| Age | Commit message (Collapse) | Author |
|---|
|
chipsets. All of those that support 64-bit CPUs should support MSI as well.
Explicitly disable MSI on chipsets that connect to the CPU over HyperTransport.
Enabling MSI on those systems is handled by the HyperTransport support code
in our PCI subsystem.
|
|
- Intel chipset supporting Pentium 4 or later.
- Any AMD chipset made in this century.
- Any NVIDIA chipset that has PCIe.
Explicitly disable MSI on chipsets that connect to the CPU over HyperTransport.
Enabling MSI on those systems is handled by the HyperTransport support code
in our PCI subsystem.
|
|
|
|
OK millert@.
|
|
ok dlg@, oga@
|
|
|
|
bytes as a bonus.
|
|
This makes writing a diff that makes 64-bit unclean applications explode
a one-line diff.
ok deraadt
|
|
|
|
names used in the documentation over marketing names).
|
|
The old VM_MAP_RANGE_CHECK macro was wrong and caused code to be unreadable
(argument altering macros are harmful).
Each function now treats the memory range outside the map as it would treat
free memory: if it would error on being given free memory, it'll error
in a similar fashion when the start,end parameters fall outside the map.
If it would accept free memory in its argument range, it'll silently accept
the outside-map memory too.
Confirmed to help ports build machines.
|
|
|
|
continue); makes the AMD E-350 speed adjust (from slow to way slower).
discussion with jsg.
|
|
|
|
|
|
specify the outgoing interface with a multicast option up. Doing
this before the route lookup allows multicast traffic to work even
when the default 224/4 reject route is installed. Raw IP and IPv6
already had this behaviour.
Based on work by Christiano F. Haesbaert. OK sthen@
|
|
Problem found by Nathanael Rensen (nathanael at polymorpheus dot com)
|
|
|
|
(the latter is the name of the associated Xeon processors).
|
|
|
|
|
|
|
|
away from them) thinkpads are returning garbage for the return value.
We never did anything special about the return value except spit out
some noise, so silence it.
ok mlarkin
|
|
|
|
|
|
|
|
|
|
away. Based on a diff from Bryan Steele.
ok deraadt@
|
|
this is not allowed according to Stevens and RFCs 5735 and 1122.
Suggestion to use ENETUNREACH from claudio.
OK phessler@, claudio@
|
|
known the register is to disable broadcast instead of enabling
broadcast packets.
From Brad
|
|
From Brad. Tested by Thomas Pfaff
|
|
|
|
errno not 0/1.
ok guenther
|
|
|
|
Tested by Joe Gidi
|
|
Doesn't matter much since C++ ABI used by GCC doesn't mangle variable
names; however technically is required by Section 7.5 of the C++ spec.
Discussed with/OK guenther@, matthew@.
|
|
the real hardware, some emulators (such as those which name start with `qe'
and end in `mu' and are four letters long) expect the cpu behaviour to
honour the value of these bits. This is not worth doing but it's cheap.
|
|
|
|
(firstname dot lastname at orange dot frogland).
|
|
found on some G4 PowerBook.
Tested by many, thanks.
ok sthen@, kettenis@, miod@
|
|
pf_scrub in the rule (no-state) case. Since the action (a) may be NULL
for e.g. the implicit pass rule. Should fix the panics seen by other
people.
|
|
It's the last file referencing atapiscsi.h too, so might as well get
rid of the need-flags in files.atapiscsi.
|
|
capability to mii(4).
- Limit DMA burst size to be less than or equal to 1024 bytes.
Controller does not seem to support more than 1024 bytes DMA burst.
- Do not touch CMB TX threshold register when CMB is not used.
From FreeBSD via Brad
- Properly initialize sc_product and alc_rev early enough in
alc_attach() with the PCI product id and PCI revision.
- Further sync if_alcvar.h changes from FreeBSD for L2C/L1D
addition commit which in OpenBSD has been merged into if_alcreg.h
From Brad; tested by Gabriel Linder and edd@.
|
|
normal intx style interrupt.
tested on a box with three mpii(4) controllers:
mpii0 at pci5 dev 0 function 0 "Symbios Logic SAS2008" rev 0x03: msi
mpii1 at pci8 dev 0 function 0 "Symbios Logic SAS2008" rev 0x03: msi
mpii2 at pci14 dev 0 function 0 "Symbios Logic SAS2008" rev 0x03: apic 2 int 8
no functional change, ie, everything still works.
it is ok to do this in mpii(4) since it is only enabled on i386 and
amd64, which are the only archs to get msi code so far.
discussed with and ok kettenis@
|
|
kernel without the former. Also, eliminate two dead stores in
wdcattach().
ok dlg@
|
|
ATAPI devices. atapiscsi(4) is only for handling ATAPI devices on an
ATA bus, so umass(4) shouldn't care about it.
ok krw@, dlg@; no objections from deraadt@
|
|
|
|
|
|
vmmap is designed to perform address space randomized allocations,
without letting fragmentation of the address space go through the roof.
Some highlights:
- kernel address space randomization
- proper implementation of guardpages
- roughly 10% system time reduction during kernel build
Tested by alot of people on tech@ and developers.
Theo's machines are still happy.
|
|
pf_scrub with the right arugments in the rule case so that match
rules will work as expected. As a benefit allow setting the tos
on IPv6 packets as well.
OK henning@
|
