nvme: support scatter gather lists

For now, support the Data Block, Segment and Last Segment descriptor
types.

See NVM Express 1.3d, Section 4.4 ("Scatter Gather List (SGL)").

Signed-off-by: Klaus Birkelund Jensen <klaus.jensen@cnexlabs.com>

diff --git a/block/nvme.c b/block/nvme.c
index 5be3a39b632ec327406c730c3a7dad164c38ddda..8825c19c72c23efb4a412dd71468451fdd147dc5 100644 (file)
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -440,7 +440,7 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
         error_setg(errp, "Cannot map buffer for DMA");
         goto out;
     }
-    cmd.prp1 = cpu_to_le64(iova);
+    cmd.dptr.prp.prp1 = cpu_to_le64(iova);
 
     if (nvme_cmd_sync(bs, s->queues[0], &cmd)) {
         error_setg(errp, "Failed to identify controller");
@@ -529,7 +529,7 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
     }
     cmd = (NvmeCmd) {
         .opcode = NVME_ADM_CMD_CREATE_CQ,
-        .prp1 = cpu_to_le64(q->cq.iova),
+        .dptr.prp.prp1 = cpu_to_le64(q->cq.iova),
         .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
         .cdw11 = cpu_to_le32(0x3),
     };
@@ -540,7 +540,7 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
     }
     cmd = (NvmeCmd) {
         .opcode = NVME_ADM_CMD_CREATE_SQ,
-        .prp1 = cpu_to_le64(q->sq.iova),
+        .dptr.prp.prp1 = cpu_to_le64(q->sq.iova),
         .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
         .cdw11 = cpu_to_le32(0x1 | (n << 16)),
     };
@@ -889,16 +889,16 @@ try_map:
     case 0:
         abort();
     case 1:
-        cmd->prp1 = pagelist[0];
-        cmd->prp2 = 0;
+        cmd->dptr.prp.prp1 = pagelist[0];
+        cmd->dptr.prp.prp2 = 0;
         break;
     case 2:
-        cmd->prp1 = pagelist[0];
-        cmd->prp2 = pagelist[1];
+        cmd->dptr.prp.prp1 = pagelist[0];
+        cmd->dptr.prp.prp2 = pagelist[1];
         break;
     default:
-        cmd->prp1 = pagelist[0];
-        cmd->prp2 = cpu_to_le64(req->prp_list_iova + sizeof(uint64_t));
+        cmd->dptr.prp.prp1 = pagelist[0];
+        cmd->dptr.prp.prp2 = cpu_to_le64(req->prp_list_iova + sizeof(uint64_t));
         break;
     }
     trace_nvme_cmd_map_qiov(s, cmd, req, qiov, entries);

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index bdbb1dc31108cb9e2e23019ec212edbcc28222b1..8c1c7a2adf9ecd8230bd72e63cfadf7a08907345 100644 (file)
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -275,6 +275,198 @@ unmap:
     return status;
 }
 
+static uint16_t nvme_map_sgl_data(NvmeCtrl *n, QEMUSGList *qsg,
+    NvmeSglDescriptor *segment, uint64_t nsgld, uint32_t *len,
+    NvmeRequest *req)
+{
+    dma_addr_t addr, trans_len;
+
+    for (int i = 0; i < nsgld; i++) {
+        if (NVME_SGL_TYPE(segment[i].type) != SGL_DESCR_TYPE_DATA_BLOCK) {
+            trace_nvme_err_invalid_sgl_descriptor(req->cqe.cid,
+                NVME_SGL_TYPE(segment[i].type));
+            return NVME_SGL_DESCRIPTOR_TYPE_INVALID | NVME_DNR;
+        }
+
+        if (*len == 0) {
+            if (!NVME_CTRL_SGLS_EXCESS_LENGTH(n->id_ctrl.sgls)) {
+                trace_nvme_err_invalid_sgl_excess_length(req->cqe.cid);
+                return NVME_DATA_SGL_LENGTH_INVALID | NVME_DNR;
+            }
+
+            break;
+        }
+
+        addr = le64_to_cpu(segment[i].addr);
+        trans_len = MIN(*len, le64_to_cpu(segment[i].len));
+
+        if (nvme_addr_is_cmb(n, addr)) {
+            /*
+             * All data and metadata, if any, associated with a particular
+             * command shall be located in either the CMB or host memory. Thus,
+             * if an address if found to be in the CMB and we have already
+             * mapped data that is in host memory, the use is invalid.
+             */
+            if (!req->is_cmb && qsg->size) {
+                return NVME_INVALID_USE_OF_CMB | NVME_DNR;
+            }
+
+            req->is_cmb = true;
+        } else {
+            /*
+             * Similarly, if the address does not reference the CMB, but we
+             * have already established that the request has data or metadata
+             * in the CMB, the use is invalid.
+             */
+            if (req->is_cmb) {
+                return NVME_INVALID_USE_OF_CMB | NVME_DNR;
+            }
+        }
+
+        qemu_sglist_add(qsg, addr, trans_len);
+
+        *len -= trans_len;
+    }
+
+    return NVME_SUCCESS;
+}
+
+static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg,
+    NvmeSglDescriptor sgl, uint32_t len, NvmeRequest *req)
+{
+    const int MAX_NSGLD = 256;
+
+    NvmeSglDescriptor segment[MAX_NSGLD];
+    uint64_t nsgld;
+    uint16_t status;
+    bool sgl_in_cmb = false;
+    hwaddr addr = le64_to_cpu(sgl.addr);
+
+    trace_nvme_map_sgl(req->cqe.cid, NVME_SGL_TYPE(sgl.type), req->nlb, len);
+
+    pci_dma_sglist_init(qsg, &n->parent_obj, 1);
+
+    /*
+     * If the entire transfer can be described with a single data block it can
+     * be mapped directly.
+     */
+    if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
+        status = nvme_map_sgl_data(n, qsg, &sgl, 1, &len, req);
+        if (status) {
+            goto unmap;
+        }
+
+        goto out;
+    }
+
+    /*
+     * If the segment is located in the CMB, the submission queue of the
+     * request must also reside there.
+     */
+    if (nvme_addr_is_cmb(n, addr)) {
+        if (!nvme_addr_is_cmb(n, req->sq->dma_addr)) {
+            return NVME_INVALID_USE_OF_CMB | NVME_DNR;
+        }
+
+        sgl_in_cmb = true;
+    }
+
+    while (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_SEGMENT) {
+        bool addr_is_cmb;
+
+        nsgld = le64_to_cpu(sgl.len) / sizeof(NvmeSglDescriptor);
+
+        /* read the segment in chunks of 256 descriptors (4k) */
+        while (nsgld > MAX_NSGLD) {
+            nvme_addr_read(n, addr, segment, sizeof(segment));
+
+            status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
+            if (status) {
+                goto unmap;
+            }
+
+            nsgld -= MAX_NSGLD;
+            addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
+        }
+
+        nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
+
+        sgl = segment[nsgld - 1];
+        addr = le64_to_cpu(sgl.addr);
+
+        /* an SGL is allowed to end with a Data Block in a regular Segment */
+        if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
+            status = nvme_map_sgl_data(n, qsg, segment, nsgld, &len, req);
+            if (status) {
+                goto unmap;
+            }
+
+            goto out;
+        }
+
+        /* do not map last descriptor */
+        status = nvme_map_sgl_data(n, qsg, segment, nsgld - 1, &len, req);
+        if (status) {
+            goto unmap;
+        }
+
+        /*
+         * If the next segment is in the CMB, make sure that the sgl was
+         * already located there.
+         */
+        addr_is_cmb = nvme_addr_is_cmb(n, addr);
+        if ((sgl_in_cmb && !addr_is_cmb) || (!sgl_in_cmb && addr_is_cmb)) {
+            status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
+            goto unmap;
+        }
+    }
+
+    /*
+     * If the segment did not end with a Data Block or a Segment descriptor, it
+     * must be a Last Segment descriptor.
+     */
+    if (NVME_SGL_TYPE(sgl.type) != SGL_DESCR_TYPE_LAST_SEGMENT) {
+        trace_nvme_err_invalid_sgl_descriptor(req->cqe.cid,
+            NVME_SGL_TYPE(sgl.type));
+        return NVME_SGL_DESCRIPTOR_TYPE_INVALID | NVME_DNR;
+    }
+
+    nsgld = le64_to_cpu(sgl.len) / sizeof(NvmeSglDescriptor);
+
+    while (nsgld > MAX_NSGLD) {
+        nvme_addr_read(n, addr, segment, sizeof(segment));
+
+        status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
+        if (status) {
+            goto unmap;
+        }
+
+        nsgld -= MAX_NSGLD;
+        addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
+    }
+
+    nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
+
+    status = nvme_map_sgl_data(n, qsg, segment, nsgld, &len, req);
+    if (status) {
+        goto unmap;
+    }
+
+out:
+    /* if there is any residual left in len, the SGL was too short */
+    if (len) {
+        status = NVME_DATA_SGL_LENGTH_INVALID | NVME_DNR;
+        goto unmap;
+    }
+
+    return NVME_SUCCESS;
+
+unmap:
+    qemu_sglist_destroy(qsg);
+
+    return status;
+}
+
 static void dma_to_cmb(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov)
 {
     for (int i = 0; i < qsg->nsg; i++) {
@@ -320,6 +512,56 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
     return err;
 }
 
+static uint16_t nvme_dma_write_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
+    NvmeSglDescriptor sgl, NvmeRequest *req)
+{
+    QEMUSGList qsg;
+    uint16_t err = NVME_SUCCESS;
+
+    err = nvme_map_sgl(n, &qsg, sgl, len, req);
+    if (err) {
+        return err;
+    }
+
+    if (req->is_cmb) {
+        QEMUIOVector iov;
+
+        qemu_iovec_init(&iov, qsg.nsg);
+        dma_to_cmb(n, &qsg, &iov);
+
+        if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) {
+            trace_nvme_err_invalid_dma();
+            err = NVME_INVALID_FIELD | NVME_DNR;
+        }
+
+        qemu_iovec_destroy(&iov);
+
+        return err;
+    }
+
+    if (unlikely(dma_buf_write(ptr, len, &qsg))) {
+        trace_nvme_err_invalid_dma();
+        err = NVME_INVALID_FIELD | NVME_DNR;
+    }
+
+    qemu_sglist_destroy(&qsg);
+
+    return err;
+}
+
+static uint16_t nvme_dma_write(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
+    NvmeCmd *cmd, NvmeRequest *req)
+{
+    if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
+        return nvme_dma_write_sgl(n, ptr, len, cmd->dptr.sgl, req);
+    }
+
+    uint64_t prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
+    uint64_t prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
+
+    return nvme_dma_write_prp(n, ptr, len, prp1, prp2, req);
+}
+
 static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
     uint64_t prp1, uint64_t prp2, NvmeRequest *req)
 {
@@ -357,6 +599,57 @@ out:
     return err;
 }
 
+static uint16_t nvme_dma_read_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
+    NvmeSglDescriptor sgl, NvmeCmd *cmd, NvmeRequest *req)
+{
+    QEMUSGList qsg;
+    uint16_t err = NVME_SUCCESS;
+
+    err = nvme_map_sgl(n, &qsg, sgl, len, req);
+    if (err) {
+        return err;
+    }
+
+    if (req->is_cmb) {
+        QEMUIOVector iov;
+
+        qemu_iovec_init(&iov, qsg.nsg);
+        dma_to_cmb(n, &qsg, &iov);
+
+        if (unlikely(qemu_iovec_from_buf(&iov, 0, ptr, len) != len)) {
+            trace_nvme_err_invalid_dma();
+            err = NVME_INVALID_FIELD | NVME_DNR;
+        }
+
+        qemu_iovec_destroy(&iov);
+
+        goto out;
+    }
+
+    if (unlikely(dma_buf_read(ptr, len, &qsg))) {
+        trace_nvme_err_invalid_dma();
+        err = NVME_INVALID_FIELD | NVME_DNR;
+    }
+
+out:
+    qemu_sglist_destroy(&qsg);
+
+    return err;
+}
+
+static uint16_t nvme_dma_read(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
+    NvmeCmd *cmd, NvmeRequest *req)
+{
+    if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
+        return nvme_dma_read_sgl(n, ptr, len, cmd->dptr.sgl, cmd, req);
+    }
+
+    uint64_t prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
+    uint64_t prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
+
+    return nvme_dma_read_prp(n, ptr, len, prp1, prp2, req);
+}
+
 static void nvme_blk_req_destroy(NvmeBlockBackendRequest *blk_req)
 {
     if (blk_req->iov.nalloc) {
@@ -410,20 +703,25 @@ static uint16_t nvme_blk_map(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     uint16_t err;
 
     uint32_t len = req->nlb * nvme_ns_lbads_bytes(ns);
-    uint64_t prp1 = le64_to_cpu(cmd->prp1);
-    uint64_t prp2 = le64_to_cpu(cmd->prp2);
 
-    err = nvme_map_prp(n, &req->qsg, prp1, prp2, len, req);
-    if (err) {
-        return err;
+    if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
+        err = nvme_map_sgl(n, &req->qsg, cmd->dptr.sgl, len, req);
+        if (err) {
+            return err;
+        }
+    } else {
+        uint64_t prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
+        uint64_t prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
+
+        err = nvme_map_prp(n, &req->qsg, prp1, prp2, len, req);
+        if (err) {
+            return err;
+        }
     }
 
     err = nvme_blk_setup(n, ns, &req->qsg, req);
-    if (err) {
-        return err;
-    }
 
-    return NVME_SUCCESS;
+    return err;
 }
 
 static void nvme_post_cqes(void *opaque)
@@ -986,25 +1284,18 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
     return NVME_SUCCESS;
 }
 
-static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c,
-    NvmeRequest *req)
+static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 {
-    uint64_t prp1 = le64_to_cpu(c->prp1);
-    uint64_t prp2 = le64_to_cpu(c->prp2);
-
     trace_nvme_identify_ctrl();
 
-    return nvme_dma_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl),
-        prp1, prp2, req);
+    return nvme_dma_read(n, (uint8_t *) &n->id_ctrl, sizeof(n->id_ctrl), cmd,
+        req);
 }
 
-static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c,
-    NvmeRequest *req)
+static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 {
     NvmeNamespace *ns;
-    uint32_t nsid = le32_to_cpu(c->nsid);
-    uint64_t prp1 = le64_to_cpu(c->prp1);
-    uint64_t prp2 = le64_to_cpu(c->prp2);
+    uint32_t nsid = le32_to_cpu(cmd->nsid);
 
     trace_nvme_identify_ns(nsid);
 
@@ -1015,17 +1306,15 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c,
 
     ns = &n->namespace;
 
-    return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns),
-        prp1, prp2, req);
+    return nvme_dma_read(n, (uint8_t *) &ns->id_ns, sizeof(ns->id_ns), cmd,
+        req);
 }
 
-static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c,
+static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeCmd *cmd,
     NvmeRequest *req)
 {
     static const int data_len = 4 * KiB;
-    uint32_t min_nsid = le32_to_cpu(c->nsid);
-    uint64_t prp1 = le64_to_cpu(c->prp1);
-    uint64_t prp2 = le64_to_cpu(c->prp2);
+    uint32_t min_nsid = le32_to_cpu(cmd->nsid);
     uint32_t *list;
     uint16_t ret;
     int i, j = 0;
@@ -1042,12 +1331,12 @@ static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c,
             break;
         }
     }
-    ret = nvme_dma_read_prp(n, (uint8_t *)list, data_len, prp1, prp2, req);
+    ret = nvme_dma_read(n, (uint8_t *) list, data_len, cmd, req);
     g_free(list);
     return ret;
 }
 
-static uint16_t nvme_identify_ns_descriptor_list(NvmeCtrl *n, NvmeCmd *c,
+static uint16_t nvme_identify_ns_descriptor_list(NvmeCtrl *n, NvmeCmd *cmd,
     NvmeRequest *req)
 {
     static const int data_len = 4 * KiB;
@@ -1065,9 +1354,7 @@ static uint16_t nvme_identify_ns_descriptor_list(NvmeCtrl *n, NvmeCmd *c,
         uint32_t nid;
     };
 
-    uint32_t nsid = le32_to_cpu(c->nsid);
-    uint64_t prp1 = le64_to_cpu(c->prp1);
-    uint64_t prp2 = le64_to_cpu(c->prp2);
+    uint32_t nsid = le32_to_cpu(cmd->nsid);
 
     struct ns_descr *list;
     uint16_t ret;
@@ -1084,7 +1371,7 @@ static uint16_t nvme_identify_ns_descriptor_list(NvmeCtrl *n, NvmeCmd *c,
     list->nidl = 0x10;
     list->nid = cpu_to_be32(nsid);
 
-    ret = nvme_dma_read_prp(n, (uint8_t *) list, data_len, prp1, prp2, req);
+    ret = nvme_dma_read(n, (uint8_t *) list, data_len, cmd, req);
     g_free(list);
     return ret;
 }
@@ -1095,11 +1382,11 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 
     switch (le32_to_cpu(c->cns)) {
     case 0x00:
-        return nvme_identify_ns(n, c, req);
+        return nvme_identify_ns(n, cmd, req);
     case 0x01:
-        return nvme_identify_ctrl(n, c, req);
+        return nvme_identify_ctrl(n, cmd, req);
     case 0x02:
-        return nvme_identify_ns_list(n, c, req);
+        return nvme_identify_ns_list(n, cmd, req);
     case 0x03:
         return nvme_identify_ns_descriptor_list(n, cmd, req);
     default:
@@ -1151,13 +1438,10 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)
 static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
     NvmeRequest *req)
 {
-    uint64_t prp1 = le64_to_cpu(cmd->prp1);
-    uint64_t prp2 = le64_to_cpu(cmd->prp2);
-
     uint64_t timestamp = nvme_get_timestamp(n);
 
-    return nvme_dma_read_prp(n, (uint8_t *)&timestamp, sizeof(timestamp),
-        prp1, prp2, req);
+    return nvme_dma_read(n, (uint8_t *)&timestamp, sizeof(timestamp), cmd,
+        req);
 }
 
 static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
@@ -1222,11 +1506,9 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
 {
     uint16_t ret;
     uint64_t timestamp;
-    uint64_t prp1 = le64_to_cpu(cmd->prp1);
-    uint64_t prp2 = le64_to_cpu(cmd->prp2);
 
-    ret = nvme_dma_write_prp(n, (uint8_t *)&timestamp,
-                                sizeof(timestamp), prp1, prp2, req);
+    ret = nvme_dma_write(n, (uint8_t *)&timestamp, sizeof(timestamp), cmd,
+        req);
     if (ret != NVME_SUCCESS) {
         return ret;
     }
@@ -1303,8 +1585,6 @@ static uint16_t nvme_error_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
     uint32_t buf_len, uint64_t off, NvmeRequest *req)
 {
     uint32_t trans_len;
-    uint64_t prp1 = le64_to_cpu(cmd->prp1);
-    uint64_t prp2 = le64_to_cpu(cmd->prp2);
 
     if (off > sizeof(*n->elpes) * (NVME_ELPE + 1)) {
         return NVME_INVALID_FIELD | NVME_DNR;
@@ -1316,16 +1596,12 @@ static uint16_t nvme_error_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
         nvme_clear_events(n, NVME_AER_TYPE_ERROR);
     }
 
-    return nvme_dma_read_prp(n, (uint8_t *) n->elpes + off, trans_len, prp1,
-        prp2, req);
+    return nvme_dma_read(n, (uint8_t *) n->elpes + off, trans_len, cmd, req);
 }
 
 static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
     uint32_t buf_len, uint64_t off, NvmeRequest *req)
 {
-    uint64_t prp1 = le64_to_cpu(cmd->prp1);
-    uint64_t prp2 = le64_to_cpu(cmd->prp2);
-
     uint32_t trans_len;
     time_t current_ms;
     NvmeSmartLog smart;
@@ -1359,16 +1635,13 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
         nvme_clear_events(n, NVME_AER_TYPE_SMART);
     }
 
-    return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
-        prp2, req);
+    return nvme_dma_read(n, (uint8_t *) &smart + off, trans_len, cmd, req);
 }
 
 static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
     uint64_t off, NvmeRequest *req)
 {
     uint32_t trans_len;
-    uint64_t prp1 = le64_to_cpu(cmd->prp1);
-    uint64_t prp2 = le64_to_cpu(cmd->prp2);
     NvmeFwSlotInfoLog fw_log;
 
     if (off > sizeof(fw_log)) {
@@ -1379,8 +1652,7 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
 
     trans_len = MIN(sizeof(fw_log) - off, buf_len);
 
-    return nvme_dma_read_prp(n, (uint8_t *) &fw_log + off, trans_len, prp1,
-        prp2, req);
+    return nvme_dma_read(n, (uint8_t *) &fw_log + off, trans_len, cmd, req);
 }
 
 
@@ -2139,6 +2411,8 @@ static void nvme_init_ctrl(NvmeCtrl *n)
         id->vwc = 1;
     }
 
+    id->sgls = cpu_to_le32(0x1);
+
     strcpy((char *) id->subnqn, "nqn.2014-08.org.nvmexpress:uuid:");
     qemu_uuid_unparse(&qemu_uuid,
         (char *) id->subnqn + strlen((char *) id->subnqn));

diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 832094f77845bd1558892e2abdcedca84da21030..1d52b183d263aa7e1c0d79b49fd5fc59def42aad 100644 (file)
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -142,6 +142,12 @@ static inline bool nvme_rw_is_write(NvmeRequest *req)
     return req->cmd.opcode == NVME_CMD_WRITE;
 }
 
+static inline bool nvme_is_error(uint16_t status, uint16_t err)
+{
+    /* strip DNR and MORE */
+    return (status & 0xfff) == err;
+}
+
 static inline uint8_t nvme_ns_lbads(NvmeNamespace *ns)
 {
     NvmeIdNs *id = &ns->id_ns;

diff --git a/hw/block/trace-events b/hw/block/trace-events
index b324751ad99089658429a9969e2f884e256a89f7..b239e92294e4b3d540fe60b0f3cd51a1f92093ea 100644 (file)
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -34,6 +34,7 @@ nvme_irq_pin(void) "pulsing IRQ pin"
 nvme_irq_masked(void) "IRQ is masked"
 nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64""
 nvme_map_prp(uint8_t cmd_opcode, uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "cmd_opcode=0x%"PRIx8", trans_len=%"PRIu64", len=%"PRIu32", prp1=0x%"PRIx64", prp2=0x%"PRIx64", num_prps=%d"
+nvme_map_sgl(uint16_t cid, uint8_t typ, uint16_t nlb, uint64_t len) "cid %"PRIu16" type 0x%"PRIx8" nlb %"PRIu16" len %"PRIu64""
 nvme_io_cmd(uint16_t cid, uint32_t nsid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" opc %"PRIu8""
 nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
 nvme_rw_cb(uint16_t cid, uint32_t nsid) "cid %"PRIu16" nsid %"PRIu32""
@@ -76,6 +77,8 @@ nvme_mmio_shutdown_cleared(void) "shutdown bit cleared"
 
 # nvme traces for error conditions
 nvme_err(uint16_t cid, const char *s, uint16_t status) "cid %"PRIu16" \"%s\" status 0x%"PRIx16""
+nvme_err_invalid_sgl_descriptor(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8""
+nvme_err_invalid_sgl_excess_length(uint16_t cid) "cid %"PRIu16""
 nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size"
 nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64""
 nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""

diff --git a/include/block/nvme.h b/include/block/nvme.h
index a6ef8d8ff25aa715a1c15b0c6067541f48d59d30..f79c71ba3f8cf43366c16aa986d22f424d18bd2d 100644 (file)
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -205,15 +205,53 @@ enum NvmeCmbszMask {
 #define NVME_CMBSZ_GETSIZE(cmbsz) \
     (NVME_CMBSZ_SZ(cmbsz) * (1 << (12 + 4 * NVME_CMBSZ_SZU(cmbsz))))
 
+enum NvmeSglDescriptorType {
+    SGL_DESCR_TYPE_DATA_BLOCK           = 0x0,
+    SGL_DESCR_TYPE_BIT_BUCKET           = 0x1,
+    SGL_DESCR_TYPE_SEGMENT              = 0x2,
+    SGL_DESCR_TYPE_LAST_SEGMENT         = 0x3,
+    SGL_DESCR_TYPE_KEYED_DATA_BLOCK     = 0x4,
+
+    SGL_DESCR_TYPE_VENDOR_SPECIFIC      = 0xf,
+};
+
+enum NvmeSglDescriptorSubtype {
+    SGL_DESCR_SUBTYPE_ADDRESS = 0x0,
+    SGL_DESCR_SUBTYPE_OFFSET  = 0x1,
+};
+
+typedef struct NvmeSglDescriptor {
+    uint64_t addr;
+    uint32_t len;
+    uint8_t  rsvd[3];
+    uint8_t  type;
+} NvmeSglDescriptor;
+
+#define NVME_SGL_TYPE(type)     (type >> 4)
+
+typedef union NvmeCmdDptr {
+    struct {
+        uint64_t    prp1;
+        uint64_t    prp2;
+    } prp;
+
+    NvmeSglDescriptor sgl;
+} NvmeCmdDptr;
+
+enum NvmePsdt {
+    PSDT_PRP                 = 0x0,
+    PSDT_SGL_MPTR_CONTIGUOUS = 0x1,
+    PSDT_SGL_MPTR_SGL        = 0x2,
+};
+
 typedef struct NvmeCmd {
     uint8_t     opcode;
-    uint8_t     fuse;
+    uint8_t     flags;
     uint16_t    cid;
     uint32_t    nsid;
-    uint64_t    res1;
+    uint64_t    rsvd2;
     uint64_t    mptr;
-    uint64_t    prp1;
-    uint64_t    prp2;
+    NvmeCmdDptr dptr;
     uint32_t    cdw10;
     uint32_t    cdw11;
     uint32_t    cdw12;
@@ -222,6 +260,9 @@ typedef struct NvmeCmd {
     uint32_t    cdw15;
 } NvmeCmd;
 
+#define NVME_CMD_FLAGS_FUSE(flags) (flags & 0x3)
+#define NVME_CMD_FLAGS_PSDT(flags) ((flags >> 6) & 0x3)
+
 enum NvmeAdminCommands {
     NVME_ADM_CMD_DELETE_SQ      = 0x00,
     NVME_ADM_CMD_CREATE_SQ      = 0x01,
@@ -427,6 +468,11 @@ enum NvmeStatusCodes {
     NVME_CMD_ABORT_MISSING_FUSE = 0x000a,
     NVME_INVALID_NSID           = 0x000b,
     NVME_CMD_SEQ_ERROR          = 0x000c,
+    NVME_INVALID_SGL_SEG_DESCRIPTOR  = 0x000d,
+    NVME_INVALID_NUM_SGL_DESCRIPTORS = 0x000e,
+    NVME_DATA_SGL_LENGTH_INVALID     = 0x000f,
+    NVME_METADATA_SGL_LENGTH_INVALID = 0x0010,
+    NVME_SGL_DESCRIPTOR_TYPE_INVALID = 0x0011,
     NVME_INVALID_USE_OF_CMB     = 0x0012,
     NVME_LBA_RANGE              = 0x0080,
     NVME_CAP_EXCEEDED           = 0x0081,
@@ -623,6 +669,16 @@ enum NvmeIdCtrlOncs {
 #define NVME_CTRL_CQES_MIN(cqes) ((cqes) & 0xf)
 #define NVME_CTRL_CQES_MAX(cqes) (((cqes) >> 4) & 0xf)
 
+#define NVME_CTRL_SGLS_SUPPORTED(sgls)                 ((sgls) & 0x3)
+#define NVME_CTRL_SGLS_SUPPORTED_NO_ALIGNMENT(sgls)    ((sgls) & (0x1 <<  0))
+#define NVME_CTRL_SGLS_SUPPORTED_DWORD_ALIGNMENT(sgls) ((sgls) & (0x1 <<  1))
+#define NVME_CTRL_SGLS_KEYED(sgls)                     ((sgls) & (0x1 <<  2))
+#define NVME_CTRL_SGLS_BITBUCKET(sgls)                 ((sgls) & (0x1 << 16))
+#define NVME_CTRL_SGLS_MPTR_CONTIGUOUS(sgls)           ((sgls) & (0x1 << 17))
+#define NVME_CTRL_SGLS_EXCESS_LENGTH(sgls)             ((sgls) & (0x1 << 18))
+#define NVME_CTRL_SGLS_MPTR_SGL(sgls)                  ((sgls) & (0x1 << 19))
+#define NVME_CTRL_SGLS_ADDR_OFFSET(sgls)               ((sgls) & (0x1 << 20))
+
 typedef struct NvmeFeatureVal {
     uint32_t    arbitration;
     uint32_t    power_mgmt;