AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

mm/thp: fix vma_address() if virtual address below file offset

Browse Source 
commit 494334e43c16d63b878536a26505397fce6ff3a2 upstream.

Running certain tests with a DEBUG_VM kernel would crash within hours,
on the total_mapcount BUG() in split_huge_page_to_list(), while trying
to free up some memory by punching a hole in a shmem huge page: split's
try_to_unmap() was unable to find all the mappings of the page (which,
on a !DEBUG_VM kernel, would then keep the huge page pinned in memory).

When that BUG() was changed to a WARN(), it would later crash on the
VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in
mm/internal.h:vma_address(), used by rmap_walk_file() for
try_to_unmap().

vma_address() is usually correct, but there's a wraparound case when the
vm_start address is unusually low, but vm_pgoff not so low:
vma_address() chooses max(start, vma->vm_start), but that decides on the
wrong address, because start has become almost ULONG_MAX.

Rewrite vma_address() to be more careful about vm_pgoff; move the
VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can
be safely used from page_mapped_in_vma() and page_address_in_vma() too.

Add vma_address_end() to apply similar care to end address calculation,
in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one();
though it raises a question of whether callers would do better to supply
pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch.

An irritation is that their apparent generality breaks down on KSM
pages, which cannot be located by the page->index that page_to_pgoff()
uses: as commit 4b0ece6fa0 ("mm: migrate: fix remove_migration_pte()
for ksm pages") once discovered.  I dithered over the best thing to do
about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both
vma_address() and vma_address_end(); though the only place in danger of
using it on them was try_to_unmap_one().

Sidenote: vma_address() and vma_address_end() now use compound_nr() on a
head page, instead of thp_size(): to make the right calculation on a
hugetlbfs page, whether or not THPs are configured.  try_to_unmap() is
used on hugetlbfs pages, but perhaps the wrong calculation never
mattered.

Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com
Fixes: a8fa41ad2f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of")
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jue Wang <juew@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Hugh Dickins 2021-06-15 18:23:56 -07:00 committed by Sasha Levin
parent 66be14a926
commit 37ffe9f4d7
3 changed files with 53 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
mm/internal.h
View File

@ -379,27 +379,52 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
/*
* At what user virtual address is page expected in @vma?
* At what user virtual address is page expected in vma?
* Returns -EFAULT if all of the page is outside the range of vma.
* If page is a compound head, the entire compound page is considered.
*/
static inline unsigned long
__vma_address(struct page *page, struct vm_area_struct *vma)
{
pgoff_t pgoff = page_to_pgoff(page);
return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
}
static inline unsigned long
vma_address(struct page *page, struct vm_area_struct *vma)
{
unsigned long start, end;
pgoff_t pgoff;
unsigned long address;
start = __vma_address(page, vma);
end = start + thp_size(page) - PAGE_SIZE;
VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
pgoff = page_to_pgoff(page);
if (pgoff >= vma->vm_pgoff) {
address = vma->vm_start +
((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
/* Check for address beyond vma (or wrapped through 0?) */
if (address < vma->vm_start || address >= vma->vm_end)
address = -EFAULT;
} else if (PageHead(page) &&
pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) {
/* Test above avoids possibility of wrap to 0 on 32-bit */
address = vma->vm_start;
} else {
address = -EFAULT;
}
return address;
}
/* page should be within @vma mapping range */
VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma);
/*
* Then at what user virtual address will none of the page be found in vma?
* Assumes that vma_address() already returned a good starting address.
* If page is a compound head, the entire compound page is considered.
*/
static inline unsigned long
vma_address_end(struct page *page, struct vm_area_struct *vma)
{
pgoff_t pgoff;
unsigned long address;
return max(start, vma->vm_start);
VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
pgoff = page_to_pgoff(page) + compound_nr(page);
address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
/* Check for address beyond vma (or wrapped through 0?) */
if (address < vma->vm_start || address > vma->vm_end)
address = vma->vm_end;
return address;
}
static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,

16
mm/page_vma_mapped.c
View File

@ -227,18 +227,18 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
if (!map_pte(pvmw))
goto next_pte;
while (1) {
unsigned long end;
if (check_pte(pvmw))
return true;
next_pte:
/* Seek to next pte only makes sense for THP */
if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
return not_found(pvmw);
end = vma_address_end(pvmw->page, pvmw->vma);
do {
pvmw->address += PAGE_SIZE;
if (pvmw->address >= pvmw->vma->vm_end ||
pvmw->address >=
__vma_address(pvmw->page, pvmw->vma) +
thp_size(pvmw->page))
if (pvmw->address >= end)
return not_found(pvmw);
/* Did we cross page table boundary? */
if (pvmw->address % PMD_SIZE == 0) {
@ -276,14 +276,10 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
.vma = vma,
.flags = PVMW_SYNC,
};
unsigned long start, end;
start = __vma_address(page, vma);
end = start + thp_size(page) - PAGE_SIZE;
if (unlikely(end < vma->vm_start || start >= vma->vm_end))
pvmw.address = vma_address(page, vma);
if (pvmw.address == -EFAULT)
return 0;
pvmw.address = max(start, vma->vm_start);
if (!page_vma_mapped_walk(&pvmw))
return 0;
page_vma_mapped_walk_done(&pvmw);

16
mm/rmap.c
View File

@ -700,7 +700,6 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
*/
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
unsigned long address;
if (PageAnon(page)) {
struct anon_vma *page__anon_vma = page_anon_vma(page);
/*
@ -715,10 +714,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
return -EFAULT;
} else
return -EFAULT;
address = __vma_address(page, vma);
if (unlikely(address < vma->vm_start || address >= vma->vm_end))
return -EFAULT;
return address;
return vma_address(page, vma);
}
pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
@ -912,7 +909,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
*/
mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
0, vma, vma->vm_mm, address,
min(vma->vm_end, address + page_size(page)));
vma_address_end(page, vma));
mmu_notifier_invalidate_range_start(&range);
while (page_vma_mapped_walk(&pvmw)) {
@ -1415,9 +1412,10 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* Note that the page can not be free in this function as call of
* try_to_unmap() must hold a reference on the page.
*/
range.end = PageKsm(page) ?
address + PAGE_SIZE : vma_address_end(page, vma);
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
address,
min(vma->vm_end, address + page_size(page)));
address, range.end);
if (PageHuge(page)) {
/*
* If sharing is possible, start and end will be adjusted
@ -1869,6 +1867,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc,
struct vm_area_struct *vma = avc->vma;
unsigned long address = vma_address(page, vma);
VM_BUG_ON_VMA(address == -EFAULT, vma);
cond_resched();
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
@ -1923,6 +1922,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc,
pgoff_start, pgoff_end) {
unsigned long address = vma_address(page, vma);
VM_BUG_ON_VMA(address == -EFAULT, vma);
cond_resched();
if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))