perf trace beauty: Add script to autogenerate socket families table

To use with 'perf trace', to convert the protocol families to strings,
e.g:

  $ tools/perf/trace/beauty/socket.sh
  static const char *socket_families[] = {
  	[0] = "UNSPEC",
  	[1] = "LOCAL",
  	[2] = "INET",
  	[3] = "AX25",
  	[4] = "IPX",
  	[5] = "APPLETALK",
  	[6] = "NETROM",
  	[7] = "BRIDGE",
  	[8] = "ATMPVC",
  	[9] = "X25",
  	[10] = "INET6",
  	[11] = "ROSE",
  	[12] = "DECnet",
  	[13] = "NETBEUI",
  	[14] = "SECURITY",
  	[15] = "KEY",
  	[16] = "NETLINK",
  	[17] = "PACKET",
  	[18] = "ASH",
  	[19] = "ECONET",
  	[20] = "ATMSVC",
  	[21] = "RDS",
  	[22] = "SNA",
  	[23] = "IRDA",
  	[24] = "PPPOX",
  	[25] = "WANPIPE",
  	[26] = "LLC",
  	[27] = "IB",
  	[28] = "MPLS",
  	[29] = "CAN",
  	[30] = "TIPC",
  	[31] = "BLUETOOTH",
  	[32] = "IUCV",
  	[33] = "RXRPC",
  	[34] = "ISDN",
  	[35] = "PHONET",
  	[36] = "IEEE802154",
  	[37] = "CAIF",
  	[38] = "ALG",
  	[39] = "NFC",
  	[40] = "VSOCK",
  	[41] = "KCM",
  	[42] = "QIPCRTR",
  	[43] = "SMC",
  	[44] = "XDP",
  };
  $

This uses a copy of include/linux/socket.h that is kept in a directory
to be used just for these table generation scripts and for checking if
the kernel has a new file that maybe gets something new for these
tables.

This allows us to:

- Avoid accessing files outside tools/, in the kernel sources, that may
  be changed in unexpected ways and thus break these scripts.

- Notice when those files change and thus check if the changes don't
  break those scripts, update them to automatically get the new
  definitions, a new socket family, for instance.

- Not add then to the tools/include/ where it may end up used while
  building the tools and end up requiring dragging yet more stuff from
  the kernel or plain break the build in some of the myriad environments
  where perf may be built.

This will replace the previous static array in tools/perf/ that was
dated and was already missing the AF_KCM, AF_QIPCRTR, AF_SMC and AF_XDP
families.

The next cset will wire this up to the perf build process.

At some point this must be made into a library to be used in places such
as libtraceevent, bpftrace, etc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/trace/beauty/include/linux/socket.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SOCKET_H
+#define _LINUX_SOCKET_H
+
+
+#include <asm/socket.h>			/* arch-dependent defines	*/
+#include <linux/sockios.h>		/* the SIOCxxx I/O controls	*/
+#include <linux/uio.h>			/* iovec support		*/
+#include <linux/types.h>		/* pid_t			*/
+#include <linux/compiler.h>		/* __user			*/
+#include <uapi/linux/socket.h>
+
+struct file;
+struct pid;
+struct cred;
+struct socket;
+
+#define __sockaddr_check_size(size)	\
+	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
+
+#ifdef CONFIG_PROC_FS
+struct seq_file;
+extern void socket_seq_show(struct seq_file *seq);
+#endif
+
+typedef __kernel_sa_family_t	sa_family_t;
+
+/*
+ *	1003.1g requires sa_family_t and that sa_data is char.
+ */
+
+struct sockaddr {
+	sa_family_t	sa_family;	/* address family, AF_xxx	*/
+	char		sa_data[14];	/* 14 bytes of protocol address	*/
+};
+
+struct linger {
+	int		l_onoff;	/* Linger active		*/
+	int		l_linger;	/* How long to linger for	*/
+};
+
+#define sockaddr_storage __kernel_sockaddr_storage
+
+/*
+ *	As we do 4.4BSD message passing we use a 4.4BSD message passing
+ *	system, not 4.3. Thus msg_accrights(len) are now missing. They
+ *	belong in an obscure libc emulation or the bin.
+ */
+
+struct msghdr {
+	void		*msg_name;	/* ptr to socket address structure */
+	int		msg_namelen;	/* size of socket address structure */
+	struct iov_iter	msg_iter;	/* data */
+
+	/*
+	 * Ancillary data. msg_control_user is the user buffer used for the
+	 * recv* side when msg_control_is_user is set, msg_control is the kernel
+	 * buffer used for all other cases.
+	 */
+	union {
+		void		*msg_control;
+		void __user	*msg_control_user;
+	};
+	bool		msg_control_is_user : 1;
+	__kernel_size_t	msg_controllen;	/* ancillary data buffer length */
+	unsigned int	msg_flags;	/* flags on received message */
+	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
+};
+
+struct user_msghdr {
+	void		__user *msg_name;	/* ptr to socket address structure */
+	int		msg_namelen;		/* size of socket address structure */
+	struct iovec	__user *msg_iov;	/* scatter/gather array */
+	__kernel_size_t	msg_iovlen;		/* # elements in msg_iov */
+	void		__user *msg_control;	/* ancillary data */
+	__kernel_size_t	msg_controllen;		/* ancillary data buffer length */
+	unsigned int	msg_flags;		/* flags on received message */
+};
+
+/* For recvmmsg/sendmmsg */
+struct mmsghdr {
+	struct user_msghdr  msg_hdr;
+	unsigned int        msg_len;
+};
+
+/*
+ *	POSIX 1003.1g - ancillary data object information
+ *	Ancillary data consits of a sequence of pairs of
+ *	(cmsghdr, cmsg_data[])
+ */
+
+struct cmsghdr {
+	__kernel_size_t	cmsg_len;	/* data byte count, including hdr */
+        int		cmsg_level;	/* originating protocol */
+        int		cmsg_type;	/* protocol-specific type */
+};
+
+/*
+ *	Ancillary data object information MACROS
+ *	Table 5-14 of POSIX 1003.1g
+ */
+
+#define __CMSG_NXTHDR(ctl, len, cmsg) __cmsg_nxthdr((ctl),(len),(cmsg))
+#define CMSG_NXTHDR(mhdr, cmsg) cmsg_nxthdr((mhdr), (cmsg))
+
+#define CMSG_ALIGN(len) ( ((len)+sizeof(long)-1) & ~(sizeof(long)-1) )
+
+#define CMSG_DATA(cmsg) \
+	((void *)(cmsg) + sizeof(struct cmsghdr))
+#define CMSG_USER_DATA(cmsg) \
+	((void __user *)(cmsg) + sizeof(struct cmsghdr))
+#define CMSG_SPACE(len) (sizeof(struct cmsghdr) + CMSG_ALIGN(len))
+#define CMSG_LEN(len) (sizeof(struct cmsghdr) + (len))
+
+#define __CMSG_FIRSTHDR(ctl,len) ((len) >= sizeof(struct cmsghdr) ? \
+				  (struct cmsghdr *)(ctl) : \
+				  (struct cmsghdr *)NULL)
+#define CMSG_FIRSTHDR(msg)	__CMSG_FIRSTHDR((msg)->msg_control, (msg)->msg_controllen)
+#define CMSG_OK(mhdr, cmsg) ((cmsg)->cmsg_len >= sizeof(struct cmsghdr) && \
+			     (cmsg)->cmsg_len <= (unsigned long) \
+			     ((mhdr)->msg_controllen - \
+			      ((char *)(cmsg) - (char *)(mhdr)->msg_control)))
+#define for_each_cmsghdr(cmsg, msg) \
+	for (cmsg = CMSG_FIRSTHDR(msg); \
+	     cmsg; \
+	     cmsg = CMSG_NXTHDR(msg, cmsg))
+
+/*
+ *	Get the next cmsg header
+ *
+ *	PLEASE, do not touch this function. If you think, that it is
+ *	incorrect, grep kernel sources and think about consequences
+ *	before trying to improve it.
+ *
+ *	Now it always returns valid, not truncated ancillary object
+ *	HEADER. But caller still MUST check, that cmsg->cmsg_len is
+ *	inside range, given by msg->msg_controllen before using
+ *	ancillary object DATA.				--ANK (980731)
+ */
+
+static inline struct cmsghdr * __cmsg_nxthdr(void *__ctl, __kernel_size_t __size,
+					       struct cmsghdr *__cmsg)
+{
+	struct cmsghdr * __ptr;
+
+	__ptr = (struct cmsghdr*)(((unsigned char *) __cmsg) +  CMSG_ALIGN(__cmsg->cmsg_len));
+	if ((unsigned long)((char*)(__ptr+1) - (char *) __ctl) > __size)
+		return (struct cmsghdr *)0;
+
+	return __ptr;
+}
+
+static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr *__cmsg)
+{
+	return __cmsg_nxthdr(__msg->msg_control, __msg->msg_controllen, __cmsg);
+}
+
+static inline size_t msg_data_left(struct msghdr *msg)
+{
+	return iov_iter_count(&msg->msg_iter);
+}
+
+/* "Socket"-level control message types: */
+
+#define	SCM_RIGHTS	0x01		/* rw: access rights (array of int) */
+#define SCM_CREDENTIALS 0x02		/* rw: struct ucred		*/
+#define SCM_SECURITY	0x03		/* rw: security label		*/
+
+struct ucred {
+	__u32	pid;
+	__u32	uid;
+	__u32	gid;
+};
+
+/* Supported address families. */
+#define AF_UNSPEC	0
+#define AF_UNIX		1	/* Unix domain sockets 		*/
+#define AF_LOCAL	1	/* POSIX name for AF_UNIX	*/
+#define AF_INET		2	/* Internet IP Protocol 	*/
+#define AF_AX25		3	/* Amateur Radio AX.25 		*/
+#define AF_IPX		4	/* Novell IPX 			*/
+#define AF_APPLETALK	5	/* AppleTalk DDP 		*/
+#define AF_NETROM	6	/* Amateur Radio NET/ROM 	*/
+#define AF_BRIDGE	7	/* Multiprotocol bridge 	*/
+#define AF_ATMPVC	8	/* ATM PVCs			*/
+#define AF_X25		9	/* Reserved for X.25 project 	*/
+#define AF_INET6	10	/* IP version 6			*/
+#define AF_ROSE		11	/* Amateur Radio X.25 PLP	*/
+#define AF_DECnet	12	/* Reserved for DECnet project	*/
+#define AF_NETBEUI	13	/* Reserved for 802.2LLC project*/
+#define AF_SECURITY	14	/* Security callback pseudo AF */
+#define AF_KEY		15      /* PF_KEY key management API */
+#define AF_NETLINK	16
+#define AF_ROUTE	AF_NETLINK /* Alias to emulate 4.4BSD */
+#define AF_PACKET	17	/* Packet family		*/
+#define AF_ASH		18	/* Ash				*/
+#define AF_ECONET	19	/* Acorn Econet			*/
+#define AF_ATMSVC	20	/* ATM SVCs			*/
+#define AF_RDS		21	/* RDS sockets 			*/
+#define AF_SNA		22	/* Linux SNA Project (nutters!) */
+#define AF_IRDA		23	/* IRDA sockets			*/
+#define AF_PPPOX	24	/* PPPoX sockets		*/
+#define AF_WANPIPE	25	/* Wanpipe API Sockets */
+#define AF_LLC		26	/* Linux LLC			*/
+#define AF_IB		27	/* Native InfiniBand address	*/
+#define AF_MPLS		28	/* MPLS */
+#define AF_CAN		29	/* Controller Area Network      */
+#define AF_TIPC		30	/* TIPC sockets			*/
+#define AF_BLUETOOTH	31	/* Bluetooth sockets 		*/
+#define AF_IUCV		32	/* IUCV sockets			*/
+#define AF_RXRPC	33	/* RxRPC sockets 		*/
+#define AF_ISDN		34	/* mISDN sockets 		*/
+#define AF_PHONET	35	/* Phonet sockets		*/
+#define AF_IEEE802154	36	/* IEEE802154 sockets		*/
+#define AF_CAIF		37	/* CAIF sockets			*/
+#define AF_ALG		38	/* Algorithm sockets		*/
+#define AF_NFC		39	/* NFC sockets			*/
+#define AF_VSOCK	40	/* vSockets			*/
+#define AF_KCM		41	/* Kernel Connection Multiplexor*/
+#define AF_QIPCRTR	42	/* Qualcomm IPC Router          */
+#define AF_SMC		43	/* smc sockets: reserve number for
+				 * PF_SMC protocol family that
+				 * reuses AF_INET address family
+				 */
+#define AF_XDP		44	/* XDP sockets			*/
+
+#define AF_MAX		45	/* For now.. */
+
+/* Protocol families, same as address families. */
+#define PF_UNSPEC	AF_UNSPEC
+#define PF_UNIX		AF_UNIX
+#define PF_LOCAL	AF_LOCAL
+#define PF_INET		AF_INET
+#define PF_AX25		AF_AX25
+#define PF_IPX		AF_IPX
+#define PF_APPLETALK	AF_APPLETALK
+#define	PF_NETROM	AF_NETROM
+#define PF_BRIDGE	AF_BRIDGE
+#define PF_ATMPVC	AF_ATMPVC
+#define PF_X25		AF_X25
+#define PF_INET6	AF_INET6
+#define PF_ROSE		AF_ROSE
+#define PF_DECnet	AF_DECnet
+#define PF_NETBEUI	AF_NETBEUI
+#define PF_SECURITY	AF_SECURITY
+#define PF_KEY		AF_KEY
+#define PF_NETLINK	AF_NETLINK
+#define PF_ROUTE	AF_ROUTE
+#define PF_PACKET	AF_PACKET
+#define PF_ASH		AF_ASH
+#define PF_ECONET	AF_ECONET
+#define PF_ATMSVC	AF_ATMSVC
+#define PF_RDS		AF_RDS
+#define PF_SNA		AF_SNA
+#define PF_IRDA		AF_IRDA
+#define PF_PPPOX	AF_PPPOX
+#define PF_WANPIPE	AF_WANPIPE
+#define PF_LLC		AF_LLC
+#define PF_IB		AF_IB
+#define PF_MPLS		AF_MPLS
+#define PF_CAN		AF_CAN
+#define PF_TIPC		AF_TIPC
+#define PF_BLUETOOTH	AF_BLUETOOTH
+#define PF_IUCV		AF_IUCV
+#define PF_RXRPC	AF_RXRPC
+#define PF_ISDN		AF_ISDN
+#define PF_PHONET	AF_PHONET
+#define PF_IEEE802154	AF_IEEE802154
+#define PF_CAIF		AF_CAIF
+#define PF_ALG		AF_ALG
+#define PF_NFC		AF_NFC
+#define PF_VSOCK	AF_VSOCK
+#define PF_KCM		AF_KCM
+#define PF_QIPCRTR	AF_QIPCRTR
+#define PF_SMC		AF_SMC
+#define PF_XDP		AF_XDP
+#define PF_MAX		AF_MAX
+
+/* Maximum queue length specifiable by listen.  */
+#define SOMAXCONN	4096
+
+/* Flags we can use with send/ and recv.
+   Added those for 1003.1g not all are supported yet
+ */
+
+#define MSG_OOB		1
+#define MSG_PEEK	2
+#define MSG_DONTROUTE	4
+#define MSG_TRYHARD     4       /* Synonym for MSG_DONTROUTE for DECnet */
+#define MSG_CTRUNC	8
+#define MSG_PROBE	0x10	/* Do not send. Only probe path f.e. for MTU */
+#define MSG_TRUNC	0x20
+#define MSG_DONTWAIT	0x40	/* Nonblocking io		 */
+#define MSG_EOR         0x80	/* End of record */
+#define MSG_WAITALL	0x100	/* Wait for a full request */
+#define MSG_FIN         0x200
+#define MSG_SYN		0x400
+#define MSG_CONFIRM	0x800	/* Confirm path validity */
+#define MSG_RST		0x1000
+#define MSG_ERRQUEUE	0x2000	/* Fetch message from error queue */
+#define MSG_NOSIGNAL	0x4000	/* Do not generate SIGPIPE */
+#define MSG_MORE	0x8000	/* Sender will send more */
+#define MSG_WAITFORONE	0x10000	/* recvmmsg(): block until 1+ packets avail */
+#define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */
+#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
+#define MSG_BATCH	0x40000 /* sendmmsg(): more messages coming */
+#define MSG_EOF         MSG_FIN
+#define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */
+#define MSG_SENDPAGE_DECRYPTED	0x100000 /* sendpage() internal : page may carry
+					  * plain text and require encryption
+					  */
+
+#define MSG_ZEROCOPY	0x4000000	/* Use user data in kernel path */
+#define MSG_FASTOPEN	0x20000000	/* Send data in TCP SYN */
+#define MSG_CMSG_CLOEXEC 0x40000000	/* Set close_on_exec for file
+					   descriptor received through
+					   SCM_RIGHTS */
+#if defined(CONFIG_COMPAT)
+#define MSG_CMSG_COMPAT	0x80000000	/* This message needs 32 bit fixups */
+#else
+#define MSG_CMSG_COMPAT	0		/* We never have 32 bit fixups */
+#endif
+
+
+/* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */
+#define SOL_IP		0
+/* #define SOL_ICMP	1	No-no-no! Due to Linux :-) we cannot use SOL_ICMP=1 */
+#define SOL_TCP		6
+#define SOL_UDP		17
+#define SOL_IPV6	41
+#define SOL_ICMPV6	58
+#define SOL_SCTP	132
+#define SOL_UDPLITE	136     /* UDP-Lite (RFC 3828) */
+#define SOL_RAW		255
+#define SOL_IPX		256
+#define SOL_AX25	257
+#define SOL_ATALK	258
+#define SOL_NETROM	259
+#define SOL_ROSE	260
+#define SOL_DECNET	261
+#define	SOL_X25		262
+#define SOL_PACKET	263
+#define SOL_ATM		264	/* ATM layer (cell level) */
+#define SOL_AAL		265	/* ATM Adaption Layer (packet level) */
+#define SOL_IRDA        266
+#define SOL_NETBEUI	267
+#define SOL_LLC		268
+#define SOL_DCCP	269
+#define SOL_NETLINK	270
+#define SOL_TIPC	271
+#define SOL_RXRPC	272
+#define SOL_PPPOL2TP	273
+#define SOL_BLUETOOTH	274
+#define SOL_PNPIPE	275
+#define SOL_RDS		276
+#define SOL_IUCV	277
+#define SOL_CAIF	278
+#define SOL_ALG		279
+#define SOL_NFC		280
+#define SOL_KCM		281
+#define SOL_TLS		282
+#define SOL_XDP		283
+
+/* IPX options */
+#define IPX_TYPE	1
+
+extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
+extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
+
+struct timespec64;
+struct __kernel_timespec;
+struct old_timespec32;
+
+struct scm_timestamping_internal {
+	struct timespec64 ts[3];
+};
+
+extern void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss);
+extern void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss);
+
+/* The __sys_...msg variants allow MSG_CMSG_COMPAT iff
+ * forbid_cmsg_compat==false
+ */
+extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg,
+			  unsigned int flags, bool forbid_cmsg_compat);
+extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg,
+			  unsigned int flags, bool forbid_cmsg_compat);
+extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg,
+			  unsigned int vlen, unsigned int flags,
+			  struct __kernel_timespec __user *timeout,
+			  struct old_timespec32 __user *timeout32);
+extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
+			  unsigned int vlen, unsigned int flags,
+			  bool forbid_cmsg_compat);
+extern long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg,
+			       unsigned int flags);
+extern long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg,
+			       struct user_msghdr __user *umsg,
+			       struct sockaddr __user *uaddr,
+			       unsigned int flags);
+extern int sendmsg_copy_msghdr(struct msghdr *msg,
+			       struct user_msghdr __user *umsg, unsigned flags,
+			       struct iovec **iov);
+extern int recvmsg_copy_msghdr(struct msghdr *msg,
+			       struct user_msghdr __user *umsg, unsigned flags,
+			       struct sockaddr __user **uaddr,
+			       struct iovec **iov);
+extern int __copy_msghdr_from_user(struct msghdr *kmsg,
+				   struct user_msghdr __user *umsg,
+				   struct sockaddr __user **save_addr,
+				   struct iovec __user **uiov, size_t *nsegs);
+
+/* helpers which do the actual work for syscalls */
+extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
+			  unsigned int flags, struct sockaddr __user *addr,
+			  int __user *addr_len);
+extern int __sys_sendto(int fd, void __user *buff, size_t len,
+			unsigned int flags, struct sockaddr __user *addr,
+			int addr_len);
+extern int __sys_accept4_file(struct file *file, unsigned file_flags,
+			struct sockaddr __user *upeer_sockaddr,
+			 int __user *upeer_addrlen, int flags,
+			 unsigned long nofile);
+extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
+			 int __user *upeer_addrlen, int flags);
+extern int __sys_socket(int family, int type, int protocol);
+extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, 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_getsockname(int fd, struct sockaddr __user *usockaddr,
+			     int __user *usockaddr_len);
+extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
+			     int __user *usockaddr_len);
+extern int __sys_socketpair(int family, int type, int protocol,
+			    int __user *usockvec);
+extern int __sys_shutdown(int fd, int how);
+
+extern struct ns_common *get_net_ns(struct ns_common *ns);
+#endif /* _LINUX_SOCKET_H */

tools/perf/trace/beauty/socket.sh

+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+# This one uses a copy from the kernel sources headers that is in a
+# place used just for these tools/perf/beauty/ usage, we shouldn't not
+# put it in tools/include/linux otherwise they would be used in the
+# normal compiler building process and would drag needless stuff from the
+# kernel.
+
+# When what these scripts need is already in tools/include/ then use it,
+# otherwise grab and check the copy from the kernel sources just for these
+# string table building scripts.
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/linux/
+
+printf "static const char *socket_families[] = {\n"
+# #define AF_LOCAL	1	/* POSIX name for AF_UNIX	*/
+regex='^#define[[:space:]]+AF_(\w+)[[:space:]]+([[:digit:]]+).*'
+
+egrep $regex ${header_dir}/socket.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[%s] = \"%s\",\n" | \
+	egrep -v "\"(UNIX|MAX)\""
+printf "};\n"