diff options
Diffstat (limited to 'drivers/vhost')
-rw-r--r-- | drivers/vhost/scsi.c | 58 | ||||
-rw-r--r-- | drivers/vhost/vdpa.c | 32 | ||||
-rw-r--r-- | drivers/vhost/vringh.c | 69 |
3 files changed, 79 insertions, 80 deletions
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 5de21ad4bd05..d16c04dcc144 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -85,7 +85,7 @@ struct vhost_scsi_cmd { /* The number of scatterlists associated with this cmd */ u32 tvc_sgl_count; u32 tvc_prot_sgl_count; - /* Saved unpacked SCSI LUN for vhost_scsi_submission_work() */ + /* Saved unpacked SCSI LUN for vhost_scsi_target_queue_cmd() */ u32 tvc_lun; /* Pointer to the SGL formatted memory from virtio-scsi */ struct scatterlist *tvc_sgl; @@ -101,8 +101,6 @@ struct vhost_scsi_cmd { struct vhost_scsi_nexus *tvc_nexus; /* The TCM I/O descriptor that is accessed via container_of() */ struct se_cmd tvc_se_cmd; - /* work item used for cmwq dispatch to vhost_scsi_submission_work() */ - struct work_struct work; /* Copy of the incoming SCSI command descriptor block (CDB) */ unsigned char tvc_cdb[VHOST_SCSI_MAX_CDB_SIZE]; /* Sense buffer that will be mapped into outgoing status */ @@ -240,8 +238,6 @@ struct vhost_scsi_ctx { struct iov_iter out_iter; }; -static struct workqueue_struct *vhost_scsi_workqueue; - /* Global spinlock to protect vhost_scsi TPG list for vhost IOCTL access */ static DEFINE_MUTEX(vhost_scsi_mutex); static LIST_HEAD(vhost_scsi_list); @@ -614,7 +610,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, return ERR_PTR(-EIO); } - tag = sbitmap_get(&svq->scsi_tags, 0, false); + tag = sbitmap_get(&svq->scsi_tags); if (tag < 0) { pr_err("Unable to obtain tag for vhost_scsi_cmd\n"); return ERR_PTR(-ENOMEM); @@ -782,14 +778,11 @@ static int vhost_scsi_to_tcm_attr(int attr) return TCM_SIMPLE_TAG; } -static void vhost_scsi_submission_work(struct work_struct *work) +static void vhost_scsi_target_queue_cmd(struct vhost_scsi_cmd *cmd) { - struct vhost_scsi_cmd *cmd = - container_of(work, struct vhost_scsi_cmd, work); - struct vhost_scsi_nexus *tv_nexus; struct se_cmd *se_cmd = &cmd->tvc_se_cmd; + struct vhost_scsi_nexus *tv_nexus; struct scatterlist *sg_ptr, *sg_prot_ptr = NULL; - int rc; /* FIXME: BIDI operation */ if (cmd->tvc_sgl_count) { @@ -805,18 +798,17 @@ static void vhost_scsi_submission_work(struct work_struct *work) tv_nexus = cmd->tvc_nexus; se_cmd->tag = 0; - rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess, - cmd->tvc_cdb, &cmd->tvc_sense_buf[0], + target_init_cmd(se_cmd, tv_nexus->tvn_se_sess, &cmd->tvc_sense_buf[0], cmd->tvc_lun, cmd->tvc_exp_data_len, vhost_scsi_to_tcm_attr(cmd->tvc_task_attr), - cmd->tvc_data_direction, TARGET_SCF_ACK_KREF, - sg_ptr, cmd->tvc_sgl_count, NULL, 0, sg_prot_ptr, - cmd->tvc_prot_sgl_count); - if (rc < 0) { - transport_send_check_condition_and_sense(se_cmd, - TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0); - transport_generic_free_cmd(se_cmd, 0); - } + cmd->tvc_data_direction, TARGET_SCF_ACK_KREF); + + if (target_submit_prep(se_cmd, cmd->tvc_cdb, sg_ptr, + cmd->tvc_sgl_count, NULL, 0, sg_prot_ptr, + cmd->tvc_prot_sgl_count, GFP_KERNEL)) + return; + + target_queue_submission(se_cmd); } static void @@ -1132,14 +1124,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) * vhost_scsi_queue_data_in() and vhost_scsi_queue_status() */ cmd->tvc_vq_desc = vc.head; - /* - * Dispatch cmd descriptor for cmwq execution in process - * context provided by vhost_scsi_workqueue. This also ensures - * cmd is executed on the same kworker CPU as this vhost - * thread to gain positive L2 cache locality effects. - */ - INIT_WORK(&cmd->work, vhost_scsi_submission_work); - queue_work(vhost_scsi_workqueue, &cmd->work); + vhost_scsi_target_queue_cmd(cmd); ret = 0; err: /* @@ -1512,7 +1497,7 @@ static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) return 0; if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL, - NUMA_NO_NODE)) + NUMA_NO_NODE, false, true)) return -ENOMEM; svq->max_cmds = max_cmds; @@ -2486,17 +2471,9 @@ static int __init vhost_scsi_init(void) " on "UTS_RELEASE"\n", VHOST_SCSI_VERSION, utsname()->sysname, utsname()->machine); - /* - * Use our own dedicated workqueue for submitting I/O into - * target core to avoid contention within system_wq. - */ - vhost_scsi_workqueue = alloc_workqueue("vhost_scsi", 0, 0); - if (!vhost_scsi_workqueue) - goto out; - ret = vhost_scsi_register(); if (ret < 0) - goto out_destroy_workqueue; + goto out; ret = target_register_template(&vhost_scsi_ops); if (ret < 0) @@ -2506,8 +2483,6 @@ static int __init vhost_scsi_init(void) out_vhost_scsi_deregister: vhost_scsi_deregister(); -out_destroy_workqueue: - destroy_workqueue(vhost_scsi_workqueue); out: return ret; }; @@ -2516,7 +2491,6 @@ static void vhost_scsi_exit(void) { target_unregister_template(&vhost_scsi_ops); vhost_scsi_deregister(); - destroy_workqueue(vhost_scsi_workqueue); }; MODULE_DESCRIPTION("VHOST_SCSI series fabric driver"); diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index e0a27e336293..fb41db3da611 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -16,12 +16,12 @@ #include <linux/cdev.h> #include <linux/device.h> #include <linux/mm.h> +#include <linux/slab.h> #include <linux/iommu.h> #include <linux/uuid.h> #include <linux/vdpa.h> #include <linux/nospec.h> #include <linux/vhost.h> -#include <linux/virtio_net.h> #include "vhost.h" @@ -188,13 +188,8 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) static int vhost_vdpa_config_validate(struct vhost_vdpa *v, struct vhost_vdpa_config *c) { - long size = 0; - - switch (v->virtio_id) { - case VIRTIO_ID_NET: - size = sizeof(struct virtio_net_config); - break; - } + struct vdpa_device *vdpa = v->vdpa; + long size = vdpa->config->get_config_size(vdpa); if (c->len == 0) return -EINVAL; @@ -745,9 +740,11 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, const struct vdpa_config_ops *ops = vdpa->config; int r = 0; + mutex_lock(&dev->mutex); + r = vhost_dev_check_owner(dev); if (r) - return r; + goto unlock; switch (msg->type) { case VHOST_IOTLB_UPDATE: @@ -768,6 +765,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, r = -EINVAL; break; } +unlock: + mutex_unlock(&dev->mutex); return r; } @@ -832,18 +831,14 @@ static void vhost_vdpa_free_domain(struct vhost_vdpa *v) static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v) { struct vdpa_iova_range *range = &v->range; - struct iommu_domain_geometry geo; struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; if (ops->get_iova_range) { *range = ops->get_iova_range(vdpa); - } else if (v->domain && - !iommu_domain_get_attr(v->domain, - DOMAIN_ATTR_GEOMETRY, &geo) && - geo.force_aperture) { - range->first = geo.aperture_start; - range->last = geo.aperture_end; + } else if (v->domain && v->domain->geometry.force_aperture) { + range->first = v->domain->geometry.aperture_start; + range->last = v->domain->geometry.aperture_end; } else { range->first = 0; range->last = ULLONG_MAX; @@ -989,6 +984,7 @@ static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma) if (vma->vm_end - vma->vm_start != notify.size) return -ENOTSUPP; + vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_ops = &vhost_vdpa_vm_ops; return 0; } @@ -1023,10 +1019,6 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) int minor; int r; - /* Currently, we only accept the network devices. */ - if (ops->get_device_id(vdpa) != VIRTIO_ID_NET) - return -ENOTSUPP; - v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!v) return -ENOMEM; diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 85d85faba058..4af8fa259d65 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -75,6 +75,34 @@ static inline int __vringh_get_head(const struct vringh *vrh, return head; } +/** + * vringh_kiov_advance - skip bytes from vring_kiov + * @iov: an iov passed to vringh_getdesc_*() (updated as we consume) + * @len: the maximum length to advance + */ +void vringh_kiov_advance(struct vringh_kiov *iov, size_t len) +{ + while (len && iov->i < iov->used) { + size_t partlen = min(iov->iov[iov->i].iov_len, len); + + iov->consumed += partlen; + iov->iov[iov->i].iov_len -= partlen; + iov->iov[iov->i].iov_base += partlen; + + if (!iov->iov[iov->i].iov_len) { + /* Fix up old iov element then increment. */ + iov->iov[iov->i].iov_len = iov->consumed; + iov->iov[iov->i].iov_base -= iov->consumed; + + iov->consumed = 0; + iov->i++; + } + + len -= partlen; + } +} +EXPORT_SYMBOL(vringh_kiov_advance); + /* Copy some bytes to/from the iovec. Returns num copied. */ static inline ssize_t vringh_iov_xfer(struct vringh *vrh, struct vringh_kiov *iov, @@ -95,19 +123,8 @@ static inline ssize_t vringh_iov_xfer(struct vringh *vrh, done += partlen; len -= partlen; ptr += partlen; - iov->consumed += partlen; - iov->iov[iov->i].iov_len -= partlen; - iov->iov[iov->i].iov_base += partlen; - if (!iov->iov[iov->i].iov_len) { - /* Fix up old iov element then increment. */ - iov->iov[iov->i].iov_len = iov->consumed; - iov->iov[iov->i].iov_base -= iov->consumed; - - - iov->consumed = 0; - iov->i++; - } + vringh_kiov_advance(iov, partlen); } return done; } @@ -290,9 +307,9 @@ __vringh_iov(struct vringh *vrh, u16 i, return -EINVAL; if (riov) - riov->i = riov->used = 0; + riov->i = riov->used = riov->consumed = 0; if (wiov) - wiov->i = wiov->used = 0; + wiov->i = wiov->used = wiov->consumed = 0; for (;;) { void *addr; @@ -662,7 +679,10 @@ EXPORT_SYMBOL(vringh_init_user); * *head will be vrh->vring.num. You may be able to ignore an invalid * descriptor, but there's not much you can do with an invalid ring. * - * Note that you may need to clean up riov and wiov, even on error! + * Note that you can reuse riov and wiov with subsequent calls. Content is + * overwritten and memory reallocated if more space is needed. + * When you don't have to use riov and wiov anymore, you should clean up them + * calling vringh_iov_cleanup() to release the memory, even on error! */ int vringh_getdesc_user(struct vringh *vrh, struct vringh_iov *riov, @@ -932,7 +952,10 @@ EXPORT_SYMBOL(vringh_init_kern); * *head will be vrh->vring.num. You may be able to ignore an invalid * descriptor, but there's not much you can do with an invalid ring. * - * Note that you may need to clean up riov and wiov, even on error! + * Note that you can reuse riov and wiov with subsequent calls. Content is + * overwritten and memory reallocated if more space is needed. + * When you don't have to use riov and wiov anymore, you should clean up them + * calling vringh_kiov_cleanup() to release the memory, even on error! */ int vringh_getdesc_kern(struct vringh *vrh, struct vringh_kiov *riov, @@ -1074,6 +1097,8 @@ static int iotlb_translate(const struct vringh *vrh, int ret = 0; u64 s = 0; + spin_lock(vrh->iotlb_lock); + while (len > s) { u64 size, pa, pfn; @@ -1103,6 +1128,8 @@ static int iotlb_translate(const struct vringh *vrh, ++ret; } + spin_unlock(vrh->iotlb_lock); + return ret; } @@ -1262,10 +1289,13 @@ EXPORT_SYMBOL(vringh_init_iotlb); * vringh_set_iotlb - initialize a vringh for a ring with IOTLB. * @vrh: the vring * @iotlb: iotlb associated with this vring + * @iotlb_lock: spinlock to synchronize the iotlb accesses */ -void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb) +void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb, + spinlock_t *iotlb_lock) { vrh->iotlb = iotlb; + vrh->iotlb_lock = iotlb_lock; } EXPORT_SYMBOL(vringh_set_iotlb); @@ -1285,7 +1315,10 @@ EXPORT_SYMBOL(vringh_set_iotlb); * *head will be vrh->vring.num. You may be able to ignore an invalid * descriptor, but there's not much you can do with an invalid ring. * - * Note that you may need to clean up riov and wiov, even on error! + * Note that you can reuse riov and wiov with subsequent calls. Content is + * overwritten and memory reallocated if more space is needed. + * When you don't have to use riov and wiov anymore, you should clean up them + * calling vringh_kiov_cleanup() to release the memory, even on error! */ int vringh_getdesc_iotlb(struct vringh *vrh, struct vringh_kiov *riov, |