[Qemu-devel] [PATCH v2 0/3] vfio-pci: support recovery of AER non fatal error

[Qemu-devel] [PATCH v2 0/3] vfio-pci: support recovery of AER non fatal error

[Cao jin]

v2 changelog:
Add the boilerplate code for new eventfd in patch 3. The corresponding
kernel patch is v5.

Test:
Test with func1 passthroughed while func0 doesn't have user.

Cao jin (3):
  pcie aer: verify if AER functionality is available
  vfio pci: new function to init AER capability
  vfio-pci: process non fatal error of AER

 hw/pci/pcie_aer.c          |  28 +++++
 hw/vfio/pci.c              | 288 ++++++++++++++++++++++++++++++++++++++++++++-
 hw/vfio/pci.h              |   5 +
 linux-headers/linux/vfio.h |   2 +
 4 files changed, 318 insertions(+), 5 deletions(-)

-- 
1.8.3.1

[Qemu-devel] [PATCH v2 1/3] pcie aer: verify if AER functionality is available

[Cao jin]

For devices which support AER function, verify it can work or not in the
system:
1. AER capable device is a PCIe device, it can't be plugged into PCI bus
2. If root port doesn't support AER, then there is no need to expose the
   AER capability

Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Signed-off-by: Cao jin <caoj.fnst@cn.fujitsu.com>
---
 hw/pci/pcie_aer.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/hw/pci/pcie_aer.c b/hw/pci/pcie_aer.c
index daf1f65..a2e9818 100644
--- a/hw/pci/pcie_aer.c
+++ b/hw/pci/pcie_aer.c
@@ -100,6 +100,34 @@ static void aer_log_clear_all_err(PCIEAERLog *aer_log)
 int pcie_aer_init(PCIDevice *dev, uint8_t cap_ver, uint16_t offset,
                   uint16_t size, Error **errp)
 {
+    PCIDevice *parent_dev;
+    uint8_t type;
+    uint8_t parent_type;
+
+    /* Topology test: see if there is need to expose AER cap */
+    type = pcie_cap_get_type(dev);
+    parent_dev = pci_bridge_get_device(dev->bus);
+    while (parent_dev) {
+        parent_type = pcie_cap_get_type(parent_dev);
+
+        if (type == PCI_EXP_TYPE_ENDPOINT &&
+                (parent_type != PCI_EXP_TYPE_ROOT_PORT &&
+                 parent_type != PCI_EXP_TYPE_DOWNSTREAM)) {
+            error_setg(errp, "Parent device is not a PCIe component");
+            return -ENOTSUP;
+        }
+        
+        if (parent_type == PCI_EXP_TYPE_ROOT_PORT) {
+            if (!parent_dev->exp.aer_cap)
+            {
+                error_setg(errp, "Root port does not support AER");
+                return -ENOTSUP;
+            }
+        }
+
+        parent_dev = pci_bridge_get_device(parent_dev->bus);
+    }
+
     pcie_add_capability(dev, PCI_EXT_CAP_ID_ERR, cap_ver,
                         offset, size);
     dev->exp.aer_cap = offset;
-- 
1.8.3.1

[Qemu-devel] [PATCH v2 2/3] vfio pci: new function to init AER capability

[Cao jin]

Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Signed-off-by: Cao jin <caoj.fnst@cn.fujitsu.com>
---
 hw/vfio/pci.c | 41 ++++++++++++++++++++++++++++++++++++-----
 hw/vfio/pci.h |  1 +
 2 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 332f41d..3d0d005 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1855,18 +1855,42 @@ out:
     return 0;
 }
 
-static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
+static int vfio_setup_aer(VFIOPCIDevice *vdev, uint8_t cap_ver,
+                          int pos, uint16_t size, Error **errp)
+{
+    PCIDevice *pdev = &vdev->pdev;
+    uint32_t errcap;
+
+    errcap = vfio_pci_read_config(pdev, pos + PCI_ERR_CAP, 4);
+    /*
+     * The ability to record multiple headers is depending on
+     * the state of the Multiple Header Recording Capable bit and
+     * enabled by the Multiple Header Recording Enable bit.
+     */
+    if ((errcap & PCI_ERR_CAP_MHRC) &&
+        (errcap & PCI_ERR_CAP_MHRE)) {
+        pdev->exp.aer_log.log_max = PCIE_AER_LOG_MAX_DEFAULT;
+    } else {
+        pdev->exp.aer_log.log_max = 0;
+    }
+
+    pcie_cap_deverr_init(pdev);
+    return pcie_aer_init(pdev, cap_ver, pos, size, errp);
+}
+
+static int vfio_add_ext_cap(VFIOPCIDevice *vdev, Error **errp)
 {
     PCIDevice *pdev = &vdev->pdev;
     uint32_t header;
     uint16_t cap_id, next, size;
     uint8_t cap_ver;
     uint8_t *config;
+    int ret = 0;
 
     /* Only add extended caps if we have them and the guest can see them */
     if (!pci_is_express(pdev) || !pci_bus_is_express(pdev->bus) ||
         !pci_get_long(pdev->config + PCI_CONFIG_SPACE_SIZE)) {
-        return;
+        return 0;
     }
 
     /*
@@ -1915,6 +1939,9 @@ static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
                                    PCI_EXT_CAP_NEXT_MASK);
 
         switch (cap_id) {
+        case PCI_EXT_CAP_ID_ERR:
+            ret = vfio_setup_aer(vdev, cap_ver, next, size, errp);
+            break;
         case PCI_EXT_CAP_ID_SRIOV: /* Read-only VF BARs confuse OVMF */
         case PCI_EXT_CAP_ID_ARI: /* XXX Needs next function virtualization */
             trace_vfio_add_ext_cap_dropped(vdev->vbasedev.name, cap_id, next);
@@ -1923,6 +1950,9 @@ static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
             pcie_add_capability(pdev, cap_id, cap_ver, next, size);
         }
 
+        if (ret) {
+            goto out;
+        }
     }
 
     /* Cleanup chain head ID if necessary */
@@ -1930,8 +1960,9 @@ static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
         pci_set_word(pdev->config + PCI_CONFIG_SPACE_SIZE, 0);
     }
 
+out:
     g_free(config);
-    return;
+    return ret;
 }
 
 static int vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp)
@@ -1949,8 +1980,8 @@ static int vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp)
         return ret;
     }
 
-    vfio_add_ext_cap(vdev);
-    return 0;
+    ret = vfio_add_ext_cap(vdev, errp);
+    return ret;
 }
 
 static void vfio_pci_pre_reset(VFIOPCIDevice *vdev)
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index a8366bb..34e8b04 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -15,6 +15,7 @@
 #include "qemu-common.h"
 #include "exec/memory.h"
 #include "hw/pci/pci.h"
+#include "hw/pci/pci_bridge.h"
 #include "hw/vfio/vfio-common.h"
 #include "qemu/event_notifier.h"
 #include "qemu/queue.h"
-- 
1.8.3.1

[Qemu-devel] [PATCH v2 3/3] vfio-pci: process non fatal error of AER

[Cao jin]

Make use of the non fatal error eventfd that the kernel module provide
to process the AER non fatal error. Fatal error still goes into the
legacy way which results in VM stop.

Register the handler, wait for notification. Construct aer message and
pass it to root port on notification. Root port will trigger an interrupt
to signal guest, then guest driver will do the recovery.

Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Signed-off-by: Cao jin <caoj.fnst@cn.fujitsu.com>
---
 hw/vfio/pci.c              | 247 +++++++++++++++++++++++++++++++++++++++++++++
 hw/vfio/pci.h              |   4 +
 linux-headers/linux/vfio.h |   2 +
 3 files changed, 253 insertions(+)

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 3d0d005..4912bc6 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2422,6 +2422,34 @@ static void vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
                      "Could not enable error recovery for the device",
                      vbasedev->name);
     }
+
+    irq_info.index = VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX;
+    irq_info.count = 0; /* clear */
+    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
+    if (ret) {
+        /* This can fail for an old kernel or legacy PCI dev */
+        trace_vfio_populate_device_get_irq_info_failure();
+    } else if (irq_info.count == 1) {
+        vdev->pci_aer_non_fatal = true;
+    } else {
+        error_report(WARN_PREFIX
+                     "Couldn't enable non fatal error recovery for the device",
+                     vbasedev->name);
+    }
+
+    irq_info.index = VFIO_PCI_PASSIVE_RESET_IRQ_INDEX;
+    irq_info.count = 0; /* clear */
+    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
+    if (ret) {
+        /* This can fail for an old kernel or legacy PCI dev */
+        trace_vfio_populate_device_get_irq_info_failure();
+    } else if (irq_info.count == 1) {
+        vdev->passive_reset = true;
+    } else {
+        error_report(WARN_PREFIX
+                     "Don't support passive reset notification",
+                     vbasedev->name);
+    }
 }
 
 static void vfio_put_device(VFIOPCIDevice *vdev)
@@ -2432,6 +2460,221 @@ static void vfio_put_device(VFIOPCIDevice *vdev)
     vfio_put_base_device(&vdev->vbasedev);
 }
 
+static void vfio_non_fatal_err_notifier_handler(void *opaque)
+{
+    VFIOPCIDevice *vdev = opaque;
+    PCIDevice *dev = &vdev->pdev;
+    PCIEAERMsg msg = {
+        .severity = PCI_ERR_ROOT_CMD_NONFATAL_EN,
+        .source_id = (pci_bus_num(dev->bus) << 8) | dev->devfn,
+    };
+
+    if (!event_notifier_test_and_clear(&vdev->non_fatal_err_notifier)) {
+        return;
+    }
+
+    /* Populate the aer msg and send it to root port */
+    if (dev->exp.aer_cap) {
+        uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+        uint32_t uncor_status;
+        bool isfatal;
+
+        uncor_status = vfio_pci_read_config(dev,
+                            dev->exp.aer_cap + PCI_ERR_UNCOR_STATUS, 4);
+        if (!uncor_status) {
+            return;
+        }
+
+        isfatal = uncor_status & pci_get_long(aer_cap + PCI_ERR_UNCOR_SEVER);
+        if (isfatal) {
+            goto stop;
+        }
+
+        error_report("%s sending non fatal event to root port. uncor status = "
+                     "0x%"PRIx32, vdev->vbasedev.name, uncor_status);
+        pcie_aer_msg(dev, &msg);
+        return;
+    }
+
+stop:
+    /* Terminate the guest in case of fatal error */
+    error_report("%s(%s) fatal error detected. Please collect any data"
+            " possible and then kill the guest", __func__, vdev->vbasedev.name);
+    vm_stop(RUN_STATE_INTERNAL_ERROR);
+}
+
+/*
+ * Register non fatal error notifier for devices supporting error recovery.
+ * If we encounter a failure in this function, we report an error
+ * and continue after disabling error recovery support for the device.
+ */
+static void vfio_register_non_fatal_err_notifier(VFIOPCIDevice *vdev)
+{
+    int ret;
+    int argsz;
+    struct vfio_irq_set *irq_set;
+    int32_t *pfd;
+
+    if (!vdev->pci_aer_non_fatal) {
+        return;
+    }
+
+    if (event_notifier_init(&vdev->non_fatal_err_notifier, 0)) {
+        error_report("vfio: Unable to init event notifier for non-fatal error detection");
+        vdev->pci_aer_non_fatal = false;
+        return;
+    }
+
+    argsz = sizeof(*irq_set) + sizeof(*pfd);
+
+    irq_set = g_malloc0(argsz);
+    irq_set->argsz = argsz;
+    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
+                     VFIO_IRQ_SET_ACTION_TRIGGER;
+    irq_set->index = VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX;
+    irq_set->start = 0;
+    irq_set->count = 1;
+    pfd = (int32_t *)&irq_set->data;
+
+    *pfd = event_notifier_get_fd(&vdev->non_fatal_err_notifier);
+    qemu_set_fd_handler(*pfd, vfio_non_fatal_err_notifier_handler, NULL, vdev);
+
+    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
+    if (ret) {
+        error_report("vfio: Failed to set up non-fatal error notification");
+        qemu_set_fd_handler(*pfd, NULL, NULL, vdev);
+        event_notifier_cleanup(&vdev->non_fatal_err_notifier);
+        vdev->pci_aer_non_fatal = false;
+    }
+    g_free(irq_set);
+}
+
+static void vfio_unregister_non_fatal_err_notifier(VFIOPCIDevice *vdev)
+{
+    int argsz;
+    struct vfio_irq_set *irq_set;
+    int32_t *pfd;
+    int ret;
+
+    if (!vdev->pci_aer_non_fatal) {
+        return;
+    }
+
+    argsz = sizeof(*irq_set) + sizeof(*pfd);
+
+    irq_set = g_malloc0(argsz);
+    irq_set->argsz = argsz;
+    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
+                     VFIO_IRQ_SET_ACTION_TRIGGER;
+    irq_set->index = VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX;
+    irq_set->start = 0;
+    irq_set->count = 1;
+    pfd = (int32_t *)&irq_set->data;
+    *pfd = -1;
+
+    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
+    if (ret) {
+        error_report("vfio: Failed to de-assign error fd: %m");
+    }
+    g_free(irq_set);
+    qemu_set_fd_handler(event_notifier_get_fd(&vdev->non_fatal_err_notifier),
+                        NULL, NULL, vdev);
+    event_notifier_cleanup(&vdev->non_fatal_err_notifier);
+}
+
+static void vfio_passive_reset_notifier_handler(void *opaque)
+{
+    VFIOPCIDevice *vdev = opaque;
+
+    if (!event_notifier_test_and_clear(&vdev->passive_reset_notifier)) {
+        return;
+    }
+
+    error_report("device %s is forced to be reset. Please collect any data"
+            " possible and then kill the guest", vdev->vbasedev.name);
+    vm_stop(RUN_STATE_INTERNAL_ERROR);
+}
+
+/*
+ * Register passive reset notifier, in case of certain function of a
+ * multifunction device is passthroughed,  while other functions are still
+ * controlled by device driver.
+ */
+static void vfio_register_passive_reset_notifier(VFIOPCIDevice *vdev)
+{
+    int ret;
+    int argsz;
+    struct vfio_irq_set *irq_set;
+    int32_t *pfd;
+
+    error_report("Registering event notifier for passive reset");
+    if (!vdev->passive_reset) {
+        return;
+    }
+
+    if (event_notifier_init(&vdev->passive_reset_notifier, 0)) {
+        error_report("vfio: Unable to init event notifier for passive reset");
+        vdev->passive_reset = false;
+        return;
+    }
+
+    argsz = sizeof(*irq_set) + sizeof(*pfd);
+
+    irq_set = g_malloc0(argsz);
+    irq_set->argsz = argsz;
+    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
+                     VFIO_IRQ_SET_ACTION_TRIGGER;
+    irq_set->index = VFIO_PCI_PASSIVE_RESET_IRQ_INDEX;
+    irq_set->start = 0;
+    irq_set->count = 1;
+    pfd = (int32_t *)&irq_set->data;
+
+    *pfd = event_notifier_get_fd(&vdev->passive_reset_notifier);
+    qemu_set_fd_handler(*pfd, vfio_passive_reset_notifier_handler, NULL, vdev);
+
+    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
+    if (ret) {
+        error_report("vfio: Failed to set up passive reset notification");
+        qemu_set_fd_handler(*pfd, NULL, NULL, vdev);
+        event_notifier_cleanup(&vdev->passive_reset_notifier);
+        vdev->passive_reset = false;
+    }
+    g_free(irq_set);
+}
+
+static void vfio_unregister_passive_reset_notifier(VFIOPCIDevice *vdev)
+{
+    int argsz;
+    struct vfio_irq_set *irq_set;
+    int32_t *pfd;
+    int ret;
+
+    if (!vdev->passive_reset) {
+        return;
+    }
+
+    argsz = sizeof(*irq_set) + sizeof(*pfd);
+
+    irq_set = g_malloc0(argsz);
+    irq_set->argsz = argsz;
+    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
+                     VFIO_IRQ_SET_ACTION_TRIGGER;
+    irq_set->index = VFIO_PCI_PASSIVE_RESET_IRQ_INDEX;
+    irq_set->start = 0;
+    irq_set->count = 1;
+    pfd = (int32_t *)&irq_set->data;
+    *pfd = -1;
+
+    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
+    if (ret) {
+        error_report("vfio: Failed to de-assign error fd: %m");
+    }
+    g_free(irq_set);
+    qemu_set_fd_handler(event_notifier_get_fd(&vdev->passive_reset_notifier),
+                        NULL, NULL, vdev);
+    event_notifier_cleanup(&vdev->passive_reset_notifier);
+}
+
 static void vfio_err_notifier_handler(void *opaque)
 {
     VFIOPCIDevice *vdev = opaque;
@@ -2860,6 +3103,8 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
         }
     }
 
+    vfio_register_passive_reset_notifier(vdev);
+    vfio_register_non_fatal_err_notifier(vdev);
     vfio_register_err_notifier(vdev);
     vfio_register_req_notifier(vdev);
     vfio_setup_resetfn_quirk(vdev);
@@ -2900,6 +3145,8 @@ static void vfio_exitfn(PCIDevice *pdev)
 
     vfio_unregister_req_notifier(vdev);
     vfio_unregister_err_notifier(vdev);
+    vfio_unregister_non_fatal_err_notifier(vdev);
+    vfio_unregister_passive_reset_notifier(vdev);
     pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
     vfio_disable_interrupts(vdev);
     if (vdev->intx.mmap_timer) {
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 34e8b04..dcb0e0a 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -119,6 +119,8 @@ typedef struct VFIOPCIDevice {
     void *igd_opregion;
     PCIHostDeviceAddress host;
     EventNotifier err_notifier;
+    EventNotifier non_fatal_err_notifier;
+    EventNotifier passive_reset_notifier;
     EventNotifier req_notifier;
     int (*resetfn)(struct VFIOPCIDevice *);
     uint32_t vendor_id;
@@ -137,6 +139,8 @@ typedef struct VFIOPCIDevice {
     uint32_t igd_gms;
     uint8_t pm_cap;
     bool pci_aer;
+    bool pci_aer_non_fatal;
+    bool passive_reset;
     bool req_enabled;
     bool has_flr;
     bool has_pm_reset;
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index 759b850..726ddbe 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -433,6 +433,8 @@ enum {
 	VFIO_PCI_MSIX_IRQ_INDEX,
 	VFIO_PCI_ERR_IRQ_INDEX,
 	VFIO_PCI_REQ_IRQ_INDEX,
+	VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX,
+	VFIO_PCI_PASSIVE_RESET_IRQ_INDEX,
 	VFIO_PCI_NUM_IRQS
 };
 
-- 
1.8.3.1

Re: [Qemu-devel] [PATCH v2 3/3] vfio-pci: process non fatal error of AER

[Michael S. Tsirkin]

On Wed, Mar 22, 2017 at 06:36:52PM +0800, Cao jin wrote:
> Make use of the non fatal error eventfd that the kernel module provide
> to process the AER non fatal error. Fatal error still goes into the
> legacy way which results in VM stop.
> 
> Register the handler, wait for notification. Construct aer message and
> pass it to root port on notification. Root port will trigger an interrupt
> to signal guest, then guest driver will do the recovery.
> 
> Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
> Signed-off-by: Cao jin <caoj.fnst@cn.fujitsu.com>
> ---
>  hw/vfio/pci.c              | 247 +++++++++++++++++++++++++++++++++++++++++++++
>  hw/vfio/pci.h              |   4 +
>  linux-headers/linux/vfio.h |   2 +
>  3 files changed, 253 insertions(+)
> 
> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> index 3d0d005..4912bc6 100644
> --- a/hw/vfio/pci.c
> +++ b/hw/vfio/pci.c
> @@ -2422,6 +2422,34 @@ static void vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
>                       "Could not enable error recovery for the device",
>                       vbasedev->name);
>      }
> +
> +    irq_info.index = VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX;
> +    irq_info.count = 0; /* clear */
> +    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
> +    if (ret) {
> +        /* This can fail for an old kernel or legacy PCI dev */
> +        trace_vfio_populate_device_get_irq_info_failure();
> +    } else if (irq_info.count == 1) {
> +        vdev->pci_aer_non_fatal = true;
> +    } else {
> +        error_report(WARN_PREFIX
> +                     "Couldn't enable non fatal error recovery for the device",
> +                     vbasedev->name);

when does this trigger?

> +    }
> +
> +    irq_info.index = VFIO_PCI_PASSIVE_RESET_IRQ_INDEX;
> +    irq_info.count = 0; /* clear */
> +    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
> +    if (ret) {
> +        /* This can fail for an old kernel or legacy PCI dev */
> +        trace_vfio_populate_device_get_irq_info_failure();
> +    } else if (irq_info.count == 1) {
> +        vdev->passive_reset = true;
> +    } else {
> +        error_report(WARN_PREFIX
> +                     "Don't support passive reset notification",
> +                     vbasedev->name);

when does this happen?
what does this message mean?

> +    }
>  }
>  
>  static void vfio_put_device(VFIOPCIDevice *vdev)
> @@ -2432,6 +2460,221 @@ static void vfio_put_device(VFIOPCIDevice *vdev)
>      vfio_put_base_device(&vdev->vbasedev);
>  }
>  
> +static void vfio_non_fatal_err_notifier_handler(void *opaque)
> +{
> +    VFIOPCIDevice *vdev = opaque;
> +    PCIDevice *dev = &vdev->pdev;
> +    PCIEAERMsg msg = {
> +        .severity = PCI_ERR_ROOT_CMD_NONFATAL_EN,
> +        .source_id = (pci_bus_num(dev->bus) << 8) | dev->devfn,
> +    };
> +

Should this just use pci_requester_id?


At least Peter thought so.

> +    if (!event_notifier_test_and_clear(&vdev->non_fatal_err_notifier)) {
> +        return;
> +    }
> +
> +    /* Populate the aer msg and send it to root port */
> +    if (dev->exp.aer_cap) {
> +        uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
> +        uint32_t uncor_status;
> +        bool isfatal;
> +
> +        uncor_status = vfio_pci_read_config(dev,
> +                            dev->exp.aer_cap + PCI_ERR_UNCOR_STATUS, 4);
> +        if (!uncor_status) {
> +            return;
> +        }
> +
> +        isfatal = uncor_status & pci_get_long(aer_cap + PCI_ERR_UNCOR_SEVER);
> +        if (isfatal) {
> +            goto stop;
> +        }
> +
> +        error_report("%s sending non fatal event to root port. uncor status = "
> +                     "0x%"PRIx32, vdev->vbasedev.name, uncor_status);
> +        pcie_aer_msg(dev, &msg);
> +        return;
> +    }
> +
> +stop:
> +    /* Terminate the guest in case of fatal error */
> +    error_report("%s(%s) fatal error detected. Please collect any data"
> +            " possible and then kill the guest", __func__, vdev->vbasedev.name);

"Device detected a fatal error. VM stopped".

would be better IMO.


> +    vm_stop(RUN_STATE_INTERNAL_ERROR);
> +}
> +
> +/*
> + * Register non fatal error notifier for devices supporting error recovery.
> + * If we encounter a failure in this function, we report an error
> + * and continue after disabling error recovery support for the device.
> + */
> +static void vfio_register_non_fatal_err_notifier(VFIOPCIDevice *vdev)
> +{
> +    int ret;
> +    int argsz;
> +    struct vfio_irq_set *irq_set;
> +    int32_t *pfd;
> +
> +    if (!vdev->pci_aer_non_fatal) {
> +        return;
> +    }
> +
> +    if (event_notifier_init(&vdev->non_fatal_err_notifier, 0)) {
> +        error_report("vfio: Unable to init event notifier for non-fatal error detection");
> +        vdev->pci_aer_non_fatal = false;
> +        return;
> +    }
> +
> +    argsz = sizeof(*irq_set) + sizeof(*pfd);
> +
> +    irq_set = g_malloc0(argsz);
> +    irq_set->argsz = argsz;
> +    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
> +                     VFIO_IRQ_SET_ACTION_TRIGGER;
> +    irq_set->index = VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX;
> +    irq_set->start = 0;
> +    irq_set->count = 1;
> +    pfd = (int32_t *)&irq_set->data;
> +
> +    *pfd = event_notifier_get_fd(&vdev->non_fatal_err_notifier);
> +    qemu_set_fd_handler(*pfd, vfio_non_fatal_err_notifier_handler, NULL, vdev);
> +
> +    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
> +    if (ret) {
> +        error_report("vfio: Failed to set up non-fatal error notification");
> +        qemu_set_fd_handler(*pfd, NULL, NULL, vdev);
> +        event_notifier_cleanup(&vdev->non_fatal_err_notifier);
> +        vdev->pci_aer_non_fatal = false;
> +    }
> +    g_free(irq_set);
> +}
> +
> +static void vfio_unregister_non_fatal_err_notifier(VFIOPCIDevice *vdev)
> +{
> +    int argsz;
> +    struct vfio_irq_set *irq_set;
> +    int32_t *pfd;
> +    int ret;
> +
> +    if (!vdev->pci_aer_non_fatal) {
> +        return;
> +    }
> +
> +    argsz = sizeof(*irq_set) + sizeof(*pfd);
> +
> +    irq_set = g_malloc0(argsz);
> +    irq_set->argsz = argsz;
> +    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
> +                     VFIO_IRQ_SET_ACTION_TRIGGER;
> +    irq_set->index = VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX;
> +    irq_set->start = 0;
> +    irq_set->count = 1;
> +    pfd = (int32_t *)&irq_set->data;
> +    *pfd = -1;
> +
> +    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
> +    if (ret) {
> +        error_report("vfio: Failed to de-assign error fd: %m");
> +    }
> +    g_free(irq_set);
> +    qemu_set_fd_handler(event_notifier_get_fd(&vdev->non_fatal_err_notifier),
> +                        NULL, NULL, vdev);
> +    event_notifier_cleanup(&vdev->non_fatal_err_notifier);
> +}
> +
> +static void vfio_passive_reset_notifier_handler(void *opaque)
> +{
> +    VFIOPCIDevice *vdev = opaque;
> +
> +    if (!event_notifier_test_and_clear(&vdev->passive_reset_notifier)) {
> +        return;
> +    }
> +
> +    error_report("device %s is forced to be reset. Please collect any data"
> +            " possible and then kill the guest", vdev->vbasedev.name);

I think we should just tell what happened in detail. Don't tell user what to do:

"Device lost state due to host device reset. VM stopped".


> +    vm_stop(RUN_STATE_INTERNAL_ERROR);
> +}
> +
> +/*
> + * Register passive reset notifier, in case of certain function of a
> + * multifunction device is passthroughed,  while other functions are still
> + * controlled by device driver.
> + */
> +static void vfio_register_passive_reset_notifier(VFIOPCIDevice *vdev)
> +{
> +    int ret;
> +    int argsz;
> +    struct vfio_irq_set *irq_set;
> +    int32_t *pfd;
> +
> +    error_report("Registering event notifier for passive reset");
> +    if (!vdev->passive_reset) {
> +        return;
> +    }
> +
> +    if (event_notifier_init(&vdev->passive_reset_notifier, 0)) {
> +        error_report("vfio: Unable to init event notifier for passive reset");
> +        vdev->passive_reset = false;
> +        return;
> +    }
> +
> +    argsz = sizeof(*irq_set) + sizeof(*pfd);
> +
> +    irq_set = g_malloc0(argsz);
> +    irq_set->argsz = argsz;
> +    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
> +                     VFIO_IRQ_SET_ACTION_TRIGGER;
> +    irq_set->index = VFIO_PCI_PASSIVE_RESET_IRQ_INDEX;
> +    irq_set->start = 0;
> +    irq_set->count = 1;
> +    pfd = (int32_t *)&irq_set->data;
> +
> +    *pfd = event_notifier_get_fd(&vdev->passive_reset_notifier);
> +    qemu_set_fd_handler(*pfd, vfio_passive_reset_notifier_handler, NULL, vdev);
> +
> +    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
> +    if (ret) {
> +        error_report("vfio: Failed to set up passive reset notification");
> +        qemu_set_fd_handler(*pfd, NULL, NULL, vdev);
> +        event_notifier_cleanup(&vdev->passive_reset_notifier);
> +        vdev->passive_reset = false;
> +    }
> +    g_free(irq_set);
> +}
> +
> +static void vfio_unregister_passive_reset_notifier(VFIOPCIDevice *vdev)
> +{
> +    int argsz;
> +    struct vfio_irq_set *irq_set;
> +    int32_t *pfd;
> +    int ret;
> +
> +    if (!vdev->passive_reset) {
> +        return;
> +    }
> +
> +    argsz = sizeof(*irq_set) + sizeof(*pfd);
> +
> +    irq_set = g_malloc0(argsz);
> +    irq_set->argsz = argsz;
> +    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD |
> +                     VFIO_IRQ_SET_ACTION_TRIGGER;
> +    irq_set->index = VFIO_PCI_PASSIVE_RESET_IRQ_INDEX;
> +    irq_set->start = 0;
> +    irq_set->count = 1;
> +    pfd = (int32_t *)&irq_set->data;
> +    *pfd = -1;
> +
> +    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set);
> +    if (ret) {
> +        error_report("vfio: Failed to de-assign error fd: %m");
> +    }
> +    g_free(irq_set);
> +    qemu_set_fd_handler(event_notifier_get_fd(&vdev->passive_reset_notifier),
> +                        NULL, NULL, vdev);
> +    event_notifier_cleanup(&vdev->passive_reset_notifier);
> +}
> +
>  static void vfio_err_notifier_handler(void *opaque)
>  {
>      VFIOPCIDevice *vdev = opaque;
> @@ -2860,6 +3103,8 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
>          }
>      }
>  
> +    vfio_register_passive_reset_notifier(vdev);
> +    vfio_register_non_fatal_err_notifier(vdev);
>      vfio_register_err_notifier(vdev);
>      vfio_register_req_notifier(vdev);
>      vfio_setup_resetfn_quirk(vdev);
> @@ -2900,6 +3145,8 @@ static void vfio_exitfn(PCIDevice *pdev)
>  
>      vfio_unregister_req_notifier(vdev);
>      vfio_unregister_err_notifier(vdev);
> +    vfio_unregister_non_fatal_err_notifier(vdev);
> +    vfio_unregister_passive_reset_notifier(vdev);
>      pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
>      vfio_disable_interrupts(vdev);
>      if (vdev->intx.mmap_timer) {
> diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
> index 34e8b04..dcb0e0a 100644
> --- a/hw/vfio/pci.h
> +++ b/hw/vfio/pci.h
> @@ -119,6 +119,8 @@ typedef struct VFIOPCIDevice {
>      void *igd_opregion;
>      PCIHostDeviceAddress host;
>      EventNotifier err_notifier;
> +    EventNotifier non_fatal_err_notifier;
> +    EventNotifier passive_reset_notifier;
>      EventNotifier req_notifier;
>      int (*resetfn)(struct VFIOPCIDevice *);
>      uint32_t vendor_id;
> @@ -137,6 +139,8 @@ typedef struct VFIOPCIDevice {
>      uint32_t igd_gms;
>      uint8_t pm_cap;
>      bool pci_aer;
> +    bool pci_aer_non_fatal;
> +    bool passive_reset;
>      bool req_enabled;
>      bool has_flr;
>      bool has_pm_reset;

Why do you need these flags? Why isn't the notifier sufficient?

> diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
> index 759b850..726ddbe 100644
> --- a/linux-headers/linux/vfio.h
> +++ b/linux-headers/linux/vfio.h
> @@ -433,6 +433,8 @@ enum {
>  	VFIO_PCI_MSIX_IRQ_INDEX,
>  	VFIO_PCI_ERR_IRQ_INDEX,
>  	VFIO_PCI_REQ_IRQ_INDEX,
> +	VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX,
> +	VFIO_PCI_PASSIVE_RESET_IRQ_INDEX,
>  	VFIO_PCI_NUM_IRQS
>  };
>  
> -- 
> 1.8.3.1
> 
> 

Re: [Qemu-devel] [PATCH v2 3/3] vfio-pci: process non fatal error of AER

[Cao jin]

On 03/22/2017 09:27 PM, Michael S. Tsirkin wrote:
> On Wed, Mar 22, 2017 at 06:36:52PM +0800, Cao jin wrote:
>> Make use of the non fatal error eventfd that the kernel module provide
>> to process the AER non fatal error. Fatal error still goes into the
>> legacy way which results in VM stop.
>>
>> Register the handler, wait for notification. Construct aer message and
>> pass it to root port on notification. Root port will trigger an interrupt
>> to signal guest, then guest driver will do the recovery.
>>
>> Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
>> Signed-off-by: Cao jin <caoj.fnst@cn.fujitsu.com>
>> ---
>>  hw/vfio/pci.c              | 247 +++++++++++++++++++++++++++++++++++++++++++++
>>  hw/vfio/pci.h              |   4 +
>>  linux-headers/linux/vfio.h |   2 +
>>  3 files changed, 253 insertions(+)
>>
>> diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
>> index 3d0d005..4912bc6 100644
>> --- a/hw/vfio/pci.c
>> +++ b/hw/vfio/pci.c
>> @@ -2422,6 +2422,34 @@ static void vfio_populate_device(VFIOPCIDevice *vdev, Error **errp)
>>                       "Could not enable error recovery for the device",
>>                       vbasedev->name);
>>      }
>> +
>> +    irq_info.index = VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX;
>> +    irq_info.count = 0; /* clear */
>> +    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
>> +    if (ret) {
>> +        /* This can fail for an old kernel or legacy PCI dev */
>> +        trace_vfio_populate_device_get_irq_info_failure();
>> +    } else if (irq_info.count == 1) {
>> +        vdev->pci_aer_non_fatal = true;
>> +    } else {
>> +        error_report(WARN_PREFIX
>> +                     "Couldn't enable non fatal error recovery for the device",
>> +                     vbasedev->name);
> 
> when does this trigger?
> 
>> +    }
>> +
>> +    irq_info.index = VFIO_PCI_PASSIVE_RESET_IRQ_INDEX;
>> +    irq_info.count = 0; /* clear */
>> +    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
>> +    if (ret) {
>> +        /* This can fail for an old kernel or legacy PCI dev */
>> +        trace_vfio_populate_device_get_irq_info_failure();
>> +    } else if (irq_info.count == 1) {
>> +        vdev->passive_reset = true;
>> +    } else {
>> +        error_report(WARN_PREFIX
>> +                     "Don't support passive reset notification",
>> +                     vbasedev->name);
> 
> when does this happen?
> what does this message mean?
> 

Both are boilerplate code as err_notifier. They will be triggered by
running latest QEMU on older kernel.  Will drop these code & the flags

>> +    }
>>  }
>>  
>>  static void vfio_put_device(VFIOPCIDevice *vdev)
>> @@ -2432,6 +2460,221 @@ static void vfio_put_device(VFIOPCIDevice *vdev)
>>      vfio_put_base_device(&vdev->vbasedev);
>>  }
>>  
>> +static void vfio_non_fatal_err_notifier_handler(void *opaque)
>> +{
>> +    VFIOPCIDevice *vdev = opaque;
>> +    PCIDevice *dev = &vdev->pdev;
>> +    PCIEAERMsg msg = {
>> +        .severity = PCI_ERR_ROOT_CMD_NONFATAL_EN,
>> +        .source_id = (pci_bus_num(dev->bus) << 8) | dev->devfn,
>> +    };
>> +
> 
> Should this just use pci_requester_id?
> 
> 
> At least Peter thought so.
> 
>> +    if (!event_notifier_test_and_clear(&vdev->non_fatal_err_notifier)) {
>> +        return;
>> +    }
>> +
>> +    /* Populate the aer msg and send it to root port */
>> +    if (dev->exp.aer_cap) {
>> +        uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
>> +        uint32_t uncor_status;
>> +        bool isfatal;
>> +
>> +        uncor_status = vfio_pci_read_config(dev,
>> +                            dev->exp.aer_cap + PCI_ERR_UNCOR_STATUS, 4);
>> +        if (!uncor_status) {
>> +            return;
>> +        }
>> +
>> +        isfatal = uncor_status & pci_get_long(aer_cap + PCI_ERR_UNCOR_SEVER);
>> +        if (isfatal) {
>> +            goto stop;
>> +        }
>> +
>> +        error_report("%s sending non fatal event to root port. uncor status = "
>> +                     "0x%"PRIx32, vdev->vbasedev.name, uncor_status);
>> +        pcie_aer_msg(dev, &msg);
>> +        return;
>> +    }
>> +
>> +stop:
>> +    /* Terminate the guest in case of fatal error */
>> +    error_report("%s(%s) fatal error detected. Please collect any data"
>> +            " possible and then kill the guest", __func__, vdev->vbasedev.name);
> 
> "Device detected a fatal error. VM stopped".
> 
> would be better IMO.
> 

Yes, user has no way to collect any data.

>> diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
>> index 34e8b04..dcb0e0a 100644
>> --- a/hw/vfio/pci.h
>> +++ b/hw/vfio/pci.h
>> @@ -119,6 +119,8 @@ typedef struct VFIOPCIDevice {
>>      void *igd_opregion;
>>      PCIHostDeviceAddress host;
>>      EventNotifier err_notifier;
>> +    EventNotifier non_fatal_err_notifier;
>> +    EventNotifier passive_reset_notifier;
>>      EventNotifier req_notifier;
>>      int (*resetfn)(struct VFIOPCIDevice *);
>>      uint32_t vendor_id;
>> @@ -137,6 +139,8 @@ typedef struct VFIOPCIDevice {
>>      uint32_t igd_gms;
>>      uint8_t pm_cap;
>>      bool pci_aer;
>> +    bool pci_aer_non_fatal;
>> +    bool passive_reset;
>>      bool req_enabled;
>>      bool has_flr;
>>      bool has_pm_reset;
> 
> Why do you need these flags? Why isn't the notifier sufficient?
> 

sounds good. Will remove pci_aer also

-- 
Sincerely,
Cao jin