Commit c7ab0d2f authored by Kirill A. Shutemov's avatar Kirill A. Shutemov Committed by Linus Torvalds

mm: convert try_to_unmap_one() to use page_vma_mapped_walk()

For consistency, it worth converting all page_check_address() to
page_vma_mapped_walk(), so we could drop the former.

It also makes freeze_page() as we walk though rmap only once.

Link: http://lkml.kernel.org/r/20170129173858.45174-8-kirill.shutemov@linux.intel.comSigned-off-by: default avatarKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent f27176cf
......@@ -2106,24 +2106,16 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
static void freeze_page(struct page *page)
{
enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
TTU_RMAP_LOCKED;
int i, ret;
TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
int ret;
VM_BUG_ON_PAGE(!PageHead(page), page);
if (PageAnon(page))
ttu_flags |= TTU_MIGRATION;
/* We only need TTU_SPLIT_HUGE_PMD once */
ret = try_to_unmap(page, ttu_flags | TTU_SPLIT_HUGE_PMD);
for (i = 1; !ret && i < HPAGE_PMD_NR; i++) {
/* Cut short if the page is unmapped */
if (page_count(page) == 1)
return;
ret = try_to_unmap(page + i, ttu_flags);
}
VM_BUG_ON_PAGE(ret, page + i - 1);
ret = try_to_unmap(page, ttu_flags);
VM_BUG_ON_PAGE(ret, page);
}
static void unfreeze_page(struct page *page)
......
......@@ -607,8 +607,7 @@ void try_to_unmap_flush_dirty(void)
try_to_unmap_flush();
}
static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
struct page *page, bool writable)
static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
{
struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
......@@ -643,8 +642,7 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
return should_defer;
}
#else
static void set_tlb_ubc_flush_pending(struct mm_struct *mm,
struct page *page, bool writable)
static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
{
}
......@@ -1459,29 +1457,32 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
unsigned long address, void *arg)
{
struct mm_struct *mm = vma->vm_mm;
pte_t *pte;
struct page_vma_mapped_walk pvmw = {
.page = page,
.vma = vma,
.address = address,
};
pte_t pteval;
spinlock_t *ptl;
struct page *subpage;
int ret = SWAP_AGAIN;
struct rmap_private *rp = arg;
enum ttu_flags flags = rp->flags;
/* munlock has nothing to gain from examining un-locked vmas */
if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
goto out;
return SWAP_AGAIN;
if (flags & TTU_SPLIT_HUGE_PMD) {
split_huge_pmd_address(vma, address,
flags & TTU_MIGRATION, page);
/* check if we have anything to do after split */
if (page_mapcount(page) == 0)
goto out;
}
pte = page_check_address(page, mm, address, &ptl,
PageTransCompound(page));
if (!pte)
goto out;
while (page_vma_mapped_walk(&pvmw)) {
subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
address = pvmw.address;
/* Unexpected PMD-mapped THP? */
VM_BUG_ON_PAGE(!pvmw.pte, page);
/*
* If the page is mlock()d, we cannot swap it out.
......@@ -1499,36 +1500,41 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
mlock_vma_page(page);
}
ret = SWAP_MLOCK;
goto out_unmap;
page_vma_mapped_walk_done(&pvmw);
break;
}
if (flags & TTU_MUNLOCK)
goto out_unmap;
continue;
}
if (!(flags & TTU_IGNORE_ACCESS)) {
if (ptep_clear_flush_young_notify(vma, address, pte)) {
if (ptep_clear_flush_young_notify(vma, address,
pvmw.pte)) {
ret = SWAP_FAIL;
goto out_unmap;
page_vma_mapped_walk_done(&pvmw);
break;
}
}
/* Nuke the page table entry. */
flush_cache_page(vma, address, page_to_pfn(page));
flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
if (should_defer_flush(mm, flags)) {
/*
* We clear the PTE but do not flush so potentially a remote
* CPU could still be writing to the page. If the entry was
* previously clean then the architecture must guarantee that
* a clear->dirty transition on a cached TLB entry is written
* through and traps if the PTE is unmapped.
* We clear the PTE but do not flush so potentially
* a remote CPU could still be writing to the page.
* If the entry was previously clean then the
* architecture must guarantee that a clear->dirty
* transition on a cached TLB entry is written through
* and traps if the PTE is unmapped.
*/
pteval = ptep_get_and_clear(mm, address, pte);
pteval = ptep_get_and_clear(mm, address, pvmw.pte);
set_tlb_ubc_flush_pending(mm, page, pte_dirty(pteval));
set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
} else {
pteval = ptep_clear_flush(vma, address, pte);
pteval = ptep_clear_flush(vma, address, pvmw.pte);
}
/* Move the dirty bit to the physical page now the pte is gone. */
/* Move the dirty bit to the page. Now the pte is gone. */
if (pte_dirty(pteval))
set_page_dirty(page);
......@@ -1537,12 +1543,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
if (PageHuge(page)) {
hugetlb_count_sub(1 << compound_order(page), mm);
int nr = 1 << compound_order(page);
hugetlb_count_sub(nr, mm);
} else {
dec_mm_counter(mm, mm_counter(page));
}
set_pte_at(mm, address, pte,
swp_entry_to_pte(make_hwpoison_entry(page)));
pteval = swp_entry_to_pte(make_hwpoison_entry(subpage));
set_pte_at(mm, address, pvmw.pte, pteval);
} else if (pte_unused(pteval)) {
/*
* The guest indicated that the page content is of no
......@@ -1550,7 +1558,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* will take care of the rest.
*/
dec_mm_counter(mm, mm_counter(page));
} else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) {
} else if (IS_ENABLED(CONFIG_MIGRATION) &&
(flags & TTU_MIGRATION)) {
swp_entry_t entry;
pte_t swp_pte;
/*
......@@ -1558,13 +1567,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* pte. do_swap_page() will wait until the migration
* pte is removed and then restart fault handling.
*/
entry = make_migration_entry(page, pte_write(pteval));
entry = make_migration_entry(subpage,
pte_write(pteval));
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
set_pte_at(mm, address, pte, swp_pte);
set_pte_at(mm, address, pvmw.pte, swp_pte);
} else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(page) };
swp_entry_t entry = { .val = page_private(subpage) };
pte_t swp_pte;
/*
* Store the swap location in the pte.
......@@ -1580,9 +1590,10 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
}
if (swap_duplicate(entry) < 0) {
set_pte_at(mm, address, pte, pteval);
set_pte_at(mm, address, pvmw.pte, pteval);
ret = SWAP_FAIL;
goto out_unmap;
page_vma_mapped_walk_done(&pvmw);
break;
}
if (list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
......@@ -1595,19 +1606,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
swp_pte = swp_entry_to_pte(entry);
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
set_pte_at(mm, address, pte, swp_pte);
set_pte_at(mm, address, pvmw.pte, swp_pte);
} else
dec_mm_counter(mm, mm_counter_file(page));
discard:
page_remove_rmap(page, PageHuge(page));
page_remove_rmap(subpage, PageHuge(page));
put_page(page);
out_unmap:
pte_unmap_unlock(pte, ptl);
if (ret != SWAP_FAIL && ret != SWAP_MLOCK && !(flags & TTU_MUNLOCK))
mmu_notifier_invalidate_page(mm, address);
out:
}
return ret;
}
......@@ -1632,7 +1638,7 @@ static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg)
static int page_mapcount_is_zero(struct page *page)
{
return !page_mapcount(page);
return !total_mapcount(page);
}
/**
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment