1 files changed, 234 insertions, 141 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index cbb15716a5d..6234b2e8458 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -133,7 +133,7 @@ static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
 static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
 {
 	int sectors = bio_sectors(bio);
-	if (bio->bi_sector + sectors < sector + STRIPE_SECTORS)
+	if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS)
 		return bio->bi_next;
 	else
 		return NULL;
@@ -225,7 +225,7 @@ static void return_io(struct bio *return_bi)
 
 		return_bi = bi->bi_next;
 		bi->bi_next = NULL;
-		bi->bi_size = 0;
+		bi->bi_iter.bi_size = 0;
 		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
 					 bi, 0);
 		bio_endio(bi, 0);
@@ -292,9 +292,12 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 	BUG_ON(atomic_read(&conf->active_stripes)==0);
 	if (test_bit(STRIPE_HANDLE, &sh->state)) {
 		if (test_bit(STRIPE_DELAYED, &sh->state) &&
-		    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+		    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
 			list_add_tail(&sh->lru, &conf->delayed_list);
-		else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
+			if (atomic_read(&conf->preread_active_stripes)
+			    < IO_THRESHOLD)
+				md_wakeup_thread(conf->mddev->thread);
+		} else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
 			   sh->bm_seq - conf->seq_write > 0)
 			list_add_tail(&sh->lru, &conf->bitmap_list);
 		else {
@@ -413,6 +416,11 @@ static void release_stripe(struct stripe_head *sh)
 	int hash;
 	bool wakeup;
 
+	/* Avoid release_list until the last reference.
+	 */
+	if (atomic_add_unless(&sh->count, -1, 1))
+		return;
+
 	if (unlikely(!conf->mddev->thread) ||
 		test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state))
 		goto slow_path;
@@ -479,6 +487,7 @@ static void shrink_buffers(struct stripe_head *sh)
 	int num = sh->raid_conf->pool_size;
 
 	for (i = 0; i < num ; i++) {
+		WARN_ON(sh->dev[i].page != sh->dev[i].orig_page);
 		p = sh->dev[i].page;
 		if (!p)
 			continue;
@@ -499,6 +508,7 @@ static int grow_buffers(struct stripe_head *sh)
 			return 1;
 		}
 		sh->dev[i].page = page;
+		sh->dev[i].orig_page = page;
 	}
 	return 0;
 }
@@ -675,16 +685,13 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 					 || !conf->inactive_blocked),
 					*(conf->hash_locks + hash));
 				conf->inactive_blocked = 0;
-			} else
+			} else {
 				init_stripe(sh, sector, previous);
-		} else {
+				atomic_inc(&sh->count);
+			}
+		} else if (!atomic_inc_not_zero(&sh->count)) {
 			spin_lock(&conf->device_lock);
-			if (atomic_read(&sh->count)) {
-				BUG_ON(!list_empty(&sh->lru)
-				    && !test_bit(STRIPE_EXPANDING, &sh->state)
-				    && !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state)
-					);
-			} else {
+			if (!atomic_read(&sh->count)) {
 				if (!test_bit(STRIPE_HANDLE, &sh->state))
 					atomic_inc(&conf->active_stripes);
 				BUG_ON(list_empty(&sh->lru) &&
@@ -695,13 +702,11 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 					sh->group = NULL;
 				}
 			}
+			atomic_inc(&sh->count);
 			spin_unlock(&conf->device_lock);
 		}
 	} while (sh == NULL);
 
-	if (sh)
-		atomic_inc(&sh->count);
-
 	spin_unlock_irq(conf->hash_locks + hash);
 	return sh;
 }
@@ -852,18 +857,21 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 				bi->bi_rw, i);
 			atomic_inc(&sh->count);
 			if (use_new_offset(conf, sh))
-				bi->bi_sector = (sh->sector
+				bi->bi_iter.bi_sector = (sh->sector
 						 + rdev->new_data_offset);
 			else
-				bi->bi_sector = (sh->sector
+				bi->bi_iter.bi_sector = (sh->sector
 						 + rdev->data_offset);
 			if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
 				bi->bi_rw |= REQ_NOMERGE;
 
+			if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
+				WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+			sh->dev[i].vec.bv_page = sh->dev[i].page;
 			bi->bi_vcnt = 1;
 			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			bi->bi_io_vec[0].bv_offset = 0;
-			bi->bi_size = STRIPE_SIZE;
+			bi->bi_iter.bi_size = STRIPE_SIZE;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -899,15 +907,18 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 				rbi->bi_rw, i);
 			atomic_inc(&sh->count);
 			if (use_new_offset(conf, sh))
-				rbi->bi_sector = (sh->sector
+				rbi->bi_iter.bi_sector = (sh->sector
 						  + rrdev->new_data_offset);
 			else
-				rbi->bi_sector = (sh->sector
+				rbi->bi_iter.bi_sector = (sh->sector
 						  + rrdev->data_offset);
+			if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
+				WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+			sh->dev[i].rvec.bv_page = sh->dev[i].page;
 			rbi->bi_vcnt = 1;
 			rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			rbi->bi_io_vec[0].bv_offset = 0;
-			rbi->bi_size = STRIPE_SIZE;
+			rbi->bi_iter.bi_size = STRIPE_SIZE;
 			/*
 			 * If this is discard request, set bi_vcnt 0. We don't
 			 * want to confuse SCSI because SCSI will replace payload
@@ -932,27 +943,28 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 }
 
 static struct dma_async_tx_descriptor *
-async_copy_data(int frombio, struct bio *bio, struct page *page,
-	sector_t sector, struct dma_async_tx_descriptor *tx)
+async_copy_data(int frombio, struct bio *bio, struct page **page,
+	sector_t sector, struct dma_async_tx_descriptor *tx,
+	struct stripe_head *sh)
 {
-	struct bio_vec *bvl;
+	struct bio_vec bvl;
+	struct bvec_iter iter;
 	struct page *bio_page;
-	int i;
 	int page_offset;
 	struct async_submit_ctl submit;
 	enum async_tx_flags flags = 0;
 
-	if (bio->bi_sector >= sector)
-		page_offset = (signed)(bio->bi_sector - sector) * 512;
+	if (bio->bi_iter.bi_sector >= sector)
+		page_offset = (signed)(bio->bi_iter.bi_sector - sector) * 512;
 	else
-		page_offset = (signed)(sector - bio->bi_sector) * -512;
+		page_offset = (signed)(sector - bio->bi_iter.bi_sector) * -512;
 
 	if (frombio)
 		flags |= ASYNC_TX_FENCE;
 	init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
 
-	bio_for_each_segment(bvl, bio, i) {
-		int len = bvl->bv_len;
+	bio_for_each_segment(bvl, bio, iter) {
+		int len = bvl.bv_len;
 		int clen;
 		int b_offset = 0;
 
@@ -968,13 +980,18 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 			clen = len;
 
 		if (clen > 0) {
-			b_offset += bvl->bv_offset;
-			bio_page = bvl->bv_page;
-			if (frombio)
-				tx = async_memcpy(page, bio_page, page_offset,
+			b_offset += bvl.bv_offset;
+			bio_page = bvl.bv_page;
+			if (frombio) {
+				if (sh->raid_conf->skip_copy &&
+				    b_offset == 0 && page_offset == 0 &&
+				    clen == STRIPE_SIZE)
+					*page = bio_page;
+				else
+					tx = async_memcpy(*page, bio_page, page_offset,
 						  b_offset, clen, &submit);
-			else
-				tx = async_memcpy(bio_page, page, b_offset,
+			} else
+				tx = async_memcpy(bio_page, *page, b_offset,
 						  page_offset, clen, &submit);
 		}
 		/* chain the operations */
@@ -1012,7 +1029,7 @@ static void ops_complete_biofill(void *stripe_head_ref)
 			BUG_ON(!dev->read);
 			rbi = dev->read;
 			dev->read = NULL;
-			while (rbi && rbi->bi_sector <
+			while (rbi && rbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				rbi2 = r5_next_bio(rbi, dev->sector);
 				if (!raid5_dec_bi_active_stripes(rbi)) {
@@ -1048,10 +1065,10 @@ static void ops_run_biofill(struct stripe_head *sh)
 			dev->read = rbi = dev->toread;
 			dev->toread = NULL;
 			spin_unlock_irq(&sh->stripe_lock);
-			while (rbi && rbi->bi_sector <
+			while (rbi && rbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
-				tx = async_copy_data(0, rbi, dev->page,
-					dev->sector, tx);
+				tx = async_copy_data(0, rbi, &dev->page,
+					dev->sector, tx, sh);
 				rbi = r5_next_bio(rbi, dev->sector);
 			}
 		}
@@ -1389,8 +1406,9 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 			BUG_ON(dev->written);
 			wbi = dev->written = chosen;
 			spin_unlock_irq(&sh->stripe_lock);
+			WARN_ON(dev->page != dev->orig_page);
 
-			while (wbi && wbi->bi_sector <
+			while (wbi && wbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				if (wbi->bi_rw & REQ_FUA)
 					set_bit(R5_WantFUA, &dev->flags);
@@ -1398,9 +1416,15 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 					set_bit(R5_SyncIO, &dev->flags);
 				if (wbi->bi_rw & REQ_DISCARD)
 					set_bit(R5_Discard, &dev->flags);
-				else
-					tx = async_copy_data(1, wbi, dev->page,
-						dev->sector, tx);
+				else {
+					tx = async_copy_data(1, wbi, &dev->page,
+						dev->sector, tx, sh);
+					if (dev->page != dev->orig_page) {
+						set_bit(R5_SkipCopy, &dev->flags);
+						clear_bit(R5_UPTODATE, &dev->flags);
+						clear_bit(R5_OVERWRITE, &dev->flags);
+					}
+				}
 				wbi = r5_next_bio(wbi, dev->sector);
 			}
 		}
@@ -1431,7 +1455,7 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
 		struct r5dev *dev = &sh->dev[i];
 
 		if (dev->written || i == pd_idx || i == qd_idx) {
-			if (!discard)
+			if (!discard && !test_bit(R5_SkipCopy, &dev->flags))
 				set_bit(R5_UPTODATE, &dev->flags);
 			if (fua)
 				set_bit(R5_WantFUA, &dev->flags);
@@ -1844,8 +1868,10 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		osh = get_free_stripe(conf, hash);
 		unlock_device_hash_lock(conf, hash);
 		atomic_set(&nsh->count, 1);
-		for(i=0; i<conf->pool_size; i++)
+		for(i=0; i<conf->pool_size; i++) {
 			nsh->dev[i].page = osh->dev[i].page;
+			nsh->dev[i].orig_page = osh->dev[i].page;
+		}
 		for( ; i<newsize; i++)
 			nsh->dev[i].page = NULL;
 		nsh->hash_lock_index = hash;
@@ -1901,6 +1927,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 			if (nsh->dev[i].page == NULL) {
 				struct page *p = alloc_page(GFP_NOIO);
 				nsh->dev[i].page = p;
+				nsh->dev[i].orig_page = p;
 				if (!p)
 					err = -ENOMEM;
 			}
@@ -2111,6 +2138,7 @@ static void raid5_end_write_request(struct bio *bi, int error)
 			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
 	} else {
 		if (!uptodate) {
+			set_bit(STRIPE_DEGRADED, &sh->state);
 			set_bit(WriteErrorSeen, &rdev->flags);
 			set_bit(R5_WriteError, &sh->dev[i].flags);
 			if (!test_and_set_bit(WantReplacement, &rdev->flags))
@@ -2137,24 +2165,20 @@ static void raid5_end_write_request(struct bio *bi, int error)
 }
 
 static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous);
-	
+
 static void raid5_build_block(struct stripe_head *sh, int i, int previous)
 {
 	struct r5dev *dev = &sh->dev[i];
 
 	bio_init(&dev->req);
 	dev->req.bi_io_vec = &dev->vec;
-	dev->req.bi_vcnt++;
-	dev->req.bi_max_vecs++;
+	dev->req.bi_max_vecs = 1;
 	dev->req.bi_private = sh;
-	dev->vec.bv_page = dev->page;
 
 	bio_init(&dev->rreq);
 	dev->rreq.bi_io_vec = &dev->rvec;
-	dev->rreq.bi_vcnt++;
-	dev->rreq.bi_max_vecs++;
+	dev->rreq.bi_max_vecs = 1;
 	dev->rreq.bi_private = sh;
-	dev->rvec.bv_page = dev->page;
 
 	dev->flags = 0;
 	dev->sector = compute_blocknr(sh, i, previous);
@@ -2614,7 +2638,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 	int firstwrite=0;
 
 	pr_debug("adding bi b#%llu to stripe s#%llu\n",
-		(unsigned long long)bi->bi_sector,
+		(unsigned long long)bi->bi_iter.bi_sector,
 		(unsigned long long)sh->sector);
 
 	/*
@@ -2632,12 +2656,12 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 			firstwrite = 1;
 	} else
 		bip = &sh->dev[dd_idx].toread;
-	while (*bip && (*bip)->bi_sector < bi->bi_sector) {
-		if (bio_end_sector(*bip) > bi->bi_sector)
+	while (*bip && (*bip)->bi_iter.bi_sector < bi->bi_iter.bi_sector) {
+		if (bio_end_sector(*bip) > bi->bi_iter.bi_sector)
 			goto overlap;
 		bip = & (*bip)->bi_next;
 	}
-	if (*bip && (*bip)->bi_sector < bio_end_sector(bi))
+	if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi))
 		goto overlap;
 
 	BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
@@ -2651,7 +2675,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 		sector_t sector = sh->dev[dd_idx].sector;
 		for (bi=sh->dev[dd_idx].towrite;
 		     sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
-			     bi && bi->bi_sector <= sector;
+			     bi && bi->bi_iter.bi_sector <= sector;
 		     bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
 			if (bio_end_sector(bi) >= sector)
 				sector = bio_end_sector(bi);
@@ -2661,7 +2685,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
 	}
 
 	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
-		(unsigned long long)(*bip)->bi_sector,
+		(unsigned long long)(*bip)->bi_iter.bi_sector,
 		(unsigned long long)sh->sector, dd_idx);
 	spin_unlock_irq(&sh->stripe_lock);
 
@@ -2736,7 +2760,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 			wake_up(&conf->wait_for_overlap);
 
-		while (bi && bi->bi_sector <
+		while (bi && bi->bi_iter.bi_sector <
 			sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
 			clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -2754,8 +2778,13 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		/* and fail all 'written' */
 		bi = sh->dev[i].written;
 		sh->dev[i].written = NULL;
+		if (test_and_clear_bit(R5_SkipCopy, &sh->dev[i].flags)) {
+			WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+			sh->dev[i].page = sh->dev[i].orig_page;
+		}
+
 		if (bi) bitmap_end = 1;
-		while (bi && bi->bi_sector <
+		while (bi && bi->bi_iter.bi_sector <
 		       sh->dev[i].sector + STRIPE_SECTORS) {
 			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
 			clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -2779,7 +2808,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			spin_unlock_irq(&sh->stripe_lock);
 			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 				wake_up(&conf->wait_for_overlap);
-			while (bi && bi->bi_sector <
+			while (bi && bi->bi_iter.bi_sector <
 			       sh->dev[i].sector + STRIPE_SECTORS) {
 				struct bio *nextbi =
 					r5_next_bio(bi, sh->dev[i].sector);
@@ -2890,8 +2919,11 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
 	     (s->failed >= 1 && fdev[0]->toread) ||
 	     (s->failed >= 2 && fdev[1]->toread) ||
 	     (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
+	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) &&
 	      !test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
-	     (sh->raid_conf->level == 6 && s->failed && s->to_write))) {
+	     (sh->raid_conf->level == 6 && s->failed && s->to_write &&
+	      s->to_write < sh->raid_conf->raid_disks - 2 &&
+	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) {
 		/* we would like to get this block, possibly by computing it,
 		 * otherwise read it if the backing disk is insync
 		 */
@@ -2995,15 +3027,20 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 			dev = &sh->dev[i];
 			if (!test_bit(R5_LOCKED, &dev->flags) &&
 			    (test_bit(R5_UPTODATE, &dev->flags) ||
-			     test_bit(R5_Discard, &dev->flags))) {
+			     test_bit(R5_Discard, &dev->flags) ||
+			     test_bit(R5_SkipCopy, &dev->flags))) {
 				/* We can return any write requests */
 				struct bio *wbi, *wbi2;
 				pr_debug("Return write for disc %d\n", i);
 				if (test_and_clear_bit(R5_Discard, &dev->flags))
 					clear_bit(R5_UPTODATE, &dev->flags);
+				if (test_and_clear_bit(R5_SkipCopy, &dev->flags)) {
+					WARN_ON(test_bit(R5_UPTODATE, &dev->flags));
+					dev->page = dev->orig_page;
+				}
 				wbi = dev->written;
 				dev->written = NULL;
-				while (wbi && wbi->bi_sector <
+				while (wbi && wbi->bi_iter.bi_sector <
 					dev->sector + STRIPE_SECTORS) {
 					wbi2 = r5_next_bio(wbi, dev->sector);
 					if (!raid5_dec_bi_active_stripes(wbi)) {
@@ -3019,6 +3056,8 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 						0);
 			} else if (test_bit(R5_Discard, &dev->flags))
 				discard_pending = 1;
+			WARN_ON(test_bit(R5_SkipCopy, &dev->flags));
+			WARN_ON(dev->page != dev->orig_page);
 		}
 	if (!discard_pending &&
 	    test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
@@ -3090,7 +3129,8 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 		    !test_bit(R5_LOCKED, &dev->flags) &&
 		    !(test_bit(R5_UPTODATE, &dev->flags) ||
 		    test_bit(R5_Wantcompute, &dev->flags))) {
-			if (test_bit(R5_Insync, &dev->flags)) rcw++;
+			if (test_bit(R5_Insync, &dev->flags))
+				rcw++;
 			else
 				rcw += 2*disks;
 		}
@@ -3111,10 +3151,10 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 			    !(test_bit(R5_UPTODATE, &dev->flags) ||
 			    test_bit(R5_Wantcompute, &dev->flags)) &&
 			    test_bit(R5_Insync, &dev->flags)) {
-				if (
-				  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
-					pr_debug("Read_old block "
-						 "%d for r-m-w\n", i);
+				if (test_bit(STRIPE_PREREAD_ACTIVE,
+					     &sh->state)) {
+					pr_debug("Read_old block %d for r-m-w\n",
+						 i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
 					s->locked++;
@@ -3137,10 +3177,9 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 			    !(test_bit(R5_UPTODATE, &dev->flags) ||
 			      test_bit(R5_Wantcompute, &dev->flags))) {
 				rcw++;
-				if (!test_bit(R5_Insync, &dev->flags))
-					continue; /* it's a failed drive */
-				if (
-				  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+				if (test_bit(R5_Insync, &dev->flags) &&
+				    test_bit(STRIPE_PREREAD_ACTIVE,
+					     &sh->state)) {
 					pr_debug("Read_old block "
 						"%d for Reconstruct\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
@@ -4095,7 +4134,7 @@ static int raid5_mergeable_bvec(struct request_queue *q,
 
 static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
 {
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	sector_t sector = bio->bi_iter.bi_sector + get_start_sect(bio->bi_bdev);
 	unsigned int chunk_sectors = mddev->chunk_sectors;
 	unsigned int bio_sectors = bio_sectors(bio);
 
@@ -4232,9 +4271,9 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 	/*
 	 *	compute position
 	 */
-	align_bi->bi_sector =  raid5_compute_sector(conf, raid_bio->bi_sector,
-						    0,
-						    &dd_idx, NULL);
+	align_bi->bi_iter.bi_sector =
+		raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector,
+				     0, &dd_idx, NULL);
 
 	end_sector = bio_end_sector(align_bi);
 	rcu_read_lock();
@@ -4259,7 +4298,8 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
 
 		if (!bio_fits_rdev(align_bi) ||
-		    is_badblock(rdev, align_bi->bi_sector, bio_sectors(align_bi),
+		    is_badblock(rdev, align_bi->bi_iter.bi_sector,
+				bio_sectors(align_bi),
 				&first_bad, &bad_sectors)) {
 			/* too big in some way, or has a known bad block */
 			bio_put(align_bi);
@@ -4268,7 +4308,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		}
 
 		/* No reshape active, so we can trust rdev->data_offset */
-		align_bi->bi_sector += rdev->data_offset;
+		align_bi->bi_iter.bi_sector += rdev->data_offset;
 
 		spin_lock_irq(&conf->device_lock);
 		wait_event_lock_irq(conf->wait_for_stripe,
@@ -4280,7 +4320,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
 		if (mddev->gendisk)
 			trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev),
 					      align_bi, disk_devt(mddev->gendisk),
-					      raid_bio->bi_sector);
+					      raid_bio->bi_iter.bi_sector);
 		generic_make_request(align_bi);
 		return 1;
 	} else {
@@ -4373,8 +4413,7 @@ static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
 		sh->group = NULL;
 	}
 	list_del_init(&sh->lru);
-	atomic_inc(&sh->count);
-	BUG_ON(atomic_read(&sh->count) != 1);
+	BUG_ON(atomic_inc_return(&sh->count) != 1);
 	return sh;
 }
 
@@ -4404,7 +4443,7 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
 			 * STRIPE_ON_UNPLUG_LIST clear but the stripe
 			 * is still in our list
 			 */
-			smp_mb__before_clear_bit();
+			smp_mb__before_atomic();
 			clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state);
 			/*
 			 * STRIPE_ON_RELEASE_LIST could be set here. In that
@@ -4463,8 +4502,8 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
 		/* Skip discard while reshape is happening */
 		return;
 
-	logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
-	last_sector = bi->bi_sector + (bi->bi_size>>9);
+	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+	last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9);
 
 	bi->bi_next = NULL;
 	bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
@@ -4550,6 +4589,8 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 	struct stripe_head *sh;
 	const int rw = bio_data_dir(bi);
 	int remaining;
+	DEFINE_WAIT(w);
+	bool do_prepare;
 
 	if (unlikely(bi->bi_rw & REQ_FLUSH)) {
 		md_flush_request(mddev, bi);
@@ -4568,20 +4609,23 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 		return;
 	}
 
-	logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
 	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
 	bi->bi_phys_segments = 1;	/* over-loaded to count active stripes */
 
+	prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
 	for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
-		DEFINE_WAIT(w);
 		int previous;
 		int seq;
 
+		do_prepare = false;
 	retry:
 		seq = read_seqcount_begin(&conf->gen_lock);
 		previous = 0;
-		prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
+		if (do_prepare)
+			prepare_to_wait(&conf->wait_for_overlap, &w,
+				TASK_UNINTERRUPTIBLE);
 		if (unlikely(conf->reshape_progress != MaxSector)) {
 			/* spinlock is needed as reshape_progress may be
 			 * 64bit on a 32bit platform, and so it might be
@@ -4602,6 +4646,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 				    : logical_sector >= conf->reshape_safe) {
 					spin_unlock_irq(&conf->device_lock);
 					schedule();
+					do_prepare = true;
 					goto retry;
 				}
 			}
@@ -4638,6 +4683,7 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 				if (must_retry) {
 					release_stripe(sh);
 					schedule();
+					do_prepare = true;
 					goto retry;
 				}
 			}
@@ -4661,8 +4707,10 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 				prepare_to_wait(&conf->wait_for_overlap,
 						&w, TASK_INTERRUPTIBLE);
 				if (logical_sector >= mddev->suspend_lo &&
-				    logical_sector < mddev->suspend_hi)
+				    logical_sector < mddev->suspend_hi) {
 					schedule();
+					do_prepare = true;
+				}
 				goto retry;
 			}
 
@@ -4675,9 +4723,9 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 				md_wakeup_thread(mddev->thread);
 				release_stripe(sh);
 				schedule();
+				do_prepare = true;
 				goto retry;
 			}
-			finish_wait(&conf->wait_for_overlap, &w);
 			set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			if ((bi->bi_rw & REQ_SYNC) &&
@@ -4687,10 +4735,10 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 		} else {
 			/* cannot get stripe for read-ahead, just give-up */
 			clear_bit(BIO_UPTODATE, &bi->bi_flags);
-			finish_wait(&conf->wait_for_overlap, &w);
 			break;
 		}
 	}
+	finish_wait(&conf->wait_for_overlap, &w);
 
 	remaining = raid5_dec_bi_active_stripes(bi);
 	if (remaining == 0) {
@@ -5026,8 +5074,8 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int
 	bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
 
 	set_bit(STRIPE_SYNC_REQUESTED, &sh->state);
+	set_bit(STRIPE_HANDLE, &sh->state);
 
-	handle_stripe(sh);
 	release_stripe(sh);
 
 	return STRIPE_SECTORS;
@@ -5052,7 +5100,8 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 	int remaining;
 	int handled = 0;
 
-	logical_sector = raid_bio->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+	logical_sector = raid_bio->bi_iter.bi_sector &
+		~((sector_t)STRIPE_SECTORS-1);
 	sector = raid5_compute_sector(conf, logical_sector,
 				      0, &dd_idx, NULL);
 	last_sector = bio_end_sector(raid_bio);
@@ -5066,7 +5115,7 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 			/* already done this stripe */
 			continue;
 
-		sh = get_active_stripe(conf, sector, 0, 1, 0);
+		sh = get_active_stripe(conf, sector, 0, 1, 1);
 
 		if (!sh) {
 			/* failed to get a stripe - must wait */
@@ -5349,6 +5398,50 @@ raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
 					raid5_store_preread_threshold);
 
 static ssize_t
+raid5_show_skip_copy(struct mddev *mddev, char *page)
+{
+	struct r5conf *conf = mddev->private;
+	if (conf)
+		return sprintf(page, "%d\n", conf->skip_copy);
+	else
+		return 0;
+}
+
+static ssize_t
+raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
+{
+	struct r5conf *conf = mddev->private;
+	unsigned long new;
+	if (len >= PAGE_SIZE)
+		return -EINVAL;
+	if (!conf)
+		return -ENODEV;
+
+	if (kstrtoul(page, 10, &new))
+		return -EINVAL;
+	new = !!new;
+	if (new == conf->skip_copy)
+		return len;
+
+	mddev_suspend(mddev);
+	conf->skip_copy = new;
+	if (new)
+		mddev->queue->backing_dev_info.capabilities |=
+						BDI_CAP_STABLE_WRITES;
+	else
+		mddev->queue->backing_dev_info.capabilities &=
+						~BDI_CAP_STABLE_WRITES;
+	mddev_resume(mddev);
+	return len;
+}
+
+static struct md_sysfs_entry
+raid5_skip_copy = __ATTR(skip_copy, S_IRUGO | S_IWUSR,
+					raid5_show_skip_copy,
+					raid5_store_skip_copy);
+
+
+static ssize_t
 stripe_cache_active_show(struct mddev *mddev, char *page)
 {
 	struct r5conf *conf = mddev->private;
@@ -5433,6 +5526,7 @@ static struct attribute *raid5_attrs[] =  {
 	&raid5_stripecache_active.attr,
 	&raid5_preread_bypass_threshold.attr,
 	&raid5_group_thread_cnt.attr,
+	&raid5_skip_copy.attr,
 	NULL,
 };
 static struct attribute_group raid5_attrs_group = {
@@ -5511,23 +5605,43 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks)
 	return sectors * (raid_disks - conf->max_degraded);
 }
 
+static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+	safe_put_page(percpu->spare_page);
+	kfree(percpu->scribble);
+	percpu->spare_page = NULL;
+	percpu->scribble = NULL;
+}
+
+static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+	if (conf->level == 6 && !percpu->spare_page)
+		percpu->spare_page = alloc_page(GFP_KERNEL);
+	if (!percpu->scribble)
+		percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
+
+	if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
+		free_scratch_buffer(conf, percpu);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static void raid5_free_percpu(struct r5conf *conf)
 {
-	struct raid5_percpu *percpu;
 	unsigned long cpu;
 
 	if (!conf->percpu)
 		return;
 
-	get_online_cpus();
-	for_each_possible_cpu(cpu) {
-		percpu = per_cpu_ptr(conf->percpu, cpu);
-		safe_put_page(percpu->spare_page);
-		kfree(percpu->scribble);
-	}
 #ifdef CONFIG_HOTPLUG_CPU
 	unregister_cpu_notifier(&conf->cpu_notify);
 #endif
+
+	get_online_cpus();
+	for_each_possible_cpu(cpu)
+		free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
 	put_online_cpus();
 
 	free_percpu(conf->percpu);
@@ -5554,15 +5668,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		if (conf->level == 6 && !percpu->spare_page)
-			percpu->spare_page = alloc_page(GFP_KERNEL);
-		if (!percpu->scribble)
-			percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
-
-		if (!percpu->scribble ||
-		    (conf->level == 6 && !percpu->spare_page)) {
-			safe_put_page(percpu->spare_page);
-			kfree(percpu->scribble);
+		if (alloc_scratch_buffer(conf, percpu)) {
 			pr_err("%s: failed memory allocation for cpu%ld\n",
 			       __func__, cpu);
 			return notifier_from_errno(-ENOMEM);
@@ -5570,10 +5676,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		safe_put_page(percpu->spare_page);
-		kfree(percpu->scribble);
-		percpu->spare_page = NULL;
-		percpu->scribble = NULL;
+		free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
 		break;
 	default:
 		break;
@@ -5585,40 +5688,29 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
 static int raid5_alloc_percpu(struct r5conf *conf)
 {
 	unsigned long cpu;
-	struct page *spare_page;
-	struct raid5_percpu __percpu *allcpus;
-	void *scribble;
-	int err;
+	int err = 0;
 
-	allcpus = alloc_percpu(struct raid5_percpu);
-	if (!allcpus)
+	conf->percpu = alloc_percpu(struct raid5_percpu);
+	if (!conf->percpu)
 		return -ENOMEM;
-	conf->percpu = allcpus;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	conf->cpu_notify.notifier_call = raid456_cpu_notify;
+	conf->cpu_notify.priority = 0;
+	err = register_cpu_notifier(&conf->cpu_notify);
+	if (err)
+		return err;
+#endif
 
 	get_online_cpus();
-	err = 0;
 	for_each_present_cpu(cpu) {
-		if (conf->level == 6) {
-			spare_page = alloc_page(GFP_KERNEL);
-			if (!spare_page) {
-				err = -ENOMEM;
-				break;
-			}
-			per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
-		}
-		scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
-		if (!scribble) {
-			err = -ENOMEM;
+		err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
+		if (err) {
+			pr_err("%s: failed memory allocation for cpu%ld\n",
+			       __func__, cpu);
 			break;
 		}
-		per_cpu_ptr(conf->percpu, cpu)->scribble = scribble;
 	}
-#ifdef CONFIG_HOTPLUG_CPU
-	conf->cpu_notify.notifier_call = raid456_cpu_notify;
-	conf->cpu_notify.priority = 0;
-	if (err == 0)
-		err = register_cpu_notifier(&conf->cpu_notify);
-#endif
 	put_online_cpus();
 
 	return err;
@@ -6100,6 +6192,7 @@ static int run(struct mddev *mddev)
 		blk_queue_io_min(mddev->queue, chunk_size);
 		blk_queue_io_opt(mddev->queue, chunk_size *
 				 (conf->raid_disks - conf->max_degraded));
+		mddev->queue->limits.raid_partial_stripes_expensive = 1;
 		/*
 		 * We can only discard a whole stripe. It doesn't make sense to
 		 * discard data disk but write parity disk