diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-16 19:50:13 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-16 19:50:13 -0700 |
commit | 517d08699b250021303f9a7cf0d758b6dc0748ed (patch) | |
tree | 5e5b0134c3fffb78fe9d8b1641a64ff28fdd7bbc /mm | |
parent | 8eeee4e2f04fc551f50c9d9847da2d73d7d33728 (diff) | |
parent | a34601c5d84134055782ee031d58d82f5440e918 (diff) |
Merge branch 'akpm'
* akpm: (182 commits)
fbdev: bf54x-lq043fb: use kzalloc over kmalloc/memset
fbdev: *bfin*: fix __dev{init,exit} markings
fbdev: *bfin*: drop unnecessary calls to memset
fbdev: bfin-t350mcqb-fb: drop unused local variables
fbdev: blackfin has __raw I/O accessors, so use them in fb.h
fbdev: s1d13xxxfb: add accelerated bitblt functions
tcx: use standard fields for framebuffer physical address and length
fbdev: add support for handoff from firmware to hw framebuffers
intelfb: fix a bug when changing video timing
fbdev: use framebuffer_release() for freeing fb_info structures
radeon: P2G2CLK_ALWAYS_ONb tested twice, should 2nd be P2G2CLK_DAC_ALWAYS_ONb?
s3c-fb: CPUFREQ frequency scaling support
s3c-fb: fix resource releasing on error during probing
carminefb: fix possible access beyond end of carmine_modedb[]
acornfb: remove fb_mmap function
mb862xxfb: use CONFIG_OF instead of CONFIG_PPC_OF
mb862xxfb: restrict compliation of platform driver to PPC
Samsung SoC Framebuffer driver: add Alpha Channel support
atmel-lcdc: fix pixclock upper bound detection
offb: use framebuffer_alloc() to allocate fb_info struct
...
Manually fix up conflicts due to kmemcheck in mm/slab.c
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 14 | ||||
-rw-r--r-- | mm/Makefile | 1 | ||||
-rw-r--r-- | mm/fadvise.c | 2 | ||||
-rw-r--r-- | mm/filemap.c | 169 | ||||
-rw-r--r-- | mm/hugetlb.c | 106 | ||||
-rw-r--r-- | mm/init-mm.c | 20 | ||||
-rw-r--r-- | mm/internal.h | 33 | ||||
-rw-r--r-- | mm/madvise.c | 26 | ||||
-rw-r--r-- | mm/memcontrol.c | 11 | ||||
-rw-r--r-- | mm/memory.c | 128 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 6 | ||||
-rw-r--r-- | mm/mempolicy.c | 145 | ||||
-rw-r--r-- | mm/migrate.c | 6 | ||||
-rw-r--r-- | mm/mlock.c | 22 | ||||
-rw-r--r-- | mm/oom_kill.c | 64 | ||||
-rw-r--r-- | mm/page-writeback.c | 19 | ||||
-rw-r--r-- | mm/page_alloc.c | 754 | ||||
-rw-r--r-- | mm/page_io.c | 2 | ||||
-rw-r--r-- | mm/readahead.c | 145 | ||||
-rw-r--r-- | mm/rmap.c | 40 | ||||
-rw-r--r-- | mm/shmem.c | 4 | ||||
-rw-r--r-- | mm/slab.c | 11 | ||||
-rw-r--r-- | mm/slob.c | 4 | ||||
-rw-r--r-- | mm/slub.c | 2 | ||||
-rw-r--r-- | mm/swap_state.c | 17 | ||||
-rw-r--r-- | mm/swapfile.c | 276 | ||||
-rw-r--r-- | mm/truncate.c | 39 | ||||
-rw-r--r-- | mm/util.c | 16 | ||||
-rw-r--r-- | mm/vmscan.c | 372 | ||||
-rw-r--r-- | mm/vmstat.c | 19 |
30 files changed, 1598 insertions, 875 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 6f4610a9ce55..c948d4ca8bde 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -203,25 +203,13 @@ config VIRT_TO_BUS def_bool y depends on !ARCH_NO_VIRT_TO_BUS -config UNEVICTABLE_LRU - bool "Add LRU list to track non-evictable pages" - default y - help - Keeps unevictable pages off of the active and inactive pageout - lists, so kswapd will not waste CPU time or have its balancing - algorithms thrown off by scanning these pages. Selecting this - will use one page flag and increase the code size a little, - say Y unless you know what you are doing. - - See Documentation/vm/unevictable-lru.txt for more information. - config HAVE_MLOCK bool default y if MMU=y config HAVE_MLOCKED_PAGE_BIT bool - default y if HAVE_MLOCK=y && UNEVICTABLE_LRU=y + default y if HAVE_MLOCK=y config MMU_NOTIFIER bool diff --git a/mm/Makefile b/mm/Makefile index c379ce08354a..5e0bd6426693 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -12,6 +12,7 @@ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ page_isolation.o mm_init.o $(mmu-y) +obj-y += init-mm.o obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o obj-$(CONFIG_BOUNCE) += bounce.o diff --git a/mm/fadvise.c b/mm/fadvise.c index 54a0f8040afa..e43359214f6f 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -101,7 +101,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) ret = force_page_cache_readahead(mapping, file, start_index, - max_sane_readahead(nrpages)); + nrpages); if (ret > 0) ret = 0; break; diff --git a/mm/filemap.c b/mm/filemap.c index 1b60f30cebfa..22396713feb9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -521,7 +521,7 @@ struct page *__page_cache_alloc(gfp_t gfp) { if (cpuset_do_page_mem_spread()) { int n = cpuset_mem_spread_node(); - return alloc_pages_node(n, gfp, 0); + return alloc_pages_exact_node(n, gfp, 0); } return alloc_pages(gfp, 0); } @@ -1004,9 +1004,6 @@ EXPORT_SYMBOL(grab_cache_page_nowait); static void shrink_readahead_size_eio(struct file *filp, struct file_ra_state *ra) { - if (!ra->ra_pages) - return; - ra->ra_pages /= 4; } @@ -1390,8 +1387,7 @@ do_readahead(struct address_space *mapping, struct file *filp, if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage) return -EINVAL; - force_page_cache_readahead(mapping, filp, index, - max_sane_readahead(nr)); + force_page_cache_readahead(mapping, filp, index, nr); return 0; } @@ -1457,6 +1453,73 @@ static int page_cache_read(struct file *file, pgoff_t offset) #define MMAP_LOTSAMISS (100) +/* + * Synchronous readahead happens when we don't even find + * a page in the page cache at all. + */ +static void do_sync_mmap_readahead(struct vm_area_struct *vma, + struct file_ra_state *ra, + struct file *file, + pgoff_t offset) +{ + unsigned long ra_pages; + struct address_space *mapping = file->f_mapping; + + /* If we don't want any read-ahead, don't bother */ + if (VM_RandomReadHint(vma)) + return; + + if (VM_SequentialReadHint(vma) || + offset - 1 == (ra->prev_pos >> PAGE_CACHE_SHIFT)) { + page_cache_sync_readahead(mapping, ra, file, offset, + ra->ra_pages); + return; + } + + if (ra->mmap_miss < INT_MAX) + ra->mmap_miss++; + + /* + * Do we miss much more than hit in this file? If so, + * stop bothering with read-ahead. It will only hurt. + */ + if (ra->mmap_miss > MMAP_LOTSAMISS) + return; + + /* + * mmap read-around + */ + ra_pages = max_sane_readahead(ra->ra_pages); + if (ra_pages) { + ra->start = max_t(long, 0, offset - ra_pages/2); + ra->size = ra_pages; + ra->async_size = 0; + ra_submit(ra, mapping, file); + } +} + +/* + * Asynchronous readahead happens when we find the page and PG_readahead, + * so we want to possibly extend the readahead further.. + */ +static void do_async_mmap_readahead(struct vm_area_struct *vma, + struct file_ra_state *ra, + struct file *file, + struct page *page, + pgoff_t offset) +{ + struct address_space *mapping = file->f_mapping; + + /* If we don't want any read-ahead, don't bother */ + if (VM_RandomReadHint(vma)) + return; + if (ra->mmap_miss > 0) + ra->mmap_miss--; + if (PageReadahead(page)) + page_cache_async_readahead(mapping, ra, file, + page, offset, ra->ra_pages); +} + /** * filemap_fault - read in file data for page fault handling * @vma: vma in which the fault was taken @@ -1476,78 +1539,44 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct address_space *mapping = file->f_mapping; struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; + pgoff_t offset = vmf->pgoff; struct page *page; pgoff_t size; - int did_readaround = 0; int ret = 0; size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (vmf->pgoff >= size) + if (offset >= size) return VM_FAULT_SIGBUS; - /* If we don't want any read-ahead, don't bother */ - if (VM_RandomReadHint(vma)) - goto no_cached_page; - /* * Do we have something in the page cache already? */ -retry_find: - page = find_lock_page(mapping, vmf->pgoff); - /* - * For sequential accesses, we use the generic readahead logic. - */ - if (VM_SequentialReadHint(vma)) { - if (!page) { - page_cache_sync_readahead(mapping, ra, file, - vmf->pgoff, 1); - page = find_lock_page(mapping, vmf->pgoff); - if (!page) - goto no_cached_page; - } - if (PageReadahead(page)) { - page_cache_async_readahead(mapping, ra, file, page, - vmf->pgoff, 1); - } - } - - if (!page) { - unsigned long ra_pages; - - ra->mmap_miss++; - + page = find_get_page(mapping, offset); + if (likely(page)) { /* - * Do we miss much more than hit in this file? If so, - * stop bothering with read-ahead. It will only hurt. + * We found the page, so try async readahead before + * waiting for the lock. */ - if (ra->mmap_miss > MMAP_LOTSAMISS) - goto no_cached_page; + do_async_mmap_readahead(vma, ra, file, page, offset); + lock_page(page); - /* - * To keep the pgmajfault counter straight, we need to - * check did_readaround, as this is an inner loop. - */ - if (!did_readaround) { - ret = VM_FAULT_MAJOR; - count_vm_event(PGMAJFAULT); - } - did_readaround = 1; - ra_pages = max_sane_readahead(file->f_ra.ra_pages); - if (ra_pages) { - pgoff_t start = 0; - - if (vmf->pgoff > ra_pages / 2) - start = vmf->pgoff - ra_pages / 2; - do_page_cache_readahead(mapping, file, start, ra_pages); + /* Did it get truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + put_page(page); + goto no_cached_page; } - page = find_lock_page(mapping, vmf->pgoff); + } else { + /* No page in the page cache at all */ + do_sync_mmap_readahead(vma, ra, file, offset); + count_vm_event(PGMAJFAULT); + ret = VM_FAULT_MAJOR; +retry_find: + page = find_lock_page(mapping, offset); if (!page) goto no_cached_page; } - if (!did_readaround) - ra->mmap_miss--; - /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. @@ -1555,18 +1584,18 @@ retry_find: if (unlikely(!PageUptodate(page))) goto page_not_uptodate; - /* Must recheck i_size under page lock */ + /* + * Found the page and have a reference on it. + * We must recheck i_size under page lock. + */ size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (unlikely(vmf->pgoff >= size)) { + if (unlikely(offset >= size)) { unlock_page(page); page_cache_release(page); return VM_FAULT_SIGBUS; } - /* - * Found the page and have a reference on it. - */ - ra->prev_pos = (loff_t)page->index << PAGE_CACHE_SHIFT; + ra->prev_pos = (loff_t)offset << PAGE_CACHE_SHIFT; vmf->page = page; return ret | VM_FAULT_LOCKED; @@ -1575,7 +1604,7 @@ no_cached_page: * We're only likely to ever get here if MADV_RANDOM is in * effect. */ - error = page_cache_read(file, vmf->pgoff); + error = page_cache_read(file, offset); /* * The page we want has now been added to the page cache. @@ -1595,12 +1624,6 @@ no_cached_page: return VM_FAULT_SIGBUS; page_not_uptodate: - /* IO error path */ - if (!did_readaround) { - ret = VM_FAULT_MAJOR; - count_vm_event(PGMAJFAULT); - } - /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e83ad2c9228c..a56e6f3ce979 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -578,41 +578,6 @@ static void free_huge_page(struct page *page) hugetlb_put_quota(mapping, 1); } -/* - * Increment or decrement surplus_huge_pages. Keep node-specific counters - * balanced by operating on them in a round-robin fashion. - * Returns 1 if an adjustment was made. - */ -static int adjust_pool_surplus(struct hstate *h, int delta) -{ - static int prev_nid; - int nid = prev_nid; - int ret = 0; - - VM_BUG_ON(delta != -1 && delta != 1); - do { - nid = next_node(nid, node_online_map); - if (nid == MAX_NUMNODES) - nid = first_node(node_online_map); - - /* To shrink on this node, there must be a surplus page */ - if (delta < 0 && !h->surplus_huge_pages_node[nid]) - continue; - /* Surplus cannot exceed the total number of pages */ - if (delta > 0 && h->surplus_huge_pages_node[nid] >= - h->nr_huge_pages_node[nid]) - continue; - - h->surplus_huge_pages += delta; - h->surplus_huge_pages_node[nid] += delta; - ret = 1; - break; - } while (nid != prev_nid); - - prev_nid = nid; - return ret; -} - static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { set_compound_page_dtor(page, free_huge_page); @@ -623,6 +588,34 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) put_page(page); /* free it into the hugepage allocator */ } +static void prep_compound_gigantic_page(struct page *page, unsigned long order) +{ + int i; + int nr_pages = 1 << order; + struct page *p = page + 1; + + /* we rely on prep_new_huge_page to set the destructor */ + set_compound_order(page, order); + __SetPageHead(page); + for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + __SetPageTail(p); + p->first_page = page; + } +} + +int PageHuge(struct page *page) +{ + compound_page_dtor *dtor; + + if (!PageCompound(page)) + return 0; + + page = compound_head(page); + dtor = get_compound_page_dtor(page); + + return dtor == free_huge_page; +} + static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; @@ -630,7 +623,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) if (h->order >= MAX_ORDER) return NULL; - page = alloc_pages_node(nid, + page = alloc_pages_exact_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); @@ -649,7 +642,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) * Use a helper variable to find the next node and then * copy it back to hugetlb_next_nid afterwards: * otherwise there's a window in which a racer might - * pass invalid nid MAX_NUMNODES to alloc_pages_node. + * pass invalid nid MAX_NUMNODES to alloc_pages_exact_node. * But we don't need to use a spin_lock here: it really * doesn't matter if occasionally a racer chooses the * same nid as we do. Move nid forward in the mask even @@ -875,7 +868,7 @@ static void return_unused_surplus_pages(struct hstate *h, * can no longer free unreserved surplus pages. This occurs when * the nodes with surplus pages have no free pages. */ - unsigned long remaining_iterations = num_online_nodes(); + unsigned long remaining_iterations = nr_online_nodes; /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; @@ -904,7 +897,7 @@ static void return_unused_surplus_pages(struct hstate *h, h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; nr_pages--; - remaining_iterations = num_online_nodes(); + remaining_iterations = nr_online_nodes; } } } @@ -1140,6 +1133,41 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count) } #endif +/* + * Increment or decrement surplus_huge_pages. Keep node-specific counters + * balanced by operating on them in a round-robin fashion. + * Returns 1 if an adjustment was made. + */ +static int adjust_pool_surplus(struct hstate *h, int delta) +{ + static int prev_nid; + int nid = prev_nid; + int ret = 0; + + VM_BUG_ON(delta != -1 && delta != 1); + do { + nid = next_node(nid, node_online_map); + if (nid == MAX_NUMNODES) + nid = first_node(node_online_map); + + /* To shrink on this node, there must be a surplus page */ + if (delta < 0 && !h->surplus_huge_pages_node[nid]) + continue; + /* Surplus cannot exceed the total number of pages */ + if (delta > 0 && h->surplus_huge_pages_node[nid] >= + h->nr_huge_pages_node[nid]) + continue; + + h->surplus_huge_pages += delta; + h->surplus_huge_pages_node[nid] += delta; + ret = 1; + break; + } while (nid != prev_nid); + + prev_nid = nid; + return ret; +} + #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count) { diff --git a/mm/init-mm.c b/mm/init-mm.c new file mode 100644 index 000000000000..57aba0da9668 --- /dev/null +++ b/mm/init-mm.c @@ -0,0 +1,20 @@ +#include <linux/mm_types.h> +#include <linux/rbtree.h> +#include <linux/rwsem.h> +#include <linux/spinlock.h> +#include <linux/list.h> +#include <linux/cpumask.h> + +#include <asm/atomic.h> +#include <asm/pgtable.h> + +struct mm_struct init_mm = { + .mm_rb = RB_ROOT, + .pgd = swapper_pg_dir, + .mm_users = ATOMIC_INIT(2), + .mm_count = ATOMIC_INIT(1), + .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem), + .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), + .mmlist = LIST_HEAD_INIT(init_mm.mmlist), + .cpu_vm_mask = CPU_MASK_ALL, +}; diff --git a/mm/internal.h b/mm/internal.h index 987bb03fbdd8..f290c4db528b 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -16,9 +16,6 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); -extern void prep_compound_page(struct page *page, unsigned long order); -extern void prep_compound_gigantic_page(struct page *page, unsigned long order); - static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_count, v); @@ -51,6 +48,8 @@ extern void putback_lru_page(struct page *page); */ extern unsigned long highest_memmap_pfn; extern void __free_pages_bootmem(struct page *page, unsigned int order); +extern void prep_compound_page(struct page *page, unsigned long order); + /* * function for dealing with page's order in buddy system. @@ -74,7 +73,6 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma) } #endif -#ifdef CONFIG_UNEVICTABLE_LRU /* * unevictable_migrate_page() called only from migrate_page_copy() to * migrate unevictable flag to new page. @@ -86,11 +84,6 @@ static inline void unevictable_migrate_page(struct page *new, struct page *old) if (TestClearPageUnevictable(old)) SetPageUnevictable(new); } -#else -static inline void unevictable_migrate_page(struct page *new, struct page *old) -{ -} -#endif #ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT /* @@ -150,23 +143,6 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) } } -/* - * free_page_mlock() -- clean up attempts to free and mlocked() page. - * Page should not be on lru, so no need to fix that up. - * free_pages_check() will verify... - */ -static inline void free_page_mlock(struct page *page) -{ - if (unlikely(TestClearPageMlocked(page))) { - unsigned long flags; - - local_irq_save(flags); - __dec_zone_page_state(page, NR_MLOCK); - __count_vm_event(UNEVICTABLE_MLOCKFREED); - local_irq_restore(flags); - } -} - #else /* CONFIG_HAVE_MLOCKED_PAGE_BIT */ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p) { @@ -175,7 +151,6 @@ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p) static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void mlock_migrate_page(struct page *new, struct page *old) { } -static inline void free_page_mlock(struct page *page) { } #endif /* CONFIG_HAVE_MLOCKED_PAGE_BIT */ @@ -284,4 +259,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int flags, struct page **pages, struct vm_area_struct **vmas); +#define ZONE_RECLAIM_NOSCAN -2 +#define ZONE_RECLAIM_FULL -1 +#define ZONE_RECLAIM_SOME 0 +#define ZONE_RECLAIM_SUCCESS 1 #endif diff --git a/mm/madvise.c b/mm/madvise.c index b9ce574827c8..76eb4193acdd 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -123,8 +123,7 @@ static long madvise_willneed(struct vm_area_struct * vma, end = vma->vm_end; end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - force_page_cache_readahead(file->f_mapping, - file, start, max_sane_readahead(end - start)); + force_page_cache_readahead(file->f_mapping, file, start, end - start); return 0; } @@ -239,12 +238,30 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, break; default: - error = -EINVAL; + BUG(); break; } return error; } +static int +madvise_behavior_valid(int behavior) +{ + switch (behavior) { + case MADV_DOFORK: + case MADV_DONTFORK: + case MADV_NORMAL: + case MADV_SEQUENTIAL: + case MADV_RANDOM: + case MADV_REMOVE: + case MADV_WILLNEED: + case MADV_DONTNEED: + return 1; + + default: + return 0; + } +} /* * The madvise(2) system call. * @@ -290,6 +307,9 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) int write; size_t len; + if (!madvise_behavior_valid(behavior)) + return error; + write = madvise_need_mmap_write(behavior); if (write) down_write(¤t->mm->mmap_sem); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 78eb8552818b..70db6e0a5eec 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -570,6 +570,17 @@ int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg) return 0; } +int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg) +{ + unsigned long active; + unsigned long inactive; + + inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE); + active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE); + + return (active > inactive); +} + unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, struct zone *zone, enum lru_list lru) diff --git a/mm/memory.c b/mm/memory.c index 4126dd16778c..d5d1653d60a6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1360,6 +1360,56 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, return i; } +/** + * get_user_pages() - pin user pages in memory + * @tsk: task_struct of target task + * @mm: mm_struct of target mm + * @start: starting user address + * @len: number of pages from start to pin + * @write: whether pages will be written to by the caller + * @force: whether to force write access even if user mapping is + * readonly. This will result in the page being COWed even + * in MAP_SHARED mappings. You do not want this. + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If len is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. vmas will only + * remain valid while mmap_sem is held. + * + * Must be called with mmap_sem held for read or write. + * + * get_user_pages walks a process's page tables and takes a reference to + * each struct page that each user address corresponds to at a given + * instant. That is, it takes the page that would be accessed if a user + * thread accesses the given user virtual address at that instant. + * + * This does not guarantee that the page exists in the user mappings when + * get_user_pages returns, and there may even be a completely different + * page there in some cases (eg. if mmapped pagecache has been invalidated + * and subsequently re faulted). However it does guarantee that the page + * won't be freed completely. And mostly callers simply care that the page + * contains data that was valid *at some point in time*. Typically, an IO + * or similar operation cannot guarantee anything stronger anyway because + * locks can't be held over the syscall boundary. + * + * If write=0, the page must not be written to. If the page is written to, + * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called + * after the page is finished with, and before put_page is called. + * + * get_user_pages is typically used for fewer-copy IO operations, to get a + * handle on the memory by some means other than accesses via the user virtual + * addresses. The pages may be submitted for DMA to devices or accessed via + * their kernel linear mapping (via the kmap APIs). Care should be taken to + * use the correct cache flushing APIs. + * + * See also get_user_pages_fast, for performance critical applications. + */ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int write, int force, struct page **pages, struct vm_area_struct **vmas) @@ -3053,22 +3103,13 @@ int in_gate_area_no_task(unsigned long addr) #endif /* __HAVE_ARCH_GATE_AREA */ -#ifdef CONFIG_HAVE_IOREMAP_PROT -int follow_phys(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned long *prot, resource_size_t *phys) +static int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; - pte_t *ptep, pte; - spinlock_t *ptl; - resource_size_t phys_addr = 0; - struct mm_struct *mm = vma->vm_mm; - int ret = -EINVAL; - - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - goto out; + pte_t *ptep; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) @@ -3086,22 +3127,71 @@ int follow_phys(struct vm_area_struct *vma, if (pmd_huge(*pmd)) goto out; - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!ptep) goto out; + if (!pte_present(*ptep)) + goto unlock; + *ptepp = ptep; + return 0; +unlock: + pte_unmap_unlock(ptep, *ptlp); +out: + return -EINVAL; +} +/** + * follow_pfn - look up PFN at a user virtual address + * @vma: memory mapping + * @address: user virtual address + * @pfn: location to store found PFN + * + * Only IO mappings and raw PFN mappings are allowed. + * + * Returns zero and the pfn at @pfn on success, -ve otherwise. + */ +int follow_pfn(struct vm_area_struct *vma, unsigned long address, + unsigned long *pfn) +{ + int ret = -EINVAL; + spinlock_t *ptl; + pte_t *ptep; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return ret; + + ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); + if (ret) + return ret; + *pfn = pte_pfn(*ptep); + pte_unmap_unlock(ptep, ptl); + return 0; +} +EXPORT_SYMBOL(follow_pfn); + +#ifdef CONFIG_HAVE_IOREMAP_PROT +int follow_phys(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned long *prot, resource_size_t *phys) +{ + int ret = -EINVAL; + pte_t *ptep, pte; + spinlock_t *ptl; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; + + if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) + goto out; pte = *ptep; - if (!pte_present(pte)) - goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; - phys_addr = pte_pfn(pte); - phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */ *prot = pgprot_val(pte_pgprot(pte)); - *phys = phys_addr; - ret = 0; + *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + ret = 0; unlock: pte_unmap_unlock(ptep, ptl); out: diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c083cf5fd6df..e4412a676c88 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -422,7 +422,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) zone->present_pages += onlined_pages; zone->zone_pgdat->node_present_pages += onlined_pages; - setup_per_zone_pages_min(); + setup_per_zone_wmarks(); + calculate_zone_inactive_ratio(zone); if (onlined_pages) { kswapd_run(zone_to_nid(zone)); node_set_state(zone_to_nid(zone), N_HIGH_MEMORY); @@ -832,6 +833,9 @@ repeat: totalram_pages -= offlined_pages; num_physpages -= offlined_pages; + setup_per_zone_wmarks(); + calculate_zone_inactive_ratio(zone); + vm_total_pages = nr_free_pagecache_pages(); writeback_set_ratelimit(); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3eb4a6fdc043..e08e2c4da63a 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -182,13 +182,54 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) return 0; } -/* Create a new policy */ +/* + * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if + * any, for the new policy. mpol_new() has already validated the nodes + * parameter with respect to the policy mode and flags. But, we need to + * handle an empty nodemask with MPOL_PREFERRED here. + * + * Must be called holding task's alloc_lock to protect task's mems_allowed + * and mempolicy. May also be called holding the mmap_semaphore for write. + */ +static int mpol_set_nodemask(struc |