1 files changed, 168 insertions, 49 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 538cbc725620..03252af8c82c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -20,6 +20,7 @@
 #include <linux/blk-mq.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
+#include <linux/pagemap.h>
 #include <linux/kernel_stat.h>
 #include <linux/string.h>
 #include <linux/init.h>
@@ -38,6 +39,8 @@
 #include <linux/debugfs.h>
 #include <linux/bpf.h>
 #include <linux/psi.h>
+#include <linux/sched/sysctl.h>
+#include <linux/blk-crypto.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
@@ -120,6 +123,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->start_time_ns = ktime_get_ns();
 	rq->part = NULL;
 	refcount_set(&rq->ref, 1);
+	blk_crypto_rq_set_defaults(rq);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -135,6 +139,7 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(ZONE_OPEN),
 	REQ_OP_NAME(ZONE_CLOSE),
 	REQ_OP_NAME(ZONE_FINISH),
+	REQ_OP_NAME(ZONE_APPEND),
 	REQ_OP_NAME(WRITE_SAME),
 	REQ_OP_NAME(WRITE_ZEROES),
 	REQ_OP_NAME(SCSI_IN),
@@ -240,6 +245,17 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 
 	bio_advance(bio, nbytes);
 
+	if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) {
+		/*
+		 * Partial zone append completions cannot be supported as the
+		 * BIO fragments may end up not being written sequentially.
+		 */
+		if (bio->bi_iter.bi_size)
+			bio->bi_status = BLK_STS_IOERR;
+		else
+			bio->bi_iter.bi_sector = rq->__sector;
+	}
+
 	/* don't actually finish bio if it's part of flush sequence */
 	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
 		bio_endio(bio);
@@ -621,6 +637,16 @@ void blk_put_request(struct request *req)
 }
 EXPORT_SYMBOL(blk_put_request);
 
+static void blk_account_io_merge_bio(struct request *req)
+{
+	if (!blk_do_io_stat(req))
+		return;
+
+	part_stat_lock();
+	part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
+	part_stat_unlock();
+}
+
 bool bio_attempt_back_merge(struct request *req, struct bio *bio,
 		unsigned int nr_segs)
 {
@@ -639,7 +665,9 @@ bool bio_attempt_back_merge(struct request *req, struct bio *bio,
 	req->biotail = bio;
 	req->__data_len += bio->bi_iter.bi_size;
 
-	blk_account_io_start(req, false);
+	bio_crypt_free_ctx(bio);
+
+	blk_account_io_merge_bio(req);
 	return true;
 }
 
@@ -663,7 +691,9 @@ bool bio_attempt_front_merge(struct request *req, struct bio *bio,
 	req->__sector = bio->bi_iter.bi_sector;
 	req->__data_len += bio->bi_iter.bi_size;
 
-	blk_account_io_start(req, false);
+	bio_crypt_do_front_merge(req, bio);
+
+	blk_account_io_merge_bio(req);
 	return true;
 }
 
@@ -685,7 +715,7 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
 	req->__data_len += bio->bi_iter.bi_size;
 	req->nr_phys_segments = segments + 1;
 
-	blk_account_io_start(req, false);
+	blk_account_io_merge_bio(req);
 	return true;
 no_merge:
 	req_set_nomerge(q, req);
@@ -887,6 +917,41 @@ out:
 	return ret;
 }
 
+/*
+ * Check write append to a zoned block device.
+ */
+static inline blk_status_t blk_check_zone_append(struct request_queue *q,
+						 struct bio *bio)
+{
+	sector_t pos = bio->bi_iter.bi_sector;
+	int nr_sectors = bio_sectors(bio);
+
+	/* Only applicable to zoned block devices */
+	if (!blk_queue_is_zoned(q))
+		return BLK_STS_NOTSUPP;
+
+	/* The bio sector must point to the start of a sequential zone */
+	if (pos & (blk_queue_zone_sectors(q) - 1) ||
+	    !blk_queue_zone_is_seq(q, pos))
+		return BLK_STS_IOERR;
+
+	/*
+	 * Not allowed to cross zone boundaries. Otherwise, the BIO will be
+	 * split and could result in non-contiguous sectors being written in
+	 * different zones.
+	 */
+	if (nr_sectors > q->limits.chunk_sectors)
+		return BLK_STS_IOERR;
+
+	/* Make sure the BIO is small enough and will not get split */
+	if (nr_sectors > q->limits.max_zone_append_sectors)
+		return BLK_STS_IOERR;
+
+	bio->bi_opf |= REQ_NOMERGE;
+
+	return BLK_STS_OK;
+}
+
 static noinline_for_stack bool
 generic_make_request_checks(struct bio *bio)
 {
@@ -907,14 +972,11 @@ generic_make_request_checks(struct bio *bio)
 	}
 
 	/*
-	 * Non-mq queues do not honor REQ_NOWAIT, so complete a bio
-	 * with BLK_STS_AGAIN status in order to catch -EAGAIN and
-	 * to give a chance to the caller to repeat request gracefully.
+	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
+	 * if queue is not a request based queue.
 	 */
-	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) {
-		status = BLK_STS_AGAIN;
-		goto end_io;
-	}
+	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
+		goto not_supported;
 
 	if (should_fail_bio(bio))
 		goto end_io;
@@ -959,6 +1021,11 @@ generic_make_request_checks(struct bio *bio)
 		if (!q->limits.max_write_same_sectors)
 			goto not_supported;
 		break;
+	case REQ_OP_ZONE_APPEND:
+		status = blk_check_zone_append(q, bio);
+		if (status != BLK_STS_OK)
+			goto end_io;
+		break;
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
@@ -1007,6 +1074,20 @@ end_io:
 	return false;
 }
 
+static blk_qc_t do_make_request(struct bio *bio)
+{
+	struct request_queue *q = bio->bi_disk->queue;
+	blk_qc_t ret = BLK_QC_T_NONE;
+
+	if (blk_crypto_bio_prep(&bio)) {
+		if (!q->make_request_fn)
+			return blk_mq_make_request(q, bio);
+		ret = q->make_request_fn(q, bio);
+	}
+	blk_queue_exit(q);
+	return ret;
+}
+
 /**
  * generic_make_request - re-submit a bio to the block device layer for I/O
  * @bio:  The bio describing the location in memory and on the device.
@@ -1072,12 +1153,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 			/* 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]);
-			if (q->make_request_fn)
-				ret = q->make_request_fn(q, bio);
-			else
-				ret = blk_mq_make_request(q, bio);
-
-			blk_queue_exit(q);
+			ret = do_make_request(bio);
 
 			/* sort new bios into those for a lower level
 			 * and those for the same level
@@ -1114,7 +1190,6 @@ EXPORT_SYMBOL(generic_make_request);
 blk_qc_t direct_make_request(struct bio *bio)
 {
 	struct request_queue *q = bio->bi_disk->queue;
-	blk_qc_t ret;
 
 	if (WARN_ON_ONCE(q->make_request_fn)) {
 		bio_io_error(bio);
@@ -1124,9 +1199,11 @@ blk_qc_t direct_make_request(struct bio *bio)
 		return BLK_QC_T_NONE;
 	if (unlikely(bio_queue_enter(bio)))
 		return BLK_QC_T_NONE;
-	ret = blk_mq_make_request(q, bio);
-	blk_queue_exit(q);
-	return ret;
+	if (!blk_crypto_bio_prep(&bio)) {
+		blk_queue_exit(q);
+		return BLK_QC_T_NONE;
+	}
+	return blk_mq_make_request(q, bio);
 }
 EXPORT_SYMBOL_GPL(direct_make_request);
 
@@ -1256,8 +1333,11 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	    should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
+	if (blk_crypto_insert_cloned_request(rq))
+		return BLK_STS_IOERR;
+
 	if (blk_queue_io_stat(q))
-		blk_account_io_start(rq, true);
+		blk_account_io_start(rq);
 
 	/*
 	 * Since we have a scheduler attached on the top device,
@@ -1309,7 +1389,22 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 
-void blk_account_io_completion(struct request *req, unsigned int bytes)
+static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end)
+{
+	unsigned long stamp;
+again:
+	stamp = READ_ONCE(part->stamp);
+	if (unlikely(stamp != now)) {
+		if (likely(cmpxchg(&part->stamp, stamp, now) == stamp))
+			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
+	}
+	if (part->partno) {
+		part = &part_to_disk(part)->part0;
+		goto again;
+	}
+}
+
+static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (req->part && blk_do_io_stat(req)) {
 		const int sgrp = op_stat_group(req_op(req));
@@ -1340,48 +1435,57 @@ void blk_account_io_done(struct request *req, u64 now)
 		update_io_ticks(part, jiffies, true);
 		part_stat_inc(part, ios[sgrp]);
 		part_stat_add(part, nsecs[sgrp], now - req->start_time_ns);
-		part_dec_in_flight(req->q, part, rq_data_dir(req));
+		part_stat_unlock();
 
 		hd_struct_put(part);
-		part_stat_unlock();
 	}
 }
 
-void blk_account_io_start(struct request *rq, bool new_io)
+void blk_account_io_start(struct request *rq)
 {
-	struct hd_struct *part;
-	int rw = rq_data_dir(rq);
-
 	if (!blk_do_io_stat(rq))
 		return;
 
+	rq->part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
+
 	part_stat_lock();
+	update_io_ticks(rq->part, jiffies, false);
+	part_stat_unlock();
+}
 
-	if (!new_io) {
-		part = rq->part;
-		part_stat_inc(part, merges[rw]);
-	} else {
-		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
-		if (!hd_struct_try_get(part)) {
-			/*
-			 * The partition is already being removed,
-			 * the request will be accounted on the disk only
-			 *
-			 * We take a reference on disk->part0 although that
-			 * partition will never be deleted, so we can treat
-			 * it as any other partition.
-			 */
-			part = &rq->rq_disk->part0;
-			hd_struct_get(part);
-		}
-		part_inc_in_flight(rq->q, part, rw);
-		rq->part = part;
-	}
+unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
+		unsigned int op)
+{
+	struct hd_struct *part = &disk->part0;
+	const int sgrp = op_stat_group(op);
+	unsigned long now = READ_ONCE(jiffies);
+
+	part_stat_lock();
+	update_io_ticks(part, now, false);
+	part_stat_inc(part, ios[sgrp]);
+	part_stat_add(part, sectors[sgrp], sectors);
+	part_stat_local_inc(part, in_flight[op_is_write(op)]);
+	part_stat_unlock();
 
-	update_io_ticks(part, jiffies, false);
+	return now;
+}
+EXPORT_SYMBOL(disk_start_io_acct);
 
+void disk_end_io_acct(struct gendisk *disk, unsigned int op,
+		unsigned long start_time)
+{
+	struct hd_struct *part = &disk->part0;
+	const int sgrp = op_stat_group(op);
+	unsigned long now = READ_ONCE(jiffies);
+	unsigned long duration = now - start_time;
+
+	part_stat_lock();
+	update_io_ticks(part, now, true);
+	part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration));
+	part_stat_local_dec(part, in_flight[op_is_write(op)]);
 	part_stat_unlock();
 }
+EXPORT_SYMBOL(disk_end_io_acct);
 
 /*
  * Steal bios from a request and add them to a bio list.
@@ -1632,6 +1736,9 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 	rq->nr_phys_segments = rq_src->nr_phys_segments;
 	rq->ioprio = rq_src->ioprio;
 
+	if (rq->bio)
+		blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask);
+
 	return 0;
 
 free_and_out:
@@ -1772,6 +1879,18 @@ void blk_finish_plug(struct blk_plug *plug)
 }
 EXPORT_SYMBOL(blk_finish_plug);
 
+void blk_io_schedule(void)
+{
+	/* Prevent hang_check timer from firing at us during very long I/O */
+	unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2;
+
+	if (timeout)
+		io_schedule_timeout(timeout);
+	else
+		io_schedule();
+}
+EXPORT_SYMBOL_GPL(blk_io_schedule);
+
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS));