created | 2019-05-14T10:57:45Z |
---|---|
begin | 2019-05-07T00:00:00Z |
end | 2019-05-08T00:00:00Z |
path | src/sys |
commits | 5 |
date | 2019-05-07T00:06:00Z | |||
---|---|---|---|---|
author | dlg | |||
files | src/sys/dev/pci/if_mcx.c | log | diff | annotate |
message |
use MCX_PAGE_SIZE when calculating number of pages for queues PAGE_SIZE might be the same, but isn't on sparc64 at least. ok jmatthew@ |
date | 2019-05-07T00:08:33Z | |||
---|---|---|---|---|
author | dlg | |||
files | src/sys/dev/pci/if_mcx.c | log | diff | annotate |
message |
align the rx buffer to ETHER_ALIGN this will probably change as the rx handling grows to cope with the hardware max mru. ok jmatthew@ |
date | 2019-05-07T04:12:15Z | |||
---|---|---|---|---|
author | jmatthew | |||
files | src/sys/dev/pci/if_mcx.c | log | diff | annotate |
message |
always rearm completion queues as leaving them disarmed would lead to rx or tx completion stalling. (also replace a line dlg didn't mean to remove) |
date | 2019-05-07T14:22:06Z | |||
---|---|---|---|---|
author | cheloha | |||
files | src/sys/dev/ic/ncr53c9x.c | log | diff | annotate |
message | Fix delay logic: measure w/ uptime, pack timeval correctly. ok krw@ |
date | 2019-05-07T23:21:49Z | |||
---|---|---|---|---|
author | jmatthew | |||
files | src/sys/dev/pci/if_mcx.c | log | diff | annotate |
message |
Use the same completion queue for both the send and receive queues. We don't get any benefit from having separate queues (yet), and the tx completion queue seems to stall sometimes if it's on its own. |