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
  ...

3 files changed, 122 insertions, 319 deletions

diff --git a/init/do_mounts.c b/init/do_mounts.c
index d67efddf8597..2a970f6ac68f 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -28,7 +28,6 @@
 #include "do_mounts.h"
 
 int root_mountflags = MS_RDONLY | MS_SILENT;
-static char * __initdata root_device_name;
 static char __initdata saved_root_name[64];
 static int root_wait;
 
@@ -60,240 +59,6 @@ static int __init readwrite(char *str)
 __setup("ro", readonly);
 __setup("rw", readwrite);
 
-#ifdef CONFIG_BLOCK
-struct uuidcmp {
-	const char *uuid;
-	int len;
-};
-
-/**
- * match_dev_by_uuid - callback for finding a partition using its uuid
- * @dev:	device passed in by the caller
- * @data:	opaque pointer to the desired struct uuidcmp to match
- *
- * Returns 1 if the device matches, and 0 otherwise.
- */
-static int match_dev_by_uuid(struct device *dev, const void *data)
-{
-	struct block_device *bdev = dev_to_bdev(dev);
-	const struct uuidcmp *cmp = data;
-
-	if (!bdev->bd_meta_info ||
-	    strncasecmp(cmp->uuid, bdev->bd_meta_info->uuid, cmp->len))
-		return 0;
-	return 1;
-}
-
-/**
- * devt_from_partuuid - looks up the dev_t of a partition by its UUID
- * @uuid_str:	char array containing ascii UUID
- *
- * The function will return the first partition which contains a matching
- * UUID value in its partition_meta_info struct.  This does not search
- * by filesystem UUIDs.
- *
- * If @uuid_str is followed by a "/PARTNROFF=%d", then the number will be
- * extracted and used as an offset from the partition identified by the UUID.
- *
- * Returns the matching dev_t on success or 0 on failure.
- */
-static dev_t devt_from_partuuid(const char *uuid_str)
-{
-	struct uuidcmp cmp;
-	struct device *dev = NULL;
-	dev_t devt = 0;
-	int offset = 0;
-	char *slash;
-
-	cmp.uuid = uuid_str;
-
-	slash = strchr(uuid_str, '/');
-	/* Check for optional partition number offset attributes. */
-	if (slash) {
-		char c = 0;
-
-		/* Explicitly fail on poor PARTUUID syntax. */
-		if (sscanf(slash + 1, "PARTNROFF=%d%c", &offset, &c) != 1)
-			goto clear_root_wait;
-		cmp.len = slash - uuid_str;
-	} else {
-		cmp.len = strlen(uuid_str);
-	}
-
-	if (!cmp.len)
-		goto clear_root_wait;
-
-	dev = class_find_device(&block_class, NULL, &cmp, &match_dev_by_uuid);
-	if (!dev)
-		return 0;
-
-	if (offset) {
-		/*
-		 * Attempt to find the requested partition by adding an offset
-		 * to the partition number found by UUID.
-		 */
-		devt = part_devt(dev_to_disk(dev),
-				 dev_to_bdev(dev)->bd_partno + offset);
-	} else {
-		devt = dev->devt;
-	}
-
-	put_device(dev);
-	return devt;
-
-clear_root_wait:
-	pr_err("VFS: PARTUUID= is invalid.\n"
-	       "Expected PARTUUID=<valid-uuid-id>[/PARTNROFF=%%d]\n");
-	if (root_wait)
-		pr_err("Disabling rootwait; root= is invalid.\n");
-	root_wait = 0;
-	return 0;
-}
-
-/**
- * match_dev_by_label - callback for finding a partition using its label
- * @dev:	device passed in by the caller
- * @data:	opaque pointer to the label to match
- *
- * Returns 1 if the device matches, and 0 otherwise.
- */
-static int match_dev_by_label(struct device *dev, const void *data)
-{
-	struct block_device *bdev = dev_to_bdev(dev);
-	const char *label = data;
-
-	if (!bdev->bd_meta_info || strcmp(label, bdev->bd_meta_info->volname))
-		return 0;
-	return 1;
-}
-
-static dev_t devt_from_partlabel(const char *label)
-{
-	struct device *dev;
-	dev_t devt = 0;
-
-	dev = class_find_device(&block_class, NULL, label, &match_dev_by_label);
-	if (dev) {
-		devt = dev->devt;
-		put_device(dev);
-	}
-
-	return devt;
-}
-
-static dev_t devt_from_devname(const char *name)
-{
-	dev_t devt = 0;
-	int part;
-	char s[32];
-	char *p;
-
-	if (strlen(name) > 31)
-		return 0;
-	strcpy(s, name);
-	for (p = s; *p; p++) {
-		if (*p == '/')
-			*p = '!';
-	}
-
-	devt = blk_lookup_devt(s, 0);
-	if (devt)
-		return devt;
-
-	/*
-	 * Try non-existent, but valid partition, which may only exist after
-	 * opening the device, like partitioned md devices.
-	 */
-	while (p > s && isdigit(p[-1]))
-		p--;
-	if (p == s || !*p || *p == '0')
-		return 0;
-
-	/* try disk name without <part number> */
-	part = simple_strtoul(p, NULL, 10);
-	*p = '\0';
-	devt = blk_lookup_devt(s, part);
-	if (devt)
-		return devt;
-
-	/* try disk name without p<part number> */
-	if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p')
-		return 0;
-	p[-1] = '\0';
-	return blk_lookup_devt(s, part);
-}
-#endif /* CONFIG_BLOCK */
-
-static dev_t devt_from_devnum(const char *name)
-{
-	unsigned maj, min, offset;
-	dev_t devt = 0;
-	char *p, dummy;
-
-	if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 ||
-	    sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) {
-		devt = MKDEV(maj, min);
-		if (maj != MAJOR(devt) || min != MINOR(devt))
-			return 0;
-	} else {
-		devt = new_decode_dev(simple_strtoul(name, &p, 16));
-		if (*p)
-			return 0;
-	}
-
-	return devt;
-}
-
-/*
- *	Convert a name into device number.  We accept the following variants:
- *
- *	1) <hex_major><hex_minor> device number in hexadecimal represents itself
- *         no leading 0x, for example b302.
- *	2) /dev/nfs represents Root_NFS (0xff)
- *	3) /dev/<disk_name> represents the device number of disk
- *	4) /dev/<disk_name><decimal> represents the device number
- *         of partition - device number of disk plus the partition number
- *	5) /dev/<disk_name>p<decimal> - same as the above, that form is
- *	   used when disk name of partitioned disk ends on a digit.
- *	6) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the
- *	   unique id of a partition if the partition table provides it.
- *	   The UUID may be either an EFI/GPT UUID, or refer to an MSDOS
- *	   partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero-
- *	   filled hex representation of the 32-bit "NT disk signature", and PP
- *	   is a zero-filled hex representation of the 1-based partition number.
- *	7) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to
- *	   a partition with a known unique id.
- *	8) <major>:<minor> major and minor number of the device separated by
- *	   a colon.
- *	9) PARTLABEL=<name> with name being the GPT partition label.
- *	   MSDOS partitions do not support labels!
- *	10) /dev/cifs represents Root_CIFS (0xfe)
- *
- *	If name doesn't have fall into the categories above, we return (0,0).
- *	block_class is used to check if something is a disk name. If the disk
- *	name contains slashes, the device name has them replaced with
- *	bangs.
- */
-dev_t name_to_dev_t(const char *name)
-{
-	if (strcmp(name, "/dev/nfs") == 0)
-		return Root_NFS;
-	if (strcmp(name, "/dev/cifs") == 0)
-		return Root_CIFS;
-	if (strcmp(name, "/dev/ram") == 0)
-		return Root_RAM0;
-#ifdef CONFIG_BLOCK
-	if (strncmp(name, "PARTUUID=", 9) == 0)
-		return devt_from_partuuid(name + 9);
-	if (strncmp(name, "PARTLABEL=", 10) == 0)
-		return devt_from_partlabel(name + 10);
-	if (strncmp(name, "/dev/", 5) == 0)
-		return devt_from_devname(name + 5);
-#endif
-	return devt_from_devnum(name);
-}
-EXPORT_SYMBOL_GPL(name_to_dev_t);
-
 static int __init root_dev_setup(char *line)
 {
 	strscpy(saved_root_name, line, sizeof(saved_root_name));
@@ -391,7 +156,7 @@ out:
 	return ret;
 }
 
-void __init mount_block_root(char *name, int flags)
+void __init mount_root_generic(char *name, char *pretty_name, int flags)
 {
 	struct page *page = alloc_page(GFP_KERNEL);
 	char *fs_names = page_address(page);
@@ -425,7 +190,7 @@ retry:
 		 * and give them a list of the available devices
 		 */
 		printk("VFS: Cannot open root device \"%s\" or %s: error %d\n",
-				root_device_name, b, err);
+				pretty_name, b, err);
 		printk("Please append a correct \"root=\" boot option; here are the available partitions:\n");
 
 		printk_all_partitions();
@@ -453,15 +218,14 @@ out:
 #define NFSROOT_TIMEOUT_MAX	30
 #define NFSROOT_RETRY_MAX	5
 
-static int __init mount_nfs_root(void)
+static void __init mount_nfs_root(void)
 {
 	char *root_dev, *root_data;
 	unsigned int timeout;
-	int try, err;
+	int try;
 
-	err = nfs_root_data(&root_dev, &root_data);
-	if (err != 0)
-		return 0;
+	if (nfs_root_data(&root_dev, &root_data))
+		goto fail;
 
 	/*
 	 * The server or network may not be ready, so try several
@@ -470,10 +234,8 @@ static int __init mount_nfs_root(void)
 	 */
 	timeout = NFSROOT_TIMEOUT_MIN;
 	for (try = 1; ; try++) {
-		err = do_mount_root(root_dev, "nfs",
-					root_mountflags, root_data);
-		if (err == 0)
-			return 1;
+		if (!do_mount_root(root_dev, "nfs", root_mountflags, root_data))
+			return;
 		if (try > NFSROOT_RETRY_MAX)
 			break;
 
@@ -483,9 +245,14 @@ static int __init mount_nfs_root(void)
 		if (timeout > NFSROOT_TIMEOUT_MAX)
 			timeout = NFSROOT_TIMEOUT_MAX;
 	}
-	return 0;
+fail:
+	pr_err("VFS: Unable to mount root fs via NFS.\n");
+}
+#else
+static inline void mount_nfs_root(void)
+{
 }
-#endif
+#endif /* CONFIG_ROOT_NFS */
 
 #ifdef CONFIG_CIFS_ROOT
 
@@ -495,22 +262,20 @@ extern int cifs_root_data(char **dev, char **opts);
 #define CIFSROOT_TIMEOUT_MAX	30
 #define CIFSROOT_RETRY_MAX	5
 
-static int __init mount_cifs_root(void)
+static void __init mount_cifs_root(void)
 {
 	char *root_dev, *root_data;
 	unsigned int timeout;
-	int try, err;
+	int try;
 
-	err = cifs_root_data(&root_dev, &root_data);
-	if (err != 0)
-		return 0;
+	if (cifs_root_data(&root_dev, &root_data))
+		goto fail;
 
 	timeout = CIFSROOT_TIMEOUT_MIN;
 	for (try = 1; ; try++) {
-		err = do_mount_root(root_dev, "cifs", root_mountflags,
-				    root_data);
-		if (err == 0)
-			return 1;
+		if (!do_mount_root(root_dev, "cifs", root_mountflags,
+				   root_data))
+			return;
 		if (try > CIFSROOT_RETRY_MAX)
 			break;
 
@@ -519,9 +284,14 @@ static int __init mount_cifs_root(void)
 		if (timeout > CIFSROOT_TIMEOUT_MAX)
 			timeout = CIFSROOT_TIMEOUT_MAX;
 	}
-	return 0;
+fail:
+	pr_err("VFS: Unable to mount root fs via SMB.\n");
 }
-#endif
+#else
+static inline void mount_cifs_root(void)
+{
+}
+#endif /* CONFIG_CIFS_ROOT */
 
 static bool __init fs_is_nodev(char *fstype)
 {
@@ -536,7 +306,7 @@ static bool __init fs_is_nodev(char *fstype)
 	return ret;
 }
 
-static int __init mount_nodev_root(void)
+static int __init mount_nodev_root(char *root_device_name)
 {
 	char *fs_names, *fstype;
 	int err = -EINVAL;
@@ -563,35 +333,84 @@ static int __init mount_nodev_root(void)
 	return err;
 }
 
-void __init mount_root(void)
+#ifdef CONFIG_BLOCK
+static void __init mount_block_root(char *root_device_name)
 {
-#ifdef CONFIG_ROOT_NFS
-	if (ROOT_DEV == Root_NFS) {
-		if (!mount_nfs_root())
-			printk(KERN_ERR "VFS: Unable to mount root fs via NFS.\n");
-		return;
+	int err = create_dev("/dev/root", ROOT_DEV);
+
+	if (err < 0)
+		pr_emerg("Failed to create /dev/root: %d\n", err);
+	mount_root_generic("/dev/root", root_device_name, root_mountflags);
+}
+#else
+static inline void mount_block_root(char *root_device_name)
+{
+}
+#endif /* CONFIG_BLOCK */
+
+void __init mount_root(char *root_device_name)
+{
+	switch (ROOT_DEV) {
+	case Root_NFS:
+		mount_nfs_root();
+		break;
+	case Root_CIFS:
+		mount_cifs_root();
+		break;
+	case Root_Generic:
+		mount_root_generic(root_device_name, root_device_name,
+				   root_mountflags);
+		break;
+	case 0:
+		if (root_device_name && root_fs_names &&
+		    mount_nodev_root(root_device_name) == 0)
+			break;
+		fallthrough;
+	default:
+		mount_block_root(root_device_name);
+		break;
 	}
-#endif
-#ifdef CONFIG_CIFS_ROOT
-	if (ROOT_DEV == Root_CIFS) {
-		if (!mount_cifs_root())
-			printk(KERN_ERR "VFS: Unable to mount root fs via SMB.\n");
+}
+
+/* wait for any asynchronous scanning to complete */
+static void __init wait_for_root(char *root_device_name)
+{
+	if (ROOT_DEV != 0)
 		return;
-	}
-#endif
-	if (ROOT_DEV == 0 && root_device_name && root_fs_names) {
-		if (mount_nodev_root() == 0)
-			return;
-	}
-#ifdef CONFIG_BLOCK
-	{
-		int err = create_dev("/dev/root", ROOT_DEV);
 
-		if (err < 0)
-			pr_emerg("Failed to create /dev/root: %d\n", err);
-		mount_block_root("/dev/root", root_mountflags);
+	pr_info("Waiting for root device %s...\n", root_device_name);
+
+	while (!driver_probe_done() ||
+	       early_lookup_bdev(root_device_name, &ROOT_DEV) < 0)
+		msleep(5);
+	async_synchronize_full();
+
+}
+
+static dev_t __init parse_root_device(char *root_device_name)
+{
+	int error;
+	dev_t dev;
+
+	if (!strncmp(root_device_name, "mtd", 3) ||
+	    !strncmp(root_device_name, "ubi", 3))
+		return Root_Generic;
+	if (strcmp(root_device_name, "/dev/nfs") == 0)
+		return Root_NFS;
+	if (strcmp(root_device_name, "/dev/cifs") == 0)
+		return Root_CIFS;
+	if (strcmp(root_device_name, "/dev/ram") == 0)
+		return Root_RAM0;
+
+	error = early_lookup_bdev(root_device_name, &dev);
+	if (error) {
+		if (error == -EINVAL && root_wait) {
+			pr_err("Disabling rootwait; root= is invalid.\n");
+			root_wait = 0;
+		}
+		return 0;
 	}
-#endif
+	return dev;
 }
 
 /*
@@ -616,32 +435,15 @@ void __init prepare_namespace(void)
 
 	md_run_setup();
 
-	if (saved_root_name[0]) {
-		root_device_name = saved_root_name;
-		if (!strncmp(root_device_name, "mtd", 3) ||
-		    !strncmp(root_device_name, "ubi", 3)) {
-			mount_block_root(root_device_name, root_mountflags);
-			goto out;
-		}
-		ROOT_DEV = name_to_dev_t(root_device_name);
-		if (strncmp(root_device_name, "/dev/", 5) == 0)
-			root_device_name += 5;
-	}
+	if (saved_root_name[0])
+		ROOT_DEV = parse_root_device(saved_root_name);
 
-	if (initrd_load())
+	if (initrd_load(saved_root_name))
 		goto out;
 
-	/* wait for any asynchronous scanning to complete */
-	if ((ROOT_DEV == 0) && root_wait) {
-		printk(KERN_INFO "Waiting for root device %s...\n",
-			saved_root_name);
-		while (driver_probe_done() != 0 ||
-			(ROOT_DEV = name_to_dev_t(saved_root_name)) == 0)
-			msleep(5);
-		async_synchronize_full();
-	}
-
-	mount_root();
+	if (root_wait)
+		wait_for_root(saved_root_name);
+	mount_root(saved_root_name);
 out:
 	devtmpfs_mount();
 	init_mount(".", "/", NULL, MS_MOVE, NULL);
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 7a29ac3e427b..15e372b00ce7 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -10,8 +10,8 @@
 #include <linux/root_dev.h>
 #include <linux/init_syscalls.h>
 
-void  mount_block_root(char *name, int flags);
-void  mount_root(void);
+void  mount_root_generic(char *name, char *pretty_name, int flags);
+void  mount_root(char *root_device_name);
 extern int root_mountflags;
 
 static inline __init int create_dev(char *name, dev_t dev)
@@ -33,11 +33,11 @@ static inline int rd_load_image(char *from) { return 0; }
 #endif
 
 #ifdef CONFIG_BLK_DEV_INITRD
-
-bool __init initrd_load(void);
-
+bool __init initrd_load(char *root_device_name);
 #else
-
-static inline bool initrd_load(void) { return false; }
+static inline bool initrd_load(char *root_device_name)
+{
+	return false;
+	}
 
 #endif
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 34731241377d..425f4bcf4b77 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -83,7 +83,7 @@ static int __init init_linuxrc(struct subprocess_info *info, struct cred *new)
 	return 0;
 }
 
-static void __init handle_initrd(void)
+static void __init handle_initrd(char *root_device_name)
 {
 	struct subprocess_info *info;
 	static char *argv[] = { "linuxrc", NULL, };
@@ -95,7 +95,8 @@ static void __init handle_initrd(void)
 	real_root_dev = new_encode_dev(ROOT_DEV);
 	create_dev("/dev/root.old", Root_RAM0);
 	/* mount initrd on rootfs' /root */
-	mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY);
+	mount_root_generic("/dev/root.old", root_device_name,
+			   root_mountflags & ~MS_RDONLY);
 	init_mkdir("/old", 0700);
 	init_chdir("/old");
 
@@ -117,7 +118,7 @@ static void __init handle_initrd(void)
 
 	init_chdir("/");
 	ROOT_DEV = new_decode_dev(real_root_dev);
-	mount_root();
+	mount_root(root_device_name);
 
 	printk(KERN_NOTICE "Trying to move old root to /initrd ... ");
 	error = init_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL);
@@ -133,7 +134,7 @@ static void __init handle_initrd(void)
 	}
 }
 
-bool __init initrd_load(void)
+bool __init initrd_load(char *root_device_name)
 {
 	if (mount_initrd) {
 		create_dev("/dev/ram", Root_RAM0);
@@ -145,7 +146,7 @@ bool __init initrd_load(void)
 		 */
 		if (rd_load_image("/initrd.image") && ROOT_DEV != Root_RAM0) {
 			init_unlink("/initrd.image");
-			handle_initrd();
+			handle_initrd(root_device_name);
 			return true;
 		}
 	}