- 25 May, 2011 40 commits
-
-
Mike Frysinger authored
The copy_to_user_page() function is supposed to flush the icache on the memory that was written, but the current asm-generic version lacks that logic. While normally it isn't a big deal as the asm-generic version of icache flushing is a stub, it is a deal for ports that want to use the asm-generic version as a baseline and then overlay its own specific parts (like icache flushing). Signed-off-by:
Mike Frysinger <vapier@gentoo.org> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Andrew Barry authored
I believe I found a problem in __alloc_pages_slowpath, which allows a process to get stuck endlessly looping, even when lots of memory is available. Running an I/O and memory intensive stress-test I see a 0-order page allocation with __GFP_IO and __GFP_WAIT, running on a system with very little free memory. Right about the same time that the stress-test gets killed by the OOM-killer, the utility trying to allocate memory gets stuck in __alloc_pages_slowpath even though most of the systems memory was freed by the oom-kill of the stress-test. The utility ends up looping from the rebalance label down through the wait_iff_congested continiously. Because order=0, __alloc_pages_direct_compact skips the call to get_page_from_freelist. Because all of the reclaimable memory on the system has already been reclaimed, __alloc_pages_direct_reclaim skips the call to get_page_from_freelist. Since there is no __GFP_FS flag, the block with __alloc_pages_may_oom is skipped. The loop hits the wait_iff_congested, then jumps back to rebalance without ever trying to get_page_from_freelist. This loop repeats infinitely. The test case is pretty pathological. Running a mix of I/O stress-tests that do a lot of fork() and consume all of the system memory, I can pretty reliably hit this on 600 nodes, in about 12 hours. 32GB/node. Signed-off-by:
Andrew Barry <abarry@cray.com> Signed-off-by:
Minchan Kim <minchan.kim@gmail.com> Reviewed-by: Rik van Riel<riel@redhat.com> Acked-by:
Mel Gorman <mgorman@suse.de> Cc: <stable@kernel.org> Signed-off-by:
-
Daniel Kiper authored
Add SECTION_ALIGN_UP() and SECTION_ALIGN_DOWN() macro which aligns given pfn to upper section and lower section boundary accordingly. Required for the latest memory hotplug support for the Xen balloon driver. Signed-off-by:
Daniel Kiper <dkiper@net-space.pl> Reviewed-by:
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> David Rientjes <rientjes@google.com> Signed-off-by:
-
Michal Hocko authored
The noswapaccount parameter has been deprecated since 2.6.38 without any complaints from users so we can remove it. swapaccount=0|1 can be used instead. As we are removing the parameter we can also clean up swapaccount because it doesn't have to accept an empty string anymore (to match noswapaccount) and so we can push = into __setup macro rather than checking "=1" resp. "=0" strings Signed-off-by:
Michal Hocko <mhocko@suse.cz> Cc: Hiroyuki Kamezawa <kamezawa.hiroyuki@gmail.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by:
-
Stephen Wilson authored
In show_numa_map() we collect statistics into a numa_maps structure. Since the number of NUMA nodes can be very large, this structure is not a candidate for stack allocation. Instead of going thru a kmalloc()+kfree() cycle each time show_numa_map() is invoked, perform the allocation just once when /proc/pid/numa_maps is opened. Performing the allocation when numa_maps is opened, and thus before a reference to the target tasks mm is taken, eliminates a potential stalemate condition in the oom-killer as originally described by Hugh Dickins: ... imagine what happens if the system is out of memory, and the mm we're looking at is selected for killing by the OOM killer: while we wait in __get_free_page for more memory, no memory is freed from the selected mm because it cannot reach exit_mmap while we hold that reference. Signed-off-by:
Stephen Wilson <wilsons@start.ca> Reviewed-by:
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hughd@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by:
-
Stephen Wilson authored
Now that mm/mempolicy.c is no longer implementing /proc/pid/numa_maps there is no need to export struct proc_maps_private to the world. Move it to fs/proc/internal.h instead. Signed-off-by:
-
Stephen Wilson authored
Moving show_numa_map() from mempolicy.c to task_mmu.c solves several issues. - Having the show() operation "miles away" from the corresponding seq_file iteration operations is a maintenance burden. - The need to export ad hoc info like struct proc_maps_private is eliminated. - The implementation of show_numa_map() can be improved in a simple manner by cooperating with the other seq_file operations (start, stop, etc) -- something that would be messy to do without this change. Signed-off-by: -
Stephen Wilson authored
When CONFIG_TMPFS=n mpol_to_str() is not declared in mempolicy.h. However, in the NUMA case, the definition is always compiled. Since it is not strictly true that tmpfs is the only client, and since the symbol was always lurking around anyways, export mpol_to_str() unconditionally. Furthermore, this will allow us to move show_numa_map() out of mempolicy.c and into the procfs subsystem. Signed-off-by:
-
Stephen Wilson authored
This function has been superseded by gather_hugetbl_stats() and is no longer needed. Signed-off-by:
-
Stephen Wilson authored
Improve the prototype of gather_stats() to take a struct numa_maps as argument instead of a generic void *. Update all callers to make the required type explicit. Since gather_stats() is not needed before its definition and is scheduled to be moved out of mempolicy.c the declaration is removed as well. Signed-off-by:
-
Stephen Wilson authored
Mapping statistics in a NUMA environment is now computed using the generic walk_page_range() logic. Remove the old/equivalent functionality. Signed-off-by:
-
Stephen Wilson authored
Converting show_numa_map() to use the generic routine decouples the function from mempolicy.c, allowing it to be moved out of the mm subsystem and into fs/proc. Also, include KSM pages in /proc/pid/numa_maps statistics. The pagewalk logic implemented by check_pte_range() failed to account for such pages as they were not applicable to the page migration case. Signed-off-by:
-
Stephen Wilson authored
In commit 48fce342 ("mempolicies: unexport get_vma_policy()") get_vma_policy() was marked static as all clients were local to mempolicy.c. However, the decision to generate /proc/pid/numa_maps in the numa memory policy code and outside the procfs subsystem introduces an artificial interdependency between the two systems. Exporting get_vma_policy() once again is the first step to clean up this interdependency. Signed-off-by:
-
Hugh Dickins authored
Remove noMMU declaration of shmem_get_unmapped_area() from mm.h: it fell out of use in 2.6.21 and ceased to exist in 2.6.29. Signed-off-by:
Hugh Dickins <hughd@google.com> Signed-off-by:
-
Eric Paris authored
Implement generic xattrs for tmpfs filesystems. The Feodra project, while trying to replace suid apps with file capabilities, realized that tmpfs, which is used on the build systems, does not support file capabilities and thus cannot be used to build packages which use file capabilities. Xattrs are also needed for overlayfs. The xattr interface is a bit odd. If a filesystem does not implement any {get,set,list}xattr functions the VFS will call into some random LSM hooks and the running LSM can then implement some method for handling xattrs. SELinux for example provides a method to support security.selinux but no other security.* xattrs. As it stands today when one enables CONFIG_TMPFS_POSIX_ACL tmpfs will have xattr handler routines specifically to handle acls. Because of this tmpfs would loose the VFS/LSM helpers to support the running LSM. To make up for that tmpfs had stub functions that did nothing but call into the LSM hooks which implement the helpers. This new patch does not use the LSM fallback functions and instead just implements a native get/set/list xattr feature for the full security.* and trusted.* namespace like a normal filesystem. This means that tmpfs can now support both security.selinux and security.capability, which was not previously possible. The basic implementation is that I attach a: struct shmem_xattr { struct list_head list; /* anchored by shmem_inode_info->xattr_list */ char *name; size_t size; char value[0]; }; Into the struct shmem_inode_info for each xattr that is set. This implementation could easily support the user.* namespace as well, except some care needs to be taken to prevent large amounts of unswappable memory being allocated for unprivileged users. [mszeredi@suse.cz: new config option, suport trusted.*, support symlinks] Signed-off-by:Eric Paris <eparis@redhat.com> Signed-off-by:
Miklos Szeredi <mszeredi@suse.cz> Acked-by:
Serge Hallyn <serge.hallyn@ubuntu.com> Tested-by:
Jordi Pujol <jordipujolp@gmail.com> Signed-off-by:
-
Yinghai Lu authored
The bootmem wrapper with memblock supports top-down now, so we no longer need this trick. Signed-off-by:
Yinghai LU <yinghai@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Olaf Hering <olaf@aepfle.de> Cc: Tejun Heo <tj@kernel.org> Cc: Lucas De Marchi <lucas.demarchi@profusion.mobi> Signed-off-by:
-
Yinghai Lu authored
The bootmem wrapper with memblock supports top-down now, so we do not need to set the low limit to __pa(MAX_DMA_ADDRESS). The logic should be: good to allocate above __pa(MAX_DMA_ADDRESS), but it is ok if we can not find memory above 16M on system that has a small amount of RAM. Signed-off-by:
-
Matt Fleming authored
The problem with having two different types of counters is that developers adding new code need to keep in mind whether it's safe to use both the atomic and non-atomic implementations. For example, when adding new callers of the *_mm_counter() functions a developer needs to ensure that those paths are always executed with page_table_lock held, in case we're using the non-atomic implementation of mm counters. Hugh Dickins introduced the atomic mm counters in commit f412ac08 ("[PATCH] mm: fix rss and mmlist locking"). When asked why he left the non-atomic counters around he said, | The only reason was to avoid adding costly atomic operations into a | configuration that had no need for them there: the page_table_lock | sufficed. | | Certainly it would be simpler just to delete the non-atomic variant. | | And I think it's fair to say that any configuration on which we're | measuring performance to that degree (rather than "does it boot fast?" | type measurements), would already be going the split ptlocks route. Removing the non-atomic counters eases the maintenance burden because developers no longer have to mindful of the two implementations when using *_mm_counter(). Note that all architectures provide a means of atomically updating atomic_long_t variables, even if they have to revert to the generic spinlock implementation because they don't support 64-bit atomic instructions (see lib/atomic64.c). Signed-off-by:
Matt Fleming <matt.fleming@linux.intel.com> Acked-by:
Dave Hansen <dave@linux.vnet.ibm.com> Acked-by:
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hugh Dickins <hughd@google.com> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by:
-
David Rientjes authored
The page allocator will improperly return a page from ZONE_NORMAL even when __GFP_DMA is passed if CONFIG_ZONE_DMA is disabled. The caller expects DMA memory, perhaps for ISA devices with 16-bit address registers, and may get higher memory resulting in undefined behavior. This patch causes the page allocator to return NULL in such circumstances with a warning emitted to the kernel log on the first occurrence. Signed-off-by:
David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by:
-
Daniel Kiper authored
Do not define PFN_SECTION_SHIFT if !CONFIG_SPARSEMEM. Signed-off-by:
-
Daniel Kiper authored
pfn_to_section_nr()/section_nr_to_pfn() is valid only in CONFIG_SPARSEMEM context. Move it to proper place. Signed-off-by:
-
Daniel Kiper authored
set_page_section() is meaningful only in CONFIG_SPARSEMEM and !CONFIG_SPARSEMEM_VMEMMAP context. Move it to proper place and amend accordingly functions which are using it. Signed-off-by:
-
Daniel Kiper authored
online_pages() is only compiled for CONFIG_MEMORY_HOTPLUG_SPARSE, so there is no need to support CONFIG_FLATMEM code within it. This patch removes code that is never used. Signed-off-by:
-
Minchan Kim authored
It's pointless that deactive_page's operates on unevictable pages. This patch removes unnecessary overhead which might be a bit problem in case that there are many unevictable page in system(ex, mprotect workload) [akpm@linux-foundation.org: tidy up comment] Reviewed-by:
-
Wu Fengguang authored
Previously the mmap sequential readahead is triggered by updating ra->prev_pos on each page fault and compare it with current page offset. It costs dirtying the cache line on each _minor_ page fault. So remove the ra->prev_pos recording, and instead tag PG_readahead to trigger the possible sequential readahead. It's not only more simple, but also will work more reliably and reduce cache line bouncing on concurrent page faults on shared struct file. In the mosbench exim benchmark which does multi-threaded page faults on shared struct file, the ra->mmap_miss and ra->prev_pos updates are found to cause excessive cache line bouncing on tmpfs, which actually disabled readahead totally (shmem_backing_dev_info.ra_pages == 0). So remove the ra->prev_pos recording, and instead tag PG_readahead to trigger the possible sequential readahead. It's not only more simple, but also will work more reliably on concurrent reads on shared struct file. Signed-off-by:
Wu Fengguang <fengguang.wu@intel.com> Tested-by:
Tim Chen <tim.c.chen@intel.com> Reported-by:
Andi Kleen <ak@linux.intel.com> Signed-off-by:
-
Andi Kleen authored
The original INT_MAX is too large, reduce it to - avoid unnecessarily dirtying/bouncing the cache line - restore mmap read-around faster on changed access pattern Background: in the mosbench exim benchmark which does multi-threaded page faults on shared struct file, the ra->mmap_miss updates are found to cause excessive cache line bouncing on tmpfs. The ra state updates are needless for tmpfs because it actually disabled readahead totally (shmem_backing_dev_info.ra_pages == 0). Tested-by:
-
Wu Fengguang authored
Reduce readahead overheads by returning early in do_sync_mmap_readahead(). tmpfs has ra_pages=0 and it can page fault really fast (not constraint by IO if not swapping). Signed-off-by:
-
Ying Han authored
Change each shrinker's API by consolidating the existing parameters into shrink_control struct. This will simplify any further features added w/o touching each file of shrinker. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: fix warning] [kosaki.motohiro@jp.fujitsu.com: fix up new shrinker API] [akpm@linux-foundation.org: fix xfs warning] [akpm@linux-foundation.org: update gfs2] Signed-off-by:
Ying Han <yinghan@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Acked-by:
Pavel Emelyanov <xemul@openvz.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Acked-by:
Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Signed-off-by:
-
Ying Han authored
Consolidate the existing parameters to shrink_slab() into a new shrink_control struct. This is needed later to pass the same struct to shrinkers. Signed-off-by:
-
Wu Fengguang authored
Pass __GFP_NORETRY|__GFP_NOWARN for readahead page allocations. readahead page allocations are completely optional. They are OK to fail and in particular shall not trigger OOM on themselves. Reported-by:
Dave Young <hidave.darkstar@gmail.com> Reviewed-by:
Pekka Enberg <penberg@kernel.org> Signed-off-by:
-
Arve Hjønnevåg authored
This fixes a problem where the first pageblock got marked MIGRATE_RESERVE even though it only had a few free pages. eg, On current ARM port, The kernel starts at offset 0x8000 to leave room for boot parameters, and the memory is freed later. This in turn caused no contiguous memory to be reserved and frequent kswapd wakeups that emptied the caches to get more contiguous memory. Unfortunatelly, ARM needs order-2 allocation for pgd (see arm/mm/pgd.c#pgd_alloc()). Therefore the issue is not minor nor easy avoidable. [kosaki.motohiro@jp.fujitsu.com: added some explanation] [kosaki.motohiro@jp.fujitsu.com: add !pfn_valid_within() to check] [minchan.kim@gmail.com: check end_pfn in pageblock_is_reserved] Signed-off-by:
John Stultz <john.stultz@linaro.org> Signed-off-by:
Arve Hjønnevåg <arve@android.com> Signed-off-by:
Mel Gorman <mel@csn.ul.ie> Acked-by:
-
David Rientjes authored
For m32r, N_NORMAL_MEMORY represents all nodes that have present memory since it does not support HIGHMEM. This patch sets the bit at the time the node is initialized. If N_NORMAL_MEMORY is not accurate, slub may encounter errors since it uses this nodemask to setup per-cache kmem_cache_node data structures. Signed-off-by:
-
David Rientjes authored
For alpha, N_NORMAL_MEMORY represents all nodes that have present memory since it does not support HIGHMEM. This patch sets the bit at the time the node is initialized. If N_NORMAL_MEMORY is not accurate, slub may encounter errors since it uses this nodemask to setup per-cache kmem_cache_node data structures. Signed-off-by:
-
Konstantin Khlebnikov authored
isolate_lru_page() must be called only with stable reference to the page, this is what is written in the comment above it, this is reasonable. current isolate_lru_page() users and its page extra reference sources: mm/huge_memory.c: __collapse_huge_page_isolate() - reference from pte mm/memcontrol.c: mem_cgroup_move_parent() - get_page_unless_zero() mem_cgroup_move_charge_pte_range() - reference from pte mm/memory-failure.c: soft_offline_page() - fixed, reference from get_any_page() delete_from_lru_cache() - reference from caller or get_page_unless_zero() [ seems like there bug, because __memory_failure() can call page_action() for hpages tail, but it is ok for isolate_lru_page(), tail getted and not in lru] mm/memory_hotplug.c: do_migrate_range() - fixed, get_page_unless_zero() mm/mempolicy.c: migrate_page_add() - reference from pte mm/migrate.c: do_move_page_to_node_array() - reference from follow_page() mlock.c: - various external references mm/vmscan.c: putback_lru_page() - reference from isolate_lru_page() It seems that all isolate_lru_page() users are ready now for this restriction. So, let's replace redundant get_page_unless_zero() with get_page() and add page initial reference count check with VM_BUG_ON() Signed-off-by:
Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by:
-
Konstantin Khlebnikov authored
Drop first page reference only after calling isolate_lru_page() to keep page stable reference while isolating. Signed-off-by:
-
Konstantin Khlebnikov authored
isolate_lru_page() must be called only with stable reference to page. So, let's grab normal page reference. Signed-off-by:
-
Dave Hansen authored
I was tracking down a page allocation failure that ended up in vmalloc(). Since vmalloc() uses 0-order pages, if somebody asks for an insane amount of memory, we'll still get a warning with "order:0" in it. That's not very useful. During recovery, vmalloc() also nicely frees all of the memory that it got up to the point of the failure. That is wonderful, but it also quickly hides any issues. We have a much different sitation if vmalloc() repeatedly fails 10GB in to: vmalloc(100 * 1<<30); versus repeatedly failing 4096 bytes in to a: vmalloc(8192); This patch will print out messages that look like this: [ 68.123503] vmalloc: allocation failure, allocated 66805763 of 13426688 bytes [ 68.124218] bash: page allocation failure: order:0, mode:0xd2 [ 68.124811] Pid: 3770, comm: bash Not tainted 2.6.39-rc3-00082-g85f2e689-dirty #333 [ 68.125579] Call Trace: [ 68.125853] [<ffffffff810f6da6>] warn_alloc_failed+0x146/0x170 [ 68.126464] [<ffffffff8107e05c>] ? printk+0x6c/0x70 [ 68.126791] [<ffffffff8112b5d4>] ? alloc_pages_current+0x94/0xe0 [ 68.127661] [<ffffffff8111ed37>] __vmalloc_node_range+0x237/0x290 ... The 'order' variable is added for clarity when calling warn_alloc_failed() to avoid having an unexplained '0' as an argument. The 'tmp_mask' is because adding an open-coded '| __GFP_NOWARN' would take us over 80 columns for the alloc_pages_node() call. If we are going to add a line, it might as well be one that makes the sucker easier to read. As a side issue, I also noticed that ctl_ioctl() does vmalloc() based solely on an unverified value passed in from userspace. Granted, it's under CAP_SYS_ADMIN, but it still frightens me a bit. Signed-off-by:
-
Dave Hansen authored
This originally started as a simple patch to give vmalloc() some more verbose output on failure on top of the plain page allocator messages. Johannes suggested that it might be nicer to lead with the vmalloc() info _before_ the page allocator messages. But, I do think there's a lot of value in what __alloc_pages_slowpath() does with its filtering and so forth. This patch creates a new function which other allocators can call instead of relying on the internal page allocator warnings. It also gives this function private rate-limiting which separates it from other printk_ratelimit() users. Signed-off-by:
-
KOSAKI Motohiro authored
cpumask_t is very big struct and cpu_vm_mask is placed wrong position. It might lead to reduce cache hit ratio. This patch has two change. 1) Move the place of cpumask into last of mm_struct. Because usually cpumask is accessed only front bits when the system has cpu-hotplug capability 2) Convert cpu_vm_mask into cpumask_var_t. It may help to reduce memory footprint if cpumask_size() will use nr_cpumask_bits properly in future. In addition, this patch change the name of cpu_vm_mask with cpu_vm_mask_var. It may help to detect out of tree cpu_vm_mask users. This patch has no functional change. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by:
-
Andrea Arcangeli authored
We don't need to hold the mmmap_sem through mem_cgroup_newpage_charge(), the mmap_sem is only hold for keeping the vma stable and we don't need the vma stable anymore after we return from alloc_hugepage_vma(). Signed-off-by:
Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by:
-
