Commit 204ec841 authored by Peter Zijlstra's avatar Peter Zijlstra Committed by Linus Torvalds
Browse files

[PATCH] mm: msync() cleanup 



With the tracking of dirty pages properly done now, msync doesn't need to scan
the PTEs anymore to determine the dirty status.

From: Hugh Dickins <hugh@veritas.com>

In looking to do that, I made some other tidyups: can remove several
#includes, and sys_msync loop termination not quite right.

Most of those points are criticisms of the existing sys_msync, not of your
patch.  In particular, the loop termination errors were introduced in 2.6.17:
I did notice this shortly before it came out, but decided I was more likely to
get it wrong myself, and make matters worse if I tried to rush a last-minute
fix in.  And it's not terribly likely to go wrong, nor disastrous if it does
go wrong (may miss reporting an unmapped area; may also fsync file of a
following vma).

Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: default avatarHugh Dickins <hugh@veritas.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
parent ee6a6457

mm/msync.c

+33 −163
Original line number Diff line number Diff line
@@ -7,149 +7,33 @@ 
/*

 * The msync() system call.

 */

#include <linux/slab.h>

#include <linux/pagemap.h>

#include <linux/fs.h>

#include <linux/mm.h>

#include <linux/mman.h>

#include <linux/hugetlb.h>

#include <linux/writeback.h>

#include <linux/file.h>

#include <linux/syscalls.h>



#include <asm/pgtable.h>

#include <asm/tlbflush.h>



static unsigned long msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,

				unsigned long addr, unsigned long end)

{

	pte_t *pte;

	spinlock_t *ptl;

	int progress = 0;

	unsigned long ret = 0;



again:

	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);

	do {

		struct page *page;



		if (progress >= 64) {

			progress = 0;

			if (need_resched() || need_lockbreak(ptl))

				break;

		}

		progress++;

		if (!pte_present(*pte))

			continue;

		if (!pte_maybe_dirty(*pte))

			continue;

		page = vm_normal_page(vma, addr, *pte);

		if (!page)

			continue;

		if (ptep_clear_flush_dirty(vma, addr, pte) ||

				page_test_and_clear_dirty(page))

			ret += set_page_dirty(page);

		progress += 3;

	} while (pte++, addr += PAGE_SIZE, addr != end);

	pte_unmap_unlock(pte - 1, ptl);

	cond_resched();

	if (addr != end)

		goto again;

	return ret;

}



static inline unsigned long msync_pmd_range(struct vm_area_struct *vma,

			pud_t *pud, unsigned long addr, unsigned long end)

{

	pmd_t *pmd;

	unsigned long next;

	unsigned long ret = 0;



	pmd = pmd_offset(pud, addr);

	do {

		next = pmd_addr_end(addr, end);

		if (pmd_none_or_clear_bad(pmd))

			continue;

		ret += msync_pte_range(vma, pmd, addr, next);

	} while (pmd++, addr = next, addr != end);

	return ret;

}



static inline unsigned long msync_pud_range(struct vm_area_struct *vma,

			pgd_t *pgd, unsigned long addr, unsigned long end)

{

	pud_t *pud;

	unsigned long next;

	unsigned long ret = 0;



	pud = pud_offset(pgd, addr);

	do {

		next = pud_addr_end(addr, end);

		if (pud_none_or_clear_bad(pud))

			continue;

		ret += msync_pmd_range(vma, pud, addr, next);

	} while (pud++, addr = next, addr != end);

	return ret;

}



static unsigned long msync_page_range(struct vm_area_struct *vma,

				unsigned long addr, unsigned long end)

{

	pgd_t *pgd;

	unsigned long next;

	unsigned long ret = 0;



	/* For hugepages we can't go walking the page table normally,

	 * but that's ok, hugetlbfs is memory based, so we don't need

	 * to do anything more on an msync().

	 */

	if (vma->vm_flags & VM_HUGETLB)

		return 0;



	BUG_ON(addr >= end);

	pgd = pgd_offset(vma->vm_mm, addr);

	flush_cache_range(vma, addr, end);

	do {

		next = pgd_addr_end(addr, end);

		if (pgd_none_or_clear_bad(pgd))

			continue;

		ret += msync_pud_range(vma, pgd, addr, next);

	} while (pgd++, addr = next, addr != end);

	return ret;

}



/*

 * MS_SYNC syncs the entire file - including mappings.

 *

 * MS_ASYNC does not start I/O (it used to, up to 2.5.67).  Instead, it just

 * marks the relevant pages dirty.  The application may now run fsync() to

 * MS_ASYNC does not start I/O (it used to, up to 2.5.67).

 * Nor does it marks the relevant pages dirty (it used to up to 2.6.17).

 * Now it doesn't do anything, since dirty pages are properly tracked.

 *

 * The application may now run fsync() to

 * write out the dirty pages and wait on the writeout and check the result.

 * Or the application may run fadvise(FADV_DONTNEED) against the fd to start

 * async writeout immediately.

 * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to

 * applications.

 */

static int msync_interval(struct vm_area_struct *vma, unsigned long addr,

			unsigned long end, int flags,

			unsigned long *nr_pages_dirtied)

{

	struct file *file = vma->vm_file;



	if ((flags & MS_INVALIDATE) && (vma->vm_flags & VM_LOCKED))

		return -EBUSY;



	if (file && (vma->vm_flags & VM_SHARED))

		*nr_pages_dirtied = msync_page_range(vma, addr, end);

	return 0;

}



asmlinkage long sys_msync(unsigned long start, size_t len, int flags)

{

	unsigned long end;

	struct mm_struct *mm = current->mm;

	struct vm_area_struct *vma;

	int unmapped_error = 0;

	int error = -EINVAL;

	int done = 0;



	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))

		goto out;
@@ -169,64 +53,50 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags) 
	 * If the interval [start,end) covers some unmapped address ranges,

	 * just ignore them, but return -ENOMEM at the end.

	 */

	down_read(&current->mm->mmap_sem);

	vma = find_vma(current->mm, start);

	if (!vma) {

		error = -ENOMEM;

		goto out_unlock;

	}

	do {

		unsigned long nr_pages_dirtied = 0;

	down_read(&mm->mmap_sem);

	vma = find_vma(mm, start);

	for (;;) {

		struct file *file;



		/* Still start < end. */

		error = -ENOMEM;

		if (!vma)

			goto out_unlock;

		/* Here start < vma->vm_end. */

		if (start < vma->vm_start) {

			unmapped_error = -ENOMEM;

			start = vma->vm_start;

		}

		/* Here vma->vm_start <= start < vma->vm_end. */

		if (end <= vma->vm_end) {

			if (start < end) {

				error = msync_interval(vma, start, end, flags,

							&nr_pages_dirtied);

				if (error)

			if (start >= end)

				goto out_unlock;

			unmapped_error = -ENOMEM;

		}

			error = unmapped_error;

			done = 1;

		} else {

			/* Here vma->vm_start <= start < vma->vm_end < end. */

			error = msync_interval(vma, start, vma->vm_end, flags,

						&nr_pages_dirtied);

			if (error)

		/* Here vma->vm_start <= start < vma->vm_end. */

		if ((flags & MS_INVALIDATE) &&

				(vma->vm_flags & VM_LOCKED)) {

			error = -EBUSY;

			goto out_unlock;

		}

		file = vma->vm_file;

		start = vma->vm_end;

		if ((flags & MS_ASYNC) && file && nr_pages_dirtied) {

			get_file(file);

			up_read(&current->mm->mmap_sem);

			balance_dirty_pages_ratelimited_nr(file->f_mapping,

							nr_pages_dirtied);

			fput(file);

			down_read(&current->mm->mmap_sem);

			vma = find_vma(current->mm, start);

		} else if ((flags & MS_SYNC) && file &&

		if ((flags & MS_SYNC) && file &&

				(vma->vm_flags & VM_SHARED)) {

			get_file(file);

			up_read(&current->mm->mmap_sem);

			up_read(&mm->mmap_sem);

			error = do_fsync(file, 0);

			fput(file);

			down_read(&current->mm->mmap_sem);

			if (error)

				goto out_unlock;

			vma = find_vma(current->mm, start);

			if (error || start >= end)

				goto out;

			down_read(&mm->mmap_sem);

			vma = find_vma(mm, start);

		} else {

			if (start >= end) {

				error = 0;

				goto out_unlock;

			}

			vma = vma->vm_next;

		}

	} while (vma && !done);

	}

out_unlock:

	up_read(&current->mm->mmap_sem);

	up_read(&mm->mmap_sem);

out:

	return error;

	return error ? : unmapped_error;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE