From 68ca5d4eebb8c4de246ee5f634eee26bc689562d Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 19 Mar 2024 16:38:50 -0700
Subject: bpf: support BPF cookie in raw tracepoint (raw_tp, tp_btf) programs

Wire up BPF cookie for raw tracepoint programs (both BTF and non-BTF
aware variants). This brings them up to part w.r.t. BPF cookie usage
with classic tracepoint and fentry/fexit programs.

Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Message-ID: <20240319233852.1977493-4-andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3c42b9f1bada..bf80b614c4db 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1664,6 +1664,7 @@ union bpf_attr {
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
 		__u64 name;
 		__u32 prog_fd;
+		__aligned_u64 cookie;
 	} raw_tracepoint;
 
 	struct { /* anonymous struct for BPF_BTF_LOAD */
-- 
cgit 


From faf7217a397f041f146a4cf6d9f1c9bd99cd5ca4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Mar 2024 17:07:33 -0300
Subject: perf beauty: Move uapi/linux/fs.h copy out of the directory used to
 build perf

It is mostly used only to generate string tables, not to build perf, so
move it to the tools/perf/trace/beauty/include/ hierarchy, that is used
just for scraping.

The only case where it was being used to build was in
tools/perf/trace/beauty/sync_file_range.c, because some older systems
doesn't have the SYNC_FILE_RANGE_WRITE_AND_WAIT define, just use the
system's linux/fs.h header instead, defining it if not available.

This is a something that should've have happened, as happened with the
linux/socket.h scrapper, do it now as Ian suggested while doing an
audit/refactor session in the headers used by perf.

No other tools/ living code uses it, just <linux/fs.h> coming from
either 'make install_headers' or from the system /usr/include/
directory.

Suggested-by: Ian Rogers <irogers@google.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/CAP-5=fWZVrpRufO4w-S4EcSi9STXcTAN2ERLwTSN7yrSSA-otQ@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fs.h                   | 368 ------------------------
 tools/perf/Makefile.perf                        |   9 +-
 tools/perf/check-headers.sh                     |   2 +-
 tools/perf/trace/beauty/include/uapi/linux/fs.h | 368 ++++++++++++++++++++++++
 tools/perf/trace/beauty/rename_flags.sh         |   2 +-
 tools/perf/trace/beauty/sync_file_range.c       |  11 +-
 tools/perf/trace/beauty/sync_file_range.sh      |   2 +-
 7 files changed, 386 insertions(+), 376 deletions(-)
 delete mode 100644 tools/include/uapi/linux/fs.h
 create mode 100644 tools/perf/trace/beauty/include/uapi/linux/fs.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
deleted file mode 100644
index 48ad69f7722e..000000000000
--- a/tools/include/uapi/linux/fs.h
+++ /dev/null
@@ -1,368 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_FS_H
-#define _UAPI_LINUX_FS_H
-
-/*
- * This file has definitions for some important file table structures
- * and constants and structures used by various generic file system
- * ioctl's.  Please do not make any changes in this file before
- * sending patches for review to linux-fsdevel@vger.kernel.org and
- * linux-api@vger.kernel.org.
- */
-
-#include <linux/limits.h>
-#include <linux/ioctl.h>
-#include <linux/types.h>
-#ifndef __KERNEL__
-#include <linux/fscrypt.h>
-#endif
-
-/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
-#if !defined(__KERNEL__)
-#include <linux/mount.h>
-#endif
-
-/*
- * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
- * the file limit at runtime and only root can increase the per-process
- * nr_file rlimit, so it's safe to set up a ridiculously high absolute
- * upper limit on files-per-process.
- *
- * Some programs (notably those using select()) may have to be 
- * recompiled to take full advantage of the new limits..  
- */
-
-/* Fixed constants first: */
-#undef NR_OPEN
-#define INR_OPEN_CUR 1024	/* Initial setting for nfile rlimits */
-#define INR_OPEN_MAX 4096	/* Hard limit for nfile rlimits */
-
-#define BLOCK_SIZE_BITS 10
-#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
-
-#define SEEK_SET	0	/* seek relative to beginning of file */
-#define SEEK_CUR	1	/* seek relative to current file position */
-#define SEEK_END	2	/* seek relative to end of file */
-#define SEEK_DATA	3	/* seek to the next data */
-#define SEEK_HOLE	4	/* seek to the next hole */
-#define SEEK_MAX	SEEK_HOLE
-
-#define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
-#define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
-#define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
-
-struct file_clone_range {
-	__s64 src_fd;
-	__u64 src_offset;
-	__u64 src_length;
-	__u64 dest_offset;
-};
-
-struct fstrim_range {
-	__u64 start;
-	__u64 len;
-	__u64 minlen;
-};
-
-/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
-#define FILE_DEDUPE_RANGE_SAME		0
-#define FILE_DEDUPE_RANGE_DIFFERS	1
-
-/* from struct btrfs_ioctl_file_extent_same_info */
-struct file_dedupe_range_info {
-	__s64 dest_fd;		/* in - destination file */
-	__u64 dest_offset;	/* in - start of extent in destination */
-	__u64 bytes_deduped;	/* out - total # of bytes we were able
-				 * to dedupe from this file. */
-	/* status of this dedupe operation:
-	 * < 0 for error
-	 * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
-	 * == FILE_DEDUPE_RANGE_DIFFERS if data differs
-	 */
-	__s32 status;		/* out - see above description */
-	__u32 reserved;		/* must be zero */
-};
-
-/* from struct btrfs_ioctl_file_extent_same_args */
-struct file_dedupe_range {
-	__u64 src_offset;	/* in - start of extent in source */
-	__u64 src_length;	/* in - length of extent */
-	__u16 dest_count;	/* in - total elements in info array */
-	__u16 reserved1;	/* must be zero */
-	__u32 reserved2;	/* must be zero */
-	struct file_dedupe_range_info info[];
-};
-
-/* And dynamically-tunable limits and defaults: */
-struct files_stat_struct {
-	unsigned long nr_files;		/* read only */
-	unsigned long nr_free_files;	/* read only */
-	unsigned long max_files;		/* tunable */
-};
-
-struct inodes_stat_t {
-	long nr_inodes;
-	long nr_unused;
-	long dummy[5];		/* padding for sysctl ABI compatibility */
-};
-
-
-#define NR_FILE  8192	/* this can well be larger on a larger system */
-
-/*
- * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
- */
-struct fsxattr {
-	__u32		fsx_xflags;	/* xflags field value (get/set) */
-	__u32		fsx_extsize;	/* extsize field value (get/set)*/
-	__u32		fsx_nextents;	/* nextents field value (get)	*/
-	__u32		fsx_projid;	/* project identifier (get/set) */
-	__u32		fsx_cowextsize;	/* CoW extsize field value (get/set)*/
-	unsigned char	fsx_pad[8];
-};
-
-/*
- * Flags for the fsx_xflags field
- */
-#define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
-#define FS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
-#define FS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
-#define FS_XFLAG_APPEND		0x00000010	/* all writes append */
-#define FS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
-#define FS_XFLAG_NOATIME	0x00000040	/* do not update access time */
-#define FS_XFLAG_NODUMP		0x00000080	/* do not include in backups */
-#define FS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
-#define FS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
-#define FS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
-#define FS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
-#define FS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
-#define FS_XFLAG_NODEFRAG	0x00002000	/* do not defragment */
-#define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
-#define FS_XFLAG_DAX		0x00008000	/* use DAX for IO */
-#define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
-#define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
-
-/* the read-only stuff doesn't really belong here, but any other place is
-   probably as bad and I don't want to create yet another include file. */
-
-#define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
-#define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
-#define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
-#define BLKGETSIZE _IO(0x12,96)	/* return device size /512 (long *arg) */
-#define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
-#define BLKRASET   _IO(0x12,98)	/* set read ahead for block device */
-#define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
-#define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
-#define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
-#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
-#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
-#define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
-#if 0
-#define BLKPG      _IO(0x12,105)/* See blkpg.h */
-
-/* Some people are morons.  Do not use sizeof! */
-
-#define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
-#define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
-/* This was here just to show that the number is taken -
-   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
-#endif
-/* A jump here: 108-111 have been used for various private purposes. */
-#define BLKBSZGET  _IOR(0x12,112,size_t)
-#define BLKBSZSET  _IOW(0x12,113,size_t)
-#define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
-#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
-#define BLKTRACESTART _IO(0x12,116)
-#define BLKTRACESTOP _IO(0x12,117)
-#define BLKTRACETEARDOWN _IO(0x12,118)
-#define BLKDISCARD _IO(0x12,119)
-#define BLKIOMIN _IO(0x12,120)
-#define BLKIOOPT _IO(0x12,121)
-#define BLKALIGNOFF _IO(0x12,122)
-#define BLKPBSZGET _IO(0x12,123)
-#define BLKDISCARDZEROES _IO(0x12,124)
-#define BLKSECDISCARD _IO(0x12,125)
-#define BLKROTATIONAL _IO(0x12,126)
-#define BLKZEROOUT _IO(0x12,127)
-#define BLKGETDISKSEQ _IOR(0x12,128,__u64)
-/*
- * A jump here: 130-136 are reserved for zoned block devices
- * (see uapi/linux/blkzoned.h)
- */
-
-#define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
-#define FIBMAP	   _IO(0x00,1)	/* bmap access */
-#define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
-#define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
-#define FITHAW		_IOWR('X', 120, int)	/* Thaw */
-#define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
-#define FICLONE		_IOW(0x94, 9, int)
-#define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
-#define FIDEDUPERANGE	_IOWR(0x94, 54, struct file_dedupe_range)
-
-#define FSLABEL_MAX 256	/* Max chars for the interface; each fs may differ */
-
-#define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
-#define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
-#define	FS_IOC_GETVERSION		_IOR('v', 1, long)
-#define	FS_IOC_SETVERSION		_IOW('v', 2, long)
-#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
-#define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
-#define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
-#define FS_IOC32_GETVERSION		_IOR('v', 1, int)
-#define FS_IOC32_SETVERSION		_IOW('v', 2, int)
-#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
-#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
-#define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
-#define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
-
-/*
- * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
- *
- * Note: for historical reasons, these flags were originally used and
- * defined for use by ext2/ext3, and then other file systems started
- * using these flags so they wouldn't need to write their own version
- * of chattr/lsattr (which was shipped as part of e2fsprogs).  You
- * should think twice before trying to use these flags in new
- * contexts, or trying to assign these flags, since they are used both
- * as the UAPI and the on-disk encoding for ext2/3/4.  Also, we are
- * almost out of 32-bit flags.  :-)
- *
- * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from
- * XFS to the generic FS level interface.  This uses a structure that
- * has padding and hence has more room to grow, so it may be more
- * appropriate for many new use cases.
- *
- * Please do not change these flags or interfaces before checking with
- * linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org.
- */
-#define	FS_SECRM_FL			0x00000001 /* Secure deletion */
-#define	FS_UNRM_FL			0x00000002 /* Undelete */
-#define	FS_COMPR_FL			0x00000004 /* Compress file */
-#define FS_SYNC_FL			0x00000008 /* Synchronous updates */
-#define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
-#define FS_APPEND_FL			0x00000020 /* writes to file may only append */
-#define FS_NODUMP_FL			0x00000040 /* do not dump file */
-#define FS_NOATIME_FL			0x00000080 /* do not update atime */
-/* Reserved for compression usage... */
-#define FS_DIRTY_FL			0x00000100
-#define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
-#define FS_NOCOMP_FL			0x00000400 /* Don't compress */
-/* End compression flags --- maybe not all used */
-#define FS_ENCRYPT_FL			0x00000800 /* Encrypted file */
-#define FS_BTREE_FL			0x00001000 /* btree format dir */
-#define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
-#define FS_IMAGIC_FL			0x00002000 /* AFS directory */
-#define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
-#define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
-#define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
-#define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
-#define FS_HUGE_FILE_FL			0x00040000 /* Reserved for ext4 */
-#define FS_EXTENT_FL			0x00080000 /* Extents */
-#define FS_VERITY_FL			0x00100000 /* Verity protected inode */
-#define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
-#define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
-#define FS_NOCOW_FL			0x00800000 /* Do not cow file */
-#define FS_DAX_FL			0x02000000 /* Inode is DAX */
-#define FS_INLINE_DATA_FL		0x10000000 /* Reserved for ext4 */
-#define FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
-#define FS_CASEFOLD_FL			0x40000000 /* Folder is case insensitive */
-#define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */
-
-#define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
-#define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
-
-
-#define SYNC_FILE_RANGE_WAIT_BEFORE	1
-#define SYNC_FILE_RANGE_WRITE		2
-#define SYNC_FILE_RANGE_WAIT_AFTER	4
-#define SYNC_FILE_RANGE_WRITE_AND_WAIT	(SYNC_FILE_RANGE_WRITE | \
-					 SYNC_FILE_RANGE_WAIT_BEFORE | \
-					 SYNC_FILE_RANGE_WAIT_AFTER)
-
-/*
- * Flags for preadv2/pwritev2:
- */
-
-typedef int __bitwise __kernel_rwf_t;
-
-/* high priority request, poll if possible */
-#define RWF_HIPRI	((__force __kernel_rwf_t)0x00000001)
-
-/* per-IO O_DSYNC */
-#define RWF_DSYNC	((__force __kernel_rwf_t)0x00000002)
-
-/* per-IO O_SYNC */
-#define RWF_SYNC	((__force __kernel_rwf_t)0x00000004)
-
-/* per-IO, return -EAGAIN if operation would block */
-#define RWF_NOWAIT	((__force __kernel_rwf_t)0x00000008)
-
-/* per-IO O_APPEND */
-#define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
-
-/* mask of flags supported by the kernel */
-#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-			 RWF_APPEND)
-
-/* Pagemap ioctl */
-#define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
-
-/* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */
-#define PAGE_IS_WPALLOWED	(1 << 0)
-#define PAGE_IS_WRITTEN		(1 << 1)
-#define PAGE_IS_FILE		(1 << 2)
-#define PAGE_IS_PRESENT		(1 << 3)
-#define PAGE_IS_SWAPPED		(1 << 4)
-#define PAGE_IS_PFNZERO		(1 << 5)
-#define PAGE_IS_HUGE		(1 << 6)
-#define PAGE_IS_SOFT_DIRTY	(1 << 7)
-
-/*
- * struct page_region - Page region with flags
- * @start:	Start of the region
- * @end:	End of the region (exclusive)
- * @categories:	PAGE_IS_* category bitmask for the region
- */
-struct page_region {
-	__u64 start;
-	__u64 end;
-	__u64 categories;
-};
-
-/* Flags for PAGEMAP_SCAN ioctl */
-#define PM_SCAN_WP_MATCHING	(1 << 0)	/* Write protect the pages matched. */
-#define PM_SCAN_CHECK_WPASYNC	(1 << 1)	/* Abort the scan when a non-WP-enabled page is found. */
-
-/*
- * struct pm_scan_arg - Pagemap ioctl argument
- * @size:		Size of the structure
- * @flags:		Flags for the IOCTL
- * @start:		Starting address of the region
- * @end:		Ending address of the region
- * @walk_end		Address where the scan stopped (written by kernel).
- *			walk_end == end (address tags cleared) informs that the scan completed on entire range.
- * @vec:		Address of page_region struct array for output
- * @vec_len:		Length of the page_region struct array
- * @max_pages:		Optional limit for number of returned pages (0 = disabled)
- * @category_inverted:	PAGE_IS_* categories which values match if 0 instead of 1
- * @category_mask:	Skip pages for which any category doesn't match
- * @category_anyof_mask: Skip pages for which no category matches
- * @return_mask:	PAGE_IS_* categories that are to be reported in `page_region`s returned
- */
-struct pm_scan_arg {
-	__u64 size;
-	__u64 flags;
-	__u64 start;
-	__u64 end;
-	__u64 walk_end;
-	__u64 vec;
-	__u64 vec_len;
-	__u64 max_pages;
-	__u64 category_inverted;
-	__u64 category_mask;
-	__u64 category_anyof_mask;
-	__u64 return_mask;
-};
-
-#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index d3a568abc389..643e9fa6ec89 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -472,6 +472,7 @@ arm64-sysreg-defs-clean:
 		clean > /dev/null
 
 beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/
+beauty_uapi_linux_dir := $(srctree)/tools/perf/trace/beauty/include/uapi/linux/
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
 arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
@@ -647,8 +648,8 @@ $(x86_arch_MSRs_array): $(x86_arch_asm_dir)/msr-index.h $(x86_arch_MSRs_tbl)
 rename_flags_array := $(beauty_outdir)/rename_flags_array.c
 rename_flags_tbl := $(srctree)/tools/perf/trace/beauty/rename_flags.sh
 
-$(rename_flags_array): $(linux_uapi_dir)/fs.h $(rename_flags_tbl)
-	$(Q)$(SHELL) '$(rename_flags_tbl)' $(linux_uapi_dir) > $@
+$(rename_flags_array): $(beauty_uapi_linux_dir)/fs.h $(rename_flags_tbl)
+	$(Q)$(SHELL) '$(rename_flags_tbl)' $(beauty_uapi_linux_dir) > $@
 
 arch_errno_name_array := $(beauty_outdir)/arch_errno_name_array.c
 arch_errno_hdr_dir := $(srctree)/tools
@@ -660,8 +661,8 @@ $(arch_errno_name_array): $(arch_errno_tbl)
 sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
 sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh
 
-$(sync_file_range_arrays): $(linux_uapi_dir)/fs.h $(sync_file_range_tbls)
-	$(Q)$(SHELL) '$(sync_file_range_tbls)' $(linux_uapi_dir) > $@
+$(sync_file_range_arrays): $(beauty_uapi_linux_dir)/fs.h $(sync_file_range_tbls)
+	$(Q)$(SHELL) '$(sync_file_range_tbls)' $(beauty_uapi_linux_dir) > $@
 
 TESTS_CORESIGHT_DIR := $(srctree)/tools/perf/tests/shell/coresight
 
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 66ba33dbcef2..015f74137b75 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -11,7 +11,6 @@ FILES=(
   "include/uapi/drm/i915_drm.h"
   "include/uapi/linux/fadvise.h"
   "include/uapi/linux/fcntl.h"
-  "include/uapi/linux/fs.h"
   "include/uapi/linux/fscrypt.h"
   "include/uapi/linux/kcmp.h"
   "include/uapi/linux/kvm.h"
@@ -98,6 +97,7 @@ SYNC_CHECK_FILES=(
 declare -a BEAUTY_FILES
 BEAUTY_FILES=(
   "include/linux/socket.h"
+  "include/uapi/linux/fs.h"
 )
 
 declare -a FAILURES
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
new file mode 100644
index 000000000000..48ad69f7722e
--- /dev/null
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -0,0 +1,368 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FS_H
+#define _UAPI_LINUX_FS_H
+
+/*
+ * This file has definitions for some important file table structures
+ * and constants and structures used by various generic file system
+ * ioctl's.  Please do not make any changes in this file before
+ * sending patches for review to linux-fsdevel@vger.kernel.org and
+ * linux-api@vger.kernel.org.
+ */
+
+#include <linux/limits.h>
+#include <linux/ioctl.h>
+#include <linux/types.h>
+#ifndef __KERNEL__
+#include <linux/fscrypt.h>
+#endif
+
+/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
+#if !defined(__KERNEL__)
+#include <linux/mount.h>
+#endif
+
+/*
+ * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
+ * the file limit at runtime and only root can increase the per-process
+ * nr_file rlimit, so it's safe to set up a ridiculously high absolute
+ * upper limit on files-per-process.
+ *
+ * Some programs (notably those using select()) may have to be 
+ * recompiled to take full advantage of the new limits..  
+ */
+
+/* Fixed constants first: */
+#undef NR_OPEN
+#define INR_OPEN_CUR 1024	/* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096	/* Hard limit for nfile rlimits */
+
+#define BLOCK_SIZE_BITS 10
+#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
+
+#define SEEK_SET	0	/* seek relative to beginning of file */
+#define SEEK_CUR	1	/* seek relative to current file position */
+#define SEEK_END	2	/* seek relative to end of file */
+#define SEEK_DATA	3	/* seek to the next data */
+#define SEEK_HOLE	4	/* seek to the next hole */
+#define SEEK_MAX	SEEK_HOLE
+
+#define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
+#define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
+#define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
+
+struct file_clone_range {
+	__s64 src_fd;
+	__u64 src_offset;
+	__u64 src_length;
+	__u64 dest_offset;
+};
+
+struct fstrim_range {
+	__u64 start;
+	__u64 len;
+	__u64 minlen;
+};
+
+/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
+#define FILE_DEDUPE_RANGE_SAME		0
+#define FILE_DEDUPE_RANGE_DIFFERS	1
+
+/* from struct btrfs_ioctl_file_extent_same_info */
+struct file_dedupe_range_info {
+	__s64 dest_fd;		/* in - destination file */
+	__u64 dest_offset;	/* in - start of extent in destination */
+	__u64 bytes_deduped;	/* out - total # of bytes we were able
+				 * to dedupe from this file. */
+	/* status of this dedupe operation:
+	 * < 0 for error
+	 * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
+	 * == FILE_DEDUPE_RANGE_DIFFERS if data differs
+	 */
+	__s32 status;		/* out - see above description */
+	__u32 reserved;		/* must be zero */
+};
+
+/* from struct btrfs_ioctl_file_extent_same_args */
+struct file_dedupe_range {
+	__u64 src_offset;	/* in - start of extent in source */
+	__u64 src_length;	/* in - length of extent */
+	__u16 dest_count;	/* in - total elements in info array */
+	__u16 reserved1;	/* must be zero */
+	__u32 reserved2;	/* must be zero */
+	struct file_dedupe_range_info info[];
+};
+
+/* And dynamically-tunable limits and defaults: */
+struct files_stat_struct {
+	unsigned long nr_files;		/* read only */
+	unsigned long nr_free_files;	/* read only */
+	unsigned long max_files;		/* tunable */
+};
+
+struct inodes_stat_t {
+	long nr_inodes;
+	long nr_unused;
+	long dummy[5];		/* padding for sysctl ABI compatibility */
+};
+
+
+#define NR_FILE  8192	/* this can well be larger on a larger system */
+
+/*
+ * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
+ */
+struct fsxattr {
+	__u32		fsx_xflags;	/* xflags field value (get/set) */
+	__u32		fsx_extsize;	/* extsize field value (get/set)*/
+	__u32		fsx_nextents;	/* nextents field value (get)	*/
+	__u32		fsx_projid;	/* project identifier (get/set) */
+	__u32		fsx_cowextsize;	/* CoW extsize field value (get/set)*/
+	unsigned char	fsx_pad[8];
+};
+
+/*
+ * Flags for the fsx_xflags field
+ */
+#define FS_XFLAG_REALTIME	0x00000001	/* data in realtime volume */
+#define FS_XFLAG_PREALLOC	0x00000002	/* preallocated file extents */
+#define FS_XFLAG_IMMUTABLE	0x00000008	/* file cannot be modified */
+#define FS_XFLAG_APPEND		0x00000010	/* all writes append */
+#define FS_XFLAG_SYNC		0x00000020	/* all writes synchronous */
+#define FS_XFLAG_NOATIME	0x00000040	/* do not update access time */
+#define FS_XFLAG_NODUMP		0x00000080	/* do not include in backups */
+#define FS_XFLAG_RTINHERIT	0x00000100	/* create with rt bit set */
+#define FS_XFLAG_PROJINHERIT	0x00000200	/* create with parents projid */
+#define FS_XFLAG_NOSYMLINKS	0x00000400	/* disallow symlink creation */
+#define FS_XFLAG_EXTSIZE	0x00000800	/* extent size allocator hint */
+#define FS_XFLAG_EXTSZINHERIT	0x00001000	/* inherit inode extent size */
+#define FS_XFLAG_NODEFRAG	0x00002000	/* do not defragment */
+#define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
+#define FS_XFLAG_DAX		0x00008000	/* use DAX for IO */
+#define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
+#define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
+
+/* the read-only stuff doesn't really belong here, but any other place is
+   probably as bad and I don't want to create yet another include file. */
+
+#define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
+#define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
+#define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
+#define BLKGETSIZE _IO(0x12,96)	/* return device size /512 (long *arg) */
+#define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
+#define BLKRASET   _IO(0x12,98)	/* set read ahead for block device */
+#define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
+#define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
+#define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
+#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
+#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
+#define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
+#if 0
+#define BLKPG      _IO(0x12,105)/* See blkpg.h */
+
+/* Some people are morons.  Do not use sizeof! */
+
+#define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
+#define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
+/* This was here just to show that the number is taken -
+   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
+#endif
+/* A jump here: 108-111 have been used for various private purposes. */
+#define BLKBSZGET  _IOR(0x12,112,size_t)
+#define BLKBSZSET  _IOW(0x12,113,size_t)
+#define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
+#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
+#define BLKTRACESTART _IO(0x12,116)
+#define BLKTRACESTOP _IO(0x12,117)
+#define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
+#define BLKIOMIN _IO(0x12,120)
+#define BLKIOOPT _IO(0x12,121)
+#define BLKALIGNOFF _IO(0x12,122)
+#define BLKPBSZGET _IO(0x12,123)
+#define BLKDISCARDZEROES _IO(0x12,124)
+#define BLKSECDISCARD _IO(0x12,125)
+#define BLKROTATIONAL _IO(0x12,126)
+#define BLKZEROOUT _IO(0x12,127)
+#define BLKGETDISKSEQ _IOR(0x12,128,__u64)
+/*
+ * A jump here: 130-136 are reserved for zoned block devices
+ * (see uapi/linux/blkzoned.h)
+ */
+
+#define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
+#define FIBMAP	   _IO(0x00,1)	/* bmap access */
+#define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
+#define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
+#define FITHAW		_IOWR('X', 120, int)	/* Thaw */
+#define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
+#define FICLONE		_IOW(0x94, 9, int)
+#define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
+#define FIDEDUPERANGE	_IOWR(0x94, 54, struct file_dedupe_range)
+
+#define FSLABEL_MAX 256	/* Max chars for the interface; each fs may differ */
+
+#define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
+#define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
+#define	FS_IOC_GETVERSION		_IOR('v', 1, long)
+#define	FS_IOC_SETVERSION		_IOW('v', 2, long)
+#define FS_IOC_FIEMAP			_IOWR('f', 11, struct fiemap)
+#define FS_IOC32_GETFLAGS		_IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS		_IOW('f', 2, int)
+#define FS_IOC32_GETVERSION		_IOR('v', 1, int)
+#define FS_IOC32_SETVERSION		_IOW('v', 2, int)
+#define FS_IOC_FSGETXATTR		_IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR		_IOW('X', 32, struct fsxattr)
+#define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
+#define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ *
+ * Note: for historical reasons, these flags were originally used and
+ * defined for use by ext2/ext3, and then other file systems started
+ * using these flags so they wouldn't need to write their own version
+ * of chattr/lsattr (which was shipped as part of e2fsprogs).  You
+ * should think twice before trying to use these flags in new
+ * contexts, or trying to assign these flags, since they are used both
+ * as the UAPI and the on-disk encoding for ext2/3/4.  Also, we are
+ * almost out of 32-bit flags.  :-)
+ *
+ * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from
+ * XFS to the generic FS level interface.  This uses a structure that
+ * has padding and hence has more room to grow, so it may be more
+ * appropriate for many new use cases.
+ *
+ * Please do not change these flags or interfaces before checking with
+ * linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org.
+ */
+#define	FS_SECRM_FL			0x00000001 /* Secure deletion */
+#define	FS_UNRM_FL			0x00000002 /* Undelete */
+#define	FS_COMPR_FL			0x00000004 /* Compress file */
+#define FS_SYNC_FL			0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL			0x00000010 /* Immutable file */
+#define FS_APPEND_FL			0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL			0x00000040 /* do not dump file */
+#define FS_NOATIME_FL			0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL			0x00000100
+#define FS_COMPRBLK_FL			0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL			0x00000400 /* Don't compress */
+/* End compression flags --- maybe not all used */
+#define FS_ENCRYPT_FL			0x00000800 /* Encrypted file */
+#define FS_BTREE_FL			0x00001000 /* btree format dir */
+#define FS_INDEX_FL			0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL			0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL		0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL			0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
+#define FS_HUGE_FILE_FL			0x00040000 /* Reserved for ext4 */
+#define FS_EXTENT_FL			0x00080000 /* Extents */
+#define FS_VERITY_FL			0x00100000 /* Verity protected inode */
+#define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
+#define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
+#define FS_NOCOW_FL			0x00800000 /* Do not cow file */
+#define FS_DAX_FL			0x02000000 /* Inode is DAX */
+#define FS_INLINE_DATA_FL		0x10000000 /* Reserved for ext4 */
+#define FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
+#define FS_CASEFOLD_FL			0x40000000 /* Folder is case insensitive */
+#define FS_RESERVED_FL			0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE		0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE		0x000380FF /* User modifiable flags */
+
+
+#define SYNC_FILE_RANGE_WAIT_BEFORE	1
+#define SYNC_FILE_RANGE_WRITE		2
+#define SYNC_FILE_RANGE_WAIT_AFTER	4
+#define SYNC_FILE_RANGE_WRITE_AND_WAIT	(SYNC_FILE_RANGE_WRITE | \
+					 SYNC_FILE_RANGE_WAIT_BEFORE | \
+					 SYNC_FILE_RANGE_WAIT_AFTER)
+
+/*
+ * Flags for preadv2/pwritev2:
+ */
+
+typedef int __bitwise __kernel_rwf_t;
+
+/* high priority request, poll if possible */
+#define RWF_HIPRI	((__force __kernel_rwf_t)0x00000001)
+
+/* per-IO O_DSYNC */
+#define RWF_DSYNC	((__force __kernel_rwf_t)0x00000002)
+
+/* per-IO O_SYNC */
+#define RWF_SYNC	((__force __kernel_rwf_t)0x00000004)
+
+/* per-IO, return -EAGAIN if operation would block */
+#define RWF_NOWAIT	((__force __kernel_rwf_t)0x00000008)
+
+/* per-IO O_APPEND */
+#define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
+
+/* mask of flags supported by the kernel */
+#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
+			 RWF_APPEND)
+
+/* Pagemap ioctl */
+#define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
+
+/* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */
+#define PAGE_IS_WPALLOWED	(1 << 0)
+#define PAGE_IS_WRITTEN		(1 << 1)
+#define PAGE_IS_FILE		(1 << 2)
+#define PAGE_IS_PRESENT		(1 << 3)
+#define PAGE_IS_SWAPPED		(1 << 4)
+#define PAGE_IS_PFNZERO		(1 << 5)
+#define PAGE_IS_HUGE		(1 << 6)
+#define PAGE_IS_SOFT_DIRTY	(1 << 7)
+
+/*
+ * struct page_region - Page region with flags
+ * @start:	Start of the region
+ * @end:	End of the region (exclusive)
+ * @categories:	PAGE_IS_* category bitmask for the region
+ */
+struct page_region {
+	__u64 start;
+	__u64 end;
+	__u64 categories;
+};
+
+/* Flags for PAGEMAP_SCAN ioctl */
+#define PM_SCAN_WP_MATCHING	(1 << 0)	/* Write protect the pages matched. */
+#define PM_SCAN_CHECK_WPASYNC	(1 << 1)	/* Abort the scan when a non-WP-enabled page is found. */
+
+/*
+ * struct pm_scan_arg - Pagemap ioctl argument
+ * @size:		Size of the structure
+ * @flags:		Flags for the IOCTL
+ * @start:		Starting address of the region
+ * @end:		Ending address of the region
+ * @walk_end		Address where the scan stopped (written by kernel).
+ *			walk_end == end (address tags cleared) informs that the scan completed on entire range.
+ * @vec:		Address of page_region struct array for output
+ * @vec_len:		Length of the page_region struct array
+ * @max_pages:		Optional limit for number of returned pages (0 = disabled)
+ * @category_inverted:	PAGE_IS_* categories which values match if 0 instead of 1
+ * @category_mask:	Skip pages for which any category doesn't match
+ * @category_anyof_mask: Skip pages for which no category matches
+ * @return_mask:	PAGE_IS_* categories that are to be reported in `page_region`s returned
+ */
+struct pm_scan_arg {
+	__u64 size;
+	__u64 flags;
+	__u64 start;
+	__u64 end;
+	__u64 walk_end;
+	__u64 vec;
+	__u64 vec_len;
+	__u64 max_pages;
+	__u64 category_inverted;
+	__u64 category_mask;
+	__u64 category_anyof_mask;
+	__u64 return_mask;
+};
+
+#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/perf/trace/beauty/rename_flags.sh b/tools/perf/trace/beauty/rename_flags.sh
index 94bf7f45d28e..702411dd7a1c 100755
--- a/tools/perf/trace/beauty/rename_flags.sh
+++ b/tools/perf/trace/beauty/rename_flags.sh
@@ -2,7 +2,7 @@
 # Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/uapi/linux/
 
 fs_header=${header_dir}/fs.h
 
diff --git a/tools/perf/trace/beauty/sync_file_range.c b/tools/perf/trace/beauty/sync_file_range.c
index 1c425f04047d..3e8f50ff4fc7 100644
--- a/tools/perf/trace/beauty/sync_file_range.c
+++ b/tools/perf/trace/beauty/sync_file_range.c
@@ -7,7 +7,16 @@
 
 #include "trace/beauty/beauty.h"
 #include <linux/log2.h>
-#include <uapi/linux/fs.h>
+#include <linux/fs.h>
+
+#ifndef SYNC_FILE_RANGE_WRITE_AND_WAIT
+#define SYNC_FILE_RANGE_WAIT_BEFORE     1
+#define SYNC_FILE_RANGE_WRITE           2
+#define SYNC_FILE_RANGE_WAIT_AFTER      4
+#define SYNC_FILE_RANGE_WRITE_AND_WAIT  (SYNC_FILE_RANGE_WRITE | \
+                                         SYNC_FILE_RANGE_WAIT_BEFORE | \
+                                         SYNC_FILE_RANGE_WAIT_AFTER)
+#endif
 
 static size_t sync_file_range__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
 {
diff --git a/tools/perf/trace/beauty/sync_file_range.sh b/tools/perf/trace/beauty/sync_file_range.sh
index 90bf633be879..b1084c4cab63 100755
--- a/tools/perf/trace/beauty/sync_file_range.sh
+++ b/tools/perf/trace/beauty/sync_file_range.sh
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	linux_header_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
 	linux_header_dir=$1
 fi
-- 
cgit 


From ab3316119f9d0b3a1c4b90809ea37ab7927de72b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Mar 2024 17:07:33 -0300
Subject: perf beauty: Move uapi/linux/mount.h copy out of the directory used
 to build perf

It is mostly used only to generate string tables, not to build perf, so
move it to the tools/perf/trace/beauty/include/ hierarchy, that is used
just for scraping.

This is a something that should've have happened, as happened with the
linux/socket.h scrapper, do it now as Ian suggested while doing an
audit/refactor session in the headers used by perf.

No other tools/ living code uses it, just <linux/mount.h> coming from
either 'make install_headers' or from the system /usr/include/
directory.

Suggested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/CAP-5=fWZVrpRufO4w-S4EcSi9STXcTAN2ERLwTSN7yrSSA-otQ@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/mount.h                   | 211 ---------------------
 tools/perf/Makefile.perf                           |  21 +-
 tools/perf/check-headers.sh                        |   2 +-
 tools/perf/trace/beauty/fsconfig.sh                |   6 +-
 tools/perf/trace/beauty/fsmount.sh                 |   6 +-
 tools/perf/trace/beauty/fspick.sh                  |   6 +-
 tools/perf/trace/beauty/include/uapi/linux/mount.h | 211 +++++++++++++++++++++
 tools/perf/trace/beauty/mount_flags.sh             |   6 +-
 tools/perf/trace/beauty/move_mount_flags.sh        |   6 +-
 9 files changed, 237 insertions(+), 238 deletions(-)
 delete mode 100644 tools/include/uapi/linux/mount.h
 create mode 100644 tools/perf/trace/beauty/include/uapi/linux/mount.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
deleted file mode 100644
index ad5478dbad00..000000000000
--- a/tools/include/uapi/linux/mount.h
+++ /dev/null
@@ -1,211 +0,0 @@
-#ifndef _UAPI_LINUX_MOUNT_H
-#define _UAPI_LINUX_MOUNT_H
-
-#include <linux/types.h>
-
-/*
- * These are the fs-independent mount-flags: up to 32 flags are supported
- *
- * Usage of these is restricted within the kernel to core mount(2) code and
- * callers of sys_mount() only.  Filesystems should be using the SB_*
- * equivalent instead.
- */
-#define MS_RDONLY	 1	/* Mount read-only */
-#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
-#define MS_NODEV	 4	/* Disallow access to device special files */
-#define MS_NOEXEC	 8	/* Disallow program execution */
-#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
-#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
-#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
-#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
-#define MS_NOSYMFOLLOW	256	/* Do not follow symlinks */
-#define MS_NOATIME	1024	/* Do not update access times. */
-#define MS_NODIRATIME	2048	/* Do not update directory access times */
-#define MS_BIND		4096
-#define MS_MOVE		8192
-#define MS_REC		16384
-#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
-				   MS_VERBOSE is deprecated. */
-#define MS_SILENT	32768
-#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
-#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
-#define MS_PRIVATE	(1<<18)	/* change to private */
-#define MS_SLAVE	(1<<19)	/* change to slave */
-#define MS_SHARED	(1<<20)	/* change to shared */
-#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
-#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
-#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
-#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
-#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
-
-/* These sb flags are internal to the kernel */
-#define MS_SUBMOUNT     (1<<26)
-#define MS_NOREMOTELOCK	(1<<27)
-#define MS_NOSEC	(1<<28)
-#define MS_BORN		(1<<29)
-#define MS_ACTIVE	(1<<30)
-#define MS_NOUSER	(1<<31)
-
-/*
- * Superblock flags that can be altered by MS_REMOUNT
- */
-#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
-			 MS_LAZYTIME)
-
-/*
- * Old magic mount flag and mask
- */
-#define MS_MGC_VAL 0xC0ED0000
-#define MS_MGC_MSK 0xffff0000
-
-/*
- * open_tree() flags.
- */
-#define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
-#define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
-
-/*
- * move_mount() flags.
- */
-#define MOVE_MOUNT_F_SYMLINKS		0x00000001 /* Follow symlinks on from path */
-#define MOVE_MOUNT_F_AUTOMOUNTS		0x00000002 /* Follow automounts on from path */
-#define MOVE_MOUNT_F_EMPTY_PATH		0x00000004 /* Empty from path permitted */
-#define MOVE_MOUNT_T_SYMLINKS		0x00000010 /* Follow symlinks on to path */
-#define MOVE_MOUNT_T_AUTOMOUNTS		0x00000020 /* Follow automounts on to path */
-#define MOVE_MOUNT_T_EMPTY_PATH		0x00000040 /* Empty to path permitted */
-#define MOVE_MOUNT_SET_GROUP		0x00000100 /* Set sharing group instead */
-#define MOVE_MOUNT_BENEATH		0x00000200 /* Mount beneath top mount */
-#define MOVE_MOUNT__MASK		0x00000377
-
-/*
- * fsopen() flags.
- */
-#define FSOPEN_CLOEXEC		0x00000001
-
-/*
- * fspick() flags.
- */
-#define FSPICK_CLOEXEC		0x00000001
-#define FSPICK_SYMLINK_NOFOLLOW	0x00000002
-#define FSPICK_NO_AUTOMOUNT	0x00000004
-#define FSPICK_EMPTY_PATH	0x00000008
-
-/*
- * The type of fsconfig() call made.
- */
-enum fsconfig_command {
-	FSCONFIG_SET_FLAG	= 0,	/* Set parameter, supplying no value */
-	FSCONFIG_SET_STRING	= 1,	/* Set parameter, supplying a string value */
-	FSCONFIG_SET_BINARY	= 2,	/* Set parameter, supplying a binary blob value */
-	FSCONFIG_SET_PATH	= 3,	/* Set parameter, supplying an object by path */
-	FSCONFIG_SET_PATH_EMPTY	= 4,	/* Set parameter, supplying an object by (empty) path */
-	FSCONFIG_SET_FD		= 5,	/* Set parameter, supplying an object by fd */
-	FSCONFIG_CMD_CREATE	= 6,	/* Create new or reuse existing superblock */
-	FSCONFIG_CMD_RECONFIGURE = 7,	/* Invoke superblock reconfiguration */
-	FSCONFIG_CMD_CREATE_EXCL = 8,	/* Create new superblock, fail if reusing existing superblock */
-};
-
-/*
- * fsmount() flags.
- */
-#define FSMOUNT_CLOEXEC		0x00000001
-
-/*
- * Mount attributes.
- */
-#define MOUNT_ATTR_RDONLY	0x00000001 /* Mount read-only */
-#define MOUNT_ATTR_NOSUID	0x00000002 /* Ignore suid and sgid bits */
-#define MOUNT_ATTR_NODEV	0x00000004 /* Disallow access to device special files */
-#define MOUNT_ATTR_NOEXEC	0x00000008 /* Disallow program execution */
-#define MOUNT_ATTR__ATIME	0x00000070 /* Setting on how atime should be updated */
-#define MOUNT_ATTR_RELATIME	0x00000000 /* - Update atime relative to mtime/ctime. */
-#define MOUNT_ATTR_NOATIME	0x00000010 /* - Do not update access times. */
-#define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
-#define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
-#define MOUNT_ATTR_IDMAP	0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
-#define MOUNT_ATTR_NOSYMFOLLOW	0x00200000 /* Do not follow symlinks */
-
-/*
- * mount_setattr()
- */
-struct mount_attr {
-	__u64 attr_set;
-	__u64 attr_clr;
-	__u64 propagation;
-	__u64 userns_fd;
-};
-
-/* List of all mount_attr versions. */
-#define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
-
-
-/*
- * Structure for getting mount/superblock/filesystem info with statmount(2).
- *
- * The interface is similar to statx(2): individual fields or groups can be
- * selected with the @mask argument of statmount().  Kernel will set the @mask
- * field according to the supported fields.
- *
- * If string fields are selected, then the caller needs to pass a buffer that
- * has space after the fixed part of the structure.  Nul terminated strings are
- * copied there and offsets relative to @str are stored in the relevant fields.
- * If the buffer is too small, then EOVERFLOW is returned.  The actually used
- * size is returned in @size.
- */
-struct statmount {
-	__u32 size;		/* Total size, including strings */
-	__u32 __spare1;
-	__u64 mask;		/* What results were written */
-	__u32 sb_dev_major;	/* Device ID */
-	__u32 sb_dev_minor;
-	__u64 sb_magic;		/* ..._SUPER_MAGIC */
-	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
-	__u32 fs_type;		/* [str] Filesystem type */
-	__u64 mnt_id;		/* Unique ID of mount */
-	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
-	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
-	__u32 mnt_parent_id_old;
-	__u64 mnt_attr;		/* MOUNT_ATTR_... */
-	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
-	__u64 mnt_peer_group;	/* ID of shared peer group */
-	__u64 mnt_master;	/* Mount receives propagation from this ID */
-	__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];
-	char str[];		/* Variable size part containing strings */
-};
-
-/*
- * Structure for passing mount ID and miscellaneous parameters to statmount(2)
- * and listmount(2).
- *
- * For statmount(2) @param represents the request mask.
- * For listmount(2) @param represents the last listed mount id (or zero).
- */
-struct mnt_id_req {
-	__u32 size;
-	__u32 spare;
-	__u64 mnt_id;
-	__u64 param;
-};
-
-/* List of all mnt_id_req versions. */
-#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
-
-/*
- * @mask bits for statmount(2)
- */
-#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
-#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
-#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
-#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 */
-
-/*
- * Special @mnt_id values that can be passed to listmount
- */
-#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
-
-#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 643e9fa6ec89..523c3b7d6c9d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -500,20 +500,20 @@ $(fadvise_advice_array): $(linux_uapi_dir)/in.h $(fadvise_advice_tbl)
 fsmount_arrays := $(beauty_outdir)/fsmount_arrays.c
 fsmount_tbls := $(srctree)/tools/perf/trace/beauty/fsmount.sh
 
-$(fsmount_arrays): $(linux_uapi_dir)/mount.h $(fsmount_tbls)
-	$(Q)$(SHELL) '$(fsmount_tbls)' $(linux_uapi_dir) > $@
+$(fsmount_arrays): $(beauty_uapi_linux_dir)/mount.h $(fsmount_tbls)
+	$(Q)$(SHELL) '$(fsmount_tbls)' $(beauty_uapi_linux_dir) > $@
 
 fspick_arrays := $(beauty_outdir)/fspick_arrays.c
 fspick_tbls := $(srctree)/tools/perf/trace/beauty/fspick.sh
 
-$(fspick_arrays): $(linux_uapi_dir)/mount.h $(fspick_tbls)
-	$(Q)$(SHELL) '$(fspick_tbls)' $(linux_uapi_dir) > $@
+$(fspick_arrays): $(beauty_uapi_linux_dir)/mount.h $(fspick_tbls)
+	$(Q)$(SHELL) '$(fspick_tbls)' $(beauty_uapi_linux_dir) > $@
 
 fsconfig_arrays := $(beauty_outdir)/fsconfig_arrays.c
 fsconfig_tbls := $(srctree)/tools/perf/trace/beauty/fsconfig.sh
 
-$(fsconfig_arrays): $(linux_uapi_dir)/mount.h $(fsconfig_tbls)
-	$(Q)$(SHELL) '$(fsconfig_tbls)' $(linux_uapi_dir) > $@
+$(fsconfig_arrays): $(beauty_uapi_linux_dir)/mount.h $(fsconfig_tbls)
+	$(Q)$(SHELL) '$(fsconfig_tbls)' $(beauty_uapi_linux_dir) > $@
 
 pkey_alloc_access_rights_array := $(beauty_outdir)/pkey_alloc_access_rights_array.c
 asm_generic_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
@@ -598,15 +598,14 @@ $(mremap_flags_array): $(linux_uapi_dir)/mman.h $(mremap_flags_tbl)
 mount_flags_array := $(beauty_outdir)/mount_flags_array.c
 mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
 
-$(mount_flags_array): $(linux_uapi_dir)/mount.h $(mount_flags_tbl)
-	$(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
+$(mount_flags_array): $(beauty_uapi_linux_dir)/mount.h $(mount_flags_tbl)
+	$(Q)$(SHELL) '$(mount_flags_tbl)' $(beauty_uapi_linux_dir) > $@
 
 move_mount_flags_array := $(beauty_outdir)/move_mount_flags_array.c
 move_mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/move_mount_flags.sh
 
-$(move_mount_flags_array): $(linux_uapi_dir)/mount.h $(move_mount_flags_tbl)
-	$(Q)$(SHELL) '$(move_mount_flags_tbl)' $(linux_uapi_dir) > $@
-
+$(move_mount_flags_array): $(beauty_uapi_linux_dir)/mount.h $(move_mount_flags_tbl)
+	$(Q)$(SHELL) '$(move_mount_flags_tbl)' $(beauty_uapi_linux_dir) > $@
 
 mmap_prot_array := $(beauty_outdir)/mmap_prot_array.c
 mmap_prot_tbl := $(srctree)/tools/perf/trace/beauty/mmap_prot.sh
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 015f74137b75..c2c26d6b87ef 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -15,7 +15,6 @@ FILES=(
   "include/uapi/linux/kcmp.h"
   "include/uapi/linux/kvm.h"
   "include/uapi/linux/in.h"
-  "include/uapi/linux/mount.h"
   "include/uapi/linux/openat2.h"
   "include/uapi/linux/perf_event.h"
   "include/uapi/linux/prctl.h"
@@ -98,6 +97,7 @@ declare -a BEAUTY_FILES
 BEAUTY_FILES=(
   "include/linux/socket.h"
   "include/uapi/linux/fs.h"
+  "include/uapi/linux/mount.h"
 )
 
 declare -a FAILURES
diff --git a/tools/perf/trace/beauty/fsconfig.sh b/tools/perf/trace/beauty/fsconfig.sh
index bc6ef7bb7a5f..09cee79de00c 100755
--- a/tools/perf/trace/beauty/fsconfig.sh
+++ b/tools/perf/trace/beauty/fsconfig.sh
@@ -2,12 +2,12 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
-	linux_header_dir=$1
+	beauty_uapi_linux_dir=$1
 fi
 
-linux_mount=${linux_header_dir}/mount.h
+linux_mount=${beauty_uapi_linux_dir}/mount.h
 
 printf "static const char *fsconfig_cmds[] = {\n"
 ms='[[:space:]]*'
diff --git a/tools/perf/trace/beauty/fsmount.sh b/tools/perf/trace/beauty/fsmount.sh
index cba8897a751f..6b67a54cdeee 100755
--- a/tools/perf/trace/beauty/fsmount.sh
+++ b/tools/perf/trace/beauty/fsmount.sh
@@ -2,12 +2,12 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
-	linux_header_dir=$1
+	beauty_uapi_linux_dir=$1
 fi
 
-linux_mount=${linux_header_dir}/mount.h
+linux_mount=${beauty_uapi_linux_dir}/mount.h
 
 # Remove MOUNT_ATTR_RELATIME as it is zeros, handle it a special way in the beautifier
 # Only handle MOUNT_ATTR_ followed by a capital letter/num as __ is special case
diff --git a/tools/perf/trace/beauty/fspick.sh b/tools/perf/trace/beauty/fspick.sh
index 1f088329b96e..0d9951c22b95 100755
--- a/tools/perf/trace/beauty/fspick.sh
+++ b/tools/perf/trace/beauty/fspick.sh
@@ -2,12 +2,12 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
-	linux_header_dir=$1
+	beauty_uapi_linux_dir=$1
 fi
 
-linux_mount=${linux_header_dir}/mount.h
+linux_mount=${beauty_uapi_linux_dir}/mount.h
 
 printf "static const char *fspick_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+FSPICK_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
new file mode 100644
index 000000000000..ad5478dbad00
--- /dev/null
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
@@ -0,0 +1,211 @@
+#ifndef _UAPI_LINUX_MOUNT_H
+#define _UAPI_LINUX_MOUNT_H
+
+#include <linux/types.h>
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ *
+ * Usage of these is restricted within the kernel to core mount(2) code and
+ * callers of sys_mount() only.  Filesystems should be using the SB_*
+ * equivalent instead.
+ */
+#define MS_RDONLY	 1	/* Mount read-only */
+#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
+#define MS_NODEV	 4	/* Disallow access to device special files */
+#define MS_NOEXEC	 8	/* Disallow program execution */
+#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
+#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
+#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
+#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOSYMFOLLOW	256	/* Do not follow symlinks */
+#define MS_NOATIME	1024	/* Do not update access times. */
+#define MS_NODIRATIME	2048	/* Do not update directory access times */
+#define MS_BIND		4096
+#define MS_MOVE		8192
+#define MS_REC		16384
+#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
+				   MS_VERBOSE is deprecated. */
+#define MS_SILENT	32768
+#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
+#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
+#define MS_PRIVATE	(1<<18)	/* change to private */
+#define MS_SLAVE	(1<<19)	/* change to slave */
+#define MS_SHARED	(1<<20)	/* change to shared */
+#define MS_RELATIME	(1<<21)	/* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION	(1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT     (1<<26)
+#define MS_NOREMOTELOCK	(1<<27)
+#define MS_NOSEC	(1<<28)
+#define MS_BORN		(1<<29)
+#define MS_ACTIVE	(1<<30)
+#define MS_NOUSER	(1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+			 MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+/*
+ * open_tree() flags.
+ */
+#define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
+
+/*
+ * move_mount() flags.
+ */
+#define MOVE_MOUNT_F_SYMLINKS		0x00000001 /* Follow symlinks on from path */
+#define MOVE_MOUNT_F_AUTOMOUNTS		0x00000002 /* Follow automounts on from path */
+#define MOVE_MOUNT_F_EMPTY_PATH		0x00000004 /* Empty from path permitted */
+#define MOVE_MOUNT_T_SYMLINKS		0x00000010 /* Follow symlinks on to path */
+#define MOVE_MOUNT_T_AUTOMOUNTS		0x00000020 /* Follow automounts on to path */
+#define MOVE_MOUNT_T_EMPTY_PATH		0x00000040 /* Empty to path permitted */
+#define MOVE_MOUNT_SET_GROUP		0x00000100 /* Set sharing group instead */
+#define MOVE_MOUNT_BENEATH		0x00000200 /* Mount beneath top mount */
+#define MOVE_MOUNT__MASK		0x00000377
+
+/*
+ * fsopen() flags.
+ */
+#define FSOPEN_CLOEXEC		0x00000001
+
+/*
+ * fspick() flags.
+ */
+#define FSPICK_CLOEXEC		0x00000001
+#define FSPICK_SYMLINK_NOFOLLOW	0x00000002
+#define FSPICK_NO_AUTOMOUNT	0x00000004
+#define FSPICK_EMPTY_PATH	0x00000008
+
+/*
+ * The type of fsconfig() call made.
+ */
+enum fsconfig_command {
+	FSCONFIG_SET_FLAG	= 0,	/* Set parameter, supplying no value */
+	FSCONFIG_SET_STRING	= 1,	/* Set parameter, supplying a string value */
+	FSCONFIG_SET_BINARY	= 2,	/* Set parameter, supplying a binary blob value */
+	FSCONFIG_SET_PATH	= 3,	/* Set parameter, supplying an object by path */
+	FSCONFIG_SET_PATH_EMPTY	= 4,	/* Set parameter, supplying an object by (empty) path */
+	FSCONFIG_SET_FD		= 5,	/* Set parameter, supplying an object by fd */
+	FSCONFIG_CMD_CREATE	= 6,	/* Create new or reuse existing superblock */
+	FSCONFIG_CMD_RECONFIGURE = 7,	/* Invoke superblock reconfiguration */
+	FSCONFIG_CMD_CREATE_EXCL = 8,	/* Create new superblock, fail if reusing existing superblock */
+};
+
+/*
+ * fsmount() flags.
+ */
+#define FSMOUNT_CLOEXEC		0x00000001
+
+/*
+ * Mount attributes.
+ */
+#define MOUNT_ATTR_RDONLY	0x00000001 /* Mount read-only */
+#define MOUNT_ATTR_NOSUID	0x00000002 /* Ignore suid and sgid bits */
+#define MOUNT_ATTR_NODEV	0x00000004 /* Disallow access to device special files */
+#define MOUNT_ATTR_NOEXEC	0x00000008 /* Disallow program execution */
+#define MOUNT_ATTR__ATIME	0x00000070 /* Setting on how atime should be updated */
+#define MOUNT_ATTR_RELATIME	0x00000000 /* - Update atime relative to mtime/ctime. */
+#define MOUNT_ATTR_NOATIME	0x00000010 /* - Do not update access times. */
+#define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
+#define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
+#define MOUNT_ATTR_IDMAP	0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+#define MOUNT_ATTR_NOSYMFOLLOW	0x00200000 /* Do not follow symlinks */
+
+/*
+ * mount_setattr()
+ */
+struct mount_attr {
+	__u64 attr_set;
+	__u64 attr_clr;
+	__u64 propagation;
+	__u64 userns_fd;
+};
+
+/* List of all mount_attr versions. */
+#define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
+
+
+/*
+ * Structure for getting mount/superblock/filesystem info with statmount(2).
+ *
+ * The interface is similar to statx(2): individual fields or groups can be
+ * selected with the @mask argument of statmount().  Kernel will set the @mask
+ * field according to the supported fields.
+ *
+ * If string fields are selected, then the caller needs to pass a buffer that
+ * has space after the fixed part of the structure.  Nul terminated strings are
+ * copied there and offsets relative to @str are stored in the relevant fields.
+ * If the buffer is too small, then EOVERFLOW is returned.  The actually used
+ * size is returned in @size.
+ */
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 __spare1;
+	__u64 mask;		/* What results were written */
+	__u32 sb_dev_major;	/* Device ID */
+	__u32 sb_dev_minor;
+	__u64 sb_magic;		/* ..._SUPER_MAGIC */
+	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
+	__u32 fs_type;		/* [str] Filesystem type */
+	__u64 mnt_id;		/* Unique ID of mount */
+	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
+	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
+	__u32 mnt_parent_id_old;
+	__u64 mnt_attr;		/* MOUNT_ATTR_... */
+	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
+	__u64 mnt_peer_group;	/* ID of shared peer group */
+	__u64 mnt_master;	/* Mount receives propagation from this ID */
+	__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];
+	char str[];		/* Variable size part containing strings */
+};
+
+/*
+ * Structure for passing mount ID and miscellaneous parameters to statmount(2)
+ * and listmount(2).
+ *
+ * For statmount(2) @param represents the request mask.
+ * For listmount(2) @param represents the last listed mount id (or zero).
+ */
+struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
+	__u64 mnt_id;
+	__u64 param;
+};
+
+/* List of all mnt_id_req versions. */
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+
+/*
+ * @mask bits for statmount(2)
+ */
+#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
+#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
+#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 */
+
+/*
+ * Special @mnt_id values that can be passed to listmount
+ */
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+
+#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/perf/trace/beauty/mount_flags.sh b/tools/perf/trace/beauty/mount_flags.sh
index 730099a9a67c..ff578f7b451b 100755
--- a/tools/perf/trace/beauty/mount_flags.sh
+++ b/tools/perf/trace/beauty/mount_flags.sh
@@ -1,15 +1,15 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && beauty_uapi_linux_dir=$1 || beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 
 printf "static const char *mount_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
-grep -E $regex ${header_dir}/mount.h | grep -E -v '(MSK|VERBOSE|MGC_VAL)\>' | \
+grep -E $regex ${beauty_uapi_linux_dir}/mount.h | grep -E -v '(MSK|VERBOSE|MGC_VAL)\>' | \
 	sed -r "s/$regex/\2 \2 \1/g" | sort -n | \
 	xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+\(1<<([[:digit:]]+)\)[[:space:]]*.*'
-grep -E $regex ${header_dir}/mount.h | \
+grep -E $regex ${beauty_uapi_linux_dir}/mount.h | \
 	sed -r "s/$regex/\2 \1/g" | \
 	xargs printf "\t[%s + 1] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/trace/beauty/move_mount_flags.sh b/tools/perf/trace/beauty/move_mount_flags.sh
index ce5e632d1448..c0dde9020bc3 100755
--- a/tools/perf/trace/beauty/move_mount_flags.sh
+++ b/tools/perf/trace/beauty/move_mount_flags.sh
@@ -2,12 +2,12 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
-	linux_header_dir=$1
+	beauty_uapi_linux_dir=$1
 fi
 
-linux_mount=${linux_header_dir}/mount.h
+linux_mount=${beauty_uapi_linux_dir}/mount.h
 
 printf "static const char *move_mount_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOVE_MOUNT_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
-- 
cgit 


From 44512bd6136ec7bb31e4dfaaf49313d91539af6f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Mar 2024 17:07:33 -0300
Subject: perf beauty: Move uapi/linux/usbdevice_fs.h copy out of the directory
 used to build perf

It is mostly used only to generate string tables, not to build perf, so
move it to the tools/perf/trace/beauty/include/ hierarchy, that is used
just for scraping.

This is a something that should've have happened, as happened with the
linux/socket.h scrapper, do it now as Ian suggested while doing an
audit/refactor session in the headers used by perf.

No other tools/ living code uses it, just <linux/usbdevice_fs.h> coming
from either 'make install_headers' or from the system /usr/include/
directory.

Suggested-by: Ian Rogers <irogers@google.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/CAP-5=fWZVrpRufO4w-S4EcSi9STXcTAN2ERLwTSN7yrSSA-otQ@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/usbdevice_fs.h            | 231 ---------------------
 tools/perf/Makefile.perf                           |   4 +-
 tools/perf/check-headers.sh                        |   2 +-
 .../trace/beauty/include/uapi/linux/usbdevice_fs.h | 231 +++++++++++++++++++++
 tools/perf/trace/beauty/usbdevfs_ioctl.sh          |   6 +-
 5 files changed, 237 insertions(+), 237 deletions(-)
 delete mode 100644 tools/include/uapi/linux/usbdevice_fs.h
 create mode 100644 tools/perf/trace/beauty/include/uapi/linux/usbdevice_fs.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
deleted file mode 100644
index 74a84e02422a..000000000000
--- a/tools/include/uapi/linux/usbdevice_fs.h
+++ /dev/null
@@ -1,231 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-/*****************************************************************************/
-
-/*
- *	usbdevice_fs.h  --  USB device file system.
- *
- *	Copyright (C) 2000
- *          Thomas Sailer (sailer@ife.ee.ethz.ch)
- *
- *	This program is free software; you can redistribute it and/or modify
- *	it under the terms of the GNU General Public License as published by
- *	the Free Software Foundation; either version 2 of the License, or
- *	(at your option) any later version.
- *
- *	This program is distributed in the hope that it will be useful,
- *	but WITHOUT ANY WARRANTY; without even the implied warranty of
- *	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *	GNU General Public License for more details.
- *
- *	You should have received a copy of the GNU General Public License
- *	along with this program; if not, write to the Free Software
- *	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- *  History:
- *   0.1  04.01.2000  Created
- */
-
-/*****************************************************************************/
-
-#ifndef _UAPI_LINUX_USBDEVICE_FS_H
-#define _UAPI_LINUX_USBDEVICE_FS_H
-
-#include <linux/types.h>
-#include <linux/magic.h>
-
-/* --------------------------------------------------------------------- */
-
-/* usbdevfs ioctl codes */
-
-struct usbdevfs_ctrltransfer {
-	__u8 bRequestType;
-	__u8 bRequest;
-	__u16 wValue;
-	__u16 wIndex;
-	__u16 wLength;
-	__u32 timeout;  /* in milliseconds */
- 	void __user *data;
-};
-
-struct usbdevfs_bulktransfer {
-	unsigned int ep;
-	unsigned int len;
-	unsigned int timeout; /* in milliseconds */
-	void __user *data;
-};
-
-struct usbdevfs_setinterface {
-	unsigned int interface;
-	unsigned int altsetting;
-};
-
-struct usbdevfs_disconnectsignal {
-	unsigned int signr;
-	void __user *context;
-};
-
-#define USBDEVFS_MAXDRIVERNAME 255
-
-struct usbdevfs_getdriver {
-	unsigned int interface;
-	char driver[USBDEVFS_MAXDRIVERNAME + 1];
-};
-
-struct usbdevfs_connectinfo {
-	unsigned int devnum;
-	unsigned char slow;
-};
-
-struct usbdevfs_conninfo_ex {
-	__u32 size;		/* Size of the structure from the kernel's */
-				/* point of view. Can be used by userspace */
-				/* to determine how much data can be       */
-				/* used/trusted.                           */
-	__u32 busnum;           /* USB bus number, as enumerated by the    */
-				/* kernel, the device is connected to.     */
-	__u32 devnum;           /* Device address on the bus.              */
-	__u32 speed;		/* USB_SPEED_* constants from ch9.h        */
-	__u8 num_ports;		/* Number of ports the device is connected */
-				/* to on the way to the root hub. It may   */
-				/* be bigger than size of 'ports' array so */
-				/* userspace can detect overflows.         */
-	__u8 ports[7];		/* List of ports on the way from the root  */
-				/* hub to the device. Current limit in     */
-				/* USB specification is 7 tiers (root hub, */
-				/* 5 intermediate hubs, device), which     */
-				/* gives at most 6 port entries.           */
-};
-
-#define USBDEVFS_URB_SHORT_NOT_OK	0x01
-#define USBDEVFS_URB_ISO_ASAP		0x02
-#define USBDEVFS_URB_BULK_CONTINUATION	0x04
-#define USBDEVFS_URB_NO_FSBR		0x20	/* Not used */
-#define USBDEVFS_URB_ZERO_PACKET	0x40
-#define USBDEVFS_URB_NO_INTERRUPT	0x80
-
-#define USBDEVFS_URB_TYPE_ISO		   0
-#define USBDEVFS_URB_TYPE_INTERRUPT	   1
-#define USBDEVFS_URB_TYPE_CONTROL	   2
-#define USBDEVFS_URB_TYPE_BULK		   3
-
-struct usbdevfs_iso_packet_desc {
-	unsigned int length;
-	unsigned int actual_length;
-	unsigned int status;
-};
-
-struct usbdevfs_urb {
-	unsigned char type;
-	unsigned char endpoint;
-	int status;
-	unsigned int flags;
-	void __user *buffer;
-	int buffer_length;
-	int actual_length;
-	int start_frame;
-	union {
-		int number_of_packets;	/* Only used for isoc urbs */
-		unsigned int stream_id;	/* Only used with bulk streams */
-	};
-	int error_count;
-	unsigned int signr;	/* signal to be sent on completion,
-				  or 0 if none should be sent. */
-	void __user *usercontext;
-	struct usbdevfs_iso_packet_desc iso_frame_desc[];
-};
-
-/* ioctls for talking directly to drivers */
-struct usbdevfs_ioctl {
-	int	ifno;		/* interface 0..N ; negative numbers reserved */
-	int	ioctl_code;	/* MUST encode size + direction of data so the
-				 * macros in <asm/ioctl.h> give correct values */
-	void __user *data;	/* param buffer (in, or out) */
-};
-
-/* You can do most things with hubs just through control messages,
- * except find out what device connects to what port. */
-struct usbdevfs_hub_portinfo {
-	char nports;		/* number of downstream ports in this hub */
-	char port [127];	/* e.g. port 3 connects to device 27 */
-};
-
-/* System and bus capability flags */
-#define USBDEVFS_CAP_ZERO_PACKET		0x01
-#define USBDEVFS_CAP_BULK_CONTINUATION		0x02
-#define USBDEVFS_CAP_NO_PACKET_SIZE_LIM		0x04
-#define USBDEVFS_CAP_BULK_SCATTER_GATHER	0x08
-#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT	0x10
-#define USBDEVFS_CAP_MMAP			0x20
-#define USBDEVFS_CAP_DROP_PRIVILEGES		0x40
-#define USBDEVFS_CAP_CONNINFO_EX		0x80
-#define USBDEVFS_CAP_SUSPEND			0x100
-
-/* USBDEVFS_DISCONNECT_CLAIM flags & struct */
-
-/* disconnect-and-claim if the driver matches the driver field */
-#define USBDEVFS_DISCONNECT_CLAIM_IF_DRIVER	0x01
-/* disconnect-and-claim except when the driver matches the driver field */
-#define USBDEVFS_DISCONNECT_CLAIM_EXCEPT_DRIVER	0x02
-
-struct usbdevfs_disconnect_claim {
-	unsigned int interface;
-	unsigned int flags;
-	char driver[USBDEVFS_MAXDRIVERNAME + 1];
-};
-
-struct usbdevfs_streams {
-	unsigned int num_streams; /* Not used by USBDEVFS_FREE_STREAMS */
-	unsigned int num_eps;
-	unsigned char eps[];
-};
-
-/*
- * USB_SPEED_* values returned by USBDEVFS_GET_SPEED are defined in
- * linux/usb/ch9.h
- */
-
-#define USBDEVFS_CONTROL           _IOWR('U', 0, struct usbdevfs_ctrltransfer)
-#define USBDEVFS_CONTROL32           _IOWR('U', 0, struct usbdevfs_ctrltransfer32)
-#define USBDEVFS_BULK              _IOWR('U', 2, struct usbdevfs_bulktransfer)
-#define USBDEVFS_BULK32              _IOWR('U', 2, struct usbdevfs_bulktransfer32)
-#define USBDEVFS_RESETEP           _IOR('U', 3, unsigned int)
-#define USBDEVFS_SETINTERFACE      _IOR('U', 4, struct usbdevfs_setinterface)
-#define USBDEVFS_SETCONFIGURATION  _IOR('U', 5, unsigned int)
-#define USBDEVFS_GETDRIVER         _IOW('U', 8, struct usbdevfs_getdriver)
-#define USBDEVFS_SUBMITURB         _IOR('U', 10, struct usbdevfs_urb)
-#define USBDEVFS_SUBMITURB32       _IOR('U', 10, struct usbdevfs_urb32)
-#define USBDEVFS_DISCARDURB        _IO('U', 11)
-#define USBDEVFS_REAPURB           _IOW('U', 12, void *)
-#define USBDEVFS_REAPURB32         _IOW('U', 12, __u32)
-#define USBDEVFS_REAPURBNDELAY     _IOW('U', 13, void *)
-#define USBDEVFS_REAPURBNDELAY32   _IOW('U', 13, __u32)
-#define USBDEVFS_DISCSIGNAL        _IOR('U', 14, struct usbdevfs_disconnectsignal)
-#define USBDEVFS_DISCSIGNAL32      _IOR('U', 14, struct usbdevfs_disconnectsignal32)
-#define USBDEVFS_CLAIMINTERFACE    _IOR('U', 15, unsigned int)
-#define USBDEVFS_RELEASEINTERFACE  _IOR('U', 16, unsigned int)
-#define USBDEVFS_CONNECTINFO       _IOW('U', 17, struct usbdevfs_connectinfo)
-#define USBDEVFS_IOCTL             _IOWR('U', 18, struct usbdevfs_ioctl)
-#define USBDEVFS_IOCTL32           _IOWR('U', 18, struct usbdevfs_ioctl32)
-#define USBDEVFS_HUB_PORTINFO      _IOR('U', 19, struct usbdevfs_hub_portinfo)
-#define USBDEVFS_RESET             _IO('U', 20)
-#define USBDEVFS_CLEAR_HALT        _IOR('U', 21, unsigned int)
-#define USBDEVFS_DISCONNECT        _IO('U', 22)
-#define USBDEVFS_CONNECT           _IO('U', 23)
-#define USBDEVFS_CLAIM_PORT        _IOR('U', 24, unsigned int)
-#define USBDEVFS_RELEASE_PORT      _IOR('U', 25, unsigned int)
-#define USBDEVFS_GET_CAPABILITIES  _IOR('U', 26, __u32)
-#define USBDEVFS_DISCONNECT_CLAIM  _IOR('U', 27, struct usbdevfs_disconnect_claim)
-#define USBDEVFS_ALLOC_STREAMS     _IOR('U', 28, struct usbdevfs_streams)
-#define USBDEVFS_FREE_STREAMS      _IOR('U', 29, struct usbdevfs_streams)
-#define USBDEVFS_DROP_PRIVILEGES   _IOW('U', 30, __u32)
-#define USBDEVFS_GET_SPEED         _IO('U', 31)
-/*
- * Returns struct usbdevfs_conninfo_ex; length is variable to allow
- * extending size of the data returned.
- */
-#define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
-#define USBDEVFS_FORBID_SUSPEND    _IO('U', 33)
-#define USBDEVFS_ALLOW_SUSPEND     _IO('U', 34)
-#define USBDEVFS_WAIT_FOR_RESUME   _IO('U', 35)
-
-#endif /* _UAPI_LINUX_USBDEVICE_FS_H */
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 523c3b7d6c9d..53ec3765b4b2 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -623,8 +623,8 @@ $(prctl_option_array): $(prctl_hdr_dir)/prctl.h $(prctl_option_tbl)
 usbdevfs_ioctl_array := $(beauty_ioctl_outdir)/usbdevfs_ioctl_array.c
 usbdevfs_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/usbdevfs_ioctl.sh
 
-$(usbdevfs_ioctl_array): $(linux_uapi_dir)/usbdevice_fs.h $(usbdevfs_ioctl_tbl)
-	$(Q)$(SHELL) '$(usbdevfs_ioctl_tbl)' $(linux_uapi_dir) > $@
+$(usbdevfs_ioctl_array): $(beauty_uapi_linux_dir)/usbdevice_fs.h $(usbdevfs_ioctl_tbl)
+	$(Q)$(SHELL) '$(usbdevfs_ioctl_tbl)' $(beauty_uapi_linux_dir) > $@
 
 x86_arch_prctl_code_array := $(beauty_outdir)/x86_arch_prctl_code_array.c
 x86_arch_prctl_code_tbl := $(srctree)/tools/perf/trace/beauty/x86_arch_prctl.sh
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index c2c26d6b87ef..356ddb76a954 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -21,7 +21,6 @@ FILES=(
   "include/uapi/linux/sched.h"
   "include/uapi/linux/seccomp.h"
   "include/uapi/linux/stat.h"
-  "include/uapi/linux/usbdevice_fs.h"
   "include/uapi/linux/vhost.h"
   "include/uapi/sound/asound.h"
   "include/linux/bits.h"
@@ -98,6 +97,7 @@ BEAUTY_FILES=(
   "include/linux/socket.h"
   "include/uapi/linux/fs.h"
   "include/uapi/linux/mount.h"
+  "include/uapi/linux/usbdevice_fs.h"
 )
 
 declare -a FAILURES
diff --git a/tools/perf/trace/beauty/include/uapi/linux/usbdevice_fs.h b/tools/perf/trace/beauty/include/uapi/linux/usbdevice_fs.h
new file mode 100644
index 000000000000..74a84e02422a
--- /dev/null
+++ b/tools/perf/trace/beauty/include/uapi/linux/usbdevice_fs.h
@@ -0,0 +1,231 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*****************************************************************************/
+
+/*
+ *	usbdevice_fs.h  --  USB device file system.
+ *
+ *	Copyright (C) 2000
+ *          Thomas Sailer (sailer@ife.ee.ethz.ch)
+ *
+ *	This program is free software; you can redistribute it and/or modify
+ *	it under the terms of the GNU General Public License as published by
+ *	the Free Software Foundation; either version 2 of the License, or
+ *	(at your option) any later version.
+ *
+ *	This program is distributed in the hope that it will be useful,
+ *	but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *	GNU General Public License for more details.
+ *
+ *	You should have received a copy of the GNU General Public License
+ *	along with this program; if not, write to the Free Software
+ *	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *  History:
+ *   0.1  04.01.2000  Created
+ */
+
+/*****************************************************************************/
+
+#ifndef _UAPI_LINUX_USBDEVICE_FS_H
+#define _UAPI_LINUX_USBDEVICE_FS_H
+
+#include <linux/types.h>
+#include <linux/magic.h>
+
+/* --------------------------------------------------------------------- */
+
+/* usbdevfs ioctl codes */
+
+struct usbdevfs_ctrltransfer {
+	__u8 bRequestType;
+	__u8 bRequest;
+	__u16 wValue;
+	__u16 wIndex;
+	__u16 wLength;
+	__u32 timeout;  /* in milliseconds */
+ 	void __user *data;
+};
+
+struct usbdevfs_bulktransfer {
+	unsigned int ep;
+	unsigned int len;
+	unsigned int timeout; /* in milliseconds */
+	void __user *data;
+};
+
+struct usbdevfs_setinterface {
+	unsigned int interface;
+	unsigned int altsetting;
+};
+
+struct usbdevfs_disconnectsignal {
+	unsigned int signr;
+	void __user *context;
+};
+
+#define USBDEVFS_MAXDRIVERNAME 255
+
+struct usbdevfs_getdriver {
+	unsigned int interface;
+	char driver[USBDEVFS_MAXDRIVERNAME + 1];
+};
+
+struct usbdevfs_connectinfo {
+	unsigned int devnum;
+	unsigned char slow;
+};
+
+struct usbdevfs_conninfo_ex {
+	__u32 size;		/* Size of the structure from the kernel's */
+				/* point of view. Can be used by userspace */
+				/* to determine how much data can be       */
+				/* used/trusted.                           */
+	__u32 busnum;           /* USB bus number, as enumerated by the    */
+				/* kernel, the device is connected to.     */
+	__u32 devnum;           /* Device address on the bus.              */
+	__u32 speed;		/* USB_SPEED_* constants from ch9.h        */
+	__u8 num_ports;		/* Number of ports the device is connected */
+				/* to on the way to the root hub. It may   */
+				/* be bigger than size of 'ports' array so */
+				/* userspace can detect overflows.         */
+	__u8 ports[7];		/* List of ports on the way from the root  */
+				/* hub to the device. Current limit in     */
+				/* USB specification is 7 tiers (root hub, */
+				/* 5 intermediate hubs, device), which     */
+				/* gives at most 6 port entries.           */
+};
+
+#define USBDEVFS_URB_SHORT_NOT_OK	0x01
+#define USBDEVFS_URB_ISO_ASAP		0x02
+#define USBDEVFS_URB_BULK_CONTINUATION	0x04
+#define USBDEVFS_URB_NO_FSBR		0x20	/* Not used */
+#define USBDEVFS_URB_ZERO_PACKET	0x40
+#define USBDEVFS_URB_NO_INTERRUPT	0x80
+
+#define USBDEVFS_URB_TYPE_ISO		   0
+#define USBDEVFS_URB_TYPE_INTERRUPT	   1
+#define USBDEVFS_URB_TYPE_CONTROL	   2
+#define USBDEVFS_URB_TYPE_BULK		   3
+
+struct usbdevfs_iso_packet_desc {
+	unsigned int length;
+	unsigned int actual_length;
+	unsigned int status;
+};
+
+struct usbdevfs_urb {
+	unsigned char type;
+	unsigned char endpoint;
+	int status;
+	unsigned int flags;
+	void __user *buffer;
+	int buffer_length;
+	int actual_length;
+	int start_frame;
+	union {
+		int number_of_packets;	/* Only used for isoc urbs */
+		unsigned int stream_id;	/* Only used with bulk streams */
+	};
+	int error_count;
+	unsigned int signr;	/* signal to be sent on completion,
+				  or 0 if none should be sent. */
+	void __user *usercontext;
+	struct usbdevfs_iso_packet_desc iso_frame_desc[];
+};
+
+/* ioctls for talking directly to drivers */
+struct usbdevfs_ioctl {
+	int	ifno;		/* interface 0..N ; negative numbers reserved */
+	int	ioctl_code;	/* MUST encode size + direction of data so the
+				 * macros in <asm/ioctl.h> give correct values */
+	void __user *data;	/* param buffer (in, or out) */
+};
+
+/* You can do most things with hubs just through control messages,
+ * except find out what device connects to what port. */
+struct usbdevfs_hub_portinfo {
+	char nports;		/* number of downstream ports in this hub */
+	char port [127];	/* e.g. port 3 connects to device 27 */
+};
+
+/* System and bus capability flags */
+#define USBDEVFS_CAP_ZERO_PACKET		0x01
+#define USBDEVFS_CAP_BULK_CONTINUATION		0x02
+#define USBDEVFS_CAP_NO_PACKET_SIZE_LIM		0x04
+#define USBDEVFS_CAP_BULK_SCATTER_GATHER	0x08
+#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT	0x10
+#define USBDEVFS_CAP_MMAP			0x20
+#define USBDEVFS_CAP_DROP_PRIVILEGES		0x40
+#define USBDEVFS_CAP_CONNINFO_EX		0x80
+#define USBDEVFS_CAP_SUSPEND			0x100
+
+/* USBDEVFS_DISCONNECT_CLAIM flags & struct */
+
+/* disconnect-and-claim if the driver matches the driver field */
+#define USBDEVFS_DISCONNECT_CLAIM_IF_DRIVER	0x01
+/* disconnect-and-claim except when the driver matches the driver field */
+#define USBDEVFS_DISCONNECT_CLAIM_EXCEPT_DRIVER	0x02
+
+struct usbdevfs_disconnect_claim {
+	unsigned int interface;
+	unsigned int flags;
+	char driver[USBDEVFS_MAXDRIVERNAME + 1];
+};
+
+struct usbdevfs_streams {
+	unsigned int num_streams; /* Not used by USBDEVFS_FREE_STREAMS */
+	unsigned int num_eps;
+	unsigned char eps[];
+};
+
+/*
+ * USB_SPEED_* values returned by USBDEVFS_GET_SPEED are defined in
+ * linux/usb/ch9.h
+ */
+
+#define USBDEVFS_CONTROL           _IOWR('U', 0, struct usbdevfs_ctrltransfer)
+#define USBDEVFS_CONTROL32           _IOWR('U', 0, struct usbdevfs_ctrltransfer32)
+#define USBDEVFS_BULK              _IOWR('U', 2, struct usbdevfs_bulktransfer)
+#define USBDEVFS_BULK32              _IOWR('U', 2, struct usbdevfs_bulktransfer32)
+#define USBDEVFS_RESETEP           _IOR('U', 3, unsigned int)
+#define USBDEVFS_SETINTERFACE      _IOR('U', 4, struct usbdevfs_setinterface)
+#define USBDEVFS_SETCONFIGURATION  _IOR('U', 5, unsigned int)
+#define USBDEVFS_GETDRIVER         _IOW('U', 8, struct usbdevfs_getdriver)
+#define USBDEVFS_SUBMITURB         _IOR('U', 10, struct usbdevfs_urb)
+#define USBDEVFS_SUBMITURB32       _IOR('U', 10, struct usbdevfs_urb32)
+#define USBDEVFS_DISCARDURB        _IO('U', 11)
+#define USBDEVFS_REAPURB           _IOW('U', 12, void *)
+#define USBDEVFS_REAPURB32         _IOW('U', 12, __u32)
+#define USBDEVFS_REAPURBNDELAY     _IOW('U', 13, void *)
+#define USBDEVFS_REAPURBNDELAY32   _IOW('U', 13, __u32)
+#define USBDEVFS_DISCSIGNAL        _IOR('U', 14, struct usbdevfs_disconnectsignal)
+#define USBDEVFS_DISCSIGNAL32      _IOR('U', 14, struct usbdevfs_disconnectsignal32)
+#define USBDEVFS_CLAIMINTERFACE    _IOR('U', 15, unsigned int)
+#define USBDEVFS_RELEASEINTERFACE  _IOR('U', 16, unsigned int)
+#define USBDEVFS_CONNECTINFO       _IOW('U', 17, struct usbdevfs_connectinfo)
+#define USBDEVFS_IOCTL             _IOWR('U', 18, struct usbdevfs_ioctl)
+#define USBDEVFS_IOCTL32           _IOWR('U', 18, struct usbdevfs_ioctl32)
+#define USBDEVFS_HUB_PORTINFO      _IOR('U', 19, struct usbdevfs_hub_portinfo)
+#define USBDEVFS_RESET             _IO('U', 20)
+#define USBDEVFS_CLEAR_HALT        _IOR('U', 21, unsigned int)
+#define USBDEVFS_DISCONNECT        _IO('U', 22)
+#define USBDEVFS_CONNECT           _IO('U', 23)
+#define USBDEVFS_CLAIM_PORT        _IOR('U', 24, unsigned int)
+#define USBDEVFS_RELEASE_PORT      _IOR('U', 25, unsigned int)
+#define USBDEVFS_GET_CAPABILITIES  _IOR('U', 26, __u32)
+#define USBDEVFS_DISCONNECT_CLAIM  _IOR('U', 27, struct usbdevfs_disconnect_claim)
+#define USBDEVFS_ALLOC_STREAMS     _IOR('U', 28, struct usbdevfs_streams)
+#define USBDEVFS_FREE_STREAMS      _IOR('U', 29, struct usbdevfs_streams)
+#define USBDEVFS_DROP_PRIVILEGES   _IOW('U', 30, __u32)
+#define USBDEVFS_GET_SPEED         _IO('U', 31)
+/*
+ * Returns struct usbdevfs_conninfo_ex; length is variable to allow
+ * extending size of the data returned.
+ */
+#define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
+#define USBDEVFS_FORBID_SUSPEND    _IO('U', 33)
+#define USBDEVFS_ALLOW_SUSPEND     _IO('U', 34)
+#define USBDEVFS_WAIT_FOR_RESUME   _IO('U', 35)
+
+#endif /* _UAPI_LINUX_USBDEVICE_FS_H */
diff --git a/tools/perf/trace/beauty/usbdevfs_ioctl.sh b/tools/perf/trace/beauty/usbdevfs_ioctl.sh
index b39cfb3720b8..12a30a9a8e0c 100755
--- a/tools/perf/trace/beauty/usbdevfs_ioctl.sh
+++ b/tools/perf/trace/beauty/usbdevfs_ioctl.sh
@@ -1,21 +1,21 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && beauty_uapi_linux_dir=$1 || beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 
 # also as:
 # #define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
 
 printf "static const char *usbdevfs_ioctl_cmds[] = {\n"
 regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)(\(\w+\))?[[:space:]]+_IO[CWR]{0,2}\([[:space:]]*(_IOC_\w+,[[:space:]]*)?'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
-grep -E "$regex" ${header_dir}/usbdevice_fs.h | grep -E -v 'USBDEVFS_\w+32[[:space:]]' | \
+grep -E "$regex" ${beauty_uapi_linux_dir}/usbdevice_fs.h | grep -E -v 'USBDEVFS_\w+32[[:space:]]' | \
 	sed -r "s/$regex/\4 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n\n"
 printf "#if 0\n"
 printf "static const char *usbdevfs_ioctl_32_cmds[] = {\n"
 regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
-grep -E $regex ${header_dir}/usbdevice_fs.h | grep -E 'USBDEVFS_\w+32[[:space:]]' | \
+grep -E $regex ${beauty_uapi_linux_dir}/usbdevice_fs.h | grep -E 'USBDEVFS_\w+32[[:space:]]' | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
-- 
cgit 


From eb01fe7abbe2d0b38824d2a93fdb4cc3eaf2ccc1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Mar 2024 17:07:33 -0300
Subject: perf beauty: Move prctl.h files (uapi/linux and x86's) copy out of
 the directory used to build perf

It is used only to generate string tables, not to build perf, so move it
to the tools/perf/trace/beauty/{include,arch}/ hierarchies, that is used
just for scraping.

This is a something that should've have happened, as happened with the
linux/socket.h scrapper, do it now as Ian suggested while doing an
audit/refactor session in the headers used by perf.

No other tools/ living code uses it, just <linux/usbdevice_fs.h> coming
from either 'make install_headers' or from the system /usr/include/
directory.

Suggested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20240315204835.748716-3-acme@kernel.org
Link: https://lore.kernel.org/lkml/CAP-5=fWZVrpRufO4w-S4EcSi9STXcTAN2ERLwTSN7yrSSA-otQ@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/prctl.h            |  43 ---
 tools/include/uapi/linux/prctl.h                   | 309 ---------------------
 tools/perf/Makefile.perf                           |  11 +-
 tools/perf/check-headers.sh                        |   4 +-
 .../trace/beauty/arch/x86/include/uapi/asm/prctl.h |  43 +++
 tools/perf/trace/beauty/include/uapi/linux/prctl.h | 309 +++++++++++++++++++++
 tools/perf/trace/beauty/prctl_option.sh            |   6 +-
 tools/perf/trace/beauty/x86_arch_prctl.sh          |   4 +-
 8 files changed, 364 insertions(+), 365 deletions(-)
 delete mode 100644 tools/arch/x86/include/uapi/asm/prctl.h
 delete mode 100644 tools/include/uapi/linux/prctl.h
 create mode 100644 tools/perf/trace/beauty/arch/x86/include/uapi/asm/prctl.h
 create mode 100644 tools/perf/trace/beauty/include/uapi/linux/prctl.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h
deleted file mode 100644
index 384e2cc6ac19..000000000000
--- a/tools/arch/x86/include/uapi/asm/prctl.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_X86_PRCTL_H
-#define _ASM_X86_PRCTL_H
-
-#define ARCH_SET_GS			0x1001
-#define ARCH_SET_FS			0x1002
-#define ARCH_GET_FS			0x1003
-#define ARCH_GET_GS			0x1004
-
-#define ARCH_GET_CPUID			0x1011
-#define ARCH_SET_CPUID			0x1012
-
-#define ARCH_GET_XCOMP_SUPP		0x1021
-#define ARCH_GET_XCOMP_PERM		0x1022
-#define ARCH_REQ_XCOMP_PERM		0x1023
-#define ARCH_GET_XCOMP_GUEST_PERM	0x1024
-#define ARCH_REQ_XCOMP_GUEST_PERM	0x1025
-
-#define ARCH_XCOMP_TILECFG		17
-#define ARCH_XCOMP_TILEDATA		18
-
-#define ARCH_MAP_VDSO_X32		0x2001
-#define ARCH_MAP_VDSO_32		0x2002
-#define ARCH_MAP_VDSO_64		0x2003
-
-/* Don't use 0x3001-0x3004 because of old glibcs */
-
-#define ARCH_GET_UNTAG_MASK		0x4001
-#define ARCH_ENABLE_TAGGED_ADDR		0x4002
-#define ARCH_GET_MAX_TAG_BITS		0x4003
-#define ARCH_FORCE_TAGGED_SVA		0x4004
-
-#define ARCH_SHSTK_ENABLE		0x5001
-#define ARCH_SHSTK_DISABLE		0x5002
-#define ARCH_SHSTK_LOCK			0x5003
-#define ARCH_SHSTK_UNLOCK		0x5004
-#define ARCH_SHSTK_STATUS		0x5005
-
-/* ARCH_SHSTK_ features bits */
-#define ARCH_SHSTK_SHSTK		(1ULL <<  0)
-#define ARCH_SHSTK_WRSS			(1ULL <<  1)
-
-#endif /* _ASM_X86_PRCTL_H */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
deleted file mode 100644
index 370ed14b1ae0..000000000000
--- a/tools/include/uapi/linux/prctl.h
+++ /dev/null
@@ -1,309 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _LINUX_PRCTL_H
-#define _LINUX_PRCTL_H
-
-#include <linux/types.h>
-
-/* Values to pass as first argument to prctl() */
-
-#define PR_SET_PDEATHSIG  1  /* Second arg is a signal */
-#define PR_GET_PDEATHSIG  2  /* Second arg is a ptr to return the signal */
-
-/* Get/set current->mm->dumpable */
-#define PR_GET_DUMPABLE   3
-#define PR_SET_DUMPABLE   4
-
-/* Get/set unaligned access control bits (if meaningful) */
-#define PR_GET_UNALIGN	  5
-#define PR_SET_UNALIGN	  6
-# define PR_UNALIGN_NOPRINT	1	/* silently fix up unaligned user accesses */
-# define PR_UNALIGN_SIGBUS	2	/* generate SIGBUS on unaligned user access */
-
-/* Get/set whether or not to drop capabilities on setuid() away from
- * uid 0 (as per security/commoncap.c) */
-#define PR_GET_KEEPCAPS   7
-#define PR_SET_KEEPCAPS   8
-
-/* Get/set floating-point emulation control bits (if meaningful) */
-#define PR_GET_FPEMU  9
-#define PR_SET_FPEMU 10
-# define PR_FPEMU_NOPRINT	1	/* silently emulate fp operations accesses */
-# define PR_FPEMU_SIGFPE	2	/* don't emulate fp operations, send SIGFPE instead */
-
-/* Get/set floating-point exception mode (if meaningful) */
-#define PR_GET_FPEXC	11
-#define PR_SET_FPEXC	12
-# define PR_FP_EXC_SW_ENABLE	0x80	/* Use FPEXC for FP exception enables */
-# define PR_FP_EXC_DIV		0x010000	/* floating point divide by zero */
-# define PR_FP_EXC_OVF		0x020000	/* floating point overflow */
-# define PR_FP_EXC_UND		0x040000	/* floating point underflow */
-# define PR_FP_EXC_RES		0x080000	/* floating point inexact result */
-# define PR_FP_EXC_INV		0x100000	/* floating point invalid operation */
-# define PR_FP_EXC_DISABLED	0	/* FP exceptions disabled */
-# define PR_FP_EXC_NONRECOV	1	/* async non-recoverable exc. mode */
-# define PR_FP_EXC_ASYNC	2	/* async recoverable exception mode */
-# define PR_FP_EXC_PRECISE	3	/* precise exception mode */
-
-/* Get/set whether we use statistical process timing or accurate timestamp
- * based process timing */
-#define PR_GET_TIMING   13
-#define PR_SET_TIMING   14
-# define PR_TIMING_STATISTICAL  0       /* Normal, traditional,
-                                                   statistical process timing */
-# define PR_TIMING_TIMESTAMP    1       /* Accurate timestamp based
-                                                   process timing */
-
-#define PR_SET_NAME    15		/* Set process name */
-#define PR_GET_NAME    16		/* Get process name */
-
-/* Get/set process endian */
-#define PR_GET_ENDIAN	19
-#define PR_SET_ENDIAN	20
-# define PR_ENDIAN_BIG		0
-# define PR_ENDIAN_LITTLE	1	/* True little endian mode */
-# define PR_ENDIAN_PPC_LITTLE	2	/* "PowerPC" pseudo little endian */
-
-/* Get/set process seccomp mode */
-#define PR_GET_SECCOMP	21
-#define PR_SET_SECCOMP	22
-
-/* Get/set the capability bounding set (as per security/commoncap.c) */
-#define PR_CAPBSET_READ 23
-#define PR_CAPBSET_DROP 24
-
-/* Get/set the process' ability to use the timestamp counter instruction */
-#define PR_GET_TSC 25
-#define PR_SET_TSC 26
-# define PR_TSC_ENABLE		1	/* allow the use of the timestamp counter */
-# define PR_TSC_SIGSEGV		2	/* throw a SIGSEGV instead of reading the TSC */
-
-/* Get/set securebits (as per security/commoncap.c) */
-#define PR_GET_SECUREBITS 27
-#define PR_SET_SECUREBITS 28
-
-/*
- * Get/set the timerslack as used by poll/select/nanosleep
- * A value of 0 means "use default"
- */
-#define PR_SET_TIMERSLACK 29
-#define PR_GET_TIMERSLACK 30
-
-#define PR_TASK_PERF_EVENTS_DISABLE		31
-#define PR_TASK_PERF_EVENTS_ENABLE		32
-
-/*
- * Set early/late kill mode for hwpoison memory corruption.
- * This influences when the process gets killed on a memory corruption.
- */
-#define PR_MCE_KILL	33
-# define PR_MCE_KILL_CLEAR   0
-# define PR_MCE_KILL_SET     1
-
-# define PR_MCE_KILL_LATE    0
-# define PR_MCE_KILL_EARLY   1
-# define PR_MCE_KILL_DEFAULT 2
-
-#define PR_MCE_KILL_GET 34
-
-/*
- * Tune up process memory map specifics.
- */
-#define PR_SET_MM		35
-# define PR_SET_MM_START_CODE		1
-# define PR_SET_MM_END_CODE		2
-# define PR_SET_MM_START_DATA		3
-# define PR_SET_MM_END_DATA		4
-# define PR_SET_MM_START_STACK		5
-# define PR_SET_MM_START_BRK		6
-# define PR_SET_MM_BRK			7
-# define PR_SET_MM_ARG_START		8
-# define PR_SET_MM_ARG_END		9
-# define PR_SET_MM_ENV_START		10
-# define PR_SET_MM_ENV_END		11
-# define PR_SET_MM_AUXV			12
-# define PR_SET_MM_EXE_FILE		13
-# define PR_SET_MM_MAP			14
-# define PR_SET_MM_MAP_SIZE		15
-
-/*
- * This structure provides new memory descriptor
- * map which mostly modifies /proc/pid/stat[m]
- * output for a task. This mostly done in a
- * sake of checkpoint/restore functionality.
- */
-struct prctl_mm_map {
-	__u64	start_code;		/* code section bounds */
-	__u64	end_code;
-	__u64	start_data;		/* data section bounds */
-	__u64	end_data;
-	__u64	start_brk;		/* heap for brk() syscall */
-	__u64	brk;
-	__u64	start_stack;		/* stack starts at */
-	__u64	arg_start;		/* command line arguments bounds */
-	__u64	arg_end;
-	__u64	env_start;		/* environment variables bounds */
-	__u64	env_end;
-	__u64	*auxv;			/* auxiliary vector */
-	__u32	auxv_size;		/* vector size */
-	__u32	exe_fd;			/* /proc/$pid/exe link file */
-};
-
-/*
- * Set specific pid that is allowed to ptrace the current task.
- * A value of 0 mean "no process".
- */
-#define PR_SET_PTRACER 0x59616d61
-# define PR_SET_PTRACER_ANY ((unsigned long)-1)
-
-#define PR_SET_CHILD_SUBREAPER	36
-#define PR_GET_CHILD_SUBREAPER	37
-
-/*
- * If no_new_privs is set, then operations that grant new privileges (i.e.
- * execve) will either fail or not grant them.  This affects suid/sgid,
- * file capabilities, and LSMs.
- *
- * Operations that merely manipulate or drop existing privileges (setresuid,
- * capset, etc.) will still work.  Drop those privileges if you want them gone.
- *
- * Changing LSM security domain is considered a new privilege.  So, for example,
- * asking selinux for a specific new context (e.g. with runcon) will result
- * in execve returning -EPERM.
- *
- * See Documentation/userspace-api/no_new_privs.rst for more details.
- */
-#define PR_SET_NO_NEW_PRIVS	38
-#define PR_GET_NO_NEW_PRIVS	39
-
-#define PR_GET_TID_ADDRESS	40
-
-#define PR_SET_THP_DISABLE	41
-#define PR_GET_THP_DISABLE	42
-
-/*
- * No longer implemented, but left here to ensure the numbers stay reserved:
- */
-#define PR_MPX_ENABLE_MANAGEMENT  43
-#define PR_MPX_DISABLE_MANAGEMENT 44
-
-#define PR_SET_FP_MODE		45
-#define PR_GET_FP_MODE		46
-# define PR_FP_MODE_FR		(1 << 0)	/* 64b FP registers */
-# define PR_FP_MODE_FRE		(1 << 1)	/* 32b compatibility */
-
-/* Control the ambient capability set */
-#define PR_CAP_AMBIENT			47
-# define PR_CAP_AMBIENT_IS_SET		1
-# define PR_CAP_AMBIENT_RAISE		2
-# define PR_CAP_AMBIENT_LOWER		3
-# define PR_CAP_AMBIENT_CLEAR_ALL	4
-
-/* arm64 Scalable Vector Extension controls */
-/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
-#define PR_SVE_SET_VL			50	/* set task vector length */
-# define PR_SVE_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
-#define PR_SVE_GET_VL			51	/* get task vector length */
-/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
-# define PR_SVE_VL_LEN_MASK		0xffff
-# define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
-
-/* Per task speculation control */
-#define PR_GET_SPECULATION_CTRL		52
-#define PR_SET_SPECULATION_CTRL		53
-/* Speculation control variants */
-# define PR_SPEC_STORE_BYPASS		0
-# define PR_SPEC_INDIRECT_BRANCH	1
-# define PR_SPEC_L1D_FLUSH		2
-/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
-# define PR_SPEC_NOT_AFFECTED		0
-# define PR_SPEC_PRCTL			(1UL << 0)
-# define PR_SPEC_ENABLE			(1UL << 1)
-# define PR_SPEC_DISABLE		(1UL << 2)
-# define PR_SPEC_FORCE_DISABLE		(1UL << 3)
-# define PR_SPEC_DISABLE_NOEXEC		(1UL << 4)
-
-/* Reset arm64 pointer authentication keys */
-#define PR_PAC_RESET_KEYS		54
-# define PR_PAC_APIAKEY			(1UL << 0)
-# define PR_PAC_APIBKEY			(1UL << 1)
-# define PR_PAC_APDAKEY			(1UL << 2)
-# define PR_PAC_APDBKEY			(1UL << 3)
-# define PR_PAC_APGAKEY			(1UL << 4)
-
-/* Tagged user address controls for arm64 */
-#define PR_SET_TAGGED_ADDR_CTRL		55
-#define PR_GET_TAGGED_ADDR_CTRL		56
-# define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
-/* MTE tag check fault modes */
-# define PR_MTE_TCF_NONE		0UL
-# define PR_MTE_TCF_SYNC		(1UL << 1)
-# define PR_MTE_TCF_ASYNC		(1UL << 2)
-# define PR_MTE_TCF_MASK		(PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC)
-/* MTE tag inclusion mask */
-# define PR_MTE_TAG_SHIFT		3
-# define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
-/* Unused; kept only for source compatibility */
-# define PR_MTE_TCF_SHIFT		1
-
-/* Control reclaim behavior when allocating memory */
-#define PR_SET_IO_FLUSHER		57
-#define PR_GET_IO_FLUSHER		58
-
-/* Dispatch syscalls to a userspace handler */
-#define PR_SET_SYSCALL_USER_DISPATCH	59
-# define PR_SYS_DISPATCH_OFF		0
-# define PR_SYS_DISPATCH_ON		1
-/* The control values for the user space selector when dispatch is enabled */
-# define SYSCALL_DISPATCH_FILTER_ALLOW	0
-# define SYSCALL_DISPATCH_FILTER_BLOCK	1
-
-/* Set/get enabled arm64 pointer authentication keys */
-#define PR_PAC_SET_ENABLED_KEYS		60
-#define PR_PAC_GET_ENABLED_KEYS		61
-
-/* Request the scheduler to share a core */
-#define PR_SCHED_CORE			62
-# define PR_SCHED_CORE_GET		0
-# define PR_SCHED_CORE_CREATE		1 /* create unique core_sched cookie */
-# define PR_SCHED_CORE_SHARE_TO		2 /* push core_sched cookie to pid */
-# define PR_SCHED_CORE_SHARE_FROM	3 /* pull core_sched cookie to pid */
-# define PR_SCHED_CORE_MAX		4
-# define PR_SCHED_CORE_SCOPE_THREAD		0
-# define PR_SCHED_CORE_SCOPE_THREAD_GROUP	1
-# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP	2
-
-/* arm64 Scalable Matrix Extension controls */
-/* Flag values must be in sync with SVE versions */
-#define PR_SME_SET_VL			63	/* set task vector length */
-# define PR_SME_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
-#define PR_SME_GET_VL			64	/* get task vector length */
-/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */
-# define PR_SME_VL_LEN_MASK		0xffff
-# define PR_SME_VL_INHERIT		(1 << 17) /* inherit across exec */
-
-/* Memory deny write / execute */
-#define PR_SET_MDWE			65
-# define PR_MDWE_REFUSE_EXEC_GAIN	(1UL << 0)
-# define PR_MDWE_NO_INHERIT		(1UL << 1)
-
-#define PR_GET_MDWE			66
-
-#define PR_SET_VMA		0x53564d41
-# define PR_SET_VMA_ANON_NAME		0
-
-#define PR_GET_AUXV			0x41555856
-
-#define PR_SET_MEMORY_MERGE		67
-#define PR_GET_MEMORY_MERGE		68
-
-#define PR_RISCV_V_SET_CONTROL		69
-#define PR_RISCV_V_GET_CONTROL		70
-# define PR_RISCV_V_VSTATE_CTRL_DEFAULT		0
-# define PR_RISCV_V_VSTATE_CTRL_OFF		1
-# define PR_RISCV_V_VSTATE_CTRL_ON		2
-# define PR_RISCV_V_VSTATE_CTRL_INHERIT		(1 << 4)
-# define PR_RISCV_V_VSTATE_CTRL_CUR_MASK	0x3
-# define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK	0xc
-# define PR_RISCV_V_VSTATE_CTRL_MASK		0x1f
-
-#endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index c75342b21089..b36c0c68c346 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -475,11 +475,11 @@ beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/
 beauty_uapi_linux_dir := $(srctree)/tools/perf/trace/beauty/include/uapi/linux/
 beauty_uapi_sound_dir := $(srctree)/tools/perf/trace/beauty/include/uapi/sound/
 beauty_arch_asm_dir := $(srctree)/tools/perf/trace/beauty/arch/x86/include/asm/
+beauty_x86_arch_asm_uapi_dir := $(srctree)/tools/perf/trace/beauty/arch/x86/include/uapi/asm/
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
 arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
-x86_arch_asm_uapi_dir := $(srctree)/tools/arch/x86/include/uapi/asm/
 x86_arch_asm_dir := $(srctree)/tools/arch/x86/include/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
@@ -617,11 +617,10 @@ $(mmap_prot_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-
 	$(Q)$(SHELL) '$(mmap_prot_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
 
 prctl_option_array := $(beauty_outdir)/prctl_option_array.c
-prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
 prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
 
-$(prctl_option_array): $(prctl_hdr_dir)/prctl.h $(prctl_option_tbl)
-	$(Q)$(SHELL) '$(prctl_option_tbl)' $(prctl_hdr_dir) > $@
+$(prctl_option_array): $(beauty_uapi_linux_dir)/prctl.h $(prctl_option_tbl)
+	$(Q)$(SHELL) '$(prctl_option_tbl)' $(beauty_uapi_linux_dir) > $@
 
 usbdevfs_ioctl_array := $(beauty_ioctl_outdir)/usbdevfs_ioctl_array.c
 usbdevfs_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/usbdevfs_ioctl.sh
@@ -632,8 +631,8 @@ $(usbdevfs_ioctl_array): $(beauty_uapi_linux_dir)/usbdevice_fs.h $(usbdevfs_ioct
 x86_arch_prctl_code_array := $(beauty_outdir)/x86_arch_prctl_code_array.c
 x86_arch_prctl_code_tbl := $(srctree)/tools/perf/trace/beauty/x86_arch_prctl.sh
 
-$(x86_arch_prctl_code_array): $(x86_arch_asm_uapi_dir)/prctl.h $(x86_arch_prctl_code_tbl)
-	$(Q)$(SHELL) '$(x86_arch_prctl_code_tbl)' $(x86_arch_asm_uapi_dir) > $@
+$(x86_arch_prctl_code_array): $(beauty_x86_arch_asm_uapi_dir)/prctl.h $(x86_arch_prctl_code_tbl)
+	$(Q)$(SHELL) '$(x86_arch_prctl_code_tbl)' $(beauty_x86_arch_asm_uapi_dir) > $@
 
 x86_arch_irq_vectors_array := $(beauty_outdir)/x86_arch_irq_vectors_array.c
 x86_arch_irq_vectors_tbl := $(srctree)/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index b35eba5e99c8..03d00110a48f 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -17,7 +17,6 @@ FILES=(
   "include/uapi/linux/in.h"
   "include/uapi/linux/openat2.h"
   "include/uapi/linux/perf_event.h"
-  "include/uapi/linux/prctl.h"
   "include/uapi/linux/sched.h"
   "include/uapi/linux/seccomp.h"
   "include/uapi/linux/stat.h"
@@ -35,7 +34,6 @@ FILES=(
   "arch/x86/include/asm/inat_types.h"
   "arch/x86/include/asm/emulate_prefix.h"
   "arch/x86/include/asm/msr-index.h"
-  "arch/x86/include/uapi/asm/prctl.h"
   "arch/x86/lib/x86-opcode-map.txt"
   "arch/x86/tools/gen-insn-attr-x86.awk"
   "arch/arm/include/uapi/asm/perf_regs.h"
@@ -93,9 +91,11 @@ SYNC_CHECK_FILES=(
 declare -a BEAUTY_FILES
 BEAUTY_FILES=(
   "arch/x86/include/asm/irq_vectors.h"
+  "arch/x86/include/uapi/asm/prctl.h"
   "include/linux/socket.h"
   "include/uapi/linux/fs.h"
   "include/uapi/linux/mount.h"
+  "include/uapi/linux/prctl.h"
   "include/uapi/linux/usbdevice_fs.h"
   "include/uapi/sound/asound.h"
 )
diff --git a/tools/perf/trace/beauty/arch/x86/include/uapi/asm/prctl.h b/tools/perf/trace/beauty/arch/x86/include/uapi/asm/prctl.h
new file mode 100644
index 000000000000..384e2cc6ac19
--- /dev/null
+++ b/tools/perf/trace/beauty/arch/x86/include/uapi/asm/prctl.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_X86_PRCTL_H
+#define _ASM_X86_PRCTL_H
+
+#define ARCH_SET_GS			0x1001
+#define ARCH_SET_FS			0x1002
+#define ARCH_GET_FS			0x1003
+#define ARCH_GET_GS			0x1004
+
+#define ARCH_GET_CPUID			0x1011
+#define ARCH_SET_CPUID			0x1012
+
+#define ARCH_GET_XCOMP_SUPP		0x1021
+#define ARCH_GET_XCOMP_PERM		0x1022
+#define ARCH_REQ_XCOMP_PERM		0x1023
+#define ARCH_GET_XCOMP_GUEST_PERM	0x1024
+#define ARCH_REQ_XCOMP_GUEST_PERM	0x1025
+
+#define ARCH_XCOMP_TILECFG		17
+#define ARCH_XCOMP_TILEDATA		18
+
+#define ARCH_MAP_VDSO_X32		0x2001
+#define ARCH_MAP_VDSO_32		0x2002
+#define ARCH_MAP_VDSO_64		0x2003
+
+/* Don't use 0x3001-0x3004 because of old glibcs */
+
+#define ARCH_GET_UNTAG_MASK		0x4001
+#define ARCH_ENABLE_TAGGED_ADDR		0x4002
+#define ARCH_GET_MAX_TAG_BITS		0x4003
+#define ARCH_FORCE_TAGGED_SVA		0x4004
+
+#define ARCH_SHSTK_ENABLE		0x5001
+#define ARCH_SHSTK_DISABLE		0x5002
+#define ARCH_SHSTK_LOCK			0x5003
+#define ARCH_SHSTK_UNLOCK		0x5004
+#define ARCH_SHSTK_STATUS		0x5005
+
+/* ARCH_SHSTK_ features bits */
+#define ARCH_SHSTK_SHSTK		(1ULL <<  0)
+#define ARCH_SHSTK_WRSS			(1ULL <<  1)
+
+#endif /* _ASM_X86_PRCTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
new file mode 100644
index 000000000000..370ed14b1ae0
--- /dev/null
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -0,0 +1,309 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_PRCTL_H
+#define _LINUX_PRCTL_H
+
+#include <linux/types.h>
+
+/* Values to pass as first argument to prctl() */
+
+#define PR_SET_PDEATHSIG  1  /* Second arg is a signal */
+#define PR_GET_PDEATHSIG  2  /* Second arg is a ptr to return the signal */
+
+/* Get/set current->mm->dumpable */
+#define PR_GET_DUMPABLE   3
+#define PR_SET_DUMPABLE   4
+
+/* Get/set unaligned access control bits (if meaningful) */
+#define PR_GET_UNALIGN	  5
+#define PR_SET_UNALIGN	  6
+# define PR_UNALIGN_NOPRINT	1	/* silently fix up unaligned user accesses */
+# define PR_UNALIGN_SIGBUS	2	/* generate SIGBUS on unaligned user access */
+
+/* Get/set whether or not to drop capabilities on setuid() away from
+ * uid 0 (as per security/commoncap.c) */
+#define PR_GET_KEEPCAPS   7
+#define PR_SET_KEEPCAPS   8
+
+/* Get/set floating-point emulation control bits (if meaningful) */
+#define PR_GET_FPEMU  9
+#define PR_SET_FPEMU 10
+# define PR_FPEMU_NOPRINT	1	/* silently emulate fp operations accesses */
+# define PR_FPEMU_SIGFPE	2	/* don't emulate fp operations, send SIGFPE instead */
+
+/* Get/set floating-point exception mode (if meaningful) */
+#define PR_GET_FPEXC	11
+#define PR_SET_FPEXC	12
+# define PR_FP_EXC_SW_ENABLE	0x80	/* Use FPEXC for FP exception enables */
+# define PR_FP_EXC_DIV		0x010000	/* floating point divide by zero */
+# define PR_FP_EXC_OVF		0x020000	/* floating point overflow */
+# define PR_FP_EXC_UND		0x040000	/* floating point underflow */
+# define PR_FP_EXC_RES		0x080000	/* floating point inexact result */
+# define PR_FP_EXC_INV		0x100000	/* floating point invalid operation */
+# define PR_FP_EXC_DISABLED	0	/* FP exceptions disabled */
+# define PR_FP_EXC_NONRECOV	1	/* async non-recoverable exc. mode */
+# define PR_FP_EXC_ASYNC	2	/* async recoverable exception mode */
+# define PR_FP_EXC_PRECISE	3	/* precise exception mode */
+
+/* Get/set whether we use statistical process timing or accurate timestamp
+ * based process timing */
+#define PR_GET_TIMING   13
+#define PR_SET_TIMING   14
+# define PR_TIMING_STATISTICAL  0       /* Normal, traditional,
+                                                   statistical process timing */
+# define PR_TIMING_TIMESTAMP    1       /* Accurate timestamp based
+                                                   process timing */
+
+#define PR_SET_NAME    15		/* Set process name */
+#define PR_GET_NAME    16		/* Get process name */
+
+/* Get/set process endian */
+#define PR_GET_ENDIAN	19
+#define PR_SET_ENDIAN	20
+# define PR_ENDIAN_BIG		0
+# define PR_ENDIAN_LITTLE	1	/* True little endian mode */
+# define PR_ENDIAN_PPC_LITTLE	2	/* "PowerPC" pseudo little endian */
+
+/* Get/set process seccomp mode */
+#define PR_GET_SECCOMP	21
+#define PR_SET_SECCOMP	22
+
+/* Get/set the capability bounding set (as per security/commoncap.c) */
+#define PR_CAPBSET_READ 23
+#define PR_CAPBSET_DROP 24
+
+/* Get/set the process' ability to use the timestamp counter instruction */
+#define PR_GET_TSC 25
+#define PR_SET_TSC 26
+# define PR_TSC_ENABLE		1	/* allow the use of the timestamp counter */
+# define PR_TSC_SIGSEGV		2	/* throw a SIGSEGV instead of reading the TSC */
+
+/* Get/set securebits (as per security/commoncap.c) */
+#define PR_GET_SECUREBITS 27
+#define PR_SET_SECUREBITS 28
+
+/*
+ * Get/set the timerslack as used by poll/select/nanosleep
+ * A value of 0 means "use default"
+ */
+#define PR_SET_TIMERSLACK 29
+#define PR_GET_TIMERSLACK 30
+
+#define PR_TASK_PERF_EVENTS_DISABLE		31
+#define PR_TASK_PERF_EVENTS_ENABLE		32
+
+/*
+ * Set early/late kill mode for hwpoison memory corruption.
+ * This influences when the process gets killed on a memory corruption.
+ */
+#define PR_MCE_KILL	33
+# define PR_MCE_KILL_CLEAR   0
+# define PR_MCE_KILL_SET     1
+
+# define PR_MCE_KILL_LATE    0
+# define PR_MCE_KILL_EARLY   1
+# define PR_MCE_KILL_DEFAULT 2
+
+#define PR_MCE_KILL_GET 34
+
+/*
+ * Tune up process memory map specifics.
+ */
+#define PR_SET_MM		35
+# define PR_SET_MM_START_CODE		1
+# define PR_SET_MM_END_CODE		2
+# define PR_SET_MM_START_DATA		3
+# define PR_SET_MM_END_DATA		4
+# define PR_SET_MM_START_STACK		5
+# define PR_SET_MM_START_BRK		6
+# define PR_SET_MM_BRK			7
+# define PR_SET_MM_ARG_START		8
+# define PR_SET_MM_ARG_END		9
+# define PR_SET_MM_ENV_START		10
+# define PR_SET_MM_ENV_END		11
+# define PR_SET_MM_AUXV			12
+# define PR_SET_MM_EXE_FILE		13
+# define PR_SET_MM_MAP			14
+# define PR_SET_MM_MAP_SIZE		15
+
+/*
+ * This structure provides new memory descriptor
+ * map which mostly modifies /proc/pid/stat[m]
+ * output for a task. This mostly done in a
+ * sake of checkpoint/restore functionality.
+ */
+struct prctl_mm_map {
+	__u64	start_code;		/* code section bounds */
+	__u64	end_code;
+	__u64	start_data;		/* data section bounds */
+	__u64	end_data;
+	__u64	start_brk;		/* heap for brk() syscall */
+	__u64	brk;
+	__u64	start_stack;		/* stack starts at */
+	__u64	arg_start;		/* command line arguments bounds */
+	__u64	arg_end;
+	__u64	env_start;		/* environment variables bounds */
+	__u64	env_end;
+	__u64	*auxv;			/* auxiliary vector */
+	__u32	auxv_size;		/* vector size */
+	__u32	exe_fd;			/* /proc/$pid/exe link file */
+};
+
+/*
+ * Set specific pid that is allowed to ptrace the current task.
+ * A value of 0 mean "no process".
+ */
+#define PR_SET_PTRACER 0x59616d61
+# define PR_SET_PTRACER_ANY ((unsigned long)-1)
+
+#define PR_SET_CHILD_SUBREAPER	36
+#define PR_GET_CHILD_SUBREAPER	37
+
+/*
+ * If no_new_privs is set, then operations that grant new privileges (i.e.
+ * execve) will either fail or not grant them.  This affects suid/sgid,
+ * file capabilities, and LSMs.
+ *
+ * Operations that merely manipulate or drop existing privileges (setresuid,
+ * capset, etc.) will still work.  Drop those privileges if you want them gone.
+ *
+ * Changing LSM security domain is considered a new privilege.  So, for example,
+ * asking selinux for a specific new context (e.g. with runcon) will result
+ * in execve returning -EPERM.
+ *
+ * See Documentation/userspace-api/no_new_privs.rst for more details.
+ */
+#define PR_SET_NO_NEW_PRIVS	38
+#define PR_GET_NO_NEW_PRIVS	39
+
+#define PR_GET_TID_ADDRESS	40
+
+#define PR_SET_THP_DISABLE	41
+#define PR_GET_THP_DISABLE	42
+
+/*
+ * No longer implemented, but left here to ensure the numbers stay reserved:
+ */
+#define PR_MPX_ENABLE_MANAGEMENT  43
+#define PR_MPX_DISABLE_MANAGEMENT 44
+
+#define PR_SET_FP_MODE		45
+#define PR_GET_FP_MODE		46
+# define PR_FP_MODE_FR		(1 << 0)	/* 64b FP registers */
+# define PR_FP_MODE_FRE		(1 << 1)	/* 32b compatibility */
+
+/* Control the ambient capability set */
+#define PR_CAP_AMBIENT			47
+# define PR_CAP_AMBIENT_IS_SET		1
+# define PR_CAP_AMBIENT_RAISE		2
+# define PR_CAP_AMBIENT_LOWER		3
+# define PR_CAP_AMBIENT_CLEAR_ALL	4
+
+/* arm64 Scalable Vector Extension controls */
+/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
+#define PR_SVE_SET_VL			50	/* set task vector length */
+# define PR_SVE_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SVE_GET_VL			51	/* get task vector length */
+/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
+# define PR_SVE_VL_LEN_MASK		0xffff
+# define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
+
+/* Per task speculation control */
+#define PR_GET_SPECULATION_CTRL		52
+#define PR_SET_SPECULATION_CTRL		53
+/* Speculation control variants */
+# define PR_SPEC_STORE_BYPASS		0
+# define PR_SPEC_INDIRECT_BRANCH	1
+# define PR_SPEC_L1D_FLUSH		2
+/* Return and control values for PR_SET/GET_SPECULATION_CTRL */
+# define PR_SPEC_NOT_AFFECTED		0
+# define PR_SPEC_PRCTL			(1UL << 0)
+# define PR_SPEC_ENABLE			(1UL << 1)
+# define PR_SPEC_DISABLE		(1UL << 2)
+# define PR_SPEC_FORCE_DISABLE		(1UL << 3)
+# define PR_SPEC_DISABLE_NOEXEC		(1UL << 4)
+
+/* Reset arm64 pointer authentication keys */
+#define PR_PAC_RESET_KEYS		54
+# define PR_PAC_APIAKEY			(1UL << 0)
+# define PR_PAC_APIBKEY			(1UL << 1)
+# define PR_PAC_APDAKEY			(1UL << 2)
+# define PR_PAC_APDBKEY			(1UL << 3)
+# define PR_PAC_APGAKEY			(1UL << 4)
+
+/* Tagged user address controls for arm64 */
+#define PR_SET_TAGGED_ADDR_CTRL		55
+#define PR_GET_TAGGED_ADDR_CTRL		56
+# define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
+/* MTE tag check fault modes */
+# define PR_MTE_TCF_NONE		0UL
+# define PR_MTE_TCF_SYNC		(1UL << 1)
+# define PR_MTE_TCF_ASYNC		(1UL << 2)
+# define PR_MTE_TCF_MASK		(PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC)
+/* MTE tag inclusion mask */
+# define PR_MTE_TAG_SHIFT		3
+# define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
+/* Unused; kept only for source compatibility */
+# define PR_MTE_TCF_SHIFT		1
+
+/* Control reclaim behavior when allocating memory */
+#define PR_SET_IO_FLUSHER		57
+#define PR_GET_IO_FLUSHER		58
+
+/* Dispatch syscalls to a userspace handler */
+#define PR_SET_SYSCALL_USER_DISPATCH	59
+# define PR_SYS_DISPATCH_OFF		0
+# define PR_SYS_DISPATCH_ON		1
+/* The control values for the user space selector when dispatch is enabled */
+# define SYSCALL_DISPATCH_FILTER_ALLOW	0
+# define SYSCALL_DISPATCH_FILTER_BLOCK	1
+
+/* Set/get enabled arm64 pointer authentication keys */
+#define PR_PAC_SET_ENABLED_KEYS		60
+#define PR_PAC_GET_ENABLED_KEYS		61
+
+/* Request the scheduler to share a core */
+#define PR_SCHED_CORE			62
+# define PR_SCHED_CORE_GET		0
+# define PR_SCHED_CORE_CREATE		1 /* create unique core_sched cookie */
+# define PR_SCHED_CORE_SHARE_TO		2 /* push core_sched cookie to pid */
+# define PR_SCHED_CORE_SHARE_FROM	3 /* pull core_sched cookie to pid */
+# define PR_SCHED_CORE_MAX		4
+# define PR_SCHED_CORE_SCOPE_THREAD		0
+# define PR_SCHED_CORE_SCOPE_THREAD_GROUP	1
+# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP	2
+
+/* arm64 Scalable Matrix Extension controls */
+/* Flag values must be in sync with SVE versions */
+#define PR_SME_SET_VL			63	/* set task vector length */
+# define PR_SME_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SME_GET_VL			64	/* get task vector length */
+/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */
+# define PR_SME_VL_LEN_MASK		0xffff
+# define PR_SME_VL_INHERIT		(1 << 17) /* inherit across exec */
+
+/* Memory deny write / execute */
+#define PR_SET_MDWE			65
+# define PR_MDWE_REFUSE_EXEC_GAIN	(1UL << 0)
+# define PR_MDWE_NO_INHERIT		(1UL << 1)
+
+#define PR_GET_MDWE			66
+
+#define PR_SET_VMA		0x53564d41
+# define PR_SET_VMA_ANON_NAME		0
+
+#define PR_GET_AUXV			0x41555856
+
+#define PR_SET_MEMORY_MERGE		67
+#define PR_GET_MEMORY_MERGE		68
+
+#define PR_RISCV_V_SET_CONTROL		69
+#define PR_RISCV_V_GET_CONTROL		70
+# define PR_RISCV_V_VSTATE_CTRL_DEFAULT		0
+# define PR_RISCV_V_VSTATE_CTRL_OFF		1
+# define PR_RISCV_V_VSTATE_CTRL_ON		2
+# define PR_RISCV_V_VSTATE_CTRL_INHERIT		(1 << 4)
+# define PR_RISCV_V_VSTATE_CTRL_CUR_MASK	0x3
+# define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK	0xc
+# define PR_RISCV_V_VSTATE_CTRL_MASK		0x1f
+
+#endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index 9455d9672f14..e049f5e9c011 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,18 +1,18 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && beauty_uapi_linux_dir=$1 || beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
 regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*/.*)?$'
-grep -E $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
+grep -E $regex ${beauty_uapi_linux_dir}/prctl.h | grep -v PR_SET_PTRACER | \
 	sed -E "s%$regex%\2 \1%g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *prctl_set_mm_options[] = {\n"
 regex='^#[[:space:]]+define[[:space:]]+PR_SET_MM_(\w+)[[:space:]]*([[:digit:]]+).*'
-grep -E $regex ${header_dir}/prctl.h | \
+grep -E $regex ${beauty_uapi_linux_dir}/prctl.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh
index b1596df251f0..b714ffa3cb7a 100755
--- a/tools/perf/trace/beauty/x86_arch_prctl.sh
+++ b/tools/perf/trace/beauty/x86_arch_prctl.sh
@@ -2,9 +2,9 @@
 # Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && x86_header_dir=$1 || x86_header_dir=tools/arch/x86/include/uapi/asm/
+[ $# -eq 1 ] && beauty_x86_arch_asm_uapi_dir=$1 || beauty_x86_arch_asm_uapi_dir=tools/perf/trace/beauty/arch/x86/include/uapi/asm/
 
-prctl_arch_header=${x86_header_dir}/prctl.h
+prctl_arch_header=${beauty_x86_arch_asm_uapi_dir}/prctl.h
 
 print_range () {
 	idx=$1
-- 
cgit 


From 8a1ad4413519b10fbe5e73300b198498a0b28806 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 15 Mar 2024 16:18:14 -0300
Subject: tools headers: Remove now unused copies of uapi/{fcntl,openat2}.h and
 asm/fcntl.h

These were used to build perf to provide defines not available in older
distros, but this was back in 2017, nowadays all the distros that are
supported and I have build containers for work using just the system
headers, so ditch them.

Some of these older distros may not have things that are used in 'perf
trace', but then they also don't have libtraceevent packages, so don't
build 'perf trace'.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20240315204835.748716-5-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/asm-generic/fcntl.h | 221 ---------------------------------
 tools/include/uapi/linux/fcntl.h       | 123 ------------------
 tools/include/uapi/linux/openat2.h     |  43 -------
 tools/perf/check-headers.sh            |   2 -
 4 files changed, 389 deletions(-)
 delete mode 100644 tools/include/uapi/asm-generic/fcntl.h
 delete mode 100644 tools/include/uapi/linux/fcntl.h
 delete mode 100644 tools/include/uapi/linux/openat2.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h
deleted file mode 100644
index 1c7a0f6632c0..000000000000
--- a/tools/include/uapi/asm-generic/fcntl.h
+++ /dev/null
@@ -1,221 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_GENERIC_FCNTL_H
-#define _ASM_GENERIC_FCNTL_H
-
-#include <linux/types.h>
-
-/*
- * FMODE_EXEC is 0x20
- * FMODE_NONOTIFY is 0x4000000
- * These cannot be used by userspace O_* until internal and external open
- * flags are split.
- * -Eric Paris
- */
-
-/*
- * When introducing new O_* bits, please check its uniqueness in fcntl_init().
- */
-
-#define O_ACCMODE	00000003
-#define O_RDONLY	00000000
-#define O_WRONLY	00000001
-#define O_RDWR		00000002
-#ifndef O_CREAT
-#define O_CREAT		00000100	/* not fcntl */
-#endif
-#ifndef O_EXCL
-#define O_EXCL		00000200	/* not fcntl */
-#endif
-#ifndef O_NOCTTY
-#define O_NOCTTY	00000400	/* not fcntl */
-#endif
-#ifndef O_TRUNC
-#define O_TRUNC		00001000	/* not fcntl */
-#endif
-#ifndef O_APPEND
-#define O_APPEND	00002000
-#endif
-#ifndef O_NONBLOCK
-#define O_NONBLOCK	00004000
-#endif
-#ifndef O_DSYNC
-#define O_DSYNC		00010000	/* used to be O_SYNC, see below */
-#endif
-#ifndef FASYNC
-#define FASYNC		00020000	/* fcntl, for BSD compatibility */
-#endif
-#ifndef O_DIRECT
-#define O_DIRECT	00040000	/* direct disk access hint */
-#endif
-#ifndef O_LARGEFILE
-#define O_LARGEFILE	00100000
-#endif
-#ifndef O_DIRECTORY
-#define O_DIRECTORY	00200000	/* must be a directory */
-#endif
-#ifndef O_NOFOLLOW
-#define O_NOFOLLOW	00400000	/* don't follow links */
-#endif
-#ifndef O_NOATIME
-#define O_NOATIME	01000000
-#endif
-#ifndef O_CLOEXEC
-#define O_CLOEXEC	02000000	/* set close_on_exec */
-#endif
-
-/*
- * Before Linux 2.6.33 only O_DSYNC semantics were implemented, but using
- * the O_SYNC flag.  We continue to use the existing numerical value
- * for O_DSYNC semantics now, but using the correct symbolic name for it.
- * This new value is used to request true Posix O_SYNC semantics.  It is
- * defined in this strange way to make sure applications compiled against
- * new headers get at least O_DSYNC semantics on older kernels.
- *
- * This has the nice side-effect that we can simply test for O_DSYNC
- * wherever we do not care if O_DSYNC or O_SYNC is used.
- *
- * Note: __O_SYNC must never be used directly.
- */
-#ifndef O_SYNC
-#define __O_SYNC	04000000
-#define O_SYNC		(__O_SYNC|O_DSYNC)
-#endif
-
-#ifndef O_PATH
-#define O_PATH		010000000
-#endif
-
-#ifndef __O_TMPFILE
-#define __O_TMPFILE	020000000
-#endif
-
-/* a horrid kludge trying to make sure that this will fail on old kernels */
-#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
-
-#ifndef O_NDELAY
-#define O_NDELAY	O_NONBLOCK
-#endif
-
-#define F_DUPFD		0	/* dup */
-#define F_GETFD		1	/* get close_on_exec */
-#define F_SETFD		2	/* set/clear close_on_exec */
-#define F_GETFL		3	/* get file->f_flags */
-#define F_SETFL		4	/* set file->f_flags */
-#ifndef F_GETLK
-#define F_GETLK		5
-#define F_SETLK		6
-#define F_SETLKW	7
-#endif
-#ifndef F_SETOWN
-#define F_SETOWN	8	/* for sockets. */
-#define F_GETOWN	9	/* for sockets. */
-#endif
-#ifndef F_SETSIG
-#define F_SETSIG	10	/* for sockets. */
-#define F_GETSIG	11	/* for sockets. */
-#endif
-
-#if __BITS_PER_LONG == 32 || defined(__KERNEL__)
-#ifndef F_GETLK64
-#define F_GETLK64	12	/*  using 'struct flock64' */
-#define F_SETLK64	13
-#define F_SETLKW64	14
-#endif
-#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */
-
-#ifndef F_SETOWN_EX
-#define F_SETOWN_EX	15
-#define F_GETOWN_EX	16
-#endif
-
-#ifndef F_GETOWNER_UIDS
-#define F_GETOWNER_UIDS	17
-#endif
-
-/*
- * Open File Description Locks
- *
- * Usually record locks held by a process are released on *any* close and are
- * not inherited across a fork().
- *
- * These cmd values will set locks that conflict with process-associated
- * record  locks, but are "owned" by the open file description, not the
- * process. This means that they are inherited across fork() like BSD (flock)
- * locks, and they are only released automatically when the last reference to
- * the open file against which they were acquired is put.
- */
-#define F_OFD_GETLK	36
-#define F_OFD_SETLK	37
-#define F_OFD_SETLKW	38
-
-#define F_OWNER_TID	0
-#define F_OWNER_PID	1
-#define F_OWNER_PGRP	2
-
-struct f_owner_ex {
-	int	type;
-	__kernel_pid_t	pid;
-};
-
-/* for F_[GET|SET]FL */
-#define FD_CLOEXEC	1	/* actually anything with low bit set goes */
-
-/* for posix fcntl() and lockf() */
-#ifndef F_RDLCK
-#define F_RDLCK		0
-#define F_WRLCK		1
-#define F_UNLCK		2
-#endif
-
-/* for old implementation of bsd flock () */
-#ifndef F_EXLCK
-#define F_EXLCK		4	/* or 3 */
-#define F_SHLCK		8	/* or 4 */
-#endif
-
-/* operations for bsd flock(), also used by the kernel implementation */
-#define LOCK_SH		1	/* shared lock */
-#define LOCK_EX		2	/* exclusive lock */
-#define LOCK_NB		4	/* or'd with one of the above to prevent
-				   blocking */
-#define LOCK_UN		8	/* remove lock */
-
-/*
- * LOCK_MAND support has been removed from the kernel. We leave the symbols
- * here to not break legacy builds, but these should not be used in new code.
- */
-#define LOCK_MAND	32	/* This is a mandatory flock ... */
-#define LOCK_READ	64	/* which allows concurrent read operations */
-#define LOCK_WRITE	128	/* which allows concurrent write operations */
-#define LOCK_RW		192	/* which allows concurrent read & write ops */
-
-#define F_LINUX_SPECIFIC_BASE	1024
-
-#ifndef HAVE_ARCH_STRUCT_FLOCK
-struct flock {
-	short	l_type;
-	short	l_whence;
-	__kernel_off_t	l_start;
-	__kernel_off_t	l_len;
-	__kernel_pid_t	l_pid;
-#ifdef	__ARCH_FLOCK_EXTRA_SYSID
-	__ARCH_FLOCK_EXTRA_SYSID
-#endif
-#ifdef	__ARCH_FLOCK_PAD
-	__ARCH_FLOCK_PAD
-#endif
-};
-
-struct flock64 {
-	short  l_type;
-	short  l_whence;
-	__kernel_loff_t l_start;
-	__kernel_loff_t l_len;
-	__kernel_pid_t  l_pid;
-#ifdef	__ARCH_FLOCK64_PAD
-	__ARCH_FLOCK64_PAD
-#endif
-};
-#endif /* HAVE_ARCH_STRUCT_FLOCK */
-
-#endif /* _ASM_GENERIC_FCNTL_H */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
deleted file mode 100644
index 282e90aeb163..000000000000
--- a/tools/include/uapi/linux/fcntl.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_FCNTL_H
-#define _UAPI_LINUX_FCNTL_H
-
-#include <asm/fcntl.h>
-#include <linux/openat2.h>
-
-#define F_SETLEASE	(F_LINUX_SPECIFIC_BASE + 0)
-#define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
-
-/*
- * Cancel a blocking posix lock; internal use only until we expose an
- * asynchronous lock api to userspace:
- */
-#define F_CANCELLK	(F_LINUX_SPECIFIC_BASE + 5)
-
-/* Create a file descriptor with FD_CLOEXEC set. */
-#define F_DUPFD_CLOEXEC	(F_LINUX_SPECIFIC_BASE + 6)
-
-/*
- * Request nofications on a directory.
- * See below for events that may be notified.
- */
-#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE+2)
-
-/*
- * Set and get of pipe page size array
- */
-#define F_SETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 7)
-#define F_GETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 8)
-
-/*
- * Set/Get seals
- */
-#define F_ADD_SEALS	(F_LINUX_SPECIFIC_BASE + 9)
-#define F_GET_SEALS	(F_LINUX_SPECIFIC_BASE + 10)
-
-/*
- * Types of seals
- */
-#define F_SEAL_SEAL	0x0001	/* prevent further seals from being set */
-#define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
-#define F_SEAL_GROW	0x0004	/* prevent file from growing */
-#define F_SEAL_WRITE	0x0008	/* prevent writes */
-#define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
-#define F_SEAL_EXEC	0x0020  /* prevent chmod modifying exec bits */
-/* (1U << 31) is reserved for signed error codes */
-
-/*
- * Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
- * underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
- * the specific file.
- */
-#define F_GET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 11)
-#define F_SET_RW_HINT		(F_LINUX_SPECIFIC_BASE + 12)
-#define F_GET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 13)
-#define F_SET_FILE_RW_HINT	(F_LINUX_SPECIFIC_BASE + 14)
-
-/*
- * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
- * used to clear any hints previously set.
- */
-#define RWH_WRITE_LIFE_NOT_SET	0
-#define RWH_WRITE_LIFE_NONE	1
-#define RWH_WRITE_LIFE_SHORT	2
-#define RWH_WRITE_LIFE_MEDIUM	3
-#define RWH_WRITE_LIFE_LONG	4
-#define RWH_WRITE_LIFE_EXTREME	5
-
-/*
- * The originally introduced spelling is remained from the first
- * versions of the patch set that introduced the feature, see commit
- * v4.13-rc1~212^2~51.
- */
-#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
-
-/*
- * Types of directory notifications that may be requested.
- */
-#define DN_ACCESS	0x00000001	/* File accessed */
-#define DN_MODIFY	0x00000002	/* File modified */
-#define DN_CREATE	0x00000004	/* File created */
-#define DN_DELETE	0x00000008	/* File removed */
-#define DN_RENAME	0x00000010	/* File renamed */
-#define DN_ATTRIB	0x00000020	/* File changed attibutes */
-#define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
-
-/*
- * The constants AT_REMOVEDIR and AT_EACCESS have the same value.  AT_EACCESS is
- * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
- * unlinkat.  The two functions do completely different things and therefore,
- * the flags can be allowed to overlap.  For example, passing AT_REMOVEDIR to
- * faccessat would be undefined behavior and thus treating it equivalent to
- * AT_EACCESS is valid undefined behavior.
- */
-#define AT_FDCWD		-100    /* Special value used to indicate
-                                           openat should use the current
-                                           working directory. */
-#define AT_SYMLINK_NOFOLLOW	0x100   /* Do not follow symbolic links.  */
-#define AT_EACCESS		0x200	/* Test access permitted for
-                                           effective IDs, not real IDs.  */
-#define AT_REMOVEDIR		0x200   /* Remove directory instead of
-                                           unlinking file.  */
-#define AT_SYMLINK_FOLLOW	0x400   /* Follow symbolic links.  */
-#define AT_NO_AUTOMOUNT		0x800	/* Suppress terminal automount traversal */
-#define AT_EMPTY_PATH		0x1000	/* Allow empty relative pathname */
-
-#define AT_STATX_SYNC_TYPE	0x6000	/* Type of synchronisation required from statx() */
-#define AT_STATX_SYNC_AS_STAT	0x0000	/* - Do whatever stat() does */
-#define AT_STATX_FORCE_SYNC	0x2000	/* - Force the attributes to be sync'd with the server */
-#define AT_STATX_DONT_SYNC	0x4000	/* - Don't sync attributes with the server */
-
-#define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
-
-/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */
-#define AT_HANDLE_FID		AT_REMOVEDIR	/* file handle is needed to
-					compare object identity and may not
-					be usable to open_by_handle_at(2) */
-#if defined(__KERNEL__)
-#define AT_GETATTR_NOSEC	0x80000000
-#endif
-
-#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
deleted file mode 100644
index a5feb7604948..000000000000
--- a/tools/include/uapi/linux/openat2.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_OPENAT2_H
-#define _UAPI_LINUX_OPENAT2_H
-
-#include <linux/types.h>
-
-/*
- * Arguments for how openat2(2) should open the target path. If only @flags and
- * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
- *
- * However, unlike openat(2), unknown or invalid bits in @flags result in
- * -EINVAL rather than being silently ignored. @mode must be zero unless one of
- * {O_CREAT, O_TMPFILE} are set.
- *
- * @flags: O_* flags.
- * @mode: O_CREAT/O_TMPFILE file mode.
- * @resolve: RESOLVE_* flags.
- */
-struct open_how {
-	__u64 flags;
-	__u64 mode;
-	__u64 resolve;
-};
-
-/* how->resolve flags for openat2(2). */
-#define RESOLVE_NO_XDEV		0x01 /* Block mount-point crossings
-					(includes bind-mounts). */
-#define RESOLVE_NO_MAGICLINKS	0x02 /* Block traversal through procfs-style
-					"magic-links". */
-#define RESOLVE_NO_SYMLINKS	0x04 /* Block traversal through all symlinks
-					(implies OEXT_NO_MAGICLINKS) */
-#define RESOLVE_BENEATH		0x08 /* Block "lexical" trickery like
-					"..", symlinks, and absolute
-					paths which escape the dirfd. */
-#define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
-					be scoped inside the dirfd
-					(similar to chroot(2)). */
-#define RESOLVE_CACHED		0x20 /* Only complete if resolution can be
-					completed through cached lookup. May
-					return -EAGAIN if that's not
-					possible. */
-
-#endif /* _UAPI_LINUX_OPENAT2_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 03d00110a48f..4ea674df11f8 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -10,12 +10,10 @@ FILES=(
   "include/uapi/drm/drm.h"
   "include/uapi/drm/i915_drm.h"
   "include/uapi/linux/fadvise.h"
-  "include/uapi/linux/fcntl.h"
   "include/uapi/linux/fscrypt.h"
   "include/uapi/linux/kcmp.h"
   "include/uapi/linux/kvm.h"
   "include/uapi/linux/in.h"
-  "include/uapi/linux/openat2.h"
   "include/uapi/linux/perf_event.h"
   "include/uapi/linux/sched.h"
   "include/uapi/linux/seccomp.h"
-- 
cgit 


From a672af9139a843eb7a48fd7846bb6df8f81b5f86 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 15 Mar 2024 16:18:14 -0300
Subject: tools headers: Remove almost unused copy of uapi/stat.h, add few
 conditional defines

These were used to build perf to provide defines not available in older
distros, but this was back in 2017, nowadays most the distros that are
supported and I have build containers for work using just the system
headers, so ditch them.

For the few that don't have STATX_MNT_ID{_UNIQUE}, or STATX_MNT_DIOALIGN
add them conditionally.

Some of these older distros may not have things that are used in 'perf
trace', but then they also don't have libtraceevent packages, so don't
build 'perf trace'.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20240315204835.748716-6-acme@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/stat.h | 195 ----------------------------------------
 tools/perf/check-headers.sh     |   1 -
 tools/perf/trace/beauty/statx.c |  12 ++-
 3 files changed, 11 insertions(+), 197 deletions(-)
 delete mode 100644 tools/include/uapi/linux/stat.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
deleted file mode 100644
index 2f2ee82d5517..000000000000
--- a/tools/include/uapi/linux/stat.h
+++ /dev/null
@@ -1,195 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_STAT_H
-#define _UAPI_LINUX_STAT_H
-
-#include <linux/types.h>
-
-#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
-
-#define S_IFMT  00170000
-#define S_IFSOCK 0140000
-#define S_IFLNK	 0120000
-#define S_IFREG  0100000
-#define S_IFBLK  0060000
-#define S_IFDIR  0040000
-#define S_IFCHR  0020000
-#define S_IFIFO  0010000
-#define S_ISUID  0004000
-#define S_ISGID  0002000
-#define S_ISVTX  0001000
-
-#define S_ISLNK(m)	(((m) & S_IFMT) == S_IFLNK)
-#define S_ISREG(m)	(((m) & S_IFMT) == S_IFREG)
-#define S_ISDIR(m)	(((m) & S_IFMT) == S_IFDIR)
-#define S_ISCHR(m)	(((m) & S_IFMT) == S_IFCHR)
-#define S_ISBLK(m)	(((m) & S_IFMT) == S_IFBLK)
-#define S_ISFIFO(m)	(((m) & S_IFMT) == S_IFIFO)
-#define S_ISSOCK(m)	(((m) & S_IFMT) == S_IFSOCK)
-
-#define S_IRWXU 00700
-#define S_IRUSR 00400
-#define S_IWUSR 00200
-#define S_IXUSR 00100
-
-#define S_IRWXG 00070
-#define S_IRGRP 00040
-#define S_IWGRP 00020
-#define S_IXGRP 00010
-
-#define S_IRWXO 00007
-#define S_IROTH 00004
-#define S_IWOTH 00002
-#define S_IXOTH 00001
-
-#endif
-
-/*
- * Timestamp structure for the timestamps in struct statx.
- *
- * tv_sec holds the number of seconds before (negative) or after (positive)
- * 00:00:00 1st January 1970 UTC.
- *
- * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time.
- *
- * __reserved is held in case we need a yet finer resolution.
- */
-struct statx_timestamp {
-	__s64	tv_sec;
-	__u32	tv_nsec;
-	__s32	__reserved;
-};
-
-/*
- * Structures for the extended file attribute retrieval system call
- * (statx()).
- *
- * The caller passes a mask of what they're specifically interested in as a
- * parameter to statx().  What statx() actually got will be indicated in
- * st_mask upon return.
- *
- * For each bit in the mask argument:
- *
- * - if the datum is not supported:
- *
- *   - the bit will be cleared, and
- *
- *   - the datum will be set to an appropriate fabricated value if one is
- *     available (eg. CIFS can take a default uid and gid), otherwise
- *
- *   - the field will be cleared;
- *
- * - otherwise, if explicitly requested:
- *
- *   - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is
- *     set or if the datum is considered out of date, and
- *
- *   - the field will be filled in and the bit will be set;
- *
- * - otherwise, if not requested, but available in approximate form without any
- *   effort, it will be filled in anyway, and the bit will be set upon return
- *   (it might not be up to date, however, and no attempt will be made to
- *   synchronise the internal state first);
- *
- * - otherwise the field and the bit will be cleared before returning.
- *
- * Items in STATX_BASIC_STATS may be marked unavailable on return, but they
- * will have values installed for compatibility purposes so that stat() and
- * co. can be emulated in userspace.
- */
-struct statx {
-	/* 0x00 */
-	__u32	stx_mask;	/* What results were written [uncond] */
-	__u32	stx_blksize;	/* Preferred general I/O size [uncond] */
-	__u64	stx_attributes;	/* Flags conveying information about the file [uncond] */
-	/* 0x10 */
-	__u32	stx_nlink;	/* Number of hard links */
-	__u32	stx_uid;	/* User ID of owner */
-	__u32	stx_gid;	/* Group ID of owner */
-	__u16	stx_mode;	/* File mode */
-	__u16	__spare0[1];
-	/* 0x20 */
-	__u64	stx_ino;	/* Inode number */
-	__u64	stx_size;	/* File size */
-	__u64	stx_blocks;	/* Number of 512-byte blocks allocated */
-	__u64	stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
-	/* 0x40 */
-	struct statx_timestamp	stx_atime;	/* Last access time */
-	struct statx_timestamp	stx_btime;	/* File creation time */
-	struct statx_timestamp	stx_ctime;	/* Last attribute change time */
-	struct statx_timestamp	stx_mtime;	/* Last data modification time */
-	/* 0x80 */
-	__u32	stx_rdev_major;	/* Device ID of special file [if bdev/cdev] */
-	__u32	stx_rdev_minor;
-	__u32	stx_dev_major;	/* ID of device containing file [uncond] */
-	__u32	stx_dev_minor;
-	/* 0x90 */
-	__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 */
-	/* 0xa0 */
-	__u64	__spare3[12];	/* Spare space for future expansion */
-	/* 0x100 */
-};
-
-/*
- * Flags to be stx_mask
- *
- * Query request/result mask for statx() and struct statx::stx_mask.
- *
- * These bits should be set in the mask argument of statx() to request
- * particular items when calling statx().
- */
-#define STATX_TYPE		0x00000001U	/* Want/got stx_mode & S_IFMT */
-#define STATX_MODE		0x00000002U	/* Want/got stx_mode & ~S_IFMT */
-#define STATX_NLINK		0x00000004U	/* Want/got stx_nlink */
-#define STATX_UID		0x00000008U	/* Want/got stx_uid */
-#define STATX_GID		0x00000010U	/* Want/got stx_gid */
-#define STATX_ATIME		0x00000020U	/* Want/got stx_atime */
-#define STATX_MTIME		0x00000040U	/* Want/got stx_mtime */
-#define STATX_CTIME		0x00000080U	/* Want/got stx_ctime */
-#define STATX_INO		0x00000100U	/* Want/got stx_ino */
-#define STATX_SIZE		0x00000200U	/* Want/got stx_size */
-#define STATX_BLOCKS		0x00000400U	/* Want/got stx_blocks */
-#define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
-#define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
-#define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
-#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__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
-
-#ifndef __KERNEL__
-/*
- * This is deprecated, and shall remain the same value in the future.  To avoid
- * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME)
- * instead.
- */
-#define STATX_ALL		0x00000fffU
-#endif
-
-/*
- * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
- *
- * These give information about the features or the state of a file that might
- * be of use to ordinary userspace programs such as GUIs or ls rather than
- * specialised tools.
- *
- * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags
- * semantically.  Where possible, the numerical value is picked to correspond
- * also.  Note that the DAX attribute indicates that the file is in the CPU
- * direct access state.  It does not correspond to the per-inode flag that
- * some filesystems support.
- *
- */
-#define STATX_ATTR_COMPRESSED		0x00000004 /* [I] File is compressed by the fs */
-#define STATX_ATTR_IMMUTABLE		0x00000010 /* [I] File is marked immutable */
-#define STATX_ATTR_APPEND		0x00000020 /* [I] File is append-only */
-#define STATX_ATTR_NODUMP		0x00000040 /* [I] File is not to be dumped */
-#define STATX_ATTR_ENCRYPTED		0x00000800 /* [I] File requires key to decrypt in fs */
-#define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
-#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 */
-
-
-#endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 4ea674df11f8..859cd6f35b0a 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -17,7 +17,6 @@ FILES=(
   "include/uapi/linux/perf_event.h"
   "include/uapi/linux/sched.h"
   "include/uapi/linux/seccomp.h"
-  "include/uapi/linux/stat.h"
   "include/uapi/linux/vhost.h"
   "include/linux/bits.h"
   "include/vdso/bits.h"
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index d1ccc93316bd..1f7e34ed4e02 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -9,7 +9,17 @@
 #include <linux/kernel.h>
 #include <sys/types.h>
 #include <linux/fcntl.h>
-#include <uapi/linux/stat.h>
+#include <linux/stat.h>
+
+#ifndef STATX_MNT_ID
+#define STATX_MNT_ID		0x00001000U
+#endif
+#ifndef STATX_DIOALIGN
+#define STATX_DIOALIGN		0x00002000U
+#endif
+#ifndef STATX_MNT_ID_UNIQUE
+#define STATX_MNT_ID_UNIQUE	0x00004000U
+#endif
 
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg)
 {
-- 
cgit 


From 2316ef589181b5b2fd6cbced24439ba4ac096bd8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 19 Mar 2024 14:49:32 -0300
Subject: perf beauty: Introduce scrape script for 'clone' syscall 'flags'
 argument

It was using the first variation on producing a string representation
for a binary flag, one that used the copy of uapi/linux/sched.h with
preprocessor tricks that had to be updated everytime a new flag was
introduced.

Use the more recent scrape script + strarray + strarray__scnprintf_flags() combo.

  $ tools/perf/trace/beauty/clone.sh | head -5
  static const char *clone_flags[] = {
  	[ilog2(0x00000100) + 1] = "VM",
  	[ilog2(0x00000200) + 1] = "FS",
  	[ilog2(0x00000400) + 1] = "FILES",
  	[ilog2(0x00000800) + 1] = "SIGHAND",
  $

Now we can move uapi/linux/sched.h from tools/include/, that is used for
building perf to the scrape only directory tools/perf/trace/beauty/include.

Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZfnULIn3XKDq0bpc@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/sched.h                   | 148 ---------------------
 tools/perf/Makefile.perf                           |  14 +-
 tools/perf/check-headers.sh                        |   2 +-
 tools/perf/trace/beauty/clone.c                    |  46 +------
 tools/perf/trace/beauty/clone.sh                   |  17 +++
 tools/perf/trace/beauty/include/uapi/linux/sched.h | 148 +++++++++++++++++++++
 6 files changed, 182 insertions(+), 193 deletions(-)
 delete mode 100644 tools/include/uapi/linux/sched.h
 create mode 100755 tools/perf/trace/beauty/clone.sh
 create mode 100644 tools/perf/trace/beauty/include/uapi/linux/sched.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
deleted file mode 100644
index 3bac0a8ceab2..000000000000
--- a/tools/include/uapi/linux/sched.h
+++ /dev/null
@@ -1,148 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_SCHED_H
-#define _UAPI_LINUX_SCHED_H
-
-#include <linux/types.h>
-
-/*
- * cloning flags:
- */
-#define CSIGNAL		0x000000ff	/* signal mask to be sent at exit */
-#define CLONE_VM	0x00000100	/* set if VM shared between processes */
-#define CLONE_FS	0x00000200	/* set if fs info shared between processes */
-#define CLONE_FILES	0x00000400	/* set if open files shared between processes */
-#define CLONE_SIGHAND	0x00000800	/* set if signal handlers and blocked signals shared */
-#define CLONE_PIDFD	0x00001000	/* set if a pidfd should be placed in parent */
-#define CLONE_PTRACE	0x00002000	/* set if we want to let tracing continue on the child too */
-#define CLONE_VFORK	0x00004000	/* set if the parent wants the child to wake it up on mm_release */
-#define CLONE_PARENT	0x00008000	/* set if we want to have the same parent as the cloner */
-#define CLONE_THREAD	0x00010000	/* Same thread group? */
-#define CLONE_NEWNS	0x00020000	/* New mount namespace group */
-#define CLONE_SYSVSEM	0x00040000	/* share system V SEM_UNDO semantics */
-#define CLONE_SETTLS	0x00080000	/* create a new TLS for the child */
-#define CLONE_PARENT_SETTID	0x00100000	/* set the TID in the parent */
-#define CLONE_CHILD_CLEARTID	0x00200000	/* clear the TID in the child */
-#define CLONE_DETACHED		0x00400000	/* Unused, ignored */
-#define CLONE_UNTRACED		0x00800000	/* set if the tracing process can't force CLONE_PTRACE on this clone */
-#define CLONE_CHILD_SETTID	0x01000000	/* set the TID in the child */
-#define CLONE_NEWCGROUP		0x02000000	/* New cgroup namespace */
-#define CLONE_NEWUTS		0x04000000	/* New utsname namespace */
-#define CLONE_NEWIPC		0x08000000	/* New ipc namespace */
-#define CLONE_NEWUSER		0x10000000	/* New user namespace */
-#define CLONE_NEWPID		0x20000000	/* New pid namespace */
-#define CLONE_NEWNET		0x40000000	/* New network namespace */
-#define CLONE_IO		0x80000000	/* Clone io context */
-
-/* Flags for the clone3() syscall. */
-#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
-#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
-
-/*
- * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
- * syscalls only:
- */
-#define CLONE_NEWTIME	0x00000080	/* New time namespace */
-
-#ifndef __ASSEMBLY__
-/**
- * struct clone_args - arguments for the clone3 syscall
- * @flags:        Flags for the new process as listed above.
- *                All flags are valid except for CSIGNAL and
- *                CLONE_DETACHED.
- * @pidfd:        If CLONE_PIDFD is set, a pidfd will be
- *                returned in this argument.
- * @child_tid:    If CLONE_CHILD_SETTID is set, the TID of the
- *                child process will be returned in the child's
- *                memory.
- * @parent_tid:   If CLONE_PARENT_SETTID is set, the TID of
- *                the child process will be returned in the
- *                parent's memory.
- * @exit_signal:  The exit_signal the parent process will be
- *                sent when the child exits.
- * @stack:        Specify the location of the stack for the
- *                child process.
- *                Note, @stack is expected to point to the
- *                lowest address. The stack direction will be
- *                determined by the kernel and set up
- *                appropriately based on @stack_size.
- * @stack_size:   The size of the stack for the child process.
- * @tls:          If CLONE_SETTLS is set, the tls descriptor
- *                is set to tls.
- * @set_tid:      Pointer to an array of type *pid_t. The size
- *                of the array is defined using @set_tid_size.
- *                This array is used to select PIDs/TIDs for
- *                newly created processes. The first element in
- *                this defines the PID in the most nested PID
- *                namespace. Each additional element in the array
- *                defines the PID in the parent PID namespace of
- *                the original PID namespace. If the array has
- *                less entries than the number of currently
- *                nested PID namespaces only the PIDs in the
- *                corresponding namespaces are set.
- * @set_tid_size: This defines the size of the array referenced
- *                in @set_tid. This cannot be larger than the
- *                kernel's limit of nested PID namespaces.
- * @cgroup:       If CLONE_INTO_CGROUP is specified set this to
- *                a file descriptor for the cgroup.
- *
- * The structure is versioned by size and thus extensible.
- * New struct members must go at the end of the struct and
- * must be properly 64bit aligned.
- */
-struct clone_args {
-	__aligned_u64 flags;
-	__aligned_u64 pidfd;
-	__aligned_u64 child_tid;
-	__aligned_u64 parent_tid;
-	__aligned_u64 exit_signal;
-	__aligned_u64 stack;
-	__aligned_u64 stack_size;
-	__aligned_u64 tls;
-	__aligned_u64 set_tid;
-	__aligned_u64 set_tid_size;
-	__aligned_u64 cgroup;
-};
-#endif
-
-#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
-#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
-#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */
-
-/*
- * Scheduling policies
- */
-#define SCHED_NORMAL		0
-#define SCHED_FIFO		1
-#define SCHED_RR		2
-#define SCHED_BATCH		3
-/* SCHED_ISO: reserved but not implemented yet */
-#define SCHED_IDLE		5
-#define SCHED_DEADLINE		6
-
-/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
-#define SCHED_RESET_ON_FORK     0x40000000
-
-/*
- * For the sched_{set,get}attr() calls
- */
-#define SCHED_FLAG_RESET_ON_FORK	0x01
-#define SCHED_FLAG_RECLAIM		0x02
-#define SCHED_FLAG_DL_OVERRUN		0x04
-#define SCHED_FLAG_KEEP_POLICY		0x08
-#define SCHED_FLAG_KEEP_PARAMS		0x10
-#define SCHED_FLAG_UTIL_CLAMP_MIN	0x20
-#define SCHED_FLAG_UTIL_CLAMP_MAX	0x40
-
-#define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
-				 SCHED_FLAG_KEEP_PARAMS)
-
-#define SCHED_FLAG_UTIL_CLAMP	(SCHED_FLAG_UTIL_CLAMP_MIN | \
-				 SCHED_FLAG_UTIL_CLAMP_MAX)
-
-#define SCHED_FLAG_ALL	(SCHED_FLAG_RESET_ON_FORK	| \
-			 SCHED_FLAG_RECLAIM		| \
-			 SCHED_FLAG_DL_OVERRUN		| \
-			 SCHED_FLAG_KEEP_ALL		| \
-			 SCHED_FLAG_UTIL_CLAMP)
-
-#endif /* _UAPI_LINUX_SCHED_H */
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index f5654d06e313..ccd2dcbc64f7 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -485,13 +485,20 @@ x86_arch_asm_dir := $(srctree)/tools/arch/x86/include/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
-drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
-drm_hdr_dir := $(srctree)/tools/include/uapi/drm
-drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
 
 # Create output directory if not already present
 $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_outdir)')
 
+clone_flags_array := $(beauty_outdir)/clone_flags_array.c
+clone_flags_tbl := $(srctree)/tools/perf/trace/beauty/clone.sh
+
+$(clone_flags_array): $(beauty_uapi_linux_dir)/sched.h $(clone_flags_tbl)
+	$(Q)$(SHELL) '$(clone_flags_tbl)' $(beauty_uapi_linux_dir) > $@
+
+drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
+drm_hdr_dir := $(srctree)/tools/include/uapi/drm
+drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
+
 $(drm_ioctl_array): $(drm_hdr_dir)/drm.h $(drm_hdr_dir)/i915_drm.h $(drm_ioctl_tbl)
 	$(Q)$(SHELL) '$(drm_ioctl_tbl)' $(drm_hdr_dir) > $@
 
@@ -765,6 +772,7 @@ build-dir   = $(or $(__build-dir),.)
 
 prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders \
 	arm64-sysreg-defs \
+	$(clone_flags_array) \
 	$(drm_ioctl_array) \
 	$(fadvise_advice_array) \
 	$(fsconfig_arrays) \
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 859cd6f35b0a..413c9b747216 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -15,7 +15,6 @@ FILES=(
   "include/uapi/linux/kvm.h"
   "include/uapi/linux/in.h"
   "include/uapi/linux/perf_event.h"
-  "include/uapi/linux/sched.h"
   "include/uapi/linux/seccomp.h"
   "include/uapi/linux/vhost.h"
   "include/linux/bits.h"
@@ -93,6 +92,7 @@ BEAUTY_FILES=(
   "include/uapi/linux/fs.h"
   "include/uapi/linux/mount.h"
   "include/uapi/linux/prctl.h"
+  "include/uapi/linux/sched.h"
   "include/uapi/linux/usbdevice_fs.h"
   "include/uapi/sound/asound.h"
 )
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index f4db894e0af6..c9fa8f7e82b9 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -7,52 +7,16 @@
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
+#include <linux/log2.h>
 #include <sys/types.h>
-#include <uapi/linux/sched.h>
+#include <sched.h>
 
 static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
 {
-	const char *prefix = "CLONE_";
-	int printed = 0;
+#include "trace/beauty/generated/clone_flags_array.c"
+	static DEFINE_STRARRAY(clone_flags, "CLONE_");
 
-#define	P_FLAG(n) \
-	if (flags & CLONE_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s%s", printed ? "|" : "", show_prefix ? prefix : "", #n); \
-		flags &= ~CLONE_##n; \
-	}
-
-	P_FLAG(VM);
-	P_FLAG(FS);
-	P_FLAG(FILES);
-	P_FLAG(SIGHAND);
-	P_FLAG(PIDFD);
-	P_FLAG(PTRACE);
-	P_FLAG(VFORK);
-	P_FLAG(PARENT);
-	P_FLAG(THREAD);
-	P_FLAG(NEWNS);
-	P_FLAG(SYSVSEM);
-	P_FLAG(SETTLS);
-	P_FLAG(PARENT_SETTID);
-	P_FLAG(CHILD_CLEARTID);
-	P_FLAG(DETACHED);
-	P_FLAG(UNTRACED);
-	P_FLAG(CHILD_SETTID);
-	P_FLAG(NEWCGROUP);
-	P_FLAG(NEWUTS);
-	P_FLAG(NEWIPC);
-	P_FLAG(NEWUSER);
-	P_FLAG(NEWPID);
-	P_FLAG(NEWNET);
-	P_FLAG(IO);
-	P_FLAG(CLEAR_SIGHAND);
-	P_FLAG(INTO_CGROUP);
-#undef P_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
+	return strarray__scnprintf_flags(&strarray__clone_flags, bf, size, show_prefix, flags);
 }
 
 size_t syscall_arg__scnprintf_clone_flags(char *bf, size_t size, struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/clone.sh b/tools/perf/trace/beauty/clone.sh
new file mode 100755
index 000000000000..18b6c0d75693
--- /dev/null
+++ b/tools/perf/trace/beauty/clone.sh
@@ -0,0 +1,17 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 1 ] ; then
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
+else
+	beauty_uapi_linux_dir=$1
+fi
+
+linux_sched=${beauty_uapi_linux_dir}/sched.h
+
+printf "static const char *clone_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+CLONE_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+grep -E $regex ${linux_sched} | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/include/uapi/linux/sched.h b/tools/perf/trace/beauty/include/uapi/linux/sched.h
new file mode 100644
index 000000000000..3bac0a8ceab2
--- /dev/null
+++ b/tools/perf/trace/beauty/include/uapi/linux/sched.h
@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SCHED_H
+#define _UAPI_LINUX_SCHED_H
+
+#include <linux/types.h>
+
+/*
+ * cloning flags:
+ */
+#define CSIGNAL		0x000000ff	/* signal mask to be sent at exit */
+#define CLONE_VM	0x00000100	/* set if VM shared between processes */
+#define CLONE_FS	0x00000200	/* set if fs info shared between processes */
+#define CLONE_FILES	0x00000400	/* set if open files shared between processes */
+#define CLONE_SIGHAND	0x00000800	/* set if signal handlers and blocked signals shared */
+#define CLONE_PIDFD	0x00001000	/* set if a pidfd should be placed in parent */
+#define CLONE_PTRACE	0x00002000	/* set if we want to let tracing continue on the child too */
+#define CLONE_VFORK	0x00004000	/* set if the parent wants the child to wake it up on mm_release */
+#define CLONE_PARENT	0x00008000	/* set if we want to have the same parent as the cloner */
+#define CLONE_THREAD	0x00010000	/* Same thread group? */
+#define CLONE_NEWNS	0x00020000	/* New mount namespace group */
+#define CLONE_SYSVSEM	0x00040000	/* share system V SEM_UNDO semantics */
+#define CLONE_SETTLS	0x00080000	/* create a new TLS for the child */
+#define CLONE_PARENT_SETTID	0x00100000	/* set the TID in the parent */
+#define CLONE_CHILD_CLEARTID	0x00200000	/* clear the TID in the child */
+#define CLONE_DETACHED		0x00400000	/* Unused, ignored */
+#define CLONE_UNTRACED		0x00800000	/* set if the tracing process can't force CLONE_PTRACE on this clone */
+#define CLONE_CHILD_SETTID	0x01000000	/* set the TID in the child */
+#define CLONE_NEWCGROUP		0x02000000	/* New cgroup namespace */
+#define CLONE_NEWUTS		0x04000000	/* New utsname namespace */
+#define CLONE_NEWIPC		0x08000000	/* New ipc namespace */
+#define CLONE_NEWUSER		0x10000000	/* New user namespace */
+#define CLONE_NEWPID		0x20000000	/* New pid namespace */
+#define CLONE_NEWNET		0x40000000	/* New network namespace */
+#define CLONE_IO		0x80000000	/* Clone io context */
+
+/* Flags for the clone3() syscall. */
+#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
+
+/*
+ * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
+ * syscalls only:
+ */
+#define CLONE_NEWTIME	0x00000080	/* New time namespace */
+
+#ifndef __ASSEMBLY__
+/**
+ * struct clone_args - arguments for the clone3 syscall
+ * @flags:        Flags for the new process as listed above.
+ *                All flags are valid except for CSIGNAL and
+ *                CLONE_DETACHED.
+ * @pidfd:        If CLONE_PIDFD is set, a pidfd will be
+ *                returned in this argument.
+ * @child_tid:    If CLONE_CHILD_SETTID is set, the TID of the
+ *                child process will be returned in the child's
+ *                memory.
+ * @parent_tid:   If CLONE_PARENT_SETTID is set, the TID of
+ *                the child process will be returned in the
+ *                parent's memory.
+ * @exit_signal:  The exit_signal the parent process will be
+ *                sent when the child exits.
+ * @stack:        Specify the location of the stack for the
+ *                child process.
+ *                Note, @stack is expected to point to the
+ *                lowest address. The stack direction will be
+ *                determined by the kernel and set up
+ *                appropriately based on @stack_size.
+ * @stack_size:   The size of the stack for the child process.
+ * @tls:          If CLONE_SETTLS is set, the tls descriptor
+ *                is set to tls.
+ * @set_tid:      Pointer to an array of type *pid_t. The size
+ *                of the array is defined using @set_tid_size.
+ *                This array is used to select PIDs/TIDs for
+ *                newly created processes. The first element in
+ *                this defines the PID in the most nested PID
+ *                namespace. Each additional element in the array
+ *                defines the PID in the parent PID namespace of
+ *                the original PID namespace. If the array has
+ *                less entries than the number of currently
+ *                nested PID namespaces only the PIDs in the
+ *                corresponding namespaces are set.
+ * @set_tid_size: This defines the size of the array referenced
+ *                in @set_tid. This cannot be larger than the
+ *                kernel's limit of nested PID namespaces.
+ * @cgroup:       If CLONE_INTO_CGROUP is specified set this to
+ *                a file descriptor for the cgroup.
+ *
+ * The structure is versioned by size and thus extensible.
+ * New struct members must go at the end of the struct and
+ * must be properly 64bit aligned.
+ */
+struct clone_args {
+	__aligned_u64 flags;
+	__aligned_u64 pidfd;
+	__aligned_u64 child_tid;
+	__aligned_u64 parent_tid;
+	__aligned_u64 exit_signal;
+	__aligned_u64 stack;
+	__aligned_u64 stack_size;
+	__aligned_u64 tls;
+	__aligned_u64 set_tid;
+	__aligned_u64 set_tid_size;
+	__aligned_u64 cgroup;
+};
+#endif
+
+#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
+#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
+#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */
+
+/*
+ * Scheduling policies
+ */
+#define SCHED_NORMAL		0
+#define SCHED_FIFO		1
+#define SCHED_RR		2
+#define SCHED_BATCH		3
+/* SCHED_ISO: reserved but not implemented yet */
+#define SCHED_IDLE		5
+#define SCHED_DEADLINE		6
+
+/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
+#define SCHED_RESET_ON_FORK     0x40000000
+
+/*
+ * For the sched_{set,get}attr() calls
+ */
+#define SCHED_FLAG_RESET_ON_FORK	0x01
+#define SCHED_FLAG_RECLAIM		0x02
+#define SCHED_FLAG_DL_OVERRUN		0x04
+#define SCHED_FLAG_KEEP_POLICY		0x08
+#define SCHED_FLAG_KEEP_PARAMS		0x10
+#define SCHED_FLAG_UTIL_CLAMP_MIN	0x20
+#define SCHED_FLAG_UTIL_CLAMP_MAX	0x40
+
+#define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
+				 SCHED_FLAG_KEEP_PARAMS)
+
+#define SCHED_FLAG_UTIL_CLAMP	(SCHED_FLAG_UTIL_CLAMP_MIN | \
+				 SCHED_FLAG_UTIL_CLAMP_MAX)
+
+#define SCHED_FLAG_ALL	(SCHED_FLAG_RESET_ON_FORK	| \
+			 SCHED_FLAG_RECLAIM		| \
+			 SCHED_FLAG_DL_OVERRUN		| \
+			 SCHED_FLAG_KEEP_ALL		| \
+			 SCHED_FLAG_UTIL_CLAMP)
+
+#endif /* _UAPI_LINUX_SCHED_H */
-- 
cgit 


From 4962e1949608fed932d661ef45803a5bee69bebe Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 11 Mar 2024 17:07:33 -0300
Subject: perf beauty: Move uapi/linux/vhost.h copy out of the directory used
 to build perf

It is only used to generate string tables, not to build perf, so move it
to the tools/perf/trace/beauty/include/ hierarchy, that is used just for
scraping.

This is a something that should've have happened, as happened with the
linux/socket.h scrapper, do it now as Ian suggested while doing an
audit/refactor session in the headers used by perf.

No other tools/ living code uses it, just <linux/vhost.h> coming from
either 'make install_headers' or from the system /usr/include/
directory.

Suggested-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/CAP-5=fWZVrpRufO4w-S4EcSi9STXcTAN2ERLwTSN7yrSSA-otQ@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/vhost.h                   | 230 ---------------------
 tools/perf/Makefile.perf                           |   5 +-
 tools/perf/check-headers.sh                        |   2 +-
 tools/perf/trace/beauty/include/uapi/linux/vhost.h | 230 +++++++++++++++++++++
 tools/perf/trace/beauty/vhost_virtio_ioctl.sh      |   6 +-
 5 files changed, 236 insertions(+), 237 deletions(-)
 delete mode 100644 tools/include/uapi/linux/vhost.h
 create mode 100644 tools/perf/trace/beauty/include/uapi/linux/vhost.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
deleted file mode 100644
index 649560c685f1..000000000000
--- a/tools/include/uapi/linux/vhost.h
+++ /dev/null
@@ -1,230 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _LINUX_VHOST_H
-#define _LINUX_VHOST_H
-/* Userspace interface for in-kernel virtio accelerators. */
-
-/* vhost is used to reduce the number of system calls involved in virtio.
- *
- * Existing virtio net code is used in the guest without modification.
- *
- * This header includes interface used by userspace hypervisor for
- * device configuration.
- */
-
-#include <linux/vhost_types.h>
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-#define VHOST_FILE_UNBIND -1
-
-/* ioctls */
-
-#define VHOST_VIRTIO 0xAF
-
-/* Features bitmask for forward compatibility.  Transport bits are used for
- * vhost specific features. */
-#define VHOST_GET_FEATURES	_IOR(VHOST_VIRTIO, 0x00, __u64)
-#define VHOST_SET_FEATURES	_IOW(VHOST_VIRTIO, 0x00, __u64)
-
-/* Set current process as the (exclusive) owner of this file descriptor.  This
- * must be called before any other vhost command.  Further calls to
- * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
-#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
-/* Give up ownership, and reset the device to default values.
- * Allows subsequent call to VHOST_OWNER_SET to succeed. */
-#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
-
-/* Set up/modify memory layout */
-#define VHOST_SET_MEM_TABLE	_IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
-
-/* Write logging setup. */
-/* Memory writes can optionally be logged by setting bit at an offset
- * (calculated from the physical address) from specified log base.
- * The bit is set using an atomic 32 bit operation. */
-/* Set base address for logging. */
-#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
-/* Specify an eventfd file descriptor to signal on log write. */
-#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
-/* By default, a device gets one vhost_worker that its virtqueues share. This
- * command allows the owner of the device to create an additional vhost_worker
- * for the device. It can later be bound to 1 or more of its virtqueues using
- * the VHOST_ATTACH_VRING_WORKER command.
- *
- * This must be called after VHOST_SET_OWNER and the caller must be the owner
- * of the device. The new thread will inherit caller's cgroups and namespaces,
- * and will share the caller's memory space. The new thread will also be
- * counted against the caller's RLIMIT_NPROC value.
- *
- * The worker's ID used in other commands will be returned in
- * vhost_worker_state.
- */
-#define VHOST_NEW_WORKER _IOR(VHOST_VIRTIO, 0x8, struct vhost_worker_state)
-/* Free a worker created with VHOST_NEW_WORKER if it's not attached to any
- * virtqueue. If userspace is not able to call this for workers its created,
- * the kernel will free all the device's workers when the device is closed.
- */
-#define VHOST_FREE_WORKER _IOW(VHOST_VIRTIO, 0x9, struct vhost_worker_state)
-
-/* Ring setup. */
-/* Set number of descriptors in ring. This parameter can not
- * be modified while ring is running (bound to a device). */
-#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
-/* Set addresses for the ring. */
-#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
-/* Base value where queue looks for available descriptors */
-#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
-/* Get accessor: reads index, writes value in num */
-#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
-
-/* Set the vring byte order in num. Valid values are VHOST_VRING_LITTLE_ENDIAN
- * or VHOST_VRING_BIG_ENDIAN (other values return -EINVAL).
- * The byte order cannot be changed while the device is active: trying to do so
- * returns -EBUSY.
- * This is a legacy only API that is simply ignored when VIRTIO_F_VERSION_1 is
- * set.
- * Not all kernel configurations support this ioctl, but all configurations that
- * support SET also support GET.
- */
-#define VHOST_VRING_LITTLE_ENDIAN 0
-#define VHOST_VRING_BIG_ENDIAN 1
-#define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
-#define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
-/* Attach a vhost_worker created with VHOST_NEW_WORKER to one of the device's
- * virtqueues.
- *
- * This will replace the virtqueue's existing worker. If the replaced worker
- * is no longer attached to any virtqueues, it can be freed with
- * VHOST_FREE_WORKER.
- */
-#define VHOST_ATTACH_VRING_WORKER _IOW(VHOST_VIRTIO, 0x15,		\
-				       struct vhost_vring_worker)
-/* Return the vring worker's ID */
-#define VHOST_GET_VRING_WORKER _IOWR(VHOST_VIRTIO, 0x16,		\
-				     struct vhost_vring_worker)
-
-/* The following ioctls use eventfd file descriptors to signal and poll
- * for events. */
-
-/* Set eventfd to poll for added buffers */
-#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
-/* Set eventfd to signal when buffers have beed used */
-#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
-/* Set eventfd to signal an error */
-#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
-/* Set busy loop timeout (in us) */
-#define VHOST_SET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x23,	\
-					 struct vhost_vring_state)
-/* Get busy loop timeout (in us) */
-#define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24,	\
-					 struct vhost_vring_state)
-
-/* Set or get vhost backend capability */
-
-#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
-#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
-
-/* VHOST_NET specific defines */
-
-/* Attach virtio net ring to a raw socket, or tap device.
- * The socket must be already bound to an ethernet device, this device will be
- * used for transmit.  Pass fd -1 to unbind from the socket and the transmit
- * device.  This can be used to stop the ring (e.g. for migration). */
-#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
-
-/* VHOST_SCSI specific defines */
-
-#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
-#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
-/* Changing this breaks userspace. */
-#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, int)
-/* Set and get the events missed flag */
-#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32)
-#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32)
-
-/* VHOST_VSOCK specific defines */
-
-#define VHOST_VSOCK_SET_GUEST_CID	_IOW(VHOST_VIRTIO, 0x60, __u64)
-#define VHOST_VSOCK_SET_RUNNING		_IOW(VHOST_VIRTIO, 0x61, int)
-
-/* VHOST_VDPA specific defines */
-
-/* Get the device id. The device ids follow the same definition of
- * the device id defined in virtio-spec.
- */
-#define VHOST_VDPA_GET_DEVICE_ID	_IOR(VHOST_VIRTIO, 0x70, __u32)
-/* Get and set the status. The status bits follow the same definition
- * of the device status defined in virtio-spec.
- */
-#define VHOST_VDPA_GET_STATUS		_IOR(VHOST_VIRTIO, 0x71, __u8)
-#define VHOST_VDPA_SET_STATUS		_IOW(VHOST_VIRTIO, 0x72, __u8)
-/* Get and set the device config. The device config follows the same
- * definition of the device config defined in virtio-spec.
- */
-#define VHOST_VDPA_GET_CONFIG		_IOR(VHOST_VIRTIO, 0x73, \
-					     struct vhost_vdpa_config)
-#define VHOST_VDPA_SET_CONFIG		_IOW(VHOST_VIRTIO, 0x74, \
-					     struct vhost_vdpa_config)
-/* Enable/disable the ring. */
-#define VHOST_VDPA_SET_VRING_ENABLE	_IOW(VHOST_VIRTIO, 0x75, \
-					     struct vhost_vring_state)
-/* Get the max ring size. */
-#define VHOST_VDPA_GET_VRING_NUM	_IOR(VHOST_VIRTIO, 0x76, __u16)
-
-/* Set event fd for config interrupt*/
-#define VHOST_VDPA_SET_CONFIG_CALL	_IOW(VHOST_VIRTIO, 0x77, int)
-
-/* Get the valid iova range */
-#define VHOST_VDPA_GET_IOVA_RANGE	_IOR(VHOST_VIRTIO, 0x78, \
-					     struct vhost_vdpa_iova_range)
-/* Get the config size */
-#define VHOST_VDPA_GET_CONFIG_SIZE	_IOR(VHOST_VIRTIO, 0x79, __u32)
-
-/* Get the count of all virtqueues */
-#define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
-
-/* Get the number of virtqueue groups. */
-#define VHOST_VDPA_GET_GROUP_NUM	_IOR(VHOST_VIRTIO, 0x81, __u32)
-
-/* Get the number of address spaces. */
-#define VHOST_VDPA_GET_AS_NUM		_IOR(VHOST_VIRTIO, 0x7A, unsigned int)
-
-/* Get the group for a virtqueue: read index, write group in num,
- * The virtqueue index is stored in the index field of
- * vhost_vring_state. The group for this specific virtqueue is
- * returned via num field of vhost_vring_state.
- */
-#define VHOST_VDPA_GET_VRING_GROUP	_IOWR(VHOST_VIRTIO, 0x7B,	\
-					      struct vhost_vring_state)
-/* Set the ASID for a virtqueue group. The group index is stored in
- * the index field of vhost_vring_state, the ASID associated with this
- * group is stored at num field of vhost_vring_state.
- */
-#define VHOST_VDPA_SET_GROUP_ASID	_IOW(VHOST_VIRTIO, 0x7C, \
-					     struct vhost_vring_state)
-
-/* Suspend a device so it does not process virtqueue requests anymore
- *
- * After the return of ioctl the device must preserve all the necessary state
- * (the virtqueue vring base plus the possible device specific states) that is
- * required for restoring in the future. The device must not change its
- * configuration after that point.
- */
-#define VHOST_VDPA_SUSPEND		_IO(VHOST_VIRTIO, 0x7D)
-
-/* Resume a device so it can resume processing virtqueue requests
- *
- * After the return of this ioctl the device will have restored all the
- * necessary states and it is fully operational to continue processing the
- * virtqueue descriptors.
- */
-#define VHOST_VDPA_RESUME		_IO(VHOST_VIRTIO, 0x7E)
-
-/* Get the group for the descriptor table including driver & device areas
- * of a virtqueue: read index, write group in num.
- * The virtqueue index is stored in the index field of vhost_vring_state.
- * The group ID of the descriptor table for this specific virtqueue
- * is returned via num field of vhost_vring_state.
- */
-#define VHOST_VDPA_GET_VRING_DESC_GROUP	_IOWR(VHOST_VIRTIO, 0x7F,	\
-					      struct vhost_vring_state)
-#endif
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0d2dbdfc44df..5c35c0d89306 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -580,11 +580,10 @@ $(sockaddr_arrays): $(beauty_linux_dir)/socket.h $(sockaddr_tbl)
 	$(Q)$(SHELL) '$(sockaddr_tbl)' $(beauty_linux_dir) > $@
 
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
-vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
 vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
 
-$(vhost_virtio_ioctl_array): $(vhost_virtio_hdr_dir)/vhost.h $(vhost_virtio_ioctl_tbl)
-	$(Q)$(SHELL) '$(vhost_virtio_ioctl_tbl)' $(vhost_virtio_hdr_dir) > $@
+$(vhost_virtio_ioctl_array): $(beauty_uapi_linux_dir)/vhost.h $(vhost_virtio_ioctl_tbl)
+	$(Q)$(SHELL) '$(vhost_virtio_ioctl_tbl)' $(beauty_uapi_linux_dir) > $@
 
 perf_ioctl_array := $(beauty_ioctl_outdir)/perf_ioctl_array.c
 perf_hdr_dir := $(srctree)/tools/include/uapi/linux
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 76726a5a7c78..95a3a404bc6f 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -16,7 +16,6 @@ FILES=(
   "include/uapi/linux/in.h"
   "include/uapi/linux/perf_event.h"
   "include/uapi/linux/seccomp.h"
-  "include/uapi/linux/vhost.h"
   "include/linux/bits.h"
   "include/vdso/bits.h"
   "include/linux/const.h"
@@ -96,6 +95,7 @@ BEAUTY_FILES=(
   "include/uapi/linux/sched.h"
   "include/uapi/linux/stat.h"
   "include/uapi/linux/usbdevice_fs.h"
+  "include/uapi/linux/vhost.h"
   "include/uapi/sound/asound.h"
 )
 
diff --git a/tools/perf/trace/beauty/include/uapi/linux/vhost.h b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
new file mode 100644
index 000000000000..649560c685f1
--- /dev/null
+++ b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
@@ -0,0 +1,230 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_VHOST_H
+#define _LINUX_VHOST_H
+/* Userspace interface for in-kernel virtio accelerators. */
+
+/* vhost is used to reduce the number of system calls involved in virtio.
+ *
+ * Existing virtio net code is used in the guest without modification.
+ *
+ * This header includes interface used by userspace hypervisor for
+ * device configuration.
+ */
+
+#include <linux/vhost_types.h>
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define VHOST_FILE_UNBIND -1
+
+/* ioctls */
+
+#define VHOST_VIRTIO 0xAF
+
+/* Features bitmask for forward compatibility.  Transport bits are used for
+ * vhost specific features. */
+#define VHOST_GET_FEATURES	_IOR(VHOST_VIRTIO, 0x00, __u64)
+#define VHOST_SET_FEATURES	_IOW(VHOST_VIRTIO, 0x00, __u64)
+
+/* Set current process as the (exclusive) owner of this file descriptor.  This
+ * must be called before any other vhost command.  Further calls to
+ * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
+/* Give up ownership, and reset the device to default values.
+ * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
+
+/* Set up/modify memory layout */
+#define VHOST_SET_MEM_TABLE	_IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
+
+/* Write logging setup. */
+/* Memory writes can optionally be logged by setting bit at an offset
+ * (calculated from the physical address) from specified log base.
+ * The bit is set using an atomic 32 bit operation. */
+/* Set base address for logging. */
+#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
+/* Specify an eventfd file descriptor to signal on log write. */
+#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+/* By default, a device gets one vhost_worker that its virtqueues share. This
+ * command allows the owner of the device to create an additional vhost_worker
+ * for the device. It can later be bound to 1 or more of its virtqueues using
+ * the VHOST_ATTACH_VRING_WORKER command.
+ *
+ * This must be called after VHOST_SET_OWNER and the caller must be the owner
+ * of the device. The new thread will inherit caller's cgroups and namespaces,
+ * and will share the caller's memory space. The new thread will also be
+ * counted against the caller's RLIMIT_NPROC value.
+ *
+ * The worker's ID used in other commands will be returned in
+ * vhost_worker_state.
+ */
+#define VHOST_NEW_WORKER _IOR(VHOST_VIRTIO, 0x8, struct vhost_worker_state)
+/* Free a worker created with VHOST_NEW_WORKER if it's not attached to any
+ * virtqueue. If userspace is not able to call this for workers its created,
+ * the kernel will free all the device's workers when the device is closed.
+ */
+#define VHOST_FREE_WORKER _IOW(VHOST_VIRTIO, 0x9, struct vhost_worker_state)
+
+/* Ring setup. */
+/* Set number of descriptors in ring. This parameter can not
+ * be modified while ring is running (bound to a device). */
+#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
+/* Set addresses for the ring. */
+#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
+/* Base value where queue looks for available descriptors */
+#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+/* Get accessor: reads index, writes value in num */
+#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+
+/* Set the vring byte order in num. Valid values are VHOST_VRING_LITTLE_ENDIAN
+ * or VHOST_VRING_BIG_ENDIAN (other values return -EINVAL).
+ * The byte order cannot be changed while the device is active: trying to do so
+ * returns -EBUSY.
+ * This is a legacy only API that is simply ignored when VIRTIO_F_VERSION_1 is
+ * set.
+ * Not all kernel configurations support this ioctl, but all configurations that
+ * support SET also support GET.
+ */
+#define VHOST_VRING_LITTLE_ENDIAN 0
+#define VHOST_VRING_BIG_ENDIAN 1
+#define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
+#define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
+/* Attach a vhost_worker created with VHOST_NEW_WORKER to one of the device's
+ * virtqueues.
+ *
+ * This will replace the virtqueue's existing worker. If the replaced worker
+ * is no longer attached to any virtqueues, it can be freed with
+ * VHOST_FREE_WORKER.
+ */
+#define VHOST_ATTACH_VRING_WORKER _IOW(VHOST_VIRTIO, 0x15,		\
+				       struct vhost_vring_worker)
+/* Return the vring worker's ID */
+#define VHOST_GET_VRING_WORKER _IOWR(VHOST_VIRTIO, 0x16,		\
+				     struct vhost_vring_worker)
+
+/* The following ioctls use eventfd file descriptors to signal and poll
+ * for events. */
+
+/* Set eventfd to poll for added buffers */
+#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
+/* Set eventfd to signal when buffers have beed used */
+#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
+/* Set eventfd to signal an error */
+#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
+/* Set busy loop timeout (in us) */
+#define VHOST_SET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x23,	\
+					 struct vhost_vring_state)
+/* Get busy loop timeout (in us) */
+#define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24,	\
+					 struct vhost_vring_state)
+
+/* Set or get vhost backend capability */
+
+#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
+#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
+
+/* VHOST_NET specific defines */
+
+/* Attach virtio net ring to a raw socket, or tap device.
+ * The socket must be already bound to an ethernet device, this device will be
+ * used for transmit.  Pass fd -1 to unbind from the socket and the transmit
+ * device.  This can be used to stop the ring (e.g. for migration). */
+#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
+
+/* VHOST_SCSI specific defines */
+
+#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
+#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
+/* Changing this breaks userspace. */
+#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, int)
+/* Set and get the events missed flag */
+#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32)
+#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32)
+
+/* VHOST_VSOCK specific defines */
+
+#define VHOST_VSOCK_SET_GUEST_CID	_IOW(VHOST_VIRTIO, 0x60, __u64)
+#define VHOST_VSOCK_SET_RUNNING		_IOW(VHOST_VIRTIO, 0x61, int)
+
+/* VHOST_VDPA specific defines */
+
+/* Get the device id. The device ids follow the same definition of
+ * the device id defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_DEVICE_ID	_IOR(VHOST_VIRTIO, 0x70, __u32)
+/* Get and set the status. The status bits follow the same definition
+ * of the device status defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_STATUS		_IOR(VHOST_VIRTIO, 0x71, __u8)
+#define VHOST_VDPA_SET_STATUS		_IOW(VHOST_VIRTIO, 0x72, __u8)
+/* Get and set the device config. The device config follows the same
+ * definition of the device config defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_CONFIG		_IOR(VHOST_VIRTIO, 0x73, \
+					     struct vhost_vdpa_config)
+#define VHOST_VDPA_SET_CONFIG		_IOW(VHOST_VIRTIO, 0x74, \
+					     struct vhost_vdpa_config)
+/* Enable/disable the ring. */
+#define VHOST_VDPA_SET_VRING_ENABLE	_IOW(VHOST_VIRTIO, 0x75, \
+					     struct vhost_vring_state)
+/* Get the max ring size. */
+#define VHOST_VDPA_GET_VRING_NUM	_IOR(VHOST_VIRTIO, 0x76, __u16)
+
+/* Set event fd for config interrupt*/
+#define VHOST_VDPA_SET_CONFIG_CALL	_IOW(VHOST_VIRTIO, 0x77, int)
+
+/* Get the valid iova range */
+#define VHOST_VDPA_GET_IOVA_RANGE	_IOR(VHOST_VIRTIO, 0x78, \
+					     struct vhost_vdpa_iova_range)
+/* Get the config size */
+#define VHOST_VDPA_GET_CONFIG_SIZE	_IOR(VHOST_VIRTIO, 0x79, __u32)
+
+/* Get the count of all virtqueues */
+#define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
+
+/* Get the number of virtqueue groups. */
+#define VHOST_VDPA_GET_GROUP_NUM	_IOR(VHOST_VIRTIO, 0x81, __u32)
+
+/* Get the number of address spaces. */
+#define VHOST_VDPA_GET_AS_NUM		_IOR(VHOST_VIRTIO, 0x7A, unsigned int)
+
+/* Get the group for a virtqueue: read index, write group in num,
+ * The virtqueue index is stored in the index field of
+ * vhost_vring_state. The group for this specific virtqueue is
+ * returned via num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_GET_VRING_GROUP	_IOWR(VHOST_VIRTIO, 0x7B,	\
+					      struct vhost_vring_state)
+/* Set the ASID for a virtqueue group. The group index is stored in
+ * the index field of vhost_vring_state, the ASID associated with this
+ * group is stored at num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_SET_GROUP_ASID	_IOW(VHOST_VIRTIO, 0x7C, \
+					     struct vhost_vring_state)
+
+/* Suspend a device so it does not process virtqueue requests anymore
+ *
+ * After the return of ioctl the device must preserve all the necessary state
+ * (the virtqueue vring base plus the possible device specific states) that is
+ * required for restoring in the future. The device must not change its
+ * configuration after that point.
+ */
+#define VHOST_VDPA_SUSPEND		_IO(VHOST_VIRTIO, 0x7D)
+
+/* Resume a device so it can resume processing virtqueue requests
+ *
+ * After the return of this ioctl the device will have restored all the
+ * necessary states and it is fully operational to continue processing the
+ * virtqueue descriptors.
+ */
+#define VHOST_VDPA_RESUME		_IO(VHOST_VIRTIO, 0x7E)
+
+/* Get the group for the descriptor table including driver & device areas
+ * of a virtqueue: read index, write group in num.
+ * The virtqueue index is stored in the index field of vhost_vring_state.
+ * The group ID of the descriptor table for this specific virtqueue
+ * is returned via num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_GET_VRING_DESC_GROUP	_IOWR(VHOST_VIRTIO, 0x7F,	\
+					      struct vhost_vring_state)
+#endif
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 2dd0a3b1f55a..e4f395e7650a 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,18 +1,18 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && beauty_uapi_linux_dir=$1 || beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux
 
 printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-grep -E $regex ${header_dir}/vhost.h | \
+grep -E $regex ${beauty_uapi_linux_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-grep -E $regex ${header_dir}/vhost.h | \
+grep -E $regex ${beauty_uapi_linux_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
-- 
cgit 


From 476a5e929119725fbfcf1307cc8517d9dd2a014d Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Sun, 24 Mar 2024 20:38:42 -0700
Subject: bpf: Sync uapi bpf.h to tools directory

There is a difference between kernel uapi bpf.h and tools
uapi bpf.h. There is no functionality difference, but let
us sync properly to make it easy for later bpf.h update.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240325033842.1693553-1-yonghong.song@linux.dev
---
 tools/include/uapi/linux/bpf.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bf80b614c4db..9585f5345353 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1662,9 +1662,10 @@ union bpf_attr {
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
-		__u64 name;
-		__u32 prog_fd;
-		__aligned_u64 cookie;
+		__u64		name;
+		__u32		prog_fd;
+		__u32		:32;
+		__aligned_u64	cookie;
 	} raw_tracepoint;
 
 	struct { /* anonymous struct for BPF_BTF_LOAD */
-- 
cgit 


From 5311591fbb349fe9f5c555dcba3b13a5831aa72d Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Tue, 26 Mar 2024 10:17:40 +0000
Subject: bpf: Add support for passing mark with bpf_fib_lookup

Extend the bpf_fib_lookup() helper by making it to utilize mark if
the BPF_FIB_LOOKUP_MARK flag is set. In order to pass the mark the
four bytes of struct bpf_fib_lookup are used, shared with the
output-only smac/dmac fields.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: David Ahern <dsahern@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240326101742.17421-2-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       | 20 ++++++++++++++++++--
 net/core/filter.c              | 12 +++++++++---
 tools/include/uapi/linux/bpf.h | 20 ++++++++++++++++++--
 3 files changed, 45 insertions(+), 7 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9585f5345353..96d57e483133 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3394,6 +3394,10 @@ union bpf_attr {
  *			for the nexthop. If the src addr cannot be derived,
  *			**BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
  *			case, *params*->dmac and *params*->smac are not set either.
+ *		**BPF_FIB_LOOKUP_MARK**
+ *			Use the mark present in *params*->mark for the fib lookup.
+ *			This option should not be used with BPF_FIB_LOOKUP_DIRECT,
+ *			as it only has meaning for full lookups.
  *
  *		*ctx* is either **struct xdp_md** for XDP programs or
  *		**struct sk_buff** tc cls_act programs.
@@ -7120,6 +7124,7 @@ enum {
 	BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
 	BPF_FIB_LOOKUP_TBID    = (1U << 3),
 	BPF_FIB_LOOKUP_SRC     = (1U << 4),
+	BPF_FIB_LOOKUP_MARK    = (1U << 5),
 };
 
 enum {
@@ -7197,8 +7202,19 @@ struct bpf_fib_lookup {
 		__u32	tbid;
 	};
 
-	__u8	smac[6];     /* ETH_ALEN */
-	__u8	dmac[6];     /* ETH_ALEN */
+	union {
+		/* input */
+		struct {
+			__u32	mark;   /* policy routing */
+			/* 2 4-byte holes for input */
+		};
+
+		/* output: source and dest mac */
+		struct {
+			__u8	smac[6];	/* ETH_ALEN */
+			__u8	dmac[6];	/* ETH_ALEN */
+		};
+	};
 };
 
 struct bpf_redir_neigh {
diff --git a/net/core/filter.c b/net/core/filter.c
index 0c66e4a3fc5b..1205dd777dc2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5884,7 +5884,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 		err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
 	} else {
-		fl4.flowi4_mark = 0;
+		if (flags & BPF_FIB_LOOKUP_MARK)
+			fl4.flowi4_mark = params->mark;
+		else
+			fl4.flowi4_mark = 0;
 		fl4.flowi4_secid = 0;
 		fl4.flowi4_tun_key.tun_id = 0;
 		fl4.flowi4_uid = sock_net_uid(net, NULL);
@@ -6027,7 +6030,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res,
 						   strict);
 	} else {
-		fl6.flowi6_mark = 0;
+		if (flags & BPF_FIB_LOOKUP_MARK)
+			fl6.flowi6_mark = params->mark;
+		else
+			fl6.flowi6_mark = 0;
 		fl6.flowi6_secid = 0;
 		fl6.flowi6_tun_key.tun_id = 0;
 		fl6.flowi6_uid = sock_net_uid(net, NULL);
@@ -6105,7 +6111,7 @@ set_fwd_params:
 
 #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \
 			     BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \
-			     BPF_FIB_LOOKUP_SRC)
+			     BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_MARK)
 
 BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx,
 	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9585f5345353..96d57e483133 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3394,6 +3394,10 @@ union bpf_attr {
  *			for the nexthop. If the src addr cannot be derived,
  *			**BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this
  *			case, *params*->dmac and *params*->smac are not set either.
+ *		**BPF_FIB_LOOKUP_MARK**
+ *			Use the mark present in *params*->mark for the fib lookup.
+ *			This option should not be used with BPF_FIB_LOOKUP_DIRECT,
+ *			as it only has meaning for full lookups.
  *
  *		*ctx* is either **struct xdp_md** for XDP programs or
  *		**struct sk_buff** tc cls_act programs.
@@ -7120,6 +7124,7 @@ enum {
 	BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
 	BPF_FIB_LOOKUP_TBID    = (1U << 3),
 	BPF_FIB_LOOKUP_SRC     = (1U << 4),
+	BPF_FIB_LOOKUP_MARK    = (1U << 5),
 };
 
 enum {
@@ -7197,8 +7202,19 @@ struct bpf_fib_lookup {
 		__u32	tbid;
 	};
 
-	__u8	smac[6];     /* ETH_ALEN */
-	__u8	dmac[6];     /* ETH_ALEN */
+	union {
+		/* input */
+		struct {
+			__u32	mark;   /* policy routing */
+			/* 2 4-byte holes for input */
+		};
+
+		/* output: source and dest mac */
+		struct {
+			__u8	smac[6];	/* ETH_ALEN */
+			__u8	dmac[6];	/* ETH_ALEN */
+		};
+	};
 };
 
 struct bpf_redir_neigh {
-- 
cgit 


From ca4ddc26f8acaa9cb451fcb20f7ab0f02e4970cb Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Fri, 29 Mar 2024 10:28:46 -0500
Subject: bpf: Fix typo in uapi doc comments

In a few places in the bpf uapi headers, EOPNOTSUPP is missing a "P" in
the doc comments. This adds the missing "P".

Signed-off-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240329152900.398260-2-dlechner@baylibre.com
---
 include/uapi/linux/bpf.h       | 4 ++--
 tools/include/uapi/linux/bpf.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 96d57e483133..79c548276b6b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5026,7 +5026,7 @@ union bpf_attr {
  *		bytes will be copied to *dst*
  *	Return
  *		The **hash_algo** is returned on success,
- *		**-EOPNOTSUP** if IMA is disabled or **-EINVAL** if
+ *		**-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if
  *		invalid arguments are passed.
  *
  * struct socket *bpf_sock_from_file(struct file *file)
@@ -5512,7 +5512,7 @@ union bpf_attr {
  *		bytes will be copied to *dst*
  *	Return
  *		The **hash_algo** is returned on success,
- *		**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
+ *		**-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if
  *		invalid arguments are passed.
  *
  * void *bpf_kptr_xchg(void *map_value, void *ptr)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 96d57e483133..79c548276b6b 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5026,7 +5026,7 @@ union bpf_attr {
  *		bytes will be copied to *dst*
  *	Return
  *		The **hash_algo** is returned on success,
- *		**-EOPNOTSUP** if IMA is disabled or **-EINVAL** if
+ *		**-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if
  *		invalid arguments are passed.
  *
  * struct socket *bpf_sock_from_file(struct file *file)
@@ -5512,7 +5512,7 @@ union bpf_attr {
  *		bytes will be copied to *dst*
  *	Return
  *		The **hash_algo** is returned on success,
- *		**-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
+ *		**-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if
  *		invalid arguments are passed.
  *
  * void *bpf_kptr_xchg(void *map_value, void *ptr)
-- 
cgit 


From 7effe3fdc049a34c56a68671100b5570e53e8f0a Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Tue, 2 Apr 2024 11:45:23 +0000
Subject: tools: Add ethtool.h header to tooling infra

This commit duplicates the ethtool.h file from the include/uapi/linux
directory in the kernel source to the tools/include/uapi/linux directory.

This action ensures that the ethtool.h file used in the tools directory
is in sync with the kernel's version, maintaining consistency across the
codebase.

There are some checkpatch warnings in this file that could be cleaned up,
but I preferred to move it over as-is for now to avoid disrupting the code.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20240402114529.545475-2-tushar.vyavahare@intel.com
---
 tools/include/uapi/linux/ethtool.h | 2229 +++++++++++++++++++++++++++++++++++-
 1 file changed, 2198 insertions(+), 31 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/ethtool.h b/tools/include/uapi/linux/ethtool.h
index 47afae3895ec..11fc18988bc2 100644
--- a/tools/include/uapi/linux/ethtool.h
+++ b/tools/include/uapi/linux/ethtool.h
@@ -14,40 +14,140 @@
 #ifndef _UAPI_LINUX_ETHTOOL_H
 #define _UAPI_LINUX_ETHTOOL_H
 
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/types.h>
 #include <linux/if_ether.h>
 
-#define ETHTOOL_GCHANNELS       0x0000003c /* Get no of channels */
+#ifndef __KERNEL__
+#include <limits.h> /* for INT_MAX */
+#endif
+
+/* All structures exposed to userland should be defined such that they
+ * have the same layout for 32-bit and 64-bit userland.
+ */
+
+/* Note on reserved space.
+ * Reserved fields must not be accessed directly by user space because
+ * they may be replaced by a different field in the future. They must
+ * be initialized to zero before making the request, e.g. via memset
+ * of the entire structure or implicitly by not being set in a structure
+ * initializer.
+ */
 
 /**
- * struct ethtool_channels - configuring number of network channel
- * @cmd: ETHTOOL_{G,S}CHANNELS
- * @max_rx: Read only. Maximum number of receive channel the driver support.
- * @max_tx: Read only. Maximum number of transmit channel the driver support.
- * @max_other: Read only. Maximum number of other channel the driver support.
- * @max_combined: Read only. Maximum number of combined channel the driver
- *	support. Set of queues RX, TX or other.
- * @rx_count: Valid values are in the range 1 to the max_rx.
- * @tx_count: Valid values are in the range 1 to the max_tx.
- * @other_count: Valid values are in the range 1 to the max_other.
- * @combined_count: Valid values are in the range 1 to the max_combined.
+ * struct ethtool_cmd - DEPRECATED, link control and status
+ * This structure is DEPRECATED, please use struct ethtool_link_settings.
+ * @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET
+ * @supported: Bitmask of %SUPPORTED_* flags for the link modes,
+ *	physical connectors and other link features for which the
+ *	interface supports autonegotiation or auto-detection.
+ *	Read-only.
+ * @advertising: Bitmask of %ADVERTISED_* flags for the link modes,
+ *	physical connectors and other link features that are
+ *	advertised through autonegotiation or enabled for
+ *	auto-detection.
+ * @speed: Low bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN
+ * @duplex: Duplex mode; one of %DUPLEX_*
+ * @port: Physical connector type; one of %PORT_*
+ * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not
+ *	applicable.  For clause 45 PHYs this is the PRTAD.
+ * @transceiver: Historically used to distinguish different possible
+ *	PHY types, but not in a consistent way.  Deprecated.
+ * @autoneg: Enable/disable autonegotiation and auto-detection;
+ *	either %AUTONEG_DISABLE or %AUTONEG_ENABLE
+ * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO
+ *	protocols supported by the interface; 0 if unknown.
+ *	Read-only.
+ * @maxtxpkt: Historically used to report TX IRQ coalescing; now
+ *	obsoleted by &struct ethtool_coalesce.  Read-only; deprecated.
+ * @maxrxpkt: Historically used to report RX IRQ coalescing; now
+ *	obsoleted by &struct ethtool_coalesce.  Read-only; deprecated.
+ * @speed_hi: High bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN
+ * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of
+ *	%ETH_TP_MDI_*.  If the status is unknown or not applicable, the
+ *	value will be %ETH_TP_MDI_INVALID.  Read-only.
+ * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of
+ *	%ETH_TP_MDI_*.  If MDI(-X) control is not implemented, reads
+ *	yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected.
+ *	When written successfully, the link should be renegotiated if
+ *	necessary.
+ * @lp_advertising: Bitmask of %ADVERTISED_* flags for the link modes
+ *	and other link features that the link partner advertised
+ *	through autonegotiation; 0 if unknown or not applicable.
+ *	Read-only.
+ * @reserved: Reserved for future use; see the note on reserved space.
  *
- * This can be used to configure RX, TX and other channels.
+ * The link speed in Mbps is split between @speed and @speed_hi.  Use
+ * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to
+ * access it.
+ *
+ * If autonegotiation is disabled, the speed and @duplex represent the
+ * fixed link mode and are writable if the driver supports multiple
+ * link modes.  If it is enabled then they are read-only; if the link
+ * is up they represent the negotiated link mode; if the link is down,
+ * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and
+ * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode.
+ *
+ * Some hardware interfaces may have multiple PHYs and/or physical
+ * connectors fitted or do not allow the driver to detect which are
+ * fitted.  For these interfaces @port and/or @phy_address may be
+ * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE.
+ * Otherwise, attempts to write different values may be ignored or
+ * rejected.
+ *
+ * Users should assume that all fields not marked read-only are
+ * writable and subject to validation by the driver.  They should use
+ * %ETHTOOL_GSET to get the current values before making specific
+ * changes and then applying them with %ETHTOOL_SSET.
+ *
+ * Deprecated fields should be ignored by both users and drivers.
  */
-
-struct ethtool_channels {
+struct ethtool_cmd {
 	__u32	cmd;
-	__u32	max_rx;
-	__u32	max_tx;
-	__u32	max_other;
-	__u32	max_combined;
-	__u32	rx_count;
-	__u32	tx_count;
-	__u32	other_count;
-	__u32	combined_count;
+	__u32	supported;
+	__u32	advertising;
+	__u16	speed;
+	__u8	duplex;
+	__u8	port;
+	__u8	phy_address;
+	__u8	transceiver;
+	__u8	autoneg;
+	__u8	mdio_support;
+	__u32	maxtxpkt;
+	__u32	maxrxpkt;
+	__u16	speed_hi;
+	__u8	eth_tp_mdix;
+	__u8	eth_tp_mdix_ctrl;
+	__u32	lp_advertising;
+	__u32	reserved[2];
 };
 
+static inline void ethtool_cmd_speed_set(struct ethtool_cmd *ep,
+					 __u32 speed)
+{
+	ep->speed = (__u16)(speed & 0xFFFF);
+	ep->speed_hi = (__u16)(speed >> 16);
+}
+
+static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep)
+{
+	return (ep->speed_hi << 16) | ep->speed;
+}
+
+/* Device supports clause 22 register access to PHY or peripherals
+ * using the interface defined in <linux/mii.h>.  This should not be
+ * set if there are known to be no such peripherals present or if
+ * the driver only emulates clause 22 registers for compatibility.
+ */
+#define ETH_MDIO_SUPPORTS_C22	1
+
+/* Device supports clause 45 register access to PHY or peripherals
+ * using the interface defined in <linux/mii.h> and <linux/mdio.h>.
+ * This should not be set if there are known to be no such peripherals
+ * present.
+ */
+#define ETH_MDIO_SUPPORTS_C45	2
+
 #define ETHTOOL_FWVERS_LEN	32
 #define ETHTOOL_BUSINFO_LEN	32
 #define ETHTOOL_EROMVERS_LEN	32
@@ -59,8 +159,10 @@ struct ethtool_channels {
  *	in its bus driver structure (e.g. pci_driver::name).  Must
  *	not be an empty string.
  * @version: Driver version string; may be an empty string
- * @fw_version: Firmware version string; may be an empty string
- * @erom_version: Expansion ROM version string; may be an empty string
+ * @fw_version: Firmware version string; driver defined; may be an
+ *	empty string
+ * @erom_version: Expansion ROM version string; driver defined; may be
+ *	an empty string
  * @bus_info: Device bus address.  This should match the dev_name()
  *	string for the underlying bus device, if there is one.  May be
  *	an empty string.
@@ -79,10 +181,6 @@ struct ethtool_channels {
  *
  * Users can use the %ETHTOOL_GSSET_INFO command to get the number of
  * strings in any string set (from Linux 2.6.34).
- *
- * Drivers should set at most @driver, @version, @fw_version and
- * @bus_info in their get_drvinfo() implementation.  The ethtool
- * core fills in the other fields using other driver operations.
  */
 struct ethtool_drvinfo {
 	__u32	cmd;
@@ -99,6 +197,2075 @@ struct ethtool_drvinfo {
 	__u32	regdump_len;
 };
 
-#define ETHTOOL_GDRVINFO	0x00000003
+#define SOPASS_MAX	6
+
+/**
+ * struct ethtool_wolinfo - Wake-On-Lan configuration
+ * @cmd: Command number = %ETHTOOL_GWOL or %ETHTOOL_SWOL
+ * @supported: Bitmask of %WAKE_* flags for supported Wake-On-Lan modes.
+ *	Read-only.
+ * @wolopts: Bitmask of %WAKE_* flags for enabled Wake-On-Lan modes.
+ * @sopass: SecureOn(tm) password; meaningful only if %WAKE_MAGICSECURE
+ *	is set in @wolopts.
+ */
+struct ethtool_wolinfo {
+	__u32	cmd;
+	__u32	supported;
+	__u32	wolopts;
+	__u8	sopass[SOPASS_MAX];
+};
+
+/* for passing single values */
+struct ethtool_value {
+	__u32	cmd;
+	__u32	data;
+};
+
+#define PFC_STORM_PREVENTION_AUTO	0xffff
+#define PFC_STORM_PREVENTION_DISABLE	0
+
+enum tunable_id {
+	ETHTOOL_ID_UNSPEC,
+	ETHTOOL_RX_COPYBREAK,
+	ETHTOOL_TX_COPYBREAK,
+	ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */
+	ETHTOOL_TX_COPYBREAK_BUF_SIZE,
+	/*
+	 * Add your fresh new tunable attribute above and remember to update
+	 * tunable_strings[] in net/ethtool/common.c
+	 */
+	__ETHTOOL_TUNABLE_COUNT,
+};
+
+enum tunable_type_id {
+	ETHTOOL_TUNABLE_UNSPEC,
+	ETHTOOL_TUNABLE_U8,
+	ETHTOOL_TUNABLE_U16,
+	ETHTOOL_TUNABLE_U32,
+	ETHTOOL_TUNABLE_U64,
+	ETHTOOL_TUNABLE_STRING,
+	ETHTOOL_TUNABLE_S8,
+	ETHTOOL_TUNABLE_S16,
+	ETHTOOL_TUNABLE_S32,
+	ETHTOOL_TUNABLE_S64,
+};
+
+struct ethtool_tunable {
+	__u32	cmd;
+	__u32	id;
+	__u32	type_id;
+	__u32	len;
+	void	*data[];
+};
+
+#define DOWNSHIFT_DEV_DEFAULT_COUNT	0xff
+#define DOWNSHIFT_DEV_DISABLE		0
+
+/* Time in msecs after which link is reported as down
+ * 0 = lowest time supported by the PHY
+ * 0xff = off, link down detection according to standard
+ */
+#define ETHTOOL_PHY_FAST_LINK_DOWN_ON	0
+#define ETHTOOL_PHY_FAST_LINK_DOWN_OFF	0xff
+
+/* Energy Detect Power Down (EDPD) is a feature supported by some PHYs, where
+ * the PHY's RX & TX blocks are put into a low-power mode when there is no
+ * link detected (typically cable is un-plugged). For RX, only a minimal
+ * link-detection is available, and for TX the PHY wakes up to send link pulses
+ * to avoid any lock-ups in case the peer PHY may also be running in EDPD mode.
+ *
+ * Some PHYs may support configuration of the wake-up interval for TX pulses,
+ * and some PHYs may support only disabling TX pulses entirely. For the latter
+ * a special value is required (ETHTOOL_PHY_EDPD_NO_TX) so that this can be
+ * configured from userspace (should the user want it).
+ *
+ * The interval units for TX wake-up are in milliseconds, since this should
+ * cover a reasonable range of intervals:
+ *  - from 1 millisecond, which does not sound like much of a power-saver
+ *  - to ~65 seconds which is quite a lot to wait for a link to come up when
+ *    plugging a cable
+ */
+#define ETHTOOL_PHY_EDPD_DFLT_TX_MSECS		0xffff
+#define ETHTOOL_PHY_EDPD_NO_TX			0xfffe
+#define ETHTOOL_PHY_EDPD_DISABLE		0
+
+enum phy_tunable_id {
+	ETHTOOL_PHY_ID_UNSPEC,
+	ETHTOOL_PHY_DOWNSHIFT,
+	ETHTOOL_PHY_FAST_LINK_DOWN,
+	ETHTOOL_PHY_EDPD,
+	/*
+	 * Add your fresh new phy tunable attribute above and remember to update
+	 * phy_tunable_strings[] in net/ethtool/common.c
+	 */
+	__ETHTOOL_PHY_TUNABLE_COUNT,
+};
+
+/**
+ * struct ethtool_regs - hardware register dump
+ * @cmd: Command number = %ETHTOOL_GREGS
+ * @version: Dump format version.  This is driver-specific and may
+ *	distinguish different chips/revisions.  Drivers must use new
+ *	version numbers whenever the dump format changes in an
+ *	incompatible way.
+ * @len: On entry, the real length of @data.  On return, the number of
+ *	bytes used.
+ * @data: Buffer for the register dump
+ *
+ * Users should use %ETHTOOL_GDRVINFO to find the maximum length of
+ * a register dump for the interface.  They must allocate the buffer
+ * immediately following this structure.
+ */
+struct ethtool_regs {
+	__u32	cmd;
+	__u32	version;
+	__u32	len;
+	__u8	data[];
+};
+
+/**
+ * struct ethtool_eeprom - EEPROM dump
+ * @cmd: Command number = %ETHTOOL_GEEPROM, %ETHTOOL_GMODULEEEPROM or
+ *	%ETHTOOL_SEEPROM
+ * @magic: A 'magic cookie' value to guard against accidental changes.
+ *	The value passed in to %ETHTOOL_SEEPROM must match the value
+ *	returned by %ETHTOOL_GEEPROM for the same device.  This is
+ *	unused when @cmd is %ETHTOOL_GMODULEEEPROM.
+ * @offset: Offset within the EEPROM to begin reading/writing, in bytes
+ * @len: On entry, number of bytes to read/write.  On successful
+ *	return, number of bytes actually read/written.  In case of
+ *	error, this may indicate at what point the error occurred.
+ * @data: Buffer to read/write from
+ *
+ * Users may use %ETHTOOL_GDRVINFO or %ETHTOOL_GMODULEINFO to find
+ * the length of an on-board or module EEPROM, respectively.  They
+ * must allocate the buffer immediately following this structure.
+ */
+struct ethtool_eeprom {
+	__u32	cmd;
+	__u32	magic;
+	__u32	offset;
+	__u32	len;
+	__u8	data[];
+};
+
+/**
+ * struct ethtool_eee - Energy Efficient Ethernet information
+ * @cmd: ETHTOOL_{G,S}EEE
+ * @supported: Mask of %SUPPORTED_* flags for the speed/duplex combinations
+ *	for which there is EEE support.
+ * @advertised: Mask of %ADVERTISED_* flags for the speed/duplex combinations
+ *	advertised as eee capable.
+ * @lp_advertised: Mask of %ADVERTISED_* flags for the speed/duplex
+ *	combinations advertised by the link partner as eee capable.
+ * @eee_active: Result of the eee auto negotiation.
+ * @eee_enabled: EEE configured mode (enabled/disabled).
+ * @tx_lpi_enabled: Whether the interface should assert its tx lpi, given
+ *	that eee was negotiated.
+ * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting
+ *	its tx lpi (after reaching 'idle' state). Effective only when eee
+ *	was negotiated and tx_lpi_enabled was set.
+ * @reserved: Reserved for future use; see the note on reserved space.
+ */
+struct ethtool_eee {
+	__u32	cmd;
+	__u32	supported;
+	__u32	advertised;
+	__u32	lp_advertised;
+	__u32	eee_active;
+	__u32	eee_enabled;
+	__u32	tx_lpi_enabled;
+	__u32	tx_lpi_timer;
+	__u32	reserved[2];
+};
+
+/**
+ * struct ethtool_modinfo - plugin module eeprom information
+ * @cmd: %ETHTOOL_GMODULEINFO
+ * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx
+ * @eeprom_len: Length of the eeprom
+ * @reserved: Reserved for future use; see the note on reserved space.
+ *
+ * This structure is used to return the information to
+ * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM.
+ * The type code indicates the eeprom data format
+ */
+struct ethtool_modinfo {
+	__u32   cmd;
+	__u32   type;
+	__u32   eeprom_len;
+	__u32   reserved[8];
+};
+
+/**
+ * struct ethtool_coalesce - coalescing parameters for IRQs and stats updates
+ * @cmd: ETHTOOL_{G,S}COALESCE
+ * @rx_coalesce_usecs: How many usecs to delay an RX interrupt after
+ *	a packet arrives.
+ * @rx_max_coalesced_frames: Maximum number of packets to receive
+ *	before an RX interrupt.
+ * @rx_coalesce_usecs_irq: Same as @rx_coalesce_usecs, except that
+ *	this value applies while an IRQ is being serviced by the host.
+ * @rx_max_coalesced_frames_irq: Same as @rx_max_coalesced_frames,
+ *	except that this value applies while an IRQ is being serviced
+ *	by the host.
+ * @tx_coalesce_usecs: How many usecs to delay a TX interrupt after
+ *	a packet is sent.
+ * @tx_max_coalesced_frames: Maximum number of packets to be sent
+ *	before a TX interrupt.
+ * @tx_coalesce_usecs_irq: Same as @tx_coalesce_usecs, except that
+ *	this value applies while an IRQ is being serviced by the host.
+ * @tx_max_coalesced_frames_irq: Same as @tx_max_coalesced_frames,
+ *	except that this value applies while an IRQ is being serviced
+ *	by the host.
+ * @stats_block_coalesce_usecs: How many usecs to delay in-memory
+ *	statistics block updates.  Some drivers do not have an
+ *	in-memory statistic block, and in such cases this value is
+ *	ignored.  This value must not be zero.
+ * @use_adaptive_rx_coalesce: Enable adaptive RX coalescing.
+ * @use_adaptive_tx_coalesce: Enable adaptive TX coalescing.
+ * @pkt_rate_low: Threshold for low packet rate (packets per second).
+ * @rx_coalesce_usecs_low: How many usecs to delay an RX interrupt after
+ *	a packet arrives, when the packet rate is below @pkt_rate_low.
+ * @rx_max_coalesced_frames_low: Maximum number of packets to be received
+ *	before an RX interrupt, when the packet rate is below @pkt_rate_low.
+ * @tx_coalesce_usecs_low: How many usecs to delay a TX interrupt after
+ *	a packet is sent, when the packet rate is below @pkt_rate_low.
+ * @tx_max_coalesced_frames_low: Maximum nuumber of packets to be sent before
+ *	a TX interrupt, when the packet rate is below @pkt_rate_low.
+ * @pkt_rate_high: Threshold for high packet rate (packets per second).
+ * @rx_coalesce_usecs_high: How many usecs to delay an RX interrupt after
+ *	a packet arrives, when the packet rate is above @pkt_rate_high.
+ * @rx_max_coalesced_frames_high: Maximum number of packets to be received
+ *	before an RX interrupt, when the packet rate is above @pkt_rate_high.
+ * @tx_coalesce_usecs_high: How many usecs to delay a TX interrupt after
+ *	a packet is sent, when the packet rate is above @pkt_rate_high.
+ * @tx_max_coalesced_frames_high: Maximum number of packets to be sent before
+ *	a TX interrupt, when the packet rate is above @pkt_rate_high.
+ * @rate_sample_interval: How often to do adaptive coalescing packet rate
+ *	sampling, measured in seconds.  Must not be zero.
+ *
+ * Each pair of (usecs, max_frames) fields specifies that interrupts
+ * should be coalesced until
+ *	(usecs > 0 && time_since_first_completion >= usecs) ||
+ *	(max_frames > 0 && completed_frames >= max_frames)
+ *
+ * It is illegal to set both usecs and max_frames to zero as this
+ * would cause interrupts to never be generated.  To disable
+ * coalescing, set usecs = 0 and max_frames = 1.
+ *
+ * Some implementations ignore the value of max_frames and use the
+ * condition time_since_first_completion >= usecs
+ *
+ * This is deprecated.  Drivers for hardware that does not support
+ * counting completions should validate that max_frames == !rx_usecs.
+ *
+ * Adaptive RX/TX coalescing is an algorithm implemented by some
+ * drivers to improve latency under low packet rates and improve
+ * throughput under high packet rates.  Some drivers only implement
+ * one of RX or TX adaptive coalescing.  Anything not implemented by
+ * the driver causes these values to be silently ignored.
+ *
+ * When the packet rate is below @pkt_rate_high but above
+ * @pkt_rate_low (both measured in packets per second) the
+ * normal {rx,tx}_* coalescing parameters are used.
+ */
+struct ethtool_coalesce {
+	__u32	cmd;
+	__u32	rx_coalesce_usecs;
+	__u32	rx_max_coalesced_frames;
+	__u32	rx_coalesce_usecs_irq;
+	__u32	rx_max_coalesced_frames_irq;
+	__u32	tx_coalesce_usecs;
+	__u32	tx_max_coalesced_frames;
+	__u32	tx_coalesce_usecs_irq;
+	__u32	tx_max_coalesced_frames_irq;
+	__u32	stats_block_coalesce_usecs;
+	__u32	use_adaptive_rx_coalesce;
+	__u32	use_adaptive_tx_coalesce;
+	__u32	pkt_rate_low;
+	__u32	rx_coalesce_usecs_low;
+	__u32	rx_max_coalesced_frames_low;
+	__u32	tx_coalesce_usecs_low;
+	__u32	tx_max_coalesced_frames_low;
+	__u32	pkt_rate_high;
+	__u32	rx_coalesce_usecs_high;
+	__u32	rx_max_coalesced_frames_high;
+	__u32	tx_coalesce_usecs_high;
+	__u32	tx_max_coalesced_frames_high;
+	__u32	rate_sample_interval;
+};
+
+/**
+ * struct ethtool_ringparam - RX/TX ring parameters
+ * @cmd: Command number = %ETHTOOL_GRINGPARAM or %ETHTOOL_SRINGPARAM
+ * @rx_max_pending: Maximum supported number of pending entries per
+ *	RX ring.  Read-only.
+ * @rx_mini_max_pending: Maximum supported number of pending entries
+ *	per RX mini ring.  Read-only.
+ * @rx_jumbo_max_pending: Maximum supported number of pending entries
+ *	per RX jumbo ring.  Read-only.
+ * @tx_max_pending: Maximum supported number of pending entries per
+ *	TX ring.  Read-only.
+ * @rx_pending: Current maximum number of pending entries per RX ring
+ * @rx_mini_pending: Current maximum number of pending entries per RX
+ *	mini ring
+ * @rx_jumbo_pending: Current maximum number of pending entries per RX
+ *	jumbo ring
+ * @tx_pending: Current maximum supported number of pending entries
+ *	per TX ring
+ *
+ * If the interface does not have separate RX mini and/or jumbo rings,
+ * @rx_mini_max_pending and/or @rx_jumbo_max_pending will be 0.
+ *
+ * There may also be driver-dependent minimum values for the number
+ * of entries per ring.
+ */
+struct ethtool_ringparam {
+	__u32	cmd;
+	__u32	rx_max_pending;
+	__u32	rx_mini_max_pending;
+	__u32	rx_jumbo_max_pending;
+	__u32	tx_max_pending;
+	__u32	rx_pending;
+	__u32	rx_mini_pending;
+	__u32	rx_jumbo_pending;
+	__u32	tx_pending;
+};
+
+/**
+ * struct ethtool_channels - configuring number of network channel
+ * @cmd: ETHTOOL_{G,S}CHANNELS
+ * @max_rx: Read only. Maximum number of receive channel the driver support.
+ * @max_tx: Read only. Maximum number of transmit channel the driver support.
+ * @max_other: Read only. Maximum number of other channel the driver support.
+ * @max_combined: Read only. Maximum number of combined channel the driver
+ *	support. Set of queues RX, TX or other.
+ * @rx_count: Valid values are in the range 1 to the max_rx.
+ * @tx_count: Valid values are in the range 1 to the max_tx.
+ * @other_count: Valid values are in the range 1 to the max_other.
+ * @combined_count: Valid values are in the range 1 to the max_combined.
+ *
+ * This can be used to configure RX, TX and other channels.
+ */
+
+struct ethtool_channels {
+	__u32	cmd;
+	__u32	max_rx;
+	__u32	max_tx;
+	__u32	max_other;
+	__u32	max_combined;
+	__u32	rx_count;
+	__u32	tx_count;
+	__u32	other_count;
+	__u32	combined_count;
+};
+
+/**
+ * struct ethtool_pauseparam - Ethernet pause (flow control) parameters
+ * @cmd: Command number = %ETHTOOL_GPAUSEPARAM or %ETHTOOL_SPAUSEPARAM
+ * @autoneg: Flag to enable autonegotiation of pause frame use
+ * @rx_pause: Flag to enable reception of pause frames
+ * @tx_pause: Flag to enable transmission of pause frames
+ *
+ * Drivers should reject a non-zero setting of @autoneg when
+ * autoneogotiation is disabled (or not supported) for the link.
+ *
+ * If the link is autonegotiated, drivers should use
+ * mii_advertise_flowctrl() or similar code to set the advertised
+ * pause frame capabilities based on the @rx_pause and @tx_pause flags,
+ * even if @autoneg is zero.  They should also allow the advertised
+ * pause frame capabilities to be controlled directly through the
+ * advertising field of &struct ethtool_cmd.
+ *
+ * If @autoneg is non-zero, the MAC is configured to send and/or
+ * receive pause frames according to the result of autonegotiation.
+ * Otherwise, it is configured directly based on the @rx_pause and
+ * @tx_pause flags.
+ */
+struct ethtool_pauseparam {
+	__u32	cmd;
+	__u32	autoneg;
+	__u32	rx_pause;
+	__u32	tx_pause;
+};
+
+/* Link extended state */
+enum ethtool_link_ext_state {
+	ETHTOOL_LINK_EXT_STATE_AUTONEG,
+	ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
+	ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH,
+	ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY,
+	ETHTOOL_LINK_EXT_STATE_NO_CABLE,
+	ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE,
+	ETHTOOL_LINK_EXT_STATE_EEPROM_ISSUE,
+	ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE,
+	ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED,
+	ETHTOOL_LINK_EXT_STATE_OVERHEAT,
+	ETHTOOL_LINK_EXT_STATE_MODULE,
+};
+
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */
+enum ethtool_link_ext_substate_autoneg {
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_NEXT_PAGE_EXCHANGE_FAILED,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED_FORCE_MODE,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_FEC_MISMATCH_DURING_OVERRIDE,
+	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD,
+};
+
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
+ */
+enum ethtool_link_ext_substate_link_training {
+	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_INHIBIT_TIMEOUT,
+	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_PARTNER_DID_NOT_SET_RECEIVER_READY,
+	ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT,
+};
+
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
+ */
+enum ethtool_link_ext_substate_link_logical_mismatch {
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_AM_LOCK,
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_GET_ALIGN_STATUS,
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_FC_FEC_IS_NOT_LOCKED,
+	ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED,
+};
+
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
+ */
+enum ethtool_link_ext_substate_bad_signal_integrity {
+	ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE,
+	ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_REFERENCE_CLOCK_LOST,
+	ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_ALOS,
+};
+
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */
+enum ethtool_link_ext_substate_cable_issue {
+	ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1,
+	ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE,
+};
+
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_MODULE. */
+enum ethtool_link_ext_substate_module {
+	ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY = 1,
+};
+
+#define ETH_GSTRING_LEN		32
+
+/**
+ * enum ethtool_stringset - string set ID
+ * @ETH_SS_TEST: Self-test result names, for use with %ETHTOOL_TEST
+ * @ETH_SS_STATS: Statistic names, for use with %ETHTOOL_GSTATS
+ * @ETH_SS_PRIV_FLAGS: Driver private flag names, for use with
+ *	%ETHTOOL_GPFLAGS and %ETHTOOL_SPFLAGS
+ * @ETH_SS_NTUPLE_FILTERS: Previously used with %ETHTOOL_GRXNTUPLE;
+ *	now deprecated
+ * @ETH_SS_FEATURES: Device feature names
+ * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names
+ * @ETH_SS_TUNABLES: tunable names
+ * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS
+ * @ETH_SS_PHY_TUNABLES: PHY tunable names
+ * @ETH_SS_LINK_MODES: link mode names
+ * @ETH_SS_MSG_CLASSES: debug message class names
+ * @ETH_SS_WOL_MODES: wake-on-lan modes
+ * @ETH_SS_SOF_TIMESTAMPING: SOF_TIMESTAMPING_* flags
+ * @ETH_SS_TS_TX_TYPES: timestamping Tx types
+ * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters
+ * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types
+ * @ETH_SS_STATS_STD: standardized stats
+ * @ETH_SS_STATS_ETH_PHY: names of IEEE 802.3 PHY statistics
+ * @ETH_SS_STATS_ETH_MAC: names of IEEE 802.3 MAC statistics
+ * @ETH_SS_STATS_ETH_CTRL: names of IEEE 802.3 MAC Control statistics
+ * @ETH_SS_STATS_RMON: names of RMON statistics
+ *
+ * @ETH_SS_COUNT: number of defined string sets
+ */
+enum ethtool_stringset {
+	ETH_SS_TEST		= 0,
+	ETH_SS_STATS,
+	ETH_SS_PRIV_FLAGS,
+	ETH_SS_NTUPLE_FILTERS,
+	ETH_SS_FEATURES,
+	ETH_SS_RSS_HASH_FUNCS,
+	ETH_SS_TUNABLES,
+	ETH_SS_PHY_STATS,
+	ETH_SS_PHY_TUNABLES,
+	ETH_SS_LINK_MODES,
+	ETH_SS_MSG_CLASSES,
+	ETH_SS_WOL_MODES,
+	ETH_SS_SOF_TIMESTAMPING,
+	ETH_SS_TS_TX_TYPES,
+	ETH_SS_TS_RX_FILTERS,
+	ETH_SS_UDP_TUNNEL_TYPES,
+	ETH_SS_STATS_STD,
+	ETH_SS_STATS_ETH_PHY,
+	ETH_SS_STATS_ETH_MAC,
+	ETH_SS_STATS_ETH_CTRL,
+	ETH_SS_STATS_RMON,
+
+	/* add new constants above here */
+	ETH_SS_COUNT
+};
+
+/**
+ * enum ethtool_mac_stats_src - source of ethtool MAC statistics
+ * @ETHTOOL_MAC_STATS_SRC_AGGREGATE:
+ *	if device supports a MAC merge layer, this retrieves the aggregate
+ *	statistics of the eMAC and pMAC. Otherwise, it retrieves just the
+ *	statistics of the single (express) MAC.
+ * @ETHTOOL_MAC_STATS_SRC_EMAC:
+ *	if device supports a MM layer, this retrieves the eMAC statistics.
+ *	Otherwise, it retrieves the statistics of the single (express) MAC.
+ * @ETHTOOL_MAC_STATS_SRC_PMAC:
+ *	if device supports a MM layer, this retrieves the pMAC statistics.
+ */
+enum ethtool_mac_stats_src {
+	ETHTOOL_MAC_STATS_SRC_AGGREGATE,
+	ETHTOOL_MAC_STATS_SRC_EMAC,
+	ETHTOOL_MAC_STATS_SRC_PMAC,
+};
+
+/**
+ * enum ethtool_module_power_mode_policy - plug-in module power mode policy
+ * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode.
+ * @ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO: Module is transitioned by the host
+ *	to high power mode when the first port using it is put administratively
+ *	up and to low power mode when the last port using it is put
+ *	administratively down.
+ */
+enum ethtool_module_power_mode_policy {
+	ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH = 1,
+	ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO,
+};
+
+/**
+ * enum ethtool_module_power_mode - plug-in module power mode
+ * @ETHTOOL_MODULE_POWER_MODE_LOW: Module is in low power mode.
+ * @ETHTOOL_MODULE_POWER_MODE_HIGH: Module is in high power mode.
+ */
+enum ethtool_module_power_mode {
+	ETHTOOL_MODULE_POWER_MODE_LOW = 1,
+	ETHTOOL_MODULE_POWER_MODE_HIGH,
+};
+
+/**
+ * enum ethtool_podl_pse_admin_state - operational state of the PoDL PSE
+ *	functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState
+ * @ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN: state of PoDL PSE functions are
+ * 	unknown
+ * @ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED: PoDL PSE functions are disabled
+ * @ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED: PoDL PSE functions are enabled
+ */
+enum ethtool_podl_pse_admin_state {
+	ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN = 1,
+	ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED,
+	ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED,
+};
+
+/**
+ * enum ethtool_podl_pse_pw_d_status - power detection status of the PoDL PSE.
+ *	IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus:
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN: PoDL PSE
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED: "The enumeration “disabled” is
+ *	asserted true when the PoDL PSE state diagram variable mr_pse_enable is
+ *	false"
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING: "The enumeration “searching” is
+ *	asserted true when either of the PSE state diagram variables
+ *	pi_detecting or pi_classifying is true."
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING: "The enumeration “deliveringPower”
+ *	is asserted true when the PoDL PSE state diagram variable pi_powered is
+ *	true."
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP: "The enumeration “sleep” is asserted
+ *	true when the PoDL PSE state diagram variable pi_sleeping is true."
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE: "The enumeration “idle” is asserted true
+ *	when the logical combination of the PoDL PSE state diagram variables
+ *	pi_prebiased*!pi_sleeping is true."
+ * @ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR: "The enumeration “error” is asserted
+ *	true when the PoDL PSE state diagram variable overload_held is true."
+ */
+enum ethtool_podl_pse_pw_d_status {
+	ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN = 1,
+	ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED,
+	ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING,
+	ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING,
+	ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP,
+	ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE,
+	ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR,
+};
+
+/**
+ * enum ethtool_mm_verify_status - status of MAC Merge Verify function
+ * @ETHTOOL_MM_VERIFY_STATUS_UNKNOWN:
+ *	verification status is unknown
+ * @ETHTOOL_MM_VERIFY_STATUS_INITIAL:
+ *	the 802.3 Verify State diagram is in the state INIT_VERIFICATION
+ * @ETHTOOL_MM_VERIFY_STATUS_VERIFYING:
+ *	the Verify State diagram is in the state VERIFICATION_IDLE,
+ *	SEND_VERIFY or WAIT_FOR_RESPONSE
+ * @ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED:
+ *	indicates that the Verify State diagram is in the state VERIFIED
+ * @ETHTOOL_MM_VERIFY_STATUS_FAILED:
+ *	the Verify State diagram is in the state VERIFY_FAIL
+ * @ETHTOOL_MM_VERIFY_STATUS_DISABLED:
+ *	verification of preemption operation is disabled
+ */
+enum ethtool_mm_verify_status {
+	ETHTOOL_MM_VERIFY_STATUS_UNKNOWN,
+	ETHTOOL_MM_VERIFY_STATUS_INITIAL,
+	ETHTOOL_MM_VERIFY_STATUS_VERIFYING,
+	ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED,
+	ETHTOOL_MM_VERIFY_STATUS_FAILED,
+	ETHTOOL_MM_VERIFY_STATUS_DISABLED,
+};
+
+/**
+ * struct ethtool_gstrings - string set for data tagging
+ * @cmd: Command number = %ETHTOOL_GSTRINGS
+ * @string_set: String set ID; one of &enum ethtool_stringset
+ * @len: On return, the number of strings in the string set
+ * @data: Buffer for strings.  Each string is null-padded to a size of
+ *	%ETH_GSTRING_LEN.
+ *
+ * Users must use %ETHTOOL_GSSET_INFO to find the number of strings in
+ * the string set.  They must allocate a buffer of the appropriate
+ * size immediately following this structure.
+ */
+struct ethtool_gstrings {
+	__u32	cmd;
+	__u32	string_set;
+	__u32	len;
+	__u8	data[];
+};
+
+/**
+ * struct ethtool_sset_info - string set information
+ * @cmd: Command number = %ETHTOOL_GSSET_INFO
+ * @reserved: Reserved for future use; see the note on reserved space.
+ * @sset_mask: On entry, a bitmask of string sets to query, with bits
+ *	numbered according to &enum ethtool_stringset.  On return, a
+ *	bitmask of those string sets queried that are supported.
+ * @data: Buffer for string set sizes.  On return, this contains the
+ *	size of each string set that was queried and supported, in
+ *	order of ID.
+ *
+ * Example: The user passes in @sset_mask = 0x7 (sets 0, 1, 2) and on
+ * return @sset_mask == 0x6 (sets 1, 2).  Then @data[0] contains the
+ * size of set 1 and @data[1] contains the size of set 2.
+ *
+ * Users must allocate a buffer of the appropriate size (4 * number of
+ * sets queried) immediately following this structure.
+ */
+struct ethtool_sset_info {
+	__u32	cmd;
+	__u32	reserved;
+	__u64	sset_mask;
+	__u32	data[];
+};
+
+/**
+ * enum ethtool_test_flags - flags definition of ethtool_test
+ * @ETH_TEST_FL_OFFLINE: if set perform online and offline tests, otherwise
+ *	only online tests.
+ * @ETH_TEST_FL_FAILED: Driver set this flag if test fails.
+ * @ETH_TEST_FL_EXTERNAL_LB: Application request to perform external loopback
+ *	test.
+ * @ETH_TEST_FL_EXTERNAL_LB_DONE: Driver performed the external loopback test
+ */
+
+enum ethtool_test_flags {
+	ETH_TEST_FL_OFFLINE	= (1 << 0),
+	ETH_TEST_FL_FAILED	= (1 << 1),
+	ETH_TEST_FL_EXTERNAL_LB	= (1 << 2),
+	ETH_TEST_FL_EXTERNAL_LB_DONE	= (1 << 3),
+};
+
+/**
+ * struct ethtool_test - device self-test invocation
+ * @cmd: Command number = %ETHTOOL_TEST
+ * @flags: A bitmask of flags from &enum ethtool_test_flags.  Some
+ *	flags may be set by the user on entry; others may be set by
+ *	the driver on return.
+ * @reserved: Reserved for future use; see the note on reserved space.
+ * @len: On return, the number of test results
+ * @data: Array of test results
+ *
+ * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the
+ * number of test results that will be returned.  They must allocate a
+ * buffer of the appropriate size (8 * number of results) immediately
+ * following this structure.
+ */
+struct ethtool_test {
+	__u32	cmd;
+	__u32	flags;
+	__u32	reserved;
+	__u32	len;
+	__u64	data[];
+};
+
+/**
+ * struct ethtool_stats - device-specific statistics
+ * @cmd: Command number = %ETHTOOL_GSTATS
+ * @n_stats: On return, the number of statistics
+ * @data: Array of statistics
+ *
+ * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the
+ * number of statistics that will be returned.  They must allocate a
+ * buffer of the appropriate size (8 * number of statistics)
+ * immediately following this structure.
+ */
+struct ethtool_stats {
+	__u32	cmd;
+	__u32	n_stats;
+	__u64	data[];
+};
+
+/**
+ * struct ethtool_perm_addr - permanent hardware address
+ * @cmd: Command number = %ETHTOOL_GPERMADDR
+ * @size: On entry, the size of the buffer.  On return, the size of the
+ *	address.  The command fails if the buffer is too small.
+ * @data: Buffer for the address
+ *
+ * Users must allocate the buffer immediately following this structure.
+ * A buffer size of %MAX_ADDR_LEN should be sufficient for any address
+ * type.
+ */
+struct ethtool_perm_addr {
+	__u32	cmd;
+	__u32	size;
+	__u8	data[];
+};
 
+/* boolean flags controlling per-interface behavior characteristics.
+ * When reading, the flag indicates whether or not a certain behavior
+ * is enabled/present.  When writing, the flag indicates whether
+ * or not the driver should turn on (set) or off (clear) a behavior.
+ *
+ * Some behaviors may read-only (unconditionally absent or present).
+ * If such is the case, return EINVAL in the set-flags operation if the
+ * flag differs from the read-only value.
+ */
+enum ethtool_flags {
+	ETH_FLAG_TXVLAN		= (1 << 7),	/* TX VLAN offload enabled */
+	ETH_FLAG_RXVLAN		= (1 << 8),	/* RX VLAN offload enabled */
+	ETH_FLAG_LRO		= (1 << 15),	/* LRO is enabled */
+	ETH_FLAG_NTUPLE		= (1 << 27),	/* N-tuple filters enabled */
+	ETH_FLAG_RXHASH		= (1 << 28),
+};
+
+/* The following structures are for supporting RX network flow
+ * classification and RX n-tuple configuration. Note, all multibyte
+ * fields, e.g., ip4src, ip4dst, psrc, pdst, spi, etc. are expected to
+ * be in network byte order.
+ */
+
+/**
+ * struct ethtool_tcpip4_spec - flow specification for TCP/IPv4 etc.
+ * @ip4src: Source host
+ * @ip4dst: Destination host
+ * @psrc: Source port
+ * @pdst: Destination port
+ * @tos: Type-of-service
+ *
+ * This can be used to specify a TCP/IPv4, UDP/IPv4 or SCTP/IPv4 flow.
+ */
+struct ethtool_tcpip4_spec {
+	__be32	ip4src;
+	__be32	ip4dst;
+	__be16	psrc;
+	__be16	pdst;
+	__u8    tos;
+};
+
+/**
+ * struct ethtool_ah_espip4_spec - flow specification for IPsec/IPv4
+ * @ip4src: Source host
+ * @ip4dst: Destination host
+ * @spi: Security parameters index
+ * @tos: Type-of-service
+ *
+ * This can be used to specify an IPsec transport or tunnel over IPv4.
+ */
+struct ethtool_ah_espip4_spec {
+	__be32	ip4src;
+	__be32	ip4dst;
+	__be32	spi;
+	__u8    tos;
+};
+
+#define	ETH_RX_NFC_IP4	1
+
+/**
+ * struct ethtool_usrip4_spec - general flow specification for IPv4
+ * @ip4src: Source host
+ * @ip4dst: Destination host
+ * @l4_4_bytes: First 4 bytes of transport (layer 4) header
+ * @tos: Type-of-service
+ * @ip_ver: Value must be %ETH_RX_NFC_IP4; mask must be 0
+ * @proto: Transport protocol number; mask must be 0
+ */
+struct ethtool_usrip4_spec {
+	__be32	ip4src;
+	__be32	ip4dst;
+	__be32	l4_4_bytes;
+	__u8    tos;
+	__u8    ip_ver;
+	__u8    proto;
+};
+
+/**
+ * struct ethtool_tcpip6_spec - flow specification for TCP/IPv6 etc.
+ * @ip6src: Source host
+ * @ip6dst: Destination host
+ * @psrc: Source port
+ * @pdst: Destination port
+ * @tclass: Traffic Class
+ *
+ * This can be used to specify a TCP/IPv6, UDP/IPv6 or SCTP/IPv6 flow.
+ */
+struct ethtool_tcpip6_spec {
+	__be32	ip6src[4];
+	__be32	ip6dst[4];
+	__be16	psrc;
+	__be16	pdst;
+	__u8    tclass;
+};
+
+/**
+ * struct ethtool_ah_espip6_spec - flow specification for IPsec/IPv6
+ * @ip6src: Source host
+ * @ip6dst: Destination host
+ * @spi: Security parameters index
+ * @tclass: Traffic Class
+ *
+ * This can be used to specify an IPsec transport or tunnel over IPv6.
+ */
+struct ethtool_ah_espip6_spec {
+	__be32	ip6src[4];
+	__be32	ip6dst[4];
+	__be32	spi;
+	__u8    tclass;
+};
+
+/**
+ * struct ethtool_usrip6_spec - general flow specification for IPv6
+ * @ip6src: Source host
+ * @ip6dst: Destination host
+ * @l4_4_bytes: First 4 bytes of transport (layer 4) header
+ * @tclass: Traffic Class
+ * @l4_proto: Transport protocol number (nexthdr after any Extension Headers)
+ */
+struct ethtool_usrip6_spec {
+	__be32	ip6src[4];
+	__be32	ip6dst[4];
+	__be32	l4_4_bytes;
+	__u8    tclass;
+	__u8    l4_proto;
+};
+
+union ethtool_flow_union {
+	struct ethtool_tcpip4_spec		tcp_ip4_spec;
+	struct ethtool_tcpip4_spec		udp_ip4_spec;
+	struct ethtool_tcpip4_spec		sctp_ip4_spec;
+	struct ethtool_ah_espip4_spec		ah_ip4_spec;
+	struct ethtool_ah_espip4_spec		esp_ip4_spec;
+	struct ethtool_usrip4_spec		usr_ip4_spec;
+	struct ethtool_tcpip6_spec		tcp_ip6_spec;
+	struct ethtool_tcpip6_spec		udp_ip6_spec;
+	struct ethtool_tcpip6_spec		sctp_ip6_spec;
+	struct ethtool_ah_espip6_spec		ah_ip6_spec;
+	struct ethtool_ah_espip6_spec		esp_ip6_spec;
+	struct ethtool_usrip6_spec		usr_ip6_spec;
+	struct ethhdr				ether_spec;
+	__u8					hdata[52];
+};
+
+/**
+ * struct ethtool_flow_ext - additional RX flow fields
+ * @h_dest: destination MAC address
+ * @vlan_etype: VLAN EtherType
+ * @vlan_tci: VLAN tag control information
+ * @data: user defined data
+ * @padding: Reserved for future use; see the note on reserved space.
+ *
+ * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT
+ * is set in &struct ethtool_rx_flow_spec @flow_type.
+ * @h_dest is valid if %FLOW_MAC_EXT is set.
+ */
+struct ethtool_flow_ext {
+	__u8		padding[2];
+	unsigned char	h_dest[ETH_ALEN];
+	__be16		vlan_etype;
+	__be16		vlan_tci;
+	__be32		data[2];
+};
+
+/**
+ * struct ethtool_rx_flow_spec - classification rule for RX flows
+ * @flow_type: Type of match to perform, e.g. %TCP_V4_FLOW
+ * @h_u: Flow fields to match (dependent on @flow_type)
+ * @h_ext: Additional fields to match
+ * @m_u: Masks for flow field bits to be matched
+ * @m_ext: Masks for additional field bits to be matched
+ *	Note, all additional fields must be ignored unless @flow_type
+ *	includes the %FLOW_EXT or %FLOW_MAC_EXT flag
+ *	(see &struct ethtool_flow_ext description).
+ * @ring_cookie: RX ring/queue index to deliver to, or %RX_CLS_FLOW_DISC
+ *	if packets should be discarded, or %RX_CLS_FLOW_WAKE if the
+ *	packets should be used for Wake-on-LAN with %WAKE_FILTER
+ * @location: Location of rule in the table.  Locations must be
+ *	numbered such that a flow matching multiple rules will be
+ *	classified according to the first (lowest numbered) rule.
+ */
+struct ethtool_rx_flow_spec {
+	__u32		flow_type;
+	union ethtool_flow_union h_u;
+	struct ethtool_flow_ext h_ext;
+	union ethtool_flow_union m_u;
+	struct ethtool_flow_ext m_ext;
+	__u64		ring_cookie;
+	__u32		location;
+};
+
+/* How rings are laid out when accessing virtual functions or
+ * offloaded queues is device specific. To allow users to do flow
+ * steering and specify these queues the ring cookie is partitioned
+ * into a 32bit queue index with an 8 bit virtual function id.
+ * This also leaves the 3bytes for further specifiers. It is possible
+ * future devices may support more than 256 virtual functions if
+ * devices start supporting PCIe w/ARI. However at the moment I
+ * do not know of any devices that support this so I do not reserve
+ * space for this at this time. If a future patch consumes the next
+ * byte it should be aware of this possibility.
+ */
+#define ETHTOOL_RX_FLOW_SPEC_RING	0x00000000FFFFFFFFLL
+#define ETHTOOL_RX_FLOW_SPEC_RING_VF	0x000000FF00000000LL
+#define ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF 32
+static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie)
+{
+	return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie;
+}
+
+static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie)
+{
+	return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >>
+				ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
+}
+
+/**
+ * struct ethtool_rxnfc - command to get or set RX flow classification rules
+ * @cmd: Specific command number - %ETHTOOL_GRXFH, %ETHTOOL_SRXFH,
+ *	%ETHTOOL_GRXRINGS, %ETHTOOL_GRXCLSRLCNT, %ETHTOOL_GRXCLSRULE,
+ *	%ETHTOOL_GRXCLSRLALL, %ETHTOOL_SRXCLSRLDEL or %ETHTOOL_SRXCLSRLINS
+ * @flow_type: Type of flow to be affected, e.g. %TCP_V4_FLOW
+ * @data: Command-dependent value
+ * @fs: Flow classification rule
+ * @rss_context: RSS context to be affected
+ * @rule_cnt: Number of rules to be affected
+ * @rule_locs: Array of used rule locations
+ *
+ * For %ETHTOOL_GRXFH and %ETHTOOL_SRXFH, @data is a bitmask indicating
+ * the fields included in the flow hash, e.g. %RXH_IP_SRC.  The following
+ * structure fields must not be used, except that if @flow_type includes
+ * the %FLOW_RSS flag, then @rss_context determines which RSS context to
+ * act on.
+ *
+ * For %ETHTOOL_GRXRINGS, @data is set to the number of RX rings/queues
+ * on return.
+ *
+ * For %ETHTOOL_GRXCLSRLCNT, @rule_cnt is set to the number of defined
+ * rules on return.  If @data is non-zero on return then it is the
+ * size of the rule table, plus the flag %RX_CLS_LOC_SPECIAL if the
+ * driver supports any special location values.  If that flag is not
+ * set in @data then special location values should not be used.
+ *
+ * For %ETHTOOL_GRXCLSRULE, @fs.@location specifies the location of an
+ * existing rule on entry and @fs contains the rule on return; if
+ * @fs.@flow_type includes the %FLOW_RSS flag, then @rss_context is
+ * filled with the RSS context ID associated with the rule.
+ *
+ * For %ETHTOOL_GRXCLSRLALL, @rule_cnt specifies the array size of the
+ * user buffer for @rule_locs on entry.  On return, @data is the size
+ * of the rule table, @rule_cnt is the number of defined rules, and
+ * @rule_locs contains the locations of the defined rules.  Drivers
+ * must use the second parameter to get_rxnfc() instead of @rule_locs.
+ *
+ * For %ETHTOOL_SRXCLSRLINS, @fs specifies the rule to add or update.
+ * @fs.@location either specifies the location to use or is a special
+ * location value with %RX_CLS_LOC_SPECIAL flag set.  On return,
+ * @fs.@location is the actual rule location.  If @fs.@flow_type
+ * includes the %FLOW_RSS flag, @rss_context is the RSS context ID to
+ * use for flow spreading traffic which matches this rule.  The value
+ * from the rxfh indirection table will be added to @fs.@ring_cookie
+ * to choose which ring to deliver to.
+ *
+ * For %ETHTOOL_SRXCLSRLDEL, @fs.@location specifies the location of an
+ * existing rule on entry.
+ *
+ * A driver supporting the special location values for
+ * %ETHTOOL_SRXCLSRLINS may add the rule at any suitable unused
+ * location, and may remove a rule at a later location (lower
+ * priority) that matches exactly the same set of flows.  The special
+ * values are %RX_CLS_LOC_ANY, selecting any location;
+ * %RX_CLS_LOC_FIRST, selecting the first suitable location (maximum
+ * priority); and %RX_CLS_LOC_LAST, selecting the last suitable
+ * location (minimum priority).  Additional special values may be
+ * defined in future and drivers must return -%EINVAL for any
+ * unrecognised value.
+ */
+struct ethtool_rxnfc {
+	__u32				cmd;
+	__u32				flow_type;
+	__u64				data;
+	struct ethtool_rx_flow_spec	fs;
+	union {
+		__u32			rule_cnt;
+		__u32			rss_context;
+	};
+	__u32				rule_locs[];
+};
+
+
+/**
+ * struct ethtool_rxfh_indir - command to get or set RX flow hash indirection
+ * @cmd: Specific command number - %ETHTOOL_GRXFHINDIR or %ETHTOOL_SRXFHINDIR
+ * @size: On entry, the array size of the user buffer, which may be zero.
+ *	On return from %ETHTOOL_GRXFHINDIR, the array size of the hardware
+ *	indirection table.
+ * @ring_index: RX ring/queue index for each hash value
+ *
+ * For %ETHTOOL_GRXFHINDIR, a @size of zero means that only the size
+ * should be returned.  For %ETHTOOL_SRXFHINDIR, a @size of zero means
+ * the table should be reset to default values.  This last feature
+ * is not supported by the original implementations.
+ */
+struct ethtool_rxfh_indir {
+	__u32	cmd;
+	__u32	size;
+	__u32	ring_index[];
+};
+
+/**
+ * struct ethtool_rxfh - command to get/set RX flow hash indir or/and hash key.
+ * @cmd: Specific command number - %ETHTOOL_GRSSH or %ETHTOOL_SRSSH
+ * @rss_context: RSS context identifier.  Context 0 is the default for normal
+ *	traffic; other contexts can be referenced as the destination for RX flow
+ *	classification rules.  %ETH_RXFH_CONTEXT_ALLOC is used with command
+ *	%ETHTOOL_SRSSH to allocate a new RSS context; on return this field will
+ *	contain the ID of the newly allocated context.
+ * @indir_size: On entry, the array size of the user buffer for the
+ *	indirection table, which may be zero, or (for %ETHTOOL_SRSSH),
+ *	%ETH_RXFH_INDIR_NO_CHANGE.  On return from %ETHTOOL_GRSSH,
+ *	the array size of the hardware indirection table.
+ * @key_size: On entry, the array size of the user buffer for the hash key,
+ *	which may be zero.  On return from %ETHTOOL_GRSSH, the size of the
+ *	hardware hash key.
+ * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
+ *	Valid values are one of the %ETH_RSS_HASH_*.
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ *	of %RXH_XFRM_*.
+ * @rsvd8: Reserved for future use; see the note on reserved space.
+ * @rsvd32: Reserved for future use; see the note on reserved space.
+ * @rss_config: RX ring/queue index for each hash value i.e., indirection table
+ *	of @indir_size __u32 elements, followed by hash key of @key_size
+ *	bytes.
+ *
+ * For %ETHTOOL_GRSSH, a @indir_size and key_size of zero means that only the
+ * size should be returned.  For %ETHTOOL_SRSSH, an @indir_size of
+ * %ETH_RXFH_INDIR_NO_CHANGE means that indir table setting is not requested
+ * and a @indir_size of zero means the indir table should be reset to default
+ * values (if @rss_context == 0) or that the RSS context should be deleted.
+ * An hfunc of zero means that hash function setting is not requested.
+ */
+struct ethtool_rxfh {
+	__u32   cmd;
+	__u32	rss_context;
+	__u32   indir_size;
+	__u32   key_size;
+	__u8	hfunc;
+	__u8	input_xfrm;
+	__u8	rsvd8[2];
+	__u32	rsvd32;
+	__u32   rss_config[];
+};
+#define ETH_RXFH_CONTEXT_ALLOC		0xffffffff
+#define ETH_RXFH_INDIR_NO_CHANGE	0xffffffff
+
+/**
+ * struct ethtool_rx_ntuple_flow_spec - specification for RX flow filter
+ * @flow_type: Type of match to perform, e.g. %TCP_V4_FLOW
+ * @h_u: Flow field values to match (dependent on @flow_type)
+ * @m_u: Masks for flow field value bits to be ignored
+ * @vlan_tag: VLAN tag to match
+ * @vlan_tag_mask: Mask for VLAN tag bits to be ignored
+ * @data: Driver-dependent data to match
+ * @data_mask: Mask for driver-dependent data bits to be ignored
+ * @action: RX ring/queue index to deliver to (non-negative) or other action
+ *	(negative, e.g. %ETHTOOL_RXNTUPLE_ACTION_DROP)
+ *
+ * For flow types %TCP_V4_FLOW, %UDP_V4_FLOW and %SCTP_V4_FLOW, where
+ * a field value and mask are both zero this is treated as if all mask
+ * bits are set i.e. the field is ignored.
+ */
+struct ethtool_rx_ntuple_flow_spec {
+	__u32		 flow_type;
+	union {
+		struct ethtool_tcpip4_spec		tcp_ip4_spec;
+		struct ethtool_tcpip4_spec		udp_ip4_spec;
+		struct ethtool_tcpip4_spec		sctp_ip4_spec;
+		struct ethtool_ah_espip4_spec		ah_ip4_spec;
+		struct ethtool_ah_espip4_spec		esp_ip4_spec;
+		struct ethtool_usrip4_spec		usr_ip4_spec;
+		struct ethhdr				ether_spec;
+		__u8					hdata[72];
+	} h_u, m_u;
+
+	__u16	        vlan_tag;
+	__u16	        vlan_tag_mask;
+	__u64		data;
+	__u64		data_mask;
+
+	__s32		action;
+#define ETHTOOL_RXNTUPLE_ACTION_DROP	(-1)	/* drop packet */
+#define ETHTOOL_RXNTUPLE_ACTION_CLEAR	(-2)	/* clear filter */
+};
+
+/**
+ * struct ethtool_rx_ntuple - command to set or clear RX flow filter
+ * @cmd: Command number - %ETHTOOL_SRXNTUPLE
+ * @fs: Flow filter specification
+ */
+struct ethtool_rx_ntuple {
+	__u32					cmd;
+	struct ethtool_rx_ntuple_flow_spec	fs;
+};
+
+#define ETHTOOL_FLASH_MAX_FILENAME	128
+enum ethtool_flash_op_type {
+	ETHTOOL_FLASH_ALL_REGIONS	= 0,
+};
+
+/* for passing firmware flashing related parameters */
+struct ethtool_flash {
+	__u32	cmd;
+	__u32	region;
+	char	data[ETHTOOL_FLASH_MAX_FILENAME];
+};
+
+/**
+ * struct ethtool_dump - used for retrieving, setting device dump
+ * @cmd: Command number - %ETHTOOL_GET_DUMP_FLAG, %ETHTOOL_GET_DUMP_DATA, or
+ * 	%ETHTOOL_SET_DUMP
+ * @version: FW version of the dump, filled in by driver
+ * @flag: driver dependent flag for dump setting, filled in by driver during
+ *        get and filled in by ethtool for set operation.
+ *        flag must be initialized by macro ETH_FW_DUMP_DISABLE value when
+ *        firmware dump is disabled.
+ * @len: length of dump data, used as the length of the user buffer on entry to
+ * 	 %ETHTOOL_GET_DUMP_DATA and this is returned as dump length by driver
+ * 	 for %ETHTOOL_GET_DUMP_FLAG command
+ * @data: data collected for get dump data operation
+ */
+struct ethtool_dump {
+	__u32	cmd;
+	__u32	version;
+	__u32	flag;
+	__u32	len;
+	__u8	data[];
+};
+
+#define ETH_FW_DUMP_DISABLE 0
+
+/* for returning and changing feature sets */
+
+/**
+ * struct ethtool_get_features_block - block with state of 32 features
+ * @available: mask of changeable features
+ * @requested: mask of features requested to be enabled if possible
+ * @active: mask of currently enabled features
+ * @never_changed: mask of features not changeable for any device
+ */
+struct ethtool_get_features_block {
+	__u32	available;
+	__u32	requested;
+	__u32	active;
+	__u32	never_changed;
+};
+
+/**
+ * struct ethtool_gfeatures - command to get state of device's features
+ * @cmd: command number = %ETHTOOL_GFEATURES
+ * @size: On entry, the number of elements in the features[] array;
+ *	on return, the number of elements in features[] needed to hold
+ *	all features
+ * @features: state of features
+ */
+struct ethtool_gfeatures {
+	__u32	cmd;
+	__u32	size;
+	struct ethtool_get_features_block features[];
+};
+
+/**
+ * struct ethtool_set_features_block - block with request for 32 features
+ * @valid: mask of features to be changed
+ * @requested: values of features to be changed
+ */
+struct ethtool_set_features_block {
+	__u32	valid;
+	__u32	requested;
+};
+
+/**
+ * struct ethtool_sfeatures - command to request change in device's features
+ * @cmd: command number = %ETHTOOL_SFEATURES
+ * @size: array size of the features[] array
+ * @features: feature change masks
+ */
+struct ethtool_sfeatures {
+	__u32	cmd;
+	__u32	size;
+	struct ethtool_set_features_block features[];
+};
+
+/**
+ * struct ethtool_ts_info - holds a device's timestamping and PHC association
+ * @cmd: command number = %ETHTOOL_GET_TS_INFO
+ * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags
+ * @phc_index: device index of the associated PHC, or -1 if there is none
+ * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values
+ * @tx_reserved: Reserved for future use; see the note on reserved space.
+ * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values
+ * @rx_reserved: Reserved for future use; see the note on reserved space.
+ *
+ * The bits in the 'tx_types' and 'rx_filters' fields correspond to
+ * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values,
+ * respectively.  For example, if the device supports HWTSTAMP_TX_ON,
+ * then (1 << HWTSTAMP_TX_ON) in 'tx_types' will be set.
+ *
+ * Drivers should only report the filters they actually support without
+ * upscaling in the SIOCSHWTSTAMP ioctl. If the SIOCSHWSTAMP request for
+ * HWTSTAMP_FILTER_V1_SYNC is supported by HWTSTAMP_FILTER_V1_EVENT, then the
+ * driver should only report HWTSTAMP_FILTER_V1_EVENT in this op.
+ */
+struct ethtool_ts_info {
+	__u32	cmd;
+	__u32	so_timestamping;
+	__s32	phc_index;
+	__u32	tx_types;
+	__u32	tx_reserved[3];
+	__u32	rx_filters;
+	__u32	rx_reserved[3];
+};
+
+/*
+ * %ETHTOOL_SFEATURES changes features present in features[].valid to the
+ * values of corresponding bits in features[].requested. Bits in .requested
+ * not set in .valid or not changeable are ignored.
+ *
+ * Returns %EINVAL when .valid contains undefined or never-changeable bits
+ * or size is not equal to required number of features words (32-bit blocks).
+ * Returns >= 0 if request was completed; bits set in the value mean:
+ *   %ETHTOOL_F_UNSUPPORTED - there were bits set in .valid that are not
+ *	changeable (not present in %ETHTOOL_GFEATURES' features[].available)
+ *	those bits were ignored.
+ *   %ETHTOOL_F_WISH - some or all changes requested were recorded but the
+ *      resulting state of bits masked by .valid is not equal to .requested.
+ *      Probably there are other device-specific constraints on some features
+ *      in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered
+ *      here as though ignored bits were cleared.
+ *   %ETHTOOL_F_COMPAT - some or all changes requested were made by calling
+ *      compatibility functions. Requested offload state cannot be properly
+ *      managed by kernel.
+ *
+ * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of
+ * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands
+ * for ETH_SS_FEATURES string set. First entry in the table corresponds to least
+ * significant bit in features[0] fields. Empty strings mark undefined features.
+ */
+enum ethtool_sfeatures_retval_bits {
+	ETHTOOL_F_UNSUPPORTED__BIT,
+	ETHTOOL_F_WISH__BIT,
+	ETHTOOL_F_COMPAT__BIT,
+};
+
+#define ETHTOOL_F_UNSUPPORTED   (1 << ETHTOOL_F_UNSUPPORTED__BIT)
+#define ETHTOOL_F_WISH          (1 << ETHTOOL_F_WISH__BIT)
+#define ETHTOOL_F_COMPAT        (1 << ETHTOOL_F_COMPAT__BIT)
+
+#define MAX_NUM_QUEUE		4096
+
+/**
+ * struct ethtool_per_queue_op - apply sub command to the queues in mask.
+ * @cmd: ETHTOOL_PERQUEUE
+ * @sub_command: the sub command which apply to each queues
+ * @queue_mask: Bitmap of the queues which sub command apply to
+ * @data: A complete command structure following for each of the queues addressed
+ */
+struct ethtool_per_queue_op {
+	__u32	cmd;
+	__u32	sub_command;
+	__u32	queue_mask[__KERNEL_DIV_ROUND_UP(MAX_NUM_QUEUE, 32)];
+	char	data[];
+};
+
+/**
+ * struct ethtool_fecparam - Ethernet Forward Error Correction parameters
+ * @cmd: Command number = %ETHTOOL_GFECPARAM or %ETHTOOL_SFECPARAM
+ * @active_fec: FEC mode which is active on the port, single bit set, GET only.
+ * @fec: Bitmask of configured FEC modes.
+ * @reserved: Reserved for future extensions, ignore on GET, write 0 for SET.
+ *
+ * Note that @reserved was never validated on input and ethtool user space
+ * left it uninitialized when calling SET. Hence going forward it can only be
+ * used to return a value to userspace with GET.
+ *
+ * FEC modes supported by the device can be read via %ETHTOOL_GLINKSETTINGS.
+ * FEC settings are configured by link autonegotiation whenever it's enabled.
+ * With autoneg on %ETHTOOL_GFECPARAM can be used to read the current mode.
+ *
+ * When autoneg is disabled %ETHTOOL_SFECPARAM controls the FEC settings.
+ * It is recommended that drivers only accept a single bit set in @fec.
+ * When multiple bits are set in @fec drivers may pick mode in an implementation
+ * dependent way. Drivers should reject mixing %ETHTOOL_FEC_AUTO_BIT with other
+ * FEC modes, because it's unclear whether in this case other modes constrain
+ * AUTO or are independent choices.
+ * Drivers must reject SET requests if they support none of the requested modes.
+ *
+ * If device does not support FEC drivers may use %ETHTOOL_FEC_NONE instead
+ * of returning %EOPNOTSUPP from %ETHTOOL_GFECPARAM.
+ *
+ * See enum ethtool_fec_config_bits for definition of valid bits for both
+ * @fec and @active_fec.
+ */
+struct ethtool_fecparam {
+	__u32   cmd;
+	/* bitmask of FEC modes */
+	__u32   active_fec;
+	__u32   fec;
+	__u32   reserved;
+};
+
+/**
+ * enum ethtool_fec_config_bits - flags definition of ethtool_fec_configuration
+ * @ETHTOOL_FEC_NONE_BIT: FEC mode configuration is not supported. Should not
+ *			be used together with other bits. GET only.
+ * @ETHTOOL_FEC_AUTO_BIT: Select default/best FEC mode automatically, usually
+ *			based link mode and SFP parameters read from module's
+ *			EEPROM. This bit does _not_ mean autonegotiation.
+ * @ETHTOOL_FEC_OFF_BIT: No FEC Mode
+ * @ETHTOOL_FEC_RS_BIT: Reed-Solomon FEC Mode
+ * @ETHTOOL_FEC_BASER_BIT: Base-R/Reed-Solomon FEC Mode
+ * @ETHTOOL_FEC_LLRS_BIT: Low Latency Reed Solomon FEC Mode (25G/50G Ethernet
+ *			Consortium)
+ */
+enum ethtool_fec_config_bits {
+	ETHTOOL_FEC_NONE_BIT,
+	ETHTOOL_FEC_AUTO_BIT,
+	ETHTOOL_FEC_OFF_BIT,
+	ETHTOOL_FEC_RS_BIT,
+	ETHTOOL_FEC_BASER_BIT,
+	ETHTOOL_FEC_LLRS_BIT,
+};
+
+#define ETHTOOL_FEC_NONE		(1 << ETHTOOL_FEC_NONE_BIT)
+#define ETHTOOL_FEC_AUTO		(1 << ETHTOOL_FEC_AUTO_BIT)
+#define ETHTOOL_FEC_OFF			(1 << ETHTOOL_FEC_OFF_BIT)
+#define ETHTOOL_FEC_RS			(1 << ETHTOOL_FEC_RS_BIT)
+#define ETHTOOL_FEC_BASER		(1 << ETHTOOL_FEC_BASER_BIT)
+#define ETHTOOL_FEC_LLRS		(1 << ETHTOOL_FEC_LLRS_BIT)
+
+/* CMDs currently supported */
+#define ETHTOOL_GSET		0x00000001 /* DEPRECATED, Get settings.
+					    * Please use ETHTOOL_GLINKSETTINGS
+					    */
+#define ETHTOOL_SSET		0x00000002 /* DEPRECATED, Set settings.
+					    * Please use ETHTOOL_SLINKSETTINGS
+					    */
+#define ETHTOOL_GDRVINFO	0x00000003 /* Get driver info. */
+#define ETHTOOL_GREGS		0x00000004 /* Get NIC registers. */
+#define ETHTOOL_GWOL		0x00000005 /* Get wake-on-lan options. */
+#define ETHTOOL_SWOL		0x00000006 /* Set wake-on-lan options. */
+#define ETHTOOL_GMSGLVL		0x00000007 /* Get driver message level */
+#define ETHTOOL_SMSGLVL		0x00000008 /* Set driver msg level. */
+#define ETHTOOL_NWAY_RST	0x00000009 /* Restart autonegotiation. */
+/* Get link status for host, i.e. whether the interface *and* the
+ * physical port (if there is one) are up (ethtool_value). */
+#define ETHTOOL_GLINK		0x0000000a
+#define ETHTOOL_GEEPROM		0x0000000b /* Get EEPROM data */
+#define ETHTOOL_SEEPROM		0x0000000c /* Set EEPROM data. */
+#define ETHTOOL_GCOALESCE	0x0000000e /* Get coalesce config */
+#define ETHTOOL_SCOALESCE	0x0000000f /* Set coalesce config. */
+#define ETHTOOL_GRINGPARAM	0x00000010 /* Get ring parameters */
+#define ETHTOOL_SRINGPARAM	0x00000011 /* Set ring parameters. */
+#define ETHTOOL_GPAUSEPARAM	0x00000012 /* Get pause parameters */
+#define ETHTOOL_SPAUSEPARAM	0x00000013 /* Set pause parameters. */
+#define ETHTOOL_GRXCSUM		0x00000014 /* Get RX hw csum enable (ethtool_value) */
+#define ETHTOOL_SRXCSUM		0x00000015 /* Set RX hw csum enable (ethtool_value) */
+#define ETHTOOL_GTXCSUM		0x00000016 /* Get TX hw csum enable (ethtool_value) */
+#define ETHTOOL_STXCSUM		0x00000017 /* Set TX hw csum enable (ethtool_value) */
+#define ETHTOOL_GSG		0x00000018 /* Get scatter-gather enable
+					    * (ethtool_value) */
+#define ETHTOOL_SSG		0x00000019 /* Set scatter-gather enable
+					    * (ethtool_value). */
+#define ETHTOOL_TEST		0x0000001a /* execute NIC self-test. */
+#define ETHTOOL_GSTRINGS	0x0000001b /* get specified string set */
+#define ETHTOOL_PHYS_ID		0x0000001c /* identify the NIC */
+#define ETHTOOL_GSTATS		0x0000001d /* get NIC-specific statistics */
+#define ETHTOOL_GTSO		0x0000001e /* Get TSO enable (ethtool_value) */
+#define ETHTOOL_STSO		0x0000001f /* Set TSO enable (ethtool_value) */
+#define ETHTOOL_GPERMADDR	0x00000020 /* Get permanent hardware address */
+#define ETHTOOL_GUFO		0x00000021 /* Get UFO enable (ethtool_value) */
+#define ETHTOOL_SUFO		0x00000022 /* Set UFO enable (ethtool_value) */
+#define ETHTOOL_GGSO		0x00000023 /* Get GSO enable (ethtool_value) */
+#define ETHTOOL_SGSO		0x00000024 /* Set GSO enable (ethtool_value) */
+#define ETHTOOL_GFLAGS		0x00000025 /* Get flags bitmap(ethtool_value) */
+#define ETHTOOL_SFLAGS		0x00000026 /* Set flags bitmap(ethtool_value) */
+#define ETHTOOL_GPFLAGS		0x00000027 /* Get driver-private flags bitmap */
+#define ETHTOOL_SPFLAGS		0x00000028 /* Set driver-private flags bitmap */
+
+#define ETHTOOL_GRXFH		0x00000029 /* Get RX flow hash configuration */
+#define ETHTOOL_SRXFH		0x0000002a /* Set RX flow hash configuration */
+#define ETHTOOL_GGRO		0x0000002b /* Get GRO enable (ethtool_value) */
+#define ETHTOOL_SGRO		0x0000002c /* Set GRO enable (ethtool_value) */
+#define ETHTOOL_GRXRINGS	0x0000002d /* Get RX rings available for LB */
+#define ETHTOOL_GRXCLSRLCNT	0x0000002e /* Get RX class rule count */
+#define ETHTOOL_GRXCLSRULE	0x0000002f /* Get RX classification rule */
+#define ETHTOOL_GRXCLSRLALL	0x00000030 /* Get all RX classification rule */
+#define ETHTOOL_SRXCLSRLDEL	0x00000031 /* Delete RX classification rule */
+#define ETHTOOL_SRXCLSRLINS	0x00000032 /* Insert RX classification rule */
+#define ETHTOOL_FLASHDEV	0x00000033 /* Flash firmware to device */
+#define ETHTOOL_RESET		0x00000034 /* Reset hardware */
+#define ETHTOOL_SRXNTUPLE	0x00000035 /* Add an n-tuple filter to device */
+#define ETHTOOL_GRXNTUPLE	0x00000036 /* deprecated */
+#define ETHTOOL_GSSET_INFO	0x00000037 /* Get string set info */
+#define ETHTOOL_GRXFHINDIR	0x00000038 /* Get RX flow hash indir'n table */
+#define ETHTOOL_SRXFHINDIR	0x00000039 /* Set RX flow hash indir'n table */
+
+#define ETHTOOL_GFEATURES	0x0000003a /* Get device offload settings */
+#define ETHTOOL_SFEATURES	0x0000003b /* Change device offload settings */
+#define ETHTOOL_GCHANNELS	0x0000003c /* Get no of channels */
+#define ETHTOOL_SCHANNELS	0x0000003d /* Set no of channels */
+#define ETHTOOL_SET_DUMP	0x0000003e /* Set dump settings */
+#define ETHTOOL_GET_DUMP_FLAG	0x0000003f /* Get dump settings */
+#define ETHTOOL_GET_DUMP_DATA	0x00000040 /* Get dump data */
+#define ETHTOOL_GET_TS_INFO	0x00000041 /* Get time stamping and PHC info */
+#define ETHTOOL_GMODULEINFO	0x00000042 /* Get plug-in module information */
+#define ETHTOOL_GMODULEEEPROM	0x00000043 /* Get plug-in module eeprom */
+#define ETHTOOL_GEEE		0x00000044 /* Get EEE settings */
+#define ETHTOOL_SEEE		0x00000045 /* Set EEE settings */
+
+#define ETHTOOL_GRSSH		0x00000046 /* Get RX flow hash configuration */
+#define ETHTOOL_SRSSH		0x00000047 /* Set RX flow hash configuration */
+#define ETHTOOL_GTUNABLE	0x00000048 /* Get tunable configuration */
+#define ETHTOOL_STUNABLE	0x00000049 /* Set tunable configuration */
+#define ETHTOOL_GPHYSTATS	0x0000004a /* get PHY-specific statistics */
+
+#define ETHTOOL_PERQUEUE	0x0000004b /* Set per queue options */
+
+#define ETHTOOL_GLINKSETTINGS	0x0000004c /* Get ethtool_link_settings */
+#define ETHTOOL_SLINKSETTINGS	0x0000004d /* Set ethtool_link_settings */
+#define ETHTOOL_PHY_GTUNABLE	0x0000004e /* Get PHY tunable configuration */
+#define ETHTOOL_PHY_STUNABLE	0x0000004f /* Set PHY tunable configuration */
+#define ETHTOOL_GFECPARAM	0x00000050 /* Get FEC settings */
+#define ETHTOOL_SFECPARAM	0x00000051 /* Set FEC settings */
+
+/* compatibility with older code */
+#define SPARC_ETH_GSET		ETHTOOL_GSET
+#define SPARC_ETH_SSET		ETHTOOL_SSET
+
+/* Link mode bit indices */
+enum ethtool_link_mode_bit_indices {
+	ETHTOOL_LINK_MODE_10baseT_Half_BIT	= 0,
+	ETHTOOL_LINK_MODE_10baseT_Full_BIT	= 1,
+	ETHTOOL_LINK_MODE_100baseT_Half_BIT	= 2,
+	ETHTOOL_LINK_MODE_100baseT_Full_BIT	= 3,
+	ETHTOOL_LINK_MODE_1000baseT_Half_BIT	= 4,
+	ETHTOOL_LINK_MODE_1000baseT_Full_BIT	= 5,
+	ETHTOOL_LINK_MODE_Autoneg_BIT		= 6,
+	ETHTOOL_LINK_MODE_TP_BIT		= 7,
+	ETHTOOL_LINK_MODE_AUI_BIT		= 8,
+	ETHTOOL_LINK_MODE_MII_BIT		= 9,
+	ETHTOOL_LINK_MODE_FIBRE_BIT		= 10,
+	ETHTOOL_LINK_MODE_BNC_BIT		= 11,
+	ETHTOOL_LINK_MODE_10000baseT_Full_BIT	= 12,
+	ETHTOOL_LINK_MODE_Pause_BIT		= 13,
+	ETHTOOL_LINK_MODE_Asym_Pause_BIT	= 14,
+	ETHTOOL_LINK_MODE_2500baseX_Full_BIT	= 15,
+	ETHTOOL_LINK_MODE_Backplane_BIT		= 16,
+	ETHTOOL_LINK_MODE_1000baseKX_Full_BIT	= 17,
+	ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT	= 18,
+	ETHTOOL_LINK_MODE_10000baseKR_Full_BIT	= 19,
+	ETHTOOL_LINK_MODE_10000baseR_FEC_BIT	= 20,
+	ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT = 21,
+	ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT	= 22,
+	ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT	= 23,
+	ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT	= 24,
+	ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT	= 25,
+	ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT	= 26,
+	ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT	= 27,
+	ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT	= 28,
+	ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT	= 29,
+	ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT	= 30,
+	ETHTOOL_LINK_MODE_25000baseCR_Full_BIT	= 31,
+
+	/* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit
+	 * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_*
+	 * macro for bits > 31. The only way to use indices > 31 is to
+	 * use the new ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API.
+	 */
+
+	ETHTOOL_LINK_MODE_25000baseKR_Full_BIT	= 32,
+	ETHTOOL_LINK_MODE_25000baseSR_Full_BIT	= 33,
+	ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT	= 34,
+	ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT	= 35,
+	ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT	= 36,
+	ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT	= 37,
+	ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT	= 38,
+	ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT	= 39,
+	ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT		= 40,
+	ETHTOOL_LINK_MODE_1000baseX_Full_BIT	= 41,
+	ETHTOOL_LINK_MODE_10000baseCR_Full_BIT	= 42,
+	ETHTOOL_LINK_MODE_10000baseSR_Full_BIT	= 43,
+	ETHTOOL_LINK_MODE_10000baseLR_Full_BIT	= 44,
+	ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT	= 45,
+	ETHTOOL_LINK_MODE_10000baseER_Full_BIT	= 46,
+	ETHTOOL_LINK_MODE_2500baseT_Full_BIT	= 47,
+	ETHTOOL_LINK_MODE_5000baseT_Full_BIT	= 48,
+
+	ETHTOOL_LINK_MODE_FEC_NONE_BIT	= 49,
+	ETHTOOL_LINK_MODE_FEC_RS_BIT	= 50,
+	ETHTOOL_LINK_MODE_FEC_BASER_BIT	= 51,
+	ETHTOOL_LINK_MODE_50000baseKR_Full_BIT		 = 52,
+	ETHTOOL_LINK_MODE_50000baseSR_Full_BIT		 = 53,
+	ETHTOOL_LINK_MODE_50000baseCR_Full_BIT		 = 54,
+	ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT	 = 55,
+	ETHTOOL_LINK_MODE_50000baseDR_Full_BIT		 = 56,
+	ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT	 = 57,
+	ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT	 = 58,
+	ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT	 = 59,
+	ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT = 60,
+	ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT	 = 61,
+	ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT	 = 62,
+	ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT	 = 63,
+	ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT = 64,
+	ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT	 = 65,
+	ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT	 = 66,
+	ETHTOOL_LINK_MODE_100baseT1_Full_BIT		 = 67,
+	ETHTOOL_LINK_MODE_1000baseT1_Full_BIT		 = 68,
+	ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT	 = 69,
+	ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT	 = 70,
+	ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT = 71,
+	ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT	 = 72,
+	ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT	 = 73,
+	ETHTOOL_LINK_MODE_FEC_LLRS_BIT			 = 74,
+	ETHTOOL_LINK_MODE_100000baseKR_Full_BIT		 = 75,
+	ETHTOOL_LINK_MODE_100000baseSR_Full_BIT		 = 76,
+	ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT	 = 77,
+	ETHTOOL_LINK_MODE_100000baseCR_Full_BIT		 = 78,
+	ETHTOOL_LINK_MODE_100000baseDR_Full_BIT		 = 79,
+	ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT	 = 80,
+	ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT	 = 81,
+	ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT = 82,
+	ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT	 = 83,
+	ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT	 = 84,
+	ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT	 = 85,
+	ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT	 = 86,
+	ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT = 87,
+	ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT	 = 88,
+	ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT	 = 89,
+	ETHTOOL_LINK_MODE_100baseFX_Half_BIT		 = 90,
+	ETHTOOL_LINK_MODE_100baseFX_Full_BIT		 = 91,
+	ETHTOOL_LINK_MODE_10baseT1L_Full_BIT		 = 92,
+	ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT	 = 93,
+	ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT	 = 94,
+	ETHTOOL_LINK_MODE_800000baseDR8_Full_BIT	 = 95,
+	ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT	 = 96,
+	ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT	 = 97,
+	ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT	 = 98,
+	ETHTOOL_LINK_MODE_10baseT1S_Full_BIT		 = 99,
+	ETHTOOL_LINK_MODE_10baseT1S_Half_BIT		 = 100,
+	ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT	 = 101,
+
+	/* must be last entry */
+	__ETHTOOL_LINK_MODE_MASK_NBITS
+};
+
+#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name)	\
+	(1UL << (ETHTOOL_LINK_MODE_ ## base_name ## _BIT))
+
+/* DEPRECATED macros. Please migrate to
+ * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT
+ * define any new SUPPORTED_* macro for bits > 31.
+ */
+#define SUPPORTED_10baseT_Half		__ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half)
+#define SUPPORTED_10baseT_Full		__ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full)
+#define SUPPORTED_100baseT_Half		__ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half)
+#define SUPPORTED_100baseT_Full		__ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full)
+#define SUPPORTED_1000baseT_Half	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half)
+#define SUPPORTED_1000baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full)
+#define SUPPORTED_Autoneg		__ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg)
+#define SUPPORTED_TP			__ETHTOOL_LINK_MODE_LEGACY_MASK(TP)
+#define SUPPORTED_AUI			__ETHTOOL_LINK_MODE_LEGACY_MASK(AUI)
+#define SUPPORTED_MII			__ETHTOOL_LINK_MODE_LEGACY_MASK(MII)
+#define SUPPORTED_FIBRE			__ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE)
+#define SUPPORTED_BNC			__ETHTOOL_LINK_MODE_LEGACY_MASK(BNC)
+#define SUPPORTED_10000baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full)
+#define SUPPORTED_Pause			__ETHTOOL_LINK_MODE_LEGACY_MASK(Pause)
+#define SUPPORTED_Asym_Pause		__ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause)
+#define SUPPORTED_2500baseX_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full)
+#define SUPPORTED_Backplane		__ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane)
+#define SUPPORTED_1000baseKX_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full)
+#define SUPPORTED_10000baseKX4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full)
+#define SUPPORTED_10000baseKR_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full)
+#define SUPPORTED_10000baseR_FEC	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC)
+#define SUPPORTED_20000baseMLD2_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full)
+#define SUPPORTED_20000baseKR2_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full)
+#define SUPPORTED_40000baseKR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full)
+#define SUPPORTED_40000baseCR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full)
+#define SUPPORTED_40000baseSR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full)
+#define SUPPORTED_40000baseLR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full)
+#define SUPPORTED_56000baseKR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full)
+#define SUPPORTED_56000baseCR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full)
+#define SUPPORTED_56000baseSR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full)
+#define SUPPORTED_56000baseLR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full)
+/* Please do not define any new SUPPORTED_* macro for bits > 31, see
+ * notice above.
+ */
+
+/*
+ * DEPRECATED macros. Please migrate to
+ * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT
+ * define any new ADERTISE_* macro for bits > 31.
+ */
+#define ADVERTISED_10baseT_Half		__ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half)
+#define ADVERTISED_10baseT_Full		__ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full)
+#define ADVERTISED_100baseT_Half	__ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half)
+#define ADVERTISED_100baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full)
+#define ADVERTISED_1000baseT_Half	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half)
+#define ADVERTISED_1000baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full)
+#define ADVERTISED_Autoneg		__ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg)
+#define ADVERTISED_TP			__ETHTOOL_LINK_MODE_LEGACY_MASK(TP)
+#define ADVERTISED_AUI			__ETHTOOL_LINK_MODE_LEGACY_MASK(AUI)
+#define ADVERTISED_MII			__ETHTOOL_LINK_MODE_LEGACY_MASK(MII)
+#define ADVERTISED_FIBRE		__ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE)
+#define ADVERTISED_BNC			__ETHTOOL_LINK_MODE_LEGACY_MASK(BNC)
+#define ADVERTISED_10000baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full)
+#define ADVERTISED_Pause		__ETHTOOL_LINK_MODE_LEGACY_MASK(Pause)
+#define ADVERTISED_Asym_Pause		__ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause)
+#define ADVERTISED_2500baseX_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full)
+#define ADVERTISED_Backplane		__ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane)
+#define ADVERTISED_1000baseKX_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full)
+#define ADVERTISED_10000baseKX4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full)
+#define ADVERTISED_10000baseKR_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full)
+#define ADVERTISED_10000baseR_FEC	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC)
+#define ADVERTISED_20000baseMLD2_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full)
+#define ADVERTISED_20000baseKR2_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full)
+#define ADVERTISED_40000baseKR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full)
+#define ADVERTISED_40000baseCR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full)
+#define ADVERTISED_40000baseSR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full)
+#define ADVERTISED_40000baseLR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full)
+#define ADVERTISED_56000baseKR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full)
+#define ADVERTISED_56000baseCR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full)
+#define ADVERTISED_56000baseSR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full)
+#define ADVERTISED_56000baseLR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full)
+/* Please do not define any new ADVERTISED_* macro for bits > 31, see
+ * notice above.
+ */
+
+/* The following are all involved in forcing a particular link
+ * mode for the device for setting things.  When getting the
+ * devices settings, these indicate the current mode and whether
+ * it was forced up into this mode or autonegotiated.
+ */
+
+/* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal.
+ * Update drivers/net/phy/phy.c:phy_speed_to_str() and
+ * drivers/net/bonding/bond_3ad.c:__get_link_speed() when adding new values.
+ */
+#define SPEED_10		10
+#define SPEED_100		100
+#define SPEED_1000		1000
+#define SPEED_2500		2500
+#define SPEED_5000		5000
+#define SPEED_10000		10000
+#define SPEED_14000		14000
+#define SPEED_20000		20000
+#define SPEED_25000		25000
+#define SPEED_40000		40000
+#define SPEED_50000		50000
+#define SPEED_56000		56000
+#define SPEED_100000		100000
+#define SPEED_200000		200000
+#define SPEED_400000		400000
+#define SPEED_800000		800000
+
+#define SPEED_UNKNOWN		-1
+
+static inline int ethtool_validate_speed(__u32 speed)
+{
+	return speed <= INT_MAX || speed == (__u32)SPEED_UNKNOWN;
+}
+
+/* Duplex, half or full. */
+#define DUPLEX_HALF		0x00
+#define DUPLEX_FULL		0x01
+#define DUPLEX_UNKNOWN		0xff
+
+static inline int ethtool_validate_duplex(__u8 duplex)
+{
+	switch (duplex) {
+	case DUPLEX_HALF:
+	case DUPLEX_FULL:
+	case DUPLEX_UNKNOWN:
+		return 1;
+	}
+
+	return 0;
+}
+
+#define MASTER_SLAVE_CFG_UNSUPPORTED		0
+#define MASTER_SLAVE_CFG_UNKNOWN		1
+#define MASTER_SLAVE_CFG_MASTER_PREFERRED	2
+#define MASTER_SLAVE_CFG_SLAVE_PREFERRED	3
+#define MASTER_SLAVE_CFG_MASTER_FORCE		4
+#define MASTER_SLAVE_CFG_SLAVE_FORCE		5
+#define MASTER_SLAVE_STATE_UNSUPPORTED		0
+#define MASTER_SLAVE_STATE_UNKNOWN		1
+#define MASTER_SLAVE_STATE_MASTER		2
+#define MASTER_SLAVE_STATE_SLAVE		3
+#define MASTER_SLAVE_STATE_ERR			4
+
+/* These are used to throttle the rate of data on the phy interface when the
+ * native speed of the interface is higher than the link speed. These should
+ * not be used for phy interfaces which natively support multiple speeds (e.g.
+ * MII or SGMII).
+ */
+/* No rate matching performed. */
+#define RATE_MATCH_NONE		0
+/* The phy sends pause frames to throttle the MAC. */
+#define RATE_MATCH_PAUSE	1
+/* The phy asserts CRS to prevent the MAC from transmitting. */
+#define RATE_MATCH_CRS		2
+/* The MAC is programmed with a sufficiently-large IPG. */
+#define RATE_MATCH_OPEN_LOOP	3
+
+/* Which connector port. */
+#define PORT_TP			0x00
+#define PORT_AUI		0x01
+#define PORT_MII		0x02
+#define PORT_FIBRE		0x03
+#define PORT_BNC		0x04
+#define PORT_DA			0x05
+#define PORT_NONE		0xef
+#define PORT_OTHER		0xff
+
+/* Which transceiver to use. */
+#define XCVR_INTERNAL		0x00 /* PHY and MAC are in the same package */
+#define XCVR_EXTERNAL		0x01 /* PHY and MAC are in different packages */
+#define XCVR_DUMMY1		0x02
+#define XCVR_DUMMY2		0x03
+#define XCVR_DUMMY3		0x04
+
+/* Enable or disable autonegotiation. */
+#define AUTONEG_DISABLE		0x00
+#define AUTONEG_ENABLE		0x01
+
+/* MDI or MDI-X status/control - if MDI/MDI_X/AUTO is set then
+ * the driver is required to renegotiate link
+ */
+#define ETH_TP_MDI_INVALID	0x00 /* status: unknown; control: unsupported */
+#define ETH_TP_MDI		0x01 /* status: MDI;     control: force MDI */
+#define ETH_TP_MDI_X		0x02 /* status: MDI-X;   control: force MDI-X */
+#define ETH_TP_MDI_AUTO		0x03 /*                  control: auto-select */
+
+/* Wake-On-Lan options. */
+#define WAKE_PHY		(1 << 0)
+#define WAKE_UCAST		(1 << 1)
+#define WAKE_MCAST		(1 << 2)
+#define WAKE_BCAST		(1 << 3)
+#define WAKE_ARP		(1 << 4)
+#define WAKE_MAGIC		(1 << 5)
+#define WAKE_MAGICSECURE	(1 << 6) /* only meaningful if WAKE_MAGIC */
+#define WAKE_FILTER		(1 << 7)
+
+#define WOL_MODE_COUNT		8
+
+/* RSS hash function data
+ * XOR the corresponding source and destination fields of each specified
+ * protocol. Both copies of the XOR'ed fields are fed into the RSS and RXHASH
+ * calculation. Note that this XORing reduces the input set entropy and could
+ * be exploited to reduce the RSS queue spread.
+ */
+#define	RXH_XFRM_SYM_XOR	(1 << 0)
+#define	RXH_XFRM_NO_CHANGE	0xff
+
+/* L2-L4 network traffic flow types */
+#define	TCP_V4_FLOW	0x01	/* hash or spec (tcp_ip4_spec) */
+#define	UDP_V4_FLOW	0x02	/* hash or spec (udp_ip4_spec) */
+#define	SCTP_V4_FLOW	0x03	/* hash or spec (sctp_ip4_spec) */
+#define	AH_ESP_V4_FLOW	0x04	/* hash only */
+#define	TCP_V6_FLOW	0x05	/* hash or spec (tcp_ip6_spec; nfc only) */
+#define	UDP_V6_FLOW	0x06	/* hash or spec (udp_ip6_spec; nfc only) */
+#define	SCTP_V6_FLOW	0x07	/* hash or spec (sctp_ip6_spec; nfc only) */
+#define	AH_ESP_V6_FLOW	0x08	/* hash only */
+#define	AH_V4_FLOW	0x09	/* hash or spec (ah_ip4_spec) */
+#define	ESP_V4_FLOW	0x0a	/* hash or spec (esp_ip4_spec) */
+#define	AH_V6_FLOW	0x0b	/* hash or spec (ah_ip6_spec; nfc only) */
+#define	ESP_V6_FLOW	0x0c	/* hash or spec (esp_ip6_spec; nfc only) */
+#define	IPV4_USER_FLOW	0x0d	/* spec only (usr_ip4_spec) */
+#define	IP_USER_FLOW	IPV4_USER_FLOW
+#define	IPV6_USER_FLOW	0x0e	/* spec only (usr_ip6_spec; nfc only) */
+#define	IPV4_FLOW	0x10	/* hash only */
+#define	IPV6_FLOW	0x11	/* hash only */
+#define	ETHER_FLOW	0x12	/* spec only (ether_spec) */
+
+/* Used for GTP-U IPv4 and IPv6.
+ * The format of GTP packets only includes
+ * elements such as TEID and GTP version.
+ * It is primarily intended for data communication of the UE.
+ */
+#define GTPU_V4_FLOW 0x13	/* hash only */
+#define GTPU_V6_FLOW 0x14	/* hash only */
+
+/* Use for GTP-C IPv4 and v6.
+ * The format of these GTP packets does not include TEID.
+ * Primarily expected to be used for communication
+ * to create sessions for UE data communication,
+ * commonly referred to as CSR (Create Session Request).
+ */
+#define GTPC_V4_FLOW 0x15	/* hash only */
+#define GTPC_V6_FLOW 0x16	/* hash only */
+
+/* Use for GTP-C IPv4 and v6.
+ * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID.
+ * After session creation, it becomes this packet.
+ * This is mainly used for requests to realize UE handover.
+ */
+#define GTPC_TEID_V4_FLOW 0x17	/* hash only */
+#define GTPC_TEID_V6_FLOW 0x18	/* hash only */
+
+/* Use for GTP-U and extended headers for the PSC (PDU Session Container).
+ * The format of these GTP packets includes TEID and QFI.
+ * In 5G communication using UPF (User Plane Function),
+ * data communication with this extended header is performed.
+ */
+#define GTPU_EH_V4_FLOW 0x19	/* hash only */
+#define GTPU_EH_V6_FLOW 0x1a	/* hash only */
+
+/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers.
+ * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by
+ * UL/DL included in the PSC.
+ * There are differences in the data included based on Downlink/Uplink,
+ * and can be used to distinguish packets.
+ * The functions described so far are useful when you want to
+ * handle communication from the mobile network in UPF, PGW, etc.
+ */
+#define GTPU_UL_V4_FLOW 0x1b	/* hash only */
+#define GTPU_UL_V6_FLOW 0x1c	/* hash only */
+#define GTPU_DL_V4_FLOW 0x1d	/* hash only */
+#define GTPU_DL_V6_FLOW 0x1e	/* hash only */
+
+/* Flag to enable additional fields in struct ethtool_rx_flow_spec */
+#define	FLOW_EXT	0x80000000
+#define	FLOW_MAC_EXT	0x40000000
+/* Flag to enable RSS spreading of traffic matching rule (nfc only) */
+#define	FLOW_RSS	0x20000000
+
+/* L3-L4 network traffic flow hash options */
+#define	RXH_L2DA	(1 << 1)
+#define	RXH_VLAN	(1 << 2)
+#define	RXH_L3_PROTO	(1 << 3)
+#define	RXH_IP_SRC	(1 << 4)
+#define	RXH_IP_DST	(1 << 5)
+#define	RXH_L4_B_0_1	(1 << 6) /* src port in case of TCP/UDP/SCTP */
+#define	RXH_L4_B_2_3	(1 << 7) /* dst port in case of TCP/UDP/SCTP */
+#define	RXH_GTP_TEID	(1 << 8) /* teid in case of GTP */
+#define	RXH_DISCARD	(1 << 31)
+
+#define	RX_CLS_FLOW_DISC	0xffffffffffffffffULL
+#define RX_CLS_FLOW_WAKE	0xfffffffffffffffeULL
+
+/* Special RX classification rule insert location values */
+#define RX_CLS_LOC_SPECIAL	0x80000000	/* flag */
+#define RX_CLS_LOC_ANY		0xffffffff
+#define RX_CLS_LOC_FIRST	0xfffffffe
+#define RX_CLS_LOC_LAST		0xfffffffd
+
+/* EEPROM Standards for plug in modules */
+#define ETH_MODULE_SFF_8079		0x1
+#define ETH_MODULE_SFF_8079_LEN		256
+#define ETH_MODULE_SFF_8472		0x2
+#define ETH_MODULE_SFF_8472_LEN		512
+#define ETH_MODULE_SFF_8636		0x3
+#define ETH_MODULE_SFF_8636_LEN		256
+#define ETH_MODULE_SFF_8436		0x4
+#define ETH_MODULE_SFF_8436_LEN		256
+
+#define ETH_MODULE_SFF_8636_MAX_LEN     640
+#define ETH_MODULE_SFF_8436_MAX_LEN     640
+
+/* Reset flags */
+/* The reset() operation must clear the flags for the components which
+ * were actually reset.  On successful return, the flags indicate the
+ * components which were not reset, either because they do not exist
+ * in the hardware or because they cannot be reset independently.  The
+ * driver must never reset any components that were not requested.
+ */
+enum ethtool_reset_flags {
+	/* These flags represent components dedicated to the interface
+	 * the command is addressed to.  Shift any flag left by
+	 * ETH_RESET_SHARED_SHIFT to reset a shared component of the
+	 * same type.
+	 */
+	ETH_RESET_MGMT		= 1 << 0,	/* Management processor */
+	ETH_RESET_IRQ		= 1 << 1,	/* Interrupt requester */
+	ETH_RESET_DMA		= 1 << 2,	/* DMA engine */
+	ETH_RESET_FILTER	= 1 << 3,	/* Filtering/flow direction */
+	ETH_RESET_OFFLOAD	= 1 << 4,	/* Protocol offload */
+	ETH_RESET_MAC		= 1 << 5,	/* Media access controller */
+	ETH_RESET_PHY		= 1 << 6,	/* Transceiver/PHY */
+	ETH_RESET_RAM		= 1 << 7,	/* RAM shared between
+						 * multiple components */
+	ETH_RESET_AP		= 1 << 8,	/* Application processor */
+
+	ETH_RESET_DEDICATED	= 0x0000ffff,	/* All components dedicated to
+						 * this interface */
+	ETH_RESET_ALL		= 0xffffffff,	/* All components used by this
+						 * interface, even if shared */
+};
+#define ETH_RESET_SHARED_SHIFT	16
+
+
+/**
+ * struct ethtool_link_settings - link control and status
+ *
+ * IMPORTANT, Backward compatibility notice: When implementing new
+ *	user-space tools, please first try %ETHTOOL_GLINKSETTINGS, and
+ *	if it succeeds use %ETHTOOL_SLINKSETTINGS to change link
+ *	settings; do not use %ETHTOOL_SSET if %ETHTOOL_GLINKSETTINGS
+ *	succeeded: stick to %ETHTOOL_GLINKSETTINGS/%SLINKSETTINGS in
+ *	that case.  Conversely, if %ETHTOOL_GLINKSETTINGS fails, use
+ *	%ETHTOOL_GSET to query and %ETHTOOL_SSET to change link
+ *	settings; do not use %ETHTOOL_SLINKSETTINGS if
+ *	%ETHTOOL_GLINKSETTINGS failed: stick to
+ *	%ETHTOOL_GSET/%ETHTOOL_SSET in that case.
+ *
+ * @cmd: Command number = %ETHTOOL_GLINKSETTINGS or %ETHTOOL_SLINKSETTINGS
+ * @speed: Link speed (Mbps)
+ * @duplex: Duplex mode; one of %DUPLEX_*
+ * @port: Physical connector type; one of %PORT_*
+ * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not
+ *	applicable.  For clause 45 PHYs this is the PRTAD.
+ * @autoneg: Enable/disable autonegotiation and auto-detection;
+ *	either %AUTONEG_DISABLE or %AUTONEG_ENABLE
+ * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO
+ *	protocols supported by the interface; 0 if unknown.
+ *	Read-only.
+ * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of
+ *	%ETH_TP_MDI_*.  If the status is unknown or not applicable, the
+ *	value will be %ETH_TP_MDI_INVALID.  Read-only.
+ * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of
+ *	%ETH_TP_MDI_*.  If MDI(-X) control is not implemented, reads
+ *	yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected.
+ *	When written successfully, the link should be renegotiated if
+ *	necessary.
+ * @link_mode_masks_nwords: Number of 32-bit words for each of the
+ *	supported, advertising, lp_advertising link mode bitmaps. For
+ *	%ETHTOOL_GLINKSETTINGS: on entry, number of words passed by user
+ *	(>= 0); on return, if handshake in progress, negative if
+ *	request size unsupported by kernel: absolute value indicates
+ *	kernel expected size and all the other fields but cmd
+ *	are 0; otherwise (handshake completed), strictly positive
+ *	to indicate size used by kernel and cmd field stays
+ *	%ETHTOOL_GLINKSETTINGS, all other fields populated by driver. For
+ *	%ETHTOOL_SLINKSETTINGS: must be valid on entry, ie. a positive
+ *	value returned previously by %ETHTOOL_GLINKSETTINGS, otherwise
+ *	refused. For drivers: ignore this field (use kernel's
+ *	__ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will
+ *	be overwritten by kernel.
+ * @transceiver: Used to distinguish different possible PHY types,
+ *	reported consistently by PHYLIB.  Read-only.
+ * @master_slave_cfg: Master/slave port mode.
+ * @master_slave_state: Master/slave port state.
+ * @rate_matching: Rate adaptation performed by the PHY
+ * @reserved: Reserved for future use; see the note on reserved space.
+ * @link_mode_masks: Variable length bitmaps.
+ *
+ * If autonegotiation is disabled, the speed and @duplex represent the
+ * fixed link mode and are writable if the driver supports multiple
+ * link modes.  If it is enabled then they are read-only; if the link
+ * is up they represent the negotiated link mode; if the link is down,
+ * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and
+ * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode.
+ *
+ * Some hardware interfaces may have multiple PHYs and/or physical
+ * connectors fitted or do not allow the driver to detect which are
+ * fitted.  For these interfaces @port and/or @phy_address may be
+ * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE.
+ * Otherwise, attempts to write different values may be ignored or
+ * rejected.
+ *
+ * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt
+ * are not available in %ethtool_link_settings. These fields will be
+ * always set to zero in %ETHTOOL_GSET reply and %ETHTOOL_SSET will
+ * fail if any of them is set to non-zero value.
+ *
+ * Users should assume that all fields not marked read-only are
+ * writable and subject to validation by the driver.  They should use
+ * %ETHTOOL_GLINKSETTINGS to get the current values before making specific
+ * changes and then applying them with %ETHTOOL_SLINKSETTINGS.
+ *
+ * Drivers that implement %get_link_ksettings and/or
+ * %set_link_ksettings should ignore the @cmd
+ * and @link_mode_masks_nwords fields (any change to them overwritten
+ * by kernel), and rely only on kernel's internal
+ * %__ETHTOOL_LINK_MODE_MASK_NBITS and
+ * %ethtool_link_mode_mask_t. Drivers that implement
+ * %set_link_ksettings() should validate all fields other than @cmd
+ * and @link_mode_masks_nwords that are not described as read-only or
+ * deprecated, and must ignore all fields described as read-only.
+ *
+ * @link_mode_masks is divided into three bitfields, each of length
+ * @link_mode_masks_nwords:
+ * - supported: Bitmap with each bit meaning given by
+ *	%ethtool_link_mode_bit_indices for the link modes, physical
+ *	connectors and other link features for which the interface
+ *	supports autonegotiation or auto-detection.  Read-only.
+ * - advertising: Bitmap with each bit meaning given by
+ *	%ethtool_link_mode_bit_indices for the link modes, physical
+ *	connectors and other link features that are advertised through
+ *	autonegotiation or enabled for auto-detection.
+ * - lp_advertising: Bitmap with each bit meaning given by
+ *	%ethtool_link_mode_bit_indices for the link modes, and other
+ *	link features that the link partner advertised through
+ *	autonegotiation; 0 if unknown or not applicable.  Read-only.
+ */
+struct ethtool_link_settings {
+	__u32	cmd;
+	__u32	speed;
+	__u8	duplex;
+	__u8	port;
+	__u8	phy_address;
+	__u8	autoneg;
+	__u8	mdio_support;
+	__u8	eth_tp_mdix;
+	__u8	eth_tp_mdix_ctrl;
+	__s8	link_mode_masks_nwords;
+	__u8	transceiver;
+	__u8	master_slave_cfg;
+	__u8	master_slave_state;
+	__u8	rate_matching;
+	__u32	reserved[7];
+	__u32	link_mode_masks[];
+	/* layout of link_mode_masks fields:
+	 * __u32 map_supported[link_mode_masks_nwords];
+	 * __u32 map_advertising[link_mode_masks_nwords];
+	 * __u32 map_lp_advertising[link_mode_masks_nwords];
+	 */
+};
 #endif /* _UAPI_LINUX_ETHTOOL_H */
-- 
cgit 


From f91717007217d975aa975ddabd91ae1a107b9bff Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Wed, 3 Apr 2024 14:33:03 +0200
Subject: bpf: Pack struct bpf_fib_lookup

The struct bpf_fib_lookup is supposed to be of size 64. A recent commit
59b418c7063d ("bpf: Add a check for struct bpf_fib_lookup size") added
a static assertion to check this property so that future changes to the
structure will not accidentally break this assumption.

As it immediately turned out, on some 32-bit arm systems, when AEABI=n,
the total size of the structure was equal to 68, see [1]. This happened
because the bpf_fib_lookup structure contains a union of two 16-bit
fields:

    union {
            __u16 tot_len;
            __u16 mtu_result;
    };

which was supposed to compile to a 16-bit-aligned 16-bit field. On the
aforementioned setups it was instead both aligned and padded to 32-bits.

Declare this inner union as __attribute__((packed, aligned(2))) such
that it always is of size 2 and is aligned to 16 bits.

  [1] https://lore.kernel.org/all/CA+G9fYtsoP51f-oP_Sp5MOq-Ffv8La2RztNpwvE6+R1VtFiLrw@mail.gmail.com/#t

Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Fixes: e1850ea9bd9e ("bpf: bpf_fib_lookup return MTU value as output when looked up")
Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240403123303.1452184-1-aspsk@isovalent.com
---
 include/uapi/linux/bpf.h       | 2 +-
 tools/include/uapi/linux/bpf.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 79c548276b6b..6fe9f11c8abe 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7157,7 +7157,7 @@ struct bpf_fib_lookup {
 
 		/* output: MTU value */
 		__u16	mtu_result;
-	};
+	} __attribute__((packed, aligned(2)));
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 79c548276b6b..6fe9f11c8abe 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7157,7 +7157,7 @@ struct bpf_fib_lookup {
 
 		/* output: MTU value */
 		__u16	mtu_result;
-	};
+	} __attribute__((packed, aligned(2)));
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */
-- 
cgit 


From 699c23f02c65cbfc3e638f14ce0d70c23a2e1f02 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Tue, 9 Apr 2024 21:35:27 -0700
Subject: bpf: Add bpf_link support for sk_msg and sk_skb progs

Add bpf_link support for sk_msg and sk_skb programs. We have an
internal request to support bpf_link for sk_msg programs so user
space can have a uniform handling with bpf_link based libbpf
APIs. Using bpf_link based libbpf API also has a benefit which
makes system robust by decoupling prog life cycle and
attachment life cycle.

Reviewed-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20240410043527.3737160-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h            |   6 +
 include/linux/skmsg.h          |   4 +
 include/uapi/linux/bpf.h       |   5 +
 kernel/bpf/syscall.c           |   4 +
 net/core/sock_map.c            | 263 ++++++++++++++++++++++++++++++++++++++---
 tools/include/uapi/linux/bpf.h |   5 +
 6 files changed, 271 insertions(+), 16 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 62762390c93d..5034c1b4ded7 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2996,6 +2996,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
 int sock_map_bpf_prog_query(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr);
+int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog);
 
 void sock_map_unhash(struct sock *sk);
 void sock_map_destroy(struct sock *sk);
@@ -3094,6 +3095,11 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr,
 {
 	return -EINVAL;
 }
+
+static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e65ec3fd2799..9c8dd4c01412 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -58,6 +58,10 @@ struct sk_psock_progs {
 	struct bpf_prog			*stream_parser;
 	struct bpf_prog			*stream_verdict;
 	struct bpf_prog			*skb_verdict;
+	struct bpf_link			*msg_parser_link;
+	struct bpf_link			*stream_parser_link;
+	struct bpf_link			*stream_verdict_link;
+	struct bpf_link			*skb_verdict_link;
 };
 
 enum sk_psock_state_bits {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6fe9f11c8abe..cee0a7915c08 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1135,6 +1135,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	BPF_LINK_TYPE_NETKIT = 13,
+	BPF_LINK_TYPE_SOCKMAP = 14,
 	__MAX_BPF_LINK_TYPE,
 };
 
@@ -6724,6 +6725,10 @@ struct bpf_link_info {
 			__u32 ifindex;
 			__u32 attach_type;
 		} netkit;
+		struct {
+			__u32 map_id;
+			__u32 attach_type;
+		} sockmap;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e44c276e8617..7d392ec83655 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5213,6 +5213,10 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	case BPF_PROG_TYPE_SK_LOOKUP:
 		ret = netns_bpf_link_create(attr, prog);
 		break;
+	case BPF_PROG_TYPE_SK_MSG:
+	case BPF_PROG_TYPE_SK_SKB:
+		ret = sock_map_link_create(attr, prog);
+		break;
 #ifdef CONFIG_NET
 	case BPF_PROG_TYPE_XDP:
 		ret = bpf_xdp_link_attach(attr, prog);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 27d733c0f65e..63c016b4c169 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -24,8 +24,16 @@ struct bpf_stab {
 #define SOCK_CREATE_FLAG_MASK				\
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
 
+/* This mutex is used to
+ *  - protect race between prog/link attach/detach and link prog update, and
+ *  - protect race between releasing and accessing map in bpf_link.
+ * A single global mutex lock is used since it is expected contention is low.
+ */
+static DEFINE_MUTEX(sockmap_mutex);
+
 static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
-				struct bpf_prog *old, u32 which);
+				struct bpf_prog *old, struct bpf_link *link,
+				u32 which);
 static struct sk_psock_progs *sock_map_progs(struct bpf_map *map);
 
 static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
@@ -71,7 +79,9 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-	ret = sock_map_prog_update(map, prog, NULL, attr->attach_type);
+	mutex_lock(&sockmap_mutex);
+	ret = sock_map_prog_update(map, prog, NULL, NULL, attr->attach_type);
+	mutex_unlock(&sockmap_mutex);
 	fdput(f);
 	return ret;
 }
@@ -103,7 +113,9 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
 		goto put_prog;
 	}
 
-	ret = sock_map_prog_update(map, NULL, prog, attr->attach_type);
+	mutex_lock(&sockmap_mutex);
+	ret = sock_map_prog_update(map, NULL, prog, NULL, attr->attach_type);
+	mutex_unlock(&sockmap_mutex);
 put_prog:
 	bpf_prog_put(prog);
 put_map:
@@ -1454,55 +1466,84 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
 	return NULL;
 }
 
-static int sock_map_prog_lookup(struct bpf_map *map, struct bpf_prog ***pprog,
-				u32 which)
+static int sock_map_prog_link_lookup(struct bpf_map *map, struct bpf_prog ***pprog,
+				     struct bpf_link ***plink, u32 which)
 {
 	struct sk_psock_progs *progs = sock_map_progs(map);
+	struct bpf_prog **cur_pprog;
+	struct bpf_link **cur_plink;
 
 	if (!progs)
 		return -EOPNOTSUPP;
 
 	switch (which) {
 	case BPF_SK_MSG_VERDICT:
-		*pprog = &progs->msg_parser;
+		cur_pprog = &progs->msg_parser;
+		cur_plink = &progs->msg_parser_link;
 		break;
 #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
 	case BPF_SK_SKB_STREAM_PARSER:
-		*pprog = &progs->stream_parser;
+		cur_pprog = &progs->stream_parser;
+		cur_plink = &progs->stream_parser_link;
 		break;
 #endif
 	case BPF_SK_SKB_STREAM_VERDICT:
 		if (progs->skb_verdict)
 			return -EBUSY;
-		*pprog = &progs->stream_verdict;
+		cur_pprog = &progs->stream_verdict;
+		cur_plink = &progs->stream_verdict_link;
 		break;
 	case BPF_SK_SKB_VERDICT:
 		if (progs->stream_verdict)
 			return -EBUSY;
-		*pprog = &progs->skb_verdict;
+		cur_pprog = &progs->skb_verdict;
+		cur_plink = &progs->skb_verdict_link;
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
+	*pprog = cur_pprog;
+	if (plink)
+		*plink = cur_plink;
 	return 0;
 }
 
+/* Handle the following four cases:
+ * prog_attach: prog != NULL, old == NULL, link == NULL
+ * prog_detach: prog == NULL, old != NULL, link == NULL
+ * link_attach: prog != NULL, old == NULL, link != NULL
+ * link_detach: prog == NULL, old != NULL, link != NULL
+ */
 static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
-				struct bpf_prog *old, u32 which)
+				struct bpf_prog *old, struct bpf_link *link,
+				u32 which)
 {
 	struct bpf_prog **pprog;
+	struct bpf_link **plink;
 	int ret;
 
-	ret = sock_map_prog_lookup(map, &pprog, which);
+	ret = sock_map_prog_link_lookup(map, &pprog, &plink, which);
 	if (ret)
 		return ret;
 
-	if (old)
-		return psock_replace_prog(pprog, prog, old);
+	/* for prog_attach/prog_detach/link_attach, return error if a bpf_link
+	 * exists for that prog.
+	 */
+	if ((!link || prog) && *plink)
+		return -EBUSY;
 
-	psock_set_prog(pprog, prog);
-	return 0;
+	if (old) {
+		ret = psock_replace_prog(pprog, prog, old);
+		if (!ret)
+			*plink = NULL;
+	} else {
+		psock_set_prog(pprog, prog);
+		if (link)
+			*plink = link;
+	}
+
+	return ret;
 }
 
 int sock_map_bpf_prog_query(const union bpf_attr *attr,
@@ -1527,7 +1568,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr,
 
 	rcu_read_lock();
 
-	ret = sock_map_prog_lookup(map, &pprog, attr->query.attach_type);
+	ret = sock_map_prog_link_lookup(map, &pprog, NULL, attr->query.attach_type);
 	if (ret)
 		goto end;
 
@@ -1657,6 +1698,196 @@ void sock_map_close(struct sock *sk, long timeout)
 }
 EXPORT_SYMBOL_GPL(sock_map_close);
 
+struct sockmap_link {
+	struct bpf_link link;
+	struct bpf_map *map;
+	enum bpf_attach_type attach_type;
+};
+
+static void sock_map_link_release(struct bpf_link *link)
+{
+	struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link);
+
+	mutex_lock(&sockmap_mutex);
+	if (!sockmap_link->map)
+		goto out;
+
+	WARN_ON_ONCE(sock_map_prog_update(sockmap_link->map, NULL, link->prog, link,
+					  sockmap_link->attach_type));
+
+	bpf_map_put_with_uref(sockmap_link->map);
+	sockmap_link->map = NULL;
+out:
+	mutex_unlock(&sockmap_mutex);
+}
+
+static int sock_map_link_detach(struct bpf_link *link)
+{
+	sock_map_link_release(link);
+	return 0;
+}
+
+static void sock_map_link_dealloc(struct bpf_link *link)
+{
+	kfree(link);
+}
+
+/* Handle the following two cases:
+ * case 1: link != NULL, prog != NULL, old != NULL
+ * case 2: link != NULL, prog != NULL, old == NULL
+ */
+static int sock_map_link_update_prog(struct bpf_link *link,
+				     struct bpf_prog *prog,
+				     struct bpf_prog *old)
+{
+	const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link);
+	struct bpf_prog **pprog, *old_link_prog;
+	struct bpf_link **plink;
+	int ret = 0;
+
+	mutex_lock(&sockmap_mutex);
+
+	/* If old prog is not NULL, ensure old prog is the same as link->prog. */
+	if (old && link->prog != old) {
+		ret = -EPERM;
+		goto out;
+	}
+	/* Ensure link->prog has the same type/attach_type as the new prog. */
+	if (link->prog->type != prog->type ||
+	    link->prog->expected_attach_type != prog->expected_attach_type) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink,
+					sockmap_link->attach_type);
+	if (ret)
+		goto out;
+
+	/* return error if the stored bpf_link does not match the incoming bpf_link. */
+	if (link != *plink) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (old) {
+		ret = psock_replace_prog(pprog, prog, old);
+		if (ret)
+			goto out;
+	} else {
+		psock_set_prog(pprog, prog);
+	}
+
+	bpf_prog_inc(prog);
+	old_link_prog = xchg(&link->prog, prog);
+	bpf_prog_put(old_link_prog);
+
+out:
+	mutex_unlock(&sockmap_mutex);
+	return ret;
+}
+
+static u32 sock_map_link_get_map_id(const struct sockmap_link *sockmap_link)
+{
+	u32 map_id = 0;
+
+	mutex_lock(&sockmap_mutex);
+	if (sockmap_link->map)
+		map_id = sockmap_link->map->id;
+	mutex_unlock(&sockmap_mutex);
+	return map_id;
+}
+
+static int sock_map_link_fill_info(const struct bpf_link *link,
+				   struct bpf_link_info *info)
+{
+	const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link);
+	u32 map_id = sock_map_link_get_map_id(sockmap_link);
+
+	info->sockmap.map_id = map_id;
+	info->sockmap.attach_type = sockmap_link->attach_type;
+	return 0;
+}
+
+static void sock_map_link_show_fdinfo(const struct bpf_link *link,
+				      struct seq_file *seq)
+{
+	const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link);
+	u32 map_id = sock_map_link_get_map_id(sockmap_link);
+
+	seq_printf(seq, "map_id:\t%u\n", map_id);
+	seq_printf(seq, "attach_type:\t%u\n", sockmap_link->attach_type);
+}
+
+static const struct bpf_link_ops sock_map_link_ops = {
+	.release = sock_map_link_release,
+	.dealloc = sock_map_link_dealloc,
+	.detach = sock_map_link_detach,
+	.update_prog = sock_map_link_update_prog,
+	.fill_link_info = sock_map_link_fill_info,
+	.show_fdinfo = sock_map_link_show_fdinfo,
+};
+
+int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	struct bpf_link_primer link_primer;
+	struct sockmap_link *sockmap_link;
+	enum bpf_attach_type attach_type;
+	struct bpf_map *map;
+	int ret;
+
+	if (attr->link_create.flags)
+		return -EINVAL;
+
+	map = bpf_map_get_with_uref(attr->link_create.target_fd);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+	if (map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	sockmap_link = kzalloc(sizeof(*sockmap_link), GFP_USER);
+	if (!sockmap_link) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	attach_type = attr->link_create.attach_type;
+	bpf_link_init(&sockmap_link->link, BPF_LINK_TYPE_SOCKMAP, &sock_map_link_ops, prog);
+	sockmap_link->map = map;
+	sockmap_link->attach_type = attach_type;
+
+	ret = bpf_link_prime(&sockmap_link->link, &link_primer);
+	if (ret) {
+		kfree(sockmap_link);
+		goto out;
+	}
+
+	mutex_lock(&sockmap_mutex);
+	ret = sock_map_prog_update(map, prog, NULL, &sockmap_link->link, attach_type);
+	mutex_unlock(&sockmap_mutex);
+	if (ret) {
+		bpf_link_cleanup(&link_primer);
+		goto out;
+	}
+
+	/* Increase refcnt for the prog since when old prog is replaced with
+	 * psock_replace_prog() and psock_set_prog() its refcnt will be decreased.
+	 *
+	 * Actually, we do not need to increase refcnt for the prog since bpf_link
+	 * will hold a reference. But in order to have less complexity w.r.t.
+	 * replacing/setting prog, let us increase the refcnt to make things simpler.
+	 */
+	bpf_prog_inc(prog);
+
+	return bpf_link_settle(&link_primer);
+
+out:
+	bpf_map_put_with_uref(map);
+	return ret;
+}
+
 static int sock_map_iter_attach_target(struct bpf_prog *prog,
 				       union bpf_iter_link_info *linfo,
 				       struct bpf_iter_aux_info *aux)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6fe9f11c8abe..cee0a7915c08 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1135,6 +1135,7 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	BPF_LINK_TYPE_NETKIT = 13,
+	BPF_LINK_TYPE_SOCKMAP = 14,
 	__MAX_BPF_LINK_TYPE,
 };
 
@@ -6724,6 +6725,10 @@ struct bpf_link_info {
 			__u32 ifindex;
 			__u32 attach_type;
 		} netkit;
+		struct {
+			__u32 map_id;
+			__u32 attach_type;
+		} sockmap;
 	};
 } __attribute__((aligned(8)));
 
-- 
cgit 


From 61ba075d9911d2a6db181fbb5602762a24d5d0a9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 18 Apr 2024 18:15:33 -0300
Subject: Revert "tools headers: Remove almost unused copy of uapi/stat.h, add
 few conditional defines"

This reverts commit a672af9139a843eb7a48fd7846bb6df8f81b5f86.

By now it is not used for building tools/perf, but Stephen Rothwell
reported that when building on a O= directory that had been built with
torvalds/master and this perf build command line:

  $ make -C tools/perf -f Makefile.perf -s -O -j60 O=/home/sfr/next/perf NO_BPF_SKEL=1

If we then merge perf-tools-next, as he did for linux-next, then we end
up with a build failure for libbpf:

    PERF_VERSION = 6.9.rc3.g42c4635c8dee
  make[3]: *** No rule to make target '/home/sfr/next/next/tools/include/uapi/linux/stat.h', needed by '/home/sfr/next/perf/libbpf/staticobjs/libbpf.o'.  Stop.
  make[2]: *** [Makefile:157: /home/sfr/next/perf/libbpf/staticobjs/libbpf-in.o] Error 2
  make[1]: *** [Makefile.perf:892: /home/sfr/next/perf/libbpf/libbpf.a] Error 2
  make[1]: *** Waiting for unfinished jobs....
  make: *** [Makefile.perf:264: sub-make] Error 2

This needs to be further investigated to figure out how to check if
libbpf really needs something that is in that
tools/include/uapi/linux/stat.h file and if not to remove that file in a
way that we don't break the build in any situation, to avoid requiring
doing a 'make clean'.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Tested-by: Stephen Rothwell <sfr@canb.auug.org.au> # PowerPC le incermental build
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/20240413124340.4d48c6d8@canb.auug.org.au
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/stat.h | 195 ++++++++++++++++++++++++++++++++++++++++
 tools/perf/check-headers.sh     |   1 +
 2 files changed, 196 insertions(+)
 create mode 100644 tools/include/uapi/linux/stat.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
new file mode 100644
index 000000000000..2f2ee82d5517
--- /dev/null
+++ b/tools/include/uapi/linux/stat.h
@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_STAT_H
+#define _UAPI_LINUX_STAT_H
+
+#include <linux/types.h>
+
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+
+#define S_IFMT  00170000
+#define S_IFSOCK 0140000
+#define S_IFLNK	 0120000
+#define S_IFREG  0100000
+#define S_IFBLK  0060000
+#define S_IFDIR  0040000
+#define S_IFCHR  0020000
+#define S_IFIFO  0010000
+#define S_ISUID  0004000
+#define S_ISGID  0002000
+#define S_ISVTX  0001000
+
+#define S_ISLNK(m)	(((m) & S_IFMT) == S_IFLNK)
+#define S_ISREG(m)	(((m) & S_IFMT) == S_IFREG)
+#define S_ISDIR(m)	(((m) & S_IFMT) == S_IFDIR)
+#define S_ISCHR(m)	(((m) & S_IFMT) == S_IFCHR)
+#define S_ISBLK(m)	(((m) & S_IFMT) == S_IFBLK)
+#define S_ISFIFO(m)	(((m) & S_IFMT) == S_IFIFO)
+#define S_ISSOCK(m)	(((m) & S_IFMT) == S_IFSOCK)
+
+#define S_IRWXU 00700
+#define S_IRUSR 00400
+#define S_IWUSR 00200
+#define S_IXUSR 00100
+
+#define S_IRWXG 00070
+#define S_IRGRP 00040
+#define S_IWGRP 00020
+#define S_IXGRP 00010
+
+#define S_IRWXO 00007
+#define S_IROTH 00004
+#define S_IWOTH 00002
+#define S_IXOTH 00001
+
+#endif
+
+/*
+ * Timestamp structure for the timestamps in struct statx.
+ *
+ * tv_sec holds the number of seconds before (negative) or after (positive)
+ * 00:00:00 1st January 1970 UTC.
+ *
+ * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time.
+ *
+ * __reserved is held in case we need a yet finer resolution.
+ */
+struct statx_timestamp {
+	__s64	tv_sec;
+	__u32	tv_nsec;
+	__s32	__reserved;
+};
+
+/*
+ * Structures for the extended file attribute retrieval system call
+ * (statx()).
+ *
+ * The caller passes a mask of what they're specifically interested in as a
+ * parameter to statx().  What statx() actually got will be indicated in
+ * st_mask upon return.
+ *
+ * For each bit in the mask argument:
+ *
+ * - if the datum is not supported:
+ *
+ *   - the bit will be cleared, and
+ *
+ *   - the datum will be set to an appropriate fabricated value if one is
+ *     available (eg. CIFS can take a default uid and gid), otherwise
+ *
+ *   - the field will be cleared;
+ *
+ * - otherwise, if explicitly requested:
+ *
+ *   - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is
+ *     set or if the datum is considered out of date, and
+ *
+ *   - the field will be filled in and the bit will be set;
+ *
+ * - otherwise, if not requested, but available in approximate form without any
+ *   effort, it will be filled in anyway, and the bit will be set upon return
+ *   (it might not be up to date, however, and no attempt will be made to
+ *   synchronise the internal state first);
+ *
+ * - otherwise the field and the bit will be cleared before returning.
+ *
+ * Items in STATX_BASIC_STATS may be marked unavailable on return, but they
+ * will have values installed for compatibility purposes so that stat() and
+ * co. can be emulated in userspace.
+ */
+struct statx {
+	/* 0x00 */
+	__u32	stx_mask;	/* What results were written [uncond] */
+	__u32	stx_blksize;	/* Preferred general I/O size [uncond] */
+	__u64	stx_attributes;	/* Flags conveying information about the file [uncond] */
+	/* 0x10 */
+	__u32	stx_nlink;	/* Number of hard links */
+	__u32	stx_uid;	/* User ID of owner */
+	__u32	stx_gid;	/* Group ID of owner */
+	__u16	stx_mode;	/* File mode */
+	__u16	__spare0[1];
+	/* 0x20 */
+	__u64	stx_ino;	/* Inode number */
+	__u64	stx_size;	/* File size */
+	__u64	stx_blocks;	/* Number of 512-byte blocks allocated */
+	__u64	stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
+	/* 0x40 */
+	struct statx_timestamp	stx_atime;	/* Last access time */
+	struct statx_timestamp	stx_btime;	/* File creation time */
+	struct statx_timestamp	stx_ctime;	/* Last attribute change time */
+	struct statx_timestamp	stx_mtime;	/* Last data modification time */
+	/* 0x80 */
+	__u32	stx_rdev_major;	/* Device ID of special file [if bdev/cdev] */
+	__u32	stx_rdev_minor;
+	__u32	stx_dev_major;	/* ID of device containing file [uncond] */
+	__u32	stx_dev_minor;
+	/* 0x90 */
+	__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 */
+	/* 0xa0 */
+	__u64	__spare3[12];	/* Spare space for future expansion */
+	/* 0x100 */
+};
+
+/*
+ * Flags to be stx_mask
+ *
+ * Query request/result mask for statx() and struct statx::stx_mask.
+ *
+ * These bits should be set in the mask argument of statx() to request
+ * particular items when calling statx().
+ */
+#define STATX_TYPE		0x00000001U	/* Want/got stx_mode & S_IFMT */
+#define STATX_MODE		0x00000002U	/* Want/got stx_mode & ~S_IFMT */
+#define STATX_NLINK		0x00000004U	/* Want/got stx_nlink */
+#define STATX_UID		0x00000008U	/* Want/got stx_uid */
+#define STATX_GID		0x00000010U	/* Want/got stx_gid */
+#define STATX_ATIME		0x00000020U	/* Want/got stx_atime */
+#define STATX_MTIME		0x00000040U	/* Want/got stx_mtime */
+#define STATX_CTIME		0x00000080U	/* Want/got stx_ctime */
+#define STATX_INO		0x00000100U	/* Want/got stx_ino */
+#define STATX_SIZE		0x00000200U	/* Want/got stx_size */
+#define STATX_BLOCKS		0x00000400U	/* Want/got stx_blocks */
+#define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
+#define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
+#define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
+#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__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
+
+#ifndef __KERNEL__
+/*
+ * This is deprecated, and shall remain the same value in the future.  To avoid
+ * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME)
+ * instead.
+ */
+#define STATX_ALL		0x00000fffU
+#endif
+
+/*
+ * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
+ *
+ * These give information about the features or the state of a file that might
+ * be of use to ordinary userspace programs such as GUIs or ls rather than
+ * specialised tools.
+ *
+ * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags
+ * semantically.  Where possible, the numerical value is picked to correspond
+ * also.  Note that the DAX attribute indicates that the file is in the CPU
+ * direct access state.  It does not correspond to the per-inode flag that
+ * some filesystems support.
+ *
+ */
+#define STATX_ATTR_COMPRESSED		0x00000004 /* [I] File is compressed by the fs */
+#define STATX_ATTR_IMMUTABLE		0x00000010 /* [I] File is marked immutable */
+#define STATX_ATTR_APPEND		0x00000020 /* [I] File is append-only */
+#define STATX_ATTR_NODUMP		0x00000040 /* [I] File is not to be dumped */
+#define STATX_ATTR_ENCRYPTED		0x00000800 /* [I] File requires key to decrypt in fs */
+#define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
+#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 */
+
+
+#endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 95a3a404bc6f..9c84fd049070 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -16,6 +16,7 @@ FILES=(
   "include/uapi/linux/in.h"
   "include/uapi/linux/perf_event.h"
   "include/uapi/linux/seccomp.h"
+  "include/uapi/linux/stat.h"
   "include/linux/bits.h"
   "include/vdso/bits.h"
   "include/linux/const.h"
-- 
cgit 


From f1d0a2fbb0088675cceeab73d1f4b4308b289984 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <bentiss@kernel.org>
Date: Sat, 20 Apr 2024 11:09:06 +0200
Subject: tools: sync include/uapi/linux/bpf.h

cp include/uapi/linux/bpf.h tools/include/uapi/linux/bpf.h

Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
Link: https://lore.kernel.org/r/20240420-bpf_wq-v2-6-6c986a5a741f@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index cee0a7915c08..e4ae83550fb3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7306,6 +7306,10 @@ struct bpf_timer {
 	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
+struct bpf_wq {
+	__u64 __opaque[2];
+} __attribute__((aligned(8)));
+
 struct bpf_dynptr {
 	__u64 __opaque[2];
 } __attribute__((aligned(8)));
-- 
cgit 


From 48e2cd3e3dcfe04f212df4fb189fa04c2a87b980 Mon Sep 17 00:00:00 2001
From: Philo Lu <lulie@linux.alibaba.com>
Date: Fri, 26 Apr 2024 00:17:23 +0800
Subject: bpf: add mrtt and srtt as BPF_SOCK_OPS_RTT_CB args

Two important arguments in RTT estimation, mrtt and srtt, are passed to
tcp_bpf_rtt(), so that bpf programs get more information about RTT
computation in BPF_SOCK_OPS_RTT_CB.

The difference between bpf_sock_ops->srtt_us and the srtt here is: the
former is an old rtt before update, while srtt passed by tcp_bpf_rtt()
is that after update.

Signed-off-by: Philo Lu <lulie@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240425161724.73707-2-lulie@linux.alibaba.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/net/tcp.h              | 4 ++--
 include/uapi/linux/bpf.h       | 2 ++
 net/ipv4/tcp_input.c           | 4 ++--
 tools/include/uapi/linux/bpf.h | 2 ++
 4 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ae35199d3b3..0f75d03287c2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2706,10 +2706,10 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk)
 	return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1);
 }
 
-static inline void tcp_bpf_rtt(struct sock *sk)
+static inline void tcp_bpf_rtt(struct sock *sk, long mrtt, u32 srtt)
 {
 	if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG))
-		tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL);
+		tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RTT_CB, mrtt, srtt);
 }
 
 #if IS_ENABLED(CONFIG_SMC)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e4ae83550fb3..d94a72593ead 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6947,6 +6947,8 @@ enum {
 					 * socket transition to LISTEN state.
 					 */
 	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
+					 * Arg1: measured RTT input (mrtt)
+					 * Arg2: updated srtt
 					 */
 	BPF_SOCK_OPS_PARSE_HDR_OPT_CB,	/* Parse the header option.
 					 * It will be called to handle
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5d874817a78d..d1115d7c3936 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -911,7 +911,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 			tp->rtt_seq = tp->snd_nxt;
 			tp->mdev_max_us = tcp_rto_min_us(sk);
 
-			tcp_bpf_rtt(sk);
+			tcp_bpf_rtt(sk, mrtt_us, srtt);
 		}
 	} else {
 		/* no previous measure. */
@@ -921,7 +921,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 		tp->mdev_max_us = tp->rttvar_us;
 		tp->rtt_seq = tp->snd_nxt;
 
-		tcp_bpf_rtt(sk);
+		tcp_bpf_rtt(sk, mrtt_us, srtt);
 	}
 	tp->srtt_us = max(1U, srtt);
 }
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e4ae83550fb3..d94a72593ead 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6947,6 +6947,8 @@ enum {
 					 * socket transition to LISTEN state.
 					 */
 	BPF_SOCK_OPS_RTT_CB,		/* Called on every RTT.
+					 * Arg1: measured RTT input (mrtt)
+					 * Arg2: updated srtt
 					 */
 	BPF_SOCK_OPS_PARSE_HDR_OPT_CB,	/* Parse the header option.
 					 * It will be called to handle
-- 
cgit 


From 580ea358af0ade1176326e76edcf60dd50938808 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Wed, 27 Mar 2024 20:34:18 -0700
Subject: selftests/mm: fix additional build errors for selftests

These build errors only occur if one fails to first run "make headers".
However, that is a non-obvious and instrusive requirement, and so there
was a discussion on how to get rid of it [1].  This uses that solution.

These two files were created by taking a snapshot of the generated header
files that are created via "make headers".  These two files were copied
from ./usr/include/linux/ to ./tools/include/uapi/linux/ .

That fixes the selftests/mm build on today's Arch Linux (which required
the userfaultfd.h) and Ubuntu 23.04 (which additionally required memfd.h).

[1] https://lore.kernel.org/all/783a4178-1dec-4e30-989a-5174b8176b09@redhat.com/

Link: https://lkml.kernel.org/r/20240328033418.203790-3-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/include/uapi/linux/memfd.h       |  39 ++++
 tools/include/uapi/linux/userfaultfd.h | 386 +++++++++++++++++++++++++++++++++
 2 files changed, 425 insertions(+)
 create mode 100644 tools/include/uapi/linux/memfd.h
 create mode 100644 tools/include/uapi/linux/userfaultfd.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/memfd.h b/tools/include/uapi/linux/memfd.h
new file mode 100644
index 000000000000..01c0324e7733
--- /dev/null
+++ b/tools/include/uapi/linux/memfd.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_MEMFD_H
+#define _LINUX_MEMFD_H
+
+#include <asm-generic/hugetlb_encode.h>
+
+/* flags for memfd_create(2) (unsigned int) */
+#define MFD_CLOEXEC		0x0001U
+#define MFD_ALLOW_SEALING	0x0002U
+#define MFD_HUGETLB		0x0004U
+/* not executable and sealed to prevent changing to executable. */
+#define MFD_NOEXEC_SEAL		0x0008U
+/* executable */
+#define MFD_EXEC		0x0010U
+
+/*
+ * Huge page size encoding when MFD_HUGETLB is specified, and a huge page
+ * size other than the default is desired.  See hugetlb_encode.h.
+ * All known huge page size encodings are provided here.  It is the
+ * responsibility of the application to know which sizes are supported on
+ * the running system.  See mmap(2) man page for details.
+ */
+#define MFD_HUGE_SHIFT	HUGETLB_FLAG_ENCODE_SHIFT
+#define MFD_HUGE_MASK	HUGETLB_FLAG_ENCODE_MASK
+
+#define MFD_HUGE_64KB	HUGETLB_FLAG_ENCODE_64KB
+#define MFD_HUGE_512KB	HUGETLB_FLAG_ENCODE_512KB
+#define MFD_HUGE_1MB	HUGETLB_FLAG_ENCODE_1MB
+#define MFD_HUGE_2MB	HUGETLB_FLAG_ENCODE_2MB
+#define MFD_HUGE_8MB	HUGETLB_FLAG_ENCODE_8MB
+#define MFD_HUGE_16MB	HUGETLB_FLAG_ENCODE_16MB
+#define MFD_HUGE_32MB	HUGETLB_FLAG_ENCODE_32MB
+#define MFD_HUGE_256MB	HUGETLB_FLAG_ENCODE_256MB
+#define MFD_HUGE_512MB	HUGETLB_FLAG_ENCODE_512MB
+#define MFD_HUGE_1GB	HUGETLB_FLAG_ENCODE_1GB
+#define MFD_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
+#define MFD_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
+
+#endif /* _LINUX_MEMFD_H */
diff --git a/tools/include/uapi/linux/userfaultfd.h b/tools/include/uapi/linux/userfaultfd.h
new file mode 100644
index 000000000000..4283de22d5b6
--- /dev/null
+++ b/tools/include/uapi/linux/userfaultfd.h
@@ -0,0 +1,386 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ *  include/linux/userfaultfd.h
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
+ *  Copyright (C) 2015  Red Hat, Inc.
+ *
+ */
+
+#ifndef _LINUX_USERFAULTFD_H
+#define _LINUX_USERFAULTFD_H
+
+#include <linux/types.h>
+
+/* ioctls for /dev/userfaultfd */
+#define USERFAULTFD_IOC 0xAA
+#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00)
+
+/*
+ * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and
+ * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR.  In
+ * userfaultfd.h we assumed the kernel was reading (instead _IOC_READ
+ * means the userland is reading).
+ */
+#define UFFD_API ((__u64)0xAA)
+#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING |	\
+				 UFFDIO_REGISTER_MODE_WP |	\
+				 UFFDIO_REGISTER_MODE_MINOR)
+#define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP |	\
+			   UFFD_FEATURE_EVENT_FORK |		\
+			   UFFD_FEATURE_EVENT_REMAP |		\
+			   UFFD_FEATURE_EVENT_REMOVE |		\
+			   UFFD_FEATURE_EVENT_UNMAP |		\
+			   UFFD_FEATURE_MISSING_HUGETLBFS |	\
+			   UFFD_FEATURE_MISSING_SHMEM |		\
+			   UFFD_FEATURE_SIGBUS |		\
+			   UFFD_FEATURE_THREAD_ID |		\
+			   UFFD_FEATURE_MINOR_HUGETLBFS |	\
+			   UFFD_FEATURE_MINOR_SHMEM |		\
+			   UFFD_FEATURE_EXACT_ADDRESS |		\
+			   UFFD_FEATURE_WP_HUGETLBFS_SHMEM |	\
+			   UFFD_FEATURE_WP_UNPOPULATED |	\
+			   UFFD_FEATURE_POISON |		\
+			   UFFD_FEATURE_WP_ASYNC |		\
+			   UFFD_FEATURE_MOVE)
+#define UFFD_API_IOCTLS				\
+	((__u64)1 << _UFFDIO_REGISTER |		\
+	 (__u64)1 << _UFFDIO_UNREGISTER |	\
+	 (__u64)1 << _UFFDIO_API)
+#define UFFD_API_RANGE_IOCTLS			\
+	((__u64)1 << _UFFDIO_WAKE |		\
+	 (__u64)1 << _UFFDIO_COPY |		\
+	 (__u64)1 << _UFFDIO_ZEROPAGE |		\
+	 (__u64)1 << _UFFDIO_MOVE |		\
+	 (__u64)1 << _UFFDIO_WRITEPROTECT |	\
+	 (__u64)1 << _UFFDIO_CONTINUE |		\
+	 (__u64)1 << _UFFDIO_POISON)
+#define UFFD_API_RANGE_IOCTLS_BASIC		\
+	((__u64)1 << _UFFDIO_WAKE |		\
+	 (__u64)1 << _UFFDIO_COPY |		\
+	 (__u64)1 << _UFFDIO_WRITEPROTECT |	\
+	 (__u64)1 << _UFFDIO_CONTINUE |		\
+	 (__u64)1 << _UFFDIO_POISON)
+
+/*
+ * Valid ioctl command number range with this API is from 0x00 to
+ * 0x3F.  UFFDIO_API is the fixed number, everything else can be
+ * changed by implementing a different UFFD_API. If sticking to the
+ * same UFFD_API more ioctl can be added and userland will be aware of
+ * which ioctl the running kernel implements through the ioctl command
+ * bitmask written by the UFFDIO_API.
+ */
+#define _UFFDIO_REGISTER		(0x00)
+#define _UFFDIO_UNREGISTER		(0x01)
+#define _UFFDIO_WAKE			(0x02)
+#define _UFFDIO_COPY			(0x03)
+#define _UFFDIO_ZEROPAGE		(0x04)
+#define _UFFDIO_MOVE			(0x05)
+#define _UFFDIO_WRITEPROTECT		(0x06)
+#define _UFFDIO_CONTINUE		(0x07)
+#define _UFFDIO_POISON			(0x08)
+#define _UFFDIO_API			(0x3F)
+
+/* userfaultfd ioctl ids */
+#define UFFDIO 0xAA
+#define UFFDIO_API		_IOWR(UFFDIO, _UFFDIO_API,	\
+				      struct uffdio_api)
+#define UFFDIO_REGISTER		_IOWR(UFFDIO, _UFFDIO_REGISTER, \
+				      struct uffdio_register)
+#define UFFDIO_UNREGISTER	_IOR(UFFDIO, _UFFDIO_UNREGISTER,	\
+				     struct uffdio_range)
+#define UFFDIO_WAKE		_IOR(UFFDIO, _UFFDIO_WAKE,	\
+				     struct uffdio_range)
+#define UFFDIO_COPY		_IOWR(UFFDIO, _UFFDIO_COPY,	\
+				      struct uffdio_copy)
+#define UFFDIO_ZEROPAGE		_IOWR(UFFDIO, _UFFDIO_ZEROPAGE,	\
+				      struct uffdio_zeropage)
+#define UFFDIO_MOVE		_IOWR(UFFDIO, _UFFDIO_MOVE,	\
+				      struct uffdio_move)
+#define UFFDIO_WRITEPROTECT	_IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
+				      struct uffdio_writeprotect)
+#define UFFDIO_CONTINUE		_IOWR(UFFDIO, _UFFDIO_CONTINUE,	\
+				      struct uffdio_continue)
+#define UFFDIO_POISON		_IOWR(UFFDIO, _UFFDIO_POISON, \
+				      struct uffdio_poison)
+
+/* read() structure */
+struct uffd_msg {
+	__u8	event;
+
+	__u8	reserved1;
+	__u16	reserved2;
+	__u32	reserved3;
+
+	union {
+		struct {
+			__u64	flags;
+			__u64	address;
+			union {
+				__u32 ptid;
+			} feat;
+		} pagefault;
+
+		struct {
+			__u32	ufd;
+		} fork;
+
+		struct {
+			__u64	from;
+			__u64	to;
+			__u64	len;
+		} remap;
+
+		struct {
+			__u64	start;
+			__u64	end;
+		} remove;
+
+		struct {
+			/* unused reserved fields */
+			__u64	reserved1;
+			__u64	reserved2;
+			__u64	reserved3;
+		} reserved;
+	} arg;
+} __attribute__((packed));
+
+/*
+ * Start at 0x12 and not at 0 to be more strict against bugs.
+ */
+#define UFFD_EVENT_PAGEFAULT	0x12
+#define UFFD_EVENT_FORK		0x13
+#define UFFD_EVENT_REMAP	0x14
+#define UFFD_EVENT_REMOVE	0x15
+#define UFFD_EVENT_UNMAP	0x16
+
+/* flags for UFFD_EVENT_PAGEFAULT */
+#define UFFD_PAGEFAULT_FLAG_WRITE	(1<<0)	/* If this was a write fault */
+#define UFFD_PAGEFAULT_FLAG_WP		(1<<1)	/* If reason is VM_UFFD_WP */
+#define UFFD_PAGEFAULT_FLAG_MINOR	(1<<2)	/* If reason is VM_UFFD_MINOR */
+
+struct uffdio_api {
+	/* userland asks for an API number and the features to enable */
+	__u64 api;
+	/*
+	 * Kernel answers below with the all available features for
+	 * the API, this notifies userland of which events and/or
+	 * which flags for each event are enabled in the current
+	 * kernel.
+	 *
+	 * Note: UFFD_EVENT_PAGEFAULT and UFFD_PAGEFAULT_FLAG_WRITE
+	 * are to be considered implicitly always enabled in all kernels as
+	 * long as the uffdio_api.api requested matches UFFD_API.
+	 *
+	 * UFFD_FEATURE_MISSING_HUGETLBFS means an UFFDIO_REGISTER
+	 * with UFFDIO_REGISTER_MODE_MISSING mode will succeed on
+	 * hugetlbfs virtual memory ranges. Adding or not adding
+	 * UFFD_FEATURE_MISSING_HUGETLBFS to uffdio_api.features has
+	 * no real functional effect after UFFDIO_API returns, but
+	 * it's only useful for an initial feature set probe at
+	 * UFFDIO_API time. There are two ways to use it:
+	 *
+	 * 1) by adding UFFD_FEATURE_MISSING_HUGETLBFS to the
+	 *    uffdio_api.features before calling UFFDIO_API, an error
+	 *    will be returned by UFFDIO_API on a kernel without
+	 *    hugetlbfs missing support
+	 *
+	 * 2) the UFFD_FEATURE_MISSING_HUGETLBFS can not be added in
+	 *    uffdio_api.features and instead it will be set by the
+	 *    kernel in the uffdio_api.features if the kernel supports
+	 *    it, so userland can later check if the feature flag is
+	 *    present in uffdio_api.features after UFFDIO_API
+	 *    succeeded.
+	 *
+	 * UFFD_FEATURE_MISSING_SHMEM works the same as
+	 * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem
+	 * (i.e. tmpfs and other shmem based APIs).
+	 *
+	 * UFFD_FEATURE_SIGBUS feature means no page-fault
+	 * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead
+	 * a SIGBUS signal will be sent to the faulting process.
+	 *
+	 * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will
+	 * be returned, if feature is not requested 0 will be returned.
+	 *
+	 * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults
+	 * can be intercepted (via REGISTER_MODE_MINOR) for
+	 * hugetlbfs-backed pages.
+	 *
+	 * UFFD_FEATURE_MINOR_SHMEM indicates the same support as
+	 * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead.
+	 *
+	 * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page
+	 * faults would be provided and the offset within the page would not be
+	 * masked.
+	 *
+	 * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd
+	 * write-protection mode is supported on both shmem and hugetlbfs.
+	 *
+	 * UFFD_FEATURE_WP_UNPOPULATED indicates that userfaultfd
+	 * write-protection mode will always apply to unpopulated pages
+	 * (i.e. empty ptes).  This will be the default behavior for shmem
+	 * & hugetlbfs, so this flag only affects anonymous memory behavior
+	 * when userfault write-protection mode is registered.
+	 *
+	 * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection
+	 * asynchronous mode is supported in which the write fault is
+	 * automatically resolved and write-protection is un-set.
+	 * It implies UFFD_FEATURE_WP_UNPOPULATED.
+	 *
+	 * UFFD_FEATURE_MOVE indicates that the kernel supports moving an
+	 * existing page contents from userspace.
+	 */
+#define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
+#define UFFD_FEATURE_EVENT_FORK			(1<<1)
+#define UFFD_FEATURE_EVENT_REMAP		(1<<2)
+#define UFFD_FEATURE_EVENT_REMOVE		(1<<3)
+#define UFFD_FEATURE_MISSING_HUGETLBFS		(1<<4)
+#define UFFD_FEATURE_MISSING_SHMEM		(1<<5)
+#define UFFD_FEATURE_EVENT_UNMAP		(1<<6)
+#define UFFD_FEATURE_SIGBUS			(1<<7)
+#define UFFD_FEATURE_THREAD_ID			(1<<8)
+#define UFFD_FEATURE_MINOR_HUGETLBFS		(1<<9)
+#define UFFD_FEATURE_MINOR_SHMEM		(1<<10)
+#define UFFD_FEATURE_EXACT_ADDRESS		(1<<11)
+#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM		(1<<12)
+#define UFFD_FEATURE_WP_UNPOPULATED		(1<<13)
+#define UFFD_FEATURE_POISON			(1<<14)
+#define UFFD_FEATURE_WP_ASYNC			(1<<15)
+#define UFFD_FEATURE_MOVE			(1<<16)
+	__u64 features;
+
+	__u64 ioctls;
+};
+
+struct uffdio_range {
+	__u64 start;
+	__u64 len;
+};
+
+struct uffdio_register {
+	struct uffdio_range range;
+#define UFFDIO_REGISTER_MODE_MISSING	((__u64)1<<0)
+#define UFFDIO_REGISTER_MODE_WP		((__u64)1<<1)
+#define UFFDIO_REGISTER_MODE_MINOR	((__u64)1<<2)
+	__u64 mode;
+
+	/*
+	 * kernel answers which ioctl commands are available for the
+	 * range, keep at the end as the last 8 bytes aren't read.
+	 */
+	__u64 ioctls;
+};
+
+struct uffdio_copy {
+	__u64 dst;
+	__u64 src;
+	__u64 len;
+#define UFFDIO_COPY_MODE_DONTWAKE		((__u64)1<<0)
+	/*
+	 * UFFDIO_COPY_MODE_WP will map the page write protected on
+	 * the fly.  UFFDIO_COPY_MODE_WP is available only if the
+	 * write protected ioctl is implemented for the range
+	 * according to the uffdio_register.ioctls.
+	 */
+#define UFFDIO_COPY_MODE_WP			((__u64)1<<1)
+	__u64 mode;
+
+	/*
+	 * "copy" is written by the ioctl and must be at the end: the
+	 * copy_from_user will not read the last 8 bytes.
+	 */
+	__s64 copy;
+};
+
+struct uffdio_zeropage {
+	struct uffdio_range range;
+#define UFFDIO_ZEROPAGE_MODE_DONTWAKE		((__u64)1<<0)
+	__u64 mode;
+
+	/*
+	 * "zeropage" is written by the ioctl and must be at the end:
+	 * the copy_from_user will not read the last 8 bytes.
+	 */
+	__s64 zeropage;
+};
+
+struct uffdio_writeprotect {
+	struct uffdio_range range;
+/*
+ * UFFDIO_WRITEPROTECT_MODE_WP: set the flag to write protect a range,
+ * unset the flag to undo protection of a range which was previously
+ * write protected.
+ *
+ * UFFDIO_WRITEPROTECT_MODE_DONTWAKE: set the flag to avoid waking up
+ * any wait thread after the operation succeeds.
+ *
+ * NOTE: Write protecting a region (WP=1) is unrelated to page faults,
+ * therefore DONTWAKE flag is meaningless with WP=1.  Removing write
+ * protection (WP=0) in response to a page fault wakes the faulting
+ * task unless DONTWAKE is set.
+ */
+#define UFFDIO_WRITEPROTECT_MODE_WP		((__u64)1<<0)
+#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE	((__u64)1<<1)
+	__u64 mode;
+};
+
+struct uffdio_continue {
+	struct uffdio_range range;
+#define UFFDIO_CONTINUE_MODE_DONTWAKE		((__u64)1<<0)
+	/*
+	 * UFFDIO_CONTINUE_MODE_WP will map the page write protected on
+	 * the fly.  UFFDIO_CONTINUE_MODE_WP is available only if the
+	 * write protected ioctl is implemented for the range
+	 * according to the uffdio_register.ioctls.
+	 */
+#define UFFDIO_CONTINUE_MODE_WP			((__u64)1<<1)
+	__u64 mode;
+
+	/*
+	 * Fields below here are written by the ioctl and must be at the end:
+	 * the copy_from_user will not read past here.
+	 */
+	__s64 mapped;
+};
+
+struct uffdio_poison {
+	struct uffdio_range range;
+#define UFFDIO_POISON_MODE_DONTWAKE		((__u64)1<<0)
+	__u64 mode;
+
+	/*
+	 * Fields below here are written by the ioctl and must be at the end:
+	 * the copy_from_user will not read past here.
+	 */
+	__s64 updated;
+};
+
+struct uffdio_move {
+	__u64 dst;
+	__u64 src;
+	__u64 len;
+	/*
+	 * Especially if used to atomically remove memory from the
+	 * address space the wake on the dst range is not needed.
+	 */
+#define UFFDIO_MOVE_MODE_DONTWAKE		((__u64)1<<0)
+#define UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES	((__u64)1<<1)
+	__u64 mode;
+	/*
+	 * "move" is written by the ioctl and must be at the end: the
+	 * copy_from_user will not read the last 8 bytes.
+	 */
+	__s64 move;
+};
+
+/*
+ * Flags for the userfaultfd(2) system call itself.
+ */
+
+/*
+ * Create a userfaultfd that can handle page faults only in user mode.
+ */
+#define UFFD_USER_MODE_ONLY 1
+
+#endif /* _LINUX_USERFAULTFD_H */
-- 
cgit 


From 450f941ea9dce7256a485baf36f2b8d85a64e1c0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 26 Apr 2024 15:52:09 -0300
Subject: tools headers: Synchronize linux/bits.h with the kernel sources

To pick up the changes in this cset:

   3c7a8e190bc58081 ("uapi: introduce uapi-friendly macros for GENMASK")

That just causes perf to rebuild. Its just some macros going to an uapi
header that we now have to grab a copy into tools/ as well.

This addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/linux/bits.h include/linux/bits.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/lkml/ZiwJsFOBez0MS4r9@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/bits.h                   |  8 +-------
 tools/include/uapi/asm-generic/bitsperlong.h |  4 ++++
 tools/include/uapi/linux/bits.h              | 15 +++++++++++++++
 tools/perf/check-headers.sh                  |  1 +
 4 files changed, 21 insertions(+), 7 deletions(-)
 create mode 100644 tools/include/uapi/linux/bits.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 7c0cf5031abe..0eb24d21aac2 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -4,6 +4,7 @@
 
 #include <linux/const.h>
 #include <vdso/bits.h>
+#include <uapi/linux/bits.h>
 #include <asm/bitsperlong.h>
 
 #define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
@@ -30,15 +31,8 @@
 #define GENMASK_INPUT_CHECK(h, l) 0
 #endif
 
-#define __GENMASK(h, l) \
-	(((~UL(0)) - (UL(1) << (l)) + 1) & \
-	 (~UL(0) >> (BITS_PER_LONG - 1 - (h))))
 #define GENMASK(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
-
-#define __GENMASK_ULL(h, l) \
-	(((~ULL(0)) - (ULL(1) << (l)) + 1) & \
-	 (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
 #define GENMASK_ULL(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
 
diff --git a/tools/include/uapi/asm-generic/bitsperlong.h b/tools/include/uapi/asm-generic/bitsperlong.h
index 352cb81947b8..fadb3f857f28 100644
--- a/tools/include/uapi/asm-generic/bitsperlong.h
+++ b/tools/include/uapi/asm-generic/bitsperlong.h
@@ -24,4 +24,8 @@
 #endif
 #endif
 
+#ifndef __BITS_PER_LONG_LONG
+#define __BITS_PER_LONG_LONG 64
+#endif
+
 #endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h
new file mode 100644
index 000000000000..3c2a101986a3
--- /dev/null
+++ b/tools/include/uapi/linux/bits.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* bits.h: Macros for dealing with bitmasks.  */
+
+#ifndef _UAPI_LINUX_BITS_H
+#define _UAPI_LINUX_BITS_H
+
+#define __GENMASK(h, l) \
+        (((~_UL(0)) - (_UL(1) << (l)) + 1) & \
+         (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
+
+#define __GENMASK_ULL(h, l) \
+        (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \
+         (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif /* _UAPI_LINUX_BITS_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 9c84fd049070..672421b858ac 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -9,6 +9,7 @@ FILES=(
   "include/uapi/linux/const.h"
   "include/uapi/drm/drm.h"
   "include/uapi/drm/i915_drm.h"
+  "include/uapi/linux/bits.h"
   "include/uapi/linux/fadvise.h"
   "include/uapi/linux/fscrypt.h"
   "include/uapi/linux/kcmp.h"
-- 
cgit 


From 0cfe71f45f420e412fda2395807a56c453a6e0b6 Mon Sep 17 00:00:00 2001
From: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Date: Fri, 26 Apr 2024 11:39:27 +0800
Subject: netdev: add queue stats

These stats are commonly. Support reporting those via netdev-genl queue
stats.

name: rx-hw-drops
name: rx-hw-drop-overruns
name: rx-csum-unnecessary
name: rx-csum-none
name: rx-csum-bad
name: rx-hw-gro-packets
name: rx-hw-gro-bytes
name: rx-hw-gro-wire-packets
name: rx-hw-gro-wire-bytes
name: rx-hw-drop-ratelimits
name: tx-hw-drops
name: tx-hw-drop-errors
name: tx-csum-none
name: tx-needs-csum
name: tx-hw-gso-packets
name: tx-hw-gso-bytes
name: tx-hw-gso-wire-packets
name: tx-hw-gso-wire-bytes
name: tx-hw-drop-ratelimits

Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/netdev.yaml | 104 ++++++++++++++++++++++++++++++++
 include/net/netdev_queues.h             |  27 +++++++++
 include/uapi/linux/netdev.h             |  19 ++++++
 net/core/netdev-genl.c                  |  23 ++++++-
 tools/include/uapi/linux/netdev.h       |  19 ++++++
 5 files changed, 190 insertions(+), 2 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 679c4130707c..2be4b3714d17 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -335,6 +335,110 @@ attribute-sets:
           Allocation failure may, or may not result in a packet drop, depending
           on driver implementation and whether system recovers quickly.
         type: uint
+      -
+        name: rx-hw-drops
+        doc: |
+          Number of all packets which entered the device, but never left it,
+          including but not limited to: packets dropped due to lack of buffer
+          space, processing errors, explicit or implicit policies and packet
+          filters.
+        type: uint
+      -
+        name: rx-hw-drop-overruns
+        doc: |
+          Number of packets dropped due to transient lack of resources, such as
+          buffer space, host descriptors etc.
+        type: uint
+      -
+        name: rx-csum-unnecessary
+        doc: Number of packets that were marked as CHECKSUM_UNNECESSARY.
+        type: uint
+      -
+        name: rx-csum-none
+        doc: Number of packets that were not checksummed by device.
+        type: uint
+      -
+        name: rx-csum-bad
+        doc: |
+          Number of packets with bad checksum. The packets are not discarded,
+          but still delivered to the stack.
+        type: uint
+      -
+        name: rx-hw-gro-packets
+        doc: |
+          Number of packets that were coalesced from smaller packets by the device.
+          Counts only packets coalesced with the HW-GRO netdevice feature,
+          LRO-coalesced packets are not counted.
+        type: uint
+      -
+        name: rx-hw-gro-bytes
+        doc: See `rx-hw-gro-packets`.
+        type: uint
+      -
+        name: rx-hw-gro-wire-packets
+        doc: |
+          Number of packets that were coalesced to bigger packetss with the HW-GRO
+          netdevice feature. LRO-coalesced packets are not counted.
+        type: uint
+      -
+        name: rx-hw-gro-wire-bytes
+        doc: See `rx-hw-gro-wire-packets`.
+        type: uint
+      -
+        name: rx-hw-drop-ratelimits
+        doc: |
+          Number of the packets dropped by the device due to the received
+          packets bitrate exceeding the device rate limit.
+        type: uint
+      -
+        name: tx-hw-drops
+        doc: |
+          Number of packets that arrived at the device but never left it,
+          encompassing packets dropped for reasons such as processing errors, as
+          well as those affected by explicitly defined policies and packet
+          filtering criteria.
+        type: uint
+      -
+        name: tx-hw-drop-errors
+        doc: Number of packets dropped because they were invalid or malformed.
+        type: uint
+      -
+        name: tx-csum-none
+        doc: |
+          Number of packets that did not require the device to calculate the
+          checksum.
+        type: uint
+      -
+        name: tx-needs-csum
+        doc: |
+          Number of packets that required the device to calculate the checksum.
+        type: uint
+      -
+        name: tx-hw-gso-packets
+        doc: |
+          Number of packets that necessitated segmentation into smaller packets
+          by the device.
+        type: uint
+      -
+        name: tx-hw-gso-bytes
+        doc: See `tx-hw-gso-packets`.
+        type: uint
+      -
+        name: tx-hw-gso-wire-packets
+        doc: |
+          Number of wire-sized packets generated by processing
+          `tx-hw-gso-packets`
+        type: uint
+      -
+        name: tx-hw-gso-wire-bytes
+        doc: See `tx-hw-gso-wire-packets`.
+        type: uint
+      -
+        name: tx-hw-drop-ratelimits
+        doc: |
+          Number of the packets dropped by the device due to the transmit
+          packets bitrate exceeding the device rate limit.
+        type: uint
 
 operations:
   list:
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 1ec408585373..c7ac4539eafc 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -9,11 +9,38 @@ struct netdev_queue_stats_rx {
 	u64 bytes;
 	u64 packets;
 	u64 alloc_fail;
+
+	u64 hw_drops;
+	u64 hw_drop_overruns;
+
+	u64 csum_unnecessary;
+	u64 csum_none;
+	u64 csum_bad;
+
+	u64 hw_gro_packets;
+	u64 hw_gro_bytes;
+	u64 hw_gro_wire_packets;
+	u64 hw_gro_wire_bytes;
+
+	u64 hw_drop_ratelimits;
 };
 
 struct netdev_queue_stats_tx {
 	u64 bytes;
 	u64 packets;
+
+	u64 hw_drops;
+	u64 hw_drop_errors;
+
+	u64 csum_none;
+	u64 needs_csum;
+
+	u64 hw_gso_packets;
+	u64 hw_gso_bytes;
+	u64 hw_gso_wire_packets;
+	u64 hw_gso_wire_bytes;
+
+	u64 hw_drop_ratelimits;
 };
 
 /**
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index bb65ee840cda..cf24f1d9adf8 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -146,6 +146,25 @@ enum {
 	NETDEV_A_QSTATS_TX_PACKETS,
 	NETDEV_A_QSTATS_TX_BYTES,
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
+	NETDEV_A_QSTATS_RX_HW_DROPS,
+	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
+	NETDEV_A_QSTATS_RX_CSUM_NONE,
+	NETDEV_A_QSTATS_RX_CSUM_BAD,
+	NETDEV_A_QSTATS_RX_HW_GRO_PACKETS,
+	NETDEV_A_QSTATS_RX_HW_GRO_BYTES,
+	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS,
+	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES,
+	NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS,
+	NETDEV_A_QSTATS_TX_HW_DROPS,
+	NETDEV_A_QSTATS_TX_HW_DROP_ERRORS,
+	NETDEV_A_QSTATS_TX_CSUM_NONE,
+	NETDEV_A_QSTATS_TX_NEEDS_CSUM,
+	NETDEV_A_QSTATS_TX_HW_GSO_PACKETS,
+	NETDEV_A_QSTATS_TX_HW_GSO_BYTES,
+	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS,
+	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES,
+	NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS,
 
 	__NETDEV_A_QSTATS_MAX,
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index dd6510f2c652..4b5054087309 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -489,7 +489,17 @@ netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx)
 {
 	if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) ||
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) ||
-	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail))
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROPS, rx->hw_drops) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, rx->hw_drop_overruns) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, rx->csum_unnecessary) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_NONE, rx->csum_none) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_BAD, rx->csum_bad) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, rx->hw_gro_packets) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_BYTES, rx->hw_gro_bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, rx->hw_gro_wire_packets) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, rx->hw_gro_wire_bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, rx->hw_drop_ratelimits))
 		return -EMSGSIZE;
 	return 0;
 }
@@ -498,7 +508,16 @@ static int
 netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx)
 {
 	if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) ||
-	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes))
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROPS, tx->hw_drops) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, tx->hw_drop_errors) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_CSUM_NONE, tx->csum_none) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_NEEDS_CSUM, tx->needs_csum) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, tx->hw_gso_packets) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_BYTES, tx->hw_gso_bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, tx->hw_gso_wire_packets) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, tx->hw_gso_wire_bytes) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits))
 		return -EMSGSIZE;
 	return 0;
 }
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index bb65ee840cda..cf24f1d9adf8 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -146,6 +146,25 @@ enum {
 	NETDEV_A_QSTATS_TX_PACKETS,
 	NETDEV_A_QSTATS_TX_BYTES,
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
+	NETDEV_A_QSTATS_RX_HW_DROPS,
+	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
+	NETDEV_A_QSTATS_RX_CSUM_NONE,
+	NETDEV_A_QSTATS_RX_CSUM_BAD,
+	NETDEV_A_QSTATS_RX_HW_GRO_PACKETS,
+	NETDEV_A_QSTATS_RX_HW_GRO_BYTES,
+	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS,
+	NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES,
+	NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS,
+	NETDEV_A_QSTATS_TX_HW_DROPS,
+	NETDEV_A_QSTATS_TX_HW_DROP_ERRORS,
+	NETDEV_A_QSTATS_TX_CSUM_NONE,
+	NETDEV_A_QSTATS_TX_NEEDS_CSUM,
+	NETDEV_A_QSTATS_TX_HW_GSO_PACKETS,
+	NETDEV_A_QSTATS_TX_HW_GSO_BYTES,
+	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS,
+	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES,
+	NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS,
 
 	__NETDEV_A_QSTATS_MAX,
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
-- 
cgit 


From 535a3692ba7245792e6f23654507865d4293c850 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 30 Apr 2024 13:28:24 +0200
Subject: bpf: Add support for kprobe session attach

Adding support to attach bpf program for entry and return probe
of the same function. This is common use case which at the moment
requires to create two kprobe multi links.

Adding new BPF_TRACE_KPROBE_SESSION attach type that instructs
kernel to attach single link program to both entry and exit probe.

It's possible to control execution of the bpf program on return
probe simply by returning zero or non zero from the entry bpf
program execution to execute or not the bpf program on return
probe respectively.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240430112830.1184228-2-jolsa@kernel.org
---
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/syscall.c           |  7 ++++++-
 kernel/trace/bpf_trace.c       | 28 ++++++++++++++++++++--------
 tools/include/uapi/linux/bpf.h |  1 +
 4 files changed, 28 insertions(+), 9 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d94a72593ead..90706a47f6ff 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1115,6 +1115,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_UNIX_GETSOCKNAME,
 	BPF_NETKIT_PRIMARY,
 	BPF_NETKIT_PEER,
+	BPF_TRACE_KPROBE_SESSION,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f655adf42e39..13ad74ecf2cd 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4016,11 +4016,15 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI &&
 		    attach_type != BPF_TRACE_KPROBE_MULTI)
 			return -EINVAL;
+		if (prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION &&
+		    attach_type != BPF_TRACE_KPROBE_SESSION)
+			return -EINVAL;
 		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI &&
 		    attach_type != BPF_TRACE_UPROBE_MULTI)
 			return -EINVAL;
 		if (attach_type != BPF_PERF_EVENT &&
 		    attach_type != BPF_TRACE_KPROBE_MULTI &&
+		    attach_type != BPF_TRACE_KPROBE_SESSION &&
 		    attach_type != BPF_TRACE_UPROBE_MULTI)
 			return -EINVAL;
 		return 0;
@@ -5281,7 +5285,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 	case BPF_PROG_TYPE_KPROBE:
 		if (attr->link_create.attach_type == BPF_PERF_EVENT)
 			ret = bpf_perf_link_attach(attr, prog);
-		else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI)
+		else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI ||
+			 attr->link_create.attach_type == BPF_TRACE_KPROBE_SESSION)
 			ret = bpf_kprobe_multi_link_attach(attr, prog);
 		else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI)
 			ret = bpf_uprobe_multi_link_attach(attr, prog);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0ba722b57af3..06a9671834b6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1631,6 +1631,17 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	}
 }
 
+static bool is_kprobe_multi(const struct bpf_prog *prog)
+{
+	return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ||
+	       prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION;
+}
+
+static inline bool is_kprobe_session(const struct bpf_prog *prog)
+{
+	return prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION;
+}
+
 static const struct bpf_func_proto *
 kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1646,13 +1657,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_override_return_proto;
 #endif
 	case BPF_FUNC_get_func_ip:
-		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI)
+		if (is_kprobe_multi(prog))
 			return &bpf_get_func_ip_proto_kprobe_multi;
 		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
 			return &bpf_get_func_ip_proto_uprobe_multi;
 		return &bpf_get_func_ip_proto_kprobe;
 	case BPF_FUNC_get_attach_cookie:
-		if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI)
+		if (is_kprobe_multi(prog))
 			return &bpf_get_attach_cookie_proto_kmulti;
 		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
 			return &bpf_get_attach_cookie_proto_umulti;
@@ -2834,10 +2845,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip,
 			  void *data)
 {
 	struct bpf_kprobe_multi_link *link;
+	int err;
 
 	link = container_of(fp, struct bpf_kprobe_multi_link, fp);
-	kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs);
-	return 0;
+	err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs);
+	return is_kprobe_session(link->link.prog) ? err : 0;
 }
 
 static void
@@ -2981,7 +2993,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	if (sizeof(u64) != sizeof(void *))
 		return -EOPNOTSUPP;
 
-	if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI)
+	if (!is_kprobe_multi(prog))
 		return -EINVAL;
 
 	flags = attr->link_create.kprobe_multi.flags;
@@ -3062,10 +3074,10 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	if (err)
 		goto error;
 
-	if (flags & BPF_F_KPROBE_MULTI_RETURN)
-		link->fp.exit_handler = kprobe_multi_link_exit_handler;
-	else
+	if (!(flags & BPF_F_KPROBE_MULTI_RETURN))
 		link->fp.entry_handler = kprobe_multi_link_handler;
+	if ((flags & BPF_F_KPROBE_MULTI_RETURN) || is_kprobe_session(prog))
+		link->fp.exit_handler = kprobe_multi_link_exit_handler;
 
 	link->addrs = addrs;
 	link->cookies = cookies;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d94a72593ead..90706a47f6ff 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1115,6 +1115,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_UNIX_GETSOCKNAME,
 	BPF_NETKIT_PRIMARY,
 	BPF_NETKIT_PEER,
+	BPF_TRACE_KPROBE_SESSION,
 	__MAX_BPF_ATTACH_TYPE
 };
 
-- 
cgit 


From 651d61bc8b7d8bb622cfc24be2ee92eebb4ed3cc Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Tue, 11 Apr 2023 15:44:46 +0930
Subject: KVM: PPC: Fix documentation for ppc mmu caps

The documentation mentions KVM_CAP_PPC_RADIX_MMU, but the defines in the
kvm headers spell it KVM_CAP_PPC_MMU_RADIX. Similarly with
KVM_CAP_PPC_MMU_HASH_V3.

Fixes: c92701322711 ("KVM: PPC: Book3S HV: Add userspace interfaces for POWER9 MMU")
Signed-off-by: Joel Stanley <joel@jms.id.au>
Acked-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20230411061446.26324-1-joel@jms.id.au
---
 Documentation/virt/kvm/api.rst | 8 ++++----
 include/uapi/linux/kvm.h       | 4 ++--
 tools/include/uapi/linux/kvm.h | 2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'tools/include/uapi/linux')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 0b5a33ee71ee..636e6794828f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4300,7 +4300,7 @@ operating system that uses the PIT for timing (e.g. Linux 2.4.x).
 4.100 KVM_PPC_CONFIGURE_V3_MMU
 ------------------------------
 
-:Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3
+:Capability: KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3
 :Architectures: ppc
 :Type: vm ioctl
 :Parameters: struct kvm_ppc_mmuv3_cfg (in)
@@ -4334,7 +4334,7 @@ the Power ISA V3.00, Book III section 5.7.6.1.
 4.101 KVM_PPC_GET_RMMU_INFO
 ---------------------------
 
-:Capability: KVM_CAP_PPC_RADIX_MMU
+:Capability: KVM_CAP_PPC_MMU_RADIX
 :Architectures: ppc
 :Type: vm ioctl
 :Parameters: struct kvm_ppc_rmmu_info (out)
@@ -8095,7 +8095,7 @@ capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
 will disable the use of APIC hardware virtualization even if supported
 by the CPU, as it's incompatible with SynIC auto-EOI behavior.
 
-8.3 KVM_CAP_PPC_RADIX_MMU
+8.3 KVM_CAP_PPC_MMU_RADIX
 -------------------------
 
 :Architectures: ppc
@@ -8105,7 +8105,7 @@ available, means that the kernel can support guests using the
 radix MMU defined in Power ISA V3.00 (as implemented in the POWER9
 processor).
 
-8.4 KVM_CAP_PPC_HASH_MMU_V3
+8.4 KVM_CAP_PPC_MMU_HASH_V3
 ---------------------------
 
 :Architectures: ppc
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 2190adbe3002..d03842abae57 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1221,9 +1221,9 @@ struct kvm_vfio_spapr_tce {
 /* Available with KVM_CAP_SPAPR_RESIZE_HPT */
 #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
 #define KVM_PPC_RESIZE_HPT_COMMIT  _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
-/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */
+/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */
 #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
-/* Available with KVM_CAP_PPC_RADIX_MMU */
+/* Available with KVM_CAP_PPC_MMU_RADIX */
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
 /* Available with KVM_CAP_PPC_GET_CPU_CHAR */
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index c3308536482b..4b6b635b8bd1 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1502,7 +1502,7 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_SPAPR_RESIZE_HPT */
 #define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
 #define KVM_PPC_RESIZE_HPT_COMMIT  _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
-/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */
+/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_MMU_HASH_V3 */
 #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
 /* Available with KVM_CAP_PPC_RADIX_MMU */
 #define KVM_PPC_GET_RMMU_INFO	  _IOW(KVMIO,  0xb0, struct kvm_ppc_rmmu_info)
-- 
cgit 


From bbe91a9f6889934e661fa924144c7023f0a1c4cf Mon Sep 17 00:00:00 2001
From: Tushar Vyavahare <tushar.vyavahare@intel.com>
Date: Wed, 8 May 2024 10:41:23 +0000
Subject: tools: remove redundant ethtool.h from tooling infra

Remove the redundant ethtool.h header file from tools/include/uapi/linux.
The file is unnecessary as the system uses the kernel's
include/uapi/linux/ethtool.h directly.

Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20240508104123.434769-1-tushar.vyavahare@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/ethtool.h | 2271 ------------------------------------
 1 file changed, 2271 deletions(-)
 delete mode 100644 tools/include/uapi/linux/ethtool.h

(limited to 'tools/include/uapi/linux')

diff --git a/tools/include/uapi/linux/ethtool.h b/tools/include/uapi/linux/ethtool.h
deleted file mode 100644
index 11fc18988bc2..000000000000
--- a/tools/include/uapi/linux/ethtool.h
+++ /dev/null
@@ -1,2271 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * ethtool.h: Defines for Linux ethtool.
- *
- * Copyright (C) 1998 David S. Miller (davem@redhat.com)
- * Copyright 2001 Jeff Garzik <jgarzik@pobox.com>
- * Portions Copyright 2001 Sun Microsystems (thockin@sun.com)
- * Portions Copyright 2002 Intel (eli.kupermann@intel.com,
- *                                christopher.leech@intel.com,
- *                                scott.feldman@intel.com)
- * Portions Copyright (C) Sun Microsystems 2008
- */
-
-#ifndef _UAPI_LINUX_ETHTOOL_H
-#define _UAPI_LINUX_ETHTOOL_H
-
-#include <linux/const.h>
-#include <linux/types.h>
-#include <linux/if_ether.h>
-
-#ifndef __KERNEL__
-#include <limits.h> /* for INT_MAX */
-#endif
-
-/* All structures exposed to userland should be defined such that they
- * have the same layout for 32-bit and 64-bit userland.
- */
-
-/* Note on reserved space.
- * Reserved fields must not be accessed directly by user space because
- * they may be replaced by a different field in the future. They must
- * be initialized to zero before making the request, e.g. via memset
- * of the entire structure or implicitly by not being set in a structure
- * initializer.
- */
-
-/**
- * struct ethtool_cmd - DEPRECATED, link control and status
- * This structure is DEPRECATED, please use struct ethtool_link_settings.
- * @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET
- * @supported: Bitmask of %SUPPORTED_* flags for the link modes,
- *	physical connectors and other link features for which the
- *	interface supports autonegotiation or auto-detection.
- *	Read-only.
- * @advertising: Bitmask of %ADVERTISED_* flags for the link modes,
- *	physical connectors and other link features that are
- *	advertised through autonegotiation or enabled for
- *	auto-detection.
- * @speed: Low bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN
- * @duplex: Duplex mode; one of %DUPLEX_*
- * @port: Physical connector type; one of %PORT_*
- * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not
- *	applicable.  For clause 45 PHYs this is the PRTAD.
- * @transceiver: Historically used to distinguish different possible
- *	PHY types, but not in a consistent way.  Deprecated.
- * @autoneg: Enable/disable autonegotiation and auto-detection;
- *	either %AUTONEG_DISABLE or %AUTONEG_ENABLE
- * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO
- *	protocols supported by the interface; 0 if unknown.
- *	Read-only.
- * @maxtxpkt: Historically used to report TX IRQ coalescing; now
- *	obsoleted by &struct ethtool_coalesce.  Read-only; deprecated.
- * @maxrxpkt: Historically used to report RX IRQ coalescing; now
- *	obsoleted by &struct ethtool_coalesce.  Read-only; deprecated.
- * @speed_hi: High bits of the speed, 1Mb units, 0 to INT_MAX or SPEED_UNKNOWN
- * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of
- *	%ETH_TP_MDI_*.  If the status is unknown or not applicable, the
- *	value will be %ETH_TP_MDI_INVALID.  Read-only.
- * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of
- *	%ETH_TP_MDI_*.  If MDI(-X) control is not implemented, reads
- *	yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected.
- *	When written successfully, the link should be renegotiated if
- *	necessary.
- * @lp_advertising: Bitmask of %ADVERTISED_* flags for the link modes
- *	and other link features that the link partner advertised
- *	through autonegotiation; 0 if unknown or not applicable.
- *	Read-only.
- * @reserved: Reserved for future use; see the note on reserved space.
- *
- * The link speed in Mbps is split between @speed and @speed_hi.  Use
- * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to
- * access it.
- *
- * If autonegotiation is disabled, the speed and @duplex represent the
- * fixed link mode and are writable if the driver supports multiple
- * link modes.  If it is enabled then they are read-only; if the link
- * is up they represent the negotiated link mode; if the link is down,
- * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and
- * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode.
- *
- * Some hardware interfaces may have multiple PHYs and/or physical
- * connectors fitted or do not allow the driver to detect which are
- * fitted.  For these interfaces @port and/or @phy_address may be
- * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE.
- * Otherwise, attempts to write different values may be ignored or
- * rejected.
- *
- * Users should assume that all fields not marked read-only are
- * writable and subject to validation by the driver.  They should use
- * %ETHTOOL_GSET to get the current values before making specific
- * changes and then applying them with %ETHTOOL_SSET.
- *
- * Deprecated fields should be ignored by both users and drivers.
- */
-struct ethtool_cmd {
-	__u32	cmd;
-	__u32	supported;
-	__u32	advertising;
-	__u16	speed;
-	__u8	duplex;
-	__u8	port;
-	__u8	phy_address;
-	__u8	transceiver;
-	__u8	autoneg;
-	__u8	mdio_support;
-	__u32	maxtxpkt;
-	__u32	maxrxpkt;
-	__u16	speed_hi;
-	__u8	eth_tp_mdix;
-	__u8	eth_tp_mdix_ctrl;
-	__u32	lp_advertising;
-	__u32	reserved[2];
-};
-
-static inline void ethtool_cmd_speed_set(struct ethtool_cmd *ep,
-					 __u32 speed)
-{
-	ep->speed = (__u16)(speed & 0xFFFF);
-	ep->speed_hi = (__u16)(speed >> 16);
-}
-
-static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep)
-{
-	return (ep->speed_hi << 16) | ep->speed;
-}
-
-/* Device supports clause 22 register access to PHY or peripherals
- * using the interface defined in <linux/mii.h>.  This should not be
- * set if there are known to be no such peripherals present or if
- * the driver only emulates clause 22 registers for compatibility.
- */
-#define ETH_MDIO_SUPPORTS_C22	1
-
-/* Device supports clause 45 register access to PHY or peripherals
- * using the interface defined in <linux/mii.h> and <linux/mdio.h>.
- * This should not be set if there are known to be no such peripherals
- * present.
- */
-#define ETH_MDIO_SUPPORTS_C45	2
-
-#define ETHTOOL_FWVERS_LEN	32
-#define ETHTOOL_BUSINFO_LEN	32
-#define ETHTOOL_EROMVERS_LEN	32
-
-/**
- * struct ethtool_drvinfo - general driver and device information
- * @cmd: Command number = %ETHTOOL_GDRVINFO
- * @driver: Driver short name.  This should normally match the name
- *	in its bus driver structure (e.g. pci_driver::name).  Must
- *	not be an empty string.
- * @version: Driver version string; may be an empty string
- * @fw_version: Firmware version string; driver defined; may be an
- *	empty string
- * @erom_version: Expansion ROM version string; driver defined; may be
- *	an empty string
- * @bus_info: Device bus address.  This should match the dev_name()
- *	string for the underlying bus device, if there is one.  May be
- *	an empty string.
- * @reserved2: Reserved for future use; see the note on reserved space.
- * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and
- *	%ETHTOOL_SPFLAGS commands; also the number of strings in the
- *	%ETH_SS_PRIV_FLAGS set
- * @n_stats: Number of u64 statistics returned by the %ETHTOOL_GSTATS
- *	command; also the number of strings in the %ETH_SS_STATS set
- * @testinfo_len: Number of results returned by the %ETHTOOL_TEST
- *	command; also the number of strings in the %ETH_SS_TEST set
- * @eedump_len: Size of EEPROM accessible through the %ETHTOOL_GEEPROM
- *	and %ETHTOOL_SEEPROM commands, in bytes
- * @regdump_len: Size of register dump returned by the %ETHTOOL_GREGS
- *	command, in bytes
- *
- * Users can use the %ETHTOOL_GSSET_INFO command to get the number of
- * strings in any string set (from Linux 2.6.34).
- */
-struct ethtool_drvinfo {
-	__u32	cmd;
-	char	driver[32];
-	char	version[32];
-	char	fw_version[ETHTOOL_FWVERS_LEN];
-	char	bus_info[ETHTOOL_BUSINFO_LEN];
-	char	erom_version[ETHTOOL_EROMVERS_LEN];
-	char	reserved2[12];
-	__u32	n_priv_flags;
-	__u32	n_stats;
-	__u32	testinfo_len;
-	__u32	eedump_len;
-	__u32	regdump_len;
-};
-
-#define SOPASS_MAX	6
-
-/**
- * struct ethtool_wolinfo - Wake-On-Lan configuration
- * @cmd: Command number = %ETHTOOL_GWOL or %ETHTOOL_SWOL
- * @supported: Bitmask of %WAKE_* flags for supported Wake-On-Lan modes.
- *	Read-only.
- * @wolopts: Bitmask of %WAKE_* flags for enabled Wake-On-Lan modes.
- * @sopass: SecureOn(tm) password; meaningful only if %WAKE_MAGICSECURE
- *	is set in @wolopts.
- */
-struct ethtool_wolinfo {
-	__u32	cmd;
-	__u32	supported;
-	__u32	wolopts;
-	__u8	sopass[SOPASS_MAX];
-};
-
-/* for passing single values */
-struct ethtool_value {
-	__u32	cmd;
-	__u32	data;
-};
-
-#define PFC_STORM_PREVENTION_AUTO	0xffff
-#define PFC_STORM_PREVENTION_DISABLE	0
-
-enum tunable_id {
-	ETHTOOL_ID_UNSPEC,
-	ETHTOOL_RX_COPYBREAK,
-	ETHTOOL_TX_COPYBREAK,
-	ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */
-	ETHTOOL_TX_COPYBREAK_BUF_SIZE,
-	/*
-	 * Add your fresh new tunable attribute above and remember to update
-	 * tunable_strings[] in net/ethtool/common.c
-	 */
-	__ETHTOOL_TUNABLE_COUNT,
-};
-
-enum tunable_type_id {
-	ETHTOOL_TUNABLE_UNSPEC,
-	ETHTOOL_TUNABLE_U8,
-	ETHTOOL_TUNABLE_U16,
-	ETHTOOL_TUNABLE_U32,
-	ETHTOOL_TUNABLE_U64,
-	ETHTOOL_TUNABLE_STRING,
-	ETHTOOL_TUNABLE_S8,
-	ETHTOOL_TUNABLE_S16,
-	ETHTOOL_TUNABLE_S32,
-	ETHTOOL_TUNABLE_S64,
-};
-
-struct ethtool_tunable {
-	__u32	cmd;
-	__u32	id;
-	__u32	type_id;
-	__u32	len;
-	void	*data[];
-};
-
-#define DOWNSHIFT_DEV_DEFAULT_COUNT	0xff
-#define DOWNSHIFT_DEV_DISABLE		0
-
-/* Time in msecs after which link is reported as down
- * 0 = lowest time supported by the PHY
- * 0xff = off, link down detection according to standard
- */
-#define ETHTOOL_PHY_FAST_LINK_DOWN_ON	0
-#define ETHTOOL_PHY_FAST_LINK_DOWN_OFF	0xff
-
-/* Energy Detect Power Down (EDPD) is a feature supported by some PHYs, where
- * the PHY's RX & TX blocks are put into a low-power mode when there is no
- * link detected (typically cable is un-plugged). For RX, only a minimal
- * link-detection is available, and for TX the PHY wakes up to send link pulses
- * to avoid any lock-ups in case the peer PHY may also be running in EDPD mode.
- *
- * Some PHYs may support configuration of the wake-up interval for TX pulses,
- * and some PHYs may support only disabling TX pulses entirely. For the latter
- * a special value is required (ETHTOOL_PHY_EDPD_NO_TX) so that this can be
- * configured from userspace (should the user want it).
- *
- * The interval units for TX wake-up are in milliseconds, since this should
- * cover a reasonable range of intervals:
- *  - from 1 millisecond, which does not sound like much of a power-saver
- *  - to ~65 seconds which is quite a lot to wait for a link to come up when
- *    plugging a cable
- */
-#define ETHTOOL_PHY_EDPD_DFLT_TX_MSECS		0xffff
-#define ETHTOOL_PHY_EDPD_NO_TX			0xfffe
-#define ETHTOOL_PHY_EDPD_DISABLE		0
-
-enum phy_tunable_id {
-	ETHTOOL_PHY_ID_UNSPEC,
-	ETHTOOL_PHY_DOWNSHIFT,
-	ETHTOOL_PHY_FAST_LINK_DOWN,
-	ETHTOOL_PHY_EDPD,
-	/*
-	 * Add your fresh new phy tunable attribute above and remember to update
-	 * phy_tunable_strings[] in net/ethtool/common.c
-	 */
-	__ETHTOOL_PHY_TUNABLE_COUNT,
-};
-
-/**
- * struct ethtool_regs - hardware register dump
- * @cmd: Command number = %ETHTOOL_GREGS
- * @version: Dump format version.  This is driver-specific and may
- *	distinguish different chips/revisions.  Drivers must use new
- *	version numbers whenever the dump format changes in an
- *	incompatible way.
- * @len: On entry, the real length of @data.  On return, the number of
- *	bytes used.
- * @data: Buffer for the register dump
- *
- * Users should use %ETHTOOL_GDRVINFO to find the maximum length of
- * a register dump for the interface.  They must allocate the buffer
- * immediately following this structure.
- */
-struct ethtool_regs {
-	__u32	cmd;
-	__u32	version;
-	__u32	len;
-	__u8	data[];
-};
-
-/**
- * struct ethtool_eeprom - EEPROM dump
- * @cmd: Command number = %ETHTOOL_GEEPROM, %ETHTOOL_GMODULEEEPROM or
- *	%ETHTOOL_SEEPROM
- * @magic: A 'magic cookie' value to guard against accidental changes.
- *	The value passed in to %ETHTOOL_SEEPROM must match the value
- *	returned by %ETHTOOL_GEEPROM for the same device.  This is
- *	unused when @cmd is %ETHTOOL_GMODULEEEPROM.
- * @offset: Offset within the EEPROM to begin reading/writing, in bytes
- * @len: On entry, number of bytes to read/write.  On successful
- *	return, number of bytes actually read/written.  In case of
- *	error, this may indicate at what point the error occurred.
- * @data: Buffer to read/write from
- *
- * Users may use %ETHTOOL_GDRVINFO or %ETHTOOL_GMODULEINFO to find
- * the length of an on-board or module EEPROM, respectively.  They
- * must allocate the buffer immediately following this structure.
- */
-struct ethtool_eeprom {
-	__u32	cmd;
-	__u32	magic;
-	__u32	offset;
-	__u32	len;
-	__u8	data[];
-};
-
-/**
- * struct ethtool_eee - Energy Efficient Ethernet information
- * @cmd: ETHTOOL_{G,S}EEE
- * @supported: Mask of %SUPPORTED_* flags for the speed/duplex combinations
- *	for which there is EEE support.
- * @advertised: Mask of %ADVERTISED_* flags for the speed/duplex combinations
- *	advertised as eee capable.
- * @lp_advertised: Mask of %ADVERTISED_* flags for the speed/duplex
- *	combinations advertised by the link partner as eee capable.
- * @eee_active: Result of the eee auto negotiation.
- * @eee_enabled: EEE configured mode (enabled/disabled).
- * @tx_lpi_enabled: Whether the interface should assert its tx lpi, given
- *	that eee was negotiated.
- * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting
- *	its tx lpi (after reaching 'idle' state). Effective only when eee
- *	was negotiated and tx_lpi_enabled was set.
- * @reserved: Reserved for future use; see the note on reserved space.
- */
-struct ethtool_eee {
-	__u32	cmd;
-	__u32	supported;
-	__u32	advertised;
-	__u32	lp_advertised;
-	__u32	eee_active;
-	__u32	eee_enabled;
-	__u32	tx_lpi_enabled;
-	__u32	tx_lpi_timer;
-	__u32	reserved[2];
-};
-
-/**
- * struct ethtool_modinfo - plugin module eeprom information
- * @cmd: %ETHTOOL_GMODULEINFO
- * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx
- * @eeprom_len: Length of the eeprom
- * @reserved: Reserved for future use; see the note on reserved space.
- *
- * This structure is used to return the information to
- * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM.
- * The type code indicates the eeprom data format
- */
-struct ethtool_modinfo {
-	__u32   cmd;
-	__u32   type;
-	__u32   eeprom_len;
-	__u32   reserved[8];
-};
-
-/**
- * struct ethtool_coalesce - coalescing parameters for IRQs and stats updates
- * @cmd: ETHTOOL_{G,S}COALESCE
- * @rx_coalesce_usecs: How many usecs to delay an RX interrupt after
- *	a packet arrives.
- * @rx_max_coalesced_frames: Maximum number of packets to receive
- *	before an RX interrupt.
- * @rx_coalesce_usecs_irq: Same as @rx_coalesce_usecs, except that
- *	this value applies while an IRQ is being serviced by the host.
- * @rx_max_coalesced_frames_irq: Same as @rx_max_coalesced_frames,
- *	except that this value applies while an IRQ is being serviced
- *	by the host.
- * @tx_coalesce_usecs: How many usecs to delay a TX interrupt after
- *	a packet is sent.
- * @tx_max_coalesced_frames: Maximum number of packets to be sent
- *	before a TX interrupt.
- * @tx_coalesce_usecs_irq: Same as @tx_coalesce_usecs, except that
- *	this value applies while an IRQ is being serviced by the host.
- * @tx_max_coalesced_frames_irq: Same as @tx_max_coalesced_frames,
- *	except that this value applies while an IRQ is being serviced
- *	by the host.
- * @stats_block_coalesce_usecs: How many usecs to delay in-memory
- *	statistics block updates.  Some drivers do not have an
- *	in-memory statistic block, and in such cases this value is
- *	ignored.  This value must not be zero.
- * @use_adaptive_rx_coalesce: Enable adaptive RX coalescing.
- * @use_adaptive_tx_coalesce: Enable adaptive TX coalescing.
- * @pkt_rate_low: Threshold for low packet rate (packets per second).
- * @rx_coalesce_usecs_low: How many usecs to delay an RX interrupt after
- *	a packet arrives, when the packet rate is below @pkt_rate_low.
- * @rx_max_coalesced_frames_low: Maximum number of packets to be received
- *	before an RX interrupt, when the packet rate is below @pkt_rate_low.
- * @tx_coalesce_usecs_low: How many usecs to delay a TX interrupt after
- *	a packet is sent, when the packet rate is below @pkt_rate_low.
- * @tx_max_coalesced_frames_low: Maximum nuumber of packets to be sent before
- *	a TX interrupt, when the packet rate is below @pkt_rate_low.
- * @pkt_rate_high: Threshold for high packet rate (packets per second).
- * @rx_coalesce_usecs_high: How many usecs to delay an RX interrupt after
- *	a packet arrives, when the packet rate is above @pkt_rate_high.
- * @rx_max_coalesced_frames_high: Maximum number of packets to be received
- *	before an RX interrupt, when the packet rate is above @pkt_rate_high.
- * @tx_coalesce_usecs_high: How many usecs to delay a TX interrupt after
- *	a packet is sent, when the packet rate is above @pkt_rate_high.
- * @tx_max_coalesced_frames_high: Maximum number of packets to be sent before
- *	a TX interrupt, when the packet rate is above @pkt_rate_high.
- * @rate_sample_interval: How often to do adaptive coalescing packet rate
- *	sampling, measured in seconds.  Must not be zero.
- *
- * Each pair of (usecs, max_frames) fields specifies that interrupts
- * should be coalesced until
- *	(usecs > 0 && time_since_first_completion >= usecs) ||
- *	(max_frames > 0 && completed_frames >= max_frames)
- *
- * It is illegal to set both usecs and max_frames to zero as this
- * would cause interrupts to never be generated.  To disable
- * coalescing, set usecs = 0 and max_frames = 1.
- *
- * Some implementations ignore the value of max_frames and use the
- * condition time_since_first_completion >= usecs
- *
- * This is deprecated.  Drivers for hardware that does not support
- * counting completions should validate that max_frames == !rx_usecs.
- *
- * Adaptive RX/TX coalescing is an algorithm implemented by some
- * drivers to improve latency under low packet rates and improve
- * throughput under high packet rates.  Some drivers only implement
- * one of RX or TX adaptive coalescing.  Anything not implemented by
- * the driver causes these values to be silently ignored.
- *
- * When the packet rate is below @pkt_rate_high but above
- * @pkt_rate_low (both measured in packets per second) the
- * normal {rx,tx}_* coalescing parameters are used.
- */
-struct ethtool_coalesce {
-	__u32	cmd;
-	__u32	rx_coalesce_usecs;
-	__u32	rx_max_coalesced_frames;
-	__u32	rx_coalesce_usecs_irq;
-	__u32	rx_max_coalesced_frames_irq;
-	__u32	tx_coalesce_usecs;
-	__u32	tx_max_coalesced_frames;
-	__u32	tx_coalesce_usecs_irq;
-	__u32	tx_max_coalesced_frames_irq;
-	__u32	stats_block_coalesce_usecs;
-	__u32	use_adaptive_rx_coalesce;
-	__u32	use_adaptive_tx_coalesce;
-	__u32	pkt_rate_low;
-	__u32	rx_coalesce_usecs_low;
-	__u32	rx_max_coalesced_frames_low;
-	__u32	tx_coalesce_usecs_low;
-	__u32	tx_max_coalesced_frames_low;
-	__u32	pkt_rate_high;
-	__u32	rx_coalesce_usecs_high;
-	__u32	rx_max_coalesced_frames_high;
-	__u32	tx_coalesce_usecs_high;
-	__u32	tx_max_coalesced_frames_high;
-	__u32	rate_sample_interval;
-};
-
-/**
- * struct ethtool_ringparam - RX/TX ring parameters
- * @cmd: Command number = %ETHTOOL_GRINGPARAM or %ETHTOOL_SRINGPARAM
- * @rx_max_pending: Maximum supported number of pending entries per
- *	RX ring.  Read-only.
- * @rx_mini_max_pending: Maximum supported number of pending entries
- *	per RX mini ring.  Read-only.
- * @rx_jumbo_max_pending: Maximum supported number of pending entries
- *	per RX jumbo ring.  Read-only.
- * @tx_max_pending: Maximum supported number of pending entries per
- *	TX ring.  Read-only.
- * @rx_pending: Current maximum number of pending entries per RX ring
- * @rx_mini_pending: Current maximum number of pending entries per RX
- *	mini ring
- * @rx_jumbo_pending: Current maximum number of pending entries per RX
- *	jumbo ring
- * @tx_pending: Current maximum supported number of pending entries
- *	per TX ring
- *
- * If the interface does not have separate RX mini and/or jumbo rings,
- * @rx_mini_max_pending and/or @rx_jumbo_max_pending will be 0.
- *
- * There may also be driver-dependent minimum values for the number
- * of entries per ring.
- */
-struct ethtool_ringparam {
-	__u32	cmd;
-	__u32	rx_max_pending;
-	__u32	rx_mini_max_pending;
-	__u32	rx_jumbo_max_pending;
-	__u32	tx_max_pending;
-	__u32	rx_pending;
-	__u32	rx_mini_pending;
-	__u32	rx_jumbo_pending;
-	__u32	tx_pending;
-};
-
-/**
- * struct ethtool_channels - configuring number of network channel
- * @cmd: ETHTOOL_{G,S}CHANNELS
- * @max_rx: Read only. Maximum number of receive channel the driver support.
- * @max_tx: Read only. Maximum number of transmit channel the driver support.
- * @max_other: Read only. Maximum number of other channel the driver support.
- * @max_combined: Read only. Maximum number of combined channel the driver
- *	support. Set of queues RX, TX or other.
- * @rx_count: Valid values are in the range 1 to the max_rx.
- * @tx_count: Valid values are in the range 1 to the max_tx.
- * @other_count: Valid values are in the range 1 to the max_other.
- * @combined_count: Valid values are in the range 1 to the max_combined.
- *
- * This can be used to configure RX, TX and other channels.
- */
-
-struct ethtool_channels {
-	__u32	cmd;
-	__u32	max_rx;
-	__u32	max_tx;
-	__u32	max_other;
-	__u32	max_combined;
-	__u32	rx_count;
-	__u32	tx_count;
-	__u32	other_count;
-	__u32	combined_count;
-};
-
-/**
- * struct ethtool_pauseparam - Ethernet pause (flow control) parameters
- * @cmd: Command number = %ETHTOOL_GPAUSEPARAM or %ETHTOOL_SPAUSEPARAM
- * @autoneg: Flag to enable autonegotiation of pause frame use
- * @rx_pause: Flag to enable reception of pause frames
- * @tx_pause: Flag to enable transmission of pause frames
- *
- * Drivers should reject a non-zero setting of @autoneg when
- * autoneogotiation is disabled (or not supported) for the link.
- *
- * If the link is autonegotiated, drivers should use
- * mii_advertise_flowctrl() or similar code to set the advertised
- * pause frame capabilities based on the @rx_pause and @tx_pause flags,
- * even if @autoneg is zero.  They should also allow the advertised
- * pause frame capabilities to be controlled directly through the
- * advertising field of &struct ethtool_cmd.
- *
- * If @autoneg is non-zero, the MAC is configured to send and/or
- * receive pause frames according to the result of autonegotiation.
- * Otherwise, it is configured directly based on the @rx_pause and
- * @tx_pause flags.
- */
-struct ethtool_pauseparam {
-	__u32	cmd;
-	__u32	autoneg;
-	__u32	rx_pause;
-	__u32	tx_pause;
-};
-
-/* Link extended state */
-enum ethtool_link_ext_state {
-	ETHTOOL_LINK_EXT_STATE_AUTONEG,
-	ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
-	ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH,
-	ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY,
-	ETHTOOL_LINK_EXT_STATE_NO_CABLE,
-	ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE,
-	ETHTOOL_LINK_EXT_STATE_EEPROM_ISSUE,
-	ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE,
-	ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED,
-	ETHTOOL_LINK_EXT_STATE_OVERHEAT,
-	ETHTOOL_LINK_EXT_STATE_MODULE,
-};
-
-/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */
-enum ethtool_link_ext_substate_autoneg {
-	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1,
-	ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED,
-	ETHTOOL_LINK_EXT_SUBSTATE_AN_NEXT_PAGE_EXCHANGE_FAILED,
-	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED_FORCE_MODE,
-	ETHTOOL_LINK_EXT_SUBSTATE_AN_FEC_MISMATCH_DURING_OVERRIDE,
-	ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD,
-};
-
-/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
- */
-enum ethtool_link_ext_substate_link_training {
-	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1,
-	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_INHIBIT_TIMEOUT,
-	ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_LINK_PARTNER_DID_NOT_SET_RECEIVER_READY,
-	ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT,
-};
-
-/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
- */
-enum ethtool_link_ext_substate_link_logical_mismatch {
-	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1,
-	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_AM_LOCK,
-	ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_GET_ALIGN_STATUS,
-	ETHTOOL_LINK_EXT_SUBSTATE_LLM_FC_FEC_IS_NOT_LOCKED,
-	ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED,
-};
-
-/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
- */
-enum ethtool_link_ext_substate_bad_signal_integrity {
-	ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1,
-	ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE,
-	ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_REFERENCE_CLOCK_LOST,
-	ETHTOOL_LINK_EXT_SUBSTATE_BSI_SERDES_ALOS,
-};
-
-/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */
-enum ethtool_link_ext_substate_cable_issue {
-	ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1,
-	ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE,
-};
-
-/* More information in addition to ETHTOOL_LINK_EXT_STATE_MODULE. */
-enum ethtool_link_ext_substate_module {
-	ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY = 1,
-};
-
-#define ETH_GSTRING_LEN		32
-
-/**
- * enum ethtool_stringset - string set ID
- * @ETH_SS_TEST: Self-test result names, for use with %ETHTOOL_TEST
- * @ETH_SS_STATS: Statistic names, for use with %ETHTOOL_GSTATS
- * @ETH_SS_PRIV_FLAGS: Driver private flag names, for use with
- *	%ETHTOOL_GPFLAGS and %ETHTOOL_SPFLAGS
- * @ETH_SS_NTUPLE_FILTERS: Previously used with %ETHTOOL_GRXNTUPLE;
- *	now deprecated
- * @ETH_SS_FEATURES: Device feature names
- * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names
- * @ETH_SS_TUNABLES: tunable names
- * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS
- * @ETH_SS_PHY_TUNABLES: PHY tunable names
- * @ETH_SS_LINK_MODES: link mode names
- * @ETH_SS_MSG_CLASSES: debug message class names
- * @ETH_SS_WOL_MODES: wake-on-lan modes
- * @ETH_SS_SOF_TIMESTAMPING: SOF_TIMESTAMPING_* flags
- * @ETH_SS_TS_TX_TYPES: timestamping Tx types
- * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters
- * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types
- * @ETH_SS_STATS_STD: standardized stats
- * @ETH_SS_STATS_ETH_PHY: names of IEEE 802.3 PHY statistics
- * @ETH_SS_STATS_ETH_MAC: names of IEEE 802.3 MAC statistics
- * @ETH_SS_STATS_ETH_CTRL: names of IEEE 802.3 MAC Control statistics
- * @ETH_SS_STATS_RMON: names of RMON statistics
- *
- * @ETH_SS_COUNT: number of defined string sets
- */
-enum ethtool_stringset {
-	ETH_SS_TEST		= 0,
-	ETH_SS_STATS,
-	ETH_SS_PRIV_FLAGS,
-	ETH_SS_NTUPLE_FILTERS,
-	ETH_SS_FEATURES,
-	ETH_SS_RSS_HASH_FUNCS,
-	ETH_SS_TUNABLES,
-	ETH_SS_PHY_STATS,
-	ETH_SS_PHY_TUNABLES,
-	ETH_SS_LINK_MODES,
-	ETH_SS_MSG_CLASSES,
-	ETH_SS_WOL_MODES,
-	ETH_SS_SOF_TIMESTAMPING,
-	ETH_SS_TS_TX_TYPES,
-	ETH_SS_TS_RX_FILTERS,
-	ETH_SS_UDP_TUNNEL_TYPES,
-	ETH_SS_STATS_STD,
-	ETH_SS_STATS_ETH_PHY,
-	ETH_SS_STATS_ETH_MAC,
-	ETH_SS_STATS_ETH_CTRL,
-	ETH_SS_STATS_RMON,
-
-	/* add new constants above here */
-	ETH_SS_COUNT
-};
-
-/**
- * enum ethtool_mac_stats_src - source of ethtool MAC statistics
- * @ETHTOOL_MAC_STATS_SRC_AGGREGATE:
- *	if device supports a MAC merge layer, this retrieves the aggregate
- *	statistics of the eMAC and pMAC. Otherwise, it retrieves just the
- *	statistics of the single (express) MAC.
- * @ETHTOOL_MAC_STATS_SRC_EMAC:
- *	if device supports a MM layer, this retrieves the eMAC statistics.
- *	Otherwise, it retrieves the statistics of the single (express) MAC.
- * @ETHTOOL_MAC_STATS_SRC_PMAC:
- *	if device supports a MM layer, this retrieves the pMAC statistics.
- */
-enum ethtool_mac_stats_src {
-	ETHTOOL_MAC_STATS_SRC_AGGREGATE,
-	ETHTOOL_MAC_STATS_SRC_EMAC,
-	ETHTOOL_MAC_STATS_SRC_PMAC,
-};
-
-/**
- * enum ethtool_module_power_mode_policy - plug-in module power mode policy
- * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode.
- * @ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO: Module is transitioned by the host
- *	to high power mode when the first port using it is put administratively
- *	up and to low power mode when the last port using it is put
- *	administratively down.
- */
-enum ethtool_module_power_mode_policy {
-	ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH = 1,
-	ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO,
-};
-
-/**
- * enum ethtool_module_power_mode - plug-in module power mode
- * @ETHTOOL_MODULE_POWER_MODE_LOW: Module is in low power mode.
- * @ETHTOOL_MODULE_POWER_MODE_HIGH: Module is in high power mode.
- */
-enum ethtool_module_power_mode {
-	ETHTOOL_MODULE_POWER_MODE_LOW = 1,
-	ETHTOOL_MODULE_POWER_MODE_HIGH,
-};
-
-/**
- * enum ethtool_podl_pse_admin_state - operational state of the PoDL PSE
- *	functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState
- * @ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN: state of PoDL PSE functions are
- * 	unknown
- * @ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED: PoDL PSE functions are disabled
- * @ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED: PoDL PSE functions are enabled
- */
-enum ethtool_podl_pse_admin_state {
-	ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN = 1,
-	ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED,
-	ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED,
-};
-
-/**
- * enum ethtool_podl_pse_pw_d_status - power detection status of the PoDL PSE.
- *	IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus:
- * @ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN: PoDL PSE
- * @ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED: "The enumeration “disabled” is
- *	asserted true when the PoDL PSE state diagram variable mr_pse_enable is
- *	false"
- * @ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING: "The enumeration “searching” is
- *	asserted true when either of the PSE state diagram variables
- *	pi_detecting or pi_classifying is true."
- * @ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING: "The enumeration “deliveringPower”
- *	is asserted true when the PoDL PSE state diagram variable pi_powered is
- *	true."
- * @ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP: "The enumeration “sleep” is asserted
- *	true when the PoDL PSE state diagram variable pi_sleeping is true."
- * @ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE: "The enumeration “idle” is asserted true
- *	when the logical combination of the PoDL PSE state diagram variables
- *	pi_prebiased*!pi_sleeping is true."
- * @ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR: "The enumeration “error” is asserted
- *	true when the PoDL PSE state diagram variable overload_held is true."
- */
-enum ethtool_podl_pse_pw_d_status {
-	ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN = 1,
-	ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED,
-	ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING,
-	ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING,
-	ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP,
-	ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE,
-	ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR,
-};
-
-/**
- * enum ethtool_mm_verify_status - status of MAC Merge Verify function
- * @ETHTOOL_MM_VERIFY_STATUS_UNKNOWN:
- *	verification status is unknown
- * @ETHTOOL_MM_VERIFY_STATUS_INITIAL:
- *	the 802.3 Verify State diagram is in the state INIT_VERIFICATION
- * @ETHTOOL_MM_VERIFY_STATUS_VERIFYING:
- *	the Verify State diagram is in the state VERIFICATION_IDLE,
- *	SEND_VERIFY or WAIT_FOR_RESPONSE
- * @ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED:
- *	indicates that the Verify State diagram is in the state VERIFIED
- * @ETHTOOL_MM_VERIFY_STATUS_FAILED:
- *	the Verify State diagram is in the state VERIFY_FAIL
- * @ETHTOOL_MM_VERIFY_STATUS_DISABLED:
- *	verification of preemption operation is disabled
- */
-enum ethtool_mm_verify_status {
-	ETHTOOL_MM_VERIFY_STATUS_UNKNOWN,
-	ETHTOOL_MM_VERIFY_STATUS_INITIAL,
-	ETHTOOL_MM_VERIFY_STATUS_VERIFYING,
-	ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED,
-	ETHTOOL_MM_VERIFY_STATUS_FAILED,
-	ETHTOOL_MM_VERIFY_STATUS_DISABLED,
-};
-
-/**
- * struct ethtool_gstrings - string set for data tagging
- * @cmd: Command number = %ETHTOOL_GSTRINGS
- * @string_set: String set ID; one of &enum ethtool_stringset
- * @len: On return, the number of strings in the string set
- * @data: Buffer for strings.  Each string is null-padded to a size of
- *	%ETH_GSTRING_LEN.
- *
- * Users must use %ETHTOOL_GSSET_INFO to find the number of strings in
- * the string set.  They must allocate a buffer of the appropriate
- * size immediately following this structure.
- */
-struct ethtool_gstrings {
-	__u32	cmd;
-	__u32	string_set;
-	__u32	len;
-	__u8	data[];
-};
-
-/**
- * struct ethtool_sset_info - string set information
- * @cmd: Command number = %ETHTOOL_GSSET_INFO
- * @reserved: Reserved for future use; see the note on reserved space.
- * @sset_mask: On entry, a bitmask of string sets to query, with bits
- *	numbered according to &enum ethtool_stringset.  On return, a
- *	bitmask of those string sets queried that are supported.
- * @data: Buffer for string set sizes.  On return, this contains the
- *	size of each string set that was queried and supported, in
- *	order of ID.
- *
- * Example: The user passes in @sset_mask = 0x7 (sets 0, 1, 2) and on
- * return @sset_mask == 0x6 (sets 1, 2).  Then @data[0] contains the
- * size of set 1 and @data[1] contains the size of set 2.
- *
- * Users must allocate a buffer of the appropriate size (4 * number of
- * sets queried) immediately following this structure.
- */
-struct ethtool_sset_info {
-	__u32	cmd;
-	__u32	reserved;
-	__u64	sset_mask;
-	__u32	data[];
-};
-
-/**
- * enum ethtool_test_flags - flags definition of ethtool_test
- * @ETH_TEST_FL_OFFLINE: if set perform online and offline tests, otherwise
- *	only online tests.
- * @ETH_TEST_FL_FAILED: Driver set this flag if test fails.
- * @ETH_TEST_FL_EXTERNAL_LB: Application request to perform external loopback
- *	test.
- * @ETH_TEST_FL_EXTERNAL_LB_DONE: Driver performed the external loopback test
- */
-
-enum ethtool_test_flags {
-	ETH_TEST_FL_OFFLINE	= (1 << 0),
-	ETH_TEST_FL_FAILED	= (1 << 1),
-	ETH_TEST_FL_EXTERNAL_LB	= (1 << 2),
-	ETH_TEST_FL_EXTERNAL_LB_DONE	= (1 << 3),
-};
-
-/**
- * struct ethtool_test - device self-test invocation
- * @cmd: Command number = %ETHTOOL_TEST
- * @flags: A bitmask of flags from &enum ethtool_test_flags.  Some
- *	flags may be set by the user on entry; others may be set by
- *	the driver on return.
- * @reserved: Reserved for future use; see the note on reserved space.
- * @len: On return, the number of test results
- * @data: Array of test results
- *
- * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the
- * number of test results that will be returned.  They must allocate a
- * buffer of the appropriate size (8 * number of results) immediately
- * following this structure.
- */
-struct ethtool_test {
-	__u32	cmd;
-	__u32	flags;
-	__u32	reserved;
-	__u32	len;
-	__u64	data[];
-};
-
-/**
- * struct ethtool_stats - device-specific statistics
- * @cmd: Command number = %ETHTOOL_GSTATS
- * @n_stats: On return, the number of statistics
- * @data: Array of statistics
- *
- * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the
- * number of statistics that will be returned.  They must allocate a
- * buffer of the appropriate size (8 * number of statistics)
- * immediately following this structure.
- */
-struct ethtool_stats {
-	__u32	cmd;
-	__u32	n_stats;
-	__u64	data[];
-};
-
-/**
- * struct ethtool_perm_addr - permanent hardware address
- * @cmd: Command number = %ETHTOOL_GPERMADDR
- * @size: On entry, the size of the buffer.  On return, the size of the
- *	address.  The command fails if the buffer is too small.
- * @data: Buffer for the address
- *
- * Users must allocate the buffer immediately following this structure.
- * A buffer size of %MAX_ADDR_LEN should be sufficient for any address
- * type.
- */
-struct ethtool_perm_addr {
-	__u32	cmd;
-	__u32	size;
-	__u8	data[];
-};
-
-/* boolean flags controlling per-interface behavior characteristics.
- * When reading, the flag indicates whether or not a certain behavior
- * is enabled/present.  When writing, the flag indicates whether
- * or not the driver should turn on (set) or off (clear) a behavior.
- *
- * Some behaviors may read-only (unconditionally absent or present).
- * If such is the case, return EINVAL in the set-flags operation if the
- * flag differs from the read-only value.
- */
-enum ethtool_flags {
-	ETH_FLAG_TXVLAN		= (1 << 7),	/* TX VLAN offload enabled */
-	ETH_FLAG_RXVLAN		= (1 << 8),	/* RX VLAN offload enabled */
-	ETH_FLAG_LRO		= (1 << 15),	/* LRO is enabled */
-	ETH_FLAG_NTUPLE		= (1 << 27),	/* N-tuple filters enabled */
-	ETH_FLAG_RXHASH		= (1 << 28),
-};
-
-/* The following structures are for supporting RX network flow
- * classification and RX n-tuple configuration. Note, all multibyte
- * fields, e.g., ip4src, ip4dst, psrc, pdst, spi, etc. are expected to
- * be in network byte order.
- */
-
-/**
- * struct ethtool_tcpip4_spec - flow specification for TCP/IPv4 etc.
- * @ip4src: Source host
- * @ip4dst: Destination host
- * @psrc: Source port
- * @pdst: Destination port
- * @tos: Type-of-service
- *
- * This can be used to specify a TCP/IPv4, UDP/IPv4 or SCTP/IPv4 flow.
- */
-struct ethtool_tcpip4_spec {
-	__be32	ip4src;
-	__be32	ip4dst;
-	__be16	psrc;
-	__be16	pdst;
-	__u8    tos;
-};
-
-/**
- * struct ethtool_ah_espip4_spec - flow specification for IPsec/IPv4
- * @ip4src: Source host
- * @ip4dst: Destination host
- * @spi: Security parameters index
- * @tos: Type-of-service
- *
- * This can be used to specify an IPsec transport or tunnel over IPv4.
- */
-struct ethtool_ah_espip4_spec {
-	__be32	ip4src;
-	__be32	ip4dst;
-	__be32	spi;
-	__u8    tos;
-};
-
-#define	ETH_RX_NFC_IP4	1
-
-/**
- * struct ethtool_usrip4_spec - general flow specification for IPv4
- * @ip4src: Source host
- * @ip4dst: Destination host
- * @l4_4_bytes: First 4 bytes of transport (layer 4) header
- * @tos: Type-of-service
- * @ip_ver: Value must be %ETH_RX_NFC_IP4; mask must be 0
- * @proto: Transport protocol number; mask must be 0
- */
-struct ethtool_usrip4_spec {
-	__be32	ip4src;
-	__be32	ip4dst;
-	__be32	l4_4_bytes;
-	__u8    tos;
-	__u8    ip_ver;
-	__u8    proto;
-};
-
-/**
- * struct ethtool_tcpip6_spec - flow specification for TCP/IPv6 etc.
- * @ip6src: Source host
- * @ip6dst: Destination host
- * @psrc: Source port
- * @pdst: Destination port
- * @tclass: Traffic Class
- *
- * This can be used to specify a TCP/IPv6, UDP/IPv6 or SCTP/IPv6 flow.
- */
-struct ethtool_tcpip6_spec {
-	__be32	ip6src[4];
-	__be32	ip6dst[4];
-	__be16	psrc;
-	__be16	pdst;
-	__u8    tclass;
-};
-
-/**
- * struct ethtool_ah_espip6_spec - flow specification for IPsec/IPv6
- * @ip6src: Source host
- * @ip6dst: Destination host
- * @spi: Security parameters index
- * @tclass: Traffic Class
- *
- * This can be used to specify an IPsec transport or tunnel over IPv6.
- */
-struct ethtool_ah_espip6_spec {
-	__be32	ip6src[4];
-	__be32	ip6dst[4];
-	__be32	spi;
-	__u8    tclass;
-};
-
-/**
- * struct ethtool_usrip6_spec - general flow specification for IPv6
- * @ip6src: Source host
- * @ip6dst: Destination host
- * @l4_4_bytes: First 4 bytes of transport (layer 4) header
- * @tclass: Traffic Class
- * @l4_proto: Transport protocol number (nexthdr after any Extension Headers)
- */
-struct ethtool_usrip6_spec {
-	__be32	ip6src[4];
-	__be32	ip6dst[4];
-	__be32	l4_4_bytes;
-	__u8    tclass;
-	__u8    l4_proto;
-};
-
-union ethtool_flow_union {
-	struct ethtool_tcpip4_spec		tcp_ip4_spec;
-	struct ethtool_tcpip4_spec		udp_ip4_spec;
-	struct ethtool_tcpip4_spec		sctp_ip4_spec;
-	struct ethtool_ah_espip4_spec		ah_ip4_spec;
-	struct ethtool_ah_espip4_spec		esp_ip4_spec;
-	struct ethtool_usrip4_spec		usr_ip4_spec;
-	struct ethtool_tcpip6_spec		tcp_ip6_spec;
-	struct ethtool_tcpip6_spec		udp_ip6_spec;
-	struct ethtool_tcpip6_spec		sctp_ip6_spec;
-	struct ethtool_ah_espip6_spec		ah_ip6_spec;
-	struct ethtool_ah_espip6_spec		esp_ip6_spec;
-	struct ethtool_usrip6_spec		usr_ip6_spec;
-	struct ethhdr				ether_spec;
-	__u8					hdata[52];
-};
-
-/**
- * struct ethtool_flow_ext - additional RX flow fields
- * @h_dest: destination MAC address
- * @vlan_etype: VLAN EtherType
- * @vlan_tci: VLAN tag control information
- * @data: user defined data
- * @padding: Reserved for future use; see the note on reserved space.
- *
- * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT
- * is set in &struct ethtool_rx_flow_spec @flow_type.
- * @h_dest is valid if %FLOW_MAC_EXT is set.
- */
-struct ethtool_flow_ext {
-	__u8		padding[2];
-	unsigned char	h_dest[ETH_ALEN];
-	__be16		vlan_etype;
-	__be16		vlan_tci;
-	__be32		data[2];
-};
-
-/**
- * struct ethtool_rx_flow_spec - classification rule for RX flows
- * @flow_type: Type of match to perform, e.g. %TCP_V4_FLOW
- * @h_u: Flow fields to match (dependent on @flow_type)
- * @h_ext: Additional fields to match
- * @m_u: Masks for flow field bits to be matched
- * @m_ext: Masks for additional field bits to be matched
- *	Note, all additional fields must be ignored unless @flow_type
- *	includes the %FLOW_EXT or %FLOW_MAC_EXT flag
- *	(see &struct ethtool_flow_ext description).
- * @ring_cookie: RX ring/queue index to deliver to, or %RX_CLS_FLOW_DISC
- *	if packets should be discarded, or %RX_CLS_FLOW_WAKE if the
- *	packets should be used for Wake-on-LAN with %WAKE_FILTER
- * @location: Location of rule in the table.  Locations must be
- *	numbered such that a flow matching multiple rules will be
- *	classified according to the first (lowest numbered) rule.
- */
-struct ethtool_rx_flow_spec {
-	__u32		flow_type;
-	union ethtool_flow_union h_u;
-	struct ethtool_flow_ext h_ext;
-	union ethtool_flow_union m_u;
-	struct ethtool_flow_ext m_ext;
-	__u64		ring_cookie;
-	__u32		location;
-};
-
-/* How rings are laid out when accessing virtual functions or
- * offloaded queues is device specific. To allow users to do flow
- * steering and specify these queues the ring cookie is partitioned
- * into a 32bit queue index with an 8 bit virtual function id.
- * This also leaves the 3bytes for further specifiers. It is possible
- * future devices may support more than 256 virtual functions if
- * devices start supporting PCIe w/ARI. However at the moment I
- * do not know of any devices that support this so I do not reserve
- * space for this at this time. If a future patch consumes the next
- * byte it should be aware of this possibility.
- */
-#define ETHTOOL_RX_FLOW_SPEC_RING	0x00000000FFFFFFFFLL
-#define ETHTOOL_RX_FLOW_SPEC_RING_VF	0x000000FF00000000LL
-#define ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF 32
-static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie)
-{
-	return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie;
-}
-
-static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie)
-{
-	return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >>
-				ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
-}
-
-/**
- * struct ethtool_rxnfc - command to get or set RX flow classification rules
- * @cmd: Specific command number - %ETHTOOL_GRXFH, %ETHTOOL_SRXFH,
- *	%ETHTOOL_GRXRINGS, %ETHTOOL_GRXCLSRLCNT, %ETHTOOL_GRXCLSRULE,
- *	%ETHTOOL_GRXCLSRLALL, %ETHTOOL_SRXCLSRLDEL or %ETHTOOL_SRXCLSRLINS
- * @flow_type: Type of flow to be affected, e.g. %TCP_V4_FLOW
- * @data: Command-dependent value
- * @fs: Flow classification rule
- * @rss_context: RSS context to be affected
- * @rule_cnt: Number of rules to be affected
- * @rule_locs: Array of used rule locations
- *
- * For %ETHTOOL_GRXFH and %ETHTOOL_SRXFH, @data is a bitmask indicating
- * the fields included in the flow hash, e.g. %RXH_IP_SRC.  The following
- * structure fields must not be used, except that if @flow_type includes
- * the %FLOW_RSS flag, then @rss_context determines which RSS context to
- * act on.
- *
- * For %ETHTOOL_GRXRINGS, @data is set to the number of RX rings/queues
- * on return.
- *
- * For %ETHTOOL_GRXCLSRLCNT, @rule_cnt is set to the number of defined
- * rules on return.  If @data is non-zero on return then it is the
- * size of the rule table, plus the flag %RX_CLS_LOC_SPECIAL if the
- * driver supports any special location values.  If that flag is not
- * set in @data then special location values should not be used.
- *
- * For %ETHTOOL_GRXCLSRULE, @fs.@location specifies the location of an
- * existing rule on entry and @fs contains the rule on return; if
- * @fs.@flow_type includes the %FLOW_RSS flag, then @rss_context is
- * filled with the RSS context ID associated with the rule.
- *
- * For %ETHTOOL_GRXCLSRLALL, @rule_cnt specifies the array size of the
- * user buffer for @rule_locs on entry.  On return, @data is the size
- * of the rule table, @rule_cnt is the number of defined rules, and
- * @rule_locs contains the locations of the defined rules.  Drivers
- * must use the second parameter to get_rxnfc() instead of @rule_locs.
- *
- * For %ETHTOOL_SRXCLSRLINS, @fs specifies the rule to add or update.
- * @fs.@location either specifies the location to use or is a special
- * location value with %RX_CLS_LOC_SPECIAL flag set.  On return,
- * @fs.@location is the actual rule location.  If @fs.@flow_type
- * includes the %FLOW_RSS flag, @rss_context is the RSS context ID to
- * use for flow spreading traffic which matches this rule.  The value
- * from the rxfh indirection table will be added to @fs.@ring_cookie
- * to choose which ring to deliver to.
- *
- * For %ETHTOOL_SRXCLSRLDEL, @fs.@location specifies the location of an
- * existing rule on entry.
- *
- * A driver supporting the special location values for
- * %ETHTOOL_SRXCLSRLINS may add the rule at any suitable unused
- * location, and may remove a rule at a later location (lower
- * priority) that matches exactly the same set of flows.  The special
- * values are %RX_CLS_LOC_ANY, selecting any location;
- * %RX_CLS_LOC_FIRST, selecting the first suitable location (maximum
- * priority); and %RX_CLS_LOC_LAST, selecting the last suitable
- * location (minimum priority).  Additional special values may be
- * defined in future and drivers must return -%EINVAL for any
- * unrecognised value.
- */
-struct ethtool_rxnfc {
-	__u32				cmd;
-	__u32				flow_type;
-	__u64				data;
-	struct ethtool_rx_flow_spec	fs;
-	union {
-		__u32			rule_cnt;
-		__u32			rss_context;
-	};
-	__u32				rule_locs[];
-};
-
-
-/**
- * struct ethtool_rxfh_indir - command to get or set RX flow hash indirection
- * @cmd: Specific command number - %ETHTOOL_GRXFHINDIR or %ETHTOOL_SRXFHINDIR
- * @size: On entry, the array size of the user buffer, which may be zero.
- *	On return from %ETHTOOL_GRXFHINDIR, the array size of the hardware
- *	indirection table.
- * @ring_index: RX ring/queue index for each hash value
- *
- * For %ETHTOOL_GRXFHINDIR, a @size of zero means that only the size
- * should be returned.  For %ETHTOOL_SRXFHINDIR, a @size of zero means
- * the table should be reset to default values.  This last feature
- * is not supported by the original implementations.
- */
-struct ethtool_rxfh_indir {
-	__u32	cmd;
-	__u32	size;
-	__u32	ring_index[];
-};
-
-/**
- * struct ethtool_rxfh - command to get/set RX flow hash indir or/and hash key.
- * @cmd: Specific command number - %ETHTOOL_GRSSH or %ETHTOOL_SRSSH
- * @rss_context: RSS context identifier.  Context 0 is the default for normal
- *	traffic; other contexts can be referenced as the destination for RX flow
- *	classification rules.  %ETH_RXFH_CONTEXT_ALLOC is used with command
- *	%ETHTOOL_SRSSH to allocate a new RSS context; on return this field will
- *	contain the ID of the newly allocated context.
- * @indir_size: On entry, the array size of the user buffer for the
- *	indirection table, which may be zero, or (for %ETHTOOL_SRSSH),
- *	%ETH_RXFH_INDIR_NO_CHANGE.  On return from %ETHTOOL_GRSSH,
- *	the array size of the hardware indirection table.
- * @key_size: On entry, the array size of the user buffer for the hash key,
- *	which may be zero.  On return from %ETHTOOL_GRSSH, the size of the
- *	hardware hash key.
- * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
- *	Valid values are one of the %ETH_RSS_HASH_*.
- * @input_xfrm: Defines how the input data is transformed. Valid values are one
- *	of %RXH_XFRM_*.
- * @rsvd8: Reserved for future use; see the note on reserved space.
- * @rsvd32: Reserved for future use; see the note on reserved space.
- * @rss_config: RX ring/queue index for each hash value i.e., indirection table
- *	of @indir_size __u32 elements, followed by hash key of @key_size
- *	bytes.
- *
- * For %ETHTOOL_GRSSH, a @indir_size and key_size of zero means that only the
- * size should be returned.  For %ETHTOOL_SRSSH, an @indir_size of
- * %ETH_RXFH_INDIR_NO_CHANGE means that indir table setting is not requested
- * and a @indir_size of zero means the indir table should be reset to default
- * values (if @rss_context == 0) or that the RSS context should be deleted.
- * An hfunc of zero means that hash function setting is not requested.
- */
-struct ethtool_rxfh {
-	__u32   cmd;
-	__u32	rss_context;
-	__u32   indir_size;
-	__u32   key_size;
-	__u8	hfunc;
-	__u8	input_xfrm;
-	__u8	rsvd8[2];
-	__u32	rsvd32;
-	__u32   rss_config[];
-};
-#define ETH_RXFH_CONTEXT_ALLOC		0xffffffff
-#define ETH_RXFH_INDIR_NO_CHANGE	0xffffffff
-
-/**
- * struct ethtool_rx_ntuple_flow_spec - specification for RX flow filter
- * @flow_type: Type of match to perform, e.g. %TCP_V4_FLOW
- * @h_u: Flow field values to match (dependent on @flow_type)
- * @m_u: Masks for flow field value bits to be ignored
- * @vlan_tag: VLAN tag to match
- * @vlan_tag_mask: Mask for VLAN tag bits to be ignored
- * @data: Driver-dependent data to match
- * @data_mask: Mask for driver-dependent data bits to be ignored
- * @action: RX ring/queue index to deliver to (non-negative) or other action
- *	(negative, e.g. %ETHTOOL_RXNTUPLE_ACTION_DROP)
- *
- * For flow types %TCP_V4_FLOW, %UDP_V4_FLOW and %SCTP_V4_FLOW, where
- * a field value and mask are both zero this is treated as if all mask
- * bits are set i.e. the field is ignored.
- */
-struct ethtool_rx_ntuple_flow_spec {
-	__u32		 flow_type;
-	union {
-		struct ethtool_tcpip4_spec		tcp_ip4_spec;
-		struct ethtool_tcpip4_spec		udp_ip4_spec;
-		struct ethtool_tcpip4_spec		sctp_ip4_spec;
-		struct ethtool_ah_espip4_spec		ah_ip4_spec;
-		struct ethtool_ah_espip4_spec		esp_ip4_spec;
-		struct ethtool_usrip4_spec		usr_ip4_spec;
-		struct ethhdr				ether_spec;
-		__u8					hdata[72];
-	} h_u, m_u;
-
-	__u16	        vlan_tag;
-	__u16	        vlan_tag_mask;
-	__u64		data;
-	__u64		data_mask;
-
-	__s32		action;
-#define ETHTOOL_RXNTUPLE_ACTION_DROP	(-1)	/* drop packet */
-#define ETHTOOL_RXNTUPLE_ACTION_CLEAR	(-2)	/* clear filter */
-};
-
-/**
- * struct ethtool_rx_ntuple - command to set or clear RX flow filter
- * @cmd: Command number - %ETHTOOL_SRXNTUPLE
- * @fs: Flow filter specification
- */
-struct ethtool_rx_ntuple {
-	__u32					cmd;
-	struct ethtool_rx_ntuple_flow_spec	fs;
-};
-
-#define ETHTOOL_FLASH_MAX_FILENAME	128
-enum ethtool_flash_op_type {
-	ETHTOOL_FLASH_ALL_REGIONS	= 0,
-};
-
-/* for passing firmware flashing related parameters */
-struct ethtool_flash {
-	__u32	cmd;
-	__u32	region;
-	char	data[ETHTOOL_FLASH_MAX_FILENAME];
-};
-
-/**
- * struct ethtool_dump - used for retrieving, setting device dump
- * @cmd: Command number - %ETHTOOL_GET_DUMP_FLAG, %ETHTOOL_GET_DUMP_DATA, or
- * 	%ETHTOOL_SET_DUMP
- * @version: FW version of the dump, filled in by driver
- * @flag: driver dependent flag for dump setting, filled in by driver during
- *        get and filled in by ethtool for set operation.
- *        flag must be initialized by macro ETH_FW_DUMP_DISABLE value when
- *        firmware dump is disabled.
- * @len: length of dump data, used as the length of the user buffer on entry to
- * 	 %ETHTOOL_GET_DUMP_DATA and this is returned as dump length by driver
- * 	 for %ETHTOOL_GET_DUMP_FLAG command
- * @data: data collected for get dump data operation
- */
-struct ethtool_dump {
-	__u32	cmd;
-	__u32	version;
-	__u32	flag;
-	__u32	len;
-	__u8	data[];
-};
-
-#define ETH_FW_DUMP_DISABLE 0
-
-/* for returning and changing feature sets */
-
-/**
- * struct ethtool_get_features_block - block with state of 32 features
- * @available: mask of changeable features
- * @requested: mask of features requested to be enabled if possible
- * @active: mask of currently enabled features
- * @never_changed: mask of features not changeable for any device
- */
-struct ethtool_get_features_block {
-	__u32	available;
-	__u32	requested;
-	__u32	active;
-	__u32	never_changed;
-};
-
-/**
- * struct ethtool_gfeatures - command to get state of device's features
- * @cmd: command number = %ETHTOOL_GFEATURES
- * @size: On entry, the number of elements in the features[] array;
- *	on return, the number of elements in features[] needed to hold
- *	all features
- * @features: state of features
- */
-struct ethtool_gfeatures {
-	__u32	cmd;
-	__u32	size;
-	struct ethtool_get_features_block features[];
-};
-
-/**
- * struct ethtool_set_features_block - block with request for 32 features
- * @valid: mask of features to be changed
- * @requested: values of features to be changed
- */
-struct ethtool_set_features_block {
-	__u32	valid;
-	__u32	requested;
-};
-
-/**
- * struct ethtool_sfeatures - command to request change in device's features
- * @cmd: command number = %ETHTOOL_SFEATURES
- * @size: array size of the features[] array
- * @features: feature change masks
- */
-struct ethtool_sfeatures {
-	__u32	cmd;
-	__u32	size;
-	struct ethtool_set_features_block features[];
-};
-
-/**
- * struct ethtool_ts_info - holds a device's timestamping and PHC association
- * @cmd: command number = %ETHTOOL_GET_TS_INFO
- * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags
- * @phc_index: device index of the associated PHC, or -1 if there is none
- * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values
- * @tx_reserved: Reserved for future use; see the note on reserved space.
- * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values
- * @rx_reserved: Reserved for future use; see the note on reserved space.
- *
- * The bits in the 'tx_types' and 'rx_filters' fields correspond to
- * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values,
- * respectively.  For example, if the device supports HWTSTAMP_TX_ON,
- * then (1 << HWTSTAMP_TX_ON) in 'tx_types' will be set.
- *
- * Drivers should only report the filters they actually support without
- * upscaling in the SIOCSHWTSTAMP ioctl. If the SIOCSHWSTAMP request for
- * HWTSTAMP_FILTER_V1_SYNC is supported by HWTSTAMP_FILTER_V1_EVENT, then the
- * driver should only report HWTSTAMP_FILTER_V1_EVENT in this op.
- */
-struct ethtool_ts_info {
-	__u32	cmd;
-	__u32	so_timestamping;
-	__s32	phc_index;
-	__u32	tx_types;
-	__u32	tx_reserved[3];
-	__u32	rx_filters;
-	__u32	rx_reserved[3];
-};
-
-/*
- * %ETHTOOL_SFEATURES changes features present in features[].valid to the
- * values of corresponding bits in features[].requested. Bits in .requested
- * not set in .valid or not changeable are ignored.
- *
- * Returns %EINVAL when .valid contains undefined or never-changeable bits
- * or size is not equal to required number of features words (32-bit blocks).
- * Returns >= 0 if request was completed; bits set in the value mean:
- *   %ETHTOOL_F_UNSUPPORTED - there were bits set in .valid that are not
- *	changeable (not present in %ETHTOOL_GFEATURES' features[].available)
- *	those bits were ignored.
- *   %ETHTOOL_F_WISH - some or all changes requested were recorded but the
- *      resulting state of bits masked by .valid is not equal to .requested.
- *      Probably there are other device-specific constraints on some features
- *      in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered
- *      here as though ignored bits were cleared.
- *   %ETHTOOL_F_COMPAT - some or all changes requested were made by calling
- *      compatibility functions. Requested offload state cannot be properly
- *      managed by kernel.
- *
- * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of
- * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands
- * for ETH_SS_FEATURES string set. First entry in the table corresponds to least
- * significant bit in features[0] fields. Empty strings mark undefined features.
- */
-enum ethtool_sfeatures_retval_bits {
-	ETHTOOL_F_UNSUPPORTED__BIT,
-	ETHTOOL_F_WISH__BIT,
-	ETHTOOL_F_COMPAT__BIT,
-};
-
-#define ETHTOOL_F_UNSUPPORTED   (1 << ETHTOOL_F_UNSUPPORTED__BIT)
-#define ETHTOOL_F_WISH          (1 << ETHTOOL_F_WISH__BIT)
-#define ETHTOOL_F_COMPAT        (1 << ETHTOOL_F_COMPAT__BIT)
-
-#define MAX_NUM_QUEUE		4096
-
-/**
- * struct ethtool_per_queue_op - apply sub command to the queues in mask.
- * @cmd: ETHTOOL_PERQUEUE
- * @sub_command: the sub command which apply to each queues
- * @queue_mask: Bitmap of the queues which sub command apply to
- * @data: A complete command structure following for each of the queues addressed
- */
-struct ethtool_per_queue_op {
-	__u32	cmd;
-	__u32	sub_command;
-	__u32	queue_mask[__KERNEL_DIV_ROUND_UP(MAX_NUM_QUEUE, 32)];
-	char	data[];
-};
-
-/**
- * struct ethtool_fecparam - Ethernet Forward Error Correction parameters
- * @cmd: Command number = %ETHTOOL_GFECPARAM or %ETHTOOL_SFECPARAM
- * @active_fec: FEC mode which is active on the port, single bit set, GET only.
- * @fec: Bitmask of configured FEC modes.
- * @reserved: Reserved for future extensions, ignore on GET, write 0 for SET.
- *
- * Note that @reserved was never validated on input and ethtool user space
- * left it uninitialized when calling SET. Hence going forward it can only be
- * used to return a value to userspace with GET.
- *
- * FEC modes supported by the device can be read via %ETHTOOL_GLINKSETTINGS.
- * FEC settings are configured by link autonegotiation whenever it's enabled.
- * With autoneg on %ETHTOOL_GFECPARAM can be used to read the current mode.
- *
- * When autoneg is disabled %ETHTOOL_SFECPARAM controls the FEC settings.
- * It is recommended that drivers only accept a single bit set in @fec.
- * When multiple bits are set in @fec drivers may pick mode in an implementation
- * dependent way. Drivers should reject mixing %ETHTOOL_FEC_AUTO_BIT with other
- * FEC modes, because it's unclear whether in this case other modes constrain
- * AUTO or are independent choices.
- * Drivers must reject SET requests if they support none of the requested modes.
- *
- * If device does not support FEC drivers may use %ETHTOOL_FEC_NONE instead
- * of returning %EOPNOTSUPP from %ETHTOOL_GFECPARAM.
- *
- * See enum ethtool_fec_config_bits for definition of valid bits for both
- * @fec and @active_fec.
- */
-struct ethtool_fecparam {
-	__u32   cmd;
-	/* bitmask of FEC modes */
-	__u32   active_fec;
-	__u32   fec;
-	__u32   reserved;
-};
-
-/**
- * enum ethtool_fec_config_bits - flags definition of ethtool_fec_configuration
- * @ETHTOOL_FEC_NONE_BIT: FEC mode configuration is not supported. Should not
- *			be used together with other bits. GET only.
- * @ETHTOOL_FEC_AUTO_BIT: Select default/best FEC mode automatically, usually
- *			based link mode and SFP parameters read from module's
- *			EEPROM. This bit does _not_ mean autonegotiation.
- * @ETHTOOL_FEC_OFF_BIT: No FEC Mode
- * @ETHTOOL_FEC_RS_BIT: Reed-Solomon FEC Mode
- * @ETHTOOL_FEC_BASER_BIT: Base-R/Reed-Solomon FEC Mode
- * @ETHTOOL_FEC_LLRS_BIT: Low Latency Reed Solomon FEC Mode (25G/50G Ethernet
- *			Consortium)
- */
-enum ethtool_fec_config_bits {
-	ETHTOOL_FEC_NONE_BIT,
-	ETHTOOL_FEC_AUTO_BIT,
-	ETHTOOL_FEC_OFF_BIT,
-	ETHTOOL_FEC_RS_BIT,
-	ETHTOOL_FEC_BASER_BIT,
-	ETHTOOL_FEC_LLRS_BIT,
-};
-
-#define ETHTOOL_FEC_NONE		(1 << ETHTOOL_FEC_NONE_BIT)
-#define ETHTOOL_FEC_AUTO		(1 << ETHTOOL_FEC_AUTO_BIT)
-#define ETHTOOL_FEC_OFF			(1 << ETHTOOL_FEC_OFF_BIT)
-#define ETHTOOL_FEC_RS			(1 << ETHTOOL_FEC_RS_BIT)
-#define ETHTOOL_FEC_BASER		(1 << ETHTOOL_FEC_BASER_BIT)
-#define ETHTOOL_FEC_LLRS		(1 << ETHTOOL_FEC_LLRS_BIT)
-
-/* CMDs currently supported */
-#define ETHTOOL_GSET		0x00000001 /* DEPRECATED, Get settings.
-					    * Please use ETHTOOL_GLINKSETTINGS
-					    */
-#define ETHTOOL_SSET		0x00000002 /* DEPRECATED, Set settings.
-					    * Please use ETHTOOL_SLINKSETTINGS
-					    */
-#define ETHTOOL_GDRVINFO	0x00000003 /* Get driver info. */
-#define ETHTOOL_GREGS		0x00000004 /* Get NIC registers. */
-#define ETHTOOL_GWOL		0x00000005 /* Get wake-on-lan options. */
-#define ETHTOOL_SWOL		0x00000006 /* Set wake-on-lan options. */
-#define ETHTOOL_GMSGLVL		0x00000007 /* Get driver message level */
-#define ETHTOOL_SMSGLVL		0x00000008 /* Set driver msg level. */
-#define ETHTOOL_NWAY_RST	0x00000009 /* Restart autonegotiation. */
-/* Get link status for host, i.e. whether the interface *and* the
- * physical port (if there is one) are up (ethtool_value). */
-#define ETHTOOL_GLINK		0x0000000a
-#define ETHTOOL_GEEPROM		0x0000000b /* Get EEPROM data */
-#define ETHTOOL_SEEPROM		0x0000000c /* Set EEPROM data. */
-#define ETHTOOL_GCOALESCE	0x0000000e /* Get coalesce config */
-#define ETHTOOL_SCOALESCE	0x0000000f /* Set coalesce config. */
-#define ETHTOOL_GRINGPARAM	0x00000010 /* Get ring parameters */
-#define ETHTOOL_SRINGPARAM	0x00000011 /* Set ring parameters. */
-#define ETHTOOL_GPAUSEPARAM	0x00000012 /* Get pause parameters */
-#define ETHTOOL_SPAUSEPARAM	0x00000013 /* Set pause parameters. */
-#define ETHTOOL_GRXCSUM		0x00000014 /* Get RX hw csum enable (ethtool_value) */
-#define ETHTOOL_SRXCSUM		0x00000015 /* Set RX hw csum enable (ethtool_value) */
-#define ETHTOOL_GTXCSUM		0x00000016 /* Get TX hw csum enable (ethtool_value) */
-#define ETHTOOL_STXCSUM		0x00000017 /* Set TX hw csum enable (ethtool_value) */
-#define ETHTOOL_GSG		0x00000018 /* Get scatter-gather enable
-					    * (ethtool_value) */
-#define ETHTOOL_SSG		0x00000019 /* Set scatter-gather enable
-					    * (ethtool_value). */
-#define ETHTOOL_TEST		0x0000001a /* execute NIC self-test. */
-#define ETHTOOL_GSTRINGS	0x0000001b /* get specified string set */
-#define ETHTOOL_PHYS_ID		0x0000001c /* identify the NIC */
-#define ETHTOOL_GSTATS		0x0000001d /* get NIC-specific statistics */
-#define ETHTOOL_GTSO		0x0000001e /* Get TSO enable (ethtool_value) */
-#define ETHTOOL_STSO		0x0000001f /* Set TSO enable (ethtool_value) */
-#define ETHTOOL_GPERMADDR	0x00000020 /* Get permanent hardware address */
-#define ETHTOOL_GUFO		0x00000021 /* Get UFO enable (ethtool_value) */
-#define ETHTOOL_SUFO		0x00000022 /* Set UFO enable (ethtool_value) */
-#define ETHTOOL_GGSO		0x00000023 /* Get GSO enable (ethtool_value) */
-#define ETHTOOL_SGSO		0x00000024 /* Set GSO enable (ethtool_value) */
-#define ETHTOOL_GFLAGS		0x00000025 /* Get flags bitmap(ethtool_value) */
-#define ETHTOOL_SFLAGS		0x00000026 /* Set flags bitmap(ethtool_value) */
-#define ETHTOOL_GPFLAGS		0x00000027 /* Get driver-private flags bitmap */
-#define ETHTOOL_SPFLAGS		0x00000028 /* Set driver-private flags bitmap */
-
-#define ETHTOOL_GRXFH		0x00000029 /* Get RX flow hash configuration */
-#define ETHTOOL_SRXFH		0x0000002a /* Set RX flow hash configuration */
-#define ETHTOOL_GGRO		0x0000002b /* Get GRO enable (ethtool_value) */
-#define ETHTOOL_SGRO		0x0000002c /* Set GRO enable (ethtool_value) */
-#define ETHTOOL_GRXRINGS	0x0000002d /* Get RX rings available for LB */
-#define ETHTOOL_GRXCLSRLCNT	0x0000002e /* Get RX class rule count */
-#define ETHTOOL_GRXCLSRULE	0x0000002f /* Get RX classification rule */
-#define ETHTOOL_GRXCLSRLALL	0x00000030 /* Get all RX classification rule */
-#define ETHTOOL_SRXCLSRLDEL	0x00000031 /* Delete RX classification rule */
-#define ETHTOOL_SRXCLSRLINS	0x00000032 /* Insert RX classification rule */
-#define ETHTOOL_FLASHDEV	0x00000033 /* Flash firmware to device */
-#define ETHTOOL_RESET		0x00000034 /* Reset hardware */
-#define ETHTOOL_SRXNTUPLE	0x00000035 /* Add an n-tuple filter to device */
-#define ETHTOOL_GRXNTUPLE	0x00000036 /* deprecated */
-#define ETHTOOL_GSSET_INFO	0x00000037 /* Get string set info */
-#define ETHTOOL_GRXFHINDIR	0x00000038 /* Get RX flow hash indir'n table */
-#define ETHTOOL_SRXFHINDIR	0x00000039 /* Set RX flow hash indir'n table */
-
-#define ETHTOOL_GFEATURES	0x0000003a /* Get device offload settings */
-#define ETHTOOL_SFEATURES	0x0000003b /* Change device offload settings */
-#define ETHTOOL_GCHANNELS	0x0000003c /* Get no of channels */
-#define ETHTOOL_SCHANNELS	0x0000003d /* Set no of channels */
-#define ETHTOOL_SET_DUMP	0x0000003e /* Set dump settings */
-#define ETHTOOL_GET_DUMP_FLAG	0x0000003f /* Get dump settings */
-#define ETHTOOL_GET_DUMP_DATA	0x00000040 /* Get dump data */
-#define ETHTOOL_GET_TS_INFO	0x00000041 /* Get time stamping and PHC info */
-#define ETHTOOL_GMODULEINFO	0x00000042 /* Get plug-in module information */
-#define ETHTOOL_GMODULEEEPROM	0x00000043 /* Get plug-in module eeprom */
-#define ETHTOOL_GEEE		0x00000044 /* Get EEE settings */
-#define ETHTOOL_SEEE		0x00000045 /* Set EEE settings */
-
-#define ETHTOOL_GRSSH		0x00000046 /* Get RX flow hash configuration */
-#define ETHTOOL_SRSSH		0x00000047 /* Set RX flow hash configuration */
-#define ETHTOOL_GTUNABLE	0x00000048 /* Get tunable configuration */
-#define ETHTOOL_STUNABLE	0x00000049 /* Set tunable configuration */
-#define ETHTOOL_GPHYSTATS	0x0000004a /* get PHY-specific statistics */
-
-#define ETHTOOL_PERQUEUE	0x0000004b /* Set per queue options */
-
-#define ETHTOOL_GLINKSETTINGS	0x0000004c /* Get ethtool_link_settings */
-#define ETHTOOL_SLINKSETTINGS	0x0000004d /* Set ethtool_link_settings */
-#define ETHTOOL_PHY_GTUNABLE	0x0000004e /* Get PHY tunable configuration */
-#define ETHTOOL_PHY_STUNABLE	0x0000004f /* Set PHY tunable configuration */
-#define ETHTOOL_GFECPARAM	0x00000050 /* Get FEC settings */
-#define ETHTOOL_SFECPARAM	0x00000051 /* Set FEC settings */
-
-/* compatibility with older code */
-#define SPARC_ETH_GSET		ETHTOOL_GSET
-#define SPARC_ETH_SSET		ETHTOOL_SSET
-
-/* Link mode bit indices */
-enum ethtool_link_mode_bit_indices {
-	ETHTOOL_LINK_MODE_10baseT_Half_BIT	= 0,
-	ETHTOOL_LINK_MODE_10baseT_Full_BIT	= 1,
-	ETHTOOL_LINK_MODE_100baseT_Half_BIT	= 2,
-	ETHTOOL_LINK_MODE_100baseT_Full_BIT	= 3,
-	ETHTOOL_LINK_MODE_1000baseT_Half_BIT	= 4,
-	ETHTOOL_LINK_MODE_1000baseT_Full_BIT	= 5,
-	ETHTOOL_LINK_MODE_Autoneg_BIT		= 6,
-	ETHTOOL_LINK_MODE_TP_BIT		= 7,
-	ETHTOOL_LINK_MODE_AUI_BIT		= 8,
-	ETHTOOL_LINK_MODE_MII_BIT		= 9,
-	ETHTOOL_LINK_MODE_FIBRE_BIT		= 10,
-	ETHTOOL_LINK_MODE_BNC_BIT		= 11,
-	ETHTOOL_LINK_MODE_10000baseT_Full_BIT	= 12,
-	ETHTOOL_LINK_MODE_Pause_BIT		= 13,
-	ETHTOOL_LINK_MODE_Asym_Pause_BIT	= 14,
-	ETHTOOL_LINK_MODE_2500baseX_Full_BIT	= 15,
-	ETHTOOL_LINK_MODE_Backplane_BIT		= 16,
-	ETHTOOL_LINK_MODE_1000baseKX_Full_BIT	= 17,
-	ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT	= 18,
-	ETHTOOL_LINK_MODE_10000baseKR_Full_BIT	= 19,
-	ETHTOOL_LINK_MODE_10000baseR_FEC_BIT	= 20,
-	ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT = 21,
-	ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT	= 22,
-	ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT	= 23,
-	ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT	= 24,
-	ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT	= 25,
-	ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT	= 26,
-	ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT	= 27,
-	ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT	= 28,
-	ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT	= 29,
-	ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT	= 30,
-	ETHTOOL_LINK_MODE_25000baseCR_Full_BIT	= 31,
-
-	/* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit
-	 * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_*
-	 * macro for bits > 31. The only way to use indices > 31 is to
-	 * use the new ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API.
-	 */
-
-	ETHTOOL_LINK_MODE_25000baseKR_Full_BIT	= 32,
-	ETHTOOL_LINK_MODE_25000baseSR_Full_BIT	= 33,
-	ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT	= 34,
-	ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT	= 35,
-	ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT	= 36,
-	ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT	= 37,
-	ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT	= 38,
-	ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT	= 39,
-	ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT		= 40,
-	ETHTOOL_LINK_MODE_1000baseX_Full_BIT	= 41,
-	ETHTOOL_LINK_MODE_10000baseCR_Full_BIT	= 42,
-	ETHTOOL_LINK_MODE_10000baseSR_Full_BIT	= 43,
-	ETHTOOL_LINK_MODE_10000baseLR_Full_BIT	= 44,
-	ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT	= 45,
-	ETHTOOL_LINK_MODE_10000baseER_Full_BIT	= 46,
-	ETHTOOL_LINK_MODE_2500baseT_Full_BIT	= 47,
-	ETHTOOL_LINK_MODE_5000baseT_Full_BIT	= 48,
-
-	ETHTOOL_LINK_MODE_FEC_NONE_BIT	= 49,
-	ETHTOOL_LINK_MODE_FEC_RS_BIT	= 50,
-	ETHTOOL_LINK_MODE_FEC_BASER_BIT	= 51,
-	ETHTOOL_LINK_MODE_50000baseKR_Full_BIT		 = 52,
-	ETHTOOL_LINK_MODE_50000baseSR_Full_BIT		 = 53,
-	ETHTOOL_LINK_MODE_50000baseCR_Full_BIT		 = 54,
-	ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT	 = 55,
-	ETHTOOL_LINK_MODE_50000baseDR_Full_BIT		 = 56,
-	ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT	 = 57,
-	ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT	 = 58,
-	ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT	 = 59,
-	ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT = 60,
-	ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT	 = 61,
-	ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT	 = 62,
-	ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT	 = 63,
-	ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT = 64,
-	ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT	 = 65,
-	ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT	 = 66,
-	ETHTOOL_LINK_MODE_100baseT1_Full_BIT		 = 67,
-	ETHTOOL_LINK_MODE_1000baseT1_Full_BIT		 = 68,
-	ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT	 = 69,
-	ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT	 = 70,
-	ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT = 71,
-	ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT	 = 72,
-	ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT	 = 73,
-	ETHTOOL_LINK_MODE_FEC_LLRS_BIT			 = 74,
-	ETHTOOL_LINK_MODE_100000baseKR_Full_BIT		 = 75,
-	ETHTOOL_LINK_MODE_100000baseSR_Full_BIT		 = 76,
-	ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT	 = 77,
-	ETHTOOL_LINK_MODE_100000baseCR_Full_BIT		 = 78,
-	ETHTOOL_LINK_MODE_100000baseDR_Full_BIT		 = 79,
-	ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT	 = 80,
-	ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT	 = 81,
-	ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT = 82,
-	ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT	 = 83,
-	ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT	 = 84,
-	ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT	 = 85,
-	ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT	 = 86,
-	ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT = 87,
-	ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT	 = 88,
-	ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT	 = 89,
-	ETHTOOL_LINK_MODE_100baseFX_Half_BIT		 = 90,
-	ETHTOOL_LINK_MODE_100baseFX_Full_BIT		 = 91,
-	ETHTOOL_LINK_MODE_10baseT1L_Full_BIT		 = 92,
-	ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT	 = 93,
-	ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT	 = 94,
-	ETHTOOL_LINK_MODE_800000baseDR8_Full_BIT	 = 95,
-	ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT	 = 96,
-	ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT	 = 97,
-	ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT	 = 98,
-	ETHTOOL_LINK_MODE_10baseT1S_Full_BIT		 = 99,
-	ETHTOOL_LINK_MODE_10baseT1S_Half_BIT		 = 100,
-	ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT	 = 101,
-
-	/* must be last entry */
-	__ETHTOOL_LINK_MODE_MASK_NBITS
-};
-
-#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name)	\
-	(1UL << (ETHTOOL_LINK_MODE_ ## base_name ## _BIT))
-
-/* DEPRECATED macros. Please migrate to
- * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT
- * define any new SUPPORTED_* macro for bits > 31.
- */
-#define SUPPORTED_10baseT_Half		__ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half)
-#define SUPPORTED_10baseT_Full		__ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full)
-#define SUPPORTED_100baseT_Half		__ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half)
-#define SUPPORTED_100baseT_Full		__ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full)
-#define SUPPORTED_1000baseT_Half	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half)
-#define SUPPORTED_1000baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full)
-#define SUPPORTED_Autoneg		__ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg)
-#define SUPPORTED_TP			__ETHTOOL_LINK_MODE_LEGACY_MASK(TP)
-#define SUPPORTED_AUI			__ETHTOOL_LINK_MODE_LEGACY_MASK(AUI)
-#define SUPPORTED_MII			__ETHTOOL_LINK_MODE_LEGACY_MASK(MII)
-#define SUPPORTED_FIBRE			__ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE)
-#define SUPPORTED_BNC			__ETHTOOL_LINK_MODE_LEGACY_MASK(BNC)
-#define SUPPORTED_10000baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full)
-#define SUPPORTED_Pause			__ETHTOOL_LINK_MODE_LEGACY_MASK(Pause)
-#define SUPPORTED_Asym_Pause		__ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause)
-#define SUPPORTED_2500baseX_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full)
-#define SUPPORTED_Backplane		__ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane)
-#define SUPPORTED_1000baseKX_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full)
-#define SUPPORTED_10000baseKX4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full)
-#define SUPPORTED_10000baseKR_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full)
-#define SUPPORTED_10000baseR_FEC	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC)
-#define SUPPORTED_20000baseMLD2_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full)
-#define SUPPORTED_20000baseKR2_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full)
-#define SUPPORTED_40000baseKR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full)
-#define SUPPORTED_40000baseCR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full)
-#define SUPPORTED_40000baseSR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full)
-#define SUPPORTED_40000baseLR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full)
-#define SUPPORTED_56000baseKR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full)
-#define SUPPORTED_56000baseCR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full)
-#define SUPPORTED_56000baseSR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full)
-#define SUPPORTED_56000baseLR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full)
-/* Please do not define any new SUPPORTED_* macro for bits > 31, see
- * notice above.
- */
-
-/*
- * DEPRECATED macros. Please migrate to
- * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT
- * define any new ADERTISE_* macro for bits > 31.
- */
-#define ADVERTISED_10baseT_Half		__ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half)
-#define ADVERTISED_10baseT_Full		__ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full)
-#define ADVERTISED_100baseT_Half	__ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half)
-#define ADVERTISED_100baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full)
-#define ADVERTISED_1000baseT_Half	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half)
-#define ADVERTISED_1000baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full)
-#define ADVERTISED_Autoneg		__ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg)
-#define ADVERTISED_TP			__ETHTOOL_LINK_MODE_LEGACY_MASK(TP)
-#define ADVERTISED_AUI			__ETHTOOL_LINK_MODE_LEGACY_MASK(AUI)
-#define ADVERTISED_MII			__ETHTOOL_LINK_MODE_LEGACY_MASK(MII)
-#define ADVERTISED_FIBRE		__ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE)
-#define ADVERTISED_BNC			__ETHTOOL_LINK_MODE_LEGACY_MASK(BNC)
-#define ADVERTISED_10000baseT_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full)
-#define ADVERTISED_Pause		__ETHTOOL_LINK_MODE_LEGACY_MASK(Pause)
-#define ADVERTISED_Asym_Pause		__ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause)
-#define ADVERTISED_2500baseX_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full)
-#define ADVERTISED_Backplane		__ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane)
-#define ADVERTISED_1000baseKX_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full)
-#define ADVERTISED_10000baseKX4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full)
-#define ADVERTISED_10000baseKR_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full)
-#define ADVERTISED_10000baseR_FEC	__ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC)
-#define ADVERTISED_20000baseMLD2_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full)
-#define ADVERTISED_20000baseKR2_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full)
-#define ADVERTISED_40000baseKR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full)
-#define ADVERTISED_40000baseCR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full)
-#define ADVERTISED_40000baseSR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full)
-#define ADVERTISED_40000baseLR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full)
-#define ADVERTISED_56000baseKR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full)
-#define ADVERTISED_56000baseCR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full)
-#define ADVERTISED_56000baseSR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full)
-#define ADVERTISED_56000baseLR4_Full	__ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full)
-/* Please do not define any new ADVERTISED_* macro for bits > 31, see
- * notice above.
- */
-
-/* The following are all involved in forcing a particular link
- * mode for the device for setting things.  When getting the
- * devices settings, these indicate the current mode and whether
- * it was forced up into this mode or autonegotiated.
- */
-
-/* The forced speed, in units of 1Mb. All values 0 to INT_MAX are legal.
- * Update drivers/net/phy/phy.c:phy_speed_to_str() and
- * drivers/net/bonding/bond_3ad.c:__get_link_speed() when adding new values.
- */
-#define SPEED_10		10
-#define SPEED_100		100
-#define SPEED_1000		1000
-#define SPEED_2500		2500
-#define SPEED_5000		5000
-#define SPEED_10000		10000
-#define SPEED_14000		14000
-#define SPEED_20000		20000
-#define SPEED_25000		25000
-#define SPEED_40000		40000
-#define SPEED_50000		50000
-#define SPEED_56000		56000
-#define SPEED_100000		100000
-#define SPEED_200000		200000
-#define SPEED_400000		400000
-#define SPEED_800000		800000
-
-#define SPEED_UNKNOWN		-1
-
-static inline int ethtool_validate_speed(__u32 speed)
-{
-	return speed <= INT_MAX || speed == (__u32)SPEED_UNKNOWN;
-}
-
-/* Duplex, half or full. */
-#define DUPLEX_HALF		0x00
-#define DUPLEX_FULL		0x01
-#define DUPLEX_UNKNOWN		0xff
-
-static inline int ethtool_validate_duplex(__u8 duplex)
-{
-	switch (duplex) {
-	case DUPLEX_HALF:
-	case DUPLEX_FULL:
-	case DUPLEX_UNKNOWN:
-		return 1;
-	}
-
-	return 0;
-}
-
-#define MASTER_SLAVE_CFG_UNSUPPORTED		0
-#define MASTER_SLAVE_CFG_UNKNOWN		1
-#define MASTER_SLAVE_CFG_MASTER_PREFERRED	2
-#define MASTER_SLAVE_CFG_SLAVE_PREFERRED	3
-#define MASTER_SLAVE_CFG_MASTER_FORCE		4
-#define MASTER_SLAVE_CFG_SLAVE_FORCE		5
-#define MASTER_SLAVE_STATE_UNSUPPORTED		0
-#define MASTER_SLAVE_STATE_UNKNOWN		1
-#define MASTER_SLAVE_STATE_MASTER		2
-#define MASTER_SLAVE_STATE_SLAVE		3
-#define MASTER_SLAVE_STATE_ERR			4
-
-/* These are used to throttle the rate of data on the phy interface when the
- * native speed of the interface is higher than the link speed. These should
- * not be used for phy interfaces which natively support multiple speeds (e.g.
- * MII or SGMII).
- */
-/* No rate matching performed. */
-#define RATE_MATCH_NONE		0
-/* The phy sends pause frames to throttle the MAC. */
-#define RATE_MATCH_PAUSE	1
-/* The phy asserts CRS to prevent the MAC from transmitting. */
-#define RATE_MATCH_CRS		2
-/* The MAC is programmed with a sufficiently-large IPG. */
-#define RATE_MATCH_OPEN_LOOP	3
-
-/* Which connector port. */
-#define PORT_TP			0x00
-#define PORT_AUI		0x01
-#define PORT_MII		0x02
-#define PORT_FIBRE		0x03
-#define PORT_BNC		0x04
-#define PORT_DA			0x05
-#define PORT_NONE		0xef
-#define PORT_OTHER		0xff
-
-/* Which transceiver to use. */
-#define XCVR_INTERNAL		0x00 /* PHY and MAC are in the same package */
-#define XCVR_EXTERNAL		0x01 /* PHY and MAC are in different packages */
-#define XCVR_DUMMY1		0x02
-#define XCVR_DUMMY2		0x03
-#define XCVR_DUMMY3		0x04
-
-/* Enable or disable autonegotiation. */
-#define AUTONEG_DISABLE		0x00
-#define AUTONEG_ENABLE		0x01
-
-/* MDI or MDI-X status/control - if MDI/MDI_X/AUTO is set then
- * the driver is required to renegotiate link
- */
-#define ETH_TP_MDI_INVALID	0x00 /* status: unknown; control: unsupported */
-#define ETH_TP_MDI		0x01 /* status: MDI;     control: force MDI */
-#define ETH_TP_MDI_X		0x02 /* status: MDI-X;   control: force MDI-X */
-#define ETH_TP_MDI_AUTO		0x03 /*                  control: auto-select */
-
-/* Wake-On-Lan options. */
-#define WAKE_PHY		(1 << 0)
-#define WAKE_UCAST		(1 << 1)
-#define WAKE_MCAST		(1 << 2)
-#define WAKE_BCAST		(1 << 3)
-#define WAKE_ARP		(1 << 4)
-#define WAKE_MAGIC		(1 << 5)
-#define WAKE_MAGICSECURE	(1 << 6) /* only meaningful if WAKE_MAGIC */
-#define WAKE_FILTER		(1 << 7)
-
-#define WOL_MODE_COUNT		8
-
-/* RSS hash function data
- * XOR the corresponding source and destination fields of each specified
- * protocol. Both copies of the XOR'ed fields are fed into the RSS and RXHASH
- * calculation. Note that this XORing reduces the input set entropy and could
- * be exploited to reduce the RSS queue spread.
- */
-#define	RXH_XFRM_SYM_XOR	(1 << 0)
-#define	RXH_XFRM_NO_CHANGE	0xff
-
-/* L2-L4 network traffic flow types */
-#define	TCP_V4_FLOW	0x01	/* hash or spec (tcp_ip4_spec) */
-#define	UDP_V4_FLOW	0x02	/* hash or spec (udp_ip4_spec) */
-#define	SCTP_V4_FLOW	0x03	/* hash or spec (sctp_ip4_spec) */
-#define	AH_ESP_V4_FLOW	0x04	/* hash only */
-#define	TCP_V6_FLOW	0x05	/* hash or spec (tcp_ip6_spec; nfc only) */
-#define	UDP_V6_FLOW	0x06	/* hash or spec (udp_ip6_spec; nfc only) */
-#define	SCTP_V6_FLOW	0x07	/* hash or spec (sctp_ip6_spec; nfc only) */
-#define	AH_ESP_V6_FLOW	0x08	/* hash only */
-#define	AH_V4_FLOW	0x09	/* hash or spec (ah_ip4_spec) */
-#define	ESP_V4_FLOW	0x0a	/* hash or spec (esp_ip4_spec) */
-#define	AH_V6_FLOW	0x0b	/* hash or spec (ah_ip6_spec; nfc only) */
-#define	ESP_V6_FLOW	0x0c	/* hash or spec (esp_ip6_spec; nfc only) */
-#define	IPV4_USER_FLOW	0x0d	/* spec only (usr_ip4_spec) */
-#define	IP_USER_FLOW	IPV4_USER_FLOW
-#define	IPV6_USER_FLOW	0x0e	/* spec only (usr_ip6_spec; nfc only) */
-#define	IPV4_FLOW	0x10	/* hash only */
-#define	IPV6_FLOW	0x11	/* hash only */
-#define	ETHER_FLOW	0x12	/* spec only (ether_spec) */
-
-/* Used for GTP-U IPv4 and IPv6.
- * The format of GTP packets only includes
- * elements such as TEID and GTP version.
- * It is primarily intended for data communication of the UE.
- */
-#define GTPU_V4_FLOW 0x13	/* hash only */
-#define GTPU_V6_FLOW 0x14	/* hash only */
-
-/* Use for GTP-C IPv4 and v6.
- * The format of these GTP packets does not include TEID.
- * Primarily expected to be used for communication
- * to create sessions for UE data communication,
- * commonly referred to as CSR (Create Session Request).
- */
-#define GTPC_V4_FLOW 0x15	/* hash only */
-#define GTPC_V6_FLOW 0x16	/* hash only */
-
-/* Use for GTP-C IPv4 and v6.
- * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID.
- * After session creation, it becomes this packet.
- * This is mainly used for requests to realize UE handover.
- */
-#define GTPC_TEID_V4_FLOW 0x17	/* hash only */
-#define GTPC_TEID_V6_FLOW 0x18	/* hash only */
-
-/* Use for GTP-U and extended headers for the PSC (PDU Session Container).
- * The format of these GTP packets includes TEID and QFI.
- * In 5G communication using UPF (User Plane Function),
- * data communication with this extended header is performed.
- */
-#define GTPU_EH_V4_FLOW 0x19	/* hash only */
-#define GTPU_EH_V6_FLOW 0x1a	/* hash only */
-
-/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers.
- * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by
- * UL/DL included in the PSC.
- * There are differences in the data included based on Downlink/Uplink,
- * and can be used to distinguish packets.
- * The functions described so far are useful when you want to
- * handle communication from the mobile network in UPF, PGW, etc.
- */
-#define GTPU_UL_V4_FLOW 0x1b	/* hash only */
-#define GTPU_UL_V6_FLOW 0x1c	/* hash only */
-#define GTPU_DL_V4_FLOW 0x1d	/* hash only */
-#define GTPU_DL_V6_FLOW 0x1e	/* hash only */
-
-/* Flag to enable additional fields in struct ethtool_rx_flow_spec */
-#define	FLOW_EXT	0x80000000
-#define	FLOW_MAC_EXT	0x40000000
-/* Flag to enable RSS spreading of traffic matching rule (nfc only) */
-#define	FLOW_RSS	0x20000000
-
-/* L3-L4 network traffic flow hash options */
-#define	RXH_L2DA	(1 << 1)
-#define	RXH_VLAN	(1 << 2)
-#define	RXH_L3_PROTO	(1 << 3)
-#define	RXH_IP_SRC	(1 << 4)
-#define	RXH_IP_DST	(1 << 5)
-#define	RXH_L4_B_0_1	(1 << 6) /* src port in case of TCP/UDP/SCTP */
-#define	RXH_L4_B_2_3	(1 << 7) /* dst port in case of TCP/UDP/SCTP */
-#define	RXH_GTP_TEID	(1 << 8) /* teid in case of GTP */
-#define	RXH_DISCARD	(1 << 31)
-
-#define	RX_CLS_FLOW_DISC	0xffffffffffffffffULL
-#define RX_CLS_FLOW_WAKE	0xfffffffffffffffeULL
-
-/* Special RX classification rule insert location values */
-#define RX_CLS_LOC_SPECIAL	0x80000000	/* flag */
-#define RX_CLS_LOC_ANY		0xffffffff
-#define RX_CLS_LOC_FIRST	0xfffffffe
-#define RX_CLS_LOC_LAST		0xfffffffd
-
-/* EEPROM Standards for plug in modules */
-#define ETH_MODULE_SFF_8079		0x1
-#define ETH_MODULE_SFF_8079_LEN		256
-#define ETH_MODULE_SFF_8472		0x2
-#define ETH_MODULE_SFF_8472_LEN		512
-#define ETH_MODULE_SFF_8636		0x3
-#define ETH_MODULE_SFF_8636_LEN		256
-#define ETH_MODULE_SFF_8436		0x4
-#define ETH_MODULE_SFF_8436_LEN		256
-
-#define ETH_MODULE_SFF_8636_MAX_LEN     640
-#define ETH_MODULE_SFF_8436_MAX_LEN     640
-
-/* Reset flags */
-/* The reset() operation must clear the flags for the components which
- * were actually reset.  On successful return, the flags indicate the
- * components which were not reset, either because they do not exist
- * in the hardware or because they cannot be reset independently.  The
- * driver must never reset any components that were not requested.
- */
-enum ethtool_reset_flags {
-	/* These flags represent components dedicated to the interface
-	 * the command is addressed to.  Shift any flag left by
-	 * ETH_RESET_SHARED_SHIFT to reset a shared component of the
-	 * same type.
-	 */
-	ETH_RESET_MGMT		= 1 << 0,	/* Management processor */
-	ETH_RESET_IRQ		= 1 << 1,	/* Interrupt requester */
-	ETH_RESET_DMA		= 1 << 2,	/* DMA engine */
-	ETH_RESET_FILTER	= 1 << 3,	/* Filtering/flow direction */
-	ETH_RESET_OFFLOAD	= 1 << 4,	/* Protocol offload */
-	ETH_RESET_MAC		= 1 << 5,	/* Media access controller */
-	ETH_RESET_PHY		= 1 << 6,	/* Transceiver/PHY */
-	ETH_RESET_RAM		= 1 << 7,	/* RAM shared between
-						 * multiple components */
-	ETH_RESET_AP		= 1 << 8,	/* Application processor */
-
-	ETH_RESET_DEDICATED	= 0x0000ffff,	/* All components dedicated to
-						 * this interface */
-	ETH_RESET_ALL		= 0xffffffff,	/* All components used by this
-						 * interface, even if shared */
-};
-#define ETH_RESET_SHARED_SHIFT	16
-
-
-/**
- * struct ethtool_link_settings - link control and status
- *
- * IMPORTANT, Backward compatibility notice: When implementing new
- *	user-space tools, please first try %ETHTOOL_GLINKSETTINGS, and
- *	if it succeeds use %ETHTOOL_SLINKSETTINGS to change link
- *	settings; do not use %ETHTOOL_SSET if %ETHTOOL_GLINKSETTINGS
- *	succeeded: stick to %ETHTOOL_GLINKSETTINGS/%SLINKSETTINGS in
- *	that case.  Conversely, if %ETHTOOL_GLINKSETTINGS fails, use
- *	%ETHTOOL_GSET to query and %ETHTOOL_SSET to change link
- *	settings; do not use %ETHTOOL_SLINKSETTINGS if
- *	%ETHTOOL_GLINKSETTINGS failed: stick to
- *	%ETHTOOL_GSET/%ETHTOOL_SSET in that case.
- *
- * @cmd: Command number = %ETHTOOL_GLINKSETTINGS or %ETHTOOL_SLINKSETTINGS
- * @speed: Link speed (Mbps)
- * @duplex: Duplex mode; one of %DUPLEX_*
- * @port: Physical connector type; one of %PORT_*
- * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not
- *	applicable.  For clause 45 PHYs this is the PRTAD.
- * @autoneg: Enable/disable autonegotiation and auto-detection;
- *	either %AUTONEG_DISABLE or %AUTONEG_ENABLE
- * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO
- *	protocols supported by the interface; 0 if unknown.
- *	Read-only.
- * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of
- *	%ETH_TP_MDI_*.  If the status is unknown or not applicable, the
- *	value will be %ETH_TP_MDI_INVALID.  Read-only.
- * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of
- *	%ETH_TP_MDI_*.  If MDI(-X) control is not implemented, reads
- *	yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected.
- *	When written successfully, the link should be renegotiated if
- *	necessary.
- * @link_mode_masks_nwords: Number of 32-bit words for each of the
- *	supported, advertising, lp_advertising link mode bitmaps. For
- *	%ETHTOOL_GLINKSETTINGS: on entry, number of words passed by user
- *	(>= 0); on return, if handshake in progress, negative if
- *	request size unsupported by kernel: absolute value indicates
- *	kernel expected size and all the other fields but cmd
- *	are 0; otherwise (handshake completed), strictly positive
- *	to indicate size used by kernel and cmd field stays
- *	%ETHTOOL_GLINKSETTINGS, all other fields populated by driver. For
- *	%ETHTOOL_SLINKSETTINGS: must be valid on entry, ie. a positive
- *	value returned previously by %ETHTOOL_GLINKSETTINGS, otherwise
- *	refused. For drivers: ignore this field (use kernel's
- *	__ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will
- *	be overwritten by kernel.
- * @transceiver: Used to distinguish different possible PHY types,
- *	reported consistently by PHYLIB.  Read-only.
- * @master_slave_cfg: Master/slave port mode.
- * @master_slave_state: Master/slave port state.
- * @rate_matching: Rate adaptation performed by the PHY
- * @reserved: Reserved for future use; see the note on reserved space.
- * @link_mode_masks: Variable length bitmaps.
- *
- * If autonegotiation is disabled, the speed and @duplex represent the
- * fixed link mode and are writable if the driver supports multiple
- * link modes.  If it is enabled then they are read-only; if the link
- * is up they represent the negotiated link mode; if the link is down,
- * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and
- * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode.
- *
- * Some hardware interfaces may have multiple PHYs and/or physical
- * connectors fitted or do not allow the driver to detect which are
- * fitted.  For these interfaces @port and/or @phy_address may be
- * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE.
- * Otherwise, attempts to write different values may be ignored or
- * rejected.
- *
- * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt
- * are not available in %ethtool_link_settings. These fields will be
- * always set to zero in %ETHTOOL_GSET reply and %ETHTOOL_SSET will
- * fail if any of them is set to non-zero value.
- *
- * Users should assume that all fields not marked read-only are
- * writable and subject to validation by the driver.  They should use
- * %ETHTOOL_GLINKSETTINGS to get the current values before making specific
- * changes and then applying them with %ETHTOOL_SLINKSETTINGS.
- *
- * Drivers that implement %get_link_ksettings and/or
- * %set_link_ksettings should ignore the @cmd
- * and @link_mode_masks_nwords fields (any change to them overwritten
- * by kernel), and rely only on kernel's internal
- * %__ETHTOOL_LINK_MODE_MASK_NBITS and
- * %ethtool_link_mode_mask_t. Drivers that implement
- * %set_link_ksettings() should validate all fields other than @cmd
- * and @link_mode_masks_nwords that are not described as read-only or
- * deprecated, and must ignore all fields described as read-only.
- *
- * @link_mode_masks is divided into three bitfields, each of length
- * @link_mode_masks_nwords:
- * - supported: Bitmap with each bit meaning given by
- *	%ethtool_link_mode_bit_indices for the link modes, physical
- *	connectors and other link features for which the interface
- *	supports autonegotiation or auto-detection.  Read-only.
- * - advertising: Bitmap with each bit meaning given by
- *	%ethtool_link_mode_bit_indices for the link modes, physical
- *	connectors and other link features that are advertised through
- *	autonegotiation or enabled for auto-detection.
- * - lp_advertising: Bitmap with each bit meaning given by
- *	%ethtool_link_mode_bit_indices for the link modes, and other
- *	link features that the link partner advertised through
- *	autonegotiation; 0 if unknown or not applicable.  Read-only.
- */
-struct ethtool_link_settings {
-	__u32	cmd;
-	__u32	speed;
-	__u8	duplex;
-	__u8	port;
-	__u8	phy_address;
-	__u8	autoneg;
-	__u8	mdio_support;
-	__u8	eth_tp_mdix;
-	__u8	eth_tp_mdix_ctrl;
-	__s8	link_mode_masks_nwords;
-	__u8	transceiver;
-	__u8	master_slave_cfg;
-	__u8	master_slave_state;
-	__u8	rate_matching;
-	__u32	reserved[7];
-	__u32	link_mode_masks[];
-	/* layout of link_mode_masks fields:
-	 * __u32 map_supported[link_mode_masks_nwords];
-	 * __u32 map_advertising[link_mode_masks_nwords];
-	 * __u32 map_lp_advertising[link_mode_masks_nwords];
-	 */
-};
-#endif /* _UAPI_LINUX_ETHTOOL_H */
-- 
cgit 


From b56035101e1cdd9c4420ea5da17f09f87fb69285 Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@nvidia.com>
Date: Fri, 10 May 2024 23:19:26 +0300
Subject: netdev: Add queue stats for TX stop and wake

TX queue stop and wake are counted by some drivers.
Support reporting these via netdev-genl queue stats.

Signed-off-by: Daniel Jurgens <danielj@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20240510201927.1821109-2-danielj@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 14 ++++++++++++++
 include/net/netdev_queues.h             |  3 +++
 include/uapi/linux/netdev.h             |  2 ++
 net/core/netdev-genl.c                  |  4 +++-
 tools/include/uapi/linux/netdev.h       |  2 ++
 5 files changed, 24 insertions(+), 1 deletion(-)

(limited to 'tools/include/uapi/linux')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 2be4b3714d17..11a32373365a 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -439,6 +439,20 @@ attribute-sets:
           Number of the packets dropped by the device due to the transmit
           packets bitrate exceeding the device rate limit.
         type: uint
+      -
+        name: tx-stop
+        doc: |
+          Number of times driver paused accepting new tx packets
+          from the stack to this queue, because the queue was full.
+          Note that if BQL is supported and enabled on the device
+          the networking stack will avoid queuing a lot of data at once.
+        type: uint
+      -
+        name: tx-wake
+        doc: |
+          Number of times driver re-started accepting send
+          requests to this queue from the stack.
+        type: uint
 
 operations:
   list:
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index e7b84f018cee..a8a7e48dfa6c 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -41,6 +41,9 @@ struct netdev_queue_stats_tx {
 	u64 hw_gso_wire_bytes;
 
 	u64 hw_drop_ratelimits;
+
+	u64 stop;
+	u64 wake;
 };
 
 /**
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index cf24f1d9adf8..a8188202413e 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -165,6 +165,8 @@ enum {
 	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS,
 	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES,
 	NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS,
+	NETDEV_A_QSTATS_TX_STOP,
+	NETDEV_A_QSTATS_TX_WAKE,
 
 	__NETDEV_A_QSTATS_MAX,
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 4b5054087309..1f6ae6379e0f 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -517,7 +517,9 @@ netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx)
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_BYTES, tx->hw_gso_bytes) ||
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, tx->hw_gso_wire_packets) ||
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, tx->hw_gso_wire_bytes) ||
-	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits))
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_STOP, tx->stop) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_WAKE, tx->wake))
 		return -EMSGSIZE;
 	return 0;
 }
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index cf24f1d9adf8..a8188202413e 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -165,6 +165,8 @@ enum {
 	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS,
 	NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES,
 	NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS,
+	NETDEV_A_QSTATS_TX_STOP,
+	NETDEV_A_QSTATS_TX_WAKE,
 
 	__NETDEV_A_QSTATS_MAX,
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
-- 
cgit