From 13f063815265c5397ee92d84436804bc9fb6b58b Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Sun, 24 Mar 2019 17:57:07 +0800 Subject: blk-mq: use blk_mq_put_driver_tag() to put tag Expect arguments, blk_mq_put_driver_tag_hctx() and blk_mq_put_driver_tag() is same. We can just use argument 'request' to put tag by blk_mq_put_driver_tag(). Then we can remove the unused blk_mq_put_driver_tag_hctx(). Signed-off-by: Yufen Yu Signed-off-by: Jens Axboe --- block/blk-flush.c | 4 ++-- block/blk-mq.h | 9 --------- 2 files changed, 2 insertions(+), 11 deletions(-) diff --git a/block/blk-flush.c b/block/blk-flush.c index 6e0f2d97fc6d..d95f94892015 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -220,7 +220,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq); flush_rq->tag = -1; } else { - blk_mq_put_driver_tag_hctx(hctx, flush_rq); + blk_mq_put_driver_tag(flush_rq); flush_rq->internal_tag = -1; } @@ -324,7 +324,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error) if (q->elevator) { WARN_ON(rq->tag < 0); - blk_mq_put_driver_tag_hctx(hctx, rq); + blk_mq_put_driver_tag(rq); } /* diff --git a/block/blk-mq.h b/block/blk-mq.h index 0ed8e5a8729f..d704fc7766f4 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -224,15 +224,6 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, } } -static inline void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx, - struct request *rq) -{ - if (rq->tag == -1 || rq->internal_tag == -1) - return; - - __blk_mq_put_driver_tag(hctx, rq); -} - static inline void blk_mq_put_driver_tag(struct request *rq) { if (rq->tag == -1 || rq->internal_tag == -1) -- cgit v1.2.3-58-ga151 From 85fae294e1a506b4213668716acb586bd6b4ae1e Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Sun, 24 Mar 2019 17:57:08 +0800 Subject: blk-mq: update comment for blk_mq_hctx_has_pending() For now, blk_mq_hctx_has_pending() checks any of ctx, hctx->dispatch or io scheduler have pending work. So, update the comment accordingly. Signed-off-by: Yufen Yu Signed-off-by: Jens Axboe --- block/blk-mq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 70b210a308c4..28080b0235f0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -59,7 +59,8 @@ static int blk_mq_poll_stats_bkt(const struct request *rq) } /* - * Check if any of the ctx's have pending work in this hardware queue + * Check if any of the ctx, dispatch list or elevator + * have pending work in this hardware queue. */ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx) { -- cgit v1.2.3-58-ga151 From 9e75ad5d8f399a21c86271571aa630dd080223e2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 25 Mar 2019 15:34:53 +0100 Subject: io_uring: fix big-endian compat signal mask handling On big-endian architectures, the signal masks are differnet between 32-bit and 64-bit tasks, so we have to use a different function for reading them from user space. io_cqring_wait() initially got this wrong, and always interprets this as a native structure. This is ok on x86 and most arm64, but not on s390, ppc64be, mips64be, sparc64 and parisc. Signed-off-by: Arnd Bergmann Signed-off-by: Jens Axboe --- fs/io_uring.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 6aaa30580a2b..8f48d29abf76 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1968,7 +1968,15 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return 0; if (sig) { - ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz); +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, + &ksigmask, &sigsaved, sigsz); + else +#endif + ret = set_user_sigmask(sig, &ksigmask, + &sigsaved, sigsz); + if (ret) return ret; } -- cgit v1.2.3-58-ga151 From e861857545567adec8da3bdff728efdf7db12285 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 25 Mar 2019 12:34:10 -0600 Subject: blk-mq: fix sbitmap ws_active for shared tags We now wrap sbitmap waitqueues in an active counter, so we can avoid iterating wakeups unless we have waiters there. This works as long as everyone that's manipulating the waitqueues use the proper helpers. For the tag wait case for shared tags, however, we add ourselves to the waitqueue without incrementing/decrementing the ->ws_active count. This means that wakeups can take a long time to happen. Fix this by manually doing the inc/dec as needed for the wait queue handling. Reported-by: Michael Leun Tested-by: Michael Leun Cc: stable@vger.kernel.org Reviewed-by: Omar Sandoval Fixes: 5d2ee7122c73 ("sbitmap: optimize wakeup check") Signed-off-by: Jens Axboe --- block/blk-mq.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 28080b0235f0..3ff3d7b49969 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1072,7 +1072,13 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait); spin_lock(&hctx->dispatch_wait_lock); - list_del_init(&wait->entry); + if (!list_empty(&wait->entry)) { + struct sbitmap_queue *sbq; + + list_del_init(&wait->entry); + sbq = &hctx->tags->bitmap_tags; + atomic_dec(&sbq->ws_active); + } spin_unlock(&hctx->dispatch_wait_lock); blk_mq_run_hw_queue(hctx, true); @@ -1088,6 +1094,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { + struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags; struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; @@ -1110,7 +1117,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, if (!list_empty_careful(&wait->entry)) return false; - wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait; + wq = &bt_wait_ptr(sbq, hctx)->wait; spin_lock_irq(&wq->lock); spin_lock(&hctx->dispatch_wait_lock); @@ -1120,6 +1127,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, return false; } + atomic_inc(&sbq->ws_active); wait->flags &= ~WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq, wait); @@ -1140,6 +1148,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, * someone else gets the wakeup. */ list_del_init(&wait->entry); + atomic_dec(&sbq->ws_active); spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); -- cgit v1.2.3-58-ga151 From e6d1fa584e0dd9bfebaf345e9feea588cf75ead2 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Mar 2019 09:13:51 +0800 Subject: sbitmap: order READ/WRITE freed instance and setting clear bit Inside sbitmap_queue_clear(), once the clear bit is set, it will be visiable to allocation path immediately. Meantime READ/WRITE on old associated instance(such as request in case of blk-mq) may be out-of-order with the setting clear bit, so race with re-allocation may be triggered. Adds one memory barrier for ordering READ/WRITE of the freed associated instance with setting clear bit for avoiding race with re-allocation. The following kernel oops triggerd by block/006 on aarch64 may be fixed: [ 142.330954] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000330 [ 142.338794] Mem abort info: [ 142.341554] ESR = 0x96000005 [ 142.344632] Exception class = DABT (current EL), IL = 32 bits [ 142.350500] SET = 0, FnV = 0 [ 142.353544] EA = 0, S1PTW = 0 [ 142.356678] Data abort info: [ 142.359528] ISV = 0, ISS = 0x00000005 [ 142.363343] CM = 0, WnR = 0 [ 142.366305] user pgtable: 64k pages, 48-bit VAs, pgdp = 000000002a3c51c0 [ 142.372983] [0000000000000330] pgd=0000000000000000, pud=0000000000000000 [ 142.379777] Internal error: Oops: 96000005 [#1] SMP [ 142.384613] Modules linked in: null_blk ib_isert iscsi_target_mod ib_srpt target_core_mod ib_srp scsi_transport_srp vfat fat rpcrdma sunrpc rdma_ucm ib_iser rdma_cm iw_cm libiscsi ib_umad scsi_transport_iscsi ib_ipoib ib_cm mlx5_ib ib_uverbs ib_core sbsa_gwdt crct10dif_ce ghash_ce ipmi_ssif sha2_ce ipmi_devintf sha256_arm64 sg sha1_ce ipmi_msghandler ip_tables xfs libcrc32c mlx5_core sdhci_acpi mlxfw ahci_platform at803x sdhci libahci_platform qcom_emac mmc_core hdma hdma_mgmt i2c_dev [last unloaded: null_blk] [ 142.429753] CPU: 7 PID: 1983 Comm: fio Not tainted 5.0.0.cki #2 [ 142.449458] pstate: 00400005 (nzcv daif +PAN -UAO) [ 142.454239] pc : __blk_mq_free_request+0x4c/0xa8 [ 142.458830] lr : blk_mq_free_request+0xec/0x118 [ 142.463344] sp : ffff00003360f6a0 [ 142.466646] x29: ffff00003360f6a0 x28: ffff000010e70000 [ 142.471941] x27: ffff801729a50048 x26: 0000000000010000 [ 142.477232] x25: ffff00003360f954 x24: ffff7bdfff021440 [ 142.482529] x23: 0000000000000000 x22: 00000000ffffffff [ 142.487830] x21: ffff801729810000 x20: 0000000000000000 [ 142.493123] x19: ffff801729a50000 x18: 0000000000000000 [ 142.498413] x17: 0000000000000000 x16: 0000000000000001 [ 142.503709] x15: 00000000000000ff x14: ffff7fe000000000 [ 142.509003] x13: ffff8017dcde09a0 x12: 0000000000000000 [ 142.514308] x11: 0000000000000001 x10: 0000000000000008 [ 142.519597] x9 : ffff8017dcde09a0 x8 : 0000000000002000 [ 142.524889] x7 : ffff8017dcde0a00 x6 : 000000015388f9be [ 142.530187] x5 : 0000000000000001 x4 : 0000000000000000 [ 142.535478] x3 : 0000000000000000 x2 : 0000000000000000 [ 142.540777] x1 : 0000000000000001 x0 : ffff00001041b194 [ 142.546071] Process fio (pid: 1983, stack limit = 0x000000006460a0ea) [ 142.552500] Call trace: [ 142.554926] __blk_mq_free_request+0x4c/0xa8 [ 142.559181] blk_mq_free_request+0xec/0x118 [ 142.563352] blk_mq_end_request+0xfc/0x120 [ 142.567444] end_cmd+0x3c/0xa8 [null_blk] [ 142.571434] null_complete_rq+0x20/0x30 [null_blk] [ 142.576194] blk_mq_complete_request+0x108/0x148 [ 142.580797] null_handle_cmd+0x1d4/0x718 [null_blk] [ 142.585662] null_queue_rq+0x60/0xa8 [null_blk] [ 142.590171] blk_mq_try_issue_directly+0x148/0x280 [ 142.594949] blk_mq_try_issue_list_directly+0x9c/0x108 [ 142.600064] blk_mq_sched_insert_requests+0xb0/0xd0 [ 142.604926] blk_mq_flush_plug_list+0x16c/0x2a0 [ 142.609441] blk_flush_plug_list+0xec/0x118 [ 142.613608] blk_finish_plug+0x3c/0x4c [ 142.617348] blkdev_direct_IO+0x3b4/0x428 [ 142.621336] generic_file_read_iter+0x84/0x180 [ 142.625761] blkdev_read_iter+0x50/0x78 [ 142.629579] aio_read.isra.6+0xf8/0x190 [ 142.633409] __io_submit_one.isra.8+0x148/0x738 [ 142.637912] io_submit_one.isra.9+0x88/0xb8 [ 142.642078] __arm64_sys_io_submit+0xe0/0x238 [ 142.646428] el0_svc_handler+0xa0/0x128 [ 142.650238] el0_svc+0x8/0xc [ 142.653104] Code: b9402a63 f9000a7f 3100047f 540000a0 (f9419a81) [ 142.659202] ---[ end trace 467586bc175eb09d ]--- Fixes: ea86ea2cdced20057da ("sbitmap: ammortize cost of clearing bits") Reported-and-bisected_and_tested-by: Yi Zhang Cc: Yi Zhang Cc: "jianchao.wang" Reviewed-by: Omar Sandoval Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- lib/sbitmap.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 5b382c1244ed..155fe38756ec 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -591,6 +591,17 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, unsigned int cpu) { + /* + * Once the clear bit is set, the bit may be allocated out. + * + * Orders READ/WRITE on the asssociated instance(such as request + * of blk_mq) by this bit for avoiding race with re-allocation, + * and its pair is the memory barrier implied in __sbitmap_get_word. + * + * One invariant is that the clear bit has to be zero when the bit + * is in use. + */ + smp_mb__before_atomic(); sbitmap_deferred_clear_bit(&sbq->sb, nr); /* -- cgit v1.2.3-58-ga151 From 9bf7933fc3f306bc4ce74ad734f690a71670178a Mon Sep 17 00:00:00 2001 From: Roman Penyaev Date: Mon, 25 Mar 2019 20:09:24 +0100 Subject: io_uring: offload write to async worker in case of -EAGAIN In case of direct write -EAGAIN will be returned if page cache was previously populated. To avoid immediate completion of a request with -EAGAIN error write has to be offloaded to the async worker, like io_read() does. Signed-off-by: Roman Penyaev Cc: Jens Axboe Cc: linux-block@vger.kernel.org Signed-off-by: Jens Axboe --- fs/io_uring.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 8f48d29abf76..bbdbd56cf2ac 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1022,6 +1022,8 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count); if (!ret) { + ssize_t ret2; + /* * Open-code file_start_write here to grab freeze protection, * which will be released by another thread in @@ -1036,7 +1038,19 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, SB_FREEZE_WRITE); } kiocb->ki_flags |= IOCB_WRITE; - io_rw_done(kiocb, call_write_iter(file, kiocb, &iter)); + + ret2 = call_write_iter(file, kiocb, &iter); + if (!force_nonblock || ret2 != -EAGAIN) { + io_rw_done(kiocb, ret2); + } else { + /* + * If ->needs_lock is true, we're already in async + * context. + */ + if (!s->needs_lock) + io_async_list_note(WRITE, req, iov_count); + ret = -EAGAIN; + } } out_free: kfree(iovec); -- cgit v1.2.3-58-ga151 From dd08a8d9a66de4b54575c294a92630299f7e0fe7 Mon Sep 17 00:00:00 2001 From: raymond pang Date: Thu, 28 Mar 2019 12:19:25 +0000 Subject: libata: fix using DMA buffers on stack When CONFIG_VMAP_STACK=y, __pa() returns incorrect physical address for a stack virtual address. Stack DMA buffers must be avoided. Signed-off-by: raymond pang Signed-off-by: Jens Axboe --- drivers/ata/libata-zpodd.c | 34 ++++++++++++++++++++++++---------- 1 file changed, 24 insertions(+), 10 deletions(-) diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c index b3ed8f9953a8..173e6f2dd9af 100644 --- a/drivers/ata/libata-zpodd.c +++ b/drivers/ata/libata-zpodd.c @@ -52,38 +52,52 @@ static int eject_tray(struct ata_device *dev) /* Per the spec, only slot type and drawer type ODD can be supported */ static enum odd_mech_type zpodd_get_mech_type(struct ata_device *dev) { - char buf[16]; + char *buf; unsigned int ret; - struct rm_feature_desc *desc = (void *)(buf + 8); + struct rm_feature_desc *desc; struct ata_taskfile tf; static const char cdb[] = { GPCMD_GET_CONFIGURATION, 2, /* only 1 feature descriptor requested */ 0, 3, /* 3, removable medium feature */ 0, 0, 0,/* reserved */ - 0, sizeof(buf), + 0, 16, 0, 0, 0, }; + buf = kzalloc(16, GFP_KERNEL); + if (!buf) + return ODD_MECH_TYPE_UNSUPPORTED; + desc = (void *)(buf + 8); + ata_tf_init(dev, &tf); tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf.command = ATA_CMD_PACKET; tf.protocol = ATAPI_PROT_PIO; - tf.lbam = sizeof(buf); + tf.lbam = 16; ret = ata_exec_internal(dev, &tf, cdb, DMA_FROM_DEVICE, - buf, sizeof(buf), 0); - if (ret) + buf, 16, 0); + if (ret) { + kfree(buf); return ODD_MECH_TYPE_UNSUPPORTED; + } - if (be16_to_cpu(desc->feature_code) != 3) + if (be16_to_cpu(desc->feature_code) != 3) { + kfree(buf); return ODD_MECH_TYPE_UNSUPPORTED; + } - if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1) + if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1) { + kfree(buf); return ODD_MECH_TYPE_SLOT; - else if (desc->mech_type == 1 && desc->load == 0 && desc->eject == 1) + } else if (desc->mech_type == 1 && desc->load == 0 && + desc->eject == 1) { + kfree(buf); return ODD_MECH_TYPE_DRAWER; - else + } else { + kfree(buf); return ODD_MECH_TYPE_UNSUPPORTED; + } } /* Test if ODD is zero power ready by sense code */ -- cgit v1.2.3-58-ga151 From 988aef9e8b0dd46b55ad08b1522429739e26122d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Mar 2019 08:41:04 +0100 Subject: nvme-tcp: fix an endianess miss-annotation nvme_tcp_end_request just takes the status value and the converts it to little endian as well as shifting for the phase bit. Fixes: 43ce38a6d823 ("nvme-tcp: support C2HData with SUCCESS flag") Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg --- drivers/nvme/host/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index e7e08889865e..68c49dd67210 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -627,7 +627,7 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb, return ret; } -static inline void nvme_tcp_end_request(struct request *rq, __le16 status) +static inline void nvme_tcp_end_request(struct request *rq, u16 status) { union nvme_result res = {}; -- cgit v1.2.3-58-ga151 From cc2278c413c3a06a93c23ee8722e4dd3d621de12 Mon Sep 17 00:00:00 2001 From: Martin George Date: Wed, 27 Mar 2019 09:52:56 +0100 Subject: nvme-multipath: relax ANA state check When undergoing state transitions I/O might be requeued, hence we should always call nvme_mpath_set_live() to schedule requeue_work whenever the nvme device is live, independent on whether the old state was live or not. Signed-off-by: Martin George Signed-off-by: Gargi Srinivas Signed-off-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/nvme/host/multipath.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 2839bb70badf..f0716f6ce41f 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -404,15 +404,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state) static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc, struct nvme_ns *ns) { - enum nvme_ana_state old; - mutex_lock(&ns->head->lock); - old = ns->ana_state; ns->ana_grpid = le32_to_cpu(desc->grpid); ns->ana_state = desc->state; clear_bit(NVME_NS_ANA_PENDING, &ns->flags); - if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old)) + if (nvme_state_is_live(ns->ana_state)) nvme_mpath_set_live(ns); mutex_unlock(&ns->head->lock); } -- cgit v1.2.3-58-ga151 From 02db99548d3608a625cf481cff2bb7b626829b3f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 27 Mar 2019 17:07:22 +0800 Subject: nvmet: fix building bvec from sg list There are two mistakes for building bvec from sg list for file backed ns: - use request data length to compute number of io vector, this way doesn't consider sg->offset, and the result may be smaller than required io vectors - bvec->bv_len isn't capped by sg->length This patch fixes this issue by building bvec from sg directly, given the whole IO stack is ready for multi-page bvec. Reported-by: Yi Zhang Fixes: 3a85a5de29ea ("nvme-loop: add a NVMe loopback host driver") Signed-off-by: Ming Lei Signed-off-by: Christoph Hellwig --- drivers/nvme/target/io-cmd-file.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 3e43212d3c1c..bc6ebb51b0bf 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -75,11 +75,11 @@ err: return ret; } -static void nvmet_file_init_bvec(struct bio_vec *bv, struct sg_page_iter *iter) +static void nvmet_file_init_bvec(struct bio_vec *bv, struct scatterlist *sg) { - bv->bv_page = sg_page_iter_page(iter); - bv->bv_offset = iter->sg->offset; - bv->bv_len = PAGE_SIZE - iter->sg->offset; + bv->bv_page = sg_page(sg); + bv->bv_offset = sg->offset; + bv->bv_len = sg->length; } static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos, @@ -128,14 +128,14 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2) static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) { - ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE); - struct sg_page_iter sg_pg_iter; + ssize_t nr_bvec = req->sg_cnt; unsigned long bv_cnt = 0; bool is_sync = false; size_t len = 0, total_len = 0; ssize_t ret = 0; loff_t pos; - + int i; + struct scatterlist *sg; if (req->f.mpool_alloc && nr_bvec > NVMET_MAX_MPOOL_BVEC) is_sync = true; @@ -147,8 +147,8 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) } memset(&req->f.iocb, 0, sizeof(struct kiocb)); - for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) { - nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter); + for_each_sg(req->sg, sg, req->sg_cnt, i) { + nvmet_file_init_bvec(&req->f.bvec[bv_cnt], sg); len += req->f.bvec[bv_cnt].bv_len; total_len += req->f.bvec[bv_cnt].bv_len; bv_cnt++; @@ -225,7 +225,7 @@ static void nvmet_file_submit_buffered_io(struct nvmet_req *req) static void nvmet_file_execute_rw(struct nvmet_req *req) { - ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE); + ssize_t nr_bvec = req->sg_cnt; if (!req->sg_cnt || !nr_bvec) { nvmet_req_complete(req, 0); -- cgit v1.2.3-58-ga151 From a536b49785759bf99465fdf6e248d34322123fcd Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 Mar 2019 12:54:03 +0200 Subject: nvmet: fix error flow during ns enable In case we fail to enable p2pmem on the current namespace, disable the backing store device before exiting. Cc: Stephen Bates Signed-off-by: Max Gurtovoy Signed-off-by: Christoph Hellwig --- drivers/nvme/target/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 2d73b66e3686..b3e765a95af8 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -509,7 +509,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns) ret = nvmet_p2pmem_ns_enable(ns); if (ret) - goto out_unlock; + goto out_dev_disable; list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) nvmet_p2pmem_ns_add_p2p(ctrl, ns); @@ -550,7 +550,7 @@ out_unlock: out_dev_put: list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid)); - +out_dev_disable: nvmet_ns_dev_disable(ns); goto out_unlock; } -- cgit v1.2.3-58-ga151