diff options
Diffstat (limited to 'tools/perf/arch/powerpc')
25 files changed, 2341 insertions, 0 deletions
diff --git a/tools/perf/arch/powerpc/Build b/tools/perf/arch/powerpc/Build new file mode 100644 index 000000000..a7dd46a5b --- /dev/null +++ b/tools/perf/arch/powerpc/Build @@ -0,0 +1,2 @@ +perf-y += util/ +perf-y += tests/ diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile new file mode 100644 index 000000000..e58d00d62 --- /dev/null +++ b/tools/perf/arch/powerpc/Makefile @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: GPL-2.0 +ifndef NO_DWARF +PERF_HAVE_DWARF_REGS := 1 +endif + +HAVE_KVM_STAT_SUPPORT := 1 +PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 +PERF_HAVE_JITDUMP := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/powerpc/include/generated/asm +header32 := $(out)/syscalls_32.c +header64 := $(out)/syscalls_64.c +syskrn := $(srctree)/arch/powerpc/kernel/syscalls/syscall.tbl +sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls +sysdef := $(sysprf)/syscall.tbl +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header64): $(sysdef) $(systbl) + @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ + (diff -B $(sysdef) $(syskrn) >/dev/null) \ + || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true + $(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@ + +$(header32): $(sysdef) $(systbl) + @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ + (diff -B $(sysdef) $(syskrn) >/dev/null) \ + || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true + $(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64) + +archheaders: $(header32) $(header64) diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c new file mode 100644 index 000000000..a3f423c27 --- /dev/null +++ b/tools/perf/arch/powerpc/annotate/instructions.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> + +static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, const char *name) +{ + int i; + struct ins_ops *ops; + + /* + * - Interested only if instruction starts with 'b'. + * - Few start with 'b', but aren't branch instructions. + */ + if (name[0] != 'b' || + !strncmp(name, "bcd", 3) || + !strncmp(name, "brinc", 5) || + !strncmp(name, "bper", 4)) + return NULL; + + ops = &jump_ops; + + i = strlen(name) - 1; + if (i < 0) + return NULL; + + /* ignore optional hints at the end of the instructions */ + if (name[i] == '+' || name[i] == '-') + i--; + + if (name[i] == 'l' || (name[i] == 'a' && name[i-1] == 'l')) { + /* + * if the instruction ends up with 'l' or 'la', then + * those are considered 'calls' since they update LR. + * ... except for 'bnl' which is branch if not less than + * and the absolute form of the same. + */ + if (strcmp(name, "bnl") && strcmp(name, "bnl+") && + strcmp(name, "bnl-") && strcmp(name, "bnla") && + strcmp(name, "bnla+") && strcmp(name, "bnla-")) + ops = &call_ops; + } + if (name[i] == 'r' && name[i-1] == 'l') + /* + * instructions ending with 'lr' are considered to be + * return instructions + */ + ops = &ret_ops; + + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + if (!arch->initialized) { + arch->initialized = true; + arch->associate_instruction_ops = powerpc__associate_instruction_ops; + arch->objdump.comment_char = '#'; + } + + return 0; +} diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000..6c58060aa --- /dev/null +++ b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl @@ -0,0 +1,39 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# s390 script. +# +# Copyright IBM Corp. 2017 +# Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> +# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com> + +wordsize=$1 +SYSCALL_TBL=$2 + +if ! test -r $SYSCALL_TBL; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table() +{ + local wordsize=$1 + local max_nr nr abi sc discard + max_nr=-1 + nr=0 + + echo "static const char *syscalltbl_powerpc_${wordsize}[] = {" + while read nr abi sc discard; do + if [ "$max_nr" -lt "$nr" ]; then + printf '\t[%d] = "%s",\n' $nr $sc + max_nr=$nr + fi + done + echo '};' + echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr" +} + +grep -E "^[[:digit:]]+[[:space:]]+(common|spu|nospu|${wordsize})" $SYSCALL_TBL \ + |sort -k1 -n \ + |create_table ${wordsize} diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl new file mode 100644 index 000000000..b168364ac --- /dev/null +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -0,0 +1,521 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note +# +# system call numbers and entry vectors for powerpc +# +# The format is: +# <number> <abi> <name> <entry point> <compat entry point> +# +# The <abi> can be common, spu, nospu, 64, or 32 for this file. +# +0 nospu restart_syscall sys_restart_syscall +1 nospu exit sys_exit +2 nospu fork ppc_fork +3 common read sys_read +4 common write sys_write +5 common open sys_open compat_sys_open +6 common close sys_close +7 common waitpid sys_waitpid +8 common creat sys_creat +9 common link sys_link +10 common unlink sys_unlink +11 nospu execve sys_execve compat_sys_execve +12 common chdir sys_chdir +13 32 time sys_time32 +13 64 time sys_time +13 spu time sys_time +14 common mknod sys_mknod +15 common chmod sys_chmod +16 common lchown sys_lchown +17 common break sys_ni_syscall +18 32 oldstat sys_stat sys_ni_syscall +18 64 oldstat sys_ni_syscall +18 spu oldstat sys_ni_syscall +19 common lseek sys_lseek compat_sys_lseek +20 common getpid sys_getpid +21 nospu mount sys_mount +22 32 umount sys_oldumount +22 64 umount sys_ni_syscall +22 spu umount sys_ni_syscall +23 common setuid sys_setuid +24 common getuid sys_getuid +25 32 stime sys_stime32 +25 64 stime sys_stime +25 spu stime sys_stime +26 nospu ptrace sys_ptrace compat_sys_ptrace +27 common alarm sys_alarm +28 32 oldfstat sys_fstat sys_ni_syscall +28 64 oldfstat sys_ni_syscall +28 spu oldfstat sys_ni_syscall +29 nospu pause sys_pause +30 32 utime sys_utime32 +30 64 utime sys_utime +31 common stty sys_ni_syscall +32 common gtty sys_ni_syscall +33 common access sys_access +34 common nice sys_nice +35 common ftime sys_ni_syscall +36 common sync sys_sync +37 common kill sys_kill +38 common rename sys_rename +39 common mkdir sys_mkdir +40 common rmdir sys_rmdir +41 common dup sys_dup +42 common pipe sys_pipe +43 common times sys_times compat_sys_times +44 common prof sys_ni_syscall +45 common brk sys_brk +46 common setgid sys_setgid +47 common getgid sys_getgid +48 nospu signal sys_signal +49 common geteuid sys_geteuid +50 common getegid sys_getegid +51 nospu acct sys_acct +52 nospu umount2 sys_umount +53 common lock sys_ni_syscall +54 common ioctl sys_ioctl compat_sys_ioctl +55 common fcntl sys_fcntl compat_sys_fcntl +56 common mpx sys_ni_syscall +57 common setpgid sys_setpgid +58 common ulimit sys_ni_syscall +59 32 oldolduname sys_olduname +59 64 oldolduname sys_ni_syscall +59 spu oldolduname sys_ni_syscall +60 common umask sys_umask +61 common chroot sys_chroot +62 nospu ustat sys_ustat compat_sys_ustat +63 common dup2 sys_dup2 +64 common getppid sys_getppid +65 common getpgrp sys_getpgrp +66 common setsid sys_setsid +67 32 sigaction sys_sigaction compat_sys_sigaction +67 64 sigaction sys_ni_syscall +67 spu sigaction sys_ni_syscall +68 common sgetmask sys_sgetmask +69 common ssetmask sys_ssetmask +70 common setreuid sys_setreuid +71 common setregid sys_setregid +72 32 sigsuspend sys_sigsuspend +72 64 sigsuspend sys_ni_syscall +72 spu sigsuspend sys_ni_syscall +73 32 sigpending sys_sigpending compat_sys_sigpending +73 64 sigpending sys_ni_syscall +73 spu sigpending sys_ni_syscall +74 common sethostname sys_sethostname +75 common setrlimit sys_setrlimit compat_sys_setrlimit +76 32 getrlimit sys_old_getrlimit compat_sys_old_getrlimit +76 64 getrlimit sys_ni_syscall +76 spu getrlimit sys_ni_syscall +77 common getrusage sys_getrusage compat_sys_getrusage +78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday +79 common settimeofday sys_settimeofday compat_sys_settimeofday +80 common getgroups sys_getgroups +81 common setgroups sys_setgroups +82 32 select ppc_select sys_ni_syscall +82 64 select sys_ni_syscall +82 spu select sys_ni_syscall +83 common symlink sys_symlink +84 32 oldlstat sys_lstat sys_ni_syscall +84 64 oldlstat sys_ni_syscall +84 spu oldlstat sys_ni_syscall +85 common readlink sys_readlink +86 nospu uselib sys_uselib +87 nospu swapon sys_swapon +88 nospu reboot sys_reboot +89 32 readdir sys_old_readdir compat_sys_old_readdir +89 64 readdir sys_ni_syscall +89 spu readdir sys_ni_syscall +90 common mmap sys_mmap +91 common munmap sys_munmap +92 common truncate sys_truncate compat_sys_truncate +93 common ftruncate sys_ftruncate compat_sys_ftruncate +94 common fchmod sys_fchmod +95 common fchown sys_fchown +96 common getpriority sys_getpriority +97 common setpriority sys_setpriority +98 common profil sys_ni_syscall +99 nospu statfs sys_statfs compat_sys_statfs +100 nospu fstatfs sys_fstatfs compat_sys_fstatfs +101 common ioperm sys_ni_syscall +102 common socketcall sys_socketcall compat_sys_socketcall +103 common syslog sys_syslog +104 common setitimer sys_setitimer compat_sys_setitimer +105 common getitimer sys_getitimer compat_sys_getitimer +106 common stat sys_newstat compat_sys_newstat +107 common lstat sys_newlstat compat_sys_newlstat +108 common fstat sys_newfstat compat_sys_newfstat +109 32 olduname sys_uname +109 64 olduname sys_ni_syscall +109 spu olduname sys_ni_syscall +110 common iopl sys_ni_syscall +111 common vhangup sys_vhangup +112 common idle sys_ni_syscall +113 common vm86 sys_ni_syscall +114 common wait4 sys_wait4 compat_sys_wait4 +115 nospu swapoff sys_swapoff +116 common sysinfo sys_sysinfo compat_sys_sysinfo +117 nospu ipc sys_ipc compat_sys_ipc +118 common fsync sys_fsync +119 32 sigreturn sys_sigreturn compat_sys_sigreturn +119 64 sigreturn sys_ni_syscall +119 spu sigreturn sys_ni_syscall +120 nospu clone ppc_clone +121 common setdomainname sys_setdomainname +122 common uname sys_newuname +123 common modify_ldt sys_ni_syscall +124 32 adjtimex sys_adjtimex_time32 +124 64 adjtimex sys_adjtimex +124 spu adjtimex sys_adjtimex +125 common mprotect sys_mprotect +126 32 sigprocmask sys_sigprocmask compat_sys_sigprocmask +126 64 sigprocmask sys_ni_syscall +126 spu sigprocmask sys_ni_syscall +127 common create_module sys_ni_syscall +128 nospu init_module sys_init_module +129 nospu delete_module sys_delete_module +130 common get_kernel_syms sys_ni_syscall +131 nospu quotactl sys_quotactl +132 common getpgid sys_getpgid +133 common fchdir sys_fchdir +134 common bdflush sys_bdflush +135 common sysfs sys_sysfs +136 32 personality sys_personality ppc64_personality +136 64 personality ppc64_personality +136 spu personality ppc64_personality +137 common afs_syscall sys_ni_syscall +138 common setfsuid sys_setfsuid +139 common setfsgid sys_setfsgid +140 common _llseek sys_llseek +141 common getdents sys_getdents compat_sys_getdents +142 common _newselect sys_select compat_sys_select +143 common flock sys_flock +144 common msync sys_msync +145 common readv sys_readv +146 common writev sys_writev +147 common getsid sys_getsid +148 common fdatasync sys_fdatasync +149 nospu _sysctl sys_ni_syscall +150 common mlock sys_mlock +151 common munlock sys_munlock +152 common mlockall sys_mlockall +153 common munlockall sys_munlockall +154 common sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler +157 common sched_getscheduler sys_sched_getscheduler +158 common sched_yield sys_sched_yield +159 common sched_get_priority_max sys_sched_get_priority_max +160 common sched_get_priority_min sys_sched_get_priority_min +161 32 sched_rr_get_interval sys_sched_rr_get_interval_time32 +161 64 sched_rr_get_interval sys_sched_rr_get_interval +161 spu sched_rr_get_interval sys_sched_rr_get_interval +162 32 nanosleep sys_nanosleep_time32 +162 64 nanosleep sys_nanosleep +162 spu nanosleep sys_nanosleep +163 common mremap sys_mremap +164 common setresuid sys_setresuid +165 common getresuid sys_getresuid +166 common query_module sys_ni_syscall +167 common poll sys_poll +168 common nfsservctl sys_ni_syscall +169 common setresgid sys_setresgid +170 common getresgid sys_getresgid +171 common prctl sys_prctl +172 nospu rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn +173 nospu rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction +174 nospu rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask +175 nospu rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending +176 32 rt_sigtimedwait sys_rt_sigtimedwait_time32 compat_sys_rt_sigtimedwait_time32 +176 64 rt_sigtimedwait sys_rt_sigtimedwait +177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo +178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend +179 common pread64 sys_pread64 compat_sys_pread64 +180 common pwrite64 sys_pwrite64 compat_sys_pwrite64 +181 common chown sys_chown +182 common getcwd sys_getcwd +183 common capget sys_capget +184 common capset sys_capset +185 nospu sigaltstack sys_sigaltstack compat_sys_sigaltstack +186 32 sendfile sys_sendfile compat_sys_sendfile +186 64 sendfile sys_sendfile64 +186 spu sendfile sys_sendfile64 +187 common getpmsg sys_ni_syscall +188 common putpmsg sys_ni_syscall +189 nospu vfork ppc_vfork +190 common ugetrlimit sys_getrlimit compat_sys_getrlimit +191 common readahead sys_readahead compat_sys_readahead +192 32 mmap2 sys_mmap2 compat_sys_mmap2 +193 32 truncate64 sys_truncate64 compat_sys_truncate64 +194 32 ftruncate64 sys_ftruncate64 compat_sys_ftruncate64 +195 32 stat64 sys_stat64 +196 32 lstat64 sys_lstat64 +197 32 fstat64 sys_fstat64 +198 nospu pciconfig_read sys_pciconfig_read +199 nospu pciconfig_write sys_pciconfig_write +200 nospu pciconfig_iobase sys_pciconfig_iobase +201 common multiplexer sys_ni_syscall +202 common getdents64 sys_getdents64 +203 common pivot_root sys_pivot_root +204 32 fcntl64 sys_fcntl64 compat_sys_fcntl64 +205 common madvise sys_madvise +206 common mincore sys_mincore +207 common gettid sys_gettid +208 common tkill sys_tkill +209 common setxattr sys_setxattr +210 common lsetxattr sys_lsetxattr +211 common fsetxattr sys_fsetxattr +212 common getxattr sys_getxattr +213 common lgetxattr sys_lgetxattr +214 common fgetxattr sys_fgetxattr +215 common listxattr sys_listxattr +216 common llistxattr sys_llistxattr +217 common flistxattr sys_flistxattr +218 common removexattr sys_removexattr +219 common lremovexattr sys_lremovexattr +220 common fremovexattr sys_fremovexattr +221 32 futex sys_futex_time32 +221 64 futex sys_futex +221 spu futex sys_futex +222 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity +223 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity +# 224 unused +225 common tuxcall sys_ni_syscall +226 32 sendfile64 sys_sendfile64 compat_sys_sendfile64 +227 common io_setup sys_io_setup compat_sys_io_setup +228 common io_destroy sys_io_destroy +229 32 io_getevents sys_io_getevents_time32 +229 64 io_getevents sys_io_getevents +229 spu io_getevents sys_io_getevents +230 common io_submit sys_io_submit compat_sys_io_submit +231 common io_cancel sys_io_cancel +232 nospu set_tid_address sys_set_tid_address +233 common fadvise64 sys_fadvise64 ppc32_fadvise64 +234 nospu exit_group sys_exit_group +235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +236 common epoll_create sys_epoll_create +237 common epoll_ctl sys_epoll_ctl +238 common epoll_wait sys_epoll_wait +239 common remap_file_pages sys_remap_file_pages +240 common timer_create sys_timer_create compat_sys_timer_create +241 32 timer_settime sys_timer_settime32 +241 64 timer_settime sys_timer_settime +241 spu timer_settime sys_timer_settime +242 32 timer_gettime sys_timer_gettime32 +242 64 timer_gettime sys_timer_gettime +242 spu timer_gettime sys_timer_gettime +243 common timer_getoverrun sys_timer_getoverrun +244 common timer_delete sys_timer_delete +245 32 clock_settime sys_clock_settime32 +245 64 clock_settime sys_clock_settime +245 spu clock_settime sys_clock_settime +246 32 clock_gettime sys_clock_gettime32 +246 64 clock_gettime sys_clock_gettime +246 spu clock_gettime sys_clock_gettime +247 32 clock_getres sys_clock_getres_time32 +247 64 clock_getres sys_clock_getres +247 spu clock_getres sys_clock_getres +248 32 clock_nanosleep sys_clock_nanosleep_time32 +248 64 clock_nanosleep sys_clock_nanosleep +248 spu clock_nanosleep sys_clock_nanosleep +249 32 swapcontext ppc_swapcontext ppc32_swapcontext +249 64 swapcontext ppc64_swapcontext +249 spu swapcontext sys_ni_syscall +250 common tgkill sys_tgkill +251 32 utimes sys_utimes_time32 +251 64 utimes sys_utimes +251 spu utimes sys_utimes +252 common statfs64 sys_statfs64 compat_sys_statfs64 +253 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 +254 32 fadvise64_64 ppc_fadvise64_64 +254 spu fadvise64_64 sys_ni_syscall +255 common rtas sys_rtas +256 32 sys_debug_setcontext sys_debug_setcontext sys_ni_syscall +256 64 sys_debug_setcontext sys_ni_syscall +256 spu sys_debug_setcontext sys_ni_syscall +# 257 reserved for vserver +258 nospu migrate_pages sys_migrate_pages compat_sys_migrate_pages +259 nospu mbind sys_mbind compat_sys_mbind +260 nospu get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy +261 nospu set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy +262 nospu mq_open sys_mq_open compat_sys_mq_open +263 nospu mq_unlink sys_mq_unlink +264 32 mq_timedsend sys_mq_timedsend_time32 +264 64 mq_timedsend sys_mq_timedsend +265 32 mq_timedreceive sys_mq_timedreceive_time32 +265 64 mq_timedreceive sys_mq_timedreceive +266 nospu mq_notify sys_mq_notify compat_sys_mq_notify +267 nospu mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr +268 nospu kexec_load sys_kexec_load compat_sys_kexec_load +269 nospu add_key sys_add_key +270 nospu request_key sys_request_key +271 nospu keyctl sys_keyctl compat_sys_keyctl +272 nospu waitid sys_waitid compat_sys_waitid +273 nospu ioprio_set sys_ioprio_set +274 nospu ioprio_get sys_ioprio_get +275 nospu inotify_init sys_inotify_init +276 nospu inotify_add_watch sys_inotify_add_watch +277 nospu inotify_rm_watch sys_inotify_rm_watch +278 nospu spu_run sys_spu_run +279 nospu spu_create sys_spu_create +280 32 pselect6 sys_pselect6_time32 compat_sys_pselect6_time32 +280 64 pselect6 sys_pselect6 +281 32 ppoll sys_ppoll_time32 compat_sys_ppoll_time32 +281 64 ppoll sys_ppoll +282 common unshare sys_unshare +283 common splice sys_splice +284 common tee sys_tee +285 common vmsplice sys_vmsplice +286 common openat sys_openat compat_sys_openat +287 common mkdirat sys_mkdirat +288 common mknodat sys_mknodat +289 common fchownat sys_fchownat +290 32 futimesat sys_futimesat_time32 +290 64 futimesat sys_futimesat +290 spu utimesat sys_futimesat +291 32 fstatat64 sys_fstatat64 +291 64 newfstatat sys_newfstatat +291 spu newfstatat sys_newfstatat +292 common unlinkat sys_unlinkat +293 common renameat sys_renameat +294 common linkat sys_linkat +295 common symlinkat sys_symlinkat +296 common readlinkat sys_readlinkat +297 common fchmodat sys_fchmodat +298 common faccessat sys_faccessat +299 common get_robust_list sys_get_robust_list compat_sys_get_robust_list +300 common set_robust_list sys_set_robust_list compat_sys_set_robust_list +301 common move_pages sys_move_pages compat_sys_move_pages +302 common getcpu sys_getcpu +303 nospu epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait +304 32 utimensat sys_utimensat_time32 +304 64 utimensat sys_utimensat +304 spu utimensat sys_utimensat +305 common signalfd sys_signalfd compat_sys_signalfd +306 common timerfd_create sys_timerfd_create +307 common eventfd sys_eventfd +308 common sync_file_range2 sys_sync_file_range2 compat_sys_sync_file_range2 +309 nospu fallocate sys_fallocate compat_sys_fallocate +310 nospu subpage_prot sys_subpage_prot +311 32 timerfd_settime sys_timerfd_settime32 +311 64 timerfd_settime sys_timerfd_settime +311 spu timerfd_settime sys_timerfd_settime +312 32 timerfd_gettime sys_timerfd_gettime32 +312 64 timerfd_gettime sys_timerfd_gettime +312 spu timerfd_gettime sys_timerfd_gettime +313 common signalfd4 sys_signalfd4 compat_sys_signalfd4 +314 common eventfd2 sys_eventfd2 +315 common epoll_create1 sys_epoll_create1 +316 common dup3 sys_dup3 +317 common pipe2 sys_pipe2 +318 nospu inotify_init1 sys_inotify_init1 +319 common perf_event_open sys_perf_event_open +320 common preadv sys_preadv compat_sys_preadv +321 common pwritev sys_pwritev compat_sys_pwritev +322 nospu rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +323 nospu fanotify_init sys_fanotify_init +324 nospu fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark +325 common prlimit64 sys_prlimit64 +326 common socket sys_socket +327 common bind sys_bind +328 common connect sys_connect +329 common listen sys_listen +330 common accept sys_accept +331 common getsockname sys_getsockname +332 common getpeername sys_getpeername +333 common socketpair sys_socketpair +334 common send sys_send +335 common sendto sys_sendto +336 common recv sys_recv compat_sys_recv +337 common recvfrom sys_recvfrom compat_sys_recvfrom +338 common shutdown sys_shutdown +339 common setsockopt sys_setsockopt sys_setsockopt +340 common getsockopt sys_getsockopt sys_getsockopt +341 common sendmsg sys_sendmsg compat_sys_sendmsg +342 common recvmsg sys_recvmsg compat_sys_recvmsg +343 32 recvmmsg sys_recvmmsg_time32 compat_sys_recvmmsg_time32 +343 64 recvmmsg sys_recvmmsg +343 spu recvmmsg sys_recvmmsg +344 common accept4 sys_accept4 +345 common name_to_handle_at sys_name_to_handle_at +346 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at +347 32 clock_adjtime sys_clock_adjtime32 +347 64 clock_adjtime sys_clock_adjtime +347 spu clock_adjtime sys_clock_adjtime +348 common syncfs sys_syncfs +349 common sendmmsg sys_sendmmsg compat_sys_sendmmsg +350 common setns sys_setns +351 nospu process_vm_readv sys_process_vm_readv +352 nospu process_vm_writev sys_process_vm_writev +353 nospu finit_module sys_finit_module +354 nospu kcmp sys_kcmp +355 common sched_setattr sys_sched_setattr +356 common sched_getattr sys_sched_getattr +357 common renameat2 sys_renameat2 +358 common seccomp sys_seccomp +359 common getrandom sys_getrandom +360 common memfd_create sys_memfd_create +361 common bpf sys_bpf +362 nospu execveat sys_execveat compat_sys_execveat +363 32 switch_endian sys_ni_syscall +363 64 switch_endian ppc_switch_endian +363 spu switch_endian sys_ni_syscall +364 common userfaultfd sys_userfaultfd +365 common membarrier sys_membarrier +# 366-377 originally left for IPC, now unused +378 nospu mlock2 sys_mlock2 +379 nospu copy_file_range sys_copy_file_range +380 common preadv2 sys_preadv2 compat_sys_preadv2 +381 common pwritev2 sys_pwritev2 compat_sys_pwritev2 +382 nospu kexec_file_load sys_kexec_file_load +383 nospu statx sys_statx +384 nospu pkey_alloc sys_pkey_alloc +385 nospu pkey_free sys_pkey_free +386 nospu pkey_mprotect sys_pkey_mprotect +387 nospu rseq sys_rseq +388 32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents +388 64 io_pgetevents sys_io_pgetevents +# room for arch specific syscalls +392 64 semtimedop sys_semtimedop +393 common semget sys_semget +394 common semctl sys_semctl compat_sys_semctl +395 common shmget sys_shmget +396 common shmctl sys_shmctl compat_sys_shmctl +397 common shmat sys_shmat compat_sys_shmat +398 common shmdt sys_shmdt +399 common msgget sys_msgget +400 common msgsnd sys_msgsnd compat_sys_msgsnd +401 common msgrcv sys_msgrcv compat_sys_msgrcv +402 common msgctl sys_msgctl compat_sys_msgctl +403 32 clock_gettime64 sys_clock_gettime sys_clock_gettime +404 32 clock_settime64 sys_clock_settime sys_clock_settime +405 32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime +406 32 clock_getres_time64 sys_clock_getres sys_clock_getres +407 32 clock_nanosleep_time64 sys_clock_nanosleep sys_clock_nanosleep +408 32 timer_gettime64 sys_timer_gettime sys_timer_gettime +409 32 timer_settime64 sys_timer_settime sys_timer_settime +410 32 timerfd_gettime64 sys_timerfd_gettime sys_timerfd_gettime +411 32 timerfd_settime64 sys_timerfd_settime sys_timerfd_settime +412 32 utimensat_time64 sys_utimensat sys_utimensat +413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 +414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend +419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive +420 32 semtimedop_time64 sys_semtimedop sys_semtimedop +421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 sys_futex sys_futex +423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +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 nospu clone3 ppc_clone3 +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h new file mode 100644 index 000000000..1c7be75cb --- /dev/null +++ b/tools/perf/arch/powerpc/include/arch-tests.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_TESTS_H +#define ARCH_TESTS_H + +#ifdef HAVE_DWARF_UNWIND_SUPPORT +struct thread; +struct perf_sample; +int test__arch_unwind_sample(struct perf_sample *sample, + struct thread *thread); +#endif + +extern struct test arch_tests[]; + +#endif diff --git a/tools/perf/arch/powerpc/include/dwarf-regs-table.h b/tools/perf/arch/powerpc/include/dwarf-regs-table.h new file mode 100644 index 000000000..66dc015a7 --- /dev/null +++ b/tools/perf/arch/powerpc/include/dwarf-regs-table.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifdef DEFINE_DWARF_REGSTR_TABLE +/* This is included in perf/util/dwarf-regs.c */ + +/* + * Reference: + * http://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi-1.9.html + * http://refspecs.linux-foundation.org/elf/elfspec_ppc.pdf + */ +#define REG_DWARFNUM_NAME(reg, idx) [idx] = "%" #reg + +static const char * const powerpc_regstr_tbl[] = { + "%gpr0", "%gpr1", "%gpr2", "%gpr3", "%gpr4", + "%gpr5", "%gpr6", "%gpr7", "%gpr8", "%gpr9", + "%gpr10", "%gpr11", "%gpr12", "%gpr13", "%gpr14", + "%gpr15", "%gpr16", "%gpr17", "%gpr18", "%gpr19", + "%gpr20", "%gpr21", "%gpr22", "%gpr23", "%gpr24", + "%gpr25", "%gpr26", "%gpr27", "%gpr28", "%gpr29", + "%gpr30", "%gpr31", + REG_DWARFNUM_NAME(msr, 66), + REG_DWARFNUM_NAME(ctr, 109), + REG_DWARFNUM_NAME(link, 108), + REG_DWARFNUM_NAME(xer, 101), + REG_DWARFNUM_NAME(dar, 119), + REG_DWARFNUM_NAME(dsisr, 118), +}; + +#endif diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h new file mode 100644 index 000000000..004bed228 --- /dev/null +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include <stdlib.h> +#include <linux/types.h> +#include <asm/perf_regs.h> + +void perf_regs_load(u64 *regs); + +#define PERF_REGS_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1) +#define PERF_REGS_MAX PERF_REG_POWERPC_MAX +#ifdef __powerpc64__ + #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64 +#else + #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 +#endif + +#define PERF_REG_IP PERF_REG_POWERPC_NIP +#define PERF_REG_SP PERF_REG_POWERPC_R1 + +static const char *reg_names[] = { + [PERF_REG_POWERPC_R0] = "r0", + [PERF_REG_POWERPC_R1] = "r1", + [PERF_REG_POWERPC_R2] = "r2", + [PERF_REG_POWERPC_R3] = "r3", + [PERF_REG_POWERPC_R4] = "r4", + [PERF_REG_POWERPC_R5] = "r5", + [PERF_REG_POWERPC_R6] = "r6", + [PERF_REG_POWERPC_R7] = "r7", + [PERF_REG_POWERPC_R8] = "r8", + [PERF_REG_POWERPC_R9] = "r9", + [PERF_REG_POWERPC_R10] = "r10", + [PERF_REG_POWERPC_R11] = "r11", + [PERF_REG_POWERPC_R12] = "r12", + [PERF_REG_POWERPC_R13] = "r13", + [PERF_REG_POWERPC_R14] = "r14", + [PERF_REG_POWERPC_R15] = "r15", + [PERF_REG_POWERPC_R16] = "r16", + [PERF_REG_POWERPC_R17] = "r17", + [PERF_REG_POWERPC_R18] = "r18", + [PERF_REG_POWERPC_R19] = "r19", + [PERF_REG_POWERPC_R20] = "r20", + [PERF_REG_POWERPC_R21] = "r21", + [PERF_REG_POWERPC_R22] = "r22", + [PERF_REG_POWERPC_R23] = "r23", + [PERF_REG_POWERPC_R24] = "r24", + [PERF_REG_POWERPC_R25] = "r25", + [PERF_REG_POWERPC_R26] = "r26", + [PERF_REG_POWERPC_R27] = "r27", + [PERF_REG_POWERPC_R28] = "r28", + [PERF_REG_POWERPC_R29] = "r29", + [PERF_REG_POWERPC_R30] = "r30", + [PERF_REG_POWERPC_R31] = "r31", + [PERF_REG_POWERPC_NIP] = "nip", + [PERF_REG_POWERPC_MSR] = "msr", + [PERF_REG_POWERPC_ORIG_R3] = "orig_r3", + [PERF_REG_POWERPC_CTR] = "ctr", + [PERF_REG_POWERPC_LINK] = "link", + [PERF_REG_POWERPC_XER] = "xer", + [PERF_REG_POWERPC_CCR] = "ccr", + [PERF_REG_POWERPC_SOFTE] = "softe", + [PERF_REG_POWERPC_TRAP] = "trap", + [PERF_REG_POWERPC_DAR] = "dar", + [PERF_REG_POWERPC_DSISR] = "dsisr", + [PERF_REG_POWERPC_SIER] = "sier", + [PERF_REG_POWERPC_MMCRA] = "mmcra", + [PERF_REG_POWERPC_MMCR0] = "mmcr0", + [PERF_REG_POWERPC_MMCR1] = "mmcr1", + [PERF_REG_POWERPC_MMCR2] = "mmcr2", + [PERF_REG_POWERPC_MMCR3] = "mmcr3", + [PERF_REG_POWERPC_SIER2] = "sier2", + [PERF_REG_POWERPC_SIER3] = "sier3", +}; + +static inline const char *__perf_reg_name(int id) +{ + return reg_names[id]; +} +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/powerpc/tests/Build b/tools/perf/arch/powerpc/tests/Build new file mode 100644 index 000000000..3526ab0af --- /dev/null +++ b/tools/perf/arch/powerpc/tests/Build @@ -0,0 +1,4 @@ +perf-$(CONFIG_DWARF_UNWIND) += regs_load.o +perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o + +perf-y += arch-tests.o diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c new file mode 100644 index 000000000..8c3fbd4af --- /dev/null +++ b/tools/perf/arch/powerpc/tests/arch-tests.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include "tests/tests.h" +#include "arch-tests.h" + +struct test arch_tests[] = { +#ifdef HAVE_DWARF_UNWIND_SUPPORT + { + .desc = "Test dwarf unwind", + .func = test__dwarf_unwind, + }, +#endif + { + .func = NULL, + }, +}; diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c new file mode 100644 index 000000000..8efd9ed9e --- /dev/null +++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c @@ -0,0 +1,64 @@ +// 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" +#include "arch-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_POWERPC_R1]; + + map = maps__find(thread->maps, (u64)sp); + if (!map) { + pr_debug("failed to get stack map\n"); + free(buf); + return -1; + } + + stack_size = map->end - sp; + stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; + + memcpy(buf, (void *) sp, stack_size); + 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 = &sample->user_regs; + u64 *buf; + + buf = calloc(1, sizeof(u64) * PERF_REGS_MAX); + 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); +} diff --git a/tools/perf/arch/powerpc/tests/regs_load.S b/tools/perf/arch/powerpc/tests/regs_load.S new file mode 100644 index 000000000..36a20b003 --- /dev/null +++ b/tools/perf/arch/powerpc/tests/regs_load.S @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> + +/* Offset is based on macros from arch/powerpc/include/uapi/asm/ptrace.h. */ +#define R0 0 +#define R1 1 * 8 +#define R2 2 * 8 +#define R3 3 * 8 +#define R4 4 * 8 +#define R5 5 * 8 +#define R6 6 * 8 +#define R7 7 * 8 +#define R8 8 * 8 +#define R9 9 * 8 +#define R10 10 * 8 +#define R11 11 * 8 +#define R12 12 * 8 +#define R13 13 * 8 +#define R14 14 * 8 +#define R15 15 * 8 +#define R16 16 * 8 +#define R17 17 * 8 +#define R18 18 * 8 +#define R19 19 * 8 +#define R20 20 * 8 +#define R21 21 * 8 +#define R22 22 * 8 +#define R23 23 * 8 +#define R24 24 * 8 +#define R25 25 * 8 +#define R26 26 * 8 +#define R27 27 * 8 +#define R28 28 * 8 +#define R29 29 * 8 +#define R30 30 * 8 +#define R31 31 * 8 +#define NIP 32 * 8 +#define CTR 35 * 8 +#define LINK 36 * 8 +#define XER 37 * 8 + +.globl perf_regs_load +perf_regs_load: + std 0, R0(3) + std 1, R1(3) + std 2, R2(3) + std 3, R3(3) + std 4, R4(3) + std 5, R5(3) + std 6, R6(3) + std 7, R7(3) + std 8, R8(3) + std 9, R9(3) + std 10, R10(3) + std 11, R11(3) + std 12, R12(3) + std 13, R13(3) + std 14, R14(3) + std 15, R15(3) + std 16, R16(3) + std 17, R17(3) + std 18, R18(3) + std 19, R19(3) + std 20, R20(3) + std 21, R21(3) + std 22, R22(3) + std 23, R23(3) + std 24, R24(3) + std 25, R25(3) + std 26, R26(3) + std 27, R27(3) + std 28, R28(3) + std 29, R29(3) + std 30, R30(3) + std 31, R31(3) + + /* store NIP */ + mflr 4 + std 4, NIP(3) + + /* Store LR */ + std 4, LINK(3) + + /* Store XER */ + mfxer 4 + std 4, XER(3) + + /* Store CTR */ + mfctr 4 + std 4, CTR(3) + + /* Restore original value of r4 */ + ld 4, R4(3) + + blr diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build new file mode 100644 index 000000000..e86e210bf --- /dev/null +++ b/tools/perf/arch/powerpc/util/Build @@ -0,0 +1,11 @@ +perf-y += header.o +perf-y += kvm-stat.o +perf-y += perf_regs.o +perf-y += mem-events.o +perf-y += sym-handling.o + +perf-$(CONFIG_DWARF) += dwarf-regs.o +perf-$(CONFIG_DWARF) += skip-callchain-idx.o + +perf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h new file mode 100644 index 000000000..488f4339b --- /dev/null +++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_PERF_BOOK3S_HV_HCALLS_H +#define ARCH_PERF_BOOK3S_HV_HCALLS_H + +/* + * PowerPC HCALL codes : hcall code to name mapping + */ +#define kvm_trace_symbol_hcall \ + {0x4, "H_REMOVE"}, \ + {0x8, "H_ENTER"}, \ + {0xc, "H_READ"}, \ + {0x10, "H_CLEAR_MOD"}, \ + {0x14, "H_CLEAR_REF"}, \ + {0x18, "H_PROTECT"}, \ + {0x1c, "H_GET_TCE"}, \ + {0x20, "H_PUT_TCE"}, \ + {0x24, "H_SET_SPRG0"}, \ + {0x28, "H_SET_DABR"}, \ + {0x2c, "H_PAGE_INIT"}, \ + {0x30, "H_SET_ASR"}, \ + {0x34, "H_ASR_ON"}, \ + {0x38, "H_ASR_OFF"}, \ + {0x3c, "H_LOGICAL_CI_LOAD"}, \ + {0x40, "H_LOGICAL_CI_STORE"}, \ + {0x44, "H_LOGICAL_CACHE_LOAD"}, \ + {0x48, "H_LOGICAL_CACHE_STORE"}, \ + {0x4c, "H_LOGICAL_ICBI"}, \ + {0x50, "H_LOGICAL_DCBF"}, \ + {0x54, "H_GET_TERM_CHAR"}, \ + {0x58, "H_PUT_TERM_CHAR"}, \ + {0x5c, "H_REAL_TO_LOGICAL"}, \ + {0x60, "H_HYPERVISOR_DATA"}, \ + {0x64, "H_EOI"}, \ + {0x68, "H_CPPR"}, \ + {0x6c, "H_IPI"}, \ + {0x70, "H_IPOLL"}, \ + {0x74, "H_XIRR"}, \ + {0x78, "H_MIGRATE_DMA"}, \ + {0x7c, "H_PERFMON"}, \ + {0xdc, "H_REGISTER_VPA"}, \ + {0xe0, "H_CEDE"}, \ + {0xe4, "H_CONFER"}, \ + {0xe8, "H_PROD"}, \ + {0xec, "H_GET_PPP"}, \ + {0xf0, "H_SET_PPP"}, \ + {0xf4, "H_PURR"}, \ + {0xf8, "H_PIC"}, \ + {0xfc, "H_REG_CRQ"}, \ + {0x100, "H_FREE_CRQ"}, \ + {0x104, "H_VIO_SIGNAL"}, \ + {0x108, "H_SEND_CRQ"}, \ + {0x110, "H_COPY_RDMA"}, \ + {0x114, "H_REGISTER_LOGICAL_LAN"}, \ + {0x118, "H_FREE_LOGICAL_LAN"}, \ + {0x11c, "H_ADD_LOGICAL_LAN_BUFFER"}, \ + {0x120, "H_SEND_LOGICAL_LAN"}, \ + {0x124, "H_BULK_REMOVE"}, \ + {0x130, "H_MULTICAST_CTRL"}, \ + {0x134, "H_SET_XDABR"}, \ + {0x138, "H_STUFF_TCE"}, \ + {0x13c, "H_PUT_TCE_INDIRECT"}, \ + {0x14c, "H_CHANGE_LOGICAL_LAN_MAC"}, \ + {0x150, "H_VTERM_PARTNER_INFO"}, \ + {0x154, "H_REGISTER_VTERM"}, \ + {0x158, "H_FREE_VTERM"}, \ + {0x15c, "H_RESET_EVENTS"}, \ + {0x160, "H_ALLOC_RESOURCE"}, \ + {0x164, "H_FREE_RESOURCE"}, \ + {0x168, "H_MODIFY_QP"}, \ + {0x16c, "H_QUERY_QP"}, \ + {0x170, "H_REREGISTER_PMR"}, \ + {0x174, "H_REGISTER_SMR"}, \ + {0x178, "H_QUERY_MR"}, \ + {0x17c, "H_QUERY_MW"}, \ + {0x180, "H_QUERY_HCA"}, \ + {0x184, "H_QUERY_PORT"}, \ + {0x188, "H_MODIFY_PORT"}, \ + {0x18c, "H_DEFINE_AQP1"}, \ + {0x190, "H_GET_TRACE_BUFFER"}, \ + {0x194, "H_DEFINE_AQP0"}, \ + {0x198, "H_RESIZE_MR"}, \ + {0x19c, "H_ATTACH_MCQP"}, \ + {0x1a0, "H_DETACH_MCQP"}, \ + {0x1a4, "H_CREATE_RPT"}, \ + {0x1a8, "H_REMOVE_RPT"}, \ + {0x1ac, "H_REGISTER_RPAGES"}, \ + {0x1b0, "H_DISABLE_AND_GET"}, \ + {0x1b4, "H_ERROR_DATA"}, \ + {0x1b8, "H_GET_HCA_INFO"}, \ + {0x1bc, "H_GET_PERF_COUNT"}, \ + {0x1c0, "H_MANAGE_TRACE"}, \ + {0x1d4, "H_FREE_LOGICAL_LAN_BUFFER"}, \ + {0x1d8, "H_POLL_PENDING"}, \ + {0x1e4, "H_QUERY_INT_STATE"}, \ + {0x244, "H_ILLAN_ATTRIBUTES"}, \ + {0x250, "H_MODIFY_HEA_QP"}, \ + {0x254, "H_QUERY_HEA_QP"}, \ + {0x258, "H_QUERY_HEA"}, \ + {0x25c, "H_QUERY_HEA_PORT"}, \ + {0x260, "H_MODIFY_HEA_PORT"}, \ + {0x264, "H_REG_BCMC"}, \ + {0x268, "H_DEREG_BCMC"}, \ + {0x26c, "H_REGISTER_HEA_RPAGES"}, \ + {0x270, "H_DISABLE_AND_GET_HEA"}, \ + {0x274, "H_GET_HEA_INFO"}, \ + {0x278, "H_ALLOC_HEA_RESOURCE"}, \ + {0x284, "H_ADD_CONN"}, \ + {0x288, "H_DEL_CONN"}, \ + {0x298, "H_JOIN"}, \ + {0x2a4, "H_VASI_STATE"}, \ + {0x2b0, "H_ENABLE_CRQ"}, \ + {0x2b8, "H_GET_EM_PARMS"}, \ + {0x2d0, "H_SET_MPP"}, \ + {0x2d4, "H_GET_MPP"}, \ + {0x2ec, "H_HOME_NODE_ASSOCIATIVITY"}, \ + {0x2f4, "H_BEST_ENERGY"}, \ + {0x2fc, "H_XIRR_X"}, \ + {0x300, "H_RANDOM"}, \ + {0x304, "H_COP"}, \ + {0x314, "H_GET_MPP_X"}, \ + {0x31c, "H_SET_MODE"}, \ + {0xf000, "H_RTAS"} \ + +#endif diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h new file mode 100644 index 000000000..2011376c7 --- /dev/null +++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_PERF_BOOK3S_HV_EXITS_H +#define ARCH_PERF_BOOK3S_HV_EXITS_H + +/* + * PowerPC Interrupt vectors : exit code to name mapping + */ + +#define kvm_trace_symbol_exit \ + {0x0, "RETURN_TO_HOST"}, \ + {0x100, "SYSTEM_RESET"}, \ + {0x200, "MACHINE_CHECK"}, \ + {0x300, "DATA_STORAGE"}, \ + {0x380, "DATA_SEGMENT"}, \ + {0x400, "INST_STORAGE"}, \ + {0x480, "INST_SEGMENT"}, \ + {0x500, "EXTERNAL"}, \ + {0x502, "EXTERNAL_HV"}, \ + {0x600, "ALIGNMENT"}, \ + {0x700, "PROGRAM"}, \ + {0x800, "FP_UNAVAIL"}, \ + {0x900, "DECREMENTER"}, \ + {0x980, "HV_DECREMENTER"}, \ + {0xc00, "SYSCALL"}, \ + {0xd00, "TRACE"}, \ + {0xe00, "H_DATA_STORAGE"}, \ + {0xe20, "H_INST_STORAGE"}, \ + {0xe40, "H_EMUL_ASSIST"}, \ + {0xf00, "PERFMON"}, \ + {0xf20, "ALTIVEC"}, \ + {0xf40, "VSX"} + +#endif diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c new file mode 100644 index 000000000..0c4f4caf5 --- /dev/null +++ b/tools/perf/arch/powerpc/util/dwarf-regs.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Mapping of DWARF debug register numbers into register names. + * + * Copyright (C) 2010 Ian Munsie, IBM Corporation. + */ + +#include <stddef.h> +#include <errno.h> +#include <string.h> +#include <dwarf-regs.h> +#include <linux/ptrace.h> +#include <linux/kernel.h> +#include <linux/stringify.h> + +struct pt_regs_dwarfnum { + const char *name; + unsigned int dwarfnum; + unsigned int ptregs_offset; +}; + +#define REG_DWARFNUM_NAME(r, num) \ + {.name = __stringify(%)__stringify(r), .dwarfnum = num, \ + .ptregs_offset = offsetof(struct pt_regs, r)} +#define GPR_DWARFNUM_NAME(num) \ + {.name = __stringify(%gpr##num), .dwarfnum = num, \ + .ptregs_offset = offsetof(struct pt_regs, gpr[num])} +#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0, .ptregs_offset = 0} + +/* + * Reference: + * http://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi-1.9.html + */ +static const struct pt_regs_dwarfnum regdwarfnum_table[] = { + GPR_DWARFNUM_NAME(0), + GPR_DWARFNUM_NAME(1), + GPR_DWARFNUM_NAME(2), + GPR_DWARFNUM_NAME(3), + GPR_DWARFNUM_NAME(4), + GPR_DWARFNUM_NAME(5), + GPR_DWARFNUM_NAME(6), + GPR_DWARFNUM_NAME(7), + GPR_DWARFNUM_NAME(8), + GPR_DWARFNUM_NAME(9), + GPR_DWARFNUM_NAME(10), + GPR_DWARFNUM_NAME(11), + GPR_DWARFNUM_NAME(12), + GPR_DWARFNUM_NAME(13), + GPR_DWARFNUM_NAME(14), + GPR_DWARFNUM_NAME(15), + GPR_DWARFNUM_NAME(16), + GPR_DWARFNUM_NAME(17), + GPR_DWARFNUM_NAME(18), + GPR_DWARFNUM_NAME(19), + GPR_DWARFNUM_NAME(20), + GPR_DWARFNUM_NAME(21), + GPR_DWARFNUM_NAME(22), + GPR_DWARFNUM_NAME(23), + GPR_DWARFNUM_NAME(24), + GPR_DWARFNUM_NAME(25), + GPR_DWARFNUM_NAME(26), + GPR_DWARFNUM_NAME(27), + GPR_DWARFNUM_NAME(28), + GPR_DWARFNUM_NAME(29), + GPR_DWARFNUM_NAME(30), + GPR_DWARFNUM_NAME(31), + REG_DWARFNUM_NAME(msr, 66), + REG_DWARFNUM_NAME(ctr, 109), + REG_DWARFNUM_NAME(link, 108), + REG_DWARFNUM_NAME(xer, 101), + REG_DWARFNUM_NAME(dar, 119), + REG_DWARFNUM_NAME(dsisr, 118), + REG_DWARFNUM_END, +}; + +/** + * get_arch_regstr() - lookup register name from it's DWARF register number + * @n: the DWARF register number + * + * get_arch_regstr() returns the name of the register in struct + * regdwarfnum_table from it's DWARF register number. If the register is not + * found in the table, this returns NULL; + */ +const char *get_arch_regstr(unsigned int n) +{ + const struct pt_regs_dwarfnum *roff; + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (roff->dwarfnum == n) + return roff->name; + return NULL; +} + +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_dwarfnum *roff; + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->ptregs_offset; + return -EINVAL; +} diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c new file mode 100644 index 000000000..58b2d610a --- /dev/null +++ b/tools/perf/arch/powerpc/util/header.c @@ -0,0 +1,50 @@ +// 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 <linux/stringify.h> +#include "header.h" +#include "utils_header.h" +#include "metricgroup.h" +#include <api/fs/fs.h> + +int +get_cpuid(char *buffer, size_t sz) +{ + unsigned long pvr; + int nb; + + pvr = mfspr(SPRN_PVR); + + nb = scnprintf(buffer, sz, "%lu,%lu$", PVR_VER(pvr), PVR_REV(pvr)); + + /* look for end marker to ensure the entire data fit */ + if (strchr(buffer, '$')) { + buffer[nb-1] = '\0'; + return 0; + } + return ENOBUFS; +} + +char * +get_cpuid_str(struct perf_pmu *pmu __maybe_unused) +{ + char *bufp; + + if (asprintf(&bufp, "%.8lx", mfspr(SPRN_PVR)) < 0) + bufp = NULL; + + return bufp; +} + +int arch_get_runtimeparam(struct pmu_event *pe) +{ + int count; + char path[PATH_MAX] = "/devices/hv_24x7/interface/"; + + atoi(pe->aggr_mode) == PerChip ? strcat(path, "sockets") : strcat(path, "coresperchip"); + return sysfs__read_int(path, &count) < 0 ? 1 : count; +} diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c new file mode 100644 index 000000000..eed9e5a42 --- /dev/null +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include "util/kvm-stat.h" +#include "util/parse-events.h" +#include "util/debug.h" +#include "util/evsel.h" +#include "util/evlist.h" +#include "util/pmu.h" + +#include "book3s_hv_exits.h" +#include "book3s_hcalls.h" +#include <subcmd/parse-options.h> + +#define NR_TPS 4 + +const char *vcpu_id_str = "vcpu_id"; +const int decode_str_len = 40; +const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter"; +const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit"; + +define_exit_reasons_table(hv_exit_reasons, kvm_trace_symbol_exit); +define_exit_reasons_table(hcall_reasons, kvm_trace_symbol_hcall); + +/* Tracepoints specific to ppc_book3s_hv */ +const char *ppc_book3s_hv_kvm_tp[] = { + "kvm_hv:kvm_guest_enter", + "kvm_hv:kvm_guest_exit", + "kvm_hv:kvm_hcall_enter", + "kvm_hv:kvm_hcall_exit", + NULL, +}; + +/* 1 extra placeholder for NULL */ +const char *kvm_events_tp[NR_TPS + 1]; +const char *kvm_exit_reason; + +static void hcall_event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = evsel__intval(evsel, sample, "req"); +} + +static const char *get_hcall_exit_reason(u64 exit_code) +{ + struct exit_reasons_table *tbl = hcall_reasons; + + while (tbl->reason != NULL) { + if (tbl->exit_code == exit_code) + return tbl->reason; + tbl++; + } + + pr_debug("Unknown hcall code: %lld\n", + (unsigned long long)exit_code); + return "UNKNOWN"; +} + +static bool hcall_event_end(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return (!strcmp(evsel->name, kvm_events_tp[3])); +} + +static bool hcall_event_begin(struct evsel *evsel, + struct perf_sample *sample, struct event_key *key) +{ + if (!strcmp(evsel->name, kvm_events_tp[2])) { + hcall_event_get_key(evsel, sample, key); + return true; + } + + return false; +} +static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, + struct event_key *key, + char *decode) +{ + const char *hcall_reason = get_hcall_exit_reason(key->key); + + scnprintf(decode, decode_str_len, "%s", hcall_reason); +} + +static struct kvm_events_ops hcall_events = { + .is_begin_event = hcall_event_begin, + .is_end_event = hcall_event_end, + .decode_key = hcall_event_decode_key, + .name = "HCALL-EVENT", +}; + +static struct kvm_events_ops exit_events = { + .is_begin_event = exit_event_begin, + .is_end_event = exit_event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +struct kvm_reg_events_ops kvm_reg_events_ops[] = { + { .name = "vmexit", .ops = &exit_events }, + { .name = "hcall", .ops = &hcall_events }, + { NULL, NULL }, +}; + +const char * const kvm_skip_events[] = { + NULL, +}; + + +static int is_tracepoint_available(const char *str, struct evlist *evlist) +{ + struct parse_events_error err; + int ret; + + bzero(&err, sizeof(err)); + ret = parse_events(evlist, str, &err); + if (err.str) + parse_events_print_error(&err, "tracepoint"); + return ret; +} + +static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm, + struct evlist *evlist) +{ + const char **events_ptr; + int i, nr_tp = 0, err = -1; + + /* Check for book3s_hv tracepoints */ + for (events_ptr = ppc_book3s_hv_kvm_tp; *events_ptr; events_ptr++) { + err = is_tracepoint_available(*events_ptr, evlist); + if (err) + return -1; + nr_tp++; + } + + for (i = 0; i < nr_tp; i++) + kvm_events_tp[i] = ppc_book3s_hv_kvm_tp[i]; + + kvm_events_tp[i] = NULL; + kvm_exit_reason = "trap"; + kvm->exit_reasons = hv_exit_reasons; + kvm->exit_reasons_isa = "HV"; + + return 0; +} + +/* Wrapper to setup kvm tracepoints */ +static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm) +{ + struct evlist *evlist = evlist__new(); + + if (evlist == NULL) + return -ENOMEM; + + /* Right now, only supported on book3s_hv */ + return ppc__setup_book3s_hv(kvm, evlist); +} + +int setup_kvm_events_tp(struct perf_kvm_stat *kvm) +{ + return ppc__setup_kvm_tp(kvm); +} + +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) +{ + int ret; + + ret = ppc__setup_kvm_tp(kvm); + if (ret) { + kvm->exit_reasons = NULL; + kvm->exit_reasons_isa = NULL; + } + + return ret; +} + +/* + * Incase of powerpc architecture, pmu registers are programmable + * by guest kernel. So monitoring guest via host may not provide + * valid samples with default 'cycles' event. It is better to use + * 'trace_imc/trace_cycles' event for guest profiling, since it + * can track the guest instruction pointer in the trace-record. + * + * Function to parse the arguments and return appropriate values. + */ +int kvm_add_default_arch_event(int *argc, const char **argv) +{ + const char **tmp; + bool event = false; + int i, j = *argc; + + const struct option event_options[] = { + OPT_BOOLEAN('e', "event", &event, NULL), + OPT_END() + }; + + tmp = calloc(j + 1, sizeof(char *)); + if (!tmp) + return -EINVAL; + + for (i = 0; i < j; i++) + tmp[i] = argv[i]; + + parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN); + if (!event) { + if (pmu_have_event("trace_imc", "trace_cycles")) { + argv[j++] = strdup("-e"); + argv[j++] = strdup("trace_imc/trace_cycles/"); + *argc += 2; + } else { + free(tmp); + return -EINVAL; + } + } + + free(tmp); + return 0; +} diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c new file mode 100644 index 000000000..07fb5e049 --- /dev/null +++ b/tools/perf/arch/powerpc/util/mem-events.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "map_symbol.h" +#include "mem-events.h" + +/* PowerPC does not support 'ldlat' parameter. */ +char *perf_mem_events__name(int i) +{ + if (i == PERF_MEM_EVENTS__LOAD) + return (char *) "cpu/mem-loads/"; + + return (char *) "cpu/mem-stores/"; +} diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c new file mode 100644 index 000000000..2b6d4704e --- /dev/null +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <string.h> +#include <regex.h> +#include <linux/zalloc.h> + +#include "../../../util/perf_regs.h" +#include "../../../util/debug.h" +#include "../../../util/event.h" +#include "../../../util/header.h" +#include "../../../perf-sys.h" +#include "utils_header.h" + +#include <linux/kernel.h> + +#define PVR_POWER9 0x004E +#define PVR_POWER10 0x0080 + +const struct sample_reg sample_reg_masks[] = { + SMPL_REG(r0, PERF_REG_POWERPC_R0), + SMPL_REG(r1, PERF_REG_POWERPC_R1), + SMPL_REG(r2, PERF_REG_POWERPC_R2), + SMPL_REG(r3, PERF_REG_POWERPC_R3), + SMPL_REG(r4, PERF_REG_POWERPC_R4), + SMPL_REG(r5, PERF_REG_POWERPC_R5), + SMPL_REG(r6, PERF_REG_POWERPC_R6), + SMPL_REG(r7, PERF_REG_POWERPC_R7), + SMPL_REG(r8, PERF_REG_POWERPC_R8), + SMPL_REG(r9, PERF_REG_POWERPC_R9), + SMPL_REG(r10, PERF_REG_POWERPC_R10), + SMPL_REG(r11, PERF_REG_POWERPC_R11), + SMPL_REG(r12, PERF_REG_POWERPC_R12), + SMPL_REG(r13, PERF_REG_POWERPC_R13), + SMPL_REG(r14, PERF_REG_POWERPC_R14), + SMPL_REG(r15, PERF_REG_POWERPC_R15), + SMPL_REG(r16, PERF_REG_POWERPC_R16), + SMPL_REG(r17, PERF_REG_POWERPC_R17), + SMPL_REG(r18, PERF_REG_POWERPC_R18), + SMPL_REG(r19, PERF_REG_POWERPC_R19), + SMPL_REG(r20, PERF_REG_POWERPC_R20), + SMPL_REG(r21, PERF_REG_POWERPC_R21), + SMPL_REG(r22, PERF_REG_POWERPC_R22), + SMPL_REG(r23, PERF_REG_POWERPC_R23), + SMPL_REG(r24, PERF_REG_POWERPC_R24), + SMPL_REG(r25, PERF_REG_POWERPC_R25), + SMPL_REG(r26, PERF_REG_POWERPC_R26), + SMPL_REG(r27, PERF_REG_POWERPC_R27), + SMPL_REG(r28, PERF_REG_POWERPC_R28), + SMPL_REG(r29, PERF_REG_POWERPC_R29), + SMPL_REG(r30, PERF_REG_POWERPC_R30), + SMPL_REG(r31, PERF_REG_POWERPC_R31), + SMPL_REG(nip, PERF_REG_POWERPC_NIP), + SMPL_REG(msr, PERF_REG_POWERPC_MSR), + SMPL_REG(orig_r3, PERF_REG_POWERPC_ORIG_R3), + SMPL_REG(ctr, PERF_REG_POWERPC_CTR), + SMPL_REG(link, PERF_REG_POWERPC_LINK), + SMPL_REG(xer, PERF_REG_POWERPC_XER), + SMPL_REG(ccr, PERF_REG_POWERPC_CCR), + SMPL_REG(softe, PERF_REG_POWERPC_SOFTE), + SMPL_REG(trap, PERF_REG_POWERPC_TRAP), + SMPL_REG(dar, PERF_REG_POWERPC_DAR), + SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR), + SMPL_REG(sier, PERF_REG_POWERPC_SIER), + SMPL_REG(mmcra, PERF_REG_POWERPC_MMCRA), + SMPL_REG(mmcr0, PERF_REG_POWERPC_MMCR0), + SMPL_REG(mmcr1, PERF_REG_POWERPC_MMCR1), + SMPL_REG(mmcr2, PERF_REG_POWERPC_MMCR2), + SMPL_REG(mmcr3, PERF_REG_POWERPC_MMCR3), + SMPL_REG(sier2, PERF_REG_POWERPC_SIER2), + SMPL_REG(sier3, PERF_REG_POWERPC_SIER3), + SMPL_REG_END +}; + +/* REG or %rREG */ +#define SDT_OP_REGEX1 "^(%r)?([1-2]?[0-9]|3[0-1])$" + +/* -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) */ +#define SDT_OP_REGEX2 "^(\\-)?([0-9]+)\\((%r)?([1-2]?[0-9]|3[0-1])\\)$" + +static regex_t sdt_op_regex1, sdt_op_regex2; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED); + if (ret) + goto error; + + ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED); + if (ret) + goto free_regex1; + + initialized = 1; + return 0; + +free_regex1: + regfree(&sdt_op_regex1); +error: + pr_debug4("Regex compilation error.\n"); + return ret; +} + +/* + * Parse OP and convert it into uprobe format, which is, +/-NUM(%gprREG). + * Possible variants of OP are: + * Format Example + * ------------------------- + * NUM(REG) 48(18) + * -NUM(REG) -48(18) + * NUM(%rREG) 48(%r18) + * -NUM(%rREG) -48(%r18) + * REG 18 + * %rREG %r18 + * iNUM i0 + * i-NUM i-1 + * + * SDT marker arguments on Powerpc uses %rREG form with -mregnames flag + * and REG form with -mno-regnames. Here REG is general purpose register, + * which is in 0 to 31 range. + */ +int arch_sdt_arg_parse_op(char *old_op, char **new_op) +{ + int ret, new_len; + regmatch_t rm[5]; + char prefix; + + /* Constant argument. Uprobe does not support it */ + if (old_op[0] == 'i') { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) { + /* REG or %rREG --> %gprREG */ + + new_len = 5; /* % g p r NULL */ + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%%gpr%.*s", + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so); + } else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) { + /* + * -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) --> + * +/-NUM(%gprREG) + */ + prefix = (rm[1].rm_so == -1) ? '+' : '-'; + + new_len = 8; /* +/- ( % g p r ) NULL */ + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + new_len += (int)(rm[4].rm_eo - rm[4].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%c%.*s(%%gpr%.*s)", prefix, + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so, + (int)(rm[4].rm_eo - rm[4].rm_so), old_op + rm[4].rm_so); + } else { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + return SDT_ARG_VALID; +} + +uint64_t arch__intr_reg_mask(void) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .sample_type = PERF_SAMPLE_REGS_INTR, + .precise_ip = 1, + .disabled = 1, + .exclude_kernel = 1, + }; + int fd; + u32 version; + u64 extended_mask = 0, mask = PERF_REGS_MASK; + + /* + * Get the PVR value to set the extended + * mask specific to platform. + */ + version = (((mfspr(SPRN_PVR)) >> 16) & 0xFFFF); + if (version == PVR_POWER9) + extended_mask = PERF_REG_PMU_MASK_300; + else if (version == PVR_POWER10) + extended_mask = PERF_REG_PMU_MASK_31; + else + return mask; + + attr.sample_regs_intr = extended_mask; + attr.sample_period = 1; + event_attr_init(&attr); + + /* + * check if the pmu supports perf extended regs, before + * returning the register mask to sample. + */ + fd = sys_perf_event_open(&attr, 0, -1, -1, 0); + if (fd != -1) { + close(fd); + mask |= extended_mask; + } + return mask; +} diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c new file mode 100644 index 000000000..3018a0545 --- /dev/null +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Use DWARF Debug information to skip unnecessary callchain entries. + * + * Copyright (C) 2014 Sukadev Bhattiprolu, IBM Corporation. + * Copyright (C) 2014 Ulrich Weigand, IBM Corporation. + */ +#include <inttypes.h> +#include <dwarf.h> +#include <elfutils/libdwfl.h> + +#include "util/thread.h" +#include "util/callchain.h" +#include "util/debug.h" +#include "util/dso.h" +#include "util/event.h" // struct ip_callchain +#include "util/map.h" +#include "util/symbol.h" + +/* + * When saving the callchain on Power, the kernel conservatively saves + * excess entries in the callchain. A few of these entries are needed + * in some cases but not others. If the unnecessary entries are not + * ignored, we end up with duplicate arcs in the call-graphs. Use + * DWARF debug information to skip over any unnecessary callchain + * entries. + * + * See function header for arch_adjust_callchain() below for more details. + * + * The libdwfl code in this file is based on code from elfutils + * (libdwfl/argp-std.c, libdwfl/tests/addrcfi.c, etc). + */ +static char *debuginfo_path; + +static const Dwfl_Callbacks offline_callbacks = { + .debuginfo_path = &debuginfo_path, + .find_debuginfo = dwfl_standard_find_debuginfo, + .section_address = dwfl_offline_section_address, +}; + + +/* + * Use the DWARF expression for the Call-frame-address and determine + * if return address is in LR and if a new frame was allocated. + */ +static int check_return_reg(int ra_regno, Dwarf_Frame *frame) +{ + Dwarf_Op ops_mem[2]; + Dwarf_Op dummy; + Dwarf_Op *ops = &dummy; + size_t nops; + int result; + + result = dwarf_frame_register(frame, ra_regno, ops_mem, &ops, &nops); + if (result < 0) { + pr_debug("dwarf_frame_register() %s\n", dwarf_errmsg(-1)); + return -1; + } + + /* + * Check if return address is on the stack. If return address + * is in a register (typically R0), it is yet to be saved on + * the stack. + */ + if ((nops != 0 || ops != NULL) && + !(nops == 1 && ops[0].atom == DW_OP_regx && + ops[0].number2 == 0 && ops[0].offset == 0)) + return 0; + + /* + * Return address is in LR. Check if a frame was allocated + * but not-yet used. + */ + result = dwarf_frame_cfa(frame, &ops, &nops); + if (result < 0) { + pr_debug("dwarf_frame_cfa() returns %d, %s\n", result, + dwarf_errmsg(-1)); + return -1; + } + + /* + * If call frame address is in r1, no new frame was allocated. + */ + if (nops == 1 && ops[0].atom == DW_OP_bregx && ops[0].number == 1 && + ops[0].number2 == 0) + return 1; + + /* + * A new frame was allocated but has not yet been used. + */ + return 2; +} + +/* + * Get the DWARF frame from the .eh_frame section. + */ +static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc) +{ + int result; + Dwarf_Addr bias; + Dwarf_CFI *cfi; + Dwarf_Frame *frame; + + cfi = dwfl_module_eh_cfi(mod, &bias); + if (!cfi) { + pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + result = dwarf_cfi_addrframe(cfi, pc-bias, &frame); + if (result) { + pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + return frame; +} + +/* + * Get the DWARF frame from the .debug_frame section. + */ +static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc) +{ + Dwarf_CFI *cfi; + Dwarf_Addr bias; + Dwarf_Frame *frame; + int result; + + cfi = dwfl_module_dwarf_cfi(mod, &bias); + if (!cfi) { + pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + result = dwarf_cfi_addrframe(cfi, pc-bias, &frame); + if (result) { + pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1)); + return NULL; + } + + return frame; +} + +/* + * Return: + * 0 if return address for the program counter @pc is on stack + * 1 if return address is in LR and no new stack frame was allocated + * 2 if return address is in LR and a new frame was allocated (but not + * yet used) + * -1 in case of errors + */ +static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc) +{ + int rc = -1; + Dwfl *dwfl; + Dwfl_Module *mod; + Dwarf_Frame *frame; + int ra_regno; + Dwarf_Addr start = pc; + Dwarf_Addr end = pc; + bool signalp; + const char *exec_file = dso->long_name; + + dwfl = dso->dwfl; + + if (!dwfl) { + dwfl = dwfl_begin(&offline_callbacks); + if (!dwfl) { + pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1)); + return -1; + } + + mod = dwfl_report_elf(dwfl, exec_file, exec_file, -1, + map_start, false); + if (!mod) { + pr_debug("dwfl_report_elf() failed %s\n", + dwarf_errmsg(-1)); + /* + * We normally cache the DWARF debug info and never + * call dwfl_end(). But to prevent fd leak, free in + * case of error. + */ + dwfl_end(dwfl); + goto out; + } + dso->dwfl = dwfl; + } + + mod = dwfl_addrmodule(dwfl, pc); + if (!mod) { + pr_debug("dwfl_addrmodule() failed, %s\n", dwarf_errmsg(-1)); + goto out; + } + + /* + * To work with split debug info files (eg: glibc), check both + * .eh_frame and .debug_frame sections of the ELF header. + */ + frame = get_eh_frame(mod, pc); + if (!frame) { + frame = get_dwarf_frame(mod, pc); + if (!frame) + goto out; + } + + ra_regno = dwarf_frame_info(frame, &start, &end, &signalp); + if (ra_regno < 0) { + pr_debug("Return address register unavailable: %s\n", + dwarf_errmsg(-1)); + goto out; + } + + rc = check_return_reg(ra_regno, frame); + +out: + return rc; +} + +/* + * The callchain saved by the kernel always includes the link register (LR). + * + * 0: PERF_CONTEXT_USER + * 1: Program counter (Next instruction pointer) + * 2: LR value + * 3: Caller's caller + * 4: ... + * + * The value in LR is only needed when it holds a return address. If the + * return address is on the stack, we should ignore the LR value. + * + * Further, when the return address is in the LR, if a new frame was just + * allocated but the LR was not saved into it, then the LR contains the + * caller, slot 4: contains the caller's caller and the contents of slot 3: + * (chain->ips[3]) is undefined and must be ignored. + * + * Use DWARF debug information to determine if any entries need to be skipped. + * + * Return: + * index: of callchain entry that needs to be ignored (if any) + * -1 if no entry needs to be ignored or in case of errors + */ +int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) +{ + struct addr_location al; + struct dso *dso = NULL; + int rc; + u64 ip; + u64 skip_slot = -1; + + if (!chain || chain->nr < 3) + return skip_slot; + + ip = chain->ips[1]; + + thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); + + if (al.map) + dso = al.map->dso; + + if (!dso) { + pr_debug("%" PRIx64 " dso is NULL\n", ip); + return skip_slot; + } + + rc = check_return_addr(dso, al.map->start, ip); + + pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n", + dso->long_name, al.sym->name, ip, rc); + + if (rc == 0) { + /* + * Return address on stack. Ignore LR value in callchain + */ + skip_slot = 2; + } else if (rc == 2) { + /* + * New frame allocated but return address still in LR. + * Ignore the caller's caller entry in callchain. + */ + skip_slot = 3; + } + return skip_slot; +} diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c new file mode 100644 index 000000000..0856b32f9 --- /dev/null +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * + * Copyright (C) 2015 Naveen N. Rao, IBM Corporation + */ + +#include "dso.h" +#include "symbol.h" +#include "map.h" +#include "probe-event.h" +#include "probe-file.h" + +int arch__choose_best_symbol(struct symbol *syma, + struct symbol *symb __maybe_unused) +{ + char *sym = syma->name; + +#if !defined(_CALL_ELF) || _CALL_ELF != 2 + /* Skip over any initial dot */ + if (*sym == '.') + sym++; +#endif + + /* Avoid "SyS" kernel syscall aliases */ + if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3)) + return SYMBOL_B; + if (strlen(sym) >= 10 && !strncmp(sym, "compat_SyS", 10)) + return SYMBOL_B; + + return SYMBOL_A; +} + +#if !defined(_CALL_ELF) || _CALL_ELF != 2 +/* Allow matching against dot variants */ +int arch__compare_symbol_names(const char *namea, const char *nameb) +{ + /* Skip over initial dot */ + if (*namea == '.') + namea++; + if (*nameb == '.') + nameb++; + + return strcmp(namea, nameb); +} + +int arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n) +{ + /* Skip over initial dot */ + if (*namea == '.') + namea++; + if (*nameb == '.') + nameb++; + + return strncmp(namea, nameb, n); +} + +const char *arch__normalize_symbol_name(const char *name) +{ + /* Skip over initial dot */ + if (name && *name == '.') + name++; + return name; +} +#endif + +#if defined(_CALL_ELF) && _CALL_ELF == 2 + +#ifdef HAVE_LIBELF_SUPPORT +void arch__sym_update(struct symbol *s, GElf_Sym *sym) +{ + s->arch_sym = sym->st_other; +} +#endif + +#define PPC64LE_LEP_OFFSET 8 + +void arch__fix_tev_from_maps(struct perf_probe_event *pev, + struct probe_trace_event *tev, struct map *map, + struct symbol *sym) +{ + int lep_offset; + + /* + * When probing at a function entry point, we normally always want the + * LEP since that catches calls to the function through both the GEP and + * the LEP. Hence, we would like to probe at an offset of 8 bytes if + * the user only specified the function entry. + * + * However, if the user specifies an offset, we fall back to using the + * GEP since all userspace applications (objdump/readelf) show function + * disassembly with offsets from the GEP. + */ + if (pev->point.offset || !map || !sym) + return; + + /* For kretprobes, add an offset only if the kernel supports it */ + if (!pev->uprobes && pev->point.retprobe) { +#ifdef HAVE_LIBELF_SUPPORT + if (!kretprobe_offset_is_supported()) +#endif + return; + } + + lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym); + + if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) + tev->point.offset += PPC64LE_LEP_OFFSET; + else if (lep_offset) { + if (pev->uprobes) + tev->point.address += lep_offset; + else + tev->point.offset += lep_offset; + } +} + +#ifdef HAVE_LIBELF_SUPPORT +void arch__post_process_probe_trace_events(struct perf_probe_event *pev, + int ntevs) +{ + struct probe_trace_event *tev; + struct map *map; + struct symbol *sym = NULL; + struct rb_node *tmp; + int i = 0; + + map = get_target_map(pev->target, pev->nsi, pev->uprobes); + if (!map || map__load(map) < 0) + return; + + for (i = 0; i < ntevs; i++) { + tev = &pev->tevs[i]; + map__for_each_symbol(map, sym, tmp) { + if (map->unmap_ip(map, sym->start) == tev->point.address) { + arch__fix_tev_from_maps(pev, tev, map, sym); + break; + } + } + } +} +#endif /* HAVE_LIBELF_SUPPORT */ + +#endif diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c new file mode 100644 index 000000000..7b2d96ec2 --- /dev/null +++ b/tools/perf/arch/powerpc/util/unwind-libdw.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <elfutils/libdwfl.h> +#include <linux/kernel.h> +#include "../../../util/unwind-libdw.h" +#include "../../../util/perf_regs.h" +#include "../../../util/event.h" + +/* See backends/ppc_initreg.c and backends/ppc_regs.c in elfutils. */ +static const int special_regs[3][2] = { + { 65, PERF_REG_POWERPC_LINK }, + { 101, PERF_REG_POWERPC_XER }, + { 109, PERF_REG_POWERPC_CTR }, +}; + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[32], dwarf_nip; + size_t i; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_POWERPC_##r); \ + val; \ +}) + + dwarf_regs[0] = REG(R0); + dwarf_regs[1] = REG(R1); + dwarf_regs[2] = REG(R2); + dwarf_regs[3] = REG(R3); + dwarf_regs[4] = REG(R4); + dwarf_regs[5] = REG(R5); + dwarf_regs[6] = REG(R6); + dwarf_regs[7] = REG(R7); + dwarf_regs[8] = REG(R8); + dwarf_regs[9] = REG(R9); + dwarf_regs[10] = REG(R10); + dwarf_regs[11] = REG(R11); + dwarf_regs[12] = REG(R12); + dwarf_regs[13] = REG(R13); + dwarf_regs[14] = REG(R14); + dwarf_regs[15] = REG(R15); + dwarf_regs[16] = REG(R16); + dwarf_regs[17] = REG(R17); + dwarf_regs[18] = REG(R18); + dwarf_regs[19] = REG(R19); + dwarf_regs[20] = REG(R20); + dwarf_regs[21] = REG(R21); + dwarf_regs[22] = REG(R22); + dwarf_regs[23] = REG(R23); + dwarf_regs[24] = REG(R24); + dwarf_regs[25] = REG(R25); + dwarf_regs[26] = REG(R26); + dwarf_regs[27] = REG(R27); + dwarf_regs[28] = REG(R28); + dwarf_regs[29] = REG(R29); + dwarf_regs[30] = REG(R30); + dwarf_regs[31] = REG(R31); + if (!dwfl_thread_state_registers(thread, 0, 32, dwarf_regs)) + return false; + + dwarf_nip = REG(NIP); + dwfl_thread_state_register_pc(thread, dwarf_nip); + for (i = 0; i < ARRAY_SIZE(special_regs); i++) { + Dwarf_Word val = 0; + perf_reg_value(&val, user_regs, special_regs[i][1]); + if (!dwfl_thread_state_registers(thread, + special_regs[i][0], 1, + &val)) + return false; + } + + return true; +} diff --git a/tools/perf/arch/powerpc/util/unwind-libunwind.c b/tools/perf/arch/powerpc/util/unwind-libunwind.c new file mode 100644 index 000000000..90a6beda2 --- /dev/null +++ b/tools/perf/arch/powerpc/util/unwind-libunwind.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2016 Chandan Kumar, IBM Corporation. + */ + +#include <errno.h> +#include <libunwind.h> +#include <asm/perf_regs.h> +#include "../../util/unwind.h" +#include "../../util/debug.h" + +int libunwind__arch_reg_id(int regnum) +{ + switch (regnum) { + case UNW_PPC64_R0: + return PERF_REG_POWERPC_R0; + case UNW_PPC64_R1: + return PERF_REG_POWERPC_R1; + case UNW_PPC64_R2: + return PERF_REG_POWERPC_R2; + case UNW_PPC64_R3: + return PERF_REG_POWERPC_R3; + case UNW_PPC64_R4: + return PERF_REG_POWERPC_R4; + case UNW_PPC64_R5: + return PERF_REG_POWERPC_R5; + case UNW_PPC64_R6: + return PERF_REG_POWERPC_R6; + case UNW_PPC64_R7: + return PERF_REG_POWERPC_R7; + case UNW_PPC64_R8: + return PERF_REG_POWERPC_R8; + case UNW_PPC64_R9: + return PERF_REG_POWERPC_R9; + case UNW_PPC64_R10: + return PERF_REG_POWERPC_R10; + case UNW_PPC64_R11: + return PERF_REG_POWERPC_R11; + case UNW_PPC64_R12: + return PERF_REG_POWERPC_R12; + case UNW_PPC64_R13: + return PERF_REG_POWERPC_R13; + case UNW_PPC64_R14: + return PERF_REG_POWERPC_R14; + case UNW_PPC64_R15: + return PERF_REG_POWERPC_R15; + case UNW_PPC64_R16: + return PERF_REG_POWERPC_R16; + case UNW_PPC64_R17: + return PERF_REG_POWERPC_R17; + case UNW_PPC64_R18: + return PERF_REG_POWERPC_R18; + case UNW_PPC64_R19: + return PERF_REG_POWERPC_R19; + case UNW_PPC64_R20: + return PERF_REG_POWERPC_R20; + case UNW_PPC64_R21: + return PERF_REG_POWERPC_R21; + case UNW_PPC64_R22: + return PERF_REG_POWERPC_R22; + case UNW_PPC64_R23: + return PERF_REG_POWERPC_R23; + case UNW_PPC64_R24: + return PERF_REG_POWERPC_R24; + case UNW_PPC64_R25: + return PERF_REG_POWERPC_R25; + case UNW_PPC64_R26: + return PERF_REG_POWERPC_R26; + case UNW_PPC64_R27: + return PERF_REG_POWERPC_R27; + case UNW_PPC64_R28: + return PERF_REG_POWERPC_R28; + case UNW_PPC64_R29: + return PERF_REG_POWERPC_R29; + case UNW_PPC64_R30: + return PERF_REG_POWERPC_R30; + case UNW_PPC64_R31: + return PERF_REG_POWERPC_R31; + case UNW_PPC64_LR: + return PERF_REG_POWERPC_LINK; + case UNW_PPC64_CTR: + return PERF_REG_POWERPC_CTR; + case UNW_PPC64_XER: + return PERF_REG_POWERPC_XER; + case UNW_PPC64_NIP: + return PERF_REG_POWERPC_NIP; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + return -EINVAL; +} diff --git a/tools/perf/arch/powerpc/util/utils_header.h b/tools/perf/arch/powerpc/util/utils_header.h new file mode 100644 index 000000000..5788eb1f1 --- /dev/null +++ b/tools/perf/arch/powerpc/util/utils_header.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_UTIL_HEADER_H +#define __PERF_UTIL_HEADER_H + +#include <linux/stringify.h> + +#define mfspr(rn) ({unsigned long rval; \ + asm volatile("mfspr %0," __stringify(rn) \ + : "=r" (rval)); rval; }) + +#define SPRN_PVR 0x11F /* Processor Version Register */ +#define PVR_VER(pvr) (((pvr) >> 16) & 0xFFFF) /* Version field */ +#define PVR_REV(pvr) (((pvr) >> 0) & 0xFFFF) /* Revison field */ + +#endif /* __PERF_UTIL_HEADER_H */ |