- 05 Mar, 2008 40 commits
-
-
Hugh Dickins authored
Ever since the VM_BUG_ON(page_get_page_cgroup(page)) (now Bad page state) went into page freeing, I've hit it from time to time in testing on some machines, sometimes only after many days. Recently found a machine which could usually produce it within a few hours, which got me there at last. The culprit is mem_cgroup_move_lists, whose locking is inadequate; and the arrangement of structures was such that you got page_cgroups from the lru list neatly put on to SLUB's freelist. Kamezawa-san identified the same hole independently. The main problem was that it was missing the lock_page_cgroup it needs to safely page_get_page_cgroup; but it's tricky to go beyond that too, and I couldn't do it with SLAB_DESTROY_BY_RCU as I'd expected. See the code for comments on the constraints. This patch immediately gets replaced by a simpler one from Hirokazu-san; but is it just foolish pride that tells me to put this one on record, in case we need to come back to it later? Signed-off-by:
Hugh Dickins <hugh@veritas.com> Cc: David Rientjes <rientjes@google.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by:
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hirokazu Takahashi <taka@valinux.co.jp> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Cc: Paul Menage <menage@google.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Hugh Dickins authored
mem_cgroup_uncharge_page does css_put on the mem_cgroup before uncharging from it, and before removing page_cgroup from one of its lru lists: isn't there a danger that struct mem_cgroup memory could be freed and reused before completing that, so corrupting something? Never seen it, and for all I know there may be other constraints which make it impossible; but let's be defensive and reverse the ordering there. mem_cgroup_force_empty_list is safe because there's an extra css_get around all its works; but even so, change its ordering the same way round, to help get in the habit of doing it like this. Signed-off-by:
-
Hugh Dickins authored
Remove clear_page_cgroup: it's an unhelpful helper, see for example how mem_cgroup_uncharge_page had to unlock_page_cgroup just in order to call it (serious races from that? I'm not sure). Once that's gone, you can see it's pointless for page_cgroup's ref_cnt to be atomic: it's always manipulated under lock_page_cgroup, except where force_empty unilaterally reset it to 0 (and how does uncharge's atomic_dec_and_test protect against that?). Simplify this page_cgroup locking: if you've got the lock and the pc is attached, then the ref_cnt must be positive: VM_BUG_ONs to check that, and to check that pc->page matches page (we're on the way to finding why sometimes it doesn't, but this patch doesn't fix that). Signed-off-by:
-
Hugh Dickins authored
More cleanup to memcontrol.c, this time changing some of the code generated. Let the compiler decide what to inline (except for page_cgroup_locked which is only used when CONFIG_DEBUG_VM): the __always_inline on lock_page_cgroup etc. was quite a waste since bit_spin_lock etc. are inlines in a header file; made mem_cgroup_force_empty and mem_cgroup_write_strategy static. Signed-off-by:
-
Hugh Dickins authored
Sorry, before getting down to more important changes, I'd like to do some cleanup in memcontrol.c. This patch doesn't change the code generated, but cleans up whitespace, moves up a double declaration, removes an unused enum, removes void returns, removes misleading comments, that kind of thing. Signed-off-by:
-
Hugh Dickins authored
Nothing uses mem_cgroup_uncharge apart from mem_cgroup_uncharge_page, (a trivial wrapper around it) and mem_cgroup_end_migration (which does the same as mem_cgroup_uncharge_page). And it often ends up having to lock just to let its caller unlock. Remove it (but leave the silly locking until a later patch). Moved mem_cgroup_cache_charge next to mem_cgroup_charge in memcontrol.h. Signed-off-by:
Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by:
-
Hugh Dickins authored
My memcgroup patch to fix hang with shmem/tmpfs added NULL page handling to mem_cgroup_charge_common. It seemed convenient at the time, but hard to justify now: there's a perfectly appropriate swappage to charge and uncharge instead, this is not on any hot path through shmem_getpage, and no performance hit was observed from the slight extra overhead. So revert that NULL page handling from mem_cgroup_charge_common; and make it clearer by bringing page_cgroup_assign_new_page_cgroup into its body - that was a helper I found more of a hindrance to understanding. Signed-off-by:
-
Hugh Dickins authored
Replace free_hot_cold_page's VM_BUG_ON(page_get_page_cgroup(page)) by a "Bad page state" and clear: most users don't have CONFIG_DEBUG_VM on, and if it were set here, it'd likely cause corruption when the page is reused. Don't use page_assign_page_cgroup to clear it: that should be private to memcontrol.c, and always called with the lock taken; and memmap_init_zone doesn't need it either - like page->mapping and other pointers throughout the kernel, Linux assumes pointers in zeroed structures are NULL pointers. Instead use page_reset_bad_cgroup, added to memcontrol.h for this only. Signed-off-by:
-
Hugh Dickins authored
Page migration gave me free_hot_cold_page's VM_BUG_ON page->page_cgroup. remove_migration_pte was calling mem_cgroup_charge on the new page whenever it found a swap pte, before it had determined it to be a migration entry. That left a surplus reference count on the page_cgroup, so it was still attached when the page was later freed. Move that mem_cgroup_charge down to where we're sure it's a migration entry. We were already under i_mmap_lock or anon_vma->lock, so its GFP_KERNEL was already inappropriate: change that to GFP_ATOMIC. It's essential that remove_migration_pte removes all the migration entries, other crashes follow if not. So proceed even when the charge fails: normally it cannot, but after a mem_cgroup_force_empty it might - comment in the code. Signed-off-by:
-
Hugh Dickins authored
Don't uncharge when do_swap_page's call to do_wp_page fails: the page which was charged for is there in the pagetable, and will be correctly uncharged when that area is unmapped - it was only its COWing which failed. And while we're here, remove earlier XXX comment: yes, OR in do_wp_page's return value (maybe VM_FAULT_WRITE) with do_swap_page's there; but if it fails, mask out success bits, which might confuse some arches e.g. sparc. Signed-off-by:
-
Hugh Dickins authored
There's nothing wrong with mem_cgroup_charge failure in do_wp_page and do_anonymous page using __free_page, but it does look odd when nearby code uses page_cache_release: use that instead (while turning a blind eye to ancient inconsistencies of page_cache_release versus put_page). Signed-off-by:
-
Hugh Dickins authored
Each caller of mem_cgroup_move_lists is having to use page_get_page_cgroup: it's more convenient if it acts upon the page itself not the page_cgroup; and in a later patch this becomes important to handle within memcontrol.c. Signed-off-by:
-
Hugh Dickins authored
vm_match_cgroup is a perverse name for a macro to match mm with cgroup: rename it mm_match_cgroup, matching mm_init_cgroup and mm_free_cgroup. Signed-off-by:
David Rientjes <rientjes@google.com> Acked-by:
-
Mathieu Desnoyers authored
Wrap __mark_check_format() into an if(0) to make sure that parameters such as trace_mark(mm_page_alloc, "order %u pfn %lu", order, page?page_to_pfn(page):0); (where page_to_pfn() has side-effects) won't generate code because of the __mark_check_format(). Thanks to Jan Kiszka for reporting this. Signed-off-by:
Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Jan Kiszka <jan.kiszka@siemens.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Signed-off-by:
-
Jesper Juhl authored
get_marker() may return NULL, so test for it. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by:
Jesper Juhl <jesper.juhl@gmail.com> Acked-by:
-
Chris Dearman authored
Signed-off-by:
Chris Dearman <chris@mips.com> Signed-off-by:
Ralf Baechle <ralf@linux-mips.org> Signed-off-by:
-
FUJITA Tomonori authored
This just removes unused DEBUG_FORCEDAC define in the IOMMU code. Signed-off-by:
FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Signed-off-by:
-
FUJITA Tomonori authored
This patch makes the IOMMU code not allocate a memory area spanning LLD's segment boundary. is_span_boundary() judges whether a memory area spans LLD's segment boundary. If iommu_arena_find_pages() finds such a area, it tries to find the next available memory area. Signed-off-by:
-
FUJITA Tomonori authored
iommu_arena_find_pages duplicates the code to access to the bitmap for free space management. This patch convert the IOMMU code to have only one place to access the bitmap, in the popular way that other IOMMUs (e.g. POWER and SPARC) do. This patch is preparation for modifications to fix the IOMMU segment boundary problem. Signed-off-by:
-
FUJITA Tomonori authored
This patch is preparation for modifications to fix the IOMMU segment boundary problem. Signed-off-by:
-
Eric Sandeen authored
Include falloc.h in header-y; it defines a flag for the fallocate sysctl. Signed-off-by:
Eric Sandeen <sandeen@redhat.com> Signed-off-by:
-
Jesper Nilsson authored
Adrian Bunk reported another compile error with a SVN head GCC: ... CC arch/cris/arch-v10/lib/string.o /home/bunk/linux/kernel-2.6/git/linux-2.6/arch/cris/arch-v10/lib/string.c:138: error: lvalue required as increment operand /home/bunk/linux/kernel-2.6/git/linux-2.6/arch/cris/arch-v10/lib/string.c:138: error: lvalue required as increment operand /home/bunk/linux/kernel-2.6/git/linux-2.6/arch/cris/arch-v10/lib/string.c:139: error: lvalue required as increment operand ... This is due to the use of the construct: *((long*)dst)++ = lc; Which isn't legal since casts don't return an lvalue. The solution is to import the implementation from newlib, which is continually autotested together with GCC mainline, and uses the construct: *(long *) dst = lc; dst += 4; Since this is an import of a file from newlib, I'm not touching the formatting or correcting any checkpatch errors. As for the earlier fix for memset.c, even if the two files for CRIS v10 and CRIS v32 are identical at the moment, it might be possible to tweak the CRIS v32 version. Thus, I'm not yet folding them into the same file, at least not until we've done some research on it. Signed-off-by:
Jesper Nilsson <jesper.nilsson@axis.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Adrian Bunk <bunk@stusta.de> Signed-off-by:
-
David Sterba authored
The Coverity checker spotted the following inconsequent NULL checking in drivers/char/pcmcia/ipwireless/network.c:ipwireless_network_packet_received() if (tty && channel_idx == IPW_CHANNEL_RAS && (network->ras_control_lines & IPW_CONTROL_LINE_DCD) != 0 && ipwireless_tty_is_modem(tty)) { ... else ipwireless_tty_received(tty, data, length); Cc: Adrian Bunk <bunk@kernel.org> Signed-off-by:David Sterba <dsterba@suse.cz> Signed-off-by:
Jiri Kosina <jkosina@suse.cz> Cc: "John W. Linville" <linville@tuxdriver.com> Signed-off-by:
-
Ville Syrjala authored
SM502 has a programmable PLL which can provide the panel pixel clock instead of the 288MHz and 336MHz PLLs. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by:
Ville Syrjala <syrjala@sci.fi> Cc: Ben Dooks <ben-linux@fluff.org> Signed-off-by:
-
Ville Syrjala authored
misc_div is a subset of px_div so eliminate the smaller table. Signed-off-by:
-
Ville Syrjala authored
Vertical sync height register can only hold 6 bits. Fix the hsync start test to use > instead of >=. Also add a few clarifying comments. Signed-off-by:
Ben Dooks <ben-linux@fluff.org> Signed-off-by:
-
Ville Syrjala authored
Even though it may not be strictly necessary transp.offset should probably be 0 when alpha channel is not available. Signed-off-by:
-
Ville Syrjala authored
The RGB offsets were reversed in 16bpp modes. Simply trying to reverse the offsets when endianness differs is clearly the wrong thing to do but that is an issue for another patch. Signed-off-by:
-
Ville Syrjala authored
The sm501fb palette code clearly does not handle direct color so change the driver to use true color visual for 16bpp. Signed-off-by:
Magnus Damm <damm@igel.co.jp> Acked-by:
-
Andrew Morton authored
We should be able to do ndelay(some_u64), but that can cause a call to __divdi3() to be emitted because the ndelay() macros does a divide. Fix it by switching to static inline which will force the u64 arg to be treated as an unsigned long. udelay() takes an unsigned long arg. [bunk@kernel.org: reported m68k build breakage] Cc: Adrian Bunk <bunk@kernel.org> Cc: Evgeniy Polyakov <johnpol@2ka.mipt.ru> Cc: Martin Michlmayr <tbm@cyrius.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Adrian Bunk <bunk@kernel.org> Signed-off-by:
-
Anton Vorontsov authored
The patch replaces dev_dbg() by dev_err(), so the user could actually see the error, instead of wondering why w1 doesn't work. The root cause of the bus reset error isn't yet debugged though, but this sometimes happens on iPaq H5555. And while I'm at it, some cosmetic cleanups also made (few lines were using spaces instead of tabs). Signed-off-by:
Anton Vorontsov <cbouatmailru@gmail.com> Acked-by:
Evgeniy Polyakov <johnpol@2ka.mipt.ru> Signed-off-by:
-
Anton Vorontsov authored
On the error condition clk_get() returns ERR_PTR(..), so checking for NULL doesn't work. ds1wm module causes a kernel oops when ds1wm clock isn't registered. This patch converts NULL check to IS_ERR(), plus uses PTR_ERR() for the return code. Signed-off-by:
-
Grant Likely authored
Commit id 94f38948 (Separate MPC52xx PSC FIOF regsiters from the rest of PSC) split the PSC fifo registers away from the core PSC regs. Doing so broke the mpc52xx_psc_spi driver. This patch teaches the mpc52xx_psc_spi driver about the new PSC fifo register definitions. Signed-off-by:
Grant Likely <grant.likely@secretlab.ca> Cc: David Brownell <david-b@pacbell.net> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Kumar Gala <galak@gate.crashing.org> Signed-off-by:
-
Peter Osterlund authored
On my system, pkt_open() consumes 584 bytes because the compiler decides to inline lots of functions that would not normally be part of long call chains. The following patch fixes that problem on my system. Signed-off-by:
Peter Osterlund <petero2@telia.com> Cc: Nix <nix@esperi.org.uk> Signed-off-by:
-
Andrew Morton authored
People are adding `noinline' in various places to prevent excess stack consumption due to gcc inlining. But once this is done, it is quite unobvious why the `noinline' is present in the code. We can comment each and every site, or we can use noinline_for_stack. Signed-off-by:
-
Krzysztof Helt authored
Correct error paths in probe function. The probe function enables mmio mode so it important to disable the mmio mode before exiting the probe function. Otherwise, the console is left in unusable state (garbled fonts at least, lock up at worst). [akpm@linux-foundation.org: cleanups] Signed-off-by:
Krzysztof Helt <krzysztof.h1@wp.pl> Cc: "Antonino A. Daplas" <adaplas@pol.net> Signed-off-by:
-
Balbir Singh authored
Rename Memory Controller to Memory Resource Controller. Reflect the same changes in the CONFIG definition for the Memory Resource Controller. Group together the config options for Resource Counters and Memory Resource Controller. Signed-off-by:
-
Ananth N Mavinakayanahalli authored
Move kprobes examples from Documentation/kprobes.txt to under samples/. Patch originally by Randy Dunlap. o Updated the patch to apply on 2.6.25-rc3 o Modified examples code to build on multiple architectures. Currently, the kprobe and jprobe examples code works for x86 and powerpc o Cleaned up unneeded #includes o Cleaned up Kconfig per Sam Ravnborg's suggestions to fix build break on archs that don't have kretprobes o Implemented suggestions by Mathieu Desnoyers on CONFIG_KRETPROBES o Included Andrew Morton's cleanup based on x86-git o Modified kretprobe_example to act as a arch-agnostic module to determine routine execution times: Use 'modprobe kretprobe_example func=<func_name>' to determine execution time of func_name in nanoseconds. Signed-off-by:
Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by:
Ananth N Mavinakayanahalli <ananth@in.ibm.com> Acked-by:
-
Ananth N Mavinakayanahalli authored
Add CONFIG_HAVE_KRETPROBES to the arch/<arch>/Kconfig file for relevant architectures with kprobes support. This facilitates easy handling of in-kernel modules (like samples/kprobes/kretprobe_example.c) that depend on kretprobes being present in the kernel. Thanks to Sam Ravnborg for helping make the patch more lean. Per Mathieu's suggestion, added CONFIG_KRETPROBES and fixed up dependencies. Signed-off-by:
Ingo Molnar <mingo@elte.hu> Signed-off-by:
-
Samuel Thibault authored
VT notifier callbacks need to be aware of console switches. This is already partially done from console_callback(), but at that time fg_console, cursor positions, etc. are not yet updated and hence screen readers fetch the old values. This adds an update notify after all of the values are updated in redraw_screen(vc, 1). Signed-off-by:
Samuel Thibault <samuel.thibault@ens-lyon.org> Cc: <stable@kernel.org> Signed-off-by:
-
