1 files changed, 84 insertions, 64 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 97a9ed8f87a9..1434e0608d5a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -130,12 +130,6 @@ static int hwpoison_filter_dev(struct page *p)
 	    hwpoison_filter_dev_minor == ~0U)
 		return 0;
 
-	/*
-	 * page_mapping() does not accept slab pages.
-	 */
-	if (PageSlab(p))
-		return -EINVAL;
-
 	mapping = page_mapping(p);
 	if (mapping == NULL || mapping->host == NULL)
 		return -EINVAL;
@@ -258,16 +252,13 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags)
 	pr_err("Memory failure: %#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
 			pfn, t->comm, t->pid);
 
-	if (flags & MF_ACTION_REQUIRED) {
-		if (t == current)
-			ret = force_sig_mceerr(BUS_MCEERR_AR,
-					 (void __user *)tk->addr, addr_lsb);
-		else
-			/* Signal other processes sharing the page if they have PF_MCE_EARLY set. */
-			ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr,
-				addr_lsb, t);
-	} else {
+	if ((flags & MF_ACTION_REQUIRED) && (t == current))
+		ret = force_sig_mceerr(BUS_MCEERR_AR,
+				 (void __user *)tk->addr, addr_lsb);
+	else
 		/*
+		 * Signal other processes sharing the page if they have
+		 * PF_MCE_EARLY set.
 		 * Don't use force here, it's convenient if the signal
 		 * can be temporarily blocked.
 		 * This could cause a loop when the user sets SIGBUS
@@ -275,7 +266,6 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags)
 		 */
 		ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr,
 				      addr_lsb, t);  /* synchronous? */
-	}
 	if (ret < 0)
 		pr_info("Memory failure: Error sending signal to %s:%d: %d\n",
 			t->comm, t->pid, ret);
@@ -315,6 +305,7 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page,
 	pmd_t *pmd;
 	pte_t *pte;
 
+	VM_BUG_ON_VMA(address == -EFAULT, vma);
 	pgd = pgd_offset(vma->vm_mm, address);
 	if (!pgd_present(*pgd))
 		return 0;
@@ -707,8 +698,10 @@ static int kill_accessing_process(struct task_struct *p, unsigned long pfn,
 			      (void *)&priv);
 	if (ret == 1 && priv.tk.addr)
 		kill_proc(&priv.tk, pfn, flags);
+	else
+		ret = 0;
 	mmap_read_unlock(p->mm);
-	return ret ? -EFAULT : -EHWPOISON;
+	return ret > 0 ? -EHWPOISON : -EFAULT;
 }
 
 static const char *action_name[] = {
@@ -739,6 +732,7 @@ static const char * const action_page_types[] = {
 	[MF_MSG_BUDDY]			= "free buddy page",
 	[MF_MSG_DAX]			= "dax page",
 	[MF_MSG_UNSPLIT_THP]		= "unsplit thp",
+	[MF_MSG_DIFFERENT_PAGE_SIZE]	= "different page size",
 	[MF_MSG_UNKNOWN]		= "unknown page",
 };
 
@@ -1182,12 +1176,18 @@ void ClearPageHWPoisonTakenOff(struct page *page)
  * does not return true for hugetlb or device memory pages, so it's assumed
  * to be called only in the context where we never have such pages.
  */
-static inline bool HWPoisonHandlable(struct page *page)
+static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
 {
-	return PageLRU(page) || __PageMovable(page) || is_free_buddy_page(page);
+	bool movable = false;
+
+	/* Soft offline could mirgate non-LRU movable pages */
+	if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
+		movable = true;
+
+	return movable || PageLRU(page) || is_free_buddy_page(page);
 }
 
-static int __get_hwpoison_page(struct page *page)
+static int __get_hwpoison_page(struct page *page, unsigned long flags)
 {
 	struct page *head = compound_head(page);
 	int ret = 0;
@@ -1202,7 +1202,7 @@ static int __get_hwpoison_page(struct page *page)
 	 * for any unsupported type of page in order to reduce the risk of
 	 * unexpected races caused by taking a page refcount.
 	 */
-	if (!HWPoisonHandlable(head))
+	if (!HWPoisonHandlable(head, flags))
 		return -EBUSY;
 
 	if (get_page_unless_zero(head)) {
@@ -1227,7 +1227,7 @@ static int get_any_page(struct page *p, unsigned long flags)
 
 try_again:
 	if (!count_increased) {
-		ret = __get_hwpoison_page(p);
+		ret = __get_hwpoison_page(p, flags);
 		if (!ret) {
 			if (page_count(p)) {
 				/* We raced with an allocation, retry. */
@@ -1255,7 +1255,7 @@ try_again:
 		}
 	}
 
-	if (PageHuge(p) || HWPoisonHandlable(p)) {
+	if (PageHuge(p) || HWPoisonHandlable(p, flags)) {
 		ret = 1;
 	} else {
 		/*
@@ -1411,26 +1411,22 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	if (kill)
 		collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED);
 
-	if (!PageHuge(hpage)) {
-		try_to_unmap(hpage, ttu);
+	if (PageHuge(hpage) && !PageAnon(hpage)) {
+		/*
+		 * For hugetlb pages in shared mappings, try_to_unmap
+		 * could potentially call huge_pmd_unshare.  Because of
+		 * this, take semaphore in write mode here and set
+		 * TTU_RMAP_LOCKED to indicate we have taken the lock
+		 * at this higher level.
+		 */
+		mapping = hugetlb_page_mapping_lock_write(hpage);
+		if (mapping) {
+			try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED);
+			i_mmap_unlock_write(mapping);
+		} else
+			pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn);
 	} else {
-		if (!PageAnon(hpage)) {
-			/*
-			 * For hugetlb pages in shared mappings, try_to_unmap
-			 * could potentially call huge_pmd_unshare.  Because of
-			 * this, take semaphore in write mode here and set
-			 * TTU_RMAP_LOCKED to indicate we have taken the lock
-			 * at this higher level.
-			 */
-			mapping = hugetlb_page_mapping_lock_write(hpage);
-			if (mapping) {
-				try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED);
-				i_mmap_unlock_write(mapping);
-			} else
-				pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn);
-		} else {
-			try_to_unmap(hpage, ttu);
-		}
+		try_to_unmap(hpage, ttu);
 	}
 
 	unmap_success = !page_mapped(hpage);
@@ -1526,7 +1522,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 				if (TestClearPageHWPoison(head))
 					num_poisoned_pages_dec();
 				unlock_page(head);
-				return 0;
+				return -EOPNOTSUPP;
 			}
 			unlock_page(head);
 			res = MF_FAILED;
@@ -1543,8 +1539,27 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 	}
 
 	lock_page(head);
+
+	/*
+	 * The page could have changed compound pages due to race window.
+	 * If this happens just bail out.
+	 */
+	if (!PageHuge(p) || compound_head(p) != head) {
+		action_result(pfn, MF_MSG_DIFFERENT_PAGE_SIZE, MF_IGNORED);
+		res = -EBUSY;
+		goto out;
+	}
+
 	page_flags = head->flags;
 
+	if (hwpoison_filter(p)) {
+		if (TestClearPageHWPoison(head))
+			num_poisoned_pages_dec();
+		put_page(p);
+		res = -EOPNOTSUPP;
+		goto out;
+	}
+
 	/*
 	 * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so
 	 * simply disable it. In order to make it work properly, we need
@@ -1613,7 +1628,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		goto out;
 
 	if (hwpoison_filter(page)) {
-		rc = 0;
+		rc = -EOPNOTSUPP;
 		goto unlock;
 	}
 
@@ -1638,7 +1653,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 	 * SIGBUS (i.e. MF_MUST_KILL)
 	 */
 	flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
-	collect_procs(page, &tokill, flags & MF_ACTION_REQUIRED);
+	collect_procs(page, &tokill, true);
 
 	list_for_each_entry(tk, &tokill, nd)
 		if (tk->size_shift)
@@ -1653,7 +1668,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
 		start = (page->index << PAGE_SHIFT) & ~(size - 1);
 		unmap_mapping_range(page->mapping, start, size, 0);
 	}
-	kill_procs(&tokill, flags & MF_MUST_KILL, false, pfn, flags);
+	kill_procs(&tokill, true, false, pfn, flags);
 	rc = 0;
 unlock:
 	dax_unlock_page(page, cookie);
@@ -1682,12 +1697,15 @@ static DEFINE_MUTEX(mf_mutex);
  *
  * Must run in process context (e.g. a work queue) with interrupts
  * enabled and no spinlocks hold.
+ *
+ * Return: 0 for successfully handled the memory error,
+ *         -EOPNOTSUPP for memory_filter() filtered the error event,
+ *         < 0(except -EOPNOTSUPP) on failure.
  */
 int memory_failure(unsigned long pfn, int flags)
 {
 	struct page *p;
 	struct page *hpage;
-	struct page *orig_head;
 	struct dev_pagemap *pgmap;
 	int res = 0;
 	unsigned long page_flags;
@@ -1733,7 +1751,7 @@ try_again:
 		goto unlock_mutex;
 	}
 
-	orig_head = hpage = compound_head(p);
+	hpage = compound_head(p);
 	num_poisoned_pages_inc();
 
 	/*
@@ -1814,10 +1832,21 @@ try_again:
 	lock_page(p);
 
 	/*
-	 * The page could have changed compound pages during the locking.
-	 * If this happens just bail out.
+	 * We're only intended to deal with the non-Compound page here.
+	 * However, the page could have changed compound pages due to
+	 * race window. If this happens, we could try again to hopefully
+	 * handle the page next round.
 	 */
-	if (PageCompound(p) && compound_head(p) != orig_head) {
+	if (PageCompound(p)) {
+		if (retry) {
+			if (TestClearPageHWPoison(p))
+				num_poisoned_pages_dec();
+			unlock_page(p);
+			put_page(p);
+			flags &= ~MF_COUNT_INCREASED;
+			retry = false;
+			goto try_again;
+		}
 		action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED);
 		res = -EBUSY;
 		goto unlock_page;
@@ -1837,6 +1866,7 @@ try_again:
 			num_poisoned_pages_dec();
 		unlock_page(p);
 		put_page(p);
+		res = -EOPNOTSUPP;
 		goto unlock_mutex;
 	}
 
@@ -1845,7 +1875,7 @@ try_again:
 	 * page_lock. We need wait writeback completion for this page or it
 	 * may trigger vfs BUG while evict inode.
 	 */
-	if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p))
+	if (!PageLRU(p) && !PageWriteback(p))
 		goto identify_page_state;
 
 	/*
@@ -2150,12 +2180,6 @@ static int __soft_offline_page(struct page *page)
 		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
 	};
 
-	/*
-	 * Check PageHWPoison again inside page lock because PageHWPoison
-	 * is set by memory_failure() outside page lock. Note that
-	 * memory_failure() also double-checks PageHWPoison inside page lock,
-	 * so there's no race between soft_offline_page() and memory_failure().
-	 */
 	lock_page(page);
 	if (!PageHuge(page))
 		wait_on_page_writeback(page);
@@ -2166,7 +2190,7 @@ static int __soft_offline_page(struct page *page)
 		return 0;
 	}
 
-	if (!PageHuge(page))
+	if (!PageHuge(page) && PageLRU(page) && !PageSwapCache(page))
 		/*
 		 * Try to invalidate first. This should work for
 		 * non dirty unmapped page cache pages.
@@ -2174,10 +2198,6 @@ static int __soft_offline_page(struct page *page)
 		ret = invalidate_inode_page(page);
 	unlock_page(page);
 
-	/*
-	 * RED-PEN would be better to keep it isolated here, but we
-	 * would need to fix isolation locking first.
-	 */
 	if (ret) {
 		pr_info("soft_offline: %#lx: invalidated\n", pfn);
 		page_handle_poison(page, false, true);
@@ -2288,7 +2308,7 @@ int soft_offline_page(unsigned long pfn, int flags)
 
 retry:
 	get_online_mems();
-	ret = get_hwpoison_page(page, flags);
+	ret = get_hwpoison_page(page, flags | MF_SOFT_OFFLINE);
 	put_online_mems();
 
 	if (ret > 0) {