Re: [PATCH v5 04/14] iommufd: Abstract an iommufd_eventq from iommufd_fault

2025-01-10 Thread Nicolin Chen
On Fri, Jan 10, 2025 at 01:26:37PM -0400, Jason Gunthorpe wrote: > +#define INIT_EVENTQ_FOPS(read_op, write_op) \ > + (struct file_operations){ \ > + .owner = THIS_MODULE, \ > + .open = nonseekab

Re: [PATCH v5 04/14] iommufd: Abstract an iommufd_eventq from iommufd_fault

2025-01-10 Thread Jason Gunthorpe
On Tue, Jan 07, 2025 at 09:10:07AM -0800, Nicolin Chen wrote: > @@ -433,32 +434,35 @@ void iopt_remove_access(struct io_pagetable *iopt, > u32 iopt_access_list_id); > void iommufd_access_destroy_object(struct iommufd_object *obj); > > -/* > - * An iommufd_fault object repr

RE: [PATCH v5 04/14] iommufd: Abstract an iommufd_eventq from iommufd_fault

2025-01-09 Thread Tian, Kevin
> From: Nicolin Chen > Sent: Wednesday, January 8, 2025 1:10 AM > > The fault object was designed exclusively for hwpt's IO page faults (PRI). > But its queue implementation can be reused for other purposes too, such as > hardware IRQ and event injections to user space. > > Meanwhile, a fault ob

[PATCH v5 04/14] iommufd: Abstract an iommufd_eventq from iommufd_fault

2025-01-07 Thread Nicolin Chen
The fault object was designed exclusively for hwpt's IO page faults (PRI). But its queue implementation can be reused for other purposes too, such as hardware IRQ and event injections to user space. Meanwhile, a fault object holds a list of faults. So it's more accurate to call it a "fault queue".