diff options
Diffstat (limited to 'tools/perf/arch/powerpc')
25 files changed, 607 insertions, 345 deletions
diff --git a/tools/perf/arch/powerpc/Build b/tools/perf/arch/powerpc/Build index a7dd46a5b678..12ebc65ea7a3 100644 --- a/tools/perf/arch/powerpc/Build +++ b/tools/perf/arch/powerpc/Build @@ -1,2 +1,2 @@ -perf-y += util/ -perf-y += tests/ +perf-util-y += util/ +perf-test-y += tests/ diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index e58d00d62f02..a295a80ea078 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -1,40 +1,3 @@ # 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 index a3f423c27cae..ca567cfdcbdb 100644 --- a/tools/perf/arch/powerpc/annotate/instructions.c +++ b/tools/perf/arch/powerpc/annotate/instructions.c @@ -49,12 +49,268 @@ static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, con return ops; } +#define PPC_OP(op) (((op) >> 26) & 0x3F) +#define PPC_21_30(R) (((R) >> 1) & 0x3ff) +#define PPC_22_30(R) (((R) >> 1) & 0x1ff) + +struct insn_offset { + const char *name; + int value; +}; + +/* + * There are memory instructions with opcode 31 which are + * of X Form, Example: + * ldx RT,RA,RB + * ______________________________________ + * | 31 | RT | RA | RB | 21 |/| + * -------------------------------------- + * 0 6 11 16 21 30 31 + * + * But all instructions with opcode 31 are not memory. + * Example: add RT,RA,RB + * + * Use bits 21 to 30 to check memory insns with 31 as opcode. + * In ins_array below, for ldx instruction: + * name => OP_31_XOP_LDX + * value => 21 + */ + +static struct insn_offset ins_array[] = { + { .name = "OP_31_XOP_LXSIWZX", .value = 12, }, + { .name = "OP_31_XOP_LWARX", .value = 20, }, + { .name = "OP_31_XOP_LDX", .value = 21, }, + { .name = "OP_31_XOP_LWZX", .value = 23, }, + { .name = "OP_31_XOP_LDUX", .value = 53, }, + { .name = "OP_31_XOP_LWZUX", .value = 55, }, + { .name = "OP_31_XOP_LXSIWAX", .value = 76, }, + { .name = "OP_31_XOP_LDARX", .value = 84, }, + { .name = "OP_31_XOP_LBZX", .value = 87, }, + { .name = "OP_31_XOP_LVX", .value = 103, }, + { .name = "OP_31_XOP_LBZUX", .value = 119, }, + { .name = "OP_31_XOP_STXSIWX", .value = 140, }, + { .name = "OP_31_XOP_STDX", .value = 149, }, + { .name = "OP_31_XOP_STWX", .value = 151, }, + { .name = "OP_31_XOP_STDUX", .value = 181, }, + { .name = "OP_31_XOP_STWUX", .value = 183, }, + { .name = "OP_31_XOP_STBX", .value = 215, }, + { .name = "OP_31_XOP_STVX", .value = 231, }, + { .name = "OP_31_XOP_STBUX", .value = 247, }, + { .name = "OP_31_XOP_LHZX", .value = 279, }, + { .name = "OP_31_XOP_LHZUX", .value = 311, }, + { .name = "OP_31_XOP_LXVDSX", .value = 332, }, + { .name = "OP_31_XOP_LWAX", .value = 341, }, + { .name = "OP_31_XOP_LHAX", .value = 343, }, + { .name = "OP_31_XOP_LWAUX", .value = 373, }, + { .name = "OP_31_XOP_LHAUX", .value = 375, }, + { .name = "OP_31_XOP_STHX", .value = 407, }, + { .name = "OP_31_XOP_STHUX", .value = 439, }, + { .name = "OP_31_XOP_LXSSPX", .value = 524, }, + { .name = "OP_31_XOP_LDBRX", .value = 532, }, + { .name = "OP_31_XOP_LSWX", .value = 533, }, + { .name = "OP_31_XOP_LWBRX", .value = 534, }, + { .name = "OP_31_XOP_LFSUX", .value = 567, }, + { .name = "OP_31_XOP_LXSDX", .value = 588, }, + { .name = "OP_31_XOP_LSWI", .value = 597, }, + { .name = "OP_31_XOP_LFDX", .value = 599, }, + { .name = "OP_31_XOP_LFDUX", .value = 631, }, + { .name = "OP_31_XOP_STXSSPX", .value = 652, }, + { .name = "OP_31_XOP_STDBRX", .value = 660, }, + { .name = "OP_31_XOP_STXWX", .value = 661, }, + { .name = "OP_31_XOP_STWBRX", .value = 662, }, + { .name = "OP_31_XOP_STFSX", .value = 663, }, + { .name = "OP_31_XOP_STFSUX", .value = 695, }, + { .name = "OP_31_XOP_STXSDX", .value = 716, }, + { .name = "OP_31_XOP_STSWI", .value = 725, }, + { .name = "OP_31_XOP_STFDX", .value = 727, }, + { .name = "OP_31_XOP_STFDUX", .value = 759, }, + { .name = "OP_31_XOP_LXVW4X", .value = 780, }, + { .name = "OP_31_XOP_LHBRX", .value = 790, }, + { .name = "OP_31_XOP_LXVD2X", .value = 844, }, + { .name = "OP_31_XOP_LFIWAX", .value = 855, }, + { .name = "OP_31_XOP_LFIWZX", .value = 887, }, + { .name = "OP_31_XOP_STXVW4X", .value = 908, }, + { .name = "OP_31_XOP_STHBRX", .value = 918, }, + { .name = "OP_31_XOP_STXVD2X", .value = 972, }, + { .name = "OP_31_XOP_STFIWX", .value = 983, }, +}; + +/* + * Arithmetic instructions which are having opcode as 31. + * These instructions are tracked to save the register state + * changes. Example: + * + * lwz r10,264(r3) + * add r31, r3, r3 + * lwz r9, 0(r31) + * + * Here instruction tracking needs to identify the "add" + * instruction and save data type of r3 to r31. If a sample + * is hit at next "lwz r9, 0(r31)", by this instruction tracking, + * data type of r31 can be resolved. + */ +static struct insn_offset arithmetic_ins_op_31[] = { + { .name = "SUB_CARRY_XO_FORM", .value = 8, }, + { .name = "MUL_HDW_XO_FORM1", .value = 9, }, + { .name = "ADD_CARRY_XO_FORM", .value = 10, }, + { .name = "MUL_HW_XO_FORM1", .value = 11, }, + { .name = "SUB_XO_FORM", .value = 40, }, + { .name = "MUL_HDW_XO_FORM", .value = 73, }, + { .name = "MUL_HW_XO_FORM", .value = 75, }, + { .name = "SUB_EXT_XO_FORM", .value = 136, }, + { .name = "ADD_EXT_XO_FORM", .value = 138, }, + { .name = "SUB_ZERO_EXT_XO_FORM", .value = 200, }, + { .name = "ADD_ZERO_EXT_XO_FORM", .value = 202, }, + { .name = "SUB_EXT_XO_FORM2", .value = 232, }, + { .name = "MUL_DW_XO_FORM", .value = 233, }, + { .name = "ADD_EXT_XO_FORM2", .value = 234, }, + { .name = "MUL_W_XO_FORM", .value = 235, }, + { .name = "ADD_XO_FORM", .value = 266, }, + { .name = "DIV_DW_XO_FORM1", .value = 457, }, + { .name = "DIV_W_XO_FORM1", .value = 459, }, + { .name = "DIV_DW_XO_FORM", .value = 489, }, + { .name = "DIV_W_XO_FORM", .value = 491, }, +}; + +static struct insn_offset arithmetic_two_ops[] = { + { .name = "mulli", .value = 7, }, + { .name = "subfic", .value = 8, }, + { .name = "addic", .value = 12, }, + { .name = "addic.", .value = 13, }, + { .name = "addi", .value = 14, }, + { .name = "addis", .value = 15, }, +}; + +static int cmp_offset(const void *a, const void *b) +{ + const struct insn_offset *val1 = a; + const struct insn_offset *val2 = b; + + return (val1->value - val2->value); +} + +static struct ins_ops *check_ppc_insn(struct disasm_line *dl) +{ + int raw_insn = dl->raw.raw_insn; + int opcode = PPC_OP(raw_insn); + int mem_insn_31 = PPC_21_30(raw_insn); + struct insn_offset *ret; + struct insn_offset mem_insns_31_opcode = { + "OP_31_INSN", + mem_insn_31 + }; + char name_insn[32]; + + /* + * Instructions with opcode 32 to 63 are memory + * instructions in powerpc + */ + if ((opcode & 0x20)) { + /* + * Set name in case of raw instruction to + * opcode to be used in insn-stat + */ + if (!strlen(dl->ins.name)) { + sprintf(name_insn, "%d", opcode); + dl->ins.name = strdup(name_insn); + } + return &load_store_ops; + } else if (opcode == 31) { + /* Check for memory instructions with opcode 31 */ + ret = bsearch(&mem_insns_31_opcode, ins_array, ARRAY_SIZE(ins_array), sizeof(ins_array[0]), cmp_offset); + if (ret) { + if (!strlen(dl->ins.name)) + dl->ins.name = strdup(ret->name); + return &load_store_ops; + } else { + mem_insns_31_opcode.value = PPC_22_30(raw_insn); + ret = bsearch(&mem_insns_31_opcode, arithmetic_ins_op_31, ARRAY_SIZE(arithmetic_ins_op_31), + sizeof(arithmetic_ins_op_31[0]), cmp_offset); + if (ret != NULL) + return &arithmetic_ops; + /* Bits 21 to 30 has value 444 for "mr" insn ie, OR X form */ + if (PPC_21_30(raw_insn) == 444) + return &arithmetic_ops; + } + } else { + mem_insns_31_opcode.value = opcode; + ret = bsearch(&mem_insns_31_opcode, arithmetic_two_ops, ARRAY_SIZE(arithmetic_two_ops), + sizeof(arithmetic_two_ops[0]), cmp_offset); + if (ret != NULL) + return &arithmetic_ops; + } + + return NULL; +} + +/* + * Instruction tracking function to track register state moves. + * Example sequence: + * ld r10,264(r3) + * mr r31,r3 + * <<after some sequence> + * ld r9,312(r31) + * + * Previous instruction sequence shows that register state of r3 + * is moved to r31. update_insn_state_powerpc tracks these state + * changes + */ +#ifdef HAVE_LIBDW_SUPPORT +static void update_insn_state_powerpc(struct type_state *state, + struct data_loc_info *dloc, Dwarf_Die * cu_die __maybe_unused, + struct disasm_line *dl) +{ + struct annotated_insn_loc loc; + struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE]; + struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET]; + struct type_state_reg *tsr; + u32 insn_offset = dl->al.offset; + + if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0) + return; + + /* + * Value 444 for bits 21:30 is for "mr" + * instruction. "mr" is extended OR. So set the + * source and destination reg correctly + */ + if (PPC_21_30(dl->raw.raw_insn) == 444) { + int src_reg = src->reg1; + + src->reg1 = dst->reg1; + dst->reg1 = src_reg; + } + + if (!has_reg_type(state, dst->reg1)) + return; + + tsr = &state->regs[dst->reg1]; + + if (!has_reg_type(state, src->reg1) || + !state->regs[src->reg1].ok) { + tsr->ok = false; + return; + } + + tsr->type = state->regs[src->reg1].type; + tsr->kind = state->regs[src->reg1].kind; + tsr->ok = true; + + pr_debug_dtp("mov [%x] reg%d -> reg%d", + insn_offset, src->reg1, dst->reg1); + pr_debug_type_name(&tsr->type, tsr->kind); +} +#endif /* HAVE_LIBDW_SUPPORT */ + 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 = '#'; + annotate_opts.show_asm_raw = true; + arch->e_machine = EM_PPC; + arch->e_flags = 0; } return 0; diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl deleted file mode 100755 index 6c58060aa03b..000000000000 --- a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl +++ /dev/null @@ -1,39 +0,0 @@ -#!/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 index 35b61bfc1b1a..9a084bdb8926 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -9,7 +9,7 @@ # 0 nospu restart_syscall sys_restart_syscall 1 nospu exit sys_exit -2 nospu fork ppc_fork +2 nospu fork sys_fork 3 common read sys_read 4 common write sys_write 5 common open sys_open compat_sys_open @@ -32,7 +32,7 @@ 18 spu oldstat sys_ni_syscall 19 common lseek sys_lseek compat_sys_lseek 20 common getpid sys_getpid -21 nospu mount sys_mount compat_sys_mount +21 nospu mount sys_mount 22 32 umount sys_oldumount 22 64 umount sys_ni_syscall 22 spu umount sys_ni_syscall @@ -110,7 +110,7 @@ 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 32 select sys_old_select compat_sys_old_select 82 64 select sys_ni_syscall 82 spu select sys_ni_syscall 83 common symlink sys_symlink @@ -158,7 +158,7 @@ 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 +120 nospu clone sys_clone 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common modify_ldt sys_ni_syscall @@ -176,11 +176,11 @@ 131 nospu quotactl sys_quotactl 132 common getpgid sys_getpgid 133 common fchdir sys_fchdir -134 common bdflush sys_bdflush +134 common bdflush sys_ni_syscall 135 common sysfs sys_sysfs -136 32 personality sys_personality ppc64_personality -136 64 personality ppc64_personality -136 spu personality ppc64_personality +136 32 personality sys_personality compat_sys_ppc64_personality +136 64 personality sys_ppc64_personality +136 spu personality sys_ppc64_personality 137 common afs_syscall sys_ni_syscall 138 common setfsuid sys_setfsuid 139 common setfsgid sys_setfsgid @@ -189,11 +189,11 @@ 142 common _newselect sys_select compat_sys_select 143 common flock sys_flock 144 common msync sys_msync -145 common readv sys_readv compat_sys_readv -146 common writev sys_writev compat_sys_writev +145 common readv sys_readv +146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 nospu _sysctl sys_sysctl compat_sys_sysctl +149 nospu _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall @@ -228,8 +228,12 @@ 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 +179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 +179 64 pread64 sys_pread64 +179 spu pread64 sys_pread64 +180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 +180 64 pwrite64 sys_pwrite64 +180 spu pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -240,12 +244,14 @@ 186 spu sendfile sys_sendfile64 187 common getpmsg sys_ni_syscall 188 common putpmsg sys_ni_syscall -189 nospu vfork ppc_vfork +189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit -191 common readahead sys_readahead compat_sys_readahead +191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead +191 64 readahead sys_readahead +191 spu readahead 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 +193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 +194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 195 32 stat64 sys_stat64 196 32 lstat64 sys_lstat64 197 32 fstat64 sys_fstat64 @@ -288,9 +294,11 @@ 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 +233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 +233 64 fadvise64 sys_fadvise64 +233 spu fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group -235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +235 nospu lookup_dcookie sys_ni_syscall 236 common epoll_create sys_epoll_create 237 common epoll_ctl sys_epoll_ctl 238 common epoll_wait sys_epoll_wait @@ -316,26 +324,24 @@ 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 +249 nospu swapcontext sys_swapcontext compat_sys_swapcontext 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 32 fadvise64_64 sys_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 +258 nospu migrate_pages sys_migrate_pages +259 nospu mbind sys_mbind +260 nospu get_mempolicy sys_get_mempolicy +261 nospu set_mempolicy 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 @@ -363,7 +369,7 @@ 282 common unshare sys_unshare 283 common splice sys_splice 284 common tee sys_tee -285 common vmsplice sys_vmsplice compat_sys_vmsplice +285 common vmsplice sys_vmsplice 286 common openat sys_openat compat_sys_openat 287 common mkdirat sys_mkdirat 288 common mknodat sys_mknodat @@ -383,7 +389,7 @@ 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 +301 common move_pages 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 @@ -392,8 +398,11 @@ 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 +308 32 sync_file_range2 sys_ppc_sync_file_range2 compat_sys_ppc_sync_file_range2 +308 64 sync_file_range2 sys_sync_file_range2 +308 spu sync_file_range2 sys_sync_file_range2 +309 32 fallocate sys_ppc_fallocate compat_sys_fallocate +309 64 fallocate sys_fallocate 310 nospu subpage_prot sys_subpage_prot 311 32 timerfd_settime sys_timerfd_settime32 311 64 timerfd_settime sys_timerfd_settime @@ -427,8 +436,8 @@ 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 compat_sys_setsockopt -340 common getsockopt sys_getsockopt compat_sys_getsockopt +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 @@ -443,8 +452,8 @@ 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 compat_sys_process_vm_readv -352 nospu process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev +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 @@ -456,7 +465,7 @@ 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 64 switch_endian sys_switch_endian 363 spu switch_endian sys_ni_syscall 364 common userfaultfd sys_userfaultfd 365 common membarrier sys_membarrier @@ -497,7 +506,7 @@ 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 +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 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 @@ -516,6 +525,36 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -435 nospu clone3 ppc_clone3 +435 nospu 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 compat_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 reserved for memfd_secret +448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv +450 nospu 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_ni_syscall +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 diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h index 1c7be75cbc78..452b3d904521 100644 --- a/tools/perf/arch/powerpc/include/arch-tests.h +++ b/tools/perf/arch/powerpc/include/arch-tests.h @@ -2,13 +2,6 @@ #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[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h index e18a3556f5e3..1c66f6ba6773 100644 --- a/tools/perf/arch/powerpc/include/perf_regs.h +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -16,59 +16,4 @@ void perf_regs_load(u64 *regs); #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" -}; - -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 index 3526ab0af9f9..275026950645 100644 --- a/tools/perf/arch/powerpc/tests/Build +++ b/tools/perf/arch/powerpc/tests/Build @@ -1,4 +1,4 @@ -perf-$(CONFIG_DWARF_UNWIND) += regs_load.o -perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o +perf-test-$(CONFIG_DWARF_UNWIND) += regs_load.o +perf-test-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o -perf-y += arch-tests.o +perf-test-y += arch-tests.o diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c index 8c3fbd4af817..eb98c57b5aeb 100644 --- a/tools/perf/arch/powerpc/tests/arch-tests.c +++ b/tools/perf/arch/powerpc/tests/arch-tests.c @@ -3,14 +3,10 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { + +struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "Test dwarf unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif - { - .func = NULL, - }, + NULL, }; diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c index 8efd9ed9e9db..66af884baa66 100644 --- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c +++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c @@ -7,7 +7,6 @@ #include "event.h" #include "debug.h" #include "tests/tests.h" -#include "arch-tests.h" #define STACK_SIZE 8192 @@ -27,14 +26,14 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_POWERPC_R1]; - map = maps__find(thread->maps, (u64)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 - sp; + stack_size = map__end(map) - sp; stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); @@ -46,7 +45,7 @@ static int sample_ustack(struct perf_sample *sample, int test__arch_unwind_sample(struct perf_sample *sample, struct thread *thread) { - struct regs_dump *regs = &sample->user_regs; + struct regs_dump *regs = perf_sample__user_regs(sample); u64 *buf; buf = calloc(1, sizeof(u64) * PERF_REGS_MAX); diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index e86e210bf514..ed82715080f9 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,11 +1,13 @@ -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-util-y += header.o +perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o +perf-util-y += perf_regs.o +perf-util-y += mem-events.o +perf-util-y += pmu.o +perf-util-y += sym-handling.o +perf-util-y += evsel.o +perf-util-y += event.o -perf-$(CONFIG_DWARF) += dwarf-regs.o -perf-$(CONFIG_DWARF) += skip-callchain-idx.o +perf-util-$(CONFIG_LIBDW) += skip-callchain-idx.o -perf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o -perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o +perf-util-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +perf-util-$(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 index 54cfa0530e86..488f4339b83c 100644 --- a/tools/perf/arch/powerpc/util/book3s_hcalls.h +++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h @@ -84,7 +84,7 @@ {0x1a4, "H_CREATE_RPT"}, \ {0x1a8, "H_REMOVE_RPT"}, \ {0x1ac, "H_REGISTER_RPAGES"}, \ - {0x1b0, "H_DISABLE_AND_GETC"}, \ + {0x1b0, "H_DISABLE_AND_GET"}, \ {0x1b4, "H_ERROR_DATA"}, \ {0x1b8, "H_GET_HCA_INFO"}, \ {0x1bc, "H_GET_PERF_COUNT"}, \ diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c deleted file mode 100644 index 0c4f4caf53ac..000000000000 --- a/tools/perf/arch/powerpc/util/dwarf-regs.c +++ /dev/null @@ -1,100 +0,0 @@ -// 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/event.c b/tools/perf/arch/powerpc/util/event.c new file mode 100644 index 000000000000..77d8cc2b5691 --- /dev/null +++ b/tools/perf/arch/powerpc/util/event.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/types.h> +#include <linux/string.h> +#include <linux/zalloc.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" + +void arch_perf_parse_sample_weight(struct perf_sample *data, + const __u64 *array, u64 type) +{ + union perf_sample_weight weight; + + weight.full = *array; + if (type & PERF_SAMPLE_WEIGHT) + data->weight = weight.full; + else { + data->weight = weight.var1_dw; + data->ins_lat = weight.var2_w; + data->p_stage_cyc = weight.var3_w; + } +} + +void arch_perf_synthesize_sample_weight(const struct perf_sample *data, + __u64 *array, u64 type) +{ + *array = data->weight; + + if (type & PERF_SAMPLE_WEIGHT_STRUCT) { + *array &= 0xffffffff; + *array |= ((u64)data->ins_lat << 32); + } +} + +const char *arch_perf_header_entry(const char *se_header) +{ + if (!strcmp(se_header, "Local INSTR Latency")) + return "Finish Cyc"; + else if (!strcmp(se_header, "INSTR Latency")) + return "Global Finish_cyc"; + else if (!strcmp(se_header, "Local Pipeline Stage Cycle")) + return "Dispatch Cyc"; + else if (!strcmp(se_header, "Pipeline Stage Cycle")) + return "Global Dispatch_cyc"; + return se_header; +} + +int arch_support_sort_key(const char *sort_key) +{ + if (!strcmp(sort_key, "p_stage_cyc")) + return 1; + if (!strcmp(sort_key, "local_p_stage_cyc")) + return 1; + return 0; +} diff --git a/tools/perf/arch/powerpc/util/evsel.c b/tools/perf/arch/powerpc/util/evsel.c new file mode 100644 index 000000000000..2f733cdc8dbb --- /dev/null +++ b/tools/perf/arch/powerpc/util/evsel.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include "util/evsel.h" + +void arch_evsel__set_sample_weight(struct evsel *evsel) +{ + evsel__set_sample_bit(evsel, WEIGHT_STRUCT); +} diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index d4870074f14c..0be74f048f96 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -7,19 +7,24 @@ #include <string.h> #include <linux/stringify.h> #include "header.h" +#include "utils_header.h" #include "metricgroup.h" #include <api/fs/fs.h> +#include <sys/auxv.h> -#define mfspr(rn) ({unsigned long rval; \ - asm volatile("mfspr %0," __stringify(rn) \ - : "=r" (rval)); rval; }) +static bool is_compat_mode(void) +{ + unsigned long base_platform = getauxval(AT_BASE_PLATFORM); + unsigned long platform = getauxval(AT_PLATFORM); + + if (!strcmp((char *)platform, (char *)base_platform)) + return false; -#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 */ + return true; +} int -get_cpuid(char *buffer, size_t sz) +get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused) { unsigned long pvr; int nb; @@ -37,18 +42,39 @@ get_cpuid(char *buffer, size_t sz) } char * -get_cpuid_str(struct perf_pmu *pmu __maybe_unused) +get_cpuid_str(struct perf_cpu cpu __maybe_unused) { char *bufp; + unsigned long pvr; + + /* + * IBM Power System supports compatible mode. That is + * Nth generation platform can support previous generation + * OS in a mode called compatibile mode. For ex. LPAR can be + * booted in a Power9 mode when the system is a Power10. + * + * In the compatible mode, care must be taken when generating + * PVR value. When read, PVR will be of the AT_BASE_PLATFORM + * To support generic events, return 0x00ffffff as pvr when + * booted in compat mode. Based on this pvr value, json will + * pick events from pmu-events/arch/powerpc/compat + */ + if (!is_compat_mode()) + pvr = mfspr(SPRN_PVR); + else + pvr = 0x00ffffff; - if (asprintf(&bufp, "%.8lx", mfspr(SPRN_PVR)) < 0) + if (asprintf(&bufp, "0x%.8lx", pvr) < 0) bufp = NULL; return bufp; } -int arch_get_runtimeparam(void) +int arch_get_runtimeparam(const struct pmu_metric *pm) { int count; - return sysfs__read_int("/devices/hv_24x7/interface/sockets", &count) < 0 ? 1 : count; + char path[PATH_MAX] = "/devices/hv_24x7/interface/"; + + strcat(path, pm->aggr_mode == PerChip ? "sockets" : "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 index eed9e5a42935..c8357b571ccf 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -5,7 +5,7 @@ #include "util/debug.h" #include "util/evsel.h" #include "util/evlist.h" -#include "util/pmu.h" +#include "util/pmus.h" #include "book3s_hv_exits.h" #include "book3s_hcalls.h" @@ -14,7 +14,6 @@ #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"; @@ -61,13 +60,13 @@ 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])); + return (evsel__name_is(evsel, 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])) { + if (evsel__name_is(evsel, kvm_events_tp[2])) { hcall_event_get_key(evsel, sample, key); return true; } @@ -80,7 +79,7 @@ static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, { const char *hcall_reason = get_hcall_exit_reason(key->key); - scnprintf(decode, decode_str_len, "%s", hcall_reason); + scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", hcall_reason); } static struct kvm_events_ops hcall_events = { @@ -113,10 +112,11 @@ static int is_tracepoint_available(const char *str, struct evlist *evlist) struct parse_events_error err; int ret; - bzero(&err, sizeof(err)); + parse_events_error__init(&err); ret = parse_events(evlist, str, &err); - if (err.str) - parse_events_print_error(&err, "tracepoint"); + if (ret) + parse_events_error__print(&err, "tracepoint"); + parse_events_error__exit(&err); return ret; } @@ -176,7 +176,7 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) } /* - * Incase of powerpc architecture, pmu registers are programmable + * In case 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 @@ -204,7 +204,7 @@ int kvm_add_default_arch_event(int *argc, const char **argv) parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN); if (!event) { - if (pmu_have_event("trace_imc", "trace_cycles")) { + if (perf_pmus__have_event("trace_imc", "trace_cycles")) { argv[j++] = strdup("-e"); argv[j++] = strdup("trace_imc/trace_cycles/"); *argc += 2; diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c index 07fb5e049488..765d4a054b0a 100644 --- a/tools/perf/arch/powerpc/util/mem-events.c +++ b/tools/perf/arch/powerpc/util/mem-events.c @@ -1,12 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 -#include "map_symbol.h" +#include "util/map_symbol.h" +#include "util/mem-events.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/"; +#define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a } - return (char *) "cpu/mem-stores/"; -} +struct perf_mem_event perf_mem_events_power[PERF_MEM_EVENTS__MAX] = { + E("ldlat-loads", "%s/mem-loads/", "mem-loads", false, 0), + E("ldlat-stores", "%s/mem-stores/", "mem-stores", false, 0), + E(NULL, NULL, NULL, false, 0), +}; diff --git a/tools/perf/arch/powerpc/util/mem-events.h b/tools/perf/arch/powerpc/util/mem-events.h new file mode 100644 index 000000000000..6acc3d1b6873 --- /dev/null +++ b/tools/perf/arch/powerpc/util/mem-events.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _POWER_MEM_EVENTS_H +#define _POWER_MEM_EVENTS_H + +extern struct perf_mem_event perf_mem_events_power[PERF_MEM_EVENTS__MAX]; + +#endif /* _POWER_MEM_EVENTS_H */ diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index 0a5242900248..bd36cfd420a2 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -4,12 +4,21 @@ #include <regex.h> #include <linux/zalloc.h> +#include "perf_regs.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> -const struct sample_reg sample_reg_masks[] = { +#define PVR_POWER9 0x004E +#define PVR_POWER10 0x0080 +#define PVR_POWER11 0x0082 + +static 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), @@ -55,6 +64,20 @@ const struct sample_reg sample_reg_masks[] = { 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(pmc1, PERF_REG_POWERPC_PMC1), + SMPL_REG(pmc2, PERF_REG_POWERPC_PMC2), + SMPL_REG(pmc3, PERF_REG_POWERPC_PMC3), + SMPL_REG(pmc4, PERF_REG_POWERPC_PMC4), + SMPL_REG(pmc5, PERF_REG_POWERPC_PMC5), + SMPL_REG(pmc6, PERF_REG_POWERPC_PMC6), + SMPL_REG(sdar, PERF_REG_POWERPC_SDAR), + SMPL_REG(siar, PERF_REG_POWERPC_SIAR), SMPL_REG_END }; @@ -163,3 +186,55 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op) 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) || (version == PVR_POWER11)) + 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; +} + +uint64_t arch__user_reg_mask(void) +{ + return PERF_REGS_MASK; +} + +const struct sample_reg *arch__sample_reg_masks(void) +{ + return sample_reg_masks; +} diff --git a/tools/perf/arch/powerpc/util/pmu.c b/tools/perf/arch/powerpc/util/pmu.c new file mode 100644 index 000000000000..554675deef7b --- /dev/null +++ b/tools/perf/arch/powerpc/util/pmu.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include "../../../util/pmu.h" +#include "mem-events.h" + +void perf_pmu__arch_init(struct perf_pmu *pmu) +{ + if (pmu->is_core) + pmu->mem_events = perf_mem_events_power; +} diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 3018a054526a..356786432fd3 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -45,7 +45,7 @@ static const Dwfl_Callbacks offline_callbacks = { */ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) { - Dwarf_Op ops_mem[2]; + Dwarf_Op ops_mem[3]; Dwarf_Op dummy; Dwarf_Op *ops = &dummy; size_t nops; @@ -159,9 +159,9 @@ static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc) Dwarf_Addr start = pc; Dwarf_Addr end = pc; bool signalp; - const char *exec_file = dso->long_name; + const char *exec_file = dso__long_name(dso); - dwfl = dso->dwfl; + dwfl = RC_CHK_ACCESS(dso)->dwfl; if (!dwfl) { dwfl = dwfl_begin(&offline_callbacks); @@ -183,7 +183,7 @@ static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc) dwfl_end(dwfl); goto out; } - dso->dwfl = dwfl; + RC_CHK_ACCESS(dso)->dwfl = dwfl; } mod = dwfl_addrmodule(dwfl, pc); @@ -250,22 +250,24 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) if (!chain || chain->nr < 3) return skip_slot; + addr_location__init(&al); ip = chain->ips[1]; thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); if (al.map) - dso = al.map->dso; + dso = map__dso(al.map); if (!dso) { pr_debug("%" PRIx64 " dso is NULL\n", ip); + addr_location__exit(&al); return skip_slot; } - rc = check_return_addr(dso, al.map->start, ip); + rc = check_return_addr(dso, map__start(al.map), ip); pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n", - dso->long_name, al.sym->name, ip, rc); + dso__long_name(dso), al.sym->name, ip, rc); if (rc == 0) { /* @@ -279,5 +281,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) */ skip_slot = 3; } + + addr_location__exit(&al); return skip_slot; } diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 0856b32f9e08..947bfad7aa59 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -104,7 +104,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym); - if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) + if (map__dso(map)->symtab_type == DSO_BINARY_TYPE__KALLSYMS) tev->point.offset += PPC64LE_LEP_OFFSET; else if (lep_offset) { if (pev->uprobes) @@ -131,7 +131,7 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev, 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) { + if (map__unmap_ip(map, sym->start) == tev->point.address) { arch__fix_tev_from_maps(pev, tev, map, sym); break; } diff --git a/tools/perf/arch/powerpc/util/unwind-libdw.c b/tools/perf/arch/powerpc/util/unwind-libdw.c index 7b2d96ec28e3..82d0c28ae345 100644 --- a/tools/perf/arch/powerpc/util/unwind-libdw.c +++ b/tools/perf/arch/powerpc/util/unwind-libdw.c @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include <elfutils/libdwfl.h> #include <linux/kernel.h> +#include "perf_regs.h" #include "../../../util/unwind-libdw.h" #include "../../../util/perf_regs.h" -#include "../../../util/event.h" +#include "../../../util/sample.h" /* See backends/ppc_initreg.c and backends/ppc_regs.c in elfutils. */ static const int special_regs[3][2] = { @@ -15,7 +16,7 @@ static const int special_regs[3][2] = { 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; + struct regs_dump *user_regs = perf_sample__user_regs(ui->sample); Dwarf_Word dwarf_regs[32], dwarf_nip; size_t i; 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 000000000000..2baeb1c1ae85 --- /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) /* Revision field */ + +#endif /* __PERF_UTIL_HEADER_H */ |