Merge tag 'v5.0-rc6' into for-5.1/block

Pull in 5.0-rc6 to avoid a dumb merge conflict with fs/iomap.c.
This is needed since io_uring is now based on the block branch,
to avoid a conflict between the multi-page bvecs and the bits
of io_uring that touch the core block parts.

* tag 'v5.0-rc6': (525 commits)
  Linux 5.0-rc6
  x86/mm: Make set_pmd_at() paravirt aware
  MAINTAINERS: Update the ocores i2c bus driver maintainer, etc
  blk-mq: remove duplicated definition of blk_mq_freeze_queue
  Blk-iolatency: warn on negative inflight IO counter
  blk-iolatency: fix IO hang due to negative inflight counter
  MAINTAINERS: unify reference to xen-devel list
  x86/mm/cpa: Fix set_mce_nospec()
  futex: Handle early deadlock return correctly
  futex: Fix barrier comment
  net: dsa: b53: Fix for failure when irq is not defined in dt
  blktrace: Show requests without sector
  mips: cm: reprime error cause
  mips: loongson64: remove unreachable(), fix loongson_poweroff().
  sit: check if IPv6 enabled before calling ip6_err_gen_icmpv6_unreach()
  geneve: should not call rt6_lookup() when ipv6 was disabled
  KVM: nVMX: unconditionally cancel preemption timer in free_nested (CVE-2019-7221)
  KVM: x86: work around leak of uninitialized stack contents (CVE-2019-7222)
  kvm: fix kvm_ioctl_create_device() reference counting (CVE-2019-6974)
  signal: Better detection of synchronous signals
  ...

7 files changed, 47 insertions, 58 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index df2e7dd5ff17..afef61656c1e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4268,7 +4268,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				break;
 			}
 			if (ret & VM_FAULT_RETRY) {
-				if (nonblocking)
+				if (nonblocking &&
+				    !(fault_flags & FAULT_FLAG_RETRY_NOWAIT))
 					*nonblocking = 0;
 				*nr_pages = 0;
 				/*
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index 0a14fcff70ed..e2bb06c1b45e 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -5,6 +5,7 @@ UBSAN_SANITIZE_generic.o := n
 UBSAN_SANITIZE_tags.o := n
 KCOV_INSTRUMENT := n
 
+CFLAGS_REMOVE_common.o = -pg
 CFLAGS_REMOVE_generic.o = -pg
 # Function splitter causes unnecessary splits in __asan_load1/__asan_store1
 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 7c72f2a95785..831be5ff5f4d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -372,7 +372,8 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
 			if (fail || tk->addr_valid == 0) {
 				pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
 				       pfn, tk->tsk->comm, tk->tsk->pid);
-				force_sig(SIGKILL, tk->tsk);
+				do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
+						 tk->tsk, PIDTYPE_PID);
 			}
 
 			/*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b9a667d36c55..124e794867c5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1233,7 +1233,8 @@ static bool is_pageblock_removable_nolock(struct page *page)
 bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 {
 	struct page *page = pfn_to_page(start_pfn);
-	struct page *end_page = page + nr_pages;
+	unsigned long end_pfn = min(start_pfn + nr_pages, zone_end_pfn(page_zone(page)));
+	struct page *end_page = pfn_to_page(end_pfn);
 
 	/* Check the starting page of each pageblock within the range */
 	for (; page < end_page; page = next_active_pageblock(page)) {
@@ -1273,6 +1274,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 				i++;
 			if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn)
 				continue;
+			/* Check if we got outside of the zone */
+			if (zone && !zone_spans_pfn(zone, pfn + i))
+				return 0;
 			page = pfn_to_page(pfn + i);
 			if (zone && page_zone(page) != zone)
 				return 0;
@@ -1301,23 +1305,27 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 {
 	unsigned long pfn;
-	struct page *page;
+
 	for (pfn = start; pfn < end; pfn++) {
-		if (pfn_valid(pfn)) {
-			page = pfn_to_page(pfn);
-			if (PageLRU(page))
-				return pfn;
-			if (__PageMovable(page))
-				return pfn;
-			if (PageHuge(page)) {
-				if (hugepage_migration_supported(page_hstate(page)) &&
-				    page_huge_active(page))
-					return pfn;
-				else
-					pfn = round_up(pfn + 1,
-						1 << compound_order(page)) - 1;
-			}
-		}
+		struct page *page, *head;
+		unsigned long skip;
+
+		if (!pfn_valid(pfn))
+			continue;
+		page = pfn_to_page(pfn);
+		if (PageLRU(page))
+			return pfn;
+		if (__PageMovable(page))
+			return pfn;
+
+		if (!PageHuge(page))
+			continue;
+		head = compound_head(page);
+		if (hugepage_migration_supported(page_hstate(head)) &&
+		    page_huge_active(head))
+			return pfn;
+		skip = (1 << compound_order(head)) - (page - head);
+		pfn += skip - 1;
 	}
 	return 0;
 }
@@ -1344,7 +1352,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long pfn;
 	struct page *page;
-	int not_managed = 0;
 	int ret = 0;
 	LIST_HEAD(source);
 
@@ -1392,7 +1399,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		else
 			ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE);
 		if (!ret) { /* Success */
-			put_page(page);
 			list_add_tail(&page->lru, &source);
 			if (!__PageMovable(page))
 				inc_node_page_state(page, NR_ISOLATED_ANON +
@@ -1401,22 +1407,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		} else {
 			pr_warn("failed to isolate pfn %lx\n", pfn);
 			dump_page(page, "isolation failed");
-			put_page(page);
-			/* Because we don't have big zone->lock. we should
-			   check this again here. */
-			if (page_count(page)) {
-				not_managed++;
-				ret = -EBUSY;
-				break;
-			}
 		}
+		put_page(page);
 	}
 	if (!list_empty(&source)) {
-		if (not_managed) {
-			putback_movable_pages(&source);
-			goto out;
-		}
-
 		/* Allocate a new page from the nearest neighbor node */
 		ret = migrate_pages(&source, new_node_page, NULL, 0,
 					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
@@ -1429,7 +1423,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			putback_movable_pages(&source);
 		}
 	}
-out:
+
 	return ret;
 }
 
@@ -1576,7 +1570,6 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	   we assume this for now. .*/
 	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start,
 				  &valid_end)) {
-		mem_hotplug_done();
 		ret = -EINVAL;
 		reason = "multizone range";
 		goto failed_removal;
@@ -1591,7 +1584,6 @@ static int __ref __offline_pages(unsigned long start_pfn,
 				       MIGRATE_MOVABLE,
 				       SKIP_HWPOISON | REPORT_FAILURE);
 	if (ret) {
-		mem_hotplug_done();
 		reason = "failure to isolate range";
 		goto failed_removal;
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index a16b15090df3..d4fd680be3b0 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -709,7 +709,6 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head,
 	/* Simple case, sync compaction */
 	if (mode != MIGRATE_ASYNC) {
 		do {
-			get_bh(bh);
 			lock_buffer(bh);
 			bh = bh->b_this_page;
 
@@ -720,18 +719,15 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head,
 
 	/* async case, we cannot block on lock_buffer so use trylock_buffer */
 	do {
-		get_bh(bh);
 		if (!trylock_buffer(bh)) {
 			/*
 			 * We failed to lock the buffer and cannot stall in
 			 * async migration. Release the taken locks
 			 */
 			struct buffer_head *failed_bh = bh;
-			put_bh(failed_bh);
 			bh = head;
 			while (bh != failed_bh) {
 				unlock_buffer(bh);
-				put_bh(bh);
 				bh = bh->b_this_page;
 			}
 			return false;
@@ -818,7 +814,6 @@ unlock_buffers:
 	bh = head;
 	do {
 		unlock_buffer(bh);
-		put_bh(bh);
 		bh = bh->b_this_page;
 
 	} while (bh != head);
@@ -1135,10 +1130,13 @@ out:
 	 * If migration is successful, decrease refcount of the newpage
 	 * which will not free the page because new page owner increased
 	 * refcounter. As well, if it is LRU page, add the page to LRU
-	 * list in here.
+	 * list in here. Use the old state of the isolated source page to
+	 * determine if we migrated a LRU page. newpage was already unlocked
+	 * and possibly modified by its owner - don't rely on the page
+	 * state.
 	 */
 	if (rc == MIGRATEPAGE_SUCCESS) {
-		if (unlikely(__PageMovable(newpage)))
+		if (unlikely(!is_lru))
 			put_page(newpage);
 		else
 			putback_lru_page(newpage);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f0e8cd9edb1a..26ea8636758f 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -647,8 +647,8 @@ static int oom_reaper(void *unused)
 
 static void wake_oom_reaper(struct task_struct *tsk)
 {
-	/* tsk is already queued? */
-	if (tsk == oom_reaper_list || tsk->oom_reaper_list)
+	/* mm is already queued? */
+	if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags))
 		return;
 
 	get_task_struct(tsk);
@@ -975,6 +975,13 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 	 * still freeing memory.
 	 */
 	read_lock(&tasklist_lock);
+
+	/*
+	 * The task 'p' might have already exited before reaching here. The
+	 * put_task_struct() will free task_struct 'p' while the loop still try
+	 * to access the field of 'p', so, get an extra reference.
+	 */
+	get_task_struct(p);
 	for_each_thread(p, t) {
 		list_for_each_entry(child, &t->children, sibling) {
 			unsigned int child_points;
@@ -994,6 +1001,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 			}
 		}
 	}
+	put_task_struct(p);
 	read_unlock(&tasklist_lock);
 
 	/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d295c9bc01a8..35fdde041f5c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5701,18 +5701,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 			cond_resched();
 		}
 	}
-#ifdef CONFIG_SPARSEMEM
-	/*
-	 * If the zone does not span the rest of the section then
-	 * we should at least initialize those pages. Otherwise we
-	 * could blow up on a poisoned page in some paths which depend
-	 * on full sections being initialized (e.g. memory hotplug).
-	 */
-	while (end_pfn % PAGES_PER_SECTION) {
-		__init_single_page(pfn_to_page(end_pfn), end_pfn, zone, nid);
-		end_pfn++;
-	}
-#endif
 }
 
 #ifdef CONFIG_ZONE_DEVICE