summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* kbuild: move -fno-dwarf2-cfi-asm to powerpc onlyAndi Kleen2010-02-052-3/+5
| | | | | | | | | | | | | | | | | | | | | Better dwarf2 unwind information is a good thing, it allows better debugging with kgdb and crash and helps systemtap. Commit 003086497f07f7f1e67c0c295e261740f822b377 ("Build with -fno-dwarf2-cfi-asm") disabled some CFI information globally to work around a module loader bug on powerpc. But this disables the better unwind tables for all architectures, not just powerpc. Move the workaround to powerpc and also add a suitable comment that's it really a workaround. This improves dwarf2 unwind tables on x86 at least. Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Michal Marek <mmarek@suse.cz>
* markup_oops.pl: minor fixesHui Zhu2010-02-051-5/+5
| | | | | | | | | | | | | | 1. Fix a little format issue. 2. Check the return of "Getopt::Long::GetOptions". Output usage and exit if it get error. 3. Change $ARGV[$#ARGV] to $ARGV[0]. 4. Change the code which get $modulefile from modinfo. Replace the pipeline with `modinfo -F filename $module`. 4. Change usage from "Specify the module directory name" to "Specify the module filename". Signed-off-by: Hui Zhu <teawater@gmail.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* markup_oops.pl: add options to improve cross-sompilation environmentsHui Zhu2010-02-051-13/+36
| | | | | | | | | | | | | | | | | | | | | | | | | | | The markup_oops.pl have 3 troubles to support cross-compiler environment: 1. It use objdump directly. 2. It use modinfo to get the message of module. 3. It use hex function that cannot support 64-bit number in 32-bit arch. This patch add 3 options to markup_oops.pl: 1. -c CROSS_COMPILE Specify the prefix used for toolchain. 2. -m MODULE_DIRNAME Specify the module directory name. 3. Change hex function to Math::BigInt->from_hex. After this patch, parse the x8664 oops in x86, we can: cat amd64m | perl ~/kernel/tmp/m.pl -c /home/teawater/kernel/bin/x8664- -m ./e.ko vmlinux Thanks, Hui Signed-off-by: Hui Zhu <teawater@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: ozan@pardus.org.tr Cc: Matthew Wilcox <willy@linux.intel.com> Acked-by: WANG Cong <xiyou.wangcong@gmail.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* Merge branch 'modpost' of git://git.pengutronix.de/git/ukl/linux-2.6 into ↵Michal Marek2010-02-021-64/+88
|\ | | | | | | | | | | | | kbuild/for-next Acked-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Michal Marek <mmarek@suse.cz>
| * modpost: don't allow *driver to reference .init.*Uwe Kleine-König2010-01-301-1/+10
| | | | | | | | Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
| * modpost: make symbol white list a per mismatch type variableUwe Kleine-König2010-01-301-18/+31
| | | | | | | | Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
| * modpost: remove now unused NO_MISMATCH constantUwe Kleine-König2010-01-301-3/+0
| | | | | | | | Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
| * modpost: pass around const struct sectioncheck * instead of enum mismatchUwe Kleine-König2010-01-301-7/+9
| | | | | | | | | | | | This prepares having a per-check whitelist of symbol names. Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
| * modpost: give most mismatch constants a better nameUwe Kleine-König2010-01-301-28/+28
| | | | | | | | Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
| * modpost: define ALL_XXX{IN,EX}IT_SECTIONSUwe Kleine-König2010-01-291-6/+9
| | | | | | | | Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
| * modpost: members of *driver structs should not point to __init functionsUwe Kleine-König2010-01-291-1/+1
| | | | | | | | | | | | | | | | Either the functions referred to in a driver struct should live in .devinit or the driver should be registered using platform_driver_probe (or equivalent for different driver types) with ->probe being NULL. Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
* | MAINTAINERS: add a few more patterns to kbuildMichal Marek2010-02-021-1/+4
| | | | | | | | | | | | | | Also, add a note that "unmaintained" files below scripts/ should go via the kbuild tree (best current practice). Signed-off-by: Michal Marek <mmarek@suse.cz>
* | scripts: use %_tmppath in "make rpm-pkg"John Saalwaechter2010-02-021-1/+1
| | | | | | | | | | | | | | | | | | | | The mkspec script hardcodes "/var/tmp" into the generated rpm spec file's BuildRoot. The user, however, may have a custom setting for %_tmppath, which should be used in BuildRoot. This patch changes mkspec's BuildRoot output to appropriately use %_tmppath. Signed-off-by: John Saalwaechter <saalwaechter@gmail.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | markup_oops.pl: fix for faulting instruction in the first line of a rangeHui Zhu2010-02-021-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I got a "No matching code found" when I use markup_oops.pl parse a error in a x86_64 module. cat e.c int init_module(void) { char *buf = 0; buf[0] = 3; return 0; } void cleanup_module(void) { //char *buf = 0; //buf[0] = 3; } MODULE_AUTHOR("Hui Zhu"); MODULE_LICENSE("GPL"); 0000000000000000 <init_module>: init_module(): /home/teawater/study/kernel/stack2core/example/e.c:10 0: c6 04 25 00 00 00 00 movb $0x3,0x0 7: 03 /home/teawater/study/kernel/stack2core/example/e.c:13 8: 31 c0 xor %eax,%eax a: c3 retq b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 0000000000000010 <cleanup_module>: cleanup_module(): /home/teawater/study/kernel/stack2core/example/e.c:20 10: f3 c3 repz retq 12: 90 nop 13: 90 nop Disassembly of section .modinfo: This is because the faulting instruction "movb $0x3,0x0" is the first line of the range. In the markup_oops.pl: main::(./scripts/markup_oops.pl:245): 245: if (InRange($1, $target)) { DB<2> p $line ffffffffa001b000: c6 04 25 00 00 00 00 movb $0x3,0x0 DB<3> p $counter 0 It just set $center in next loop. So it cannot get the $center. And even if $center is set to the right value 0. if ($center == 0) { print "No matching code found \n"; exit; } The first line $center will be 0, so I change the default value to -1. Signed-off-by: Hui Zhu <teawater@gmail.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | scripts: change scripts to use system python instead of envDon Zickus2010-02-023-3/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Just a small change to a couple of scripts to go from #!/usr/bin/env python to #!/usr/bin/python This shouldn't effect anyone, unless they don't install python there. In preparation for python3, Fedora is doing a big push to change the scripts to use the system python. This allows developers to put the python3 in their path without fear of breaking existing scripts. Now I am pretty sure anyone using python3 for testing purposes will probably not run any of the scripts I changed, but Fedora has this automated tool that checks for this stuff so I thought I would try to push it upstream. Signed-off-by: Don Zickus <dzickus@redhat.com> Acked-by: WANG Cong <xiyou.wangcong@gmail.com> Acked-by: Jarod Wilson <jarod@redhat.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | scripts/kallsyms: suppress build warningHimanshu Chauhan2010-02-021-2/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Suppress a warn_unused_result warning. fgets is called as a part of error handling. It is called just to drop a line and return immediately. read_map is reading the file in a loop and read_symbol reads line by line. So I think there is no point in using return value for useful checking. Other checks like 3 items were returned or !EOF have already been done. Signed-off-by: Himanshu Chauhan <hschauhan@nulltrace.org> Cc: WANG Cong <xiyou.wangcong@gmail.com> Cc: Michal Marek <mmarek@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | scripts/mkcompile_h: don't test for hardcoded pathsMichal Marek2010-02-021-3/+2
| | | | | | | | | | | | | | | | | | | | Don't test for /bin/{dnsdomainname,domainname}, simply try to execute the command and check if it returned something. Reported-by: Glenn Sommer <glemsom@gmail.com> Acked-by: WANG Cong <xiyou.wangcong@gmail.com> Tested-by: Glenn Sommer <glemsom@gmail.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | Improve kconfig symbol hashingAndi Kleen2010-02-024-17/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | While looking for something else I noticed that the symbol hash function used by kconfig is quite poor. It doesn't use any of the standard hash techniques but simply adds up the string and then uses power of two masking, which is both known to perform poorly. The current x86 kconfig has over 7000 symbols. When I instrumented it showed that the minimum hash chain length was 16 and a significant number of them was over 30. It didn't help that the hash table size was only 256 buckets. This patch increases the hash table size to a larger prime and switches to a FNV32 hash. I played around with a couple of hash functions, but that one seemed to perform best with reasonable hash table sizes. Increasing the hash table size even further didn't seem like a good idea, because there are a couple of global walks which walk the complete hash table. I also moved the unnamed bucket to 0. It's still the longest of all the buckets (44 entries), but hopefully it's not often hit except for the global walk which doesn't care. The result is a much nicer distribution: (first column bucket length, second number of buckets with that length) 1: 3505 2: 1236 3: 294 4: 52 5: 3 47: 1 <--- this is the unnamed symbols bucket There are still some 5+ buckets, but increasing the hash table even more would be likely not worth it. This also cleans up the code slightly by removing hard coded magic numbers. I didn't notice a big performance difference either way on my Nehalem system, but I presume it'll help somewhat on slower systems. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | Makefile: Document ability to make file.lst and file.SJoe Perches2010-02-021-1/+3
| | | | | | | | | | | | Signed-off-by: Joe Perches <joe@perches.com> Acked-by: WANG Cong <xiyou.wangcong@gmail.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | kbuild: improve version string logicDavid Rientjes2010-02-021-16/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The LOCALVERSION= string passed to "make" will now always be appended to the kernel version after CONFIG_LOCALVERSION, if it exists, regardless of whether CONFIG_LOCALVERSION_AUTO is set or not. This allows users to uniquely identify their kernel builds with a string. If CONFIG_LOCALVERSION_AUTO is enabled, the unique SCM tag reported by setlocalversion (or .scmversion) is appended to the kernel version, if it exists. When CONFIG_LOCALVERSION_AUTO is not enabled, a `+' is appended to the kernel version to represent that the kernel has been revised since the last release unless "make LOCALVERSION=" was used to uniquely identify the build. The end result is this: - when LOCALVERSION= is passed to "make", it is appended to the kernel version, - when CONFIG_LOCALVERSION_AUTO is enabled, a unique SCM identifier is appended if the respository has been revised beyond a tagged commit, and - when CONFIG_LOCALVERSION_AUTO is disabled, a `+' is appended if the repository has been revised beyond a tagged commit and LOCALVERSION= was not passed to "make". Examples: With CONFIG_LOCALVERSION_AUTO: "make" results in v2.6.32-rc4-00149-ga3ccf63. If there are uncommited changes to the respository, it results in v2.6.32-rc4-00149-ga3ccf63-dirty. If "make LOCALVERSION=kbuild" were used, it results in v2.6.32-rc4-kbuild-00149-ga3ccf63-dirty. Without CONFIG_LOCALVERSION_AUTO, "make" results in v2.6.32-rc4+ unless the repository is at the Linux v2.6.32-rc4 commit (in which case the version would be v2.6.32-rc4). If "make LOCALVERSION=kbuild" were used, it results in v2.6.32-rc4-kbuild. Also renames variables such as localver-auto and _localver-auto to more accurately describe what they represent: localver-extra and scm-identifier, respectively. Signed-off-by: David Rientjes <rientjes@google.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | nconfig: minor fixNir Tzachar2010-02-021-3/+3
| | | | | | | | | | | | | | | | | | | | This patch fixes two problems reported by Jan Engelhardt: 1) Border is now properly placed, to always be visible 2) Long menu items are properly displayed Reported-by: Jan Engelhardt <jengelh@medozas.de> Signed-off-by: Nir Tzachar <nir.tzachar@gmail.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | nconfig: mark local functions as suchMichal Marek2010-02-022-15/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | scripts/kconfig/nconf.gui.c:23: warning: no previous prototype for 'set_normal_colors' scripts/kconfig/nconf.gui.c:68: warning: no previous prototype for 'normal_color_theme' scripts/kconfig/nconf.gui.c:100: warning: no previous prototype for 'no_colors_theme' scripts/kconfig/nconf.c:455: warning: no previous prototype for 'process_special_keys' scripts/kconfig/nconf.c:487: warning: no previous prototype for 'get_next_hot' scripts/kconfig/nconf.c:506: warning: no previous prototype for 'canbhot' scripts/kconfig/nconf.c:514: warning: no previous prototype for 'is_hot' scripts/kconfig/nconf.c:522: warning: no previous prototype for 'make_hot' scripts/kconfig/nconf.c:582: warning: no previous prototype for 'item_make' scripts/kconfig/nconf.c:626: warning: no previous prototype for 'item_add_str' scripts/kconfig/nconf.c:656: warning: no previous prototype for 'item_tag' scripts/kconfig/nconf.c:668: warning: no previous prototype for 'curses_item_index' scripts/kconfig/nconf.c:673: warning: no previous prototype for 'item_data' scripts/kconfig/nconf.c:684: warning: no previous prototype for 'item_is_tag' scripts/kconfig/nconf.c:691: warning: no previous prototype for 'set_config_filename' Signed-off-by: Michal Marek <mmarek@suse.cz>
* | kconfig: new configuration interface (nconfig)nir.tzachar@gmail.com2010-02-0210-20/+2314
| | | | | | | | | | | | | | | | | | | | | | | | | | This patch was inspired by the kernel projects page, where an ncurses replacement for menuconfig was mentioned (by Sam Ravnborg). Building on menuconfig, this patch implements a more modern look interface using ncurses and ncurses' satellite libraries (menu, panel, form). The implementation does not depend on lxdialog, which is currently distributed with the kernel. Signed-off-by: Nir Tzachar <nir.tzachar@gmail.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | genksyms: close ref_file after useAlexander Beregalov2010-02-021-1/+3
| | | | | | | | | | | | | | It is the last place when the file is read, so close it. Signed-off-by: Alexander Beregalov <a.beregalov@gmail.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | menuconfig: wrap long help linesVadim Bendebury (вб)2010-02-024-2/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Help text for certain config options is very extensive (the text includes the names of all other options the option in question depends on). Long lines are not wrapped, making it impossible to see the list without scrolling horizontally. This patch adds some logic which wraps help screen lines at word boundaries to prevent truncating. Tested by running ARCH=powerpc make menuconfig O=/tmp/build which shows that the long lines are now wrapped, and ARCH=powerpc make xconfig O=/tmp/build to demonstrate that it still compiles and operates as expected. Signed-off-by: Vadim Bendebury <vbendeb@google.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | scripts: add ARM support to decodecodeRabin Vincent2010-02-021-13/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds support for decoding ARM oopses to scripts/decodecode. The following things are handled: - ARCH and CROSS_COMPILE environment variables are respected. - The Code: in x86 oopses is in bytes, while it is in either words (4 bytes) or halfwords for ARM. - Some versions of ARM objdump refuse to disassemble instructions generated by literal constants (".word 0x..."). The workaround is to strip the object file first. - The faulting instruction is marked (liked so) in ARM, but <like so> in x86. - ARM mnemonics may include characters such as [] which need to be escaped before being passed to sed for the "<- trapping instruction" substitution. Signed-off-by: Rabin Vincent <rabin@rab.in> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | kconfig CROSS_COMPILE optionRoland McGrath2010-02-022-0/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This adds CROSS_COMPILE as a kconfig string so you can store it in .config. Then you can use plain "make" in the configured kernel build directory to do the right cross compilation without setting the command-line or environment variable every time. With this, you can set up different build directories for different kernel configurations, whether native or cross-builds, and then use the simple: make -C /build/dir M=module-source-dir idiom to build modules for any given target kernel, indicating which one by nothing but the build directory chosen. I tried a version that defaults the string with env="CROSS_COMPILE" so that in a "make oldconfig" with CROSS_COMPILE in the environment you can just hit return to store the way you're building it. But the kconfig prompt for strings doesn't give you any way to say you want an empty string instead of the default, so I punted that. Signed-off-by: Roland McGrath <roland@redhat.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Anibal Monsalve Salazar <anibal@debian.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Michal Marek <mmarek@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | kbuild: Fix linking error built-in.o no such file or directoryJiafu He2010-02-021-1/+1
| | | | | | | | | | | | | | | | | | | | This patch fixes the link error "built-in.o: no such file or directory". The problem happens if "dirx/Makefile" contains only "obj-m += diry/ dirz/" and the empty "dirx/built-in.o" is missing. Adding $(subdir-m) into check for builtin-target fixes this error. Signed-off-by: Jiafu He <jay@goldhive.com> Signed-off-by: Michal Marek <mmarek@suse.cz>
* | Linux 2.6.33-rc6v2.6.33-rc6Linus Torvalds2010-01-291-1/+1
| |
* | mfd: Fix asic3 buildDmitry Artamonow2010-01-291-1/+1
|/ | | | | | | asic3 also needs tmio_core or otherwise will fail to build. Signed-off-by: Dmitry Artamonow <mad_soft@inbox.ru> Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
* Merge branch 'for-linus' of ↵Linus Torvalds2010-01-297-69/+198
|\ | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input: Input: update multi-touch protocol documentation Input: add the ABS_MT_PRESSURE event Input: winbond-cir - remove dmesg spam Input: lifebook - add another Lifebook DMI signature Input: ad7879 - support auxiliary GPIOs via gpiolib
| * Input: update multi-touch protocol documentationHenrik Rydberg2010-01-281-8/+40
| | | | | | | | | | | | | | | | | | | | | | This patch documents a new ABS_MT parameter and adds further text to clarify some points around the MT protocol. Requested-by: Yoonyoung Shim <jy0922.shim@samsung.com> Requested-by: Mika Kuoppala <mika.kuoppala@nokia.com> Requested-by: Peter Hutterer <peter.hutterer@who-t.net> Signed-off-by: Henrik Rydberg <rydberg@euromail.se> Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
| * Input: add the ABS_MT_PRESSURE eventHenrik Rydberg2010-01-282-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | For pressure-based multi-touch devices, a direct way to send sensor intensity data per finger is needed. This patch adds the ABS_MT_PRESSURE event to the MT protocol. Requested-by: Yoonyoung Shim <jy0922.shim@samsung.com> Requested-by: Mika Kuoppala <mika.kuoppala@nokia.com> Requested-by: Peter Hutterer <peter.hutterer@who-t.net> Signed-off-by: Henrik Rydberg <rydberg@euromail.se> Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
| * Input: winbond-cir - remove dmesg spamDavid Härdeman2010-01-281-1/+1
| | | | | | | | | | | | | | | | | | | | I missed converting one dev_info call to deb_dbg before submitting the driver. Without this change, a message will be printed to dmesg for each button press if a RC6 remote is used. Signed-off-by: David Härdeman <david@hardeman.nu> Cc: stable <stable@kernel.org> Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
| * Input: lifebook - add another Lifebook DMI signatureJon Dodgson2010-01-281-0/+6
| | | | | | | | | | | | | | There are many many ways one can capitalize "Lifebook B Series"... Signed-off-by: Jon Dodgson <crayzeejon@gmail.com> Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
| * Input: ad7879 - support auxiliary GPIOs via gpiolibMichael Hennerich2010-01-192-60/+149
| | | | | | | | | | | | | | | | | | Drop the simple fancy sysfs hooks for the aux GPIOs and expose these via the gpiolib interface so that other drivers can use them. Signed-off-by: Michael Hennerich <michael.hennerich@analog.com> Signed-off-by: Mike Frysinger <vapier@gentoo.org> Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
* | mm: fix migratetype bug which slowed swappingHugh Dickins2010-01-291-2/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After memory pressure has forced it to dip into the reserves, 2.6.32's 5f8dcc21211a3d4e3a7a5ca366b469fb88117f61 "page-allocator: split per-cpu list into one-list-per-migrate-type" has been returning MIGRATE_RESERVE pages to the MIGRATE_MOVABLE free_list: in some sense depleting reserves. Fix that in the most straightforward way (which, considering the overheads of alternative approaches, is Mel's preference): the right migratetype is already in page_private(page), but free_pcppages_bulk() wasn't using it. How did this bug show up? As a 20% slowdown in my tmpfs loop kbuild swapping tests, on PowerMac G5 with SLUB allocator. Bisecting to that commit was easy, but explaining the magnitude of the slowdown not easy. The same effect appears, but much less markedly, with SLAB, and even less markedly on other machines (the PowerMac divides into fewer zones than x86, I think that may be a factor). We guess that lumpy reclaim of short-lived high-order pages is implicated in some way, and probably this bug has been tickling a poor decision somewhere in page reclaim. But instrumentation hasn't told me much, I've run out of time and imagination to determine exactly what's going on, and shouldn't hold up the fix any longer: it's valid, and might even fix other misbehaviours. Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | Merge git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstableLinus Torvalds2010-01-297-30/+36
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: Btrfs: check total number of devices when removing missing Btrfs: check return value of open_bdev_exclusive properly Btrfs: do not mark the chunk as readonly if in degraded mode Btrfs: run orphan cleanup on default fs root Btrfs: fix a memory leak in btrfs_init_acl Btrfs: Use correct values when updating inode i_size on fallocate Btrfs: remove tree_search() in extent_map.c Btrfs: Add mount -o compress-force
| * | Btrfs: check total number of devices when removing missingJosef Bacik2010-01-281-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If you have a disk failure in RAID1 and then add a new disk to the array, and then try to remove the missing volume, it will fail. The reason is the sanity check only looks at the total number of rw devices, which is just 2 because we have 2 good disks and 1 bad one. Instead check the total number of devices in the array to make sure we can actually remove the device. Tested this with a failed disk setup and with this test we can now run btrfs-vol -r missing /mount/point and it works fine. Signed-off-by: Josef Bacik <josef@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * | Btrfs: check return value of open_bdev_exclusive properlyJosef Bacik2010-01-281-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Hit this problem while testing RAID1 failure stuff. open_bdev_exclusive returns ERR_PTR(), not NULL. So change the return value properly. This is important if you accidently specify a device that doesn't exist when trying to add a new device to an array, you will panic the box dereferencing bdev. Signed-off-by: Josef Bacik <josef@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * | Btrfs: do not mark the chunk as readonly if in degraded modeJosef Bacik2010-01-281-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If a RAID setup has chunks that span multiple disks, and one of those disks has failed, btrfs_chunk_readonly will return 1 since one of the disks in that chunk's stripes is dead and therefore not writeable. So instead if we are in degraded mode, return 0 so we can go ahead and allocate stuff. Without this patch all of the block groups in a RAID1 setup will end up read-only, which will mean we can't add new disks to the array since we won't be able to make allocations. Signed-off-by: Josef Bacik <josef@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * | Btrfs: run orphan cleanup on default fs rootJosef Bacik2010-01-282-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch revert's commit 6c090a11e1c403b727a6a8eff0b97d5fb9e95cb5 Since it introduces this problem where we can run orphan cleanup on a volume that can have orphan entries re-added. Instead of my original fix, Yan Zheng pointed out that we can just revert my original fix and then run the orphan cleanup in open_ctree after we look up the fs_root. I have tested this with all the tests that gave me problems and this patch fixes both problems. Thanks, Signed-off-by: Josef Bacik <josef@redhat.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * | Btrfs: fix a memory leak in btrfs_init_aclYang Hongyang2010-01-281-0/+1
| | | | | | | | | | | | | | | | | | | | | In btrfs_init_acl() cloned acl is not released Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * | Btrfs: Use correct values when updating inode i_size on fallocateAneesh Kumar K.V2010-01-281-4/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | commit f2bc9dd07e3424c4ec5f3949961fe053d47bc825 Author: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Date: Wed Jan 20 12:57:53 2010 +0530 Btrfs: Use correct values when updating inode i_size on fallocate Even though we allocate more, we should be updating inode i_size as per the arguments passed Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * | Btrfs: remove tree_search() in extent_map.cMiao Xie2010-01-281-14/+0
| | | | | | | | | | | | | | | | | | | | | | | | This patch removes tree_search() in extent_map.c because it is not called by anything. Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
| * | Btrfs: Add mount -o compress-forceChris Mason2010-01-283-2/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The default btrfs mount -o compress mode will quickly back off compressing a file if it notices that compression does not reduce the size of the data being written. This can save considerable CPU because all future writes to the file go through uncompressed. But some files are both very large and have mixed data stored in them. In that case, we want to add the ability to always try compressing data before writing it. This commit adds mount -o compress-force. A later commit will add a new inode flag that does the same thing. Signed-off-by: Chris Mason <chris.mason@oracle.com>
* | | sparc: TIF_ABI_PENDING bit removalDavid Miller2010-01-293-21/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | Here are the sparc bits to remove TIF_ABI_PENDING now that set_personality() is called at the appropriate place in exec. Signed-off-by: David S. Miller <davem@davemloft.net> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | | x86: get rid of the insane TIF_ABI_PENDING bitH. Peter Anvin2010-01-295-23/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Now that the previous commit made it possible to do the personality setting at the point of no return, we do just that for ELF binaries. And suddenly all the reasons for that insane TIF_ABI_PENDING bit go away, and we can just make SET_PERSONALITY() just do the obvious thing for a 32-bit compat process. Everything becomes much more straightforward this way. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | | Split 'flush_old_exec' into two functionsLinus Torvalds2010-01-2910-41/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 'flush_old_exec()' is the point of no return when doing an execve(), and it is pretty badly misnamed. It doesn't just flush the old executable environment, it also starts up the new one. Which is very inconvenient for things like setting up the new personality, because we want the new personality to affect the starting of the new environment, but at the same time we do _not_ want the new personality to take effect if flushing the old one fails. As a result, the x86-64 '32-bit' personality is actually done using this insane "I'm going to change the ABI, but I haven't done it yet" bit (TIF_ABI_PENDING), with SET_PERSONALITY() not actually setting the personality, but just the "pending" bit, so that "flush_thread()" can do the actual personality magic. This patch in no way changes any of that insanity, but it does split the 'flush_old_exec()' function up into a preparatory part that can fail (still called flush_old_exec()), and a new part that will actually set up the new exec environment (setup_new_exec()). All callers are changed to trivially comply with the new world order. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | | Merge branch 'for-linus' of ↵Linus Torvalds2010-01-2810-58/+62
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6 * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: Fix failure exit in ipathfs fix oops in fs/9p late mount failure fix leak in romfs_fill_super() get rid of pointless checks after simple_pin_fs() Fix failure exits in bfs_fill_super() fix affs parse_options() Fix remount races with symlink handling in affs Fix a leak in affs_fill_super()
OpenPOWER on IntegriCloud