Linus Torvalds [Fri, 30 Sep 2005 15:42:52 +0000 (08:42 -0700)]
Merge /pub/scm/linux/kernel/git/davem/net-2.6
Al Viro [Fri, 30 Sep 2005 03:20:57 +0000 (04:20 +0100)]
[PATCH] missing qualifiers in readb() et.al. on ppc
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Fri, 30 Sep 2005 03:19:43 +0000 (04:19 +0100)]
[PATCH] volatile unsigned short f(...) doesn't make sense
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Fri, 30 Sep 2005 02:36:50 +0000 (03:36 +0100)]
[PATCH] bogus BUILD_BUG_ON() in bpa_iommu
BUILD_BUG_ON(1) is asking for trouble (and getting it) when used in that
manner - dead code elimination happens after we parse it and invalid
type is invalid type, dead code or not.
It might be version-dependent, but at least 4.0.1 refuses to accept
that.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Fri, 30 Sep 2005 02:29:05 +0000 (03:29 +0100)]
[PATCH] uml get_user() NULL noise removal
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Fri, 30 Sep 2005 02:26:43 +0000 (03:26 +0100)]
[PATCH] cpuset crapectomy
Switched cpuset_common_file_read() to simple_read_from_buffer(), killed
a bunch of useless (and not quite correct - e.g. min(size_t,ssize_t))
code.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Fri, 30 Sep 2005 02:21:45 +0000 (03:21 +0100)]
[PATCH] cassini annotations and fixes
- __user annotations
- NULL noise removal
- C99 initializers
- s/u32/pm_message_t/ in ->suspend()
- removal of bogus casts in iounmap() arguments
- if_mii() instead of open-coded variant
Remains to be done: ethtool conversion.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Fri, 30 Sep 2005 02:16:43 +0000 (03:16 +0100)]
[PATCH] useless linux/irq.h includes (arch/um)
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Fri, 30 Sep 2005 02:15:08 +0000 (03:15 +0100)]
[PATCH] missing ERR_PTR in 9fs
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Linus Torvalds [Fri, 30 Sep 2005 15:39:56 +0000 (08:39 -0700)]
Merge master.kernel.org:/home/rmk/linux-2.6-arm
Linus Torvalds [Fri, 30 Sep 2005 15:38:46 +0000 (08:38 -0700)]
Merge /pub/scm/linux/kernel/git/chrisw/lsm-2.6
Gen FUKATSU [Fri, 30 Sep 2005 15:09:17 +0000 (16:09 +0100)]
[ARM] 2940/1: Fix BTB entry flush in arch/arm/mm/cache-v6.S
Patch from Gen FUKATSU
Invalidate BTB entry instruction flushes two instruction
at a time. Therefore this instruction should be done four
times after invalidate instruction cache line.
Signed-off-by: Gen Fukatsu
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Catalin Marinas [Fri, 30 Sep 2005 15:07:05 +0000 (16:07 +0100)]
[ARM] 2942/1: Fix the warning in arch/arm/common/gic.c
Patch from Catalin Marinas
The warning is caused by the gic_set_cpu() function being defined but not
used if CONFIG_SMP is not defined.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Catalin Marinas [Fri, 30 Sep 2005 15:07:04 +0000 (16:07 +0100)]
[ARM] 2939/1: Fix compilation error in arch/arm/mm/flush.c
Patch from Catalin Marinas
When CONFIG_CPU_CACHE_VIPT is defined, the flush_pfn_alias() function is
implicitely declared and it later conflicts with its actual definition.
This patch moves the function definition to the beginning of the file.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Al Viro [Fri, 30 Sep 2005 02:49:17 +0000 (19:49 -0700)]
[CASSINI]: sparse annotations and fixes
- __user annotations
- NULL noise removal
- C99 initializers
- s/u32/pm_message_t/ in ->suspend()
- removal of bogus casts in iounmap() arguments
- if_mii() instead of open-coded variant
Remains to be done: ethtool conversion.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Horms [Fri, 30 Sep 2005 02:47:06 +0000 (19:47 -0700)]
[IPVS]: Add netdev and me as maintainer contacts
Signed-off-by: Horms <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Scott Talbert [Fri, 30 Sep 2005 00:31:30 +0000 (17:31 -0700)]
[ATM]: [lec] reset retry counter when new arp issued
From: Scott Talbert <scott.talbert@lmco.com>
Signed-off-by: Chas Williams <chas@cmf.nrl.navy.mil>
Signed-off-by: David S. Miller <davem@davemloft.net>
Scott Talbert [Fri, 30 Sep 2005 00:30:54 +0000 (17:30 -0700)]
[ATM]: [lec] attempt to support cisco failover
From: Scott Talbert <scott.talbert@lmco.com>
Signed-off-by: Chas Williams <chas@cmf.nrl.navy.mil>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexey Kuznetsov [Fri, 30 Sep 2005 00:17:15 +0000 (17:17 -0700)]
[TCP]: Don't over-clamp window in tcp_clamp_window()
From: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Handle better the case where the sender sends full sized
frames initially, then moves to a mode where it trickles
out small amounts of data at a time.
This known problem is even mentioned in the comments
above tcp_grow_window() in tcp_input.c, specifically:
...
* The scheme does not work when sender sends good segments opening
* window and then starts to feed us spagetti. But it should work
* in common situations. Otherwise, we have to rely on queue collapsing.
...
When the sender gives full sized frames, the "struct sk_buff" overhead
from each packet is small. So we'll advertize a larger window.
If the sender moves to a mode where small segments are sent, this
ratio becomes tilted to the other extreme and we start overrunning
the socket buffer space.
tcp_clamp_window() tries to address this, but it's clamping of
tp->window_clamp is a wee bit too aggressive for this particular case.
Fix confirmed by Ion Badulescu.
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 30 Sep 2005 00:07:20 +0000 (17:07 -0700)]
[TCP]: Revert
6b251858d377196b8cea20e65cae60f584a42735
But retain the comment fix.
Alexey Kuznetsov has explained the situation as follows:
--------------------
I think the fix is incorrect. Look, the RFC function init_cwnd(mss) is
not continuous: f.e. for mss=1095 it needs initial window 1095*4, but
for mss=1096 it is 1096*3. We do not know exactly what mss sender used
for calculations. If we advertised 1096 (and calculate initial window
3*1096), the sender could limit it to some value < 1096 and then it
will need window his_mss*4 > 3*1096 to send initial burst.
See?
So, the honest function for inital rcv_wnd derived from
tcp_init_cwnd() is:
init_rcv_wnd(mss)=
min { init_cwnd(mss1)*mss1 for mss1 <= mss }
It is something sort of:
if (mss < 1096)
return mss*4;
if (mss < 1096*2)
return 1096*4;
return mss*2;
(I just scrablled a graph of piece of paper, it is difficult to see or
to explain without this)
I selected it differently giving more window than it is strictly
required. Initial receive window must be large enough to allow sender
following to the rfc (or just setting initial cwnd to 2) to send
initial burst. But besides that it is arbitrary, so I decided to give
slack space of one segment.
Actually, the logic was:
If mss is low/normal (<=ethernet), set window to receive more than
initial burst allowed by rfc under the worst conditions
i.e. mss*4. This gives slack space of 1 segment for ethernet frames.
For msses slighlty more than ethernet frame, take 3. Try to give slack
space of 1 frame again.
If mss is huge, force 2*mss. No slack space.
Value 1460*3 is really confusing. Minimal one is 1096*2, but besides
that it is an arbitrary value. It was meant to be ~4096. 1460*3 is
just the magic number from RFC, 1460*3 = 1095*4 is the magic :-), so
that I guess hands typed this themselves.
--------------------
Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Jacobowitz [Thu, 29 Sep 2005 23:17:35 +0000 (00:17 +0100)]
[ARM] 2941/1: Fix running legacy binaries from a soft-float root filesystem with CONFIG_IWMMXT.
Patch from Daniel Jacobowitz
Thread flags are inherited on fork(). In order for a binary which has
the iWMMXt coprocessor enabled to run a binary which needs the FPA
emulation, we need to explicitly clear TIF_USING_IWMMXT if we are not
going to set it.
Signed-off-by: Daniel Jacobowitz <dan@codesourcery.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Benjamin Herrenschmidt [Thu, 29 Sep 2005 22:25:17 +0000 (08:25 +1000)]
[PATCH] Fix ppc64 smu driver locking
The SMU driver has a small mistake in the locking of the interrupt code,
if polled access and interrupt access race, interrupt may take a lock
and return without releasing it. This fixes it. With that patch, the
driver is rock solid with my experimental thermal control (which bangs
it pretty hard) racing with real time clock and cpufreq handling.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Kostik Belousov [Wed, 28 Sep 2005 15:21:28 +0000 (18:21 +0300)]
[PATCH] readv/writev syscalls are not checked by lsm
it seems that readv(2)/writev(2) syscalls do not call
file_permission callback. Looks like this is overlook.
I have filled the issue into redhat bugzilla as
https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=169433
and got the recommendation to post this on lsm mailing list.
The following trivial patch solves the problem.
Signed-off-by: Kostik Belousov <kostikbel@gmail.com>
Signed-off-by: Chris Wright <chrisw@osdl.org>
Mike Waychison [Thu, 29 Sep 2005 22:01:27 +0000 (00:01 +0200)]
[PATCH] x86_64: Fix mce_log
The attempt to fixup the lockless mce log buffer introduced an infinite loop
when trying to find a free entry.
And:
Using rcu_dereference() to load mcelog.next doesn't seem to be sufficient
enough to ensure that mcelog.next is loaded each time around the loop in
mce_log(). Instead, use an explicit rmb() to ensure that the compiler gets it
right.
AK: turned the smp_wmbs into true wmbs to make sure they are not
reordered by the compiler on UP.
Signed-off-by: Mike Waychison <mikew@google.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Andi Kleen [Thu, 29 Sep 2005 20:05:55 +0000 (22:05 +0200)]
[PATCH] Fix up TLB flush filter disabling
I checked with AMD and they requested to only disable it for family 15.
Also disable it for i386 too. And some style fixes.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Roland McGrath [Thu, 29 Sep 2005 21:54:42 +0000 (14:54 -0700)]
[PATCH] Fix task state testing properly in do_signal_stop()
Any tests using < TASK_STOPPED or the like are left over from the time
when the TASK_ZOMBIE and TASK_DEAD bits were in the same word, and it
served to check for "stopped or dead". I think this one in
do_signal_stop is the only such case. It has been buggy ever since
exit_state was separated, and isn't testing the exit_state value.
Signed-off-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Linus Torvalds [Thu, 29 Sep 2005 22:18:21 +0000 (15:18 -0700)]
Revert task flag re-ordering, add comments
Roland points out that the flags end up having non-obvious dependencies
elsewhere, so revert
aa55a08687059aa169d10a313c41f238c2070488 and add
some comments about why things are as they are.
We'll just have to fix up the broken comparisons. Roland has a patch.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Oleg Nesterov [Thu, 29 Sep 2005 15:58:53 +0000 (19:58 +0400)]
[PATCH] fix TASK_STOPPED vs TASK_NONINTERACTIVE interaction
do_signal_stop:
for_each_thread(t) {
if (t->state < TASK_STOPPED)
++sig->group_stop_count;
}
However, TASK_NONINTERACTIVE > TASK_STOPPED, so this loop will not
count TASK_INTERRUPTIBLE | TASK_NONINTERACTIVE threads.
See also wait_task_stopped(), which checks ->state > TASK_STOPPED.
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
[ We really probably should always use the appropriate bitmasks to test
task states, not do it like this. Using something like
#define TASK_RUNNABLE (TASK_RUNNING | TASK_INTERRUPTIBLE | \
TASK_UNINTERRUPTIBLE | TASK_NONINTERACTIVE)
and then doing "if (task->state & TASK_RUNNABLE)" or similar. But the
ordering of the task states is historical, and keeping the ordering
does make sense regardless. ]
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Linus Torvalds [Thu, 29 Sep 2005 16:00:04 +0000 (09:00 -0700)]
Merge master.kernel.org:/home/rmk/linux-2.6-serial
Deepak Saxena [Thu, 29 Sep 2005 01:07:01 +0000 (18:07 -0700)]
[PATCH] Fix thinko in previous ARM 2917/1 patch
Previous patch accidently add IXDP425 mach entry when IXDP465 is configured.
Signed-off-by: Deepak Saxena <dsaxena@plexity.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Linus Torvalds [Thu, 29 Sep 2005 15:56:47 +0000 (08:56 -0700)]
Merge /pub/scm/linux/kernel/git/davem/net-2.6
Linus Torvalds [Thu, 29 Sep 2005 15:55:43 +0000 (08:55 -0700)]
Merge /pub/scm/linux/kernel/git/davem/sparc-2.6
Deepak Saxena [Wed, 28 Sep 2005 23:42:54 +0000 (16:42 -0700)]
[PATCH] Fix ixp4xx MTD driver module build
Missing ';' breaks module build.
Signed-off-by: Deepak Saxena <dsaxena@plexity.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Ben Dooks [Wed, 28 Sep 2005 21:24:38 +0000 (05:24 +0800)]
[PATCH] s3c2410fb: Minor warning fix
The function s3c2410fb_activate_var does not return
a value, therefore it should be declared void.
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Antonino Daplas <adaplas@pol.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Antonino A. Daplas [Wed, 28 Sep 2005 21:19:51 +0000 (05:19 +0800)]
[PATCH] intelfb: Fix regression (blank display) from ioremap patch
- Workaround for the ioremap patch that produces a blank display on some
chipsets
- Make hwcursor = 0 the default. The hardware cursor does not work with all
hardware.
Signed-off-by: Antonino Daplas <adaplas@pol.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:42:27 +0000 (00:42 +0100)]
[PATCH] mv64x60_wdt __user annotations and cleanups
- use nonseekable_open() instead of messing with
if (*ppos != file->f_pos)
return -EISPIPE
in ->write() (->read is NULL).
- trivial __user annotations
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:37:34 +0000 (00:37 +0100)]
[PATCH] saa6588 __user annotations
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:36:10 +0000 (00:36 +0100)]
[PATCH] i810-i2c iomem annotations
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Antonino Daplas <adaplas@pol.net>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:34:30 +0000 (00:34 +0100)]
[PATCH] mv64x60 iomem annotations
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:31:14 +0000 (00:31 +0100)]
[PATCH] ppc32 ld.script fix for building on ppc64
In arch/ppc/boot/ld.script we need OUTPUT_ARCH(powerpc:common) for the
same reasons why we need it in vmlinux.lds.S; when we build on ppc64
box, we need to be explicit about the target.
See http://linus.bkbits.net:8080/linux-2.5/cset@1.1784.8.10 for the
corresponding fix in vmlinux.lds.S.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:17:49 +0000 (00:17 +0100)]
[PATCH] ppc64 get_user annotations
long is not uintptr_t, unsigned long is.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:16:02 +0000 (00:16 +0100)]
[PATCH] s390 signal annotations
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:12:13 +0000 (00:12 +0100)]
[PATCH] ia64 basic __user annotations
- document places where we pass kernel address to low-level primitive
that deals with kernel/user addresses
- uintptr_t is unsigned long, not long
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:10:01 +0000 (00:10 +0100)]
[PATCH] arm/rpc iomem annotations
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:09:02 +0000 (00:09 +0100)]
[PATCH] arm/versatile iomem annotations
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 23:07:29 +0000 (00:07 +0100)]
[PATCH] cyblafb: portability fixes, sanitized work with pointers
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Knut Petersen <Knut_Petersen@t-online.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Alexey Dobriyan [Wed, 28 Sep 2005 23:05:58 +0000 (00:05 +0100)]
[PATCH] n_r3964: drop bogus fmt casts
- print pointers with %p
- casting pointer structure field to int and printing it with %d...
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 21:32:57 +0000 (22:32 +0100)]
[PATCH] proc_mkdir() should be used to create procfs directories
A bunch of create_proc_dir_entry() calls creating directories had crept
in since the last sweep; converted to proc_mkdir().
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Al Viro [Wed, 28 Sep 2005 21:27:23 +0000 (22:27 +0100)]
[PATCH] uml makefiles sanitized
UML makefiles sanitized:
- number of generated headers reduced to 2 (from user-offsets.c and
kernel-offsets.c resp.). The rest is made constant and simply
includes those two.
- mk_... helpers are gone now that we don't need to generate these
headers
- arch/um/include2 removed since everything under arch/um/include/sysdep
is constant now and symlink can point straight to source tree.
- dependencies seriously simplified.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Russell King [Thu, 29 Sep 2005 10:15:51 +0000 (11:15 +0100)]
[ARM] Don't include mach-types.h unnecessarily
It's pointless to include mach-types.h if you're not going to use
anything from it. These references were removed as a result of:
grep -lr 'asm/mach-types\.h' . | xargs grep -L 'machine_is_\|MACH_TYPE_\|MACHINE_START\|machine_type'
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Russell King [Thu, 29 Sep 2005 10:12:52 +0000 (11:12 +0100)]
[ARM] Don't include asm/arch/hardware.h directly
Since asm/hardware.h's only reason for existing is to include
asm/arch/hardware.h, it's completely pointless to include both.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Russell King [Thu, 29 Sep 2005 08:49:25 +0000 (09:49 +0100)]
[ARM] Fix warning in arch/arm/mach-pxa/generic.c
Fix
arch/arm/mach-pxa/generic.c:242: warning: 'struct i2c_pxa_platform_data' declared inside parameter list
caused by missing asm/arch/i2c.h include.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Russell King [Thu, 29 Sep 2005 08:44:54 +0000 (09:44 +0100)]
[ARM] pxafb: Remove #if DEBUG, convert DPRINTK to pr_debug
Fix warning:
drivers/video/pxafb.h:119:5: warning: "DEBUG" is not defined
by removing the whole
#if DEBUG
#define DPRINTK(fmt, args...) printk...etc...
#else
#define DPRINTK(fmt, args...)
#endif
stuff - we have pr_debug() for this.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
David S. Miller [Thu, 29 Sep 2005 05:37:53 +0000 (22:37 -0700)]
[NET]: Fix reversed logic in eth_type_trans().
I got the second compare_eth_addr() test reversed, oops.
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 28 Sep 2005 23:48:40 +0000 (16:48 -0700)]
[SPARC64]: Fix bug in unaligned load endianness swapping
The in-memory value was being swapped, not the value we
loaded into the register.
Signed-off-by: David S. Miller <davem@davemloft.net>
Martin Whitaker [Wed, 28 Sep 2005 23:35:22 +0000 (16:35 -0700)]
[ATM]: fix bug in atm address list handling
From: Martin Whitaker <atm@martin-whitaker.co.uk>
Signed-off-by: Chas Williams <chas@cmf.nrl.navy.mil>
Chas Williams [Wed, 28 Sep 2005 23:35:01 +0000 (16:35 -0700)]
[ATM]: track and close listen sockets when sigd exits
Signed-off-by: Chas Williams <chas@cmf.nrl.navy.mil>
Roman Kagan [Wed, 28 Sep 2005 23:34:24 +0000 (16:34 -0700)]
[ATM]: net/atm/ioctl.c: autoload pppoatm and br2684
Signed-off-by: Roman Kagan <rkagan@mail.ru>
Signed-off-by: Chas Williams <chas@cmf.nrl.navy.mil>
David S. Miller [Wed, 28 Sep 2005 23:31:48 +0000 (16:31 -0700)]
[TCP]: Fix init_cwnd calculations in tcp_select_initial_window()
Match it up to what RFC2414 really specifies.
Noticed by Rick Jones.
Signed-off-by: David S. Miller <davem@davemloft.net>
Dominik Brodowski [Wed, 28 Sep 2005 17:29:59 +0000 (19:29 +0200)]
[PATCH] pcmcia: only start up nonstatic sockets if both mem and io are available
Only start up nonstatic sockets if both IO and MEM resources are available.
Thanks to Russell King and Matthew Wilcox for tracking this down.
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
Dominik Brodowski [Wed, 28 Sep 2005 17:28:37 +0000 (19:28 +0200)]
[PATCH] pcmcia: allow one port excludes
Allow for excluding only one port in /etc/pcmcia/config.otps
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
David Howells [Wed, 28 Sep 2005 16:03:15 +0000 (17:03 +0100)]
[PATCH] Keys: Add possessor permissions to keys [try #3]
The attached patch adds extra permission grants to keys for the possessor of a
key in addition to the owner, group and other permissions bits. This makes
SUID binaries easier to support without going as far as labelling keys and key
targets using the LSM facilities.
This patch adds a second "pointer type" to key structures (struct key_ref *)
that can have the bottom bit of the address set to indicate the possession of
a key. This is propagated through searches from the keyring to the discovered
key. It has been made a separate type so that the compiler can spot attempts
to dereference a potentially incorrect pointer.
The "possession" attribute can't be attached to a key structure directly as
it's not an intrinsic property of a key.
Pointers to keys have been replaced with struct key_ref *'s wherever
possession information needs to be passed through.
This does assume that the bottom bit of the pointer will always be zero on
return from kmem_cache_alloc().
The key reference type has been made into a typedef so that at least it can be
located in the sources, even though it's basically a pointer to an undefined
type. I've also renamed the accessor functions to be more useful, and all
reference variables should now end in "_ref".
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Paul Jackson [Wed, 28 Sep 2005 13:42:24 +0000 (06:42 -0700)]
[PATCH] cpuset read past eof memory leak fix
Don't leak a page of memory if user reads a cpuset file past eof.
Signed-off-by: KUROSAWA Takahiro <kurosawa@valinux.co.jp>
Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Linus Torvalds [Wed, 28 Sep 2005 14:47:55 +0000 (07:47 -0700)]
Merge branch 'for-linus' from /linux/kernel/git/roland/infiniband
Alok N Kataria [Wed, 28 Sep 2005 04:45:46 +0000 (21:45 -0700)]
[PATCH] kmalloc_node IRQ safety fix
In kmalloc_node we are checking if the allocation is for the same node when
interrupts are "on". This may lead to an allocation on another node than
intended.
This patch just shifts the check for the current node in __cache_alloc_node
when interrupts are disabled.
Signed-off-by: Alok N Kataria <alokk@calsoftinc.com>
Acked-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Benjamin Herrenschmidt [Wed, 28 Sep 2005 04:45:45 +0000 (21:45 -0700)]
[PATCH] ppc64: More hugepage fixes
My previous patch fixing invalidation of huge PTEs wasn't good enough, we
still had an issue if a PTE invalidation batch contained both small and
large pages. This patch fixes this by making sure the batch is flushed if
the page size fed to it changes.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Alasdair G Kergon [Wed, 28 Sep 2005 04:45:45 +0000 (21:45 -0700)]
[PATCH] device-mapper: Fix queue_if_no_path initialisation
When creating a multipath device, if the queue_if_no_path parameter is
specified it gets ignored.
While the queue_if_no_path variable is correctly set to 1, the
saved_queue_if_no_path gets set to 0. When the device is subsequently made
live (resumed), the saved value (0) always overwrites the live value (1) so
the option *always* gets turned off.
The fix adds a parameter to the queue_if_no_path() function to indicate
whether the previous value should be preserved or not - if not, as when the
device is being set up, the saved value is set to the new value (1).
Signed-Off-By: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
goggin, edward [Wed, 28 Sep 2005 04:45:44 +0000 (21:45 -0700)]
[PATCH] device-mapper: Trigger an event when a table is deleted
If anything is waiting on a device's table when the device is removed, we
must first wake it up so it will release its reference. Otherwise the
table's reference count will not drop to zero and the table will not get
removed.
Signed-Off-By: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Rafael J. Wysocki [Wed, 28 Sep 2005 04:45:43 +0000 (21:45 -0700)]
[PATCH] swsusp: avoid problems if there are too many pages to save
The following patch makes swsusp avoid problems during resume if there are
too many pages to save on suspend. It adds a constant that allows us to
verify if we are going to save too many pages and implements the check
(this is done as early as we can tell that the check will trigger, which is
in swsusp_alloc()).
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Benjamin Herrenschmidt [Wed, 28 Sep 2005 04:45:41 +0000 (21:45 -0700)]
[PATCH] orinoco: Fix flood of kernel log with stupid WE warnings
Latest wireless extensions moved a field from netdev -> wireless_handlers.
The WE core will now printk a warning on every call to get_wireless_stats()
on a driver that still uses the old field. This patch fixes orinoco.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Jeff Garzik <jgarzik@pobox.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Anton Blanchard [Wed, 28 Sep 2005 04:45:38 +0000 (21:45 -0700)]
[PATCH] ppc64: Add missing barrier() in kexec code
Mikey and I were testing kexec and hit a lockup. It turns out gcc 4.0
optimises the kexec_prepare_cpus loop so we avoid reloading paca.hw_cpu_id.
A gcc barrier() fixes the problem.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Paul Jackson [Wed, 28 Sep 2005 04:45:37 +0000 (21:45 -0700)]
[PATCH] cpuset maintainers
Specify the cpuset maintainers.
Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Simon Derr <simon.derr@bull.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
john stultz [Wed, 28 Sep 2005 04:45:36 +0000 (21:45 -0700)]
[PATCH] x86-64: Fix bad assumption that dualcore cpus have synced TSCs
This should resolve the issue seen in bugme bug #5105, where it is assumed
that dualcore x86_64 systems have synced TSCs. This is not the case, and
alternate timesources should be used instead.
For more details, see:
http://bugzilla.kernel.org/show_bug.cgi?id=5105
Andi's earlier concerns that the TSCs should be synced on dualcore systems
have been resolved by confirmation from AMD folks that they can be
unsynced.
Acked-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Corey Minyard [Wed, 28 Sep 2005 04:45:35 +0000 (21:45 -0700)]
[PATCH] Add IPMI poweroff control to sysfs
Put the IPMI poweroff_powercycle parameter into sysfs. This field is
dynamically settable and is valuable to have in sysfs.
Signed-off-by: Corey Minyard <minyard@acm.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Benjamin Herrenschmidt [Wed, 28 Sep 2005 04:45:35 +0000 (21:45 -0700)]
[PATCH] ppc: fix stupid thinko in oprofile fix
I did something stupid in my oprofile fix, here's the obvious fix:
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Rusty Russell [Wed, 28 Sep 2005 04:45:34 +0000 (21:45 -0700)]
[PATCH] Ignore trailing whitespace on kernel parameters correctly
Dave Jones says:
... if the modprobe.conf has trailing whitespace, modules fail to load
with the following helpful message..
snd_intel8x0: Unknown parameter `'
Previous version truncated last argument.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Dave Jones <davej@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Davide Libenzi [Wed, 28 Sep 2005 04:45:33 +0000 (21:45 -0700)]
[PATCH] epoll: handle timeout overflow
Handle the timeout upper boundary for epoll.
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Rafael J. Wysocki [Wed, 28 Sep 2005 04:45:32 +0000 (21:45 -0700)]
[PATCH] swsusp: prevent possible memory leak
Prevent swsusp from leaking some memory in case of an error in
read_pagedir(). It also prevents the BUG_ON() from triggering if there's
an error while reading swap.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Rafael J. Wysocki [Wed, 28 Sep 2005 04:45:31 +0000 (21:45 -0700)]
[PATCH] swsusp: remove wrong code from data_free
The following patch removes some wrong code from the data_free() function
in swsusp.
This function could only be called if there's an error while writing the
suspend image to swap, so it is not triggered easily. However, if
triggered, it would probably corrupt some memory.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Peter Osterlund [Wed, 28 Sep 2005 04:45:30 +0000 (21:45 -0700)]
[PATCH] pktcdvd: MAINTAINERS record
Add a MAINTAINERS entry for the pktcdvd driver.
Signed-off-by: Peter Osterlund <petero2@telia.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Jon Burgess [Wed, 28 Sep 2005 04:45:26 +0000 (21:45 -0700)]
[PATCH] dvb: fix NULL pointer dereference when loading the budget-av module
Ralph Metzler wrote:
> AFAIR, there is a bug in tda10021.c in tda10021_readreg() which
> references state->frontend.dvb->num
> This is fatal if the frontend is not at the probed address and thus
> not yet registered (no dvb entry set yet -> NULL pointer ...).
The attached patch should get rid of the oops.
Signed-off-by: Jon Burgess <jburgess@uklinux.net>
Cc: Johannes Stezenbach <js@linuxtv.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Latchesar Ionkov [Wed, 28 Sep 2005 04:45:24 +0000 (21:45 -0700)]
[PATCH] v9fs: fix races in fid allocation
Fid management cleanup. The patch attempts to fix the races in dentry's
fid management.
Dentries don't keep the opened fids anymore, they are moved to the file
structs. Ideally there should be no more than one fid with fidcreate equal
to zero in the dentry's list of fids.
v9fs_fid_create initializes the important fields (fid, fidcreated) before
v9fs_fid is added to the list. v9fs_fid_lookup returns only fids that are
not created by v9fs_create. v9fs_fid_get_created returns the fid created
by the same process by v9fs_create (if any) and removes it from dentry's
list
Signed-off-by: Latchesar Ionkov <lucho@ionkov.net>
Cc: Eric Van Hensbergen <ericvh@gmail.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Chris Sykes [Wed, 28 Sep 2005 04:45:23 +0000 (21:45 -0700)]
[PATCH] Fix ext3_new_inode() failure paths
Fix failure paths in ext3_new_inode() and clean up duplicated code: -
DQUOT_DROP() was not being called if ext3_init_security() failed.
Signed-off-by: Chris Sykes <chris@sigsegv.plus.com>
Cc: Stephen Smalley <sds@epoch.ncsc.mil>
Cc: Jan Kara <jack@ucw.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Chris Sykes [Wed, 28 Sep 2005 04:45:22 +0000 (21:45 -0700)]
[PATCH] Fix ext2_new_inode() failure paths
Fix failure paths in ext2_new_inode() and clean up duplicated code: -
DQUOT_DROP() was not being called if ext2_init_security() failed.
Signed-off-by: Chris Sykes <chris@sigsegv.plus.com>
Cc: Stephen Smalley <sds@epoch.ncsc.mil>
Cc: Jan Kara <jack@ucw.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Miklos Szeredi [Wed, 28 Sep 2005 04:45:21 +0000 (21:45 -0700)]
[PATCH] fuse: check reserved node ID values
This patch checks reserved node ID values returned by lookup and creation
operations. In case one of the reserved values is sent, return -EIO.
Signed-off-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Miklos Szeredi [Wed, 28 Sep 2005 04:45:20 +0000 (21:45 -0700)]
[PATCH] fuse: add required version info
Add information about required version of the userspace library/utilities
to Documentation/Changes. Also add pointer to this and to FUSE
documentation from Kconfig.
Thanks to Anton Altaparmakov for the reminder.
Signed-off-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Nick Piggin [Wed, 28 Sep 2005 04:45:18 +0000 (21:45 -0700)]
[PATCH] mm: move_pte to remap ZERO_PAGE
Move the ZERO_PAGE remapping complexity to the move_pte macro in
asm-generic, have it conditionally depend on
__HAVE_ARCH_MULTIPLE_ZERO_PAGE, which gets defined for MIPS.
For architectures without __HAVE_ARCH_MULTIPLE_ZERO_PAGE, move_pte becomes
a noop.
From: Hugh Dickins <hugh@veritas.com>
Fix nasty little bug we've missed in Nick's mremap move ZERO_PAGE patch.
The "pte" at that point may be a swap entry or a pte_file entry: we must
check pte_present before perhaps corrupting such an entry.
Patch below against 2.6.14-rc2-mm1, but the same bug is in 2.6.14-rc2's
mm/mremap.c, and more dangerous there since it's affecting all arches: I
think the safest course is to send Nick's patch and Yoichi's build fix and
this fix (build tested) on to Linus - so only MIPS can be affected.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
David S. Miller [Wed, 28 Sep 2005 05:50:06 +0000 (22:50 -0700)]
[SPARC64]: Add missing IDs for newer cpus.
Also, the us3_cpufreq driver can work on Ultra-IV and IV+.
They use the SAFARI bus register to control the clock divider
just like Ultra-III and III+ do.
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 28 Sep 2005 05:37:08 +0000 (22:37 -0700)]
[SPARC64]: Add defines for 32MB/256MB PTE page size on Ultra-IV+.
Signed-off-by: David S. Miller <davem@davemloft.net>
Oliver Dawid [Tue, 27 Sep 2005 23:11:29 +0000 (16:11 -0700)]
[APPLETALK]: Fix broadcast bug.
From: Oliver Dawid <oliver@helios.de>
we found a bug in net/appletalk/ddp.c concerning broadcast packets. In
kernel 2.4 it was working fine. The bug first occured 4 years ago when
switching to new SNAP layer handling. This bug can be splitted up into a
sending(1) and reception(2) problem:
Sending(1)
In kernel 2.4 broadcast packets were sent to a matching ethernet device
and atalk_rcv() was called to receive it as "loopback" (so loopback
packets were shortcutted and handled in DDP layer).
When switching to the new SNAP structure, this shortcut was removed and
the loopback packet was send to SNAP layer. The author forgot to replace
the remote device pointer by the loopback device pointer before sending
the packet to SNAP layer (by calling ddp_dl->request() ) therfor the
packet was not sent back by underlying layers to ddp's atalk_rcv().
Reception(2)
In atalk_rcv() a packet received by this loopback mechanism contains now
the (rigth) loopback device pointer (in Kernel 2.4 it was the (wrong)
remote ethernet device pointer) and therefor no matching socket will be
found to deliver this packet to. Because a broadcast packet should be
send to the first matching socket (as it is done in many other protocols
(?)), we removed the network comparison in broadcast case.
Below you will find a patch to correct this bug. Its diffed to kernel
2.6.14-rc1
Signed-off-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 27 Sep 2005 23:03:05 +0000 (16:03 -0700)]
[NET]: Slightly optimize ethernet address comparison.
We know the thing is at least 2-byte aligned, so take
advantage of that instead of invoking memcmp() which
results in truly horrifically inefficient code because
it can't assume anything about alignment.
Signed-off-by: David S. Miller <davem@davemloft.net>
Ben Dooks [Tue, 27 Sep 2005 22:59:43 +0000 (15:59 -0700)]
[NET]: Fix GCC4 compile error: sysctl in linux/if_ether.h
The following is generated when compiling a
recent (2.6.14-rc2-git5) kernel configured for
ARM, with GCC4.
CC init/main.o
In file included from include/linux/netdevice.h:29,
from include/net/sock.h:48,
from init/main.c:50:
include/linux/if_ether.h:114: error: array type has incomplete element type
It seems that if CONFIG_SYSCTL is not set, then
the compiler will throw an error due to the definition
of the ether_table[] array
Attached is a solution to the problem
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexey Dobriyan [Tue, 27 Sep 2005 22:45:15 +0000 (15:45 -0700)]
[ROSE]: fix typo (regeistration)
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexey Dobriyan [Tue, 27 Sep 2005 22:44:36 +0000 (15:44 -0700)]
[ROSE]: check rose_ndevs earlier
* Don't bother with proto registering if rose_ndevs is bad.
* Make escape structure more coherent.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexey Dobriyan [Tue, 27 Sep 2005 22:43:46 +0000 (15:43 -0700)]
[ROSE]: return sane -E* from rose_proto_init()
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexey Dobriyan [Tue, 27 Sep 2005 22:42:58 +0000 (15:42 -0700)]
[ROSE]: do proto_unregister() on exit paths
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 27 Sep 2005 22:24:13 +0000 (15:24 -0700)]
[NET]: Add Sun Cassini driver.
Written by Adrian Sun (asun@darksunrising.com).
Ported to 2.6.x by Tom 'spot' Callaway <tcallawa@redhat.com>.
Further cleaned up and integrated by David S. Miller
Signed-off-by: David S. Miller <davem@davemloft.net>
Frank Filz [Tue, 27 Sep 2005 22:23:38 +0000 (15:23 -0700)]
[NET]: Fix module reference counts for loadable protocol modules
I have been experimenting with loadable protocol modules, and ran into
several issues with module reference counting.
The first issue was that __module_get failed at the BUG_ON check at
the top of the routine (checking that my module reference count was
not zero) when I created the first socket. When sk_alloc() is called,
my module reference count was still 0. When I looked at why sctp
didn't have this problem, I discovered that sctp creates a control
socket during module init (when the module ref count is not 0), which
keeps the reference count non-zero. This section has been updated to
address the point Stephen raised about checking the return value of
try_module_get().
The next problem arose when my socket init routine returned an error.
This resulted in my module reference count being decremented below 0.
My socket ops->release routine was also being called. The issue here
is that sock_release() calls the ops->release routine and decrements
the ref count if sock->ops is not NULL. Since the socket probably
didn't get correctly initialized, this should not be done, so we will
set sock->ops to NULL because we will not call try_module_get().
While searching for another bug, I also noticed that sys_accept() has
a possibility of doing a module_put() when it did not do an
__module_get so I re-ordered the call to security_socket_accept().
Signed-off-by: Frank Filz <ffilzlnx@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Tue, 27 Sep 2005 22:23:16 +0000 (15:23 -0700)]
[NET]: Reorder some hot fields of struct net_device
Place them on separate cache lines in SMP to lower memory bouncing
between multiple CPU accessing the device.
- One part is mostly used on receive path (including
eth_type_trans()) (poll_list, poll, quota, weight, last_rx,
dev_addr, broadcast)
- One part is mostly used on queue transmit path (qdisc)
(queue_lock, qdisc, qdisc_sleeping, qdisc_list, tx_queue_len)
- One part is mostly used on xmit path (device)
(xmit_lock, xmit_lock_owner, priv, hard_start_xmit, trans_start)
'features' is placed outside of these hot points, in a location that
may be shared by all cpus (because mostly read)
name_hlist is moved close to name[IFNAMSIZ] to speedup __dev_get_by_name()
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Tue, 27 Sep 2005 22:22:58 +0000 (15:22 -0700)]
[NET]: Prefetch dev->qdisc_lock in dev_queue_xmit()
We know the lock is going to be taken.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>