Re: [PATCH v2 1/2] vhost: fix memory leak in Virtio Tx split path

2024-02-06 Thread Maxime Coquelin
On 1/31/24 20:53, Maxime Coquelin wrote: When vIOMMU is enabled and Virtio device is bound to kernel driver in guest, rte_vhost_dequeue_burst() will often return early because of IOTLB misses. This patch fixes a mbuf leak occurring in this case. Fixes: 242695f6122a ("vhost: allocate and free

Re: [PATCH v2 1/2] vhost: fix memory leak in Virtio Tx split path

2024-02-06 Thread Maxime Coquelin
On 2/6/24 11:29, David Marchand wrote: On Wed, Jan 31, 2024 at 8:53 PM Maxime Coquelin wrote: When vIOMMU is enabled and Virtio device is bound to kernel driver in guest, rte_vhost_dequeue_burst() will often return early because of IOTLB misses. In theory, we can hit this issue with a dpd

Re: [PATCH v2 1/2] vhost: fix memory leak in Virtio Tx split path

2024-02-06 Thread David Marchand
On Wed, Jan 31, 2024 at 8:53 PM Maxime Coquelin wrote: > > When vIOMMU is enabled and Virtio device is bound to kernel > driver in guest, rte_vhost_dequeue_burst() will often return > early because of IOTLB misses. In theory, we can hit this issue with a dpdk pmd too, as long as the vIOMMU is in

[PATCH v2 1/2] vhost: fix memory leak in Virtio Tx split path

2024-01-31 Thread Maxime Coquelin
When vIOMMU is enabled and Virtio device is bound to kernel driver in guest, rte_vhost_dequeue_burst() will often return early because of IOTLB misses. This patch fixes a mbuf leak occurring in this case. Fixes: 242695f6122a ("vhost: allocate and free packets in bulk in Tx split") Cc: sta...@dpdk