Instead of taking the spinlock, the lockless versions atomically check
that the lock is not taken, and do the reference count update using a
cmpxchg() loop. This is semantically identical to doing the reference
count update protected by the lock, but avoids the "wait for lock"
contention that you get when accesses to the reference count are
contended.
Note that a "lockref" is absolutely _not_ equivalent to an atomic_t.
Even when the lockref reference counts are updated atomically with
cmpxchg, the fact that they also verify the state of the spinlock means
that the lockless updates can never happen while somebody else holds the
spinlock.
So while "lockref_put_or_lock()" looks a lot like just another name for
"atomic_dec_and_lock()", and both optimize to lockless updates, they are
fundamentally different: the decrement done by atomic_dec_and_lock() is
truly independent of any lock (as long as it doesn't decrement to zero),
so a locked region can still see the count change.
The lockref structure, in contrast, really is a *locked* reference
count. If you hold the spinlock, the reference count will be stable and
you can modify the reference count without using atomics, because even
the lockless updates will see and respect the state of the lock.
In order to enable the cmpxchg lockless code, the architecture needs to
do three things:
(1) Make sure that the "arch_spinlock_t" and an "unsigned int" can fit
in an aligned u64, and have a "cmpxchg()" implementation that works
on such a u64 data type.
(2) define a helper function to test for a spinlock being unlocked
("arch_spin_value_unlocked()")
(3) select the "ARCH_USE_CMPXCHG_LOCKREF" config variable in its
Kconfig file.
This enables it for x86-64 (but not 32-bit, we'd need to make sure
cmpxchg() turns into the proper cmpxchg8b in order to enable it for
32-bit mode).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
They aren't very good to inline, since they already call external
functions (the spinlock code), and we're going to create rather more
complicated versions of them that can do the reference count updates
locklessly.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This moves __d_rcu_to_refcount() from <linux/dcache.h> into fs/namei.c
and re-implements it using the lockref infrastructure instead. It also
adds a lot of comments about what is actually going on, because turning
a dentry that was looked up using RCU into a long-lived reference
counted entry is one of the more subtle parts of the rcu walk.
We also used to be _particularly_ subtle in unlazy_walk() where we
re-validate both the dentry and its parent using the same sequence
count. We used to do it by nesting the locks and then verifying the
sequence count just once.
That was silly, because nested locking is expensive, but the sequence
count check is not. So this just re-validates the dentry and the parent
separately, avoiding the nested locking, and making the lockref lookup
possible.
Acked-by: Waiman Long <waiman.long@hp.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A valid parent pointer is always going to have a non-zero reference
count, but if we look up the parent optimistically without locking, we
have to protect against the (very unlikely) race against renaming
changing the parent from under us.
We do that by using lockref_get_not_zero(), and then re-checking the
parent pointer after getting a valid reference.
[ This is a re-implementation of a chunk from the original patch by
Waiman Long: "dcache: Enable lockless update of dentry's refcount".
I've completely rewritten the patch-series and split it up, but I'm
attributing this part to Waiman as it's close enough to his earlier
patch - Linus ]
Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This behaves like "lockref_get_not_zero()", but instead of doing nothing
if the count was zero, it returns with the lock held.
This allows callers to revalidate the lockref-protected data structure
if required even if the count was zero to begin with, and possibly
increment the count if it passes muster.
In particular, the dentry code wants this when it wants to turn an
RCU-protected dentry into a stable refcounted one: if the dentry count
it zero, but the sequence number still validates the dentry, we can take
a reference to it.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
- Don't allow unsupported comp_mask values, user should check
ibv_query_device to know which features are supported.
- Add a check in ib_uverbs_create_flow() to verify the size passed
from the user space.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Some hardware events might not be supported on a system. Listing those
events seems meaningless and confusing to users. Let's skip them.
Before:
$ perf list cache | wc -l
33
After:
$ perf list cache | wc -l
27
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1377571313-14722-1-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add a test for the newly added PERF_COUNT_SW_DUMMY event. The test
checks that tracking events continue when an event is disabled but a
dummy software event is not disabled.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1377975053-3811-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add support for the new dummy software event PERF_COUNT_SW_DUMMY.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1377975053-3811-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When an event is disabled the "tracking" events selected by the 'mmap',
'comm' and 'task' bits of struct perf_event_attr, are also disabled.
However, the information those events provide is necessary to resolve
symbols for when the main event is re-enabled.
The "tracking" events can be kept enabled by putting them on another
event, but that requires an event that otherwise does nothing. A new
software event PERF_COUNT_SW_DUMMY is added for that purpose.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1377975053-3811-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
That uses the arg mask mechanism just introduced to suppress ignored
arguments according to the futex operation.
Based on an initial patch from David Ahern that showed the need for some
way to allow args to tell how many further args should be shown.
Initial-patch-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-0k30it46r4hv5eanefbdmj5t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The futex syscall ignores some arguments according to the 'operation'
arg, so allow arg formatters to mask those.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-abqrg3oldgfsdnltfrvso9f7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This is a bug fix for the pm80xx driver. It turns out that when the new
hardware support was added in 3.10 the IO command size was kept at the old
hard coded value. This means that the driver attaches to some new cards and
then simply hangs the system.
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.19 (GNU/Linux)
iQEcBAABAgAGBQJSIh8wAAoJEDeqqVYsXL0MCOIH/3Ii/4xKN7BK/G7UYVj7QuIu
lxmshuc6FUJJkg4fZiV3oHQgkYiUoOOYTVWg+rEKycE1XZS8b3E5BVTlM2+NHezo
OcjFmctDb5HrElbBL7BrsJwNwSeSL+ATZEqPuOoXQ+CIJ9pkFwm3u1ernDLsM0bB
PuDRn1duAbyUscHNqYsInpg2a21F1cuoLIzz/ziHgXtjRre30An2wZjmNVwDKeaY
UhnCvjUy37LFFWL3mLVaS0fhkCS484uKRyloX0FJdLgtfzGvOFGF01f02gmcziti
o0+PqIhV2wPvGpiNea761JN5opxc/IhhhPapR0kaj9Qig79TP9wjEZ8ynnQvvG4=
=i73i
-----END PGP SIGNATURE-----
Merge tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Pull SCSI fix from James Bottomley:
"This is a bug fix for the pm80xx driver. It turns out that when the
new hardware support was added in 3.10 the IO command size was kept at
the old hard coded value. This means that the driver attaches to some
new cards and then simply hangs the system"
* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
[SCSI] pm80xx: fix Adaptec 71605H hang
Ensure that we set rpc_clnt->cl_parent before calling rpc_client_register
so that rpcauth_create can find any existing RPCSEC_GSS caches for this
transport.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Pull x86 boot fix from Peter Anvin:
"A single very small boot fix for very large memory systems (> 0.5T)"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm: Fix boot crash with DEBUG_PAGE_ALLOC=y and more than 512G RAM
Pull slave-dma fix from Vinod Koul:
"A fix for resolving TI_EDMA driver's build error in allmodconfig to
have filter function built in""
* 'fixes' of git://git.infradead.org/users/vkoul/slave-dma:
dma/Kconfig: TI_EDMA needs to be boolean
Ensure that all struct rpc_clnt for any given socket/rdma channel
share the same RPCSEC_GSS/krb5,krb5i,krb5p caches.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
A few final updates for v3.12 - some cleanups, a bug fix for ssm2602,
pop removal for rt5640 and fixes for the reporting of unidirectional
links in the MXS SGTL5000 driver.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)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=oB8J
-----END PGP SIGNATURE-----
Merge tag 'asoc-v3.12-3' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-next
ASoC: Final updates for v3.12
A few final updates for v3.12 - some cleanups, a bug fix for ssm2602,
pop removal for rt5640 and fixes for the reporting of unidirectional
links in the MXS SGTL5000 driver.
hdmi_channel_allocation() tries to find a HDMI channel allocation that
matches the number channels in the playback stream and contains only
speakers that the HDMI sink has reported as available via EDID. If no
such allocation is found, 0 (stereo audio) is used.
Using CA 0 causes the audio causes the sink to discard everything except
the first two channels (front left and front right).
However, the sink may be capable of receiving more channels than it has
speakers (and then perform downmix or discard the extra channels), in
which case it is preferable to use a CA that contains extra channels
than to use CA 0 which discards all the non-stereo channels.
Additionally, it seems that HBR (HD) passthrough output does not work on
Intel HDMI codecs when CA is set to 0 (possibly the codec zeroes
channels not present in CA). This happens with all receivers that report
a 5.1 speaker mask since a HBR stream is carried on 8 channels to the
codec.
Add a fallback in the CA selection so that the CA channel count at least
matches the stream channel count, even if the stream contains channels
not present in the sink speaker descriptor.
Thanks to GrimGriefer at OpenELEC forums for discovering that changing
the sink speaker mask allowed HBR output.
Reported-by: GrimGriefer
Reported-by: Ashecrow
Reported-by: Frank Zafka <kafkaesque1978@gmail.com>
Reported-by: Peter Frühberger <fritsch@xbmc.org>
Signed-off-by: Anssi Hannula <anssi.hannula@iki.fi>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Support UART0 debug ll on Hisilicon Hi3620 SoC & Hi3716 SoC.
Signed-off-by: Haojian Zhuang <haojian.zhuang@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Now that we support a timer-backed delay loop, I'm quickly getting sick
and tired of people complaining that their beloved bogomips value has
decreased. You know who you are!
This patch removes the bogomips line from /proc/cpuinfo, based on the
reasoning that any program parsing this is already broken and, as such,
won't be further broken if the field is removed.
Acked-by: Nicolas Pitre <nico@linaro.org>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
It appears that gcc may put some code in ".text.unlikely" or
".text.hot" sections. Right now those aren't accounted for in unwind
tables. Add them.
I found some docs about this at:
http://gcc.gnu.org/onlinedocs/gcc-4.6.2/gcc.pdf
Without this, if you have slub_debug turned on, you can get messages
that look like this:
unwind: Index not found 7f008c50
Signed-off-by: Doug Anderson <dianders@chromium.org>
Acked-by: Mike Frysinger <vapier@gentoo.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The newly introduced function is to be used as .restart callback for
ARMv7-M machines. The used register is architecturally defined, so it
should work for all M-class machines.
Acked-by: Jonathan Austin <jonathan.austin@arm.com>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Section entries are 2MB on LPAE, so the DEBUG_LL virtual address must
have the same offset in the 2MB section as the physical address. This
fixes async external aborts when DEBUG_LL is enabled on Midway.
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
On Cortex-A15 CPUs up to and including r0p4, in certain rare sequences
of code, the loop buffer may deliver incorrect instructions. This
workaround disables the loop buffer to avoid the erratum.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
As pointed by Russell in [1], the sg properties are already availble in struct device,
so no need to duplicate here.
[1]: http://marc.info/?l=linux-omap&m=137416733628831
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Use devm_ioremap_resource instead of devm_request_and_ioremap.
This was done using the semantic patch
scripts/coccinelle/api/devm_ioremap_resource.cocci
The relevant call to platform_get_resource was manually moved down to the
call to devm_ioremap_resource.
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
kfree on a NULL pointer is a no-op. Null pointer check is
not necessary.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Acked-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Trivial fix for function name mismatches I stumbled over.
Signed-off-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Add support for HPB-DMAC found in Renesas R-Car SoCs, using 'shdma-base' DMA
driver framework.
Based on the original patch by Phil Edworthy <phil.edworthy@renesas.com>.
Signed-off-by: Max Filippov <max.filippov@cogentembedded.com>
[Sergei: removed useless #include, sorted #include's, fixed HPB_DMA_TCR_MAX,
fixed formats and removed line breaks in the dev_dbg() calls, rephrased and
added IRQ # to the shdma_request_irq() failure message, added MODULE_AUTHOR(),
removed '__init'/'__exit' annotations from the probe()/remove() methods, removed
'__initdata' annotation from 'hpb_dmae_driver', fixed guard macro name in the
header file, fixed #define ASYNCRSTR_ASRST20, added #define ASYNCRSTR_ASRST24,
added the necessary runtime PM calls to the probe() and remove() methods,
handled errors returned by dma_async_device_register(), beautified comments
and #define's.]
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Use devm_ioremap_resource() because devm_request_and_ioremap() is
obsoleted by devm_ioremap_resource().
Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Acked-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Instead of using data from stack for DMA in hidinput_get_battery_property(),
allocate the buffer dynamically.
Cc: stable@kernel.org
Reported-by: Richard Ryniker <ryniker@alum.mit.edu>
Reported-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
KonePureOptical is a KonePure with different sensor.
Signed-off-by: Stefan Achatz <erazor_de@users.sourceforge.net>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
The DuoSense touchscreen device causes a 10 second timeout. This fix
removes the delay.
Signed-off-by: Vasily Titskiy <qehgt0@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
via-rng currently isn't auto-loaded if built as a module.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Each call to the co-processor, with exception of the last call, needs to
send data that is multiple of block size. As consequence, any remaining
data is kept in the internal NX context.
This patch fixes a bug in the driver that causes it to save incorrect
data into the context when data is bigger than the block size.
Reviewed-by: Joy Latten <jmlatten@linux.vnet.ibm.com>
Signed-off-by: Marcelo Cerri <mhcerri@linux.vnet.ibm.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The NX CGM implementation doesn't support zero length messages and the
current implementation has two flaws:
- When the input data length is zero, it ignores the associated data.
- Even when both lengths are zero, it uses the Crypto API to encrypt a
zeroed block using ctr(aes) and because of this it allocates a new
transformation and sets the key for this new tfm. Both operations are
intended to be used only in user context, while the cryptographic
operations can be called in both user and softirq contexts.
This patch replaces the nested Crypto API use and adds two special
cases:
- When input data and associated data lengths are zero: it uses NX ECB
mode to emulate the encryption of a zeroed block using ctr(aes).
- When input data is zero and associated data is available: it uses NX
GMAC mode to calculate the associated data MAC.
Reviewed-by: Joy Latten <jmlatten@linux.vnet.ibm.com>
Signed-off-by: Marcelo Cerri <mhcerri@linux.vnet.ibm.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The NX XCBC implementation doesn't support zero length messages and
because of that NX is currently returning a hard-coded hash for zero
length messages. However this approach is incorrect since the hash value
also depends on which key is used.
This patch removes the hard-coded hash and replace it with an
implementation based on the RFC 3566 using ECB.
Reviewed-by: Joy Latten <jmlatten@linux.vnet.ibm.com>
Signed-off-by: Marcelo Cerri <mhcerri@linux.vnet.ibm.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
