From 7bcd79ac50d9d83350a835bdb91c04ac9e098412 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 26 Feb 2016 23:40:50 +0800 Subject: block: bio: introduce helpers to get the 1st and last bvec The bio passed to bio_will_gap() may be fast cloned from upper layer(dm, md, bcache, fs, ...), or from bio splitting in block core. Unfortunately bio_will_gap() just figures out the last bvec via 'bi_io_vec[prev->bi_vcnt - 1]' directly, and this way is obviously wrong. This patch introduces two helpers for getting the first and last bvec of one bio for fixing the issue. Cc: stable@vger.kernel.org Reported-by: Sagi Grimberg Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 5349e6816cbb..cb6888824108 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -310,6 +310,43 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) bio->bi_flags &= ~(1U << bit); } +static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) +{ + *bv = bio_iovec(bio); +} + +static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) +{ + struct bvec_iter iter = bio->bi_iter; + int idx; + + if (!bio_flagged(bio, BIO_CLONED)) { + *bv = bio->bi_io_vec[bio->bi_vcnt - 1]; + return; + } + + if (unlikely(!bio_multiple_segments(bio))) { + *bv = bio_iovec(bio); + return; + } + + bio_advance_iter(bio, &iter, iter.bi_size); + + if (!iter.bi_bvec_done) + idx = iter.bi_idx - 1; + else /* in the middle of bvec */ + idx = iter.bi_idx; + + *bv = bio->bi_io_vec[idx]; + + /* + * iter.bi_bvec_done records actual length of the last bvec + * if this bio ends in the middle of one io vector + */ + if (iter.bi_bvec_done) + bv->bv_len = iter.bi_bvec_done; +} + enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ -- cgit v1.2.3 From e0af29171aa8912e1ca95023b75ef336cd70d661 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 26 Feb 2016 23:40:51 +0800 Subject: block: check virt boundary in bio_will_gap() In the following patch, the way for figuring out the last bvec will be changed with a bit cost introduced, so return immediately if the queue doesn't have virt boundary limit. Actually most of devices have not this limit. Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4571ef1a12a9..cd06a41581b3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1372,6 +1372,13 @@ static inline void put_dev_sector(Sector p) page_cache_release(p.v); } +static inline bool __bvec_gap_to_prev(struct request_queue *q, + struct bio_vec *bprv, unsigned int offset) +{ + return offset || + ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); +} + /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. @@ -1381,18 +1388,17 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, { if (!queue_virt_boundary(q)) return false; - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); + return __bvec_gap_to_prev(q, bprv, offset); } static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, struct bio *next) { - if (!bio_has_data(prev)) + if (!bio_has_data(prev) || !queue_virt_boundary(q)) return false; - return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], - next->bi_io_vec[0].bv_offset); + return __bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], + next->bi_io_vec[0].bv_offset); } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) -- cgit v1.2.3 From 25e71a99f10e444cd00bb2ebccb11e1c9fb672b1 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 26 Feb 2016 23:40:52 +0800 Subject: block: get the 1st and last bvec via helpers This patch applies the two introduced helpers to figure out the 1st and last bvec, and fixes the original way after bio splitting. Cc: stable@vger.kernel.org Reported-by: Sagi Grimberg Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cd06a41581b3..d7f6bca707ef 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1394,11 +1394,16 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, struct bio *next) { - if (!bio_has_data(prev) || !queue_virt_boundary(q)) - return false; + if (bio_has_data(prev) && queue_virt_boundary(q)) { + struct bio_vec pb, nb; + + bio_get_last_bvec(prev, &pb); + bio_get_first_bvec(next, &nb); - return __bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], - next->bi_io_vec[0].bv_offset); + return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + } + + return false; } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) -- cgit v1.2.3 From a1a0e23e49037c23ea84bc8cc146a03584d13577 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 29 Feb 2016 18:28:53 -0500 Subject: writeback: flush inode cgroup wb switches instead of pinning super_block If cgroup writeback is in use, inodes can be scheduled for asynchronous wb switching. Before 5ff8eaac1636 ("writeback: keep superblock pinned during cgroup writeback association switches"), this could race with umount leading to super_block being destroyed while inodes are pinned for wb switching. 5ff8eaac1636 fixed it by bumping s_active while wb switches are in flight; however, this allowed in-flight wb switches to make umounts asynchronous when the userland expected synchronosity - e.g. fsck immediately following umount may fail because the device is still busy. This patch removes the problematic super_block pinning and instead makes generic_shutdown_super() flush in-flight wb switches. wb switches are now executed on a dedicated isw_wq so that they can be flushed and isw_nr_in_flight keeps track of the number of in-flight wb switches so that flushing can be avoided in most cases. v2: Move cgroup_writeback_umount() further below and add MS_ACTIVE check in inode_switch_wbs() as Jan an Al suggested. Signed-off-by: Tejun Heo Reported-by: Tahsin Erdogan Cc: Jan Kara Cc: Al Viro Link: http://lkml.kernel.org/g/CAAeU0aNCq7LGODvVGRU-oU_o-6enii5ey0p1c26D1ZzYwkDc5A@mail.gmail.com Fixes: 5ff8eaac1636 ("writeback: keep superblock pinned during cgroup writeback association switches") Cc: stable@vger.kernel.org #v4.5 Reviewed-by: Jan Kara Tested-by: Tahsin Erdogan Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 54 +++++++++++++++++++++++++++++++++++------------ fs/super.c | 1 + include/linux/writeback.h | 5 +++++ 3 files changed, 47 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1f76d8950a57..5c46ed9f3e14 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi, #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ +static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); +static struct workqueue_struct *isw_wq; + void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); @@ -317,7 +320,6 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; - struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -424,8 +426,9 @@ skip_switch: wb_put(new_wb); iput(inode); - deactivate_super(sb); kfree(isw); + + atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) @@ -435,7 +438,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); - schedule_work(&isw->work); + queue_work(isw_wq, &isw->work); } /** @@ -471,20 +474,20 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); - - if (inode->i_state & (I_WB_SWITCH | I_FREEING) || - inode_to_wb(inode) == isw->new_wb) - goto out_unlock; - - if (!atomic_inc_not_zero(&inode->i_sb->s_active)) - goto out_unlock; - + if (!(inode->i_sb->s_flags & MS_ACTIVE) || + inode->i_state & (I_WB_SWITCH | I_FREEING) || + inode_to_wb(inode) == isw->new_wb) { + spin_unlock(&inode->i_lock); + goto out_free; + } inode->i_state |= I_WB_SWITCH; spin_unlock(&inode->i_lock); ihold(inode); isw->inode = inode; + atomic_inc(&isw_nr_in_flight); + /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the mapping's @@ -494,8 +497,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; -out_unlock: - spin_unlock(&inode->i_lock); out_free: if (isw->new_wb) wb_put(isw->new_wb); @@ -847,6 +848,33 @@ restart: wb_put(last_wb); } +/** + * cgroup_writeback_umount - flush inode wb switches for umount + * + * This function is called when a super_block is about to be destroyed and + * flushes in-flight inode wb switches. An inode wb switch goes through + * RCU and then workqueue, so the two need to be flushed in order to ensure + * that all previously scheduled switches are finished. As wb switches are + * rare occurrences and synchronize_rcu() can take a while, perform + * flushing iff wb switches are in flight. + */ +void cgroup_writeback_umount(void) +{ + if (atomic_read(&isw_nr_in_flight)) { + synchronize_rcu(); + flush_workqueue(isw_wq); + } +} + +static int __init cgroup_writeback_init(void) +{ + isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); + if (!isw_wq) + return -ENOMEM; + return 0; +} +fs_initcall(cgroup_writeback_init); + #else /* CONFIG_CGROUP_WRITEBACK */ static struct bdi_writeback * diff --git a/fs/super.c b/fs/super.c index 1182af8fd5ff..74914b1bae70 100644 --- a/fs/super.c +++ b/fs/super.c @@ -415,6 +415,7 @@ void generic_shutdown_super(struct super_block *sb) sb->s_flags &= ~MS_ACTIVE; fsnotify_unmount_inodes(sb); + cgroup_writeback_umount(); evict_inodes(sb); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b333c945e571..d0b5ca5d4e08 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -198,6 +198,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_io(struct writeback_control *wbc, struct page *page, size_t bytes); +void cgroup_writeback_umount(void); /** * inode_attach_wb - associate an inode with its wb @@ -301,6 +302,10 @@ static inline void wbc_account_io(struct writeback_control *wbc, { } +static inline void cgroup_writeback_umount(void) +{ +} + #endif /* CONFIG_CGROUP_WRITEBACK */ /* -- cgit v1.2.3 From f21018427cb007a0894c36ad702990ab639cbbb4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Mar 2016 14:43:45 -0700 Subject: block: fix blk_rq_get_max_sectors for driver private requests Driver private request types should not get the artifical cap for the FS requests. This is important to use the full device capabilities for internal command or NVMe pass through commands. Signed-off-by: Christoph Hellwig Reported-by: Jeff Lien Tested-by: Jeff Lien Reviewed-by: Keith Busch Updated by me to use an explicit check for the one command type that does support extended checking, instead of relying on the ordering of the enum command values - as suggested by Keith. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d7f6bca707ef..413c84fbc4ed 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -895,7 +895,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) { struct request_queue *q = rq->q; - if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC)) + if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD)) -- cgit v1.2.3