mm: soft-dirty bits for user memory changes tracking

The soft-dirty is a bit on a PTE which helps to track which pages a task
writes to.  In order to do this tracking one should

  1. Clear soft-dirty bits from PTEs ("echo 4 > /proc/PID/clear_refs)
  2. Wait some time.
  3. Read soft-dirty bits (55'th in /proc/PID/pagemap2 entries)

To do this tracking, the writable bit is cleared from PTEs when the
soft-dirty bit is.  Thus, after this, when the task tries to modify a
page at some virtual address the #PF occurs and the kernel sets the
soft-dirty bit on the respective PTE.

Note, that although all the task's address space is marked as r/o after
the soft-dirty bits clear, the #PF-s that occur after that are processed
fast.  This is so, since the pages are still mapped to physical memory,
and thus all the kernel does is finds this fact out and puts back
writable, dirty and soft-dirty bits on the PTE.

Another thing to note, is that when mremap moves PTEs they are marked
with soft-dirty as well, since from the user perspective mremap modifies
the virtual memory at mremap's new address.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Glauber Costa <glommer@parallels.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 42 insertions, 5 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 39d641292579..a18e065c1c3e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -11,6 +11,7 @@
 #include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
@@ -692,13 +693,32 @@ enum clear_refs_types {
         CLEAR_REFS_ALL = 1,
         CLEAR_REFS_ANON,
         CLEAR_REFS_MAPPED,
+        CLEAR_REFS_SOFT_DIRTY,
         CLEAR_REFS_LAST,
 };
 
 struct clear_refs_private {
         struct vm_area_struct *vma;
+        enum clear_refs_types type;
 };
 
+static inline void clear_soft_dirty(struct vm_area_struct *vma,
+                unsigned long addr, pte_t *pte)
+{
+#ifdef CONFIG_MEM_SOFT_DIRTY
+        /*
+         * The soft-dirty tracker uses #PF-s to catch writes
+         * to pages, so write-protect the pte as well. See the
+         * Documentation/vm/soft-dirty.txt for full description
+         * of how soft-dirty works.
+         */
+        pte_t ptent = *pte;
+        ptent = pte_wrprotect(ptent);
+        ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+        set_pte_at(vma->vm_mm, addr, pte, ptent);
+#endif
+}
+
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
                                 unsigned long end, struct mm_walk *walk)
 {
@@ -718,6 +738,11 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
                 if (!pte_present(ptent))
                         continue;
 
+                if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+                        clear_soft_dirty(vma, addr, pte);
+                        continue;
+                }
+
                 page = vm_normal_page(vma, addr, ptent);
                 if (!page)
                         continue;
@@ -759,6 +784,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
         mm = get_task_mm(task);
         if (mm) {
                 struct clear_refs_private cp = {
+                        .type = type,
                 };
                 struct mm_walk clear_refs_walk = {
                         .pmd_entry = clear_refs_pte_range,
@@ -766,6 +792,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
                         .private = &cp,
                 };
                 down_read(&mm->mmap_sem);
+                if (type == CLEAR_REFS_SOFT_DIRTY)
+                        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))
@@ -786,6 +814,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
                         walk_page_range(vma->vm_start, vma->vm_end,
                                         &clear_refs_walk);
                 }
+                if (type == CLEAR_REFS_SOFT_DIRTY)
+                        mmu_notifier_invalidate_range_end(mm, 0, -1);
                 flush_tlb_mm(mm);
                 up_read(&mm->mmap_sem);
                 mmput(mm);
@@ -827,6 +857,7 @@ struct pagemapread {
 /* in "new" pagemap pshift bits are occupied with more status bits */
 #define PM_STATUS2(v2, x)   (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))
 
+#define __PM_SOFT_DIRTY      (1LL)
 #define PM_PRESENT          PM_STATUS(4LL)
 #define PM_SWAP             PM_STATUS(2LL)
 #define PM_FILE             PM_STATUS(1LL)
@@ -868,6 +899,7 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 {
         u64 frame, flags;
         struct page *page = NULL;
+        int flags2 = 0;
 
         if (pte_present(pte)) {
                 frame = pte_pfn(pte);
@@ -888,13 +920,15 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 
         if (page && !PageAnon(page))
                 flags |= PM_FILE;
+        if (pte_soft_dirty(pte))
+                flags2 |= __PM_SOFT_DIRTY;
 
-        *pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, 0) | flags);
+        *pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
-                                        pmd_t pmd, int offset)
+                pmd_t pmd, int offset, int pmd_flags2)
 {
         /*
          * Currently pmd for thp is always present because thp can not be
@@ -903,13 +937,13 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *p
          */
         if (pmd_present(pmd))
                 *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
-                                | PM_STATUS2(pm->v2, 0) | PM_PRESENT);
+                                | PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
         else
                 *pme = make_pme(PM_NOT_PRESENT(pm->v2));
 }
 #else
 static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
-                                                pmd_t pmd, int offset)
+                pmd_t pmd, int offset, int pmd_flags2)
 {
 }
 #endif
@@ -926,12 +960,15 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
         /* find the first VMA at or above 'addr' */
         vma = find_vma(walk->mm, addr);
         if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
+                int pmd_flags2;
+
+                pmd_flags2 = (pmd_soft_dirty(*pmd) ? __PM_SOFT_DIRTY : 0);
                 for (; addr != end; addr += PAGE_SIZE) {
                         unsigned long offset;
 
                         offset = (addr & ~PAGEMAP_WALK_MASK) >>
                                         PAGE_SHIFT;
-                        thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset);
+                        thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2);
                         err = add_to_pagemap(addr, &pme, pm);
                         if (err)
                                 break;