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

Commit af5b0f6a authored by Kirill A. Shutemov's avatar Kirill A. Shutemov Committed by Linus Torvalds
Browse files

mm: consolidate page table accounting 

Currently, we account page tables separately for each page table level,
but that's redundant -- we only make use of total memory allocated to
page tables for oom_badness calculation.  We also provide the
information to userspace, but it has dubious value there too.

This patch switches page table accounting to single counter.

mm->pgtables_bytes is now used to account all page table levels.  We use
bytes, because page table size for different levels of page table tree
may be different.

The change has user-visible effect: we don't have VmPMD and VmPUD
reported in /proc/[pid]/status.  Not sure if anybody uses them.  (As
alternative, we can always report 0 kB for them.)

OOM-killer report is also slightly changed: we now report pgtables_bytes
instead of nr_ptes, nr_pmd, nr_puds.

Apart from reducing number of counters per-mm, the benefit is that we
now calculate oom_badness() more correctly for machines which have
different size of page tables depending on level or where page tables
are less than a page in size.

The only downside can be debuggability because we do not know which page
table level could leak.  But I do not remember many bugs that would be
caught by separate counters so I wouldn't lose sleep over this.

[akpm@linux-foundation.org: fix mm/huge_memory.c]
Link: http://lkml.kernel.org/r/20171006100651.44742-2-kirill.shutemov@linux.intel.com


Signed-off-by: default avatarKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: default avatarMichal Hocko <mhocko@suse.com>
[kirill.shutemov@linux.intel.com: fix build]
  Link: http://lkml.kernel.org/r/20171016150113.ikfxy3e7zzfvsr4w@black.fi.intel.com


Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent c4812909

Documentation/filesystems/proc.txt

+0 −1
Original line number Diff line number Diff line
@@ -250,7 +250,6 @@ Table 1-2: Contents of the status files (as of 4.8) 
 VmExe                       size of text segment

 VmLib                       size of shared library code

 VmPTE                       size of page table entries

 VmPMD                       size of second level page tables

 VmSwap                      amount of swap used by anonymous private data

                             (shmem swap usage is not included)

 HugetlbPages                size of hugetlb memory portions

Documentation/sysctl/vm.txt

+4 −4
Original line number Diff line number Diff line
@@ -629,10 +629,10 @@ oom_dump_tasks 


Enables a system-wide task dump (excluding kernel threads) to be produced

when the kernel performs an OOM-killing and includes such information as

pid, uid, tgid, vm size, rss, nr_ptes, nr_pmds, nr_puds, swapents,

oom_score_adj score, and name.  This is helpful to determine why the OOM

killer was invoked, to identify the rogue task that caused it, and to

determine why the OOM killer chose the task it did to kill.

pid, uid, tgid, vm size, rss, pgtables_bytes, swapents, oom_score_adj

score, and name.  This is helpful to determine why the OOM killer was

invoked, to identify the rogue task that caused it, and to determine why

the OOM killer chose the task it did to kill.



If this is set to zero, this information is suppressed.  On very

large systems with thousands of tasks it may not be feasible to dump

fs/proc/task_mmu.c

+2 −9
Original line number Diff line number Diff line
@@ -26,7 +26,7 @@ 


void task_mem(struct seq_file *m, struct mm_struct *mm)

{

	unsigned long text, lib, swap, ptes, pmds, puds, anon, file, shmem;

	unsigned long text, lib, swap, anon, file, shmem;

	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;



	anon = get_mm_counter(mm, MM_ANONPAGES);
@@ -50,9 +50,6 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) 
	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;

	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;

	swap = get_mm_counter(mm, MM_SWAPENTS);

	ptes = PTRS_PER_PTE * sizeof(pte_t) * mm_nr_ptes(mm);

	pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm);

	puds = PTRS_PER_PUD * sizeof(pud_t) * mm_nr_puds(mm);

	seq_printf(m,

		"VmPeak:\t%8lu kB\n"

		"VmSize:\t%8lu kB\n"
@@ -68,8 +65,6 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) 
		"VmExe:\t%8lu kB\n"

		"VmLib:\t%8lu kB\n"

		"VmPTE:\t%8lu kB\n"

		"VmPMD:\t%8lu kB\n"

		"VmPUD:\t%8lu kB\n"

		"VmSwap:\t%8lu kB\n",

		hiwater_vm << (PAGE_SHIFT-10),

		total_vm << (PAGE_SHIFT-10),
@@ -82,9 +77,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) 
		shmem << (PAGE_SHIFT-10),

		mm->data_vm << (PAGE_SHIFT-10),

		mm->stack_vm << (PAGE_SHIFT-10), text, lib,

		ptes >> 10,

		pmds >> 10,

		puds >> 10,

		mm_pgtables_bytes(mm) >> 10,

		swap << (PAGE_SHIFT-10));

	hugetlb_report_usage(m, mm);

}

include/linux/mm.h

+12 −46
Original line number Diff line number Diff line
@@ -1605,37 +1605,20 @@ static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, 
{

	return 0;

}



static inline unsigned long mm_nr_puds(const struct mm_struct *mm)

{

	return 0;

}



static inline void mm_nr_puds_init(struct mm_struct *mm) {}

static inline void mm_inc_nr_puds(struct mm_struct *mm) {}

static inline void mm_dec_nr_puds(struct mm_struct *mm) {}



#else

int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);



static inline void mm_nr_puds_init(struct mm_struct *mm)

{

	atomic_long_set(&mm->nr_puds, 0);

}



static inline unsigned long mm_nr_puds(const struct mm_struct *mm)

{

	return atomic_long_read(&mm->nr_puds);

}



static inline void mm_inc_nr_puds(struct mm_struct *mm)

{

	atomic_long_inc(&mm->nr_puds);

	atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);

}



static inline void mm_dec_nr_puds(struct mm_struct *mm)

{

	atomic_long_dec(&mm->nr_puds);

	atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);

}

#endif
@@ -1646,64 +1629,47 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, 
	return 0;

}



static inline void mm_nr_pmds_init(struct mm_struct *mm) {}



static inline unsigned long mm_nr_pmds(const struct mm_struct *mm)

{

	return 0;

}



static inline void mm_inc_nr_pmds(struct mm_struct *mm) {}

static inline void mm_dec_nr_pmds(struct mm_struct *mm) {}



#else

int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);



static inline void mm_nr_pmds_init(struct mm_struct *mm)

{

	atomic_long_set(&mm->nr_pmds, 0);

}



static inline unsigned long mm_nr_pmds(const struct mm_struct *mm)

{

	return atomic_long_read(&mm->nr_pmds);

}



static inline void mm_inc_nr_pmds(struct mm_struct *mm)

{

	atomic_long_inc(&mm->nr_pmds);

	atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);

}



static inline void mm_dec_nr_pmds(struct mm_struct *mm)

{

	atomic_long_dec(&mm->nr_pmds);

	atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);

}

#endif



#ifdef CONFIG_MMU

static inline void mm_nr_ptes_init(struct mm_struct *mm)

static inline void mm_pgtables_bytes_init(struct mm_struct *mm)

{

	atomic_long_set(&mm->nr_ptes, 0);

	atomic_long_set(&mm->pgtables_bytes, 0);

}



static inline unsigned long mm_nr_ptes(const struct mm_struct *mm)

static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)

{

	return atomic_long_read(&mm->nr_ptes);

	return atomic_long_read(&mm->pgtables_bytes);

}



static inline void mm_inc_nr_ptes(struct mm_struct *mm)

{

	atomic_long_inc(&mm->nr_ptes);

	atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);

}



static inline void mm_dec_nr_ptes(struct mm_struct *mm)

{

	atomic_long_dec(&mm->nr_ptes);

	atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes);

}

#else

static inline void mm_nr_ptes_init(struct mm_struct *mm) {}



static inline unsigned long mm_nr_ptes(const struct mm_struct *mm)

static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {}

static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm)

{

	return 0;

}

include/linux/mm_types.h

+1 −7
Original line number Diff line number Diff line
@@ -402,13 +402,7 @@ struct mm_struct { 
	atomic_t mm_count;



#ifdef CONFIG_MMU

	atomic_long_t nr_ptes;			/* PTE page table pages */

#endif

#if CONFIG_PGTABLE_LEVELS > 2

	atomic_long_t nr_pmds;			/* PMD page table pages */

#endif

#if CONFIG_PGTABLE_LEVELS > 3

	atomic_long_t nr_puds;			/* PUD page table pages */

	atomic_long_t pgtables_bytes;		/* PTE page table pages */

#endif

	int map_count;				/* number of VMAs */