Merge branch 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6

* 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6: (21 commits)
  HWPOISON: Enable error_remove_page on btrfs
  HWPOISON: Add simple debugfs interface to inject hwpoison on arbitary PFNs
  HWPOISON: Add madvise() based injector for hardware poisoned pages v4
  HWPOISON: Enable error_remove_page for NFS
  HWPOISON: Enable .remove_error_page for migration aware file systems
  HWPOISON: The high level memory error handler in the VM v7
  HWPOISON: Add PR_MCE_KILL prctl to control early kill behaviour per process
  HWPOISON: shmem: call set_page_dirty() with locked page
  HWPOISON: Define a new error_remove_page address space op for async truncation
  HWPOISON: Add invalidate_inode_page
  HWPOISON: Refactor truncate to allow direct truncating of page v2
  HWPOISON: check and isolate corrupted free pages v2
  HWPOISON: Handle hardware poisoned pages in try_to_unmap
  HWPOISON: Use bitmask/action code for try_to_unmap behaviour
  HWPOISON: x86: Add VM_FAULT_HWPOISON handling to x86 page fault handler v2
  HWPOISON: Add poison check to page fault handling
  HWPOISON: Add basic support for poisoned pages in fault handler v3
  HWPOISON: Add new SIGBUS error codes for hardware poison signals
  HWPOISON: Add support for poison swap entries v2
  HWPOISON: Export some rmap vma locking to outside world
  ...

1 files changed, 38 insertions, 22 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index 720fc03a7bc4..28aafe2b5306 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -36,6 +36,11 @@
  *                 mapping->tree_lock (widely used, in set_page_dirty,
  *                           in arch-dependent flush_dcache_mmap_lock,
  *                           within inode_lock in __sync_single_inode)
+ *
+ * (code doesn't rely on that order so it could be switched around)
+ * ->tasklist_lock
+ *   anon_vma->lock      (memory_failure, collect_procs_anon)
+ *     pte map lock
  */
 
 #include <linux/mm.h>
@@ -191,7 +196,7 @@ void __init anon_vma_init(void)
  * Getting a lock on a stable anon_vma from a page off the LRU is
  * tricky: page_lock_anon_vma rely on RCU to guard against the races.
  */
-static struct anon_vma *page_lock_anon_vma(struct page *page)
+struct anon_vma *page_lock_anon_vma(struct page *page)
 {
         struct anon_vma *anon_vma;
         unsigned long anon_mapping;
@@ -211,7 +216,7 @@ out:
         return NULL;
 }
 
-static void page_unlock_anon_vma(struct anon_vma *anon_vma)
+void page_unlock_anon_vma(struct anon_vma *anon_vma)
 {
         spin_unlock(&anon_vma->lock);
         rcu_read_unlock();
@@ -311,7 +316,7 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm,
  * if the page is not mapped into the page tables of this VMA.  Only
  * valid for normal file or anonymous VMAs.
  */
-static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
+int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
 {
         unsigned long address;
         pte_t *pte;
@@ -756,7 +761,7 @@ void page_remove_rmap(struct page *page)
  * repeatedly from either try_to_unmap_anon or try_to_unmap_file.
  */
 static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
-                                int migration)
+                                enum ttu_flags flags)
 {
         struct mm_struct *mm = vma->vm_mm;
         unsigned long address;
@@ -778,11 +783,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
          * If it's recently referenced (perhaps page_referenced
          * skipped over this mm) then we should reactivate it.
          */
-        if (!migration) {
+        if (!(flags & TTU_IGNORE_MLOCK)) {
                 if (vma->vm_flags & VM_LOCKED) {
                         ret = SWAP_MLOCK;
                         goto out_unmap;
                 }
+        }
+        if (!(flags & TTU_IGNORE_ACCESS)) {
                 if (ptep_clear_flush_young_notify(vma, address, pte)) {
                         ret = SWAP_FAIL;
                         goto out_unmap;
@@ -800,7 +807,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
         /* Update high watermark before we lower rss */
         update_hiwater_rss(mm);
 
-        if (PageAnon(page)) {
+        if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
+                if (PageAnon(page))
+                        dec_mm_counter(mm, anon_rss);
+                else
+                        dec_mm_counter(mm, file_rss);
+                set_pte_at(mm, address, pte,
+                                swp_entry_to_pte(make_hwpoison_entry(page)));
+        } else if (PageAnon(page)) {
                 swp_entry_t entry = { .val = page_private(page) };
 
                 if (PageSwapCache(page)) {
@@ -822,12 +836,12 @@ 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.
                          */
-                        BUG_ON(!migration);
+                        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));
                 BUG_ON(pte_file(*pte));
-        } else if (PAGE_MIGRATION && migration) {
+        } else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) {
                 /* Establish migration entry for a file page */
                 swp_entry_t entry;
                 entry = make_migration_entry(page, pte_write(pteval));
@@ -996,12 +1010,13 @@ static int try_to_mlock_page(struct page *page, struct vm_area_struct *vma)
  * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
  * 'LOCKED.
  */
-static int try_to_unmap_anon(struct page *page, int unlock, int migration)
+static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
 {
         struct anon_vma *anon_vma;
         struct vm_area_struct *vma;
         unsigned int mlocked = 0;
         int ret = SWAP_AGAIN;
+        int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
 
         if (MLOCK_PAGES && unlikely(unlock))
                 ret = SWAP_SUCCESS;     /* default for try_to_munlock() */
@@ -1017,7 +1032,7 @@ static int try_to_unmap_anon(struct page *page, int unlock, int migration)
                                 continue;  /* must visit all unlocked vmas */
                         ret = SWAP_MLOCK;  /* saw at least one mlocked vma */
                 } else {
-                        ret = try_to_unmap_one(page, vma, migration);
+                        ret = try_to_unmap_one(page, vma, flags);
                         if (ret == SWAP_FAIL || !page_mapped(page))
                                 break;
                 }
@@ -1041,8 +1056,7 @@ static int try_to_unmap_anon(struct page *page, int unlock, int migration)
 /**
  * try_to_unmap_file - unmap/unlock file page using the object-based rmap method
  * @page: the page to unmap/unlock
- * @unlock:  request for unlock rather than unmap [unlikely]
- * @migration:  unmapping for migration - ignored if @unlock
+ * @flags: action and flags
  *
  * Find all the mappings of a page using the mapping pointer and the vma chains
  * contained in the address_space struct it points to.
@@ -1054,7 +1068,7 @@ static int try_to_unmap_anon(struct page *page, int unlock, int migration)
  * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
  * 'LOCKED.
  */
-static int try_to_unmap_file(struct page *page, int unlock, int migration)
+static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
 {
         struct address_space *mapping = page->mapping;
         pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
@@ -1066,6 +1080,7 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
         unsigned long max_nl_size = 0;
         unsigned int mapcount;
         unsigned int mlocked = 0;
+        int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
 
         if (MLOCK_PAGES && unlikely(unlock))
                 ret = SWAP_SUCCESS;     /* default for try_to_munlock() */
@@ -1078,7 +1093,7 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
                                 continue;       /* must visit all vmas */
                         ret = SWAP_MLOCK;
                 } else {
-                        ret = try_to_unmap_one(page, vma, migration);
+                        ret = try_to_unmap_one(page, vma, flags);
                         if (ret == SWAP_FAIL || !page_mapped(page))
                                 goto out;
                 }
@@ -1103,7 +1118,8 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
                         ret = SWAP_MLOCK;       /* leave mlocked == 0 */
                         goto out;               /* no need to look further */
                 }
-                if (!MLOCK_PAGES && !migration && (vma->vm_flags & VM_LOCKED))
+                if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
+                        (vma->vm_flags & VM_LOCKED))
                         continue;
                 cursor = (unsigned long) vma->vm_private_data;
                 if (cursor > max_nl_cursor)
@@ -1137,7 +1153,7 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
         do {
                 list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
                                                 shared.vm_set.list) {
-                        if (!MLOCK_PAGES && !migration &&
+                        if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
                             (vma->vm_flags & VM_LOCKED))
                                 continue;
                         cursor = (unsigned long) vma->vm_private_data;
@@ -1177,7 +1193,7 @@ out:
 /**
  * try_to_unmap - try to remove all page table mappings to a page
  * @page: the page to get unmapped
- * @migration: migration flag
+ * @flags: action and flags
  *
  * Tries to remove all the page table entries which are mapping this
  * page, used in the pageout path.  Caller must hold the page lock.
@@ -1188,16 +1204,16 @@ out:
  * SWAP_FAIL    - the page is unswappable
  * SWAP_MLOCK   - page is mlocked.
  */
-int try_to_unmap(struct page *page, int migration)
+int try_to_unmap(struct page *page, enum ttu_flags flags)
 {
         int ret;
 
         BUG_ON(!PageLocked(page));
 
         if (PageAnon(page))
-                ret = try_to_unmap_anon(page, 0, migration);
+                ret = try_to_unmap_anon(page, flags);
         else
-                ret = try_to_unmap_file(page, 0, migration);
+                ret = try_to_unmap_file(page, flags);
         if (ret != SWAP_MLOCK && !page_mapped(page))
                 ret = SWAP_SUCCESS;
         return ret;
@@ -1222,8 +1238,8 @@ int try_to_munlock(struct page *page)
         VM_BUG_ON(!PageLocked(page) || PageLRU(page));
 
         if (PageAnon(page))
-                return try_to_unmap_anon(page, 1, 0);
+                return try_to_unmap_anon(page, TTU_MUNLOCK);
         else
-                return try_to_unmap_file(page, 1, 0);
+                return try_to_unmap_file(page, TTU_MUNLOCK);
 }