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()
  ...

2 files changed, 38 insertions, 15 deletions

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'