Merge tag 'v4.9.67' into 4.9-1.0.x-imx-fixes-stable-merge

This is the 4.9.67 stable release

Resolved conflicts:
	arch/arm/boot/dts/imx6sx-sdb.dts
	drivers/dma/imx-sdma.c
	drivers/mmc/core/host.c
	drivers/usb/chipidea/otg.c
	sound/soc/fsl/fsl_ssi.c

This merge also reverts commit 3a654a85932f ("dmaengine:
imx-sdma - correct the dma transfer residue calculation"). The
downstream kernel seems to use different structures and already
use buf_ptail in its calculation.

11 files changed, 109 insertions, 62 deletions

diff --git a/block/bio.c b/block/bio.c
index db85c5753a76..07f287b14cff 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -372,10 +372,14 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 	bio_list_init(&punt);
 	bio_list_init(&nopunt);
 
-	while ((bio = bio_list_pop(current->bio_list)))
+	while ((bio = bio_list_pop(&current->bio_list[0])))
 		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[0] = nopunt;
 
-	*current->bio_list = nopunt;
+	bio_list_init(&nopunt);
+	while ((bio = bio_list_pop(&current->bio_list[1])))
+		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[1] = nopunt;
 
 	spin_lock(&bs->rescue_lock);
 	bio_list_merge(&bs->rescue_list, &punt);
@@ -462,7 +466,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		 * we retry with the original gfp_flags.
 		 */
 
-		if (current->bio_list && !bio_list_empty(current->bio_list))
+		if (current->bio_list &&
+		    (!bio_list_empty(&current->bio_list[0]) ||
+		     !bio_list_empty(&current->bio_list[1])))
 			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
 		p = mempool_alloc(bs->bio_pool, gfp_mask);
@@ -1165,8 +1171,8 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	 */
 	bmd->is_our_pages = map_data ? 0 : 1;
 	memcpy(bmd->iov, iter->iov, sizeof(struct iovec) * iter->nr_segs);
-	iov_iter_init(&bmd->iter, iter->type, bmd->iov,
-			iter->nr_segs, iter->count);
+	bmd->iter = *iter;
+	bmd->iter.iov = bmd->iov;
 
 	ret = -ENOMEM;
 	bio = bio_kmalloc(gfp_mask, nr_pages);
@@ -1260,6 +1266,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	int ret, offset;
 	struct iov_iter i;
 	struct iovec iov;
+	struct bio_vec *bvec;
 
 	iov_for_each(iov, i, *iter) {
 		unsigned long uaddr = (unsigned long) iov.iov_base;
@@ -1304,7 +1311,12 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 		ret = get_user_pages_fast(uaddr, local_nr_pages,
 				(iter->type & WRITE) != WRITE,
 				&pages[cur_page]);
-		if (ret < local_nr_pages) {
+		if (unlikely(ret < local_nr_pages)) {
+			for (j = cur_page; j < page_limit; j++) {
+				if (!pages[j])
+					break;
+				put_page(pages[j]);
+			}
 			ret = -EFAULT;
 			goto out_unmap;
 		}
@@ -1312,6 +1324,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 		offset = offset_in_page(uaddr);
 		for (j = cur_page; j < page_limit; j++) {
 			unsigned int bytes = PAGE_SIZE - offset;
+			unsigned short prev_bi_vcnt = bio->bi_vcnt;
 
 			if (len <= 0)
 				break;
@@ -1326,6 +1339,13 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 					    bytes)
 				break;
 
+			/*
+			 * check if vector was merged with previous
+			 * drop page reference if needed
+			 */
+			if (bio->bi_vcnt == prev_bi_vcnt)
+				put_page(pages[j]);
+
 			len -= bytes;
 			offset = 0;
 		}
@@ -1358,10 +1378,8 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 	return bio;
 
  out_unmap:
-	for (j = 0; j < nr_pages; j++) {
-		if (!pages[j])
-			break;
-		put_page(pages[j]);
+	bio_for_each_segment_all(bvec, bio, j) {
+		put_page(bvec->bv_page);
 	}
  out:
 	kfree(pages);
diff --git a/block/blk-core.c b/block/blk-core.c
index 14d7c0740dc0..b1c76aa73492 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -233,7 +233,7 @@ EXPORT_SYMBOL(blk_start_queue_async);
  **/
 void blk_start_queue(struct request_queue *q)
 {
-	WARN_ON(!irqs_disabled());
+	WARN_ON(!in_interrupt() && !irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
 	__blk_run_queue(q);
@@ -282,6 +282,7 @@ EXPORT_SYMBOL(blk_stop_queue);
 void blk_sync_queue(struct request_queue *q)
 {
 	del_timer_sync(&q->timeout);
+	cancel_work_sync(&q->timeout_work);
 
 	if (q->mq_ops) {
 		struct blk_mq_hw_ctx *hctx;
@@ -720,6 +721,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
+	INIT_WORK(&q->timeout_work, NULL);
 	INIT_LIST_HEAD(&q->queue_head);
 	INIT_LIST_HEAD(&q->timeout_list);
 	INIT_LIST_HEAD(&q->icq_list);
@@ -1994,7 +1996,14 @@ end_io:
  */
 blk_qc_t generic_make_request(struct bio *bio)
 {
-	struct bio_list bio_list_on_stack;
+	/*
+	 * bio_list_on_stack[0] contains bios submitted by the current
+	 * make_request_fn.
+	 * bio_list_on_stack[1] contains bios that were submitted before
+	 * the current make_request_fn, but that haven't been processed
+	 * yet.
+	 */
+	struct bio_list bio_list_on_stack[2];
 	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (!generic_make_request_checks(bio))
@@ -2011,7 +2020,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * should be added at the tail
 	 */
 	if (current->bio_list) {
-		bio_list_add(current->bio_list, bio);
+		bio_list_add(&current->bio_list[0], bio);
 		goto out;
 	}
 
@@ -2030,23 +2039,39 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * bio_list, and call into ->make_request() again.
 	 */
 	BUG_ON(bio->bi_next);
-	bio_list_init(&bio_list_on_stack);
-	current->bio_list = &bio_list_on_stack;
+	bio_list_init(&bio_list_on_stack[0]);
+	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
 		if (likely(blk_queue_enter(q, false) == 0)) {
+			struct bio_list lower, same;
+
+			/* Create a fresh bio_list for all subordinate requests */
+			bio_list_on_stack[1] = bio_list_on_stack[0];
+			bio_list_init(&bio_list_on_stack[0]);
 			ret = q->make_request_fn(q, bio);
 
 			blk_queue_exit(q);
 
-			bio = bio_list_pop(current->bio_list);
+			/* sort new bios into those for a lower level
+			 * and those for the same level
+			 */
+			bio_list_init(&lower);
+			bio_list_init(&same);
+			while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
+				if (q == bdev_get_queue(bio->bi_bdev))
+					bio_list_add(&same, bio);
+				else
+					bio_list_add(&lower, bio);
+			/* now assemble so we handle the lowest level first */
+			bio_list_merge(&bio_list_on_stack[0], &lower);
+			bio_list_merge(&bio_list_on_stack[0], &same);
+			bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 		} else {
-			struct bio *bio_next = bio_list_pop(current->bio_list);
-
 			bio_io_error(bio);
-			bio = bio_next;
 		}
+		bio = bio_list_pop(&bio_list_on_stack[0]);
 	} while (bio);
 	current->bio_list = NULL; /* deactivate */
 
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index d69c5c79f98e..478f572cb1e7 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -412,12 +412,13 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 
 	bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
 		template->flags;
-	bi->interval_exp = ilog2(queue_logical_block_size(disk->queue));
+	bi->interval_exp = template->interval_exp ? :
+		ilog2(queue_logical_block_size(disk->queue));
 	bi->profile = template->profile ? template->profile : &nop_profile;
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
 
-	blk_integrity_revalidate(disk);
+	disk->queue->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
 }
 EXPORT_SYMBOL(blk_integrity_register);
 
@@ -430,26 +431,11 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
-	blk_integrity_revalidate(disk);
+	disk->queue->backing_dev_info.capabilities &= ~BDI_CAP_STABLE_WRITES;
 	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
 
-void blk_integrity_revalidate(struct gendisk *disk)
-{
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	if (!(disk->flags & GENHD_FL_UP))
-		return;
-
-	if (bi->profile)
-		disk->queue->backing_dev_info.capabilities |=
-			BDI_CAP_STABLE_WRITES;
-	else
-		disk->queue->backing_dev_info.capabilities &=
-			~BDI_CAP_STABLE_WRITES;
-}
-
 void blk_integrity_add(struct gendisk *disk)
 {
 	if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,
diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c
index 966c2169762e..ee9d3d958fbe 100644
--- a/block/blk-mq-pci.c
+++ b/block/blk-mq-pci.c
@@ -36,12 +36,18 @@ int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev)
 	for (queue = 0; queue < set->nr_hw_queues; queue++) {
 		mask = pci_irq_get_affinity(pdev, queue);
 		if (!mask)
-			return -EINVAL;
+			goto fallback;
 
 		for_each_cpu(cpu, mask)
 			set->mq_map[cpu] = queue;
 	}
 
 	return 0;
+
+fallback:
+	WARN_ON_ONCE(set->nr_hw_queues > 1);
+	for_each_possible_cpu(cpu)
+		set->mq_map[cpu] = 0;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 81caceb96c3c..7b597ec4e9c5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -629,17 +629,8 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 {
 	struct blk_mq_timeout_data *data = priv;
 
-	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
-		/*
-		 * If a request wasn't started before the queue was
-		 * marked dying, kill it here or it'll go unnoticed.
-		 */
-		if (unlikely(blk_queue_dying(rq->q))) {
-			rq->errors = -EIO;
-			blk_mq_end_request(rq, rq->errors);
-		}
+	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
 		return;
-	}
 
 	if (time_after_eq(jiffies, rq->deadline)) {
 		if (!blk_mark_rq_complete(rq))
@@ -1483,7 +1474,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 	INIT_LIST_HEAD(&tags->page_list);
 
 	tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *),
-				 GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY,
+				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
 				 set->numa_node);
 	if (!tags->rqs) {
 		blk_mq_free_tags(tags);
@@ -1509,7 +1500,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 
 		do {
 			page = alloc_pages_node(set->numa_node,
-				GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
+				GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO,
 				this_order);
 			if (page)
 				break;
@@ -1530,7 +1521,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		 * Allow kmemleak to scan these pages as they contain pointers
 		 * to additional allocations like via ops->init_request().
 		 */
-		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_KERNEL);
+		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO);
 		entries_per_page = order_to_size(this_order) / rq_size;
 		to_do = min(entries_per_page, set->queue_depth - i);
 		left -= to_do * rq_size;
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index a30441a200c0..220661a50f58 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -135,8 +135,6 @@ void blk_timeout_work(struct work_struct *work)
 	struct request *rq, *tmp;
 	int next_set = 0;
 
-	if (blk_queue_enter(q, true))
-		return;
 	spin_lock_irqsave(q->queue_lock, flags);
 
 	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
@@ -146,7 +144,6 @@ void blk_timeout_work(struct work_struct *work)
 		mod_timer(&q->timeout, round_jiffies_up(next));
 
 	spin_unlock_irqrestore(q->queue_lock, flags);
-	blk_queue_exit(q);
 }
 
 /**
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 3ab6807773ee..c7c3d4e6bc27 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -36,9 +36,13 @@ static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;
 
 /*
- * offset from end of service tree
+ * offset from end of queue service tree for idle class
  */
 #define CFQ_IDLE_DELAY		(NSEC_PER_SEC / 5)
+/* offset from end of group service tree under time slice mode */
+#define CFQ_SLICE_MODE_GROUP_DELAY (NSEC_PER_SEC / 5)
+/* offset from end of group service under IOPS mode */
+#define CFQ_IOPS_MODE_GROUP_DELAY (HZ / 5)
 
 /*
  * below this threshold, we consider thinktime immediate
@@ -1370,6 +1374,14 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	cfqg->vfraction = max_t(unsigned, vfr, 1);
 }
 
+static inline u64 cfq_get_cfqg_vdisktime_delay(struct cfq_data *cfqd)
+{
+	if (!iops_mode(cfqd))
+		return CFQ_SLICE_MODE_GROUP_DELAY;
+	else
+		return CFQ_IOPS_MODE_GROUP_DELAY;
+}
+
 static void
 cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
@@ -1389,7 +1401,8 @@ cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	n = rb_last(&st->rb);
 	if (n) {
 		__cfqg = rb_entry_cfqg(n);
-		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+		cfqg->vdisktime = __cfqg->vdisktime +
+			cfq_get_cfqg_vdisktime_delay(cfqd);
 	} else
 		cfqg->vdisktime = st->min_vdisktime;
 	cfq_group_service_tree_add(st, cfqg);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 71d9ed9df8da..a2437c006640 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -447,7 +447,6 @@ rescan:
 
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
-	blk_integrity_revalidate(disk);
 	check_disk_size_change(disk, bdev);
 	bdev->bd_invalidated = 0;
 	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index bcd86e5cd546..39f70d968754 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -293,7 +293,7 @@ static gpt_entry *alloc_read_gpt_entries(struct parsed_partitions *state,
 	if (!gpt)
 		return NULL;
 
-	count = le32_to_cpu(gpt->num_partition_entries) *
+	count = (size_t)le32_to_cpu(gpt->num_partition_entries) *
                 le32_to_cpu(gpt->sizeof_partition_entry);
 	if (!count)
 		return NULL;
@@ -352,7 +352,7 @@ static int is_gpt_valid(struct parsed_partitions *state, u64 lba,
 			gpt_header **gpt, gpt_entry **ptes)
 {
 	u32 crc, origcrc;
-	u64 lastlba;
+	u64 lastlba, pt_size;
 
 	if (!ptes)
 		return 0;
@@ -434,13 +434,20 @@ static int is_gpt_valid(struct parsed_partitions *state, u64 lba,
 		goto fail;
 	}
 
+	/* Sanity check partition table size */
+	pt_size = (u64)le32_to_cpu((*gpt)->num_partition_entries) *
+		le32_to_cpu((*gpt)->sizeof_partition_entry);
+	if (pt_size > KMALLOC_MAX_SIZE) {
+		pr_debug("GUID Partition Table is too large: %llu > %lu bytes\n",
+			 (unsigned long long)pt_size, KMALLOC_MAX_SIZE);
+		goto fail;
+	}
+
 	if (!(*ptes = alloc_read_gpt_entries(state, *gpt)))
 		goto fail;
 
 	/* Check the GUID Partition Entry Array CRC */
-	crc = efi_crc32((const unsigned char *) (*ptes),
-			le32_to_cpu((*gpt)->num_partition_entries) *
-			le32_to_cpu((*gpt)->sizeof_partition_entry));
+	crc = efi_crc32((const unsigned char *) (*ptes), pt_size);
 
 	if (crc != le32_to_cpu((*gpt)->partition_entry_array_crc32)) {
 		pr_debug("GUID Partition Entry Array CRC check failed.\n");
diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c
index 93e7c1b32edd..5610cd537da7 100644
--- a/block/partitions/msdos.c
+++ b/block/partitions/msdos.c
@@ -300,6 +300,8 @@ static void parse_bsd(struct parsed_partitions *state,
 			continue;
 		bsd_start = le32_to_cpu(p->p_offset);
 		bsd_size = le32_to_cpu(p->p_size);
+		if (memcmp(flavour, "bsd\0", 4) == 0)
+			bsd_start += offset;
 		if (offset == bsd_start && size == bsd_size)
 			/* full parent partition, we have it already */
 			continue;
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 611abbbb037a..b00647ee3d1c 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -182,6 +182,9 @@ static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
 	__set_bit(WRITE_16, filter->write_ok);
 	__set_bit(WRITE_LONG, filter->write_ok);
 	__set_bit(WRITE_LONG_2, filter->write_ok);
+	__set_bit(WRITE_SAME, filter->write_ok);
+	__set_bit(WRITE_SAME_16, filter->write_ok);
+	__set_bit(WRITE_SAME_32, filter->write_ok);
 	__set_bit(ERASE, filter->write_ok);
 	__set_bit(GPCMD_MODE_SELECT_10, filter->write_ok);
 	__set_bit(MODE_SELECT, filter->write_ok);