Merge tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull request via Keith:
      - Various cleanups all around (Irvin, Chaitanya, Christophe)
      - Better struct packing (Christophe JAILLET)
      - Reduce controller error logs for optional commands (Keith)
      - Support for >=64KiB block sizes (Daniel Gomez)
      - Fabrics fixes and code organization (Max, Chaitanya, Daniel
        Wagner)

 - bcache updates via Coly:
      - Fix a race at init time (Mingzhe Zou)
      - Misc fixes and cleanups (Andrea, Thomas, Zheng, Ye)

 - use page pinning in the block layer for dio (David)

 - convert old block dio code to page pinning (David, Christoph)

 - cleanups for pktcdvd (Andy)

 - cleanups for rnbd (Guoqing)

 - use the unchecked __bio_add_page() for the initial single page
   additions (Johannes)

 - fix overflows in the Amiga partition handling code (Michael)

 - improve mq-deadline zoned device support (Bart)

 - keep passthrough requests out of the IO schedulers (Christoph, Ming)

 - improve support for flush requests, making them less special to deal
   with (Christoph)

 - add bdev holder ops and shutdown methods (Christoph)

 - fix the name_to_dev_t() situation and use cases (Christoph)

 - decouple the block open flags from fmode_t (Christoph)

 - ublk updates and cleanups, including adding user copy support (Ming)

 - BFQ sanity checking (Bart)

 - convert brd from radix to xarray (Pankaj)

 - constify various structures (Thomas, Ivan)

 - more fine grained persistent reservation ioctl capability checks
   (Jingbo)

 - misc fixes and cleanups (Arnd, Azeem, Demi, Ed, Hengqi, Hou, Jan,
   Jordy, Li, Min, Yu, Zhong, Waiman)

* tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux: (266 commits)
  scsi/sg: don't grab scsi host module reference
  ext4: Fix warning in blkdev_put()
  block: don't return -EINVAL for not found names in devt_from_devname
  cdrom: Fix spectre-v1 gadget
  block: Improve kernel-doc headers
  blk-mq: don't insert passthrough request into sw queue
  bsg: make bsg_class a static const structure
  ublk: make ublk_chr_class a static const structure
  aoe: make aoe_class a static const structure
  block/rnbd: make all 'class' structures const
  block: fix the exclusive open mask in disk_scan_partitions
  block: add overflow checks for Amiga partition support
  block: change all __u32 annotations to __be32 in affs_hardblocks.h
  block: fix signed int overflow in Amiga partition support
  block: add capacity validation in bdev_add_partition()
  block: fine-granular CAP_SYS_ADMIN for Persistent Reservation
  block: disallow Persistent Reservation on partitions
  reiserfs: fix blkdev_put() warning from release_journal_dev()
  block: fix wrong mode for blkdev_get_by_dev() from disk_scan_partitions()
  block: document the holder argument to blkdev_get_by_path
  ...

Documentation/admin-guide/bcache.rst

@@ -508,9 +508,6 @@ cache_miss_collisions
   cache miss, but raced with a write and data was already present (usually 0
   since the synchronization for cache misses was rewritten)
 
-cache_readaheads
-  Count of times readahead occurred.
-
 Sysfs - cache set
 ~~~~~~~~~~~~~~~~~
 

Documentation/admin-guide/cgroup-v2.rst

@@ -2022,31 +2022,33 @@ that attribute:
   no-change
 	Do not modify the I/O priority class.
 
-  none-to-rt
-	For requests that do not have an I/O priority class (NONE),
-	change the I/O priority class into RT. Do not modify
-	the I/O priority class of other requests.
+  promote-to-rt
+	For requests that have a non-RT I/O priority class, change it into RT.
+	Also change the priority level of these requests to 4. Do not modify
+	the I/O priority of requests that have priority class RT.
 
   restrict-to-be
 	For requests that do not have an I/O priority class or that have I/O
-	priority class RT, change it into BE. Do not modify the I/O priority
-	class of requests that have priority class IDLE.
+	priority class RT, change it into BE. Also change the priority level
+	of these requests to 0. Do not modify the I/O priority class of
+	requests that have priority class IDLE.
 
   idle
 	Change the I/O priority class of all requests into IDLE, the lowest
 	I/O priority class.
 
+  none-to-rt
+	Deprecated. Just an alias for promote-to-rt.
+
 The following numerical values are associated with the I/O priority policies:
 
-+-------------+---+
-| no-change   | 0 |
-+-------------+---+
-| none-to-rt  | 1 |
-+-------------+---+
-| rt-to-be    | 2 |
-+-------------+---+
-| all-to-idle | 3 |
-+-------------+---+
++----------------+---+
+| no-change      | 0 |
++----------------+---+
+| rt-to-be       | 2 |
++----------------+---+
+| all-to-idle    | 3 |
++----------------+---+
 
 The numerical value that corresponds to each I/O priority class is as follows:
 
@@ -2062,9 +2064,13 @@ The numerical value that corresponds to each I/O priority class is as follows:
 
 The algorithm to set the I/O priority class for a request is as follows:
 
-- Translate the I/O priority class policy into a number.
-- Change the request I/O priority class into the maximum of the I/O priority
-  class policy number and the numerical I/O priority class.
+- If I/O priority class policy is promote-to-rt, change the request I/O
+  priority class to IOPRIO_CLASS_RT and change the request I/O priority
+  level to 4.
+- If I/O priorityt class is not promote-to-rt, translate the I/O priority
+  class policy into a number, then change the request I/O priority class
+  into the maximum of the I/O priority class policy number and the numerical
+  I/O priority class.
 
 PID
 ---

Documentation/admin-guide/kernel-parameters.txt

@@ -5452,7 +5452,12 @@
 			port and the regular usb controller gets disabled.
 
 	root=		[KNL] Root filesystem
-			See name_to_dev_t comment in init/do_mounts.c.
+			Usually this a a block device specifier of some kind,
+			see the early_lookup_bdev comment in
+			block/early-lookup.c for details.
+			Alternatively this can be "ram" for the legacy initial
+			ramdisk, "nfs" and "cifs" for root on a network file
+			system, or "mtd" and "ubi" for mounting from raw flash.
 
 	rootdelay=	[KNL] Delay (in seconds) to pause before attempting to
 			mount the root filesystem

Documentation/core-api/pin_user_pages.rst

@@ -112,6 +112,12 @@ pages:
 This also leads to limitations: there are only 31-10==21 bits available for a
 counter that increments 10 bits at a time.
 
+* Because of that limitation, special handling is applied to the zero pages
+  when using FOLL_PIN.  We only pretend to pin a zero page - we don't alter its
+  refcount or pincount at all (it is permanent, so there's no need).  The
+  unpinning functions also don't do anything to a zero page.  This is
+  transparent to the caller.
+
 * Callers must specifically request "dma-pinned tracking of pages". In other
   words, just calling get_user_pages() will not suffice; a new set of functions,
   pin_user_page() and related, must be used.

arch/alpha/kernel/setup.c

@@ -658,7 +658,7 @@ setup_arch(char **cmdline_p)
 #endif
 
 	/* Default root filesystem to sda2.  */
-	ROOT_DEV = Root_SDA2;
+	ROOT_DEV = MKDEV(SCSI_DISK0_MAJOR, 2);
 
 #ifdef CONFIG_EISA
 	/* FIXME:  only set this when we actually have EISA in this box? */

arch/ia64/kernel/setup.c

@@ -627,7 +627,7 @@ setup_arch (char **cmdline_p)
 	 * is physical disk 1 partition 1 and the Linux root disk is
 	 * physical disk 1 partition 2.
 	 */
-	ROOT_DEV = Root_SDA2;		/* default to second partition on first drive */
+	ROOT_DEV = MKDEV(SCSI_DISK0_MAJOR, 2);
 
 	if (is_uv_system())
 		uv_setup(cmdline_p);

arch/powerpc/platforms/powermac/setup.c

@@ -76,7 +76,8 @@ int pmac_newworld;
 
 static int current_root_goodness = -1;
 
-#define DEFAULT_ROOT_DEVICE Root_SDA1	/* sda1 - slightly silly choice */
+/* sda1 - slightly silly choice */
+#define DEFAULT_ROOT_DEVICE	MKDEV(SCSI_DISK0_MAJOR, 1)
 
 sys_ctrler_t sys_ctrler = SYS_CTRLER_UNKNOWN;
 EXPORT_SYMBOL(sys_ctrler);

arch/um/drivers/ubd_kern.c

@@ -108,9 +108,9 @@ static inline void ubd_set_bit(__u64 bit, unsigned char *data)
 static DEFINE_MUTEX(ubd_lock);
 static DEFINE_MUTEX(ubd_mutex); /* replaces BKL, might not be needed */
 
-static int ubd_open(struct block_device *bdev, fmode_t mode);
-static void ubd_release(struct gendisk *disk, fmode_t mode);
-static int ubd_ioctl(struct block_device *bdev, fmode_t mode,
+static int ubd_open(struct gendisk *disk, blk_mode_t mode);
+static void ubd_release(struct gendisk *disk);
+static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg);
 static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
@@ -1154,9 +1154,8 @@ static int __init ubd_driver_init(void){
 
 device_initcall(ubd_driver_init);
 
-static int ubd_open(struct block_device *bdev, fmode_t mode)
+static int ubd_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct gendisk *disk = bdev->bd_disk;
 	struct ubd *ubd_dev = disk->private_data;
 	int err = 0;
 
@@ -1171,19 +1170,12 @@ static int ubd_open(struct block_device *bdev, fmode_t mode)
 	}
 	ubd_dev->count++;
 	set_disk_ro(disk, !ubd_dev->openflags.w);
-
-	/* This should no more be needed. And it didn't work anyway to exclude
-	 * read-write remounting of filesystems.*/
-	/*if((mode & FMODE_WRITE) && !ubd_dev->openflags.w){
-	        if(--ubd_dev->count == 0) ubd_close_dev(ubd_dev);
-	        err = -EROFS;
-	}*/
 out:
 	mutex_unlock(&ubd_mutex);
 	return err;
 }
 
-static void ubd_release(struct gendisk *disk, fmode_t mode)
+static void ubd_release(struct gendisk *disk)
 {
 	struct ubd *ubd_dev = disk->private_data;
 
@@ -1397,7 +1389,7 @@ static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static int ubd_ioctl(struct block_device *bdev, fmode_t mode,
+static int ubd_ioctl(struct block_device *bdev, blk_mode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct ubd *ubd_dev = bdev->bd_disk->private_data;

arch/xtensa/platforms/iss/simdisk.c

@@ -120,17 +120,17 @@ static void simdisk_submit_bio(struct bio *bio)
 	bio_endio(bio);
 }
 
-static int simdisk_open(struct block_device *bdev, fmode_t mode)
+static int simdisk_open(struct gendisk *disk, blk_mode_t mode)
 {
-	struct simdisk *dev = bdev->bd_disk->private_data;
+	struct simdisk *dev = disk->private_data;
 
 	spin_lock(&dev->lock);
 	++dev->users;
 	spin_unlock(&dev->lock);
 	return 0;
 }
 
-static void simdisk_release(struct gendisk *disk, fmode_t mode)
+static void simdisk_release(struct gendisk *disk)
 {
 	struct simdisk *dev = disk->private_data;
 	spin_lock(&dev->lock);

block/Makefile

@@ -9,7 +9,7 @@ obj-y		:= bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \
-			disk-events.o blk-ia-ranges.o
+			disk-events.o blk-ia-ranges.o early-lookup.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o