From: Huguanshen Chen
On arm64 virtualization platform, vfio-user devices lose their interrupts after
migration to the destination. This issue occurs because qemu fails to deliver
the msi device id to the vGIC. The error device id is calculated based on the
device's parent bus, so it is essential
From: Huaitong Han
The vring call fd is set even when the guest does not use MSI-X (e.g., in the
case of virtio PMD), leading to unnecessary CPU overhead for processing
interrupts.
The commit 96a3d98d2c("vhost: don't set vring call if no vector") optimized the
case where MSI-X is enabled but the
From: Huaitong Han
The vring call fd is set even when the guest does not use MSI-X (e.g., in the
case of virtio PMD), leading to unnecessary CPU overhead for processing
interrupts.
The commit 96a3d98d2c("vhost: don't set vring call if no vector") optimized the
case where MSI-X is enabled but the
t result:
https://raw.githubusercontent.com/oenhan/build_log/refs/heads/main/qemu/2503261015/build/meson-logs/testlog.txt
Reported-by: Zhiyuan Yuan
Signed-off-by: Jidong Xia
Signed-off-by: Huaitong Han
---
hw/pci/pci.c | 2 +-
hw/s390x/virtio-ccw.c | 9 ++---
hw
From: Huaitong Han
The vring call fd is set even when the guest does not use MSIX (e.g., virtio
PMD). This results in unnecessary CPU overhead for handling virtio interrupts.
The previous patch only optimized the condition when query_queue_notifier was
enabled and the vector was unset. However, i
From: Huaitong Han
The vring call fd is set even when the guest does not use MSIX (e.g., virtio
PMD). This results in unnecessary CPU overhead for handling virtio interrupts.
The previous patch only optimized the condition when query_queue_notifier was
enabled and the vector was unset. However, i
