Resguardo inicial

linux-7.2.3/tools/perf/arch/x86/Build

@@ -0,0 +1,15 @@
+perf-util-y += util/
+perf-test-y += tests/
+
+ifdef SHELLCHECK
+  SHELL_TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  SHELL_TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)$(SHELLCHECK) "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-test-y += $(SHELL_TEST_LOGS)

linux-7.2.3/tools/perf/arch/x86/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+PERF_HAVE_JITDUMP := 1

linux-7.2.3/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl

@@ -0,0 +1,479 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# 32-bit system call numbers and entry vectors
+#
+# The format is:
+# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
+#
+# The __ia32_sys and __ia32_compat_sys stubs are created on-the-fly for
+# sys_*() system calls and compat_sys_*() compat system calls if
+# IA32_EMULATION is defined, and expect struct pt_regs *regs as their only
+# parameter.
+#
+# The abi is always "i386" for this file.
+#
+0	i386	restart_syscall		sys_restart_syscall
+1	i386	exit			sys_exit			-			noreturn
+2	i386	fork			sys_fork
+3	i386	read			sys_read
+4	i386	write			sys_write
+5	i386	open			sys_open			compat_sys_open
+6	i386	close			sys_close
+7	i386	waitpid			sys_waitpid
+8	i386	creat			sys_creat
+9	i386	link			sys_link
+10	i386	unlink			sys_unlink
+11	i386	execve			sys_execve			compat_sys_execve
+12	i386	chdir			sys_chdir
+13	i386	time			sys_time32
+14	i386	mknod			sys_mknod
+15	i386	chmod			sys_chmod
+16	i386	lchown			sys_lchown16
+17	i386	break
+18	i386	oldstat			sys_stat
+19	i386	lseek			sys_lseek			compat_sys_lseek
+20	i386	getpid			sys_getpid
+21	i386	mount			sys_mount
+22	i386	umount			sys_oldumount
+23	i386	setuid			sys_setuid16
+24	i386	getuid			sys_getuid16
+25	i386	stime			sys_stime32
+26	i386	ptrace			sys_ptrace			compat_sys_ptrace
+27	i386	alarm			sys_alarm
+28	i386	oldfstat		sys_fstat
+29	i386	pause			sys_pause
+30	i386	utime			sys_utime32
+31	i386	stty
+32	i386	gtty
+33	i386	access			sys_access
+34	i386	nice			sys_nice
+35	i386	ftime
+36	i386	sync			sys_sync
+37	i386	kill			sys_kill
+38	i386	rename			sys_rename
+39	i386	mkdir			sys_mkdir
+40	i386	rmdir			sys_rmdir
+41	i386	dup			sys_dup
+42	i386	pipe			sys_pipe
+43	i386	times			sys_times			compat_sys_times
+44	i386	prof
+45	i386	brk			sys_brk
+46	i386	setgid			sys_setgid16
+47	i386	getgid			sys_getgid16
+48	i386	signal			sys_signal
+49	i386	geteuid			sys_geteuid16
+50	i386	getegid			sys_getegid16
+51	i386	acct			sys_acct
+52	i386	umount2			sys_umount
+53	i386	lock
+54	i386	ioctl			sys_ioctl			compat_sys_ioctl
+55	i386	fcntl			sys_fcntl			compat_sys_fcntl64
+56	i386	mpx
+57	i386	setpgid			sys_setpgid
+58	i386	ulimit
+59	i386	oldolduname		sys_olduname
+60	i386	umask			sys_umask
+61	i386	chroot			sys_chroot
+62	i386	ustat			sys_ustat			compat_sys_ustat
+63	i386	dup2			sys_dup2
+64	i386	getppid			sys_getppid
+65	i386	getpgrp			sys_getpgrp
+66	i386	setsid			sys_setsid
+67	i386	sigaction		sys_sigaction			compat_sys_sigaction
+68	i386	sgetmask		sys_sgetmask
+69	i386	ssetmask		sys_ssetmask
+70	i386	setreuid		sys_setreuid16
+71	i386	setregid		sys_setregid16
+72	i386	sigsuspend		sys_sigsuspend
+73	i386	sigpending		sys_sigpending			compat_sys_sigpending
+74	i386	sethostname		sys_sethostname
+75	i386	setrlimit		sys_setrlimit			compat_sys_setrlimit
+76	i386	getrlimit		sys_old_getrlimit		compat_sys_old_getrlimit
+77	i386	getrusage		sys_getrusage			compat_sys_getrusage
+78	i386	gettimeofday		sys_gettimeofday		compat_sys_gettimeofday
+79	i386	settimeofday		sys_settimeofday		compat_sys_settimeofday
+80	i386	getgroups		sys_getgroups16
+81	i386	setgroups		sys_setgroups16
+82	i386	select			sys_old_select			compat_sys_old_select
+83	i386	symlink			sys_symlink
+84	i386	oldlstat		sys_lstat
+85	i386	readlink		sys_readlink
+86	i386	uselib			sys_uselib
+87	i386	swapon			sys_swapon
+88	i386	reboot			sys_reboot
+89	i386	readdir			sys_old_readdir			compat_sys_old_readdir
+90	i386	mmap			sys_old_mmap			compat_sys_ia32_mmap
+91	i386	munmap			sys_munmap
+92	i386	truncate		sys_truncate			compat_sys_truncate
+93	i386	ftruncate		sys_ftruncate			compat_sys_ftruncate
+94	i386	fchmod			sys_fchmod
+95	i386	fchown			sys_fchown16
+96	i386	getpriority		sys_getpriority
+97	i386	setpriority		sys_setpriority
+98	i386	profil
+99	i386	statfs			sys_statfs			compat_sys_statfs
+100	i386	fstatfs			sys_fstatfs			compat_sys_fstatfs
+101	i386	ioperm			sys_ioperm
+102	i386	socketcall		sys_socketcall			compat_sys_socketcall
+103	i386	syslog			sys_syslog
+104	i386	setitimer		sys_setitimer			compat_sys_setitimer
+105	i386	getitimer		sys_getitimer			compat_sys_getitimer
+106	i386	stat			sys_newstat			compat_sys_newstat
+107	i386	lstat			sys_newlstat			compat_sys_newlstat
+108	i386	fstat			sys_newfstat			compat_sys_newfstat
+109	i386	olduname		sys_uname
+110	i386	iopl			sys_iopl
+111	i386	vhangup			sys_vhangup
+112	i386	idle
+113	i386	vm86old			sys_vm86old			sys_ni_syscall
+114	i386	wait4			sys_wait4			compat_sys_wait4
+115	i386	swapoff			sys_swapoff
+116	i386	sysinfo			sys_sysinfo			compat_sys_sysinfo
+117	i386	ipc			sys_ipc				compat_sys_ipc
+118	i386	fsync			sys_fsync
+119	i386	sigreturn		sys_sigreturn			compat_sys_sigreturn
+120	i386	clone			sys_clone			compat_sys_ia32_clone
+121	i386	setdomainname		sys_setdomainname
+122	i386	uname			sys_newuname
+123	i386	modify_ldt		sys_modify_ldt
+124	i386	adjtimex		sys_adjtimex_time32
+125	i386	mprotect		sys_mprotect
+126	i386	sigprocmask		sys_sigprocmask			compat_sys_sigprocmask
+127	i386	create_module
+128	i386	init_module		sys_init_module
+129	i386	delete_module		sys_delete_module
+130	i386	get_kernel_syms
+131	i386	quotactl		sys_quotactl
+132	i386	getpgid			sys_getpgid
+133	i386	fchdir			sys_fchdir
+134	i386	bdflush			sys_ni_syscall
+135	i386	sysfs			sys_sysfs
+136	i386	personality		sys_personality
+137	i386	afs_syscall
+138	i386	setfsuid		sys_setfsuid16
+139	i386	setfsgid		sys_setfsgid16
+140	i386	_llseek			sys_llseek
+141	i386	getdents		sys_getdents			compat_sys_getdents
+142	i386	_newselect		sys_select			compat_sys_select
+143	i386	flock			sys_flock
+144	i386	msync			sys_msync
+145	i386	readv			sys_readv
+146	i386	writev			sys_writev
+147	i386	getsid			sys_getsid
+148	i386	fdatasync		sys_fdatasync
+149	i386	_sysctl			sys_ni_syscall
+150	i386	mlock			sys_mlock
+151	i386	munlock			sys_munlock
+152	i386	mlockall		sys_mlockall
+153	i386	munlockall		sys_munlockall
+154	i386	sched_setparam		sys_sched_setparam
+155	i386	sched_getparam		sys_sched_getparam
+156	i386	sched_setscheduler	sys_sched_setscheduler
+157	i386	sched_getscheduler	sys_sched_getscheduler
+158	i386	sched_yield		sys_sched_yield
+159	i386	sched_get_priority_max	sys_sched_get_priority_max
+160	i386	sched_get_priority_min	sys_sched_get_priority_min
+161	i386	sched_rr_get_interval	sys_sched_rr_get_interval_time32
+162	i386	nanosleep		sys_nanosleep_time32
+163	i386	mremap			sys_mremap
+164	i386	setresuid		sys_setresuid16
+165	i386	getresuid		sys_getresuid16
+166	i386	vm86			sys_vm86			sys_ni_syscall
+167	i386	query_module
+168	i386	poll			sys_poll
+169	i386	nfsservctl
+170	i386	setresgid		sys_setresgid16
+171	i386	getresgid		sys_getresgid16
+172	i386	prctl			sys_prctl
+173	i386	rt_sigreturn		sys_rt_sigreturn		compat_sys_rt_sigreturn
+174	i386	rt_sigaction		sys_rt_sigaction		compat_sys_rt_sigaction
+175	i386	rt_sigprocmask		sys_rt_sigprocmask		compat_sys_rt_sigprocmask
+176	i386	rt_sigpending		sys_rt_sigpending		compat_sys_rt_sigpending
+177	i386	rt_sigtimedwait		sys_rt_sigtimedwait_time32	compat_sys_rt_sigtimedwait_time32
+178	i386	rt_sigqueueinfo		sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
+179	i386	rt_sigsuspend		sys_rt_sigsuspend		compat_sys_rt_sigsuspend
+180	i386	pread64			sys_ia32_pread64
+181	i386	pwrite64		sys_ia32_pwrite64
+182	i386	chown			sys_chown16
+183	i386	getcwd			sys_getcwd
+184	i386	capget			sys_capget
+185	i386	capset			sys_capset
+186	i386	sigaltstack		sys_sigaltstack			compat_sys_sigaltstack
+187	i386	sendfile		sys_sendfile			compat_sys_sendfile
+188	i386	getpmsg
+189	i386	putpmsg
+190	i386	vfork			sys_vfork
+191	i386	ugetrlimit		sys_getrlimit			compat_sys_getrlimit
+192	i386	mmap2			sys_mmap_pgoff
+193	i386	truncate64		sys_ia32_truncate64
+194	i386	ftruncate64		sys_ia32_ftruncate64
+195	i386	stat64			sys_stat64			compat_sys_ia32_stat64
+196	i386	lstat64			sys_lstat64			compat_sys_ia32_lstat64
+197	i386	fstat64			sys_fstat64			compat_sys_ia32_fstat64
+198	i386	lchown32		sys_lchown
+199	i386	getuid32		sys_getuid
+200	i386	getgid32		sys_getgid
+201	i386	geteuid32		sys_geteuid
+202	i386	getegid32		sys_getegid
+203	i386	setreuid32		sys_setreuid
+204	i386	setregid32		sys_setregid
+205	i386	getgroups32		sys_getgroups
+206	i386	setgroups32		sys_setgroups
+207	i386	fchown32		sys_fchown
+208	i386	setresuid32		sys_setresuid
+209	i386	getresuid32		sys_getresuid
+210	i386	setresgid32		sys_setresgid
+211	i386	getresgid32		sys_getresgid
+212	i386	chown32			sys_chown
+213	i386	setuid32		sys_setuid
+214	i386	setgid32		sys_setgid
+215	i386	setfsuid32		sys_setfsuid
+216	i386	setfsgid32		sys_setfsgid
+217	i386	pivot_root		sys_pivot_root
+218	i386	mincore			sys_mincore
+219	i386	madvise			sys_madvise
+220	i386	getdents64		sys_getdents64
+221	i386	fcntl64			sys_fcntl64			compat_sys_fcntl64
+# 222 is unused
+# 223 is unused
+224	i386	gettid			sys_gettid
+225	i386	readahead		sys_ia32_readahead
+226	i386	setxattr		sys_setxattr
+227	i386	lsetxattr		sys_lsetxattr
+228	i386	fsetxattr		sys_fsetxattr
+229	i386	getxattr		sys_getxattr
+230	i386	lgetxattr		sys_lgetxattr
+231	i386	fgetxattr		sys_fgetxattr
+232	i386	listxattr		sys_listxattr
+233	i386	llistxattr		sys_llistxattr
+234	i386	flistxattr		sys_flistxattr
+235	i386	removexattr		sys_removexattr
+236	i386	lremovexattr		sys_lremovexattr
+237	i386	fremovexattr		sys_fremovexattr
+238	i386	tkill			sys_tkill
+239	i386	sendfile64		sys_sendfile64
+240	i386	futex			sys_futex_time32
+241	i386	sched_setaffinity	sys_sched_setaffinity		compat_sys_sched_setaffinity
+242	i386	sched_getaffinity	sys_sched_getaffinity		compat_sys_sched_getaffinity
+243	i386	set_thread_area		sys_set_thread_area
+244	i386	get_thread_area		sys_get_thread_area
+245	i386	io_setup		sys_io_setup			compat_sys_io_setup
+246	i386	io_destroy		sys_io_destroy
+247	i386	io_getevents		sys_io_getevents_time32
+248	i386	io_submit		sys_io_submit			compat_sys_io_submit
+249	i386	io_cancel		sys_io_cancel
+250	i386	fadvise64		sys_ia32_fadvise64
+# 251 is available for reuse (was briefly sys_set_zone_reclaim)
+252	i386	exit_group		sys_exit_group			-			noreturn
+253	i386	lookup_dcookie
+254	i386	epoll_create		sys_epoll_create
+255	i386	epoll_ctl		sys_epoll_ctl
+256	i386	epoll_wait		sys_epoll_wait
+257	i386	remap_file_pages	sys_remap_file_pages
+258	i386	set_tid_address		sys_set_tid_address
+259	i386	timer_create		sys_timer_create		compat_sys_timer_create
+260	i386	timer_settime		sys_timer_settime32
+261	i386	timer_gettime		sys_timer_gettime32
+262	i386	timer_getoverrun	sys_timer_getoverrun
+263	i386	timer_delete		sys_timer_delete
+264	i386	clock_settime		sys_clock_settime32
+265	i386	clock_gettime		sys_clock_gettime32
+266	i386	clock_getres		sys_clock_getres_time32
+267	i386	clock_nanosleep		sys_clock_nanosleep_time32
+268	i386	statfs64		sys_statfs64			compat_sys_statfs64
+269	i386	fstatfs64		sys_fstatfs64			compat_sys_fstatfs64
+270	i386	tgkill			sys_tgkill
+271	i386	utimes			sys_utimes_time32
+272	i386	fadvise64_64		sys_ia32_fadvise64_64
+273	i386	vserver
+274	i386	mbind			sys_mbind
+275	i386	get_mempolicy		sys_get_mempolicy
+276	i386	set_mempolicy		sys_set_mempolicy
+277	i386	mq_open			sys_mq_open			compat_sys_mq_open
+278	i386	mq_unlink		sys_mq_unlink
+279	i386	mq_timedsend		sys_mq_timedsend_time32
+280	i386	mq_timedreceive		sys_mq_timedreceive_time32
+281	i386	mq_notify		sys_mq_notify			compat_sys_mq_notify
+282	i386	mq_getsetattr		sys_mq_getsetattr		compat_sys_mq_getsetattr
+283	i386	kexec_load		sys_kexec_load			compat_sys_kexec_load
+284	i386	waitid			sys_waitid			compat_sys_waitid
+# 285 sys_setaltroot
+286	i386	add_key			sys_add_key
+287	i386	request_key		sys_request_key
+288	i386	keyctl			sys_keyctl			compat_sys_keyctl
+289	i386	ioprio_set		sys_ioprio_set
+290	i386	ioprio_get		sys_ioprio_get
+291	i386	inotify_init		sys_inotify_init
+292	i386	inotify_add_watch	sys_inotify_add_watch
+293	i386	inotify_rm_watch	sys_inotify_rm_watch
+294	i386	migrate_pages		sys_migrate_pages
+295	i386	openat			sys_openat			compat_sys_openat
+296	i386	mkdirat			sys_mkdirat
+297	i386	mknodat			sys_mknodat
+298	i386	fchownat		sys_fchownat
+299	i386	futimesat		sys_futimesat_time32
+300	i386	fstatat64		sys_fstatat64			compat_sys_ia32_fstatat64
+301	i386	unlinkat		sys_unlinkat
+302	i386	renameat		sys_renameat
+303	i386	linkat			sys_linkat
+304	i386	symlinkat		sys_symlinkat
+305	i386	readlinkat		sys_readlinkat
+306	i386	fchmodat		sys_fchmodat
+307	i386	faccessat		sys_faccessat
+308	i386	pselect6		sys_pselect6_time32		compat_sys_pselect6_time32
+309	i386	ppoll			sys_ppoll_time32		compat_sys_ppoll_time32
+310	i386	unshare			sys_unshare
+311	i386	set_robust_list		sys_set_robust_list		compat_sys_set_robust_list
+312	i386	get_robust_list		sys_get_robust_list		compat_sys_get_robust_list
+313	i386	splice			sys_splice
+314	i386	sync_file_range		sys_ia32_sync_file_range
+315	i386	tee			sys_tee
+316	i386	vmsplice		sys_vmsplice
+317	i386	move_pages		sys_move_pages
+318	i386	getcpu			sys_getcpu
+319	i386	epoll_pwait		sys_epoll_pwait
+320	i386	utimensat		sys_utimensat_time32
+321	i386	signalfd		sys_signalfd			compat_sys_signalfd
+322	i386	timerfd_create		sys_timerfd_create
+323	i386	eventfd			sys_eventfd
+324	i386	fallocate		sys_ia32_fallocate
+325	i386	timerfd_settime		sys_timerfd_settime32
+326	i386	timerfd_gettime		sys_timerfd_gettime32
+327	i386	signalfd4		sys_signalfd4			compat_sys_signalfd4
+328	i386	eventfd2		sys_eventfd2
+329	i386	epoll_create1		sys_epoll_create1
+330	i386	dup3			sys_dup3
+331	i386	pipe2			sys_pipe2
+332	i386	inotify_init1		sys_inotify_init1
+333	i386	preadv			sys_preadv			compat_sys_preadv
+334	i386	pwritev			sys_pwritev			compat_sys_pwritev
+335	i386	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo		compat_sys_rt_tgsigqueueinfo
+336	i386	perf_event_open		sys_perf_event_open
+337	i386	recvmmsg		sys_recvmmsg_time32		compat_sys_recvmmsg_time32
+338	i386	fanotify_init		sys_fanotify_init
+339	i386	fanotify_mark		sys_fanotify_mark		compat_sys_fanotify_mark
+340	i386	prlimit64		sys_prlimit64
+341	i386	name_to_handle_at	sys_name_to_handle_at
+342	i386	open_by_handle_at	sys_open_by_handle_at		compat_sys_open_by_handle_at
+343	i386	clock_adjtime		sys_clock_adjtime32
+344	i386	syncfs			sys_syncfs
+345	i386	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
+346	i386	setns			sys_setns
+347	i386	process_vm_readv	sys_process_vm_readv
+348	i386	process_vm_writev	sys_process_vm_writev
+349	i386	kcmp			sys_kcmp
+350	i386	finit_module		sys_finit_module
+351	i386	sched_setattr		sys_sched_setattr
+352	i386	sched_getattr		sys_sched_getattr
+353	i386	renameat2		sys_renameat2
+354	i386	seccomp			sys_seccomp
+355	i386	getrandom		sys_getrandom
+356	i386	memfd_create		sys_memfd_create
+357	i386	bpf			sys_bpf
+358	i386	execveat		sys_execveat			compat_sys_execveat
+359	i386	socket			sys_socket
+360	i386	socketpair		sys_socketpair
+361	i386	bind			sys_bind
+362	i386	connect			sys_connect
+363	i386	listen			sys_listen
+364	i386	accept4			sys_accept4
+365	i386	getsockopt		sys_getsockopt			sys_getsockopt
+366	i386	setsockopt		sys_setsockopt			sys_setsockopt
+367	i386	getsockname		sys_getsockname
+368	i386	getpeername		sys_getpeername
+369	i386	sendto			sys_sendto
+370	i386	sendmsg			sys_sendmsg			compat_sys_sendmsg
+371	i386	recvfrom		sys_recvfrom			compat_sys_recvfrom
+372	i386	recvmsg			sys_recvmsg			compat_sys_recvmsg
+373	i386	shutdown		sys_shutdown
+374	i386	userfaultfd		sys_userfaultfd
+375	i386	membarrier		sys_membarrier
+376	i386	mlock2			sys_mlock2
+377	i386	copy_file_range		sys_copy_file_range
+378	i386	preadv2			sys_preadv2			compat_sys_preadv2
+379	i386	pwritev2		sys_pwritev2			compat_sys_pwritev2
+380	i386	pkey_mprotect		sys_pkey_mprotect
+381	i386	pkey_alloc		sys_pkey_alloc
+382	i386	pkey_free		sys_pkey_free
+383	i386	statx			sys_statx
+384	i386	arch_prctl		sys_arch_prctl
+385	i386	io_pgetevents		sys_io_pgetevents_time32	compat_sys_io_pgetevents
+386	i386	rseq			sys_rseq
+393	i386	semget			sys_semget
+394	i386	semctl			sys_semctl    			compat_sys_semctl
+395	i386	shmget			sys_shmget
+396	i386	shmctl			sys_shmctl    			compat_sys_shmctl
+397	i386	shmat			sys_shmat     			compat_sys_shmat
+398	i386	shmdt			sys_shmdt
+399	i386	msgget			sys_msgget
+400	i386	msgsnd			sys_msgsnd    			compat_sys_msgsnd
+401	i386	msgrcv			sys_msgrcv    			compat_sys_msgrcv
+402	i386	msgctl			sys_msgctl    			compat_sys_msgctl
+403	i386	clock_gettime64		sys_clock_gettime
+404	i386	clock_settime64		sys_clock_settime
+405	i386	clock_adjtime64		sys_clock_adjtime
+406	i386	clock_getres_time64	sys_clock_getres
+407	i386	clock_nanosleep_time64	sys_clock_nanosleep
+408	i386	timer_gettime64		sys_timer_gettime
+409	i386	timer_settime64		sys_timer_settime
+410	i386	timerfd_gettime64	sys_timerfd_gettime
+411	i386	timerfd_settime64	sys_timerfd_settime
+412	i386	utimensat_time64	sys_utimensat
+413	i386	pselect6_time64		sys_pselect6			compat_sys_pselect6_time64
+414	i386	ppoll_time64		sys_ppoll			compat_sys_ppoll_time64
+416	i386	io_pgetevents_time64	sys_io_pgetevents		compat_sys_io_pgetevents_time64
+417	i386	recvmmsg_time64		sys_recvmmsg			compat_sys_recvmmsg_time64
+418	i386	mq_timedsend_time64	sys_mq_timedsend
+419	i386	mq_timedreceive_time64	sys_mq_timedreceive
+420	i386	semtimedop_time64	sys_semtimedop
+421	i386	rt_sigtimedwait_time64	sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait_time64
+422	i386	futex_time64		sys_futex
+423	i386	sched_rr_get_interval_time64	sys_sched_rr_get_interval
+424	i386	pidfd_send_signal	sys_pidfd_send_signal
+425	i386	io_uring_setup		sys_io_uring_setup
+426	i386	io_uring_enter		sys_io_uring_enter
+427	i386	io_uring_register	sys_io_uring_register
+428	i386	open_tree		sys_open_tree
+429	i386	move_mount		sys_move_mount
+430	i386	fsopen			sys_fsopen
+431	i386	fsconfig		sys_fsconfig
+432	i386	fsmount			sys_fsmount
+433	i386	fspick			sys_fspick
+434	i386	pidfd_open		sys_pidfd_open
+435	i386	clone3			sys_clone3
+436	i386	close_range		sys_close_range
+437	i386	openat2			sys_openat2
+438	i386	pidfd_getfd		sys_pidfd_getfd
+439	i386	faccessat2		sys_faccessat2
+440	i386	process_madvise		sys_process_madvise
+441	i386	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
+442	i386	mount_setattr		sys_mount_setattr
+443	i386	quotactl_fd		sys_quotactl_fd
+444	i386	landlock_create_ruleset	sys_landlock_create_ruleset
+445	i386	landlock_add_rule	sys_landlock_add_rule
+446	i386	landlock_restrict_self	sys_landlock_restrict_self
+447	i386	memfd_secret		sys_memfd_secret
+448	i386	process_mrelease	sys_process_mrelease
+449	i386	futex_waitv		sys_futex_waitv
+450	i386	set_mempolicy_home_node		sys_set_mempolicy_home_node
+451	i386	cachestat		sys_cachestat
+452	i386	fchmodat2		sys_fchmodat2
+453	i386	map_shadow_stack	sys_map_shadow_stack
+454	i386	futex_wake		sys_futex_wake
+455	i386	futex_wait		sys_futex_wait
+456	i386	futex_requeue		sys_futex_requeue
+457	i386	statmount		sys_statmount
+458	i386	listmount		sys_listmount
+459	i386	lsm_get_self_attr	sys_lsm_get_self_attr
+460	i386	lsm_set_self_attr	sys_lsm_set_self_attr
+461	i386	lsm_list_modules	sys_lsm_list_modules
+462	i386	mseal 			sys_mseal
+463	i386	setxattrat		sys_setxattrat
+464	i386	getxattrat		sys_getxattrat
+465	i386	listxattrat		sys_listxattrat
+466	i386	removexattrat		sys_removexattrat
+467	i386	open_tree_attr		sys_open_tree_attr
+468	i386	file_getattr		sys_file_getattr
+469	i386	file_setattr		sys_file_setattr
+470	i386	listns			sys_listns
+471	i386	rseq_slice_yield	sys_rseq_slice_yield

linux-7.2.3/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl

@@ -0,0 +1,443 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# 64-bit system call numbers and entry vectors
+#
+# The format is:
+# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
+#
+# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
+#
+# The abi is "common", "64" or "x32" for this file.
+#
+0	common	read			sys_read
+1	common	write			sys_write
+2	common	open			sys_open
+3	common	close			sys_close
+4	common	stat			sys_newstat
+5	common	fstat			sys_newfstat
+6	common	lstat			sys_newlstat
+7	common	poll			sys_poll
+8	common	lseek			sys_lseek
+9	common	mmap			sys_mmap
+10	common	mprotect		sys_mprotect
+11	common	munmap			sys_munmap
+12	common	brk			sys_brk
+13	64	rt_sigaction		sys_rt_sigaction
+14	common	rt_sigprocmask		sys_rt_sigprocmask
+15	64	rt_sigreturn		sys_rt_sigreturn
+16	64	ioctl			sys_ioctl
+17	common	pread64			sys_pread64
+18	common	pwrite64		sys_pwrite64
+19	64	readv			sys_readv
+20	64	writev			sys_writev
+21	common	access			sys_access
+22	common	pipe			sys_pipe
+23	common	select			sys_select
+24	common	sched_yield		sys_sched_yield
+25	common	mremap			sys_mremap
+26	common	msync			sys_msync
+27	common	mincore			sys_mincore
+28	common	madvise			sys_madvise
+29	common	shmget			sys_shmget
+30	common	shmat			sys_shmat
+31	common	shmctl			sys_shmctl
+32	common	dup			sys_dup
+33	common	dup2			sys_dup2
+34	common	pause			sys_pause
+35	common	nanosleep		sys_nanosleep
+36	common	getitimer		sys_getitimer
+37	common	alarm			sys_alarm
+38	common	setitimer		sys_setitimer
+39	common	getpid			sys_getpid
+40	common	sendfile		sys_sendfile64
+41	common	socket			sys_socket
+42	common	connect			sys_connect
+43	common	accept			sys_accept
+44	common	sendto			sys_sendto
+45	64	recvfrom		sys_recvfrom
+46	64	sendmsg			sys_sendmsg
+47	64	recvmsg			sys_recvmsg
+48	common	shutdown		sys_shutdown
+49	common	bind			sys_bind
+50	common	listen			sys_listen
+51	common	getsockname		sys_getsockname
+52	common	getpeername		sys_getpeername
+53	common	socketpair		sys_socketpair
+54	64	setsockopt		sys_setsockopt
+55	64	getsockopt		sys_getsockopt
+56	common	clone			sys_clone
+57	common	fork			sys_fork
+58	common	vfork			sys_vfork
+59	64	execve			sys_execve
+60	common	exit			sys_exit			-			noreturn
+61	common	wait4			sys_wait4
+62	common	kill			sys_kill
+63	common	uname			sys_newuname
+64	common	semget			sys_semget
+65	common	semop			sys_semop
+66	common	semctl			sys_semctl
+67	common	shmdt			sys_shmdt
+68	common	msgget			sys_msgget
+69	common	msgsnd			sys_msgsnd
+70	common	msgrcv			sys_msgrcv
+71	common	msgctl			sys_msgctl
+72	common	fcntl			sys_fcntl
+73	common	flock			sys_flock
+74	common	fsync			sys_fsync
+75	common	fdatasync		sys_fdatasync
+76	common	truncate		sys_truncate
+77	common	ftruncate		sys_ftruncate
+78	common	getdents		sys_getdents
+79	common	getcwd			sys_getcwd
+80	common	chdir			sys_chdir
+81	common	fchdir			sys_fchdir
+82	common	rename			sys_rename
+83	common	mkdir			sys_mkdir
+84	common	rmdir			sys_rmdir
+85	common	creat			sys_creat
+86	common	link			sys_link
+87	common	unlink			sys_unlink
+88	common	symlink			sys_symlink
+89	common	readlink		sys_readlink
+90	common	chmod			sys_chmod
+91	common	fchmod			sys_fchmod
+92	common	chown			sys_chown
+93	common	fchown			sys_fchown
+94	common	lchown			sys_lchown
+95	common	umask			sys_umask
+96	common	gettimeofday		sys_gettimeofday
+97	common	getrlimit		sys_getrlimit
+98	common	getrusage		sys_getrusage
+99	common	sysinfo			sys_sysinfo
+100	common	times			sys_times
+101	64	ptrace			sys_ptrace
+102	common	getuid			sys_getuid
+103	common	syslog			sys_syslog
+104	common	getgid			sys_getgid
+105	common	setuid			sys_setuid
+106	common	setgid			sys_setgid
+107	common	geteuid			sys_geteuid
+108	common	getegid			sys_getegid
+109	common	setpgid			sys_setpgid
+110	common	getppid			sys_getppid
+111	common	getpgrp			sys_getpgrp
+112	common	setsid			sys_setsid
+113	common	setreuid		sys_setreuid
+114	common	setregid		sys_setregid
+115	common	getgroups		sys_getgroups
+116	common	setgroups		sys_setgroups
+117	common	setresuid		sys_setresuid
+118	common	getresuid		sys_getresuid
+119	common	setresgid		sys_setresgid
+120	common	getresgid		sys_getresgid
+121	common	getpgid			sys_getpgid
+122	common	setfsuid		sys_setfsuid
+123	common	setfsgid		sys_setfsgid
+124	common	getsid			sys_getsid
+125	common	capget			sys_capget
+126	common	capset			sys_capset
+127	64	rt_sigpending		sys_rt_sigpending
+128	64	rt_sigtimedwait		sys_rt_sigtimedwait
+129	64	rt_sigqueueinfo		sys_rt_sigqueueinfo
+130	common	rt_sigsuspend		sys_rt_sigsuspend
+131	64	sigaltstack		sys_sigaltstack
+132	common	utime			sys_utime
+133	common	mknod			sys_mknod
+134	64	uselib
+135	common	personality		sys_personality
+136	common	ustat			sys_ustat
+137	common	statfs			sys_statfs
+138	common	fstatfs			sys_fstatfs
+139	common	sysfs			sys_sysfs
+140	common	getpriority		sys_getpriority
+141	common	setpriority		sys_setpriority
+142	common	sched_setparam		sys_sched_setparam
+143	common	sched_getparam		sys_sched_getparam
+144	common	sched_setscheduler	sys_sched_setscheduler
+145	common	sched_getscheduler	sys_sched_getscheduler
+146	common	sched_get_priority_max	sys_sched_get_priority_max
+147	common	sched_get_priority_min	sys_sched_get_priority_min
+148	common	sched_rr_get_interval	sys_sched_rr_get_interval
+149	common	mlock			sys_mlock
+150	common	munlock			sys_munlock
+151	common	mlockall		sys_mlockall
+152	common	munlockall		sys_munlockall
+153	common	vhangup			sys_vhangup
+154	common	modify_ldt		sys_modify_ldt
+155	common	pivot_root		sys_pivot_root
+156	64	_sysctl			sys_ni_syscall
+157	common	prctl			sys_prctl
+158	common	arch_prctl		sys_arch_prctl
+159	common	adjtimex		sys_adjtimex
+160	common	setrlimit		sys_setrlimit
+161	common	chroot			sys_chroot
+162	common	sync			sys_sync
+163	common	acct			sys_acct
+164	common	settimeofday		sys_settimeofday
+165	common	mount			sys_mount
+166	common	umount2			sys_umount
+167	common	swapon			sys_swapon
+168	common	swapoff			sys_swapoff
+169	common	reboot			sys_reboot
+170	common	sethostname		sys_sethostname
+171	common	setdomainname		sys_setdomainname
+172	common	iopl			sys_iopl
+173	common	ioperm			sys_ioperm
+174	64	create_module
+175	common	init_module		sys_init_module
+176	common	delete_module		sys_delete_module
+177	64	get_kernel_syms
+178	64	query_module
+179	common	quotactl		sys_quotactl
+180	64	nfsservctl
+181	common	getpmsg
+182	common	putpmsg
+183	common	afs_syscall
+184	common	tuxcall
+185	common	security
+186	common	gettid			sys_gettid
+187	common	readahead		sys_readahead
+188	common	setxattr		sys_setxattr
+189	common	lsetxattr		sys_lsetxattr
+190	common	fsetxattr		sys_fsetxattr
+191	common	getxattr		sys_getxattr
+192	common	lgetxattr		sys_lgetxattr
+193	common	fgetxattr		sys_fgetxattr
+194	common	listxattr		sys_listxattr
+195	common	llistxattr		sys_llistxattr
+196	common	flistxattr		sys_flistxattr
+197	common	removexattr		sys_removexattr
+198	common	lremovexattr		sys_lremovexattr
+199	common	fremovexattr		sys_fremovexattr
+200	common	tkill			sys_tkill
+201	common	time			sys_time
+202	common	futex			sys_futex
+203	common	sched_setaffinity	sys_sched_setaffinity
+204	common	sched_getaffinity	sys_sched_getaffinity
+205	64	set_thread_area
+206	64	io_setup		sys_io_setup
+207	common	io_destroy		sys_io_destroy
+208	common	io_getevents		sys_io_getevents
+209	64	io_submit		sys_io_submit
+210	common	io_cancel		sys_io_cancel
+211	64	get_thread_area
+212	common	lookup_dcookie
+213	common	epoll_create		sys_epoll_create
+214	64	epoll_ctl_old
+215	64	epoll_wait_old
+216	common	remap_file_pages	sys_remap_file_pages
+217	common	getdents64		sys_getdents64
+218	common	set_tid_address		sys_set_tid_address
+219	common	restart_syscall		sys_restart_syscall
+220	common	semtimedop		sys_semtimedop
+221	common	fadvise64		sys_fadvise64
+222	64	timer_create		sys_timer_create
+223	common	timer_settime		sys_timer_settime
+224	common	timer_gettime		sys_timer_gettime
+225	common	timer_getoverrun	sys_timer_getoverrun
+226	common	timer_delete		sys_timer_delete
+227	common	clock_settime		sys_clock_settime
+228	common	clock_gettime		sys_clock_gettime
+229	common	clock_getres		sys_clock_getres
+230	common	clock_nanosleep		sys_clock_nanosleep
+231	common	exit_group		sys_exit_group			-			noreturn
+232	common	epoll_wait		sys_epoll_wait
+233	common	epoll_ctl		sys_epoll_ctl
+234	common	tgkill			sys_tgkill
+235	common	utimes			sys_utimes
+236	64	vserver
+237	common	mbind			sys_mbind
+238	common	set_mempolicy		sys_set_mempolicy
+239	common	get_mempolicy		sys_get_mempolicy
+240	common	mq_open			sys_mq_open
+241	common	mq_unlink		sys_mq_unlink
+242	common	mq_timedsend		sys_mq_timedsend
+243	common	mq_timedreceive		sys_mq_timedreceive
+244	64	mq_notify		sys_mq_notify
+245	common	mq_getsetattr		sys_mq_getsetattr
+246	64	kexec_load		sys_kexec_load
+247	64	waitid			sys_waitid
+248	common	add_key			sys_add_key
+249	common	request_key		sys_request_key
+250	common	keyctl			sys_keyctl
+251	common	ioprio_set		sys_ioprio_set
+252	common	ioprio_get		sys_ioprio_get
+253	common	inotify_init		sys_inotify_init
+254	common	inotify_add_watch	sys_inotify_add_watch
+255	common	inotify_rm_watch	sys_inotify_rm_watch
+256	common	migrate_pages		sys_migrate_pages
+257	common	openat			sys_openat
+258	common	mkdirat			sys_mkdirat
+259	common	mknodat			sys_mknodat
+260	common	fchownat		sys_fchownat
+261	common	futimesat		sys_futimesat
+262	common	newfstatat		sys_newfstatat
+263	common	unlinkat		sys_unlinkat
+264	common	renameat		sys_renameat
+265	common	linkat			sys_linkat
+266	common	symlinkat		sys_symlinkat
+267	common	readlinkat		sys_readlinkat
+268	common	fchmodat		sys_fchmodat
+269	common	faccessat		sys_faccessat
+270	common	pselect6		sys_pselect6
+271	common	ppoll			sys_ppoll
+272	common	unshare			sys_unshare
+273	64	set_robust_list		sys_set_robust_list
+274	64	get_robust_list		sys_get_robust_list
+275	common	splice			sys_splice
+276	common	tee			sys_tee
+277	common	sync_file_range		sys_sync_file_range
+278	64	vmsplice		sys_vmsplice
+279	64	move_pages		sys_move_pages
+280	common	utimensat		sys_utimensat
+281	common	epoll_pwait		sys_epoll_pwait
+282	common	signalfd		sys_signalfd
+283	common	timerfd_create		sys_timerfd_create
+284	common	eventfd			sys_eventfd
+285	common	fallocate		sys_fallocate
+286	common	timerfd_settime		sys_timerfd_settime
+287	common	timerfd_gettime		sys_timerfd_gettime
+288	common	accept4			sys_accept4
+289	common	signalfd4		sys_signalfd4
+290	common	eventfd2		sys_eventfd2
+291	common	epoll_create1		sys_epoll_create1
+292	common	dup3			sys_dup3
+293	common	pipe2			sys_pipe2
+294	common	inotify_init1		sys_inotify_init1
+295	64	preadv			sys_preadv
+296	64	pwritev			sys_pwritev
+297	64	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo
+298	common	perf_event_open		sys_perf_event_open
+299	64	recvmmsg		sys_recvmmsg
+300	common	fanotify_init		sys_fanotify_init
+301	common	fanotify_mark		sys_fanotify_mark
+302	common	prlimit64		sys_prlimit64
+303	common	name_to_handle_at	sys_name_to_handle_at
+304	common	open_by_handle_at	sys_open_by_handle_at
+305	common	clock_adjtime		sys_clock_adjtime
+306	common	syncfs			sys_syncfs
+307	64	sendmmsg		sys_sendmmsg
+308	common	setns			sys_setns
+309	common	getcpu			sys_getcpu
+310	64	process_vm_readv	sys_process_vm_readv
+311	64	process_vm_writev	sys_process_vm_writev
+312	common	kcmp			sys_kcmp
+313	common	finit_module		sys_finit_module
+314	common	sched_setattr		sys_sched_setattr
+315	common	sched_getattr		sys_sched_getattr
+316	common	renameat2		sys_renameat2
+317	common	seccomp			sys_seccomp
+318	common	getrandom		sys_getrandom
+319	common	memfd_create		sys_memfd_create
+320	common	kexec_file_load		sys_kexec_file_load
+321	common	bpf			sys_bpf
+322	64	execveat		sys_execveat
+323	common	userfaultfd		sys_userfaultfd
+324	common	membarrier		sys_membarrier
+325	common	mlock2			sys_mlock2
+326	common	copy_file_range		sys_copy_file_range
+327	64	preadv2			sys_preadv2
+328	64	pwritev2		sys_pwritev2
+329	common	pkey_mprotect		sys_pkey_mprotect
+330	common	pkey_alloc		sys_pkey_alloc
+331	common	pkey_free		sys_pkey_free
+332	common	statx			sys_statx
+333	common	io_pgetevents		sys_io_pgetevents
+334	common	rseq			sys_rseq
+335	common	uretprobe		sys_uretprobe
+336	common	uprobe			sys_uprobe
+# don't use numbers 387 through 423, add new calls after the last
+# 'common' entry
+424	common	pidfd_send_signal	sys_pidfd_send_signal
+425	common	io_uring_setup		sys_io_uring_setup
+426	common	io_uring_enter		sys_io_uring_enter
+427	common	io_uring_register	sys_io_uring_register
+428	common	open_tree		sys_open_tree
+429	common	move_mount		sys_move_mount
+430	common	fsopen			sys_fsopen
+431	common	fsconfig		sys_fsconfig
+432	common	fsmount			sys_fsmount
+433	common	fspick			sys_fspick
+434	common	pidfd_open		sys_pidfd_open
+435	common	clone3			sys_clone3
+436	common	close_range		sys_close_range
+437	common	openat2			sys_openat2
+438	common	pidfd_getfd		sys_pidfd_getfd
+439	common	faccessat2		sys_faccessat2
+440	common	process_madvise		sys_process_madvise
+441	common	epoll_pwait2		sys_epoll_pwait2
+442	common	mount_setattr		sys_mount_setattr
+443	common	quotactl_fd		sys_quotactl_fd
+444	common	landlock_create_ruleset	sys_landlock_create_ruleset
+445	common	landlock_add_rule	sys_landlock_add_rule
+446	common	landlock_restrict_self	sys_landlock_restrict_self
+447	common	memfd_secret		sys_memfd_secret
+448	common	process_mrelease	sys_process_mrelease
+449	common	futex_waitv		sys_futex_waitv
+450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
+451	common	cachestat		sys_cachestat
+452	common	fchmodat2		sys_fchmodat2
+453	common	map_shadow_stack	sys_map_shadow_stack
+454	common	futex_wake		sys_futex_wake
+455	common	futex_wait		sys_futex_wait
+456	common	futex_requeue		sys_futex_requeue
+457	common	statmount		sys_statmount
+458	common	listmount		sys_listmount
+459	common	lsm_get_self_attr	sys_lsm_get_self_attr
+460	common	lsm_set_self_attr	sys_lsm_set_self_attr
+461	common	lsm_list_modules	sys_lsm_list_modules
+462 	common  mseal			sys_mseal
+463	common	setxattrat		sys_setxattrat
+464	common	getxattrat		sys_getxattrat
+465	common	listxattrat		sys_listxattrat
+466	common	removexattrat		sys_removexattrat
+467	common	open_tree_attr		sys_open_tree_attr
+468	common	file_getattr		sys_file_getattr
+469	common	file_setattr		sys_file_setattr
+470	common	listns			sys_listns
+471	common	rseq_slice_yield	sys_rseq_slice_yield
+
+#
+# Due to a historical design error, certain syscalls are numbered differently
+# in x32 as compared to native x86_64.  These syscalls have numbers 512-547.
+# Do not add new syscalls to this range.  Numbers 548 and above are available
+# for non-x32 use.
+#
+512	x32	rt_sigaction		compat_sys_rt_sigaction
+513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
+514	x32	ioctl			compat_sys_ioctl
+515	x32	readv			sys_readv
+516	x32	writev			sys_writev
+517	x32	recvfrom		compat_sys_recvfrom
+518	x32	sendmsg			compat_sys_sendmsg
+519	x32	recvmsg			compat_sys_recvmsg
+520	x32	execve			compat_sys_execve
+521	x32	ptrace			compat_sys_ptrace
+522	x32	rt_sigpending		compat_sys_rt_sigpending
+523	x32	rt_sigtimedwait		compat_sys_rt_sigtimedwait_time64
+524	x32	rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
+525	x32	sigaltstack		compat_sys_sigaltstack
+526	x32	timer_create		compat_sys_timer_create
+527	x32	mq_notify		compat_sys_mq_notify
+528	x32	kexec_load		compat_sys_kexec_load
+529	x32	waitid			compat_sys_waitid
+530	x32	set_robust_list		compat_sys_set_robust_list
+531	x32	get_robust_list		compat_sys_get_robust_list
+532	x32	vmsplice		sys_vmsplice
+533	x32	move_pages		sys_move_pages
+534	x32	preadv			compat_sys_preadv64
+535	x32	pwritev			compat_sys_pwritev64
+536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
+537	x32	recvmmsg		compat_sys_recvmmsg_time64
+538	x32	sendmmsg		compat_sys_sendmmsg
+539	x32	process_vm_readv	sys_process_vm_readv
+540	x32	process_vm_writev	sys_process_vm_writev
+541	x32	setsockopt		sys_setsockopt
+542	x32	getsockopt		sys_getsockopt
+543	x32	io_setup		compat_sys_io_setup
+544	x32	io_submit		compat_sys_io_submit
+545	x32	execveat		compat_sys_execveat
+546	x32	preadv2			compat_sys_preadv64v2
+547	x32	pwritev2		compat_sys_pwritev64v2
+# This is the end of the legacy x32 range.  Numbers 548 and above are
+# not special and are not to be used for x32-specific syscalls.

linux-7.2.3/tools/perf/arch/x86/include/arch-tests.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#include "tests/tests.h"
+
+struct test_suite;
+
+/* Tests */
+int test__rdpmc(struct test_suite *test, int subtest);
+#ifdef HAVE_EXTRA_TESTS
+int test__insn_x86(struct test_suite *test, int subtest);
+#endif
+int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest);
+int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest);
+int test__bp_modify(struct test_suite *test, int subtest);
+int test__amd_ibs_via_core_pmu(struct test_suite *test, int subtest);
+int test__amd_ibs_period(struct test_suite *test, int subtest);
+int test__hybrid(struct test_suite *test, int subtest);
+
+DECLARE_SUITE(x86_topdown);
+
+extern struct test_suite *arch_tests[];
+
+#endif

linux-7.2.3/tools/perf/arch/x86/include/dwarf-regs-table.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifdef DEFINE_DWARF_REGSTR_TABLE
+/* This is included in perf/util/dwarf-regs.c */
+
+static const char * const x86_32_regstr_tbl[] = {
+	"%ax", "%cx", "%dx", "%bx", "$stack",/* Stack address instead of %sp */
+	"%bp", "%si", "%di",
+};
+
+static const char * const x86_64_regstr_tbl[] = {
+	"%ax", "%dx", "%cx", "%bx", "%si", "%di",
+	"%bp", "%sp", "%r8", "%r9", "%r10", "%r11",
+	"%r12", "%r13", "%r14", "%r15",
+};
+#endif

linux-7.2.3/tools/perf/arch/x86/include/perf_regs.h

@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include "../../../../arch/x86/include/uapi/asm/perf_regs.h"
+
+void perf_regs_load(u64 *regs);
+
+#define PERF_REGS_MAX PERF_REG_X86_XMM_MAX
+#ifndef HAVE_ARCH_X86_64_SUPPORT
+#define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
+#else
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+		       (1ULL << PERF_REG_X86_ES) | \
+		       (1ULL << PERF_REG_X86_FS) | \
+		       (1ULL << PERF_REG_X86_GS))
+#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
+#endif
+
+#endif /* ARCH_PERF_REGS_H */

linux-7.2.3/tools/perf/arch/x86/tests/Build

@@ -0,0 +1,27 @@
+perf-test-$(CONFIG_DWARF_UNWIND) += regs_load.o
+perf-test-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
+
+perf-test-y += arch-tests.o
+perf-test-y += hybrid.o
+perf-test-y += intel-pt-test.o
+ifeq ($(CONFIG_EXTRA_TESTS),y)
+perf-test-y += insn-x86.o
+endif
+perf-test-$(CONFIG_X86_64) += bp-modify.o
+perf-test-y += amd-ibs-via-core-pmu.o
+perf-test-y += amd-ibs-period.o
+perf-test-y += topdown.o
+
+ifdef SHELLCHECK
+  SHELL_TESTS := gen-insn-x86-dat.sh
+  SHELL_TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  SHELL_TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)$(SHELLCHECK) "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-test-y += $(SHELL_TEST_LOGS)

linux-7.2.3/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c

@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "arch-tests.h"
+#include "linux/perf_event.h"
+#include "tests/tests.h"
+#include "pmu.h"
+#include "pmus.h"
+#include "../perf-sys.h"
+#include "debug.h"
+
+#define NR_SUB_TESTS 5
+
+static struct sub_tests {
+	int type;
+	unsigned long config;
+	bool valid;
+} sub_tests[NR_SUB_TESTS] = {
+	{ PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES, true },
+	{ PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, false },
+	{ PERF_TYPE_RAW, 0x076, true },
+	{ PERF_TYPE_RAW, 0x0C1, true },
+	{ PERF_TYPE_RAW, 0x012, false },
+};
+
+static int event_open(int type, unsigned long config)
+{
+	struct perf_event_attr attr;
+
+	memset(&attr, 0, sizeof(struct perf_event_attr));
+	attr.type = type;
+	attr.size = sizeof(struct perf_event_attr);
+	attr.config = config;
+	attr.disabled = 1;
+	attr.precise_ip = 1;
+	attr.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+	attr.sample_period = 100000;
+
+	return sys_perf_event_open(&attr, -1, 0, -1, 0);
+}
+
+int test__amd_ibs_via_core_pmu(struct test_suite *test __maybe_unused,
+			       int subtest __maybe_unused)
+{
+	struct perf_pmu *ibs_pmu;
+	int ret = TEST_OK;
+	int fd, i;
+
+	ibs_pmu = perf_pmus__find("ibs_op");
+	if (!ibs_pmu)
+		return TEST_SKIP;
+
+	for (i = 0; i < NR_SUB_TESTS; i++) {
+		fd = event_open(sub_tests[i].type, sub_tests[i].config);
+		pr_debug("type: 0x%x, config: 0x%lx, fd: %d  -  ", sub_tests[i].type,
+			 sub_tests[i].config, fd);
+		if ((sub_tests[i].valid && fd == -1) ||
+		    (!sub_tests[i].valid && fd > 0)) {
+			pr_debug("Fail\n");
+			ret = TEST_FAIL;
+		} else {
+			pr_debug("Pass\n");
+		}
+
+		if (fd > 0)
+			close(fd);
+	}
+
+	return ret;
+}

linux-7.2.3/tools/perf/arch/x86/tests/arch-tests.c

@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+#ifdef HAVE_EXTRA_TESTS
+DEFINE_SUITE("x86 instruction decoder - new instructions", insn_x86);
+#endif
+
+static struct test_case intel_pt_tests[] = {
+	TEST_CASE("Intel PT packet decoder", intel_pt_pkt_decoder),
+	TEST_CASE("Intel PT hybrid CPU compatibility", intel_pt_hybrid_compat),
+	{ .name = NULL, }
+};
+
+struct test_suite suite__intel_pt = {
+	.desc = "Intel PT",
+	.test_cases = intel_pt_tests,
+};
+
+#if defined(__x86_64__)
+DEFINE_SUITE("x86 bp modify", bp_modify);
+#endif
+DEFINE_SUITE("AMD IBS via core pmu", amd_ibs_via_core_pmu);
+DEFINE_SUITE_EXCLUSIVE("AMD IBS sample period", amd_ibs_period);
+static struct test_case hybrid_tests[] = {
+	TEST_CASE_REASON("x86 hybrid event parsing", hybrid, "not hybrid"),
+	{ .name = NULL, }
+};
+
+struct test_suite suite__hybrid = {
+	.desc = "x86 hybrid",
+	.test_cases = hybrid_tests,
+};
+
+struct test_suite *arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	&suite__dwarf_unwind,
+#endif
+#ifdef HAVE_EXTRA_TESTS
+	&suite__insn_x86,
+#endif
+	&suite__intel_pt,
+#if defined(__x86_64__)
+	&suite__bp_modify,
+#endif
+	&suite__amd_ibs_via_core_pmu,
+	&suite__amd_ibs_period,
+	&suite__hybrid,
+	&suite__x86_topdown,
+	NULL,
+};

linux-7.2.3/tools/perf/arch/x86/tests/bp-modify.c

@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/user.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ptrace.h>
+#include <asm/ptrace.h>
+#include <errno.h>
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+static noinline int bp_1(void)
+{
+	pr_debug("in %s\n", __func__);
+	return 0;
+}
+
+static noinline int bp_2(void)
+{
+	pr_debug("in %s\n", __func__);
+	return 0;
+}
+
+static int spawn_child(void)
+{
+	int child = fork();
+
+	if (child == 0) {
+		/*
+		 * The child sets itself for as tracee and
+		 * waits in signal for parent to trace it,
+		 * then it calls bp_1 and quits.
+		 */
+		int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL);
+
+		if (err) {
+			pr_debug("failed to PTRACE_TRACEME\n");
+			exit(1);
+		}
+
+		raise(SIGCONT);
+		bp_1();
+		exit(0);
+	}
+
+	return child;
+}
+
+/*
+ * This tests creates HW breakpoint, tries to
+ * change it and checks it was properly changed.
+ */
+static int bp_modify1(void)
+{
+	pid_t child;
+	int status;
+	unsigned long rip = 0, dr7 = 1;
+
+	child = spawn_child();
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 1\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * The parent does following steps:
+	 *  - creates a new breakpoint (id 0) for bp_2 function
+	 *  - changes that breakpoint to bp_1 function
+	 *  - waits for the breakpoint to hit and checks
+	 *    it has proper rip of bp_1 function
+	 *  - detaches the child
+	 */
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_2)) {
+		pr_debug("failed to set breakpoint, 1st time: %m\n");
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_1)) {
+		pr_debug("failed to set breakpoint, 2nd time: %m\n");
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[7]), dr7)) {
+		pr_debug("failed to set dr7: %m\n");
+		goto out;
+	}
+
+	if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_CONT: %m\n");
+		goto out;
+	}
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 2\n");
+		return TEST_FAIL;
+	}
+
+	rip = ptrace(PTRACE_PEEKUSER, child,
+		     offsetof(struct user_regs_struct, rip), NULL);
+	if (rip == (unsigned long) -1) {
+		pr_debug("failed to PTRACE_PEEKUSER: %m\n");
+		goto out;
+	}
+
+	pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
+out:
+	if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_DETACH: %m\n");
+		return TEST_FAIL;
+
+	}
+	return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
+}
+
+/*
+ * This tests creates HW breakpoint, tries to
+ * change it to bogus value and checks the original
+ * breakpoint is hit.
+ */
+static int bp_modify2(void)
+{
+	pid_t child;
+	int status;
+	unsigned long rip = 0, dr7 = 1;
+
+	child = spawn_child();
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 1\n");
+		return TEST_FAIL;
+	}
+
+	/*
+	 * The parent does following steps:
+	 *  - creates a new breakpoint (id 0) for bp_1 function
+	 *  - tries to change that breakpoint to (-1) address
+	 *  - waits for the breakpoint to hit and checks
+	 *    it has proper rip of bp_1 function
+	 *  - detaches the child
+	 */
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), bp_1)) {
+		pr_debug("failed to set breakpoint: %m\n");
+		goto out;
+	}
+
+	if (ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[7]), dr7)) {
+		pr_debug("failed to set dr7: %m\n");
+		goto out;
+	}
+
+	if (!ptrace(PTRACE_POKEUSER, child,
+		   offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) {
+		pr_debug("failed, breakpoint set to bogus address\n");
+		goto out;
+	}
+
+	if (ptrace(PTRACE_CONT, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_CONT: %m\n");
+		goto out;
+	}
+
+	waitpid(child, &status, 0);
+	if (WIFEXITED(status)) {
+		pr_debug("tracee exited prematurely 2\n");
+		return TEST_FAIL;
+	}
+
+	rip = ptrace(PTRACE_PEEKUSER, child,
+		     offsetof(struct user_regs_struct, rip), NULL);
+	if (rip == (unsigned long) -1) {
+		pr_debug("failed to PTRACE_PEEKUSER: %m\n");
+		goto out;
+	}
+
+	pr_debug("rip %lx, bp_1 %p\n", rip, bp_1);
+
+out:
+	if (ptrace(PTRACE_DETACH, child, NULL, NULL)) {
+		pr_debug("failed to PTRACE_DETACH: %m\n");
+		return TEST_FAIL;
+	}
+
+	return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
+}
+
+int test__bp_modify(struct test_suite *test __maybe_unused,
+		    int subtest __maybe_unused)
+{
+	TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1());
+	TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2());
+
+	return 0;
+}

linux-7.2.3/tools/perf/arch/x86/tests/dwarf-unwind.c

@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "maps.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_X86_SP];
+
+	map = maps__find(thread__maps(thread), (u64)sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map__end(map) - sp;
+	map__put(map);
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+#ifdef MEMORY_SANITIZER
+	/*
+	 * Copying the stack may copy msan poison, avoid false positives in the
+	 * unwinder by removing the poison here.
+	 */
+	__msan_unpoison(buf, stack_size);
+#endif
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = perf_sample__user_regs(sample);
+	u64 *buf = calloc(PERF_REGS_MAX, sizeof(u64));
+
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}

linux-7.2.3/tools/perf/arch/x86/tests/gen-insn-x86-dat.awk

@@ -0,0 +1,68 @@
+#!/bin/awk -f
+# SPDX-License-Identifier: GPL-2.0-only
+# gen-insn-x86-dat.awk: script to convert data for the insn-x86 test
+# Copyright (c) 2015, Intel Corporation.
+#
+
+BEGIN {
+	print "/*"
+	print " * Generated by gen-insn-x86-dat.sh and gen-insn-x86-dat.awk"
+	print " * from insn-x86-dat-src.c for inclusion by insn-x86.c"
+	print " * Do not change this code."
+	print "*/\n"
+	op = ""
+	branch = ""
+	rel = 0
+	going = 0
+}
+
+/ Start here / {
+	going = 1
+}
+
+/ Stop here / {
+	going = 0
+}
+
+/^\s*[0-9a-fA-F]+\:/ {
+	if (going) {
+		colon_pos = index($0, ":")
+		useful_line = substr($0, colon_pos + 1)
+		first_pos = match(useful_line, "[0-9a-fA-F]")
+		useful_line = substr(useful_line, first_pos)
+		gsub("\t", "\\t", useful_line)
+		printf "{{"
+		len = 0
+		for (i = 2; i <= NF; i++) {
+			if (match($i, "^[0-9a-fA-F][0-9a-fA-F]$")) {
+				printf "0x%s, ", $i
+				len += 1
+			} else {
+				break
+			}
+		}
+		printf "}, %d, %s, \"%s\", \"%s\",", len, rel, op, branch
+		printf "\n\"%s\",},\n", useful_line
+		op = ""
+		branch = ""
+		rel = 0
+	}
+}
+
+/ Expecting: / {
+	expecting_str = " Expecting: "
+	expecting_len = length(expecting_str)
+	expecting_pos = index($0, expecting_str)
+	useful_line = substr($0, expecting_pos + expecting_len)
+	for (i = 1; i <= NF; i++) {
+		if ($i == "Expecting:") {
+			i++
+			op = $i
+			i++
+			branch = $i
+			i++
+			rel = $i
+			break
+		}
+	}
+}

linux-7.2.3/tools/perf/arch/x86/tests/gen-insn-x86-dat.sh

@@ -0,0 +1,36 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+# gen-insn-x86-dat: generate data for the insn-x86 test
+# Copyright (c) 2015, Intel Corporation.
+#
+
+set -e
+
+if [ "$(uname -m)" != "x86_64" ]; then
+	echo "ERROR: This script only works on x86_64"
+	exit 1
+fi
+
+cd "$(dirname $0)"
+
+trap 'echo "Might need a more recent version of binutils"' EXIT
+
+echo "Compiling insn-x86-dat-src.c to 64-bit object"
+
+gcc -g -c insn-x86-dat-src.c
+
+objdump -dSw insn-x86-dat-src.o | awk -f gen-insn-x86-dat.awk > insn-x86-dat-64.c
+
+rm -f insn-x86-dat-src.o
+
+echo "Compiling insn-x86-dat-src.c to 32-bit object"
+
+gcc -g -c -m32 insn-x86-dat-src.c
+
+objdump -dSw insn-x86-dat-src.o | awk -f gen-insn-x86-dat.awk > insn-x86-dat-32.c
+
+rm -f insn-x86-dat-src.o
+
+trap - EXIT
+
+echo "Done (use git diff to see the changes)"

linux-7.2.3/tools/perf/arch/x86/tests/hybrid.c

@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "arch-tests.h"
+#include "debug.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "pmu.h"
+#include "pmus.h"
+#include "tests/tests.h"
+
+static bool test_config(const struct evsel *evsel, __u64 expected_config)
+{
+	return (evsel->core.attr.config & PERF_HW_EVENT_MASK) == expected_config;
+}
+
+static bool test_perf_config(const struct perf_evsel *evsel, __u64 expected_config)
+{
+	return (evsel->attr.config & PERF_HW_EVENT_MASK) == expected_config;
+}
+
+static bool test_hybrid_type(const struct evsel *evsel, __u64 expected_config)
+{
+	return (evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT) == expected_config;
+}
+
+static int test__hybrid_hw_event_with_pmu(struct evlist *evlist)
+{
+	struct evsel *evsel = evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	return TEST_OK;
+}
+
+static int test__hybrid_hw_group_event(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_INSTRUCTIONS));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	return TEST_OK;
+}
+
+static int test__hybrid_sw_hw_group_event(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	return TEST_OK;
+}
+
+static int test__hybrid_hw_sw_group_event(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	return TEST_OK;
+}
+
+static int test__hybrid_group_modifier1(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_INSTRUCTIONS));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
+	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
+	return TEST_OK;
+}
+
+static int test__hybrid_raw1(struct evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	perf_evlist__for_each_evsel(&evlist->core, evsel) {
+		struct perf_pmu *pmu = perf_pmus__find_by_type(evsel->attr.type);
+
+		TEST_ASSERT_VAL("missing pmu", pmu);
+		TEST_ASSERT_VAL("unexpected pmu", !strncmp(pmu->name, "cpu_", 4));
+		TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, 0x1a));
+	}
+	return TEST_OK;
+}
+
+static int test__hybrid_raw2(struct evlist *evlist)
+{
+	struct evsel *evsel = evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, 0x1a));
+	return TEST_OK;
+}
+
+static int test__hybrid_cache_event(struct evlist *evlist)
+{
+	struct evsel *evsel = evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config", 0x2 == (evsel->core.attr.config & 0xffffffff));
+	return TEST_OK;
+}
+
+static int test__checkevent_pmu(struct evlist *evlist)
+{
+
+	struct evsel *evsel = evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config",    10 == evsel->core.attr.config);
+	TEST_ASSERT_VAL("wrong config1",    1 == evsel->core.attr.config1);
+	TEST_ASSERT_VAL("wrong config2",    3 == evsel->core.attr.config2);
+	TEST_ASSERT_VAL("wrong config3",    0 == evsel->core.attr.config3);
+	/*
+	 * The period value gets configured within evlist__config,
+	 * while this test executes only parse events method.
+	 */
+	TEST_ASSERT_VAL("wrong period",     0 == evsel->core.attr.sample_period);
+
+	return TEST_OK;
+}
+
+static int test__hybrid_hw_group_event_2(struct evlist *evlist)
+{
+	struct evsel *evsel, *leader;
+
+	evsel = leader = evlist__first(evlist);
+	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong hybrid type", test_hybrid_type(evsel, PERF_TYPE_RAW));
+	TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES));
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+
+	evsel = evsel__next(evsel);
+	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
+	TEST_ASSERT_VAL("wrong config", evsel->core.attr.config == 0x3c);
+	TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader));
+	return TEST_OK;
+}
+
+struct evlist_test {
+	const char *name;
+	bool (*valid)(void);
+	int (*check)(struct evlist *evlist);
+};
+
+static const struct evlist_test test__hybrid_events[] = {
+	{
+		.name  = "cpu_core/cycles/",
+		.check = test__hybrid_hw_event_with_pmu,
+		/* 0 */
+	},
+	{
+		.name  = "{cpu_core/cycles/,cpu_core/branches/}",
+		.check = test__hybrid_hw_group_event,
+		/* 1 */
+	},
+	{
+		.name  = "{cpu-clock,cpu_core/cycles/}",
+		.check = test__hybrid_sw_hw_group_event,
+		/* 2 */
+	},
+	{
+		.name  = "{cpu_core/cycles/,cpu-clock}",
+		.check = test__hybrid_hw_sw_group_event,
+		/* 3 */
+	},
+	{
+		.name  = "{cpu_core/cycles/k,cpu_core/branches/u}",
+		.check = test__hybrid_group_modifier1,
+		/* 4 */
+	},
+	{
+		.name  = "r1a",
+		.check = test__hybrid_raw1,
+		/* 5 */
+	},
+	{
+		.name  = "cpu_core/r1a/",
+		.check = test__hybrid_raw2,
+		/* 6 */
+	},
+	{
+		.name  = "cpu_core/config=10,config1,config2=3,period=1000/u",
+		.check = test__checkevent_pmu,
+		/* 7 */
+	},
+	{
+		.name  = "cpu_core/LLC-loads/",
+		.check = test__hybrid_cache_event,
+		/* 8 */
+	},
+	{
+		.name  = "{cpu_core/cycles/,cpu_core/cpu-cycles/}",
+		.check = test__hybrid_hw_group_event_2,
+		/* 9 */
+	},
+};
+
+static int test_event(const struct evlist_test *e)
+{
+	struct parse_events_error err;
+	struct evlist *evlist;
+	int ret;
+
+	if (e->valid && !e->valid()) {
+		pr_debug("... SKIP\n");
+		return TEST_OK;
+	}
+
+	evlist = evlist__new();
+	if (evlist == NULL) {
+		pr_err("Failed allocation");
+		return TEST_FAIL;
+	}
+	parse_events_error__init(&err);
+	ret = parse_events(evlist, e->name, &err);
+	if (ret) {
+		pr_debug("failed to parse event '%s', err %d\n", e->name, ret);
+		parse_events_error__print(&err, e->name);
+		ret = TEST_FAIL;
+		if (parse_events_error__contains(&err, "can't access trace events"))
+			ret = TEST_SKIP;
+	} else {
+		ret = e->check(evlist);
+	}
+	parse_events_error__exit(&err);
+	evlist__delete(evlist);
+
+	return ret;
+}
+
+static int combine_test_results(int existing, int latest)
+{
+	if (existing == TEST_FAIL)
+		return TEST_FAIL;
+	if (existing == TEST_SKIP)
+		return latest == TEST_OK ? TEST_SKIP : latest;
+	return latest;
+}
+
+static int test_events(const struct evlist_test *events, int cnt)
+{
+	int ret = TEST_OK;
+
+	for (int i = 0; i < cnt; i++) {
+		const struct evlist_test *e = &events[i];
+		int test_ret;
+
+		pr_debug("running test %d '%s'\n", i, e->name);
+		test_ret = test_event(e);
+		if (test_ret != TEST_OK) {
+			pr_debug("Event test failure: test %d '%s'", i, e->name);
+			ret = combine_test_results(ret, test_ret);
+		}
+	}
+
+	return ret;
+}
+
+int test__hybrid(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	if (perf_pmus__num_core_pmus() == 1)
+		return TEST_SKIP;
+
+	return test_events(test__hybrid_events, ARRAY_SIZE(test__hybrid_events));
+}

linux-7.2.3/tools/perf/arch/x86/tests/insn-x86.c

@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <string.h>
+
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+#include "../../../../arch/x86/include/asm/insn.h"
+
+#include "intel-pt-decoder/intel-pt-insn-decoder.h"
+
+struct test_data {
+	u8 data[MAX_INSN_SIZE];
+	int expected_length;
+	int expected_rel;
+	const char *expected_op_str;
+	const char *expected_branch_str;
+	const char *asm_rep;
+};
+
+const struct test_data test_data_32[] = {
+#include "insn-x86-dat-32.c"
+	{{0x0f, 0x01, 0xee}, 3, 0, NULL, NULL, "0f 01 ee             \trdpkru"},
+	{{0x0f, 0x01, 0xef}, 3, 0, NULL, NULL, "0f 01 ef             \twrpkru"},
+	{{0}, 0, 0, NULL, NULL, NULL},
+};
+
+const struct test_data test_data_64[] = {
+#include "insn-x86-dat-64.c"
+	{{0x0f, 0x01, 0xee}, 3, 0, NULL, NULL, "0f 01 ee             \trdpkru"},
+	{{0x0f, 0x01, 0xef}, 3, 0, NULL, NULL, "0f 01 ef             \twrpkru"},
+	{{0xf2, 0x0f, 0x01, 0xca}, 4, 0, "erets", "indirect", "f2 0f 01 ca  \terets"},
+	{{0xf3, 0x0f, 0x01, 0xca}, 4, 0, "eretu", "indirect", "f3 0f 01 ca  \teretu"},
+	{{0}, 0, 0, NULL, NULL, NULL},
+};
+
+static int get_op(const char *op_str)
+{
+	struct val_data {
+		const char *name;
+		int val;
+	} vals[] = {
+		{"other",   INTEL_PT_OP_OTHER},
+		{"call",    INTEL_PT_OP_CALL},
+		{"ret",     INTEL_PT_OP_RET},
+		{"jcc",     INTEL_PT_OP_JCC},
+		{"jmp",     INTEL_PT_OP_JMP},
+		{"loop",    INTEL_PT_OP_LOOP},
+		{"iret",    INTEL_PT_OP_IRET},
+		{"int",     INTEL_PT_OP_INT},
+		{"syscall", INTEL_PT_OP_SYSCALL},
+		{"sysret",  INTEL_PT_OP_SYSRET},
+		{"vmentry",  INTEL_PT_OP_VMENTRY},
+		{"erets",   INTEL_PT_OP_ERETS},
+		{"eretu",   INTEL_PT_OP_ERETU},
+		{NULL, 0},
+	};
+	struct val_data *val;
+
+	if (!op_str || !strlen(op_str))
+		return 0;
+
+	for (val = vals; val->name; val++) {
+		if (!strcmp(val->name, op_str))
+			return val->val;
+	}
+
+	pr_debug("Failed to get op\n");
+
+	return -1;
+}
+
+static int get_branch(const char *branch_str)
+{
+	struct val_data {
+		const char *name;
+		int val;
+	} vals[] = {
+		{"no_branch",     INTEL_PT_BR_NO_BRANCH},
+		{"indirect",      INTEL_PT_BR_INDIRECT},
+		{"conditional",   INTEL_PT_BR_CONDITIONAL},
+		{"unconditional", INTEL_PT_BR_UNCONDITIONAL},
+		{NULL, 0},
+	};
+	struct val_data *val;
+
+	if (!branch_str || !strlen(branch_str))
+		return 0;
+
+	for (val = vals; val->name; val++) {
+		if (!strcmp(val->name, branch_str))
+			return val->val;
+	}
+
+	pr_debug("Failed to get branch\n");
+
+	return -1;
+}
+
+static int test_data_item(const struct test_data *dat, int x86_64)
+{
+	struct intel_pt_insn intel_pt_insn;
+	int op, branch, ret;
+	struct insn insn;
+
+	ret = insn_decode(&insn, dat->data, MAX_INSN_SIZE,
+			  x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+	if (ret < 0) {
+		pr_debug("Failed to decode: %s\n", dat->asm_rep);
+		return -1;
+	}
+
+	if (insn.length != dat->expected_length) {
+		pr_debug("Failed to decode length (%d vs expected %d): %s\n",
+			 insn.length, dat->expected_length, dat->asm_rep);
+		return -1;
+	}
+
+	op = get_op(dat->expected_op_str);
+	branch = get_branch(dat->expected_branch_str);
+
+	if (intel_pt_get_insn(dat->data, MAX_INSN_SIZE, x86_64, &intel_pt_insn)) {
+		pr_debug("Intel PT failed to decode: %s\n", dat->asm_rep);
+		return -1;
+	}
+
+	if ((int)intel_pt_insn.op != op) {
+		pr_debug("Failed to decode 'op' value (%d vs expected %d): %s\n",
+			 intel_pt_insn.op, op, dat->asm_rep);
+		return -1;
+	}
+
+	if ((int)intel_pt_insn.branch != branch) {
+		pr_debug("Failed to decode 'branch' value (%d vs expected %d): %s\n",
+			 intel_pt_insn.branch, branch, dat->asm_rep);
+		return -1;
+	}
+
+	if (intel_pt_insn.rel != dat->expected_rel) {
+		pr_debug("Failed to decode 'rel' value (%#x vs expected %#x): %s\n",
+			 intel_pt_insn.rel, dat->expected_rel, dat->asm_rep);
+		return -1;
+	}
+
+	pr_debug("Decoded ok: %s\n", dat->asm_rep);
+
+	return 0;
+}
+
+static int test_data_set(const struct test_data *dat_set, int x86_64)
+{
+	const struct test_data *dat;
+	int ret = 0;
+
+	for (dat = dat_set; dat->expected_length; dat++) {
+		if (test_data_item(dat, x86_64))
+			ret = -1;
+	}
+
+	return ret;
+}
+
+/**
+ * test__insn_x86 - test x86 instruction decoder - new instructions.
+ *
+ * This function implements a test that decodes a selection of instructions and
+ * checks the results.  The Intel PT function that further categorizes
+ * instructions (i.e. intel_pt_get_insn()) is also checked.
+ *
+ * The instructions are originally in insn-x86-dat-src.c which has been
+ * processed by scripts gen-insn-x86-dat.sh and gen-insn-x86-dat.awk to produce
+ * insn-x86-dat-32.c and insn-x86-dat-64.c which are included into this program.
+ * i.e. to add new instructions to the test, edit insn-x86-dat-src.c, run the
+ * gen-insn-x86-dat.sh script, make perf, and then run the test.
+ *
+ * If the test passes %0 is returned, otherwise %-1 is returned.  Use the
+ * verbose (-v) option to see all the instructions and whether or not they
+ * decoded successfully.
+ */
+int test__insn_x86(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	int ret = 0;
+
+	if (test_data_set(test_data_32, 0))
+		ret = -1;
+
+	if (test_data_set(test_data_64, 1))
+		ret = -1;
+
+	return ret;
+}

linux-7.2.3/tools/perf/arch/x86/tests/intel-pt-test.c

@@ -0,0 +1,469 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/compiler.h>
+#include <linux/bits.h>
+#include <string.h>
+#include <sched.h>
+
+#include "intel-pt-decoder/intel-pt-pkt-decoder.h"
+
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+#include "../util/cpuid.h"
+#include "cpumap.h"
+
+/**
+ * struct test_data - Test data.
+ * @len: number of bytes to decode
+ * @bytes: bytes to decode
+ * @ctx: packet context to decode
+ * @packet: expected packet
+ * @new_ctx: expected new packet context
+ * @ctx_unchanged: the packet context must not change
+ */
+static const struct test_data {
+	int len;
+	u8 bytes[INTEL_PT_PKT_MAX_SZ];
+	enum intel_pt_pkt_ctx ctx;
+	struct intel_pt_pkt packet;
+	enum intel_pt_pkt_ctx new_ctx;
+	int ctx_unchanged;
+} data[] = {
+	/* Padding Packet */
+	{1, {0}, 0, {INTEL_PT_PAD, 0, 0}, 0, 1 },
+	/* Short Taken/Not Taken Packet */
+	{1, {4}, 0, {INTEL_PT_TNT, 1, 0}, 0, 0 },
+	{1, {6}, 0, {INTEL_PT_TNT, 1, 0x20ULL << 58}, 0, 0 },
+	{1, {0x80}, 0, {INTEL_PT_TNT, 6, 0}, 0, 0 },
+	{1, {0xfe}, 0, {INTEL_PT_TNT, 6, 0x3fULL << 58}, 0, 0 },
+	/* Long Taken/Not Taken Packet */
+	{8, {0x02, 0xa3, 2}, 0, {INTEL_PT_TNT, 1, 0xa302ULL << 47}, 0, 0 },
+	{8, {0x02, 0xa3, 3}, 0, {INTEL_PT_TNT, 1, 0x1a302ULL << 47}, 0, 0 },
+	{8, {0x02, 0xa3, 0, 0, 0, 0, 0, 0x80}, 0, {INTEL_PT_TNT, 47, 0xa302ULL << 1}, 0, 0 },
+	{8, {0x02, 0xa3, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff}, 0, {INTEL_PT_TNT, 47, 0xffffffffffffa302ULL << 1}, 0, 0 },
+	/* Target IP Packet */
+	{1, {0x0d}, 0, {INTEL_PT_TIP, 0, 0}, 0, 0 },
+	{3, {0x2d, 1, 2}, 0, {INTEL_PT_TIP, 1, 0x201}, 0, 0 },
+	{5, {0x4d, 1, 2, 3, 4}, 0, {INTEL_PT_TIP, 2, 0x4030201}, 0, 0 },
+	{7, {0x6d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP, 3, 0x60504030201}, 0, 0 },
+	{7, {0x8d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP, 4, 0x60504030201}, 0, 0 },
+	{9, {0xcd, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP, 6, 0x807060504030201}, 0, 0 },
+	/* Packet Generation Enable */
+	{1, {0x11}, 0, {INTEL_PT_TIP_PGE, 0, 0}, 0, 0 },
+	{3, {0x31, 1, 2}, 0, {INTEL_PT_TIP_PGE, 1, 0x201}, 0, 0 },
+	{5, {0x51, 1, 2, 3, 4}, 0, {INTEL_PT_TIP_PGE, 2, 0x4030201}, 0, 0 },
+	{7, {0x71, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGE, 3, 0x60504030201}, 0, 0 },
+	{7, {0x91, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGE, 4, 0x60504030201}, 0, 0 },
+	{9, {0xd1, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP_PGE, 6, 0x807060504030201}, 0, 0 },
+	/* Packet Generation Disable */
+	{1, {0x01}, 0, {INTEL_PT_TIP_PGD, 0, 0}, 0, 0 },
+	{3, {0x21, 1, 2}, 0, {INTEL_PT_TIP_PGD, 1, 0x201}, 0, 0 },
+	{5, {0x41, 1, 2, 3, 4}, 0, {INTEL_PT_TIP_PGD, 2, 0x4030201}, 0, 0 },
+	{7, {0x61, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGD, 3, 0x60504030201}, 0, 0 },
+	{7, {0x81, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_TIP_PGD, 4, 0x60504030201}, 0, 0 },
+	{9, {0xc1, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_TIP_PGD, 6, 0x807060504030201}, 0, 0 },
+	/* Flow Update Packet */
+	{1, {0x1d}, 0, {INTEL_PT_FUP, 0, 0}, 0, 0 },
+	{3, {0x3d, 1, 2}, 0, {INTEL_PT_FUP, 1, 0x201}, 0, 0 },
+	{5, {0x5d, 1, 2, 3, 4}, 0, {INTEL_PT_FUP, 2, 0x4030201}, 0, 0 },
+	{7, {0x7d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_FUP, 3, 0x60504030201}, 0, 0 },
+	{7, {0x9d, 1, 2, 3, 4, 5, 6}, 0, {INTEL_PT_FUP, 4, 0x60504030201}, 0, 0 },
+	{9, {0xdd, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_FUP, 6, 0x807060504030201}, 0, 0 },
+	/* Paging Information Packet */
+	{8, {0x02, 0x43, 2, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0xC0A08060402}, 0, 0 },
+	{8, {0x02, 0x43, 3, 4, 6, 8, 10, 12}, 0, {INTEL_PT_PIP, 0, 0xC0A08060403}, 0, 0 },
+	/* Mode Exec Packet */
+	{2, {0x99, 0x00}, 0, {INTEL_PT_MODE_EXEC, 0, 16}, 0, 0 },
+	{2, {0x99, 0x01}, 0, {INTEL_PT_MODE_EXEC, 1, 64}, 0, 0 },
+	{2, {0x99, 0x02}, 0, {INTEL_PT_MODE_EXEC, 2, 32}, 0, 0 },
+	{2, {0x99, 0x04}, 0, {INTEL_PT_MODE_EXEC, 4, 16}, 0, 0 },
+	{2, {0x99, 0x05}, 0, {INTEL_PT_MODE_EXEC, 5, 64}, 0, 0 },
+	{2, {0x99, 0x06}, 0, {INTEL_PT_MODE_EXEC, 6, 32}, 0, 0 },
+	/* Mode TSX Packet */
+	{2, {0x99, 0x20}, 0, {INTEL_PT_MODE_TSX, 0, 0}, 0, 0 },
+	{2, {0x99, 0x21}, 0, {INTEL_PT_MODE_TSX, 0, 1}, 0, 0 },
+	{2, {0x99, 0x22}, 0, {INTEL_PT_MODE_TSX, 0, 2}, 0, 0 },
+	/* Trace Stop Packet */
+	{2, {0x02, 0x83}, 0, {INTEL_PT_TRACESTOP, 0, 0}, 0, 0 },
+	/* Core:Bus Ratio Packet */
+	{4, {0x02, 0x03, 0x12, 0}, 0, {INTEL_PT_CBR, 0, 0x12}, 0, 1 },
+	/* Timestamp Counter Packet */
+	{8, {0x19, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_TSC, 0, 0x7060504030201}, 0, 1 },
+	/* Mini Time Counter Packet */
+	{2, {0x59, 0x12}, 0, {INTEL_PT_MTC, 0, 0x12}, 0, 1 },
+	/* TSC / MTC Alignment Packet */
+	{7, {0x02, 0x73}, 0, {INTEL_PT_TMA, 0, 0}, 0, 1 },
+	{7, {0x02, 0x73, 1, 2}, 0, {INTEL_PT_TMA, 0, 0x201}, 0, 1 },
+	{7, {0x02, 0x73, 0, 0, 0, 0xff, 1}, 0, {INTEL_PT_TMA, 0x1ff, 0}, 0, 1 },
+	{7, {0x02, 0x73, 0x80, 0xc0, 0, 0xff, 1}, 0, {INTEL_PT_TMA, 0x1ff, 0xc080}, 0, 1 },
+	/* Cycle Count Packet */
+	{1, {0x03}, 0, {INTEL_PT_CYC, 0, 0}, 0, 1 },
+	{1, {0x0b}, 0, {INTEL_PT_CYC, 0, 1}, 0, 1 },
+	{1, {0xfb}, 0, {INTEL_PT_CYC, 0, 0x1f}, 0, 1 },
+	{2, {0x07, 2}, 0, {INTEL_PT_CYC, 0, 0x20}, 0, 1 },
+	{2, {0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0xfff}, 0, 1 },
+	{3, {0x07, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x1000}, 0, 1 },
+	{3, {0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x7ffff}, 0, 1 },
+	{4, {0x07, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x80000}, 0, 1 },
+	{4, {0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x3ffffff}, 0, 1 },
+	{5, {0x07, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x4000000}, 0, 1 },
+	{5, {0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x1ffffffff}, 0, 1 },
+	{6, {0x07, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x200000000}, 0, 1 },
+	{6, {0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0xffffffffff}, 0, 1 },
+	{7, {0x07, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x10000000000}, 0, 1 },
+	{7, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x7fffffffffff}, 0, 1 },
+	{8, {0x07, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x800000000000}, 0, 1 },
+	{8, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x3fffffffffffff}, 0, 1 },
+	{9, {0x07, 1, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x40000000000000}, 0, 1 },
+	{9, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xfe}, 0, {INTEL_PT_CYC, 0, 0x1fffffffffffffff}, 0, 1 },
+	{10, {0x07, 1, 1, 1, 1, 1, 1, 1, 1, 2}, 0, {INTEL_PT_CYC, 0, 0x2000000000000000}, 0, 1 },
+	{10, {0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xe}, 0, {INTEL_PT_CYC, 0, 0xffffffffffffffff}, 0, 1 },
+	/* Virtual-Machine Control Structure Packet */
+	{7, {0x02, 0xc8, 1, 2, 3, 4, 5}, 0, {INTEL_PT_VMCS, 5, 0x504030201}, 0, 0 },
+	/* Overflow Packet */
+	{2, {0x02, 0xf3}, 0, {INTEL_PT_OVF, 0, 0}, 0, 0 },
+	{2, {0x02, 0xf3}, INTEL_PT_BLK_4_CTX, {INTEL_PT_OVF, 0, 0}, 0, 0 },
+	{2, {0x02, 0xf3}, INTEL_PT_BLK_8_CTX, {INTEL_PT_OVF, 0, 0}, 0, 0 },
+	/* Packet Stream Boundary*/
+	{16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, 0, {INTEL_PT_PSB, 0, 0}, 0, 0 },
+	{16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, INTEL_PT_BLK_4_CTX, {INTEL_PT_PSB, 0, 0}, 0, 0 },
+	{16, {0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82, 0x02, 0x82}, INTEL_PT_BLK_8_CTX, {INTEL_PT_PSB, 0, 0}, 0, 0 },
+	/* PSB End Packet */
+	{2, {0x02, 0x23}, 0, {INTEL_PT_PSBEND, 0, 0}, 0, 0 },
+	/* Maintenance Packet */
+	{11, {0x02, 0xc3, 0x88, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_MNT, 0, 0x7060504030201}, 0, 1 },
+	/* Write Data to PT Packet */
+	{6, {0x02, 0x12, 1, 2, 3, 4}, 0, {INTEL_PT_PTWRITE, 0, 0x4030201}, 0, 0 },
+	{10, {0x02, 0x32, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_PTWRITE, 1, 0x807060504030201}, 0, 0 },
+	{6, {0x02, 0x92, 1, 2, 3, 4}, 0, {INTEL_PT_PTWRITE_IP, 0, 0x4030201}, 0, 0 },
+	{10, {0x02, 0xb2, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_PTWRITE_IP, 1, 0x807060504030201}, 0, 0 },
+	/* Execution Stop Packet */
+	{2, {0x02, 0x62}, 0, {INTEL_PT_EXSTOP, 0, 0}, 0, 1 },
+	{2, {0x02, 0xe2}, 0, {INTEL_PT_EXSTOP_IP, 0, 0}, 0, 1 },
+	/* Monitor Wait Packet */
+	{10, {0x02, 0xc2}, 0, {INTEL_PT_MWAIT, 0, 0}, 0, 0 },
+	{10, {0x02, 0xc2, 1, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_MWAIT, 0, 0x807060504030201}, 0, 0 },
+	{10, {0x02, 0xc2, 0xff, 2, 3, 4, 7, 6, 7, 8}, 0, {INTEL_PT_MWAIT, 0, 0x8070607040302ff}, 0, 0 },
+	/* Power Entry Packet */
+	{4, {0x02, 0x22}, 0, {INTEL_PT_PWRE, 0, 0}, 0, 1 },
+	{4, {0x02, 0x22, 1, 2}, 0, {INTEL_PT_PWRE, 0, 0x0201}, 0, 1 },
+	{4, {0x02, 0x22, 0x80, 0x34}, 0, {INTEL_PT_PWRE, 0, 0x3480}, 0, 1 },
+	{4, {0x02, 0x22, 0x00, 0x56}, 0, {INTEL_PT_PWRE, 0, 0x5600}, 0, 1 },
+	/* Power Exit Packet */
+	{7, {0x02, 0xa2}, 0, {INTEL_PT_PWRX, 0, 0}, 0, 1 },
+	{7, {0x02, 0xa2, 1, 2, 3, 4, 5}, 0, {INTEL_PT_PWRX, 0, 0x504030201}, 0, 1 },
+	{7, {0x02, 0xa2, 0xff, 0xff, 0xff, 0xff, 0xff}, 0, {INTEL_PT_PWRX, 0, 0xffffffffff}, 0, 1 },
+	/* Block Begin Packet */
+	{3, {0x02, 0x63, 0x00}, 0, {INTEL_PT_BBP, 0, 0}, INTEL_PT_BLK_8_CTX, 0 },
+	{3, {0x02, 0x63, 0x80}, 0, {INTEL_PT_BBP, 1, 0}, INTEL_PT_BLK_4_CTX, 0 },
+	{3, {0x02, 0x63, 0x1f}, 0, {INTEL_PT_BBP, 0, 0x1f}, INTEL_PT_BLK_8_CTX, 0 },
+	{3, {0x02, 0x63, 0x9f}, 0, {INTEL_PT_BBP, 1, 0x1f}, INTEL_PT_BLK_4_CTX, 0 },
+	/* 4-byte Block Item Packet */
+	{5, {0x04}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0, 0}, INTEL_PT_BLK_4_CTX, 0 },
+	{5, {0xfc}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0x1f, 0}, INTEL_PT_BLK_4_CTX, 0 },
+	{5, {0x04, 1, 2, 3, 4}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0, 0x04030201}, INTEL_PT_BLK_4_CTX, 0 },
+	{5, {0xfc, 1, 2, 3, 4}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BIP, 0x1f, 0x04030201}, INTEL_PT_BLK_4_CTX, 0 },
+	/* 8-byte Block Item Packet */
+	{9, {0x04}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0, 0}, INTEL_PT_BLK_8_CTX, 0 },
+	{9, {0xfc}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0x1f, 0}, INTEL_PT_BLK_8_CTX, 0 },
+	{9, {0x04, 1, 2, 3, 4, 5, 6, 7, 8}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0, 0x0807060504030201}, INTEL_PT_BLK_8_CTX, 0 },
+	{9, {0xfc, 1, 2, 3, 4, 5, 6, 7, 8}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BIP, 0x1f, 0x0807060504030201}, INTEL_PT_BLK_8_CTX, 0 },
+	/* Block End Packet */
+	{2, {0x02, 0x33}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BEP, 0, 0}, 0, 0 },
+	{2, {0x02, 0xb3}, INTEL_PT_BLK_4_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 },
+	{2, {0x02, 0x33}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP, 0, 0}, 0, 0 },
+	{2, {0x02, 0xb3}, INTEL_PT_BLK_8_CTX, {INTEL_PT_BEP_IP, 0, 0}, 0, 0 },
+	/* Control Flow Event Packet */
+	{4, {0x02, 0x13, 0x01, 0x03}, 0, {INTEL_PT_CFE, 1, 3}, 0, 0 },
+	{4, {0x02, 0x13, 0x81, 0x03}, 0, {INTEL_PT_CFE_IP, 1, 3}, 0, 0 },
+	{4, {0x02, 0x13, 0x1f, 0x00}, 0, {INTEL_PT_CFE, 0x1f, 0}, 0, 0 },
+	{4, {0x02, 0x13, 0x9f, 0xff}, 0, {INTEL_PT_CFE_IP, 0x1f, 0xff}, 0, 0 },
+	/*  */
+	{11, {0x02, 0x53, 0x09, 1, 2, 3, 4, 5, 6, 7}, 0, {INTEL_PT_EVD, 0x09, 0x7060504030201}, 0, 0 },
+	{11, {0x02, 0x53, 0x3f, 2, 3, 4, 5, 6, 7, 8}, 0, {INTEL_PT_EVD, 0x3f, 0x8070605040302}, 0, 0 },
+	/* Terminator */
+	{0, {0}, 0, {0, 0, 0}, 0, 0 },
+};
+
+static int dump_packet(const struct intel_pt_pkt *packet, const u8 *bytes, int len)
+{
+	char desc[INTEL_PT_PKT_DESC_MAX];
+	int ret, i;
+
+	for (i = 0; i < len; i++)
+		pr_debug(" %02x", bytes[i]);
+	for (; i < INTEL_PT_PKT_MAX_SZ; i++)
+		pr_debug("   ");
+	pr_debug("   ");
+	ret = intel_pt_pkt_desc(packet, desc, INTEL_PT_PKT_DESC_MAX);
+	if (ret < 0) {
+		pr_debug("intel_pt_pkt_desc failed!\n");
+		return TEST_FAIL;
+	}
+	pr_debug("%s\n", desc);
+
+	return TEST_OK;
+}
+
+static void decoding_failed(const struct test_data *d)
+{
+	pr_debug("Decoding failed!\n");
+	pr_debug("Decoding:  ");
+	dump_packet(&d->packet, d->bytes, d->len);
+}
+
+static int fail(const struct test_data *d, struct intel_pt_pkt *packet, int len,
+		enum intel_pt_pkt_ctx new_ctx)
+{
+	decoding_failed(d);
+
+	if (len != d->len)
+		pr_debug("Expected length: %d   Decoded length %d\n",
+			 d->len, len);
+
+	if (packet->type != d->packet.type)
+		pr_debug("Expected type: %d   Decoded type %d\n",
+			 d->packet.type, packet->type);
+
+	if (packet->count != d->packet.count)
+		pr_debug("Expected count: %d   Decoded count %d\n",
+			 d->packet.count, packet->count);
+
+	if (packet->payload != d->packet.payload)
+		pr_debug("Expected payload: 0x%llx   Decoded payload 0x%llx\n",
+			 (unsigned long long)d->packet.payload,
+			 (unsigned long long)packet->payload);
+
+	if (new_ctx != d->new_ctx)
+		pr_debug("Expected packet context: %d   Decoded packet context %d\n",
+			 d->new_ctx, new_ctx);
+
+	return TEST_FAIL;
+}
+
+static int test_ctx_unchanged(const struct test_data *d, struct intel_pt_pkt *packet,
+			      enum intel_pt_pkt_ctx ctx)
+{
+	enum intel_pt_pkt_ctx old_ctx = ctx;
+
+	intel_pt_upd_pkt_ctx(packet, &ctx);
+
+	if (ctx != old_ctx) {
+		decoding_failed(d);
+		pr_debug("Packet context changed!\n");
+		return TEST_FAIL;
+	}
+
+	return TEST_OK;
+}
+
+static int test_one(const struct test_data *d)
+{
+	struct intel_pt_pkt packet;
+	enum intel_pt_pkt_ctx ctx = d->ctx;
+	int ret;
+
+	memset(&packet, 0xff, sizeof(packet));
+
+	/* Decode a packet */
+	ret = intel_pt_get_packet(d->bytes, d->len, &packet, &ctx);
+	if (ret < 0 || ret > INTEL_PT_PKT_MAX_SZ) {
+		decoding_failed(d);
+		pr_debug("intel_pt_get_packet returned %d\n", ret);
+		return TEST_FAIL;
+	}
+
+	/* Some packets must always leave the packet context unchanged */
+	if (d->ctx_unchanged) {
+		int err;
+
+		err = test_ctx_unchanged(d, &packet, INTEL_PT_NO_CTX);
+		if (err)
+			return err;
+		err = test_ctx_unchanged(d, &packet, INTEL_PT_BLK_4_CTX);
+		if (err)
+			return err;
+		err = test_ctx_unchanged(d, &packet, INTEL_PT_BLK_8_CTX);
+		if (err)
+			return err;
+	}
+
+	/* Compare to the expected values */
+	if (ret != d->len || packet.type != d->packet.type ||
+	    packet.count != d->packet.count ||
+	    packet.payload != d->packet.payload || ctx != d->new_ctx)
+		return fail(d, &packet, ret, ctx);
+
+	pr_debug("Decoded ok:");
+	ret = dump_packet(&d->packet, d->bytes, d->len);
+
+	return ret;
+}
+
+/*
+ * This test feeds byte sequences to the Intel PT packet decoder and checks the
+ * results. Changes to the packet context are also checked.
+ */
+int test__intel_pt_pkt_decoder(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	const struct test_data *d = data;
+	int ret;
+
+	for (d = data; d->len; d++) {
+		ret = test_one(d);
+		if (ret)
+			return ret;
+	}
+
+	return TEST_OK;
+}
+
+static int setaffinity(int cpu)
+{
+	cpu_set_t cpu_set;
+
+	CPU_ZERO(&cpu_set);
+	CPU_SET(cpu, &cpu_set);
+	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set)) {
+		pr_debug("sched_setaffinity() failed for CPU %d\n", cpu);
+		return -1;
+	}
+	return 0;
+}
+
+#define INTEL_PT_ADDR_FILT_CNT_MASK	GENMASK(2, 0)
+#define INTEL_PT_SUBLEAF_CNT		2
+#define CPUID_REG_CNT			4
+
+struct cpuid_result {
+	union {
+		struct {
+			unsigned int eax;
+			unsigned int ebx;
+			unsigned int ecx;
+			unsigned int edx;
+		};
+		unsigned int reg[CPUID_REG_CNT];
+	};
+};
+
+struct pt_caps {
+	struct cpuid_result subleaf[INTEL_PT_SUBLEAF_CNT];
+};
+
+static int get_pt_caps(int cpu, struct pt_caps *caps)
+{
+	struct cpuid_result r;
+	int i;
+
+	if (setaffinity(cpu))
+		return -1;
+
+	memset(caps, 0, sizeof(*caps));
+
+	for (i = 0; i < INTEL_PT_SUBLEAF_CNT; i++) {
+		cpuid(20, i, &r.eax, &r.ebx, &r.ecx, &r.edx);
+		pr_debug("CPU %d CPUID leaf 20 subleaf %d\n", cpu, i);
+		pr_debug("eax = 0x%08x\n", r.eax);
+		pr_debug("ebx = 0x%08x\n", r.ebx);
+		pr_debug("ecx = 0x%08x\n", r.ecx);
+		pr_debug("edx = 0x%08x\n", r.edx);
+		caps->subleaf[i] = r;
+	}
+
+	return 0;
+}
+
+static bool is_hybrid(void)
+{
+	unsigned int eax, ebx, ecx, edx = 0;
+	bool result;
+
+	cpuid(7, 0, &eax, &ebx, &ecx, &edx);
+	result = edx & BIT(15);
+	pr_debug("Is %shybrid : CPUID leaf 7 subleaf 0 edx %#x (bit-15 indicates hybrid)\n",
+		 result ? "" : "not ", edx);
+	return result;
+}
+
+static int compare_caps(int cpu, struct pt_caps *caps, struct pt_caps *caps0)
+{
+	struct pt_caps mask = { /* Mask of bits to check*/
+		.subleaf = {
+			[0] = {
+				.ebx = GENMASK(8, 0),
+				.ecx = GENMASK(3, 0),
+			},
+			[1] = {
+				.eax = GENMASK(31, 16),
+				.ebx = GENMASK(31, 0),
+			}
+		}
+	};
+	unsigned int m, reg, reg0;
+	int ret = 0;
+	int i, j;
+
+	for (i = 0; i < INTEL_PT_SUBLEAF_CNT; i++) {
+		for (j = 0; j < CPUID_REG_CNT; j++) {
+			m = mask.subleaf[i].reg[j];
+			reg = m & caps->subleaf[i].reg[j];
+			reg0 = m & caps0->subleaf[i].reg[j];
+			if ((reg & reg0) != reg0) {
+				pr_debug("CPU %d subleaf %d reg %d FAIL %#x vs %#x\n",
+					 cpu, i, j, reg, reg0);
+				ret = -1;
+			}
+		}
+	}
+
+	m = INTEL_PT_ADDR_FILT_CNT_MASK;
+	reg = m & caps->subleaf[1].eax;
+	reg0 = m & caps0->subleaf[1].eax;
+	if (reg < reg0) {
+		pr_debug("CPU %d subleaf 1 reg 0 FAIL address filter count %#x vs %#x\n",
+			 cpu, reg, reg0);
+		ret = -1;
+	}
+
+	if (!ret)
+		pr_debug("CPU %d OK\n", cpu);
+
+	return ret;
+}
+
+int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest)
+{
+	int max_cpu = cpu__max_cpu().cpu;
+	struct pt_caps last_caps;
+	struct pt_caps caps0;
+	int ret = TEST_OK;
+	int cpu;
+
+	if (!is_hybrid()) {
+		test->test_cases[subtest].skip_reason = "not hybrid";
+		return TEST_SKIP;
+	}
+
+	if (get_pt_caps(0, &caps0))
+		return TEST_FAIL;
+
+	for (cpu = 1, last_caps = caps0; cpu < max_cpu; cpu++) {
+		struct pt_caps caps;
+
+		if (get_pt_caps(cpu, &caps)) {
+			pr_debug("CPU %d not found\n", cpu);
+			continue;
+		}
+		if (!memcmp(&caps, &last_caps, sizeof(caps))) {
+			pr_debug("CPU %d same caps as previous CPU\n", cpu);
+			continue;
+		}
+		if (compare_caps(cpu, &caps, &caps0))
+			ret = TEST_FAIL;
+		last_caps = caps;
+	}
+
+	return ret;
+}

linux-7.2.3/tools/perf/arch/x86/tests/regs_load.S

@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+
+#define AX	 0
+#define BX	 1 * 8
+#define CX	 2 * 8
+#define DX	 3 * 8
+#define SI	 4 * 8
+#define DI	 5 * 8
+#define BP	 6 * 8
+#define SP	 7 * 8
+#define IP	 8 * 8
+#define FLAGS	 9 * 8
+#define CS	10 * 8
+#define SS	11 * 8
+#define DS	12 * 8
+#define ES	13 * 8
+#define FS	14 * 8
+#define GS	15 * 8
+#define R8	16 * 8
+#define R9	17 * 8
+#define R10	18 * 8
+#define R11	19 * 8
+#define R12	20 * 8
+#define R13	21 * 8
+#define R14	22 * 8
+#define R15	23 * 8
+
+.text
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+SYM_FUNC_START(perf_regs_load)
+	movq %rax, AX(%rdi)
+	movq %rbx, BX(%rdi)
+	movq %rcx, CX(%rdi)
+	movq %rdx, DX(%rdi)
+	movq %rsi, SI(%rdi)
+	movq %rdi, DI(%rdi)
+	movq %rbp, BP(%rdi)
+
+	leaq 8(%rsp), %rax /* exclude this call.  */
+	movq %rax, SP(%rdi)
+
+	movq 0(%rsp), %rax
+	movq %rax, IP(%rdi)
+
+	movq $0, FLAGS(%rdi)
+	movq $0, CS(%rdi)
+	movq $0, SS(%rdi)
+	movq $0, DS(%rdi)
+	movq $0, ES(%rdi)
+	movq $0, FS(%rdi)
+	movq $0, GS(%rdi)
+
+	movq %r8,  R8(%rdi)
+	movq %r9,  R9(%rdi)
+	movq %r10, R10(%rdi)
+	movq %r11, R11(%rdi)
+	movq %r12, R12(%rdi)
+	movq %r13, R13(%rdi)
+	movq %r14, R14(%rdi)
+	movq %r15, R15(%rdi)
+	ret
+SYM_FUNC_END(perf_regs_load)
+#else
+SYM_FUNC_START(perf_regs_load)
+	push %edi
+	movl 8(%esp), %edi
+	movl %eax, AX(%edi)
+	movl %ebx, BX(%edi)
+	movl %ecx, CX(%edi)
+	movl %edx, DX(%edi)
+	movl %esi, SI(%edi)
+	pop %eax
+	movl %eax, DI(%edi)
+	movl %ebp, BP(%edi)
+
+	leal 4(%esp), %eax /* exclude this call.  */
+	movl %eax, SP(%edi)
+
+	movl 0(%esp), %eax
+	movl %eax, IP(%edi)
+
+	movl $0, FLAGS(%edi)
+	movl $0, CS(%edi)
+	movl $0, SS(%edi)
+	movl $0, DS(%edi)
+	movl $0, ES(%edi)
+	movl $0, FS(%edi)
+	movl $0, GS(%edi)
+	ret
+SYM_FUNC_END(perf_regs_load)
+#endif
+
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits

linux-7.2.3/tools/perf/arch/x86/tests/topdown.c

@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include "arch-tests.h"
+#include "../util/topdown.h"
+#include "debug.h"
+#include "evlist.h"
+#include "parse-events.h"
+#include "pmu.h"
+#include "pmus.h"
+
+static int event_cb(void *state, struct pmu_event_info *info)
+{
+	char buf[256];
+	struct parse_events_error parse_err;
+	int *ret = state, err;
+	struct evlist *evlist = evlist__new();
+	struct evsel *evsel;
+
+	if (!evlist)
+		return -ENOMEM;
+
+	parse_events_error__init(&parse_err);
+	snprintf(buf, sizeof(buf), "%s/%s/", info->pmu->name, info->name);
+	err = parse_events(evlist, buf, &parse_err);
+	if (err) {
+		parse_events_error__print(&parse_err, buf);
+		*ret = TEST_FAIL;
+	}
+	parse_events_error__exit(&parse_err);
+	evlist__for_each_entry(evlist, evsel) {
+		bool fail = false;
+		bool p_core_pmu = evsel->pmu->type == PERF_TYPE_RAW;
+		const char *name = evsel__name(evsel);
+
+		if (strcasestr(name, "uops_retired.slots") ||
+		    strcasestr(name, "topdown.backend_bound_slots") ||
+		    strcasestr(name, "topdown.br_mispredict_slots") ||
+		    strcasestr(name, "topdown.memory_bound_slots") ||
+		    strcasestr(name, "topdown.bad_spec_slots") ||
+		    strcasestr(name, "topdown.slots_p")) {
+			if (arch_is_topdown_slots(evsel) || arch_is_topdown_metrics(evsel))
+				fail = true;
+		} else if (strcasestr(name, "slots")) {
+			if (arch_is_topdown_slots(evsel) != p_core_pmu ||
+			    arch_is_topdown_metrics(evsel))
+				fail = true;
+		} else if (strcasestr(name, "topdown")) {
+			if (arch_is_topdown_slots(evsel) ||
+			    arch_is_topdown_metrics(evsel) != p_core_pmu)
+				fail = true;
+		} else if (arch_is_topdown_slots(evsel) || arch_is_topdown_metrics(evsel)) {
+			fail = true;
+		}
+		if (fail) {
+			pr_debug("Broken topdown information for '%s'\n", evsel__name(evsel));
+			*ret = TEST_FAIL;
+		}
+	}
+	evlist__delete(evlist);
+	return 0;
+}
+
+static int test__x86_topdown(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	int ret = TEST_OK;
+	struct perf_pmu *pmu = NULL;
+
+	if (!topdown_sys_has_perf_metrics())
+		return TEST_OK;
+
+	while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+		if (perf_pmu__for_each_event(pmu, /*skip_duplicate_pmus=*/false, &ret, event_cb))
+			break;
+	}
+	return ret;
+}
+
+#define CHECK_COND(cond, text)					\
+do {								\
+	if (!(cond)) {						\
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		ret = TEST_FAIL;				\
+		goto out_err;					\
+	}							\
+} while (0)
+
+#define CHECK_EQUAL(val, expected, text)			\
+do {								\
+	if ((val) != (expected)) {				\
+		pr_debug("FAILED %s:%d %s (%d != %d)\n",	\
+			 __FILE__, __LINE__, text, (val), (expected)); \
+		ret = TEST_FAIL;				\
+		goto out_err;					\
+	}							\
+} while (0)
+
+static int test_sort(const char *str, int expected_slots_group_size,
+		     int expected_instructions_group_size)
+{
+	struct evlist *evlist = NULL;
+	struct parse_events_error err;
+	struct evsel *evsel;
+	int ret = TEST_FAIL;
+	bool slots_seen = false;
+
+	parse_events_error__init(&err);
+
+	evlist = evlist__new();
+	if (!evlist)
+		goto out_err;
+
+	if (parse_events(evlist, str, &err)) {
+		pr_debug("parse_events failed for %s\n", str);
+		goto out_err;
+	}
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (!evsel__is_group_leader(evsel))
+			continue;
+
+		if (strstr(evsel__name(evsel), "slots")) {
+			/*
+			 * Slots as a leader means the PMU is for a perf metric
+			 * group as the slots event isn't present when not.
+			 */
+			slots_seen = true;
+			CHECK_EQUAL(evsel->core.nr_members, expected_slots_group_size,
+				    "slots group size");
+			if (expected_slots_group_size == 3) {
+				struct evsel *next = evsel__next(evsel);
+				struct evsel *next2 = evsel__next(next);
+
+				CHECK_COND(strstr(evsel__name(next), "instructions") != NULL,
+					   "slots second event is instructions");
+				CHECK_COND(strstr(evsel__name(next2), "topdown-retiring") != NULL,
+					   "slots third event is topdown-retiring");
+			} else if (expected_slots_group_size == 2) {
+				struct evsel *next = evsel__next(evsel);
+
+				CHECK_COND(strstr(evsel__name(next), "topdown-retiring") != NULL,
+					   "slots second event is topdown-retiring");
+			}
+		} else if (strstr(evsel__name(evsel), "instructions")) {
+			CHECK_EQUAL(evsel->core.nr_members, expected_instructions_group_size,
+				    "instructions group size");
+			if (expected_instructions_group_size == 2) {
+				/*
+				 * On Intel hybrid CPUs (e.g., Alder Lake/
+				 * Raptor Lake), E-cores (cpu_atom) do not
+				 * support/enforce the slots event. When
+				 * parsing event groups containing slots
+				 * across all PMUs, slots is automatically
+				 * filtered out from cpu_atom, leaving
+				 * {cpu_atom/instructions/,
+				 *  cpu_atom/topdown-retiring/}. On cpu_atom,
+				 * instructions correctly leads this group of
+				 * 2 without slots reordering.
+				 */
+				struct evsel *next = evsel__next(evsel);
+
+				CHECK_COND(strstr(evsel__name(next), "topdown-retiring") != NULL,
+					   "instructions second event is topdown-retiring");
+			}
+		} else if (strstr(evsel__name(evsel), "topdown-retiring")) {
+			/*
+			 * A perf metric event where the PMU doesn't require
+			 * slots as a leader.
+			 */
+			CHECK_EQUAL(evsel->core.nr_members, 1, "topdown-retiring group size");
+		} else if (strstr(evsel__name(evsel), "cycles")) {
+			CHECK_EQUAL(evsel->core.nr_members, 1, "cycles group size");
+		}
+	}
+	CHECK_COND(slots_seen, "slots seen");
+	ret = TEST_OK;
+out_err:
+	evlist__delete(evlist);
+	parse_events_error__exit(&err);
+	return ret;
+}
+
+static int test__x86_topdown_sorting(struct test_suite *test __maybe_unused,
+				     int subtest __maybe_unused)
+{
+	int ret;
+
+	if (!topdown_sys_has_perf_metrics())
+		return TEST_OK;
+
+	ret = test_sort("{instructions,topdown-retiring,slots}", 3, 2);
+	TEST_ASSERT_EQUAL("all events in a group", ret, TEST_OK);
+	ret = test_sort("instructions,topdown-retiring,slots", 2, 1);
+	TEST_ASSERT_EQUAL("all events not in a group", ret, TEST_OK);
+	ret = test_sort("{instructions,slots},topdown-retiring", 2, 1);
+	TEST_ASSERT_EQUAL("slots event in a group but topdown metrics events outside the group",
+			  ret, TEST_OK);
+	ret = test_sort("{instructions,slots},{topdown-retiring}", 2, 1);
+	TEST_ASSERT_EQUAL("slots event and topdown metrics events in two groups",
+			  ret, TEST_OK);
+	ret = test_sort("{instructions,slots},cycles,topdown-retiring", 2, 1);
+	TEST_ASSERT_EQUAL("slots event and metrics event are not in a group and not adjacent",
+			  ret, TEST_OK);
+
+	return TEST_OK;
+}
+
+static int test__x86_topdown_slots_injection(struct test_suite *test __maybe_unused,
+					     int subtest __maybe_unused)
+{
+	int ret;
+
+	if (!topdown_sys_has_perf_metrics())
+		return TEST_OK;
+
+	ret = test_sort("{instructions,topdown-retiring}", 3, 2);
+	TEST_ASSERT_EQUAL("all events in a group", ret, TEST_OK);
+	ret = test_sort("instructions,topdown-retiring", 2, 1);
+	TEST_ASSERT_EQUAL("all events not in a group", ret, TEST_OK);
+	ret = test_sort("{instructions},topdown-retiring", 2, 1);
+	TEST_ASSERT_EQUAL("event in a group but topdown metrics events outside the group",
+			  ret, TEST_OK);
+	ret = test_sort("{instructions},{topdown-retiring}", 2, 1);
+	TEST_ASSERT_EQUAL("event and topdown metrics events in two groups",
+			  ret, TEST_OK);
+	ret = test_sort("{instructions},cycles,topdown-retiring", 2, 1);
+	TEST_ASSERT_EQUAL("event and metrics event are not in a group and not adjacent",
+			  ret, TEST_OK);
+
+	return TEST_OK;
+}
+
+static struct test_case x86_topdown_tests[] = {
+	TEST_CASE("topdown events", x86_topdown),
+	TEST_CASE("topdown sorting", x86_topdown_sorting),
+	TEST_CASE("topdown slots injection", x86_topdown_slots_injection),
+	{ .name = NULL, }
+};
+
+struct test_suite suite__x86_topdown = {
+	.desc = "x86 topdown",
+	.test_cases = x86_topdown_tests,
+};

linux-7.2.3/tools/perf/arch/x86/util/Build

@@ -0,0 +1,13 @@
+perf-util-y += header.o
+perf-util-y += tsc.o
+perf-util-y += pmu.o
+perf-util-y += topdown.o
+perf-util-y += machine.o
+perf-util-y += event.o
+perf-util-y += evlist.o
+perf-util-y += mem-events.o
+perf-util-y += evsel.o
+perf-util-y += iostat.o
+perf-util-y += auxtrace.o
+perf-util-y += intel-pt.o
+perf-util-y += intel-bts.o

linux-7.2.3/tools/perf/arch/x86/util/auxtrace.c

@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * auxtrace.c: AUX area tracing support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ */
+
+#include <errno.h>
+#include <stdbool.h>
+
+#include "../../../util/header.h"
+#include "../../../util/debug.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmus.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/evlist.h"
+
+static
+struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist,
+						    int *err)
+{
+	struct perf_pmu *intel_pt_pmu;
+	struct perf_pmu *intel_bts_pmu;
+	struct evsel *evsel;
+	bool found_pt = false;
+	bool found_bts = false;
+
+	intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME);
+	intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME);
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type)
+			found_pt = true;
+		if (intel_bts_pmu && evsel->core.attr.type == intel_bts_pmu->type)
+			found_bts = true;
+	}
+
+	if (found_pt && found_bts) {
+		pr_err("intel_pt and intel_bts may not be used together\n");
+		*err = -EINVAL;
+		return NULL;
+	}
+
+	if (found_pt)
+		return intel_pt_recording_init(err);
+
+	if (found_bts)
+		return intel_bts_recording_init(err);
+
+	return NULL;
+}
+
+struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,
+					      int *err)
+{
+	char buffer[64];
+	struct perf_cpu cpu = perf_cpu_map__min(evlist->core.all_cpus);
+	int ret;
+
+	*err = 0;
+
+	ret = get_cpuid(buffer, sizeof(buffer), cpu);
+	if (ret) {
+		*err = ret;
+		return NULL;
+	}
+
+	if (!strncmp(buffer, "GenuineIntel,", 13))
+		return auxtrace_record__init_intel(evlist, err);
+
+	return NULL;
+}

linux-7.2.3/tools/perf/arch/x86/util/cpuid.h

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_CPUID_H
+#define PERF_CPUID_H 1
+
+
+static inline void
+cpuid(unsigned int op, unsigned int op2, unsigned int *a, unsigned int *b,
+	unsigned int *c, unsigned int *d)
+{
+	/*
+	 * Preserve %ebx/%rbx register by either placing it in %rdi or saving it
+	 * on the stack - x86-64 needs to avoid the stack red zone. In PIC
+	 * compilations %ebx contains the address of the global offset
+	 * table. %rbx is occasionally used to address stack variables in
+	 * presence of dynamic allocas.
+	 */
+	asm(
+#if defined(__x86_64__)
+		"mov %%rbx, %%rdi\n"
+		"cpuid\n"
+		"xchg %%rdi, %%rbx\n"
+#else
+		"pushl %%ebx\n"
+		"cpuid\n"
+		"movl %%ebx, %%edi\n"
+		"popl %%ebx\n"
+#endif
+		: "=a"(*a), "=D"(*b), "=c"(*c), "=d"(*d)
+		: "a"(op), "2"(op2));
+}
+
+void get_cpuid_0(char *vendor, unsigned int *lvl);
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/event.c

@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
+#include <stdlib.h>
+
+#include "../../../util/event.h"
+#include "../../../util/synthetic-events.h"
+#include "../../../util/machine.h"
+#include "../../../util/tool.h"
+#include "../../../util/map.h"
+#include "../../../util/debug.h"
+#include "util/sample.h"
+
+#if defined(__x86_64__)
+
+struct perf_event__synthesize_extra_kmaps_cb_args {
+	const struct perf_tool *tool;
+	perf_event__handler_t process;
+	struct machine *machine;
+	union perf_event *event;
+};
+
+static int perf_event__synthesize_extra_kmaps_cb(struct map *map, void *data)
+{
+	struct perf_event__synthesize_extra_kmaps_cb_args *args = data;
+	union perf_event *event = args->event;
+	struct kmap *kmap;
+	size_t size;
+
+	if (!__map__is_extra_kernel_map(map))
+		return 0;
+
+	kmap = map__kmap(map);
+
+	size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
+		      PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
+		      args->machine->id_hdr_size;
+
+	memset(event, 0, size);
+
+	event->mmap.header.type = PERF_RECORD_MMAP;
+
+	/*
+	 * kernel uses 0 for user space maps, see kernel/perf_event.c
+	 * __perf_event_mmap
+	 */
+	if (machine__is_host(args->machine))
+		event->header.misc = PERF_RECORD_MISC_KERNEL;
+	else
+		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+	event->mmap.header.size = size;
+
+	event->mmap.start = map__start(map);
+	event->mmap.len   = map__size(map);
+	event->mmap.pgoff = map__pgoff(map);
+	event->mmap.pid   = args->machine->pid;
+
+	strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
+
+	if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0)
+		return -1;
+
+	return 0;
+}
+
+int perf_event__synthesize_extra_kmaps(const struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int rc;
+	struct maps *kmaps = machine__kernel_maps(machine);
+	struct perf_event__synthesize_extra_kmaps_cb_args args = {
+		.tool = tool,
+		.process = process,
+		.machine = machine,
+		.event = zalloc(sizeof(args.event->mmap) + machine->id_hdr_size),
+	};
+
+	if (!args.event) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for extra kernel maps\n");
+		return -1;
+	}
+
+	rc = maps__for_each_map(kmaps, perf_event__synthesize_extra_kmaps_cb, &args);
+
+	free(args.event);
+	return rc;
+}
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/evlist.c

@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "topdown.h"
+#include "evsel.h"
+
+int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
+{
+	/*
+	 * Currently the following topdown events sequence are supported to
+	 * move and regroup correctly.
+	 *
+	 * a. all events in a group
+	 *    perf stat -e "{instructions,topdown-retiring,slots}" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *          15,066,240     slots
+	 *          1,899,760      instructions
+	 *          2,126,998      topdown-retiring
+	 * b. all events not in a group
+	 *    perf stat -e "instructions,topdown-retiring,slots" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *          2,045,561      instructions
+	 *          17,108,370     slots
+	 *          2,281,116      topdown-retiring
+	 * c. slots event in a group but topdown metrics events outside the group
+	 *    perf stat -e "{instructions,slots},topdown-retiring" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *         20,323,878      slots
+	 *          2,634,884      instructions
+	 *          3,028,656      topdown-retiring
+	 * d. slots event and topdown metrics events in two groups
+	 *    perf stat -e "{instructions,slots},{topdown-retiring}" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *         26,319,024      slots
+	 *          2,427,791      instructions
+	 *          2,683,508      topdown-retiring
+	 * e. slots event and metrics event are not in a group and not adjacent
+	 *    perf stat -e "{instructions,slots},cycles,topdown-retiring" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *         68,433,522      slots
+	 *          8,856,102      topdown-retiring
+	 *          7,791,494      instructions
+	 *         11,469,513      cycles
+	 */
+	if (topdown_sys_has_perf_metrics() &&
+	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
+		/* Ensure the topdown slots comes first. */
+		if (arch_is_topdown_slots(lhs))
+			return -1;
+		if (arch_is_topdown_slots(rhs))
+			return 1;
+
+		/*
+		 * Move topdown metrics events forward only when topdown metrics
+		 * events are not in same group with previous slots event. If
+		 * topdown metrics events are already in same group with slots
+		 * event, do nothing.
+		 */
+		if (lhs->core.leader != rhs->core.leader) {
+			bool lhs_topdown = arch_is_topdown_metrics(lhs);
+			bool rhs_topdown = arch_is_topdown_metrics(rhs);
+
+			if (lhs_topdown && !rhs_topdown)
+				return -1;
+			if (!lhs_topdown && rhs_topdown)
+				return 1;
+		}
+	}
+
+	/* Retire latency event should not be group leader*/
+	if (lhs->retire_lat && !rhs->retire_lat)
+		return 1;
+	if (!lhs->retire_lat && rhs->retire_lat)
+		return -1;
+
+	/* Default ordering by insertion index. */
+	return lhs->core.idx - rhs->core.idx;
+}
+
+int arch_evlist__add_required_events(struct list_head *list)
+{
+	struct evsel *pos, *metric_event = NULL;
+	int idx = 0;
+
+	if (!topdown_sys_has_perf_metrics())
+		return 0;
+
+	list_for_each_entry(pos, list, core.node) {
+		if (arch_is_topdown_slots(pos)) {
+			/* Slots event already present, nothing to do. */
+			return 0;
+		}
+		if (metric_event == NULL && arch_is_topdown_metrics(pos))
+			metric_event = pos;
+		idx++;
+	}
+	if (metric_event == NULL) {
+		/* No topdown metric events, nothing to do. */
+		return 0;
+	}
+	return topdown_insert_slots_event(list, idx + 1, metric_event);
+}

linux-7.2.3/tools/perf/arch/x86/util/evsel.c

@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/evsel_config.h"
+#include "util/env.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
+#include "util/stat.h"
+#include "util/strbuf.h"
+#include "linux/string.h"
+#include "topdown.h"
+#include "evsel.h"
+#include "util/debug.h"
+#include "env.h"
+
+#define IBS_FETCH_L3MISSONLY   (1ULL << 59)
+#define IBS_OP_L3MISSONLY      (1ULL << 16)
+
+void arch_evsel__set_sample_weight(struct evsel *evsel)
+{
+	evsel__set_sample_bit(evsel, WEIGHT_STRUCT);
+}
+
+/* Check whether the evsel's PMU supports the perf metrics */
+bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
+{
+	struct perf_pmu *pmu;
+
+	if (!topdown_sys_has_perf_metrics())
+		return false;
+
+	/*
+	 * The PERF_TYPE_RAW type is the core PMU type, e.g., "cpu" PMU on a
+	 * non-hybrid machine, "cpu_core" PMU on a hybrid machine.  The
+	 * topdown_sys_has_perf_metrics checks the slots event is only available
+	 * for the core PMU, which supports the perf metrics feature. Checking
+	 * both the PERF_TYPE_RAW type and the slots event should be good enough
+	 * to detect the perf metrics feature.
+	 */
+	pmu = evsel__find_pmu(evsel);
+	return pmu && pmu->type == PERF_TYPE_RAW;
+}
+
+bool arch_evsel__must_be_in_group(const struct evsel *evsel)
+{
+	if (!evsel__sys_has_perf_metrics(evsel))
+		return false;
+
+	return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel);
+}
+
+int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
+{
+	u64 event = evsel->core.attr.config & PERF_HW_EVENT_MASK;
+	u64 pmu = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
+	const char *event_name;
+
+	if (event < PERF_COUNT_HW_MAX && evsel__hw_names[event])
+		event_name = evsel__hw_names[event];
+	else
+		event_name = "unknown-hardware";
+
+	/* The PMU type is not required for the non-hybrid platform. */
+	if (!pmu)
+		return  scnprintf(bf, size, "%s", event_name);
+
+	return scnprintf(bf, size, "%s/%s/",
+			 evsel->pmu ? evsel->pmu->name : "cpu",
+			 event_name);
+}
+
+void arch_evsel__apply_ratio_to_prev(struct evsel *evsel,
+				struct perf_event_attr *attr)
+{
+	struct perf_event_attr *prev_attr = NULL;
+	struct evsel *evsel_prev = NULL;
+	const char *name = "acr_mask";
+	int evsel_idx = 0;
+	__u64 ev_mask, pr_ev_mask;
+
+	if (!perf_pmu__has_format(evsel->pmu, name)) {
+		pr_err("'%s' does not have acr_mask format support\n", evsel->pmu->name);
+		return;
+	}
+	if (perf_pmu__format_type(evsel->pmu, name) !=
+			PERF_PMU_FORMAT_VALUE_CONFIG2) {
+		pr_err("'%s' does not have config2 format support\n", evsel->pmu->name);
+		return;
+	}
+
+	evsel_prev = evsel__prev(evsel);
+	if (!evsel_prev) {
+		pr_err("Previous event does not exist.\n");
+		return;
+	}
+
+	prev_attr = &evsel_prev->core.attr;
+
+	if (prev_attr->config2) {
+		pr_err("'%s' has set config2 (acr_mask?) already, configuration not supported\n", evsel_prev->name);
+		return;
+	}
+
+	/*
+	 * acr_mask (config2) is calculated using the event's index in
+	 * the event group. The first event will use the index of the
+	 * second event as its mask (e.g., 0x2), indicating that the
+	 * second event counter will be reset and a sample taken for
+	 * the first event if its counter overflows. The second event
+	 * will use the mask consisting of the first and second bits
+	 * (e.g., 0x3), meaning both counters will be reset if the
+	 * second event counter overflows.
+	 */
+
+	evsel_idx = evsel__group_idx(evsel);
+	ev_mask = 1ull << evsel_idx;
+	pr_ev_mask = 1ull << (evsel_idx - 1);
+
+	prev_attr->config2 = ev_mask;
+	attr->config2 = ev_mask | pr_ev_mask;
+}
+
+static void ibs_l3miss_warn(void)
+{
+	pr_warning(
+"WARNING: Hw internally resets sampling period when L3 Miss Filtering is enabled\n"
+"and tagged operation does not cause L3 Miss. This causes sampling period skew.\n");
+}
+
+void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr)
+{
+	struct perf_pmu *evsel_pmu, *ibs_fetch_pmu, *ibs_op_pmu;
+	static int warned_once;
+
+	if (warned_once || !x86__is_amd_cpu())
+		return;
+
+	evsel_pmu = evsel__find_pmu(evsel);
+	if (!evsel_pmu)
+		return;
+
+	ibs_fetch_pmu = perf_pmus__find("ibs_fetch");
+	ibs_op_pmu = perf_pmus__find("ibs_op");
+
+	if (ibs_fetch_pmu && ibs_fetch_pmu->type == evsel_pmu->type) {
+		if (attr->config & IBS_FETCH_L3MISSONLY) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	} else if (ibs_op_pmu && ibs_op_pmu->type == evsel_pmu->type) {
+		if (attr->config & IBS_OP_L3MISSONLY) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	}
+}
+
+static int amd_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size)
+{
+	struct perf_pmu *pmu;
+
+	if (evsel->core.attr.precise_ip == 0)
+		return 0;
+
+	pmu = evsel__find_pmu(evsel);
+	if (!pmu || strncmp(pmu->name, "ibs", 3))
+		return 0;
+
+	/* More verbose IBS errors. */
+	if (evsel->core.attr.exclude_kernel || evsel->core.attr.exclude_user ||
+	    evsel->core.attr.exclude_hv || evsel->core.attr.exclude_idle ||
+	    evsel->core.attr.exclude_host || evsel->core.attr.exclude_guest) {
+		return scnprintf(msg, size, "AMD IBS doesn't support privilege filtering. Try "
+				 "again without the privilege modifiers (like 'k') at the end.");
+	}
+	return 0;
+}
+
+static int intel_evsel__open_strerror(struct evsel *evsel, int err, char *msg, size_t size)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int ret;
+
+	if (err != EINVAL)
+		return 0;
+
+	if (!topdown_sys_has_perf_metrics())
+		return 0;
+
+	if (arch_is_topdown_slots(evsel)) {
+		if (!evsel__is_group_leader(evsel)) {
+			evlist__uniquify_evsel_names(evsel->evlist, &stat_config);
+			evlist__format_evsels(evsel->evlist, &sb, 2048);
+			ret = scnprintf(msg, size, "Topdown slots event can only be group leader "
+					"in '%s'.", sb.buf);
+			strbuf_release(&sb);
+			return ret;
+		}
+	} else if (arch_is_topdown_metrics(evsel)) {
+		struct evsel *pos;
+
+		evlist__for_each_entry(evsel->evlist, pos) {
+			if (pos == evsel || !arch_is_topdown_metrics(pos))
+				continue;
+
+			if (pos->core.attr.config != evsel->core.attr.config)
+				continue;
+
+			evlist__uniquify_evsel_names(evsel->evlist, &stat_config);
+			evlist__format_evsels(evsel->evlist, &sb, 2048);
+			ret = scnprintf(msg, size, "Perf metric event '%s' is duplicated "
+					"in the same group (only one event is allowed) in '%s'.",
+					evsel__name(evsel), sb.buf);
+			strbuf_release(&sb);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+int arch_evsel__open_strerror(struct evsel *evsel, int err, char *msg, size_t size)
+{
+	return x86__is_amd_cpu()
+		? amd_evsel__open_strerror(evsel, msg, size)
+		: intel_evsel__open_strerror(evsel, err, msg, size);
+}

linux-7.2.3/tools/perf/arch/x86/util/evsel.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _EVSEL_H
+#define _EVSEL_H 1
+
+bool evsel__sys_has_perf_metrics(const struct evsel *evsel);
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/header.c

@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/types.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <regex.h>
+
+#include "../../../util/debug.h"
+#include "../../../util/header.h"
+#include "cpuid.h"
+
+void get_cpuid_0(char *vendor, unsigned int *lvl)
+{
+	unsigned int b, c, d;
+
+	cpuid(0, 0, lvl, &b, &c, &d);
+	strncpy(&vendor[0], (char *)(&b), 4);
+	strncpy(&vendor[4], (char *)(&d), 4);
+	strncpy(&vendor[8], (char *)(&c), 4);
+	vendor[12] = '\0';
+}
+
+static int
+__get_cpuid(char *buffer, size_t sz, const char *fmt)
+{
+	unsigned int a, b, c, d, lvl;
+	int family = -1, model = -1, step = -1;
+	int nb;
+	char vendor[16];
+
+	get_cpuid_0(vendor, &lvl);
+
+	if (lvl >= 1) {
+		cpuid(1, 0, &a, &b, &c, &d);
+
+		family = (a >> 8) & 0xf;  /* bits 11 - 8 */
+		model  = (a >> 4) & 0xf;  /* Bits  7 - 4 */
+		step   = a & 0xf;
+
+		/* extended family */
+		if (family == 0xf)
+			family += (a >> 20) & 0xff;
+
+		/* extended model */
+		if (family >= 0x6)
+			model += ((a >> 16) & 0xf) << 4;
+	}
+	nb = scnprintf(buffer, sz, fmt, vendor, family, model, step);
+
+	/* look for end marker to ensure the entire data fit */
+	if (strchr(buffer, '$')) {
+		buffer[nb-1] = '\0';
+		return 0;
+	}
+	return ENOBUFS;
+}
+
+int
+get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
+{
+	return __get_cpuid(buffer, sz, "%s,%u,%u,%u$");
+}
+
+char *get_cpuid_str(struct perf_cpu cpu __maybe_unused)
+{
+	char *buf = malloc(128);
+
+	if (buf && __get_cpuid(buf, 128, "%s-%u-%X-%X$") < 0) {
+		free(buf);
+		return NULL;
+	}
+	return buf;
+}
+
+/* Full CPUID format for x86 is vendor-family-model-stepping */
+static bool is_full_cpuid(const char *id)
+{
+	const char *tmp = id;
+	int count = 0;
+
+	while ((tmp = strchr(tmp, '-')) != NULL) {
+		count++;
+		tmp++;
+	}
+
+	if (count == 3)
+		return true;
+
+	return false;
+}
+
+int strcmp_cpuid_str(const char *mapcpuid, const char *id)
+{
+	regex_t re;
+	regmatch_t pmatch[1];
+	int match;
+	bool full_mapcpuid = is_full_cpuid(mapcpuid);
+	bool full_cpuid = is_full_cpuid(id);
+
+	/*
+	 * Full CPUID format is required to identify a platform.
+	 * Error out if the cpuid string is incomplete.
+	 */
+	if (full_mapcpuid && !full_cpuid) {
+		pr_info("Invalid CPUID %s. Full CPUID is required, "
+			"vendor-family-model-stepping\n", id);
+		return 1;
+	}
+
+	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
+		/* Warn unable to generate match particular string. */
+		pr_info("Invalid regular expression %s\n", mapcpuid);
+		return 1;
+	}
+
+	match = !regexec(&re, id, 1, pmatch, 0);
+	regfree(&re);
+	if (match) {
+		size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+		size_t cpuid_len;
+
+		/* If the full CPUID format isn't required,
+		 * ignoring the stepping.
+		 */
+		if (!full_mapcpuid && full_cpuid)
+			cpuid_len = strrchr(id, '-') - id;
+		else
+			cpuid_len = strlen(id);
+
+		/* Verify the entire string matched. */
+		if (match_len == cpuid_len)
+			return 0;
+	}
+
+	return 1;
+}

linux-7.2.3/tools/perf/arch/x86/util/intel-bts.c

@@ -0,0 +1,453 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * intel-bts.c: Intel Processor Trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ */
+
+#include "../../../util/intel-bts.h"
+
+#include <errno.h>
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <linux/types.h>
+#include <linux/zalloc.h>
+
+#include <internal/lib.h> // page_size
+
+#include "../../../util/auxtrace.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/debug.h"
+#include "../../../util/event.h"
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "../../../util/mmap.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmus.h"
+#include "../../../util/record.h"
+#include "../../../util/session.h"
+#include "../../../util/tsc.h"
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+#define KiB_MASK(x) (KiB(x) - 1)
+#define MiB_MASK(x) (MiB(x) - 1)
+
+struct intel_bts_snapshot_ref {
+	void	*ref_buf;
+	size_t	ref_offset;
+	bool	wrapped;
+};
+
+struct intel_bts_recording {
+	struct auxtrace_record		itr;
+	struct perf_pmu			*intel_bts_pmu;
+	struct evlist		*evlist;
+	bool				snapshot_mode;
+	size_t				snapshot_size;
+	int				snapshot_ref_cnt;
+	struct intel_bts_snapshot_ref	*snapshot_refs;
+};
+
+struct branch {
+	u64 from;
+	u64 to;
+	u64 misc;
+};
+
+static size_t
+intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+			 struct evlist *evlist __maybe_unused)
+{
+	return INTEL_BTS_AUXTRACE_PRIV_SIZE;
+}
+
+static int intel_bts_info_fill(struct auxtrace_record *itr,
+			       struct perf_session *session,
+			       struct perf_record_auxtrace_info *auxtrace_info,
+			       size_t priv_size)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
+	struct perf_event_mmap_page *pc;
+	struct perf_tsc_conversion tc = { .time_mult = 0, };
+	bool cap_user_time_zero = false;
+	int err;
+
+	if (priv_size != INTEL_BTS_AUXTRACE_PRIV_SIZE)
+		return -EINVAL;
+
+	if (!session->evlist->core.nr_mmaps)
+		return -EINVAL;
+
+	pc = session->evlist->mmap[0].core.base;
+	if (pc) {
+		err = perf_read_tsc_conversion(pc, &tc);
+		if (err) {
+			if (err != -EOPNOTSUPP)
+				return err;
+		} else {
+			cap_user_time_zero = tc.time_mult != 0;
+		}
+		if (!cap_user_time_zero)
+			ui__warning("Intel BTS: TSC not available\n");
+	}
+
+	auxtrace_info->type = PERF_AUXTRACE_INTEL_BTS;
+	auxtrace_info->priv[INTEL_BTS_PMU_TYPE] = intel_bts_pmu->type;
+	auxtrace_info->priv[INTEL_BTS_TIME_SHIFT] = tc.time_shift;
+	auxtrace_info->priv[INTEL_BTS_TIME_MULT] = tc.time_mult;
+	auxtrace_info->priv[INTEL_BTS_TIME_ZERO] = tc.time_zero;
+	auxtrace_info->priv[INTEL_BTS_CAP_USER_TIME_ZERO] = cap_user_time_zero;
+	auxtrace_info->priv[INTEL_BTS_SNAPSHOT_MODE] = btsr->snapshot_mode;
+
+	return 0;
+}
+
+static int intel_bts_recording_options(struct auxtrace_record *itr,
+				       struct evlist *evlist,
+				       struct record_opts *opts)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu;
+	struct evsel *evsel, *intel_bts_evsel = NULL;
+	const struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
+	bool privileged = perf_event_paranoid_check(-1);
+
+	if (opts->auxtrace_sample_mode) {
+		pr_err("Intel BTS does not support AUX area sampling\n");
+		return -EINVAL;
+	}
+
+	btsr->evlist = evlist;
+	btsr->snapshot_mode = opts->auxtrace_snapshot_mode;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->core.attr.type == intel_bts_pmu->type) {
+			if (intel_bts_evsel) {
+				pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n");
+				return -EINVAL;
+			}
+			evsel->core.attr.freq = 0;
+			evsel->core.attr.sample_period = 1;
+			evsel->needs_auxtrace_mmap = true;
+			intel_bts_evsel = evsel;
+			opts->full_auxtrace = true;
+		}
+	}
+
+	if (opts->auxtrace_snapshot_mode && !opts->full_auxtrace) {
+		pr_err("Snapshot mode (-S option) requires " INTEL_BTS_PMU_NAME " PMU event (-e " INTEL_BTS_PMU_NAME ")\n");
+		return -EINVAL;
+	}
+
+	if (!opts->full_auxtrace)
+		return 0;
+
+	if (opts->full_auxtrace && !perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
+		pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n");
+		return -EINVAL;
+	}
+
+	/* Set default sizes for snapshot mode */
+	if (opts->auxtrace_snapshot_mode) {
+		if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) {
+			if (privileged) {
+				opts->auxtrace_mmap_pages = MiB(4) / page_size;
+			} else {
+				opts->auxtrace_mmap_pages = KiB(128) / page_size;
+				if (opts->mmap_pages == UINT_MAX)
+					opts->mmap_pages = KiB(256) / page_size;
+			}
+		} else if (!opts->auxtrace_mmap_pages && !privileged &&
+			   opts->mmap_pages == UINT_MAX) {
+			opts->mmap_pages = KiB(256) / page_size;
+		}
+		if (!opts->auxtrace_snapshot_size)
+			opts->auxtrace_snapshot_size =
+				opts->auxtrace_mmap_pages * (size_t)page_size;
+		if (!opts->auxtrace_mmap_pages) {
+			size_t sz = opts->auxtrace_snapshot_size;
+
+			sz = round_up(sz, page_size) / page_size;
+			opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+		}
+		if (opts->auxtrace_snapshot_size >
+				opts->auxtrace_mmap_pages * (size_t)page_size) {
+			pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+			       opts->auxtrace_snapshot_size,
+			       opts->auxtrace_mmap_pages * (size_t)page_size);
+			return -EINVAL;
+		}
+		if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) {
+			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+			return -EINVAL;
+		}
+		pr_debug2("Intel BTS snapshot size: %zu\n",
+			  opts->auxtrace_snapshot_size);
+	}
+
+	/* Set default sizes for full trace mode */
+	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+	}
+
+	/* Validate auxtrace_mmap_pages */
+	if (opts->auxtrace_mmap_pages) {
+		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+		size_t min_sz;
+
+		if (opts->auxtrace_snapshot_mode)
+			min_sz = KiB(4);
+		else
+			min_sz = KiB(8);
+
+		if (sz < min_sz || !is_power_of_2(sz)) {
+			pr_err("Invalid mmap size for Intel BTS: must be at least %zuKiB and a power of 2\n",
+			       min_sz / 1024);
+			return -EINVAL;
+		}
+	}
+
+	if (intel_bts_evsel) {
+		/*
+		 * To obtain the auxtrace buffer file descriptor, the auxtrace event
+		 * must come first.
+		 */
+		evlist__to_front(evlist, intel_bts_evsel);
+		/*
+		 * In the case of per-cpu mmaps, we need the CPU on the
+		 * AUX event.
+		 */
+		if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus))
+			evsel__set_sample_bit(intel_bts_evsel, CPU);
+	}
+
+	/* Add dummy event to keep tracking */
+	if (opts->full_auxtrace) {
+		struct evsel *tracking_evsel;
+		int err;
+
+		err = parse_event(evlist, "dummy:u");
+		if (err)
+			return err;
+
+		tracking_evsel = evlist__last(evlist);
+
+		evlist__set_tracking_event(evlist, tracking_evsel);
+
+		tracking_evsel->core.attr.freq = 0;
+		tracking_evsel->core.attr.sample_period = 1;
+	}
+
+	return 0;
+}
+
+static int intel_bts_parse_snapshot_options(struct auxtrace_record *itr,
+					    struct record_opts *opts,
+					    const char *str)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	unsigned long long snapshot_size = 0;
+	char *endptr;
+
+	if (str) {
+		snapshot_size = strtoull(str, &endptr, 0);
+		if (*endptr || snapshot_size > SIZE_MAX)
+			return -1;
+	}
+
+	opts->auxtrace_snapshot_mode = true;
+	opts->auxtrace_snapshot_size = snapshot_size;
+
+	btsr->snapshot_size = snapshot_size;
+
+	return 0;
+}
+
+static u64 intel_bts_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return rdtsc();
+}
+
+static int intel_bts_alloc_snapshot_refs(struct intel_bts_recording *btsr,
+					 int idx)
+{
+	const size_t sz = sizeof(struct intel_bts_snapshot_ref);
+	int cnt = btsr->snapshot_ref_cnt, new_cnt = cnt * 2;
+	struct intel_bts_snapshot_ref *refs;
+
+	if (!new_cnt)
+		new_cnt = 16;
+
+	while (new_cnt <= idx)
+		new_cnt *= 2;
+
+	refs = calloc(new_cnt, sz);
+	if (!refs)
+		return -ENOMEM;
+
+	memcpy(refs, btsr->snapshot_refs, cnt * sz);
+
+	btsr->snapshot_refs = refs;
+	btsr->snapshot_ref_cnt = new_cnt;
+
+	return 0;
+}
+
+static void intel_bts_free_snapshot_refs(struct intel_bts_recording *btsr)
+{
+	int i;
+
+	for (i = 0; i < btsr->snapshot_ref_cnt; i++)
+		zfree(&btsr->snapshot_refs[i].ref_buf);
+	zfree(&btsr->snapshot_refs);
+}
+
+static void intel_bts_recording_free(struct auxtrace_record *itr)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+
+	intel_bts_free_snapshot_refs(btsr);
+	free(btsr);
+}
+
+static int intel_bts_snapshot_start(struct auxtrace_record *itr)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(btsr->evlist, evsel) {
+		if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
+			return evsel__disable(evsel);
+	}
+	return -EINVAL;
+}
+
+static int intel_bts_snapshot_finish(struct auxtrace_record *itr)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(btsr->evlist, evsel) {
+		if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
+			return evsel__enable(evsel);
+	}
+	return -EINVAL;
+}
+
+static bool intel_bts_first_wrap(u64 *data, size_t buf_size)
+{
+	int i, a, b;
+
+	b = buf_size >> 3;
+	a = b - 512;
+	if (a < 0)
+		a = 0;
+
+	for (i = a; i < b; i++) {
+		if (data[i])
+			return true;
+	}
+
+	return false;
+}
+
+static int intel_bts_find_snapshot(struct auxtrace_record *itr, int idx,
+				   struct auxtrace_mmap *mm, unsigned char *data,
+				   u64 *head, u64 *old)
+{
+	struct intel_bts_recording *btsr =
+			container_of(itr, struct intel_bts_recording, itr);
+	bool wrapped;
+	int err;
+
+	pr_debug3("%s: mmap index %d old head %zu new head %zu\n",
+		  __func__, idx, (size_t)*old, (size_t)*head);
+
+	if (idx >= btsr->snapshot_ref_cnt) {
+		err = intel_bts_alloc_snapshot_refs(btsr, idx);
+		if (err)
+			goto out_err;
+	}
+
+	wrapped = btsr->snapshot_refs[idx].wrapped;
+	if (!wrapped && intel_bts_first_wrap((u64 *)data, mm->len)) {
+		btsr->snapshot_refs[idx].wrapped = true;
+		wrapped = true;
+	}
+
+	/*
+	 * In full trace mode 'head' continually increases.  However in snapshot
+	 * mode 'head' is an offset within the buffer.  Here 'old' and 'head'
+	 * are adjusted to match the full trace case which expects that 'old' is
+	 * always less than 'head'.
+	 */
+	if (wrapped) {
+		*old = *head;
+		*head += mm->len;
+	} else {
+		if (mm->mask)
+			*old &= mm->mask;
+		else
+			*old %= mm->len;
+		if (*old > *head)
+			*head += mm->len;
+	}
+
+	pr_debug3("%s: wrap-around %sdetected, adjusted old head %zu adjusted new head %zu\n",
+		  __func__, wrapped ? "" : "not ", (size_t)*old, (size_t)*head);
+
+	return 0;
+
+out_err:
+	pr_err("%s: failed, error %d\n", __func__, err);
+	return err;
+}
+
+struct auxtrace_record *intel_bts_recording_init(int *err)
+{
+	struct perf_pmu *intel_bts_pmu = perf_pmus__find(INTEL_BTS_PMU_NAME);
+	struct intel_bts_recording *btsr;
+
+	if (!intel_bts_pmu)
+		return NULL;
+
+	if (setenv("JITDUMP_USE_ARCH_TIMESTAMP", "1", 1)) {
+		*err = -errno;
+		return NULL;
+	}
+
+	btsr = zalloc(sizeof(struct intel_bts_recording));
+	if (!btsr) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	btsr->intel_bts_pmu = intel_bts_pmu;
+	btsr->itr.recording_options = intel_bts_recording_options;
+	btsr->itr.info_priv_size = intel_bts_info_priv_size;
+	btsr->itr.info_fill = intel_bts_info_fill;
+	btsr->itr.free = intel_bts_recording_free;
+	btsr->itr.snapshot_start = intel_bts_snapshot_start;
+	btsr->itr.snapshot_finish = intel_bts_snapshot_finish;
+	btsr->itr.find_snapshot = intel_bts_find_snapshot;
+	btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
+	btsr->itr.reference = intel_bts_reference;
+	btsr->itr.read_finish = auxtrace_record__read_finish;
+	btsr->itr.alignment = sizeof(struct branch);
+	return &btsr->itr;
+}

linux-7.2.3/tools/perf/arch/x86/util/iostat.c

@@ -0,0 +1,475 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * perf iostat
+ *
+ * Copyright (C) 2020, Intel Corporation
+ *
+ * Authors: Alexander Antonov <alexander.antonov@linux.intel.com>
+ */
+
+#include <api/fs/fs.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/zalloc.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <dirent.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <regex.h>
+#include "util/cpumap.h"
+#include "util/debug.h"
+#include "util/iostat.h"
+#include "util/counts.h"
+#include "path.h"
+
+#ifndef MAX_PATH
+#define MAX_PATH 1024
+#endif
+
+#define UNCORE_IIO_PMU_PATH	"bus/event_source/devices/uncore_iio_%d"
+#define SYSFS_UNCORE_PMU_PATH	"%s/"UNCORE_IIO_PMU_PATH
+#define PLATFORM_MAPPING_PATH	UNCORE_IIO_PMU_PATH"/die%d"
+
+/*
+ * Each metric requiries one IIO event which increments at every 4B transfer
+ * in corresponding direction. The formulas to compute metrics are generic:
+ *     #EventCount * 4B / (1024 * 1024)
+ */
+static const char * const iostat_metrics[] = {
+	"Inbound Read(MB)",
+	"Inbound Write(MB)",
+	"Outbound Read(MB)",
+	"Outbound Write(MB)",
+};
+
+static inline int iostat_metrics_count(void)
+{
+	return sizeof(iostat_metrics) / sizeof(char *);
+}
+
+static const char *iostat_metric_by_idx(int idx)
+{
+	return *(iostat_metrics + idx % iostat_metrics_count());
+}
+
+struct iio_root_port {
+	u32 domain;
+	u8 bus;
+	u8 die;
+	u8 pmu_idx;
+	int idx;
+};
+
+struct iio_root_ports_list {
+	struct iio_root_port **rps;
+	int nr_entries;
+};
+
+static struct iio_root_ports_list *root_ports;
+
+static void iio_root_port_show(FILE *output,
+			       const struct iio_root_port * const rp)
+{
+	if (output && rp)
+		fprintf(output, "S%d-uncore_iio_%d<%04x:%02x>\n",
+			rp->die, rp->pmu_idx, rp->domain, rp->bus);
+}
+
+static struct iio_root_port *iio_root_port_new(u32 domain, u8 bus,
+					       u8 die, u8 pmu_idx)
+{
+	struct iio_root_port *p = calloc(1, sizeof(*p));
+
+	if (p) {
+		p->domain = domain;
+		p->bus = bus;
+		p->die = die;
+		p->pmu_idx = pmu_idx;
+	}
+	return p;
+}
+
+static void iio_root_ports_list_free(struct iio_root_ports_list *list)
+{
+	int idx;
+
+	if (list) {
+		for (idx = 0; idx < list->nr_entries; idx++)
+			zfree(&list->rps[idx]);
+		zfree(&list->rps);
+		free(list);
+	}
+}
+
+static struct iio_root_port *iio_root_port_find_by_notation(
+	const struct iio_root_ports_list * const list, u32 domain, u8 bus)
+{
+	int idx;
+	struct iio_root_port *rp;
+
+	if (list) {
+		for (idx = 0; idx < list->nr_entries; idx++) {
+			rp = list->rps[idx];
+			if (rp && rp->domain == domain && rp->bus == bus)
+				return rp;
+		}
+	}
+	return NULL;
+}
+
+static int iio_root_ports_list_insert(struct iio_root_ports_list *list,
+				      struct iio_root_port * const rp)
+{
+	struct iio_root_port **tmp_buf;
+
+	if (list && rp) {
+		rp->idx = list->nr_entries++;
+		tmp_buf = realloc(list->rps,
+				  list->nr_entries * sizeof(*list->rps));
+		if (!tmp_buf) {
+			pr_err("Failed to realloc memory\n");
+			return -ENOMEM;
+		}
+		tmp_buf[rp->idx] = rp;
+		list->rps = tmp_buf;
+	}
+	return 0;
+}
+
+static int iio_mapping(u8 pmu_idx, struct iio_root_ports_list * const list)
+{
+	char *buf;
+	char path[MAX_PATH];
+	u32 domain;
+	u8 bus;
+	struct iio_root_port *rp;
+	size_t size;
+	int ret;
+
+	for (int die = 0; die < cpu__max_node(); die++) {
+		scnprintf(path, MAX_PATH, PLATFORM_MAPPING_PATH, pmu_idx, die);
+		if (sysfs__read_str(path, &buf, &size) < 0) {
+			if (pmu_idx)
+				goto out;
+			pr_err("Mode iostat is not supported\n");
+			return -1;
+		}
+		ret = sscanf(buf, "%04x:%02hhx", &domain, &bus);
+		free(buf);
+		if (ret != 2) {
+			pr_err("Invalid mapping data: iio_%d; die%d\n",
+			       pmu_idx, die);
+			return -1;
+		}
+		rp = iio_root_port_new(domain, bus, die, pmu_idx);
+		if (!rp || iio_root_ports_list_insert(list, rp)) {
+			free(rp);
+			return -ENOMEM;
+		}
+	}
+out:
+	return 0;
+}
+
+static u8 iio_pmu_count(void)
+{
+	u8 pmu_idx = 0;
+	char path[MAX_PATH];
+	const char *sysfs = sysfs__mountpoint();
+
+	if (sysfs) {
+		for (;; pmu_idx++) {
+			snprintf(path, sizeof(path), SYSFS_UNCORE_PMU_PATH,
+				 sysfs, pmu_idx);
+			if (access(path, F_OK) != 0)
+				break;
+		}
+	}
+	return pmu_idx;
+}
+
+static int iio_root_ports_scan(struct iio_root_ports_list **list)
+{
+	int ret = -ENOMEM;
+	struct iio_root_ports_list *tmp_list;
+	u8 pmu_count = iio_pmu_count();
+
+	if (!pmu_count) {
+		pr_err("Unsupported uncore pmu configuration\n");
+		return -1;
+	}
+
+	tmp_list = calloc(1, sizeof(*tmp_list));
+	if (!tmp_list)
+		goto err;
+
+	for (u8 pmu_idx = 0; pmu_idx < pmu_count; pmu_idx++) {
+		ret = iio_mapping(pmu_idx, tmp_list);
+		if (ret)
+			break;
+	}
+err:
+	if (!ret)
+		*list = tmp_list;
+	else
+		iio_root_ports_list_free(tmp_list);
+
+	return ret;
+}
+
+static int iio_root_port_parse_str(u32 *domain, u8 *bus, char *str)
+{
+	int ret;
+	regex_t regex;
+	/*
+	 * Expected format domain:bus:
+	 * Valid domain range [0:ffff]
+	 * Valid bus range [0:ff]
+	 * Example: 0000:af, 0:3d, 01:7
+	 */
+	regcomp(&regex, "^([a-f0-9A-F]{1,}):([a-f0-9A-F]{1,2})", REG_EXTENDED);
+	ret = regexec(&regex, str, 0, NULL, 0);
+	if (ret || sscanf(str, "%08x:%02hhx", domain, bus) != 2)
+		pr_warning("Unrecognized root port format: %s\n"
+			   "Please use the following format:\n"
+			   "\t [domain]:[bus]\n"
+			   "\t for example: 0000:3d\n", str);
+
+	regfree(&regex);
+	return ret;
+}
+
+static int iio_root_ports_list_filter(struct iio_root_ports_list **list,
+				      const char *filter)
+{
+	char *tok, *tmp, *filter_copy = NULL;
+	struct iio_root_port *rp;
+	u32 domain;
+	u8 bus;
+	int ret = -ENOMEM;
+	struct iio_root_ports_list *tmp_list = calloc(1, sizeof(*tmp_list));
+
+	if (!tmp_list)
+		goto err;
+
+	filter_copy = strdup(filter);
+	if (!filter_copy)
+		goto err;
+
+	for (tok = strtok_r(filter_copy, ",", &tmp); tok;
+	     tok = strtok_r(NULL, ",", &tmp)) {
+		if (!iio_root_port_parse_str(&domain, &bus, tok)) {
+			rp = iio_root_port_find_by_notation(*list, domain, bus);
+			if (rp) {
+				(*list)->rps[rp->idx] = NULL;
+				ret = iio_root_ports_list_insert(tmp_list, rp);
+				if (ret) {
+					free(rp);
+					goto err;
+				}
+			} else if (!iio_root_port_find_by_notation(tmp_list,
+								   domain, bus))
+				pr_warning("Root port %04x:%02x were not found\n",
+					   domain, bus);
+		}
+	}
+
+	if (tmp_list->nr_entries == 0) {
+		pr_err("Requested root ports were not found\n");
+		ret = -EINVAL;
+	}
+err:
+	iio_root_ports_list_free(*list);
+	if (ret)
+		iio_root_ports_list_free(tmp_list);
+	else
+		*list = tmp_list;
+
+	free(filter_copy);
+	return ret;
+}
+
+static int iostat_event_group(struct evlist *evl,
+			      struct iio_root_ports_list *list)
+{
+	int ret;
+	int idx;
+	const char *iostat_cmd_template =
+	"{uncore_iio_%x/event=0x83,umask=0x04,ch_mask=0xF,fc_mask=0x07/,\
+	  uncore_iio_%x/event=0x83,umask=0x01,ch_mask=0xF,fc_mask=0x07/,\
+	  uncore_iio_%x/event=0xc0,umask=0x04,ch_mask=0xF,fc_mask=0x07/,\
+	  uncore_iio_%x/event=0xc0,umask=0x01,ch_mask=0xF,fc_mask=0x07/}";
+	const int len_template = strlen(iostat_cmd_template) + 1;
+	struct evsel *evsel = NULL;
+	int metrics_count = iostat_metrics_count();
+	char *iostat_cmd = calloc(len_template, 1);
+
+	if (!iostat_cmd)
+		return -ENOMEM;
+
+	for (idx = 0; idx < list->nr_entries; idx++) {
+		sprintf(iostat_cmd, iostat_cmd_template,
+			list->rps[idx]->pmu_idx, list->rps[idx]->pmu_idx,
+			list->rps[idx]->pmu_idx, list->rps[idx]->pmu_idx);
+		ret = parse_event(evl, iostat_cmd);
+		if (ret)
+			goto err;
+	}
+
+	evlist__for_each_entry(evl, evsel) {
+		evsel->priv = list->rps[evsel->core.idx / metrics_count];
+	}
+	list->nr_entries = 0;
+err:
+	iio_root_ports_list_free(list);
+	free(iostat_cmd);
+	return ret;
+}
+
+int iostat_prepare(struct evlist *evlist, struct perf_stat_config *config)
+{
+	if (evlist->core.nr_entries > 0) {
+		pr_warning("The -e and -M options are not supported."
+			   "All chosen events/metrics will be dropped\n");
+		evlist__delete(evlist);
+		evlist = evlist__new();
+		if (!evlist)
+			return -ENOMEM;
+	}
+
+	config->metric_only = true;
+	config->aggr_mode = AGGR_GLOBAL;
+
+	return iostat_event_group(evlist, root_ports);
+}
+
+int iostat_parse(const struct option *opt, const char *str,
+		 int unset __maybe_unused)
+{
+	int ret;
+	struct perf_stat_config *config = (struct perf_stat_config *)opt->data;
+
+	ret = iio_root_ports_scan(&root_ports);
+	if (!ret) {
+		config->iostat_run = true;
+		if (!str)
+			iostat_mode = IOSTAT_RUN;
+		else if (!strcmp(str, "list"))
+			iostat_mode = IOSTAT_LIST;
+		else {
+			iostat_mode = IOSTAT_RUN;
+			ret = iio_root_ports_list_filter(&root_ports, str);
+		}
+	}
+	return ret;
+}
+
+void iostat_list(struct evlist *evlist, struct perf_stat_config *config)
+{
+	struct evsel *evsel;
+	struct iio_root_port *rp = NULL;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (rp != evsel->priv) {
+			rp = evsel->priv;
+			iio_root_port_show(config->output, rp);
+		}
+	}
+}
+
+void iostat_release(struct evlist *evlist)
+{
+	struct evsel *evsel;
+	struct iio_root_port *rp = NULL;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (rp != evsel->priv) {
+			rp = evsel->priv;
+			zfree(&evsel->priv);
+		}
+	}
+}
+
+void iostat_prefix(struct evlist *evlist,
+		   struct perf_stat_config *config,
+		   char *prefix, struct timespec *ts)
+{
+	struct iio_root_port *rp = evlist->selected->priv;
+
+	if (rp) {
+		/*
+		 * TODO: This is the incorrect format in JSON mode.
+		 *       See prepare_timestamp()
+		 */
+		if (ts)
+			sprintf(prefix, "%6lu.%09lu%s%04x:%02x%s",
+				ts->tv_sec, ts->tv_nsec,
+				config->csv_sep, rp->domain, rp->bus,
+				config->csv_sep);
+		else
+			sprintf(prefix, "%04x:%02x%s", rp->domain, rp->bus,
+				config->csv_sep);
+	}
+}
+
+void iostat_print_header_prefix(struct perf_stat_config *config)
+{
+	if (config->csv_output)
+		fputs("port,", config->output);
+	else if (config->interval)
+		fprintf(config->output, "#          time    port         ");
+	else
+		fprintf(config->output, "   port         ");
+}
+
+void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel,
+			 struct perf_stat_output_ctx *out)
+{
+	double iostat_value = 0;
+	u64 prev_count_val = 0;
+	const char *iostat_metric = iostat_metric_by_idx(evsel->core.idx);
+	u8 die = ((struct iio_root_port *)evsel->priv)->die;
+	struct perf_counts_values *count = perf_counts(evsel->counts, die, 0);
+
+	if (count && count->run && count->ena) {
+		if (evsel->prev_raw_counts && !out->force_header) {
+			struct perf_counts_values *prev_count =
+				perf_counts(evsel->prev_raw_counts, die, 0);
+
+			prev_count_val = prev_count->val;
+			prev_count->val = count->val;
+		}
+		iostat_value = (count->val - prev_count_val) /
+			       ((double) count->run / count->ena);
+	}
+	out->print_metric(config, out->ctx, METRIC_THRESHOLD_UNKNOWN, "%8.0f", iostat_metric,
+			  iostat_value / (256 * 1024));
+}
+
+void iostat_print_counters(struct evlist *evlist,
+			   struct perf_stat_config *config, struct timespec *ts,
+			   char *prefix, iostat_print_counter_t print_cnt_cb, void *arg)
+{
+	void *perf_device = NULL;
+	struct evsel *counter = evlist__first(evlist);
+
+	evlist__set_selected(evlist, counter);
+	iostat_prefix(evlist, config, prefix, ts);
+	fprintf(config->output, "%s", prefix);
+	evlist__for_each_entry(evlist, counter) {
+		perf_device = evlist->selected->priv;
+		if (perf_device && perf_device != counter->priv) {
+			evlist__set_selected(evlist, counter);
+			iostat_prefix(evlist, config, prefix, ts);
+			fprintf(config->output, "\n%s", prefix);
+		}
+		print_cnt_cb(config, counter, arg);
+	}
+	fputc('\n', config->output);
+}

linux-7.2.3/tools/perf/arch/x86/util/machine.c

@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <limits.h>
+#include <stdlib.h>
+
+#include <internal/lib.h> // page_size
+#include "../../../util/machine.h"
+#include "../../../util/map.h"
+#include "../../../util/symbol.h"
+#include <linux/ctype.h>
+
+#include <symbol/kallsyms.h>
+
+#if defined(__x86_64__)
+
+struct extra_kernel_map_info {
+	int cnt;
+	int max_cnt;
+	struct extra_kernel_map *maps;
+	bool get_entry_trampolines;
+	u64 entry_trampoline;
+};
+
+static int add_extra_kernel_map(struct extra_kernel_map_info *mi, u64 start,
+				u64 end, u64 pgoff, const char *name)
+{
+	if (mi->cnt >= mi->max_cnt) {
+		void *buf;
+		size_t sz;
+
+		mi->max_cnt = mi->max_cnt ? mi->max_cnt * 2 : 32;
+		sz = sizeof(struct extra_kernel_map) * mi->max_cnt;
+		buf = realloc(mi->maps, sz);
+		if (!buf)
+			return -1;
+		mi->maps = buf;
+	}
+
+	mi->maps[mi->cnt].start = start;
+	mi->maps[mi->cnt].end   = end;
+	mi->maps[mi->cnt].pgoff = pgoff;
+	strlcpy(mi->maps[mi->cnt].name, name, KMAP_NAME_LEN);
+
+	mi->cnt += 1;
+
+	return 0;
+}
+
+static int find_extra_kernel_maps(void *arg, const char *name, char type,
+				  u64 start)
+{
+	struct extra_kernel_map_info *mi = arg;
+
+	if (!mi->entry_trampoline && kallsyms2elf_binding(type) == STB_GLOBAL &&
+	    !strcmp(name, "_entry_trampoline")) {
+		mi->entry_trampoline = start;
+		return 0;
+	}
+
+	if (is_entry_trampoline(name)) {
+		u64 end = start + page_size;
+
+		return add_extra_kernel_map(mi, start, end, 0, name);
+	}
+
+	return 0;
+}
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+				      struct dso *kernel)
+{
+	struct extra_kernel_map_info mi = { .cnt = 0, };
+	char filename[PATH_MAX];
+	int ret;
+	int i;
+
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
+	ret = kallsyms__parse(filename, &mi, find_extra_kernel_maps);
+	if (ret)
+		goto out_free;
+
+	if (!mi.entry_trampoline)
+		goto out_free;
+
+	for (i = 0; i < mi.cnt; i++) {
+		struct extra_kernel_map *xm = &mi.maps[i];
+
+		xm->pgoff = mi.entry_trampoline;
+		ret = machine__create_extra_kernel_map(machine, kernel, xm);
+		if (ret)
+			goto out_free;
+	}
+
+	machine->trampolines_mapped = mi.cnt;
+out_free:
+	free(mi.maps);
+	return ret;
+}
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/mem-events.c

@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "linux/string.h"
+#include "util/map_symbol.h"
+#include "util/mem-events.h"
+#include "mem-events.h"
+
+
+#define MEM_LOADS_AUX		0x8203
+
+#define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a }
+
+struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"mem-loads",	true,	0),
+	E("ldlat-stores",	"%s/mem-stores/P",		"mem-stores",	false,	0),
+	E(NULL,			NULL,				NULL,		false,	0),
+};
+
+struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P",	"mem-loads",	true,	MEM_LOADS_AUX),
+	E("ldlat-stores",	"%s/mem-stores/P",		"mem-stores",	false,	0),
+	E(NULL,			NULL,				NULL,		false,	0),
+};
+
+struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL,	false,	0),
+	E(NULL,		NULL,		NULL,	false,	0),
+	E("mem-ldst",	"%s//",		NULL,	false,	0),
+};
+
+struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL,	false,	0),
+	E(NULL,		NULL,		NULL,	false,	0),
+	E("mem-ldst",	"%s/ldlat=%u/",	NULL,	true,	0),
+};

linux-7.2.3/tools/perf/arch/x86/util/mem-events.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _X86_MEM_EVENTS_H
+#define _X86_MEM_EVENTS_H
+
+extern struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX];
+
+extern struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX];
+
+#endif /* _X86_MEM_EVENTS_H */

linux-7.2.3/tools/perf/arch/x86/util/pmu.c

@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <fcntl.h>
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <linux/perf_event.h>
+#include <api/fs/fs.h>
+#include <api/io_dir.h>
+#include <internal/cpumap.h>
+#include <errno.h>
+
+#include "../../../util/intel-pt.h"
+#include "../../../util/intel-bts.h"
+#include "../../../util/pmu.h"
+#include "../../../util/fncache.h"
+#include "../../../util/pmus.h"
+#include "mem-events.h"
+#include "util/debug.h"
+#include "util/env.h"
+#include "util/header.h"
+
+static bool x86__is_intel_graniterapids(void)
+{
+	static bool checked_if_graniterapids;
+	static bool is_graniterapids;
+
+	if (!checked_if_graniterapids) {
+		const char *graniterapids_cpuid = "GenuineIntel-6-A[DE]";
+		char *cpuid = get_cpuid_str((struct perf_cpu){0});
+
+		is_graniterapids = cpuid && strcmp_cpuid_str(graniterapids_cpuid, cpuid) == 0;
+		free(cpuid);
+		checked_if_graniterapids = true;
+	}
+	return is_graniterapids;
+}
+
+static struct perf_cpu_map *read_sysfs_cpu_map(const char *sysfs_path)
+{
+	struct perf_cpu_map *cpus;
+	char *buf = NULL;
+	size_t buf_len;
+
+	if (sysfs__read_str(sysfs_path, &buf, &buf_len) < 0)
+		return NULL;
+
+	cpus = perf_cpu_map__new(buf);
+	free(buf);
+	return cpus;
+}
+
+static int snc_nodes_per_l3_cache(void)
+{
+	static bool checked_snc;
+	static int snc_nodes;
+
+	if (!checked_snc) {
+		struct perf_cpu_map *node_cpus =
+			read_sysfs_cpu_map("devices/system/node/node0/cpulist");
+		struct perf_cpu_map *cache_cpus =
+			read_sysfs_cpu_map("devices/system/cpu/cpu0/cache/index3/shared_cpu_list");
+
+		snc_nodes = perf_cpu_map__nr(cache_cpus) / perf_cpu_map__nr(node_cpus);
+		perf_cpu_map__put(cache_cpus);
+		perf_cpu_map__put(node_cpus);
+		checked_snc = true;
+	}
+	return snc_nodes;
+}
+
+static int num_chas(void)
+{
+	static bool checked_chas;
+	static int num_chas;
+
+	if (!checked_chas) {
+		int fd = perf_pmu__event_source_devices_fd();
+		struct io_dir dir;
+		struct io_dirent64 *dent;
+
+		if (fd < 0)
+			return -1;
+
+		io_dir__init(&dir, fd);
+
+		while ((dent = io_dir__readdir(&dir)) != NULL) {
+			/* Note, dent->d_type will be DT_LNK and so isn't a useful filter. */
+			if (strstarts(dent->d_name, "uncore_cha_"))
+				num_chas++;
+		}
+		close(fd);
+		checked_chas = true;
+	}
+	return num_chas;
+}
+
+#define MAX_SNCS 6
+
+static int uncore_cha_snc(struct perf_pmu *pmu)
+{
+	// CHA SNC numbers are ordered correspond to the CHAs number.
+	unsigned int cha_num;
+	int num_cha, chas_per_node, cha_snc;
+	int snc_nodes = snc_nodes_per_l3_cache();
+
+	if (snc_nodes <= 1)
+		return 0;
+
+	num_cha = num_chas();
+	if (num_cha <= 0) {
+		pr_warning("Unexpected: no CHAs found\n");
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_cha_%u", &cha_num) != 1) {
+		pr_warning("Unexpected: unable to compute CHA number '%s'\n", pmu->name);
+		return 0;
+	}
+	chas_per_node = num_cha / snc_nodes;
+	cha_snc = cha_num / chas_per_node;
+
+	/* Range check cha_snc. for unexpected out of bounds. */
+	return cha_snc >= MAX_SNCS ? 0 : cha_snc;
+}
+
+static int uncore_imc_snc(struct perf_pmu *pmu)
+{
+	// Compute the IMC SNC using lookup tables.
+	unsigned int imc_num;
+	int snc_nodes = snc_nodes_per_l3_cache();
+	const u8 snc2_map[] = {1, 1, 0, 0, 1, 1, 0, 0};
+	const u8 snc3_map[] = {1, 1, 0, 0, 2, 2, 1, 1, 0, 0, 2, 2};
+	const u8 *snc_map;
+	size_t snc_map_len;
+
+	switch (snc_nodes) {
+	case 2:
+		snc_map = snc2_map;
+		snc_map_len = ARRAY_SIZE(snc2_map);
+		break;
+	case 3:
+		snc_map = snc3_map;
+		snc_map_len = ARRAY_SIZE(snc3_map);
+		break;
+	default:
+		/* Error or no lookup support for SNC with >3 nodes. */
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_imc_%u", &imc_num) != 1) {
+		pr_warning("Unexpected: unable to compute IMC number '%s'\n", pmu->name);
+		return 0;
+	}
+	if (imc_num >= snc_map_len) {
+		pr_warning("Unexpected IMC %d for SNC%d mapping\n", imc_num, snc_nodes);
+		return 0;
+	}
+	return snc_map[imc_num];
+}
+
+static int uncore_cha_imc_compute_cpu_adjust(int pmu_snc)
+{
+	static bool checked_cpu_adjust[MAX_SNCS];
+	static int cpu_adjust[MAX_SNCS];
+	struct perf_cpu_map *node_cpus;
+	char node_path[] = "devices/system/node/node0/cpulist";
+
+	/* Was adjust already computed? */
+	if (checked_cpu_adjust[pmu_snc])
+		return cpu_adjust[pmu_snc];
+
+	/* SNC0 doesn't need an adjust. */
+	if (pmu_snc == 0) {
+		cpu_adjust[0] = 0;
+		checked_cpu_adjust[0] = true;
+		return 0;
+	}
+
+	/*
+	 * Use NUMA topology to compute first CPU of the NUMA node, we want to
+	 * adjust CPU 0 to be this and similarly for other CPUs if there is >1
+	 * socket.
+	 */
+	assert(pmu_snc >= 0 && pmu_snc <= 9);
+	node_path[24] += pmu_snc; // Shift node0 to be node<pmu_snc>.
+	node_cpus = read_sysfs_cpu_map(node_path);
+	cpu_adjust[pmu_snc] = perf_cpu_map__cpu(node_cpus, 0).cpu;
+	if (cpu_adjust[pmu_snc] < 0) {
+		pr_debug("Failed to read valid CPU list from <sysfs>/%s\n", node_path);
+		cpu_adjust[pmu_snc] = 0;
+	} else {
+		checked_cpu_adjust[pmu_snc] = true;
+	}
+	perf_cpu_map__put(node_cpus);
+	return cpu_adjust[pmu_snc];
+}
+
+static void gnr_uncore_cha_imc_adjust_cpumask_for_snc(struct perf_pmu *pmu, bool cha)
+{
+	// With sub-NUMA clustering (SNC) there is a NUMA node per SNC in the
+	// topology. For example, a two socket graniterapids machine may be set
+	// up with 3-way SNC meaning there are 6 NUMA nodes that should be
+	// displayed with --per-node. The cpumask of the CHA and IMC PMUs
+	// reflects per-socket information meaning, for example, uncore_cha_60
+	// on a two socket graniterapids machine with 120 cores per socket will
+	// have a cpumask of "0,120". This cpumask needs adjusting to "40,160"
+	// to reflect that uncore_cha_60 is used for the 2nd SNC of each
+	// socket. Without the adjustment events on uncore_cha_60 will appear in
+	// node 0 and node 3 (in our example 2 socket 3-way set up), but with
+	// the adjustment they will appear in node 1 and node 4. The number of
+	// CHAs is typically larger than the number of cores. The CHA numbers
+	// are assumed to split evenly and inorder wrt core numbers. There are
+	// fewer memory IMC PMUs than cores and mapping is handled using lookup
+	// tables.
+	static struct perf_cpu_map *cha_adjusted[MAX_SNCS];
+	static struct perf_cpu_map *imc_adjusted[MAX_SNCS];
+	struct perf_cpu_map **adjusted = cha ? cha_adjusted : imc_adjusted;
+	unsigned int idx;
+	int pmu_snc, cpu_adjust;
+	struct perf_cpu cpu;
+	bool alloc;
+
+	// Cpus from the kernel holds first CPU of each socket. e.g. 0,120.
+	if (perf_cpu_map__cpu(pmu->cpus, 0).cpu != 0) {
+		pr_debug("Ignoring cpumask adjust for %s as unexpected first CPU\n", pmu->name);
+		return;
+	}
+
+	pmu_snc = cha ? uncore_cha_snc(pmu) : uncore_imc_snc(pmu);
+	if (pmu_snc == 0) {
+		// No adjustment necessary for the first SNC.
+		return;
+	}
+
+	alloc = adjusted[pmu_snc] == NULL;
+	if (alloc) {
+		// Hold onto the perf_cpu_map globally to avoid recomputation.
+		cpu_adjust = uncore_cha_imc_compute_cpu_adjust(pmu_snc);
+		adjusted[pmu_snc] = perf_cpu_map__empty_new(perf_cpu_map__nr(pmu->cpus));
+		if (!adjusted[pmu_snc])
+			return;
+	}
+
+	perf_cpu_map__for_each_cpu(cpu, idx, pmu->cpus) {
+		// Compute the new cpu map values or if not allocating, assert
+		// that they match expectations. asserts will be removed to
+		// avoid overhead in NDEBUG builds.
+		if (alloc) {
+			RC_CHK_ACCESS(adjusted[pmu_snc])->map[idx].cpu = cpu.cpu + cpu_adjust;
+		} else if (idx == 0) {
+			cpu_adjust = perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu - cpu.cpu;
+			assert(uncore_cha_imc_compute_cpu_adjust(pmu_snc) == cpu_adjust);
+		} else {
+			assert(perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu ==
+			       cpu.cpu + cpu_adjust);
+		}
+	}
+
+	perf_cpu_map__put(pmu->cpus);
+	pmu->cpus = perf_cpu_map__get(adjusted[pmu_snc]);
+}
+
+void perf_pmu__arch_init(struct perf_pmu *pmu)
+{
+	struct perf_pmu_caps *ldlat_cap;
+
+	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) {
+		pmu->auxtrace = true;
+		pmu->selectable = true;
+		pmu->perf_event_attr_init_default = intel_pt_pmu_default_config;
+	}
+	if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME)) {
+		pmu->auxtrace = true;
+		pmu->selectable = true;
+	}
+
+	if (x86__is_amd_cpu()) {
+		if (strcmp(pmu->name, "ibs_op"))
+			return;
+
+		pmu->mem_events = perf_mem_events_amd;
+
+		if (!perf_pmu__caps_parse(pmu))
+			return;
+
+		ldlat_cap = perf_pmu__get_cap(pmu, "ldlat");
+		if (!ldlat_cap || strcmp(ldlat_cap->value, "1"))
+			return;
+
+		perf_mem_events__loads_ldlat = 0;
+		pmu->mem_events = perf_mem_events_amd_ldlat;
+	} else {
+		if (pmu->is_core) {
+			if (perf_pmu__have_event(pmu, "mem-loads-aux"))
+				pmu->mem_events = perf_mem_events_intel_aux;
+			else
+				pmu->mem_events = perf_mem_events_intel;
+		} else if (x86__is_intel_graniterapids()) {
+			if (strstarts(pmu->name, "uncore_cha_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/true);
+			else if (strstarts(pmu->name, "uncore_imc_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/false);
+		}
+	}
+}

linux-7.2.3/tools/perf/arch/x86/util/topdown.c

@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include "util/evlist.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
+#include "util/topdown.h"
+#include "topdown.h"
+#include "evsel.h"
+
+// cmask=0, inv=0, pc=0, edge=0, umask=4, event=0
+#define TOPDOWN_SLOTS		0x0400
+
+/* Check whether there is a PMU which supports the perf metrics. */
+bool topdown_sys_has_perf_metrics(void)
+{
+	static bool has_perf_metrics;
+	static bool cached;
+	struct perf_pmu *pmu;
+
+	if (cached)
+		return has_perf_metrics;
+
+	/*
+	 * The perf metrics feature is a core PMU feature.
+	 * The PERF_TYPE_RAW type is the type of a core PMU.
+	 * The slots event is only available when the core PMU
+	 * supports the perf metrics feature.
+	 */
+	pmu = perf_pmus__find_by_type(PERF_TYPE_RAW);
+	if (pmu && perf_pmu__have_event(pmu, "slots"))
+		has_perf_metrics = true;
+
+	cached = true;
+	return has_perf_metrics;
+}
+
+bool arch_is_topdown_slots(const struct evsel *evsel)
+{
+	return evsel->core.attr.type == PERF_TYPE_RAW &&
+	       evsel->core.attr.config == TOPDOWN_SLOTS &&
+	       evsel->core.attr.config1 == 0;
+}
+
+bool arch_is_topdown_metrics(const struct evsel *evsel)
+{
+	// cmask=0, inv=0, pc=0, edge=0, umask=0x80-0x87, event=0
+	return evsel->core.attr.type == PERF_TYPE_RAW &&
+		(evsel->core.attr.config & 0xFFFFF8FF) == 0x8000 &&
+		evsel->core.attr.config1 == 0;
+}
+
+/*
+ * Check whether a topdown group supports sample-read.
+ *
+ * Only Topdown metric supports sample-read. The slots
+ * event must be the leader of the topdown group.
+ */
+bool arch_topdown_sample_read(struct evsel *leader)
+{
+	struct evsel *evsel;
+
+	if (!evsel__sys_has_perf_metrics(leader))
+		return false;
+
+	if (!arch_is_topdown_slots(leader))
+		return false;
+
+	/*
+	 * If slots event as leader event but no topdown metric events
+	 * in group, slots event should still sample as leader.
+	 */
+	evlist__for_each_entry(leader->evlist, evsel) {
+		if (evsel->core.leader != leader->core.leader)
+			continue;
+		if (evsel != leader && arch_is_topdown_metrics(evsel))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Make a copy of the topdown metric event metric_event with the given index but
+ * change its configuration to be a topdown slots event. Copying from
+ * metric_event ensures modifiers are the same.
+ */
+int topdown_insert_slots_event(struct list_head *list, int idx, struct evsel *metric_event)
+{
+	struct evsel *evsel = evsel__new_idx(&metric_event->core.attr, idx);
+
+	if (!evsel)
+		return -ENOMEM;
+
+	evsel->core.attr.config = TOPDOWN_SLOTS;
+	evsel->core.cpus = perf_cpu_map__get(metric_event->core.cpus);
+	evsel->core.pmu_cpus = perf_cpu_map__get(metric_event->core.pmu_cpus);
+	evsel->core.is_pmu_core = true;
+	evsel->pmu = metric_event->pmu;
+	evsel->name = strdup("slots");
+	evsel->precise_max = metric_event->precise_max;
+	evsel->sample_read = metric_event->sample_read;
+	evsel->weak_group = metric_event->weak_group;
+	evsel->bpf_counter = metric_event->bpf_counter;
+	evsel->retire_lat = metric_event->retire_lat;
+	evsel__set_leader(evsel, evsel__leader(metric_event));
+	list_add_tail(&evsel->core.node, list);
+	return 0;
+}

linux-7.2.3/tools/perf/arch/x86/util/topdown.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOPDOWN_H
+#define _TOPDOWN_H 1
+
+#include <stdbool.h>
+
+struct evsel;
+struct list_head;
+
+bool topdown_sys_has_perf_metrics(void);
+bool arch_is_topdown_slots(const struct evsel *evsel);
+bool arch_is_topdown_metrics(const struct evsel *evsel);
+int topdown_insert_slots_event(struct list_head *list, int idx, struct evsel *metric_event);
+
+#endif

linux-7.2.3/tools/perf/arch/x86/util/tsc.c

@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <math.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "../../../util/debug.h"
+#include "../../../util/tsc.h"
+#include "cpuid.h"
+
+u64 rdtsc(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
+
+/*
+ * Derive the TSC frequency in Hz from the /proc/cpuinfo, for example:
+ * ...
+ * model name      : Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
+ * ...
+ * will return 3000000000.
+ */
+static u64 cpuinfo_tsc_freq(void)
+{
+	u64 result = 0;
+	FILE *cpuinfo;
+	char *line = NULL;
+	size_t len = 0;
+
+	cpuinfo = fopen("/proc/cpuinfo", "r");
+	if (!cpuinfo) {
+		pr_err("Failed to read /proc/cpuinfo for TSC frequency\n");
+		return 0;
+	}
+	while (getline(&line, &len, cpuinfo) > 0) {
+		if (!strncmp(line, "model name", 10)) {
+			char *pos = strstr(line + 11, " @ ");
+			double float_result;
+
+			if (pos && sscanf(pos, " @ %lfGHz", &float_result) == 1) {
+				float_result *= 1000000000;
+				result = (u64)float_result;
+				goto out;
+			}
+		}
+	}
+out:
+	if (result == 0)
+		pr_err("Failed to find TSC frequency in /proc/cpuinfo\n");
+
+	free(line);
+	fclose(cpuinfo);
+	return result;
+}
+
+u64 arch_get_tsc_freq(void)
+{
+	unsigned int a, b, c, d, lvl;
+	static bool cached;
+	static double tsc;
+	char vendor[16];
+
+	if (cached)
+		return tsc;
+
+	cached = true;
+	get_cpuid_0(vendor, &lvl);
+	if (!strstr(vendor, "Intel"))
+		return 0;
+
+	/*
+	 * Don't support Time Stamp Counter and
+	 * Nominal Core Crystal Clock Information Leaf.
+	 */
+	if (lvl < 0x15) {
+		tsc = cpuinfo_tsc_freq();
+		return tsc;
+	}
+
+	cpuid(0x15, 0, &a, &b, &c, &d);
+	/* TSC frequency is not enumerated */
+	if (!a || !b || !c) {
+		tsc = cpuinfo_tsc_freq();
+		return tsc;
+	}
+
+	tsc = (u64)c * (u64)b / (u64)a;
+	return tsc;
+}