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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


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 v1.2.3


From 1693c5db6ab8262e6f5263f9d211855959aa5acd Mon Sep 17 00:00:00 2001
From: Abhishek Chauhan <quic_abchauha@quicinc.com>
Date: Thu, 9 May 2024 14:18:33 -0700
Subject: net: Add additional bit to support clockid_t timestamp type

tstamp_type is now set based on actual clockid_t compressed
into 2 bits.

To make the design scalable for future needs this commit bring in
the change to extend the tstamp_type:1 to tstamp_type:2 to support
other clockid_t timestamp.

We now support CLOCK_TAI as part of tstamp_type as part of this
commit with existing support CLOCK_MONOTONIC and CLOCK_REALTIME.

Signed-off-by: Abhishek Chauhan <quic_abchauha@quicinc.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20240509211834.3235191-3-quic_abchauha@quicinc.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/linux/skbuff.h         | 18 +++++++++++------
 include/uapi/linux/bpf.h       | 15 +++++++++-----
 net/core/filter.c              | 46 ++++++++++++++++++++++++------------------
 net/ipv4/ip_output.c           |  5 ++++-
 net/ipv4/raw.c                 |  2 +-
 net/ipv4/tcp_ipv4.c            |  2 ++
 net/ipv6/ip6_output.c          |  5 ++++-
 net/ipv6/raw.c                 |  2 +-
 net/ipv6/tcp_ipv6.c            | 10 +++++++--
 net/packet/af_packet.c         |  7 +++----
 tools/include/uapi/linux/bpf.h | 15 +++++++++-----
 11 files changed, 81 insertions(+), 46 deletions(-)

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

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3a721cc3b644..1e5c97daaa37 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -709,6 +709,8 @@ typedef unsigned char *sk_buff_data_t;
 enum skb_tstamp_type {
 	SKB_CLOCK_REALTIME,
 	SKB_CLOCK_MONOTONIC,
+	SKB_CLOCK_TAI,
+	__SKB_CLOCK_MAX = SKB_CLOCK_TAI,
 };
 
 /**
@@ -957,7 +959,7 @@ struct sk_buff {
 	/* private: */
 	__u8			__mono_tc_offset[0];
 	/* public: */
-	__u8			tstamp_type:1;	/* See skb_tstamp_type */
+	__u8			tstamp_type:2;	/* See skb_tstamp_type */
 #ifdef CONFIG_NET_XGRESS
 	__u8			tc_at_ingress:1;	/* See TC_AT_INGRESS_MASK */
 	__u8			tc_skip_classify:1;
@@ -1087,15 +1089,16 @@ struct sk_buff {
 #endif
 #define PKT_TYPE_OFFSET		offsetof(struct sk_buff, __pkt_type_offset)
 
-/* if you move tc_at_ingress or mono_delivery_time
+/* if you move tc_at_ingress or tstamp_type
  * around, you also must adapt these constants.
  */
 #ifdef __BIG_ENDIAN_BITFIELD
-#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 7)
-#define TC_AT_INGRESS_MASK		(1 << 6)
+#define SKB_TSTAMP_TYPE_MASK		(3 << 6)
+#define SKB_TSTAMP_TYPE_RSHIFT		(6)
+#define TC_AT_INGRESS_MASK		(1 << 5)
 #else
-#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 0)
-#define TC_AT_INGRESS_MASK		(1 << 1)
+#define SKB_TSTAMP_TYPE_MASK		(3)
+#define TC_AT_INGRESS_MASK		(1 << 2)
 #endif
 #define SKB_BF_MONO_TC_OFFSET		offsetof(struct sk_buff, __mono_tc_offset)
 
@@ -4216,6 +4219,9 @@ static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb,
 	case CLOCK_MONOTONIC:
 		tstamp_type = SKB_CLOCK_MONOTONIC;
 		break;
+	case CLOCK_TAI:
+		tstamp_type = SKB_CLOCK_TAI;
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		kt = 0;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 90706a47f6ff..25ea393cf084 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6207,12 +6207,17 @@ union {					\
 	__u64 :64;			\
 } __attribute__((aligned(8)))
 
+/* The enum used in skb->tstamp_type. It specifies the clock type
+ * of the time stored in the skb->tstamp.
+ */
 enum {
-	BPF_SKB_TSTAMP_UNSPEC,
-	BPF_SKB_TSTAMP_DELIVERY_MONO,	/* tstamp has mono delivery time */
-	/* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle,
-	 * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC
-	 * and try to deduce it by ingress, egress or skb->sk->sk_clockid.
+	BPF_SKB_TSTAMP_UNSPEC = 0,		/* DEPRECATED */
+	BPF_SKB_TSTAMP_DELIVERY_MONO = 1,	/* DEPRECATED */
+	BPF_SKB_CLOCK_REALTIME = 0,
+	BPF_SKB_CLOCK_MONOTONIC = 1,
+	BPF_SKB_CLOCK_TAI = 2,
+	/* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle,
+	 * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid.
 	 */
 };
 
diff --git a/net/core/filter.c b/net/core/filter.c
index a3781a796da4..c6edfe9f41bc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7726,17 +7726,21 @@ BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb,
 		return -EOPNOTSUPP;
 
 	switch (tstamp_type) {
-	case BPF_SKB_TSTAMP_DELIVERY_MONO:
+	case BPF_SKB_CLOCK_REALTIME:
+		skb->tstamp = tstamp;
+		skb->tstamp_type = SKB_CLOCK_REALTIME;
+		break;
+	case BPF_SKB_CLOCK_MONOTONIC:
 		if (!tstamp)
 			return -EINVAL;
 		skb->tstamp = tstamp;
 		skb->tstamp_type = SKB_CLOCK_MONOTONIC;
 		break;
-	case BPF_SKB_TSTAMP_UNSPEC:
-		if (tstamp)
+	case BPF_SKB_CLOCK_TAI:
+		if (!tstamp)
 			return -EINVAL;
-		skb->tstamp = 0;
-		skb->tstamp_type = SKB_CLOCK_REALTIME;
+		skb->tstamp = tstamp;
+		skb->tstamp_type = SKB_CLOCK_TAI;
 		break;
 	default:
 		return -EINVAL;
@@ -9387,16 +9391,17 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si,
 {
 	__u8 value_reg = si->dst_reg;
 	__u8 skb_reg = si->src_reg;
-	/* AX is needed because src_reg and dst_reg could be the same */
-	__u8 tmp_reg = BPF_REG_AX;
-
-	*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg,
-			      SKB_BF_MONO_TC_OFFSET);
-	*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg,
-				SKB_MONO_DELIVERY_TIME_MASK, 2);
-	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC);
-	*insn++ = BPF_JMP_A(1);
-	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO);
+	BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI);
+	BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME);
+	BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC);
+	BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI);
+	*insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
+	*insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK);
+#ifdef __BIG_ENDIAN_BITFIELD
+	*insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT);
+#else
+	BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1));
+#endif
 
 	return insn;
 }
@@ -9439,10 +9444,11 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog,
 		__u8 tmp_reg = BPF_REG_AX;
 
 		*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
-		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg,
-					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK);
-		*insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg,
-					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 2);
+		/* check if ingress mask bits is set */
+		*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1);
+		*insn++ = BPF_JMP_A(4);
+		*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1);
+		*insn++ = BPF_JMP_A(2);
 		/* skb->tc_at_ingress && skb->tstamp_type,
 		 * read 0 as the (rcv) timestamp.
 		 */
@@ -9479,7 +9485,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog,
 		/* goto <store> */
 		*insn++ = BPF_JMP_A(2);
 		/* <clear>: skb->tstamp_type */
-		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK);
 		*insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET);
 	}
 #endif
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index fe86cadfa85b..b90d0f78ac80 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1457,7 +1457,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 
 	skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority);
 	skb->mark = cork->mark;
-	skb->tstamp = cork->transmit_time;
+	if (sk_is_tcp(sk))
+		skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC);
+	else
+		skb_set_delivery_type_by_clockid(skb, cork->transmit_time, sk->sk_clockid);
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
 	 * on dst refcount
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 4cb43401e0e0..1a0953650356 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -360,7 +360,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 	skb->protocol = htons(ETH_P_IP);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid);
 	skb_dst_set(skb, &rt->dst);
 	*rtp = NULL;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 30ef0c8f5e92..8f70b8d1d1e5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3625,6 +3625,8 @@ void __init tcp_v4_init(void)
 		 */
 		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
 
+		sk->sk_clockid = CLOCK_MONOTONIC;
+
 		per_cpu(ipv4_tcp_sk, cpu) = sk;
 	}
 	if (register_pernet_subsys(&tcp_sk_ops))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1ab0f23d37bf..e7a19df3125e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1924,7 +1924,10 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = cork->base.mark;
-	skb->tstamp = cork->base.transmit_time;
+	if (sk_is_tcp(sk))
+		skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC);
+	else
+		skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid);
 
 	ip6_cork_steal_dst(skb, cork);
 	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 2eedf255600b..f838366e8256 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -621,7 +621,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid);
 
 	skb_put(skb, length);
 	skb_reset_network_header(skb);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 8333005c5c2e..750aa681779c 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2387,8 +2387,14 @@ static struct inet_protosw tcpv6_protosw = {
 
 static int __net_init tcpv6_net_init(struct net *net)
 {
-	return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
-				    SOCK_RAW, IPPROTO_TCP, net);
+	int res;
+
+	res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
+				   SOCK_RAW, IPPROTO_TCP, net);
+	if (!res)
+		net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC;
+
+	return res;
 }
 
 static void __net_exit tcpv6_net_exit(struct net *net)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ea3ebc160e25..fce390887591 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2056,8 +2056,7 @@ retry:
 	skb->dev = dev;
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = READ_ONCE(sk->sk_mark);
-	skb->tstamp = sockc.transmit_time;
-
+	skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid);
 	skb_setup_tx_timestamp(skb, sockc.tsflags);
 
 	if (unlikely(extra_len == 4))
@@ -2584,7 +2583,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->dev = dev;
 	skb->priority = READ_ONCE(po->sk.sk_priority);
 	skb->mark = READ_ONCE(po->sk.sk_mark);
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid);
 	skb_setup_tx_timestamp(skb, sockc->tsflags);
 	skb_zcopy_set_nouarg(skb, ph.raw);
 
@@ -3062,7 +3061,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->dev = dev;
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc.mark;
-	skb->tstamp = sockc.transmit_time;
+	skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid);
 
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 90706a47f6ff..25ea393cf084 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6207,12 +6207,17 @@ union {					\
 	__u64 :64;			\
 } __attribute__((aligned(8)))
 
+/* The enum used in skb->tstamp_type. It specifies the clock type
+ * of the time stored in the skb->tstamp.
+ */
 enum {
-	BPF_SKB_TSTAMP_UNSPEC,
-	BPF_SKB_TSTAMP_DELIVERY_MONO,	/* tstamp has mono delivery time */
-	/* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle,
-	 * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC
-	 * and try to deduce it by ingress, egress or skb->sk->sk_clockid.
+	BPF_SKB_TSTAMP_UNSPEC = 0,		/* DEPRECATED */
+	BPF_SKB_TSTAMP_DELIVERY_MONO = 1,	/* DEPRECATED */
+	BPF_SKB_CLOCK_REALTIME = 0,
+	BPF_SKB_CLOCK_MONOTONIC = 1,
+	BPF_SKB_CLOCK_TAI = 2,
+	/* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle,
+	 * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid.
 	 */
 };
 
-- 
cgit v1.2.3


From 88e520512a68b4e724cb0f4281c79ae28673ccb1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 28 May 2024 16:24:15 -0300
Subject: tools headers UAPI: Sync kvm headers with the kernel sources

To pick the changes in:

  4af663c2f64a8d25 ("KVM: SEV: Allow per-guest configuration of GHCB protocol version")
  4f5defae708992dd ("KVM: SEV: introduce KVM_SEV_INIT2 operation")
  26c44aa9e076ed83 ("KVM: SEV: define VM types for SEV and SEV-ES")
  ac5c48027bacb1b5 ("KVM: SEV: publish supported VMSA features")
  651d61bc8b7d8bb6 ("KVM: PPC: Fix documentation for ppc mmu caps")

That don't change functionality in tools/perf, as no new ioctl is added
for the 'perf trace' scripts to harvest.

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
    diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Joel Stanley <joel@jms.id.au>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michael Roth <michael.roth@amd.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/lkml/ZlYxAdHjyAkvGtMW@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h | 22 ++++++++++++++++++++--
 tools/include/uapi/linux/kvm.h        |  4 ++--
 2 files changed, 22 insertions(+), 4 deletions(-)

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

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index ef11aa4cab42..9fae1b73b529 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -457,8 +457,13 @@ struct kvm_sync_regs {
 
 #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE	0x00000001
 
-/* attributes for system fd (group 0) */
-#define KVM_X86_XCOMP_GUEST_SUPP	0
+/* vendor-independent attributes for system fd (group 0) */
+#define KVM_X86_GRP_SYSTEM		0
+#  define KVM_X86_XCOMP_GUEST_SUPP	0
+
+/* vendor-specific groups and attributes for system fd */
+#define KVM_X86_GRP_SEV			1
+#  define KVM_X86_SEV_VMSA_FEATURES	0
 
 struct kvm_vmx_nested_state_data {
 	__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
@@ -689,6 +694,9 @@ enum sev_cmd_id {
 	/* Guest Migration Extension */
 	KVM_SEV_SEND_CANCEL,
 
+	/* Second time is the charm; improved versions of the above ioctls.  */
+	KVM_SEV_INIT2,
+
 	KVM_SEV_NR_MAX,
 };
 
@@ -700,6 +708,14 @@ struct kvm_sev_cmd {
 	__u32 sev_fd;
 };
 
+struct kvm_sev_init {
+	__u64 vmsa_features;
+	__u32 flags;
+	__u16 ghcb_version;
+	__u16 pad1;
+	__u32 pad2[8];
+};
+
 struct kvm_sev_launch_start {
 	__u32 handle;
 	__u32 policy;
@@ -856,5 +872,7 @@ struct kvm_hyperv_eventfd {
 
 #define KVM_X86_DEFAULT_VM	0
 #define KVM_X86_SW_PROTECTED_VM	1
+#define KVM_X86_SEV_VM		2
+#define KVM_X86_SEV_ES_VM	3
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index ea32b101b999..d03842abae57 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/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_MMU_HASH_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)
-- 
cgit v1.2.3


From 13c7c941e72908b8cce5a84b45a7b5e485ca12ed Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 29 May 2024 09:35:47 -0700
Subject: netdev: add qstat for csum complete

Recent commit 0cfe71f45f42 ("netdev: add queue stats") added
a lot of useful stats, but only those immediately needed by virtio.
Presumably virtio does not support CHECKSUM_COMPLETE,
so statistic for that form of checksumming wasn't included.
Other drivers will definitely need it, in fact we expect it
to be needed in net-next soon (mlx5). So let's add the definition
of the counter for CHECKSUM_COMPLETE to uAPI in net already,
so that the counters are in a more natural order (all subsequent
counters have not been present in any released kernel, yet).

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Fixes: 0cfe71f45f42 ("netdev: add queue stats")
Link: https://lore.kernel.org/r/20240529163547.3693194-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/netdev.yaml | 4 ++++
 include/uapi/linux/netdev.h             | 1 +
 tools/include/uapi/linux/netdev.h       | 1 +
 3 files changed, 6 insertions(+)

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

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 11a32373365a..959755be4d7f 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -349,6 +349,10 @@ attribute-sets:
           Number of packets dropped due to transient lack of resources, such as
           buffer space, host descriptors etc.
         type: uint
+      -
+        name: rx-csum-complete
+        doc: Number of packets that were marked as CHECKSUM_COMPLETE.
+        type: uint
       -
         name: rx-csum-unnecessary
         doc: Number of packets that were marked as CHECKSUM_UNNECESSARY.
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index a8188202413e..43742ac5b00d 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -148,6 +148,7 @@ enum {
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
 	NETDEV_A_QSTATS_RX_HW_DROPS,
 	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_COMPLETE,
 	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
 	NETDEV_A_QSTATS_RX_CSUM_NONE,
 	NETDEV_A_QSTATS_RX_CSUM_BAD,
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index a8188202413e..43742ac5b00d 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -148,6 +148,7 @@ enum {
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
 	NETDEV_A_QSTATS_RX_HW_DROPS,
 	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_COMPLETE,
 	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
 	NETDEV_A_QSTATS_RX_CSUM_NONE,
 	NETDEV_A_QSTATS_RX_CSUM_BAD,
-- 
cgit v1.2.3


From d6283b160a12010b2113cc64726a3c9eda13dc5f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 29 May 2024 10:38:04 -0300
Subject: tools headers uapi: Sync linux/stat.h with the kernel sources to pick
 STATX_SUBVOL

To pick the changes from:

  2a82bb02941fb53d ("statx: stx_subvol")

This silences this perf build warning:

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

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/lkml/ZlnK2Fmx_gahzwZI@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/stat.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

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

diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 2f2ee82d5517..67626d535316 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -126,8 +126,9 @@ struct statx {
 	__u64	stx_mnt_id;
 	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
 	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
+	__u64	stx_subvol;	/* Subvolume identifier */
 	/* 0xa0 */
-	__u64	__spare3[12];	/* Spare space for future expansion */
+	__u64	__spare3[11];	/* Spare space for future expansion */
 	/* 0x100 */
 };
 
@@ -155,6 +156,7 @@ struct statx {
 #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_SUBVOL		0x00008000U	/* Want/got stx_subvol */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
-- 
cgit v1.2.3


From a3cfe84cca28f205761a0450016593b0d728165e Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadfed@meta.com>
Date: Thu, 6 Jun 2024 07:58:50 -0700
Subject: bpf: Add CHECKSUM_COMPLETE to bpf test progs

Add special flag to validate that TC BPF program properly updates
checksum information in skb.

Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240606145851.229116-1-vadfed@meta.com
---
 include/uapi/linux/bpf.h       |  2 ++
 net/bpf/test_run.c             | 28 +++++++++++++++++++++++++++-
 tools/include/uapi/linux/bpf.h |  2 ++
 3 files changed, 31 insertions(+), 1 deletion(-)

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

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 25ea393cf084..35bcf52dbc65 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1425,6 +1425,8 @@ enum {
 #define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
 /* If set, XDP frames will be transmitted after processing */
 #define BPF_F_TEST_XDP_LIVE_FRAMES	(1U << 1)
+/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */
+#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE	(1U << 2)
 
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 36ae54f57bf5..3c965e32fc33 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -983,7 +983,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;
 
-	if (kattr->test.flags || kattr->test.cpu || kattr->test.batch_size)
+	if ((kattr->test.flags & ~BPF_F_TEST_SKB_CHECKSUM_COMPLETE) ||
+	    kattr->test.cpu || kattr->test.batch_size)
 		return -EINVAL;
 
 	data = bpf_test_init(kattr, kattr->test.data_size_in,
@@ -1031,6 +1032,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
 	__skb_put(skb, size);
+
 	if (ctx && ctx->ifindex > 1) {
 		dev = dev_get_by_index(net, ctx->ifindex);
 		if (!dev) {
@@ -1066,9 +1068,19 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		__skb_push(skb, hh_len);
 	if (is_direct_pkt_access)
 		bpf_compute_data_pointers(skb);
+
 	ret = convert___skb_to_skb(skb, ctx);
 	if (ret)
 		goto out;
+
+	if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) {
+		const int off = skb_network_offset(skb);
+		int len = skb->len - off;
+
+		skb->csum = skb_checksum(skb, off, len, 0);
+		skb->ip_summed = CHECKSUM_COMPLETE;
+	}
+
 	ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false);
 	if (ret)
 		goto out;
@@ -1083,6 +1095,20 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		}
 		memset(__skb_push(skb, hh_len), 0, hh_len);
 	}
+
+	if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) {
+		const int off = skb_network_offset(skb);
+		int len = skb->len - off;
+		__wsum csum;
+
+		csum = skb_checksum(skb, off, len, 0);
+
+		if (csum_fold(skb->csum) != csum_fold(csum)) {
+			ret = -EBADMSG;
+			goto out;
+		}
+	}
+
 	convert_skb_to___skb(skb, ctx);
 
 	size = skb->len;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 25ea393cf084..35bcf52dbc65 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1425,6 +1425,8 @@ enum {
 #define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
 /* If set, XDP frames will be transmitted after processing */
 #define BPF_F_TEST_XDP_LIVE_FRAMES	(1U << 1)
+/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */
+#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE	(1U << 2)
 
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
-- 
cgit v1.2.3


From e20194725bb25bb94c238fd9056108ea50a760c0 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Mon, 17 Jun 2024 19:24:20 -0700
Subject: selftests/mm: fix vm_util.c build failures: add snapshot of fs.h

On Ubuntu 23.04, on a clean git tree, the selftests/mm build fails due 10
or 20 missing items, all of which are found in fs.h, which is created via
"make headers".  However, as per [1], the idea is to stop requiring "make
headers", and instead, take a snapshot of the files and check them in.

Here are a few of the build errors:

vm_util.c:34:21: error: variable has incomplete type 'struct pm_scan_arg'
        struct pm_scan_arg arg;
...
vm_util.c:45:28: error: use of undeclared identifier 'PAGE_IS_WPALLOWED'
...
vm_util.c:55:21: error: variable has incomplete type 'struct page_region'
...
vm_util.c:105:20: error: use of undeclared identifier 'PAGE_IS_SOFT_DIRTY'

To fix this, add fs.h, taken from a snapshot of ./usr/include/linux/fs.h
after running "make headers".

[1] commit e076eaca5906 ("selftests: break the dependency upon local
header files")

Link: https://lkml.kernel.org/r/20240618022422.804305-5-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andrei Vagin <avagin@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rich Felker <dalias@libc.org>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/include/uapi/linux/fs.h | 392 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 392 insertions(+)
 create mode 100644 tools/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
new file mode 100644
index 000000000000..cc3fea99fd43
--- /dev/null
+++ b/tools/include/uapi/linux/fs.h
@@ -0,0 +1,392 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_FS_H
+#define _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>
+#include <linux/fscrypt.h>
+
+/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
+#include <linux/mount.h>
+
+/*
+ * 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;
+};
+
+/*
+ * We include a length field because some filesystems (vfat) have an identifier
+ * that we do want to expose as a UUID, but doesn't have the standard length.
+ *
+ * We use a fixed size buffer beacuse this interface will, by fiat, never
+ * support "UUIDs" longer than 16 bytes; we don't want to force all downstream
+ * users to have to deal with that.
+ */
+struct fsuuid2 {
+	__u8	len;
+	__u8	uuid[16];
+};
+
+struct fs_sysfs_path {
+	__u8			len;
+	__u8			name[128];
+};
+
+/* 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])
+/* Returns the external filesystem UUID, the same one blkid returns */
+#define FS_IOC_GETFSUUID		_IOR(0x15, 0, struct fsuuid2)
+/*
+ * Returns the path component under /sys/fs/ that refers to this filesystem;
+ * also /sys/kernel/debug/ for filesystems with debugfs exports
+ */
+#define FS_IOC_GETFSSYSFSPATH		_IOR(0x15, 1, struct fs_sysfs_path)
+
+/*
+ * 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	((__kernel_rwf_t)0x00000001)
+
+/* per-IO O_DSYNC */
+#define RWF_DSYNC	((__kernel_rwf_t)0x00000002)
+
+/* per-IO O_SYNC */
+#define RWF_SYNC	((__kernel_rwf_t)0x00000004)
+
+/* per-IO, return -EAGAIN if operation would block */
+#define RWF_NOWAIT	((__kernel_rwf_t)0x00000008)
+
+/* per-IO O_APPEND */
+#define RWF_APPEND	((__kernel_rwf_t)0x00000010)
+
+/* per-IO negation of O_APPEND */
+#define RWF_NOAPPEND	((__kernel_rwf_t)0x00000020)
+
+/* mask of flags supported by the kernel */
+#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
+			 RWF_APPEND | RWF_NOAPPEND)
+
+/* 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 /* _LINUX_FS_H */
-- 
cgit v1.2.3


From c142850fbc956058ff2f2987d3d11eb2c628f710 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Mon, 17 Jun 2024 19:24:21 -0700
Subject: selftests/mm: kvm, mdwe fixes to avoid requiring "make headers"

On Ubuntu 23.04, the kvm and mdwe selftests/mm build fails due to
missing a few items that are found in prctl.h. Here is an excerpt of the
build failures:

ksm_tests.c:252:13: error: use of undeclared identifier 'PR_SET_MEMORY_MERGE'
...
mdwe_test.c:26:18: error: use of undeclared identifier 'PR_SET_MDWE'
mdwe_test.c:38:18: error: use of undeclared identifier 'PR_GET_MDWE'

Fix these errors by adding a new tools/include/uapi/linux/prctl.h . This
file was created by running "make headers", and then copying a snapshot
over from ./usr/include/linux/prctl.h, as per the approach we settled on
in [1].

[1] commit e076eaca5906 ("selftests: break the dependency upon local
header files")

Link: https://lkml.kernel.org/r/20240618022422.804305-6-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andrei Vagin <avagin@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rich Felker <dalias@libc.org>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/include/uapi/linux/prctl.h | 331 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 331 insertions(+)
 create mode 100644 tools/include/uapi/linux/prctl.h

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

diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
new file mode 100644
index 000000000000..35791791a879
--- /dev/null
+++ b/tools/include/uapi/linux/prctl.h
@@ -0,0 +1,331 @@
+/* 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
+
+#define PR_RISCV_SET_ICACHE_FLUSH_CTX	71
+# define PR_RISCV_CTX_SW_FENCEI_ON	0
+# define PR_RISCV_CTX_SW_FENCEI_OFF	1
+# define PR_RISCV_SCOPE_PER_PROCESS	0
+# define PR_RISCV_SCOPE_PER_THREAD	1
+
+/* PowerPC Dynamic Execution Control Register (DEXCR) controls */
+#define PR_PPC_GET_DEXCR		72
+#define PR_PPC_SET_DEXCR		73
+/* DEXCR aspect to act on */
+# define PR_PPC_DEXCR_SBHE		0 /* Speculative branch hint enable */
+# define PR_PPC_DEXCR_IBRTPD		1 /* Indirect branch recurrent target prediction disable */
+# define PR_PPC_DEXCR_SRAPD		2 /* Subroutine return address prediction disable */
+# define PR_PPC_DEXCR_NPHIE		3 /* Non-privileged hash instruction enable */
+/* Action to apply / return */
+# define PR_PPC_DEXCR_CTRL_EDITABLE	 0x1 /* Aspect can be modified with PR_PPC_SET_DEXCR */
+# define PR_PPC_DEXCR_CTRL_SET		 0x2 /* Set the aspect for this process */
+# define PR_PPC_DEXCR_CTRL_CLEAR	 0x4 /* Clear the aspect for this process */
+# define PR_PPC_DEXCR_CTRL_SET_ONEXEC	 0x8 /* Set the aspect on exec */
+# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC	0x10 /* Clear the aspect on exec */
+# define PR_PPC_DEXCR_CTRL_MASK		0x1f
+
+#endif /* _LINUX_PRCTL_H */
-- 
cgit v1.2.3


From 9ff0e37c68821d1a6c482cb258ad3b4696f91254 Mon Sep 17 00:00:00 2001
From: Isaku Yamahata <isaku.yamahata@intel.com>
Date: Wed, 10 Apr 2024 15:07:36 -0700
Subject: KVM: selftests: x86: Add test for KVM_PRE_FAULT_MEMORY

Add a test case to exercise KVM_PRE_FAULT_MEMORY and run the guest to access the
pre-populated area.  It tests KVM_PRE_FAULT_MEMORY ioctl for KVM_X86_DEFAULT_VM
and KVM_X86_SW_PROTECTED_VM.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Message-ID: <32427791ef42e5efaafb05d2ac37fa4372715f47.1712785629.git.isaku.yamahata@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/include/uapi/linux/kvm.h                     |  14 +-
 tools/testing/selftests/kvm/Makefile               |   1 +
 .../testing/selftests/kvm/pre_fault_memory_test.c  | 146 +++++++++++++++++++++
 3 files changed, 159 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/pre_fault_memory_test.c

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

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index ea32b101b999..e5af8c692dc0 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -917,6 +917,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_MEMORY_ATTRIBUTES 233
 #define KVM_CAP_GUEST_MEMFD 234
 #define KVM_CAP_VM_TYPES 235
+#define KVM_CAP_PRE_FAULT_MEMORY 236
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1221,9 +1222,9 @@ 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_MMU_HASH_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)
@@ -1548,4 +1549,13 @@ struct kvm_create_guest_memfd {
 	__u64 reserved[6];
 };
 
+#define KVM_PRE_FAULT_MEMORY	_IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory)
+
+struct kvm_pre_fault_memory {
+	__u64 gpa;
+	__u64 size;
+	__u64 flags;
+	__u64 padding[5];
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index ce8ff8e8ce3a..e915d4ae1793 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -145,6 +145,7 @@ TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test
 TEST_GEN_PROGS_x86_64 += system_counter_offset_test
+TEST_GEN_PROGS_x86_64 += pre_fault_memory_test
 
 # Compiled outputs used by test targets
 TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test
diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c
new file mode 100644
index 000000000000..0350a8896a2f
--- /dev/null
+++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024, Intel, Inc
+ *
+ * Author:
+ * Isaku Yamahata <isaku.yamahata at gmail.com>
+ */
+#include <linux/sizes.h>
+
+#include <test_util.h>
+#include <kvm_util.h>
+#include <processor.h>
+
+/* Arbitrarily chosen values */
+#define TEST_SIZE		(SZ_2M + PAGE_SIZE)
+#define TEST_NPAGES		(TEST_SIZE / PAGE_SIZE)
+#define TEST_SLOT		10
+
+static void guest_code(uint64_t base_gpa)
+{
+	volatile uint64_t val __used;
+	int i;
+
+	for (i = 0; i < TEST_NPAGES; i++) {
+		uint64_t *src = (uint64_t *)(base_gpa + i * PAGE_SIZE);
+
+		val = *src;
+	}
+
+	GUEST_DONE();
+}
+
+static void pre_fault_memory(struct kvm_vcpu *vcpu, u64 gpa, u64 size,
+			     u64 left)
+{
+	struct kvm_pre_fault_memory range = {
+		.gpa = gpa,
+		.size = size,
+		.flags = 0,
+	};
+	u64 prev;
+	int ret, save_errno;
+
+	do {
+		prev = range.size;
+		ret = __vcpu_ioctl(vcpu, KVM_PRE_FAULT_MEMORY, &range);
+		save_errno = errno;
+		TEST_ASSERT((range.size < prev) ^ (ret < 0),
+			    "%sexpecting range.size to change on %s",
+			    ret < 0 ? "not " : "",
+			    ret < 0 ? "failure" : "success");
+	} while (ret >= 0 ? range.size : save_errno == EINTR);
+
+	TEST_ASSERT(range.size == left,
+		    "Completed with %lld bytes left, expected %" PRId64,
+		    range.size, left);
+
+	if (left == 0)
+		__TEST_ASSERT_VM_VCPU_IOCTL(!ret, "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm);
+	else
+		/* No memory slot causes RET_PF_EMULATE. it results in -ENOENT. */
+		__TEST_ASSERT_VM_VCPU_IOCTL(ret && save_errno == ENOENT,
+					    "KVM_PRE_FAULT_MEMORY", ret, vcpu->vm);
+}
+
+static void __test_pre_fault_memory(unsigned long vm_type, bool private)
+{
+	const struct vm_shape shape = {
+		.mode = VM_MODE_DEFAULT,
+		.type = vm_type,
+	};
+	struct kvm_vcpu *vcpu;
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+	struct ucall uc;
+
+	uint64_t guest_test_phys_mem;
+	uint64_t guest_test_virt_mem;
+	uint64_t alignment, guest_page_size;
+
+	vm = vm_create_shape_with_one_vcpu(shape, &vcpu, guest_code);
+
+	alignment = guest_page_size = vm_guest_mode_params[VM_MODE_DEFAULT].page_size;
+	guest_test_phys_mem = (vm->max_gfn - TEST_NPAGES) * guest_page_size;
+#ifdef __s390x__
+	alignment = max(0x100000UL, guest_page_size);
+#else
+	alignment = SZ_2M;
+#endif
+	guest_test_phys_mem = align_down(guest_test_phys_mem, alignment);
+	guest_test_virt_mem = guest_test_phys_mem & ((1ULL << (vm->va_bits - 1)) - 1);
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    guest_test_phys_mem, TEST_SLOT, TEST_NPAGES,
+				    private ? KVM_MEM_GUEST_MEMFD : 0);
+	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, TEST_NPAGES);
+
+	if (private)
+		vm_mem_set_private(vm, guest_test_phys_mem, TEST_SIZE);
+	pre_fault_memory(vcpu, guest_test_phys_mem, SZ_2M, 0);
+	pre_fault_memory(vcpu, guest_test_phys_mem + SZ_2M, PAGE_SIZE * 2, PAGE_SIZE);
+	pre_fault_memory(vcpu, guest_test_phys_mem + TEST_SIZE, PAGE_SIZE, PAGE_SIZE);
+
+	vcpu_args_set(vcpu, 1, guest_test_virt_mem);
+	vcpu_run(vcpu);
+
+	run = vcpu->run;
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Wanted KVM_EXIT_IO, got exit reason: %u (%s)",
+		    run->exit_reason, exit_reason_str(run->exit_reason));
+
+	switch (get_ucall(vcpu, &uc)) {
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT(uc);
+		break;
+	case UCALL_DONE:
+		break;
+	default:
+		TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd);
+		break;
+	}
+
+	kvm_vm_free(vm);
+}
+
+static void test_pre_fault_memory(unsigned long vm_type, bool private)
+{
+	if (vm_type && !(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(vm_type))) {
+		pr_info("Skipping tests for vm_type 0x%lx\n", vm_type);
+		return;
+	}
+
+	__test_pre_fault_memory(vm_type, private);
+}
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_check_cap(KVM_CAP_PRE_FAULT_MEMORY));
+
+	test_pre_fault_memory(0, false);
+#ifdef __x86_64__
+	test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, false);
+	test_pre_fault_memory(KVM_X86_SW_PROTECTED_VM, true);
+#endif
+	return 0;
+}
-- 
cgit v1.2.3


From 77179b6f30811bf0bd2f62fcdf235997123e70dc Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 27 Jun 2024 10:08:57 -0700
Subject: tools: sync uapi/linux/fs.h header into tools subdir

We need this UAPI header in tools/include subdirectory for using it from
BPF selftests.

Link: https://lkml.kernel.org/r/20240627170900.1672542-6-andrii@kernel.org
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/include/uapi/linux/fs.h | 180 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 170 insertions(+), 10 deletions(-)

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

diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index cc3fea99fd43..8a27bc5c7a7f 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _LINUX_FS_H
-#define _LINUX_FS_H
+#ifndef _UAPI_LINUX_FS_H
+#define _UAPI_LINUX_FS_H
 
 /*
  * This file has definitions for some important file table structures
@@ -13,10 +13,14 @@
 #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
@@ -308,29 +312,31 @@ struct fsxattr {
 typedef int __bitwise __kernel_rwf_t;
 
 /* high priority request, poll if possible */
-#define RWF_HIPRI	((__kernel_rwf_t)0x00000001)
+#define RWF_HIPRI	((__force __kernel_rwf_t)0x00000001)
 
 /* per-IO O_DSYNC */
-#define RWF_DSYNC	((__kernel_rwf_t)0x00000002)
+#define RWF_DSYNC	((__force __kernel_rwf_t)0x00000002)
 
 /* per-IO O_SYNC */
-#define RWF_SYNC	((__kernel_rwf_t)0x00000004)
+#define RWF_SYNC	((__force __kernel_rwf_t)0x00000004)
 
 /* per-IO, return -EAGAIN if operation would block */
-#define RWF_NOWAIT	((__kernel_rwf_t)0x00000008)
+#define RWF_NOWAIT	((__force __kernel_rwf_t)0x00000008)
 
 /* per-IO O_APPEND */
-#define RWF_APPEND	((__kernel_rwf_t)0x00000010)
+#define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
 
 /* per-IO negation of O_APPEND */
-#define RWF_NOAPPEND	((__kernel_rwf_t)0x00000020)
+#define RWF_NOAPPEND	((__force __kernel_rwf_t)0x00000020)
 
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
 			 RWF_APPEND | RWF_NOAPPEND)
 
+#define PROCFS_IOCTL_MAGIC 'f'
+
 /* Pagemap ioctl */
-#define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
+#define PAGEMAP_SCAN	_IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg)
 
 /* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */
 #define PAGE_IS_WPALLOWED	(1 << 0)
@@ -389,4 +395,158 @@ struct pm_scan_arg {
 	__u64 return_mask;
 };
 
-#endif /* _LINUX_FS_H */
+/* /proc/<pid>/maps ioctl */
+#define PROCMAP_QUERY	_IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query)
+
+enum procmap_query_flags {
+	/*
+	 * VMA permission flags.
+	 *
+	 * Can be used as part of procmap_query.query_flags field to look up
+	 * only VMAs satisfying specified subset of permissions. E.g., specifying
+	 * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs,
+	 * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only
+	 * return read/write VMAs, though both executable/non-executable and
+	 * private/shared will be ignored.
+	 *
+	 * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags
+	 * field to specify actual VMA permissions.
+	 */
+	PROCMAP_QUERY_VMA_READABLE		= 0x01,
+	PROCMAP_QUERY_VMA_WRITABLE		= 0x02,
+	PROCMAP_QUERY_VMA_EXECUTABLE		= 0x04,
+	PROCMAP_QUERY_VMA_SHARED		= 0x08,
+	/*
+	 * Query modifier flags.
+	 *
+	 * By default VMA that covers provided address is returned, or -ENOENT
+	 * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest
+	 * VMA with vma_start > addr will be returned if no covering VMA is
+	 * found.
+	 *
+	 * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that
+	 * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA
+	 * to iterate all VMAs with file backing.
+	 */
+	PROCMAP_QUERY_COVERING_OR_NEXT_VMA	= 0x10,
+	PROCMAP_QUERY_FILE_BACKED_VMA		= 0x20,
+};
+
+/*
+ * Input/output argument structured passed into ioctl() call. It can be used
+ * to query a set of VMAs (Virtual Memory Areas) of a process.
+ *
+ * Each field can be one of three kinds, marked in a short comment to the
+ * right of the field:
+ *   - "in", input argument, user has to provide this value, kernel doesn't modify it;
+ *   - "out", output argument, kernel sets this field with VMA data;
+ *   - "in/out", input and output argument; user provides initial value (used
+ *     to specify maximum allowable buffer size), and kernel sets it to actual
+ *     amount of data written (or zero, if there is no data).
+ *
+ * If matching VMA is found (according to criterias specified by
+ * query_addr/query_flags, all the out fields are filled out, and ioctl()
+ * returns 0. If there is no matching VMA, -ENOENT will be returned.
+ * In case of any other error, negative error code other than -ENOENT is
+ * returned.
+ *
+ * Most of the data is similar to the one returned as text in /proc/<pid>/maps
+ * file, but procmap_query provides more querying flexibility. There are no
+ * consistency guarantees between subsequent ioctl() calls, but data returned
+ * for matched VMA is self-consistent.
+ */
+struct procmap_query {
+	/* Query struct size, for backwards/forward compatibility */
+	__u64 size;
+	/*
+	 * Query flags, a combination of enum procmap_query_flags values.
+	 * Defines query filtering and behavior, see enum procmap_query_flags.
+	 *
+	 * Input argument, provided by user. Kernel doesn't modify it.
+	 */
+	__u64 query_flags;		/* in */
+	/*
+	 * Query address. By default, VMA that covers this address will
+	 * be looked up. PROCMAP_QUERY_* flags above modify this default
+	 * behavior further.
+	 *
+	 * Input argument, provided by user. Kernel doesn't modify it.
+	 */
+	__u64 query_addr;		/* in */
+	/* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */
+	__u64 vma_start;		/* out */
+	__u64 vma_end;			/* out */
+	/* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */
+	__u64 vma_flags;		/* out */
+	/* VMA backing page size granularity. */
+	__u64 vma_page_size;		/* out */
+	/*
+	 * VMA file offset. If VMA has file backing, this specifies offset
+	 * within the file that VMA's start address corresponds to.
+	 * Is set to zero if VMA has no backing file.
+	 */
+	__u64 vma_offset;		/* out */
+	/* Backing file's inode number, or zero, if VMA has no backing file. */
+	__u64 inode;			/* out */
+	/* Backing file's device major/minor number, or zero, if VMA has no backing file. */
+	__u32 dev_major;		/* out */
+	__u32 dev_minor;		/* out */
+	/*
+	 * If set to non-zero value, signals the request to return VMA name
+	 * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix
+	 * appended, if file was unlinked from FS) for matched VMA. VMA name
+	 * can also be some special name (e.g., "[heap]", "[stack]") or could
+	 * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME).
+	 *
+	 * Kernel will set this field to zero, if VMA has no associated name.
+	 * Otherwise kernel will return actual amount of bytes filled in
+	 * user-supplied buffer (see vma_name_addr field below), including the
+	 * terminating zero.
+	 *
+	 * If VMA name is longer that user-supplied maximum buffer size,
+	 * -E2BIG error is returned.
+	 *
+	 * If this field is set to non-zero value, vma_name_addr should point
+	 * to valid user space memory buffer of at least vma_name_size bytes.
+	 * If set to zero, vma_name_addr should be set to zero as well
+	 */
+	__u32 vma_name_size;		/* in/out */
+	/*
+	 * If set to non-zero value, signals the request to extract and return
+	 * VMA's backing file's build ID, if the backing file is an ELF file
+	 * and it contains embedded build ID.
+	 *
+	 * Kernel will set this field to zero, if VMA has no backing file,
+	 * backing file is not an ELF file, or ELF file has no build ID
+	 * embedded.
+	 *
+	 * Build ID is a binary value (not a string). Kernel will set
+	 * build_id_size field to exact number of bytes used for build ID.
+	 * If build ID is requested and present, but needs more bytes than
+	 * user-supplied maximum buffer size (see build_id_addr field below),
+	 * -E2BIG error will be returned.
+	 *
+	 * If this field is set to non-zero value, build_id_addr should point
+	 * to valid user space memory buffer of at least build_id_size bytes.
+	 * If set to zero, build_id_addr should be set to zero as well
+	 */
+	__u32 build_id_size;		/* in/out */
+	/*
+	 * User-supplied address of a buffer of at least vma_name_size bytes
+	 * for kernel to fill with matched VMA's name (see vma_name_size field
+	 * description above for details).
+	 *
+	 * Should be set to zero if VMA name should not be returned.
+	 */
+	__u64 vma_name_addr;		/* in */
+	/*
+	 * User-supplied address of a buffer of at least build_id_size bytes
+	 * for kernel to fill with matched VMA's ELF build ID, if available
+	 * (see build_id_size field description above for details).
+	 *
+	 * Should be set to zero if build ID should not be returned.
+	 */
+	__u64 build_id_addr;		/* in */
+};
+
+#endif /* _UAPI_LINUX_FS_H */
-- 
cgit v1.2.3


From 9651fcedf7b92d3f7f1ab179e8ab55b85ee10fc1 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Thu, 8 Dec 2022 17:55:04 +0100
Subject: mm: add MAP_DROPPABLE for designating always lazily freeable mappings

The vDSO getrandom() implementation works with a buffer allocated with a
new system call that has certain requirements:

- It shouldn't be written to core dumps.
  * Easy: VM_DONTDUMP.
- It should be zeroed on fork.
  * Easy: VM_WIPEONFORK.

- It shouldn't be written to swap.
  * Uh-oh: mlock is rlimited.
  * Uh-oh: mlock isn't inherited by forks.

- It shouldn't reserve actual memory, but it also shouldn't crash when
  page faulting in memory if none is available
  * Uh-oh: VM_NORESERVE means segfaults.

It turns out that the vDSO getrandom() function has three really nice
characteristics that we can exploit to solve this problem:

1) Due to being wiped during fork(), the vDSO code is already robust to
   having the contents of the pages it reads zeroed out midway through
   the function's execution.

2) In the absolute worst case of whatever contingency we're coding for,
   we have the option to fallback to the getrandom() syscall, and
   everything is fine.

3) The buffers the function uses are only ever useful for a maximum of
   60 seconds -- a sort of cache, rather than a long term allocation.

These characteristics mean that we can introduce VM_DROPPABLE, which
has the following semantics:

a) It never is written out to swap.
b) Under memory pressure, mm can just drop the pages (so that they're
   zero when read back again).
c) It is inherited by fork.
d) It doesn't count against the mlock budget, since nothing is locked.
e) If there's not enough memory to service a page fault, it's not fatal,
   and no signal is sent.

This way, allocations used by vDSO getrandom() can use:

    VM_DROPPABLE | VM_DONTDUMP | VM_WIPEONFORK | VM_NORESERVE

And there will be no problem with OOMing, crashing on overcommitment,
using memory when not in use, not wiping on fork(), coredumps, or
writing out to swap.

In order to let vDSO getrandom() use this, expose these via mmap(2) as
MAP_DROPPABLE.

Note that this involves removing the MADV_FREE special case from
sort_folio(), which according to Yu Zhao is unnecessary and will simply
result in an extra call to shrink_folio_list() in the worst case. The
chunk removed reenables the swapbacked flag, which we don't want for
VM_DROPPABLE, and we can't conditionalize it here because there isn't a
vma reference available.

Finally, the provided self test ensures that this is working as desired.

Cc: linux-mm@kvack.org
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 fs/proc/task_mmu.c                     |  1 +
 include/linux/mm.h                     |  7 +++++
 include/linux/userfaultfd_k.h          |  3 ++
 include/trace/events/mmflags.h         |  7 +++++
 include/uapi/linux/mman.h              |  1 +
 mm/ksm.c                               |  2 +-
 mm/madvise.c                           |  5 +++-
 mm/memory.c                            | 13 +++++++++
 mm/mempolicy.c                         |  3 ++
 mm/mlock.c                             |  2 +-
 mm/mmap.c                              | 30 +++++++++++++++++++
 mm/rmap.c                              | 22 ++++++++++++--
 mm/vmscan.c                            |  9 ------
 tools/include/uapi/linux/mman.h        |  1 +
 tools/testing/selftests/mm/.gitignore  |  1 +
 tools/testing/selftests/mm/Makefile    |  1 +
 tools/testing/selftests/mm/droppable.c | 53 ++++++++++++++++++++++++++++++++++
 17 files changed, 146 insertions(+), 15 deletions(-)
 create mode 100644 tools/testing/selftests/mm/droppable.c

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

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 71e5039d940d..46f0b0fe9ee3 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -708,6 +708,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_SHADOW_STACK)] = "ss",
 #endif
 #ifdef CONFIG_64BIT
+		[ilog2(VM_DROPPABLE)] = "dp",
 		[ilog2(VM_SEALED)] = "sl",
 #endif
 	};
diff --git a/include/linux/mm.h b/include/linux/mm.h
index eb7c96d24ac0..e078c2890bf8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -406,6 +406,13 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_ALLOW_ANY_UNCACHED		VM_NONE
 #endif
 
+#ifdef CONFIG_64BIT
+#define VM_DROPPABLE_BIT	40
+#define VM_DROPPABLE		BIT(VM_DROPPABLE_BIT)
+#else
+#define VM_DROPPABLE		VM_NONE
+#endif
+
 #ifdef CONFIG_64BIT
 /* VM is sealed, in vm_flags */
 #define VM_SEALED	_BITUL(63)
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 05d59f74fc88..a12bcf042551 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -218,6 +218,9 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 {
 	vm_flags &= __VM_UFFD_FLAGS;
 
+	if (vm_flags & VM_DROPPABLE)
+		return false;
+
 	if ((vm_flags & VM_UFFD_MINOR) &&
 	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
 		return false;
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index e46d6e82765e..b63d211bd141 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -165,6 +165,12 @@ IF_HAVE_PG_ARCH_X(arch_3)
 # define IF_HAVE_UFFD_MINOR(flag, name)
 #endif
 
+#ifdef CONFIG_64BIT
+# define IF_HAVE_VM_DROPPABLE(flag, name) {flag, name},
+#else
+# define IF_HAVE_VM_DROPPABLE(flag, name)
+#endif
+
 #define __def_vmaflag_names						\
 	{VM_READ,			"read"		},		\
 	{VM_WRITE,			"write"		},		\
@@ -197,6 +203,7 @@ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY,	"softdirty"	)		\
 	{VM_MIXEDMAP,			"mixedmap"	},		\
 	{VM_HUGEPAGE,			"hugepage"	},		\
 	{VM_NOHUGEPAGE,			"nohugepage"	},		\
+IF_HAVE_VM_DROPPABLE(VM_DROPPABLE,	"droppable"	)		\
 	{VM_MERGEABLE,			"mergeable"	}		\
 
 #define show_vma_flags(flags)						\
diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h
index a246e11988d5..e89d00528f2f 100644
--- a/include/uapi/linux/mman.h
+++ b/include/uapi/linux/mman.h
@@ -17,6 +17,7 @@
 #define MAP_SHARED	0x01		/* Share changes */
 #define MAP_PRIVATE	0x02		/* Changes are private */
 #define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+#define MAP_DROPPABLE	0x08		/* Zero memory under memory pressure. */
 
 /*
  * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
diff --git a/mm/ksm.c b/mm/ksm.c
index 34c4820e0d3d..8778eb7c40f8 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -717,7 +717,7 @@ static bool vma_ksm_compatible(struct vm_area_struct *vma)
 {
 	if (vma->vm_flags & (VM_SHARED  | VM_MAYSHARE   | VM_PFNMAP  |
 			     VM_IO      | VM_DONTEXPAND | VM_HUGETLB |
-			     VM_MIXEDMAP))
+			     VM_MIXEDMAP| VM_DROPPABLE))
 		return false;		/* just ignore the advice */
 
 	if (vma_is_dax(vma))
diff --git a/mm/madvise.c b/mm/madvise.c
index a77893462b92..cba5bc652fc4 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1068,13 +1068,16 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
 		new_flags |= VM_WIPEONFORK;
 		break;
 	case MADV_KEEPONFORK:
+		if (vma->vm_flags & VM_DROPPABLE)
+			return -EINVAL;
 		new_flags &= ~VM_WIPEONFORK;
 		break;
 	case MADV_DONTDUMP:
 		new_flags |= VM_DONTDUMP;
 		break;
 	case MADV_DODUMP:
-		if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL)
+		if ((!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) ||
+		    (vma->vm_flags & VM_DROPPABLE))
 			return -EINVAL;
 		new_flags &= ~VM_DONTDUMP;
 		break;
diff --git a/mm/memory.c b/mm/memory.c
index d10e616d7389..98d9a4485d24 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5660,6 +5660,7 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	/* If the fault handler drops the mmap_lock, vma may be freed */
 	struct mm_struct *mm = vma->vm_mm;
 	vm_fault_t ret;
+	bool is_droppable;
 
 	__set_current_state(TASK_RUNNING);
 
@@ -5674,6 +5675,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 		goto out;
 	}
 
+	is_droppable = !!(vma->vm_flags & VM_DROPPABLE);
+
 	/*
 	 * Enable the memcg OOM handling for faults triggered in user
 	 * space.  Kernel faults are handled more gracefully.
@@ -5688,8 +5691,18 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	else
 		ret = __handle_mm_fault(vma, address, flags);
 
+	/*
+	 * Warning: It is no longer safe to dereference vma-> after this point,
+	 * because mmap_lock might have been dropped by __handle_mm_fault(), so
+	 * vma might be destroyed from underneath us.
+	 */
+
 	lru_gen_exit_fault();
 
+	/* If the mapping is droppable, then errors due to OOM aren't fatal. */
+	if (is_droppable)
+		ret &= ~VM_FAULT_OOM;
+
 	if (flags & FAULT_FLAG_USER) {
 		mem_cgroup_exit_user_fault();
 		/*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index aec756ae5637..32291ab25960 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2300,6 +2300,9 @@ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct
 	pgoff_t ilx;
 	struct page *page;
 
+	if (vma->vm_flags & VM_DROPPABLE)
+		gfp |= __GFP_NOWARN;
+
 	pol = get_vma_policy(vma, addr, order, &ilx);
 	page = alloc_pages_mpol_noprof(gfp | __GFP_COMP, order,
 				       pol, ilx, numa_node_id());
diff --git a/mm/mlock.c b/mm/mlock.c
index 30b51cdea89d..b87b3d8cc9cc 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -485,7 +485,7 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
 
 	if (newflags == oldflags || (oldflags & VM_SPECIAL) ||
 	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
-	    vma_is_dax(vma) || vma_is_secretmem(vma))
+	    vma_is_dax(vma) || vma_is_secretmem(vma) || (oldflags & VM_DROPPABLE))
 		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
 		goto out;
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 83b4682ec85c..8aeedeb784c2 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1369,6 +1369,36 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 			pgoff = 0;
 			vm_flags |= VM_SHARED | VM_MAYSHARE;
 			break;
+		case MAP_DROPPABLE:
+			if (VM_DROPPABLE == VM_NONE)
+				return -ENOTSUPP;
+			/*
+			 * A locked or stack area makes no sense to be droppable.
+			 *
+			 * Also, since droppable pages can just go away at any time
+			 * it makes no sense to copy them on fork or dump them.
+			 *
+			 * And don't attempt to combine with hugetlb for now.
+			 */
+			if (flags & (MAP_LOCKED | MAP_HUGETLB))
+			        return -EINVAL;
+			if (vm_flags & (VM_GROWSDOWN | VM_GROWSUP))
+			        return -EINVAL;
+
+			vm_flags |= VM_DROPPABLE;
+
+			/*
+			 * If the pages can be dropped, then it doesn't make
+			 * sense to reserve them.
+			 */
+			vm_flags |= VM_NORESERVE;
+
+			/*
+			 * Likewise, they're volatile enough that they
+			 * shouldn't survive forks or coredumps.
+			 */
+			vm_flags |= VM_WIPEONFORK | VM_DONTDUMP;
+			fallthrough;
 		case MAP_PRIVATE:
 			/*
 			 * Set pgoff according to addr for anon_vma.
diff --git a/mm/rmap.c b/mm/rmap.c
index e8fc5ecb59b2..1f9b5a9cb121 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1397,7 +1397,12 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
 	VM_BUG_ON_VMA(address < vma->vm_start ||
 			address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
-	__folio_set_swapbacked(folio);
+	/*
+	 * VM_DROPPABLE mappings don't swap; instead they're just dropped when
+	 * under memory pressure.
+	 */
+	if (!(vma->vm_flags & VM_DROPPABLE))
+		__folio_set_swapbacked(folio);
 	__folio_set_anon(folio, vma, address, true);
 
 	if (likely(!folio_test_large(folio))) {
@@ -1841,7 +1846,13 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				 * plus the rmap(s) (dropped by discard:).
 				 */
 				if (ref_count == 1 + map_count &&
-				    !folio_test_dirty(folio)) {
+				    (!folio_test_dirty(folio) ||
+				     /*
+				      * Unlike MADV_FREE mappings, VM_DROPPABLE
+				      * ones can be dropped even if they've
+				      * been dirtied.
+				      */
+				     (vma->vm_flags & VM_DROPPABLE))) {
 					dec_mm_counter(mm, MM_ANONPAGES);
 					goto discard;
 				}
@@ -1851,7 +1862,12 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				 * discarded. Remap the page to page table.
 				 */
 				set_pte_at(mm, address, pvmw.pte, pteval);
-				folio_set_swapbacked(folio);
+				/*
+				 * Unlike MADV_FREE mappings, VM_DROPPABLE ones
+				 * never get swap backed on failure to drop.
+				 */
+				if (!(vma->vm_flags & VM_DROPPABLE))
+					folio_set_swapbacked(folio);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
 				break;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2e34de9cd0d4..5ef0ee4610d6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4265,15 +4265,6 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 		return true;
 	}
 
-	/* dirty lazyfree */
-	if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) {
-		success = lru_gen_del_folio(lruvec, folio, true);
-		VM_WARN_ON_ONCE_FOLIO(!success, folio);
-		folio_set_swapbacked(folio);
-		lruvec_add_folio_tail(lruvec, folio);
-		return true;
-	}
-
 	/* promoted */
 	if (gen != lru_gen_from_seq(lrugen->min_seq[type])) {
 		list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index a246e11988d5..e89d00528f2f 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -17,6 +17,7 @@
 #define MAP_SHARED	0x01		/* Share changes */
 #define MAP_PRIVATE	0x02		/* Changes are private */
 #define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+#define MAP_DROPPABLE	0x08		/* Zero memory under memory pressure. */
 
 /*
  * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index 0b9ab987601c..a8beeb43c2b5 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -49,3 +49,4 @@ hugetlb_fault_after_madv
 hugetlb_madv_vs_map
 mseal_test
 seal_elf
+droppable
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 3b49bc3d0a3b..e3e5740e13e1 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -73,6 +73,7 @@ TEST_GEN_FILES += ksm_functional_tests
 TEST_GEN_FILES += mdwe_test
 TEST_GEN_FILES += hugetlb_fault_after_madv
 TEST_GEN_FILES += hugetlb_madv_vs_map
+TEST_GEN_FILES += droppable
 
 ifneq ($(ARCH),arm64)
 TEST_GEN_FILES += soft-dirty
diff --git a/tools/testing/selftests/mm/droppable.c b/tools/testing/selftests/mm/droppable.c
new file mode 100644
index 000000000000..f3d9ecf96890
--- /dev/null
+++ b/tools/testing/selftests/mm/droppable.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <assert.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/mman.h>
+
+#include "../kselftest.h"
+
+int main(int argc, char *argv[])
+{
+	size_t alloc_size = 134217728;
+	size_t page_size = getpagesize();
+	void *alloc;
+	pid_t child;
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	alloc = mmap(0, alloc_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_DROPPABLE, -1, 0);
+	assert(alloc != MAP_FAILED);
+	memset(alloc, 'A', alloc_size);
+	for (size_t i = 0; i < alloc_size; i += page_size)
+		assert(*(uint8_t *)(alloc + i));
+
+	child = fork();
+	assert(child >= 0);
+	if (!child) {
+		for (;;)
+			*(char *)malloc(page_size) = 'B';
+	}
+
+	for (bool done = false; !done;) {
+		for (size_t i = 0; i < alloc_size; i += page_size) {
+			if (!*(uint8_t *)(alloc + i)) {
+				done = true;
+				break;
+			}
+		}
+	}
+	kill(child, SIGTERM);
+
+	ksft_test_result_pass("MAP_DROPPABLE: PASS\n");
+	exit(KSFT_PASS);
+}
-- 
cgit v1.2.3


From 9b9969c40b0d63a8fca434d4ea01c60a39699aa3 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Fri, 12 Jul 2024 18:52:52 -0700
Subject: selftests/bpf: Add XDP_UMEM_TX_METADATA_LEN to XSK TX metadata test

This flag is now required to use tx_metadata_len.

Fixes: 40808a237d9c ("selftests/bpf: Add TX side to xdp_metadata")
Reported-by: Julian Schindel <mail@arctic-alpaca.de>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20240713015253.121248-3-sdf@fomichev.me
---
 tools/include/uapi/linux/if_xdp.h                     | 4 ++++
 tools/testing/selftests/bpf/prog_tests/xdp_metadata.c | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

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

diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 638c606dfa74..2f082b01ff22 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -41,6 +41,10 @@
  */
 #define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
+/* Request to reserve tx_metadata_len bytes of per-chunk metadata.
+ */
+#define XDP_UMEM_TX_METADATA_LEN	(1 << 2)
+
 struct sockaddr_xdp {
 	__u16 sxdp_family;
 	__u16 sxdp_flags;
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
index f76b5d67a3ee..c87ee2bf558c 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -68,7 +68,8 @@ static int open_xsk(int ifindex, struct xsk *xsk)
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG | XDP_UMEM_TX_SW_CSUM,
+		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG | XDP_UMEM_TX_SW_CSUM |
+			 XDP_UMEM_TX_METADATA_LEN,
 		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
 	};
 	__u32 idx;
-- 
cgit v1.2.3


From a625df3995c31a5d8cf46f2337b207e93bef9bdd Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 6 Aug 2024 12:07:50 -0700
Subject: tools/include: Sync uapi/linux/kvm.h with the kernel sources

And other arch-specific UAPI headers to pick up changes from:

  4b23e0c199b2 KVM: Ensure new code that references immediate_exit gets extra scrutiny
  85542adb65ec KVM: x86: Add KVM_RUN_X86_GUEST_MODE kvm_run flag
  6fef518594bc KVM: x86: Add a capability to configure bus frequency for APIC timer
  34ff65901735 x86/sev: Use kernel provided SVSM Calling Areas
  5dcc1e76144f Merge tag 'kvm-x86-misc-6.11' of https://github.com/kvm-x86/linux into HEAD
  9a0d2f4995dd KVM: PPC: Book3S HV: Add one-reg interface for HASHPKEYR register
  e9eb790b2557 KVM: PPC: Book3S HV: Add one-reg interface for HASHKEYR register
  1a1e6865f516 KVM: PPC: Book3S HV: Add one-reg interface for DEXCR register

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

  Warning: Kernel ABI header differences:
  diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
  diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h
  diff -u tools/arch/x86/include/uapi/asm/svm.h arch/x86/include/uapi/asm/svm.h
  diff -u tools/arch/powerpc/include/uapi/asm/kvm.h arch/powerpc/include/uapi/asm/kvm.h

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

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/arch/powerpc/include/uapi/asm/kvm.h |  3 ++
 tools/arch/x86/include/uapi/asm/kvm.h     | 49 +++++++++++++++++++++++++++++++
 tools/arch/x86/include/uapi/asm/svm.h     |  1 +
 tools/include/uapi/linux/kvm.h            | 17 ++++++++++-
 4 files changed, 69 insertions(+), 1 deletion(-)

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

diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 1691297a766a..eaeda001784e 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -645,6 +645,9 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_SIER3	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3)
 #define KVM_REG_PPC_DAWR1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4)
 #define KVM_REG_PPC_DAWRX1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5)
+#define KVM_REG_PPC_DEXCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc6)
+#define KVM_REG_PPC_HASHKEYR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc7)
+#define KVM_REG_PPC_HASHPKEYR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc8)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 9fae1b73b529..bf57a824f722 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -106,6 +106,7 @@ struct kvm_ioapic_state {
 
 #define KVM_RUN_X86_SMM		 (1 << 0)
 #define KVM_RUN_X86_BUS_LOCK     (1 << 1)
+#define KVM_RUN_X86_GUEST_MODE   (1 << 2)
 
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
@@ -697,6 +698,11 @@ enum sev_cmd_id {
 	/* Second time is the charm; improved versions of the above ioctls.  */
 	KVM_SEV_INIT2,
 
+	/* SNP-specific commands */
+	KVM_SEV_SNP_LAUNCH_START = 100,
+	KVM_SEV_SNP_LAUNCH_UPDATE,
+	KVM_SEV_SNP_LAUNCH_FINISH,
+
 	KVM_SEV_NR_MAX,
 };
 
@@ -824,6 +830,48 @@ struct kvm_sev_receive_update_data {
 	__u32 pad2;
 };
 
+struct kvm_sev_snp_launch_start {
+	__u64 policy;
+	__u8 gosvw[16];
+	__u16 flags;
+	__u8 pad0[6];
+	__u64 pad1[4];
+};
+
+/* Kept in sync with firmware values for simplicity. */
+#define KVM_SEV_SNP_PAGE_TYPE_NORMAL		0x1
+#define KVM_SEV_SNP_PAGE_TYPE_ZERO		0x3
+#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED	0x4
+#define KVM_SEV_SNP_PAGE_TYPE_SECRETS		0x5
+#define KVM_SEV_SNP_PAGE_TYPE_CPUID		0x6
+
+struct kvm_sev_snp_launch_update {
+	__u64 gfn_start;
+	__u64 uaddr;
+	__u64 len;
+	__u8 type;
+	__u8 pad0;
+	__u16 flags;
+	__u32 pad1;
+	__u64 pad2[4];
+};
+
+#define KVM_SEV_SNP_ID_BLOCK_SIZE	96
+#define KVM_SEV_SNP_ID_AUTH_SIZE	4096
+#define KVM_SEV_SNP_FINISH_DATA_SIZE	32
+
+struct kvm_sev_snp_launch_finish {
+	__u64 id_block_uaddr;
+	__u64 id_auth_uaddr;
+	__u8 id_block_en;
+	__u8 auth_key_en;
+	__u8 vcek_disabled;
+	__u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE];
+	__u8 pad0[3];
+	__u16 flags;
+	__u64 pad1[4];
+};
+
 #define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
 
@@ -874,5 +922,6 @@ struct kvm_hyperv_eventfd {
 #define KVM_X86_SW_PROTECTED_VM	1
 #define KVM_X86_SEV_VM		2
 #define KVM_X86_SEV_ES_VM	3
+#define KVM_X86_SNP_VM		4
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index 80e1df482337..1814b413fd57 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -115,6 +115,7 @@
 #define SVM_VMGEXIT_AP_CREATE_ON_INIT		0
 #define SVM_VMGEXIT_AP_CREATE			1
 #define SVM_VMGEXIT_AP_DESTROY			2
+#define SVM_VMGEXIT_SNP_RUN_VMPL		0x80000018
 #define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
 #define SVM_VMGEXIT_TERM_REQUEST		0x8000fffe
 #define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code)	\
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index e5af8c692dc0..637efc055145 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -192,11 +192,24 @@ struct kvm_xen_exit {
 /* Flags that describe what fields in emulation_failure hold valid data. */
 #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0)
 
+/*
+ * struct kvm_run can be modified by userspace at any time, so KVM must be
+ * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM()
+ * renames fields in struct kvm_run from <symbol> to <symbol>__unsafe when
+ * compiled into the kernel, ensuring that any use within KVM is obvious and
+ * gets extra scrutiny.
+ */
+#ifdef __KERNEL__
+#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe
+#else
+#define HINT_UNSAFE_IN_KVM(_symbol) _symbol
+#endif
+
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
 	/* in */
 	__u8 request_interrupt_window;
-	__u8 immediate_exit;
+	__u8 HINT_UNSAFE_IN_KVM(immediate_exit);
 	__u8 padding1[6];
 
 	/* out */
@@ -918,6 +931,8 @@ struct kvm_enable_cap {
 #define KVM_CAP_GUEST_MEMFD 234
 #define KVM_CAP_VM_TYPES 235
 #define KVM_CAP_PRE_FAULT_MEMORY 236
+#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
+#define KVM_CAP_X86_GUEST_MODE 238
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
-- 
cgit v1.2.3


From 8ec9497d3ef34fab216e277eca5035811f06b421 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 6 Aug 2024 12:07:50 -0700
Subject: tools/include: Sync uapi/linux/perf.h with the kernel sources

To pick up changes from:

  608f6976c309 perf/x86/intel: Support new data source for Lunar Lake

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

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

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

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: linux-perf-users@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/include/uapi/linux/perf_event.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

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

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 3a64499b0f5d..4842c36fdf80 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1349,12 +1349,14 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
-/* 5-0x7 available */
+#define PERF_MEM_LVLNUM_L2_MHB	0x05 /* L2 Miss Handling Buffer */
+#define PERF_MEM_LVLNUM_MSC	0x06 /* Memory-side Cache */
+/* 0x7 available */
 #define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
-#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
+#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB / L1 Miss Handling Buffer */
 #define PERF_MEM_LVLNUM_RAM	0x0d /* RAM */
 #define PERF_MEM_LVLNUM_PMEM	0x0e /* PMEM */
 #define PERF_MEM_LVLNUM_NA	0x0f /* N/A */
-- 
cgit v1.2.3


From ed86525f1f4b738bae75c73e89f25430bd0af1b0 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 6 Aug 2024 12:07:50 -0700
Subject: tools/include: Sync network socket headers with the kernel sources

To pick up changes from:

  d25a92ccae6b net/smc: Introduce IPPROTO_SMC
  060f4ba6e403 io_uring/net: move charging socket out of zc io_uring
  bb6aaf736680 net: Split a __sys_listen helper for io_uring
  dc2e77979412 net: Split a __sys_bind helper for io_uring

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

  Warning: Kernel ABI header differences:
  diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h
  diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h

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

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: netdev@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/include/uapi/linux/in.h                  | 2 ++
 tools/perf/trace/beauty/include/linux/socket.h | 5 ++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

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

diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index e682ab628dfa..d358add1611c 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -81,6 +81,8 @@ enum {
 #define IPPROTO_ETHERNET	IPPROTO_ETHERNET
   IPPROTO_RAW = 255,		/* Raw IP packets			*/
 #define IPPROTO_RAW		IPPROTO_RAW
+  IPPROTO_SMC = 256,		/* Shared Memory Communications		*/
+#define IPPROTO_SMC		IPPROTO_SMC
   IPPROTO_MPTCP = 262,		/* Multipath TCP connection		*/
 #define IPPROTO_MPTCP		IPPROTO_MPTCP
   IPPROTO_MAX
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 89d16b90370b..df9cdb8bbfb8 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -76,7 +76,7 @@ struct msghdr {
 	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
 	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
 	struct ubuf_info *msg_ubuf;
-	int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb,
+	int (*sg_from_iter)(struct sk_buff *skb,
 			    struct iov_iter *from, size_t length);
 };
 
@@ -442,11 +442,14 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
 extern int __sys_socket(int family, int type, int protocol);
 extern struct file *__sys_socket_file(int family, int type, int protocol);
 extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen);
+extern int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address,
+			     int addrlen);
 extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr,
 			      int addrlen, int file_flags);
 extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
 			 int addrlen);
 extern int __sys_listen(int fd, int backlog);
+extern int __sys_listen_socket(struct socket *sock, int backlog);
 extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
 			     int __user *usockaddr_len);
 extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
-- 
cgit v1.2.3


From 845295f4004c7e1591bab4bad01b51f37d32272f Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 6 Aug 2024 12:07:50 -0700
Subject: tools/include: Sync filesystem headers with the kernel sources

To pick up changes from:

  0f9ca80fa4f9 fs: Add initial atomic write support info to statx
  f9af549d1fd3 fs: export mount options via statmount()
  0a3deb11858a fs: Allow listmount() in foreign mount namespace
  09b31295f833 fs: export the mount ns id via statmount
  d04bccd8c19d listmount: allow listing in reverse order
  bfc69fd05ef9 fs/procfs: add build ID fetching to PROCMAP_QUERY API
  ed5d583a88a9 fs/procfs: implement efficient VMA querying API for /proc/<pid>/maps

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

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

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

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/include/uapi/linux/stat.h                    |  12 +-
 tools/perf/trace/beauty/include/uapi/linux/fs.h    | 163 ++++++++++++++++++++-
 tools/perf/trace/beauty/include/uapi/linux/mount.h |  10 +-
 tools/perf/trace/beauty/include/uapi/linux/stat.h  |  12 +-
 4 files changed, 189 insertions(+), 8 deletions(-)

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

diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 67626d535316..887a25286441 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -126,9 +126,15 @@ struct statx {
 	__u64	stx_mnt_id;
 	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
 	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
-	__u64	stx_subvol;	/* Subvolume identifier */
 	/* 0xa0 */
-	__u64	__spare3[11];	/* Spare space for future expansion */
+	__u64	stx_subvol;	/* Subvolume identifier */
+	__u32	stx_atomic_write_unit_min;	/* Min atomic write unit in bytes */
+	__u32	stx_atomic_write_unit_max;	/* Max atomic write unit in bytes */
+	/* 0xb0 */
+	__u32   stx_atomic_write_segments_max;	/* Max atomic write segment count */
+	__u32   __spare1[1];
+	/* 0xb8 */
+	__u64	__spare3[9];	/* Spare space for future expansion */
 	/* 0x100 */
 };
 
@@ -157,6 +163,7 @@ struct statx {
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
 #define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 #define STATX_SUBVOL		0x00008000U	/* Want/got stx_subvol */
+#define STATX_WRITE_ATOMIC	0x00010000U	/* Want/got atomic_write_* fields */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
@@ -192,6 +199,7 @@ struct statx {
 #define STATX_ATTR_MOUNT_ROOT		0x00002000 /* Root of a mount */
 #define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
 #define STATX_ATTR_DAX			0x00200000 /* File is currently in DAX state */
+#define STATX_ATTR_WRITE_ATOMIC		0x00400000 /* File supports atomic write operations */
 
 
 #endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 45e4e64fd664..753971770733 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -329,12 +329,17 @@ typedef int __bitwise __kernel_rwf_t;
 /* per-IO negation of O_APPEND */
 #define RWF_NOAPPEND	((__force __kernel_rwf_t)0x00000020)
 
+/* Atomic Write */
+#define RWF_ATOMIC	((__force __kernel_rwf_t)0x00000040)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-			 RWF_APPEND | RWF_NOAPPEND)
+			 RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC)
+
+#define PROCFS_IOCTL_MAGIC 'f'
 
 /* Pagemap ioctl */
-#define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
+#define PAGEMAP_SCAN	_IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg)
 
 /* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */
 #define PAGE_IS_WPALLOWED	(1 << 0)
@@ -393,4 +398,158 @@ struct pm_scan_arg {
 	__u64 return_mask;
 };
 
+/* /proc/<pid>/maps ioctl */
+#define PROCMAP_QUERY	_IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query)
+
+enum procmap_query_flags {
+	/*
+	 * VMA permission flags.
+	 *
+	 * Can be used as part of procmap_query.query_flags field to look up
+	 * only VMAs satisfying specified subset of permissions. E.g., specifying
+	 * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs,
+	 * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only
+	 * return read/write VMAs, though both executable/non-executable and
+	 * private/shared will be ignored.
+	 *
+	 * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags
+	 * field to specify actual VMA permissions.
+	 */
+	PROCMAP_QUERY_VMA_READABLE		= 0x01,
+	PROCMAP_QUERY_VMA_WRITABLE		= 0x02,
+	PROCMAP_QUERY_VMA_EXECUTABLE		= 0x04,
+	PROCMAP_QUERY_VMA_SHARED		= 0x08,
+	/*
+	 * Query modifier flags.
+	 *
+	 * By default VMA that covers provided address is returned, or -ENOENT
+	 * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest
+	 * VMA with vma_start > addr will be returned if no covering VMA is
+	 * found.
+	 *
+	 * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that
+	 * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA
+	 * to iterate all VMAs with file backing.
+	 */
+	PROCMAP_QUERY_COVERING_OR_NEXT_VMA	= 0x10,
+	PROCMAP_QUERY_FILE_BACKED_VMA		= 0x20,
+};
+
+/*
+ * Input/output argument structured passed into ioctl() call. It can be used
+ * to query a set of VMAs (Virtual Memory Areas) of a process.
+ *
+ * Each field can be one of three kinds, marked in a short comment to the
+ * right of the field:
+ *   - "in", input argument, user has to provide this value, kernel doesn't modify it;
+ *   - "out", output argument, kernel sets this field with VMA data;
+ *   - "in/out", input and output argument; user provides initial value (used
+ *     to specify maximum allowable buffer size), and kernel sets it to actual
+ *     amount of data written (or zero, if there is no data).
+ *
+ * If matching VMA is found (according to criterias specified by
+ * query_addr/query_flags, all the out fields are filled out, and ioctl()
+ * returns 0. If there is no matching VMA, -ENOENT will be returned.
+ * In case of any other error, negative error code other than -ENOENT is
+ * returned.
+ *
+ * Most of the data is similar to the one returned as text in /proc/<pid>/maps
+ * file, but procmap_query provides more querying flexibility. There are no
+ * consistency guarantees between subsequent ioctl() calls, but data returned
+ * for matched VMA is self-consistent.
+ */
+struct procmap_query {
+	/* Query struct size, for backwards/forward compatibility */
+	__u64 size;
+	/*
+	 * Query flags, a combination of enum procmap_query_flags values.
+	 * Defines query filtering and behavior, see enum procmap_query_flags.
+	 *
+	 * Input argument, provided by user. Kernel doesn't modify it.
+	 */
+	__u64 query_flags;		/* in */
+	/*
+	 * Query address. By default, VMA that covers this address will
+	 * be looked up. PROCMAP_QUERY_* flags above modify this default
+	 * behavior further.
+	 *
+	 * Input argument, provided by user. Kernel doesn't modify it.
+	 */
+	__u64 query_addr;		/* in */
+	/* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */
+	__u64 vma_start;		/* out */
+	__u64 vma_end;			/* out */
+	/* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */
+	__u64 vma_flags;		/* out */
+	/* VMA backing page size granularity. */
+	__u64 vma_page_size;		/* out */
+	/*
+	 * VMA file offset. If VMA has file backing, this specifies offset
+	 * within the file that VMA's start address corresponds to.
+	 * Is set to zero if VMA has no backing file.
+	 */
+	__u64 vma_offset;		/* out */
+	/* Backing file's inode number, or zero, if VMA has no backing file. */
+	__u64 inode;			/* out */
+	/* Backing file's device major/minor number, or zero, if VMA has no backing file. */
+	__u32 dev_major;		/* out */
+	__u32 dev_minor;		/* out */
+	/*
+	 * If set to non-zero value, signals the request to return VMA name
+	 * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix
+	 * appended, if file was unlinked from FS) for matched VMA. VMA name
+	 * can also be some special name (e.g., "[heap]", "[stack]") or could
+	 * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME).
+	 *
+	 * Kernel will set this field to zero, if VMA has no associated name.
+	 * Otherwise kernel will return actual amount of bytes filled in
+	 * user-supplied buffer (see vma_name_addr field below), including the
+	 * terminating zero.
+	 *
+	 * If VMA name is longer that user-supplied maximum buffer size,
+	 * -E2BIG error is returned.
+	 *
+	 * If this field is set to non-zero value, vma_name_addr should point
+	 * to valid user space memory buffer of at least vma_name_size bytes.
+	 * If set to zero, vma_name_addr should be set to zero as well
+	 */
+	__u32 vma_name_size;		/* in/out */
+	/*
+	 * If set to non-zero value, signals the request to extract and return
+	 * VMA's backing file's build ID, if the backing file is an ELF file
+	 * and it contains embedded build ID.
+	 *
+	 * Kernel will set this field to zero, if VMA has no backing file,
+	 * backing file is not an ELF file, or ELF file has no build ID
+	 * embedded.
+	 *
+	 * Build ID is a binary value (not a string). Kernel will set
+	 * build_id_size field to exact number of bytes used for build ID.
+	 * If build ID is requested and present, but needs more bytes than
+	 * user-supplied maximum buffer size (see build_id_addr field below),
+	 * -E2BIG error will be returned.
+	 *
+	 * If this field is set to non-zero value, build_id_addr should point
+	 * to valid user space memory buffer of at least build_id_size bytes.
+	 * If set to zero, build_id_addr should be set to zero as well
+	 */
+	__u32 build_id_size;		/* in/out */
+	/*
+	 * User-supplied address of a buffer of at least vma_name_size bytes
+	 * for kernel to fill with matched VMA's name (see vma_name_size field
+	 * description above for details).
+	 *
+	 * Should be set to zero if VMA name should not be returned.
+	 */
+	__u64 vma_name_addr;		/* in */
+	/*
+	 * User-supplied address of a buffer of at least build_id_size bytes
+	 * for kernel to fill with matched VMA's ELF build ID, if available
+	 * (see build_id_size field description above for details).
+	 *
+	 * Should be set to zero if build ID should not be returned.
+	 */
+	__u64 build_id_addr;		/* in */
+};
+
 #endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
index ad5478dbad00..225bc366ffcb 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/mount.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
@@ -154,7 +154,7 @@ struct mount_attr {
  */
 struct statmount {
 	__u32 size;		/* Total size, including strings */
-	__u32 __spare1;
+	__u32 mnt_opts;		/* [str] Mount options of the mount */
 	__u64 mask;		/* What results were written */
 	__u32 sb_dev_major;	/* Device ID */
 	__u32 sb_dev_minor;
@@ -172,7 +172,8 @@ struct statmount {
 	__u64 propagate_from;	/* Propagation from in current namespace */
 	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
 	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
-	__u64 __spare2[50];
+	__u64 mnt_ns_id;	/* ID of the mount namespace */
+	__u64 __spare2[49];
 	char str[];		/* Variable size part containing strings */
 };
 
@@ -188,10 +189,12 @@ struct mnt_id_req {
 	__u32 spare;
 	__u64 mnt_id;
 	__u64 param;
+	__u64 mnt_ns_id;
 };
 
 /* List of all mnt_id_req versions. */
 #define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+#define MNT_ID_REQ_SIZE_VER1	32 /* sizeof second published struct */
 
 /*
  * @mask bits for statmount(2)
@@ -202,10 +205,13 @@ struct mnt_id_req {
 #define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
 #define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
 #define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+#define STATMOUNT_MNT_NS_ID		0x00000040U	/* Want/got mnt_ns_id */
+#define STATMOUNT_MNT_OPTS		0x00000080U	/* Want/got mnt_opts */
 
 /*
  * Special @mnt_id values that can be passed to listmount
  */
 #define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+#define LISTMOUNT_REVERSE	(1 << 0) /* List later mounts first */
 
 #endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h
index 67626d535316..887a25286441 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/stat.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h
@@ -126,9 +126,15 @@ struct statx {
 	__u64	stx_mnt_id;
 	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
 	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
-	__u64	stx_subvol;	/* Subvolume identifier */
 	/* 0xa0 */
-	__u64	__spare3[11];	/* Spare space for future expansion */
+	__u64	stx_subvol;	/* Subvolume identifier */
+	__u32	stx_atomic_write_unit_min;	/* Min atomic write unit in bytes */
+	__u32	stx_atomic_write_unit_max;	/* Max atomic write unit in bytes */
+	/* 0xb0 */
+	__u32   stx_atomic_write_segments_max;	/* Max atomic write segment count */
+	__u32   __spare1[1];
+	/* 0xb8 */
+	__u64	__spare3[9];	/* Spare space for future expansion */
 	/* 0x100 */
 };
 
@@ -157,6 +163,7 @@ struct statx {
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
 #define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 #define STATX_SUBVOL		0x00008000U	/* Want/got stx_subvol */
+#define STATX_WRITE_ATOMIC	0x00010000U	/* Want/got atomic_write_* fields */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
@@ -192,6 +199,7 @@ struct statx {
 #define STATX_ATTR_MOUNT_ROOT		0x00002000 /* Root of a mount */
 #define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
 #define STATX_ATTR_DAX			0x00200000 /* File is currently in DAX state */
+#define STATX_ATTR_WRITE_ATOMIC		0x00400000 /* File supports atomic write operations */
 
 
 #endif /* _UAPI_LINUX_STAT_H */
-- 
cgit v1.2.3


From 3882dccf48f9fbe787b5df3187d708ef348ac860 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Thu, 8 Aug 2024 16:05:57 +0100
Subject: bpf/bpf_get,set_sockopt: add option to set TCP-BPF sock ops flags

Currently the only opportunity to set sock ops flags dictating
which callbacks fire for a socket is from within a TCP-BPF sockops
program.  This is problematic if the connection is already set up
as there is no further chance to specify callbacks for that socket.
Add TCP_BPF_SOCK_OPS_CB_FLAGS to bpf_setsockopt() and bpf_getsockopt()
to allow users to specify callbacks later, either via an iterator
over sockets or via a socket-specific program triggered by a
setsockopt() on the socket.

Previous discussion on this here [1].

[1] https://lore.kernel.org/bpf/f42f157b-6e52-dd4d-3d97-9b86c84c0b00@oracle.com/

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Link: https://lore.kernel.org/r/20240808150558.1035626-2-alan.maguire@oracle.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/uapi/linux/bpf.h       |  3 ++-
 net/core/filter.c              | 16 ++++++++++++++++
 tools/include/uapi/linux/bpf.h |  3 ++-
 3 files changed, 20 insertions(+), 2 deletions(-)

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

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 35bcf52dbc65..e05b39e39c3f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2851,7 +2851,7 @@ union bpf_attr {
  * 		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**,
  * 		  **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**,
  * 		  **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**,
- * 		  **TCP_BPF_RTO_MIN**.
+ *		  **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 		* **IPPROTO_IPV6**, which supports the following *optname*\ s:
  * 		  **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
@@ -7080,6 +7080,7 @@ enum {
 	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
+	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
 };
 
 enum {
diff --git a/net/core/filter.c b/net/core/filter.c
index f3c72cf86099..d96a50f3f016 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5278,6 +5278,11 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
 			return -EINVAL;
 		inet_csk(sk)->icsk_rto_min = timeout;
 		break;
+	case TCP_BPF_SOCK_OPS_CB_FLAGS:
+		if (val & ~(BPF_SOCK_OPS_ALL_CB_FLAGS))
+			return -EINVAL;
+		tp->bpf_sock_ops_cb_flags = val;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -5366,6 +5371,17 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 		if (*optlen < 1)
 			return -EINVAL;
 		break;
+	case TCP_BPF_SOCK_OPS_CB_FLAGS:
+		if (*optlen != sizeof(int))
+			return -EINVAL;
+		if (getopt) {
+			struct tcp_sock *tp = tcp_sk(sk);
+			int cb_flags = tp->bpf_sock_ops_cb_flags;
+
+			memcpy(optval, &cb_flags, *optlen);
+			return 0;
+		}
+		return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen);
 	default:
 		if (getopt)
 			return -EINVAL;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 35bcf52dbc65..e05b39e39c3f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2851,7 +2851,7 @@ union bpf_attr {
  * 		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**,
  * 		  **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**,
  * 		  **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**,
- * 		  **TCP_BPF_RTO_MIN**.
+ *		  **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 		* **IPPROTO_IPV6**, which supports the following *optname*\ s:
  * 		  **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
@@ -7080,6 +7080,7 @@ enum {
 	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
+	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
 };
 
 enum {
-- 
cgit v1.2.3


From 65ab5ac4df012388481d0414fcac1d5ac1721fb3 Mon Sep 17 00:00:00 2001
From: Jordan Rome <linux@jordanrome.com>
Date: Fri, 23 Aug 2024 12:51:00 -0700
Subject: bpf: Add bpf_copy_from_user_str kfunc

This adds a kfunc wrapper around strncpy_from_user,
which can be called from sleepable BPF programs.

This matches the non-sleepable 'bpf_probe_read_user_str'
helper except it includes an additional 'flags'
param, which allows consumers to clear the entire
destination buffer on success or failure.

Signed-off-by: Jordan Rome <linux@jordanrome.com>
Link: https://lore.kernel.org/r/20240823195101.3621028-1-linux@jordanrome.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       |  9 +++++++++
 kernel/bpf/helpers.c           | 42 ++++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  9 +++++++++
 3 files changed, 60 insertions(+)

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

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e2629457d72d..c3a5728db115 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7513,4 +7513,13 @@ struct bpf_iter_num {
 	__u64 __opaque[1];
 } __attribute__((aligned(8)));
 
+/*
+ * Flags to control BPF kfunc behaviour.
+ *     - BPF_F_PAD_ZEROS: Pad destination buffer with zeros. (See the respective
+ *       helper documentation for details.)
+ */
+enum bpf_kfunc_flags {
+	BPF_F_PAD_ZEROS = (1ULL << 0),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index f12f075b70c5..7e7761c537f8 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2962,6 +2962,47 @@ __bpf_kfunc void bpf_iter_bits_destroy(struct bpf_iter_bits *it)
 	bpf_mem_free(&bpf_global_ma, kit->bits);
 }
 
+/**
+ * bpf_copy_from_user_str() - Copy a string from an unsafe user address
+ * @dst:             Destination address, in kernel space.  This buffer must be
+ *                   at least @dst__sz bytes long.
+ * @dst__sz:         Maximum number of bytes to copy, includes the trailing NUL.
+ * @unsafe_ptr__ign: Source address, in user space.
+ * @flags:           The only supported flag is BPF_F_PAD_ZEROS
+ *
+ * Copies a NUL-terminated string from userspace to BPF space. If user string is
+ * too long this will still ensure zero termination in the dst buffer unless
+ * buffer size is 0.
+ *
+ * If BPF_F_PAD_ZEROS flag is set, memset the tail of @dst to 0 on success and
+ * memset all of @dst on failure.
+ */
+__bpf_kfunc int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void __user *unsafe_ptr__ign, u64 flags)
+{
+	int ret;
+
+	if (unlikely(flags & ~BPF_F_PAD_ZEROS))
+		return -EINVAL;
+
+	if (unlikely(!dst__sz))
+		return 0;
+
+	ret = strncpy_from_user(dst, unsafe_ptr__ign, dst__sz - 1);
+	if (ret < 0) {
+		if (flags & BPF_F_PAD_ZEROS)
+			memset((char *)dst, 0, dst__sz);
+
+		return ret;
+	}
+
+	if (flags & BPF_F_PAD_ZEROS)
+		memset((char *)dst + ret, 0, dst__sz - ret);
+	else
+		((char *)dst)[ret] = '\0';
+
+	return ret + 1;
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(generic_btf_ids)
@@ -3047,6 +3088,7 @@ BTF_ID_FLAGS(func, bpf_preempt_enable)
 BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW)
 BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE)
 BTF_KFUNCS_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 35bcf52dbc65..f329ee44627a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7512,4 +7512,13 @@ struct bpf_iter_num {
 	__u64 __opaque[1];
 } __attribute__((aligned(8)));
 
+/*
+ * Flags to control BPF kfunc behaviour.
+ *     - BPF_F_PAD_ZEROS: Pad destination buffer with zeros. (See the respective
+ *       helper documentation for details.)
+ */
+enum bpf_kfunc_flags {
+	BPF_F_PAD_ZEROS = (1ULL << 0),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
-- 
cgit v1.2.3


From 3efd7ab46d0aebc3e567a9846e79a98dbad3291c Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:46 +0000
Subject: net: netdev netlink api to bind dma-buf to a net device

API takes the dma-buf fd as input, and binds it to the netdevice. The
user can specify the rx queues to bind the dma-buf to.

Suggested-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-3-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 47 +++++++++++++++++++++++++++++++++
 include/uapi/linux/netdev.h             | 11 ++++++++
 net/core/netdev-genl-gen.c              | 19 +++++++++++++
 net/core/netdev-genl-gen.h              |  2 ++
 net/core/netdev-genl.c                  |  6 +++++
 tools/include/uapi/linux/netdev.h       | 11 ++++++++
 6 files changed, 96 insertions(+)

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

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 959755be4d7f..4930e8142aa6 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -457,6 +457,39 @@ attribute-sets:
           Number of times driver re-started accepting send
           requests to this queue from the stack.
         type: uint
+  -
+    name: queue-id
+    subset-of: queue
+    attributes:
+      -
+        name: id
+      -
+        name: type
+  -
+    name: dmabuf
+    attributes:
+      -
+        name: ifindex
+        doc: netdev ifindex to bind the dmabuf to.
+        type: u32
+        checks:
+          min: 1
+      -
+        name: queues
+        doc: receive queues to bind the dmabuf to.
+        type: nest
+        nested-attributes: queue-id
+        multi-attr: true
+      -
+        name: fd
+        doc: dmabuf file descriptor to bind.
+        type: u32
+      -
+        name: id
+        doc: id of the dmabuf binding
+        type: u32
+        checks:
+          min: 1
 
 operations:
   list:
@@ -619,6 +652,20 @@ operations:
             - rx-bytes
             - tx-packets
             - tx-bytes
+    -
+      name: bind-rx
+      doc: Bind dmabuf to netdev
+      attribute-set: dmabuf
+      flags: [ admin-perm ]
+      do:
+        request:
+          attributes:
+            - ifindex
+            - fd
+            - queues
+        reply:
+          attributes:
+            - id
 
 mcast-groups:
   list:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 43742ac5b00d..91bf3ecc5f1d 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -173,6 +173,16 @@ enum {
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
 };
 
+enum {
+	NETDEV_A_DMABUF_IFINDEX = 1,
+	NETDEV_A_DMABUF_QUEUES,
+	NETDEV_A_DMABUF_FD,
+	NETDEV_A_DMABUF_ID,
+
+	__NETDEV_A_DMABUF_MAX,
+	NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
@@ -186,6 +196,7 @@ enum {
 	NETDEV_CMD_QUEUE_GET,
 	NETDEV_CMD_NAPI_GET,
 	NETDEV_CMD_QSTATS_GET,
+	NETDEV_CMD_BIND_RX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 8350a0afa9ec..6b7fe6035067 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -27,6 +27,11 @@ const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFIND
 	[NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range),
 };
 
+const struct nla_policy netdev_queue_id_nl_policy[NETDEV_A_QUEUE_TYPE + 1] = {
+	[NETDEV_A_QUEUE_ID] = { .type = NLA_U32, },
+	[NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1),
+};
+
 /* NETDEV_CMD_DEV_GET - do */
 static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = {
 	[NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
@@ -74,6 +79,13 @@ static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE
 	[NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1),
 };
 
+/* NETDEV_CMD_BIND_RX - do */
+static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1] = {
+	[NETDEV_A_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+	[NETDEV_A_DMABUF_FD] = { .type = NLA_U32, },
+	[NETDEV_A_DMABUF_QUEUES] = NLA_POLICY_NESTED(netdev_queue_id_nl_policy),
+};
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -151,6 +163,13 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.maxattr	= NETDEV_A_QSTATS_SCOPE,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= NETDEV_CMD_BIND_RX,
+		.doit		= netdev_nl_bind_rx_doit,
+		.policy		= netdev_bind_rx_nl_policy,
+		.maxattr	= NETDEV_A_DMABUF_FD,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 4db40fd5b4a9..67c34005750c 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -13,6 +13,7 @@
 
 /* Common nested types */
 extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1];
+extern const struct nla_policy netdev_queue_id_nl_policy[NETDEV_A_QUEUE_TYPE + 1];
 
 int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
@@ -30,6 +31,7 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
 				struct netlink_callback *cb);
+int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info);
 
 enum {
 	NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index a17d7eaeb001..699c34b9b03c 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -723,6 +723,12 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
 	return err;
 }
 
+/* Stub */
+int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return 0;
+}
+
 static int netdev_genl_netdevice_event(struct notifier_block *nb,
 				       unsigned long event, void *ptr)
 {
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 43742ac5b00d..91bf3ecc5f1d 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -173,6 +173,16 @@ enum {
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
 };
 
+enum {
+	NETDEV_A_DMABUF_IFINDEX = 1,
+	NETDEV_A_DMABUF_QUEUES,
+	NETDEV_A_DMABUF_FD,
+	NETDEV_A_DMABUF_ID,
+
+	__NETDEV_A_DMABUF_MAX,
+	NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
@@ -186,6 +196,7 @@ enum {
 	NETDEV_CMD_QUEUE_GET,
 	NETDEV_CMD_NAPI_GET,
 	NETDEV_CMD_QSTATS_GET,
+	NETDEV_CMD_BIND_RX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
-- 
cgit v1.2.3


From d0caf9876a1c9f844307effb598ad1312d9e0025 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:57 +0000
Subject: netdev: add dmabuf introspection

Add dmabuf information to page_pool stats:

$ ./cli.py --spec ../netlink/specs/netdev.yaml --dump page-pool-get
...
 {'dmabuf': 10,
  'id': 456,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 455,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 454,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 453,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 452,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 451,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 450,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 449,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},

And queue stats:

$ ./cli.py --spec ../netlink/specs/netdev.yaml --dump queue-get
...
{'dmabuf': 10, 'id': 8, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 9, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 10, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 11, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 12, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 13, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 14, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 15, 'ifindex': 3, 'type': 'rx'},

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-14-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 10 ++++++++++
 include/uapi/linux/netdev.h             |  2 ++
 net/core/netdev-genl.c                  |  7 +++++++
 net/core/page_pool_user.c               |  5 +++++
 tools/include/uapi/linux/netdev.h       |  2 ++
 5 files changed, 26 insertions(+)

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

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 0c747530c275..08412c279297 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -167,6 +167,10 @@ attribute-sets:
           "re-attached", they are just waiting to disappear.
           Attribute is absent if Page Pool has not been detached, and
           can still be used to allocate new memory.
+      -
+        name: dmabuf
+        doc: ID of the dmabuf this page-pool is attached to.
+        type: u32
   -
     name: page-pool-info
     subset-of: page-pool
@@ -268,6 +272,10 @@ attribute-sets:
         name: napi-id
         doc: ID of the NAPI instance which services this queue.
         type: u32
+      -
+        name: dmabuf
+        doc: ID of the dmabuf attached to this queue, if any.
+        type: u32
 
   -
     name: qstats
@@ -543,6 +551,7 @@ operations:
             - inflight
             - inflight-mem
             - detach-time
+            - dmabuf
       dump:
         reply: *pp-reply
       config-cond: page-pool
@@ -607,6 +616,7 @@ operations:
             - type
             - napi-id
             - ifindex
+            - dmabuf
       dump:
         request:
           attributes:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 91bf3ecc5f1d..7c308f04e7a0 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -93,6 +93,7 @@ enum {
 	NETDEV_A_PAGE_POOL_INFLIGHT,
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 	NETDEV_A_PAGE_POOL_DETACH_TIME,
+	NETDEV_A_PAGE_POOL_DMABUF,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
@@ -131,6 +132,7 @@ enum {
 	NETDEV_A_QUEUE_IFINDEX,
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
+	NETDEV_A_QUEUE_DMABUF,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 9153a8ab0cf8..1cb954f2d39e 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -295,6 +295,7 @@ static int
 netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 			 u32 q_idx, u32 q_type, const struct genl_info *info)
 {
+	struct net_devmem_dmabuf_binding *binding;
 	struct netdev_rx_queue *rxq;
 	struct netdev_queue *txq;
 	void *hdr;
@@ -314,6 +315,12 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 		if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
 					     rxq->napi->napi_id))
 			goto nla_put_failure;
+
+		binding = rxq->mp_params.mp_priv;
+		if (binding &&
+		    nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id))
+			goto nla_put_failure;
+
 		break;
 	case NETDEV_QUEUE_TYPE_TX:
 		txq = netdev_get_tx_queue(netdev, q_idx);
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index cd6267ba6fa3..48335766c1bf 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -9,6 +9,7 @@
 #include <net/page_pool/types.h>
 #include <net/sock.h>
 
+#include "devmem.h"
 #include "page_pool_priv.h"
 #include "netdev-genl-gen.h"
 
@@ -213,6 +214,7 @@ static int
 page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		  const struct genl_info *info)
 {
+	struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
 	size_t inflight, refsz;
 	void *hdr;
 
@@ -242,6 +244,9 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 			 pool->user.detach_time))
 		goto err_cancel;
 
+	if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id))
+		goto err_cancel;
+
 	genlmsg_end(rsp, hdr);
 
 	return 0;
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 91bf3ecc5f1d..7c308f04e7a0 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -93,6 +93,7 @@ enum {
 	NETDEV_A_PAGE_POOL_INFLIGHT,
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 	NETDEV_A_PAGE_POOL_DETACH_TIME,
+	NETDEV_A_PAGE_POOL_DMABUF,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
@@ -131,6 +132,7 @@ enum {
 	NETDEV_A_QUEUE_IFINDEX,
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
+	NETDEV_A_QUEUE_DMABUF,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
-- 
cgit v1.2.3


From dc1e764b398e0548b1bb12fb234ed0b673cd60fb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 30 Sep 2024 13:08:39 -0300
Subject: tools headers UAPI: Sync the linux/in.h with the kernel sources

Picking the changes from:

  70d0bb45fae87a3b ("net: Correct spelling in headers")

Just a comment fix, addressing this perf build warning:

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

Please see tools/include/uapi/README for details.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/lkml/ZvrNlLdtXAZ1sIIj@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/in.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

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

diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index d358add1611c..5d32d53508d9 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -141,7 +141,7 @@ struct in_addr {
  */
 #define IP_PMTUDISC_INTERFACE		4
 /* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
- * fragmented if they exeed the interface mtu
+ * fragmented if they exceed the interface mtu
  */
 #define IP_PMTUDISC_OMIT		5
 
-- 
cgit v1.2.3


From 3ed6be68913b2d56a35d30c67f83ba3d2f1998fc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 1 Oct 2024 21:41:05 +0200
Subject: bpf: Sync uapi bpf.h header to tools directory

There is a delta between kernel UAPI bpf.h and tools UAPI bpf.h,
thus sync them again.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

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

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1fb3cb2636e6..e8241b320c6d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5519,11 +5519,12 @@ union bpf_attr {
  *		**-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if
  *		invalid arguments are passed.
  *
- * void *bpf_kptr_xchg(void *map_value, void *ptr)
+ * void *bpf_kptr_xchg(void *dst, void *ptr)
  *	Description
- *		Exchange kptr at pointer *map_value* with *ptr*, and return the
- *		old value. *ptr* can be NULL, otherwise it must be a referenced
- *		pointer which will be released when this helper is called.
+ *		Exchange kptr at pointer *dst* with *ptr*, and return the old value.
+ *		*dst* can be map value or local kptr. *ptr* can be NULL, otherwise
+ *		it must be a referenced pointer which will be released when this helper
+ *		is called.
  *	Return
  *		The old value of kptr (which can be NULL). The returned pointer
  *		if not NULL, is a reference which must be released using its
@@ -6046,11 +6047,6 @@ enum {
 	BPF_F_MARK_ENFORCE		= (1ULL << 6),
 };
 
-/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
-enum {
-	BPF_F_INGRESS			= (1ULL << 0),
-};
-
 /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
 enum {
 	BPF_F_TUNINFO_IPV6		= (1ULL << 0),
@@ -6197,10 +6193,12 @@ enum {
 	BPF_F_BPRM_SECUREEXEC	= (1ULL << 0),
 };
 
-/* Flags for bpf_redirect_map helper */
+/* Flags for bpf_redirect and bpf_redirect_map helpers */
 enum {
-	BPF_F_BROADCAST		= (1ULL << 3),
-	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4),
+	BPF_F_INGRESS		= (1ULL << 0), /* used for skb path */
+	BPF_F_BROADCAST		= (1ULL << 3), /* used for XDP path */
+	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4), /* used for XDP path */
+#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS)
 };
 
 #define __bpf_md_ptr(type, name)	\
-- 
cgit v1.2.3


From 4f647a780f3606acbd2116248d51eadb4d865615 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Mon, 16 Sep 2024 02:17:10 -0700
Subject: bpf: __bpf_fastcall for bpf_get_smp_processor_id in uapi

Since [1] kernel supports __bpf_fastcall attribute for helper function
bpf_get_smp_processor_id(). Update uapi definition for this helper in
order to have this attribute in the generated bpf_helper_defs.h

[1] commit 91b7fbf3936f ("bpf, x86, riscv, arm: no_caller_saved_registers for bpf_get_smp_processor_id()")

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20240916091712.2929279-3-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       | 2 ++
 tools/include/uapi/linux/bpf.h | 2 ++
 2 files changed, 4 insertions(+)

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

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c6cd7c7aeeee..8ab4d8184b9d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1970,6 +1970,8 @@ union bpf_attr {
  * 		program.
  * 	Return
  * 		The SMP id of the processor running the program.
+ * 	Attributes
+ * 		__bpf_fastcall
  *
  * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
  * 	Description
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1fb3cb2636e6..7610883c8191 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1970,6 +1970,8 @@ union bpf_attr {
  * 		program.
  * 	Return
  * 		The SMP id of the processor running the program.
+ * 	Attributes
+ * 		__bpf_fastcall
  *
  * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags)
  * 	Description
-- 
cgit v1.2.3


From f858cc9eed5b05cbe38d7ffd2787c21e3718eb7d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 3 Oct 2024 12:12:18 +0000
Subject: net: add IFLA_MAX_PACING_OFFLOAD_HORIZON device attribute

Some network devices have the ability to offload EDT (Earliest
Departure Time) which is the model used for TCP pacing and FQ
packet scheduler.

Some of them implement the timing wheel mechanism described in
https://saeed.github.io/files/carousel-sigcomm17.pdf
with an associated 'timing wheel horizon'.

This patch adds dev->max_pacing_offload_horizon expressing
this timing wheel horizon in nsec units.

This is a read-only attribute.

Unless a driver sets it, dev->max_pacing_offload_horizon
is zero.

v2: addressed Jakub feedback ( https://lore.kernel.org/netdev/20240930152304.472767-2-edumazet@google.com/T/#mf6294d714c41cc459962154cc2580ce3c9693663 )
v3: added yaml doc (also per Jakub feedback)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20241003121219.2396589-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_link.yaml               | 4 ++++
 Documentation/networking/net_cachelines/net_device.rst | 1 +
 include/linux/netdevice.h                              | 4 ++++
 include/uapi/linux/if_link.h                           | 1 +
 net/core/rtnetlink.c                                   | 4 ++++
 tools/include/uapi/linux/if_link.h                     | 1 +
 6 files changed, 15 insertions(+)

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

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 0c4d5d40cae9..d7131a1afadf 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -1137,6 +1137,10 @@ attribute-sets:
         name: dpll-pin
         type: nest
         nested-attributes: link-dpll-pin-attrs
+      -
+        name: max-pacing-offload-horizon
+        type: uint
+        doc: EDT offload horizon supported by the device (in nsec).
   -
     name: af-spec-attrs
     attributes:
diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 22b07c814f4a..49f03cb78c6e 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -183,3 +183,4 @@ struct_devlink_port*                devlink_port
 struct_dpll_pin*                    dpll_pin                                                        
 struct hlist_head                   page_pools
 struct dim_irq_moder*               irq_moder
+u64                                 max_pacing_offload_horizon
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4d20c776a4ff..49a7e7db0883 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2009,6 +2009,8 @@ enum netdev_reg_state {
  *	@dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem,
  *		   where the clock is recovered.
  *
+ *	@max_pacing_offload_horizon: max EDT offload horizon in nsec.
+ *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
  */
@@ -2399,6 +2401,8 @@ struct net_device {
 	/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
 	struct dim_irq_moder	*irq_moder;
 
+	u64			max_pacing_offload_horizon;
+
 	u8			priv[] ____cacheline_aligned
 				       __counted_by(priv_len);
 } ____cacheline_aligned;
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 6dc258993b17..506ba9c80e83 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -377,6 +377,7 @@ enum {
 	IFLA_GSO_IPV4_MAX_SIZE,
 	IFLA_GRO_IPV4_MAX_SIZE,
 	IFLA_DPLL_PIN,
+	IFLA_MAX_PACING_OFFLOAD_HORIZON,
 	__IFLA_MAX
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f0a520987085..682d8d3127db 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1118,6 +1118,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */
 	       + rtnl_devlink_port_size(dev)
 	       + rtnl_dpll_pin_size(dev)
+	       + nla_total_size(8)  /* IFLA_MAX_PACING_OFFLOAD_HORIZON */
 	       + 0;
 }
 
@@ -1867,6 +1868,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 			READ_ONCE(dev->tso_max_size)) ||
 	    nla_put_u32(skb, IFLA_TSO_MAX_SEGS,
 			READ_ONCE(dev->tso_max_segs)) ||
+	    nla_put_uint(skb, IFLA_MAX_PACING_OFFLOAD_HORIZON,
+			 READ_ONCE(dev->max_pacing_offload_horizon)) ||
 #ifdef CONFIG_RPS
 	    nla_put_u32(skb, IFLA_NUM_RX_QUEUES,
 			READ_ONCE(dev->num_rx_queues)) ||
@@ -1975,6 +1978,7 @@ nla_put_failure:
 }
 
 static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
+	[IFLA_UNSPEC]		= { .strict_start_type = IFLA_DPLL_PIN },
 	[IFLA_IFNAME]		= { .type = NLA_STRING, .len = IFNAMSIZ-1 },
 	[IFLA_ADDRESS]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
 	[IFLA_BROADCAST]	= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index f0d71b2a3f1e..96ec2b01e725 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -377,6 +377,7 @@ enum {
 	IFLA_GSO_IPV4_MAX_SIZE,
 	IFLA_GRO_IPV4_MAX_SIZE,
 	IFLA_DPLL_PIN,
+	IFLA_MAX_PACING_OFFLOAD_HORIZON,
 	__IFLA_MAX
 };
 
-- 
cgit v1.2.3


From 107525833bcedb9d7c2c6a21abb8b9747410f364 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 4 Oct 2024 12:13:34 +0200
Subject: tools: Sync if_link.h uapi tooling header

Sync if_link uapi header to the latest version as we need the refresher
in tooling for netkit device. Given it's been a while since the last sync
and the diff is fairly big, it has been done as its own commit.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/r/20241004101335.117711-4-daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/include/uapi/linux/if_link.h | 553 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 552 insertions(+), 1 deletion(-)

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

diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index f0d71b2a3f1e..2acc7687e017 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -461,6 +461,286 @@ enum in6_addr_gen_mode {
 
 /* Bridge section */
 
+/**
+ * DOC: Bridge enum definition
+ *
+ * Please *note* that the timer values in the following section are expected
+ * in clock_t format, which is seconds multiplied by USER_HZ (generally
+ * defined as 100).
+ *
+ * @IFLA_BR_FORWARD_DELAY
+ *   The bridge forwarding delay is the time spent in LISTENING state
+ *   (before moving to LEARNING) and in LEARNING state (before moving
+ *   to FORWARDING). Only relevant if STP is enabled.
+ *
+ *   The valid values are between (2 * USER_HZ) and (30 * USER_HZ).
+ *   The default value is (15 * USER_HZ).
+ *
+ * @IFLA_BR_HELLO_TIME
+ *   The time between hello packets sent by the bridge, when it is a root
+ *   bridge or a designated bridge. Only relevant if STP is enabled.
+ *
+ *   The valid values are between (1 * USER_HZ) and (10 * USER_HZ).
+ *   The default value is (2 * USER_HZ).
+ *
+ * @IFLA_BR_MAX_AGE
+ *   The hello packet timeout is the time until another bridge in the
+ *   spanning tree is assumed to be dead, after reception of its last hello
+ *   message. Only relevant if STP is enabled.
+ *
+ *   The valid values are between (6 * USER_HZ) and (40 * USER_HZ).
+ *   The default value is (20 * USER_HZ).
+ *
+ * @IFLA_BR_AGEING_TIME
+ *   Configure the bridge's FDB entries aging time. It is the time a MAC
+ *   address will be kept in the FDB after a packet has been received from
+ *   that address. After this time has passed, entries are cleaned up.
+ *   Allow values outside the 802.1 standard specification for special cases:
+ *
+ *     * 0 - entry never ages (all permanent)
+ *     * 1 - entry disappears (no persistence)
+ *
+ *   The default value is (300 * USER_HZ).
+ *
+ * @IFLA_BR_STP_STATE
+ *   Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off
+ *   (*IFLA_BR_STP_STATE* == 0) for this bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_PRIORITY
+ *   Set this bridge's spanning tree priority, used during STP root bridge
+ *   election.
+ *
+ *   The valid values are between 0 and 65535.
+ *
+ * @IFLA_BR_VLAN_FILTERING
+ *   Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off
+ *   (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not
+ *   consider the VLAN tag when handling packets.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_PROTOCOL
+ *   Set the protocol used for VLAN filtering.
+ *
+ *   The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value
+ *   is 0x8100(802.1Q).
+ *
+ * @IFLA_BR_GROUP_FWD_MASK
+ *   The group forwarding mask. This is the bitmask that is applied to
+ *   decide whether to forward incoming frames destined to link-local
+ *   addresses (of the form 01:80:C2:00:00:0X).
+ *
+ *   The default value is 0, which means the bridge does not forward any
+ *   link-local frames coming on this port.
+ *
+ * @IFLA_BR_ROOT_ID
+ *   The bridge root id, read only.
+ *
+ * @IFLA_BR_BRIDGE_ID
+ *   The bridge id, read only.
+ *
+ * @IFLA_BR_ROOT_PORT
+ *   The bridge root port, read only.
+ *
+ * @IFLA_BR_ROOT_PATH_COST
+ *   The bridge root path cost, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE
+ *   The bridge topology change, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED
+ *   The bridge topology change detected, read only.
+ *
+ * @IFLA_BR_HELLO_TIMER
+ *   The bridge hello timer, read only.
+ *
+ * @IFLA_BR_TCN_TIMER
+ *   The bridge tcn timer, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_TIMER
+ *   The bridge topology change timer, read only.
+ *
+ * @IFLA_BR_GC_TIMER
+ *   The bridge gc timer, read only.
+ *
+ * @IFLA_BR_GROUP_ADDR
+ *   Set the MAC address of the multicast group this bridge uses for STP.
+ *   The address must be a link-local address in standard Ethernet MAC address
+ *   format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f].
+ *
+ *   The default value is 0.
+ *
+ * @IFLA_BR_FDB_FLUSH
+ *   Flush bridge's fdb dynamic entries.
+ *
+ * @IFLA_BR_MCAST_ROUTER
+ *   Set bridge's multicast router if IGMP snooping is enabled.
+ *   The valid values are:
+ *
+ *     * 0 - disabled.
+ *     * 1 - automatic (queried).
+ *     * 2 - permanently enabled.
+ *
+ *   The default value is 1.
+ *
+ * @IFLA_BR_MCAST_SNOOPING
+ *   Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off
+ *   (*IFLA_BR_MCAST_SNOOPING* == 0).
+ *
+ *   The default value is 1.
+ *
+ * @IFLA_BR_MCAST_QUERY_USE_IFADDR
+ *   If enabled use the bridge's own IP address as source address for IGMP
+ *   queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0
+ *   (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0).
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_QUERIER
+ *   Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable
+ *   (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast
+ *   queries by the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_HASH_ELASTICITY
+ *   Set multicast database hash elasticity, It is the maximum chain length in
+ *   the multicast hash table. This attribute is *deprecated* and the value
+ *   is always 16.
+ *
+ * @IFLA_BR_MCAST_HASH_MAX
+ *   Set maximum size of the multicast hash table
+ *
+ *   The default value is 4096, the value must be a power of 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_CNT
+ *   The Last Member Query Count is the number of Group-Specific Queries
+ *   sent before the router assumes there are no local members. The Last
+ *   Member Query Count is also the number of Group-and-Source-Specific
+ *   Queries sent before the router assumes there are no listeners for a
+ *   particular source.
+ *
+ *   The default value is 2.
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_CNT
+ *   The Startup Query Count is the number of Queries sent out on startup,
+ *   separated by the Startup Query Interval.
+ *
+ *   The default value is 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_INTVL
+ *   The Last Member Query Interval is the Max Response Time inserted into
+ *   Group-Specific Queries sent in response to Leave Group messages, and
+ *   is also the amount of time between Group-Specific Query messages.
+ *
+ *   The default value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_MEMBERSHIP_INTVL
+ *   The interval after which the bridge will leave a group, if no membership
+ *   reports for this group are received.
+ *
+ *   The default value is (260 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERIER_INTVL
+ *   The interval between queries sent by other routers. if no queries are
+ *   seen after this delay has passed, the bridge will start to send its own
+ *   queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled).
+ *
+ *   The default value is (255 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_INTVL
+ *   The Query Interval is the interval between General Queries sent by
+ *   the Querier.
+ *
+ *   The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL
+ *   The Max Response Time used to calculate the Max Resp Code inserted
+ *   into the periodic General Queries.
+ *
+ *   The default value is (10 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL
+ *   The interval between queries in the startup phase.
+ *
+ *   The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_NF_CALL_IPTABLES
+ *   Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0)
+ *   iptables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_IP6TABLES
+ *   Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0)
+ *   ip6tables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_ARPTABLES
+ *   Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0)
+ *   arptables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_DEFAULT_PVID
+ *   VLAN ID applied to untagged and priority-tagged incoming packets.
+ *
+ *   The default value is 1. Setting to the special value 0 makes all ports of
+ *   this bridge not have a PVID by default, which means that they will
+ *   not accept VLAN-untagged traffic.
+ *
+ * @IFLA_BR_PAD
+ *   Bridge attribute padding type for netlink message.
+ *
+ * @IFLA_BR_VLAN_STATS_ENABLED
+ *   Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable
+ *   (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_STATS_ENABLED
+ *   Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable
+ *   (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats
+ *   accounting.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_IGMP_VERSION
+ *   Set the IGMP version.
+ *
+ *   The valid values are 2 and 3. The default value is 2.
+ *
+ * @IFLA_BR_MCAST_MLD_VERSION
+ *   Set the MLD version.
+ *
+ *   The valid values are 1 and 2. The default value is 1.
+ *
+ * @IFLA_BR_VLAN_STATS_PER_PORT
+ *   Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable
+ *   (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting.
+ *   Can be changed only when there are no port VLANs configured.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MULTI_BOOLOPT
+ *   The multi_boolopt is used to control new boolean options to avoid adding
+ *   new netlink attributes. You can look at ``enum br_boolopt_id`` for those
+ *   options.
+ *
+ * @IFLA_BR_MCAST_QUERIER_STATE
+ *   Bridge mcast querier states, read only.
+ *
+ * @IFLA_BR_FDB_N_LEARNED
+ *   The number of dynamically learned FDB entries for the current bridge,
+ *   read only.
+ *
+ * @IFLA_BR_FDB_MAX_LEARNED
+ *   Set the number of max dynamically learned FDB entries for the current
+ *   bridge.
+ */
 enum {
 	IFLA_BR_UNSPEC,
 	IFLA_BR_FORWARD_DELAY,
@@ -510,6 +790,8 @@ enum {
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
 	IFLA_BR_MCAST_QUERIER_STATE,
+	IFLA_BR_FDB_N_LEARNED,
+	IFLA_BR_FDB_MAX_LEARNED,
 	__IFLA_BR_MAX,
 };
 
@@ -520,11 +802,252 @@ struct ifla_bridge_id {
 	__u8	addr[6]; /* ETH_ALEN */
 };
 
+/**
+ * DOC: Bridge mode enum definition
+ *
+ * @BRIDGE_MODE_HAIRPIN
+ *   Controls whether traffic may be sent back out of the port on which it
+ *   was received. This option is also called reflective relay mode, and is
+ *   used to support basic VEPA (Virtual Ethernet Port Aggregator)
+ *   capabilities. By default, this flag is turned off and the bridge will
+ *   not forward traffic back out of the receiving port.
+ */
 enum {
 	BRIDGE_MODE_UNSPEC,
 	BRIDGE_MODE_HAIRPIN,
 };
 
+/**
+ * DOC: Bridge port enum definition
+ *
+ * @IFLA_BRPORT_STATE
+ *   The operation state of the port. Here are the valid values.
+ *
+ *     * 0 - port is in STP *DISABLED* state. Make this port completely
+ *       inactive for STP. This is also called BPDU filter and could be used
+ *       to disable STP on an untrusted port, like a leaf virtual device.
+ *       The traffic forwarding is also stopped on this port.
+ *     * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled
+ *       on the bridge. In this state the port listens for STP BPDUs and
+ *       drops all other traffic frames.
+ *     * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on
+ *       the bridge. In this state the port will accept traffic only for the
+ *       purpose of updating MAC address tables.
+ *     * 3 - port is in STP *FORWARDING* state. Port is fully active.
+ *     * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on
+ *       the bridge. This state is used during the STP election process.
+ *       In this state, port will only process STP BPDUs.
+ *
+ * @IFLA_BRPORT_PRIORITY
+ *   The STP port priority. The valid values are between 0 and 255.
+ *
+ * @IFLA_BRPORT_COST
+ *   The STP path cost of the port. The valid values are between 1 and 65535.
+ *
+ * @IFLA_BRPORT_MODE
+ *   Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details.
+ *
+ * @IFLA_BRPORT_GUARD
+ *   Controls whether STP BPDUs will be processed by the bridge port. By
+ *   default, the flag is turned off to allow BPDU processing. Turning this
+ *   flag on will disable the bridge port if a STP BPDU packet is received.
+ *
+ *   If the bridge has Spanning Tree enabled, hostile devices on the network
+ *   may send BPDU on a port and cause network failure. Setting *guard on*
+ *   will detect and stop this by disabling the port. The port will be
+ *   restarted if the link is brought down, or removed and reattached.
+ *
+ * @IFLA_BRPORT_PROTECT
+ *   Controls whether a given port is allowed to become a root port or not.
+ *   Only used when STP is enabled on the bridge. By default the flag is off.
+ *
+ *   This feature is also called root port guard. If BPDU is received from a
+ *   leaf (edge) port, it should not be elected as root port. This could
+ *   be used if using STP on a bridge and the downstream bridges are not fully
+ *   trusted; this prevents a hostile guest from rerouting traffic.
+ *
+ * @IFLA_BRPORT_FAST_LEAVE
+ *   This flag allows the bridge to immediately stop multicast traffic
+ *   forwarding on a port that receives an IGMP Leave message. It is only used
+ *   when IGMP snooping is enabled on the bridge. By default the flag is off.
+ *
+ * @IFLA_BRPORT_LEARNING
+ *   Controls whether a given port will learn *source* MAC addresses from
+ *   received traffic or not. Also controls whether dynamic FDB entries
+ *   (which can also be added by software) will be refreshed by incoming
+ *   traffic. By default this flag is on.
+ *
+ * @IFLA_BRPORT_UNICAST_FLOOD
+ *   Controls whether unicast traffic for which there is no FDB entry will
+ *   be flooded towards this port. By default this flag is on.
+ *
+ * @IFLA_BRPORT_PROXYARP
+ *   Enable proxy ARP on this port.
+ *
+ * @IFLA_BRPORT_LEARNING_SYNC
+ *   Controls whether a given port will sync MAC addresses learned on device
+ *   port to bridge FDB.
+ *
+ * @IFLA_BRPORT_PROXYARP_WIFI
+ *   Enable proxy ARP on this port which meets extended requirements by
+ *   IEEE 802.11 and Hotspot 2.0 specifications.
+ *
+ * @IFLA_BRPORT_ROOT_ID
+ *
+ * @IFLA_BRPORT_BRIDGE_ID
+ *
+ * @IFLA_BRPORT_DESIGNATED_PORT
+ *
+ * @IFLA_BRPORT_DESIGNATED_COST
+ *
+ * @IFLA_BRPORT_ID
+ *
+ * @IFLA_BRPORT_NO
+ *
+ * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK
+ *
+ * @IFLA_BRPORT_CONFIG_PENDING
+ *
+ * @IFLA_BRPORT_MESSAGE_AGE_TIMER
+ *
+ * @IFLA_BRPORT_FORWARD_DELAY_TIMER
+ *
+ * @IFLA_BRPORT_HOLD_TIMER
+ *
+ * @IFLA_BRPORT_FLUSH
+ *   Flush bridge ports' fdb dynamic entries.
+ *
+ * @IFLA_BRPORT_MULTICAST_ROUTER
+ *   Configure the port's multicast router presence. A port with
+ *   a multicast router will receive all multicast traffic.
+ *   The valid values are:
+ *
+ *     * 0 disable multicast routers on this port
+ *     * 1 let the system detect the presence of routers (default)
+ *     * 2 permanently enable multicast traffic forwarding on this port
+ *     * 3 enable multicast routers temporarily on this port, not depending
+ *         on incoming queries.
+ *
+ * @IFLA_BRPORT_PAD
+ *
+ * @IFLA_BRPORT_MCAST_FLOOD
+ *   Controls whether a given port will flood multicast traffic for which
+ *   there is no MDB entry. By default this flag is on.
+ *
+ * @IFLA_BRPORT_MCAST_TO_UCAST
+ *   Controls whether a given port will replicate packets using unicast
+ *   instead of multicast. By default this flag is off.
+ *
+ *   This is done by copying the packet per host and changing the multicast
+ *   destination MAC to a unicast one accordingly.
+ *
+ *   *mcast_to_unicast* works on top of the multicast snooping feature of the
+ *   bridge. Which means unicast copies are only delivered to hosts which
+ *   are interested in unicast and signaled this via IGMP/MLD reports previously.
+ *
+ *   This feature is intended for interface types which have a more reliable
+ *   and/or efficient way to deliver unicast packets than broadcast ones
+ *   (e.g. WiFi).
+ *
+ *   However, it should only be enabled on interfaces where no IGMPv2/MLDv1
+ *   report suppression takes place. IGMP/MLD report suppression issue is
+ *   usually overcome by the network daemon (supplicant) enabling AP isolation
+ *   and by that separating all STAs.
+ *
+ *   Delivery of STA-to-STA IP multicast is made possible again by enabling
+ *   and utilizing the bridge hairpin mode, which considers the incoming port
+ *   as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option).
+ *   Hairpin mode is performed after multicast snooping, therefore leading
+ *   to only deliver reports to STAs running a multicast router.
+ *
+ * @IFLA_BRPORT_VLAN_TUNNEL
+ *   Controls whether vlan to tunnel mapping is enabled on the port.
+ *   By default this flag is off.
+ *
+ * @IFLA_BRPORT_BCAST_FLOOD
+ *   Controls flooding of broadcast traffic on the given port. By default
+ *   this flag is on.
+ *
+ * @IFLA_BRPORT_GROUP_FWD_MASK
+ *   Set the group forward mask. This is a bitmask that is applied to
+ *   decide whether to forward incoming frames destined to link-local
+ *   addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults
+ *   to 0, which means the bridge does not forward any link-local frames
+ *   coming on this port).
+ *
+ * @IFLA_BRPORT_NEIGH_SUPPRESS
+ *   Controls whether neighbor discovery (arp and nd) proxy and suppression
+ *   is enabled on the port. By default this flag is off.
+ *
+ * @IFLA_BRPORT_ISOLATED
+ *   Controls whether a given port will be isolated, which means it will be
+ *   able to communicate with non-isolated ports only. By default this
+ *   flag is off.
+ *
+ * @IFLA_BRPORT_BACKUP_PORT
+ *   Set a backup port. If the port loses carrier all traffic will be
+ *   redirected to the configured backup port. Set the value to 0 to disable
+ *   it.
+ *
+ * @IFLA_BRPORT_MRP_RING_OPEN
+ *
+ * @IFLA_BRPORT_MRP_IN_OPEN
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT
+ *   The number of per-port EHT hosts limit. The default value is 512.
+ *   Setting to 0 is not allowed.
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT
+ *   The current number of tracked hosts, read only.
+ *
+ * @IFLA_BRPORT_LOCKED
+ *   Controls whether a port will be locked, meaning that hosts behind the
+ *   port will not be able to communicate through the port unless an FDB
+ *   entry with the unit's MAC address is in the FDB. The common use case is
+ *   that hosts are allowed access through authentication with the IEEE 802.1X
+ *   protocol or based on whitelists. By default this flag is off.
+ *
+ *   Please note that secure 802.1X deployments should always use the
+ *   *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its
+ *   FDB based on link-local (EAPOL) traffic received on the port.
+ *
+ * @IFLA_BRPORT_MAB
+ *   Controls whether a port will use MAC Authentication Bypass (MAB), a
+ *   technique through which select MAC addresses may be allowed on a locked
+ *   port, without using 802.1X authentication. Packets with an unknown source
+ *   MAC address generates a "locked" FDB entry on the incoming bridge port.
+ *   The common use case is for user space to react to these bridge FDB
+ *   notifications and optionally replace the locked FDB entry with a normal
+ *   one, allowing traffic to pass for whitelisted MAC addresses.
+ *
+ *   Setting this flag also requires *IFLA_BRPORT_LOCKED* and
+ *   *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized
+ *   data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic
+ *   FDB entries installed by user space (as replacements for the locked FDB
+ *   entries) to be refreshed and/or aged out.
+ *
+ * @IFLA_BRPORT_MCAST_N_GROUPS
+ *
+ * @IFLA_BRPORT_MCAST_MAX_GROUPS
+ *   Sets the maximum number of MDB entries that can be registered for a
+ *   given port. Attempts to register more MDB entries at the port than this
+ *   limit allows will be rejected, whether they are done through netlink
+ *   (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a
+ *   limit of 0 disables the limit. The default value is 0.
+ *
+ * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS
+ *   Controls whether neighbor discovery (arp and nd) proxy and suppression is
+ *   enabled for a given port. By default this flag is off.
+ *
+ *   Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS*
+ *   is enabled for a given port.
+ *
+ * @IFLA_BRPORT_BACKUP_NHID
+ *   The FDB nexthop object ID to attach to packets being redirected to a
+ *   backup port that has VLAN tunnel mapping enabled (via the
+ *   *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has
+ *   the effect of not attaching any ID.
+ */
 enum {
 	IFLA_BRPORT_UNSPEC,
 	IFLA_BRPORT_STATE,	/* Spanning tree state     */
@@ -769,6 +1292,19 @@ enum netkit_mode {
 	NETKIT_L3,
 };
 
+/* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to
+ * the BPF program if attached. This also means the latter can
+ * consume the two fields if they were populated earlier.
+ *
+ * NETKIT_SCRUB_DEFAULT zeroes skb->{mark,priority} fields before
+ * invoking the attached BPF program when the peer device resides
+ * in a different network namespace. This is the default behavior.
+ */
+enum netkit_scrub {
+	NETKIT_SCRUB_NONE,
+	NETKIT_SCRUB_DEFAULT,
+};
+
 enum {
 	IFLA_NETKIT_UNSPEC,
 	IFLA_NETKIT_PEER_INFO,
@@ -776,6 +1312,8 @@ enum {
 	IFLA_NETKIT_POLICY,
 	IFLA_NETKIT_PEER_POLICY,
 	IFLA_NETKIT_MODE,
+	IFLA_NETKIT_SCRUB,
+	IFLA_NETKIT_PEER_SCRUB,
 	__IFLA_NETKIT_MAX,
 };
 #define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
@@ -854,6 +1392,7 @@ enum {
 	IFLA_VXLAN_DF,
 	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
 	IFLA_VXLAN_LOCALBYPASS,
+	IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -871,6 +1410,13 @@ enum ifla_vxlan_df {
 	VXLAN_DF_MAX = __VXLAN_DF_END - 1,
 };
 
+enum ifla_vxlan_label_policy {
+	VXLAN_LABEL_FIXED = 0,
+	VXLAN_LABEL_INHERIT = 1,
+	__VXLAN_LABEL_END,
+	VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1,
+};
+
 /* GENEVE section */
 enum {
 	IFLA_GENEVE_UNSPEC,
@@ -935,6 +1481,8 @@ enum {
 	IFLA_GTP_ROLE,
 	IFLA_GTP_CREATE_SOCKETS,
 	IFLA_GTP_RESTART_COUNT,
+	IFLA_GTP_LOCAL,
+	IFLA_GTP_LOCAL6,
 	__IFLA_GTP_MAX,
 };
 #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
@@ -1240,6 +1788,7 @@ enum {
 	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
 					 * HSR. For example PRP.
 					 */
+	IFLA_HSR_INTERLINK,		/* HSR interlink network device */
 	__IFLA_HSR_MAX,
 };
 
@@ -1417,7 +1966,9 @@ enum {
 
 enum {
 	IFLA_DSA_UNSPEC,
-	IFLA_DSA_MASTER,
+	IFLA_DSA_CONDUIT,
+	/* Deprecated, use IFLA_DSA_CONDUIT instead */
+	IFLA_DSA_MASTER = IFLA_DSA_CONDUIT,
 	__IFLA_DSA_MAX,
 };
 
-- 
cgit v1.2.3


From 5bd48a3a14df4b3ee1be0757efcc0f40d4f57b35 Mon Sep 17 00:00:00 2001
From: Matteo Croce <teknoraver@meta.com>
Date: Thu, 10 Oct 2024 04:56:52 +0100
Subject: bpf: fix argument type in bpf_loop documentation

The `index` argument to bpf_loop() is threaded as an u64.
This lead in a subtle verifier denial where clang cloned the argument
in another register[1].

[1] https://github.com/systemd/systemd/pull/34650#issuecomment-2401092895

Signed-off-by: Matteo Croce <teknoraver@meta.com>
Link: https://lore.kernel.org/r/20241010035652.17830-1-technoboy85@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       | 2 +-
 kernel/bpf/verifier.c          | 2 +-
 tools/include/uapi/linux/bpf.h | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

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

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8ab4d8184b9d..874af0186fe8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5371,7 +5371,7 @@ union bpf_attr {
  *		Currently, the **flags** must be 0. Currently, nr_loops is
  *		limited to 1 << 23 (~8 million) loops.
  *
- *		long (\*callback_fn)(u32 index, void \*ctx);
+ *		long (\*callback_fn)(u64 index, void \*ctx);
  *
  *		where **index** is the current index in the loop. The index
  *		is zero-indexed.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7d9b38ffd220..cfc62e0776bf 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9917,7 +9917,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env,
 {
 	/* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx,
 	 *	    u64 flags);
-	 * callback_fn(u32 index, void *callback_ctx);
+	 * callback_fn(u64 index, void *callback_ctx);
 	 */
 	callee->regs[BPF_REG_1].type = SCALAR_VALUE;
 	callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3];
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7610883c8191..5937c39069ba 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5371,7 +5371,7 @@ union bpf_attr {
  *		Currently, the **flags** must be 0. Currently, nr_loops is
  *		limited to 1 << 23 (~8 million) loops.
  *
- *		long (\*callback_fn)(u32 index, void \*ctx);
+ *		long (\*callback_fn)(u64 index, void \*ctx);
  *
  *		where **index** is the current index in the loop. The index
  *		is zero-indexed.
-- 
cgit v1.2.3


From c6ca31981b545ad3081007b6aa88b6aab1b0cece Mon Sep 17 00:00:00 2001
From: Martin Kelly <martin.kelly@crowdstrike.com>
Date: Thu, 10 Oct 2024 12:33:01 -0700
Subject: bpf: Update bpf_override_return() comment

The documentation says CONFIG_FUNCTION_ERROR_INJECTION is supported only
on x86. This was presumably true at the time of writing, but it's now
supported on many other architectures too. Drop this statement, since
it's not correct anymore and it fits better in other documentation
anyway.

Signed-off-by: Martin Kelly <martin.kelly@crowdstrike.com>
Link: https://lore.kernel.org/r/20241010193301.995909-1-martin.kelly@crowdstrike.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       | 4 ----
 tools/include/uapi/linux/bpf.h | 4 ----
 2 files changed, 8 deletions(-)

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

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 874af0186fe8..627c4195f04f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3103,10 +3103,6 @@ union bpf_attr {
  * 		with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration
  * 		option, and in this case it only works on functions tagged with
  * 		**ALLOW_ERROR_INJECTION** in the kernel code.
- *
- * 		Also, the helper is only available for the architectures having
- * 		the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing,
- * 		x86 architecture is the only one to support this feature.
  * 	Return
  * 		0
  *
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 5937c39069ba..0e49ce2981a0 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3103,10 +3103,6 @@ union bpf_attr {
  * 		with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration
  * 		option, and in this case it only works on functions tagged with
  * 		**ALLOW_ERROR_INJECTION** in the kernel code.
- *
- * 		Also, the helper is only available for the architectures having
- * 		the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing,
- * 		x86 architecture is the only one to support this feature.
  * 	Return
  * 		0
  *
-- 
cgit v1.2.3


From 516010460011ae74ac3b7383cf90ed27e2711cd6 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 11 Oct 2024 18:44:57 +0000
Subject: netdev-genl: Dump napi_defer_hard_irqs

Support dumping defer_hard_irqs for a NAPI ID.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20241011184527.16393-3-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 8 ++++++++
 include/uapi/linux/netdev.h             | 1 +
 net/core/netdev-genl.c                  | 6 ++++++
 tools/include/uapi/linux/netdev.h       | 1 +
 4 files changed, 16 insertions(+)

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

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 08412c279297..585e87ec3c16 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -248,6 +248,13 @@ attribute-sets:
              threaded mode. If NAPI is not in threaded mode (i.e. uses normal
              softirq context), the attribute will be absent.
         type: u32
+      -
+        name: defer-hard-irqs
+        doc: The number of consecutive empty polls before IRQ deferral ends
+             and hardware IRQs are re-enabled.
+        type: u32
+        checks:
+          max: s32-max
   -
     name: queue
     attributes:
@@ -636,6 +643,7 @@ operations:
             - ifindex
             - irq
             - pid
+            - defer-hard-irqs
       dump:
         request:
           attributes:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 7c308f04e7a0..13dc0b027e86 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -122,6 +122,7 @@ enum {
 	NETDEV_A_NAPI_ID,
 	NETDEV_A_NAPI_IRQ,
 	NETDEV_A_NAPI_PID,
+	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 358cba248796..f98e5d1d0d21 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -161,6 +161,7 @@ static int
 netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 			const struct genl_info *info)
 {
+	u32 napi_defer_hard_irqs;
 	void *hdr;
 	pid_t pid;
 
@@ -189,6 +190,11 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 			goto nla_put_failure;
 	}
 
+	napi_defer_hard_irqs = napi_get_defer_hard_irqs(napi);
+	if (nla_put_s32(rsp, NETDEV_A_NAPI_DEFER_HARD_IRQS,
+			napi_defer_hard_irqs))
+		goto nla_put_failure;
+
 	genlmsg_end(rsp, hdr);
 
 	return 0;
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 7c308f04e7a0..13dc0b027e86 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -122,6 +122,7 @@ enum {
 	NETDEV_A_NAPI_ID,
 	NETDEV_A_NAPI_IRQ,
 	NETDEV_A_NAPI_PID,
+	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
-- 
cgit v1.2.3


From 0137891e74576f77a7901718dc0ce08ca074ae74 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 11 Oct 2024 18:44:59 +0000
Subject: netdev-genl: Dump gro_flush_timeout

Support dumping gro_flush_timeout for a NAPI ID.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20241011184527.16393-5-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 9 +++++++++
 include/uapi/linux/netdev.h             | 1 +
 net/core/netdev-genl.c                  | 6 ++++++
 tools/include/uapi/linux/netdev.h       | 1 +
 4 files changed, 17 insertions(+)

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

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 585e87ec3c16..7b47454c51dd 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -255,6 +255,14 @@ attribute-sets:
         type: u32
         checks:
           max: s32-max
+      -
+        name: gro-flush-timeout
+        doc: The timeout, in nanoseconds, of when to trigger the NAPI watchdog
+             timer which schedules NAPI processing. Additionally, a non-zero
+             value will also prevent GRO from flushing recent super-frames at
+             the end of a NAPI cycle. This may add receive latency in exchange
+             for reducing the number of frames processed by the network stack.
+        type: uint
   -
     name: queue
     attributes:
@@ -644,6 +652,7 @@ operations:
             - irq
             - pid
             - defer-hard-irqs
+            - gro-flush-timeout
       dump:
         request:
           attributes:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 13dc0b027e86..cacd33359c76 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -123,6 +123,7 @@ enum {
 	NETDEV_A_NAPI_IRQ,
 	NETDEV_A_NAPI_PID,
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
+	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index f98e5d1d0d21..ac19f2e6cfbe 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -161,6 +161,7 @@ static int
 netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 			const struct genl_info *info)
 {
+	unsigned long gro_flush_timeout;
 	u32 napi_defer_hard_irqs;
 	void *hdr;
 	pid_t pid;
@@ -195,6 +196,11 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 			napi_defer_hard_irqs))
 		goto nla_put_failure;
 
+	gro_flush_timeout = napi_get_gro_flush_timeout(napi);
+	if (nla_put_uint(rsp, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
+			 gro_flush_timeout))
+		goto nla_put_failure;
+
 	genlmsg_end(rsp, hdr);
 
 	return 0;
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 13dc0b027e86..cacd33359c76 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -123,6 +123,7 @@ enum {
 	NETDEV_A_NAPI_IRQ,
 	NETDEV_A_NAPI_PID,
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
+	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
-- 
cgit v1.2.3


From 1287c1ae0fc227e5acef11a539eb4e75646e31c7 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 11 Oct 2024 18:45:01 +0000
Subject: netdev-genl: Support setting per-NAPI config values

Add support to set per-NAPI defer_hard_irqs and gro_flush_timeout.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20241011184527.16393-7-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 11 ++++++++
 include/uapi/linux/netdev.h             |  1 +
 net/core/netdev-genl-gen.c              | 18 +++++++++++++
 net/core/netdev-genl-gen.h              |  1 +
 net/core/netdev-genl.c                  | 45 +++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/netdev.h       |  1 +
 6 files changed, 77 insertions(+)

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

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 7b47454c51dd..f9cb97d6106c 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -693,6 +693,17 @@ operations:
         reply:
           attributes:
             - id
+    -
+      name: napi-set
+      doc: Set configurable NAPI instance settings.
+      attribute-set: napi
+      flags: [ admin-perm ]
+      do:
+        request:
+          attributes:
+            - id
+            - defer-hard-irqs
+            - gro-flush-timeout
 
 kernel-family:
   headers: [ "linux/list.h"]
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index cacd33359c76..e3ebb49f60d2 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -201,6 +201,7 @@ enum {
 	NETDEV_CMD_NAPI_GET,
 	NETDEV_CMD_QSTATS_GET,
 	NETDEV_CMD_BIND_RX,
+	NETDEV_CMD_NAPI_SET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index b28424ae06d5..e197bd84997c 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -22,6 +22,10 @@ static const struct netlink_range_validation netdev_a_page_pool_ifindex_range =
 	.max	= 2147483647ULL,
 };
 
+static const struct netlink_range_validation netdev_a_napi_defer_hard_irqs_range = {
+	.max	= 2147483647ULL,
+};
+
 /* Common nested types */
 const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1] = {
 	[NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range),
@@ -87,6 +91,13 @@ static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1]
 	[NETDEV_A_DMABUF_QUEUES] = NLA_POLICY_NESTED(netdev_queue_id_nl_policy),
 };
 
+/* NETDEV_CMD_NAPI_SET - do */
+static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT + 1] = {
+	[NETDEV_A_NAPI_ID] = { .type = NLA_U32, },
+	[NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range),
+	[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, },
+};
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -171,6 +182,13 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.maxattr	= NETDEV_A_DMABUF_FD,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
+	{
+		.cmd		= NETDEV_CMD_NAPI_SET,
+		.doit		= netdev_nl_napi_set_doit,
+		.policy		= netdev_napi_set_nl_policy,
+		.maxattr	= NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 8cda334fd042..e09dd7539ff2 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -33,6 +33,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
 				struct netlink_callback *cb);
 int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info);
 
 enum {
 	NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index ac19f2e6cfbe..b49c3b4e5fbe 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -303,6 +303,51 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return err;
 }
 
+static int
+netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
+{
+	u64 gro_flush_timeout = 0;
+	u32 defer = 0;
+
+	if (info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]) {
+		defer = nla_get_u32(info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]);
+		napi_set_defer_hard_irqs(napi, defer);
+	}
+
+	if (info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]) {
+		gro_flush_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]);
+		napi_set_gro_flush_timeout(napi, gro_flush_timeout);
+	}
+
+	return 0;
+}
+
+int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct napi_struct *napi;
+	unsigned int napi_id;
+	int err;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID))
+		return -EINVAL;
+
+	napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]);
+
+	rtnl_lock();
+
+	napi = napi_by_id(napi_id);
+	if (napi) {
+		err = netdev_nl_napi_set_config(napi, info);
+	} else {
+		NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]);
+		err = -ENOENT;
+	}
+
+	rtnl_unlock();
+
+	return err;
+}
+
 static int
 netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 			 u32 q_idx, u32 q_type, const struct genl_info *info)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index cacd33359c76..e3ebb49f60d2 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -201,6 +201,7 @@ enum {
 	NETDEV_CMD_NAPI_GET,
 	NETDEV_CMD_QSTATS_GET,
 	NETDEV_CMD_BIND_RX,
+	NETDEV_CMD_NAPI_SET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
-- 
cgit v1.2.3


From ab8aaab874c4aa378e76d0a55ce6e0fad6e042a2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 11 Oct 2024 15:20:17 -0300
Subject: tools headers UAPI: Sync linux/const.h with the kernel headers

To pick up the changes in:

  947697c6f0f75f98 ("uapi: Define GENMASK_U128")

That causes no changes in tooling, just addresses this perf build
warning:

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

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.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: Yury Norov <yury.norov@gmail.com>
Link: https://lore.kernel.org/lkml/ZwltGNJwujKu1Fgn@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/const.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

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

diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
index a429381e7ca5..e16be0d37746 100644
--- a/tools/include/uapi/linux/const.h
+++ b/tools/include/uapi/linux/const.h
@@ -28,6 +28,23 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __BIT128() would not work in the asm code, as it shifts an
+ * 'unsigned __init128' data type as direct representation of
+ * 128 bit constants is not supported in the gcc compiler, as
+ * they get silently truncated.
+ *
+ * TODO: Please revisit this implementation when gcc compiler
+ * starts representing 128 bit constants directly like long
+ * and unsigned long etc. Subsequently drop the comment for
+ * GENMASK_U128() which would then start supporting asm code.
+ */
+#define _BIT128(x)	((unsigned __int128)(1) << (x))
+#endif
+
 #define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
 #define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
 
-- 
cgit v1.2.3


From c2f803052bc7a7feb2e03befccc8e49b6ff1f5f5 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Thu, 24 Oct 2024 09:35:57 +0800
Subject: bpf: Add the missing BPF_LINK_TYPE invocation for sockmap

There is an out-of-bounds read in bpf_link_show_fdinfo() for the sockmap
link fd. Fix it by adding the missing BPF_LINK_TYPE invocation for
sockmap link

Also add comments for bpf_link_type to prevent missing updates in the
future.

Fixes: 699c23f02c65 ("bpf: Add bpf_link support for sk_msg and sk_skb progs")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20241024013558.1135167-2-houtao@huaweicloud.com
---
 include/linux/bpf_types.h      | 1 +
 include/uapi/linux/bpf.h       | 3 +++
 tools/include/uapi/linux/bpf.h | 3 +++
 3 files changed, 7 insertions(+)

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

diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 9f2a6b83b49e..fa78f49d4a9a 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -146,6 +146,7 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter)
 BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx)
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit)
+BPF_LINK_TYPE(BPF_LINK_TYPE_SOCKMAP, sockmap)
 #endif
 #ifdef CONFIG_PERF_EVENTS
 BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e8241b320c6d..4a939c90dc2e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1121,6 +1121,9 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[]
+ * in sync with the definitions below.
+ */
 enum bpf_link_type {
 	BPF_LINK_TYPE_UNSPEC = 0,
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e8241b320c6d..4a939c90dc2e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1121,6 +1121,9 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[]
+ * in sync with the definitions below.
+ */
 enum bpf_link_type {
 	BPF_LINK_TYPE_UNSPEC = 0,
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
-- 
cgit v1.2.3


From 21a3a3d015aeee2402d14b425197d70aa3bd0d91 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 28 Oct 2024 10:55:09 -0300
Subject: tools headers: Synchronize {uapi/}linux/bits.h with the kernel
 sources

To pick up the changes in this cset:

  947697c6f0f75f98 ("uapi: Define GENMASK_U128")

This addresses these perf build warnings:

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

Please see tools/include/uapi/README for further details.

Acked-by: Yury Norov <yury.norov@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.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>
Link: https://lore.kernel.org/lkml/Zx-ZVH7bHqtFn8Dv@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/bits.h      | 15 +++++++++++++++
 tools/include/uapi/linux/bits.h |  3 +++
 2 files changed, 18 insertions(+)

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

diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 0eb24d21aac2..60044b608817 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -36,4 +36,19 @@
 #define GENMASK_ULL(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
 
+#if !defined(__ASSEMBLY__)
+/*
+ * Missing asm support
+ *
+ * __GENMASK_U128() depends on _BIT128() which would not work
+ * in the asm code, as it shifts an 'unsigned __init128' data
+ * type instead of direct representation of 128 bit constants
+ * such as long and unsigned long. The fundamental problem is
+ * that a 128 bit constant will get silently truncated by the
+ * gcc compiler.
+ */
+#define GENMASK_U128(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l))
+#endif
+
 #endif	/* __LINUX_BITS_H */
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h
index 3c2a101986a3..5ee30f882736 100644
--- a/tools/include/uapi/linux/bits.h
+++ b/tools/include/uapi/linux/bits.h
@@ -12,4 +12,7 @@
         (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \
          (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
 
+#define __GENMASK_U128(h, l) \
+	((_BIT128((h)) << 1) - (_BIT128(l)))
+
 #endif /* _UAPI_LINUX_BITS_H */
-- 
cgit v1.2.3


From d920179b3d4842a0e27cae54fdddbe5ef3977e73 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 8 Nov 2024 14:45:34 +0100
Subject: bpf: Add support for uprobe multi 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 uprobe multi links.

Adding new BPF_TRACE_UPROBE_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>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20241108134544.480660-4-jolsa@kernel.org
---
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/syscall.c           |  9 +++++++--
 kernel/bpf/verifier.c          |  1 +
 kernel/trace/bpf_trace.c       | 36 +++++++++++++++++++++++++++---------
 tools/include/uapi/linux/bpf.h |  1 +
 tools/lib/bpf/libbpf.c         |  1 +
 6 files changed, 38 insertions(+), 11 deletions(-)

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

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f28b6527e815..4162afc6b5d0 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1116,6 +1116,7 @@ enum bpf_attach_type {
 	BPF_NETKIT_PRIMARY,
 	BPF_NETKIT_PEER,
 	BPF_TRACE_KPROBE_SESSION,
+	BPF_TRACE_UPROBE_SESSION,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8254b2973157..58190ca724a2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4103,10 +4103,14 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI &&
 		    attach_type != BPF_TRACE_UPROBE_MULTI)
 			return -EINVAL;
+		if (prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION &&
+		    attach_type != BPF_TRACE_UPROBE_SESSION)
+			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)
+		    attach_type != BPF_TRACE_UPROBE_MULTI &&
+		    attach_type != BPF_TRACE_UPROBE_SESSION)
 			return -EINVAL;
 		return 0;
 	case BPF_PROG_TYPE_SCHED_CLS:
@@ -5359,7 +5363,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		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)
+		else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI ||
+			 attr->link_create.attach_type == BPF_TRACE_UPROBE_SESSION)
 			ret = bpf_uprobe_multi_link_attach(attr, prog);
 		break;
 	default:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7d8ed377b35d..132fc172961f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -16027,6 +16027,7 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char
 	case BPF_PROG_TYPE_KPROBE:
 		switch (env->prog->expected_attach_type) {
 		case BPF_TRACE_KPROBE_SESSION:
+		case BPF_TRACE_UPROBE_SESSION:
 			range = retval_range(0, 1);
 			break;
 		default:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index db9e2792b42b..9c04b1364de2 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1581,6 +1581,17 @@ static inline bool is_kprobe_session(const struct bpf_prog *prog)
 	return prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION;
 }
 
+static inline bool is_uprobe_multi(const struct bpf_prog *prog)
+{
+	return prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI ||
+	       prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION;
+}
+
+static inline bool is_uprobe_session(const struct bpf_prog *prog)
+{
+	return prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION;
+}
+
 static const struct bpf_func_proto *
 kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1598,13 +1609,13 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_func_ip:
 		if (is_kprobe_multi(prog))
 			return &bpf_get_func_ip_proto_kprobe_multi;
-		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+		if (is_uprobe_multi(prog))
 			return &bpf_get_func_ip_proto_uprobe_multi;
 		return &bpf_get_func_ip_proto_kprobe;
 	case BPF_FUNC_get_attach_cookie:
 		if (is_kprobe_multi(prog))
 			return &bpf_get_attach_cookie_proto_kmulti;
-		if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI)
+		if (is_uprobe_multi(prog))
 			return &bpf_get_attach_cookie_proto_umulti;
 		return &bpf_get_attach_cookie_proto_trace;
 	default:
@@ -3096,6 +3107,7 @@ struct bpf_uprobe {
 	u64 cookie;
 	struct uprobe *uprobe;
 	struct uprobe_consumer consumer;
+	bool session;
 };
 
 struct bpf_uprobe_multi_link {
@@ -3267,9 +3279,13 @@ uprobe_multi_link_handler(struct uprobe_consumer *con, struct pt_regs *regs,
 			  __u64 *data)
 {
 	struct bpf_uprobe *uprobe;
+	int ret;
 
 	uprobe = container_of(con, struct bpf_uprobe, consumer);
-	return uprobe_prog_run(uprobe, instruction_pointer(regs), regs);
+	ret = uprobe_prog_run(uprobe, instruction_pointer(regs), regs);
+	if (uprobe->session)
+		return ret ? UPROBE_HANDLER_IGNORE : 0;
+	return 0;
 }
 
 static int
@@ -3279,7 +3295,8 @@ uprobe_multi_link_ret_handler(struct uprobe_consumer *con, unsigned long func, s
 	struct bpf_uprobe *uprobe;
 
 	uprobe = container_of(con, struct bpf_uprobe, consumer);
-	return uprobe_prog_run(uprobe, func, regs);
+	uprobe_prog_run(uprobe, func, regs);
+	return 0;
 }
 
 static u64 bpf_uprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
@@ -3318,7 +3335,7 @@ int bpf_uprobe_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_UPROBE_MULTI)
+	if (!is_uprobe_multi(prog))
 		return -EINVAL;
 
 	flags = attr->link_create.uprobe_multi.flags;
@@ -3394,11 +3411,12 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 
 		uprobes[i].link = link;
 
-		if (flags & BPF_F_UPROBE_MULTI_RETURN)
-			uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler;
-		else
+		if (!(flags & BPF_F_UPROBE_MULTI_RETURN))
 			uprobes[i].consumer.handler = uprobe_multi_link_handler;
-
+		if (flags & BPF_F_UPROBE_MULTI_RETURN || is_uprobe_session(prog))
+			uprobes[i].consumer.ret_handler = uprobe_multi_link_ret_handler;
+		if (is_uprobe_session(prog))
+			uprobes[i].session = true;
 		if (pid)
 			uprobes[i].consumer.filter = uprobe_multi_link_filter;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f28b6527e815..4162afc6b5d0 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1116,6 +1116,7 @@ enum bpf_attach_type {
 	BPF_NETKIT_PRIMARY,
 	BPF_NETKIT_PEER,
 	BPF_TRACE_KPROBE_SESSION,
+	BPF_TRACE_UPROBE_SESSION,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 711173acbcef..faac1c79840d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -133,6 +133,7 @@ static const char * const attach_type_name[] = {
 	[BPF_NETKIT_PRIMARY]		= "netkit_primary",
 	[BPF_NETKIT_PEER]		= "netkit_peer",
 	[BPF_TRACE_KPROBE_SESSION]	= "trace_kprobe_session",
+	[BPF_TRACE_UPROBE_SESSION]	= "trace_uprobe_session",
 };
 
 static const char * const link_type_name[] = {
-- 
cgit v1.2.3


From 5dc51ec86df6e2214d8398079c1e31736593ab53 Mon Sep 17 00:00:00 2001
From: Martin Karsten <mkarsten@uwaterloo.ca>
Date: Sat, 9 Nov 2024 05:02:31 +0000
Subject: net: Add napi_struct parameter irq_suspend_timeout

Add a per-NAPI IRQ suspension parameter, which can be get/set with
netdev-genl.

This patch doesn't change any behavior but prepares the code for other
changes in the following commits which use irq_suspend_timeout as a
timeout for IRQ suspension.

Signed-off-by: Martin Karsten <mkarsten@uwaterloo.ca>
Co-developed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://patch.msgid.link/20241109050245.191288-2-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml |  7 +++++++
 include/linux/netdevice.h               |  2 ++
 include/uapi/linux/netdev.h             |  1 +
 net/core/dev.c                          |  2 ++
 net/core/dev.h                          | 25 +++++++++++++++++++++++++
 net/core/netdev-genl-gen.c              |  5 +++--
 net/core/netdev-genl.c                  | 12 ++++++++++++
 tools/include/uapi/linux/netdev.h       |  1 +
 8 files changed, 53 insertions(+), 2 deletions(-)

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

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index f9cb97d6106c..cbb544bd6c84 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -263,6 +263,11 @@ attribute-sets:
              the end of a NAPI cycle. This may add receive latency in exchange
              for reducing the number of frames processed by the network stack.
         type: uint
+      -
+        name: irq-suspend-timeout
+        doc: The timeout, in nanoseconds, of how long to suspend irq
+             processing, if event polling finds events
+        type: uint
   -
     name: queue
     attributes:
@@ -653,6 +658,7 @@ operations:
             - pid
             - defer-hard-irqs
             - gro-flush-timeout
+            - irq-suspend-timeout
       dump:
         request:
           attributes:
@@ -704,6 +710,7 @@ operations:
             - id
             - defer-hard-irqs
             - gro-flush-timeout
+            - irq-suspend-timeout
 
 kernel-family:
   headers: [ "linux/list.h"]
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index df4483598628..0aae346d919e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -348,6 +348,7 @@ struct gro_list {
  */
 struct napi_config {
 	u64 gro_flush_timeout;
+	u64 irq_suspend_timeout;
 	u32 defer_hard_irqs;
 	unsigned int napi_id;
 };
@@ -384,6 +385,7 @@ struct napi_struct {
 	struct hrtimer		timer;
 	struct task_struct	*thread;
 	unsigned long		gro_flush_timeout;
+	unsigned long		irq_suspend_timeout;
 	u32			defer_hard_irqs;
 	/* control-path-only fields follow */
 	struct list_head	dev_list;
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index e3ebb49f60d2..e4be227d3ad6 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -124,6 +124,7 @@ enum {
 	NETDEV_A_NAPI_PID,
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
+	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/net/core/dev.c b/net/core/dev.c
index 6a31152e4606..4d910872963f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6666,6 +6666,7 @@ static void napi_restore_config(struct napi_struct *n)
 {
 	n->defer_hard_irqs = n->config->defer_hard_irqs;
 	n->gro_flush_timeout = n->config->gro_flush_timeout;
+	n->irq_suspend_timeout = n->config->irq_suspend_timeout;
 	/* a NAPI ID might be stored in the config, if so use it. if not, use
 	 * napi_hash_add to generate one for us. It will be saved to the config
 	 * in napi_disable.
@@ -6680,6 +6681,7 @@ static void napi_save_config(struct napi_struct *n)
 {
 	n->config->defer_hard_irqs = n->defer_hard_irqs;
 	n->config->gro_flush_timeout = n->gro_flush_timeout;
+	n->config->irq_suspend_timeout = n->irq_suspend_timeout;
 	n->config->napi_id = n->napi_id;
 	napi_hash_del(n);
 }
diff --git a/net/core/dev.h b/net/core/dev.h
index 7881bced70a9..d043dee25a68 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -236,6 +236,31 @@ static inline void netdev_set_gro_flush_timeout(struct net_device *netdev,
 		netdev->napi_config[i].gro_flush_timeout = timeout;
 }
 
+/**
+ * napi_get_irq_suspend_timeout - get the irq_suspend_timeout
+ * @n: napi struct to get the irq_suspend_timeout from
+ *
+ * Return: the per-NAPI value of the irq_suspend_timeout field.
+ */
+static inline unsigned long
+napi_get_irq_suspend_timeout(const struct napi_struct *n)
+{
+	return READ_ONCE(n->irq_suspend_timeout);
+}
+
+/**
+ * napi_set_irq_suspend_timeout - set the irq_suspend_timeout for a napi
+ * @n: napi struct to set the irq_suspend_timeout
+ * @timeout: timeout value to set
+ *
+ * napi_set_irq_suspend_timeout sets the per-NAPI irq_suspend_timeout
+ */
+static inline void napi_set_irq_suspend_timeout(struct napi_struct *n,
+						unsigned long timeout)
+{
+	WRITE_ONCE(n->irq_suspend_timeout, timeout);
+}
+
 int rps_cpumask_housekeeping(struct cpumask *mask);
 
 #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 21de7e10be16..a89cbd8d87c3 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -92,10 +92,11 @@ static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1]
 };
 
 /* NETDEV_CMD_NAPI_SET - do */
-static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT + 1] = {
+static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT + 1] = {
 	[NETDEV_A_NAPI_ID] = { .type = NLA_U32, },
 	[NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range),
 	[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, },
+	[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, },
 };
 
 /* Ops table for netdev */
@@ -186,7 +187,7 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.cmd		= NETDEV_CMD_NAPI_SET,
 		.doit		= netdev_nl_napi_set_doit,
 		.policy		= netdev_napi_set_nl_policy,
-		.maxattr	= NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
+		.maxattr	= NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 };
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index b49c3b4e5fbe..765ce7c9d73b 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -161,6 +161,7 @@ static int
 netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 			const struct genl_info *info)
 {
+	unsigned long irq_suspend_timeout;
 	unsigned long gro_flush_timeout;
 	u32 napi_defer_hard_irqs;
 	void *hdr;
@@ -196,6 +197,11 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 			napi_defer_hard_irqs))
 		goto nla_put_failure;
 
+	irq_suspend_timeout = napi_get_irq_suspend_timeout(napi);
+	if (nla_put_uint(rsp, NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+			 irq_suspend_timeout))
+		goto nla_put_failure;
+
 	gro_flush_timeout = napi_get_gro_flush_timeout(napi);
 	if (nla_put_uint(rsp, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 			 gro_flush_timeout))
@@ -306,6 +312,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 static int
 netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
 {
+	u64 irq_suspend_timeout = 0;
 	u64 gro_flush_timeout = 0;
 	u32 defer = 0;
 
@@ -314,6 +321,11 @@ netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
 		napi_set_defer_hard_irqs(napi, defer);
 	}
 
+	if (info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]) {
+		irq_suspend_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]);
+		napi_set_irq_suspend_timeout(napi, irq_suspend_timeout);
+	}
+
 	if (info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]) {
 		gro_flush_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]);
 		napi_set_gro_flush_timeout(napi, gro_flush_timeout);
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index e3ebb49f60d2..e4be227d3ad6 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -124,6 +124,7 @@ enum {
 	NETDEV_A_NAPI_PID,
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
+	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
-- 
cgit v1.2.3


From 5229df8fb6796ff4aba39b16cf617028fa5d94b7 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 2 Dec 2024 19:53:40 -0800
Subject: tools headers: Sync uapi/linux/perf_event.h with the kernel sources

To pick up the changes in this cset:

  18d92bb57c39504d ("perf/core: Add aux_pause, aux_resume, aux_start_paused")

This addresses these perf build warnings:

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

Please see tools/include/uapi/README for further details.

Reviewed-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20241203035349.1901262-3-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/include/uapi/linux/perf_event.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

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

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 4842c36fdf80..0524d541d4e3 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -511,7 +511,16 @@ struct perf_event_attr {
 	__u16	sample_max_stack;
 	__u16	__reserved_2;
 	__u32	aux_sample_size;
-	__u32	__reserved_3;
+
+	union {
+		__u32	aux_action;
+		struct {
+			__u32	aux_start_paused :  1, /* start AUX area tracing paused */
+				aux_pause        :  1, /* on overflow, pause AUX area tracing */
+				aux_resume       :  1, /* on overflow, resume AUX area tracing */
+				__reserved_3     : 29;
+		};
+	};
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
-- 
cgit v1.2.3


From e2064b7c5d82651a418b86078597e51dea3f3123 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 2 Dec 2024 19:53:41 -0800
Subject: tools headers: Sync uapi/linux/kvm.h with the kernel sources

To pick up the changes in this cset:

  e785dfacf7e7fe94 ("LoongArch: KVM: Add PCHPIC device support")
  2e8b9df82631e714 ("LoongArch: KVM: Add EIOINTC device support")
  c532de5a67a70f85 ("LoongArch: KVM: Add IPI device support")

This addresses these perf build warnings:

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

Please see tools/include/uapi/README for further details.

Reviewed-by: James Clark <james.clark@linaro.org>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Tianrui Zhao <zhaotianrui@loongson.cn>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: kvm@vger.kernel.org
Cc: loongarch@lists.linux.dev
Link: https://lore.kernel.org/r/20241203035349.1901262-4-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/include/uapi/linux/kvm.h | 8 ++++++++
 1 file changed, 8 insertions(+)

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

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 637efc055145..502ea63b5d2e 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1158,7 +1158,15 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_ARM_PV_TIME	KVM_DEV_TYPE_ARM_PV_TIME
 	KVM_DEV_TYPE_RISCV_AIA,
 #define KVM_DEV_TYPE_RISCV_AIA		KVM_DEV_TYPE_RISCV_AIA
+	KVM_DEV_TYPE_LOONGARCH_IPI,
+#define KVM_DEV_TYPE_LOONGARCH_IPI	KVM_DEV_TYPE_LOONGARCH_IPI
+	KVM_DEV_TYPE_LOONGARCH_EIOINTC,
+#define KVM_DEV_TYPE_LOONGARCH_EIOINTC	KVM_DEV_TYPE_LOONGARCH_EIOINTC
+	KVM_DEV_TYPE_LOONGARCH_PCHPIC,
+#define KVM_DEV_TYPE_LOONGARCH_PCHPIC	KVM_DEV_TYPE_LOONGARCH_PCHPIC
+
 	KVM_DEV_TYPE_MAX,
+
 };
 
 struct kvm_vfio_spapr_tce {
-- 
cgit v1.2.3


From 4d3ae294f900fb7232fb6c890dbd3176b8a5f121 Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Fri, 13 Dec 2024 13:09:31 +0000
Subject: bpf: Add fd_array_cnt attribute for prog_load

The fd_array attribute of the BPF_PROG_LOAD syscall may contain a set
of file descriptors: maps or btfs. This field was introduced as a
sparse array. Introduce a new attribute, fd_array_cnt, which, if
present, indicates that the fd_array is a continuous array of the
corresponding length.

If fd_array_cnt is non-zero, then every map in the fd_array will be
bound to the program, as if it was used by the program. This
functionality is similar to the BPF_PROG_BIND_MAP syscall, but such
maps can be used by the verifier during the program load.

Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20241213130934.1087929-5-aspsk@isovalent.com
---
 include/uapi/linux/bpf.h       |  10 ++++
 kernel/bpf/syscall.c           |   2 +-
 kernel/bpf/verifier.c          | 106 +++++++++++++++++++++++++++++++++++------
 tools/include/uapi/linux/bpf.h |  10 ++++
 4 files changed, 112 insertions(+), 16 deletions(-)

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

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4162afc6b5d0..2acf9b336371 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1573,6 +1573,16 @@ union bpf_attr {
 		 * If provided, prog_flags should have BPF_F_TOKEN_FD flag set.
 		 */
 		__s32		prog_token_fd;
+		/* The fd_array_cnt can be used to pass the length of the
+		 * fd_array array. In this case all the [map] file descriptors
+		 * passed in this array will be bound to the program, even if
+		 * the maps are not referenced directly. The functionality is
+		 * similar to the BPF_PROG_BIND_MAP syscall, but maps can be
+		 * used by the verifier during the program load. If provided,
+		 * then the fd_array[0,...,fd_array_cnt-1] is expected to be
+		 * continuous.
+		 */
+		__u32		fd_array_cnt;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5684e8ce132d..4e88797fdbeb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2730,7 +2730,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd
+#define BPF_PROG_LOAD_LAST_FIELD fd_array_cnt
 
 static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 296765ffbdc5..c0e772996c52 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -19505,22 +19505,10 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 	return 0;
 }
 
-/* Add map behind fd to used maps list, if it's not already there, and return
- * its index.
- * Returns <0 on error, or >= 0 index, on success.
- */
-static int add_used_map_from_fd(struct bpf_verifier_env *env, int fd)
+static int __add_used_map(struct bpf_verifier_env *env, struct bpf_map *map)
 {
-	CLASS(fd, f)(fd);
-	struct bpf_map *map;
 	int i, err;
 
-	map = __bpf_map_get(f);
-	if (IS_ERR(map)) {
-		verbose(env, "fd %d is not pointing to valid bpf_map\n", fd);
-		return PTR_ERR(map);
-	}
-
 	/* check whether we recorded this map already */
 	for (i = 0; i < env->used_map_cnt; i++)
 		if (env->used_maps[i] == map)
@@ -19551,6 +19539,24 @@ static int add_used_map_from_fd(struct bpf_verifier_env *env, int fd)
 	return env->used_map_cnt - 1;
 }
 
+/* Add map behind fd to used maps list, if it's not already there, and return
+ * its index.
+ * Returns <0 on error, or >= 0 index, on success.
+ */
+static int add_used_map(struct bpf_verifier_env *env, int fd)
+{
+	struct bpf_map *map;
+	CLASS(fd, f)(fd);
+
+	map = __bpf_map_get(f);
+	if (IS_ERR(map)) {
+		verbose(env, "fd %d is not pointing to valid bpf_map\n", fd);
+		return PTR_ERR(map);
+	}
+
+	return __add_used_map(env, map);
+}
+
 /* find and rewrite pseudo imm in ld_imm64 instructions:
  *
  * 1. if it accesses map FD, replace it with actual map pointer.
@@ -19642,7 +19648,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 				break;
 			}
 
-			map_idx = add_used_map_from_fd(env, fd);
+			map_idx = add_used_map(env, fd);
 			if (map_idx < 0)
 				return map_idx;
 			map = env->used_maps[map_idx];
@@ -22850,6 +22856,73 @@ struct btf *bpf_get_btf_vmlinux(void)
 	return btf_vmlinux;
 }
 
+/*
+ * The add_fd_from_fd_array() is executed only if fd_array_cnt is non-zero. In
+ * this case expect that every file descriptor in the array is either a map or
+ * a BTF. Everything else is considered to be trash.
+ */
+static int add_fd_from_fd_array(struct bpf_verifier_env *env, int fd)
+{
+	struct bpf_map *map;
+	struct btf *btf;
+	CLASS(fd, f)(fd);
+	int err;
+
+	map = __bpf_map_get(f);
+	if (!IS_ERR(map)) {
+		err = __add_used_map(env, map);
+		if (err < 0)
+			return err;
+		return 0;
+	}
+
+	btf = __btf_get_by_fd(f);
+	if (!IS_ERR(btf)) {
+		err = __add_used_btf(env, btf);
+		if (err < 0)
+			return err;
+		return 0;
+	}
+
+	verbose(env, "fd %d is not pointing to valid bpf_map or btf\n", fd);
+	return PTR_ERR(map);
+}
+
+static int process_fd_array(struct bpf_verifier_env *env, union bpf_attr *attr, bpfptr_t uattr)
+{
+	size_t size = sizeof(int);
+	int ret;
+	int fd;
+	u32 i;
+
+	env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel);
+
+	/*
+	 * The only difference between old (no fd_array_cnt is given) and new
+	 * APIs is that in the latter case the fd_array is expected to be
+	 * continuous and is scanned for map fds right away
+	 */
+	if (!attr->fd_array_cnt)
+		return 0;
+
+	/* Check for integer overflow */
+	if (attr->fd_array_cnt >= (U32_MAX / size)) {
+		verbose(env, "fd_array_cnt is too big (%u)\n", attr->fd_array_cnt);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < attr->fd_array_cnt; i++) {
+		if (copy_from_bpfptr_offset(&fd, env->fd_array, i * size, size))
+			return -EFAULT;
+
+		ret = add_fd_from_fd_array(env, fd);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size)
 {
 	u64 start_time = ktime_get_ns();
@@ -22881,7 +22954,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 		env->insn_aux_data[i].orig_idx = i;
 	env->prog = *prog;
 	env->ops = bpf_verifier_ops[env->prog->type];
-	env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel);
 
 	env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token);
 	env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token);
@@ -22904,6 +22976,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (ret)
 		goto err_unlock;
 
+	ret = process_fd_array(env, attr, uattr);
+	if (ret)
+		goto skip_full_check;
+
 	mark_verifier_state_clean(env);
 
 	if (IS_ERR(btf_vmlinux)) {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4162afc6b5d0..2acf9b336371 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1573,6 +1573,16 @@ union bpf_attr {
 		 * If provided, prog_flags should have BPF_F_TOKEN_FD flag set.
 		 */
 		__s32		prog_token_fd;
+		/* The fd_array_cnt can be used to pass the length of the
+		 * fd_array array. In this case all the [map] file descriptors
+		 * passed in this array will be bound to the program, even if
+		 * the maps are not referenced directly. The functionality is
+		 * similar to the BPF_PROG_BIND_MAP syscall, but maps can be
+		 * used by the verifier during the program load. If provided,
+		 * then the fd_array[0,...,fd_array_cnt-1] is expected to be
+		 * continuous.
+		 */
+		__u32		fd_array_cnt;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
-- 
cgit v1.2.3


From 724c6ce38bbaeb4b3f109b0e066d6c0ecd15446c Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 19 Dec 2024 14:57:34 +0100
Subject: stddef: make __struct_group() UAPI C++-friendly

For the most part of the C++ history, it couldn't have type
declarations inside anonymous unions for different reasons. At the
same time, __struct_group() relies on the latters, so when the @TAG
argument is not empty, C++ code doesn't want to build (even under
`extern "C"`):

../linux/include/uapi/linux/pkt_cls.h:25:24: error:
'struct tc_u32_sel::<unnamed union>::tc_u32_sel_hdr,' invalid;
an anonymous union may only have public non-static data members
[-fpermissive]

The safest way to fix this without trying to switch standards (which
is impossible in UAPI anyway) etc., is to disable tag declaration
for that language. This won't break anything since for now it's not
buildable at all.
Use a separate definition for __struct_group() when __cplusplus is
defined to mitigate the error, including the version from tools/.

Fixes: 50d7bd38c3aa ("stddef: Introduce struct_group() helper macro")
Reported-by: Christopher Ferris <cferris@google.com>
Closes: https://lore.kernel.org/linux-hardening/Z1HZpe3WE5As8UAz@google.com
Suggested-by: Kees Cook <kees@kernel.org> # __struct_group_tag()
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20241219135734.2130002-1-aleksander.lobakin@intel.com
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/uapi/linux/stddef.h       | 13 ++++++++++---
 tools/include/uapi/linux/stddef.h | 15 +++++++++++----
 2 files changed, 21 insertions(+), 7 deletions(-)

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

diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
index 58154117d9b0..a6fce46aeb37 100644
--- a/include/uapi/linux/stddef.h
+++ b/include/uapi/linux/stddef.h
@@ -8,6 +8,13 @@
 #define __always_inline inline
 #endif
 
+/* Not all C++ standards support type declarations inside an anonymous union */
+#ifndef __cplusplus
+#define __struct_group_tag(TAG)		TAG
+#else
+#define __struct_group_tag(TAG)
+#endif
+
 /**
  * __struct_group() - Create a mirrored named and anonyomous struct
  *
@@ -20,13 +27,13 @@
  * and size: one anonymous and one named. The former's members can be used
  * normally without sub-struct naming, and the latter can be used to
  * reason about the start, end, and size of the group of struct members.
- * The named struct can also be explicitly tagged for layer reuse, as well
- * as both having struct attributes appended.
+ * The named struct can also be explicitly tagged for layer reuse (C only),
+ * as well as both having struct attributes appended.
  */
 #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
 	union { \
 		struct { MEMBERS } ATTRS; \
-		struct TAG { MEMBERS } ATTRS NAME; \
+		struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \
 	} ATTRS
 
 #ifdef __cplusplus
diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h
index bb6ea517efb5..c53cde425406 100644
--- a/tools/include/uapi/linux/stddef.h
+++ b/tools/include/uapi/linux/stddef.h
@@ -8,6 +8,13 @@
 #define __always_inline __inline__
 #endif
 
+/* Not all C++ standards support type declarations inside an anonymous union */
+#ifndef __cplusplus
+#define __struct_group_tag(TAG)		TAG
+#else
+#define __struct_group_tag(TAG)
+#endif
+
 /**
  * __struct_group() - Create a mirrored named and anonyomous struct
  *
@@ -20,14 +27,14 @@
  * and size: one anonymous and one named. The former's members can be used
  * normally without sub-struct naming, and the latter can be used to
  * reason about the start, end, and size of the group of struct members.
- * The named struct can also be explicitly tagged for layer reuse, as well
- * as both having struct attributes appended.
+ * The named struct can also be explicitly tagged for layer reuse (C only),
+ * as well as both having struct attributes appended.
  */
 #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
 	union { \
 		struct { MEMBERS } ATTRS; \
-		struct TAG { MEMBERS } ATTRS NAME; \
-	}
+		struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \
+	} ATTRS
 
 /**
  * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
-- 
cgit v1.2.3


From b9ed315d3c4c0c294a4348edb6874d489bac47fa Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sat, 21 Dec 2024 00:46:56 +0100
Subject: netkit: Allow for configuring needed_{head,tail}room

Allow the user to configure needed_{head,tail}room for both netkit
devices. The idea is similar to 163e529200af ("veth: implement
ndo_set_rx_headroom") with the difference that the two parameters
can be specified upon device creation. By default the current behavior
stays as is which is needed_{head,tail}room is 0.

In case of Cilium, for example, the netkit devices are not enslaved
into a bridge or openvswitch device (rather, BPF-based redirection
is used out of tcx), and as such these parameters are not propagated
into the Pod's netns via peer device.

Given Cilium can run in vxlan/geneve tunneling mode (needed_headroom)
and/or be used in combination with WireGuard (needed_{head,tail}room),
allow the Cilium CNI plugin to specify these two upon netkit device
creation.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://lore.kernel.org/bpf/20241220234658.490686-1-daniel@iogearbox.net
---
 drivers/net/netkit.c               | 66 +++++++++++++++++++++++++-------------
 include/uapi/linux/if_link.h       |  2 ++
 tools/include/uapi/linux/if_link.h |  2 ++
 3 files changed, 47 insertions(+), 23 deletions(-)

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

diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index c1d881dc6409..1e1b00756be7 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -338,6 +338,7 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev,
 	enum netkit_scrub scrub_peer = NETKIT_SCRUB_DEFAULT;
 	enum netkit_mode mode = NETKIT_L3;
 	unsigned char ifname_assign_type;
+	u16 headroom = 0, tailroom = 0;
 	struct ifinfomsg *ifmp = NULL;
 	struct net_device *peer;
 	char ifname[IFNAMSIZ];
@@ -371,6 +372,10 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev,
 			if (err < 0)
 				return err;
 		}
+		if (data[IFLA_NETKIT_HEADROOM])
+			headroom = nla_get_u16(data[IFLA_NETKIT_HEADROOM]);
+		if (data[IFLA_NETKIT_TAILROOM])
+			tailroom = nla_get_u16(data[IFLA_NETKIT_TAILROOM]);
 	}
 
 	if (ifmp && tbp[IFLA_IFNAME]) {
@@ -390,6 +395,14 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev,
 		return PTR_ERR(peer);
 
 	netif_inherit_tso_max(peer, dev);
+	if (headroom) {
+		peer->needed_headroom = headroom;
+		dev->needed_headroom = headroom;
+	}
+	if (tailroom) {
+		peer->needed_tailroom = tailroom;
+		dev->needed_tailroom = tailroom;
+	}
 
 	if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS]))
 		eth_hw_addr_random(peer);
@@ -401,6 +414,7 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev,
 	nk->policy = policy_peer;
 	nk->scrub = scrub_peer;
 	nk->mode = mode;
+	nk->headroom = headroom;
 	bpf_mprog_bundle_init(&nk->bundle);
 
 	err = register_netdevice(peer);
@@ -426,6 +440,7 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev,
 	nk->policy = policy_prim;
 	nk->scrub = scrub_prim;
 	nk->mode = mode;
+	nk->headroom = headroom;
 	bpf_mprog_bundle_init(&nk->bundle);
 
 	err = register_netdevice(dev);
@@ -850,7 +865,18 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
 	struct net_device *peer = rtnl_dereference(nk->peer);
 	enum netkit_action policy;
 	struct nlattr *attr;
-	int err;
+	int err, i;
+	static const struct {
+		u32 attr;
+		char *name;
+	} fixed_params[] = {
+		{ IFLA_NETKIT_MODE,       "operating mode" },
+		{ IFLA_NETKIT_SCRUB,      "scrubbing" },
+		{ IFLA_NETKIT_PEER_SCRUB, "peer scrubbing" },
+		{ IFLA_NETKIT_PEER_INFO,  "peer info" },
+		{ IFLA_NETKIT_HEADROOM,   "headroom" },
+		{ IFLA_NETKIT_TAILROOM,   "tailroom" },
+	};
 
 	if (!nk->primary) {
 		NL_SET_ERR_MSG(extack,
@@ -858,28 +884,14 @@ static int netkit_change_link(struct net_device *dev, struct nlattr *tb[],
 		return -EACCES;
 	}
 
-	if (data[IFLA_NETKIT_MODE]) {
-		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_MODE],
-				    "netkit link operating mode cannot be changed after device creation");
-		return -EACCES;
-	}
-
-	if (data[IFLA_NETKIT_SCRUB]) {
-		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_SCRUB],
-				    "netkit scrubbing cannot be changed after device creation");
-		return -EACCES;
-	}
-
-	if (data[IFLA_NETKIT_PEER_SCRUB]) {
-		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_PEER_SCRUB],
-				    "netkit scrubbing cannot be changed after device creation");
-		return -EACCES;
-	}
-
-	if (data[IFLA_NETKIT_PEER_INFO]) {
-		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_PEER_INFO],
-				    "netkit peer info cannot be changed after device creation");
-		return -EINVAL;
+	for (i = 0; i < ARRAY_SIZE(fixed_params); i++) {
+		attr = data[fixed_params[i].attr];
+		if (attr) {
+			NL_SET_ERR_MSG_ATTR_FMT(extack, attr,
+						"netkit link %s cannot be changed after device creation",
+						fixed_params[i].name);
+			return -EACCES;
+		}
 	}
 
 	if (data[IFLA_NETKIT_POLICY]) {
@@ -914,6 +926,8 @@ static size_t netkit_get_size(const struct net_device *dev)
 	       nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_SCRUB */
 	       nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_MODE */
 	       nla_total_size(sizeof(u8))  + /* IFLA_NETKIT_PRIMARY */
+	       nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_HEADROOM */
+	       nla_total_size(sizeof(u16)) + /* IFLA_NETKIT_TAILROOM */
 	       0;
 }
 
@@ -930,6 +944,10 @@ static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev)
 		return -EMSGSIZE;
 	if (nla_put_u32(skb, IFLA_NETKIT_SCRUB, nk->scrub))
 		return -EMSGSIZE;
+	if (nla_put_u16(skb, IFLA_NETKIT_HEADROOM, dev->needed_headroom))
+		return -EMSGSIZE;
+	if (nla_put_u16(skb, IFLA_NETKIT_TAILROOM, dev->needed_tailroom))
+		return -EMSGSIZE;
 
 	if (peer) {
 		nk = netkit_priv(peer);
@@ -947,6 +965,8 @@ static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = {
 	[IFLA_NETKIT_MODE]		= NLA_POLICY_MAX(NLA_U32, NETKIT_L3),
 	[IFLA_NETKIT_POLICY]		= { .type = NLA_U32 },
 	[IFLA_NETKIT_PEER_POLICY]	= { .type = NLA_U32 },
+	[IFLA_NETKIT_HEADROOM]		= { .type = NLA_U16 },
+	[IFLA_NETKIT_TAILROOM]		= { .type = NLA_U16 },
 	[IFLA_NETKIT_SCRUB]		= NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT),
 	[IFLA_NETKIT_PEER_SCRUB]	= NLA_POLICY_MAX(NLA_U32, NETKIT_SCRUB_DEFAULT),
 	[IFLA_NETKIT_PRIMARY]		= { .type = NLA_REJECT,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 2575e0cd9b48..2fa2c265dcba 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1315,6 +1315,8 @@ enum {
 	IFLA_NETKIT_MODE,
 	IFLA_NETKIT_SCRUB,
 	IFLA_NETKIT_PEER_SCRUB,
+	IFLA_NETKIT_HEADROOM,
+	IFLA_NETKIT_TAILROOM,
 	__IFLA_NETKIT_MAX,
 };
 #define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 8516c1ccd57a..7e46ca4cd31b 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -1315,6 +1315,8 @@ enum {
 	IFLA_NETKIT_MODE,
 	IFLA_NETKIT_SCRUB,
 	IFLA_NETKIT_PEER_SCRUB,
+	IFLA_NETKIT_HEADROOM,
+	IFLA_NETKIT_TAILROOM,
 	__IFLA_NETKIT_MAX,
 };
 #define IFLA_NETKIT_MAX	(__IFLA_NETKIT_MAX - 1)
-- 
cgit v1.2.3


From 01f3ce5328c405179b2c69ea047c423dad2bfa6d Mon Sep 17 00:00:00 2001
From: Vishal Chourasia <vishalc@linux.ibm.com>
Date: Fri, 17 Jan 2025 15:42:59 +0100
Subject: tools: Sync if_xdp.h uapi tooling header

Sync if_xdp.h uapi header to remove following warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h'
  differs from latest version at 'include/uapi/linux/if_xdp.h'

Fixes: 48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support")
Signed-off-by: Vishal Chourasia <vishalc@linux.ibm.com>
Signed-off-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20250115032248.125742-1-yoong.siang.song@intel.com
---
 tools/include/uapi/linux/if_xdp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

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

diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 2f082b01ff22..42ec5ddaab8d 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -117,12 +117,12 @@ struct xdp_options {
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
 /* Request transmit timestamp. Upon completion, put it into tx_timestamp
- * field of union xsk_tx_metadata.
+ * field of struct xsk_tx_metadata.
  */
 #define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
 
 /* Request transmit checksum offload. Checksum start position and offset
- * are communicated via csum_start and csum_offset fields of union
+ * are communicated via csum_start and csum_offset fields of struct
  * xsk_tx_metadata.
  */
 #define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
-- 
cgit v1.2.3