--- /dev/null
+From 81d0fa623c5b8dbd5279d9713094b0f9b0a00fb4 Mon Sep 17 00:00:00 2001
+From: Peter Feiner <pfeiner@google.com>
+Date: Thu, 9 Oct 2014 15:28:32 -0700
+Subject: mm: softdirty: unmapped addresses between VMAs are clean
+
+From: Peter Feiner <pfeiner@google.com>
+
+commit 81d0fa623c5b8dbd5279d9713094b0f9b0a00fb4 upstream.
+
+If a /proc/pid/pagemap read spans a [VMA, an unmapped region, then a
+VM_SOFTDIRTY VMA], the virtual pages in the unmapped region are reported
+as softdirty. Here's a program to demonstrate the bug:
+
+int main() {
+ const uint64_t PAGEMAP_SOFTDIRTY = 1ul << 55;
+ uint64_t pme[3];
+ int fd = open("/proc/self/pagemap", O_RDONLY);;
+ char *m = mmap(NULL, 3 * getpagesize(), PROT_READ,
+ MAP_ANONYMOUS | MAP_SHARED, -1, 0);
+ munmap(m + getpagesize(), getpagesize());
+ pread(fd, pme, 24, (unsigned long) m / getpagesize() * 8);
+ assert(pme[0] & PAGEMAP_SOFTDIRTY); /* passes */
+ assert(!(pme[1] & PAGEMAP_SOFTDIRTY)); /* fails */
+ assert(pme[2] & PAGEMAP_SOFTDIRTY); /* passes */
+ return 0;
+}
+
+(Note that all pages in new VMAs are softdirty until cleared).
+
+Tested:
+ Used the program given above. I'm going to include this code in
+ a selftest in the future.
+
+[n-horiguchi@ah.jp.nec.com: prevent pagemap_pte_range() from overrunning]
+Signed-off-by: Peter Feiner <pfeiner@google.com>
+Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
+Cc: Cyrill Gorcunov <gorcunov@openvz.org>
+Cc: Pavel Emelyanov <xemul@parallels.com>
+Cc: Jamie Liu <jamieliu@google.com>
+Cc: Hugh Dickins <hughd@google.com>
+Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+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>
+
+---
+ fs/proc/task_mmu.c | 59 +++++++++++++++++++++++++++++++++++------------------
+ 1 file changed, 39 insertions(+), 20 deletions(-)
+
+--- a/fs/proc/task_mmu.c
++++ b/fs/proc/task_mmu.c
+@@ -995,7 +995,6 @@ static int pagemap_pte_range(pmd_t *pmd,
+ spinlock_t *ptl;
+ pte_t *pte;
+ int err = 0;
+- pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+
+ /* find the first VMA at or above 'addr' */
+ vma = find_vma(walk->mm, addr);
+@@ -1009,6 +1008,7 @@ static int pagemap_pte_range(pmd_t *pmd,
+
+ for (; addr != end; addr += PAGE_SIZE) {
+ unsigned long offset;
++ pagemap_entry_t pme;
+
+ offset = (addr & ~PAGEMAP_WALK_MASK) >>
+ PAGE_SHIFT;
+@@ -1023,32 +1023,51 @@ static int pagemap_pte_range(pmd_t *pmd,
+
+ if (pmd_trans_unstable(pmd))
+ return 0;
+- for (; addr != end; addr += PAGE_SIZE) {
+- int flags2;
+
+- /* check to see if we've left 'vma' behind
+- * and need a new, higher one */
+- if (vma && (addr >= vma->vm_end)) {
+- vma = find_vma(walk->mm, addr);
+- if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+- flags2 = __PM_SOFT_DIRTY;
+- else
+- flags2 = 0;
+- pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
++ while (1) {
++ /* End of address space hole, which we mark as non-present. */
++ unsigned long hole_end;
++
++ if (vma)
++ hole_end = min(end, vma->vm_start);
++ else
++ hole_end = end;
++
++ for (; addr < hole_end; addr += PAGE_SIZE) {
++ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
++
++ err = add_to_pagemap(addr, &pme, pm);
++ if (err)
++ return err;
+ }
+
+- /* check that 'vma' actually covers this address,
+- * and that it isn't a huge page vma */
+- if (vma && (vma->vm_start <= addr) &&
+- !is_vm_hugetlb_page(vma)) {
++ if (!vma || vma->vm_start >= end)
++ break;
++ /*
++ * We can't possibly be in a hugetlb VMA. In general,
++ * for a mm_walk with a pmd_entry and a hugetlb_entry,
++ * the pmd_entry can only be called on addresses in a
++ * hugetlb if the walk starts in a non-hugetlb VMA and
++ * spans a hugepage VMA. Since pagemap_read walks are
++ * PMD-sized and PMD-aligned, this will never be true.
++ */
++ BUG_ON(is_vm_hugetlb_page(vma));
++
++ /* Addresses in the VMA. */
++ for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
++ pagemap_entry_t pme;
+ pte = pte_offset_map(pmd, addr);
+ pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
+- /* unmap before userspace copy */
+ pte_unmap(pte);
++ err = add_to_pagemap(addr, &pme, pm);
++ if (err)
++ return err;
+ }
+- err = add_to_pagemap(addr, &pme, pm);
+- if (err)
+- return err;
++
++ if (addr == end)
++ break;
++
++ vma = find_vma(walk->mm, addr);
+ }
+
+ cond_resched();
--- /dev/null
+From 05fbf357d94152171bc50f8a369390f1f16efd89 Mon Sep 17 00:00:00 2001
+From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
+Date: Wed, 11 Feb 2015 15:27:31 -0800
+Subject: proc/pagemap: walk page tables under pte lock
+
+From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
+
+commit 05fbf357d94152171bc50f8a369390f1f16efd89 upstream.
+
+Lockless access to pte in pagemap_pte_range() might race with page
+migration and trigger BUG_ON(!PageLocked()) in migration_entry_to_page():
+
+CPU A (pagemap) CPU B (migration)
+ lock_page()
+ try_to_unmap(page, TTU_MIGRATION...)
+ make_migration_entry()
+ set_pte_at()
+<read *pte>
+pte_to_pagemap_entry()
+ remove_migration_ptes()
+ unlock_page()
+ if(is_migration_entry())
+ migration_entry_to_page()
+ BUG_ON(!PageLocked(page))
+
+Also lockless read might be non-atomic if pte is larger than wordsize.
+Other pte walkers (smaps, numa_maps, clear_refs) already lock ptes.
+
+Fixes: 052fb0d635df ("proc: report file/anon bit in /proc/pid/pagemap")
+Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
+Reported-by: Andrey Ryabinin <a.ryabinin@samsung.com>
+Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
+Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
+Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+Cc: <stable@vger.kernel.org> [3.5+]
+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>
+
+---
+ fs/proc/task_mmu.c | 14 +++++++++-----
+ 1 file changed, 9 insertions(+), 5 deletions(-)
+
+--- a/fs/proc/task_mmu.c
++++ b/fs/proc/task_mmu.c
+@@ -993,7 +993,7 @@ static int pagemap_pte_range(pmd_t *pmd,
+ struct vm_area_struct *vma;
+ struct pagemapread *pm = walk->private;
+ spinlock_t *ptl;
+- pte_t *pte;
++ pte_t *pte, *orig_pte;
+ int err = 0;
+
+ /* find the first VMA at or above 'addr' */
+@@ -1054,15 +1054,19 @@ static int pagemap_pte_range(pmd_t *pmd,
+ BUG_ON(is_vm_hugetlb_page(vma));
+
+ /* Addresses in the VMA. */
+- for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
++ orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
++ for (; addr < min(end, vma->vm_end); pte++, addr += PAGE_SIZE) {
+ pagemap_entry_t pme;
+- pte = pte_offset_map(pmd, addr);
++
+ pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
+- pte_unmap(pte);
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+- return err;
++ break;
+ }
++ pte_unmap_unlock(orig_pte, ptl);
++
++ if (err)
++ return err;
+
+ if (addr == end)
+ break;
projects / thirdparty / kernel / stable-queue.git / commitdiff
