Merge tag 'for-6.19/block-20251201' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block updates from Jens Axboe:

 - Fix head insertion for mq-deadline, a regression from when priority
   support was added

 - Series simplifying and improving the ublk user copy code

 - Various ublk related cleanups

 - Fixup REQ_NOWAIT handling in loop/zloop, clearing NOWAIT when the
   request is punted to a thread for handling

 - Merge and then later revert loop dio nowait support, as it ended up
   causing excessive stack usage for when the inline issue code needs to
   dip back into the full file system code

 - Improve auto integrity code, making it less deadlock prone

 - Speedup polled IO handling, but manually managing the hctx lookups

 - Fixes for blk-throttle for SSD devices

 - Small series with fixes for the S390 dasd driver

 - Add support for caching zones, avoiding unnecessary report zone
   queries

 - MD pull requests via Yu:
      - fix null-ptr-dereference regression for dm-raid0
      - fix IO hang for raid5 when array is broken with IO inflight
      - remove legacy 1s delay to speed up system shutdown
      - change maintainer's email address
      - data can be lost if array is created with different lbs devices,
        fix this problem and record lbs of the array in metadata
      - fix rcu protection for md_thread
      - fix mddev kobject lifetime regression
      - enable atomic writes for md-linear
      - some cleanups

 - bcache updates via Coly
      - remove useless discard and cache device code
      - improve usage of per-cpu workqueues

 - Reorganize the IO scheduler switching code, fixing some lockdep
   reports as well

 - Improve the block layer P2P DMA support

 - Add support to the block tracing code for zoned devices

 - Segment calculation improves, and memory alignment flexibility
   improvements

 - Set of prep and cleanups patches for ublk batching support. The
   actual batching hasn't been added yet, but helps shrink down the
   workload of getting that patchset ready for 6.20

 - Fix for how the ps3 block driver handles segments offsets

 - Improve how block plugging handles batch tag allocations

 - nbd fixes for use-after-free of the configuration on device clear/put

 - Set of improvements and fixes for zloop

 - Add Damien as maintainer of the block zoned device code handling

 - Various other fixes and cleanups

* tag 'for-6.19/block-20251201' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (162 commits)
  block/rnbd: correct all kernel-doc complaints
  blk-mq: use queue_hctx in blk_mq_map_queue_type
  md: remove legacy 1s delay in md_notify_reboot
  md/raid5: fix IO hang when array is broken with IO inflight
  md: warn about updating super block failure
  md/raid0: fix NULL pointer dereference in create_strip_zones() for dm-raid
  sbitmap: fix all kernel-doc warnings
  ublk: add helper of __ublk_fetch()
  ublk: pass const pointer to ublk_queue_is_zoned()
  ublk: refactor auto buffer register in ublk_dispatch_req()
  ublk: add `union ublk_io_buf` with improved naming
  ublk: add parameter `struct io_uring_cmd *` to ublk_prep_auto_buf_reg()
  kfifo: add kfifo_alloc_node() helper for NUMA awareness
  blk-mq: fix potential uaf for 'queue_hw_ctx'
  blk-mq: use array manage hctx map instead of xarray
  ublk: prevent invalid access with DEBUG
  s390/dasd: Use scnprintf() instead of sprintf()
  s390/dasd: Move device name formatting into separate function
  s390/dasd: Remove unnecessary debugfs_create() return checks
  s390/dasd: Fix gendisk parent after copy pair swap
  ...

1 files changed, 414 insertions, 119 deletions

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 6941145b5058..af8cbc8e1a7c 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -63,13 +63,116 @@ static int blk_probes_ref;
 static void blk_register_tracepoints(void);
 static void blk_unregister_tracepoints(void);
 
+static void record_blktrace_event(struct blk_io_trace *t, pid_t pid, int cpu,
+				  sector_t sector, int bytes, u64 what,
+				  dev_t dev, int error, u64 cgid,
+				  ssize_t cgid_len, void *pdu_data, int pdu_len)
+
+{
+	/*
+	 * These two are not needed in ftrace as they are in the
+	 * generic trace_entry, filled by tracing_generic_entry_update,
+	 * but for the trace_event->bin() synthesizer benefit we do it
+	 * here too.
+	 */
+	t->cpu = cpu;
+	t->pid = pid;
+
+	t->sector = sector;
+	t->bytes = bytes;
+	t->action = lower_32_bits(what);
+	t->device = dev;
+	t->error = error;
+	t->pdu_len = pdu_len + cgid_len;
+
+	if (cgid_len)
+		memcpy((void *)t + sizeof(*t), &cgid, cgid_len);
+	if (pdu_len)
+		memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len);
+}
+
+static void record_blktrace_event2(struct blk_io_trace2 *t2, pid_t pid, int cpu,
+				   sector_t sector, int bytes, u64 what,
+				   dev_t dev, int error, u64 cgid,
+				   ssize_t cgid_len, void *pdu_data,
+				   int pdu_len)
+{
+	t2->pid = pid;
+	t2->cpu = cpu;
+
+	t2->sector = sector;
+	t2->bytes = bytes;
+	t2->action = what;
+	t2->device = dev;
+	t2->error = error;
+	t2->pdu_len = pdu_len + cgid_len;
+
+	if (cgid_len)
+		memcpy((void *)t2 + sizeof(*t2), &cgid, cgid_len);
+	if (pdu_len)
+		memcpy((void *)t2 + sizeof(*t2) + cgid_len, pdu_data, pdu_len);
+}
+
+static void relay_blktrace_event1(struct blk_trace *bt, unsigned long sequence,
+				 pid_t pid, int cpu, sector_t sector, int bytes,
+				 u64 what, int error, u64 cgid,
+				 ssize_t cgid_len, void *pdu_data, int pdu_len)
+{
+	struct blk_io_trace *t;
+	size_t trace_len = sizeof(*t) + pdu_len + cgid_len;
+
+	t = relay_reserve(bt->rchan, trace_len);
+	if (!t)
+		return;
+
+	t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
+	t->sequence = sequence;
+	t->time = ktime_to_ns(ktime_get());
+
+	record_blktrace_event(t, pid, cpu, sector, bytes, what, bt->dev, error,
+			      cgid, cgid_len, pdu_data, pdu_len);
+}
+
+static void relay_blktrace_event2(struct blk_trace *bt, unsigned long sequence,
+				  pid_t pid, int cpu, sector_t sector,
+				  int bytes, u64 what, int error, u64 cgid,
+				  ssize_t cgid_len, void *pdu_data, int pdu_len)
+{
+	struct blk_io_trace2 *t;
+	size_t trace_len = sizeof(struct blk_io_trace2) + pdu_len + cgid_len;
+
+	t = relay_reserve(bt->rchan, trace_len);
+	if (!t)
+		return;
+
+	t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE2_VERSION;
+	t->sequence = sequence;
+	t->time = ktime_to_ns(ktime_get());
+
+	record_blktrace_event2(t, pid, cpu, sector, bytes, what, bt->dev, error,
+			       cgid, cgid_len, pdu_data, pdu_len);
+}
+
+static void relay_blktrace_event(struct blk_trace *bt, unsigned long sequence,
+				 pid_t pid, int cpu, sector_t sector, int bytes,
+				 u64 what, int error, u64 cgid,
+				 ssize_t cgid_len, void *pdu_data, int pdu_len)
+{
+	if (bt->version == 2)
+		return relay_blktrace_event2(bt, sequence, pid, cpu, sector,
+					     bytes, what, error, cgid, cgid_len,
+					     pdu_data, pdu_len);
+	return relay_blktrace_event1(bt, sequence, pid, cpu, sector, bytes,
+				     what, error, cgid, cgid_len, pdu_data,
+				     pdu_len);
+}
+
 /*
  * Send out a notify message.
  */
-static void trace_note(struct blk_trace *bt, pid_t pid, int action,
+static void trace_note(struct blk_trace *bt, pid_t pid, u64 action,
 		       const void *data, size_t len, u64 cgid)
 {
-	struct blk_io_trace *t;
 	struct ring_buffer_event *event = NULL;
 	struct trace_buffer *buffer = NULL;
 	unsigned int trace_ctx = 0;
@@ -77,38 +180,30 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 	bool blk_tracer = blk_tracer_enabled;
 	ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
 
+	action = lower_32_bits(action | (cgid ? __BLK_TN_CGROUP : 0));
 	if (blk_tracer) {
+		struct blk_io_trace2 *t;
+		size_t trace_len = sizeof(*t) + cgid_len + len;
+
 		buffer = blk_tr->array_buffer.buffer;
 		trace_ctx = tracing_gen_ctx_flags(0);
 		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
-						  sizeof(*t) + len + cgid_len,
-						  trace_ctx);
+						  trace_len, trace_ctx);
 		if (!event)
 			return;
 		t = ring_buffer_event_data(event);
-		goto record_it;
+		record_blktrace_event2(t, pid, cpu, 0, 0,
+				       action, bt->dev, 0, cgid, cgid_len,
+				       (void *)data, len);
+		trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx);
+		return;
 	}
 
 	if (!bt->rchan)
 		return;
 
-	t = relay_reserve(bt->rchan, sizeof(*t) + len + cgid_len);
-	if (t) {
-		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
-		t->time = ktime_to_ns(ktime_get());
-record_it:
-		t->device = bt->dev;
-		t->action = action | (cgid ? __BLK_TN_CGROUP : 0);
-		t->pid = pid;
-		t->cpu = cpu;
-		t->pdu_len = len + cgid_len;
-		if (cgid_len)
-			memcpy((void *)t + sizeof(*t), &cgid, cgid_len);
-		memcpy((void *) t + sizeof(*t) + cgid_len, data, len);
-
-		if (blk_tracer)
-			trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx);
-	}
+	relay_blktrace_event(bt, 0, pid, cpu, 0, 0, action, 0, cgid,
+			     cgid_len, (void *)data, len);
 }
 
 /*
@@ -182,7 +277,7 @@ void __blk_trace_note_message(struct blk_trace *bt,
 }
 EXPORT_SYMBOL_GPL(__blk_trace_note_message);
 
-static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
+static int act_log_check(struct blk_trace *bt, u64 what, sector_t sector,
 			 pid_t pid)
 {
 	if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
@@ -213,13 +308,12 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
  * blk_io_trace structure and places it in a per-cpu subbuffer.
  */
 static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
-			    const blk_opf_t opf, u32 what, int error,
+			    const blk_opf_t opf, u64 what, int error,
 			    int pdu_len, void *pdu_data, u64 cgid)
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
 	struct trace_buffer *buffer = NULL;
-	struct blk_io_trace *t;
 	unsigned long flags = 0;
 	unsigned long *sequence;
 	unsigned int trace_ctx = 0;
@@ -228,6 +322,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	bool blk_tracer = blk_tracer_enabled;
 	ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
 	const enum req_op op = opf & REQ_OP_MASK;
+	size_t trace_len;
 
 	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
@@ -238,10 +333,47 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(opf, META);
 	what |= MASK_TC_BIT(opf, PREFLUSH);
 	what |= MASK_TC_BIT(opf, FUA);
-	if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
+
+	switch (op) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
-	if (op == REQ_OP_FLUSH)
+		break;
+	case REQ_OP_FLUSH:
 		what |= BLK_TC_ACT(BLK_TC_FLUSH);
+		break;
+	case REQ_OP_ZONE_APPEND:
+		what |= BLK_TC_ACT(BLK_TC_ZONE_APPEND);
+		break;
+	case REQ_OP_ZONE_RESET:
+		what |= BLK_TC_ACT(BLK_TC_ZONE_RESET);
+		break;
+	case REQ_OP_ZONE_RESET_ALL:
+		what |= BLK_TC_ACT(BLK_TC_ZONE_RESET_ALL);
+		break;
+	case REQ_OP_ZONE_FINISH:
+		what |= BLK_TC_ACT(BLK_TC_ZONE_FINISH);
+		break;
+	case REQ_OP_ZONE_OPEN:
+		what |= BLK_TC_ACT(BLK_TC_ZONE_OPEN);
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		what |= BLK_TC_ACT(BLK_TC_ZONE_CLOSE);
+		break;
+	case REQ_OP_WRITE_ZEROES:
+		what |= BLK_TC_ACT(BLK_TC_WRITE_ZEROES);
+		break;
+	default:
+		break;
+	}
+
+	/* Drop trace events for zone operations with blktrace v1 */
+	if (bt->version == 1 && (what >> BLK_TC_SHIFT) > BLK_TC_END_V1) {
+		pr_debug_ratelimited("blktrace v1 cannot trace zone operation 0x%llx\n",
+				(unsigned long long)what);
+		return;
+	}
+
 	if (cgid)
 		what |= __BLK_TA_CGROUP;
 
@@ -255,13 +387,68 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 
 		buffer = blk_tr->array_buffer.buffer;
 		trace_ctx = tracing_gen_ctx_flags(0);
+		switch (bt->version) {
+		case 1:
+			trace_len = sizeof(struct blk_io_trace);
+			break;
+		case 2:
+		default:
+			/*
+			 * ftrace always uses v2 (blk_io_trace2) format.
+			 *
+			 * For sysfs-enabled tracing path (enabled via
+			 * /sys/block/DEV/trace/enable), blk_trace_setup_queue()
+			 * never initializes bt->version, leaving it 0 from
+			 * kzalloc(). We must handle version==0 safely here.
+			 *
+			 * Fall through to default to ensure we never hit the
+			 * old bug where default set trace_len=0, causing
+			 * buffer underflow and memory corruption.
+			 *
+			 * Always use v2 format for ftrace and normalize
+			 * bt->version to 2 when uninitialized.
+			 */
+			trace_len = sizeof(struct blk_io_trace2);
+			if (bt->version == 0)
+				bt->version = 2;
+			break;
+		}
+		trace_len += pdu_len + cgid_len;
 		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
-						  sizeof(*t) + pdu_len + cgid_len,
-						  trace_ctx);
+						  trace_len, trace_ctx);
 		if (!event)
 			return;
-		t = ring_buffer_event_data(event);
-		goto record_it;
+
+		switch (bt->version) {
+		case 1:
+			record_blktrace_event(ring_buffer_event_data(event),
+					      pid, cpu, sector, bytes,
+					      what, bt->dev, error, cgid, cgid_len,
+					      pdu_data, pdu_len);
+			break;
+		case 2:
+		default:
+			/*
+			 * Use v2 recording function (record_blktrace_event2)
+			 * which writes blk_io_trace2 structure with correct
+			 * field layout:
+			 *   - 32-bit pid at offset 28
+			 *   - 64-bit action at offset 32
+			 *
+			 * Fall through to default handles version==0 case
+			 * (from sysfs path), ensuring we always use correct
+			 * v2 recording function to match the v2 buffer
+			 * allocated above.
+			 */
+			record_blktrace_event2(ring_buffer_event_data(event),
+					       pid, cpu, sector, bytes,
+					       what, bt->dev, error, cgid, cgid_len,
+					       pdu_data, pdu_len);
+			break;
+		}
+
+		trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx);
+		return;
 	}
 
 	if (unlikely(tsk->btrace_seq != blktrace_seq))
@@ -273,41 +460,10 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	 * from coming in and stepping on our toes.
 	 */
 	local_irq_save(flags);
-	t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len + cgid_len);
-	if (t) {
-		sequence = per_cpu_ptr(bt->sequence, cpu);
-
-		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
-		t->sequence = ++(*sequence);
-		t->time = ktime_to_ns(ktime_get());
-record_it:
-		/*
-		 * These two are not needed in ftrace as they are in the
-		 * generic trace_entry, filled by tracing_generic_entry_update,
-		 * but for the trace_event->bin() synthesizer benefit we do it
-		 * here too.
-		 */
-		t->cpu = cpu;
-		t->pid = pid;
-
-		t->sector = sector;
-		t->bytes = bytes;
-		t->action = what;
-		t->device = bt->dev;
-		t->error = error;
-		t->pdu_len = pdu_len + cgid_len;
-
-		if (cgid_len)
-			memcpy((void *)t + sizeof(*t), &cgid, cgid_len);
-		if (pdu_len)
-			memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len);
-
-		if (blk_tracer) {
-			trace_buffer_unlock_commit(blk_tr, buffer, event, trace_ctx);
-			return;
-		}
-	}
-
+	sequence = per_cpu_ptr(bt->sequence, cpu);
+	(*sequence)++;
+	relay_blktrace_event(bt, *sequence, pid, cpu, sector, bytes,
+			     what, error, cgid, cgid_len, pdu_data, pdu_len);
 	local_irq_restore(flags);
 }
 
@@ -494,9 +650,10 @@ static void blk_trace_setup_lba(struct blk_trace *bt,
 /*
  * Setup everything required to start tracing
  */
-static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-			      struct block_device *bdev,
-			      struct blk_user_trace_setup *buts)
+static struct blk_trace *blk_trace_setup_prepare(struct request_queue *q,
+						 char *name, dev_t dev,
+						 u32 buf_size, u32 buf_nr,
+						 struct block_device *bdev)
 {
 	struct blk_trace *bt = NULL;
 	struct dentry *dir = NULL;
@@ -504,31 +661,19 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	lockdep_assert_held(&q->debugfs_mutex);
 
-	if (!buts->buf_size || !buts->buf_nr)
-		return -EINVAL;
-
-	strscpy_pad(buts->name, name, BLKTRACE_BDEV_SIZE);
-
-	/*
-	 * some device names have larger paths - convert the slashes
-	 * to underscores for this to work as expected
-	 */
-	strreplace(buts->name, '/', '_');
-
 	/*
 	 * bdev can be NULL, as with scsi-generic, this is a helpful as
 	 * we can be.
 	 */
 	if (rcu_dereference_protected(q->blk_trace,
 				      lockdep_is_held(&q->debugfs_mutex))) {
-		pr_warn("Concurrent blktraces are not allowed on %s\n",
-			buts->name);
-		return -EBUSY;
+		pr_warn("Concurrent blktraces are not allowed on %s\n", name);
+		return ERR_PTR(-EBUSY);
 	}
 
 	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
 	if (!bt)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	ret = -ENOMEM;
 	bt->sequence = alloc_percpu(unsigned long);
@@ -548,7 +693,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (bdev && !bdev_is_partition(bdev))
 		dir = q->debugfs_dir;
 	else
-		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
+		bt->dir = dir = debugfs_create_dir(name, blk_debugfs_root);
 
 	/*
 	 * As blktrace relies on debugfs for its interface the debugfs directory
@@ -556,8 +701,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 * files or directories.
 	 */
 	if (IS_ERR_OR_NULL(dir)) {
-		pr_warn("debugfs_dir not present for %s so skipping\n",
-			buts->name);
+		pr_warn("debugfs_dir not present for %s so skipping\n", name);
 		ret = -ENOENT;
 		goto err;
 	}
@@ -569,17 +713,40 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops);
 	debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
 
-	bt->rchan = relay_open("trace", dir, buts->buf_size,
-				buts->buf_nr, &blk_relay_callbacks, bt);
+	bt->rchan = relay_open("trace", dir, buf_size, buf_nr,
+			       &blk_relay_callbacks, bt);
 	if (!bt->rchan)
 		goto err;
 
+	blk_trace_setup_lba(bt, bdev);
+
+	return bt;
+
+err:
+	blk_trace_free(q, bt);
+
+	return ERR_PTR(ret);
+}
+
+static void blk_trace_setup_finalize(struct request_queue *q,
+				     char *name, int version,
+				     struct blk_trace *bt,
+				     struct blk_user_trace_setup2 *buts)
+
+{
+	strscpy_pad(buts->name, name, BLKTRACE_BDEV_SIZE2);
+
+	/*
+	 * some device names have larger paths - convert the slashes
+	 * to underscores for this to work as expected
+	 */
+	strreplace(buts->name, '/', '_');
+
+	bt->version = version;
 	bt->act_mask = buts->act_mask;
 	if (!bt->act_mask)
 		bt->act_mask = (u16) -1;
 
-	blk_trace_setup_lba(bt, bdev);
-
 	/* overwrite with user settings */
 	if (buts->start_lba)
 		bt->start_lba = buts->start_lba;
@@ -591,30 +758,43 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	rcu_assign_pointer(q->blk_trace, bt);
 	get_probe_ref();
-
-	ret = 0;
-err:
-	if (ret)
-		blk_trace_free(q, bt);
-	return ret;
 }
 
 int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		    struct block_device *bdev,
 		    char __user *arg)
 {
+	struct blk_user_trace_setup2 buts2;
 	struct blk_user_trace_setup buts;
+	struct blk_trace *bt;
 	int ret;
 
 	ret = copy_from_user(&buts, arg, sizeof(buts));
 	if (ret)
 		return -EFAULT;
 
+	if (!buts.buf_size || !buts.buf_nr)
+		return -EINVAL;
+
+	buts2 = (struct blk_user_trace_setup2) {
+		.act_mask = buts.act_mask,
+		.buf_size = buts.buf_size,
+		.buf_nr = buts.buf_nr,
+		.start_lba = buts.start_lba,
+		.end_lba = buts.end_lba,
+		.pid = buts.pid,
+	};
+
 	mutex_lock(&q->debugfs_mutex);
-	ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
+	bt = blk_trace_setup_prepare(q, name, dev, buts.buf_size, buts.buf_nr,
+				     bdev);
+	if (IS_ERR(bt)) {
+		mutex_unlock(&q->debugfs_mutex);
+		return PTR_ERR(bt);
+	}
+	blk_trace_setup_finalize(q, name, 1, bt, &buts2);
+	strcpy(buts.name, buts2.name);
 	mutex_unlock(&q->debugfs_mutex);
-	if (ret)
-		return ret;
 
 	if (copy_to_user(arg, &buts, sizeof(buts))) {
 		blk_trace_remove(q);
@@ -624,19 +804,54 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 }
 EXPORT_SYMBOL_GPL(blk_trace_setup);
 
+static int blk_trace_setup2(struct request_queue *q, char *name, dev_t dev,
+			    struct block_device *bdev, char __user *arg)
+{
+	struct blk_user_trace_setup2 buts2;
+	struct blk_trace *bt;
+
+	if (copy_from_user(&buts2, arg, sizeof(buts2)))
+		return -EFAULT;
+
+	if (!buts2.buf_size || !buts2.buf_nr)
+		return -EINVAL;
+
+	if (buts2.flags != 0)
+		return -EINVAL;
+
+	mutex_lock(&q->debugfs_mutex);
+	bt = blk_trace_setup_prepare(q, name, dev, buts2.buf_size, buts2.buf_nr,
+				     bdev);
+	if (IS_ERR(bt)) {
+		mutex_unlock(&q->debugfs_mutex);
+		return PTR_ERR(bt);
+	}
+	blk_trace_setup_finalize(q, name, 2, bt, &buts2);
+	mutex_unlock(&q->debugfs_mutex);
+
+	if (copy_to_user(arg, &buts2, sizeof(buts2))) {
+		blk_trace_remove(q);
+		return -EFAULT;
+	}
+	return 0;
+}
+
 #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
 static int compat_blk_trace_setup(struct request_queue *q, char *name,
 				  dev_t dev, struct block_device *bdev,
 				  char __user *arg)
 {
-	struct blk_user_trace_setup buts;
+	struct blk_user_trace_setup2 buts2;
 	struct compat_blk_user_trace_setup cbuts;
-	int ret;
+	struct blk_trace *bt;
 
 	if (copy_from_user(&cbuts, arg, sizeof(cbuts)))
 		return -EFAULT;
 
-	buts = (struct blk_user_trace_setup) {
+	if (!cbuts.buf_size || !cbuts.buf_nr)
+		return -EINVAL;
+
+	buts2 = (struct blk_user_trace_setup2) {
 		.act_mask = cbuts.act_mask,
 		.buf_size = cbuts.buf_size,
 		.buf_nr = cbuts.buf_nr,
@@ -646,12 +861,16 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name,
 	};
 
 	mutex_lock(&q->debugfs_mutex);
-	ret = do_blk_trace_setup(q, name, dev, bdev, &buts);
+	bt = blk_trace_setup_prepare(q, name, dev, buts2.buf_size, buts2.buf_nr,
+				     bdev);
+	if (IS_ERR(bt)) {
+		mutex_unlock(&q->debugfs_mutex);
+		return PTR_ERR(bt);
+	}
+	blk_trace_setup_finalize(q, name, 1, bt, &buts2);
 	mutex_unlock(&q->debugfs_mutex);
-	if (ret)
-		return ret;
 
-	if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) {
+	if (copy_to_user(arg, &buts2.name, ARRAY_SIZE(buts2.name))) {
 		blk_trace_remove(q);
 		return -EFAULT;
 	}
@@ -707,6 +926,10 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	char b[BDEVNAME_SIZE];
 
 	switch (cmd) {
+	case BLKTRACESETUP2:
+		snprintf(b, sizeof(b), "%pg", bdev);
+		ret = blk_trace_setup2(q, b, bdev->bd_dev, bdev, arg);
+		break;
 	case BLKTRACESETUP:
 		snprintf(b, sizeof(b), "%pg", bdev);
 		ret = blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
@@ -794,7 +1017,7 @@ blk_trace_request_get_cgid(struct request *rq)
  *
  **/
 static void blk_add_trace_rq(struct request *rq, blk_status_t error,
-			     unsigned int nr_bytes, u32 what, u64 cgid)
+			     unsigned int nr_bytes, u64 what, u64 cgid)
 {
 	struct blk_trace *bt;
 
@@ -846,6 +1069,22 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
 			 blk_trace_request_get_cgid(rq));
 }
 
+static void blk_add_trace_zone_update_request(void *ignore, struct request *rq)
+{
+	struct blk_trace *bt;
+
+	rcu_read_lock();
+	bt = rcu_dereference(rq->q->blk_trace);
+	if (likely(!bt) || bt->version < 2) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ZONE_APPEND,
+			 blk_trace_request_get_cgid(rq));
+}
+
 /**
  * blk_add_trace_bio - Add a trace for a bio oriented action
  * @q:		queue the io is for
@@ -858,7 +1097,7 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
  *
  **/
 static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
-			      u32 what, int error)
+			      u64 what, int error)
 {
 	struct blk_trace *bt;
 
@@ -924,7 +1163,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 	bt = rcu_dereference(q->blk_trace);
 	if (bt) {
 		__be64 rpdu = cpu_to_be64(depth);
-		u32 what;
+		u64 what;
 
 		if (explicit)
 			what = BLK_TA_UNPLUG_IO;
@@ -936,6 +1175,37 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 	rcu_read_unlock();
 }
 
+static void blk_add_trace_zone_plug(void *ignore, struct request_queue *q,
+				    unsigned int zno, sector_t sector,
+				    unsigned int sectors)
+{
+	struct blk_trace *bt;
+
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (bt && bt->version >= 2)
+		__blk_add_trace(bt, sector, sectors << SECTOR_SHIFT, 0,
+				BLK_TA_ZONE_PLUG, 0, 0, NULL, 0);
+	rcu_read_unlock();
+
+	return;
+}
+
+static void blk_add_trace_zone_unplug(void *ignore, struct request_queue *q,
+				      unsigned int zno, sector_t sector,
+				      unsigned int sectors)
+{
+	struct blk_trace *bt;
+
+	rcu_read_lock();
+	bt = rcu_dereference(q->blk_trace);
+	if (bt && bt->version >= 2)
+		__blk_add_trace(bt, sector, sectors << SECTOR_SHIFT, 0,
+				BLK_TA_ZONE_UNPLUG, 0, 0, NULL, 0);
+	rcu_read_unlock();
+	return;
+}
+
 static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu)
 {
 	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
@@ -1076,6 +1346,15 @@ static void blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_getrq(blk_add_trace_getrq, NULL);
 	WARN_ON(ret);
+	ret = register_trace_blk_zone_append_update_request_bio(
+		blk_add_trace_zone_update_request, NULL);
+	WARN_ON(ret);
+	ret = register_trace_disk_zone_wplug_add_bio(blk_add_trace_zone_plug,
+						     NULL);
+	WARN_ON(ret);
+	ret = register_trace_blk_zone_wplug_bio(blk_add_trace_zone_unplug,
+						NULL);
+	WARN_ON(ret);
 	ret = register_trace_block_plug(blk_add_trace_plug, NULL);
 	WARN_ON(ret);
 	ret = register_trace_block_unplug(blk_add_trace_unplug, NULL);
@@ -1095,6 +1374,10 @@ static void blk_unregister_tracepoints(void)
 	unregister_trace_block_split(blk_add_trace_split, NULL);
 	unregister_trace_block_unplug(blk_add_trace_unplug, NULL);
 	unregister_trace_block_plug(blk_add_trace_plug, NULL);
+	unregister_trace_blk_zone_wplug_bio(blk_add_trace_zone_unplug, NULL);
+	unregister_trace_disk_zone_wplug_add_bio(blk_add_trace_zone_plug, NULL);
+	unregister_trace_blk_zone_append_update_request_bio(
+		blk_add_trace_zone_update_request, NULL);
 	unregister_trace_block_getrq(blk_add_trace_getrq, NULL);
 	unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
 	unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
@@ -1113,7 +1396,7 @@ static void blk_unregister_tracepoints(void)
  * struct blk_io_tracer formatting routines
  */
 
-static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
+static void fill_rwbs(char *rwbs, const struct blk_io_trace2 *t)
 {
 	int i = 0;
 	int tc = t->action >> BLK_TC_SHIFT;
@@ -1128,7 +1411,10 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 
 	if (tc & BLK_TC_DISCARD)
 		rwbs[i++] = 'D';
-	else if (tc & BLK_TC_WRITE)
+	else if (tc & BLK_TC_WRITE_ZEROES) {
+		rwbs[i++] = 'W';
+		rwbs[i++] = 'Z';
+	} else if (tc & BLK_TC_WRITE)
 		rwbs[i++] = 'W';
 	else if (t->bytes)
 		rwbs[i++] = 'R';
@@ -1148,9 +1434,9 @@ out:
 }
 
 static inline
-const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent)
+const struct blk_io_trace2 *te_blk_io_trace(const struct trace_entry *ent)
 {
-	return (const struct blk_io_trace *)ent;
+	return (const struct blk_io_trace2 *)ent;
 }
 
 static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg)
@@ -1209,7 +1495,7 @@ static void blk_log_action_classic(struct trace_iterator *iter, const char *act,
 	unsigned long long ts  = iter->ts;
 	unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC);
 	unsigned secs	       = (unsigned long)ts;
-	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
+	const struct blk_io_trace2 *t = te_blk_io_trace(iter->ent);
 
 	fill_rwbs(rwbs, t);
 
@@ -1223,7 +1509,7 @@ static void blk_log_action(struct trace_iterator *iter, const char *act,
 	bool has_cg)
 {
 	char rwbs[RWBS_LEN];
-	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
+	const struct blk_io_trace2 *t = te_blk_io_trace(iter->ent);
 
 	fill_rwbs(rwbs, t);
 	if (has_cg) {
@@ -1444,7 +1730,7 @@ static enum print_line_t print_one_line(struct trace_iterator *iter,
 {
 	struct trace_array *tr = iter->tr;
 	struct trace_seq *s = &iter->seq;
-	const struct blk_io_trace *t;
+	const struct blk_io_trace2 *t;
 	u16 what;
 	bool long_act;
 	blk_log_action_t *log_action;
@@ -1481,8 +1767,8 @@ static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
 static void blk_trace_synthesize_old_trace(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
-	struct blk_io_trace *t = (struct blk_io_trace *)iter->ent;
-	const int offset = offsetof(struct blk_io_trace, sector);
+	struct blk_io_trace2 *t = (struct blk_io_trace2 *)iter->ent;
+	const int offset = offsetof(struct blk_io_trace2, sector);
 	struct blk_io_trace old = {
 		.magic	  = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION,
 		.time     = iter->ts,
@@ -1559,6 +1845,10 @@ static int __init init_blk_tracer(void)
 		return 1;
 	}
 
+	BUILD_BUG_ON(__alignof__(struct blk_user_trace_setup2) %
+		     __alignof__(long));
+	BUILD_BUG_ON(__alignof__(struct blk_io_trace2) % __alignof__(long));
+
 	return 0;
 }
 
@@ -1667,6 +1957,7 @@ static const struct {
 	{ BLK_TC_DISCARD,	"discard"	},
 	{ BLK_TC_DRV_DATA,	"drv_data"	},
 	{ BLK_TC_FUA,		"fua"		},
+	{ BLK_TC_WRITE_ZEROES,	"write-zeroes"	},
 };
 
 static int blk_trace_str2mask(const char *str)
@@ -1880,6 +2171,10 @@ void blk_fill_rwbs(char *rwbs, blk_opf_t opf)
 		rwbs[i++] = 'Z';
 		rwbs[i++] = 'C';
 		break;
+	case REQ_OP_WRITE_ZEROES:
+		rwbs[i++] = 'W';
+		rwbs[i++] = 'Z';
+		break;
 	default:
 		rwbs[i++] = 'N';
 	}