25 May, 2011
40 commits
-
commit 2687a356 ("Add lock_page_killable") introduced killable
lock_page(). Similarly this patch introdues killable
wait_on_page_locked().Signed-off-by: KOSAKI Motohiro
Acked-by: KAMEZAWA Hiroyuki
Reviewed-by: Minchan Kim
Cc: Matthew Wilcox
Cc: Ingo Molnar
Cc: Thomas Gleixner
Cc: "H. Peter Anvin"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
commit 2ac390370a ("writeback: add
/sys/devices/system/node//vmstat") added vmstat entry. But
strangely it only show nr_written and nr_dirtied.# cat /sys/devices/system/node/node20/vmstat
nr_written 0
nr_dirtied 0Of course, It's not adequate. With this patch, the vmstat show all vm
stastics as /proc/vmstat.# cat /sys/devices/system/node/node0/vmstat
nr_free_pages 899224
nr_inactive_anon 201
nr_active_anon 17380
nr_inactive_file 31572
nr_active_file 28277
nr_unevictable 0
nr_mlock 0
nr_anon_pages 17321
nr_mapped 8640
nr_file_pages 60107
nr_dirty 33
nr_writeback 0
nr_slab_reclaimable 6850
nr_slab_unreclaimable 7604
nr_page_table_pages 3105
nr_kernel_stack 175
nr_unstable 0
nr_bounce 0
nr_vmscan_write 0
nr_writeback_temp 0
nr_isolated_anon 0
nr_isolated_file 0
nr_shmem 260
nr_dirtied 1050
nr_written 938
numa_hit 962872
numa_miss 0
numa_foreign 0
numa_interleave 8617
numa_local 962872
numa_other 0
nr_anon_transparent_hugepages 0[akpm@linux-foundation.org: no externs in .c files]
Signed-off-by: KOSAKI Motohiro
Cc: Michael Rubin
Cc: Wu Fengguang
Acked-by: David Rientjes
Cc: Randy Dunlap
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Because 'ret' is declared as int, not unsigned long, no need to cast the
error contants into unsigned long. If you compile this code on a 64-bit
machine somehow, you'll see following warning:CC mm/nommu.o
mm/nommu.c: In function `do_mmap_pgoff':
mm/nommu.c:1411: warning: overflow in implicit constant conversionSigned-off-by: Namhyung Kim
Acked-by: Greg Ungerer
Cc: David Howells
Cc: Paul Mundt
Cc: Geert Uytterhoeven
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
If f_op->read() fails and sysctl_nr_trim_pages > 1, there could be a
memory leak between @region->vm_end and @region->vm_top.Signed-off-by: Namhyung Kim
Acked-by: Greg Ungerer
Cc: David Howells
Cc: Paul Mundt
Cc: Geert Uytterhoeven
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Now we have the sorted vma list, use it in do_munmap() to check that we
have an exact match.Signed-off-by: Namhyung Kim
Acked-by: Greg Ungerer
Cc: David Howells
Cc: Paul Mundt
Cc: Geert Uytterhoeven
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Now we have the sorted vma list, use it in the find_vma[_exact]() rather
than doing linear search on the rb-tree.Signed-off-by: Namhyung Kim
Acked-by: Greg Ungerer
Cc: David Howells
Cc: Paul Mundt
Cc: Geert Uytterhoeven
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Since commit 297c5eee3724 ("mm: make the vma list be doubly linked") made
it a doubly linked list, we don't need to scan the list when deleting
@vma.And the original code didn't update the prev pointer. Fix it too.
Signed-off-by: Namhyung Kim
Acked-by: Greg Ungerer
Cc: David Howells
Cc: Paul Mundt
Cc: Geert Uytterhoeven
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
When I was reading nommu code, I found that it handles the vma list/tree
in an unusual way. IIUC, because there can be more than one
identical/overrapped vmas in the list/tree, it sorts the tree more
strictly and does a linear search on the tree. But it doesn't applied to
the list (i.e. the list could be constructed in a different order than
the tree so that we can't use the list when finding the first vma in that
order).Since inserting/sorting a vma in the tree and link is done at the same
time, we can easily construct both of them in the same order. And linear
searching on the tree could be more costly than doing it on the list, it
can be converted to use the list.Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly
linked") made the list be doubly linked, there were a couple of code need
to be fixed to construct the list properly.Patch 1/6 is a preparation. It maintains the list sorted same as the tree
and construct doubly-linked list properly. Patch 2/6 is a simple
optimization for the vma deletion. Patch 3/6 and 4/6 convert tree
traversal to list traversal and the rest are simple fixes and cleanups.This patch:
@vma added into @mm should be sorted by start addr, end addr and VMA
struct addr in that order because we may get identical VMAs in the @mm.
However this was true only for the rbtree, not for the list.This patch fixes this by remembering 'rb_prev' during the tree traversal
like find_vma_prepare() does and linking the @vma via __vma_link_list().
After this patch, we can iterate the whole VMAs in correct order simply by
using @mm->mmap list.[akpm@linux-foundation.org: avoid duplicating __vma_link_list()]
Signed-off-by: Namhyung Kim
Acked-by: Greg Ungerer
Cc: David Howells
Cc: Paul Mundt
Cc: Geert Uytterhoeven
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Signed-off-by: Sergey Senozhatsky
Reviewed-by: Christoph Lameter
Acked-by: KAMEZAWA Hiroyuki
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Avoid merging a VMA with another VMA which is cloned from the parent process.
The cloned VMA shares the anon_vma lock with the parent process's VMA. If
we do the merge, more vmas (even the new range is only for current
process) use the perent process's anon_vma lock. This introduces
scalability issues. find_mergeable_anon_vma() already considers this
case.Signed-off-by: Shaohua Li
Cc: Rik van Riel
Cc: Hugh Dickins
Cc: Andi Kleen
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
If we only change vma->vm_end, we can avoid taking anon_vma lock even if
'insert' isn't NULL, which is the case of split_vma.As I understand it, we need the lock before because rmap must get the
'insert' VMA when we adjust old VMA's vm_end (the 'insert' VMA is linked
to anon_vma list in __insert_vm_struct before).But now this isn't true any more. The 'insert' VMA is already linked to
anon_vma list in __split_vma(with anon_vma_clone()) instead of
__insert_vm_struct. There is no race rmap can't get required VMAs. So
the anon_vma lock is unnecessary, and this can reduce one locking in brk
case and improve scalability.Signed-off-by: Shaohua Li
Cc: Rik van Riel
Acked-by: Hugh Dickins
Cc: Andi Kleen
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Make some variables have correct alignment/section to avoid cache issue.
In a workload which heavily does mmap/munmap, the variables will be used
frequently.Signed-off-by: Shaohua Li
Cc: Andi Kleen
Cc: Rik van Riel
Cc: Hugh Dickins
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Architectures that implement their own show_mem() function did not pass
the filter argument to show_free_areas() to appropriately avoid emitting
the state of nodes that are disallowed in the current context. This patch
now passes the filter argument to show_free_areas() so those nodes are now
avoided.This patch also removes the show_free_areas() wrapper around
__show_free_areas() and converts existing callers to pass an empty filter.ia64 emits additional information for each node, so skip_free_areas_zone()
must be made global to filter disallowed nodes and it is converted to use
a nid argument rather than a zone for this use case.Signed-off-by: David Rientjes
Cc: Russell King
Cc: Tony Luck
Cc: Fenghua Yu
Cc: Kyle McMartin
Cc: Helge Deller
Cc: James Bottomley
Cc: "David S. Miller"
Cc: Guan Xuetao
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This is not useful: it provides page->virtual and is used with highmem.
xtensa has no support for highmem and those HIGHMEM bits which are found
by grep are partly implemented. The interesting functions like kmap() are
missing. If someone actually implements the complete HIGHMEM support he
could use HASHED_PAGE_VIRTUAL like most others do.Signed-off-by: Sebastian Andrzej Siewior
Cc: Chris Zankel
Cc: Thomas Gleixner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
It is not referenced by any Makefile. pte_alloc_one_kernel() and
pte_alloc_one() is implemented in arch/xtensa/include/asm/pgalloc.h.Signed-off-by: Sebastian Andrzej Siewior
Cc: Chris Zankel
Cc: Thomas Gleixner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
It should check if strict_strtoul() succeeds.
[akpm@linux-foundation.org: don't override strict_strtoul() return value]
Signed-off-by: Liu Yuan
Acked-by: Michael Hennerich
Cc: Richard Purdie
Cc: Paul Mundt
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
It has been reported on some laptops that kswapd is consuming large
amounts of CPU and not being scheduled when SLUB is enabled during large
amounts of file copying. It is expected that this is due to kswapd
missing every cond_resched() point because;shrink_page_list() calls cond_resched() if inactive pages were isolated
which in turn may not happen if all_unreclaimable is set in
shrink_zones(). If for whatver reason, all_unreclaimable is
set on all zones, we can miss calling cond_resched().balance_pgdat() only calls cond_resched if the zones are not
balanced. For a high-order allocation that is balanced, it
checks order-0 again. During that window, order-0 might have
become unbalanced so it loops again for order-0 and returns
that it was reclaiming for order-0 to kswapd(). It can then
find that a caller has rewoken kswapd for a high-order and
re-enters balance_pgdat() without ever calling cond_resched().shrink_slab only calls cond_resched() if we are reclaiming slab
pages. If there are a large number of direct reclaimers, the
shrinker_rwsem can be contended and prevent kswapd calling
cond_resched().This patch modifies the shrink_slab() case. If the semaphore is
contended, the caller will still check cond_resched(). After each
successful call into a shrinker, the check for cond_resched() remains in
case one shrinker is particularly slow.[mgorman@suse.de: preserve call to cond_resched after each call into shrinker]
Signed-off-by: Mel Gorman
Signed-off-by: Minchan Kim
Cc: Rik van Riel
Cc: Johannes Weiner
Cc: Wu Fengguang
Cc: James Bottomley
Tested-by: Colin King
Cc: Raghavendra D Prabhu
Cc: Jan Kara
Cc: Chris Mason
Cc: Christoph Lameter
Cc: Pekka Enberg
Cc: Rik van Riel
Cc: [2.6.38+]
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
There are a few reports of people experiencing hangs when copying large
amounts of data with kswapd using a large amount of CPU which appear to be
due to recent reclaim changes. SLUB using high orders is the trigger but
not the root cause as SLUB has been using high orders for a while. The
root cause was bugs introduced into reclaim which are addressed by the
following two patches.Patch 1 corrects logic introduced by commit 1741c877 ("mm: kswapd:
keep kswapd awake for high-order allocations until a percentage of
the node is balanced") to allow kswapd to go to sleep when
balanced for high orders.Patch 2 notes that it is possible for kswapd to miss every
cond_resched() and updates shrink_slab() so it'll at least reach
that scheduling point.Chris Wood reports that these two patches in isolation are sufficient to
prevent the system hanging. AFAIK, they should also resolve similar hangs
experienced by James Bottomley.This patch:
Johannes Weiner poined out that the logic in commit 1741c877 ("mm: kswapd:
keep kswapd awake for high-order allocations until a percentage of the
node is balanced") is backwards. Instead of allowing kswapd to go to
sleep when balancing for high order allocations, it keeps it kswapd
running uselessly.Signed-off-by: Mel Gorman
Reviewed-by: Rik van Riel
Signed-off-by: Johannes Weiner
Reviewed-by: Wu Fengguang
Cc: James Bottomley
Tested-by: Colin King
Cc: Raghavendra D Prabhu
Cc: Jan Kara
Cc: Chris Mason
Cc: Christoph Lameter
Cc: Pekka Enberg
Cc: Rik van Riel
Reviewed-by: Minchan Kim
Reviewed-by: Wu Fengguang
Cc: [2.6.38+]
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Commit 442b06bcea23 ("slub: Remove node check in slab_free") added a
call to deactivate_slab() in the debug case in __slab_alloc(), which
unlocks the current slab used for allocation. Going to the label
'unlock_out' then does it again.Also, in the debug case we do not need all the other processing that the
'unlock_out' path does. We always fall back to the slow path in the
debug case. So the tid update is useless.Similarly, ALLOC_SLOWPATH would just be incremented for all allocations.
Also a pretty useless thing.So simply restore irq flags and return the object.
Signed-off-by: Christoph Lameter
Reported-and-bisected-by: James Morris
Reported-by: Ingo Molnar
Reported-by: Jens Axboe
Cc: Pekka Enberg
Signed-off-by: Linus Torvalds -
* 'for-linus/2640/i2c' of git://git.fluff.org/bjdooks/linux: (21 commits)
mach-ux500: set proper I2C platform data from MOP500s
i2c-nomadik: break out single messsage transmission
i2c-nomadik: reset the hw after status check
i2c-nomadik: remove the unnecessary delay
i2c-nomadik: change the TX and RX threshold
i2c-nomadik: add code to retry on timeout failure
i2c-nomadik: use pm_runtime API
i2c-nomadik: print abort cause only on abort tag
i2c-nomadik: correct adapter timeout initialization
i2c-nomadik: remove the redundant error message
i2c-nomadik: corrrect returned error numbers
i2c-nomadik: fix speed enumerator
i2c-nomadik: make i2c timeout specific per i2c bus
i2c-nomadik: add regulator support
i2c: i2c-sh_mobile bus speed platform data V2
i2c: i2c-sh_mobile clock string removal
i2c-eg20t: Support new device ML7223 IOH
i2c: tegra: Add de-bounce cycles.
i2c: tegra: fix repeated start handling
i2c: tegra: recover from spurious interrupt storm
... -
…a' and 'for-2639/i2c-nomadik2' into for-linus/2640/i2c
-
This specifies the new per-platform timeout per I2C bus and
switches the I2C buses to fast mode, and increase the FIFO
depth to 8 for reads and writes.Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
Reduce code size in the message transfer function by factoring out
a single-message transfer function.Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
In case of I2C timeout, reset the HW only after the HW status
is read, otherwise the staus will be lost.Signed-off-by: Virupax Sadashivpetimath
Reviewed-by: Jonas Aberg
Reviewed-by: Srinidhi Kasagar
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
The delay in the driver seems to be not needed, so remove it.
Signed-off-by: Virupax Sadashivpetimath
Reviewed-by: Markus Grape
Tested-by: Per Persson
Tested-by: Chethan Krishna N
Reviewed-by: Srinidhi Kasagar
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
1) Increase RX FIFO threshold so that there is a reduction in
the number of interrupts handled to complete a transaction.2) Fill TX FIFO in the write function.
Signed-off-by: Virupax Sadashivpetimath
Reviewed-by: Jonas Aberg
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
It is seen that i2c-nomadik controller randomly stops generating the
interrupts leading to a i2c timeout. As a workaround to this problem,
add retries to the on going transfer on failure.Signed-off-by: Virupax Sadashivpetimath
Reviewed-by: Jonas ABERG
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
Use the pm_runtime API for pins control.
Signed-off-by: Rabin Vincent
Reviewed-by: Srinidhi Kasagar
Reviewed-by: Jonas Aberg
[deleted some surplus runtime PM code]
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
Modify the code to:
1)Print the cause of i2c failure only if the status is set to ABORT.
2)Print slave address on send/receive fail, will help in which slave
failed.Signed-off-by: Virupax Sadashivpetimath
Reviewed-by: Jonas Aberg
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
Correct the incorrect initialization of adapter timeout not to be
in milliseconds, as it needs to be done in jiffies.Signed-off-by: Virupax Sadashivpetimath
Reviewed-by: Srinidhi Kasagar
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
The abort cause string itself is an error, so remove the redundant
explicit error message.Signed-off-by: Srinidhi Kasagar
Reviewed-by: Jonas Aberg
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
The code was returning bad error numbers or just -1 in some cases.
Signed-off-by: Virupax Sadashivpetimath
Reviewed-by: Srinidhi Kasagar
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
The I2C speed enumerators in the i2c-nomadik header file were in
the wrong order.Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
Add option to have different i2c timeout delay for different i2c buses
specified in platform data. Default to the old value unless specified.Signed-off-by: Virupax Sadashivpetimath
Reviewed-by: Srinidhi Kasagar
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
This on-chip I2C controller needs to fetch the regulator
representing its voltage domain so that it won't be switched off.Signed-off-by: Jonas Aberg
Signed-off-by: Linus Walleij
Signed-off-by: Ben Dooks -
* 'i2c-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jdelvare/staging:
i2c-parport: Various cleanups
i2c-i801: Don't depend on other kernel driver config options
i2c-i801: Check for vendor Fujitsu before probing for apanel
i2c-i801: Don't probe for slaves on IDF channels
i2c-i801: SMBus patch for Intel Panther Point DeviceIDs
i2c/writing-clients: Fix foo_driver.id_table -
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs-2.6:
jbd: Fix comment to match the code in journal_start()
jbd/jbd2: remove obsolete summarise_journal_usage.
jbd: Fix forever sleeping process in do_get_write_access()
ext2: fix error msg when mounting fs with too-large blocksize
jbd: fix fsync() tid wraparound bug
ext3: Fix fs corruption when make_indexed_dir() fails
ext3: Fix lock inversion in ext3_symlink() -
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/dlm:
dlm: make plock operation killable
dlm: remove shared message stub for recovery
dlm: delayed reply message warning
dlm: Remove superfluous call to recalc_sigpending() -
…s/security-testing-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6: (43 commits)
TOMOYO: Fix wrong domainname validation.
SELINUX: add /sys/fs/selinux mount point to put selinuxfs
CRED: Fix load_flat_shared_library() to initialise bprm correctly
SELinux: introduce path_has_perm
flex_array: allow 0 length elements
flex_arrays: allow zero length flex arrays
flex_array: flex_array_prealloc takes a number of elements, not an end
SELinux: pass last path component in may_create
SELinux: put name based create rules in a hashtable
SELinux: generic hashtab entry counter
SELinux: calculate and print hashtab stats with a generic function
SELinux: skip filename trans rules if ttype does not match parent dir
SELinux: rename filename_compute_type argument to *type instead of *con
SELinux: fix comment to state filename_compute_type takes an objname not a qstr
SMACK: smack_file_lock can use the struct path
LSM: separate LSM_AUDIT_DATA_DENTRY from LSM_AUDIT_DATA_PATH
LSM: split LSM_AUDIT_DATA_FS into _PATH and _INODE
SELINUX: Make selinux cache VFS RCU walks safe
SECURITY: Move exec_permission RCU checks into security modules
SELinux: security_read_policy should take a size_t not ssize_t
... -
* 'kbuild' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6:
kbuild: make KBUILD_NOCMDDEP=1 handle empty built-in.o
scripts/kallsyms.c: fix potential segfault
scripts/gen_initramfs_list.sh: Convert to a /bin/sh script
kbuild: Fix GNU make v3.80 compatibility
kbuild: Fix passing -Wno-* options to gcc 4.4+
kbuild: move scripts/basic/docproc.c to scripts/docproc.c
kbuild: Fix Makefile.asm-generic for um
kbuild: Allow to combine multiple W= levels
kbuild: Disable -Wunused-but-set-variable for gcc 4.6.0
Fix handling of backlash character in LINUX_COMPILE_BY name
kbuild: asm-generic support
kbuild: implement several W= levels
kbuild: Fix build with binutils <= 2.19
initramfs: Use KBUILD_BUILD_TIMESTAMP for generated entries
kbuild: Allow to override LINUX_COMPILE_BY and LINUX_COMPILE_HOST macros
kbuild: Drop unused LINUX_COMPILE_TIME and LINUX_COMPILE_DOMAIN macros
kbuild: Use the deterministic mode of ar
kbuild: Call gzip with -n
kbuild: move KALLSYMS_EXTRA_PASS from Kconfig to Makefile
Kconfig: improve KALLSYMS_ALL documentationFix up trivial conflict in Makefile
