From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/drivers/vhost/scsi.c | 852 +++++++++++++++++++++++++++++++++++++++++---------------
1 files changed, 615 insertions(+), 237 deletions(-)
diff --git a/kernel/drivers/vhost/scsi.c b/kernel/drivers/vhost/scsi.c
index 5e298d9..4ce9f00 100644
--- a/kernel/drivers/vhost/scsi.c
+++ b/kernel/drivers/vhost/scsi.c
@@ -52,7 +52,6 @@
#define VHOST_SCSI_VERSION "v0.1"
#define VHOST_SCSI_NAMELEN 256
#define VHOST_SCSI_MAX_CDB_SIZE 32
-#define VHOST_SCSI_DEFAULT_TAGS 256
#define VHOST_SCSI_PREALLOC_SGLS 2048
#define VHOST_SCSI_PREALLOC_UPAGES 2048
#define VHOST_SCSI_PREALLOC_PROT_SGLS 2048
@@ -140,6 +139,7 @@
struct se_portal_group se_tpg;
/* Pointer back to vhost_scsi, protected by tv_tpg_mutex */
struct vhost_scsi *vhost_scsi;
+ struct list_head tmf_queue;
};
struct vhost_scsi_tport {
@@ -189,6 +189,9 @@
* Writers must also take dev mutex and flush under it.
*/
int inflight_idx;
+ struct vhost_scsi_cmd *scsi_cmds;
+ struct sbitmap scsi_tags;
+ int max_cmds;
};
struct vhost_scsi {
@@ -207,6 +210,34 @@
bool vs_events_missed; /* any missed events, protected by vq->mutex */
int vs_events_nr; /* num of pending events, protected by vq->mutex */
+};
+
+struct vhost_scsi_tmf {
+ struct vhost_work vwork;
+ struct vhost_scsi_tpg *tpg;
+ struct vhost_scsi *vhost;
+ struct vhost_scsi_virtqueue *svq;
+ struct list_head queue_entry;
+
+ struct se_cmd se_cmd;
+ u8 scsi_resp;
+ struct vhost_scsi_inflight *inflight;
+ struct iovec resp_iov;
+ int in_iovs;
+ int vq_desc;
+};
+
+/*
+ * Context for processing request and control queue operations.
+ */
+struct vhost_scsi_ctx {
+ int head;
+ unsigned int out, in;
+ size_t req_size, rsp_size;
+ size_t out_size, in_size;
+ u8 *target, *lunp;
+ void *req;
+ struct iov_iter out_iter;
};
static struct workqueue_struct *vhost_scsi_workqueue;
@@ -278,11 +309,6 @@
return 0;
}
-static char *vhost_scsi_get_fabric_name(void)
-{
- return "vhost";
-}
-
static char *vhost_scsi_get_fabric_wwn(struct se_portal_group *se_tpg)
{
struct vhost_scsi_tpg *tpg = container_of(se_tpg,
@@ -312,11 +338,13 @@
return 1;
}
-static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd)
{
struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd,
struct vhost_scsi_cmd, tvc_se_cmd);
- struct se_session *se_sess = tv_cmd->tvc_nexus->tvn_se_sess;
+ struct vhost_scsi_virtqueue *svq = container_of(tv_cmd->tvc_vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_inflight *inflight = tv_cmd->inflight;
int i;
if (tv_cmd->tvc_sgl_count) {
@@ -328,8 +356,36 @@
put_page(sg_page(&tv_cmd->tvc_prot_sgl[i]));
}
- vhost_scsi_put_inflight(tv_cmd->inflight);
- target_free_tag(se_sess, se_cmd);
+ sbitmap_clear_bit(&svq->scsi_tags, se_cmd->map_tag);
+ vhost_scsi_put_inflight(inflight);
+}
+
+static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf)
+{
+ struct vhost_scsi_tpg *tpg = tmf->tpg;
+ struct vhost_scsi_inflight *inflight = tmf->inflight;
+
+ mutex_lock(&tpg->tv_tpg_mutex);
+ list_add_tail(&tpg->tmf_queue, &tmf->queue_entry);
+ mutex_unlock(&tpg->tv_tpg_mutex);
+ vhost_scsi_put_inflight(inflight);
+}
+
+static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+{
+ if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) {
+ struct vhost_scsi_tmf *tmf = container_of(se_cmd,
+ struct vhost_scsi_tmf, se_cmd);
+
+ vhost_work_queue(&tmf->vhost->dev, &tmf->vwork);
+ } else {
+ struct vhost_scsi_cmd *cmd = container_of(se_cmd,
+ struct vhost_scsi_cmd, tvc_se_cmd);
+ struct vhost_scsi *vs = cmd->tvc_vhost;
+
+ llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
+ vhost_work_queue(&vs->dev, &vs->vs_completion_work);
+ }
}
static u32 vhost_scsi_sess_get_index(struct se_session *se_sess)
@@ -344,11 +400,6 @@
return 0;
}
-static int vhost_scsi_write_pending_status(struct se_cmd *se_cmd)
-{
- return 0;
-}
-
static void vhost_scsi_set_default_node_attrs(struct se_node_acl *nacl)
{
return;
@@ -359,34 +410,25 @@
return 0;
}
-static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd)
-{
- struct vhost_scsi *vs = cmd->tvc_vhost;
-
- llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
-
- vhost_work_queue(&vs->dev, &vs->vs_completion_work);
-}
-
static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd)
{
- struct vhost_scsi_cmd *cmd = container_of(se_cmd,
- struct vhost_scsi_cmd, tvc_se_cmd);
- vhost_scsi_complete_cmd(cmd);
+ transport_generic_free_cmd(se_cmd, 0);
return 0;
}
static int vhost_scsi_queue_status(struct se_cmd *se_cmd)
{
- struct vhost_scsi_cmd *cmd = container_of(se_cmd,
- struct vhost_scsi_cmd, tvc_se_cmd);
- vhost_scsi_complete_cmd(cmd);
+ transport_generic_free_cmd(se_cmd, 0);
return 0;
}
static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd)
{
- return;
+ struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf,
+ se_cmd);
+
+ tmf->scsi_resp = se_cmd->se_tmr_req->response;
+ transport_generic_free_cmd(&tmf->se_cmd, 0);
}
static void vhost_scsi_aborted_task(struct se_cmd *se_cmd)
@@ -426,15 +468,6 @@
return evt;
}
-static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd)
-{
- struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
-
- /* TODO locking against target/backend threads? */
- transport_generic_free_cmd(se_cmd, 0);
-
-}
-
static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd)
{
return target_put_sess_cmd(se_cmd);
@@ -449,7 +482,7 @@
unsigned out, in;
int head, ret;
- if (!vq->private_data) {
+ if (!vhost_vq_get_backend(vq)) {
vs->vs_events_missed = true;
return;
}
@@ -553,7 +586,7 @@
} else
pr_err("Faulted on virtio_scsi_cmd_resp\n");
- vhost_scsi_free_cmd(cmd);
+ vhost_scsi_release_cmd_res(se_cmd);
}
vq = -1;
@@ -563,31 +596,31 @@
}
static struct vhost_scsi_cmd *
-vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
+vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr,
u32 exp_data_len, int data_direction)
{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
struct vhost_scsi_cmd *cmd;
struct vhost_scsi_nexus *tv_nexus;
- struct se_session *se_sess;
struct scatterlist *sg, *prot_sg;
struct page **pages;
- int tag, cpu;
+ int tag;
tv_nexus = tpg->tpg_nexus;
if (!tv_nexus) {
pr_err("Unable to locate active struct vhost_scsi_nexus\n");
return ERR_PTR(-EIO);
}
- se_sess = tv_nexus->tvn_se_sess;
- tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
+ tag = sbitmap_get(&svq->scsi_tags, 0, false);
if (tag < 0) {
pr_err("Unable to obtain tag for vhost_scsi_cmd\n");
return ERR_PTR(-ENOMEM);
}
- cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[tag];
+ cmd = &svq->scsi_cmds[tag];
sg = cmd->tvc_sgl;
prot_sg = cmd->tvc_prot_sgl;
pages = cmd->tvc_upages;
@@ -596,7 +629,6 @@
cmd->tvc_prot_sgl = prot_sg;
cmd->tvc_upages = pages;
cmd->tvc_se_cmd.map_tag = tag;
- cmd->tvc_se_cmd.map_cpu = cpu;
cmd->tvc_tag = scsi_tag;
cmd->tvc_lun = lun;
cmd->tvc_task_attr = task_attr;
@@ -806,113 +838,176 @@
pr_err("Faulted on virtio_scsi_cmd_resp\n");
}
+static int
+vhost_scsi_get_desc(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
+ struct vhost_scsi_ctx *vc)
+{
+ int ret = -ENXIO;
+
+ vc->head = vhost_get_vq_desc(vq, vq->iov,
+ ARRAY_SIZE(vq->iov), &vc->out, &vc->in,
+ NULL, NULL);
+
+ pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n",
+ vc->head, vc->out, vc->in);
+
+ /* On error, stop handling until the next kick. */
+ if (unlikely(vc->head < 0))
+ goto done;
+
+ /* Nothing new? Wait for eventfd to tell us they refilled. */
+ if (vc->head == vq->num) {
+ if (unlikely(vhost_enable_notify(&vs->dev, vq))) {
+ vhost_disable_notify(&vs->dev, vq);
+ ret = -EAGAIN;
+ }
+ goto done;
+ }
+
+ /*
+ * Get the size of request and response buffers.
+ * FIXME: Not correct for BIDI operation
+ */
+ vc->out_size = iov_length(vq->iov, vc->out);
+ vc->in_size = iov_length(&vq->iov[vc->out], vc->in);
+
+ /*
+ * Copy over the virtio-scsi request header, which for a
+ * ANY_LAYOUT enabled guest may span multiple iovecs, or a
+ * single iovec may contain both the header + outgoing
+ * WRITE payloads.
+ *
+ * copy_from_iter() will advance out_iter, so that it will
+ * point at the start of the outgoing WRITE payload, if
+ * DMA_TO_DEVICE is set.
+ */
+ iov_iter_init(&vc->out_iter, WRITE, vq->iov, vc->out, vc->out_size);
+ ret = 0;
+
+done:
+ return ret;
+}
+
+static int
+vhost_scsi_chk_size(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc)
+{
+ if (unlikely(vc->in_size < vc->rsp_size)) {
+ vq_err(vq,
+ "Response buf too small, need min %zu bytes got %zu",
+ vc->rsp_size, vc->in_size);
+ return -EINVAL;
+ } else if (unlikely(vc->out_size < vc->req_size)) {
+ vq_err(vq,
+ "Request buf too small, need min %zu bytes got %zu",
+ vc->req_size, vc->out_size);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static int
+vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc,
+ struct vhost_scsi_tpg **tpgp)
+{
+ int ret = -EIO;
+
+ if (unlikely(!copy_from_iter_full(vc->req, vc->req_size,
+ &vc->out_iter))) {
+ vq_err(vq, "Faulted on copy_from_iter_full\n");
+ } else if (unlikely(*vc->lunp != 1)) {
+ /* virtio-scsi spec requires byte 0 of the lun to be 1 */
+ vq_err(vq, "Illegal virtio-scsi lun: %u\n", *vc->lunp);
+ } else {
+ struct vhost_scsi_tpg **vs_tpg, *tpg;
+
+ vs_tpg = vhost_vq_get_backend(vq); /* validated at handler entry */
+
+ tpg = READ_ONCE(vs_tpg[*vc->target]);
+ if (unlikely(!tpg)) {
+ vq_err(vq, "Target 0x%x does not exist\n", *vc->target);
+ } else {
+ if (tpgp)
+ *tpgp = tpg;
+ ret = 0;
+ }
+ }
+
+ return ret;
+}
+
+static u16 vhost_buf_to_lun(u8 *lun_buf)
+{
+ return ((lun_buf[2] << 8) | lun_buf[3]) & 0x3FFF;
+}
+
static void
vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
{
struct vhost_scsi_tpg **vs_tpg, *tpg;
struct virtio_scsi_cmd_req v_req;
struct virtio_scsi_cmd_req_pi v_req_pi;
+ struct vhost_scsi_ctx vc;
struct vhost_scsi_cmd *cmd;
- struct iov_iter out_iter, in_iter, prot_iter, data_iter;
+ struct iov_iter in_iter, prot_iter, data_iter;
u64 tag;
u32 exp_data_len, data_direction;
- unsigned int out = 0, in = 0;
- int head, ret, prot_bytes, c = 0;
- size_t req_size, rsp_size = sizeof(struct virtio_scsi_cmd_resp);
- size_t out_size, in_size;
+ int ret, prot_bytes, c = 0;
u16 lun;
- u8 *target, *lunp, task_attr;
+ u8 task_attr;
bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI);
- void *req, *cdb;
+ void *cdb;
mutex_lock(&vq->mutex);
/*
* We can handle the vq only after the endpoint is setup by calling the
* VHOST_SCSI_SET_ENDPOINT ioctl.
*/
- vs_tpg = vq->private_data;
+ vs_tpg = vhost_vq_get_backend(vq);
if (!vs_tpg)
goto out;
+
+ memset(&vc, 0, sizeof(vc));
+ vc.rsp_size = sizeof(struct virtio_scsi_cmd_resp);
vhost_disable_notify(&vs->dev, vq);
do {
- head = vhost_get_vq_desc(vq, vq->iov,
- ARRAY_SIZE(vq->iov), &out, &in,
- NULL, NULL);
- pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n",
- head, out, in);
- /* On error, stop handling until the next kick. */
- if (unlikely(head < 0))
- break;
- /* Nothing new? Wait for eventfd to tell us they refilled. */
- if (head == vq->num) {
- if (unlikely(vhost_enable_notify(&vs->dev, vq))) {
- vhost_disable_notify(&vs->dev, vq);
- continue;
- }
- break;
- }
- /*
- * Check for a sane response buffer so we can report early
- * errors back to the guest.
- */
- if (unlikely(vq->iov[out].iov_len < rsp_size)) {
- vq_err(vq, "Expecting at least virtio_scsi_cmd_resp"
- " size, got %zu bytes\n", vq->iov[out].iov_len);
- break;
- }
+ ret = vhost_scsi_get_desc(vs, vq, &vc);
+ if (ret)
+ goto err;
+
/*
* Setup pointers and values based upon different virtio-scsi
* request header if T10_PI is enabled in KVM guest.
*/
if (t10_pi) {
- req = &v_req_pi;
- req_size = sizeof(v_req_pi);
- lunp = &v_req_pi.lun[0];
- target = &v_req_pi.lun[1];
+ vc.req = &v_req_pi;
+ vc.req_size = sizeof(v_req_pi);
+ vc.lunp = &v_req_pi.lun[0];
+ vc.target = &v_req_pi.lun[1];
} else {
- req = &v_req;
- req_size = sizeof(v_req);
- lunp = &v_req.lun[0];
- target = &v_req.lun[1];
+ vc.req = &v_req;
+ vc.req_size = sizeof(v_req);
+ vc.lunp = &v_req.lun[0];
+ vc.target = &v_req.lun[1];
}
- /*
- * FIXME: Not correct for BIDI operation
- */
- out_size = iov_length(vq->iov, out);
- in_size = iov_length(&vq->iov[out], in);
/*
- * Copy over the virtio-scsi request header, which for a
- * ANY_LAYOUT enabled guest may span multiple iovecs, or a
- * single iovec may contain both the header + outgoing
- * WRITE payloads.
- *
- * copy_from_iter() will advance out_iter, so that it will
- * point at the start of the outgoing WRITE payload, if
- * DMA_TO_DEVICE is set.
+ * Validate the size of request and response buffers.
+ * Check for a sane response buffer so we can report
+ * early errors back to the guest.
*/
- iov_iter_init(&out_iter, WRITE, vq->iov, out, out_size);
+ ret = vhost_scsi_chk_size(vq, &vc);
+ if (ret)
+ goto err;
- if (unlikely(!copy_from_iter_full(req, req_size, &out_iter))) {
- vq_err(vq, "Faulted on copy_from_iter\n");
- vhost_scsi_send_bad_target(vs, vq, head, out);
- continue;
- }
- /* virtio-scsi spec requires byte 0 of the lun to be 1 */
- if (unlikely(*lunp != 1)) {
- vq_err(vq, "Illegal virtio-scsi lun: %u\n", *lunp);
- vhost_scsi_send_bad_target(vs, vq, head, out);
- continue;
- }
+ ret = vhost_scsi_get_req(vq, &vc, &tpg);
+ if (ret)
+ goto err;
- tpg = READ_ONCE(vs_tpg[*target]);
- if (unlikely(!tpg)) {
- /* Target does not exist, fail the request */
- vhost_scsi_send_bad_target(vs, vq, head, out);
- continue;
- }
+ ret = -EIO; /* bad target on any error from here on */
+
/*
* Determine data_direction by calculating the total outgoing
* iovec sizes + incoming iovec sizes vs. virtio-scsi request +
@@ -930,17 +1025,17 @@
*/
prot_bytes = 0;
- if (out_size > req_size) {
+ if (vc.out_size > vc.req_size) {
data_direction = DMA_TO_DEVICE;
- exp_data_len = out_size - req_size;
- data_iter = out_iter;
- } else if (in_size > rsp_size) {
+ exp_data_len = vc.out_size - vc.req_size;
+ data_iter = vc.out_iter;
+ } else if (vc.in_size > vc.rsp_size) {
data_direction = DMA_FROM_DEVICE;
- exp_data_len = in_size - rsp_size;
+ exp_data_len = vc.in_size - vc.rsp_size;
- iov_iter_init(&in_iter, READ, &vq->iov[out], in,
- rsp_size + exp_data_len);
- iov_iter_advance(&in_iter, rsp_size);
+ iov_iter_init(&in_iter, READ, &vq->iov[vc.out], vc.in,
+ vc.rsp_size + exp_data_len);
+ iov_iter_advance(&in_iter, vc.rsp_size);
data_iter = in_iter;
} else {
data_direction = DMA_NONE;
@@ -956,16 +1051,14 @@
if (data_direction != DMA_TO_DEVICE) {
vq_err(vq, "Received non zero pi_bytesout,"
" but wrong data_direction\n");
- vhost_scsi_send_bad_target(vs, vq, head, out);
- continue;
+ goto err;
}
prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesout);
} else if (v_req_pi.pi_bytesin) {
if (data_direction != DMA_FROM_DEVICE) {
vq_err(vq, "Received non zero pi_bytesin,"
" but wrong data_direction\n");
- vhost_scsi_send_bad_target(vs, vq, head, out);
- continue;
+ goto err;
}
prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesin);
}
@@ -986,12 +1079,12 @@
tag = vhost64_to_cpu(vq, v_req_pi.tag);
task_attr = v_req_pi.task_attr;
cdb = &v_req_pi.cdb[0];
- lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF;
+ lun = vhost_buf_to_lun(v_req_pi.lun);
} else {
tag = vhost64_to_cpu(vq, v_req.tag);
task_attr = v_req.task_attr;
cdb = &v_req.cdb[0];
- lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;
+ lun = vhost_buf_to_lun(v_req.lun);
}
/*
* Check that the received CDB size does not exceeded our
@@ -1004,22 +1097,20 @@
vq_err(vq, "Received SCSI CDB with command_size: %d that"
" exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n",
scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE);
- vhost_scsi_send_bad_target(vs, vq, head, out);
- continue;
+ goto err;
}
- cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr,
+ cmd = vhost_scsi_get_cmd(vq, tpg, cdb, tag, lun, task_attr,
exp_data_len + prot_bytes,
data_direction);
if (IS_ERR(cmd)) {
- vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
+ vq_err(vq, "vhost_scsi_get_cmd failed %ld\n",
PTR_ERR(cmd));
- vhost_scsi_send_bad_target(vs, vq, head, out);
- continue;
+ goto err;
}
cmd->tvc_vhost = vs;
cmd->tvc_vq = vq;
- cmd->tvc_resp_iov = vq->iov[out];
- cmd->tvc_in_iovs = in;
+ cmd->tvc_resp_iov = vq->iov[vc.out];
+ cmd->tvc_in_iovs = vc.in;
pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
cmd->tvc_cdb[0], cmd->tvc_lun);
@@ -1027,14 +1118,12 @@
" %d\n", cmd, exp_data_len, prot_bytes, data_direction);
if (data_direction != DMA_NONE) {
- ret = vhost_scsi_mapal(cmd,
- prot_bytes, &prot_iter,
- exp_data_len, &data_iter);
- if (unlikely(ret)) {
+ if (unlikely(vhost_scsi_mapal(cmd, prot_bytes,
+ &prot_iter, exp_data_len,
+ &data_iter))) {
vq_err(vq, "Failed to map iov to sgl\n");
- vhost_scsi_release_cmd(&cmd->tvc_se_cmd);
- vhost_scsi_send_bad_target(vs, vq, head, out);
- continue;
+ vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd);
+ goto err;
}
}
/*
@@ -1042,7 +1131,7 @@
* complete the virtio-scsi request in TCM callback context via
* vhost_scsi_queue_data_in() and vhost_scsi_queue_status()
*/
- cmd->tvc_vq_desc = head;
+ cmd->tvc_vq_desc = vc.head;
/*
* Dispatch cmd descriptor for cmwq execution in process
* context provided by vhost_scsi_workqueue. This also ensures
@@ -1051,6 +1140,241 @@
*/
INIT_WORK(&cmd->work, vhost_scsi_submission_work);
queue_work(vhost_scsi_workqueue, &cmd->work);
+ ret = 0;
+err:
+ /*
+ * ENXIO: No more requests, or read error, wait for next kick
+ * EINVAL: Invalid response buffer, drop the request
+ * EIO: Respond with bad target
+ * EAGAIN: Pending request
+ */
+ if (ret == -ENXIO)
+ break;
+ else if (ret == -EIO)
+ vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+ } while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
+out:
+ mutex_unlock(&vq->mutex);
+}
+
+static void
+vhost_scsi_send_tmf_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
+ int in_iovs, int vq_desc, struct iovec *resp_iov,
+ int tmf_resp_code)
+{
+ struct virtio_scsi_ctrl_tmf_resp rsp;
+ struct iov_iter iov_iter;
+ int ret;
+
+ pr_debug("%s\n", __func__);
+ memset(&rsp, 0, sizeof(rsp));
+ rsp.response = tmf_resp_code;
+
+ iov_iter_init(&iov_iter, READ, resp_iov, in_iovs, sizeof(rsp));
+
+ ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
+ if (likely(ret == sizeof(rsp)))
+ vhost_add_used_and_signal(&vs->dev, vq, vq_desc, 0);
+ else
+ pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n");
+}
+
+static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
+{
+ struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf,
+ vwork);
+ int resp_code;
+
+ if (tmf->scsi_resp == TMR_FUNCTION_COMPLETE)
+ resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED;
+ else
+ resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+
+ vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
+ tmf->vq_desc, &tmf->resp_iov, resp_code);
+ vhost_scsi_release_tmf_res(tmf);
+}
+
+static void
+vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg,
+ struct vhost_virtqueue *vq,
+ struct virtio_scsi_ctrl_tmf_req *vtmf,
+ struct vhost_scsi_ctx *vc)
+{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_tmf *tmf;
+
+ if (vhost32_to_cpu(vq, vtmf->subtype) !=
+ VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET)
+ goto send_reject;
+
+ if (!tpg->tpg_nexus || !tpg->tpg_nexus->tvn_se_sess) {
+ pr_err("Unable to locate active struct vhost_scsi_nexus for LUN RESET.\n");
+ goto send_reject;
+ }
+
+ mutex_lock(&tpg->tv_tpg_mutex);
+ if (list_empty(&tpg->tmf_queue)) {
+ pr_err("Missing reserve TMF. Could not handle LUN RESET.\n");
+ mutex_unlock(&tpg->tv_tpg_mutex);
+ goto send_reject;
+ }
+
+ tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf,
+ queue_entry);
+ list_del_init(&tmf->queue_entry);
+ mutex_unlock(&tpg->tv_tpg_mutex);
+
+ tmf->tpg = tpg;
+ tmf->vhost = vs;
+ tmf->svq = svq;
+ tmf->resp_iov = vq->iov[vc->out];
+ tmf->vq_desc = vc->head;
+ tmf->in_iovs = vc->in;
+ tmf->inflight = vhost_scsi_get_inflight(vq);
+
+ if (target_submit_tmr(&tmf->se_cmd, tpg->tpg_nexus->tvn_se_sess, NULL,
+ vhost_buf_to_lun(vtmf->lun), NULL,
+ TMR_LUN_RESET, GFP_KERNEL, 0,
+ TARGET_SCF_ACK_KREF) < 0) {
+ vhost_scsi_release_tmf_res(tmf);
+ goto send_reject;
+ }
+
+ return;
+
+send_reject:
+ vhost_scsi_send_tmf_resp(vs, vq, vc->in, vc->head, &vq->iov[vc->out],
+ VIRTIO_SCSI_S_FUNCTION_REJECTED);
+}
+
+static void
+vhost_scsi_send_an_resp(struct vhost_scsi *vs,
+ struct vhost_virtqueue *vq,
+ struct vhost_scsi_ctx *vc)
+{
+ struct virtio_scsi_ctrl_an_resp rsp;
+ struct iov_iter iov_iter;
+ int ret;
+
+ pr_debug("%s\n", __func__);
+ memset(&rsp, 0, sizeof(rsp)); /* event_actual = 0 */
+ rsp.response = VIRTIO_SCSI_S_OK;
+
+ iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp));
+
+ ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
+ if (likely(ret == sizeof(rsp)))
+ vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
+ else
+ pr_err("Faulted on virtio_scsi_ctrl_an_resp\n");
+}
+
+static void
+vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
+{
+ struct vhost_scsi_tpg *tpg;
+ union {
+ __virtio32 type;
+ struct virtio_scsi_ctrl_an_req an;
+ struct virtio_scsi_ctrl_tmf_req tmf;
+ } v_req;
+ struct vhost_scsi_ctx vc;
+ size_t typ_size;
+ int ret, c = 0;
+
+ mutex_lock(&vq->mutex);
+ /*
+ * We can handle the vq only after the endpoint is setup by calling the
+ * VHOST_SCSI_SET_ENDPOINT ioctl.
+ */
+ if (!vhost_vq_get_backend(vq))
+ goto out;
+
+ memset(&vc, 0, sizeof(vc));
+
+ vhost_disable_notify(&vs->dev, vq);
+
+ do {
+ ret = vhost_scsi_get_desc(vs, vq, &vc);
+ if (ret)
+ goto err;
+
+ /*
+ * Get the request type first in order to setup
+ * other parameters dependent on the type.
+ */
+ vc.req = &v_req.type;
+ typ_size = sizeof(v_req.type);
+
+ if (unlikely(!copy_from_iter_full(vc.req, typ_size,
+ &vc.out_iter))) {
+ vq_err(vq, "Faulted on copy_from_iter tmf type\n");
+ /*
+ * The size of the response buffer depends on the
+ * request type and must be validated against it.
+ * Since the request type is not known, don't send
+ * a response.
+ */
+ continue;
+ }
+
+ switch (vhost32_to_cpu(vq, v_req.type)) {
+ case VIRTIO_SCSI_T_TMF:
+ vc.req = &v_req.tmf;
+ vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req);
+ vc.rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp);
+ vc.lunp = &v_req.tmf.lun[0];
+ vc.target = &v_req.tmf.lun[1];
+ break;
+ case VIRTIO_SCSI_T_AN_QUERY:
+ case VIRTIO_SCSI_T_AN_SUBSCRIBE:
+ vc.req = &v_req.an;
+ vc.req_size = sizeof(struct virtio_scsi_ctrl_an_req);
+ vc.rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp);
+ vc.lunp = &v_req.an.lun[0];
+ vc.target = NULL;
+ break;
+ default:
+ vq_err(vq, "Unknown control request %d", v_req.type);
+ continue;
+ }
+
+ /*
+ * Validate the size of request and response buffers.
+ * Check for a sane response buffer so we can report
+ * early errors back to the guest.
+ */
+ ret = vhost_scsi_chk_size(vq, &vc);
+ if (ret)
+ goto err;
+
+ /*
+ * Get the rest of the request now that its size is known.
+ */
+ vc.req += typ_size;
+ vc.req_size -= typ_size;
+
+ ret = vhost_scsi_get_req(vq, &vc, &tpg);
+ if (ret)
+ goto err;
+
+ if (v_req.type == VIRTIO_SCSI_T_TMF)
+ vhost_scsi_handle_tmf(vs, tpg, vq, &v_req.tmf, &vc);
+ else
+ vhost_scsi_send_an_resp(vs, vq, &vc);
+err:
+ /*
+ * ENXIO: No more requests, or read error, wait for next kick
+ * EINVAL: Invalid response buffer, drop the request
+ * EIO: Respond with bad target
+ * EAGAIN: Pending request
+ */
+ if (ret == -ENXIO)
+ break;
+ else if (ret == -EIO)
+ vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
out:
mutex_unlock(&vq->mutex);
@@ -1058,7 +1382,12 @@
static void vhost_scsi_ctl_handle_kick(struct vhost_work *work)
{
+ struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
+ poll.work);
+ struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev);
+
pr_debug("%s: The handling func for control queue.\n", __func__);
+ vhost_scsi_ctl_handle_vq(vs, vq);
}
static void
@@ -1098,7 +1427,7 @@
struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev);
mutex_lock(&vq->mutex);
- if (!vq->private_data)
+ if (!vhost_vq_get_backend(vq))
goto out;
if (vs->vs_events_missed)
@@ -1147,6 +1476,83 @@
/* Wait for all reqs issued before the flush to be finished */
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
wait_for_completion(&old_inflight[i]->comp);
+}
+
+static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq)
+{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_cmd *tv_cmd;
+ unsigned int i;
+
+ if (!svq->scsi_cmds)
+ return;
+
+ for (i = 0; i < svq->max_cmds; i++) {
+ tv_cmd = &svq->scsi_cmds[i];
+
+ kfree(tv_cmd->tvc_sgl);
+ kfree(tv_cmd->tvc_prot_sgl);
+ kfree(tv_cmd->tvc_upages);
+ }
+
+ sbitmap_free(&svq->scsi_tags);
+ kfree(svq->scsi_cmds);
+ svq->scsi_cmds = NULL;
+}
+
+static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds)
+{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_cmd *tv_cmd;
+ unsigned int i;
+
+ if (svq->scsi_cmds)
+ return 0;
+
+ if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL,
+ NUMA_NO_NODE))
+ return -ENOMEM;
+ svq->max_cmds = max_cmds;
+
+ svq->scsi_cmds = kcalloc(max_cmds, sizeof(*tv_cmd), GFP_KERNEL);
+ if (!svq->scsi_cmds) {
+ sbitmap_free(&svq->scsi_tags);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < max_cmds; i++) {
+ tv_cmd = &svq->scsi_cmds[i];
+
+ tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS,
+ sizeof(struct scatterlist),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_sgl) {
+ pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
+ goto out;
+ }
+
+ tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES,
+ sizeof(struct page *),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_upages) {
+ pr_err("Unable to allocate tv_cmd->tvc_upages\n");
+ goto out;
+ }
+
+ tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
+ sizeof(struct scatterlist),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_prot_sgl) {
+ pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
+ goto out;
+ }
+ }
+ return 0;
+out:
+ vhost_scsi_destroy_vq_cmds(vq);
+ return -ENOMEM;
}
/*
@@ -1203,10 +1609,9 @@
if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) {
- kfree(vs_tpg);
mutex_unlock(&tpg->tv_tpg_mutex);
ret = -EEXIST;
- goto out;
+ goto undepend;
}
/*
* In order to ensure individual vhost-scsi configfs
@@ -1217,15 +1622,13 @@
se_tpg = &tpg->se_tpg;
ret = target_depend_item(&se_tpg->tpg_group.cg_item);
if (ret) {
- pr_warn("configfs_depend_item() failed: %d\n", ret);
- kfree(vs_tpg);
+ pr_warn("target_depend_item() failed: %d\n", ret);
mutex_unlock(&tpg->tv_tpg_mutex);
- goto out;
+ goto undepend;
}
tpg->tv_tpg_vhost_count++;
tpg->vhost_scsi = vs;
vs_tpg[tpg->tport_tpgt] = tpg;
- smp_mb__after_atomic();
match = true;
}
mutex_unlock(&tpg->tv_tpg_mutex);
@@ -1234,10 +1637,21 @@
if (match) {
memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
sizeof(vs->vs_vhost_wwpn));
+
+ for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) {
+ vq = &vs->vqs[i].vq;
+ if (!vhost_vq_is_setup(vq))
+ continue;
+
+ ret = vhost_scsi_setup_vq_cmds(vq, vq->num);
+ if (ret)
+ goto destroy_vq_cmds;
+ }
+
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
vq = &vs->vqs[i].vq;
mutex_lock(&vq->mutex);
- vq->private_data = vs_tpg;
+ vhost_vq_set_backend(vq, vs_tpg);
vhost_vq_init_access(vq);
mutex_unlock(&vq->mutex);
}
@@ -1253,7 +1667,22 @@
vhost_scsi_flush(vs);
kfree(vs->vs_tpg);
vs->vs_tpg = vs_tpg;
+ goto out;
+destroy_vq_cmds:
+ for (i--; i >= VHOST_SCSI_VQ_IO; i--) {
+ if (!vhost_vq_get_backend(&vs->vqs[i].vq))
+ vhost_scsi_destroy_vq_cmds(&vs->vqs[i].vq);
+ }
+undepend:
+ for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) {
+ tpg = vs_tpg[i];
+ if (tpg) {
+ tpg->tv_tpg_vhost_count--;
+ target_undepend_item(&tpg->se_tpg.tpg_group.cg_item);
+ }
+ }
+ kfree(vs_tpg);
out:
mutex_unlock(&vs->dev.mutex);
mutex_unlock(&vhost_scsi_mutex);
@@ -1324,8 +1753,14 @@
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
vq = &vs->vqs[i].vq;
mutex_lock(&vq->mutex);
- vq->private_data = NULL;
+ vhost_vq_set_backend(vq, NULL);
mutex_unlock(&vq->mutex);
+ /*
+ * Make sure cmds are not running before tearing them
+ * down.
+ */
+ vhost_scsi_flush(vs);
+ vhost_scsi_destroy_vq_cmds(vq);
}
}
/*
@@ -1405,7 +1840,7 @@
vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
}
vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV,
- VHOST_SCSI_WEIGHT, 0);
+ VHOST_SCSI_WEIGHT, 0, true, NULL);
vhost_scsi_init_inflight(vs, NULL);
@@ -1504,21 +1939,11 @@
}
}
-#ifdef CONFIG_COMPAT
-static long vhost_scsi_compat_ioctl(struct file *f, unsigned int ioctl,
- unsigned long arg)
-{
- return vhost_scsi_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
-}
-#endif
-
static const struct file_operations vhost_scsi_fops = {
.owner = THIS_MODULE,
.release = vhost_scsi_release,
.unlocked_ioctl = vhost_scsi_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = vhost_scsi_compat_ioctl,
-#endif
+ .compat_ioctl = compat_ptr_ioctl,
.open = vhost_scsi_open,
.llseek = noop_llseek,
};
@@ -1598,11 +2023,19 @@
{
struct vhost_scsi_tpg *tpg = container_of(se_tpg,
struct vhost_scsi_tpg, se_tpg);
+ struct vhost_scsi_tmf *tmf;
+
+ tmf = kzalloc(sizeof(*tmf), GFP_KERNEL);
+ if (!tmf)
+ return -ENOMEM;
+ INIT_LIST_HEAD(&tmf->queue_entry);
+ vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work);
mutex_lock(&vhost_scsi_mutex);
mutex_lock(&tpg->tv_tpg_mutex);
tpg->tv_tpg_port_count++;
+ list_add_tail(&tmf->queue_entry, &tpg->tmf_queue);
mutex_unlock(&tpg->tv_tpg_mutex);
vhost_scsi_hotplug(tpg, lun);
@@ -1617,33 +2050,21 @@
{
struct vhost_scsi_tpg *tpg = container_of(se_tpg,
struct vhost_scsi_tpg, se_tpg);
+ struct vhost_scsi_tmf *tmf;
mutex_lock(&vhost_scsi_mutex);
mutex_lock(&tpg->tv_tpg_mutex);
tpg->tv_tpg_port_count--;
+ tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf,
+ queue_entry);
+ list_del(&tmf->queue_entry);
+ kfree(tmf);
mutex_unlock(&tpg->tv_tpg_mutex);
vhost_scsi_hotunplug(tpg, lun);
mutex_unlock(&vhost_scsi_mutex);
-}
-
-static void vhost_scsi_free_cmd_map_res(struct se_session *se_sess)
-{
- struct vhost_scsi_cmd *tv_cmd;
- unsigned int i;
-
- if (!se_sess->sess_cmd_map)
- return;
-
- for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
- tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];
-
- kfree(tv_cmd->tvc_sgl);
- kfree(tv_cmd->tvc_prot_sgl);
- kfree(tv_cmd->tvc_upages);
- }
}
static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store(
@@ -1685,45 +2106,6 @@
NULL,
};
-static int vhost_scsi_nexus_cb(struct se_portal_group *se_tpg,
- struct se_session *se_sess, void *p)
-{
- struct vhost_scsi_cmd *tv_cmd;
- unsigned int i;
-
- for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
- tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];
-
- tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS,
- sizeof(struct scatterlist),
- GFP_KERNEL);
- if (!tv_cmd->tvc_sgl) {
- pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
- goto out;
- }
-
- tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES,
- sizeof(struct page *),
- GFP_KERNEL);
- if (!tv_cmd->tvc_upages) {
- pr_err("Unable to allocate tv_cmd->tvc_upages\n");
- goto out;
- }
-
- tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
- sizeof(struct scatterlist),
- GFP_KERNEL);
- if (!tv_cmd->tvc_prot_sgl) {
- pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
- goto out;
- }
- }
- return 0;
-out:
- vhost_scsi_free_cmd_map_res(se_sess);
- return -ENOMEM;
-}
-
static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg,
const char *name)
{
@@ -1747,12 +2129,9 @@
* struct se_node_acl for the vhost_scsi struct se_portal_group with
* the SCSI Initiator port name of the passed configfs group 'name'.
*/
- tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
- VHOST_SCSI_DEFAULT_TAGS,
- sizeof(struct vhost_scsi_cmd),
+ tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, 0, 0,
TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
- (unsigned char *)name, tv_nexus,
- vhost_scsi_nexus_cb);
+ (unsigned char *)name, tv_nexus, NULL);
if (IS_ERR(tv_nexus->tvn_se_sess)) {
mutex_unlock(&tpg->tv_tpg_mutex);
kfree(tv_nexus);
@@ -1802,7 +2181,6 @@
" %s Initiator Port: %s\n", vhost_scsi_dump_proto_id(tpg->tport),
tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
- vhost_scsi_free_cmd_map_res(se_sess);
/*
* Release the SCSI I_T Nexus to the emulated vhost Target Port
*/
@@ -1942,6 +2320,7 @@
}
mutex_init(&tpg->tv_tpg_mutex);
INIT_LIST_HEAD(&tpg->tv_tpg_list);
+ INIT_LIST_HEAD(&tpg->tmf_queue);
tpg->tport = tport;
tpg->tport_tpgt = tpgt;
@@ -2066,8 +2445,8 @@
static const struct target_core_fabric_ops vhost_scsi_ops = {
.module = THIS_MODULE,
- .name = "vhost",
- .get_fabric_name = vhost_scsi_get_fabric_name,
+ .fabric_name = "vhost",
+ .max_data_sg_nents = VHOST_SCSI_PREALLOC_SGLS,
.tpg_get_wwn = vhost_scsi_get_fabric_wwn,
.tpg_get_tag = vhost_scsi_get_tpgt,
.tpg_check_demo_mode = vhost_scsi_check_true,
@@ -2081,7 +2460,6 @@
.sess_get_index = vhost_scsi_sess_get_index,
.sess_get_initiator_sid = NULL,
.write_pending = vhost_scsi_write_pending,
- .write_pending_status = vhost_scsi_write_pending_status,
.set_default_node_attributes = vhost_scsi_set_default_node_attrs,
.get_cmd_state = vhost_scsi_get_cmd_state,
.queue_data_in = vhost_scsi_queue_data_in,
--
Gitblit v1.6.2