From 018e0446890661504783f92388ecce7138c1566d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Jun 2009 16:27:10 +0200 Subject: block: get rid of queue-private command filter The initial patches to support this through sysfs export were broken and have been if 0'ed out in any release. So lets just kill the code and reclaim some space in struct request_queue, if anyone would later like to fixup the sysfs bits, the git history can easily restore the removed bits. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8963d9149b5f..49ae07951d55 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -301,12 +301,6 @@ struct blk_queue_tag { #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) -struct blk_cmd_filter { - unsigned long read_ok[BLK_SCSI_CMD_PER_LONG]; - unsigned long write_ok[BLK_SCSI_CMD_PER_LONG]; - struct kobject kobj; -}; - struct queue_limits { unsigned long bounce_pfn; unsigned long seg_boundary_mask; @@ -445,7 +439,6 @@ struct request_queue #if defined(CONFIG_BLK_DEV_BSG) struct bsg_class_device bsg_dev; #endif - struct blk_cmd_filter cmd_filter; }; #define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ @@ -998,13 +991,7 @@ static inline int sb_issue_discard(struct super_block *sb, return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL); } -/* -* command filter functions -*/ -extern int blk_verify_command(struct blk_cmd_filter *filter, - unsigned char *cmd, fmode_t has_write_perm); -extern void blk_unregister_filter(struct gendisk *disk); -extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter); +extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); #define MAX_PHYS_SEGMENTS 128 #define MAX_HW_SEGMENTS 128 -- cgit v1.2.3 From 8aa7e847d834ed937a9ad37a0f2ad5b8584c1ab0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 9 Jul 2009 14:52:32 +0200 Subject: Fix congestion_wait() sync/async vs read/write confusion Commit 1faa16d22877f4839bd433547d770c676d1d964c accidentally broke the bdi congestion wait queue logic, causing us to wait on congestion for WRITE (== 1) when we really wanted BLK_RW_ASYNC (== 0) instead. Signed-off-by: Jens Axboe --- arch/x86/lib/usercopy_32.c | 2 +- drivers/block/pktcdvd.c | 10 ++++++---- drivers/md/dm-crypt.c | 2 +- fs/fat/file.c | 2 +- fs/fuse/dev.c | 8 ++++---- fs/nfs/write.c | 8 +++++--- fs/reiserfs/journal.c | 2 +- fs/xfs/linux-2.6/kmem.c | 4 ++-- fs/xfs/linux-2.6/xfs_buf.c | 2 +- include/linux/backing-dev.h | 6 +++--- include/linux/blkdev.h | 8 ++++---- mm/backing-dev.c | 7 +++---- mm/memcontrol.c | 2 +- mm/page-writeback.c | 8 ++++---- mm/page_alloc.c | 4 ++-- mm/vmscan.c | 8 ++++---- 16 files changed, 43 insertions(+), 40 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index 7c8ca91bb9ec..1f118d462acc 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -751,7 +751,7 @@ survive: if (retval == -ENOMEM && is_global_init(current)) { up_read(¤t->mm->mmap_sem); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); goto survive; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 83650e00632d..99a506f619b7 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1372,8 +1372,10 @@ try_next_bio: wakeup = (pd->write_congestion_on > 0 && pd->bio_queue_size <= pd->write_congestion_off); spin_unlock(&pd->lock); - if (wakeup) - clear_bdi_congested(&pd->disk->queue->backing_dev_info, WRITE); + if (wakeup) { + clear_bdi_congested(&pd->disk->queue->backing_dev_info, + BLK_RW_ASYNC); + } pkt->sleep_time = max(PACKET_WAIT_TIME, 1); pkt_set_state(pkt, PACKET_WAITING_STATE); @@ -2592,10 +2594,10 @@ static int pkt_make_request(struct request_queue *q, struct bio *bio) spin_lock(&pd->lock); if (pd->write_congestion_on > 0 && pd->bio_queue_size >= pd->write_congestion_on) { - set_bdi_congested(&q->backing_dev_info, WRITE); + set_bdi_congested(&q->backing_dev_info, BLK_RW_ASYNC); do { spin_unlock(&pd->lock); - congestion_wait(WRITE, HZ); + congestion_wait(BLK_RW_ASYNC, HZ); spin_lock(&pd->lock); } while(pd->bio_queue_size > pd->write_congestion_off); } diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 9933eb861c71..529e2ba505c3 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -776,7 +776,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) * But don't wait if split was due to the io size restriction */ if (unlikely(out_of_pages)) - congestion_wait(WRITE, HZ/100); + congestion_wait(BLK_RW_ASYNC, HZ/100); /* * With async crypto it is unsafe to share the crypto context diff --git a/fs/fat/file.c b/fs/fat/file.c index b28ea646ff60..f042b965c95c 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -134,7 +134,7 @@ static int fat_file_release(struct inode *inode, struct file *filp) if ((filp->f_mode & FMODE_WRITE) && MSDOS_SB(inode->i_sb)->options.flush) { fat_flush_inodes(inode->i_sb, inode, NULL); - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } return 0; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index f58ecbc416c8..6484eb75acd6 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -286,8 +286,8 @@ __releases(&fc->lock) } if (fc->num_background == FUSE_CONGESTION_THRESHOLD && fc->connected && fc->bdi_initialized) { - clear_bdi_congested(&fc->bdi, READ); - clear_bdi_congested(&fc->bdi, WRITE); + clear_bdi_congested(&fc->bdi, BLK_RW_SYNC); + clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC); } fc->num_background--; fc->active_background--; @@ -414,8 +414,8 @@ static void fuse_request_send_nowait_locked(struct fuse_conn *fc, fc->blocked = 1; if (fc->num_background == FUSE_CONGESTION_THRESHOLD && fc->bdi_initialized) { - set_bdi_congested(&fc->bdi, READ); - set_bdi_congested(&fc->bdi, WRITE); + set_bdi_congested(&fc->bdi, BLK_RW_SYNC); + set_bdi_congested(&fc->bdi, BLK_RW_ASYNC); } list_add_tail(&req->list, &fc->bg_queue); flush_bg_queue(fc); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index ce728829f79a..0a0a2ff767c3 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -202,8 +202,10 @@ static int nfs_set_page_writeback(struct page *page) struct nfs_server *nfss = NFS_SERVER(inode); if (atomic_long_inc_return(&nfss->writeback) > - NFS_CONGESTION_ON_THRESH) - set_bdi_congested(&nfss->backing_dev_info, WRITE); + NFS_CONGESTION_ON_THRESH) { + set_bdi_congested(&nfss->backing_dev_info, + BLK_RW_ASYNC); + } } return ret; } @@ -215,7 +217,7 @@ static void nfs_end_page_writeback(struct page *page) end_page_writeback(page); if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) - clear_bdi_congested(&nfss->backing_dev_info, WRITE); + clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } /* diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 77f5bb746bf0..90622200b39c 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -997,7 +997,7 @@ static int reiserfs_async_progress_wait(struct super_block *s) DEFINE_WAIT(wait); struct reiserfs_journal *j = SB_JOURNAL(s); if (atomic_read(&j->j_async_throttle)) - congestion_wait(WRITE, HZ / 10); + congestion_wait(BLK_RW_ASYNC, HZ / 10); return 0; } diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c index 1cd3b55ee3d2..2d3f90afe5f1 100644 --- a/fs/xfs/linux-2.6/kmem.c +++ b/fs/xfs/linux-2.6/kmem.c @@ -53,7 +53,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags) printk(KERN_ERR "XFS: possible memory allocation " "deadlock in %s (mode:0x%x)\n", __func__, lflags); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); } while (1); } @@ -130,7 +130,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags) printk(KERN_ERR "XFS: possible memory allocation " "deadlock in %s (mode:0x%x)\n", __func__, lflags); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); } while (1); } diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 1418b916fc27..0c93c7ef3d18 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -412,7 +412,7 @@ _xfs_buf_lookup_pages( XFS_STATS_INC(xb_page_retries); xfsbufd_wakeup(0, gfp_mask); - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0ec2c594868e..3a52a63c1351 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -229,9 +229,9 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << BDI_async_congested)); } -void clear_bdi_congested(struct backing_dev_info *bdi, int rw); -void set_bdi_congested(struct backing_dev_info *bdi, int rw); -long congestion_wait(int rw, long timeout); +void clear_bdi_congested(struct backing_dev_info *bdi, int sync); +void set_bdi_congested(struct backing_dev_info *bdi, int sync); +long congestion_wait(int sync, long timeout); static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49ae07951d55..bb3d39978701 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -779,18 +779,18 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, * congested queues, and wake up anyone who was waiting for requests to be * put back. */ -static inline void blk_clear_queue_congested(struct request_queue *q, int rw) +static inline void blk_clear_queue_congested(struct request_queue *q, int sync) { - clear_bdi_congested(&q->backing_dev_info, rw); + clear_bdi_congested(&q->backing_dev_info, sync); } /* * A queue has just entered congestion. Flag that in the queue's VM-visible * state flags and increment the global gounter of congested queues. */ -static inline void blk_set_queue_congested(struct request_queue *q, int rw) +static inline void blk_set_queue_congested(struct request_queue *q, int sync) { - set_bdi_congested(&q->backing_dev_info, rw); + set_bdi_congested(&q->backing_dev_info, sync); } extern void blk_start_queue(struct request_queue *q); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 493b468a5035..c86edd244294 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -283,7 +283,6 @@ static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) }; - void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { enum bdi_state bit; @@ -308,18 +307,18 @@ EXPORT_SYMBOL(set_bdi_congested); /** * congestion_wait - wait for a backing_dev to become uncongested - * @rw: READ or WRITE + * @sync: SYNC or ASYNC IO * @timeout: timeout in jiffies * * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit * write congestion. If no backing_devs are congested then just wait for the * next write to be completed. */ -long congestion_wait(int rw, long timeout) +long congestion_wait(int sync, long timeout) { long ret; DEFINE_WAIT(wait); - wait_queue_head_t *wqh = &congestion_wqh[rw]; + wait_queue_head_t *wqh = &congestion_wqh[sync]; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = io_schedule_timeout(timeout); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e2fa20dadf40..e717964cb5a0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1973,7 +1973,7 @@ try_to_free: if (!progress) { nr_retries--; /* maybe some writeback is necessary */ - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7687879253b9..81627ebcd313 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -575,7 +575,7 @@ static void balance_dirty_pages(struct address_space *mapping) if (pages_written >= write_chunk) break; /* We've done our duty */ - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && @@ -669,7 +669,7 @@ void throttle_vm_writeout(gfp_t gfp_mask) if (global_page_state(NR_UNSTABLE_NFS) + global_page_state(NR_WRITEBACK) <= dirty_thresh) break; - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* * The caller might hold locks which can prevent IO completion @@ -715,7 +715,7 @@ static void background_writeout(unsigned long _min_pages) if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { /* Wrote less than expected */ if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); else break; } @@ -787,7 +787,7 @@ static void wb_kupdate(unsigned long arg) writeback_inodes(&wbc); if (wbc.nr_to_write > 0) { if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); else break; /* All the old data is written */ } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ad7cd1c56b07..a35eeab2724c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1666,7 +1666,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, preferred_zone, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); } while (!page && (gfp_mask & __GFP_NOFAIL)); return page; @@ -1831,7 +1831,7 @@ rebalance: pages_reclaimed += did_some_progress; if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) { /* Wait for some write requests to complete then retry */ - congestion_wait(WRITE, HZ/50); + congestion_wait(BLK_RW_ASYNC, HZ/50); goto rebalance; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 54155268dfca..dea7abd31098 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1104,7 +1104,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, */ if (nr_freed < nr_taken && !current_is_kswapd() && lumpy_reclaim) { - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* * The attempt at page out may have made some @@ -1721,7 +1721,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, /* Take a nap, wait for some writeback to complete */ if (sc->nr_scanned && priority < DEF_PRIORITY - 2) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } /* top priority shrink_zones still had more to do? don't OOM, then */ if (!sc->all_unreclaimable && scanning_global_lru(sc)) @@ -1960,7 +1960,7 @@ loop_again: * another pass across the zones. */ if (total_scanned && priority < DEF_PRIORITY - 2) - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); /* * We do this so kswapd doesn't build up large priorities for @@ -2233,7 +2233,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages) goto out; if (sc.nr_scanned && prio < DEF_PRIORITY - 2) - congestion_wait(WRITE, HZ / 10); + congestion_wait(BLK_RW_ASYNC, HZ / 10); } } -- cgit v1.2.3 From ecb554a846f8e9d2a58f6d6c118168a63ac065aa Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Thu, 9 Jul 2009 14:46:53 +0200 Subject: block: fix sg SG_DXFER_TO_FROM_DEV regression I overlooked SG_DXFER_TO_FROM_DEV support when I converted sg to use the block layer mapping API (2.6.28). Douglas Gilbert explained SG_DXFER_TO_FROM_DEV: http://www.spinics.net/lists/linux-scsi/msg37135.html = The semantics of SG_DXFER_TO_FROM_DEV were: - copy user space buffer to kernel (LLD) buffer - do SCSI command which is assumed to be of the DATA_IN (data from device) variety. This would overwrite some or all of the kernel buffer - copy kernel (LLD) buffer back to the user space. The idea was to detect short reads by filling the original user space buffer with some marker bytes ("0xec" it would seem in this report). The "resid" value is a better way of detecting short reads but that was only added this century and requires co-operation from the LLD. = This patch changes the block layer mapping API to support this semantics. This simply adds another field to struct rq_map_data and enables __bio_copy_iov() to copy data from user space even with READ requests. It's better to add the flags field and kills null_mapped and the new from_user fields in struct rq_map_data but that approach makes it difficult to send this patch to stable trees because st and osst drivers use struct rq_map_data (they were converted to use the block layer in 2.6.29 and 2.6.30). Well, I should clean up the block layer mapping API. zhou sf reported this regiression and tested this patch: http://www.spinics.net/lists/linux-scsi/msg37128.html http://www.spinics.net/lists/linux-scsi/msg37168.html Reported-by: zhou sf Tested-by: zhou sf Cc: stable@kernel.org Signed-off-by: FUJITA Tomonori Signed-off-by: Jens Axboe --- drivers/scsi/sg.c | 4 ++++ fs/bio.c | 22 ++++++++++++---------- include/linux/blkdev.h | 1 + 3 files changed, 17 insertions(+), 10 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 4d6f2fe1cfe9..9230402c45af 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1656,6 +1656,10 @@ static int sg_start_req(Sg_request *srp, unsigned char *cmd) md->nr_entries = req_schp->k_use_sg; md->offset = 0; md->null_mapped = hp->dxferp ? 0 : 1; + if (dxfer_dir == SG_DXFER_TO_FROM_DEV) + md->from_user = 1; + else + md->from_user = 0; } if (iov_count) { diff --git a/fs/bio.c b/fs/bio.c index 1486b19fc431..76738005c8e8 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -705,14 +705,13 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count, } static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs, - struct sg_iovec *iov, int iov_count, int uncopy, - int do_free_page) + struct sg_iovec *iov, int iov_count, + int to_user, int from_user, int do_free_page) { int ret = 0, i; struct bio_vec *bvec; int iov_idx = 0; unsigned int iov_off = 0; - int read = bio_data_dir(bio) == READ; __bio_for_each_segment(bvec, bio, i, 0) { char *bv_addr = page_address(bvec->bv_page); @@ -727,13 +726,14 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs, iov_addr = iov[iov_idx].iov_base + iov_off; if (!ret) { - if (!read && !uncopy) - ret = copy_from_user(bv_addr, iov_addr, - bytes); - if (read && uncopy) + if (to_user) ret = copy_to_user(iov_addr, bv_addr, bytes); + if (from_user) + ret = copy_from_user(bv_addr, iov_addr, + bytes); + if (ret) ret = -EFAULT; } @@ -770,7 +770,8 @@ int bio_uncopy_user(struct bio *bio) if (!bio_flagged(bio, BIO_NULL_MAPPED)) ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs, - bmd->nr_sgvecs, 1, bmd->is_our_pages); + bmd->nr_sgvecs, bio_data_dir(bio) == READ, + 0, bmd->is_our_pages); bio_free_map_data(bmd); bio_put(bio); return ret; @@ -875,8 +876,9 @@ struct bio *bio_copy_user_iov(struct request_queue *q, /* * success */ - if (!write_to_vm && (!map_data || !map_data->null_mapped)) { - ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 0); + if ((!write_to_vm && (!map_data || !map_data->null_mapped)) || + (map_data && map_data->from_user)) { + ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 1, 0); if (ret) goto cleanup; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb3d39978701..0146e0fecf1a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -723,6 +723,7 @@ struct rq_map_data { int nr_entries; unsigned long offset; int null_mapped; + int from_user; }; struct req_iterator { -- cgit v1.2.3 From 373c0a7ed3ea3b34efedb7c83ffb521adff7c894 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 11 Jul 2009 10:06:54 -0400 Subject: Fix compile error due to congestion_wait() changes Move the definition of BLK_RW_ASYNC/BLK_RW_SYNC into linux/backing-dev.h so that it is available to all callers of set/clear_bdi_congested(). This replaces commit 097041e576ee3a50d92dd643ee8ca65bf6a62e21 ("fuse: Fix build error"), which will be reverted. Signed-off-by: Trond Myklebust Acked-by: Larry Finger Cc: Jens Axboe Cc: Miklos Szeredi Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 5 +++++ include/linux/blkdev.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 3a52a63c1351..1d52425a6118 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -229,6 +229,11 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << BDI_async_congested)); } +enum { + BLK_RW_ASYNC = 0, + BLK_RW_SYNC = 1, +}; + void clear_bdi_congested(struct backing_dev_info *bdi, int sync); void set_bdi_congested(struct backing_dev_info *bdi, int sync); long congestion_wait(int sync, long timeout); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0146e0fecf1a..e7cb5dbf6c26 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -70,11 +70,6 @@ enum rq_cmd_type_bits { REQ_TYPE_ATA_PC, }; -enum { - BLK_RW_ASYNC = 0, - BLK_RW_SYNC = 1, -}; - /* * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a -- cgit v1.2.3 From 7c958e32649e0c35801762878fb0b6da8c55a515 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 31 Jul 2009 11:49:11 -0400 Subject: block: Add a wrapper for setting minimum request size without a queue Introduce blk_limits_io_min() and make blk_queue_io_min() call it. Signed-off-by: Mike Snitzer Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 31 ++++++++++++++++++++++++------- include/linux/blkdev.h | 1 + 2 files changed, 25 insertions(+), 7 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 8e86e2d2b147..1f7197434166 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -383,6 +383,29 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset) } EXPORT_SYMBOL(blk_queue_alignment_offset); +/** + * blk_limits_io_min - set minimum request size for a device + * @limits: the queue limits + * @min: smallest I/O size in bytes + * + * Description: + * Some devices have an internal block size bigger than the reported + * hardware sector size. This function can be used to signal the + * smallest I/O the device can perform without incurring a performance + * penalty. + */ +void blk_limits_io_min(struct queue_limits *limits, unsigned int min) +{ + limits->io_min = min; + + if (limits->io_min < limits->logical_block_size) + limits->io_min = limits->logical_block_size; + + if (limits->io_min < limits->physical_block_size) + limits->io_min = limits->physical_block_size; +} +EXPORT_SYMBOL(blk_limits_io_min); + /** * blk_queue_io_min - set minimum request size for the queue * @q: the request queue for the device @@ -396,13 +419,7 @@ EXPORT_SYMBOL(blk_queue_alignment_offset); */ void blk_queue_io_min(struct request_queue *q, unsigned int min) { - q->limits.io_min = min; - - if (q->limits.io_min < q->limits.logical_block_size) - q->limits.io_min = q->limits.logical_block_size; - - if (q->limits.io_min < q->limits.physical_block_size) - q->limits.io_min = q->limits.physical_block_size; + blk_limits_io_min(&q->limits, min); } EXPORT_SYMBOL(blk_queue_io_min); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e7cb5dbf6c26..69103e053c92 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -913,6 +913,7 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned short) extern void blk_queue_physical_block_size(struct request_queue *, unsigned short); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); +extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_default_limits(struct queue_limits *lim); -- cgit v1.2.3 From a82afdfcb8c0df09776b6458af6b68fc58b2e87b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Jul 2009 17:48:16 +0900 Subject: block: use the same failfast bits for bio and request bio and request use the same set of failfast bits. This patch makes the following changes to simplify things. * enumify BIO_RW* bits and reorder bits such that BIOS_RW_FAILFAST_* bits coincide with __REQ_FAILFAST_* bits. * The above pushes BIO_RW_AHEAD out of sync with __REQ_FAILFAST_DEV but the matching is useless anyway. init_request_from_bio() is responsible for setting FAILFAST bits on FS requests and non-FS requests never use BIO_RW_AHEAD. Drop the code and comment from blk_rq_bio_prep(). * Define REQ_FAILFAST_MASK which is OR of all FAILFAST bits and simplify FAILFAST flags handling in init_request_from_bio(). Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-core.c | 19 +++++++------------ include/linux/bio.h | 43 +++++++++++++++++++++++-------------------- include/linux/blkdev.h | 4 ++++ 3 files changed, 34 insertions(+), 32 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index e3299a77a0d8..4daae1ee2b23 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1111,17 +1111,13 @@ void init_request_from_bio(struct request *req, struct bio *bio) req->cmd_type = REQ_TYPE_FS; /* - * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST) + * Inherit FAILFAST from bio (for read-ahead, and explicit + * FAILFAST). FAILFAST flags are identical for req and bio. */ if (bio_rw_ahead(bio)) - req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | - REQ_FAILFAST_DRIVER); - if (bio_failfast_dev(bio)) - req->cmd_flags |= REQ_FAILFAST_DEV; - if (bio_failfast_transport(bio)) - req->cmd_flags |= REQ_FAILFAST_TRANSPORT; - if (bio_failfast_driver(bio)) - req->cmd_flags |= REQ_FAILFAST_DRIVER; + req->cmd_flags |= REQ_FAILFAST_MASK; + else + req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK; if (unlikely(bio_discard(bio))) { req->cmd_flags |= REQ_DISCARD; @@ -2239,9 +2235,8 @@ EXPORT_SYMBOL(__blk_end_request_cur); void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio) { - /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw, and - we want BIO_RW_AHEAD (bit 1) to imply REQ_FAILFAST (bit 1). */ - rq->cmd_flags |= (bio->bi_rw & 3); + /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */ + rq->cmd_flags |= bio->bi_rw & REQ_RW; if (bio_has_data(bio)) { rq->nr_phys_segments = bio_phys_segments(q, bio); diff --git a/include/linux/bio.h b/include/linux/bio.h index 2892b710771c..a299ed38fcd7 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -142,37 +142,40 @@ struct bio { * * bit 0 -- data direction * If not set, bio is a read from device. If set, it's a write to device. - * bit 1 -- rw-ahead when set - * bit 2 -- barrier + * bit 1 -- fail fast device errors + * bit 2 -- fail fast transport errors + * bit 3 -- fail fast driver errors + * bit 4 -- rw-ahead when set + * bit 5 -- barrier * Insert a serialization point in the IO queue, forcing previously * submitted IO to be completed before this one is issued. - * bit 3 -- synchronous I/O hint. - * bit 4 -- Unplug the device immediately after submitting this bio. - * bit 5 -- metadata request + * bit 6 -- synchronous I/O hint. + * bit 7 -- Unplug the device immediately after submitting this bio. + * bit 8 -- metadata request * Used for tracing to differentiate metadata and data IO. May also * get some preferential treatment in the IO scheduler - * bit 6 -- discard sectors + * bit 9 -- discard sectors * Informs the lower level device that this range of sectors is no longer * used by the file system and may thus be freed by the device. Used * for flash based storage. - * bit 7 -- fail fast device errors - * bit 8 -- fail fast transport errors - * bit 9 -- fail fast driver errors * Don't want driver retries for any fast fail whatever the reason. * bit 10 -- Tell the IO scheduler not to wait for more requests after this one has been submitted, even if it is a SYNC request. */ -#define BIO_RW 0 /* Must match RW in req flags (blkdev.h) */ -#define BIO_RW_AHEAD 1 /* Must match FAILFAST in req flags */ -#define BIO_RW_BARRIER 2 -#define BIO_RW_SYNCIO 3 -#define BIO_RW_UNPLUG 4 -#define BIO_RW_META 5 -#define BIO_RW_DISCARD 6 -#define BIO_RW_FAILFAST_DEV 7 -#define BIO_RW_FAILFAST_TRANSPORT 8 -#define BIO_RW_FAILFAST_DRIVER 9 -#define BIO_RW_NOIDLE 10 +enum bio_rw_flags { + BIO_RW, + BIO_RW_FAILFAST_DEV, + BIO_RW_FAILFAST_TRANSPORT, + BIO_RW_FAILFAST_DRIVER, + /* above flags must match REQ_* */ + BIO_RW_AHEAD, + BIO_RW_BARRIER, + BIO_RW_SYNCIO, + BIO_RW_UNPLUG, + BIO_RW_META, + BIO_RW_DISCARD, + BIO_RW_NOIDLE, +}; #define bio_rw_flagged(bio, flag) ((bio)->bi_rw & (1 << (flag))) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 69103e053c92..c3015736d814 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -93,6 +93,7 @@ enum rq_flag_bits { __REQ_FAILFAST_DEV, /* no driver retries of device errors */ __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ + /* above flags must match BIO_RW_* */ __REQ_DISCARD, /* request to discard sectors */ __REQ_SORTED, /* elevator knows about this request */ __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ @@ -143,6 +144,9 @@ enum rq_flag_bits { #define REQ_NOIDLE (1 << __REQ_NOIDLE) #define REQ_IO_STAT (1 << __REQ_IO_STAT) +#define REQ_FAILFAST_MASK (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \ + REQ_FAILFAST_DRIVER) + #define BLK_MAX_CDB 16 /* -- cgit v1.2.3 From 80a761fd33cf812f771e212139157bf8f58d4b3f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Jul 2009 17:48:17 +0900 Subject: block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo Cc: Niel Lambrechts Signed-off-by: Jens Axboe --- block/blk-core.c | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++ block/blk-merge.c | 43 ++++++++++++++++++++++ block/blk.h | 1 + include/linux/blkdev.h | 23 +++++++++--- 4 files changed, 161 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 4daae1ee2b23..c822239bcc9d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1157,6 +1157,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) const unsigned short prio = bio_prio(bio); const int sync = bio_sync(bio); const int unplug = bio_unplug(bio); + const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK; int rw_flags; if (bio_barrier(bio) && bio_has_data(bio) && @@ -1186,6 +1187,9 @@ static int __make_request(struct request_queue *q, struct bio *bio) trace_block_bio_backmerge(q, bio); + if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) + blk_rq_set_mixed_merge(req); + req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bytes; @@ -1205,6 +1209,12 @@ static int __make_request(struct request_queue *q, struct bio *bio) trace_block_bio_frontmerge(q, bio); + if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) { + blk_rq_set_mixed_merge(req); + req->cmd_flags &= ~REQ_FAILFAST_MASK; + req->cmd_flags |= ff; + } + bio->bi_next = req->bio; req->bio = bio; @@ -1649,6 +1659,50 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq) } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); +/** + * blk_rq_err_bytes - determine number of bytes till the next failure boundary + * @rq: request to examine + * + * Description: + * A request could be merge of IOs which require different failure + * handling. This function determines the number of bytes which + * can be failed from the beginning of the request without + * crossing into area which need to be retried further. + * + * Return: + * The number of bytes to fail. + * + * Context: + * queue_lock must be held. + */ +unsigned int blk_rq_err_bytes(const struct request *rq) +{ + unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; + unsigned int bytes = 0; + struct bio *bio; + + if (!(rq->cmd_flags & REQ_MIXED_MERGE)) + return blk_rq_bytes(rq); + + /* + * Currently the only 'mixing' which can happen is between + * different fastfail types. We can safely fail portions + * which have all the failfast bits that the first one has - + * the ones which are at least as eager to fail as the first + * one. + */ + for (bio = rq->bio; bio; bio = bio->bi_next) { + if ((bio->bi_rw & ff) != ff) + break; + bytes += bio->bi_size; + } + + /* this could lead to infinite loop */ + BUG_ON(blk_rq_bytes(rq) && !bytes); + return bytes; +} +EXPORT_SYMBOL_GPL(blk_rq_err_bytes); + static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (blk_do_io_stat(req)) { @@ -1995,6 +2049,12 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) if (blk_fs_request(req) || blk_discard_rq(req)) req->__sector += total_bytes >> 9; + /* mixed attributes always follow the first bio */ + if (req->cmd_flags & REQ_MIXED_MERGE) { + req->cmd_flags &= ~REQ_FAILFAST_MASK; + req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK; + } + /* * If total number of sectors is less than the first segment * size, something has gone terribly wrong. @@ -2173,6 +2233,25 @@ bool blk_end_request_cur(struct request *rq, int error) } EXPORT_SYMBOL(blk_end_request_cur); +/** + * blk_end_request_err - Finish a request till the next failure boundary. + * @rq: the request to finish till the next failure boundary for + * @error: must be negative errno + * + * Description: + * Complete @rq till the next failure boundary. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool blk_end_request_err(struct request *rq, int error) +{ + WARN_ON(error >= 0); + return blk_end_request(rq, error, blk_rq_err_bytes(rq)); +} +EXPORT_SYMBOL_GPL(blk_end_request_err); + /** * __blk_end_request - Helper function for drivers to complete the request. * @rq: the request being processed @@ -2232,6 +2311,26 @@ bool __blk_end_request_cur(struct request *rq, int error) } EXPORT_SYMBOL(__blk_end_request_cur); +/** + * __blk_end_request_err - Finish a request till the next failure boundary. + * @rq: the request to finish till the next failure boundary for + * @error: must be negative errno + * + * Description: + * Complete @rq till the next failure boundary. Must be called + * with queue lock held. + * + * Return: + * %false - we are done with this request + * %true - still buffers pending for this request + */ +bool __blk_end_request_err(struct request *rq, int error) +{ + WARN_ON(error >= 0); + return __blk_end_request(rq, error, blk_rq_err_bytes(rq)); +} +EXPORT_SYMBOL_GPL(__blk_end_request_err); + void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio) { diff --git a/block/blk-merge.c b/block/blk-merge.c index e1999679a4d5..7c9ca01baa45 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -311,6 +311,36 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, return 1; } +/** + * blk_rq_set_mixed_merge - mark a request as mixed merge + * @rq: request to mark as mixed merge + * + * Description: + * @rq is about to be mixed merged. Make sure the attributes + * which can be mixed are set in each bio and mark @rq as mixed + * merged. + */ +void blk_rq_set_mixed_merge(struct request *rq) +{ + unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; + struct bio *bio; + + if (rq->cmd_flags & REQ_MIXED_MERGE) + return; + + /* + * @rq will no longer represent mixable attributes for all the + * contained bios. It will just track those of the first one. + * Distributes the attributs to each bio. + */ + for (bio = rq->bio; bio; bio = bio->bi_next) { + WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) && + (bio->bi_rw & REQ_FAILFAST_MASK) != ff); + bio->bi_rw |= ff; + } + rq->cmd_flags |= REQ_MIXED_MERGE; +} + static void blk_account_io_merge(struct request *req) { if (blk_do_io_stat(req)) { @@ -365,6 +395,19 @@ static int attempt_merge(struct request_queue *q, struct request *req, if (!ll_merge_requests_fn(q, req, next)) return 0; + /* + * If failfast settings disagree or any of the two is already + * a mixed merge, mark both as mixed before proceeding. This + * makes sure that all involved bios have mixable attributes + * set properly. + */ + if ((req->cmd_flags | next->cmd_flags) & REQ_MIXED_MERGE || + (req->cmd_flags & REQ_FAILFAST_MASK) != + (next->cmd_flags & REQ_FAILFAST_MASK)) { + blk_rq_set_mixed_merge(req); + blk_rq_set_mixed_merge(next); + } + /* * At this point we have either done a back merge * or front merge. We need the smaller start_time of diff --git a/block/blk.h b/block/blk.h index 3fae6add5430..5ee3d7e72feb 100644 --- a/block/blk.h +++ b/block/blk.h @@ -104,6 +104,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req, int attempt_back_merge(struct request_queue *q, struct request *rq); int attempt_front_merge(struct request_queue *q, struct request *rq); void blk_recalc_rq_segments(struct request *rq); +void blk_rq_set_mixed_merge(struct request *rq); void blk_queue_congestion_threshold(struct request_queue *q); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c3015736d814..650b6a9cb679 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -115,6 +115,7 @@ enum rq_flag_bits { __REQ_INTEGRITY, /* integrity metadata has been remapped */ __REQ_NOIDLE, /* Don't anticipate more IO after this one */ __REQ_IO_STAT, /* account I/O stat */ + __REQ_MIXED_MERGE, /* merge of different types, fail separately */ __REQ_NR_BITS, /* stops here */ }; @@ -143,6 +144,7 @@ enum rq_flag_bits { #define REQ_INTEGRITY (1 << __REQ_INTEGRITY) #define REQ_NOIDLE (1 << __REQ_NOIDLE) #define REQ_IO_STAT (1 << __REQ_IO_STAT) +#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) #define REQ_FAILFAST_MASK (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \ REQ_FAILFAST_DRIVER) @@ -832,11 +834,13 @@ static inline void blk_run_address_space(struct address_space *mapping) } /* - * blk_rq_pos() : the current sector - * blk_rq_bytes() : bytes left in the entire request - * blk_rq_cur_bytes() : bytes left in the current segment - * blk_rq_sectors() : sectors left in the entire request - * blk_rq_cur_sectors() : sectors left in the current segment + * blk_rq_pos() : the current sector + * blk_rq_bytes() : bytes left in the entire request + * blk_rq_cur_bytes() : bytes left in the current segment + * blk_rq_err_bytes() : bytes left till the next error boundary + * blk_rq_sectors() : sectors left in the entire request + * blk_rq_cur_sectors() : sectors left in the current segment + * blk_rq_err_sectors() : sectors left till the next error boundary */ static inline sector_t blk_rq_pos(const struct request *rq) { @@ -853,6 +857,8 @@ static inline int blk_rq_cur_bytes(const struct request *rq) return rq->bio ? bio_cur_bytes(rq->bio) : 0; } +extern unsigned int blk_rq_err_bytes(const struct request *rq); + static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> 9; @@ -863,6 +869,11 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> 9; } +static inline unsigned int blk_rq_err_sectors(const struct request *rq) +{ + return blk_rq_err_bytes(rq) >> 9; +} + /* * Request issue related functions. */ @@ -889,10 +900,12 @@ extern bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes); extern void blk_end_request_all(struct request *rq, int error); extern bool blk_end_request_cur(struct request *rq, int error); +extern bool blk_end_request_err(struct request *rq, int error); extern bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes); extern void __blk_end_request_all(struct request *rq, int error); extern bool __blk_end_request_cur(struct request *rq, int error); +extern bool __blk_end_request_err(struct request *rq, int error); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); -- cgit v1.2.3 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 --- block/blk-core.c | 25 +++++++++++++------------ block/cfq-iosched.c | 2 +- block/elevator.c | 3 ++- drivers/block/loop.c | 2 +- drivers/md/dm-raid1.c | 2 +- drivers/md/dm-stripe.c | 2 +- drivers/md/dm.c | 12 ++++++------ drivers/md/linear.c | 2 +- drivers/md/multipath.c | 4 ++-- drivers/md/raid0.c | 2 +- drivers/md/raid1.c | 14 ++++++++------ drivers/md/raid10.c | 6 +++--- drivers/md/raid5.c | 2 +- drivers/staging/dst/dcore.c | 5 +++-- fs/btrfs/volumes.c | 4 ++-- include/linux/bio.h | 25 +++++++------------------ include/linux/blkdev.h | 2 +- 17 files changed, 54 insertions(+), 60 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index c822239bcc9d..52559715cb90 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1114,24 +1114,24 @@ void init_request_from_bio(struct request *req, struct bio *bio) * Inherit FAILFAST from bio (for read-ahead, and explicit * FAILFAST). FAILFAST flags are identical for req and bio. */ - if (bio_rw_ahead(bio)) + if (bio_rw_flagged(bio, BIO_RW_AHEAD)) req->cmd_flags |= REQ_FAILFAST_MASK; else req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK; - if (unlikely(bio_discard(bio))) { + if (unlikely(bio_rw_flagged(bio, BIO_RW_DISCARD))) { req->cmd_flags |= REQ_DISCARD; - if (bio_barrier(bio)) + if (bio_rw_flagged(bio, BIO_RW_BARRIER)) req->cmd_flags |= REQ_SOFTBARRIER; req->q->prepare_discard_fn(req->q, req); - } else if (unlikely(bio_barrier(bio))) + } else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) req->cmd_flags |= REQ_HARDBARRIER; - if (bio_sync(bio)) + if (bio_rw_flagged(bio, BIO_RW_SYNCIO)) req->cmd_flags |= REQ_RW_SYNC; - if (bio_rw_meta(bio)) + if (bio_rw_flagged(bio, BIO_RW_META)) req->cmd_flags |= REQ_RW_META; - if (bio_noidle(bio)) + if (bio_rw_flagged(bio, BIO_RW_NOIDLE)) req->cmd_flags |= REQ_NOIDLE; req->errors = 0; @@ -1155,12 +1155,12 @@ static int __make_request(struct request_queue *q, struct bio *bio) int el_ret; unsigned int bytes = bio->bi_size; const unsigned short prio = bio_prio(bio); - const int sync = bio_sync(bio); - const int unplug = bio_unplug(bio); + const bool sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); + const bool unplug = bio_rw_flagged(bio, BIO_RW_UNPLUG); const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK; int rw_flags; - if (bio_barrier(bio) && bio_has_data(bio) && + if (bio_rw_flagged(bio, BIO_RW_BARRIER) && bio_has_data(bio) && (q->next_ordered == QUEUE_ORDERED_NONE)) { bio_endio(bio, -EOPNOTSUPP); return 0; @@ -1174,7 +1174,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) spin_lock_irq(q->queue_lock); - if (unlikely(bio_barrier(bio)) || elv_queue_empty(q)) + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q)) goto get_rq; el_ret = elv_merge(q, &req, bio); @@ -1470,7 +1470,8 @@ static inline void __generic_make_request(struct bio *bio) if (bio_check_eod(bio, nr_sectors)) goto end_io; - if (bio_discard(bio) && !q->prepare_discard_fn) { + if (bio_rw_flagged(bio, BIO_RW_DISCARD) && + !q->prepare_discard_fn) { err = -EOPNOTSUPP; goto end_io; } diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index ca0d7e71324b..9e6d0af6c990 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -257,7 +257,7 @@ static inline void cic_set_cfqq(struct cfq_io_context *cic, */ static inline int cfq_bio_sync(struct bio *bio) { - if (bio_data_dir(bio) == READ || bio_sync(bio)) + if (bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO)) return 1; return 0; diff --git a/block/elevator.c b/block/elevator.c index ca861927ba41..1975b619c86d 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -79,7 +79,8 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio) /* * Don't merge file system requests and discard requests */ - if (bio_discard(bio) != bio_discard(rq->bio)) + if (bio_rw_flagged(bio, BIO_RW_DISCARD) != + bio_rw_flagged(rq->bio, BIO_RW_DISCARD)) return 0; /* diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 5757188cd1fb..bbb79441d895 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -475,7 +475,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio) pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset; if (bio_rw(bio) == WRITE) { - int barrier = bio_barrier(bio); + bool barrier = bio_rw_flagged(bio, BIO_RW_BARRIER); struct file *file = lo->lo_backing_file; if (barrier) { diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 33f179e66bf5..cc9dc79b0784 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1129,7 +1129,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, if (error == -EOPNOTSUPP) goto out; - if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio)) + if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD)) goto out; if (unlikely(error)) { diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 3e563d251733..fde658ccbcec 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -285,7 +285,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio, if (!error) return 0; /* I/O complete */ - if ((error == -EWOULDBLOCK) && bio_rw_ahead(bio)) + if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD)) return error; if (error == -EOPNOTSUPP) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index b4845b14740d..ec012f030240 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -586,7 +586,7 @@ static void dec_pending(struct dm_io *io, int error) */ spin_lock_irqsave(&md->deferred_lock, flags); if (__noflush_suspending(md)) { - if (!bio_barrier(io->bio)) + if (!bio_rw_flagged(io->bio, BIO_RW_BARRIER)) bio_list_add_head(&md->deferred, io->bio); } else @@ -598,7 +598,7 @@ static void dec_pending(struct dm_io *io, int error) io_error = io->error; bio = io->bio; - if (bio_barrier(bio)) { + if (bio_rw_flagged(bio, BIO_RW_BARRIER)) { /* * There can be just one barrier request so we use * a per-device variable for error reporting. @@ -1209,7 +1209,7 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio) ci.map = dm_get_table(md); if (unlikely(!ci.map)) { - if (!bio_barrier(bio)) + if (!bio_rw_flagged(bio, BIO_RW_BARRIER)) bio_io_error(bio); else if (!md->barrier_error) @@ -1321,7 +1321,7 @@ static int _dm_request(struct request_queue *q, struct bio *bio) * we have to queue this io for later. */ if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) || - unlikely(bio_barrier(bio))) { + unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { up_read(&md->io_lock); if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) && @@ -1344,7 +1344,7 @@ static int dm_make_request(struct request_queue *q, struct bio *bio) { struct mapped_device *md = q->queuedata; - if (unlikely(bio_barrier(bio))) { + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { bio_endio(bio, -EOPNOTSUPP); return 0; } @@ -2164,7 +2164,7 @@ static void dm_wq_work(struct work_struct *work) if (dm_request_based(md)) generic_make_request(c); else { - if (bio_barrier(c)) + if (bio_rw_flagged(c, BIO_RW_BARRIER)) process_barrier(md, c); else __split_and_process_bio(md, c); diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 5fe39c2a3d2b..ea4842905444 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -288,7 +288,7 @@ static int linear_make_request (struct request_queue *q, struct bio *bio) sector_t start_sector; int cpu; - if (unlikely(bio_barrier(bio))) { + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { bio_endio(bio, -EOPNOTSUPP); return 0; } diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 7140909f6662..89e76819f61f 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -90,7 +90,7 @@ static void multipath_end_request(struct bio *bio, int error) if (uptodate) multipath_end_bh_io(mp_bh, 0); - else if (!bio_rw_ahead(bio)) { + else if (!bio_rw_flagged(bio, BIO_RW_AHEAD)) { /* * oops, IO error: */ @@ -144,7 +144,7 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio) const int rw = bio_data_dir(bio); int cpu; - if (unlikely(bio_barrier(bio))) { + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { bio_endio(bio, -EOPNOTSUPP); return 0; } diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 898e2bdfee47..f845ed98fec9 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -448,7 +448,7 @@ static int raid0_make_request(struct request_queue *q, struct bio *bio) const int rw = bio_data_dir(bio); int cpu; - if (unlikely(bio_barrier(bio))) { + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { bio_endio(bio, -EOPNOTSUPP); return 0; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 8726fd7ebce5..ff7ed3335995 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -782,8 +782,9 @@ static int make_request(struct request_queue *q, struct bio * bio) struct bio_list bl; struct page **behind_pages = NULL; const int rw = bio_data_dir(bio); - const int do_sync = bio_sync(bio); - int cpu, do_barriers; + const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); + int cpu; + bool do_barriers; mdk_rdev_t *blocked_rdev; /* @@ -797,7 +798,8 @@ static int make_request(struct request_queue *q, struct bio * bio) md_write_start(mddev, bio); /* wait on superblock update early */ - if (unlikely(!mddev->barriers_work && bio_barrier(bio))) { + if (unlikely(!mddev->barriers_work && + bio_rw_flagged(bio, BIO_RW_BARRIER))) { if (rw == WRITE) md_write_end(mddev); bio_endio(bio, -EOPNOTSUPP); @@ -925,7 +927,7 @@ static int make_request(struct request_queue *q, struct bio * bio) atomic_set(&r1_bio->remaining, 0); atomic_set(&r1_bio->behind_remaining, 0); - do_barriers = bio_barrier(bio); + do_barriers = bio_rw_flagged(bio, BIO_RW_BARRIER); if (do_barriers) set_bit(R1BIO_Barrier, &r1_bio->state); @@ -1600,7 +1602,7 @@ static void raid1d(mddev_t *mddev) * We already have a nr_pending reference on these rdevs. */ int i; - const int do_sync = bio_sync(r1_bio->master_bio); + const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO); clear_bit(R1BIO_BarrierRetry, &r1_bio->state); clear_bit(R1BIO_Barrier, &r1_bio->state); for (i=0; i < conf->raid_disks; i++) @@ -1654,7 +1656,7 @@ static void raid1d(mddev_t *mddev) (unsigned long long)r1_bio->sector); raid_end_bio_io(r1_bio); } else { - const int do_sync = bio_sync(r1_bio->master_bio); + const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO); r1_bio->bios[r1_bio->read_disk] = mddev->ro ? IO_BLOCKED : NULL; r1_bio->read_disk = disk; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 3d9020cf6f6e..d0a2152e064f 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -796,12 +796,12 @@ static int make_request(struct request_queue *q, struct bio * bio) int i; int chunk_sects = conf->chunk_mask + 1; const int rw = bio_data_dir(bio); - const int do_sync = bio_sync(bio); + const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); struct bio_list bl; unsigned long flags; mdk_rdev_t *blocked_rdev; - if (unlikely(bio_barrier(bio))) { + if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { bio_endio(bio, -EOPNOTSUPP); return 0; } @@ -1610,7 +1610,7 @@ static void raid10d(mddev_t *mddev) raid_end_bio_io(r10_bio); bio_put(bio); } else { - const int do_sync = bio_sync(r10_bio->master_bio); + const bool do_sync = bio_rw_flagged(r10_bio->master_bio, BIO_RW_SYNCIO); bio_put(bio); rdev = conf->mirrors[mirror].rdev; if (printk_ratelimit()) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index b8a2c5dc67ba..826eb3467357 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3606,7 +3606,7 @@ static int make_request(struct request_queue *q, struct bio * bi) const int rw = bio_data_dir(bi); int cpu, remaining; - if (unlikely(bio_barrier(bi))) { + if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) { bio_endio(bi, -EOPNOTSUPP); return 0; } diff --git a/drivers/staging/dst/dcore.c b/drivers/staging/dst/dcore.c index fad25b753042..b1c258ca2102 100644 --- a/drivers/staging/dst/dcore.c +++ b/drivers/staging/dst/dcore.c @@ -112,8 +112,9 @@ static int dst_request(struct request_queue *q, struct bio *bio) * I worked with. * * Empty barriers are not allowed anyway, see 51fd77bd9f512 - * for example, although later it was changed to bio_discard() - * only, which does not work in this case. + * for example, although later it was changed to + * bio_rw_flagged(bio, BIO_RW_DISCARD) only, which does not + * work in this case. */ //err = -EOPNOTSUPP; err = 0; 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; diff --git a/include/linux/bio.h b/include/linux/bio.h index 4f8fd0221cd2..5be93f18d842 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -177,28 +177,17 @@ enum bio_rw_flags { BIO_RW_NOIDLE, }; +/* + * First four bits must match between bio->bi_rw and rq->cmd_flags, make + * that explicit here. + */ +#define BIO_RW_RQ_MASK 0xf + static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag) { return (bio->bi_rw & (1 << flag)) != 0; } -/* - * Old defines, these should eventually be replaced by direct usage of - * bio_rw_flagged() - */ -#define bio_barrier(bio) bio_rw_flagged(bio, BIO_RW_BARRIER) -#define bio_sync(bio) bio_rw_flagged(bio, BIO_RW_SYNCIO) -#define bio_unplug(bio) bio_rw_flagged(bio, BIO_RW_UNPLUG) -#define bio_failfast_dev(bio) bio_rw_flagged(bio, BIO_RW_FAILFAST_DEV) -#define bio_failfast_transport(bio) \ - bio_rw_flagged(bio, BIO_RW_FAILFAST_TRANSPORT) -#define bio_failfast_driver(bio) \ - bio_rw_flagged(bio, BIO_RW_FAILFAST_DRIVER) -#define bio_rw_ahead(bio) bio_rw_flagged(bio, BIO_RW_AHEAD) -#define bio_rw_meta(bio) bio_rw_flagged(bio, BIO_RW_META) -#define bio_discard(bio) bio_rw_flagged(bio, BIO_RW_DISCARD) -#define bio_noidle(bio) bio_rw_flagged(bio, BIO_RW_NOIDLE) - /* * upper 16 bits of bi_rw define the io priority of this bio */ @@ -222,7 +211,7 @@ static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag) #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) -#define bio_empty_barrier(bio) (bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio)) +#define bio_empty_barrier(bio) (bio_rw_flagged(bio, BIO_RW_BARRIER) && !bio_has_data(bio) && !bio_rw_flagged(bio, BIO_RW_DISCARD)) static inline unsigned int bio_cur_bytes(struct bio *bio) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 650b6a9cb679..88edb62def82 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -86,7 +86,7 @@ enum { }; /* - * request type modified bits. first two bits match BIO_RW* bits, important + * request type modified bits. first four bits match BIO_RW* bits, important */ enum rq_flag_bits { __REQ_RW, /* not set, read. set, write */ -- cgit v1.2.3 From fb1e75389bd06fd5987e9cda1b4e0305c782f854 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 30 Jul 2009 08:18:24 +0200 Subject: block: improve queue_should_plug() by looking at IO depths Instead of just checking whether this device uses block layer tagging, we can improve the detection by looking at the maximum queue depth it has reached. If that crosses 4, then deem it a queuing device. This is important on high IOPS devices, since plugging hurts the performance there (it can be as much as 10-15% of the sys time). Signed-off-by: Jens Axboe --- block/blk-core.c | 11 +++++++++-- include/linux/blkdev.h | 2 ++ 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 52559715cb90..93051d151635 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1146,7 +1146,7 @@ void init_request_from_bio(struct request *req, struct bio *bio) */ static inline bool queue_should_plug(struct request_queue *q) { - return !(blk_queue_nonrot(q) && blk_queue_tagged(q)); + return !(blk_queue_nonrot(q) && blk_queue_queuing(q)); } static int __make_request(struct request_queue *q, struct bio *bio) @@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq) * and to it is freed is accounted as io that is in progress at * the driver side. */ - if (blk_account_rq(rq)) + if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]++; + /* + * Mark this device as supporting hardware queuing, if + * we have more IOs in flight than 4. + */ + if (!blk_queue_queuing(q) && queue_in_flight(q) > 4) + set_bit(QUEUE_FLAG_CQ, &q->queue_flags); + } } /** diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 88edb62def82..98b45633a27e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -459,6 +459,7 @@ struct request_queue #define QUEUE_FLAG_NONROT 14 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ +#define QUEUE_FLAG_CQ 16 /* hardware does queuing */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -581,6 +582,7 @@ enum { #define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) #define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) +#define blk_queue_queuing(q) test_bit(QUEUE_FLAG_CQ, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) -- cgit v1.2.3 From 01e97f6b897bf06ec83375d691f2f4d57f5b3a09 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 3 Sep 2009 20:06:47 +0200 Subject: block: enable rq CPU completion affinity by default Test results here look good, and on big OLTP runs it has also shown to significantly increase cycles attributed to the database and cause a performance boost. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 98b45633a27e..8bf1a10e4d88 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -463,7 +463,8 @@ struct request_queue #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ - (1 << QUEUE_FLAG_STACKABLE)) + (1 << QUEUE_FLAG_STACKABLE) | \ + (1 << QUEUE_FLAG_SAME_COMP)) static inline int queue_is_locked(struct request_queue *q) { -- cgit v1.2.3 From 3c5820c743479285ce2678fd3c12b1fd39fe998f Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 11 Sep 2009 21:54:52 +0200 Subject: block: Optimal I/O limit wrapper Implement blk_limits_io_opt() and make blk_queue_io_opt() a wrapper around it. DM needs this to avoid poking at the queue_limits directly. Signed-off-by: Martin K. Petersen Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-settings.c | 21 ++++++++++++++++++++- drivers/md/dm-stripe.c | 2 +- include/linux/blkdev.h | 1 + 3 files changed, 22 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 476d87065073..83413ff83739 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -427,6 +427,25 @@ void blk_queue_io_min(struct request_queue *q, unsigned int min) } EXPORT_SYMBOL(blk_queue_io_min); +/** + * blk_limits_io_opt - set optimal request size for a device + * @limits: the queue limits + * @opt: smallest I/O size in bytes + * + * Description: + * Storage devices may report an optimal I/O size, which is the + * device's preferred unit for sustained I/O. This is rarely reported + * for disk drives. For RAID arrays it is usually the stripe width or + * the internal track size. A properly aligned multiple of + * optimal_io_size is the preferred request size for workloads where + * sustained throughput is desired. + */ +void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt) +{ + limits->io_opt = opt; +} +EXPORT_SYMBOL(blk_limits_io_opt); + /** * blk_queue_io_opt - set optimal request size for the queue * @q: the request queue for the device @@ -442,7 +461,7 @@ EXPORT_SYMBOL(blk_queue_io_min); */ void blk_queue_io_opt(struct request_queue *q, unsigned int opt) { - q->limits.io_opt = opt; + blk_limits_io_opt(&q->limits, opt); } EXPORT_SYMBOL(blk_queue_io_opt); diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index fde658ccbcec..e0efc1adcaff 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -336,7 +336,7 @@ static void stripe_io_hints(struct dm_target *ti, unsigned chunk_size = (sc->chunk_mask + 1) << 9; blk_limits_io_min(limits, chunk_size); - limits->io_opt = chunk_size * sc->stripes; + blk_limits_io_opt(limits, chunk_size * sc->stripes); } static struct target_type stripe_target = { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8bf1a10e4d88..86c2bdff3b89 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -935,6 +935,7 @@ extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); 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 int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, -- 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 'include/linux/blkdev.h') 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 From c15227de132f1295f3db6b7df9079956b1020fd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:52:12 +0200 Subject: block: use normal I/O path for discard requests prepare_discard_fn() was being called in a place where memory allocation was effectively impossible. This makes it inappropriate for all but the most trivial translations of Linux's DISCARD operation to the block command set. Additionally adding a payload there makes the ownership of the bio backing unclear as it's now allocated by the device driver and not the submitter as usual. It is replaced with QUEUE_FLAG_DISCARD which is used to indicate whether the queue supports discard operations or not. blkdev_issue_discard now allocates a one-page, sector-length payload which is the right thing for the common ATA and SCSI implementations. The mtd implementation of prepare_discard_fn() is replaced with simply checking for the request being a discard. Largely based on a previous patch from Matthew Wilcox which did the prepare_discard_fn but not the different payload allocation yet. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 35 ++++++++++++++++++++++++++++++----- block/blk-core.c | 3 +-- block/blk-settings.c | 17 ----------------- drivers/mtd/mtd_blkdevs.c | 19 +++++-------------- drivers/staging/dst/dcore.c | 2 +- include/linux/blkdev.h | 6 ++---- 6 files changed, 39 insertions(+), 43 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 6593ab39cfe9..21f5025c3945 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -350,6 +350,7 @@ static void blkdev_discard_end_io(struct bio *bio, int err) if (bio->bi_private) complete(bio->bi_private); + __free_page(bio_page(bio)); bio_put(bio); } @@ -372,26 +373,44 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, struct request_queue *q = bdev_get_queue(bdev); int type = flags & DISCARD_FL_BARRIER ? DISCARD_BARRIER : DISCARD_NOBARRIER; + struct bio *bio; + struct page *page; int ret = 0; if (!q) return -ENXIO; - if (!q->prepare_discard_fn) + if (!blk_queue_discard(q)) return -EOPNOTSUPP; while (nr_sects && !ret) { - struct bio *bio = bio_alloc(gfp_mask, 0); - if (!bio) - return -ENOMEM; + unsigned int sector_size = q->limits.logical_block_size; + bio = bio_alloc(gfp_mask, 1); + if (!bio) + goto out; + bio->bi_sector = sector; 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; + /* + * Add a zeroed one-sector payload as that's what + * our current implementations need. If we'll ever need + * more the interface will need revisiting. + */ + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + goto out_free_bio; + if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size) + goto out_free_page; + /* + * And override the bio size - the way discard works we + * touch many more blocks on disk than the actual payload + * length. + */ if (nr_sects > queue_max_hw_sectors(q)) { bio->bi_size = queue_max_hw_sectors(q) << 9; nr_sects -= queue_max_hw_sectors(q); @@ -414,5 +433,11 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_put(bio); } return ret; +out_free_page: + __free_page(page); +out_free_bio: + bio_put(bio); +out: + return -ENOMEM; } EXPORT_SYMBOL(blkdev_issue_discard); diff --git a/block/blk-core.c b/block/blk-core.c index 8135228e4b29..80a020dd1580 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1124,7 +1124,6 @@ void init_request_from_bio(struct request *req, struct bio *bio) req->cmd_flags |= REQ_DISCARD; if (bio_rw_flagged(bio, BIO_RW_BARRIER)) req->cmd_flags |= REQ_SOFTBARRIER; - req->q->prepare_discard_fn(req->q, req); } else if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) req->cmd_flags |= REQ_HARDBARRIER; @@ -1470,7 +1469,7 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; if (bio_rw_flagged(bio, BIO_RW_DISCARD) && - !q->prepare_discard_fn) { + !blk_queue_discard(q)) { err = -EOPNOTSUPP; goto end_io; } diff --git a/block/blk-settings.c b/block/blk-settings.c index eaf122ff5f16..d29498ef1eb5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -33,23 +33,6 @@ void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn) } EXPORT_SYMBOL(blk_queue_prep_rq); -/** - * blk_queue_set_discard - set a discard_sectors function for queue - * @q: queue - * @dfn: prepare_discard function - * - * It's possible for a queue to register a discard callback which is used - * to transform a discard request into the appropriate type for the - * hardware. If none is registered, then discard requests are failed - * with %EOPNOTSUPP. - * - */ -void blk_queue_set_discard(struct request_queue *q, prepare_discard_fn *dfn) -{ - q->prepare_discard_fn = dfn; -} -EXPORT_SYMBOL(blk_queue_set_discard); - /** * blk_queue_merge_bvec - set a merge_bvec function for queue * @q: queue diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 0acbf4f5be50..8ca17a3e96ea 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -32,14 +32,6 @@ struct mtd_blkcore_priv { spinlock_t queue_lock; }; -static int blktrans_discard_request(struct request_queue *q, - struct request *req) -{ - req->cmd_type = REQ_TYPE_LINUX_BLOCK; - req->cmd[0] = REQ_LB_OP_DISCARD; - return 0; -} - static int do_blktrans_request(struct mtd_blktrans_ops *tr, struct mtd_blktrans_dev *dev, struct request *req) @@ -52,10 +44,6 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, buf = req->buffer; - if (req->cmd_type == REQ_TYPE_LINUX_BLOCK && - req->cmd[0] == REQ_LB_OP_DISCARD) - return tr->discard(dev, block, nsect); - if (!blk_fs_request(req)) return -EIO; @@ -63,6 +51,9 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, get_capacity(req->rq_disk)) return -EIO; + if (blk_discard_rq(req)) + return tr->discard(dev, block, nsect); + switch(rq_data_dir(req)) { case READ: for (; nsect > 0; nsect--, block++, buf += tr->blksize) @@ -380,8 +371,8 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr) tr->blkcore_priv->rq->queuedata = tr; blk_queue_logical_block_size(tr->blkcore_priv->rq, tr->blksize); if (tr->discard) - blk_queue_set_discard(tr->blkcore_priv->rq, - blktrans_discard_request); + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, + tr->blkcore_priv->rq); tr->blkshift = ffs(tr->blksize) - 1; diff --git a/drivers/staging/dst/dcore.c b/drivers/staging/dst/dcore.c index ac8577358ba0..5e8db0677582 100644 --- a/drivers/staging/dst/dcore.c +++ b/drivers/staging/dst/dcore.c @@ -102,7 +102,7 @@ static int dst_request(struct request_queue *q, struct bio *bio) struct dst_node *n = q->queuedata; int err = -EIO; - if (bio_empty_barrier(bio) && !q->prepare_discard_fn) { + if (bio_empty_barrier(bio) && !blk_queue_discard(q)) { /* * This is a dirty^Wnice hack, but if we complete this * operation with -EOPNOTSUPP like intended, XFS diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e23a86cae5ac..f62d45e87618 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -82,7 +82,6 @@ enum rq_cmd_type_bits { enum { REQ_LB_OP_EJECT = 0x40, /* eject request */ REQ_LB_OP_FLUSH = 0x41, /* flush request */ - REQ_LB_OP_DISCARD = 0x42, /* discard sectors */ }; /* @@ -261,7 +260,6 @@ typedef void (request_fn_proc) (struct request_queue *q); typedef int (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); typedef void (unplug_fn) (struct request_queue *); -typedef int (prepare_discard_fn) (struct request_queue *, struct request *); struct bio_vec; struct bvec_merge_data { @@ -340,7 +338,6 @@ struct request_queue make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; unplug_fn *unplug_fn; - prepare_discard_fn *prepare_discard_fn; merge_bvec_fn *merge_bvec_fn; prepare_flush_fn *prepare_flush_fn; softirq_done_fn *softirq_done_fn; @@ -460,6 +457,7 @@ struct request_queue #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ #define QUEUE_FLAG_CQ 16 /* hardware does queuing */ +#define QUEUE_FLAG_DISCARD 17 /* supports DISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -591,6 +589,7 @@ enum { #define blk_queue_flushing(q) ((q)->ordseq) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) +#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) #define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) @@ -955,7 +954,6 @@ extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); -extern void blk_queue_set_discard(struct request_queue *, prepare_discard_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -- cgit v1.2.3 From 67efc9258010da35b27b3854d0880c7e193004ed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 13:54:20 +0200 Subject: block: allow large discard requests Currently we set the bio size to the byte equivalent of the blocks to be trimmed when submitting the initial DISCARD ioctl. That means it is subject to the max_hw_sectors limitation of the HBA which is much lower than the size of a DISCARD request we can support. Add a separate max_discard_sectors tunable to limit the size for discard requests. We limit the max discard request size in bytes to 32bit as that is the limit for bio->bi_size. This could be much larger if we had a way to pass that information through the block layer. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 10 ++++++---- block/blk-core.c | 3 ++- block/blk-settings.c | 13 +++++++++++++ include/linux/blkdev.h | 3 +++ 4 files changed, 24 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 21f5025c3945..8873b9b439ff 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -385,6 +385,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, while (nr_sects && !ret) { unsigned int sector_size = q->limits.logical_block_size; + unsigned int max_discard_sectors = + min(q->limits.max_discard_sectors, UINT_MAX >> 9); bio = bio_alloc(gfp_mask, 1); if (!bio) @@ -411,10 +413,10 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, * touch many more blocks on disk than the actual payload * length. */ - if (nr_sects > queue_max_hw_sectors(q)) { - bio->bi_size = queue_max_hw_sectors(q) << 9; - nr_sects -= queue_max_hw_sectors(q); - sector += queue_max_hw_sectors(q); + if (nr_sects > max_discard_sectors) { + bio->bi_size = max_discard_sectors << 9; + nr_sects -= max_discard_sectors; + sector += max_discard_sectors; } else { bio->bi_size = nr_sects << 9; nr_sects = 0; diff --git a/block/blk-core.c b/block/blk-core.c index 80a020dd1580..34504f309728 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1436,7 +1436,8 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; } - if (unlikely(nr_sectors > queue_max_hw_sectors(q))) { + if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) && + nr_sectors > queue_max_hw_sectors(q))) { printk(KERN_ERR "bio too big device %s (%u > %u)\n", bdevname(bio->bi_bdev, b), bio_sectors(bio), diff --git a/block/blk-settings.c b/block/blk-settings.c index d29498ef1eb5..e0695bca7027 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -96,6 +96,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->max_segment_size = MAX_SEGMENT_SIZE; lim->max_sectors = BLK_DEF_MAX_SECTORS; lim->max_hw_sectors = INT_MAX; + lim->max_discard_sectors = SAFE_MAX_SECTORS; lim->logical_block_size = lim->physical_block_size = lim->io_min = 512; lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT); lim->alignment_offset = 0; @@ -238,6 +239,18 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors) } EXPORT_SYMBOL(blk_queue_max_hw_sectors); +/** + * blk_queue_max_discard_sectors - set max sectors for a single discard + * @q: the request queue for the device + * @max_discard: maximum number of sectors to discard + **/ +void blk_queue_max_discard_sectors(struct request_queue *q, + unsigned int max_discard_sectors) +{ + q->limits.max_discard_sectors = max_discard_sectors; +} +EXPORT_SYMBOL(blk_queue_max_discard_sectors); + /** * blk_queue_max_phys_segments - set max phys segments for a request for this queue * @q: the request queue for the device diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f62d45e87618..1a03b715dfad 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -311,6 +311,7 @@ struct queue_limits { unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; + unsigned int max_discard_sectors; unsigned short logical_block_size; unsigned short max_hw_segments; @@ -928,6 +929,8 @@ extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); +extern void blk_queue_max_discard_sectors(struct request_queue *q, + unsigned int max_discard_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); extern void blk_queue_physical_block_size(struct request_queue *, unsigned short); extern void blk_queue_alignment_offset(struct request_queue *q, -- cgit v1.2.3 From 8e2967555571659d2c8a70dd120710110ed7bba4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 3 Oct 2009 16:26:03 +0200 Subject: cfq-iosched: implement slower async initiate and queue ramp up This slowly ramps up the async queue depth based on the time passed since the sync IO, and doesn't allow async at all until a sync slice period has passed. Signed-off-by: Jens Axboe --- block/blk-core.c | 8 ++++++++ block/cfq-iosched.c | 56 ++++++++++++++++++++++++++++++++------------------ include/linux/blkdev.h | 4 ++++ 3 files changed, 48 insertions(+), 20 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index ddaaea4fdffc..a8c7fbe52e24 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2492,6 +2492,14 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *work, + unsigned long delay) +{ + return queue_delayed_work(kblockd_workqueue, work, delay); +} +EXPORT_SYMBOL(kblockd_schedule_delayed_work); + int __init blk_dev_init(void) { BUILD_BUG_ON(__REQ_NR_BITS > 8 * diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 70b48ea0e3e9..fce8a749f4be 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -150,7 +150,7 @@ struct cfq_data { * idle window management */ struct timer_list idle_slice_timer; - struct work_struct unplug_work; + struct delayed_work unplug_work; struct cfq_queue *active_queue; struct cfq_io_context *active_cic; @@ -268,11 +268,13 @@ static inline int cfq_bio_sync(struct bio *bio) * scheduler run of queue, if there are requests pending and no one in the * driver that will restart queueing */ -static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) +static inline void cfq_schedule_dispatch(struct cfq_data *cfqd, + unsigned long delay) { if (cfqd->busy_queues) { cfq_log(cfqd, "schedule dispatch"); - kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work); + kblockd_schedule_delayed_work(cfqd->queue, &cfqd->unplug_work, + delay); } } @@ -1316,8 +1318,6 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) * Does this cfqq already have too much IO in flight? */ if (cfqq->dispatched >= max_dispatch) { - unsigned long load_at = cfqd->last_end_sync_rq + cfq_slice_sync; - /* * idle queue must always only have a single IO in flight */ @@ -1331,20 +1331,36 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) return 0; /* - * If a sync request has completed recently, don't overload - * the dispatch queue yet with async requests. + * Sole queue user, allow bigger slice */ - if (cfqd->cfq_desktop && !cfq_cfqq_sync(cfqq) - && time_before(jiffies, load_at)) - return 0; + max_dispatch *= 4; + } + + /* + * Async queues must wait a bit before being allowed dispatch. + * We also ramp up the dispatch depth gradually for async IO, + * based on the last sync IO we serviced + */ + if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_desktop) { + unsigned long last_sync = jiffies - cfqd->last_end_sync_rq; + unsigned int depth; /* - * we are the only queue, allow up to 4 times of 'quantum' + * must wait a bit longer */ - if (cfqq->dispatched >= 4 * max_dispatch) + if (last_sync < cfq_slice_sync) { + cfq_schedule_dispatch(cfqd, cfq_slice_sync - last_sync); return 0; + } + + depth = last_sync / cfq_slice_sync; + if (depth < max_dispatch) + max_dispatch = depth; } + if (cfqq->dispatched >= max_dispatch) + return 0; + /* * Dispatch a request from this cfqq */ @@ -1389,7 +1405,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq) if (unlikely(cfqd->active_queue == cfqq)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } kmem_cache_free(cfq_pool, cfqq); @@ -1484,7 +1500,7 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (unlikely(cfqq == cfqd->active_queue)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } cfq_put_queue(cfqq); @@ -2201,7 +2217,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) } if (!rq_in_driver(cfqd)) - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); } /* @@ -2331,7 +2347,7 @@ queue_fail: if (cic) put_io_context(cic->ioc); - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); spin_unlock_irqrestore(q->queue_lock, flags); cfq_log(cfqd, "set_request fail"); return 1; @@ -2340,7 +2356,7 @@ queue_fail: static void cfq_kick_queue(struct work_struct *work) { struct cfq_data *cfqd = - container_of(work, struct cfq_data, unplug_work); + container_of(work, struct cfq_data, unplug_work.work); struct request_queue *q = cfqd->queue; spin_lock_irq(q->queue_lock); @@ -2394,7 +2410,7 @@ static void cfq_idle_slice_timer(unsigned long data) expire: cfq_slice_expired(cfqd, timed_out); out_kick: - cfq_schedule_dispatch(cfqd); + cfq_schedule_dispatch(cfqd, 0); out_cont: spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); } @@ -2402,7 +2418,7 @@ out_cont: static void cfq_shutdown_timer_wq(struct cfq_data *cfqd) { del_timer_sync(&cfqd->idle_slice_timer); - cancel_work_sync(&cfqd->unplug_work); + cancel_delayed_work_sync(&cfqd->unplug_work); } static void cfq_put_async_queues(struct cfq_data *cfqd) @@ -2484,7 +2500,7 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->idle_slice_timer.function = cfq_idle_slice_timer; cfqd->idle_slice_timer.data = (unsigned long) cfqd; - INIT_WORK(&cfqd->unplug_work, cfq_kick_queue); + INIT_DELAYED_WORK(&cfqd->unplug_work, cfq_kick_queue); cfqd->cfq_quantum = cfq_quantum; cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0]; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1a03b715dfad..a7323930d2ba 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1147,7 +1147,11 @@ static inline void put_dev_sector(Sector p) } struct work_struct; +struct delayed_work; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *work, + unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From ac481c20ef8f6c6f2be75d581863f40c43874ef7 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Sat, 3 Oct 2009 20:52:01 +0200 Subject: block: Topology ioctls Not all users of the topology information want to use libblkid. Provide the topology information through bdev ioctls. Also clarify sector size comments for existing BLK ioctls. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/compat_ioctl.c | 13 +++++++++++++ block/ioctl.c | 17 +++++++++++++++-- include/linux/blkdev.h | 35 ++++++++++++++++++++++++++++++----- include/linux/fs.h | 4 ++++ 4 files changed, 62 insertions(+), 7 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 7865a34e0faa..9bd086c1a4d5 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -21,6 +21,11 @@ static int compat_put_int(unsigned long arg, int val) return put_user(val, (compat_int_t __user *)compat_ptr(arg)); } +static int compat_put_uint(unsigned long arg, unsigned int val) +{ + return put_user(val, (compat_uint_t __user *)compat_ptr(arg)); +} + static int compat_put_long(unsigned long arg, long val) { return put_user(val, (compat_long_t __user *)compat_ptr(arg)); @@ -734,6 +739,14 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) switch (cmd) { case HDIO_GETGEO: return compat_hdio_getgeo(disk, bdev, compat_ptr(arg)); + case BLKPBSZGET: + return compat_put_uint(arg, bdev_physical_block_size(bdev)); + case BLKIOMIN: + return compat_put_uint(arg, bdev_io_min(bdev)); + case BLKIOOPT: + return compat_put_uint(arg, bdev_io_opt(bdev)); + case BLKALIGNOFF: + return compat_put_int(arg, bdev_alignment_offset(bdev)); case BLKFLSBUF: case BLKROSET: case BLKDISCARD: diff --git a/block/ioctl.c b/block/ioctl.c index d3e6b5827a34..1f4d1de12b09 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -138,6 +138,11 @@ static int put_int(unsigned long arg, int val) return put_user(val, (int __user *)arg); } +static int put_uint(unsigned long arg, unsigned int val) +{ + return put_user(val, (unsigned int __user *)arg); +} + static int put_long(unsigned long arg, long val) { return put_user(val, (long __user *)arg); @@ -263,10 +268,18 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512); case BLKROGET: return put_int(arg, bdev_read_only(bdev) != 0); - case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */ + case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ return put_int(arg, block_size(bdev)); - case BLKSSZGET: /* get block device hardware sector size */ + case BLKSSZGET: /* get block device logical block size */ return put_int(arg, bdev_logical_block_size(bdev)); + case BLKPBSZGET: /* get block device physical block size */ + return put_uint(arg, bdev_physical_block_size(bdev)); + case BLKIOMIN: + return put_uint(arg, bdev_io_min(bdev)); + case BLKIOOPT: + return put_uint(arg, bdev_io_opt(bdev)); + case BLKALIGNOFF: + return put_int(arg, bdev_alignment_offset(bdev)); case BLKSECTGET: return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev))); case BLKRASET: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a7323930d2ba..25119041e034 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1081,25 +1081,37 @@ static inline unsigned int queue_physical_block_size(struct request_queue *q) return q->limits.physical_block_size; } +static inline int bdev_physical_block_size(struct block_device *bdev) +{ + return queue_physical_block_size(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_min(struct request_queue *q) { return q->limits.io_min; } +static inline int bdev_io_min(struct block_device *bdev) +{ + return queue_io_min(bdev_get_queue(bdev)); +} + static inline unsigned int queue_io_opt(struct request_queue *q) { return q->limits.io_opt; } +static inline int bdev_io_opt(struct block_device *bdev) +{ + return queue_io_opt(bdev_get_queue(bdev)); +} + static inline int queue_alignment_offset(struct request_queue *q) { - if (q && q->limits.misaligned) + if (q->limits.misaligned) return -1; - if (q && q->limits.alignment_offset) - return q->limits.alignment_offset; - - return 0; + return q->limits.alignment_offset; } static inline int queue_sector_alignment_offset(struct request_queue *q, @@ -1109,6 +1121,19 @@ static inline int queue_sector_alignment_offset(struct request_queue *q, & (q->limits.io_min - 1); } +static inline int bdev_alignment_offset(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q->limits.misaligned) + return -1; + + if (bdev != bdev->bd_contains) + return bdev->bd_part->alignment_offset; + + return q->limits.alignment_offset; +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; diff --git a/include/linux/fs.h b/include/linux/fs.h index 2adaa2529f18..883eaacfd924 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -300,6 +300,10 @@ struct inodes_stat_t { #define BLKTRACESTOP _IO(0x12,117) #define BLKTRACETEARDOWN _IO(0x12,118) #define BLKDISCARD _IO(0x12,119) +#define BLKIOMIN _IO(0x12,120) +#define BLKIOOPT _IO(0x12,121) +#define BLKALIGNOFF _IO(0x12,122) +#define BLKPBSZGET _IO(0x12,123) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 23e018a1b083ecb4b8bb2fb43d58e7c19b5d7959 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 5 Oct 2009 08:52:35 +0200 Subject: block: get rid of kblock_schedule_delayed_work() It was briefly introduced to allow CFQ to to delayed scheduling, but we ended up removing that feature again. So lets kill the function and export, and just switch CFQ back to the normal work schedule since it is now passing in a '0' delay from all call sites. Signed-off-by: Jens Axboe --- block/blk-core.c | 8 -------- block/cfq-iosched.c | 24 +++++++++++------------- include/linux/blkdev.h | 4 ---- 3 files changed, 11 insertions(+), 25 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 81f34311659a..73ecbed02605 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2492,14 +2492,6 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); -int kblockd_schedule_delayed_work(struct request_queue *q, - struct delayed_work *work, - unsigned long delay) -{ - return queue_delayed_work(kblockd_workqueue, work, delay); -} -EXPORT_SYMBOL(kblockd_schedule_delayed_work); - int __init blk_dev_init(void) { BUILD_BUG_ON(__REQ_NR_BITS > 8 * diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index ae14cbaf9d0e..690ebd96dc42 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -150,7 +150,7 @@ struct cfq_data { * idle window management */ struct timer_list idle_slice_timer; - struct delayed_work unplug_work; + struct work_struct unplug_work; struct cfq_queue *active_queue; struct cfq_io_context *active_cic; @@ -268,13 +268,11 @@ static inline int cfq_bio_sync(struct bio *bio) * scheduler run of queue, if there are requests pending and no one in the * driver that will restart queueing */ -static inline void cfq_schedule_dispatch(struct cfq_data *cfqd, - unsigned long delay) +static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) { if (cfqd->busy_queues) { cfq_log(cfqd, "schedule dispatch"); - kblockd_schedule_delayed_work(cfqd->queue, &cfqd->unplug_work, - delay); + kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work); } } @@ -1400,7 +1398,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq) if (unlikely(cfqd->active_queue == cfqq)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); } kmem_cache_free(cfq_pool, cfqq); @@ -1495,7 +1493,7 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (unlikely(cfqq == cfqd->active_queue)) { __cfq_slice_expired(cfqd, cfqq, 0); - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); } cfq_put_queue(cfqq); @@ -2213,7 +2211,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) } if (!rq_in_driver(cfqd)) - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); } /* @@ -2343,7 +2341,7 @@ queue_fail: if (cic) put_io_context(cic->ioc); - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); spin_unlock_irqrestore(q->queue_lock, flags); cfq_log(cfqd, "set_request fail"); return 1; @@ -2352,7 +2350,7 @@ queue_fail: static void cfq_kick_queue(struct work_struct *work) { struct cfq_data *cfqd = - container_of(work, struct cfq_data, unplug_work.work); + container_of(work, struct cfq_data, unplug_work); struct request_queue *q = cfqd->queue; spin_lock_irq(q->queue_lock); @@ -2406,7 +2404,7 @@ static void cfq_idle_slice_timer(unsigned long data) expire: cfq_slice_expired(cfqd, timed_out); out_kick: - cfq_schedule_dispatch(cfqd, 0); + cfq_schedule_dispatch(cfqd); out_cont: spin_unlock_irqrestore(cfqd->queue->queue_lock, flags); } @@ -2414,7 +2412,7 @@ out_cont: static void cfq_shutdown_timer_wq(struct cfq_data *cfqd) { del_timer_sync(&cfqd->idle_slice_timer); - cancel_delayed_work_sync(&cfqd->unplug_work); + cancel_work_sync(&cfqd->unplug_work); } static void cfq_put_async_queues(struct cfq_data *cfqd) @@ -2496,7 +2494,7 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->idle_slice_timer.function = cfq_idle_slice_timer; cfqd->idle_slice_timer.data = (unsigned long) cfqd; - INIT_DELAYED_WORK(&cfqd->unplug_work, cfq_kick_queue); + INIT_WORK(&cfqd->unplug_work, cfq_kick_queue); cfqd->cfq_quantum = cfq_quantum; cfqd->cfq_fifo_expire[0] = cfq_fifo_expire[0]; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 25119041e034..221cecd86bd3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1172,11 +1172,7 @@ static inline void put_dev_sector(Sector p) } struct work_struct; -struct delayed_work; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); -int kblockd_schedule_delayed_work(struct request_queue *q, - struct delayed_work *work, - unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) -- cgit v1.2.3 From b9d128f1088ea5245109dfc9bbceb128b6371a77 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 29 Oct 2009 13:59:26 +0100 Subject: block: move bdi/address_space unplug functions to backing-dev.h There's nothing block related about them, the backing device is used by things like NFS etc as well. This gets rid of the need to protect such calls by CONFIG_BLOCK. Signed-off-by: Jens Axboe --- fs/aio.c | 1 + include/linux/backing-dev.h | 13 +++++++++++++ include/linux/blkdev.h | 13 ------------- 3 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/fs/aio.c b/fs/aio.c index cf0bef428f88..c30dfc006108 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #define DEBUG 0 diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index b449e738533a..fcbc26af00e4 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -331,4 +331,17 @@ static inline int bdi_sched_wait(void *word) return 0; } +static inline void blk_run_backing_dev(struct backing_dev_info *bdi, + struct page *page) +{ + if (bdi && bdi->unplug_io_fn) + bdi->unplug_io_fn(bdi, page); +} + +static inline void blk_run_address_space(struct address_space *mapping) +{ + if (mapping) + blk_run_backing_dev(mapping->backing_dev_info, NULL); +} + #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 221cecd86bd3..39c601f783a0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -823,19 +823,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) return bdev->bd_disk->queue; } -static inline void blk_run_backing_dev(struct backing_dev_info *bdi, - struct page *page) -{ - if (bdi && bdi->unplug_io_fn) - bdi->unplug_io_fn(bdi, page); -} - -static inline void blk_run_address_space(struct address_space *mapping) -{ - if (mapping) - blk_run_backing_dev(mapping->backing_dev_info, NULL); -} - /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request -- cgit v1.2.3 From 86b37281411cf1e9bc0a6b5406c45edb7bd9ea5d Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 10 Nov 2009 11:50:21 +0100 Subject: block: Expose discard granularity While SSDs track block usage on a per-sector basis, RAID arrays often have allocation blocks that are bigger. Allow the discard granularity and alignment to be set and teach the topology stacking logic how to handle them. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 46 ++++++++++++++++++++++++++++++++++++---------- block/blk-sysfs.c | 22 ++++++++++++++++++++++ block/genhd.c | 12 ++++++++++++ fs/partitions/check.c | 12 ++++++++++++ include/linux/blkdev.h | 18 ++++++++++++++++++ include/linux/genhd.h | 1 + 6 files changed, 101 insertions(+), 10 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 66d4aa8799b7..7f986cafacd5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -96,7 +96,10 @@ void blk_set_default_limits(struct queue_limits *lim) lim->max_segment_size = MAX_SEGMENT_SIZE; lim->max_sectors = BLK_DEF_MAX_SECTORS; lim->max_hw_sectors = INT_MAX; - lim->max_discard_sectors = SAFE_MAX_SECTORS; + lim->max_discard_sectors = 0; + lim->discard_granularity = 0; + lim->discard_alignment = 0; + lim->discard_misaligned = 0; lim->logical_block_size = lim->physical_block_size = lim->io_min = 512; lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT); lim->alignment_offset = 0; @@ -488,6 +491,16 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) } EXPORT_SYMBOL(blk_queue_stack_limits); +static unsigned int lcm(unsigned int a, unsigned int b) +{ + if (a && b) + return (a * b) / gcd(a, b); + else if (b) + return b; + + return a; +} + /** * blk_stack_limits - adjust queue_limits for stacked devices * @t: the stacking driver limits (top) @@ -502,6 +515,10 @@ EXPORT_SYMBOL(blk_queue_stack_limits); int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset) { + int ret; + + ret = 0; + t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn); @@ -531,7 +548,13 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, if (offset && (offset & (b->physical_block_size - 1)) != b->alignment_offset) { t->misaligned = 1; - return -1; + ret = -1; + } + + if (offset && + (offset & (b->discard_granularity - 1)) != b->discard_alignment) { + t->discard_misaligned = 1; + ret = -1; } /* If top has no alignment offset, inherit from bottom */ @@ -539,23 +562,26 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->alignment_offset = b->alignment_offset & (b->physical_block_size - 1); + if (!t->discard_alignment) + t->discard_alignment = + b->discard_alignment & (b->discard_granularity - 1); + /* Top device aligned on logical block boundary? */ if (t->alignment_offset & (t->logical_block_size - 1)) { t->misaligned = 1; - return -1; + ret = -1; } - /* Find lcm() of optimal I/O size */ - if (t->io_opt && b->io_opt) - t->io_opt = (t->io_opt * b->io_opt) / gcd(t->io_opt, b->io_opt); - else if (b->io_opt) - t->io_opt = b->io_opt; + /* Find lcm() of optimal I/O size and granularity */ + t->io_opt = lcm(t->io_opt, b->io_opt); + t->discard_granularity = lcm(t->discard_granularity, + b->discard_granularity); /* Verify that optimal I/O size is a multiple of io_min */ if (t->io_min && t->io_opt % t->io_min) - return -1; + ret = -1; - return 0; + return ret; } EXPORT_SYMBOL(blk_stack_limits); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 8a6d81afb284..3147145edc15 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -126,6 +126,16 @@ static ssize_t queue_io_opt_show(struct request_queue *q, char *page) return queue_var_show(queue_io_opt(q), page); } +static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page) +{ + return queue_var_show(q->limits.discard_granularity, page); +} + +static ssize_t queue_discard_max_show(struct request_queue *q, char *page) +{ + return queue_var_show(q->limits.max_discard_sectors << 9, page); +} + static ssize_t queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) { @@ -293,6 +303,16 @@ static struct queue_sysfs_entry queue_io_opt_entry = { .show = queue_io_opt_show, }; +static struct queue_sysfs_entry queue_discard_granularity_entry = { + .attr = {.name = "discard_granularity", .mode = S_IRUGO }, + .show = queue_discard_granularity_show, +}; + +static struct queue_sysfs_entry queue_discard_max_entry = { + .attr = {.name = "discard_max_bytes", .mode = S_IRUGO }, + .show = queue_discard_max_show, +}; + static struct queue_sysfs_entry queue_nonrot_entry = { .attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR }, .show = queue_nonrot_show, @@ -328,6 +348,8 @@ static struct attribute *default_attrs[] = { &queue_physical_block_size_entry.attr, &queue_io_min_entry.attr, &queue_io_opt_entry.attr, + &queue_discard_granularity_entry.attr, + &queue_discard_max_entry.attr, &queue_nonrot_entry.attr, &queue_nomerges_entry.attr, &queue_rq_affinity_entry.attr, diff --git a/block/genhd.c b/block/genhd.c index 517e4332cb37..b11a4ad7d571 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -861,12 +861,23 @@ static ssize_t disk_alignment_offset_show(struct device *dev, return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue)); } +static ssize_t disk_discard_alignment_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + + return sprintf(buf, "%u\n", queue_discard_alignment(disk->queue)); +} + static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL); static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL); static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL); static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL); 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(discard_alignment, S_IRUGO, disk_discard_alignment_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); @@ -887,6 +898,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_ro.attr, &dev_attr_size.attr, &dev_attr_alignment_offset.attr, + &dev_attr_discard_alignment.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 7b685e10cbad..64bc8998ac9a 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -226,6 +226,13 @@ ssize_t part_alignment_offset_show(struct device *dev, return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset); } +ssize_t part_discard_alignment_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + return sprintf(buf, "%u\n", p->discard_alignment); +} + ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -288,6 +295,8 @@ static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL); 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(discard_alignment, S_IRUGO, part_discard_alignment_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 @@ -300,6 +309,7 @@ static struct attribute *part_attrs[] = { &dev_attr_start.attr, &dev_attr_size.attr, &dev_attr_alignment_offset.attr, + &dev_attr_discard_alignment.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST @@ -403,6 +413,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, p->start_sect = start; p->alignment_offset = queue_sector_alignment_offset(disk->queue, start); + p->discard_alignment = queue_sector_discard_alignment(disk->queue, + start); p->nr_sects = len; p->partno = partno; p->policy = get_disk_ro(disk); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 39c601f783a0..1cc02972fbe2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -312,12 +312,15 @@ struct queue_limits { unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; + unsigned int discard_granularity; + unsigned int discard_alignment; unsigned short logical_block_size; unsigned short max_hw_segments; unsigned short max_phys_segments; unsigned char misaligned; + unsigned char discard_misaligned; unsigned char no_cluster; }; @@ -1121,6 +1124,21 @@ static inline int bdev_alignment_offset(struct block_device *bdev) return q->limits.alignment_offset; } +static inline int queue_discard_alignment(struct request_queue *q) +{ + if (q->limits.discard_misaligned) + return -1; + + return q->limits.discard_alignment; +} + +static inline int queue_sector_discard_alignment(struct request_queue *q, + sector_t sector) +{ + return ((sector << 9) - q->limits.discard_alignment) + & (q->limits.discard_granularity - 1); +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 297df45ffd0a..c6c0c41af35f 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -91,6 +91,7 @@ struct hd_struct { sector_t start_sect; sector_t nr_sects; sector_t alignment_offset; + unsigned int discard_alignment; struct device __dev; struct kobject *holder_dir; int policy, partno; -- cgit v1.2.3 From 2d4dc890b5c8fabd818a8586607e6843c4375e62 Mon Sep 17 00:00:00 2001 From: Ilya Loginov Date: Thu, 26 Nov 2009 09:16:19 +0100 Subject: block: add helpers to run flush_dcache_page() against a bio and a request's pages Mtdblock driver doesn't call flush_dcache_page for pages in request. So, this causes problems on architectures where the icache doesn't fill from the dcache or with dcache aliases. The patch fixes this. The ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE symbol was introduced to avoid pointless empty cache-thrashing loops on architectures for which flush_dcache_page() is a no-op. Every architecture was provided with this flush pages on architectires where ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE is equal 1 or do nothing otherwise. See "fix mtd_blkdevs problem with caches on some architectures" discussion on LKML for more information. Signed-off-by: Ilya Loginov Cc: Ingo Molnar Cc: David Woodhouse Cc: Peter Horton Cc: "Ed L. Cashin" Signed-off-by: Jens Axboe --- arch/alpha/include/asm/cacheflush.h | 1 + arch/arm/include/asm/cacheflush.h | 1 + arch/avr32/include/asm/cacheflush.h | 1 + arch/blackfin/include/asm/cacheflush.h | 2 ++ arch/cris/include/asm/cacheflush.h | 1 + arch/frv/include/asm/cacheflush.h | 1 + arch/h8300/include/asm/cacheflush.h | 1 + arch/ia64/include/asm/cacheflush.h | 1 + arch/m32r/include/asm/cacheflush.h | 3 +++ arch/m68k/include/asm/cacheflush_mm.h | 1 + arch/m68k/include/asm/cacheflush_no.h | 1 + arch/microblaze/include/asm/cacheflush.h | 1 + arch/mips/include/asm/cacheflush.h | 1 + arch/mn10300/include/asm/cacheflush.h | 1 + arch/parisc/include/asm/cacheflush.h | 1 + arch/powerpc/include/asm/cacheflush.h | 1 + arch/s390/include/asm/cacheflush.h | 1 + arch/score/include/asm/cacheflush.h | 1 + arch/sh/include/asm/cacheflush.h | 1 + arch/sparc/include/asm/cacheflush_32.h | 1 + arch/sparc/include/asm/cacheflush_64.h | 1 + arch/x86/include/asm/cacheflush.h | 1 + arch/xtensa/include/asm/cacheflush.h | 1 + block/blk-core.c | 19 +++++++++++++++++++ drivers/mtd/mtd_blkdevs.c | 2 ++ fs/bio.c | 12 ++++++++++++ include/asm-generic/cacheflush.h | 1 + include/linux/bio.h | 12 ++++++++++++ include/linux/blkdev.h | 11 +++++++++++ 29 files changed, 83 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/arch/alpha/include/asm/cacheflush.h b/arch/alpha/include/asm/cacheflush.h index b686cc7fc44e..01d71e1c8a9e 100644 --- a/arch/alpha/include/asm/cacheflush.h +++ b/arch/alpha/include/asm/cacheflush.h @@ -9,6 +9,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index fd03fb63a332..247b7b0adc2a 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -408,6 +408,7 @@ extern void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, * about to change to user space. This is the same method as used on SPARC64. * See update_mmu_cache for the user space part. */ +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); extern void __flush_dcache_page(struct address_space *mapping, struct page *page); diff --git a/arch/avr32/include/asm/cacheflush.h b/arch/avr32/include/asm/cacheflush.h index 670674749b20..96e53820bbbd 100644 --- a/arch/avr32/include/asm/cacheflush.h +++ b/arch/avr32/include/asm/cacheflush.h @@ -107,6 +107,7 @@ extern void flush_icache_page(struct vm_area_struct *vma, struct page *page); * do something here, but only for certain configurations. No such * configurations exist at this time. */ +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(page) do { } while (0) #define flush_dcache_mmap_unlock(page) do { } while (0) diff --git a/arch/blackfin/include/asm/cacheflush.h b/arch/blackfin/include/asm/cacheflush.h index af03a36c7a4e..417eaac7fe99 100644 --- a/arch/blackfin/include/asm/cacheflush.h +++ b/arch/blackfin/include/asm/cacheflush.h @@ -68,9 +68,11 @@ do { memcpy(dst, src, len); \ #endif #if defined(CONFIG_BFIN_EXTMEM_WRITEBACK) || defined(CONFIG_BFIN_L2_WRITEBACK) # define flush_dcache_range(start,end) blackfin_dcache_flush_range((start), (end)) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 # define flush_dcache_page(page) blackfin_dflush_page(page_address(page)) #else # define flush_dcache_range(start,end) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 # define flush_dcache_page(page) do { } while (0) #endif diff --git a/arch/cris/include/asm/cacheflush.h b/arch/cris/include/asm/cacheflush.h index cf60e3f69f8d..36795bca605e 100644 --- a/arch/cris/include/asm/cacheflush.h +++ b/arch/cris/include/asm/cacheflush.h @@ -12,6 +12,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/frv/include/asm/cacheflush.h b/arch/frv/include/asm/cacheflush.h index 432a69e7f3d4..edbac54ae015 100644 --- a/arch/frv/include/asm/cacheflush.h +++ b/arch/frv/include/asm/cacheflush.h @@ -47,6 +47,7 @@ static inline void __flush_cache_all(void) } /* dcache/icache coherency... */ +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #ifdef CONFIG_MMU extern void flush_dcache_page(struct page *page); #else diff --git a/arch/h8300/include/asm/cacheflush.h b/arch/h8300/include/asm/cacheflush.h index 5ffdca217b95..4cf2df20c1ce 100644 --- a/arch/h8300/include/asm/cacheflush.h +++ b/arch/h8300/include/asm/cacheflush.h @@ -15,6 +15,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma,a,b) #define flush_cache_page(vma,p,pfn) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) #define flush_dcache_mmap_lock(mapping) #define flush_dcache_mmap_unlock(mapping) diff --git a/arch/ia64/include/asm/cacheflush.h b/arch/ia64/include/asm/cacheflush.h index c8ce2719fee8..429eefc93ee7 100644 --- a/arch/ia64/include/asm/cacheflush.h +++ b/arch/ia64/include/asm/cacheflush.h @@ -25,6 +25,7 @@ #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) \ do { \ clear_bit(PG_arch_1, &(page)->flags); \ diff --git a/arch/m32r/include/asm/cacheflush.h b/arch/m32r/include/asm/cacheflush.h index 78587c958146..8e8e04516c39 100644 --- a/arch/m32r/include/asm/cacheflush.h +++ b/arch/m32r/include/asm/cacheflush.h @@ -12,6 +12,7 @@ extern void _flush_cache_copyback_all(void); #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) @@ -33,6 +34,7 @@ extern void smp_flush_cache_all(void); #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) @@ -46,6 +48,7 @@ extern void smp_flush_cache_all(void); #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h index 16bf375fdbe1..73de7c89d8e0 100644 --- a/arch/m68k/include/asm/cacheflush_mm.h +++ b/arch/m68k/include/asm/cacheflush_mm.h @@ -128,6 +128,7 @@ static inline void __flush_page_to_ram(void *vaddr) } } +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) __flush_page_to_ram(page_address(page)) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/m68k/include/asm/cacheflush_no.h b/arch/m68k/include/asm/cacheflush_no.h index c65f00a94553..89f195656be7 100644 --- a/arch/m68k/include/asm/cacheflush_no.h +++ b/arch/m68k/include/asm/cacheflush_no.h @@ -12,6 +12,7 @@ #define flush_cache_range(vma, start, end) __flush_cache_all() #define flush_cache_page(vma, vmaddr) do { } while (0) #define flush_dcache_range(start,len) __flush_cache_all() +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/microblaze/include/asm/cacheflush.h b/arch/microblaze/include/asm/cacheflush.h index f989d6aad648..088076e657b3 100644 --- a/arch/microblaze/include/asm/cacheflush.h +++ b/arch/microblaze/include/asm/cacheflush.h @@ -37,6 +37,7 @@ #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) #define flush_dcache_range(start, end) __invalidate_dcache_range(start, end) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index 03b1d69b142f..40bb9fde205f 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -38,6 +38,7 @@ extern void (*flush_cache_range)(struct vm_area_struct *vma, extern void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page, unsigned long pfn); extern void __flush_dcache_page(struct page *page); +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 static inline void flush_dcache_page(struct page *page) { if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) diff --git a/arch/mn10300/include/asm/cacheflush.h b/arch/mn10300/include/asm/cacheflush.h index 1a55d61f0d06..29e692f7f030 100644 --- a/arch/mn10300/include/asm/cacheflush.h +++ b/arch/mn10300/include/asm/cacheflush.h @@ -26,6 +26,7 @@ #define flush_cache_page(vma, vmaddr, pfn) do {} while (0) #define flush_cache_vmap(start, end) do {} while (0) #define flush_cache_vunmap(start, end) do {} while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do {} while (0) #define flush_dcache_mmap_lock(mapping) do {} while (0) #define flush_dcache_mmap_unlock(mapping) do {} while (0) diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 724395143f26..7a73b615c23d 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -42,6 +42,7 @@ void flush_cache_mm(struct mm_struct *mm); #define flush_cache_vmap(start, end) flush_cache_all() #define flush_cache_vunmap(start, end) flush_cache_all() +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) \ diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index ba667a383b8c..ab9e402518e8 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -25,6 +25,7 @@ #define flush_cache_vmap(start, end) do { } while (0) #define flush_cache_vunmap(start, end) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h index 49d5af916d01..405cc97c6249 100644 --- a/arch/s390/include/asm/cacheflush.h +++ b/arch/s390/include/asm/cacheflush.h @@ -10,6 +10,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/score/include/asm/cacheflush.h b/arch/score/include/asm/cacheflush.h index 07cc8fc457cd..caaba24036e3 100644 --- a/arch/score/include/asm/cacheflush.h +++ b/arch/score/include/asm/cacheflush.h @@ -16,6 +16,7 @@ extern void flush_icache_range(unsigned long start, unsigned long end); extern void flush_dcache_range(unsigned long start, unsigned long end); #define flush_cache_dup_mm(mm) do {} while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do {} while (0) #define flush_dcache_mmap_lock(mapping) do {} while (0) #define flush_dcache_mmap_unlock(mapping) do {} while (0) diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index c29918f3c819..dda96eb3e7c0 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -42,6 +42,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); extern void flush_icache_range(unsigned long start, unsigned long end); extern void flush_icache_page(struct vm_area_struct *vma, diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h index 68ac10910271..2e468773f250 100644 --- a/arch/sparc/include/asm/cacheflush_32.h +++ b/arch/sparc/include/asm/cacheflush_32.h @@ -75,6 +75,7 @@ BTFIXUPDEF_CALL(void, flush_sig_insns, struct mm_struct *, unsigned long) extern void sparc_flush_page_to_ram(struct page *page); +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) sparc_flush_page_to_ram(page) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h index c43321729b3b..b95384033e89 100644 --- a/arch/sparc/include/asm/cacheflush_64.h +++ b/arch/sparc/include/asm/cacheflush_64.h @@ -37,6 +37,7 @@ extern void flush_dcache_page_all(struct mm_struct *mm, struct page *page); #endif extern void __flush_dcache_range(unsigned long start, unsigned long end); +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); #define flush_icache_page(vma, pg) do { } while(0) diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index b54f6afe7ec4..9076add593a8 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -12,6 +12,7 @@ static inline void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { } static inline void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { } +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 static inline void flush_dcache_page(struct page *page) { } static inline void flush_dcache_mmap_lock(struct address_space *mapping) { } static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { } diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index b7b8fbe47c77..a508f2f73bd7 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -101,6 +101,7 @@ static inline void __invalidate_icache_page_alias(unsigned long virt, #define flush_cache_vmap(start,end) flush_cache_all() #define flush_cache_vunmap(start,end) flush_cache_all() +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page*); extern void flush_cache_range(struct vm_area_struct*, ulong, ulong); extern void flush_cache_page(struct vm_area_struct*, unsigned long, unsigned long); diff --git a/block/blk-core.c b/block/blk-core.c index 71da5111120c..718897e6d37f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2358,6 +2358,25 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq, rq->rq_disk = bio->bi_bdev->bd_disk; } +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +/** + * rq_flush_dcache_pages - Helper function to flush all pages in a request + * @rq: the request to be flushed + * + * Description: + * Flush all pages in @rq. + */ +void rq_flush_dcache_pages(struct request *rq) +{ + struct req_iterator iter; + struct bio_vec *bvec; + + rq_for_each_segment(bvec, rq, iter) + flush_dcache_page(bvec->bv_page); +} +EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); +#endif + /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 8ca17a3e96ea..64e2b379a350 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -59,12 +59,14 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, for (; nsect > 0; nsect--, block++, buf += tr->blksize) if (tr->readsect(dev, block, buf)) return -EIO; + rq_flush_dcache_pages(req); return 0; case WRITE: if (!tr->writesect) return -EIO; + rq_flush_dcache_pages(req); for (; nsect > 0; nsect--, block++, buf += tr->blksize) if (tr->writesect(dev, block, buf)) return -EIO; diff --git a/fs/bio.c b/fs/bio.c index 12da5db8682c..e23a63f4f7de 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -1393,6 +1393,18 @@ void bio_check_pages_dirty(struct bio *bio) } } +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +void bio_flush_dcache_pages(struct bio *bi) +{ + int i; + struct bio_vec *bvec; + + bio_for_each_segment(bvec, bi, i) + flush_dcache_page(bvec->bv_page); +} +EXPORT_SYMBOL(bio_flush_dcache_pages); +#endif + /** * bio_endio - end I/O on a bio * @bio: bio diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index ba4ec39a1131..57b5c3c82e86 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -13,6 +13,7 @@ #define flush_cache_dup_mm(mm) do { } while (0) #define flush_cache_range(vma, start, end) do { } while (0) #define flush_cache_page(vma, vmaddr, pfn) do { } while (0) +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 #define flush_dcache_page(page) do { } while (0) #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/include/linux/bio.h b/include/linux/bio.h index 474792b825d0..7fc5606e6ea5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -391,6 +391,18 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int, gfp_t, int); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); + +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" +#endif +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +extern void bio_flush_dcache_pages(struct bio *bi); +#else +static inline void bio_flush_dcache_pages(struct bio *bi) +{ +} +#endif + extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *, unsigned long, unsigned int, int, gfp_t); extern struct bio *bio_copy_user_iov(struct request_queue *, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1cc02972fbe2..e727f6c44c44 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -752,6 +752,17 @@ struct req_iterator { #define rq_iter_last(rq, _iter) \ (_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1) +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" +#endif +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +extern void rq_flush_dcache_pages(struct request *rq); +#else +static inline void rq_flush_dcache_pages(struct request *rq) +{ +} +#endif + extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern void register_disk(struct gendisk *dev); -- cgit v1.2.3 From 98262f2762f0067375f83824d81ea929e37e6bfe Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 3 Dec 2009 09:24:48 +0100 Subject: block: Allow devices to indicate whether discarded blocks are zeroed The discard ioctl is used by mkfs utilities to clear a block device prior to putting metadata down. However, not all devices return zeroed blocks after a discard. Some drives return stale data, potentially containing old superblocks. It is therefore important to know whether discarded blocks are properly zeroed. Both ATA and SCSI drives have configuration bits that indicate whether zeroes are returned after a discard operation. Implement a block level interface that allows this information to be bubbled up the stack and queried via a new block device ioctl. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 2 ++ block/blk-sysfs.c | 11 +++++++++++ block/compat_ioctl.c | 2 ++ block/ioctl.c | 2 ++ include/linux/blkdev.h | 14 ++++++++++++++ include/linux/fs.h | 1 + 6 files changed, 32 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 1ebc1fdb9144..dd1f1e0e196f 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -101,6 +101,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->discard_granularity = 0; lim->discard_alignment = 0; lim->discard_misaligned = 0; + lim->discard_zeroes_data = -1; lim->logical_block_size = lim->physical_block_size = lim->io_min = 512; lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT); lim->alignment_offset = 0; @@ -544,6 +545,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->io_min = max(t->io_min, b->io_min); t->no_cluster |= b->no_cluster; + t->discard_zeroes_data &= b->discard_zeroes_data; /* Bottom device offset aligned? */ if (offset && diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 3147145edc15..8606c9543fdd 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -136,6 +136,11 @@ static ssize_t queue_discard_max_show(struct request_queue *q, char *page) return queue_var_show(q->limits.max_discard_sectors << 9, page); } +static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page) +{ + return queue_var_show(queue_discard_zeroes_data(q), page); +} + static ssize_t queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) { @@ -313,6 +318,11 @@ static struct queue_sysfs_entry queue_discard_max_entry = { .show = queue_discard_max_show, }; +static struct queue_sysfs_entry queue_discard_zeroes_data_entry = { + .attr = {.name = "discard_zeroes_data", .mode = S_IRUGO }, + .show = queue_discard_zeroes_data_show, +}; + static struct queue_sysfs_entry queue_nonrot_entry = { .attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR }, .show = queue_nonrot_show, @@ -350,6 +360,7 @@ static struct attribute *default_attrs[] = { &queue_io_opt_entry.attr, &queue_discard_granularity_entry.attr, &queue_discard_max_entry.attr, + &queue_discard_zeroes_data_entry.attr, &queue_nonrot_entry.attr, &queue_nomerges_entry.attr, &queue_rq_affinity_entry.attr, diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 9bd086c1a4d5..4eb8e9ea4af5 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -747,6 +747,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return compat_put_uint(arg, bdev_io_opt(bdev)); case BLKALIGNOFF: return compat_put_int(arg, bdev_alignment_offset(bdev)); + case BLKDISCARDZEROES: + return compat_put_uint(arg, bdev_discard_zeroes_data(bdev)); case BLKFLSBUF: case BLKROSET: case BLKDISCARD: diff --git a/block/ioctl.c b/block/ioctl.c index 1f4d1de12b09..be48ea51faee 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -280,6 +280,8 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return put_uint(arg, bdev_io_opt(bdev)); case BLKALIGNOFF: return put_int(arg, bdev_alignment_offset(bdev)); + case BLKDISCARDZEROES: + return put_uint(arg, bdev_discard_zeroes_data(bdev)); case BLKSECTGET: return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev))); case BLKRASET: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e727f6c44c44..784a919aa0d0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -322,6 +322,7 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; unsigned char no_cluster; + signed char discard_zeroes_data; }; struct request_queue @@ -1150,6 +1151,19 @@ static inline int queue_sector_discard_alignment(struct request_queue *q, & (q->limits.discard_granularity - 1); } +static inline unsigned int queue_discard_zeroes_data(struct request_queue *q) +{ + if (q->limits.discard_zeroes_data == 1) + return 1; + + return 0; +} + +static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev) +{ + return queue_discard_zeroes_data(bdev_get_queue(bdev)); +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; diff --git a/include/linux/fs.h b/include/linux/fs.h index 79cea8051736..891f7d642e5c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -304,6 +304,7 @@ struct inodes_stat_t { #define BLKIOOPT _IO(0x12,121) #define BLKALIGNOFF _IO(0x12,122) #define BLKPBSZGET _IO(0x12,123) +#define BLKDISCARDZEROES _IO(0x12,124) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 81744ee44ab2845c16ffd7d6f762f7b4a49a4750 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 29 Dec 2009 08:35:35 +0100 Subject: block: Fix incorrect alignment offset reporting and update documentation queue_sector_alignment_offset returned the wrong value which caused partitions to report an incorrect alignment_offset. Since offset alignment calculation is needed several places it has been split into a separate helper function. The topology stacking function has been updated accordingly. Furthermore, comments have been added to clarify how the stacking function works. Signed-off-by: Martin K. Petersen Tested-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-settings.c | 44 +++++++++++++++++++++++++++++++++----------- include/linux/blkdev.h | 11 +++++++++-- 2 files changed, 42 insertions(+), 13 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index e14fcbcedbfa..d52d4adc440b 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -505,20 +505,30 @@ static unsigned int lcm(unsigned int a, unsigned int b) /** * blk_stack_limits - adjust queue_limits for stacked devices - * @t: the stacking driver limits (top) - * @b: the underlying queue limits (bottom) + * @t: the stacking driver limits (top device) + * @b: the underlying queue limits (bottom, component device) * @offset: offset to beginning of data within component device * * Description: - * Merges two queue_limit structs. Returns 0 if alignment didn't - * change. Returns -1 if adding the bottom device caused - * misalignment. + * This function is used by stacking drivers like MD and DM to ensure + * that all component devices have compatible block sizes and + * alignments. The stacking driver must provide a queue_limits + * struct (top) and then iteratively call the stacking function for + * all component (bottom) devices. The stacking function will + * attempt to combine the values and ensure proper alignment. + * + * Returns 0 if the top and bottom queue_limits are compatible. The + * top device's block sizes and alignment offsets may be adjusted to + * ensure alignment with the bottom device. If no compatible sizes + * and alignments exist, -1 is returned and the resulting top + * queue_limits will have the misaligned flag set to indicate that + * the alignment_offset is undefined. */ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset) { sector_t alignment; - unsigned int top, bottom, granularity; + unsigned int top, bottom; t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); @@ -536,15 +546,18 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size); - granularity = max(b->physical_block_size, b->io_min); - alignment = b->alignment_offset - (offset & (granularity - 1)); + alignment = queue_limit_alignment_offset(b, offset); + /* Bottom device has different alignment. Check that it is + * compatible with the current top alignment. + */ if (t->alignment_offset != alignment) { top = max(t->physical_block_size, t->io_min) + t->alignment_offset; - bottom = granularity + alignment; + bottom = max(b->physical_block_size, b->io_min) + alignment; + /* Verify that top and bottom intervals line up */ if (max(top, bottom) & (min(top, bottom) - 1)) t->misaligned = 1; } @@ -561,32 +574,39 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->no_cluster |= b->no_cluster; t->discard_zeroes_data &= b->discard_zeroes_data; + /* Physical block size a multiple of the logical block size? */ if (t->physical_block_size & (t->logical_block_size - 1)) { t->physical_block_size = t->logical_block_size; t->misaligned = 1; } + /* Minimum I/O a multiple of the physical block size? */ if (t->io_min & (t->physical_block_size - 1)) { t->io_min = t->physical_block_size; t->misaligned = 1; } + /* Optimal I/O a multiple of the physical block size? */ if (t->io_opt & (t->physical_block_size - 1)) { t->io_opt = 0; t->misaligned = 1; } + /* Find lowest common alignment_offset */ t->alignment_offset = lcm(t->alignment_offset, alignment) & (max(t->physical_block_size, t->io_min) - 1); + /* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) t->misaligned = 1; /* Discard alignment and granularity */ if (b->discard_granularity) { + unsigned int granularity = b->discard_granularity; + offset &= granularity - 1; - alignment = b->discard_alignment - - (offset & (b->discard_granularity - 1)); + alignment = (granularity + b->discard_alignment - offset) + & (granularity - 1); if (t->discard_granularity != 0 && t->discard_alignment != alignment) { @@ -598,6 +618,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->discard_misaligned = 1; } + t->max_discard_sectors = min_not_zero(t->max_discard_sectors, + b->max_discard_sectors); t->discard_granularity = max(t->discard_granularity, b->discard_granularity); t->discard_alignment = lcm(t->discard_alignment, alignment) & diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 784a919aa0d0..59b832be3044 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1116,11 +1116,18 @@ static inline int queue_alignment_offset(struct request_queue *q) return q->limits.alignment_offset; } +static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t offset) +{ + unsigned int granularity = max(lim->physical_block_size, lim->io_min); + + offset &= granularity - 1; + return (granularity + lim->alignment_offset - offset) & (granularity - 1); +} + static inline int queue_sector_alignment_offset(struct request_queue *q, sector_t sector) { - return ((sector << 9) - q->limits.alignment_offset) - & (q->limits.io_min - 1); + return queue_limit_alignment_offset(&q->limits, sector << 9); } static inline int bdev_alignment_offset(struct block_device *bdev) -- cgit v1.2.3 From 9bd3f98821a83041e77ee25158b80b535d02d7b4 Mon Sep 17 00:00:00 2001 From: Gui Jianfeng Date: Wed, 30 Dec 2009 08:41:07 +0100 Subject: block: blk_rq_err_sectors cleanup blk_rq_err_sectors() seems useless, get rid of it. Signed-off-by: Gui Jianfeng Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 59b832be3044..9b98173a8184 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -845,7 +845,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment - * blk_rq_err_sectors() : sectors left till the next error boundary */ static inline sector_t blk_rq_pos(const struct request *rq) { @@ -874,11 +873,6 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> 9; } -static inline unsigned int blk_rq_err_sectors(const struct request *rq) -{ - return blk_rq_err_bytes(rq) >> 9; -} - /* * Request issue related functions. */ -- cgit v1.2.3 From dd3d145d49c5816b79acc6761ebbd842bc50b0ee Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Mon, 11 Jan 2010 03:21:48 -0500 Subject: block: Fix discard alignment calculation and printing Discard alignment reporting for partitions was incorrect. Update to match the algorithm used elsewhere. The alignment can be negative (misaligned). Fix format string accordingly. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/genhd.c | 2 +- include/linux/blkdev.h | 7 +++++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/genhd.c b/block/genhd.c index b11a4ad7d571..d13ba76a169c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -867,7 +867,7 @@ static ssize_t disk_discard_alignment_show(struct device *dev, { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%u\n", queue_discard_alignment(disk->queue)); + return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue)); } static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9b98173a8184..a41bcc8e140f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1148,8 +1148,11 @@ static inline int queue_discard_alignment(struct request_queue *q) static inline int queue_sector_discard_alignment(struct request_queue *q, sector_t sector) { - return ((sector << 9) - q->limits.discard_alignment) - & (q->limits.discard_granularity - 1); + struct queue_limits *lim = &q->limits; + unsigned int alignment = (sector << 9) & (lim->discard_granularity - 1); + + return (lim->discard_granularity + lim->discard_alignment - alignment) + & (lim->discard_granularity - 1); } static inline unsigned int queue_discard_zeroes_data(struct request_queue *q) -- cgit v1.2.3 From 17be8c245054b9c7786545af3ba3ca4e54cd4ad9 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Mon, 11 Jan 2010 03:21:49 -0500 Subject: block: bdev_stack_limits wrapper DM does not want to know about partition offsets. Add a partition-aware wrapper that DM can use when stacking block devices. Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Reviewed-by: Alasdair G Kergon Signed-off-by: Jens Axboe --- block/blk-settings.c | 22 ++++++++++++++++++++++ include/linux/blkdev.h | 2 ++ 2 files changed, 24 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 127f82551855..5eeb9e0d256e 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -639,6 +639,28 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, } EXPORT_SYMBOL(blk_stack_limits); +/** + * bdev_stack_limits - adjust queue limits for stacked drivers + * @t: the stacking driver limits (top device) + * @bdev: the component block_device (bottom) + * @start: first data sector within component device + * + * Description: + * Merges queue limits for a top device and a block_device. Returns + * 0 if alignment didn't change. Returns -1 if adding the bottom + * device caused misalignment. + */ +int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev, + sector_t start) +{ + struct request_queue *bq = bdev_get_queue(bdev); + + start += get_start_sect(bdev); + + return blk_stack_limits(t, &bq->limits, start << 9); +} +EXPORT_SYMBOL(bdev_stack_limits); + /** * disk_stack_limits - adjust queue limits for stacked drivers * @disk: MD/DM gendisk (top) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a41bcc8e140f..5c8018977efa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -938,6 +938,8 @@ extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_default_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, + sector_t offset); extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset); extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); -- cgit v1.2.3 From e03a72e13648ac6277bf2bab6b8324d51f89c0fa Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Mon, 11 Jan 2010 03:21:51 -0500 Subject: block: Stop using byte offsets All callers of the stacking functions use 512-byte sector units rather than byte offsets. Simplify the code so the stacking functions take sectors when specifying data offsets. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 26 +++++++++----------------- fs/partitions/check.c | 7 ++++--- include/linux/blkdev.h | 17 +++++------------ 3 files changed, 18 insertions(+), 32 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 5eeb9e0d256e..78549c723783 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -507,7 +507,7 @@ static unsigned int lcm(unsigned int a, unsigned int b) * blk_stack_limits - adjust queue_limits for stacked devices * @t: the stacking driver limits (top device) * @b: the underlying queue limits (bottom, component device) - * @offset: offset to beginning of data within component device + * @start: first data sector within component device * * Description: * This function is used by stacking drivers like MD and DM to ensure @@ -525,10 +525,9 @@ static unsigned int lcm(unsigned int a, unsigned int b) * the alignment_offset is undefined. */ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, - sector_t offset) + sector_t start) { - sector_t alignment; - unsigned int top, bottom, ret = 0; + unsigned int top, bottom, alignment, ret = 0; t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); @@ -548,7 +547,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->misaligned |= b->misaligned; - alignment = queue_limit_alignment_offset(b, offset); + alignment = queue_limit_alignment_offset(b, start); /* Bottom device has different alignment. Check that it is * compatible with the current top alignment. @@ -611,11 +610,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, /* Discard alignment and granularity */ if (b->discard_granularity) { - unsigned int granularity = b->discard_granularity; - offset &= granularity - 1; - - alignment = (granularity + b->discard_alignment - offset) - & (granularity - 1); + alignment = queue_limit_discard_alignment(b, start); if (t->discard_granularity != 0 && t->discard_alignment != alignment) { @@ -657,7 +652,7 @@ int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev, start += get_start_sect(bdev); - return blk_stack_limits(t, &bq->limits, start << 9); + return blk_stack_limits(t, &bq->limits, start); } EXPORT_SYMBOL(bdev_stack_limits); @@ -668,9 +663,8 @@ EXPORT_SYMBOL(bdev_stack_limits); * @offset: offset to beginning of data within component device * * Description: - * Merges the limits for two queues. Returns 0 if alignment - * didn't change. Returns -1 if adding the bottom device caused - * misalignment. + * Merges the limits for a top level gendisk and a bottom level + * block_device. */ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset) @@ -678,9 +672,7 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, struct request_queue *t = disk->queue; struct request_queue *b = bdev_get_queue(bdev); - offset += get_start_sect(bdev) << 9; - - if (blk_stack_limits(&t->limits, &b->limits, offset) < 0) { + if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) { char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE]; disk_name(disk, 0, top); diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 64bc8998ac9a..e8865c11777f 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -412,9 +412,10 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, pdev = part_to_dev(p); p->start_sect = start; - p->alignment_offset = queue_sector_alignment_offset(disk->queue, start); - p->discard_alignment = queue_sector_discard_alignment(disk->queue, - start); + p->alignment_offset = + queue_limit_alignment_offset(&disk->queue->limits, start); + p->discard_alignment = + queue_limit_discard_alignment(&disk->queue->limits, start); p->nr_sects = len; p->partno = partno; p->policy = get_disk_ro(disk); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c8018977efa..ffb13ad35716 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1112,18 +1112,13 @@ static inline int queue_alignment_offset(struct request_queue *q) return q->limits.alignment_offset; } -static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t offset) +static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); + unsigned int alignment = (sector << 9) & (granularity - 1); - offset &= granularity - 1; - return (granularity + lim->alignment_offset - offset) & (granularity - 1); -} - -static inline int queue_sector_alignment_offset(struct request_queue *q, - sector_t sector) -{ - return queue_limit_alignment_offset(&q->limits, sector << 9); + return (granularity + lim->alignment_offset - alignment) + & (granularity - 1); } static inline int bdev_alignment_offset(struct block_device *bdev) @@ -1147,10 +1142,8 @@ static inline int queue_discard_alignment(struct request_queue *q) return q->limits.discard_alignment; } -static inline int queue_sector_discard_alignment(struct request_queue *q, - sector_t sector) +static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { - struct queue_limits *lim = &q->limits; unsigned int alignment = (sector << 9) & (lim->discard_granularity - 1); return (lim->discard_granularity + lim->discard_alignment - alignment) -- cgit v1.2.3 From 488991e28e55b4fbca8067edf0259f69d1a6f92c Mon Sep 17 00:00:00 2001 From: "Alan D. Brunelle" Date: Fri, 29 Jan 2010 09:04:08 +0100 Subject: block: Added in stricter no merge semantics for block I/O Updated 'nomerges' tunable to accept a value of '2' - indicating that _no_ merges at all are to be attempted (not even the simple one-hit cache). The following table illustrates the additional benefit - 5 minute runs of a random I/O load were applied to a dozen devices on a 16-way x86_64 system. nomerges Throughput %System Improvement (tput / %sys) -------- ------------ ----------- ------------------------- 0 12.45 MB/sec 0.669365609 1 12.50 MB/sec 0.641519199 0.40% / 2.71% 2 12.52 MB/sec 0.639849750 0.56% / 2.96% Signed-off-by: Alan D. Brunelle Signed-off-by: Jens Axboe --- Documentation/ABI/testing/sysfs-block | 14 ++++++++++++++ Documentation/block/queue-sysfs.txt | 10 +++++----- block/blk-sysfs.c | 11 +++++++---- block/elevator.c | 11 ++++++++++- include/linux/blkdev.h | 3 +++ 5 files changed, 39 insertions(+), 10 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index d2f90334bb93..4873c759d535 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -128,3 +128,17 @@ Description: preferred request size for workloads where sustained throughput is desired. If no optimal I/O size is reported this file contains 0. + +What: /sys/block//queue/nomerges +Date: January 2010 +Contact: +Description: + Standard I/O elevator operations include attempts to + merge contiguous I/Os. For known random I/O loads these + attempts will always fail and result in extra cycles + being spent in the kernel. This allows one to turn off + this behavior on one of two ways: When set to 1, complex + merge checks are disabled, but the simple one-shot merges + with the previous I/O request are enabled. When set to 2, + all merge tries are disabled. The default value is 0 - + which enables all types of merge tries. diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index e164403f60e1..f65274081c8d 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -25,11 +25,11 @@ size allowed by the hardware. nomerges (RW) ------------- -This enables the user to disable the lookup logic involved with IO merging -requests in the block layer. Merging may still occur through a direct -1-hit cache, since that comes for (almost) free. The IO scheduler will not -waste cycles doing tree/hash lookups for merges if nomerges is 1. Defaults -to 0, enabling all merges. +This enables the user to disable the lookup logic involved with IO +merging requests in the block layer. By default (0) all merges are +enabled. When set to 1 only simple one-hit merges will be tried. When +set to 2 no merge algorithms will be tried (including one-hit or more +complex tree/hash lookups). nr_requests (RW) ---------------- diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 8606c9543fdd..e85442415db3 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -189,7 +189,8 @@ static ssize_t queue_nonrot_store(struct request_queue *q, const char *page, static ssize_t queue_nomerges_show(struct request_queue *q, char *page) { - return queue_var_show(blk_queue_nomerges(q), page); + return queue_var_show((blk_queue_nomerges(q) << 1) | + blk_queue_noxmerges(q), page); } static ssize_t queue_nomerges_store(struct request_queue *q, const char *page, @@ -199,10 +200,12 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page, ssize_t ret = queue_var_store(&nm, page, count); spin_lock_irq(q->queue_lock); - if (nm) + queue_flag_clear(QUEUE_FLAG_NOMERGES, q); + queue_flag_clear(QUEUE_FLAG_NOXMERGES, q); + if (nm == 2) queue_flag_set(QUEUE_FLAG_NOMERGES, q); - else - queue_flag_clear(QUEUE_FLAG_NOMERGES, q); + else if (nm) + queue_flag_set(QUEUE_FLAG_NOXMERGES, q); spin_unlock_irq(q->queue_lock); return ret; diff --git a/block/elevator.c b/block/elevator.c index 9ad5ccc4c5ee..ee3a883840f2 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -473,6 +473,15 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio) struct request *__rq; int ret; + /* + * Levels of merges: + * nomerges: No merges at all attempted + * noxmerges: Only simple one-hit cache try + * merges: All merge tries attempted + */ + if (blk_queue_nomerges(q)) + return ELEVATOR_NO_MERGE; + /* * First try one-hit cache. */ @@ -484,7 +493,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio) } } - if (blk_queue_nomerges(q)) + if (blk_queue_noxmerges(q)) return ELEVATOR_NO_MERGE; /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ffb13ad35716..f71f5c58620c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -463,6 +463,7 @@ struct request_queue #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ #define QUEUE_FLAG_CQ 16 /* hardware does queuing */ #define QUEUE_FLAG_DISCARD 17 /* supports DISCARD */ +#define QUEUE_FLAG_NOXMERGES 18 /* No extended merges */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -589,6 +590,8 @@ enum { #define blk_queue_queuing(q) test_bit(QUEUE_FLAG_CQ, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(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) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_flushing(q) ((q)->ordseq) -- cgit v1.2.3 From 79da0644a8e0838522828f106e4049639eea6baf Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 23 Feb 2010 08:40:43 +0100 Subject: Revert "block: improve queue_should_plug() by looking at IO depths" This reverts commit fb1e75389bd06fd5987e9cda1b4e0305c782f854. "Benjamin S." reports that the patch in question causes a big drop in sequential throughput for him, dropping from 200MB/sec down to only 70MB/sec. Needs to be investigated more fully, for now lets just revert the offending commit. Conflicts: include/linux/blkdev.h Signed-off-by: Jens Axboe --- block/blk-core.c | 11 ++--------- include/linux/blkdev.h | 4 +--- 2 files changed, 3 insertions(+), 12 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 718897e6d37f..d1a9a0a64f95 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1147,7 +1147,7 @@ void init_request_from_bio(struct request *req, struct bio *bio) */ static inline bool queue_should_plug(struct request_queue *q) { - return !(blk_queue_nonrot(q) && blk_queue_queuing(q)); + return !(blk_queue_nonrot(q) && blk_queue_tagged(q)); } static int __make_request(struct request_queue *q, struct bio *bio) @@ -1859,15 +1859,8 @@ void blk_dequeue_request(struct request *rq) * and to it is freed is accounted as io that is in progress at * the driver side. */ - if (blk_account_rq(rq)) { + if (blk_account_rq(rq)) q->in_flight[rq_is_sync(rq)]++; - /* - * Mark this device as supporting hardware queuing, if - * we have more IOs in flight than 4. - */ - if (!blk_queue_queuing(q) && queue_in_flight(q) > 4) - set_bit(QUEUE_FLAG_CQ, &q->queue_flags); - } } /** diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c8018977efa..1896e868854f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -461,8 +461,7 @@ struct request_queue #define QUEUE_FLAG_NONROT 14 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ -#define QUEUE_FLAG_CQ 16 /* hardware does queuing */ -#define QUEUE_FLAG_DISCARD 17 /* supports DISCARD */ +#define QUEUE_FLAG_DISCARD 16 /* supports DISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -586,7 +585,6 @@ enum { #define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) #define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) -#define blk_queue_queuing(q) test_bit(QUEUE_FLAG_CQ, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) -- cgit v1.2.3 From e751e76a5f7adeee7438e68b0965559ad2864d0d Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Feb 2010 00:20:36 -0500 Subject: block: Remove unused accessor function blk_queue_max_hw_sectors is no longer called by any subsystem and can be removed. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 9 --------- include/linux/blkdev.h | 1 - 2 files changed, 10 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 605df9b3de8f..4db46f2fcbe5 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -239,15 +239,6 @@ void blk_queue_max_sectors(struct request_queue *q, unsigned int max_hw_sectors) } EXPORT_SYMBOL(blk_queue_max_sectors); -void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors) -{ - if (BLK_DEF_MAX_SECTORS > max_sectors) - q->limits.max_hw_sectors = BLK_DEF_MAX_SECTORS; - else - q->limits.max_hw_sectors = max_sectors; -} -EXPORT_SYMBOL(blk_queue_max_hw_sectors); - /** * blk_queue_max_discard_sectors - set max sectors for a single discard * @q: the request queue for the device diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2f17793048e7..c051cea2df07 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -922,7 +922,6 @@ extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_sectors(struct request_queue *, unsigned int); -extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); -- cgit v1.2.3 From eb28d31bc97e6374d81f404da309401ffaed467b Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Feb 2010 00:20:37 -0500 Subject: block: Add BLK_ prefix to definitions Add a BLK_ prefix to block layer constants. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 4 ++-- drivers/block/ps3vram.c | 4 ++-- include/linux/blkdev.h | 10 +++++++--- 3 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index 4db46f2fcbe5..3c53b0beb8dd 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -94,7 +94,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->max_phys_segments = MAX_PHYS_SEGMENTS; lim->max_hw_segments = MAX_HW_SEGMENTS; lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; - lim->max_segment_size = MAX_SEGMENT_SIZE; + lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; lim->max_sectors = BLK_DEF_MAX_SECTORS; lim->max_hw_sectors = INT_MAX; lim->max_discard_sectors = 0; @@ -154,7 +154,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn) q->unplug_timer.data = (unsigned long)q; blk_set_default_limits(&q->limits); - blk_queue_max_sectors(q, SAFE_MAX_SECTORS); + blk_queue_max_sectors(q, BLK_SAFE_MAX_SECTORS); /* * If the caller didn't supply a lock, fall back to our embedded diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 1fb6c3135fc8..a7ecb43b16ab 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -753,8 +753,8 @@ static int __devinit ps3vram_probe(struct ps3_system_bus_device *dev) blk_queue_make_request(queue, ps3vram_make_request); blk_queue_max_phys_segments(queue, MAX_PHYS_SEGMENTS); blk_queue_max_hw_segments(queue, MAX_HW_SEGMENTS); - blk_queue_max_segment_size(queue, MAX_SEGMENT_SIZE); - blk_queue_max_sectors(queue, SAFE_MAX_SECTORS); + blk_queue_max_segment_size(queue, BLK_MAX_SEGMENT_SIZE); + blk_queue_max_sectors(queue, BLK_SAFE_MAX_SECTORS); gendisk = alloc_disk(1); if (!gendisk) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c051cea2df07..5d378627f446 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1016,11 +1016,15 @@ extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); #define MAX_PHYS_SEGMENTS 128 #define MAX_HW_SEGMENTS 128 #define SAFE_MAX_SECTORS 255 -#define BLK_DEF_MAX_SECTORS 1024 - #define MAX_SEGMENT_SIZE 65536 -#define BLK_SEG_BOUNDARY_MASK 0xFFFFFFFFUL +enum blk_default_limits { + BLK_MAX_SEGMENTS = 128, + BLK_SAFE_MAX_SECTORS = 255, + BLK_DEF_MAX_SECTORS = 1024, + BLK_MAX_SEGMENT_SIZE = 65536, + BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, +}; #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) -- cgit v1.2.3 From 086fa5ff0854c676ec333760f4c0154b3b242616 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Feb 2010 00:20:38 -0500 Subject: block: Rename blk_queue_max_sectors to blk_queue_max_hw_sectors The block layer calling convention is blk_queue_. blk_queue_max_sectors predates this practice, leading to some confusion. Rename the function to appropriately reflect that its intended use is to set max_hw_sectors. Also introduce a temporary wrapper for backwards compability. This can be removed after the merge window is closed. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- arch/um/drivers/ubd_kern.c | 2 +- block/blk-settings.c | 8 ++++---- drivers/ata/libata-scsi.c | 2 +- drivers/block/DAC960.c | 2 +- drivers/block/brd.c | 2 +- drivers/block/cciss.c | 2 +- drivers/block/drbd/drbd_nl.c | 2 +- drivers/block/floppy.c | 2 +- drivers/block/hd.c | 2 +- drivers/block/mg_disk.c | 2 +- drivers/block/paride/pd.c | 2 +- drivers/block/pktcdvd.c | 4 ++-- drivers/block/ps3disk.c | 2 +- drivers/block/ps3vram.c | 2 +- drivers/block/sunvdc.c | 2 +- drivers/block/ub.c | 2 +- drivers/block/viodasd.c | 2 +- drivers/block/xd.c | 2 +- drivers/block/xen-blkfront.c | 2 +- drivers/cdrom/viocd.c | 2 +- drivers/firewire/sbp2.c | 2 +- drivers/ide/ide-disk.c | 2 +- drivers/ide/ide-floppy.c | 4 ++-- drivers/ide/ide-probe.c | 2 +- drivers/ieee1394/sbp2.c | 2 +- drivers/md/linear.c | 2 +- drivers/md/multipath.c | 4 ++-- drivers/md/raid0.c | 4 ++-- drivers/md/raid1.c | 4 ++-- drivers/md/raid10.c | 4 ++-- drivers/memstick/core/mspro_block.c | 2 +- drivers/message/i2o/i2o_block.c | 2 +- drivers/mmc/card/queue.c | 4 ++-- drivers/s390/block/dasd.c | 2 +- drivers/s390/char/tape_block.c | 2 +- drivers/scsi/ipr.c | 2 +- drivers/scsi/pmcraid.c | 2 +- drivers/scsi/scsi_lib.c | 2 +- drivers/scsi/scsi_scan.c | 2 +- drivers/usb/storage/scsiglue.c | 6 +++--- include/linux/blkdev.h | 9 ++++++++- 41 files changed, 60 insertions(+), 53 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 5ff554677f40..c2051b0737cb 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -747,7 +747,7 @@ static int ubd_open_dev(struct ubd *ubd_dev) ubd_dev->fd = fd; if(ubd_dev->cow.file != NULL){ - blk_queue_max_sectors(ubd_dev->queue, 8 * sizeof(long)); + blk_queue_max_hw_sectors(ubd_dev->queue, 8 * sizeof(long)); err = -ENOMEM; ubd_dev->cow.bitmap = vmalloc(ubd_dev->cow.bitmap_len); diff --git a/block/blk-settings.c b/block/blk-settings.c index 3c53b0beb8dd..61afae9dbc6d 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -154,7 +154,7 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn) q->unplug_timer.data = (unsigned long)q; blk_set_default_limits(&q->limits); - blk_queue_max_sectors(q, BLK_SAFE_MAX_SECTORS); + blk_queue_max_hw_sectors(q, BLK_SAFE_MAX_SECTORS); /* * If the caller didn't supply a lock, fall back to our embedded @@ -210,7 +210,7 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask) EXPORT_SYMBOL(blk_queue_bounce_limit); /** - * blk_queue_max_sectors - set max sectors for a request for this queue + * blk_queue_max_hw_sectors - set max sectors for a request for this queue * @q: the request queue for the device * @max_hw_sectors: max hardware sectors in the usual 512b unit * @@ -225,7 +225,7 @@ EXPORT_SYMBOL(blk_queue_bounce_limit); * per-device basis in /sys/block//queue/max_sectors_kb. * The soft limit can not exceed max_hw_sectors. **/ -void blk_queue_max_sectors(struct request_queue *q, unsigned int max_hw_sectors) +void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors) { if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) { max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9); @@ -237,7 +237,7 @@ void blk_queue_max_sectors(struct request_queue *q, unsigned int max_hw_sectors) q->limits.max_sectors = min_t(unsigned int, max_hw_sectors, BLK_DEF_MAX_SECTORS); } -EXPORT_SYMBOL(blk_queue_max_sectors); +EXPORT_SYMBOL(blk_queue_max_hw_sectors); /** * blk_queue_max_discard_sectors - set max sectors for a single discard diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index d096fbcbc771..bea003a24d27 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1097,7 +1097,7 @@ static int ata_scsi_dev_config(struct scsi_device *sdev, dev->flags |= ATA_DFLAG_NO_UNLOAD; /* configure max sectors */ - blk_queue_max_sectors(sdev->request_queue, dev->max_sectors); + blk_queue_max_hw_sectors(sdev->request_queue, dev->max_sectors); if (dev->class == ATA_DEV_ATAPI) { struct request_queue *q = sdev->request_queue; diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index 7412b5d4f5f3..1c0cd35e1913 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -2535,7 +2535,7 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller) RequestQueue->queuedata = Controller; blk_queue_max_hw_segments(RequestQueue, Controller->DriverScatterGatherLimit); blk_queue_max_phys_segments(RequestQueue, Controller->DriverScatterGatherLimit); - blk_queue_max_sectors(RequestQueue, Controller->MaxBlocksPerCommand); + blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand); disk->queue = RequestQueue; sprintf(disk->disk_name, "rd/c%dd%d", Controller->ControllerNumber, n); disk->major = MajorNumber; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 4f688434daf1..c6ddeacb77fd 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -434,7 +434,7 @@ static struct brd_device *brd_alloc(int i) goto out_free_dev; blk_queue_make_request(brd->brd_queue, brd_make_request); blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG, NULL); - blk_queue_max_sectors(brd->brd_queue, 1024); + blk_queue_max_hw_sectors(brd->brd_queue, 1024); blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY); disk = brd->brd_disk = alloc_disk(1 << part_shift); diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 86acdca5d0ce..030e52d72254 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1802,7 +1802,7 @@ static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk, /* This is a limit in the driver and could be eliminated. */ blk_queue_max_phys_segments(disk->queue, h->maxsgentries); - blk_queue_max_sectors(disk->queue, h->cciss_max_sectors); + blk_queue_max_hw_sectors(disk->queue, h->cciss_max_sectors); blk_queue_softirq_done(disk->queue, cciss_softirq_done); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 1292e0620663..9b55e64196fc 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -709,7 +709,7 @@ void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_seg_s) __mu max_seg_s = min(queue_max_sectors(b) * queue_logical_block_size(b), max_seg_s); - blk_queue_max_sectors(q, max_seg_s >> 9); + blk_queue_max_hw_sectors(q, max_seg_s >> 9); blk_queue_max_phys_segments(q, max_segments ? max_segments : MAX_PHYS_SEGMENTS); blk_queue_max_hw_segments(q, max_segments ? max_segments : MAX_HW_SEGMENTS); blk_queue_max_segment_size(q, max_seg_s); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 3266b4f65daa..b9b117059b62 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4234,7 +4234,7 @@ static int __init floppy_init(void) err = -ENOMEM; goto out_unreg_driver; } - blk_queue_max_sectors(floppy_queue, 64); + blk_queue_max_hw_sectors(floppy_queue, 64); blk_register_region(MKDEV(FLOPPY_MAJOR, 0), 256, THIS_MODULE, floppy_find, NULL, NULL); diff --git a/drivers/block/hd.c b/drivers/block/hd.c index d5cdce08ffd2..5116c65c07cb 100644 --- a/drivers/block/hd.c +++ b/drivers/block/hd.c @@ -719,7 +719,7 @@ static int __init hd_init(void) return -ENOMEM; } - blk_queue_max_sectors(hd_queue, 255); + blk_queue_max_hw_sectors(hd_queue, 255); init_timer(&device_timer); device_timer.function = hd_times_out; blk_queue_logical_block_size(hd_queue, 512); diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c index 02b2583df7fc..5416c9a606e4 100644 --- a/drivers/block/mg_disk.c +++ b/drivers/block/mg_disk.c @@ -980,7 +980,7 @@ static int mg_probe(struct platform_device *plat_dev) __func__, __LINE__); goto probe_err_6; } - blk_queue_max_sectors(host->breq, MG_MAX_SECTS); + blk_queue_max_hw_sectors(host->breq, MG_MAX_SECTS); blk_queue_logical_block_size(host->breq, MG_SECTOR_SIZE); init_timer(&host->timer); diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 569e39e8f114..e712cd51af15 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -906,7 +906,7 @@ static int __init pd_init(void) if (!pd_queue) goto out1; - blk_queue_max_sectors(pd_queue, cluster); + blk_queue_max_hw_sectors(pd_queue, cluster); if (register_blkdev(major, name)) goto out2; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 7cd2973ebb7b..6e1daa24da2f 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2312,7 +2312,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) * even if the size is a multiple of the packet size. */ spin_lock_irq(q->queue_lock); - blk_queue_max_sectors(q, pd->settings.size); + blk_queue_max_hw_sectors(q, pd->settings.size); spin_unlock_irq(q->queue_lock); set_bit(PACKET_WRITABLE, &pd->flags); } else { @@ -2613,7 +2613,7 @@ static void pkt_init_queue(struct pktcdvd_device *pd) blk_queue_make_request(q, pkt_make_request); blk_queue_logical_block_size(q, CD_FRAMESIZE); - blk_queue_max_sectors(q, PACKET_MAX_SECTORS); + blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS); blk_queue_merge_bvec(q, pkt_merge_bvec); q->queuedata = pd; } diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 03a130dca8ab..9cd1a4a542b8 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -474,7 +474,7 @@ static int __devinit ps3disk_probe(struct ps3_system_bus_device *_dev) blk_queue_bounce_limit(queue, BLK_BOUNCE_HIGH); - blk_queue_max_sectors(queue, dev->bounce_size >> 9); + blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9); blk_queue_segment_boundary(queue, -1UL); blk_queue_dma_alignment(queue, dev->blk_size-1); blk_queue_logical_block_size(queue, dev->blk_size); diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index a7ecb43b16ab..6416b262934b 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -754,7 +754,7 @@ static int __devinit ps3vram_probe(struct ps3_system_bus_device *dev) blk_queue_max_phys_segments(queue, MAX_PHYS_SEGMENTS); blk_queue_max_hw_segments(queue, MAX_HW_SEGMENTS); blk_queue_max_segment_size(queue, BLK_MAX_SEGMENT_SIZE); - blk_queue_max_sectors(queue, BLK_SAFE_MAX_SECTORS); + blk_queue_max_hw_sectors(queue, BLK_SAFE_MAX_SECTORS); gendisk = alloc_disk(1); if (!gendisk) { diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 411f064760b4..dd30cddd0f7f 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -693,7 +693,7 @@ static int probe_disk(struct vdc_port *port) blk_queue_max_hw_segments(q, port->ring_cookies); blk_queue_max_phys_segments(q, port->ring_cookies); - blk_queue_max_sectors(q, port->max_xfer_size); + blk_queue_max_hw_sectors(q, port->max_xfer_size); g->major = vdc_major; g->first_minor = port->vio.vdev->dev_no << PARTITION_SHIFT; strcpy(g->disk_name, port->disk_name); diff --git a/drivers/block/ub.c b/drivers/block/ub.c index d86d1357ccef..352ea24d66e8 100644 --- a/drivers/block/ub.c +++ b/drivers/block/ub.c @@ -2323,7 +2323,7 @@ static int ub_probe_lun(struct ub_dev *sc, int lnum) blk_queue_max_hw_segments(q, UB_MAX_REQ_SG); blk_queue_max_phys_segments(q, UB_MAX_REQ_SG); blk_queue_segment_boundary(q, 0xffffffff); /* Dubious. */ - blk_queue_max_sectors(q, UB_MAX_SECTORS); + blk_queue_max_hw_sectors(q, UB_MAX_SECTORS); blk_queue_logical_block_size(q, lun->capacity.bsize); lun->disk = disk; diff --git a/drivers/block/viodasd.c b/drivers/block/viodasd.c index a8c8b56b275e..d44ece7d7b7c 100644 --- a/drivers/block/viodasd.c +++ b/drivers/block/viodasd.c @@ -473,7 +473,7 @@ retry: d->disk = g; blk_queue_max_hw_segments(q, VIOMAXBLOCKDMA); blk_queue_max_phys_segments(q, VIOMAXBLOCKDMA); - blk_queue_max_sectors(q, VIODASD_MAXSECTORS); + blk_queue_max_hw_sectors(q, VIODASD_MAXSECTORS); g->major = VIODASD_MAJOR; g->first_minor = dev_no << PARTITION_SHIFT; if (dev_no >= 26) diff --git a/drivers/block/xd.c b/drivers/block/xd.c index d1fd032e7514..1a325fb05c92 100644 --- a/drivers/block/xd.c +++ b/drivers/block/xd.c @@ -242,7 +242,7 @@ static int __init xd_init(void) } /* xd_maxsectors depends on controller - so set after detection */ - blk_queue_max_sectors(xd_queue, xd_maxsectors); + blk_queue_max_hw_sectors(xd_queue, xd_maxsectors); for (i = 0; i < xd_drives; i++) add_disk(xd_gendisk[i]); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index a84702d1a35e..f9861aaa1fef 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -346,7 +346,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size) /* Hard sector size and max sectors impersonate the equiv. hardware. */ blk_queue_logical_block_size(rq, sector_size); - blk_queue_max_sectors(rq, 512); + blk_queue_max_hw_sectors(rq, 512); /* Each segment in a request is up to an aligned page in size. */ blk_queue_segment_boundary(rq, PAGE_SIZE - 1); diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c index 57ca69e0ac55..b1dfd23eb832 100644 --- a/drivers/cdrom/viocd.c +++ b/drivers/cdrom/viocd.c @@ -618,7 +618,7 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id) sizeof(gendisk->disk_name)); blk_queue_max_hw_segments(q, 1); blk_queue_max_phys_segments(q, 1); - blk_queue_max_sectors(q, 4096 / 512); + blk_queue_max_hw_sectors(q, 4096 / 512); gendisk->queue = q; gendisk->fops = &viocd_fops; gendisk->flags = GENHD_FL_CD|GENHD_FL_REMOVABLE; diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index d485cdd8cbac..70fef40cd22f 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -1571,7 +1571,7 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev) sdev->start_stop_pwr_cond = 1; if (lu->tgt->workarounds & SBP2_WORKAROUND_128K_MAX_TRANS) - blk_queue_max_sectors(sdev->request_queue, 128 * 1024 / 512); + blk_queue_max_hw_sectors(sdev->request_queue, 128 * 1024 / 512); blk_queue_max_segment_size(sdev->request_queue, SBP2_MAX_SEG_SIZE); diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 7f878017b736..3b128dce9c3a 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -679,7 +679,7 @@ static void ide_disk_setup(ide_drive_t *drive) if (max_s > hwif->rqsize) max_s = hwif->rqsize; - blk_queue_max_sectors(q, max_s); + blk_queue_max_hw_sectors(q, max_s); } printk(KERN_INFO "%s: max request size: %dKiB\n", drive->name, diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index fefbdfc8db06..efd907623469 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -486,7 +486,7 @@ static void ide_floppy_setup(ide_drive_t *drive) drive->atapi_flags |= IDE_AFLAG_ZIP_DRIVE; /* This value will be visible in the /proc/ide/hdx/settings */ drive->pc_delay = IDEFLOPPY_PC_DELAY; - blk_queue_max_sectors(drive->queue, 64); + blk_queue_max_hw_sectors(drive->queue, 64); } /* @@ -494,7 +494,7 @@ static void ide_floppy_setup(ide_drive_t *drive) * nasty clicking noises without it, so please don't remove this. */ if (strncmp((char *)&id[ATA_ID_PROD], "IOMEGA Clik!", 11) == 0) { - blk_queue_max_sectors(drive->queue, 64); + blk_queue_max_hw_sectors(drive->queue, 64); drive->atapi_flags |= IDE_AFLAG_CLIK_DRIVE; /* IOMEGA Clik! drives do not support lock/unlock commands */ drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 4d76ba473097..1ec8b31277bd 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -774,7 +774,7 @@ static int ide_init_queue(ide_drive_t *drive) if (hwif->rqsize < max_sectors) max_sectors = hwif->rqsize; - blk_queue_max_sectors(q, max_sectors); + blk_queue_max_hw_sectors(q, max_sectors); #ifdef CONFIG_PCI /* When we have an IOMMU, we may have a problem where pci_map_sg() diff --git a/drivers/ieee1394/sbp2.c b/drivers/ieee1394/sbp2.c index f199896c4113..c88696a6cf8a 100644 --- a/drivers/ieee1394/sbp2.c +++ b/drivers/ieee1394/sbp2.c @@ -2020,7 +2020,7 @@ static int sbp2scsi_slave_configure(struct scsi_device *sdev) if (lu->workarounds & SBP2_WORKAROUND_POWER_CONDITION) sdev->start_stop_pwr_cond = 1; if (lu->workarounds & SBP2_WORKAROUND_128K_MAX_TRANS) - blk_queue_max_sectors(sdev->request_queue, 128 * 1024 / 512); + blk_queue_max_hw_sectors(sdev->request_queue, 128 * 1024 / 512); blk_queue_max_segment_size(sdev->request_queue, SBP2_MAX_SEG_SIZE); return 0; diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 00435bd20699..af2d39d603c7 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -177,7 +177,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks) */ if (rdev->bdev->bd_disk->queue->merge_bvec_fn && queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9); conf->array_sectors += rdev->sectors; cnt++; diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 32a662fc55c9..4b323f45ad74 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -308,7 +308,7 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) */ if (q->merge_bvec_fn && queue_max_sectors(q) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9); conf->working_disks++; mddev->degraded--; @@ -478,7 +478,7 @@ static int multipath_run (mddev_t *mddev) * a merge_bvec_fn to be involved in multipath */ if (rdev->bdev->bd_disk->queue->merge_bvec_fn && queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9); if (!test_bit(Faulty, &rdev->flags)) conf->working_disks++; diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 77605cdceaf1..a1f7147b757f 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -182,7 +182,7 @@ static int create_strip_zones(mddev_t *mddev) if (rdev1->bdev->bd_disk->queue->merge_bvec_fn && queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9); if (!smallest || (rdev1->sectors < smallest->sectors)) smallest = rdev1; @@ -325,7 +325,7 @@ static int raid0_run(mddev_t *mddev) } if (md_check_no_bitmap(mddev)) return -EINVAL; - blk_queue_max_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); mddev->queue->queue_lock = &mddev->queue->__queue_lock; ret = create_strip_zones(mddev); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 859bd3ffe435..5a06122abd3b 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1158,7 +1158,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) */ if (rdev->bdev->bd_disk->queue->merge_bvec_fn && queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9); p->head_position = 0; rdev->raid_disk = mirror; @@ -2103,7 +2103,7 @@ static int run(mddev_t *mddev) */ if (rdev->bdev->bd_disk->queue->merge_bvec_fn && queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9); } mddev->degraded = 0; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index d119b7b75e71..7584f9ab9bcf 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1161,7 +1161,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) */ if (rdev->bdev->bd_disk->queue->merge_bvec_fn && queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9); p->head_position = 0; rdev->raid_disk = mirror; @@ -2260,7 +2260,7 @@ static int run(mddev_t *mddev) */ if (rdev->bdev->bd_disk->queue->merge_bvec_fn && queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9)) - blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9); + blk_queue_max_hw_sectors(mddev->queue, PAGE_SIZE>>9); disk->head_position = 0; } diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index bd83fa0a4970..44d4178c4c15 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -1226,7 +1226,7 @@ static int mspro_block_init_disk(struct memstick_dev *card) blk_queue_prep_rq(msb->queue, mspro_block_prepare_req); blk_queue_bounce_limit(msb->queue, limit); - blk_queue_max_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES); + blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES); blk_queue_max_phys_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS); blk_queue_max_hw_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS); blk_queue_max_segment_size(msb->queue, diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c index e39986a78273..d033cfdb516f 100644 --- a/drivers/message/i2o/i2o_block.c +++ b/drivers/message/i2o/i2o_block.c @@ -1066,7 +1066,7 @@ static int i2o_block_probe(struct device *dev) queue->queuedata = i2o_blk_dev; blk_queue_max_phys_segments(queue, I2O_MAX_PHYS_SEGMENTS); - blk_queue_max_sectors(queue, max_sectors); + blk_queue_max_hw_sectors(queue, max_sectors); blk_queue_max_hw_segments(queue, i2o_sg_tablesize(c, body_size)); osm_debug("max sectors = %d\n", queue->max_sectors); diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index c5a7a855f4b1..09b633d5657b 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -154,7 +154,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock if (mq->bounce_buf) { blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY); - blk_queue_max_sectors(mq->queue, bouncesz / 512); + blk_queue_max_hw_sectors(mq->queue, bouncesz / 512); blk_queue_max_phys_segments(mq->queue, bouncesz / 512); blk_queue_max_hw_segments(mq->queue, bouncesz / 512); blk_queue_max_segment_size(mq->queue, bouncesz); @@ -180,7 +180,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock if (!mq->bounce_buf) { blk_queue_bounce_limit(mq->queue, limit); - blk_queue_max_sectors(mq->queue, + blk_queue_max_hw_sectors(mq->queue, min(host->max_blk_count, host->max_req_size / 512)); blk_queue_max_phys_segments(mq->queue, host->max_phys_segs); blk_queue_max_hw_segments(mq->queue, host->max_hw_segs); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 5905936c7c60..14b1e25b9dcf 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2129,7 +2129,7 @@ static void dasd_setup_queue(struct dasd_block *block) blk_queue_logical_block_size(block->request_queue, block->bp_block); max = block->base->discipline->max_blocks << block->s2b_shift; - blk_queue_max_sectors(block->request_queue, max); + blk_queue_max_hw_sectors(block->request_queue, max); blk_queue_max_phys_segments(block->request_queue, -1L); blk_queue_max_hw_segments(block->request_queue, -1L); /* with page sized segments we can translate each segement into diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c index 8d3d720737da..509ed056fddd 100644 --- a/drivers/s390/char/tape_block.c +++ b/drivers/s390/char/tape_block.c @@ -222,7 +222,7 @@ tapeblock_setup_device(struct tape_device * device) goto cleanup_queue; blk_queue_logical_block_size(blkdat->request_queue, TAPEBLOCK_HSEC_SIZE); - blk_queue_max_sectors(blkdat->request_queue, TAPEBLOCK_MAX_SEC); + blk_queue_max_hw_sectors(blkdat->request_queue, TAPEBLOCK_MAX_SEC); blk_queue_max_phys_segments(blkdat->request_queue, -1L); blk_queue_max_hw_segments(blkdat->request_queue, -1L); blk_queue_max_segment_size(blkdat->request_queue, -1L); diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 9e52d16c7c39..032f0d0e6cb4 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -3674,7 +3674,7 @@ static int ipr_slave_configure(struct scsi_device *sdev) if (ipr_is_vset_device(res)) { blk_queue_rq_timeout(sdev->request_queue, IPR_VSET_RW_TIMEOUT); - blk_queue_max_sectors(sdev->request_queue, IPR_VSET_MAX_SECTORS); + blk_queue_max_hw_sectors(sdev->request_queue, IPR_VSET_MAX_SECTORS); } if (ipr_is_vset_device(res) || ipr_is_scsi_disk(res)) sdev->allow_restart = 1; diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index b6f1ef954af1..9b1c1433c26b 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -235,7 +235,7 @@ static int pmcraid_slave_configure(struct scsi_device *scsi_dev) scsi_dev->allow_restart = 1; blk_queue_rq_timeout(scsi_dev->request_queue, PMCRAID_VSET_IO_TIMEOUT); - blk_queue_max_sectors(scsi_dev->request_queue, + blk_queue_max_hw_sectors(scsi_dev->request_queue, PMCRAID_VSET_MAX_SECTORS); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index c6642423cc67..ac3cca74bdfb 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1627,7 +1627,7 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, blk_queue_max_hw_segments(q, shost->sg_tablesize); blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS); - blk_queue_max_sectors(q, shost->max_sectors); + blk_queue_max_hw_sectors(q, shost->max_sectors); blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost)); blk_queue_segment_boundary(q, shost->dma_boundary); dma_set_seg_boundary(dev, shost->dma_boundary); diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 012f73a96880..5d9b5130d8c8 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -879,7 +879,7 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, * broken RA4x00 Compaq Disk Array */ if (*bflags & BLIST_MAX_512) - blk_queue_max_sectors(sdev->request_queue, 512); + blk_queue_max_hw_sectors(sdev->request_queue, 512); /* * Some devices may not want to have a start command automatically diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index e5e6df39e737..aadc16b5eed7 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -134,14 +134,14 @@ static int slave_configure(struct scsi_device *sdev) if (us->fflags & US_FL_MAX_SECTORS_MIN) max_sectors = PAGE_CACHE_SIZE >> 9; if (queue_max_sectors(sdev->request_queue) > max_sectors) - blk_queue_max_sectors(sdev->request_queue, + blk_queue_max_hw_sectors(sdev->request_queue, max_sectors); } else if (sdev->type == TYPE_TAPE) { /* Tapes need much higher max_sector limits, so just * raise it to the maximum possible (4 GB / 512) and * let the queue segment size sort out the real limit. */ - blk_queue_max_sectors(sdev->request_queue, 0x7FFFFF); + blk_queue_max_hw_sectors(sdev->request_queue, 0x7FFFFF); } /* Some USB host controllers can't do DMA; they have to use PIO. @@ -495,7 +495,7 @@ static ssize_t store_max_sectors(struct device *dev, struct device_attribute *at unsigned short ms; if (sscanf(buf, "%hu", &ms) > 0 && ms <= SCSI_DEFAULT_MAX_SECTORS) { - blk_queue_max_sectors(sdev->request_queue, ms); + blk_queue_max_hw_sectors(sdev->request_queue, ms); return strlen(buf); } return -EINVAL; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5d378627f446..57bc48446e92 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -921,7 +921,14 @@ extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); -extern void blk_queue_max_sectors(struct request_queue *, unsigned int); +extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); + +/* Temporary compatibility wrapper */ +static inline void blk_queue_max_sectors(struct request_queue *q, unsigned int max) +{ + blk_queue_max_hw_sectors(q, max); +} + extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); -- cgit v1.2.3 From 8a78362c4eefc1deddbefe2c7f38aabbc2429d6b Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 26 Feb 2010 00:20:39 -0500 Subject: block: Consolidate phys_segment and hw_segment limits Except for SCSI no device drivers distinguish between physical and hardware segment limits. Consolidate the two into a single segment limit. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- arch/um/drivers/ubd_kern.c | 2 +- block/blk-core.c | 3 +- block/blk-merge.c | 8 ++--- block/blk-settings.c | 60 ++++++++----------------------------- drivers/ata/sata_nv.c | 2 +- drivers/block/DAC960.c | 2 +- drivers/block/cciss.c | 5 +--- drivers/block/cpqarray.c | 5 +--- drivers/block/drbd/drbd_nl.c | 3 +- drivers/block/paride/pf.c | 3 +- drivers/block/pktcdvd.c | 4 +-- drivers/block/ps3disk.c | 3 +- drivers/block/ps3vram.c | 3 +- drivers/block/sunvdc.c | 3 +- drivers/block/sx8.c | 3 +- drivers/block/ub.c | 3 +- drivers/block/viodasd.c | 3 +- drivers/block/xen-blkfront.c | 3 +- drivers/cdrom/gdrom.c | 2 +- drivers/cdrom/viocd.c | 3 +- drivers/ide/ide-probe.c | 3 +- drivers/md/raid5.c | 2 +- drivers/memstick/core/mspro_block.c | 3 +- drivers/message/i2o/i2o_block.c | 3 +- drivers/mmc/card/queue.c | 6 ++-- drivers/s390/block/dasd.c | 3 +- drivers/s390/char/tape_block.c | 3 +- drivers/scsi/ibmvscsi/ibmvfc.c | 4 +-- drivers/scsi/scsi_lib.c | 4 +-- drivers/scsi/sg.c | 6 ++-- drivers/scsi/st.c | 3 +- drivers/staging/hv/blkvsc_drv.c | 5 +--- fs/bio.c | 9 ++---- include/linux/blkdev.h | 27 ++++++++++------- include/linux/i2o.h | 2 +- 35 files changed, 70 insertions(+), 136 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index c2051b0737cb..c1ff6903b622 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -849,7 +849,7 @@ static int ubd_add(int n, char **error_out) } ubd_dev->queue->queuedata = ubd_dev; - blk_queue_max_hw_segments(ubd_dev->queue, MAX_SG); + blk_queue_max_segments(ubd_dev->queue, MAX_SG); err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, &ubd_gendisk[n]); if(err){ *error_out = "Failed to register device"; diff --git a/block/blk-core.c b/block/blk-core.c index 36c0deebc2dc..9fe174dc74d1 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1614,8 +1614,7 @@ int blk_rq_check_limits(struct request_queue *q, struct request *rq) * limitation. */ blk_recalc_rq_segments(rq); - if (rq->nr_phys_segments > queue_max_phys_segments(q) || - rq->nr_phys_segments > queue_max_hw_segments(q)) { + if (rq->nr_phys_segments > queue_max_segments(q)) { printk(KERN_ERR "%s: over max segments limit.\n", __func__); return -EIO; } diff --git a/block/blk-merge.c b/block/blk-merge.c index 99cb5cf1f447..5e7dc9973458 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -206,8 +206,7 @@ static inline int ll_new_hw_segment(struct request_queue *q, { int nr_phys_segs = bio_phys_segments(q, bio); - if (req->nr_phys_segments + nr_phys_segs > queue_max_hw_segments(q) || - req->nr_phys_segments + nr_phys_segs > queue_max_phys_segments(q)) { + if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q)) { req->cmd_flags |= REQ_NOMERGE; if (req == q->last_merge) q->last_merge = NULL; @@ -300,10 +299,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, total_phys_segments--; } - if (total_phys_segments > queue_max_phys_segments(q)) - return 0; - - if (total_phys_segments > queue_max_hw_segments(q)) + if (total_phys_segments > queue_max_segments(q)) return 0; /* Merge is OK... */ diff --git a/block/blk-settings.c b/block/blk-settings.c index 61afae9dbc6d..31e7a9375c13 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -91,8 +91,7 @@ EXPORT_SYMBOL_GPL(blk_queue_lld_busy); */ void blk_set_default_limits(struct queue_limits *lim) { - lim->max_phys_segments = MAX_PHYS_SEGMENTS; - lim->max_hw_segments = MAX_HW_SEGMENTS; + lim->max_segments = BLK_MAX_SEGMENTS; lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; lim->max_sectors = BLK_DEF_MAX_SECTORS; @@ -252,17 +251,15 @@ void blk_queue_max_discard_sectors(struct request_queue *q, EXPORT_SYMBOL(blk_queue_max_discard_sectors); /** - * blk_queue_max_phys_segments - set max phys segments for a request for this queue + * blk_queue_max_segments - set max hw segments for a request for this queue * @q: the request queue for the device * @max_segments: max number of segments * * Description: * Enables a low level driver to set an upper limit on the number of - * physical data segments in a request. This would be the largest sized - * scatter list the driver could handle. + * hw data segments in a request. **/ -void blk_queue_max_phys_segments(struct request_queue *q, - unsigned short max_segments) +void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments) { if (!max_segments) { max_segments = 1; @@ -270,33 +267,9 @@ void blk_queue_max_phys_segments(struct request_queue *q, __func__, max_segments); } - q->limits.max_phys_segments = max_segments; + q->limits.max_segments = max_segments; } -EXPORT_SYMBOL(blk_queue_max_phys_segments); - -/** - * blk_queue_max_hw_segments - set max hw segments for a request for this queue - * @q: the request queue for the device - * @max_segments: max number of segments - * - * Description: - * Enables a low level driver to set an upper limit on the number of - * hw data segments in a request. This would be the largest number of - * address/length pairs the host adapter can actually give at once - * to the device. - **/ -void blk_queue_max_hw_segments(struct request_queue *q, - unsigned short max_segments) -{ - if (!max_segments) { - max_segments = 1; - printk(KERN_INFO "%s: set to minimum %d\n", - __func__, max_segments); - } - - q->limits.max_hw_segments = max_segments; -} -EXPORT_SYMBOL(blk_queue_max_hw_segments); +EXPORT_SYMBOL(blk_queue_max_segments); /** * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg @@ -531,11 +504,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask); - t->max_phys_segments = min_not_zero(t->max_phys_segments, - b->max_phys_segments); - - t->max_hw_segments = min_not_zero(t->max_hw_segments, - b->max_hw_segments); + t->max_segments = min_not_zero(t->max_segments, b->max_segments); t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size); @@ -739,22 +708,19 @@ EXPORT_SYMBOL(blk_queue_update_dma_pad); * does is adjust the queue so that the buf is always appended * silently to the scatterlist. * - * Note: This routine adjusts max_hw_segments to make room for - * appending the drain buffer. If you call - * blk_queue_max_hw_segments() or blk_queue_max_phys_segments() after - * calling this routine, you must set the limit to one fewer than your - * device can support otherwise there won't be room for the drain - * buffer. + * Note: This routine adjusts max_hw_segments to make room for appending + * the drain buffer. If you call blk_queue_max_segments() after calling + * this routine, you must set the limit to one fewer than your device + * can support otherwise there won't be room for the drain buffer. */ int blk_queue_dma_drain(struct request_queue *q, dma_drain_needed_fn *dma_drain_needed, void *buf, unsigned int size) { - if (queue_max_hw_segments(q) < 2 || queue_max_phys_segments(q) < 2) + if (queue_max_segments(q) < 2) return -EINVAL; /* make room for appending the drain */ - blk_queue_max_hw_segments(q, queue_max_hw_segments(q) - 1); - blk_queue_max_phys_segments(q, queue_max_phys_segments(q) - 1); + blk_queue_max_segments(q, queue_max_segments(q) - 1); q->dma_drain_needed = dma_drain_needed; q->dma_drain_buffer = buf; q->dma_drain_size = size; diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 0c82d335c55d..684fe04dbbb7 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -772,7 +772,7 @@ static int nv_adma_slave_config(struct scsi_device *sdev) } blk_queue_segment_boundary(sdev->request_queue, segment_boundary); - blk_queue_max_hw_segments(sdev->request_queue, sg_tablesize); + blk_queue_max_segments(sdev->request_queue, sg_tablesize); ata_port_printk(ap, KERN_INFO, "DMA mask 0x%llX, segment boundary 0x%lX, hw segs %hu\n", (unsigned long long)*ap->host->dev->dma_mask, diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index 1c0cd35e1913..459f1bc25a7b 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -2534,7 +2534,7 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller) blk_queue_bounce_limit(RequestQueue, Controller->BounceBufferLimit); RequestQueue->queuedata = Controller; blk_queue_max_hw_segments(RequestQueue, Controller->DriverScatterGatherLimit); - blk_queue_max_phys_segments(RequestQueue, Controller->DriverScatterGatherLimit); + blk_queue_max_segments(RequestQueue, Controller->DriverScatterGatherLimit); blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand); disk->queue = RequestQueue; sprintf(disk->disk_name, "rd/c%dd%d", Controller->ControllerNumber, n); diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 030e52d72254..a29e69418a03 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1797,10 +1797,7 @@ static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk, blk_queue_bounce_limit(disk->queue, h->pdev->dma_mask); /* This is a hardware imposed limit. */ - blk_queue_max_hw_segments(disk->queue, h->maxsgentries); - - /* This is a limit in the driver and could be eliminated. */ - blk_queue_max_phys_segments(disk->queue, h->maxsgentries); + blk_queue_max_segments(disk->queue, h->maxsgentries); blk_queue_max_hw_sectors(disk->queue, h->cciss_max_sectors); diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c index 6422651ec364..91d11631cec9 100644 --- a/drivers/block/cpqarray.c +++ b/drivers/block/cpqarray.c @@ -448,11 +448,8 @@ static int __init cpqarray_register_ctlr( int i, struct pci_dev *pdev) blk_queue_bounce_limit(q, hba[i]->pci_dev->dma_mask); /* This is a hardware imposed limit. */ - blk_queue_max_hw_segments(q, SG_MAX); + blk_queue_max_segments(q, SG_MAX); - /* This is a driver limit and could be eliminated. */ - blk_queue_max_phys_segments(q, SG_MAX); - init_timer(&hba[i]->timer); hba[i]->timer.expires = jiffies + IDA_TIMER; hba[i]->timer.data = (unsigned long)hba[i]; diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 9b55e64196fc..4df3b40b1057 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -710,8 +710,7 @@ void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_seg_s) __mu max_seg_s = min(queue_max_sectors(b) * queue_logical_block_size(b), max_seg_s); blk_queue_max_hw_sectors(q, max_seg_s >> 9); - blk_queue_max_phys_segments(q, max_segments ? max_segments : MAX_PHYS_SEGMENTS); - blk_queue_max_hw_segments(q, max_segments ? max_segments : MAX_HW_SEGMENTS); + blk_queue_max_segments(q, max_segments ? max_segments : BLK_MAX_SEGMENTS); blk_queue_max_segment_size(q, max_seg_s); blk_queue_logical_block_size(q, 512); blk_queue_segment_boundary(q, PAGE_SIZE-1); diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index ea54ea393553..ddb4f9abd480 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -956,8 +956,7 @@ static int __init pf_init(void) return -ENOMEM; } - blk_queue_max_phys_segments(pf_queue, cluster); - blk_queue_max_hw_segments(pf_queue, cluster); + blk_queue_max_segments(pf_queue, cluster); for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { struct gendisk *disk = pf->disk; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 6e1daa24da2f..b72935b8f203 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -950,14 +950,14 @@ 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_phys_segments(q)) { + <= 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_phys_segments(q)) { + <= queue_max_segments(q)) { /* * We can handle this case at the expense of some extra memory * copies during write operations diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 9cd1a4a542b8..bc95469d33c1 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -482,8 +482,7 @@ static int __devinit ps3disk_probe(struct ps3_system_bus_device *_dev) blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH, ps3disk_prepare_flush); - blk_queue_max_phys_segments(queue, -1); - blk_queue_max_hw_segments(queue, -1); + blk_queue_max_segments(queue, -1); blk_queue_max_segment_size(queue, dev->bounce_size); gendisk = alloc_disk(PS3DISK_MINORS); diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 6416b262934b..83ebb390b164 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -751,8 +751,7 @@ static int __devinit ps3vram_probe(struct ps3_system_bus_device *dev) priv->queue = queue; queue->queuedata = dev; blk_queue_make_request(queue, ps3vram_make_request); - blk_queue_max_phys_segments(queue, MAX_PHYS_SEGMENTS); - blk_queue_max_hw_segments(queue, MAX_HW_SEGMENTS); + blk_queue_max_segments(queue, BLK_MAX_HW_SEGMENTS); blk_queue_max_segment_size(queue, BLK_MAX_SEGMENT_SIZE); blk_queue_max_hw_sectors(queue, BLK_SAFE_MAX_SECTORS); diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index dd30cddd0f7f..48e8fee9f2d4 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -691,8 +691,7 @@ static int probe_disk(struct vdc_port *port) port->disk = g; - blk_queue_max_hw_segments(q, port->ring_cookies); - blk_queue_max_phys_segments(q, port->ring_cookies); + blk_queue_max_segments(q, port->ring_cookies); blk_queue_max_hw_sectors(q, port->max_xfer_size); g->major = vdc_major; g->first_minor = port->vio.vdev->dev_no << PARTITION_SHIFT; diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index 7bd7b2f83116..b70f0fca9a42 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -1518,8 +1518,7 @@ static int carm_init_disks(struct carm_host *host) break; } disk->queue = q; - blk_queue_max_hw_segments(q, CARM_MAX_REQ_SG); - blk_queue_max_phys_segments(q, CARM_MAX_REQ_SG); + blk_queue_max_segments(q, CARM_MAX_REQ_SG); blk_queue_segment_boundary(q, CARM_SG_BOUNDARY); q->queuedata = port; diff --git a/drivers/block/ub.c b/drivers/block/ub.c index 352ea24d66e8..2e889838e819 100644 --- a/drivers/block/ub.c +++ b/drivers/block/ub.c @@ -2320,8 +2320,7 @@ static int ub_probe_lun(struct ub_dev *sc, int lnum) disk->queue = q; blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH); - blk_queue_max_hw_segments(q, UB_MAX_REQ_SG); - blk_queue_max_phys_segments(q, UB_MAX_REQ_SG); + blk_queue_max_segments(q, UB_MAX_REQ_SG); blk_queue_segment_boundary(q, 0xffffffff); /* Dubious. */ blk_queue_max_hw_sectors(q, UB_MAX_SECTORS); blk_queue_logical_block_size(q, lun->capacity.bsize); diff --git a/drivers/block/viodasd.c b/drivers/block/viodasd.c index d44ece7d7b7c..c12b31362ac6 100644 --- a/drivers/block/viodasd.c +++ b/drivers/block/viodasd.c @@ -471,8 +471,7 @@ retry: } d->disk = g; - blk_queue_max_hw_segments(q, VIOMAXBLOCKDMA); - blk_queue_max_phys_segments(q, VIOMAXBLOCKDMA); + blk_queue_max_segments(q, VIOMAXBLOCKDMA); blk_queue_max_hw_sectors(q, VIODASD_MAXSECTORS); g->major = VIODASD_MAJOR; g->first_minor = dev_no << PARTITION_SHIFT; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index f9861aaa1fef..9c09694b2520 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -353,8 +353,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size) blk_queue_max_segment_size(rq, PAGE_SIZE); /* Ensure a merged request will fit in a single I/O ring slot. */ - blk_queue_max_phys_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST); - blk_queue_max_hw_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST); + blk_queue_max_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST); /* Make sure buffer addresses are sector-aligned. */ blk_queue_dma_alignment(rq, 511); diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index e789e6c9a422..03c71f7698cb 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -741,7 +741,7 @@ static int __devinit probe_gdrom_setupqueue(void) { blk_queue_logical_block_size(gd.gdrom_rq, GDROM_HARD_SECTOR); /* using DMA so memory will need to be contiguous */ - blk_queue_max_hw_segments(gd.gdrom_rq, 1); + blk_queue_max_segments(gd.gdrom_rq, 1); /* set a large max size to get most from DMA */ blk_queue_max_segment_size(gd.gdrom_rq, 0x40000); gd.disk->queue = gd.gdrom_rq; diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c index b1dfd23eb832..cc435be0bc13 100644 --- a/drivers/cdrom/viocd.c +++ b/drivers/cdrom/viocd.c @@ -616,8 +616,7 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id) gendisk->first_minor = deviceno; strncpy(gendisk->disk_name, c->name, sizeof(gendisk->disk_name)); - blk_queue_max_hw_segments(q, 1); - blk_queue_max_phys_segments(q, 1); + blk_queue_max_segments(q, 1); blk_queue_max_hw_sectors(q, 4096 / 512); gendisk->queue = q; gendisk->fops = &viocd_fops; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 1ec8b31277bd..f8c1ae6ad74c 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -790,8 +790,7 @@ static int ide_init_queue(ide_drive_t *drive) max_sg_entries >>= 1; #endif /* CONFIG_PCI */ - blk_queue_max_hw_segments(q, max_sg_entries); - blk_queue_max_phys_segments(q, max_sg_entries); + blk_queue_max_segments(q, max_sg_entries); /* assign drive queue */ drive->queue = q; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ceb24afdc147..509c8f3dd9a5 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3739,7 +3739,7 @@ static int bio_fits_rdev(struct bio *bi) if ((bi->bi_size>>9) > queue_max_sectors(q)) return 0; blk_recount_segments(q, bi); - if (bi->bi_phys_segments > queue_max_phys_segments(q)) + if (bi->bi_phys_segments > queue_max_segments(q)) return 0; if (q->merge_bvec_fn) diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index 44d4178c4c15..972b87069d55 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -1227,8 +1227,7 @@ static int mspro_block_init_disk(struct memstick_dev *card) blk_queue_bounce_limit(msb->queue, limit); blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES); - blk_queue_max_phys_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS); - blk_queue_max_hw_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS); + blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS); blk_queue_max_segment_size(msb->queue, MSPRO_BLOCK_MAX_PAGES * msb->page_size); diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c index d033cfdb516f..2658b1484a2c 100644 --- a/drivers/message/i2o/i2o_block.c +++ b/drivers/message/i2o/i2o_block.c @@ -1065,9 +1065,8 @@ static int i2o_block_probe(struct device *dev) queue = gd->queue; queue->queuedata = i2o_blk_dev; - blk_queue_max_phys_segments(queue, I2O_MAX_PHYS_SEGMENTS); blk_queue_max_hw_sectors(queue, max_sectors); - blk_queue_max_hw_segments(queue, i2o_sg_tablesize(c, body_size)); + blk_queue_max_segments(queue, i2o_sg_tablesize(c, body_size)); osm_debug("max sectors = %d\n", queue->max_sectors); osm_debug("phys segments = %d\n", queue->max_phys_segments); diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 09b633d5657b..381fe032caa1 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -155,8 +155,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock if (mq->bounce_buf) { blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY); blk_queue_max_hw_sectors(mq->queue, bouncesz / 512); - blk_queue_max_phys_segments(mq->queue, bouncesz / 512); - blk_queue_max_hw_segments(mq->queue, bouncesz / 512); + blk_queue_max_segments(mq->queue, bouncesz / 512); blk_queue_max_segment_size(mq->queue, bouncesz); mq->sg = kmalloc(sizeof(struct scatterlist), @@ -182,8 +181,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock blk_queue_bounce_limit(mq->queue, limit); blk_queue_max_hw_sectors(mq->queue, min(host->max_blk_count, host->max_req_size / 512)); - blk_queue_max_phys_segments(mq->queue, host->max_phys_segs); - blk_queue_max_hw_segments(mq->queue, host->max_hw_segs); + blk_queue_max_segments(mq->queue, host->max_hw_segs); blk_queue_max_segment_size(mq->queue, host->max_seg_size); mq->sg = kmalloc(sizeof(struct scatterlist) * diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 14b1e25b9dcf..8831e9308d05 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2130,8 +2130,7 @@ static void dasd_setup_queue(struct dasd_block *block) blk_queue_logical_block_size(block->request_queue, block->bp_block); max = block->base->discipline->max_blocks << block->s2b_shift; blk_queue_max_hw_sectors(block->request_queue, max); - blk_queue_max_phys_segments(block->request_queue, -1L); - blk_queue_max_hw_segments(block->request_queue, -1L); + blk_queue_max_segments(block->request_queue, -1L); /* with page sized segments we can translate each segement into * one idaw/tidaw */ diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c index 509ed056fddd..097da8ce6be6 100644 --- a/drivers/s390/char/tape_block.c +++ b/drivers/s390/char/tape_block.c @@ -223,8 +223,7 @@ tapeblock_setup_device(struct tape_device * device) blk_queue_logical_block_size(blkdat->request_queue, TAPEBLOCK_HSEC_SIZE); blk_queue_max_hw_sectors(blkdat->request_queue, TAPEBLOCK_MAX_SEC); - blk_queue_max_phys_segments(blkdat->request_queue, -1L); - blk_queue_max_hw_segments(blkdat->request_queue, -1L); + blk_queue_max_segments(blkdat->request_queue, -1L); blk_queue_max_segment_size(blkdat->request_queue, -1L); blk_queue_segment_boundary(blkdat->request_queue, -1L); diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 87b536a97cb4..732f6d35b4a8 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -4195,7 +4195,7 @@ static void ibmvfc_tgt_add_rport(struct ibmvfc_target *tgt) if (tgt->service_parms.class3_parms[0] & 0x80000000) rport->supported_classes |= FC_COS_CLASS3; if (rport->rqst_q) - blk_queue_max_hw_segments(rport->rqst_q, 1); + blk_queue_max_segments(rport->rqst_q, 1); } else tgt_dbg(tgt, "rport add failed\n"); spin_unlock_irqrestore(vhost->host->host_lock, flags); @@ -4669,7 +4669,7 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id) } if (shost_to_fc_host(shost)->rqst_q) - blk_queue_max_hw_segments(shost_to_fc_host(shost)->rqst_q, 1); + blk_queue_max_segments(shost_to_fc_host(shost)->rqst_q, 1); dev_set_drvdata(dev, vhost); spin_lock(&ibmvfc_driver_lock); list_add_tail(&vhost->queue, &ibmvfc_head); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index ac3cca74bdfb..f8fbf47377ae 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1624,8 +1624,8 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, /* * this limit is imposed by hardware restrictions */ - blk_queue_max_hw_segments(q, shost->sg_tablesize); - blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS); + blk_queue_max_segments(q, min_t(unsigned short, shost->sg_tablesize, + SCSI_MAX_SG_CHAIN_SEGMENTS)); blk_queue_max_hw_sectors(q, shost->max_sectors); blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost)); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 040f751809ea..c996d98636f3 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -287,8 +287,7 @@ sg_open(struct inode *inode, struct file *filp) if (list_empty(&sdp->sfds)) { /* no existing opens on this device */ sdp->sgdebug = 0; q = sdp->device->request_queue; - sdp->sg_tablesize = min(queue_max_hw_segments(q), - queue_max_phys_segments(q)); + sdp->sg_tablesize = queue_max_segments(q); } if ((sfp = sg_add_sfp(sdp, dev))) filp->private_data = sfp; @@ -1376,8 +1375,7 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp) sdp->device = scsidp; INIT_LIST_HEAD(&sdp->sfds); init_waitqueue_head(&sdp->o_excl_wait); - sdp->sg_tablesize = min(queue_max_hw_segments(q), - queue_max_phys_segments(q)); + sdp->sg_tablesize = queue_max_segments(q); sdp->index = k; kref_init(&sdp->d_ref); diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index d04ea9a6f673..f67d1a159aad 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -3983,8 +3983,7 @@ static int st_probe(struct device *dev) return -ENODEV; } - i = min(queue_max_hw_segments(SDp->request_queue), - queue_max_phys_segments(SDp->request_queue)); + i = queue_max_segments(SDp->request_queue); if (st_max_sg_segs < i) i = st_max_sg_segs; buffer = new_tape_buffer((SDp->host)->unchecked_isa_dma, i); diff --git a/drivers/staging/hv/blkvsc_drv.c b/drivers/staging/hv/blkvsc_drv.c index 62b282844a53..45d908114d11 100644 --- a/drivers/staging/hv/blkvsc_drv.c +++ b/drivers/staging/hv/blkvsc_drv.c @@ -363,10 +363,7 @@ static int blkvsc_probe(struct device *device) blkdev->gd->queue = blk_init_queue(blkvsc_request, &blkdev->lock); blk_queue_max_segment_size(blkdev->gd->queue, PAGE_SIZE); - blk_queue_max_phys_segments(blkdev->gd->queue, - MAX_MULTIPAGE_BUFFER_COUNT); - blk_queue_max_hw_segments(blkdev->gd->queue, - MAX_MULTIPAGE_BUFFER_COUNT); + blk_queue_max_segments(blkdev->gd->queue, MAX_MULTIPAGE_BUFFER_COUNT); blk_queue_segment_boundary(blkdev->gd->queue, PAGE_SIZE-1); blk_queue_bounce_limit(blkdev->gd->queue, BLK_BOUNCE_ANY); blk_queue_dma_alignment(blkdev->gd->queue, 511); diff --git a/fs/bio.c b/fs/bio.c index 88094afc29ea..dc17afd672e3 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -507,10 +507,8 @@ int bio_get_nr_vecs(struct block_device *bdev) int nr_pages; nr_pages = ((queue_max_sectors(q) << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (nr_pages > queue_max_phys_segments(q)) - nr_pages = queue_max_phys_segments(q); - if (nr_pages > queue_max_hw_segments(q)) - nr_pages = queue_max_hw_segments(q); + if (nr_pages > queue_max_segments(q)) + nr_pages = queue_max_segments(q); return nr_pages; } @@ -575,8 +573,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page * make this too complex. */ - while (bio->bi_phys_segments >= queue_max_phys_segments(q) - || bio->bi_phys_segments >= queue_max_hw_segments(q)) { + while (bio->bi_phys_segments >= queue_max_segments(q)) { if (retried_segments) return 0; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 57bc48446e92..ebd22dbed861 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -316,8 +316,7 @@ struct queue_limits { unsigned int discard_alignment; unsigned short logical_block_size; - unsigned short max_hw_segments; - unsigned short max_phys_segments; + unsigned short max_segments; unsigned char misaligned; unsigned char discard_misaligned; @@ -929,8 +928,19 @@ static inline void blk_queue_max_sectors(struct request_queue *q, unsigned int m blk_queue_max_hw_sectors(q, max); } -extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); -extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); +extern void blk_queue_max_segments(struct request_queue *, unsigned short); + +static inline void blk_queue_max_phys_segments(struct request_queue *q, unsigned short max) +{ + blk_queue_max_segments(q, max); +} + +static inline void blk_queue_max_hw_segments(struct request_queue *q, unsigned short max) +{ + blk_queue_max_segments(q, max); +} + + extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1055,14 +1065,9 @@ static inline unsigned int queue_max_hw_sectors(struct request_queue *q) return q->limits.max_hw_sectors; } -static inline unsigned short queue_max_hw_segments(struct request_queue *q) -{ - return q->limits.max_hw_segments; -} - -static inline unsigned short queue_max_phys_segments(struct request_queue *q) +static inline unsigned short queue_max_segments(struct request_queue *q) { - return q->limits.max_phys_segments; + return q->limits.max_segments; } static inline unsigned int queue_max_segment_size(struct request_queue *q) diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 4c4e57d1f19d..87018dc5527d 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -385,7 +385,7 @@ /* defines for max_sectors and max_phys_segments */ #define I2O_MAX_SECTORS 1024 #define I2O_MAX_SECTORS_LIMITED 128 -#define I2O_MAX_PHYS_SEGMENTS MAX_PHYS_SEGMENTS +#define I2O_MAX_PHYS_SEGMENTS BLK_MAX_SEGMENTS /* * Message structures -- cgit v1.2.3 From ee714f2dd33e726346e34f5cda12543162f4753e Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 10 Mar 2010 00:48:32 -0500 Subject: block: Finalize conversion of block limits functions Remove compatibility wrappers and update remaining drivers. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- drivers/block/DAC960.c | 1 - drivers/block/virtio_blk.c | 5 ++--- include/linux/blkdev.h | 24 ------------------------ 3 files changed, 2 insertions(+), 28 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index 459f1bc25a7b..c5f22bb0a48e 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -2533,7 +2533,6 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller) Controller->RequestQueue[n] = RequestQueue; blk_queue_bounce_limit(RequestQueue, Controller->BounceBufferLimit); RequestQueue->queuedata = Controller; - blk_queue_max_hw_segments(RequestQueue, Controller->DriverScatterGatherLimit); blk_queue_max_segments(RequestQueue, Controller->DriverScatterGatherLimit); blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand); disk->queue = RequestQueue; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 3c64af05fa82..653817ceeedd 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -347,14 +347,13 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) set_capacity(vblk->disk, cap); /* We can handle whatever the host told us to handle. */ - blk_queue_max_phys_segments(q, vblk->sg_elems-2); - blk_queue_max_hw_segments(q, vblk->sg_elems-2); + blk_queue_max_segments(q, vblk->sg_elems-2); /* No need to bounce any requests */ blk_queue_bounce_limit(q, BLK_BOUNCE_ANY); /* No real sector limit. */ - blk_queue_max_sectors(q, -1U); + blk_queue_max_hw_sectors(q, -1U); /* Host can optionally specify maximum segment size and number of * segments. */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ebd22dbed861..41551c9341b6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -921,26 +921,7 @@ extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); - -/* Temporary compatibility wrapper */ -static inline void blk_queue_max_sectors(struct request_queue *q, unsigned int max) -{ - blk_queue_max_hw_sectors(q, max); -} - extern void blk_queue_max_segments(struct request_queue *, unsigned short); - -static inline void blk_queue_max_phys_segments(struct request_queue *q, unsigned short max) -{ - blk_queue_max_segments(q, max); -} - -static inline void blk_queue_max_hw_segments(struct request_queue *q, unsigned short max) -{ - blk_queue_max_segments(q, max); -} - - extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1030,11 +1011,6 @@ static inline int sb_issue_discard(struct super_block *sb, extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); -#define MAX_PHYS_SEGMENTS 128 -#define MAX_HW_SEGMENTS 128 -#define SAFE_MAX_SECTORS 255 -#define MAX_SEGMENT_SIZE 65536 - enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, -- cgit v1.2.3 From 181fdde3b4268cb7b4af76ba6337e7ec8accbb36 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Fri, 19 Mar 2010 08:58:16 +0100 Subject: block: remove 16 bytes of padding from struct request on 64bits Remove alignment padding to shrink struct request from 336 to 320 bytes so needing one fewer cacheline and therefore removing 48 bytes from struct request_queue. Signed-off-by: Richard Kennedy Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 41551c9341b6..6690e8bae7bb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -158,7 +158,6 @@ enum rq_flag_bits { struct request { struct list_head queuelist; struct call_single_data csd; - int cpu; struct request_queue *q; @@ -166,9 +165,11 @@ struct request { enum rq_cmd_type_bits cmd_type; unsigned long atomic_flags; + int cpu; + /* the following two fields are internal, NEVER access directly */ - sector_t __sector; /* sector cursor */ unsigned int __data_len; /* total data len */ + sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; @@ -201,20 +202,20 @@ struct request { unsigned short ioprio; + int ref_count; + void *special; /* opaque pointer available for LLD use */ char *buffer; /* kaddr of the current segment if available */ int tag; int errors; - int ref_count; - /* * when request is used as a packet command carrier */ - unsigned short cmd_len; unsigned char __cmd[BLK_MAX_CDB]; unsigned char *cmd; + unsigned short cmd_len; unsigned int extra_len; /* length of alignment and padding */ unsigned int sense_len; -- cgit v1.2.3 From 9195291e5f05e01d67f9a09c756b8aca8f009089 Mon Sep 17 00:00:00 2001 From: Divyesh Shah Date: Thu, 1 Apr 2010 15:01:41 -0700 Subject: blkio: Increment the blkio cgroup stats for real now We also add start_time_ns and io_start_time_ns fields to struct request here to record the time when a request is created and when it is dispatched to device. We use ns uints here as ms and jiffies are not very useful for non-rotational media. Signed-off-by: Divyesh Shah Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++-- block/blk-cgroup.h | 14 +++++++++--- block/blk-core.c | 6 +++-- block/cfq-iosched.c | 4 +++- include/linux/blkdev.h | 20 ++++++++++++++++- 5 files changed, 95 insertions(+), 9 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index ad6843f2e0ab..9af7257f429c 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "blk-cgroup.h" static DEFINE_SPINLOCK(blkio_list_lock); @@ -55,6 +56,26 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup) } EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup); +/* + * Add to the appropriate stat variable depending on the request type. + * This should be called with the blkg->stats_lock held. + */ +void io_add_stat(uint64_t *stat, uint64_t add, unsigned int flags) +{ + if (flags & REQ_RW) + stat[IO_WRITE] += add; + else + stat[IO_READ] += add; + /* + * Everywhere in the block layer, an IO is treated as sync if it is a + * read or a SYNC write. We follow the same norm. + */ + if (!(flags & REQ_RW) || flags & REQ_RW_SYNC) + stat[IO_SYNC] += add; + else + stat[IO_ASYNC] += add; +} + void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) { unsigned long flags; @@ -65,6 +86,41 @@ void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) } EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used); +void blkiocg_update_request_dispatch_stats(struct blkio_group *blkg, + struct request *rq) +{ + struct blkio_group_stats *stats; + unsigned long flags; + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + stats->sectors += blk_rq_sectors(rq); + io_add_stat(stats->io_serviced, 1, rq->cmd_flags); + io_add_stat(stats->io_service_bytes, blk_rq_sectors(rq) << 9, + rq->cmd_flags); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} + +void blkiocg_update_request_completion_stats(struct blkio_group *blkg, + struct request *rq) +{ + struct blkio_group_stats *stats; + unsigned long flags; + unsigned long long now = sched_clock(); + + spin_lock_irqsave(&blkg->stats_lock, flags); + stats = &blkg->stats; + if (time_after64(now, rq->io_start_time_ns)) + io_add_stat(stats->io_service_time, now - rq->io_start_time_ns, + rq->cmd_flags); + if (time_after64(rq->io_start_time_ns, rq->start_time_ns)) + io_add_stat(stats->io_wait_time, + rq->io_start_time_ns - rq->start_time_ns, + rq->cmd_flags); + spin_unlock_irqrestore(&blkg->stats_lock, flags); +} +EXPORT_SYMBOL_GPL(blkiocg_update_request_completion_stats); + void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, struct blkio_group *blkg, void *key, dev_t dev) { @@ -325,12 +381,12 @@ SHOW_FUNCTION_PER_GROUP(dequeue, get_stat, get_dequeue_stat, 0); #undef SHOW_FUNCTION_PER_GROUP #ifdef CONFIG_DEBUG_BLK_CGROUP -void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, +void blkiocg_update_dequeue_stats(struct blkio_group *blkg, unsigned long dequeue) { blkg->stats.dequeue += dequeue; } -EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_dequeue_stats); +EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats); #endif struct cftype blkio_files[] = { diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 5c5e5294b506..80010ef64ab0 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -112,12 +112,12 @@ static inline char *blkg_path(struct blkio_group *blkg) { return blkg->path; } -void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg, +void blkiocg_update_dequeue_stats(struct blkio_group *blkg, unsigned long dequeue); #else static inline char *blkg_path(struct blkio_group *blkg) { return NULL; } -static inline void blkiocg_update_blkio_group_dequeue_stats( - struct blkio_group *blkg, unsigned long dequeue) {} +static inline void blkiocg_update_dequeue_stats(struct blkio_group *blkg, + unsigned long dequeue) {} #endif #if defined(CONFIG_BLK_CGROUP) || defined(CONFIG_BLK_CGROUP_MODULE) @@ -130,6 +130,10 @@ extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key); void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time); +void blkiocg_update_request_dispatch_stats(struct blkio_group *blkg, + struct request *rq); +void blkiocg_update_request_completion_stats(struct blkio_group *blkg, + struct request *rq); #else struct cgroup; static inline struct blkio_cgroup * @@ -147,5 +151,9 @@ static inline struct blkio_group * blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; } static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) {} +static inline void blkiocg_update_request_dispatch_stats( + struct blkio_group *blkg, struct request *rq) {} +static inline void blkiocg_update_request_completion_stats( + struct blkio_group *blkg, struct request *rq) {} #endif #endif /* _BLK_CGROUP_H */ diff --git a/block/blk-core.c b/block/blk-core.c index 9fe174dc74d1..1d94f15d7f0d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -127,6 +127,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq) rq->tag = -1; rq->ref_count = 1; rq->start_time = jiffies; + set_start_time_ns(rq); } EXPORT_SYMBOL(blk_rq_init); @@ -1855,8 +1856,10 @@ void blk_dequeue_request(struct request *rq) * and to it is freed is accounted as io that is in progress at * the driver side. */ - if (blk_account_rq(rq)) + if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]++; + set_io_start_time_ns(rq); + } } /** @@ -2517,4 +2520,3 @@ int __init blk_dev_init(void) return 0; } - diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index c5161bbf2fe9..42028e7128a7 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -855,7 +855,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg) if (!RB_EMPTY_NODE(&cfqg->rb_node)) cfq_rb_erase(&cfqg->rb_node, st); cfqg->saved_workload_slice = 0; - blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1); + blkiocg_update_dequeue_stats(&cfqg->blkg, 1); } static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq) @@ -1865,6 +1865,7 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) elv_dispatch_sort(q, rq); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++; + blkiocg_update_request_dispatch_stats(&cfqq->cfqg->blkg, rq); } /* @@ -3285,6 +3286,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) WARN_ON(!cfqq->dispatched); cfqd->rq_in_driver--; cfqq->dispatched--; + blkiocg_update_request_completion_stats(&cfqq->cfqg->blkg, rq); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6690e8bae7bb..f3fff8bf85ee 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -194,7 +194,10 @@ struct request { struct gendisk *rq_disk; unsigned long start_time; - +#ifdef CONFIG_BLK_CGROUP + unsigned long long start_time_ns; + unsigned long long io_start_time_ns; /* when passed to hardware */ +#endif /* Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ @@ -1196,6 +1199,21 @@ static inline void put_dev_sector(Sector p) struct work_struct; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +#ifdef CONFIG_BLK_CGROUP +static inline void set_start_time_ns(struct request *req) +{ + req->start_time_ns = sched_clock(); +} + +static inline void set_io_start_time_ns(struct request *req) +{ + req->io_start_time_ns = sched_clock(); +} +#else +static inline void set_start_time_ns(struct request *req) {} +static inline void set_io_start_time_ns(struct request *req) {} +#endif + #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ -- cgit v1.2.3 From 84c124da9ff50bd71fab9c939ee5b7cd8bef2bd9 Mon Sep 17 00:00:00 2001 From: Divyesh Shah Date: Fri, 9 Apr 2010 08:31:19 +0200 Subject: blkio: Changes to IO controller additional stats patches that include some minor fixes and addresses all comments. Changelog: (most based on Vivek Goyal's comments) o renamed blkiocg_reset_write to blkiocg_reset_stats o more clarification in the documentation on io_service_time and io_wait_time o Initialize blkg->stats_lock o rename io_add_stat to blkio_add_stat and declare it static o use bool for direction and sync o derive direction and sync info from existing rq methods o use 12 for major:minor string length o define io_service_time better to cover the NCQ case o add a separate reset_stats interface o make the indexed stats a 2d array to simplify macro and function pointer code o blkio.time now exports in jiffies as before o Added stats description in patch description and Documentation/cgroup/blkio-controller.txt o Prefix all stats functions with blkio and make them static as applicable o replace IO_TYPE_MAX with IO_TYPE_TOTAL o Moved #define constant to top of blk-cgroup.c o Pass dev_t around instead of char * o Add note to documentation file about resetting stats o use BLK_CGROUP_MODULE in addition to BLK_CGROUP config option in #ifdef statements o Avoid struct request specific knowledge in blk-cgroup. blk-cgroup.h now has rq_direction() and rq_sync() functions which are used by CFQ and when using io-controller at a higher level, bio_* functions can be added. Signed-off-by: Divyesh Shah Signed-off-by: Jens Axboe --- Documentation/cgroups/blkio-controller.txt | 48 +++++++- block/blk-cgroup.c | 190 +++++++++++++---------------- block/blk-cgroup.h | 64 ++++++---- block/cfq-iosched.c | 8 +- include/linux/blkdev.h | 18 +++ 5 files changed, 198 insertions(+), 130 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index 630879cd9a42..ed04fe9cce1a 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -77,7 +77,6 @@ Details of cgroup files ======================= - blkio.weight - Specifies per cgroup weight. - Currently allowed range of weights is from 100 to 1000. - blkio.time @@ -92,6 +91,49 @@ Details of cgroup files third field specifies the number of sectors transferred by the group to/from the device. +- blkio.io_service_bytes + - Number of bytes transferred to/from the disk by the group. These + are further divided by the type of operation - read or write, sync + or async. First two fields specify the major and minor number of the + device, third field specifies the operation type and the fourth field + specifies the number of bytes. + +- blkio.io_serviced + - Number of IOs completed to/from the disk by the group. These + are further divided by the type of operation - read or write, sync + or async. First two fields specify the major and minor number of the + device, third field specifies the operation type and the fourth field + specifies the number of IOs. + +- blkio.io_service_time + - Total amount of time between request dispatch and request completion + for the IOs done by this cgroup. This is in nanoseconds to make it + meaningful for flash devices too. For devices with queue depth of 1, + this time represents the actual service time. When queue_depth > 1, + that is no longer true as requests may be served out of order. This + may cause the service time for a given IO to include the service time + of multiple IOs when served out of order which may result in total + io_service_time > actual time elapsed. This time is further divided by + the type of operation - read or write, sync or async. First two fields + specify the major and minor number of the device, third field + specifies the operation type and the fourth field specifies the + io_service_time in ns. + +- blkio.io_wait_time + - Total amount of time the IOs for this cgroup spent waiting in the + scheduler queues for service. This can be greater than the total time + elapsed since it is cumulative io_wait_time for all IOs. It is not a + measure of total time the cgroup spent waiting but rather a measure of + the wait_time for its individual IOs. For devices with queue_depth > 1 + this metric does not include the time spent waiting for service once + the IO is dispatched to the device but till it actually gets serviced + (there might be a time lag here due to re-ordering of requests by the + device). This is in nanoseconds to make it meaningful for flash + devices too. This time is further divided by the type of operation - + read or write, sync or async. First two fields specify the major and + minor number of the device, third field specifies the operation type + and the fourth field specifies the io_wait_time in ns. + - blkio.dequeue - Debugging aid only enabled if CONFIG_DEBUG_CFQ_IOSCHED=y. This gives the statistics about how many a times a group was dequeued @@ -99,6 +141,10 @@ Details of cgroup files and minor number of the device and third field specifies the number of times a group was dequeued from a particular device. +- blkio.reset_stats + - Writing an int to this file will result in resetting all the stats + for that cgroup. + CFQ sysfs tunable ================= /sys/block//queue/iosched/group_isolation diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 9af7257f429c..6797df508821 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -18,6 +18,8 @@ #include #include "blk-cgroup.h" +#define MAX_KEY_LEN 100 + static DEFINE_SPINLOCK(blkio_list_lock); static LIST_HEAD(blkio_list); @@ -56,24 +58,27 @@ struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup) } EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup); +void blkio_group_init(struct blkio_group *blkg) +{ + spin_lock_init(&blkg->stats_lock); +} +EXPORT_SYMBOL_GPL(blkio_group_init); + /* * Add to the appropriate stat variable depending on the request type. * This should be called with the blkg->stats_lock held. */ -void io_add_stat(uint64_t *stat, uint64_t add, unsigned int flags) +static void blkio_add_stat(uint64_t *stat, uint64_t add, bool direction, + bool sync) { - if (flags & REQ_RW) - stat[IO_WRITE] += add; + if (direction) + stat[BLKIO_STAT_WRITE] += add; else - stat[IO_READ] += add; - /* - * Everywhere in the block layer, an IO is treated as sync if it is a - * read or a SYNC write. We follow the same norm. - */ - if (!(flags & REQ_RW) || flags & REQ_RW_SYNC) - stat[IO_SYNC] += add; + stat[BLKIO_STAT_READ] += add; + if (sync) + stat[BLKIO_STAT_SYNC] += add; else - stat[IO_ASYNC] += add; + stat[BLKIO_STAT_ASYNC] += add; } void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) @@ -86,23 +91,25 @@ void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) } EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used); -void blkiocg_update_request_dispatch_stats(struct blkio_group *blkg, - struct request *rq) +void blkiocg_update_dispatch_stats(struct blkio_group *blkg, + uint64_t bytes, bool direction, bool sync) { struct blkio_group_stats *stats; unsigned long flags; spin_lock_irqsave(&blkg->stats_lock, flags); stats = &blkg->stats; - stats->sectors += blk_rq_sectors(rq); - io_add_stat(stats->io_serviced, 1, rq->cmd_flags); - io_add_stat(stats->io_service_bytes, blk_rq_sectors(rq) << 9, - rq->cmd_flags); + stats->sectors += bytes >> 9; + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICED], 1, direction, + sync); + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_BYTES], bytes, + direction, sync); spin_unlock_irqrestore(&blkg->stats_lock, flags); } +EXPORT_SYMBOL_GPL(blkiocg_update_dispatch_stats); -void blkiocg_update_request_completion_stats(struct blkio_group *blkg, - struct request *rq) +void blkiocg_update_completion_stats(struct blkio_group *blkg, + uint64_t start_time, uint64_t io_start_time, bool direction, bool sync) { struct blkio_group_stats *stats; unsigned long flags; @@ -110,16 +117,15 @@ void blkiocg_update_request_completion_stats(struct blkio_group *blkg, spin_lock_irqsave(&blkg->stats_lock, flags); stats = &blkg->stats; - if (time_after64(now, rq->io_start_time_ns)) - io_add_stat(stats->io_service_time, now - rq->io_start_time_ns, - rq->cmd_flags); - if (time_after64(rq->io_start_time_ns, rq->start_time_ns)) - io_add_stat(stats->io_wait_time, - rq->io_start_time_ns - rq->start_time_ns, - rq->cmd_flags); + if (time_after64(now, io_start_time)) + blkio_add_stat(stats->stat_arr[BLKIO_STAT_SERVICE_TIME], + now - io_start_time, direction, sync); + if (time_after64(io_start_time, start_time)) + blkio_add_stat(stats->stat_arr[BLKIO_STAT_WAIT_TIME], + io_start_time - start_time, direction, sync); spin_unlock_irqrestore(&blkg->stats_lock, flags); } -EXPORT_SYMBOL_GPL(blkiocg_update_request_completion_stats); +EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats); void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, struct blkio_group *blkg, void *key, dev_t dev) @@ -230,7 +236,7 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) } static int -blkiocg_reset_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) +blkiocg_reset_stats(struct cgroup *cgroup, struct cftype *cftype, u64 val) { struct blkio_cgroup *blkcg; struct blkio_group *blkg; @@ -249,29 +255,32 @@ blkiocg_reset_write(struct cgroup *cgroup, struct cftype *cftype, u64 val) return 0; } -void get_key_name(int type, char *disk_id, char *str, int chars_left) +static void blkio_get_key_name(enum stat_sub_type type, dev_t dev, char *str, + int chars_left, bool diskname_only) { - strlcpy(str, disk_id, chars_left); + snprintf(str, chars_left, "%d:%d", MAJOR(dev), MINOR(dev)); chars_left -= strlen(str); if (chars_left <= 0) { printk(KERN_WARNING "Possibly incorrect cgroup stat display format"); return; } + if (diskname_only) + return; switch (type) { - case IO_READ: + case BLKIO_STAT_READ: strlcat(str, " Read", chars_left); break; - case IO_WRITE: + case BLKIO_STAT_WRITE: strlcat(str, " Write", chars_left); break; - case IO_SYNC: + case BLKIO_STAT_SYNC: strlcat(str, " Sync", chars_left); break; - case IO_ASYNC: + case BLKIO_STAT_ASYNC: strlcat(str, " Async", chars_left); break; - case IO_TYPE_MAX: + case BLKIO_STAT_TOTAL: strlcat(str, " Total", chars_left); break; default: @@ -279,63 +288,47 @@ void get_key_name(int type, char *disk_id, char *str, int chars_left) } } -typedef uint64_t (get_var) (struct blkio_group *, int); +static uint64_t blkio_fill_stat(char *str, int chars_left, uint64_t val, + struct cgroup_map_cb *cb, dev_t dev) +{ + blkio_get_key_name(0, dev, str, chars_left, true); + cb->fill(cb, str, val); + return val; +} -#define MAX_KEY_LEN 100 -uint64_t get_typed_stat(struct blkio_group *blkg, struct cgroup_map_cb *cb, - get_var *getvar, char *disk_id) +/* This should be called with blkg->stats_lock held */ +static uint64_t blkio_get_stat(struct blkio_group *blkg, + struct cgroup_map_cb *cb, dev_t dev, enum stat_type type) { uint64_t disk_total; char key_str[MAX_KEY_LEN]; - int type; + enum stat_sub_type sub_type; + + if (type == BLKIO_STAT_TIME) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.time, cb, dev); + if (type == BLKIO_STAT_SECTORS) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.sectors, cb, dev); +#ifdef CONFIG_DEBUG_BLK_CGROUP + if (type == BLKIO_STAT_DEQUEUE) + return blkio_fill_stat(key_str, MAX_KEY_LEN - 1, + blkg->stats.dequeue, cb, dev); +#endif - for (type = 0; type < IO_TYPE_MAX; type++) { - get_key_name(type, disk_id, key_str, MAX_KEY_LEN); - cb->fill(cb, key_str, getvar(blkg, type)); + for (sub_type = BLKIO_STAT_READ; sub_type < BLKIO_STAT_TOTAL; + sub_type++) { + blkio_get_key_name(sub_type, dev, key_str, MAX_KEY_LEN, false); + cb->fill(cb, key_str, blkg->stats.stat_arr[type][sub_type]); } - disk_total = getvar(blkg, IO_READ) + getvar(blkg, IO_WRITE); - get_key_name(IO_TYPE_MAX, disk_id, key_str, MAX_KEY_LEN); + disk_total = blkg->stats.stat_arr[type][BLKIO_STAT_READ] + + blkg->stats.stat_arr[type][BLKIO_STAT_WRITE]; + blkio_get_key_name(BLKIO_STAT_TOTAL, dev, key_str, MAX_KEY_LEN, false); cb->fill(cb, key_str, disk_total); return disk_total; } -uint64_t get_stat(struct blkio_group *blkg, struct cgroup_map_cb *cb, - get_var *getvar, char *disk_id) -{ - uint64_t var = getvar(blkg, 0); - cb->fill(cb, disk_id, var); - return var; -} - -#define GET_STAT_INDEXED(__VAR) \ -uint64_t get_##__VAR##_stat(struct blkio_group *blkg, int type) \ -{ \ - return blkg->stats.__VAR[type]; \ -} \ - -GET_STAT_INDEXED(io_service_bytes); -GET_STAT_INDEXED(io_serviced); -GET_STAT_INDEXED(io_service_time); -GET_STAT_INDEXED(io_wait_time); -#undef GET_STAT_INDEXED - -#define GET_STAT(__VAR, __CONV) \ -uint64_t get_##__VAR##_stat(struct blkio_group *blkg, int dummy) \ -{ \ - uint64_t data = blkg->stats.__VAR; \ - if (__CONV) \ - data = (uint64_t)jiffies_to_msecs(data) * NSEC_PER_MSEC;\ - return data; \ -} - -GET_STAT(time, 1); -GET_STAT(sectors, 0); -#ifdef CONFIG_DEBUG_BLK_CGROUP -GET_STAT(dequeue, 0); -#endif -#undef GET_STAT - -#define SHOW_FUNCTION_PER_GROUP(__VAR, get_stats, getvar, show_total) \ +#define SHOW_FUNCTION_PER_GROUP(__VAR, type, show_total) \ static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \ struct cftype *cftype, struct cgroup_map_cb *cb) \ { \ @@ -343,7 +336,6 @@ static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \ struct blkio_group *blkg; \ struct hlist_node *n; \ uint64_t cgroup_total = 0; \ - char disk_id[10]; \ \ if (!cgroup_lock_live_group(cgroup)) \ return -ENODEV; \ @@ -353,10 +345,8 @@ static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \ hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {\ if (blkg->dev) { \ spin_lock_irq(&blkg->stats_lock); \ - snprintf(disk_id, 10, "%u:%u", MAJOR(blkg->dev),\ - MINOR(blkg->dev)); \ - cgroup_total += get_stats(blkg, cb, getvar, \ - disk_id); \ + cgroup_total += blkio_get_stat(blkg, cb, \ + blkg->dev, type); \ spin_unlock_irq(&blkg->stats_lock); \ } \ } \ @@ -367,16 +357,14 @@ static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \ return 0; \ } -SHOW_FUNCTION_PER_GROUP(time, get_stat, get_time_stat, 0); -SHOW_FUNCTION_PER_GROUP(sectors, get_stat, get_sectors_stat, 0); -SHOW_FUNCTION_PER_GROUP(io_service_bytes, get_typed_stat, - get_io_service_bytes_stat, 1); -SHOW_FUNCTION_PER_GROUP(io_serviced, get_typed_stat, get_io_serviced_stat, 1); -SHOW_FUNCTION_PER_GROUP(io_service_time, get_typed_stat, - get_io_service_time_stat, 1); -SHOW_FUNCTION_PER_GROUP(io_wait_time, get_typed_stat, get_io_wait_time_stat, 1); +SHOW_FUNCTION_PER_GROUP(time, BLKIO_STAT_TIME, 0); +SHOW_FUNCTION_PER_GROUP(sectors, BLKIO_STAT_SECTORS, 0); +SHOW_FUNCTION_PER_GROUP(io_service_bytes, BLKIO_STAT_SERVICE_BYTES, 1); +SHOW_FUNCTION_PER_GROUP(io_serviced, BLKIO_STAT_SERVICED, 1); +SHOW_FUNCTION_PER_GROUP(io_service_time, BLKIO_STAT_SERVICE_TIME, 1); +SHOW_FUNCTION_PER_GROUP(io_wait_time, BLKIO_STAT_WAIT_TIME, 1); #ifdef CONFIG_DEBUG_BLK_CGROUP -SHOW_FUNCTION_PER_GROUP(dequeue, get_stat, get_dequeue_stat, 0); +SHOW_FUNCTION_PER_GROUP(dequeue, BLKIO_STAT_DEQUEUE, 0); #endif #undef SHOW_FUNCTION_PER_GROUP @@ -398,32 +386,30 @@ struct cftype blkio_files[] = { { .name = "time", .read_map = blkiocg_time_read, - .write_u64 = blkiocg_reset_write, }, { .name = "sectors", .read_map = blkiocg_sectors_read, - .write_u64 = blkiocg_reset_write, }, { .name = "io_service_bytes", .read_map = blkiocg_io_service_bytes_read, - .write_u64 = blkiocg_reset_write, }, { .name = "io_serviced", .read_map = blkiocg_io_serviced_read, - .write_u64 = blkiocg_reset_write, }, { .name = "io_service_time", .read_map = blkiocg_io_service_time_read, - .write_u64 = blkiocg_reset_write, }, { .name = "io_wait_time", .read_map = blkiocg_io_wait_time_read, - .write_u64 = blkiocg_reset_write, + }, + { + .name = "reset_stats", + .write_u64 = blkiocg_reset_stats, }, #ifdef CONFIG_DEBUG_BLK_CGROUP { diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 80010ef64ab0..b22e55390a4f 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -23,12 +23,31 @@ extern struct cgroup_subsys blkio_subsys; #define blkio_subsys_id blkio_subsys.subsys_id #endif -enum io_type { - IO_READ = 0, - IO_WRITE, - IO_SYNC, - IO_ASYNC, - IO_TYPE_MAX +enum stat_type { + /* Total time spent (in ns) between request dispatch to the driver and + * request completion for IOs doen by this cgroup. This may not be + * accurate when NCQ is turned on. */ + BLKIO_STAT_SERVICE_TIME = 0, + /* Total bytes transferred */ + BLKIO_STAT_SERVICE_BYTES, + /* Total IOs serviced, post merge */ + BLKIO_STAT_SERVICED, + /* Total time spent waiting in scheduler queue in ns */ + BLKIO_STAT_WAIT_TIME, + /* All the single valued stats go below this */ + BLKIO_STAT_TIME, + BLKIO_STAT_SECTORS, +#ifdef CONFIG_DEBUG_BLK_CGROUP + BLKIO_STAT_DEQUEUE +#endif +}; + +enum stat_sub_type { + BLKIO_STAT_READ = 0, + BLKIO_STAT_WRITE, + BLKIO_STAT_SYNC, + BLKIO_STAT_ASYNC, + BLKIO_STAT_TOTAL }; struct blkio_cgroup { @@ -42,13 +61,7 @@ struct blkio_group_stats { /* total disk time and nr sectors dispatched by this group */ uint64_t time; uint64_t sectors; - /* Total disk time used by IOs in ns */ - uint64_t io_service_time[IO_TYPE_MAX]; - uint64_t io_service_bytes[IO_TYPE_MAX]; /* Total bytes transferred */ - /* Total IOs serviced, post merge */ - uint64_t io_serviced[IO_TYPE_MAX]; - /* Total time spent waiting in scheduler queue in ns */ - uint64_t io_wait_time[IO_TYPE_MAX]; + uint64_t stat_arr[BLKIO_STAT_WAIT_TIME + 1][BLKIO_STAT_TOTAL]; #ifdef CONFIG_DEBUG_BLK_CGROUP /* How many times this group has been removed from service tree */ unsigned long dequeue; @@ -65,7 +78,7 @@ struct blkio_group { char path[128]; #endif /* The device MKDEV(major, minor), this group has been created for */ - dev_t dev; + dev_t dev; /* Need to serialize the stats in the case of reset/update */ spinlock_t stats_lock; @@ -128,21 +141,21 @@ extern void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, extern int blkiocg_del_blkio_group(struct blkio_group *blkg); extern struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key); +void blkio_group_init(struct blkio_group *blkg); void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time); -void blkiocg_update_request_dispatch_stats(struct blkio_group *blkg, - struct request *rq); -void blkiocg_update_request_completion_stats(struct blkio_group *blkg, - struct request *rq); +void blkiocg_update_dispatch_stats(struct blkio_group *blkg, uint64_t bytes, + bool direction, bool sync); +void blkiocg_update_completion_stats(struct blkio_group *blkg, + uint64_t start_time, uint64_t io_start_time, bool direction, bool sync); #else struct cgroup; static inline struct blkio_cgroup * cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; } +static inline void blkio_group_init(struct blkio_group *blkg) {} static inline void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg, - struct blkio_group *blkg, void *key, dev_t dev) -{ -} + struct blkio_group *blkg, void *key, dev_t dev) {} static inline int blkiocg_del_blkio_group(struct blkio_group *blkg) { return 0; } @@ -151,9 +164,10 @@ static inline struct blkio_group * blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key) { return NULL; } static inline void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time) {} -static inline void blkiocg_update_request_dispatch_stats( - struct blkio_group *blkg, struct request *rq) {} -static inline void blkiocg_update_request_completion_stats( - struct blkio_group *blkg, struct request *rq) {} +static inline void blkiocg_update_dispatch_stats(struct blkio_group *blkg, + uint64_t bytes, bool direction, bool sync) {} +static inline void blkiocg_update_completion_stats(struct blkio_group *blkg, + uint64_t start_time, uint64_t io_start_time, bool direction, + bool sync) {} #endif #endif /* _BLK_CGROUP_H */ diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 42028e7128a7..5617ae030b15 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -955,6 +955,7 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create) for_each_cfqg_st(cfqg, i, j, st) *st = CFQ_RB_ROOT; RB_CLEAR_NODE(&cfqg->rb_node); + blkio_group_init(&cfqg->blkg); /* * Take the initial reference that will be released on destroy @@ -1865,7 +1866,8 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) elv_dispatch_sort(q, rq); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++; - blkiocg_update_request_dispatch_stats(&cfqq->cfqg->blkg, rq); + blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq), + rq_data_dir(rq), rq_is_sync(rq)); } /* @@ -3286,7 +3288,9 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) WARN_ON(!cfqq->dispatched); cfqd->rq_in_driver--; cfqq->dispatched--; - blkiocg_update_request_completion_stats(&cfqq->cfqg->blkg, rq); + blkiocg_update_completion_stats(&cfqq->cfqg->blkg, rq_start_time_ns(rq), + rq_io_start_time_ns(rq), rq_data_dir(rq), + rq_is_sync(rq)); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3fff8bf85ee..d483c494672a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1209,9 +1209,27 @@ static inline void set_io_start_time_ns(struct request *req) { req->io_start_time_ns = sched_clock(); } + +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return req->start_time_ns; +} + +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return req->io_start_time_ns; +} #else static inline void set_start_time_ns(struct request *req) {} static inline void set_io_start_time_ns(struct request *req) {} +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return 0; +} +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return 0; +} #endif #define MODULE_ALIAS_BLOCKDEV(major,minor) \ -- cgit v1.2.3 From 7f1dc8a2d2f45fc557b27fd56115338b1d34fc24 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 21 Apr 2010 17:44:16 +0200 Subject: blkio: Fix blkio crash during rq stat update blkio + cfq was crashing even when two sequential readers were put in two separate cgroups (group_isolation=0). The reason being that cfqq can migrate across groups based on its being sync-noidle or not, it can happen that at request insertion time, cfqq belonged to one cfqg and at request dispatch time, it belonged to root group. In this case request stats per cgroup can go wrong and it also runs into BUG_ON(). This patch implements rq stashing away a cfq group pointer and not relying on cfqq->cfqg pointer alone for rq stat accounting. [ 65.163523] ------------[ cut here ]------------ [ 65.164301] kernel BUG at block/blk-cgroup.c:117! [ 65.164301] invalid opcode: 0000 [#1] SMP [ 65.164301] last sysfs file: /sys/devices/pci0000:00/0000:00:05.0/0000:60:00.1/host9/rport-9:0-0/target9:0:0/9:0:0:2/block/sde/stat [ 65.164301] CPU 1 [ 65.164301] Modules linked in: dm_round_robin dm_multipath qla2xxx scsi_transport_fc dm_zero dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] [ 65.164301] [ 65.164301] Pid: 4505, comm: fio Not tainted 2.6.34-rc4-blk-for-35 #34 0A98h/HP xw8600 Workstation [ 65.164301] RIP: 0010:[] [] blkiocg_update_io_remove_stats+0x5b/0xaf [ 65.164301] RSP: 0018:ffff8800ba5a79e8 EFLAGS: 00010046 [ 65.164301] RAX: 0000000000000096 RBX: ffff8800bb268d60 RCX: 0000000000000000 [ 65.164301] RDX: ffff8800bb268eb8 RSI: 0000000000000000 RDI: ffff8800bb268e00 [ 65.164301] RBP: ffff8800ba5a7a08 R08: 0000000000000064 R09: 0000000000000001 [ 65.164301] R10: 0000000000079640 R11: ffff8800a0bd5bf0 R12: ffff8800bab4af01 [ 65.164301] R13: ffff8800bab4af00 R14: ffff8800bb1d8928 R15: 0000000000000000 [ 65.164301] FS: 00007f18f75056f0(0000) GS:ffff880001e40000(0000) knlGS:0000000000000000 [ 65.164301] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 65.164301] CR2: 000000000040e7f0 CR3: 00000000ba52b000 CR4: 00000000000006e0 [ 65.164301] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 65.164301] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 65.164301] Process fio (pid: 4505, threadinfo ffff8800ba5a6000, task ffff8800ba45ae80) [ 65.164301] Stack: [ 65.164301] ffff8800ba5a7a08 ffff8800ba722540 ffff8800bab4af68 ffff8800bab4af68 [ 65.164301] <0> ffff8800ba5a7a38 ffffffff8121d814 ffff8800ba722540 ffff8800bab4af68 [ 65.164301] <0> ffff8800ba722540 ffff8800a08f6800 ffff8800ba5a7a68 ffffffff8121d8ca [ 65.164301] Call Trace: [ 65.164301] [] cfq_remove_request+0xe4/0x116 [ 65.164301] [] cfq_dispatch_insert+0x84/0xe1 [ 65.164301] [] cfq_dispatch_requests+0x767/0x8e8 [ 65.164301] [] ? submit_bio+0xc3/0xcc [ 65.164301] [] ? sync_page_killable+0x0/0x35 [ 65.164301] [] blk_peek_request+0x191/0x1a7 [ 65.164301] [] ? dm_get_live_table+0x44/0x4f [dm_mod] [ 65.164301] [] dm_request_fn+0x38/0x14c [dm_mod] [ 65.164301] [] ? sync_page_killable+0x0/0x35 [ 65.164301] [] __generic_unplug_device+0x32/0x37 [ 65.164301] [] generic_unplug_device+0x2e/0x3c [ 65.164301] [] dm_unplug_all+0x42/0x5b [dm_mod] [ 65.164301] [] blk_unplug+0x29/0x2d [ 65.164301] [] blk_backing_dev_unplug+0x12/0x14 [ 65.164301] [] block_sync_page+0x35/0x39 [ 65.164301] [] sync_page+0x41/0x4a [ 65.164301] [] sync_page_killable+0xe/0x35 [ 65.164301] [] __wait_on_bit_lock+0x46/0x8f [ 65.164301] [] __lock_page_killable+0x66/0x6d [ 65.164301] [] ? wake_bit_function+0x0/0x33 [ 65.164301] [] lock_page_killable+0x2c/0x2e [ 65.164301] [] generic_file_aio_read+0x361/0x4f0 [ 65.164301] [] do_sync_read+0xcb/0x108 [ 65.164301] [] ? security_file_permission+0x16/0x18 [ 65.164301] [] vfs_read+0xab/0x108 [ 65.164301] [] sys_read+0x4a/0x6e [ 65.164301] [] system_call_fastpath+0x16/0x1b [ 65.164301] Code: 00 74 1c 48 8b 8b 60 01 00 00 48 85 c9 75 04 0f 0b eb fe 48 ff c9 48 89 8b 60 01 00 00 eb 1a 48 8b 8b 58 01 00 00 48 85 c9 75 04 <0f> 0b eb fe 48 ff c9 48 89 8b 58 01 00 00 45 84 e4 74 16 48 8b [ 65.164301] RIP [] blkiocg_update_io_remove_stats+0x5b/0xaf [ 65.164301] RSP [ 65.164301] ---[ end trace 1b2b828753032e68 ]--- Signed-off-by: Vivek Goyal Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 36 ++++++++++++++++++++++++++---------- include/linux/blkdev.h | 3 ++- 2 files changed, 28 insertions(+), 11 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 62defd05518f..d5927b53020e 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -55,6 +55,7 @@ static const int cfq_hist_divisor = 4; #define RQ_CIC(rq) \ ((struct cfq_io_context *) (rq)->elevator_private) #define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private2) +#define RQ_CFQG(rq) (struct cfq_group *) ((rq)->elevator_private3) static struct kmem_cache *cfq_pool; static struct kmem_cache *cfq_ioc_pool; @@ -1001,6 +1002,12 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create) return cfqg; } +static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg) +{ + atomic_inc(&cfqg->ref); + return cfqg; +} + static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) { /* Currently, all async queues are mapped to root group */ @@ -1084,6 +1091,12 @@ static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create) { return &cfqd->root_group; } + +static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg) +{ + return NULL; +} + static inline void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) { cfqq->cfqg = cfqg; @@ -1386,12 +1399,12 @@ static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq) { elv_rb_del(&cfqq->sort_list, rq); cfqq->queued[rq_is_sync(rq)]--; - blkiocg_update_io_remove_stats(&cfqq->cfqg->blkg, rq_data_dir(rq), + blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), rq_is_sync(rq)); cfq_add_rq_rb(rq); - blkiocg_update_io_add_stats( - &cfqq->cfqg->blkg, &cfqq->cfqd->serving_group->blkg, - rq_data_dir(rq), rq_is_sync(rq)); + blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg, + &cfqq->cfqd->serving_group->blkg, rq_data_dir(rq), + rq_is_sync(rq)); } static struct request * @@ -1447,7 +1460,7 @@ static void cfq_remove_request(struct request *rq) cfq_del_rq_rb(rq); cfqq->cfqd->rq_queued--; - blkiocg_update_io_remove_stats(&cfqq->cfqg->blkg, rq_data_dir(rq), + blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), rq_is_sync(rq)); if (rq_is_meta(rq)) { WARN_ON(!cfqq->meta_pending); @@ -1483,8 +1496,7 @@ static void cfq_merged_request(struct request_queue *q, struct request *req, static void cfq_bio_merged(struct request_queue *q, struct request *req, struct bio *bio) { - struct cfq_queue *cfqq = RQ_CFQQ(req); - blkiocg_update_io_merged_stats(&cfqq->cfqg->blkg, bio_data_dir(bio), + blkiocg_update_io_merged_stats(&(RQ_CFQG(req))->blkg, bio_data_dir(bio), cfq_bio_sync(bio)); } @@ -1505,7 +1517,7 @@ cfq_merged_requests(struct request_queue *q, struct request *rq, if (cfqq->next_rq == next) cfqq->next_rq = rq; cfq_remove_request(next); - blkiocg_update_io_merged_stats(&cfqq->cfqg->blkg, rq_data_dir(next), + blkiocg_update_io_merged_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(next), rq_is_sync(next)); } @@ -3240,8 +3252,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]); list_add_tail(&rq->queuelist, &cfqq->fifo); cfq_add_rq_rb(rq); - - blkiocg_update_io_add_stats(&cfqq->cfqg->blkg, + blkiocg_update_io_add_stats(&(RQ_CFQG(rq))->blkg, &cfqd->serving_group->blkg, rq_data_dir(rq), rq_is_sync(rq)); cfq_rq_enqueued(cfqd, cfqq, rq); @@ -3472,6 +3483,10 @@ static void cfq_put_request(struct request *rq) rq->elevator_private = NULL; rq->elevator_private2 = NULL; + /* Put down rq reference on cfqg */ + cfq_put_cfqg(RQ_CFQG(rq)); + rq->elevator_private3 = NULL; + cfq_put_queue(cfqq); } } @@ -3560,6 +3575,7 @@ new_queue: rq->elevator_private = cic; rq->elevator_private2 = cfqq; + rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg); return 0; queue_fail: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d483c494672a..5cf17a49ce38 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -186,11 +186,12 @@ struct request { }; /* - * two pointers are available for the IO schedulers, if they need + * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. */ void *elevator_private; void *elevator_private2; + void *elevator_private3; struct gendisk *rq_disk; unsigned long start_time; -- cgit v1.2.3 From fbd9b09a177a481eda256447c881f014f29034fe Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 28 Apr 2010 17:55:06 +0400 Subject: blkdev: generalize flags for blkdev_issue_fn functions The patch just convert all blkdev_issue_xxx function to common set of flags. Wait/allocation semantics preserved. Signed-off-by: Dmitry Monakhov Signed-off-by: Jens Axboe --- block/blk-barrier.c | 20 +++++++++++--------- block/ioctl.c | 2 +- drivers/block/drbd/drbd_int.h | 3 ++- drivers/block/drbd/drbd_receiver.c | 3 ++- fs/block_dev.c | 3 ++- fs/btrfs/extent-tree.c | 2 +- fs/ext3/fsync.c | 3 ++- fs/ext4/fsync.c | 6 ++++-- fs/gfs2/rgrp.c | 5 +++-- fs/jbd2/checkpoint.c | 3 ++- fs/jbd2/commit.c | 6 ++++-- fs/reiserfs/file.c | 3 ++- fs/xfs/linux-2.6/xfs_super.c | 3 ++- include/linux/blkdev.h | 18 +++++++++++------- mm/swapfile.c | 9 ++++++--- 15 files changed, 55 insertions(+), 34 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 6d88544b677f..cf14311b98fc 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -293,19 +293,22 @@ static void bio_end_empty_barrier(struct bio *bio, int err) /** * blkdev_issue_flush - queue a flush * @bdev: blockdev to issue flush for + * @gfp_mask: memory allocation flags (for bio_alloc) * @error_sector: error sector + * @flags: BLKDEV_IFL_* flags to control behaviour * * Description: * Issue a flush for the block device in question. Caller can supply * room for storing the error offset in case of a flush error, if they * wish to. */ -int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector) +int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, + sector_t *error_sector, unsigned long flags) { DECLARE_COMPLETION_ONSTACK(wait); struct request_queue *q; struct bio *bio; - int ret; + int ret = 0; if (bdev->bd_disk == NULL) return -ENXIO; @@ -314,7 +317,7 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector) if (!q) return -ENXIO; - bio = bio_alloc(GFP_KERNEL, 0); + bio = bio_alloc(gfp_mask, 0); bio->bi_end_io = bio_end_empty_barrier; bio->bi_private = &wait; bio->bi_bdev = bdev; @@ -330,7 +333,6 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector) if (error_sector) *error_sector = bio->bi_sector; - ret = 0; if (bio_flagged(bio, BIO_EOPNOTSUPP)) ret = -EOPNOTSUPP; else if (!bio_flagged(bio, BIO_UPTODATE)) @@ -362,17 +364,17 @@ 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 + * @flags: BLKDEV_IFL_* flags to control behaviour * * Description: * 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 flags) + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags) { DECLARE_COMPLETION_ONSTACK(wait); struct request_queue *q = bdev_get_queue(bdev); - int type = flags & DISCARD_FL_BARRIER ? + int type = flags & BLKDEV_IFL_BARRIER ? DISCARD_BARRIER : DISCARD_NOBARRIER; struct bio *bio; struct page *page; @@ -395,7 +397,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio->bi_sector = sector; bio->bi_end_io = blkdev_discard_end_io; bio->bi_bdev = bdev; - if (flags & DISCARD_FL_WAIT) + if (flags & BLKDEV_IFL_WAIT) bio->bi_private = &wait; /* @@ -426,7 +428,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_get(bio); submit_bio(type, bio); - if (flags & DISCARD_FL_WAIT) + if (flags & BLKDEV_IFL_WAIT) wait_for_completion(&wait); if (bio_flagged(bio, BIO_EOPNOTSUPP)) diff --git a/block/ioctl.c b/block/ioctl.c index 8905d2a2a717..e8eb679f2f9b 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -126,7 +126,7 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, if (start + len > (bdev->bd_inode->i_size >> 9)) return -EINVAL; return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, - DISCARD_FL_WAIT); + BLKDEV_IFL_WAIT); } static int put_ushort(unsigned long arg, unsigned short val) diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index e5e86a781820..d6f1ae342b1d 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -2251,7 +2251,8 @@ static inline void drbd_md_flush(struct drbd_conf *mdev) if (test_bit(MD_NO_BARRIER, &mdev->flags)) return; - r = blkdev_issue_flush(mdev->ldev->md_bdev, NULL); + r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); if (r) { set_bit(MD_NO_BARRIER, &mdev->flags); dev_err(DEV, "meta data flush failed with status %d, disabling md-flushes\n", r); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index ed9f1de24a71..54f56ea8a786 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -945,7 +945,8 @@ static enum finish_epoch drbd_flush_after_epoch(struct drbd_conf *mdev, struct d int rv; if (mdev->write_ordering >= WO_bdev_flush && get_ldev(mdev)) { - rv = blkdev_issue_flush(mdev->ldev->backing_bdev, NULL); + rv = blkdev_issue_flush(mdev->ldev->backing_bdev, GFP_KERNEL, + NULL, BLKDEV_IFL_WAIT); if (rv) { dev_err(DEV, "local disk flush failed with status %d\n", rv); /* would rather check on EOPNOTSUPP, but that is not reliable. diff --git a/fs/block_dev.c b/fs/block_dev.c index ea8385ea58ab..dd769304382e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -413,7 +413,8 @@ int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync) if (error) return error; - error = blkdev_issue_flush(bdev, NULL); + error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL, + (BLKDEV_IFL_WAIT)); if (error == -EOPNOTSUPP) error = 0; return error; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b34d32fdaaec..c6a4f459ad76 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1589,7 +1589,7 @@ static void btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len) { blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, - DISCARD_FL_BARRIER); + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); } static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c index 8209f266e9ad..9492f6003ef9 100644 --- a/fs/ext3/fsync.c +++ b/fs/ext3/fsync.c @@ -91,7 +91,8 @@ int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync) * storage */ if (test_opt(inode->i_sb, BARRIER)) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); out: return ret; } diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 0d0c3239c1cd..ef3d980e67cb 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -100,9 +100,11 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) if (ext4_should_writeback_data(inode) && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, + NULL, BLKDEV_IFL_WAIT); jbd2_log_wait_commit(journal, commit_tid); } else if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); return ret; } diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 503b842f3ba2..bf011dc63471 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -854,7 +854,8 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, if ((start + nr_sects) != blk) { rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, - DISCARD_FL_BARRIER); + BLKDEV_IFL_WAIT | + BLKDEV_IFL_BARRIER); if (rv) goto fail; nr_sects = 0; @@ -869,7 +870,7 @@ start_new_extent: } if (nr_sects) { rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, - DISCARD_FL_BARRIER); + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); if (rv) goto fail; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 30beb11ef928..076d1cc44f95 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -530,7 +530,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal) */ if ((journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, NULL); + blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); if (!(journal->j_flags & JBD2_ABORT)) jbd2_journal_update_superblock(journal, 1); return 0; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 671da7fb7ffd..75716d3d2be0 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -717,7 +717,8 @@ start_journal_io: if (commit_transaction->t_flushed_data_blocks && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, NULL); + blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, @@ -727,7 +728,8 @@ start_journal_io: if (err) __jbd2_journal_abort_hard(journal); if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(journal->j_dev, NULL); + blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); } err = journal_finish_inode_data_buffers(journal, commit_transaction); diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 1d9c12714c5c..9977df9f3a54 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -147,7 +147,8 @@ static int reiserfs_sync_file(struct file *filp, barrier_done = reiserfs_commit_for_inode(inode); reiserfs_write_unlock(inode->i_sb); if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb)) - blkdev_issue_flush(inode->i_sb->s_bdev, NULL); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); if (barrier_done < 0) return barrier_done; return (err < 0) ? -EIO : 0; diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 52e06b487ced..2b177c778ba7 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -725,7 +725,8 @@ void xfs_blkdev_issue_flush( xfs_buftarg_t *buftarg) { - blkdev_issue_flush(buftarg->bt_bdev, NULL); + blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL, + BLKDEV_IFL_WAIT); } STATIC void diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5cf17a49ce38..59b9aed0ee7d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -998,12 +998,16 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, return NULL; return bqt->tag_index[tag]; } - -extern int blkdev_issue_flush(struct block_device *, sector_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); +enum{ + BLKDEV_WAIT, /* wait for completion */ + BLKDEV_BARRIER, /*issue request with barrier */ +}; +#define BLKDEV_IFL_WAIT (1 << BLKDEV_WAIT) +#define BLKDEV_IFL_BARRIER (1 << BLKDEV_BARRIER) +extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *, + unsigned long); +extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks) @@ -1011,7 +1015,7 @@ static inline int sb_issue_discard(struct super_block *sb, 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, - DISCARD_FL_BARRIER); + BLKDEV_IFL_WAIT | BLKDEV_IFL_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 6cd0a8f90dc7..eb086e0f4dcc 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -139,7 +139,8 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, DISCARD_FL_BARRIER); + nr_blocks, GFP_KERNEL, + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); if (err) return err; cond_resched(); @@ -150,7 +151,8 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, DISCARD_FL_BARRIER); + nr_blocks, GFP_KERNEL, + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); if (err) break; @@ -189,7 +191,8 @@ 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, DISCARD_FL_BARRIER)) + nr_blocks, GFP_NOIO, BLKDEV_IFL_WAIT | + BLKDEV_IFL_BARRIER)) break; } -- cgit v1.2.3 From 3f14d792f9a8fede64ce918dbb517f934497a4f8 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 28 Apr 2010 17:55:09 +0400 Subject: blkdev: add blkdev_issue_zeroout helper function - Add bio_batch helper primitive. This is rather generic primitive for submitting/waiting a complex request which consists of several bios. - blkdev_issue_zeroout() generate number of zero filed write bios. Signed-off-by: Dmitry Monakhov Signed-off-by: Jens Axboe --- block/blk-lib.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/blkdev.h | 3 +- 2 files changed, 120 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-lib.c b/block/blk-lib.c index 0dc438812d81..886c3f9e1be4 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -112,3 +112,121 @@ out: return -ENOMEM; } EXPORT_SYMBOL(blkdev_issue_discard); + +struct bio_batch +{ + atomic_t done; + unsigned long flags; + struct completion *wait; + bio_end_io_t *end_io; +}; + +static void bio_batch_end_io(struct bio *bio, int err) +{ + struct bio_batch *bb = bio->bi_private; + if (err) { + if (err == -EOPNOTSUPP) + set_bit(BIO_EOPNOTSUPP, &bb->flags); + else + clear_bit(BIO_UPTODATE, &bb->flags); + } + if (bb) { + if (bb->end_io) + bb->end_io(bio, err); + atomic_inc(&bb->done); + complete(bb->wait); + } + bio_put(bio); +} + +/** + * blkdev_issue_zeroout generate number of zero filed write bios + * @bdev: blockdev to issue + * @sector: start sector + * @nr_sects: number of sectors to write + * @gfp_mask: memory allocation flags (for bio_alloc) + * @flags: BLKDEV_IFL_* flags to control behaviour + * + * Description: + * Generate and issue number of bios with zerofiled pages. + * Send barrier at the beginning and at the end if requested. This guarantie + * correct request ordering. Empty barrier allow us to avoid post queue flush. + */ + +int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags) +{ + int ret = 0; + struct bio *bio; + struct bio_batch bb; + unsigned int sz, issued = 0; + DECLARE_COMPLETION_ONSTACK(wait); + + atomic_set(&bb.done, 0); + bb.flags = 1 << BIO_UPTODATE; + bb.wait = &wait; + bb.end_io = NULL; + + if (flags & BLKDEV_IFL_BARRIER) { + /* issue async barrier before the data */ + ret = blkdev_issue_flush(bdev, gfp_mask, NULL, 0); + if (ret) + return ret; + } +submit: + while (nr_sects != 0) { + bio = bio_alloc(gfp_mask, + min(nr_sects, (sector_t)BIO_MAX_PAGES)); + if (!bio) + break; + + bio->bi_sector = sector; + bio->bi_bdev = bdev; + bio->bi_end_io = bio_batch_end_io; + if (flags & BLKDEV_IFL_WAIT) + bio->bi_private = &bb; + + while(nr_sects != 0) { + sz = min(PAGE_SIZE >> 9 , nr_sects); + if (sz == 0) + /* bio has maximum size possible */ + break; + ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0); + nr_sects -= ret >> 9; + sector += ret >> 9; + if (ret < (sz << 9)) + break; + } + issued++; + submit_bio(WRITE, bio); + } + /* + * When all data bios are in flight. Send final barrier if requeted. + */ + if (nr_sects == 0 && flags & BLKDEV_IFL_BARRIER) + ret = blkdev_issue_flush(bdev, gfp_mask, NULL, + flags & BLKDEV_IFL_WAIT); + + + if (flags & BLKDEV_IFL_WAIT) + /* Wait for bios in-flight */ + while ( issued != atomic_read(&bb.done)) + wait_for_completion(&wait); + + if (!test_bit(BIO_UPTODATE, &bb.flags)) + /* One of bios in the batch was completed with error.*/ + ret = -EIO; + + if (ret) + goto out; + + if (test_bit(BIO_EOPNOTSUPP, &bb.flags)) { + ret = -EOPNOTSUPP; + goto out; + } + if (nr_sects != 0) + goto submit; +out: + return ret; +} +EXPORT_SYMBOL(blkdev_issue_zeroout); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 59b9aed0ee7d..3ac2bd2fc485 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1008,7 +1008,8 @@ extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *, unsigned long); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); - +extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks) { -- cgit v1.2.3 From 01effb0dc1451fad55925873ffbfb88fa4eadce0 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 11 May 2010 08:57:42 +0200 Subject: block: allow initialization of previously allocated request_queue blk_init_queue() allocates the request_queue structure and then initializes it as needed (request_fn, elevator, etc). Split initialization out to blk_init_allocated_queue_node. Introduce blk_init_allocated_queue wrapper function to model existing blk_init_queue and blk_init_queue_node interfaces. Export elv_register_queue to allow a newly added elevator to be registered with sysfs. Export elv_unregister_queue for symmetry. These changes allow DM to initialize a device's request_queue with more precision. In particular, DM no longer unconditionally initializes a full request_queue (elevator et al). It only does so for a request-based DM device. Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-core.c | 18 +++++++++++++++++- block/elevator.c | 2 ++ include/linux/blkdev.h | 5 +++++ 3 files changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index e9a5ae25db8c..3bc5579d6f54 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -572,6 +572,22 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) { struct request_queue *q = blk_alloc_queue_node(GFP_KERNEL, node_id); + return blk_init_allocated_queue_node(q, rfn, lock, node_id); +} +EXPORT_SYMBOL(blk_init_queue_node); + +struct request_queue * +blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, + spinlock_t *lock) +{ + return blk_init_allocated_queue_node(q, rfn, lock, -1); +} +EXPORT_SYMBOL(blk_init_allocated_queue); + +struct request_queue * +blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn, + spinlock_t *lock, int node_id) +{ if (!q) return NULL; @@ -605,7 +621,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) blk_put_queue(q); return NULL; } -EXPORT_SYMBOL(blk_init_queue_node); +EXPORT_SYMBOL(blk_init_allocated_queue_node); int blk_get_queue(struct request_queue *q) { diff --git a/block/elevator.c b/block/elevator.c index 5e734592bb40..6df2b5056b51 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -930,6 +930,7 @@ int elv_register_queue(struct request_queue *q) } return error; } +EXPORT_SYMBOL(elv_register_queue); static void __elv_unregister_queue(struct elevator_queue *e) { @@ -942,6 +943,7 @@ void elv_unregister_queue(struct request_queue *q) if (q) __elv_unregister_queue(q->elevator); } +EXPORT_SYMBOL(elv_unregister_queue); void elv_register(struct elevator_type *e) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3ac2bd2fc485..346fd4856733 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -921,7 +921,12 @@ extern void blk_abort_queue(struct request_queue *); */ 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 *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); -- cgit v1.2.3 From b3a27d0529c6e5206f1b60f60263e3ecfd0d77cb Mon Sep 17 00:00:00 2001 From: Nitin Gupta Date: Mon, 17 May 2010 11:02:43 +0530 Subject: swap: Add swap slot free callback to block_device_operations This callback is required when RAM based devices are used as swap disks. One such device is ramzswap which is used as compressed in-memory swap disk. For such devices, we need a callback as soon as a swap slot is no longer used to allow freeing memory allocated for this slot. Without this callback, stale data can quickly accumulate in memory defeating the whole purpose of such devices. Signed-off-by: Nitin Gupta Acked-by: Linus Torvalds Acked-by: Nigel Cunningham Acked-by: Pekka Enberg Reviewed-by: Minchan Kim Signed-off-by: Greg Kroah-Hartman --- include/linux/blkdev.h | 2 ++ mm/swapfile.c | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6690e8bae7bb..413284a51ccc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1287,6 +1287,8 @@ struct block_device_operations { unsigned long long); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); + /* this callback is with swap_lock and sometimes page table lock held */ + void (*swap_slot_free_notify) (struct block_device *, unsigned long); struct module *owner; }; diff --git a/mm/swapfile.c b/mm/swapfile.c index ecb069e213d0..f5ccc476aa51 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -574,6 +574,7 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, /* free if no reference */ if (!usage) { + struct gendisk *disk = p->bdev->bd_disk; if (offset < p->lowest_bit) p->lowest_bit = offset; if (offset > p->highest_bit) @@ -583,6 +584,9 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, swap_list.next = p->type; nr_swap_pages++; p->inuse_pages--; + if ((p->flags & SWP_BLKDEV) && + disk->fops->swap_slot_free_notify) + disk->fops->swap_slot_free_notify(p->bdev, offset); } return usage; -- cgit v1.2.3 From c3e33e043f5e9c583aa59d5591a614b2a8243d3a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 15 May 2010 20:09:29 +0200 Subject: block,ide: simplify bdops->set_capacity() to ->unlock_native_capacity() bdops->set_capacity() is unnecessarily generic. All that's required is a simple one way notification to lower level driver telling it to try to unlock native capacity. There's no reason to pass in target capacity or return the new capacity. The former is always the inherent native capacity and the latter can be handled via the usual device resize / revalidation path. In fact, the current API is always used that way. Replace ->set_capacity() with ->unlock_native_capacity() which take only @disk and doesn't return anything. IDE which is the only current user of the API is converted accordingly. Signed-off-by: Tejun Heo Cc: Ben Hutchings Cc: Bartlomiej Zolnierkiewicz Acked-by: David S. Miller Signed-off-by: Jens Axboe --- drivers/ide/ide-disk.c | 40 ++++++++++++++++------------------------ drivers/ide/ide-gd.c | 11 ++++------- fs/partitions/check.c | 4 ++-- include/linux/blkdev.h | 3 +-- include/linux/ide.h | 2 +- 5 files changed, 24 insertions(+), 36 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 3b128dce9c3a..33d65039cce9 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -407,32 +407,24 @@ static int ide_disk_get_capacity(ide_drive_t *drive) return 0; } -static u64 ide_disk_set_capacity(ide_drive_t *drive, u64 capacity) +static void ide_disk_unlock_native_capacity(ide_drive_t *drive) { - u64 set = min(capacity, drive->probed_capacity); u16 *id = drive->id; int lba48 = ata_id_lba48_enabled(id); if ((drive->dev_flags & IDE_DFLAG_LBA) == 0 || ata_id_hpa_enabled(id) == 0) - goto out; + return; /* * according to the spec the SET MAX ADDRESS command shall be * immediately preceded by a READ NATIVE MAX ADDRESS command */ - capacity = ide_disk_hpa_get_native_capacity(drive, lba48); - if (capacity == 0) - goto out; - - set = ide_disk_hpa_set_capacity(drive, set, lba48); - if (set) { - /* needed for ->resume to disable HPA */ - drive->dev_flags |= IDE_DFLAG_NOHPA; - return set; - } -out: - return drive->capacity64; + if (!ide_disk_hpa_get_native_capacity(drive, lba48)) + return; + + if (ide_disk_hpa_set_capacity(drive, drive->probed_capacity, lba48)) + drive->dev_flags |= IDE_DFLAG_NOHPA; /* disable HPA on resume */ } static void idedisk_prepare_flush(struct request_queue *q, struct request *rq) @@ -783,13 +775,13 @@ static int ide_disk_set_doorlock(ide_drive_t *drive, struct gendisk *disk, } const struct ide_disk_ops ide_ata_disk_ops = { - .check = ide_disk_check, - .set_capacity = ide_disk_set_capacity, - .get_capacity = ide_disk_get_capacity, - .setup = ide_disk_setup, - .flush = ide_disk_flush, - .init_media = ide_disk_init_media, - .set_doorlock = ide_disk_set_doorlock, - .do_request = ide_do_rw_disk, - .ioctl = ide_disk_ioctl, + .check = ide_disk_check, + .unlock_native_capacity = ide_disk_unlock_native_capacity, + .get_capacity = ide_disk_get_capacity, + .setup = ide_disk_setup, + .flush = ide_disk_flush, + .init_media = ide_disk_init_media, + .set_doorlock = ide_disk_set_doorlock, + .do_request = ide_do_rw_disk, + .ioctl = ide_disk_ioctl, }; diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c index c32d83996ae1..c102d23d9b38 100644 --- a/drivers/ide/ide-gd.c +++ b/drivers/ide/ide-gd.c @@ -288,17 +288,14 @@ static int ide_gd_media_changed(struct gendisk *disk) return ret; } -static unsigned long long ide_gd_set_capacity(struct gendisk *disk, - unsigned long long capacity) +static void ide_gd_unlock_native_capacity(struct gendisk *disk) { struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj); ide_drive_t *drive = idkp->drive; const struct ide_disk_ops *disk_ops = drive->disk_ops; - if (disk_ops->set_capacity) - return disk_ops->set_capacity(drive, capacity); - - return drive->capacity64; + if (disk_ops->unlock_native_capacity) + disk_ops->unlock_native_capacity(drive); } static int ide_gd_revalidate_disk(struct gendisk *disk) @@ -329,7 +326,7 @@ static const struct block_device_operations ide_gd_ops = { .locked_ioctl = ide_gd_ioctl, .getgeo = ide_gd_getgeo, .media_changed = ide_gd_media_changed, - .set_capacity = ide_gd_set_capacity, + .unlock_native_capacity = ide_gd_unlock_native_capacity, .revalidate_disk = ide_gd_revalidate_disk }; diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 8f01df354f04..4f1fee0355ad 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -601,10 +601,10 @@ rescan: "%s: p%d size %llu exceeds device capacity, ", disk->disk_name, p, (unsigned long long) size); - if (bdops->set_capacity && + if (bdops->unlock_native_capacity && (disk->flags & GENHD_FL_NATIVE_CAPACITY) == 0) { printk(KERN_CONT "enabling native capacity\n"); - bdops->set_capacity(disk, ~0ULL); + bdops->unlock_native_capacity(disk); disk->flags |= GENHD_FL_NATIVE_CAPACITY; /* free state and restart */ kfree(state); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 346fd4856733..be411c12ebbe 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1330,8 +1330,7 @@ struct block_device_operations { int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *); int (*media_changed) (struct gendisk *); - unsigned long long (*set_capacity) (struct gendisk *, - unsigned long long); + void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); struct module *owner; diff --git a/include/linux/ide.h b/include/linux/ide.h index 3239d1c10acb..b6d448048ae2 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -362,7 +362,7 @@ struct ide_drive_s; struct ide_disk_ops { int (*check)(struct ide_drive_s *, const char *); int (*get_capacity)(struct ide_drive_s *); - u64 (*set_capacity)(struct ide_drive_s *, u64); + void (*unlock_native_capacity)(struct ide_drive_s *); void (*setup)(struct ide_drive_s *); void (*flush)(struct ide_drive_s *); int (*init_media)(struct ide_drive_s *, struct gendisk *); -- cgit v1.2.3 From 28f4197e5d4707311febeec8a0eb97cb5fd93c97 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 1 Jun 2010 12:23:18 +0200 Subject: block: disable preemption before using sched_clock() Commit 9195291e5f05e01d67f9a09c756b8aca8f009089 added calls to sched_clock() from preemptible code. sched_clock() is both the wrong interface AND cannot be called without preempt disabled. Apply a temporary fix to get rid of the warnings, a real patch is in the works. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8b7f5e0914ad..09a840264d6f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1211,14 +1211,23 @@ struct work_struct; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); #ifdef CONFIG_BLK_CGROUP +/* + * This should not be using sched_clock(). A real patch is in progress + * to fix this up, until that is in place we need to disable preemption + * around sched_clock() in this function and set_io_start_time_ns(). + */ static inline void set_start_time_ns(struct request *req) { + preempt_disable(); req->start_time_ns = sched_clock(); + preempt_enable(); } static inline void set_io_start_time_ns(struct request *req) { + preempt_disable(); req->io_start_time_ns = sched_clock(); + preempt_enable(); } static inline uint64_t rq_start_time_ns(struct request *req) -- cgit v1.2.3 From e2e1a148bc45855816ae6b4692ce29d0020fa22e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Jun 2010 10:42:09 +0200 Subject: block: add sysfs knob for turning off disk entropy contributions There are two reasons for doing this: - On SSD disks, the completion times aren't as random as they are for rotational drives. So it's questionable whether they should contribute to the random pool in the first place. - Calling add_disk_randomness() has a lot of overhead. This adds /sys/block//queue/add_random that will allow you to switch off on a per-device basis. The default setting is on, so there should be no functional changes from this patch. Signed-off-by: Jens Axboe --- block/blk-core.c | 3 ++- block/blk-sysfs.c | 28 ++++++++++++++++++++++++++++ include/linux/blkdev.h | 5 ++++- 3 files changed, 34 insertions(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index f0640d7f800f..b4131d29148c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2111,7 +2111,8 @@ static bool blk_update_bidi_request(struct request *rq, int error, blk_update_request(rq->next_rq, error, bidi_bytes)) return true; - add_disk_randomness(rq->rq_disk); + if (blk_queue_add_random(rq->q)) + add_disk_randomness(rq->rq_disk); return false; } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 306759bbdf1b..58b53c354c2c 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -250,6 +250,27 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count) return ret; } +static ssize_t queue_random_show(struct request_queue *q, char *page) +{ + return queue_var_show(blk_queue_add_random(q), page); +} + +static ssize_t queue_random_store(struct request_queue *q, const char *page, + size_t count) +{ + unsigned long val; + ssize_t ret = queue_var_store(&val, page, count); + + spin_lock_irq(q->queue_lock); + if (val) + queue_flag_set(QUEUE_FLAG_ADD_RANDOM, q); + else + queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); + spin_unlock_irq(q->queue_lock); + + return ret; +} + static ssize_t queue_iostats_show(struct request_queue *q, char *page) { return queue_var_show(blk_queue_io_stat(q), page); @@ -374,6 +395,12 @@ static struct queue_sysfs_entry queue_iostats_entry = { .store = queue_iostats_store, }; +static struct queue_sysfs_entry queue_random_entry = { + .attr = {.name = "add_random", .mode = S_IRUGO | S_IWUSR }, + .show = queue_random_show, + .store = queue_random_store, +}; + static struct attribute *default_attrs[] = { &queue_requests_entry.attr, &queue_ra_entry.attr, @@ -394,6 +421,7 @@ static struct attribute *default_attrs[] = { &queue_nomerges_entry.attr, &queue_rq_affinity_entry.attr, &queue_iostats_entry.attr, + &queue_random_entry.attr, NULL, }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 09a840264d6f..b8224ea4a5de 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -467,11 +467,13 @@ struct request_queue #define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ #define QUEUE_FLAG_DISCARD 16 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 17 /* No extended merges */ +#define QUEUE_FLAG_ADD_RANDOM 18 /* Contributes to random pool */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ (1 << QUEUE_FLAG_STACKABLE) | \ - (1 << QUEUE_FLAG_SAME_COMP)) + (1 << QUEUE_FLAG_SAME_COMP) | \ + (1 << QUEUE_FLAG_ADD_RANDOM)) static inline int queue_is_locked(struct request_queue *q) { @@ -596,6 +598,7 @@ enum { test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) +#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_flushing(q) ((q)->ordseq) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) -- cgit v1.2.3 From bfe172310e58225f0d07f9354b683abacbd6a0d8 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Mon, 31 May 2010 15:59:03 +0900 Subject: block: kill ISA_DMA_THRESHOLD usage block uses ISA_DMA_THRESHOLD for BLK_BOUNCE_ISA. Only SCSI uses ISA_DMA_THRESHOLD for ancient drivers with non-zero unchecked_isa_dma. Nowadays drivers (and subsystems) use dma_mask properly instead of ISA_DMA_THRESHOLD. Documentation/scsi/scsi_mid_low_api.txt says: unchecked_isa_dma - 1=>only use bottom 16 MB of ram (ISA DMA addressing restriction), 0=>can use full 32 bit (or better) DMA address space So block simply uses DMA_BIT_MASK(24) for BLK_BOUNCE_ISA for SCSI. Signed-off-by: FUJITA Tomonori Acked-by: James Bottomley 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 b8224ea4a5de..d7ae241a9e55 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -712,7 +712,7 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; #define BLK_BOUNCE_HIGH -1ULL #endif #define BLK_BOUNCE_ANY (-1ULL) -#define BLK_BOUNCE_ISA (ISA_DMA_THRESHOLD) +#define BLK_BOUNCE_ISA (DMA_BIT_MASK(24)) /* * default timeout for SG_IO if none specified -- cgit v1.2.3 From 33659ebbae262228eef4e0fe990f393d1f0ed941 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 7 Aug 2010 18:17:56 +0200 Subject: block: remove wrappers for request type/flags Remove all the trivial wrappers for the cmd_type and cmd_flags fields in struct requests. This allows much easier grepping for different request types instead of unwinding through macros. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 7 ++-- block/blk-core.c | 13 ++++---- block/blk-exec.c | 2 +- block/blk-merge.c | 4 +-- block/blk.h | 6 ++-- block/cfq-iosched.c | 19 ++++++----- block/elevator.c | 16 +++++---- drivers/ata/libata-scsi.c | 2 +- drivers/block/cciss.c | 49 ++++++++++++++++----------- drivers/block/hd.c | 2 +- drivers/block/mg_disk.c | 4 +-- drivers/block/nbd.c | 2 +- drivers/block/osdblk.c | 3 +- drivers/block/paride/pd.c | 2 +- drivers/block/ps3disk.c | 2 +- drivers/block/ub.c | 8 ++--- drivers/block/viodasd.c | 2 +- drivers/block/virtio_blk.c | 15 +++++---- drivers/block/xd.c | 2 +- drivers/block/xen-blkfront.c | 4 +-- drivers/block/xsysace.c | 2 +- drivers/cdrom/gdrom.c | 2 +- drivers/cdrom/viocd.c | 2 +- drivers/ide/ide-atapi.c | 17 ++++++---- drivers/ide/ide-cd.c | 66 ++++++++++++++++++++----------------- drivers/ide/ide-disk.c | 2 +- drivers/ide/ide-eh.c | 5 +-- drivers/ide/ide-floppy.c | 25 +++++++++----- drivers/ide/ide-io.c | 8 ++--- drivers/ide/ide-pm.c | 8 ++--- drivers/ide/ide-tape.c | 3 +- drivers/md/dm.c | 10 +++--- drivers/memstick/core/mspro_block.c | 3 +- drivers/message/i2o/i2o_block.c | 2 +- drivers/mmc/card/queue.c | 2 +- drivers/mtd/mtd_blkdevs.c | 4 +-- drivers/scsi/scsi_error.c | 10 +++--- drivers/scsi/scsi_lib.c | 5 +-- drivers/scsi/sd.c | 12 +++---- drivers/scsi/sun3_NCR5380.c | 2 +- drivers/scsi/sun3_scsi.c | 2 +- drivers/scsi/sun3_scsi_vme.c | 2 +- drivers/staging/hv/blkvsc_drv.c | 8 +++-- include/linux/blkdev.h | 41 ++++++++--------------- include/linux/blktrace_api.h | 2 +- include/trace/events/block.h | 15 ++++++--- kernel/trace/blktrace.c | 10 +++--- 47 files changed, 236 insertions(+), 198 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 0d710c9d403b..74e404393172 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -79,7 +79,7 @@ unsigned blk_ordered_req_seq(struct request *rq) * * http://thread.gmane.org/gmane.linux.kernel/537473 */ - if (!blk_fs_request(rq)) + if (rq->cmd_type != REQ_TYPE_FS) return QUEUE_ORDSEQ_DRAIN; if ((rq->cmd_flags & REQ_ORDERED_COLOR) == @@ -236,7 +236,8 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp) bool blk_do_ordered(struct request_queue *q, struct request **rqp) { struct request *rq = *rqp; - const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq); + const int is_barrier = rq->cmd_type == REQ_TYPE_FS && + (rq->cmd_flags & REQ_HARDBARRIER); if (!q->ordseq) { if (!is_barrier) @@ -261,7 +262,7 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp) */ /* Special requests are not subject to ordering rules. */ - if (!blk_fs_request(rq) && + if (rq->cmd_type != REQ_TYPE_FS && rq != &q->pre_flush_rq && rq != &q->post_flush_rq) return true; diff --git a/block/blk-core.c b/block/blk-core.c index b4131d29148c..dca43a31e725 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -184,7 +184,7 @@ void blk_dump_rq_flags(struct request *rq, char *msg) printk(KERN_INFO " bio %p, biotail %p, buffer %p, len %u\n", rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq)); - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { printk(KERN_INFO " cdb: "); for (bit = 0; bit < BLK_MAX_CDB; bit++) printk("%02x ", rq->cmd[bit]); @@ -1796,7 +1796,7 @@ struct request *blk_peek_request(struct request_queue *q) * sees this request (possibly after * requeueing). Notify IO scheduler. */ - if (blk_sorted_rq(rq)) + if (rq->cmd_flags & REQ_SORTED) elv_activate_rq(q, rq); /* @@ -1984,10 +1984,11 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) * TODO: tj: This is too subtle. It would be better to let * low level drivers do what they see fit. */ - if (blk_fs_request(req)) + if (req->cmd_type == REQ_TYPE_FS) req->errors = 0; - if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) { + if (error && req->cmd_type == REQ_TYPE_FS && + !(req->cmd_flags & REQ_QUIET)) { printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n", req->rq_disk ? req->rq_disk->disk_name : "?", (unsigned long long)blk_rq_pos(req)); @@ -2074,7 +2075,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) req->buffer = bio_data(req->bio); /* update sector only for requests with clear definition of sector */ - if (blk_fs_request(req) || blk_discard_rq(req)) + if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ @@ -2127,7 +2128,7 @@ static void blk_finish_request(struct request *req, int error) BUG_ON(blk_queued_rq(req)); - if (unlikely(laptop_mode) && blk_fs_request(req)) + if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS) laptop_io_completion(&req->q->backing_dev_info); blk_delete_timer(req); diff --git a/block/blk-exec.c b/block/blk-exec.c index 49557e91f0da..e1672f14840e 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -57,7 +57,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, __elv_add_request(q, rq, where, 1); __generic_unplug_device(q); /* the queue is stopped so it won't be plugged+unplugged */ - if (blk_pm_resume_request(rq)) + if (rq->cmd_type == REQ_TYPE_PM_RESUME) q->request_fn(q); spin_unlock_irq(q->queue_lock); } diff --git a/block/blk-merge.c b/block/blk-merge.c index 5e7dc9973458..87e4fb7d0e98 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -226,7 +226,7 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req, { unsigned short max_sectors; - if (unlikely(blk_pc_request(req))) + if (unlikely(req->cmd_type == REQ_TYPE_BLOCK_PC)) max_sectors = queue_max_hw_sectors(q); else max_sectors = queue_max_sectors(q); @@ -250,7 +250,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req, { unsigned short max_sectors; - if (unlikely(blk_pc_request(req))) + if (unlikely(req->cmd_type == REQ_TYPE_BLOCK_PC)) max_sectors = queue_max_hw_sectors(q); else max_sectors = queue_max_sectors(q); diff --git a/block/blk.h b/block/blk.h index 5ee3d7e72feb..6e7dc87141e4 100644 --- a/block/blk.h +++ b/block/blk.h @@ -161,8 +161,10 @@ static inline int blk_cpu_to_group(int cpu) */ static inline int blk_do_io_stat(struct request *rq) { - return rq->rq_disk && blk_rq_io_stat(rq) && - (blk_fs_request(rq) || blk_discard_rq(rq)); + return rq->rq_disk && + (rq->cmd_flags & REQ_IO_STAT) && + (rq->cmd_type == REQ_TYPE_FS || + (rq->cmd_flags & REQ_DISCARD)); } #endif diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 7982b830db58..d4edeb8fceb8 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -646,9 +646,10 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, return rq1; else if (rq_is_sync(rq2) && !rq_is_sync(rq1)) return rq2; - if (rq_is_meta(rq1) && !rq_is_meta(rq2)) + if ((rq1->cmd_flags & REQ_RW_META) && !(rq2->cmd_flags & REQ_RW_META)) return rq1; - else if (rq_is_meta(rq2) && !rq_is_meta(rq1)) + else if ((rq2->cmd_flags & REQ_RW_META) && + !(rq1->cmd_flags & REQ_RW_META)) return rq2; s1 = blk_rq_pos(rq1); @@ -1484,7 +1485,7 @@ static void cfq_remove_request(struct request *rq) cfqq->cfqd->rq_queued--; cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), rq_is_sync(rq)); - if (rq_is_meta(rq)) { + if (rq->cmd_flags & REQ_RW_META) { WARN_ON(!cfqq->meta_pending); cfqq->meta_pending--; } @@ -3176,7 +3177,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, * So both queues are sync. Let the new request get disk time if * it's a metadata request and the current queue is doing regular IO. */ - if (rq_is_meta(rq) && !cfqq->meta_pending) + if ((rq->cmd_flags & REQ_RW_META) && !cfqq->meta_pending) return true; /* @@ -3230,7 +3231,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct cfq_io_context *cic = RQ_CIC(rq); cfqd->rq_queued++; - if (rq_is_meta(rq)) + if (rq->cmd_flags & REQ_RW_META) cfqq->meta_pending++; cfq_update_io_thinktime(cfqd, cic); @@ -3365,7 +3366,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) unsigned long now; now = jiffies; - cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", !!rq_noidle(rq)); + cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", + !!(rq->cmd_flags & REQ_NOIDLE)); cfq_update_hw_tag(cfqd); @@ -3419,11 +3421,12 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) cfq_slice_expired(cfqd, 1); else if (sync && cfqq_empty && !cfq_close_cooperator(cfqd, cfqq)) { - cfqd->noidle_tree_requires_idle |= !rq_noidle(rq); + cfqd->noidle_tree_requires_idle |= + !(rq->cmd_flags & REQ_NOIDLE); /* * Idling is enabled for SYNC_WORKLOAD. * SYNC_NOIDLE_WORKLOAD idles at the end of the tree - * only if we processed at least one !rq_noidle request + * only if we processed at least one !REQ_NOIDLE request */ if (cfqd->serving_type == SYNC_WORKLOAD || cfqd->noidle_tree_requires_idle diff --git a/block/elevator.c b/block/elevator.c index 923a9139106c..aa99b59c03d6 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -428,7 +428,8 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); - if (blk_discard_rq(rq) != blk_discard_rq(pos)) + if ((rq->cmd_flags & REQ_DISCARD) != + (pos->cmd_flags & REQ_DISCARD)) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; @@ -558,7 +559,7 @@ void elv_requeue_request(struct request_queue *q, struct request *rq) */ if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]--; - if (blk_sorted_rq(rq)) + if (rq->cmd_flags & REQ_SORTED) elv_deactivate_rq(q, rq); } @@ -644,7 +645,8 @@ void elv_insert(struct request_queue *q, struct request *rq, int where) break; case ELEVATOR_INSERT_SORT: - BUG_ON(!blk_fs_request(rq) && !blk_discard_rq(rq)); + BUG_ON(rq->cmd_type != REQ_TYPE_FS && + !(rq->cmd_flags & REQ_DISCARD)); rq->cmd_flags |= REQ_SORTED; q->nr_sorted++; if (rq_mergeable(rq)) { @@ -716,7 +718,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where, /* * toggle ordered color */ - if (blk_barrier_rq(rq)) + if (rq->cmd_flags & REQ_HARDBARRIER) q->ordcolor ^= 1; /* @@ -729,7 +731,8 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where, * this request is scheduling boundary, update * end_sector */ - if (blk_fs_request(rq) || blk_discard_rq(rq)) { + if (rq->cmd_type == REQ_TYPE_FS || + (rq->cmd_flags & REQ_DISCARD)) { q->end_sector = rq_end_sector(rq); q->boundary_rq = rq; } @@ -843,7 +846,8 @@ void elv_completed_request(struct request_queue *q, struct request *rq) */ if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]--; - if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn) + if ((rq->cmd_flags & REQ_SORTED) && + e->ops->elevator_completed_req_fn) e->ops->elevator_completed_req_fn(q, rq); } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index a54273d2c3c6..a5c08b082edb 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1111,7 +1111,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev) */ static int atapi_drain_needed(struct request *rq) { - if (likely(!blk_pc_request(rq))) + if (likely(rq->cmd_type != REQ_TYPE_BLOCK_PC)) return 0; if (!blk_rq_bytes(rq) || (rq->cmd_flags & REQ_RW)) diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 10a0268a1f92..11b377762b8e 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1783,7 +1783,7 @@ static void cciss_softirq_done(struct request *rq) #endif /* CCISS_DEBUG */ /* set the residual count for pc requests */ - if (blk_pc_request(rq)) + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) rq->resid_len = cmd->err_info->ResidualCnt; blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO); @@ -2983,7 +2983,7 @@ static inline int evaluate_target_status(ctlr_info_t *h, driver_byte = DRIVER_OK; msg_byte = cmd->err_info->CommandStatus; /* correct? seems too device specific */ - if (blk_pc_request(cmd->rq)) + if (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) host_byte = DID_PASSTHROUGH; else host_byte = DID_OK; @@ -2992,7 +2992,7 @@ static inline int evaluate_target_status(ctlr_info_t *h, host_byte, driver_byte); if (cmd->err_info->ScsiStatus != SAM_STAT_CHECK_CONDITION) { - if (!blk_pc_request(cmd->rq)) + if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC) printk(KERN_WARNING "cciss: cmd %p " "has SCSI Status 0x%x\n", cmd, cmd->err_info->ScsiStatus); @@ -3002,15 +3002,17 @@ static inline int evaluate_target_status(ctlr_info_t *h, /* check the sense key */ sense_key = 0xf & cmd->err_info->SenseInfo[2]; /* no status or recovered error */ - if (((sense_key == 0x0) || (sense_key == 0x1)) && !blk_pc_request(cmd->rq)) + if (((sense_key == 0x0) || (sense_key == 0x1)) && + (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC)) error_value = 0; if (check_for_unit_attention(h, cmd)) { - *retry_cmd = !blk_pc_request(cmd->rq); + *retry_cmd = !(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC); return 0; } - if (!blk_pc_request(cmd->rq)) { /* Not SG_IO or similar? */ + /* Not SG_IO or similar? */ + if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC) { if (error_value != 0) printk(KERN_WARNING "cciss: cmd %p has CHECK CONDITION" " sense key = 0x%x\n", cmd, sense_key); @@ -3052,7 +3054,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, rq->errors = evaluate_target_status(h, cmd, &retry_cmd); break; case CMD_DATA_UNDERRUN: - if (blk_fs_request(cmd->rq)) { + if (cmd->rq->cmd_type == REQ_TYPE_FS) { printk(KERN_WARNING "cciss: cmd %p has" " completed with data underrun " "reported\n", cmd); @@ -3060,7 +3062,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, } break; case CMD_DATA_OVERRUN: - if (blk_fs_request(cmd->rq)) + if (cmd->rq->cmd_type == REQ_TYPE_FS) printk(KERN_WARNING "cciss: cmd %p has" " completed with data overrun " "reported\n", cmd); @@ -3070,42 +3072,48 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "reported invalid\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_PROTOCOL_ERR: printk(KERN_WARNING "cciss: cmd %p has " "protocol error \n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_HARDWARE_ERR: printk(KERN_WARNING "cciss: cmd %p had " " hardware error\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_CONNECTION_LOST: printk(KERN_WARNING "cciss: cmd %p had " "connection lost\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_ABORTED: printk(KERN_WARNING "cciss: cmd %p was " "aborted\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ABORT); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ABORT); break; case CMD_ABORT_FAILED: printk(KERN_WARNING "cciss: cmd %p reports " "abort failed\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_UNSOLICITED_ABORT: printk(KERN_WARNING "cciss%d: unsolicited " @@ -3121,13 +3129,15 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "many times\n", h->ctlr, cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ABORT); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ABORT); break; case CMD_TIMEOUT: printk(KERN_WARNING "cciss: cmd %p timedout\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; default: printk(KERN_WARNING "cciss: cmd %p returned " @@ -3135,7 +3145,8 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, cmd->err_info->CommandStatus); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); } after_error_processing: @@ -3294,7 +3305,7 @@ static void do_cciss_request(struct request_queue *q) c->Header.SGList = h->max_cmd_sgentries; set_performant_mode(h, c); - if (likely(blk_fs_request(creq))) { + if (likely(creq->cmd_type == REQ_TYPE_FS)) { if(h->cciss_read == CCISS_READ_10) { c->Request.CDB[1] = 0; c->Request.CDB[2] = (start_blk >> 24) & 0xff; /* MSB */ @@ -3324,7 +3335,7 @@ static void do_cciss_request(struct request_queue *q) c->Request.CDB[13]= blk_rq_sectors(creq) & 0xff; c->Request.CDB[14] = c->Request.CDB[15] = 0; } - } else if (blk_pc_request(creq)) { + } else if (creq->cmd_type == REQ_TYPE_BLOCK_PC) { c->Request.CDBLen = creq->cmd_len; memcpy(c->Request.CDB, creq->cmd, BLK_MAX_CDB); } else { diff --git a/drivers/block/hd.c b/drivers/block/hd.c index 81c78b3ce2df..30ec6b37424e 100644 --- a/drivers/block/hd.c +++ b/drivers/block/hd.c @@ -627,7 +627,7 @@ repeat: req_data_dir(req) == READ ? "read" : "writ", cyl, head, sec, nsect, req->buffer); #endif - if (blk_fs_request(req)) { + if (req->cmd_type == REQ_TYPE_FS) { switch (rq_data_dir(req)) { case READ: hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ, diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c index 28db925dbdad..b82c5ce5e9df 100644 --- a/drivers/block/mg_disk.c +++ b/drivers/block/mg_disk.c @@ -670,7 +670,7 @@ static void mg_request_poll(struct request_queue *q) break; } - if (unlikely(!blk_fs_request(host->req))) { + if (unlikely(host->req->cmd_type != REQ_TYPE_FS)) { mg_end_request_cur(host, -EIO); continue; } @@ -756,7 +756,7 @@ static void mg_request(struct request_queue *q) continue; } - if (unlikely(!blk_fs_request(req))) { + if (unlikely(req->cmd_type != REQ_TYPE_FS)) { mg_end_request_cur(host, -EIO); continue; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 218d091f3c52..2e74e7d475ca 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -448,7 +448,7 @@ static void nbd_clear_que(struct nbd_device *lo) static void nbd_handle_req(struct nbd_device *lo, struct request *req) { - if (!blk_fs_request(req)) + if (req->cmd_type != REQ_TYPE_FS) goto error_out; nbd_cmd(req) = NBD_CMD_READ; diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c index 6cd8b705b11b..819002ba3433 100644 --- a/drivers/block/osdblk.c +++ b/drivers/block/osdblk.c @@ -310,7 +310,8 @@ static void osdblk_rq_fn(struct request_queue *q) break; /* filter out block requests we don't understand */ - if (!blk_fs_request(rq) && !blk_barrier_rq(rq)) { + if (rq->cmd_type != REQ_TYPE_FS && + !(rq->cmd_flags & REQ_HARDBARRIER)) { blk_end_request_all(rq, 0); continue; } diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index c1e5cd029b23..4e8b9bff3abe 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -439,7 +439,7 @@ static char *pd_buf; /* buffer for request in progress */ static enum action do_pd_io_start(void) { - if (blk_special_request(pd_req)) { + if (pd_req->cmd_type == REQ_TYPE_SPECIAL) { phase = pd_special; return pd_special(); } diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 3b419e3fffa1..5f208c0bf156 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -196,7 +196,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev, dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__); while ((req = blk_fetch_request(q))) { - if (blk_fs_request(req)) { + if (req->cmd_type == REQ_TYPE_FS) { if (ps3disk_submit_request_sg(dev, req)) break; } else if (req->cmd_type == REQ_TYPE_LINUX_BLOCK && diff --git a/drivers/block/ub.c b/drivers/block/ub.c index 0536b5b29adc..034b34440ffa 100644 --- a/drivers/block/ub.c +++ b/drivers/block/ub.c @@ -648,7 +648,7 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq) return 0; } - if (lun->changed && !blk_pc_request(rq)) { + if (lun->changed && rq->cmd_type != REQ_TYPE_BLOCK_PC) blk_start_request(rq); ub_end_rq(rq, SAM_STAT_CHECK_CONDITION); return 0; @@ -684,7 +684,7 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq) } urq->nsg = n_elem; - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { ub_cmd_build_packet(sc, lun, cmd, urq); } else { ub_cmd_build_block(sc, lun, cmd, urq); @@ -781,7 +781,7 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd) rq = urq->rq; if (cmd->error == 0) { - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { if (cmd->act_len >= rq->resid_len) rq->resid_len = 0; else @@ -795,7 +795,7 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd) } } } else { - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { /* UB_SENSE_SIZE is smaller than SCSI_SENSE_BUFFERSIZE */ memcpy(rq->sense, sc->top_sense, UB_SENSE_SIZE); rq->sense_len = UB_SENSE_SIZE; diff --git a/drivers/block/viodasd.c b/drivers/block/viodasd.c index 788d93882ab9..5663d3c284c8 100644 --- a/drivers/block/viodasd.c +++ b/drivers/block/viodasd.c @@ -361,7 +361,7 @@ static void do_viodasd_request(struct request_queue *q) if (req == NULL) return; /* check that request contains a valid command */ - if (!blk_fs_request(req)) { + if (req->cmd_type != REQ_TYPE_FS) { viodasd_end_request(req, -EIO, blk_rq_sectors(req)); continue; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 258bc2ae2885..774144334ece 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -65,13 +65,16 @@ static void blk_done(struct virtqueue *vq) break; } - if (blk_pc_request(vbr->req)) { + switch (vbr->req->cmd_type) { + case REQ_TYPE_BLOCK_PC: vbr->req->resid_len = vbr->in_hdr.residual; vbr->req->sense_len = vbr->in_hdr.sense_len; vbr->req->errors = vbr->in_hdr.errors; - } - if (blk_special_request(vbr->req)) + break; + case REQ_TYPE_SPECIAL: vbr->req->errors = (error != 0); + break; + } __blk_end_request_all(vbr->req, error); list_del(&vbr->list); @@ -123,7 +126,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk, BUG(); } - if (blk_barrier_rq(vbr->req)) + if (vbr->req->cmd_flags & REQ_HARDBARRIER) vbr->out_hdr.type |= VIRTIO_BLK_T_BARRIER; sg_set_buf(&vblk->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr)); @@ -134,12 +137,12 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk, * block, and before the normal inhdr we put the sense data and the * inhdr with additional status information before the normal inhdr. */ - if (blk_pc_request(vbr->req)) + if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) sg_set_buf(&vblk->sg[out++], vbr->req->cmd, vbr->req->cmd_len); num = blk_rq_map_sg(q, vbr->req, vblk->sg + out); - if (blk_pc_request(vbr->req)) { + if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) { sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96); sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr, sizeof(vbr->in_hdr)); diff --git a/drivers/block/xd.c b/drivers/block/xd.c index 18a80ff57ce8..4dc298376098 100644 --- a/drivers/block/xd.c +++ b/drivers/block/xd.c @@ -322,7 +322,7 @@ static void do_xd_request (struct request_queue * q) int res = -EIO; int retry; - if (!blk_fs_request(req)) + if (req->cmd_type != REQ_TYPE_FS) { goto done; if (block + count > get_capacity(req->rq_disk)) goto done; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 82ed403147c0..495533e66542 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -238,7 +238,7 @@ static int blkif_queue_request(struct request *req) ring_req->operation = rq_data_dir(req) ? BLKIF_OP_WRITE : BLKIF_OP_READ; - if (blk_barrier_rq(req)) + if (req->cmd_flags & REQ_HARDBARRIER) ring_req->operation = BLKIF_OP_WRITE_BARRIER; ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg); @@ -309,7 +309,7 @@ static void do_blkif_request(struct request_queue *rq) blk_start_request(req); - if (!blk_fs_request(req)) { + if (req->cmd_type != REQ_TYPE_FS) { __blk_end_request_all(req, -EIO); continue; } diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index a7b83c0a7eb5..ac278ac908d5 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -465,7 +465,7 @@ struct request *ace_get_next_request(struct request_queue * q) struct request *req; while ((req = blk_peek_request(q)) != NULL) { - if (blk_fs_request(req)) + if (req->cmd_type == REQ_TYPE_FS) break; blk_start_request(req); __blk_end_request_all(req, -EIO); diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 03c71f7698cb..7c05ddc63ae8 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -643,7 +643,7 @@ static void gdrom_request(struct request_queue *rq) struct request *req; while ((req = blk_fetch_request(rq)) != NULL) { - if (!blk_fs_request(req)) { + if (req->cmd_type != REQ_TYPE_FS) { printk(KERN_DEBUG "GDROM: Non-fs request ignored\n"); __blk_end_request_all(req, -EIO); continue; diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c index 451cd7071b1d..14e420168764 100644 --- a/drivers/cdrom/viocd.c +++ b/drivers/cdrom/viocd.c @@ -298,7 +298,7 @@ static void do_viocd_request(struct request_queue *q) struct request *req; while ((rwreq == 0) && ((req = blk_fetch_request(q)) != NULL)) { - if (!blk_fs_request(req)) + if (req->cmd_type != REQ_TYPE_FS) __blk_end_request_all(req, -EIO); else if (send_request(req) < 0) { printk(VIOCD_KERN_WARNING diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index f9daffd7d0e3..3117a894d20e 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -190,7 +190,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq) BUG_ON(sense_len > sizeof(*sense)); - if (blk_sense_request(rq) || drive->sense_rq_armed) + if (rq->cmd_type == REQ_TYPE_SENSE || drive->sense_rq_armed) return; memset(sense, 0, sizeof(*sense)); @@ -307,13 +307,16 @@ EXPORT_SYMBOL_GPL(ide_cd_expiry); int ide_cd_get_xferlen(struct request *rq) { - if (blk_fs_request(rq)) + switch (rq->cmd_type) + case REQ_TYPE_FS: return 32768; - else if (blk_sense_request(rq) || blk_pc_request(rq) || - rq->cmd_type == REQ_TYPE_ATA_PC) + case REQ_TYPE_SENSE: + case REQ_TYPE_BLOCK_PC: + case REQ_TYPE_ATA_PC: return blk_rq_bytes(rq); - else + default: return 0; + } } EXPORT_SYMBOL_GPL(ide_cd_get_xferlen); @@ -474,12 +477,12 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) if (uptodate == 0) drive->failed_pc = NULL; - if (blk_special_request(rq)) { + if (rq->cmd_type == REQ_TYPE_SPECIAL) rq->errors = 0; error = 0; } else { - if (blk_fs_request(rq) == 0 && uptodate <= 0) { + if (req->cmd_type != REQ_TYPE_FS && uptodate <= 0) { if (rq->errors == 0) rq->errors = -EIO; } diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 64207df8da82..26a3688de467 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -176,7 +176,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive, if (!sense->valid) break; if (failed_command == NULL || - !blk_fs_request(failed_command)) + failed_command->cmd_type != REQ_TYPE_FS) break; sector = (sense->information[0] << 24) | (sense->information[1] << 16) | @@ -292,7 +292,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) "stat 0x%x", rq->cmd[0], rq->cmd_type, err, stat); - if (blk_sense_request(rq)) { + if (rq->cmd_type == REQ_TYPE_SENSE) { /* * We got an error trying to get sense info from the drive * (probably while trying to recover from a former error). @@ -303,7 +303,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) } /* if we have an error, pass CHECK_CONDITION as the SCSI status byte */ - if (blk_pc_request(rq) && !rq->errors) + if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !rq->errors) rq->errors = SAM_STAT_CHECK_CONDITION; if (blk_noretry_request(rq)) @@ -311,13 +311,14 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) switch (sense_key) { case NOT_READY: - if (blk_fs_request(rq) && rq_data_dir(rq) == WRITE) { + if (rq->cmd_type == REQ_TYPE_FS && rq_data_dir(rq) == WRITE) { if (ide_cd_breathe(drive, rq)) return 1; } else { cdrom_saw_media_change(drive); - if (blk_fs_request(rq) && !blk_rq_quiet(rq)) + if (rq->cmd_type == REQ_TYPE_FS && + !(rq->cmd_flags & REQ_QUIET)) { printk(KERN_ERR PFX "%s: tray open\n", drive->name); } @@ -326,7 +327,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) case UNIT_ATTENTION: cdrom_saw_media_change(drive); - if (blk_fs_request(rq) == 0) + if (rq->cmd_type != REQ_TYPE_FS) return 0; /* @@ -352,7 +353,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) * No point in retrying after an illegal request or data * protect error. */ - if (!blk_rq_quiet(rq)) + if (!(rq->cmd_flags & REQ_QUIET)) ide_dump_status(drive, "command error", stat); do_end_request = 1; break; @@ -361,20 +362,20 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) * No point in re-trying a zillion times on a bad sector. * If we got here the error is not correctable. */ - if (!blk_rq_quiet(rq)) + if (!(rq->cmd_flags & REQ_QUIET)) ide_dump_status(drive, "media error " "(bad sector)", stat); do_end_request = 1; break; case BLANK_CHECK: /* disk appears blank? */ - if (!blk_rq_quiet(rq)) + if (!(rq->cmd_flags & REQ_QUIET)) ide_dump_status(drive, "media error (blank)", stat); do_end_request = 1; break; default: - if (blk_fs_request(rq) == 0) + if (req->cmd_type != REQ_TYPE_FS) break; if (err & ~ATA_ABORTED) { /* go to the default handler for other errors */ @@ -385,7 +386,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) do_end_request = 1; } - if (blk_fs_request(rq) == 0) { + if (rq->cmd_type != REQ_TYPE_FS) { rq->cmd_flags |= REQ_FAILED; do_end_request = 1; } @@ -525,7 +526,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) ide_expiry_t *expiry = NULL; int dma_error = 0, dma, thislen, uptodate = 0; int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0; - int sense = blk_sense_request(rq); + int sense = (rq->cmd_type == REQ_TYPE_SENSE); unsigned int timeout; u16 len; u8 ireason, stat; @@ -568,7 +569,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) ide_read_bcount_and_ireason(drive, &len, &ireason); - thislen = blk_fs_request(rq) ? len : cmd->nleft; + thislen = (rq->cmd_type == REQ_TYPE_FS) ? len : cmd->nleft; if (thislen > len) thislen = len; @@ -577,7 +578,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) /* If DRQ is clear, the command has completed. */ if ((stat & ATA_DRQ) == 0) { - if (blk_fs_request(rq)) { + if (rq->cmd_type == REQ_TYPE_FS) { /* * If we're not done reading/writing, complain. * Otherwise, complete the command normally. @@ -591,7 +592,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) rq->cmd_flags |= REQ_FAILED; uptodate = 0; } - } else if (!blk_pc_request(rq)) { + } else if (rq->cmd_type != REQ_TYPE_BLOCK_PC) { ide_cd_request_sense_fixup(drive, cmd); uptodate = cmd->nleft ? 0 : 1; @@ -640,7 +641,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) /* pad, if necessary */ if (len > 0) { - if (blk_fs_request(rq) == 0 || write == 0) + if (rq->cmd_type != REQ_TYPE_FS || write == 0) ide_pad_transfer(drive, write, len); else { printk(KERN_ERR PFX "%s: confused, missing data\n", @@ -649,11 +650,11 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) } } - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { timeout = rq->timeout; } else { timeout = ATAPI_WAIT_PC; - if (!blk_fs_request(rq)) + if (rq->cmd_type != REQ_TYPE_FS) expiry = ide_cd_expiry; } @@ -662,7 +663,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) return ide_started; out_end: - if (blk_pc_request(rq) && rc == 0) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC && rc == 0) { rq->resid_len = 0; blk_end_request_all(rq, 0); hwif->rq = NULL; @@ -670,7 +671,7 @@ out_end: if (sense && uptodate) ide_cd_complete_failed_rq(drive, rq); - if (blk_fs_request(rq)) { + if (rq->cmd_type == REQ_TYPE_FS) { if (cmd->nleft == 0) uptodate = 1; } else { @@ -682,7 +683,7 @@ out_end: ide_cd_error_cmd(drive, cmd); /* make sure it's fully ended */ - if (blk_fs_request(rq) == 0) { + if (rq->cmd_type != REQ_TYPE_FS) { rq->resid_len -= cmd->nbytes - cmd->nleft; if (uptodate == 0 && (cmd->tf_flags & IDE_TFLAG_WRITE)) rq->resid_len += cmd->last_xfer_len; @@ -742,7 +743,7 @@ static void cdrom_do_block_pc(ide_drive_t *drive, struct request *rq) ide_debug_log(IDE_DBG_PC, "rq->cmd[0]: 0x%x, rq->cmd_type: 0x%x", rq->cmd[0], rq->cmd_type); - if (blk_pc_request(rq)) + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) rq->cmd_flags |= REQ_QUIET; else rq->cmd_flags &= ~REQ_FAILED; @@ -783,21 +784,26 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq, if (drive->debug_mask & IDE_DBG_RQ) blk_dump_rq_flags(rq, "ide_cd_do_request"); - if (blk_fs_request(rq)) { + switch (rq->cmd_type) { + case REQ_TYPE_FS: if (cdrom_start_rw(drive, rq) == ide_stopped) goto out_end; - } else if (blk_sense_request(rq) || blk_pc_request(rq) || - rq->cmd_type == REQ_TYPE_ATA_PC) { + break; + case REQ_TYPE_SENSE: + case REQ_TYPE_BLOCK_PC: + case REQ_TYPE_ATA_PC: if (!rq->timeout) rq->timeout = ATAPI_WAIT_PC; cdrom_do_block_pc(drive, rq); - } else if (blk_special_request(rq)) { + break; + case REQ_TYPE_SPECIAL: /* right now this can only be a reset... */ uptodate = 1; goto out_end; - } else + default: BUG(); + } /* prepare sense request for this command */ ide_prep_sense(drive, rq); @@ -809,7 +815,7 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq, cmd.rq = rq; - if (blk_fs_request(rq) || blk_rq_bytes(rq)) { + if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) { ide_init_sg_cmd(&cmd, blk_rq_bytes(rq)); ide_map_sg(drive, &cmd); } @@ -1365,9 +1371,9 @@ static int ide_cdrom_prep_pc(struct request *rq) static int ide_cdrom_prep_fn(struct request_queue *q, struct request *rq) { - if (blk_fs_request(rq)) + if (rq->cmd_type == REQ_TYPE_FS) return ide_cdrom_prep_fs(q, rq); - else if (blk_pc_request(rq)) + else if (rq->cmd_type == REQ_TYPE_BLOCK_PC) return ide_cdrom_prep_pc(rq); return 0; diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 33d65039cce9..df3d91ba1c96 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -184,7 +184,7 @@ static ide_startstop_t ide_do_rw_disk(ide_drive_t *drive, struct request *rq, ide_hwif_t *hwif = drive->hwif; BUG_ON(drive->dev_flags & IDE_DFLAG_BLOCKED); - BUG_ON(!blk_fs_request(rq)); + BUG_ON(rq->cmd_type != REQ_TYPE_FS); ledtrig_ide_activity(); diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c index e9abf2c3c335..c0aa93fb7a60 100644 --- a/drivers/ide/ide-eh.c +++ b/drivers/ide/ide-eh.c @@ -122,7 +122,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat) return ide_stopped; /* retry only "normal" I/O: */ - if (!blk_fs_request(rq)) { + if (rq->cmd_type != REQ_TYPE_FS) { if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE) { struct ide_cmd *cmd = rq->special; @@ -146,7 +146,8 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err) { struct request *rq = drive->hwif->rq; - if (rq && blk_special_request(rq) && rq->cmd[0] == REQ_DRIVE_RESET) { + if (rq && rq->cmd_type == REQ_TYPE_SPECIAL && + rq->cmd[0] == REQ_DRIVE_RESET) { if (err <= 0 && rq->errors == 0) rq->errors = -EIO; ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq)); diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index 4713bdca20b6..c7d0737bb18a 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -73,7 +73,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc) drive->failed_pc = NULL; if (pc->c[0] == GPCMD_READ_10 || pc->c[0] == GPCMD_WRITE_10 || - (rq && blk_pc_request(rq))) + (rq && rq->cmd_type == REQ_TYPE_BLOCK_PC)) uptodate = 1; /* FIXME */ else if (pc->c[0] == GPCMD_REQUEST_SENSE) { @@ -98,7 +98,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc) "Aborting request!\n"); } - if (blk_special_request(rq)) + if (rq->cmd_type == REQ_TYPE_SPECIAL) rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL; return uptodate; @@ -247,14 +247,16 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, } else printk(KERN_ERR PFX "%s: I/O error\n", drive->name); - if (blk_special_request(rq)) { + if (rq->cmd_type == REQ_TYPE_SPECIAL) { rq->errors = 0; ide_complete_rq(drive, 0, blk_rq_bytes(rq)); return ide_stopped; } else goto out_end; } - if (blk_fs_request(rq)) { + + switch (rq->cmd_type) { + case REQ_TYPE_FS: if (((long)blk_rq_pos(rq) % floppy->bs_factor) || (blk_rq_sectors(rq) % floppy->bs_factor)) { printk(KERN_ERR PFX "%s: unsupported r/w rq size\n", @@ -263,13 +265,18 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, } pc = &floppy->queued_pc; idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block); - } else if (blk_special_request(rq) || blk_sense_request(rq)) { + break; + case REQ_TYPE_SPECIAL: + case REQ_TYPE_SENSE: pc = (struct ide_atapi_pc *)rq->special; - } else if (blk_pc_request(rq)) { + break; + case REQ_TYPE_BLOCK_PC: pc = &floppy->queued_pc; idefloppy_blockpc_cmd(floppy, pc, rq); - } else + break; + default: BUG(); + } ide_prep_sense(drive, rq); @@ -280,7 +287,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, cmd.rq = rq; - if (blk_fs_request(rq) || blk_rq_bytes(rq)) { + if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) { ide_init_sg_cmd(&cmd, blk_rq_bytes(rq)); ide_map_sg(drive, &cmd); } @@ -290,7 +297,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, return ide_floppy_issue_pc(drive, &cmd, pc); out_end: drive->failed_pc = NULL; - if (blk_fs_request(rq) == 0 && rq->errors == 0) + if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0) rq->errors = -EIO; ide_complete_rq(drive, -EIO, blk_rq_bytes(rq)); return ide_stopped; diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 172ac9218154..9304a7e54d9e 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -135,7 +135,7 @@ EXPORT_SYMBOL(ide_complete_rq); void ide_kill_rq(ide_drive_t *drive, struct request *rq) { - u8 drv_req = blk_special_request(rq) && rq->rq_disk; + u8 drv_req = (rq->cmd_type == REQ_TYPE_SPECIAL) && rq->rq_disk; u8 media = drive->media; drive->failed_pc = NULL; @@ -145,7 +145,7 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq) } else { if (media == ide_tape) rq->errors = IDE_DRV_ERROR_GENERAL; - else if (blk_fs_request(rq) == 0 && rq->errors == 0) + else if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0) rq->errors = -EIO; } @@ -307,7 +307,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq) { ide_startstop_t startstop; - BUG_ON(!blk_rq_started(rq)); + BUG_ON(!(rq->cmd_flags & REQ_STARTED)); #ifdef DEBUG printk("%s: start_request: current=0x%08lx\n", @@ -353,7 +353,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq) pm->pm_step == IDE_PM_COMPLETED) ide_complete_pm_rq(drive, rq); return startstop; - } else if (!rq->rq_disk && blk_special_request(rq)) + } else if (!rq->rq_disk && rq->cmd_type == REQ_TYPE_SPECIAL) { /* * TODO: Once all ULDs have been modified to * check for specific op codes rather than diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index 1c08311b0a0e..92406097efeb 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -191,10 +191,10 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq) #ifdef DEBUG_PM printk("%s: completing PM request, %s\n", drive->name, - blk_pm_suspend_request(rq) ? "suspend" : "resume"); + (rq->cmd_type == REQ_TYPE_PM_SUSPEND) ? "suspend" : "resume"); #endif spin_lock_irqsave(q->queue_lock, flags); - if (blk_pm_suspend_request(rq)) + if (rq->cmd_type == REQ_TYPE_PM_SUSPEND) blk_stop_queue(q); else drive->dev_flags &= ~IDE_DFLAG_BLOCKED; @@ -210,11 +210,11 @@ void ide_check_pm_state(ide_drive_t *drive, struct request *rq) { struct request_pm_state *pm = rq->special; - if (blk_pm_suspend_request(rq) && + if (rq->cmd_type == REQ_TYPE_PM_SUSPEND && pm->pm_step == IDE_PM_START_SUSPEND) /* Mark drive blocked when starting the suspend sequence. */ drive->dev_flags |= IDE_DFLAG_BLOCKED; - else if (blk_pm_resume_request(rq) && + else if (rq->cmd_type == REQ_TYPE_PM_RESUME && pm->pm_step == IDE_PM_START_RESUME) { /* * The first thing we do on wakeup is to wait for BSY bit to diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index b07232880ec9..635fd72d4728 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -577,7 +577,8 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive, rq->cmd[0], (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq)); - BUG_ON(!(blk_special_request(rq) || blk_sense_request(rq))); + BUG_ON(!(rq->cmd_type == REQ_TYPE_SPECIAL || + rq->cmd_type == REQ_TYPE_SENSE)); /* Retry a failed packet command */ if (drive->failed_pc && drive->pc->c[0] == REQUEST_SENSE) { diff --git a/drivers/md/dm.c b/drivers/md/dm.c index d21e1284604f..1e0e6dd51501 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -792,12 +792,12 @@ static void dm_end_request(struct request *clone, int error) { int rw = rq_data_dir(clone); int run_queue = 1; - bool is_barrier = blk_barrier_rq(clone); + bool is_barrier = clone->cmd_flags & REQ_HARDBARRIER; struct dm_rq_target_io *tio = clone->end_io_data; struct mapped_device *md = tio->md; struct request *rq = tio->orig; - if (blk_pc_request(rq) && !is_barrier) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !is_barrier) { rq->errors = clone->errors; rq->resid_len = clone->resid_len; @@ -844,7 +844,7 @@ void dm_requeue_unmapped_request(struct request *clone) struct request_queue *q = rq->q; unsigned long flags; - if (unlikely(blk_barrier_rq(clone))) { + if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) { /* * Barrier clones share an original request. * Leave it to dm_end_request(), which handles this special @@ -943,7 +943,7 @@ static void dm_complete_request(struct request *clone, int error) struct dm_rq_target_io *tio = clone->end_io_data; struct request *rq = tio->orig; - if (unlikely(blk_barrier_rq(clone))) { + if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) { /* * Barrier clones share an original request. So can't use * softirq_done with the original. @@ -972,7 +972,7 @@ void dm_kill_unmapped_request(struct request *clone, int error) struct dm_rq_target_io *tio = clone->end_io_data; struct request *rq = tio->orig; - if (unlikely(blk_barrier_rq(clone))) { + if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) { /* * Barrier clones share an original request. * Leave it to dm_end_request(), which handles this special diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index 8327e248520a..56645408d225 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -805,7 +805,8 @@ static void mspro_block_start(struct memstick_dev *card) static int mspro_block_prepare_req(struct request_queue *q, struct request *req) { - if (!blk_fs_request(req) && !blk_pc_request(req)) { + if (req->cmd_type != REQ_TYPE_FS && + req->cmd_type != REQ_TYPE_BLOCK_PC) { blk_dump_rq_flags(req, "MSPro unsupported request"); return BLKPREP_KILL; } diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c index fc593fbab696..108f0c2b2bfd 100644 --- a/drivers/message/i2o/i2o_block.c +++ b/drivers/message/i2o/i2o_block.c @@ -883,7 +883,7 @@ static void i2o_block_request_fn(struct request_queue *q) if (!req) break; - if (blk_fs_request(req)) { + if (req->cmd_type == REQ_TYPE_FS) { struct i2o_block_delayed_request *dreq; struct i2o_block_request *ireq = req->special; unsigned int queue_depth; diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index d6ded247d941..ec92bcbdeddb 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -32,7 +32,7 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) /* * We only like normal block requests. */ - if (!blk_fs_request(req)) { + if (req->cmd_type != REQ_TYPE_FS) { blk_dump_rq_flags(req, "MMC bad request"); return BLKPREP_KILL; } diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 03e19c1965cc..475af42745cb 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -73,14 +73,14 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, buf = req->buffer; - if (!blk_fs_request(req)) + if (req->cmd_type != REQ_TYPE_FS) return -EIO; if (blk_rq_pos(req) + blk_rq_cur_sectors(req) > get_capacity(req->rq_disk)) return -EIO; - if (blk_discard_rq(req)) + if (req->cmd_flags & REQ_DISCARD) return tr->discard(dev, block, nsect); switch(rq_data_dir(req)) { diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index a5d630f5f519..1b88af89d0c7 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -307,7 +307,7 @@ static int scsi_check_sense(struct scsi_cmnd *scmd) (sshdr.asc == 0x04) && (sshdr.ascq == 0x02)) return FAILED; - if (blk_barrier_rq(scmd->request)) + if (scmd->request->cmd_flags & REQ_HARDBARRIER) /* * barrier requests should always retry on UA * otherwise block will get a spurious error @@ -1318,16 +1318,16 @@ int scsi_noretry_cmd(struct scsi_cmnd *scmd) case DID_OK: break; case DID_BUS_BUSY: - return blk_failfast_transport(scmd->request); + return (scmd->request->cmd_flags & REQ_FAILFAST_TRANSPORT); case DID_PARITY: - return blk_failfast_dev(scmd->request); + return (scmd->request->cmd_flags & REQ_FAILFAST_DEV); case DID_ERROR: if (msg_byte(scmd->result) == COMMAND_COMPLETE && status_byte(scmd->result) == RESERVATION_CONFLICT) return 0; /* fall through */ case DID_SOFT_ERROR: - return blk_failfast_driver(scmd->request); + return (scmd->request->cmd_flags & REQ_FAILFAST_DRIVER); } switch (status_byte(scmd->result)) { @@ -1336,7 +1336,7 @@ int scsi_noretry_cmd(struct scsi_cmnd *scmd) * assume caller has checked sense and determinted * the check condition was retryable. */ - return blk_failfast_dev(scmd->request); + return (scmd->request->cmd_flags & REQ_FAILFAST_DEV); } return 0; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 1646fe7cbd4b..5f1160841b0e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -722,7 +722,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) sense_deferred = scsi_sense_is_deferred(&sshdr); } - if (blk_pc_request(req)) { /* SG_IO ioctl from block level */ + if (req->cmd_type == REQ_TYPE_BLOCK_PC) { /* SG_IO ioctl from block level */ req->errors = result; if (result) { if (sense_valid && req->sense) { @@ -757,7 +757,8 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) } } - BUG_ON(blk_bidi_rq(req)); /* bidi not support for !blk_pc_request yet */ + /* no bidi support for !REQ_TYPE_BLOCK_PC yet */ + BUG_ON(blk_bidi_rq(req)); /* * Next deal with any sectors which we were able to correctly diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 8802e48bc063..a3fdf4dc59da 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -485,7 +485,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) * Discard request come in as REQ_TYPE_FS but we turn them into * block PC requests to make life easier. */ - if (blk_discard_rq(rq)) + if (rq->cmd_flags & REQ_DISCARD) ret = sd_prepare_discard(rq); if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { @@ -636,7 +636,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[0] = VARIABLE_LENGTH_CMD; SCpnt->cmnd[7] = 0x18; SCpnt->cmnd[9] = (rq_data_dir(rq) == READ) ? READ_32 : WRITE_32; - SCpnt->cmnd[10] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + SCpnt->cmnd[10] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0); /* LBA */ SCpnt->cmnd[12] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0; @@ -661,7 +661,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[31] = (unsigned char) this_count & 0xff; } else if (block > 0xffffffff) { SCpnt->cmnd[0] += READ_16 - READ_6; - SCpnt->cmnd[1] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0); SCpnt->cmnd[2] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0; SCpnt->cmnd[3] = sizeof(block) > 4 ? (unsigned char) (block >> 48) & 0xff : 0; SCpnt->cmnd[4] = sizeof(block) > 4 ? (unsigned char) (block >> 40) & 0xff : 0; @@ -682,7 +682,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) this_count = 0xffff; SCpnt->cmnd[0] += READ_10 - READ_6; - SCpnt->cmnd[1] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0); SCpnt->cmnd[2] = (unsigned char) (block >> 24) & 0xff; SCpnt->cmnd[3] = (unsigned char) (block >> 16) & 0xff; SCpnt->cmnd[4] = (unsigned char) (block >> 8) & 0xff; @@ -691,7 +691,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[7] = (unsigned char) (this_count >> 8) & 0xff; SCpnt->cmnd[8] = (unsigned char) this_count & 0xff; } else { - if (unlikely(blk_fua_rq(rq))) { + if (unlikely(rq->cmd_flags & REQ_FUA)) { /* * This happens only if this drive failed * 10byte rw command with ILLEGAL_REQUEST @@ -1112,7 +1112,7 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) u64 bad_lba; int info_valid; - if (!blk_fs_request(scmd->request)) + if (scmd->request->cmd_type != REQ_TYPE_FS) return 0; info_valid = scsi_get_sense_info_fld(scmd->sense_buffer, diff --git a/drivers/scsi/sun3_NCR5380.c b/drivers/scsi/sun3_NCR5380.c index b5838d547c68..713620ed70d9 100644 --- a/drivers/scsi/sun3_NCR5380.c +++ b/drivers/scsi/sun3_NCR5380.c @@ -2022,7 +2022,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance) if((count > SUN3_DMA_MINSIZE) && (sun3_dma_setup_done != cmd)) { - if(blk_fs_request(cmd->request)) { + if (cmd->request->cmd_type == REQ_TYPE_FS) { sun3scsi_dma_setup(d, count, rq_data_dir(cmd->request)); sun3_dma_setup_done = cmd; diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c index e606cf0a2eb7..613f5880d135 100644 --- a/drivers/scsi/sun3_scsi.c +++ b/drivers/scsi/sun3_scsi.c @@ -524,7 +524,7 @@ static inline unsigned long sun3scsi_dma_xfer_len(unsigned long wanted, struct scsi_cmnd *cmd, int write_flag) { - if(blk_fs_request(cmd->request)) + if (cmd->request->cmd_type == REQ_TYPE_FS) return wanted; else return 0; diff --git a/drivers/scsi/sun3_scsi_vme.c b/drivers/scsi/sun3_scsi_vme.c index aaa4fd0dd1b9..7c526b8e30ac 100644 --- a/drivers/scsi/sun3_scsi_vme.c +++ b/drivers/scsi/sun3_scsi_vme.c @@ -458,7 +458,7 @@ static inline unsigned long sun3scsi_dma_xfer_len(unsigned long wanted, struct scsi_cmnd *cmd, int write_flag) { - if(blk_fs_request(cmd->request)) + if (cmd->request->cmd_type == REQ_TYPE_FS) return wanted; else return 0; diff --git a/drivers/staging/hv/blkvsc_drv.c b/drivers/staging/hv/blkvsc_drv.c index 61bd0be5fb18..a9aff90e58e0 100644 --- a/drivers/staging/hv/blkvsc_drv.c +++ b/drivers/staging/hv/blkvsc_drv.c @@ -823,7 +823,8 @@ static void blkvsc_init_rw(struct blkvsc_request *blkvsc_req) blkvsc_req->cmnd[0] = READ_16; } - blkvsc_req->cmnd[1] |= blk_fua_rq(blkvsc_req->req) ? 0x8 : 0; + blkvsc_req->cmnd[1] |= + (blkvsc_req->req->cmd_flags & REQ_FUA) ? 0x8 : 0; *(unsigned long long *)&blkvsc_req->cmnd[2] = cpu_to_be64(blkvsc_req->sector_start); @@ -839,7 +840,8 @@ static void blkvsc_init_rw(struct blkvsc_request *blkvsc_req) blkvsc_req->cmnd[0] = READ_10; } - blkvsc_req->cmnd[1] |= blk_fua_rq(blkvsc_req->req) ? 0x8 : 0; + blkvsc_req->cmnd[1] |= + (blkvsc_req->req->cmd_flags & REQ_FUA) ? 0x8 : 0; *(unsigned int *)&blkvsc_req->cmnd[2] = cpu_to_be32(blkvsc_req->sector_start); @@ -1286,7 +1288,7 @@ static void blkvsc_request(struct request_queue *queue) DPRINT_DBG(BLKVSC_DRV, "- req %p\n", req); blkdev = req->rq_disk->private_data; - if (blkdev->shutting_down || !blk_fs_request(req) || + if (blkdev->shutting_down || req->cmd_type != REQ_TYPE_FS || blkdev->media_not_present) { __blk_end_request_cur(req, 0); continue; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d7ae241a9e55..3ecd28ef9ba4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -604,33 +604,20 @@ enum { test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) -#define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) -#define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) -#define blk_special_request(rq) ((rq)->cmd_type == REQ_TYPE_SPECIAL) -#define blk_sense_request(rq) ((rq)->cmd_type == REQ_TYPE_SENSE) - -#define blk_failfast_dev(rq) ((rq)->cmd_flags & REQ_FAILFAST_DEV) -#define blk_failfast_transport(rq) ((rq)->cmd_flags & REQ_FAILFAST_TRANSPORT) -#define blk_failfast_driver(rq) ((rq)->cmd_flags & REQ_FAILFAST_DRIVER) -#define blk_noretry_request(rq) (blk_failfast_dev(rq) || \ - blk_failfast_transport(rq) || \ - blk_failfast_driver(rq)) -#define blk_rq_started(rq) ((rq)->cmd_flags & REQ_STARTED) -#define blk_rq_io_stat(rq) ((rq)->cmd_flags & REQ_IO_STAT) -#define blk_rq_quiet(rq) ((rq)->cmd_flags & REQ_QUIET) - -#define blk_account_rq(rq) (blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq))) - -#define blk_pm_suspend_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND) -#define blk_pm_resume_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_RESUME) +#define blk_noretry_request(rq) \ + ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ + REQ_FAILFAST_DRIVER)) + +#define blk_account_rq(rq) \ + (((rq)->cmd_flags & REQ_STARTED) && \ + ((rq)->cmd_type == REQ_TYPE_FS || \ + ((rq)->cmd_flags & REQ_DISCARD))) + #define blk_pm_request(rq) \ - (blk_pm_suspend_request(rq) || blk_pm_resume_request(rq)) + ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \ + (rq)->cmd_type == REQ_TYPE_PM_RESUME) #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) -#define blk_sorted_rq(rq) ((rq)->cmd_flags & REQ_SORTED) -#define blk_barrier_rq(rq) ((rq)->cmd_flags & REQ_HARDBARRIER) -#define blk_fua_rq(rq) ((rq)->cmd_flags & REQ_FUA) -#define blk_discard_rq(rq) ((rq)->cmd_flags & REQ_DISCARD) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) /* rq->queuelist of dequeued request must be list_empty() */ #define blk_queued_rq(rq) (!list_empty(&(rq)->queuelist)) @@ -652,9 +639,6 @@ static inline bool rq_is_sync(struct request *rq) return rw_is_sync(rq->cmd_flags); } -#define rq_is_meta(rq) ((rq)->cmd_flags & REQ_RW_META) -#define rq_noidle(rq) ((rq)->cmd_flags & REQ_NOIDLE) - static inline int blk_queue_full(struct request_queue *q, int sync) { if (sync) @@ -687,7 +671,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync) (REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \ - (blk_discard_rq(rq) || blk_fs_request((rq)))) + (((rq)->cmd_flags & REQ_DISCARD) || \ + (rq)->cmd_type == REQ_TYPE_FS)) /* * q->prep_rq_fn return values diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 416bf62d6d46..23faa67e8022 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -224,7 +224,7 @@ static inline int blk_trace_init_sysfs(struct device *dev) static inline int blk_cmd_buf_len(struct request *rq) { - return blk_pc_request(rq) ? rq->cmd_len * 3 : 1; + return (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? rq->cmd_len * 3 : 1; } extern void blk_dump_cmd(char *buf, struct request *rq); diff --git a/include/trace/events/block.h b/include/trace/events/block.h index d870a918559c..d8ce278515c3 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -25,8 +25,10 @@ DECLARE_EVENT_CLASS(block_rq_with_error, TP_fast_assign( __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; - __entry->sector = blk_pc_request(rq) ? 0 : blk_rq_pos(rq); - __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq); + __entry->sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + 0 : blk_rq_pos(rq); + __entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + 0 : blk_rq_sectors(rq); __entry->errors = rq->errors; blk_fill_rwbs_rq(__entry->rwbs, rq); @@ -109,9 +111,12 @@ DECLARE_EVENT_CLASS(block_rq, TP_fast_assign( __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; - __entry->sector = blk_pc_request(rq) ? 0 : blk_rq_pos(rq); - __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq); - __entry->bytes = blk_pc_request(rq) ? blk_rq_bytes(rq) : 0; + __entry->sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + 0 : blk_rq_pos(rq); + __entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + 0 : blk_rq_sectors(rq); + __entry->bytes = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_bytes(rq) : 0; blk_fill_rwbs_rq(__entry->rwbs, rq); blk_dump_cmd(__get_str(cmd), rq); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 638711c17504..4f149944cb89 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -661,10 +661,10 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, if (likely(!bt)) return; - if (blk_discard_rq(rq)) + if (rq->cmd_flags & REQ_DISCARD) rw |= (1 << BIO_RW_DISCARD); - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { what |= BLK_TC_ACT(BLK_TC_PC); __blk_add_trace(bt, 0, blk_rq_bytes(rq), rw, what, rq->errors, rq->cmd_len, rq->cmd); @@ -925,7 +925,7 @@ void blk_add_driver_data(struct request_queue *q, if (likely(!bt)) return; - if (blk_pc_request(rq)) + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) __blk_add_trace(bt, 0, blk_rq_bytes(rq), 0, BLK_TA_DRV_DATA, rq->errors, len, data); else @@ -1730,7 +1730,7 @@ void blk_dump_cmd(char *buf, struct request *rq) int len = rq->cmd_len; unsigned char *cmd = rq->cmd; - if (!blk_pc_request(rq)) { + if (rq->cmd_type != REQ_TYPE_BLOCK_PC) { buf[0] = '\0'; return; } @@ -1779,7 +1779,7 @@ void blk_fill_rwbs_rq(char *rwbs, struct request *rq) int rw = rq->cmd_flags & 0x03; int bytes; - if (blk_discard_rq(rq)) + if (rq->cmd_flags & REQ_DISCARD) rw |= (1 << BIO_RW_DISCARD); bytes = blk_rq_bytes(rq); -- cgit v1.2.3 From 7b6d91daee5cac6402186ff224c3af39d79f4a0e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 7 Aug 2010 18:20:39 +0200 Subject: block: unify flags for struct bio and struct request Remove the current bio flags and reuse the request flags for the bio, too. This allows to more easily trace the type of I/O from the filesystem down to the block driver. There were two flags in the bio that were missing in the requests: BIO_RW_UNPLUG and BIO_RW_AHEAD. Also I've renamed two request flags that had a superflous RW in them. Note that the flags are in bio.h despite having the REQ_ name - as blkdev.h includes bio.h that is the only way to go for now. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 2 +- block/blk-core.c | 37 +++-------- block/blk-map.c | 2 +- block/blk-merge.c | 2 +- block/cfq-iosched.c | 14 ++--- block/elevator.c | 3 +- drivers/ata/libata-scsi.c | 2 +- drivers/block/aoe/aoeblk.c | 2 +- drivers/block/brd.c | 2 +- drivers/block/drbd/drbd_actlog.c | 8 +-- drivers/block/drbd/drbd_main.c | 6 +- drivers/block/drbd/drbd_receiver.c | 22 +++---- drivers/block/drbd/drbd_req.c | 2 +- drivers/block/loop.c | 2 +- drivers/block/pktcdvd.c | 2 +- drivers/block/umem.c | 2 +- drivers/ide/ide-cd_ioctl.c | 2 +- drivers/ide/ide-floppy.c | 2 +- drivers/md/dm-io.c | 12 ++-- drivers/md/dm-kcopyd.c | 2 +- drivers/md/dm-raid1.c | 2 +- drivers/md/dm-stripe.c | 2 +- drivers/md/dm.c | 14 ++--- drivers/md/linear.c | 2 +- drivers/md/md.c | 10 +-- drivers/md/md.h | 4 +- drivers/md/multipath.c | 8 +-- drivers/md/raid0.c | 2 +- drivers/md/raid1.c | 22 +++---- drivers/md/raid10.c | 12 ++-- drivers/md/raid5.c | 2 +- drivers/scsi/osd/osd_initiator.c | 8 +-- fs/bio.c | 5 +- fs/btrfs/disk-io.c | 8 +-- fs/btrfs/inode.c | 6 +- fs/btrfs/volumes.c | 18 +++--- fs/exofs/ios.c | 2 +- fs/gfs2/log.c | 4 +- fs/gfs2/meta_io.c | 8 +-- fs/gfs2/ops_fstype.c | 2 +- fs/nilfs2/segbuf.c | 2 +- include/linux/bio.h | 125 +++++++++++++++++++++++-------------- include/linux/blkdev.h | 66 +------------------- include/linux/fs.h | 38 +++++------ kernel/power/block_io.c | 2 +- kernel/trace/blktrace.c | 27 ++++---- mm/page_io.c | 2 +- 47 files changed, 242 insertions(+), 289 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 74e404393172..7c6f4a714687 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -203,7 +203,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp) /* initialize proxy request and queue it */ blk_rq_init(q, rq); if (bio_data_dir(q->orig_bar_rq->bio) == WRITE) - rq->cmd_flags |= REQ_RW; + rq->cmd_flags |= REQ_WRITE; if (q->ordered & QUEUE_ORDERED_DO_FUA) rq->cmd_flags |= REQ_FUA; init_request_from_bio(rq, q->orig_bar_rq->bio); diff --git a/block/blk-core.c b/block/blk-core.c index dca43a31e725..66c3cfe94d0a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1140,25 +1140,9 @@ void init_request_from_bio(struct request *req, struct bio *bio) req->cpu = bio->bi_comp_cpu; req->cmd_type = REQ_TYPE_FS; - /* - * Inherit FAILFAST from bio (for read-ahead, and explicit - * FAILFAST). FAILFAST flags are identical for req and bio. - */ - if (bio_rw_flagged(bio, BIO_RW_AHEAD)) + req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK; + if (bio->bi_rw & REQ_RAHEAD) req->cmd_flags |= REQ_FAILFAST_MASK; - else - req->cmd_flags |= bio->bi_rw & REQ_FAILFAST_MASK; - - if (bio_rw_flagged(bio, BIO_RW_DISCARD)) - req->cmd_flags |= REQ_DISCARD; - if (bio_rw_flagged(bio, BIO_RW_BARRIER)) - req->cmd_flags |= REQ_HARDBARRIER; - if (bio_rw_flagged(bio, BIO_RW_SYNCIO)) - req->cmd_flags |= REQ_RW_SYNC; - if (bio_rw_flagged(bio, BIO_RW_META)) - req->cmd_flags |= REQ_RW_META; - if (bio_rw_flagged(bio, BIO_RW_NOIDLE)) - req->cmd_flags |= REQ_NOIDLE; req->errors = 0; req->__sector = bio->bi_sector; @@ -1181,12 +1165,12 @@ static int __make_request(struct request_queue *q, struct bio *bio) int el_ret; unsigned int bytes = bio->bi_size; const unsigned short prio = bio_prio(bio); - const bool sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); - const bool unplug = bio_rw_flagged(bio, BIO_RW_UNPLUG); + const bool sync = (bio->bi_rw & REQ_SYNC); + const bool unplug = (bio->bi_rw & REQ_UNPLUG); const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK; int rw_flags; - if (bio_rw_flagged(bio, BIO_RW_BARRIER) && + if ((bio->bi_rw & REQ_HARDBARRIER) && (q->next_ordered == QUEUE_ORDERED_NONE)) { bio_endio(bio, -EOPNOTSUPP); return 0; @@ -1200,7 +1184,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) spin_lock_irq(q->queue_lock); - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER)) || elv_queue_empty(q)) + if (unlikely((bio->bi_rw & REQ_HARDBARRIER)) || elv_queue_empty(q)) goto get_rq; el_ret = elv_merge(q, &req, bio); @@ -1275,7 +1259,7 @@ get_rq: */ rw_flags = bio_data_dir(bio); if (sync) - rw_flags |= REQ_RW_SYNC; + rw_flags |= REQ_SYNC; /* * Grab a free request. This is might sleep but can not fail. @@ -1464,7 +1448,7 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; } - if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) && + if (unlikely(!(bio->bi_rw & REQ_DISCARD) && nr_sectors > queue_max_hw_sectors(q))) { printk(KERN_ERR "bio too big device %s (%u > %u)\n", bdevname(bio->bi_bdev, b), @@ -1497,8 +1481,7 @@ static inline void __generic_make_request(struct bio *bio) if (bio_check_eod(bio, nr_sectors)) goto end_io; - if (bio_rw_flagged(bio, BIO_RW_DISCARD) && - !blk_queue_discard(q)) { + if ((bio->bi_rw & REQ_DISCARD) && !blk_queue_discard(q)) { err = -EOPNOTSUPP; goto end_io; } @@ -2365,7 +2348,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio) { /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */ - rq->cmd_flags |= bio->bi_rw & REQ_RW; + rq->cmd_flags |= bio->bi_rw & REQ_WRITE; if (bio_has_data(bio)) { rq->nr_phys_segments = bio_phys_segments(q, bio); diff --git a/block/blk-map.c b/block/blk-map.c index 9083cf0180cc..c65d7593f7f1 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -307,7 +307,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, return PTR_ERR(bio); if (rq_data_dir(rq) == WRITE) - bio->bi_rw |= (1 << BIO_RW); + bio->bi_rw |= (1 << REQ_WRITE); if (do_copy) rq->cmd_flags |= REQ_COPY_USER; diff --git a/block/blk-merge.c b/block/blk-merge.c index 87e4fb7d0e98..4852475521ea 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -180,7 +180,7 @@ new_segment: } if (q->dma_drain_size && q->dma_drain_needed(rq)) { - if (rq->cmd_flags & REQ_RW) + if (rq->cmd_flags & REQ_WRITE) memset(q->dma_drain_buffer, 0, q->dma_drain_size); sg->page_link &= ~0x02; diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index d4edeb8fceb8..eb4086f7dfef 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -458,7 +458,7 @@ static inline struct cfq_data *cic_to_cfqd(struct cfq_io_context *cic) */ static inline bool cfq_bio_sync(struct bio *bio) { - return bio_data_dir(bio) == READ || bio_rw_flagged(bio, BIO_RW_SYNCIO); + return bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC); } /* @@ -646,10 +646,10 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, return rq1; else if (rq_is_sync(rq2) && !rq_is_sync(rq1)) return rq2; - if ((rq1->cmd_flags & REQ_RW_META) && !(rq2->cmd_flags & REQ_RW_META)) + if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META)) return rq1; - else if ((rq2->cmd_flags & REQ_RW_META) && - !(rq1->cmd_flags & REQ_RW_META)) + else if ((rq2->cmd_flags & REQ_META) && + !(rq1->cmd_flags & REQ_META)) return rq2; s1 = blk_rq_pos(rq1); @@ -1485,7 +1485,7 @@ static void cfq_remove_request(struct request *rq) cfqq->cfqd->rq_queued--; cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), rq_is_sync(rq)); - if (rq->cmd_flags & REQ_RW_META) { + if (rq->cmd_flags & REQ_META) { WARN_ON(!cfqq->meta_pending); cfqq->meta_pending--; } @@ -3177,7 +3177,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, * So both queues are sync. Let the new request get disk time if * it's a metadata request and the current queue is doing regular IO. */ - if ((rq->cmd_flags & REQ_RW_META) && !cfqq->meta_pending) + if ((rq->cmd_flags & REQ_META) && !cfqq->meta_pending) return true; /* @@ -3231,7 +3231,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct cfq_io_context *cic = RQ_CIC(rq); cfqd->rq_queued++; - if (rq->cmd_flags & REQ_RW_META) + if (rq->cmd_flags & REQ_META) cfqq->meta_pending++; cfq_update_io_thinktime(cfqd, cic); diff --git a/block/elevator.c b/block/elevator.c index aa99b59c03d6..816a7c8d6394 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -79,8 +79,7 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio) /* * Don't merge file system requests and discard requests */ - if (bio_rw_flagged(bio, BIO_RW_DISCARD) != - bio_rw_flagged(rq->bio, BIO_RW_DISCARD)) + if ((bio->bi_rw & REQ_DISCARD) != (rq->bio->bi_rw & REQ_DISCARD)) return 0; /* diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index a5c08b082edb..0a8cd3484791 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1114,7 +1114,7 @@ static int atapi_drain_needed(struct request *rq) if (likely(rq->cmd_type != REQ_TYPE_BLOCK_PC)) return 0; - if (!blk_rq_bytes(rq) || (rq->cmd_flags & REQ_RW)) + if (!blk_rq_bytes(rq) || (rq->cmd_flags & REQ_WRITE)) return 0; return atapi_cmd_type(rq->cmd[0]) == ATAPI_MISC; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 035cefe4045a..65deffde60ac 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -173,7 +173,7 @@ aoeblk_make_request(struct request_queue *q, struct bio *bio) BUG(); bio_endio(bio, -ENXIO); return 0; - } else if (bio_rw_flagged(bio, BIO_RW_BARRIER)) { + } else if (bio->bi_rw & REQ_HARDBARRIER) { bio_endio(bio, -EOPNOTSUPP); return 0; } else if (bio->bi_io_vec == NULL) { diff --git a/drivers/block/brd.c b/drivers/block/brd.c index f1bf79d9bc0a..1b218c6b6820 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -340,7 +340,7 @@ static int brd_make_request(struct request_queue *q, struct bio *bio) get_capacity(bdev->bd_disk)) goto out; - if (unlikely(bio_rw_flagged(bio, BIO_RW_DISCARD))) { + if (unlikely(bio->bi_rw & REQ_DISCARD)) { err = 0; discard_from_brd(brd, sector, bio->bi_size); goto out; diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index df018990c422..9400845d602e 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -79,8 +79,8 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev, md_io.error = 0; if ((rw & WRITE) && !test_bit(MD_NO_BARRIER, &mdev->flags)) - rw |= (1 << BIO_RW_BARRIER); - rw |= ((1<bi_rw & REQ_HARDBARRIER) && !ok)) { /* Try again with no barrier */ dev_warn(DEV, "Barriers not supported on meta data device - disabling\n"); set_bit(MD_NO_BARRIER, &mdev->flags); - rw &= ~(1 << BIO_RW_BARRIER); + rw &= ~REQ_HARDBARRIER; bio_put(bio); goto retry; } diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 7258c95e895e..e2ab13d99d69 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2425,15 +2425,15 @@ int drbd_send_dblock(struct drbd_conf *mdev, struct drbd_request *req) /* NOTE: no need to check if barriers supported here as we would * not pass the test in make_request_common in that case */ - if (bio_rw_flagged(req->master_bio, BIO_RW_BARRIER)) { + if (req->master_bio->bi_rw & REQ_HARDBARRIER) { dev_err(DEV, "ASSERT FAILED would have set DP_HARDBARRIER\n"); /* dp_flags |= DP_HARDBARRIER; */ } - if (bio_rw_flagged(req->master_bio, BIO_RW_SYNCIO)) + if (req->master_bio->bi_rw & REQ_SYNC) dp_flags |= DP_RW_SYNC; /* for now handle SYNCIO and UNPLUG * as if they still were one and the same flag */ - if (bio_rw_flagged(req->master_bio, BIO_RW_UNPLUG)) + if (req->master_bio->bi_rw & REQ_UNPLUG) dp_flags |= DP_RW_SYNC; if (mdev->state.conn >= C_SYNC_SOURCE && mdev->state.conn <= C_PAUSED_SYNC_T) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index dff48701b84d..cba1deb7b271 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1180,7 +1180,7 @@ next_bio: bio->bi_sector = sector; bio->bi_bdev = mdev->ldev->backing_bdev; /* we special case some flags in the multi-bio case, see below - * (BIO_RW_UNPLUG, BIO_RW_BARRIER) */ + * (REQ_UNPLUG, REQ_HARDBARRIER) */ bio->bi_rw = rw; bio->bi_private = e; bio->bi_end_io = drbd_endio_sec; @@ -1209,16 +1209,16 @@ next_bio: bios = bios->bi_next; bio->bi_next = NULL; - /* strip off BIO_RW_UNPLUG unless it is the last bio */ + /* strip off REQ_UNPLUG unless it is the last bio */ if (bios) - bio->bi_rw &= ~(1<bi_rw &= ~REQ_UNPLUG; drbd_generic_make_request(mdev, fault_type, bio); - /* strip off BIO_RW_BARRIER, + /* strip off REQ_HARDBARRIER, * unless it is the first or last bio */ if (bios && bios->bi_next) - bios->bi_rw &= ~(1<bi_rw &= ~REQ_HARDBARRIER; } while (bios); maybe_kick_lo(mdev); return 0; @@ -1233,7 +1233,7 @@ fail: } /** - * w_e_reissue() - Worker callback; Resubmit a bio, without BIO_RW_BARRIER set + * w_e_reissue() - Worker callback; Resubmit a bio, without REQ_HARDBARRIER set * @mdev: DRBD device. * @w: work object. * @cancel: The connection will be closed anyways (unused in this callback) @@ -1245,7 +1245,7 @@ int w_e_reissue(struct drbd_conf *mdev, struct drbd_work *w, int cancel) __relea (and DE_BARRIER_IN_NEXT_EPOCH_ISSUED in the previous Epoch) so that we can finish that epoch in drbd_may_finish_epoch(). That is necessary if we already have a long chain of Epochs, before - we realize that BIO_RW_BARRIER is actually not supported */ + we realize that REQ_HARDBARRIER is actually not supported */ /* As long as the -ENOTSUPP on the barrier is reported immediately that will never trigger. If it is reported late, we will just @@ -1824,14 +1824,14 @@ static int receive_Data(struct drbd_conf *mdev, struct p_header *h) epoch = list_entry(e->epoch->list.prev, struct drbd_epoch, list); if (epoch == e->epoch) { set_bit(DE_CONTAINS_A_BARRIER, &e->epoch->flags); - rw |= (1<flags |= EE_IS_BARRIER; } else { if (atomic_read(&epoch->epoch_size) > 1 || !test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags)) { set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags); set_bit(DE_CONTAINS_A_BARRIER, &e->epoch->flags); - rw |= (1<flags |= EE_IS_BARRIER; } } @@ -1841,10 +1841,10 @@ static int receive_Data(struct drbd_conf *mdev, struct p_header *h) dp_flags = be32_to_cpu(p->dp_flags); if (dp_flags & DP_HARDBARRIER) { dev_err(DEV, "ASSERT FAILED would have submitted barrier request\n"); - /* rw |= (1<flags |= EE_MAY_SET_IN_SYNC; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 654f1ef5cbb0..f761d98a4e90 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -997,7 +997,7 @@ int drbd_make_request_26(struct request_queue *q, struct bio *bio) * because of those XXX, this is not yet enabled, * i.e. in drbd_init_set_defaults we set the NO_BARRIER_SUPP bit. */ - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER) && test_bit(NO_BARRIER_SUPP, &mdev->flags))) { + if (unlikely(bio->bi_rw & REQ_HARDBARRIER) && test_bit(NO_BARRIER_SUPP, &mdev->flags)) { /* dev_warn(DEV, "Rejecting barrier request as underlying device does not support\n"); */ bio_endio(bio, -EOPNOTSUPP); return 0; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 6120922f459f..fedfdb7d3cdf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -476,7 +476,7 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio) pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset; if (bio_rw(bio) == WRITE) { - bool barrier = bio_rw_flagged(bio, BIO_RW_BARRIER); + bool barrier = (bio->bi_rw & REQ_HARDBARRIER); struct file *file = lo->lo_backing_file; if (barrier) { diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 8a549db2aa78..9f3e4454274b 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1221,7 +1221,7 @@ static int pkt_start_recovery(struct packet_data *pkt) pkt->bio->bi_flags = 1 << BIO_UPTODATE; pkt->bio->bi_idx = 0; - BUG_ON(pkt->bio->bi_rw != (1 << BIO_RW)); + BUG_ON(pkt->bio->bi_rw != REQ_WRITE); BUG_ON(pkt->bio->bi_vcnt != pkt->frames); BUG_ON(pkt->bio->bi_size != pkt->frames * CD_FRAMESIZE); BUG_ON(pkt->bio->bi_end_io != pkt_end_io_packet_write); diff --git a/drivers/block/umem.c b/drivers/block/umem.c index 2f9470ff8f7c..8be57151f5d6 100644 --- a/drivers/block/umem.c +++ b/drivers/block/umem.c @@ -478,7 +478,7 @@ static void process_page(unsigned long data) le32_to_cpu(desc->local_addr)>>9, le32_to_cpu(desc->transfer_size)); dump_dmastat(card, control); - } else if (test_bit(BIO_RW, &bio->bi_rw) && + } else if ((bio->bi_rw & REQ_WRITE) && le32_to_cpu(desc->local_addr) >> 9 == card->init_size) { card->init_size += le32_to_cpu(desc->transfer_size) >> 9; diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c index 02712bf045c1..766b3deeb23c 100644 --- a/drivers/ide/ide-cd_ioctl.c +++ b/drivers/ide/ide-cd_ioctl.c @@ -454,7 +454,7 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi, touch it at all. */ if (cgc->data_direction == CGC_DATA_WRITE) - flags |= REQ_RW; + flags |= REQ_WRITE; if (cgc->sense) memset(cgc->sense, 0, sizeof(struct request_sense)); diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index c7d0737bb18a..5406b6ea3ad1 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -207,7 +207,7 @@ static void idefloppy_create_rw_cmd(ide_drive_t *drive, memcpy(rq->cmd, pc->c, 12); pc->rq = rq; - if (rq->cmd_flags & REQ_RW) + if (rq->cmd_flags & REQ_WRITE) pc->flags |= PC_FLAG_WRITING; pc->flags |= PC_FLAG_DMA_OK; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 10f457ca6af2..0590c75b0ab6 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -356,7 +356,7 @@ static void dispatch_io(int rw, unsigned int num_regions, BUG_ON(num_regions > DM_IO_MAX_REGIONS); if (sync) - rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); + rw |= REQ_SYNC | REQ_UNPLUG; /* * For multiple regions we need to be careful to rewind @@ -364,7 +364,7 @@ static void dispatch_io(int rw, unsigned int num_regions, */ for (i = 0; i < num_regions; i++) { *dp = old_pages; - if (where[i].count || (rw & (1 << BIO_RW_BARRIER))) + if (where[i].count || (rw & REQ_HARDBARRIER)) do_region(rw, i, where + i, dp, io); } @@ -412,8 +412,8 @@ retry: } set_current_state(TASK_RUNNING); - if (io->eopnotsupp_bits && (rw & (1 << BIO_RW_BARRIER))) { - rw &= ~(1 << BIO_RW_BARRIER); + if (io->eopnotsupp_bits && (rw & REQ_HARDBARRIER)) { + rw &= ~REQ_HARDBARRIER; goto retry; } @@ -479,8 +479,8 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp) * New collapsed (a)synchronous interface. * * If the IO is asynchronous (i.e. it has notify.fn), you must either unplug - * the queue with blk_unplug() some time later or set the BIO_RW_SYNC bit in - * io_req->bi_rw. If you fail to do one of these, the IO will be submitted to + * the queue with blk_unplug() some time later or set REQ_SYNC in +io_req->bi_rw. If you fail to do one of these, the IO will be submitted to * the disk after q->unplug_delay, which defaults to 3ms in blk-settings.c. */ int dm_io(struct dm_io_request *io_req, unsigned num_regions, diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index addf83475040..d8587bac5682 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -345,7 +345,7 @@ static int run_io_job(struct kcopyd_job *job) { int r; struct dm_io_request io_req = { - .bi_rw = job->rw | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG), + .bi_rw = job->rw | REQ_SYNC | REQ_UNPLUG, .mem.type = DM_IO_PAGE_LIST, .mem.ptr.pl = job->pages, .mem.offset = job->offset, diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index ddda531723dc..74136262d654 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1211,7 +1211,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, if (error == -EOPNOTSUPP) goto out; - if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD)) + if ((error == -EWOULDBLOCK) && (bio->bi_rw & REQ_RAHEAD)) goto out; if (unlikely(error)) { diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index e610725db766..d6e28d732b4d 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -284,7 +284,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio, if (!error) return 0; /* I/O complete */ - if ((error == -EWOULDBLOCK) && bio_rw_flagged(bio, BIO_RW_AHEAD)) + if ((error == -EWOULDBLOCK) && (bio->bi_rw & REQ_RAHEAD)) return error; if (error == -EOPNOTSUPP) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 1e0e6dd51501..d6f77baeafd6 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -614,7 +614,7 @@ static void dec_pending(struct dm_io *io, int error) */ spin_lock_irqsave(&md->deferred_lock, flags); if (__noflush_suspending(md)) { - if (!bio_rw_flagged(io->bio, BIO_RW_BARRIER)) + if (!(io->bio->bi_rw & REQ_HARDBARRIER)) bio_list_add_head(&md->deferred, io->bio); } else @@ -626,7 +626,7 @@ static void dec_pending(struct dm_io *io, int error) io_error = io->error; bio = io->bio; - if (bio_rw_flagged(bio, BIO_RW_BARRIER)) { + if (bio->bi_rw & REQ_HARDBARRIER) { /* * There can be just one barrier request so we use * a per-device variable for error reporting. @@ -1106,7 +1106,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector, clone->bi_sector = sector; clone->bi_bdev = bio->bi_bdev; - clone->bi_rw = bio->bi_rw & ~(1 << BIO_RW_BARRIER); + clone->bi_rw = bio->bi_rw & ~REQ_HARDBARRIER; clone->bi_vcnt = 1; clone->bi_size = to_bytes(len); clone->bi_io_vec->bv_offset = offset; @@ -1133,7 +1133,7 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector, clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs); __bio_clone(clone, bio); - clone->bi_rw &= ~(1 << BIO_RW_BARRIER); + clone->bi_rw &= ~REQ_HARDBARRIER; clone->bi_destructor = dm_bio_destructor; clone->bi_sector = sector; clone->bi_idx = idx; @@ -1301,7 +1301,7 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio) ci.map = dm_get_live_table(md); if (unlikely(!ci.map)) { - if (!bio_rw_flagged(bio, BIO_RW_BARRIER)) + if (!(bio->bi_rw & REQ_HARDBARRIER)) bio_io_error(bio); else if (!md->barrier_error) @@ -1414,7 +1414,7 @@ static int _dm_request(struct request_queue *q, struct bio *bio) * we have to queue this io for later. */ if (unlikely(test_bit(DMF_QUEUE_IO_TO_THREAD, &md->flags)) || - unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + unlikely(bio->bi_rw & REQ_HARDBARRIER)) { up_read(&md->io_lock); if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) && @@ -2296,7 +2296,7 @@ static void dm_wq_work(struct work_struct *work) if (dm_request_based(md)) generic_make_request(c); else { - if (bio_rw_flagged(c, BIO_RW_BARRIER)) + if (c->bi_rw & REQ_HARDBARRIER) process_barrier(md, c); else __split_and_process_bio(md, c); diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 7e0e057db9a7..ba19060bcf3f 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -294,7 +294,7 @@ static int linear_make_request (mddev_t *mddev, struct bio *bio) dev_info_t *tmp_dev; sector_t start_sector; - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { md_barrier_request(mddev, bio); return 0; } diff --git a/drivers/md/md.c b/drivers/md/md.c index cb20d0b0555a..1893af678779 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -353,7 +353,7 @@ static void md_submit_barrier(struct work_struct *ws) /* an empty barrier - all done */ bio_endio(bio, 0); else { - bio->bi_rw &= ~(1<bi_rw &= ~REQ_HARDBARRIER; if (mddev->pers->make_request(mddev, bio)) generic_make_request(bio); mddev->barrier = POST_REQUEST_BARRIER; @@ -675,11 +675,11 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, * if zero is reached. * If an error occurred, call md_error * - * As we might need to resubmit the request if BIO_RW_BARRIER + * As we might need to resubmit the request if REQ_HARDBARRIER * causes ENOTSUPP, we allocate a spare bio... */ struct bio *bio = bio_alloc(GFP_NOIO, 1); - int rw = (1<bi_bdev = rdev->bdev; bio->bi_sector = sector; @@ -691,7 +691,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, atomic_inc(&mddev->pending_writes); if (!test_bit(BarriersNotsupp, &rdev->flags)) { struct bio *rbio; - rw |= (1<bi_private = bio; rbio->bi_end_io = super_written_barrier; @@ -736,7 +736,7 @@ int sync_page_io(struct block_device *bdev, sector_t sector, int size, struct completion event; int ret; - rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); + rw |= REQ_SYNC | REQ_UNPLUG; bio->bi_bdev = bdev; bio->bi_sector = sector; diff --git a/drivers/md/md.h b/drivers/md/md.h index 10597bfec000..fc56e0f21c80 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -67,7 +67,7 @@ struct mdk_rdev_s #define Faulty 1 /* device is known to have a fault */ #define In_sync 2 /* device is in_sync with rest of array */ #define WriteMostly 4 /* Avoid reading if at all possible */ -#define BarriersNotsupp 5 /* BIO_RW_BARRIER is not supported */ +#define BarriersNotsupp 5 /* REQ_HARDBARRIER is not supported */ #define AllReserved 6 /* If whole device is reserved for * one array */ #define AutoDetected 7 /* added by auto-detect */ @@ -254,7 +254,7 @@ struct mddev_s * fails. Only supported */ struct bio *biolist; /* bios that need to be retried - * because BIO_RW_BARRIER is not supported + * because REQ_HARDBARRIER is not supported */ atomic_t recovery_active; /* blocks scheduled, but not written */ diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 410fb60699ac..0307d217e7a4 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -91,7 +91,7 @@ static void multipath_end_request(struct bio *bio, int error) if (uptodate) multipath_end_bh_io(mp_bh, 0); - else if (!bio_rw_flagged(bio, BIO_RW_AHEAD)) { + else if (!(bio->bi_rw & REQ_RAHEAD)) { /* * oops, IO error: */ @@ -142,7 +142,7 @@ static int multipath_make_request(mddev_t *mddev, struct bio * bio) struct multipath_bh * mp_bh; struct multipath_info *multipath; - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { md_barrier_request(mddev, bio); return 0; } @@ -163,7 +163,7 @@ static int multipath_make_request(mddev_t *mddev, struct bio * bio) mp_bh->bio = *bio; mp_bh->bio.bi_sector += multipath->rdev->data_offset; mp_bh->bio.bi_bdev = multipath->rdev->bdev; - mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT); + mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT; mp_bh->bio.bi_end_io = multipath_end_request; mp_bh->bio.bi_private = mp_bh; generic_make_request(&mp_bh->bio); @@ -398,7 +398,7 @@ static void multipathd (mddev_t *mddev) *bio = *(mp_bh->master_bio); bio->bi_sector += conf->multipaths[mp_bh->path].rdev->data_offset; bio->bi_bdev = conf->multipaths[mp_bh->path].rdev->bdev; - bio->bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT); + bio->bi_rw |= REQ_FAILFAST_TRANSPORT; bio->bi_end_io = multipath_end_request; bio->bi_private = mp_bh; generic_make_request(bio); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 563abed5a2cb..6f7af46d623c 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -483,7 +483,7 @@ static int raid0_make_request(mddev_t *mddev, struct bio *bio) struct strip_zone *zone; mdk_rdev_t *tmp_dev; - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { md_barrier_request(mddev, bio); return 0; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a948da8012de..73cc74ffc26b 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -787,7 +787,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) struct bio_list bl; struct page **behind_pages = NULL; const int rw = bio_data_dir(bio); - const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); + const bool do_sync = (bio->bi_rw & REQ_SYNC); bool do_barriers; mdk_rdev_t *blocked_rdev; @@ -822,7 +822,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) finish_wait(&conf->wait_barrier, &w); } if (unlikely(!mddev->barriers_work && - bio_rw_flagged(bio, BIO_RW_BARRIER))) { + (bio->bi_rw & REQ_HARDBARRIER))) { if (rw == WRITE) md_write_end(mddev); bio_endio(bio, -EOPNOTSUPP); @@ -877,7 +877,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset; read_bio->bi_bdev = mirror->rdev->bdev; read_bio->bi_end_io = raid1_end_read_request; - read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO); + read_bio->bi_rw = READ | do_sync; read_bio->bi_private = r1_bio; generic_make_request(read_bio); @@ -959,7 +959,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) atomic_set(&r1_bio->remaining, 0); atomic_set(&r1_bio->behind_remaining, 0); - do_barriers = bio_rw_flagged(bio, BIO_RW_BARRIER); + do_barriers = bio->bi_rw & REQ_HARDBARRIER; if (do_barriers) set_bit(R1BIO_Barrier, &r1_bio->state); @@ -975,8 +975,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) mbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset; mbio->bi_bdev = conf->mirrors[i].rdev->bdev; mbio->bi_end_io = raid1_end_write_request; - mbio->bi_rw = WRITE | (do_barriers << BIO_RW_BARRIER) | - (do_sync << BIO_RW_SYNCIO); + mbio->bi_rw = WRITE | do_barriers | do_sync; mbio->bi_private = r1_bio; if (behind_pages) { @@ -1633,7 +1632,7 @@ static void raid1d(mddev_t *mddev) sync_request_write(mddev, r1_bio); unplug = 1; } else if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) { - /* some requests in the r1bio were BIO_RW_BARRIER + /* some requests in the r1bio were REQ_HARDBARRIER * requests which failed with -EOPNOTSUPP. Hohumm.. * Better resubmit without the barrier. * We know which devices to resubmit for, because @@ -1641,7 +1640,7 @@ static void raid1d(mddev_t *mddev) * We already have a nr_pending reference on these rdevs. */ int i; - const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO); + const bool do_sync = (r1_bio->master_bio->bi_rw & REQ_SYNC); clear_bit(R1BIO_BarrierRetry, &r1_bio->state); clear_bit(R1BIO_Barrier, &r1_bio->state); for (i=0; i < conf->raid_disks; i++) @@ -1662,8 +1661,7 @@ static void raid1d(mddev_t *mddev) conf->mirrors[i].rdev->data_offset; bio->bi_bdev = conf->mirrors[i].rdev->bdev; bio->bi_end_io = raid1_end_write_request; - bio->bi_rw = WRITE | - (do_sync << BIO_RW_SYNCIO); + bio->bi_rw = WRITE | do_sync; bio->bi_private = r1_bio; r1_bio->bios[i] = bio; generic_make_request(bio); @@ -1698,7 +1696,7 @@ static void raid1d(mddev_t *mddev) (unsigned long long)r1_bio->sector); raid_end_bio_io(r1_bio); } else { - const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO); + const bool do_sync = r1_bio->master_bio->bi_rw & REQ_SYNC; r1_bio->bios[r1_bio->read_disk] = mddev->ro ? IO_BLOCKED : NULL; r1_bio->read_disk = disk; @@ -1715,7 +1713,7 @@ static void raid1d(mddev_t *mddev) bio->bi_sector = r1_bio->sector + rdev->data_offset; bio->bi_bdev = rdev->bdev; bio->bi_end_io = raid1_end_read_request; - bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO); + bio->bi_rw = READ | do_sync; bio->bi_private = r1_bio; unplug = 1; generic_make_request(bio); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 42e64e4e5e25..62ecb6650fd0 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -799,12 +799,12 @@ static int make_request(mddev_t *mddev, struct bio * bio) int i; int chunk_sects = conf->chunk_mask + 1; const int rw = bio_data_dir(bio); - const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO); + const bool do_sync = (bio->bi_rw & REQ_SYNC); struct bio_list bl; unsigned long flags; mdk_rdev_t *blocked_rdev; - if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) { + if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) { md_barrier_request(mddev, bio); return 0; } @@ -879,7 +879,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) mirror->rdev->data_offset; read_bio->bi_bdev = mirror->rdev->bdev; read_bio->bi_end_io = raid10_end_read_request; - read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO); + read_bio->bi_rw = READ | do_sync; read_bio->bi_private = r10_bio; generic_make_request(read_bio); @@ -947,7 +947,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) conf->mirrors[d].rdev->data_offset; mbio->bi_bdev = conf->mirrors[d].rdev->bdev; mbio->bi_end_io = raid10_end_write_request; - mbio->bi_rw = WRITE | (do_sync << BIO_RW_SYNCIO); + mbio->bi_rw = WRITE | do_sync; mbio->bi_private = r10_bio; atomic_inc(&r10_bio->remaining); @@ -1716,7 +1716,7 @@ static void raid10d(mddev_t *mddev) raid_end_bio_io(r10_bio); bio_put(bio); } else { - const bool do_sync = bio_rw_flagged(r10_bio->master_bio, BIO_RW_SYNCIO); + const bool do_sync = (r10_bio->master_bio->bi_rw & REQ_SYNC); bio_put(bio); rdev = conf->mirrors[mirror].rdev; if (printk_ratelimit()) @@ -1730,7 +1730,7 @@ static void raid10d(mddev_t *mddev) bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr + rdev->data_offset; bio->bi_bdev = rdev->bdev; - bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO); + bio->bi_rw = READ | do_sync; bio->bi_private = r10_bio; bio->bi_end_io = raid10_end_read_request; unplug = 1; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 96c690279fc6..20ac2f14376a 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3958,7 +3958,7 @@ static int make_request(mddev_t *mddev, struct bio * bi) const int rw = bio_data_dir(bi); int remaining; - if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) { + if (unlikely(bi->bi_rw & REQ_HARDBARRIER)) { /* Drain all pending writes. We only really need * to ensure they have been submitted, but this is * easier. diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c index ee4b6914667f..fda4de3440c4 100644 --- a/drivers/scsi/osd/osd_initiator.c +++ b/drivers/scsi/osd/osd_initiator.c @@ -716,7 +716,7 @@ static int _osd_req_list_objects(struct osd_request *or, return PTR_ERR(bio); } - bio->bi_rw &= ~(1 << BIO_RW); + bio->bi_rw &= ~REQ_WRITE; or->in.bio = bio; or->in.total_bytes = bio->bi_size; return 0; @@ -814,7 +814,7 @@ void osd_req_write(struct osd_request *or, { _osd_req_encode_common(or, OSD_ACT_WRITE, obj, offset, len); WARN_ON(or->out.bio || or->out.total_bytes); - WARN_ON(0 == bio_rw_flagged(bio, BIO_RW)); + WARN_ON(0 == (bio->bi_rw & REQ_WRITE)); or->out.bio = bio; or->out.total_bytes = len; } @@ -829,7 +829,7 @@ int osd_req_write_kern(struct osd_request *or, if (IS_ERR(bio)) return PTR_ERR(bio); - bio->bi_rw |= (1 << BIO_RW); /* FIXME: bio_set_dir() */ + bio->bi_rw |= REQ_WRITE; /* FIXME: bio_set_dir() */ osd_req_write(or, obj, offset, bio, len); return 0; } @@ -865,7 +865,7 @@ void osd_req_read(struct osd_request *or, { _osd_req_encode_common(or, OSD_ACT_READ, obj, offset, len); WARN_ON(or->in.bio || or->in.total_bytes); - WARN_ON(1 == bio_rw_flagged(bio, BIO_RW)); + WARN_ON(1 == (bio->bi_rw & REQ_WRITE)); or->in.bio = bio; or->in.total_bytes = len; } diff --git a/fs/bio.c b/fs/bio.c index e7bf6ca64dcf..8abb2dfb2e7c 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -843,7 +843,8 @@ struct bio *bio_copy_user_iov(struct request_queue *q, if (!bio) goto out_bmd; - bio->bi_rw |= (!write_to_vm << BIO_RW); + if (!write_to_vm) + bio->bi_rw |= REQ_WRITE; ret = 0; @@ -1024,7 +1025,7 @@ static struct bio *__bio_map_user_iov(struct request_queue *q, * set data direction, and check if mapped pages need bouncing */ if (!write_to_vm) - bio->bi_rw |= (1 << BIO_RW); + bio->bi_rw |= REQ_WRITE; bio->bi_bdev = bdev; bio->bi_flags |= (1 << BIO_USER_MAPPED); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 34f7c375567e..64f10082f048 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -480,7 +480,7 @@ static void end_workqueue_bio(struct bio *bio, int err) end_io_wq->work.func = end_workqueue_fn; end_io_wq->work.flags = 0; - if (bio->bi_rw & (1 << BIO_RW)) { + if (bio->bi_rw & REQ_WRITE) { if (end_io_wq->metadata) btrfs_queue_worker(&fs_info->endio_meta_write_workers, &end_io_wq->work); @@ -604,7 +604,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, atomic_inc(&fs_info->nr_async_submits); - if (rw & (1 << BIO_RW_SYNCIO)) + if (rw & REQ_SYNC) btrfs_set_work_high_prio(&async->work); btrfs_queue_worker(&fs_info->workers, &async->work); @@ -668,7 +668,7 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, bio, 1); BUG_ON(ret); - if (!(rw & (1 << BIO_RW))) { + if (!(rw & REQ_WRITE)) { /* * called for a read, do the setup so that checksum validation * can happen in the async kernel threads @@ -1427,7 +1427,7 @@ static void end_workqueue_fn(struct btrfs_work *work) * ram and up to date before trying to verify things. For * blocksize <= pagesize, it is basically a noop */ - if (!(bio->bi_rw & (1 << BIO_RW)) && end_io_wq->metadata && + if (!(bio->bi_rw & REQ_WRITE) && end_io_wq->metadata && !bio_ready_for_csum(bio)) { btrfs_queue_worker(&fs_info->endio_meta_workers, &end_io_wq->work); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1bff92ad4744..e975d7180a88 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1429,7 +1429,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0); BUG_ON(ret); - if (!(rw & (1 << BIO_RW))) { + if (!(rw & REQ_WRITE)) { if (bio_flags & EXTENT_BIO_COMPRESSED) { return btrfs_submit_compressed_read(inode, bio, mirror_num, bio_flags); @@ -1841,7 +1841,7 @@ static int btrfs_io_failed_hook(struct bio *failed_bio, bio->bi_size = 0; bio_add_page(bio, page, failrec->len, start - page_offset(page)); - if (failed_bio->bi_rw & (1 << BIO_RW)) + if (failed_bio->bi_rw & REQ_WRITE) rw = WRITE; else rw = READ; @@ -5642,7 +5642,7 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode, struct bio_vec *bvec = bio->bi_io_vec; u64 start; int skip_sum; - int write = rw & (1 << BIO_RW); + int write = rw & REQ_WRITE; int ret = 0; skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d6e3af8be95b..dd318ff280b2 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -258,7 +258,7 @@ loop_lock: BUG_ON(atomic_read(&cur->bi_cnt) == 0); - if (bio_rw_flagged(cur, BIO_RW_SYNCIO)) + if (cur->bi_rw & REQ_SYNC) num_sync_run++; submit_bio(cur->bi_rw, cur); @@ -2651,7 +2651,7 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, int max_errors = 0; struct btrfs_multi_bio *multi = NULL; - if (multi_ret && !(rw & (1 << BIO_RW))) + if (multi_ret && !(rw & REQ_WRITE)) stripes_allocated = 1; again: if (multi_ret) { @@ -2687,7 +2687,7 @@ again: mirror_num = 0; /* if our multi bio struct is too small, back off and try again */ - if (rw & (1 << BIO_RW)) { + if (rw & REQ_WRITE) { if (map->type & (BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_DUP)) { stripes_required = map->num_stripes; @@ -2697,7 +2697,7 @@ again: max_errors = 1; } } - if (multi_ret && (rw & (1 << BIO_RW)) && + if (multi_ret && (rw & REQ_WRITE) && stripes_allocated < stripes_required) { stripes_allocated = map->num_stripes; free_extent_map(em); @@ -2733,7 +2733,7 @@ again: num_stripes = 1; stripe_index = 0; if (map->type & BTRFS_BLOCK_GROUP_RAID1) { - if (unplug_page || (rw & (1 << BIO_RW))) + if (unplug_page || (rw & REQ_WRITE)) num_stripes = map->num_stripes; else if (mirror_num) stripe_index = mirror_num - 1; @@ -2744,7 +2744,7 @@ again: } } else if (map->type & BTRFS_BLOCK_GROUP_DUP) { - if (rw & (1 << BIO_RW)) + if (rw & REQ_WRITE) num_stripes = map->num_stripes; else if (mirror_num) stripe_index = mirror_num - 1; @@ -2755,7 +2755,7 @@ again: stripe_index = do_div(stripe_nr, factor); stripe_index *= map->sub_stripes; - if (unplug_page || (rw & (1 << BIO_RW))) + if (unplug_page || (rw & REQ_WRITE)) num_stripes = map->sub_stripes; else if (mirror_num) stripe_index += mirror_num - 1; @@ -2945,7 +2945,7 @@ static noinline int schedule_bio(struct btrfs_root *root, struct btrfs_pending_bios *pending_bios; /* don't bother with additional async steps for reads, right now */ - if (!(rw & (1 << BIO_RW))) { + if (!(rw & REQ_WRITE)) { bio_get(bio); submit_bio(rw, bio); bio_put(bio); @@ -2964,7 +2964,7 @@ static noinline int schedule_bio(struct btrfs_root *root, bio->bi_rw |= rw; spin_lock(&device->io_lock); - if (bio_rw_flagged(bio, BIO_RW_SYNCIO)) + if (bio->bi_rw & REQ_SYNC) pending_bios = &device->pending_sync_bios; else pending_bios = &device->pending_bios; diff --git a/fs/exofs/ios.c b/fs/exofs/ios.c index 4337cad7777b..e2732203fa93 100644 --- a/fs/exofs/ios.c +++ b/fs/exofs/ios.c @@ -599,7 +599,7 @@ static int _sbi_write_mirror(struct exofs_io_state *ios, int cur_comp) } else { bio = master_dev->bio; /* FIXME: bio_set_dir() */ - bio->bi_rw |= (1 << BIO_RW); + bio->bi_rw |= REQ_WRITE; } osd_req_write(or, &ios->obj, per_dev->offset, bio, diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index efc3539ac5a1..cde1248a6225 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -595,7 +595,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) goto skip_barrier; get_bh(bh); - submit_bh(WRITE_BARRIER | (1 << BIO_RW_META), bh); + submit_bh(WRITE_BARRIER | REQ_META, bh); wait_on_buffer(bh); if (buffer_eopnotsupp(bh)) { clear_buffer_eopnotsupp(bh); @@ -605,7 +605,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) lock_buffer(bh); skip_barrier: get_bh(bh); - submit_bh(WRITE_SYNC | (1 << BIO_RW_META), bh); + submit_bh(WRITE_SYNC | REQ_META, bh); wait_on_buffer(bh); } if (!buffer_uptodate(bh)) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 18176d0b75d7..f3b071f921aa 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -36,8 +36,8 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb { struct buffer_head *bh, *head; int nr_underway = 0; - int write_op = (1 << BIO_RW_META) | ((wbc->sync_mode == WB_SYNC_ALL ? - WRITE_SYNC_PLUG : WRITE)); + int write_op = REQ_META | + (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC_PLUG : WRITE); BUG_ON(!PageLocked(page)); BUG_ON(!page_has_buffers(page)); @@ -225,7 +225,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, } bh->b_end_io = end_buffer_read_sync; get_bh(bh); - submit_bh(READ_SYNC | (1 << BIO_RW_META), bh); + submit_bh(READ_SYNC | REQ_META, bh); if (!(flags & DIO_WAIT)) return 0; @@ -432,7 +432,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen) if (buffer_uptodate(first_bh)) goto out; if (!buffer_locked(first_bh)) - ll_rw_block(READ_SYNC | (1 << BIO_RW_META), 1, &first_bh); + ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh); dblock++; extlen--; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 3593b3a7290e..fd4f8946abf5 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -275,7 +275,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector) bio->bi_end_io = end_bio_io_page; bio->bi_private = page; - submit_bio(READ_SYNC | (1 << BIO_RW_META), bio); + submit_bio(READ_SYNC | REQ_META, bio); wait_on_page_locked(page); bio_put(bio); if (!PageUptodate(page)) { diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 2e6a2723b8fa..4588fb9e93df 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -508,7 +508,7 @@ static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf, * Last BIO is always sent through the following * submission. */ - rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); + rw |= REQ_SYNC | REQ_UNPLUG; res = nilfs_segbuf_submit_bio(segbuf, &wi, rw); } diff --git a/include/linux/bio.h b/include/linux/bio.h index 7fc5606e6ea5..4d379c8250ae 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -138,55 +138,83 @@ struct bio { #define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) /* - * bio bi_rw flags - * - * bit 0 -- data direction - * If not set, bio is a read from device. If set, it's a write to device. - * bit 1 -- fail fast device errors - * bit 2 -- fail fast transport errors - * bit 3 -- fail fast driver errors - * bit 4 -- rw-ahead when set - * bit 5 -- barrier - * Insert a serialization point in the IO queue, forcing previously - * submitted IO to be completed before this one is issued. - * bit 6 -- synchronous I/O hint. - * bit 7 -- Unplug the device immediately after submitting this bio. - * bit 8 -- metadata request - * Used for tracing to differentiate metadata and data IO. May also - * get some preferential treatment in the IO scheduler - * bit 9 -- discard sectors - * Informs the lower level device that this range of sectors is no longer - * used by the file system and may thus be freed by the device. Used - * for flash based storage. - * Don't want driver retries for any fast fail whatever the reason. - * bit 10 -- Tell the IO scheduler not to wait for more requests after this - one has been submitted, even if it is a SYNC request. + * Request flags. For use in the cmd_flags field of struct request, and in + * bi_rw of struct bio. Note that some flags are only valid in either one. */ -enum bio_rw_flags { - BIO_RW, - BIO_RW_FAILFAST_DEV, - BIO_RW_FAILFAST_TRANSPORT, - BIO_RW_FAILFAST_DRIVER, - /* above flags must match REQ_* */ - BIO_RW_AHEAD, - BIO_RW_BARRIER, - BIO_RW_SYNCIO, - BIO_RW_UNPLUG, - BIO_RW_META, - BIO_RW_DISCARD, - BIO_RW_NOIDLE, +enum rq_flag_bits { + /* common flags */ + __REQ_WRITE, /* not set, read. set, write */ + __REQ_FAILFAST_DEV, /* no driver retries of device errors */ + __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ + __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ + + __REQ_HARDBARRIER, /* may not be passed by drive either */ + __REQ_SYNC, /* request is sync (sync write or read) */ + __REQ_META, /* metadata io request */ + __REQ_DISCARD, /* request to discard sectors */ + __REQ_NOIDLE, /* don't anticipate more IO after this one */ + + /* bio only flags */ + __REQ_UNPLUG, /* unplug the immediately after submission */ + __REQ_RAHEAD, /* read ahead, can fail anytime */ + + /* request only flags */ + __REQ_SORTED, /* elevator knows about this request */ + __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ + __REQ_FUA, /* forced unit access */ + __REQ_NOMERGE, /* don't touch this for merging */ + __REQ_STARTED, /* drive already may have started this one */ + __REQ_DONTPREP, /* don't call prep for this one */ + __REQ_QUEUED, /* uses queueing */ + __REQ_ELVPRIV, /* elevator private data attached */ + __REQ_FAILED, /* set if the request failed */ + __REQ_QUIET, /* don't worry about errors */ + __REQ_PREEMPT, /* set for "ide_preempt" requests */ + __REQ_ORDERED_COLOR, /* is before or after barrier */ + __REQ_ALLOCED, /* request came from our alloc pool */ + __REQ_COPY_USER, /* contains copies of user pages */ + __REQ_INTEGRITY, /* integrity metadata has been remapped */ + __REQ_IO_STAT, /* account I/O stat */ + __REQ_MIXED_MERGE, /* merge of different types, fail separately */ + __REQ_NR_BITS, /* stops here */ }; -/* - * First four bits must match between bio->bi_rw and rq->cmd_flags, make - * that explicit here. - */ -#define BIO_RW_RQ_MASK 0xf - -static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag) -{ - return (bio->bi_rw & (1 << flag)) != 0; -} +#define REQ_WRITE (1 << __REQ_WRITE) +#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) +#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) +#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) +#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) +#define REQ_SYNC (1 << __REQ_SYNC) +#define REQ_META (1 << __REQ_META) +#define REQ_DISCARD (1 << __REQ_DISCARD) +#define REQ_NOIDLE (1 << __REQ_NOIDLE) + +#define REQ_FAILFAST_MASK \ + (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) +#define REQ_COMMON_MASK \ + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ + REQ_META| REQ_DISCARD | REQ_NOIDLE) + +#define REQ_UNPLUG (1 << __REQ_UNPLUG) +#define REQ_RAHEAD (1 << __REQ_RAHEAD) + +#define REQ_SORTED (1 << __REQ_SORTED) +#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) +#define REQ_FUA (1 << __REQ_FUA) +#define REQ_NOMERGE (1 << __REQ_NOMERGE) +#define REQ_STARTED (1 << __REQ_STARTED) +#define REQ_DONTPREP (1 << __REQ_DONTPREP) +#define REQ_QUEUED (1 << __REQ_QUEUED) +#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) +#define REQ_FAILED (1 << __REQ_FAILED) +#define REQ_QUIET (1 << __REQ_QUIET) +#define REQ_PREEMPT (1 << __REQ_PREEMPT) +#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) +#define REQ_ALLOCED (1 << __REQ_ALLOCED) +#define REQ_COPY_USER (1 << __REQ_COPY_USER) +#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) +#define REQ_IO_STAT (1 << __REQ_IO_STAT) +#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) /* * upper 16 bits of bi_rw define the io priority of this bio @@ -211,7 +239,10 @@ static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag) #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) -#define bio_empty_barrier(bio) (bio_rw_flagged(bio, BIO_RW_BARRIER) && !bio_has_data(bio) && !bio_rw_flagged(bio, BIO_RW_DISCARD)) +#define bio_empty_barrier(bio) \ + ((bio->bi_rw & REQ_HARDBARRIER) && \ + !bio_has_data(bio) && \ + !(bio->bi_rw & REQ_DISCARD)) static inline unsigned int bio_cur_bytes(struct bio *bio) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3ecd28ef9ba4..3fc0f5908619 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -84,70 +84,6 @@ enum { REQ_LB_OP_FLUSH = 0x41, /* flush request */ }; -/* - * request type modified bits. first four bits match BIO_RW* bits, important - */ -enum rq_flag_bits { - __REQ_RW, /* not set, read. set, write */ - __REQ_FAILFAST_DEV, /* no driver retries of device errors */ - __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ - __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ - /* above flags must match BIO_RW_* */ - __REQ_DISCARD, /* request to discard sectors */ - __REQ_SORTED, /* elevator knows about this request */ - __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ - __REQ_HARDBARRIER, /* may not be passed by drive either */ - __REQ_FUA, /* forced unit access */ - __REQ_NOMERGE, /* don't touch this for merging */ - __REQ_STARTED, /* drive already may have started this one */ - __REQ_DONTPREP, /* don't call prep for this one */ - __REQ_QUEUED, /* uses queueing */ - __REQ_ELVPRIV, /* elevator private data attached */ - __REQ_FAILED, /* set if the request failed */ - __REQ_QUIET, /* don't worry about errors */ - __REQ_PREEMPT, /* set for "ide_preempt" requests */ - __REQ_ORDERED_COLOR, /* is before or after barrier */ - __REQ_RW_SYNC, /* request is sync (sync write or read) */ - __REQ_ALLOCED, /* request came from our alloc pool */ - __REQ_RW_META, /* metadata io request */ - __REQ_COPY_USER, /* contains copies of user pages */ - __REQ_INTEGRITY, /* integrity metadata has been remapped */ - __REQ_NOIDLE, /* Don't anticipate more IO after this one */ - __REQ_IO_STAT, /* account I/O stat */ - __REQ_MIXED_MERGE, /* merge of different types, fail separately */ - __REQ_NR_BITS, /* stops here */ -}; - -#define REQ_RW (1 << __REQ_RW) -#define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) -#define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) -#define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) -#define REQ_DISCARD (1 << __REQ_DISCARD) -#define REQ_SORTED (1 << __REQ_SORTED) -#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) -#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) -#define REQ_FUA (1 << __REQ_FUA) -#define REQ_NOMERGE (1 << __REQ_NOMERGE) -#define REQ_STARTED (1 << __REQ_STARTED) -#define REQ_DONTPREP (1 << __REQ_DONTPREP) -#define REQ_QUEUED (1 << __REQ_QUEUED) -#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) -#define REQ_FAILED (1 << __REQ_FAILED) -#define REQ_QUIET (1 << __REQ_QUIET) -#define REQ_PREEMPT (1 << __REQ_PREEMPT) -#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) -#define REQ_RW_SYNC (1 << __REQ_RW_SYNC) -#define REQ_ALLOCED (1 << __REQ_ALLOCED) -#define REQ_RW_META (1 << __REQ_RW_META) -#define REQ_COPY_USER (1 << __REQ_COPY_USER) -#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) -#define REQ_NOIDLE (1 << __REQ_NOIDLE) -#define REQ_IO_STAT (1 << __REQ_IO_STAT) -#define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) - -#define REQ_FAILFAST_MASK (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \ - REQ_FAILFAST_DRIVER) - #define BLK_MAX_CDB 16 /* @@ -631,7 +567,7 @@ enum { */ static inline bool rw_is_sync(unsigned int rw_flags) { - return !(rw_flags & REQ_RW) || (rw_flags & REQ_RW_SYNC); + return !(rw_flags & REQ_WRITE) || (rw_flags & REQ_SYNC); } static inline bool rq_is_sync(struct request *rq) diff --git a/include/linux/fs.h b/include/linux/fs.h index 598878831497..c5c92943c767 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -144,29 +144,31 @@ struct inodes_stat_t { * of this IO. * */ -#define RW_MASK 1 -#define RWA_MASK 2 -#define READ 0 -#define WRITE 1 -#define READA 2 /* read-ahead - don't block if no resources */ -#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ -#define READ_SYNC (READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) -#define READ_META (READ | (1 << BIO_RW_META)) -#define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) -#define WRITE_SYNC (WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_ODIRECT_PLUG (WRITE | (1 << BIO_RW_SYNCIO)) -#define WRITE_META (WRITE | (1 << BIO_RW_META)) -#define SWRITE_SYNC_PLUG \ - (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) -#define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_BARRIER (WRITE_SYNC | (1 << BIO_RW_BARRIER)) +#define RW_MASK 1 +#define RWA_MASK 2 + +#define READ 0 +#define WRITE 1 +#define READA 2 /* readahead - don't block if no resources */ +#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ + +#define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) +#define READ_META (READ | REQ_META) +#define WRITE_SYNC_PLUG (WRITE | REQ_SYNC | REQ_NOIDLE) +#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) +#define WRITE_ODIRECT_PLUG (WRITE | REQ_SYNC) +#define WRITE_META (WRITE | REQ_META) +#define WRITE_BARRIER (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ + REQ_HARDBARRIER) +#define SWRITE_SYNC_PLUG (SWRITE | REQ_SYNC | REQ_NOIDLE) +#define SWRITE_SYNC (SWRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) /* * These aren't really reads or writes, they pass down information about * parts of device that are now unused by the file system. */ -#define DISCARD_NOBARRIER (WRITE | (1 << BIO_RW_DISCARD)) -#define DISCARD_BARRIER (DISCARD_NOBARRIER | (1 << BIO_RW_BARRIER)) +#define DISCARD_NOBARRIER (WRITE | REQ_DISCARD) +#define DISCARD_BARRIER (WRITE | REQ_DISCARD | REQ_HARDBARRIER) #define SEL_IN 1 #define SEL_OUT 2 diff --git a/kernel/power/block_io.c b/kernel/power/block_io.c index 97024fd40cd5..83bbc7c02df9 100644 --- a/kernel/power/block_io.c +++ b/kernel/power/block_io.c @@ -28,7 +28,7 @@ static int submit(int rw, struct block_device *bdev, sector_t sector, struct page *page, struct bio **bio_chain) { - const int bio_rw = rw | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); + const int bio_rw = rw | REQ_SYNC | REQ_UNPLUG; struct bio *bio; bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 4f149944cb89..3b4a695051b6 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -169,9 +169,12 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) }; +#define BLK_TC_HARDBARRIER BLK_TC_BARRIER +#define BLK_TC_RAHEAD BLK_TC_AHEAD + /* The ilog2() calls fall out because they're constant */ -#define MASK_TC_BIT(rw, __name) ((rw & (1 << BIO_RW_ ## __name)) << \ - (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name)) +#define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \ + (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name)) /* * The worker for the various blk_add_trace*() types. Fills out a @@ -194,9 +197,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, return; what |= ddir_act[rw & WRITE]; - what |= MASK_TC_BIT(rw, BARRIER); - what |= MASK_TC_BIT(rw, SYNCIO); - what |= MASK_TC_BIT(rw, AHEAD); + what |= MASK_TC_BIT(rw, HARDBARRIER); + what |= MASK_TC_BIT(rw, SYNC); + what |= MASK_TC_BIT(rw, RAHEAD); what |= MASK_TC_BIT(rw, META); what |= MASK_TC_BIT(rw, DISCARD); @@ -662,7 +665,7 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, return; if (rq->cmd_flags & REQ_DISCARD) - rw |= (1 << BIO_RW_DISCARD); + rw |= REQ_DISCARD; if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { what |= BLK_TC_ACT(BLK_TC_PC); @@ -1755,20 +1758,20 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) if (rw & WRITE) rwbs[i++] = 'W'; - else if (rw & 1 << BIO_RW_DISCARD) + else if (rw & REQ_DISCARD) rwbs[i++] = 'D'; else if (bytes) rwbs[i++] = 'R'; else rwbs[i++] = 'N'; - if (rw & 1 << BIO_RW_AHEAD) + if (rw & REQ_RAHEAD) rwbs[i++] = 'A'; - if (rw & 1 << BIO_RW_BARRIER) + if (rw & REQ_HARDBARRIER) rwbs[i++] = 'B'; - if (rw & 1 << BIO_RW_SYNCIO) + if (rw & REQ_SYNC) rwbs[i++] = 'S'; - if (rw & 1 << BIO_RW_META) + if (rw & REQ_META) rwbs[i++] = 'M'; rwbs[i] = '\0'; @@ -1780,7 +1783,7 @@ void blk_fill_rwbs_rq(char *rwbs, struct request *rq) int bytes; if (rq->cmd_flags & REQ_DISCARD) - rw |= (1 << BIO_RW_DISCARD); + rw |= REQ_DISCARD; bytes = blk_rq_bytes(rq); diff --git a/mm/page_io.c b/mm/page_io.c index 31a3b962230a..2dee975bf469 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -106,7 +106,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) goto out; } if (wbc->sync_mode == WB_SYNC_ALL) - rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG); + rw |= REQ_SYNC | REQ_UNPLUG; count_vm_event(PSWPOUT); set_page_writeback(page); unlock_page(page); -- cgit v1.2.3 From 66ac0280197981f88774e74b60c8e5f9f07c1dba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Jun 2010 16:59:42 +0200 Subject: block: don't allocate a payload for discard request Allocating a fixed payload for discard requests always was a horrible hack, and it's not coming to byte us when adding support for discard in DM/MD. So change the code to leave the allocation of a payload to the lowlevel driver. Unfortunately that means we'll need another hack, which allows us to update the various block layer length fields indicating that we have a payload. Instead of hiding this in sd.c, which we already partially do for UNMAP support add a documented helper in the core block layer for it. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-core.c | 32 +++++++++++++++++++++++++++++++ block/blk-lib.c | 33 ++++++-------------------------- drivers/scsi/sd.c | 52 +++++++++++++++++++++++++++++++++----------------- include/linux/blkdev.h | 2 ++ 4 files changed, 74 insertions(+), 45 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 66c3cfe94d0a..3531d8e1da04 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1135,6 +1135,38 @@ void blk_put_request(struct request *req) } EXPORT_SYMBOL(blk_put_request); +/** + * blk_add_request_payload - add a payload to a request + * @rq: request to update + * @page: page backing the payload + * @len: length of the payload. + * + * This allows to later add a payload to an already submitted request by + * a block driver. The driver needs to take care of freeing the payload + * itself. + * + * Note that this is a quite horrible hack and nothing but handling of + * discard requests should ever use it. + */ +void blk_add_request_payload(struct request *rq, struct page *page, + unsigned int len) +{ + struct bio *bio = rq->bio; + + bio->bi_io_vec->bv_page = page; + bio->bi_io_vec->bv_offset = 0; + bio->bi_io_vec->bv_len = len; + + bio->bi_size = len; + bio->bi_vcnt = 1; + bio->bi_phys_segments = 1; + + rq->__data_len = rq->resid_len = len; + rq->nr_phys_segments = 1; + rq->buffer = bio_data(bio); +} +EXPORT_SYMBOL_GPL(blk_add_request_payload); + void init_request_from_bio(struct request *req, struct bio *bio) { req->cpu = bio->bi_comp_cpu; diff --git a/block/blk-lib.c b/block/blk-lib.c index d0216b9f22d4..e16185b0d8e1 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -19,7 +19,6 @@ static void blkdev_discard_end_io(struct bio *bio, int err) if (bio->bi_private) complete(bio->bi_private); - __free_page(bio_page(bio)); bio_put(bio); } @@ -43,7 +42,6 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, int type = flags & BLKDEV_IFL_BARRIER ? DISCARD_BARRIER : DISCARD_NOBARRIER; struct bio *bio; - struct page *page; int ret = 0; if (!q) @@ -53,35 +51,21 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, return -EOPNOTSUPP; while (nr_sects && !ret) { - unsigned int sector_size = q->limits.logical_block_size; unsigned int max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9); bio = bio_alloc(gfp_mask, 1); - if (!bio) - goto out; + if (!bio) { + ret = -ENOMEM; + break; + } + bio->bi_sector = sector; bio->bi_end_io = blkdev_discard_end_io; bio->bi_bdev = bdev; if (flags & BLKDEV_IFL_WAIT) bio->bi_private = &wait; - /* - * Add a zeroed one-sector payload as that's what - * our current implementations need. If we'll ever need - * more the interface will need revisiting. - */ - page = alloc_page(gfp_mask | __GFP_ZERO); - if (!page) - goto out_free_bio; - if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size) - goto out_free_page; - - /* - * And override the bio size - the way discard works we - * touch many more blocks on disk than the actual payload - * length. - */ if (nr_sects > max_discard_sectors) { bio->bi_size = max_discard_sectors << 9; nr_sects -= max_discard_sectors; @@ -103,13 +87,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, ret = -EIO; bio_put(bio); } + return ret; -out_free_page: - __free_page(page); -out_free_bio: - bio_put(bio); -out: - return -ENOMEM; } EXPORT_SYMBOL(blkdev_issue_discard); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a3fdf4dc59da..86da819c70eb 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -411,22 +411,25 @@ static void sd_prot_op(struct scsi_cmnd *scmd, unsigned int dif) } /** - * sd_prepare_discard - unmap blocks on thinly provisioned device + * scsi_setup_discard_cmnd - unmap blocks on thinly provisioned device + * @sdp: scsi device to operate one * @rq: Request to prepare * * Will issue either UNMAP or WRITE SAME(16) depending on preference * indicated by target device. **/ -static int sd_prepare_discard(struct request *rq) +static int scsi_setup_discard_cmnd(struct scsi_device *sdp, struct request *rq) { struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); struct bio *bio = rq->bio; sector_t sector = bio->bi_sector; - unsigned int num = bio_sectors(bio); + unsigned int nr_sectors = bio_sectors(bio); + unsigned int len; + struct page *page; if (sdkp->device->sector_size == 4096) { sector >>= 3; - num >>= 3; + nr_sectors >>= 3; } rq->cmd_type = REQ_TYPE_BLOCK_PC; @@ -434,31 +437,35 @@ static int sd_prepare_discard(struct request *rq) memset(rq->cmd, 0, rq->cmd_len); + page = alloc_page(GFP_ATOMIC | __GFP_ZERO); + if (!page) + return BLKPREP_DEFER; + if (sdkp->unmap) { - char *buf = kmap_atomic(bio_page(bio), KM_USER0); + char *buf = page_address(page); + rq->cmd_len = 10; rq->cmd[0] = UNMAP; rq->cmd[8] = 24; - rq->cmd_len = 10; - - /* Ensure that data length matches payload */ - rq->__data_len = bio->bi_size = bio->bi_io_vec->bv_len = 24; put_unaligned_be16(6 + 16, &buf[0]); put_unaligned_be16(16, &buf[2]); put_unaligned_be64(sector, &buf[8]); - put_unaligned_be32(num, &buf[16]); + put_unaligned_be32(nr_sectors, &buf[16]); - kunmap_atomic(buf, KM_USER0); + len = 24; } else { + rq->cmd_len = 16; rq->cmd[0] = WRITE_SAME_16; rq->cmd[1] = 0x8; /* UNMAP */ put_unaligned_be64(sector, &rq->cmd[2]); - put_unaligned_be32(num, &rq->cmd[10]); - rq->cmd_len = 16; + put_unaligned_be32(nr_sectors, &rq->cmd[10]); + + len = sdkp->device->sector_size; } - return BLKPREP_OK; + blk_add_request_payload(rq, page, len); + return scsi_setup_blk_pc_cmnd(sdp, rq); } /** @@ -485,10 +492,10 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) * Discard request come in as REQ_TYPE_FS but we turn them into * block PC requests to make life easier. */ - if (rq->cmd_flags & REQ_DISCARD) - ret = sd_prepare_discard(rq); - - if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { + if (rq->cmd_flags & REQ_DISCARD) { + ret = scsi_setup_discard_cmnd(sdp, rq); + goto out; + } else if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { ret = scsi_setup_blk_pc_cmnd(sdp, rq); goto out; } else if (rq->cmd_type != REQ_TYPE_FS) { @@ -1163,6 +1170,15 @@ static int sd_done(struct scsi_cmnd *SCpnt) int sense_valid = 0; int sense_deferred = 0; + /* + * If this is a discard request that originated from the kernel + * we need to free our payload here. Note that we need to check + * the request flag as the normal payload rules apply for + * pass-through UNMAP / WRITE SAME requests. + */ + if (SCpnt->request->cmd_flags & REQ_DISCARD) + __free_page(bio_page(SCpnt->request->bio)); + if (result) { sense_valid = scsi_command_normalize_sense(SCpnt, &sshdr); if (sense_valid) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3fc0f5908619..204fbe22354d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -705,6 +705,8 @@ 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); extern int blk_rq_check_limits(struct request_queue *q, struct request *rq); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, -- cgit v1.2.3 From 28018c242a4ec7017bbbf81d2d3952f820a27118 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Thu, 1 Jul 2010 19:49:17 +0900 Subject: block: implement an unprep function corresponding directly to prep Reviewed-by: FUJITA Tomonori Signed-off-by: Jens Axboe --- block/blk-core.c | 25 +++++++++++++++++++++++++ block/blk-settings.c | 17 +++++++++++++++++ drivers/scsi/scsi_lib.c | 2 +- include/linux/blkdev.h | 4 ++++ 4 files changed, 47 insertions(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 3c3789492c10..5ab3ac22930c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -608,6 +608,7 @@ blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn, q->request_fn = rfn; q->prep_rq_fn = NULL; + q->unprep_rq_fn = NULL; q->unplug_fn = generic_unplug_device; q->queue_flags = QUEUE_FLAG_DEFAULT; q->queue_lock = lock; @@ -2133,6 +2134,26 @@ static bool blk_update_bidi_request(struct request *rq, int error, return false; } +/** + * blk_unprep_request - unprepare a request + * @req: the request + * + * This function makes a request ready for complete resubmission (or + * completion). It happens only after all error handling is complete, + * so represents the appropriate moment to deallocate any resources + * that were allocated to the request in the prep_rq_fn. The queue + * lock is held when calling this. + */ +void blk_unprep_request(struct request *req) +{ + struct request_queue *q = req->q; + + req->cmd_flags &= ~REQ_DONTPREP; + if (q->unprep_rq_fn) + q->unprep_rq_fn(q, req); +} +EXPORT_SYMBOL_GPL(blk_unprep_request); + /* * queue lock must be held */ @@ -2148,6 +2169,10 @@ static void blk_finish_request(struct request *req, int error) blk_delete_timer(req); + if (req->cmd_flags & REQ_DONTPREP) + blk_unprep_request(req); + + blk_account_io_done(req); if (req->end_io) diff --git a/block/blk-settings.c b/block/blk-settings.c index f5ed5a1187ba..a234f4bf1d6f 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -36,6 +36,23 @@ void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn) } EXPORT_SYMBOL(blk_queue_prep_rq); +/** + * blk_queue_unprep_rq - set an unprepare_request function for queue + * @q: queue + * @ufn: unprepare_request function + * + * It's possible for a queue to register an unprepare_request callback + * which is invoked before the request is finally completed. The goal + * of the function is to deallocate any data that was allocated in the + * prepare_request callback. + * + */ +void blk_queue_unprep_rq(struct request_queue *q, unprep_rq_fn *ufn) +{ + q->unprep_rq_fn = ufn; +} +EXPORT_SYMBOL(blk_queue_unprep_rq); + /** * blk_queue_merge_bvec - set a merge_bvec function for queue * @q: queue diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 5f1160841b0e..ee836193f531 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -85,7 +85,7 @@ static void scsi_unprep_request(struct request *req) { struct scsi_cmnd *cmd = req->special; - req->cmd_flags &= ~REQ_DONTPREP; + blk_unprep_request(req); req->special = NULL; scsi_put_command(cmd); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 204fbe22354d..6bba04c7ec48 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -200,6 +200,7 @@ struct request_pm_state typedef void (request_fn_proc) (struct request_queue *q); typedef int (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); +typedef void (unprep_rq_fn) (struct request_queue *, struct request *); typedef void (unplug_fn) (struct request_queue *); struct bio_vec; @@ -282,6 +283,7 @@ struct request_queue request_fn_proc *request_fn; make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; + unprep_rq_fn *unprep_rq_fn; unplug_fn *unplug_fn; merge_bvec_fn *merge_bvec_fn; prepare_flush_fn *prepare_flush_fn; @@ -841,6 +843,7 @@ extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); extern void blk_abort_queue(struct request_queue *); +extern void blk_unprep_request(struct request *); /* * Access functions for manipulating queue properties @@ -885,6 +888,7 @@ extern int blk_queue_dma_drain(struct request_queue *q, extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); +extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn); extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); -- cgit v1.2.3 From 00fff26539bfe3fad21c164fc4002d9ede056fb0 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Sat, 3 Jul 2010 17:45:40 +0900 Subject: block: remove q->prepare_flush_fn completely This removes q->prepare_flush_fn completely (changes the blk_queue_ordered API). Signed-off-by: FUJITA Tomonori Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 7 +------ drivers/block/brd.c | 2 +- drivers/block/loop.c | 2 +- drivers/block/osdblk.c | 2 +- drivers/block/ps3disk.c | 2 +- drivers/block/virtio_blk.c | 4 ++-- drivers/block/xen-blkfront.c | 3 +-- drivers/ide/ide-disk.c | 2 +- drivers/md/dm.c | 2 +- drivers/mmc/card/queue.c | 2 +- drivers/s390/block/dasd.c | 2 +- drivers/scsi/sd.c | 2 +- include/linux/blkdev.h | 4 +--- 13 files changed, 14 insertions(+), 22 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 7ce0a32a21fd..eefbde835308 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -13,7 +13,6 @@ * blk_queue_ordered - does this queue support ordered writes * @q: the request queue * @ordered: one of QUEUE_ORDERED_* - * @prepare_flush_fn: rq setup helper for cache flush ordered writes * * Description: * For journalled file systems, doing ordered writes on a commit @@ -22,8 +21,7 @@ * feature should call this function and indicate so. * **/ -int blk_queue_ordered(struct request_queue *q, unsigned ordered, - prepare_flush_fn *prepare_flush_fn) +int blk_queue_ordered(struct request_queue *q, unsigned ordered) { if (ordered != QUEUE_ORDERED_NONE && ordered != QUEUE_ORDERED_DRAIN && @@ -38,7 +36,6 @@ int blk_queue_ordered(struct request_queue *q, unsigned ordered, q->ordered = ordered; q->next_ordered = ordered; - q->prepare_flush_fn = prepare_flush_fn; return 0; } @@ -140,8 +137,6 @@ static void queue_flush(struct request_queue *q, unsigned which) rq->cmd_flags = REQ_HARDBARRIER | REQ_FLUSH; rq->rq_disk = q->bar_rq.rq_disk; rq->end_io = end_io; - if (q->prepare_flush_fn) - q->prepare_flush_fn(q, rq); elv_insert(q, rq, ELEVATOR_INSERT_FRONT); } diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 1b218c6b6820..1d2c18620f9a 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -479,7 +479,7 @@ static struct brd_device *brd_alloc(int i) if (!brd->brd_queue) goto out_free_dev; blk_queue_make_request(brd->brd_queue, brd_make_request); - blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG, NULL); + blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG); blk_queue_max_hw_sectors(brd->brd_queue, 1024); blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index fedfdb7d3cdf..d285a5481965 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -831,7 +831,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, lo->lo_queue->unplug_fn = loop_unplug; if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) - blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN, NULL); + blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN); set_capacity(lo->lo_disk, size); bd_set_size(bdev, size << 9); diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c index 9639565a9a6a..2284b4f05c62 100644 --- a/drivers/block/osdblk.c +++ b/drivers/block/osdblk.c @@ -439,7 +439,7 @@ static int osdblk_init_disk(struct osdblk_device *osdev) blk_queue_stack_limits(q, osd_request_queue(osdev->osd)); blk_queue_prep_rq(q, blk_queue_start_tag); - blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH, NULL); + blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH); disk->queue = q; diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index ab528a480f98..e9da874d0419 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -468,7 +468,7 @@ static int __devinit ps3disk_probe(struct ps3_system_bus_device *_dev) blk_queue_dma_alignment(queue, dev->blk_size-1); blk_queue_logical_block_size(queue, dev->blk_size); - blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH, NULL); + blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH); blk_queue_max_segments(queue, -1); blk_queue_max_segment_size(queue, dev->bounce_size); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index b277f9e6abac..0a3222fd4442 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -366,9 +366,9 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) /* If barriers are supported, tell block layer that queue is ordered */ if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH)) - blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH, NULL); + blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH); else if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER)) - blk_queue_ordered(q, QUEUE_ORDERED_TAG, NULL); + blk_queue_ordered(q, QUEUE_ORDERED_TAG); /* If disk is read-only in the host, the guest should obey */ if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO)) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 495533e66542..76af65b654e3 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -373,8 +373,7 @@ static int xlvbd_barrier(struct blkfront_info *info) int err; err = blk_queue_ordered(info->rq, - info->feature_barrier ? QUEUE_ORDERED_DRAIN : QUEUE_ORDERED_NONE, - NULL); + info->feature_barrier ? QUEUE_ORDERED_DRAIN : QUEUE_ORDERED_NONE); if (err) return err; diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index c22e6226e9e9..7433e07de30e 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -549,7 +549,7 @@ static void update_ordered(ide_drive_t *drive) } else ordered = QUEUE_ORDERED_DRAIN; - blk_queue_ordered(drive->queue, ordered, NULL); + blk_queue_ordered(drive->queue, ordered); } ide_devset_get_flag(wcache, IDE_DFLAG_WCACHE); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 00c810551814..d505a96845c1 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1901,7 +1901,7 @@ static struct mapped_device *alloc_dev(int minor) blk_queue_softirq_done(md->queue, dm_softirq_done); blk_queue_prep_rq(md->queue, dm_prep_fn); blk_queue_lld_busy(md->queue, dm_lld_busy); - blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH, NULL); + blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH); md->disk = alloc_disk(1); if (!md->disk) diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index ec92bcbdeddb..c77eb49eda0e 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -128,7 +128,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock mq->req = NULL; blk_queue_prep_rq(mq->queue, mmc_prep_request); - blk_queue_ordered(mq->queue, QUEUE_ORDERED_DRAIN, NULL); + blk_queue_ordered(mq->queue, QUEUE_ORDERED_DRAIN); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue); #ifdef CONFIG_MMC_BLOCK_BOUNCE diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 33975e922d65..17b033d0e050 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2196,7 +2196,7 @@ static void dasd_setup_queue(struct dasd_block *block) */ blk_queue_max_segment_size(block->request_queue, PAGE_SIZE); blk_queue_segment_boundary(block->request_queue, PAGE_SIZE - 1); - blk_queue_ordered(block->request_queue, QUEUE_ORDERED_DRAIN, NULL); + blk_queue_ordered(block->request_queue, QUEUE_ORDERED_DRAIN); } /* diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index e8c295e01466..d9a4314a1948 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2135,7 +2135,7 @@ static int sd_revalidate_disk(struct gendisk *disk) else ordered = QUEUE_ORDERED_DRAIN; - blk_queue_ordered(sdkp->disk->queue, ordered, NULL); + blk_queue_ordered(sdkp->disk->queue, ordered); set_capacity(disk, sdkp->capacity); kfree(buffer); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6bba04c7ec48..3a2c5d9a9288 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -212,7 +212,6 @@ struct bvec_merge_data { }; typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *, struct bio_vec *); -typedef void (prepare_flush_fn) (struct request_queue *, struct request *); typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); typedef int (lld_busy_fn) (struct request_queue *q); @@ -286,7 +285,6 @@ struct request_queue unprep_rq_fn *unprep_rq_fn; unplug_fn *unplug_fn; merge_bvec_fn *merge_bvec_fn; - prepare_flush_fn *prepare_flush_fn; softirq_done_fn *softirq_done_fn; rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; @@ -896,7 +894,7 @@ extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *); +extern int blk_queue_ordered(struct request_queue *, unsigned); extern bool blk_do_ordered(struct request_queue *, struct request **); extern unsigned blk_ordered_cur_seq(struct request_queue *); extern unsigned blk_ordered_req_seq(struct request *); -- cgit v1.2.3 From a89f5c899db3c6be4bb426e4efb72ecee29a93b5 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Tue, 6 Jul 2010 09:03:18 +0200 Subject: block: remove unused REQ_TYPE_LINUX_BLOCK Nobody uses REQ_TYPE_LINUX_BLOCK (and its REQ_LB_OP_*). Signed-off-by: FUJITA Tomonori Acked-by: Jeff Garzik Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3a2c5d9a9288..baf5258f5985 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -60,7 +60,6 @@ enum rq_cmd_type_bits { REQ_TYPE_PM_RESUME, /* resume request */ REQ_TYPE_PM_SHUTDOWN, /* shutdown request */ REQ_TYPE_SPECIAL, /* driver defined type */ - REQ_TYPE_LINUX_BLOCK, /* generic block layer message */ /* * for ATA/ATAPI devices. this really doesn't belong here, ide should * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver @@ -70,20 +69,6 @@ enum rq_cmd_type_bits { REQ_TYPE_ATA_PC, }; -/* - * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being - * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a - * SCSI cdb. - * - * 0x00 -> 0x3f are driver private, to be used for whatever purpose they need, - * typically to differentiate REQ_TYPE_SPECIAL requests. - * - */ -enum { - REQ_LB_OP_EJECT = 0x40, /* eject request */ - REQ_LB_OP_FLUSH = 0x41, /* flush request */ -}; - #define BLK_MAX_CDB 16 /* -- cgit v1.2.3 From 8a6cfeb6deca3a8fefd639d898b0d163c0b5d368 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 8 Jul 2010 10:18:46 +0200 Subject: block: push down BKL into .locked_ioctl As a preparation for the removal of the big kernel lock in the block layer, this removes the BKL from the common ioctl handling code, moving it into every single driver still using it. Signed-off-by: Arnd Bergmann Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/ioctl.c | 11 +---------- drivers/block/amiflop.c | 17 +++++++++++++++-- drivers/block/ataflop.c | 18 +++++++++++++++--- drivers/block/brd.c | 5 ++++- drivers/block/cciss.c | 8 +++++--- drivers/block/cpqarray.c | 18 ++++++++++++++++-- drivers/block/floppy.c | 17 +++++++++++++++-- drivers/block/nbd.c | 5 ++++- drivers/block/paride/pcd.c | 11 +++++++++-- drivers/block/paride/pd.c | 5 ++++- drivers/block/paride/pf.c | 6 +++++- drivers/block/pktcdvd.c | 13 +++++++++---- drivers/block/swim.c | 5 ++++- drivers/block/swim3.c | 17 +++++++++++++++-- drivers/block/ub.c | 10 ++++++++-- drivers/block/virtio_blk.c | 17 +++++++++++++++-- drivers/block/xd.c | 17 +++++++++++++++-- drivers/block/xen-blkfront.c | 2 +- drivers/cdrom/gdrom.c | 11 +++++++++-- drivers/cdrom/viocd.c | 11 +++++++++-- drivers/ide/ide-cd.c | 18 ++++++++++++++++-- drivers/ide/ide-disk_ioctl.c | 9 +++++++-- drivers/ide/ide-floppy_ioctl.c | 12 +++++++++--- drivers/ide/ide-gd.c | 2 +- drivers/ide/ide-tape.c | 10 ++++++++-- drivers/message/i2o/i2o_block.c | 22 +++++----------------- drivers/mtd/mtd_blkdevs.c | 5 ++++- drivers/scsi/sd.c | 17 ++++++++++++----- drivers/scsi/sr.c | 18 +++++++++++++----- include/linux/blkdev.h | 1 - 30 files changed, 253 insertions(+), 85 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/ioctl.c b/block/ioctl.c index e8eb679f2f9b..1cfa8d449d90 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -163,18 +163,10 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; - int ret; if (disk->fops->ioctl) return disk->fops->ioctl(bdev, mode, cmd, arg); - if (disk->fops->locked_ioctl) { - lock_kernel(); - ret = disk->fops->locked_ioctl(bdev, mode, cmd, arg); - unlock_kernel(); - return ret; - } - return -ENOTTY; } /* @@ -185,8 +177,7 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl); /* - * always keep this in sync with compat_blkdev_ioctl() and - * compat_blkdev_locked_ioctl() + * always keep this in sync with compat_blkdev_ioctl() */ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 832798aa14f6..0fa26359304c 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -60,6 +60,7 @@ #include #include #include +#include #include #include #include @@ -1423,7 +1424,7 @@ static int fd_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static int fd_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long param) { struct amiga_floppy_struct *p = bdev->bd_disk->private_data; @@ -1500,6 +1501,18 @@ static int fd_ioctl(struct block_device *bdev, fmode_t mode, return 0; } +static int fd_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long param) +{ + int ret; + + lock_kernel(); + ret = fd_locked_ioctl(bdev, mode, cmd, param); + unlock_kernel(); + + return ret; +} + static void fd_probe(int dev) { unsigned long code; @@ -1638,7 +1651,7 @@ static const struct block_device_operations floppy_fops = { .owner = THIS_MODULE, .open = floppy_open, .release = floppy_release, - .locked_ioctl = fd_ioctl, + .ioctl = fd_ioctl, .getgeo = fd_getgeo, .media_changed = amiga_floppy_change, }; diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index e35cf59cbfde..1bb8bfcfdbd9 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -67,6 +67,7 @@ #include #include #include +#include #include #include @@ -359,7 +360,7 @@ static void finish_fdc( void ); static void finish_fdc_done( int dummy ); static void setup_req_params( int drive ); static void redo_fd_request( void); -static int fd_ioctl(struct block_device *bdev, fmode_t mode, unsigned int +static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long param); static void fd_probe( int drive ); static int fd_test_drive_present( int drive ); @@ -1480,7 +1481,7 @@ void do_fd_request(struct request_queue * q) atari_enable_irq( IRQ_MFP_FDC ); } -static int fd_ioctl(struct block_device *bdev, fmode_t mode, +static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long param) { struct gendisk *disk = bdev->bd_disk; @@ -1665,6 +1666,17 @@ static int fd_ioctl(struct block_device *bdev, fmode_t mode, } } +static int fd_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + int ret; + + lock_kernel(); + ret = fd_locked_ioctl(bdev, mode, cmd, arg); + unlock_kernel(); + + return ret; +} /* Initialize the 'unit' variable for drive 'drive' */ @@ -1855,7 +1867,7 @@ static const struct block_device_operations floppy_fops = { .owner = THIS_MODULE, .open = floppy_open, .release = floppy_release, - .locked_ioctl = fd_ioctl, + .ioctl = fd_ioctl, .media_changed = check_floppy_change, .revalidate_disk= floppy_revalidate, }; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 1d2c18620f9a..1c7f63792ff8 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include /* invalidate_bh_lrus() */ #include @@ -401,6 +402,7 @@ static int brd_ioctl(struct block_device *bdev, fmode_t mode, * ram device BLKFLSBUF has special semantics, we want to actually * release and destroy the ramdisk data. */ + lock_kernel(); mutex_lock(&bdev->bd_mutex); error = -EBUSY; if (bdev->bd_openers <= 1) { @@ -417,13 +419,14 @@ static int brd_ioctl(struct block_device *bdev, fmode_t mode, error = 0; } mutex_unlock(&bdev->bd_mutex); + unlock_kernel(); return error; } static const struct block_device_operations brd_fops = { .owner = THIS_MODULE, - .locked_ioctl = brd_ioctl, + .ioctl = brd_ioctl, #ifdef CONFIG_BLK_DEV_XIP .direct_access = brd_direct_access, #endif diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 11b377762b8e..a6c0494dd054 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -179,6 +179,8 @@ static irqreturn_t do_cciss_intx(int irq, void *dev_id); static irqreturn_t do_cciss_msix_intr(int irq, void *dev_id); static int cciss_open(struct block_device *bdev, fmode_t mode); static int cciss_release(struct gendisk *disk, fmode_t mode); +static int do_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); static int cciss_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); static int cciss_getgeo(struct block_device *bdev, struct hd_geometry *geo); @@ -237,7 +239,7 @@ static const struct block_device_operations cciss_fops = { .owner = THIS_MODULE, .open = cciss_open, .release = cciss_release, - .locked_ioctl = cciss_ioctl, + .ioctl = do_ioctl, .getgeo = cciss_getgeo, #ifdef CONFIG_COMPAT .compat_ioctl = cciss_compat_ioctl, @@ -1057,8 +1059,6 @@ static int cciss_release(struct gendisk *disk, fmode_t mode) return 0; } -#ifdef CONFIG_COMPAT - static int do_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { @@ -1069,6 +1069,8 @@ static int do_ioctl(struct block_device *bdev, fmode_t mode, return ret; } +#ifdef CONFIG_COMPAT + static int cciss_ioctl32_passthru(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg); static int cciss_ioctl32_big_passthru(struct block_device *bdev, fmode_t mode, diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c index abb4ec6690fc..c459aeea3c0c 100644 --- a/drivers/block/cpqarray.c +++ b/drivers/block/cpqarray.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -197,7 +198,7 @@ static const struct block_device_operations ida_fops = { .owner = THIS_MODULE, .open = ida_open, .release = ida_release, - .locked_ioctl = ida_ioctl, + .ioctl = ida_ioctl, .getgeo = ida_getgeo, .revalidate_disk= ida_revalidate, }; @@ -1128,7 +1129,7 @@ static int ida_getgeo(struct block_device *bdev, struct hd_geometry *geo) * ida_ioctl does some miscellaneous stuff like reporting drive geometry, * setting readahead and submitting commands from userspace to the controller. */ -static int ida_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) +static int ida_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { drv_info_t *drv = get_drv(bdev->bd_disk); ctlr_info_t *host = get_host(bdev->bd_disk); @@ -1192,6 +1193,19 @@ out_passthru: } } + +static int ida_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long param) +{ + int ret; + + lock_kernel(); + ret = ida_locked_ioctl(bdev, mode, cmd, param); + unlock_kernel(); + + return ret; +} + /* * ida_ctlr_ioctl is for passing commands to the controller from userspace. * The command block (io) has already been copied to kernel space for us, diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 82c30f9f81ca..40419b066aa9 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -178,6 +178,7 @@ static int print_unex = 1; #include #include #include +#include #include #include #include @@ -3371,7 +3372,7 @@ static int fd_getgeo(struct block_device *bdev, struct hd_geometry *geo) return 0; } -static int fd_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, +static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long param) { int drive = (long)bdev->bd_disk->private_data; @@ -3547,6 +3548,18 @@ static int fd_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, return 0; } +static int fd_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long param) +{ + int ret; + + lock_kernel(); + ret = fd_locked_ioctl(bdev, mode, cmd, param); + unlock_kernel(); + + return ret; +} + static void __init config_types(void) { bool has_drive = false; @@ -3848,7 +3861,7 @@ static const struct block_device_operations floppy_fops = { .owner = THIS_MODULE, .open = floppy_open, .release = floppy_release, - .locked_ioctl = fd_ioctl, + .ioctl = fd_ioctl, .getgeo = fd_getgeo, .media_changed = check_floppy_change, .revalidate_disk = floppy_revalidate, diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 2e74e7d475ca..6751789fb379 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -716,9 +717,11 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode, dprintk(DBG_IOCTL, "%s: nbd_ioctl cmd=%s(0x%x) arg=%lu\n", lo->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg); + lock_kernel(); mutex_lock(&lo->tx_lock); error = __nbd_ioctl(bdev, lo, cmd, arg); mutex_unlock(&lo->tx_lock); + unlock_kernel(); return error; } @@ -726,7 +729,7 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode, static const struct block_device_operations nbd_fops = { .owner = THIS_MODULE, - .locked_ioctl = nbd_ioctl, + .ioctl = nbd_ioctl, }; /* diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 71acf4e53356..daba7a62a663 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -138,6 +138,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_SLV, D_DLY}; #include #include #include +#include #include static DEFINE_SPINLOCK(pcd_lock); @@ -238,7 +239,13 @@ static int pcd_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { struct pcd_unit *cd = bdev->bd_disk->private_data; - return cdrom_ioctl(&cd->info, bdev, mode, cmd, arg); + int ret; + + lock_kernel(); + ret = cdrom_ioctl(&cd->info, bdev, mode, cmd, arg); + unlock_kernel(); + + return ret; } static int pcd_block_media_changed(struct gendisk *disk) @@ -251,7 +258,7 @@ static const struct block_device_operations pcd_bdops = { .owner = THIS_MODULE, .open = pcd_block_open, .release = pcd_block_release, - .locked_ioctl = pcd_block_ioctl, + .ioctl = pcd_block_ioctl, .media_changed = pcd_block_media_changed, }; diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 4e8b9bff3abe..c4d6ed9846ca 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -153,6 +153,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_GEO, D_SBY, D_DLY, D_SLV}; #include #include #include +#include #include #include @@ -768,8 +769,10 @@ static int pd_ioctl(struct block_device *bdev, fmode_t mode, switch (cmd) { case CDROMEJECT: + lock_kernel(); if (disk->access == 1) pd_special_command(disk, pd_eject); + unlock_kernel(); return 0; default: return -EINVAL; @@ -812,7 +815,7 @@ static const struct block_device_operations pd_fops = { .owner = THIS_MODULE, .open = pd_open, .release = pd_release, - .locked_ioctl = pd_ioctl, + .ioctl = pd_ioctl, .getgeo = pd_getgeo, .media_changed = pd_check_media, .revalidate_disk= pd_revalidate diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index c059aab3006b..38b4d566b816 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -152,6 +152,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_SLV, D_LUN, D_DLY}; #include #include #include +#include #include static DEFINE_SPINLOCK(pf_spin_lock); @@ -266,7 +267,7 @@ static const struct block_device_operations pf_fops = { .owner = THIS_MODULE, .open = pf_open, .release = pf_release, - .locked_ioctl = pf_ioctl, + .ioctl = pf_ioctl, .getgeo = pf_getgeo, .media_changed = pf_check_media, }; @@ -342,7 +343,10 @@ static int pf_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, u if (pf->access != 1) return -EBUSY; + lock_kernel(); pf_eject(pf); + unlock_kernel(); + return 0; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 9f3e4454274b..40f1e31f42c4 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include #include @@ -2762,10 +2763,12 @@ out_mem: static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct pktcdvd_device *pd = bdev->bd_disk->private_data; + int ret; VPRINTK("pkt_ioctl: cmd %x, dev %d:%d\n", cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); + lock_kernel(); switch (cmd) { case CDROMEJECT: /* @@ -2783,14 +2786,16 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, case CDROM_LAST_WRITTEN: case CDROM_SEND_PACKET: case SCSI_IOCTL_SEND_COMMAND: - return __blkdev_driver_ioctl(pd->bdev, mode, cmd, arg); + ret = __blkdev_driver_ioctl(pd->bdev, mode, cmd, arg); + break; default: VPRINTK(DRIVER_NAME": Unknown ioctl for %s (%x)\n", pd->name, cmd); - return -ENOTTY; + ret = -ENOTTY; } + unlock_kernel(); - return 0; + return ret; } static int pkt_media_changed(struct gendisk *disk) @@ -2812,7 +2817,7 @@ static const struct block_device_operations pktcdvd_ops = { .owner = THIS_MODULE, .open = pkt_open, .release = pkt_close, - .locked_ioctl = pkt_ioctl, + .ioctl = pkt_ioctl, .media_changed = pkt_media_changed, }; diff --git a/drivers/block/swim.c b/drivers/block/swim.c index e463657569ff..f04f74e3758f 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -690,7 +691,9 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode, case FDEJECT: if (fs->ref_count != 1) return -EBUSY; + lock_kernel(); err = floppy_eject(fs); + unlock_kernel(); return err; case FDGETPRM: @@ -753,7 +756,7 @@ static const struct block_device_operations floppy_fops = { .owner = THIS_MODULE, .open = floppy_open, .release = floppy_release, - .locked_ioctl = floppy_ioctl, + .ioctl = floppy_ioctl, .getgeo = floppy_getgeo, .media_changed = floppy_check_change, .revalidate_disk = floppy_revalidate, diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index ed6fb91123ab..f3657b2a5386 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -839,7 +840,7 @@ 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_ioctl(struct block_device *bdev, fmode_t mode, +static int floppy_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long param) { struct floppy_state *fs = bdev->bd_disk->private_data; @@ -867,6 +868,18 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode, return -ENOTTY; } +static int floppy_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long param) +{ + int ret; + + lock_kernel(); + ret = floppy_locked_ioctl(bdev, mode, cmd, param); + unlock_kernel(); + + return ret; +} + static int floppy_open(struct block_device *bdev, fmode_t mode) { struct floppy_state *fs = bdev->bd_disk->private_data; @@ -997,7 +1010,7 @@ static int floppy_revalidate(struct gendisk *disk) static const struct block_device_operations floppy_fops = { .open = floppy_open, .release = floppy_release, - .locked_ioctl = floppy_ioctl, + .ioctl = floppy_ioctl, .media_changed = floppy_check_change, .revalidate_disk= floppy_revalidate, }; diff --git a/drivers/block/ub.c b/drivers/block/ub.c index aaf27fb4efd6..102ed52d0e0f 100644 --- a/drivers/block/ub.c +++ b/drivers/block/ub.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #define DRV_NAME "ub" @@ -1729,8 +1730,13 @@ static int ub_bd_ioctl(struct block_device *bdev, fmode_t mode, { struct gendisk *disk = bdev->bd_disk; void __user *usermem = (void __user *) arg; + int ret; + + lock_kernel(); + ret = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, usermem); + unlock_kernel(); - return scsi_cmd_ioctl(disk->queue, disk, mode, cmd, usermem); + return ret; } /* @@ -1794,7 +1800,7 @@ static const struct block_device_operations ub_bd_fops = { .owner = THIS_MODULE, .open = ub_bd_open, .release = ub_bd_release, - .locked_ioctl = ub_bd_ioctl, + .ioctl = ub_bd_ioctl, .media_changed = ub_bd_media_changed, .revalidate_disk = ub_bd_revalidate, }; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 0a3222fd4442..7b0f7b624adf 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include #include @@ -217,7 +218,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) return blk_execute_rq(vblk->disk->queue, vblk->disk, req, false); } -static int virtblk_ioctl(struct block_device *bdev, fmode_t mode, +static int virtblk_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long data) { struct gendisk *disk = bdev->bd_disk; @@ -243,6 +244,18 @@ static int virtblk_ioctl(struct block_device *bdev, fmode_t mode, (void __user *)data); } +static int virtblk_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long param) +{ + int ret; + + lock_kernel(); + ret = virtblk_locked_ioctl(bdev, mode, cmd, param); + unlock_kernel(); + + return ret; +} + /* We provide getgeo only to please some old bootloader/partitioning tools */ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) { @@ -269,7 +282,7 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) } static const struct block_device_operations virtblk_fops = { - .locked_ioctl = virtblk_ioctl, + .ioctl = virtblk_ioctl, .owner = THIS_MODULE, .getgeo = virtblk_getgeo, }; diff --git a/drivers/block/xd.c b/drivers/block/xd.c index b16a3a926cf2..d5a3cd750561 100644 --- a/drivers/block/xd.c +++ b/drivers/block/xd.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include #include @@ -133,7 +134,7 @@ static int xd_getgeo(struct block_device *bdev, struct hd_geometry *geo); static const struct block_device_operations xd_fops = { .owner = THIS_MODULE, - .locked_ioctl = xd_ioctl, + .ioctl = xd_ioctl, .getgeo = xd_getgeo, }; static DECLARE_WAIT_QUEUE_HEAD(xd_wait_int); @@ -347,7 +348,7 @@ static int xd_getgeo(struct block_device *bdev, struct hd_geometry *geo) } /* xd_ioctl: handle device ioctl's */ -static int xd_ioctl(struct block_device *bdev, fmode_t mode, u_int cmd, u_long arg) +static int xd_locked_ioctl(struct block_device *bdev, fmode_t mode, u_int cmd, u_long arg) { switch (cmd) { case HDIO_SET_DMA: @@ -375,6 +376,18 @@ static int xd_ioctl(struct block_device *bdev, fmode_t mode, u_int cmd, u_long a } } +static int xd_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long param) +{ + int ret; + + lock_kernel(); + ret = xd_locked_ioctl(bdev, mode, cmd, param); + unlock_kernel(); + + return ret; +} + /* xd_readwrite: handle a read/write request */ static int xd_readwrite (u_char operation,XD_INFO *p,char *buffer,u_int block,u_int count) { diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 76af65b654e3..9119cd3d56a4 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1045,7 +1045,7 @@ static const struct block_device_operations xlvbd_block_fops = .open = blkif_open, .release = blkif_release, .getgeo = blkif_getgeo, - .locked_ioctl = blkif_ioctl, + .ioctl = blkif_ioctl, }; diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 5219b57deb36..1772fd914fb9 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -509,7 +510,13 @@ static int gdrom_bdops_mediachanged(struct gendisk *disk) static int gdrom_bdops_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { - return cdrom_ioctl(gd.cd_info, bdev, mode, cmd, arg); + int ret; + + lock_kernel(); + ret = cdrom_ioctl(gd.cd_info, bdev, mode, cmd, arg); + unlock_kernel(); + + return ret; } static const struct block_device_operations gdrom_bdops = { @@ -517,7 +524,7 @@ static const struct block_device_operations gdrom_bdops = { .open = gdrom_bdops_open, .release = gdrom_bdops_release, .media_changed = gdrom_bdops_mediachanged, - .locked_ioctl = gdrom_bdops_ioctl, + .ioctl = gdrom_bdops_ioctl, }; static irqreturn_t gdrom_command_interrupt(int irq, void *dev_id) diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c index 1fa6628d150b..16dada0627ee 100644 --- a/drivers/cdrom/viocd.c +++ b/drivers/cdrom/viocd.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -167,7 +168,13 @@ static int viocd_blk_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { struct disk_info *di = bdev->bd_disk->private_data; - return cdrom_ioctl(&di->viocd_info, bdev, mode, cmd, arg); + int ret; + + lock_kernel(); + ret = cdrom_ioctl(&di->viocd_info, bdev, mode, cmd, arg); + unlock_kernel(); + + return ret; } static int viocd_blk_media_changed(struct gendisk *disk) @@ -180,7 +187,7 @@ static const struct block_device_operations viocd_fops = { .owner = THIS_MODULE, .open = viocd_blk_open, .release = viocd_blk_release, - .locked_ioctl = viocd_blk_ioctl, + .ioctl = viocd_blk_ioctl, .media_changed = viocd_blk_media_changed, }; diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index ef7e3a9bee51..bf9f61a5c2f8 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -1654,7 +1655,7 @@ static int idecd_get_spindown(struct cdrom_device_info *cdi, unsigned long arg) return 0; } -static int idecd_ioctl(struct block_device *bdev, fmode_t mode, +static int idecd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct cdrom_info *info = ide_drv_g(bdev->bd_disk, cdrom_info); @@ -1676,6 +1677,19 @@ static int idecd_ioctl(struct block_device *bdev, fmode_t mode, return err; } +static int idecd_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) +{ + int ret; + + lock_kernel(); + ret = idecd_locked_ioctl(bdev, mode, cmd, arg); + unlock_kernel(); + + return ret; +} + + static int idecd_media_changed(struct gendisk *disk) { struct cdrom_info *info = ide_drv_g(disk, cdrom_info); @@ -1696,7 +1710,7 @@ static const struct block_device_operations idecd_ops = { .owner = THIS_MODULE, .open = idecd_open, .release = idecd_release, - .locked_ioctl = idecd_ioctl, + .ioctl = idecd_ioctl, .media_changed = idecd_media_changed, .revalidate_disk = idecd_revalidate_disk }; diff --git a/drivers/ide/ide-disk_ioctl.c b/drivers/ide/ide-disk_ioctl.c index 7b783dd7c0be..ec94c66918f6 100644 --- a/drivers/ide/ide-disk_ioctl.c +++ b/drivers/ide/ide-disk_ioctl.c @@ -1,6 +1,7 @@ #include #include #include +#include #include "ide-disk.h" @@ -18,9 +19,13 @@ int ide_disk_ioctl(ide_drive_t *drive, struct block_device *bdev, fmode_t mode, { int err; + lock_kernel(); err = ide_setting_ioctl(drive, bdev, cmd, arg, ide_disk_ioctl_settings); if (err != -EOPNOTSUPP) - return err; + goto out; - return generic_ide_ioctl(drive, bdev, cmd, arg); + err = generic_ide_ioctl(drive, bdev, cmd, arg); +out: + unlock_kernel(); + return err; } diff --git a/drivers/ide/ide-floppy_ioctl.c b/drivers/ide/ide-floppy_ioctl.c index 9c2288234dea..fd3d05ab3417 100644 --- a/drivers/ide/ide-floppy_ioctl.c +++ b/drivers/ide/ide-floppy_ioctl.c @@ -5,6 +5,7 @@ #include #include #include +#include #include @@ -275,12 +276,15 @@ int ide_floppy_ioctl(ide_drive_t *drive, struct block_device *bdev, void __user *argp = (void __user *)arg; int err; - if (cmd == CDROMEJECT || cmd == CDROM_LOCKDOOR) - return ide_floppy_lockdoor(drive, &pc, arg, cmd); + lock_kernel(); + if (cmd == CDROMEJECT || cmd == CDROM_LOCKDOOR) { + err = ide_floppy_lockdoor(drive, &pc, arg, cmd); + goto out; + } err = ide_floppy_format_ioctl(drive, &pc, mode, cmd, argp); if (err != -ENOTTY) - return err; + goto out; /* * skip SCSI_IOCTL_SEND_COMMAND (deprecated) @@ -293,5 +297,7 @@ int ide_floppy_ioctl(ide_drive_t *drive, struct block_device *bdev, if (err == -ENOTTY) err = generic_ide_ioctl(drive, bdev, cmd, arg); +out: + unlock_kernel(); return err; } diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c index c102d23d9b38..883f0c979c9f 100644 --- a/drivers/ide/ide-gd.c +++ b/drivers/ide/ide-gd.c @@ -323,7 +323,7 @@ static const struct block_device_operations ide_gd_ops = { .owner = THIS_MODULE, .open = ide_gd_open, .release = ide_gd_release, - .locked_ioctl = ide_gd_ioctl, + .ioctl = ide_gd_ioctl, .getgeo = ide_gd_getgeo, .media_changed = ide_gd_media_changed, .unlock_native_capacity = ide_gd_unlock_native_capacity, diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index 635fd72d4728..39b0a5c45f07 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -1927,9 +1928,14 @@ static int idetape_ioctl(struct block_device *bdev, fmode_t mode, { struct ide_tape_obj *tape = ide_drv_g(bdev->bd_disk, ide_tape_obj); ide_drive_t *drive = tape->drive; - int err = generic_ide_ioctl(drive, bdev, cmd, arg); + int err; + + lock_kernel(); + err = generic_ide_ioctl(drive, bdev, cmd, arg); if (err == -EINVAL) err = idetape_blkdev_ioctl(drive, cmd, arg); + unlock_kernel(); + return err; } @@ -1937,7 +1943,7 @@ static const struct block_device_operations idetape_block_ops = { .owner = THIS_MODULE, .open = idetape_open, .release = idetape_release, - .locked_ioctl = idetape_ioctl, + .ioctl = idetape_ioctl, }; static int ide_tape_probe(ide_drive_t *drive) diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c index b8233ff863e3..d1bdf8abe5db 100644 --- a/drivers/message/i2o/i2o_block.c +++ b/drivers/message/i2o/i2o_block.c @@ -53,7 +53,6 @@ #include #include #include -#include #include @@ -653,40 +652,30 @@ static int i2o_block_ioctl(struct block_device *bdev, fmode_t mode, { struct gendisk *disk = bdev->bd_disk; struct i2o_block_device *dev = disk->private_data; - int ret = -ENOTTY; /* Anyone capable of this syscall can do *real bad* things */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; - lock_kernel(); switch (cmd) { case BLKI2OGRSTRAT: - ret = put_user(dev->rcache, (int __user *)arg); - break; + return put_user(dev->rcache, (int __user *)arg); case BLKI2OGWSTRAT: - ret = put_user(dev->wcache, (int __user *)arg); - break; + return put_user(dev->wcache, (int __user *)arg); case BLKI2OSRSTRAT: - ret = -EINVAL; if (arg < 0 || arg > CACHE_SMARTFETCH) - break; + return -EINVAL; dev->rcache = arg; - ret = 0; break; case BLKI2OSWSTRAT: - ret = -EINVAL; if (arg != 0 && (arg < CACHE_WRITETHROUGH || arg > CACHE_SMARTBACK)) - break; + return -EINVAL; dev->wcache = arg; - ret = 0; break; } - unlock_kernel(); - - return ret; + return -ENOTTY; }; /** @@ -942,7 +931,6 @@ static const struct block_device_operations i2o_block_fops = { .open = i2o_block_open, .release = i2o_block_release, .ioctl = i2o_block_ioctl, - .compat_ioctl = i2o_block_ioctl, .getgeo = i2o_block_getgeo, .media_changed = i2o_block_media_changed }; diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 475af42745cb..8c83b11a77d5 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -237,6 +238,7 @@ static int blktrans_ioctl(struct block_device *bdev, fmode_t mode, if (!dev) return ret; + lock_kernel(); mutex_lock(&dev->lock); if (!dev->mtd) @@ -250,6 +252,7 @@ static int blktrans_ioctl(struct block_device *bdev, fmode_t mode, } unlock: mutex_unlock(&dev->lock); + unlock_kernel(); blktrans_dev_put(dev); return ret; } @@ -258,7 +261,7 @@ static const struct block_device_operations mtd_blktrans_ops = { .owner = THIS_MODULE, .open = blktrans_open, .release = blktrans_release, - .locked_ioctl = blktrans_ioctl, + .ioctl = blktrans_ioctl, .getgeo = blktrans_getgeo, }; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 1d0c4b7c3b69..633ac32b25c1 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include #include @@ -924,6 +925,7 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, SCSI_LOG_IOCTL(1, printk("sd_ioctl: disk=%s, cmd=0x%x\n", disk->disk_name, cmd)); + lock_kernel(); /* * If we are in the middle of error recovery, don't let anyone * else try and use this device. Also, if error recovery fails, it @@ -933,7 +935,7 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, error = scsi_nonblockable_ioctl(sdp, cmd, p, (mode & FMODE_NDELAY) != 0); if (!scsi_block_when_processing_errors(sdp) || !error) - return error; + goto out; /* * Send SCSI addressing ioctls directly to mid level, send other @@ -943,13 +945,18 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, switch (cmd) { case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: - return scsi_ioctl(sdp, cmd, p); + error = scsi_ioctl(sdp, cmd, p); + break; default: error = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, p); if (error != -ENOTTY) - return error; + break; + error = scsi_ioctl(sdp, cmd, p); + break; } - return scsi_ioctl(sdp, cmd, p); +out: + unlock_kernel(); + return error; } static void set_media_not_present(struct scsi_disk *sdkp) @@ -1123,7 +1130,7 @@ static const struct block_device_operations sd_fops = { .owner = THIS_MODULE, .open = sd_open, .release = sd_release, - .locked_ioctl = sd_ioctl, + .ioctl = sd_ioctl, .getgeo = sd_getgeo, #ifdef CONFIG_COMPAT .compat_ioctl = sd_compat_ioctl, diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 0a90abc7f140..d42fa6468f41 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include @@ -493,6 +494,8 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, void __user *argp = (void __user *)arg; int ret; + lock_kernel(); + /* * Send SCSI addressing ioctls directly to mid level, send other * ioctls to cdrom/block level. @@ -500,12 +503,13 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, switch (cmd) { case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: - return scsi_ioctl(sdev, cmd, argp); + ret = scsi_ioctl(sdev, cmd, argp); + goto out; } ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); if (ret != -ENOSYS) - return ret; + goto out; /* * ENODEV means that we didn't recognise the ioctl, or that we @@ -516,8 +520,12 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, ret = scsi_nonblockable_ioctl(sdev, cmd, argp, (mode & FMODE_NDELAY) != 0); if (ret != -ENODEV) - return ret; - return scsi_ioctl(sdev, cmd, argp); + goto out; + ret = scsi_ioctl(sdev, cmd, argp); + +out: + unlock_kernel(); + return ret; } static int sr_block_media_changed(struct gendisk *disk) @@ -531,7 +539,7 @@ static const struct block_device_operations sr_bdops = .owner = THIS_MODULE, .open = sr_block_open, .release = sr_block_release, - .locked_ioctl = sr_block_ioctl, + .ioctl = sr_block_ioctl, .media_changed = sr_block_media_changed, /* * No compat_ioctl for now because sr_block_ioctl never diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index baf5258f5985..a8b05fc80c6d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1246,7 +1246,6 @@ static inline int blk_integrity_rq(struct request *rq) struct block_device_operations { int (*open) (struct block_device *, fmode_t); int (*release) (struct gendisk *, fmode_t); - int (*locked_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*direct_access) (struct block_device *, sector_t, -- cgit v1.2.3 From edca4a380584a65a16839bdee33ec82244f0f88e Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 3 Aug 2010 12:54:51 +0200 Subject: block: disallow FS recursion from sb_issue_discard allocation Filesystems can call sb_issue_discard on a memory reclaim path (e.g. ext4 calls sb_issue_discard during journal commit). Use GFP_NOFS in sb_issue_discard to avoid recursing back into the FS. Reported-by: Mikulas Patocka Signed-off-by: Mike Snitzer 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 a8b05fc80c6d..89c855c5655c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -933,7 +933,7 @@ static inline int sb_issue_discard(struct super_block *sb, { 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_NOFS, BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); } -- cgit v1.2.3 From 8d57a98ccd0b4489003473979da8f5a1363ba7a3 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 11 Aug 2010 14:17:49 -0700 Subject: block: add secure discard Secure discard is the same as discard except that all copies of the discarded sectors (perhaps created by garbage collection) must also be erased. Signed-off-by: Adrian Hunter Acked-by: Jens Axboe Cc: Kyungmin Park Cc: Madhusudhan Chikkature Cc: Christoph Hellwig Cc: Ben Gardiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- block/blk-core.c | 5 ++++- block/blk-lib.c | 6 ++++++ block/compat_ioctl.c | 1 + block/elevator.c | 6 ++++++ block/ioctl.c | 15 ++++++++++----- include/linux/blk_types.h | 2 ++ include/linux/blkdev.h | 7 ++++++- include/linux/fs.h | 2 ++ kernel/trace/blktrace.c | 8 ++++++++ 9 files changed, 45 insertions(+), 7 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 7da630e25ae7..ee1a1e7e63cc 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1514,7 +1514,10 @@ static inline void __generic_make_request(struct bio *bio) if (bio_check_eod(bio, nr_sectors)) goto end_io; - if ((bio->bi_rw & REQ_DISCARD) && !blk_queue_discard(q)) { + if ((bio->bi_rw & REQ_DISCARD) && + (!blk_queue_discard(q) || + ((bio->bi_rw & REQ_SECURE) && + !blk_queue_secdiscard(q)))) { err = -EOPNOTSUPP; goto end_io; } diff --git a/block/blk-lib.c b/block/blk-lib.c index c1fc55a83ba1..c392029a104e 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -62,6 +62,12 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, max_discard_sectors &= ~(disc_sects - 1); } + if (flags & BLKDEV_IFL_SECURE) { + if (!blk_queue_secdiscard(q)) + return -EOPNOTSUPP; + type |= DISCARD_SECURE; + } + while (nr_sects && !ret) { bio = bio_alloc(gfp_mask, 1); if (!bio) { diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index d53085637731..119f07b74dc0 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -703,6 +703,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKFLSBUF: case BLKROSET: case BLKDISCARD: + case BLKSECDISCARD: /* * the ones below are implemented in blkdev_locked_ioctl, * but we call blkdev_ioctl, which gets the lock for us diff --git a/block/elevator.c b/block/elevator.c index 816a7c8d6394..ec585c9554d3 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -82,6 +82,12 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio) if ((bio->bi_rw & REQ_DISCARD) != (rq->bio->bi_rw & REQ_DISCARD)) return 0; + /* + * Don't merge discard requests and secure discard requests + */ + if ((bio->bi_rw & REQ_SECURE) != (rq->bio->bi_rw & REQ_SECURE)) + return 0; + /* * different data direction or already started, don't merge */ diff --git a/block/ioctl.c b/block/ioctl.c index 09fd7f1ef23a..d8052f0dabd3 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -114,8 +114,10 @@ static int blkdev_reread_part(struct block_device *bdev) } static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, - uint64_t len) + uint64_t len, int secure) { + unsigned long flags = BLKDEV_IFL_WAIT; + if (start & 511) return -EINVAL; if (len & 511) @@ -125,8 +127,9 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, if (start + len > (bdev->bd_inode->i_size >> 9)) return -EINVAL; - return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, - BLKDEV_IFL_WAIT); + if (secure) + flags |= BLKDEV_IFL_SECURE; + return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags); } static int put_ushort(unsigned long arg, unsigned short val) @@ -213,7 +216,8 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, set_device_ro(bdev, n); return 0; - case BLKDISCARD: { + case BLKDISCARD: + case BLKSECDISCARD: { uint64_t range[2]; if (!(mode & FMODE_WRITE)) @@ -222,7 +226,8 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, if (copy_from_user(range, (void __user *)arg, sizeof(range))) return -EFAULT; - return blk_ioctl_discard(bdev, range[0], range[1]); + return blk_ioctl_discard(bdev, range[0], range[1], + cmd == BLKSECDISCARD); } case HDIO_GETGEO: { diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 53691774d34e..ca83a97c9715 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -150,6 +150,7 @@ enum rq_flag_bits { __REQ_FLUSH, /* request for cache flush */ __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ + __REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */ __REQ_NR_BITS, /* stops here */ }; @@ -190,5 +191,6 @@ enum rq_flag_bits { #define REQ_FLUSH (1 << __REQ_FLUSH) #define REQ_IO_STAT (1 << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) +#define REQ_SECURE (1 << __REQ_SECURE) #endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 89c855c5655c..2c54906f678f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -389,6 +389,7 @@ struct request_queue #define QUEUE_FLAG_DISCARD 16 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 17 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 18 /* Contributes to random pool */ +#define QUEUE_FLAG_SECDISCARD 19 /* supports SECDISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_CLUSTER) | \ @@ -524,6 +525,8 @@ enum { #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) +#define blk_queue_secdiscard(q) (blk_queue_discard(q) && \ + test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags)) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ @@ -918,10 +921,12 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, } enum{ BLKDEV_WAIT, /* wait for completion */ - BLKDEV_BARRIER, /*issue request with barrier */ + BLKDEV_BARRIER, /* issue request with barrier */ + BLKDEV_SECURE, /* secure discard */ }; #define BLKDEV_IFL_WAIT (1 << BLKDEV_WAIT) #define BLKDEV_IFL_BARRIER (1 << BLKDEV_BARRIER) +#define BLKDEV_IFL_SECURE (1 << BLKDEV_SECURE) extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *, unsigned long); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, diff --git a/include/linux/fs.h b/include/linux/fs.h index 267d02630517..7a0625e26a39 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -174,6 +174,7 @@ struct inodes_stat_t { */ #define DISCARD_NOBARRIER (WRITE | REQ_DISCARD) #define DISCARD_BARRIER (WRITE | REQ_DISCARD | REQ_HARDBARRIER) +#define DISCARD_SECURE (DISCARD_NOBARRIER | REQ_SECURE) #define SEL_IN 1 #define SEL_OUT 2 @@ -317,6 +318,7 @@ struct inodes_stat_t { #define BLKALIGNOFF _IO(0x12,122) #define BLKPBSZGET _IO(0x12,123) #define BLKDISCARDZEROES _IO(0x12,124) +#define BLKSECDISCARD _IO(0x12,125) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 82499a5bdcb7..959f8d6c8cc1 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -710,6 +710,9 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, if (rq->cmd_flags & REQ_DISCARD) rw |= REQ_DISCARD; + if (rq->cmd_flags & REQ_SECURE) + rw |= REQ_SECURE; + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { what |= BLK_TC_ACT(BLK_TC_PC); __blk_add_trace(bt, 0, blk_rq_bytes(rq), rw, @@ -1816,6 +1819,8 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) rwbs[i++] = 'S'; if (rw & REQ_META) rwbs[i++] = 'M'; + if (rw & REQ_SECURE) + rwbs[i++] = 'E'; rwbs[i] = '\0'; } @@ -1828,6 +1833,9 @@ void blk_fill_rwbs_rq(char *rwbs, struct request *rq) if (rq->cmd_flags & REQ_DISCARD) rw |= REQ_DISCARD; + if (rq->cmd_flags & REQ_SECURE) + rw |= REQ_SECURE; + bytes = blk_rq_bytes(rq); blk_fill_rwbs(rwbs, rw, bytes); -- cgit v1.2.3 From 0da2f50944976e890ccc9436ab88c0da87788d02 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Sep 2010 11:56:16 +0200 Subject: ide: remove unnecessary blk_queue_flushing() test in do_ide_request() Unplugging from a request function doesn't really help much (it's already in the request_fn) and soon block layer will be updated to mix barrier sequence with other commands, so there's no need to treat queue flushing any differently. ide was the only user of blk_queue_flushing(). Remove it. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Acked-by: David S. Miller Signed-off-by: Jens Axboe --- drivers/ide/ide-io.c | 13 ------------- include/linux/blkdev.h | 1 - 2 files changed, 14 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index a381be814070..999dac054bcc 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -441,19 +441,6 @@ void do_ide_request(struct request_queue *q) struct request *rq = NULL; ide_startstop_t startstop; - /* - * drive is doing pre-flush, ordered write, post-flush sequence. even - * though that is 3 requests, it must be seen as a single transaction. - * we must not preempt this drive until that is complete - */ - if (blk_queue_flushing(q)) - /* - * small race where queue could get replugged during - * the 3-request flush cycle, just yank the plug since - * we want it to finish asap - */ - blk_remove_plug(q); - spin_unlock_irq(q->queue_lock); /* HLD do_request() callback might sleep, make sure it's okay */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c54906f678f..015375c7d031 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -521,7 +521,6 @@ enum { #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_flushing(q) ((q)->ordseq) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) -- cgit v1.2.3 From 6958f145459ca7ad9715024de97445addacb8510 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Sep 2010 11:56:16 +0200 Subject: block: kill QUEUE_ORDERED_BY_TAG Nobody is making meaningful use of ORDERED_BY_TAG now and queue draining for barrier requests will be removed soon which will render the advantage of tag ordering moot. Kill ORDERED_BY_TAG. The following users are affected. * brd: converted to ORDERED_DRAIN. * virtio_blk: ORDERED_TAG path was already marked deprecated. Removed. * xen-blkfront: ORDERED_TAG case dropped. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Cc: Nick Piggin Cc: Michael S. Tsirkin Cc: Jeremy Fitzhardinge Cc: Chris Wright Signed-off-by: Jens Axboe --- block/blk-barrier.c | 35 +++++++---------------------------- drivers/block/brd.c | 2 +- drivers/block/virtio_blk.c | 9 --------- drivers/block/xen-blkfront.c | 8 +++----- drivers/scsi/sd.c | 4 +--- include/linux/blkdev.h | 17 +---------------- 6 files changed, 13 insertions(+), 62 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index f0faefca032f..c807e9ca3a68 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -26,10 +26,7 @@ int blk_queue_ordered(struct request_queue *q, unsigned ordered) if (ordered != QUEUE_ORDERED_NONE && ordered != QUEUE_ORDERED_DRAIN && ordered != QUEUE_ORDERED_DRAIN_FLUSH && - ordered != QUEUE_ORDERED_DRAIN_FUA && - ordered != QUEUE_ORDERED_TAG && - ordered != QUEUE_ORDERED_TAG_FLUSH && - ordered != QUEUE_ORDERED_TAG_FUA) { + ordered != QUEUE_ORDERED_DRAIN_FUA) { printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered); return -EINVAL; } @@ -155,21 +152,9 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp) * For an empty barrier, there's no actual BAR request, which * in turn makes POSTFLUSH unnecessary. Mask them off. */ - if (!blk_rq_sectors(rq)) { + if (!blk_rq_sectors(rq)) q->ordered &= ~(QUEUE_ORDERED_DO_BAR | QUEUE_ORDERED_DO_POSTFLUSH); - /* - * Empty barrier on a write-through device w/ ordered - * tag has no command to issue and without any command - * to issue, ordering by tag can't be used. Drain - * instead. - */ - if ((q->ordered & QUEUE_ORDERED_BY_TAG) && - !(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) { - q->ordered &= ~QUEUE_ORDERED_BY_TAG; - q->ordered |= QUEUE_ORDERED_BY_DRAIN; - } - } /* stash away the original request */ blk_dequeue_request(rq); @@ -210,7 +195,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp) } else skip |= QUEUE_ORDSEQ_PREFLUSH; - if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q)) + if (queue_in_flight(q)) rq = NULL; else skip |= QUEUE_ORDSEQ_DRAIN; @@ -257,16 +242,10 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp) rq != &q->pre_flush_rq && rq != &q->post_flush_rq) return true; - if (q->ordered & QUEUE_ORDERED_BY_TAG) { - /* Ordered by tag. Blocking the next barrier is enough. */ - if (is_barrier && rq != &q->bar_rq) - *rqp = NULL; - } else { - /* Ordered by draining. Wait for turn. */ - WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q)); - if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q)) - *rqp = NULL; - } + /* Ordered by draining. Wait for turn. */ + WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q)); + if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q)) + *rqp = NULL; return true; } diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 1c7f63792ff8..47a41272d26b 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -482,7 +482,7 @@ static struct brd_device *brd_alloc(int i) if (!brd->brd_queue) goto out_free_dev; blk_queue_make_request(brd->brd_queue, brd_make_request); - blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG); + blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_DRAIN); blk_queue_max_hw_sectors(brd->brd_queue, 1024); blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 2aafafca2b13..79652809eee8 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -395,15 +395,6 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) * to implement write barrier support. */ blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH); - } else if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER)) { - /* - * If the BARRIER feature is supported the host expects us - * to order request by tags. This implies there is not - * volatile write cache on the host, and that the host - * never re-orders outstanding I/O. This feature is not - * useful for real life scenarious and deprecated. - */ - blk_queue_ordered(q, QUEUE_ORDERED_TAG); } else { /* * If the FLUSH feature is not supported we must assume that diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index ac1b682edecb..50ec6f834996 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -424,8 +424,7 @@ static int xlvbd_barrier(struct blkfront_info *info) const char *barrier; switch (info->feature_barrier) { - case QUEUE_ORDERED_DRAIN: barrier = "enabled (drain)"; break; - case QUEUE_ORDERED_TAG: barrier = "enabled (tag)"; break; + case QUEUE_ORDERED_DRAIN: barrier = "enabled"; break; case QUEUE_ORDERED_NONE: barrier = "disabled"; break; default: return -EINVAL; } @@ -1078,8 +1077,7 @@ static void blkfront_connect(struct blkfront_info *info) * we're dealing with a very old backend which writes * synchronously; draining will do what needs to get done. * - * If there are barriers, then we can do full queued writes - * with tagged barriers. + * If there are barriers, then we use flush. * * If barriers are not supported, then there's no much we can * do, so just set ordering to NONE. @@ -1087,7 +1085,7 @@ static void blkfront_connect(struct blkfront_info *info) if (err) info->feature_barrier = QUEUE_ORDERED_DRAIN; else if (barrier) - info->feature_barrier = QUEUE_ORDERED_TAG; + info->feature_barrier = QUEUE_ORDERED_DRAIN_FLUSH; else info->feature_barrier = QUEUE_ORDERED_NONE; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 2714becc2eaf..cdfc51ab9cf2 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2151,9 +2151,7 @@ static int sd_revalidate_disk(struct gendisk *disk) /* * We now have all cache related info, determine how we deal - * with ordered requests. Note that as the current SCSI - * dispatch function can alter request order, we cannot use - * QUEUE_ORDERED_TAG_* even when ordered tag is supported. + * with ordered requests. */ if (sdkp->WCE) ordered = sdkp->DPOFUA diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 015375c7d031..7077bc0d6138 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -470,12 +470,7 @@ enum { * DRAIN : ordering by draining is enough * DRAIN_FLUSH : ordering by draining w/ pre and post flushes * DRAIN_FUA : ordering by draining w/ pre flush and FUA write - * TAG : ordering by tag is enough - * TAG_FLUSH : ordering by tag w/ pre and post flushes - * TAG_FUA : ordering by tag w/ pre flush and FUA write */ - QUEUE_ORDERED_BY_DRAIN = 0x01, - QUEUE_ORDERED_BY_TAG = 0x02, QUEUE_ORDERED_DO_PREFLUSH = 0x10, QUEUE_ORDERED_DO_BAR = 0x20, QUEUE_ORDERED_DO_POSTFLUSH = 0x40, @@ -483,8 +478,7 @@ enum { QUEUE_ORDERED_NONE = 0x00, - QUEUE_ORDERED_DRAIN = QUEUE_ORDERED_BY_DRAIN | - QUEUE_ORDERED_DO_BAR, + QUEUE_ORDERED_DRAIN = QUEUE_ORDERED_DO_BAR, QUEUE_ORDERED_DRAIN_FLUSH = QUEUE_ORDERED_DRAIN | QUEUE_ORDERED_DO_PREFLUSH | QUEUE_ORDERED_DO_POSTFLUSH, @@ -492,15 +486,6 @@ enum { QUEUE_ORDERED_DO_PREFLUSH | QUEUE_ORDERED_DO_FUA, - QUEUE_ORDERED_TAG = QUEUE_ORDERED_BY_TAG | - QUEUE_ORDERED_DO_BAR, - QUEUE_ORDERED_TAG_FLUSH = QUEUE_ORDERED_TAG | - QUEUE_ORDERED_DO_PREFLUSH | - QUEUE_ORDERED_DO_POSTFLUSH, - QUEUE_ORDERED_TAG_FUA = QUEUE_ORDERED_TAG | - QUEUE_ORDERED_DO_PREFLUSH | - QUEUE_ORDERED_DO_FUA, - /* * Ordered operation sequence */ -- cgit v1.2.3 From 4913efe456c987057e5d36a3f0a55422a9072cae Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Sep 2010 11:56:16 +0200 Subject: block: deprecate barrier and replace blk_queue_ordered() with blk_queue_flush() Barrier is deemed too heavy and will soon be replaced by FLUSH/FUA requests. Deprecate barrier. All REQ_HARDBARRIERs are failed with -EOPNOTSUPP and blk_queue_ordered() is replaced with simpler blk_queue_flush(). blk_queue_flush() takes combinations of REQ_FLUSH and FUA. If a device has write cache and can flush it, it should set REQ_FLUSH. If the device can handle FUA writes, it should also set REQ_FUA. All blk_queue_ordered() users are converted. * ORDERED_DRAIN is mapped to 0 which is the default value. * ORDERED_DRAIN_FLUSH is mapped to REQ_FLUSH. * ORDERED_DRAIN_FLUSH_FUA is mapped to REQ_FLUSH | REQ_FUA. Signed-off-by: Tejun Heo Acked-by: Boaz Harrosh Cc: Christoph Hellwig Cc: Nick Piggin Cc: Michael S. Tsirkin Cc: Jeremy Fitzhardinge Cc: Chris Wright Cc: FUJITA Tomonori Cc: Geert Uytterhoeven Cc: David S. Miller Cc: Alasdair G Kergon Cc: Pierre Ossman Cc: Stefan Weinhuber Signed-off-by: Jens Axboe --- block/blk-barrier.c | 29 ----------------------------- block/blk-core.c | 6 ++++-- block/blk-settings.c | 20 ++++++++++++++++++++ drivers/block/brd.c | 1 - drivers/block/loop.c | 2 +- drivers/block/osdblk.c | 2 +- drivers/block/ps3disk.c | 2 +- drivers/block/virtio_blk.c | 25 +++++++++---------------- drivers/block/xen-blkfront.c | 43 ++++++++++++------------------------------- drivers/ide/ide-disk.c | 13 ++++++------- drivers/md/dm.c | 2 +- drivers/mmc/card/queue.c | 1 - drivers/s390/block/dasd.c | 1 - drivers/scsi/sd.c | 16 ++++++++-------- include/linux/blkdev.h | 6 ++++-- 15 files changed, 67 insertions(+), 102 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index c807e9ca3a68..ed0aba5463ab 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -9,35 +9,6 @@ #include "blk.h" -/** - * blk_queue_ordered - does this queue support ordered writes - * @q: the request queue - * @ordered: one of QUEUE_ORDERED_* - * - * Description: - * For journalled file systems, doing ordered writes on a commit - * block instead of explicitly doing wait_on_buffer (which is bad - * for performance) can be a big win. Block drivers supporting this - * feature should call this function and indicate so. - * - **/ -int blk_queue_ordered(struct request_queue *q, unsigned ordered) -{ - if (ordered != QUEUE_ORDERED_NONE && - ordered != QUEUE_ORDERED_DRAIN && - ordered != QUEUE_ORDERED_DRAIN_FLUSH && - ordered != QUEUE_ORDERED_DRAIN_FUA) { - printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered); - return -EINVAL; - } - - q->ordered = ordered; - q->next_ordered = ordered; - - return 0; -} -EXPORT_SYMBOL(blk_queue_ordered); - /* * Cache flushing for ordered writes handling */ diff --git a/block/blk-core.c b/block/blk-core.c index ee1a1e7e63cc..f06354183b29 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1203,11 +1203,13 @@ static int __make_request(struct request_queue *q, struct bio *bio) const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK; int rw_flags; - if ((bio->bi_rw & REQ_HARDBARRIER) && - (q->next_ordered == QUEUE_ORDERED_NONE)) { + /* REQ_HARDBARRIER is no more */ + if (WARN_ONCE(bio->bi_rw & REQ_HARDBARRIER, + "block: HARDBARRIER is deprecated, use FLUSH/FUA instead\n")) { bio_endio(bio, -EOPNOTSUPP); return 0; } + /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even diff --git a/block/blk-settings.c b/block/blk-settings.c index a234f4bf1d6f..9b18afcfe925 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -794,6 +794,26 @@ void blk_queue_update_dma_alignment(struct request_queue *q, int mask) } EXPORT_SYMBOL(blk_queue_update_dma_alignment); +/** + * blk_queue_flush - configure queue's cache flush capability + * @q: the request queue for the device + * @flush: 0, REQ_FLUSH or REQ_FLUSH | REQ_FUA + * + * Tell block layer cache flush capability of @q. If it supports + * flushing, REQ_FLUSH should be set. If it supports bypassing + * write cache for individual writes, REQ_FUA should be set. + */ +void blk_queue_flush(struct request_queue *q, unsigned int flush) +{ + WARN_ON_ONCE(flush & ~(REQ_FLUSH | REQ_FUA)); + + if (WARN_ON_ONCE(!(flush & REQ_FLUSH) && (flush & REQ_FUA))) + flush &= ~REQ_FUA; + + q->flush_flags = flush & (REQ_FLUSH | REQ_FUA); +} +EXPORT_SYMBOL_GPL(blk_queue_flush); + static int __init blk_settings_init(void) { blk_max_low_pfn = max_low_pfn - 1; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 47a41272d26b..fa33f97722ba 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -482,7 +482,6 @@ static struct brd_device *brd_alloc(int i) if (!brd->brd_queue) goto out_free_dev; blk_queue_make_request(brd->brd_queue, brd_make_request); - blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_DRAIN); blk_queue_max_hw_sectors(brd->brd_queue, 1024); blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index c3a4a2e176da..953d1e12f4d4 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -832,7 +832,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, lo->lo_queue->unplug_fn = loop_unplug; if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) - blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN_FLUSH); + blk_queue_flush(lo->lo_queue, REQ_FLUSH); set_capacity(lo->lo_disk, size); bd_set_size(bdev, size << 9); diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c index 2284b4f05c62..72d62462433d 100644 --- a/drivers/block/osdblk.c +++ b/drivers/block/osdblk.c @@ -439,7 +439,7 @@ static int osdblk_init_disk(struct osdblk_device *osdev) blk_queue_stack_limits(q, osd_request_queue(osdev->osd)); blk_queue_prep_rq(q, blk_queue_start_tag); - blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH); + blk_queue_flush(q, REQ_FLUSH); disk->queue = q; diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index e9da874d0419..4911f9e57bc7 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -468,7 +468,7 @@ static int __devinit ps3disk_probe(struct ps3_system_bus_device *_dev) blk_queue_dma_alignment(queue, dev->blk_size-1); blk_queue_logical_block_size(queue, dev->blk_size); - blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH); + blk_queue_flush(queue, REQ_FLUSH); blk_queue_max_segments(queue, -1); blk_queue_max_segment_size(queue, dev->bounce_size); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 79652809eee8..d10b635b3946 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -388,22 +388,15 @@ static int __devinit virtblk_probe(struct virtio_device *vdev) vblk->disk->driverfs_dev = &vdev->dev; index++; - if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH)) { - /* - * If the FLUSH feature is supported we do have support for - * flushing a volatile write cache on the host. Use that - * to implement write barrier support. - */ - blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH); - } else { - /* - * If the FLUSH feature is not supported we must assume that - * the host does not perform any kind of volatile write - * caching. We still need to drain the queue to provider - * proper barrier semantics. - */ - blk_queue_ordered(q, QUEUE_ORDERED_DRAIN); - } + /* + * If the FLUSH feature is supported we do have support for + * flushing a volatile write cache on the host. Use that to + * implement write barrier support; otherwise, we must assume + * that the host does not perform any kind of volatile write + * caching. + */ + if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH)) + blk_queue_flush(q, REQ_FLUSH); /* If disk is read-only in the host, the guest should obey */ if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO)) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 50ec6f834996..0b1eea643262 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -95,7 +95,7 @@ struct blkfront_info struct gnttab_free_callback callback; struct blk_shadow shadow[BLK_RING_SIZE]; unsigned long shadow_free; - int feature_barrier; + unsigned int feature_flush; int is_ready; }; @@ -418,25 +418,12 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size) } -static int xlvbd_barrier(struct blkfront_info *info) +static void xlvbd_flush(struct blkfront_info *info) { - int err; - const char *barrier; - - switch (info->feature_barrier) { - case QUEUE_ORDERED_DRAIN: barrier = "enabled"; break; - case QUEUE_ORDERED_NONE: barrier = "disabled"; break; - default: return -EINVAL; - } - - err = blk_queue_ordered(info->rq, info->feature_barrier); - - if (err) - return err; - + blk_queue_flush(info->rq, info->feature_flush); printk(KERN_INFO "blkfront: %s: barriers %s\n", - info->gd->disk_name, barrier); - return 0; + info->gd->disk_name, + info->feature_flush ? "enabled" : "disabled"); } @@ -515,7 +502,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, info->rq = gd->queue; info->gd = gd; - xlvbd_barrier(info); + xlvbd_flush(info); if (vdisk_info & VDISK_READONLY) set_disk_ro(gd, 1); @@ -661,8 +648,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) printk(KERN_WARNING "blkfront: %s: write barrier op failed\n", info->gd->disk_name); error = -EOPNOTSUPP; - info->feature_barrier = QUEUE_ORDERED_NONE; - xlvbd_barrier(info); + info->feature_flush = 0; + xlvbd_flush(info); } /* fall through */ case BLKIF_OP_READ: @@ -1075,19 +1062,13 @@ static void blkfront_connect(struct blkfront_info *info) /* * If there's no "feature-barrier" defined, then it means * we're dealing with a very old backend which writes - * synchronously; draining will do what needs to get done. + * synchronously; nothing to do. * * If there are barriers, then we use flush. - * - * If barriers are not supported, then there's no much we can - * do, so just set ordering to NONE. */ - if (err) - info->feature_barrier = QUEUE_ORDERED_DRAIN; - else if (barrier) - info->feature_barrier = QUEUE_ORDERED_DRAIN_FLUSH; - else - info->feature_barrier = QUEUE_ORDERED_NONE; + info->feature_flush = 0; + if (!err && barrier) + info->feature_flush = REQ_FLUSH; err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size); if (err) { diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 7433e07de30e..7c5b01ce51d2 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -516,10 +516,10 @@ static int ide_do_setfeature(ide_drive_t *drive, u8 feature, u8 nsect) return ide_no_data_taskfile(drive, &cmd); } -static void update_ordered(ide_drive_t *drive) +static void update_flush(ide_drive_t *drive) { u16 *id = drive->id; - unsigned ordered = QUEUE_ORDERED_NONE; + unsigned flush = 0; if (drive->dev_flags & IDE_DFLAG_WCACHE) { unsigned long long capacity; @@ -543,13 +543,12 @@ static void update_ordered(ide_drive_t *drive) drive->name, barrier ? "" : "not "); if (barrier) { - ordered = QUEUE_ORDERED_DRAIN_FLUSH; + flush = REQ_FLUSH; blk_queue_prep_rq(drive->queue, idedisk_prep_fn); } - } else - ordered = QUEUE_ORDERED_DRAIN; + } - blk_queue_ordered(drive->queue, ordered); + blk_queue_flush(drive->queue, flush); } ide_devset_get_flag(wcache, IDE_DFLAG_WCACHE); @@ -572,7 +571,7 @@ static int set_wcache(ide_drive_t *drive, int arg) } } - update_ordered(drive); + update_flush(drive); return err; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ac384b2a6a33..b1d92be8f990 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2245,7 +2245,7 @@ static int dm_init_request_based_queue(struct mapped_device *md) blk_queue_softirq_done(md->queue, dm_softirq_done); blk_queue_prep_rq(md->queue, dm_prep_fn); blk_queue_lld_busy(md->queue, dm_lld_busy); - blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH); + blk_queue_flush(md->queue, REQ_FLUSH); elv_register_queue(md->queue); diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index e876678176be..9c0b42bfe089 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -128,7 +128,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock mq->req = NULL; blk_queue_prep_rq(mq->queue, mmc_prep_request); - blk_queue_ordered(mq->queue, QUEUE_ORDERED_DRAIN); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue); if (mmc_can_erase(card)) { queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mq->queue); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 8373ca0de8e0..9b106d83b0cd 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2197,7 +2197,6 @@ static void dasd_setup_queue(struct dasd_block *block) */ blk_queue_max_segment_size(block->request_queue, PAGE_SIZE); blk_queue_segment_boundary(block->request_queue, PAGE_SIZE - 1); - blk_queue_ordered(block->request_queue, QUEUE_ORDERED_DRAIN); } /* diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index cdfc51ab9cf2..63bd01ae534f 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2109,7 +2109,7 @@ static int sd_revalidate_disk(struct gendisk *disk) struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdp = sdkp->device; unsigned char *buffer; - unsigned ordered; + unsigned flush = 0; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_revalidate_disk\n")); @@ -2151,15 +2151,15 @@ static int sd_revalidate_disk(struct gendisk *disk) /* * We now have all cache related info, determine how we deal - * with ordered requests. + * with flush requests. */ - if (sdkp->WCE) - ordered = sdkp->DPOFUA - ? QUEUE_ORDERED_DRAIN_FUA : QUEUE_ORDERED_DRAIN_FLUSH; - else - ordered = QUEUE_ORDERED_DRAIN; + if (sdkp->WCE) { + flush |= REQ_FLUSH; + if (sdkp->DPOFUA) + flush |= REQ_FUA; + } - blk_queue_ordered(sdkp->disk->queue, ordered); + blk_queue_flush(sdkp->disk->queue, flush); set_capacity(disk, sdkp->capacity); kfree(buffer); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7077bc0d6138..e97911d4dec3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -355,8 +355,10 @@ struct request_queue struct blk_trace *blk_trace; #endif /* - * reserved for flush operations + * for flush operations */ + unsigned int flush_flags; + unsigned int ordered, next_ordered, ordseq; int orderr, ordcolor; struct request pre_flush_rq, bar_rq, post_flush_rq; @@ -865,8 +867,8 @@ extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); +extern void blk_queue_flush(struct request_queue *q, unsigned int flush); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -extern int blk_queue_ordered(struct request_queue *, unsigned); extern bool blk_do_ordered(struct request_queue *, struct request **); extern unsigned blk_ordered_cur_seq(struct request_queue *); extern unsigned blk_ordered_req_seq(struct request *); -- cgit v1.2.3 From dd831006d5be7f74c3fe7aef82380c51c3637960 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Sep 2010 11:56:16 +0200 Subject: block: misc cleanups in barrier code Make the following cleanups in preparation of barrier/flush update. * blk_do_ordered() declaration is moved from include/linux/blkdev.h to block/blk.h. * blk_do_ordered() now returns pointer to struct request, with %NULL meaning "try the next request" and ERR_PTR(-EAGAIN) "try again later". The third case will be dropped with further changes. * In the initialization of proxy barrier request, data direction is already set by init_request_from_bio(). Drop unnecessary explicit REQ_WRITE setting and move init_request_from_bio() above REQ_FUA flag setting. * add_request() is collapsed into __make_request(). These changes don't make any functional difference. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-barrier.c | 32 ++++++++++++++------------------ block/blk-core.c | 21 ++++----------------- block/blk.h | 7 +++++-- include/linux/blkdev.h | 1 - 4 files changed, 23 insertions(+), 38 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index ed0aba5463ab..f1be85ba2bb5 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -110,9 +110,9 @@ static void queue_flush(struct request_queue *q, unsigned which) elv_insert(q, rq, ELEVATOR_INSERT_FRONT); } -static inline bool start_ordered(struct request_queue *q, struct request **rqp) +static inline struct request *start_ordered(struct request_queue *q, + struct request *rq) { - struct request *rq = *rqp; unsigned skip = 0; q->orderr = 0; @@ -149,11 +149,9 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp) /* initialize proxy request and queue it */ blk_rq_init(q, rq); - if (bio_data_dir(q->orig_bar_rq->bio) == WRITE) - rq->cmd_flags |= REQ_WRITE; + init_request_from_bio(rq, q->orig_bar_rq->bio); if (q->ordered & QUEUE_ORDERED_DO_FUA) rq->cmd_flags |= REQ_FUA; - init_request_from_bio(rq, q->orig_bar_rq->bio); rq->end_io = bar_end_io; elv_insert(q, rq, ELEVATOR_INSERT_FRONT); @@ -171,27 +169,26 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp) else skip |= QUEUE_ORDSEQ_DRAIN; - *rqp = rq; - /* * Complete skipped sequences. If whole sequence is complete, - * return false to tell elevator that this request is gone. + * return %NULL to tell elevator that this request is gone. */ - return !blk_ordered_complete_seq(q, skip, 0); + if (blk_ordered_complete_seq(q, skip, 0)) + rq = NULL; + return rq; } -bool blk_do_ordered(struct request_queue *q, struct request **rqp) +struct request *blk_do_ordered(struct request_queue *q, struct request *rq) { - struct request *rq = *rqp; const int is_barrier = rq->cmd_type == REQ_TYPE_FS && (rq->cmd_flags & REQ_HARDBARRIER); if (!q->ordseq) { if (!is_barrier) - return true; + return rq; if (q->next_ordered != QUEUE_ORDERED_NONE) - return start_ordered(q, rqp); + return start_ordered(q, rq); else { /* * Queue ordering not supported. Terminate @@ -199,8 +196,7 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp) */ blk_dequeue_request(rq); __blk_end_request_all(rq, -EOPNOTSUPP); - *rqp = NULL; - return false; + return NULL; } } @@ -211,14 +207,14 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp) /* Special requests are not subject to ordering rules. */ if (rq->cmd_type != REQ_TYPE_FS && rq != &q->pre_flush_rq && rq != &q->post_flush_rq) - return true; + return rq; /* Ordered by draining. Wait for turn. */ WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q)); if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q)) - *rqp = NULL; + rq = ERR_PTR(-EAGAIN); - return true; + return rq; } static void bio_end_empty_barrier(struct bio *bio, int err) diff --git a/block/blk-core.c b/block/blk-core.c index f06354183b29..f8d37a8e2c55 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1037,22 +1037,6 @@ void blk_insert_request(struct request_queue *q, struct request *rq, } EXPORT_SYMBOL(blk_insert_request); -/* - * add-request adds a request to the linked list. - * queue lock is held and interrupts disabled, as we muck with the - * request queue list. - */ -static inline void add_request(struct request_queue *q, struct request *req) -{ - drive_stat_acct(req, 1); - - /* - * elevator indicated where it wants this request to be - * inserted at elevator_merge time - */ - __elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0); -} - static void part_round_stats_single(int cpu, struct hd_struct *part, unsigned long now) { @@ -1316,7 +1300,10 @@ get_rq: req->cpu = blk_cpu_to_group(smp_processor_id()); if (queue_should_plug(q) && elv_queue_empty(q)) blk_plug_device(q); - add_request(q, req); + + /* insert the request into the elevator */ + drive_stat_acct(req, 1); + __elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0); out: if (unplug || !queue_should_plug(q)) __generic_unplug_device(q); diff --git a/block/blk.h b/block/blk.h index 6e7dc87141e4..874eb4ea8093 100644 --- a/block/blk.h +++ b/block/blk.h @@ -51,6 +51,8 @@ static inline void blk_clear_rq_complete(struct request *rq) */ #define ELV_ON_HASH(rq) (!hlist_unhashed(&(rq)->hash)) +struct request *blk_do_ordered(struct request_queue *q, struct request *rq); + static inline struct request *__elv_next_request(struct request_queue *q) { struct request *rq; @@ -58,8 +60,9 @@ static inline struct request *__elv_next_request(struct request_queue *q) while (1) { while (!list_empty(&q->queue_head)) { rq = list_entry_rq(q->queue_head.next); - if (blk_do_ordered(q, &rq)) - return rq; + rq = blk_do_ordered(q, rq); + if (rq) + return !IS_ERR(rq) ? rq : NULL; } if (!q->elevator->ops->elevator_dispatch_fn(q, 0)) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e97911d4dec3..996549d71923 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -869,7 +869,6 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush(struct request_queue *q, unsigned int flush); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -extern bool blk_do_ordered(struct request_queue *, struct request **); extern unsigned blk_ordered_cur_seq(struct request_queue *); extern unsigned blk_ordered_req_seq(struct request *); extern bool blk_ordered_complete_seq(struct request_queue *, unsigned, int); -- cgit v1.2.3 From 28e7d1845216538303bb95d679d8fd4de50e2f1a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Sep 2010 11:56:16 +0200 Subject: block: drop barrier ordering by queue draining Filesystems will take all the responsibilities for ordering requests around commit writes and will only indicate how the commit writes themselves should be handled by block layers. This patch drops barrier ordering by queue draining from block layer. Ordering by draining implementation was somewhat invasive to request handling. List of notable changes follow. * Each queue has 1 bit color which is flipped on each barrier issue. This is used to track whether a given request is issued before the current barrier or not. REQ_ORDERED_COLOR flag and coloring implementation in __elv_add_request() are removed. * Requests which shouldn't be processed yet for draining were stalled by returning -EAGAIN from blk_do_ordered() according to the test result between blk_ordered_req_seq() and blk_blk_ordered_cur_seq(). This logic is removed. * Draining completion logic in elv_completed_request() removed. * All barrier sequence requests were queued to request queue and then trckled to lower layer according to progress and thus maintaining request orders during requeue was necessary. This is replaced by queueing the next request in the barrier sequence only after the current one is complete from blk_ordered_complete_seq(), which removes the need for multiple proxy requests in struct request_queue and the request sorting logic in the ELEVATOR_INSERT_REQUEUE path of elv_insert(). * As barriers no longer have ordering constraints, there's no need to dump the whole elevator onto the dispatch queue on each barrier. Insert barriers at the front instead. * If other barrier requests come to the front of the dispatch queue while one is already in progress, they are stored in q->pending_barriers and restored to dispatch queue one-by-one after each barrier completion from blk_ordered_complete_seq(). Signed-off-by: Tejun Heo Cc: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 220 ++++++++++++++++++---------------------------- block/blk-core.c | 11 ++- block/blk.h | 2 +- block/elevator.c | 79 ++--------------- include/linux/blk_types.h | 2 - include/linux/blkdev.h | 19 ++-- 6 files changed, 113 insertions(+), 220 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index f1be85ba2bb5..e8b2e5c091b1 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -9,6 +9,8 @@ #include "blk.h" +static struct request *queue_next_ordseq(struct request_queue *q); + /* * Cache flushing for ordered writes handling */ @@ -19,38 +21,10 @@ unsigned blk_ordered_cur_seq(struct request_queue *q) return 1 << ffz(q->ordseq); } -unsigned blk_ordered_req_seq(struct request *rq) -{ - struct request_queue *q = rq->q; - - BUG_ON(q->ordseq == 0); - - if (rq == &q->pre_flush_rq) - return QUEUE_ORDSEQ_PREFLUSH; - if (rq == &q->bar_rq) - return QUEUE_ORDSEQ_BAR; - if (rq == &q->post_flush_rq) - return QUEUE_ORDSEQ_POSTFLUSH; - - /* - * !fs requests don't need to follow barrier ordering. Always - * put them at the front. This fixes the following deadlock. - * - * http://thread.gmane.org/gmane.linux.kernel/537473 - */ - if (rq->cmd_type != REQ_TYPE_FS) - return QUEUE_ORDSEQ_DRAIN; - - if ((rq->cmd_flags & REQ_ORDERED_COLOR) == - (q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR)) - return QUEUE_ORDSEQ_DRAIN; - else - return QUEUE_ORDSEQ_DONE; -} - -bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error) +static struct request *blk_ordered_complete_seq(struct request_queue *q, + unsigned seq, int error) { - struct request *rq; + struct request *next_rq = NULL; if (error && !q->orderr) q->orderr = error; @@ -58,16 +32,22 @@ bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error) BUG_ON(q->ordseq & seq); q->ordseq |= seq; - if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE) - return false; - - /* - * Okay, sequence complete. - */ - q->ordseq = 0; - rq = q->orig_bar_rq; - __blk_end_request_all(rq, q->orderr); - return true; + if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE) { + /* not complete yet, queue the next ordered sequence */ + next_rq = queue_next_ordseq(q); + } else { + /* complete this barrier request */ + __blk_end_request_all(q->orig_bar_rq, q->orderr); + q->orig_bar_rq = NULL; + q->ordseq = 0; + + /* dispatch the next barrier if there's one */ + if (!list_empty(&q->pending_barriers)) { + next_rq = list_entry_rq(q->pending_barriers.next); + list_move(&next_rq->queuelist, &q->queue_head); + } + } + return next_rq; } static void pre_flush_end_io(struct request *rq, int error) @@ -88,133 +68,105 @@ static void post_flush_end_io(struct request *rq, int error) blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error); } -static void queue_flush(struct request_queue *q, unsigned which) +static void queue_flush(struct request_queue *q, struct request *rq, + rq_end_io_fn *end_io) { - struct request *rq; - rq_end_io_fn *end_io; - - if (which == QUEUE_ORDERED_DO_PREFLUSH) { - rq = &q->pre_flush_rq; - end_io = pre_flush_end_io; - } else { - rq = &q->post_flush_rq; - end_io = post_flush_end_io; - } - blk_rq_init(q, rq); rq->cmd_type = REQ_TYPE_FS; - rq->cmd_flags = REQ_HARDBARRIER | REQ_FLUSH; + rq->cmd_flags = REQ_FLUSH; rq->rq_disk = q->orig_bar_rq->rq_disk; rq->end_io = end_io; elv_insert(q, rq, ELEVATOR_INSERT_FRONT); } -static inline struct request *start_ordered(struct request_queue *q, - struct request *rq) +static struct request *queue_next_ordseq(struct request_queue *q) { - unsigned skip = 0; - - q->orderr = 0; - q->ordered = q->next_ordered; - q->ordseq |= QUEUE_ORDSEQ_STARTED; - - /* - * For an empty barrier, there's no actual BAR request, which - * in turn makes POSTFLUSH unnecessary. Mask them off. - */ - if (!blk_rq_sectors(rq)) - q->ordered &= ~(QUEUE_ORDERED_DO_BAR | - QUEUE_ORDERED_DO_POSTFLUSH); - - /* stash away the original request */ - blk_dequeue_request(rq); - q->orig_bar_rq = rq; - rq = NULL; - - /* - * Queue ordered sequence. As we stack them at the head, we - * need to queue in reverse order. Note that we rely on that - * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs - * request gets inbetween ordered sequence. - */ - if (q->ordered & QUEUE_ORDERED_DO_POSTFLUSH) { - queue_flush(q, QUEUE_ORDERED_DO_POSTFLUSH); - rq = &q->post_flush_rq; - } else - skip |= QUEUE_ORDSEQ_POSTFLUSH; + struct request *rq = &q->bar_rq; - if (q->ordered & QUEUE_ORDERED_DO_BAR) { - rq = &q->bar_rq; + switch (blk_ordered_cur_seq(q)) { + case QUEUE_ORDSEQ_PREFLUSH: + queue_flush(q, rq, pre_flush_end_io); + break; + case QUEUE_ORDSEQ_BAR: /* initialize proxy request and queue it */ blk_rq_init(q, rq); init_request_from_bio(rq, q->orig_bar_rq->bio); + rq->cmd_flags &= ~REQ_HARDBARRIER; if (q->ordered & QUEUE_ORDERED_DO_FUA) rq->cmd_flags |= REQ_FUA; rq->end_io = bar_end_io; elv_insert(q, rq, ELEVATOR_INSERT_FRONT); - } else - skip |= QUEUE_ORDSEQ_BAR; + break; - if (q->ordered & QUEUE_ORDERED_DO_PREFLUSH) { - queue_flush(q, QUEUE_ORDERED_DO_PREFLUSH); - rq = &q->pre_flush_rq; - } else - skip |= QUEUE_ORDSEQ_PREFLUSH; + case QUEUE_ORDSEQ_POSTFLUSH: + queue_flush(q, rq, post_flush_end_io); + break; - if (queue_in_flight(q)) - rq = NULL; - else - skip |= QUEUE_ORDSEQ_DRAIN; - - /* - * Complete skipped sequences. If whole sequence is complete, - * return %NULL to tell elevator that this request is gone. - */ - if (blk_ordered_complete_seq(q, skip, 0)) - rq = NULL; + default: + BUG(); + } return rq; } struct request *blk_do_ordered(struct request_queue *q, struct request *rq) { - const int is_barrier = rq->cmd_type == REQ_TYPE_FS && - (rq->cmd_flags & REQ_HARDBARRIER); - - if (!q->ordseq) { - if (!is_barrier) - return rq; - - if (q->next_ordered != QUEUE_ORDERED_NONE) - return start_ordered(q, rq); - else { - /* - * Queue ordering not supported. Terminate - * with prejudice. - */ - blk_dequeue_request(rq); - __blk_end_request_all(rq, -EOPNOTSUPP); - return NULL; - } + unsigned skip = 0; + + if (!(rq->cmd_flags & REQ_HARDBARRIER)) + return rq; + + if (q->ordseq) { + /* + * Barrier is already in progress and they can't be + * processed in parallel. Queue for later processing. + */ + list_move_tail(&rq->queuelist, &q->pending_barriers); + return NULL; + } + + if (unlikely(q->next_ordered == QUEUE_ORDERED_NONE)) { + /* + * Queue ordering not supported. Terminate + * with prejudice. + */ + blk_dequeue_request(rq); + __blk_end_request_all(rq, -EOPNOTSUPP); + return NULL; } /* - * Ordered sequence in progress + * Start a new ordered sequence */ + q->orderr = 0; + q->ordered = q->next_ordered; + q->ordseq |= QUEUE_ORDSEQ_STARTED; - /* Special requests are not subject to ordering rules. */ - if (rq->cmd_type != REQ_TYPE_FS && - rq != &q->pre_flush_rq && rq != &q->post_flush_rq) - return rq; + /* + * For an empty barrier, there's no actual BAR request, which + * in turn makes POSTFLUSH unnecessary. Mask them off. + */ + if (!blk_rq_sectors(rq)) + q->ordered &= ~(QUEUE_ORDERED_DO_BAR | + QUEUE_ORDERED_DO_POSTFLUSH); - /* Ordered by draining. Wait for turn. */ - WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q)); - if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q)) - rq = ERR_PTR(-EAGAIN); + /* stash away the original request */ + blk_dequeue_request(rq); + q->orig_bar_rq = rq; - return rq; + if (!(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) + skip |= QUEUE_ORDSEQ_PREFLUSH; + + if (!(q->ordered & QUEUE_ORDERED_DO_BAR)) + skip |= QUEUE_ORDSEQ_BAR; + + if (!(q->ordered & QUEUE_ORDERED_DO_POSTFLUSH)) + skip |= QUEUE_ORDSEQ_POSTFLUSH; + + /* complete skipped sequences and return the first sequence */ + return blk_ordered_complete_seq(q, skip, 0); } static void bio_end_empty_barrier(struct bio *bio, int err) diff --git a/block/blk-core.c b/block/blk-core.c index f8d37a8e2c55..d316662682c8 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -520,6 +520,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) init_timer(&q->unplug_timer); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); INIT_LIST_HEAD(&q->timeout_list); + INIT_LIST_HEAD(&q->pending_barriers); INIT_WORK(&q->unplug_work, blk_unplug_work); kobject_init(&q->kobj, &blk_queue_ktype); @@ -1185,6 +1186,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) const bool sync = (bio->bi_rw & REQ_SYNC); const bool unplug = (bio->bi_rw & REQ_UNPLUG); const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK; + int where = ELEVATOR_INSERT_SORT; int rw_flags; /* REQ_HARDBARRIER is no more */ @@ -1203,7 +1205,12 @@ static int __make_request(struct request_queue *q, struct bio *bio) spin_lock_irq(q->queue_lock); - if (unlikely((bio->bi_rw & REQ_HARDBARRIER)) || elv_queue_empty(q)) + if (bio->bi_rw & REQ_HARDBARRIER) { + where = ELEVATOR_INSERT_FRONT; + goto get_rq; + } + + if (elv_queue_empty(q)) goto get_rq; el_ret = elv_merge(q, &req, bio); @@ -1303,7 +1310,7 @@ get_rq: /* insert the request into the elevator */ drive_stat_acct(req, 1); - __elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0); + __elv_add_request(q, req, where, 0); out: if (unplug || !queue_should_plug(q)) __generic_unplug_device(q); diff --git a/block/blk.h b/block/blk.h index 874eb4ea8093..08081e4b294e 100644 --- a/block/blk.h +++ b/block/blk.h @@ -62,7 +62,7 @@ static inline struct request *__elv_next_request(struct request_queue *q) rq = list_entry_rq(q->queue_head.next); rq = blk_do_ordered(q, rq); if (rq) - return !IS_ERR(rq) ? rq : NULL; + return rq; } if (!q->elevator->ops->elevator_dispatch_fn(q, 0)) diff --git a/block/elevator.c b/block/elevator.c index ec585c9554d3..241c69c45c5f 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -617,8 +617,6 @@ void elv_quiesce_end(struct request_queue *q) void elv_insert(struct request_queue *q, struct request *rq, int where) { - struct list_head *pos; - unsigned ordseq; int unplug_it = 1; trace_block_rq_insert(q, rq); @@ -626,9 +624,16 @@ void elv_insert(struct request_queue *q, struct request *rq, int where) rq->q = q; switch (where) { + case ELEVATOR_INSERT_REQUEUE: + /* + * Most requeues happen because of a busy condition, + * don't force unplug of the queue for that case. + * Clear unplug_it and fall through. + */ + unplug_it = 0; + case ELEVATOR_INSERT_FRONT: rq->cmd_flags |= REQ_SOFTBARRIER; - list_add(&rq->queuelist, &q->queue_head); break; @@ -668,36 +673,6 @@ void elv_insert(struct request_queue *q, struct request *rq, int where) q->elevator->ops->elevator_add_req_fn(q, rq); break; - case ELEVATOR_INSERT_REQUEUE: - /* - * If ordered flush isn't in progress, we do front - * insertion; otherwise, requests should be requeued - * in ordseq order. - */ - rq->cmd_flags |= REQ_SOFTBARRIER; - - /* - * Most requeues happen because of a busy condition, - * don't force unplug of the queue for that case. - */ - unplug_it = 0; - - if (q->ordseq == 0) { - list_add(&rq->queuelist, &q->queue_head); - break; - } - - ordseq = blk_ordered_req_seq(rq); - - list_for_each(pos, &q->queue_head) { - struct request *pos_rq = list_entry_rq(pos); - if (ordseq <= blk_ordered_req_seq(pos_rq)) - break; - } - - list_add_tail(&rq->queuelist, pos); - break; - default: printk(KERN_ERR "%s: bad insertion point %d\n", __func__, where); @@ -716,26 +691,8 @@ void elv_insert(struct request_queue *q, struct request *rq, int where) void __elv_add_request(struct request_queue *q, struct request *rq, int where, int plug) { - if (q->ordcolor) - rq->cmd_flags |= REQ_ORDERED_COLOR; - if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) { - /* - * toggle ordered color - */ - if (rq->cmd_flags & REQ_HARDBARRIER) - q->ordcolor ^= 1; - - /* - * barriers implicitly indicate back insertion - */ - if (where == ELEVATOR_INSERT_SORT) - where = ELEVATOR_INSERT_BACK; - - /* - * this request is scheduling boundary, update - * end_sector - */ + /* barriers are scheduling boundary, update end_sector */ if (rq->cmd_type == REQ_TYPE_FS || (rq->cmd_flags & REQ_DISCARD)) { q->end_sector = rq_end_sector(rq); @@ -855,24 +812,6 @@ void elv_completed_request(struct request_queue *q, struct request *rq) e->ops->elevator_completed_req_fn) e->ops->elevator_completed_req_fn(q, rq); } - - /* - * Check if the queue is waiting for fs requests to be - * drained for flush sequence. - */ - if (unlikely(q->ordseq)) { - struct request *next = NULL; - - if (!list_empty(&q->queue_head)) - next = list_entry_rq(q->queue_head.next); - - if (!queue_in_flight(q) && - blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN && - (!next || blk_ordered_req_seq(next) > QUEUE_ORDSEQ_DRAIN)) { - blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0); - __blk_run_queue(q); - } - } } #define to_elv(atr) container_of((atr), struct elv_fs_entry, attr) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index ca83a97c9715..9192282b4259 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -143,7 +143,6 @@ enum rq_flag_bits { __REQ_FAILED, /* set if the request failed */ __REQ_QUIET, /* don't worry about errors */ __REQ_PREEMPT, /* set for "ide_preempt" requests */ - __REQ_ORDERED_COLOR, /* is before or after barrier */ __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_COPY_USER, /* contains copies of user pages */ __REQ_INTEGRITY, /* integrity metadata has been remapped */ @@ -184,7 +183,6 @@ enum rq_flag_bits { #define REQ_FAILED (1 << __REQ_FAILED) #define REQ_QUIET (1 << __REQ_QUIET) #define REQ_PREEMPT (1 << __REQ_PREEMPT) -#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) #define REQ_ALLOCED (1 << __REQ_ALLOCED) #define REQ_COPY_USER (1 << __REQ_COPY_USER) #define REQ_INTEGRITY (1 << __REQ_INTEGRITY) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 996549d71923..20a3710a481b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -360,9 +360,10 @@ struct request_queue unsigned int flush_flags; unsigned int ordered, next_ordered, ordseq; - int orderr, ordcolor; - struct request pre_flush_rq, bar_rq, post_flush_rq; + int orderr; + struct request bar_rq; struct request *orig_bar_rq; + struct list_head pending_barriers; struct mutex sysfs_lock; @@ -491,12 +492,11 @@ enum { /* * Ordered operation sequence */ - QUEUE_ORDSEQ_STARTED = 0x01, /* flushing in progress */ - QUEUE_ORDSEQ_DRAIN = 0x02, /* waiting for the queue to be drained */ - QUEUE_ORDSEQ_PREFLUSH = 0x04, /* pre-flushing in progress */ - QUEUE_ORDSEQ_BAR = 0x08, /* original barrier req in progress */ - QUEUE_ORDSEQ_POSTFLUSH = 0x10, /* post-flushing in progress */ - QUEUE_ORDSEQ_DONE = 0x20, + QUEUE_ORDSEQ_STARTED = (1 << 0), /* flushing in progress */ + QUEUE_ORDSEQ_PREFLUSH = (1 << 1), /* pre-flushing in progress */ + QUEUE_ORDSEQ_BAR = (1 << 2), /* barrier write in progress */ + QUEUE_ORDSEQ_POSTFLUSH = (1 << 3), /* post-flushing in progress */ + QUEUE_ORDSEQ_DONE = (1 << 4), }; #define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) @@ -869,9 +869,6 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush(struct request_queue *q, unsigned int flush); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -extern unsigned blk_ordered_cur_seq(struct request_queue *); -extern unsigned blk_ordered_req_seq(struct request *); -extern bool blk_ordered_complete_seq(struct request_queue *, unsigned, int); extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); extern void blk_dump_rq_flags(struct request *, char *); -- cgit v1.2.3 From dd4c133f387c48f526022860ad70354637a80f4c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Sep 2010 11:56:16 +0200 Subject: block: rename barrier/ordered to flush With ordering requirements dropped, barrier and ordered are misnomers. Now all block layer does is sequencing FLUSH and FUA. Rename them to flush. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 21 ++++++----- block/blk-flush.c | 98 +++++++++++++++++++++++++------------------------- block/blk.h | 4 +-- include/linux/blkdev.h | 24 ++++++------- 4 files changed, 72 insertions(+), 75 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index d316662682c8..8870ae40179d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -136,7 +136,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio, { struct request_queue *q = rq->q; - if (&q->bar_rq != rq) { + if (&q->flush_rq != rq) { if (error) clear_bit(BIO_UPTODATE, &bio->bi_flags); else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) @@ -160,13 +160,12 @@ static void req_bio_endio(struct request *rq, struct bio *bio, if (bio->bi_size == 0) bio_endio(bio, error); } else { - /* - * Okay, this is the barrier request in progress, just - * record the error; + * Okay, this is the sequenced flush request in + * progress, just record the error; */ - if (error && !q->orderr) - q->orderr = error; + if (error && !q->flush_err) + q->flush_err = error; } } @@ -520,7 +519,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) init_timer(&q->unplug_timer); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); INIT_LIST_HEAD(&q->timeout_list); - INIT_LIST_HEAD(&q->pending_barriers); + INIT_LIST_HEAD(&q->pending_flushes); INIT_WORK(&q->unplug_work, blk_unplug_work); kobject_init(&q->kobj, &blk_queue_ktype); @@ -1764,11 +1763,11 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes) static void blk_account_io_done(struct request *req) { /* - * Account IO completion. bar_rq isn't accounted as a normal - * IO on queueing nor completion. Accounting the containing - * request is enough. + * Account IO completion. flush_rq isn't accounted as a + * normal IO on queueing nor completion. Accounting the + * containing request is enough. */ - if (blk_do_io_stat(req) && req != &req->q->bar_rq) { + if (blk_do_io_stat(req) && req != &req->q->flush_rq) { unsigned long duration = jiffies - req->start_time; const int rw = rq_data_dir(req); struct hd_struct *part; diff --git a/block/blk-flush.c b/block/blk-flush.c index e8b2e5c091b1..dd873225da97 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -9,41 +9,38 @@ #include "blk.h" -static struct request *queue_next_ordseq(struct request_queue *q); +static struct request *queue_next_fseq(struct request_queue *q); -/* - * Cache flushing for ordered writes handling - */ -unsigned blk_ordered_cur_seq(struct request_queue *q) +unsigned blk_flush_cur_seq(struct request_queue *q) { - if (!q->ordseq) + if (!q->flush_seq) return 0; - return 1 << ffz(q->ordseq); + return 1 << ffz(q->flush_seq); } -static struct request *blk_ordered_complete_seq(struct request_queue *q, - unsigned seq, int error) +static struct request *blk_flush_complete_seq(struct request_queue *q, + unsigned seq, int error) { struct request *next_rq = NULL; - if (error && !q->orderr) - q->orderr = error; + if (error && !q->flush_err) + q->flush_err = error; - BUG_ON(q->ordseq & seq); - q->ordseq |= seq; + BUG_ON(q->flush_seq & seq); + q->flush_seq |= seq; - if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE) { - /* not complete yet, queue the next ordered sequence */ - next_rq = queue_next_ordseq(q); + if (blk_flush_cur_seq(q) != QUEUE_FSEQ_DONE) { + /* not complete yet, queue the next flush sequence */ + next_rq = queue_next_fseq(q); } else { - /* complete this barrier request */ - __blk_end_request_all(q->orig_bar_rq, q->orderr); - q->orig_bar_rq = NULL; - q->ordseq = 0; - - /* dispatch the next barrier if there's one */ - if (!list_empty(&q->pending_barriers)) { - next_rq = list_entry_rq(q->pending_barriers.next); + /* complete this flush request */ + __blk_end_request_all(q->orig_flush_rq, q->flush_err); + q->orig_flush_rq = NULL; + q->flush_seq = 0; + + /* dispatch the next flush if there's one */ + if (!list_empty(&q->pending_flushes)) { + next_rq = list_entry_rq(q->pending_flushes.next); list_move(&next_rq->queuelist, &q->queue_head); } } @@ -53,19 +50,19 @@ static struct request *blk_ordered_complete_seq(struct request_queue *q, static void pre_flush_end_io(struct request *rq, int error) { elv_completed_request(rq->q, rq); - blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_PREFLUSH, error); + blk_flush_complete_seq(rq->q, QUEUE_FSEQ_PREFLUSH, error); } -static void bar_end_io(struct request *rq, int error) +static void flush_data_end_io(struct request *rq, int error) { elv_completed_request(rq->q, rq); - blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_BAR, error); + blk_flush_complete_seq(rq->q, QUEUE_FSEQ_DATA, error); } static void post_flush_end_io(struct request *rq, int error) { elv_completed_request(rq->q, rq); - blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error); + blk_flush_complete_seq(rq->q, QUEUE_FSEQ_POSTFLUSH, error); } static void queue_flush(struct request_queue *q, struct request *rq, @@ -74,34 +71,34 @@ static void queue_flush(struct request_queue *q, struct request *rq, blk_rq_init(q, rq); rq->cmd_type = REQ_TYPE_FS; rq->cmd_flags = REQ_FLUSH; - rq->rq_disk = q->orig_bar_rq->rq_disk; + rq->rq_disk = q->orig_flush_rq->rq_disk; rq->end_io = end_io; elv_insert(q, rq, ELEVATOR_INSERT_FRONT); } -static struct request *queue_next_ordseq(struct request_queue *q) +static struct request *queue_next_fseq(struct request_queue *q) { - struct request *rq = &q->bar_rq; + struct request *rq = &q->flush_rq; - switch (blk_ordered_cur_seq(q)) { - case QUEUE_ORDSEQ_PREFLUSH: + switch (blk_flush_cur_seq(q)) { + case QUEUE_FSEQ_PREFLUSH: queue_flush(q, rq, pre_flush_end_io); break; - case QUEUE_ORDSEQ_BAR: + case QUEUE_FSEQ_DATA: /* initialize proxy request and queue it */ blk_rq_init(q, rq); - init_request_from_bio(rq, q->orig_bar_rq->bio); + init_request_from_bio(rq, q->orig_flush_rq->bio); rq->cmd_flags &= ~REQ_HARDBARRIER; if (q->ordered & QUEUE_ORDERED_DO_FUA) rq->cmd_flags |= REQ_FUA; - rq->end_io = bar_end_io; + rq->end_io = flush_data_end_io; elv_insert(q, rq, ELEVATOR_INSERT_FRONT); break; - case QUEUE_ORDSEQ_POSTFLUSH: + case QUEUE_FSEQ_POSTFLUSH: queue_flush(q, rq, post_flush_end_io); break; @@ -111,19 +108,20 @@ static struct request *queue_next_ordseq(struct request_queue *q) return rq; } -struct request *blk_do_ordered(struct request_queue *q, struct request *rq) +struct request *blk_do_flush(struct request_queue *q, struct request *rq) { unsigned skip = 0; if (!(rq->cmd_flags & REQ_HARDBARRIER)) return rq; - if (q->ordseq) { + if (q->flush_seq) { /* - * Barrier is already in progress and they can't be - * processed in parallel. Queue for later processing. + * Sequenced flush is already in progress and they + * can't be processed in parallel. Queue for later + * processing. */ - list_move_tail(&rq->queuelist, &q->pending_barriers); + list_move_tail(&rq->queuelist, &q->pending_flushes); return NULL; } @@ -138,11 +136,11 @@ struct request *blk_do_ordered(struct request_queue *q, struct request *rq) } /* - * Start a new ordered sequence + * Start a new flush sequence */ - q->orderr = 0; + q->flush_err = 0; q->ordered = q->next_ordered; - q->ordseq |= QUEUE_ORDSEQ_STARTED; + q->flush_seq |= QUEUE_FSEQ_STARTED; /* * For an empty barrier, there's no actual BAR request, which @@ -154,19 +152,19 @@ struct request *blk_do_ordered(struct request_queue *q, struct request *rq) /* stash away the original request */ blk_dequeue_request(rq); - q->orig_bar_rq = rq; + q->orig_flush_rq = rq; if (!(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) - skip |= QUEUE_ORDSEQ_PREFLUSH; + skip |= QUEUE_FSEQ_PREFLUSH; if (!(q->ordered & QUEUE_ORDERED_DO_BAR)) - skip |= QUEUE_ORDSEQ_BAR; + skip |= QUEUE_FSEQ_DATA; if (!(q->ordered & QUEUE_ORDERED_DO_POSTFLUSH)) - skip |= QUEUE_ORDSEQ_POSTFLUSH; + skip |= QUEUE_FSEQ_POSTFLUSH; /* complete skipped sequences and return the first sequence */ - return blk_ordered_complete_seq(q, skip, 0); + return blk_flush_complete_seq(q, skip, 0); } static void bio_end_empty_barrier(struct bio *bio, int err) diff --git a/block/blk.h b/block/blk.h index 08081e4b294e..24b92bd78f37 100644 --- a/block/blk.h +++ b/block/blk.h @@ -51,7 +51,7 @@ static inline void blk_clear_rq_complete(struct request *rq) */ #define ELV_ON_HASH(rq) (!hlist_unhashed(&(rq)->hash)) -struct request *blk_do_ordered(struct request_queue *q, struct request *rq); +struct request *blk_do_flush(struct request_queue *q, struct request *rq); static inline struct request *__elv_next_request(struct request_queue *q) { @@ -60,7 +60,7 @@ static inline struct request *__elv_next_request(struct request_queue *q) while (1) { while (!list_empty(&q->queue_head)) { rq = list_entry_rq(q->queue_head.next); - rq = blk_do_ordered(q, rq); + rq = blk_do_flush(q, rq); if (rq) return rq; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 20a3710a481b..1cd83ec077db 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -357,13 +357,13 @@ struct request_queue /* * for flush operations */ + unsigned int ordered, next_ordered; unsigned int flush_flags; - - unsigned int ordered, next_ordered, ordseq; - int orderr; - struct request bar_rq; - struct request *orig_bar_rq; - struct list_head pending_barriers; + unsigned int flush_seq; + int flush_err; + struct request flush_rq; + struct request *orig_flush_rq; + struct list_head pending_flushes; struct mutex sysfs_lock; @@ -490,13 +490,13 @@ enum { QUEUE_ORDERED_DO_FUA, /* - * Ordered operation sequence + * FLUSH/FUA sequences. */ - QUEUE_ORDSEQ_STARTED = (1 << 0), /* flushing in progress */ - QUEUE_ORDSEQ_PREFLUSH = (1 << 1), /* pre-flushing in progress */ - QUEUE_ORDSEQ_BAR = (1 << 2), /* barrier write in progress */ - QUEUE_ORDSEQ_POSTFLUSH = (1 << 3), /* post-flushing in progress */ - QUEUE_ORDSEQ_DONE = (1 << 4), + QUEUE_FSEQ_STARTED = (1 << 0), /* flushing in progress */ + QUEUE_FSEQ_PREFLUSH = (1 << 1), /* pre-flushing in progress */ + QUEUE_FSEQ_DATA = (1 << 2), /* data write in progress */ + QUEUE_FSEQ_POSTFLUSH = (1 << 3), /* post-flushing in progress */ + QUEUE_FSEQ_DONE = (1 << 4), }; #define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) -- cgit v1.2.3 From 4fed947cb311e5aa51781d316cefca836352f6ce Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Sep 2010 11:56:17 +0200 Subject: block: implement REQ_FLUSH/FUA based interface for FLUSH/FUA requests Now that the backend conversion is complete, export sequenced FLUSH/FUA capability through REQ_FLUSH/FUA flags. REQ_FLUSH means the device cache should be flushed before executing the request. REQ_FUA means that the data in the request should be on non-volatile media on completion. Block layer will choose the correct way of implementing the semantics and execute it. The request may be passed to the device directly if the device can handle it; otherwise, it will be sequenced using one or more proxy requests. Devices will never see REQ_FLUSH and/or FUA which it doesn't support. Also, unlike the original REQ_HARDBARRIER, REQ_FLUSH/FUA requests are never failed with -EOPNOTSUPP. If the underlying device doesn't support FLUSH/FUA, the block layer simply make those noop. IOW, it no longer distinguishes between writeback cache which doesn't support cache flush and writethrough/no cache. Devices which have WB cache w/o flush are very difficult to come by these days and there's nothing much we can do anyway, so it doesn't make sense to require everyone to implement -EOPNOTSUPP handling. This will simplify filesystems and block drivers as they can drop -EOPNOTSUPP retry logic for barriers. * QUEUE_ORDERED_* are removed and QUEUE_FSEQ_* are moved into blk-flush.c. * REQ_FLUSH w/o data can also be directly passed to drivers without sequencing but some drivers assume that zero length requests don't have rq->bio which isn't true for these requests requiring the use of proxy requests. * REQ_COMMON_MASK now includes REQ_FLUSH | REQ_FUA so that they are copied from bio to request. * WRITE_BARRIER is marked deprecated and WRITE_FLUSH, WRITE_FUA and WRITE_FLUSH_FUA are added. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- block/blk-flush.c | 85 ++++++++++++++++++++++++--------------------- block/blk.h | 3 ++ include/linux/blk_types.h | 2 +- include/linux/blkdev.h | 38 ++------------------ include/linux/buffer_head.h | 2 +- include/linux/fs.h | 19 ++++++---- 7 files changed, 67 insertions(+), 84 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 8870ae40179d..18455c4f618a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1204,7 +1204,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) spin_lock_irq(q->queue_lock); - if (bio->bi_rw & REQ_HARDBARRIER) { + if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) { where = ELEVATOR_INSERT_FRONT; goto get_rq; } diff --git a/block/blk-flush.c b/block/blk-flush.c index dd873225da97..452c552e9ead 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -1,5 +1,5 @@ /* - * Functions related to barrier IO handling + * Functions to sequence FLUSH and FUA writes. */ #include #include @@ -9,6 +9,15 @@ #include "blk.h" +/* FLUSH/FUA sequences */ +enum { + QUEUE_FSEQ_STARTED = (1 << 0), /* flushing in progress */ + QUEUE_FSEQ_PREFLUSH = (1 << 1), /* pre-flushing in progress */ + QUEUE_FSEQ_DATA = (1 << 2), /* data write in progress */ + QUEUE_FSEQ_POSTFLUSH = (1 << 3), /* post-flushing in progress */ + QUEUE_FSEQ_DONE = (1 << 4), +}; + static struct request *queue_next_fseq(struct request_queue *q); unsigned blk_flush_cur_seq(struct request_queue *q) @@ -79,6 +88,7 @@ static void queue_flush(struct request_queue *q, struct request *rq, static struct request *queue_next_fseq(struct request_queue *q) { + struct request *orig_rq = q->orig_flush_rq; struct request *rq = &q->flush_rq; switch (blk_flush_cur_seq(q)) { @@ -87,12 +97,11 @@ static struct request *queue_next_fseq(struct request_queue *q) break; case QUEUE_FSEQ_DATA: - /* initialize proxy request and queue it */ + /* initialize proxy request, inherit FLUSH/FUA and queue it */ blk_rq_init(q, rq); - init_request_from_bio(rq, q->orig_flush_rq->bio); - rq->cmd_flags &= ~REQ_HARDBARRIER; - if (q->ordered & QUEUE_ORDERED_DO_FUA) - rq->cmd_flags |= REQ_FUA; + init_request_from_bio(rq, orig_rq->bio); + rq->cmd_flags &= ~(REQ_FLUSH | REQ_FUA); + rq->cmd_flags |= orig_rq->cmd_flags & (REQ_FLUSH | REQ_FUA); rq->end_io = flush_data_end_io; elv_insert(q, rq, ELEVATOR_INSERT_FRONT); @@ -110,60 +119,58 @@ static struct request *queue_next_fseq(struct request_queue *q) struct request *blk_do_flush(struct request_queue *q, struct request *rq) { + unsigned int fflags = q->flush_flags; /* may change, cache it */ + bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA; + bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH); + bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA); unsigned skip = 0; - if (!(rq->cmd_flags & REQ_HARDBARRIER)) + /* + * Special case. If there's data but flush is not necessary, + * the request can be issued directly. + * + * Flush w/o data should be able to be issued directly too but + * currently some drivers assume that rq->bio contains + * non-zero data if it isn't NULL and empty FLUSH requests + * getting here usually have bio's without data. + */ + if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) { + rq->cmd_flags &= ~REQ_FLUSH; + if (!has_fua) + rq->cmd_flags &= ~REQ_FUA; return rq; + } + /* + * Sequenced flushes can't be processed in parallel. If + * another one is already in progress, queue for later + * processing. + */ if (q->flush_seq) { - /* - * Sequenced flush is already in progress and they - * can't be processed in parallel. Queue for later - * processing. - */ list_move_tail(&rq->queuelist, &q->pending_flushes); return NULL; } - if (unlikely(q->next_ordered == QUEUE_ORDERED_NONE)) { - /* - * Queue ordering not supported. Terminate - * with prejudice. - */ - blk_dequeue_request(rq); - __blk_end_request_all(rq, -EOPNOTSUPP); - return NULL; - } - /* * Start a new flush sequence */ q->flush_err = 0; - q->ordered = q->next_ordered; q->flush_seq |= QUEUE_FSEQ_STARTED; - /* - * For an empty barrier, there's no actual BAR request, which - * in turn makes POSTFLUSH unnecessary. Mask them off. - */ - if (!blk_rq_sectors(rq)) - q->ordered &= ~(QUEUE_ORDERED_DO_BAR | - QUEUE_ORDERED_DO_POSTFLUSH); - - /* stash away the original request */ + /* adjust FLUSH/FUA of the original request and stash it away */ + rq->cmd_flags &= ~REQ_FLUSH; + if (!has_fua) + rq->cmd_flags &= ~REQ_FUA; blk_dequeue_request(rq); q->orig_flush_rq = rq; - if (!(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) + /* skip unneded sequences and return the first one */ + if (!do_preflush) skip |= QUEUE_FSEQ_PREFLUSH; - - if (!(q->ordered & QUEUE_ORDERED_DO_BAR)) + if (!blk_rq_sectors(rq)) skip |= QUEUE_FSEQ_DATA; - - if (!(q->ordered & QUEUE_ORDERED_DO_POSTFLUSH)) + if (!do_postflush) skip |= QUEUE_FSEQ_POSTFLUSH; - - /* complete skipped sequences and return the first sequence */ return blk_flush_complete_seq(q, skip, 0); } diff --git a/block/blk.h b/block/blk.h index 24b92bd78f37..a09c18b19116 100644 --- a/block/blk.h +++ b/block/blk.h @@ -60,6 +60,9 @@ static inline struct request *__elv_next_request(struct request_queue *q) while (1) { while (!list_empty(&q->queue_head)) { rq = list_entry_rq(q->queue_head.next); + if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) || + rq == &q->flush_rq) + return rq; rq = blk_do_flush(q, rq); if (rq) return rq; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 9192282b4259..179799479e6f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -167,7 +167,7 @@ enum rq_flag_bits { (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ - REQ_META| REQ_DISCARD | REQ_NOIDLE) + REQ_META | REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) #define REQ_UNPLUG (1 << __REQ_UNPLUG) #define REQ_RAHEAD (1 << __REQ_RAHEAD) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1cd83ec077db..8ef705f800ab 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -357,7 +357,6 @@ struct request_queue /* * for flush operations */ - unsigned int ordered, next_ordered; unsigned int flush_flags; unsigned int flush_seq; int flush_err; @@ -465,40 +464,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) __clear_bit(flag, &q->queue_flags); } -enum { - /* - * Hardbarrier is supported with one of the following methods. - * - * NONE : hardbarrier unsupported - * DRAIN : ordering by draining is enough - * DRAIN_FLUSH : ordering by draining w/ pre and post flushes - * DRAIN_FUA : ordering by draining w/ pre flush and FUA write - */ - QUEUE_ORDERED_DO_PREFLUSH = 0x10, - QUEUE_ORDERED_DO_BAR = 0x20, - QUEUE_ORDERED_DO_POSTFLUSH = 0x40, - QUEUE_ORDERED_DO_FUA = 0x80, - - QUEUE_ORDERED_NONE = 0x00, - - QUEUE_ORDERED_DRAIN = QUEUE_ORDERED_DO_BAR, - QUEUE_ORDERED_DRAIN_FLUSH = QUEUE_ORDERED_DRAIN | - QUEUE_ORDERED_DO_PREFLUSH | - QUEUE_ORDERED_DO_POSTFLUSH, - QUEUE_ORDERED_DRAIN_FUA = QUEUE_ORDERED_DRAIN | - QUEUE_ORDERED_DO_PREFLUSH | - QUEUE_ORDERED_DO_FUA, - - /* - * FLUSH/FUA sequences. - */ - QUEUE_FSEQ_STARTED = (1 << 0), /* flushing in progress */ - QUEUE_FSEQ_PREFLUSH = (1 << 1), /* pre-flushing in progress */ - QUEUE_FSEQ_DATA = (1 << 2), /* data write in progress */ - QUEUE_FSEQ_POSTFLUSH = (1 << 3), /* post-flushing in progress */ - QUEUE_FSEQ_DONE = (1 << 4), -}; - #define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) #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) @@ -578,7 +543,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync) * it already be started by driver. */ #define RQ_NOMERGE_FLAGS \ - (REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER) + (REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER | \ + REQ_FLUSH | REQ_FUA) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \ (((rq)->cmd_flags & REQ_DISCARD) || \ diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index ec94c12f21da..fc999f583fda 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -32,7 +32,7 @@ enum bh_state_bits { BH_Delay, /* Buffer is not yet allocated on disk */ BH_Boundary, /* Block is followed by a discontiguity */ BH_Write_EIO, /* I/O error on write */ - BH_Eopnotsupp, /* operation not supported (barrier) */ + BH_Eopnotsupp, /* DEPRECATED: operation not supported (barrier) */ BH_Unwritten, /* Buffer is allocated on disk but not written */ BH_Quiet, /* Buffer Error Prinks to be quiet */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 76041b614758..352c48627381 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -135,12 +135,13 @@ struct inodes_stat_t { * immediately after submission. The write equivalent * of READ_SYNC. * WRITE_ODIRECT_PLUG Special case write for O_DIRECT only. - * WRITE_BARRIER Like WRITE_SYNC, but tells the block layer that all - * previously submitted writes must be safely on storage - * before this one is started. Also guarantees that when - * this write is complete, it itself is also safely on - * storage. Prevents reordering of writes on both sides - * of this IO. + * WRITE_BARRIER DEPRECATED. Always fails. Use FLUSH/FUA instead. + * WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush. + * WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on + * non-volatile media on completion. + * WRITE_FLUSH_FUA Combination of WRITE_FLUSH and FUA. The IO is preceded + * by a cache flush and data is guaranteed to be on + * non-volatile media on completion. * */ #define RW_MASK REQ_WRITE @@ -158,6 +159,12 @@ struct inodes_stat_t { #define WRITE_META (WRITE | REQ_META) #define WRITE_BARRIER (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ REQ_HARDBARRIER) +#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ + REQ_FLUSH) +#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ + REQ_FUA) +#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ + REQ_FLUSH | REQ_FUA) /* * These aren't really reads or writes, they pass down information about -- cgit v1.2.3 From 2cf6d26a354ab6362e301b5a323832b02867df47 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 18 Aug 2010 05:29:10 -0400 Subject: block: pass gfp_mask and flags to sb_issue_discard We'll need to get rid of the BLKDEV_IFL_BARRIER flag, and to facilitate that and to make the interface less confusing pass all flags explicitly. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/ext4/mballoc.c | 3 ++- fs/fat/fatent.c | 4 +++- include/linux/blkdev.h | 11 +++++------ 3 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 4b4ad4b7ce57..df44b345f662 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2566,7 +2566,8 @@ static inline void ext4_issue_discard(struct super_block *sb, discard_block = block + ext4_group_first_block_no(sb, block_group); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); - ret = sb_issue_discard(sb, discard_block, count); + ret = sb_issue_discard(sb, discard_block, count, GFP_NOFS, + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); if (ret == EOPNOTSUPP) { ext4_warning(sb, "discard not supported, disabling"); clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD); diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 81184d3b75a3..3a56a82f5658 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -577,7 +577,9 @@ int fat_free_clusters(struct inode *inode, int cluster) sb_issue_discard(sb, fat_clus_to_blknr(sbi, first_cl), - nr_clus * sbi->sec_per_clus); + nr_clus * sbi->sec_per_clus, + GFP_NOFS, + BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); first_cl = cluster; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8ef705f800ab..6b305eb4a343 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -881,13 +881,12 @@ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); -static inline int sb_issue_discard(struct super_block *sb, - sector_t block, sector_t nr_blocks) +static inline int sb_issue_discard(struct super_block *sb, sector_t block, + sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { - block <<= (sb->s_blocksize_bits - 9); - nr_blocks <<= (sb->s_blocksize_bits - 9); - return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_NOFS, - BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); + return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9), + nr_blocks << (sb->s_blocksize_bits - 9), + gfp_mask, flags); } extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); -- cgit v1.2.3 From 8c5553678237b7121355108e03c36086037d8975 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 18 Aug 2010 05:29:22 -0400 Subject: block: remove the BLKDEV_IFL_BARRIER flag Remove support for barriers on discards, which is unused now. Also remove the DISCARD_NOBARRIER I/O type in favour of just setting the rw flags up locally in blkdev_issue_discard. tj: Also remove DISCARD_SECURE and use REQ_SECURE directly. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-lib.c | 18 ++---------------- include/linux/blkdev.h | 2 -- include/linux/fs.h | 8 -------- 3 files changed, 2 insertions(+), 26 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-lib.c b/block/blk-lib.c index c392029a104e..fe2e6ed0f510 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -39,8 +39,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, { DECLARE_COMPLETION_ONSTACK(wait); struct request_queue *q = bdev_get_queue(bdev); - int type = flags & BLKDEV_IFL_BARRIER ? - DISCARD_BARRIER : DISCARD_NOBARRIER; + int type = REQ_WRITE | REQ_DISCARD; unsigned int max_discard_sectors; struct bio *bio; int ret = 0; @@ -65,7 +64,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, if (flags & BLKDEV_IFL_SECURE) { if (!blk_queue_secdiscard(q)) return -EOPNOTSUPP; - type |= DISCARD_SECURE; + type |= REQ_SECURE; } while (nr_sects && !ret) { @@ -162,12 +161,6 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, bb.wait = &wait; bb.end_io = NULL; - if (flags & BLKDEV_IFL_BARRIER) { - /* issue async barrier before the data */ - ret = blkdev_issue_flush(bdev, gfp_mask, NULL, 0); - if (ret) - return ret; - } submit: ret = 0; while (nr_sects != 0) { @@ -199,13 +192,6 @@ submit: issued++; submit_bio(WRITE, bio); } - /* - * When all data bios are in flight. Send final barrier if requeted. - */ - if (nr_sects == 0 && flags & BLKDEV_IFL_BARRIER) - ret = blkdev_issue_flush(bdev, gfp_mask, NULL, - flags & BLKDEV_IFL_WAIT); - if (flags & BLKDEV_IFL_WAIT) /* Wait for bios in-flight */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6b305eb4a343..cfcb3a610605 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -869,11 +869,9 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, } enum{ BLKDEV_WAIT, /* wait for completion */ - BLKDEV_BARRIER, /* issue request with barrier */ BLKDEV_SECURE, /* secure discard */ }; #define BLKDEV_IFL_WAIT (1 << BLKDEV_WAIT) -#define BLKDEV_IFL_BARRIER (1 << BLKDEV_BARRIER) #define BLKDEV_IFL_SECURE (1 << BLKDEV_SECURE) extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *, unsigned long); diff --git a/include/linux/fs.h b/include/linux/fs.h index d6add69bc170..6b0f6e9993a3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -163,14 +163,6 @@ struct inodes_stat_t { #define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ REQ_FLUSH | REQ_FUA) -/* - * These aren't really reads or writes, they pass down information about - * parts of device that are now unused by the file system. - */ -#define DISCARD_NOBARRIER (WRITE | REQ_DISCARD) -#define DISCARD_BARRIER (WRITE | REQ_DISCARD | REQ_HARDBARRIER) -#define DISCARD_SECURE (DISCARD_NOBARRIER | REQ_SECURE) - #define SEL_IN 1 #define SEL_OUT 2 #define SEL_EX 4 -- cgit v1.2.3 From 13f05c8d8e98bbdce89158bfdb2e380940695a88 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 10 Sep 2010 20:50:10 +0200 Subject: block/scsi: Provide a limit on the number of integrity segments Some controllers have a hardware limit on the number of protection information scatter-gather list segments they can handle. Introduce a max_integrity_segments limit in the block layer and provide a new scsi_host_template setting that allows HBA drivers to provide a value suitable for the hardware. Add support for honoring the integrity segment limit when merging both bios and requests. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-integrity.c | 93 ++++++++++++++++++++++++++++++++++++----------- block/blk-merge.c | 23 +++++++----- block/blk-settings.c | 3 ++ block/blk-sysfs.c | 11 ++++++ block/blk.h | 8 ---- drivers/scsi/hosts.c | 1 + drivers/scsi/scsi_lib.c | 26 +++++++++---- drivers/scsi/scsi_sysfs.c | 2 + include/linux/bio.h | 4 ++ include/linux/blkdev.h | 33 +++++++++++++++-- include/scsi/scsi.h | 6 +++ include/scsi/scsi_host.h | 7 ++++ 12 files changed, 167 insertions(+), 50 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-integrity.c b/block/blk-integrity.c index edce1ef7933d..885cbb59967e 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -32,24 +32,37 @@ static struct kmem_cache *integrity_cachep; /** * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements - * @rq: request with integrity metadata attached + * @q: request queue + * @bio: bio with integrity metadata attached * * Description: Returns the number of elements required in a - * scatterlist corresponding to the integrity metadata in a request. + * scatterlist corresponding to the integrity metadata in a bio. */ -int blk_rq_count_integrity_sg(struct request *rq) +int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio) { - struct bio_vec *iv, *ivprv; - struct req_iterator iter; - unsigned int segments; + struct bio_vec *iv, *ivprv = NULL; + unsigned int segments = 0; + unsigned int seg_size = 0; + unsigned int i = 0; - ivprv = NULL; - segments = 0; + bio_for_each_integrity_vec(iv, bio, i) { - rq_for_each_integrity_segment(iv, rq, iter) { + if (ivprv) { + if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv)) + goto new_segment; + + if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv)) + goto new_segment; + + if (seg_size + iv->bv_len > queue_max_segment_size(q)) + goto new_segment; - if (!ivprv || !BIOVEC_PHYS_MERGEABLE(ivprv, iv)) + seg_size += iv->bv_len; + } else { +new_segment: segments++; + seg_size = iv->bv_len; + } ivprv = iv; } @@ -60,30 +73,34 @@ EXPORT_SYMBOL(blk_rq_count_integrity_sg); /** * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist - * @rq: request with integrity metadata attached + * @q: request queue + * @bio: bio with integrity metadata attached * @sglist: target scatterlist * * Description: Map the integrity vectors in request into a * scatterlist. The scatterlist must be big enough to hold all * elements. I.e. sized using blk_rq_count_integrity_sg(). */ -int blk_rq_map_integrity_sg(struct request *rq, struct scatterlist *sglist) +int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio, + struct scatterlist *sglist) { - struct bio_vec *iv, *ivprv; - struct req_iterator iter; - struct scatterlist *sg; - unsigned int segments; + struct bio_vec *iv, *ivprv = NULL; + struct scatterlist *sg = NULL; + unsigned int segments = 0; + unsigned int i = 0; - ivprv = NULL; - sg = NULL; - segments = 0; - - rq_for_each_integrity_segment(iv, rq, iter) { + bio_for_each_integrity_vec(iv, bio, i) { if (ivprv) { if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv)) goto new_segment; + if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv)) + goto new_segment; + + if (sg->length + iv->bv_len > queue_max_segment_size(q)) + goto new_segment; + sg->length += iv->bv_len; } else { new_segment: @@ -162,6 +179,40 @@ int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2) } EXPORT_SYMBOL(blk_integrity_compare); +int blk_integrity_merge_rq(struct request_queue *q, struct request *req, + struct request *next) +{ + if (blk_integrity_rq(req) != blk_integrity_rq(next)) + return -1; + + if (req->nr_integrity_segments + next->nr_integrity_segments > + q->limits.max_integrity_segments) + return -1; + + return 0; +} +EXPORT_SYMBOL(blk_integrity_merge_rq); + +int blk_integrity_merge_bio(struct request_queue *q, struct request *req, + struct bio *bio) +{ + int nr_integrity_segs; + struct bio *next = bio->bi_next; + + bio->bi_next = NULL; + nr_integrity_segs = blk_rq_count_integrity_sg(q, bio); + bio->bi_next = next; + + if (req->nr_integrity_segments + nr_integrity_segs > + q->limits.max_integrity_segments) + return -1; + + req->nr_integrity_segments += nr_integrity_segs; + + return 0; +} +EXPORT_SYMBOL(blk_integrity_merge_bio); + struct integrity_sysfs_entry { struct attribute attr; ssize_t (*show)(struct blk_integrity *, char *); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3b0cd4249671..6a725461654d 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -205,12 +205,11 @@ static inline int ll_new_hw_segment(struct request_queue *q, { int nr_phys_segs = bio_phys_segments(q, bio); - if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q)) { - req->cmd_flags |= REQ_NOMERGE; - if (req == q->last_merge) - q->last_merge = NULL; - return 0; - } + if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q)) + goto no_merge; + + if (bio_integrity(bio) && blk_integrity_merge_bio(q, req, bio)) + goto no_merge; /* * This will form the start of a new hw segment. Bump both @@ -218,6 +217,12 @@ static inline int ll_new_hw_segment(struct request_queue *q, */ req->nr_phys_segments += nr_phys_segs; return 1; + +no_merge: + req->cmd_flags |= REQ_NOMERGE; + if (req == q->last_merge) + q->last_merge = NULL; + return 0; } int ll_back_merge_fn(struct request_queue *q, struct request *req, @@ -301,6 +306,9 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, if (total_phys_segments > queue_max_segments(q)) return 0; + if (blk_integrity_rq(req) && blk_integrity_merge_rq(q, req, next)) + return 0; + /* Merge is OK... */ req->nr_phys_segments = total_phys_segments; return 1; @@ -372,9 +380,6 @@ static int attempt_merge(struct request_queue *q, struct request *req, || next->special) return 0; - if (blk_integrity_rq(req) != blk_integrity_rq(next)) - return 0; - /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn diff --git a/block/blk-settings.c b/block/blk-settings.c index 8d592b559bd3..f8f2ddf20613 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -111,6 +111,7 @@ EXPORT_SYMBOL_GPL(blk_queue_lld_busy); void blk_set_default_limits(struct queue_limits *lim) { lim->max_segments = BLK_MAX_SEGMENTS; + lim->max_integrity_segments = 0; lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; lim->max_sectors = BLK_DEF_MAX_SECTORS; @@ -509,6 +510,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, b->seg_boundary_mask); t->max_segments = min_not_zero(t->max_segments, b->max_segments); + t->max_integrity_segments = min_not_zero(t->max_integrity_segments, + b->max_integrity_segments); t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 001ab18078f5..b014f7739e98 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -112,6 +112,11 @@ static ssize_t queue_max_segments_show(struct request_queue *q, char *page) return queue_var_show(queue_max_segments(q), (page)); } +static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page) +{ + return queue_var_show(q->limits.max_integrity_segments, (page)); +} + static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) { if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags)) @@ -288,6 +293,11 @@ static struct queue_sysfs_entry queue_max_segments_entry = { .show = queue_max_segments_show, }; +static struct queue_sysfs_entry queue_max_integrity_segments_entry = { + .attr = {.name = "max_integrity_segments", .mode = S_IRUGO }, + .show = queue_max_integrity_segments_show, +}; + static struct queue_sysfs_entry queue_max_segment_size_entry = { .attr = {.name = "max_segment_size", .mode = S_IRUGO }, .show = queue_max_segment_size_show, @@ -375,6 +385,7 @@ static struct attribute *default_attrs[] = { &queue_max_hw_sectors_entry.attr, &queue_max_sectors_entry.attr, &queue_max_segments_entry.attr, + &queue_max_integrity_segments_entry.attr, &queue_max_segment_size_entry.attr, &queue_iosched_entry.attr, &queue_hw_sector_size_entry.attr, diff --git a/block/blk.h b/block/blk.h index 6e7dc87141e4..6738831ba447 100644 --- a/block/blk.h +++ b/block/blk.h @@ -132,14 +132,6 @@ static inline int queue_congestion_off_threshold(struct request_queue *q) return q->nr_congestion_off; } -#if defined(CONFIG_BLK_DEV_INTEGRITY) - -#define rq_for_each_integrity_segment(bvl, _rq, _iter) \ - __rq_for_each_bio(_iter.bio, _rq) \ - bip_for_each_vec(bvl, _iter.bio->bi_integrity, _iter.i) - -#endif /* BLK_DEV_INTEGRITY */ - static inline int blk_cpu_to_group(int cpu) { #ifdef CONFIG_SCHED_MC diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 8a8f803439e1..10478153641b 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -376,6 +376,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) shost->this_id = sht->this_id; shost->can_queue = sht->can_queue; shost->sg_tablesize = sht->sg_tablesize; + shost->sg_prot_tablesize = sht->sg_prot_tablesize; shost->cmd_per_lun = sht->cmd_per_lun; shost->unchecked_isa_dma = sht->unchecked_isa_dma; shost->use_clustering = sht->use_clustering; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 9ade720422c6..861c0b937ac9 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -968,11 +968,13 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb, */ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask) { - int error = scsi_init_sgtable(cmd->request, &cmd->sdb, gfp_mask); + struct request *rq = cmd->request; + + int error = scsi_init_sgtable(rq, &cmd->sdb, gfp_mask); if (error) goto err_exit; - if (blk_bidi_rq(cmd->request)) { + if (blk_bidi_rq(rq)) { struct scsi_data_buffer *bidi_sdb = kmem_cache_zalloc( scsi_sdb_cache, GFP_ATOMIC); if (!bidi_sdb) { @@ -980,28 +982,28 @@ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask) goto err_exit; } - cmd->request->next_rq->special = bidi_sdb; - error = scsi_init_sgtable(cmd->request->next_rq, bidi_sdb, - GFP_ATOMIC); + rq->next_rq->special = bidi_sdb; + error = scsi_init_sgtable(rq->next_rq, bidi_sdb, GFP_ATOMIC); if (error) goto err_exit; } - if (blk_integrity_rq(cmd->request)) { + if (blk_integrity_rq(rq)) { struct scsi_data_buffer *prot_sdb = cmd->prot_sdb; int ivecs, count; BUG_ON(prot_sdb == NULL); - ivecs = blk_rq_count_integrity_sg(cmd->request); + ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio); if (scsi_alloc_sgtable(prot_sdb, ivecs, gfp_mask)) { error = BLKPREP_DEFER; goto err_exit; } - count = blk_rq_map_integrity_sg(cmd->request, + count = blk_rq_map_integrity_sg(rq->q, rq->bio, prot_sdb->table.sgl); BUG_ON(unlikely(count > ivecs)); + BUG_ON(unlikely(count > queue_max_integrity_segments(rq->q))); cmd->prot_sdb = prot_sdb; cmd->prot_sdb->table.nents = count; @@ -1625,6 +1627,14 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, blk_queue_max_segments(q, min_t(unsigned short, shost->sg_tablesize, SCSI_MAX_SG_CHAIN_SEGMENTS)); + if (scsi_host_prot_dma(shost)) { + shost->sg_prot_tablesize = + min_not_zero(shost->sg_prot_tablesize, + (unsigned short)SCSI_MAX_PROT_SG_SEGMENTS); + BUG_ON(shost->sg_prot_tablesize < shost->sg_tablesize); + blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize); + } + blk_queue_max_hw_sectors(q, shost->max_sectors); blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost)); blk_queue_segment_boundary(q, shost->dma_boundary); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index c3f67373a4f8..20ad59dff730 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -251,6 +251,7 @@ shost_rd_attr(host_busy, "%hu\n"); shost_rd_attr(cmd_per_lun, "%hd\n"); shost_rd_attr(can_queue, "%hd\n"); shost_rd_attr(sg_tablesize, "%hu\n"); +shost_rd_attr(sg_prot_tablesize, "%hu\n"); shost_rd_attr(unchecked_isa_dma, "%d\n"); shost_rd_attr(prot_capabilities, "%u\n"); shost_rd_attr(prot_guard_type, "%hd\n"); @@ -262,6 +263,7 @@ static struct attribute *scsi_sysfs_shost_attrs[] = { &dev_attr_cmd_per_lun.attr, &dev_attr_can_queue.attr, &dev_attr_sg_tablesize.attr, + &dev_attr_sg_prot_tablesize.attr, &dev_attr_unchecked_isa_dma.attr, &dev_attr_proc_name.attr, &dev_attr_scan.attr, diff --git a/include/linux/bio.h b/include/linux/bio.h index 5274103434ad..2c3fd7421607 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -496,6 +496,10 @@ static inline struct bio *bio_list_get(struct bio_list *bl) #define bip_for_each_vec(bvl, bip, i) \ __bip_for_each_vec(bvl, bip, i, (bip)->bip_idx) +#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ + for_each_bio(_bio) \ + bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) + #define bio_integrity(bio) (bio->bi_integrity != NULL) extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c54906f678f..7e661106270a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -124,6 +124,9 @@ struct request { * physical address coalescing is performed. */ unsigned short nr_phys_segments; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + unsigned short nr_integrity_segments; +#endif unsigned short ioprio; @@ -243,6 +246,7 @@ struct queue_limits { unsigned short logical_block_size; unsigned short max_segments; + unsigned short max_integrity_segments; unsigned char misaligned; unsigned char discard_misaligned; @@ -1213,8 +1217,13 @@ struct blk_integrity { extern int blk_integrity_register(struct gendisk *, struct blk_integrity *); extern void blk_integrity_unregister(struct gendisk *); extern int blk_integrity_compare(struct gendisk *, struct gendisk *); -extern int blk_rq_map_integrity_sg(struct request *, struct scatterlist *); -extern int blk_rq_count_integrity_sg(struct request *); +extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, + struct scatterlist *); +extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); +extern int blk_integrity_merge_rq(struct request_queue *, struct request *, + struct request *); +extern int blk_integrity_merge_bio(struct request_queue *, struct request *, + struct bio *); static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev) @@ -1235,16 +1244,32 @@ static inline int blk_integrity_rq(struct request *rq) return bio_integrity(rq->bio); } +static inline void blk_queue_max_integrity_segments(struct request_queue *q, + unsigned int segs) +{ + q->limits.max_integrity_segments = segs; +} + +static inline unsigned short +queue_max_integrity_segments(struct request_queue *q) +{ + return q->limits.max_integrity_segments; +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ #define blk_integrity_rq(rq) (0) -#define blk_rq_count_integrity_sg(a) (0) -#define blk_rq_map_integrity_sg(a, b) (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) #endif /* CONFIG_BLK_DEV_INTEGRITY */ diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 8fcb6e0e9e72..d63533a4a59e 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -31,6 +31,12 @@ struct scsi_cmnd; #define SCSI_MAX_SG_CHAIN_SEGMENTS SCSI_MAX_SG_SEGMENTS #endif +/* + * DIX-capable adapters effectively support infinite chaining for the + * protection information scatterlist + */ +#define SCSI_MAX_PROT_SG_SEGMENTS 0xFFFF + /* * Special value for scanning to specify scanning or rescanning of all * possible channels, (target) ids, or luns on a given shost. diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index b7bdecb7b76e..d0a6a845f204 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -388,6 +388,7 @@ struct scsi_host_template { * of scatter-gather. */ unsigned short sg_tablesize; + unsigned short sg_prot_tablesize; /* * Set this if the host adapter has limitations beside segment count. @@ -599,6 +600,7 @@ struct Scsi_Host { int can_queue; short cmd_per_lun; short unsigned int sg_tablesize; + short unsigned int sg_prot_tablesize; short unsigned int max_sectors; unsigned long dma_boundary; /* @@ -823,6 +825,11 @@ static inline unsigned int scsi_host_get_prot(struct Scsi_Host *shost) return shost->prot_capabilities; } +static inline int scsi_host_prot_dma(struct Scsi_Host *shost) +{ + return shost->prot_capabilities >= SHOST_DIX_TYPE0_PROTECTION; +} + static inline unsigned int scsi_host_dif_capable(struct Scsi_Host *shost, unsigned int target_type) { static unsigned char cap[] = { 0, -- cgit v1.2.3 From 144177991ca624841ddbd1e7edff958fc0f6d1fe Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 15 Sep 2010 13:08:27 +0200 Subject: block: fix an address space warning in blk-map.c Change type of 2nd parameter of blk_rq_aligned() into unsigned long and remove unnecessary casting. Now we can call it with 'uaddr' instead of 'ubuf' in __blk_rq_map_user() so that it can remove following warnings from sparse: block/blk-map.c:57:31: warning: incorrect type in argument 2 (different address spaces) block/blk-map.c:57:31: expected void *addr block/blk-map.c:57:31: got void [noderef] *ubuf However blk_rq_map_kern() needs one more local variable to handle it. Signed-off-by: Namhyung Kim Signed-off-by: Jens Axboe --- block/blk-map.c | 5 +++-- include/linux/blkdev.h | 4 ++-- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-map.c b/block/blk-map.c index c65d7593f7f1..ac0f7d46db63 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -54,7 +54,7 @@ static int __blk_rq_map_user(struct request_queue *q, struct request *rq, * direct dma. else, set up kernel bounce buffers */ uaddr = (unsigned long) ubuf; - if (blk_rq_aligned(q, ubuf, len) && !map_data) + if (blk_rq_aligned(q, uaddr, len) && !map_data) bio = bio_map_user(q, NULL, uaddr, len, reading, gfp_mask); else bio = bio_copy_user(q, map_data, uaddr, len, reading, gfp_mask); @@ -288,6 +288,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, unsigned int len, gfp_t gfp_mask) { int reading = rq_data_dir(rq) == READ; + unsigned long addr = (unsigned long) kbuf; int do_copy = 0; struct bio *bio; int ret; @@ -297,7 +298,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, if (!len || !kbuf) return -EINVAL; - do_copy = !blk_rq_aligned(q, kbuf, len) || object_is_on_stack(kbuf); + do_copy = !blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf); if (do_copy) bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading); else diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7e661106270a..780824edac16 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1097,11 +1097,11 @@ static inline int queue_dma_alignment(struct request_queue *q) return q ? q->dma_alignment : 511; } -static inline int blk_rq_aligned(struct request_queue *q, void *addr, +static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask; - return !((unsigned long)addr & alignment) && !(len & alignment); + return !(addr & alignment) && !(len & alignment); } /* assumes size > 256 */ -- cgit v1.2.3 From e43473b7f223ec866f7db273697e76c337c390f9 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 15 Sep 2010 17:06:35 -0400 Subject: blkio: Core implementation of throttle policy o Actual implementation of throttling policy in block layer. Currently it implements READ and WRITE bytes per second throttling logic. IOPS throttling comes in later patches. Signed-off-by: Vivek Goyal Signed-off-by: Jens Axboe --- block/Kconfig | 12 + block/Makefile | 1 + block/blk-core.c | 24 ++ block/blk-throttle.c | 909 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/blk_types.h | 3 + include/linux/blkdev.h | 24 ++ init/Kconfig | 9 +- 7 files changed, 979 insertions(+), 3 deletions(-) create mode 100644 block/blk-throttle.c (limited to 'include/linux/blkdev.h') diff --git a/block/Kconfig b/block/Kconfig index 9be0b56eaee1..6c9213ef15a1 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -77,6 +77,18 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. +config BLK_DEV_THROTTLING + bool "Block layer bio throttling support" + depends on BLK_CGROUP=y && EXPERIMENTAL + default n + ---help--- + Block layer bio throttling support. It can be used to limit + the IO rate to a device. IO rate policies are per cgroup and + one needs to mount and use blkio cgroup controller for creating + cgroups and specifying per device IO rate policies. + + See Documentation/cgroups/blkio-controller.txt for more information. + endif # BLOCK config BLOCK_COMPAT diff --git a/block/Makefile b/block/Makefile index 0bb499a739cd..c850d5ef80a2 100644 --- a/block/Makefile +++ b/block/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \ obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o +obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o diff --git a/block/blk-core.c b/block/blk-core.c index 8d07c1b7e701..797d5095eb83 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -382,6 +382,7 @@ void blk_sync_queue(struct request_queue *q) del_timer_sync(&q->unplug_timer); del_timer_sync(&q->timeout); cancel_work_sync(&q->unplug_work); + throtl_shutdown_timer_wq(q); } EXPORT_SYMBOL(blk_sync_queue); @@ -459,6 +460,8 @@ void blk_cleanup_queue(struct request_queue *q) if (q->elevator) elevator_exit(q->elevator); + blk_throtl_exit(q); + blk_put_queue(q); } EXPORT_SYMBOL(blk_cleanup_queue); @@ -515,6 +518,11 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) return NULL; } + if (blk_throtl_init(q)) { + kmem_cache_free(blk_requestq_cachep, q); + return NULL; + } + setup_timer(&q->backing_dev_info.laptop_mode_wb_timer, laptop_mode_timer_fn, (unsigned long) q); init_timer(&q->unplug_timer); @@ -1522,6 +1530,15 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; } + blk_throtl_bio(q, &bio); + + /* + * If bio = NULL, bio has been throttled and will be submitted + * later. + */ + if (!bio) + break; + trace_block_bio_queue(q, bio); ret = q->make_request_fn(q, bio); @@ -2580,6 +2597,13 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *dwork, unsigned long delay) +{ + return queue_delayed_work(kblockd_workqueue, dwork, delay); +} +EXPORT_SYMBOL(kblockd_schedule_delayed_work); + int __init blk_dev_init(void) { BUILD_BUG_ON(__REQ_NR_BITS > 8 * diff --git a/block/blk-throttle.c b/block/blk-throttle.c new file mode 100644 index 000000000000..4b492011e0de --- /dev/null +++ b/block/blk-throttle.c @@ -0,0 +1,909 @@ +/* + * Interface for controlling IO bandwidth on a request queue + * + * Copyright (C) 2010 Vivek Goyal + */ + +#include +#include +#include +#include +#include +#include "blk-cgroup.h" + +/* Max dispatch from a group in 1 round */ +static int throtl_grp_quantum = 8; + +/* Total max dispatch from all groups in one round */ +static int throtl_quantum = 32; + +/* Throttling is performed over 100ms slice and after that slice is renewed */ +static unsigned long throtl_slice = HZ/10; /* 100 ms */ + +struct throtl_rb_root { + struct rb_root rb; + struct rb_node *left; + unsigned int count; + unsigned long min_disptime; +}; + +#define THROTL_RB_ROOT (struct throtl_rb_root) { .rb = RB_ROOT, .left = NULL, \ + .count = 0, .min_disptime = 0} + +#define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node) + +struct throtl_grp { + /* List of throtl groups on the request queue*/ + struct hlist_node tg_node; + + /* active throtl group service_tree member */ + struct rb_node rb_node; + + /* + * Dispatch time in jiffies. This is the estimated time when group + * will unthrottle and is ready to dispatch more bio. It is used as + * key to sort active groups in service tree. + */ + unsigned long disptime; + + struct blkio_group blkg; + atomic_t ref; + unsigned int flags; + + /* Two lists for READ and WRITE */ + struct bio_list bio_lists[2]; + + /* Number of queued bios on READ and WRITE lists */ + unsigned int nr_queued[2]; + + /* bytes per second rate limits */ + uint64_t bps[2]; + + /* Number of bytes disptached in current slice */ + uint64_t bytes_disp[2]; + + /* When did we start a new slice */ + unsigned long slice_start[2]; + unsigned long slice_end[2]; +}; + +struct throtl_data +{ + /* List of throtl groups */ + struct hlist_head tg_list; + + /* service tree for active throtl groups */ + struct throtl_rb_root tg_service_tree; + + struct throtl_grp root_tg; + struct request_queue *queue; + + /* Total Number of queued bios on READ and WRITE lists */ + unsigned int nr_queued[2]; + + /* + * number of total undestroyed groups (excluding root group) + */ + unsigned int nr_undestroyed_grps; + + /* Work for dispatching throttled bios */ + struct delayed_work throtl_work; +}; + +enum tg_state_flags { + THROTL_TG_FLAG_on_rr = 0, /* on round-robin busy list */ +}; + +#define THROTL_TG_FNS(name) \ +static inline void throtl_mark_tg_##name(struct throtl_grp *tg) \ +{ \ + (tg)->flags |= (1 << THROTL_TG_FLAG_##name); \ +} \ +static inline void throtl_clear_tg_##name(struct throtl_grp *tg) \ +{ \ + (tg)->flags &= ~(1 << THROTL_TG_FLAG_##name); \ +} \ +static inline int throtl_tg_##name(const struct throtl_grp *tg) \ +{ \ + return ((tg)->flags & (1 << THROTL_TG_FLAG_##name)) != 0; \ +} + +THROTL_TG_FNS(on_rr); + +#define throtl_log_tg(td, tg, fmt, args...) \ + blk_add_trace_msg((td)->queue, "throtl %s " fmt, \ + blkg_path(&(tg)->blkg), ##args); \ + +#define throtl_log(td, fmt, args...) \ + blk_add_trace_msg((td)->queue, "throtl " fmt, ##args) + +static inline struct throtl_grp *tg_of_blkg(struct blkio_group *blkg) +{ + if (blkg) + return container_of(blkg, struct throtl_grp, blkg); + + return NULL; +} + +static inline int total_nr_queued(struct throtl_data *td) +{ + return (td->nr_queued[0] + td->nr_queued[1]); +} + +static inline struct throtl_grp *throtl_ref_get_tg(struct throtl_grp *tg) +{ + atomic_inc(&tg->ref); + return tg; +} + +static void throtl_put_tg(struct throtl_grp *tg) +{ + BUG_ON(atomic_read(&tg->ref) <= 0); + if (!atomic_dec_and_test(&tg->ref)) + return; + kfree(tg); +} + +static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td, + struct cgroup *cgroup) +{ + struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup); + struct throtl_grp *tg = NULL; + void *key = td; + struct backing_dev_info *bdi = &td->queue->backing_dev_info; + unsigned int major, minor; + + /* + * TODO: Speed up blkiocg_lookup_group() by maintaining a radix + * tree of blkg (instead of traversing through hash list all + * the time. + */ + tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key)); + + /* Fill in device details for root group */ + if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) { + sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); + tg->blkg.dev = MKDEV(major, minor); + goto done; + } + + if (tg) + goto done; + + tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node); + if (!tg) + goto done; + + INIT_HLIST_NODE(&tg->tg_node); + RB_CLEAR_NODE(&tg->rb_node); + bio_list_init(&tg->bio_lists[0]); + bio_list_init(&tg->bio_lists[1]); + + /* + * Take the initial reference that will be released on destroy + * This can be thought of a joint reference by cgroup and + * request queue which will be dropped by either request queue + * exit or cgroup deletion path depending on who is exiting first. + */ + atomic_set(&tg->ref, 1); + + /* Add group onto cgroup list */ + sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); + blkiocg_add_blkio_group(blkcg, &tg->blkg, (void *)td, + MKDEV(major, minor), BLKIO_POLICY_THROTL); + + tg->bps[READ] = blkcg_get_read_bps(blkcg, tg->blkg.dev); + tg->bps[WRITE] = blkcg_get_write_bps(blkcg, tg->blkg.dev); + + hlist_add_head(&tg->tg_node, &td->tg_list); + td->nr_undestroyed_grps++; +done: + return tg; +} + +static struct throtl_grp * throtl_get_tg(struct throtl_data *td) +{ + struct cgroup *cgroup; + struct throtl_grp *tg = NULL; + + rcu_read_lock(); + cgroup = task_cgroup(current, blkio_subsys_id); + tg = throtl_find_alloc_tg(td, cgroup); + if (!tg) + tg = &td->root_tg; + rcu_read_unlock(); + return tg; +} + +static struct throtl_grp *throtl_rb_first(struct throtl_rb_root *root) +{ + /* Service tree is empty */ + if (!root->count) + return NULL; + + if (!root->left) + root->left = rb_first(&root->rb); + + if (root->left) + return rb_entry_tg(root->left); + + return NULL; +} + +static void rb_erase_init(struct rb_node *n, struct rb_root *root) +{ + rb_erase(n, root); + RB_CLEAR_NODE(n); +} + +static void throtl_rb_erase(struct rb_node *n, struct throtl_rb_root *root) +{ + if (root->left == n) + root->left = NULL; + rb_erase_init(n, &root->rb); + --root->count; +} + +static void update_min_dispatch_time(struct throtl_rb_root *st) +{ + struct throtl_grp *tg; + + tg = throtl_rb_first(st); + if (!tg) + return; + + st->min_disptime = tg->disptime; +} + +static void +tg_service_tree_add(struct throtl_rb_root *st, struct throtl_grp *tg) +{ + struct rb_node **node = &st->rb.rb_node; + struct rb_node *parent = NULL; + struct throtl_grp *__tg; + unsigned long key = tg->disptime; + int left = 1; + + while (*node != NULL) { + parent = *node; + __tg = rb_entry_tg(parent); + + if (time_before(key, __tg->disptime)) + node = &parent->rb_left; + else { + node = &parent->rb_right; + left = 0; + } + } + + if (left) + st->left = &tg->rb_node; + + rb_link_node(&tg->rb_node, parent, node); + rb_insert_color(&tg->rb_node, &st->rb); +} + +static void __throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + struct throtl_rb_root *st = &td->tg_service_tree; + + tg_service_tree_add(st, tg); + throtl_mark_tg_on_rr(tg); + st->count++; +} + +static void throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + if (!throtl_tg_on_rr(tg)) + __throtl_enqueue_tg(td, tg); +} + +static void __throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + throtl_rb_erase(&tg->rb_node, &td->tg_service_tree); + throtl_clear_tg_on_rr(tg); +} + +static void throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + if (throtl_tg_on_rr(tg)) + __throtl_dequeue_tg(td, tg); +} + +static void throtl_schedule_next_dispatch(struct throtl_data *td) +{ + struct throtl_rb_root *st = &td->tg_service_tree; + + /* + * If there are more bios pending, schedule more work. + */ + if (!total_nr_queued(td)) + return; + + BUG_ON(!st->count); + + update_min_dispatch_time(st); + + if (time_before_eq(st->min_disptime, jiffies)) + throtl_schedule_delayed_work(td->queue, 0); + else + throtl_schedule_delayed_work(td->queue, + (st->min_disptime - jiffies)); +} + +static inline void +throtl_start_new_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw) +{ + tg->bytes_disp[rw] = 0; + tg->slice_start[rw] = jiffies; + tg->slice_end[rw] = jiffies + throtl_slice; + throtl_log_tg(td, tg, "[%c] new slice start=%lu end=%lu jiffies=%lu", + rw == READ ? 'R' : 'W', tg->slice_start[rw], + tg->slice_end[rw], jiffies); +} + +static inline void throtl_extend_slice(struct throtl_data *td, + struct throtl_grp *tg, bool rw, unsigned long jiffy_end) +{ + tg->slice_end[rw] = roundup(jiffy_end, throtl_slice); + throtl_log_tg(td, tg, "[%c] extend slice start=%lu end=%lu jiffies=%lu", + rw == READ ? 'R' : 'W', tg->slice_start[rw], + tg->slice_end[rw], jiffies); +} + +/* Determine if previously allocated or extended slice is complete or not */ +static bool +throtl_slice_used(struct throtl_data *td, struct throtl_grp *tg, bool rw) +{ + if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw])) + return 0; + + return 1; +} + +/* Trim the used slices and adjust slice start accordingly */ +static inline void +throtl_trim_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw) +{ + unsigned long nr_slices, bytes_trim, time_elapsed; + + BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw])); + + /* + * If bps are unlimited (-1), then time slice don't get + * renewed. Don't try to trim the slice if slice is used. A new + * slice will start when appropriate. + */ + if (throtl_slice_used(td, tg, rw)) + return; + + time_elapsed = jiffies - tg->slice_start[rw]; + + nr_slices = time_elapsed / throtl_slice; + + if (!nr_slices) + return; + + bytes_trim = (tg->bps[rw] * throtl_slice * nr_slices)/HZ; + + if (!bytes_trim) + return; + + if (tg->bytes_disp[rw] >= bytes_trim) + tg->bytes_disp[rw] -= bytes_trim; + else + tg->bytes_disp[rw] = 0; + + tg->slice_start[rw] += nr_slices * throtl_slice; + + throtl_log_tg(td, tg, "[%c] trim slice nr=%lu bytes=%lu" + " start=%lu end=%lu jiffies=%lu", + rw == READ ? 'R' : 'W', nr_slices, bytes_trim, + tg->slice_start[rw], tg->slice_end[rw], jiffies); +} + +/* + * Returns whether one can dispatch a bio or not. Also returns approx number + * of jiffies to wait before this bio is with-in IO rate and can be dispatched + */ +static bool tg_may_dispatch(struct throtl_data *td, struct throtl_grp *tg, + struct bio *bio, unsigned long *wait) +{ + bool rw = bio_data_dir(bio); + u64 bytes_allowed, extra_bytes; + unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; + + /* + * Currently whole state machine of group depends on first bio + * queued in the group bio list. So one should not be calling + * this function with a different bio if there are other bios + * queued. + */ + BUG_ON(tg->nr_queued[rw] && bio != bio_list_peek(&tg->bio_lists[rw])); + + /* If tg->bps = -1, then BW is unlimited */ + if (tg->bps[rw] == -1) { + if (wait) + *wait = 0; + return 1; + } + + /* + * If previous slice expired, start a new one otherwise renew/extend + * existing slice to make sure it is at least throtl_slice interval + * long since now. + */ + if (throtl_slice_used(td, tg, rw)) + throtl_start_new_slice(td, tg, rw); + else { + if (time_before(tg->slice_end[rw], jiffies + throtl_slice)) + throtl_extend_slice(td, tg, rw, jiffies + throtl_slice); + } + + jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw]; + + /* Slice has just started. Consider one slice interval */ + if (!jiffy_elapsed) + jiffy_elapsed_rnd = throtl_slice; + + jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice); + + bytes_allowed = (tg->bps[rw] * jiffies_to_msecs(jiffy_elapsed_rnd)) + / MSEC_PER_SEC; + + if (tg->bytes_disp[rw] + bio->bi_size <= bytes_allowed) { + if (wait) + *wait = 0; + return 1; + } + + /* Calc approx time to dispatch */ + extra_bytes = tg->bytes_disp[rw] + bio->bi_size - bytes_allowed; + jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]); + + if (!jiffy_wait) + jiffy_wait = 1; + + /* + * This wait time is without taking into consideration the rounding + * up we did. Add that time also. + */ + jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed); + + if (wait) + *wait = jiffy_wait; + + if (time_before(tg->slice_end[rw], jiffies + jiffy_wait)) + throtl_extend_slice(td, tg, rw, jiffies + jiffy_wait); + + return 0; +} + +static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) +{ + bool rw = bio_data_dir(bio); + bool sync = bio->bi_rw & REQ_SYNC; + + /* Charge the bio to the group */ + tg->bytes_disp[rw] += bio->bi_size; + + /* + * TODO: This will take blkg->stats_lock. Figure out a way + * to avoid this cost. + */ + blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size, rw, sync); + +} + +static void throtl_add_bio_tg(struct throtl_data *td, struct throtl_grp *tg, + struct bio *bio) +{ + bool rw = bio_data_dir(bio); + + bio_list_add(&tg->bio_lists[rw], bio); + /* Take a bio reference on tg */ + throtl_ref_get_tg(tg); + tg->nr_queued[rw]++; + td->nr_queued[rw]++; + throtl_enqueue_tg(td, tg); +} + +static void tg_update_disptime(struct throtl_data *td, struct throtl_grp *tg) +{ + unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime; + struct bio *bio; + + if ((bio = bio_list_peek(&tg->bio_lists[READ]))) + tg_may_dispatch(td, tg, bio, &read_wait); + + if ((bio = bio_list_peek(&tg->bio_lists[WRITE]))) + tg_may_dispatch(td, tg, bio, &write_wait); + + min_wait = min(read_wait, write_wait); + disptime = jiffies + min_wait; + + /* + * If group is already on active tree, then update dispatch time + * only if it is lesser than existing dispatch time. Otherwise + * always update the dispatch time + */ + + if (throtl_tg_on_rr(tg) && time_before(disptime, tg->disptime)) + return; + + /* Update dispatch time */ + throtl_dequeue_tg(td, tg); + tg->disptime = disptime; + throtl_enqueue_tg(td, tg); +} + +static void tg_dispatch_one_bio(struct throtl_data *td, struct throtl_grp *tg, + bool rw, struct bio_list *bl) +{ + struct bio *bio; + + bio = bio_list_pop(&tg->bio_lists[rw]); + tg->nr_queued[rw]--; + /* Drop bio reference on tg */ + throtl_put_tg(tg); + + BUG_ON(td->nr_queued[rw] <= 0); + td->nr_queued[rw]--; + + throtl_charge_bio(tg, bio); + bio_list_add(bl, bio); + bio->bi_rw |= REQ_THROTTLED; + + throtl_trim_slice(td, tg, rw); +} + +static int throtl_dispatch_tg(struct throtl_data *td, struct throtl_grp *tg, + struct bio_list *bl) +{ + unsigned int nr_reads = 0, nr_writes = 0; + unsigned int max_nr_reads = throtl_grp_quantum*3/4; + unsigned int max_nr_writes = throtl_grp_quantum - nr_reads; + struct bio *bio; + + /* Try to dispatch 75% READS and 25% WRITES */ + + while ((bio = bio_list_peek(&tg->bio_lists[READ])) + && tg_may_dispatch(td, tg, bio, NULL)) { + + tg_dispatch_one_bio(td, tg, bio_data_dir(bio), bl); + nr_reads++; + + if (nr_reads >= max_nr_reads) + break; + } + + while ((bio = bio_list_peek(&tg->bio_lists[WRITE])) + && tg_may_dispatch(td, tg, bio, NULL)) { + + tg_dispatch_one_bio(td, tg, bio_data_dir(bio), bl); + nr_writes++; + + if (nr_writes >= max_nr_writes) + break; + } + + return nr_reads + nr_writes; +} + +static int throtl_select_dispatch(struct throtl_data *td, struct bio_list *bl) +{ + unsigned int nr_disp = 0; + struct throtl_grp *tg; + struct throtl_rb_root *st = &td->tg_service_tree; + + while (1) { + tg = throtl_rb_first(st); + + if (!tg) + break; + + if (time_before(jiffies, tg->disptime)) + break; + + throtl_dequeue_tg(td, tg); + + nr_disp += throtl_dispatch_tg(td, tg, bl); + + if (tg->nr_queued[0] || tg->nr_queued[1]) { + tg_update_disptime(td, tg); + throtl_enqueue_tg(td, tg); + } + + if (nr_disp >= throtl_quantum) + break; + } + + return nr_disp; +} + +/* Dispatch throttled bios. Should be called without queue lock held. */ +static int throtl_dispatch(struct request_queue *q) +{ + struct throtl_data *td = q->td; + unsigned int nr_disp = 0; + struct bio_list bio_list_on_stack; + struct bio *bio; + + spin_lock_irq(q->queue_lock); + + if (!total_nr_queued(td)) + goto out; + + bio_list_init(&bio_list_on_stack); + + throtl_log(td, "dispatch nr_queued=%lu read=%u write=%u", + total_nr_queued(td), td->nr_queued[READ], + td->nr_queued[WRITE]); + + nr_disp = throtl_select_dispatch(td, &bio_list_on_stack); + + if (nr_disp) + throtl_log(td, "bios disp=%u", nr_disp); + + throtl_schedule_next_dispatch(td); +out: + spin_unlock_irq(q->queue_lock); + + /* + * If we dispatched some requests, unplug the queue to make sure + * immediate dispatch + */ + if (nr_disp) { + while((bio = bio_list_pop(&bio_list_on_stack))) + generic_make_request(bio); + blk_unplug(q); + } + return nr_disp; +} + +void blk_throtl_work(struct work_struct *work) +{ + struct throtl_data *td = container_of(work, struct throtl_data, + throtl_work.work); + struct request_queue *q = td->queue; + + throtl_dispatch(q); +} + +/* Call with queue lock held */ +void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) +{ + + struct throtl_data *td = q->td; + struct delayed_work *dwork = &td->throtl_work; + + if (total_nr_queued(td) > 0) { + /* + * We might have a work scheduled to be executed in future. + * Cancel that and schedule a new one. + */ + __cancel_delayed_work(dwork); + kblockd_schedule_delayed_work(q, dwork, delay); + throtl_log(td, "schedule work. delay=%lu jiffies=%lu", + delay, jiffies); + } +} +EXPORT_SYMBOL(throtl_schedule_delayed_work); + +static void +throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + /* Something wrong if we are trying to remove same group twice */ + BUG_ON(hlist_unhashed(&tg->tg_node)); + + hlist_del_init(&tg->tg_node); + + /* + * Put the reference taken at the time of creation so that when all + * queues are gone, group can be destroyed. + */ + throtl_put_tg(tg); + td->nr_undestroyed_grps--; +} + +static void throtl_release_tgs(struct throtl_data *td) +{ + struct hlist_node *pos, *n; + struct throtl_grp *tg; + + hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) { + /* + * If cgroup removal path got to blk_group first and removed + * it from cgroup list, then it will take care of destroying + * cfqg also. + */ + if (!blkiocg_del_blkio_group(&tg->blkg)) + throtl_destroy_tg(td, tg); + } +} + +static void throtl_td_free(struct throtl_data *td) +{ + kfree(td); +} + +/* + * Blk cgroup controller notification saying that blkio_group object is being + * delinked as associated cgroup object is going away. That also means that + * no new IO will come in this group. So get rid of this group as soon as + * any pending IO in the group is finished. + * + * This function is called under rcu_read_lock(). key is the rcu protected + * pointer. That means "key" is a valid throtl_data pointer as long as we are + * rcu read lock. + * + * "key" was fetched from blkio_group under blkio_cgroup->lock. That means + * it should not be NULL as even if queue was going away, cgroup deltion + * path got to it first. + */ +void throtl_unlink_blkio_group(void *key, struct blkio_group *blkg) +{ + unsigned long flags; + struct throtl_data *td = key; + + spin_lock_irqsave(td->queue->queue_lock, flags); + throtl_destroy_tg(td, tg_of_blkg(blkg)); + spin_unlock_irqrestore(td->queue->queue_lock, flags); +} + +static void throtl_update_blkio_group_read_bps (struct blkio_group *blkg, + u64 read_bps) +{ + tg_of_blkg(blkg)->bps[READ] = read_bps; +} + +static void throtl_update_blkio_group_write_bps (struct blkio_group *blkg, + u64 write_bps) +{ + tg_of_blkg(blkg)->bps[WRITE] = write_bps; +} + +void throtl_shutdown_timer_wq(struct request_queue *q) +{ + struct throtl_data *td = q->td; + + cancel_delayed_work_sync(&td->throtl_work); +} + +static struct blkio_policy_type blkio_policy_throtl = { + .ops = { + .blkio_unlink_group_fn = throtl_unlink_blkio_group, + .blkio_update_group_read_bps_fn = + throtl_update_blkio_group_read_bps, + .blkio_update_group_write_bps_fn = + throtl_update_blkio_group_write_bps, + }, +}; + +int blk_throtl_bio(struct request_queue *q, struct bio **biop) +{ + struct throtl_data *td = q->td; + struct throtl_grp *tg; + struct bio *bio = *biop; + bool rw = bio_data_dir(bio), update_disptime = true; + + if (bio->bi_rw & REQ_THROTTLED) { + bio->bi_rw &= ~REQ_THROTTLED; + return 0; + } + + spin_lock_irq(q->queue_lock); + tg = throtl_get_tg(td); + + if (tg->nr_queued[rw]) { + /* + * There is already another bio queued in same dir. No + * need to update dispatch time. + */ + update_disptime = false; + goto queue_bio; + } + + /* Bio is with-in rate limit of group */ + if (tg_may_dispatch(td, tg, bio, NULL)) { + throtl_charge_bio(tg, bio); + goto out; + } + +queue_bio: + throtl_log_tg(td, tg, "[%c] bio. disp=%u sz=%u bps=%llu" + " queued=%d/%d", rw == READ ? 'R' : 'W', + tg->bytes_disp[rw], bio->bi_size, tg->bps[rw], + tg->nr_queued[READ], tg->nr_queued[WRITE]); + + throtl_add_bio_tg(q->td, tg, bio); + *biop = NULL; + + if (update_disptime) { + tg_update_disptime(td, tg); + throtl_schedule_next_dispatch(td); + } + +out: + spin_unlock_irq(q->queue_lock); + return 0; +} + +int blk_throtl_init(struct request_queue *q) +{ + struct throtl_data *td; + struct throtl_grp *tg; + + td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node); + if (!td) + return -ENOMEM; + + INIT_HLIST_HEAD(&td->tg_list); + td->tg_service_tree = THROTL_RB_ROOT; + + /* Init root group */ + tg = &td->root_tg; + INIT_HLIST_NODE(&tg->tg_node); + RB_CLEAR_NODE(&tg->rb_node); + bio_list_init(&tg->bio_lists[0]); + bio_list_init(&tg->bio_lists[1]); + + /* Practically unlimited BW */ + tg->bps[0] = tg->bps[1] = -1; + atomic_set(&tg->ref, 1); + + INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work); + + rcu_read_lock(); + blkiocg_add_blkio_group(&blkio_root_cgroup, &tg->blkg, (void *)td, + 0, BLKIO_POLICY_THROTL); + rcu_read_unlock(); + + /* Attach throtl data to request queue */ + td->queue = q; + q->td = td; + return 0; +} + +void blk_throtl_exit(struct request_queue *q) +{ + struct throtl_data *td = q->td; + bool wait = false; + + BUG_ON(!td); + + throtl_shutdown_timer_wq(q); + + spin_lock_irq(q->queue_lock); + throtl_release_tgs(td); + blkiocg_del_blkio_group(&td->root_tg.blkg); + + /* If there are other groups */ + if (td->nr_undestroyed_grps >= 1) + wait = true; + + spin_unlock_irq(q->queue_lock); + + /* + * Wait for tg->blkg->key accessors to exit their grace periods. + * Do this wait only if there are other undestroyed groups out + * there (other than root group). This can happen if cgroup deletion + * path claimed the responsibility of cleaning up a group before + * queue cleanup code get to the group. + * + * Do not call synchronize_rcu() unconditionally as there are drivers + * which create/delete request queue hundreds of times during scan/boot + * and synchronize_rcu() can take significant time and slow down boot. + */ + if (wait) + synchronize_rcu(); + throtl_td_free(td); +} + +static int __init throtl_init(void) +{ + blkio_policy_register(&blkio_policy_throtl); + return 0; +} + +module_init(throtl_init); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index ca83a97c9715..10a0c291b55a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -130,6 +130,8 @@ enum rq_flag_bits { /* bio only flags */ __REQ_UNPLUG, /* unplug the immediately after submission */ __REQ_RAHEAD, /* read ahead, can fail anytime */ + __REQ_THROTTLED, /* This bio has already been subjected to + * throttling rules. Don't do it again. */ /* request only flags */ __REQ_SORTED, /* elevator knows about this request */ @@ -172,6 +174,7 @@ enum rq_flag_bits { #define REQ_UNPLUG (1 << __REQ_UNPLUG) #define REQ_RAHEAD (1 << __REQ_RAHEAD) +#define REQ_THROTTLED (1 << __REQ_THROTTLED) #define REQ_SORTED (1 << __REQ_SORTED) #define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 780824edac16..1341df5806df 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -371,6 +371,11 @@ struct request_queue #if defined(CONFIG_BLK_DEV_BSG) struct bsg_class_device bsg_dev; #endif + +#ifdef CONFIG_BLK_DEV_THROTTLING + /* Throttle data */ + struct throtl_data *td; +#endif }; #define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ @@ -1131,6 +1136,7 @@ static inline void put_dev_sector(Sector p) struct work_struct; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay); #ifdef CONFIG_BLK_CGROUP /* @@ -1174,6 +1180,24 @@ static inline uint64_t rq_io_start_time_ns(struct request *req) } #endif +#ifdef CONFIG_BLK_DEV_THROTTLING +extern int blk_throtl_init(struct request_queue *q); +extern void blk_throtl_exit(struct request_queue *q); +extern int blk_throtl_bio(struct request_queue *q, struct bio **bio); +extern void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay); +extern void throtl_shutdown_timer_wq(struct request_queue *q); +#else /* CONFIG_BLK_DEV_THROTTLING */ +static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio) +{ + return 0; +} + +static inline int blk_throtl_init(struct request_queue *q) { return 0; } +static inline int blk_throtl_exit(struct request_queue *q) { return 0; } +static inline void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) {} +static inline void throtl_shutdown_timer_wq(struct request_queue *q) {} +#endif /* CONFIG_BLK_DEV_THROTTLING */ + #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ diff --git a/init/Kconfig b/init/Kconfig index 2de5b1cbadd9..950ba26f7233 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -634,11 +634,14 @@ config BLK_CGROUP Currently, CFQ IO scheduler uses it to recognize task groups and control disk bandwidth allocation (proportional time slice allocation) - to such task groups. + to such task groups. It is also used by bio throttling logic in + block layer to implement upper limit in IO rates on a device. This option only enables generic Block IO controller infrastructure. - One needs to also enable actual IO controlling logic in CFQ for it - to take effect. (CONFIG_CFQ_GROUP_IOSCHED=y). + One needs to also enable actual IO controlling logic/policy. For + enabling proportional weight division of disk bandwidth in CFQ seti + CONFIG_CFQ_GROUP_IOSCHED=y and for enabling throttling policy set + CONFIG_BLK_THROTTLE=y. See Documentation/cgroups/blkio-controller.txt for more information. -- cgit v1.2.3 From dd3932eddf428571762596e17b65f5dc92ca361b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Sep 2010 20:51:46 +0200 Subject: block: remove BLKDEV_IFL_WAIT All the blkdev_issue_* helpers can only sanely be used for synchronous caller. To issue cache flushes or barriers asynchronously the caller needs to set up a bio by itself with a completion callback to move the asynchronous state machine ahead. So drop the BLKDEV_IFL_WAIT flag that is always specified when calling blkdev_issue_* and also remove the now unused flags argument to blkdev_issue_flush and blkdev_issue_zeroout. For blkdev_issue_discard we need to keep it for the secure discard flag, which gains a more descriptive name and loses the bitops vs flag confusion. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-flush.c | 25 +++++++++++-------------- block/blk-lib.c | 21 ++++++++------------- block/ioctl.c | 4 ++-- drivers/block/drbd/drbd_int.h | 3 +-- drivers/block/drbd/drbd_receiver.c | 2 +- fs/block_dev.c | 2 +- fs/btrfs/extent-tree.c | 3 +-- fs/ext3/fsync.c | 3 +-- fs/ext4/fsync.c | 5 ++--- fs/ext4/mballoc.c | 3 +-- fs/fat/fatent.c | 3 +-- fs/gfs2/rgrp.c | 5 ++--- fs/jbd2/checkpoint.c | 3 +-- fs/jbd2/commit.c | 6 ++---- fs/nilfs2/the_nilfs.c | 4 ++-- fs/reiserfs/file.c | 3 +-- fs/xfs/linux-2.6/xfs_super.c | 3 +-- include/linux/blkdev.h | 14 +++++--------- mm/swapfile.c | 6 +++--- 19 files changed, 47 insertions(+), 71 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-flush.c b/block/blk-flush.c index 62b7df9bca9d..54b123d6563e 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -205,7 +205,6 @@ static void bio_end_flush(struct bio *bio, int err) * @bdev: blockdev to issue flush for * @gfp_mask: memory allocation flags (for bio_alloc) * @error_sector: error sector - * @flags: BLKDEV_IFL_* flags to control behaviour * * Description: * Issue a flush for the block device in question. Caller can supply @@ -214,7 +213,7 @@ static void bio_end_flush(struct bio *bio, int err) * request was pushed in some internal queue for later handling. */ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, - sector_t *error_sector, unsigned long flags) + sector_t *error_sector) { DECLARE_COMPLETION_ONSTACK(wait); struct request_queue *q; @@ -240,21 +239,19 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, bio = bio_alloc(gfp_mask, 0); bio->bi_end_io = bio_end_flush; bio->bi_bdev = bdev; - if (test_bit(BLKDEV_WAIT, &flags)) - bio->bi_private = &wait; + bio->bi_private = &wait; bio_get(bio); submit_bio(WRITE_FLUSH, bio); - if (test_bit(BLKDEV_WAIT, &flags)) { - wait_for_completion(&wait); - /* - * The driver must store the error location in ->bi_sector, if - * it supports it. For non-stacked drivers, this should be - * copied from blk_rq_pos(rq). - */ - if (error_sector) - *error_sector = bio->bi_sector; - } + wait_for_completion(&wait); + + /* + * The driver must store the error location in ->bi_sector, if + * it supports it. For non-stacked drivers, this should be + * copied from blk_rq_pos(rq). + */ + if (error_sector) + *error_sector = bio->bi_sector; if (!bio_flagged(bio, BIO_UPTODATE)) ret = -EIO; diff --git a/block/blk-lib.c b/block/blk-lib.c index fe2e6ed0f510..1a320d2406b0 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -61,7 +61,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, max_discard_sectors &= ~(disc_sects - 1); } - if (flags & BLKDEV_IFL_SECURE) { + if (flags & BLKDEV_DISCARD_SECURE) { if (!blk_queue_secdiscard(q)) return -EOPNOTSUPP; type |= REQ_SECURE; @@ -77,8 +77,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio->bi_sector = sector; bio->bi_end_io = blkdev_discard_end_io; bio->bi_bdev = bdev; - if (flags & BLKDEV_IFL_WAIT) - bio->bi_private = &wait; + bio->bi_private = &wait; if (nr_sects > max_discard_sectors) { bio->bi_size = max_discard_sectors << 9; @@ -92,8 +91,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_get(bio); submit_bio(type, bio); - if (flags & BLKDEV_IFL_WAIT) - wait_for_completion(&wait); + wait_for_completion(&wait); if (bio_flagged(bio, BIO_EOPNOTSUPP)) ret = -EOPNOTSUPP; @@ -139,7 +137,6 @@ static void bio_batch_end_io(struct bio *bio, int err) * @sector: start sector * @nr_sects: number of sectors to write * @gfp_mask: memory allocation flags (for bio_alloc) - * @flags: BLKDEV_IFL_* flags to control behaviour * * Description: * Generate and issue number of bios with zerofiled pages. @@ -148,7 +145,7 @@ static void bio_batch_end_io(struct bio *bio, int err) */ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags) + sector_t nr_sects, gfp_t gfp_mask) { int ret; struct bio *bio; @@ -174,8 +171,7 @@ submit: bio->bi_sector = sector; bio->bi_bdev = bdev; bio->bi_end_io = bio_batch_end_io; - if (flags & BLKDEV_IFL_WAIT) - bio->bi_private = &bb; + bio->bi_private = &bb; while (nr_sects != 0) { sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects); @@ -193,10 +189,9 @@ submit: submit_bio(WRITE, bio); } - if (flags & BLKDEV_IFL_WAIT) - /* Wait for bios in-flight */ - while ( issued != atomic_read(&bb.done)) - wait_for_completion(&wait); + /* Wait for bios in-flight */ + while (issued != atomic_read(&bb.done)) + wait_for_completion(&wait); if (!test_bit(BIO_UPTODATE, &bb.flags)) /* One of bios in the batch was completed with error.*/ diff --git a/block/ioctl.c b/block/ioctl.c index d8052f0dabd3..cb2b9099862b 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -116,7 +116,7 @@ static int blkdev_reread_part(struct block_device *bdev) static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, uint64_t len, int secure) { - unsigned long flags = BLKDEV_IFL_WAIT; + unsigned long flags = 0; if (start & 511) return -EINVAL; @@ -128,7 +128,7 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start, if (start + len > (bdev->bd_inode->i_size >> 9)) return -EINVAL; if (secure) - flags |= BLKDEV_IFL_SECURE; + flags |= BLKDEV_DISCARD_SECURE; return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags); } diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 352441b0f92f..c2ef476f5711 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -2321,8 +2321,7 @@ static inline void drbd_md_flush(struct drbd_conf *mdev) if (test_bit(MD_NO_BARRIER, &mdev->flags)) return; - r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL); if (r) { set_bit(MD_NO_BARRIER, &mdev->flags); dev_err(DEV, "meta data flush failed with status %d, disabling md-flushes\n", r); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 081522d3c742..df15e7f0e7b7 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -975,7 +975,7 @@ static enum finish_epoch drbd_flush_after_epoch(struct drbd_conf *mdev, struct d if (mdev->write_ordering >= WO_bdev_flush && get_ldev(mdev)) { rv = blkdev_issue_flush(mdev->ldev->backing_bdev, GFP_KERNEL, - NULL, BLKDEV_IFL_WAIT); + NULL); if (rv) { dev_err(DEV, "local disk flush failed with status %d\n", rv); /* would rather check on EOPNOTSUPP, but that is not reliable. diff --git a/fs/block_dev.c b/fs/block_dev.c index 50e8c8582faa..b737451e2e9d 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -370,7 +370,7 @@ int blkdev_fsync(struct file *filp, int datasync) */ mutex_unlock(&bd_inode->i_mutex); - error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL, BLKDEV_IFL_WAIT); + error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL); if (error == -EOPNOTSUPP) error = 0; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 43dc9ea9aef6..0b81ecdb101c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1695,8 +1695,7 @@ 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_IFL_WAIT); + blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0); } static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c index d7e9f74dc3a6..09b13bb34c94 100644 --- a/fs/ext3/fsync.c +++ b/fs/ext3/fsync.c @@ -90,7 +90,6 @@ int ext3_sync_file(struct file *file, int datasync) * storage */ if (needs_barrier) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); return ret; } diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 592adf2e546e..3f3ff5ee8f9d 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -128,10 +128,9 @@ int ext4_sync_file(struct file *file, int datasync) (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, - NULL, BLKDEV_IFL_WAIT); + NULL); ret = jbd2_log_wait_commit(journal, commit_tid); } else if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); return ret; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a22bfef3da95..19aa0d44d822 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2566,8 +2566,7 @@ static inline void ext4_issue_discard(struct super_block *sb, discard_block = block + ext4_group_first_block_no(sb, block_group); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); - ret = sb_issue_discard(sb, discard_block, count, GFP_NOFS, - BLKDEV_IFL_WAIT); + ret = sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); if (ret == EOPNOTSUPP) { ext4_warning(sb, "discard not supported, disabling"); clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD); diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index f9a0b7ae8648..b47d2c9f4fa1 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -578,8 +578,7 @@ int fat_free_clusters(struct inode *inode, int cluster) sb_issue_discard(sb, fat_clus_to_blknr(sbi, first_cl), nr_clus * sbi->sec_per_clus, - GFP_NOFS, - BLKDEV_IFL_WAIT); + GFP_NOFS, 0); first_cl = cluster; } diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 379316472918..38b3ea1abacc 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -854,7 +854,7 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, if ((start + nr_sects) != blk) { rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, - BLKDEV_IFL_WAIT); + 0); if (rv) goto fail; nr_sects = 0; @@ -868,8 +868,7 @@ start_new_extent: } } if (nr_sects) { - rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, - BLKDEV_IFL_WAIT); + rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS, 0); if (rv) goto fail; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 5247e7ffdcb4..6571a056e55d 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -532,8 +532,7 @@ int jbd2_cleanup_journal_tail(journal_t *journal) */ if ((journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); if (!(journal->j_flags & JBD2_ABORT)) jbd2_journal_update_superblock(journal, 1); return 0; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index f204e27f44d1..cb43c605cfaa 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -684,8 +684,7 @@ start_journal_io: if (commit_transaction->t_flushed_data_blocks && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, @@ -810,8 +809,7 @@ wait_for_iobuf: if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) && journal->j_flags & JBD2_BARRIER) { - blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL); } if (err) diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 400b2caef4d8..d97310f07bef 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -774,7 +774,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, BLKDEV_IFL_WAIT); + GFP_NOFS, 0); if (ret < 0) return ret; nblocks = 0; @@ -784,7 +784,7 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, - GFP_NOFS, BLKDEV_IFL_WAIT); + GFP_NOFS, 0); return ret; } diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 6846371498b6..91f080cc76c8 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -152,8 +152,7 @@ static int reiserfs_sync_file(struct file *filp, int datasync) barrier_done = reiserfs_commit_for_inode(inode); reiserfs_write_unlock(inode->i_sb); if (barrier_done != 1 && reiserfs_barrier_flush(inode->i_sb)) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); if (barrier_done < 0) return barrier_done; return (err < 0) ? -EIO : 0; diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 15c35b62ff14..5fa7a30cc3f0 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -693,8 +693,7 @@ void xfs_blkdev_issue_flush( xfs_buftarg_t *buftarg) { - blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL, - BLKDEV_IFL_WAIT); + blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL); } STATIC void diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cfcb3a610605..accbd0e5c893 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -867,18 +867,14 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, return NULL; return bqt->tag_index[tag]; } -enum{ - BLKDEV_WAIT, /* wait for completion */ - BLKDEV_SECURE, /* secure discard */ -}; -#define BLKDEV_IFL_WAIT (1 << BLKDEV_WAIT) -#define BLKDEV_IFL_SECURE (1 << BLKDEV_SECURE) -extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *, - unsigned long); + +#define BLKDEV_DISCARD_SECURE 0x01 /* secure discard */ + +extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); + sector_t nr_sects, gfp_t gfp_mask); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 68cda164dff6..e132e1708acc 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -141,7 +141,7 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT); + nr_blocks, GFP_KERNEL, 0); if (err) return err; cond_resched(); @@ -152,7 +152,7 @@ static int discard_swap(struct swap_info_struct *si) nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, - nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT); + nr_blocks, GFP_KERNEL, 0); if (err) break; @@ -191,7 +191,7 @@ 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, BLKDEV_IFL_WAIT)) + nr_blocks, GFP_NOIO, 0)) break; } -- cgit v1.2.3 From 892b6f90db81cccb723d5d92f4fddc2d68b206e1 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 13 Oct 2010 21:18:03 +0200 Subject: block: Ensure physical block size is unsigned int Physical block size was declared unsigned int to accomodate the maximum size reported by READ CAPACITY(16). Make sure we use the right type in the related functions. Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Cc: stable@kernel.org Signed-off-by: Jens Axboe --- block/blk-settings.c | 2 +- include/linux/blkdev.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index a3600a7ab8bb..315b88c8cbbb 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -344,7 +344,7 @@ EXPORT_SYMBOL(blk_queue_logical_block_size); * hardware can operate on without reverting to read-modify-write * operations. */ -void blk_queue_physical_block_size(struct request_queue *q, unsigned short size) +void blk_queue_physical_block_size(struct request_queue *q, unsigned int size) { q->limits.physical_block_size = size; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1341df5806df..8f3dd981b973 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -860,7 +860,7 @@ extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); -extern void blk_queue_physical_block_size(struct request_queue *, unsigned short); +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); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); @@ -1013,7 +1013,7 @@ static inline unsigned int queue_physical_block_size(struct request_queue *q) return q->limits.physical_block_size; } -static inline int bdev_physical_block_size(struct block_device *bdev) +static inline unsigned int bdev_physical_block_size(struct block_device *bdev) { return queue_physical_block_size(bdev_get_queue(bdev)); } -- cgit v1.2.3 From 7681bfeeccff5efa9eb29bf09249a3c400b15327 Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Tue, 19 Oct 2010 09:05:00 +0200 Subject: block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. When reloading partition tables, quiesce IO to ensure that no request references to the partition struct exists. When it is safe to free the partition table, the IO for that device is restarted again. Signed-off-by: Yasuaki Ishimatsu Cc: stable@kernel.org Signed-off-by: Jens Axboe --- block/blk-core.c | 24 ++++++++++++++++-------- block/blk-merge.c | 2 +- block/blk.h | 4 ---- block/genhd.c | 14 ++++++++++++++ fs/partitions/check.c | 12 ++++++++++++ include/linux/blkdev.h | 1 + include/linux/elevator.h | 2 ++ include/linux/genhd.h | 1 + 8 files changed, 47 insertions(+), 13 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 797d5095eb83..ddc68332d655 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -64,13 +64,15 @@ static void drive_stat_acct(struct request *rq, int new_io) return; cpu = part_stat_lock(); - part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); - if (!new_io) + if (!new_io) { + part = rq->part; part_stat_inc(cpu, part, merges[rw]); - else { + } else { + part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); part_round_stats(cpu, part); part_inc_in_flight(part, rw); + rq->part = part; } part_stat_unlock(); @@ -128,6 +130,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq) rq->ref_count = 1; rq->start_time = jiffies; set_start_time_ns(rq); + rq->part = NULL; } EXPORT_SYMBOL(blk_rq_init); @@ -804,11 +807,16 @@ static struct request *get_request(struct request_queue *q, int rw_flags, rl->starved[is_sync] = 0; priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags); - if (priv) + if (priv) { rl->elvpriv++; - if (blk_queue_io_stat(q)) - rw_flags |= REQ_IO_STAT; + /* + * Don't do stats for non-priv requests + */ + if (blk_queue_io_stat(q)) + rw_flags |= REQ_IO_STAT; + } + spin_unlock_irq(q->queue_lock); rq = blk_alloc_request(q, rw_flags, priv, gfp_mask); @@ -1777,7 +1785,7 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes) int cpu; cpu = part_stat_lock(); - part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); + part = req->part; part_stat_add(cpu, part, sectors[rw], bytes >> 9); part_stat_unlock(); } @@ -1797,7 +1805,7 @@ static void blk_account_io_done(struct request *req) int cpu; cpu = part_stat_lock(); - part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); + part = req->part; part_stat_inc(cpu, part, ios[rw]); part_stat_add(cpu, part, ticks[rw], duration); diff --git a/block/blk-merge.c b/block/blk-merge.c index 6a725461654d..38ff234012a4 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req) int cpu; cpu = part_stat_lock(); - part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); + part = req->part; part_round_stats(cpu, part); part_dec_in_flight(part, rq_data_dir(req)); diff --git a/block/blk.h b/block/blk.h index 6738831ba447..1340cce5721a 100644 --- a/block/blk.h +++ b/block/blk.h @@ -110,10 +110,6 @@ void blk_queue_congestion_threshold(struct request_queue *q); int blk_dev_init(void); -void elv_quiesce_start(struct request_queue *q); -void elv_quiesce_end(struct request_queue *q); - - /* * Return the threshold (number of used requests) at which the queue is * considered to be congested. It include a little hysteresis to keep the diff --git a/block/genhd.c b/block/genhd.c index 7923e720ddf5..8313834596db 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -932,8 +932,15 @@ static void disk_free_ptbl_rcu_cb(struct rcu_head *head) { struct disk_part_tbl *ptbl = container_of(head, struct disk_part_tbl, rcu_head); + struct gendisk *disk = ptbl->disk; + struct request_queue *q = disk->queue; + unsigned long flags; kfree(ptbl); + + spin_lock_irqsave(q->queue_lock, flags); + elv_quiesce_end(q); + spin_unlock_irqrestore(q->queue_lock, flags); } /** @@ -951,11 +958,17 @@ static void disk_replace_part_tbl(struct gendisk *disk, struct disk_part_tbl *new_ptbl) { struct disk_part_tbl *old_ptbl = disk->part_tbl; + struct request_queue *q = disk->queue; rcu_assign_pointer(disk->part_tbl, new_ptbl); if (old_ptbl) { rcu_assign_pointer(old_ptbl->last_lookup, NULL); + + spin_lock_irq(q->queue_lock); + elv_quiesce_start(q); + spin_unlock_irq(q->queue_lock); + call_rcu(&old_ptbl->rcu_head, disk_free_ptbl_rcu_cb); } } @@ -996,6 +1009,7 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno) return -ENOMEM; new_ptbl->len = target; + new_ptbl->disk = disk; for (i = 0; i < len; i++) rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]); diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 6dfbee03ccc6..30f46c2cb9d5 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -365,17 +365,25 @@ struct device_type part_type = { static void delete_partition_rcu_cb(struct rcu_head *head) { struct hd_struct *part = container_of(head, struct hd_struct, rcu_head); + struct gendisk *disk = part_to_disk(part); + struct request_queue *q = disk->queue; + unsigned long flags; part->start_sect = 0; part->nr_sects = 0; part_stat_set_all(part, 0); put_device(part_to_dev(part)); + + spin_lock_irqsave(q->queue_lock, flags); + elv_quiesce_end(q); + spin_unlock_irqrestore(q->queue_lock, flags); } void delete_partition(struct gendisk *disk, int partno) { struct disk_part_tbl *ptbl = disk->part_tbl; struct hd_struct *part; + struct request_queue *q = disk->queue; if (partno >= ptbl->len) return; @@ -390,6 +398,10 @@ void delete_partition(struct gendisk *disk, int partno) kobject_put(part->holder_dir); device_del(part_to_dev(part)); + spin_lock_irq(q->queue_lock); + elv_quiesce_start(q); + spin_unlock_irq(q->queue_lock); + call_rcu(&part->rcu_head, delete_partition_rcu_cb); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8f3dd981b973..16f7f1be1acf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -115,6 +115,7 @@ struct request { void *elevator_private3; struct gendisk *rq_disk; + struct hd_struct *part; unsigned long start_time; #ifdef CONFIG_BLK_CGROUP unsigned long long start_time_ns; diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2c958f4fce1e..df1ee866d715 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -121,6 +121,8 @@ extern void elv_completed_request(struct request_queue *, struct request *); extern int elv_set_request(struct request_queue *, struct request *, gfp_t); extern void elv_put_request(struct request_queue *, struct request *); extern void elv_drain_elevator(struct request_queue *); +extern void elv_quiesce_start(struct request_queue *); +extern void elv_quiesce_end(struct request_queue *); /* * io scheduler registration diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 66e26b5a1537..57647ecfc1bd 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -140,6 +140,7 @@ struct disk_part_tbl { struct rcu_head rcu_head; int len; struct hd_struct *last_lookup; + struct gendisk *disk; struct hd_struct *part[]; }; -- cgit v1.2.3 From f253b86b4ad1b3220544e75880510fd455ebd23f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 24 Oct 2010 22:06:02 +0200 Subject: Revert "block: fix accounting bug on cross partition merges" This reverts commit 7681bfeeccff5efa9eb29bf09249a3c400b15327. Conflicts: include/linux/genhd.h It has numerous issues with the cleanup path and non-elevator devices. Revert it for now so we can come up with a clean version without rushing things. Signed-off-by: Jens Axboe --- block/blk-core.c | 24 ++++++++---------------- block/blk-merge.c | 2 +- block/blk.h | 4 ++++ block/genhd.c | 14 -------------- fs/partitions/check.c | 12 ------------ include/linux/blkdev.h | 1 - include/linux/elevator.h | 2 -- include/linux/genhd.h | 1 - 8 files changed, 13 insertions(+), 47 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 51efd835d4cf..f8548876d7ea 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -64,15 +64,13 @@ static void drive_stat_acct(struct request *rq, int new_io) return; cpu = part_stat_lock(); + part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); - if (!new_io) { - part = rq->part; + if (!new_io) part_stat_inc(cpu, part, merges[rw]); - } else { - part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); + else { part_round_stats(cpu, part); part_inc_in_flight(part, rw); - rq->part = part; } part_stat_unlock(); @@ -130,7 +128,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq) rq->ref_count = 1; rq->start_time = jiffies; set_start_time_ns(rq); - rq->part = NULL; } EXPORT_SYMBOL(blk_rq_init); @@ -805,16 +802,11 @@ static struct request *get_request(struct request_queue *q, int rw_flags, rl->starved[is_sync] = 0; priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags); - if (priv) { + if (priv) rl->elvpriv++; - /* - * Don't do stats for non-priv requests - */ - if (blk_queue_io_stat(q)) - rw_flags |= REQ_IO_STAT; - } - + if (blk_queue_io_stat(q)) + rw_flags |= REQ_IO_STAT; spin_unlock_irq(q->queue_lock); rq = blk_alloc_request(q, rw_flags, priv, gfp_mask); @@ -1791,7 +1783,7 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes) int cpu; cpu = part_stat_lock(); - part = req->part; + part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_stat_add(cpu, part, sectors[rw], bytes >> 9); part_stat_unlock(); } @@ -1811,7 +1803,7 @@ static void blk_account_io_done(struct request *req) int cpu; cpu = part_stat_lock(); - part = req->part; + part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_stat_inc(cpu, part, ios[rw]); part_stat_add(cpu, part, ticks[rw], duration); diff --git a/block/blk-merge.c b/block/blk-merge.c index 0a2fd8a48a38..77b7c26df6b5 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req) int cpu; cpu = part_stat_lock(); - part = req->part; + part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_round_stats(cpu, part); part_dec_in_flight(part, rq_data_dir(req)); diff --git a/block/blk.h b/block/blk.h index 1e675e5ade02..2db8f32838e7 100644 --- a/block/blk.h +++ b/block/blk.h @@ -116,6 +116,10 @@ void blk_queue_congestion_threshold(struct request_queue *q); int blk_dev_init(void); +void elv_quiesce_start(struct request_queue *q); +void elv_quiesce_end(struct request_queue *q); + + /* * Return the threshold (number of used requests) at which the queue is * considered to be congested. It include a little hysteresis to keep the diff --git a/block/genhd.c b/block/genhd.c index a8adf96a4b41..5fa2b44a72ff 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -929,15 +929,8 @@ static void disk_free_ptbl_rcu_cb(struct rcu_head *head) { struct disk_part_tbl *ptbl = container_of(head, struct disk_part_tbl, rcu_head); - struct gendisk *disk = ptbl->disk; - struct request_queue *q = disk->queue; - unsigned long flags; kfree(ptbl); - - spin_lock_irqsave(q->queue_lock, flags); - elv_quiesce_end(q); - spin_unlock_irqrestore(q->queue_lock, flags); } /** @@ -955,17 +948,11 @@ static void disk_replace_part_tbl(struct gendisk *disk, struct disk_part_tbl *new_ptbl) { struct disk_part_tbl *old_ptbl = disk->part_tbl; - struct request_queue *q = disk->queue; rcu_assign_pointer(disk->part_tbl, new_ptbl); if (old_ptbl) { rcu_assign_pointer(old_ptbl->last_lookup, NULL); - - spin_lock_irq(q->queue_lock); - elv_quiesce_start(q); - spin_unlock_irq(q->queue_lock); - call_rcu(&old_ptbl->rcu_head, disk_free_ptbl_rcu_cb); } } @@ -1006,7 +993,6 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno) return -ENOMEM; new_ptbl->len = target; - new_ptbl->disk = disk; for (i = 0; i < len; i++) rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]); diff --git a/fs/partitions/check.c b/fs/partitions/check.c index b81bfc016a05..0a8b0ad0c7e2 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -365,25 +365,17 @@ struct device_type part_type = { static void delete_partition_rcu_cb(struct rcu_head *head) { struct hd_struct *part = container_of(head, struct hd_struct, rcu_head); - struct gendisk *disk = part_to_disk(part); - struct request_queue *q = disk->queue; - unsigned long flags; part->start_sect = 0; part->nr_sects = 0; part_stat_set_all(part, 0); put_device(part_to_dev(part)); - - spin_lock_irqsave(q->queue_lock, flags); - elv_quiesce_end(q); - spin_unlock_irqrestore(q->queue_lock, flags); } void delete_partition(struct gendisk *disk, int partno) { struct disk_part_tbl *ptbl = disk->part_tbl; struct hd_struct *part; - struct request_queue *q = disk->queue; if (partno >= ptbl->len) return; @@ -398,10 +390,6 @@ void delete_partition(struct gendisk *disk, int partno) kobject_put(part->holder_dir); device_del(part_to_dev(part)); - spin_lock_irq(q->queue_lock); - elv_quiesce_start(q); - spin_unlock_irq(q->queue_lock); - call_rcu(&part->rcu_head, delete_partition_rcu_cb); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 009b80e49f53..646b462d04df 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -115,7 +115,6 @@ struct request { void *elevator_private3; struct gendisk *rq_disk; - struct hd_struct *part; unsigned long start_time; #ifdef CONFIG_BLK_CGROUP unsigned long long start_time_ns; diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 80a0ece8f7e4..4fd978e7eb83 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -122,8 +122,6 @@ extern void elv_completed_request(struct request_queue *, struct request *); extern int elv_set_request(struct request_queue *, struct request *, gfp_t); extern void elv_put_request(struct request_queue *, struct request *); extern void elv_drain_elevator(struct request_queue *); -extern void elv_quiesce_start(struct request_queue *); -extern void elv_quiesce_end(struct request_queue *); /* * io scheduler registration diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 557c3927e70f..7a7b9c1644e4 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -140,7 +140,6 @@ struct disk_part_tbl { struct rcu_head rcu_head; int len; struct hd_struct __rcu *last_lookup; - struct gendisk *disk; struct hd_struct __rcu *part[]; }; -- cgit v1.2.3 From e6fa0be699449d28a20e815bfe9ce26725ec4962 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Wed, 27 Oct 2010 21:30:04 -0400 Subject: Add helper function for blkdev_issue_zeroout (sb_issue_discard) This is done the same way as helper sb_issue_discard for blkdev_issue_discard. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- include/linux/blkdev.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c54906f678f..e5cb4d029689 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -941,6 +941,14 @@ static inline int sb_issue_discard(struct super_block *sb, return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_NOFS, BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER); } +static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, + sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) +{ + return blkdev_issue_zeroout(sb->s_bdev, + block << (sb->s_blocksize_bits - 9), + nr_blocks << (sb->s_blocksize_bits - 9), + gfp_mask, flags); +} extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); -- cgit v1.2.3 From 02e031cbc843b010e72fcc05c76113c688b2860f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Nov 2010 14:54:09 +0100 Subject: block: remove REQ_HARDBARRIER REQ_HARDBARRIER is dead now, so remove the leftovers. What's left at this point is: - various checks inside the block layer. - sanity checks in bio based drivers. - now unused bio_empty_barrier helper. - Xen blockfront use of BLKIF_OP_WRITE_BARRIER - it's dead for a while, but Xen really needs to sort out it's barrier situaton. - setting of ordered tags in uas - dead code copied from old scsi drivers. - scsi different retry for barriers - it's dead and should have been removed when flushes were converted to FS requests. - blktrace handling of barriers - removed. Someone who knows blktrace better should add support for REQ_FLUSH and REQ_FUA, though. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 7 ------- block/elevator.c | 4 ++-- drivers/block/aoe/aoeblk.c | 3 --- drivers/block/loop.c | 6 ------ drivers/block/xen-blkfront.c | 2 -- drivers/scsi/scsi_error.c | 18 +++++------------- drivers/usb/storage/uas.c | 5 +---- include/linux/bio.h | 4 ---- include/linux/blk_types.h | 6 ++---- include/linux/blkdev.h | 3 +-- kernel/trace/blktrace.c | 4 ---- 11 files changed, 11 insertions(+), 51 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 17fcb83670c0..4ce953f1b390 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1194,13 +1194,6 @@ static int __make_request(struct request_queue *q, struct bio *bio) int where = ELEVATOR_INSERT_SORT; int rw_flags; - /* REQ_HARDBARRIER is no more */ - if (WARN_ONCE(bio->bi_rw & REQ_HARDBARRIER, - "block: HARDBARRIER is deprecated, use FLUSH/FUA instead\n")) { - bio_endio(bio, -EOPNOTSUPP); - return 0; - } - /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even diff --git a/block/elevator.c b/block/elevator.c index 282e8308f7e2..2569512830d3 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -429,7 +429,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) q->nr_sorted--; boundary = q->end_sector; - stop_flags = REQ_SOFTBARRIER | REQ_HARDBARRIER | REQ_STARTED; + stop_flags = REQ_SOFTBARRIER | REQ_STARTED; list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); @@ -691,7 +691,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where) void __elv_add_request(struct request_queue *q, struct request *rq, int where, int plug) { - if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) { + if (rq->cmd_flags & REQ_SOFTBARRIER) { /* barriers are scheduling boundary, update end_sector */ if (rq->cmd_type == REQ_TYPE_FS || (rq->cmd_flags & REQ_DISCARD)) { diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 541e18879965..528f6318ded1 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -180,9 +180,6 @@ aoeblk_make_request(struct request_queue *q, struct bio *bio) BUG(); bio_endio(bio, -ENXIO); return 0; - } else if (bio->bi_rw & REQ_HARDBARRIER) { - bio_endio(bio, -EOPNOTSUPP); - return 0; } else if (bio->bi_io_vec == NULL) { printk(KERN_ERR "aoe: bi_io_vec is NULL\n"); BUG(); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 1e5284ef65fa..7ea0bea2f7e3 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -481,12 +481,6 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio) if (bio_rw(bio) == WRITE) { struct file *file = lo->lo_backing_file; - /* REQ_HARDBARRIER is deprecated */ - if (bio->bi_rw & REQ_HARDBARRIER) { - ret = -EOPNOTSUPP; - goto out; - } - if (bio->bi_rw & REQ_FLUSH) { ret = vfs_fsync(file, 0); if (unlikely(ret && ret != -EINVAL)) { diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 06e2812ba124..255035cfc88a 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -289,8 +289,6 @@ static int blkif_queue_request(struct request *req) ring_req->operation = rq_data_dir(req) ? BLKIF_OP_WRITE : BLKIF_OP_READ; - if (req->cmd_flags & REQ_HARDBARRIER) - ring_req->operation = BLKIF_OP_WRITE_BARRIER; ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg); BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 1de30eb83bb0..f3cf924a2cd9 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -320,19 +320,11 @@ static int scsi_check_sense(struct scsi_cmnd *scmd) "changed. The Linux SCSI layer does not " "automatically adjust these parameters.\n"); - if (scmd->request->cmd_flags & REQ_HARDBARRIER) - /* - * barrier requests should always retry on UA - * otherwise block will get a spurious error - */ - return NEEDS_RETRY; - else - /* - * for normal (non barrier) commands, pass the - * UA upwards for a determination in the - * completion functions - */ - return SUCCESS; + /* + * Pass the UA upwards for a determination in the completion + * functions. + */ + return SUCCESS; /* these three are not supported */ case COPY_ABORTED: diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 2054b1e25a65..d1268191acbd 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -331,10 +331,7 @@ static struct urb *uas_alloc_cmd_urb(struct uas_dev_info *devinfo, gfp_t gfp, iu->iu_id = IU_ID_COMMAND; iu->tag = cpu_to_be16(stream_id); - if (sdev->ordered_tags && (cmnd->request->cmd_flags & REQ_HARDBARRIER)) - iu->prio_attr = UAS_ORDERED_TAG; - else - iu->prio_attr = UAS_SIMPLE_TAG; + iu->prio_attr = UAS_SIMPLE_TAG; iu->len = len; int_to_scsilun(sdev->lun, &iu->lun); memcpy(iu->cdb, cmnd->cmnd, cmnd->cmd_len); diff --git a/include/linux/bio.h b/include/linux/bio.h index ba679992d39b..35dcdb3589bc 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -66,10 +66,6 @@ #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) -#define bio_empty_barrier(bio) \ - ((bio->bi_rw & REQ_HARDBARRIER) && \ - !bio_has_data(bio) && \ - !(bio->bi_rw & REQ_DISCARD)) static inline unsigned int bio_cur_bytes(struct bio *bio) { diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 0437ab6bb54c..46ad5197537a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -122,7 +122,6 @@ enum rq_flag_bits { __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ - __REQ_HARDBARRIER, /* may not be passed by drive either */ __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_DISCARD, /* request to discard sectors */ @@ -159,7 +158,6 @@ enum rq_flag_bits { #define REQ_FAILFAST_DEV (1 << __REQ_FAILFAST_DEV) #define REQ_FAILFAST_TRANSPORT (1 << __REQ_FAILFAST_TRANSPORT) #define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) -#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) #define REQ_SYNC (1 << __REQ_SYNC) #define REQ_META (1 << __REQ_META) #define REQ_DISCARD (1 << __REQ_DISCARD) @@ -168,8 +166,8 @@ enum rq_flag_bits { #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ - (REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \ - REQ_META | REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \ + REQ_NOIDLE | REQ_FLUSH | REQ_FUA) #define REQ_CLONE_MASK REQ_COMMON_MASK #define REQ_UNPLUG (1 << __REQ_UNPLUG) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5027a599077d..aae86fd10c4f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -552,8 +552,7 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync) * it already be started by driver. */ #define RQ_NOMERGE_FLAGS \ - (REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER | \ - REQ_FLUSH | REQ_FUA) + (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \ (((rq)->cmd_flags & REQ_DISCARD) || \ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index bc251ed66724..7b8ec0281548 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -168,7 +168,6 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector, static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) }; -#define BLK_TC_HARDBARRIER BLK_TC_BARRIER #define BLK_TC_RAHEAD BLK_TC_AHEAD /* The ilog2() calls fall out because they're constant */ @@ -196,7 +195,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, return; what |= ddir_act[rw & WRITE]; - what |= MASK_TC_BIT(rw, HARDBARRIER); what |= MASK_TC_BIT(rw, SYNC); what |= MASK_TC_BIT(rw, RAHEAD); what |= MASK_TC_BIT(rw, META); @@ -1807,8 +1805,6 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) if (rw & REQ_RAHEAD) rwbs[i++] = 'A'; - if (rw & REQ_HARDBARRIER) - rwbs[i++] = 'B'; if (rw & REQ_SYNC) rwbs[i++] = 'S'; if (rw & REQ_META) -- cgit v1.2.3 From e692cb668fdd5a712c6ed2a2d6f2a36ee83997b4 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 1 Dec 2010 19:41:49 +0100 Subject: block: Deprecate QUEUE_FLAG_CLUSTER and use queue_limits instead When stacking devices, a request_queue is not always available. This forced us to have a no_cluster flag in the queue_limits that could be used as a carrier until the request_queue had been set up for a metadevice. There were several problems with that approach. First of all it was up to the stacking device to remember to set queue flag after stacking had completed. Also, the queue flag and the queue limits had to be kept in sync at all times. We got that wrong, which could lead to us issuing commands that went beyond the max scatterlist limit set by the driver. The proper fix is to avoid having two flags for tracking the same thing. We deprecate QUEUE_FLAG_CLUSTER and use the queue limit directly in the block layer merging functions. The queue_limit 'no_cluster' is turned into 'cluster' to avoid double negatives and to ease stacking. Clustering defaults to being enabled as before. The queue flag logic is removed from the stacking function, and explicitly setting the cluster flag is no longer necessary in DM and MD. Reported-by: Ed Lin Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Cc: stable@kernel.org Signed-off-by: Jens Axboe --- block/blk-merge.c | 6 +++--- block/blk-settings.c | 25 ++----------------------- block/blk-sysfs.c | 2 +- drivers/md/dm-table.c | 5 ----- drivers/md/md.c | 3 --- drivers/scsi/scsi_lib.c | 3 +-- include/linux/blkdev.h | 9 ++++++--- 7 files changed, 13 insertions(+), 40 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-merge.c b/block/blk-merge.c index 77b7c26df6b5..74bc4a768f32 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -21,7 +21,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, return 0; fbio = bio; - cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags); + cluster = blk_queue_cluster(q); seg_size = 0; nr_phys_segs = 0; for_each_bio(bio) { @@ -87,7 +87,7 @@ EXPORT_SYMBOL(blk_recount_segments); static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, struct bio *nxt) { - if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags)) + if (!blk_queue_cluster(q)) return 0; if (bio->bi_seg_back_size + nxt->bi_seg_front_size > @@ -123,7 +123,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, int nsegs, cluster; nsegs = 0; - cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags); + cluster = blk_queue_cluster(q); /* * for each bio in rq diff --git a/block/blk-settings.c b/block/blk-settings.c index 701859fb9647..e55f5fc4ca22 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -126,7 +126,7 @@ void blk_set_default_limits(struct queue_limits *lim) lim->alignment_offset = 0; lim->io_opt = 0; lim->misaligned = 0; - lim->no_cluster = 0; + lim->cluster = 1; } EXPORT_SYMBOL(blk_set_default_limits); @@ -464,15 +464,6 @@ EXPORT_SYMBOL(blk_queue_io_opt); void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) { blk_stack_limits(&t->limits, &b->limits, 0); - - if (!t->queue_lock) - WARN_ON_ONCE(1); - else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) { - unsigned long flags; - spin_lock_irqsave(t->queue_lock, flags); - queue_flag_clear(QUEUE_FLAG_CLUSTER, t); - spin_unlock_irqrestore(t->queue_lock, flags); - } } EXPORT_SYMBOL(blk_queue_stack_limits); @@ -545,7 +536,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->io_min = max(t->io_min, b->io_min); t->io_opt = lcm(t->io_opt, b->io_opt); - t->no_cluster |= b->no_cluster; + t->cluster &= b->cluster; t->discard_zeroes_data &= b->discard_zeroes_data; /* Physical block size a multiple of the logical block size? */ @@ -641,7 +632,6 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset) { struct request_queue *t = disk->queue; - struct request_queue *b = bdev_get_queue(bdev); if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) { char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE]; @@ -652,17 +642,6 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n", top, bottom); } - - if (!t->queue_lock) - WARN_ON_ONCE(1); - else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) { - unsigned long flags; - - spin_lock_irqsave(t->queue_lock, flags); - if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) - queue_flag_clear(QUEUE_FLAG_CLUSTER, t); - spin_unlock_irqrestore(t->queue_lock, flags); - } } EXPORT_SYMBOL(disk_stack_limits); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 013457f47fdc..41fb69150b4d 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -119,7 +119,7 @@ static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char * static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) { - if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags)) + if (blk_queue_cluster(q)) return queue_var_show(queue_max_segment_size(q), (page)); return queue_var_show(PAGE_CACHE_SIZE, (page)); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 90267f8d64ee..e2da1912a2cb 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1131,11 +1131,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, */ q->limits = *limits; - if (limits->no_cluster) - queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q); - else - queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, q); - if (!dm_table_supports_discards(t)) queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); else diff --git a/drivers/md/md.c b/drivers/md/md.c index 84c46a161927..52694d29663d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4296,9 +4296,6 @@ static int md_alloc(dev_t dev, char *name) goto abort; mddev->queue->queuedata = mddev; - /* Can be unlocked because the queue is new: no concurrency */ - queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, mddev->queue); - blk_queue_make_request(mddev->queue, md_make_request); disk = alloc_disk(1 << shift); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index eafeeda6e194..9d7ba07dc5ef 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1642,9 +1642,8 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, blk_queue_max_segment_size(q, dma_get_max_seg_size(dev)); - /* New queue, no concurrency on queue_flags */ if (!shost->use_clustering) - queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q); + q->limits.cluster = 0; /* * set a reasonable default alignment on word boundaries: the diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aae86fd10c4f..95aeeeb49e8b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -250,7 +250,7 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; - unsigned char no_cluster; + unsigned char cluster; signed char discard_zeroes_data; }; @@ -380,7 +380,6 @@ struct request_queue #endif }; -#define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ #define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ #define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ @@ -403,7 +402,6 @@ struct request_queue #define QUEUE_FLAG_SECDISCARD 19 /* supports SECDISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_CLUSTER) | \ (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_ADD_RANDOM)) @@ -510,6 +508,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define rq_data_dir(rq) ((rq)->cmd_flags & 1) +static inline unsigned int blk_queue_cluster(struct request_queue *q) +{ + return q->limits.cluster; +} + /* * We regard a request as sync, if either a read or a sync write */ -- cgit v1.2.3 From 72d4cd9f38b5ed96b75df4c622be25e1c2648dd3 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 17 Dec 2010 08:34:20 +0100 Subject: block: max hardware sectors limit wrapper Implement blk_limits_max_hw_sectors() and make blk_queue_max_hw_sectors() a wrapper around it. DM needs this to avoid setting queue_limits' max_hw_sectors and max_sectors directly. dm_set_device_limits() now leverages blk_limits_max_hw_sectors() logic to establish the appropriate max_hw_sectors minimum (PAGE_SIZE). Fixes issue where DM was incorrectly setting max_sectors rather than max_hw_sectors (which caused dm_merge_bvec()'s max_hw_sectors check to be ineffective). Signed-off-by: Mike Snitzer Cc: stable@kernel.org Acked-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 26 ++++++++++++++++++++------ drivers/md/dm-table.c | 5 ++--- include/linux/blkdev.h | 1 + 3 files changed, 23 insertions(+), 9 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-settings.c b/block/blk-settings.c index e55f5fc4ca22..36c8c1f2af18 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -229,8 +229,8 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask) EXPORT_SYMBOL(blk_queue_bounce_limit); /** - * blk_queue_max_hw_sectors - set max sectors for a request for this queue - * @q: the request queue for the device + * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request + * @limits: the queue limits * @max_hw_sectors: max hardware sectors in the usual 512b unit * * Description: @@ -244,7 +244,7 @@ EXPORT_SYMBOL(blk_queue_bounce_limit); * per-device basis in /sys/block//queue/max_sectors_kb. * The soft limit can not exceed max_hw_sectors. **/ -void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors) +void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors) { if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) { max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9); @@ -252,9 +252,23 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto __func__, max_hw_sectors); } - q->limits.max_hw_sectors = max_hw_sectors; - q->limits.max_sectors = min_t(unsigned int, max_hw_sectors, - BLK_DEF_MAX_SECTORS); + limits->max_hw_sectors = max_hw_sectors; + limits->max_sectors = min_t(unsigned int, max_hw_sectors, + BLK_DEF_MAX_SECTORS); +} +EXPORT_SYMBOL(blk_limits_max_hw_sectors); + +/** + * blk_queue_max_hw_sectors - set max sectors for a request for this queue + * @q: the request queue for the device + * @max_hw_sectors: max hardware sectors in the usual 512b unit + * + * Description: + * See description for blk_limits_max_hw_sectors(). + **/ +void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors) +{ + blk_limits_max_hw_sectors(&q->limits, max_hw_sectors); } EXPORT_SYMBOL(blk_queue_max_hw_sectors); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index e2da1912a2cb..4d705cea0f8c 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -517,9 +517,8 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, */ if (q->merge_bvec_fn && !ti->type->merge) - limits->max_sectors = - min_not_zero(limits->max_sectors, - (unsigned int) (PAGE_SIZE >> 9)); + blk_limits_max_hw_sectors(limits, + (unsigned int) (PAGE_SIZE >> 9)); return 0; } EXPORT_SYMBOL_GPL(dm_set_device_limits); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 95aeeeb49e8b..36ab42c9bb99 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -808,6 +808,7 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *, extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); +extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); -- cgit v1.2.3