Re: MSI-X support

2016-09-01 Thread Hrvoje Popovski
On 4.5.2016. 16:32, Mark Kettenis wrote: >>> This is great, thanks for doing this! I'm a bit surprised that >>> we don't need to the same suspend/resume dance in ppb(4) as with >>> MSI. >>> >> >> That is an excellent point I overlooked. Kettenis, do we? > > Almost certainly. I committed the diff

Re: MSI-X support

2016-05-04 Thread Mark Kettenis
*); > > > > > > You use it like pci_intr_map_msi(9) and pci_intr_map(9), buthave to > > > pass it a vector number as the 2nd argument. Typically you'll pass 0, > > > wich will map the 1st vector, which is always there on hardware with > > > MSI-X

Re: MSI-X support

2016-05-04 Thread Mike Belopuhov
on: > > int pci_intr_map_msix(struct pci_attach_args *, int, pci_intr_handle_t *); > > You use it like pci_intr_map_msi(9) and pci_intr_map(9), buthave to > pass it a vector number as the 2nd argument. Typically you'll pass 0, > wich will map the 1st vector, which is al

Re: MSI-X support

2016-05-04 Thread Mike Larkin
ctor number as the 2nd argument. Typically you'll pass 0, > > wich will map the 1st vector, which is always there on hardware with > > MSI-X support. Some hardware supports more than 1 vector. Typical > > examples are network cards that support multiple rings. Please be

Re: MSI-X support

2016-05-04 Thread Mike Larkin
nt, pci_intr_handle_t *); > > > > > > You use it like pci_intr_map_msi(9) and pci_intr_map(9), buthave to > > > pass it a vector number as the 2nd argument. Typically you'll pass 0, > > > wich will map the 1st vector, which is always there on hardware with > >

Re: MSI-X support

2016-05-04 Thread Hrvoje Popovski
You use it like pci_intr_map_msi(9) and pci_intr_map(9), buthave to >>> pass it a vector number as the 2nd argument. Typically you'll pass 0, >>> wich will map the 1st vector, which is always there on hardware with >>> MSI-X support. Some hardware supports more tha

Re: MSI-X support

2016-05-03 Thread Mark Kettenis
gt; pass it a vector number as the 2nd argument. Typically you'll pass 0, > > wich will map the 1st vector, which is always there on hardware with > > MSI-X support. Some hardware supports more than 1 vector. Typical > > examples are network cards that support mult

Re: MSI-X support

2016-05-03 Thread Mike Larkin
always there on hardware with > MSI-X support. Some hardware supports more than 1 vector. Typical > examples are network cards that support multiple rings. Please be > aware that on architectures like i386 and amd64, the number of > interrupt vectors at each level is limited. If you

MSI-X support

2016-05-03 Thread Mark Kettenis
*); You use it like pci_intr_map_msi(9) and pci_intr_map(9), buthave to pass it a vector number as the 2nd argument. Typically you'll pass 0, wich will map the 1st vector, which is always there on hardware with MSI-X support. Some hardware supports more than 1 vector. Typical examples are ne