linux-stable/include/asm-generic/pgalloc.h
Baolin Wang 55d2a0bd5e mm: add statistics for PUD level pagetable
Recently, we found that cross-die access to pagetable pages on ARM64
machines can cause performance fluctuations in our business.  Currently,
there are no PMU events available to track this situation on our ARM64
machines, so accurate pagetable accounting can help to analyze this issue,
but now the PUD level pagetable accounting is missed.

So introduce pagetable_pud_ctor/dtor() to help to get accurate PUD
pagetable accounting, as well as converting the architectures which use
generic PUD pagetable allocation to add corresponding PUD pagetable
accounting.  Moreover this patch will mark the PUD level pagetable with
PG_table flag, which will help to do sanity validation in
unpoison_memory().

On my testing machine, I can see more pagetables statistics after the patch
with page-types tool:

Before patch:
        flags           page-count      MB  symbolic-flags                     long-symbolic-flags
0x0000000004000000           27326      106  __________________________g_________________       pgtable
After patch:
0x0000000004000000           27541      107  __________________________g_________________       pgtable

Link: https://lkml.kernel.org/r/876c71c03a7e69c17722a690e3225a4f7b172fb2.1695017383.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Acked-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-10-06 14:44:10 -07:00

220 lines
5.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __ASM_GENERIC_PGALLOC_H
#define __ASM_GENERIC_PGALLOC_H
#ifdef CONFIG_MMU
#define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO)
#define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT)
/**
* __pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table
* @mm: the mm_struct of the current context
*
* This function is intended for architectures that need
* anything beyond simple page allocation.
*
* Return: pointer to the allocated memory or %NULL on error
*/
static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm)
{
struct ptdesc *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL &
~__GFP_HIGHMEM, 0);
if (!ptdesc)
return NULL;
return ptdesc_address(ptdesc);
}
#ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
/**
* pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table
* @mm: the mm_struct of the current context
*
* Return: pointer to the allocated memory or %NULL on error
*/
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
{
return __pte_alloc_one_kernel(mm);
}
#endif
/**
* pte_free_kernel - free PTE-level kernel page table memory
* @mm: the mm_struct of the current context
* @pte: pointer to the memory containing the page table
*/
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
{
pagetable_free(virt_to_ptdesc(pte));
}
/**
* __pte_alloc_one - allocate memory for a PTE-level user page table
* @mm: the mm_struct of the current context
* @gfp: GFP flags to use for the allocation
*
* Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor().
*
* This function is intended for architectures that need
* anything beyond simple page allocation or must have custom GFP flags.
*
* Return: `struct page` referencing the ptdesc or %NULL on error
*/
static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp)
{
struct ptdesc *ptdesc;
ptdesc = pagetable_alloc(gfp, 0);
if (!ptdesc)
return NULL;
if (!pagetable_pte_ctor(ptdesc)) {
pagetable_free(ptdesc);
return NULL;
}
return ptdesc_page(ptdesc);
}
#ifndef __HAVE_ARCH_PTE_ALLOC_ONE
/**
* pte_alloc_one - allocate a page for PTE-level user page table
* @mm: the mm_struct of the current context
*
* Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor().
*
* Return: `struct page` referencing the ptdesc or %NULL on error
*/
static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
{
return __pte_alloc_one(mm, GFP_PGTABLE_USER);
}
#endif
/*
* Should really implement gc for free page table pages. This could be
* done with a reference count in struct page.
*/
/**
* pte_free - free PTE-level user page table memory
* @mm: the mm_struct of the current context
* @pte_page: the `struct page` referencing the ptdesc
*/
static inline void pte_free(struct mm_struct *mm, struct page *pte_page)
{
struct ptdesc *ptdesc = page_ptdesc(pte_page);
pagetable_pte_dtor(ptdesc);
pagetable_free(ptdesc);
}
#if CONFIG_PGTABLE_LEVELS > 2
#ifndef __HAVE_ARCH_PMD_ALLOC_ONE
/**
* pmd_alloc_one - allocate memory for a PMD-level page table
* @mm: the mm_struct of the current context
*
* Allocate memory for a page table and ptdesc and runs pagetable_pmd_ctor().
*
* Allocations use %GFP_PGTABLE_USER in user context and
* %GFP_PGTABLE_KERNEL in kernel context.
*
* Return: pointer to the allocated memory or %NULL on error
*/
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
struct ptdesc *ptdesc;
gfp_t gfp = GFP_PGTABLE_USER;
if (mm == &init_mm)
gfp = GFP_PGTABLE_KERNEL;
ptdesc = pagetable_alloc(gfp, 0);
if (!ptdesc)
return NULL;
if (!pagetable_pmd_ctor(ptdesc)) {
pagetable_free(ptdesc);
return NULL;
}
return ptdesc_address(ptdesc);
}
#endif
#ifndef __HAVE_ARCH_PMD_FREE
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
pagetable_pmd_dtor(ptdesc);
pagetable_free(ptdesc);
}
#endif
#endif /* CONFIG_PGTABLE_LEVELS > 2 */
#if CONFIG_PGTABLE_LEVELS > 3
static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
gfp_t gfp = GFP_PGTABLE_USER;
struct ptdesc *ptdesc;
if (mm == &init_mm)
gfp = GFP_PGTABLE_KERNEL;
gfp &= ~__GFP_HIGHMEM;
ptdesc = pagetable_alloc(gfp, 0);
if (!ptdesc)
return NULL;
pagetable_pud_ctor(ptdesc);
return ptdesc_address(ptdesc);
}
#ifndef __HAVE_ARCH_PUD_ALLOC_ONE
/**
* pud_alloc_one - allocate memory for a PUD-level page table
* @mm: the mm_struct of the current context
*
* Allocate memory for a page table using %GFP_PGTABLE_USER for user context
* and %GFP_PGTABLE_KERNEL for kernel context.
*
* Return: pointer to the allocated memory or %NULL on error
*/
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
return __pud_alloc_one(mm, addr);
}
#endif
static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
{
struct ptdesc *ptdesc = virt_to_ptdesc(pud);
BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
pagetable_pud_dtor(ptdesc);
pagetable_free(ptdesc);
}
#ifndef __HAVE_ARCH_PUD_FREE
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
{
__pud_free(mm, pud);
}
#endif
#endif /* CONFIG_PGTABLE_LEVELS > 3 */
#ifndef __HAVE_ARCH_PGD_FREE
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
pagetable_free(virt_to_ptdesc(pgd));
}
#endif
#endif /* CONFIG_MMU */
#endif /* __ASM_GENERIC_PGALLOC_H */