, -subnd) -static inline void part_inc_in_flight(struct hd_struct *part) +static inline void part_inc_in_flight(struct hd_struct *part, int rw) { - part->in_flight++; + part->in_flight[rw]++; if (part->partno) - part_to_disk(part)->part0.in_flight++; + part_to_disk(part)->part0.in_flight[rw]++; } -static inline void part_dec_in_flight(struct hd_struct *part) +static inline void part_dec_in_flight(struct hd_struct *part, int rw) { - part->in_flight--; + part->in_flight[rw]--; if (part->partno) - part_to_disk(part)->part0.in_flight--; + part_to_disk(part)->part0.in_flight[rw]--; +} + +static inline int part_in_flight(struct hd_struct *part) +{ + return part->in_flight[0] + part->in_flight[1]; } /* block/blk-core.c */ @@ -546,6 +551,8 @@ extern ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t part_inflight_show(struct device *dev, + struct device_attribute *attr, char *buf); #ifdef CONFIG_FAIL_MAKE_REQUEST extern ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); -- cgit v1.2.3 From 746cd1e7e4a555ddaee53b19a46e05c9c61eaf09 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 12 Sep 2009 07:35:43 +0200 Subject: block: use blkdev_issue_discard in blk_ioctl_discard blk_ioctl_discard duplicates large amounts of code from blkdev_issue_discard, the only difference between the two is that blkdev_issue_discard needs to send a barrier discard request and blk_ioctl_discard a non-barrier one, and blk_ioctl_discard needs to wait on the request. To facilitates this add a flags argument to blkdev_issue_discard to control both aspects of the behaviour. This will be very useful later on for using the waiting funcitonality for other callers. Based on an earlier patch from Matthew Wilcox . Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 31 +++++++++++++++++++------------ block/ioctl.c | 49 ++----------------------------------------------- fs/btrfs/extent-tree.c | 3 ++- fs/gfs2/rgrp.c | 6 ++++-- include/linux/blkdev.h | 9 ++++++--- mm/swapfile.c | 6 ++++-- 6 files changed, 37 insertions(+), 67 deletions(-) (limited to 'fs') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 30022b4e2f63..6593ab39cfe9 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -348,6 +348,9 @@ static void blkdev_discard_end_io(struct bio *bio, int err) clear_bit(BIO_UPTODATE, &bio->bi_flags); } + if (bio->bi_private) + complete(bio->bi_private); + bio_put(bio); } @@ -357,21 +360,20 @@ static void blkdev_discard_end_io(struct bio *bio, int err) * @sector: start sector * @nr_sects: number of sectors to discard * @gfp_mask: memory allocation flags (for bio_alloc) + * @flags: DISCARD_FL_* flags to control behaviour * * Description: - * Issue a discard request for the sectors in question. Does not wait. + * Issue a discard request for the sectors in question. */ -int blkdev_issue_discard(struct block_device *bdev, - sector_t sector, sector_t nr_sects, gfp_t gfp_mask) +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, int flags) { - struct request_queue *q; - struct bio *bio; + DECLARE_COMPLETION_ONSTACK(wait); + struct request_queue *q = bdev_get_queue(bdev); + int type = flags & DISCARD_FL_BARRIER ? + DISCARD_BARRIER : DISCARD_NOBARRIER; int ret = 0; - if (bdev->bd_disk == NULL) - return -ENXIO; - - q = bdev_get_queue(bdev); if (!q) return -ENXIO; @@ -379,12 +381,14 @@ int blkdev_issue_discard(struct block_device *bdev, return -EOPNOTSUPP; while (nr_sects && !ret) { - bio = bio_alloc(gfp_mask, 0); + struct bio *bio = bio_alloc(gfp_mask, 0); if (!bio) return -ENOMEM; bio->bi_end_io = blkdev_discard_end_io; bio->bi_bdev = bdev; + if (flags & DISCARD_FL_WAIT) + bio->bi_private = &wait; bio->bi_sector = sector; @@ -396,10 +400,13 @@ int blkdev_issue_discard(struct block_device *bdev, bio->bi_size = nr_sects << 9; nr_sects = 0; } + bio_get(bio); - submit_bio(DISCARD_BARRIER, bio); + submit_bio(type, bio); + + if (flags & DISCARD_FL_WAIT) + wait_for_completion(&wait); - /* Check if it failed immediately */ if (bio_flagged(bio, BIO_EOPNOTSUPP)) ret = -EOPNOTSUPP; else if (!bio_flagged(bio, BIO_UPTODATE)) diff --git a/block/ioctl.c b/block/ioctl.c index 500e4c73cc52..d3e6b5827a34 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -112,22 +112,9 @@ static int blkdev_reread_part(struct block_device *bdev) return res; } -static void blk_ioc_discard_endio(struct bio *bio, int err) -{ - if (err) { - if (err == -EOPNOTSUPP) - set_bit(BIO_EOPNOTSUPP, &bio->bi_flags); - clear_bit(BIO_UPTODATE, &bio->bi_flags); - } - complete(bio->bi_private); -} - static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, uint64_t len) { - struct request_queue *q = bdev_get_queue(bdev); - int ret = 0; - if (start & 511) return -EINVAL; if (len & 511) @@ -137,40 +124,8 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, if (start + len > (bdev->bd_inode->i_size >> 9)) return -EINVAL; - - if (!q->prepare_discard_fn) - return -EOPNOTSUPP; - - while (len && !ret) { - DECLARE_COMPLETION_ONSTACK(wait); - struct bio *bio; - - bio = bio_alloc(GFP_KERNEL, 0); - - bio->bi_end_io = blk_ioc_discard_endio; - bio->bi_bdev = bdev; - bio->bi_private = &wait; - bio->bi_sector = start; - - if (len > queue_max_hw_sectors(q)) { - bio->bi_size = queue_max_hw_sectors(q) << 9; - len -= queue_max_hw_sectors(q); - start += queue_max_hw_sectors(q); - } else { - bio->bi_size = len << 9; - len = 0; - } - submit_bio(DISCARD_NOBARRIER, bio); - - wait_for_completion(&wait); - - if (bio_flagged(bio, BIO_EOPNOTSUPP)) - ret = -EOPNOTSUPP; - else if (!bio_flagged(bio, BIO_UPTODATE)) - ret = -EIO; - bio_put(bio); - } - return ret; + return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, + DISCARD_FL_WAIT); } static int put_ushort(unsigned long arg, unsigned short val) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 72a2b9c28e9f..535f85ba104f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1511,7 +1511,8 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans, static void btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len) { - blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL); + blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, + DISCARD_FL_BARRIER); } #endif diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index fba795798d3a..fbc43241f2ef 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -857,7 +857,8 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, goto start_new_extent; if ((start + nr_sects) != blk) { rv = blkdev_issue_discard(bdev, start, - nr_sects, GFP_NOFS); + nr_sects, GFP_NOFS, + DISCARD_FL_BARRIER); if (rv) goto fail; nr_sects = 0; @@ -871,7 +872,8 @@ start_new_extent: } } if (nr_sects) { - rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS); + rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, + DISCARD_FL_BARRIER); if (rv) goto fail; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 86c2bdff3b89..e23a86cae5ac 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -998,15 +998,18 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, } extern int blkdev_issue_flush(struct block_device *, sector_t *); -extern int blkdev_issue_discard(struct block_device *, - sector_t sector, sector_t nr_sects, gfp_t); +#define DISCARD_FL_WAIT 0x01 /* wait for completion */ +#define DISCARD_FL_BARRIER 0x02 /* issue DISCARD_BARRIER request */ +extern int blkdev_issue_discard(struct block_device *, sector_t sector, + sector_t nr_sects, gfp_t, int flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks) { block <<= (sb->s_blocksize_bits - 9); nr_blocks <<= (sb->s_blocksize_bits - 9); - return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL); + return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL, + DISCARD_FL_BARRIER); } extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); diff --git a/mm/swapfile.c b/mm/swapfile.c index 8ffdc0d23c53..74f1102e8749 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -161,7 +161,8 @@ static int discard_swap(struct swap_info_struct *si) } err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL); + nr_blocks, GFP_KERNEL, + DISCARD_FL_BARRIER); if (err) break; @@ -200,7 +201,8 @@ static void discard_swap_cluster(struct swap_info_struct *si, start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_NOIO)) + nr_blocks, GFP_NOIO, + DISCARD_FL_BARRIER)) break; } -- cgit v1.2.3