mm: save soft-dirty bits on swapped pages
Andy Lutomirski reported that if a page with _PAGE_SOFT_DIRTY bit set
get swapped out, the bit is getting lost and no longer available when
pte read back.
To resolve this we introduce _PTE_SWP_SOFT_DIRTY bit which is saved in
pte entry for the page being swapped out. When such page is to be read
back from a swap cache we check for bit presence and if it's there we
clear it and restore the former _PAGE_SOFT_DIRTY bit back.
One of the problem was to find a place in pte entry where we can save
the _PTE_SWP_SOFT_DIRTY bit while page is in swap. The _PAGE_PSE was
chosen for that, it doesn't intersect with swap entry format stored in
pte.
Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 7dc305a..bd0518a 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -314,6 +314,21 @@
return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
}
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+ return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+ return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+ return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
/*
* Mask out unsupported bits in a present pgprot. Non-present pgprots
* can use those bits for other purposes, so leave them be.
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index c98ac63..5e8442f 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -67,6 +67,19 @@
#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 0))
#endif
+/*
+ * Tracking soft dirty bit when a page goes to a swap is tricky.
+ * We need a bit which can be stored in pte _and_ not conflict
+ * with swap entry format. On x86 bits 6 and 7 are *not* involved
+ * into swap entry computation, but bit 6 is used for nonlinear
+ * file mapping, so we borrow bit 7 for soft dirty tracking.
+ */
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SWP_SOFT_DIRTY _PAGE_PSE
+#else
+#define _PAGE_SWP_SOFT_DIRTY (_AT(pteval_t, 0))
+#endif
+
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX)
#else
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index dbf61f6..e2d9bdc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -730,8 +730,14 @@
* of how soft-dirty works.
*/
pte_t ptent = *pte;
- ptent = pte_wrprotect(ptent);
- ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+
+ if (pte_present(ptent)) {
+ ptent = pte_wrprotect(ptent);
+ ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+ } else if (is_swap_pte(ptent)) {
+ ptent = pte_swp_clear_soft_dirty(ptent);
+ }
+
set_pte_at(vma->vm_mm, addr, pte, ptent);
#endif
}
@@ -752,14 +758,15 @@
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
- if (!pte_present(ptent))
- continue;
if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
clear_soft_dirty(vma, addr, pte);
continue;
}
+ if (!pte_present(ptent))
+ continue;
+
page = vm_normal_page(vma, addr, ptent);
if (!page)
continue;
@@ -930,8 +937,10 @@
flags = PM_PRESENT;
page = vm_normal_page(vma, addr, pte);
} else if (is_swap_pte(pte)) {
- swp_entry_t entry = pte_to_swp_entry(pte);
-
+ swp_entry_t entry;
+ if (pte_swp_soft_dirty(pte))
+ flags2 |= __PM_SOFT_DIRTY;
+ entry = pte_to_swp_entry(pte);
frame = swp_type(entry) |
(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
flags = PM_SWAP;
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 2f47ade..2a7e0d1 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -417,6 +417,21 @@
{
return pmd;
}
+
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+ return pte;
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+ return 0;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+ return pte;
+}
#endif
#ifndef __HAVE_PFNMAP_TRACKING
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index c5fd30d..8d4fa82 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -67,6 +67,8 @@
swp_entry_t arch_entry;
BUG_ON(pte_file(pte));
+ if (pte_swp_soft_dirty(pte))
+ pte = pte_swp_clear_soft_dirty(pte);
arch_entry = __pte_to_swp_entry(pte);
return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
}
diff --git a/mm/memory.c b/mm/memory.c
index 1ce2e2a..e98ecad2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3115,6 +3115,8 @@
exclusive = 1;
}
flush_icache_page(vma, page);
+ if (pte_swp_soft_dirty(orig_pte))
+ pte = pte_mksoft_dirty(pte);
set_pte_at(mm, address, page_table, pte);
if (page == swapcache)
do_page_add_anon_rmap(page, vma, address, exclusive);
diff --git a/mm/rmap.c b/mm/rmap.c
index cd356df..83325b8 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1236,6 +1236,7 @@
swp_entry_to_pte(make_hwpoison_entry(page)));
} else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(page) };
+ pte_t swp_pte;
if (PageSwapCache(page)) {
/*
@@ -1264,7 +1265,10 @@
BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
entry = make_migration_entry(page, pte_write(pteval));
}
- set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
+ 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);
BUG_ON(pte_file(*pte));
} else if (IS_ENABLED(CONFIG_MIGRATION) &&
(TTU_ACTION(flags) == TTU_MIGRATION)) {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 36af6ee..6cf2e60 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -866,6 +866,21 @@
}
#endif /* CONFIG_HIBERNATION */
+static inline int maybe_same_pte(pte_t pte, pte_t swp_pte)
+{
+#ifdef CONFIG_MEM_SOFT_DIRTY
+ /*
+ * When pte keeps soft dirty bit the pte generated
+ * from swap entry does not has it, still it's same
+ * pte from logical point of view.
+ */
+ pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte);
+ return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty);
+#else
+ return pte_same(pte, swp_pte);
+#endif
+}
+
/*
* No need to decide whether this PTE shares the swap entry with others,
* just let do_wp_page work it out if a write is requested later - to
@@ -892,7 +907,7 @@
}
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
- if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
+ if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
mem_cgroup_cancel_charge_swapin(memcg);
ret = 0;
goto out;
@@ -947,7 +962,7 @@
* swapoff spends a _lot_ of time in this loop!
* Test inline before going to call unuse_pte.
*/
- if (unlikely(pte_same(*pte, swp_pte))) {
+ if (unlikely(maybe_same_pte(*pte, swp_pte))) {
pte_unmap(pte);
ret = unuse_pte(vma, pmd, addr, entry, page);
if (ret)