1 files changed, 44 insertions, 53 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 7ef849da8278..41c634f45d45 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -199,7 +199,6 @@ struct to_kill {
 	struct task_struct *tsk;
 	unsigned long addr;
 	short size_shift;
-	char addr_valid;
 };
 
 /*
@@ -304,43 +303,43 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page,
 /*
  * Schedule a process for later kill.
  * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM.
- * TBD would GFP_NOIO be enough?
  */
 static void add_to_kill(struct task_struct *tsk, struct page *p,
 		       struct vm_area_struct *vma,
-		       struct list_head *to_kill,
-		       struct to_kill **tkc)
+		       struct list_head *to_kill)
 {
 	struct to_kill *tk;
 
-	if (*tkc) {
-		tk = *tkc;
-		*tkc = NULL;
-	} else {
-		tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC);
-		if (!tk) {
-			pr_err("Memory failure: Out of memory while machine check handling\n");
-			return;
-		}
+	tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC);
+	if (!tk) {
+		pr_err("Memory failure: Out of memory while machine check handling\n");
+		return;
 	}
+
 	tk->addr = page_address_in_vma(p, vma);
-	tk->addr_valid = 1;
 	if (is_zone_device_page(p))
 		tk->size_shift = dev_pagemap_mapping_shift(p, vma);
 	else
-		tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT;
+		tk->size_shift = page_shift(compound_head(p));
 
 	/*
-	 * In theory we don't have to kill when the page was
-	 * munmaped. But it could be also a mremap. Since that's
-	 * likely very rare kill anyways just out of paranoia, but use
-	 * a SIGKILL because the error is not contained anymore.
+	 * Send SIGKILL if "tk->addr == -EFAULT". Also, as
+	 * "tk->size_shift" is always non-zero for !is_zone_device_page(),
+	 * so "tk->size_shift == 0" effectively checks no mapping on
+	 * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times
+	 * to a process' address space, it's possible not all N VMAs
+	 * contain mappings for the page, but at least one VMA does.
+	 * Only deliver SIGBUS with payload derived from the VMA that
+	 * has a mapping for the page.
 	 */
-	if (tk->addr == -EFAULT || tk->size_shift == 0) {
+	if (tk->addr == -EFAULT) {
 		pr_info("Memory failure: Unable to find user space address %lx in %s\n",
 			page_to_pfn(p), tsk->comm);
-		tk->addr_valid = 0;
+	} else if (tk->size_shift == 0) {
+		kfree(tk);
+		return;
 	}
+
 	get_task_struct(tsk);
 	tk->tsk = tsk;
 	list_add_tail(&tk->nd, to_kill);
@@ -366,7 +365,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
 			 * make sure the process doesn't catch the
 			 * signal and then access the memory. Just kill it.
 			 */
-			if (fail || tk->addr_valid == 0) {
+			if (fail || tk->addr == -EFAULT) {
 				pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
 				       pfn, tk->tsk->comm, tk->tsk->pid);
 				do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
@@ -432,7 +431,7 @@ static struct task_struct *task_early_kill(struct task_struct *tsk,
  * Collect processes when the error hit an anonymous page.
  */
 static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc, int force_early)
+				int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -457,7 +456,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 			if (!page_mapped_in_vma(page, vma))
 				continue;
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, vma, to_kill, tkc);
+				add_to_kill(t, page, vma, to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -468,7 +467,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
  * Collect processes when the error hit a file mapped page.
  */
 static void collect_procs_file(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc, int force_early)
+				int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -492,7 +491,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 			 * to be informed of all such data corruptions.
 			 */
 			if (vma->vm_mm == t->mm)
-				add_to_kill(t, page, vma, to_kill, tkc);
+				add_to_kill(t, page, vma, to_kill);
 		}
 	}
 	read_unlock(&tasklist_lock);
@@ -501,26 +500,17 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 
 /*
  * Collect the processes who have the corrupted page mapped to kill.
- * This is done in two steps for locking reasons.
- * First preallocate one tokill structure outside the spin locks,
- * so that we can kill at least one process reasonably reliable.
  */
 static void collect_procs(struct page *page, struct list_head *tokill,
 				int force_early)
 {
-	struct to_kill *tk;
-
 	if (!page->mapping)
 		return;
 
-	tk = kmalloc(sizeof(struct to_kill), GFP_NOIO);
-	if (!tk)
-		return;
 	if (PageAnon(page))
-		collect_procs_anon(page, tokill, &tk, force_early);
+		collect_procs_anon(page, tokill, force_early);
 	else
-		collect_procs_file(page, tokill, &tk, force_early);
-	kfree(tk);
+		collect_procs_file(page, tokill, force_early);
 }
 
 static const char *action_name[] = {
@@ -1253,17 +1243,19 @@ int memory_failure(unsigned long pfn, int flags)
 	if (!sysctl_memory_failure_recovery)
 		panic("Memory failure on page %lx", pfn);
 
-	if (!pfn_valid(pfn)) {
+	p = pfn_to_online_page(pfn);
+	if (!p) {
+		if (pfn_valid(pfn)) {
+			pgmap = get_dev_pagemap(pfn, NULL);
+			if (pgmap)
+				return memory_failure_dev_pagemap(pfn, flags,
+								  pgmap);
+		}
 		pr_err("Memory failure: %#lx: memory outside kernel control\n",
 			pfn);
 		return -ENXIO;
 	}
 
-	pgmap = get_dev_pagemap(pfn, NULL);
-	if (pgmap)
-		return memory_failure_dev_pagemap(pfn, flags, pgmap);
-
-	p = pfn_to_page(pfn);
 	if (PageHuge(p))
 		return memory_failure_hugetlb(pfn, flags);
 	if (TestSetPageHWPoison(p)) {
@@ -1484,7 +1476,7 @@ static void memory_failure_work_func(struct work_struct *work)
 		if (!gotten)
 			break;
 		if (entry.flags & MF_SOFT_OFFLINE)
-			soft_offline_page(pfn_to_page(entry.pfn), entry.flags);
+			soft_offline_page(entry.pfn, entry.flags);
 		else
 			memory_failure(entry.pfn, entry.flags);
 	}
@@ -1865,7 +1857,7 @@ static int soft_offline_free_page(struct page *page)
 
 /**
  * soft_offline_page - Soft offline a page.
- * @page: page to offline
+ * @pfn: pfn to soft-offline
  * @flags: flags. Same as memory_failure().
  *
  * Returns 0 on success, otherwise negated errno.
@@ -1885,18 +1877,17 @@ static int soft_offline_free_page(struct page *page)
  * This is not a 100% solution for all memory, but tries to be
  * ``good enough'' for the majority of memory.
  */
-int soft_offline_page(struct page *page, int flags)
+int soft_offline_page(unsigned long pfn, int flags)
 {
 	int ret;
-	unsigned long pfn = page_to_pfn(page);
+	struct page *page;
 
-	if (is_zone_device_page(page)) {
-		pr_debug_ratelimited("soft_offline: %#lx page is device page\n",
-				pfn);
-		if (flags & MF_COUNT_INCREASED)
-			put_page(page);
+	if (!pfn_valid(pfn))
+		return -ENXIO;
+	/* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */
+	page = pfn_to_online_page(pfn);
+	if (!page)
 		return -EIO;
-	}
 
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);