diff options
Diffstat (limited to 'tools')
38 files changed, 2510 insertions, 933 deletions
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index 797699462cd8..8fd63a067308 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -13,6 +13,7 @@ #endif #include "../include/asm/inat.h" /* __ignore_sync_check__ */ #include "../include/asm/insn.h" /* __ignore_sync_check__ */ +#include "../include/asm-generic/unaligned.h" /* __ignore_sync_check__ */ #include <linux/errno.h> #include <linux/kconfig.h> @@ -37,10 +38,10 @@ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ - ({ t r; memcpy(&r, insn->next_byte, sizeof(t)); insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) + ({ t r = get_unaligned((t *)(insn)->next_byte); (insn)->next_byte += sizeof(t); leXX_to_cpu(t, r); }) #define __peek_nbyte_next(t, insn, n) \ - ({ t r; memcpy(&r, (insn)->next_byte + n, sizeof(t)); leXX_to_cpu(t, r); }) + ({ t r = get_unaligned((t *)(insn)->next_byte + n); leXX_to_cpu(t, r); }) #define get_next(t, insn) \ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h new file mode 100644 index 000000000000..47387c607035 --- /dev/null +++ b/tools/include/asm-generic/unaligned.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copied from the kernel sources to tools/perf/: + */ + +#ifndef __TOOLS_LINUX_ASM_GENERIC_UNALIGNED_H +#define __TOOLS_LINUX_ASM_GENERIC_UNALIGNED_H + +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define __put_unaligned_t(type, val, ptr) do { \ + struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ + __pptr->x = (val); \ +} while (0) + +#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) +#define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) + +#endif /* __TOOLS_LINUX_ASM_GENERIC_UNALIGNED_H */ + diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index f92880a15645..2fc09579e24a 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1210,14 +1210,16 @@ union perf_mem_data_src { mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ mem_blk:3, /* access blocked */ - mem_rsvd:21; + mem_hops:3, /* hop level */ + mem_rsvd:18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:21, + __u64 mem_rsvd:18, + mem_hops:3, /* hop level */ mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ @@ -1241,7 +1243,13 @@ union perf_mem_data_src { #define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ #define PERF_MEM_OP_SHIFT 0 -/* memory hierarchy (memory level, hit or miss) */ +/* + * PERF_MEM_LVL_* namespace being depricated to some extent in the + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * Supporting this namespace inorder to not break defined ABIs. + * + * memory hierarchy (memory level, hit or miss) + */ #define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ @@ -1307,6 +1315,11 @@ union perf_mem_data_src { #define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ #define PERF_MEM_BLK_SHIFT 40 +/* hop level */ +#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ +/* 2-7 available */ +#define PERF_MEM_HOPS_SHIFT 43 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 0893436cc09f..4d6d7fc13255 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -20,6 +20,7 @@ #include <objtool/arch.h> #include <objtool/warn.h> #include <objtool/endianness.h> +#include <objtool/builtin.h> #include <arch/elf.h> static int is_x86_64(const struct elf *elf) @@ -102,12 +103,13 @@ unsigned long arch_jump_destination(struct instruction *insn) #define rm_is_mem(reg) (mod_is_mem() && !is_RIP() && rm_is(reg)) #define rm_is_reg(reg) (mod_is_reg() && modrm_rm == (reg)) -int arch_decode_instruction(const struct elf *elf, const struct section *sec, +int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, enum insn_type *type, unsigned long *immediate, struct list_head *ops_list) { + const struct elf *elf = file->elf; struct insn insn; int x86_64, ret; unsigned char op1, op2, @@ -544,6 +546,36 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec, *type = INSN_RETURN; break; + case 0xc7: /* mov imm, r/m */ + if (!noinstr) + break; + + if (insn.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) { + struct reloc *immr, *disp; + struct symbol *func; + int idx; + + immr = find_reloc_by_dest(elf, (void *)sec, offset+3); + disp = find_reloc_by_dest(elf, (void *)sec, offset+7); + + if (!immr || strcmp(immr->sym->name, "pv_ops")) + break; + + idx = (immr->addend + 8) / sizeof(void *); + + func = disp->sym; + if (disp->sym->type == STT_SECTION) + func = find_symbol_by_offset(disp->sym->sec, disp->addend); + if (!func) { + WARN("no func for pv_ops[]"); + return -1; + } + + objtool_pv_add(file, idx, func); + } + + break; + case 0xcf: /* iret */ /* * Handle sync_core(), which has an IRET to self. @@ -659,154 +691,52 @@ const char *arch_nop_insn(int len) return nops[len-1]; } -/* asm/alternative.h ? */ - -#define ALTINSTR_FLAG_INV (1 << 15) -#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) - -struct alt_instr { - s32 instr_offset; /* original instruction */ - s32 repl_offset; /* offset to replacement instruction */ - u16 cpuid; /* cpuid bit set for replacement */ - u8 instrlen; /* length of original instruction */ - u8 replacementlen; /* length of new instruction */ -} __packed; - -static int elf_add_alternative(struct elf *elf, - struct instruction *orig, struct symbol *sym, - int cpuid, u8 orig_len, u8 repl_len) -{ - const int size = sizeof(struct alt_instr); - struct alt_instr *alt; - struct section *sec; - Elf_Scn *s; - - sec = find_section_by_name(elf, ".altinstructions"); - if (!sec) { - sec = elf_create_section(elf, ".altinstructions", - SHF_ALLOC, 0, 0); - - if (!sec) { - WARN_ELF("elf_create_section"); - return -1; - } - } - - s = elf_getscn(elf->elf, sec->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return -1; - } - - sec->data = elf_newdata(s); - if (!sec->data) { - WARN_ELF("elf_newdata"); - return -1; - } - - sec->data->d_size = size; - sec->data->d_align = 1; - - alt = sec->data->d_buf = malloc(size); - if (!sec->data->d_buf) { - perror("malloc"); - return -1; - } - memset(sec->data->d_buf, 0, size); - - if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size, - R_X86_64_PC32, orig->sec, orig->offset)) { - WARN("elf_create_reloc: alt_instr::instr_offset"); - return -1; - } - - if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4, - R_X86_64_PC32, sym, 0)) { - WARN("elf_create_reloc: alt_instr::repl_offset"); - return -1; - } - - alt->cpuid = bswap_if_needed(cpuid); - alt->instrlen = orig_len; - alt->replacementlen = repl_len; - - sec->sh.sh_size += size; - sec->changed = true; - - return 0; -} - -#define X86_FEATURE_RETPOLINE ( 7*32+12) +#define BYTE_RET 0xC3 -int arch_rewrite_retpolines(struct objtool_file *file) +const char *arch_ret_insn(int len) { - struct instruction *insn; - struct reloc *reloc; - struct symbol *sym; - char name[32] = ""; - - list_for_each_entry(insn, &file->retpoline_call_list, call_node) { - - if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) - continue; - - if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) - continue; - - reloc = insn->reloc; - - sprintf(name, "__x86_indirect_alt_%s_%s", - insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call", - reloc->sym->name + 21); - - sym = find_symbol_by_name(file->elf, name); - if (!sym) { - sym = elf_create_undef_symbol(file->elf, name); - if (!sym) { - WARN("elf_create_undef_symbol"); - return -1; - } - } + static const char ret[5][5] = { + { BYTE_RET }, + { BYTE_RET, BYTES_NOP1 }, + { BYTE_RET, BYTES_NOP2 }, + { BYTE_RET, BYTES_NOP3 }, + { BYTE_RET, BYTES_NOP4 }, + }; - if (elf_add_alternative(file->elf, insn, sym, - ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) { - WARN("elf_add_alternative"); - return -1; - } + if (len < 1 || len > 5) { + WARN("invalid RET size: %d\n", len); + return NULL; } - return 0; + return ret[len-1]; } -int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg) +int arch_decode_hint_reg(u8 sp_reg, int *base) { - struct cfi_reg *cfa = &insn->cfi.cfa; - switch (sp_reg) { case ORC_REG_UNDEFINED: - cfa->base = CFI_UNDEFINED; + *base = CFI_UNDEFINED; break; case ORC_REG_SP: - cfa->base = CFI_SP; + *base = CFI_SP; break; case ORC_REG_BP: - cfa->base = CFI_BP; + *base = CFI_BP; break; case ORC_REG_SP_INDIRECT: - cfa->base = CFI_SP_INDIRECT; + *base = CFI_SP_INDIRECT; break; case ORC_REG_R10: - cfa->base = CFI_R10; + *base = CFI_R10; break; case ORC_REG_R13: - cfa->base = CFI_R13; + *base = CFI_R13; break; case ORC_REG_DI: - cfa->base = CFI_DI; + *base = CFI_DI; break; case ORC_REG_DX: - cfa->base = CFI_DX; + *base = CFI_DX; break; default: return -1; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 06b5c164ae93..fb3f251ea021 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -5,6 +5,7 @@ #include <string.h> #include <stdlib.h> +#include <sys/mman.h> #include <arch/elf.h> #include <objtool/builtin.h> @@ -26,7 +27,11 @@ struct alternative { bool skip_orig; }; -struct cfi_init_state initial_func_cfi; +static unsigned long nr_cfi, nr_cfi_reused, nr_cfi_cache; + +static struct cfi_init_state initial_func_cfi; +static struct cfi_state init_cfi; +static struct cfi_state func_cfi; struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset) @@ -173,6 +178,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "rewind_stack_do_exit", "kunit_try_catch_throw", "xen_start_kernel", + "cpu_bringup_and_idle", }; if (!func) @@ -265,6 +271,78 @@ static void init_insn_state(struct insn_state *state, struct section *sec) state->noinstr = sec->noinstr; } +static struct cfi_state *cfi_alloc(void) +{ + struct cfi_state *cfi = calloc(sizeof(struct cfi_state), 1); + if (!cfi) { + WARN("calloc failed"); + exit(1); + } + nr_cfi++; + return cfi; +} + +static int cfi_bits; +static struct hlist_head *cfi_hash; + +static inline bool cficmp(struct cfi_state *cfi1, struct cfi_state *cfi2) +{ + return memcmp((void *)cfi1 + sizeof(cfi1->hash), + (void *)cfi2 + sizeof(cfi2->hash), + sizeof(struct cfi_state) - sizeof(struct hlist_node)); +} + +static inline u32 cfi_key(struct cfi_state *cfi) +{ + return jhash((void *)cfi + sizeof(cfi->hash), + sizeof(*cfi) - sizeof(cfi->hash), 0); +} + +static struct cfi_state *cfi_hash_find_or_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + struct cfi_state *obj; + + hlist_for_each_entry(obj, head, hash) { + if (!cficmp(cfi, obj)) { + nr_cfi_cache++; + return obj; + } + } + + obj = cfi_alloc(); + *obj = *cfi; + hlist_add_head(&obj->hash, head); + + return obj; +} + +static void cfi_hash_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + + hlist_add_head(&cfi->hash, head); +} + +static void *cfi_hash_alloc(unsigned long size) +{ + cfi_bits = max(10, ilog2(size)); + cfi_hash = mmap(NULL, sizeof(struct hlist_head) << cfi_bits, + PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANON, -1, 0); + if (cfi_hash == (void *)-1L) { + WARN("mmap fail cfi_hash"); + cfi_hash = NULL; + } else if (stats) { + printf("cfi_bits: %d\n", cfi_bits); + } + + return cfi_hash; +} + +static unsigned long nr_insns; +static unsigned long nr_insns_visited; + /* * Call the arch-specific instruction decoder for all the instructions and add * them to the global instruction list. @@ -275,7 +353,6 @@ static int decode_instructions(struct objtool_file *file) struct symbol *func; unsigned long offset; struct instruction *insn; - unsigned long nr_insns = 0; int ret; for_each_sec(file, sec) { @@ -301,12 +378,11 @@ static int decode_instructions(struct objtool_file *file) memset(insn, 0, sizeof(*insn)); INIT_LIST_HEAD(&insn->alts); INIT_LIST_HEAD(&insn->stack_ops); - init_cfi_state(&insn->cfi); insn->sec = sec; insn->offset = offset; - ret = arch_decode_instruction(file->elf, sec, offset, + ret = arch_decode_instruction(file, sec, offset, sec->sh.sh_size - offset, &insn->len, &insn->type, &insn->immediate, @@ -344,6 +420,82 @@ err: return ret; } +/* + * Read the pv_ops[] .data table to find the static initialized values. + */ +static int add_pv_ops(struct objtool_file *file, const char *symname) +{ + struct symbol *sym, *func; + unsigned long off, end; + struct reloc *rel; + int idx; + + sym = find_symbol_by_name(file->elf, symname); + if (!sym) + return 0; + + off = sym->offset; + end = off + sym->len; + for (;;) { + rel = find_reloc_by_dest_range(file->elf, sym->sec, off, end - off); + if (!rel) + break; + + func = rel->sym; + if (func->type == STT_SECTION) + func = find_symbol_by_offset(rel->sym->sec, rel->addend); + + idx = (rel->offset - sym->offset) / sizeof(unsigned long); + + objtool_pv_add(file, idx, func); + + off = rel->offset + 1; + if (off > end) + break; + } + + return 0; +} + +/* + * Allocate and initialize file->pv_ops[]. + */ +static int init_pv_ops(struct objtool_file *file) +{ + static const char *pv_ops_tables[] = { + "pv_ops", + "xen_cpu_ops", + "xen_irq_ops", + "xen_mmu_ops", + NULL, + }; + const char *pv_ops; + struct symbol *sym; + int idx, nr; + + if (!noinstr) + return 0; + + file->pv_ops = NULL; + + sym = find_symbol_by_name(file->elf, "pv_ops"); + if (!sym) + return 0; + + nr = sym->len / sizeof(unsigned long); + file->pv_ops = calloc(sizeof(struct pv_state), nr); + if (!file->pv_ops) + return -1; + + for (idx = 0; idx < nr; idx++) + INIT_LIST_HEAD(&file->pv_ops[idx].targets); + + for (idx = 0; (pv_ops = pv_ops_tables[idx]); idx++) + add_pv_ops(file, pv_ops); + + return 0; +} + static struct instruction *find_last_insn(struct objtool_file *file, struct section *sec) { @@ -531,6 +683,52 @@ static int create_static_call_sections(struct objtool_file *file) return 0; } +static int create_retpoline_sites_sections(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + int idx; + + sec = find_section_by_name(file->elf, ".retpoline_sites"); + if (sec) { + WARN("file already has .retpoline_sites, skipping"); + return 0; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) + idx++; + + if (!idx) + return 0; + + sec = elf_create_section(file->elf, ".retpoline_sites", 0, + sizeof(int), idx); + if (!sec) { + WARN("elf_create_section: .retpoline_sites"); + return -1; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + + int *site = (int *)sec->data->d_buf + idx; + *site = 0; + + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(int), + R_X86_64_PC32, + insn->sec, insn->offset)) { + WARN("elf_add_reloc_to_insn: .retpoline_sites"); + return -1; + } + + idx++; + } + + return 0; +} + static int create_mcount_loc_sections(struct objtool_file *file) { struct section *sec; @@ -549,7 +747,7 @@ static int create_mcount_loc_sections(struct objtool_file *file) return 0; idx = 0; - list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) + list_for_each_entry(insn, &file->mcount_loc_list, call_node) idx++; sec = elf_create_section(file->elf, "__mcount_loc", 0, sizeof(unsigned long), idx); @@ -557,7 +755,7 @@ static int create_mcount_loc_sections(struct objtool_file *file) return -1; idx = 0; - list_for_each_entry(insn, &file->mcount_loc_list, mcount_loc_node) { + list_for_each_entry(insn, &file->mcount_loc_list, call_node) { loc = (unsigned long *)sec->data->d_buf + idx; memset(loc, 0, sizeof(unsigned long)); @@ -817,6 +1015,9 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i return NULL; if (!insn->reloc) { + if (!file) + return NULL; + insn->reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); if (!insn->reloc) { @@ -828,6 +1029,136 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i return insn->reloc; } +static void remove_insn_ops(struct instruction *insn) +{ + struct stack_op *op, *tmp; + + list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) { + list_del(&op->list); + free(op); + } +} + +static void annotate_call_site(struct objtool_file *file, + struct instruction *insn, bool sibling) +{ + struct reloc *reloc = insn_reloc(file, insn); + struct symbol *sym = insn->call_dest; + + if (!sym) + sym = reloc->sym; + + /* + * Alternative replacement code is just template code which is + * sometimes copied to the original instruction. For now, don't + * annotate it. (In the future we might consider annotating the + * original instruction if/when it ever makes sense to do so.) + */ + if (!strcmp(insn->sec->name, ".altinstr_replacement")) + return; + + if (sym->static_call_tramp) { + list_add_tail(&insn->call_node, &file->static_call_list); + return; + } + + if (sym->retpoline_thunk) { + list_add_tail(&insn->call_node, &file->retpoline_call_list); + return; + } + + /* + * Many compilers cannot disable KCOV with a function attribute + * so they need a little help, NOP out any KCOV calls from noinstr + * text. + */ + if (insn->sec->noinstr && sym->kcov) { + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); + } + + elf_write_insn(file->elf, insn->sec, + insn->offset, insn->len, + sibling ? arch_ret_insn(insn->len) + : arch_nop_insn(insn->len)); + + insn->type = sibling ? INSN_RETURN : INSN_NOP; + return; + } + + if (mcount && sym->fentry) { + if (sibling) + WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset); + + if (reloc) { + reloc->type = R_NONE; + elf_write_reloc(file->elf, reloc); + } + + elf_write_insn(file->elf, insn->sec, + insn->offset, insn->len, + arch_nop_insn(insn->len)); + + insn->type = INSN_NOP; + + list_add_tail(&insn->call_node, &file->mcount_loc_list); + return; + } +} + +static void add_call_dest(struct objtool_file *file, struct instruction *insn, + struct symbol *dest, bool sibling) +{ + insn->call_dest = dest; + if (!dest) + return; + + /* + * Whatever stack impact regular CALLs have, should be undone + * by the RETURN of the called function. + * + * Annotated intra-function calls retain the stack_ops but + * are converted to JUMP, see read_intra_function_calls(). + */ + remove_insn_ops(insn); + + annotate_call_site(file, insn, sibling); +} + +static void add_retpoline_call(struct objtool_file *file, struct instruction *insn) +{ + /* + * Retpoline calls/jumps are really dynamic calls/jumps in disguise, + * so convert them accordingly. + */ + switch (insn->type) { + case INSN_CALL: + insn->type = INSN_CALL_DYNAMIC; + break; + case INSN_JUMP_UNCONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC; + break; + case INSN_JUMP_CONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; + break; + default: + return; + } + + insn->retpoline_safe = true; + + /* + * Whatever stack impact regular CALLs have, should be undone + * by the RETURN of the called function. + * + * Annotated intra-function calls retain the stack_ops but + * are converted to JUMP, see read_intra_function_calls(). + */ + remove_insn_ops(insn); + + annotate_call_site(file, insn, false); +} /* * Find the destination instructions for all jumps. */ @@ -849,28 +1180,12 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_sec = reloc->sym->sec; dest_off = arch_dest_reloc_offset(reloc->addend); - } else if (arch_is_retpoline(reloc->sym)) { - /* - * Retpoline jumps are really dynamic jumps in - * disguise, so convert them accordingly. - */ - if (insn->type == INSN_JUMP_UNCONDITIONAL) - insn->type = INSN_JUMP_DYNAMIC; - else - insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; - - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - insn->retpoline_safe = true; + } else if (reloc->sym->retpoline_thunk) { + add_retpoline_call(file, insn); continue; } else if (insn->func) { /* internal or external sibling call (with reloc) */ - insn->call_dest = reloc->sym; - if (insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); - } + add_call_dest(file, insn, reloc->sym, true); continue; } else if (reloc->sym->sec->idx) { dest_sec = reloc->sym->sec; @@ -926,13 +1241,8 @@ 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) { - /* internal sibling call (without reloc) */ - insn->call_dest = insn->jump_dest->func; - if (insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); - } + add_call_dest(file, insn, insn->jump_dest->func, true); } } } @@ -940,16 +1250,6 @@ static int add_jump_destinations(struct objtool_file *file) return 0; } -static void remove_insn_ops(struct instruction *insn) -{ - struct stack_op *op, *tmp; - - list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) { - list_del(&op->list); - free(op); - } -} - static struct symbol *find_call_destination(struct section *sec, unsigned long offset) { struct symbol *call_dest; @@ -968,6 +1268,7 @@ static int add_call_destinations(struct objtool_file *file) { struct instruction *insn; unsigned long dest_off; + struct symbol *dest; struct reloc *reloc; for_each_insn(file, insn) { @@ -977,7 +1278,9 @@ static int add_call_destinations(struct objtool_file *file) reloc = insn_reloc(file, insn); if (!reloc) { dest_off = arch_jump_destination(insn); - insn->call_dest = find_call_destination(insn->sec, dest_off); + dest = find_call_destination(insn->sec, dest_off); + + add_call_dest(file, insn, dest, false); if (insn->ignore) continue; @@ -995,9 +1298,8 @@ static int add_call_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_off = arch_dest_reloc_offset(reloc->addend); - insn->call_dest = find_call_destination(reloc->sym->sec, - dest_off); - if (!insn->call_dest) { + dest = find_call_destination(reloc->sym->sec, dest_off); + if (!dest) { WARN_FUNC("can't find call dest symbol at %s+0x%lx", insn->sec, insn->offset, reloc->sym->sec->name, @@ -1005,70 +1307,13 @@ static int add_call_destinations(struct objtool_file *file) return -1; } - } else if (arch_is_retpoline(reloc->sym)) { - /* - * Retpoline calls are really dynamic calls in - * disguise, so convert them accordingly. - */ - insn->type = INSN_CALL_DYNAMIC; - insn->retpoline_safe = true; + add_call_dest(file, insn, dest, false); - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - remove_insn_ops(insn); - continue; + } else if (reloc->sym->retpoline_thunk) { + add_retpoline_call(file, insn); } else - insn->call_dest = reloc->sym; - - if (insn->call_dest && insn->call_dest->static_call_tramp) { - list_add_tail(&insn->call_node, - &file->static_call_list); - } - - /* - * Many compilers cannot disable KCOV with a function attribute - * so they need a little help, NOP out any KCOV calls from noinstr - * text. - */ - if (insn->sec->noinstr && - !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } - - elf_write_insn(file->elf, insn->sec, - insn->offset, insn->len, - arch_nop_insn(insn->len)); - insn->type = INSN_NOP; - } - - if (mcount && !strcmp(insn->call_dest->name, "__fentry__")) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } - - elf_write_insn(file->elf, insn->sec, - insn->offset, insn->len, - arch_nop_insn(insn->len)); - - insn->type = INSN_NOP; - - list_add_tail(&insn->mcount_loc_node, - &file->mcount_loc_list); - } - - /* - * Whatever stack impact regular CALLs have, should be undone - * by the RETURN of the called function. - * - * Annotated intra-function calls retain the stack_ops but - * are converted to JUMP, see read_intra_function_calls(). - */ - remove_insn_ops(insn); + add_call_dest(file, insn, reloc->sym, false); } return 0; @@ -1136,7 +1381,6 @@ static int handle_group_alt(struct objtool_file *file, memset(nop, 0, sizeof(*nop)); INIT_LIST_HEAD(&nop->alts); INIT_LIST_HEAD(&nop->stack_ops); - init_cfi_state(&nop->cfi); nop->sec = special_alt->new_sec; nop->offset = special_alt->new_off + special_alt->new_len; @@ -1545,10 +1789,11 @@ static void set_func_state(struct cfi_state *state) static int read_unwind_hints(struct objtool_file *file) { + struct cfi_state cfi = init_cfi; struct section *sec, *relocsec; - struct reloc *reloc; struct unwind_hint *hint; struct instruction *insn; + struct reloc *reloc; int i; sec = find_section_by_name(file->elf, ".discard.unwind_hints"); @@ -1586,19 +1831,24 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; if (hint->type == UNWIND_HINT_TYPE_FUNC) { - set_func_state(&insn->cfi); + insn->cfi = &func_cfi; continue; } - if (arch_decode_hint_reg(insn, hint->sp_reg)) { + if (insn->cfi) + cfi = *(insn->cfi); + + if (arch_decode_hint_reg(hint->sp_reg, &cfi.cfa.base)) { WARN_FUNC("unsupported unwind_hint sp base reg %d", insn->sec, insn->offset, hint->sp_reg); return -1; } - insn->cfi.cfa.offset = bswap_if_needed(hint->sp_offset); - insn->cfi.type = hint->type; - insn->cfi.end = hint->end; + cfi.cfa.offset = bswap_if_needed(hint->sp_offset); + cfi.type = hint->type; + cfi.end = hint->end; + + insn->cfi = cfi_hash_find_or_add(&cfi); } return 0; @@ -1737,17 +1987,28 @@ static int read_intra_function_calls(struct objtool_file *file) return 0; } -static int read_static_call_tramps(struct objtool_file *file) +static int classify_symbols(struct objtool_file *file) { struct section *sec; struct symbol *func; for_each_sec(file, sec) { list_for_each_entry(func, &sec->symbol_list, list) { - if (func->bind == STB_GLOBAL && - !strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, + if (func->bind != STB_GLOBAL) + continue; + + if (!strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, strlen(STATIC_CALL_TRAMP_PREFIX_STR))) func->static_call_tramp = true; + + if (arch_is_retpoline(func)) + func->retpoline_thunk = true; + + if (!strcmp(func->name, "__fentry__")) + func->fentry = true; + + if (!strncmp(func->name, "__sanitizer_cov_", 16)) + func->kcov = true; } } @@ -1780,17 +2041,16 @@ static void mark_rodata(struct objtool_file *file) file->rodata = found; } -__weak int arch_rewrite_retpolines(struct objtool_file *file) -{ - return 0; -} - static int decode_sections(struct objtool_file *file) { int ret; mark_rodata(file); + ret = init_pv_ops(file); + if (ret) + return ret; + ret = decode_instructions(file); if (ret) return ret; @@ -1809,7 +2069,7 @@ static int decode_sections(struct objtool_file *file) /* * Must be before add_{jump_call}_destination. */ - ret = read_static_call_tramps(file); + ret = classify_symbols(file); if (ret) return ret; @@ -1853,23 +2113,14 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; - /* - * Must be after add_special_section_alts(), since this will emit - * alternatives. Must be after add_{jump,call}_destination(), since - * those create the call insn lists. - */ - ret = arch_rewrite_retpolines(file); - if (ret) - return ret; - return 0; } static bool is_fentry_call(struct instruction *insn) { - if (insn->type == INSN_CALL && insn->call_dest && - insn->call_dest->type == STT_NOTYPE && - !strcmp(insn->call_dest->name, "__fentry__")) + if (insn->type == INSN_CALL && + insn->call_dest && + insn->call_dest->fentry) return true; return false; @@ -2452,13 +2703,18 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn if (!insn->alt_group) return 0; + if (!insn->cfi) { + WARN("CFI missing"); + return -1; + } + alt_cfi = insn->alt_group->cfi; group_off = insn->offset - insn->alt_group->first_insn->offset; if (!alt_cfi[group_off]) { - alt_cfi[group_off] = &insn->cfi; + alt_cfi[group_off] = insn->cfi; } else { - if (memcmp(alt_cfi[group_off], &insn->cfi, sizeof(struct cfi_state))) { + if (cficmp(alt_cfi[group_off], insn->cfi)) { WARN_FUNC("stack layout conflict in alternatives", insn->sec, insn->offset); return -1; @@ -2509,9 +2765,14 @@ static int handle_insn_ops(struct instruction *insn, static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) { - struct cfi_state *cfi1 = &insn->cfi; + struct cfi_state *cfi1 = insn->cfi; int i; + if (!cfi1) { + WARN("CFI missing"); + return false; + } + if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) { WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d", @@ -2562,20 +2823,64 @@ static inline bool func_uaccess_safe(struct symbol *func) static inline const char *call_dest_name(struct instruction *insn) { + static char pvname[16]; + struct reloc *rel; + int idx; + if (insn->call_dest) return insn->call_dest->name; + rel = insn_reloc(NULL, insn); + if (rel && !strcmp(rel->sym->name, "pv_ops")) { + idx = (rel->addend / sizeof(void *)); + snprintf(pvname, sizeof(pvname), "pv_ops[%d]", idx); + return pvname; + } + return "{dynamic}"; } -static inline bool noinstr_call_dest(struct symbol *func) +static bool pv_call_dest(struct objtool_file *file, struct instruction *insn) +{ + struct symbol *target; + struct reloc *rel; + int idx; + + rel = insn_reloc(file, insn); + if (!rel || strcmp(rel->sym->name, "pv_ops")) + return false; + + idx = (arch_dest_reloc_offset(rel->addend) / sizeof(void *)); + + if (file->pv_ops[idx].clean) + return true; + + file->pv_ops[idx].clean = true; + + list_for_each_entry(target, &file->pv_ops[idx].targets, pv_target) { + if (!target->sec->noinstr) { + WARN("pv_ops[%d]: %s", idx, target->name); + file->pv_ops[idx].clean = false; + } + } + + return file->pv_ops[idx].clean; +} + +static inline bool noinstr_call_dest(struct objtool_file *file, + struct instruction *insn, + struct symbol *func) { /* * We can't deal with indirect function calls at present; * assume they're instrumented. */ - if (!func) + if (!func) { + if (file->pv_ops) + return pv_call_dest(file, insn); + return false; + } /* * If the symbol is from a noinstr section; we good. @@ -2594,10 +2899,12 @@ static inline bool noinstr_call_dest(struct symbol *func) return false; } -static int validate_call(struct instruction *insn, struct insn_state *state) +static int validate_call(struct objtool_file *file, + struct instruction *insn, + struct insn_state *state) { if (state->noinstr && state->instr <= 0 && - !noinstr_call_dest(insn->call_dest)) { + !noinstr_call_dest(file, insn, insn->call_dest)) { WARN_FUNC("call to %s() leaves .noinstr.text section", insn->sec, insn->offset, call_dest_name(insn)); return 1; @@ -2618,7 +2925,9 @@ static int validate_call(struct instruction *insn, struct insn_state *state) return 0; } -static int validate_sibling_call(struct instruction *insn, struct insn_state *state) +static int validate_sibling_call(struct objtool_file *file, + struct instruction *insn, + struct insn_state *state) { if (has_modified_stack_frame(insn, state)) { WARN_FUNC("sibling call from callable instruction with modified stack frame", @@ -2626,7 +2935,7 @@ static int validate_sibling_call(struct instruction *insn, struct insn_state *st return 1; } - return validate_call(insn, state); + return validate_call(file, insn, state); } static int validate_return(struct symbol *func, struct instruction *insn, struct insn_state *state) @@ -2696,7 +3005,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, struct instruction *insn, struct insn_state state) { struct alternative *alt; - struct instruction *next_insn; + struct instruction *next_insn, *prev_insn = NULL; struct section *sec; u8 visited; int ret; @@ -2725,15 +3034,25 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (insn->visited & visited) return 0; + } else { + nr_insns_visited++; } if (state.noinstr) state.instr += insn->instr; - if (insn->hint) - state.cfi = insn->cfi; - else - insn->cfi = state.cfi; + if (insn->hint) { + state.cfi = *insn->cfi; + } else { + /* XXX track if we actually changed state.cfi */ + + if (prev_insn && !cficmp(prev_insn->cfi, &state.cfi)) { + insn->cfi = prev_insn->cfi; + nr_cfi_reused++; + } else { + insn->cfi = cfi_hash_find_or_add(&state.cfi); + } + } insn->visited |= visited; @@ -2769,7 +3088,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_CALL: case INSN_CALL_DYNAMIC: - ret = validate_call(insn, &state); + ret = validate_call(file, insn, &state); if (ret) return ret; @@ -2788,7 +3107,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_JUMP_CONDITIONAL: case INSN_JUMP_UNCONDITIONAL: if (is_sibling_call(insn)) { - ret = validate_sibling_call(insn, &state); + ret = validate_sibling_call(file, insn, &state); if (ret) return ret; @@ -2810,7 +3129,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_JUMP_DYNAMIC: case INSN_JUMP_DYNAMIC_CONDITIONAL: if (is_sibling_call(insn)) { - ret = validate_sibling_call(insn, &state); + ret = validate_sibling_call(file, insn, &state); if (ret) return ret; } @@ -2883,6 +3202,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; } + prev_insn = insn; insn = next_insn; } @@ -3138,10 +3458,20 @@ int check(struct objtool_file *file) int ret, warnings = 0; arch_initial_func_cfi_state(&initial_func_cfi); + init_cfi_state(&init_cfi); + init_cfi_state(&func_cfi); + set_func_state(&func_cfi); + + if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3))) + goto out; + + cfi_hash_add(&init_cfi); + cfi_hash_add(&func_cfi); ret = decode_sections(file); if (ret < 0) goto out; + warnings += ret; if (list_empty(&file->insn_list)) @@ -3185,6 +3515,13 @@ int check(struct objtool_file *file) goto out; warnings += ret; + if (retpoline) { + ret = create_retpoline_sites_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } + if (mcount) { ret = create_mcount_loc_sections(file); if (ret < 0) @@ -3192,6 +3529,13 @@ int check(struct objtool_file *file) warnings += ret; } + if (stats) { + printf("nr_insns_visited: %ld\n", nr_insns_visited); + printf("nr_cfi: %ld\n", nr_cfi); + printf("nr_cfi_reused: %ld\n", nr_cfi_reused); + printf("nr_cfi_cache: %ld\n", nr_cfi_cache); + } + out: /* * For now, don't fail the kernel build on fatal warnings. These diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index fee03b744a6e..81a4c543ff7e 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -741,90 +741,6 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) return len; } -struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) -{ - struct section *symtab, *symtab_shndx; - struct symbol *sym; - Elf_Data *data; - Elf_Scn *s; - - sym = malloc(sizeof(*sym)); - if (!sym) { - perror("malloc"); - return NULL; - } - memset(sym, 0, sizeof(*sym)); - - sym->name = strdup(name); - - sym->sym.st_name = elf_add_string(elf, NULL, sym->name); - if (sym->sym.st_name == -1) - return NULL; - - sym->sym.st_info = GELF_ST_INFO(STB_GLOBAL, STT_NOTYPE); - // st_other 0 - // st_shndx 0 - // st_value 0 - // st_size 0 - - symtab = find_section_by_name(elf, ".symtab"); - if (!symtab) { - WARN("can't find .symtab"); - return NULL; - } - - s = elf_getscn(elf->elf, symtab->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym; - data->d_size = sizeof(sym->sym); - data->d_align = 1; - data->d_type = ELF_T_SYM; - - sym->idx = symtab->sh.sh_size / sizeof(sym->sym); - - symtab->sh.sh_size += data->d_size; - symtab->changed = true; - - symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); - if (symtab_shndx) { - s = elf_getscn(elf->elf, symtab_shndx->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym.st_size; /* conveniently 0 */ - data->d_size = sizeof(Elf32_Word); - data->d_align = 4; - data->d_type = ELF_T_WORD; - - symtab_shndx->sh.sh_size += 4; - symtab_shndx->changed = true; - } - - sym->sec = find_section_by_index(elf, 0); - - elf_add_symbol(elf, sym); - - return sym; -} - struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr) { diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h index 062bb6e9b865..589ff58426ab 100644 --- a/tools/objtool/include/objtool/arch.h +++ b/tools/objtool/include/objtool/arch.h @@ -69,7 +69,7 @@ struct instruction; void arch_initial_func_cfi_state(struct cfi_init_state *state); -int arch_decode_instruction(const struct elf *elf, const struct section *sec, +int arch_decode_instruction(struct objtool_file *file, const struct section *sec, unsigned long offset, unsigned int maxlen, unsigned int *len, enum insn_type *type, unsigned long *immediate, @@ -82,8 +82,9 @@ unsigned long arch_jump_destination(struct instruction *insn); unsigned long arch_dest_reloc_offset(int addend); const char *arch_nop_insn(int len); +const char *arch_ret_insn(int len); -int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg); +int arch_decode_hint_reg(u8 sp_reg, int *base); bool arch_is_retpoline(struct symbol *sym); diff --git a/tools/objtool/include/objtool/cfi.h b/tools/objtool/include/objtool/cfi.h index fd5cb0bed9bf..f11d1ac1dadf 100644 --- a/tools/objtool/include/objtool/cfi.h +++ b/tools/objtool/include/objtool/cfi.h @@ -7,6 +7,7 @@ #define _OBJTOOL_CFI_H #include <arch/cfi_regs.h> +#include <linux/list.h> #define CFI_UNDEFINED -1 #define CFI_CFA -2 @@ -24,6 +25,7 @@ struct cfi_init_state { }; struct cfi_state { + struct hlist_node hash; /* must be first, cficmp() */ struct cfi_reg regs[CFI_NUM_REGS]; struct cfi_reg vals[CFI_NUM_REGS]; struct cfi_reg cfa; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index 56d50bc50c10..6cfff078897f 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -40,7 +40,6 @@ struct instruction { struct list_head list; struct hlist_node hash; struct list_head call_node; - struct list_head mcount_loc_node; struct section *sec; unsigned long offset; unsigned int len; @@ -60,7 +59,7 @@ struct instruction { struct list_head alts; struct symbol *func; struct list_head stack_ops; - struct cfi_state cfi; + struct cfi_state *cfi; }; static inline bool is_static_jump(struct instruction *insn) diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index 075d8291b854..cdc739fa9a6f 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -54,8 +54,12 @@ struct symbol { unsigned long offset; unsigned int len; struct symbol *pfunc, *cfunc, *alias; - bool uaccess_safe; - bool static_call_tramp; + u8 uaccess_safe : 1; + u8 static_call_tramp : 1; + u8 retpoline_thunk : 1; + u8 fentry : 1; + u8 kcov : 1; + struct list_head pv_target; }; struct reloc { @@ -140,7 +144,6 @@ int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); int elf_write_reloc(struct elf *elf, struct reloc *reloc); -struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name); int elf_write(struct elf *elf); void elf_close(struct elf *elf); diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index 24fa83634de4..f99fbc6078d5 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -14,6 +14,11 @@ #define __weak __attribute__((weak)) +struct pv_state { + bool clean; + struct list_head targets; +}; + struct objtool_file { struct elf *elf; struct list_head insn_list; @@ -25,10 +30,14 @@ struct objtool_file { unsigned long jl_short, jl_long; unsigned long jl_nop_short, jl_nop_long; + + struct pv_state *pv_ops; }; struct objtool_file *objtool_open_read(const char *_objname); +void objtool_pv_add(struct objtool_file *file, int idx, struct symbol *func); + int check(struct objtool_file *file); int orc_dump(const char *objname); int orc_create(struct objtool_file *file); diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index e21db8bce493..c90c7084e45a 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -135,6 +135,28 @@ struct objtool_file *objtool_open_read(const char *_objname) return &file; } +void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) +{ + if (!noinstr) + return; + + if (!f->pv_ops) { + WARN("paravirt confusion"); + return; + } + + /* + * These functions will be patched into native code, + * see paravirt_patch(). + */ + if (!strcmp(func->name, "_paravirt_nop") || + !strcmp(func->name, "_paravirt_ident_64")) + return; + + list_add(&func->pv_target, &f->pv_ops[idx].targets); + f->pv_ops[idx].clean = false; +} + static void cmd_usage(void) { unsigned int i, longest = 0; diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index b5865e2450cb..dd3c64af9db2 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -13,13 +13,19 @@ #include <objtool/warn.h> #include <objtool/endianness.h> -static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi) +static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, + struct instruction *insn) { - struct instruction *insn = container_of(cfi, struct instruction, cfi); struct cfi_reg *bp = &cfi->regs[CFI_BP]; memset(orc, 0, sizeof(*orc)); + if (!cfi) { + orc->end = 0; + orc->sp_reg = ORC_REG_UNDEFINED; + return 0; + } + orc->end = cfi->end; if (cfi->cfa.base == CFI_UNDEFINED) { @@ -162,7 +168,7 @@ int orc_create(struct objtool_file *file) int i; if (!alt_group) { - if (init_orc_entry(&orc, &insn->cfi)) + if (init_orc_entry(&orc, insn->cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue; @@ -186,7 +192,8 @@ int orc_create(struct objtool_file *file) struct cfi_state *cfi = alt_group->cfi[i]; if (!cfi) continue; - if (init_orc_entry(&orc, cfi)) + /* errors are reported on the original insn */ + if (init_orc_entry(&orc, cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue; diff --git a/tools/objtool/special.c b/tools/objtool/special.c index 06c3eacab3d5..e2223dd91c37 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -109,14 +109,6 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, return -1; } - /* - * Skip retpoline .altinstr_replacement... we already rewrite the - * instructions for retpolines anyway, see arch_is_retpoline() - * usage in add_{call,jump}_destinations(). - */ - if (arch_is_retpoline(new_reloc->sym)) - return 1; - reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off); /* _ASM_EXTABLE_EX hack */ diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5cd702062a04..b856afa6eb52 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -787,6 +787,8 @@ $(OUTPUT)dlfilters/%.o: dlfilters/%.c include/perf/perf_dlfilter.h $(Q)$(MKDIR) -p $(OUTPUT)dlfilters $(QUIET_CC)$(CC) -c -Iinclude $(EXTRA_CFLAGS) -o $@ -fpic $< +.SECONDARY: $(DLFILTERS:.so=.o) + $(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o $(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) -shared -o $@ $< diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 3018a054526a..20cd6244863b 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -45,7 +45,7 @@ static const Dwfl_Callbacks offline_callbacks = { */ static int check_return_reg(int ra_regno, Dwarf_Frame *frame) { - Dwarf_Op ops_mem[2]; + Dwarf_Op ops_mem[3]; Dwarf_Op dummy; Dwarf_Op *ops = &dummy; size_t nops; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 6211d0b84b7a..c32c2eb16d7d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -459,7 +459,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(WEIGHT) && - evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", PERF_OUTPUT_WEIGHT)) + evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT)) return -EINVAL; if (PRINT_FIELD(SYM) && @@ -4039,11 +4039,15 @@ script_found: goto out_delete; uname(&uts); - if (data.is_pipe || /* assume pipe_mode indicates native_arch */ - !strcmp(uts.machine, session->header.env.arch) || - (!strcmp(uts.machine, "x86_64") && - !strcmp(session->header.env.arch, "i386"))) + if (data.is_pipe) { /* Assume pipe_mode indicates native_arch */ native_arch = true; + } else if (session->header.env.arch) { + if (!strcmp(uts.machine, session->header.env.arch)) + native_arch = true; + else if (!strcmp(uts.machine, "x86_64") && + !strcmp(session->header.env.arch, "i386")) + native_arch = true; + } script.session = session; script__setup_sample_type(&script); diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index bc629359826f..b41c2e9c6f88 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -18,3 +18,5 @@ CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder ifeq ($(CC_NO_CLANG), 1) CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init endif + +CFLAGS_intel-pt-insn-decoder.o += -Wno-packed diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index f0e75df72b80..3167b4628b6d 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -301,6 +301,16 @@ static const char * const mem_lvlnum[] = { [PERF_MEM_LVLNUM_NA] = "N/A", }; +static const char * const mem_hops[] = { + "N/A", + /* + * While printing, 'Remote' will be added to represent + * 'Remote core, same node' accesses as remote field need + * to be set with mem_hops field. + */ + "core, same node", +}; + int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) { size_t i, l = 0; @@ -320,12 +330,14 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) /* already taken care of */ m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); - if (mem_info && mem_info->data_src.mem_remote) { strcat(out, "Remote "); l += 7; } + if (mem_info && mem_info->data_src.mem_hops) + l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]); + printed = 0; for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { if (!(m & 0x1)) @@ -472,8 +484,12 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi) /* * Skylake might report unknown remote level via this * bit, consider it when evaluating remote HITMs. + * + * Incase of power, remote field can also be used to denote cache + * accesses from the another core of same node. Hence, setting + * mrem only when HOPS is zero along with set remote field. */ - bool mrem = data_src->mem_remote; + bool mrem = (data_src->mem_remote && !data_src->mem_hops); int err = 0; #define HITM_INC(__f) \ diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index f2abdd6ba12e..ba1488c7c315 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -9,12 +9,12 @@ TEST_PROGS_EXTENDED := fpsimd-test fpsimd-stress \ all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED) -fpsimd-test: fpsimd-test.o +fpsimd-test: fpsimd-test.o asm-utils.o $(CC) -nostdlib $^ -o $@ rdvl-sve: rdvl-sve.o rdvl.o -sve-ptrace: sve-ptrace.o sve-ptrace-asm.o +sve-ptrace: sve-ptrace.o sve-probe-vls: sve-probe-vls.o rdvl.o -sve-test: sve-test.o +sve-test: sve-test.o asm-utils.o $(CC) -nostdlib $^ -o $@ vec-syscfg: vec-syscfg.o rdvl.o vlset: vlset.o diff --git a/tools/testing/selftests/arm64/fp/TODO b/tools/testing/selftests/arm64/fp/TODO index b6b7ebfcf362..44004e53da33 100644 --- a/tools/testing/selftests/arm64/fp/TODO +++ b/tools/testing/selftests/arm64/fp/TODO @@ -1,4 +1,7 @@ - Test unsupported values in the ABIs. -- More coverage for ptrace (eg, vector length conversions). -- Coverage for signals. -- Test PR_SVE_VL_INHERITY after a double fork. +- More coverage for ptrace: + - Get/set of FFR. + - Ensure ptraced processes actually see the register state visible through + the ptrace interface. + - Big endian. +- Test PR_SVE_VL_INHERIT after a double fork. diff --git a/tools/testing/selftests/arm64/fp/asm-utils.S b/tools/testing/selftests/arm64/fp/asm-utils.S new file mode 100644 index 000000000000..4b9728efc18d --- /dev/null +++ b/tools/testing/selftests/arm64/fp/asm-utils.S @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2015-2021 ARM Limited. +// Original author: Dave Martin <Dave.Martin@arm.com> +// +// Utility functions for assembly code. + +#include <asm/unistd.h> +#include "assembler.h" + +// Print a single character x0 to stdout +// Clobbers x0-x2,x8 +function putc + str x0, [sp, #-16]! + + mov x0, #1 // STDOUT_FILENO + mov x1, sp + mov x2, #1 + mov x8, #__NR_write + svc #0 + + add sp, sp, #16 + ret +endfunction +.globl putc + +// Print a NUL-terminated string starting at address x0 to stdout +// Clobbers x0-x3,x8 +function puts + mov x1, x0 + + mov x2, #0 +0: ldrb w3, [x0], #1 + cbz w3, 1f + add x2, x2, #1 + b 0b + +1: mov w0, #1 // STDOUT_FILENO + mov x8, #__NR_write + svc #0 + + ret +endfunction +.globl puts + +// Print an unsigned decimal number x0 to stdout +// Clobbers x0-x4,x8 +function putdec + mov x1, sp + str x30, [sp, #-32]! // Result can't be > 20 digits + + mov x2, #0 + strb w2, [x1, #-1]! // Write the NUL terminator + + mov x2, #10 +0: udiv x3, x0, x2 // div-mod loop to generate the digits + msub x0, x3, x2, x0 + add w0, w0, #'0' + strb w0, [x1, #-1]! + mov x0, x3 + cbnz x3, 0b + + ldrb w0, [x1] + cbnz w0, 1f + mov w0, #'0' // Print "0" for 0, not "" + strb w0, [x1, #-1]! + +1: mov x0, x1 + bl puts + + ldr x30, [sp], #32 + ret +endfunction +.globl putdec + +// Print an unsigned decimal number x0 to stdout, followed by a newline +// Clobbers x0-x5,x8 +function putdecn + mov x5, x30 + + bl putdec + mov x0, #'\n' + bl putc + + ret x5 +endfunction +.globl putdecn + +// Clobbers x0-x3,x8 +function puthexb + str x30, [sp, #-0x10]! + + mov w3, w0 + lsr w0, w0, #4 + bl puthexnibble + mov w0, w3 + + ldr x30, [sp], #0x10 + // fall through to puthexnibble +endfunction +.globl puthexb + +// Clobbers x0-x2,x8 +function puthexnibble + and w0, w0, #0xf + cmp w0, #10 + blo 1f + add w0, w0, #'a' - ('9' + 1) +1: add w0, w0, #'0' + b putc +endfunction +.globl puthexnibble + +// x0=data in, x1=size in, clobbers x0-x5,x8 +function dumphex + str x30, [sp, #-0x10]! + + mov x4, x0 + mov x5, x1 + +0: subs x5, x5, #1 + b.lo 1f + ldrb w0, [x4], #1 + bl puthexb + b 0b + +1: ldr x30, [sp], #0x10 + ret +endfunction +.globl dumphex + + // Trivial memory copy: copy x2 bytes, starting at address x1, to address x0. +// Clobbers x0-x3 +function memcpy + cmp x2, #0 + b.eq 1f +0: ldrb w3, [x1], #1 + strb w3, [x0], #1 + subs x2, x2, #1 + b.ne 0b +1: ret +endfunction +.globl memcpy + +// Fill x1 bytes starting at x0 with 0xae (for canary purposes) +// Clobbers x1, x2. +function memfill_ae + mov w2, #0xae + b memfill +endfunction +.globl memfill_ae + +// Fill x1 bytes starting at x0 with 0. +// Clobbers x1, x2. +function memclr + mov w2, #0 +endfunction +.globl memclr + // fall through to memfill + +// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2 +// Clobbers x1 +function memfill + cmp x1, #0 + b.eq 1f + +0: strb w2, [x0], #1 + subs x1, x1, #1 + b.ne 0b + +1: ret +endfunction +.globl memfill diff --git a/tools/testing/selftests/arm64/fp/assembler.h b/tools/testing/selftests/arm64/fp/assembler.h index 8944f2189206..90bd433d2665 100644 --- a/tools/testing/selftests/arm64/fp/assembler.h +++ b/tools/testing/selftests/arm64/fp/assembler.h @@ -54,4 +54,15 @@ endfunction .purgem \name\()_entry .endm +// Utility macro to print a literal string +// Clobbers x0-x4,x8 +.macro puts string + .pushsection .rodata.str1.1, "aMS", 1 +.L__puts_literal\@: .string "\string" + .popsection + + ldr x0, =.L__puts_literal\@ + bl puts +.endm + #endif /* ! ASSEMBLER_H */ diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S index 0dbd594c2747..e21e8ea52c7e 100644 --- a/tools/testing/selftests/arm64/fp/fpsimd-test.S +++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S @@ -33,131 +33,6 @@ define_accessor setv, NVR, _vldr define_accessor getv, NVR, _vstr -// Print a single character x0 to stdout -// Clobbers x0-x2,x8 -function putc - str x0, [sp, #-16]! - - mov x0, #1 // STDOUT_FILENO - mov x1, sp - mov x2, #1 - mov x8, #__NR_write - svc #0 - - add sp, sp, #16 - ret -endfunction - -// Print a NUL-terminated string starting at address x0 to stdout -// Clobbers x0-x3,x8 -function puts - mov x1, x0 - - mov x2, #0 -0: ldrb w3, [x0], #1 - cbz w3, 1f - add x2, x2, #1 - b 0b - -1: mov w0, #1 // STDOUT_FILENO - mov x8, #__NR_write - svc #0 - - ret -endfunction - -// Utility macro to print a literal string -// Clobbers x0-x4,x8 -.macro puts string - .pushsection .rodata.str1.1, "aMS", 1 -.L__puts_literal\@: .string "\string" - .popsection - - ldr x0, =.L__puts_literal\@ - bl puts -.endm - -// Print an unsigned decimal number x0 to stdout -// Clobbers x0-x4,x8 -function putdec - mov x1, sp - str x30, [sp, #-32]! // Result can't be > 20 digits - - mov x2, #0 - strb w2, [x1, #-1]! // Write the NUL terminator - - mov x2, #10 -0: udiv x3, x0, x2 // div-mod loop to generate the digits - msub x0, x3, x2, x0 - add w0, w0, #'0' - strb w0, [x1, #-1]! - mov x0, x3 - cbnz x3, 0b - - ldrb w0, [x1] - cbnz w0, 1f - mov w0, #'0' // Print "0" for 0, not "" - strb w0, [x1, #-1]! - -1: mov x0, x1 - bl puts - - ldr x30, [sp], #32 - ret -endfunction - -// Print an unsigned decimal number x0 to stdout, followed by a newline -// Clobbers x0-x5,x8 -function putdecn - mov x5, x30 - - bl putdec - mov x0, #'\n' - bl putc - - ret x5 -endfunction - - -// Clobbers x0-x3,x8 -function puthexb - str x30, [sp, #-0x10]! - - mov w3, w0 - lsr w0, w0, #4 - bl puthexnibble - mov w0, w3 - - ldr x30, [sp], #0x10 - // fall through to puthexnibble -endfunction -// Clobbers x0-x2,x8 -function puthexnibble - and w0, w0, #0xf - cmp w0, #10 - blo 1f - add w0, w0, #'a' - ('9' + 1) -1: add w0, w0, #'0' - b putc -endfunction - -// x0=data in, x1=size in, clobbers x0-x5,x8 -function dumphex - str x30, [sp, #-0x10]! - - mov x4, x0 - mov x5, x1 - -0: subs x5, x5, #1 - b.lo 1f - ldrb w0, [x4], #1 - bl puthexb - b 0b - -1: ldr x30, [sp], #0x10 - ret -endfunction - // Declare some storate space to shadow the SVE register contents: .pushsection .text .data @@ -168,18 +43,6 @@ scratch: .space MAXVL_B .popsection -// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0. -// Clobbers x0-x3 -function memcpy - cmp x2, #0 - b.eq 1f -0: ldrb w3, [x1], #1 - strb w3, [x0], #1 - subs x2, x2, #1 - b.ne 0b -1: ret -endfunction - // Generate a test pattern for storage in SVE registers // x0: pid (16 bits) // x1: register number (6 bits) @@ -227,33 +90,6 @@ function setup_vreg ret x4 endfunction -// Fill x1 bytes starting at x0 with 0xae (for canary purposes) -// Clobbers x1, x2. -function memfill_ae - mov w2, #0xae - b memfill -endfunction - -// Fill x1 bytes starting at x0 with 0. -// Clobbers x1, x2. -function memclr - mov w2, #0 -endfunction - // fall through to memfill - -// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2 -// Clobbers x1 -function memfill - cmp x1, #0 - b.eq 1f - -0: strb w2, [x0], #1 - subs x1, x1, #1 - b.ne 0b - -1: ret -endfunction - // Trivial memory compare: compare x2 bytes starting at address x0 with // bytes starting at address x1. // Returns only if all bytes match; otherwise, the program is aborted. diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace-asm.S b/tools/testing/selftests/arm64/fp/sve-ptrace-asm.S deleted file mode 100644 index 3e81f9fab574..000000000000 --- a/tools/testing/selftests/arm64/fp/sve-ptrace-asm.S +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -// Copyright (C) 2015-2019 ARM Limited. -// Original author: Dave Martin <Dave.Martin@arm.com> -#include <asm/unistd.h> - -.arch_extension sve - -.globl sve_store_patterns - -sve_store_patterns: - mov x1, x0 - - index z0.b, #0, #1 - str q0, [x1] - - mov w8, #__NR_getpid - svc #0 - str q0, [x1, #0x10] - - mov z1.d, z0.d - str q0, [x1, #0x20] - - mov w8, #__NR_getpid - svc #0 - str q0, [x1, #0x30] - - mov z1.d, z0.d - str q0, [x1, #0x40] - - ret - -.size sve_store_patterns, . - sve_store_patterns -.type sve_store_patterns, @function diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index 612d3899614a..c4417bc48d4f 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -1,15 +1,17 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2015-2020 ARM Limited. + * Copyright (C) 2015-2021 ARM Limited. * Original author: Dave Martin <Dave.Martin@arm.com> */ #include <errno.h> +#include <stdbool.h> #include <stddef.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <unistd.h> #include <sys/auxv.h> +#include <sys/prctl.h> #include <sys/ptrace.h> #include <sys/types.h> #include <sys/uio.h> @@ -19,40 +21,22 @@ #include "../../kselftest.h" +#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3) +#define FPSIMD_TESTS 5 + +#define EXPECTED_TESTS (VL_TESTS + FPSIMD_TESTS) + /* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */ #ifndef NT_ARM_SVE #define NT_ARM_SVE 0x405 #endif -/* Number of registers filled in by sve_store_patterns */ -#define NR_VREGS 5 - -void sve_store_patterns(__uint128_t v[NR_VREGS]); - -static void dump(const void *buf, size_t size) -{ - size_t i; - const unsigned char *p = buf; - - for (i = 0; i < size; ++i) - printf(" %.2x", *p++); -} - -static int check_vregs(const __uint128_t vregs[NR_VREGS]) +static void fill_buf(char *buf, size_t size) { int i; - int ok = 1; - - for (i = 0; i < NR_VREGS; ++i) { - printf("# v[%d]:", i); - dump(&vregs[i], sizeof vregs[i]); - putchar('\n'); - - if (vregs[i] != vregs[0]) - ok = 0; - } - return ok; + for (i = 0; i < size; i++) + buf[i] = random(); } static int do_child(void) @@ -66,6 +50,15 @@ static int do_child(void) return EXIT_SUCCESS; } +static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd) +{ + struct iovec iov; + + iov.iov_base = fpsimd; + iov.iov_len = sizeof(*fpsimd); + return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov); +} + static struct user_sve_header *get_sve(pid_t pid, void **buf, size_t *size) { struct user_sve_header *sve; @@ -112,25 +105,335 @@ static int set_sve(pid_t pid, const struct user_sve_header *sve) return ptrace(PTRACE_SETREGSET, pid, NT_ARM_SVE, &iov); } -static void dump_sve_regs(const struct user_sve_header *sve, unsigned int num, - unsigned int vlmax) +/* Validate setting and getting the inherit flag */ +static void ptrace_set_get_inherit(pid_t child) +{ + struct user_sve_header sve; + struct user_sve_header *new_sve = NULL; + size_t new_sve_size = 0; + int ret; + + /* First set the flag */ + memset(&sve, 0, sizeof(sve)); + sve.size = sizeof(sve); + sve.vl = sve_vl_from_vq(SVE_VQ_MIN); + sve.flags = SVE_PT_VL_INHERIT; + ret = set_sve(child, &sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set SVE_PT_VL_INHERIT\n"); + return; + } + + /* + * Read back the new register state and verify that we have + * set the flags we expected. + */ + if (!get_sve(child, (void **)&new_sve, &new_sve_size)) { + ksft_test_result_fail("Failed to read SVE flags\n"); + return; + } + + ksft_test_result(new_sve->flags & SVE_PT_VL_INHERIT, + "SVE_PT_VL_INHERIT set\n"); + + /* Now clear */ + sve.flags &= ~SVE_PT_VL_INHERIT; + ret = set_sve(child, &sve); + if (ret != 0) { + ksft_test_result_fail("Failed to clear SVE_PT_VL_INHERIT\n"); + return; + } + + if (!get_sve(child, (void **)&new_sve, &new_sve_size)) { + ksft_test_result_fail("Failed to read SVE flags\n"); + return; + } + + ksft_test_result(!(new_sve->flags & SVE_PT_VL_INHERIT), + "SVE_PT_VL_INHERIT cleared\n"); + + free(new_sve); +} + +/* Validate attempting to set the specfied VL via ptrace */ +static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported) +{ + struct user_sve_header sve; + struct user_sve_header *new_sve = NULL; + size_t new_sve_size = 0; + int ret, prctl_vl; + + *supported = false; + + /* Check if the VL is supported in this process */ + prctl_vl = prctl(PR_SVE_SET_VL, vl); + if (prctl_vl == -1) + ksft_exit_fail_msg("prctl(PR_SVE_SET_VL) failed: %s (%d)\n", + strerror(errno), errno); + + /* If the VL is not supported then a supported VL will be returned */ + *supported = (prctl_vl == vl); + + /* Set the VL by doing a set with no register payload */ + memset(&sve, 0, sizeof(sve)); + sve.size = sizeof(sve); + sve.vl = vl; + ret = set_sve(child, &sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u\n", vl); + return; + } + + /* + * Read back the new register state and verify that we have the + * same VL that we got from prctl() on ourselves. + */ + if (!get_sve(child, (void **)&new_sve, &new_sve_size)) { + ksft_test_result_fail("Failed to read VL %u\n", vl); + return; + } + + ksft_test_result(new_sve->vl = prctl_vl, "Set VL %u\n", vl); + + free(new_sve); +} + +static void check_u32(unsigned int vl, const char *reg, + uint32_t *in, uint32_t *out, int *errors) +{ + if (*in != *out) { + printf("# VL %d %s wrote %x read %x\n", + vl, reg, *in, *out); + (*errors)++; + } +} + +/* Access the FPSIMD registers via the SVE regset */ +static void ptrace_sve_fpsimd(pid_t child) { - unsigned int vq; - unsigned int i; + void *svebuf = NULL; + size_t svebufsz = 0; + struct user_sve_header *sve; + struct user_fpsimd_state *fpsimd, new_fpsimd; + unsigned int i, j; + unsigned char *p; + + /* New process should start with FPSIMD registers only */ + sve = get_sve(child, &svebuf, &svebufsz); + if (!sve) { + ksft_test_result_fail("get_sve: %s\n", strerror(errno)); + + return; + } else { + ksft_test_result_pass("get_sve(FPSIMD)\n"); + } - if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_SVE) - ksft_exit_fail_msg("Dumping non-SVE register\n"); + ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, + "Set FPSIMD registers\n"); + if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) + goto out; - if (vlmax > sve->vl) - vlmax = sve->vl; + /* Try to set a known FPSIMD state via PT_REGS_SVE */ + fpsimd = (struct user_fpsimd_state *)((char *)sve + + SVE_PT_FPSIMD_OFFSET); + for (i = 0; i < 32; ++i) { + p = (unsigned char *)&fpsimd->vregs[i]; - vq = sve_vq_from_vl(sve->vl); - for (i = 0; i < num; ++i) { - printf("# z%u:", i); - dump((const char *)sve + SVE_PT_SVE_ZREG_OFFSET(vq, i), - vlmax); - printf("%s\n", vlmax == sve->vl ? "" : " ..."); + for (j = 0; j < sizeof(fpsimd->vregs[i]); ++j) + p[j] = j; } + + if (set_sve(child, sve)) { + ksft_test_result_fail("set_sve(FPSIMD): %s\n", + strerror(errno)); + + goto out; + } + + /* Verify via the FPSIMD regset */ + if (get_fpsimd(child, &new_fpsimd)) { + ksft_test_result_fail("get_fpsimd(): %s\n", + strerror(errno)); + goto out; + } + if (memcmp(fpsimd, &new_fpsimd, sizeof(*fpsimd)) == 0) + ksft_test_result_pass("get_fpsimd() gave same state\n"); + else + ksft_test_result_fail("get_fpsimd() gave different state\n"); + +out: + free(svebuf); +} + +/* Validate attempting to set SVE data and read SVE data */ +static void ptrace_set_sve_get_sve_data(pid_t child, unsigned int vl) +{ + void *write_buf; + void *read_buf = NULL; + struct user_sve_header *write_sve; + struct user_sve_header *read_sve; + size_t read_sve_size = 0; + unsigned int vq = sve_vq_from_vl(vl); + int ret, i; + size_t data_size; + int errors = 0; + + data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + write_buf = malloc(data_size); + if (!write_buf) { + ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n", + data_size, vl); + return; + } + write_sve = write_buf; + + /* Set up some data and write it out */ + memset(write_sve, 0, data_size); + write_sve->size = data_size; + write_sve->vl = vl; + write_sve->flags = SVE_PT_REGS_SVE; + + for (i = 0; i < __SVE_NUM_ZREGS; i++) + fill_buf(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + SVE_PT_SVE_ZREG_SIZE(vq)); + + for (i = 0; i < __SVE_NUM_PREGS; i++) + fill_buf(write_buf + SVE_PT_SVE_PREG_OFFSET(vq, i), + SVE_PT_SVE_PREG_SIZE(vq)); + + fill_buf(write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), SVE_PT_SVE_FPSR_SIZE); + fill_buf(write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), SVE_PT_SVE_FPCR_SIZE); + + /* TODO: Generate a valid FFR pattern */ + + ret = set_sve(child, write_sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u data\n", vl); + goto out; + } + + /* Read the data back */ + if (!get_sve(child, (void **)&read_buf, &read_sve_size)) { + ksft_test_result_fail("Failed to read VL %u data\n", vl); + goto out; + } + read_sve = read_buf; + + /* We might read more data if there's extensions we don't know */ + if (read_sve->size < write_sve->size) { + ksft_test_result_fail("Wrote %d bytes, only read %d\n", + write_sve->size, read_sve->size); + goto out_read; + } + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + if (memcmp(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + read_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + SVE_PT_SVE_ZREG_SIZE(vq)) != 0) { + printf("# Mismatch in %u Z%d\n", vl, i); + errors++; + } + } + + for (i = 0; i < __SVE_NUM_PREGS; i++) { + if (memcmp(write_buf + SVE_PT_SVE_PREG_OFFSET(vq, i), + read_buf + SVE_PT_SVE_PREG_OFFSET(vq, i), + SVE_PT_SVE_PREG_SIZE(vq)) != 0) { + printf("# Mismatch in %u P%d\n", vl, i); + errors++; + } + } + + check_u32(vl, "FPSR", write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), + read_buf + SVE_PT_SVE_FPSR_OFFSET(vq), &errors); + check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), + read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors); + + ksft_test_result(errors == 0, "Set and get SVE data for VL %u\n", vl); + +out_read: + free(read_buf); +out: + free(write_buf); +} + +/* Validate attempting to set SVE data and read SVE data */ +static void ptrace_set_sve_get_fpsimd_data(pid_t child, unsigned int vl) +{ + void *write_buf; + struct user_sve_header *write_sve; + unsigned int vq = sve_vq_from_vl(vl); + struct user_fpsimd_state fpsimd_state; + int ret, i; + size_t data_size; + int errors = 0; + + if (__BYTE_ORDER == __BIG_ENDIAN) { + ksft_test_result_skip("Big endian not supported\n"); + return; + } + + data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + write_buf = malloc(data_size); + if (!write_buf) { + ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n", + data_size, vl); + return; + } + write_sve = write_buf; + + /* Set up some data and write it out */ + memset(write_sve, 0, data_size); + write_sve->size = data_size; + write_sve->vl = vl; + write_sve->flags = SVE_PT_REGS_SVE; + + for (i = 0; i < __SVE_NUM_ZREGS; i++) + fill_buf(write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + SVE_PT_SVE_ZREG_SIZE(vq)); + + fill_buf(write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), SVE_PT_SVE_FPSR_SIZE); + fill_buf(write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), SVE_PT_SVE_FPCR_SIZE); + + ret = set_sve(child, write_sve); + if (ret != 0) { + ksft_test_result_fail("Failed to set VL %u data\n", vl); + goto out; + } + + /* Read the data back */ + if (get_fpsimd(child, &fpsimd_state)) { + ksft_test_result_fail("Failed to read VL %u FPSIMD data\n", + vl); + goto out; + } + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + __uint128_t tmp = 0; + + /* + * Z regs are stored endianness invariant, this won't + * work for big endian + */ + memcpy(&tmp, write_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i), + sizeof(tmp)); + + if (tmp != fpsimd_state.vregs[i]) { + printf("# Mismatch in FPSIMD for VL %u Z%d\n", vl, i); + errors++; + } + } + + check_u32(vl, "FPSR", write_buf + SVE_PT_SVE_FPSR_OFFSET(vq), + &fpsimd_state.fpsr, &errors); + check_u32(vl, "FPCR", write_buf + SVE_PT_SVE_FPCR_OFFSET(vq), + &fpsimd_state.fpcr, &errors); + + ksft_test_result(errors == 0, "Set and get FPSIMD data for VL %u\n", + vl); + +out: + free(write_buf); } static int do_parent(pid_t child) @@ -139,13 +442,8 @@ static int do_parent(pid_t child) pid_t pid; int status; siginfo_t si; - void *svebuf = NULL, *newsvebuf; - size_t svebufsz = 0, newsvebufsz; - struct user_sve_header *sve, *new_sve; - struct user_fpsimd_state *fpsimd; - unsigned int i, j; - unsigned char *p; - unsigned int vq; + unsigned int vq, vl; + bool vl_supported; /* Attach to the child */ while (1) { @@ -167,8 +465,6 @@ static int do_parent(pid_t child) if (WIFEXITED(status) || WIFSIGNALED(status)) ksft_exit_fail_msg("Child died unexpectedly\n"); - ksft_test_result(WIFSTOPPED(status), "WIFSTOPPED(%d)\n", - status); if (!WIFSTOPPED(status)) goto error; @@ -203,98 +499,27 @@ static int do_parent(pid_t child) } } - sve = get_sve(pid, &svebuf, &svebufsz); - if (!sve) { - int e = errno; + /* FPSIMD via SVE regset */ + ptrace_sve_fpsimd(child); - ksft_test_result_fail("get_sve: %s\n", strerror(errno)); - if (e == ESRCH) - goto disappeared; + /* prctl() flags */ + ptrace_set_get_inherit(child); - goto error; - } else { - ksft_test_result_pass("get_sve\n"); - } - - ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, - "FPSIMD registers\n"); - if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) - goto error; - - fpsimd = (struct user_fpsimd_state *)((char *)sve + - SVE_PT_FPSIMD_OFFSET); - for (i = 0; i < 32; ++i) { - p = (unsigned char *)&fpsimd->vregs[i]; - - for (j = 0; j < sizeof fpsimd->vregs[i]; ++j) - p[j] = j; - } - - if (set_sve(pid, sve)) { - int e = errno; - - ksft_test_result_fail("set_sve(FPSIMD): %s\n", - strerror(errno)); - if (e == ESRCH) - goto disappeared; - - goto error; - } + /* Step through every possible VQ */ + for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + vl = sve_vl_from_vq(vq); - vq = sve_vq_from_vl(sve->vl); + /* First, try to set this vector length */ + ptrace_set_get_vl(child, vl, &vl_supported); - newsvebufsz = SVE_PT_SVE_ZREG_OFFSET(vq, 1); - new_sve = newsvebuf = malloc(newsvebufsz); - if (!new_sve) { - errno = ENOMEM; - perror(NULL); - goto error; - } - - *new_sve = *sve; - new_sve->flags &= ~SVE_PT_REGS_MASK; - new_sve->flags |= SVE_PT_REGS_SVE; - memset((char *)new_sve + SVE_PT_SVE_ZREG_OFFSET(vq, 0), - 0, SVE_PT_SVE_ZREG_SIZE(vq)); - new_sve->size = SVE_PT_SVE_ZREG_OFFSET(vq, 1); - if (set_sve(pid, new_sve)) { - int e = errno; - - ksft_test_result_fail("set_sve(ZREG): %s\n", strerror(errno)); - if (e == ESRCH) - goto disappeared; - - goto error; - } - - new_sve = get_sve(pid, &newsvebuf, &newsvebufsz); - if (!new_sve) { - int e = errno; - - ksft_test_result_fail("get_sve(ZREG): %s\n", strerror(errno)); - if (e == ESRCH) - goto disappeared; - - goto error; - } - - ksft_test_result((new_sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE, - "SVE registers\n"); - if ((new_sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_SVE) - goto error; - - dump_sve_regs(new_sve, 3, sizeof fpsimd->vregs[0]); - - p = (unsigned char *)new_sve + SVE_PT_SVE_ZREG_OFFSET(vq, 1); - for (i = 0; i < sizeof fpsimd->vregs[0]; ++i) { - unsigned char expected = i; - - if (__BYTE_ORDER == __BIG_ENDIAN) - expected = sizeof fpsimd->vregs[0] - 1 - expected; - - ksft_test_result(p[i] == expected, "p[%d] == expected\n", i); - if (p[i] != expected) - goto error; + /* If the VL is supported validate data set/get */ + if (vl_supported) { + ptrace_set_sve_get_sve_data(child, vl); + ptrace_set_sve_get_fpsimd_data(child, vl); + } else { + ksft_test_result_skip("set SVE get SVE for VL %d\n", vl); + ksft_test_result_skip("set SVE get FPSIMD for VL %d\n", vl); + } } ret = EXIT_SUCCESS; @@ -309,20 +534,16 @@ disappeared: int main(void) { int ret = EXIT_SUCCESS; - __uint128_t v[NR_VREGS]; pid_t child; + srandom(getpid()); + ksft_print_header(); - ksft_set_plan(20); + ksft_set_plan(EXPECTED_TESTS); if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) ksft_exit_skip("SVE not available\n"); - sve_store_patterns(v); - - if (!check_vregs(v)) - ksft_exit_fail_msg("Initial check_vregs() failed\n"); - child = fork(); if (!child) return do_child(); diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index e3e08d9c7020..f5b1b48ffff2 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -46,130 +46,6 @@ define_accessor getz, NZR, _sve_str_v define_accessor setp, NPR, _sve_ldr_p define_accessor getp, NPR, _sve_str_p -// Print a single character x0 to stdout -// Clobbers x0-x2,x8 -function putc - str x0, [sp, #-16]! - - mov x0, #1 // STDOUT_FILENO - mov x1, sp - mov x2, #1 - mov x8, #__NR_write - svc #0 - - add sp, sp, #16 - ret -endfunction - -// Print a NUL-terminated string starting at address x0 to stdout -// Clobbers x0-x3,x8 -function puts - mov x1, x0 - - mov x2, #0 -0: ldrb w3, [x0], #1 - cbz w3, 1f - add x2, x2, #1 - b 0b - -1: mov w0, #1 // STDOUT_FILENO - mov x8, #__NR_write - svc #0 - - ret -endfunction - -// Utility macro to print a literal string -// Clobbers x0-x4,x8 -.macro puts string - .pushsection .rodata.str1.1, "aMS", 1 -.L__puts_literal\@: .string "\string" - .popsection - - ldr x0, =.L__puts_literal\@ - bl puts -.endm - -// Print an unsigned decimal number x0 to stdout -// Clobbers x0-x4,x8 -function putdec - mov x1, sp - str x30, [sp, #-32]! // Result can't be > 20 digits - - mov x2, #0 - strb w2, [x1, #-1]! // Write the NUL terminator - - mov x2, #10 -0: udiv x3, x0, x2 // div-mod loop to generate the digits - msub x0, x3, x2, x0 - add w0, w0, #'0' - strb w0, [x1, #-1]! - mov x0, x3 - cbnz x3, 0b - - ldrb w0, [x1] - cbnz w0, 1f - mov w0, #'0' // Print "0" for 0, not "" - strb w0, [x1, #-1]! - -1: mov x0, x1 - bl puts - - ldr x30, [sp], #32 - ret -endfunction - -// Print an unsigned decimal number x0 to stdout, followed by a newline -// Clobbers x0-x5,x8 -function putdecn - mov x5, x30 - - bl putdec - mov x0, #'\n' - bl putc - - ret x5 -endfunction - -// Clobbers x0-x3,x8 -function puthexb - str x30, [sp, #-0x10]! - - mov w3, w0 - lsr w0, w0, #4 - bl puthexnibble - mov w0, w3 - - ldr x30, [sp], #0x10 - // fall through to puthexnibble -endfunction -// Clobbers x0-x2,x8 -function puthexnibble - and w0, w0, #0xf - cmp w0, #10 - blo 1f - add w0, w0, #'a' - ('9' + 1) -1: add w0, w0, #'0' - b putc -endfunction - -// x0=data in, x1=size in, clobbers x0-x5,x8 -function dumphex - str x30, [sp, #-0x10]! - - mov x4, x0 - mov x5, x1 - -0: subs x5, x5, #1 - b.lo 1f - ldrb w0, [x4], #1 - bl puthexb - b 0b - -1: ldr x30, [sp], #0x10 - ret -endfunction - // Declare some storate space to shadow the SVE register contents: .pushsection .text .data @@ -184,18 +60,6 @@ scratch: .space MAXVL_B .popsection -// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0. -// Clobbers x0-x3 -function memcpy - cmp x2, #0 - b.eq 1f -0: ldrb w3, [x1], #1 - strb w3, [x0], #1 - subs x2, x2, #1 - b.ne 0b -1: ret -endfunction - // Generate a test pattern for storage in SVE registers // x0: pid (16 bits) // x1: register number (6 bits) @@ -316,33 +180,6 @@ function setup_ffr ret x4 endfunction -// Fill x1 bytes starting at x0 with 0xae (for canary purposes) -// Clobbers x1, x2. -function memfill_ae - mov w2, #0xae - b memfill -endfunction - -// Fill x1 bytes starting at x0 with 0. -// Clobbers x1, x2. -function memclr - mov w2, #0 -endfunction - // fall through to memfill - -// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2 -// Clobbers x1 -function memfill - cmp x1, #0 - b.eq 1f - -0: strb w2, [x0], #1 - subs x1, x1, #1 - b.ne 0b - -1: ret -endfunction - // Trivial memory compare: compare x2 bytes starting at address x0 with // bytes starting at address x1. // Returns only if all bytes match; otherwise, the program is aborted. diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c index c02071dcb563..272b888e018e 100644 --- a/tools/testing/selftests/arm64/fp/vec-syscfg.c +++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c @@ -109,7 +109,7 @@ static int get_child_rdvl(struct vec_data *data) /* exec() a new binary which puts the VL on stdout */ ret = execl(data->rdvl_binary, data->rdvl_binary, NULL); - fprintf(stderr, "execl(%s) failed: %d\n", + fprintf(stderr, "execl(%s) failed: %d (%s)\n", data->rdvl_binary, errno, strerror(errno)); exit(EXIT_FAILURE); @@ -180,7 +180,6 @@ static int file_read_integer(const char *name, int *val) static int file_write_integer(const char *name, int val) { FILE *f; - int ret; f = fopen(name, "w"); if (!f) { @@ -192,11 +191,6 @@ static int file_write_integer(const char *name, int val) fprintf(f, "%d", val); fclose(f); - if (ret < 0) { - ksft_test_result_fail("Error writing %d to %s\n", - val, name); - return -1; - } return 0; } @@ -335,12 +329,9 @@ static void prctl_set_same(struct vec_data *data) return; } - if (cur_vl != data->rdvl()) - ksft_test_result_pass("%s current VL is %d\n", - data->name, ret); - else - ksft_test_result_fail("%s prctl() VL %d but RDVL is %d\n", - data->name, ret, data->rdvl()); + ksft_test_result(cur_vl == data->rdvl(), + "%s set VL %d and have VL %d\n", + data->name, cur_vl, data->rdvl()); } /* Can we set a new VL for this process? */ @@ -549,6 +540,82 @@ static void prctl_set_onexec(struct vec_data *data) file_write_integer(data->default_vl_file, data->default_vl); } +/* For each VQ verify that setting via prctl() does the right thing */ +static void prctl_set_all_vqs(struct vec_data *data) +{ + int ret, vq, vl, new_vl; + int errors = 0; + + if (!data->min_vl || !data->max_vl) { + ksft_test_result_skip("%s Failed to enumerate VLs, not testing VL setting\n", + data->name); + return; + } + + for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + vl = sve_vl_from_vq(vq); + + /* Attempt to set the VL */ + ret = prctl(data->prctl_set, vl); + if (ret < 0) { + errors++; + ksft_print_msg("%s prctl set failed for %d: %d (%s)\n", + data->name, vl, + errno, strerror(errno)); + continue; + } + + new_vl = ret & PR_SVE_VL_LEN_MASK; + + /* Check that we actually have the reported new VL */ + if (data->rdvl() != new_vl) { + ksft_print_msg("Set %s VL %d but RDVL reports %d\n", + data->name, new_vl, data->rdvl()); + errors++; + } + + /* Was that the VL we asked for? */ + if (new_vl == vl) + continue; + + /* Should round up to the minimum VL if below it */ + if (vl < data->min_vl) { + if (new_vl != data->min_vl) { + ksft_print_msg("%s VL %d returned %d not minimum %d\n", + data->name, vl, new_vl, + data->min_vl); + errors++; + } + + continue; + } + + /* Should round down to maximum VL if above it */ + if (vl > data->max_vl) { + if (new_vl != data->max_vl) { + ksft_print_msg("%s VL %d returned %d not maximum %d\n", + data->name, vl, new_vl, + data->max_vl); + errors++; + } + + continue; + } + + /* Otherwise we should've rounded down */ + if (!(new_vl < vl)) { + ksft_print_msg("%s VL %d returned %d, did not round down\n", + data->name, vl, new_vl); + errors++; + + continue; + } + } + + ksft_test_result(errors == 0, "%s prctl() set all VLs, %d errors\n", + data->name, errors); +} + typedef void (*test_type)(struct vec_data *); static const test_type tests[] = { @@ -561,10 +628,12 @@ static const test_type tests[] = { proc_write_max, prctl_get, + prctl_set_same, prctl_set, prctl_set_no_child, prctl_set_for_child, prctl_set_onexec, + prctl_set_all_vqs, }; int main(void) diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index 0e78b49d0f2f..fbcbdb6963b3 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -8,3 +8,4 @@ futex_wait_uninitialized_heap futex_wait_wouldblock futex_wait futex_requeue +futex_waitv diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index bd1fec59e010..5cc38de9d8ea 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -17,7 +17,8 @@ TEST_GEN_FILES := \ futex_wait_uninitialized_heap \ futex_wait_private_mapped_file \ futex_wait \ - futex_requeue + futex_requeue \ + futex_waitv TEST_PROGS := run.sh diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c index 1f8f6daaf1e7..3651ce17beeb 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c +++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c @@ -17,6 +17,7 @@ #include <pthread.h> #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-timeout" @@ -96,6 +97,12 @@ int main(int argc, char *argv[]) struct timespec to; pthread_t thread; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -118,7 +125,7 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(7); + ksft_set_plan(9); ksft_print_msg("%s: Block on a futex and wait for timeout\n", basename(argv[0])); ksft_print_msg("\tArguments: timeout=%ldns\n", timeout_ns); @@ -175,6 +182,18 @@ int main(int argc, char *argv[]) res = futex_lock_pi(&futex_pi, NULL, 0, FUTEX_CLOCK_REALTIME); test_timeout(res, &ret, "futex_lock_pi invalid timeout flag", ENOSYS); + /* futex_waitv with CLOCK_MONOTONIC */ + if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + test_timeout(res, &ret, "futex_waitv monotonic", ETIMEDOUT); + + /* futex_waitv with CLOCK_REALTIME */ + if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns)) + return RET_FAIL; + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_REALTIME); + test_timeout(res, &ret, "futex_waitv realtime", ETIMEDOUT); + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c index 0ae390ff8164..7d7a6a06cdb7 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c +++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c @@ -22,6 +22,7 @@ #include <string.h> #include <time.h> #include "futextest.h" +#include "futex2test.h" #include "logging.h" #define TEST_NAME "futex-wait-wouldblock" @@ -42,6 +43,12 @@ int main(int argc, char *argv[]) futex_t f1 = FUTEX_INITIALIZER; int res, ret = RET_PASS; int c; + struct futex_waitv waitv = { + .uaddr = (uintptr_t)&f1, + .val = f1+1, + .flags = FUTEX_32, + .__reserved = 0 + }; while ((c = getopt(argc, argv, "cht:v:")) != -1) { switch (c) { @@ -61,18 +68,44 @@ int main(int argc, char *argv[]) } ksft_print_header(); - ksft_set_plan(1); + ksft_set_plan(2); ksft_print_msg("%s: Test the unexpected futex value in FUTEX_WAIT\n", basename(argv[0])); info("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); res = futex_wait(&f1, f1+1, &to, FUTEX_PRIVATE_FLAG); if (!res || errno != EWOULDBLOCK) { - fail("futex_wait returned: %d %s\n", - res ? errno : res, res ? strerror(errno) : ""); + ksft_test_result_fail("futex_wait returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_wait\n"); } - print_result(TEST_NAME, ret); + if (clock_gettime(CLOCK_MONOTONIC, &to)) { + error("clock_gettime failed\n", errno); + return errno; + } + + to.tv_nsec += timeout_ns; + + if (to.tv_nsec >= 1000000000) { + to.tv_sec++; + to.tv_nsec -= 1000000000; + } + + info("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1); + res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC); + if (!res || errno != EWOULDBLOCK) { + ksft_test_result_pass("futex_waitv returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv\n"); + } + + ksft_print_cnts(); return ret; } diff --git a/tools/testing/selftests/futex/functional/futex_waitv.c b/tools/testing/selftests/futex/functional/futex_waitv.c new file mode 100644 index 000000000000..a94337f677e1 --- /dev/null +++ b/tools/testing/selftests/futex/functional/futex_waitv.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * futex_waitv() test by André Almeida <andrealmeid@collabora.com> + * + * Copyright 2021 Collabora Ltd. + */ + +#include <errno.h> +#include <error.h> +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <pthread.h> +#include <stdint.h> +#include <sys/shm.h> +#include "futextest.h" +#include "futex2test.h" +#include "logging.h" + +#define TEST_NAME "futex-wait" +#define WAKE_WAIT_US 10000 +#define NR_FUTEXES 30 +static struct futex_waitv waitv[NR_FUTEXES]; +u_int32_t futexes[NR_FUTEXES] = {0}; + +void usage(char *prog) +{ + printf("Usage: %s\n", prog); + printf(" -c Use color\n"); + printf(" -h Display this help message\n"); + printf(" -v L Verbosity level: %d=QUIET %d=CRITICAL %d=INFO\n", + VQUIET, VCRITICAL, VINFO); +} + +void *waiterfn(void *arg) +{ + struct timespec to; + int res; + + /* setting absolute timeout for futex2 */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res < 0) { + ksft_test_result_fail("futex_waitv returned: %d %s\n", + errno, strerror(errno)); + } else if (res != NR_FUTEXES - 1) { + ksft_test_result_fail("futex_waitv returned: %d, expecting %d\n", + res, NR_FUTEXES - 1); + } + + return NULL; +} + +int main(int argc, char *argv[]) +{ + pthread_t waiter; + int res, ret = RET_PASS; + struct timespec to; + int c, i; + + while ((c = getopt(argc, argv, "cht:v:")) != -1) { + switch (c) { + case 'c': + log_color(1); + break; + case 'h': + usage(basename(argv[0])); + exit(0); + case 'v': + log_verbosity(atoi(optarg)); + break; + default: + usage(basename(argv[0])); + exit(1); + } + } + + ksft_print_header(); + ksft_set_plan(7); + ksft_print_msg("%s: Test FUTEX_WAITV\n", + basename(argv[0])); + + for (i = 0; i < NR_FUTEXES; i++) { + waitv[i].uaddr = (uintptr_t)&futexes[i]; + waitv[i].flags = FUTEX_32 | FUTEX_PRIVATE_FLAG; + waitv[i].val = 0; + waitv[i].__reserved = 0; + } + + /* Private waitv */ + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); + + usleep(WAKE_WAIT_US); + + res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, FUTEX_PRIVATE_FLAG); + if (res != 1) { + ksft_test_result_fail("futex_wake private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv private\n"); + } + + /* Shared waitv */ + for (i = 0; i < NR_FUTEXES; i++) { + int shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666); + + if (shm_id < 0) { + perror("shmget"); + exit(1); + } + + unsigned int *shared_data = shmat(shm_id, NULL, 0); + + *shared_data = 0; + waitv[i].uaddr = (uintptr_t)shared_data; + waitv[i].flags = FUTEX_32; + waitv[i].val = 0; + waitv[i].__reserved = 0; + } + + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); + + usleep(WAKE_WAIT_US); + + res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, 0); + if (res != 1) { + ksft_test_result_fail("futex_wake shared returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv shared\n"); + } + + for (i = 0; i < NR_FUTEXES; i++) + shmdt(u64_to_ptr(waitv[i].uaddr)); + + /* Testing a waiter without FUTEX_32 flag */ + waitv[0].flags = FUTEX_PRIVATE_FLAG; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv without FUTEX_32\n"); + } + + /* Testing a waiter with an unaligned address */ + waitv[0].flags = FUTEX_PRIVATE_FLAG | FUTEX_32; + waitv[0].uaddr = 1; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_wake private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv with an unaligned address\n"); + } + + /* Testing a NULL address for waiters.uaddr */ + waitv[0].uaddr = 0x00000000; + + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv NULL address in waitv.uaddr\n"); + } + + /* Testing a NULL address for *waiters */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv NULL address in *waiters\n"); + } + + /* Testing an invalid clockid */ + if (clock_gettime(CLOCK_MONOTONIC, &to)) + error("gettime64 failed\n", errno); + + to.tv_sec++; + + res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_TAI); + if (res == EINVAL) { + ksft_test_result_fail("futex_waitv private returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_waitv invalid clockid\n"); + } + + ksft_print_cnts(); + return ret; +} diff --git a/tools/testing/selftests/futex/functional/run.sh b/tools/testing/selftests/futex/functional/run.sh index 11a9d62290f5..5ccd599da6c3 100755 --- a/tools/testing/selftests/futex/functional/run.sh +++ b/tools/testing/selftests/futex/functional/run.sh @@ -79,3 +79,6 @@ echo echo ./futex_requeue $COLOR + +echo +./futex_waitv $COLOR diff --git a/tools/testing/selftests/futex/include/futex2test.h b/tools/testing/selftests/futex/include/futex2test.h new file mode 100644 index 000000000000..9d305520e849 --- /dev/null +++ b/tools/testing/selftests/futex/include/futex2test.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Futex2 library addons for futex tests + * + * Copyright 2021 Collabora Ltd. + */ +#include <stdint.h> + +#define u64_to_ptr(x) ((void *)(uintptr_t)(x)) + +/** + * futex_waitv - Wait at multiple futexes, wake on any + * @waiters: Array of waiters + * @nr_waiters: Length of waiters array + * @flags: Operation flags + * @timo: Optional timeout for operation + */ +static inline int futex_waitv(volatile struct futex_waitv *waiters, unsigned long nr_waiters, + unsigned long flags, struct timespec *timo, clockid_t clockid) +{ + return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, timo, clockid); +} diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 7db9cf822dc7..8109b17dc764 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -62,6 +62,17 @@ enum pid_type {PIDTYPE_PID = 0, PIDTYPE_TGID, PIDTYPE_PGID}; const int THREAD_CLONE_FLAGS = CLONE_THREAD | CLONE_SIGHAND | CLONE_FS | CLONE_VM | CLONE_FILES; +struct child_args { + int num_threads; + int pfd[2]; + int cpid; + int thr_tids[MAX_THREADS]; +}; + +static struct child_args procs[MAX_PROCESSES]; +static int num_processes = 2; +static int need_cleanup = 0; + static int _prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { @@ -78,8 +89,14 @@ static int _prctl(int option, unsigned long arg2, unsigned long arg3, unsigned l #define handle_error(msg) __handle_error(__FILE__, __LINE__, msg) static void __handle_error(char *fn, int ln, char *msg) { + int pidx; printf("(%s:%d) - ", fn, ln); perror(msg); + if (need_cleanup) { + for (pidx = 0; pidx < num_processes; ++pidx) + kill(procs[pidx].cpid, 15); + need_cleanup = 0; + } exit(EXIT_FAILURE); } @@ -106,13 +123,6 @@ static unsigned long get_cs_cookie(int pid) return cookie; } -struct child_args { - int num_threads; - int pfd[2]; - int cpid; - int thr_tids[MAX_THREADS]; -}; - static int child_func_thread(void __attribute__((unused))*arg) { while (1) @@ -212,10 +222,7 @@ void _validate(int line, int val, char *msg) int main(int argc, char *argv[]) { - struct child_args procs[MAX_PROCESSES]; - int keypress = 0; - int num_processes = 2; int num_threads = 3; int delay = 0; int res = 0; @@ -262,6 +269,7 @@ int main(int argc, char *argv[]) printf("\n## Create a thread/process/process group hiearchy\n"); create_processes(num_processes, num_threads, procs); + need_cleanup = 1; disp_processes(num_processes, procs); validate(get_cs_cookie(0) == 0); diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index b4142cd1c5c2..8a1f62ab3c8e 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -18,7 +18,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \ - corrupt_xstate_header + corrupt_xstate_header amx # Some selftests require 32bit support enabled also on 64bit systems TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall diff --git a/tools/testing/selftests/x86/amx.c b/tools/testing/selftests/x86/amx.c new file mode 100644 index 000000000000..3615ef4a48bb --- /dev/null +++ b/tools/testing/selftests/x86/amx.c @@ -0,0 +1,851 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <err.h> +#include <errno.h> +#include <pthread.h> +#include <setjmp.h> +#include <stdio.h> +#include <string.h> +#include <stdbool.h> +#include <unistd.h> +#include <x86intrin.h> + +#include <sys/auxv.h> +#include <sys/mman.h> +#include <sys/shm.h> +#include <sys/syscall.h> +#include <sys/wait.h> + +#ifndef __x86_64__ +# error This test is 64-bit only +#endif + +#define XSAVE_HDR_OFFSET 512 +#define XSAVE_HDR_SIZE 64 + +struct xsave_buffer { + union { + struct { + char legacy[XSAVE_HDR_OFFSET]; + char header[XSAVE_HDR_SIZE]; + char extended[0]; + }; + char bytes[0]; + }; +}; + +static inline uint64_t xgetbv(uint32_t index) +{ + uint32_t eax, edx; + + asm volatile("xgetbv;" + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((uint64_t)edx << 32); +} + +static inline void cpuid(uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx) +{ + asm volatile("cpuid;" + : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline void xsave(struct xsave_buffer *xbuf, uint64_t rfbm) +{ + uint32_t rfbm_lo = rfbm; + uint32_t rfbm_hi = rfbm >> 32; + + asm volatile("xsave (%%rdi)" + : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi) + : "memory"); +} + +static inline void xrstor(struct xsave_buffer *xbuf, uint64_t rfbm) +{ + uint32_t rfbm_lo = rfbm; + uint32_t rfbm_hi = rfbm >> 32; + + asm volatile("xrstor (%%rdi)" + : : "D" (xbuf), "a" (rfbm_lo), "d" (rfbm_hi)); +} + +/* err() exits and will not return */ +#define fatal_error(msg, ...) err(1, "[FAIL]\t" msg, ##__VA_ARGS__) + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + fatal_error("sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + fatal_error("sigaction"); +} + +#define XFEATURE_XTILECFG 17 +#define XFEATURE_XTILEDATA 18 +#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG) +#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) + +#define CPUID_LEAF1_ECX_XSAVE_MASK (1 << 26) +#define CPUID_LEAF1_ECX_OSXSAVE_MASK (1 << 27) +static inline void check_cpuid_xsave(void) +{ + uint32_t eax, ebx, ecx, edx; + + /* + * CPUID.1:ECX.XSAVE[bit 26] enumerates general + * support for the XSAVE feature set, including + * XGETBV. + */ + eax = 1; + ecx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + if (!(ecx & CPUID_LEAF1_ECX_XSAVE_MASK)) + fatal_error("cpuid: no CPU xsave support"); + if (!(ecx & CPUID_LEAF1_ECX_OSXSAVE_MASK)) + fatal_error("cpuid: no OS xsave support"); +} + +static uint32_t xbuf_size; + +static struct { + uint32_t xbuf_offset; + uint32_t size; +} xtiledata; + +#define CPUID_LEAF_XSTATE 0xd +#define CPUID_SUBLEAF_XSTATE_USER 0x0 +#define TILE_CPUID 0x1d +#define TILE_PALETTE_ID 0x1 + +static void check_cpuid_xtiledata(void) +{ + uint32_t eax, ebx, ecx, edx; + + eax = CPUID_LEAF_XSTATE; + ecx = CPUID_SUBLEAF_XSTATE_USER; + cpuid(&eax, &ebx, &ecx, &edx); + + /* + * EBX enumerates the size (in bytes) required by the XSAVE + * instruction for an XSAVE area containing all the user state + * components corresponding to bits currently set in XCR0. + * + * Stash that off so it can be used to allocate buffers later. + */ + xbuf_size = ebx; + + eax = CPUID_LEAF_XSTATE; + ecx = XFEATURE_XTILEDATA; + + cpuid(&eax, &ebx, &ecx, &edx); + /* + * eax: XTILEDATA state component size + * ebx: XTILEDATA state component offset in user buffer + */ + if (!eax || !ebx) + fatal_error("xstate cpuid: invalid tile data size/offset: %d/%d", + eax, ebx); + + xtiledata.size = eax; + xtiledata.xbuf_offset = ebx; +} + +/* The helpers for managing XSAVE buffer and tile states: */ + +struct xsave_buffer *alloc_xbuf(void) +{ + struct xsave_buffer *xbuf; + + /* XSAVE buffer should be 64B-aligned. */ + xbuf = aligned_alloc(64, xbuf_size); + if (!xbuf) + fatal_error("aligned_alloc()"); + return xbuf; +} + +static inline void clear_xstate_header(struct xsave_buffer *buffer) +{ + memset(&buffer->header, 0, sizeof(buffer->header)); +} + +static inline uint64_t get_xstatebv(struct xsave_buffer *buffer) +{ + /* XSTATE_BV is at the beginning of the header: */ + return *(uint64_t *)&buffer->header; +} + +static inline void set_xstatebv(struct xsave_buffer *buffer, uint64_t bv) +{ + /* XSTATE_BV is at the beginning of the header: */ + *(uint64_t *)(&buffer->header) = bv; +} + +static void set_rand_tiledata(struct xsave_buffer *xbuf) +{ + int *ptr = (int *)&xbuf->bytes[xtiledata.xbuf_offset]; + int data; + int i; + + /* + * Ensure that 'data' is never 0. This ensures that + * the registers are never in their initial configuration + * and thus never tracked as being in the init state. + */ + data = rand() | 1; + + for (i = 0; i < xtiledata.size / sizeof(int); i++, ptr++) + *ptr = data; +} + +struct xsave_buffer *stashed_xsave; + +static void init_stashed_xsave(void) +{ + stashed_xsave = alloc_xbuf(); + if (!stashed_xsave) + fatal_error("failed to allocate stashed_xsave\n"); + clear_xstate_header(stashed_xsave); +} + +static void free_stashed_xsave(void) +{ + free(stashed_xsave); +} + +/* See 'struct _fpx_sw_bytes' at sigcontext.h */ +#define SW_BYTES_OFFSET 464 +/* N.B. The struct's field name varies so read from the offset. */ +#define SW_BYTES_BV_OFFSET (SW_BYTES_OFFSET + 8) + +static inline struct _fpx_sw_bytes *get_fpx_sw_bytes(void *buffer) +{ + return (struct _fpx_sw_bytes *)(buffer + SW_BYTES_OFFSET); +} + +static inline uint64_t get_fpx_sw_bytes_features(void *buffer) +{ + return *(uint64_t *)(buffer + SW_BYTES_BV_OFFSET); +} + +/* Work around printf() being unsafe in signals: */ +#define SIGNAL_BUF_LEN 1000 +char signal_message_buffer[SIGNAL_BUF_LEN]; +void sig_print(char *msg) +{ + int left = SIGNAL_BUF_LEN - strlen(signal_message_buffer) - 1; + + strncat(signal_message_buffer, msg, left); +} + +static volatile bool noperm_signaled; +static int noperm_errs; +/* + * Signal handler for when AMX is used but + * permission has not been obtained. + */ +static void handle_noperm(int sig, siginfo_t *si, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t *)ctx_void; + void *xbuf = ctx->uc_mcontext.fpregs; + struct _fpx_sw_bytes *sw_bytes; + uint64_t features; + + /* Reset the signal message buffer: */ + signal_message_buffer[0] = '\0'; + sig_print("\tAt SIGILL handler,\n"); + + if (si->si_code != ILL_ILLOPC) { + noperm_errs++; + sig_print("[FAIL]\tInvalid signal code.\n"); + } else { + sig_print("[OK]\tValid signal code (ILL_ILLOPC).\n"); + } + + sw_bytes = get_fpx_sw_bytes(xbuf); + /* + * Without permission, the signal XSAVE buffer should not + * have room for AMX register state (aka. xtiledata). + * Check that the size does not overlap with where xtiledata + * will reside. + * + * This also implies that no state components *PAST* + * XTILEDATA (features >=19) can be present in the buffer. + */ + if (sw_bytes->xstate_size <= xtiledata.xbuf_offset) { + sig_print("[OK]\tValid xstate size\n"); + } else { + noperm_errs++; + sig_print("[FAIL]\tInvalid xstate size\n"); + } + + features = get_fpx_sw_bytes_features(xbuf); + /* + * Without permission, the XTILEDATA feature + * bit should not be set. + */ + if ((features & XFEATURE_MASK_XTILEDATA) == 0) { + sig_print("[OK]\tValid xstate mask\n"); + } else { + noperm_errs++; + sig_print("[FAIL]\tInvalid xstate mask\n"); + } + + noperm_signaled = true; + ctx->uc_mcontext.gregs[REG_RIP] += 3; /* Skip the faulting XRSTOR */ +} + +/* Return true if XRSTOR is successful; otherwise, false. */ +static inline bool xrstor_safe(struct xsave_buffer *xbuf, uint64_t mask) +{ + noperm_signaled = false; + xrstor(xbuf, mask); + + /* Print any messages produced by the signal code: */ + printf("%s", signal_message_buffer); + /* + * Reset the buffer to make sure any future printing + * only outputs new messages: + */ + signal_message_buffer[0] = '\0'; + + if (noperm_errs) + fatal_error("saw %d errors in noperm signal handler\n", noperm_errs); + + return !noperm_signaled; +} + +/* + * Use XRSTOR to populate the XTILEDATA registers with + * random data. + * + * Return true if successful; otherwise, false. + */ +static inline bool load_rand_tiledata(struct xsave_buffer *xbuf) +{ + clear_xstate_header(xbuf); + set_xstatebv(xbuf, XFEATURE_MASK_XTILEDATA); + set_rand_tiledata(xbuf); + return xrstor_safe(xbuf, XFEATURE_MASK_XTILEDATA); +} + +/* Return XTILEDATA to its initial configuration. */ +static inline void init_xtiledata(void) +{ + clear_xstate_header(stashed_xsave); + xrstor_safe(stashed_xsave, XFEATURE_MASK_XTILEDATA); +} + +enum expected_result { FAIL_EXPECTED, SUCCESS_EXPECTED }; + +/* arch_prctl() and sigaltstack() test */ + +#define ARCH_GET_XCOMP_PERM 0x1022 +#define ARCH_REQ_XCOMP_PERM 0x1023 + +static void req_xtiledata_perm(void) +{ + syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA); +} + +static void validate_req_xcomp_perm(enum expected_result exp) +{ + unsigned long bitmask; + long rc; + + rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, XFEATURE_XTILEDATA); + if (exp == FAIL_EXPECTED) { + if (rc) { + printf("[OK]\tARCH_REQ_XCOMP_PERM saw expected failure..\n"); + return; + } + + fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected success.\n"); + } else if (rc) { + fatal_error("ARCH_REQ_XCOMP_PERM saw unexpected failure.\n"); + } + + rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_PERM, &bitmask); + if (rc) { + fatal_error("prctl(ARCH_GET_XCOMP_PERM) error: %ld", rc); + } else if (bitmask & XFEATURE_MASK_XTILE) { + printf("\tARCH_REQ_XCOMP_PERM is successful.\n"); + } +} + +static void validate_xcomp_perm(enum expected_result exp) +{ + bool load_success = load_rand_tiledata(stashed_xsave); + + if (exp == FAIL_EXPECTED) { + if (load_success) { + noperm_errs++; + printf("[FAIL]\tLoad tiledata succeeded.\n"); + } else { + printf("[OK]\tLoad tiledata failed.\n"); + } + } else if (exp == SUCCESS_EXPECTED) { + if (load_success) { + printf("[OK]\tLoad tiledata succeeded.\n"); + } else { + noperm_errs++; + printf("[FAIL]\tLoad tiledata failed.\n"); + } + } +} + +#ifndef AT_MINSIGSTKSZ +# define AT_MINSIGSTKSZ 51 +#endif + +static void *alloc_altstack(unsigned int size) +{ + void *altstack; + + altstack = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + + if (altstack == MAP_FAILED) + fatal_error("mmap() for altstack"); + + return altstack; +} + +static void setup_altstack(void *addr, unsigned long size, enum expected_result exp) +{ + stack_t ss; + int rc; + + memset(&ss, 0, sizeof(ss)); + ss.ss_size = size; + ss.ss_sp = addr; + + rc = sigaltstack(&ss, NULL); + + if (exp == FAIL_EXPECTED) { + if (rc) { + printf("[OK]\tsigaltstack() failed.\n"); + } else { + fatal_error("sigaltstack() succeeded unexpectedly.\n"); + } + } else if (rc) { + fatal_error("sigaltstack()"); + } +} + +static void test_dynamic_sigaltstack(void) +{ + unsigned int small_size, enough_size; + unsigned long minsigstksz; + void *altstack; + + minsigstksz = getauxval(AT_MINSIGSTKSZ); + printf("\tAT_MINSIGSTKSZ = %lu\n", minsigstksz); + /* + * getauxval() itself can return 0 for failure or + * success. But, in this case, AT_MINSIGSTKSZ + * will always return a >=0 value if implemented. + * Just check for 0. + */ + if (minsigstksz == 0) { + printf("no support for AT_MINSIGSTKSZ, skipping sigaltstack tests\n"); + return; + } + + enough_size = minsigstksz * 2; + + altstack = alloc_altstack(enough_size); + printf("\tAllocate memory for altstack (%u bytes).\n", enough_size); + + /* + * Try setup_altstack() with a size which can not fit + * XTILEDATA. ARCH_REQ_XCOMP_PERM should fail. + */ + small_size = minsigstksz - xtiledata.size; + printf("\tAfter sigaltstack() with small size (%u bytes).\n", small_size); + setup_altstack(altstack, small_size, SUCCESS_EXPECTED); + validate_req_xcomp_perm(FAIL_EXPECTED); + + /* + * Try setup_altstack() with a size derived from + * AT_MINSIGSTKSZ. It should be more than large enough + * and thus ARCH_REQ_XCOMP_PERM should succeed. + */ + printf("\tAfter sigaltstack() with enough size (%u bytes).\n", enough_size); + setup_altstack(altstack, enough_size, SUCCESS_EXPECTED); + validate_req_xcomp_perm(SUCCESS_EXPECTED); + + /* + * Try to coerce setup_altstack() to again accept a + * too-small altstack. This ensures that big-enough + * sigaltstacks can not shrink to a too-small value + * once XTILEDATA permission is established. + */ + printf("\tThen, sigaltstack() with small size (%u bytes).\n", small_size); + setup_altstack(altstack, small_size, FAIL_EXPECTED); +} + +static void test_dynamic_state(void) +{ + pid_t parent, child, grandchild; + + parent = fork(); + if (parent < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (parent > 0) { + int status; + /* fork() succeeded. Now in the parent. */ + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("arch_prctl test parent exit"); + return; + } + /* fork() succeeded. Now in the child . */ + + printf("[RUN]\tCheck ARCH_REQ_XCOMP_PERM around process fork() and sigaltack() test.\n"); + + printf("\tFork a child.\n"); + child = fork(); + if (child < 0) { + fatal_error("fork"); + } else if (child > 0) { + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("arch_prctl test child exit"); + _exit(0); + } + + /* + * The permission request should fail without an + * XTILEDATA-compatible signal stack + */ + printf("\tTest XCOMP_PERM at child.\n"); + validate_xcomp_perm(FAIL_EXPECTED); + + /* + * Set up an XTILEDATA-compatible signal stack and + * also obtain permission to populate XTILEDATA. + */ + printf("\tTest dynamic sigaltstack at child:\n"); + test_dynamic_sigaltstack(); + + /* Ensure that XTILEDATA can be populated. */ + printf("\tTest XCOMP_PERM again at child.\n"); + validate_xcomp_perm(SUCCESS_EXPECTED); + + printf("\tFork a grandchild.\n"); + grandchild = fork(); + if (grandchild < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (!grandchild) { + /* fork() succeeded. Now in the (grand)child. */ + printf("\tTest XCOMP_PERM at grandchild.\n"); + + /* + * Ensure that the grandchild inherited + * permission and a compatible sigaltstack: + */ + validate_xcomp_perm(SUCCESS_EXPECTED); + } else { + int status; + /* fork() succeeded. Now in the parent. */ + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("fork test grandchild"); + } + + _exit(0); +} + +/* + * Save current register state and compare it to @xbuf1.' + * + * Returns false if @xbuf1 matches the registers. + * Returns true if @xbuf1 differs from the registers. + */ +static inline bool __validate_tiledata_regs(struct xsave_buffer *xbuf1) +{ + struct xsave_buffer *xbuf2; + int ret; + + xbuf2 = alloc_xbuf(); + if (!xbuf2) + fatal_error("failed to allocate XSAVE buffer\n"); + + xsave(xbuf2, XFEATURE_MASK_XTILEDATA); + ret = memcmp(&xbuf1->bytes[xtiledata.xbuf_offset], + &xbuf2->bytes[xtiledata.xbuf_offset], + xtiledata.size); + + free(xbuf2); + + if (ret == 0) + return false; + return true; +} + +static inline void validate_tiledata_regs_same(struct xsave_buffer *xbuf) +{ + int ret = __validate_tiledata_regs(xbuf); + + if (ret != 0) + fatal_error("TILEDATA registers changed"); +} + +static inline void validate_tiledata_regs_changed(struct xsave_buffer *xbuf) +{ + int ret = __validate_tiledata_regs(xbuf); + + if (ret == 0) + fatal_error("TILEDATA registers did not change"); +} + +/* tiledata inheritance test */ + +static void test_fork(void) +{ + pid_t child, grandchild; + + child = fork(); + if (child < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (child > 0) { + /* fork() succeeded. Now in the parent. */ + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("fork test child"); + return; + } + /* fork() succeeded. Now in the child. */ + printf("[RUN]\tCheck tile data inheritance.\n\tBefore fork(), load tiledata\n"); + + load_rand_tiledata(stashed_xsave); + + grandchild = fork(); + if (grandchild < 0) { + /* fork() failed */ + fatal_error("fork"); + } else if (grandchild > 0) { + /* fork() succeeded. Still in the first child. */ + int status; + + wait(&status); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + fatal_error("fork test grand child"); + _exit(0); + } + /* fork() succeeded. Now in the (grand)child. */ + + /* + * TILEDATA registers are not preserved across fork(). + * Ensure that their value has changed: + */ + validate_tiledata_regs_changed(stashed_xsave); + + _exit(0); +} + +/* Context switching test */ + +static struct _ctxtswtest_cfg { + unsigned int iterations; + unsigned int num_threads; +} ctxtswtest_config; + +struct futex_info { + pthread_t thread; + int nr; + pthread_mutex_t mutex; + struct futex_info *next; +}; + +static void *check_tiledata(void *info) +{ + struct futex_info *finfo = (struct futex_info *)info; + struct xsave_buffer *xbuf; + int i; + + xbuf = alloc_xbuf(); + if (!xbuf) + fatal_error("unable to allocate XSAVE buffer"); + + /* + * Load random data into 'xbuf' and then restore + * it to the tile registers themselves. + */ + load_rand_tiledata(xbuf); + for (i = 0; i < ctxtswtest_config.iterations; i++) { + pthread_mutex_lock(&finfo->mutex); + + /* + * Ensure the register values have not + * diverged from those recorded in 'xbuf'. + */ + validate_tiledata_regs_same(xbuf); + + /* Load new, random values into xbuf and registers */ + load_rand_tiledata(xbuf); + + /* + * The last thread's last unlock will be for + * thread 0's mutex. However, thread 0 will + * have already exited the loop and the mutex + * will already be unlocked. + * + * Because this is not an ERRORCHECK mutex, + * that inconsistency will be silently ignored. + */ + pthread_mutex_unlock(&finfo->next->mutex); + } + + free(xbuf); + /* + * Return this thread's finfo, which is + * a unique value for this thread. + */ + return finfo; +} + +static int create_threads(int num, struct futex_info *finfo) +{ + int i; + + for (i = 0; i < num; i++) { + int next_nr; + + finfo[i].nr = i; + /* + * Thread 'i' will wait on this mutex to + * be unlocked. Lock it immediately after + * initialization: + */ + pthread_mutex_init(&finfo[i].mutex, NULL); + pthread_mutex_lock(&finfo[i].mutex); + + next_nr = (i + 1) % num; + finfo[i].next = &finfo[next_nr]; + + if (pthread_create(&finfo[i].thread, NULL, check_tiledata, &finfo[i])) + fatal_error("pthread_create()"); + } + return 0; +} + +static void affinitize_cpu0(void) +{ + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) + fatal_error("sched_setaffinity to CPU 0"); +} + +static void test_context_switch(void) +{ + struct futex_info *finfo; + int i; + + /* Affinitize to one CPU to force context switches */ + affinitize_cpu0(); + + req_xtiledata_perm(); + + printf("[RUN]\tCheck tiledata context switches, %d iterations, %d threads.\n", + ctxtswtest_config.iterations, + ctxtswtest_config.num_threads); + + + finfo = malloc(sizeof(*finfo) * ctxtswtest_config.num_threads); + if (!finfo) + fatal_error("malloc()"); + + create_threads(ctxtswtest_config.num_threads, finfo); + + /* + * This thread wakes up thread 0 + * Thread 0 will wake up 1 + * Thread 1 will wake up 2 + * ... + * the last thread will wake up 0 + * + * ... this will repeat for the configured + * number of iterations. + */ + pthread_mutex_unlock(&finfo[0].mutex); + + /* Wait for all the threads to finish: */ + for (i = 0; i < ctxtswtest_config.num_threads; i++) { + void *thread_retval; + int rc; + + rc = pthread_join(finfo[i].thread, &thread_retval); + + if (rc) + fatal_error("pthread_join() failed for thread %d err: %d\n", + i, rc); + + if (thread_retval != &finfo[i]) + fatal_error("unexpected thread retval for thread %d: %p\n", + i, thread_retval); + + } + + printf("[OK]\tNo incorrect case was found.\n"); + + free(finfo); +} + +int main(void) +{ + /* Check hardware availability at first */ + check_cpuid_xsave(); + check_cpuid_xtiledata(); + + init_stashed_xsave(); + sethandler(SIGILL, handle_noperm, 0); + + test_dynamic_state(); + + /* Request permission for the following tests */ + req_xtiledata_perm(); + + test_fork(); + + ctxtswtest_config.iterations = 10; + ctxtswtest_config.num_threads = 5; + test_context_switch(); + + clearhandler(SIGILL); + free_stashed_xsave(); + + return 0; +} |