Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with
or
.
Download ZIP

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also compare across forks.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also compare across forks.
base fork: NigelCunningham/tuxonice-kernel
...
head fork: NigelCunningham/tuxonice-kernel
Commits on Jan 19, 2013
John David Anglin [PARISC] Purge existing TLB entries in set_pte_at and ptep_set_wrprotect
This patch goes a long way toward fixing the minifail bug, and
it  significantly improves the stability of SMP machines such as
the rp3440.  When write  protecting a page for COW, we need to
purge the existing translation.  Otherwise, the COW break
doesn't occur as expected because the TLB may still have a stale entry
which allows writes.

[jejb: fix up checkpatch errors]
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Cc: stable@vger.kernel.org
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
7139bc1
Commits on Jan 30, 2013
@geertu geertu [PARISC] hpux: Remove obsolete regs parameter from do_execve() in hpu…
…x_execve()

commit da3d4c5 ("get rid of pt_regs
argument of do_execve()") removed the parameter, but forgot to update
hpux_execve():

arch/parisc/hpux/fs.c: In function 'hpux_execve':
arch/parisc/hpux/fs.c:47:6: error: too many arguments to function 'do_execve'

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
6c700d7
Commits on Jan 31, 2013
Fenghua Yu x86, doc: Documentation for early microcode loading
Documenation for early loading microcode methodology.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-2-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
0d91ea8
Fenghua Yu x86/microcode_intel.h: Define functions and macros for early loading …
…ucode

Define some functions and macros that will be used in early loading ucode. Some
of them are moved from microcode_intel.c driver in order to be called in early
boot phase before module can be called.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-3-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
9cd4d78
Fenghua Yu x86/common.c: Make have_cpuid_p() a global function
Remove static declaration in have_cpuid_p() to make it a global function. The
function will be called in early loading microcode.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-4-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
d288e1c
Fenghua Yu x86/common.c: load ucode in 64 bit or show loading ucode info in 32 b…
…it on AP

In 64 bit, load ucode on AP in cpu_init().

In 32 bit, show ucode loading info on AP in cpu_init(). Microcode has been
loaded earlier before paging. Now it is safe to show the loading microcode
info on this AP.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-5-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
e6ebf5d
Fenghua Yu x86/microcode_core_early.c: Define interfaces for early loading ucode
Define interfaces load_ucode_bsp() and load_ucode_ap() to load ucode on BSP and
AP in early boot time. These are generic interfaces. Internally they call
vendor specific implementations.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-6-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
a8ebf6d
Fenghua Yu x86/microcode_intel_lib.c: Early update ucode on Intel's CPU
Define interfaces microcode_sanity_check() and get_matching_microcode(). They
are called both in early boot time and in microcode Intel driver.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-7-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
e666dfa
Fenghua Yu x86/tlbflush.h: Define __native_flush_tlb_global_irq_disabled()
This function is called in __native_flush_tlb_global() and after
apply_microcode_early().

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-8-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
086fc8f
Fenghua Yu x86/microcode_intel_early.c: Early update ucode on Intel's CPU
Implementation of early update ucode on Intel's CPU.

load_ucode_intel_bsp() scans ucode in initrd image file which is a cpio format
ucode followed by ordinary initrd image file. The binary ucode file is stored
in kernel/x86/microcode/GenuineIntel.bin in the cpio data. All ucode
patches with the same model as BSP are saved in memory. A matching ucode patch
is updated on BSP.

load_ucode_intel_ap() reads saved ucoded patches and updates ucode on AP.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-9-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
ec400dd
Fenghua Yu x86/head_32.S: Early update ucode in 32-bit
This updates ucode in 32-bit kernel on BSP and AP. At this point, there is no
paging and no virtual address yet.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-10-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
63b553c
Fenghua Yu x86/head64.c: Early update ucode in 64-bit
This updates ucode on BSP in 64-bit mode. Paging and virtual address are
working now.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-11-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
feddc9d
Fenghua Yu x86/mm/init.c: Copy ucode from initrd image to kernel memory
Before initrd image is freed, copy valid ucode patches from initrd image
to kernel memory. The saved ucode will be used to update AP in resume
or hotplug.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-12-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
cd745be
Fenghua Yu x86/Kconfig: Make early microcode loading a configuration feature
MICROCODE_INTEL_LIB, MICROCODE_INTEL_EARLY, and MICROCODE_EARLY are three new
configurations to enable or disable the feature.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1356075872-3054-13-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
da76f64
Commits on Feb 19, 2013
Yuanhan Liu locking/stat: Fix a typo
s/STATS/STAT

Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1359019365-23646-1-git-send-email-yuanhan.liu@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
0be5c8f
Srivatsa S. Bhat lockdep: Rename print_unlock_inbalance_bug() to print_unlock_imbalanc…
…e_bug()

Fix the typo in the function name (s/inbalance/imbalance)

Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: rostedt@goodmis.org
Cc: peterz@infradead.org
Link: http://lkml.kernel.org/r/20130108130547.32733.79507.stgit@srivatsabhat.in.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
f86f755
Namhyung Kim watchdog: Use local_clock for get_timestamp()
The get_timestamp() function is always called with current cpu,
thus using local_clock() would be more appropriate and it makes
the code shorter and cleaner IMHO.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Don Zickus <dzickus@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1356576585-28782-1-git-send-email-namhyung@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
c06b4f1
@pebolle pebolle lockdep: Silence warning if CONFIG_LOCKDEP isn't set
Since commit c9a4962 ("nfsd:
make client_lock per net") compiling nfs4state.o without
CONFIG_LOCKDEP set, triggers this GCC warning:

    fs/nfsd/nfs4state.c: In function ‘free_client’:
    fs/nfsd/nfs4state.c:1051:19: warning: unused variable ‘nn’ [-Wunused-variable]

The cause of that warning is that lockdep_assert_held() compiles
away if CONFIG_LOCKDEP is not set. Silence this warning by using
the argument to lockdep_assert_held() as a nop if CONFIG_LOCKDEP
is not set.

Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislav Kinsbursky <skinsbursky@parallels.com>
Cc: J. Bruce Fields <bfields@redhat.com>
Link: http://lkml.kernel.org/r/1359060797.1325.33.camel@x61.thuisdomein
Signed-off-by: Ingo Molnar <mingo@kernel.org>
--
 include/linux/lockdep.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
5cd3f5a
Alex Shi rwsem: Implement writer lock-stealing for better scalability
Commit 5a50508 ("mm/rmap: Convert the struct anon_vma::mutex
to an rwsem") changed struct anon_vma::mutex to an rwsem, which
caused aim7 fork_test performance to drop by 50%.

Yuanhan Liu did the following excellent analysis:

    https://lkml.org/lkml/2013/1/29/84

and found that the regression is caused by strict, serialized,
FIFO sequential write-ownership of rwsems. Ingo suggested
implementing opportunistic lock-stealing for the front writer
task in the waitqueue.

Yuanhan Liu implemented lock-stealing for spinlock-rwsems,
which indeed recovered much of the regression - confirming
the analysis that the main factor in the regression was the
FIFO writer-fairness of rwsems.

In this patch we allow lock-stealing to happen when the first
waiter is also writer. With that change in place the
aim7 fork_test performance is fully recovered on my
Intel NHM EP, NHM EX, SNB EP 2S and 4S test-machines.

Reported-by: lkp@linux.intel.com
Reported-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Signed-off-by: Alex Shi <alex.shi@intel.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Anton Blanchard <anton@samba.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: paul.gortmaker@windriver.com
Link: https://lkml.org/lkml/2013/1/29/84
Link: http://lkml.kernel.org/r/1360069915-31619-1-git-send-email-alex.shi@intel.com
[ Small stylistic fixes, updated changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
ce6711f
@greearb greearb lockdep: Print more info when MAX_LOCK_DEPTH is exceeded
This helps debug cases where a lock is acquired over and
over without being released.

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ben Greear <greearb@candelatech.com>
Cc: peterz@infradead.org
Link: http://lkml.kernel.org/r/1360176979-4421-1-git-send-email-greearb@candelatech.com
[ Changed the printout ordering. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
c054060
Thomas Gleixner locking: Various static lock initializer fixes
The static lock initializers want to be fed the proper name of the
lock and not some random string. In mainline random strings are
obfuscating the readability of debug output, but for RT they prevent
the spinlock substitution. Fix it up.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
eece09e
Mike Galbraith intel_idle: Convert i7300_idle_lock to raw_spinlock
24 core Intel box's first exposure to 3.0.12-rt30-rc3 didn't go well.

[   27.104159] i7300_idle: loaded v1.55
[   27.104192] BUG: scheduling while atomic: swapper/2/0/0x00000002
[   27.104309] Pid: 0, comm: swapper/2 Tainted: G           N  3.0.12-rt30-rc3-rt #1
[   27.104317] Call Trace:
[   27.104338]  [<ffffffff810046a5>] dump_trace+0x85/0x2e0
[   27.104372]  [<ffffffff8144eb00>] thread_return+0x12b/0x30b
[   27.104381]  [<ffffffff8144f1b9>] schedule+0x29/0xb0
[   27.104389]  [<ffffffff814506e5>] rt_spin_lock_slowlock+0xc5/0x240
[   27.104401]  [<ffffffffa01f818f>] i7300_idle_notifier+0x3f/0x360 [i7300_idle]
[   27.104415]  [<ffffffff814546c7>] notifier_call_chain+0x37/0x70
[   27.104426]  [<ffffffff81454748>] __atomic_notifier_call_chain+0x48/0x70
[   27.104439]  [<ffffffff81001a39>] cpu_idle+0x89/0xb0
[   27.104449] bad: scheduling from the idle thread!

This lock is taken from interrupt disabled context in the guts of
idle. Convert it to a raw_spinlock.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Andy Henroid <andrew.d.henroid@intel.com>
Link: http://lkml.kernel.org/r/1323258522.5057.73.camel@marge.simson.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
066361a
Thomas Gleixner ntp: Make ntp_lock raw
seconds_overflow() is called from hard interrupt context even on
Preempt-RT. This requires the lock to be a raw_spinlock.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <john.stultz@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
a6c0c94
Thomas Gleixner seqlock: Remove unused functions
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
65c9d1b
Thomas Gleixner seqlock: Use seqcount infrastructure
No point in having different implementations for the same
thing. Change the macro mess to inline functions where possible.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
6617fec
@yongzhang yongzhang lockdep: Selftest: convert spinlock to raw spinlock
To make the lockdep selftest working on RT we need to convert the
spinlock tests to a raw spinlock. Otherwise we cannot run the irq
context checks. For mainline this is just annotational as spinlocks
are mapped to raw_spinlocks anyway.

Signed-off-by: Yong Zhang <yong.zhang0@gmail.com>
Link: http://lkml.kernel.org/r/1334559716-18447-2-git-send-email-yong.zhang0@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
9fb1b90
Ingo Molnar generic: Use raw local irq variant for generic cmpxchg
The interrupt disabled region is extremly tiny and therefor not
latency relevant. Avoid cluttering the traces with those pointless
entries.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
5042afe
Thomas Gleixner futex: Revert "futex: Mark get_robust_list as deprecated"
This reverts commit ec0c427.

get_robust_list() is in use and a removal would break existing user
space. With the permission checks in place it's not longer a security
hole. Remove the deprecation warnings.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: akpm@linux-foundation.org
Cc: paul.gortmaker@windriver.com
Cc: davej@redhat.com
Cc: keescook@chromium.org
Cc: stable@vger.kernel.org
Cc: ebiederm@xmission.com
fe2b05f
Yuanhan Liu rwsem-spinlock: Implement writer lock-stealing for better scalability
We (Linux Kernel Performance project) found a regression
introduced by commit:

  5a50508 mm/rmap: Convert the struct anon_vma::mutex to an rwsem

which converted all anon_vma::mutex locks rwsem write locks.

The semantics are the same, but the behavioral difference is
quite huge in some cases. After investigating it we found the
root cause: mutexes support lock stealing while rwsems don't.

Here is the link for the detailed regression report:

  https://lkml.org/lkml/2013/1/29/84

Ingo suggested adding write lock stealing to rwsems:

    "I think we should allow lock-steal between rwsem writers - that
     will not hurt fairness as most rwsem fairness concerns relate to
     reader vs. writer fairness"

And here is the rwsem-spinlock version.

With this patch, we got a double performance increase in one
test box with following aim7 workfile:

    FILESIZE: 1M
    POOLSIZE: 10M
    10 fork_test

 /usr/bin/time output w/o patch                       /usr/bin/time_output with patch
 -- Percent of CPU this job got: 369%                 Percent of CPU this job got: 537%
 Voluntary context switches: 640595016                Voluntary context switches: 157915561

We got a 45% increase in CPU usage and saved about 3/4 voluntary context switches.

Reported-by: LKP project <lkp@linux.intel.com>
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: Alex Shi <alex.shi@intel.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Anton Blanchard <anton@samba.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: paul.gortmaker@windriver.com
Link: http://lkml.kernel.org/r/1359716356-23865-1-git-send-email-yuanhan.liu@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
41ef8f8
Commits on Feb 20, 2013
@lliubbo lliubbo blackfin: mem_init: update dmc config register
Update dmc config register to increase memory performance.

Signed-off-by: Bob Liu <lliubbo@gmail.com>
c428f8e
@mita mita blackfin: use bitmap library functions
The bitmap library provides more efficient functions than accessing
individual bits with bitops.

This uses bitmap_find_next_zero_area() to find a continuing zero area,
and uses bitmap_set()/bitmap_clear() to set/clear specified bit area.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: uclinux-dist-devel@blackfin.uclinux.org
Signed-off-by: Bob Liu <lliubbo@gmail.com>
c73bc70
@sonicz sonicz blackfin: sync data in blackfin write buffer
Sync data in blackfin write buffer to DRAM before return from
copy_to_user.
Otherwise, application may read wrong data from stat syscall occasionally.

Signed-off-by: Sonic Zhang <sonic.zhang@analog.com>
Signed-off-by: Bob Liu <lliubbo@gmail.com>
293be8d
@realmz realmz blackfin: pm: fix build error
Only register pm ops when defined CONFIG_PM.

Signed-off-by: Steven Miao <realmz6@gmail.com>
Signed-off-by: Bob Liu <lliubbo@gmail.com>
36c4723
@bebarino bebarino blackfin: time-ts: Remove duplicate assignment
It seems that this assignment is done twice in a row. Remove the
duplicate assignment.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Cc: Steven Miao <realmz6@gmail.com>
Cc: trivial@kernel.org
Signed-off-by: Bob Liu <lliubbo@gmail.com>
f656c24
Helge Deller Merge tag 'parisc-fixes' of git://git.kernel.org/pub/scm/linux/kernel…
…/git/jejb/parisc-2.6 into stable-3.8

PARISC fixes on 20130213

This is a couple of patches, one to fix a broken build with HPUX compatibility
and the other to solve a coherency problem we've been seeing in our TLB where
setting a page read only occasionally fails to trigger a COW because of a
stale writeable TLB entry.

Signed-off-by: James Bottomley <JBottomley@Parallels.com>
26ad19d
Helge Deller parisc: enhance automatic CONFIG_CROSS_COMPILE detection
The current Makefile will only choose the hppa64 cross compiler when
running natively on hppa in a 32bit userspace.
This patch additionally chooses the correct 32/64 bit hppa compiler even
when doing real cross compiling to hppa/hppa64 from another architecture.

Signed-off-by: Helge Deller <deller@gmx.de>
0e39718
John David Anglin parisc: Fix comment describing setup of access rights in entry.S
This comment describes incredibly subtle code, so it should be right!

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
1c4c659
Helge Deller parisc: add CONFIG_MLONGCALLS option to enable linkage of huge vmlinu…
…x executables

When building a 64bit kernel which includes all necessary drivers and
filesystems the vmlinux kernel often gets so huge, that the linker won't
be able to resolve the branch stubs. This patch overcomes this limit by
providing an option to compile the kernel with the -mlong-calls compiler
option.

Signed-off-by: Helge Deller <deller@gmx.de>
ec758f9
Wei Yongjun parisc: fix possible memory leak in pat_query_module()
pa_pdc_cell has been allocated in this function and so should be
freed before leaving from the error handling cases.

spatch with a semantic match is used to found this problem.
(http://coccinelle.lip6.fr/)

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: Helge Deller <deller@gmx.de>
fbd4843
@JoePerches JoePerches drivers/parisc: Use printf extension %pR for struct resource
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Helge Deller <deller@gmx.de>
3fad9b8
@JuliaLawall JuliaLawall drivers/parisc/pdc_stable.c: use WARN
Use WARN rather than printk followed by WARN_ON(1), for conciseness.

Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: Helge Deller <deller@gmx.de>
93c3e91
John David Anglin parisc: fixes and cleanups in page cache flushing (1/4)
This is the first patch in a series of 4, with which the page cache flushing of
parisc will gets fixed and enhanced. This even fixes the nasty "minifail" bug
(http://wiki.parisc-linux.org/TestCases?highlight=%28minifail%29) which
prevented parisc to stay an official debian port.  Basically the flush in
copy_user_page together with the TLB patch from commit
7139bc1 is what fixes the minifail bug.

This patch still uses the TMPALIAS approach.  The new copy_user_page
implementation calls flush_dcache_page_asm to flush the user dcache page
(crucial for minifail fix) via a kernel TMPALIAS mapping.  After that, it just
copies the page using the kernel mapping.  It does a final flush if needed.
Generally it is hard to avoid doing some cache flushes using the kernel mapping
(e.g., copy_to_user_page and copy_from_user_page).

This patch depends on a subsequent change to pacache.S implementing
clear_page_asm and copy_page_asm.  These are optimized routines to clear and
copy a page.  The calls in clear_user_page and copy_user_page could be replaced
by calls to memset and memcpy, respectively.  I tested prefetch optimizations
in clear_page_asm and copy_page_asm but didn't see any significant performance
improvement on rp3440.  I'm not sure if these are routines are significantly
faster than memset and/or memcpy, but they are there for further performance
evaluation.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
7633453
John David Anglin parisc: fixes and cleanups in page cache flushing (2/4)
Implement clear_page_asm and copy_page_asm. These are optimized routines to
clear and copy a page.  I tested prefetch optimizations in clear_page_asm and
copy_page_asm but didn't see any significant performance improvement on rp3440.
I'm not sure if these are routines are significantly faster than memset and/or
memcpy, but they are there for further performance evaluation.

TLB purge operations on PA 1.X SMP machines are now serialized with the help of
the new tlb_lock() and tlb_unlock() macros, since on some PA-RISC machines, TLB
purges need to be serialized in software.  Obviously, lock isn't needed in UP
kernels.  On PA 2.0 machines, there is a local TLB instruction which is much
less disruptive to the memory subsystem.  No lock is needed for local purge.

Loops are also unrolled in flush_instruction_cache_local and
flush_data_cache_local.

The implementation of what used to be copy_user_page (now copy_user_page_asm)
is now fixed. Additionally 64-bit support is now added. Read the preceding
comment which I didn't change.  I left the comment but it is now inaccurate.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
6d2ddc2
John David Anglin parisc: fixes and cleanups in page cache flushing (3/4)
flush_cache_mm, for the non current case also uses flush_dcache_page_asm
and flush_icache_page_asm which are TMPALIAS flushes.

For the non current case, the algorithm used by get_ptep is derived from the
vmalloc_to_page implementation in vmalloc.c.  It is essentially a generic page
table lookup.  The other alternative was to duplicate the lookup in entry.S.
The break point for switching to a full cache flush is somewhat arbitrary.  The
same approach is used in flush_cache_range for non current case.  In a GCC
build and check, many small programs are executed and this change provided a
significant performance enhancement, e.g. GCC build time was cut almost in half
on a rp3440 at j4.  Previously, we always flushed the entire cache.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
6d2439d
John David Anglin parisc: fixes and cleanups in page cache flushing (4/4)
CONFIG_PARISC_TMPALIAS enables clear_user_highpage and copy_user_highpage.
These are essentially alternative implementations of clear_user_page and
copy_user_page.  They don't have anything to do with x86 high pages, but they
build on the infrastructure to save a few instructions.  Read the comment in
clear_user_highpage as it is very important to the implementation.  For this
reason, there isn't any gain in using the TMPALIAS/highpage approach.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
cca8e90
Peter Zijlstra parisc: remove IRQF_DISABLED
People are playing odd games with IRQF_DISABLED, remove it.

Its not reliable, since shared interrupt lines could disable it for you,
and its possible and allowed for archs to disable IRQs to limit IRQ nesting.

Therefore, simply mandate that _ALL_ IRQ handlers are run with IRQs disabled.

[ This _should_ not break anything, since we've mandated that IRQ handlers
  _must_ be able to deal with this for a _long_ time ]

IRQ handlers should be fast, no if buts and any other exceptions. We also have
plenty instrumentation to find any offending IRQ latency sources.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Helge Deller <deller@gmx.de>
b54cb23
John David Anglin parisc: disable preemption while flushing D- or I-caches through TMPA…
…LIAS region

It is necessary to disable preemption during cache flushes done through the
TMPALIAS region to ensure that the TLB setup is not clobbered by another flush.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
027f27c
John David Anglin parisc: ensure that mmapped shared pages are aligned at SHMLBA addresses
Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
5ca8b91
John David Anglin parisc: always detect multiple physical ranges
This patch unbreaks the current logic in that way, that even if
CONFIG_DISCONTIGMEM isn't set, the user may be informed, that he should turn on
CONFIG_DISCONTIGMEM for his machine.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
872420b
Al Viro parisc: fix ptrace breakage
1) PTRACE_SYSCALL doesn't work for 64bit process on parisc64.
Compat syscall table is used instead of 64bit one.  IMO we should either
refuse to allow PTRACE_SYSCALL for 64bit processes or duplicate the
logics choosing the right syscall table into .Ltracesys.

	2) if you have let the tracee run with PTRACE_SYSCALL and
it had stopped, you can use PTRACE_POKEUSR to modify syscall number
(r20) and arguments 1--4 (r26--r23).  Modifications will have effect.
However, modifying arguments 5 and 6 (r22 and r21 resp.) works only
when process (32bit one) runs on 64bit host - on 32bit one it has no
effect.  AFAICS, the diff below should fix that one.

Signed-off-by: Al Viro <viro@ZenIV.linux.org.uk>
Tested-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
52ab532
John David Anglin parisc: space register variables need to be in native length (unsigne…
…d long)

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Signed-off-by: Helge Deller <deller@gmx.de>
45b6eff
Kautuk Consul parisc/mm/fault.c: Port OOM changes to do_page_fault
Commit d065bd8
(mm: retry page fault when blocking on disk transfer) and
commit 37b23e0
(x86,mm: make pagefault killable)

The above commits introduced changes into the x86 pagefault handler
for making the page fault handler retryable as well as killable.

These changes reduce the mmap_sem hold time, which is crucial
during OOM killer invocation.

Port these changes to parisc.

Signed-off-by: Kautuk Consul <consul.kautuk@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
3805747
@pebolle pebolle parisc: remove unused compat_rt_sigframe.h header
Nothing uses compat_rt_sigframe.h anymore. Commit
f671c45 ("[PARISC] Arch-specific compat
signals") removed all includes of that header. It also basically copied
that entire header verbatim into signal32.h. It seems it was just
forgotten to also remove compat_rt_sigframe.h from the tree. Remove that
header now.

Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Helge Deller <deller@gmx.de>
d313d4e
Helge Deller parisc: led driver requires CONFIG_VM_EVENT_COUNTERS
LED activity is calculated out of the vm event counters wich are delivered
through the all_vm_events() function which requires CONFIG_VM_EVENT_COUNTERS.

Signed-off-by: Helge Deller <deller@gmx.de>
95bb2f0
Helge Deller parisc: wire up process_vm_readv, process_vm_writev, kcmp and finit_m…
…odule syscalls

Signed-off-by: Helge Deller <deller@gmx.de>
2408474
Helge Deller parisc: fix personality on 32bit kernel
Process personality is stored together with other flags like UNAME26 in
an integer variable.  Overwriting this value with PER_LINUX drops all
other existing flags and as such broke tools like the uname26 tool.

Actually this was only broken on 32bit kernels, since for 32bit-ELF
binaries on 64-bit kernels the SET_PERSONALITY macro from
arch/parisc/kernel/binfmt_elf32.c is used which does not modifies the
personality value at all (which is wrong as long as we don't run HPUX
binaries or similiar).

Signed-off-by: Helge Deller <deller@gmx.de>
330cb32
Helge Deller parisc: correctly wire up mq_* functions for CONFIG_COMPAT case
Fix mq_open, mq_timedsend, mq_timedreceive, mq_notify and mq_getsetattr
syscalls when running 32bit applications on 64bit kernel.

Signed-off-by: Helge Deller <deller@gmx.de>
fee707b
Helge Deller parisc: convert msgrcv and msgsnd syscalls to use compat layer
Switch over to use the existing compat_* implementation for msgrcv() and
msgsnd().  Existing code was even partly buggy since it returned on some paths
different error codes than the standard.

Signed-off-by: Helge Deller <deller@gmx.de>
bf581e1
Helge Deller parisc: fix error return codes for rt_sigaction and rt_sigprocmask
Signed-off-by: Helge Deller <deller@gmx.de>
2e800df
Helge Deller parisc: fix fallocate syscall
fallocate(off_t) gets redirected by glibc to fallocate64(loff_t)
where the 64bit loff_t values get splitted into two 32bit (hi/lo)
values. This patch fixes this syscall for the 32- and 64bit kernel.

Signed-off-by: Helge Deller <deller@gmx.de>
4474a33
Helge Deller parisc: switch to available compat_sched_rr_get_interval implementation
Signed-off-by: Helge Deller <deller@gmx.de>
e27da28
Helge Deller parisc: sendfile and sendfile64 syscall cleanups
Utilize the existing compat_sys_sendfile function for 64bit kernel and add
wrappers for sendfile and sendfile64 to correctly handle the 32/64 bit sign
extension.

Signed-off-by: Helge Deller <deller@gmx.de>
f03d70a
Helge Deller parisc: remove empty lines and unnecessary #ifdef coding in include/a…
…sm/signal.h

Signed-off-by: Helge Deller <deller@gmx.de>
dc5322e
Nikitas Angelinas arch/parisc/include/asm: use ARRAY_SIZE macro in mmzone.h
Signed-off-by: Nikitas Angelinas <nikitasangelinas@gmail.com>
Signed-off-by: Helge Deller <deller@gmx.de>
1dda59b
Commits on Feb 22, 2013
@clrkwllms clrkwllms sched: move RR_TIMESLICE from sysctl.h to rt.h
Originally submitted by Clark Williams as part of a cleanup,
but happens also to fix an ia64 build problem:

arch/ia64/kernel/init_task.c:38: error: 'RR_TIMESLICE' undeclared here (not in a function)

Signed-off-by: Clark Williams <clark.williams@gmail.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
bc68159
Commits on Feb 23, 2013
Konrad Rzeszutek Wilk x86-64, xen, mmu: Provide an early version of write_cr3.
With commit 8170e6b ("x86, 64bit: Use a #PF handler to materialize
early mappings on demand") we started hitting an early bootup crash
where the Xen hypervisor would inform us that:

    (XEN) d7:v0: unhandled page fault (ec=0000)
    (XEN) Pagetable walk from ffffea000005b2d0:
    (XEN)  L4[0x1d4] = 0000000000000000 ffffffffffffffff
    (XEN) domain_crash_sync called from entry.S
    (XEN) Domain 7 (vcpu#0) crashed on cpu#3:
    (XEN) ----[ Xen-4.2.0  x86_64  debug=n  Not tainted ]----

.. that Xen was unable to context switch back to dom0.

Looking at the calling stack we find:

    [<ffffffff8103feba>] xen_get_user_pgd+0x5a  <--
    [<ffffffff8103feba>] xen_get_user_pgd+0x5a
    [<ffffffff81042d27>] xen_write_cr3+0x77
    [<ffffffff81ad2d21>] init_mem_mapping+0x1f9
    [<ffffffff81ac293f>] setup_arch+0x742
    [<ffffffff81666d71>] printk+0x48

We are trying to figure out whether we need to up-date the user PGD as
well.  Please keep in mind that under 64-bit PV guests we have a limited
amount of rings: 0 for the Hypervisor, and 1 for both the Linux kernel
and user-space.  As such the Linux pvops'fied version of write_cr3
checks if it has to update the user-space cr3 as well.

That clearly is not needed during early bootup.  The recent changes (see
above git commit) streamline the x86 page table allocation to be much
simpler (And also incidentally the #PF handler ends up in spirit being
similar to how the Xen toolstack sets up the initial page-tables).

The fix is to have an early-bootup version of cr3 that just loads the
kernel %cr3.  The later version - which also handles user-page
modifications will be used after the initial page tables have been
setup.

[ hpa: removed a redundant #ifdef and made the new function __init.
  Also note that x86-32 already has such an early xen_write_cr3. ]

Tested-by: "H. Peter Anvin" <hpa@zytor.com>
Reported-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Link: http://lkml.kernel.org/r/1361579812-23709-1-git-send-email-konrad.wilk@oracle.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
0cc9129
@torvalds torvalds Merge branch 'x86/microcode' of git://git.kernel.org/pub/scm/linux/ke…
…rnel/git/tip/tip

Pull x86 microcode loading update from Peter Anvin:
 "This patchset lets us update the CPU microcode very, very early in
  initialization if the BIOS fails to do so (never happens, right?)

  This is handy for dealing with things like the Atom erratum where we
  have to run without PSE because microcode loading happens too late.

  As I mentioned in the x86/mm push request it depends on that
  infrastructure but it is otherwise a standalone feature."

* 'x86/microcode' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/Kconfig: Make early microcode loading a configuration feature
  x86/mm/init.c: Copy ucode from initrd image to kernel memory
  x86/head64.c: Early update ucode in 64-bit
  x86/head_32.S: Early update ucode in 32-bit
  x86/microcode_intel_early.c: Early update ucode on Intel's CPU
  x86/tlbflush.h: Define __native_flush_tlb_global_irq_disabled()
  x86/microcode_intel_lib.c: Early update ucode on Intel's CPU
  x86/microcode_core_early.c: Define interfaces for early loading ucode
  x86/common.c: load ucode in 64 bit or show loading ucode info in 32 bit on AP
  x86/common.c: Make have_cpuid_p() a global function
  x86/microcode_intel.h: Define functions and macros for early loading ucode
  x86, doc: Documentation for early microcode loading
c47f39e
@torvalds torvalds Merge branch 'core-locking-for-linus' of git://git.kernel.org/pub/scm…
…/linux/kernel/git/tip/tip

Pull core locking changes from Ingo Molnar:
 "The biggest change is the rwsem lock-steal improvements, both to the
  assembly optimized and the spinlock based variants.

  The other notable change is the clean up of the seqlock implementation
  to be based on the seqcount infrastructure.

  The rest is assorted smaller debuggability, cleanup and continued -rt
  locking changes."

* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  rwsem-spinlock: Implement writer lock-stealing for better scalability
  futex: Revert "futex: Mark get_robust_list as deprecated"
  generic: Use raw local irq variant for generic cmpxchg
  lockdep: Selftest: convert spinlock to raw spinlock
  seqlock: Use seqcount infrastructure
  seqlock: Remove unused functions
  ntp: Make ntp_lock raw
  intel_idle: Convert i7300_idle_lock to raw_spinlock
  locking: Various static lock initializer fixes
  lockdep: Print more info when MAX_LOCK_DEPTH is exceeded
  rwsem: Implement writer lock-stealing for better scalability
  lockdep: Silence warning if CONFIG_LOCKDEP isn't set
  watchdog: Use local_clock for get_timestamp()
  lockdep: Rename print_unlock_inbalance_bug() to print_unlock_imbalance_bug()
  locking/stat: Fix a typo
3b5d851
@torvalds torvalds Merge tag 'please-pull-fix-ia64-build' of git://git.kernel.org/pub/sc…
…m/linux/kernel/git/aegl/linux

Pull ia64 build breakage fix from Tony Luck.

* tag 'please-pull-fix-ia64-build' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux:
  sched: move RR_TIMESLICE from sysctl.h to rt.h
c68fea3
@torvalds torvalds Merge branch 'parisc-3.9' of git://git.kernel.org/pub/scm/linux/kerne…
…l/git/deller/parisc-linux

Pull parisc updates from Helge Deller.

The bulk of this is optimized page coping/clearing and cache flushing
(virtual caches are lovely) by John David Anglin.

* 'parisc-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux: (31 commits)
  arch/parisc/include/asm: use ARRAY_SIZE macro in mmzone.h
  parisc: remove empty lines and unnecessary #ifdef coding in include/asm/signal.h
  parisc: sendfile and sendfile64 syscall cleanups
  parisc: switch to available compat_sched_rr_get_interval implementation
  parisc: fix fallocate syscall
  parisc: fix error return codes for rt_sigaction and rt_sigprocmask
  parisc: convert msgrcv and msgsnd syscalls to use compat layer
  parisc: correctly wire up mq_* functions for CONFIG_COMPAT case
  parisc: fix personality on 32bit kernel
  parisc: wire up process_vm_readv, process_vm_writev, kcmp and finit_module syscalls
  parisc: led driver requires CONFIG_VM_EVENT_COUNTERS
  parisc: remove unused compat_rt_sigframe.h header
  parisc/mm/fault.c: Port OOM changes to do_page_fault
  parisc: space register variables need to be in native length (unsigned long)
  parisc: fix ptrace breakage
  parisc: always detect multiple physical ranges
  parisc: ensure that mmapped shared pages are aligned at SHMLBA addresses
  parisc: disable preemption while flushing D- or I-caches through TMPALIAS region
  parisc: remove IRQF_DISABLED
  parisc: fixes and cleanups in page cache flushing (4/4)
  ...
5f32ed1
@torvalds torvalds Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…
…/git/lliubbo/blackfin

Pull small blackfin update from Bob Liu.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/lliubbo/blackfin:
  blackfin: time-ts: Remove duplicate assignment
  blackfin: pm: fix build error
  blackfin: sync data in blackfin write buffer
  blackfin: use bitmap library functions
  blackfin: mem_init: update dmc config register
df24eef
@NigelCunningham Merge branch 'upstream-head' into tuxonice-head b9bd0bc