From: Balbir Singh Date: Thu, 7 Feb 2008 08:14:01 +0000 (-0800) Subject: Memory controller: make page_referenced() cgroup aware X-Git-Tag: v2.6.25-rc1~469 X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=bed7161a519a2faef53e1bce1b47595e297c1d14;p=linux-2.6 Memory controller: make page_referenced() cgroup aware Make page_referenced() cgroup aware. Without this patch, page_referenced() can cause a page to be skipped while reclaiming pages. This patch ensures that other cgroups do not hold pages in a particular cgroup hostage. It is required to ensure that shared pages are freed from a cgroup when they are not actively referenced from the cgroup that brought them in Signed-off-by: Balbir Singh Cc: Pavel Emelianov Cc: Paul Menage Cc: Peter Zijlstra Cc: "Eric W. Biederman" Cc: Nick Piggin Cc: Kirill Korotaev Cc: Herbert Poetzl Cc: David Rientjes Cc: Vaidyanathan Srinivasan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bb6f510540..9d0a830423 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -43,6 +43,7 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, int active); extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask); extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm); +extern struct mem_cgroup *mm_cgroup(struct mm_struct *mm); static inline void mem_cgroup_uncharge_page(struct page *page) { @@ -93,6 +94,11 @@ static inline int mem_cgroup_cache_charge(struct page *page, return 0; } +static inline struct mem_cgroup *mm_cgroup(struct mm_struct *mm) +{ + return NULL; +} + #endif /* CONFIG_CGROUP_MEM_CONT */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 97347f22fc..1383692ac5 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -8,6 +8,7 @@ #include #include #include +#include /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -86,7 +87,7 @@ static inline void page_dup_rmap(struct page *page, struct vm_area_struct *vma, /* * Called from mm/vmscan.c to handle paging out */ -int page_referenced(struct page *, int is_locked); +int page_referenced(struct page *, int is_locked, struct mem_cgroup *cnt); int try_to_unmap(struct page *, int ignore_refs); /* @@ -114,7 +115,7 @@ int page_mkclean(struct page *); #define anon_vma_prepare(vma) (0) #define anon_vma_link(vma) do {} while (0) -#define page_referenced(page,l) TestClearPageReferenced(page) +#define page_referenced(page,l,cnt) TestClearPageReferenced(page) #define try_to_unmap(page, refs) SWAP_FAIL static inline int page_mkclean(struct page *page) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 10833d969e..ff7cac6029 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -110,6 +110,11 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) struct mem_cgroup, css); } +inline struct mem_cgroup *mm_cgroup(struct mm_struct *mm) +{ + return rcu_dereference(mm->mem_cgroup); +} + void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p) { struct mem_cgroup *mem; diff --git a/mm/rmap.c b/mm/rmap.c index 4a3487921e..a0e92a263d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -302,7 +302,8 @@ out: return referenced; } -static int page_referenced_anon(struct page *page) +static int page_referenced_anon(struct page *page, + struct mem_cgroup *mem_cont) { unsigned int mapcount; struct anon_vma *anon_vma; @@ -315,6 +316,13 @@ static int page_referenced_anon(struct page *page) mapcount = page_mapcount(page); list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { + /* + * If we are reclaiming on behalf of a cgroup, skip + * counting on behalf of references from different + * cgroups + */ + if (mem_cont && (mm_cgroup(vma->vm_mm) != mem_cont)) + continue; referenced += page_referenced_one(page, vma, &mapcount); if (!mapcount) break; @@ -335,7 +343,8 @@ static int page_referenced_anon(struct page *page) * * This function is only called from page_referenced for object-based pages. */ -static int page_referenced_file(struct page *page) +static int page_referenced_file(struct page *page, + struct mem_cgroup *mem_cont) { unsigned int mapcount; struct address_space *mapping = page->mapping; @@ -368,6 +377,13 @@ static int page_referenced_file(struct page *page) mapcount = page_mapcount(page); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + /* + * If we are reclaiming on behalf of a cgroup, skip + * counting on behalf of references from different + * cgroups + */ + if (mem_cont && (mm_cgroup(vma->vm_mm) != mem_cont)) + continue; if ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE)) == (VM_LOCKED|VM_MAYSHARE)) { referenced++; @@ -390,7 +406,8 @@ static int page_referenced_file(struct page *page) * Quick test_and_clear_referenced for all mappings to a page, * returns the number of ptes which referenced the page. */ -int page_referenced(struct page *page, int is_locked) +int page_referenced(struct page *page, int is_locked, + struct mem_cgroup *mem_cont) { int referenced = 0; @@ -402,14 +419,15 @@ int page_referenced(struct page *page, int is_locked) if (page_mapped(page) && page->mapping) { if (PageAnon(page)) - referenced += page_referenced_anon(page); + referenced += page_referenced_anon(page, mem_cont); else if (is_locked) - referenced += page_referenced_file(page); + referenced += page_referenced_file(page, mem_cont); else if (TestSetPageLocked(page)) referenced++; else { if (page->mapping) - referenced += page_referenced_file(page); + referenced += + page_referenced_file(page, mem_cont); unlock_page(page); } } diff --git a/mm/vmscan.c b/mm/vmscan.c index 7408a8a7d8..215f6a726b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -503,7 +503,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep_locked; } - referenced = page_referenced(page, 1); + referenced = page_referenced(page, 1, sc->mem_cgroup); /* In active use or really unfreeable? Activate it. */ if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced && page_mapping_inuse(page)) @@ -1057,7 +1057,7 @@ force_reclaim_mapped: if (page_mapped(page)) { if (!reclaim_mapped || (total_swap_pages == 0 && PageAnon(page)) || - page_referenced(page, 0)) { + page_referenced(page, 0, sc->mem_cgroup)) { list_add(&page->lru, &l_active); continue; }