linux/mm/fremap.c

236 lines
6.0 KiB
C
Raw Normal View History

/*
* linux/mm/fremap.c
*
* Explicit pagetable population and nonlinear (random) mappings support.
*
* started by Ingo Molnar, Copyright (C) 2002, 2003
*/
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/file.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
pte_t pte = *ptep;
if (pte_present(pte)) {
struct page *page;
flush_cache_page(vma, addr, pte_pfn(pte));
pte = ptep_clear_flush(vma, addr, ptep);
page = vm_normal_page(vma, addr, pte);
if (page) {
if (pte_dirty(pte))
set_page_dirty(page);
page_remove_rmap(page, vma);
page_cache_release(page);
update_hiwater_rss(mm);
dec_mm_counter(mm, file_rss);
}
} else {
if (!pte_file(pte))
free_swap_and_cache(pte_to_swp_entry(pte));
pte_clear_not_present_full(mm, addr, ptep, 0);
}
}
/*
* Install a file pte to a given virtual memory address, release any
* previously existing mapping.
*/
static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long pgoff, pgprot_t prot)
{
int err = -ENOMEM;
pte_t *pte;
spinlock_t *ptl;
pte = get_locked_pte(mm, addr, &ptl);
if (!pte)
goto out;
if (!pte_none(*pte))
zap_pte(mm, vma, addr, pte);
set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
/*
* We don't need to run update_mmu_cache() here because the "file pte"
* being installed by install_file_pte() is not a real pte - it's a
* non-present entry (like a swap entry), noting what file offset should
* be mapped there when there's a fault (in a non-linear vma where
* that's not obvious).
*/
pte_unmap_unlock(pte, ptl);
err = 0;
out:
return err;
}
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:46:59 +00:00
static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long size, pgoff_t pgoff)
{
int err;
do {
err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot);
if (err)
return err;
size -= PAGE_SIZE;
addr += PAGE_SIZE;
pgoff++;
} while (size);
return 0;
}
/***
* sys_remap_file_pages - remap arbitrary pages of a shared backing store
* file within an existing vma.
* @start: start of the remapped virtual memory range
* @size: size of the remapped virtual memory range
* @prot: new protection bits of the range
* @pgoff: to be mapped page of the backing store file
* @flags: 0 or MAP_NONBLOCKED - the later will cause no IO.
*
* this syscall works purely via pagetables, so it's the most efficient
* way to map the same (large) file into a given virtual window. Unlike
* mmap()/mremap() it does not create any new vmas. The new mappings are
* also safe across swapout.
*
* NOTE: the 'prot' parameter right now is ignored, and the vma's default
* protection is used. Arbitrary protections might be implemented in the
* future.
*/
asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
unsigned long __prot, unsigned long pgoff, unsigned long flags)
{
struct mm_struct *mm = current->mm;
struct address_space *mapping;
unsigned long end = start + size;
struct vm_area_struct *vma;
int err = -EINVAL;
int has_write_lock = 0;
if (__prot)
return err;
/*
* Sanitize the syscall parameters:
*/
start = start & PAGE_MASK;
size = size & PAGE_MASK;
/* Does the address range wrap, or is the span zero-sized? */
if (start + size <= start)
return err;
/* Can we represent this offset inside this architecture's pte's? */
#if PTE_FILE_MAX_BITS < BITS_PER_LONG
if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
return err;
#endif
/* We need down_write() to change vma->vm_flags. */
down_read(&mm->mmap_sem);
retry:
vma = find_vma(mm, start);
/*
* Make sure the vma is shared, that it supports prefaulting,
* and that the remapped range is valid and fully within
* the single existing vma. vm_private_data is used as a
* swapout cursor in a VM_NONLINEAR vma.
*/
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:46:59 +00:00
if (!vma || !(vma->vm_flags & VM_SHARED))
goto out;
if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
goto out;
if (!(vma->vm_flags & VM_CAN_NONLINEAR))
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:46:59 +00:00
goto out;
if (end <= start || start < vma->vm_start || end > vma->vm_end)
goto out;
/* Must set VM_NONLINEAR before any pages are populated. */
if (!(vma->vm_flags & VM_NONLINEAR)) {
/* Don't need a nonlinear mapping, exit success */
if (pgoff == linear_page_index(vma, start)) {
err = 0;
goto out;
}
if (!has_write_lock) {
up_read(&mm->mmap_sem);
down_write(&mm->mmap_sem);
has_write_lock = 1;
goto retry;
}
mapping = vma->vm_file->f_mapping;
/*
* page_mkclean doesn't work on nonlinear vmas, so if
* dirty pages need to be accounted, emulate with linear
* vmas.
*/
if (mapping_cap_account_dirty(mapping)) {
unsigned long addr;
flags &= MAP_NONBLOCK;
addr = mmap_region(vma->vm_file, start, size,
flags, vma->vm_flags, pgoff, 1);
if (IS_ERR_VALUE(addr)) {
err = addr;
} else {
BUG_ON(addr != start);
err = 0;
}
goto out;
}
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:46:59 +00:00
spin_lock(&mapping->i_mmap_lock);
flush_dcache_mmap_lock(mapping);
vma->vm_flags |= VM_NONLINEAR;
vma_prio_tree_remove(vma, &mapping->i_mmap);
vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
flush_dcache_mmap_unlock(mapping);
spin_unlock(&mapping->i_mmap_lock);
}
err = populate_range(mm, vma, start, size, pgoff);
if (!err && !(flags & MAP_NONBLOCK)) {
if (unlikely(has_write_lock)) {
downgrade_write(&mm->mmap_sem);
has_write_lock = 0;
}
make_pages_present(start, start+size);
}
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:46:59 +00:00
/*
* We can't clear VM_NONLINEAR because we'd have to do
* it after ->populate completes, and that would prevent
* downgrading the lock. (Locks can't be upgraded).
*/
mm: merge populate and nopage into fault (fixes nonlinear) Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes the virtual address -> file offset differently from linear mappings. ->populate is a layering violation because the filesystem/pagecache code should need to know anything about the virtual memory mapping. The hitch here is that the ->nopage handler didn't pass down enough information (ie. pgoff). But it is more logical to pass pgoff rather than have the ->nopage function calculate it itself anyway (because that's a similar layering violation). Having the populate handler install the pte itself is likewise a nasty thing to be doing. This patch introduces a new fault handler that replaces ->nopage and ->populate and (later) ->nopfn. Most of the old mechanism is still in place so there is a lot of duplication and nice cleanups that can be removed if everyone switches over. The rationale for doing this in the first place is that nonlinear mappings are subject to the pagefault vs invalidate/truncate race too, and it seemed stupid to duplicate the synchronisation logic rather than just consolidate the two. After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in pagecache. Seems like a fringe functionality anyway. NOPAGE_REFAULT is removed. This should be implemented with ->fault, and no users have hit mainline yet. [akpm@linux-foundation.org: cleanup] [randy.dunlap@oracle.com: doc. fixes for readahead] [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Cc: Mark Fasheh <mark.fasheh@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:46:59 +00:00
out:
if (likely(!has_write_lock))
up_read(&mm->mmap_sem);
else
up_write(&mm->mmap_sem);
return err;
}