hw/nvme: Add support for the Virtualization Management command

With the new command one can:
 - assign flexible resources (queues, interrupts) to primary and
   secondary controllers,
 - toggle the online/offline state of given controller.

Signed-off-by: Łukasz Gieryk <lukasz.gieryk@linux.intel.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>

1 files changed, 255 insertions, 2 deletions

diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index 3728813e90..20f1a73995 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -188,6 +188,7 @@
 #include "qemu/error-report.h"
 #include "qemu/log.h"
 #include "qemu/units.h"
+#include "qemu/range.h"
 #include "qapi/error.h"
 #include "qapi/visitor.h"
 #include "sysemu/sysemu.h"
@@ -262,6 +263,7 @@ static const uint32_t nvme_cse_acs[256] = {
     [NVME_ADM_CMD_GET_FEATURES]     = NVME_CMD_EFF_CSUPP,
     [NVME_ADM_CMD_ASYNC_EV_REQ]     = NVME_CMD_EFF_CSUPP,
     [NVME_ADM_CMD_NS_ATTACHMENT]    = NVME_CMD_EFF_CSUPP | NVME_CMD_EFF_NIC,
+    [NVME_ADM_CMD_VIRT_MNGMT]       = NVME_CMD_EFF_CSUPP,
     [NVME_ADM_CMD_FORMAT_NVM]       = NVME_CMD_EFF_CSUPP | NVME_CMD_EFF_LBCC,
 };
 
@@ -293,6 +295,7 @@ static const uint32_t nvme_cse_iocs_zoned[256] = {
 };
 
 static void nvme_process_sq(void *opaque);
+static void nvme_ctrl_reset(NvmeCtrl *n, NvmeResetType rst);
 
 static uint16_t nvme_sqid(NvmeRequest *req)
 {
@@ -5840,6 +5843,167 @@ out:
     return status;
 }
 
+static void nvme_get_virt_res_num(NvmeCtrl *n, uint8_t rt, int *num_total,
+                                  int *num_prim, int *num_sec)
+{
+    *num_total = le32_to_cpu(rt ?
+                             n->pri_ctrl_cap.vifrt : n->pri_ctrl_cap.vqfrt);
+    *num_prim = le16_to_cpu(rt ?
+                            n->pri_ctrl_cap.virfap : n->pri_ctrl_cap.vqrfap);
+    *num_sec = le16_to_cpu(rt ? n->pri_ctrl_cap.virfa : n->pri_ctrl_cap.vqrfa);
+}
+
+static uint16_t nvme_assign_virt_res_to_prim(NvmeCtrl *n, NvmeRequest *req,
+                                             uint16_t cntlid, uint8_t rt,
+                                             int nr)
+{
+    int num_total, num_prim, num_sec;
+
+    if (cntlid != n->cntlid) {
+        return NVME_INVALID_CTRL_ID | NVME_DNR;
+    }
+
+    nvme_get_virt_res_num(n, rt, &num_total, &num_prim, &num_sec);
+
+    if (nr > num_total) {
+        return NVME_INVALID_NUM_RESOURCES | NVME_DNR;
+    }
+
+    if (nr > num_total - num_sec) {
+        return NVME_INVALID_RESOURCE_ID | NVME_DNR;
+    }
+
+    if (rt) {
+        n->next_pri_ctrl_cap.virfap = cpu_to_le16(nr);
+    } else {
+        n->next_pri_ctrl_cap.vqrfap = cpu_to_le16(nr);
+    }
+
+    req->cqe.result = cpu_to_le32(nr);
+    return req->status;
+}
+
+static void nvme_update_virt_res(NvmeCtrl *n, NvmeSecCtrlEntry *sctrl,
+                                 uint8_t rt, int nr)
+{
+    int prev_nr, prev_total;
+
+    if (rt) {
+        prev_nr = le16_to_cpu(sctrl->nvi);
+        prev_total = le32_to_cpu(n->pri_ctrl_cap.virfa);
+        sctrl->nvi = cpu_to_le16(nr);
+        n->pri_ctrl_cap.virfa = cpu_to_le32(prev_total + nr - prev_nr);
+    } else {
+        prev_nr = le16_to_cpu(sctrl->nvq);
+        prev_total = le32_to_cpu(n->pri_ctrl_cap.vqrfa);
+        sctrl->nvq = cpu_to_le16(nr);
+        n->pri_ctrl_cap.vqrfa = cpu_to_le32(prev_total + nr - prev_nr);
+    }
+}
+
+static uint16_t nvme_assign_virt_res_to_sec(NvmeCtrl *n, NvmeRequest *req,
+                                            uint16_t cntlid, uint8_t rt, int nr)
+{
+    int num_total, num_prim, num_sec, num_free, diff, limit;
+    NvmeSecCtrlEntry *sctrl;
+
+    sctrl = nvme_sctrl_for_cntlid(n, cntlid);
+    if (!sctrl) {
+        return NVME_INVALID_CTRL_ID | NVME_DNR;
+    }
+
+    if (sctrl->scs) {
+        return NVME_INVALID_SEC_CTRL_STATE | NVME_DNR;
+    }
+
+    limit = le16_to_cpu(rt ? n->pri_ctrl_cap.vifrsm : n->pri_ctrl_cap.vqfrsm);
+    if (nr > limit) {
+        return NVME_INVALID_NUM_RESOURCES | NVME_DNR;
+    }
+
+    nvme_get_virt_res_num(n, rt, &num_total, &num_prim, &num_sec);
+    num_free = num_total - num_prim - num_sec;
+    diff = nr - le16_to_cpu(rt ? sctrl->nvi : sctrl->nvq);
+
+    if (diff > num_free) {
+        return NVME_INVALID_RESOURCE_ID | NVME_DNR;
+    }
+
+    nvme_update_virt_res(n, sctrl, rt, nr);
+    req->cqe.result = cpu_to_le32(nr);
+
+    return req->status;
+}
+
+static uint16_t nvme_virt_set_state(NvmeCtrl *n, uint16_t cntlid, bool online)
+{
+    NvmeCtrl *sn = NULL;
+    NvmeSecCtrlEntry *sctrl;
+    int vf_index;
+
+    sctrl = nvme_sctrl_for_cntlid(n, cntlid);
+    if (!sctrl) {
+        return NVME_INVALID_CTRL_ID | NVME_DNR;
+    }
+
+    if (!pci_is_vf(&n->parent_obj)) {
+        vf_index = le16_to_cpu(sctrl->vfn) - 1;
+        sn = NVME(pcie_sriov_get_vf_at_index(&n->parent_obj, vf_index));
+    }
+
+    if (online) {
+        if (!sctrl->nvi || (le16_to_cpu(sctrl->nvq) < 2) || !sn) {
+            return NVME_INVALID_SEC_CTRL_STATE | NVME_DNR;
+        }
+
+        if (!sctrl->scs) {
+            sctrl->scs = 0x1;
+            nvme_ctrl_reset(sn, NVME_RESET_FUNCTION);
+        }
+    } else {
+        nvme_update_virt_res(n, sctrl, NVME_VIRT_RES_INTERRUPT, 0);
+        nvme_update_virt_res(n, sctrl, NVME_VIRT_RES_QUEUE, 0);
+
+        if (sctrl->scs) {
+            sctrl->scs = 0x0;
+            if (sn) {
+                nvme_ctrl_reset(sn, NVME_RESET_FUNCTION);
+            }
+        }
+    }
+
+    return NVME_SUCCESS;
+}
+
+static uint16_t nvme_virt_mngmt(NvmeCtrl *n, NvmeRequest *req)
+{
+    uint32_t dw10 = le32_to_cpu(req->cmd.cdw10);
+    uint32_t dw11 = le32_to_cpu(req->cmd.cdw11);
+    uint8_t act = dw10 & 0xf;
+    uint8_t rt = (dw10 >> 8) & 0x7;
+    uint16_t cntlid = (dw10 >> 16) & 0xffff;
+    int nr = dw11 & 0xffff;
+
+    trace_pci_nvme_virt_mngmt(nvme_cid(req), act, cntlid, rt ? "VI" : "VQ", nr);
+
+    if (rt != NVME_VIRT_RES_QUEUE && rt != NVME_VIRT_RES_INTERRUPT) {
+        return NVME_INVALID_RESOURCE_ID | NVME_DNR;
+    }
+
+    switch (act) {
+    case NVME_VIRT_MNGMT_ACTION_SEC_ASSIGN:
+        return nvme_assign_virt_res_to_sec(n, req, cntlid, rt, nr);
+    case NVME_VIRT_MNGMT_ACTION_PRM_ALLOC:
+        return nvme_assign_virt_res_to_prim(n, req, cntlid, rt, nr);
+    case NVME_VIRT_MNGMT_ACTION_SEC_ONLINE:
+        return nvme_virt_set_state(n, cntlid, true);
+    case NVME_VIRT_MNGMT_ACTION_SEC_OFFLINE:
+        return nvme_virt_set_state(n, cntlid, false);
+    default:
+        return NVME_INVALID_FIELD | NVME_DNR;
+    }
+}
+
 static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req)
 {
     trace_pci_nvme_admin_cmd(nvme_cid(req), nvme_sqid(req), req->cmd.opcode,
@@ -5882,6 +6046,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req)
         return nvme_aer(n, req);
     case NVME_ADM_CMD_NS_ATTACHMENT:
         return nvme_ns_attachment(n, req);
+    case NVME_ADM_CMD_VIRT_MNGMT:
+        return nvme_virt_mngmt(n, req);
     case NVME_ADM_CMD_FORMAT_NVM:
         return nvme_format(n, req);
     default:
@@ -5943,9 +6109,33 @@ static void nvme_update_msixcap_ts(PCIDevice *pci_dev, uint32_t table_size)
                          table_size - 1);
 }
 
+static void nvme_activate_virt_res(NvmeCtrl *n)
+{
+    PCIDevice *pci_dev = &n->parent_obj;
+    NvmePriCtrlCap *cap = &n->pri_ctrl_cap;
+    NvmeSecCtrlEntry *sctrl;
+
+    /* -1 to account for the admin queue */
+    if (pci_is_vf(pci_dev)) {
+        sctrl = nvme_sctrl(n);
+        cap->vqprt = sctrl->nvq;
+        cap->viprt = sctrl->nvi;
+        n->conf_ioqpairs = sctrl->nvq ? le16_to_cpu(sctrl->nvq) - 1 : 0;
+        n->conf_msix_qsize = sctrl->nvi ? le16_to_cpu(sctrl->nvi) : 1;
+    } else {
+        cap->vqrfap = n->next_pri_ctrl_cap.vqrfap;
+        cap->virfap = n->next_pri_ctrl_cap.virfap;
+        n->conf_ioqpairs = le16_to_cpu(cap->vqprt) +
+                           le16_to_cpu(cap->vqrfap) - 1;
+        n->conf_msix_qsize = le16_to_cpu(cap->viprt) +
+                             le16_to_cpu(cap->virfap);
+    }
+}
+
 static void nvme_ctrl_reset(NvmeCtrl *n, NvmeResetType rst)
 {
     PCIDevice *pci_dev = &n->parent_obj;
+    NvmeSecCtrlEntry *sctrl;
     NvmeNamespace *ns;
     int i;
 
@@ -5975,9 +6165,20 @@ static void nvme_ctrl_reset(NvmeCtrl *n, NvmeResetType rst)
         g_free(event);
     }
 
-    if (!pci_is_vf(pci_dev) && n->params.sriov_max_vfs) {
+    if (n->params.sriov_max_vfs) {
+        if (!pci_is_vf(pci_dev)) {
+            for (i = 0; i < n->sec_ctrl_list.numcntl; i++) {
+                sctrl = &n->sec_ctrl_list.sec[i];
+                nvme_virt_set_state(n, le16_to_cpu(sctrl->scid), false);
+            }
+
+            if (rst != NVME_RESET_CONTROLLER) {
+                pcie_sriov_pf_disable_vfs(pci_dev);
+            }
+        }
+
         if (rst != NVME_RESET_CONTROLLER) {
-            pcie_sriov_pf_disable_vfs(pci_dev);
+            nvme_activate_virt_res(n);
         }
     }
 
@@ -5986,6 +6187,13 @@ static void nvme_ctrl_reset(NvmeCtrl *n, NvmeResetType rst)
     n->qs_created = false;
 
     nvme_update_msixcap_ts(pci_dev, n->conf_msix_qsize);
+
+    if (pci_is_vf(pci_dev)) {
+        sctrl = nvme_sctrl(n);
+        stl_le_p(&n->bar.csts, sctrl->scs ? 0 : NVME_CSTS_FAILED);
+    } else {
+        stl_le_p(&n->bar.csts, 0);
+    }
 }
 
 static void nvme_ctrl_shutdown(NvmeCtrl *n)
@@ -6031,7 +6239,15 @@ static int nvme_start_ctrl(NvmeCtrl *n)
     uint64_t acq = ldq_le_p(&n->bar.acq);
     uint32_t page_bits = NVME_CC_MPS(cc) + 12;
     uint32_t page_size = 1 << page_bits;
+    NvmeSecCtrlEntry *sctrl = nvme_sctrl(n);
 
+    if (pci_is_vf(&n->parent_obj) && !sctrl->scs) {
+        trace_pci_nvme_err_startfail_virt_state(le16_to_cpu(sctrl->nvi),
+                                                le16_to_cpu(sctrl->nvq),
+                                                sctrl->scs ? "ONLINE" :
+                                                             "OFFLINE");
+        return -1;
+    }
     if (unlikely(n->cq[0])) {
         trace_pci_nvme_err_startfail_cq();
         return -1;
@@ -6414,6 +6630,12 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size)
         return 0;
     }
 
+    if (pci_is_vf(&n->parent_obj) && !nvme_sctrl(n)->scs &&
+        addr != NVME_REG_CSTS) {
+        trace_pci_nvme_err_ignored_mmio_vf_offline(addr, size);
+        return 0;
+    }
+
     /*
      * When PMRWBM bit 1 is set then read from
      * from PMRSTS should ensure prior writes
@@ -6563,6 +6785,12 @@ static void nvme_mmio_write(void *opaque, hwaddr addr, uint64_t data,
 
     trace_pci_nvme_mmio_write(addr, data, size);
 
+    if (pci_is_vf(&n->parent_obj) && !nvme_sctrl(n)->scs &&
+        addr != NVME_REG_CSTS) {
+        trace_pci_nvme_err_ignored_mmio_vf_offline(addr, size);
+        return;
+    }
+
     if (addr < sizeof(n->bar)) {
         nvme_write_bar(n, addr, data, size);
     } else {
@@ -7297,9 +7525,34 @@ static void nvme_pci_reset(DeviceState *qdev)
     nvme_ctrl_reset(n, NVME_RESET_FUNCTION);
 }
 
+static void nvme_sriov_pre_write_ctrl(PCIDevice *dev, uint32_t address,
+                                      uint32_t val, int len)
+{
+    NvmeCtrl *n = NVME(dev);
+    NvmeSecCtrlEntry *sctrl;
+    uint16_t sriov_cap = dev->exp.sriov_cap;
+    uint32_t off = address - sriov_cap;
+    int i, num_vfs;
+
+    if (!sriov_cap) {
+        return;
+    }
+
+    if (range_covers_byte(off, len, PCI_SRIOV_CTRL)) {
+        if (!(val & PCI_SRIOV_CTRL_VFE)) {
+            num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF);
+            for (i = 0; i < num_vfs; i++) {
+                sctrl = &n->sec_ctrl_list.sec[i];
+                nvme_virt_set_state(n, le16_to_cpu(sctrl->scid), false);
+            }
+        }
+    }
+}
+
 static void nvme_pci_write_config(PCIDevice *dev, uint32_t address,
                                   uint32_t val, int len)
 {
+    nvme_sriov_pre_write_ctrl(dev, address, val, len);
     pci_default_write_config(dev, address, val, len);
     pcie_cap_flr_write_config(dev, address, val, len);
 }