virtio: features,fixes

Message-Id: <[email protected]>

Acked-by Srujana Challa <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/block/vhost-user-blk.c    | 1 +
 hw/net/vhost_net.c           | 2 ++
 hw/scsi/vhost-scsi.c         | 1 +
 hw/scsi/vhost-user-scsi.c    | 1 +
 hw/virtio/vhost-user-fs.c    | 2 +-
 hw/virtio/vhost-user-vsock.c | 1 +
 net/vhost-vdpa.c             | 1 +
 7 files changed, 8 insertions(+), 1 deletion(-)

hw/block/vhost-user-blk.c +1 -0

index 9e6bbc6950..bc2677dbef 100644
@@ -51,6 +51,7 @@ static const int user_feature_bits[] = {
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };

hw/net/vhost_net.c +2 -0

index fd1a93701a..18898afe81 100644
@@ -48,6 +48,7 @@ static const int kernel_feature_bits[] = {
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_NOTIFICATION_DATA,
     VIRTIO_NET_F_HASH_REPORT,
     VHOST_INVALID_FEATURE_BIT
 };

@@ -55,6 +56,7 @@ static const int kernel_feature_bits[] = {
 /* Features supported by others. */
 static const int user_feature_bits[] = {
     VIRTIO_F_NOTIFY_ON_EMPTY,
+    VIRTIO_F_NOTIFICATION_DATA,
     VIRTIO_RING_F_INDIRECT_DESC,
     VIRTIO_RING_F_EVENT_IDX,

hw/scsi/vhost-scsi.c +1 -0

index ae26bc19a4..3d5fe0994d 100644
@@ -38,6 +38,7 @@ static const int kernel_feature_bits[] = {
     VIRTIO_RING_F_EVENT_IDX,
     VIRTIO_SCSI_F_HOTPLUG,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };

hw/scsi/vhost-user-scsi.c +1 -0

index a63b1f4948..0b050805a8 100644
@@ -36,6 +36,7 @@ static const int user_feature_bits[] = {
     VIRTIO_RING_F_EVENT_IDX,
     VIRTIO_SCSI_F_HOTPLUG,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };

hw/virtio/vhost-user-fs.c +1 -1

index cca2cd41be..ae48cc1c96 100644
@@ -33,7 +33,7 @@ static const int user_feature_bits[] = {
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_RESET,
-
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };

hw/virtio/vhost-user-vsock.c +1 -0

index 9431b9792c..802b44a07d 100644
@@ -21,6 +21,7 @@ static const int user_feature_bits[] = {
     VIRTIO_RING_F_INDIRECT_DESC,
     VIRTIO_RING_F_EVENT_IDX,
     VIRTIO_F_NOTIFY_ON_EMPTY,
+    VIRTIO_F_NOTIFICATION_DATA,
     VHOST_INVALID_FEATURE_BIT
 };

net/vhost-vdpa.c +1 -0

index eda714d1a4..daa38428c5 100644
@@ -62,6 +62,7 @@ const int vdpa_feature_bits[] = {
     VIRTIO_F_RING_PACKED,
     VIRTIO_F_RING_RESET,
     VIRTIO_F_VERSION_1,
+    VIRTIO_F_NOTIFICATION_DATA,
     VIRTIO_NET_F_CSUM,
     VIRTIO_NET_F_CTRL_GUEST_OFFLOADS,
     VIRTIO_NET_F_CTRL_MAC_ADDR,

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:35 UTC #2 lore raw

[PULL v3 01/41] vhost: dirty log should be per backend type

From: Si-Wei Liu <[email protected]>

There could be a mix of both vhost-user and vhost-kernel clients in the same QEMU process, where separate vhost loggers for the specific vhost type have to be used. Make the vhost logger per backend type, and have them properly reference counted.

Signed-off-by Si-Wei Liu <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/virtio/vhost.c | 45 +++++++++++++++++++++++++++++++++------------
 1 file changed, 33 insertions(+), 12 deletions(-)

hw/virtio/vhost.c +33 ~~-12~~

index 4acd77e890..a1e8b79e1a 100644
@@ -43,8 +43,8 @@
     do { } while (0)
 #endif
 
-static struct vhost_log *vhost_log;
-static struct vhost_log *vhost_log_shm;
+static struct vhost_log *vhost_log[VHOST_BACKEND_TYPE_MAX];
+static struct vhost_log *vhost_log_shm[VHOST_BACKEND_TYPE_MAX];
 
 /* Memslots used by backends that support private memslots (without an fd). */
 static unsigned int used_memslots;

@@ -287,6 +287,10 @@ static int vhost_set_backend_type(struct vhost_dev *dev,
         r = -1;
     }
 
+    if (r == 0) {
+        assert(dev->vhost_ops->backend_type == backend_type);
+    }
+
     return r;
 }

@@ -319,16 +323,22 @@ static struct vhost_log *vhost_log_alloc(uint64_t size, bool share)
     return log;
 }
 
-static struct vhost_log *vhost_log_get(uint64_t size, bool share)
+static struct vhost_log *vhost_log_get(VhostBackendType backend_type,
+                                       uint64_t size, bool share)
 {
-    struct vhost_log *log = share ? vhost_log_shm : vhost_log;
+    struct vhost_log *log;
+
+    assert(backend_type > VHOST_BACKEND_TYPE_NONE);
+    assert(backend_type < VHOST_BACKEND_TYPE_MAX);
+
+    log = share ? vhost_log_shm[backend_type] : vhost_log[backend_type];
 
     if (!log || log->size != size) {
         log = vhost_log_alloc(size, share);
         if (share) {
-            vhost_log_shm = log;
+            vhost_log_shm[backend_type] = log;
         } else {
-            vhost_log = log;
+            vhost_log[backend_type] = log;
         }
     } else {
         ++log->refcnt;

@@ -340,11 +350,20 @@ static struct vhost_log *vhost_log_get(uint64_t size, bool share)
 static void vhost_log_put(struct vhost_dev *dev, bool sync)
 {
     struct vhost_log *log = dev->log;
+    VhostBackendType backend_type;
 
     if (!log) {
         return;
     }
 
+    assert(dev->vhost_ops);
+    backend_type = dev->vhost_ops->backend_type;
+
+    if (backend_type == VHOST_BACKEND_TYPE_NONE ||
+        backend_type >= VHOST_BACKEND_TYPE_MAX) {
+        return;
+    }
+
     --log->refcnt;
     if (log->refcnt == 0) {
         /* Sync only the range covered by the old log */

@@ -352,13 +371,13 @@ static void vhost_log_put(struct vhost_dev *dev, bool sync)
             vhost_log_sync_range(dev, 0, dev->log_size * VHOST_LOG_CHUNK - 1);
         }
 
-        if (vhost_log == log) {
+        if (vhost_log[backend_type] == log) {
             g_free(log->log);
-            vhost_log = NULL;
-        } else if (vhost_log_shm == log) {
+            vhost_log[backend_type] = NULL;
+        } else if (vhost_log_shm[backend_type] == log) {
             qemu_memfd_free(log->log, log->size * sizeof(*(log->log)),
                             log->fd);
-            vhost_log_shm = NULL;
+            vhost_log_shm[backend_type] = NULL;
         }
 
         g_free(log);

@@ -376,7 +395,8 @@ static bool vhost_dev_log_is_shared(struct vhost_dev *dev)
 
 static inline void vhost_dev_log_resize(struct vhost_dev *dev, uint64_t size)
 {
-    struct vhost_log *log = vhost_log_get(size, vhost_dev_log_is_shared(dev));
+    struct vhost_log *log = vhost_log_get(dev->vhost_ops->backend_type,
+                                          size, vhost_dev_log_is_shared(dev));
     uint64_t log_base = (uintptr_t)log->log;
     int r;

@@ -2044,7 +2064,8 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev, bool vrings)
         uint64_t log_base;
 
         hdev->log_size = vhost_get_log_size(hdev);
-        hdev->log = vhost_log_get(hdev->log_size,
+        hdev->log = vhost_log_get(hdev->vhost_ops->backend_type,
+                                  hdev->log_size,
                                   vhost_dev_log_is_shared(hdev));
         log_base = (uintptr_t)hdev->log->log;
         r = hdev->vhost_ops->vhost_set_log_base(hdev,

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:35 UTC #3 lore raw

[PULL v3 03/41] vhost-vdpa: check vhost_vdpa_set_vring_ready() return value

[1] https://lore.kernel.org/virtualization/[email protected]/T/#u

From: Stefano Garzarella <[email protected]>

vhost_vdpa_set_vring_ready() could already fail, but if Linux's patch [1] will be merged, it may fail with more chance if userspace does not activate virtqueues before DRIVER_OK when VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK is not negotiated.

So better check its return value anyway.

Acked-by Eugenio Pérez <[email protected]>

Acked-by Jason Wang <[email protected]>

Signed-off-by Stefano Garzarella <[email protected]>

Message-Id: <[email protected]>

Reviewed-by Philippe Mathieu-Daudé <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 net/vhost-vdpa.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

net/vhost-vdpa.c +12 -3

index 85e73dd6a7..eda714d1a4 100644
@@ -399,7 +399,10 @@ static int vhost_vdpa_net_data_load(NetClientState *nc)
     }
 
     for (int i = 0; i < v->dev->nvqs; ++i) {
-        vhost_vdpa_set_vring_ready(v, i + v->dev->vq_index);
+        int ret = vhost_vdpa_set_vring_ready(v, i + v->dev->vq_index);
+        if (ret < 0) {
+            return ret;
+        }
     }
     return 0;
 }

@@ -1238,7 +1241,10 @@ static int vhost_vdpa_net_cvq_load(NetClientState *nc)
 
     assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
 
-    vhost_vdpa_set_vring_ready(v, v->dev->vq_index);
+    r = vhost_vdpa_set_vring_ready(v, v->dev->vq_index);
+    if (unlikely(r < 0)) {
+        return r;
+    }
 
     if (v->shadow_vqs_enabled) {
         n = VIRTIO_NET(v->dev->vdev);

@@ -1277,7 +1283,10 @@ static int vhost_vdpa_net_cvq_load(NetClientState *nc)
     }
 
     for (int i = 0; i < v->dev->vq_index; ++i) {
-        vhost_vdpa_set_vring_ready(v, i);
+        r = vhost_vdpa_set_vring_ready(v, i);
+        if (unlikely(r < 0)) {
+            return r;
+        }
     }
 
     return 0;

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #4 lore raw

[PULL v3 09/41] Fix vhost user assertion when sending more than one fd

From: Christian Pötzsch <[email protected]>

If the client sends more than one region this assert triggers. The reason is that two fd's are 8 bytes and VHOST_MEMORY_BASELINE_NREGIONS is exactly 8.

The assert is wrong because it should not test for the size of the fd array, but for the numbers of regions.

Signed-off-by Christian Pötzsch <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 subprojects/libvhost-user/libvhost-user.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

subprojects/libvhost-user/libvhost-user.c +1 -1

index a879149fef..8adb277d54 100644
@@ -568,7 +568,7 @@ vu_message_read_default(VuDev *dev, int conn_fd, VhostUserMsg *vmsg)
         if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == SCM_RIGHTS) {
             fd_size = cmsg->cmsg_len - CMSG_LEN(0);
             vmsg->fd_num = fd_size / sizeof(int);
-            assert(fd_size < VHOST_MEMORY_BASELINE_NREGIONS);
+            assert(vmsg->fd_num <= VHOST_MEMORY_BASELINE_NREGIONS);
             memcpy(vmsg->fds, CMSG_DATA(cmsg), fd_size);
             break;
         }

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #5 lore raw

[PULL v3 07/41] virtio-ccw: Handle extra notification data

From: Jonah Palmer <[email protected]>

Add support to virtio-ccw devices for handling the extra data sent from the driver to the device when the VIRTIO_F_NOTIFICATION_DATA transport feature has been negotiated.

The extra data that's passed to the virtio-ccw device when this feature is enabled varies depending on the device's virtqueue layout.

That data passed to the virtio-ccw device is in the same format as the data passed to virtio-pci devices.

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/s390x/s390-virtio-ccw.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

hw/s390x/s390-virtio-ccw.c +13 -4

index 3d0bc3e7f2..956ef7b98d 100644
@@ -125,9 +125,11 @@ static void subsystem_reset(void)
 static int virtio_ccw_hcall_notify(const uint64_t *args)
 {
     uint64_t subch_id = args[0];
-    uint64_t queue = args[1];
+    uint64_t data = args[1];
     SubchDev *sch;
+    VirtIODevice *vdev;
     int cssid, ssid, schid, m;
+    uint16_t vq_idx = data;
 
     if (ioinst_disassemble_sch_ident(subch_id, &m, &cssid, &ssid, &schid)) {
         return -EINVAL;

@@ -136,12 +138,19 @@ static int virtio_ccw_hcall_notify(const uint64_t *args)
     if (!sch || !css_subch_visible(sch)) {
         return -EINVAL;
     }
-    if (queue >= VIRTIO_QUEUE_MAX) {
+
+    vdev = virtio_ccw_get_vdev(sch);
+    if (vq_idx >= VIRTIO_QUEUE_MAX || !virtio_queue_get_num(vdev, vq_idx)) {
         return -EINVAL;
     }
-    virtio_queue_notify(virtio_ccw_get_vdev(sch), queue);
-    return 0;
 
+    if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFICATION_DATA)) {
+        virtio_queue_set_shadow_avail_idx(virtio_get_queue(vdev, vq_idx),
+                                          (data >> 16) & 0xFFFF);
+    }
+
+    virtio_queue_notify(vdev, vq_idx);
+    return 0;
 }
 
 static int virtio_ccw_hcall_early_printk(const uint64_t *args)

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #6 lore raw

[PULL v3 11/41] hw/virtio: Fix obtain the buffer id from the last descriptor

From: Wafer <[email protected]>

The virtio-1.3 specification
<https://docs.oasis-open.org/virtio/virtio/v1.3/virtio-v1.3.html> writes:
2.8.6 Next Flag: Descriptor Chaining
Buffer ID is included in the last descriptor in the list.

If the feature (_F_INDIRECT_DESC) has been negotiated, install only one descriptor in the virtqueue.
Therefor the buffer id should be obtained from the first descriptor.

In descriptor chaining scenarios, the buffer id should be obtained from the last descriptor.

Fixes 86044b24e8 ("virtio: basic packed virtqueue support")

Signed-off-by Wafer <[email protected]>

Reviewed-by Jason Wang <[email protected]>

Reviewed-by Eugenio Pérez <[email protected]>

Acked-by Jason Wang <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/virtio/virtio.c | 5 +++++
 1 file changed, 5 insertions(+)

hw/virtio/virtio.c +5 -0

index 28cd406e16..3678ec2f88 100644
@@ -1745,6 +1745,11 @@ static void *virtqueue_packed_pop(VirtQueue *vq, size_t sz)
                                              &indirect_desc_cache);
     } while (rc == VIRTQUEUE_READ_DESC_MORE);
 
+    if (desc_cache != &indirect_desc_cache) {
+        /* Buffer ID is included in the last descriptor in the list. */
+        id = desc.id;
+    }
+
     /* Now copy what we have collected and mapped */
     elem = virtqueue_alloc_element(sz, out_num, in_num);
     for (i = 0; i < out_num; i++) {

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #7 lore raw

[PULL v3 30/41] hw/acpi/GI: Fix trivial parameter alignment issue.

From: Jonathan Cameron <[email protected]>

Before making additional modification, tidy up this misleading indentation.

Reviewed-by Ankit Agrawal <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/acpi/acpi_generic_initiator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

hw/acpi/acpi_generic_initiator.c +1 -1

index 17b9a052f5..18a939b0e5 100644
@@ -132,7 +132,7 @@ static int build_all_acpi_generic_initiators(Object *obj, void *opaque)
 
     dev_handle.segment = 0;
     dev_handle.bdf = PCI_BUILD_BDF(pci_bus_num(pci_get_bus(pci_dev)),
-                                               pci_dev->devfn);
+                                   pci_dev->devfn);
 
     build_srat_generic_pci_initiator_affinity(table_data,
                                               gi->node, &dev_handle);

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #8 lore raw

[PULL v3 16/41] hw/cxl/mailbox: change CCI cmd set structure to be a member, not a reference

From: Gregory Price <[email protected]>

This allows devices to have fully customized CCIs, along with complex devices where wrapper devices can override or add additional CCI commands without having to replicate full command structures or pollute a base device with every command that might ever be used.

Signed-off-by Gregory Price <[email protected]>

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/cxl/cxl_device.h |  2 +-
 hw/cxl/cxl-mailbox-utils.c  | 19 +++++++++++++++----
 2 files changed, 16 insertions(+), 5 deletions(-)

include/hw/cxl/cxl_device.h +1 -1

index 279b276bda..ccc4611875 100644
@@ -164,7 +164,7 @@ typedef struct CXLEventLog {
 } CXLEventLog;
 
 typedef struct CXLCCI {
-    const struct cxl_cmd (*cxl_cmd_set)[256];
+    struct cxl_cmd cxl_cmd_set[256][256];
     struct cel_log {
         uint16_t opcode;
         uint16_t effect;

hw/cxl/cxl-mailbox-utils.c +15 -4

index e5eb97cb91..2c9f50f0f9 100644
@@ -1447,10 +1447,21 @@ void cxl_init_cci(CXLCCI *cci, size_t payload_max)
                                  bg_timercb, cci);
 }
 
+static void cxl_copy_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmds)[256])
+{
+    for (int set = 0; set < 256; set++) {
+        for (int cmd = 0; cmd < 256; cmd++) {
+            if (cxl_cmds[set][cmd].handler) {
+                cci->cxl_cmd_set[set][cmd] = cxl_cmds[set][cmd];
+            }
+        }
+    }
+}
+
 void cxl_initialize_mailbox_swcci(CXLCCI *cci, DeviceState *intf,
                                   DeviceState *d, size_t payload_max)
 {
-    cci->cxl_cmd_set = cxl_cmd_set_sw;
+    cxl_copy_cci_commands(cci, cxl_cmd_set_sw);
     cci->d = d;
     cci->intf = intf;
     cxl_init_cci(cci, payload_max);

@@ -1458,7 +1469,7 @@ void cxl_initialize_mailbox_swcci(CXLCCI *cci, DeviceState *intf,
 
 void cxl_initialize_mailbox_t3(CXLCCI *cci, DeviceState *d, size_t payload_max)
 {
-    cci->cxl_cmd_set = cxl_cmd_set;
+    cxl_copy_cci_commands(cci, cxl_cmd_set);
     cci->d = d;
 
     /* No separation for PCI MB as protocol handled in PCI device */

@@ -1476,7 +1487,7 @@ static const struct cxl_cmd cxl_cmd_set_t3_ld[256][256] = {
 void cxl_initialize_t3_ld_cci(CXLCCI *cci, DeviceState *d, DeviceState *intf,
                                size_t payload_max)
 {
-    cci->cxl_cmd_set = cxl_cmd_set_t3_ld;
+    cxl_copy_cci_commands(cci, cxl_cmd_set_t3_ld);
     cci->d = d;
     cci->intf = intf;
     cxl_init_cci(cci, payload_max);

@@ -1496,7 +1507,7 @@ void cxl_initialize_t3_fm_owned_ld_mctpcci(CXLCCI *cci, DeviceState *d,
                                            DeviceState *intf,
                                            size_t payload_max)
 {
-    cci->cxl_cmd_set = cxl_cmd_set_t3_fm_owned_ld_mctp;
+    cxl_copy_cci_commands(cci, cxl_cmd_set_t3_fm_owned_ld_mctp);
     cci->d = d;
     cci->intf = intf;
     cxl_init_cci(cci, payload_max);

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #9 lore raw

[PULL v3 15/41] vhost-user: fix lost reconnect again

From: Li Feng <[email protected]>

When the vhost-user is reconnecting to the backend, and if the vhost-user fails at the get_features in vhost_dev_init(), then the reconnect will fail and it will not be retriggered forever.

The reason is:
When the vhost-user fail at get_features, the vhost_dev_cleanup will be called immediately.

vhost_dev_cleanup calls 'memset(hdev, 0, sizeof(struct vhost_dev))'.

The reconnect path is:
vhost_user_blk_event
vhost_user_async_close(.. vhost_user_blk_disconnect ..)
qemu_chr_fe_set_handlers <----- clear the notifier callback
schedule vhost_user_async_close_bh

The vhost->vdev is null, so the vhost_user_blk_disconnect will not be called, then the event fd callback will not be reinstalled.

We need to ensure that even if vhost_dev_init initialization fails, the event handler still needs to be reinstalled when s->connected is false.

All vhost-user devices have this issue, including vhost-user-blk/scsi.

Fixes 71e076a07d ("hw/virtio: generalise CHR_EVENT_CLOSED handling")

Signed-off-by Li Feng <[email protected]>

Message-Id: <[email protected]>

Reviewed-by Raphael Norwitz <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/block/vhost-user-blk.c   |  3 ++-
 hw/scsi/vhost-user-scsi.c   |  3 ++-
 hw/virtio/vhost-user-base.c |  3 ++-
 hw/virtio/vhost-user.c      | 10 +---------
 4 files changed, 7 insertions(+), 12 deletions(-)

hw/block/vhost-user-blk.c +2 -1

index 15cc24d017..fdbc30b9ce 100644
@@ -354,7 +354,7 @@ static void vhost_user_blk_disconnect(DeviceState *dev)
     VHostUserBlk *s = VHOST_USER_BLK(vdev);
 
     if (!s->connected) {
-        return;
+        goto done;
     }
     s->connected = false;

@@ -362,6 +362,7 @@ static void vhost_user_blk_disconnect(DeviceState *dev)
 
     vhost_dev_cleanup(&s->dev);
 
+done:
     /* Re-instate the event handler for new connections */
     qemu_chr_fe_set_handlers(&s->chardev, NULL, NULL, vhost_user_blk_event,
                              NULL, dev, NULL, true);

hw/scsi/vhost-user-scsi.c +2 -1

index 421cd654f8..cc91ade525 100644
@@ -182,7 +182,7 @@ static void vhost_user_scsi_disconnect(DeviceState *dev)
     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev);
 
     if (!s->connected) {
-        return;
+        goto done;
     }
     s->connected = false;

@@ -190,6 +190,7 @@ static void vhost_user_scsi_disconnect(DeviceState *dev)
 
     vhost_dev_cleanup(&vsc->dev);
 
+done:
     /* Re-instate the event handler for new connections */
     qemu_chr_fe_set_handlers(&vs->conf.chardev, NULL, NULL,
                              vhost_user_scsi_event, NULL, dev, NULL, true);

hw/virtio/vhost-user-base.c +2 -1

index 4b54255682..11e72b1e3b 100644
@@ -225,13 +225,14 @@ static void vub_disconnect(DeviceState *dev)
     VHostUserBase *vub = VHOST_USER_BASE(vdev);
 
     if (!vub->connected) {
-        return;
+        goto done;
     }
     vub->connected = false;
 
     vub_stop(vdev);
     vhost_dev_cleanup(&vub->vhost_dev);
 
+done:
     /* Re-instate the event handler for new connections */
     qemu_chr_fe_set_handlers(&vub->chardev,
                              NULL, NULL, vub_event,

hw/virtio/vhost-user.c +1 -9

index c929097e87..c407ea8939 100644
@@ -2781,16 +2781,8 @@ typedef struct {
 static void vhost_user_async_close_bh(void *opaque)
 {
     VhostAsyncCallback *data = opaque;
-    struct vhost_dev *vhost = data->vhost;
 
-    /*
-     * If the vhost_dev has been cleared in the meantime there is
-     * nothing left to do as some other path has completed the
-     * cleanup.
-     */
-    if (vhost->vdev) {
-        data->cb(data->dev);
-    }
+    data->cb(data->dev);
 
     g_free(data);
 }

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #10 lore raw

[PULL v3 33/41] linux-headers: update to 6.10-rc1

From: Thomas Weißschuh <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/standard-headers/linux/ethtool.h    |  55 ++++++++
 include/standard-headers/linux/pci_regs.h   |   6 +
 include/standard-headers/linux/pvpanic.h    |   7 +-
 include/standard-headers/linux/virtio_bt.h  |   1 -
 include/standard-headers/linux/virtio_mem.h |   2 +
 include/standard-headers/linux/virtio_net.h | 143 ++++++++++++++++++++
 linux-headers/asm-generic/unistd.h          |   5 +-
 linux-headers/asm-loongarch/kvm.h           |   4 +
 linux-headers/asm-mips/unistd_n32.h         |   1 +
 linux-headers/asm-mips/unistd_n64.h         |   1 +
 linux-headers/asm-mips/unistd_o32.h         |   1 +
 linux-headers/asm-powerpc/unistd_32.h       |   1 +
 linux-headers/asm-powerpc/unistd_64.h       |   1 +
 linux-headers/asm-riscv/kvm.h               |   1 +
 linux-headers/asm-s390/unistd_32.h          |   1 +
 linux-headers/asm-s390/unistd_64.h          |   1 +
 linux-headers/asm-x86/kvm.h                 |   4 +-
 linux-headers/asm-x86/unistd_32.h           |   1 +
 linux-headers/asm-x86/unistd_64.h           |   1 +
 linux-headers/asm-x86/unistd_x32.h          |   2 +
 linux-headers/linux/kvm.h                   |   4 +-
 linux-headers/linux/stddef.h                |   8 ++
 linux-headers/linux/vhost.h                 |  15 +-
 23 files changed, 252 insertions(+), 14 deletions(-)

include/standard-headers/linux/ethtool.h +55 -0

index 01503784d2..b0b4b68410 100644
@@ -752,6 +752,61 @@ enum ethtool_module_power_mode {
 	ETHTOOL_MODULE_POWER_MODE_HIGH,
 };
 
+/**
+ * enum ethtool_pse_types - Types of PSE controller.
+ * @ETHTOOL_PSE_UNKNOWN: Type of PSE controller is unknown
+ * @ETHTOOL_PSE_PODL: PSE controller which support PoDL
+ * @ETHTOOL_PSE_C33: PSE controller which support Clause 33 (PoE)
+ */
+enum ethtool_pse_types {
+	ETHTOOL_PSE_UNKNOWN =	1 << 0,
+	ETHTOOL_PSE_PODL =	1 << 1,
+	ETHTOOL_PSE_C33 =	1 << 2,
+};
+
+/**
+ * enum ethtool_c33_pse_admin_state - operational state of the PoDL PSE
+ *	functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState
+ * @ETHTOOL_C33_PSE_ADMIN_STATE_UNKNOWN: state of PSE functions is unknown
+ * @ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED: PSE functions are disabled
+ * @ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED: PSE functions are enabled
+ */
+enum ethtool_c33_pse_admin_state {
+	ETHTOOL_C33_PSE_ADMIN_STATE_UNKNOWN = 1,
+	ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED,
+	ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED,
+};
+
+/**
+ * enum ethtool_c33_pse_pw_d_status - power detection status of the PSE.
+ *	IEEE 802.3-2022 30.9.1.1.3 aPoDLPSEPowerDetectionStatus:
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_UNKNOWN: PSE status is unknown
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED: The enumeration "disabled"
+ *	indicates that the PSE State diagram is in the state DISABLED.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING: The enumeration "searching"
+ *	indicates the PSE State diagram is in a state other than those
+ *	listed.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING: The enumeration
+ *	"deliveringPower" indicates that the PSE State diagram is in the
+ *	state POWER_ON.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_TEST: The enumeration "test" indicates that
+ *	the PSE State diagram is in the state TEST_MODE.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_FAULT: The enumeration "fault" indicates that
+ *	the PSE State diagram is in the state TEST_ERROR.
+ * @ETHTOOL_C33_PSE_PW_D_STATUS_OTHERFAULT: The enumeration "otherFault"
+ *	indicates that the PSE State diagram is in the state IDLE due to
+ *	the variable error_condition = true.
+ */
+enum ethtool_c33_pse_pw_d_status {
+	ETHTOOL_C33_PSE_PW_D_STATUS_UNKNOWN = 1,
+	ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED,
+	ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING,
+	ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING,
+	ETHTOOL_C33_PSE_PW_D_STATUS_TEST,
+	ETHTOOL_C33_PSE_PW_D_STATUS_FAULT,
+	ETHTOOL_C33_PSE_PW_D_STATUS_OTHERFAULT,
+};
+
 /**
  * enum ethtool_podl_pse_admin_state - operational state of the PoDL PSE
  *	functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState

include/standard-headers/linux/pci_regs.h +6 -0

index a39193213f..94c00996e6 100644
@@ -1144,8 +1144,14 @@
 #define PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH		0x0003ffff
 
 #define PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX		0x000000ff
+#define PCI_DOE_DATA_OBJECT_DISC_REQ_3_VER		0x0000ff00
 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID		0x0000ffff
 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL		0x00ff0000
 #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX	0xff000000
 
+/* Compute Express Link (CXL r3.1, sec 8.1.5) */
+#define PCI_DVSEC_CXL_PORT				3
+#define PCI_DVSEC_CXL_PORT_CTL				0x0c
+#define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR		0x00000001
+
 #endif /* LINUX_PCI_REGS_H */

include/standard-headers/linux/pvpanic.h +5 -2

index 54b7485390..b115094431 100644
@@ -3,7 +3,10 @@
 #ifndef __PVPANIC_H__
 #define __PVPANIC_H__
 
-#define PVPANIC_PANICKED	(1 << 0)
-#define PVPANIC_CRASH_LOADED	(1 << 1)
+#include "standard-headers/linux/const.h"
+
+#define PVPANIC_PANICKED	_BITUL(0)
+#define PVPANIC_CRASH_LOADED	_BITUL(1)
+#define PVPANIC_SHUTDOWN	_BITUL(2)
 
 #endif /* __PVPANIC_H__ */

include/standard-headers/linux/virtio_bt.h +0 -1

index a11ecc3f92..6f0dee7e32 100644
@@ -13,7 +13,6 @@
 
 enum virtio_bt_config_type {
 	VIRTIO_BT_CONFIG_TYPE_PRIMARY	= 0,
-	VIRTIO_BT_CONFIG_TYPE_AMP	= 1,
 };
 
 enum virtio_bt_config_vendor {

include/standard-headers/linux/virtio_mem.h +2 -0

index 18c74c527c..6bfa41bd8b 100644
@@ -90,6 +90,8 @@
 #define VIRTIO_MEM_F_ACPI_PXM		0
 /* unplugged memory must not be accessed */
 #define VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE	1
+/* plugged memory will remain plugged when suspending+resuming */
+#define VIRTIO_MEM_F_PERSISTENT_SUSPEND		2
 
 
 /* --- virtio-mem: guest -> host requests --- */

include/standard-headers/linux/virtio_net.h +143 -0

153 lines not on this page · raw message

linux-headers/asm-generic/unistd.h +4 -1

index 75f00965ab..d983c48a3b 100644
@@ -842,8 +842,11 @@ __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
 #define __NR_lsm_list_modules 461
 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
 
+#define __NR_mseal 462
+__SYSCALL(__NR_mseal, sys_mseal)
+
 #undef __NR_syscalls
-#define __NR_syscalls 462
+#define __NR_syscalls 463
 
 /*
  * 32 bit systems traditionally used different

linux-headers/asm-loongarch/kvm.h +4 -0

index 109785922c..f9abef3823 100644
@@ -17,6 +17,8 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET	1
 #define KVM_DIRTY_LOG_PAGE_OFFSET	64
 
+#define KVM_GUESTDBG_USE_SW_BP		0x00010000
+
 /*
  * for KVM_GET_REGS and KVM_SET_REGS
  */

@@ -72,6 +74,8 @@ struct kvm_fpu {
 
 #define KVM_REG_LOONGARCH_COUNTER	(KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 1)
 #define KVM_REG_LOONGARCH_VCPU_RESET	(KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 2)
+/* Debugging: Special instruction for software breakpoint */
+#define KVM_REG_LOONGARCH_DEBUG_INST	(KVM_REG_LOONGARCH_KVM | KVM_REG_SIZE_U64 | 3)
 
 #define LOONGARCH_REG_SHIFT		3
 #define LOONGARCH_REG_64(TYPE, REG)	(TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT))

linux-headers/asm-mips/unistd_n32.h +1 -0

index ce2e050a9b..fc93b3be30 100644
@@ -390,5 +390,6 @@
 #define __NR_lsm_get_self_attr (__NR_Linux + 459)
 #define __NR_lsm_set_self_attr (__NR_Linux + 460)
 #define __NR_lsm_list_modules (__NR_Linux + 461)
+#define __NR_mseal (__NR_Linux + 462)
 
 #endif /* _ASM_UNISTD_N32_H */

linux-headers/asm-mips/unistd_n64.h +1 -0

index 5bfb3733ff..e72a3eb2c9 100644
@@ -366,5 +366,6 @@
 #define __NR_lsm_get_self_attr (__NR_Linux + 459)
 #define __NR_lsm_set_self_attr (__NR_Linux + 460)
 #define __NR_lsm_list_modules (__NR_Linux + 461)
+#define __NR_mseal (__NR_Linux + 462)
 
 #endif /* _ASM_UNISTD_N64_H */

linux-headers/asm-mips/unistd_o32.h +1 -0

index 02eaecd020..b86eb0786c 100644
@@ -436,5 +436,6 @@
 #define __NR_lsm_get_self_attr (__NR_Linux + 459)
 #define __NR_lsm_set_self_attr (__NR_Linux + 460)
 #define __NR_lsm_list_modules (__NR_Linux + 461)
+#define __NR_mseal (__NR_Linux + 462)
 
 #endif /* _ASM_UNISTD_O32_H */

linux-headers/asm-powerpc/unistd_32.h +1 -0

index bbab08d6ec..28627b6546 100644
@@ -443,6 +443,7 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 
 #endif /* _ASM_UNISTD_32_H */

linux-headers/asm-powerpc/unistd_64.h +1 -0

index af34cde70f..1fc42a8300 100644
@@ -415,6 +415,7 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 
 #endif /* _ASM_UNISTD_64_H */

linux-headers/asm-riscv/kvm.h +1 -0

index b1c503c295..e878e7cc39 100644
@@ -167,6 +167,7 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZFA,
 	KVM_RISCV_ISA_EXT_ZTSO,
 	KVM_RISCV_ISA_EXT_ZACAS,
+	KVM_RISCV_ISA_EXT_SSCOFPMF,
 	KVM_RISCV_ISA_EXT_MAX,
 };

linux-headers/asm-s390/unistd_32.h +1 -0

index a3ece69d82..7706c21b87 100644
@@ -434,5 +434,6 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 #endif /* _ASM_S390_UNISTD_32_H */

linux-headers/asm-s390/unistd_64.h +1 -0

index 8c5fd93495..62082d592d 100644
@@ -382,5 +382,6 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 #endif /* _ASM_S390_UNISTD_64_H */

linux-headers/asm-x86/kvm.h +3 -1

index 31c95c2dfe..b4e2e8d220 100644
@@ -709,7 +709,9 @@ struct kvm_sev_cmd {
 struct kvm_sev_init {
 	__u64 vmsa_features;
 	__u32 flags;
-	__u32 pad[9];
+	__u16 ghcb_version;
+	__u16 pad1;
+	__u32 pad2[8];
 };
 
 struct kvm_sev_launch_start {

linux-headers/asm-x86/unistd_32.h +1 -0

index 5c9c329e93..fb7b8b169b 100644
@@ -452,6 +452,7 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 
 #endif /* _ASM_UNISTD_32_H */

linux-headers/asm-x86/unistd_64.h +1 -0

index d9aab7ae87..da439afee1 100644
@@ -374,6 +374,7 @@
 #define __NR_lsm_get_self_attr 459
 #define __NR_lsm_set_self_attr 460
 #define __NR_lsm_list_modules 461
+#define __NR_mseal 462
 
 
 #endif /* _ASM_UNISTD_64_H */

linux-headers/asm-x86/unistd_x32.h +2 -0

index 63cdd1ee43..4fcb607c72 100644
@@ -318,6 +318,7 @@
 #define __NR_set_mempolicy_home_node (__X32_SYSCALL_BIT + 450)
 #define __NR_cachestat (__X32_SYSCALL_BIT + 451)
 #define __NR_fchmodat2 (__X32_SYSCALL_BIT + 452)
+#define __NR_map_shadow_stack (__X32_SYSCALL_BIT + 453)
 #define __NR_futex_wake (__X32_SYSCALL_BIT + 454)
 #define __NR_futex_wait (__X32_SYSCALL_BIT + 455)
 #define __NR_futex_requeue (__X32_SYSCALL_BIT + 456)

@@ -326,6 +327,7 @@
 #define __NR_lsm_get_self_attr (__X32_SYSCALL_BIT + 459)
 #define __NR_lsm_set_self_attr (__X32_SYSCALL_BIT + 460)
 #define __NR_lsm_list_modules (__X32_SYSCALL_BIT + 461)
+#define __NR_mseal (__X32_SYSCALL_BIT + 462)
 #define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512)
 #define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513)
 #define __NR_ioctl (__X32_SYSCALL_BIT + 514)

linux-headers/linux/kvm.h +2 -2

index 038731cdef..c93876ca0b 100644
@@ -1217,9 +1217,9 @@ struct kvm_vfio_spapr_tce {
 /* Available with KVM_CAP_SPAPR_RESIZE_HPT */
 #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
 #define KVM_PPC_RESIZE_HPT_COMMIT  _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
-/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */
+/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */
 #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
-/* Available with KVM_CAP_PPC_RADIX_MMU */
+/* Available with KVM_CAP_PPC_MMU_RADIX */
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
 /* Available with KVM_CAP_PPC_GET_CPU_CHAR */
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)

linux-headers/linux/stddef.h +8 -0

index bf9749dd14..96aa341942 100644
@@ -55,4 +55,12 @@
 #define __counted_by(m)
 #endif
 
+#ifndef __counted_by_le
+#define __counted_by_le(m)
+#endif
+
+#ifndef __counted_by_be
+#define __counted_by_be(m)
+#endif
+
 #endif /* _LINUX_STDDEF_H */

linux-headers/linux/vhost.h +8 -7

index bea6973906..b95dd84eef 100644
@@ -179,12 +179,6 @@
 /* Get the config size */
 #define VHOST_VDPA_GET_CONFIG_SIZE	_IOR(VHOST_VIRTIO, 0x79, __u32)
 
-/* Get the count of all virtqueues */
-#define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
-
-/* Get the number of virtqueue groups. */
-#define VHOST_VDPA_GET_GROUP_NUM	_IOR(VHOST_VIRTIO, 0x81, __u32)
-
 /* Get the number of address spaces. */
 #define VHOST_VDPA_GET_AS_NUM		_IOR(VHOST_VIRTIO, 0x7A, unsigned int)

@@ -228,10 +222,17 @@
 #define VHOST_VDPA_GET_VRING_DESC_GROUP	_IOWR(VHOST_VIRTIO, 0x7F,	\
 					      struct vhost_vring_state)
 
+
+/* Get the count of all virtqueues */
+#define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
+
+/* Get the number of virtqueue groups. */
+#define VHOST_VDPA_GET_GROUP_NUM	_IOR(VHOST_VIRTIO, 0x81, __u32)
+
 /* Get the queue size of a specific virtqueue.
  * userspace set the vring index in vhost_vring_state.index
  * kernel set the queue size in vhost_vring_state.num
  */
-#define VHOST_VDPA_GET_VRING_SIZE	_IOWR(VHOST_VIRTIO, 0x80,	\
+#define VHOST_VDPA_GET_VRING_SIZE	_IOWR(VHOST_VIRTIO, 0x82,	\
 					      struct vhost_vring_state)
 #endif

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #11 lore raw

[PULL v3 25/41] hw/cxl/cxl-mailbox-utils: Add mailbox commands to support add/release dynamic capacity response

From: Fan Ni <[email protected]>

Per CXL spec 3.1, two mailbox commands are implemented:
Add Dynamic Capacity Response (Opcode 4802h) 8.2.9.9.9.3, and Release Dynamic Capacity (Opcode 4803h) 8.2.9.9.9.4.

For the process of the above two commands, we use two-pass approach. Pass 1: Check whether the input payload is valid or not; if not, skip
Pass 2 and return mailbox process error.
Pass 2: Do the real work--add or release extents, respectively.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/cxl/cxl_device.h |   4 +
 hw/cxl/cxl-mailbox-utils.c  | 394 ++++++++++++++++++++++++++++++++++++
 hw/mem/cxl_type3.c          |  11 +
 3 files changed, 409 insertions(+)

include/hw/cxl/cxl_device.h +4 -0

index 6aec6ac983..df3511e91b 100644
@@ -551,4 +551,8 @@ void cxl_event_irq_assert(CXLType3Dev *ct3d);
 
 void cxl_set_poison_list_overflowed(CXLType3Dev *ct3d);
 
+CXLDCRegion *cxl_find_dc_region(CXLType3Dev *ct3d, uint64_t dpa, uint64_t len);
+
+void cxl_remove_extent_from_extent_list(CXLDCExtentList *list,
+                                        CXLDCExtent *extent);
 #endif

hw/cxl/cxl-mailbox-utils.c +394 -0

418 lines not on this page · raw message

hw/mem/cxl_type3.c +11 -0

index 2075846b1b..db5191b3b7 100644
@@ -678,6 +678,15 @@ static bool cxl_create_dc_regions(CXLType3Dev *ct3d, Error **errp)
     return true;
 }
 
+static void cxl_destroy_dc_regions(CXLType3Dev *ct3d)
+{
+    CXLDCExtent *ent, *ent_next;
+
+    QTAILQ_FOREACH_SAFE(ent, &ct3d->dc.extents, node, ent_next) {
+        cxl_remove_extent_from_extent_list(&ct3d->dc.extents, ent);
+    }
+}
+
 static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
 {
     DeviceState *ds = DEVICE(ct3d);

@@ -874,6 +883,7 @@ err_free_special_ops:
     g_free(regs->special_ops);
 err_address_space_free:
     if (ct3d->dc.host_dc) {
+        cxl_destroy_dc_regions(ct3d);
         address_space_destroy(&ct3d->dc.host_dc_as);
     }
     if (ct3d->hostpmem) {

@@ -895,6 +905,7 @@ static void ct3_exit(PCIDevice *pci_dev)
     cxl_doe_cdat_release(cxl_cstate);
     g_free(regs->special_ops);
     if (ct3d->dc.host_dc) {
+        cxl_destroy_dc_regions(ct3d);
         address_space_destroy(&ct3d->dc.host_dc_as);
     }
     if (ct3d->hostpmem) {

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #12 lore raw

[PULL v3 23/41] hw/mem/cxl_type3: Add host backend and address space handling for DC regions

From: Fan Ni <[email protected]>

Add (file/memory backed) host backend for DCD. All the dynamic capacity regions will share a single, large enough host backend. Set up address space for DC regions to support read/write operations to dynamic capacity for DCD.

With the change, the following support is added:
1. Add a new property to type3 device "volatile-dc-memdev" to point to host memory backend for dynamic capacity. Currently, all DC regions share one host backend;
2. Add namespace for dynamic capacity for read/write support;
3. Create cdat entries for each dynamic capacity region.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/cxl/cxl_device.h |   8 ++
 hw/cxl/cxl-mailbox-utils.c  |  16 +++-
 hw/mem/cxl_type3.c          | 177 +++++++++++++++++++++++++++++-------
 3 files changed, 164 insertions(+), 37 deletions(-)

include/hw/cxl/cxl_device.h +8 -0

index f7f56b44e3..c2c3df0d2a 100644
@@ -467,6 +467,14 @@ struct CXLType3Dev {
     uint64_t poison_list_overflow_ts;
 
     struct dynamic_capacity {
+        HostMemoryBackend *host_dc;
+        AddressSpace host_dc_as;
+        /*
+         * total_capacity is equivalent to the dynamic capability
+         * memory region size.
+         */
+        uint64_t total_capacity; /* 256M aligned */
+
         uint8_t num_regions; /* 0-8 regions */
         CXLDCRegion regions[DCD_MAX_NUM_REGION];
     } dc;

hw/cxl/cxl-mailbox-utils.c +11 -5

index b592473587..6ad227f112 100644
@@ -622,7 +622,8 @@ static CXLRetCode cmd_firmware_update_get_info(const struct cxl_cmd *cmd,
                                                size_t *len_out,
                                                CXLCCI *cci)
 {
-    CXLDeviceState *cxl_dstate = &CXL_TYPE3(cci->d)->cxl_dstate;
+    CXLType3Dev *ct3d = CXL_TYPE3(cci->d);
+    CXLDeviceState *cxl_dstate = &ct3d->cxl_dstate;
     struct {
         uint8_t slots_supported;
         uint8_t slot_info;

@@ -636,7 +637,8 @@ static CXLRetCode cmd_firmware_update_get_info(const struct cxl_cmd *cmd,
     QEMU_BUILD_BUG_ON(sizeof(*fw_info) != 0x50);
 
     if ((cxl_dstate->vmem_size < CXL_CAPACITY_MULTIPLIER) ||
-        (cxl_dstate->pmem_size < CXL_CAPACITY_MULTIPLIER)) {
+        (cxl_dstate->pmem_size < CXL_CAPACITY_MULTIPLIER) ||
+        (ct3d->dc.total_capacity < CXL_CAPACITY_MULTIPLIER)) {
         return CXL_MBOX_INTERNAL_ERROR;
     }

@@ -793,7 +795,8 @@ static CXLRetCode cmd_identify_memory_device(const struct cxl_cmd *cmd,
     CXLDeviceState *cxl_dstate = &ct3d->cxl_dstate;
 
     if ((!QEMU_IS_ALIGNED(cxl_dstate->vmem_size, CXL_CAPACITY_MULTIPLIER)) ||
-        (!QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER))) {
+        (!QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER)) ||
+        (!QEMU_IS_ALIGNED(ct3d->dc.total_capacity, CXL_CAPACITY_MULTIPLIER))) {
         return CXL_MBOX_INTERNAL_ERROR;
     }

@@ -835,9 +838,11 @@ static CXLRetCode cmd_ccls_get_partition_info(const struct cxl_cmd *cmd,
         uint64_t next_pmem;
     } QEMU_PACKED *part_info = (void *)payload_out;
     QEMU_BUILD_BUG_ON(sizeof(*part_info) != 0x20);
+    CXLType3Dev *ct3d = container_of(cxl_dstate, CXLType3Dev, cxl_dstate);
 
     if ((!QEMU_IS_ALIGNED(cxl_dstate->vmem_size, CXL_CAPACITY_MULTIPLIER)) ||
-        (!QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER))) {
+        (!QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER)) ||
+        (!QEMU_IS_ALIGNED(ct3d->dc.total_capacity, CXL_CAPACITY_MULTIPLIER))) {
         return CXL_MBOX_INTERNAL_ERROR;
     }

@@ -1179,7 +1184,8 @@ static CXLRetCode cmd_media_clear_poison(const struct cxl_cmd *cmd,
     struct clear_poison_pl *in = (void *)payload_in;
 
     dpa = ldq_le_p(&in->dpa);
-    if (dpa + CXL_CACHE_LINE_SIZE > cxl_dstate->static_mem_size) {
+    if (dpa + CXL_CACHE_LINE_SIZE > cxl_dstate->static_mem_size +
+        ct3d->dc.total_capacity) {
         return CXL_MBOX_INVALID_PA;
     }

hw/mem/cxl_type3.c +145 ~~-32~~

326 lines not on this page · raw message

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:36 UTC #13 lore raw

[PULL v3 24/41] hw/mem/cxl_type3: Add DC extent list representative and get DC extent list mailbox support

From: Fan Ni <[email protected]>

Add dynamic capacity extent list representative to the definition of CXLType3Dev and implement get DC extent list mailbox command per CXL.spec.3.1:.8.2.9.9.9.2.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/cxl/cxl_device.h | 22 +++++++++++
 hw/cxl/cxl-mailbox-utils.c  | 73 ++++++++++++++++++++++++++++++++++++-
 hw/mem/cxl_type3.c          |  1 +
 3 files changed, 95 insertions(+), 1 deletion(-)

include/hw/cxl/cxl_device.h +22 -0

index c2c3df0d2a..6aec6ac983 100644
@@ -424,6 +424,25 @@ typedef QLIST_HEAD(, CXLPoison) CXLPoisonList;
 
 #define DCD_MAX_NUM_REGION 8
 
+typedef struct CXLDCExtentRaw {
+    uint64_t start_dpa;
+    uint64_t len;
+    uint8_t tag[0x10];
+    uint16_t shared_seq;
+    uint8_t rsvd[0x6];
+} QEMU_PACKED CXLDCExtentRaw;
+
+typedef struct CXLDCExtent {
+    uint64_t start_dpa;
+    uint64_t len;
+    uint8_t tag[0x10];
+    uint16_t shared_seq;
+    uint8_t rsvd[0x6];
+
+    QTAILQ_ENTRY(CXLDCExtent) node;
+} CXLDCExtent;
+typedef QTAILQ_HEAD(, CXLDCExtent) CXLDCExtentList;
+
 typedef struct CXLDCRegion {
     uint64_t base;       /* aligned to 256*MiB */
     uint64_t decode_len; /* aligned to 256*MiB */

@@ -474,6 +493,9 @@ struct CXLType3Dev {
          * memory region size.
          */
         uint64_t total_capacity; /* 256M aligned */
+        CXLDCExtentList extents;
+        uint32_t total_extent_count;
+        uint32_t ext_list_gen_seq;
 
         uint8_t num_regions; /* 0-8 regions */
         CXLDCRegion regions[DCD_MAX_NUM_REGION];

hw/cxl/cxl-mailbox-utils.c +72 -1

97 lines not on this page · raw message

hw/mem/cxl_type3.c +1 -0

index 658570aa1a..2075846b1b 100644
@@ -673,6 +673,7 @@ static bool cxl_create_dc_regions(CXLType3Dev *ct3d, Error **errp)
         };
         ct3d->dc.total_capacity += region->len;
     }
+    QTAILQ_INIT(&ct3d->dc.extents);
 
     return true;
 }

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #14 lore raw

[PULL v3 13/41] vhost-user-gpu: fix import of DMABUF

From: Marc-André Lureau <[email protected]>

When using vhost-user-gpu with GL, qemu -display gtk doesn't show output and prints: qemu: eglCreateImageKHR failed

Since commit 9ac06df8b ("virtio-gpu-udmabuf: correct naming of QemuDmaBuf size properties"), egl_dmabuf_import_texture() uses backing_{width,height} for the texture dimension.

Fixes 9ac06df8b ("virtio-gpu-udmabuf: correct naming of QemuDmaBuf size properties")

Signed-off-by Marc-André Lureau <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/display/vhost-user-gpu.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

hw/display/vhost-user-gpu.c +3 -2

index e4b398d26c..63c64ddde6 100644
@@ -281,8 +281,9 @@ vhost_user_gpu_handle_display(VhostUserGPU *g, VhostUserGpuMsg *msg)
             modifier = m2->modifier;
         }
 
-        dmabuf = qemu_dmabuf_new(m->fd_width, m->fd_height,
-                                 m->fd_stride, 0, 0, 0, 0,
+        dmabuf = qemu_dmabuf_new(m->width, m->height,
+                                 m->fd_stride, 0, 0,
+                                 m->fd_width, m->fd_height,
                                  m->fd_drm_fourcc, modifier,
                                  fd, false, m->fd_flags &
                                  VIRTIO_GPU_RESOURCE_FLAG_Y_0_TOP);

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #15 lore raw

[PULL v3 26/41] hw/cxl/events: Add qmp interfaces to add/release dynamic capacity extents

From: Fan Ni <[email protected]>

To simulate FM functionalities for initiating Dynamic Capacity Add (Opcode 5604h) and Dynamic Capacity Release (Opcode 5605h) as in CXL spec r3.1 7.6.7.6.5 and 7.6.7.6.6, we implemented two QMP interfaces to issue add/release dynamic capacity extents requests.

With the change, we allow to release an extent only when its DPA range is contained by a single accepted extent in the device. That is to say, extent superset release is not supported yet.

1. Add dynamic capacity extents:

For example, the command to add two continuous extents (each 128MiB long) to region 0 (starting at DPA offset 0) looks like below:

{ "execute": "qmp_capabilities" }

{ "execute": "cxl-add-dynamic-capacity",

  "arguments": {
      "path": "/machine/peripheral/cxl-dcd0",
      "host-id": 0,
      "selection-policy": "prescriptive",
      "region": 0,
      "extents": [
      {
          "offset": 0,
          "len": 134217728
      },
      {
          "offset": 134217728,
          "len": 134217728
      }
      ]

}
}

2. Release dynamic capacity extents:

For example, the command to release an extent of size 128MiB from region 0 (DPA offset 128MiB) looks like below:

{ "execute": "cxl-release-dynamic-capacity",

  "arguments": {
      "path": "/machine/peripheral/cxl-dcd0",
      "host-id": 0,
      "removal-policy":"prescriptive",
      "region": 0,
      "extents": [
      {
          "offset": 134217728,
          "len": 134217728
      }
      ]

}
}

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 qapi/cxl.json               | 143 +++++++++++++++++
 include/hw/cxl/cxl_device.h |  22 +++
 include/hw/cxl/cxl_events.h |  18 +++
 hw/cxl/cxl-mailbox-utils.c  |  62 ++++++--
 hw/mem/cxl_type3.c          | 306 +++++++++++++++++++++++++++++++++++-
 hw/mem/cxl_type3_stubs.c    |  25 +++
 6 files changed, 563 insertions(+), 13 deletions(-)

qapi/cxl.json +143 -0

index 4281726dec..57d9f82014 100644
@@ -361,3 +361,146 @@
 ##
 {'command': 'cxl-inject-correctable-error',
  'data': {'path': 'str', 'type': 'CxlCorErrorType'}}
+
+##
+# @CXLDynamicCapacityExtent:
+#
+# A single dynamic capacity extent
+#
+# @offset: The offset (in bytes) to the start of the region
+#     where the extent belongs to.
+#
+# @len: The length of the extent in bytes.
+#
+# Since: 9.1
+##
+{ 'struct': 'CXLDynamicCapacityExtent',
+  'data': {
+      'offset':'uint64',
+      'len': 'uint64'
+  }
+}
+
+##
+# @CXLExtSelPolicy:
+#
+# The policy to use for selecting which extents comprise the added
+# capacity, as defined in cxl spec r3.1 Table 7-70.
+#
+# @free: 0h = Free
+#
+# @contiguous: 1h = Continuous
+#
+# @prescriptive: 2h = Prescriptive
+#
+# @enable-shared-access: 3h = Enable Shared Access
+#
+# Since: 9.1
+##
+{ 'enum': 'CXLExtSelPolicy',
+  'data': ['free',
+           'contiguous',
+           'prescriptive',
+           'enable-shared-access']
+}
+
+##
+# @cxl-add-dynamic-capacity:
+#
+# Command to initiate to add dynamic capacity extents to a host.  It
+# simulates operations defined in cxl spec r3.1 7.6.7.6.5.
+#
+# @path: CXL DCD canonical QOM path.
+#
+# @host-id: The "Host ID" field as defined in cxl spec r3.1
+#     Table 7-70.
+#
+# @selection-policy: The "Selection Policy" bits as defined in
+#     cxl spec r3.1 Table 7-70.  It specifies the policy to use for
+#     selecting which extents comprise the added capacity.
+#
+# @region: The "Region Number" field as defined in cxl spec r3.1
+#     Table 7-70.  The dynamic capacity region where the capacity
+#     is being added.  Valid range is from 0-7.
+#
+# @tag: The "Tag" field as defined in cxl spec r3.1 Table 7-70.
+#
+# @extents: The "Extent List" field as defined in cxl spec r3.1
+#     Table 7-70.
+#
+# Since : 9.1
+##
+{ 'command': 'cxl-add-dynamic-capacity',
+  'data': { 'path': 'str',
+            'host-id': 'uint16',
+            'selection-policy': 'CXLExtSelPolicy',
+            'region': 'uint8',
+            '*tag': 'str',
+            'extents': [ 'CXLDynamicCapacityExtent' ]
+           }
+}
+
+##
+# @CXLExtRemovalPolicy:
+#
+# The policy to use for selecting which extents comprise the released
+# capacity, defined in the "Flags" field in cxl spec r3.1 Table 7-71.
+#
+# @tag-based: value = 0h.  Extents are selected by the device based
+#     on tag, with no requirement for contiguous extents.
+#
+# @prescriptive: value = 1h.  Extent list of capacity to release is
+#     included in the request payload.
+#
+# Since: 9.1
+##
+{ 'enum': 'CXLExtRemovalPolicy',
+  'data': ['tag-based',
+           'prescriptive']
+}
+
+##
+# @cxl-release-dynamic-capacity:
+#
+# Command to initiate to release dynamic capacity extents from a
+# host.  It simulates operations defined in cxl spec r3.1 7.6.7.6.6.
+#
+# @path: CXL DCD canonical QOM path.
+#
+# @host-id: The "Host ID" field as defined in cxl spec r3.1
+#     Table 7-71.
+#
+# @removal-policy: Bit[3:0] of the "Flags" field as defined in cxl
+#     spec r3.1 Table 7-71.
+#
+# @forced-removal: Bit[4] of the "Flags" field in cxl spec r3.1
+#     Table 7-71.  When set, device does not wait for a Release
+#     Dynamic Capacity command from the host.  Host immediately
+#     loses access to released capacity.
+#
+# @sanitize-on-release: Bit[5] of the "Flags" field in cxl spec r3.1
+#     Table 7-71.  When set, device should sanitize all released
+#     capacity as a result of this request.
+#
+# @region: The "Region Number" field as defined in cxl spec r3.1
+#     Table 7-71.  The dynamic capacity region where the capacity
+#     is being added.  Valid range is from 0-7.
+#
+# @tag: The "Tag" field as defined in cxl spec r3.1 Table 7-71.
+#
+# @extents: The "Extent List" field as defined in cxl spec r3.1
+#     Table 7-71.
+#
+# Since : 9.1
+##
+{ 'command': 'cxl-release-dynamic-capacity',
+  'data': { 'path': 'str',
+            'host-id': 'uint16',
+            'removal-policy': 'CXLExtRemovalPolicy',
+            '*forced-removal': 'bool',
+            '*sanitize-on-release': 'bool',
+            'region': 'uint8',
+            '*tag': 'str',
+            'extents': [ 'CXLDynamicCapacityExtent' ]
+           }
+}

include/hw/cxl/cxl_device.h +22 -0

index df3511e91b..c69ff6b5de 100644
@@ -443,6 +443,12 @@ typedef struct CXLDCExtent {
 } CXLDCExtent;
 typedef QTAILQ_HEAD(, CXLDCExtent) CXLDCExtentList;
 
+typedef struct CXLDCExtentGroup {
+    CXLDCExtentList list;
+    QTAILQ_ENTRY(CXLDCExtentGroup) node;
+} CXLDCExtentGroup;
+typedef QTAILQ_HEAD(, CXLDCExtentGroup) CXLDCExtentGroupList;
+
 typedef struct CXLDCRegion {
     uint64_t base;       /* aligned to 256*MiB */
     uint64_t decode_len; /* aligned to 256*MiB */

@@ -494,6 +500,7 @@ struct CXLType3Dev {
          */
         uint64_t total_capacity; /* 256M aligned */
         CXLDCExtentList extents;
+        CXLDCExtentGroupList extents_pending;
         uint32_t total_extent_count;
         uint32_t ext_list_gen_seq;

@@ -555,4 +562,19 @@ CXLDCRegion *cxl_find_dc_region(CXLType3Dev *ct3d, uint64_t dpa, uint64_t len);
 
 void cxl_remove_extent_from_extent_list(CXLDCExtentList *list,
                                         CXLDCExtent *extent);
+void cxl_insert_extent_to_extent_list(CXLDCExtentList *list, uint64_t dpa,
+                                      uint64_t len, uint8_t *tag,
+                                      uint16_t shared_seq);
+bool test_any_bits_set(const unsigned long *addr, unsigned long nr,
+                       unsigned long size);
+bool cxl_extents_contains_dpa_range(CXLDCExtentList *list,
+                                    uint64_t dpa, uint64_t len);
+CXLDCExtentGroup *cxl_insert_extent_to_extent_group(CXLDCExtentGroup *group,
+                                                    uint64_t dpa,
+                                                    uint64_t len,
+                                                    uint8_t *tag,
+                                                    uint16_t shared_seq);
+void cxl_extent_group_list_insert_tail(CXLDCExtentGroupList *list,
+                                       CXLDCExtentGroup *group);
+void cxl_extent_group_list_delete_front(CXLDCExtentGroupList *list);
 #endif

include/hw/cxl/cxl_events.h +18 -0

index 5170b8dbf8..38cadaa0f3 100644
@@ -166,4 +166,22 @@ typedef struct CXLEventMemoryModule {
     uint8_t reserved[0x3d];
 } QEMU_PACKED CXLEventMemoryModule;
 
+/*
+ * CXL r3.1 section Table 8-50: Dynamic Capacity Event Record
+ * All fields little endian.
+ */
+typedef struct CXLEventDynamicCapacity {
+    CXLEventRecordHdr hdr;
+    uint8_t type;
+    uint8_t validity_flags;
+    uint16_t host_id;
+    uint8_t updated_region_id;
+    uint8_t flags;
+    uint8_t reserved2[2];
+    uint8_t dynamic_capacity_extent[0x28]; /* defined in cxl_device.h */
+    uint8_t reserved[0x18];
+    uint32_t extents_avail;
+    uint32_t tags_avail;
+} QEMU_PACKED CXLEventDynamicCapacity;
+
 #endif /* CXL_EVENTS_H */

hw/cxl/cxl-mailbox-utils.c +50 ~~-12~~

106 lines not on this page · raw message

hw/mem/cxl_type3.c +305 -1

334 lines not on this page · raw message

hw/mem/cxl_type3_stubs.c +25 -0

index 3e1851e32b..45419bbefe 100644
@@ -67,3 +67,28 @@ void qmp_cxl_inject_correctable_error(const char *path, CxlCorErrorType type,
 {
     error_setg(errp, "CXL Type 3 support is not compiled in");
 }
+
+void qmp_cxl_add_dynamic_capacity(const char *path,
+                                  uint16_t host_id,
+                                  CXLExtSelPolicy sel_policy,
+                                  uint8_t region,
+                                  const char *tag,
+                                  CXLDynamicCapacityExtentList *extents,
+                                  Error **errp)
+{
+    error_setg(errp, "CXL Type 3 support is not compiled in");
+}
+
+void qmp_cxl_release_dynamic_capacity(const char *path, uint16_t host_id,
+                                      CXLExtRemovalPolicy removal_policy,
+                                      bool has_forced_removal,
+                                      bool forced_removal,
+                                      bool has_sanitize_on_release,
+                                      bool sanitize_on_release,
+                                      uint8_t region,
+                                      const char *tag,
+                                      CXLDynamicCapacityExtentList *extents,
+                                      Error **errp)
+{
+    error_setg(errp, "CXL Type 3 support is not compiled in");
+}

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #16 lore raw

[PULL v3 04/41] virtio/virtio-pci: Handle extra notification data

From: Jonah Palmer <[email protected]>

Add support to virtio-pci devices for handling the extra data sent from the driver to the device when the VIRTIO_F_NOTIFICATION_DATA transport feature has been negotiated.

The extra data that's passed to the virtio-pci device when this feature is enabled varies depending on the device's virtqueue layout.

In a split virtqueue layout, this data includes:
- upper 16 bits: shadow_avail_idx
- lower 16 bits: virtqueue index

In a packed virtqueue layout, this data includes:
- upper 16 bits: 1-bit wrap counter & 15-bit shadow_avail_idx
- lower 16 bits: virtqueue index

Message-Id: <[email protected]>

Reviewed-by Eugenio Pérez <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/virtio/virtio.h |  2 ++
 hw/virtio/virtio-pci.c     | 12 +++++++++---
 hw/virtio/virtio.c         | 18 ++++++++++++++++++
 3 files changed, 29 insertions(+), 3 deletions(-)

include/hw/virtio/virtio.h +2 -0

index 7d5ffdc145..1451926a13 100644
@@ -307,6 +307,8 @@ int virtio_queue_ready(VirtQueue *vq);
 
 int virtio_queue_empty(VirtQueue *vq);
 
+void virtio_queue_set_shadow_avail_idx(VirtQueue *vq, uint16_t idx);
+
 /* Host binding interface.  */
 
 uint32_t virtio_config_readb(VirtIODevice *vdev, uint32_t addr);

hw/virtio/virtio-pci.c +9 -3

index b1d02f4b3d..cffc7efcae 100644
@@ -384,7 +384,7 @@ static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
 {
     VirtIOPCIProxy *proxy = opaque;
     VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
-    uint16_t vector;
+    uint16_t vector, vq_idx;
     hwaddr pa;
 
     switch (addr) {

@@ -408,8 +408,14 @@ static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
             vdev->queue_sel = val;
         break;
     case VIRTIO_PCI_QUEUE_NOTIFY:
-        if (val < VIRTIO_QUEUE_MAX) {
-            virtio_queue_notify(vdev, val);
+        vq_idx = val;
+        if (vq_idx < VIRTIO_QUEUE_MAX && virtio_queue_get_num(vdev, vq_idx)) {
+            if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFICATION_DATA)) {
+                VirtQueue *vq = virtio_get_queue(vdev, vq_idx);
+
+                virtio_queue_set_shadow_avail_idx(vq, val >> 16);
+            }
+            virtio_queue_notify(vdev, vq_idx);
         }
         break;
     case VIRTIO_PCI_STATUS:

hw/virtio/virtio.c +18 -0

index 893a072c9d..f7c99e3a96 100644
@@ -2264,6 +2264,24 @@ void virtio_queue_set_align(VirtIODevice *vdev, int n, int align)
     }
 }
 
+void virtio_queue_set_shadow_avail_idx(VirtQueue *vq, uint16_t shadow_avail_idx)
+{
+    if (!vq->vring.desc) {
+        return;
+    }
+
+    /*
+     * 16-bit data for packed VQs include 1-bit wrap counter and
+     * 15-bit shadow_avail_idx.
+     */
+    if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) {
+        vq->shadow_avail_wrap_counter = (shadow_avail_idx >> 15) & 0x1;
+        vq->shadow_avail_idx = shadow_avail_idx & 0x7FFF;
+    } else {
+        vq->shadow_avail_idx = shadow_avail_idx;
+    }
+}
+
 static void virtio_queue_notify_vq(VirtQueue *vq)
 {
     if (vq->vring.desc && vq->handle_output) {

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #17 lore raw

[PULL v3 31/41] hw/acpi: Insert an acpi-generic-node base under acpi-generic-initiator

From: Jonathan Cameron <[email protected]>

This will simplify reuse when adding acpi-generic-port.
Note that some error_printf() messages will now print acpi-generic-node whereas others will move to type specific cases in next patch so are left alone for now.

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/acpi/acpi_generic_initiator.h | 15 ++++-
 hw/acpi/acpi_generic_initiator.c         | 80 +++++++++++++++---------
 2 files changed, 63 insertions(+), 32 deletions(-)

include/hw/acpi/acpi_generic_initiator.h +13 -2

index a304bad73e..dd4be19c8f 100644
@@ -8,15 +8,26 @@
 
 #include "qom/object_interfaces.h"
 
-#define TYPE_ACPI_GENERIC_INITIATOR "acpi-generic-initiator"
+/*
+ * Abstract type to be used as base for
+ * - acpi-generic-initiator
+ * - acpi-generic-port
+ */
+#define TYPE_ACPI_GENERIC_NODE "acpi-generic-node"
 
-typedef struct AcpiGenericInitiator {
+typedef struct AcpiGenericNode {
     /* private */
     Object parent;
 
     /* public */
     char *pci_dev;
     uint16_t node;
+} AcpiGenericNode;
+
+#define TYPE_ACPI_GENERIC_INITIATOR "acpi-generic-initiator"
+
+typedef struct AcpiGenericInitiator {
+    AcpiGenericNode parent;
 } AcpiGenericInitiator;
 
 /*

hw/acpi/acpi_generic_initiator.c +50 ~~-30~~

145 lines not on this page · raw message

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #18 lore raw

[PULL v3 05/41] virtio: Prevent creation of device using notification-data with ioeventfd

From: Jonah Palmer <[email protected]>

Prevent the realization of a virtio device that attempts to use the VIRTIO_F_NOTIFICATION_DATA transport feature without disabling ioeventfd.

Due to ioeventfd not being able to carry the extra data associated with this feature, having both enabled is a functional mismatch and therefore Qemu should not continue the device's realization process.

Although the device does not yet know if the feature will be successfully negotiated, many devices using this feature wont actually work without this extra data and would fail FEATURES_OK anyway.

If ioeventfd is able to work with the extra notification data in the future, this compatibility check can be removed.

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/virtio/virtio.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

hw/virtio/virtio.c +22 -0

index f7c99e3a96..28cd406e16 100644
@@ -2980,6 +2980,20 @@ int virtio_set_features(VirtIODevice *vdev, uint64_t val)
     return ret;
 }
 
+static void virtio_device_check_notification_compatibility(VirtIODevice *vdev,
+                                                           Error **errp)
+{
+    VirtioBusState *bus = VIRTIO_BUS(qdev_get_parent_bus(DEVICE(vdev)));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
+    DeviceState *proxy = DEVICE(BUS(bus)->parent);
+
+    if (virtio_host_has_feature(vdev, VIRTIO_F_NOTIFICATION_DATA) &&
+        k->ioeventfd_enabled(proxy)) {
+        error_setg(errp,
+                   "notification_data=on without ioeventfd=off is not supported");
+    }
+}
+
 size_t virtio_get_config_size(const VirtIOConfigSizeParams *params,
                               uint64_t host_features)
 {

@@ -3740,6 +3754,14 @@ static void virtio_device_realize(DeviceState *dev, Error **errp)
         }
     }
 
+    /* Devices should not use both ioeventfd and notification data feature */
+    virtio_device_check_notification_compatibility(vdev, &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        vdc->unrealize(dev);
+        return;
+    }
+
     virtio_bus_device_plugged(vdev, &err);
     if (err != NULL) {
         error_propagate(errp, err);

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #19 lore raw

[PULL v3 34/41] hw/misc/pvpanic: centralize definition of supported events

From: Thomas Weißschuh <[email protected]>

The different components of pvpanic duplicate the list of supported events. Move it to the shared header file to minimize changes when new events are added.

Reviewed-by Thomas Huth <[email protected]>

Reviewed-by Cornelia Huck <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/misc/pvpanic.h | 4 ++++
 hw/misc/pvpanic-isa.c     | 3 +--
 hw/misc/pvpanic-pci.c     | 3 +--
 hw/misc/pvpanic.c         | 3 +--
 4 files changed, 7 insertions(+), 6 deletions(-)

include/hw/misc/pvpanic.h +4 -0

index fab94165d0..947468b81b 100644
@@ -18,6 +18,10 @@
 #include "exec/memory.h"
 #include "qom/object.h"
 
+#include "standard-headers/linux/pvpanic.h"
+
+#define PVPANIC_EVENTS (PVPANIC_PANICKED | PVPANIC_CRASH_LOADED)
+
 #define TYPE_PVPANIC_ISA_DEVICE "pvpanic"
 #define TYPE_PVPANIC_PCI_DEVICE "pvpanic-pci"

hw/misc/pvpanic-isa.c +1 -2

index ccec50f61b..9a923b7869 100644
@@ -21,7 +21,6 @@
 #include "hw/misc/pvpanic.h"
 #include "qom/object.h"
 #include "hw/isa/isa.h"
-#include "standard-headers/linux/pvpanic.h"
 #include "hw/acpi/acpi_aml_interface.h"
 
 OBJECT_DECLARE_SIMPLE_TYPE(PVPanicISAState, PVPANIC_ISA_DEVICE)

@@ -102,7 +101,7 @@ static void build_pvpanic_isa_aml(AcpiDevAmlIf *adev, Aml *scope)
 static Property pvpanic_isa_properties[] = {
     DEFINE_PROP_UINT16(PVPANIC_IOPORT_PROP, PVPanicISAState, ioport, 0x505),
     DEFINE_PROP_UINT8("events", PVPanicISAState, pvpanic.events,
-                      PVPANIC_PANICKED | PVPANIC_CRASH_LOADED),
+                      PVPANIC_EVENTS),
     DEFINE_PROP_END_OF_LIST(),
 };

hw/misc/pvpanic-pci.c +1 -2

index 83be95d0d2..603c5c7600 100644
@@ -21,7 +21,6 @@
 #include "hw/misc/pvpanic.h"
 #include "qom/object.h"
 #include "hw/pci/pci_device.h"
-#include "standard-headers/linux/pvpanic.h"
 
 OBJECT_DECLARE_SIMPLE_TYPE(PVPanicPCIState, PVPANIC_PCI_DEVICE)

@@ -55,7 +54,7 @@ static void pvpanic_pci_realizefn(PCIDevice *dev, Error **errp)
 
 static Property pvpanic_pci_properties[] = {
     DEFINE_PROP_UINT8("events", PVPanicPCIState, pvpanic.events,
-                      PVPANIC_PANICKED | PVPANIC_CRASH_LOADED),
+                      PVPANIC_EVENTS),
     DEFINE_PROP_END_OF_LIST(),
 };

hw/misc/pvpanic.c +1 -2

index 1540e9091a..a4982cc592 100644
@@ -21,13 +21,12 @@
 #include "hw/qdev-properties.h"
 #include "hw/misc/pvpanic.h"
 #include "qom/object.h"
-#include "standard-headers/linux/pvpanic.h"
 
 static void handle_event(int event)
 {
     static bool logged;
 
-    if (event & ~(PVPANIC_PANICKED | PVPANIC_CRASH_LOADED) && !logged) {
+    if (event & ~PVPANIC_EVENTS && !logged) {
         qemu_log_mask(LOG_GUEST_ERROR, "pvpanic: unknown event %#x.\n", event);
         logged = true;
     }

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #20 lore raw

[PULL v3 10/41] vhost-vsock: add VIRTIO_F_RING_PACKED to feature_bits

From: Halil Pasic <[email protected]>

Not having VIRTIO_F_RING_PACKED in feature_bits[] is a problem when the vhost-vsock device does not offer the feature bit VIRTIO_F_RING_PACKED but the in QEMU device is configured to try to use the packed layout (the virtio property "packed" is on).

As of today, the Linux kernel vhost-vsock device does not support the packed queue layout (as vhost does not support packed), and does not offer VIRTIO_F_RING_PACKED. Thus when for example a vhost-vsock-ccw is used with packed=on, VIRTIO_F_RING_PACKED ends up being negotiated, despite the fact that the device does not actually support it, and one gets to keep the pieces.

Fixes 74b3e46630 ("virtio: add property to enable packed virtqueue")

Reported-by Marc Hartmayer <[email protected]>

Signed-off-by Halil Pasic <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/virtio/vhost-vsock-common.c | 1 +
 1 file changed, 1 insertion(+)

hw/virtio/vhost-vsock-common.c +1 -0

index 12ea87d7a7..fd88df2560 100644
@@ -22,6 +22,7 @@
 const int feature_bits[] = {
     VIRTIO_VSOCK_F_SEQPACKET,
     VIRTIO_F_RING_RESET,
+    VIRTIO_F_RING_PACKED,
     VHOST_INVALID_FEATURE_BIT
 };

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #21 lore raw

[PULL v3 36/41] hw/misc/pvpanic: add support for normal shutdowns

From: Thomas Weißschuh <[email protected]>

Shutdown requests are normally hardware dependent.
By extending pvpanic to also handle shutdown requests, guests can submit such requests with an easily implementable and cross-platform mechanism.

Acked-by Cornelia Huck <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/misc/pvpanic.h | 4 +++-
 include/sysemu/runstate.h | 1 +
 hw/misc/pvpanic.c         | 5 +++++
 system/runstate.c         | 5 +++++
 4 files changed, 14 insertions(+), 1 deletion(-)

include/hw/misc/pvpanic.h +3 -1

index 947468b81b..04986537af 100644
@@ -20,7 +20,9 @@
 
 #include "standard-headers/linux/pvpanic.h"
 
-#define PVPANIC_EVENTS (PVPANIC_PANICKED | PVPANIC_CRASH_LOADED)
+#define PVPANIC_EVENTS (PVPANIC_PANICKED | \
+                        PVPANIC_CRASH_LOADED | \
+                        PVPANIC_SHUTDOWN)
 
 #define TYPE_PVPANIC_ISA_DEVICE "pvpanic"
 #define TYPE_PVPANIC_PCI_DEVICE "pvpanic-pci"

include/sysemu/runstate.h +1 -0

index 0117d243c4..e210a37abf 100644
@@ -104,6 +104,7 @@ void qemu_system_killed(int signal, pid_t pid);
 void qemu_system_reset(ShutdownCause reason);
 void qemu_system_guest_panicked(GuestPanicInformation *info);
 void qemu_system_guest_crashloaded(GuestPanicInformation *info);
+void qemu_system_guest_pvshutdown(void);
 bool qemu_system_dump_in_progress(void);
 
 #endif

hw/misc/pvpanic.c +5 -0

index a4982cc592..0e9505451a 100644
@@ -40,6 +40,11 @@ static void handle_event(int event)
         qemu_system_guest_crashloaded(NULL);
         return;
     }
+
+    if (event & PVPANIC_SHUTDOWN) {
+        qemu_system_guest_pvshutdown();
+        return;
+    }
 }
 
 /* return supported events on read */

system/runstate.c +5 -0

index cb4905a40f..83055f3278 100644
@@ -585,6 +585,11 @@ void qemu_system_guest_crashloaded(GuestPanicInformation *info)
     qapi_free_GuestPanicInformation(info);
 }
 
+void qemu_system_guest_pvshutdown(void)
+{
+    qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
+}
+
 void qemu_system_reset_request(ShutdownCause reason)
 {
     if (reboot_action == REBOOT_ACTION_SHUTDOWN &&

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #22 lore raw

[PULL v3 28/41] hw/cxl/cxl-mailbox-utils: Add superset extent release mailbox support

From: Fan Ni <[email protected]>

With the change, we extend the extent release mailbox command processing to allow more flexible release. As long as the DPA range of the extent to release is covered by accepted extent(s) in the device, the release can be performed.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/cxl/cxl-mailbox-utils.c | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

hw/cxl/cxl-mailbox-utils.c +8 ~~-13~~

index c4852112fe..74eeb6fde7 100644
@@ -1704,6 +1704,13 @@ static CXLRetCode cxl_dc_extent_release_dry_run(CXLType3Dev *ct3d,
         dpa = in->updated_entries[i].start_dpa;
         len = in->updated_entries[i].len;
 
+        /* Check if the DPA range is not fully backed with valid extents */
+        if (!ct3_test_region_block_backed(ct3d, dpa, len)) {
+            ret = CXL_MBOX_INVALID_PA;
+            goto free_and_exit;
+        }
+
+        /* After this point, extent overflow is the only error can happen */
         while (len > 0) {
             QTAILQ_FOREACH(ent, updated_list, node) {
                 range_init_nofail(&range, ent->start_dpa, ent->len);

@@ -1718,14 +1725,7 @@ static CXLRetCode cxl_dc_extent_release_dry_run(CXLType3Dev *ct3d,
                     if (range_contains(&range, dpa + len - 1)) {
                         len2 = ent_start_dpa + ent_len - dpa - len;
                     } else {
-                        /*
-                         * TODO: we reject the attempt to remove an extent
-                         * that overlaps with multiple extents in the device
-                         * for now. We will allow it once superset release
-                         * support is added.
-                         */
-                        ret = CXL_MBOX_INVALID_PA;
-                        goto free_and_exit;
+                        dpa = ent_start_dpa + ent_len;
                     }
                     len_done = ent_len - len1 - len2;

@@ -1752,14 +1752,9 @@ static CXLRetCode cxl_dc_extent_release_dry_run(CXLType3Dev *ct3d,
                     }
 
                     len -= len_done;
-                    /* len == 0 here until superset release is added */
                     break;
                 }
             }
-            if (len) {
-                ret = CXL_MBOX_INVALID_PA;
-                goto free_and_exit;
-            }
         }
     }
 free_and_exit:

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:37 UTC #23 lore raw

[PULL v3 35/41] tests/qtest/pvpanic: use centralized definition of supported events

From: Thomas Weißschuh <[email protected]>

Avoid the necessity to update all tests when new events are added to the device.

Acked-by Thomas Huth <[email protected]>

Reviewed-by Cornelia Huck <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 tests/qtest/pvpanic-pci-test.c | 5 +++--
 tests/qtest/pvpanic-test.c     | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

tests/qtest/pvpanic-pci-test.c +3 -2

index 2c05b376ba..b372caf41d 100644
@@ -16,6 +16,7 @@
 #include "qapi/qmp/qdict.h"
 #include "libqos/pci.h"
 #include "libqos/pci-pc.h"
+#include "hw/misc/pvpanic.h"
 #include "hw/pci/pci_regs.h"
 
 static void test_panic_nopause(void)

@@ -34,7 +35,7 @@ static void test_panic_nopause(void)
     bar = qpci_iomap(dev, 0, NULL);
 
     qpci_memread(dev, bar, 0, &val, sizeof(val));
-    g_assert_cmpuint(val, ==, 3);
+    g_assert_cmpuint(val, ==, PVPANIC_EVENTS);
 
     val = 1;
     qpci_memwrite(dev, bar, 0, &val, sizeof(val));

@@ -67,7 +68,7 @@ static void test_panic(void)
     bar = qpci_iomap(dev, 0, NULL);
 
     qpci_memread(dev, bar, 0, &val, sizeof(val));
-    g_assert_cmpuint(val, ==, 3);
+    g_assert_cmpuint(val, ==, PVPANIC_EVENTS);
 
     val = 1;
     qpci_memwrite(dev, bar, 0, &val, sizeof(val));

tests/qtest/pvpanic-test.c +3 -2

index 78f1cf8186..ccc603472f 100644
@@ -10,6 +10,7 @@
 #include "qemu/osdep.h"
 #include "libqtest.h"
 #include "qapi/qmp/qdict.h"
+#include "hw/misc/pvpanic.h"
 
 static void test_panic_nopause(void)
 {

@@ -20,7 +21,7 @@ static void test_panic_nopause(void)
     qts = qtest_init("-device pvpanic -action panic=none");
 
     val = qtest_inb(qts, 0x505);
-    g_assert_cmpuint(val, ==, 3);
+    g_assert_cmpuint(val, ==, PVPANIC_EVENTS);
 
     qtest_outb(qts, 0x505, 0x1);

@@ -43,7 +44,7 @@ static void test_panic(void)
     qts = qtest_init("-device pvpanic -action panic=pause");
 
     val = qtest_inb(qts, 0x505);
-    g_assert_cmpuint(val, ==, 3);
+    g_assert_cmpuint(val, ==, PVPANIC_EVENTS);
 
     qtest_outb(qts, 0x505, 0x1);

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:38 UTC #24 lore raw

[PULL v3 41/41] hw/cxl: Fix read from bogus memory

Link https://lore.kernel.org/all/CAFEAcA-u4sytGwTKsb__Y+_+0O2-WwARntm3x8WNhvL1WfHOBg@mail.gmail.com/ open here

From: Ira Weiny <[email protected]>

Peter and coverity report:

We've passed '&data' to address_space_write(), which means "read from the address on the stack where the function argument 'data' lives", so instead of writing 64 bytes of data to the guest , we'll write 64 bytes which start with a host pointer value and then continue with whatever happens to be on the host stack after that.

Indeed the intention was to write 64 bytes of data at the address given.

Fix the parameter to address_space_write().

Reported-by Peter Maydell <[email protected]>

Fixes 6bda41a69bdc ("hw/cxl: Add clear poison mailbox command support.")

Cc Jonathan Cameron <[email protected]>

Signed-off-by Ira Weiny <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/mem/cxl_type3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

hw/mem/cxl_type3.c +1 -1

index 5d4a1276be..3274e5dcbb 100644
@@ -1292,7 +1292,7 @@ static bool set_cacheline(CXLType3Dev *ct3d, uint64_t dpa_offset, uint8_t *data)
         dpa_offset -= (vmr_size + pmr_size);
     }
 
-    address_space_write(as, dpa_offset, MEMTXATTRS_UNSPECIFIED, &data,
+    address_space_write(as, dpa_offset, MEMTXATTRS_UNSPECIFIED, data,
                         CXL_CACHE_LINE_SIZE);
     return true;
 }

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:38 UTC #25 lore raw

[PULL v3 32/41] scripts/update-linux-headers: Copy setup_data.h to correct directory

From: Thomas Weißschuh <[email protected]>

Add the missing "include/" path component, so the files ends up in the correct place like the other headers.

Fixes 66210a1a30f2 ("scripts/update-linux-headers: Add setup_data.h to import list")

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

Reviewed-by Thomas Huth <[email protected]>

---
 scripts/update-linux-headers.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

scripts/update-linux-headers.sh +1 -1

index 8963c39189..a148793bd5 100755
@@ -158,7 +158,7 @@ for arch in $ARCHLIST; do
         cp_portable "$hdrdir/bootparam.h" \
                     "$output/include/standard-headers/asm-$arch"
         cp_portable "$hdrdir/include/asm/setup_data.h" \
-                    "$output/standard-headers/asm-x86"
+                    "$output/include/standard-headers/asm-x86"
     fi
     if [ $arch = riscv ]; then
         cp "$hdrdir/include/asm/ptrace.h" "$output/linux-headers/asm-riscv/"

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:38 UTC #26 lore raw

[PULL v3 02/41] vhost: Perform memory section dirty scans once per iteration

From: Si-Wei Liu <[email protected]>

On setups with one or more virtio-net devices with vhost on, dirty tracking iteration increases cost the bigger the number amount of queues are set up e.g. on idle guests migration the following is observed with virtio-net with vhost=on:

48 queues -> 78.11%  [.] vhost_dev_sync_region.isra.13
8 queues -> 40.50%   [.] vhost_dev_sync_region.isra.13
1 queue -> 6.89%     [.] vhost_dev_sync_region.isra.13

2 devices, 1 queue -> 18.60% [.] vhost_dev_sync_region.isra.14

With high memory rates the symptom is lack of convergence as soon as it has a vhost device with a sufficiently high number of queues, the sufficient number of vhost devices.

On every migration iteration (every 100msecs) it will redundantly query the *shared log* the number of queues configured with vhost that exist in the guest. For the virtqueue data, this is necessary, but not for the memory sections which are the same. So essentially we end up scanning the dirty log too often.

To fix that, select a vhost device responsible for scanning the log with regards to memory sections dirty tracking. It is selected when we enable the logger (during migration) and cleared when we disable the logger. If the vhost logger device goes away for some reason, the logger will be re-selected from the rest of vhost devices.

After making mem-section logger a singleton instance, constant cost of 7%-9% (like the 1 queue report) will be seen, no matter how many queues or how many vhost devices are configured:

48 queues -> 8.71% [.] vhost_dev_sync_region.isra.13
2 devices, 8 queues -> 7.97% [.] vhost_dev_sync_region.isra.14

Co-developed-by Joao Martins <[email protected]>

Signed-off-by Joao Martins <[email protected]>

Signed-off-by Si-Wei Liu <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

Acked-by Jason Wang <[email protected]>

---
 include/hw/virtio/vhost.h |  1 +
 hw/virtio/vhost.c         | 67 +++++++++++++++++++++++++++++++++++----
 2 files changed, 62 insertions(+), 6 deletions(-)

include/hw/virtio/vhost.h +1 -0

index 02477788df..d75faf46e9 100644
@@ -129,6 +129,7 @@ struct vhost_dev {
     void *opaque;
     struct vhost_log *log;
     QLIST_ENTRY(vhost_dev) entry;
+    QLIST_ENTRY(vhost_dev) logdev_entry;
     QLIST_HEAD(, vhost_iommu) iommu_list;
     IOMMUNotifier n;
     const VhostDevConfigOps *config_ops;

hw/virtio/vhost.c +61 -6

103 lines not on this page · raw message

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:38 UTC #27 lore raw

[PULL v3 17/41] hw/cxl/mailbox: interface to add CCI commands to an existing CCI

From: Gregory Price <[email protected]>

This enables wrapper devices to customize the base device's CCI (for example, with custom commands outside the specification) without the need to change the base device.

The also enabled the base device to dispatch those commands without requiring additional driver support.

Heavily edited by Jonathan Cameron to increase code reuse

Signed-off-by Gregory Price <[email protected]>

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/cxl/cxl_device.h |  2 ++
 hw/cxl/cxl-mailbox-utils.c  | 19 +++++++++++++++++--
 2 files changed, 19 insertions(+), 2 deletions(-)

include/hw/cxl/cxl_device.h +2 -0

index ccc4611875..a5f8e25020 100644
@@ -301,6 +301,8 @@ void cxl_initialize_mailbox_t3(CXLCCI *cci, DeviceState *d, size_t payload_max);
 void cxl_initialize_mailbox_swcci(CXLCCI *cci, DeviceState *intf,
                                   DeviceState *d, size_t payload_max);
 void cxl_init_cci(CXLCCI *cci, size_t payload_max);
+void cxl_add_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmd_set)[256],
+                          size_t payload_max);
 int cxl_process_cci_message(CXLCCI *cci, uint8_t set, uint8_t cmd,
                             size_t len_in, uint8_t *pl_in,
                             size_t *len_out, uint8_t *pl_out,

hw/cxl/cxl-mailbox-utils.c +17 -2

index 2c9f50f0f9..2a64c58e2f 100644
@@ -1424,9 +1424,9 @@ static void bg_timercb(void *opaque)
     }
 }
 
-void cxl_init_cci(CXLCCI *cci, size_t payload_max)
+static void cxl_rebuild_cel(CXLCCI *cci)
 {
-    cci->payload_max = payload_max;
+    cci->cel_size = 0; /* Reset for a fresh build */
     for (int set = 0; set < 256; set++) {
         for (int cmd = 0; cmd < 256; cmd++) {
             if (cci->cxl_cmd_set[set][cmd].handler) {

@@ -1440,6 +1440,13 @@ void cxl_init_cci(CXLCCI *cci, size_t payload_max)
             }
         }
     }
+}
+
+void cxl_init_cci(CXLCCI *cci, size_t payload_max)
+{
+    cci->payload_max = payload_max;
+    cxl_rebuild_cel(cci);
+
     cci->bg.complete_pct = 0;
     cci->bg.starttime = 0;
     cci->bg.runtime = 0;

@@ -1458,6 +1465,14 @@ static void cxl_copy_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmds)[
     }
 }
 
+void cxl_add_cci_commands(CXLCCI *cci, const struct cxl_cmd (*cxl_cmd_set)[256],
+                                 size_t payload_max)
+{
+    cci->payload_max = MAX(payload_max, cci->payload_max);
+    cxl_copy_cci_commands(cci, cxl_cmd_set);
+    cxl_rebuild_cel(cci);
+}
+
 void cxl_initialize_mailbox_swcci(CXLCCI *cci, DeviceState *intf,
                                   DeviceState *d, size_t payload_max)
 {

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:38 UTC #28 lore raw

[PULL v3 29/41] hw/mem/cxl_type3: Allow to release extent superset in QMP interface

From: Fan Ni <[email protected]>

Before the change, the QMP interface used for add/release DC extents only allows to release an extent whose DPA range is contained by a single accepted extent in the device.

With the change, we relax the constraints. As long as the DPA range of the extent is covered by accepted extents, we allow the release.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/mem/cxl_type3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

hw/mem/cxl_type3.c +1 -1

index 0d18259ec0..5d4a1276be 100644
@@ -1947,7 +1947,7 @@ static void qmp_cxl_process_dynamic_capacity_prescriptive(const char *path,
                            "cannot release extent with pending DPA range");
                 return;
             }
-            if (!cxl_extents_contains_dpa_range(&dcd->dc.extents, dpa, len)) {
+            if (!ct3_test_region_block_backed(dcd, dpa, len)) {
                 error_setg(errp,
                            "cannot release extent with non-existing DPA range");
                 return;

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:38 UTC #29 lore raw

[PULL v3 19/41] hw/cxl/cxl-mailbox-utils: Add dynamic capacity region representative and mailbox command support

From: Fan Ni <[email protected]>

Per cxl spec r3.1, add dynamic capacity (DC) region representative based on Table 8-165 and extend the cxl type3 device definition to include DC region information. Also, based on info in 8.2.9.9.9.1, add 'Get Dynamic Capacity Configuration' mailbox support.

Note: we store region decode length as byte-wise length on the device, which should be divided by 256 * MiB before being returned to the host for "Get Dynamic Capacity Configuration" mailbox command per specification.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/cxl/cxl_device.h | 16 +++++++
 hw/cxl/cxl-mailbox-utils.c  | 96 +++++++++++++++++++++++++++++++++++++
 2 files changed, 112 insertions(+)

include/hw/cxl/cxl_device.h +16 -0

index a5f8e25020..e839370266 100644
@@ -422,6 +422,17 @@ typedef struct CXLPoison {
 typedef QLIST_HEAD(, CXLPoison) CXLPoisonList;
 #define CXL_POISON_LIST_LIMIT 256
 
+#define DCD_MAX_NUM_REGION 8
+
+typedef struct CXLDCRegion {
+    uint64_t base;       /* aligned to 256*MiB */
+    uint64_t decode_len; /* aligned to 256*MiB */
+    uint64_t len;
+    uint64_t block_size;
+    uint32_t dsmadhandle;
+    uint8_t flags;
+} CXLDCRegion;
+
 struct CXLType3Dev {
     /* Private */
     PCIDevice parent_obj;

@@ -454,6 +465,11 @@ struct CXLType3Dev {
     unsigned int poison_list_cnt;
     bool poison_list_overflowed;
     uint64_t poison_list_overflow_ts;
+
+    struct dynamic_capacity {
+        uint8_t num_regions; /* 0-8 regions */
+        CXLDCRegion regions[DCD_MAX_NUM_REGION];
+    } dc;
 };
 
 #define TYPE_CXL_TYPE3 "cxl-type3"

hw/cxl/cxl-mailbox-utils.c +96 -0

127 lines not on this page · raw message

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #30 lore raw

[PULL v3 20/41] include/hw/cxl/cxl_device: Rename mem_size as static_mem_size for type3 memory devices

From: Fan Ni <[email protected]>

Rename mem_size as static_mem_size for type3 memdev to cover static RAM and pmem capacity, preparing for the introduction of dynamic capacity to support dynamic capacity devices.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/cxl/cxl_device.h | 2 +-
 hw/cxl/cxl-mailbox-utils.c  | 4 ++--
 hw/mem/cxl_type3.c          | 8 ++++----
 3 files changed, 7 insertions(+), 7 deletions(-)

include/hw/cxl/cxl_device.h +1 -1

index e839370266..f7f56b44e3 100644
@@ -234,7 +234,7 @@ typedef struct cxl_device_state {
     } timestamp;
 
     /* memory region size, HDM */
-    uint64_t mem_size;
+    uint64_t static_mem_size;
     uint64_t pmem_size;
     uint64_t vmem_size;

hw/cxl/cxl-mailbox-utils.c +2 -2

index bede28e3c8..b592473587 100644
@@ -803,7 +803,7 @@ static CXLRetCode cmd_identify_memory_device(const struct cxl_cmd *cmd,
     snprintf(id->fw_revision, 0x10, "BWFW VERSION %02d", 0);
 
     stq_le_p(&id->total_capacity,
-             cxl_dstate->mem_size / CXL_CAPACITY_MULTIPLIER);
+             cxl_dstate->static_mem_size / CXL_CAPACITY_MULTIPLIER);
     stq_le_p(&id->persistent_capacity,
              cxl_dstate->pmem_size / CXL_CAPACITY_MULTIPLIER);
     stq_le_p(&id->volatile_capacity,

@@ -1179,7 +1179,7 @@ static CXLRetCode cmd_media_clear_poison(const struct cxl_cmd *cmd,
     struct clear_poison_pl *in = (void *)payload_in;
 
     dpa = ldq_le_p(&in->dpa);
-    if (dpa + CXL_CACHE_LINE_SIZE > cxl_dstate->mem_size) {
+    if (dpa + CXL_CACHE_LINE_SIZE > cxl_dstate->static_mem_size) {
         return CXL_MBOX_INVALID_PA;
     }

hw/mem/cxl_type3.c +4 -4

index 3e42490b6c..7194c8f902 100644
@@ -608,7 +608,7 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
         }
         address_space_init(&ct3d->hostvmem_as, vmr, v_name);
         ct3d->cxl_dstate.vmem_size = memory_region_size(vmr);
-        ct3d->cxl_dstate.mem_size += memory_region_size(vmr);
+        ct3d->cxl_dstate.static_mem_size += memory_region_size(vmr);
         g_free(v_name);
     }

@@ -631,7 +631,7 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
         }
         address_space_init(&ct3d->hostpmem_as, pmr, p_name);
         ct3d->cxl_dstate.pmem_size = memory_region_size(pmr);
-        ct3d->cxl_dstate.mem_size += memory_region_size(pmr);
+        ct3d->cxl_dstate.static_mem_size += memory_region_size(pmr);
         g_free(p_name);
     }

@@ -837,7 +837,7 @@ static int cxl_type3_hpa_to_as_and_dpa(CXLType3Dev *ct3d,
         return -EINVAL;
     }
 
-    if (*dpa_offset > ct3d->cxl_dstate.mem_size) {
+    if (*dpa_offset > ct3d->cxl_dstate.static_mem_size) {
         return -EINVAL;
     }

@@ -1010,7 +1010,7 @@ static bool set_cacheline(CXLType3Dev *ct3d, uint64_t dpa_offset, uint8_t *data)
         return false;
     }
 
-    if (dpa_offset + CXL_CACHE_LINE_SIZE > ct3d->cxl_dstate.mem_size) {
+    if (dpa_offset + CXL_CACHE_LINE_SIZE > ct3d->cxl_dstate.static_mem_size) {
         return false;
     }

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #31 lore raw

[PULL v3 22/41] hw/mem/cxl-type3: Refactor ct3_build_cdat_entries_for_mr to take mr size instead of mr as argument

From: Fan Ni <[email protected]>

The function ct3_build_cdat_entries_for_mr only uses size of the passed memory region argument, refactor the function definition to make the passed arguments more specific.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/mem/cxl_type3.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

hw/mem/cxl_type3.c +9 -6

index 06c6f9bb78..51be50ce87 100644
@@ -44,7 +44,7 @@ enum {
 };
 
 static void ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
-                                          int dsmad_handle, MemoryRegion *mr,
+                                          int dsmad_handle, uint64_t size,
                                           bool is_pmem, uint64_t dpa_base)
 {
     CDATDsmas *dsmas;

@@ -63,7 +63,7 @@ static void ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
         .DSMADhandle = dsmad_handle,
         .flags = is_pmem ? CDAT_DSMAS_FLAG_NV : 0,
         .DPA_base = dpa_base,
-        .DPA_length = memory_region_size(mr),
+        .DPA_length = size,
     };
 
     /* For now, no memory side cache, plausiblish numbers */

@@ -132,7 +132,7 @@ static void ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
          */
         .EFI_memory_type_attr = is_pmem ? 2 : 1,
         .DPA_offset = 0,
-        .DPA_length = memory_region_size(mr),
+        .DPA_length = size,
     };
 
     /* Header always at start of structure */

@@ -149,6 +149,7 @@ static int ct3_build_cdat_table(CDATSubHeader ***cdat_table, void *priv)
     g_autofree CDATSubHeader **table = NULL;
     CXLType3Dev *ct3d = priv;
     MemoryRegion *volatile_mr = NULL, *nonvolatile_mr = NULL;
+    uint64_t vmr_size = 0, pmr_size = 0;
     int dsmad_handle = 0;
     int cur_ent = 0;
     int len = 0;

@@ -163,6 +164,7 @@ static int ct3_build_cdat_table(CDATSubHeader ***cdat_table, void *priv)
             return -EINVAL;
         }
         len += CT3_CDAT_NUM_ENTRIES;
+        vmr_size = memory_region_size(volatile_mr);
     }
 
     if (ct3d->hostpmem) {

@@ -171,21 +173,22 @@ static int ct3_build_cdat_table(CDATSubHeader ***cdat_table, void *priv)
             return -EINVAL;
         }
         len += CT3_CDAT_NUM_ENTRIES;
+        pmr_size = memory_region_size(nonvolatile_mr);
     }
 
     table = g_malloc0(len * sizeof(*table));
 
     /* Now fill them in */
     if (volatile_mr) {
-        ct3_build_cdat_entries_for_mr(table, dsmad_handle++, volatile_mr,
+        ct3_build_cdat_entries_for_mr(table, dsmad_handle++, vmr_size,
                                       false, 0);
         cur_ent = CT3_CDAT_NUM_ENTRIES;
     }
 
     if (nonvolatile_mr) {
-        uint64_t base = volatile_mr ? memory_region_size(volatile_mr) : 0;
+        uint64_t base = vmr_size;
         ct3_build_cdat_entries_for_mr(&(table[cur_ent]), dsmad_handle++,
-                                      nonvolatile_mr, true, base);
+                                      pmr_size, true, base);
         cur_ent += CT3_CDAT_NUM_ENTRIES;
     }
     assert(len == cur_ent);

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #32 lore raw

[PULL v3 37/41] pvpanic: Emit GUEST_PVSHUTDOWN QMP event on pvpanic shutdown signal

From: Alejandro Jimenez <[email protected]>

Emit a QMP event on receiving a PVPANIC_SHUTDOWN event. Even though a typical SHUTDOWN event will be sent, it will be indistinguishable from a shutdown originating from other cases (e.g. KVM exit due to KVM_SYSTEM_EVENT_SHUTDOWN) that also issue the guest-shutdown cause.
A management layer application can detect the new GUEST_PVSHUTDOWN event to determine if the guest is using the pvpanic interface to request shutdowns.

Signed-off-by Alejandro Jimenez <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 qapi/run-state.json | 14 ++++++++++++++
 system/runstate.c   |  1 +
 2 files changed, 15 insertions(+)

qapi/run-state.json +14 -0

index f8773f23b2..5ac0fec852 100644
@@ -462,6 +462,20 @@
 { 'event': 'GUEST_CRASHLOADED',
   'data': { 'action': 'GuestPanicAction', '*info': 'GuestPanicInformation' } }
 
+##
+# @GUEST_PVSHUTDOWN:
+#
+# Emitted when guest submits a shutdown request via pvpanic interface
+#
+# Since: 9.1
+#
+# Example:
+#
+#     <- { "event": "GUEST_PVSHUTDOWN",
+#          "timestamp": { "seconds": 1648245259, "microseconds": 893771 } }
+##
+{ 'event': 'GUEST_PVSHUTDOWN' }
+
 ##
 # @GuestPanicAction:
 #

system/runstate.c +1 -0

index 83055f3278..c149b1ab4b 100644
@@ -587,6 +587,7 @@ void qemu_system_guest_crashloaded(GuestPanicInformation *info)
 
 void qemu_system_guest_pvshutdown(void)
 {
+    qapi_event_send_guest_pvshutdown();
     qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
 }

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #33 lore raw

[PULL v3 06/41] virtio-mmio: Handle extra notification data

From: Jonah Palmer <[email protected]>

Add support to virtio-mmio devices for handling the extra data sent from the driver to the device when the VIRTIO_F_NOTIFICATION_DATA transport feature has been negotiated.

The extra data that's passed to the virtio-mmio device when this feature is enabled varies depending on the device's virtqueue layout.

The data passed to the virtio-mmio device is in the same format as the data passed to virtio-pci devices.

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/virtio/virtio-mmio.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

hw/virtio/virtio-mmio.c +9 -2

index 22f9fbcf5a..320428ac0d 100644
@@ -248,6 +248,7 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value,
 {
     VirtIOMMIOProxy *proxy = (VirtIOMMIOProxy *)opaque;
     VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    uint16_t vq_idx;
 
     trace_virtio_mmio_write_offset(offset, value);

@@ -407,8 +408,14 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value,
         }
         break;
     case VIRTIO_MMIO_QUEUE_NOTIFY:
-        if (value < VIRTIO_QUEUE_MAX) {
-            virtio_queue_notify(vdev, value);
+        vq_idx = value;
+        if (vq_idx < VIRTIO_QUEUE_MAX && virtio_queue_get_num(vdev, vq_idx)) {
+            if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFICATION_DATA)) {
+                VirtQueue *vq = virtio_get_queue(vdev, vq_idx);
+
+                virtio_queue_set_shadow_avail_idx(vq, (value >> 16) & 0xFFFF);
+            }
+            virtio_queue_notify(vdev, vq_idx);
         }
         break;
     case VIRTIO_MMIO_INTERRUPT_ACK:

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #34 lore raw

[PULL v3 18/41] hw/cxl/cxl-mailbox-utils: Add dc_event_log_size field to output payload of identify memory device command

From: Fan Ni <[email protected]>

Based on CXL spec r3.1 Table 8-127 (Identify Memory Device Output Payload), dynamic capacity event log size should be part of output of the Identify command.
Add dc_event_log_size to the output payload for the host to get the info.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/cxl/cxl-mailbox-utils.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

hw/cxl/cxl-mailbox-utils.c +4 -1

index 2a64c58e2f..626acc1d0d 100644
@@ -21,6 +21,7 @@
 #include "sysemu/hostmem.h"
 
 #define CXL_CAPACITY_MULTIPLIER   (256 * MiB)
+#define CXL_DC_EVENT_LOG_SIZE 8
 
 /*
  * How to add a new command, example. The command set FOO, with cmd BAR.

@@ -780,8 +781,9 @@ static CXLRetCode cmd_identify_memory_device(const struct cxl_cmd *cmd,
         uint16_t inject_poison_limit;
         uint8_t poison_caps;
         uint8_t qos_telemetry_caps;
+        uint16_t dc_event_log_size;
     } QEMU_PACKED *id;
-    QEMU_BUILD_BUG_ON(sizeof(*id) != 0x43);
+    QEMU_BUILD_BUG_ON(sizeof(*id) != 0x45);
     CXLType3Dev *ct3d = CXL_TYPE3(cci->d);
     CXLType3Class *cvc = CXL_TYPE3_GET_CLASS(ct3d);
     CXLDeviceState *cxl_dstate = &ct3d->cxl_dstate;

@@ -807,6 +809,7 @@ static CXLRetCode cmd_identify_memory_device(const struct cxl_cmd *cmd,
     st24_le_p(id->poison_list_max_mer, 256);
     /* No limit - so limited by main poison record limit */
     stw_le_p(&id->inject_poison_limit, 0);
+    stw_le_p(&id->dc_event_log_size, CXL_DC_EVENT_LOG_SIZE);
 
     *len_out = sizeof(*id);
     return CXL_MBOX_SUCCESS;

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #35 lore raw

[PULL v3 27/41] hw/mem/cxl_type3: Add DPA range validation for accesses to DC regions

From: Fan Ni <[email protected]>

All DPA ranges in the DC regions are invalid to access until an extent covering the range has been successfully accepted by the host. A bitmap is added to each region to record whether a DC block in the region has been backed by a DC extent. Each bit in the bitmap represents a DC block. When a DC extent is accepted, all the bits representing the blocks in the extent are set, which will be cleared when the extent is released.

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/cxl/cxl_device.h |  7 ++++
 hw/cxl/cxl-mailbox-utils.c  |  3 ++
 hw/mem/cxl_type3.c          | 76 +++++++++++++++++++++++++++++++++++++
 3 files changed, 86 insertions(+)

include/hw/cxl/cxl_device.h +7 -0

index c69ff6b5de..0a4fcb2800 100644
@@ -456,6 +456,7 @@ typedef struct CXLDCRegion {
     uint64_t block_size;
     uint32_t dsmadhandle;
     uint8_t flags;
+    unsigned long *blk_bitmap;
 } CXLDCRegion;
 
 struct CXLType3Dev {

@@ -577,4 +578,10 @@ CXLDCExtentGroup *cxl_insert_extent_to_extent_group(CXLDCExtentGroup *group,
 void cxl_extent_group_list_insert_tail(CXLDCExtentGroupList *list,
                                        CXLDCExtentGroup *group);
 void cxl_extent_group_list_delete_front(CXLDCExtentGroupList *list);
+void ct3_set_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa,
+                                 uint64_t len);
+void ct3_clear_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa,
+                                   uint64_t len);
+bool ct3_test_region_block_backed(CXLType3Dev *ct3d, uint64_t dpa,
+                                  uint64_t len);
 #endif

hw/cxl/cxl-mailbox-utils.c +3 -0

index 64387f34ce..c4852112fe 100644
@@ -1655,6 +1655,7 @@ static CXLRetCode cmd_dcd_add_dyn_cap_rsp(const struct cxl_cmd *cmd,
 
         cxl_insert_extent_to_extent_list(extent_list, dpa, len, NULL, 0);
         ct3d->dc.total_extent_count += 1;
+        ct3_set_region_block_backed(ct3d, dpa, len);
     }
     /* Remove the first extent group in the pending list */
     cxl_extent_group_list_delete_front(&ct3d->dc.extents_pending);

@@ -1813,10 +1814,12 @@ static CXLRetCode cmd_dcd_release_dyn_cap(const struct cxl_cmd *cmd,
      * list and update the extent count;
      */
     QTAILQ_FOREACH_SAFE(ent, &ct3d->dc.extents, node, ent_next) {
+        ct3_clear_region_block_backed(ct3d, ent->start_dpa, ent->len);
         cxl_remove_extent_from_extent_list(&ct3d->dc.extents, ent);
     }
     copy_extent_list(&ct3d->dc.extents, &updated_list);
     QTAILQ_FOREACH_SAFE(ent, &updated_list, node, ent_next) {
+        ct3_set_region_block_backed(ct3d, ent->start_dpa, ent->len);
         cxl_remove_extent_from_extent_list(&updated_list, ent);
     }
     ct3d->dc.total_extent_count = updated_list_size;

hw/mem/cxl_type3.c +76 -0

106 lines not on this page · raw message

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #36 lore raw

[PULL v3 38/41] tests/qtest/pvpanic: add tests for pvshutdown event

From: Thomas Weißschuh <[email protected]>

Validate that a shutdown via the pvpanic device emits the correct QMP events.

Reviewed-by Thomas Huth <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 tests/qtest/pvpanic-pci-test.c | 39 ++++++++++++++++++++++++++++++++++
 tests/qtest/pvpanic-test.c     | 29 +++++++++++++++++++++++++
 2 files changed, 68 insertions(+)

tests/qtest/pvpanic-pci-test.c +39 -0

index b372caf41d..dc021c2fdf 100644
@@ -85,11 +85,50 @@ static void test_panic(void)
     qtest_quit(qts);
 }
 
+static void test_pvshutdown(void)
+{
+    uint8_t val;
+    QDict *response, *data;
+    QTestState *qts;
+    QPCIBus *pcibus;
+    QPCIDevice *dev;
+    QPCIBar bar;
+
+    qts = qtest_init("-device pvpanic-pci,addr=04.0");
+    pcibus = qpci_new_pc(qts, NULL);
+    dev = qpci_device_find(pcibus, QPCI_DEVFN(0x4, 0x0));
+    qpci_device_enable(dev);
+    bar = qpci_iomap(dev, 0, NULL);
+
+    qpci_memread(dev, bar, 0, &val, sizeof(val));
+    g_assert_cmpuint(val, ==, PVPANIC_EVENTS);
+
+    val = PVPANIC_SHUTDOWN;
+    qpci_memwrite(dev, bar, 0, &val, sizeof(val));
+
+    response = qtest_qmp_eventwait_ref(qts, "GUEST_PVSHUTDOWN");
+    qobject_unref(response);
+
+    response = qtest_qmp_eventwait_ref(qts, "SHUTDOWN");
+    g_assert(qdict_haskey(response, "data"));
+    data = qdict_get_qdict(response, "data");
+    g_assert(qdict_haskey(data, "guest"));
+    g_assert(qdict_get_bool(data, "guest"));
+    g_assert(qdict_haskey(data, "reason"));
+    g_assert_cmpstr(qdict_get_str(data, "reason"), ==, "guest-shutdown");
+    qobject_unref(response);
+
+    g_free(dev);
+    qpci_free_pc(pcibus);
+    qtest_quit(qts);
+}
+
 int main(int argc, char **argv)
 {
     g_test_init(&argc, &argv, NULL);
     qtest_add_func("/pvpanic-pci/panic", test_panic);
     qtest_add_func("/pvpanic-pci/panic-nopause", test_panic_nopause);
+    qtest_add_func("/pvpanic-pci/pvshutdown", test_pvshutdown);
 
     return g_test_run();
 }

tests/qtest/pvpanic-test.c +29 -0

index ccc603472f..d49d2ba931 100644
@@ -58,11 +58,40 @@ static void test_panic(void)
     qtest_quit(qts);
 }
 
+static void test_pvshutdown(void)
+{
+    uint8_t val;
+    QDict *response, *data;
+    QTestState *qts;
+
+    qts = qtest_init("-device pvpanic");
+
+    val = qtest_inb(qts, 0x505);
+    g_assert_cmpuint(val, ==, PVPANIC_EVENTS);
+
+    qtest_outb(qts, 0x505, PVPANIC_SHUTDOWN);
+
+    response = qtest_qmp_eventwait_ref(qts, "GUEST_PVSHUTDOWN");
+    qobject_unref(response);
+
+    response = qtest_qmp_eventwait_ref(qts, "SHUTDOWN");
+    g_assert(qdict_haskey(response, "data"));
+    data = qdict_get_qdict(response, "data");
+    g_assert(qdict_haskey(data, "guest"));
+    g_assert(qdict_get_bool(data, "guest"));
+    g_assert(qdict_haskey(data, "reason"));
+    g_assert_cmpstr(qdict_get_str(data, "reason"), ==, "guest-shutdown");
+    qobject_unref(response);
+
+    qtest_quit(qts);
+}
+
 int main(int argc, char **argv)
 {
     g_test_init(&argc, &argv, NULL);
     qtest_add_func("/pvpanic/panic", test_panic);
     qtest_add_func("/pvpanic/panic-nopause", test_panic_nopause);
+    qtest_add_func("/pvpanic/pvshutdown", test_pvshutdown);
 
     return g_test_run();
 }

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #37 lore raw

[PULL v3 12/41] virtio-pci: only reset pm state during resetting

From: Jiqian Chen <[email protected]>

Fix bug imported by 27ce0f3afc9dd ("fix Power Management Control Register for PCI Express virtio devices" After this change, observe that QEMU may erroneously clear the power status of the device, or may erroneously clear non writable registers, such as NO_SOFT_RESET, etc.

Only state of PM_CTRL is writable.
Only when flag VIRTIO_PCI_FLAG_INIT_PM is set, need to reset state.

Fixes 27ce0f3afc9dd ("fix Power Management Control Register for PCI Express virtio devices"

Signed-off-by Jiqian Chen <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/virtio/virtio-pci.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

hw/virtio/virtio-pci.c +7 -1

index cffc7efcae..7d62e92365 100644
@@ -2306,10 +2306,16 @@ static void virtio_pci_bus_reset_hold(Object *obj, ResetType type)
     virtio_pci_reset(qdev);
 
     if (pci_is_express(dev)) {
+        VirtIOPCIProxy *proxy = VIRTIO_PCI(dev);
+
         pcie_cap_deverr_reset(dev);
         pcie_cap_lnkctl_reset(dev);
 
-        pci_set_word(dev->config + dev->exp.pm_cap + PCI_PM_CTRL, 0);
+        if (proxy->flags & VIRTIO_PCI_FLAG_INIT_PM) {
+            pci_word_test_and_clear_mask(
+                dev->config + dev->exp.pm_cap + PCI_PM_CTRL,
+                PCI_PM_CTRL_STATE_MASK);
+        }
     }
 }

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #38 lore raw

[PULL v3 40/41] virtio-pci: Fix the failure process in kvm_virtio_pci_vector_use_one()

From: Cindy Lu <[email protected]>

In function kvm_virtio_pci_vector_use_one(), the function will only use the irqfd/vector for itself. Therefore, in the undo label, the failing process is incorrect.
To fix this, we can just remove this label.

Fixes f9a09ca3ea ("vhost: add support for configure interrupt")

Cc [email protected]

Signed-off-by Cindy Lu <[email protected]>

Message-Id: <[email protected]>

Reviewed-by Peter Maydell <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 hw/virtio/virtio-pci.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

hw/virtio/virtio-pci.c +2 ~~-16~~

index 7d62e92365..5941f1a94d 100644
@@ -898,7 +898,7 @@ static int kvm_virtio_pci_vector_use_one(VirtIOPCIProxy *proxy, int queue_no)
     }
     ret = kvm_virtio_pci_vq_vector_use(proxy, vector);
     if (ret < 0) {
-        goto undo;
+        return ret;
     }
     /*
      * If guest supports masking, set up irqfd now.

@@ -908,25 +908,11 @@ static int kvm_virtio_pci_vector_use_one(VirtIOPCIProxy *proxy, int queue_no)
         ret = kvm_virtio_pci_irqfd_use(proxy, n, vector);
         if (ret < 0) {
             kvm_virtio_pci_vq_vector_release(proxy, vector);
-            goto undo;
+            return ret;
         }
     }
 
     return 0;
-undo:
-
-    vector = virtio_queue_vector(vdev, queue_no);
-    if (vector >= msix_nr_vectors_allocated(dev)) {
-        return ret;
-    }
-    if (vdev->use_guest_notifier_mask && k->guest_notifier_mask) {
-        ret = virtio_pci_get_notifier(proxy, queue_no, &n, &vector);
-        if (ret < 0) {
-            return ret;
-        }
-        kvm_virtio_pci_irqfd_release(proxy, n, vector);
-    }
-    return ret;
 }
 static int kvm_virtio_pci_vector_vq_use(VirtIOPCIProxy *proxy, int nvqs)
 {

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #39 lore raw

[PULL v3 39/41] Revert "docs/specs/pvpanic: mark shutdown event as not implemented"

From: Thomas Weißschuh <[email protected]>

The missing functionality has been implemented now.

This reverts commit e739d1935c461d0668057e9dbba9d06f728d29ec.

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 docs/specs/pvpanic.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

docs/specs/pvpanic.rst +1 -1

index b0f27860ec..61a80480ed 100644
@@ -29,7 +29,7 @@ bit 1
   a guest panic has happened and will be handled by the guest;
   the host should record it or report it, but should not affect
   the execution of the guest.
-bit 2 (to be implemented)
+bit 2
   a regular guest shutdown has happened and should be processed by the host
 
 PCI Interface

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #40 lore raw

[PULL v3 14/41] Revert "vhost-user: fix lost reconnect"

From: Li Feng <[email protected]>

This reverts commit f02a4b8e6431598612466f76aac64ab492849abf.

Since the current patch cannot completely fix the lost reconnect problem, there is a scenario that is not considered:
- When the virtio-blk driver is removed from the guest os, s->connected has no chance to be set to false, resulting in subsequent reconnection not being executed.

The next patch will completely fix this issue with a better approach.

Signed-off-by Li Feng <[email protected]>

Message-Id: <[email protected]>

Reviewed-by Raphael Norwitz <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

---
 include/hw/virtio/vhost-user.h |  3 +--
 hw/block/vhost-user-blk.c      |  2 +-
 hw/scsi/vhost-user-scsi.c      |  3 +--
 hw/virtio/vhost-user-base.c    |  2 +-
 hw/virtio/vhost-user.c         | 10 ++--------
 5 files changed, 6 insertions(+), 14 deletions(-)

include/hw/virtio/vhost-user.h +1 -2

index d7c09ffd34..324cd8663a 100644
@@ -108,7 +108,6 @@ typedef void (*vu_async_close_fn)(DeviceState *cb);
 
 void vhost_user_async_close(DeviceState *d,
                             CharBackend *chardev, struct vhost_dev *vhost,
-                            vu_async_close_fn cb,
-                            IOEventHandler *event_cb);
+                            vu_async_close_fn cb);
 
 #endif

hw/block/vhost-user-blk.c +1 -1

index bc2677dbef..15cc24d017 100644
@@ -385,7 +385,7 @@ static void vhost_user_blk_event(void *opaque, QEMUChrEvent event)
     case CHR_EVENT_CLOSED:
         /* defer close until later to avoid circular close */
         vhost_user_async_close(dev, &s->chardev, &s->dev,
-                               vhost_user_blk_disconnect, vhost_user_blk_event);
+                               vhost_user_blk_disconnect);
         break;
     case CHR_EVENT_BREAK:
     case CHR_EVENT_MUX_IN:

hw/scsi/vhost-user-scsi.c +1 -2

index 0b050805a8..421cd654f8 100644
@@ -215,8 +215,7 @@ static void vhost_user_scsi_event(void *opaque, QEMUChrEvent event)
     case CHR_EVENT_CLOSED:
         /* defer close until later to avoid circular close */
         vhost_user_async_close(dev, &vs->conf.chardev, &vsc->dev,
-                               vhost_user_scsi_disconnect,
-                               vhost_user_scsi_event);
+                               vhost_user_scsi_disconnect);
         break;
     case CHR_EVENT_BREAK:
     case CHR_EVENT_MUX_IN:

hw/virtio/vhost-user-base.c +1 -1

index a83167191e..4b54255682 100644
@@ -254,7 +254,7 @@ static void vub_event(void *opaque, QEMUChrEvent event)
     case CHR_EVENT_CLOSED:
         /* defer close until later to avoid circular close */
         vhost_user_async_close(dev, &vub->chardev, &vub->vhost_dev,
-                               vub_disconnect, vub_event);
+                               vub_disconnect);
         break;
     case CHR_EVENT_BREAK:
     case CHR_EVENT_MUX_IN:

hw/virtio/vhost-user.c +2 -8

index cdf9af4a4b..c929097e87 100644
@@ -2776,7 +2776,6 @@ typedef struct {
     DeviceState *dev;
     CharBackend *cd;
     struct vhost_dev *vhost;
-    IOEventHandler *event_cb;
 } VhostAsyncCallback;
 
 static void vhost_user_async_close_bh(void *opaque)

@@ -2791,10 +2790,7 @@ static void vhost_user_async_close_bh(void *opaque)
      */
     if (vhost->vdev) {
         data->cb(data->dev);
-    } else if (data->event_cb) {
-        qemu_chr_fe_set_handlers(data->cd, NULL, NULL, data->event_cb,
-                                 NULL, data->dev, NULL, true);
-   }
+    }
 
     g_free(data);
 }

@@ -2806,8 +2802,7 @@ static void vhost_user_async_close_bh(void *opaque)
  */
 void vhost_user_async_close(DeviceState *d,
                             CharBackend *chardev, struct vhost_dev *vhost,
-                            vu_async_close_fn cb,
-                            IOEventHandler *event_cb)
+                            vu_async_close_fn cb)
 {
     if (!runstate_check(RUN_STATE_SHUTDOWN)) {
         /*

@@ -2823,7 +2818,6 @@ void vhost_user_async_close(DeviceState *d,
         data->dev = d;
         data->cd = chardev;
         data->vhost = vhost;
-        data->event_cb = event_cb;
 
         /* Disable any further notifications on the chardev */
         qemu_chr_fe_set_handlers(chardev,

Signature · 1 line

MST

Michael S. Tsirkin

author

2024-06-05 23:39 UTC #41 lore raw

[PULL v3 21/41] hw/mem/cxl_type3: Add support to create DC regions to type3 memory devices

From: Fan Ni <[email protected]>

With the change, when setting up memory for type3 memory device, we can create DC regions.
A property 'num-dc-regions' is added to ct3_props to allow users to pass the number of DC regions to create. To make it easier, other region parameters like region base, length, and block size are hard coded. If needed, these parameters can be added easily.

With the change, we can create DC regions with proper kernel side support like below:

region=$(cat /sys/bus/cxl/devices/decoder0.0/create_dc_region) echo $region > /sys/bus/cxl/devices/decoder0.0/create_dc_region echo 256 > /sys/bus/cxl/devices/$region/interleave_granularity echo 1 > /sys/bus/cxl/devices/$region/interleave_ways

echo "dc0" >/sys/bus/cxl/devices/decoder2.0/mode echo 0x40000000 >/sys/bus/cxl/devices/decoder2.0/dpa_size

echo 0x40000000 > /sys/bus/cxl/devices/$region/size echo "decoder2.0" > /sys/bus/cxl/devices/$region/target0 echo 1 > /sys/bus/cxl/devices/$region/commit echo $region > /sys/bus/cxl/drivers/cxl_region/bind

Signed-off-by Fan Ni <[email protected]>

Message-Id: <[email protected]>

Signed-off-by Michael S. Tsirkin <[email protected]>

Reviewed-by Li Zhijian <[email protected]>

---
 hw/mem/cxl_type3.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

hw/mem/cxl_type3.c +53 -0

index 7194c8f902..06c6f9bb78 100644
@@ -30,6 +30,7 @@
 #include "hw/pci/msix.h"
 
 #define DWORD_BYTE 4
+#define CXL_CAPACITY_MULTIPLIER   (256 * MiB)
 
 /* Default CDAT entries for a memory region */
 enum {

@@ -567,6 +568,50 @@ static void ct3d_reg_write(void *opaque, hwaddr offset, uint64_t value,
     }
 }
 
+/*
+ * TODO: dc region configuration will be updated once host backend and address
+ * space support is added for DCD.
+ */
+static bool cxl_create_dc_regions(CXLType3Dev *ct3d, Error **errp)
+{
+    int i;
+    uint64_t region_base = 0;
+    uint64_t region_len =  2 * GiB;
+    uint64_t decode_len = 2 * GiB;
+    uint64_t blk_size = 2 * MiB;
+    CXLDCRegion *region;
+    MemoryRegion *mr;
+
+    if (ct3d->hostvmem) {
+        mr = host_memory_backend_get_memory(ct3d->hostvmem);
+        region_base += memory_region_size(mr);
+    }
+    if (ct3d->hostpmem) {
+        mr = host_memory_backend_get_memory(ct3d->hostpmem);
+        region_base += memory_region_size(mr);
+    }
+    if (region_base % CXL_CAPACITY_MULTIPLIER != 0) {
+        error_setg(errp, "DC region base not aligned to 0x%lx",
+                   CXL_CAPACITY_MULTIPLIER);
+        return false;
+    }
+
+    for (i = 0, region = &ct3d->dc.regions[0];
+         i < ct3d->dc.num_regions;
+         i++, region++, region_base += region_len) {
+        *region = (CXLDCRegion) {
+            .base = region_base,
+            .decode_len = decode_len,
+            .len = region_len,
+            .block_size = blk_size,
+            /* dsmad_handle set when creating CDAT table entries */
+            .flags = 0,
+        };
+    }
+
+    return true;
+}
+
 static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
 {
     DeviceState *ds = DEVICE(ct3d);

@@ -635,6 +680,13 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
         g_free(p_name);
     }
 
+    if (ct3d->dc.num_regions > 0) {
+        if (!cxl_create_dc_regions(ct3d, errp)) {
+            error_append_hint(errp, "setup DC regions failed");
+            return false;
+        }
+    }
+
     return true;
 }

@@ -930,6 +982,7 @@ static Property ct3_props[] = {
                      HostMemoryBackend *),
     DEFINE_PROP_UINT64("sn", CXLType3Dev, sn, UI64_NULL),
     DEFINE_PROP_STRING("cdat", CXLType3Dev, cxl_cstate.cdat.filename),
+    DEFINE_PROP_UINT8("num-dc-regions", CXLType3Dev, dc.num_regions, 0),
     DEFINE_PROP_END_OF_LIST(),
 };

Signature · 1 line

MST

Richard Henderson

2024-06-05 23:57 UTC #42 lore raw