@@ -4545,6 +4545,14 @@ static uint16_t nvme_identify_pri_ctrl_cap(NvmeCtrl *n, NvmeRequest *req)
return nvme_c2h(n, (uint8_t *)&n->pri_ctrl_cap, sizeof(NvmePriCtrlCap), req);
}
+static uint16_t nvme_identify_sec_ctrl_list(NvmeCtrl *n, NvmeRequest *req)
+{
+ trace_pci_nvme_identify_sec_ctrl_list(le16_to_cpu(n->pri_ctrl_cap.cntlid),
+ n->sec_ctrl_list.numcntl);
+
+ return nvme_c2h(n, (uint8_t *)&n->sec_ctrl_list, sizeof(NvmeSecCtrlList), req);
+}
+
static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req,
bool active)
{
@@ -4765,6 +4773,8 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req)
return nvme_identify_ctrl_list(n, req, false);
case NVME_ID_CNS_PRIMARY_CTRL_CAP:
return nvme_identify_pri_ctrl_cap(n, req);
+ case NVME_ID_CNS_SECONDARY_CTRL_LIST:
+ return nvme_identify_sec_ctrl_list(n, req);
case NVME_ID_CNS_CS_NS:
return nvme_identify_ns_csi(n, req, true);
case NVME_ID_CNS_CS_NS_PRESENT:
@@ -6306,6 +6316,9 @@ static void nvme_check_constraints(NvmeCtrl *n, Error **errp)
static void nvme_init_state(NvmeCtrl *n)
{
NvmePriCtrlCap *cap = &n->pri_ctrl_cap;
+ NvmeSecCtrlList *list = &n->sec_ctrl_list;
+ NvmeSecCtrlEntry *sctrl;
+ int i;
/* add one to max_ioqpairs to account for the admin queue pair */
n->reg_size = pow2ceil(sizeof(NvmeBar) +
@@ -6317,6 +6330,12 @@ static void nvme_init_state(NvmeCtrl *n)
n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
n->aer_reqs = g_new0(NvmeRequest *, n->params.aerl + 1);
+ list->numcntl = cpu_to_le16(n->params.sriov_max_vfs);
+ for (i = 0; i < n->params.sriov_max_vfs; i++) {
+ sctrl = &list->sec[i];
+ sctrl->pcid = cpu_to_le16(n->cntlid);
+ }
+
cap->cntlid = cpu_to_le16(n->cntlid);
}
@@ -6362,6 +6381,27 @@ static void nvme_init_pmr(NvmeCtrl *n, PCIDevice *pci_dev)
memory_region_set_enabled(&n->pmr.dev->mr, false);
}
+static void nvme_update_vfs(PCIDevice *pci_dev, uint16_t prev_num_vfs,
+ uint16_t num_vfs)
+{
+ NvmeCtrl *n = NVME(pci_dev);
+ uint16_t num_active_vfs = MAX(prev_num_vfs, num_vfs);
+ bool vf_enable = (prev_num_vfs < num_vfs);
+ uint16_t i;
+
+ /*
+ * As per SR-IOV design,
+ * VF count can only go from 0 to a set value and vice versa.
+ */
+ for (i = 0; i < num_active_vfs; i++) {
+ if (vf_enable) {
+ n->sec_ctrl_list.sec[i].vfn = cpu_to_le16(i + 1);
+ } else {
+ n->sec_ctrl_list.sec[i].vfn = 0;
+ }
+ }
+}
+
static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset,
uint64_t bar_size)
{
@@ -6370,7 +6410,7 @@ static void nvme_init_sriov(NvmeCtrl *n, PCIDevice *pci_dev, uint16_t offset,
pcie_sriov_pf_init(pci_dev, offset, "nvme", vf_dev_id,
n->params.sriov_max_vfs, n->params.sriov_max_vfs,
- NVME_VF_OFFSET, NVME_VF_STRIDE, NULL);
+ NVME_VF_OFFSET, NVME_VF_STRIDE, nvme_update_vfs);
pcie_sriov_pf_init_vf_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
PCI_BASE_ADDRESS_MEM_TYPE_64, bar_size);
@@ -517,7 +517,7 @@ static void nvme_ns_realize(DeviceState *dev, Error **errp)
for (i = 0; i < ARRAY_SIZE(subsys->ctrls); i++) {
NvmeCtrl *ctrl = subsys->ctrls[i];
- if (ctrl) {
+ if (ctrl && ctrl != SUBSYS_SLOT_RSVD) {
nvme_attach_ns(ctrl, ns);
}
}
@@ -24,7 +24,7 @@
#include "block/nvme.h"
-#define NVME_MAX_CONTROLLERS 32
+#define NVME_MAX_CONTROLLERS 256
#define NVME_MAX_NAMESPACES 256
#define NVME_EUI64_DEFAULT ((uint64_t)0x5254000000000000)
@@ -43,6 +43,7 @@ typedef struct NvmeBus {
#define TYPE_NVME_SUBSYS "nvme-subsys"
#define NVME_SUBSYS(obj) \
OBJECT_CHECK(NvmeSubsystem, (obj), TYPE_NVME_SUBSYS)
+#define SUBSYS_SLOT_RSVD (void *)0xFFFF
typedef struct NvmeSubsystem {
DeviceState parent_obj;
@@ -463,6 +464,7 @@ typedef struct NvmeCtrl {
} features;
NvmePriCtrlCap pri_ctrl_cap;
+ NvmeSecCtrlList sec_ctrl_list;
} NvmeCtrl;
static inline NvmeNamespace *nvme_ns(NvmeCtrl *n, uint32_t nsid)
@@ -497,6 +499,18 @@ static inline uint16_t nvme_cid(NvmeRequest *req)
return le16_to_cpu(req->cqe.cid);
}
+static inline NvmeSecCtrlEntry *nvme_sctrl(NvmeCtrl *n)
+{
+ PCIDevice *pci_dev = &n->parent_obj;
+ NvmeCtrl *pf = NVME(pcie_sriov_get_pf(pci_dev));
+
+ if (pci_is_vf(pci_dev)) {
+ return &pf->sec_ctrl_list.sec[pcie_sriov_vf_number(pci_dev)];
+ }
+
+ return NULL;
+}
+
void nvme_attach_ns(NvmeCtrl *n, NvmeNamespace *ns);
uint16_t nvme_bounce_data(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
NvmeTxDirection dir, NvmeRequest *req);
@@ -11,20 +11,71 @@
#include "nvme.h"
-int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp)
+static int nvme_subsys_reserve_cntlids(NvmeCtrl *n, int start, int num)
{
NvmeSubsystem *subsys = n->subsys;
- int cntlid;
+ NvmeSecCtrlList *list = &n->sec_ctrl_list;
+ NvmeSecCtrlEntry *sctrl;
+ int i, cnt = 0;
+
+ for (i = start; i < ARRAY_SIZE(subsys->ctrls) && cnt < num; i++) {
+ if (!subsys->ctrls[i]) {
+ sctrl = &list->sec[cnt];
+ sctrl->scid = cpu_to_le16(i);
+ subsys->ctrls[i] = SUBSYS_SLOT_RSVD;
+ cnt++;
+ }
+ }
+
+ return cnt;
+}
- for (cntlid = 0; cntlid < ARRAY_SIZE(subsys->ctrls); cntlid++) {
- if (!subsys->ctrls[cntlid]) {
- break;
+static void nvme_subsys_unreserve_cntlids(NvmeCtrl *n)
+{
+ NvmeSubsystem *subsys = n->subsys;
+ NvmeSecCtrlList *list = &n->sec_ctrl_list;
+ NvmeSecCtrlEntry *sctrl;
+ int i, cntlid;
+
+ for (i = 0; i < n->params.sriov_max_vfs; i++) {
+ sctrl = &list->sec[i];
+ cntlid = le16_to_cpu(sctrl->scid);
+
+ if (cntlid) {
+ assert(subsys->ctrls[cntlid] == SUBSYS_SLOT_RSVD);
+ subsys->ctrls[cntlid] = NULL;
+ sctrl->scid = 0;
}
}
+}
- if (cntlid == ARRAY_SIZE(subsys->ctrls)) {
- error_setg(errp, "no more free controller id");
- return -1;
+int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp)
+{
+ NvmeSubsystem *subsys = n->subsys;
+ NvmeSecCtrlEntry *sctrl = nvme_sctrl(n);
+ int cntlid, num_rsvd, num_vfs = n->params.sriov_max_vfs;
+
+ if (pci_is_vf(&n->parent_obj)) {
+ cntlid = le16_to_cpu(sctrl->scid);
+ } else {
+ for (cntlid = 0; cntlid < ARRAY_SIZE(subsys->ctrls); cntlid++) {
+ if (!subsys->ctrls[cntlid]) {
+ break;
+ }
+ }
+
+ if (cntlid == ARRAY_SIZE(subsys->ctrls)) {
+ error_setg(errp, "no more free controller id");
+ return -1;
+ }
+
+ num_rsvd = nvme_subsys_reserve_cntlids(n, cntlid + 1, num_vfs);
+ if (num_rsvd != num_vfs) {
+ nvme_subsys_unreserve_cntlids(n);
+ error_setg(errp,
+ "no more free controller ids for secondary controllers");
+ return -1;
+ }
}
subsys->ctrls[cntlid] = n;
@@ -34,7 +85,12 @@ int nvme_subsys_register_ctrl(NvmeCtrl *n, Error **errp)
void nvme_subsys_unregister_ctrl(NvmeSubsystem *subsys, NvmeCtrl *n)
{
- subsys->ctrls[n->cntlid] = NULL;
+ if (pci_is_vf(&n->parent_obj)) {
+ subsys->ctrls[n->cntlid] = SUBSYS_SLOT_RSVD;
+ } else {
+ subsys->ctrls[n->cntlid] = NULL;
+ nvme_subsys_unreserve_cntlids(n);
+ }
}
static void nvme_subsys_setup(NvmeSubsystem *subsys)
@@ -53,6 +53,7 @@ pci_nvme_identify_ctrl_csi(uint8_t csi) "identify controller, csi=0x%"PRIx8""
pci_nvme_identify_ns(uint32_t ns) "nsid %"PRIu32""
pci_nvme_identify_ctrl_list(uint8_t cns, uint16_t cntid) "cns 0x%"PRIx8" cntid %"PRIu16""
pci_nvme_identify_pri_ctrl_cap(uint16_t cntlid) "identify primary controller capabilities cntlid=%"PRIu16""
+pci_nvme_identify_sec_ctrl_list(uint16_t cntlid, uint8_t numcntl) "identify secondary controller list cntlid=%"PRIu16" numcntl=%"PRIu8""
pci_nvme_identify_ns_csi(uint32_t ns, uint8_t csi) "nsid=%"PRIu32", csi=0x%"PRIx8""
pci_nvme_identify_nslist(uint32_t ns) "nsid %"PRIu32""
pci_nvme_identify_nslist_csi(uint16_t ns, uint8_t csi) "nsid=%"PRIu16", csi=0x%"PRIx8""
@@ -1018,6 +1018,7 @@ enum NvmeIdCns {
NVME_ID_CNS_NS_ATTACHED_CTRL_LIST = 0x12,
NVME_ID_CNS_CTRL_LIST = 0x13,
NVME_ID_CNS_PRIMARY_CTRL_CAP = 0x14,
+ NVME_ID_CNS_SECONDARY_CTRL_LIST = 0x15,
NVME_ID_CNS_CS_NS_PRESENT_LIST = 0x1a,
NVME_ID_CNS_CS_NS_PRESENT = 0x1b,
NVME_ID_CNS_IO_COMMAND_SET = 0x1c,
@@ -1487,6 +1488,23 @@ typedef struct QEMU_PACKED NvmePriCtrlCap {
uint8_t rsvd80[4016];
} NvmePriCtrlCap;
+typedef struct QEMU_PACKED NvmeSecCtrlEntry {
+ uint16_t scid;
+ uint16_t pcid;
+ uint8_t scs;
+ uint8_t rsvd5[3];
+ uint16_t vfn;
+ uint16_t nvq;
+ uint16_t nvi;
+ uint8_t rsvd14[18];
+} NvmeSecCtrlEntry;
+
+typedef struct QEMU_PACKED NvmeSecCtrlList {
+ uint8_t numcntl;
+ uint8_t rsvd1[31];
+ NvmeSecCtrlEntry sec[127];
+} NvmeSecCtrlList;
+
static inline void _nvme_check_size(void)
{
QEMU_BUILD_BUG_ON(sizeof(NvmeBar) != 4096);
@@ -1520,5 +1538,7 @@ static inline void _nvme_check_size(void)
QEMU_BUILD_BUG_ON(sizeof(NvmeZoneDescr) != 64);
QEMU_BUILD_BUG_ON(sizeof(NvmeDifTuple) != 8);
QEMU_BUILD_BUG_ON(sizeof(NvmePriCtrlCap) != 4096);
+ QEMU_BUILD_BUG_ON(sizeof(NvmeSecCtrlEntry) != 32);
+ QEMU_BUILD_BUG_ON(sizeof(NvmeSecCtrlList) != 4096);
}
#endif
Introduce handling for Secondary Controller List (Identify command with CNS value of 15h). Secondary controller ids are unique in the subsystem, hence they are reserved by it upon initialization of the primary controller to the number of sriov_max_vfs. ID reservation requires the addition of an intermediate controller slot state, so the reserved controller has the address 0xFFFF. A secondary controller is in the reserved state when it has no virtual function assigned, but its primary controller is realized. Secondary controller reservations are released to NULL when its primary controller is unregistered. Signed-off-by: Lukasz Maniak <lukasz.maniak@linux.intel.com> --- hw/nvme/ctrl.c | 42 ++++++++++++++++++++++++- hw/nvme/ns.c | 2 +- hw/nvme/nvme.h | 16 +++++++++- hw/nvme/subsys.c | 74 ++++++++++++++++++++++++++++++++++++++------ hw/nvme/trace-events | 1 + include/block/nvme.h | 20 ++++++++++++ 6 files changed, 143 insertions(+), 12 deletions(-)