18 Apr, 2015
1 commit
-
Pull documentation updates from Jonathan Corbet:
"Numerous fixes, the overdue removal of the i2o docs, some new Chinese
translations, and, hopefully, the README fix that will end the flow of
identical patches to that file"* tag 'docs-for-linus' of git://git.lwn.net/linux-2.6: (34 commits)
Documentation/memcg: update memcg/kmem status
Documentation: blackfin: Makefile: Typo building issue
Documentation/vm/pagemap.txt: correct location of page-types tool
Documentation/memory-barriers.txt: typo fix
doc: Add guest_nice column to example output of `cat /proc/stat'
Documentation/kernel-parameters: Move "eagerfpu" to its right place
Documentation: gpio: Update ACPI part of the document to mention _DSD
docs/completion.txt: Various tweaks and corrections
doc: completion: context, scope and language fixes
Documentation:Update Documentation/zh_CN/arm64/memory.txt
Documentation:Update Documentation/zh_CN/arm64/booting.txt
Documentation: Chinese translation of arm64/legacy_instructions.txt
DocBook media: fix broken EIA hyperlink
Documentation: tweak the maintainers entry
README: Change gzip/bzip2 to xz compression format
README: Update version number reference
doc:pci: Fix typo in Documentation/PCI
Documentation: drm: Use '->' when describing access through pointers.
Documentation: Remove mentioning of block barriers
Documentation/email-clients.txt: Fix one grammar mistake, add extra info about TB
...
09 Apr, 2015
1 commit
-
Fix an obvious typo in the documentation.
Signed-off-by: Michael S. Tsirkin
Signed-off-by: Jonathan Corbet
27 Feb, 2015
1 commit
-
This commit explicitly states that control dependencies pair normally
with other barriers, and gives an example of such pairing.Reported-by: Peter Zijlstra
Signed-off-by: Paul E. McKenney
Acked-by: Peter Zijlstra (Intel)
08 Jan, 2015
2 commits
-
Signed-off-by: Davidlohr Bueso
Signed-off-by: Paul E. McKenney -
This commit documents the fact that it is not safe to use bitfields
as shared variables in synchronization algorithms. It also documents
that CPUs must be able to concurrently load from and store to adjacent
one-byte and two-byte variables, which is in fact required by the
C11 standard (Section 3.14).Signed-off-by: Paul E. McKenney
12 Dec, 2014
1 commit
-
There are a number of situations where the mandatory barriers rmb() and
wmb() are used to order memory/memory operations in the device drivers
and those barriers are much heavier than they actually need to be. For
example in the case of PowerPC wmb() calls the heavy-weight sync
instruction when for coherent memory operations all that is really needed
is an lsync or eieio instruction.This commit adds a coherent only version of the mandatory memory barriers
rmb() and wmb(). In most cases this should result in the barrier being the
same as the SMP barriers for the SMP case, however in some cases we use a
barrier that is somewhere in between rmb() and smp_rmb(). For example on
ARM the rmb barriers break down as follows:Barrier Call Explanation
--------- -------- ----------------------------------
rmb() dsb() Data synchronization barrier - system
dma_rmb() dmb(osh) data memory barrier - outer sharable
smp_rmb() dmb(ish) data memory barrier - inner sharableThese new barriers are not as safe as the standard rmb() and wmb().
Specifically they do not guarantee ordering between coherent and incoherent
memories. The primary use case for these would be to enforce ordering of
reads and writes when accessing coherent memory that is shared between the
CPU and a device.It may also be noted that there is no dma_mb(). Most architectures don't
provide a good mechanism for performing a coherent only full barrier without
resorting to the same mechanism used in mb(). As such there isn't much to
be gained in trying to define such a function.Cc: Frederic Weisbecker
Cc: Mathieu Desnoyers
Cc: Michael Ellerman
Cc: Michael Neuling
Cc: Russell King
Cc: Geert Uytterhoeven
Cc: Heiko Carstens
Cc: Linus Torvalds
Cc: Martin Schwidefsky
Cc: Tony Luck
Cc: Oleg Nesterov
Cc: "Paul E. McKenney"
Cc: Peter Zijlstra
Cc: Ingo Molnar
Cc: David Miller
Acked-by: Benjamin Herrenschmidt
Acked-by: Will Deacon
Signed-off-by: Alexander Duyck
Signed-off-by: David S. Miller
10 Dec, 2014
1 commit
-
Pull RCU updates from Ingo Molnar:
"These are the main changes in this cycle:- Streamline RCU's use of per-CPU variables, shifting from "cpu"
arguments to functions to "this_"-style per-CPU variable
accessors.- signal-handling RCU updates.
- real-time updates.
- torture-test updates.
- miscellaneous fixes.
- documentation updates"
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
rcu: Fix FIXME in rcu_tasks_kthread()
rcu: More info about potential deadlocks with rcu_read_unlock()
rcu: Optimize cond_resched_rcu_qs()
rcu: Add sparse check for RCU_INIT_POINTER()
documentation: memory-barriers.txt: Correct example for reorderings
documentation: Add atomic_long_t to atomic_ops.txt
documentation: Additional restriction for control dependencies
documentation: Document RCU self test boot params
rcutorture: Fix rcu_torture_cbflood() memory leak
rcutorture: Remove obsolete kversion param in kvm.sh
rcutorture: Remove stale test configurations
rcutorture: Enable RCU self test in configs
rcutorture: Add early boot self tests
torture: Run Linux-kernel binary out of results directory
cpu: Avoid puts_pending overflow
rcu: Remove "cpu" argument to rcu_cleanup_after_idle()
rcu: Remove "cpu" argument to rcu_prepare_for_idle()
rcu: Remove "cpu" argument to rcu_needs_cpu()
rcu: Remove "cpu" argument to rcu_note_context_switch()
rcu: Remove "cpu" argument to rcu_preempt_check_callbacks()
...
14 Nov, 2014
2 commits
-
Correct the example of memory orderings in memory-barriers.txt
Commit 615cc2c9cf95 "Documentation/memory-barriers.txt: fix important typo re
memory barriers" changed the assignment to x and y. Change the rest of the
example to match this change.Reported-by: Ganesh Rapolu
Signed-off-by: Pranith Kumar
Signed-off-by: Paul E. McKenney -
Short-circuit booleans are not defences against compilers breaking
your intended control dependencies.Signed-off-by: Paul E. McKenney
Reviewed-by: Pranith Kumar
21 Oct, 2014
1 commit
-
This patch extends the paragraph describing the relaxed read io accessors
so that the relaxed accessors are defined to be:- Ordered with respect to each other if accessing the same peripheral
- Unordered with respect to normal memory accesses
- Unordered with respect to LOCK/UNLOCK operations
Whilst many architectures will provide stricter semantics, ARM, Alpha and
PPC can achieve significant performance gains by taking advantage of some
or all of the above relaxations.Cc: Randy Dunlap
Cc: Benjamin Herrenschmidt
Cc: Paul E. McKenney
Cc: David Howells
Signed-off-by: Will Deacon
08 Sep, 2014
3 commits
-
Sad to say, current compilers really will hoist identical stores from both
branches of an "if" statement to precede the conditional. This commit
therefore updates the description of control dependencies to reflect this
ugly reality.Reported-by: Pranith Kumar
Reported-by: Peter Zijlstra
Signed-off-by: Paul E. McKenney -
The transformation in the fold-to-zero example incorrectly omits the
barrier() directive. This commit therefore adds it back in.Reported-by: Pranith Kumar
Signed-off-by: Paul E. McKenney -
The control-ordering example demonstrating lack of transitivity had
multiple problems. This commit fixes them.Reported-by: Nikolay Samofatov
Signed-off-by: Paul E. McKenney
Reviewed-by: Pranith Kumar
08 Jul, 2014
2 commits
-
It is possible to pair acquire and release barriers with other barriers,
so this commit adds them to the list in the SMP barrier pairing section.Reported-by: Lai Jiangshan
Signed-off-by: Paul E. McKenney
Reviewed-by: Tejun Heo
Reviewed-by: Josh Triplett
[ paulmck: Updated pairing discussion as suggested by Peter Zijlstra. ] -
This commit adds an example demonstrating that if a wake_up() doesn't
actually wake something up, no memory ordering is provided.Reported-by: Peter Zijlstra
Signed-off-by: Paul E. McKenney
Reviewed-by: Josh Triplett
Reviewed-by: Lai Jiangshan
Acked-by: Peter Zijlstra
07 Jun, 2014
1 commit
-
Examples introducing neccesity of RMB+WMP pair reads as
A=3 READ B
www rrrrrr
B=4 READ ANote the opposite order of reads vs writes.
But the first example without barriers reads as
A=3 READ A
B=4 READ BThere are 4 outcomes in the first example.
But if someone new to the concept tries to insert barriers like this:
A=3 READ A
www rrrrrr
B=4 READ Bhe will still get all 4 possible outcomes, because "READ A" is first.
All this can be utterly confusing because barrier pair seems to be
superfluous. In short, fixup first example to match latter examples
with barriers.Signed-off-by: Alexey Dobriyan
Cc: David Howells
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
18 Apr, 2014
1 commit
-
Update the documentation to reflect the change of barrier primitives.
Signed-off-by: Peter Zijlstra
Reviewed-by: Paul E. McKenney
Acked-by: David Howells
Link: http://lkml.kernel.org/n/tip-xslfehiga1twbk5uk94rij1e@git.kernel.org
Cc: Linus Torvalds
Cc: Randy Dunlap
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar
03 Apr, 2014
1 commit
-
Pull trivial tree updates from Jiri Kosina:
"Usual rocket science -- mostly documentation and comment updates"* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial:
sparse: fix comment
doc: fix double words
isdn: capi: fix "CAPI_VERSION" comment
doc: DocBook: Fix typos in xml and template file
Bluetooth: add module name for btwilink
driver core: unexport static function create_syslog_header
mmc: core: typo fix in printk specifier
ARM: spear: clean up editing mistake
net-sysfs: fix comment typo 'CONFIG_SYFS'
doc: Insert MODULE_ in module-signing macros
Documentation: update URL to hfsplus Technote 1150
gpio: update path to documentation
ixgbe: Fix format string in ixgbe_fcoe.
Kconfig: Remove useless "default N" lines
user_namespace.c: Remove duplicated word in comment
CREDITS: fix formatting
treewide: Fix typo in Documentation/DocBook
mm: Fix warning on make htmldocs caused by slab.c
ata: ata-samsung_cf: cleanup in header file
idr: remove unused prototype of idr_free()
21 Mar, 2014
1 commit
-
Fix double words "the the" in various files
within Documentations.Signed-off-by: Masanari Iida
Signed-off-by: Jiri Kosina
25 Feb, 2014
1 commit
-
This commit fixes a couple of typos and clarifies what happens when
the CPU chooses to execute a later lock acquisition before a prior
lock release, in particular, why deadlock is avoided.Reported-by: Peter Hurley
Reported-by: James Bottomley
Reported-by: Stefan Richter
Signed-off-by: Paul E. McKenney
18 Feb, 2014
3 commits
-
Current compilers can "speculate" stores in the case where both legs
of the "if" statement start with identical stores. Because the stores
are identical, the compiler knows that the store will unconditionally
execute regardless of the "if" condition, and so the compiler is within
its rights to hoist the store to precede the condition. Such hoisting
destroys the control-dependency ordering. This ordering can be restored
by placing a barrier() at the beginning of each leg of the "if" statement.
This commit adds this requirement to the control-dependencies section.Signed-off-by: Paul E. McKenney
-
A control dependency consists of a load, a conditional that depends on
that load, and a store. This commit emphasizes this point in the
summary.Signed-off-by: Paul E. McKenney
Reviewed-by: Josh Triplett -
The ACCESS_ONCE() primitive provides cache coherence, but the
documentation does not clearly state this. This commit therefore upgrades
the documentation.Signed-off-by: Paul E. McKenney
Reviewed-by: Josh Triplett
12 Jan, 2014
1 commit
-
The LOCK and UNLOCK barriers as described in our barrier document are
generally known as ACQUIRE and RELEASE barriers in other literature.Since we plan to introduce the acquire and release nomenclature in
generic kernel primitives we should amend the document to avoid
confusion as to what an acquire/release means.Reviewed-by: "Paul E. McKenney"
Signed-off-by: Peter Zijlstra
Acked-by: Mathieu Desnoyers
Cc: Benjamin Herrenschmidt
Cc: Frederic Weisbecker
Cc: Michael Ellerman
Cc: Michael Neuling
Cc: Russell King
Cc: Geert Uytterhoeven
Cc: Heiko Carstens
Cc: Linus Torvalds
Cc: Martin Schwidefsky
Cc: Victor Kaplansky
Cc: Tony Luck
Cc: Oleg Nesterov
Link: http://lkml.kernel.org/r/20131217092435.GC21999@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar
16 Dec, 2013
5 commits
-
Historically, an UNLOCK+LOCK pair executed by one CPU, by one
task, or on a given lock variable has implied a full memory
barrier. In a recent LKML thread, the wisdom of this historical
approach was called into question:
http://www.spinics.net/lists/linux-mm/msg65653.html, in part due
to the memory-order complexities of low-handoff-overhead queued
locks on x86 systems.This patch therefore removes this guarantee from the
documentation, and further documents how to restore it via a new
smp_mb__after_unlock_lock() primitive.Signed-off-by: Paul E. McKenney
Reviewed-by: Peter Zijlstra
Cc:
Cc: Linus Torvalds
Cc: Andrew Morton
Link: http://lkml.kernel.org/r/1386799151-2219-6-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar -
The situations in which ACCESS_ONCE() is required are not well
documented, so this commit adds some verbiage to
memory-barriers.txt.Reported-by: Peter Zijlstra
Signed-off-by: Paul E. McKenney
Reviewed-by: Josh Triplett
Reviewed-by: Peter Zijlstra
Cc:
Cc: Linus Torvalds
Cc: Andrew Morton
Link: http://lkml.kernel.org/r/1386799151-2219-4-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar -
No SMP architecture currently supporting Linux allows
speculative writes, so this commit updates
Documentation/memory-barriers.txt to prohibit them in Linux core
code. It also records restrictions on their use.Signed-off-by: Peter Zijlstra
Signed-off-by: Paul E. McKenney
Reviewed-by: Josh Triplett
Reviewed-by: Peter Zijlstra
Cc:
Cc: Linus Torvalds
Cc: Andrew Morton
Link: http://lkml.kernel.org/r/1386799151-2219-3-git-send-email-paulmck@linux.vnet.ibm.com
[ Paul modified the original patch from Peter. ]
Signed-off-by: Ingo Molnar -
Although the atomic_long_t functions are quite useful, they are
a bit obscure. This commit therefore adds the common ones
alongside their atomic_t counterparts in
Documentation/memory-barriers.txt.Signed-off-by: Paul E. McKenney
Reviewed-by: Josh Triplett
Reviewed-by: Peter Zijlstra
Cc:
Cc: Linus Torvalds
Cc: Andrew Morton
Link: http://lkml.kernel.org/r/1386799151-2219-2-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar -
The Documentation/memory-barriers.txt file was written before
the need for ACCESS_ONCE() was fully appreciated. It therefore
contains no ACCESS_ONCE() calls, which can be a problem when
people lift examples from it. This commit therefore adds
ACCESS_ONCE() calls.Signed-off-by: Paul E. McKenney
Reviewed-by: Josh Triplett
Reviewed-by: Peter Zijlstra
Cc:
Cc: Linus Torvalds
Cc: Andrew Morton
Link: http://lkml.kernel.org/r/1386799151-2219-1-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar
22 Nov, 2013
1 commit
-
This typo has been there forever, it is 7.5 years old, looks like this
section of our memory ordering documentation is a place where most eyes
are glazed over already ;-)[ Also fix some stray spaces and stray tabs while at it, shrinking the
file by 49 bytes. Visual output unchanged. ]Cc: Peter Zijlstra
Cc: Linus Torvalds
Cc: Andrew Morton
Cc: Thomas Gleixner
Cc: Paul E. McKenney
Link: http://lkml.kernel.org/n/tip-gncea9cb8igosblizfqMXrie@git.kernel.org
Signed-off-by: Ingo Molnar
20 Aug, 2013
1 commit
-
Each control-dependency example needs its barriers between the "if"
condition and the body of the "if" because a control dependency is
a dependency induced by a branch. This commit makes the needed
adjustment.Reported-by: Yongming Shen
Signed-off-by: Paul E. McKenney
Reviewed-by: Josh Triplett
09 Jan, 2013
1 commit
-
Add atomic_xchg() to documentation for atomic operations and
memory barriers.Signed-off-by: Richard Braun
Signed-off-by: Paul E. McKenney
Reviewed-by: Josh Triplett
24 Oct, 2012
1 commit
-
This commit fixes a broken example of overlapping stores in the
Documentation/memory-barriers.txt file.Reported-by: Nikunj A Dadhania
Signed-off-by: Paul E. McKenney
28 Sep, 2011
1 commit
-
There are numerous broken references to Documentation files (in other
Documentation files, in comments, etc.). These broken references are
caused by typo's in the references, and by renames or removals of the
Documentation files. Some broken references are simply odd.Fix these broken references, sometimes by dropping the irrelevant text
they were part of.Signed-off-by: Paul Bolle
Signed-off-by: Jiri Kosina
05 Mar, 2011
1 commit
-
Transitivity is guaranteed only for full memory barriers (smp_mb()).
Signed-off-by: Paul E. McKenney
25 Mar, 2010
1 commit
-
Document the circular buffering capabilities available in Linux.
Signed-off-by: David Howells
Signed-off-by: Paul E. McKenney
Reviewed-by: Randy Dunlap
Reviewed-by: Stefan Richter
Signed-off-by: Linus Torvalds
29 Apr, 2009
1 commit
-
Add a section to the memory barriers document to note the implied
memory barriers of sleep primitives (set_current_state() and wrappers)
and wake-up primitives (wake_up() and co.).Also extend the in-code comments on the wake_up() functions to note
these implied barriers.[ Impact: add documentation ]
Signed-off-by: David Howells
Cc: Oleg Nesterov
Cc: Linus Torvalds
Cc: Andrew Morton
LKML-Reference:
Signed-off-by: Ingo Molnar
15 May, 2008
1 commit
-
read_barrie_depends has always been a noop (not a compiler barrier) on all
architectures except SMP alpha. This brings UP alpha and frv into line with all
other architectures, and fixes incorrect documentation.Signed-off-by: Nick Piggin
Acked-by: Paul E. McKenney
Signed-off-by: Linus Torvalds
21 Apr, 2008
1 commit
-
Create Documentation/PCI/ and move PCI-related files to it.
Fix a few instances of trailing whitespace.
Update references to the new file locations.Signed-off-by: Randy Dunlap
Cc: Jesse Barnes
Signed-off-by: Greg Kroah-Hartman
24 Feb, 2008
1 commit
-
(sorry for being offtpoic, but while experts are here...)
A "typical" implementation of atomic_add_unless() can return 0 immediately
after the first atomic_read() (before doing cmpxchg). In that case it doesn't
provide any barrier semantics. See include/asm-ia64/atomic.h as an example.We should either change the implementation, or fix the docs.
Signed-off-by: Oleg Nesterov
Acked-by: Nick Piggin
Signed-off-by: Linus Torvalds
