Files
linux-stable-mirror/include/linux/ksm.h
T
Lorenzo Stoakes (Oracle) 3a6455d56b mm: convert do_brk_flags() to use vma_flags_t
In order to be able to do this, we need to change VM_DATA_DEFAULT_FLAGS
and friends and update the architecture-specific definitions also.

We then have to update some KSM logic to handle VMA flags, and introduce
VMA_STACK_FLAGS to define the vma_flags_t equivalent of VM_STACK_FLAGS.

We also introduce two helper functions for use during the time we are
converting legacy flags to vma_flags_t values - vma_flags_to_legacy() and
legacy_to_vma_flags().

This enables us to iteratively make changes to break these changes up into
separate parts.

We use these explicitly here to keep VM_STACK_FLAGS around for certain
users which need to maintain the legacy vm_flags_t values for the time
being.

We are no longer able to rely on the simple VM_xxx being set to zero if
the feature is not enabled, so in the case of VM_DROPPABLE we introduce
VMA_DROPPABLE as the vma_flags_t equivalent, which is set to
EMPTY_VMA_FLAGS if the droppable flag is not available.

While we're here, we make the description of do_brk_flags() into a kdoc
comment, as it almost was already.

We use vma_flags_to_legacy() to not need to update the vm_get_page_prot()
logic as this time.

Note that in create_init_stack_vma() we have to replace the BUILD_BUG_ON()
with a VM_WARN_ON_ONCE() as the tested values are no longer build time
available.

We also update mprotect_fixup() to use VMA flags where possible, though we
have to live with a little duplication between vm_flags_t and vma_flags_t
values for the time being until further conversions are made.

While we're here, update VM_SPECIAL to be defined in terms of
VMA_SPECIAL_FLAGS now we have vma_flags_to_legacy().

Finally, we update the VMA tests to reflect these changes.

Link: https://lkml.kernel.org/r/d02e3e45d9a33d7904b149f5604904089fd640ae.1774034900.git.ljs@kernel.org
Signed-off-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Acked-by: Paul Moore <paul@paul-moore.com>	[SELinux]
Acked-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Kees Cook <kees@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ondrej Mosnacek <omosnace@redhat.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Will Deacon <will@kernel.org>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2026-04-05 13:53:40 -07:00

165 lines
4.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_KSM_H
#define __LINUX_KSM_H
/*
* Memory merging support.
*
* This code enables dynamic sharing of identical pages found in different
* memory areas, even if they are not shared by fork().
*/
#include <linux/bitops.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/sched.h>
#ifdef CONFIG_KSM
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, vm_flags_t *vm_flags);
vma_flags_t ksm_vma_flags(struct mm_struct *mm, const struct file *file,
vma_flags_t vma_flags);
int ksm_enable_merge_any(struct mm_struct *mm);
int ksm_disable_merge_any(struct mm_struct *mm);
int ksm_disable(struct mm_struct *mm);
int __ksm_enter(struct mm_struct *mm);
void __ksm_exit(struct mm_struct *mm);
/*
* To identify zeropages that were mapped by KSM, we reuse the dirty bit
* in the PTE. If the PTE is dirty, the zeropage was mapped by KSM when
* deduplicating memory.
*/
#define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte))
extern atomic_long_t ksm_zero_pages;
static inline void ksm_map_zero_page(struct mm_struct *mm)
{
atomic_long_inc(&ksm_zero_pages);
atomic_long_inc(&mm->ksm_zero_pages);
}
static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte)
{
if (is_ksm_zero_pte(pte)) {
atomic_long_dec(&ksm_zero_pages);
atomic_long_dec(&mm->ksm_zero_pages);
}
}
static inline long mm_ksm_zero_pages(struct mm_struct *mm)
{
return atomic_long_read(&mm->ksm_zero_pages);
}
static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
/* Adding mm to ksm is best effort on fork. */
if (mm_flags_test(MMF_VM_MERGEABLE, oldmm)) {
long nr_ksm_zero_pages = atomic_long_read(&mm->ksm_zero_pages);
mm->ksm_merging_pages = 0;
mm->ksm_rmap_items = 0;
atomic_long_add(nr_ksm_zero_pages, &ksm_zero_pages);
__ksm_enter(mm);
}
}
static inline int ksm_execve(struct mm_struct *mm)
{
if (mm_flags_test(MMF_VM_MERGE_ANY, mm))
return __ksm_enter(mm);
return 0;
}
static inline void ksm_exit(struct mm_struct *mm)
{
if (mm_flags_test(MMF_VM_MERGEABLE, mm))
__ksm_exit(mm);
}
/*
* When do_swap_page() first faults in from swap what used to be a KSM page,
* no problem, it will be assigned to this vma's anon_vma; but thereafter,
* it might be faulted into a different anon_vma (or perhaps to a different
* offset in the same anon_vma). do_swap_page() cannot do all the locking
* needed to reconstitute a cross-anon_vma KSM page: for now it has to make
* a copy, and leave remerging the pages to a later pass of ksmd.
*
* We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
* but what if the vma was unmerged while the page was swapped out?
*/
struct folio *ksm_might_need_to_copy(struct folio *folio,
struct vm_area_struct *vma, unsigned long addr);
void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
void collect_procs_ksm(const struct folio *folio, const struct page *page,
struct list_head *to_kill, int force_early);
long ksm_process_profit(struct mm_struct *);
bool ksm_process_mergeable(struct mm_struct *mm);
#else /* !CONFIG_KSM */
static inline vma_flags_t ksm_vma_flags(struct mm_struct *mm,
const struct file *file, vma_flags_t vma_flags)
{
return vma_flags;
}
static inline int ksm_disable(struct mm_struct *mm)
{
return 0;
}
static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
}
static inline int ksm_execve(struct mm_struct *mm)
{
return 0;
}
static inline void ksm_exit(struct mm_struct *mm)
{
}
static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte)
{
}
static inline void collect_procs_ksm(const struct folio *folio,
const struct page *page, struct list_head *to_kill,
int force_early)
{
}
#ifdef CONFIG_MMU
static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, vm_flags_t *vm_flags)
{
return 0;
}
static inline struct folio *ksm_might_need_to_copy(struct folio *folio,
struct vm_area_struct *vma, unsigned long addr)
{
return folio;
}
static inline void rmap_walk_ksm(struct folio *folio,
struct rmap_walk_control *rwc)
{
}
static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old)
{
}
#endif /* CONFIG_MMU */
#endif /* !CONFIG_KSM */
#endif /* __LINUX_KSM_H */