Merge 4.14.239 into android-4.14-stable

Changes in 4.14.239
	include/linux/mmdebug.h: make VM_WARN* non-rvals
	mm: add VM_WARN_ON_ONCE_PAGE() macro
	mm/rmap: remove unneeded semicolon in page_not_mapped()
	mm/rmap: use page_not_mapped in try_to_unmap()
	mm/thp: try_to_unmap() use TTU_SYNC for safe splitting
	mm/thp: fix vma_address() if virtual address below file offset
	mm/thp: fix page_address_in_vma() on file THP tails
	mm: thp: replace DEBUG_VM BUG with VM_WARN when unmap fails for split
	mm: page_vma_mapped_walk(): use page for pvmw->page
	mm: page_vma_mapped_walk(): settle PageHuge on entry
	mm: page_vma_mapped_walk(): use pmde for *pvmw->pmd
	mm: page_vma_mapped_walk(): prettify PVMW_MIGRATION block
	mm: page_vma_mapped_walk(): crossing page table boundary
	mm: page_vma_mapped_walk(): add a level of indentation
	mm: page_vma_mapped_walk(): use goto instead of while (1)
	mm: page_vma_mapped_walk(): get vma_address_end() earlier
	mm/thp: fix page_vma_mapped_walk() if THP mapped by ptes
	mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk()
	mm, futex: fix shared futex pgoff on shmem huge page
	scsi: sr: Return appropriate error code when disk is ejected
	drm/nouveau: fix dma_address check for CPU/GPU sync
	kfifo: DECLARE_KIFO_PTR(fifo, u64) does not work on arm 32 bit
	kthread_worker: split code for canceling the delayed work timer
	kthread: prevent deadlock when kthread_mod_delayed_work() races with kthread_cancel_delayed_work_sync()
	xen/events: reset active flag for lateeoi events later
	Linux 4.14.239

Signed-off-by: Greg Kroah-Hartman <[email protected]>
Change-Id: I8bf22702e61b998602c9c195fec19a2b42f89e1b

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 238
+SUBLEVEL = 239
 EXTRAVERSION =
 NAME = Petit Gorille
 

drivers/gpu/drm/nouveau/nouveau_bo.c

@@ -450,7 +450,7 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo)
 	struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm;
 	int i;
 
-	if (!ttm_dma)
+	if (!ttm_dma || !ttm_dma->dma_address)
 		return;
 
 	/* Don't waste time looping if the object is coherent */
@@ -470,7 +470,7 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo)
 	struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm;
 	int i;
 
-	if (!ttm_dma)
+	if (!ttm_dma || !ttm_dma->dma_address)
 		return;
 
 	/* Don't waste time looping if the object is coherent */

drivers/scsi/sr.c

@@ -216,6 +216,8 @@ static unsigned int sr_get_events(struct scsi_device *sdev)
 		return DISK_EVENT_EJECT_REQUEST;
 	else if (med->media_event_code == 2)
 		return DISK_EVENT_MEDIA_CHANGE;
+	else if (med->media_event_code == 3)
+		return DISK_EVENT_EJECT_REQUEST;
 	return 0;
 }
 

drivers/xen/events/events_base.c

@@ -524,6 +524,9 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious)
 	}
 
 	info->eoi_time = 0;
+
+	/* is_active hasn't been reset yet, do it now. */
+	smp_store_release(&info->is_active, 0);
 	do_unmask(info, EVT_MASK_REASON_EOI_PENDING);
 }
 
@@ -1780,10 +1783,22 @@ static void lateeoi_ack_dynirq(struct irq_data *data)
 	struct irq_info *info = info_for_irq(data->irq);
 	evtchn_port_t evtchn = info ? info->evtchn : 0;
 
-	if (VALID_EVTCHN(evtchn)) {
-		do_mask(info, EVT_MASK_REASON_EOI_PENDING);
-		ack_dynirq(data);
-	}
+	if (!VALID_EVTCHN(evtchn))
+		return;
+
+	do_mask(info, EVT_MASK_REASON_EOI_PENDING);
+
+	if (unlikely(irqd_is_setaffinity_pending(data)) &&
+	    likely(!irqd_irq_disabled(data))) {
+		do_mask(info, EVT_MASK_REASON_TEMPORARY);
+
+		clear_evtchn(evtchn);
+
+		irq_move_masked_irq(data);
+
+		do_unmask(info, EVT_MASK_REASON_TEMPORARY);
+	} else
+		clear_evtchn(evtchn);
 }
 
 static void lateeoi_mask_ack_dynirq(struct irq_data *data)

include/linux/hugetlb.h

@@ -467,17 +467,6 @@ static inline int hstate_index(struct hstate *h)
 	return h - hstates;
 }
 
-pgoff_t __basepage_index(struct page *page);
-
-/* Return page->index in PAGE_SIZE units */
-static inline pgoff_t basepage_index(struct page *page)
-{
-	if (!PageCompound(page))
-		return page->index;
-
-	return __basepage_index(page);
-}
-
 extern int dissolve_free_huge_page(struct page *page);
 extern int dissolve_free_huge_pages(unsigned long start_pfn,
 				    unsigned long end_pfn);
@@ -572,11 +561,6 @@ static inline int hstate_index(struct hstate *h)
 	return 0;
 }
 
-static inline pgoff_t basepage_index(struct page *page)
-{
-	return page->index;
-}
-
 static inline int dissolve_free_huge_page(struct page *page)
 {
 	return 0;

include/linux/kfifo.h

@@ -113,7 +113,8 @@ struct kfifo_rec_ptr_2 __STRUCT_KFIFO_PTR(unsigned char, 2, void);
  * array is a part of the structure and the fifo type where the array is
  * outside of the fifo structure.
  */
-#define	__is_kfifo_ptr(fifo)	(sizeof(*fifo) == sizeof(struct __kfifo))
+#define	__is_kfifo_ptr(fifo) \
+	(sizeof(*fifo) == sizeof(STRUCT_KFIFO_PTR(typeof(*(fifo)->type))))
 
 /**
  * DECLARE_KFIFO_PTR - macro to declare a fifo pointer object

include/linux/mmdebug.h

@@ -37,17 +37,30 @@ void dump_mm(const struct mm_struct *mm);
 			BUG();						\
 		}							\
 	} while (0)
-#define VM_WARN_ON(cond) WARN_ON(cond)
-#define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond)
-#define VM_WARN_ONCE(cond, format...) WARN_ONCE(cond, format)
-#define VM_WARN(cond, format...) WARN(cond, format)
+#define VM_WARN_ON_ONCE_PAGE(cond, page)	({			\
+	static bool __section(".data.once") __warned;			\
+	int __ret_warn_once = !!(cond);					\
+									\
+	if (unlikely(__ret_warn_once && !__warned)) {			\
+		dump_page(page, "VM_WARN_ON_ONCE_PAGE(" __stringify(cond)")");\
+		__warned = true;					\
+		WARN_ON(1);						\
+	}								\
+	unlikely(__ret_warn_once);					\
+})
+
+#define VM_WARN_ON(cond) (void)WARN_ON(cond)
+#define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
+#define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format)
+#define VM_WARN(cond, format...) (void)WARN(cond, format)
 #else
 #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond)
 #define VM_BUG_ON_VMA(cond, vma) VM_BUG_ON(cond)
 #define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond)
 #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ON_ONCE_PAGE(cond, page)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #endif

include/linux/pagemap.h

@@ -408,7 +408,7 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
 }
 
 /*
- * Get index of the page with in radix-tree
+ * Get index of the page within radix-tree (but not for hugetlb pages).
  * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE)
  */
 static inline pgoff_t page_to_index(struct page *page)
@@ -427,15 +427,16 @@ static inline pgoff_t page_to_index(struct page *page)
 	return pgoff;
 }
 
+extern pgoff_t hugetlb_basepage_index(struct page *page);
+
 /*
- * Get the offset in PAGE_SIZE.
- * (TODO: hugepage should have ->index in PAGE_SIZE)
+ * Get the offset in PAGE_SIZE (even for hugetlb pages).
+ * (TODO: hugetlb pages should have ->index in PAGE_SIZE)
  */
 static inline pgoff_t page_to_pgoff(struct page *page)
 {
-	if (unlikely(PageHeadHuge(page)))
-		return page->index << compound_order(page);
-
+	if (unlikely(PageHuge(page)))
+		return hugetlb_basepage_index(page);
 	return page_to_index(page);
 }
 

include/linux/rmap.h

@@ -98,7 +98,8 @@ enum ttu_flags {
 					 * do a final flush if necessary */
 	TTU_RMAP_LOCKED		= 0x80,	/* do not grab rmap lock:
 					 * caller holds it */
-	TTU_SPLIT_FREEZE	= 0x100,		/* freeze pte under splitting thp */
+	TTU_SPLIT_FREEZE	= 0x100, /* freeze pte under splitting thp */
+	TTU_SYNC		= 0x200, /* avoid racy checks with PVMW_SYNC */
 };
 
 #ifdef CONFIG_MMU

kernel/futex.c

@@ -719,7 +719,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
 		key->shared.i_seq = get_inode_sequence_number(inode);
-		key->shared.pgoff = basepage_index(tail);
+		key->shared.pgoff = page_to_pgoff(tail);
 		rcu_read_unlock();
 	}
 

kernel/kthread.c

@@ -979,37 +979,47 @@ void kthread_flush_work(struct kthread_work *work)
 EXPORT_SYMBOL_GPL(kthread_flush_work);
 
 /*
- * This function removes the work from the worker queue. Also it makes sure
- * that it won't get queued later via the delayed work's timer.
+ * Make sure that the timer is neither set nor running and could
+ * not manipulate the work list_head any longer.
+ *
+ * The function is called under worker->lock. The lock is temporary
+ * released but the timer can't be set again in the meantime.
+ */
+static void kthread_cancel_delayed_work_timer(struct kthread_work *work,
+					      unsigned long *flags)
+{
+	struct kthread_delayed_work *dwork =
+		container_of(work, struct kthread_delayed_work, work);
+	struct kthread_worker *worker = work->worker;
+
+	/*
+	 * del_timer_sync() must be called to make sure that the timer
+	 * callback is not running. The lock must be temporary released
+	 * to avoid a deadlock with the callback. In the meantime,
+	 * any queuing is blocked by setting the canceling counter.
+	 */
+	work->canceling++;
+	spin_unlock_irqrestore(&worker->lock, *flags);
+	del_timer_sync(&dwork->timer);
+	spin_lock_irqsave(&worker->lock, *flags);
+	work->canceling--;
+}
+
+/*
+ * This function removes the work from the worker queue.
+ *
+ * It is called under worker->lock. The caller must make sure that
+ * the timer used by delayed work is not running, e.g. by calling
+ * kthread_cancel_delayed_work_timer().
  *
  * The work might still be in use when this function finishes. See the
  * current_work proceed by the worker.
  *
  * Return: %true if @work was pending and successfully canceled,
  *	%false if @work was not pending
  */
-static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork,
-				  unsigned long *flags)
+static bool __kthread_cancel_work(struct kthread_work *work)
 {
-	/* Try to cancel the timer if exists. */
-	if (is_dwork) {
-		struct kthread_delayed_work *dwork =
-			container_of(work, struct kthread_delayed_work, work);
-		struct kthread_worker *worker = work->worker;
-
-		/*
-		 * del_timer_sync() must be called to make sure that the timer
-		 * callback is not running. The lock must be temporary released
-		 * to avoid a deadlock with the callback. In the meantime,
-		 * any queuing is blocked by setting the canceling counter.
-		 */
-		work->canceling++;
-		spin_unlock_irqrestore(&worker->lock, *flags);
-		del_timer_sync(&dwork->timer);
-		spin_lock_irqsave(&worker->lock, *flags);
-		work->canceling--;
-	}
-
 	/*
 	 * Try to remove the work from a worker list. It might either
 	 * be from worker->work_list or from worker->delayed_work_list.
@@ -1062,11 +1072,23 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker,
 	/* Work must not be used with >1 worker, see kthread_queue_work() */
 	WARN_ON_ONCE(work->worker != worker);
 
-	/* Do not fight with another command that is canceling this work. */
+	/*
+	 * Temporary cancel the work but do not fight with another command
+	 * that is canceling the work as well.
+	 *
+	 * It is a bit tricky because of possible races with another
+	 * mod_delayed_work() and cancel_delayed_work() callers.
+	 *
+	 * The timer must be canceled first because worker->lock is released
+	 * when doing so. But the work can be removed from the queue (list)
+	 * only when it can be queued again so that the return value can
+	 * be used for reference counting.
+	 */
+	kthread_cancel_delayed_work_timer(work, &flags);
 	if (work->canceling)
 		goto out;
+	ret = __kthread_cancel_work(work);
 
-	ret = __kthread_cancel_work(work, true, &flags);
 fast_queue:
 	__kthread_queue_delayed_work(worker, dwork, delay);
 out:
@@ -1088,7 +1110,10 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork)
 	/* Work must not be used with >1 worker, see kthread_queue_work(). */
 	WARN_ON_ONCE(work->worker != worker);
 
-	ret = __kthread_cancel_work(work, is_dwork, &flags);
+	if (is_dwork)
+		kthread_cancel_delayed_work_timer(work, &flags);
+
+	ret = __kthread_cancel_work(work);
 
 	if (worker->current_work != work)
 		goto out_fast;

mm/huge_memory.c

@@ -2324,16 +2324,16 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 static void unmap_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
-		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
-	bool unmap_success;
+		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC;
 
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
 	if (PageAnon(page))
 		ttu_flags |= TTU_SPLIT_FREEZE;
 
-	unmap_success = try_to_unmap(page, ttu_flags);
-	VM_BUG_ON_PAGE(!unmap_success, page);
+	try_to_unmap(page, ttu_flags);
+
+	VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
 }
 
 static void remap_page(struct page *page)
@@ -2587,7 +2587,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
-	int count, mapcount, extra_pins, ret;
+	int extra_pins, ret;
 	bool mlocked;
 	unsigned long flags;
 	pgoff_t end;
@@ -2649,7 +2649,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 	mlocked = PageMlocked(page);
 	unmap_page(head);
-	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* Make sure the page is not on per-CPU pagevec as it takes pin */
 	if (mlocked)
@@ -2675,9 +2674,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 	/* Prevent deferred_split_scan() touching ->_refcount */
 	spin_lock(&pgdata->split_queue_lock);
-	count = page_count(head);
-	mapcount = total_mapcount(head);
-	if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
+	if (page_ref_freeze(head, 1 + extra_pins)) {
 		if (!list_empty(page_deferred_list(head))) {
 			pgdata->split_queue_len--;
 			list_del(page_deferred_list(head));
@@ -2693,16 +2690,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		} else
 			ret = 0;
 	} else {
-		if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
-			pr_alert("total_mapcount: %u, page_count(): %u\n",
-					mapcount, count);
-			if (PageTail(page))
-				dump_page(head, NULL);
-			dump_page(page, "total_mapcount(head) > 0");
-			BUG();
-		}
 		spin_unlock(&pgdata->split_queue_lock);
-fail:		if (mapping)
+fail:
+		if (mapping)
 			spin_unlock(&mapping->tree_lock);
 		spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
 		remap_page(head);

mm/hugetlb.c

@@ -1403,15 +1403,12 @@ int PageHeadHuge(struct page *page_head)
 	return get_compound_page_dtor(page_head) == free_huge_page;
 }
 
-pgoff_t __basepage_index(struct page *page)
+pgoff_t hugetlb_basepage_index(struct page *page)
 {
 	struct page *page_head = compound_head(page);
 	pgoff_t index = page_index(page_head);
 	unsigned long compound_idx;
 
-	if (!PageHuge(page_head))
-		return page_index(page);
-
 	if (compound_order(page_head) >= MAX_ORDER)
 		compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
 	else