From 6605bdd59c21bb34c8f14ac4d6f2d419185f3528 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 28 Jun 2019 09:53:29 -0700 Subject: nvme: add I/O characteristics fields Several new fields have been introduced in version 1.4 of the NVMe spec at offsets that were defined as reserved in version 1.3d of the NVMe spec. Update the definition of the nvme_id_ns data structure such that it is in sync with version 1.4 of the NVMe spec. This change preserves backwards compatibility. Signed-off-by: Bart Van Assche Reviewed-by: Keith Busch Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d98b2d8baf4e..01aa6a6c241d 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -315,7 +315,7 @@ struct nvme_id_ns { __u8 nmic; __u8 rescap; __u8 fpi; - __u8 rsvd33; + __u8 dlfeat; __le16 nawun; __le16 nawupf; __le16 nacwu; @@ -324,11 +324,17 @@ struct nvme_id_ns { __le16 nabspf; __le16 noiob; __u8 nvmcap[16]; - __u8 rsvd64[28]; + __le16 npwg; + __le16 npwa; + __le16 npdg; + __le16 npda; + __le16 nows; + __u8 rsvd74[18]; __le32 anagrpid; __u8 rsvd96[3]; __u8 nsattr; - __u8 rsvd100[4]; + __le16 nvmsetid; + __le16 endgid; __u8 nguid[16]; __u8 eui64[8]; struct nvme_lbaf lbaf[16]; -- cgit v1.2.3-71-gd317 From 9b0eb69b75bccada2d341d7e7ca342f0cb1c9a6a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:48 -0700 Subject: cgroup, blkcg: Prepare some symbols for module and !CONFIG_CGROUP usages btrfs is going to use css_put() and wbc helpers to improve cgroup writeback support. Add dummy css_get() definition and export wbc helpers to prepare for module and !CONFIG_CGROUP builds. Reported-by: kbuild test robot Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 1 + fs/fs-writeback.c | 3 +++ include/linux/cgroup.h | 1 + 3 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 8afa52b0d148..ad7a91dec934 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -48,6 +48,7 @@ struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; +EXPORT_SYMBOL_GPL(blkcg_root_css); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 9ebfb1b28430..a8a40bc26c2f 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -270,6 +270,7 @@ void __inode_attach_wb(struct inode *inode, struct page *page) if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } +EXPORT_SYMBOL_GPL(__inode_attach_wb); /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it @@ -582,6 +583,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, if (unlikely(wb_dying(wbc->wb))) inode_switch_wbs(inode, wbc->wb_id); } +EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection @@ -701,6 +703,7 @@ void wbc_detach_inode(struct writeback_control *wbc) wb_put(wbc->wb); wbc->wb = NULL; } +EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_io - account IO issued during writeback diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3745ecdad925..852d885df10a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -699,6 +699,7 @@ void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, struct cgroup_subsys_state; struct cgroup; +static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } -- cgit v1.2.3-71-gd317 From 34e51a5e1a6e939ed7d99c38173821ab86d577f4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:49 -0700 Subject: blkcg, writeback: Rename wbc_account_io() to wbc_account_cgroup_owner() wbc_account_io() does a very specific job - try to see which cgroup is actually dirtying an inode and transfer its ownership to the majority dirtier if needed. The name is too generic and confusing. Let's rename it to something more specific. Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- Documentation/admin-guide/cgroup-v2.rst | 2 +- fs/btrfs/extent_io.c | 4 ++-- fs/buffer.c | 2 +- fs/ext4/page-io.c | 2 +- fs/f2fs/data.c | 4 ++-- fs/fs-writeback.c | 8 ++++---- fs/mpage.c | 2 +- include/linux/writeback.h | 8 ++++---- 8 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index a5c845338d6d..6223f485f7e1 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -2114,7 +2114,7 @@ following two functions. a queue (device) has been associated with the bio and before submission. - wbc_account_io(@wbc, @page, @bytes) + wbc_account_cgroup_owner(@wbc, @page, @bytes) Should be called for each data segment being written out. While this function doesn't care exactly when it's called during the writeback session, it's the easiest and most diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index db337e53aab3..5106008f5e28 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2911,7 +2911,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree, bio = NULL; } else { if (wbc) - wbc_account_io(wbc, page, page_size); + wbc_account_cgroup_owner(wbc, page, page_size); return 0; } } @@ -2924,7 +2924,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree, bio->bi_opf = opf; if (wbc) { wbc_init_bio(wbc, bio); - wbc_account_io(wbc, page, page_size); + wbc_account_cgroup_owner(wbc, page, page_size); } *bio_ret = bio; diff --git a/fs/buffer.c b/fs/buffer.c index e450c55f6434..40547bbbea94 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3093,7 +3093,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, if (wbc) { wbc_init_bio(wbc, bio); - wbc_account_io(wbc, bh->b_page, bh->b_size); + wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size); } submit_bio(bio); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 4690618a92e9..56e287f5ee50 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -404,7 +404,7 @@ submit_and_retry: ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; - wbc_account_io(io->io_wbc, page, bh->b_size); + wbc_account_cgroup_owner(io->io_wbc, page, bh->b_size); io->io_next_block++; return 0; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index eda4181d2092..e1cab1717ac7 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -470,7 +470,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) } if (fio->io_wbc && !is_read_io(fio->op)) - wbc_account_io(fio->io_wbc, page, PAGE_SIZE); + wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE); bio_set_op_attrs(bio, fio->op, fio->op_flags); @@ -537,7 +537,7 @@ alloc_new: } if (fio->io_wbc) - wbc_account_io(fio->io_wbc, bio_page, PAGE_SIZE); + wbc_account_cgroup_owner(fio->io_wbc, bio_page, PAGE_SIZE); io->last_block_in_bio = fio->new_blkaddr; f2fs_trace_ios(fio, 0); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index a8a40bc26c2f..0aef79e934bb 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -706,7 +706,7 @@ void wbc_detach_inode(struct writeback_control *wbc) EXPORT_SYMBOL_GPL(wbc_detach_inode); /** - * wbc_account_io - account IO issued during writeback + * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @page: page being written out * @bytes: number of bytes being written out @@ -715,8 +715,8 @@ EXPORT_SYMBOL_GPL(wbc_detach_inode); * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ -void wbc_account_io(struct writeback_control *wbc, struct page *page, - size_t bytes) +void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, + size_t bytes) { struct cgroup_subsys_state *css; int id; @@ -753,7 +753,7 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page, else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } -EXPORT_SYMBOL_GPL(wbc_account_io); +EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * inode_congested - test whether an inode is congested diff --git a/fs/mpage.c b/fs/mpage.c index 436a85260394..a63620cdb73a 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -647,7 +647,7 @@ alloc_new: * the confused fail path above (OOM) will be very confused when * it finds all bh marked clean (i.e. it will not write anything) */ - wbc_account_io(wbc, page, PAGE_SIZE); + wbc_account_cgroup_owner(wbc, page, PAGE_SIZE); length = first_unmapped << blkbits; if (bio_add_page(bio, page, length, 0) < length) { bio = mpage_bio_submit(REQ_OP_WRITE, op_flags, bio); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 738a0c24874f..dda5cf228172 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -188,8 +188,8 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock); void wbc_detach_inode(struct writeback_control *wbc); -void wbc_account_io(struct writeback_control *wbc, struct page *page, - size_t bytes); +void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, + size_t bytes); void cgroup_writeback_umount(void); /** @@ -291,8 +291,8 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { } -static inline void wbc_account_io(struct writeback_control *wbc, - struct page *page, size_t bytes) +static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, + struct page *page, size_t bytes) { } -- cgit v1.2.3-71-gd317 From 27b36d8fa81fa8274fb72f4eb1484026f6b6daa8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:50 -0700 Subject: blkcg, writeback: Add wbc->no_cgroup_owner When writeback IOs are bounced through async layers, the IOs should only be accounted against the wbc from the original bdi writeback to avoid confusing cgroup inode ownership arbitration. Add wbc->no_cgroup_owner to allow disabling wbc cgroup owner accounting. This will be used make btrfs compression work well with cgroup IO control. v2: Renamed from no_wbc_acct to no_cgroup_owner and added comment as per Jan. Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 2 +- include/linux/writeback.h | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 0aef79e934bb..542b02d170f8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -727,7 +727,7 @@ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ - if (!wbc->wb) + if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_page(page); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index dda5cf228172..33a50fa09fac 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -68,6 +68,15 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + + /* + * When writeback IOs are bounced through async layers, only the + * initial synchronous phase should be accounted towards inode + * cgroup ownership arbitration to avoid confusion. Later stages + * can set the following flag to disable the accounting. + */ + unsigned no_cgroup_owner:1; + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ -- cgit v1.2.3-71-gd317 From 653c45c6b90c9659facbef10546d1f3a8e37d0cf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:51 -0700 Subject: blkcg, writeback: Implement wbc_blkcg_css() Add a helper to determine the target blkcg from wbc. Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/writeback.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 33a50fa09fac..e056a22075cf 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -11,6 +11,7 @@ #include #include #include +#include struct bio; @@ -101,6 +102,16 @@ static inline int wbc_to_write_flags(struct writeback_control *wbc) return 0; } +static inline struct cgroup_subsys_state * +wbc_blkcg_css(struct writeback_control *wbc) +{ +#ifdef CONFIG_CGROUP_WRITEBACK + if (wbc->wb) + return wbc->wb->blkcg_css; +#endif + return blkcg_root_css; +} + /* * A wb_domain represents a domain that wb's (bdi_writeback's) belong to * and are measured against each other in. There always is one global -- cgit v1.2.3-71-gd317 From d3f77dfdc71835f8db71ca57d272b1fbec9dfc18 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 27 Jun 2019 13:39:52 -0700 Subject: blkcg: implement REQ_CGROUP_PUNT When a shared kthread needs to issue a bio for a cgroup, doing so synchronously can lead to priority inversions as the kthread can be trapped waiting for that cgroup. This patch implements REQ_CGROUP_PUNT flag which makes submit_bio() punt the actual issuing to a dedicated per-blkcg work item to avoid such priority inversions. This will be used to fix priority inversions in btrfs compression and should be generally useful as we grow filesystem support for comprehensive IO control. Cc: Chris Mason Reviewed-by: Josef Bacik Reviewed-by: Jan Kara Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 53 +++++++++++++++++++++++++++++++++++++++++++++ block/blk-core.c | 3 +++ include/linux/backing-dev.h | 1 + include/linux/blk-cgroup.h | 16 +++++++++++++- include/linux/blk_types.h | 10 +++++++++ include/linux/writeback.h | 13 ++++++++--- 6 files changed, 92 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index ad7a91dec934..24ed26957367 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -55,6 +55,7 @@ static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ static bool blkcg_debug_stats = false; +static struct workqueue_struct *blkcg_punt_bio_wq; static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) @@ -89,6 +90,8 @@ static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); + WARN_ON(!bio_list_empty(&blkg->async_bios)); + /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); if (blkg->parent) @@ -114,6 +117,23 @@ static void blkg_release(struct percpu_ref *ref) call_rcu(&blkg->rcu_head, __blkg_release); } +static void blkg_async_bio_workfn(struct work_struct *work) +{ + struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, + async_bio_work); + struct bio_list bios = BIO_EMPTY_LIST; + struct bio *bio; + + /* as long as there are pending bios, @blkg can't go away */ + spin_lock_bh(&blkg->async_bio_lock); + bio_list_merge(&bios, &blkg->async_bios); + bio_list_init(&blkg->async_bios); + spin_unlock_bh(&blkg->async_bio_lock); + + while ((bio = bio_list_pop(&bios))) + submit_bio(bio); +} + /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with @@ -142,6 +162,9 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, blkg->q = q; INIT_LIST_HEAD(&blkg->q_node); + spin_lock_init(&blkg->async_bio_lock); + bio_list_init(&blkg->async_bios); + INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); blkg->blkcg = blkcg; for (i = 0; i < BLKCG_MAX_POLS; i++) { @@ -1528,6 +1551,25 @@ out_unlock: } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); +bool __blkcg_punt_bio_submit(struct bio *bio) +{ + struct blkcg_gq *blkg = bio->bi_blkg; + + /* consume the flag first */ + bio->bi_opf &= ~REQ_CGROUP_PUNT; + + /* never bounce for the root cgroup */ + if (!blkg->parent) + return false; + + spin_lock_bh(&blkg->async_bio_lock); + bio_list_add(&blkg->async_bios, bio); + spin_unlock_bh(&blkg->async_bio_lock); + + queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work); + return true; +} + /* * Scale the accumulated delay based on how long it has been since we updated * the delay. We only call this when we are adding delay, in case it's been a @@ -1729,5 +1771,16 @@ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) atomic64_add(delta, &blkg->delay_nsec); } +static int __init blkcg_init(void) +{ + blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", + WQ_MEM_RECLAIM | WQ_FREEZABLE | + WQ_UNBOUND | WQ_SYSFS, 0); + if (!blkcg_punt_bio_wq) + return -ENOMEM; + return 0; +} +subsys_initcall(blkcg_init); + module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); diff --git a/block/blk-core.c b/block/blk-core.c index edd009213f5b..260e36a2c343 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1128,6 +1128,9 @@ EXPORT_SYMBOL_GPL(direct_make_request); */ blk_qc_t submit_bio(struct bio *bio) { + if (blkcg_punt_bio_submit(bio)) + return BLK_QC_T_NONE; + /* * If it's a regular read/write or a barrier with data attached, * go through the normal accounting stuff before submission. diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f9b029180241..35b31d176f74 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -48,6 +48,7 @@ extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; +extern struct workqueue_struct *bdi_async_bio_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 33f23a858438..689a58231288 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -132,13 +132,17 @@ struct blkcg_gq { struct blkg_policy_data *pd[BLKCG_MAX_POLS]; - struct rcu_head rcu_head; + spinlock_t async_bio_lock; + struct bio_list async_bios; + struct work_struct async_bio_work; atomic_t use_delay; atomic64_t delay_nsec; atomic64_t delay_start; u64 last_delay; int last_use; + + struct rcu_head rcu_head; }; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); @@ -701,6 +705,15 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif +bool __blkcg_punt_bio_submit(struct bio *bio); + +static inline bool blkcg_punt_bio_submit(struct bio *bio) +{ + if (bio->bi_opf & REQ_CGROUP_PUNT) + return __blkcg_punt_bio_submit(bio); + else + return false; +} static inline void blkcg_bio_issue_init(struct bio *bio) { @@ -848,6 +861,7 @@ static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } static inline void blkg_get(struct blkcg_gq *blkg) { } static inline void blkg_put(struct blkcg_gq *blkg) { } +static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 6a53799c3fe2..feff3fe4467e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -311,6 +311,14 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ + /* + * When a shared kthread needs to issue a bio for a cgroup, doing + * so synchronously can lead to priority inversions as the kthread + * can be trapped waiting for that cgroup. CGROUP_PUNT flag makes + * submit_bio() punt the actual issuing to a dedicated per-blkcg + * work item to avoid such priority inversions. + */ + __REQ_CGROUP_PUNT, /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ @@ -337,6 +345,8 @@ enum req_flag_bits { #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) #define REQ_NOWAIT (1ULL << __REQ_NOWAIT) +#define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) + #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_HIPRI (1ULL << __REQ_HIPRI) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index e056a22075cf..8945aac31392 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -78,6 +78,8 @@ struct writeback_control { */ unsigned no_cgroup_owner:1; + unsigned punt_to_cgroup:1; /* cgrp punting, see __REQ_CGROUP_PUNT */ + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ @@ -94,12 +96,17 @@ struct writeback_control { static inline int wbc_to_write_flags(struct writeback_control *wbc) { + int flags = 0; + + if (wbc->punt_to_cgroup) + flags = REQ_CGROUP_PUNT; + if (wbc->sync_mode == WB_SYNC_ALL) - return REQ_SYNC; + flags |= REQ_SYNC; else if (wbc->for_kupdate || wbc->for_background) - return REQ_BACKGROUND; + flags |= REQ_BACKGROUND; - return 0; + return flags; } static inline struct cgroup_subsys_state * -- cgit v1.2.3-71-gd317 From 113ab72ed4794c193509a97d7c6d32a6886e1682 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 10 Jul 2019 13:53:10 +0900 Subject: block: Fix potential overflow in blk_report_zones() For large values of the number of zones reported and/or large zone sizes, the sector increment calculated with blk_queue_zone_sectors(q) * n in blk_report_zones() loop can overflow the unsigned int type used for the calculation as both "n" and blk_queue_zone_sectors() value are unsigned int. E.g. for a device with 256 MB zones (524288 sectors), overflow happens with 8192 or more zones reported. Changing the return type of blk_queue_zone_sectors() to sector_t, fixes this problem and avoids overflow problem for all other callers of this helper too. The same change is also applied to the bdev_zone_sectors() helper. Fixes: e76239a3748c ("block: add a report_zones method") Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-zoned.c | 2 +- include/linux/blkdev.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index ae7e91bd0618..3249738242b4 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -70,7 +70,7 @@ EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock); static inline unsigned int __blkdev_nr_zones(struct request_queue *q, sector_t nr_sectors) { - unsigned long zone_sectors = blk_queue_zone_sectors(q); + sector_t zone_sectors = blk_queue_zone_sectors(q); return (nr_sectors + zone_sectors - 1) >> ilog2(zone_sectors); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0c482371c8b3..259bd7ad8312 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -681,7 +681,7 @@ static inline bool blk_queue_is_zoned(struct request_queue *q) } } -static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) +static inline sector_t blk_queue_zone_sectors(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } @@ -1418,7 +1418,7 @@ static inline bool bdev_is_zoned(struct block_device *bdev) return false; } -static inline unsigned int bdev_zone_sectors(struct block_device *bdev) +static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3-71-gd317 From 36847a005489cfb74dc6388952da73346f867dca Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 Jul 2019 00:56:08 +0900 Subject: block: Remove unused definitions The ELV_MQUEUE_XXX definitions in include/linux/elevator.h are unused since the removal of elevator_may_queue_fn in kernel 5.0. Remove these definitions and also remove the documentation of elevator_may_queue_fn in Documentiation/block/biodoc.txt. Acked-by: Marcos Paulo de Souza Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- Documentation/block/biodoc.txt | 5 ----- include/linux/elevator.h | 9 --------- 2 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 31c177663ed5..5a4a799fe61b 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -843,11 +843,6 @@ elevator_latter_req_fn These return the request before or after the elevator_completed_req_fn called when a request is completed. -elevator_may_queue_fn returns true if the scheduler wants to allow the - current context to queue a new request even if - it is over the queue limit. This must be used - very carefully!! - elevator_set_req_fn elevator_put_req_fn Must be used to allocate and free any elevator specific storage for a request. diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 169bb2e02516..38590c30a11d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -160,15 +160,6 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t); #define ELEVATOR_INSERT_FLUSH 5 #define ELEVATOR_INSERT_SORT_MERGE 6 -/* - * return values from elevator_may_queue_fn - */ -enum { - ELV_MQUEUE_MAY, - ELV_MQUEUE_NO, - ELV_MQUEUE_MUST, -}; - #define rq_end_sector(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq)) #define rb_entry_rq(node) rb_entry((node), struct request, rb_node) -- cgit v1.2.3-71-gd317 From 9305d5d721f2bd5e2eeb670035159b560ca211ca Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 11 Jul 2019 00:57:41 +0900 Subject: block: Fix elevator name declaration The elevator_name field in struct elevator_type is declared as an array of characters (ELV_NAME_MAX size) but in practice used as a string pointer with its initialization done statically within each elevator elevator_type structure declaration. Change the declaration of elevator_name to the more appropriate "const char *" type. Acked-by: Marcos Paulo de Souza Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/elevator.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 38590c30a11d..17cd0078377c 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -75,7 +75,7 @@ struct elevator_type size_t icq_size; /* see iocontext.h */ size_t icq_align; /* ditto */ struct elv_fs_entry *elevator_attrs; - char elevator_name[ELV_NAME_MAX]; + const char *elevator_name; const char *elevator_alias; struct module *elevator_owner; #ifdef CONFIG_BLK_DEBUG_FS -- cgit v1.2.3-71-gd317 From bd976e52725965ddcceb9abecbcc7ca46863665c Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 1 Jul 2019 14:09:16 +0900 Subject: block: Kill gfp_t argument of blkdev_report_zones() Only GFP_KERNEL and GFP_NOIO are used with blkdev_report_zones(). In preparation of using vmalloc() for large report buffer and zone array allocations used by this function, remove its "gfp_t gfp_mask" argument and rely on the caller context to use memalloc_noio_save/restore() where necessary (block layer zone revalidation and dm-zoned I/O error path). Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-zoned.c | 31 +++++++++++++++++++------------ drivers/block/null_blk.h | 3 +-- drivers/block/null_blk_zoned.c | 3 +-- drivers/md/dm-flakey.c | 5 ++--- drivers/md/dm-linear.c | 5 ++--- drivers/md/dm-zoned-metadata.c | 16 ++++++++++++---- drivers/md/dm.c | 6 ++---- drivers/scsi/sd.h | 3 +-- drivers/scsi/sd_zbc.c | 6 ++---- fs/f2fs/super.c | 4 +--- include/linux/blkdev.h | 5 ++--- include/linux/device-mapper.h | 3 +-- 12 files changed, 46 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 3249738242b4..58ced170b424 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "blk.h" @@ -117,8 +118,7 @@ static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep) } static int blk_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask) + struct blk_zone *zones, unsigned int *nr_zones) { struct request_queue *q = disk->queue; unsigned int z = 0, n, nrz = *nr_zones; @@ -127,8 +127,7 @@ static int blk_report_zones(struct gendisk *disk, sector_t sector, while (z < nrz && sector < capacity) { n = nrz - z; - ret = disk->fops->report_zones(disk, sector, &zones[z], &n, - gfp_mask); + ret = disk->fops->report_zones(disk, sector, &zones[z], &n); if (ret) return ret; if (!n) @@ -149,17 +148,18 @@ static int blk_report_zones(struct gendisk *disk, sector_t sector, * @sector: Sector from which to report zones * @zones: Array of zone structures where to return the zones information * @nr_zones: Number of zone structures in the zone array - * @gfp_mask: Memory allocation flags (for bio_alloc) * * Description: * Get zone information starting from the zone containing @sector. * The number of zone information reported may be less than the number * requested by @nr_zones. The number of zones actually reported is * returned in @nr_zones. + * The caller must use memalloc_noXX_save/restore() calls to control + * memory allocations done within this function (zone array and command + * buffer allocation by the device driver). */ int blkdev_report_zones(struct block_device *bdev, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask) + struct blk_zone *zones, unsigned int *nr_zones) { struct request_queue *q = bdev_get_queue(bdev); unsigned int i, nrz; @@ -184,7 +184,7 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, nrz = min(*nr_zones, __blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector)); ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector, - zones, &nrz, gfp_mask); + zones, &nrz); if (ret) return ret; @@ -305,9 +305,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, if (!zones) return -ENOMEM; - ret = blkdev_report_zones(bdev, rep.sector, - zones, &rep.nr_zones, - GFP_KERNEL); + ret = blkdev_report_zones(bdev, rep.sector, zones, &rep.nr_zones); if (ret) goto out; @@ -415,6 +413,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL; unsigned int i, rep_nr_zones = 0, z = 0, nrz; struct blk_zone *zones = NULL; + unsigned int noio_flag; sector_t sector = 0; int ret = 0; @@ -427,6 +426,12 @@ int blk_revalidate_disk_zones(struct gendisk *disk) return 0; } + /* + * Ensure that all memory allocations in this context are done as + * if GFP_NOIO was specified. + */ + noio_flag = memalloc_noio_save(); + if (!blk_queue_is_zoned(q) || !nr_zones) { nr_zones = 0; goto update; @@ -449,7 +454,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) while (z < nr_zones) { nrz = min(nr_zones - z, rep_nr_zones); - ret = blk_report_zones(disk, sector, zones, &nrz, GFP_NOIO); + ret = blk_report_zones(disk, sector, zones, &nrz); if (ret) goto out; if (!nrz) @@ -480,6 +485,8 @@ update: blk_mq_unfreeze_queue(q); out: + memalloc_noio_restore(noio_flag); + free_pages((unsigned long)zones, get_order(rep_nr_zones * sizeof(struct blk_zone))); kfree(seq_zones_wlock); diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index 34b22d6523ba..4b9bbe3bb5a1 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -89,8 +89,7 @@ struct nullb { int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); int null_zone_report(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask); + struct blk_zone *zones, unsigned int *nr_zones); void null_zone_write(struct nullb_cmd *cmd, sector_t sector, unsigned int nr_sectors); void null_zone_reset(struct nullb_cmd *cmd, sector_t sector); diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index fca0c97ff1aa..cb28d93f2bd1 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -67,8 +67,7 @@ void null_zone_exit(struct nullb_device *dev) } int null_zone_report(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask) + struct blk_zone *zones, unsigned int *nr_zones) { struct nullb *nullb = disk->private_data; struct nullb_device *dev = nullb->dev; diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index a9bc518156f2..2900fbde89b3 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -461,15 +461,14 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev #ifdef CONFIG_BLK_DEV_ZONED static int flakey_report_zones(struct dm_target *ti, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask) + struct blk_zone *zones, unsigned int *nr_zones) { struct flakey_c *fc = ti->private; int ret; /* Do report and remap it */ ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector), - zones, nr_zones, gfp_mask); + zones, nr_zones); if (ret != 0) return ret; diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index ad980a38fb1e..ecefe6703736 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -137,15 +137,14 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev #ifdef CONFIG_BLK_DEV_ZONED static int linear_report_zones(struct dm_target *ti, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask) + struct blk_zone *zones, unsigned int *nr_zones) { struct linear_c *lc = (struct linear_c *) ti->private; int ret; /* Do report and remap it */ ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector), - zones, nr_zones, gfp_mask); + zones, nr_zones); if (ret != 0) return ret; diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index d8334cd45d7c..9faf3e49c7af 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -8,6 +8,7 @@ #include #include +#include #define DM_MSG_PREFIX "zoned metadata" @@ -1162,8 +1163,7 @@ static int dmz_init_zones(struct dmz_metadata *zmd) while (sector < dev->capacity) { /* Get zone information */ nr_blkz = DMZ_REPORT_NR_ZONES; - ret = blkdev_report_zones(dev->bdev, sector, blkz, - &nr_blkz, GFP_KERNEL); + ret = blkdev_report_zones(dev->bdev, sector, blkz, &nr_blkz); if (ret) { dmz_dev_err(dev, "Report zones failed %d", ret); goto out; @@ -1201,12 +1201,20 @@ out: static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) { unsigned int nr_blkz = 1; + unsigned int noio_flag; struct blk_zone blkz; int ret; - /* Get zone information from disk */ + /* + * Get zone information from disk. Since blkdev_report_zones() uses + * GFP_KERNEL by default for memory allocations, set the per-task + * PF_MEMALLOC_NOIO flag so that all allocations are done as if + * GFP_NOIO was specified. + */ + noio_flag = memalloc_noio_save(); ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), - &blkz, &nr_blkz, GFP_NOIO); + &blkz, &nr_blkz); + memalloc_noio_restore(noio_flag); if (!nr_blkz) ret = -EIO; if (ret) { diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 5475081dcbd6..61f1152b74e9 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -441,8 +441,7 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) } static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask) + struct blk_zone *zones, unsigned int *nr_zones) { #ifdef CONFIG_BLK_DEV_ZONED struct mapped_device *md = disk->private_data; @@ -480,8 +479,7 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, * So there is no need to loop here trying to fill the entire array * of zones. */ - ret = tgt->type->report_zones(tgt, sector, zones, - nr_zones, gfp_mask); + ret = tgt->type->report_zones(tgt, sector, zones, nr_zones); out: dm_put_live_table(md, srcu_idx); diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 5796ace76225..38c50946fc42 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -213,8 +213,7 @@ extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd); extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr); extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask); + struct blk_zone *zones, unsigned int *nr_zones); #else /* CONFIG_BLK_DEV_ZONED */ diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 7334024b64f1..ec3764c8f3f1 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -109,13 +109,11 @@ static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf, * @sector: Start 512B sector of the report * @zones: Array of zone descriptors * @nr_zones: Number of descriptors in the array - * @gfp_mask: Memory allocation mask * * Execute a report zones command on the target disk. */ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask) + struct blk_zone *zones, unsigned int *nr_zones) { struct scsi_disk *sdkp = scsi_disk(disk); unsigned int i, buflen, nrz = *nr_zones; @@ -134,7 +132,7 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, */ buflen = min(queue_max_hw_sectors(disk->queue) << 9, roundup((nrz + 1) * 64, 512)); - buf = kmalloc(buflen, gfp_mask); + buf = kmalloc(buflen, GFP_KERNEL); if (!buf) return -ENOMEM; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 6b959bbb336a..4e91ba6c8a2e 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2841,9 +2841,7 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) while (zones && sector < nr_sectors) { nr_zones = F2FS_REPORT_NR_ZONES; - err = blkdev_report_zones(bdev, sector, - zones, &nr_zones, - GFP_KERNEL); + err = blkdev_report_zones(bdev, sector, zones, &nr_zones); if (err) break; if (!nr_zones) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 259bd7ad8312..05036e3e3458 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -347,7 +347,7 @@ struct queue_limits { extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, - unsigned int *nr_zones, gfp_t gfp_mask); + unsigned int *nr_zones); extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); extern int blk_revalidate_disk_zones(struct gendisk *disk); @@ -1673,8 +1673,7 @@ struct block_device_operations { /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones, - gfp_t gfp_mask); + struct blk_zone *zones, unsigned int *nr_zones); struct module *owner; const struct pr_ops *pr_ops; }; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index e1f51d607cc5..3b470cb03b66 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -95,8 +95,7 @@ typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device ** typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector, struct blk_zone *zones, - unsigned int *nr_zones, - gfp_t gfp_mask); + unsigned int *nr_zones); /* * These iteration functions are typically used to check (and combine) -- cgit v1.2.3-71-gd317 From 26202928fafad8bda8b478edb7e62c885be623d7 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 1 Jul 2019 14:09:18 +0900 Subject: block: Limit zone array allocation size Limit the size of the struct blk_zone array used in blk_revalidate_disk_zones() to avoid memory allocation failures leading to disk revalidation failure. Also further reduce the likelyhood of such failures by using kvcalloc() (that is vmalloc()) instead of allocating contiguous pages with alloc_pages(). Fixes: 515ce6061312 ("scsi: sd_zbc: Fix sd_zbc_report_zones() buffer allocation") Fixes: e76239a3748c ("block: add a report_zones method") Cc: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-zoned.c | 36 ++++++++++++++++++++---------------- include/linux/blkdev.h | 5 +++++ 2 files changed, 25 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 58ced170b424..6c503824ba3f 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include #include #include "blk.h" @@ -371,22 +373,25 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node, * Allocate an array of struct blk_zone to get nr_zones zone information. * The allocated array may be smaller than nr_zones. */ -static struct blk_zone *blk_alloc_zones(int node, unsigned int *nr_zones) +static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones) { - size_t size = *nr_zones * sizeof(struct blk_zone); - struct page *page; - int order; - - for (order = get_order(size); order >= 0; order--) { - page = alloc_pages_node(node, GFP_NOIO | __GFP_ZERO, order); - if (page) { - *nr_zones = min_t(unsigned int, *nr_zones, - (PAGE_SIZE << order) / sizeof(struct blk_zone)); - return page_address(page); - } + struct blk_zone *zones; + size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES); + + /* + * GFP_KERNEL here is meaningless as the caller task context has + * the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones() + * with memalloc_noio_save(). + */ + zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL); + if (!zones) { + *nr_zones = 0; + return NULL; } - return NULL; + *nr_zones = nrz; + + return zones; } void blk_queue_free_zone_bitmaps(struct request_queue *q) @@ -448,7 +453,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) /* Get zone information and initialize seq_zones_bitmap */ rep_nr_zones = nr_zones; - zones = blk_alloc_zones(q->node, &rep_nr_zones); + zones = blk_alloc_zones(&rep_nr_zones); if (!zones) goto out; @@ -487,8 +492,7 @@ update: out: memalloc_noio_restore(noio_flag); - free_pages((unsigned long)zones, - get_order(rep_nr_zones * sizeof(struct blk_zone))); + kvfree(zones); kfree(seq_zones_wlock); kfree(seq_zones_bitmap); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 05036e3e3458..1ef375dafb1c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -344,6 +344,11 @@ struct queue_limits { #ifdef CONFIG_BLK_DEV_ZONED +/* + * Maximum number of zones to report with a single report zones command. + */ +#define BLK_ZONED_REPORT_MAX_ZONES 8192U + extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, -- cgit v1.2.3-71-gd317