gonzo [Thu, 29 Oct 2015 22:12:03 +0000 (22:12 +0000)]
Fix LEAVE_HYP macro: spsr is not guaranteed to contain valid value at this
point, e.g. on RaspberryPi 2 when control is passed from loader to kernel
it contains garbage. So we use cpsr as a base for new cpsr value: if we
have reached this point it means current value is OK
jhb [Thu, 29 Oct 2015 21:25:46 +0000 (21:25 +0000)]
Use movw instead of movl (or plain mov) when moving segment registers
into memory. This is a nop on clang's assembler, but some assemblers
complain if the size suffix is incorrect.
kp [Thu, 29 Oct 2015 20:45:53 +0000 (20:45 +0000)]
pf: Fix IPv6 checksums with route-to.
When using route-to (or reply-to) pf sends the packet directly to the output
interface. If that interface doesn't support checksum offloading the checksum
has to be calculated in software.
That was already done in the IPv4 case, but not for the IPv6 case. As a result
we'd emit packets with pseudo-header checksums (i.e. incorrect checksums).
This issue was exposed by the changes in r289316 when pf stopped performing full
checksum calculations for all packets.
cem [Thu, 29 Oct 2015 19:07:00 +0000 (19:07 +0000)]
pmap_change_attr: Only fixup DMAP for DMAPed ranges
pmap_change_attr must change the memory type of both the requested KVA
and the corresponding DMAP mappings (if such mappings exist), to satisfy
an Intel requirement that two or more mappings to the same physical
pages must have the same memory type.
However, not all kernel mapped pages have corresponding DMAP mappings --
for example, 64-bit BARs. Skip fixing up the DMAP for out-of-bounds
addresses.
hselasky [Thu, 29 Oct 2015 13:53:37 +0000 (13:53 +0000)]
Add missing NULL check in physio().
When destroying a character device the si_devsw field is set to NULL
before all references are gone, to indicate the character device is
going away. This can cause a NULL-dereference fault inside physio().
The callers of physio() should own a thread reference on the cdev and
if si_devsw is seen as non-NULL, it is usable during the execution of
the function. Else an ENXIO error code is returned.
hselasky [Thu, 29 Oct 2015 08:28:39 +0000 (08:28 +0000)]
Finish process of moving the LinuxKPI module into the default kernel build.
- Move all files related to the LinuxKPI into sys/compat/linuxkpi and
its subfolders.
- Update sys/conf/files and some Makefiles to use new file locations.
- Added description of COMPAT_LINUXKPI to sys/conf/NOTES which in turn
adds the LinuxKPI to all LINT builds.
- The LinuxKPI can be added to the kernel by setting the
COMPAT_LINUXKPI option. The OFED kernel option no longer builds the
LinuxKPI into the kernel. This was done to keep the build rules for
the LinuxKPI in sys/conf/files simple.
- Extend the LinuxKPI module to include support for USB by moving the
Linux USB compat from usb.ko to linuxkpi.ko.
- Bump the FreeBSD_version.
- A universe kernel build has been done.
Reviewed by: np @ (cxgb and cxgbe related changes only)
Sponsored by: Mellanox Technologies
cem [Thu, 29 Oct 2015 04:16:16 +0000 (04:16 +0000)]
ioatcontrol(8): Add and document "raw" testing mode
Allows DMA from/to arbitrary KVA or physical address. /dev/ioat_test
must be enabled by root and is only R/W root, so this is approximately
as dangerous as /dev/mem and /dev/kmem.
bdrewery [Thu, 29 Oct 2015 00:41:03 +0000 (00:41 +0000)]
Fix regression from using .USEBEFORE in _SUBDIR in r289705.
Using .USEBEFORE had the unintended side-effect of changing the directory for
the real target ran in the current directory. For example this meant that
the 'make clean' would run in one of the SUBDIR.
Sponsored by: EMC / Isilon Storage Division
Pointyhat to: bdrewery
hiren [Wed, 28 Oct 2015 22:57:51 +0000 (22:57 +0000)]
Calculate the correct amount of bytes that are in-flight for a connection as
suggested by RFC 6675.
Currently differnt places in the stack tries to guess this in suboptimal ways.
The main problem is that current calculations don't take sacked bytes into
account. Sacked bytes are the bytes receiver acked via SACK option. This is
suboptimal because it assumes that network has more outstanding (unacked) bytes
than the actual value and thus sends less data by setting congestion window
lower than what's possible which in turn may cause slower recovery from losses.
As an example, one of the current calculations looks something like this:
snd_nxt - snd_fack + sackhint.sack_bytes_rexmit
New proposal from RFC 6675 is:
snd_max - snd_una - sackhint.sacked_bytes + sackhint.sack_bytes_rexmit
which takes sacked bytes into account which is a new addition to the sackhint
struct. Only thing we are missing from RFC 6675 is isLost() i.e. segment being
considered lost and thus adjusting pipe based on that which makes this
calculation a bit on conservative side.
The approach is very simple. We already process each ack with sack info in
tcp_sack_doack() and extract sack blocks/holes out of it. We'd now also track
this new variable sacked_bytes which keeps track of total sacked bytes reported.
One downside to this approach is that we may get incorrect count of sacked_bytes
if the other end decides to drop sack info in the ack because of memory pressure
or some other reasons. But in this (not very likely) case also the pipe
calculation would be conservative which is okay as opposed to being aggressive
in sending packets into the network.
Next step is to use this more accurate pipe estimation to drive congestion
window adjustments.
imp [Wed, 28 Oct 2015 19:11:06 +0000 (19:11 +0000)]
BUS_ADD_CHILD calls device_add_child. device_add_child does not call
BUS_ADD_CHILD. Make it explicit since it follows the command paradigm
rather than the callback paradigm. Add other clarifying notes as well.
andrew [Wed, 28 Oct 2015 13:14:16 +0000 (13:14 +0000)]
Remove the s3c2xx0 code, it's no longer used. As far as I know I as the
main user of this code, however I haven't used it in over two years, and
don't expect to in the future.
mav [Wed, 28 Oct 2015 12:34:59 +0000 (12:34 +0000)]
Improve/fix loop scanning routine.
For the most of chips (except anscient ones) port handlers have no relation
to port IDs. In such situation old code scanning first 125 handlers was
quite naive. Instead of doing that, send to chip single request to get full
list of port handlers available on specific virtual port and scan only them.
Old code had problems with case of several virtual ports enabled, when port
handlers allocated from global address space could easily go above 125.
This change was successfully tested on 23xx, 24xx and 25xx chips in loop
mode with 4 virtual initiator ports, each seing 50 virtual target ports.
gnn [Wed, 28 Oct 2015 03:43:24 +0000 (03:43 +0000)]
Add a test for the listen queue using two test programs,
listen, and connect. The listen program is a simple server that
accepts and closes sockets, until a fixed limit, then sets the listen
queue to 0 and counts how many remaining connections it processes.
The connect program repeatedly opens connections and closes them
serving as the driver for the listen program.
mckusick [Tue, 27 Oct 2015 22:59:24 +0000 (22:59 +0000)]
Bring the tags and links entries for amd64 up to date.
Based on how out of date it is, I doubt that anyone
other than me and my code-reading students still use it.
andrew [Tue, 27 Oct 2015 22:24:57 +0000 (22:24 +0000)]
Mark functions as such. This means we call them directly rather than have
the dynamic linker copy them, but not relocate them at the new location.
This allows us to run sqlite3 without it crashing.
hiren [Tue, 27 Oct 2015 09:43:05 +0000 (09:43 +0000)]
Add sysctl tunable net.inet.tcp.initcwnd_segments to specify initial congestion
window in number of segments on fly. It is set to 10 segments by default.
Remove net.inet.tcp.experimental.initcwnd10 which is now redundant. Also remove
the parent node net.inet.tcp.experimental as it's not needed anymore and also
because it was not well thought out.
bdrewery [Tue, 27 Oct 2015 01:29:38 +0000 (01:29 +0000)]
META MODE: Fix after addition of bsd.confs.mk: Stage in "files" set.
The "files" staging name is not the same as "bsd.files.mk" but seems to just be
a group of extra files that are not the essential includes or libraries, which
include .
delphij [Tue, 27 Oct 2015 01:26:50 +0000 (01:26 +0000)]
Revert r289269 for now. After looking at share/zoneinfo/Makefile this could
potentially break non-root installs and we need a better solution, probably
by doing it differently when no UI is involved.
* refactor out the rx filter and operating mode code into a separate
method.
* add some comments about what's left with setting the operating mode
based on what carl9170 does.
* comment out some init from otus_init_mac() - it's no longer needed as
it's always init'ed now.
* add debugging and a missing return around a failure to call m_get2() -
during monitor mode operation I found RXing of frames > 2k, which
fails allocation. I'm sure they're valid (it's configuring 11n RX and
receiving 11n frames even though the driver doesn't "do" 11n)
and may be A-MSDU; but allocations fail and we should handle that
gracefully.
Tested:
* UB82 reference NIC (AR9170 + AR9104 2x2 dual band NIC); STA and
monitor mode operation.
gnn [Tue, 27 Oct 2015 00:42:15 +0000 (00:42 +0000)]
Turning on IPSEC used to introduce a slight amount of performance
degradation (7%) for host host TCP connections over 10Gbps links,
even when there were no secuirty policies in place. There is no
change in performance on 1Gbps network links. Testing GENERIC vs.
GENERIC-NOIPSEC vs. GENERIC with this change shows that the new
code removes any overhead introduced by having IPSEC always in the
kernel.
projects / people / julieng / freebsd.git / log