From 23022aab1a90cc3117b3816c79aea3977bce09ff Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Mon, 14 Dec 2009 17:59:58 -0800 Subject: mm: hugetlb: fix hugepage memory leak in mincore() commit 4f16fc107d9c9b8a72aa19b189a9216e90a7aaef upstream. Most callers of pmd_none_or_clear_bad() check whether the target page is in a hugepage or not, but mincore() and walk_page_range() do not check it. So if we use mincore() on a hugepage on x86 machine, the hugepage memory is leaked as shown below. This patch fixes it by extending mincore() system call to support hugepages. Details ======= My test program (leak_mincore) works as follows: - creat() and mmap() a file on hugetlbfs (file size is 200MB == 100 hugepages,) - read()/write() something on it, - call mincore() for first ten pages and printf() the values of *vec - munmap() and unlink() the file on hugetlbfs Without my patch ---------------- $ cat /proc/meminfo| grep "HugePage" HugePages_Total: 1000 HugePages_Free: 1000 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ./leak_mincore vec[0] 0 vec[1] 0 vec[2] 0 vec[3] 0 vec[4] 0 vec[5] 0 vec[6] 0 vec[7] 0 vec[8] 0 vec[9] 0 $ cat /proc/meminfo |grep "HugePage" HugePages_Total: 1000 HugePages_Free: 999 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ls /hugetlbfs/ $ Return values in *vec from mincore() are set to 0, while the hugepage should be in memory, and 1 hugepage is still accounted as used while there is no file on hugetlbfs. With my patch ------------- $ cat /proc/meminfo| grep "HugePage" HugePages_Total: 1000 HugePages_Free: 1000 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ./leak_mincore vec[0] 1 vec[1] 1 vec[2] 1 vec[3] 1 vec[4] 1 vec[5] 1 vec[6] 1 vec[7] 1 vec[8] 1 vec[9] 1 $ cat /proc/meminfo |grep "HugePage" HugePages_Total: 1000 HugePages_Free: 1000 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ls /hugetlbfs/ $ Return value in *vec set to 1 and no memory leaks. [akpm@linux-foundation.org: cleanup] [akpm@linux-foundation.org: build fix] Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Wu Fengguang Cc: Hugh Dickins Cc: Mel Gorman Cc: Lee Schermerhorn Cc: Andy Whitcroft Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/mincore.c | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'mm') diff --git a/mm/mincore.c b/mm/mincore.c index 8cb508f84ea4..7a3436ef39eb 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -72,6 +73,42 @@ static long do_mincore(unsigned long addr, unsigned char *vec, unsigned long pag if (!vma || addr < vma->vm_start) return -ENOMEM; +#ifdef CONFIG_HUGETLB_PAGE + if (is_vm_hugetlb_page(vma)) { + struct hstate *h; + unsigned long nr_huge; + unsigned char present; + + i = 0; + nr = min(pages, (vma->vm_end - addr) >> PAGE_SHIFT); + h = hstate_vma(vma); + nr_huge = ((addr + pages * PAGE_SIZE - 1) >> huge_page_shift(h)) + - (addr >> huge_page_shift(h)) + 1; + nr_huge = min(nr_huge, + (vma->vm_end - addr) >> huge_page_shift(h)); + while (1) { + /* hugepage always in RAM for now, + * but generally it needs to be check */ + ptep = huge_pte_offset(current->mm, + addr & huge_page_mask(h)); + present = !!(ptep && + !huge_pte_none(huge_ptep_get(ptep))); + while (1) { + vec[i++] = present; + addr += PAGE_SIZE; + /* reach buffer limit */ + if (i == nr) + return nr; + /* check hugepage border */ + if (!((addr & ~huge_page_mask(h)) + >> PAGE_SHIFT)) + break; + } + } + return nr; + } +#endif + /* * Calculate how many pages there are left in the last level of the * PTE array for our address. -- cgit v1.2.3 From 0a0fa09874289cbfce7e94bc1b61b57e7751a63f Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Mon, 14 Dec 2009 17:59:59 -0800 Subject: mm: hugetlb: fix hugepage memory leak in walk_page_range() commit d33b9f45bd24a6391bc05e2b5a13c1b5787ca9c2 upstream. Most callers of pmd_none_or_clear_bad() check whether the target page is in a hugepage or not, but walk_page_range() do not check it. So if we read /proc/pid/pagemap for the hugepage on x86 machine, the hugepage memory is leaked as shown below. This patch fixes it. Details ======= My test program (leak_pagemap) works as follows: - creat() and mmap() a file on hugetlbfs (file size is 200MB == 100 hugepages,) - read()/write() something on it, - call page-types with option -p (walk around the page tables), - munmap() and unlink() the file on hugetlbfs Without my patches ------------------ $ cat /proc/meminfo |grep "HugePage" HugePages_Total: 1000 HugePages_Free: 1000 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ./leak_pagemap [snip output] $ cat /proc/meminfo |grep "HugePage" HugePages_Total: 1000 HugePages_Free: 900 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ls /hugetlbfs/ $ 100 hugepages are accounted as used while there is no file on hugetlbfs. With my patches --------------- $ cat /proc/meminfo |grep "HugePage" HugePages_Total: 1000 HugePages_Free: 1000 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ./leak_pagemap [snip output] $ cat /proc/meminfo |grep "HugePage" HugePages_Total: 1000 HugePages_Free: 1000 HugePages_Rsvd: 0 HugePages_Surp: 0 $ ls /hugetlbfs $ No memory leaks. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Wu Fengguang Cc: Hugh Dickins Cc: Mel Gorman Cc: Lee Schermerhorn Cc: Andy Whitcroft Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/pagewalk.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/pagewalk.c b/mm/pagewalk.c index d5878bed7841..a286915e23ef 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -1,6 +1,7 @@ #include #include #include +#include static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -107,6 +108,7 @@ int walk_page_range(unsigned long addr, unsigned long end, pgd_t *pgd; unsigned long next; int err = 0; + struct vm_area_struct *vma; if (addr >= end) return err; @@ -117,11 +119,22 @@ int walk_page_range(unsigned long addr, unsigned long end, pgd = pgd_offset(walk->mm, addr); do { next = pgd_addr_end(addr, end); + + /* skip hugetlb vma to avoid hugepage PMD being cleared + * in pmd_none_or_clear_bad(). */ + vma = find_vma(walk->mm, addr); + if (vma && is_vm_hugetlb_page(vma)) { + if (vma->vm_end < next) + next = vma->vm_end; + continue; + } + if (pgd_none_or_clear_bad(pgd)) { if (walk->pte_hole) err = walk->pte_hole(addr, next, walk); if (err) break; + pgd++; continue; } if (walk->pgd_entry) @@ -131,7 +144,8 @@ int walk_page_range(unsigned long addr, unsigned long end, err = walk_pud_range(pgd, addr, next, walk); if (err) break; - } while (pgd++, addr = next, addr != end); + pgd++; + } while (addr = next, addr != end); return err; } -- cgit v1.2.3 From 3dac78c65b4c503199f1ef157e2934eea33425e8 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 15 Dec 2009 16:47:01 -0800 Subject: memcg: fix memory.memsw.usage_in_bytes for root cgroup commit cd9b45b78a61e8df250e69385c74e729e5b66abf upstream. A memory cgroup has a memory.memsw.usage_in_bytes file. It shows the sum of the usage of pages and swapents in the cgroup. Presently the root cgroup's memsw.usage_in_bytes shows the wrong value - the number of swapents are not added. So take MEM_CGROUP_STAT_SWAPOUT into account. Signed-off-by: Kirill A. Shutemov Reviewed-by: Daisuke Nishimura Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/memcontrol.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f99f5991d6bb..63140151b618 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2541,6 +2541,7 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) val += idx_val; mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_SWAPOUT, &idx_val); + val += idx_val; val <<= PAGE_SHIFT; } else val = res_counter_read_u64(&mem->memsw, name); -- cgit v1.2.3 From f0cc8412be0a164f9472f161dfd74fc1ca6ac284 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 10 Dec 2009 08:43:16 +0900 Subject: vmalloc: conditionalize build of pcpu_get_vm_areas() No matching upstream commit as it was resolved differently there. pcpu_get_vm_areas() is used only when dynamic percpu allocator is used by the architecture. In 2.6.32, ia64 doesn't use dynamic percpu allocator and has a macro which makes pcpu_get_vm_areas() buggy via local/global variable aliasing and triggers compile warning. The problem is fixed in upstream and ia64 uses dynamic percpu allocators, so the only left issue is inclusion of unnecessary code and compile warning on ia64 on 2.6.32. Don't build pcpu_get_vm_areas() if legacy percpu allocator is in use. Signed-off-by: Tejun Heo Reported-by: Jan Beulich Signed-off-by: Greg Kroah-Hartman --- mm/vmalloc.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 0f551a4a44cd..775872681d0c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1993,6 +1993,7 @@ void free_vm_area(struct vm_struct *area) } EXPORT_SYMBOL_GPL(free_vm_area); +#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA static struct vmap_area *node_to_va(struct rb_node *n) { return n ? rb_entry(n, struct vmap_area, rb_node) : NULL; @@ -2257,6 +2258,7 @@ err_free: kfree(vms); return NULL; } +#endif /** * pcpu_free_vm_areas - free vmalloc areas for percpu allocator -- cgit v1.2.3 From 1c723eb018de64d2159e9ce66ec6df0d1798e1e3 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Dec 2009 17:59:04 -0800 Subject: mm: sigbus instead of abusing oom commit d99be1a8ecf377c2c9b3372d36411ad6547bbd4c upstream. When do_nonlinear_fault() realizes that the page table must have been corrupted for it to have been called, it does print_bad_pte() and returns ... VM_FAULT_OOM, which is hard to understand. It made some sense when I did it for 2.6.15, when do_page_fault() just killed the current process; but nowadays it lets the OOM killer decide who to kill - so page table corruption in one process would be liable to kill another. Change it to return VM_FAULT_SIGBUS instead: that doesn't guarantee that the process will be killed, but is good enough for such a rare abnormality, accompanied as it is by the "BUG: Bad page map" message. And recent HWPOISON work has copied that code into do_swap_page(), when it finds an impossible swap entry: fix that to VM_FAULT_SIGBUS too. Signed-off-by: Hugh Dickins Cc: Izik Eidus Cc: Andrea Arcangeli Cc: Nick Piggin Reviewed-by: KOSAKI Motohiro Cc: Rik van Riel Cc: Lee Schermerhorn Cc: Andi Kleen Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Wu Fengguang Reviewed-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/memory.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 6ab19dd4a199..4e5945588c73 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2514,7 +2514,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, ret = VM_FAULT_HWPOISON; } else { print_bad_pte(vma, address, orig_pte, NULL); - ret = VM_FAULT_OOM; + ret = VM_FAULT_SIGBUS; } goto out; } @@ -2910,7 +2910,7 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, * Page table corrupted: show pte and kill process. */ print_bad_pte(vma, address, orig_pte, NULL); - return VM_FAULT_OOM; + return VM_FAULT_SIGBUS; } pgoff = pte_to_pgoff(orig_pte); -- cgit v1.2.3 From 0399123f3dcce1a515d021107ec0fb4413ca3efa Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 15 Dec 2009 19:27:45 +0000 Subject: NOMMU: Optimise away the {dac_,}mmap_min_addr tests commit 6e1415467614e854fee660ff6648bd10fa976e95 upstream. In NOMMU mode clamp dac_mmap_min_addr to zero to cause the tests on it to be skipped by the compiler. We do this as the minimum mmap address doesn't make any sense in NOMMU mode. mmap_min_addr and round_hint_to_min() can be discarded entirely in NOMMU mode. Signed-off-by: David Howells Acked-by: Eric Paris Signed-off-by: James Morris Signed-off-by: Greg Kroah-Hartman --- mm/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/Kconfig b/mm/Kconfig index 44cf6f0a3a6d..2c19c0bac10e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -227,6 +227,7 @@ config KSM config DEFAULT_MMAP_MIN_ADDR int "Low address space to protect from user allocation" + depends on MMU default 4096 help This is the portion of low virtual memory which should be protected -- cgit v1.2.3 From ad46fed9c9b596b6ece5728aad3722a9c4acc8cb Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Tue, 15 Dec 2009 16:47:12 -0800 Subject: memcg: avoid oom-killing innocent task in case of use_hierarchy commit d31f56dbf8bafaacb0c617f9a6f137498d5c7aed upstream. task_in_mem_cgroup(), which is called by select_bad_process() to check whether a task can be a candidate for being oom-killed from memcg's limit, checks "curr->use_hierarchy"("curr" is the mem_cgroup the task belongs to). But this check return true(it's false positive) when: /aa use_hierarchy == 0 <- hitting limit /aa/00 use_hierarchy == 1 <- the task belongs to This leads to killing an innocent task in aa/00. This patch is a fix for this bug. And this patch also fixes the arg for mem_cgroup_print_oom_info(). We should print information of mem_cgroup which the task being killed, not current, belongs to. Signed-off-by: Daisuke Nishimura Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/memcontrol.c | 8 +++++++- mm/oom_kill.c | 2 +- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 63140151b618..5dc10374d769 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -758,7 +758,13 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem) task_unlock(task); if (!curr) return 0; - if (curr->use_hierarchy) + /* + * We should check use_hierarchy of "mem" not "curr". Because checking + * use_hierarchy of "curr" here make this function true if hierarchy is + * enabled in "curr" and "curr" is a child of "mem" in *cgroup* + * hierarchy(even if use_hierarchy is disabled in "mem"). + */ + if (mem->use_hierarchy) ret = css_is_ancestor(&curr->css, &mem->css); else ret = (curr == mem); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index ea2147dabba6..9092b43f07fa 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -404,7 +404,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); - mem_cgroup_print_oom_info(mem, current); + mem_cgroup_print_oom_info(mem, p); show_mem(); if (sysctl_oom_dump_tasks) dump_tasks(mem); -- cgit v1.2.3 From b2ea8cb9c8f1937cb80b9beb50548a05bfc37819 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 14 Dec 2009 17:59:48 -0800 Subject: vmscan: do not evict inactive pages when skipping an active list scan commit b39415b2731d7dec5e612d2d12595da82399eedf upstream. In AIM7 runs, recent kernels start swapping out anonymous pages well before they should. This is due to shrink_list falling through to shrink_inactive_list if !inactive_anon_is_low(zone, sc), when all we really wanted to do is pre-age some anonymous pages to give them extra time to be referenced while on the inactive list. The obvious fix is to make sure that shrink_list does not fall through to scanning/reclaiming inactive pages when we called it to scan one of the active lists. This change should be safe because the loop in shrink_zone ensures that we will still shrink the anon and file inactive lists whenever we should. [kosaki.motohiro@jp.fujitsu.com: inactive_file_is_low() should be inactive_anon_is_low()] Reported-by: Larry Woodman Signed-off-by: Rik van Riel Acked-by: Johannes Weiner Cc: Tomasz Chmielewski Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Cc: Rik Theys Signed-off-by: Greg Kroah-Hartman --- mm/vmscan.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/vmscan.c b/mm/vmscan.c index 777af57fd8c8..692807f2228b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1464,20 +1464,26 @@ static int inactive_file_is_low(struct zone *zone, struct scan_control *sc) return low; } +static int inactive_list_is_low(struct zone *zone, struct scan_control *sc, + int file) +{ + if (file) + return inactive_file_is_low(zone, sc); + else + return inactive_anon_is_low(zone, sc); +} + static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct zone *zone, struct scan_control *sc, int priority) { int file = is_file_lru(lru); - if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) { - shrink_active_list(nr_to_scan, zone, sc, priority, file); + if (is_active_lru(lru)) { + if (inactive_list_is_low(zone, sc, file)) + shrink_active_list(nr_to_scan, zone, sc, priority, file); return 0; } - if (lru == LRU_ACTIVE_ANON && inactive_anon_is_low(zone, sc)) { - shrink_active_list(nr_to_scan, zone, sc, priority, file); - return 0; - } return shrink_inactive_list(nr_to_scan, zone, sc, priority, file); } -- cgit v1.2.3 From 8ac9e802007e99534ec66af850ef7b099df27499 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 30 Dec 2009 23:00:30 +0000 Subject: ksm: fix mlockfreed to munlocked 2.6.33-rc1 commit 73848b4684e84a84cfd1555af78d41158f31e16b, adjusted to include 31e855ea7173bdb0520f9684580423a9560f66e0's movement of the unlock_page(oldpage), but omit other intervening cleanups. When KSM merges an mlocked page, it has been forgetting to munlock it: that's been left to free_page_mlock(), which reports it in /proc/vmstat as unevictable_pgs_mlockfreed instead of unevictable_pgs_munlocked, which indicates that such pages _might_ be left unevictable for long after they should be evictable. Call munlock_vma_page() to fix that. Signed-off-by: Hugh Dickins Signed-off-by: Greg Kroah-Hartman --- mm/internal.h | 3 ++- mm/ksm.c | 14 +++++++------- mm/mlock.c | 4 ++-- 3 files changed, 11 insertions(+), 10 deletions(-) (limited to 'mm') diff --git a/mm/internal.h b/mm/internal.h index 22ec8d2b0fb8..17bc0df273bb 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -107,9 +107,10 @@ static inline int is_mlocked_vma(struct vm_area_struct *vma, struct page *page) } /* - * must be called with vma's mmap_sem held for read, and page locked. + * must be called with vma's mmap_sem held for read or write, and page locked. */ extern void mlock_vma_page(struct page *page); +extern void munlock_vma_page(struct page *page); /* * Clear the page's PageMlocked(). This can be useful in a situation where diff --git a/mm/ksm.c b/mm/ksm.c index 5575f8628fef..e9501f833374 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -34,6 +34,7 @@ #include #include +#include "internal.h" /* * A few notes about the KSM scanning process, @@ -767,15 +768,14 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, * ptes are necessarily already write-protected. But in either * case, we need to lock and check page_count is not raised. */ - if (write_protect_page(vma, oldpage, &orig_pte)) { - unlock_page(oldpage); - goto out_putpage; - } - unlock_page(oldpage); - - if (pages_identical(oldpage, newpage)) + if (write_protect_page(vma, oldpage, &orig_pte) == 0 && + pages_identical(oldpage, newpage)) err = replace_page(vma, oldpage, newpage, orig_pte); + if ((vma->vm_flags & VM_LOCKED) && !err) + munlock_vma_page(oldpage); + + unlock_page(oldpage); out_putpage: put_page(oldpage); put_page(newpage); diff --git a/mm/mlock.c b/mm/mlock.c index bd6f0e466f6c..2e05c97b04f5 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -99,14 +99,14 @@ void mlock_vma_page(struct page *page) * not get another chance to clear PageMlocked. If we successfully * isolate the page and try_to_munlock() detects other VM_LOCKED vmas * mapping the page, it will restore the PageMlocked state, unless the page - * is mapped in a non-linear vma. So, we go ahead and SetPageMlocked(), + * is mapped in a non-linear vma. So, we go ahead and ClearPageMlocked(), * perhaps redundantly. * If we lose the isolation race, and the page is mapped by other VM_LOCKED * vmas, we'll detect this in vmscan--via try_to_munlock() or try_to_unmap() * either of which will restore the PageMlocked state by calling * mlock_vma_page() above, if it can grab the vma's mmap sem. */ -static void munlock_vma_page(struct page *page) +void munlock_vma_page(struct page *page) { BUG_ON(!PageLocked(page)); -- cgit v1.2.3 From 1f51eb3a881359e97dc2c228e55c83fba598e349 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 14 Jan 2010 11:39:39 -0800 Subject: untangle the do_mremap() mess This backports the following upstream commits all as one patch: 54f5de709984bae0d31d823ff03de755f9dcac54 ecc1a8993751de4e82eb18640d631dae1f626bd6 1a0ef85f84feb13f07b604fcf5b90ef7c2b5c82f f106af4e90eadd76cfc0b5325f659619e08fb762 097eed103862f9c6a97f2e415e21d1134017b135 935874141df839c706cd6cdc438e85eb69d1525e 0ec62d290912bb4b989be7563851bc364ec73b56 c4caa778157dbbf04116f0ac2111e389b5cd7a29 2ea1d13f64efdf49319e86c87d9ba38c30902782 570dcf2c15463842e384eb597a87c1e39bead99b 564b3bffc619dcbdd160de597b0547a7017ea010 0067bd8a55862ac9dd212bd1c4f6f5bff1ca1301 f8b7256096a20436f6d0926747e3ac3d64c81d24 8c7b49b3ecd48923eb64ff57e07a1cdb74782970 9206de95b1ea68357996ec02be5db0638a0de2c1 2c6a10161d0b5fc047b5bd81b03693b9af99fab5 05d72faa6d13c9d857478a5d35c85db9adada685 bb52d6694002b9d632bb355f64daa045c6293a4e e77414e0aad6a1b063ba5e5750c582c75327ea6a aa65607373a4daf2010e8c3867b6317619f3c1a3 Backport done by Greg Kroah-Hartman. Only minor tweaks were needed. Cc: David S. Miller Cc: Hugh Dickins Cc: Paul Mundt Cc: Russell King Cc: Linus Torvalds Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- mm/mmap.c | 42 +++-------- mm/mremap.c | 241 +++++++++++++++++++++++++++++++++++++++--------------------- mm/util.c | 44 +++++++++++ 3 files changed, 211 insertions(+), 116 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index 73f5e4b64010..ae197468b352 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -932,13 +932,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); - error = arch_mmap_check(addr, len, flags); - if (error) - return error; - /* Careful about overflows.. */ len = PAGE_ALIGN(len); - if (!len || len > TASK_SIZE) + if (!len) return -ENOMEM; /* offset overflow? */ @@ -949,24 +945,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, if (mm->map_count > sysctl_max_map_count) return -ENOMEM; - if (flags & MAP_HUGETLB) { - struct user_struct *user = NULL; - if (file) - return -EINVAL; - - /* - * VM_NORESERVE is used because the reservations will be - * taken when vm_ops->mmap() is called - * A dummy user value is used because we are not locking - * memory so no accounting is necessary - */ - len = ALIGN(len, huge_page_size(&default_hstate)); - file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, - &user, HUGETLB_ANONHUGE_INODE); - if (IS_ERR(file)) - return PTR_ERR(file); - } - /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ @@ -1459,6 +1437,14 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); + unsigned long error = arch_mmap_check(addr, len, flags); + if (error) + return error; + + /* Careful about overflows.. */ + if (len > TASK_SIZE) + return -ENOMEM; + get_area = current->mm->get_unmapped_area; if (file && file->f_op && file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; @@ -2003,20 +1989,14 @@ unsigned long do_brk(unsigned long addr, unsigned long len) if (!len) return addr; - if ((addr + len) > TASK_SIZE || (addr + len) < addr) - return -EINVAL; - - if (is_hugepage_only_range(mm, addr, len)) - return -EINVAL; - error = security_file_mmap(NULL, 0, 0, 0, addr, 1); if (error) return error; flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; - error = arch_mmap_check(addr, len, flags); - if (error) + error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); + if (error & ~PAGE_MASK) return error; /* diff --git a/mm/mremap.c b/mm/mremap.c index 97bff2547719..845190898d59 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -261,6 +261,137 @@ static unsigned long move_vma(struct vm_area_struct *vma, return new_addr; } +static struct vm_area_struct *vma_to_resize(unsigned long addr, + unsigned long old_len, unsigned long new_len, unsigned long *p) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma = find_vma(mm, addr); + + if (!vma || vma->vm_start > addr) + goto Efault; + + if (is_vm_hugetlb_page(vma)) + goto Einval; + + /* We can't remap across vm area boundaries */ + if (old_len > vma->vm_end - addr) + goto Efault; + + if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) { + if (new_len > old_len) + goto Efault; + } + + if (vma->vm_flags & VM_LOCKED) { + unsigned long locked, lock_limit; + locked = mm->locked_vm << PAGE_SHIFT; + lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; + locked += new_len - old_len; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) + goto Eagain; + } + + if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) + goto Enomem; + + if (vma->vm_flags & VM_ACCOUNT) { + unsigned long charged = (new_len - old_len) >> PAGE_SHIFT; + if (security_vm_enough_memory(charged)) + goto Efault; + *p = charged; + } + + return vma; + +Efault: /* very odd choice for most of the cases, but... */ + return ERR_PTR(-EFAULT); +Einval: + return ERR_PTR(-EINVAL); +Enomem: + return ERR_PTR(-ENOMEM); +Eagain: + return ERR_PTR(-EAGAIN); +} + +static unsigned long mremap_to(unsigned long addr, + unsigned long old_len, unsigned long new_addr, + unsigned long new_len) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long ret = -EINVAL; + unsigned long charged = 0; + unsigned long map_flags; + + if (new_addr & ~PAGE_MASK) + goto out; + + if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len) + goto out; + + /* Check if the location we're moving into overlaps the + * old location at all, and fail if it does. + */ + if ((new_addr <= addr) && (new_addr+new_len) > addr) + goto out; + + if ((addr <= new_addr) && (addr+old_len) > new_addr) + goto out; + + ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); + if (ret) + goto out; + + ret = do_munmap(mm, new_addr, new_len); + if (ret) + goto out; + + if (old_len >= new_len) { + ret = do_munmap(mm, addr+new_len, old_len - new_len); + if (ret && old_len != new_len) + goto out; + old_len = new_len; + } + + vma = vma_to_resize(addr, old_len, new_len, &charged); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; + } + + map_flags = MAP_FIXED; + if (vma->vm_flags & VM_MAYSHARE) + map_flags |= MAP_SHARED; + + ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff + + ((addr - vma->vm_start) >> PAGE_SHIFT), + map_flags); + if (ret & ~PAGE_MASK) + goto out1; + + ret = move_vma(vma, addr, old_len, new_len, new_addr); + if (!(ret & ~PAGE_MASK)) + goto out; +out1: + vm_unacct_memory(charged); + +out: + return ret; +} + +static int vma_expandable(struct vm_area_struct *vma, unsigned long delta) +{ + unsigned long end = vma->vm_end + delta; + if (end < vma->vm_end) /* overflow */ + return 0; + if (vma->vm_next && vma->vm_next->vm_start < end) /* intersection */ + return 0; + if (get_unmapped_area(NULL, vma->vm_start, end - vma->vm_start, + 0, MAP_FIXED) & ~PAGE_MASK) + return 0; + return 1; +} + /* * Expand (or shrink) an existing mapping, potentially moving it at the * same time (controlled by the MREMAP_MAYMOVE flag and available VM space) @@ -294,32 +425,10 @@ unsigned long do_mremap(unsigned long addr, if (!new_len) goto out; - /* new_addr is only valid if MREMAP_FIXED is specified */ if (flags & MREMAP_FIXED) { - if (new_addr & ~PAGE_MASK) - goto out; - if (!(flags & MREMAP_MAYMOVE)) - goto out; - - if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len) - goto out; - - /* Check if the location we're moving into overlaps the - * old location at all, and fail if it does. - */ - if ((new_addr <= addr) && (new_addr+new_len) > addr) - goto out; - - if ((addr <= new_addr) && (addr+old_len) > new_addr) - goto out; - - ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); - if (ret) - goto out; - - ret = do_munmap(mm, new_addr, new_len); - if (ret) - goto out; + if (flags & MREMAP_MAYMOVE) + ret = mremap_to(addr, old_len, new_addr, new_len); + goto out; } /* @@ -332,60 +441,23 @@ unsigned long do_mremap(unsigned long addr, if (ret && old_len != new_len) goto out; ret = addr; - if (!(flags & MREMAP_FIXED) || (new_addr == addr)) - goto out; - old_len = new_len; + goto out; } /* - * Ok, we need to grow.. or relocate. + * Ok, we need to grow.. */ - ret = -EFAULT; - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) - goto out; - if (is_vm_hugetlb_page(vma)) { - ret = -EINVAL; - goto out; - } - /* We can't remap across vm area boundaries */ - if (old_len > vma->vm_end - addr) - goto out; - if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) { - if (new_len > old_len) - goto out; - } - if (vma->vm_flags & VM_LOCKED) { - unsigned long locked, lock_limit; - locked = mm->locked_vm << PAGE_SHIFT; - lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; - locked += new_len - old_len; - ret = -EAGAIN; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - goto out; - } - if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) { - ret = -ENOMEM; + vma = vma_to_resize(addr, old_len, new_len, &charged); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); goto out; } - if (vma->vm_flags & VM_ACCOUNT) { - charged = (new_len - old_len) >> PAGE_SHIFT; - if (security_vm_enough_memory(charged)) - goto out_nc; - } - /* old_len exactly to the end of the area.. - * And we're not relocating the area. */ - if (old_len == vma->vm_end - addr && - !((flags & MREMAP_FIXED) && (addr != new_addr)) && - (old_len != new_len || !(flags & MREMAP_MAYMOVE))) { - unsigned long max_addr = TASK_SIZE; - if (vma->vm_next) - max_addr = vma->vm_next->vm_start; + if (old_len == vma->vm_end - addr) { /* can we just expand the current mapping? */ - if (max_addr - addr >= new_len) { + if (vma_expandable(vma, new_len - old_len)) { int pages = (new_len - old_len) >> PAGE_SHIFT; vma_adjust(vma, vma->vm_start, @@ -409,28 +481,27 @@ unsigned long do_mremap(unsigned long addr, */ ret = -ENOMEM; if (flags & MREMAP_MAYMOVE) { - if (!(flags & MREMAP_FIXED)) { - unsigned long map_flags = 0; - if (vma->vm_flags & VM_MAYSHARE) - map_flags |= MAP_SHARED; - - new_addr = get_unmapped_area(vma->vm_file, 0, new_len, - vma->vm_pgoff, map_flags); - if (new_addr & ~PAGE_MASK) { - ret = new_addr; - goto out; - } - - ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); - if (ret) - goto out; + unsigned long map_flags = 0; + if (vma->vm_flags & VM_MAYSHARE) + map_flags |= MAP_SHARED; + + new_addr = get_unmapped_area(vma->vm_file, 0, new_len, + vma->vm_pgoff + + ((addr - vma->vm_start) >> PAGE_SHIFT), + map_flags); + if (new_addr & ~PAGE_MASK) { + ret = new_addr; + goto out; } + + ret = security_file_mmap(NULL, 0, 0, 0, new_addr, 1); + if (ret) + goto out; ret = move_vma(vma, addr, old_len, new_len, new_addr); } out: if (ret & ~PAGE_MASK) vm_unacct_memory(charged); -out_nc: return ret; } diff --git a/mm/util.c b/mm/util.c index 7c35ad95f927..b377ce430803 100644 --- a/mm/util.c +++ b/mm/util.c @@ -4,6 +4,10 @@ #include #include #include +#include +#include +#include +#include #include #define CREATE_TRACE_POINTS @@ -268,6 +272,46 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start, } EXPORT_SYMBOL_GPL(get_user_pages_fast); +SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, pgoff) +{ + struct file * file = NULL; + unsigned long retval = -EBADF; + + if (!(flags & MAP_ANONYMOUS)) { + if (unlikely(flags & MAP_HUGETLB)) + return -EINVAL; + file = fget(fd); + if (!file) + goto out; + } else if (flags & MAP_HUGETLB) { + struct user_struct *user = NULL; + /* + * VM_NORESERVE is used because the reservations will be + * taken when vm_ops->mmap() is called + * A dummy user value is used because we are not locking + * memory so no accounting is necessary + */ + len = ALIGN(len, huge_page_size(&default_hstate)); + file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, + &user, HUGETLB_ANONHUGE_INODE); + if (IS_ERR(file)) + return PTR_ERR(file); + } + + flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + + down_write(¤t->mm->mmap_sem); + retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff); + up_write(¤t->mm->mmap_sem); + + if (file) + fput(file); +out: + return retval; +} + /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); -- cgit v1.2.3 From 4334ab76da3dc18a531948882ff6247764d96ea8 Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Fri, 15 Jan 2010 17:01:30 -0800 Subject: memcg: ensure list is empty at rmdir commit fce66477578d081f19aef5ea218664ff7758c33a upstream. Current mem_cgroup_force_empty() only ensures mem->res.usage == 0 on success. But this doesn't guarantee memcg's LRU is really empty, because there are some cases in which !PageCgrupUsed pages exist on memcg's LRU. For example: - Pages can be uncharged by its owner process while they are on LRU. - race between mem_cgroup_add_lru_list() and __mem_cgroup_uncharge_common(). So there can be a case in which the usage is zero but some of the LRUs are not empty. OTOH, mem_cgroup_del_lru_list(), which can be called asynchronously with rmdir, accesses the mem_cgroup, so this access can cause a problem if it races with rmdir because the mem_cgroup might have been freed by rmdir. Actually, I saw a bug which seems to be caused by this race. [1530745.949906] BUG: unable to handle kernel NULL pointer dereference at 0000000000000230 [1530745.950651] IP: [] mem_cgroup_del_lru_list+0x30/0x80 [1530745.950651] PGD 3863de067 PUD 3862c7067 PMD 0 [1530745.950651] Oops: 0002 [#1] SMP [1530745.950651] last sysfs file: /sys/devices/system/cpu/cpu7/cache/index1/shared_cpu_map [1530745.950651] CPU 3 [1530745.950651] Modules linked in: configs ipt_REJECT xt_tcpudp iptable_filter ip_tables x_tables bridge stp nfsd nfs_acl auth_rpcgss exportfs autofs4 hidp rfcomm l2cap crc16 bluetooth lockd sunrpc ib_iser rdma_cm ib_cm iw_cm ib_sa ib_mad ib_core ib_addr iscsi_tcp bnx2i cnic uio ipv6 cxgb3i cxgb3 mdio libiscsi_tcp libiscsi scsi_transport_iscsi dm_mirror dm_multipath scsi_dh video output sbs sbshc battery ac lp kvm_intel kvm sg ide_cd_mod cdrom serio_raw tpm_tis tpm tpm_bios acpi_memhotplug button parport_pc parport rtc_cmos rtc_core rtc_lib e1000 i2c_i801 i2c_core pcspkr dm_region_hash dm_log dm_mod ata_piix libata shpchp megaraid_mbox sd_mod scsi_mod megaraid_mm ext3 jbd uhci_hcd ohci_hcd ehci_hcd [last unloaded: freq_table] [1530745.950651] Pid: 19653, comm: shmem_test_02 Tainted: G M 2.6.32-mm1-00701-g2b04386 #3 Express5800/140Rd-4 [N8100-1065] [1530745.950651] RIP: 0010:[] [] mem_cgroup_del_lru_list+0x30/0x80 [1530745.950651] RSP: 0018:ffff8803863ddcb8 EFLAGS: 00010002 [1530745.950651] RAX: 00000000000001e0 RBX: ffff8803abc02238 RCX: 00000000000001e0 [1530745.950651] RDX: 0000000000000000 RSI: ffff88038611a000 RDI: ffff8803abc02238 [1530745.950651] RBP: ffff8803863ddcc8 R08: 0000000000000002 R09: ffff8803a04c8643 [1530745.950651] R10: 0000000000000000 R11: ffffffff810c7333 R12: 0000000000000000 [1530745.950651] R13: ffff880000017f00 R14: 0000000000000092 R15: ffff8800179d0310 [1530745.950651] FS: 0000000000000000(0000) GS:ffff880017800000(0000) knlGS:0000000000000000 [1530745.950651] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [1530745.950651] CR2: 0000000000000230 CR3: 0000000379d87000 CR4: 00000000000006e0 [1530745.950651] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [1530745.950651] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [1530745.950651] Process shmem_test_02 (pid: 19653, threadinfo ffff8803863dc000, task ffff88038612a8a0) [1530745.950651] Stack: [1530745.950651] ffffea00040c2fe8 0000000000000000 ffff8803863ddd98 ffffffff810c739a [1530745.950651] <0> 00000000863ddd18 000000000000000c 0000000000000000 0000000000000000 [1530745.950651] <0> 0000000000000002 0000000000000000 ffff8803863ddd68 0000000000000046 [1530745.950651] Call Trace: [1530745.950651] [] release_pages+0x142/0x1e7 [1530745.950651] [] ? pagevec_move_tail+0x6e/0x112 [1530745.950651] [] pagevec_move_tail+0xfd/0x112 [1530745.950651] [] lru_add_drain+0x76/0x94 [1530745.950651] [] exit_mmap+0x6e/0x145 [1530745.950651] [] mmput+0x5e/0xcf [1530745.950651] [] exit_mm+0x11c/0x129 [1530745.950651] [] ? audit_free+0x196/0x1c9 [1530745.950651] [] do_exit+0x1f5/0x6b7 [1530745.950651] [] ? up_read+0x2b/0x2f [1530745.950651] [] ? lockdep_sys_exit_thunk+0x35/0x67 [1530745.950651] [] do_group_exit+0x83/0xb0 [1530745.950651] [] sys_exit_group+0x17/0x1b [1530745.950651] [] system_call_fastpath+0x16/0x1b [1530745.950651] Code: 54 53 0f 1f 44 00 00 83 3d cc 29 7c 00 00 41 89 f4 75 63 eb 4e 48 83 7b 08 00 75 04 0f 0b eb fe 48 89 df e8 18 f3 ff ff 44 89 e2 <48> ff 4c d0 50 48 8b 05 2b 2d 7c 00 48 39 43 08 74 39 48 8b 4b [1530745.950651] RIP [] mem_cgroup_del_lru_list+0x30/0x80 [1530745.950651] RSP [1530745.950651] CR2: 0000000000000230 [1530745.950651] ---[ end trace c3419c1bb8acc34f ]--- [1530745.950651] Fixing recursive fault but reboot is needed! The problem here is pages on LRU may contain pointer to stale memcg. To make res->usage to be 0, all pages on memcg must be uncharged or moved to another(parent) memcg. Moved page_cgroup have already removed from original LRU, but uncharged page_cgroup contains pointer to memcg withou PCG_USED bit. (This asynchronous LRU work is for improving performance.) If PCG_USED bit is not set, page_cgroup will never be added to memcg's LRU. So, about pages not on LRU, they never access stale pointer. Then, what we have to take care of is page_cgroup _on_ LRU list. This patch fixes this problem by making mem_cgroup_force_empty() visit all LRUs before exiting its loop and guarantee there are no pages on its LRU. Signed-off-by: Daisuke Nishimura Acked-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/memcontrol.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5dc10374d769..66035bf92612 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2381,7 +2381,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all) if (free_all) goto try_to_free; move_account: - while (mem->res.usage > 0) { + do { ret = -EBUSY; if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children)) goto out; @@ -2408,8 +2408,8 @@ move_account: if (ret == -ENOMEM) goto try_to_free; cond_resched(); - } - ret = 0; + /* "ret" should also be checked to ensure all lists are empty. */ + } while (mem->res.usage > 0 || ret); out: css_put(&mem->css); return ret; @@ -2442,10 +2442,7 @@ try_to_free: } lru_add_drain(); /* try move_account...there may be some *locked* pages. */ - if (mem->res.usage) - goto move_account; - ret = 0; - goto out; + goto move_account; } int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event) -- cgit v1.2.3 From c91ab0438c6700e4be078d64cfb01879986e3bde Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Fri, 15 Jan 2010 17:01:18 -0800 Subject: page allocator: update NR_FREE_PAGES only when necessary commit 6ccf80eb15ccaca4d3f1ab5162b9ded5eecd9971 upstream. commit f2260e6b (page allocator: update NR_FREE_PAGES only as necessary) made one minor regression. if __rmqueue() was failed, NR_FREE_PAGES stat go wrong. this patch fixes it. Signed-off-by: KOSAKI Motohiro Cc: Mel Gorman Reviewed-by: Minchan Kim Reported-by: Huang Shijie Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2bc2ac63f41e..3a78e2e864e8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1225,10 +1225,10 @@ again: } spin_lock_irqsave(&zone->lock, flags); page = __rmqueue(zone, order, migratetype); - __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order)); spin_unlock(&zone->lock); if (!page) goto failed; + __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order)); } __count_zone_vm_events(PGALLOC, zone, 1 << order); -- cgit v1.2.3 From af55a3da5049fb26a84ba562c7c8b55b910ff234 Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Wed, 13 Jan 2010 21:14:09 +0900 Subject: vfs: Fix vmtruncate() regression commit cedabed49b39b4319bccc059a63344b6232b619c upstream. If __block_prepare_write() was failed in block_write_begin(), the allocated blocks can be outside of ->i_size. But new truncate_pagecache() in vmtuncate() does nothing if new < old. It means the above usage is not working anymore. So, this patch fixes it by removing "new < old" check. It would need more cleanup/change. But, now -rc and truncate working is in progress, so, this tried to fix it minimum change. Acked-by: Nick Piggin Signed-off-by: OGAWA Hirofumi Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/truncate.c | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-) (limited to 'mm') diff --git a/mm/truncate.c b/mm/truncate.c index 450cebdabfc0..258bda7ec31d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -516,22 +516,20 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2); */ void truncate_pagecache(struct inode *inode, loff_t old, loff_t new) { - if (new < old) { - struct address_space *mapping = inode->i_mapping; - - /* - * unmap_mapping_range is called twice, first simply for - * efficiency so that truncate_inode_pages does fewer - * single-page unmaps. However after this first call, and - * before truncate_inode_pages finishes, it is possible for - * private pages to be COWed, which remain after - * truncate_inode_pages finishes, hence the second - * unmap_mapping_range call must be made for correctness. - */ - unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1); - truncate_inode_pages(mapping, new); - unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1); - } + struct address_space *mapping = inode->i_mapping; + + /* + * unmap_mapping_range is called twice, first simply for + * efficiency so that truncate_inode_pages does fewer + * single-page unmaps. However after this first call, and + * before truncate_inode_pages finishes, it is possible for + * private pages to be COWed, which remain after + * truncate_inode_pages finishes, hence the second + * unmap_mapping_range call must be made for correctness. + */ + unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1); + truncate_inode_pages(mapping, new); + unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1); } EXPORT_SYMBOL(truncate_pagecache); -- cgit v1.2.3 From f2fa92b29da64ead309293a048fe41776338a280 Mon Sep 17 00:00:00 2001 From: Yongseok Koh Date: Tue, 19 Jan 2010 17:33:49 +0900 Subject: vmalloc: remove BUG_ON due to racy counting of VM_LAZY_FREE commit 88f5004430babb836cfce886d5d54c82166f8ba4 upstream. In free_unmap_area_noflush(), va->flags is marked as VM_LAZY_FREE first, and then vmap_lazy_nr is increased atomically. But, in __purge_vmap_area_lazy(), while traversing of vmap_are_list, nr is counted by checking VM_LAZY_FREE is set to va->flags. After counting the variable nr, kernel reads vmap_lazy_nr atomically and checks a BUG_ON condition whether nr is greater than vmap_lazy_nr to prevent vmap_lazy_nr from being negative. The problem is that, if interrupted right after marking VM_LAZY_FREE, increment of vmap_lazy_nr can be delayed. Consequently, BUG_ON condition can be met because nr is counted more than vmap_lazy_nr. It is highly probable when vmalloc/vfree are called frequently. This scenario have been verified by adding delay between marking VM_LAZY_FREE and increasing vmap_lazy_nr in free_unmap_area_noflush(). Even the vmap_lazy_nr is for checking high watermark, it never be the strict watermark. Although the BUG_ON condition is to prevent vmap_lazy_nr from being negative, vmap_lazy_nr is signed variable. So, it could go down to negative value temporarily. Consequently, removing the BUG_ON condition is proper. A possible BUG_ON message is like the below. kernel BUG at mm/vmalloc.c:517! invalid opcode: 0000 [#1] SMP EIP: 0060:[] EFLAGS: 00010297 CPU: 3 EIP is at __purge_vmap_area_lazy+0x144/0x150 EAX: ee8a8818 EBX: c08e77d4 ECX: e7c7ae40 EDX: c08e77ec ESI: 000081fe EDI: e7c7ae60 EBP: e7c7ae64 ESP: e7c7ae3c DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Call Trace: [] free_unmap_vmap_area_noflush+0x69/0x70 [] remove_vm_area+0x22/0x70 [] __vunmap+0x45/0xe0 [] vmalloc+0x2c/0x30 Code: 8d 59 e0 eb 04 66 90 89 cb 89 d0 e8 87 fe ff ff 8b 43 20 89 da 8d 48 e0 8d 43 20 3b 04 24 75 e7 fe 05 a8 a5 a3 c0 e9 78 ff ff ff <0f> 0b eb fe 90 8d b4 26 00 00 00 00 56 89 c6 b8 ac a5 a3 c0 31 EIP: [] __purge_vmap_area_lazy+0x144/0x150 SS:ESP 0068:e7c7ae3c [ See also http://marc.info/?l=linux-kernel&m=126335856228090&w=2 ] Signed-off-by: Yongseok Koh Reviewed-by: Minchan Kim Cc: Nick Piggin Cc: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/vmalloc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 775872681d0c..a3a99d39188b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -555,10 +555,8 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, } rcu_read_unlock(); - if (nr) { - BUG_ON(nr > atomic_read(&vmap_lazy_nr)); + if (nr) atomic_sub(nr, &vmap_lazy_nr); - } if (nr || force_flush) flush_tlb_kernel_range(*start, *end); -- cgit v1.2.3 From 8268c0bce9f4df836265ac5c7982ff8f8808f199 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 27 Jan 2010 09:20:03 -0800 Subject: mm: add new 'read_cache_page_gfp()' helper function commit 0531b2aac59c2296570ac52bfc032ef2ace7d5e1 upstream. It's a simplified 'read_cache_page()' which takes a page allocation flag, so that different paths can control how aggressive the memory allocations are that populate a address space. In particular, the intel GPU object mapping code wants to be able to do a certain amount of own internal memory management by automatically shrinking the address space when memory starts getting tight. This allows it to dynamically use different memory allocation policies on a per-allocation basis, rather than depend on the (static) address space gfp policy. The actual new function is a one-liner, but re-organizing the helper functions to the point where you can do this with a single line of code is what most of the patch is all about. Tested-by: Chris Wilson Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/filemap.c | 100 ++++++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 68 insertions(+), 32 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index ef169f37156d..fbdacb717ae9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1655,14 +1655,15 @@ EXPORT_SYMBOL(generic_file_readonly_mmap); static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *,struct page*), - void *data) + void *data, + gfp_t gfp) { struct page *page; int err; repeat: page = find_get_page(mapping, index); if (!page) { - page = page_cache_alloc_cold(mapping); + page = __page_cache_alloc(gfp | __GFP_COLD); if (!page) return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); @@ -1682,31 +1683,18 @@ repeat: return page; } -/** - * read_cache_page_async - read into page cache, fill it if needed - * @mapping: the page's address_space - * @index: the page index - * @filler: function to perform the read - * @data: destination for read data - * - * Same as read_cache_page, but don't wait for page to become unlocked - * after submitting it to the filler. - * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page but don't wait for it to become unlocked. - * - * If the page does not get brought uptodate, return -EIO. - */ -struct page *read_cache_page_async(struct address_space *mapping, +static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *,struct page*), - void *data) + void *data, + gfp_t gfp) + { struct page *page; int err; retry: - page = __read_cache_page(mapping, index, filler, data); + page = __read_cache_page(mapping, index, filler, data, gfp); if (IS_ERR(page)) return page; if (PageUptodate(page)) @@ -1731,8 +1719,67 @@ out: mark_page_accessed(page); return page; } + +/** + * read_cache_page_async - read into page cache, fill it if needed + * @mapping: the page's address_space + * @index: the page index + * @filler: function to perform the read + * @data: destination for read data + * + * Same as read_cache_page, but don't wait for page to become unlocked + * after submitting it to the filler. + * + * Read into the page cache. If a page already exists, and PageUptodate() is + * not set, try to fill the page but don't wait for it to become unlocked. + * + * If the page does not get brought uptodate, return -EIO. + */ +struct page *read_cache_page_async(struct address_space *mapping, + pgoff_t index, + int (*filler)(void *,struct page*), + void *data) +{ + return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); +} EXPORT_SYMBOL(read_cache_page_async); +static struct page *wait_on_page_read(struct page *page) +{ + if (!IS_ERR(page)) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + page_cache_release(page); + page = ERR_PTR(-EIO); + } + } + return page; +} + +/** + * read_cache_page_gfp - read into page cache, using specified page allocation flags. + * @mapping: the page's address_space + * @index: the page index + * @gfp: the page allocator flags to use if allocating + * + * This is the same as "read_mapping_page(mapping, index, NULL)", but with + * any new page allocations done using the specified allocation flags. Note + * that the Radix tree operations will still use GFP_KERNEL, so you can't + * expect to do this atomically or anything like that - but you can pass in + * other page requirements. + * + * If the page does not get brought uptodate, return -EIO. + */ +struct page *read_cache_page_gfp(struct address_space *mapping, + pgoff_t index, + gfp_t gfp) +{ + filler_t *filler = (filler_t *)mapping->a_ops->readpage; + + return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp)); +} +EXPORT_SYMBOL(read_cache_page_gfp); + /** * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space @@ -1750,18 +1797,7 @@ struct page *read_cache_page(struct address_space *mapping, int (*filler)(void *,struct page*), void *data) { - struct page *page; - - page = read_cache_page_async(mapping, index, filler, data); - if (IS_ERR(page)) - goto out; - wait_on_page_locked(page); - if (!PageUptodate(page)) { - page_cache_release(page); - page = ERR_PTR(-EIO); - } - out: - return page; + return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); } EXPORT_SYMBOL(read_cache_page); -- cgit v1.2.3 From 0b3bf81197f05e1bf0ed93c5f2525030b127faaa Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 29 Jan 2010 17:46:34 +0000 Subject: mm: fix migratetype bug which slowed swapping commit a7016235a61d520e6806f38129001d935c4b6661 upstream. 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 Acked-by: Mel Gorman Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/page_alloc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3a78e2e864e8..36992b68500b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -559,8 +559,9 @@ static void free_pcppages_bulk(struct zone *zone, int count, page = list_entry(list->prev, struct page, lru); /* must delete as __free_one_page list manipulates */ list_del(&page->lru); - __free_one_page(page, zone, 0, migratetype); - trace_mm_page_pcpu_drain(page, 0, migratetype); + /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ + __free_one_page(page, zone, 0, page_private(page)); + trace_mm_page_pcpu_drain(page, 0, page_private(page)); } while (--count && --batch_free && !list_empty(list)); } spin_unlock(&zone->lock); -- cgit v1.2.3 From 56d4b77f0492eb137fd950e48a7b2364f380d33d Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Mon, 1 Feb 2010 22:24:18 +1100 Subject: mm: percpu-vmap fix RCU list walking commit de5604231ce4bc8db1bc1dcd27d8540cbedf1518 upstream. RCU list walking of the per-cpu vmap cache was broken. It did not use RCU primitives, and also the union of free_list and rcu_head is obviously wrong (because free_list is indeed the list we are RCU walking). While we are there, remove a couple of unused fields from an earlier iteration. These APIs aren't actually used anywhere, because of problems with the XFS conversion. Christoph has now verified that the problems are solved with these patches. Also it is an exported interface, so I think it will be good to be merged now (and Christoph wants to get the XFS changes into their local tree). Cc: linux-mm@kvack.org Tested-by: Christoph Hellwig Signed-off-by: Nick Piggin Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/vmalloc.c | 20 ++++++-------------- 1 file changed, 6 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a3a99d39188b..6e5a1d263842 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -667,8 +667,6 @@ static bool vmap_initialized __read_mostly = false; struct vmap_block_queue { spinlock_t lock; struct list_head free; - struct list_head dirty; - unsigned int nr_dirty; }; struct vmap_block { @@ -678,10 +676,8 @@ struct vmap_block { unsigned long free, dirty; DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS); DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); - union { - struct list_head free_list; - struct rcu_head rcu_head; - }; + struct list_head free_list; + struct rcu_head rcu_head; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ @@ -757,7 +753,7 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask) vbq = &get_cpu_var(vmap_block_queue); vb->vbq = vbq; spin_lock(&vbq->lock); - list_add(&vb->free_list, &vbq->free); + list_add_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); put_cpu_var(vmap_cpu_blocks); @@ -776,8 +772,6 @@ static void free_vmap_block(struct vmap_block *vb) struct vmap_block *tmp; unsigned long vb_idx; - BUG_ON(!list_empty(&vb->free_list)); - vb_idx = addr_to_vb_idx(vb->va->va_start); spin_lock(&vmap_block_tree_lock); tmp = radix_tree_delete(&vmap_block_tree, vb_idx); @@ -816,7 +810,7 @@ again: vb->free -= 1UL << order; if (vb->free == 0) { spin_lock(&vbq->lock); - list_del_init(&vb->free_list); + list_del_rcu(&vb->free_list); spin_unlock(&vbq->lock); } spin_unlock(&vb->lock); @@ -860,11 +854,11 @@ static void vb_free(const void *addr, unsigned long size) BUG_ON(!vb); spin_lock(&vb->lock); - bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order); + BUG_ON(bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order)); vb->dirty += 1UL << order; if (vb->dirty == VMAP_BBMAP_BITS) { - BUG_ON(vb->free || !list_empty(&vb->free_list)); + BUG_ON(vb->free); spin_unlock(&vb->lock); free_vmap_block(vb); } else @@ -1033,8 +1027,6 @@ void __init vmalloc_init(void) vbq = &per_cpu(vmap_block_queue, i); spin_lock_init(&vbq->lock); INIT_LIST_HEAD(&vbq->free); - INIT_LIST_HEAD(&vbq->dirty); - vbq->nr_dirty = 0; } /* Import existing vmlist entries. */ -- cgit v1.2.3 From e52299d0b100ab8d92fe6e980b4d7ee24dd1398c Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Mon, 1 Feb 2010 22:25:57 +1100 Subject: mm: purge fragmented percpu vmap blocks commit 02b709df817c0db174f249cc59e5f7fd01b64d92 upstream. Improve handling of fragmented per-CPU vmaps. We previously don't free up per-CPU maps until all its addresses have been used and freed. So fragmented blocks could fill up vmalloc space even if they actually had no active vmap regions within them. Add some logic to allow all CPUs to have these blocks purged in the case of failure to allocate a new vm area, and also put some logic to trim such blocks of a current CPU if we hit them in the allocation path (so as to avoid a large build up of them). Christoph reported some vmap allocation failures when using the per CPU vmap APIs in XFS, which cannot be reproduced after this patch and the previous bug fix. Cc: linux-mm@kvack.org Tested-by: Christoph Hellwig Signed-off-by: Nick Piggin Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/vmalloc.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 80 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6e5a1d263842..c2287313b985 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -509,6 +509,9 @@ static unsigned long lazy_max_pages(void) static atomic_t vmap_lazy_nr = ATOMIC_INIT(0); +/* for per-CPU blocks */ +static void purge_fragmented_blocks_allcpus(void); + /* * Purges all lazily-freed vmap areas. * @@ -539,6 +542,9 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, } else spin_lock(&purge_lock); + if (sync) + purge_fragmented_blocks_allcpus(); + rcu_read_lock(); list_for_each_entry_rcu(va, &vmap_area_list, list) { if (va->flags & VM_LAZY_FREE) { @@ -678,6 +684,7 @@ struct vmap_block { DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); struct list_head free_list; struct rcu_head rcu_head; + struct list_head purge; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ @@ -782,12 +789,61 @@ static void free_vmap_block(struct vmap_block *vb) call_rcu(&vb->rcu_head, rcu_free_vb); } +static void purge_fragmented_blocks(int cpu) +{ + LIST_HEAD(purge); + struct vmap_block *vb; + struct vmap_block *n_vb; + struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); + + rcu_read_lock(); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + + if (!(vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS)) + continue; + + spin_lock(&vb->lock); + if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) { + vb->free = 0; /* prevent further allocs after releasing lock */ + vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */ + bitmap_fill(vb->alloc_map, VMAP_BBMAP_BITS); + bitmap_fill(vb->dirty_map, VMAP_BBMAP_BITS); + spin_lock(&vbq->lock); + list_del_rcu(&vb->free_list); + spin_unlock(&vbq->lock); + spin_unlock(&vb->lock); + list_add_tail(&vb->purge, &purge); + } else + spin_unlock(&vb->lock); + } + rcu_read_unlock(); + + list_for_each_entry_safe(vb, n_vb, &purge, purge) { + list_del(&vb->purge); + free_vmap_block(vb); + } +} + +static void purge_fragmented_blocks_thiscpu(void) +{ + purge_fragmented_blocks(smp_processor_id()); +} + +static void purge_fragmented_blocks_allcpus(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + purge_fragmented_blocks(cpu); +} + static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; unsigned long addr = 0; unsigned int order; + int purge = 0; BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -800,24 +856,37 @@ again: int i; spin_lock(&vb->lock); + if (vb->free < 1UL << order) + goto next; i = bitmap_find_free_region(vb->alloc_map, VMAP_BBMAP_BITS, order); - if (i >= 0) { - addr = vb->va->va_start + (i << PAGE_SHIFT); - BUG_ON(addr_to_vb_idx(addr) != - addr_to_vb_idx(vb->va->va_start)); - vb->free -= 1UL << order; - if (vb->free == 0) { - spin_lock(&vbq->lock); - list_del_rcu(&vb->free_list); - spin_unlock(&vbq->lock); + if (i < 0) { + if (vb->free + vb->dirty == VMAP_BBMAP_BITS) { + /* fragmented and no outstanding allocations */ + BUG_ON(vb->dirty != VMAP_BBMAP_BITS); + purge = 1; } - spin_unlock(&vb->lock); - break; + goto next; } + addr = vb->va->va_start + (i << PAGE_SHIFT); + BUG_ON(addr_to_vb_idx(addr) != + addr_to_vb_idx(vb->va->va_start)); + vb->free -= 1UL << order; + if (vb->free == 0) { + spin_lock(&vbq->lock); + list_del_rcu(&vb->free_list); + spin_unlock(&vbq->lock); + } + spin_unlock(&vb->lock); + break; +next: spin_unlock(&vb->lock); } + + if (purge) + purge_fragmented_blocks_thiscpu(); + put_cpu_var(vmap_cpu_blocks); rcu_read_unlock(); -- cgit v1.2.3 From 3a9353f232812dc9057cbee39c618f400a8c5f60 Mon Sep 17 00:00:00 2001 From: anfei zhou Date: Tue, 2 Feb 2010 13:44:02 -0800 Subject: mm: flush dcache before writing into page to avoid alias commit 931e80e4b3263db75c8e34f078d22f11bbabd3a3 upstream. The cache alias problem will happen if the changes of user shared mapping is not flushed before copying, then user and kernel mapping may be mapped into two different cache line, it is impossible to guarantee the coherence after iov_iter_copy_from_user_atomic. So the right steps should be: flush_dcache_page(page); kmap_atomic(page); write to page; kunmap_atomic(page); flush_dcache_page(page); More precisely, we might create two new APIs flush_dcache_user_page and flush_dcache_kern_page to replace the two flush_dcache_page accordingly. Here is a snippet tested on omap2430 with VIPT cache, and I think it is not ARM-specific: int val = 0x11111111; fd = open("abc", O_RDWR); addr = mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); *(addr+0) = 0x44444444; tmp = *(addr+0); *(addr+1) = 0x77777777; write(fd, &val, sizeof(int)); close(fd); The results are not always 0x11111111 0x77777777 at the beginning as expected. Sometimes we see 0x44444444 0x77777777. Signed-off-by: Anfei Cc: Russell King Cc: Miklos Szeredi Cc: Nick Piggin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/filemap.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index fbdacb717ae9..8e96c9076f80 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2253,6 +2253,9 @@ again: if (unlikely(status)) break; + if (mapping_writably_mapped(mapping)) + flush_dcache_page(page); + pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); pagefault_enable(); -- cgit v1.2.3 From 7313f5ad0cb1b501cbe67cf6c2dee018a2aa3321 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 5 Feb 2010 16:16:50 -0800 Subject: Fix potential crash with sys_move_pages commit 6f5a55f1a6c5abee15a0e878e5c74d9f1569b8b0 upstream. We incorrectly depended on the 'node_state/node_isset()' functions testing the node range, rather than checking it explicitly. That's not reliable, even if it might often happen to work. So do the proper explicit test. Reported-by: Marcus Meissner Acked-and-tested-by: Brice Goglin Acked-by: Hugh Dickins Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- mm/migrate.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index 7dbcb22316d2..0e39f94b2d9c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -953,6 +953,9 @@ static int do_pages_move(struct mm_struct *mm, struct task_struct *task, goto out_pm; err = -ENODEV; + if (node < 0 || node >= MAX_NUMNODES) + goto out_pm; + if (!node_state(node, N_HIGH_MEMORY)) goto out_pm; -- cgit v1.2.3