From 3e79ec7ddc33e5c69c20ce7f768d0e5c8b824f69 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 26 Jul 2016 15:24:30 -0700 Subject: arch: x86: charge page tables to kmemcg Page tables can bite a relatively big chunk off system memory and their allocations are easy to trigger from userspace, so they should be accounted to kmemcg. This patch marks page table allocations as __GFP_ACCOUNT for x86. Note we must not charge allocations of kernel page tables, because they can be shared among processes from different cgroups so accounting them to a particular one can pin other cgroups for indefinitely long. So we clear __GFP_ACCOUNT flag if a page table is allocated for the kernel. Link: http://lkml.kernel.org/r/7d5c54f6a2bcbe76f03171689440003d87e6c742.1464079538.git.vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Johannes Weiner Cc: Michal Hocko Cc: Eric Dumazet Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/pgtable.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index aa0ff4b..3feec5a 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -6,7 +6,7 @@ #include #include -#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO +#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | __GFP_ZERO) #ifdef CONFIG_HIGHPTE #define PGALLOC_USER_GFP __GFP_HIGHMEM @@ -18,7 +18,7 @@ gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP; pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)__get_free_page(PGALLOC_GFP); + return (pte_t *)__get_free_page(PGALLOC_GFP & ~__GFP_ACCOUNT); } pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) @@ -207,9 +207,13 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) { int i; bool failed = false; + gfp_t gfp = PGALLOC_GFP; + + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; for(i = 0; i < PREALLOCATED_PMDS; i++) { - pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP); + pmd_t *pmd = (pmd_t *)__get_free_page(gfp); if (!pmd) failed = true; if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) { -- cgit v1.1 From dcddffd41d3f1d3bdcc1dce3f1cd142779b6d4c1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:18 -0700 Subject: mm: do not pass mm_struct into handle_mm_fault We always have vma->vm_mm around. Link: http://lkml.kernel.org/r/1466021202-61880-8-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d22161a..dc80230 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1353,7 +1353,7 @@ good_area: * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); major |= fault & VM_FAULT_MAJOR; /* -- cgit v1.1