Re: [PATCH v3 14/28] vhost: add helper for interrupt injection

2023-06-01 Thread Maxime Coquelin
On 5/26/23 10:54, David Marchand wrote: On Thu, May 25, 2023 at 6:26 PM Maxime Coquelin wrote: @@ -900,6 +905,24 @@ vhost_need_event(uint16_t event_idx, uint16_t new_idx, uint16_t old) return (uint16_t)(new_idx - event_idx - 1) < (uint16_t)(new_idx - old); } +static __rte_always

Re: [PATCH v3 14/28] vhost: add helper for interrupt injection

2023-05-26 Thread David Marchand
On Thu, May 25, 2023 at 6:26 PM Maxime Coquelin wrote: > @@ -900,6 +905,24 @@ vhost_need_event(uint16_t event_idx, uint16_t new_idx, > uint16_t old) > return (uint16_t)(new_idx - event_idx - 1) < (uint16_t)(new_idx - > old); > } > > +static __rte_always_inline void > +vhost_vring_inject

[PATCH v3 14/28] vhost: add helper for interrupt injection

2023-05-25 Thread Maxime Coquelin
Vhost-user uses eventfd to inject IRQs, but VDUSE uses an ioctl. This patch prepares vhost_vring_call_split() and vhost_vring_call_packed() to support VDUSE by introducing a new helper. It also adds a new counter for guest notification failures, which could happen in case of uninitialized call fi