Commit de3b8761 authored by Balbir Singh's avatar Balbir Singh Committed by Michael Ellerman

powerpc/mm/book(e)(3s)/64: Add page table accounting

Introduce a helper pgtable_gfp_flags() which
just returns the current gfp flags and adds
__GFP_ACCOUNT to account for page table allocation.
The generic helper is added to include/asm/pgalloc.h
and has two variants - WARNING ugly bits ahead

1. If the header is included from a module, no check
for mm == &init_mm is done, since init_mm is not
exported
2. For kernel includes, the check is done and required
see (3e79ec7d arch: x86: charge page tables to kmemcg)

The fundamental assumption is that no module should be
doing pgd/pud/pmd and pte alloc's on behalf of init_mm
directly.

NOTE: This adds an overhead to pmd/pud/pgd allocations
similar to x86.  The other alternative was to implement
pmd_alloc_kernel/pud_alloc_kernel and pgd_alloc_kernel
with their offset variants.

For 4k page size, pte_alloc_one no longer calls
pte_alloc_one_kernel.
Signed-off-by: default avatarBalbir Singh <bsingharora@gmail.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
parent c5cee642
...@@ -31,7 +31,8 @@ extern struct kmem_cache *pgtable_cache[]; ...@@ -31,7 +31,8 @@ extern struct kmem_cache *pgtable_cache[];
static inline pgd_t *pgd_alloc(struct mm_struct *mm) static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{ {
return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL); return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
pgtable_gfp_flags(mm, GFP_KERNEL));
} }
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
......
...@@ -53,10 +53,11 @@ extern void __tlb_remove_table(void *_table); ...@@ -53,10 +53,11 @@ extern void __tlb_remove_table(void *_table);
static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
{ {
#ifdef CONFIG_PPC_64K_PAGES #ifdef CONFIG_PPC_64K_PAGES
return (pgd_t *)__get_free_page(PGALLOC_GFP); return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP));
#else #else
struct page *page; struct page *page;
page = alloc_pages(PGALLOC_GFP | __GFP_REPEAT, 4); page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_REPEAT),
4);
if (!page) if (!page)
return NULL; return NULL;
return (pgd_t *) page_address(page); return (pgd_t *) page_address(page);
...@@ -76,7 +77,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) ...@@ -76,7 +77,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{ {
if (radix_enabled()) if (radix_enabled())
return radix__pgd_alloc(mm); return radix__pgd_alloc(mm);
return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL); return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
pgtable_gfp_flags(mm, GFP_KERNEL));
} }
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
...@@ -93,7 +95,8 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) ...@@ -93,7 +95,8 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{ {
return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL); return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
pgtable_gfp_flags(mm, GFP_KERNEL));
} }
static inline void pud_free(struct mm_struct *mm, pud_t *pud) static inline void pud_free(struct mm_struct *mm, pud_t *pud)
...@@ -119,7 +122,8 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, ...@@ -119,7 +122,8 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{ {
return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL); return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
pgtable_gfp_flags(mm, GFP_KERNEL));
} }
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
...@@ -168,7 +172,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, ...@@ -168,7 +172,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
struct page *page; struct page *page;
pte_t *pte; pte_t *pte;
pte = pte_alloc_one_kernel(mm, address); pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT);
if (!pte) if (!pte)
return NULL; return NULL;
page = virt_to_page(pte); page = virt_to_page(pte);
......
...@@ -43,7 +43,8 @@ extern struct kmem_cache *pgtable_cache[]; ...@@ -43,7 +43,8 @@ extern struct kmem_cache *pgtable_cache[];
static inline pgd_t *pgd_alloc(struct mm_struct *mm) static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{ {
return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL); return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
pgtable_gfp_flags(mm, GFP_KERNEL));
} }
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
...@@ -57,7 +58,8 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) ...@@ -57,7 +58,8 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{ {
return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL); return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
pgtable_gfp_flags(mm, GFP_KERNEL));
} }
static inline void pud_free(struct mm_struct *mm, pud_t *pud) static inline void pud_free(struct mm_struct *mm, pud_t *pud)
...@@ -96,7 +98,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, ...@@ -96,7 +98,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
struct page *page; struct page *page;
pte_t *pte; pte_t *pte;
pte = pte_alloc_one_kernel(mm, address); pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT);
if (!pte) if (!pte)
return NULL; return NULL;
page = virt_to_page(pte); page = virt_to_page(pte);
...@@ -189,7 +191,8 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, ...@@ -189,7 +191,8 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{ {
return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL); return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
pgtable_gfp_flags(mm, GFP_KERNEL));
} }
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
......
...@@ -3,6 +3,20 @@ ...@@ -3,6 +3,20 @@
#include <linux/mm.h> #include <linux/mm.h>
#ifndef MODULE
static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp)
{
if (unlikely(mm == &init_mm))
return gfp;
return gfp | __GFP_ACCOUNT;
}
#else /* !MODULE */
static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp)
{
return gfp | __GFP_ACCOUNT;
}
#endif /* MODULE */
#ifdef CONFIG_PPC_BOOK3S #ifdef CONFIG_PPC_BOOK3S
#include <asm/book3s/pgalloc.h> #include <asm/book3s/pgalloc.h>
#else #else
......
...@@ -351,12 +351,20 @@ static pte_t *get_from_cache(struct mm_struct *mm) ...@@ -351,12 +351,20 @@ static pte_t *get_from_cache(struct mm_struct *mm)
static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
{ {
void *ret = NULL; void *ret = NULL;
struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); struct page *page;
if (!page)
return NULL; if (!kernel) {
if (!kernel && !pgtable_page_ctor(page)) { page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT);
__free_page(page); if (!page)
return NULL; return NULL;
if (!pgtable_page_ctor(page)) {
__free_page(page);
return NULL;
}
} else {
page = alloc_page(PGALLOC_GFP);
if (!page)
return NULL;
} }
ret = page_address(page); ret = page_address(page);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment