this_cpu: Implement X86 optimized this_cpu operations
Basically the existing percpu ops can be used for this_cpu variants that allow
operations also on dynamically allocated percpu data. However, we do not pass a
reference to a percpu variable in. Instead a dynamically or statically
allocated percpu variable is provided.
Preempt, the non preempt and the irqsafe operations generate the same code.
It will always be possible to have the requires per cpu atomicness in a single
RMW instruction with segment override on x86.
64 bit this_cpu operations are not supported on 32 bit.
Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Tejun Heo <tj@kernel.org>
this_cpu: Introduce this_cpu_ptr() and generic this_cpu_* operations
This patch introduces two things: First this_cpu_ptr and then per cpu
atomic operations.
this_cpu_ptr
------------
A common operation when dealing with cpu data is to get the instance of the
cpu data associated with the currently executing processor. This can be
optimized by
The problem with per_cpu_ptr(x, smp_processor_id) is that it requires
an array lookup to find the offset for the cpu. Processors typically
have the offset for the current cpu area in some kind of (arch dependent)
efficiently accessible register or memory location.
We can use that instead of doing the array lookup to speed up the
determination of the address of the percpu variable. This is particularly
significant because these lookups occur in performance critical paths
of the core kernel. this_cpu_ptr() can avoid memory accesses and
this_cpu_ptr comes in two flavors. The preemption context matters since we
are referring the the currently executing processor. In many cases we must
insure that the processor does not change while a code segment is executed.
__this_cpu_ptr -> Do not check for preemption context
this_cpu_ptr -> Check preemption context
The parameter to these operations is a per cpu pointer. This can be the
address of a statically defined per cpu variable (&per_cpu_var(xxx)) or
the address of a per cpu variable allocated with the per cpu allocator.
per cpu atomic operations: this_cpu_*(var, val)
-----------------------------------------------
this_cpu_* operations (like this_cpu_add(struct->y, value) operate on
abitrary scalars that are members of structures allocated with the new
per cpu allocator. They can also operate on static per_cpu variables
if they are passed to per_cpu_var() (See patch to use this_cpu_*
operations for vm statistics).
These operations are guaranteed to be atomic vs preemption when modifying
the scalar. The calculation of the per cpu offset is also guaranteed to
be atomic at the same time. This means that a this_cpu_* operation can be
safely used to modify a per cpu variable in a context where interrupts are
enabled and preemption is allowed. Many architectures can perform such
a per cpu atomic operation with a single instruction.
Note that the atomicity here is different from regular atomic operations.
Atomicity is only guaranteed for data accessed from the currently executing
processor. Modifications from other processors are still possible. There
must be other guarantees that the per cpu data is not modified from another
processor when using these instruction. The per cpu atomicity is created
by the fact that the processor either executes and instruction or not.
Embedded in the instruction is the relocation of the per cpu address to
the are reserved for the current processor and the RMW action. Therefore
interrupts or preemption cannot occur in the mids of this processing.
Generic fallback functions are used if an arch does not define optimized
this_cpu operations. The functions come also come in the two flavors used
for this_cpu_ptr().
The firstparameter is a scalar that is a member of a structure allocated
through allocpercpu or a per cpu variable (use per_cpu_var(xxx)). The
operations are similar to what percpu_add() and friends do.
Arch code can override the generic functions and provide optimized atomic
per cpu operations. These atomic operations must provide both the relocation
(x86 does it through a segment override) and the operation on the data in a
single instruction. Otherwise preempt needs to be disabled and there is no
gain from providing arch implementations.
A third variant is provided prefixed by irqsafe_. These variants are safe
against hardware interrupts on the *same* processor (all per cpu atomic
primitives are *always* *only* providing safety for code running on the
*same* processor!). The increment needs to be implemented by the hardware
in such a way that it is a single RMW instruction that is either processed
before or after an interrupt.
cc: David Howells <dhowells@redhat.com>
cc: Ingo Molnar <mingo@elte.hu>
cc: Rusty Russell <rusty@rustcorp.com.au>
cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Tejun Heo <tj@kernel.org>
Tejun Heo [Fri, 2 Oct 2009 04:28:56 +0000 (13:28 +0900)]
ia64: convert to dynamic percpu allocator
Unlike other archs, ia64 reserves space for percpu areas during early
memory initialization. These areas occupy a contiguous region indexed
by cpu number on contiguous memory model or are grouped by node on
discontiguous memory model.
As allocation and initialization are done by the arch code, all that
setup_per_cpu_areas() needs to do is communicating the determined
layout to the percpu allocator. This patch implements
setup_per_cpu_areas() for both contig and discontig memory models and
drops HAVE_LEGACY_PER_CPU_AREA.
Please note that for contig model, the allocation itself is modified
only to allocate for possible cpus instead of NR_CPUS. As dynamic
percpu allocator can handle non-direct mapping, there's no reason to
allocate memory for cpus which aren't possible.
Tejun Heo [Fri, 2 Oct 2009 04:28:56 +0000 (13:28 +0900)]
ia64: allocate percpu area for cpu0 like percpu areas for other cpus
cpu0 used special percpu area reserved by the linker, __cpu0_per_cpu,
which is set up early in boot by head.S. However, this doesn't
guarantee that the area will be on the same node as cpu0 and the
percpu area for cpu0 ends up very far away from percpu areas for other
cpus which cause problems for congruent percpu allocator.
This patch makes percpu area initialization allocate percpu area for
cpu0 like any other cpus and copy it from __cpu0_per_cpu which now
resides in the __init area. This means that for cpu0, percpu area is
first setup at __cpu0_per_cpu early by head.S and then moved to an
area in the linear mapping during memory initialization and it's not
allowed to take a pointer to percpu variables between head.S and
memory initialization.
Tejun Heo [Fri, 2 Oct 2009 04:28:56 +0000 (13:28 +0900)]
ia64: initialize cpu maps early
All information necessary to initialize cpu possible and present maps
are available once early_acpi_boot_init() is complete. Reorganize
setup_arch() and acpi init functions such that,
* CPU information is printed after LAPIC entries are parsed in
early_acpi_boot_init().
* smp_build_cpu_map() is called by setup_arch() instead of acpi
functions.
* smp_build_cpu_map() is called once all CPU related information is
available before memory is initialized.
This is primarily to allow find_memory() to use cpu maps but is also a
general cleanup. Please note that with this change, the somewhat
ad-hoc early_cpu_possible_map defined and used for NUMA configurations
is probably unnecessary. Something to clean up another day.
Tejun Heo [Fri, 2 Oct 2009 04:28:55 +0000 (13:28 +0900)]
ia64: don't alias VMALLOC_END to vmalloc_end
If CONFIG_VIRTUAL_MEM_MAP is enabled, ia64 defines macro VMALLOC_END
as unsigned long variable vmalloc_end which is adjusted to prepare
room for vmemmap. This becomes probnlematic if a local variables
vmalloc_end is defined in some function (not very unlikely) and
VMALLOC_END is used in the function - the function thinks its
referencing the global VMALLOC_END value but would be referencing its
own local vmalloc_end variable.
There's no reason VMALLOC_END should be a macro. Just define it as an
unsigned long variable if CONFIG_VIRTUAL_MEM_MAP is set to avoid nasty
surprises.
Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Tony Luck <tony.luck@intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: linux-ia64 <linux-ia64@vger.kernel.org> Cc: Christoph Lameter <cl@linux-foundation.org>
Linus Torvalds [Fri, 2 Oct 2009 03:23:15 +0000 (20:23 -0700)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: fix data space leak fix
Btrfs: remove duplicates of filemap_ helpers
Btrfs: take i_mutex before generic_write_checks
Btrfs: fix arguments to btrfs_wait_on_page_writeback_range
Btrfs: fix deadlock with free space handling and user transactions
Btrfs: fix error cases for ioctl transactions
Btrfs: Use CONFIG_BTRFS_POSIX_ACL to enable ACL code
Btrfs: introduce missing kfree
Btrfs: Fix setting umask when POSIX ACLs are not enabled
Btrfs: proper -ENOSPC handling
Otherwise the config function uses random data from the stack. This
didn't stick out because config is called once more in the chipselect
function with correct parameters.
Andy Spencer [Thu, 1 Oct 2009 22:44:27 +0000 (15:44 -0700)]
sscanf(): fix %*s%n
When using %*s, sscanf should honor conversion specifiers immediately
following the %*s. For example, the following code should find the
position of the end of the string "hello".
Ideally, sscanf would advance the fmt and str pointers the same as it
would without the *, but the code for that is rather complicated and is
not included in the patch.
Signed-off-by: Andy Spencer <andy753421@gmail.com> Acked-by: WANG Cong <xiyou.wangcong@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Chuck Ebbert [Thu, 1 Oct 2009 22:44:26 +0000 (15:44 -0700)]
serial: add parameter to force skipping the test for the TXEN bug
Allow users to force skipping the TXEN test at init time. Applies
to all serial ports. Intended for debugging only.
There is a blacklist for devices where we need to skip the test but the
list is not complete. This lets users force skipping the test so we can
determine if they need to be added to the list.
Some HP machines with weird serial consoles have this problem and there
may be more.
Signed-off-by: Chuck Ebbert <cebbert@redhat.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Roel Kluin [Thu, 1 Oct 2009 22:44:24 +0000 (15:44 -0700)]
cyclades: fix read buffer overflow
irq is declared with size NR_CARDS (4), but the loop containing this
segment runs up until NR_ISA_ADDRS (16), possibly reading from irq[i] (and
trying to use the result)
Ben Dooks [Thu, 1 Oct 2009 22:44:21 +0000 (15:44 -0700)]
s3cmci: add better support for no card detect or write protect available
Add better support for omitting either the card detect or the write
protect GPIOs if the board does not support it. Add the fields
no_wprotect and no_detect to the platform data which when set indicate the
absence of the respective GPIOs.
Note, this also fixes a minor bug where it tries to free IRQ0 if there is
no detect gpio available.
Signed-off-by: Ben Dooks <ben@simtec.co.uk> Cc: <linux-mmc@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ben Dooks [Thu, 1 Oct 2009 22:44:20 +0000 (15:44 -0700)]
s3cmci: make SDIO IRQ hardware IRQ support build-time configurable
We have found a couple of boards where the SDIO IRQ hardware support has
failed to work properly, and thus we should make it configurable whether
or not to be included in the driver.
Signed-off-by: Ben Dooks <ben@simtec.co.uk> Cc: <linux-mmc@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ben Dooks [Thu, 1 Oct 2009 22:44:19 +0000 (15:44 -0700)]
s3cmci: DMA fixes
Fixes for the DMA transfer mode of the driver to try and improve the state
of the code:
- Ensure that dma_complete is set during the end of the command phase
so that transfers do not stall awaiting the completion
- Update the DMA debugging to provide a bit more useful information
such as how many DMA descriptors where not processed and print the
DMA addresses in hexadecimal.
- Fix the DMA channel request code to actually request DMA for the
S3CMCI block instead of whatever '0' signified.
- Add fallback to PIO if we cannot get the DMA channel, as many of the
devices with this block only have a limited number of DMA channels.
- Only try and claim and free the DMA channel if we are trying to use it.
This improves the driver DMA code to the point where it can now identify a
card and read the partition table. However the DMA can still stall when
trying to move data between the host and memory.
Signed-off-by: Ben Dooks <ben@simtec.co.uk> Cc: <linux-mmc@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ben Dooks [Thu, 1 Oct 2009 22:44:18 +0000 (15:44 -0700)]
s3cmci: Kconfig selection for PIO/DMA/Both
Add a selection for the data transfer mode of the s3cmci driver, allowing
for either a configuration or rumtime selection of the use of the DMA or
PIO transfer code.
The PIO only mode is 476 bytes smaller than the driver with both methods
compiled in.
Signed-off-by: Ben Dooks <ben@simtec.co.uk> Cc: <linux-mmc@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ben Dooks [Thu, 1 Oct 2009 22:44:18 +0000 (15:44 -0700)]
s3cmci: add SDIO IRQ support
The controller supports SDIO IRQ detection so add support for hardware
assisted SDIO interrupt detection for the SDIO core. This improves the
response time for SDIO interrupts and thus the transfer rate from devices
such as the Marvel 8686.
As a note, it does seem that the controller will miss an IRQ than is held
asserted, so there are some manual checks to see if the SDIO interrupt is
active after a transfer.
Major testing on the S3C2440.
Signed-off-by: Ben Dooks <ben@simtec.co.uk> Cc: <linux-mmc@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ben Dooks [Thu, 1 Oct 2009 22:44:17 +0000 (15:44 -0700)]
s3cmci: add debugfs support for examining driver and hardware state
Export driver state and hardware register state via debugfs entries
created under a directory formed from dev_name() on the probed device when
CONFIG_DEBUG_FS is set.
Signed-off-by: Ben Dooks <ben@simtec.co.uk> Cc: <linux-mmc@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ben Dooks [Thu, 1 Oct 2009 22:44:14 +0000 (15:44 -0700)]
s3cmci: update probe to use new platform id list
Use the platform id list to match the three different versions of the
hardware block that this driver supports.
This will change the prefix of the console messages produced by this
driver to be prefixed by s3c-mci instead of the hardware block name, such
as s3c2440-mci.
Signed-off-by: Ben Dooks <ben@simtec.co.uk> Cc: <linux-mmc@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
memcg: some modification to softlimit under hierarchical memory reclaim.
This patch clean up/fixes for memcg's uncharge soft limit path.
Problems:
Now, res_counter_charge()/uncharge() handles softlimit information at
charge/uncharge and softlimit-check is done when event counter per memcg
goes over limit. Now, event counter per memcg is updated only when
memory usage is over soft limit. Here, considering hierarchical memcg
management, ancesotors should be taken care of.
Now, ancerstors(hierarchy) are handled in charge() but not in uncharge().
This is not good.
Prolems:
1. memcg's event counter incremented only when softlimit hits. That's bad.
It makes event counter hard to be reused for other purpose.
2. At uncharge, only the lowest level rescounter is handled. This is bug.
Because ancesotor's event counter is not incremented, children should
take care of them.
3. res_counter_uncharge()'s 3rd argument is NULL in most case.
ops under res_counter->lock should be small. No "if" sentense is better.
Fixes:
* Removed soft_limit_xx poitner and checks in charge and uncharge.
Do-check-only-when-necessary scheme works enough well without them.
* make event-counter of memcg incremented at every charge/uncharge.
(per-cpu area will be accessed soon anyway)
* All ancestors are checked at soft-limit-check. This is necessary because
ancesotor's event counter may never be modified. Then, they should be
checked at the same time.
Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__mem_cgroup_largest_soft_limit_node() returns a mem_cgroup_per_zone "mz"
with incremnted mz->mem->css's refcnt. Then, the caller of this function
has to call css_put(mz->mem->css).
But, mz can be !NULL even if "not found" i.e. without css_get(). By
this, css->refcnt will go down to minus.
This may cause various things...one of results will be
initite-loop in css_tryget() as this.
INFO: RCU detected CPU 0 stall (t=10000 jiffies)
sending NMI to all CPUs:
NMI backtrace for cpu 0
CPU 0:
<snip>
Albert Herranz [Thu, 1 Oct 2009 22:44:05 +0000 (15:44 -0700)]
sdio: pass whitelisted cis funce tuples to sdio drivers
Some manufacturers provide vendor information in non-vendor specific CIS
tuples. For example, Broadcom uses an Extended Function tuple to provide
the MAC address on some of their network cards, as in the case of the
Nintendo Wii WLAN daughter card.
This patch allows passing whitelisted FUNCE tuples unknown to the SDIO
core to a matching SDIO driver instead of rejecting them and failing.
Signed-off-by: Albert Herranz <albert_herranz@yahoo.es> Cc: <linux-mmc@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Samuel Thibault [Thu, 1 Oct 2009 22:44:02 +0000 (15:44 -0700)]
x86: fix csum_ipv6_magic asm memory clobber
Just like ip_fast_csum, the assembly snippet in csum_ipv6_magic needs a
memory clobber, as it is only passed the address of the buffer, not a
memory reference to the buffer itself.
This caused failures in Hurd's pfinetv4 when we tried to compile it with
gcc-4.3 (bogus checksums).
Signed-off-by: Samuel Thibault <samuel.thibault@ens-lyon.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Acked-by: "David S. Miller" <davem@davemloft.net> Cc: Andi Kleen <andi@firstfloor.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mark Salter [Thu, 1 Oct 2009 22:44:01 +0000 (15:44 -0700)]
mn10300: fix kernel build failures when using gcc-4.x
Fix some build failures when using gcc-4.x for MN10300.
Firstly, __get_user() fails to build because the pointer points to a const and
__gu_val ends up being read-only:
In file included from include/linux/mempolicy.h:62,
from init/main.c:50:
include/linux/pagemap.h: In function 'fault_in_pages_readable':
include/linux/pagemap.h:394: error: read-only variable '__gu_val' used as 'asm' output
include/linux/pagemap.h:394: error: read-only variable '__gu_val' used as 'asm' output
include/linux/pagemap.h:394: error: read-only variable '__gu_val' used as 'asm' output
include/linux/pagemap.h:400: error: read-only variable '__gu_val' used as 'asm' output
include/linux/pagemap.h:400: error: read-only variable '__gu_val' used as 'asm' output
include/linux/pagemap.h:400: error: read-only variable '__gu_val' used as 'asm' output
make[1]: *** [init/main.o] Error 1
Secondly, gcc-4 doesn't allow casts of lvalues:
UPD include/linux/compile.h
arch/mn10300/kernel/rtc.c: In function 'calibrate_clock':
arch/mn10300/kernel/rtc.c:170: error: lvalue required as left operand of assignment
arch/mn10300/kernel/rtc.c:172: error: lvalue required as left operand of assignment
make[1]: *** [arch/mn10300/kernel/rtc.o] Error 1
These are seen with gcc 4.2.1.
Signed-off-by: Mark Salter <msalter@redhat.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Joe Perches [Thu, 1 Oct 2009 22:43:59 +0000 (15:43 -0700)]
MAINTAINERS: ARM/Palm file patterns
Signed-off-by: Joe Perches <joe@perches.com> Acked-by: Marek Vasut <marek.vasut@gmail.com> Acked-by: Tomas Cech <sleep_walker@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In file included from include/linux/irq.h:12,
from include/asm-generic/hardirq.h:6,
from /usr/src/devel/arch/m68k/include/asm/hardirq_mm.h:6,
from /usr/src/devel/arch/m68k/include/asm/hardirq.h:4,
from include/linux/hardirq.h:10,
from /usr/src/devel/arch/m68k/include/asm/system_mm.h:69,
from /usr/src/devel/arch/m68k/include/asm/system.h:4,
from include/linux/list.h:7,
from include/linux/preempt.h:11,
from include/linux/spinlock.h:50,
from include/linux/seqlock.h:29,
from include/linux/time.h:8,
from include/linux/timex.h:56,
from include/linux/sched.h:56,
from arch/m68k/kernel/asm-offsets.c:14:
include/linux/smp.h:17: error: field 'list' has incomplete type
Cc: Christoph Hellwig <hch@lst.de> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mike Frysinger [Thu, 1 Oct 2009 22:43:56 +0000 (15:43 -0700)]
asm-generic/gpio.h: pull in linux/kernel.h for might_sleep()
The asm-generic/gpio.h header uses the might_sleep() macro but doesn't
include the header for it, so any source code that might include
linux/gpio.h before linux/kernel.h can easily lead to a build failure.
Signed-off-by: Mike Frysinger <vapier@gentoo.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Paul Mundt [Thu, 1 Oct 2009 22:43:54 +0000 (15:43 -0700)]
module: fix up CONFIG_KALLSYMS=n build.
Starting from commit 4a4962263f07d14660849ec134ee42b63e95ea9a "reduce
symbol table for loaded modules (v2)", the kernel/module.c build is broken
with CONFIG_KALLSYMS disabled.
CC kernel/module.o
kernel/module.c:1995: warning: type defaults to 'int' in declaration of 'Elf_Hdr'
kernel/module.c:1995: error: expected ';', ',' or ')' before '*' token
kernel/module.c: In function 'load_module':
kernel/module.c:2203: error: 'strmap' undeclared (first use in this function)
kernel/module.c:2203: error: (Each undeclared identifier is reported only once
kernel/module.c:2203: error: for each function it appears in.)
kernel/module.c:2239: error: 'symoffs' undeclared (first use in this function)
kernel/module.c:2239: error: implicit declaration of function 'layout_symtab'
kernel/module.c:2240: error: 'stroffs' undeclared (first use in this function)
make[1]: *** [kernel/module.o] Error 1
make: *** [kernel/module.o] Error 2
There are three different issues:
- layout_symtab() takes a const Elf_Ehdr
- layout_symtab() needs to return a value
- symoffs/stroffs/strmap are referenced by the load_module() code
despite being ifdefed out, which seems unnecessary given the noop
behaviour of layout_symtab()/add_kallsyms() in the case of
CONFIG_KALLSYMS=n.
Signed-off-by: Paul Mundt <lethal@linux-sh.org> Acked-by: Jan Beulich <jbeulich@novell.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Josef Bacik [Thu, 1 Oct 2009 21:10:23 +0000 (17:10 -0400)]
Btrfs: fix data space leak fix
There is a problem where page_mkwrite can be called on a dirtied page that
already has a delalloc range associated with it. The fix is to clear any
delalloc bits for the range we are dirtying so the space accounting gets
handled properly. This is the same thing we do in the normal write case, so we
are consistent across the board. With this patch we no longer leak reserved
space.
Signed-off-by: Josef Bacik <jbacik@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
Use filemap_fdatawrite_range and filemap_fdatawait_range instead of
local copies of the functions. For filemap_fdatawait_range that
also means replacing the awkward old wait_on_page_writeback_range
calling convention with the regular filemap byte offsets.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Chris Mason <chris.mason@oracle.com>
Chris Mason [Thu, 1 Oct 2009 16:29:10 +0000 (12:29 -0400)]
Btrfs: take i_mutex before generic_write_checks
btrfs_file_write was incorrectly calling generic_write_checks without
taking i_mutex. This lead to problems with racing around i_size when
doing O_APPEND writes.
The fix here is to move i_mutex higher.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Btrfs: fix arguments to btrfs_wait_on_page_writeback_range
wait_on_page_writeback_range/btrfs_wait_on_page_writeback_range takes
a pagecache offset, not a byte offset into the file. Shift the arguments
around to wait for the correct range
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Chris Mason <chris.mason@oracle.com>
In ax25_make_new, if kmemdup of digipeat returns an error, there would
be an oops in sk_free while calling sk_destruct, because sk_protinfo
is NULL at the moment; move sk->sk_destruct initialization after this.
BTW of reported-by: Bernard Pidoux F6BVP <f6bvp@free.fr>
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
We lost rx timestamping of packets received on accelerated vlans.
Effect is that tcpdump on real dev can show strange timings, since it gets rx timestamps
too late (ie at skb dequeueing time, not at skb queueing time)
When requesting all prl entries (kprl.addr == INADDR_ANY) and there are
more prl entries than there is space passed from userspace, the existing
code would always copy cmax+1 entries, which is more than can be handled.
This patch makes the kernel copy only exactly cmax entries.
Signed-off-by: Sascha Hlusiak <contact@saschahlusiak.de> Acked-By: Fred L. Templin <Fred.L.Templin@boeing.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Thu, 24 Sep 2009 10:49:24 +0000 (10:49 +0000)]
net: Fix sock_wfree() race
Commit 2b85a34e911bf483c27cfdd124aeb1605145dc80
(net: No more expensive sock_hold()/sock_put() on each tx)
opens a window in sock_wfree() where another cpu
might free the socket we are working on.
A fix is to call sk->sk_write_space(sk) while still
holding a reference on sk.
Reported-by: Jike Song <albcamus@gmail.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 30 Sep 2009 23:12:20 +0000 (16:12 -0700)]
net: Make setsockopt() optlen be unsigned.
This provides safety against negative optlen at the type
level instead of depending upon (sometimes non-trivial)
checks against this sprinkled all over the the place, in
each and every implementation.
Based upon work done by Arjan van de Ven and feedback
from Linus Torvalds.
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched_clock: Fix atomicity/continuity bug by using cmpxchg64()
x86: Provide an alternative() based cmpxchg64()
Eric Dumazet [Wed, 30 Sep 2009 18:36:19 +0000 (20:36 +0200)]
sched_clock: Fix atomicity/continuity bug by using cmpxchg64()
Commit def0a9b2573 (sched_clock: Make it NMI safe) assumed
cmpxchg() of 64bit values was available on X86_32.
That is not so - and causes some subtle scheduler misbehavior due
to incorrect timestamps off to up by ~4 seconds.
Two symptoms are known right now:
- interactivity problems seen by Arjan: up to 600 msecs
latencies instead of the expected 20-40 msecs. These
latencies are very visible on the desktop.
- incorrect CPU stats: occasionally too high percentages in 'top',
and crazy CPU usage stats.
Reported-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: John Stultz <johnstul@us.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20090930170754.0886ff2e@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Arjan van de Ven [Wed, 30 Sep 2009 15:07:54 +0000 (17:07 +0200)]
x86: Provide an alternative() based cmpxchg64()
cmpxchg64() today generates, to quote Linus, "barf bag" code.
cmpxchg64() is about to get used in the scheduler to fix a bug there,
but it's a prerequisite that cmpxchg64() first be made non-sucking.
This patch turns cmpxchg64() into an efficient implementation that
uses the alternative() mechanism to just use the raw instruction on
all modern systems.
Note: the fallback is NOT smp safe, just like the current fallback
is not SMP safe. (Interested parties with i486 based SMP systems
are welcome to submit fix patches for that.)
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
[ fixed asm constraint bug ] Fixed-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: John Stultz <johnstul@us.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20090930170754.0886ff2e@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
There are 16 individual channels (NUM_DBDMA_CHANS) to save/restore plus the
global ddma block config (the +1). The last register in a channel can be
skipped since it's read-only (at offset 0x18).
Signed-off-by: Roel Kluin <roel.kluin@gmail.com> Cc: Manuel Lauss <manuel.lauss@googlemail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Julia Lawall [Mon, 21 Sep 2009 15:08:55 +0000 (17:08 +0200)]
MIPS: SMTC: Remove duplicate structure field initialization
The definition of the irq_ipi structure has two initializations of the
flags field. This combines them.
[Ralf: The issue was originally introduced by commit be4894196d79455f420dd7bb78be7dc73bec115c (linux-mips.org) rsp. 033890b084adfa367c544864451d7730552ce8bf (kernel.org). The original
intention of the code was to initialize .flags with both flags ored together.
The broken C code as actually implemented will be compiled by an equally
broken gcc to use only the last initialization, that is IRQF_PERCPU
which means this turned into an SMTC bug for 2.6.23 and newer.]
The semantic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@r@
identifier I, s, fld;
position p0,p;
expression E;
@@
struct I s =@p0 { ... .fld@p = E, ...};
@s@
identifier I, s, r.fld;
position r.p0,p;
expression E;
@@
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ryusuke/nilfs2
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ryusuke/nilfs2:
nilfs2: fix missing initialization of i_dir_start_lookup member
nilfs2: fix missing zero-fill initialization of btree node cache
Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: Fix time encoding with extra epoch bits
ext4: Add a stub for mpage_da_data in the trace header
jbd2: Use tracepoints for history file
ext4: Use tracepoints for mb_history trace file
ext4, jbd2: Drop unneeded printks at mount and unmount time
ext4: Handle nested ext4_journal_start/stop calls without a journal
ext4: Make sure ext4_dirty_inode() updates the inode in no journal mode
ext4: Avoid updating the inode table bh twice in no journal mode
ext4: EXT4_IOC_MOVE_EXT: Check for different original and donor inodes first
ext4: async direct IO for holes and fallocate support
ext4: Use end_io callback to avoid direct I/O fallback to buffered I/O
ext4: Split uninitialized extents for direct I/O
ext4: release reserved quota when block reservation for delalloc retry
ext4: Adjust ext4_da_writepages() to write out larger contiguous chunks
ext4: Fix hueristic which avoids group preallocation for closed files
ext4: Use ext4_msg() for ext4_da_writepage() errors
ext4: Update documentation about quota mount options
* git://git.kernel.org/pub/scm/linux/kernel/git/hirofumi/fatfs-2.6:
fat: Check s_dirt in fat_sync_fs()
vfat: change the default from shortname=lower to shortname=mixed
fat/nls: Fix handling of utf8 invalid char
Merge branch 'pm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6
* 'pm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6:
PM / yenta: Fix cardbus suspend/resume regression
PM / PCMCIA: Drop second argument of pcmcia_socket_dev_suspend()
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (33 commits)
sony-laptop: re-read the rfkill state when resuming from suspend
sony-laptop: check for rfkill hard block at load time
wext: add back wireless/ dir in sysfs for cfg80211 interfaces
wext: Add bound checks for copy_from_user
mac80211: improve/fix mlme messages
cfg80211: always get BSS
iwlwifi: fix 3945 ucode info retrieval after failure
iwlwifi: fix memory leak in command queue handling
iwlwifi: fix debugfs buffer handling
cfg80211: don't set privacy w/o key
cfg80211: wext: don't display BSSID unless associated
net: Add explicit bound checks in net/socket.c
bridge: Fix double-free in br_add_if.
isdn: fix netjet/isdnhdlc build errors
atm: dereference of he_dev->rbps_virt in he_init_group()
ax25: Add missing dev_put in ax25_setsockopt
Revert "sit: stateless autoconf for isatap"
net: fix double skb free in dcbnl
net: fix nlmsg len size for skb when error bit is set.
net: fix vlan_get_size to include vlan_flags size
...
Merge branch 'drm-next' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6
* 'drm-next' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6: (25 commits)
drm/radeon/kms: Convert R520 to new init path and associated cleanup
drm/radeon/kms: Convert RV515 to new init path and associated cleanup
drm: fix radeon DRM warnings when !CONFIG_DEBUG_FS
drm: fix drm_fb_helper warning when !CONFIG_MAGIC_SYSRQ
drm/r600: fix memory leak introduced with 64k malloc avoidance fix.
drm/kms: make fb helper work for all drivers.
drm/radeon/r600: fix offset handling in CS parser
drm/radeon/kms/r600: fix forcing pci mode on agp cards
drm/radeon/kms: fix for the extra pages copying.
drm/radeon/kms/r600: add support for vline relocs
drm/radeon/kms: fix some bugs in vline reloc
drm/radeon/kms/r600: clamp vram to aperture size
drm/kms: protect against fb helper not being created.
drm/r600: get values from the passed in IB not the copy.
drm: create gitignore file for radeon
drm/radeon/kms: remove unneeded master create/destroy functions.
drm/kms: start adding command line interface using fb.
fb: change rules for global rules match.
drm/radeon/kms: don't require up to 64k allocations. (v2)
drm/radeon/kms: enable dac load detection by default.
...
Trivial conflicts in drivers/gpu/drm/radeon/radeon_asic.h due to adding
'->vga_set_state' function pointers.
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu:
percpu: make allocation failures more verbose
percpu: make pcpu_setup_first_chunk() failures more verbose
percpu: make embedding first chunk allocator check vmalloc space size
sparc64: implement page mapping percpu first chunk allocator
percpu: make pcpu_build_alloc_info() clear static buffers
percpu: fix unit_map[] verification in pcpu_setup_first_chunk()
pty: reconnect the BSD TIOCSPTLCK handling to legacy ptys
David Howells noticed (due to the compiler warning about an unused
'pty_ops_bsd' variable) that we haven't actually been using the code
that implements TIOCSPTLCK for legacy pty handling. It's been that way
since 2.6.26, commit 3e8e88ca053150efdbecb45d8f481cf560ec808d to be
exact ("pty: prepare for tty->ops changes").
DavidH initially submitted a patch just removing the dead code entirely,
and since nobody has apparently ever complained, I'm not entirely sure
that wouldn't be the right thing to do. But since the whole and only
point of the legacy pty code is to be compatible with legacy distros
that don't use the new unix98 pty model, let's just wire it up again.
And clean it up a bit while we're at it.
Acked-by: David Howells <dhowells@redhat.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
"Looking at ext4.h, I think the setting of extra time fields forgets to
mask the epoch bits so the epoch part overwrites nsec part. The second
change is only for coherency (2 -> EXT4_EPOCH_BITS)."
Thanks to Damien Guibouret for pointing out this problem.
Josh Stone [Wed, 30 Sep 2009 04:51:22 +0000 (00:51 -0400)]
ext4: Add a stub for mpage_da_data in the trace header
The tracepoint ext4_da_write_pages has a struct mpage_da_data*
parameter, but that struct is only defined in fs/ext4/ext4.h. This
patch adds a forward declaration for that struct, so this tracepoint
header can still be used by tools like SystemTap.
This is a continuation of the fix in commit 3661d286.
The /proc/fs/jbd2/<dev>/history was maintained manually; by using
tracepoints, we can get all of the existing functionality of the /proc
file plus extra capabilities thanks to the ftrace infrastructure. We
save memory as a bonus.
The /proc/fs/ext4/<dev>/mb_history was maintained manually, and had a
number of problems: it required a largish amount of memory to be
allocated for each ext4 filesystem, and the s_mb_history_lock
introduced a CPU contention problem.
By ripping out the mb_history code and replacing it with ftrace
tracepoints, and we get more functionality: timestamps, event
filtering, the ability to correlate mballoc history with other ext4
tracepoints, etc.
Sage Weil [Tue, 29 Sep 2009 22:38:44 +0000 (18:38 -0400)]
Btrfs: fix deadlock with free space handling and user transactions
If an ioctl-initiated transaction is open, we can't force a commit during
the free space checks in order to free up pinned extents or else we
deadlock. Just ENOSPC instead.
A more satisfying solution that reserves space for the entire user
transaction up front is forthcoming...
Signed-off-by: Sage Weil <sage@newdream.net> Signed-off-by: Chris Mason <chris.mason@oracle.com>
projects / linux-beck.git / log