Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 3b4a7af2 authored by qctecmdr Service's avatar qctecmdr Service Committed by Gerrit - the friendly Code Review server
Browse files

Merge "mm: swap: free up swap on mm reap"

parents f0ec2388 7b5df13b

Documentation/sysctl/vm.txt

+22 −0
Original line number Diff line number Diff line
@@ -67,6 +67,7 @@ Currently, these files are in /proc/sys/vm: 
- vfs_cache_pressure

- watermark_scale_factor

- zone_reclaim_mode

- want_old_faultaround_pte



==============================================================
@@ -945,4 +946,25 @@ Allowing regular swap effectively restricts allocations to the local 
node unless explicitly overridden by memory policies or cpuset

configurations.



=============================================================



want_old_faultaround_pte:



By default faultaround code produces young pte. When want_old_faultaround_pte is

set to 1, faultaround produces old ptes.



During sparse file access faultaround gets more pages mapped and when all of

them are young (default), under memory pressure, this makes vmscan swap out anon

pages instead, or to drop other page cache pages which otherwise stay resident.

Setting want_old_faultaround_pte to 1 avoids this.



Making the faultaround ptes old can result in performance regression on some

architectures. This is due to cycles spent in micro-faults which would take page

walk to set young bit in the pte. One such known test that shows a regression on

x86 is unixbench shell8. Set want_old_faultaround_pte to 1 on architectures

which does not show this regression or if the workload shows overall performance

benefit with old faultaround ptes.



The default value is 0.



============ End of Document =================================

include/linux/mm.h

+3 −0
Original line number Diff line number Diff line
@@ -318,6 +318,7 @@ extern pgprot_t protection_map[16]; 
#define FAULT_FLAG_USER		0x40	/* The fault originated in userspace */

#define FAULT_FLAG_REMOTE	0x80	/* faulting for non current tsk/mm */

#define FAULT_FLAG_INSTRUCTION  0x100	/* The fault was during an instruction fetch */

#define FAULT_FLAG_PREFAULT_OLD 0x400   /* Make faultaround ptes old */



#define FAULT_FLAG_TRACE \

	{ FAULT_FLAG_WRITE,		"WRITE" }, \
@@ -2796,5 +2797,7 @@ void __init setup_nr_node_ids(void); 
static inline void setup_nr_node_ids(void) {}

#endif



extern int want_old_faultaround_pte;



#endif /* __KERNEL__ */

#endif /* _LINUX_MM_H */

kernel/sysctl.c

+9 −0
Original line number Diff line number Diff line
@@ -1550,6 +1550,15 @@ static struct ctl_table vm_table[] = { 
		.extra1		= &zero,

		.extra2		= &one_hundred,

	},

	{

		.procname       = "want_old_faultaround_pte",

		.data           = &want_old_faultaround_pte,

		.maxlen         = sizeof(want_old_faultaround_pte),

		.mode           = 0644,

		.proc_handler   = proc_dointvec_minmax,

		.extra1         = &zero,

		.extra2         = &one,

	},

#ifdef CONFIG_HUGETLB_PAGE

	{

		.procname	= "nr_hugepages",

mm/filemap.c

+10 −0
Original line number Diff line number Diff line
@@ -48,6 +48,8 @@ 


#include <asm/mman.h>



int want_old_faultaround_pte = 1;



/*

 * Shared mappings implemented 30.11.1994. It's not fully working yet,

 * though.
@@ -2676,6 +2678,14 @@ void filemap_map_pages(struct vm_fault *vmf, 
		if (vmf->pte)

			vmf->pte += iter.index - last_pgoff;

		last_pgoff = iter.index;



		if (want_old_faultaround_pte) {

			if (iter.index == vmf->pgoff)

				vmf->flags &= ~FAULT_FLAG_PREFAULT_OLD;

			else

				vmf->flags |= FAULT_FLAG_PREFAULT_OLD;

		}



		if (alloc_set_pte(vmf, NULL, page))

			goto unlock;

		unlock_page(page);

mm/memory.c

+4 −0
Original line number Diff line number Diff line
@@ -3455,6 +3455,10 @@ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, 
	entry = mk_pte(page, vma->vm_page_prot);

	if (write)

		entry = maybe_mkwrite(pte_mkdirty(entry), vma);



	if (vmf->flags & FAULT_FLAG_PREFAULT_OLD)

		entry = pte_mkold(entry);



	/* copy-on-write page */

	if (write && !(vma->vm_flags & VM_SHARED)) {

		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);