Merge tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Improve the type checking of request flags (Bart)

 - Ensure queue mapping for a single queues always picks the right queue
   (Bart)

 - Sanitize the io priority handling (Jan)

 - rq-qos race fix (Jinke)

 - Reserved tags handling improvements (John)

 - Separate memory alignment from file/disk offset aligment for O_DIRECT
   (Keith)

 - Add new ublk driver, userspace block driver using io_uring for
   communication with the userspace backend (Ming)

 - Use try_cmpxchg() to cleanup the code in various spots (Uros)

 - Finally remove bdevname() (Christoph)

 - Clean up the zoned device handling (Christoph)

 - Clean up independent access range support (Christoph)

 - Clean up and improve block sysfs handling (Christoph)

 - Clean up and improve teardown of block devices.

   This turns the usual two step process into something that is simpler
   to implement and handle in block drivers (Christoph)

 - Clean up chunk size handling (Christoph)

 - Misc cleanups and fixes (Bart, Bo, Dan, GuoYong, Jason, Keith, Liu,
   Ming, Sebastian, Yang, Ying)

* tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block: (178 commits)
  ublk_drv: fix double shift bug
  ublk_drv: make sure that correct flags(features) returned to userspace
  ublk_drv: fix error handling of ublk_add_dev
  ublk_drv: fix lockdep warning
  block: remove __blk_get_queue
  block: call blk_mq_exit_queue from disk_release for never added disks
  blk-mq: fix error handling in __blk_mq_alloc_disk
  ublk: defer disk allocation
  ublk: rewrite ublk_ctrl_get_queue_affinity to not rely on hctx->cpumask
  ublk: fold __ublk_create_dev into ublk_ctrl_add_dev
  ublk: cleanup ublk_ctrl_uring_cmd
  ublk: simplify ublk_ch_open and ublk_ch_release
  ublk: remove the empty open and release block device operations
  ublk: remove UBLK_IO_F_PREFLUSH
  ublk: add a MAINTAINERS entry
  block: don't allow the same type rq_qos add more than once
  mmc: fix disk/queue leak in case of adding disk failure
  ublk_drv: fix an IS_ERR() vs NULL check
  ublk: remove UBLK_IO_F_INTEGRITY
  ublk_drv: remove unneeded semicolon
  ...

2 files changed, 43 insertions, 58 deletions

diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 91fffdd2c7fb..277434b6c0bf 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -269,15 +269,14 @@ static void hib_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
-static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr,
-		struct hib_bio_batch *hb)
+static int hib_submit_io(blk_opf_t opf, pgoff_t page_off, void *addr,
+			 struct hib_bio_batch *hb)
 {
 	struct page *page = virt_to_page(addr);
 	struct bio *bio;
 	int error = 0;
 
-	bio = bio_alloc(hib_resume_bdev, 1, op | op_flags,
-			GFP_NOIO | __GFP_HIGH);
+	bio = bio_alloc(hib_resume_bdev, 1, opf, GFP_NOIO | __GFP_HIGH);
 	bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9);
 
 	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
@@ -317,8 +316,7 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 {
 	int error;
 
-	hib_submit_io(REQ_OP_READ, 0, swsusp_resume_block,
-		      swsusp_header, NULL);
+	hib_submit_io(REQ_OP_READ, swsusp_resume_block, swsusp_header, NULL);
 	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
 	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
@@ -331,7 +329,7 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags)
 		swsusp_header->flags = flags;
 		if (flags & SF_CRC32_MODE)
 			swsusp_header->crc32 = handle->crc32;
-		error = hib_submit_io(REQ_OP_WRITE, REQ_SYNC,
+		error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC,
 				      swsusp_resume_block, swsusp_header, NULL);
 	} else {
 		pr_err("Swap header not found!\n");
@@ -408,7 +406,7 @@ static int write_page(void *buf, sector_t offset, struct hib_bio_batch *hb)
 	} else {
 		src = buf;
 	}
-	return hib_submit_io(REQ_OP_WRITE, REQ_SYNC, offset, src, hb);
+	return hib_submit_io(REQ_OP_WRITE | REQ_SYNC, offset, src, hb);
 }
 
 static void release_swap_writer(struct swap_map_handle *handle)
@@ -1003,7 +1001,7 @@ static int get_swap_reader(struct swap_map_handle *handle,
 			return -ENOMEM;
 		}
 
-		error = hib_submit_io(REQ_OP_READ, 0, offset, tmp->map, NULL);
+		error = hib_submit_io(REQ_OP_READ, offset, tmp->map, NULL);
 		if (error) {
 			release_swap_reader(handle);
 			return error;
@@ -1027,7 +1025,7 @@ static int swap_read_page(struct swap_map_handle *handle, void *buf,
 	offset = handle->cur->entries[handle->k];
 	if (!offset)
 		return -EFAULT;
-	error = hib_submit_io(REQ_OP_READ, 0, offset, buf, hb);
+	error = hib_submit_io(REQ_OP_READ, offset, buf, hb);
 	if (error)
 		return error;
 	if (++handle->k >= MAP_PAGE_ENTRIES) {
@@ -1526,8 +1524,7 @@ int swsusp_check(void)
 	if (!IS_ERR(hib_resume_bdev)) {
 		set_blocksize(hib_resume_bdev, PAGE_SIZE);
 		clear_page(swsusp_header);
-		error = hib_submit_io(REQ_OP_READ, 0,
-					swsusp_resume_block,
+		error = hib_submit_io(REQ_OP_READ, swsusp_resume_block,
 					swsusp_header, NULL);
 		if (error)
 			goto put;
@@ -1535,7 +1532,7 @@ int swsusp_check(void)
 		if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) {
 			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
-			error = hib_submit_io(REQ_OP_WRITE, REQ_SYNC,
+			error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC,
 						swsusp_resume_block,
 						swsusp_header, NULL);
 		} else {
@@ -1586,11 +1583,11 @@ int swsusp_unmark(void)
 {
 	int error;
 
-	hib_submit_io(REQ_OP_READ, 0, swsusp_resume_block,
-		      swsusp_header, NULL);
+	hib_submit_io(REQ_OP_READ, swsusp_resume_block,
+			swsusp_header, NULL);
 	if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) {
 		memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10);
-		error = hib_submit_io(REQ_OP_WRITE, REQ_SYNC,
+		error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC,
 					swsusp_resume_block,
 					swsusp_header, NULL);
 	} else {
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index fe04c6f96ca5..7f5eb295fe19 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -205,7 +205,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
 #define BLK_TC_PREFLUSH		BLK_TC_FLUSH
 
 /* The ilog2() calls fall out because they're constant */
-#define MASK_TC_BIT(rw, __name) ((rw & REQ_ ## __name) << \
+#define MASK_TC_BIT(rw, __name) ((__force u32)(rw & REQ_ ## __name) <<	\
 	  (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - __REQ_ ## __name))
 
 /*
@@ -213,8 +213,8 @@ 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,
-		     int op, int op_flags, u32 what, int error, int pdu_len,
-		     void *pdu_data, u64 cgid)
+			    const blk_opf_t opf, u32 what, int error,
+			    int pdu_len, void *pdu_data, u64 cgid)
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
@@ -227,16 +227,17 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	int cpu;
 	bool blk_tracer = blk_tracer_enabled;
 	ssize_t cgid_len = cgid ? sizeof(cgid) : 0;
+	const enum req_op op = opf & REQ_OP_MASK;
 
 	if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer))
 		return;
 
 	what |= ddir_act[op_is_write(op) ? WRITE : READ];
-	what |= MASK_TC_BIT(op_flags, SYNC);
-	what |= MASK_TC_BIT(op_flags, RAHEAD);
-	what |= MASK_TC_BIT(op_flags, META);
-	what |= MASK_TC_BIT(op_flags, PREFLUSH);
-	what |= MASK_TC_BIT(op_flags, FUA);
+	what |= MASK_TC_BIT(opf, SYNC);
+	what |= MASK_TC_BIT(opf, RAHEAD);
+	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)
 		what |= BLK_TC_ACT(BLK_TC_DISCARD);
 	if (op == REQ_OP_FLUSH)
@@ -736,12 +737,12 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 
 	switch (cmd) {
 	case BLKTRACESETUP:
-		bdevname(bdev, b);
+		snprintf(b, sizeof(b), "%pg", bdev);
 		ret = __blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 #if defined(CONFIG_COMPAT) && defined(CONFIG_X86_64)
 	case BLKTRACESETUP32:
-		bdevname(bdev, b);
+		snprintf(b, sizeof(b), "%pg", bdev);
 		ret = compat_blk_trace_setup(q, b, bdev->bd_dev, bdev, arg);
 		break;
 #endif
@@ -842,9 +843,8 @@ static void blk_add_trace_rq(struct request *rq, blk_status_t error,
 	else
 		what |= BLK_TC_ACT(BLK_TC_FS);
 
-	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
-			rq->cmd_flags, what, blk_status_to_errno(error), 0,
-			NULL, cgid);
+	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, rq->cmd_flags,
+			what, blk_status_to_errno(error), 0, NULL, cgid);
 	rcu_read_unlock();
 }
 
@@ -903,7 +903,7 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 	}
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, what, error, 0, NULL,
+			bio->bi_opf, what, error, 0, NULL,
 			blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
 }
@@ -949,7 +949,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 	rcu_read_lock();
 	bt = rcu_dereference(q->blk_trace);
 	if (bt)
-		__blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
+		__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0);
 	rcu_read_unlock();
 }
 
@@ -969,7 +969,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 		else
 			what = BLK_TA_UNPLUG_TIMER;
 
-		__blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
+		__blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0);
 	}
 	rcu_read_unlock();
 }
@@ -985,8 +985,7 @@ static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu)
 		__be64 rpdu = cpu_to_be64(pdu);
 
 		__blk_add_trace(bt, bio->bi_iter.bi_sector,
-				bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf,
-				BLK_TA_SPLIT,
+				bio->bi_iter.bi_size, bio->bi_opf, BLK_TA_SPLIT,
 				blk_status_to_errno(bio->bi_status),
 				sizeof(rpdu), &rpdu,
 				blk_trace_bio_get_cgid(q, bio));
@@ -1022,7 +1021,7 @@ static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size,
-			bio_op(bio), bio->bi_opf, BLK_TA_REMAP,
+			bio->bi_opf, BLK_TA_REMAP,
 			blk_status_to_errno(bio->bi_status),
 			sizeof(r), &r, blk_trace_bio_get_cgid(q, bio));
 	rcu_read_unlock();
@@ -1058,7 +1057,7 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev,
 	r.sector_from = cpu_to_be64(from);
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
-			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
+			rq->cmd_flags, BLK_TA_REMAP, 0,
 			sizeof(r), &r, blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
 }
@@ -1084,7 +1083,7 @@ void blk_add_driver_data(struct request *rq, void *data, size_t len)
 		return;
 	}
 
-	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
+	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0,
 				BLK_TA_DRV_DATA, 0, len, data,
 				blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
@@ -1867,17 +1866,6 @@ out_unlock_bdev:
 out:
 	return ret ? ret : count;
 }
-
-int blk_trace_init_sysfs(struct device *dev)
-{
-	return sysfs_create_group(&dev->kobj, &blk_trace_attr_group);
-}
-
-void blk_trace_remove_sysfs(struct device *dev)
-{
-	sysfs_remove_group(&dev->kobj, &blk_trace_attr_group);
-}
-
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_EVENT_TRACING
@@ -1885,21 +1873,21 @@ void blk_trace_remove_sysfs(struct device *dev)
 /**
  * blk_fill_rwbs - Fill the buffer rwbs by mapping op to character string.
  * @rwbs:	buffer to be filled
- * @op:		REQ_OP_XXX for the tracepoint
+ * @opf:	request operation type (REQ_OP_XXX) and flags for the tracepoint
  *
  * Description:
- *     Maps the REQ_OP_XXX to character and fills the buffer provided by the
- *     caller with resulting string.
+ *     Maps each request operation and flag to a single character and fills the
+ *     buffer provided by the caller with resulting string.
  *
  **/
-void blk_fill_rwbs(char *rwbs, unsigned int op)
+void blk_fill_rwbs(char *rwbs, blk_opf_t opf)
 {
 	int i = 0;
 
-	if (op & REQ_PREFLUSH)
+	if (opf & REQ_PREFLUSH)
 		rwbs[i++] = 'F';
 
-	switch (op & REQ_OP_MASK) {
+	switch (opf & REQ_OP_MASK) {
 	case REQ_OP_WRITE:
 		rwbs[i++] = 'W';
 		break;
@@ -1920,13 +1908,13 @@ void blk_fill_rwbs(char *rwbs, unsigned int op)
 		rwbs[i++] = 'N';
 	}
 
-	if (op & REQ_FUA)
+	if (opf & REQ_FUA)
 		rwbs[i++] = 'F';
-	if (op & REQ_RAHEAD)
+	if (opf & REQ_RAHEAD)
 		rwbs[i++] = 'A';
-	if (op & REQ_SYNC)
+	if (opf & REQ_SYNC)
 		rwbs[i++] = 'S';
-	if (op & REQ_META)
+	if (opf & REQ_META)
 		rwbs[i++] = 'M';
 
 	rwbs[i] = '\0';