diff options
Diffstat (limited to 'tools')
56 files changed, 1040 insertions, 301 deletions
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 2ba95d6fe852..caae4843cb70 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -195,6 +195,12 @@ struct kvm_arch_memory_slot { #define KVM_REG_ARM_VFP_FPINST 0x1009 #define KVM_REG_ARM_VFP_FPINST2 0x100A +/* KVM-as-firmware specific pseudo-registers */ +#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW | ((r) & 0xffff)) +#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 9abbf3044654..04b3256f8e6d 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -206,6 +206,12 @@ struct kvm_arch_memory_slot { #define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) #define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2) +/* KVM-as-firmware specific pseudo-registers */ +#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW | ((r) & 0xffff)) +#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index d554c11e01ff..578793e97431 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -320,6 +320,7 @@ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ +#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 1ea545965ee3..53b60ad452f5 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -76,6 +76,8 @@ $(OUTPUT)bpf_asm: $(OUTPUT)bpf_asm.o $(OUTPUT)bpf_exp.yacc.o $(OUTPUT)bpf_exp.le $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c +$(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c +$(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c clean: bpftool_clean $(call QUIET_CLEAN, bpf-progs) diff --git a/tools/bpf/bpf_dbg.c b/tools/bpf/bpf_dbg.c index 4f254bcc4423..61b9aa5d6415 100644 --- a/tools/bpf/bpf_dbg.c +++ b/tools/bpf/bpf_dbg.c @@ -1063,7 +1063,7 @@ static int cmd_load_pcap(char *file) static int cmd_load(char *arg) { - char *subcmd, *cont, *tmp = strdup(arg); + char *subcmd, *cont = NULL, *tmp = strdup(arg); int ret = CMD_OK; subcmd = strtok_r(tmp, " ", &cont); @@ -1073,7 +1073,10 @@ static int cmd_load(char *arg) bpf_reset(); bpf_reset_breakpoints(); - ret = cmd_load_bpf(cont); + if (!cont) + ret = CMD_ERR; + else + ret = cmd_load_bpf(cont); } else if (matches(subcmd, "pcap") == 0) { ret = cmd_load_pcap(cont); } else { diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index b21b586b9854..1738c0391da4 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -6,8 +6,9 @@ #include <stdbool.h> #define spinlock_t pthread_mutex_t -#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER; +#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER #define __SPIN_LOCK_UNLOCKED(x) (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER +#define spin_lock_init(x) pthread_mutex_init(x, NULL) #define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x) #define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 1065006c9bf5..b02c41e53d56 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -676,6 +676,13 @@ struct kvm_ioeventfd { __u8 pad[36]; }; +#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) +#define KVM_X86_DISABLE_EXITS_HTL (1 << 1) +#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) +#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \ + KVM_X86_DISABLE_EXITS_HTL | \ + KVM_X86_DISABLE_EXITS_PAUSE) + /* for KVM_ENABLE_CAP */ struct kvm_enable_cap { /* in */ diff --git a/tools/objtool/arch/x86/include/asm/insn.h b/tools/objtool/arch/x86/include/asm/insn.h index b3e32b010ab1..c2c01f84df75 100644 --- a/tools/objtool/arch/x86/include/asm/insn.h +++ b/tools/objtool/arch/x86/include/asm/insn.h @@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +#define POP_SS_OPCODE 0x1f +#define MOV_SREG_OPCODE 0x8e + +/* + * Intel SDM Vol.3A 6.8.3 states; + * "Any single-step trap that would be delivered following the MOV to SS + * instruction or POP to SS instruction (because EFLAGS.TF is 1) is + * suppressed." + * This function returns true if @insn is MOV SS or POP SS. On these + * instructions, single stepping is suppressed. + */ +static inline int insn_masking_exception(struct insn *insn) +{ + return insn->opcode.bytes[0] == POP_SS_OPCODE || + (insn->opcode.bytes[0] == MOV_SREG_OPCODE && + X86_MODRM_REG(insn->modrm.bytes[0]) == 2); +} + #endif /* _ASM_X86_INSN_H */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5409f6f6c48d..3a31b238f885 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -59,6 +59,31 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file, return next; } +static struct instruction *next_insn_same_func(struct objtool_file *file, + struct instruction *insn) +{ + struct instruction *next = list_next_entry(insn, list); + struct symbol *func = insn->func; + + if (!func) + return NULL; + + if (&next->list != &file->insn_list && next->func == func) + return next; + + /* Check if we're already in the subfunction: */ + if (func == func->cfunc) + return NULL; + + /* Move to the subfunction: */ + return find_insn(file, func->cfunc->sec, func->cfunc->offset); +} + +#define func_for_each_insn_all(file, func, insn) \ + for (insn = find_insn(file, func->sec, func->offset); \ + insn; \ + insn = next_insn_same_func(file, insn)) + #define func_for_each_insn(file, func, insn) \ for (insn = find_insn(file, func->sec, func->offset); \ insn && &insn->list != &file->insn_list && \ @@ -149,10 +174,14 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func, if (!strcmp(func->name, global_noreturns[i])) return 1; - if (!func->sec) + if (!func->len) return 0; - func_for_each_insn(file, func, insn) { + insn = find_insn(file, func->sec, func->offset); + if (!insn->func) + return 0; + + func_for_each_insn_all(file, func, insn) { empty = false; if (insn->type == INSN_RETURN) @@ -167,35 +196,28 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func, * case, the function's dead-end status depends on whether the target * of the sibling call returns. */ - func_for_each_insn(file, func, insn) { - if (insn->sec != func->sec || - insn->offset >= func->offset + func->len) - break; - + func_for_each_insn_all(file, func, insn) { if (insn->type == INSN_JUMP_UNCONDITIONAL) { struct instruction *dest = insn->jump_dest; - struct symbol *dest_func; if (!dest) /* sibling call to another file */ return 0; - if (dest->sec != func->sec || - dest->offset < func->offset || - dest->offset >= func->offset + func->len) { - /* local sibling call */ - dest_func = find_symbol_by_offset(dest->sec, - dest->offset); - if (!dest_func) - continue; + if (dest->func && dest->func->pfunc != insn->func->pfunc) { + /* local sibling call */ if (recursion == 5) { - WARN_FUNC("infinite recursion (objtool bug!)", - dest->sec, dest->offset); - return -1; + /* + * Infinite recursion: two functions + * have sibling calls to each other. + * This is a very rare case. It means + * they aren't dead ends. + */ + return 0; } - return __dead_end_function(file, dest_func, + return __dead_end_function(file, dest->func, recursion + 1); } } @@ -422,7 +444,7 @@ static void add_ignores(struct objtool_file *file) if (!ignore_func(file, func)) continue; - func_for_each_insn(file, func, insn) + func_for_each_insn_all(file, func, insn) insn->ignore = true; } } @@ -782,30 +804,35 @@ out: return ret; } -static int add_switch_table(struct objtool_file *file, struct symbol *func, - struct instruction *insn, struct rela *table, - struct rela *next_table) +static int add_switch_table(struct objtool_file *file, struct instruction *insn, + struct rela *table, struct rela *next_table) { struct rela *rela = table; struct instruction *alt_insn; struct alternative *alt; + struct symbol *pfunc = insn->func->pfunc; + unsigned int prev_offset = 0; list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) { if (rela == next_table) break; - if (rela->sym->sec != insn->sec || - rela->addend <= func->offset || - rela->addend >= func->offset + func->len) + /* Make sure the switch table entries are consecutive: */ + if (prev_offset && rela->offset != prev_offset + 8) break; - alt_insn = find_insn(file, insn->sec, rela->addend); - if (!alt_insn) { - WARN("%s: can't find instruction at %s+0x%x", - file->rodata->rela->name, insn->sec->name, - rela->addend); - return -1; - } + /* Detect function pointers from contiguous objects: */ + if (rela->sym->sec == pfunc->sec && + rela->addend == pfunc->offset) + break; + + alt_insn = find_insn(file, rela->sym->sec, rela->addend); + if (!alt_insn) + break; + + /* Make sure the jmp dest is in the function or subfunction: */ + if (alt_insn->func->pfunc != pfunc) + break; alt = malloc(sizeof(*alt)); if (!alt) { @@ -815,6 +842,13 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func, alt->insn = alt_insn; list_add_tail(&alt->list, &insn->alts); + prev_offset = rela->offset; + } + + if (!prev_offset) { + WARN_FUNC("can't find switch jump table", + insn->sec, insn->offset); + return -1; } return 0; @@ -869,40 +903,21 @@ static struct rela *find_switch_table(struct objtool_file *file, { struct rela *text_rela, *rodata_rela; struct instruction *orig_insn = insn; + unsigned long table_offset; - text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); - if (text_rela && text_rela->sym == file->rodata->sym) { - /* case 1 */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend); - if (rodata_rela) - return rodata_rela; - - /* case 2 */ - rodata_rela = find_rela_by_dest(file->rodata, - text_rela->addend + 4); - if (!rodata_rela) - return NULL; - - file->ignore_unreachables = true; - return rodata_rela; - } - - /* case 3 */ /* * Backward search using the @first_jump_src links, these help avoid * much of the 'in between' code. Which avoids us getting confused by * it. */ - for (insn = list_prev_entry(insn, list); - + for (; &insn->list != &file->insn_list && insn->sec == func->sec && insn->offset >= func->offset; insn = insn->first_jump_src ?: list_prev_entry(insn, list)) { - if (insn->type == INSN_JUMP_DYNAMIC) + if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC) break; /* allow small jumps within the range */ @@ -918,18 +933,29 @@ static struct rela *find_switch_table(struct objtool_file *file, if (!text_rela || text_rela->sym != file->rodata->sym) continue; + table_offset = text_rela->addend; + if (text_rela->type == R_X86_64_PC32) + table_offset += 4; + /* * Make sure the .rodata address isn't associated with a * symbol. gcc jump tables are anonymous data. */ - if (find_symbol_containing(file->rodata, text_rela->addend)) + if (find_symbol_containing(file->rodata, table_offset)) continue; - rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend); - if (!rodata_rela) - continue; + rodata_rela = find_rela_by_dest(file->rodata, table_offset); + if (rodata_rela) { + /* + * Use of RIP-relative switch jumps is quite rare, and + * indicates a rare GCC quirk/bug which can leave dead + * code behind. + */ + if (text_rela->type == R_X86_64_PC32) + file->ignore_unreachables = true; - return rodata_rela; + return rodata_rela; + } } return NULL; @@ -943,7 +969,7 @@ static int add_func_switch_tables(struct objtool_file *file, struct rela *rela, *prev_rela = NULL; int ret; - func_for_each_insn(file, func, insn) { + func_for_each_insn_all(file, func, insn) { if (!last) last = insn; @@ -974,8 +1000,7 @@ static int add_func_switch_tables(struct objtool_file *file, * the beginning of another switch table in the same function. */ if (prev_jump) { - ret = add_switch_table(file, func, prev_jump, prev_rela, - rela); + ret = add_switch_table(file, prev_jump, prev_rela, rela); if (ret) return ret; } @@ -985,7 +1010,7 @@ static int add_func_switch_tables(struct objtool_file *file, } if (prev_jump) { - ret = add_switch_table(file, func, prev_jump, prev_rela, NULL); + ret = add_switch_table(file, prev_jump, prev_rela, NULL); if (ret) return ret; } @@ -1749,15 +1774,13 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, while (1) { next_insn = next_insn_same_sec(file, insn); - - if (file->c_file && func && insn->func && func != insn->func) { + if (file->c_file && func && insn->func && func != insn->func->pfunc) { WARN("%s() falls through to next function %s()", func->name, insn->func->name); return 1; } - if (insn->func) - func = insn->func; + func = insn->func ? insn->func->pfunc : NULL; if (func && insn->ignore) { WARN_FUNC("BUG: why am I validating an ignored function?", @@ -1778,7 +1801,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, i = insn; save_insn = NULL; - func_for_each_insn_continue_reverse(file, func, i) { + func_for_each_insn_continue_reverse(file, insn->func, i) { if (i->save) { save_insn = i; break; @@ -1865,7 +1888,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, case INSN_JUMP_UNCONDITIONAL: if (insn->jump_dest && (!func || !insn->jump_dest->func || - func == insn->jump_dest->func)) { + insn->jump_dest->func->pfunc == func)) { ret = validate_branch(file, insn->jump_dest, state); if (ret) @@ -2060,7 +2083,7 @@ static int validate_functions(struct objtool_file *file) for_each_sec(file, sec) { list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) + if (func->type != STT_FUNC || func->pfunc != func) continue; insn = find_insn(file, sec, func->offset); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index c1c338661699..4e60e105583e 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -79,6 +79,19 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset) return NULL; } +struct symbol *find_symbol_by_name(struct elf *elf, const char *name) +{ + struct section *sec; + struct symbol *sym; + + list_for_each_entry(sec, &elf->sections, list) + list_for_each_entry(sym, &sec->symbol_list, list) + if (!strcmp(sym->name, name)) + return sym; + + return NULL; +} + struct symbol *find_symbol_containing(struct section *sec, unsigned long offset) { struct symbol *sym; @@ -203,10 +216,11 @@ static int read_sections(struct elf *elf) static int read_symbols(struct elf *elf) { - struct section *symtab; - struct symbol *sym; + struct section *symtab, *sec; + struct symbol *sym, *pfunc; struct list_head *entry, *tmp; int symbols_nr, i; + char *coldstr; symtab = find_section_by_name(elf, ".symtab"); if (!symtab) { @@ -281,6 +295,30 @@ static int read_symbols(struct elf *elf) hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx); } + /* Create parent/child links for any cold subfunctions */ + list_for_each_entry(sec, &elf->sections, list) { + list_for_each_entry(sym, &sec->symbol_list, list) { + if (sym->type != STT_FUNC) + continue; + sym->pfunc = sym->cfunc = sym; + coldstr = strstr(sym->name, ".cold."); + if (coldstr) { + coldstr[0] = '\0'; + pfunc = find_symbol_by_name(elf, sym->name); + coldstr[0] = '.'; + + if (!pfunc) { + WARN("%s(): can't find parent function", + sym->name); + goto err; + } + + sym->pfunc = pfunc; + pfunc->cfunc = sym; + } + } + } + return 0; err: diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index d86e2ff14466..de5cd2ddded9 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -61,6 +61,7 @@ struct symbol { unsigned char bind, type; unsigned long offset; unsigned int len; + struct symbol *pfunc, *cfunc; }; struct rela { @@ -86,6 +87,7 @@ struct elf { struct elf *elf_open(const char *name, int flags); struct section *find_section_by_name(struct elf *elf, const char *name); struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); +struct symbol *find_symbol_by_name(struct elf *elf, const char *name); struct symbol *find_symbol_containing(struct section *sec, unsigned long offset); struct rela *find_rela_by_dest(struct section *sec, unsigned long offset); struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset, diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 8806ed5f3802..f8d2167cf3e7 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -28,29 +28,46 @@ OPTIONS <command>...:: Any command you can specify in a shell. +-i:: +--input=<file>:: + Input file name. + -f:: --force:: Don't do ownership validation -t:: ---type=:: +--type=<type>:: Select the memory operation type: load or store (default: load,store) -D:: ---dump-raw-samples=:: +--dump-raw-samples:: Dump the raw decoded samples on the screen in a format that is easy to parse with one sample per line. -x:: ---field-separator:: +--field-separator=<separator>:: Specify the field separator used when dump raw samples (-D option). By default, The separator is the space character. -C:: ---cpu-list:: - Restrict dump of raw samples to those provided via this option. Note that the same - option can be passed in record mode. It will be interpreted the same way as perf - record. +--cpu=<cpu>:: + Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a + comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default + is to monitor all CPUS. +-U:: +--hide-unresolved:: + Only display entries resolved to a symbol. + +-p:: +--phys-data:: + Record/Report sample physical addresses + +RECORD OPTIONS +-------------- +-e:: +--event <event>:: + Event selector. Use 'perf mem record -e list' to list available events. -K:: --all-kernel:: @@ -60,12 +77,12 @@ OPTIONS --all-user:: Configure all used events to run in user space. ---ldload:: - Specify desired latency for loads event. +-v:: +--verbose:: + Be more verbose (show counter open errors, etc) --p:: ---phys-data:: - Record/Report sample physical addresses +--ldlat <n>:: + Specify desired latency for loads event. In addition, for report all perf report options are valid, and for record all perf record options. diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c index 6cb48e4cffd9..3afe8256eff2 100644 --- a/tools/perf/arch/s390/util/auxtrace.c +++ b/tools/perf/arch/s390/util/auxtrace.c @@ -87,6 +87,7 @@ struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, struct perf_evsel *pos; int diagnose = 0; + *err = 0; if (evlist->nr_entries == 0) return NULL; diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c index a4c30f1c70be..163b92f33998 100644 --- a/tools/perf/arch/s390/util/header.c +++ b/tools/perf/arch/s390/util/header.c @@ -146,21 +146,3 @@ char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused) zfree(&buf); return buf; } - -/* - * Compare the cpuid string returned by get_cpuid() function - * with the name generated by the jevents file read from - * pmu-events/arch/s390/mapfile.csv. - * - * Parameter mapcpuid is the cpuid as stored in the - * pmu-events/arch/s390/mapfile.csv. This is just the type number. - * Parameter cpuid is the cpuid returned by function get_cpuid(). - */ -int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) -{ - char *cp = strchr(cpuid, ','); - - if (cp == NULL) - return -1; - return strncmp(cp + 1, mapcpuid, strlen(mapcpuid)); -} diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 944070e98a2c..63eb49082774 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -175,7 +175,7 @@ static const struct option options[] = { OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run (default: 5 secs)"), OPT_UINTEGER('u', "usleep" , &p0.sleep_usecs, "usecs to sleep per loop iteration"), - OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via writes (can be mixed with -W)"), + OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via reads (can be mixed with -W)"), OPT_BOOLEAN('W', "data_writes" , &p0.data_writes, "access the data via writes (can be mixed with -R)"), OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards, "access the data backwards as well"), OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"), diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 147a27e8c937..f17dc601b0f3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -172,6 +172,7 @@ static bool interval_count; static const char *output_name; static int output_fd; static int print_free_counters_hint; +static int print_mixed_hw_group_error; struct perf_stat { bool record; @@ -1126,6 +1127,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); } +static bool is_mixed_hw_group(struct perf_evsel *counter) +{ + struct perf_evlist *evlist = counter->evlist; + u32 pmu_type = counter->attr.type; + struct perf_evsel *pos; + + if (counter->nr_members < 2) + return false; + + evlist__for_each_entry(evlist, pos) { + /* software events can be part of any hardware group */ + if (pos->attr.type == PERF_TYPE_SOFTWARE) + continue; + if (pmu_type == PERF_TYPE_SOFTWARE) { + pmu_type = pos->attr.type; + continue; + } + if (pmu_type != pos->attr.type) + return true; + } + + return false; +} + static void printout(int id, int nr, struct perf_evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise, struct runtime_stat *st) @@ -1178,8 +1203,11 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep); - if (counter->supported) + if (counter->supported) { print_free_counters_hint = 1; + if (is_mixed_hw_group(counter)) + print_mixed_hw_group_error = 1; + } fprintf(stat_config.output, "%-*s%s", csv_output ? 0 : unit_width, @@ -1256,7 +1284,8 @@ static void uniquify_event_name(struct perf_evsel *counter) char *new_name; char *config; - if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name, + if (counter->uniquified_name || + !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, strlen(counter->pmu_name))) return; @@ -1274,6 +1303,8 @@ static void uniquify_event_name(struct perf_evsel *counter) counter->name = new_name; } } + + counter->uniquified_name = true; } static void collect_all_aliases(struct perf_evsel *counter, @@ -1757,6 +1788,11 @@ static void print_footer(void) " echo 0 > /proc/sys/kernel/nmi_watchdog\n" " perf stat ...\n" " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); + + if (print_mixed_hw_group_error) + fprintf(output, + "The events in group usually have to be from " + "the same PMU. Try reorganizing the group.\n"); } static void print_counters(struct timespec *ts, int argc, const char **argv) diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv index ca7682748a4b..78bcf7f8e206 100644 --- a/tools/perf/pmu-events/arch/s390/mapfile.csv +++ b/tools/perf/pmu-events/arch/s390/mapfile.csv @@ -1,6 +1,6 @@ Family-model,Version,Filename,EventType -209[78],1,cf_z10,core -281[78],1,cf_z196,core -282[78],1,cf_zec12,core -296[45],1,cf_z13,core -3906,3,cf_z14,core +^IBM.209[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z10,core +^IBM.281[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z196,core +^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core +^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core +^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 93656f2fd53a..7e3cce3bcf3b 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -29,7 +29,6 @@ GenuineIntel-6-4D,v13,silvermont,core GenuineIntel-6-4C,v13,silvermont,core GenuineIntel-6-2A,v15,sandybridge,core GenuineIntel-6-2C,v2,westmereep-dp,core -GenuineIntel-6-2C,v2,westmereep-dp,core GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core GenuineIntel-6-55,v1,skylakex,core diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index f906b793196f..8a33ca4f9e1f 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -35,3 +35,6 @@ inherit=0 # sampling disabled sample_freq=0 sample_period=0 +freq=0 +write_backward=0 +sample_id_all=0 diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 1ecc1f0ff84a..ee86473643be 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -16,15 +16,13 @@ nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254 trace_libc_inet_pton_backtrace() { idx=0 expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" - expected[1]=".*inet_pton[[:space:]]\($libc\)$" + expected[1]=".*inet_pton[[:space:]]\($libc|inlined\)$" case "$(uname -m)" in s390x) - eventattr='call-graph=dwarf' + eventattr='call-graph=dwarf,max-stack=4' expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$" - expected[3]="__GI_getaddrinfo[[:space:]]\($libc|inlined\)$" + expected[3]="(__GI_)?getaddrinfo[[:space:]]\($libc|inlined\)$" expected[4]="main[[:space:]]\(.*/bin/ping.*\)$" - expected[5]="__libc_start_main[[:space:]]\($libc\)$" - expected[6]="_start[[:space:]]\(.*/bin/ping.*\)$" ;; *) eventattr='max-stack=3' diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 536ee148bff8..5d74a30fe00f 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1263,6 +1263,9 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start max_percent = sample->percent; } + if (al->samples_nr > nr_percent) + nr_percent = al->samples_nr; + if (max_percent < min_pcnt) return -1; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 40020b1ca54f..bf16dc9ee507 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -239,6 +239,7 @@ static void cs_etm__free(struct perf_session *session) for (i = 0; i < aux->num_cpu; i++) zfree(&aux->metadata[i]); + thread__zput(aux->unknown_thread); zfree(&aux->metadata); zfree(&aux); } @@ -612,8 +613,8 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq) return buff->len; } -static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, - struct auxtrace_queue *queue) +static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, + struct auxtrace_queue *queue) { struct cs_etm_queue *etmq = queue->priv; @@ -1357,6 +1358,23 @@ int cs_etm__process_auxtrace_info(union perf_event *event, etm->auxtrace.free = cs_etm__free; session->auxtrace = &etm->auxtrace; + etm->unknown_thread = thread__new(999999999, 999999999); + if (!etm->unknown_thread) + goto err_free_queues; + + /* + * Initialize list node so that at thread__zput() we can avoid + * segmentation fault at list_del_init(). + */ + INIT_LIST_HEAD(&etm->unknown_thread->node); + + err = thread__set_comm(etm->unknown_thread, "unknown", 0); + if (err) + goto err_delete_thread; + + if (thread__init_map_groups(etm->unknown_thread, etm->machine)) + goto err_delete_thread; + if (dump_trace) { cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu); return 0; @@ -1371,16 +1389,18 @@ int cs_etm__process_auxtrace_info(union perf_event *event, err = cs_etm__synth_events(etm, session); if (err) - goto err_free_queues; + goto err_delete_thread; err = auxtrace_queues__process_index(&etm->queues, session); if (err) - goto err_free_queues; + goto err_delete_thread; etm->data_queued = etm->queues.populated; return 0; +err_delete_thread: + thread__zput(etm->unknown_thread); err_free_queues: auxtrace_queues__free(&etm->queues); session->auxtrace = NULL; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 3e87486c28fe..4cd2cf93f726 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -930,8 +930,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * than leader in case leader 'leads' the sampling. */ if ((leader != evsel) && leader->sample_read) { - attr->sample_freq = 0; - attr->sample_period = 0; + attr->freq = 0; + attr->sample_freq = 0; + attr->sample_period = 0; + attr->write_backward = 0; + attr->sample_id_all = 0; } if (opts->no_samples) @@ -1922,7 +1925,8 @@ try_fallback: goto fallback_missing_features; } else if (!perf_missing_features.group_read && evsel->attr.inherit && - (evsel->attr.read_format & PERF_FORMAT_GROUP)) { + (evsel->attr.read_format & PERF_FORMAT_GROUP) && + perf_evsel__is_group_leader(evsel)) { perf_missing_features.group_read = true; pr_debug2("switching off group read\n"); goto fallback_missing_features; @@ -2754,8 +2758,14 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, (paranoid = perf_event_paranoid()) > 1) { const char *name = perf_evsel__name(evsel); char *new_name; + const char *sep = ":"; - if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0) + /* Is there already the separator in the name. */ + if (strchr(name, '/') || + strchr(name, ':')) + sep = ""; + + if (asprintf(&new_name, "%s%su", name, sep) < 0) return false; if (evsel->name) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d3ee3af618ef..92ec009a292d 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -115,6 +115,7 @@ struct perf_evsel { unsigned int sample_size; int id_pos; int is_pos; + bool uniquified_name; bool snapshot; bool supported; bool needs_swap; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 2eca8478e24f..32d50492505d 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1019,13 +1019,6 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type) return ret; } -static void map_groups__fixup_end(struct map_groups *mg) -{ - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - __map_groups__fixup_end(mg, i); -} - static char *get_kernel_version(const char *root_dir) { char version[PATH_MAX]; @@ -1233,6 +1226,7 @@ int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); const char *name = NULL; + struct map *map; u64 addr = 0; int ret; @@ -1259,13 +1253,25 @@ int machine__create_kernel_maps(struct machine *machine) machine__destroy_kernel_maps(machine); return -1; } - machine__set_kernel_mmap(machine, addr, 0); + + /* we have a real start address now, so re-order the kmaps */ + map = machine__kernel_map(machine); + + map__get(map); + map_groups__remove(&machine->kmaps, map); + + /* assume it's the last in the kmaps */ + machine__set_kernel_mmap(machine, addr, ~0ULL); + + map_groups__insert(&machine->kmaps, map); + map__put(map); } - /* - * Now that we have all the maps created, just set the ->end of them: - */ - map_groups__fixup_end(&machine->kmaps); + /* update end address of the kernel map using adjacent module address */ + map = map__next(machine__kernel_map(machine)); + if (map) + machine__set_kernel_mmap(machine, addr, map->start); + return 0; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 2fb0272146d8..b8b8a9558d32 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1715,7 +1715,7 @@ int parse_events(struct perf_evlist *evlist, const char *str, struct perf_evsel *last; if (list_empty(&parse_state.list)) { - WARN_ONCE(true, "WARNING: event parser found nothing"); + WARN_ONCE(true, "WARNING: event parser found nothing\n"); return -1; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 61a5e5027338..d2fb597c9a8c 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -539,9 +539,10 @@ static bool pmu_is_uncore(const char *name) /* * PMU CORE devices have different name other than cpu in sysfs on some - * platforms. looking for possible sysfs files to identify as core device. + * platforms. + * Looking for possible sysfs files to identify the arm core device. */ -static int is_pmu_core(const char *name) +static int is_arm_pmu_core(const char *name) { struct stat st; char path[PATH_MAX]; @@ -550,12 +551,6 @@ static int is_pmu_core(const char *name) if (!sysfs) return 0; - /* Look for cpu sysfs (x86 and others) */ - scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs); - if ((stat(path, &st) == 0) && - (strncmp(name, "cpu", strlen("cpu")) == 0)) - return 1; - /* Look for cpu sysfs (specific to arm) */ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus", sysfs, name); @@ -586,7 +581,7 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused) * cpuid string generated on this platform. * Otherwise return non-zero. */ -int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) +int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) { regex_t re; regmatch_t pmatch[1]; @@ -668,6 +663,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) struct pmu_events_map *map; struct pmu_event *pe; const char *name = pmu->name; + const char *pname; map = perf_pmu__find_map(pmu); if (!map) @@ -686,11 +682,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) break; } - if (!is_pmu_core(name)) { - /* check for uncore devices */ - if (pe->pmu == NULL) - continue; - if (strncmp(pe->pmu, name, strlen(pe->pmu))) + if (!is_arm_pmu_core(name)) { + pname = pe->pmu ? pe->pmu : "cpu"; + if (strncmp(pname, name, strlen(pname))) continue; } diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config index 2cccbba64418..f304be71c278 100644 --- a/tools/power/acpi/Makefile.config +++ b/tools/power/acpi/Makefile.config @@ -56,6 +56,7 @@ INSTALL_SCRIPT = ${INSTALL_PROGRAM} # to compile vs uClibc, that can be done here as well. CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc- CROSS_COMPILE ?= $(CROSS) +LD = $(CC) HOSTCC = gcc # check if compiler option is supported diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index fa7ee369b3c9..db66f8a0d4be 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -17,7 +17,7 @@ ifeq ($(BUILD), 32) LDFLAGS += -m32 endif -targets: mapshift $(TARGETS) +targets: generated/map-shift.h $(TARGETS) main: $(OFILES) @@ -42,9 +42,7 @@ radix-tree.c: ../../../lib/radix-tree.c idr.c: ../../../lib/idr.c sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ -.PHONY: mapshift - -mapshift: +generated/map-shift.h: @if ! grep -qws $(SHIFT) generated/map-shift.h; then \ echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \ generated/map-shift.h; \ diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 59245b3d587c..7bf405638b0b 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -16,6 +16,7 @@ #include <linux/radix-tree.h> #include <linux/slab.h> #include <linux/errno.h> +#include <pthread.h> #include "test.h" @@ -624,6 +625,67 @@ static void multiorder_account(void) item_kill_tree(&tree); } +bool stop_iteration = false; + +static void *creator_func(void *ptr) +{ + /* 'order' is set up to ensure we have sibling entries */ + unsigned int order = RADIX_TREE_MAP_SHIFT - 1; + struct radix_tree_root *tree = ptr; + int i; + + for (i = 0; i < 10000; i++) { + item_insert_order(tree, 0, order); + item_delete_rcu(tree, 0); + } + + stop_iteration = true; + return NULL; +} + +static void *iterator_func(void *ptr) +{ + struct radix_tree_root *tree = ptr; + struct radix_tree_iter iter; + struct item *item; + void **slot; + + while (!stop_iteration) { + rcu_read_lock(); + radix_tree_for_each_slot(slot, tree, &iter, 0) { + item = radix_tree_deref_slot(slot); + + if (!item) + continue; + if (radix_tree_deref_retry(item)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + item_sanity(item, iter.index); + } + rcu_read_unlock(); + } + return NULL; +} + +static void multiorder_iteration_race(void) +{ + const int num_threads = sysconf(_SC_NPROCESSORS_ONLN); + pthread_t worker_thread[num_threads]; + RADIX_TREE(tree, GFP_KERNEL); + int i; + + pthread_create(&worker_thread[0], NULL, &creator_func, &tree); + for (i = 1; i < num_threads; i++) + pthread_create(&worker_thread[i], NULL, &iterator_func, &tree); + + for (i = 0; i < num_threads; i++) + pthread_join(worker_thread[i], NULL); + + item_kill_tree(&tree); +} + void multiorder_checks(void) { int i; @@ -644,6 +706,7 @@ void multiorder_checks(void) multiorder_join(); multiorder_split(); multiorder_account(); + multiorder_iteration_race(); radix_tree_cpu_dead(0); } diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index 5978ab1f403d..def6015570b2 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -75,6 +75,25 @@ int item_delete(struct radix_tree_root *root, unsigned long index) return 0; } +static void item_free_rcu(struct rcu_head *head) +{ + struct item *item = container_of(head, struct item, rcu_head); + + free(item); +} + +int item_delete_rcu(struct radix_tree_root *root, unsigned long index) +{ + struct item *item = radix_tree_delete(root, index); + + if (item) { + item_sanity(item, index); + call_rcu(&item->rcu_head, item_free_rcu); + return 1; + } + return 0; +} + void item_check_present(struct radix_tree_root *root, unsigned long index) { struct item *item; diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index d9c031dbeb1a..31f1d9b6f506 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -5,6 +5,7 @@ #include <linux/rcupdate.h> struct item { + struct rcu_head rcu_head; unsigned long index; unsigned int order; }; @@ -12,9 +13,11 @@ struct item { struct item *item_create(unsigned long index, unsigned int order); int __item_insert(struct radix_tree_root *root, struct item *item); int item_insert(struct radix_tree_root *root, unsigned long index); +void item_sanity(struct item *item, unsigned long index); int item_insert_order(struct radix_tree_root *root, unsigned long index, unsigned order); int item_delete(struct radix_tree_root *root, unsigned long index); +int item_delete_rcu(struct radix_tree_root *root, unsigned long index); struct item *item_lookup(struct radix_tree_root *root, unsigned long index); void item_check_present(struct radix_tree_root *root, unsigned long index); diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 9cf83f895d98..5e1ab2f0eb79 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -12,3 +12,6 @@ test_tcpbpf_user test_verifier_log feature test_libbpf_open +test_sock +test_sock_addr +urandom_read diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index faadbe233966..4123d0ab90ba 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -1108,7 +1108,7 @@ static void test_stacktrace_build_id(void) assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0); - assert(system("./urandom_read if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0); + assert(system("./urandom_read") == 0); /* disable stack trace collection */ key = 0; val = 1; @@ -1158,7 +1158,7 @@ static void test_stacktrace_build_id(void) } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0); CHECK(build_id_matches < 1, "build id match", - "Didn't find expected build ID from the map"); + "Didn't find expected build ID from the map\n"); disable_pmu: ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE); diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index 73bb20cfb9b7..f4d99fabc56d 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -13,6 +13,7 @@ #include <bpf/bpf.h> #include "cgroup_helpers.h" +#include "bpf_rlimit.h" #ifndef ARRAY_SIZE # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index d488f20926e8..2950f80ba7fb 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -15,6 +15,7 @@ #include <bpf/libbpf.h> #include "cgroup_helpers.h" +#include "bpf_rlimit.h" #define CG_PATH "/foo" #define CONNECT4_PROG_PATH "./connect4_prog.o" diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh index c6e1dcf992c4..9832a875a828 100755 --- a/tools/testing/selftests/bpf/test_sock_addr.sh +++ b/tools/testing/selftests/bpf/test_sock_addr.sh @@ -4,7 +4,7 @@ set -eu ping_once() { - ping -q -c 1 -W 1 ${1%%/*} >/dev/null 2>&1 + ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1 } wait_for_ip() @@ -13,7 +13,7 @@ wait_for_ip() echo -n "Wait for testing IPv4/IPv6 to become available " for _i in $(seq ${MAX_PING_TRIES}); do echo -n "." - if ping_once ${TEST_IPv4} && ping_once ${TEST_IPv6}; then + if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then echo " OK" return fi diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile index 826f38d5dd19..261c81f08606 100644 --- a/tools/testing/selftests/firmware/Makefile +++ b/tools/testing/selftests/firmware/Makefile @@ -4,6 +4,7 @@ all: TEST_PROGS := fw_run_tests.sh +TEST_FILES := fw_fallback.sh fw_filesystem.sh fw_lib.sh include ../lib.mk diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh index 9ea31b57d71a..962d7f4ac627 100755 --- a/tools/testing/selftests/firmware/fw_lib.sh +++ b/tools/testing/selftests/firmware/fw_lib.sh @@ -154,11 +154,13 @@ test_finish() if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout fi - if [ "$OLD_FWPATH" = "" ]; then - OLD_FWPATH=" " - fi if [ "$TEST_REQS_FW_SET_CUSTOM_PATH" = "yes" ]; then - echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path + if [ "$OLD_FWPATH" = "" ]; then + # A zero-length write won't work; write a null byte + printf '\000' >/sys/module/firmware_class/parameters/path + else + echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path + fi fi if [ -f $FW ]; then rm -f "$FW" diff --git a/tools/testing/selftests/firmware/fw_run_tests.sh b/tools/testing/selftests/firmware/fw_run_tests.sh index 06d638e9dc62..cffdd4eb0a57 100755 --- a/tools/testing/selftests/firmware/fw_run_tests.sh +++ b/tools/testing/selftests/firmware/fw_run_tests.sh @@ -66,5 +66,5 @@ if [ -f $FW_FORCE_SYSFS_FALLBACK ]; then run_test_config_0003 else echo "Running basic kernel configuration, working with your config" - run_test + run_tests fi diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc index 786dce7e48be..2aabab363cfb 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc @@ -29,7 +29,7 @@ do_reset echo "Test extended error support" echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger -echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger &>/dev/null +! echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger 2> /dev/null if ! grep -q "ERROR:" events/sched/sched_wakeup/hist; then fail "Failed to generate extended error in histogram" fi diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc new file mode 100644 index 000000000000..c193dce611a2 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc @@ -0,0 +1,44 @@ +#!/bin/sh +# description: event trigger - test multiple actions on hist trigger + + +do_reset() { + reset_trigger + echo > set_event + clear_trace +} + +fail() { #msg + do_reset + echo $1 + exit_fail +} + +if [ ! -f set_event ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +if [ ! -f synthetic_events ]; then + echo "synthetic event is not supported" + exit_unsupported +fi + +clear_synthetic_events +reset_tracer +do_reset + +echo "Test multiple actions on hist trigger" +echo 'wakeup_latency u64 lat; pid_t pid' >> synthetic_events +TRIGGER1=events/sched/sched_wakeup/trigger +TRIGGER2=events/sched/sched_switch/trigger + +echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="cyclictest"' > $TRIGGER1 +echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0 if next_comm=="cyclictest"' >> $TRIGGER2 +echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,next_pid) if next_comm=="cyclictest"' >> $TRIGGER2 +echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,prev_pid) if next_comm=="cyclictest"' >> $TRIGGER2 +echo 'hist:keys=next_pid if next_comm=="cyclictest"' >> $TRIGGER2 + +do_reset + +exit 0 diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 2ddcc96ae456..d9d00319b07c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -15,7 +15,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ -CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) +CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I.. # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 7ab98e41324f..ac53730b30aa 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -19,6 +19,7 @@ #include <errno.h> #include <unistd.h> #include <fcntl.h> +#include "kselftest.h" ssize_t test_write(int fd, const void *buf, size_t count); ssize_t test_read(int fd, void *buf, size_t count); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 2cedfda181d4..37e2a787d2fc 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -50,8 +50,8 @@ int kvm_check_cap(long cap) int kvm_fd; kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i", - KVM_DEV_PATH, kvm_fd, errno); + if (kvm_fd < 0) + exit(KSFT_SKIP); ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" @@ -91,8 +91,8 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) vm->mode = mode; kvm_fd = open(KVM_DEV_PATH, perm); - TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i", - KVM_DEV_PATH, kvm_fd, errno); + if (kvm_fd < 0) + exit(KSFT_SKIP); /* Create VM. */ vm->fd = ioctl(kvm_fd, KVM_CREATE_VM, NULL); @@ -418,8 +418,8 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void) cpuid = allocate_kvm_cpuid2(); kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i", - KVM_DEV_PATH, kvm_fd, errno); + if (kvm_fd < 0) + exit(KSFT_SKIP); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", @@ -675,8 +675,8 @@ static int vcpu_mmap_sz(void) int dev_fd, ret; dev_fd = open(KVM_DEV_PATH, O_RDONLY); - TEST_ASSERT(dev_fd >= 0, "%s open %s failed, rc: %i errno: %i", - __func__, KVM_DEV_PATH, dev_fd, errno); + if (dev_fd < 0) + exit(KSFT_SKIP); ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); TEST_ASSERT(ret >= sizeof(struct kvm_run), diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/sync_regs_test.c index 428e9473f5e2..eae1ece3c31b 100644 --- a/tools/testing/selftests/kvm/sync_regs_test.c +++ b/tools/testing/selftests/kvm/sync_regs_test.c @@ -85,6 +85,9 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left, { } +#define TEST_SYNC_FIELDS (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS) +#define INVALID_SYNC_FIELD 0x80000000 + int main(int argc, char *argv[]) { struct kvm_vm *vm; @@ -98,9 +101,14 @@ int main(int argc, char *argv[]) setbuf(stdout, NULL); cap = kvm_check_cap(KVM_CAP_SYNC_REGS); - TEST_ASSERT((unsigned long)cap == KVM_SYNC_X86_VALID_FIELDS, - "KVM_CAP_SYNC_REGS (0x%x) != KVM_SYNC_X86_VALID_FIELDS (0x%lx)\n", - cap, KVM_SYNC_X86_VALID_FIELDS); + if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) { + fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n"); + exit(KSFT_SKIP); + } + if ((cap & INVALID_SYNC_FIELD) != 0) { + fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n"); + exit(KSFT_SKIP); + } /* Create VM */ vm = vm_create_default(VCPU_ID, guest_code); @@ -108,7 +116,14 @@ int main(int argc, char *argv[]) run = vcpu_state(vm, VCPU_ID); /* Request reading invalid register set from VCPU. */ - run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS << 1; + run->kvm_valid_regs = INVALID_SYNC_FIELD; + rv = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rv < 0 && errno == EINVAL, + "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", + rv); + vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; + + run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", @@ -116,7 +131,14 @@ int main(int argc, char *argv[]) vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; /* Request setting invalid register set into VCPU. */ - run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS << 1; + run->kvm_dirty_regs = INVALID_SYNC_FIELD; + rv = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rv < 0 && errno == EINVAL, + "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", + rv); + vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0; + + run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", @@ -125,7 +147,7 @@ int main(int argc, char *argv[]) /* Request and verify all valid register sets. */ /* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */ - run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS; + run->kvm_valid_regs = TEST_SYNC_FIELDS; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", @@ -146,7 +168,7 @@ int main(int argc, char *argv[]) run->s.regs.sregs.apic_base = 1 << 11; /* TODO run->s.regs.events.XYZ = ABC; */ - run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS; + run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, @@ -172,7 +194,7 @@ int main(int argc, char *argv[]) /* Clear kvm_dirty_regs bits, verify new s.regs values are * overwritten with existing guest values. */ - run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS; + run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = 0; run->s.regs.regs.r11 = 0xDEADBEEF; rv = _vcpu_run(vm, VCPU_ID); @@ -211,7 +233,7 @@ int main(int argc, char *argv[]) * with kvm_sync_regs values. */ run->kvm_valid_regs = 0; - run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS; + run->kvm_dirty_regs = TEST_SYNC_FIELDS; run->s.regs.regs.r11 = 0xBBBB; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c index 8f7f62093add..aaa633263b2c 100644 --- a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c @@ -189,8 +189,8 @@ int main(int argc, char *argv[]) struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); if (!(entry->ecx & CPUID_VMX)) { - printf("nested VMX not enabled, skipping test"); - return 0; + fprintf(stderr, "nested VMX not enabled, skipping test\n"); + exit(KSFT_SKIP); } vm = vm_create_default_vmx(VCPU_ID, (void *) l1_guest_code); diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 195e9d4739a9..c1b1a4dc6a96 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -20,10 +20,10 @@ all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) .ONESHELL: define RUN_TESTS - @export KSFT_TAP_LEVEL=`echo 1`; - @test_num=`echo 0`; - @echo "TAP version 13"; - @for TEST in $(1); do \ + @export KSFT_TAP_LEVEL=`echo 1`; \ + test_num=`echo 0`; \ + echo "TAP version 13"; \ + for TEST in $(1); do \ BASENAME_TEST=`basename $$TEST`; \ test_num=`echo $$test_num+1 | bc`; \ echo "selftests: $$BASENAME_TEST"; \ diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 8f1e13d2e547..3ff81a478dbe 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,7 +5,8 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh -TEST_PROGS += fib_tests.sh fib-onlink-tests.sh in_netns.sh pmtu.sh +TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh +TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 5b012f4981d4..6f289a49e5ec 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -66,7 +66,7 @@ "cmdUnderTest": "$TC action add action bpf object-file _b.o index 667", "expExitCode": "0", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c default-action pipe.*index 667 ref", + "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref", "matchCount": "1", "teardown": [ "$TC action flush action bpf", @@ -92,10 +92,15 @@ "cmdUnderTest": "$TC action add action bpf object-file _c.o index 667", "expExitCode": "255", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9].*index 667 ref", + "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref", "matchCount": "0", "teardown": [ - "$TC action flush action bpf", + [ + "$TC action flush action bpf", + 0, + 1, + 255 + ], "rm -f _c.o" ] }, diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index d744991c0f4f..39f66bc29b82 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -11,7 +11,7 @@ CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl mpx-mini-test ioperm \ - protection_keys test_vdso test_vsyscall + protection_keys test_vdso test_vsyscall mov_ss_trap TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/mov_ss_trap.c b/tools/testing/selftests/x86/mov_ss_trap.c new file mode 100644 index 000000000000..3c3a022654f3 --- /dev/null +++ b/tools/testing/selftests/x86/mov_ss_trap.c @@ -0,0 +1,285 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * mov_ss_trap.c: Exercise the bizarre side effects of a watchpoint on MOV SS + * + * This does MOV SS from a watchpointed address followed by various + * types of kernel entries. A MOV SS that hits a watchpoint will queue + * up a #DB trap but will not actually deliver that trap. The trap + * will be delivered after the next instruction instead. The CPU's logic + * seems to be: + * + * - Any fault: drop the pending #DB trap. + * - INT $N, INT3, INTO, SYSCALL, SYSENTER: enter the kernel and then + * deliver #DB. + * - ICEBP: enter the kernel but do not deliver the watchpoint trap + * - breakpoint: only one #DB is delivered (phew!) + * + * There are plenty of ways for a kernel to handle this incorrectly. This + * test tries to exercise all the cases. + * + * This should mostly cover CVE-2018-1087 and CVE-2018-8897. + */ +#define _GNU_SOURCE + +#include <stdlib.h> +#include <sys/ptrace.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/user.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <errno.h> +#include <stddef.h> +#include <stdio.h> +#include <err.h> +#include <string.h> +#include <setjmp.h> +#include <sys/prctl.h> + +#define X86_EFLAGS_RF (1UL << 16) + +#if __x86_64__ +# define REG_IP REG_RIP +#else +# define REG_IP REG_EIP +#endif + +unsigned short ss; +extern unsigned char breakpoint_insn[]; +sigjmp_buf jmpbuf; +static unsigned char altstack_data[SIGSTKSZ]; + +static void enable_watchpoint(void) +{ + pid_t parent = getpid(); + int status; + + pid_t child = fork(); + if (child < 0) + err(1, "fork"); + + if (child) { + if (waitpid(child, &status, 0) != child) + err(1, "waitpid for child"); + } else { + unsigned long dr0, dr1, dr7; + + dr0 = (unsigned long)&ss; + dr1 = (unsigned long)breakpoint_insn; + dr7 = ((1UL << 1) | /* G0 */ + (3UL << 16) | /* RW0 = read or write */ + (1UL << 18) | /* LEN0 = 2 bytes */ + (1UL << 3)); /* G1, RW1 = insn */ + + if (ptrace(PTRACE_ATTACH, parent, NULL, NULL) != 0) + err(1, "PTRACE_ATTACH"); + + if (waitpid(parent, &status, 0) != parent) + err(1, "waitpid for child"); + + if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[0]), dr0) != 0) + err(1, "PTRACE_POKEUSER DR0"); + + if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[1]), dr1) != 0) + err(1, "PTRACE_POKEUSER DR1"); + + if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[7]), dr7) != 0) + err(1, "PTRACE_POKEUSER DR7"); + + printf("\tDR0 = %lx, DR1 = %lx, DR7 = %lx\n", dr0, dr1, dr7); + + if (ptrace(PTRACE_DETACH, parent, NULL, NULL) != 0) + err(1, "PTRACE_DETACH"); + + exit(0); + } +} + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static char const * const signames[] = { + [SIGSEGV] = "SIGSEGV", + [SIGBUS] = "SIBGUS", + [SIGTRAP] = "SIGTRAP", + [SIGILL] = "SIGILL", +}; + +static void sigtrap(int sig, siginfo_t *si, void *ctx_void) +{ + ucontext_t *ctx = ctx_void; + + printf("\tGot SIGTRAP with RIP=%lx, EFLAGS.RF=%d\n", + (unsigned long)ctx->uc_mcontext.gregs[REG_IP], + !!(ctx->uc_mcontext.gregs[REG_EFL] & X86_EFLAGS_RF)); +} + +static void handle_and_return(int sig, siginfo_t *si, void *ctx_void) +{ + ucontext_t *ctx = ctx_void; + + printf("\tGot %s with RIP=%lx\n", signames[sig], + (unsigned long)ctx->uc_mcontext.gregs[REG_IP]); +} + +static void handle_and_longjmp(int sig, siginfo_t *si, void *ctx_void) +{ + ucontext_t *ctx = ctx_void; + + printf("\tGot %s with RIP=%lx\n", signames[sig], + (unsigned long)ctx->uc_mcontext.gregs[REG_IP]); + + siglongjmp(jmpbuf, 1); +} + +int main() +{ + unsigned long nr; + + asm volatile ("mov %%ss, %[ss]" : [ss] "=m" (ss)); + printf("\tSS = 0x%hx, &SS = 0x%p\n", ss, &ss); + + if (prctl(PR_SET_PTRACER, PR_SET_PTRACER_ANY, 0, 0, 0) == 0) + printf("\tPR_SET_PTRACER_ANY succeeded\n"); + + printf("\tSet up a watchpoint\n"); + sethandler(SIGTRAP, sigtrap, 0); + enable_watchpoint(); + + printf("[RUN]\tRead from watched memory (should get SIGTRAP)\n"); + asm volatile ("mov %[ss], %[tmp]" : [tmp] "=r" (nr) : [ss] "m" (ss)); + + printf("[RUN]\tMOV SS; INT3\n"); + asm volatile ("mov %[ss], %%ss; int3" :: [ss] "m" (ss)); + + printf("[RUN]\tMOV SS; INT 3\n"); + asm volatile ("mov %[ss], %%ss; .byte 0xcd, 0x3" :: [ss] "m" (ss)); + + printf("[RUN]\tMOV SS; CS CS INT3\n"); + asm volatile ("mov %[ss], %%ss; .byte 0x2e, 0x2e; int3" :: [ss] "m" (ss)); + + printf("[RUN]\tMOV SS; CSx14 INT3\n"); + asm volatile ("mov %[ss], %%ss; .fill 14,1,0x2e; int3" :: [ss] "m" (ss)); + + printf("[RUN]\tMOV SS; INT 4\n"); + sethandler(SIGSEGV, handle_and_return, SA_RESETHAND); + asm volatile ("mov %[ss], %%ss; int $4" :: [ss] "m" (ss)); + +#ifdef __i386__ + printf("[RUN]\tMOV SS; INTO\n"); + sethandler(SIGSEGV, handle_and_return, SA_RESETHAND); + nr = -1; + asm volatile ("add $1, %[tmp]; mov %[ss], %%ss; into" + : [tmp] "+r" (nr) : [ss] "m" (ss)); +#endif + + if (sigsetjmp(jmpbuf, 1) == 0) { + printf("[RUN]\tMOV SS; ICEBP\n"); + + /* Some emulators (e.g. QEMU TCG) don't emulate ICEBP. */ + sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND); + + asm volatile ("mov %[ss], %%ss; .byte 0xf1" :: [ss] "m" (ss)); + } + + if (sigsetjmp(jmpbuf, 1) == 0) { + printf("[RUN]\tMOV SS; CLI\n"); + sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND); + asm volatile ("mov %[ss], %%ss; cli" :: [ss] "m" (ss)); + } + + if (sigsetjmp(jmpbuf, 1) == 0) { + printf("[RUN]\tMOV SS; #PF\n"); + sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND); + asm volatile ("mov %[ss], %%ss; mov (-1), %[tmp]" + : [tmp] "=r" (nr) : [ss] "m" (ss)); + } + + /* + * INT $1: if #DB has DPL=3 and there isn't special handling, + * then the kernel will die. + */ + if (sigsetjmp(jmpbuf, 1) == 0) { + printf("[RUN]\tMOV SS; INT 1\n"); + sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND); + asm volatile ("mov %[ss], %%ss; int $1" :: [ss] "m" (ss)); + } + +#ifdef __x86_64__ + /* + * In principle, we should test 32-bit SYSCALL as well, but + * the calling convention is so unpredictable that it's + * not obviously worth the effort. + */ + if (sigsetjmp(jmpbuf, 1) == 0) { + printf("[RUN]\tMOV SS; SYSCALL\n"); + sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND); + nr = SYS_getpid; + /* + * Toggle the high bit of RSP to make it noncanonical to + * strengthen this test on non-SMAP systems. + */ + asm volatile ("btc $63, %%rsp\n\t" + "mov %[ss], %%ss; syscall\n\t" + "btc $63, %%rsp" + : "+a" (nr) : [ss] "m" (ss) + : "rcx" +#ifdef __x86_64__ + , "r11" +#endif + ); + } +#endif + + printf("[RUN]\tMOV SS; breakpointed NOP\n"); + asm volatile ("mov %[ss], %%ss; breakpoint_insn: nop" :: [ss] "m" (ss)); + + /* + * Invoking SYSENTER directly breaks all the rules. Just handle + * the SIGSEGV. + */ + if (sigsetjmp(jmpbuf, 1) == 0) { + printf("[RUN]\tMOV SS; SYSENTER\n"); + stack_t stack = { + .ss_sp = altstack_data, + .ss_size = SIGSTKSZ, + }; + if (sigaltstack(&stack, NULL) != 0) + err(1, "sigaltstack"); + sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND | SA_ONSTACK); + nr = SYS_getpid; + asm volatile ("mov %[ss], %%ss; SYSENTER" : "+a" (nr) + : [ss] "m" (ss) : "flags", "rcx" +#ifdef __x86_64__ + , "r11" +#endif + ); + + /* We're unreachable here. SYSENTER forgets RIP. */ + } + + if (sigsetjmp(jmpbuf, 1) == 0) { + printf("[RUN]\tMOV SS; INT $0x80\n"); + sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND); + nr = 20; /* compat getpid */ + asm volatile ("mov %[ss], %%ss; int $0x80" + : "+a" (nr) : [ss] "m" (ss) + : "flags" +#ifdef __x86_64__ + , "r8", "r9", "r10", "r11" +#endif + ); + } + + printf("[OK]\tI aten't dead\n"); + return 0; +} diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c index 9c0325e1ea68..50f7e9272481 100644 --- a/tools/testing/selftests/x86/mpx-mini-test.c +++ b/tools/testing/selftests/x86/mpx-mini-test.c @@ -368,6 +368,11 @@ static int expected_bnd_index = -1; uint64_t shadow_plb[NR_MPX_BOUNDS_REGISTERS][2]; /* shadow MPX bound registers */ unsigned long shadow_map[NR_MPX_BOUNDS_REGISTERS]; +/* Failed address bound checks: */ +#ifndef SEGV_BNDERR +# define SEGV_BNDERR 3 +#endif + /* * The kernel is supposed to provide some information about the bounds * exception in the siginfo. It should match what we have in the bounds @@ -419,8 +424,6 @@ void handler(int signum, siginfo_t *si, void *vucontext) br_count++; dprintf1("#BR 0x%jx (total seen: %d)\n", status, br_count); -#define SEGV_BNDERR 3 /* failed address bound checks */ - dprintf2("Saw a #BR! status 0x%jx at %016lx br_reason: %jx\n", status, ip, br_reason); dprintf2("si_signo: %d\n", si->si_signo); diff --git a/tools/testing/selftests/x86/pkey-helpers.h b/tools/testing/selftests/x86/pkey-helpers.h index b3cb7670e026..254e5436bdd9 100644 --- a/tools/testing/selftests/x86/pkey-helpers.h +++ b/tools/testing/selftests/x86/pkey-helpers.h @@ -26,30 +26,26 @@ static inline void sigsafe_printf(const char *format, ...) { va_list ap; - va_start(ap, format); if (!dprint_in_signal) { + va_start(ap, format); vprintf(format, ap); + va_end(ap); } else { int ret; - int len = vsnprintf(dprint_in_signal_buffer, - DPRINT_IN_SIGNAL_BUF_SIZE, - format, ap); /* - * len is amount that would have been printed, - * but actual write is truncated at BUF_SIZE. + * No printf() functions are signal-safe. + * They deadlock easily. Write the format + * string to get some output, even if + * incomplete. */ - if (len > DPRINT_IN_SIGNAL_BUF_SIZE) - len = DPRINT_IN_SIGNAL_BUF_SIZE; - ret = write(1, dprint_in_signal_buffer, len); + ret = write(1, format, strlen(format)); if (ret < 0) - abort(); + exit(1); } - va_end(ap); } #define dprintf_level(level, args...) do { \ if (level <= DEBUG_LEVEL) \ sigsafe_printf(args); \ - fflush(NULL); \ } while (0) #define dprintf0(args...) dprintf_level(0, args) #define dprintf1(args...) dprintf_level(1, args) diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index f15aa5a76fe3..460b4bdf4c1e 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -72,10 +72,9 @@ extern void abort_hooks(void); test_nr, iteration_nr); \ dprintf0("errno at assert: %d", errno); \ abort_hooks(); \ - assert(condition); \ + exit(__LINE__); \ } \ } while (0) -#define raw_assert(cond) assert(cond) void cat_into_file(char *str, char *file) { @@ -87,12 +86,17 @@ void cat_into_file(char *str, char *file) * these need to be raw because they are called under * pkey_assert() */ - raw_assert(fd >= 0); + if (fd < 0) { + fprintf(stderr, "error opening '%s'\n", str); + perror("error: "); + exit(__LINE__); + } + ret = write(fd, str, strlen(str)); if (ret != strlen(str)) { perror("write to file failed"); fprintf(stderr, "filename: '%s' str: '%s'\n", file, str); - raw_assert(0); + exit(__LINE__); } close(fd); } @@ -191,26 +195,30 @@ void lots_o_noops_around_write(int *write_to_me) #ifdef __i386__ #ifndef SYS_mprotect_key -# define SYS_mprotect_key 380 +# define SYS_mprotect_key 380 #endif + #ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 381 -# define SYS_pkey_free 382 +# define SYS_pkey_alloc 381 +# define SYS_pkey_free 382 #endif -#define REG_IP_IDX REG_EIP -#define si_pkey_offset 0x14 + +#define REG_IP_IDX REG_EIP +#define si_pkey_offset 0x14 #else #ifndef SYS_mprotect_key -# define SYS_mprotect_key 329 +# define SYS_mprotect_key 329 #endif + #ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 330 -# define SYS_pkey_free 331 +# define SYS_pkey_alloc 330 +# define SYS_pkey_free 331 #endif -#define REG_IP_IDX REG_RIP -#define si_pkey_offset 0x20 + +#define REG_IP_IDX REG_RIP +#define si_pkey_offset 0x20 #endif @@ -225,8 +233,14 @@ void dump_mem(void *dumpme, int len_bytes) } } -#define SEGV_BNDERR 3 /* failed address bound checks */ -#define SEGV_PKUERR 4 +/* Failed address bound checks: */ +#ifndef SEGV_BNDERR +# define SEGV_BNDERR 3 +#endif + +#ifndef SEGV_PKUERR +# define SEGV_PKUERR 4 +#endif static char *si_code_str(int si_code) { @@ -289,13 +303,6 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) dump_mem(pkru_ptr - 128, 256); pkey_assert(*pkru_ptr); - si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset); - dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr); - dump_mem(si_pkey_ptr - 8, 24); - siginfo_pkey = *si_pkey_ptr; - pkey_assert(siginfo_pkey < NR_PKEYS); - last_si_pkey = siginfo_pkey; - if ((si->si_code == SEGV_MAPERR) || (si->si_code == SEGV_ACCERR) || (si->si_code == SEGV_BNDERR)) { @@ -303,6 +310,13 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) exit(4); } + si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset); + dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr); + dump_mem((u8 *)si_pkey_ptr - 8, 24); + siginfo_pkey = *si_pkey_ptr; + pkey_assert(siginfo_pkey < NR_PKEYS); + last_si_pkey = siginfo_pkey; + dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr); /* need __rdpkru() version so we do not do shadow_pkru checking */ dprintf1("signal pkru from pkru: %08x\n", __rdpkru()); @@ -311,22 +325,6 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n"); pkru_faults++; dprintf1("<<<<==================================================\n"); - return; - if (trapno == 14) { - fprintf(stderr, - "ERROR: In signal handler, page fault, trapno = %d, ip = %016lx\n", - trapno, ip); - fprintf(stderr, "si_addr %p\n", si->si_addr); - fprintf(stderr, "REG_ERR: %lx\n", - (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]); - exit(1); - } else { - fprintf(stderr, "unexpected trap %d! at 0x%lx\n", trapno, ip); - fprintf(stderr, "si_addr %p\n", si->si_addr); - fprintf(stderr, "REG_ERR: %lx\n", - (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]); - exit(2); - } dprint_in_signal = 0; } @@ -393,10 +391,15 @@ pid_t fork_lazy_child(void) return forkret; } -#define PKEY_DISABLE_ACCESS 0x1 -#define PKEY_DISABLE_WRITE 0x2 +#ifndef PKEY_DISABLE_ACCESS +# define PKEY_DISABLE_ACCESS 0x1 +#endif + +#ifndef PKEY_DISABLE_WRITE +# define PKEY_DISABLE_WRITE 0x2 +#endif -u32 pkey_get(int pkey, unsigned long flags) +static u32 hw_pkey_get(int pkey, unsigned long flags) { u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE); u32 pkru = __rdpkru(); @@ -418,7 +421,7 @@ u32 pkey_get(int pkey, unsigned long flags) return masked_pkru; } -int pkey_set(int pkey, unsigned long rights, unsigned long flags) +static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags) { u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE); u32 old_pkru = __rdpkru(); @@ -452,15 +455,15 @@ void pkey_disable_set(int pkey, int flags) pkey, flags); pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)); - pkey_rights = pkey_get(pkey, syscall_flags); + pkey_rights = hw_pkey_get(pkey, syscall_flags); - dprintf1("%s(%d) pkey_get(%d): %x\n", __func__, + dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__, pkey, pkey, pkey_rights); pkey_assert(pkey_rights >= 0); pkey_rights |= flags; - ret = pkey_set(pkey, pkey_rights, syscall_flags); + ret = hw_pkey_set(pkey, pkey_rights, syscall_flags); assert(!ret); /*pkru and flags have the same format */ shadow_pkru |= flags << (pkey * 2); @@ -468,8 +471,8 @@ void pkey_disable_set(int pkey, int flags) pkey_assert(ret >= 0); - pkey_rights = pkey_get(pkey, syscall_flags); - dprintf1("%s(%d) pkey_get(%d): %x\n", __func__, + pkey_rights = hw_pkey_get(pkey, syscall_flags); + dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__, pkey, pkey, pkey_rights); dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru()); @@ -483,24 +486,24 @@ void pkey_disable_clear(int pkey, int flags) { unsigned long syscall_flags = 0; int ret; - int pkey_rights = pkey_get(pkey, syscall_flags); + int pkey_rights = hw_pkey_get(pkey, syscall_flags); u32 orig_pkru = rdpkru(); pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)); - dprintf1("%s(%d) pkey_get(%d): %x\n", __func__, + dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__, pkey, pkey, pkey_rights); pkey_assert(pkey_rights >= 0); pkey_rights |= flags; - ret = pkey_set(pkey, pkey_rights, 0); + ret = hw_pkey_set(pkey, pkey_rights, 0); /* pkru and flags have the same format */ shadow_pkru &= ~(flags << (pkey * 2)); pkey_assert(ret >= 0); - pkey_rights = pkey_get(pkey, syscall_flags); - dprintf1("%s(%d) pkey_get(%d): %x\n", __func__, + pkey_rights = hw_pkey_get(pkey, syscall_flags); + dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__, pkey, pkey, pkey_rights); dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru()); @@ -674,10 +677,12 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, struct pkey_malloc_record { void *ptr; long size; + int prot; }; struct pkey_malloc_record *pkey_malloc_records; +struct pkey_malloc_record *pkey_last_malloc_record; long nr_pkey_malloc_records; -void record_pkey_malloc(void *ptr, long size) +void record_pkey_malloc(void *ptr, long size, int prot) { long i; struct pkey_malloc_record *rec = NULL; @@ -709,6 +714,8 @@ void record_pkey_malloc(void *ptr, long size) (int)(rec - pkey_malloc_records), rec, ptr, size); rec->ptr = ptr; rec->size = size; + rec->prot = prot; + pkey_last_malloc_record = rec; nr_pkey_malloc_records++; } @@ -753,7 +760,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) pkey_assert(ptr != (void *)-1); ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey); pkey_assert(!ret); - record_pkey_malloc(ptr, size); + record_pkey_malloc(ptr, size, prot); rdpkru(); dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr); @@ -774,7 +781,7 @@ void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) size = ALIGN_UP(size, HPAGE_SIZE * 2); ptr = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); pkey_assert(ptr != (void *)-1); - record_pkey_malloc(ptr, size); + record_pkey_malloc(ptr, size, prot); mprotect_pkey(ptr, size, prot, pkey); dprintf1("unaligned ptr: %p\n", ptr); @@ -847,7 +854,7 @@ void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) pkey_assert(ptr != (void *)-1); mprotect_pkey(ptr, size, prot, pkey); - record_pkey_malloc(ptr, size); + record_pkey_malloc(ptr, size, prot); dprintf1("mmap()'d hugetlbfs for pkey %d @ %p\n", pkey, ptr); return ptr; @@ -869,7 +876,7 @@ void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey) mprotect_pkey(ptr, size, prot, pkey); - record_pkey_malloc(ptr, size); + record_pkey_malloc(ptr, size, prot); dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr); close(fd); @@ -918,13 +925,21 @@ void *malloc_pkey(long size, int prot, u16 pkey) } int last_pkru_faults; +#define UNKNOWN_PKEY -2 void expected_pk_fault(int pkey) { dprintf2("%s(): last_pkru_faults: %d pkru_faults: %d\n", __func__, last_pkru_faults, pkru_faults); dprintf2("%s(%d): last_si_pkey: %d\n", __func__, pkey, last_si_pkey); pkey_assert(last_pkru_faults + 1 == pkru_faults); - pkey_assert(last_si_pkey == pkey); + + /* + * For exec-only memory, we do not know the pkey in + * advance, so skip this check. + */ + if (pkey != UNKNOWN_PKEY) + pkey_assert(last_si_pkey == pkey); + /* * The signal handler shold have cleared out PKRU to let the * test program continue. We now have to restore it. @@ -939,10 +954,11 @@ void expected_pk_fault(int pkey) last_si_pkey = -1; } -void do_not_expect_pk_fault(void) -{ - pkey_assert(last_pkru_faults == pkru_faults); -} +#define do_not_expect_pk_fault(msg) do { \ + if (last_pkru_faults != pkru_faults) \ + dprintf0("unexpected PK fault: %s\n", msg); \ + pkey_assert(last_pkru_faults == pkru_faults); \ +} while (0) int test_fds[10] = { -1 }; int nr_test_fds; @@ -1151,12 +1167,15 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) pkey_assert(i < NR_PKEYS*2); /* - * There are 16 pkeys supported in hardware. One is taken - * up for the default (0) and another can be taken up by - * an execute-only mapping. Ensure that we can allocate - * at least 14 (16-2). + * There are 16 pkeys supported in hardware. Three are + * allocated by the time we get here: + * 1. The default key (0) + * 2. One possibly consumed by an execute-only mapping. + * 3. One allocated by the test code and passed in via + * 'pkey' to this function. + * Ensure that we can allocate at least another 13 (16-3). */ - pkey_assert(i >= NR_PKEYS-2); + pkey_assert(i >= NR_PKEYS-3); for (i = 0; i < nr_allocated_pkeys; i++) { err = sys_pkey_free(allocated_pkeys[i]); @@ -1165,6 +1184,35 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) } } +/* + * pkey 0 is special. It is allocated by default, so you do not + * have to call pkey_alloc() to use it first. Make sure that it + * is usable. + */ +void test_mprotect_with_pkey_0(int *ptr, u16 pkey) +{ + long size; + int prot; + + assert(pkey_last_malloc_record); + size = pkey_last_malloc_record->size; + /* + * This is a bit of a hack. But mprotect() requires + * huge-page-aligned sizes when operating on hugetlbfs. + * So, make sure that we use something that's a multiple + * of a huge page when we can. + */ + if (size >= HPAGE_SIZE) + size = HPAGE_SIZE; + prot = pkey_last_malloc_record->prot; + + /* Use pkey 0 */ + mprotect_pkey(ptr, size, prot, 0); + + /* Make sure that we can set it back to the original pkey. */ + mprotect_pkey(ptr, size, prot, pkey); +} + void test_ptrace_of_child(int *ptr, u16 pkey) { __attribute__((__unused__)) int peek_result; @@ -1228,7 +1276,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey) pkey_assert(ret != -1); /* Now access from the current task, and expect NO exception: */ peek_result = read_ptr(plain_ptr); - do_not_expect_pk_fault(); + do_not_expect_pk_fault("read plain pointer after ptrace"); ret = ptrace(PTRACE_DETACH, child_pid, ignored, 0); pkey_assert(ret != -1); @@ -1241,12 +1289,9 @@ void test_ptrace_of_child(int *ptr, u16 pkey) free(plain_ptr_unaligned); } -void test_executing_on_unreadable_memory(int *ptr, u16 pkey) +void *get_pointer_to_instructions(void) { void *p1; - int scratch; - int ptr_contents; - int ret; p1 = ALIGN_PTR_UP(&lots_o_noops_around_write, PAGE_SIZE); dprintf3("&lots_o_noops: %p\n", &lots_o_noops_around_write); @@ -1256,7 +1301,23 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey) /* Point 'p1' at the *second* page of the function: */ p1 += PAGE_SIZE; + /* + * Try to ensure we fault this in on next touch to ensure + * we get an instruction fault as opposed to a data one + */ madvise(p1, PAGE_SIZE, MADV_DONTNEED); + + return p1; +} + +void test_executing_on_unreadable_memory(int *ptr, u16 pkey) +{ + void *p1; + int scratch; + int ptr_contents; + int ret; + + p1 = get_pointer_to_instructions(); lots_o_noops_around_write(&scratch); ptr_contents = read_ptr(p1); dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); @@ -1272,12 +1333,55 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey) */ madvise(p1, PAGE_SIZE, MADV_DONTNEED); lots_o_noops_around_write(&scratch); - do_not_expect_pk_fault(); + do_not_expect_pk_fault("executing on PROT_EXEC memory"); ptr_contents = read_ptr(p1); dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); expected_pk_fault(pkey); } +void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) +{ + void *p1; + int scratch; + int ptr_contents; + int ret; + + dprintf1("%s() start\n", __func__); + + p1 = get_pointer_to_instructions(); + lots_o_noops_around_write(&scratch); + ptr_contents = read_ptr(p1); + dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); + + /* Use a *normal* mprotect(), not mprotect_pkey(): */ + ret = mprotect(p1, PAGE_SIZE, PROT_EXEC); + pkey_assert(!ret); + + dprintf2("pkru: %x\n", rdpkru()); + + /* Make sure this is an *instruction* fault */ + madvise(p1, PAGE_SIZE, MADV_DONTNEED); + lots_o_noops_around_write(&scratch); + do_not_expect_pk_fault("executing on PROT_EXEC memory"); + ptr_contents = read_ptr(p1); + dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); + expected_pk_fault(UNKNOWN_PKEY); + + /* + * Put the memory back to non-PROT_EXEC. Should clear the + * exec-only pkey off the VMA and allow it to be readable + * again. Go to PROT_NONE first to check for a kernel bug + * that did not clear the pkey when doing PROT_NONE. + */ + ret = mprotect(p1, PAGE_SIZE, PROT_NONE); + pkey_assert(!ret); + + ret = mprotect(p1, PAGE_SIZE, PROT_READ|PROT_EXEC); + pkey_assert(!ret); + ptr_contents = read_ptr(p1); + do_not_expect_pk_fault("plain read on recently PROT_EXEC area"); +} + void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) { int size = PAGE_SIZE; @@ -1302,6 +1406,8 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = { test_kernel_gup_of_access_disabled_region, test_kernel_gup_write_to_write_disabled_region, test_executing_on_unreadable_memory, + test_implicit_mprotect_exec_only_memory, + test_mprotect_with_pkey_0, test_ptrace_of_child, test_pkey_syscalls_on_non_allocated_pkey, test_pkey_syscalls_bad_args, diff --git a/tools/testing/selftests/x86/test_syscall_vdso.c b/tools/testing/selftests/x86/test_syscall_vdso.c index 40370354d4c1..c9c3281077bc 100644 --- a/tools/testing/selftests/x86/test_syscall_vdso.c +++ b/tools/testing/selftests/x86/test_syscall_vdso.c @@ -100,12 +100,19 @@ asm ( " shl $32, %r8\n" " orq $0x7f7f7f7f, %r8\n" " movq %r8, %r9\n" - " movq %r8, %r10\n" - " movq %r8, %r11\n" - " movq %r8, %r12\n" - " movq %r8, %r13\n" - " movq %r8, %r14\n" - " movq %r8, %r15\n" + " incq %r9\n" + " movq %r9, %r10\n" + " incq %r10\n" + " movq %r10, %r11\n" + " incq %r11\n" + " movq %r11, %r12\n" + " incq %r12\n" + " movq %r12, %r13\n" + " incq %r13\n" + " movq %r13, %r14\n" + " incq %r14\n" + " movq %r14, %r15\n" + " incq %r15\n" " ret\n" " .code32\n" " .popsection\n" @@ -128,12 +135,13 @@ int check_regs64(void) int err = 0; int num = 8; uint64_t *r64 = ®s64.r8; + uint64_t expected = 0x7f7f7f7f7f7f7f7fULL; if (!kernel_is_64bit) return 0; do { - if (*r64 == 0x7f7f7f7f7f7f7f7fULL) + if (*r64 == expected++) continue; /* register did not change */ if (syscall_addr != (long)&int80) { /* @@ -147,18 +155,17 @@ int check_regs64(void) continue; } } else { - /* INT80 syscall entrypoint can be used by + /* + * INT80 syscall entrypoint can be used by * 64-bit programs too, unlike SYSCALL/SYSENTER. * Therefore it must preserve R12+ * (they are callee-saved registers in 64-bit C ABI). * - * This was probably historically not intended, - * but R8..11 are clobbered (cleared to 0). - * IOW: they are the only registers which aren't - * preserved across INT80 syscall. + * Starting in Linux 4.17 (and any kernel that + * backports the change), R8..11 are preserved. + * Historically (and probably unintentionally), they + * were clobbered or zeroed. */ - if (*r64 == 0 && num <= 11) - continue; } printf("[FAIL]\tR%d has changed:%016llx\n", num, *r64); err++; |
