Add a workaround for a deadlock between the rt_setgate() and rt_check()
functions. It is easily triggered by running routed, and, I expect, by
running any other daemon that uses routing sockets.
Implement a workaround of the datacorruption problem on ServerWorks
HT1000 chipsets. The HT1000 DMA engine seems to not always like 64K
transfers and sometimes barfs data all over memory leading to instant
chrash and burn.
Also fix 48bit adressing issues, apparently newer chips needs 16bit
writes and not the usual fifo thing.
HW donated by: Travis Mikalson at TerraNovaNet
Original work: sos
Increase control channel xmit queue to 128 packets.
Previous value 16 was too small for real LAC as temporal activity
spike cound easily overflow queue demanding tunnel disconnection due
to possible state inconsistency.
Fix a panic where if the mbuf was consumed by the filter for requeueing
(dummynet), ipsec_filter() would return the empty error code and the ipsec
code would continue to forward/deference the null mbuf.
Approved by: re (gnn)
When IPSEC fails to allocate policy state for an inpcb, and MAC is in use,
free the MAC label on the inpcb before freeing the inpcb.
Submitted by: tanyong <tanyong at ercist dot iscas dot ac dot cn>,
zhouzhouyi
Approved by: re (kensmith)
Fix a MAC label leak for POSIX semaphores, in which per-policy labels
would be properly disposed of, but the global label structure for the
semaphore wouldn't be freed.
Reported by: tanyong <tanyong at ercist dot iscas dot ac dot cn>,
zhouzhouyi
Approved by: re (kensmith)
Fix leaking MAC labels for IPv6 inpcbs by adding missing MAC label
destroy call; this transpired because the inpcb alloc path for IPv4/IPv6
is the same code, but IPv6 has a separate free path. The results was
that as new IPv6 TCP connections were created, kernel memory would
gradually leak.
Reported by: tanyong <tanyong at ercist dot iscas dot ac dot cn>,
zhouzhouyi
Approved by: re (kensmith)
- Use the macro to check the port status has it will also test if its
administratively down (!IFF_UP)
- Use the same parameters to lagg_link_active() to get the backup port as in
the output path, this didnt actually matter in practice as sc_primary is
always the first on the port list.
Approved by: re (kensmith)
When the bridge has an address and a packet comes in for it then drop it if
the link has been marked discarding by Spanning Tree.
Approved by: re (kensmith)
Disallow the legacy USB circuit to generate an SMI# via an ICH
register (MacBooks only).
This allows MacBooks to boot in SMP mode without any trick and
solves
the timer problems with HZ=1000.
Approved by: re (kensmith), njl (mentor)
Disallow the legacy USB circuit to generate an SMI# via an ICH
register (MacBooks only).
This allows MacBooks to boot in SMP mode without any trick and
solves the timer problems with HZ=1000.
Approved by: re (kensmith), njl (mentor)
machines with hz=1000 drop connections in a matter of a few seconds on a
fast link (eg: ethernet). With this change, it drops them in the same
time as a machine with hz=100 would.
Remove ng_pppoe_sendpacket() function to simplify code as it is called
as much times as it has cases inside of it.
Split ng_pppoe_rcvdata() function into three hook-specific ones
to simplify code and reduce stack usage.
trips over often. Specifically, in these chipsets DMA transfers that
cross a page boundary result in data corruption. The workaround is to
not allow any DMA transfers for non-static DMA maps (i.e. "real"
transfers as opposed to work areas allocated with bus_dmamem_alloc()) to
cross a page in a single S/G element. This behavior is enabled by
setting 'busdma_pyxis_bug' to 1.
- Add a new tunable 'machdep.busdma_pyxis_bug' that can be used to enable
the workaround from the loader. This can be used to enable it on
chipsets where we don't automatically enable it.
- Auto-enable the workaround for buggy PYXIS 1 chipsets supported via
cia(4).
PR: alpha/75317
* Add preliminary SATA ATAPI support for sii 3132/3124 chips.
* Fix speed report on Intel SATA chips in compat mode.
* Fix broken detect of JMicron 368.
Related revisions:
- ata-chipset.c: 1.208, 1.210
- ata-disk.c.c: 1.205
Approved by: re (kensmith), sos
3 arguments, but we had forgotten the second argument. Also make the
Linux statfs64 struct depend on the architecture because it has an
extra 4 bytes padding on amd64 compared to i386.
The three argument fix is from David Taylor, the struct statfs64
stuff is my fault. With this patch I can install i386 Linux matlab
on an amd64 machine.
Approved by: re (kensmith)
sys/arm/include/asmacros.h rev 1.7
sys/arm/include/atomic.h rev 1.23
Close a race.
The RAS implementation would set the end address, then the start
address. These were used by the kernel to restart a RAS sequence if
it was interrupted. When the thread switching code ran, it would
check these values and adjust the PC and clear them if it did.
However, there's a small flaw in this scheme. Thread T1, sets the end
address and gets preempted. Thread T2 runs and also does a RAS
operation. This resets end to zero. Thread T1 now runs again and
sets start and then begins the RAS sequence, but is preempted before
the RAS sequence executes its last instruction. The kernel code that
would ordinarily restart the RAS sequence doesn't because the PC isn't
between start and 0, so the PC isn't set to the start of the sequence.
So when T1 is resumed again, it is at the wrong location for RAS to
produce the correct results. This causes the wrong results for the
atomic sequence.
The window for the first race is 3 instructions. The window for the
second race is 5-10 instructions depending on the atomic operation.
This makes this failure fairly rare and hard to reproduce.
Mutexs are implemented in libthr using atomic operations. When the
above race would occur, a lock could get stuck locked, causing many
downstream problems, as you might expect.
Also, make sure to reset the start and end address when doing a syscall, or
a malicious process could set them before doing a syscall.
Reviewed by: imp, ups (thanks guys)
Approved by: re (kensmith)
Pointy hat to: cognet
date: 2007/11/26 19:08:08; author: sos; state: Exp; lines: +1 -1
Use device_set_desc_copy in the generic ident as its used on a temp buffer.
Approved by: re (kensmith)
Check for the program headers alignment of the ELF images before
dereferencing. Unaligned access could cause panic on strict alignment
architectures.
Approved by: re (kensmith)
- WITNESS lock problem due to naming of multi locks
- Race in em_stop if you don't hold the TX lock
- Bug in TSO code when you have fowarding and different
MSS sizes (this more for completeness since TSO is not
enabled in 6.3)
Essentially syncs the two drivers up to version 6.7.3
Approved by:re
