Merge branch 'x86/cleanups' into perf/uprobes

Merge reason: We want to merge a dependent patch.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

12 files changed, 74 insertions, 23 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 7ba8fea..dd8e2aa 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -318,7 +318,7 @@ static void wakeup_timer_fn(unsigned long data)
 	if (bdi->wb.task) {
 		trace_writeback_wake_thread(bdi);
 		wake_up_process(bdi->wb.task);
-	} else {
+	} else if (bdi->dev) {
 		/*
 		 * When bdi tasks are inactive for long time, they are killed.
 		 * In this case we have to wake-up the forker thread which
@@ -584,6 +584,8 @@ EXPORT_SYMBOL(bdi_register_dev);
  */
 static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
+	struct task_struct *task;
+
 	if (!bdi_cap_writeback_dirty(bdi))
 		return;
 
@@ -602,8 +604,13 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	 * Finally, kill the kernel thread. We don't need to be RCU
 	 * safe anymore, since the bdi is gone from visibility.
 	 */
-	if (bdi->wb.task)
-		kthread_stop(bdi->wb.task);
+	spin_lock_bh(&bdi->wb_lock);
+	task = bdi->wb.task;
+	bdi->wb.task = NULL;
+	spin_unlock_bh(&bdi->wb_lock);
+
+	if (task)
+		kthread_stop(task);
 }
 
 /*
@@ -623,7 +630,9 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-	if (bdi->dev) {
+	struct device *dev = bdi->dev;
+
+	if (dev) {
 		bdi_set_min_ratio(bdi, 0);
 		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
@@ -632,8 +641,12 @@ void bdi_unregister(struct backing_dev_info *bdi)
 		if (!bdi_cap_flush_forker(bdi))
 			bdi_wb_shutdown(bdi);
 		bdi_debug_unregister(bdi);
-		device_unregister(bdi->dev);
+
+		spin_lock_bh(&bdi->wb_lock);
 		bdi->dev = NULL;
+		spin_unlock_bh(&bdi->wb_lock);
+
+		device_unregister(dev);
 	}
 }
 EXPORT_SYMBOL(bdi_unregister);
diff --git a/mm/compaction.c b/mm/compaction.c
index 71a58f6..d9ebebe 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -313,12 +313,34 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 		} else if (!locked)
 			spin_lock_irq(&zone->lru_lock);
 
+		/*
+		 * migrate_pfn does not necessarily start aligned to a
+		 * pageblock. Ensure that pfn_valid is called when moving
+		 * into a new MAX_ORDER_NR_PAGES range in case of large
+		 * memory holes within the zone
+		 */
+		if ((low_pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
+			if (!pfn_valid(low_pfn)) {
+				low_pfn += MAX_ORDER_NR_PAGES - 1;
+				continue;
+			}
+		}
+
 		if (!pfn_valid_within(low_pfn))
 			continue;
 		nr_scanned++;
 
-		/* Get the page and skip if free */
+		/*
+		 * Get the page and ensure the page is within the same zone.
+		 * See the comment in isolate_freepages about overlapping
+		 * nodes. It is deliberate that the new zone lock is not taken
+		 * as memory compaction should not move pages between nodes.
+		 */
 		page = pfn_to_page(low_pfn);
+		if (page_zone(page) != zone)
+			continue;
+
+		/* Skip if free */
 		if (PageBuddy(page))
 			continue;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 97f49ed..b662757 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1400,15 +1400,12 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 	unsigned long seg = 0;
 	size_t count;
 	loff_t *ppos = &iocb->ki_pos;
-	struct blk_plug plug;
 
 	count = 0;
 	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
 	if (retval)
 		return retval;
 
-	blk_start_plug(&plug);
-
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (filp->f_flags & O_DIRECT) {
 		loff_t size;
@@ -1424,8 +1421,12 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 			retval = filemap_write_and_wait_range(mapping, pos,
 					pos + iov_length(iov, nr_segs) - 1);
 			if (!retval) {
+				struct blk_plug plug;
+
+				blk_start_plug(&plug);
 				retval = mapping->a_ops->direct_IO(READ, iocb,
 							iov, pos, nr_segs);
+				blk_finish_plug(&plug);
 			}
 			if (retval > 0) {
 				*ppos = pos + retval;
@@ -1481,7 +1482,6 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 			break;
 	}
 out:
-	blk_finish_plug(&plug);
 	return retval;
 }
 EXPORT_SYMBOL(generic_file_aio_read);
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index f91b2f6..a4eb311 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -263,7 +263,12 @@ found:
 							xip_pfn);
 		if (err == -ENOMEM)
 			return VM_FAULT_OOM;
-		BUG_ON(err);
+		/*
+		 * err == -EBUSY is fine, we've raced against another thread
+		 * that faulted-in the same page
+		 */
+		if (err != -EBUSY)
+			BUG_ON(err);
 		return VM_FAULT_NOPAGE;
 	} else {
 		int err, ret = VM_FAULT_OOM;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b3ffc21..91d3efb 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2083,7 +2083,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot)
 {
 	struct mm_struct *mm = mm_slot->mm;
 
-	VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock));
+	VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock));
 
 	if (khugepaged_test_exit(mm)) {
 		/* free mm_slot */
@@ -2113,7 +2113,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 	int progress = 0;
 
 	VM_BUG_ON(!pages);
-	VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock));
+	VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock));
 
 	if (khugepaged_scan.mm_slot)
 		mm_slot = khugepaged_scan.mm_slot;
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index c833add..45eb621 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1036,7 +1036,7 @@ void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp)
 {
 	pr_debug("%s(0x%p)\n", __func__, ptr);
 
-	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
+	if (atomic_read(&kmemleak_enabled) && ptr && size && !IS_ERR(ptr))
 		add_scan_area((unsigned long)ptr, size, gfp);
 	else if (atomic_read(&kmemleak_early_log))
 		log_early(KMEMLEAK_SCAN_AREA, ptr, size, 0);
@@ -1757,6 +1757,7 @@ void __init kmemleak_init(void)
 
 #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
 	if (!kmemleak_skip_disable) {
+		atomic_set(&kmemleak_early_log, 0);
 		kmemleak_disable();
 		return;
 	}
diff --git a/mm/memblock.c b/mm/memblock.c
index 77b5f22..99f2855 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -99,9 +99,6 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
 	phys_addr_t this_start, this_end, cand;
 	u64 i;
 
-	/* align @size to avoid excessive fragmentation on reserved array */
-	size = round_up(size, align);
-
 	/* pump up @end */
 	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
 		end = memblock.current_limit;
@@ -731,6 +728,9 @@ static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
 {
 	phys_addr_t found;
 
+	/* align @size to avoid excessive fragmentation on reserved array */
+	size = round_up(size, align);
+
 	found = memblock_find_in_range_node(0, max_addr, size, align, nid);
 	if (found && !memblock_reserve(found, size))
 		return found;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 556859f..228d646 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -776,7 +776,8 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 	/* threshold event is triggered in finer grain than soft limit */
 	if (unlikely(mem_cgroup_event_ratelimit(memcg,
 						MEM_CGROUP_TARGET_THRESH))) {
-		bool do_softlimit, do_numainfo;
+		bool do_softlimit;
+		bool do_numainfo __maybe_unused;
 
 		do_softlimit = mem_cgroup_event_ratelimit(memcg,
 						MEM_CGROUP_TARGET_SOFTLIMIT);
@@ -4413,6 +4414,9 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
 	 */
 	BUG_ON(!thresholds);
 
+	if (!thresholds->primary)
+		goto unlock;
+
 	usage = mem_cgroup_usage(memcg, type == _MEMSWAP);
 
 	/* Check if a threshold crossed before removing */
@@ -4461,7 +4465,7 @@ swap_buffers:
 
 	/* To be sure that nobody uses thresholds */
 	synchronize_rcu();
-
+unlock:
 	mutex_unlock(&memcg->thresholds_lock);
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 9871a56..df141f6 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -445,7 +445,6 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 	ClearPageSwapCache(page);
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
-	page->mapping = NULL;
 
 	/*
 	 * If any waiters have accumulated on the new page then
@@ -667,6 +666,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	} else {
 		if (remap_swapcache)
 			remove_migration_ptes(page, newpage);
+		page->mapping = NULL;
 	}
 
 	unlock_page(newpage);
diff --git a/mm/nommu.c b/mm/nommu.c
index b982290..f59e170 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -696,9 +696,11 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (vma->vm_file) {
 		mapping = vma->vm_file->f_mapping;
 
+		mutex_lock(&mapping->i_mmap_mutex);
 		flush_dcache_mmap_lock(mapping);
 		vma_prio_tree_insert(vma, &mapping->i_mmap);
 		flush_dcache_mmap_unlock(mapping);
+		mutex_unlock(&mapping->i_mmap_mutex);
 	}
 
 	/* add the VMA to the tree */
@@ -760,9 +762,11 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 	if (vma->vm_file) {
 		mapping = vma->vm_file->f_mapping;
 
+		mutex_lock(&mapping->i_mmap_mutex);
 		flush_dcache_mmap_lock(mapping);
 		vma_prio_tree_remove(vma, &mapping->i_mmap);
 		flush_dcache_mmap_unlock(mapping);
+		mutex_unlock(&mapping->i_mmap_mutex);
 	}
 
 	/* remove from the MM's tree and list */
@@ -775,8 +779,6 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 
 	if (vma->vm_next)
 		vma->vm_next->vm_prev = vma->vm_prev;
-
-	vma->vm_mm = NULL;
 }
 
 /*
@@ -2052,6 +2054,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
 	high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	down_write(&nommu_region_sem);
+	mutex_lock(&inode->i_mapping->i_mmap_mutex);
 
 	/* search for VMAs that fall within the dead zone */
 	vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
@@ -2059,6 +2062,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
 		/* found one - only interested if it's shared out of the page
 		 * cache */
 		if (vma->vm_flags & VM_SHARED) {
+			mutex_unlock(&inode->i_mapping->i_mmap_mutex);
 			up_write(&nommu_region_sem);
 			return -ETXTBSY; /* not quite true, but near enough */
 		}
@@ -2086,6 +2090,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
 		}
 	}
 
+	mutex_unlock(&inode->i_mapping->i_mmap_mutex);
 	up_write(&nommu_region_sem);
 	return 0;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d2186ec..a13ded1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5236,6 +5236,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 		max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
 		do_div(max, bucketsize);
 	}
+	max = min(max, 0x80000000ULL);
 
 	if (numentries > max)
 		numentries = max;
diff --git a/mm/swap.c b/mm/swap.c
index b0f529b..fff1ff7 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -659,7 +659,7 @@ void lru_add_page_tail(struct zone* zone,
 	VM_BUG_ON(!PageHead(page));
 	VM_BUG_ON(PageCompound(page_tail));
 	VM_BUG_ON(PageLRU(page_tail));
-	VM_BUG_ON(!spin_is_locked(&zone->lru_lock));
+	VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&zone->lru_lock));
 
 	SetPageLRU(page_tail);