Merge tag 'vfs-6.14-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "Features:

   - Support caching symlink lengths in inodes

     The size is stored in a new union utilizing the same space as
     i_devices, thus avoiding growing the struct or taking up any more
     space

     When utilized it dodges strlen() in vfs_readlink(), giving about
     1.5% speed up when issuing readlink on /initrd.img on ext4

   - Add RWF_DONTCACHE iocb and FOP_DONTCACHE file_operations flag

     If a file system supports uncached buffered IO, it may set
     FOP_DONTCACHE and enable support for RWF_DONTCACHE.

     If RWF_DONTCACHE is attempted without the file system supporting
     it, it'll get errored with -EOPNOTSUPP

   - Enable VBOXGUEST and VBOXSF_FS on ARM64

     Now that VirtualBox is able to run as a host on arm64 (e.g. the
     Apple M3 processors) we can enable VBOXSF_FS (and in turn
     VBOXGUEST) for this architecture.

     Tested with various runs of bonnie++ and dbench on an Apple MacBook
     Pro with the latest Virtualbox 7.1.4 r165100 installed

  Cleanups:

   - Delay sysctl_nr_open check in expand_files()

   - Use kernel-doc includes in fiemap docbook

   - Use page->private instead of page->index in watch_queue

   - Use a consume fence in mnt_idmap() as it's heavily used in
     link_path_walk()

   - Replace magic number 7 with ARRAY_SIZE() in fc_log

   - Sort out a stale comment about races between fd alloc and dup2()

   - Fix return type of do_mount() from long to int

   - Various cosmetic cleanups for the lockref code

  Fixes:

   - Annotate spinning as unlikely() in __read_seqcount_begin

     The annotation already used to be there, but got lost in commit
     52ac39e5db51 ("seqlock: seqcount_t: Implement all read APIs as
     statement expressions")

   - Fix proc_handler for sysctl_nr_open

   - Flush delayed work in delayed fput()

   - Fix grammar and spelling in propagate_umount()

   - Fix ESP not readable during coredump

     In /proc/PID/stat, there is the kstkesp field which is the stack
     pointer of a thread. While the thread is active, this field reads
     zero. But during a coredump, it should have a valid value

     However, at the moment, kstkesp is zero even during coredump

   - Don't wake up the writer if the pipe is still full

   - Fix unbalanced user_access_end() in select code"

* tag 'vfs-6.14-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (28 commits)
  gfs2: use lockref_init for qd_lockref
  erofs: use lockref_init for pcl->lockref
  dcache: use lockref_init for d_lockref
  lockref: add a lockref_init helper
  lockref: drop superfluous externs
  lockref: use bool for false/true returns
  lockref: improve the lockref_get_not_zero description
  lockref: remove lockref_put_not_zero
  fs: Fix return type of do_mount() from long to int
  select: Fix unbalanced user_access_end()
  vbox: Enable VBOXGUEST and VBOXSF_FS on ARM64
  pipe_read: don't wake up the writer if the pipe is still full
  selftests: coredump: Add stackdump test
  fs/proc: do_task_stat: Fix ESP not readable during coredump
  fs: add RWF_DONTCACHE iocb and FOP_DONTCACHE file_operations flag
  fs: sort out a stale comment about races between fd alloc and dup2
  fs: Fix grammar and spelling in propagate_umount()
  fs: fc_log replace magic number 7 with ARRAY_SIZE()
  fs: use a consume fence in mnt_idmap()
  file: flush delayed work in delayed fput()
  ...

7 files changed, 96 insertions, 34 deletions

diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h
index c50882f19235..966092ffa89a 100644
--- a/include/linux/fiemap.h
+++ b/include/linux/fiemap.h
@@ -5,12 +5,18 @@
 #include <uapi/linux/fiemap.h>
 #include <linux/fs.h>
 
+/**
+ * struct fiemap_extent_info - fiemap request to a filesystem
+ * @fi_flags:		Flags as passed from user
+ * @fi_extents_mapped:	Number of mapped extents
+ * @fi_extents_max:	Size of fiemap_extent array
+ * @fi_extents_start:	Start of fiemap_extent array
+ */
 struct fiemap_extent_info {
-	unsigned int fi_flags;		/* Flags as passed from user */
-	unsigned int fi_extents_mapped;	/* Number of mapped extents */
-	unsigned int fi_extents_max;	/* Size of fiemap_extent array */
-	struct fiemap_extent __user *fi_extents_start; /* Start of
-							fiemap_extent array */
+	unsigned int fi_flags;
+	unsigned int fi_extents_mapped;
+	unsigned int fi_extents_max;
+	struct fiemap_extent __user *fi_extents_start;
 };
 
 int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7e29433c5ecc..e06ea7e9ca15 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -322,6 +322,7 @@ struct readahead_control;
 #define IOCB_NOWAIT		(__force int) RWF_NOWAIT
 #define IOCB_APPEND		(__force int) RWF_APPEND
 #define IOCB_ATOMIC		(__force int) RWF_ATOMIC
+#define IOCB_DONTCACHE		(__force int) RWF_DONTCACHE
 
 /* non-RWF related bits - start at 16 */
 #define IOCB_EVENTFD		(1 << 16)
@@ -356,7 +357,8 @@ struct readahead_control;
 	{ IOCB_SYNC,		"SYNC" }, \
 	{ IOCB_NOWAIT,		"NOWAIT" }, \
 	{ IOCB_APPEND,		"APPEND" }, \
-	{ IOCB_ATOMIC,		"ATOMIC"}, \
+	{ IOCB_ATOMIC,		"ATOMIC" }, \
+	{ IOCB_DONTCACHE,	"DONTCACHE" }, \
 	{ IOCB_EVENTFD,		"EVENTFD"}, \
 	{ IOCB_DIRECT,		"DIRECT" }, \
 	{ IOCB_WRITE,		"WRITE" }, \
@@ -626,6 +628,7 @@ is_uncached_acl(struct posix_acl *acl)
 #define IOP_XATTR	0x0008
 #define IOP_DEFAULT_READLINK	0x0010
 #define IOP_MGTIME	0x0020
+#define IOP_CACHED_LINK	0x0040
 
 /*
  * Keep mostly read-only and often accessed (especially for
@@ -723,7 +726,10 @@ struct inode {
 	};
 	struct file_lock_context	*i_flctx;
 	struct address_space	i_data;
-	struct list_head	i_devices;
+	union {
+		struct list_head	i_devices;
+		int			i_linklen;
+	};
 	union {
 		struct pipe_inode_info	*i_pipe;
 		struct cdev		*i_cdev;
@@ -749,6 +755,13 @@ struct inode {
 	void			*i_private; /* fs or device private pointer */
 } __randomize_layout;
 
+static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen)
+{
+	inode->i_link = link;
+	inode->i_linklen = linklen;
+	inode->i_opflags |= IOP_CACHED_LINK;
+}
+
 /*
  * Get bit address from inode->i_state to use with wait_var_event()
  * infrastructre.
@@ -2127,6 +2140,8 @@ struct file_operations {
 #define FOP_UNSIGNED_OFFSET	((__force fop_flags_t)(1 << 5))
 /* Supports asynchronous lock callbacks */
 #define FOP_ASYNC_LOCK		((__force fop_flags_t)(1 << 6))
+/* File system supports uncached read/write buffered IO */
+#define FOP_DONTCACHE		((__force fop_flags_t)(1 << 7))
 
 /* Wrap a directory iterator that needs exclusive inode access */
 int wrap_directory_iterator(struct file *, struct dir_context *,
@@ -3351,7 +3366,7 @@ extern const struct file_operations generic_ro_fops;
 
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
 
-extern int readlink_copy(char __user *, int, const char *);
+extern int readlink_copy(char __user *, int, const char *, int);
 extern int page_readlink(struct dentry *, char __user *, int);
 extern const char *page_get_link(struct dentry *, struct inode *,
 				 struct delayed_call *);
@@ -3614,6 +3629,14 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags,
 		if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE))
 			return -EOPNOTSUPP;
 	}
+	if (flags & RWF_DONTCACHE) {
+		/* file system must support it */
+		if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE))
+			return -EOPNOTSUPP;
+		/* DAX mappings not supported */
+		if (IS_DAX(ki->ki_filp->f_mapping->host))
+			return -EOPNOTSUPP;
+	}
 	kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
 	if (flags & RWF_SYNC)
 		kiocb_flags |= IOCB_DSYNC;
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index c3a1f78bc884..c39f119659ba 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -34,14 +34,24 @@ struct lockref {
 	};
 };
 
-extern void lockref_get(struct lockref *);
-extern int lockref_put_return(struct lockref *);
-extern int lockref_get_not_zero(struct lockref *);
-extern int lockref_put_not_zero(struct lockref *);
-extern int lockref_put_or_lock(struct lockref *);
-
-extern void lockref_mark_dead(struct lockref *);
-extern int lockref_get_not_dead(struct lockref *);
+/**
+ * lockref_init - Initialize a lockref
+ * @lockref: pointer to lockref structure
+ * @count: initial count
+ */
+static inline void lockref_init(struct lockref *lockref, unsigned int count)
+{
+	spin_lock_init(&lockref->lock);
+	lockref->count = count;
+}
+
+void lockref_get(struct lockref *lockref);
+int lockref_put_return(struct lockref *lockref);
+bool lockref_get_not_zero(struct lockref *lockref);
+bool lockref_put_or_lock(struct lockref *lockref);
+
+void lockref_mark_dead(struct lockref *lockref);
+bool lockref_get_not_dead(struct lockref *lockref);
 
 /* Must be called under spinlock for reliable results */
 static inline bool __lockref_is_dead(const struct lockref *l)
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 04213d8ef837..dcc17ce8a959 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -75,7 +75,7 @@ struct vfsmount {
 static inline struct mnt_idmap *mnt_idmap(const struct vfsmount *mnt)
 {
 	/* Pairs with smp_store_release() in do_idmap_mount(). */
-	return smp_load_acquire(&mnt->mnt_idmap);
+	return READ_ONCE(mnt->mnt_idmap);
 }
 
 extern int mnt_want_write(struct vfsmount *mnt);
@@ -113,7 +113,7 @@ extern struct vfsmount *kern_mount(struct file_system_type *);
 extern void kern_unmount(struct vfsmount *mnt);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
-extern long do_mount(const char *, const char __user *,
+int do_mount(const char *, const char __user *,
 		     const char *, unsigned long, void *);
 extern struct vfsmount *collect_mounts(const struct path *);
 extern void drop_collected_mounts(struct vfsmount *);
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 5298765d6ca4..eb20dcaa51b5 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -272,7 +272,7 @@ SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     mutex)
 ({									\
 	unsigned __seq;							\
 									\
-	while ((__seq = seqprop_sequence(s)) & 1)			\
+	while (unlikely((__seq = seqprop_sequence(s)) & 1))		\
 		cpu_relax();						\
 									\
 	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);			\
diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h
index 24ca0c00cae3..9d9e8ae32b41 100644
--- a/include/uapi/linux/fiemap.h
+++ b/include/uapi/linux/fiemap.h
@@ -14,37 +14,56 @@
 
 #include <linux/types.h>
 
+/**
+ * struct fiemap_extent - description of one fiemap extent
+ * @fe_logical: byte offset of the extent in the file
+ * @fe_physical: byte offset of extent on disk
+ * @fe_length: length in bytes for this extent
+ * @fe_flags: FIEMAP_EXTENT_* flags for this extent
+ */
 struct fiemap_extent {
-	__u64 fe_logical;  /* logical offset in bytes for the start of
-			    * the extent from the beginning of the file */
-	__u64 fe_physical; /* physical offset in bytes for the start
-			    * of the extent from the beginning of the disk */
-	__u64 fe_length;   /* length in bytes for this extent */
+	__u64 fe_logical;
+	__u64 fe_physical;
+	__u64 fe_length;
+	/* private: */
 	__u64 fe_reserved64[2];
-	__u32 fe_flags;    /* FIEMAP_EXTENT_* flags for this extent */
+	/* public: */
+	__u32 fe_flags;
+	/* private: */
 	__u32 fe_reserved[3];
 };
 
+/**
+ * struct fiemap - file extent mappings
+ * @fm_start: byte offset (inclusive) at which to start mapping (in)
+ * @fm_length: logical length of mapping which userspace wants (in)
+ * @fm_flags: FIEMAP_FLAG_* flags for request (in/out)
+ * @fm_mapped_extents: number of extents that were mapped (out)
+ * @fm_extent_count: size of fm_extents array (in)
+ * @fm_extents: array of mapped extents (out)
+ */
 struct fiemap {
-	__u64 fm_start;		/* logical offset (inclusive) at
-				 * which to start mapping (in) */
-	__u64 fm_length;	/* logical length of mapping which
-				 * userspace wants (in) */
-	__u32 fm_flags;		/* FIEMAP_FLAG_* flags for request (in/out) */
-	__u32 fm_mapped_extents;/* number of extents that were mapped (out) */
-	__u32 fm_extent_count;  /* size of fm_extents array (in) */
+	__u64 fm_start;
+	__u64 fm_length;
+	__u32 fm_flags;
+	__u32 fm_mapped_extents;
+	__u32 fm_extent_count;
+	/* private: */
 	__u32 fm_reserved;
-	struct fiemap_extent fm_extents[]; /* array of mapped extents (out) */
+	/* public: */
+	struct fiemap_extent fm_extents[];
 };
 
 #define FIEMAP_MAX_OFFSET	(~0ULL)
 
+/* flags used in fm_flags: */
 #define FIEMAP_FLAG_SYNC	0x00000001 /* sync file data before map */
 #define FIEMAP_FLAG_XATTR	0x00000002 /* map extended attribute tree */
 #define FIEMAP_FLAG_CACHE	0x00000004 /* request caching of the extents */
 
 #define FIEMAP_FLAGS_COMPAT	(FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR)
 
+/* flags used in fe_flags: */
 #define FIEMAP_EXTENT_LAST		0x00000001 /* Last extent in file. */
 #define FIEMAP_EXTENT_UNKNOWN		0x00000002 /* Data location unknown. */
 #define FIEMAP_EXTENT_DELALLOC		0x00000004 /* Location still pending.
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 753971770733..56a4f93a08f4 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -332,9 +332,13 @@ typedef int __bitwise __kernel_rwf_t;
 /* Atomic Write */
 #define RWF_ATOMIC	((__force __kernel_rwf_t)0x00000040)
 
+/* buffered IO that drops the cache after reading or writing data */
+#define RWF_DONTCACHE	((__force __kernel_rwf_t)0x00000080)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-			 RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC)
+			 RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\
+			 RWF_DONTCACHE)
 
 #define PROCFS_IOCTL_MAGIC 'f'