From f81cc30fefd469f19b2f4550d4453a8aaff3239a Mon Sep 17 00:00:00 2001

From: Alex Williamson <alex.williamson@redhat.com>

Date: Fri, 29 Sep 2017 21:44:49 +0200

Subject: [PATCH 06/27] hw/vfio/pci: handle reset at VFIODevice

RH-Author: Alex Williamson <alex.williamson@redhat.com>

Message-id: <20170929214449.16765.43500.stgit@gimli.home>

Patchwork-id: 76764

O-Subject: [RHEL-7.5 qemu-kvm PATCH 06/16] hw/vfio/pci: handle reset at VFIODevice

Bugzilla: 1494181

RH-Acked-by: Paolo Bonzini <pbonzini@redhat.com>

RH-Acked-by: Auger Eric <eric.auger@redhat.com>

RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>

From: Eric Auger <eric.auger@linaro.org>

Upstream: b47d8efa9f430c332bf96ce6eede169eb48422ad

Since we can potentially have both PCI and platform devices in

the same VFIO group, this latter now owns a list of VFIODevices.

A unified reset handler, vfio_reset_handler, is registered, looping

through this VFIODevice list. 2 specialized operations are introduced

(vfio_compute_needs_reset and vfio_hot_reset_multi): they allow to

implement type specific behavior. also reset_works and needs_reset

VFIOPCIDevice fields are moved into VFIODevice.

Signed-off-by: Eric Auger <eric.auger@linaro.org>

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>

---

 hw/misc/vfio.c | 95 +++++++++++++++++++++++++++++++++++++++-------------------

 1 file changed, 64 insertions(+), 31 deletions(-)

diff --git a/hw/misc/vfio.c b/hw/misc/vfio.c

index cc151e2..3e559ed 100644

--- a/hw/misc/vfio.c

+++ b/hw/misc/vfio.c

@@ -178,13 +178,24 @@ typedef struct VFIOMSIXInfo {

     void *mmap;

 } VFIOMSIXInfo;

+typedef struct VFIODeviceOps VFIODeviceOps;

+

 typedef struct VFIODevice {

+    QLIST_ENTRY(VFIODevice) next;

     struct VFIOGroup *group;

     char *name;

     int fd;

     int type;

+    bool reset_works;

+    bool needs_reset;

+    VFIODeviceOps *ops;

 } VFIODevice;

+struct VFIODeviceOps {

+    void (*vfio_compute_needs_reset)(VFIODevice *vdev);

+    int (*vfio_hot_reset_multi)(VFIODevice *vdev);

+};

+

 typedef struct VFIOPCIDevice {

     PCIDevice pdev;

     VFIODevice vbasedev;

@@ -203,7 +214,6 @@ typedef struct VFIOPCIDevice {

     VFIOBAR bars[PCI_NUM_REGIONS - 1]; /* No ROM */

     VFIOVGA vga; /* 0xa0000, 0x3b0, 0x3c0 */

     PCIHostDeviceAddress host;

-    QLIST_ENTRY(VFIOPCIDevice) next;

     EventNotifier err_notifier;

     EventNotifier req_notifier;

     uint32_t features;

@@ -213,13 +223,11 @@ typedef struct VFIOPCIDevice {

 #define VFIO_FEATURE_ENABLE_REQ (1 << VFIO_FEATURE_ENABLE_REQ_BIT)

     int32_t bootindex;

     uint8_t pm_cap;

-    bool reset_works;

     bool has_vga;

     bool pci_aer;

     bool req_enabled;

     bool has_flr;

     bool has_pm_reset;

-    bool needs_reset;

     bool rom_read_failed;

 } VFIOPCIDevice;

@@ -227,7 +235,7 @@ typedef struct VFIOGroup {

     int fd;

     int groupid;

     VFIOContainer *container;

-    QLIST_HEAD(, VFIOPCIDevice) device_list;

+    QLIST_HEAD(, VFIODevice) device_list;

     QLIST_ENTRY(VFIOGroup) next;

     QLIST_ENTRY(VFIOGroup) container_next;

 } VFIOGroup;

@@ -3064,7 +3072,7 @@ static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single)

             single ? "one" : "multi");

     vfio_pci_pre_reset(vdev);

-    vdev->needs_reset = false;

+    vdev->vbasedev.needs_reset = false;

     info = g_malloc0(sizeof(*info));

     info->argsz = sizeof(*info);

@@ -3100,6 +3108,7 @@ static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single)

     for (i = 0; i < info->count; i++) {

         PCIHostDeviceAddress host;

         VFIOPCIDevice *tmp;

+        VFIODevice *vbasedev_iter;

         host.domain = devices[i].segment;

         host.bus = devices[i].bus;

@@ -3131,7 +3140,11 @@ static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single)

         }

         /* Prep dependent devices for reset and clear our marker. */

-        QLIST_FOREACH(tmp, &group->device_list, next) {

+        QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {

+            if (vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) {

+                continue;

+            }

+            tmp = container_of(vbasedev_iter, VFIOPCIDevice, vbasedev);

             if (vfio_pci_host_match(&host, &tmp->host)) {

                 if (single) {

                     DPRINTF("vfio: found another in-use device "

@@ -3141,7 +3154,7 @@ static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single)

                     goto out_single;

                 }

                 vfio_pci_pre_reset(tmp);

-                tmp->needs_reset = false;

+                tmp->vbasedev.needs_reset = false;

                 multi = true;

                 break;

             }

@@ -3192,6 +3205,7 @@ out:

     for (i = 0; i < info->count; i++) {

         PCIHostDeviceAddress host;

         VFIOPCIDevice *tmp;

+        VFIODevice *vbasedev_iter;

         host.domain = devices[i].segment;

         host.bus = devices[i].bus;

@@ -3212,7 +3226,11 @@ out:

             break;

         }

-        QLIST_FOREACH(tmp, &group->device_list, next) {

+        QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {

+            if (vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) {

+                continue;

+            }

+            tmp = container_of(vbasedev_iter, VFIOPCIDevice, vbasedev);

             if (vfio_pci_host_match(&host, &tmp->host)) {

                 vfio_pci_post_reset(tmp);

                 break;

@@ -3246,28 +3264,40 @@ static int vfio_pci_hot_reset_one(VFIOPCIDevice *vdev)

     return vfio_pci_hot_reset(vdev, true);

 }

-static int vfio_pci_hot_reset_multi(VFIOPCIDevice *vdev)

+static int vfio_pci_hot_reset_multi(VFIODevice *vbasedev)

 {

+    VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);

     return vfio_pci_hot_reset(vdev, false);

 }

-static void vfio_pci_reset_handler(void *opaque)

+static void vfio_pci_compute_needs_reset(VFIODevice *vbasedev)

+{

+    VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev);

+    if (!vbasedev->reset_works || (!vdev->has_flr && vdev->has_pm_reset)) {

+        vbasedev->needs_reset = true;

+    }

+}

+

+static VFIODeviceOps vfio_pci_ops = {

+    .vfio_compute_needs_reset = vfio_pci_compute_needs_reset,

+    .vfio_hot_reset_multi = vfio_pci_hot_reset_multi,

+};

+

+static void vfio_reset_handler(void *opaque)

 {

     VFIOGroup *group;

-    VFIOPCIDevice *vdev;

+    VFIODevice *vbasedev;

     QLIST_FOREACH(group, &group_list, next) {

-        QLIST_FOREACH(vdev, &group->device_list, next) {

-            if (!vdev->reset_works || (!vdev->has_flr && vdev->has_pm_reset)) {

-                vdev->needs_reset = true;

-            }

+        QLIST_FOREACH(vbasedev, &group->device_list, next) {

+            vbasedev->ops->vfio_compute_needs_reset(vbasedev);

         }

     }

     QLIST_FOREACH(group, &group_list, next) {

-        QLIST_FOREACH(vdev, &group->device_list, next) {

-            if (vdev->needs_reset) {

-                vfio_pci_hot_reset_multi(vdev);

+        QLIST_FOREACH(vbasedev, &group->device_list, next) {

+            if (vbasedev->needs_reset) {

+                vbasedev->ops->vfio_hot_reset_multi(vbasedev);

             }

         }

     }

@@ -3486,7 +3516,7 @@ static VFIOGroup *vfio_get_group(int groupid)

     }

     if (QLIST_EMPTY(&group_list)) {

-        qemu_register_reset(vfio_pci_reset_handler, NULL);

+        qemu_register_reset(vfio_reset_handler, NULL);

     }

     QLIST_INSERT_HEAD(&group_list, group, next);

@@ -3510,7 +3540,7 @@ static void vfio_put_group(VFIOGroup *group)

     g_free(group);

     if (QLIST_EMPTY(&group_list)) {

-        qemu_unregister_reset(vfio_pci_reset_handler, NULL);

+        qemu_unregister_reset(vfio_reset_handler, NULL);

     }

 }

@@ -3533,7 +3563,7 @@ static int vfio_get_device(VFIOGroup *group, const char *name,

     vdev->vbasedev.fd = ret;

     vdev->vbasedev.group = group;

-    QLIST_INSERT_HEAD(&group->device_list, vdev, next);

+    QLIST_INSERT_HEAD(&group->device_list, &vdev->vbasedev, next);

     /* Sanity check device */

     ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_INFO, &dev_info);

@@ -3550,7 +3580,7 @@ static int vfio_get_device(VFIOGroup *group, const char *name,

         goto error;

     }

-    vdev->reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET);

+    vdev->vbasedev.reset_works = !!(dev_info.flags & VFIO_DEVICE_FLAGS_RESET);

     if (dev_info.num_regions < VFIO_PCI_CONFIG_REGION_INDEX + 1) {

         error_report("vfio: unexpected number of io regions %u",

@@ -3663,7 +3693,7 @@ static int vfio_get_device(VFIOGroup *group, const char *name,

 error:

     if (ret) {

-        QLIST_REMOVE(vdev, next);

+        QLIST_REMOVE(&vdev->vbasedev, next);

         vdev->vbasedev.group = NULL;

         close(vdev->vbasedev.fd);

     }

@@ -3672,7 +3702,7 @@ error:

 static void vfio_put_device(VFIOPCIDevice *vdev)

 {

-    QLIST_REMOVE(vdev, next);

+    QLIST_REMOVE(&vdev->vbasedev, next);

     vdev->vbasedev.group = NULL;

     DPRINTF("vfio_put_device: close vdev->vbasedev.fd\n");

     close(vdev->vbasedev.fd);

@@ -3881,7 +3911,8 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)

 static int vfio_initfn(PCIDevice *pdev)

 {

-    VFIOPCIDevice *pvdev, *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev);

+    VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev);

+    VFIODevice *vbasedev_iter;

     VFIOGroup *group;

     char path[PATH_MAX], iommu_group_path[PATH_MAX], *group_name;

     ssize_t len;

@@ -3890,7 +3921,7 @@ static int vfio_initfn(PCIDevice *pdev)

     int ret, i = 0;

     QLIST_FOREACH(group, &group_list, next) {

-        QLIST_FOREACH(pvdev, &group->device_list, next) {

+        QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {

             i++;

         }

     }

@@ -3911,6 +3942,8 @@ static int vfio_initfn(PCIDevice *pdev)

         return -errno;

     }

+    vdev->vbasedev.ops = &vfio_pci_ops;

+

     vdev->vbasedev.type = VFIO_DEVICE_TYPE_PCI;

     vdev->vbasedev.name = g_strdup_printf("%04x:%02x:%02x.%01x",

                                           vdev->host.domain, vdev->host.bus,

@@ -3945,9 +3978,8 @@ static int vfio_initfn(PCIDevice *pdev)

             vdev->host.domain, vdev->host.bus, vdev->host.slot,

             vdev->host.function);

-    QLIST_FOREACH(pvdev, &group->device_list, next) {

-        if (strcmp(pvdev->vbasedev.name, vdev->vbasedev.name) == 0) {

-

+    QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {

+        if (strcmp(vbasedev_iter->name, vdev->vbasedev.name) == 0) {

             error_report("vfio: error: device %s is already attached", path);

             vfio_put_group(group);

             return -EBUSY;

@@ -4078,7 +4110,8 @@ static void vfio_pci_reset(DeviceState *dev)

     vfio_pci_pre_reset(vdev);

-    if (vdev->reset_works && (vdev->has_flr || !vdev->has_pm_reset) &&

+    if (vdev->vbasedev.reset_works &&

+        (vdev->has_flr || !vdev->has_pm_reset) &&

         !ioctl(vdev->vbasedev.fd, VFIO_DEVICE_RESET)) {

         DPRINTF("%04x:%02x:%02x.%x FLR/VFIO_DEVICE_RESET\n", vdev->host.domain,

             vdev->host.bus, vdev->host.slot, vdev->host.function);

@@ -4091,7 +4124,7 @@ static void vfio_pci_reset(DeviceState *dev)

     }

     /* If nothing else works and the device supports PM reset, use it */

-    if (vdev->reset_works && vdev->has_pm_reset &&

+    if (vdev->vbasedev.reset_works && vdev->has_pm_reset &&

         !ioctl(vdev->vbasedev.fd, VFIO_DEVICE_RESET)) {

         DPRINTF("%04x:%02x:%02x.%x PCI PM Reset\n", vdev->host.domain,

             vdev->host.bus, vdev->host.slot, vdev->host.function);

-- 

1.8.3.1