forked from Minki/linux
3e79ec7ddc
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 <vdavydov@virtuozzo.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
157 lines
4.3 KiB
C
157 lines
4.3 KiB
C
#ifndef _ASM_X86_PGALLOC_H
|
|
#define _ASM_X86_PGALLOC_H
|
|
|
|
#include <linux/threads.h>
|
|
#include <linux/mm.h> /* for struct page */
|
|
#include <linux/pagemap.h>
|
|
|
|
static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
#include <asm/paravirt.h>
|
|
#else
|
|
#define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm)
|
|
static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {}
|
|
static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {}
|
|
static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {}
|
|
static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
|
|
unsigned long start, unsigned long count) {}
|
|
static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {}
|
|
static inline void paravirt_release_pte(unsigned long pfn) {}
|
|
static inline void paravirt_release_pmd(unsigned long pfn) {}
|
|
static inline void paravirt_release_pud(unsigned long pfn) {}
|
|
#endif
|
|
|
|
/*
|
|
* Flags to use when allocating a user page table page.
|
|
*/
|
|
extern gfp_t __userpte_alloc_gfp;
|
|
|
|
/*
|
|
* Allocate and free page tables.
|
|
*/
|
|
extern pgd_t *pgd_alloc(struct mm_struct *);
|
|
extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
|
|
|
|
extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
|
|
extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
|
|
|
|
/* Should really implement gc for free page table pages. This could be
|
|
done with a reference count in struct page. */
|
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
|
|
{
|
|
BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
|
|
free_page((unsigned long)pte);
|
|
}
|
|
|
|
static inline void pte_free(struct mm_struct *mm, struct page *pte)
|
|
{
|
|
pgtable_page_dtor(pte);
|
|
__free_page(pte);
|
|
}
|
|
|
|
extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
|
|
|
|
static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte,
|
|
unsigned long address)
|
|
{
|
|
___pte_free_tlb(tlb, pte);
|
|
}
|
|
|
|
static inline void pmd_populate_kernel(struct mm_struct *mm,
|
|
pmd_t *pmd, pte_t *pte)
|
|
{
|
|
paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT);
|
|
set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
|
|
}
|
|
|
|
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
|
|
struct page *pte)
|
|
{
|
|
unsigned long pfn = page_to_pfn(pte);
|
|
|
|
paravirt_alloc_pte(mm, pfn);
|
|
set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE));
|
|
}
|
|
|
|
#define pmd_pgtable(pmd) pmd_page(pmd)
|
|
|
|
#if CONFIG_PGTABLE_LEVELS > 2
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
struct page *page;
|
|
gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO;
|
|
|
|
if (mm == &init_mm)
|
|
gfp &= ~__GFP_ACCOUNT;
|
|
page = alloc_pages(gfp, 0);
|
|
if (!page)
|
|
return NULL;
|
|
if (!pgtable_pmd_page_ctor(page)) {
|
|
__free_pages(page, 0);
|
|
return NULL;
|
|
}
|
|
return (pmd_t *)page_address(page);
|
|
}
|
|
|
|
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
|
|
{
|
|
BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
|
|
pgtable_pmd_page_dtor(virt_to_page(pmd));
|
|
free_page((unsigned long)pmd);
|
|
}
|
|
|
|
extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
|
|
|
|
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
|
|
unsigned long address)
|
|
{
|
|
___pmd_free_tlb(tlb, pmd);
|
|
}
|
|
|
|
#ifdef CONFIG_X86_PAE
|
|
extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
|
|
#else /* !CONFIG_X86_PAE */
|
|
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
|
|
{
|
|
paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
|
|
set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd)));
|
|
}
|
|
#endif /* CONFIG_X86_PAE */
|
|
|
|
#if CONFIG_PGTABLE_LEVELS > 3
|
|
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
|
|
{
|
|
paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT);
|
|
set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)));
|
|
}
|
|
|
|
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
gfp_t gfp = GFP_KERNEL_ACCOUNT;
|
|
|
|
if (mm == &init_mm)
|
|
gfp &= ~__GFP_ACCOUNT;
|
|
return (pud_t *)get_zeroed_page(gfp);
|
|
}
|
|
|
|
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
|
|
{
|
|
BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
|
|
free_page((unsigned long)pud);
|
|
}
|
|
|
|
extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud);
|
|
|
|
static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
|
|
unsigned long address)
|
|
{
|
|
___pud_free_tlb(tlb, pud);
|
|
}
|
|
|
|
#endif /* CONFIG_PGTABLE_LEVELS > 3 */
|
|
#endif /* CONFIG_PGTABLE_LEVELS > 2 */
|
|
|
|
#endif /* _ASM_X86_PGALLOC_H */
|