Commit 84638335 authored by Konstantin Khlebnikov's avatar Konstantin Khlebnikov Committed by Linus Torvalds
Browse files

mm: rework virtual memory accounting 



When inspecting a vague code inside prctl(PR_SET_MM_MEM) call (which
testing the RLIMIT_DATA value to figure out if we're allowed to assign
new @start_brk, @brk, @start_data, @end_data from mm_struct) it's been
commited that RLIMIT_DATA in a form it's implemented now doesn't do
anything useful because most of user-space libraries use mmap() syscall
for dynamic memory allocations.

Linus suggested to convert RLIMIT_DATA rlimit into something suitable
for anonymous memory accounting.  But in this patch we go further, and
the changes are bundled together as:

 * keep vma counting if CONFIG_PROC_FS=n, will be used for limits
 * replace mm->shared_vm with better defined mm->data_vm
 * account anonymous executable areas as executable
 * account file-backed growsdown/up areas as stack
 * drop struct file* argument from vm_stat_account
 * enforce RLIMIT_DATA for size of data areas

This way code looks cleaner: now code/stack/data classification depends
only on vm_flags state:

 VM_EXEC & ~VM_WRITE            -> code  (VmExe + VmLib in proc)
 VM_GROWSUP | VM_GROWSDOWN      -> stack (VmStk)
 VM_WRITE & ~VM_SHARED & !stack -> data  (VmData)

The rest (VmSize - VmData - VmStk - VmExe - VmLib) could be called
"shared", but that might be strange beast like readonly-private or VM_IO
area.

 - RLIMIT_AS            limits whole address space "VmSize"
 - RLIMIT_STACK         limits stack "VmStk" (but each vma individually)
 - RLIMIT_DATA          now limits "VmData"

Signed-off-by: default avatarKonstantin Khlebnikov <koct9i@gmail.com>
Signed-off-by: default avatarCyrill Gorcunov <gorcunov@openvz.org>
Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: Vegard Nossum <vegard.nossum@oracle.com>
Acked-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Kees Cook <keescook@google.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent d30b5545

arch/ia64/kernel/perfmon.c

+1 −2
Original line number Diff line number Diff line
@@ -2332,8 +2332,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t 
	 */

	insert_vm_struct(mm, vma);



	vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,

							vma_pages(vma));

	vm_stat_account(vma->vm_mm, vma->vm_flags, vma_pages(vma));

	up_write(&task->mm->mmap_sem);



	/*

fs/proc/task_mmu.c

+3 −4
Original line number Diff line number Diff line
@@ -23,7 +23,7 @@ 


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

{

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

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

	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;



	anon = get_mm_counter(mm, MM_ANONPAGES);
@@ -44,7 +44,6 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) 
	if (hiwater_rss < mm->hiwater_rss)

		hiwater_rss = mm->hiwater_rss;



	data = mm->total_vm - mm->shared_vm - mm->stack_vm;

	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);
@@ -76,7 +75,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) 
		anon << (PAGE_SHIFT-10),

		file << (PAGE_SHIFT-10),

		shmem << (PAGE_SHIFT-10),

		data << (PAGE_SHIFT-10),

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

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

		ptes >> 10,

		pmds >> 10,
@@ -97,7 +96,7 @@ unsigned long task_statm(struct mm_struct *mm, 
			get_mm_counter(mm, MM_SHMEMPAGES);

	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))

								>> PAGE_SHIFT;

	*data = mm->total_vm - mm->shared_vm;

	*data = mm->data_vm + mm->stack_vm;

	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);

	return mm->total_vm;

}

include/linux/mm.h

+3 −10
Original line number Diff line number Diff line
@@ -1929,7 +1929,9 @@ extern void mm_drop_all_locks(struct mm_struct *mm); 
extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);

extern struct file *get_mm_exe_file(struct mm_struct *mm);



extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);

extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages);

extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages);



extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,

				   unsigned long addr, unsigned long len,

				   unsigned long flags,
@@ -2147,15 +2149,6 @@ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, 
extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,

			       unsigned long size, pte_fn_t fn, void *data);



#ifdef CONFIG_PROC_FS

void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);

#else

static inline void vm_stat_account(struct mm_struct *mm,

			unsigned long flags, struct file *file, long pages)

{

	mm->total_vm += pages;

}

#endif /* CONFIG_PROC_FS */



#ifdef CONFIG_DEBUG_PAGEALLOC

extern bool _debug_pagealloc_enabled;

include/linux/mm_types.h

+1 −1
Original line number Diff line number Diff line
@@ -427,7 +427,7 @@ struct mm_struct { 
	unsigned long total_vm;		/* Total pages mapped */

	unsigned long locked_vm;	/* Pages that have PG_mlocked set */

	unsigned long pinned_vm;	/* Refcount permanently increased */

	unsigned long shared_vm;	/* Shared pages (files) */

	unsigned long data_vm;		/* VM_WRITE & ~VM_SHARED/GROWSDOWN */

	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE */

	unsigned long stack_vm;		/* VM_GROWSUP/DOWN */

	unsigned long def_flags;

kernel/fork.c

+2 −3
Original line number Diff line number Diff line
@@ -414,7 +414,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) 
	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));



	mm->total_vm = oldmm->total_vm;

	mm->shared_vm = oldmm->shared_vm;

	mm->data_vm = oldmm->data_vm;

	mm->exec_vm = oldmm->exec_vm;

	mm->stack_vm = oldmm->stack_vm;
@@ -433,8 +433,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) 
		struct file *file;



		if (mpnt->vm_flags & VM_DONTCOPY) {

			vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,

							-vma_pages(mpnt));

			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));

			continue;

		}

		charge = 0;

CRA Git | Maintained and supported by SUSTech CRA and CCSE