At the start of the function we assign 'a->d' to 'ap'. Then we use the
RESIZE_IF_NEEDED macro on 'a' - this may free 'a->d' and replace it
with newly allocaetd storage. In that case, we'll be operating on
freed memory further down in the function when we index into 'ap[]'.
Since we don't actually need 'ap' until after the use of the
RESIZE_IF_NEEDED macro we can just delay the assignment to it until
after we've potentially resized, thus avoiding the issue.
While I was there anyway I also changed the integer variable 'n' to be
const. It might as well be since we only assign to it once and use it
as a constant, and then the compiler will tell us if we ever assign to
it in the future.
Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Acked-by: Dmitry Kasatkin <dmitry.kasatkin@intel.com>
Signed-off-by: James Morris <james.l.morris@oracle.com>
1/ convert open-coded KERN_ERR+dump_stack() to WARN(), so that automated
tools pick up this warning.
2/ include the 'child' and 'parent' kobject names. This information was
useful for tracking down the case where scsi invoked device_del() on a
parent object and subsequently invoked device_add() on a child. Now the
warning looks like:
kobject_add_internal failed for target8:0:16 (error: -2 parent: end_device-8:0:24)
Pid: 2942, comm: scsi_scan_8 Not tainted 3.3.0-rc7-isci+ #2
Call Trace:
[<ffffffff8125e551>] kobject_add_internal+0x1c1/0x1f3
[<ffffffff81075149>] ? trace_hardirqs_on+0xd/0xf
[<ffffffff8125e659>] kobject_add_varg+0x41/0x50
[<ffffffff8125e723>] kobject_add+0x64/0x66
[<ffffffff8131124b>] device_add+0x12d/0x63a
[<ffffffff8125e0ef>] ? kobject_put+0x4c/0x50
[<ffffffff8132f370>] scsi_sysfs_add_sdev+0x4e/0x28a
[<ffffffff8132dce3>] do_scan_async+0x9c/0x145
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: James Bottomley <JBottomley@parallels.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Add help text to the crc32 algorithm selection option in Kconfig.
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Reported-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rewrite radix_tree_gang_lookup_* functions using the new radix-tree
iterator.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Tested-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A series of radix tree cleanups, and usage of them in the core pagecache
code.
Micro-benchmark:
lookup 14 slots (typical page-vector size)
in radix-tree there earch <step> slot filled and tagged
before/after - nsec per full scan through tree
* Intel Sandy Bridge i7-2620M 4Mb L3
New code always faster
* AMD Athlon 6000+ 2x1Mb L2, without L3
New code generally faster,
Minor degradation (marked with "*") for huge sparse trees
* i386 on Sandy Bridge
New code faster for common cases: tagged and dense trees.
Some degradations for non-tagged lookup on sparse trees.
Ideally, there might help __ffs() analog for searching first non-zero
long element in array, gcc sometimes cannot optimize this loop corretly.
Numbers:
CPU: Intel Sandy Bridge i7-2620M 4Mb L3
radix-tree with 1024 slots:
tagged lookup
step 1 before 7156 after 3613
step 2 before 5399 after 2696
step 3 before 4779 after 1928
step 4 before 4456 after 1429
step 5 before 4292 after 1213
step 6 before 4183 after 1052
step 7 before 4157 after 951
step 8 before 4016 after 812
step 9 before 3952 after 851
step 10 before 3937 after 732
step 11 before 4023 after 709
step 12 before 3872 after 657
step 13 before 3892 after 633
step 14 before 3720 after 591
step 15 before 3879 after 578
step 16 before 3561 after 513
normal lookup
step 1 before 4266 after 3301
step 2 before 2695 after 2129
step 3 before 2083 after 1712
step 4 before 1801 after 1534
step 5 before 1628 after 1313
step 6 before 1551 after 1263
step 7 before 1475 after 1185
step 8 before 1432 after 1167
step 9 before 1373 after 1092
step 10 before 1339 after 1134
step 11 before 1292 after 1056
step 12 before 1319 after 1030
step 13 before 1276 after 1004
step 14 before 1256 after 987
step 15 before 1228 after 992
step 16 before 1247 after 999
radix-tree with 1024*1024*128 slots:
tagged lookup
step 1 before 1086102841 after 674196409
step 2 before 816839155 after 498138306
step 7 before 599728907 after 240676762
step 15 before 555729253 after 185219677
step 63 before 606637748 after 128585664
step 64 before 608384432 after 102945089
step 65 before 596987114 after 123996019
step 128 before 304459225 after 56783056
step 256 before 158846855 after 31232481
step 512 before 86085652 after 18950595
step 12345 before 6517189 after 1674057
normal lookup
step 1 before 626064869 after 544418266
step 2 before 418809975 after 336321473
step 7 before 242303598 after 207755560
step 15 before 208380563 after 176496355
step 63 before 186854206 after 167283638
step 64 before 176188060 after 170143976
step 65 before 185139608 after 167487116
step 128 before 88181865 after 86913490
step 256 before 45733628 after 45143534
step 512 before 24506038 after 23859036
step 12345 before 2177425 after 2018662
* AMD Athlon 6000+ 2x1Mb L2, without L3
radix-tree with 1024 slots:
tag-lookup
step 1 before 8164 after 5379
step 2 before 5818 after 5581
step 3 before 4959 after 4213
step 4 before 4371 after 3386
step 5 before 4204 after 2997
step 6 before 4950 after 2744
step 7 before 4598 after 2480
step 8 before 4251 after 2288
step 9 before 4262 after 2243
step 10 before 4175 after 2131
step 11 before 3999 after 2024
step 12 before 3979 after 1994
step 13 before 3842 after 1929
step 14 before 3750 after 1810
step 15 before 3735 after 1810
step 16 before 3532 after 1660
normal-lookup
step 1 before 7875 after 5847
step 2 before 4808 after 4071
step 3 before 4073 after 3462
step 4 before 3677 after 3074
step 5 before 4308 after 2978
step 6 before 3911 after 3807
step 7 before 3635 after 3522
step 8 before 3313 after 3202
step 9 before 3280 after 3257
step 10 before 3166 after 3083
step 11 before 3066 after 3026
step 12 before 2985 after 2982
step 13 before 2925 after 2924
step 14 before 2834 after 2808
step 15 before 2805 after 2803
step 16 before 2647 after 2622
radix-tree with 1024*1024*128 slots:
tag-lookup
step 1 before 1288059720 after 951736580
step 2 before 961292300 after 884212140
step 7 before 768905140 after 547267580
step 15 before 771319480 after 456550640
step 63 before 504847640 after 242704304
step 64 before 392484800 after 177920786
step 65 before 491162160 after 246895264
step 128 before 208084064 after 97348392
step 256 before 112401035 after 51408126
step 512 before 75825834 after 29145070
step 12345 before 5603166 after 2847330
normal-lookup
step 1 before 1025677120 after 861375100
step 2 before 647220080 after 572258540
step 7 before 505518960 after 484041813
step 15 before 430483053 after 444815320 *
step 63 before 388113453 after 404250546 *
step 64 before 374154666 after 396027440 *
step 65 before 381423973 after 396704853 *
step 128 before 190078700 after 202619384 *
step 256 before 100886756 after 102829108 *
step 512 before 64074505 after 56158720
step 12345 before 4237289 after 4422299 *
* i686 on Sandy bridge
radix-tree with 1024 slots:
tagged lookup
step 1 before 7990 after 4019
step 2 before 5698 after 2897
step 3 before 5013 after 2475
step 4 before 4630 after 1721
step 5 before 4346 after 1759
step 6 before 4299 after 1556
step 7 before 4098 after 1513
step 8 before 4115 after 1222
step 9 before 3983 after 1390
step 10 before 4077 after 1207
step 11 before 3921 after 1231
step 12 before 3894 after 1116
step 13 before 3840 after 1147
step 14 before 3799 after 1090
step 15 before 3797 after 1059
step 16 before 3783 after 745
normal lookup
step 1 before 5103 after 3499
step 2 before 3299 after 2550
step 3 before 2489 after 2370
step 4 before 2034 after 2302 *
step 5 before 1846 after 2268 *
step 6 before 1752 after 2249 *
step 7 before 1679 after 2164 *
step 8 before 1627 after 2153 *
step 9 before 1542 after 2095 *
step 10 before 1479 after 2109 *
step 11 before 1469 after 2009 *
step 12 before 1445 after 2039 *
step 13 before 1411 after 2013 *
step 14 before 1374 after 2046 *
step 15 before 1340 after 1975 *
step 16 before 1331 after 2000 *
radix-tree with 1024*1024*128 slots:
tagged lookup
step 1 before 1225865377 after 667153553
step 2 before 842427423 after 471533007
step 7 before 609296153 after 276260116
step 15 before 544232060 after 226859105
step 63 before 519209199 after 141343043
step 64 before 588980279 after 141951339
step 65 before 521099710 after 138282060
step 128 before 298476778 after 83390628
step 256 before 149358342 after 43602609
step 512 before 76994713 after 22911077
step 12345 before 5328666 after 1472111
normal lookup
step 1 before 819284564 after 533635310
step 2 before 512421605 after 364956155
step 7 before 271443305 after 305721345 *
step 15 before 223591630 after 273960216 *
step 63 before 190320247 after 217770207 *
step 64 before 178538168 after 267411372 *
step 65 before 186400423 after 215347937 *
step 128 before 88106045 after 140540612 *
step 256 before 44812420 after 70660377 *
step 512 before 24435438 after 36328275 *
step 12345 before 2123924 after 2148062 *
bloat-o-meter delta for this patchset + patchset with related shmem cleanups
bloat-o-meter: x86_64
add/remove: 4/3 grow/shrink: 5/6 up/down: 928/-939 (-11)
function old new delta
radix_tree_next_chunk - 499 +499
shmem_unuse 428 554 +126
shmem_radix_tree_replace 131 227 +96
find_get_pages_tag 354 419 +65
find_get_pages_contig 345 407 +62
find_get_pages 362 396 +34
__kstrtab_radix_tree_next_chunk - 22 +22
__ksymtab_radix_tree_next_chunk - 16 +16
__kcrctab_radix_tree_next_chunk - 8 +8
radix_tree_gang_lookup_slot 204 203 -1
static.shmem_xattr_set 384 381 -3
radix_tree_gang_lookup_tag_slot 208 191 -17
radix_tree_gang_lookup 231 187 -44
radix_tree_gang_lookup_tag 247 199 -48
shmem_unlock_mapping 278 190 -88
__lookup 217 - -217
__lookup_tag 242 - -242
radix_tree_locate_item 279 - -279
bloat-o-meter: i386
add/remove: 3/3 grow/shrink: 8/9 up/down: 1075/-1275 (-200)
function old new delta
radix_tree_next_chunk - 757 +757
shmem_unuse 352 449 +97
find_get_pages_contig 269 322 +53
shmem_radix_tree_replace 113 154 +41
find_get_pages_tag 277 318 +41
dcache_dir_lseek 426 458 +32
__kstrtab_radix_tree_next_chunk - 22 +22
vc_do_resize 968 977 +9
snd_pcm_lib_read1 725 733 +8
__ksymtab_radix_tree_next_chunk - 8 +8
netlbl_cipsov4_list 1120 1127 +7
find_get_pages 293 291 -2
new_slab 467 459 -8
bitfill_unaligned_rev 425 417 -8
radix_tree_gang_lookup_tag_slot 177 146 -31
blk_dump_cmd 267 229 -38
radix_tree_gang_lookup_slot 212 134 -78
shmem_unlock_mapping 221 128 -93
radix_tree_gang_lookup_tag 275 162 -113
radix_tree_gang_lookup 255 126 -129
__lookup 227 - -227
__lookup_tag 271 - -271
radix_tree_locate_item 277 - -277
This patch:
Implement a clean, simple and effective radix-tree iteration routine.
Iterating divided into two phases:
* lookup next chunk in radix-tree leaf node
* iterating through slots in this chunk
Main iterator function radix_tree_next_chunk() returns pointer to first
slot, and stores in the struct radix_tree_iter index of next-to-last slot.
For tagged-iterating it also constuct bitmask of tags for retunted chunk.
All additional logic implemented as static-inline functions and macroses.
Also adds radix_tree_find_next_bit() static-inline variant of
find_next_bit() optimized for small constant size arrays, because
find_next_bit() too heavy for searching in an array with one/two long
elements.
[akpm@linux-foundation.org: rework comments a bit]
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Tested-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__any_online_cpu() is not optimal and also unnecessary. So, replace its
use by faster cpumask_* operations.
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Venkatesh Pallipadi <venki@google.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove all #inclusions of asm/system.h preparatory to splitting and killing
it. Performed with the following command:
perl -p -i -e 's!^#\s*include\s*<asm/system[.]h>.*\n!!' `grep -Irl '^#\s*include\s*<asm/system[.]h>' *`
Signed-off-by: David Howells <dhowells@redhat.com>
Disintegrate asm/system.h for PowerPC.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
cc: linuxppc-dev@lists.ozlabs.org
There are situations where CONFIG_HAS_IOMEM is too restrictive.
For example CONFIG_MTD_NAND_NANDSIM depends on CONFIG_HAS_IOMEM
but it works perfectly fine if an architecture without io memory
just includes asm-generic/io.h or implements everything defined in it.
UML is such a corner case.
Signed-off-by: Richard Weinberger <richard@nod.at>
== stat_check.py
num = 0
with open("/proc/stat") as f:
while num < 1000 :
data = f.read()
f.seek(0, 0)
num = num + 1
==
perf shows
20.39% stat_check.py [kernel.kallsyms] [k] format_decode
13.41% stat_check.py [kernel.kallsyms] [k] number
12.61% stat_check.py [kernel.kallsyms] [k] vsnprintf
10.85% stat_check.py [kernel.kallsyms] [k] memcpy
4.85% stat_check.py [kernel.kallsyms] [k] radix_tree_lookup
4.43% stat_check.py [kernel.kallsyms] [k] seq_printf
This patch removes most of calls to vsnprintf() by adding num_to_str()
and seq_print_decimal_ull(), which prints decimal numbers without rich
functions provided by printf().
On my 8cpu box.
== Before patch ==
[root@bluextal test]# time ./stat_check.py
real 0m0.150s
user 0m0.026s
sys 0m0.121s
== After patch ==
[root@bluextal test]# time ./stat_check.py
real 0m0.055s
user 0m0.022s
sys 0m0.030s
[akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()]
[andrea@betterlinux.com: avoid breaking the ABI in /proc/stat]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrea Righi <andrea@betterlinux.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Glauber Costa <glommer@parallels.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Turner <pjt@google.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Allow the kernel builder to choose a crc32* algorithm for the kernel.
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Cc: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add self-test code for crc32c.
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Cc: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Reuse the existing crc32 code to stamp out a crc32c implementation.
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Bob Pearson <rpearson@systemfabricworks.com>
Cc: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add a comment at the top of crc32.c
[djwong@us.ibm.com: Minor changelog tweaks]
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add two changes that improve the performance of x86 systems
1. replace main loop with incrementing counter this change improves
the performance of the selftest by about 5-6% on Nehalem CPUs. The
apparent reason is that the compiler can use the loop index to perform
an indexed memory access. This is reported to make the performance of
PowerPC CPUs to get worse.
2. replace the rem_len loop with incrementing counter this change
improves the performance of the selftest, which has more than the usual
number of occurances, by about 1-2% on x86 CPUs. In actual work loads
the length is most often a multiple of 4 bytes and this code does not
get executed as often if at all. Again this change is reported to make
the performance of PowerPC get worse.
[djwong@us.ibm.com: Minor changelog tweaks]
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add slicing-by-8 algorithm to the existing slicing-by-4 algorithm. This
consists of:
- extend largest BITS size from 32 to 64
- extend tables from tab[4][256] to up to tab[8][256]
- Add code for inner loop.
[djwong@us.ibm.com: Minor changelog tweaks]
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
crc32.c provides a choice of one of several algorithms for computing the
LSB and LSB versions of the CRC32 checksum based on the parameters
CRC_LE_BITS and CRC_BE_BITS.
In the original version the values 1, 2, 4 and 8 respectively selected
versions of the alrogithm that computed the crc 1, 2, 4 and 32 bits as a
time.
This patch series adds a new version that computes the CRC 64 bits at a
time. To make things easier to understand the parameter has been
reinterpreted to actually stand for the number of bits processed in each
step of the algorithm so that the old value 8 has been replaced with the
value 32.
This also allows us to add in a widely used crc algorithm that computes
the crc 8 bits at a time called the Sarwate algorithm.
[djwong@us.ibm.com: Minor changelog tweaks]
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
crc32.c in its original version freely mixed u32, __le32 and __be32 types
which caused warnings from sparse with __CHECK_ENDIAN__. This patch fixes
these by forcing the types to u32.
[djwong@us.ibm.com: Minor changelog tweaks]
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Misc cleanup of lib/crc32.c and related files.
- remove unnecessary header files.
- straighten out some convoluted ifdef's
- rewrite some references to 2 dimensional arrays as 1 dimensional
arrays to make them correct. I.e. replace tab[i] with tab[0][i].
- a few trivial whitespace changes
- fix a warning in gen_crc32tables.c caused by a mismatch in the type of
the pointer passed to output table. Since the table is only used at
kernel compile time, it is simpler to make the table big enough to hold
the largest column size used. One cannot make the column size smaller
in output_table because it has to be used by both the le and be tables
and they can have different column sizes.
[djwong@us.ibm.com: Minor changelog tweaks]
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace the unit test provided in crc32.c, which doesn't have a makefile
and doesn't compile with current headers, with a simpler self test
routine that also gives a measure of performance and runs at module init
time. The self test option can be enabled through a configuration
option CONFIG_CRC32_SELFTEST.
The test stresses the pre and post loops and is thus not very realistic
since actual uses will likely have addresses and lengths that are at
least 4 byte aligned. However, the main loop is long enough so that the
performance is dominated by that loop.
The expected values for crc32_le and crc32_be were generated with the
original version of crc32.c using CRC_BITS_LE = 8 and CRC_BITS_BE = 8.
These values were then used to check all the values of the BITS
parameters in both the original and new versions.
The performance results show some variability from run to run in spite
of attempts to both warm the cache and reduce the amount of OS noise by
limiting interrutps during the test. To get comparable results and to
analyse options wrt performance the best time reported over a small
sample of runs has been taken.
[djwong@us.ibm.com: Minor changelog tweaks]
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Move a long comment from lib/crc32.c to Documentation/crc32.txt where it
will more likely get read.
Edited the resulting document to add an explanation of the slicing-by-n
algorithm.
[djwong@us.ibm.com: minor changelog tweaks]
[akpm@linux-foundation.org: fix typo, per George]
Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patchset (re)uses Bob Pearson's crc32 slice-by-8 code to stamp out
a software crc32c implementation. It removes the crc32c implementation
in crypto/ in favor of using the stamped-out one in lib/. There is also
a change to Kconfig so that the kernel builder can pick an
implementation best suited for the hardware.
The motivation for this patchset is that I am working on adding full
metadata checksumming to ext4. As far as performance impact of adding
checksumming goes, I see nearly no change with a standard mail server
ffsb simulation. On a test that involves only file creation and
deletion and extent tree writes, I see a drop of about 50 pcercent with
the current kernel crc32c implementation; this improves to a drop of
about 20 percent with the enclosed crc32c code.
When metadata is usually a small fraction of total IO, this new
implementation doesn't help much because metadata is usually a small
fraction of total IO. However, when we are doing IO that is almost all
metadata (such as rm -rf'ing a tree), then this patch speeds up the
operation substantially.
Incidentally, given that iscsi, sctp, and btrfs also use crc32c, this
patchset should improve their speed as well. I have not yet quantified
that, however. This latest submission combines Bob's patches from late
August 2011 with mine so that they can be one coherent patch set.
Please excuse my inability to combine some of the patches; I've been
advised to leave Bob's patches alone and build atop them instead. :/
Since the last posting, I've also collected some crc32c test results on
a bunch of different x86/powerpc/sparc platforms. The results can be
viewed here: http://goo.gl/sgt3i ; the "crc32-kern-le" and "crc32c"
columns describe the performance of the kernel's current crc32 and
crc32c software implementations. The "crc32c-by8-le" column shows
crc32c performance with this patchset applied. I expect crc32
performance to be roughly the same.
The two _boost columns at the right side of the spreadsheet shows how much
faster the new implementation is over the old one. As you can see, crc32
rises substantially, and crc32c experiences a huge increase.
This patch:
- remove trailing whitespace from lib/crc32.c
- remove trailing whitespace from lib/crc32defs.h
[djwong@us.ibm.com: changelog tweaks]
Signed-off-by: Bob Pearson <rpearson@systemfabricworks.com>
Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Introduce prio_set_parent() to abstract the operation which is used to
attach the node to its parent.
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In current code, the deleted-node is recorded from first to last,
actually, we can directly attach these node on 'node' we will insert as
the left child, it can let the code more readable.
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Introduce iter_walk_down()/iter_walk_up() to remove the common code
between prio_tree_left() and prio_tree_right().
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove the code since 'node' has already been initialized in the begin of
the function
Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
- Generate a 64-bit pattern more efficiently
memchr_inv needs to generate a 64-bit pattern filled with a target
character. The operation can be done by more efficient way.
- Don't call the slow check_bytes() if the memory area is 64-bit aligned
memchr_inv compares contiguous 64-bit words with the 64-bit pattern as
much as possible. The outside of the region is checked by check_bytes()
that scans for each byte. Unfortunately, the first 64-bit word is
unexpectedly scanned by check_bytes() even if the memory area is aligned
to a 64-bit boundary.
Both changes were originally suggested by Eric Dumazet.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
ARCH_HAS_NMI_WATCHDOG is a macro defined by arch, but config
HARDLOCKUP_DETECTOR depends on it. This is wrong, ARCH_HAS_NMI_WATCHDOG
has to be a Kconfig config, and arch's need it should select it
explicitly.
Signed-off-by: WANG Cong <xiyou.wangcong@gmail.com>
Acked-by: Don Zickus <dzickus@redhat.com>
Acked-by: Mike Frysinger <vapier@gentoo.org>
Cc: David Howells <dhowells@redhat.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Get rid of INLINE_SPIN_UNLOCK entirely replacing it with
UNINLINE_SPIN_UNLOCK instead of the reverse meaning.
Whoever wants to change the default spinlock inlining
behavior and uninline the spinlocks for some weird reason,
such as spinlock debugging, paravirt etc. can now all just
select UNINLINE_SPIN_UNLOCK
Original discussion at: https://lkml.org/lkml/2012/3/21/357
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: linux-mips@linux-mips.org
Link: http://lkml.kernel.org/r/20120322095502.30866.75756.sendpatchset@codeblue
[ tidied up the changelog a bit ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Make one small adjustment to idr_get_next(): take the height from the top
layer (stable under RCU) instead of from the root (unprotected by RCU), as
idr_find() does: so that it can be used with RCU locking. Copied comment
on RCU locking from idr_find().
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In some configurations, jiffies may be undefined in
lib/dynamic_queue_limits.c. Adding include of jiffies.h to avoid
this.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The queue handling in the udev daemon assumes that the events are
ordered.
Before this patch uevent_seqnum is incremented under sequence_lock,
than an event is send uner uevent_sock_mutex. I want to say that code
contained a window between incrementing seqnum and sending an event.
This patch locks uevent_sock_mutex before incrementing uevent_seqnum.
v2: delete sequence_lock, uevent_seqnum is protected by uevent_sock_mutex
v3: unlock the mutex before the goto exit
Thanks for Kay for the comments.
Signed-off-by: Andrew Vagin <avagin@openvz.org>
Tested-By: Kay Sievers <kay.sievers@vrfy.org>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
For files only using THIS_MODULE and/or EXPORT_SYMBOL, map
them onto including export.h -- or if the file isn't even
using those, then just delete the include. Fix up any implicit
include dependencies that were being masked by module.h along
the way.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
kasprintf() (and potentially other functions that I didn't run across so
far) want to evaluate argument lists twice. Caring to do so for the
primary list is obviously their job, but they can't reasonably be
expected to check the format string for instances of %pV, which however
need special handling too: On architectures like x86-64 (as opposed to
e.g. ix86), using the same argument list twice doesn't produce the
expected results, as an internally managed cursor gets updated during
the first run.
Fix the problem by always acting on a copy of the original list when
handling %pV.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
debugobjects is now printing a warning when a fixup for a NOTAVAILABLE
object is run. This causes the selftest to fail like:
ODEBUG: selftest warnings failed 4 != 5
We could just increase the number of warnings that the selftest is
expecting to see because that is actually what has changed. But, it turns
out that fixup_activate() was written with inverted logic and thus a fixup
for a static object returned 1 indicating the object had been fixed, and 0
otherwise. Fix the logic to be correct and update the counts to reflect
that nothing needed fixing for a static object.
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With bug.h currently living right in linux/kernel.h there
are files that use BUG_ON and friends but are not including
the header explicitly. Fix them up so we can remove the
presence in kernel.h file.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
A pending header cleanup will cause this to show up as:
lib/average.c:38: error: 'TAINT_WARN' undeclared (first use in this function)
lib/list_debug.c:24: error: 'TAINT_WARN' undeclared (first use in this function)
and TAINT_WARN comes from include/linux/kernel.h file.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
There have been situations where RCU CPU stall warnings were caused by
issues in scheduling-clock timer initialization. To make it easier to
track these down, this commit causes the RCU CPU stall-warning messages
to print out the number of scheduling-clock interrupts taken in the
current grace period for each stalled CPU.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The RCU_TRACE kernel parameter has always been intended for debugging,
not for production use. Formalize this by moving RCU_TRACE from
init/Kconfig to lib/Kconfig.debug.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The soft and hard lockup thresholds have changed so the
corresponding Kconfig entries need to be updated accordingly.
Add a reference to watchdog_thresh while at it.
Signed-off-by: Fernando Luis Vazquez Cao <fernando@oss.ntt.co.jp>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Link: http://lkml.kernel.org/r/1328827342-6253-2-git-send-email-dzickus@redhat.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
_parse_integer() does one or two division instructions (which are slow)
per digit parsed to perform the overflow check.
Furthermore, these are particularly expensive examples of division
instruction as the number of clock cycles required to complete them may
go up with the position of the most significant set bit in the dividend:
if (*res > div_u64(ULLONG_MAX - val, base))
which is as maximal as possible.
Worse, on 32-bit arches, more than one of these division instructions
may be required per digit.
So, assuming we don't support a base of more than 16, skip the check if the
top nibble of the result is not set at this point.
Signed-off-by: David Howells <dhowells@redhat.com>
[ Changed it to not dereference the pointer all the time - even if the
compiler can and does optimize it away, the code just looks cleaner.
And edited the top nybble test slightly to make the code generated on
x86-64 better in the loop - test against a hoisted constant instead of
shifting and testing the result ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This copy of longlong.h is extremely dated and results in compile
errors on sparc32 when MPILIB is enabled, copy over the more uptodate
implementation from arch/sparc/math/sfp-util_32.h
Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: James Morris <jmorris@namei.org>
Both sparc 32-bit's software divide assembler and MPILIB provide
clz_tab[] with identical contents.
Break it out into a seperate object file and select it when
SPARC32 or MPILIB is set.
Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: James Morris <jmorris@namei.org>
mpi_read_from_buffer() return value must not be NULL.
Signed-off-by: Dmitry Kasatkin <dmitry.kasatkin@intel.com>
Reviewed-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: James Morris <jmorris@namei.org>
Comment explains that existing clients do not call this function
with dsize == 0, which means that 1/0 should not happen.
Signed-off-by: Dmitry Kasatkin <dmitry.kasatkin@intel.com>
Reviewed-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: James Morris <jmorris@namei.org>
Buggy client might pass zero nlimbs which is meaningless.
Added check for zero length.
Signed-off-by: Dmitry Kasatkin <dmitry.kasatkin@intel.com>
Reviewed-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: James Morris <jmorris@namei.org>
Removed useless 'is_valid' variable in pkcs_1_v1_5_decode_emsa(),
which was inhereted from original code. Client now uses return value
to check for an error.
Signed-off-by: Dmitry Kasatkin <dmitry.kasatkin@intel.com>
Reviewed-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: James Morris <jmorris@namei.org>
Jesper Juhl