/*
* 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 <asm/pgtable.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-
-/*
- * Called with mm->page_table_lock held to protect against other
- * threads/the swapper from ripping pte's out from under us.
- */
-static int filemap_sync_pte(pte_t *ptep, struct vm_area_struct *vma,
- unsigned long address, unsigned int flags)
-{
- pte_t pte = *ptep;
- unsigned long pfn = pte_pfn(pte);
- struct page *page;
-
- if (pte_present(pte) && pfn_valid(pfn)) {
- page = pfn_to_page(pfn);
- if (!PageReserved(page) &&
- (ptep_clear_flush_dirty(vma, address, ptep) ||
- page_test_and_clear_dirty(page)))
- set_page_dirty(page);
- }
- return 0;
-}
-
-static int filemap_sync_pte_range(pmd_t * pmd,
- unsigned long address, unsigned long end,
- struct vm_area_struct *vma, unsigned int flags)
-{
- pte_t *pte;
- int error;
-
- if (pmd_none(*pmd))
- return 0;
- if (pmd_bad(*pmd)) {
- pmd_ERROR(*pmd);
- pmd_clear(pmd);
- return 0;
- }
- pte = pte_offset_map(pmd, address);
- if ((address & PMD_MASK) != (end & PMD_MASK))
- end = (address & PMD_MASK) + PMD_SIZE;
- error = 0;
- do {
- error |= filemap_sync_pte(pte, vma, address, flags);
- address += PAGE_SIZE;
- pte++;
- } while (address && (address < end));
-
- pte_unmap(pte - 1);
-
- return error;
-}
-
-static inline int filemap_sync_pmd_range(pgd_t * pgd,
- unsigned long address, unsigned long end,
- struct vm_area_struct *vma, unsigned int flags)
-{
- pmd_t * pmd;
- int error;
-
- if (pgd_none(*pgd))
- return 0;
- if (pgd_bad(*pgd)) {
- pgd_ERROR(*pgd);
- pgd_clear(pgd);
- return 0;
- }
- pmd = pmd_offset(pgd, address);
- if ((address & PGDIR_MASK) != (end & PGDIR_MASK))
- end = (address & PGDIR_MASK) + PGDIR_SIZE;
- error = 0;
- do {
- error |= filemap_sync_pte_range(pmd, address, end, vma, flags);
- address = (address + PMD_SIZE) & PMD_MASK;
- pmd++;
- } while (address && (address < end));
- return error;
-}
-
-static int filemap_sync(struct vm_area_struct * vma, unsigned long address,
- size_t size, unsigned int flags)
-{
- pgd_t * dir;
- unsigned long end = address + size;
- int error = 0;
-
- /* Aquire the lock early; it may be possible to avoid dropping
- * and reaquiring it repeatedly.
- */
- spin_lock(&vma->vm_mm->page_table_lock);
-
- dir = pgd_offset(vma->vm_mm, address);
- flush_cache_range(vma, address, end);
- if (address >= end)
- BUG();
- do {
- error |= filemap_sync_pmd_range(dir, address, end, vma, flags);
- address = (address + PGDIR_SIZE) & PGDIR_MASK;
- dir++;
- } while (address && (address < end));
- /*
- * Why flush ? filemap_sync_pte already flushed the tlbs with the
- * dirty bits.
- */
- flush_tlb_range(vma, end - size, end);
-
- spin_unlock(&vma->vm_mm->page_table_lock);
-
- return error;
-}
+#include <linux/file.h>
+#include <linux/syscalls.h>
/*
* 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 my _not_ starting I/O in MS_ASYNC we provide complete flexibility to
+ * 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 start, unsigned long end, int flags)
-{
- int ret = 0;
- struct file * file = vma->vm_file;
-
- if ((flags & MS_INVALIDATE) && (vma->vm_flags & VM_LOCKED))
- return -EBUSY;
-
- if (file && (vma->vm_flags & VM_SHARED)) {
- ret = filemap_sync(vma, start, end-start, flags);
-
- if (!ret && (flags & MS_SYNC)) {
- struct address_space *mapping = file->f_mapping;
- int err;
-
- down(&mapping->host->i_sem);
- ret = filemap_fdatawrite(mapping);
- if (file->f_op && file->f_op->fsync) {
- err = file->f_op->fsync(file,file->f_dentry,1);
- if (err && !ret)
- ret = err;
- }
- err = filemap_fdatawait(mapping);
- if (!ret)
- ret = err;
- up(&mapping->host->i_sem);
- }
- }
- return ret;
-}
-
asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
{
unsigned long end;
- struct vm_area_struct * vma;
- int unmapped_error, error = -EINVAL;
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ int unmapped_error = 0;
+ int error = -EINVAL;
- down_read(¤t->mm->mmap_sem);
if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
goto out;
if (start & ~PAGE_MASK)
* If the interval [start,end) covers some unmapped address ranges,
* just ignore them, but return -ENOMEM at the end.
*/
- vma = find_vma(current->mm, start);
- unmapped_error = 0;
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, start);
for (;;) {
+ struct file *file;
+
/* Still start < end. */
error = -ENOMEM;
if (!vma)
- goto out;
+ goto out_unlock;
/* Here start < vma->vm_end. */
if (start < vma->vm_start) {
- unmapped_error = -ENOMEM;
start = vma->vm_start;
+ if (start >= end)
+ goto out_unlock;
+ unmapped_error = -ENOMEM;
}
/* Here vma->vm_start <= start < vma->vm_end. */
- if (end <= vma->vm_end) {
- if (start < end) {
- error = msync_interval(vma, start, end, flags);
- if (error)
- goto out;
- }
- error = unmapped_error;
- goto out;
+ if ((flags & MS_INVALIDATE) &&
+ (vma->vm_flags & VM_LOCKED)) {
+ error = -EBUSY;
+ goto out_unlock;
}
- /* Here vma->vm_start <= start < vma->vm_end < end. */
- error = msync_interval(vma, start, vma->vm_end, flags);
- if (error)
- goto out;
+ file = vma->vm_file;
start = vma->vm_end;
- vma = vma->vm_next;
+ if ((flags & MS_SYNC) && file &&
+ (vma->vm_flags & VM_SHARED)) {
+ get_file(file);
+ up_read(&mm->mmap_sem);
+ error = do_fsync(file, 0);
+ fput(file);
+ 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;
+ }
}
+out_unlock:
+ up_read(&mm->mmap_sem);
out:
- up_read(¤t->mm->mmap_sem);
- return error;
+ return error ? : unmapped_error;
}