[PATCH 2/4] qemu-kvm: Ioctl for MSIX MMIO support

[PATCH 2/4] qemu-kvm: Ioctl for MSIX MMIO support

[Sheng Yang]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 qemu-kvm.c |   14 ++++++++++++++
 qemu-kvm.h |    7 +++++++
 2 files changed, 21 insertions(+), 0 deletions(-)

diff --git a/qemu-kvm.c b/qemu-kvm.c
index 471306b..956b62a 100644
--- a/qemu-kvm.c
+++ b/qemu-kvm.c
@@ -1050,6 +1050,20 @@ int kvm_assign_set_msix_entry(kvm_context_t kvm,
 }
 #endif
 
+#ifdef KVM_CAP_MSIX_MMIO
+int kvm_register_msix_mmio(kvm_context_t kvm,
+                           struct kvm_msix_mmio_user *mmio_user)
+{
+    return kvm_vm_ioctl(kvm_state, KVM_REGISTER_MSIX_MMIO, mmio_user);
+}
+
+int kvm_unregister_msix_mmio(kvm_context_t kvm,
+                             struct kvm_msix_mmio_user *mmio_user)
+{
+    return kvm_vm_ioctl(kvm_state, KVM_UNREGISTER_MSIX_MMIO, mmio_user);
+}
+#endif
+
 #if defined(KVM_CAP_IRQFD) && defined(CONFIG_EVENTFD)
 
 #include <sys/eventfd.h>
diff --git a/qemu-kvm.h b/qemu-kvm.h
index 7e6edfb..86799e6 100644
--- a/qemu-kvm.h
+++ b/qemu-kvm.h
@@ -602,6 +602,13 @@ int kvm_assign_set_msix_entry(kvm_context_t kvm,
                               struct kvm_assigned_msix_entry *entry);
 #endif
 
+#ifdef KVM_CAP_MSIX_MMIO
+int kvm_register_msix_mmio(kvm_context_t kvm,
+                           struct kvm_msix_mmio_user *mmio_user);
+int kvm_unregister_msix_mmio(kvm_context_t kvm,
+                             struct kvm_msix_mmio_user *mmio_user);
+#endif
+
 #else                           /* !CONFIG_KVM */
 
 typedef struct kvm_context *kvm_context_t;
-- 
1.7.0.1

[PATCH 2/4] qemu-kvm: Ioctl for MSIX MMIO support

[Sheng Yang]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 qemu-kvm.c |   14 ++++++++++++++
 qemu-kvm.h |    7 +++++++
 2 files changed, 21 insertions(+), 0 deletions(-)

diff --git a/qemu-kvm.c b/qemu-kvm.c
index 471306b..956b62a 100644
--- a/qemu-kvm.c
+++ b/qemu-kvm.c
@@ -1050,6 +1050,20 @@ int kvm_assign_set_msix_entry(kvm_context_t kvm,
 }
 #endif
 
+#ifdef KVM_CAP_MSIX_MMIO
+int kvm_register_msix_mmio(kvm_context_t kvm,
+                           struct kvm_msix_mmio_user *mmio_user)
+{
+    return kvm_vm_ioctl(kvm_state, KVM_REGISTER_MSIX_MMIO, mmio_user);
+}
+
+int kvm_unregister_msix_mmio(kvm_context_t kvm,
+                             struct kvm_msix_mmio_user *mmio_user)
+{
+    return kvm_vm_ioctl(kvm_state, KVM_UNREGISTER_MSIX_MMIO, mmio_user);
+}
+#endif
+
 #if defined(KVM_CAP_IRQFD) && defined(CONFIG_EVENTFD)
 
 #include <sys/eventfd.h>
diff --git a/qemu-kvm.h b/qemu-kvm.h
index 7e6edfb..86799e6 100644
--- a/qemu-kvm.h
+++ b/qemu-kvm.h
@@ -602,6 +602,13 @@ int kvm_assign_set_msix_entry(kvm_context_t kvm,
                               struct kvm_assigned_msix_entry *entry);
 #endif
 
+#ifdef KVM_CAP_MSIX_MMIO
+int kvm_register_msix_mmio(kvm_context_t kvm,
+                           struct kvm_msix_mmio_user *mmio_user);
+int kvm_unregister_msix_mmio(kvm_context_t kvm,
+                             struct kvm_msix_mmio_user *mmio_user);
+#endif
+
 #else                           /* !CONFIG_KVM */
 
 typedef struct kvm_context *kvm_context_t;
-- 
1.7.0.1

[PATCH 0/4 v8] qemu-kvm: MSI-X MMIO support for assigned device

[Sheng Yang]

Update with kernel patches v8.

Sheng Yang (4):
  qemu-kvm: device assignment: Enabling MSI-X according to the entries'
    mask bit
  qemu-kvm: Ioctl for MSIX MMIO support
  qemu-kvm: Header file update for MSI-X MMIO support
  qemu-kvm: MSI-X MMIO support for assigned device

 hw/device-assignment.c  |  275 ++++++++++++++++++++++++++++++++++++++++------
 hw/device-assignment.h  |    5 +-
 kvm/include/linux/kvm.h |   21 ++++
 qemu-kvm.c              |   54 +++++++++
 qemu-kvm.h              |   18 +++
 5 files changed, 336 insertions(+), 37 deletions(-)

[PATCH 1/4] qemu-kvm: device assignment: Enabling MSI-X according to the entries' mask bit

[Sheng Yang]

The old MSI-X enabling method assume the entries are written before MSI-X
enabled, but some OS didn't obey this, e.g. FreeBSD. This patch would fix
this.

Also, according to the PCI spec, mask bit of MSI-X table should be set
after reset.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 hw/device-assignment.c |  188 +++++++++++++++++++++++++++++++++++++++++-------
 hw/device-assignment.h |    2 +-
 2 files changed, 162 insertions(+), 28 deletions(-)

diff --git a/hw/device-assignment.c b/hw/device-assignment.c
index 8446cd4..f81050f 100644
--- a/hw/device-assignment.c
+++ b/hw/device-assignment.c
@@ -1141,15 +1141,12 @@ static void assigned_dev_update_msi(PCIDevice *pci_dev, unsigned int ctrl_pos)
 #endif
 
 #ifdef KVM_CAP_DEVICE_MSIX
-static int assigned_dev_update_msix_mmio(PCIDevice *pci_dev)
+
+#define PCI_MSIX_CTRL_MASKBIT	1ul
+static int get_msix_entries_max_nr(AssignedDevice *adev)
 {
-    AssignedDevice *adev = container_of(pci_dev, AssignedDevice, dev);
-    uint16_t entries_nr = 0, entries_max_nr;
-    int pos = 0, i, r = 0;
-    uint32_t msg_addr, msg_upper_addr, msg_data, msg_ctrl;
-    struct kvm_assigned_msix_nr msix_nr;
-    struct kvm_assigned_msix_entry msix_entry;
-    void *va = adev->msix_table_page;
+    int pos, entries_max_nr;
+    PCIDevice *pci_dev = &adev->dev;
 
     pos = pci_find_capability(pci_dev, PCI_CAP_ID_MSIX);
 
@@ -1157,20 +1154,48 @@ static int assigned_dev_update_msix_mmio(PCIDevice *pci_dev)
     entries_max_nr &= PCI_MSIX_TABSIZE;
     entries_max_nr += 1;
 
+    return entries_max_nr;
+}
+
+static int assigned_dev_msix_entry_masked(AssignedDevice *adev, int entry)
+{
+    uint32_t msg_ctrl;
+    void *va = adev->msix_table_page;
+
+    memcpy(&msg_ctrl, va + entry * 16 + 12, 4);
+    return (msg_ctrl & PCI_MSIX_CTRL_MASKBIT);
+}
+
+static int get_msix_valid_entries_nr(AssignedDevice *adev,
+				     uint16_t entries_max_nr)
+{
+    void *va = adev->msix_table_page;
+    uint32_t msg_ctrl;
+    uint16_t entries_nr = 0;
+    int i;
+
     /* Get the usable entry number for allocating */
     for (i = 0; i < entries_max_nr; i++) {
         memcpy(&msg_ctrl, va + i * 16 + 12, 4);
-        memcpy(&msg_data, va + i * 16 + 8, 4);
         /* Ignore unused entry even it's unmasked */
-        if (msg_data == 0)
+        if (assigned_dev_msix_entry_masked(adev, i))
             continue;
         entries_nr ++;
     }
+    return entries_nr;
+}
+
+static int assigned_dev_update_msix_mmio(PCIDevice *pci_dev,
+                                         uint16_t entries_nr,
+                                         uint16_t entries_max_nr)
+{
+    AssignedDevice *adev = container_of(pci_dev, AssignedDevice, dev);
+    int i, r = 0;
+    uint32_t msg_addr, msg_upper_addr, msg_data, msg_ctrl;
+    struct kvm_assigned_msix_nr msix_nr;
+    struct kvm_assigned_msix_entry msix_entry;
+    void *va = adev->msix_table_page;
 
-    if (entries_nr == 0) {
-        fprintf(stderr, "MSI-X entry number is zero!\n");
-        return -EINVAL;
-    }
     msix_nr.assigned_dev_id = calc_assigned_dev_id(adev->h_segnr, adev->h_busnr,
                                           (uint8_t)adev->h_devfn);
     msix_nr.entry_nr = entries_nr;
@@ -1182,6 +1207,8 @@ static int assigned_dev_update_msix_mmio(PCIDevice *pci_dev)
     }
 
     free_dev_irq_entries(adev);
+    memset(pci_dev->msix_entry_used, 0, KVM_MAX_MSIX_PER_DEV *
+                                        sizeof(*pci_dev->msix_entry_used));
     adev->irq_entries_nr = entries_nr;
     adev->entry = calloc(entries_nr, sizeof(struct kvm_irq_routing_entry));
     if (!adev->entry) {
@@ -1195,10 +1222,10 @@ static int assigned_dev_update_msix_mmio(PCIDevice *pci_dev)
         if (entries_nr >= msix_nr.entry_nr)
             break;
         memcpy(&msg_ctrl, va + i * 16 + 12, 4);
-        memcpy(&msg_data, va + i * 16 + 8, 4);
-        if (msg_data == 0)
+        if (assigned_dev_msix_entry_masked(adev, i))
             continue;
 
+        memcpy(&msg_data, va + i * 16 + 8, 4);
         memcpy(&msg_addr, va + i * 16, 4);
         memcpy(&msg_upper_addr, va + i * 16 + 4, 4);
 
@@ -1212,17 +1239,18 @@ static int assigned_dev_update_msix_mmio(PCIDevice *pci_dev)
         adev->entry[entries_nr].u.msi.address_lo = msg_addr;
         adev->entry[entries_nr].u.msi.address_hi = msg_upper_addr;
         adev->entry[entries_nr].u.msi.data = msg_data;
-        DEBUG("MSI-X data 0x%x, MSI-X addr_lo 0x%x\n!", msg_data, msg_addr);
-	kvm_add_routing_entry(&adev->entry[entries_nr]);
+        DEBUG("MSI-X data 0x%x, MSI-X addr_lo 0x%x!\n", msg_data, msg_addr);
+        kvm_add_routing_entry(&adev->entry[entries_nr]);
 
         msix_entry.gsi = adev->entry[entries_nr].gsi;
         msix_entry.entry = i;
+        pci_dev->msix_entry_used[i] = 1;
         r = kvm_assign_set_msix_entry(kvm_context, &msix_entry);
         if (r) {
             fprintf(stderr, "fail to set MSI-X entry! %s\n", strerror(-r));
             break;
         }
-        DEBUG("MSI-X entry gsi 0x%x, entry %d\n!",
+        DEBUG("MSI-X entry gsi 0x%x, entry %d!\n",
                 msix_entry.gsi, msix_entry.entry);
         entries_nr ++;
     }
@@ -1239,20 +1267,24 @@ static void assigned_dev_update_msix(PCIDevice *pci_dev, unsigned int ctrl_pos)
 {
     struct kvm_assigned_irq assigned_irq_data;
     AssignedDevice *assigned_dev = container_of(pci_dev, AssignedDevice, dev);
-    uint16_t *ctrl_word = (uint16_t *)(pci_dev->config + ctrl_pos);
+    uint16_t ctrl_word = *(uint16_t *)(pci_dev->config + ctrl_pos);
     int r;
+    uint16_t entries_nr, entries_max_nr;
+    int enable_msix;
 
     memset(&assigned_irq_data, 0, sizeof assigned_irq_data);
     assigned_irq_data.assigned_dev_id  =
             calc_assigned_dev_id(assigned_dev->h_segnr, assigned_dev->h_busnr,
                     (uint8_t)assigned_dev->h_devfn);
 
+    enable_msix = ((ctrl_word & PCI_MSIX_ENABLE) &&
+                  !(ctrl_word & PCI_MSIX_MASK));
+
     /* Some guests gratuitously disable MSIX even if they're not using it,
      * try to catch this by only deassigning irqs if the guest is using
      * MSIX or intends to start. */
     if ((assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MSIX) ||
-        (*ctrl_word & PCI_MSIX_ENABLE)) {
-
+            enable_msix) {
         assigned_irq_data.flags = assigned_dev->irq_requested_type;
         free_dev_irq_entries(assigned_dev);
         r = kvm_deassign_irq(kvm_context, &assigned_irq_data);
@@ -1261,16 +1293,30 @@ static void assigned_dev_update_msix(PCIDevice *pci_dev, unsigned int ctrl_pos)
             perror("assigned_dev_update_msix: deassign irq");
 
         assigned_dev->irq_requested_type = 0;
+        memset(pci_dev->msix_entry_used, 0, KVM_MAX_MSIX_PER_DEV *
+                                        sizeof(*pci_dev->msix_entry_used));
     }
 
-    if (*ctrl_word & PCI_MSIX_ENABLE) {
-        assigned_irq_data.flags = KVM_DEV_IRQ_HOST_MSIX |
-                                  KVM_DEV_IRQ_GUEST_MSIX;
-
-        if (assigned_dev_update_msix_mmio(pci_dev) < 0) {
+    entries_max_nr = assigned_dev->max_msix_entries_nr;
+    if (entries_max_nr == 0) {
+        fprintf(stderr, "assigned_dev_update_msix: MSI-X entries_max_nr == 0");
+        return;
+    }
+    /*
+     * Guest may try to enable MSI-X before setting MSI-X entry done, so
+     * let's wait until guest unmask the entries.
+     */
+    entries_nr = get_msix_valid_entries_nr(assigned_dev, entries_max_nr);
+    if (entries_nr == 0)
+        return;
+    if (enable_msix) {
+        if (assigned_dev_update_msix_mmio(pci_dev,
+                    entries_nr, entries_max_nr) < 0) {
             perror("assigned_dev_update_msix_mmio");
             return;
         }
+        assigned_irq_data.flags = KVM_DEV_IRQ_HOST_MSIX |
+                                  KVM_DEV_IRQ_GUEST_MSIX;
         if (kvm_assign_irq(kvm_context, &assigned_irq_data) < 0) {
             perror("assigned_dev_enable_msix: assign irq");
             return;
@@ -1441,6 +1487,7 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev)
         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->max_msix_entries_nr = get_msix_entries_max_nr(dev);
     }
 #endif
 #endif
@@ -1629,10 +1676,90 @@ static void msix_mmio_writel(void *opaque,
     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 = {};
+    int entry_idx, entries_max_nr, r = 0, i;
+    uint32_t msg_ctrl, msg_data, msg_upper_addr, msg_addr;
+    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;
+
+    /* Check if mask bit is being accessed */
+    memcpy(&msg_addr, (char *)page + index * 16, 4);
+    memcpy(&msg_upper_addr, (char *)page + index * 16 + 4, 4);
+    memcpy(&msg_data, (char *)page + index * 16 + 8, 4);
+    memcpy(&msg_ctrl, (char *)page + index * 16 + 12, 4);
+    DEBUG("MSI-X entries index %d: "
+            "msg_addr 0x%x, msg_upper_addr 0x%x, msg_data 0x%x, vec_ctl 0x%x\n",
+            index, msg_addr, msg_upper_addr, msg_data, msg_ctrl);
+
+    ctrl_word = pci_get_word(pci_dev->config + cap + PCI_MSIX_FLAGS);
+
+    if (!((ctrl_word & PCI_MSIX_ENABLE) && !(ctrl_word & PCI_MSIX_MASK)))
+        return;
+
+    if (!assigned_dev_msix_entry_masked(adev, index)) {
+        if (!adev->dev.msix_entry_used[index]) {
+            DEBUG("Try to modify unenabled MSI-X entry %d's mask. "
+                    "Reenable MSI-X.\n",
+                    index);
+            assigned_dev_update_msix(&adev->dev, cap + PCI_MSIX_FLAGS);
+        }
+        return;
+    }
+
+    if (!adev->dev.msix_entry_used[index])
+        return;
+
+    entries_max_nr = adev->max_msix_entries_nr;
+
+    /*
+     * Find the index of routing entry, it can be different from 'index' if
+     * empty entry existed in between
+     */
+    entry_idx = -1;
+    for (i = 0; i <= index; i++) {
+        if (adev->dev.msix_entry_used[i])
+            entry_idx ++;
+    }
+    if (entry_idx >= entries_max_nr || entry_idx == -1) {
+        fprintf(stderr, "msix_mmio_writel: Entry idx %d exceed limit!\n",
+			entry_idx);
+        return;
+    }
+
+    if (!assigned_dev_msix_entry_masked(adev, index)) {
+        fprintf(stderr, "msix_mmio_writel: Trying write to unmasked entry!\n");
+        return;
+    }
+
+    new_entry.gsi = adev->entry[entry_idx].gsi;
+    new_entry.type = KVM_IRQ_ROUTING_MSI;
+    new_entry.flags = 0;
+    new_entry.u.msi.address_lo = msg_addr;
+    new_entry.u.msi.address_hi = msg_upper_addr;
+    new_entry.u.msi.data = msg_data;
+    if (memcmp(&adev->entry[entry_idx].u.msi, &new_entry.u.msi,
+                sizeof new_entry.u.msi)) {
+        r = kvm_update_routing_entry(&adev->entry[entry_idx], &new_entry);
+        if (r) {
+            perror("msix_mmio_writel: kvm_update_routing_entry failed\n");
+            return;
+        }
+        r = kvm_commit_irq_routes();
+        if (r) {
+            perror("msix_mmio_writel: kvm_commit_irq_routes failed\n");
+            return;
+        }
+    }
+    adev->entry[entry_idx].u.msi.address_lo = msg_addr;
+    adev->entry[entry_idx].u.msi.address_hi = msg_upper_addr;
+    adev->entry[entry_idx].u.msi.data = msg_data;
 }
 
 static void msix_mmio_writew(void *opaque,
@@ -1659,6 +1786,7 @@ static CPUReadMemoryFunc *msix_mmio_read[] = {
 
 static int assigned_dev_register_msix_mmio(AssignedDevice *dev)
 {
+    int i;
     dev->msix_table_page = mmap(NULL, 0x1000,
                                 PROT_READ|PROT_WRITE,
                                 MAP_ANONYMOUS|MAP_PRIVATE, 0, 0);
@@ -1668,8 +1796,12 @@ static int assigned_dev_register_msix_mmio(AssignedDevice *dev)
         return -EFAULT;
     }
     memset(dev->msix_table_page, 0, 0x1000);
+    for (i = 0; i < 0x1000; i += 0x10)
+        *(uint32_t *)(dev->msix_table_page + i + 0xc) = 1;
     dev->mmio_index = cpu_register_io_memory(
                         msix_mmio_read, msix_mmio_write, dev);
+    dev->dev.msix_entry_used = qemu_mallocz(KVM_MAX_MSIX_PER_DEV *
+                                        sizeof *dev->dev.msix_entry_used);
     return 0;
 }
 
@@ -1686,6 +1818,8 @@ static void assigned_dev_unregister_msix_mmio(AssignedDevice *dev)
                 strerror(errno));
     }
     dev->msix_table_page = NULL;
+    free(dev->dev.msix_entry_used);
+    dev->dev.msix_entry_used = NULL;
 }
 
 static const VMStateDescription vmstate_assigned_device = {
diff --git a/hw/device-assignment.h b/hw/device-assignment.h
index c94a730..754e5c0 100644
--- a/hw/device-assignment.h
+++ b/hw/device-assignment.h
@@ -104,7 +104,7 @@ typedef struct AssignedDevice {
 #define ASSIGNED_DEVICE_MSIX_MASKED (1 << 2)
         uint32_t state;
     } cap;
-    int irq_entries_nr;
+    int irq_entries_nr, max_msix_entries_nr;
     struct kvm_irq_routing_entry *entry;
     void *msix_table_page;
     target_phys_addr_t msix_table_addr;
-- 
1.7.0.1

[PATCH 2/4] qemu-kvm: Ioctl for MSIX MMIO support

[Sheng Yang]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 qemu-kvm.c |   14 ++++++++++++++
 qemu-kvm.h |    7 +++++++
 2 files changed, 21 insertions(+), 0 deletions(-)

diff --git a/qemu-kvm.c b/qemu-kvm.c
index 471306b..956b62a 100644
--- a/qemu-kvm.c
+++ b/qemu-kvm.c
@@ -1050,6 +1050,20 @@ int kvm_assign_set_msix_entry(kvm_context_t kvm,
 }
 #endif
 
+#ifdef KVM_CAP_MSIX_MMIO
+int kvm_register_msix_mmio(kvm_context_t kvm,
+                           struct kvm_msix_mmio_user *mmio_user)
+{
+    return kvm_vm_ioctl(kvm_state, KVM_REGISTER_MSIX_MMIO, mmio_user);
+}
+
+int kvm_unregister_msix_mmio(kvm_context_t kvm,
+                             struct kvm_msix_mmio_user *mmio_user)
+{
+    return kvm_vm_ioctl(kvm_state, KVM_UNREGISTER_MSIX_MMIO, mmio_user);
+}
+#endif
+
 #if defined(KVM_CAP_IRQFD) && defined(CONFIG_EVENTFD)
 
 #include <sys/eventfd.h>
diff --git a/qemu-kvm.h b/qemu-kvm.h
index 7e6edfb..86799e6 100644
--- a/qemu-kvm.h
+++ b/qemu-kvm.h
@@ -602,6 +602,13 @@ int kvm_assign_set_msix_entry(kvm_context_t kvm,
                               struct kvm_assigned_msix_entry *entry);
 #endif
 
+#ifdef KVM_CAP_MSIX_MMIO
+int kvm_register_msix_mmio(kvm_context_t kvm,
+                           struct kvm_msix_mmio_user *mmio_user);
+int kvm_unregister_msix_mmio(kvm_context_t kvm,
+                             struct kvm_msix_mmio_user *mmio_user);
+#endif
+
 #else                           /* !CONFIG_KVM */
 
 typedef struct kvm_context *kvm_context_t;
-- 
1.7.0.1

[PATCH 3/4] qemu-kvm: Header file update for MSI-X MMIO support

[Sheng Yang]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 kvm/include/linux/kvm.h |   21 +++++++++++++++++++++
 1 files changed, 21 insertions(+), 0 deletions(-)

diff --git a/kvm/include/linux/kvm.h b/kvm/include/linux/kvm.h
index e46729e..7b6d5b9 100644
--- a/kvm/include/linux/kvm.h
+++ b/kvm/include/linux/kvm.h
@@ -161,6 +161,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_NMI              16
 #define KVM_EXIT_INTERNAL_ERROR   17
 #define KVM_EXIT_OSI              18
+#define KVM_EXIT_MSIX_ROUTING_UPDATE 19
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1
@@ -530,6 +531,7 @@ struct kvm_enable_cap {
 #ifdef __KVM_HAVE_XCRS
 #define KVM_CAP_XCRS 56
 #endif
+#define KVM_CAP_MSIX_MMIO 60
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -660,6 +662,9 @@ struct kvm_clock_data {
 #define KVM_XEN_HVM_CONFIG        _IOW(KVMIO,  0x7a, struct kvm_xen_hvm_config)
 #define KVM_SET_CLOCK             _IOW(KVMIO,  0x7b, struct kvm_clock_data)
 #define KVM_GET_CLOCK             _IOR(KVMIO,  0x7c, struct kvm_clock_data)
+/* Available with KVM_CAP_MSIX_MMIO */
+#define KVM_REGISTER_MSIX_MMIO    _IOW(KVMIO, 0x7d, struct kvm_msix_mmio_user)
+#define KVM_UNREGISTER_MSIX_MMIO  _IOW(KVMIO, 0x7e, struct kvm_msix_mmio_user)
 /* Available with KVM_CAP_PIT_STATE2 */
 #define KVM_GET_PIT2              _IOR(KVMIO,  0x9f, struct kvm_pit_state2)
 #define KVM_SET_PIT2              _IOW(KVMIO,  0xa0, struct kvm_pit_state2)
@@ -781,4 +786,20 @@ struct kvm_assigned_msix_entry {
 	__u16 padding[3];
 };
 
+#define KVM_MSIX_MMIO_TYPE_ASSIGNED_DEV	    (1 << 0)
+
+#define KVM_MSIX_MMIO_TYPE_BASE_TABLE	    (1 << 8)
+
+#define KVM_MSIX_MMIO_TYPE_DEV_MASK	    0x00ff
+#define KVM_MSIX_MMIO_TYPE_BASE_MASK	    0xff00
+struct kvm_msix_mmio_user {
+	__u32 dev_id;
+	__u16 type;
+	__u16 max_entries_nr;
+	__u64 base_addr;
+	__u64 base_va;
+	__u64 flags;
+	__u64 reserved[4];
+};
+
 #endif /* __LINUX_KVM_H */
-- 
1.7.0.1

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

[Sheng Yang]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 hw/device-assignment.c |   93 +++++++++++++++++++++++++++++++++++++++++------
 hw/device-assignment.h |    3 ++
 qemu-kvm.c             |   40 ++++++++++++++++++++
 qemu-kvm.h             |   11 ++++++
 4 files changed, 135 insertions(+), 12 deletions(-)

diff --git a/hw/device-assignment.c b/hw/device-assignment.c
index f81050f..bddee2a 100644
--- a/hw/device-assignment.c
+++ b/hw/device-assignment.c
@@ -70,6 +70,11 @@ 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)
 {
@@ -272,6 +277,10 @@ 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);
@@ -290,6 +299,23 @@ 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
         }
     }
 
@@ -852,11 +878,6 @@ 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;
@@ -1263,6 +1284,8 @@ static int assigned_dev_update_msix_mmio(PCIDevice *pci_dev,
     return r;
 }
 
+static int assigned_dev_update_routing_handler(void *opaque, unsigned long addr);
+
 static void assigned_dev_update_msix(PCIDevice *pci_dev, unsigned int ctrl_pos)
 {
     struct kvm_assigned_irq assigned_irq_data;
@@ -1486,7 +1509,9 @@ 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
@@ -1670,8 +1695,7 @@ 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, unsigned long addr)
 {
     AssignedDevice *adev = opaque;
     unsigned int offset = addr & 0xfff;
@@ -1683,10 +1707,6 @@ 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;
 
     /* Check if mask bit is being accessed */
@@ -1762,6 +1782,41 @@ 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, unsigned long addr)
+{
+    AssignedDevice *adev = opaque;
+
+    if (addr >= adev->guest_msix_table_addr &&
+            addr < adev->guest_msix_table_addr + adev->max_msix_entries_nr * 16) {
+        assigned_dev_update_routing(opaque, addr);
+        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;
+#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");
+    }
+
+    assigned_dev_update_routing(opaque, addr);
+}
+
 static void msix_mmio_writew(void *opaque,
                              target_phys_addr_t addr, uint32_t val)
 {
@@ -1802,7 +1857,17 @@ static int assigned_dev_register_msix_mmio(AssignedDevice *dev)
                         msix_mmio_read, msix_mmio_write, dev);
     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)
@@ -1818,6 +1883,10 @@ 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 754e5c0..98ef82f 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))
@@ -108,9 +109,11 @@ 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;
+    KVMRoutingUpdateEntry *routing_updater_entry;
     QLIST_ENTRY(AssignedDevice) next;
 } AssignedDevice;
 
diff --git a/qemu-kvm.c b/qemu-kvm.c
index 956b62a..1ba81c4 100644
--- a/qemu-kvm.c
+++ b/qemu-kvm.c
@@ -511,6 +511,40 @@ 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)
+{
+    unsigned long addr = env->kvm_run->mmio.phys_addr;
+    KVMRoutingUpdateEntry *e;
+
+    for (e = kvm_routing_update_entry_head.lh_first; e; e = e->entries.le_next) {
+        if (e->cb(e->opaque, addr) == 0)
+            return;
+    }
+    fprintf(stderr, "unhandled MSI-X routing update addr: 0x%lx\n", addr);
+}
+#endif
+
 int handle_io_window(kvm_context_t kvm)
 {
     return 1;
@@ -647,6 +681,12 @@ 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 86799e6..21a3274 100644
--- a/qemu-kvm.h
+++ b/qemu-kvm.h
@@ -772,6 +772,17 @@ int kvm_tpr_enable_vapic(CPUState *env);
 unsigned long kvm_get_thread_id(void);
 int kvm_cpu_is_stopped(CPUState *env);
 
+typedef struct kvm_routing_update_entry KVMRoutingUpdateEntry;
+typedef int KVMRoutingUpdateHandler(void *opaque, unsigned long addr);
+
+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

[PATCH 2/4] qemu-kvm: Ioctl for MSIX MMIO support

[Sheng Yang]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 qemu-kvm.c |   14 ++++++++++++++
 qemu-kvm.h |    7 +++++++
 2 files changed, 21 insertions(+), 0 deletions(-)

diff --git a/qemu-kvm.c b/qemu-kvm.c
index 49cd683..d282c95 100644
--- a/qemu-kvm.c
+++ b/qemu-kvm.c
@@ -1050,6 +1050,20 @@ int kvm_assign_set_msix_entry(kvm_context_t kvm,
 }
 #endif
 
+#ifdef KVM_CAP_MSIX_MMIO
+int kvm_register_msix_mmio(kvm_context_t kvm,
+                           struct kvm_msix_mmio_user *mmio_user)
+{
+    return kvm_vm_ioctl(kvm_state, KVM_REGISTER_MSIX_MMIO, mmio_user);
+}
+
+int kvm_unregister_msix_mmio(kvm_context_t kvm,
+                             struct kvm_msix_mmio_user *mmio_user)
+{
+    return kvm_vm_ioctl(kvm_state, KVM_UNREGISTER_MSIX_MMIO, mmio_user);
+}
+#endif
+
 #if defined(KVM_CAP_IRQFD) && defined(CONFIG_EVENTFD)
 
 #include <sys/eventfd.h>
diff --git a/qemu-kvm.h b/qemu-kvm.h
index 88cf276..48ff52d 100644
--- a/qemu-kvm.h
+++ b/qemu-kvm.h
@@ -602,6 +602,13 @@ int kvm_assign_set_msix_entry(kvm_context_t kvm,
                               struct kvm_assigned_msix_entry *entry);
 #endif
 
+#ifdef KVM_CAP_MSIX_MMIO
+int kvm_register_msix_mmio(kvm_context_t kvm,
+                           struct kvm_msix_mmio_user *mmio_user);
+int kvm_unregister_msix_mmio(kvm_context_t kvm,
+                             struct kvm_msix_mmio_user *mmio_user);
+#endif
+
 #else                           /* !CONFIG_KVM */
 
 typedef struct kvm_context *kvm_context_t;
-- 
1.7.0.1