1

tools/include: Sync filesystem headers with the kernel sources

To pick up changes from:

  0f9ca80fa4 fs: Add initial atomic write support info to statx
  f9af549d1f fs: export mount options via statmount()
  0a3deb1185 fs: Allow listmount() in foreign mount namespace
  09b31295f8 fs: export the mount ns id via statmount
  d04bccd8c1 listmount: allow listing in reverse order
  bfc69fd05e fs/procfs: add build ID fetching to PROCMAP_QUERY API
  ed5d583a88 fs/procfs: implement efficient VMA querying API for /proc/<pid>/maps

This should be used to beautify FS syscall arguments and it addresses
these tools/perf build warnings:

  Warning: Kernel ABI header differences:
  diff -u tools/include/uapi/linux/stat.h include/uapi/linux/stat.h
  diff -u tools/perf/trace/beauty/include/uapi/linux/fs.h include/uapi/linux/fs.h
  diff -u tools/perf/trace/beauty/include/uapi/linux/mount.h include/uapi/linux/mount.h
  diff -u tools/perf/trace/beauty/include/uapi/linux/stat.h include/uapi/linux/stat.h

Please see tools/include/uapi/README for details (it's in the first patch
of this series).

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
This commit is contained in:
Namhyung Kim 2024-08-06 12:07:50 -07:00
parent ed86525f1f
commit 845295f400
4 changed files with 189 additions and 8 deletions

View File

@ -126,9 +126,15 @@ struct statx {
__u64 stx_mnt_id;
__u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
__u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
__u64 stx_subvol; /* Subvolume identifier */
/* 0xa0 */
__u64 __spare3[11]; /* Spare space for future expansion */
__u64 stx_subvol; /* Subvolume identifier */
__u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */
__u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */
/* 0xb0 */
__u32 stx_atomic_write_segments_max; /* Max atomic write segment count */
__u32 __spare1[1];
/* 0xb8 */
__u64 __spare3[9]; /* Spare space for future expansion */
/* 0x100 */
};
@ -157,6 +163,7 @@ struct statx {
#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */
#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
@ -192,6 +199,7 @@ struct statx {
#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */
#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */
#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */
#endif /* _UAPI_LINUX_STAT_H */

View File

@ -329,12 +329,17 @@ typedef int __bitwise __kernel_rwf_t;
/* per-IO negation of O_APPEND */
#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020)
/* Atomic Write */
#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040)
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
RWF_APPEND | RWF_NOAPPEND)
RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC)
#define PROCFS_IOCTL_MAGIC 'f'
/* Pagemap ioctl */
#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg)
#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg)
/* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */
#define PAGE_IS_WPALLOWED (1 << 0)
@ -393,4 +398,158 @@ struct pm_scan_arg {
__u64 return_mask;
};
/* /proc/<pid>/maps ioctl */
#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query)
enum procmap_query_flags {
/*
* VMA permission flags.
*
* Can be used as part of procmap_query.query_flags field to look up
* only VMAs satisfying specified subset of permissions. E.g., specifying
* PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs,
* while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only
* return read/write VMAs, though both executable/non-executable and
* private/shared will be ignored.
*
* PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags
* field to specify actual VMA permissions.
*/
PROCMAP_QUERY_VMA_READABLE = 0x01,
PROCMAP_QUERY_VMA_WRITABLE = 0x02,
PROCMAP_QUERY_VMA_EXECUTABLE = 0x04,
PROCMAP_QUERY_VMA_SHARED = 0x08,
/*
* Query modifier flags.
*
* By default VMA that covers provided address is returned, or -ENOENT
* is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest
* VMA with vma_start > addr will be returned if no covering VMA is
* found.
*
* PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that
* have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA
* to iterate all VMAs with file backing.
*/
PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10,
PROCMAP_QUERY_FILE_BACKED_VMA = 0x20,
};
/*
* Input/output argument structured passed into ioctl() call. It can be used
* to query a set of VMAs (Virtual Memory Areas) of a process.
*
* Each field can be one of three kinds, marked in a short comment to the
* right of the field:
* - "in", input argument, user has to provide this value, kernel doesn't modify it;
* - "out", output argument, kernel sets this field with VMA data;
* - "in/out", input and output argument; user provides initial value (used
* to specify maximum allowable buffer size), and kernel sets it to actual
* amount of data written (or zero, if there is no data).
*
* If matching VMA is found (according to criterias specified by
* query_addr/query_flags, all the out fields are filled out, and ioctl()
* returns 0. If there is no matching VMA, -ENOENT will be returned.
* In case of any other error, negative error code other than -ENOENT is
* returned.
*
* Most of the data is similar to the one returned as text in /proc/<pid>/maps
* file, but procmap_query provides more querying flexibility. There are no
* consistency guarantees between subsequent ioctl() calls, but data returned
* for matched VMA is self-consistent.
*/
struct procmap_query {
/* Query struct size, for backwards/forward compatibility */
__u64 size;
/*
* Query flags, a combination of enum procmap_query_flags values.
* Defines query filtering and behavior, see enum procmap_query_flags.
*
* Input argument, provided by user. Kernel doesn't modify it.
*/
__u64 query_flags; /* in */
/*
* Query address. By default, VMA that covers this address will
* be looked up. PROCMAP_QUERY_* flags above modify this default
* behavior further.
*
* Input argument, provided by user. Kernel doesn't modify it.
*/
__u64 query_addr; /* in */
/* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */
__u64 vma_start; /* out */
__u64 vma_end; /* out */
/* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */
__u64 vma_flags; /* out */
/* VMA backing page size granularity. */
__u64 vma_page_size; /* out */
/*
* VMA file offset. If VMA has file backing, this specifies offset
* within the file that VMA's start address corresponds to.
* Is set to zero if VMA has no backing file.
*/
__u64 vma_offset; /* out */
/* Backing file's inode number, or zero, if VMA has no backing file. */
__u64 inode; /* out */
/* Backing file's device major/minor number, or zero, if VMA has no backing file. */
__u32 dev_major; /* out */
__u32 dev_minor; /* out */
/*
* If set to non-zero value, signals the request to return VMA name
* (i.e., VMA's backing file's absolute path, with " (deleted)" suffix
* appended, if file was unlinked from FS) for matched VMA. VMA name
* can also be some special name (e.g., "[heap]", "[stack]") or could
* be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME).
*
* Kernel will set this field to zero, if VMA has no associated name.
* Otherwise kernel will return actual amount of bytes filled in
* user-supplied buffer (see vma_name_addr field below), including the
* terminating zero.
*
* If VMA name is longer that user-supplied maximum buffer size,
* -E2BIG error is returned.
*
* If this field is set to non-zero value, vma_name_addr should point
* to valid user space memory buffer of at least vma_name_size bytes.
* If set to zero, vma_name_addr should be set to zero as well
*/
__u32 vma_name_size; /* in/out */
/*
* If set to non-zero value, signals the request to extract and return
* VMA's backing file's build ID, if the backing file is an ELF file
* and it contains embedded build ID.
*
* Kernel will set this field to zero, if VMA has no backing file,
* backing file is not an ELF file, or ELF file has no build ID
* embedded.
*
* Build ID is a binary value (not a string). Kernel will set
* build_id_size field to exact number of bytes used for build ID.
* If build ID is requested and present, but needs more bytes than
* user-supplied maximum buffer size (see build_id_addr field below),
* -E2BIG error will be returned.
*
* If this field is set to non-zero value, build_id_addr should point
* to valid user space memory buffer of at least build_id_size bytes.
* If set to zero, build_id_addr should be set to zero as well
*/
__u32 build_id_size; /* in/out */
/*
* User-supplied address of a buffer of at least vma_name_size bytes
* for kernel to fill with matched VMA's name (see vma_name_size field
* description above for details).
*
* Should be set to zero if VMA name should not be returned.
*/
__u64 vma_name_addr; /* in */
/*
* User-supplied address of a buffer of at least build_id_size bytes
* for kernel to fill with matched VMA's ELF build ID, if available
* (see build_id_size field description above for details).
*
* Should be set to zero if build ID should not be returned.
*/
__u64 build_id_addr; /* in */
};
#endif /* _UAPI_LINUX_FS_H */

View File

@ -154,7 +154,7 @@ struct mount_attr {
*/
struct statmount {
__u32 size; /* Total size, including strings */
__u32 __spare1;
__u32 mnt_opts; /* [str] Mount options of the mount */
__u64 mask; /* What results were written */
__u32 sb_dev_major; /* Device ID */
__u32 sb_dev_minor;
@ -172,7 +172,8 @@ struct statmount {
__u64 propagate_from; /* Propagation from in current namespace */
__u32 mnt_root; /* [str] Root of mount relative to root of fs */
__u32 mnt_point; /* [str] Mountpoint relative to current root */
__u64 __spare2[50];
__u64 mnt_ns_id; /* ID of the mount namespace */
__u64 __spare2[49];
char str[]; /* Variable size part containing strings */
};
@ -188,10 +189,12 @@ struct mnt_id_req {
__u32 spare;
__u64 mnt_id;
__u64 param;
__u64 mnt_ns_id;
};
/* List of all mnt_id_req versions. */
#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */
#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */
/*
* @mask bits for statmount(2)
@ -202,10 +205,13 @@ struct mnt_id_req {
#define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */
#define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */
#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */
#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */
#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */
/*
* Special @mnt_id values that can be passed to listmount
*/
#define LSMT_ROOT 0xffffffffffffffff /* root mount */
#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */
#endif /* _UAPI_LINUX_MOUNT_H */

View File

@ -126,9 +126,15 @@ struct statx {
__u64 stx_mnt_id;
__u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
__u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
__u64 stx_subvol; /* Subvolume identifier */
/* 0xa0 */
__u64 __spare3[11]; /* Spare space for future expansion */
__u64 stx_subvol; /* Subvolume identifier */
__u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */
__u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */
/* 0xb0 */
__u32 stx_atomic_write_segments_max; /* Max atomic write segment count */
__u32 __spare1[1];
/* 0xb8 */
__u64 __spare3[9]; /* Spare space for future expansion */
/* 0x100 */
};
@ -157,6 +163,7 @@ struct statx {
#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */
#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
@ -192,6 +199,7 @@ struct statx {
#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */
#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */
#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */
#endif /* _UAPI_LINUX_STAT_H */