1 files changed, 258 insertions, 86 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6f5f78885ab4..e5a1531f7f4e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -56,6 +56,7 @@
 #include <linux/kfifo.h>
 #include <linux/ratelimit.h>
 #include <linux/page-isolation.h>
+#include <linux/pagewalk.h>
 #include "internal.h"
 #include "ras/ras_event.h"
 
@@ -554,6 +555,148 @@ static void collect_procs(struct page *page, struct list_head *tokill,
 		collect_procs_file(page, tokill, force_early);
 }
 
+struct hwp_walk {
+	struct to_kill tk;
+	unsigned long pfn;
+	int flags;
+};
+
+static void set_to_kill(struct to_kill *tk, unsigned long addr, short shift)
+{
+	tk->addr = addr;
+	tk->size_shift = shift;
+}
+
+static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift,
+				unsigned long poisoned_pfn, struct to_kill *tk)
+{
+	unsigned long pfn = 0;
+
+	if (pte_present(pte)) {
+		pfn = pte_pfn(pte);
+	} else {
+		swp_entry_t swp = pte_to_swp_entry(pte);
+
+		if (is_hwpoison_entry(swp))
+			pfn = hwpoison_entry_to_pfn(swp);
+	}
+
+	if (!pfn || pfn != poisoned_pfn)
+		return 0;
+
+	set_to_kill(tk, addr, shift);
+	return 1;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr,
+				      struct hwp_walk *hwp)
+{
+	pmd_t pmd = *pmdp;
+	unsigned long pfn;
+	unsigned long hwpoison_vaddr;
+
+	if (!pmd_present(pmd))
+		return 0;
+	pfn = pmd_pfn(pmd);
+	if (pfn <= hwp->pfn && hwp->pfn < pfn + HPAGE_PMD_NR) {
+		hwpoison_vaddr = addr + ((hwp->pfn - pfn) << PAGE_SHIFT);
+		set_to_kill(&hwp->tk, hwpoison_vaddr, PAGE_SHIFT);
+		return 1;
+	}
+	return 0;
+}
+#else
+static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr,
+				      struct hwp_walk *hwp)
+{
+	return 0;
+}
+#endif
+
+static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr,
+			      unsigned long end, struct mm_walk *walk)
+{
+	struct hwp_walk *hwp = (struct hwp_walk *)walk->private;
+	int ret = 0;
+	pte_t *ptep;
+	spinlock_t *ptl;
+
+	ptl = pmd_trans_huge_lock(pmdp, walk->vma);
+	if (ptl) {
+		ret = check_hwpoisoned_pmd_entry(pmdp, addr, hwp);
+		spin_unlock(ptl);
+		goto out;
+	}
+
+	if (pmd_trans_unstable(pmdp))
+		goto out;
+
+	ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp, addr, &ptl);
+	for (; addr != end; ptep++, addr += PAGE_SIZE) {
+		ret = check_hwpoisoned_entry(*ptep, addr, PAGE_SHIFT,
+					     hwp->pfn, &hwp->tk);
+		if (ret == 1)
+			break;
+	}
+	pte_unmap_unlock(ptep - 1, ptl);
+out:
+	cond_resched();
+	return ret;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask,
+			    unsigned long addr, unsigned long end,
+			    struct mm_walk *walk)
+{
+	struct hwp_walk *hwp = (struct hwp_walk *)walk->private;
+	pte_t pte = huge_ptep_get(ptep);
+	struct hstate *h = hstate_vma(walk->vma);
+
+	return check_hwpoisoned_entry(pte, addr, huge_page_shift(h),
+				      hwp->pfn, &hwp->tk);
+}
+#else
+#define hwpoison_hugetlb_range	NULL
+#endif
+
+static struct mm_walk_ops hwp_walk_ops = {
+	.pmd_entry = hwpoison_pte_range,
+	.hugetlb_entry = hwpoison_hugetlb_range,
+};
+
+/*
+ * Sends SIGBUS to the current process with error info.
+ *
+ * This function is intended to handle "Action Required" MCEs on already
+ * hardware poisoned pages. They could happen, for example, when
+ * memory_failure() failed to unmap the error page at the first call, or
+ * when multiple local machine checks happened on different CPUs.
+ *
+ * MCE handler currently has no easy access to the error virtual address,
+ * so this function walks page table to find it. The returned virtual address
+ * is proper in most cases, but it could be wrong when the application
+ * process has multiple entries mapping the error page.
+ */
+static int kill_accessing_process(struct task_struct *p, unsigned long pfn,
+				  int flags)
+{
+	int ret;
+	struct hwp_walk priv = {
+		.pfn = pfn,
+	};
+	priv.tk.tsk = p;
+
+	mmap_read_lock(p->mm);
+	ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwp_walk_ops,
+			      (void *)&priv);
+	if (ret == 1 && priv.tk.addr)
+		kill_proc(&priv.tk, pfn, flags);
+	mmap_read_unlock(p->mm);
+	return ret ? -EFAULT : -EHWPOISON;
+}
+
 static const char *action_name[] = {
 	[MF_IGNORED] = "Ignored",
 	[MF_FAILED] = "Failed",
@@ -974,13 +1117,6 @@ static inline bool HWPoisonHandlable(struct page *page)
 	return PageLRU(page) || __PageMovable(page);
 }
 
-/**
- * __get_hwpoison_page() - Get refcount for memory error handling:
- * @page:	raw error page (hit by memory error)
- *
- * Return: return 0 if failed to grab the refcount, otherwise true (some
- * non-zero value.)
- */
 static int __get_hwpoison_page(struct page *page)
 {
 	struct page *head = compound_head(page);
@@ -1025,15 +1161,6 @@ static int __get_hwpoison_page(struct page *page)
 	return 0;
 }
 
-/*
- * Safely get reference count of an arbitrary page.
- *
- * Returns 0 for a free page, 1 for an in-use page,
- * -EIO for a page-type we cannot handle and -EBUSY if we raced with an
- * allocation.
- * We only incremented refcount in case the page was already in-use and it
- * is a known type we can handle.
- */
 static int get_any_page(struct page *p, unsigned long flags)
 {
 	int ret = 0, pass = 0;
@@ -1043,50 +1170,77 @@ static int get_any_page(struct page *p, unsigned long flags)
 		count_increased = true;
 
 try_again:
-	if (!count_increased && !__get_hwpoison_page(p)) {
-		if (page_count(p)) {
-			/* We raced with an allocation, retry. */
-			if (pass++ < 3)
-				goto try_again;
-			ret = -EBUSY;
-		} else if (!PageHuge(p) && !is_free_buddy_page(p)) {
-			/* We raced with put_page, retry. */
+	if (!count_increased) {
+		ret = __get_hwpoison_page(p);
+		if (!ret) {
+			if (page_count(p)) {
+				/* We raced with an allocation, retry. */
+				if (pass++ < 3)
+					goto try_again;
+				ret = -EBUSY;
+			} else if (!PageHuge(p) && !is_free_buddy_page(p)) {
+				/* We raced with put_page, retry. */
+				if (pass++ < 3)
+					goto try_again;
+				ret = -EIO;
+			}
+			goto out;
+		} else if (ret == -EBUSY) {
+			/* We raced with freeing huge page to buddy, retry. */
 			if (pass++ < 3)
 				goto try_again;
-			ret = -EIO;
+			goto out;
 		}
+	}
+
+	if (PageHuge(p) || HWPoisonHandlable(p)) {
+		ret = 1;
 	} else {
-		if (PageHuge(p) || HWPoisonHandlable(p)) {
-			ret = 1;
-		} else {
-			/*
-			 * A page we cannot handle. Check whether we can turn
-			 * it into something we can handle.
-			 */
-			if (pass++ < 3) {
-				put_page(p);
-				shake_page(p, 1);
-				count_increased = false;
-				goto try_again;
-			}
+		/*
+		 * A page we cannot handle. Check whether we can turn
+		 * it into something we can handle.
+		 */
+		if (pass++ < 3) {
 			put_page(p);
-			ret = -EIO;
+			shake_page(p, 1);
+			count_increased = false;
+			goto try_again;
 		}
+		put_page(p);
+		ret = -EIO;
 	}
-
+out:
 	return ret;
 }
 
-static int get_hwpoison_page(struct page *p, unsigned long flags,
-			     enum mf_flags ctxt)
+/**
+ * get_hwpoison_page() - Get refcount for memory error handling
+ * @p:		Raw error page (hit by memory error)
+ * @flags:	Flags controlling behavior of error handling
+ *
+ * get_hwpoison_page() takes a page refcount of an error page to handle memory
+ * error on it, after checking that the error page is in a well-defined state
+ * (defined as a page-type we can successfully handle the memor error on it,
+ * such as LRU page and hugetlb page).
+ *
+ * Memory error handling could be triggered at any time on any type of page,
+ * so it's prone to race with typical memory management lifecycle (like
+ * allocation and free).  So to avoid such races, get_hwpoison_page() takes
+ * extra care for the error page's state (as done in __get_hwpoison_page()),
+ * and has some retry logic in get_any_page().
+ *
+ * Return: 0 on failure,
+ *         1 on success for in-use pages in a well-defined state,
+ *         -EIO for pages on which we can not handle memory errors,
+ *         -EBUSY when get_hwpoison_page() has raced with page lifecycle
+ *         operations like allocation and free.
+ */
+static int get_hwpoison_page(struct page *p, unsigned long flags)
 {
 	int ret;
 
 	zone_pcp_disable(page_zone(p));
-	if (ctxt == MF_SOFT_OFFLINE)
-		ret = get_any_page(p, flags);
-	else
-		ret = __get_hwpoison_page(p);
+	ret = get_any_page(p, flags);
 	zone_pcp_enable(page_zone(p));
 
 	return ret;
@@ -1267,32 +1421,41 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 	if (TestSetPageHWPoison(head)) {
 		pr_err("Memory failure: %#lx: already hardware poisoned\n",
 		       pfn);
-		return -EHWPOISON;
+		res = -EHWPOISON;
+		if (flags & MF_ACTION_REQUIRED)
+			res = kill_accessing_process(current, page_to_pfn(head), flags);
+		return res;
 	}
 
 	num_poisoned_pages_inc();
 
-	if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) {
-		/*
-		 * Check "filter hit" and "race with other subpage."
-		 */
-		lock_page(head);
-		if (PageHWPoison(head)) {
-			if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
-			    || (p != head && TestSetPageHWPoison(head))) {
-				num_poisoned_pages_dec();
-				unlock_page(head);
-				return 0;
+	if (!(flags & MF_COUNT_INCREASED)) {
+		res = get_hwpoison_page(p, flags);
+		if (!res) {
+			/*
+			 * Check "filter hit" and "race with other subpage."
+			 */
+			lock_page(head);
+			if (PageHWPoison(head)) {
+				if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
+				    || (p != head && TestSetPageHWPoison(head))) {
+					num_poisoned_pages_dec();
+					unlock_page(head);
+					return 0;
+				}
 			}
+			unlock_page(head);
+			res = MF_FAILED;
+			if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) {
+				page_ref_inc(p);
+				res = MF_RECOVERED;
+			}
+			action_result(pfn, MF_MSG_FREE_HUGE, res);
+			return res == MF_RECOVERED ? 0 : -EBUSY;
+		} else if (res < 0) {
+			action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
+			return -EBUSY;
 		}
-		unlock_page(head);
-		res = MF_FAILED;
-		if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) {
-			page_ref_inc(p);
-			res = MF_RECOVERED;
-		}
-		action_result(pfn, MF_MSG_FREE_HUGE, res);
-		return res == MF_RECOVERED ? 0 : -EBUSY;
 	}
 
 	lock_page(head);
@@ -1476,6 +1639,8 @@ try_again:
 		pr_err("Memory failure: %#lx: already hardware poisoned\n",
 			pfn);
 		res = -EHWPOISON;
+		if (flags & MF_ACTION_REQUIRED)
+			res = kill_accessing_process(current, pfn, flags);
 		goto unlock_mutex;
 	}
 
@@ -1493,28 +1658,35 @@ try_again:
 	 * In fact it's dangerous to directly bump up page count from 0,
 	 * that may make page_ref_freeze()/page_ref_unfreeze() mismatch.
 	 */
-	if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) {
-		if (is_free_buddy_page(p)) {
-			if (take_page_off_buddy(p)) {
-				page_ref_inc(p);
-				res = MF_RECOVERED;
-			} else {
-				/* We lost the race, try again */
-				if (retry) {
-					ClearPageHWPoison(p);
-					num_poisoned_pages_dec();
-					retry = false;
-					goto try_again;
+	if (!(flags & MF_COUNT_INCREASED)) {
+		res = get_hwpoison_page(p, flags);
+		if (!res) {
+			if (is_free_buddy_page(p)) {
+				if (take_page_off_buddy(p)) {
+					page_ref_inc(p);
+					res = MF_RECOVERED;
+				} else {
+					/* We lost the race, try again */
+					if (retry) {
+						ClearPageHWPoison(p);
+						num_poisoned_pages_dec();
+						retry = false;
+						goto try_again;
+					}
+					res = MF_FAILED;
 				}
-				res = MF_FAILED;
+				action_result(pfn, MF_MSG_BUDDY, res);
+				res = res == MF_RECOVERED ? 0 : -EBUSY;
+			} else {
+				action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
+				res = -EBUSY;
 			}
-			action_result(pfn, MF_MSG_BUDDY, res);
-			res = res == MF_RECOVERED ? 0 : -EBUSY;
-		} else {
-			action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
+			goto unlock_mutex;
+		} else if (res < 0) {
+			action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
 			res = -EBUSY;
+			goto unlock_mutex;
 		}
-		goto unlock_mutex;
 	}
 
 	if (PageTransHuge(hpage)) {
@@ -1792,7 +1964,7 @@ int unpoison_memory(unsigned long pfn)
 		return 0;
 	}
 
-	if (!get_hwpoison_page(p, flags, 0)) {
+	if (!get_hwpoison_page(p, flags)) {
 		if (TestClearPageHWPoison(p))
 			num_poisoned_pages_dec();
 		unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n",
@@ -2008,7 +2180,7 @@ int soft_offline_page(unsigned long pfn, int flags)
 
 retry:
 	get_online_mems();
-	ret = get_hwpoison_page(page, flags, MF_SOFT_OFFLINE);
+	ret = get_hwpoison_page(page, flags);
 	put_online_mems();
 
 	if (ret > 0) {