[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v4 05/14] hw/block/nvme: Add support for Namespace Types
From: |
Dmitry Fomichev |
Subject: |
[PATCH v4 05/14] hw/block/nvme: Add support for Namespace Types |
Date: |
Thu, 24 Sep 2020 03:20:12 +0900 |
From: Niklas Cassel <niklas.cassel@wdc.com>
Namespace Types introduce a new command set, "I/O Command Sets",
that allows the host to retrieve the command sets associated with
a namespace. Introduce support for the command set and enable
detection for the NVM Command Set.
The new workflows for identify commands rely heavily on zero-filled
identify structs. E.g., certain CNS commands are defined to return
a zero-filled identify struct when an inactive namespace NSID
is supplied.
Add a helper function in order to avoid code duplication when
reporting zero-filled identify structures.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
---
hw/block/nvme.c | 204 +++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 184 insertions(+), 20 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 96cd520feb..e0f885498d 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -1153,6 +1153,15 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest
*req)
return NVME_SUCCESS;
}
+static uint16_t nvme_rpt_empty_id_struct(NvmeCtrl *n, uint64_t prp1,
+ uint64_t prp2, NvmeRequest *req)
+{
+ uint8_t id[NVME_IDENTIFY_DATA_SIZE] = {};
+
+ return nvme_dma_prp(n, id, sizeof(id), prp1, prp2,
+ DMA_DIRECTION_FROM_DEVICE, req);
+}
+
static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeRequest *req)
{
NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
@@ -1165,6 +1174,21 @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n,
NvmeRequest *req)
prp2, DMA_DIRECTION_FROM_DEVICE, req);
}
+static uint16_t nvme_identify_ctrl_csi(NvmeCtrl *n, NvmeRequest *req)
+{
+ NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
+ uint64_t prp1 = le64_to_cpu(c->prp1);
+ uint64_t prp2 = le64_to_cpu(c->prp2);
+
+ trace_pci_nvme_identify_ctrl_csi(c->csi);
+
+ if (c->csi == NVME_CSI_NVM) {
+ return nvme_rpt_empty_id_struct(n, prp1, prp2, req);
+ }
+
+ return NVME_INVALID_FIELD | NVME_DNR;
+}
+
static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeRequest *req)
{
NvmeNamespace *ns;
@@ -1181,11 +1205,37 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n,
NvmeRequest *req)
}
ns = &n->namespaces[nsid - 1];
+ assert(nsid == ns->nsid);
return nvme_dma_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns), prp1,
prp2, DMA_DIRECTION_FROM_DEVICE, req);
}
+static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req)
+{
+ NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
+ 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);
+
+ trace_pci_nvme_identify_ns_csi(nsid, c->csi);
+
+ if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
+ trace_pci_nvme_err_invalid_ns(nsid, n->num_namespaces);
+ return NVME_INVALID_NSID | NVME_DNR;
+ }
+
+ ns = &n->namespaces[nsid - 1];
+ assert(nsid == ns->nsid);
+
+ if (c->csi == NVME_CSI_NVM) {
+ return nvme_rpt_empty_id_struct(n, prp1, prp2, req);
+ }
+
+ return NVME_INVALID_FIELD | NVME_DNR;
+}
+
static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeRequest *req)
{
NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
@@ -1225,23 +1275,51 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n,
NvmeRequest *req)
return ret;
}
+static uint16_t nvme_identify_nslist_csi(NvmeCtrl *n, NvmeRequest *req)
+{
+ NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
+ static const int data_len = NVME_IDENTIFY_DATA_SIZE;
+ 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 *list;
+ uint16_t ret;
+ int i, j = 0;
+
+ trace_pci_nvme_identify_nslist_csi(min_nsid, c->csi);
+
+ if (c->csi != NVME_CSI_NVM) {
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ list = g_malloc0(data_len);
+ for (i = 0; i < n->num_namespaces; i++) {
+ if (i < min_nsid) {
+ continue;
+ }
+ list[j++] = cpu_to_le32(i + 1);
+ if (j == data_len / sizeof(uint32_t)) {
+ break;
+ }
+ }
+ ret = nvme_dma_prp(n, (uint8_t *)list, data_len, prp1, prp2,
+ DMA_DIRECTION_FROM_DEVICE, req);
+ g_free(list);
+ return ret;
+}
+
static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req)
{
NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
+ 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);
-
- uint8_t list[NVME_IDENTIFY_DATA_SIZE];
-
- struct data {
- struct {
- NvmeIdNsDescr hdr;
- uint8_t v[16];
- } uuid;
- };
-
- struct data *ns_descrs = (struct data *)list;
+ void *buf_ptr;
+ NvmeIdNsDescr *desc;
+ static const int data_len = NVME_IDENTIFY_DATA_SIZE;
+ uint8_t *buf;
+ uint16_t status;
trace_pci_nvme_identify_ns_descr_list(nsid);
@@ -1250,7 +1328,11 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n,
NvmeRequest *req)
return NVME_INVALID_NSID | NVME_DNR;
}
- memset(list, 0x0, sizeof(list));
+ ns = &n->namespaces[nsid - 1];
+ assert(nsid == ns->nsid);
+
+ buf = g_malloc0(data_len);
+ buf_ptr = buf;
/*
* Because the NGUID and EUI64 fields are 0 in the Identify Namespace data
@@ -1258,12 +1340,44 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl
*n, NvmeRequest *req)
* Namespace Identification Descriptor. Add a very basic Namespace UUID
* here.
*/
- ns_descrs->uuid.hdr.nidt = NVME_NIDT_UUID;
- ns_descrs->uuid.hdr.nidl = NVME_NIDL_UUID;
- stl_be_p(&ns_descrs->uuid.v, nsid);
+ desc = buf_ptr;
+ desc->nidt = NVME_NIDT_UUID;
+ desc->nidl = NVME_NIDL_UUID;
+ buf_ptr += sizeof(*desc);
+ memcpy(buf_ptr, ns->uuid.data, NVME_NIDL_UUID);
+ buf_ptr += NVME_NIDL_UUID;
- return nvme_dma_prp(n, list, NVME_IDENTIFY_DATA_SIZE, prp1, prp2,
- DMA_DIRECTION_FROM_DEVICE, req);
+ desc = buf_ptr;
+ desc->nidt = NVME_NIDT_CSI;
+ desc->nidl = NVME_NIDL_CSI;
+ buf_ptr += sizeof(*desc);
+ *(uint8_t *)buf_ptr = NVME_CSI_NVM;
+
+ status = nvme_dma_prp(n, buf, data_len, prp1, prp2,
+ DMA_DIRECTION_FROM_DEVICE, req);
+ g_free(buf);
+ return status;
+}
+
+static uint16_t nvme_identify_cmd_set(NvmeCtrl *n, NvmeRequest *req)
+{
+ NvmeIdentify *c = (NvmeIdentify *)&req->cmd;
+ uint64_t prp1 = le64_to_cpu(c->prp1);
+ uint64_t prp2 = le64_to_cpu(c->prp2);
+ static const int data_len = NVME_IDENTIFY_DATA_SIZE;
+ uint32_t *list;
+ uint8_t *ptr;
+ uint16_t status;
+
+ trace_pci_nvme_identify_cmd_set();
+
+ list = g_malloc0(data_len);
+ ptr = (uint8_t *)list;
+ NVME_SET_CSI(*ptr, NVME_CSI_NVM);
+ status = nvme_dma_prp(n, (uint8_t *)list, data_len, prp1, prp2,
+ DMA_DIRECTION_FROM_DEVICE, req);
+ g_free(list);
+ return status;
}
static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req)
@@ -1273,12 +1387,20 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest
*req)
switch (le32_to_cpu(c->cns)) {
case NVME_ID_CNS_NS:
return nvme_identify_ns(n, req);
+ case NVME_ID_CNS_CS_NS:
+ return nvme_identify_ns_csi(n, req);
case NVME_ID_CNS_CTRL:
return nvme_identify_ctrl(n, req);
+ case NVME_ID_CNS_CS_CTRL:
+ return nvme_identify_ctrl_csi(n, req);
case NVME_ID_CNS_NS_ACTIVE_LIST:
return nvme_identify_nslist(n, req);
+ case NVME_ID_CNS_CS_NS_ACTIVE_LIST:
+ return nvme_identify_nslist_csi(n, req);
case NVME_ID_CNS_NS_DESCR_LIST:
return nvme_identify_ns_descr_list(n, req);
+ case NVME_ID_CNS_IO_COMMAND_SET:
+ return nvme_identify_cmd_set(n, req);
default:
trace_pci_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
return NVME_INVALID_FIELD | NVME_DNR;
@@ -1460,6 +1582,9 @@ defaults:
result |= NVME_INTVC_NOCOALESCING;
}
+ break;
+ case NVME_COMMAND_SET_PROFILE:
+ result = 0;
break;
default:
result = nvme_feature_default[fid];
@@ -1584,6 +1709,12 @@ static uint16_t nvme_set_feature(NvmeCtrl *n,
NvmeRequest *req)
break;
case NVME_TIMESTAMP:
return nvme_set_feature_timestamp(n, req);
+ case NVME_COMMAND_SET_PROFILE:
+ if (dw11 & 0x1ff) {
+ trace_pci_nvme_err_invalid_iocsci(dw11 & 0x1ff);
+ return NVME_CMD_SET_CMB_REJECTED | NVME_DNR;
+ }
+ break;
default:
return NVME_FEAT_NOT_CHANGEABLE | NVME_DNR;
}
@@ -1845,6 +1976,30 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset,
uint64_t data,
break;
case 0x14: /* CC */
trace_pci_nvme_mmio_cfg(data & 0xffffffff);
+
+ if (NVME_CC_CSS(data) != NVME_CC_CSS(n->bar.cc)) {
+ if (NVME_CC_EN(n->bar.cc)) {
+ NVME_GUEST_ERR(pci_nvme_err_change_css_when_enabled,
+ "changing selected command set when enabled");
+ } else {
+ switch (NVME_CC_CSS(data)) {
+ case CSS_NVM_ONLY:
+ trace_pci_nvme_css_nvm_cset_selected_by_host(data &
+ 0xffffffff);
+ break;
+ case CSS_CSI:
+ NVME_SET_CC_CSS(n->bar.cc, CSS_CSI);
+ trace_pci_nvme_css_all_csets_sel_by_host(data &
0xffffffff);
+ break;
+ case CSS_ADMIN_ONLY:
+ break;
+ default:
+ NVME_GUEST_ERR(pci_nvme_ub_unknown_css_value,
+ "unknown value in CC.CSS field");
+ }
+ }
+ }
+
/* Windows first sends data, then sends enable bit */
if (!NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc) &&
!NVME_CC_SHN(data) && !NVME_CC_SHN(n->bar.cc))
@@ -2255,6 +2410,8 @@ static void nvme_init_namespace(NvmeCtrl *n,
NvmeNamespace *ns, Error **errp)
n->ns_size = bs_size;
+ ns->csi = NVME_CSI_NVM;
+ qemu_uuid_generate(&ns->uuid); /* TODO make UUIDs persistent */
lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas);
id_ns->lbaf[lba_index].ds = 31 - clz32(n->conf.logical_block_size);
id_ns->nsze = cpu_to_le64(nvme_ns_nlbas(n, ns));
@@ -2419,7 +2576,11 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice
*pci_dev)
NVME_CAP_SET_MQES(n->bar.cap, 0x7ff);
NVME_CAP_SET_CQR(n->bar.cap, 1);
NVME_CAP_SET_TO(n->bar.cap, 0xf);
- NVME_CAP_SET_CSS(n->bar.cap, 1);
+ /*
+ * The device now always supports NS Types, but all commands
+ * that support CSI field will only handle NVM Command Set.
+ */
+ NVME_CAP_SET_CSS(n->bar.cap, (CAP_CSS_NVM | CAP_CSS_CSI_SUPP));
NVME_CAP_SET_MPSMAX(n->bar.cap, 4);
n->bar.vs = NVME_SPEC_VER;
@@ -2429,6 +2590,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice
*pci_dev)
static void nvme_realize(PCIDevice *pci_dev, Error **errp)
{
NvmeCtrl *n = NVME(pci_dev);
+ NvmeNamespace *ns;
Error *local_err = NULL;
int i;
@@ -2454,8 +2616,10 @@ static void nvme_realize(PCIDevice *pci_dev, Error
**errp)
nvme_init_ctrl(n, pci_dev);
- for (i = 0; i < n->num_namespaces; i++) {
- nvme_init_namespace(n, &n->namespaces[i], &local_err);
+ ns = n->namespaces;
+ for (i = 0; i < n->num_namespaces; i++, ns++) {
+ ns->nsid = i + 1;
+ nvme_init_namespace(n, ns, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
--
2.21.0
- [PATCH v4 01/14] hw/block/nvme: Report actual LBA data shift in LBAF, (continued)
[PATCH v4 07/14] hw/block/nvme: Make Zoned NS Command Set definitions, Dmitry Fomichev, 2020/09/23
[PATCH v4 05/14] hw/block/nvme: Add support for Namespace Types,
Dmitry Fomichev <=
[PATCH v4 08/14] hw/block/nvme: Define Zoned NS Command Set trace events, Dmitry Fomichev, 2020/09/23
[PATCH v4 10/14] hw/block/nvme: Introduce max active and open zone limits, Dmitry Fomichev, 2020/09/23
[PATCH v4 12/14] hw/block/nvme: Add injection of Offline/Read-Only zones, Dmitry Fomichev, 2020/09/23
[PATCH v4 09/14] hw/block/nvme: Support Zoned Namespace Command Set, Dmitry Fomichev, 2020/09/23
[PATCH v4 11/14] hw/block/nvme: Support Zone Descriptor Extensions, Dmitry Fomichev, 2020/09/23
[PATCH v4 13/14] hw/block/nvme: Use zone metadata file for persistence, Dmitry Fomichev, 2020/09/23
[PATCH v4 14/14] hw/block/nvme: Document zoned parameters in usage text, Dmitry Fomichev, 2020/09/23
Re: [PATCH v4 00/14] hw/block/nvme: Support Namespace Types and Zoned Namespace Command Set, Klaus Jensen, 2020/09/24