mm: fix PageUptodate data race
After running SetPageUptodate, preceeding stores to the page contents to actually bring it uptodate may not be ordered with the store to set the page uptodate. Therefore, another CPU which checks PageUptodate is true, then reads the page contents can get stale data. Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after PageUptodate. Many places that test PageUptodate, do so with the page locked, and this would be enough to ensure memory ordering in those places if SetPageUptodate were only called while the page is locked. Unfortunately that is not always the case for some filesystems, but it could be an idea for the future. Also bring the handling of anonymous page uptodateness in line with that of file backed page management, by marking anon pages as uptodate when they _are_ uptodate, rather than when our implementation requires that they be marked as such. Doing allows us to get rid of the smp_wmb's in the page copying functions, which were especially added for anonymous pages for an analogous memory ordering problem. Both file and anonymous pages are handled with the same barriers. FAQ: Q. Why not do this in flush_dcache_page? A. Firstly, flush_dcache_page handles only one side (the smb side) of the ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away memory barriers in a completely unrelated function is nasty; at least in the PageUptodate macros, they are located together with (half) the operations involved in the ordering. Thirdly, the smp_wmb is only required when first bringing the page uptodate, wheras flush_dcache_page should be called each time it is written to through the kernel mapping. It is logically the wrong place to put it. Q. Why does this increase my text size / reduce my performance / etc. A. Because it is adding the necessary instructions to eliminate the data-race. Q. Can it be improved? A. Yes, eg. if you were to create a rule that all SetPageUptodate operations run under the page lock, we could avoid the smp_rmb places where PageUptodate is queried under the page lock. Requires audit of all filesystems and at least some would need reworking. That's great you're interested, I'm eagerly awaiting your patches. Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
62e1c55300
commit
0ed361dec3
|
@ -68,8 +68,6 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
|
||||||
void *addr = kmap_atomic(page, KM_USER0);
|
void *addr = kmap_atomic(page, KM_USER0);
|
||||||
clear_user_page(addr, vaddr, page);
|
clear_user_page(addr, vaddr, page);
|
||||||
kunmap_atomic(addr, KM_USER0);
|
kunmap_atomic(addr, KM_USER0);
|
||||||
/* Make sure this page is cleared on other CPU's too before using it */
|
|
||||||
smp_wmb();
|
|
||||||
}
|
}
|
||||||
|
|
||||||
#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
|
#ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
|
||||||
|
@ -172,8 +170,6 @@ static inline void copy_user_highpage(struct page *to, struct page *from,
|
||||||
copy_user_page(vto, vfrom, vaddr, to);
|
copy_user_page(vto, vfrom, vaddr, to);
|
||||||
kunmap_atomic(vfrom, KM_USER0);
|
kunmap_atomic(vfrom, KM_USER0);
|
||||||
kunmap_atomic(vto, KM_USER1);
|
kunmap_atomic(vto, KM_USER1);
|
||||||
/* Make sure this page is cleared on other CPU's too before using it */
|
|
||||||
smp_wmb();
|
|
||||||
}
|
}
|
||||||
|
|
||||||
#endif
|
#endif
|
||||||
|
|
|
@ -131,16 +131,52 @@
|
||||||
#define ClearPageReferenced(page) clear_bit(PG_referenced, &(page)->flags)
|
#define ClearPageReferenced(page) clear_bit(PG_referenced, &(page)->flags)
|
||||||
#define TestClearPageReferenced(page) test_and_clear_bit(PG_referenced, &(page)->flags)
|
#define TestClearPageReferenced(page) test_and_clear_bit(PG_referenced, &(page)->flags)
|
||||||
|
|
||||||
#define PageUptodate(page) test_bit(PG_uptodate, &(page)->flags)
|
static inline int PageUptodate(struct page *page)
|
||||||
|
{
|
||||||
|
int ret = test_bit(PG_uptodate, &(page)->flags);
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Must ensure that the data we read out of the page is loaded
|
||||||
|
* _after_ we've loaded page->flags to check for PageUptodate.
|
||||||
|
* We can skip the barrier if the page is not uptodate, because
|
||||||
|
* we wouldn't be reading anything from it.
|
||||||
|
*
|
||||||
|
* See SetPageUptodate() for the other side of the story.
|
||||||
|
*/
|
||||||
|
if (ret)
|
||||||
|
smp_rmb();
|
||||||
|
|
||||||
|
return ret;
|
||||||
|
}
|
||||||
|
|
||||||
|
static inline void __SetPageUptodate(struct page *page)
|
||||||
|
{
|
||||||
|
smp_wmb();
|
||||||
|
__set_bit(PG_uptodate, &(page)->flags);
|
||||||
#ifdef CONFIG_S390
|
#ifdef CONFIG_S390
|
||||||
|
page_clear_dirty(page);
|
||||||
|
#endif
|
||||||
|
}
|
||||||
|
|
||||||
static inline void SetPageUptodate(struct page *page)
|
static inline void SetPageUptodate(struct page *page)
|
||||||
{
|
{
|
||||||
|
#ifdef CONFIG_S390
|
||||||
if (!test_and_set_bit(PG_uptodate, &page->flags))
|
if (!test_and_set_bit(PG_uptodate, &page->flags))
|
||||||
page_clear_dirty(page);
|
page_clear_dirty(page);
|
||||||
}
|
|
||||||
#else
|
#else
|
||||||
#define SetPageUptodate(page) set_bit(PG_uptodate, &(page)->flags)
|
/*
|
||||||
|
* Memory barrier must be issued before setting the PG_uptodate bit,
|
||||||
|
* so that all previous stores issued in order to bring the page
|
||||||
|
* uptodate are actually visible before PageUptodate becomes true.
|
||||||
|
*
|
||||||
|
* s390 doesn't need an explicit smp_wmb here because the test and
|
||||||
|
* set bit already provides full barriers.
|
||||||
|
*/
|
||||||
|
smp_wmb();
|
||||||
|
set_bit(PG_uptodate, &(page)->flags);
|
||||||
#endif
|
#endif
|
||||||
|
}
|
||||||
|
|
||||||
#define ClearPageUptodate(page) clear_bit(PG_uptodate, &(page)->flags)
|
#define ClearPageUptodate(page) clear_bit(PG_uptodate, &(page)->flags)
|
||||||
|
|
||||||
#define PageDirty(page) test_bit(PG_dirty, &(page)->flags)
|
#define PageDirty(page) test_bit(PG_dirty, &(page)->flags)
|
||||||
|
|
|
@ -813,6 +813,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
|
||||||
|
|
||||||
spin_unlock(&mm->page_table_lock);
|
spin_unlock(&mm->page_table_lock);
|
||||||
copy_huge_page(new_page, old_page, address, vma);
|
copy_huge_page(new_page, old_page, address, vma);
|
||||||
|
__SetPageUptodate(new_page);
|
||||||
spin_lock(&mm->page_table_lock);
|
spin_lock(&mm->page_table_lock);
|
||||||
|
|
||||||
ptep = huge_pte_offset(mm, address & HPAGE_MASK);
|
ptep = huge_pte_offset(mm, address & HPAGE_MASK);
|
||||||
|
@ -858,6 +859,7 @@ retry:
|
||||||
goto out;
|
goto out;
|
||||||
}
|
}
|
||||||
clear_huge_page(page, address);
|
clear_huge_page(page, address);
|
||||||
|
__SetPageUptodate(page);
|
||||||
|
|
||||||
if (vma->vm_flags & VM_SHARED) {
|
if (vma->vm_flags & VM_SHARED) {
|
||||||
int err;
|
int err;
|
||||||
|
|
|
@ -1518,10 +1518,8 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
|
||||||
memset(kaddr, 0, PAGE_SIZE);
|
memset(kaddr, 0, PAGE_SIZE);
|
||||||
kunmap_atomic(kaddr, KM_USER0);
|
kunmap_atomic(kaddr, KM_USER0);
|
||||||
flush_dcache_page(dst);
|
flush_dcache_page(dst);
|
||||||
return;
|
} else
|
||||||
|
copy_user_highpage(dst, src, va, vma);
|
||||||
}
|
|
||||||
copy_user_highpage(dst, src, va, vma);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
@ -1630,6 +1628,7 @@ gotten:
|
||||||
if (!new_page)
|
if (!new_page)
|
||||||
goto oom;
|
goto oom;
|
||||||
cow_user_page(new_page, old_page, address, vma);
|
cow_user_page(new_page, old_page, address, vma);
|
||||||
|
__SetPageUptodate(new_page);
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Re-check the pte - we dropped the lock
|
* Re-check the pte - we dropped the lock
|
||||||
|
@ -2102,6 +2101,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
|
||||||
page = alloc_zeroed_user_highpage_movable(vma, address);
|
page = alloc_zeroed_user_highpage_movable(vma, address);
|
||||||
if (!page)
|
if (!page)
|
||||||
goto oom;
|
goto oom;
|
||||||
|
__SetPageUptodate(page);
|
||||||
|
|
||||||
entry = mk_pte(page, vma->vm_page_prot);
|
entry = mk_pte(page, vma->vm_page_prot);
|
||||||
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
|
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
|
||||||
|
@ -2202,6 +2202,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
|
||||||
goto out;
|
goto out;
|
||||||
}
|
}
|
||||||
copy_user_highpage(page, vmf.page, address, vma);
|
copy_user_highpage(page, vmf.page, address, vma);
|
||||||
|
__SetPageUptodate(page);
|
||||||
} else {
|
} else {
|
||||||
/*
|
/*
|
||||||
* If the page will be shareable, see if the backing
|
* If the page will be shareable, see if the backing
|
||||||
|
|
|
@ -126,7 +126,7 @@ int swap_readpage(struct file *file, struct page *page)
|
||||||
int ret = 0;
|
int ret = 0;
|
||||||
|
|
||||||
BUG_ON(!PageLocked(page));
|
BUG_ON(!PageLocked(page));
|
||||||
ClearPageUptodate(page);
|
BUG_ON(PageUptodate(page));
|
||||||
bio = get_swap_bio(GFP_KERNEL, page_private(page), page,
|
bio = get_swap_bio(GFP_KERNEL, page_private(page), page,
|
||||||
end_swap_bio_read);
|
end_swap_bio_read);
|
||||||
if (bio == NULL) {
|
if (bio == NULL) {
|
||||||
|
|
|
@ -125,6 +125,7 @@ int add_to_swap(struct page * page, gfp_t gfp_mask)
|
||||||
int err;
|
int err;
|
||||||
|
|
||||||
BUG_ON(!PageLocked(page));
|
BUG_ON(!PageLocked(page));
|
||||||
|
BUG_ON(!PageUptodate(page));
|
||||||
|
|
||||||
for (;;) {
|
for (;;) {
|
||||||
entry = get_swap_page();
|
entry = get_swap_page();
|
||||||
|
@ -147,7 +148,6 @@ int add_to_swap(struct page * page, gfp_t gfp_mask)
|
||||||
|
|
||||||
switch (err) {
|
switch (err) {
|
||||||
case 0: /* Success */
|
case 0: /* Success */
|
||||||
SetPageUptodate(page);
|
|
||||||
SetPageDirty(page);
|
SetPageDirty(page);
|
||||||
return 1;
|
return 1;
|
||||||
case -EEXIST:
|
case -EEXIST:
|
||||||
|
|
Loading…
Reference in a new issue