[PATCH 4/4] qemu-kvm: MSI-X MMIO support for assigned device

[Sheng Yang <sheng@linux.intel.com>]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 hw/device-assignment.c |  106 +++++++++++++++++++++++++++++++++++++++++------
 hw/device-assignment.h |    3 +
 qemu-kvm.c             |   46 +++++++++++++++++++++
 qemu-kvm.h             |   19 +++++++++
 4 files changed, 160 insertions(+), 14 deletions(-)

diff --git a/hw/device-assignment.c b/hw/device-assignment.c
index 5c162c4..09e3b99 100644
--- a/hw/device-assignment.c
+++ b/hw/device-assignment.c
@@ -71,6 +71,11 @@ static void assigned_device_pci_cap_write_config(PCIDevice *pci_dev,
 static uint32_t assigned_device_pci_cap_read_config(PCIDevice *pci_dev,
                                                     uint32_t address, int len);
 
+static uint32_t calc_assigned_dev_id(uint16_t seg, uint8_t bus, uint8_t devfn)
+{
+    return (uint32_t)seg << 16 | (uint32_t)bus << 8 | (uint32_t)devfn;
+}
+
 static uint32_t assigned_dev_ioport_rw(AssignedDevRegion *dev_region,
                                        uint32_t addr, int len, uint32_t *val)
 {
@@ -274,6 +279,10 @@ static void assigned_dev_iomem_map(PCIDevice *pci_dev, int region_num,
     AssignedDevRegion *region = &r_dev->v_addrs[region_num];
     PCIRegion *real_region = &r_dev->real_device.regions[region_num];
     int ret = 0;
+#ifdef KVM_CAP_MSIX_MMIO
+    int cap_mask = kvm_check_extension(kvm_state, KVM_CAP_MSIX_MMIO);
+    struct kvm_msix_mmio_user msix_mmio;
+#endif
 
     DEBUG("e_phys=%08" FMT_PCIBUS " r_virt=%p type=%d len=%08" FMT_PCIBUS " region_num=%d \n",
           e_phys, region->u.r_virtbase, type, e_size, region_num);
@@ -292,6 +301,23 @@ static void assigned_dev_iomem_map(PCIDevice *pci_dev, int region_num,
 
             cpu_register_physical_memory(e_phys + offset,
                     TARGET_PAGE_SIZE, r_dev->mmio_index);
+#ifdef KVM_CAP_MSIX_MMIO
+            if (cap_mask) {
+                r_dev->guest_msix_table_addr = e_phys + offset;
+                memset(&msix_mmio, 0, sizeof msix_mmio);
+                msix_mmio.dev_id = calc_assigned_dev_id(r_dev->h_segnr,
+                        r_dev->h_busnr, r_dev->h_devfn);
+                msix_mmio.type = KVM_MSIX_MMIO_TYPE_ASSIGNED_DEV |
+				KVM_MSIX_MMIO_TYPE_BASE_TABLE;
+                msix_mmio.base_addr = e_phys + offset;
+                msix_mmio.base_va = (unsigned long)r_dev->msix_table_page;
+                msix_mmio.max_entries_nr = r_dev->max_msix_entries_nr;
+                msix_mmio.flags = 0;
+                ret = kvm_register_msix_mmio(kvm_context, &msix_mmio);
+                if (ret)
+                    fprintf(stderr, "fail to register in-kernel msix_mmio!\n");
+            }
+#endif
         }
     }
 
@@ -854,11 +880,6 @@ static void free_assigned_device(AssignedDevice *dev)
     }
 }
 
-static uint32_t calc_assigned_dev_id(uint16_t seg, uint8_t bus, uint8_t devfn)
-{
-    return (uint32_t)seg << 16 | (uint32_t)bus << 8 | (uint32_t)devfn;
-}
-
 static void assign_failed_examine(AssignedDevice *dev)
 {
     char name[PATH_MAX], dir[PATH_MAX], driver[PATH_MAX] = {}, *ns;
@@ -1268,6 +1289,9 @@ static int assigned_dev_update_msix_mmio(PCIDevice *pci_dev,
     return r;
 }
 
+static int assigned_dev_update_routing_handler(void *opaque,
+                                    struct kvm_msix_routing_data *data);
+
 static void assigned_dev_update_msix(PCIDevice *pci_dev, unsigned int ctrl_pos)
 {
     struct kvm_assigned_irq assigned_irq_data;
@@ -1494,7 +1518,9 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev)
         msix_table_entry = pci_get_long(pci_dev->config + pos + PCI_MSIX_TABLE);
         bar_nr = msix_table_entry & PCI_MSIX_BIR;
         msix_table_entry &= ~PCI_MSIX_BIR;
-        dev->msix_table_addr = pci_region[bar_nr].base_addr + msix_table_entry;
+        dev->msix_table_addr = pci_region[bar_nr].base_addr +
+                               msix_table_entry;
+
         dev->max_msix_entries_nr = get_msix_entries_max_nr(dev);
     }
 #endif
@@ -1678,11 +1704,10 @@ static uint32_t msix_mmio_readw(void *opaque, target_phys_addr_t addr)
             (8 * (addr & 3))) & 0xffff;
 }
 
-static void msix_mmio_writel(void *opaque,
-                             target_phys_addr_t addr, uint32_t val)
+static void assigned_dev_update_routing(void *opaque,
+                    struct kvm_msix_routing_data *data)
 {
     AssignedDevice *adev = opaque;
-    unsigned int offset = addr & 0xfff;
     void *page = adev->msix_table_page;
     int ctrl_word, index;
     struct kvm_irq_routing_entry new_entry = {};
@@ -1691,11 +1716,7 @@ static void msix_mmio_writel(void *opaque,
     struct PCIDevice *pci_dev = &adev->dev;
     uint8_t cap = pci_find_capability(pci_dev, PCI_CAP_ID_MSIX);
 
-    DEBUG("write to MSI-X entry table mmio offset 0x%lx, val 0x%x\n",
-		    addr, val);
-    memcpy((void *)((char *)page + offset), &val, 4);
-
-    index = offset / 16;
+    index = data->entry_idx;
 
     /* Check if mask bit is being accessed */
     memcpy(&msg_addr, (char *)page + index * 16, 4);
@@ -1770,6 +1791,49 @@ static void msix_mmio_writel(void *opaque,
     adev->entry[entry_idx].u.msi.data = msg_data;
 }
 
+static int assigned_dev_update_routing_handler(void *opaque,
+                                    struct kvm_msix_routing_data *data)
+{
+    AssignedDevice *adev = opaque;
+
+    if (data->type == KVM_MSIX_MMIO_TYPE_ASSIGNED_DEV &&
+        data->dev_id == calc_assigned_dev_id(adev->h_segnr,
+                        adev->h_busnr, adev->h_devfn)) {
+        assigned_dev_update_routing(opaque, data);
+        return 0;
+    }
+    return -EINVAL;
+}
+
+static void msix_mmio_writel(void *opaque,
+                             target_phys_addr_t addr, uint32_t val)
+{
+    AssignedDevice *adev = opaque;
+    void *page = adev->msix_table_page;
+    unsigned int offset = addr & 0xfff;
+    struct kvm_msix_routing_data data;
+#ifdef KVM_CAP_MSIX_MMIO
+    int cap_mask = kvm_check_extension(kvm_state, KVM_CAP_MSIX_MMIO);
+#else
+    int cap_mask = 0;
+#endif
+
+    DEBUG("write to MSI-X entry table mmio offset 0x%lx, val 0x%x\n",
+            addr, val);
+    if (!cap_mask) {
+        memcpy((void *)((char *)page + offset), &val, 4);
+    } else {
+        fprintf(stderr, "msix_mmio_writel: shouldn't be here with KVM_CAP_MSIX_MMIO!\n");
+    }
+
+    data.dev_id = calc_assigned_dev_id(adev->h_segnr, adev->h_busnr,
+                                       adev->h_devfn);
+    data.type = KVM_MSIX_MMIO_TYPE_ASSIGNED_DEV;
+    data.entry_idx = offset / 16;
+    data.flags = 0;
+    assigned_dev_update_routing(opaque, &data);
+}
+
 static void msix_mmio_writew(void *opaque,
                              target_phys_addr_t addr, uint32_t val)
 {
@@ -1811,7 +1875,17 @@ static int assigned_dev_register_msix_mmio(AssignedDevice *dev)
                         DEVICE_NATIVE_ENDIAN);
     dev->dev.msix_entry_used = qemu_mallocz(KVM_MAX_MSIX_PER_DEV *
                                         sizeof *dev->dev.msix_entry_used);
+    dev->routing_updater_entry =
+        kvm_add_routing_updater(assigned_dev_update_routing_handler, dev);
+    if (!dev->routing_updater_entry) {
+        perror("kvm_add_routing_updater");
+	goto out;
+    }
     return 0;
+out:
+    free(dev->dev.msix_entry_used);
+    munmap(dev->msix_table_page, 0x1000);
+    return -EFAULT;
 }
 
 static void assigned_dev_unregister_msix_mmio(AssignedDevice *dev)
@@ -1827,6 +1901,10 @@ static void assigned_dev_unregister_msix_mmio(AssignedDevice *dev)
                 strerror(errno));
     }
     dev->msix_table_page = NULL;
+    if (dev->routing_updater_entry) {
+        kvm_del_routing_updater(dev->routing_updater_entry);
+        dev->routing_updater_entry = NULL;
+    }
     free(dev->dev.msix_entry_used);
     dev->dev.msix_entry_used = NULL;
 }
diff --git a/hw/device-assignment.h b/hw/device-assignment.h
index d92606e..1716738 100644
--- a/hw/device-assignment.h
+++ b/hw/device-assignment.h
@@ -32,6 +32,7 @@
 #include "qemu-common.h"
 #include "qemu-queue.h"
 #include "pci.h"
+#include "qemu-kvm.h"
 
 /* From include/linux/pci.h in the kernel sources */
 #define PCI_DEVFN(slot, func)   ((((slot) & 0x1f) << 3) | ((func) & 0x07))
@@ -108,10 +109,12 @@ typedef struct AssignedDevice {
     struct kvm_irq_routing_entry *entry;
     void *msix_table_page;
     target_phys_addr_t msix_table_addr;
+    target_phys_addr_t guest_msix_table_addr;
     int mmio_index;
     int need_emulate_cmd;
     char *configfd_name;
     int32_t bootindex;
+    KVMRoutingUpdateEntry *routing_updater_entry;
     QLIST_ENTRY(AssignedDevice) next;
 } AssignedDevice;
 
diff --git a/qemu-kvm.c b/qemu-kvm.c
index d282c95..e4d100f 100644
--- a/qemu-kvm.c
+++ b/qemu-kvm.c
@@ -511,6 +511,46 @@ static int handle_mmio(CPUState *env)
     return 0;
 }
 
+static QLIST_HEAD(kvm_routing_update_entry_head, kvm_routing_update_entry) kvm_routing_update_entry_head;
+
+KVMRoutingUpdateEntry *kvm_add_routing_updater(KVMRoutingUpdateHandler *cb, void *opaque)
+{
+    KVMRoutingUpdateEntry *e;
+
+    e = qemu_mallocz(sizeof (*e));
+
+    e->cb = cb;
+    e->opaque = opaque;
+    QLIST_INSERT_HEAD(&kvm_routing_update_entry_head, e, entries);
+    return e;
+}
+
+void kvm_del_routing_updater(KVMRoutingUpdateEntry *e)
+{
+    QLIST_REMOVE(e, entries);
+    qemu_free(e);
+}
+
+#ifdef KVM_CAP_MSIX_MMIO
+static void kvm_update_msix_routing(CPUState *env)
+{
+    struct kvm_msix_routing_data data;
+    KVMRoutingUpdateEntry *e;
+
+    data.dev_id = env->kvm_run->msix_routing.dev_id;
+    data.type = env->kvm_run->msix_routing.type;
+    data.entry_idx = env->kvm_run->msix_routing.entry_idx;
+    data.flags = env->kvm_run->msix_routing.flags;
+    for (e = kvm_routing_update_entry_head.lh_first; e; e = e->entries.le_next) {
+        if (e->cb(e->opaque, &data) == 0)
+            return;
+    }
+    fprintf(stderr, "unhandled MSI-X routing update: "
+            "dev 0x%x, type %d, entry 0x%x, flags 0x%lx\n",
+            data.dev_id, data.type, data.entry_idx, data.flags);
+}
+#endif
+
 int handle_io_window(kvm_context_t kvm)
 {
     return 1;
@@ -647,6 +687,12 @@ int kvm_run(CPUState *env)
             kvm_handle_internal_error(env, run);
             r = 1;
 	    break;
+#ifdef KVM_CAP_MSIX_MMIO
+        case KVM_EXIT_MSIX_ROUTING_UPDATE:
+            kvm_update_msix_routing(env);
+            r = 1;
+            break;
+#endif
         default:
             if (kvm_arch_run(env)) {
                 fprintf(stderr, "unhandled vm exit: 0x%x\n", run->exit_reason);
diff --git a/qemu-kvm.h b/qemu-kvm.h
index 48ff52d..11a62c7 100644
--- a/qemu-kvm.h
+++ b/qemu-kvm.h
@@ -773,6 +773,25 @@ int kvm_tpr_enable_vapic(CPUState *env);
 unsigned long kvm_get_thread_id(void);
 int kvm_cpu_is_stopped(CPUState *env);
 
+struct kvm_msix_routing_data {
+	uint32_t dev_id;
+	uint16_t type;
+	uint16_t entry_idx;
+	uint64_t flags;
+};
+
+typedef struct kvm_routing_update_entry KVMRoutingUpdateEntry;
+typedef int KVMRoutingUpdateHandler(void *opaque,
+				    struct kvm_msix_routing_data *data);
+
+struct kvm_routing_update_entry {
+    KVMRoutingUpdateHandler *cb;
+    void *opaque;
+    QLIST_ENTRY (kvm_routing_update_entry) entries;
+};
+
+KVMRoutingUpdateEntry *kvm_add_routing_updater(KVMRoutingUpdateHandler *cb, void *opaque);
+void kvm_del_routing_updater(KVMRoutingUpdateEntry *e);
 #endif
 
 #endif
-- 
1.7.0.1