The patch titled
Subject: mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY cleared
has been added to the -mm tree. Its filename is
mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Peter Feiner <pfeiner@xxxxxxxxxx>
Subject: mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY cleared
For VMAs that don't want write notifications, PTEs created for read faults
have their write bit set. If the read fault happens after VM_SOFTDIRTY is
cleared, then the PTE's softdirty bit will remain clear after subsequent
writes.
Here's a simple code snippet to demonstrate the bug:
char* m = mmap(NULL, getpagesize(), PROT_READ | PROT_WRITE,
MAP_ANONYMOUS | MAP_SHARED, -1, 0);
system("echo 4 > /proc/$PPID/clear_refs"); /* clear VM_SOFTDIRTY */
assert(*m == '\0'); /* new PTE allows write access */
assert(!soft_dirty(x));
*m = 'x'; /* should dirty the page */
assert(soft_dirty(x)); /* fails */
With this patch, write notifications are enabled when VM_SOFTDIRTY is
cleared. Furthermore, to avoid unnecessary faults, write notifications
are disabled when VM_SOFTDIRTY is set.
As a side effect of enabling and disabling write notifications with care,
this patch fixes a bug in mprotect where vm_page_prot bits set by drivers
were zapped on mprotect. An analogous bug was fixed in mmap by
c9d0bf241451a3ab7d ("mm: uncached vma support with writenotify").
Signed-off-by: Peter Feiner <pfeiner@xxxxxxxxxx>
Reported-by: Peter Feiner <pfeiner@xxxxxxxxxx>
Suggested-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Cyrill Gorcunov <gorcunov@xxxxxxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
Cc: Jamie Liu <jamieliu@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/proc/task_mmu.c | 19 +++++++++----
include/asm-generic/pgtable.h | 12 ++++++++
include/linux/mm.h | 5 +++
mm/memory.c | 3 +-
mm/mmap.c | 45 +++++++++++++++++++-------------
mm/mprotect.c | 20 +++-----------
6 files changed, 66 insertions(+), 38 deletions(-)
diff -puN fs/proc/task_mmu.c~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared fs/proc/task_mmu.c
--- a/fs/proc/task_mmu.c~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared
+++ a/fs/proc/task_mmu.c
@@ -828,8 +828,21 @@ static ssize_t clear_refs_write(struct f
.private = &cp,
};
down_read(&mm->mmap_sem);
- if (type == CLEAR_REFS_SOFT_DIRTY)
+ if (type == CLEAR_REFS_SOFT_DIRTY) {
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (!(vma->vm_flags & VM_SOFTDIRTY))
+ continue;
+ up_read(&mm->mmap_sem);
+ down_write(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+ vma_set_page_prot(vma);
+ }
+ downgrade_write(&mm->mmap_sem);
+ break;
+ }
mmu_notifier_invalidate_range_start(mm, 0, -1);
+ }
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cp.vma = vma;
if (is_vm_hugetlb_page(vma))
@@ -849,10 +862,6 @@ static ssize_t clear_refs_write(struct f
continue;
if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
continue;
- if (type == CLEAR_REFS_SOFT_DIRTY) {
- if (vma->vm_flags & VM_SOFTDIRTY)
- vma->vm_flags &= ~VM_SOFTDIRTY;
- }
walk_page_range(vma->vm_start, vma->vm_end,
&clear_refs_walk);
}
diff -puN include/asm-generic/pgtable.h~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared include/asm-generic/pgtable.h
--- a/include/asm-generic/pgtable.h~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared
+++ a/include/asm-generic/pgtable.h
@@ -249,6 +249,18 @@ static inline int pmd_same(pmd_t pmd_a,
#define pgprot_writecombine pgprot_noncached
#endif
+#ifndef pgprot_modify
+#define pgprot_modify pgprot_modify
+static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+{
+ if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
+ newprot = pgprot_noncached(newprot);
+ if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
+ newprot = pgprot_writecombine(newprot);
+ return newprot;
+}
+#endif
+
/*
* When walking page tables, get the address of the next boundary,
* or the end address of the range if that comes earlier. Although no
diff -puN include/linux/mm.h~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared include/linux/mm.h
--- a/include/linux/mm.h~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared
+++ a/include/linux/mm.h
@@ -1964,11 +1964,16 @@ static inline struct vm_area_struct *fin
#ifdef CONFIG_MMU
pgprot_t vm_get_page_prot(unsigned long vm_flags);
+void vma_set_page_prot(struct vm_area_struct *vma);
#else
static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
return __pgprot(0);
}
+static inline void vma_set_page_prot(struct vm_area_struct *vma)
+{
+ vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+}
#endif
#ifdef CONFIG_NUMA_BALANCING
diff -puN mm/memory.c~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared mm/memory.c
--- a/mm/memory.c~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared
+++ a/mm/memory.c
@@ -2051,7 +2051,8 @@ static int do_wp_page(struct mm_struct *
old_page = vm_normal_page(vma, address, orig_pte);
if (!old_page) {
/*
- * VM_MIXEDMAP !pfn_valid() case
+ * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
+ * VM_PFNMAP VMA.
*
* We should not cow pages in a shared writeable mapping.
* Just mark the pages writable as we can't do any dirty
diff -puN mm/mmap.c~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared mm/mmap.c
--- a/mm/mmap.c~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared
+++ a/mm/mmap.c
@@ -89,6 +89,25 @@ pgprot_t vm_get_page_prot(unsigned long
}
EXPORT_SYMBOL(vm_get_page_prot);
+static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
+{
+ return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
+}
+
+/* Update vma->vm_page_prot to reflect vma->vm_flags. */
+void vma_set_page_prot(struct vm_area_struct *vma)
+{
+ unsigned long vm_flags = vma->vm_flags;
+
+ vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
+ if (vma_wants_writenotify(vma)) {
+ vm_flags &= ~VM_SHARED;
+ vma->vm_page_prot = vm_pgprot_modify(vma->vm_page_prot,
+ vm_flags);
+ }
+}
+
+
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio __read_mostly = 50; /* default is 50% */
unsigned long sysctl_overcommit_kbytes __read_mostly;
@@ -1474,11 +1493,16 @@ int vma_wants_writenotify(struct vm_area
if (vma->vm_ops && vma->vm_ops->page_mkwrite)
return 1;
- /* The open routine did something to the protections already? */
+ /* The open routine did something to the protections that pgprot_modify
+ * won't preserve? */
if (pgprot_val(vma->vm_page_prot) !=
- pgprot_val(vm_get_page_prot(vm_flags)))
+ pgprot_val(vm_pgprot_modify(vma->vm_page_prot, vm_flags)))
return 0;
+ /* Do we need to track softdirty? */
+ if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY))
+ return 1;
+
/* Specialty mapping? */
if (vm_flags & VM_PFNMAP)
return 0;
@@ -1614,21 +1638,6 @@ munmap_back:
goto free_vma;
}
- if (vma_wants_writenotify(vma)) {
- pgprot_t pprot = vma->vm_page_prot;
-
- /* Can vma->vm_page_prot have changed??
- *
- * Answer: Yes, drivers may have changed it in their
- * f_op->mmap method.
- *
- * Ensures that vmas marked as uncached stay that way.
- */
- vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
- if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- }
-
vma_link(mm, vma, prev, rb_link, rb_parent);
/* Once vma denies write, undo our temporary denial count */
if (file) {
@@ -1662,6 +1671,8 @@ out:
*/
vma->vm_flags |= VM_SOFTDIRTY;
+ vma_set_page_prot(vma);
+
return addr;
unmap_and_free_vma:
diff -puN mm/mprotect.c~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared mm/mprotect.c
--- a/mm/mprotect.c~mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared
+++ a/mm/mprotect.c
@@ -29,13 +29,6 @@
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
-#ifndef pgprot_modify
-static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
-{
- return newprot;
-}
-#endif
-
/*
* For a prot_numa update we only hold mmap_sem for read so there is a
* potential race with faulting where a pmd was temporarily none. This
@@ -93,7 +86,9 @@ static unsigned long change_pte_range(st
* Avoid taking write faults for pages we
* know to be dirty.
*/
- if (dirty_accountable && pte_dirty(ptent))
+ if (dirty_accountable && pte_dirty(ptent) &&
+ (pte_soft_dirty(ptent) ||
+ !(vma->vm_flags & VM_SOFTDIRTY)))
ptent = pte_mkwrite(ptent);
ptep_modify_prot_commit(mm, addr, pte, ptent);
updated = true;
@@ -320,13 +315,8 @@ success:
* held in write mode.
*/
vma->vm_flags = newflags;
- vma->vm_page_prot = pgprot_modify(vma->vm_page_prot,
- vm_get_page_prot(newflags));
-
- if (vma_wants_writenotify(vma)) {
- vma->vm_page_prot = vm_get_page_prot(newflags & ~VM_SHARED);
- dirty_accountable = 1;
- }
+ dirty_accountable = vma_wants_writenotify(vma);
+ vma_set_page_prot(vma);
change_protection(vma, start, end, vma->vm_page_prot,
dirty_accountable, 0);
_
Patches currently in -mm which might be from pfeiner@xxxxxxxxxx are
mm-softdirty-addresses-before-vmas-in-pte-holes-arent-softdirty.patch
mm-softdirty-enable-write-notifications-on-vmas-after-vm_softdirty-cleared.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
