linux/include/asm-generic/pgalloc.h
Kevin Brodsky 49f5996664 mm: call ctor/dtor for kernel PTEs
Since [1], constructors/destructors are expected to be called for all page
table pages, at all levels and for both user and kernel pgtables.  There
is however one glaring exception: kernel PTEs are managed via separate
helpers (pte_alloc_kernel/pte_free_kernel), which do not call the [cd]tor,
at least not in the generic implementation.

The most obvious reason for this anomaly is that init_mm is special-cased
not to use split page table locks.  As a result calling ptlock_init() for
PTEs associated with init_mm would be wasteful, potentially resulting in
dynamic memory allocation.  However, pgtable [cd]tors perform other
actions - currently related to accounting/statistics, and potentially more
functionally significant in the future.

Now that pagetable_pte_ctor() is passed the associated mm, we can make it
skip the call to ptlock_init() for init_mm; this allows us to call the
ctor from pte_alloc_one_kernel() too.  This is matched by a call to the
pgtable destructor in pte_free_kernel(); no special-casing is needed on
that path, as ptlock_free() is already called unconditionally. 
(ptlock_free() is a no-op unless a ptlock was allocated for the given
PTP.)

This patch ensures that all architectures that rely on
<asm-generic/pgalloc.h> call the [cd]tor for kernel PTEs. 
pte_free_kernel() cannot be overridden so changing the generic
implementation is sufficient.  pte_alloc_one_kernel() can be overridden
using __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL, and a few architectures implement
it by calling the page allocator directly.  We amend those so that they
call the generic __pte_alloc_one_kernel() instead, if possible, ensuring
that the ctor is called.

A few architectures do not use <asm-generic/pgalloc.h>; those will be
taken care of separately.

[1] https://lore.kernel.org/linux-mm/20250103184415.2744423-1-kevin.brodsky@arm.com/

Link: https://lkml.kernel.org/r/20250408095222.860601-4-kevin.brodsky@arm.com
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com> # s390
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Linus Waleij <linus.walleij@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: <x86@kernel.org>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2025-05-11 17:48:21 -07:00

301 lines
7.7 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_noprof(struct mm_struct *mm)
{
struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL &
~__GFP_HIGHMEM, 0);
if (!ptdesc)
return NULL;
if (!pagetable_pte_ctor(mm, ptdesc)) {
pagetable_free(ptdesc);
return NULL;
}
return ptdesc_address(ptdesc);
}
#define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__))
#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_noprof(struct mm_struct *mm)
{
return __pte_alloc_one_kernel_noprof(mm);
}
#define pte_alloc_one_kernel(...) alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__))
#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_dtor_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_noprof(struct mm_struct *mm, gfp_t gfp)
{
struct ptdesc *ptdesc;
ptdesc = pagetable_alloc_noprof(gfp, 0);
if (!ptdesc)
return NULL;
if (!pagetable_pte_ctor(mm, ptdesc)) {
pagetable_free(ptdesc);
return NULL;
}
return ptdesc_page(ptdesc);
}
#define __pte_alloc_one(...) alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__))
#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_noprof(struct mm_struct *mm)
{
return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER);
}
#define pte_alloc_one(...) alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__))
#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_dtor_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_noprof(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_noprof(gfp, 0);
if (!ptdesc)
return NULL;
if (!pagetable_pmd_ctor(mm, ptdesc)) {
pagetable_free(ptdesc);
return NULL;
}
return ptdesc_address(ptdesc);
}
#define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__))
#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_dtor_free(ptdesc);
}
#endif
#endif /* CONFIG_PGTABLE_LEVELS > 2 */
#if CONFIG_PGTABLE_LEVELS > 3
static inline pud_t *__pud_alloc_one_noprof(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_noprof(gfp, 0);
if (!ptdesc)
return NULL;
pagetable_pud_ctor(ptdesc);
return ptdesc_address(ptdesc);
}
#define __pud_alloc_one(...) alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__))
#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_noprof(struct mm_struct *mm, unsigned long addr)
{
return __pud_alloc_one_noprof(mm, addr);
}
#define pud_alloc_one(...) alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__))
#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_dtor_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 */
#if CONFIG_PGTABLE_LEVELS > 4
static inline p4d_t *__p4d_alloc_one_noprof(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_noprof(gfp, 0);
if (!ptdesc)
return NULL;
pagetable_p4d_ctor(ptdesc);
return ptdesc_address(ptdesc);
}
#define __p4d_alloc_one(...) alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__))
#ifndef __HAVE_ARCH_P4D_ALLOC_ONE
static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
{
return __p4d_alloc_one_noprof(mm, addr);
}
#define p4d_alloc_one(...) alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__))
#endif
static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d)
{
struct ptdesc *ptdesc = virt_to_ptdesc(p4d);
BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
pagetable_dtor_free(ptdesc);
}
#ifndef __HAVE_ARCH_P4D_FREE
static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
{
if (!mm_p4d_folded(mm))
__p4d_free(mm, p4d);
}
#endif
#endif /* CONFIG_PGTABLE_LEVELS > 4 */
static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order)
{
gfp_t gfp = GFP_PGTABLE_USER;
struct ptdesc *ptdesc;
if (mm == &init_mm)
gfp = GFP_PGTABLE_KERNEL;
gfp &= ~__GFP_HIGHMEM;
ptdesc = pagetable_alloc_noprof(gfp, order);
if (!ptdesc)
return NULL;
pagetable_pgd_ctor(ptdesc);
return ptdesc_address(ptdesc);
}
#define __pgd_alloc(...) alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__))
static inline void __pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
pagetable_dtor_free(ptdesc);
}
#ifndef __HAVE_ARCH_PGD_FREE
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
__pgd_free(mm, pgd);
}
#endif
#endif /* CONFIG_MMU */
#endif /* __ASM_GENERIC_PGALLOC_H */