diff options
Diffstat (limited to 'tools')
95 files changed, 5052 insertions, 516 deletions
diff --git a/tools/Makefile b/tools/Makefile index 3dfd72ae6c1a..68defd7ecf5d 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -19,6 +19,7 @@ help: @echo ' gpio - GPIO tools' @echo ' hv - tools used when in Hyper-V clients' @echo ' iio - IIO tools' + @echo ' intel-speed-select - Intel Speed Select tool' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' @echo ' liblockdep - user-space wrapper for kernel locking-validator' @@ -82,7 +83,7 @@ perf: FORCE selftests: FORCE $(call descend,testing/$@) -turbostat x86_energy_perf_policy: FORCE +turbostat x86_energy_perf_policy intel-speed-select: FORCE $(call descend,power/x86/$@) tmon: FORCE @@ -115,7 +116,7 @@ liblockdep_install: selftests_install: $(call descend,testing/$(@:_install=),install) -turbostat_install x86_energy_perf_policy_install: +turbostat_install x86_energy_perf_policy_install intel-speed-select_install: $(call descend,power/x86/$(@:_install=),install) tmon_install: @@ -132,7 +133,7 @@ install: acpi_install cgroup_install cpupower_install gpio_install \ perf_install selftests_install turbostat_install usb_install \ virtio_install vm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install \ - wmi_install pci_install debugging_install + wmi_install pci_install debugging_install intel-speed-select_install acpi_clean: $(call descend,power/acpi,clean) @@ -162,7 +163,7 @@ perf_clean: selftests_clean: $(call descend,testing/$(@:_clean=),clean) -turbostat_clean x86_energy_perf_policy_clean: +turbostat_clean x86_energy_perf_policy_clean intel-speed-select_clean: $(call descend,power/x86/$(@:_clean=),clean) tmon_clean: @@ -178,6 +179,7 @@ clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \ perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \ vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \ - gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean + gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \ + intel-speed-select_clean .PHONY: FORCE diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 3ef0d9051e10..7031a4bf87a0 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -74,6 +74,7 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", }; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f506c68b2612..4e455018da65 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -806,7 +806,7 @@ union bpf_attr { * based on a user-provided identifier for all traffic coming from * the tasks belonging to the related cgroup. See also the related * kernel documentation, available from the Linux sources in file - * *Documentation/cgroup-v1/net_cls.rst*. + * *Documentation/admin-guide/cgroup-v1/net_cls.rst*. * * The Linux kernel has two versions for cgroups: there are * cgroups v1 and cgroups v2. Both are available to users, who can @@ -3245,7 +3245,7 @@ struct bpf_sock_addr { __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 user_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __u32 user_port; /* Allows 4-byte read and write. @@ -3257,7 +3257,7 @@ struct bpf_sock_addr { __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __bpf_md_ptr(struct bpf_sock *, sk); diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 2fe12b40d503..c2152f3dd02d 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -696,9 +696,11 @@ struct kvm_ioeventfd { #define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) +#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) #define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \ KVM_X86_DISABLE_EXITS_HLT | \ - KVM_X86_DISABLE_EXITS_PAUSE) + KVM_X86_DISABLE_EXITS_PAUSE | \ + KVM_X86_DISABLE_EXITS_CSTATE) /* for KVM_ENABLE_CAP */ struct kvm_enable_cap { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ed07789b3e62..794dd5064ae8 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4126,8 +4126,8 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, } attr.size = sizeof(attr); attr.type = type; - attr.config1 = (uint64_t)(void *)name; /* kprobe_func or uprobe_path */ - attr.config2 = offset; /* kprobe_addr or probe_offset */ + attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */ + attr.config2 = offset; /* kprobe_addr or probe_offset */ /* pid filter is meaningful only for uprobes */ pfd = syscall(__NR_perf_event_open, &attr, diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index b33740221b7e..5007b5d4fd2c 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -517,7 +517,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, err = -errno; goto out_socket; } - strncpy(xsk->ifname, ifname, IFNAMSIZ); + strncpy(xsk->ifname, ifname, IFNAMSIZ - 1); + xsk->ifname[IFNAMSIZ - 1] = '\0'; err = xsk_set_xdp_socket_config(&xsk->config, usr_config); if (err) diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index 580e344db3dd..ced3765c4f44 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -11,22 +11,24 @@ #include "elf.h" #include "cfi.h" -#define INSN_JUMP_CONDITIONAL 1 -#define INSN_JUMP_UNCONDITIONAL 2 -#define INSN_JUMP_DYNAMIC 3 -#define INSN_CALL 4 -#define INSN_CALL_DYNAMIC 5 -#define INSN_RETURN 6 -#define INSN_CONTEXT_SWITCH 7 -#define INSN_STACK 8 -#define INSN_BUG 9 -#define INSN_NOP 10 -#define INSN_STAC 11 -#define INSN_CLAC 12 -#define INSN_STD 13 -#define INSN_CLD 14 -#define INSN_OTHER 15 -#define INSN_LAST INSN_OTHER +enum insn_type { + INSN_JUMP_CONDITIONAL, + INSN_JUMP_UNCONDITIONAL, + INSN_JUMP_DYNAMIC, + INSN_JUMP_DYNAMIC_CONDITIONAL, + INSN_CALL, + INSN_CALL_DYNAMIC, + INSN_RETURN, + INSN_CONTEXT_SWITCH, + INSN_STACK, + INSN_BUG, + INSN_NOP, + INSN_STAC, + INSN_CLAC, + INSN_STD, + INSN_CLD, + INSN_OTHER, +}; enum op_dest_type { OP_DEST_REG, @@ -68,7 +70,7 @@ void arch_initial_func_cfi_state(struct cfi_state *state); int arch_decode_instruction(struct elf *elf, struct section *sec, unsigned long offset, unsigned int maxlen, - unsigned int *len, unsigned char *type, + unsigned int *len, enum insn_type *type, unsigned long *immediate, struct stack_op *op); bool arch_callee_saved_reg(unsigned char reg); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 584568f27a83..0567c47a91b1 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -68,7 +68,7 @@ bool arch_callee_saved_reg(unsigned char reg) int arch_decode_instruction(struct elf *elf, struct section *sec, unsigned long offset, unsigned int maxlen, - unsigned int *len, unsigned char *type, + unsigned int *len, enum insn_type *type, unsigned long *immediate, struct stack_op *op) { struct insn insn; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 172f99195726..5f26620f13f5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -18,6 +18,8 @@ #define FAKE_JUMP_OFFSET -1 +#define C_JUMP_TABLE_SECTION ".rodata..c_jump_table" + struct alternative { struct list_head list; struct instruction *insn; @@ -95,6 +97,20 @@ static struct instruction *next_insn_same_func(struct objtool_file *file, for (insn = next_insn_same_sec(file, insn); insn; \ insn = next_insn_same_sec(file, insn)) +static bool is_sibling_call(struct instruction *insn) +{ + /* An indirect jump is either a sibling call or a jump to a table. */ + if (insn->type == INSN_JUMP_DYNAMIC) + return list_empty(&insn->alts); + + if (insn->type != INSN_JUMP_CONDITIONAL && + insn->type != INSN_JUMP_UNCONDITIONAL) + return false; + + /* add_jump_destinations() sets insn->call_dest for sibling calls. */ + return !!insn->call_dest; +} + /* * This checks to see if the given function is a "noreturn" function. * @@ -103,14 +119,9 @@ static struct instruction *next_insn_same_func(struct objtool_file *file, * * For local functions, we have to detect them manually by simply looking for * the lack of a return instruction. - * - * Returns: - * -1: error - * 0: no dead end - * 1: dead end */ -static int __dead_end_function(struct objtool_file *file, struct symbol *func, - int recursion) +static bool __dead_end_function(struct objtool_file *file, struct symbol *func, + int recursion) { int i; struct instruction *insn; @@ -136,30 +147,33 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func, "rewind_stack_do_exit", }; + if (!func) + return false; + if (func->bind == STB_WEAK) - return 0; + return false; if (func->bind == STB_GLOBAL) for (i = 0; i < ARRAY_SIZE(global_noreturns); i++) if (!strcmp(func->name, global_noreturns[i])) - return 1; + return true; if (!func->len) - return 0; + return false; insn = find_insn(file, func->sec, func->offset); if (!insn->func) - return 0; + return false; func_for_each_insn_all(file, func, insn) { empty = false; if (insn->type == INSN_RETURN) - return 0; + return false; } if (empty) - return 0; + return false; /* * A function can have a sibling call instead of a return. In that @@ -167,40 +181,31 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func, * of the sibling call returns. */ func_for_each_insn_all(file, func, insn) { - if (insn->type == INSN_JUMP_UNCONDITIONAL) { + if (is_sibling_call(insn)) { struct instruction *dest = insn->jump_dest; if (!dest) /* sibling call to another file */ - return 0; - - if (dest->func && dest->func->pfunc != insn->func->pfunc) { + return false; - /* local sibling call */ - if (recursion == 5) { - /* - * 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, - recursion + 1); + /* local sibling call */ + if (recursion == 5) { + /* + * Infinite recursion: two functions have + * sibling calls to each other. This is a very + * rare case. It means they aren't dead ends. + */ + return false; } - } - if (insn->type == INSN_JUMP_DYNAMIC && list_empty(&insn->alts)) - /* sibling call */ - return 0; + return __dead_end_function(file, dest->func, recursion+1); + } } - return 1; + return true; } -static int dead_end_function(struct objtool_file *file, struct symbol *func) +static bool dead_end_function(struct objtool_file *file, struct symbol *func) { return __dead_end_function(file, func, 0); } @@ -262,19 +267,12 @@ static int decode_instructions(struct objtool_file *file) if (ret) goto err; - if (!insn->type || insn->type > INSN_LAST) { - WARN_FUNC("invalid instruction type %d", - insn->sec, insn->offset, insn->type); - ret = -1; - goto err; - } - hash_add(file->insn_hash, &insn->hash, insn->offset); list_add_tail(&insn->list, &file->insn_list); } list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) + if (func->type != STT_FUNC || func->alias != func) continue; if (!find_insn(file, sec, func->offset)) { @@ -284,8 +282,7 @@ static int decode_instructions(struct objtool_file *file) } func_for_each_insn(file, func, insn) - if (!insn->func) - insn->func = func; + insn->func = func; } } @@ -488,6 +485,7 @@ static const char *uaccess_safe_builtin[] = { /* misc */ "csum_partial_copy_generic", "__memcpy_mcsafe", + "mcsafe_handle_tail", "ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */ NULL }; @@ -505,7 +503,7 @@ static void add_uaccess_safe(struct objtool_file *file) if (!func) continue; - func->alias->uaccess_safe = true; + func->uaccess_safe = true; } } @@ -577,13 +575,16 @@ static int add_jump_destinations(struct objtool_file *file) * Retpoline jumps are really dynamic jumps in * disguise, so convert them accordingly. */ - insn->type = INSN_JUMP_DYNAMIC; + if (insn->type == INSN_JUMP_UNCONDITIONAL) + insn->type = INSN_JUMP_DYNAMIC; + else + insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; + insn->retpoline_safe = true; continue; } else { - /* sibling call */ + /* external sibling call */ insn->call_dest = rela->sym; - insn->jump_dest = NULL; continue; } @@ -623,7 +624,7 @@ static int add_jump_destinations(struct objtool_file *file) * However this code can't completely replace the * read_symbols() code because this doesn't detect the * case where the parent function's only reference to a - * subfunction is through a switch table. + * subfunction is through a jump table. */ if (!strstr(insn->func->name, ".cold.") && strstr(insn->jump_dest->func->name, ".cold.")) { @@ -633,9 +634,8 @@ static int add_jump_destinations(struct objtool_file *file) } else if (insn->jump_dest->func->pfunc != insn->func->pfunc && insn->jump_dest->offset == insn->jump_dest->func->offset) { - /* sibling class */ + /* internal sibling call */ insn->call_dest = insn->jump_dest->func; - insn->jump_dest = NULL; } } } @@ -896,20 +896,26 @@ out: return ret; } -static int add_switch_table(struct objtool_file *file, struct instruction *insn, - struct rela *table, struct rela *next_table) +static int add_jump_table(struct objtool_file *file, struct instruction *insn, + struct rela *table) { struct rela *rela = table; - struct instruction *alt_insn; + struct instruction *dest_insn; struct alternative *alt; struct symbol *pfunc = insn->func->pfunc; unsigned int prev_offset = 0; - list_for_each_entry_from(rela, &table->rela_sec->rela_list, list) { - if (rela == next_table) + /* + * Each @rela is a switch table relocation which points to the target + * instruction. + */ + list_for_each_entry_from(rela, &table->sec->rela_list, list) { + + /* Check for the end of the table: */ + if (rela != table && rela->jump_table_start) break; - /* Make sure the switch table entries are consecutive: */ + /* Make sure the table entries are consecutive: */ if (prev_offset && rela->offset != prev_offset + 8) break; @@ -918,12 +924,12 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn, rela->addend == pfunc->offset) break; - alt_insn = find_insn(file, rela->sym->sec, rela->addend); - if (!alt_insn) + dest_insn = find_insn(file, rela->sym->sec, rela->addend); + if (!dest_insn) break; - /* Make sure the jmp dest is in the function or subfunction: */ - if (alt_insn->func->pfunc != pfunc) + /* Make sure the destination is in the same function: */ + if (!dest_insn->func || dest_insn->func->pfunc != pfunc) break; alt = malloc(sizeof(*alt)); @@ -932,7 +938,7 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn, return -1; } - alt->insn = alt_insn; + alt->insn = dest_insn; list_add_tail(&alt->list, &insn->alts); prev_offset = rela->offset; } @@ -947,7 +953,7 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn, } /* - * find_switch_table() - Given a dynamic jump, find the switch jump table in + * find_jump_table() - Given a dynamic jump, find the switch jump table in * .rodata associated with it. * * There are 3 basic patterns: @@ -989,13 +995,13 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn, * * NOTE: RETPOLINE made it harder still to decode dynamic jumps. */ -static struct rela *find_switch_table(struct objtool_file *file, +static struct rela *find_jump_table(struct objtool_file *file, struct symbol *func, struct instruction *insn) { - struct rela *text_rela, *rodata_rela; + struct rela *text_rela, *table_rela; struct instruction *orig_insn = insn; - struct section *rodata_sec; + struct section *table_sec; unsigned long table_offset; /* @@ -1028,42 +1034,52 @@ static struct rela *find_switch_table(struct objtool_file *file, continue; table_offset = text_rela->addend; - rodata_sec = text_rela->sym->sec; + table_sec = text_rela->sym->sec; 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. + * symbol. GCC jump tables are anonymous data. + * + * Also support C jump tables which are in the same format as + * switch jump tables. For objtool to recognize them, they + * need to be placed in the C_JUMP_TABLE_SECTION section. They + * have symbols associated with them. */ - if (find_symbol_containing(rodata_sec, table_offset)) + if (find_symbol_containing(table_sec, table_offset) && + strcmp(table_sec->name, C_JUMP_TABLE_SECTION)) continue; - rodata_rela = find_rela_by_dest(rodata_sec, 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; + /* Each table entry has a rela associated with it. */ + table_rela = find_rela_by_dest(table_sec, table_offset); + if (!table_rela) + continue; - return 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 table_rela; } return NULL; } - -static int add_func_switch_tables(struct objtool_file *file, - struct symbol *func) +/* + * First pass: Mark the head of each jump table so that in the next pass, + * we know when a given jump table ends and the next one starts. + */ +static void mark_func_jump_tables(struct objtool_file *file, + struct symbol *func) { - struct instruction *insn, *last = NULL, *prev_jump = NULL; - struct rela *rela, *prev_rela = NULL; - int ret; + struct instruction *insn, *last = NULL; + struct rela *rela; func_for_each_insn_all(file, func, insn) { if (!last) @@ -1071,7 +1087,7 @@ static int add_func_switch_tables(struct objtool_file *file, /* * Store back-pointers for unconditional forward jumps such - * that find_switch_table() can back-track using those and + * that find_jump_table() can back-track using those and * avoid some potentially confusing code. */ if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest && @@ -1086,27 +1102,25 @@ static int add_func_switch_tables(struct objtool_file *file, if (insn->type != INSN_JUMP_DYNAMIC) continue; - rela = find_switch_table(file, func, insn); - if (!rela) - continue; - - /* - * We found a switch table, but we don't know yet how big it - * is. Don't add it until we reach the end of the function or - * the beginning of another switch table in the same function. - */ - if (prev_jump) { - ret = add_switch_table(file, prev_jump, prev_rela, rela); - if (ret) - return ret; + rela = find_jump_table(file, func, insn); + if (rela) { + rela->jump_table_start = true; + insn->jump_table = rela; } - - prev_jump = insn; - prev_rela = rela; } +} + +static int add_func_jump_tables(struct objtool_file *file, + struct symbol *func) +{ + struct instruction *insn; + int ret; - if (prev_jump) { - ret = add_switch_table(file, prev_jump, prev_rela, NULL); + func_for_each_insn_all(file, func, insn) { + if (!insn->jump_table) + continue; + + ret = add_jump_table(file, insn, insn->jump_table); if (ret) return ret; } @@ -1119,7 +1133,7 @@ static int add_func_switch_tables(struct objtool_file *file, * section which contains a list of addresses within the function to jump to. * This finds these jump tables and adds them to the insn->alts lists. */ -static int add_switch_table_alts(struct objtool_file *file) +static int add_jump_table_alts(struct objtool_file *file) { struct section *sec; struct symbol *func; @@ -1133,7 +1147,8 @@ static int add_switch_table_alts(struct objtool_file *file) if (func->type != STT_FUNC) continue; - ret = add_func_switch_tables(file, func); + mark_func_jump_tables(file, func); + ret = add_func_jump_tables(file, func); if (ret) return ret; } @@ -1277,13 +1292,18 @@ static void mark_rodata(struct objtool_file *file) bool found = false; /* - * This searches for the .rodata section or multiple .rodata.func_name - * sections if -fdata-sections is being used. The .str.1.1 and .str.1.8 - * rodata sections are ignored as they don't contain jump tables. + * Search for the following rodata sections, each of which can + * potentially contain jump tables: + * + * - .rodata: can contain GCC switch tables + * - .rodata.<func>: same, if -fdata-sections is being used + * - .rodata..c_jump_table: contains C annotated jump tables + * + * .rodata.str1.* sections are ignored; they don't contain jump tables. */ for_each_sec(file, sec) { - if (!strncmp(sec->name, ".rodata", 7) && - !strstr(sec->name, ".str1.")) { + if ((!strncmp(sec->name, ".rodata", 7) && !strstr(sec->name, ".str1.")) || + !strcmp(sec->name, C_JUMP_TABLE_SECTION)) { sec->rodata = true; found = true; } @@ -1325,7 +1345,7 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - ret = add_switch_table_alts(file); + ret = add_jump_table_alts(file); if (ret) return ret; @@ -1873,12 +1893,12 @@ static bool insn_state_match(struct instruction *insn, struct insn_state *state) static inline bool func_uaccess_safe(struct symbol *func) { if (func) - return func->alias->uaccess_safe; + return func->uaccess_safe; return false; } -static inline const char *insn_dest_name(struct instruction *insn) +static inline const char *call_dest_name(struct instruction *insn) { if (insn->call_dest) return insn->call_dest->name; @@ -1890,13 +1910,13 @@ static int validate_call(struct instruction *insn, struct insn_state *state) { if (state->uaccess && !func_uaccess_safe(insn->call_dest)) { WARN_FUNC("call to %s() with UACCESS enabled", - insn->sec, insn->offset, insn_dest_name(insn)); + insn->sec, insn->offset, call_dest_name(insn)); return 1; } if (state->df) { WARN_FUNC("call to %s() with DF set", - insn->sec, insn->offset, insn_dest_name(insn)); + insn->sec, insn->offset, call_dest_name(insn)); return 1; } @@ -1920,13 +1940,12 @@ static int validate_sibling_call(struct instruction *insn, struct insn_state *st * each instruction and validate all the rules described in * tools/objtool/Documentation/stack-validation.txt. */ -static int validate_branch(struct objtool_file *file, struct instruction *first, - struct insn_state state) +static int validate_branch(struct objtool_file *file, struct symbol *func, + struct instruction *first, struct insn_state state) { struct alternative *alt; struct instruction *insn, *next_insn; struct section *sec; - struct symbol *func = NULL; int ret; insn = first; @@ -1947,9 +1966,6 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, return 1; } - if (insn->func) - func = insn->func->pfunc; - if (func && insn->ignore) { WARN_FUNC("BUG: why am I validating an ignored function?", sec, insn->offset); @@ -1971,7 +1987,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, i = insn; save_insn = NULL; - func_for_each_insn_continue_reverse(file, insn->func, i) { + func_for_each_insn_continue_reverse(file, func, i) { if (i->save) { save_insn = i; break; @@ -2017,7 +2033,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, if (alt->skip_orig) skip_orig = true; - ret = validate_branch(file, alt->insn, state); + ret = validate_branch(file, func, alt->insn, state); if (ret) { if (backtrace) BT_FUNC("(alt)", insn); @@ -2055,7 +2071,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, if (state.bp_scratch) { WARN("%s uses BP as a scratch register", - insn->func->name); + func->name); return 1; } @@ -2067,36 +2083,28 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, if (ret) return ret; - if (insn->type == INSN_CALL) { - if (is_fentry_call(insn)) - break; - - ret = dead_end_function(file, insn->call_dest); - if (ret == 1) - return 0; - if (ret == -1) - return 1; - } - - if (!no_fp && func && !has_valid_stack_frame(&state)) { + if (!no_fp && func && !is_fentry_call(insn) && + !has_valid_stack_frame(&state)) { WARN_FUNC("call without frame pointer save/setup", sec, insn->offset); return 1; } + + if (dead_end_function(file, insn->call_dest)) + return 0; + break; case INSN_JUMP_CONDITIONAL: case INSN_JUMP_UNCONDITIONAL: - if (func && !insn->jump_dest) { + if (func && is_sibling_call(insn)) { ret = validate_sibling_call(insn, &state); if (ret) return ret; - } else if (insn->jump_dest && - (!func || !insn->jump_dest->func || - insn->jump_dest->func->pfunc == func)) { - ret = validate_branch(file, insn->jump_dest, - state); + } else if (insn->jump_dest) { + ret = validate_branch(file, func, + insn->jump_dest, state); if (ret) { if (backtrace) BT_FUNC("(branch)", insn); @@ -2110,13 +2118,17 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, break; case INSN_JUMP_DYNAMIC: - if (func && list_empty(&insn->alts)) { + case INSN_JUMP_DYNAMIC_CONDITIONAL: + if (func && is_sibling_call(insn)) { ret = validate_sibling_call(insn, &state); if (ret) return ret; } - return 0; + if (insn->type == INSN_JUMP_DYNAMIC) + return 0; + + break; case INSN_CONTEXT_SWITCH: if (func && (!next_insn || !next_insn->hint)) { @@ -2162,7 +2174,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, break; case INSN_CLAC: - if (!state.uaccess && insn->func) { + if (!state.uaccess && func) { WARN_FUNC("redundant UACCESS disable", sec, insn->offset); return 1; } @@ -2183,7 +2195,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first, break; case INSN_CLD: - if (!state.df && insn->func) + if (!state.df && func) WARN_FUNC("redundant CLD", sec, insn->offset); state.df = false; @@ -2222,7 +2234,7 @@ static int validate_unwind_hints(struct objtool_file *file) for_each_insn(file, insn) { if (insn->hint && !insn->visited) { - ret = validate_branch(file, insn, state); + ret = validate_branch(file, insn->func, insn, state); if (ret && backtrace) BT_FUNC("<=== (hint)", insn); warnings += ret; @@ -2345,16 +2357,25 @@ 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 || func->pfunc != func) + if (func->type != STT_FUNC) + continue; + + if (!func->len) { + WARN("%s() is missing an ELF size annotation", + func->name); + warnings++; + } + + if (func->pfunc != func || func->alias != func) continue; insn = find_insn(file, sec, func->offset); - if (!insn || insn->ignore) + if (!insn || insn->ignore || insn->visited) continue; - state.uaccess = func->alias->uaccess_safe; + state.uaccess = func->uaccess_safe; - ret = validate_branch(file, insn, state); + ret = validate_branch(file, func, insn, state); if (ret && backtrace) BT_FUNC("<=== (func)", insn); warnings += ret; @@ -2407,7 +2428,7 @@ int check(const char *_objname, bool orc) objname = _objname; - file.elf = elf_open(objname, orc ? O_RDWR : O_RDONLY); + file.elf = elf_read(objname, orc ? O_RDWR : O_RDONLY); if (!file.elf) return 1; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index cb60b9acf5cf..b881fafcf55d 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -31,13 +31,14 @@ struct instruction { struct section *sec; unsigned long offset; unsigned int len; - unsigned char type; + enum insn_type type; unsigned long immediate; bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; bool retpoline_safe; struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; + struct rela *jump_table; struct list_head alts; struct symbol *func; struct stack_op stack_op; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index e99e1be19ad9..edba4745f25a 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -278,7 +278,7 @@ static int read_symbols(struct elf *elf) } if (sym->offset == s->offset) { - if (sym->len == s->len && alias == sym) + if (sym->len && sym->len == s->len && alias == sym) alias = s; if (sym->len >= s->len) { @@ -385,7 +385,7 @@ static int read_relas(struct elf *elf) rela->offset = rela->rela.r_offset; symndx = GELF_R_SYM(rela->rela.r_info); rela->sym = find_symbol_by_index(elf, symndx); - rela->rela_sec = sec; + rela->sec = sec; if (!rela->sym) { WARN("can't find rela entry symbol %d for %s", symndx, sec->name); @@ -401,7 +401,7 @@ static int read_relas(struct elf *elf) return 0; } -struct elf *elf_open(const char *name, int flags) +struct elf *elf_read(const char *name, int flags) { struct elf *elf; Elf_Cmd cmd; @@ -463,7 +463,7 @@ struct section *elf_create_section(struct elf *elf, const char *name, { struct section *sec, *shstrtab; size_t size = entsize * nr; - struct Elf_Scn *s; + Elf_Scn *s; Elf_Data *data; sec = malloc(sizeof(*sec)); diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index e44ca5d51871..44150204db4d 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -57,11 +57,12 @@ struct rela { struct list_head list; struct hlist_node hash; GElf_Rela rela; - struct section *rela_sec; + struct section *sec; struct symbol *sym; unsigned int type; unsigned long offset; int addend; + bool jump_table_start; }; struct elf { @@ -74,7 +75,7 @@ struct elf { }; -struct elf *elf_open(const char *name, int flags); +struct elf *elf_read(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); diff --git a/tools/pci/Makefile b/tools/pci/Makefile index 6876ee4bd78c..4b95a5176355 100644 --- a/tools/pci/Makefile +++ b/tools/pci/Makefile @@ -18,7 +18,6 @@ ALL_TARGETS := pcitest ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) SCRIPTS := pcitest.sh -ALL_SCRIPTS := $(patsubst %,$(OUTPUT)%,$(SCRIPTS)) all: $(ALL_PROGRAMS) @@ -47,10 +46,10 @@ clean: install: $(ALL_PROGRAMS) install -d -m 755 $(DESTDIR)$(bindir); \ - for program in $(ALL_PROGRAMS) pcitest.sh; do \ + for program in $(ALL_PROGRAMS); do \ install $$program $(DESTDIR)$(bindir); \ done; \ - for script in $(ALL_SCRIPTS); do \ + for script in $(SCRIPTS); do \ install $$script $(DESTDIR)$(bindir); \ done diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c index cb7a47dfd8b6..cb1e51fcc84e 100644 --- a/tools/pci/pcitest.c +++ b/tools/pci/pcitest.c @@ -36,15 +36,15 @@ struct pci_test { unsigned long size; }; -static void run_test(struct pci_test *test) +static int run_test(struct pci_test *test) { - long ret; + int ret = -EINVAL; int fd; fd = open(test->device, O_RDWR); if (fd < 0) { perror("can't open PCI Endpoint Test device"); - return; + return -ENODEV; } if (test->barnum >= 0 && test->barnum <= 5) { @@ -212,7 +212,7 @@ usage: "\t-r Read buffer test\n" "\t-w Write buffer test\n" "\t-c Copy buffer test\n" - "\t-s <size> Size of buffer {default: 100KB}\n", + "\t-s <size> Size of buffer {default: 100KB}\n" "\t-h Print this help message\n", argv[0]); return -EINVAL; diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index b6866a05edd2..ed3ecfa422e1 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -194,12 +194,13 @@ PROBE ARGUMENT -------------- Each probe argument follows below syntax. - [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE] + [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE][@user] 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) '$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters. 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo (*). Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal integers (x/x8/x16/x32/x64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail) On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid. +"@user" is a special attribute which means the LOCALVAR will be treated as a user-space memory. This is only valid for kprobe event. TYPES ----- diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 4acd3457d39d..8394d48f8b32 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1562,6 +1562,17 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg) str = tmp + 1; } + tmp = strchr(str, '@'); + if (tmp && tmp != str && strcmp(tmp + 1, "user")) { /* user attr */ + if (!user_access_is_supported()) { + semantic_error("ftrace does not support user access\n"); + return -EINVAL; + } + *tmp = '\0'; + arg->user_access = true; + pr_debug("user_access "); + } + tmp = strchr(str, ':'); if (tmp) { /* Type setting */ *tmp = '\0'; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 05c8d571a901..96a319cd2378 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -37,6 +37,7 @@ struct probe_trace_point { struct probe_trace_arg_ref { struct probe_trace_arg_ref *next; /* Next reference */ long offset; /* Offset value */ + bool user_access; /* User-memory access */ }; /* kprobe-tracer and uprobe-tracer tracing argument */ @@ -82,6 +83,7 @@ struct perf_probe_arg { char *var; /* Variable name */ char *type; /* Type name */ struct perf_probe_arg_field *field; /* Structure fields */ + bool user_access; /* User-memory access */ }; /* Perf probe probing event (point + arg) */ diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index c2998f90b23c..5b4d49382932 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -1005,6 +1005,7 @@ enum ftrace_readme { FTRACE_README_PROBE_TYPE_X = 0, FTRACE_README_KRETPROBE_OFFSET, FTRACE_README_UPROBE_REF_CTR, + FTRACE_README_USER_ACCESS, FTRACE_README_END, }; @@ -1017,6 +1018,7 @@ static struct { DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"), DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"), DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"), + DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"), }; static bool scan_ftrace_readme(enum ftrace_readme type) @@ -1077,3 +1079,8 @@ bool uprobe_ref_ctr_is_supported(void) { return scan_ftrace_readme(FTRACE_README_UPROBE_REF_CTR); } + +bool user_access_is_supported(void) +{ + return scan_ftrace_readme(FTRACE_README_USER_ACCESS); +} diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 2a249182f2a6..986c1c94f64f 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -70,6 +70,7 @@ int probe_cache__show_all_caches(struct strfilter *filter); bool probe_type_is_available(enum probe_type type); bool kretprobe_offset_is_supported(void); bool uprobe_ref_ctr_is_supported(void); +bool user_access_is_supported(void); #else /* ! HAVE_LIBELF_SUPPORT */ static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused) { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 7d8c99734928..025fc4491993 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -280,7 +280,7 @@ static_var: static int convert_variable_type(Dwarf_Die *vr_die, struct probe_trace_arg *tvar, - const char *cast) + const char *cast, bool user_access) { struct probe_trace_arg_ref **ref_ptr = &tvar->ref; Dwarf_Die type; @@ -320,7 +320,8 @@ static int convert_variable_type(Dwarf_Die *vr_die, pr_debug("%s type is %s.\n", dwarf_diename(vr_die), dwarf_diename(&type)); - if (cast && strcmp(cast, "string") == 0) { /* String type */ + if (cast && (!strcmp(cast, "string") || !strcmp(cast, "ustring"))) { + /* String type */ ret = dwarf_tag(&type); if (ret != DW_TAG_pointer_type && ret != DW_TAG_array_type) { @@ -343,6 +344,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, pr_warning("Out of memory error\n"); return -ENOMEM; } + (*ref_ptr)->user_access = user_access; } if (!die_compare_name(&type, "char") && !die_compare_name(&type, "unsigned char")) { @@ -397,7 +399,7 @@ formatted: static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, struct perf_probe_arg_field *field, struct probe_trace_arg_ref **ref_ptr, - Dwarf_Die *die_mem) + Dwarf_Die *die_mem, bool user_access) { struct probe_trace_arg_ref *ref = *ref_ptr; Dwarf_Die type; @@ -434,6 +436,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, *ref_ptr = ref; } ref->offset += dwarf_bytesize(&type) * field->index; + ref->user_access = user_access; goto next; } else if (tag == DW_TAG_pointer_type) { /* Check the pointer and dereference */ @@ -505,17 +508,18 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, } } ref->offset += (long)offs; + ref->user_access = user_access; /* If this member is unnamed, we need to reuse this field */ if (!dwarf_diename(die_mem)) return convert_variable_fields(die_mem, varname, field, - &ref, die_mem); + &ref, die_mem, user_access); next: /* Converting next field */ if (field->next) return convert_variable_fields(die_mem, field->name, - field->next, &ref, die_mem); + field->next, &ref, die_mem, user_access); else return 0; } @@ -541,11 +545,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf) else if (ret == 0 && pf->pvar->field) { ret = convert_variable_fields(vr_die, pf->pvar->var, pf->pvar->field, &pf->tvar->ref, - &die_mem); + &die_mem, pf->pvar->user_access); vr_die = &die_mem; } if (ret == 0) - ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type); + ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type, + pf->pvar->user_access); /* *expr will be cached in libdw. Don't free it. */ return ret; } diff --git a/tools/power/cpupower/debug/kernel/Makefile b/tools/power/cpupower/debug/kernel/Makefile index c23e5a6ceb7e..7b5c43684be1 100644 --- a/tools/power/cpupower/debug/kernel/Makefile +++ b/tools/power/cpupower/debug/kernel/Makefile @@ -12,8 +12,8 @@ default: $(MAKE) -C $(KDIR) M=$(CURDIR) clean: - - rm -rf *.o *.ko .tmp-versions .*.cmd .*.mod.* *.mod.c - - rm -rf .tmp_versions* Module.symvers modules.order + - rm -rf *.o *.ko .*.cmd .*.mod.* *.mod.c + - rm -rf Module.symvers modules.order install: default install -d $(KMISC) diff --git a/tools/power/x86/intel-speed-select/.gitignore b/tools/power/x86/intel-speed-select/.gitignore new file mode 100644 index 000000000000..f61145925ce9 --- /dev/null +++ b/tools/power/x86/intel-speed-select/.gitignore @@ -0,0 +1,2 @@ +include/ +intel-speed-select diff --git a/tools/power/x86/intel-speed-select/Build b/tools/power/x86/intel-speed-select/Build new file mode 100644 index 000000000000..b61456d75190 --- /dev/null +++ b/tools/power/x86/intel-speed-select/Build @@ -0,0 +1 @@ +intel-speed-select-y += isst-config.o isst-core.o isst-display.o diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile new file mode 100644 index 000000000000..12c6939dca2a --- /dev/null +++ b/tools/power/x86/intel-speed-select/Makefile @@ -0,0 +1,56 @@ +# SPDX-License-Identifier: GPL-2.0 +include ../../../scripts/Makefile.include + +bindir ?= /usr/bin + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif + +# Do not use make's built-in rules +# (this improves performance and avoids hard-to-debug behaviour); +MAKEFLAGS += -r + +override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include + +ALL_TARGETS := intel-speed-select +ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) + +all: $(ALL_PROGRAMS) + +export srctree OUTPUT CC LD CFLAGS +include $(srctree)/tools/build/Makefile.include + +# +# We need the following to be outside of kernel tree +# +$(OUTPUT)include/linux/isst_if.h: ../../../../include/uapi/linux/isst_if.h + mkdir -p $(OUTPUT)include/linux 2>&1 || true + ln -sf $(CURDIR)/../../../../include/uapi/linux/isst_if.h $@ + +prepare: $(OUTPUT)include/linux/isst_if.h + +ISST_IN := $(OUTPUT)intel-speed-select-in.o + +$(ISST_IN): prepare FORCE + $(Q)$(MAKE) $(build)=intel-speed-select +$(OUTPUT)intel-speed-select: $(ISST_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ + +clean: + rm -f $(ALL_PROGRAMS) + rm -rf $(OUTPUT)include/linux/isst_if.h + find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete + +install: $(ALL_PROGRAMS) + install -d -m 755 $(DESTDIR)$(bindir); \ + for program in $(ALL_PROGRAMS); do \ + install $$program $(DESTDIR)$(bindir); \ + done + +FORCE: + +.PHONY: all install clean FORCE prepare diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c new file mode 100644 index 000000000000..91c5ad1685a1 --- /dev/null +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -0,0 +1,1607 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Speed Select -- Enumerate and control features + * Copyright (c) 2019 Intel Corporation. + */ + +#include <linux/isst_if.h> + +#include "isst.h" + +struct process_cmd_struct { + char *feature; + char *command; + void (*process_fn)(void); +}; + +static const char *version_str = "v1.0"; +static const int supported_api_ver = 1; +static struct isst_if_platform_info isst_platform_info; +static char *progname; +static int debug_flag; +static FILE *outf; + +static int cpu_model; + +#define MAX_CPUS_IN_ONE_REQ 64 +static short max_target_cpus; +static unsigned short target_cpus[MAX_CPUS_IN_ONE_REQ]; + +static int topo_max_cpus; +static size_t present_cpumask_size; +static cpu_set_t *present_cpumask; +static size_t target_cpumask_size; +static cpu_set_t *target_cpumask; +static int tdp_level = 0xFF; +static int fact_bucket = 0xFF; +static int fact_avx = 0xFF; +static unsigned long long fact_trl; +static int out_format_json; +static int cmd_help; + +/* clos related */ +static int current_clos = -1; +static int clos_epp = -1; +static int clos_prop_prio = -1; +static int clos_min = -1; +static int clos_max = -1; +static int clos_desired = -1; +static int clos_priority_type; + +struct _cpu_map { + unsigned short core_id; + unsigned short pkg_id; + unsigned short die_id; + unsigned short punit_cpu; + unsigned short punit_cpu_core; +}; +struct _cpu_map *cpu_map; + +void debug_printf(const char *format, ...) +{ + va_list args; + + va_start(args, format); + + if (debug_flag) + vprintf(format, args); + + va_end(args); +} + +static void update_cpu_model(void) +{ + unsigned int ebx, ecx, edx; + unsigned int fms, family; + + __cpuid(1, fms, ebx, ecx, edx); + family = (fms >> 8) & 0xf; + cpu_model = (fms >> 4) & 0xf; + if (family == 6 || family == 0xf) + cpu_model += ((fms >> 16) & 0xf) << 4; +} + +/* Open a file, and exit on failure */ +static FILE *fopen_or_exit(const char *path, const char *mode) +{ + FILE *filep = fopen(path, mode); + + if (!filep) + err(1, "%s: open failed", path); + + return filep; +} + +/* Parse a file containing a single int */ +static int parse_int_file(int fatal, const char *fmt, ...) +{ + va_list args; + char path[PATH_MAX]; + FILE *filep; + int value; + + va_start(args, fmt); + vsnprintf(path, sizeof(path), fmt, args); + va_end(args); + if (fatal) { + filep = fopen_or_exit(path, "r"); + } else { + filep = fopen(path, "r"); + if (!filep) + return -1; + } + if (fscanf(filep, "%d", &value) != 1) + err(1, "%s: failed to parse number from file", path); + fclose(filep); + + return value; +} + +int cpufreq_sysfs_present(void) +{ + DIR *dir; + + dir = opendir("/sys/devices/system/cpu/cpu0/cpufreq"); + if (dir) { + closedir(dir); + return 1; + } + + return 0; +} + +int out_format_is_json(void) +{ + return out_format_json; +} + +int get_physical_package_id(int cpu) +{ + return parse_int_file( + 1, "/sys/devices/system/cpu/cpu%d/topology/physical_package_id", + cpu); +} + +int get_physical_core_id(int cpu) +{ + return parse_int_file( + 1, "/sys/devices/system/cpu/cpu%d/topology/core_id", cpu); +} + +int get_physical_die_id(int cpu) +{ + int ret; + + ret = parse_int_file(0, "/sys/devices/system/cpu/cpu%d/topology/die_id", + cpu); + if (ret < 0) + ret = 0; + + return ret; +} + +int get_topo_max_cpus(void) +{ + return topo_max_cpus; +} + +#define MAX_PACKAGE_COUNT 8 +#define MAX_DIE_PER_PACKAGE 2 +static void for_each_online_package_in_set(void (*callback)(int, void *, void *, + void *, void *), + void *arg1, void *arg2, void *arg3, + void *arg4) +{ + int max_packages[MAX_PACKAGE_COUNT * MAX_PACKAGE_COUNT]; + int pkg_index = 0, i; + + memset(max_packages, 0xff, sizeof(max_packages)); + for (i = 0; i < topo_max_cpus; ++i) { + int j, online, pkg_id, die_id = 0, skip = 0; + + if (!CPU_ISSET_S(i, present_cpumask_size, present_cpumask)) + continue; + if (i) + online = parse_int_file( + 1, "/sys/devices/system/cpu/cpu%d/online", i); + else + online = + 1; /* online entry for CPU 0 needs some special configs */ + + die_id = get_physical_die_id(i); + if (die_id < 0) + die_id = 0; + pkg_id = get_physical_package_id(i); + /* Create an unique id for package, die combination to store */ + pkg_id = (MAX_PACKAGE_COUNT * pkg_id + die_id); + + for (j = 0; j < pkg_index; ++j) { + if (max_packages[j] == pkg_id) { + skip = 1; + break; + } + } + + if (!skip && online && callback) { + callback(i, arg1, arg2, arg3, arg4); + max_packages[pkg_index++] = pkg_id; + } + } +} + +static void for_each_online_target_cpu_in_set( + void (*callback)(int, void *, void *, void *, void *), void *arg1, + void *arg2, void *arg3, void *arg4) +{ + int i; + + for (i = 0; i < topo_max_cpus; ++i) { + int online; + + if (!CPU_ISSET_S(i, target_cpumask_size, target_cpumask)) + continue; + if (i) + online = parse_int_file( + 1, "/sys/devices/system/cpu/cpu%d/online", i); + else + online = + 1; /* online entry for CPU 0 needs some special configs */ + + if (online && callback) + callback(i, arg1, arg2, arg3, arg4); + } +} + +#define BITMASK_SIZE 32 +static void set_max_cpu_num(void) +{ + FILE *filep; + unsigned long dummy; + + topo_max_cpus = 0; + filep = fopen_or_exit( + "/sys/devices/system/cpu/cpu0/topology/thread_siblings", "r"); + while (fscanf(filep, "%lx,", &dummy) == 1) + topo_max_cpus += BITMASK_SIZE; + fclose(filep); + topo_max_cpus--; /* 0 based */ + + debug_printf("max cpus %d\n", topo_max_cpus); +} + +size_t alloc_cpu_set(cpu_set_t **cpu_set) +{ + cpu_set_t *_cpu_set; + size_t size; + + _cpu_set = CPU_ALLOC((topo_max_cpus + 1)); + if (_cpu_set == NULL) + err(3, "CPU_ALLOC"); + size = CPU_ALLOC_SIZE((topo_max_cpus + 1)); + CPU_ZERO_S(size, _cpu_set); + + *cpu_set = _cpu_set; + return size; +} + +void free_cpu_set(cpu_set_t *cpu_set) +{ + CPU_FREE(cpu_set); +} + +static int cpu_cnt[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE]; +static void set_cpu_present_cpu_mask(void) +{ + size_t size; + DIR *dir; + int i; + + size = alloc_cpu_set(&present_cpumask); + present_cpumask_size = size; + for (i = 0; i < topo_max_cpus; ++i) { + char buffer[256]; + + snprintf(buffer, sizeof(buffer), + "/sys/devices/system/cpu/cpu%d", i); + dir = opendir(buffer); + if (dir) { + int pkg_id, die_id; + + CPU_SET_S(i, size, present_cpumask); + die_id = get_physical_die_id(i); + if (die_id < 0) + die_id = 0; + + pkg_id = get_physical_package_id(i); + if (pkg_id < MAX_PACKAGE_COUNT && + die_id < MAX_DIE_PER_PACKAGE) + cpu_cnt[pkg_id][die_id]++; + } + closedir(dir); + } +} + +int get_cpu_count(int pkg_id, int die_id) +{ + if (pkg_id < MAX_PACKAGE_COUNT && die_id < MAX_DIE_PER_PACKAGE) + return cpu_cnt[pkg_id][die_id] + 1; + + return 0; +} + +static void set_cpu_target_cpu_mask(void) +{ + size_t size; + int i; + + size = alloc_cpu_set(&target_cpumask); + target_cpumask_size = size; + for (i = 0; i < max_target_cpus; ++i) { + if (!CPU_ISSET_S(target_cpus[i], present_cpumask_size, + present_cpumask)) + continue; + + CPU_SET_S(target_cpus[i], size, target_cpumask); + } +} + +static void create_cpu_map(void) +{ + const char *pathname = "/dev/isst_interface"; + int i, fd = 0; + struct isst_if_cpu_maps map; + + cpu_map = malloc(sizeof(*cpu_map) * topo_max_cpus); + if (!cpu_map) + err(3, "cpumap"); + + fd = open(pathname, O_RDWR); + if (fd < 0) + err(-1, "%s open failed", pathname); + + for (i = 0; i < topo_max_cpus; ++i) { + if (!CPU_ISSET_S(i, present_cpumask_size, present_cpumask)) + continue; + + map.cmd_count = 1; + map.cpu_map[0].logical_cpu = i; + + debug_printf(" map logical_cpu:%d\n", + map.cpu_map[0].logical_cpu); + if (ioctl(fd, ISST_IF_GET_PHY_ID, &map) == -1) { + perror("ISST_IF_GET_PHY_ID"); + fprintf(outf, "Error: map logical_cpu:%d\n", + map.cpu_map[0].logical_cpu); + continue; + } + cpu_map[i].core_id = get_physical_core_id(i); + cpu_map[i].pkg_id = get_physical_package_id(i); + cpu_map[i].die_id = get_physical_die_id(i); + cpu_map[i].punit_cpu = map.cpu_map[0].physical_cpu; + cpu_map[i].punit_cpu_core = (map.cpu_map[0].physical_cpu >> + 1); // shift to get core id + + debug_printf( + "map logical_cpu:%d core: %d die:%d pkg:%d punit_cpu:%d punit_core:%d\n", + i, cpu_map[i].core_id, cpu_map[i].die_id, + cpu_map[i].pkg_id, cpu_map[i].punit_cpu, + cpu_map[i].punit_cpu_core); + } + + if (fd) + close(fd); +} + +int find_logical_cpu(int pkg_id, int die_id, int punit_core_id) +{ + int i; + + for (i = 0; i < topo_max_cpus; ++i) { + if (cpu_map[i].pkg_id == pkg_id && + cpu_map[i].die_id == die_id && + cpu_map[i].punit_cpu_core == punit_core_id) + return i; + } + + return -EINVAL; +} + +void set_cpu_mask_from_punit_coremask(int cpu, unsigned long long core_mask, + size_t core_cpumask_size, + cpu_set_t *core_cpumask, int *cpu_cnt) +{ + int i, cnt = 0; + int die_id, pkg_id; + + *cpu_cnt = 0; + die_id = get_physical_die_id(cpu); + pkg_id = get_physical_package_id(cpu); + + for (i = 0; i < 64; ++i) { + if (core_mask & BIT(i)) { + int j; + + for (j = 0; j < topo_max_cpus; ++j) { + if (cpu_map[j].pkg_id == pkg_id && + cpu_map[j].die_id == die_id && + cpu_map[j].punit_cpu_core == i) { + CPU_SET_S(j, core_cpumask_size, + core_cpumask); + ++cnt; + } + } + } + } + + *cpu_cnt = cnt; +} + +int find_phy_core_num(int logical_cpu) +{ + if (logical_cpu < topo_max_cpus) + return cpu_map[logical_cpu].punit_cpu_core; + + return -EINVAL; +} + +static int isst_send_mmio_command(unsigned int cpu, unsigned int reg, int write, + unsigned int *value) +{ + struct isst_if_io_regs io_regs; + const char *pathname = "/dev/isst_interface"; + int cmd; + int fd; + + debug_printf("mmio_cmd cpu:%d reg:%d write:%d\n", cpu, reg, write); + + fd = open(pathname, O_RDWR); + if (fd < 0) + err(-1, "%s open failed", pathname); + + io_regs.req_count = 1; + io_regs.io_reg[0].logical_cpu = cpu; + io_regs.io_reg[0].reg = reg; + cmd = ISST_IF_IO_CMD; + if (write) { + io_regs.io_reg[0].read_write = 1; + io_regs.io_reg[0].value = *value; + } else { + io_regs.io_reg[0].read_write = 0; + } + + if (ioctl(fd, cmd, &io_regs) == -1) { + perror("ISST_IF_IO_CMD"); + fprintf(outf, "Error: mmio_cmd cpu:%d reg:%x read_write:%x\n", + cpu, reg, write); + } else { + if (!write) + *value = io_regs.io_reg[0].value; + + debug_printf( + "mmio_cmd response: cpu:%d reg:%x rd_write:%x resp:%x\n", + cpu, reg, write, *value); + } + + close(fd); + + return 0; +} + +int isst_send_mbox_command(unsigned int cpu, unsigned char command, + unsigned char sub_command, unsigned int parameter, + unsigned int req_data, unsigned int *resp) +{ + const char *pathname = "/dev/isst_interface"; + int fd; + struct isst_if_mbox_cmds mbox_cmds = { 0 }; + + debug_printf( + "mbox_send: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x\n", + cpu, command, sub_command, parameter, req_data); + + if (isst_platform_info.mmio_supported && command == CONFIG_CLOS) { + unsigned int value; + int write = 0; + int clos_id, core_id, ret = 0; + + debug_printf("CLOS %d\n", cpu); + + if (parameter & BIT(MBOX_CMD_WRITE_BIT)) { + value = req_data; + write = 1; + } + + switch (sub_command) { + case CLOS_PQR_ASSOC: + core_id = parameter & 0xff; + ret = isst_send_mmio_command( + cpu, PQR_ASSOC_OFFSET + core_id * 4, write, + &value); + if (!ret && !write) + *resp = value; + break; + case CLOS_PM_CLOS: + clos_id = parameter & 0x03; + ret = isst_send_mmio_command( + cpu, PM_CLOS_OFFSET + clos_id * 4, write, + &value); + if (!ret && !write) + *resp = value; + break; + case CLOS_PM_QOS_CONFIG: + ret = isst_send_mmio_command(cpu, PM_QOS_CONFIG_OFFSET, + write, &value); + if (!ret && !write) + *resp = value; + break; + case CLOS_STATUS: + break; + default: + break; + } + return ret; + } + + mbox_cmds.cmd_count = 1; + mbox_cmds.mbox_cmd[0].logical_cpu = cpu; + mbox_cmds.mbox_cmd[0].command = command; + mbox_cmds.mbox_cmd[0].sub_command = sub_command; + mbox_cmds.mbox_cmd[0].parameter = parameter; + mbox_cmds.mbox_cmd[0].req_data = req_data; + + fd = open(pathname, O_RDWR); + if (fd < 0) + err(-1, "%s open failed", pathname); + + if (ioctl(fd, ISST_IF_MBOX_COMMAND, &mbox_cmds) == -1) { + perror("ISST_IF_MBOX_COMMAND"); + fprintf(outf, + "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x\n", + cpu, command, sub_command, parameter, req_data); + } else { + *resp = mbox_cmds.mbox_cmd[0].resp_data; + debug_printf( + "mbox_cmd response: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x resp:%x\n", + cpu, command, sub_command, parameter, req_data, *resp); + } + + close(fd); + + return 0; +} + +int isst_send_msr_command(unsigned int cpu, unsigned int msr, int write, + unsigned long long *req_resp) +{ + struct isst_if_msr_cmds msr_cmds; + const char *pathname = "/dev/isst_interface"; + int fd; + + fd = open(pathname, O_RDWR); + if (fd < 0) + err(-1, "%s open failed", pathname); + + msr_cmds.cmd_count = 1; + msr_cmds.msr_cmd[0].logical_cpu = cpu; + msr_cmds.msr_cmd[0].msr = msr; + msr_cmds.msr_cmd[0].read_write = write; + if (write) + msr_cmds.msr_cmd[0].data = *req_resp; + + if (ioctl(fd, ISST_IF_MSR_COMMAND, &msr_cmds) == -1) { + perror("ISST_IF_MSR_COMMAD"); + fprintf(outf, "Error: msr_cmd cpu:%d msr:%x read_write:%d\n", + cpu, msr, write); + } else { + if (!write) + *req_resp = msr_cmds.msr_cmd[0].data; + + debug_printf( + "msr_cmd response: cpu:%d msr:%x rd_write:%x resp:%llx %llx\n", + cpu, msr, write, *req_resp, msr_cmds.msr_cmd[0].data); + } + + close(fd); + + return 0; +} + +static int isst_fill_platform_info(void) +{ + const char *pathname = "/dev/isst_interface"; + int fd; + + fd = open(pathname, O_RDWR); + if (fd < 0) + err(-1, "%s open failed", pathname); + + if (ioctl(fd, ISST_IF_GET_PLATFORM_INFO, &isst_platform_info) == -1) { + perror("ISST_IF_GET_PLATFORM_INFO"); + close(fd); + return -1; + } + + close(fd); + + return 0; +} + +static void isst_print_platform_information(void) +{ + struct isst_if_platform_info platform_info; + const char *pathname = "/dev/isst_interface"; + int fd; + + fd = open(pathname, O_RDWR); + if (fd < 0) + err(-1, "%s open failed", pathname); + + if (ioctl(fd, ISST_IF_GET_PLATFORM_INFO, &platform_info) == -1) { + perror("ISST_IF_GET_PLATFORM_INFO"); + } else { + fprintf(outf, "Platform: API version : %d\n", + platform_info.api_version); + fprintf(outf, "Platform: Driver version : %d\n", + platform_info.driver_version); + fprintf(outf, "Platform: mbox supported : %d\n", + platform_info.mbox_supported); + fprintf(outf, "Platform: mmio supported : %d\n", + platform_info.mmio_supported); + } + + close(fd); + + exit(0); +} + +static void exec_on_get_ctdp_cpu(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + int (*fn_ptr)(int cpu, void *arg); + int ret; + + fn_ptr = arg1; + ret = fn_ptr(cpu, arg2); + if (ret) + perror("get_tdp_*"); + else + isst_display_result(cpu, outf, "perf-profile", (char *)arg3, + *(unsigned int *)arg4); +} + +#define _get_tdp_level(desc, suffix, object, help) \ + static void get_tdp_##object(void) \ + { \ + struct isst_pkg_ctdp ctdp; \ +\ + if (cmd_help) { \ + fprintf(stderr, \ + "Print %s [No command arguments are required]\n", \ + help); \ + exit(0); \ + } \ + isst_ctdp_display_information_start(outf); \ + if (max_target_cpus) \ + for_each_online_target_cpu_in_set( \ + exec_on_get_ctdp_cpu, isst_get_ctdp_##suffix, \ + &ctdp, desc, &ctdp.object); \ + else \ + for_each_online_package_in_set(exec_on_get_ctdp_cpu, \ + isst_get_ctdp_##suffix, \ + &ctdp, desc, \ + &ctdp.object); \ + isst_ctdp_display_information_end(outf); \ + } + +_get_tdp_level("get-config-levels", levels, levels, "TDP levels"); +_get_tdp_level("get-config-version", levels, version, "TDP version"); +_get_tdp_level("get-config-enabled", levels, enabled, "TDP enable status"); +_get_tdp_level("get-config-current_level", levels, current_level, + "Current TDP Level"); +_get_tdp_level("get-lock-status", levels, locked, "TDP lock status"); + +static void dump_isst_config_for_cpu(int cpu, void *arg1, void *arg2, + void *arg3, void *arg4) +{ + struct isst_pkg_ctdp pkg_dev; + int ret; + + memset(&pkg_dev, 0, sizeof(pkg_dev)); + ret = isst_get_process_ctdp(cpu, tdp_level, &pkg_dev); + if (ret) { + perror("isst_get_process_ctdp"); + } else { + isst_ctdp_display_information(cpu, outf, tdp_level, &pkg_dev); + isst_get_process_ctdp_complete(cpu, &pkg_dev); + } +} + +static void dump_isst_config(void) +{ + if (cmd_help) { + fprintf(stderr, + "Print Intel(R) Speed Select Technology Performance profile configuration\n"); + fprintf(stderr, + "including base frequency and turbo frequency configurations\n"); + fprintf(stderr, "Optional: -l|--level : Specify tdp level\n"); + fprintf(stderr, + "\tIf no arguments, dump information for all TDP levels\n"); + exit(0); + } + + isst_ctdp_display_information_start(outf); + + if (max_target_cpus) + for_each_online_target_cpu_in_set(dump_isst_config_for_cpu, + NULL, NULL, NULL, NULL); + else + for_each_online_package_in_set(dump_isst_config_for_cpu, NULL, + NULL, NULL, NULL); + + isst_ctdp_display_information_end(outf); +} + +static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + int ret; + + ret = isst_set_tdp_level(cpu, tdp_level); + if (ret) + perror("set_tdp_level_for_cpu"); + else + isst_display_result(cpu, outf, "perf-profile", "set_tdp_level", + ret); +} + +static void set_tdp_level(void) +{ + if (cmd_help) { + fprintf(stderr, "Set Config TDP level\n"); + fprintf(stderr, + "\t Arguments: -l|--level : Specify tdp level\n"); + exit(0); + } + + if (tdp_level == 0xff) { + fprintf(outf, "Invalid command: specify tdp_level\n"); + exit(1); + } + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(set_tdp_level_for_cpu, NULL, + NULL, NULL, NULL); + else + for_each_online_package_in_set(set_tdp_level_for_cpu, NULL, + NULL, NULL, NULL); + isst_ctdp_display_information_end(outf); +} + +static void dump_pbf_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + struct isst_pbf_info pbf_info; + int ret; + + ret = isst_get_pbf_info(cpu, tdp_level, &pbf_info); + if (ret) { + perror("isst_get_pbf_info"); + } else { + isst_pbf_display_information(cpu, outf, tdp_level, &pbf_info); + isst_get_pbf_info_complete(&pbf_info); + } +} + +static void dump_pbf_config(void) +{ + if (cmd_help) { + fprintf(stderr, + "Print Intel(R) Speed Select Technology base frequency configuration for a TDP level\n"); + fprintf(stderr, + "\tArguments: -l|--level : Specify tdp level\n"); + exit(0); + } + + if (tdp_level == 0xff) { + fprintf(outf, "Invalid command: specify tdp_level\n"); + exit(1); + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(dump_pbf_config_for_cpu, NULL, + NULL, NULL, NULL); + else + for_each_online_package_in_set(dump_pbf_config_for_cpu, NULL, + NULL, NULL, NULL); + isst_ctdp_display_information_end(outf); +} + +static void set_pbf_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + int ret; + int status = *(int *)arg4; + + ret = isst_set_pbf_fact_status(cpu, 1, status); + if (ret) { + perror("isst_set_pbf"); + } else { + if (status) + isst_display_result(cpu, outf, "base-freq", "enable", + ret); + else + isst_display_result(cpu, outf, "base-freq", "disable", + ret); + } +} + +static void set_pbf_enable(void) +{ + int status = 1; + + if (cmd_help) { + fprintf(stderr, + "Enable Intel Speed Select Technology base frequency feature [No command arguments are required]\n"); + exit(0); + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(set_pbf_for_cpu, NULL, NULL, + NULL, &status); + else + for_each_online_package_in_set(set_pbf_for_cpu, NULL, NULL, + NULL, &status); + isst_ctdp_display_information_end(outf); +} + +static void set_pbf_disable(void) +{ + int status = 0; + + if (cmd_help) { + fprintf(stderr, + "Disable Intel Speed Select Technology base frequency feature [No command arguments are required]\n"); + exit(0); + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(set_pbf_for_cpu, NULL, NULL, + NULL, &status); + else + for_each_online_package_in_set(set_pbf_for_cpu, NULL, NULL, + NULL, &status); + isst_ctdp_display_information_end(outf); +} + +static void dump_fact_config_for_cpu(int cpu, void *arg1, void *arg2, + void *arg3, void *arg4) +{ + struct isst_fact_info fact_info; + int ret; + + ret = isst_get_fact_info(cpu, tdp_level, &fact_info); + if (ret) + perror("isst_get_fact_bucket_info"); + else + isst_fact_display_information(cpu, outf, tdp_level, fact_bucket, + fact_avx, &fact_info); +} + +static void dump_fact_config(void) +{ + if (cmd_help) { + fprintf(stderr, + "Print complete Intel Speed Select Technology turbo frequency configuration for a TDP level. Other arguments are optional.\n"); + fprintf(stderr, + "\tArguments: -l|--level : Specify tdp level\n"); + fprintf(stderr, + "\tArguments: -b|--bucket : Bucket index to dump\n"); + fprintf(stderr, + "\tArguments: -r|--trl-type : Specify trl type: sse|avx2|avx512\n"); + exit(0); + } + + if (tdp_level == 0xff) { + fprintf(outf, "Invalid command: specify tdp_level\n"); + exit(1); + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(dump_fact_config_for_cpu, + NULL, NULL, NULL, NULL); + else + for_each_online_package_in_set(dump_fact_config_for_cpu, NULL, + NULL, NULL, NULL); + isst_ctdp_display_information_end(outf); +} + +static void set_fact_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + int ret; + int status = *(int *)arg4; + + ret = isst_set_pbf_fact_status(cpu, 0, status); + if (ret) + perror("isst_set_fact"); + else { + if (status) { + struct isst_pkg_ctdp pkg_dev; + + ret = isst_get_ctdp_levels(cpu, &pkg_dev); + if (ret) { + isst_display_result(cpu, outf, "turbo-freq", + "enable", ret); + return; + } + ret = isst_set_trl(cpu, fact_trl); + isst_display_result(cpu, outf, "turbo-freq", "enable", + ret); + } else { + /* Since we modified TRL during Fact enable, restore it */ + isst_set_trl_from_current_tdp(cpu, fact_trl); + isst_display_result(cpu, outf, "turbo-freq", "disable", + ret); + } + } +} + +static void set_fact_enable(void) +{ + int status = 1; + + if (cmd_help) { + fprintf(stderr, + "Enable Intel Speed Select Technology Turbo frequency feature\n"); + fprintf(stderr, + "Optional: -t|--trl : Specify turbo ratio limit\n"); + exit(0); + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(set_fact_for_cpu, NULL, NULL, + NULL, &status); + else + for_each_online_package_in_set(set_fact_for_cpu, NULL, NULL, + NULL, &status); + isst_ctdp_display_information_end(outf); +} + +static void set_fact_disable(void) +{ + int status = 0; + + if (cmd_help) { + fprintf(stderr, + "Disable Intel Speed Select Technology turbo frequency feature\n"); + fprintf(stderr, + "Optional: -t|--trl : Specify turbo ratio limit\n"); + exit(0); + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(set_fact_for_cpu, NULL, NULL, + NULL, &status); + else + for_each_online_package_in_set(set_fact_for_cpu, NULL, NULL, + NULL, &status); + isst_ctdp_display_information_end(outf); +} + +static void enable_clos_qos_config(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + int ret; + int status = *(int *)arg4; + + ret = isst_pm_qos_config(cpu, status, clos_priority_type); + if (ret) { + perror("isst_pm_qos_config"); + } else { + if (status) + isst_display_result(cpu, outf, "core-power", "enable", + ret); + else + isst_display_result(cpu, outf, "core-power", "disable", + ret); + } +} + +static void set_clos_enable(void) +{ + int status = 1; + + if (cmd_help) { + fprintf(stderr, "Enable core-power for a package/die\n"); + fprintf(stderr, + "\tClos Enable: Specify priority type with [--priority|-p]\n"); + fprintf(stderr, "\t\t 0: Proportional, 1: Ordered\n"); + exit(0); + } + + if (cpufreq_sysfs_present()) { + fprintf(stderr, + "cpufreq subsystem and core-power enable will interfere with each other!\n"); + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(enable_clos_qos_config, NULL, + NULL, NULL, &status); + else + for_each_online_package_in_set(enable_clos_qos_config, NULL, + NULL, NULL, &status); + isst_ctdp_display_information_end(outf); +} + +static void set_clos_disable(void) +{ + int status = 0; + + if (cmd_help) { + fprintf(stderr, + "Disable core-power: [No command arguments are required]\n"); + exit(0); + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(enable_clos_qos_config, NULL, + NULL, NULL, &status); + else + for_each_online_package_in_set(enable_clos_qos_config, NULL, + NULL, NULL, &status); + isst_ctdp_display_information_end(outf); +} + +static void dump_clos_config_for_cpu(int cpu, void *arg1, void *arg2, + void *arg3, void *arg4) +{ + struct isst_clos_config clos_config; + int ret; + + ret = isst_pm_get_clos(cpu, current_clos, &clos_config); + if (ret) + perror("isst_pm_get_clos"); + else + isst_clos_display_information(cpu, outf, current_clos, + &clos_config); +} + +static void dump_clos_config(void) +{ + if (cmd_help) { + fprintf(stderr, + "Print Intel Speed Select Technology core power configuration\n"); + fprintf(stderr, + "\tArguments: [-c | --clos]: Specify clos id\n"); + exit(0); + } + if (current_clos < 0 || current_clos > 3) { + fprintf(stderr, "Invalid clos id\n"); + exit(0); + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(dump_clos_config_for_cpu, + NULL, NULL, NULL, NULL); + else + for_each_online_package_in_set(dump_clos_config_for_cpu, NULL, + NULL, NULL, NULL); + isst_ctdp_display_information_end(outf); +} + +static void set_clos_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + struct isst_clos_config clos_config; + int ret; + + clos_config.pkg_id = get_physical_package_id(cpu); + clos_config.die_id = get_physical_die_id(cpu); + + clos_config.epp = clos_epp; + clos_config.clos_prop_prio = clos_prop_prio; + clos_config.clos_min = clos_min; + clos_config.clos_max = clos_max; + clos_config.clos_desired = clos_desired; + ret = isst_set_clos(cpu, current_clos, &clos_config); + if (ret) + perror("isst_set_clos"); + else + isst_display_result(cpu, outf, "core-power", "config", ret); +} + +static void set_clos_config(void) +{ + if (cmd_help) { + fprintf(stderr, + "Set core-power configuration for one of the four clos ids\n"); + fprintf(stderr, + "\tSpecify targeted clos id with [--clos|-c]\n"); + fprintf(stderr, "\tSpecify clos EPP with [--epp|-e]\n"); + fprintf(stderr, + "\tSpecify clos Proportional Priority [--weight|-w]\n"); + fprintf(stderr, "\tSpecify clos min with [--min|-n]\n"); + fprintf(stderr, "\tSpecify clos max with [--max|-m]\n"); + fprintf(stderr, "\tSpecify clos desired with [--desired|-d]\n"); + exit(0); + } + + if (current_clos < 0 || current_clos > 3) { + fprintf(stderr, "Invalid clos id\n"); + exit(0); + } + if (clos_epp < 0 || clos_epp > 0x0F) { + fprintf(stderr, "clos epp is not specified, default: 0\n"); + clos_epp = 0; + } + if (clos_prop_prio < 0 || clos_prop_prio > 0x0F) { + fprintf(stderr, + "clos frequency weight is not specified, default: 0\n"); + clos_prop_prio = 0; + } + if (clos_min < 0) { + fprintf(stderr, "clos min is not specified, default: 0\n"); + clos_min = 0; + } + if (clos_max < 0) { + fprintf(stderr, "clos max is not specified, default: 0xff\n"); + clos_max = 0xff; + } + if (clos_desired < 0) { + fprintf(stderr, "clos desired is not specified, default: 0\n"); + clos_desired = 0x00; + } + + isst_ctdp_display_information_start(outf); + if (max_target_cpus) + for_each_online_target_cpu_in_set(set_clos_config_for_cpu, NULL, + NULL, NULL, NULL); + else + for_each_online_package_in_set(set_clos_config_for_cpu, NULL, + NULL, NULL, NULL); + isst_ctdp_display_information_end(outf); +} + +static void set_clos_assoc_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + int ret; + + ret = isst_clos_associate(cpu, current_clos); + if (ret) + perror("isst_clos_associate"); + else + isst_display_result(cpu, outf, "core-power", "assoc", ret); +} + +static void set_clos_assoc(void) +{ + if (cmd_help) { + fprintf(stderr, "Associate a clos id to a CPU\n"); + fprintf(stderr, + "\tSpecify targeted clos id with [--clos|-c]\n"); + exit(0); + } + + if (current_clos < 0 || current_clos > 3) { + fprintf(stderr, "Invalid clos id\n"); + exit(0); + } + if (max_target_cpus) + for_each_online_target_cpu_in_set(set_clos_assoc_for_cpu, NULL, + NULL, NULL, NULL); + else { + fprintf(stderr, + "Invalid target cpu. Specify with [-c|--cpu]\n"); + } +} + +static void get_clos_assoc_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, + void *arg4) +{ + int clos, ret; + + ret = isst_clos_get_assoc_status(cpu, &clos); + if (ret) + perror("isst_clos_get_assoc_status"); + else + isst_display_result(cpu, outf, "core-power", "get-assoc", clos); +} + +static void get_clos_assoc(void) +{ + if (cmd_help) { + fprintf(stderr, "Get associate clos id to a CPU\n"); + fprintf(stderr, "\tSpecify targeted cpu id with [--cpu|-c]\n"); + exit(0); + } + if (max_target_cpus) + for_each_online_target_cpu_in_set(get_clos_assoc_for_cpu, NULL, + NULL, NULL, NULL); + else { + fprintf(stderr, + "Invalid target cpu. Specify with [-c|--cpu]\n"); + } +} + +static struct process_cmd_struct isst_cmds[] = { + { "perf-profile", "get-lock-status", get_tdp_locked }, + { "perf-profile", "get-config-levels", get_tdp_levels }, + { "perf-profile", "get-config-version", get_tdp_version }, + { "perf-profile", "get-config-enabled", get_tdp_enabled }, + { "perf-profile", "get-config-current-level", get_tdp_current_level }, + { "perf-profile", "set-config-level", set_tdp_level }, + { "perf-profile", "info", dump_isst_config }, + { "base-freq", "info", dump_pbf_config }, + { "base-freq", "enable", set_pbf_enable }, + { "base-freq", "disable", set_pbf_disable }, + { "turbo-freq", "info", dump_fact_config }, + { "turbo-freq", "enable", set_fact_enable }, + { "turbo-freq", "disable", set_fact_disable }, + { "core-power", "info", dump_clos_config }, + { "core-power", "enable", set_clos_enable }, + { "core-power", "disable", set_clos_disable }, + { "core-power", "config", set_clos_config }, + { "core-power", "assoc", set_clos_assoc }, + { "core-power", "get-assoc", get_clos_assoc }, + { NULL, NULL, NULL } +}; + +/* + * parse cpuset with following syntax + * 1,2,4..6,8-10 and set bits in cpu_subset + */ +void parse_cpu_command(char *optarg) +{ + unsigned int start, end; + char *next; + + next = optarg; + + while (next && *next) { + if (*next == '-') /* no negative cpu numbers */ + goto error; + + start = strtoul(next, &next, 10); + + if (max_target_cpus < MAX_CPUS_IN_ONE_REQ) + target_cpus[max_target_cpus++] = start; + + if (*next == '\0') + break; + + if (*next == ',') { + next += 1; + continue; + } + + if (*next == '-') { + next += 1; /* start range */ + } else if (*next == '.') { + next += 1; + if (*next == '.') + next += 1; /* start range */ + else + goto error; + } + + end = strtoul(next, &next, 10); + if (end <= start) + goto error; + + while (++start <= end) { + if (max_target_cpus < MAX_CPUS_IN_ONE_REQ) + target_cpus[max_target_cpus++] = start; + } + + if (*next == ',') + next += 1; + else if (*next != '\0') + goto error; + } + +#ifdef DEBUG + { + int i; + + for (i = 0; i < max_target_cpus; ++i) + printf("cpu [%d] in arg\n", target_cpus[i]); + } +#endif + return; + +error: + fprintf(stderr, "\"--cpu %s\" malformed\n", optarg); + exit(-1); +} + +static void parse_cmd_args(int argc, int start, char **argv) +{ + int opt; + int option_index; + + static struct option long_options[] = { + { "bucket", required_argument, 0, 'b' }, + { "level", required_argument, 0, 'l' }, + { "trl-type", required_argument, 0, 'r' }, + { "trl", required_argument, 0, 't' }, + { "help", no_argument, 0, 'h' }, + { "clos", required_argument, 0, 'c' }, + { "desired", required_argument, 0, 'd' }, + { "epp", required_argument, 0, 'e' }, + { "min", required_argument, 0, 'n' }, + { "max", required_argument, 0, 'm' }, + { "priority", required_argument, 0, 'p' }, + { "weight", required_argument, 0, 'w' }, + { 0, 0, 0, 0 } + }; + + option_index = start; + + optind = start + 1; + while ((opt = getopt_long(argc, argv, "b:l:t:c:d:e:n:m:p:w:h", + long_options, &option_index)) != -1) { + switch (opt) { + case 'b': + fact_bucket = atoi(optarg); + break; + case 'h': + cmd_help = 1; + break; + case 'l': + tdp_level = atoi(optarg); + break; + case 't': + sscanf(optarg, "0x%llx", &fact_trl); + break; + case 'r': + if (!strncmp(optarg, "sse", 3)) { + fact_avx = 0x01; + } else if (!strncmp(optarg, "avx2", 4)) { + fact_avx = 0x02; + } else if (!strncmp(optarg, "avx512", 4)) { + fact_avx = 0x04; + } else { + fprintf(outf, "Invalid sse,avx options\n"); + exit(1); + } + break; + /* CLOS related */ + case 'c': + current_clos = atoi(optarg); + printf("clos %d\n", current_clos); + break; + case 'd': + clos_desired = atoi(optarg); + break; + case 'e': + clos_epp = atoi(optarg); + break; + case 'n': + clos_min = atoi(optarg); + break; + case 'm': + clos_max = atoi(optarg); + break; + case 'p': + clos_priority_type = atoi(optarg); + break; + case 'w': + clos_prop_prio = atoi(optarg); + break; + default: + printf("no match\n"); + } + } +} + +static void isst_help(void) +{ + printf("perf-profile:\tAn architectural mechanism that allows multiple optimized \n\ + performance profiles per system via static and/or dynamic\n\ + adjustment of core count, workload, Tjmax, and\n\ + TDP, etc.\n"); + printf("\nCommands : For feature=perf-profile\n"); + printf("\tinfo\n"); + printf("\tget-lock-status\n"); + printf("\tget-config-levels\n"); + printf("\tget-config-version\n"); + printf("\tget-config-enabled\n"); + printf("\tget-config-current-level\n"); + printf("\tset-config-level\n"); +} + +static void pbf_help(void) +{ + printf("base-freq:\tEnables users to increase guaranteed base frequency\n\ + on certain cores (high priority cores) in exchange for lower\n\ + base frequency on remaining cores (low priority cores).\n"); + printf("\tcommand : info\n"); + printf("\tcommand : enable\n"); + printf("\tcommand : disable\n"); +} + +static void fact_help(void) +{ + printf("turbo-freq:\tEnables the ability to set different turbo ratio\n\ + limits to cores based on priority.\n"); + printf("\nCommand: For feature=turbo-freq\n"); + printf("\tcommand : info\n"); + printf("\tcommand : enable\n"); + printf("\tcommand : disable\n"); +} + +static void core_power_help(void) +{ + printf("core-power:\tInterface that allows user to define per core/tile\n\ + priority.\n"); + printf("\nCommands : For feature=core-power\n"); + printf("\tinfo\n"); + printf("\tenable\n"); + printf("\tdisable\n"); + printf("\tconfig\n"); + printf("\tassoc\n"); + printf("\tget-assoc\n"); +} + +struct process_cmd_help_struct { + char *feature; + void (*process_fn)(void); +}; + +static struct process_cmd_help_struct isst_help_cmds[] = { + { "perf-profile", isst_help }, + { "base-freq", pbf_help }, + { "turbo-freq", fact_help }, + { "core-power", core_power_help }, + { NULL, NULL } +}; + +void process_command(int argc, char **argv) +{ + int i = 0, matched = 0; + char *feature = argv[optind]; + char *cmd = argv[optind + 1]; + + if (!feature || !cmd) + return; + + debug_printf("feature name [%s] command [%s]\n", feature, cmd); + if (!strcmp(cmd, "-h") || !strcmp(cmd, "--help")) { + while (isst_help_cmds[i].feature) { + if (!strcmp(isst_help_cmds[i].feature, feature)) { + isst_help_cmds[i].process_fn(); + exit(0); + } + ++i; + } + } + + create_cpu_map(); + + i = 0; + while (isst_cmds[i].feature) { + if (!strcmp(isst_cmds[i].feature, feature) && + !strcmp(isst_cmds[i].command, cmd)) { + parse_cmd_args(argc, optind + 1, argv); + isst_cmds[i].process_fn(); + matched = 1; + break; + } + ++i; + } + + if (!matched) + fprintf(stderr, "Invalid command\n"); +} + +static void usage(void) +{ + printf("Intel(R) Speed Select Technology\n"); + printf("\nUsage:\n"); + printf("intel-speed-select [OPTIONS] FEATURE COMMAND COMMAND_ARGUMENTS\n"); + printf("\nUse this tool to enumerate and control the Intel Speed Select Technology features,\n"); + printf("\nFEATURE : [perf-profile|base-freq|turbo-freq|core-power]\n"); + printf("\nFor help on each feature, use --h|--help\n"); + printf("\tFor example: intel-speed-select perf-profile -h\n"); + + printf("\nFor additional help on each command for a feature, use --h|--help\n"); + printf("\tFor example: intel-speed-select perf-profile get-lock-status -h\n"); + printf("\t\t This will print help for the command \"get-lock-status\" for the feature \"perf-profile\"\n"); + + printf("\nOPTIONS\n"); + printf("\t[-c|--cpu] : logical cpu number\n"); + printf("\t\tDefault: Die scoped for all dies in the system with multiple dies/package\n"); + printf("\t\t\t Or Package scoped for all Packages when each package contains one die\n"); + printf("\t[-d|--debug] : Debug mode\n"); + printf("\t[-h|--help] : Print help\n"); + printf("\t[-i|--info] : Print platform information\n"); + printf("\t[-o|--out] : Output file\n"); + printf("\t\t\tDefault : stderr\n"); + printf("\t[-f|--format] : output format [json|text]. Default: text\n"); + printf("\t[-v|--version] : Print version\n"); + + printf("\nResult format\n"); + printf("\tResult display uses a common format for each command:\n"); + printf("\tResults are formatted in text/JSON with\n"); + printf("\t\tPackage, Die, CPU, and command specific results.\n"); + printf("\t\t\tFor Set commands, status is 0 for success and rest for failures\n"); + exit(1); +} + +static void print_version(void) +{ + fprintf(outf, "Version %s\n", version_str); + fprintf(outf, "Build date %s time %s\n", __DATE__, __TIME__); + exit(0); +} + +static void cmdline(int argc, char **argv) +{ + int opt; + int option_index = 0; + + static struct option long_options[] = { + { "cpu", required_argument, 0, 'c' }, + { "debug", no_argument, 0, 'd' }, + { "format", required_argument, 0, 'f' }, + { "help", no_argument, 0, 'h' }, + { "info", no_argument, 0, 'i' }, + { "out", required_argument, 0, 'o' }, + { "version", no_argument, 0, 'v' }, + { 0, 0, 0, 0 } + }; + + progname = argv[0]; + while ((opt = getopt_long_only(argc, argv, "+c:df:hio:v", long_options, + &option_index)) != -1) { + switch (opt) { + case 'c': + parse_cpu_command(optarg); + break; + case 'd': + debug_flag = 1; + printf("Debug Mode ON\n"); + break; + case 'f': + if (!strncmp(optarg, "json", 4)) + out_format_json = 1; + break; + case 'h': + usage(); + break; + case 'i': + isst_print_platform_information(); + break; + case 'o': + if (outf) + fclose(outf); + outf = fopen_or_exit(optarg, "w"); + break; + case 'v': + print_version(); + break; + default: + usage(); + } + } + + if (geteuid() != 0) { + fprintf(stderr, "Must run as root\n"); + exit(0); + } + + if (optind > (argc - 2)) { + fprintf(stderr, "Feature name and|or command not specified\n"); + exit(0); + } + update_cpu_model(); + printf("Intel(R) Speed Select Technology\n"); + printf("Executing on CPU model:%d[0x%x]\n", cpu_model, cpu_model); + set_max_cpu_num(); + set_cpu_present_cpu_mask(); + set_cpu_target_cpu_mask(); + isst_fill_platform_info(); + if (isst_platform_info.api_version > supported_api_ver) { + printf("Incompatible API versions; Upgrade of tool is required\n"); + exit(0); + } + + process_command(argc, argv); +} + +int main(int argc, char **argv) +{ + outf = stderr; + cmdline(argc, argv); + return 0; +} diff --git a/tools/power/x86/intel-speed-select/isst-core.c b/tools/power/x86/intel-speed-select/isst-core.c new file mode 100644 index 000000000000..8de4ac39a008 --- /dev/null +++ b/tools/power/x86/intel-speed-select/isst-core.c @@ -0,0 +1,721 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Speed Select -- Enumerate and control features + * Copyright (c) 2019 Intel Corporation. + */ + +#include "isst.h" + +int isst_get_ctdp_levels(int cpu, struct isst_pkg_ctdp *pkg_dev) +{ + unsigned int resp; + int ret; + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_GET_LEVELS_INFO, 0, 0, &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CONFIG_TDP_GET_LEVELS_INFO resp:%x\n", cpu, resp); + + pkg_dev->version = resp & 0xff; + pkg_dev->levels = (resp >> 8) & 0xff; + pkg_dev->current_level = (resp >> 16) & 0xff; + pkg_dev->locked = !!(resp & BIT(24)); + pkg_dev->enabled = !!(resp & BIT(31)); + + return 0; +} + +int isst_get_ctdp_control(int cpu, int config_index, + struct isst_pkg_ctdp_level_info *ctdp_level) +{ + unsigned int resp; + int ret; + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_GET_TDP_CONTROL, 0, + config_index, &resp); + if (ret) + return ret; + + ctdp_level->fact_support = resp & BIT(0); + ctdp_level->pbf_support = !!(resp & BIT(1)); + ctdp_level->fact_enabled = !!(resp & BIT(16)); + ctdp_level->pbf_enabled = !!(resp & BIT(17)); + + debug_printf( + "cpu:%d CONFIG_TDP_GET_TDP_CONTROL resp:%x fact_support:%d pbf_support: %d fact_enabled:%d pbf_enabled:%d\n", + cpu, resp, ctdp_level->fact_support, ctdp_level->pbf_support, + ctdp_level->fact_enabled, ctdp_level->pbf_enabled); + + return 0; +} + +int isst_get_tdp_info(int cpu, int config_index, + struct isst_pkg_ctdp_level_info *ctdp_level) +{ + unsigned int resp; + int ret; + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_TDP_INFO, + 0, config_index, &resp); + if (ret) + return ret; + + ctdp_level->pkg_tdp = resp & GENMASK(14, 0); + ctdp_level->tdp_ratio = (resp & GENMASK(23, 16)) >> 16; + + debug_printf( + "cpu:%d ctdp:%d CONFIG_TDP_GET_TDP_INFO resp:%x tdp_ratio:%d pkg_tdp:%d\n", + cpu, config_index, resp, ctdp_level->tdp_ratio, + ctdp_level->pkg_tdp); + return 0; +} + +int isst_get_pwr_info(int cpu, int config_index, + struct isst_pkg_ctdp_level_info *ctdp_level) +{ + unsigned int resp; + int ret; + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_PWR_INFO, + 0, config_index, &resp); + if (ret) + return ret; + + ctdp_level->pkg_max_power = resp & GENMASK(14, 0); + ctdp_level->pkg_min_power = (resp & GENMASK(30, 16)) >> 16; + + debug_printf( + "cpu:%d ctdp:%d CONFIG_TDP_GET_PWR_INFO resp:%x pkg_max_power:%d pkg_min_power:%d\n", + cpu, config_index, resp, ctdp_level->pkg_max_power, + ctdp_level->pkg_min_power); + + return 0; +} + +int isst_get_tjmax_info(int cpu, int config_index, + struct isst_pkg_ctdp_level_info *ctdp_level) +{ + unsigned int resp; + int ret; + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_TJMAX_INFO, + 0, config_index, &resp); + if (ret) + return ret; + + ctdp_level->t_proc_hot = resp & GENMASK(7, 0); + + debug_printf( + "cpu:%d ctdp:%d CONFIG_TDP_GET_TJMAX_INFO resp:%x t_proc_hot:%d\n", + cpu, config_index, resp, ctdp_level->t_proc_hot); + + return 0; +} + +int isst_get_coremask_info(int cpu, int config_index, + struct isst_pkg_ctdp_level_info *ctdp_level) +{ + unsigned int resp; + int i, ret; + + ctdp_level->cpu_count = 0; + for (i = 0; i < 2; ++i) { + unsigned long long mask; + int cpu_count = 0; + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_GET_CORE_MASK, 0, + (i << 8) | config_index, &resp); + if (ret) + return ret; + + debug_printf( + "cpu:%d ctdp:%d mask:%d CONFIG_TDP_GET_CORE_MASK resp:%x\n", + cpu, config_index, i, resp); + + mask = (unsigned long long)resp << (32 * i); + set_cpu_mask_from_punit_coremask(cpu, mask, + ctdp_level->core_cpumask_size, + ctdp_level->core_cpumask, + &cpu_count); + ctdp_level->cpu_count += cpu_count; + debug_printf("cpu:%d ctdp:%d mask:%d cpu count:%d\n", cpu, + config_index, i, ctdp_level->cpu_count); + } + + return 0; +} + +int isst_get_get_trl(int cpu, int level, int avx_level, int *trl) +{ + unsigned int req, resp; + int ret; + + req = level | (avx_level << 16); + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_GET_TURBO_LIMIT_RATIOS, 0, req, + &resp); + if (ret) + return ret; + + debug_printf( + "cpu:%d CONFIG_TDP_GET_TURBO_LIMIT_RATIOS req:%x resp:%x\n", + cpu, req, resp); + + trl[0] = resp & GENMASK(7, 0); + trl[1] = (resp & GENMASK(15, 8)) >> 8; + trl[2] = (resp & GENMASK(23, 16)) >> 16; + trl[3] = (resp & GENMASK(31, 24)) >> 24; + + req = level | BIT(8) | (avx_level << 16); + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_GET_TURBO_LIMIT_RATIOS, 0, req, + &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CONFIG_TDP_GET_TURBO_LIMIT req:%x resp:%x\n", cpu, + req, resp); + + trl[4] = resp & GENMASK(7, 0); + trl[5] = (resp & GENMASK(15, 8)) >> 8; + trl[6] = (resp & GENMASK(23, 16)) >> 16; + trl[7] = (resp & GENMASK(31, 24)) >> 24; + + return 0; +} + +int isst_set_tdp_level_msr(int cpu, int tdp_level) +{ + int ret; + + debug_printf("cpu: tdp_level via MSR %d\n", cpu, tdp_level); + + if (isst_get_config_tdp_lock_status(cpu)) { + debug_printf("cpu: tdp_locked %d\n", cpu); + return -1; + } + + if (tdp_level > 2) + return -1; /* invalid value */ + + ret = isst_send_msr_command(cpu, 0x64b, 1, + (unsigned long long *)&tdp_level); + if (ret) + return ret; + + debug_printf("cpu: tdp_level via MSR successful %d\n", cpu, tdp_level); + + return 0; +} + +int isst_set_tdp_level(int cpu, int tdp_level) +{ + unsigned int resp; + int ret; + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_SET_LEVEL, 0, + tdp_level, &resp); + if (ret) + return isst_set_tdp_level_msr(cpu, tdp_level); + + return 0; +} + +int isst_get_pbf_info(int cpu, int level, struct isst_pbf_info *pbf_info) +{ + unsigned int req, resp; + int i, ret; + + pbf_info->core_cpumask_size = alloc_cpu_set(&pbf_info->core_cpumask); + + for (i = 0; i < 2; ++i) { + unsigned long long mask; + int count; + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_PBF_GET_CORE_MASK_INFO, + 0, (i << 8) | level, &resp); + if (ret) + return ret; + + debug_printf( + "cpu:%d CONFIG_TDP_PBF_GET_CORE_MASK_INFO resp:%x\n", + cpu, resp); + + mask = (unsigned long long)resp << (32 * i); + set_cpu_mask_from_punit_coremask(cpu, mask, + pbf_info->core_cpumask_size, + pbf_info->core_cpumask, + &count); + } + + req = level; + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_PBF_GET_P1HI_P1LO_INFO, 0, req, + &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CONFIG_TDP_PBF_GET_P1HI_P1LO_INFO resp:%x\n", cpu, + resp); + + pbf_info->p1_low = resp & 0xff; + pbf_info->p1_high = (resp & GENMASK(15, 8)) >> 8; + + req = level; + ret = isst_send_mbox_command( + cpu, CONFIG_TDP, CONFIG_TDP_PBF_GET_TDP_INFO, 0, req, &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CONFIG_TDP_PBF_GET_TDP_INFO resp:%x\n", cpu, resp); + + pbf_info->tdp = resp & 0xffff; + + req = level; + ret = isst_send_mbox_command( + cpu, CONFIG_TDP, CONFIG_TDP_PBF_GET_TJ_MAX_INFO, 0, req, &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CONFIG_TDP_PBF_GET_TJ_MAX_INFO resp:%x\n", cpu, + resp); + pbf_info->t_control = (resp >> 8) & 0xff; + pbf_info->t_prochot = resp & 0xff; + + return 0; +} + +void isst_get_pbf_info_complete(struct isst_pbf_info *pbf_info) +{ + free_cpu_set(pbf_info->core_cpumask); +} + +int isst_set_pbf_fact_status(int cpu, int pbf, int enable) +{ + struct isst_pkg_ctdp pkg_dev; + struct isst_pkg_ctdp_level_info ctdp_level; + int current_level; + unsigned int req = 0, resp; + int ret; + + ret = isst_get_ctdp_levels(cpu, &pkg_dev); + if (ret) + return ret; + + current_level = pkg_dev.current_level; + + ret = isst_get_ctdp_control(cpu, current_level, &ctdp_level); + if (ret) + return ret; + + if (pbf) { + if (ctdp_level.fact_enabled) + req = BIT(16); + + if (enable) + req |= BIT(17); + else + req &= ~BIT(17); + } else { + if (ctdp_level.pbf_enabled) + req = BIT(17); + + if (enable) + req |= BIT(16); + else + req &= ~BIT(16); + } + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_SET_TDP_CONTROL, 0, req, &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CONFIG_TDP_SET_TDP_CONTROL pbf/fact:%d req:%x\n", + cpu, pbf, req); + + return 0; +} + +int isst_get_fact_bucket_info(int cpu, int level, + struct isst_fact_bucket_info *bucket_info) +{ + unsigned int resp; + int i, k, ret; + + for (i = 0; i < 2; ++i) { + int j; + + ret = isst_send_mbox_command( + cpu, CONFIG_TDP, + CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_NUMCORES, 0, + (i << 8) | level, &resp); + if (ret) + return ret; + + debug_printf( + "cpu:%d CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_NUMCORES index:%d level:%d resp:%x\n", + cpu, i, level, resp); + + for (j = 0; j < 4; ++j) { + bucket_info[j + (i * 4)].high_priority_cores_count = + (resp >> (j * 8)) & 0xff; + } + } + + for (k = 0; k < 3; ++k) { + for (i = 0; i < 2; ++i) { + int j; + + ret = isst_send_mbox_command( + cpu, CONFIG_TDP, + CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_RATIOS, 0, + (k << 16) | (i << 8) | level, &resp); + if (ret) + return ret; + + debug_printf( + "cpu:%d CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_RATIOS index:%d level:%d avx:%d resp:%x\n", + cpu, i, level, k, resp); + + for (j = 0; j < 4; ++j) { + switch (k) { + case 0: + bucket_info[j + (i * 4)].sse_trl = + (resp >> (j * 8)) & 0xff; + break; + case 1: + bucket_info[j + (i * 4)].avx_trl = + (resp >> (j * 8)) & 0xff; + break; + case 2: + bucket_info[j + (i * 4)].avx512_trl = + (resp >> (j * 8)) & 0xff; + break; + default: + break; + } + } + } + } + + return 0; +} + +int isst_get_fact_info(int cpu, int level, struct isst_fact_info *fact_info) +{ + unsigned int resp; + int ret; + + ret = isst_send_mbox_command(cpu, CONFIG_TDP, + CONFIG_TDP_GET_FACT_LP_CLIPPING_RATIO, 0, + level, &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CONFIG_TDP_GET_FACT_LP_CLIPPING_RATIO resp:%x\n", + cpu, resp); + + fact_info->lp_clipping_ratio_license_sse = resp & 0xff; + fact_info->lp_clipping_ratio_license_avx2 = (resp >> 8) & 0xff; + fact_info->lp_clipping_ratio_license_avx512 = (resp >> 16) & 0xff; + + ret = isst_get_fact_bucket_info(cpu, level, fact_info->bucket_info); + + return ret; +} + +int isst_set_trl(int cpu, unsigned long long trl) +{ + int ret; + + if (!trl) + trl = 0xFFFFFFFFFFFFFFFFULL; + + ret = isst_send_msr_command(cpu, 0x1AD, 1, &trl); + if (ret) + return ret; + + return 0; +} + +int isst_set_trl_from_current_tdp(int cpu, unsigned long long trl) +{ + unsigned long long msr_trl; + int ret; + + if (trl) { + msr_trl = trl; + } else { + struct isst_pkg_ctdp pkg_dev; + int trl[8]; + int i; + + ret = isst_get_ctdp_levels(cpu, &pkg_dev); + if (ret) + return ret; + + ret = isst_get_get_trl(cpu, pkg_dev.current_level, 0, trl); + if (ret) + return ret; + + msr_trl = 0; + for (i = 0; i < 8; ++i) { + unsigned long long _trl = trl[i]; + + msr_trl |= (_trl << (i * 8)); + } + } + ret = isst_send_msr_command(cpu, 0x1AD, 1, &msr_trl); + if (ret) + return ret; + + return 0; +} + +/* Return 1 if locked */ +int isst_get_config_tdp_lock_status(int cpu) +{ + unsigned long long tdp_control = 0; + int ret; + + ret = isst_send_msr_command(cpu, 0x64b, 0, &tdp_control); + if (ret) + return ret; + + ret = !!(tdp_control & BIT(31)); + + return ret; +} + +void isst_get_process_ctdp_complete(int cpu, struct isst_pkg_ctdp *pkg_dev) +{ + int i; + + if (!pkg_dev->processed) + return; + + for (i = 0; i < pkg_dev->levels; ++i) { + struct isst_pkg_ctdp_level_info *ctdp_level; + + ctdp_level = &pkg_dev->ctdp_level[i]; + if (ctdp_level->pbf_support) + free_cpu_set(ctdp_level->pbf_info.core_cpumask); + free_cpu_set(ctdp_level->core_cpumask); + } +} + +int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev) +{ + int i, ret; + + if (pkg_dev->processed) + return 0; + + ret = isst_get_ctdp_levels(cpu, pkg_dev); + if (ret) + return ret; + + debug_printf("cpu: %d ctdp enable:%d current level: %d levels:%d\n", + cpu, pkg_dev->enabled, pkg_dev->current_level, + pkg_dev->levels); + + for (i = 0; i <= pkg_dev->levels; ++i) { + struct isst_pkg_ctdp_level_info *ctdp_level; + + if (tdp_level != 0xff && i != tdp_level) + continue; + + debug_printf("cpu:%d Get Information for TDP level:%d\n", cpu, + i); + ctdp_level = &pkg_dev->ctdp_level[i]; + + ctdp_level->processed = 1; + ctdp_level->level = i; + ctdp_level->control_cpu = cpu; + ctdp_level->pkg_id = get_physical_package_id(cpu); + ctdp_level->die_id = get_physical_die_id(cpu); + + ret = isst_get_ctdp_control(cpu, i, ctdp_level); + if (ret) + return ret; + + ret = isst_get_tdp_info(cpu, i, ctdp_level); + if (ret) + return ret; + + ret = isst_get_pwr_info(cpu, i, ctdp_level); + if (ret) + return ret; + + ret = isst_get_tjmax_info(cpu, i, ctdp_level); + if (ret) + return ret; + + ctdp_level->core_cpumask_size = + alloc_cpu_set(&ctdp_level->core_cpumask); + ret = isst_get_coremask_info(cpu, i, ctdp_level); + if (ret) + return ret; + + ret = isst_get_get_trl(cpu, i, 0, + ctdp_level->trl_sse_active_cores); + if (ret) + return ret; + + ret = isst_get_get_trl(cpu, i, 1, + ctdp_level->trl_avx_active_cores); + if (ret) + return ret; + + ret = isst_get_get_trl(cpu, i, 2, + ctdp_level->trl_avx_512_active_cores); + if (ret) + return ret; + + if (ctdp_level->pbf_support) { + ret = isst_get_pbf_info(cpu, i, &ctdp_level->pbf_info); + if (!ret) + ctdp_level->pbf_found = 1; + } + + if (ctdp_level->fact_support) { + ret = isst_get_fact_info(cpu, i, + &ctdp_level->fact_info); + if (ret) + return ret; + } + } + + pkg_dev->processed = 1; + + return 0; +} + +int isst_pm_qos_config(int cpu, int enable_clos, int priority_type) +{ + unsigned int req, resp; + int ret; + + ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_QOS_CONFIG, 0, 0, + &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CLOS_PM_QOS_CONFIG resp:%x\n", cpu, resp); + + req = resp; + + if (enable_clos) + req = req | BIT(1); + else + req = req & ~BIT(1); + + if (priority_type) + req = req | BIT(2); + else + req = req & ~BIT(2); + + ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_QOS_CONFIG, + BIT(MBOX_CMD_WRITE_BIT), req, &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CLOS_PM_QOS_CONFIG priority type:%d req:%x\n", cpu, + priority_type, req); + + return 0; +} + +int isst_pm_get_clos(int cpu, int clos, struct isst_clos_config *clos_config) +{ + unsigned int resp; + int ret; + + ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_CLOS, clos, 0, + &resp); + if (ret) + return ret; + + clos_config->pkg_id = get_physical_package_id(cpu); + clos_config->die_id = get_physical_die_id(cpu); + + clos_config->epp = resp & 0x0f; + clos_config->clos_prop_prio = (resp >> 4) & 0x0f; + clos_config->clos_min = (resp >> 8) & 0xff; + clos_config->clos_max = (resp >> 16) & 0xff; + clos_config->clos_desired = (resp >> 24) & 0xff; + + return 0; +} + +int isst_set_clos(int cpu, int clos, struct isst_clos_config *clos_config) +{ + unsigned int req, resp; + unsigned int param; + int ret; + + req = clos_config->epp & 0x0f; + req |= (clos_config->clos_prop_prio & 0x0f) << 4; + req |= (clos_config->clos_min & 0xff) << 8; + req |= (clos_config->clos_max & 0xff) << 16; + req |= (clos_config->clos_desired & 0xff) << 24; + + param = BIT(MBOX_CMD_WRITE_BIT) | clos; + + ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_CLOS, param, req, + &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CLOS_PM_CLOS param:%x req:%x\n", cpu, param, req); + + return 0; +} + +int isst_clos_get_assoc_status(int cpu, int *clos_id) +{ + unsigned int resp; + unsigned int param; + int core_id, ret; + + core_id = find_phy_core_num(cpu); + param = core_id; + + ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PQR_ASSOC, param, 0, + &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CLOS_PQR_ASSOC param:%x resp:%x\n", cpu, param, + resp); + *clos_id = (resp >> 16) & 0x03; + + return 0; +} + +int isst_clos_associate(int cpu, int clos_id) +{ + unsigned int req, resp; + unsigned int param; + int core_id, ret; + + req = (clos_id & 0x03) << 16; + core_id = find_phy_core_num(cpu); + param = BIT(MBOX_CMD_WRITE_BIT) | core_id; + + ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PQR_ASSOC, param, + req, &resp); + if (ret) + return ret; + + debug_printf("cpu:%d CLOS_PQR_ASSOC param:%x req:%x\n", cpu, param, + req); + + return 0; +} diff --git a/tools/power/x86/intel-speed-select/isst-display.c b/tools/power/x86/intel-speed-select/isst-display.c new file mode 100644 index 000000000000..f368b8323742 --- /dev/null +++ b/tools/power/x86/intel-speed-select/isst-display.c @@ -0,0 +1,479 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel dynamic_speed_select -- Enumerate and control features + * Copyright (c) 2019 Intel Corporation. + */ + +#include "isst.h" + +#define DISP_FREQ_MULTIPLIER 100000 + +static void printcpumask(int str_len, char *str, int mask_size, + cpu_set_t *cpu_mask) +{ + int i, max_cpus = get_topo_max_cpus(); + unsigned int *mask; + int size, index, curr_index; + + size = max_cpus / (sizeof(unsigned int) * 8); + if (max_cpus % (sizeof(unsigned int) * 8)) + size++; + + mask = calloc(size, sizeof(unsigned int)); + if (!mask) + return; + + for (i = 0; i < max_cpus; ++i) { + int mask_index, bit_index; + + if (!CPU_ISSET_S(i, mask_size, cpu_mask)) + continue; + + mask_index = i / (sizeof(unsigned int) * 8); + bit_index = i % (sizeof(unsigned int) * 8); + mask[mask_index] |= BIT(bit_index); + } + + curr_index = 0; + for (i = size - 1; i >= 0; --i) { + index = snprintf(&str[curr_index], str_len - curr_index, "%08x", + mask[i]); + curr_index += index; + if (i) { + strncat(&str[curr_index], ",", str_len - curr_index); + curr_index++; + } + } + + free(mask); +} + +static void format_and_print_txt(FILE *outf, int level, char *header, + char *value) +{ + char *spaces = " "; + static char delimiters[256]; + int i, j = 0; + + if (!level) + return; + + if (level == 1) { + strcpy(delimiters, " "); + } else { + for (i = 0; i < level - 1; ++i) + j += snprintf(&delimiters[j], sizeof(delimiters) - j, + "%s", spaces); + } + + if (header && value) { + fprintf(outf, "%s", delimiters); + fprintf(outf, "%s:%s\n", header, value); + } else if (header) { + fprintf(outf, "%s", delimiters); + fprintf(outf, "%s\n", header); + } +} + +static int last_level; +static void format_and_print(FILE *outf, int level, char *header, char *value) +{ + char *spaces = " "; + static char delimiters[256]; + int i; + + if (!out_format_is_json()) { + format_and_print_txt(outf, level, header, value); + return; + } + + if (level == 0) { + if (header) + fprintf(outf, "{"); + else + fprintf(outf, "\n}\n"); + + } else { + int j = 0; + + for (i = 0; i < level; ++i) + j += snprintf(&delimiters[j], sizeof(delimiters) - j, + "%s", spaces); + + if (last_level == level) + fprintf(outf, ",\n"); + + if (value) { + if (last_level != level) + fprintf(outf, "\n"); + + fprintf(outf, "%s\"%s\": ", delimiters, header); + fprintf(outf, "\"%s\"", value); + } else { + for (i = last_level - 1; i >= level; --i) { + int k = 0; + + for (j = i; j > 0; --j) + k += snprintf(&delimiters[k], + sizeof(delimiters) - k, + "%s", spaces); + if (i == level && header) + fprintf(outf, "\n%s},", delimiters); + else + fprintf(outf, "\n%s}", delimiters); + } + if (abs(last_level - level) < 3) + fprintf(outf, "\n"); + if (header) + fprintf(outf, "%s\"%s\": {", delimiters, + header); + } + } + + last_level = level; +} + +static void print_packag_info(int cpu, FILE *outf) +{ + char header[256]; + + snprintf(header, sizeof(header), "package-%d", + get_physical_package_id(cpu)); + format_and_print(outf, 1, header, NULL); + snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu)); + format_and_print(outf, 2, header, NULL); + snprintf(header, sizeof(header), "cpu-%d", cpu); + format_and_print(outf, 3, header, NULL); +} + +static void _isst_pbf_display_information(int cpu, FILE *outf, int level, + struct isst_pbf_info *pbf_info, + int disp_level) +{ + char header[256]; + char value[256]; + + snprintf(header, sizeof(header), "speed-select-base-freq"); + format_and_print(outf, disp_level, header, NULL); + + snprintf(header, sizeof(header), "high-priority-base-frequency(KHz)"); + snprintf(value, sizeof(value), "%d", + pbf_info->p1_high * DISP_FREQ_MULTIPLIER); + format_and_print(outf, disp_level + 1, header, value); + + snprintf(header, sizeof(header), "high-priority-cpu-mask"); + printcpumask(sizeof(value), value, pbf_info->core_cpumask_size, + pbf_info->core_cpumask); + format_and_print(outf, disp_level + 1, header, value); + + snprintf(header, sizeof(header), "low-priority-base-frequency(KHz)"); + snprintf(value, sizeof(value), "%d", + pbf_info->p1_low * DISP_FREQ_MULTIPLIER); + format_and_print(outf, disp_level + 1, header, value); + + snprintf(header, sizeof(header), "tjunction-temperature(C)"); + snprintf(value, sizeof(value), "%d", pbf_info->t_prochot); + format_and_print(outf, disp_level + 1, header, value); + + snprintf(header, sizeof(header), "thermal-design-power(W)"); + snprintf(value, sizeof(value), "%d", pbf_info->tdp); + format_and_print(outf, disp_level + 1, header, value); +} + +static void _isst_fact_display_information(int cpu, FILE *outf, int level, + int fact_bucket, int fact_avx, + struct isst_fact_info *fact_info, + int base_level) +{ + struct isst_fact_bucket_info *bucket_info = fact_info->bucket_info; + char header[256]; + char value[256]; + int j; + + snprintf(header, sizeof(header), "speed-select-turbo-freq"); + format_and_print(outf, base_level, header, NULL); + for (j = 0; j < ISST_FACT_MAX_BUCKETS; ++j) { + if (fact_bucket != 0xff && fact_bucket != j) + continue; + + if (!bucket_info[j].high_priority_cores_count) + break; + + snprintf(header, sizeof(header), "bucket-%d", j); + format_and_print(outf, base_level + 1, header, NULL); + + snprintf(header, sizeof(header), "high-priority-cores-count"); + snprintf(value, sizeof(value), "%d", + bucket_info[j].high_priority_cores_count); + format_and_print(outf, base_level + 2, header, value); + + if (fact_avx & 0x01) { + snprintf(header, sizeof(header), + "high-priority-max-frequency(KHz)"); + snprintf(value, sizeof(value), "%d", + bucket_info[j].sse_trl * DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 2, header, value); + } + + if (fact_avx & 0x02) { + snprintf(header, sizeof(header), + "high-priority-max-avx2-frequency(KHz)"); + snprintf(value, sizeof(value), "%d", + bucket_info[j].avx_trl * DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 2, header, value); + } + + if (fact_avx & 0x04) { + snprintf(header, sizeof(header), + "high-priority-max-avx512-frequency(KHz)"); + snprintf(value, sizeof(value), "%d", + bucket_info[j].avx512_trl * + DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 2, header, value); + } + } + snprintf(header, sizeof(header), + "speed-select-turbo-freq-clip-frequencies"); + format_and_print(outf, base_level + 1, header, NULL); + snprintf(header, sizeof(header), "low-priority-max-frequency(KHz)"); + snprintf(value, sizeof(value), "%d", + fact_info->lp_clipping_ratio_license_sse * + DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 2, header, value); + snprintf(header, sizeof(header), + "low-priority-max-avx2-frequency(KHz)"); + snprintf(value, sizeof(value), "%d", + fact_info->lp_clipping_ratio_license_avx2 * + DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 2, header, value); + snprintf(header, sizeof(header), + "low-priority-max-avx512-frequency(KHz)"); + snprintf(value, sizeof(value), "%d", + fact_info->lp_clipping_ratio_license_avx512 * + DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 2, header, value); +} + +void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level, + struct isst_pkg_ctdp *pkg_dev) +{ + char header[256]; + char value[256]; + int i, base_level = 1; + + print_packag_info(cpu, outf); + + for (i = 0; i <= pkg_dev->levels; ++i) { + struct isst_pkg_ctdp_level_info *ctdp_level; + int j; + + ctdp_level = &pkg_dev->ctdp_level[i]; + if (!ctdp_level->processed) + continue; + + snprintf(header, sizeof(header), "perf-profile-level-%d", + ctdp_level->level); + format_and_print(outf, base_level + 3, header, NULL); + + snprintf(header, sizeof(header), "cpu-count"); + j = get_cpu_count(get_physical_die_id(cpu), + get_physical_die_id(cpu)); + snprintf(value, sizeof(value), "%d", j); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), "enable-cpu-mask"); + printcpumask(sizeof(value), value, + ctdp_level->core_cpumask_size, + ctdp_level->core_cpumask); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), "thermal-design-power-ratio"); + snprintf(value, sizeof(value), "%d", ctdp_level->tdp_ratio); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), "base-frequency(KHz)"); + snprintf(value, sizeof(value), "%d", + ctdp_level->tdp_ratio * DISP_FREQ_MULTIPLIER); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), + "speed-select-turbo-freq-support"); + snprintf(value, sizeof(value), "%d", ctdp_level->fact_support); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), + "speed-select-base-freq-support"); + snprintf(value, sizeof(value), "%d", ctdp_level->pbf_support); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), + "speed-select-base-freq-enabled"); + snprintf(value, sizeof(value), "%d", ctdp_level->pbf_enabled); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), + "speed-select-turbo-freq-enabled"); + snprintf(value, sizeof(value), "%d", ctdp_level->fact_enabled); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), "thermal-design-power(W)"); + snprintf(value, sizeof(value), "%d", ctdp_level->pkg_tdp); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), "tjunction-max(C)"); + snprintf(value, sizeof(value), "%d", ctdp_level->t_proc_hot); + format_and_print(outf, base_level + 4, header, value); + + snprintf(header, sizeof(header), "turbo-ratio-limits-sse"); + format_and_print(outf, base_level + 4, header, NULL); + for (j = 0; j < 8; ++j) { + snprintf(header, sizeof(header), "bucket-%d", j); + format_and_print(outf, base_level + 5, header, NULL); + + snprintf(header, sizeof(header), "core-count"); + snprintf(value, sizeof(value), "%d", j); + format_and_print(outf, base_level + 6, header, value); + + snprintf(header, sizeof(header), "turbo-ratio"); + snprintf(value, sizeof(value), "%d", + ctdp_level->trl_sse_active_cores[j]); + format_and_print(outf, base_level + 6, header, value); + } + snprintf(header, sizeof(header), "turbo-ratio-limits-avx"); + format_and_print(outf, base_level + 4, header, NULL); + for (j = 0; j < 8; ++j) { + snprintf(header, sizeof(header), "bucket-%d", j); + format_and_print(outf, base_level + 5, header, NULL); + + snprintf(header, sizeof(header), "core-count"); + snprintf(value, sizeof(value), "%d", j); + format_and_print(outf, base_level + 6, header, value); + + snprintf(header, sizeof(header), "turbo-ratio"); + snprintf(value, sizeof(value), "%d", + ctdp_level->trl_avx_active_cores[j]); + format_and_print(outf, base_level + 6, header, value); + } + + snprintf(header, sizeof(header), "turbo-ratio-limits-avx512"); + format_and_print(outf, base_level + 4, header, NULL); + for (j = 0; j < 8; ++j) { + snprintf(header, sizeof(header), "bucket-%d", j); + format_and_print(outf, base_level + 5, header, NULL); + + snprintf(header, sizeof(header), "core-count"); + snprintf(value, sizeof(value), "%d", j); + format_and_print(outf, base_level + 6, header, value); + + snprintf(header, sizeof(header), "turbo-ratio"); + snprintf(value, sizeof(value), "%d", + ctdp_level->trl_avx_512_active_cores[j]); + format_and_print(outf, base_level + 6, header, value); + } + if (ctdp_level->pbf_support) + _isst_pbf_display_information(cpu, outf, i, + &ctdp_level->pbf_info, + base_level + 4); + if (ctdp_level->fact_support) + _isst_fact_display_information(cpu, outf, i, 0xff, 0xff, + &ctdp_level->fact_info, + base_level + 4); + } + + format_and_print(outf, 1, NULL, NULL); +} + +void isst_ctdp_display_information_start(FILE *outf) +{ + last_level = 0; + format_and_print(outf, 0, "start", NULL); +} + +void isst_ctdp_display_information_end(FILE *outf) +{ + format_and_print(outf, 0, NULL, NULL); +} + +void isst_pbf_display_information(int cpu, FILE *outf, int level, + struct isst_pbf_info *pbf_info) +{ + print_packag_info(cpu, outf); + _isst_pbf_display_information(cpu, outf, level, pbf_info, 4); + format_and_print(outf, 1, NULL, NULL); +} + +void isst_fact_display_information(int cpu, FILE *outf, int level, + int fact_bucket, int fact_avx, + struct isst_fact_info *fact_info) +{ + print_packag_info(cpu, outf); + _isst_fact_display_information(cpu, outf, level, fact_bucket, fact_avx, + fact_info, 4); + format_and_print(outf, 1, NULL, NULL); +} + +void isst_clos_display_information(int cpu, FILE *outf, int clos, + struct isst_clos_config *clos_config) +{ + char header[256]; + char value[256]; + + snprintf(header, sizeof(header), "package-%d", + get_physical_package_id(cpu)); + format_and_print(outf, 1, header, NULL); + snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu)); + format_and_print(outf, 2, header, NULL); + snprintf(header, sizeof(header), "cpu-%d", cpu); + format_and_print(outf, 3, header, NULL); + + snprintf(header, sizeof(header), "core-power"); + format_and_print(outf, 4, header, NULL); + + snprintf(header, sizeof(header), "clos"); + snprintf(value, sizeof(value), "%d", clos); + format_and_print(outf, 5, header, value); + + snprintf(header, sizeof(header), "epp"); + snprintf(value, sizeof(value), "%d", clos_config->epp); + format_and_print(outf, 5, header, value); + + snprintf(header, sizeof(header), "clos-proportional-priority"); + snprintf(value, sizeof(value), "%d", clos_config->clos_prop_prio); + format_and_print(outf, 5, header, value); + + snprintf(header, sizeof(header), "clos-min"); + snprintf(value, sizeof(value), "%d", clos_config->clos_min); + format_and_print(outf, 5, header, value); + + snprintf(header, sizeof(header), "clos-max"); + snprintf(value, sizeof(value), "%d", clos_config->clos_max); + format_and_print(outf, 5, header, value); + + snprintf(header, sizeof(header), "clos-desired"); + snprintf(value, sizeof(value), "%d", clos_config->clos_desired); + format_and_print(outf, 5, header, value); + + format_and_print(outf, 1, NULL, NULL); +} + +void isst_display_result(int cpu, FILE *outf, char *feature, char *cmd, + int result) +{ + char header[256]; + char value[256]; + + snprintf(header, sizeof(header), "package-%d", + get_physical_package_id(cpu)); + format_and_print(outf, 1, header, NULL); + snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu)); + format_and_print(outf, 2, header, NULL); + snprintf(header, sizeof(header), "cpu-%d", cpu); + format_and_print(outf, 3, header, NULL); + snprintf(header, sizeof(header), "%s", feature); + format_and_print(outf, 4, header, NULL); + snprintf(header, sizeof(header), "%s", cmd); + snprintf(value, sizeof(value), "%d", result); + format_and_print(outf, 5, header, value); + + format_and_print(outf, 1, NULL, NULL); +} diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h new file mode 100644 index 000000000000..221881761609 --- /dev/null +++ b/tools/power/x86/intel-speed-select/isst.h @@ -0,0 +1,231 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Intel Speed Select -- Enumerate and control features + * Copyright (c) 2019 Intel Corporation. + */ + +#ifndef _ISST_H_ +#define _ISST_H_ + +#include <stdio.h> +#include <unistd.h> +#include <sys/types.h> +#include <sched.h> +#include <sys/stat.h> +#include <sys/resource.h> +#include <getopt.h> +#include <err.h> +#include <fcntl.h> +#include <signal.h> +#include <sys/time.h> +#include <limits.h> +#include <stdlib.h> +#include <string.h> +#include <cpuid.h> +#include <dirent.h> +#include <errno.h> + +#include <stdarg.h> +#include <sys/ioctl.h> + +#define BIT(x) (1 << (x)) +#define GENMASK(h, l) (((~0UL) << (l)) & (~0UL >> (sizeof(long) * 8 - 1 - (h)))) +#define GENMASK_ULL(h, l) \ + (((~0ULL) << (l)) & (~0ULL >> (sizeof(long long) * 8 - 1 - (h)))) + +#define CONFIG_TDP 0x7f +#define CONFIG_TDP_GET_LEVELS_INFO 0x00 +#define CONFIG_TDP_GET_TDP_CONTROL 0x01 +#define CONFIG_TDP_SET_TDP_CONTROL 0x02 +#define CONFIG_TDP_GET_TDP_INFO 0x03 +#define CONFIG_TDP_GET_PWR_INFO 0x04 +#define CONFIG_TDP_GET_TJMAX_INFO 0x05 +#define CONFIG_TDP_GET_CORE_MASK 0x06 +#define CONFIG_TDP_GET_TURBO_LIMIT_RATIOS 0x07 +#define CONFIG_TDP_SET_LEVEL 0x08 +#define CONFIG_TDP_GET_UNCORE_P0_P1_INFO 0X09 +#define CONFIG_TDP_GET_P1_INFO 0x0a +#define CONFIG_TDP_GET_MEM_FREQ 0x0b + +#define CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_NUMCORES 0x10 +#define CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_RATIOS 0x11 +#define CONFIG_TDP_GET_FACT_LP_CLIPPING_RATIO 0x12 + +#define CONFIG_TDP_PBF_GET_CORE_MASK_INFO 0x20 +#define CONFIG_TDP_PBF_GET_P1HI_P1LO_INFO 0x21 +#define CONFIG_TDP_PBF_GET_TJ_MAX_INFO 0x22 +#define CONFIG_TDP_PBF_GET_TDP_INFO 0X23 + +#define CONFIG_CLOS 0xd0 +#define CLOS_PQR_ASSOC 0x00 +#define CLOS_PM_CLOS 0x01 +#define CLOS_PM_QOS_CONFIG 0x02 +#define CLOS_STATUS 0x03 + +#define MBOX_CMD_WRITE_BIT 0x08 + +#define PM_QOS_INFO_OFFSET 0x00 +#define PM_QOS_CONFIG_OFFSET 0x04 +#define PM_CLOS_OFFSET 0x08 +#define PQR_ASSOC_OFFSET 0x20 + +struct isst_clos_config { + int pkg_id; + int die_id; + unsigned char epp; + unsigned char clos_prop_prio; + unsigned char clos_min; + unsigned char clos_max; + unsigned char clos_desired; +}; + +struct isst_fact_bucket_info { + int high_priority_cores_count; + int sse_trl; + int avx_trl; + int avx512_trl; +}; + +struct isst_pbf_info { + int pbf_acticated; + int pbf_available; + size_t core_cpumask_size; + cpu_set_t *core_cpumask; + int p1_high; + int p1_low; + int t_control; + int t_prochot; + int tdp; +}; + +#define ISST_TRL_MAX_ACTIVE_CORES 8 +#define ISST_FACT_MAX_BUCKETS 8 +struct isst_fact_info { + int lp_clipping_ratio_license_sse; + int lp_clipping_ratio_license_avx2; + int lp_clipping_ratio_license_avx512; + struct isst_fact_bucket_info bucket_info[ISST_FACT_MAX_BUCKETS]; +}; + +struct isst_pkg_ctdp_level_info { + int processed; + int control_cpu; + int pkg_id; + int die_id; + int level; + int fact_support; + int pbf_support; + int fact_enabled; + int pbf_enabled; + int tdp_ratio; + int active; + int tdp_control; + int pkg_tdp; + int pkg_min_power; + int pkg_max_power; + int fact; + int t_proc_hot; + int uncore_p0; + int uncore_p1; + int sse_p1; + int avx2_p1; + int avx512_p1; + int mem_freq; + size_t core_cpumask_size; + cpu_set_t *core_cpumask; + int cpu_count; + int trl_sse_active_cores[ISST_TRL_MAX_ACTIVE_CORES]; + int trl_avx_active_cores[ISST_TRL_MAX_ACTIVE_CORES]; + int trl_avx_512_active_cores[ISST_TRL_MAX_ACTIVE_CORES]; + int kobj_bucket_index; + int active_bucket; + int fact_max_index; + int fact_max_config; + int pbf_found; + int pbf_active; + struct isst_pbf_info pbf_info; + struct isst_fact_info fact_info; +}; + +#define ISST_MAX_TDP_LEVELS (4 + 1) /* +1 for base config */ +struct isst_pkg_ctdp { + int locked; + int version; + int processed; + int levels; + int current_level; + int enabled; + struct isst_pkg_ctdp_level_info ctdp_level[ISST_MAX_TDP_LEVELS]; +}; + +extern int get_topo_max_cpus(void); +extern int get_cpu_count(int pkg_id, int die_id); + +/* Common interfaces */ +extern void debug_printf(const char *format, ...); +extern int out_format_is_json(void); +extern int get_physical_package_id(int cpu); +extern int get_physical_die_id(int cpu); +extern size_t alloc_cpu_set(cpu_set_t **cpu_set); +extern void free_cpu_set(cpu_set_t *cpu_set); +extern int find_logical_cpu(int pkg_id, int die_id, int phy_cpu); +extern int find_phy_cpu_num(int logical_cpu); +extern int find_phy_core_num(int logical_cpu); +extern void set_cpu_mask_from_punit_coremask(int cpu, + unsigned long long core_mask, + size_t core_cpumask_size, + cpu_set_t *core_cpumask, + int *cpu_cnt); + +extern int isst_send_mbox_command(unsigned int cpu, unsigned char command, + unsigned char sub_command, + unsigned int write, + unsigned int req_data, unsigned int *resp); + +extern int isst_send_msr_command(unsigned int cpu, unsigned int command, + int write, unsigned long long *req_resp); + +extern int isst_get_ctdp_levels(int cpu, struct isst_pkg_ctdp *pkg_dev); +extern int isst_get_process_ctdp(int cpu, int tdp_level, + struct isst_pkg_ctdp *pkg_dev); +extern void isst_get_process_ctdp_complete(int cpu, + struct isst_pkg_ctdp *pkg_dev); +extern void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level, + struct isst_pkg_ctdp *pkg_dev); +extern void isst_ctdp_display_information_start(FILE *outf); +extern void isst_ctdp_display_information_end(FILE *outf); +extern void isst_pbf_display_information(int cpu, FILE *outf, int level, + struct isst_pbf_info *info); +extern int isst_set_tdp_level(int cpu, int tdp_level); +extern int isst_set_tdp_level_msr(int cpu, int tdp_level); +extern int isst_set_pbf_fact_status(int cpu, int pbf, int enable); +extern int isst_get_pbf_info(int cpu, int level, + struct isst_pbf_info *pbf_info); +extern void isst_get_pbf_info_complete(struct isst_pbf_info *pbf_info); +extern int isst_get_fact_info(int cpu, int level, + struct isst_fact_info *fact_info); +extern int isst_get_fact_bucket_info(int cpu, int level, + struct isst_fact_bucket_info *bucket_info); +extern void isst_fact_display_information(int cpu, FILE *outf, int level, + int fact_bucket, int fact_avx, + struct isst_fact_info *fact_info); +extern int isst_set_trl(int cpu, unsigned long long trl); +extern int isst_set_trl_from_current_tdp(int cpu, unsigned long long trl); +extern int isst_get_config_tdp_lock_status(int cpu); + +extern int isst_pm_qos_config(int cpu, int enable_clos, int priority_type); +extern int isst_pm_get_clos(int cpu, int clos, + struct isst_clos_config *clos_config); +extern int isst_set_clos(int cpu, int clos, + struct isst_clos_config *clos_config); +extern int isst_clos_associate(int cpu, int clos); +extern int isst_clos_get_assoc_status(int cpu, int *clos_id); +extern void isst_clos_display_information(int cpu, FILE *outf, int clos, + struct isst_clos_config *clos_config); + +extern int isst_read_reg(unsigned short reg, unsigned int *val); +extern int isst_write_reg(int reg, unsigned int val); + +extern void isst_display_result(int cpu, FILE *outf, char *feature, char *cmd, + int result); +#endif diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 076df22e4bda..cd040b5abffe 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -100,25 +100,60 @@ static void nfit_test_kill(void *_pgmap) { struct dev_pagemap *pgmap = _pgmap; - WARN_ON(!pgmap || !pgmap->ref || !pgmap->kill || !pgmap->cleanup); - pgmap->kill(pgmap->ref); - pgmap->cleanup(pgmap->ref); + WARN_ON(!pgmap || !pgmap->ref); + + if (pgmap->ops && pgmap->ops->kill) + pgmap->ops->kill(pgmap); + else + percpu_ref_kill(pgmap->ref); + + if (pgmap->ops && pgmap->ops->cleanup) { + pgmap->ops->cleanup(pgmap); + } else { + wait_for_completion(&pgmap->done); + percpu_ref_exit(pgmap->ref); + } +} + +static void dev_pagemap_percpu_release(struct percpu_ref *ref) +{ + struct dev_pagemap *pgmap = + container_of(ref, struct dev_pagemap, internal_ref); + + complete(&pgmap->done); } void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { + int error; resource_size_t offset = pgmap->res.start; struct nfit_test_resource *nfit_res = get_nfit_res(offset); - if (nfit_res) { - int rc; - - rc = devm_add_action_or_reset(dev, nfit_test_kill, pgmap); - if (rc) - return ERR_PTR(rc); - return nfit_res->buf + offset - nfit_res->res.start; + if (!nfit_res) + return devm_memremap_pages(dev, pgmap); + + pgmap->dev = dev; + if (!pgmap->ref) { + if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) + return ERR_PTR(-EINVAL); + + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->internal_ref, + dev_pagemap_percpu_release, 0, GFP_KERNEL); + if (error) + return ERR_PTR(error); + pgmap->ref = &pgmap->internal_ref; + } else { + if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { + WARN(1, "Missing reference count teardown definition\n"); + return ERR_PTR(-EINVAL); + } } - return devm_memremap_pages(dev, pgmap); + + error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap); + if (error) + return ERR_PTR(error); + return nfit_res->buf + offset - nfit_res->res.start; } EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 9781ca79794a..25b43a8c2b15 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -74,7 +74,7 @@ endif # Append kselftest to KBUILD_OUTPUT to avoid cluttering # KBUILD_OUTPUT with selftest objects and headers installed # by selftests Makefile or lib.mk. -ifneq ($(KBUILD_SRC),) +ifdef building_out_of_srctree override LDFLAGS = endif diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 2620406a53ec..11c9c62c3362 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +include ../../../../scripts/Kbuild.include +include ../../../scripts/Makefile.arch LIBDIR := ../../../lib BPFDIR := $(LIBDIR)/bpf @@ -81,13 +83,14 @@ all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/urandom_read: $(OUTPUT)/%: %.c $(CC) -o $@ $< -Wl,--build-id -$(OUTPUT)/test_maps: map_tests/*.c +$(OUTPUT)/test_stub.o: test_stub.c + $(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) -c -o $@ $< BPFOBJ := $(OUTPUT)/libbpf.a -$(TEST_GEN_PROGS): test_stub.o $(BPFOBJ) +$(TEST_GEN_PROGS): $(OUTPUT)/test_stub.o $(BPFOBJ) -$(TEST_GEN_PROGS_EXTENDED): test_stub.o $(OUTPUT)/libbpf.a +$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(OUTPUT)/libbpf.a $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c $(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c @@ -138,7 +141,8 @@ CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ $(CLANG_SYS_INCLUDES) \ - -Wno-compare-distinct-pointer-types + -Wno-compare-distinct-pointer-types \ + -D__TARGET_ARCH_$(SRCARCH) $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline @@ -172,6 +176,7 @@ endif endif TEST_PROGS_CFLAGS := -I. -I$(OUTPUT) +TEST_MAPS_CFLAGS := -I. -I$(OUTPUT) TEST_VERIFIER_CFLAGS := -I. -I$(OUTPUT) -Iverifier ifneq ($(SUBREG_CODEGEN),) @@ -180,12 +185,12 @@ TEST_CUSTOM_PROGS += $(ALU32_BUILD_DIR)/test_progs_32 $(ALU32_BUILD_DIR): mkdir -p $@ -$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read +$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read | $(ALU32_BUILD_DIR) cp $< $@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\ - $(ALU32_BUILD_DIR) \ - $(ALU32_BUILD_DIR)/urandom_read + $(ALU32_BUILD_DIR)/urandom_read \ + | $(ALU32_BUILD_DIR) $(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) \ -o $(ALU32_BUILD_DIR)/test_progs_32 \ test_progs.c test_stub.c trace_helpers.c prog_tests/*.c \ @@ -194,10 +199,10 @@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\ $(ALU32_BUILD_DIR)/test_progs_32: $(PROG_TESTS_H) $(ALU32_BUILD_DIR)/test_progs_32: prog_tests/*.c -$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR) \ - $(ALU32_BUILD_DIR)/test_progs_32 - $(CLANG) $(CLANG_FLAGS) \ - -O2 -target bpf -emit-llvm -c $< -o - | \ +$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR)/test_progs_32 \ + | $(ALU32_BUILD_DIR) + ($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \ + echo "clang failed") | \ $(LLC) -march=bpf -mattr=+alu32 -mcpu=$(CPU) $(LLC_FLAGS) \ -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) @@ -208,32 +213,30 @@ endif # Have one program compiled without "-target bpf" to test whether libbpf loads # it successfully $(OUTPUT)/test_xdp.o: progs/test_xdp.c - $(CLANG) $(CLANG_FLAGS) \ - -O2 -emit-llvm -c $< -o - | \ + ($(CLANG) $(CLANG_FLAGS) -O2 -emit-llvm -c $< -o - || \ + echo "clang failed") | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) $(BTF_PAHOLE) -J $@ endif $(OUTPUT)/%.o: progs/%.c - $(CLANG) $(CLANG_FLAGS) \ - -O2 -target bpf -emit-llvm -c $< -o - | \ + ($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \ + echo "clang failed") | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) $(BTF_PAHOLE) -J $@ endif -PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h -test_progs.c: $(PROG_TESTS_H) -$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) -$(OUTPUT)/test_progs: prog_tests/*.c - PROG_TESTS_DIR = $(OUTPUT)/prog_tests $(PROG_TESTS_DIR): mkdir -p $@ - +PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h PROG_TESTS_FILES := $(wildcard prog_tests/*.c) -$(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) +test_progs.c: $(PROG_TESTS_H) +$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) +$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES) +$(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR) $(shell ( cd prog_tests/; \ echo '/* Generated header, do not edit */'; \ echo '#ifdef DECLARE'; \ @@ -246,15 +249,15 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) echo '#endif' \ ) > $(PROG_TESTS_H)) -TEST_MAPS_CFLAGS := -I. -I$(OUTPUT) MAP_TESTS_DIR = $(OUTPUT)/map_tests $(MAP_TESTS_DIR): mkdir -p $@ MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h +MAP_TESTS_FILES := $(wildcard map_tests/*.c) test_maps.c: $(MAP_TESTS_H) $(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS) -MAP_TESTS_FILES := $(wildcard map_tests/*.c) -$(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES) +$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_H) $(MAP_TESTS_FILES) +$(MAP_TESTS_H): $(MAP_TESTS_FILES) | $(MAP_TESTS_DIR) $(shell ( cd map_tests/; \ echo '/* Generated header, do not edit */'; \ echo '#ifdef DECLARE'; \ @@ -267,16 +270,15 @@ $(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES) echo '#endif' \ ) > $(MAP_TESTS_H)) -VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h -test_verifier.c: $(VERIFIER_TESTS_H) -$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) - VERIFIER_TESTS_DIR = $(OUTPUT)/verifier $(VERIFIER_TESTS_DIR): mkdir -p $@ - +VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h VERIFIER_TEST_FILES := $(wildcard verifier/*.c) -$(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES) +test_verifier.c: $(VERIFIER_TESTS_H) +$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) +$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H) +$(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR) $(shell ( cd verifier/; \ echo '/* Generated header, do not edit */'; \ echo '#ifdef FILL_ARRAY'; \ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 5a3d92c8bec8..f804f210244e 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -315,8 +315,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #if defined(__TARGET_ARCH_x86) #define bpf_target_x86 #define bpf_target_defined -#elif defined(__TARGET_ARCH_s930x) - #define bpf_target_s930x +#elif defined(__TARGET_ARCH_s390) + #define bpf_target_s390 #define bpf_target_defined #elif defined(__TARGET_ARCH_arm) #define bpf_target_arm @@ -341,8 +341,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #ifndef bpf_target_defined #if defined(__x86_64__) #define bpf_target_x86 -#elif defined(__s390x__) - #define bpf_target_s930x +#elif defined(__s390__) + #define bpf_target_s390 #elif defined(__arm__) #define bpf_target_arm #elif defined(__aarch64__) @@ -358,6 +358,7 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #if defined(bpf_target_x86) +#ifdef __KERNEL__ #define PT_REGS_PARM1(x) ((x)->di) #define PT_REGS_PARM2(x) ((x)->si) #define PT_REGS_PARM3(x) ((x)->dx) @@ -368,19 +369,49 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #define PT_REGS_RC(x) ((x)->ax) #define PT_REGS_SP(x) ((x)->sp) #define PT_REGS_IP(x) ((x)->ip) +#else +#ifdef __i386__ +/* i386 kernel is built with -mregparm=3 */ +#define PT_REGS_PARM1(x) ((x)->eax) +#define PT_REGS_PARM2(x) ((x)->edx) +#define PT_REGS_PARM3(x) ((x)->ecx) +#define PT_REGS_PARM4(x) 0 +#define PT_REGS_PARM5(x) 0 +#define PT_REGS_RET(x) ((x)->esp) +#define PT_REGS_FP(x) ((x)->ebp) +#define PT_REGS_RC(x) ((x)->eax) +#define PT_REGS_SP(x) ((x)->esp) +#define PT_REGS_IP(x) ((x)->eip) +#else +#define PT_REGS_PARM1(x) ((x)->rdi) +#define PT_REGS_PARM2(x) ((x)->rsi) +#define PT_REGS_PARM3(x) ((x)->rdx) +#define PT_REGS_PARM4(x) ((x)->rcx) +#define PT_REGS_PARM5(x) ((x)->r8) +#define PT_REGS_RET(x) ((x)->rsp) +#define PT_REGS_FP(x) ((x)->rbp) +#define PT_REGS_RC(x) ((x)->rax) +#define PT_REGS_SP(x) ((x)->rsp) +#define PT_REGS_IP(x) ((x)->rip) +#endif +#endif -#elif defined(bpf_target_s390x) +#elif defined(bpf_target_s390) -#define PT_REGS_PARM1(x) ((x)->gprs[2]) -#define PT_REGS_PARM2(x) ((x)->gprs[3]) -#define PT_REGS_PARM3(x) ((x)->gprs[4]) -#define PT_REGS_PARM4(x) ((x)->gprs[5]) -#define PT_REGS_PARM5(x) ((x)->gprs[6]) -#define PT_REGS_RET(x) ((x)->gprs[14]) -#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_RC(x) ((x)->gprs[2]) -#define PT_REGS_SP(x) ((x)->gprs[15]) -#define PT_REGS_IP(x) ((x)->psw.addr) +/* s390 provides user_pt_regs instead of struct pt_regs to userspace */ +struct pt_regs; +#define PT_REGS_S390 const volatile user_pt_regs +#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2]) +#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3]) +#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4]) +#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5]) +#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6]) +#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14]) +/* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11]) +#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2]) +#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15]) +#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr) #elif defined(bpf_target_arm) @@ -397,16 +428,20 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #elif defined(bpf_target_arm64) -#define PT_REGS_PARM1(x) ((x)->regs[0]) -#define PT_REGS_PARM2(x) ((x)->regs[1]) -#define PT_REGS_PARM3(x) ((x)->regs[2]) -#define PT_REGS_PARM4(x) ((x)->regs[3]) -#define PT_REGS_PARM5(x) ((x)->regs[4]) -#define PT_REGS_RET(x) ((x)->regs[30]) -#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_RC(x) ((x)->regs[0]) -#define PT_REGS_SP(x) ((x)->sp) -#define PT_REGS_IP(x) ((x)->pc) +/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ +struct pt_regs; +#define PT_REGS_ARM64 const volatile struct user_pt_regs +#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0]) +#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1]) +#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2]) +#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3]) +#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4]) +#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30]) +/* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29]) +#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0]) +#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp) +#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc) #elif defined(bpf_target_mips) @@ -452,10 +487,10 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #endif -#ifdef bpf_target_powerpc +#if defined(bpf_target_powerpc) #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP -#elif bpf_target_sparc +#elif defined(bpf_target_sparc) #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP #else diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index a4686395522c..5ecc267d98b0 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -21,12 +21,6 @@ ssize_t get_base_addr() { return -EINVAL; } -#ifdef __x86_64__ -#define SYS_KPROBE_NAME "__x64_sys_nanosleep" -#else -#define SYS_KPROBE_NAME "sys_nanosleep" -#endif - void test_attach_probe(void) { const char *kprobe_name = "kprobe/sys_nanosleep"; @@ -84,7 +78,7 @@ void test_attach_probe(void) kprobe_link = bpf_program__attach_kprobe(kprobe_prog, false /* retprobe */, - SYS_KPROBE_NAME); + SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", "err %ld\n", PTR_ERR(kprobe_link))) { kprobe_link = NULL; @@ -92,7 +86,7 @@ void test_attach_probe(void) } kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog, true /* retprobe */, - SYS_KPROBE_NAME); + SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe", "err %ld\n", PTR_ERR(kretprobe_link))) { kretprobe_link = NULL; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index 3f1ef95865ff..3003fddc0613 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -5,12 +5,6 @@ #include <sys/socket.h> #include <test_progs.h> -#ifdef __x86_64__ -#define SYS_KPROBE_NAME "__x64_sys_nanosleep" -#else -#define SYS_KPROBE_NAME "sys_nanosleep" -#endif - static void on_sample(void *ctx, int cpu, void *data, __u32 size) { int cpu_data = *(int *)data, duration = 0; @@ -56,7 +50,7 @@ void test_perf_buffer(void) /* attach kprobe */ link = bpf_program__attach_kprobe(prog, false /* retprobe */, - SYS_KPROBE_NAME); + SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link))) goto out_close; diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 67cea1686305..54218ee3c004 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -173,6 +173,18 @@ static int test_send_signal_tracepoint(void) return test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint"); } +static int test_send_signal_perf(void) +{ + struct perf_event_attr attr = { + .sample_period = 1, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + + return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, + "perf_sw_event"); +} + static int test_send_signal_nmi(void) { struct perf_event_attr attr = { @@ -181,8 +193,26 @@ static int test_send_signal_nmi(void) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, }; + int pmu_fd; + + /* Some setups (e.g. virtual machines) might run with hardware + * perf events disabled. If this is the case, skip this test. + */ + pmu_fd = syscall(__NR_perf_event_open, &attr, 0 /* pid */, + -1 /* cpu */, -1 /* group_fd */, 0 /* flags */); + if (pmu_fd == -1) { + if (errno == ENOENT) { + printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", + __func__); + return 0; + } + /* Let the test fail with a more informative message */ + } else { + close(pmu_fd); + } - return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, "perf_event"); + return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, + "perf_hw_event"); } void test_send_signal(void) @@ -190,6 +220,7 @@ void test_send_signal(void) int ret = 0; ret |= test_send_signal_tracepoint(); + ret |= test_send_signal_perf(); ret |= test_send_signal_nmi(); if (!ret) printf("test_send_signal:OK\n"); diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c index dea395af9ea9..7cdb7f878310 100644 --- a/tools/testing/selftests/bpf/progs/loop1.c +++ b/tools/testing/selftests/bpf/progs/loop1.c @@ -18,7 +18,7 @@ int nested_loops(volatile struct pt_regs* ctx) for (j = 0; j < 300; j++) for (i = 0; i < j; i++) { if (j & 1) - m = ctx->rax; + m = PT_REGS_RC(ctx); else m = j; sum += i * m; diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c index 0637bd8e8bcf..9b2f808a2863 100644 --- a/tools/testing/selftests/bpf/progs/loop2.c +++ b/tools/testing/selftests/bpf/progs/loop2.c @@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx) int i = 0; while (true) { - if (ctx->rax & 1) + if (PT_REGS_RC(ctx) & 1) i += 3; else i += 7; diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c index 30a0f6cba080..d727657d51e2 100644 --- a/tools/testing/selftests/bpf/progs/loop3.c +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx) __u64 i = 0, sum = 0; do { i++; - sum += ctx->rax; + sum += PT_REGS_RC(ctx); } while (i < 0x100000000ULL); return sum; } diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index d06b47a09097..33254b771384 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -47,11 +47,12 @@ struct { * issue and avoid complicated C programming massaging. * This is an acceptable workaround since there is one entry here. */ +typedef __u64 raw_stack_trace_t[2 * MAX_STACK_RAWTP]; struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(max_entries, 1); __type(key, __u32); - __u64 (*value)[2 * MAX_STACK_RAWTP]; + __type(value, raw_stack_trace_t); } rawdata_map SEC(".maps"); SEC("tracepoint/raw_syscalls/sys_enter") diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index bbfc8337b6f0..f5638e26865d 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -36,8 +36,7 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 128); __type(key, __u32); - /* there seems to be a bug in kernel not handling typedef properly */ - struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH]; + __type(value, stack_trace_t); } stack_amap SEC(".maps"); /* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */ diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index 803c15dc109d..fa0be3e10a10 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -35,7 +35,7 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 16384); __type(key, __u32); - __u64 (*value)[PERF_MAX_STACK_DEPTH]; + __type(value, stack_trace_t); } stack_amap SEC(".maps"); /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index dad8a7e33eaa..e88d7b9d65ab 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -14,6 +14,7 @@ #include <linux/tcp.h> #include <linux/udp.h> #include "bpf_helpers.h" +#include "bpf_endian.h" static __u32 rol32(__u32 word, unsigned int shift) { @@ -305,7 +306,7 @@ bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval, ip6h->nexthdr = IPPROTO_IPV6; ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0]; ip6h->payload_len = - __builtin_bswap16(pkt_bytes + sizeof(struct ipv6hdr)); + bpf_htons(pkt_bytes + sizeof(struct ipv6hdr)); ip6h->hop_limit = 4; ip6h->saddr.in6_u.u6_addr32[0] = 1; @@ -322,7 +323,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval, struct real_definition *dst, __u32 pkt_bytes) { - __u32 ip_suffix = __builtin_bswap16(pckt->flow.port16[0]); + __u32 ip_suffix = bpf_ntohs(pckt->flow.port16[0]); struct eth_hdr *new_eth; struct eth_hdr *old_eth; __u16 *next_iph_u16; @@ -352,7 +353,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval, iph->protocol = IPPROTO_IPIP; iph->check = 0; iph->tos = 1; - iph->tot_len = __builtin_bswap16(pkt_bytes + sizeof(struct iphdr)); + iph->tot_len = bpf_htons(pkt_bytes + sizeof(struct iphdr)); /* don't update iph->daddr, since it will overwrite old eth_proto * and multiple iterations of bpf_prog_run() will fail */ @@ -639,7 +640,7 @@ static int process_l3_headers_v6(struct packet_description *pckt, iph_len = sizeof(struct ipv6hdr); *protocol = ip6h->nexthdr; pckt->flow.proto = *protocol; - *pkt_bytes = __builtin_bswap16(ip6h->payload_len); + *pkt_bytes = bpf_ntohs(ip6h->payload_len); off += iph_len; if (*protocol == 45) { return XDP_DROP; @@ -671,7 +672,7 @@ static int process_l3_headers_v4(struct packet_description *pckt, return XDP_DROP; *protocol = iph->protocol; pckt->flow.proto = *protocol; - *pkt_bytes = __builtin_bswap16(iph->tot_len); + *pkt_bytes = bpf_ntohs(iph->tot_len); off += 20; if (iph->frag_off & 65343) return XDP_DROP; @@ -808,10 +809,10 @@ int balancer_ingress(struct xdp_md *ctx) nh_off = sizeof(struct eth_hdr); if (data + nh_off > data_end) return XDP_DROP; - eth_proto = eth->eth_proto; - if (eth_proto == 8) + eth_proto = bpf_ntohs(eth->eth_proto); + if (eth_proto == ETH_P_IP) return process_packet(data, nh_off, data_end, 0, ctx); - else if (eth_proto == 56710) + else if (eth_proto == ETH_P_IPV6) return process_packet(data, nh_off, data_end, 1, ctx); else return XDP_DROP; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 8351cb5f4a20..3d617e806054 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -3417,6 +3417,94 @@ static struct btf_raw_test raw_tests[] = { .value_type_id = 1, .max_entries = 4, }, +/* + * typedef int arr_t[16]; + * struct s { + * arr_t *a; + * }; + */ +{ + .descr = "struct->ptr->typedef->array->int size resolution", + .raw_types = { + BTF_STRUCT_ENC(NAME_TBD, 1, 8), /* [1] */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), + BTF_PTR_ENC(3), /* [2] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + BTF_TYPE_ARRAY_ENC(5, 5, 16), /* [4] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [5] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0a\0arr_t"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "ptr_mod_chain_size_resolve_map", + .key_size = sizeof(int), + .value_size = sizeof(int) * 16, + .key_type_id = 5 /* int */, + .value_type_id = 3 /* arr_t */, + .max_entries = 4, +}, +/* + * typedef int arr_t[16][8][4]; + * struct s { + * arr_t *a; + * }; + */ +{ + .descr = "struct->ptr->typedef->multi-array->int size resolution", + .raw_types = { + BTF_STRUCT_ENC(NAME_TBD, 1, 8), /* [1] */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), + BTF_PTR_ENC(3), /* [2] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + BTF_TYPE_ARRAY_ENC(5, 7, 16), /* [4] */ + BTF_TYPE_ARRAY_ENC(6, 7, 8), /* [5] */ + BTF_TYPE_ARRAY_ENC(7, 7, 4), /* [6] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [7] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0a\0arr_t"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "multi_arr_size_resolve_map", + .key_size = sizeof(int), + .value_size = sizeof(int) * 16 * 8 * 4, + .key_type_id = 7 /* int */, + .value_type_id = 3 /* arr_t */, + .max_entries = 4, +}, +/* + * typedef int int_t; + * typedef int_t arr3_t[4]; + * typedef arr3_t arr2_t[8]; + * typedef arr2_t arr1_t[16]; + * struct s { + * arr1_t *a; + * }; + */ +{ + .descr = "typedef/multi-arr mix size resolution", + .raw_types = { + BTF_STRUCT_ENC(NAME_TBD, 1, 8), /* [1] */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), + BTF_PTR_ENC(3), /* [2] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + BTF_TYPE_ARRAY_ENC(5, 10, 16), /* [4] */ + BTF_TYPEDEF_ENC(NAME_TBD, 6), /* [5] */ + BTF_TYPE_ARRAY_ENC(7, 10, 8), /* [6] */ + BTF_TYPEDEF_ENC(NAME_TBD, 8), /* [7] */ + BTF_TYPE_ARRAY_ENC(9, 10, 4), /* [8] */ + BTF_TYPEDEF_ENC(NAME_TBD, 10), /* [9] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [10] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0a\0arr1_t\0arr2_t\0arr3_t\0int_t"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "typedef_arra_mix_size_resolve_map", + .key_size = sizeof(int), + .value_size = sizeof(int) * 16 * 8 * 4, + .key_type_id = 10 /* int */, + .value_type_id = 3 /* arr_t */, + .max_entries = 4, +}, }; /* struct btf_raw_test raw_tests[] */ diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index f095e1d4c657..49e0f7d85643 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -92,3 +92,11 @@ int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); int extract_build_id(char *build_id, size_t size); void *spin_lock_thread(void *arg); + +#ifdef __x86_64__ +#define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep" +#elif defined(__s390x__) +#define SYS_NANOSLEEP_KPROBE_NAME "__s390x_sys_nanosleep" +#else +#define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep" +#endif diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index b0773291012a..84135d5f4b35 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -86,7 +86,7 @@ struct bpf_test { int fixup_sk_storage_map[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; - uint32_t retval, retval_unpriv, insn_processed; + uint32_t insn_processed; int prog_len; enum { UNDEF, @@ -95,16 +95,20 @@ struct bpf_test { } result, result_unpriv; enum bpf_prog_type prog_type; uint8_t flags; - __u8 data[TEST_DATA_LEN]; void (*fill_helper)(struct bpf_test *self); uint8_t runs; - struct { - uint32_t retval, retval_unpriv; - union { - __u8 data[TEST_DATA_LEN]; - __u64 data64[TEST_DATA_LEN / 8]; - }; - } retvals[MAX_TEST_RUNS]; +#define bpf_testdata_struct_t \ + struct { \ + uint32_t retval, retval_unpriv; \ + union { \ + __u8 data[TEST_DATA_LEN]; \ + __u64 data64[TEST_DATA_LEN / 8]; \ + }; \ + } + union { + bpf_testdata_struct_t; + bpf_testdata_struct_t retvals[MAX_TEST_RUNS]; + }; enum bpf_attach_type expected_attach_type; }; @@ -949,17 +953,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, uint32_t expected_val; int i; - if (!test->runs) { - expected_val = unpriv && test->retval_unpriv ? - test->retval_unpriv : test->retval; - - err = do_prog_test_run(fd_prog, unpriv, expected_val, - test->data, sizeof(test->data)); - if (err) - run_errs++; - else - run_successes++; - } + if (!test->runs) + test->runs = 1; for (i = 0; i < test->runs; i++) { if (unpriv && test->retvals[i].retval_unpriv) diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c index bcb83196e459..f3c33e128709 100644 --- a/tools/testing/selftests/bpf/verifier/array_access.c +++ b/tools/testing/selftests/bpf/verifier/array_access.c @@ -226,7 +226,7 @@ BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, .fixup_map_array_ro = { 3 }, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index c3de1a2c9dc5..a53d99cebd9f 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -183,7 +183,7 @@ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), BPF_EXIT_INSN(), - BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_3, 0x100000), diff --git a/tools/testing/selftests/bpf/verifier/wide_access.c b/tools/testing/selftests/bpf/verifier/wide_access.c new file mode 100644 index 000000000000..ccade9312d21 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/wide_access.c @@ -0,0 +1,73 @@ +#define BPF_SOCK_ADDR_STORE(field, off, res, err) \ +{ \ + "wide store to bpf_sock_addr." #field "[" #off "]", \ + .insns = { \ + BPF_MOV64_IMM(BPF_REG_0, 1), \ + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \ + offsetof(struct bpf_sock_addr, field[off])), \ + BPF_EXIT_INSN(), \ + }, \ + .result = res, \ + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ + .errstr = err, \ +} + +/* user_ip6[0] is u64 aligned */ +BPF_SOCK_ADDR_STORE(user_ip6, 0, ACCEPT, + NULL), +BPF_SOCK_ADDR_STORE(user_ip6, 1, REJECT, + "invalid bpf_context access off=12 size=8"), +BPF_SOCK_ADDR_STORE(user_ip6, 2, ACCEPT, + NULL), +BPF_SOCK_ADDR_STORE(user_ip6, 3, REJECT, + "invalid bpf_context access off=20 size=8"), + +/* msg_src_ip6[0] is _not_ u64 aligned */ +BPF_SOCK_ADDR_STORE(msg_src_ip6, 0, REJECT, + "invalid bpf_context access off=44 size=8"), +BPF_SOCK_ADDR_STORE(msg_src_ip6, 1, ACCEPT, + NULL), +BPF_SOCK_ADDR_STORE(msg_src_ip6, 2, REJECT, + "invalid bpf_context access off=52 size=8"), +BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT, + "invalid bpf_context access off=56 size=8"), + +#undef BPF_SOCK_ADDR_STORE + +#define BPF_SOCK_ADDR_LOAD(field, off, res, err) \ +{ \ + "wide load from bpf_sock_addr." #field "[" #off "]", \ + .insns = { \ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, \ + offsetof(struct bpf_sock_addr, field[off])), \ + BPF_MOV64_IMM(BPF_REG_0, 1), \ + BPF_EXIT_INSN(), \ + }, \ + .result = res, \ + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ + .errstr = err, \ +} + +/* user_ip6[0] is u64 aligned */ +BPF_SOCK_ADDR_LOAD(user_ip6, 0, ACCEPT, + NULL), +BPF_SOCK_ADDR_LOAD(user_ip6, 1, REJECT, + "invalid bpf_context access off=12 size=8"), +BPF_SOCK_ADDR_LOAD(user_ip6, 2, ACCEPT, + NULL), +BPF_SOCK_ADDR_LOAD(user_ip6, 3, REJECT, + "invalid bpf_context access off=20 size=8"), + +/* msg_src_ip6[0] is _not_ u64 aligned */ +BPF_SOCK_ADDR_LOAD(msg_src_ip6, 0, REJECT, + "invalid bpf_context access off=44 size=8"), +BPF_SOCK_ADDR_LOAD(msg_src_ip6, 1, ACCEPT, + NULL), +BPF_SOCK_ADDR_LOAD(msg_src_ip6, 2, REJECT, + "invalid bpf_context access off=52 size=8"), +BPF_SOCK_ADDR_LOAD(msg_src_ip6, 3, REJECT, + "invalid bpf_context access off=56 size=8"), + +#undef BPF_SOCK_ADDR_LOAD diff --git a/tools/testing/selftests/bpf/verifier/wide_store.c b/tools/testing/selftests/bpf/verifier/wide_store.c deleted file mode 100644 index 8fe99602ded4..000000000000 --- a/tools/testing/selftests/bpf/verifier/wide_store.c +++ /dev/null @@ -1,36 +0,0 @@ -#define BPF_SOCK_ADDR(field, off, res, err) \ -{ \ - "wide store to bpf_sock_addr." #field "[" #off "]", \ - .insns = { \ - BPF_MOV64_IMM(BPF_REG_0, 1), \ - BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \ - offsetof(struct bpf_sock_addr, field[off])), \ - BPF_EXIT_INSN(), \ - }, \ - .result = res, \ - .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ - .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ - .errstr = err, \ -} - -/* user_ip6[0] is u64 aligned */ -BPF_SOCK_ADDR(user_ip6, 0, ACCEPT, - NULL), -BPF_SOCK_ADDR(user_ip6, 1, REJECT, - "invalid bpf_context access off=12 size=8"), -BPF_SOCK_ADDR(user_ip6, 2, ACCEPT, - NULL), -BPF_SOCK_ADDR(user_ip6, 3, REJECT, - "invalid bpf_context access off=20 size=8"), - -/* msg_src_ip6[0] is _not_ u64 aligned */ -BPF_SOCK_ADDR(msg_src_ip6, 0, REJECT, - "invalid bpf_context access off=44 size=8"), -BPF_SOCK_ADDR(msg_src_ip6, 1, ACCEPT, - NULL), -BPF_SOCK_ADDR(msg_src_ip6, 2, REJECT, - "invalid bpf_context access off=52 size=8"), -BPF_SOCK_ADDR(msg_src_ip6, 3, REJECT, - "invalid bpf_context access off=56 size=8"), - -#undef BPF_SOCK_ADDR diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index 2bfddb6d6d3b..8219a30853d2 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -11,7 +11,6 @@ #include <stdlib.h> #include <sys/inotify.h> #include <string.h> -#include <sys/types.h> #include <sys/wait.h> #include "../kselftest.h" diff --git a/tools/testing/selftests/drivers/dma-buf/config b/tools/testing/selftests/drivers/dma-buf/config new file mode 100644 index 000000000000..d708515cff1b --- /dev/null +++ b/tools/testing/selftests/drivers/dma-buf/config @@ -0,0 +1 @@ +CONFIG_UDMABUF=y diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 6d5e9e87c4b7..063ecb290a5a 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -23,9 +23,15 @@ echo " If <dir> is -, all logs output in console only" exit $1 } +# default error +err_ret=1 + +# kselftest skip code is 4 +err_skip=4 + errexit() { # message echo "Error: $1" 1>&2 - exit 1 + exit $err_ret } # Ensuring user privilege @@ -116,11 +122,31 @@ parse_opts() { # opts } # Parameters -DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1` -if [ -z "$DEBUGFS_DIR" ]; then - TRACING_DIR=`grep tracefs /proc/mounts | cut -f2 -d' ' | head -1` -else - TRACING_DIR=$DEBUGFS_DIR/tracing +TRACING_DIR=`grep tracefs /proc/mounts | cut -f2 -d' ' | head -1` +if [ -z "$TRACING_DIR" ]; then + DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1` + if [ -z "$DEBUGFS_DIR" ]; then + # If tracefs exists, then so does /sys/kernel/tracing + if [ -d "/sys/kernel/tracing" ]; then + mount -t tracefs nodev /sys/kernel/tracing || + errexit "Failed to mount /sys/kernel/tracing" + TRACING_DIR="/sys/kernel/tracing" + # If debugfs exists, then so does /sys/kernel/debug + elif [ -d "/sys/kernel/debug" ]; then + mount -t debugfs nodev /sys/kernel/debug || + errexit "Failed to mount /sys/kernel/debug" + TRACING_DIR="/sys/kernel/debug/tracing" + else + err_ret=$err_skip + errexit "debugfs and tracefs are not configured in this kernel" + fi + else + TRACING_DIR="$DEBUGFS_DIR/tracing" + fi +fi +if [ ! -d "$TRACING_DIR" ]; then + err_ret=$err_skip + errexit "ftrace is not configured in this kernel" fi TOP_DIR=`absdir $0` diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 779ec11f61bd..1d96c5f7e402 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -91,8 +91,8 @@ initialize_ftrace() { # Reset ftrace to initial-state reset_events_filter reset_ftrace_filter disable_events - echo > set_event_pid # event tracer is always on - echo > set_ftrace_pid + [ -f set_event_pid ] && echo > set_event_pid + [ -f set_ftrace_pid ] && echo > set_ftrace_pid [ -f set_ftrace_filter ] && echo | tee set_ftrace_* [ -f set_graph_function ] && echo | tee set_graph_* [ -f stack_trace_filter ] && echo > stack_trace_filter diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc new file mode 100644 index 000000000000..0f60087583d8 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc @@ -0,0 +1,32 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Kprobe event user-memory access + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +grep -q '\$arg<N>' README || exit_unresolved # depends on arch +grep -A10 "fetcharg:" README | grep -q 'ustring' || exit_unsupported +grep -A10 "fetcharg:" README | grep -q '\[u\]<offset>' || exit_unsupported + +:;: "user-memory access syntax and ustring working on user memory";: +echo 'p:myevent do_sys_open path=+0($arg2):ustring path2=+u0($arg2):string' \ + > kprobe_events + +grep myevent kprobe_events | \ + grep -q 'path=+0($arg2):ustring path2=+u0($arg2):string' +echo 1 > events/kprobes/myevent/enable +echo > /dev/null +echo 0 > events/kprobes/myevent/enable + +grep myevent trace | grep -q 'path="/dev/null" path2="/dev/null"' + +:;: "user-memory access syntax and ustring not working with kernel memory";: +echo 'p:myevent vfs_symlink path=+0($arg3):ustring path2=+u0($arg3):string' \ + > kprobe_events +echo 1 > events/kprobes/myevent/enable +ln -s foo $TMPDIR/bar +echo 0 > events/kprobes/myevent/enable + +grep myevent trace | grep -q 'path=(fault) path2=(fault)' + +exit 0 diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 62afd0b43074..ba7849751989 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -10,11 +10,11 @@ UNAME_M := $(shell uname -m) LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c LIBKVM_aarch64 = lib/aarch64/processor.c +LIBKVM_s390x = lib/s390x/processor.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid -TEST_GEN_PROGS_x86_64 += x86_64/kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test @@ -26,9 +26,14 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_test +TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_aarch64 += clear_dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_test +TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus + +TEST_GEN_PROGS_s390x += s390x/sync_regs_test +TEST_GEN_PROGS_s390x += kvm_create_max_vcpus TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M)) LIBKVM += $(LIBKVM_$(UNAME_M)) @@ -43,7 +48,12 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) -LDFLAGS += -pthread $(no-pie-option) +# On s390, build the testcases KVM-enabled +pgste-option = $(call try-run, echo 'int main() { return 0; }' | \ + $(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste) + + +LDFLAGS += -pthread $(no-pie-option) $(pgste-option) # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index fc27f890155b..ceb52b952637 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -121,7 +121,6 @@ static void *vcpu_worker(void *data) uint64_t *guest_array; uint64_t pages_count = 0; struct kvm_run *run; - struct ucall uc; run = vcpu_state(vm, VCPU_ID); @@ -132,7 +131,7 @@ static void *vcpu_worker(void *data) /* Let the guest dirty the random pages */ ret = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); - if (get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) { + if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) { pages_count += TEST_PAGES_PER_LOOP; generate_random_array(guest_array, TEST_PAGES_PER_LOOP); } else { diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 9ef2ab1a0c08..b7fa0c8551db 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -52,4 +52,8 @@ static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, ®); } +void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init); +void aarch64_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_vcpu_init *init, void *guest_code); + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 7318fb054ae9..e0e66b115ef2 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -41,6 +41,12 @@ enum vm_guest_mode { NUM_VM_MODES, }; +#ifdef __aarch64__ +#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +#else +#define VM_MODE_DEFAULT VM_MODE_P52V48_4K +#endif + #define vm_guest_mode_string(m) vm_guest_mode_string[m] extern const char * const vm_guest_mode_string[]; @@ -86,8 +92,7 @@ int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, void *arg); void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); -void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, - int gdt_memslot); +void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid); vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, uint32_t data_memslot, uint32_t pgd_memslot); void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, @@ -112,10 +117,12 @@ void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs); int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs); +#ifdef __KVM_HAVE_VCPU_EVENTS void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events); void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events); +#endif #ifdef __x86_64__ void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_nested_state *state); diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h new file mode 100644 index 000000000000..e0e96a5f608c --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/processor.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * s390x processor specific defines + */ +#ifndef SELFTEST_KVM_PROCESSOR_H +#define SELFTEST_KVM_PROCESSOR_H + +/* Bits in the region/segment table entry */ +#define REGION_ENTRY_ORIGIN ~0xfffUL /* region/segment table origin */ +#define REGION_ENTRY_PROTECT 0x200 /* region protection bit */ +#define REGION_ENTRY_NOEXEC 0x100 /* region no-execute bit */ +#define REGION_ENTRY_OFFSET 0xc0 /* region table offset */ +#define REGION_ENTRY_INVALID 0x20 /* invalid region table entry */ +#define REGION_ENTRY_TYPE 0x0c /* region/segment table type mask */ +#define REGION_ENTRY_LENGTH 0x03 /* region third length */ + +/* Bits in the page table entry */ +#define PAGE_INVALID 0x400 /* HW invalid bit */ +#define PAGE_PROTECT 0x200 /* HW read-only bit */ +#define PAGE_NOEXEC 0x100 /* HW no-execute bit */ + +#endif diff --git a/tools/testing/selftests/kvm/x86_64/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index 6a3eec8da351..231d79e57774 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -27,13 +27,13 @@ void test_vcpu_creation(int first_vcpu_id, int num_vcpus) printf("Testing creating %d vCPUs, with IDs %d...%d.\n", num_vcpus, first_vcpu_id, first_vcpu_id + num_vcpus - 1); - vm = vm_create(VM_MODE_P52V48_4K, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); for (i = 0; i < num_vcpus; i++) { int vcpu_id = first_vcpu_id + i; /* This asserts that the vCPU was created. */ - vm_vcpu_add(vm, vcpu_id, 0, 0); + vm_vcpu_add(vm, vcpu_id); } kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 19e667911496..486400a97374 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -227,7 +227,7 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2; struct kvm_vm *vm; - vm = vm_create(VM_MODE_P40V48_4K, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); kvm_vm_elf_load(vm, program_invocation_name, 0, 0); vm_vcpu_add_default(vm, vcpuid, guest_code); @@ -235,28 +235,21 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, return vm; } -void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init) { - size_t stack_size = vm->page_size == 4096 ? - DEFAULT_STACK_PGS * vm->page_size : - vm->page_size; - uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size, - DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, 0, 0); + struct kvm_vcpu_init default_init = { .target = -1, }; + uint64_t sctlr_el1, tcr_el1; - vm_vcpu_add(vm, vcpuid, 0, 0); + if (!init) + init = &default_init; - set_reg(vm, vcpuid, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size); - set_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); -} - -void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot) -{ - struct kvm_vcpu_init init; - uint64_t sctlr_el1, tcr_el1; + if (init->target == -1) { + struct kvm_vcpu_init preferred; + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &preferred); + init->target = preferred.target; + } - memset(&init, 0, sizeof(init)); - init.target = KVM_ARM_TARGET_GENERIC_V8; - vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_INIT, &init); + vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_INIT, init); /* * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15 @@ -316,3 +309,24 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) fprintf(stream, "%*spstate: 0x%.16lx pc: 0x%.16lx\n", indent, "", pstate, pc); } + +void aarch64_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_vcpu_init *init, void *guest_code) +{ + size_t stack_size = vm->page_size == 4096 ? + DEFAULT_STACK_PGS * vm->page_size : + vm->page_size; + uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size, + DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, 0, 0); + + vm_vcpu_add(vm, vcpuid); + aarch64_vcpu_setup(vm, vcpuid, init); + + set_reg(vm, vcpuid, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size); + set_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code); +} + +void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +{ + aarch64_vcpu_add_default(vm, vcpuid, NULL, guest_code); +} diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index ee864fa07d8e..6e49bb039376 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -556,6 +556,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, int ret; struct userspace_mem_region *region; size_t huge_page_size = KVM_UTIL_PGS_PER_HUGEPG * vm->page_size; + size_t alignment; TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical " "address not on a page boundary.\n" @@ -605,9 +606,20 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, TEST_ASSERT(region != NULL, "Insufficient Memory"); region->mmap_size = npages * vm->page_size; - /* Enough memory to align up to a huge page. */ +#ifdef __s390x__ + /* On s390x, the host address must be aligned to 1M (due to PGSTEs) */ + alignment = 0x100000; +#else + alignment = 1; +#endif + if (src_type == VM_MEM_SRC_ANONYMOUS_THP) - region->mmap_size += huge_page_size; + alignment = max(huge_page_size, alignment); + + /* Add enough memory to align up if necessary */ + if (alignment > 1) + region->mmap_size += alignment; + region->mmap_start = mmap(NULL, region->mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS @@ -617,9 +629,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, "test_malloc failed, mmap_start: %p errno: %i", region->mmap_start, errno); - /* Align THP allocation up to start of a huge page. */ - region->host_mem = align(region->mmap_start, - src_type == VM_MEM_SRC_ANONYMOUS_THP ? huge_page_size : 1); + /* Align host address */ + region->host_mem = align(region->mmap_start, alignment); /* As needed perform madvise */ if (src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) { @@ -763,11 +774,10 @@ static int vcpu_mmap_sz(void) * * Return: None * - * Creates and adds to the VM specified by vm and virtual CPU with - * the ID given by vcpuid. + * Adds a virtual CPU to the VM specified by vm with the ID given by vcpuid. + * No additional VCPU setup is done. */ -void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, - int gdt_memslot) +void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid) { struct vcpu *vcpu; @@ -801,8 +811,6 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, vm->vcpu_head->prev = vcpu; vcpu->next = vm->vcpu_head; vm->vcpu_head = vcpu; - - vcpu_setup(vm, vcpuid, pgd_memslot, gdt_memslot); } /* @@ -1221,6 +1229,7 @@ void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs) ret, errno); } +#ifdef __KVM_HAVE_VCPU_EVENTS void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events) { @@ -1246,6 +1255,7 @@ void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, TEST_ASSERT(ret == 0, "KVM_SET_VCPU_EVENTS, failed, rc: %i errno: %i", ret, errno); } +#endif #ifdef __x86_64__ void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid, diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 265b7822f591..f36262e0f655 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -64,8 +64,6 @@ struct kvm_vm { }; struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); -void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, - int gdt_memslot); void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent); void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent); diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c new file mode 100644 index 000000000000..32a02360b1eb --- /dev/null +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -0,0 +1,278 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM selftest s390x library code - CPU-related functions (page tables...) + * + * Copyright (C) 2019, Red Hat, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include "processor.h" +#include "kvm_util.h" +#include "../kvm_util_internal.h" + +#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 + +#define PAGES_PER_REGION 4 + +void virt_pgd_alloc(struct kvm_vm *vm, uint32_t memslot) +{ + vm_paddr_t paddr; + + TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + vm->page_size); + + if (vm->pgd_created) + return; + + paddr = vm_phy_pages_alloc(vm, PAGES_PER_REGION, + KVM_GUEST_PAGE_TABLE_MIN_PADDR, memslot); + memset(addr_gpa2hva(vm, paddr), 0xff, PAGES_PER_REGION * vm->page_size); + + vm->pgd = paddr; + vm->pgd_created = true; +} + +/* + * Allocate 4 pages for a region/segment table (ri < 4), or one page for + * a page table (ri == 4). Returns a suitable region/segment table entry + * which points to the freshly allocated pages. + */ +static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri, uint32_t memslot) +{ + uint64_t taddr; + + taddr = vm_phy_pages_alloc(vm, ri < 4 ? PAGES_PER_REGION : 1, + KVM_GUEST_PAGE_TABLE_MIN_PADDR, memslot); + memset(addr_gpa2hva(vm, taddr), 0xff, PAGES_PER_REGION * vm->page_size); + + return (taddr & REGION_ENTRY_ORIGIN) + | (((4 - ri) << 2) & REGION_ENTRY_TYPE) + | ((ri < 4 ? (PAGES_PER_REGION - 1) : 0) & REGION_ENTRY_LENGTH); +} + +/* + * VM Virtual Page Map + * + * Input Args: + * vm - Virtual Machine + * gva - VM Virtual Address + * gpa - VM Physical Address + * memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * Within the VM given by vm, creates a virtual translation for the page + * starting at vaddr to the page starting at paddr. + */ +void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa, + uint32_t memslot) +{ + int ri, idx; + uint64_t *entry; + + TEST_ASSERT((gva % vm->page_size) == 0, + "Virtual address not on page boundary,\n" + " vaddr: 0x%lx vm->page_size: 0x%x", + gva, vm->page_size); + TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, + (gva >> vm->page_shift)), + "Invalid virtual address, vaddr: 0x%lx", + gva); + TEST_ASSERT((gpa % vm->page_size) == 0, + "Physical address not on page boundary,\n" + " paddr: 0x%lx vm->page_size: 0x%x", + gva, vm->page_size); + TEST_ASSERT((gpa >> vm->page_shift) <= vm->max_gfn, + "Physical address beyond beyond maximum supported,\n" + " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x", + gva, vm->max_gfn, vm->page_size); + + /* Walk through region and segment tables */ + entry = addr_gpa2hva(vm, vm->pgd); + for (ri = 1; ri <= 4; ri++) { + idx = (gva >> (64 - 11 * ri)) & 0x7ffu; + if (entry[idx] & REGION_ENTRY_INVALID) + entry[idx] = virt_alloc_region(vm, ri, memslot); + entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN); + } + + /* Fill in page table entry */ + idx = (gva >> 12) & 0x0ffu; /* page index */ + if (!(entry[idx] & PAGE_INVALID)) + fprintf(stderr, + "WARNING: PTE for gpa=0x%"PRIx64" already set!\n", gpa); + entry[idx] = gpa; +} + +/* + * Address Guest Virtual to Guest Physical + * + * Input Args: + * vm - Virtual Machine + * gpa - VM virtual address + * + * Output Args: None + * + * Return: + * Equivalent VM physical address + * + * Translates the VM virtual address given by gva to a VM physical + * address and then locates the memory region containing the VM + * physical address, within the VM given by vm. When found, the host + * virtual address providing the memory to the vm physical address is + * returned. + * A TEST_ASSERT failure occurs if no region containing translated + * VM virtual address exists. + */ +vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +{ + int ri, idx; + uint64_t *entry; + + TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + vm->page_size); + + entry = addr_gpa2hva(vm, vm->pgd); + for (ri = 1; ri <= 4; ri++) { + idx = (gva >> (64 - 11 * ri)) & 0x7ffu; + TEST_ASSERT(!(entry[idx] & REGION_ENTRY_INVALID), + "No region mapping for vm virtual address 0x%lx", + gva); + entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN); + } + + idx = (gva >> 12) & 0x0ffu; /* page index */ + + TEST_ASSERT(!(entry[idx] & PAGE_INVALID), + "No page mapping for vm virtual address 0x%lx", gva); + + return (entry[idx] & ~0xffful) + (gva & 0xffful); +} + +static void virt_dump_ptes(FILE *stream, struct kvm_vm *vm, uint8_t indent, + uint64_t ptea_start) +{ + uint64_t *pte, ptea; + + for (ptea = ptea_start; ptea < ptea_start + 0x100 * 8; ptea += 8) { + pte = addr_gpa2hva(vm, ptea); + if (*pte & PAGE_INVALID) + continue; + fprintf(stream, "%*spte @ 0x%lx: 0x%016lx\n", + indent, "", ptea, *pte); + } +} + +static void virt_dump_region(FILE *stream, struct kvm_vm *vm, uint8_t indent, + uint64_t reg_tab_addr) +{ + uint64_t addr, *entry; + + for (addr = reg_tab_addr; addr < reg_tab_addr + 0x400 * 8; addr += 8) { + entry = addr_gpa2hva(vm, addr); + if (*entry & REGION_ENTRY_INVALID) + continue; + fprintf(stream, "%*srt%lde @ 0x%lx: 0x%016lx\n", + indent, "", 4 - ((*entry & REGION_ENTRY_TYPE) >> 2), + addr, *entry); + if (*entry & REGION_ENTRY_TYPE) { + virt_dump_region(stream, vm, indent + 2, + *entry & REGION_ENTRY_ORIGIN); + } else { + virt_dump_ptes(stream, vm, indent + 2, + *entry & REGION_ENTRY_ORIGIN); + } + } +} + +void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +{ + if (!vm->pgd_created) + return; + + virt_dump_region(stream, vm, indent, vm->pgd); +} + +/* + * Create a VM with reasonable defaults + * + * Input Args: + * vcpuid - The id of the single VCPU to add to the VM. + * extra_mem_pages - The size of extra memories to add (this will + * decide how much extra space we will need to + * setup the page tables using mem slot 0) + * guest_code - The vCPU's entry point + * + * Output Args: None + * + * Return: + * Pointer to opaque structure that describes the created VM. + */ +struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, + void *guest_code) +{ + /* + * The additional amount of pages required for the page tables is: + * 1 * n / 256 + 4 * (n / 256) / 2048 + 4 * (n / 256) / 2048^2 + ... + * which is definitely smaller than (n / 256) * 2. + */ + uint64_t extra_pg_pages = extra_mem_pages / 256 * 2; + struct kvm_vm *vm; + + vm = vm_create(VM_MODE_DEFAULT, + DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); + + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); + vm_vcpu_add_default(vm, vcpuid, guest_code); + + return vm; +} + +/* + * Adds a vCPU with reasonable defaults (i.e. a stack and initial PSW) + * + * Input Args: + * vcpuid - The id of the VCPU to add to the VM. + * guest_code - The vCPU's entry point + */ +void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) +{ + size_t stack_size = DEFAULT_STACK_PGS * getpagesize(); + uint64_t stack_vaddr; + struct kvm_regs regs; + struct kvm_sregs sregs; + struct kvm_run *run; + + TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + vm->page_size); + + stack_vaddr = vm_vaddr_alloc(vm, stack_size, + DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0); + + vm_vcpu_add(vm, vcpuid); + + /* Setup guest registers */ + vcpu_regs_get(vm, vcpuid, ®s); + regs.gprs[15] = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()) - 160; + vcpu_regs_set(vm, vcpuid, ®s); + + vcpu_sregs_get(vm, vcpuid, &sregs); + sregs.crs[0] |= 0x00040000; /* Enable floating point regs */ + sregs.crs[1] = vm->pgd | 0xf; /* Primary region table */ + vcpu_sregs_set(vm, vcpuid, &sregs); + + run = vcpu_state(vm, vcpuid); + run->psw_mask = 0x0400000180000000ULL; /* DAT enabled + 64 bit mode */ + run->psw_addr = (uintptr_t)guest_code; +} + +void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) +{ + struct vcpu *vcpu = vm->vcpu_head; + + fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n", + indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr); +} diff --git a/tools/testing/selftests/kvm/lib/ucall.c b/tools/testing/selftests/kvm/lib/ucall.c index b701a01cfcb6..dd9a66700f96 100644 --- a/tools/testing/selftests/kvm/lib/ucall.c +++ b/tools/testing/selftests/kvm/lib/ucall.c @@ -125,16 +125,16 @@ void ucall(uint64_t cmd, int nargs, ...) uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) { struct kvm_run *run = vcpu_state(vm, vcpu_id); - - memset(uc, 0, sizeof(*uc)); + struct ucall ucall = {}; + bool got_ucall = false; #ifdef __x86_64__ if (ucall_type == UCALL_PIO && run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { struct kvm_regs regs; vcpu_regs_get(vm, vcpu_id, ®s); - memcpy(uc, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi), sizeof(*uc)); - return uc->cmd; + memcpy(&ucall, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi), sizeof(ucall)); + got_ucall = true; } #endif if (ucall_type == UCALL_MMIO && run->exit_reason == KVM_EXIT_MMIO && @@ -143,8 +143,15 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8, "Unexpected ucall exit mmio address access"); memcpy(&gva, run->mmio.data, sizeof(gva)); - memcpy(uc, addr_gva2hva(vm, gva), sizeof(*uc)); + memcpy(&ucall, addr_gva2hva(vm, gva), sizeof(ucall)); + got_ucall = true; + } + + if (got_ucall) { + vcpu_run_complete_io(vm, vcpu_id); + if (uc) + memcpy(uc, &ucall, sizeof(ucall)); } - return uc->cmd; + return ucall.cmd; } diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index d2ad85fb01ac..6cb34a0fa200 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -609,7 +609,7 @@ static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp, kvm_seg_fill_gdt_64bit(vm, segp); } -void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot) +static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot) { struct kvm_sregs sregs; @@ -655,7 +655,8 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0); /* Create VCPU */ - vm_vcpu_add(vm, vcpuid, 0, 0); + vm_vcpu_add(vm, vcpuid); + vcpu_setup(vm, vcpuid, 0, 0); /* Setup guest general purpose registers */ vcpu_regs_get(vm, vcpuid, ®s); @@ -820,7 +821,7 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, uint64_t extra_pg_pages = extra_mem_pages / 512 * 2; /* Create VM */ - vm = vm_create(VM_MODE_P52V48_4K, + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index fe56d159d65f..204f847bd065 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -5,8 +5,6 @@ * Copyright (C) 2018, Google LLC. */ -#define _GNU_SOURCE /* for program_invocation_name */ - #include "test_util.h" #include "kvm_util.h" #include "processor.h" diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c new file mode 100644 index 000000000000..e85ff0d69548 --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test for s390x KVM_CAP_SYNC_REGS + * + * Based on the same test for x86: + * Copyright (C) 2018, Google LLC. + * + * Adaptions for s390x: + * Copyright (C) 2019, Red Hat, Inc. + * + * Test expected behavior of the KVM_CAP_SYNC_REGS functionality. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" + +#define VCPU_ID 5 + +static void guest_code(void) +{ + for (;;) { + asm volatile ("diag 0,0,0x501"); + asm volatile ("ahi 11,1"); + } +} + +#define REG_COMPARE(reg) \ + TEST_ASSERT(left->reg == right->reg, \ + "Register " #reg \ + " values did not match: 0x%llx, 0x%llx\n", \ + left->reg, right->reg) + +static void compare_regs(struct kvm_regs *left, struct kvm_sync_regs *right) +{ + int i; + + for (i = 0; i < 16; i++) + REG_COMPARE(gprs[i]); +} + +static void compare_sregs(struct kvm_sregs *left, struct kvm_sync_regs *right) +{ + int i; + + for (i = 0; i < 16; i++) + REG_COMPARE(acrs[i]); + + for (i = 0; i < 16; i++) + REG_COMPARE(crs[i]); +} + +#undef REG_COMPARE + +#define TEST_SYNC_FIELDS (KVM_SYNC_GPRS|KVM_SYNC_ACRS|KVM_SYNC_CRS) +#define INVALID_SYNC_FIELD 0x80000000 + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + struct kvm_run *run; + struct kvm_regs regs; + struct kvm_sregs sregs; + int rv, cap; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + cap = kvm_check_cap(KVM_CAP_SYNC_REGS); + if (!cap) { + fprintf(stderr, "CAP_SYNC_REGS not supported, skipping test\n"); + exit(KSFT_SKIP); + } + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + + run = vcpu_state(vm, VCPU_ID); + + /* Request and verify all valid register sets. */ + run->kvm_valid_regs = TEST_SYNC_FIELDS; + rv = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); + TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, + "Unexpected exit reason: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->s390_sieic.icptcode == 4 && + (run->s390_sieic.ipa >> 8) == 0x83 && + (run->s390_sieic.ipb >> 16) == 0x501, + "Unexpected interception code: ic=%u, ipa=0x%x, ipb=0x%x\n", + run->s390_sieic.icptcode, run->s390_sieic.ipa, + run->s390_sieic.ipb); + + vcpu_regs_get(vm, VCPU_ID, ®s); + compare_regs(®s, &run->s.regs); + + vcpu_sregs_get(vm, VCPU_ID, &sregs); + compare_sregs(&sregs, &run->s.regs); + + /* Set and verify various register values */ + run->s.regs.gprs[11] = 0xBAD1DEA; + run->s.regs.acrs[0] = 1 << 11; + + run->kvm_valid_regs = TEST_SYNC_FIELDS; + run->kvm_dirty_regs = KVM_SYNC_GPRS | KVM_SYNC_ACRS; + rv = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); + TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, + "Unexpected exit reason: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->s.regs.gprs[11] == 0xBAD1DEA + 1, + "r11 sync regs value incorrect 0x%llx.", + run->s.regs.gprs[11]); + TEST_ASSERT(run->s.regs.acrs[0] == 1 << 11, + "acr0 sync regs value incorrect 0x%llx.", + run->s.regs.acrs[0]); + + vcpu_regs_get(vm, VCPU_ID, ®s); + compare_regs(®s, &run->s.regs); + + vcpu_sregs_get(vm, VCPU_ID, &sregs); + compare_sregs(&sregs, &run->s.regs); + + /* Clear kvm_dirty_regs bits, verify new s.regs values are + * overwritten with existing guest values. + */ + run->kvm_valid_regs = TEST_SYNC_FIELDS; + run->kvm_dirty_regs = 0; + run->s.regs.gprs[11] = 0xDEADBEEF; + rv = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); + TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, + "Unexpected exit reason: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->s.regs.gprs[11] != 0xDEADBEEF, + "r11 sync regs value incorrect 0x%llx.", + run->s.regs.gprs[11]); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 241919ef1eac..f95c08343b48 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -144,7 +144,7 @@ int main(int argc, char *argv[]) /* Restore state in a new VM. */ kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID, 0, 0); + vm_vcpu_add(vm, VCPU_ID); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); vcpu_load_state(vm, VCPU_ID, state); diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index 4daf520bada1..8c063646f2a0 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -144,7 +144,7 @@ int main(int argc, char *argv[]) state = vcpu_save_state(vm, VCPU_ID); kvm_vm_release(vm); kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID, 0, 0); + vm_vcpu_add(vm, VCPU_ID); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 1a23617f34d9..3ab5ec3da9f4 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -176,7 +176,7 @@ int main(int argc, char *argv[]) /* Restore state in a new VM. */ kvm_vm_restart(vm, O_RDWR); - vm_vcpu_add(vm, VCPU_ID, 0, 0); + vm_vcpu_add(vm, VCPU_ID); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 077337195783..1c8a1963d03f 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -70,7 +70,7 @@ define RUN_TESTS endef run_tests: all -ifneq ($(KBUILD_SRC),) +ifdef building_out_of_srctree @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT) fi @@ -125,7 +125,7 @@ clean: # When make O= with kselftest target from main level # the following aren't defined. # -ifneq ($(KBUILD_SRC),) +ifdef building_out_of_srctree LINK.c = $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 9457aaeae092..4465fc2dae14 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,12 +9,13 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw" +TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter" VERBOSE=0 PAUSE_ON_FAIL=no PAUSE=no IP="ip -netns ns1" +NS_EXEC="ip netns exec ns1" log_test() { @@ -433,6 +434,37 @@ fib_carrier_test() fib_carrier_unicast_test } +fib_rp_filter_test() +{ + echo + echo "IPv4 rp_filter tests" + + setup + + set -e + $IP link set dev lo address 52:54:00:6a:c7:5e + $IP link set dummy0 address 52:54:00:6a:c7:5e + $IP link add dummy1 type dummy + $IP link set dummy1 address 52:54:00:6a:c7:5e + $IP link set dev dummy1 up + $NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1 + $NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1 + $NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1 + + $NS_EXEC tc qd add dev dummy1 parent root handle 1: fq_codel + $NS_EXEC tc filter add dev dummy1 parent 1: protocol arp basic action mirred egress redirect dev lo + $NS_EXEC tc filter add dev dummy1 parent 1: protocol ip basic action mirred egress redirect dev lo + set +e + + run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 198.51.100.1" + log_test $? 0 "rp_filter passes local packets" + + run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 127.0.0.1" + log_test $? 0 "rp_filter passes loopback packets" + + cleanup +} + ################################################################################ # Tests on nexthop spec @@ -1557,6 +1589,7 @@ do fib_unreg_test|unregister) fib_unreg_test;; fib_down_test|down) fib_down_test;; fib_carrier_test|carrier) fib_carrier_test;; + fib_rp_filter_test|rp_filter) fib_rp_filter_test;; fib_nexthop_test|nexthop) fib_nexthop_test;; ipv6_route_test|ipv6_rt) ipv6_route_test;; ipv4_route_test|ipv4_rt) ipv4_route_test;; diff --git a/tools/testing/selftests/networking/timestamping/timestamping.c b/tools/testing/selftests/networking/timestamping/timestamping.c index 0fbed67bf4f6..aca3491174a1 100644 --- a/tools/testing/selftests/networking/timestamping/timestamping.c +++ b/tools/testing/selftests/networking/timestamping/timestamping.c @@ -32,6 +32,7 @@ #include <asm/types.h> #include <linux/net_tstamp.h> #include <linux/errqueue.h> +#include <linux/sockios.h> #ifndef SO_TIMESTAMPING # define SO_TIMESTAMPING 37 @@ -42,14 +43,6 @@ # define SO_TIMESTAMPNS 35 #endif -#ifndef SIOCGSTAMPNS -# define SIOCGSTAMPNS 0x8907 -#endif - -#ifndef SIOCSHWTSTAMP -# define SIOCSHWTSTAMP 0x89b0 -#endif - static void usage(const char *error) { if (error) diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh index 8a20e03d4cb7..9c60337317c6 100755 --- a/tools/testing/selftests/ntb/ntb_test.sh +++ b/tools/testing/selftests/ntb/ntb_test.sh @@ -78,10 +78,10 @@ set -e function _modprobe() { - modprobe "$@" + modprobe "$@" || return 1 if [[ "$REMOTE_HOST" != "" ]]; then - ssh "$REMOTE_HOST" modprobe "$@" + ssh "$REMOTE_HOST" modprobe "$@" || return 1 fi } @@ -442,6 +442,30 @@ function pingpong_test() echo " Passed" } +function msi_test() +{ + LOC=$1 + REM=$2 + + write_file 1 $LOC/ready + + echo "Running MSI interrupt tests on: $(subdirname $LOC) / $(subdirname $REM)" + + CNT=$(read_file "$LOC/count") + for ((i = 0; i < $CNT; i++)); do + START=$(read_file $REM/../irq${i}_occurrences) + write_file $i $LOC/trigger + END=$(read_file $REM/../irq${i}_occurrences) + + if [[ $(($END - $START)) != 1 ]]; then + echo "MSI did not trigger the interrupt on the remote side!" >&2 + exit 1 + fi + done + + echo " Passed" +} + function perf_test() { USE_DMA=$1 @@ -520,6 +544,29 @@ function ntb_pingpong_tests() _modprobe -r ntb_pingpong } +function ntb_msi_tests() +{ + LOCAL_MSI="$DEBUGFS/ntb_msi_test/$LOCAL_DEV" + REMOTE_MSI="$REMOTE_HOST:$DEBUGFS/ntb_msi_test/$REMOTE_DEV" + + echo "Starting ntb_msi_test tests..." + + if ! _modprobe ntb_msi_test 2> /dev/null; then + echo " Not doing MSI tests seeing the module is not available." + return + fi + + port_test $LOCAL_MSI $REMOTE_MSI + + LOCAL_PEER="$LOCAL_MSI/peer$LOCAL_PIDX" + REMOTE_PEER="$REMOTE_MSI/peer$REMOTE_PIDX" + + msi_test $LOCAL_PEER $REMOTE_PEER + msi_test $REMOTE_PEER $LOCAL_PEER + + _modprobe -r ntb_msi_test +} + function ntb_perf_tests() { LOCAL_PERF="$DEBUGFS/ntb_perf/$LOCAL_DEV" @@ -541,6 +588,7 @@ function cleanup() _modprobe -r ntb_perf 2> /dev/null _modprobe -r ntb_pingpong 2> /dev/null _modprobe -r ntb_transport 2> /dev/null + _modprobe -r ntb_msi_test 2> /dev/null set -e } @@ -577,5 +625,7 @@ ntb_tool_tests echo ntb_pingpong_tests echo +ntb_msi_tests +echo ntb_perf_tests echo diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore index d503b8764a8e..7101ffd08d66 100644 --- a/tools/testing/selftests/powerpc/mm/.gitignore +++ b/tools/testing/selftests/powerpc/mm/.gitignore @@ -4,4 +4,4 @@ tempfile prot_sao segv_errors wild_bctr -large_vm_fork_separation
\ No newline at end of file +large_vm_fork_separation diff --git a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h index d2c0a911f55e..2b488b78c4f2 100644 --- a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h +++ b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PPC_ASM_H -#define __PPC_ASM_H +#define _PPC_ASM_H #include <ppc-asm.h> #ifndef r1 diff --git a/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c index 147c6dc4eb0b..c1e788a6df47 100644 --- a/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c +++ b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c @@ -79,7 +79,7 @@ int test_vmxcopy() "5:;" "stxvd2x 40,0,%[vecoutptr];" - : [res]"=r"(aborted) + : [res]"=&r"(aborted) : [vecinptr]"r"(&vecin), [vecoutptr]"r"(&vecout), [map]"r"(a) diff --git a/tools/testing/selftests/powerpc/vphn/Makefile b/tools/testing/selftests/powerpc/vphn/Makefile index 18b885da01bd..cf65cbf33085 100644 --- a/tools/testing/selftests/powerpc/vphn/Makefile +++ b/tools/testing/selftests/powerpc/vphn/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only TEST_GEN_PROGS := test-vphn -CFLAGS += -m64 +CFLAGS += -m64 -I$(CURDIR) top_srcdir = ../../../../.. include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/vphn/asm/lppaca.h b/tools/testing/selftests/powerpc/vphn/asm/lppaca.h new file mode 120000 index 000000000000..942b1d00999c --- /dev/null +++ b/tools/testing/selftests/powerpc/vphn/asm/lppaca.h @@ -0,0 +1 @@ +../../../../../../arch/powerpc/include/asm/lppaca.h
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/vphn/vphn.c b/tools/testing/selftests/powerpc/vphn/vphn.c index 1d1f5f2be3b2..5b5fbddccabd 120000 --- a/tools/testing/selftests/powerpc/vphn/vphn.c +++ b/tools/testing/selftests/powerpc/vphn/vphn.c @@ -1 +1 @@ -../../../../../arch/powerpc/mm/book3s64/vphn.c
\ No newline at end of file +../../../../../arch/powerpc/platforms/pseries/vphn.c
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/vphn/vphn.h b/tools/testing/selftests/powerpc/vphn/vphn.h deleted file mode 120000 index 45fe160f8288..000000000000 --- a/tools/testing/selftests/powerpc/vphn/vphn.h +++ /dev/null @@ -1 +0,0 @@ -../../../../../arch/powerpc/mm/book3s64/vphn.h
\ No newline at end of file diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index 444ad39d3700..66fab4c58ed4 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -12,4 +12,5 @@ /read /self /setns-dcache +/setns-sysvipc /thread-self diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile index 9f09fcd09ea3..a8ed0f684829 100644 --- a/tools/testing/selftests/proc/Makefile +++ b/tools/testing/selftests/proc/Makefile @@ -17,6 +17,7 @@ TEST_GEN_PROGS += proc-uptime-002 TEST_GEN_PROGS += read TEST_GEN_PROGS += self TEST_GEN_PROGS += setns-dcache +TEST_GEN_PROGS += setns-sysvipc TEST_GEN_PROGS += thread-self include ../lib.mk diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 853aa164a401..18a3bde8bc96 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -215,6 +215,11 @@ static const char str_vsyscall[] = "ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall]\n"; #ifdef __x86_64__ +static void sigaction_SIGSEGV(int _, siginfo_t *__, void *___) +{ + _exit(1); +} + /* * vsyscall page can't be unmapped, probe it with memory load. */ @@ -231,11 +236,19 @@ static void vsyscall(void) if (pid == 0) { struct rlimit rlim = {0, 0}; (void)setrlimit(RLIMIT_CORE, &rlim); + + /* Hide "segfault at ffffffffff600000" messages. */ + struct sigaction act; + memset(&act, 0, sizeof(struct sigaction)); + act.sa_flags = SA_SIGINFO; + act.sa_sigaction = sigaction_SIGSEGV; + (void)sigaction(SIGSEGV, &act, NULL); + *(volatile int *)0xffffffffff600000UL; exit(0); } - wait(&wstatus); - if (WIFEXITED(wstatus)) { + waitpid(pid, &wstatus, 0); + if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) == 0) { g_vsyscall = true; } } diff --git a/tools/testing/selftests/proc/setns-sysvipc.c b/tools/testing/selftests/proc/setns-sysvipc.c new file mode 100644 index 000000000000..903890c5e587 --- /dev/null +++ b/tools/testing/selftests/proc/setns-sysvipc.c @@ -0,0 +1,133 @@ +/* + * Copyright © 2019 Alexey Dobriyan <adobriyan@gmail.com> + * + * Permission to use, copy, modify, and distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +/* + * Test that setns(CLONE_NEWIPC) points to new /proc/sysvipc content even + * if old one is in dcache. + */ +#undef NDEBUG +#include <assert.h> +#include <errno.h> +#include <stdio.h> +#include <sched.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <sys/ipc.h> +#include <sys/shm.h> + +static pid_t pid = -1; + +static void f(void) +{ + if (pid > 0) { + kill(pid, SIGTERM); + } +} + +int main(void) +{ + int fd[2]; + char _ = 0; + int nsfd; + + atexit(f); + + /* Check for priviledges and syscall availability straight away. */ + if (unshare(CLONE_NEWIPC) == -1) { + if (errno == ENOSYS || errno == EPERM) { + return 4; + } + return 1; + } + /* Distinguisher between two otherwise empty IPC namespaces. */ + if (shmget(IPC_PRIVATE, 1, IPC_CREAT) == -1) { + return 1; + } + + if (pipe(fd) == -1) { + return 1; + } + + pid = fork(); + if (pid == -1) { + return 1; + } + + if (pid == 0) { + if (unshare(CLONE_NEWIPC) == -1) { + return 1; + } + + if (write(fd[1], &_, 1) != 1) { + return 1; + } + + pause(); + + return 0; + } + + if (read(fd[0], &_, 1) != 1) { + return 1; + } + + { + char buf[64]; + snprintf(buf, sizeof(buf), "/proc/%u/ns/ipc", pid); + nsfd = open(buf, O_RDONLY); + if (nsfd == -1) { + return 1; + } + } + + /* Reliably pin dentry into dcache. */ + (void)open("/proc/sysvipc/shm", O_RDONLY); + + if (setns(nsfd, CLONE_NEWIPC) == -1) { + return 1; + } + + kill(pid, SIGTERM); + pid = 0; + + { + char buf[4096]; + ssize_t rv; + int fd; + + fd = open("/proc/sysvipc/shm", O_RDONLY); + if (fd == -1) { + return 1; + } + +#define S32 " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n" +#define S64 " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n" + rv = read(fd, buf, sizeof(buf)); + if (rv == strlen(S32)) { + assert(memcmp(buf, S32, strlen(S32)) == 0); + } else if (rv == strlen(S64)) { + assert(memcmp(buf, S64, strlen(S64)) == 0); + } else { + assert(0); + } + } + + return 0; +} diff --git a/tools/testing/selftests/ptrace/.gitignore b/tools/testing/selftests/ptrace/.gitignore index b3e59d41fd82..cfcc49a7def7 100644 --- a/tools/testing/selftests/ptrace/.gitignore +++ b/tools/testing/selftests/ptrace/.gitignore @@ -1 +1,2 @@ +get_syscall_info peeksiginfo diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile index cb21c76a18ca..c0b7f89f0930 100644 --- a/tools/testing/selftests/ptrace/Makefile +++ b/tools/testing/selftests/ptrace/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only CFLAGS += -iquote../../../../include/uapi -Wall -TEST_GEN_PROGS := peeksiginfo +TEST_GEN_PROGS := get_syscall_info peeksiginfo include ../lib.mk diff --git a/tools/testing/selftests/ptrace/get_syscall_info.c b/tools/testing/selftests/ptrace/get_syscall_info.c new file mode 100644 index 000000000000..5bcd1c7b5be6 --- /dev/null +++ b/tools/testing/selftests/ptrace/get_syscall_info.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2018 Dmitry V. Levin <ldv@altlinux.org> + * All rights reserved. + * + * Check whether PTRACE_GET_SYSCALL_INFO semantics implemented in the kernel + * matches userspace expectations. + */ + +#include "../kselftest_harness.h" +#include <err.h> +#include <signal.h> +#include <asm/unistd.h> +#include "linux/ptrace.h" + +static int +kill_tracee(pid_t pid) +{ + if (!pid) + return 0; + + int saved_errno = errno; + + int rc = kill(pid, SIGKILL); + + errno = saved_errno; + return rc; +} + +static long +sys_ptrace(int request, pid_t pid, unsigned long addr, unsigned long data) +{ + return syscall(__NR_ptrace, request, pid, addr, data); +} + +#define LOG_KILL_TRACEE(fmt, ...) \ + do { \ + kill_tracee(pid); \ + TH_LOG("wait #%d: " fmt, \ + ptrace_stop, ##__VA_ARGS__); \ + } while (0) + +TEST(get_syscall_info) +{ + static const unsigned long args[][7] = { + /* a sequence of architecture-agnostic syscalls */ + { + __NR_chdir, + (unsigned long) "", + 0xbad1fed1, + 0xbad2fed2, + 0xbad3fed3, + 0xbad4fed4, + 0xbad5fed5 + }, + { + __NR_gettid, + 0xcaf0bea0, + 0xcaf1bea1, + 0xcaf2bea2, + 0xcaf3bea3, + 0xcaf4bea4, + 0xcaf5bea5 + }, + { + __NR_exit_group, + 0, + 0xfac1c0d1, + 0xfac2c0d2, + 0xfac3c0d3, + 0xfac4c0d4, + 0xfac5c0d5 + } + }; + const unsigned long *exp_args; + + pid_t pid = fork(); + + ASSERT_LE(0, pid) { + TH_LOG("fork: %m"); + } + + if (pid == 0) { + /* get the pid before PTRACE_TRACEME */ + pid = getpid(); + ASSERT_EQ(0, sys_ptrace(PTRACE_TRACEME, 0, 0, 0)) { + TH_LOG("PTRACE_TRACEME: %m"); + } + ASSERT_EQ(0, kill(pid, SIGSTOP)) { + /* cannot happen */ + TH_LOG("kill SIGSTOP: %m"); + } + for (unsigned int i = 0; i < ARRAY_SIZE(args); ++i) { + syscall(args[i][0], + args[i][1], args[i][2], args[i][3], + args[i][4], args[i][5], args[i][6]); + } + /* unreachable */ + _exit(1); + } + + const struct { + unsigned int is_error; + int rval; + } *exp_param, exit_param[] = { + { 1, -ENOENT }, /* chdir */ + { 0, pid } /* gettid */ + }; + + unsigned int ptrace_stop; + + for (ptrace_stop = 0; ; ++ptrace_stop) { + struct ptrace_syscall_info info = { + .op = 0xff /* invalid PTRACE_SYSCALL_INFO_* op */ + }; + const size_t size = sizeof(info); + const int expected_none_size = + (void *) &info.entry - (void *) &info; + const int expected_entry_size = + (void *) &info.entry.args[6] - (void *) &info; + const int expected_exit_size = + (void *) (&info.exit.is_error + 1) - + (void *) &info; + int status; + long rc; + + ASSERT_EQ(pid, wait(&status)) { + /* cannot happen */ + LOG_KILL_TRACEE("wait: %m"); + } + if (WIFEXITED(status)) { + pid = 0; /* the tracee is no more */ + ASSERT_EQ(0, WEXITSTATUS(status)); + break; + } + ASSERT_FALSE(WIFSIGNALED(status)) { + pid = 0; /* the tracee is no more */ + LOG_KILL_TRACEE("unexpected signal %u", + WTERMSIG(status)); + } + ASSERT_TRUE(WIFSTOPPED(status)) { + /* cannot happen */ + LOG_KILL_TRACEE("unexpected wait status %#x", status); + } + + switch (WSTOPSIG(status)) { + case SIGSTOP: + ASSERT_EQ(0, ptrace_stop) { + LOG_KILL_TRACEE("unexpected signal stop"); + } + ASSERT_EQ(0, sys_ptrace(PTRACE_SETOPTIONS, pid, 0, + PTRACE_O_TRACESYSGOOD)) { + LOG_KILL_TRACEE("PTRACE_SETOPTIONS: %m"); + } + ASSERT_LT(0, (rc = sys_ptrace(PTRACE_GET_SYSCALL_INFO, + pid, size, + (unsigned long) &info))) { + LOG_KILL_TRACEE("PTRACE_GET_SYSCALL_INFO: %m"); + } + ASSERT_EQ(expected_none_size, rc) { + LOG_KILL_TRACEE("signal stop mismatch"); + } + ASSERT_EQ(PTRACE_SYSCALL_INFO_NONE, info.op) { + LOG_KILL_TRACEE("signal stop mismatch"); + } + ASSERT_TRUE(info.arch) { + LOG_KILL_TRACEE("signal stop mismatch"); + } + ASSERT_TRUE(info.instruction_pointer) { + LOG_KILL_TRACEE("signal stop mismatch"); + } + ASSERT_TRUE(info.stack_pointer) { + LOG_KILL_TRACEE("signal stop mismatch"); + } + break; + + case SIGTRAP | 0x80: + ASSERT_LT(0, (rc = sys_ptrace(PTRACE_GET_SYSCALL_INFO, + pid, size, + (unsigned long) &info))) { + LOG_KILL_TRACEE("PTRACE_GET_SYSCALL_INFO: %m"); + } + switch (ptrace_stop) { + case 1: /* entering chdir */ + case 3: /* entering gettid */ + case 5: /* entering exit_group */ + exp_args = args[ptrace_stop / 2]; + ASSERT_EQ(expected_entry_size, rc) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_EQ(PTRACE_SYSCALL_INFO_ENTRY, info.op) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_TRUE(info.arch) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_TRUE(info.instruction_pointer) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_TRUE(info.stack_pointer) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_EQ(exp_args[0], info.entry.nr) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_EQ(exp_args[1], info.entry.args[0]) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_EQ(exp_args[2], info.entry.args[1]) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_EQ(exp_args[3], info.entry.args[2]) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_EQ(exp_args[4], info.entry.args[3]) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_EQ(exp_args[5], info.entry.args[4]) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + ASSERT_EQ(exp_args[6], info.entry.args[5]) { + LOG_KILL_TRACEE("entry stop mismatch"); + } + break; + case 2: /* exiting chdir */ + case 4: /* exiting gettid */ + exp_param = &exit_param[ptrace_stop / 2 - 1]; + ASSERT_EQ(expected_exit_size, rc) { + LOG_KILL_TRACEE("exit stop mismatch"); + } + ASSERT_EQ(PTRACE_SYSCALL_INFO_EXIT, info.op) { + LOG_KILL_TRACEE("exit stop mismatch"); + } + ASSERT_TRUE(info.arch) { + LOG_KILL_TRACEE("exit stop mismatch"); + } + ASSERT_TRUE(info.instruction_pointer) { + LOG_KILL_TRACEE("exit stop mismatch"); + } + ASSERT_TRUE(info.stack_pointer) { + LOG_KILL_TRACEE("exit stop mismatch"); + } + ASSERT_EQ(exp_param->is_error, + info.exit.is_error) { + LOG_KILL_TRACEE("exit stop mismatch"); + } + ASSERT_EQ(exp_param->rval, info.exit.rval) { + LOG_KILL_TRACEE("exit stop mismatch"); + } + break; + default: + LOG_KILL_TRACEE("unexpected syscall stop"); + abort(); + } + break; + + default: + LOG_KILL_TRACEE("unexpected stop signal %#x", + WSTOPSIG(status)); + abort(); + } + + ASSERT_EQ(0, sys_ptrace(PTRACE_SYSCALL, pid, 0, 0)) { + LOG_KILL_TRACEE("PTRACE_SYSCALL: %m"); + } + } + + ASSERT_EQ(ARRAY_SIZE(args) * 2, ptrace_stop); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h index 84f28f147fb6..5943c816c07c 100644 --- a/tools/testing/selftests/rseq/rseq-arm.h +++ b/tools/testing/selftests/rseq/rseq-arm.h @@ -6,6 +6,8 @@ */ /* + * - ARM little endian + * * RSEQ_SIG uses the udf A32 instruction with an uncommon immediate operand * value 0x5de3. This traps if user-space reaches this instruction by mistake, * and the uncommon operand ensures the kernel does not move the instruction @@ -22,36 +24,40 @@ * def3 udf #243 ; 0xf3 * e7f5 b.n <7f5> * - * pre-ARMv6 big endian code: - * e7f5 b.n <7f5> - * def3 udf #243 ; 0xf3 + * - ARMv6+ big endian (BE8): * * ARMv6+ -mbig-endian generates mixed endianness code vs data: little-endian - * code and big-endian data. Ensure the RSEQ_SIG data signature matches code - * endianness. Prior to ARMv6, -mbig-endian generates big-endian code and data - * (which match), so there is no need to reverse the endianness of the data - * representation of the signature. However, the choice between BE32 and BE8 - * is done by the linker, so we cannot know whether code and data endianness - * will be mixed before the linker is invoked. + * code and big-endian data. The data value of the signature needs to have its + * byte order reversed to generate the trap instruction: + * + * Data: 0xf3def5e7 + * + * Translates to this A32 instruction pattern: + * + * e7f5def3 udf #24035 ; 0x5de3 + * + * Translates to this T16 instruction pattern: + * + * def3 udf #243 ; 0xf3 + * e7f5 b.n <7f5> + * + * - Prior to ARMv6 big endian (BE32): + * + * Prior to ARMv6, -mbig-endian generates big-endian code and data + * (which match), so the endianness of the data representation of the + * signature should not be reversed. However, the choice between BE32 + * and BE8 is done by the linker, so we cannot know whether code and + * data endianness will be mixed before the linker is invoked. So rather + * than try to play tricks with the linker, the rseq signature is simply + * data (not a trap instruction) prior to ARMv6 on big endian. This is + * why the signature is expressed as data (.word) rather than as + * instruction (.inst) in assembler. */ -#define RSEQ_SIG_CODE 0xe7f5def3 - -#ifndef __ASSEMBLER__ - -#define RSEQ_SIG_DATA \ - ({ \ - int sig; \ - asm volatile ("b 2f\n\t" \ - "1: .inst " __rseq_str(RSEQ_SIG_CODE) "\n\t" \ - "2:\n\t" \ - "ldr %[sig], 1b\n\t" \ - : [sig] "=r" (sig)); \ - sig; \ - }) - -#define RSEQ_SIG RSEQ_SIG_DATA - +#ifdef __ARMEB__ +#define RSEQ_SIG 0xf3def5e7 /* udf #24035 ; 0x5de3 (ARMv6+) */ +#else +#define RSEQ_SIG 0xe7f5def3 /* udf #24035 ; 0x5de3 */ #endif #define rseq_smp_mb() __asm__ __volatile__ ("dmb" ::: "memory", "cc") @@ -125,8 +131,7 @@ do { \ __rseq_str(table_label) ":\n\t" \ ".word " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \ ".word " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) ", 0x0\n\t" \ - ".arm\n\t" \ - ".inst " __rseq_str(RSEQ_SIG_CODE) "\n\t" \ + ".word " __rseq_str(RSEQ_SIG) "\n\t" \ __rseq_str(label) ":\n\t" \ teardown \ "b %l[" __rseq_str(abort_label) "]\n\t" diff --git a/tools/testing/selftests/safesetid/safesetid-test.c b/tools/testing/selftests/safesetid/safesetid-test.c index 892c8e8b1b8b..8f40c6ecdad1 100644 --- a/tools/testing/selftests/safesetid/safesetid-test.c +++ b/tools/testing/selftests/safesetid/safesetid-test.c @@ -142,23 +142,19 @@ static void ensure_securityfs_mounted(void) static void write_policies(void) { + static char *policy_str = + "1:2\n" + "1:3\n" + "2:2\n" + "3:3\n"; ssize_t written; int fd; fd = open(add_whitelist_policy_file, O_WRONLY); if (fd < 0) die("cant open add_whitelist_policy file\n"); - written = write(fd, "1:2", strlen("1:2")); - if (written != strlen("1:2")) { - if (written >= 0) { - die("short write to %s\n", add_whitelist_policy_file); - } else { - die("write to %s failed: %s\n", - add_whitelist_policy_file, strerror(errno)); - } - } - written = write(fd, "1:3", strlen("1:3")); - if (written != strlen("1:3")) { + written = write(fd, policy_str, strlen(policy_str)); + if (written != strlen(policy_str)) { if (written >= 0) { die("short write to %s\n", add_whitelist_policy_file); } else { diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index dc66fe852768..6ef7f16c4cf5 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1775,13 +1775,18 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee, unsigned long msg; static bool entry; - /* Make sure we got an empty message. */ + /* + * The traditional way to tell PTRACE_SYSCALL entry/exit + * is by counting. + */ + entry = !entry; + + /* Make sure we got an appropriate message. */ ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg); EXPECT_EQ(0, ret); - EXPECT_EQ(0, msg); + EXPECT_EQ(entry ? PTRACE_EVENTMSG_SYSCALL_ENTRY + : PTRACE_EVENTMSG_SYSCALL_EXIT, msg); - /* The only way to tell PTRACE_SYSCALL entry/exit is by counting. */ - entry = !entry; if (!entry) return; diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json index 45e7e89928a5..bf5ebf59c2d4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json @@ -70,6 +70,123 @@ "teardown": [] }, { + "id": "d4cd", + "name": "Add skbedit action with valid mark and mask", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 1/0xaabb", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 1/0xaabb", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "baa7", + "name": "Add skbedit action with valid mark and 32-bit maximum mask", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 1/0xffffffff", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 1/0xffffffff", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "62a5", + "name": "Add skbedit action with valid mark and mask exceeding 32-bit maximum", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 1/0xaabbccddeeff112233", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 1/0xaabbccddeeff112233", + "matchCount": "0", + "teardown": [] + }, + { + "id": "bc15", + "name": "Add skbedit action with valid mark and mask with invalid format", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 1/-1234", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 1/-1234", + "matchCount": "0", + "teardown": [] + }, + { + "id": "57c2", + "name": "Replace skbedit action with new mask", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "$TC actions add action skbedit mark 1/0x11223344 index 1" + ], + "cmdUnderTest": "$TC actions replace action skbedit mark 1/0xaabb index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 1/0xaabb", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { "id": "081d", "name": "Add skbedit action with priority", "category": [ diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c index 5ab4c60c100e..15a329da59fa 100644 --- a/tools/testing/selftests/x86/fsgsbase.c +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -489,25 +489,11 @@ static void test_ptrace_write_gsbase(void) * selector value is changed or not by the GSBASE write in * a ptracer. */ - if (gs != *shared_scratch) { - nerrs++; - printf("[FAIL]\tGS changed to %lx\n", gs); - - /* - * On older kernels, poking a nonzero value into the - * base would zero the selector. On newer kernels, - * this behavior has changed -- poking the base - * changes only the base and, if FSGSBASE is not - * available, this may have no effect. - */ - if (gs == 0) - printf("\tNote: this is expected behavior on older kernels.\n"); - } else if (have_fsgsbase && (base != 0xFF)) { - nerrs++; - printf("[FAIL]\tGSBASE changed to %lx\n", base); + if (gs == 0 && base == 0xFF) { + printf("[OK]\tGS was reset as expected\n"); } else { - printf("[OK]\tGS remained 0x%hx%s", *shared_scratch, have_fsgsbase ? " and GSBASE changed to 0xFF" : ""); - printf("\n"); + nerrs++; + printf("[FAIL]\tGS=0x%lx, GSBASE=0x%lx (should be 0, 0xFF)\n", gs, base); } } diff --git a/tools/testing/selftests/zram/README b/tools/testing/selftests/zram/README index 7972cc512408..110b34834a6f 100644 --- a/tools/testing/selftests/zram/README +++ b/tools/testing/selftests/zram/README @@ -37,4 +37,4 @@ Commands required for testing: - mkfs/ mkfs.ext4 For more information please refer: -kernel-source-tree/Documentation/blockdev/zram.txt +kernel-source-tree/Documentation/admin-guide/blockdev/zram.rst |