mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-14 06:35:12 +00:00
79271476b3
Patch series "ksm: support tracking KSM-placed zero-pages", v10. The core idea of this patch set is to enable users to perceive the number of any pages merged by KSM, regardless of whether use_zero_page switch has been turned on, so that users can know how much free memory increase is really due to their madvise(MERGEABLE) actions. But the problem is, when enabling use_zero_pages, all empty pages will be merged with kernel zero pages instead of with each other as use_zero_pages is disabled, and then these zero-pages are no longer monitored by KSM. The motivations to do this is seen at: https://lore.kernel.org/lkml/202302100915227721315@zte.com.cn/ In one word, we hope to implement the support for KSM-placed zero pages tracking without affecting the feature of use_zero_pages, so that app developer can also benefit from knowing the actual KSM profit by getting KSM-placed zero pages to optimize applications eventually when /sys/kernel/mm/ksm/use_zero_pages is enabled. This patch (of 5): When use_zero_pages of ksm is enabled, madvise(addr, len, MADV_UNMERGEABLE) and other ways (like write 2 to /sys/kernel/mm/ksm/run) to trigger unsharing will *not* actually unshare the shared zeropage as placed by KSM (which is against the MADV_UNMERGEABLE documentation). As these KSM-placed zero pages are out of the control of KSM, the related counts of ksm pages don't expose how many zero pages are placed by KSM (these special zero pages are different from those initially mapped zero pages, because the zero pages mapped to MADV_UNMERGEABLE areas are expected to be a complete and unshared page). To not blindly unshare all shared zero_pages in applicable VMAs, the patch use pte_mkdirty (related with architecture) to mark KSM-placed zero pages. Thus, MADV_UNMERGEABLE will only unshare those KSM-placed zero pages. In addition, we'll reuse this mechanism to reliably identify KSM-placed ZeroPages to properly account for them (e.g., calculating the KSM profit that includes zeropages) in the latter patches. The patch will not degrade the performance of use_zero_pages as it doesn't change the way of merging empty pages in use_zero_pages's feature. Link: https://lkml.kernel.org/r/202306131104554703428@zte.com.cn Link: https://lkml.kernel.org/r/20230613030928.185882-1-yang.yang29@zte.com.cn Signed-off-by: xu xin <xu.xin16@zte.com.cn> Acked-by: David Hildenbrand <david@redhat.com> Cc: Claudio Imbrenda <imbrenda@linux.ibm.com> Cc: Xuexin Jiang <jiang.xuexin@zte.com.cn> Reviewed-by: Xiaokai Ran <ran.xiaokai@zte.com.cn> Reviewed-by: Yang Yang <yang.yang29@zte.com.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
135 lines
3.5 KiB
C
135 lines
3.5 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>
|
|
#include <linux/sched/coredump.h>
|
|
|
|
#ifdef CONFIG_KSM
|
|
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
|
|
unsigned long end, int advice, unsigned long *vm_flags);
|
|
|
|
void ksm_add_vma(struct vm_area_struct *vma);
|
|
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))
|
|
|
|
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
|
|
{
|
|
int ret;
|
|
|
|
if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) {
|
|
ret = __ksm_enter(mm);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
|
|
if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags))
|
|
set_bit(MMF_VM_MERGE_ANY, &mm->flags);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline void ksm_exit(struct mm_struct *mm)
|
|
{
|
|
if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
|
|
__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 page *ksm_might_need_to_copy(struct page *page,
|
|
struct vm_area_struct *vma, unsigned long address);
|
|
|
|
void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
|
|
void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
void collect_procs_ksm(struct page *page, struct list_head *to_kill,
|
|
int force_early);
|
|
#endif
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
long ksm_process_profit(struct mm_struct *);
|
|
#endif /* CONFIG_PROC_FS */
|
|
|
|
#else /* !CONFIG_KSM */
|
|
|
|
static inline void ksm_add_vma(struct vm_area_struct *vma)
|
|
{
|
|
}
|
|
|
|
static inline int ksm_disable(struct mm_struct *mm)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void ksm_exit(struct mm_struct *mm)
|
|
{
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
static inline void collect_procs_ksm(struct page *page,
|
|
struct list_head *to_kill, int force_early)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_MMU
|
|
static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
|
|
unsigned long end, int advice, unsigned long *vm_flags)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline struct page *ksm_might_need_to_copy(struct page *page,
|
|
struct vm_area_struct *vma, unsigned long address)
|
|
{
|
|
return page;
|
|
}
|
|
|
|
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 */
|