Merge tag 'for-linus-20190412' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Set of fixes that should go into this round. This pull is larger than
  I'd like at this time, but there's really no specific reason for that.
  Some are fixes for issues that went into this merge window, others are
  not. Anyway, this contains:

   - Hardware queue limiting for virtio-blk/scsi (Dongli)

   - Multi-page bvec fixes for lightnvm pblk

   - Multi-bio dio error fix (Jason)

   - Remove the cache hint from the io_uring tool side, since we didn't
     move forward with that (me)

   - Make io_uring SETUP_SQPOLL root restricted (me)

   - Fix leak of page in error handling for pc requests (Jérôme)

   - Fix BFQ regression introduced in this merge window (Paolo)

   - Fix break logic for bio segment iteration (Ming)

   - Fix NVMe cancel request error handling (Ming)

   - NVMe pull request with two fixes (Christoph):
       - fix the initial CSN for nvme-fc (James)
       - handle log page offsets properly in the target (Keith)"

* tag 'for-linus-20190412' of git://git.kernel.dk/linux-block:
  block: fix the return errno for direct IO
  nvmet: fix discover log page when offsets are used
  nvme-fc: correct csn initialization and increments on error
  block: do not leak memory in bio_copy_user_iov()
  lightnvm: pblk: fix crash in pblk_end_partial_read due to multipage bvecs
  nvme: cancel request synchronously
  blk-mq: introduce blk_mq_complete_request_sync()
  scsi: virtio_scsi: limit number of hw queues by nr_cpu_ids
  virtio-blk: limit number of hw queues by nr_cpu_ids
  block, bfq: fix use after free in bfq_bfqq_expire
  io_uring: restrict IORING_SETUP_SQPOLL to root
  tools/io_uring: remove IOCQE_FLAG_CACHEHIT
  block: don't use for-inside-for in bio_for_each_segment_all

8 files changed, 98 insertions, 51 deletions

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 4bc083b7c9b5..2a7ca4a1e6f7 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -513,6 +513,8 @@ static int init_vq(struct virtio_blk *vblk)
         if (err)
                 num_vqs = 1;
 
+        num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs);
+
         vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
         if (!vblk->vqs)
                 return -ENOMEM;
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 3789185144da..0b7d5fb4548d 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -231,14 +231,14 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
         struct pblk_sec_meta *meta;
         struct bio *new_bio = rqd->bio;
         struct bio *bio = pr_ctx->orig_bio;
-        struct bio_vec src_bv, dst_bv;
         void *meta_list = rqd->meta_list;
-        int bio_init_idx = pr_ctx->bio_init_idx;
         unsigned long *read_bitmap = pr_ctx->bitmap;
+        struct bvec_iter orig_iter = BVEC_ITER_ALL_INIT;
+        struct bvec_iter new_iter = BVEC_ITER_ALL_INIT;
         int nr_secs = pr_ctx->orig_nr_secs;
         int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
         void *src_p, *dst_p;
-        int hole, i;
+        int bit, i;
 
         if (unlikely(nr_holes == 1)) {
                 struct ppa_addr ppa;
@@ -257,33 +257,39 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
 
         /* Fill the holes in the original bio */
         i = 0;
-        hole = find_first_zero_bit(read_bitmap, nr_secs);
-        do {
-                struct pblk_line *line;
+        for (bit = 0; bit < nr_secs; bit++) {
+                if (!test_bit(bit, read_bitmap)) {
+                        struct bio_vec dst_bv, src_bv;
+                        struct pblk_line *line;
 
-                line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]);
-                kref_put(&line->ref, pblk_line_put);
+                        line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]);
+                        kref_put(&line->ref, pblk_line_put);
 
-                meta = pblk_get_meta(pblk, meta_list, hole);
-                meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]);
+                        meta = pblk_get_meta(pblk, meta_list, bit);
+                        meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]);
 
-                src_bv = new_bio->bi_io_vec[i++];
-                dst_bv = bio->bi_io_vec[bio_init_idx + hole];
+                        dst_bv = bio_iter_iovec(bio, orig_iter);
+                        src_bv = bio_iter_iovec(new_bio, new_iter);
 
-                src_p = kmap_atomic(src_bv.bv_page);
-                dst_p = kmap_atomic(dst_bv.bv_page);
+                        src_p = kmap_atomic(src_bv.bv_page);
+                        dst_p = kmap_atomic(dst_bv.bv_page);
 
-                memcpy(dst_p + dst_bv.bv_offset,
-                        src_p + src_bv.bv_offset,
-                        PBLK_EXPOSED_PAGE_SIZE);
+                        memcpy(dst_p + dst_bv.bv_offset,
+                                src_p + src_bv.bv_offset,
+                                PBLK_EXPOSED_PAGE_SIZE);
 
-                kunmap_atomic(src_p);
-                kunmap_atomic(dst_p);
+                        kunmap_atomic(src_p);
+                        kunmap_atomic(dst_p);
 
-                mempool_free(src_bv.bv_page, &pblk->page_bio_pool);
+                        flush_dcache_page(dst_bv.bv_page);
+                        mempool_free(src_bv.bv_page, &pblk->page_bio_pool);
 
-                hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1);
-        } while (hole < nr_secs);
+                        bio_advance_iter(new_bio, &new_iter,
+                                        PBLK_EXPOSED_PAGE_SIZE);
+                        i++;
+                }
+                bio_advance_iter(bio, &orig_iter, PBLK_EXPOSED_PAGE_SIZE);
+        }
 
         bio_put(new_bio);
         kfree(pr_ctx);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 470601980794..2c43e12b70af 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -288,7 +288,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
                                 "Cancelling I/O %d", req->tag);
 
         nvme_req(req)->status = NVME_SC_ABORT_REQ;
-        blk_mq_complete_request(req);
+        blk_mq_complete_request_sync(req);
         return true;
 }
 EXPORT_SYMBOL_GPL(nvme_cancel_request);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index f3b9d91ba0df..6d8451356eac 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1845,7 +1845,7 @@ nvme_fc_init_queue(struct nvme_fc_ctrl *ctrl, int idx)
         memset(queue, 0, sizeof(*queue));
         queue->ctrl = ctrl;
         queue->qnum = idx;
-        atomic_set(&queue->csn, 1);
+        atomic_set(&queue->csn, 0);
         queue->dev = ctrl->dev;
 
         if (idx > 0)
@@ -1887,7 +1887,7 @@ nvme_fc_free_queue(struct nvme_fc_queue *queue)
          */
 
         queue->connection_id = 0;
-        atomic_set(&queue->csn, 1);
+        atomic_set(&queue->csn, 0);
 }
 
 static void
@@ -2183,7 +2183,6 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 {
         struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
         struct nvme_command *sqe = &cmdiu->sqe;
-        u32 csn;
         int ret, opstate;
 
         /*
@@ -2198,8 +2197,6 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 
         /* format the FC-NVME CMD IU and fcp_req */
         cmdiu->connection_id = cpu_to_be64(queue->connection_id);
-        csn = atomic_inc_return(&queue->csn);
-        cmdiu->csn = cpu_to_be32(csn);
         cmdiu->data_len = cpu_to_be32(data_len);
         switch (io_dir) {
         case NVMEFC_FCP_WRITE:
@@ -2257,11 +2254,24 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
         if (!(op->flags & FCOP_FLAGS_AEN))
                 blk_mq_start_request(op->rq);
 
+        cmdiu->csn = cpu_to_be32(atomic_inc_return(&queue->csn));
         ret = ctrl->lport->ops->fcp_io(&ctrl->lport->localport,
                                         &ctrl->rport->remoteport,
                                         queue->lldd_handle, &op->fcp_req);
 
         if (ret) {
+                /*
+                 * If the lld fails to send the command is there an issue with
+                 * the csn value?  If the command that fails is the Connect,
+                 * no - as the connection won't be live.  If it is a command
+                 * post-connect, it's possible a gap in csn may be created.
+                 * Does this matter?  As Linux initiators don't send fused
+                 * commands, no.  The gap would exist, but as there's nothing
+                 * that depends on csn order to be delivered on the target
+                 * side, it shouldn't hurt.  It would be difficult for a
+                 * target to even detect the csn gap as it has no idea when the
+                 * cmd with the csn was supposed to arrive.
+                 */
                 opstate = atomic_xchg(&op->state, FCPOP_STATE_COMPLETE);
                 __nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
 
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 76250181fee0..9f72d515fc4b 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -24,6 +24,11 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd)
         return len;
 }
 
+u64 nvmet_get_log_page_offset(struct nvme_command *cmd)
+{
+        return le64_to_cpu(cmd->get_log_page.lpo);
+}
+
 static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
 {
         nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len));
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index c872b47a88f3..33ed95e72d6b 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -131,54 +131,76 @@ static void nvmet_set_disc_traddr(struct nvmet_req *req, struct nvmet_port *port
                 memcpy(traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE);
 }
 
+static size_t discovery_log_entries(struct nvmet_req *req)
+{
+        struct nvmet_ctrl *ctrl = req->sq->ctrl;
+        struct nvmet_subsys_link *p;
+        struct nvmet_port *r;
+        size_t entries = 0;
+
+        list_for_each_entry(p, &req->port->subsystems, entry) {
+                if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
+                        continue;
+                entries++;
+        }
+        list_for_each_entry(r, &req->port->referrals, entry)
+                entries++;
+        return entries;
+}
+
 static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
 {
         const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry);
         struct nvmet_ctrl *ctrl = req->sq->ctrl;
         struct nvmf_disc_rsp_page_hdr *hdr;
+        u64 offset = nvmet_get_log_page_offset(req->cmd);
         size_t data_len = nvmet_get_log_page_len(req->cmd);
-        size_t alloc_len = max(data_len, sizeof(*hdr));
-        int residual_len = data_len - sizeof(*hdr);
+        size_t alloc_len;
         struct nvmet_subsys_link *p;
         struct nvmet_port *r;
         u32 numrec = 0;
         u16 status = 0;
+        void *buffer;
+
+        /* Spec requires dword aligned offsets */
+        if (offset & 0x3) {
+                status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+                goto out;
+        }
 
         /*
          * Make sure we're passing at least a buffer of response header size.
          * If host provided data len is less than the header size, only the
          * number of bytes requested by host will be sent to host.
          */
-        hdr = kzalloc(alloc_len, GFP_KERNEL);
-        if (!hdr) {
+        down_read(&nvmet_config_sem);
+        alloc_len = sizeof(*hdr) + entry_size * discovery_log_entries(req);
+        buffer = kzalloc(alloc_len, GFP_KERNEL);
+        if (!buffer) {
+                up_read(&nvmet_config_sem);
                 status = NVME_SC_INTERNAL;
                 goto out;
         }
 
-        down_read(&nvmet_config_sem);
+        hdr = buffer;
         list_for_each_entry(p, &req->port->subsystems, entry) {
+                char traddr[NVMF_TRADDR_SIZE];
+
                 if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
                         continue;
-                if (residual_len >= entry_size) {
-                        char traddr[NVMF_TRADDR_SIZE];
-
-                        nvmet_set_disc_traddr(req, req->port, traddr);
-                        nvmet_format_discovery_entry(hdr, req->port,
-                                        p->subsys->subsysnqn, traddr,
-                                        NVME_NQN_NVME, numrec);
-                        residual_len -= entry_size;
-                }
+
+                nvmet_set_disc_traddr(req, req->port, traddr);
+                nvmet_format_discovery_entry(hdr, req->port,
+                                p->subsys->subsysnqn, traddr,
+                                NVME_NQN_NVME, numrec);
                 numrec++;
         }
 
         list_for_each_entry(r, &req->port->referrals, entry) {
-                if (residual_len >= entry_size) {
-                        nvmet_format_discovery_entry(hdr, r,
-                                        NVME_DISC_SUBSYS_NAME,
-                                        r->disc_addr.traddr,
-                                        NVME_NQN_DISC, numrec);
-                        residual_len -= entry_size;
-                }
+                nvmet_format_discovery_entry(hdr, r,
+                                NVME_DISC_SUBSYS_NAME,
+                                r->disc_addr.traddr,
+                                NVME_NQN_DISC, numrec);
                 numrec++;
         }
 
@@ -190,8 +212,8 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
 
         up_read(&nvmet_config_sem);
 
-        status = nvmet_copy_to_sgl(req, 0, hdr, data_len);
-        kfree(hdr);
+        status = nvmet_copy_to_sgl(req, 0, buffer + offset, data_len);
+        kfree(buffer);
 out:
         nvmet_req_complete(req, status);
 }
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 51e49efd7849..1653d19b187f 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -428,6 +428,7 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf,
 u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len);
 
 u32 nvmet_get_log_page_len(struct nvme_command *cmd);
+u64 nvmet_get_log_page_offset(struct nvme_command *cmd);
 
 extern struct list_head *nvmet_ports;
 void nvmet_port_disc_changed(struct nvmet_port *port,
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 8af01777d09c..f8cb7c23305b 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -793,6 +793,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
 
         /* We need to know how many queues before we allocate. */
         num_queues = virtscsi_config_get(vdev, num_queues) ? : 1;
+        num_queues = min_t(unsigned int, nr_cpu_ids, num_queues);
 
         num_targets = virtscsi_config_get(vdev, max_target) + 1;