diff options
Diffstat (limited to 'tools')
93 files changed, 3135 insertions, 1084 deletions
diff --git a/tools/arch/loongarch/include/uapi/asm/perf_regs.h b/tools/arch/loongarch/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..29d69c00fc7a --- /dev/null +++ b/tools/arch/loongarch/include/uapi/asm/perf_regs.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_LOONGARCH_PERF_REGS_H +#define _ASM_LOONGARCH_PERF_REGS_H + +enum perf_event_loongarch_regs { + PERF_REG_LOONGARCH_PC, + PERF_REG_LOONGARCH_R1, + PERF_REG_LOONGARCH_R2, + PERF_REG_LOONGARCH_R3, + PERF_REG_LOONGARCH_R4, + PERF_REG_LOONGARCH_R5, + PERF_REG_LOONGARCH_R6, + PERF_REG_LOONGARCH_R7, + PERF_REG_LOONGARCH_R8, + PERF_REG_LOONGARCH_R9, + PERF_REG_LOONGARCH_R10, + PERF_REG_LOONGARCH_R11, + PERF_REG_LOONGARCH_R12, + PERF_REG_LOONGARCH_R13, + PERF_REG_LOONGARCH_R14, + PERF_REG_LOONGARCH_R15, + PERF_REG_LOONGARCH_R16, + PERF_REG_LOONGARCH_R17, + PERF_REG_LOONGARCH_R18, + PERF_REG_LOONGARCH_R19, + PERF_REG_LOONGARCH_R20, + PERF_REG_LOONGARCH_R21, + PERF_REG_LOONGARCH_R22, + PERF_REG_LOONGARCH_R23, + PERF_REG_LOONGARCH_R24, + PERF_REG_LOONGARCH_R25, + PERF_REG_LOONGARCH_R26, + PERF_REG_LOONGARCH_R27, + PERF_REG_LOONGARCH_R28, + PERF_REG_LOONGARCH_R29, + PERF_REG_LOONGARCH_R30, + PERF_REG_LOONGARCH_R31, + PERF_REG_LOONGARCH_MAX, +}; +#endif /* _ASM_LOONGARCH_PERF_REGS_H */ diff --git a/tools/arch/loongarch/include/uapi/asm/unistd.h b/tools/arch/loongarch/include/uapi/asm/unistd.h new file mode 100644 index 000000000000..0c743344e92d --- /dev/null +++ b/tools/arch/loongarch/include/uapi/asm/unistd.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 + +#include <asm-generic/unistd.h> diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h index 1343a62106de..46d7e06763c9 100644 --- a/tools/arch/x86/include/asm/orc_types.h +++ b/tools/arch/x86/include/asm/orc_types.h @@ -39,6 +39,12 @@ #define ORC_REG_SP_INDIRECT 9 #define ORC_REG_MAX 15 +#define ORC_TYPE_UNDEFINED 0 +#define ORC_TYPE_END_OF_STACK 1 +#define ORC_TYPE_CALL 2 +#define ORC_TYPE_REGS 3 +#define ORC_TYPE_REGS_PARTIAL 4 + #ifndef __ASSEMBLY__ #include <asm/byteorder.h> @@ -56,16 +62,14 @@ struct orc_entry { #if defined(__LITTLE_ENDIAN_BITFIELD) unsigned sp_reg:4; unsigned bp_reg:4; - unsigned type:2; + unsigned type:3; unsigned signal:1; - unsigned end:1; #elif defined(__BIG_ENDIAN_BITFIELD) unsigned bp_reg:4; unsigned sp_reg:4; unsigned unused:4; - unsigned end:1; unsigned signal:1; - unsigned type:2; + unsigned type:3; #endif } __packed; diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h deleted file mode 100644 index 9ac3df3fccf0..000000000000 --- a/tools/include/linux/objtool.h +++ /dev/null @@ -1,200 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_OBJTOOL_H -#define _LINUX_OBJTOOL_H - -#ifndef __ASSEMBLY__ - -#include <linux/types.h> - -/* - * This struct is used by asm and inline asm code to manually annotate the - * location of registers on the stack. - */ -struct unwind_hint { - u32 ip; - s16 sp_offset; - u8 sp_reg; - u8 type; - u8 signal; - u8 end; -}; -#endif - -/* - * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP - * (the caller's SP right before it made the call). Used for all callable - * functions, i.e. all C code and all callable asm functions. - * - * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset - * points to a fully populated pt_regs from a syscall, interrupt, or exception. - * - * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that - * sp_reg+sp_offset points to the iret return frame. - * - * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. - * Useful for code which doesn't have an ELF function annotation. - * - * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. - */ -#define UNWIND_HINT_TYPE_CALL 0 -#define UNWIND_HINT_TYPE_REGS 1 -#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 -#define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_ENTRY 4 -#define UNWIND_HINT_TYPE_SAVE 5 -#define UNWIND_HINT_TYPE_RESTORE 6 - -#ifdef CONFIG_OBJTOOL - -#include <asm/asm.h> - -#ifndef __ASSEMBLY__ - -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ - "987: \n\t" \ - ".pushsection .discard.unwind_hints\n\t" \ - /* struct unwind_hint */ \ - ".long 987b - .\n\t" \ - ".short " __stringify(sp_offset) "\n\t" \ - ".byte " __stringify(sp_reg) "\n\t" \ - ".byte " __stringify(type) "\n\t" \ - ".byte " __stringify(signal) "\n\t" \ - ".byte " __stringify(end) "\n\t" \ - ".balign 4 \n\t" \ - ".popsection\n\t" - -/* - * This macro marks the given function's stack frame as "non-standard", which - * tells objtool to ignore the function when doing stack metadata validation. - * It should only be used in special cases where you're 100% sure it won't - * affect the reliability of frame pointers and kernel stack traces. - * - * For more information, see tools/objtool/Documentation/objtool.txt. - */ -#define STACK_FRAME_NON_STANDARD(func) \ - static void __used __section(".discard.func_stack_frame_non_standard") \ - *__func_stack_frame_non_standard_##func = func - -/* - * STACK_FRAME_NON_STANDARD_FP() is a frame-pointer-specific function ignore - * for the case where a function is intentionally missing frame pointer setup, - * but otherwise needs objtool/ORC coverage when frame pointers are disabled. - */ -#ifdef CONFIG_FRAME_POINTER -#define STACK_FRAME_NON_STANDARD_FP(func) STACK_FRAME_NON_STANDARD(func) -#else -#define STACK_FRAME_NON_STANDARD_FP(func) -#endif - -#define ANNOTATE_NOENDBR \ - "986: \n\t" \ - ".pushsection .discard.noendbr\n\t" \ - _ASM_PTR " 986b\n\t" \ - ".popsection\n\t" - -#define ASM_REACHABLE \ - "998:\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long 998b - .\n\t" \ - ".popsection\n\t" - -#else /* __ASSEMBLY__ */ - -/* - * This macro indicates that the following intra-function call is valid. - * Any non-annotated intra-function call will cause objtool to issue a warning. - */ -#define ANNOTATE_INTRA_FUNCTION_CALL \ - 999: \ - .pushsection .discard.intra_function_calls; \ - .long 999b; \ - .popsection; - -/* - * In asm, there are two kinds of code: normal C-type callable functions and - * the rest. The normal callable functions can be called by other code, and - * don't do anything unusual with the stack. Such normal callable functions - * are annotated with the ENTRY/ENDPROC macros. Most asm code falls in this - * category. In this case, no special debugging annotations are needed because - * objtool can automatically generate the ORC data for the ORC unwinder to read - * at runtime. - * - * Anything which doesn't fall into the above category, such as syscall and - * interrupt handlers, tends to not be called directly by other functions, and - * often does unusual non-C-function-type things with the stack pointer. Such - * code needs to be annotated such that objtool can understand it. The - * following CFI hint macros are for this type of code. - * - * These macros provide hints to objtool about the state of the stack at each - * instruction. Objtool starts from the hints and follows the code flow, - * making automatic CFI adjustments when it sees pushes and pops, filling out - * the debuginfo as necessary. It will also warn if it sees any - * inconsistencies. - */ -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 -.Lunwind_hint_ip_\@: - .pushsection .discard.unwind_hints - /* struct unwind_hint */ - .long .Lunwind_hint_ip_\@ - . - .short \sp_offset - .byte \sp_reg - .byte \type - .byte \signal - .byte \end - .balign 4 - .popsection -.endm - -.macro STACK_FRAME_NON_STANDARD func:req - .pushsection .discard.func_stack_frame_non_standard, "aw" - _ASM_PTR \func - .popsection -.endm - -.macro STACK_FRAME_NON_STANDARD_FP func:req -#ifdef CONFIG_FRAME_POINTER - STACK_FRAME_NON_STANDARD \func -#endif -.endm - -.macro ANNOTATE_NOENDBR -.Lhere_\@: - .pushsection .discard.noendbr - .quad .Lhere_\@ - .popsection -.endm - -.macro REACHABLE -.Lhere_\@: - .pushsection .discard.reachable - .long .Lhere_\@ - . - .popsection -.endm - -#endif /* __ASSEMBLY__ */ - -#else /* !CONFIG_OBJTOOL */ - -#ifndef __ASSEMBLY__ - -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ - "\n\t" -#define STACK_FRAME_NON_STANDARD(func) -#define STACK_FRAME_NON_STANDARD_FP(func) -#define ANNOTATE_NOENDBR -#define ASM_REACHABLE -#else -#define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 -.endm -.macro STACK_FRAME_NON_STANDARD func:req -.endm -.macro ANNOTATE_NOENDBR -.endm -.macro REACHABLE -.endm -#endif - -#endif /* CONFIG_OBJTOOL */ - -#endif /* _LINUX_OBJTOOL_H */ diff --git a/tools/include/linux/objtool_types.h b/tools/include/linux/objtool_types.h new file mode 100644 index 000000000000..453a4f4ef39d --- /dev/null +++ b/tools/include/linux/objtool_types.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_OBJTOOL_TYPES_H +#define _LINUX_OBJTOOL_TYPES_H + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> + +/* + * This struct is used by asm and inline asm code to manually annotate the + * location of registers on the stack. + */ +struct unwind_hint { + u32 ip; + s16 sp_offset; + u8 sp_reg; + u8 type; + u8 signal; +}; + +#endif /* __ASSEMBLY__ */ + +/* + * UNWIND_HINT_TYPE_UNDEFINED: A blind spot in ORC coverage which can result in + * a truncated and unreliable stack unwind. + * + * UNWIND_HINT_TYPE_END_OF_STACK: The end of the kernel stack unwind before + * hitting user entry, boot code, or fork entry (when there are no pt_regs + * available). + * + * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP + * (the caller's SP right before it made the call). Used for all callable + * functions, i.e. all C code and all callable asm functions. + * + * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset + * points to a fully populated pt_regs from a syscall, interrupt, or exception. + * + * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that + * sp_reg+sp_offset points to the iret return frame. + * + * UNWIND_HINT_TYPE_FUNC: Generate the unwind metadata of a callable function. + * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_TYPE_{SAVE,RESTORE}: Save the unwind metadata at a certain + * location so that it can be restored later. + */ +#define UNWIND_HINT_TYPE_UNDEFINED 0 +#define UNWIND_HINT_TYPE_END_OF_STACK 1 +#define UNWIND_HINT_TYPE_CALL 2 +#define UNWIND_HINT_TYPE_REGS 3 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 4 +/* The below hint types don't have corresponding ORC types */ +#define UNWIND_HINT_TYPE_FUNC 5 +#define UNWIND_HINT_TYPE_SAVE 6 +#define UNWIND_HINT_TYPE_RESTORE 7 + +#endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index d77aef872a0a..4003a166328c 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1451,7 +1451,7 @@ struct kvm_vfio_spapr_tce { #define KVM_CREATE_VCPU _IO(KVMIO, 0x41) #define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) #define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) -#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) +#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) /* deprecated */ #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ struct kvm_userspace_memory_region) #define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 6f28180ffeea..15bf00e79e3f 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -627,7 +627,7 @@ class TracepointProvider(Provider): name)'. All available events have directories under - /sys/kernel/debug/tracing/events/ which export information + /sys/kernel/tracing/events/ which export information about the specific event. Therefore, listing the dirs gives us a list of all available events. diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 931cdb7dba19..0fcf99c91400 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -17,7 +17,7 @@ #include <objtool/warn.h> #include <objtool/endianness.h> -#include <linux/objtool.h> +#include <linux/objtool_types.h> #include <linux/hashtable.h> #include <linux/kernel.h> #include <linux/static_call_types.h> @@ -202,6 +202,8 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "__reiserfs_panic", "__stack_chk_fail", "__ubsan_handle_builtin_unreachable", + "arch_call_rest_init", + "arch_cpu_idle_dead", "btrfs_assertfail", "cpu_bringup_and_idle", "cpu_startup_entry", @@ -210,18 +212,28 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "do_task_dead", "ex_handler_msr_mce", "fortify_panic", + "hlt_play_dead", + "hv_ghcb_terminate", "kthread_complete_and_exit", "kthread_exit", "kunit_try_catch_throw", "lbug_with_loc", "machine_real_restart", "make_task_dead", + "mpt_halt_firmware", + "nmi_panic_self_stop", "panic", + "panic_smp_self_stop", + "rest_init", + "resume_play_dead", "rewind_stack_and_make_dead", "sev_es_terminate", "snp_abort", + "start_kernel", "stop_this_cpu", "usercopy_abort", + "x86_64_start_kernel", + "x86_64_start_reservations", "xen_cpu_bringup_again", "xen_start_kernel", }; @@ -229,14 +241,14 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, if (!func) return false; - if (func->bind == STB_WEAK) - return false; - - if (func->bind == STB_GLOBAL) + if (func->bind == STB_GLOBAL || func->bind == STB_WEAK) for (i = 0; i < ARRAY_SIZE(global_noreturns); i++) if (!strcmp(func->name, global_noreturns[i])) return true; + if (func->bind == STB_WEAK) + return false; + if (!func->len) return false; @@ -470,7 +482,7 @@ static int decode_instructions(struct objtool_file *file) // printf("%s: last chunk used: %d\n", sec->name, (int)idx); - list_for_each_entry(func, &sec->symbol_list, list) { + sec_for_each_sym(sec, func) { if (func->type != STT_NOTYPE && func->type != STT_FUNC) continue; @@ -924,7 +936,7 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file) static int create_cfi_sections(struct objtool_file *file) { - struct section *sec, *s; + struct section *sec; struct symbol *sym; unsigned int *loc; int idx; @@ -937,19 +949,14 @@ static int create_cfi_sections(struct objtool_file *file) } idx = 0; - for_each_sec(file, s) { - if (!s->text) + for_each_sym(file, sym) { + if (sym->type != STT_FUNC) continue; - list_for_each_entry(sym, &s->symbol_list, list) { - if (sym->type != STT_FUNC) - continue; - - if (strncmp(sym->name, "__cfi_", 6)) - continue; + if (strncmp(sym->name, "__cfi_", 6)) + continue; - idx++; - } + idx++; } sec = elf_create_section(file->elf, ".cfi_sites", 0, sizeof(unsigned int), idx); @@ -957,28 +964,23 @@ static int create_cfi_sections(struct objtool_file *file) return -1; idx = 0; - for_each_sec(file, s) { - if (!s->text) + for_each_sym(file, sym) { + if (sym->type != STT_FUNC) continue; - list_for_each_entry(sym, &s->symbol_list, list) { - if (sym->type != STT_FUNC) - continue; - - if (strncmp(sym->name, "__cfi_", 6)) - continue; + if (strncmp(sym->name, "__cfi_", 6)) + continue; - loc = (unsigned int *)sec->data->d_buf + idx; - memset(loc, 0, sizeof(unsigned int)); + loc = (unsigned int *)sec->data->d_buf + idx; + memset(loc, 0, sizeof(unsigned int)); - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(unsigned int), - R_X86_64_PC32, - s, sym->offset)) - return -1; + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(unsigned int), + R_X86_64_PC32, + sym->sec, sym->offset)) + return -1; - idx++; - } + idx++; } return 0; @@ -1279,6 +1281,8 @@ static const char *uaccess_safe_builtin[] = { "__ubsan_handle_type_mismatch_v1", "__ubsan_handle_shift_out_of_bounds", "__ubsan_handle_load_invalid_value", + /* STACKLEAK */ + "stackleak_track_stack", /* misc */ "csum_partial_copy_generic", "copy_mc_fragile", @@ -1444,7 +1448,7 @@ static void annotate_call_site(struct objtool_file *file, if (opts.mcount && sym->fentry) { if (sibling) - WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset); + WARN_INSN(insn, "tail call to __fentry__ !?!?"); if (opts.mnop) { if (reloc) { reloc->type = R_NONE; @@ -1646,9 +1650,8 @@ static int add_jump_destinations(struct objtool_file *file) continue; } - WARN_FUNC("can't find jump dest instruction at %s+0x%lx", - insn->sec, insn->offset, dest_sec->name, - dest_off); + WARN_INSN(insn, "can't find jump dest instruction at %s+0x%lx", + dest_sec->name, dest_off); return -1; } @@ -1731,13 +1734,12 @@ static int add_call_destinations(struct objtool_file *file) continue; if (!insn_call_dest(insn)) { - WARN_FUNC("unannotated intra-function call", insn->sec, insn->offset); + WARN_INSN(insn, "unannotated intra-function call"); return -1; } if (insn_func(insn) && insn_call_dest(insn)->type != STT_FUNC) { - WARN_FUNC("unsupported call to non-function", - insn->sec, insn->offset); + WARN_INSN(insn, "unsupported call to non-function"); return -1; } @@ -1745,10 +1747,8 @@ static int add_call_destinations(struct objtool_file *file) dest_off = arch_dest_reloc_offset(reloc->addend); 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, - dest_off); + WARN_INSN(insn, "can't find call dest symbol at %s+0x%lx", + reloc->sym->sec->name, dest_off); return -1; } @@ -1808,8 +1808,7 @@ static int handle_group_alt(struct objtool_file *file, } else { if (orig_alt_group->last_insn->offset + orig_alt_group->last_insn->len - orig_alt_group->first_insn->offset != special_alt->orig_len) { - WARN_FUNC("weirdly overlapping alternative! %ld != %d", - orig_insn->sec, orig_insn->offset, + WARN_INSN(orig_insn, "weirdly overlapping alternative! %ld != %d", orig_alt_group->last_insn->offset + orig_alt_group->last_insn->len - orig_alt_group->first_insn->offset, @@ -1878,8 +1877,7 @@ static int handle_group_alt(struct objtool_file *file, if (alt_reloc && arch_pc_relative_reloc(alt_reloc) && !arch_support_alt_relocation(special_alt, insn, alt_reloc)) { - WARN_FUNC("unsupported relocation in alternatives section", - insn->sec, insn->offset); + WARN_INSN(insn, "unsupported relocation in alternatives section"); return -1; } @@ -1893,8 +1891,7 @@ static int handle_group_alt(struct objtool_file *file, if (dest_off == special_alt->new_off + special_alt->new_len) { insn->jump_dest = next_insn_same_sec(file, orig_alt_group->last_insn); if (!insn->jump_dest) { - WARN_FUNC("can't find alternative jump destination", - insn->sec, insn->offset); + WARN_INSN(insn, "can't find alternative jump destination"); return -1; } } @@ -1928,8 +1925,7 @@ static int handle_jump_alt(struct objtool_file *file, if (orig_insn->type != INSN_JUMP_UNCONDITIONAL && orig_insn->type != INSN_NOP) { - WARN_FUNC("unsupported instruction at jump label", - orig_insn->sec, orig_insn->offset); + WARN_INSN(orig_insn, "unsupported instruction at jump label"); return -1; } @@ -2008,8 +2004,7 @@ static int add_special_section_alts(struct objtool_file *file) if (special_alt->group) { if (!special_alt->orig_len) { - WARN_FUNC("empty alternative entry", - orig_insn->sec, orig_insn->offset); + WARN_INSN(orig_insn, "empty alternative entry"); continue; } @@ -2100,8 +2095,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, } if (!prev_offset) { - WARN_FUNC("can't find switch jump table", - insn->sec, insn->offset); + WARN_INSN(insn, "can't find switch jump table"); return -1; } @@ -2215,23 +2209,20 @@ static int add_func_jump_tables(struct objtool_file *file, */ static int add_jump_table_alts(struct objtool_file *file) { - struct section *sec; struct symbol *func; int ret; if (!file->rodata) return 0; - for_each_sec(file, sec) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; + for_each_sym(file, func) { + if (func->type != STT_FUNC) + continue; - mark_func_jump_tables(file, func); - ret = add_func_jump_tables(file, func); - if (ret) - return ret; - } + mark_func_jump_tables(file, func); + ret = add_func_jump_tables(file, func); + if (ret) + return ret; } return 0; @@ -2243,6 +2234,7 @@ static void set_func_state(struct cfi_state *state) memcpy(&state->regs, &initial_func_cfi.regs, CFI_NUM_REGS * sizeof(struct cfi_reg)); state->stack_size = initial_func_cfi.cfa.offset; + state->type = UNWIND_HINT_TYPE_CALL; } static int read_unwind_hints(struct objtool_file *file) @@ -2304,19 +2296,11 @@ static int read_unwind_hints(struct objtool_file *file) if (sym && sym->bind == STB_GLOBAL) { if (opts.ibt && insn->type != INSN_ENDBR && !insn->noendbr) { - WARN_FUNC("UNWIND_HINT_IRET_REGS without ENDBR", - insn->sec, insn->offset); + WARN_INSN(insn, "UNWIND_HINT_IRET_REGS without ENDBR"); } - - insn->entry = 1; } } - if (hint->type == UNWIND_HINT_TYPE_ENTRY) { - hint->type = UNWIND_HINT_TYPE_CALL; - insn->entry = 1; - } - if (hint->type == UNWIND_HINT_TYPE_FUNC) { insn->cfi = &func_cfi; continue; @@ -2326,15 +2310,13 @@ static int read_unwind_hints(struct objtool_file *file) 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); + WARN_INSN(insn, "unsupported unwind_hint sp base reg %d", hint->sp_reg); return -1; } cfi.cfa.offset = bswap_if_needed(file->elf, hint->sp_offset); cfi.type = hint->type; cfi.signal = hint->signal; - cfi.end = hint->end; insn->cfi = cfi_hash_find_or_add(&cfi); } @@ -2391,8 +2373,7 @@ static int read_retpoline_hints(struct objtool_file *file) insn->type != INSN_CALL_DYNAMIC && insn->type != INSN_RETURN && insn->type != INSN_NOP) { - WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret/nop", - insn->sec, insn->offset); + WARN_INSN(insn, "retpoline_safe hint not an indirect jump/call/ret/nop"); return -1; } @@ -2449,6 +2430,34 @@ static int read_instr_hints(struct objtool_file *file) return 0; } +static int read_validate_unret_hints(struct objtool_file *file) +{ + struct section *sec; + struct instruction *insn; + struct reloc *reloc; + + sec = find_section_by_name(file->elf, ".rela.discard.validate_unret"); + if (!sec) + return 0; + + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + + insn = find_insn(file, reloc->sym->sec, reloc->addend); + if (!insn) { + WARN("bad .discard.instr_end entry"); + return -1; + } + insn->unret = 1; + } + + return 0; +} + + static int read_intra_function_calls(struct objtool_file *file) { struct instruction *insn; @@ -2475,8 +2484,7 @@ static int read_intra_function_calls(struct objtool_file *file) } if (insn->type != INSN_CALL) { - WARN_FUNC("intra_function_call not a direct call", - insn->sec, insn->offset); + WARN_INSN(insn, "intra_function_call not a direct call"); return -1; } @@ -2490,8 +2498,7 @@ static int read_intra_function_calls(struct objtool_file *file) dest_off = arch_jump_destination(insn); insn->jump_dest = find_insn(file, insn->sec, dest_off); if (!insn->jump_dest) { - WARN_FUNC("can't find call dest at %s+0x%lx", - insn->sec, insn->offset, + WARN_INSN(insn, "can't find call dest at %s+0x%lx", insn->sec->name, dest_off); return -1; } @@ -2527,30 +2534,27 @@ static bool is_profiling_func(const char *name) 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) - continue; + for_each_sym(file, func) { + 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 (!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 (arch_is_retpoline(func)) + func->retpoline_thunk = true; - if (arch_is_rethunk(func)) - func->return_thunk = true; + if (arch_is_rethunk(func)) + func->return_thunk = true; - if (arch_ftrace_match(func->name)) - func->fentry = true; + if (arch_ftrace_match(func->name)) + func->fentry = true; - if (is_profiling_func(func->name)) - func->profiling_func = true; - } + if (is_profiling_func(func->name)) + func->profiling_func = true; } return 0; @@ -2667,6 +2671,10 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; + ret = read_validate_unret_hints(file); + if (ret) + return ret; + return 0; } @@ -2828,7 +2836,7 @@ static int update_cfi_state(struct instruction *insn, /* stack operations don't make sense with an undefined CFA */ if (cfa->base == CFI_UNDEFINED) { if (insn_func(insn)) { - WARN_FUNC("undefined stack state", insn->sec, insn->offset); + WARN_INSN(insn, "undefined stack state"); return -1; } return 0; @@ -2977,17 +2985,6 @@ static int update_cfi_state(struct instruction *insn, break; } - if (!cfi->drap && op->src.reg == CFI_SP && - op->dest.reg == CFI_BP && cfa->base == CFI_SP && - check_reg_frame_pos(®s[CFI_BP], -cfa->offset + op->src.offset)) { - - /* lea disp(%rsp), %rbp */ - cfa->base = CFI_BP; - cfa->offset -= op->src.offset; - cfi->bp_scratch = false; - break; - } - if (op->src.reg == CFI_SP && cfa->base == CFI_SP) { /* drap: lea disp(%rsp), %drap */ @@ -3022,8 +3019,7 @@ static int update_cfi_state(struct instruction *insn, } if (op->dest.reg == cfi->cfa.base && !(next_insn && next_insn->hint)) { - WARN_FUNC("unsupported stack register modification", - insn->sec, insn->offset); + WARN_INSN(insn, "unsupported stack register modification"); return -1; } @@ -3033,8 +3029,7 @@ static int update_cfi_state(struct instruction *insn, if (op->dest.reg != CFI_SP || (cfi->drap_reg != CFI_UNDEFINED && cfa->base != CFI_SP) || (cfi->drap_reg == CFI_UNDEFINED && cfa->base != CFI_BP)) { - WARN_FUNC("unsupported stack pointer realignment", - insn->sec, insn->offset); + WARN_INSN(insn, "unsupported stack pointer realignment"); return -1; } @@ -3129,8 +3124,7 @@ static int update_cfi_state(struct instruction *insn, break; default: - WARN_FUNC("unknown stack-related instruction", - insn->sec, insn->offset); + WARN_INSN(insn, "unknown stack-related instruction"); return -1; } @@ -3219,8 +3213,7 @@ static int update_cfi_state(struct instruction *insn, case OP_DEST_MEM: if (op->src.type != OP_SRC_POP && op->src.type != OP_SRC_POPF) { - WARN_FUNC("unknown stack-related memory operation", - insn->sec, insn->offset); + WARN_INSN(insn, "unknown stack-related memory operation"); return -1; } @@ -3232,8 +3225,7 @@ static int update_cfi_state(struct instruction *insn, break; default: - WARN_FUNC("unknown stack-related instruction", - insn->sec, insn->offset); + WARN_INSN(insn, "unknown stack-related instruction"); return -1; } @@ -3272,8 +3264,7 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn struct alt_group *orig_group = insn->alt_group->orig_group ?: insn->alt_group; struct instruction *orig = orig_group->first_insn; char *where = offstr(insn->sec, insn->offset); - WARN_FUNC("stack layout conflict in alternatives: %s", - orig->sec, orig->offset, where); + WARN_INSN(orig, "stack layout conflict in alternatives: %s", where); free(where); return -1; } @@ -3300,8 +3291,7 @@ static int handle_insn_ops(struct instruction *insn, if (!state->uaccess_stack) { state->uaccess_stack = 1; } else if (state->uaccess_stack >> 31) { - WARN_FUNC("PUSHF stack exhausted", - insn->sec, insn->offset); + WARN_INSN(insn, "PUSHF stack exhausted"); return 1; } state->uaccess_stack <<= 1; @@ -3333,8 +3323,7 @@ static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) { - WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d", - insn->sec, insn->offset, + WARN_INSN(insn, "stack state mismatch: cfa1=%d%+d cfa2=%d%+d", cfi1->cfa.base, cfi1->cfa.offset, cfi2->cfa.base, cfi2->cfa.offset); @@ -3344,8 +3333,7 @@ static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) sizeof(struct cfi_reg))) continue; - WARN_FUNC("stack state mismatch: reg1[%d]=%d%+d reg2[%d]=%d%+d", - insn->sec, insn->offset, + WARN_INSN(insn, "stack state mismatch: reg1[%d]=%d%+d reg2[%d]=%d%+d", i, cfi1->regs[i].base, cfi1->regs[i].offset, i, cfi2->regs[i].base, cfi2->regs[i].offset); break; @@ -3353,15 +3341,14 @@ static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) } else if (cfi1->type != cfi2->type) { - WARN_FUNC("stack state mismatch: type1=%d type2=%d", - insn->sec, insn->offset, cfi1->type, cfi2->type); + WARN_INSN(insn, "stack state mismatch: type1=%d type2=%d", + cfi1->type, cfi2->type); } else if (cfi1->drap != cfi2->drap || (cfi1->drap && cfi1->drap_reg != cfi2->drap_reg) || (cfi1->drap && cfi1->drap_offset != cfi2->drap_offset)) { - WARN_FUNC("stack state mismatch: drap1=%d(%d,%d) drap2=%d(%d,%d)", - insn->sec, insn->offset, + WARN_INSN(insn, "stack state mismatch: drap1=%d(%d,%d) drap2=%d(%d,%d)", cfi1->drap, cfi1->drap_reg, cfi1->drap_offset, cfi2->drap, cfi2->drap_reg, cfi2->drap_offset); @@ -3469,20 +3456,17 @@ static int validate_call(struct objtool_file *file, { if (state->noinstr && state->instr <= 0 && !noinstr_call_dest(file, insn, insn_call_dest(insn))) { - WARN_FUNC("call to %s() leaves .noinstr.text section", - insn->sec, insn->offset, call_dest_name(insn)); + WARN_INSN(insn, "call to %s() leaves .noinstr.text section", call_dest_name(insn)); return 1; } if (state->uaccess && !func_uaccess_safe(insn_call_dest(insn))) { - WARN_FUNC("call to %s() with UACCESS enabled", - insn->sec, insn->offset, call_dest_name(insn)); + WARN_INSN(insn, "call to %s() with UACCESS enabled", call_dest_name(insn)); return 1; } if (state->df) { - WARN_FUNC("call to %s() with DF set", - insn->sec, insn->offset, call_dest_name(insn)); + WARN_INSN(insn, "call to %s() with DF set", call_dest_name(insn)); return 1; } @@ -3494,8 +3478,7 @@ static int validate_sibling_call(struct objtool_file *file, struct insn_state *state) { if (insn_func(insn) && has_modified_stack_frame(insn, state)) { - WARN_FUNC("sibling call from callable instruction with modified stack frame", - insn->sec, insn->offset); + WARN_INSN(insn, "sibling call from callable instruction with modified stack frame"); return 1; } @@ -3505,38 +3488,32 @@ static int validate_sibling_call(struct objtool_file *file, static int validate_return(struct symbol *func, struct instruction *insn, struct insn_state *state) { if (state->noinstr && state->instr > 0) { - WARN_FUNC("return with instrumentation enabled", - insn->sec, insn->offset); + WARN_INSN(insn, "return with instrumentation enabled"); return 1; } if (state->uaccess && !func_uaccess_safe(func)) { - WARN_FUNC("return with UACCESS enabled", - insn->sec, insn->offset); + WARN_INSN(insn, "return with UACCESS enabled"); return 1; } if (!state->uaccess && func_uaccess_safe(func)) { - WARN_FUNC("return with UACCESS disabled from a UACCESS-safe function", - insn->sec, insn->offset); + WARN_INSN(insn, "return with UACCESS disabled from a UACCESS-safe function"); return 1; } if (state->df) { - WARN_FUNC("return with DF set", - insn->sec, insn->offset); + WARN_INSN(insn, "return with DF set"); return 1; } if (func && has_modified_stack_frame(insn, state)) { - WARN_FUNC("return with modified stack frame", - insn->sec, insn->offset); + WARN_INSN(insn, "return with modified stack frame"); return 1; } if (state->cfi.bp_scratch) { - WARN_FUNC("BP used as a scratch register", - insn->sec, insn->offset); + WARN_INSN(insn, "BP used as a scratch register"); return 1; } @@ -3608,8 +3585,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, } if (func && insn->ignore) { - WARN_FUNC("BUG: why am I validating an ignored function?", - sec, insn->offset); + WARN_INSN(insn, "BUG: why am I validating an ignored function?"); return 1; } @@ -3642,14 +3618,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, } if (!save_insn) { - WARN_FUNC("no corresponding CFI save for CFI restore", - sec, insn->offset); + WARN_INSN(insn, "no corresponding CFI save for CFI restore"); return 1; } if (!save_insn->visited) { - WARN_FUNC("objtool isn't smart enough to handle this CFI save/restore combo", - sec, insn->offset); + WARN_INSN(insn, "objtool isn't smart enough to handle this CFI save/restore combo"); return 1; } @@ -3709,8 +3683,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (opts.stackval && func && !is_fentry_call(insn) && !has_valid_stack_frame(&state)) { - WARN_FUNC("call without frame pointer save/setup", - sec, insn->offset); + WARN_INSN(insn, "call without frame pointer save/setup"); return 1; } @@ -3756,15 +3729,14 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_CONTEXT_SWITCH: if (func && (!next_insn || !next_insn->hint)) { - WARN_FUNC("unsupported instruction in callable function", - sec, insn->offset); + WARN_INSN(insn, "unsupported instruction in callable function"); return 1; } return 0; case INSN_STAC: if (state.uaccess) { - WARN_FUNC("recursive UACCESS enable", sec, insn->offset); + WARN_INSN(insn, "recursive UACCESS enable"); return 1; } @@ -3773,12 +3745,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_CLAC: if (!state.uaccess && func) { - WARN_FUNC("redundant UACCESS disable", sec, insn->offset); + WARN_INSN(insn, "redundant UACCESS disable"); return 1; } if (func_uaccess_safe(func) && !state.uaccess_stack) { - WARN_FUNC("UACCESS-safe disables UACCESS", sec, insn->offset); + WARN_INSN(insn, "UACCESS-safe disables UACCESS"); return 1; } @@ -3787,7 +3759,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_STD: if (state.df) { - WARN_FUNC("recursive STD", sec, insn->offset); + WARN_INSN(insn, "recursive STD"); return 1; } @@ -3796,7 +3768,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_CLD: if (!state.df && func) { - WARN_FUNC("redundant CLD", sec, insn->offset); + WARN_INSN(insn, "redundant CLD"); return 1; } @@ -3863,10 +3835,10 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) /* * Validate rethunk entry constraint: must untrain RET before the first RET. * - * Follow every branch (intra-function) and ensure ANNOTATE_UNRET_END comes + * Follow every branch (intra-function) and ensure VALIDATE_UNRET_END comes * before an actual RET instruction. */ -static int validate_entry(struct objtool_file *file, struct instruction *insn) +static int validate_unret(struct objtool_file *file, struct instruction *insn) { struct instruction *next, *dest; int ret, warnings = 0; @@ -3874,10 +3846,10 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) for (;;) { next = next_insn_to_validate(file, insn); - if (insn->visited & VISITED_ENTRY) + if (insn->visited & VISITED_UNRET) return 0; - insn->visited |= VISITED_ENTRY; + insn->visited |= VISITED_UNRET; if (!insn->ignore_alts && insn->alts) { struct alternative *alt; @@ -3887,7 +3859,7 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) if (alt->skip_orig) skip_orig = true; - ret = validate_entry(file, alt->insn); + ret = validate_unret(file, alt->insn); if (ret) { if (opts.backtrace) BT_FUNC("(alt)", insn); @@ -3904,18 +3876,17 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) case INSN_CALL_DYNAMIC: case INSN_JUMP_DYNAMIC: case INSN_JUMP_DYNAMIC_CONDITIONAL: - WARN_FUNC("early indirect call", insn->sec, insn->offset); + WARN_INSN(insn, "early indirect call"); return 1; case INSN_JUMP_UNCONDITIONAL: case INSN_JUMP_CONDITIONAL: if (!is_sibling_call(insn)) { if (!insn->jump_dest) { - WARN_FUNC("unresolved jump target after linking?!?", - insn->sec, insn->offset); + WARN_INSN(insn, "unresolved jump target after linking?!?"); return -1; } - ret = validate_entry(file, insn->jump_dest); + ret = validate_unret(file, insn->jump_dest); if (ret) { if (opts.backtrace) { BT_FUNC("(branch%s)", insn, @@ -3940,7 +3911,7 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) return -1; } - ret = validate_entry(file, dest); + ret = validate_unret(file, dest); if (ret) { if (opts.backtrace) BT_FUNC("(call)", insn); @@ -3953,7 +3924,7 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) return 0; case INSN_RETURN: - WARN_FUNC("RET before UNTRAIN", insn->sec, insn->offset); + WARN_INSN(insn, "RET before UNTRAIN"); return 1; case INSN_NOP: @@ -3966,7 +3937,7 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) } if (!next) { - WARN_FUNC("teh end!", insn->sec, insn->offset); + WARN_INSN(insn, "teh end!"); return -1; } insn = next; @@ -3976,21 +3947,21 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) } /* - * Validate that all branches starting at 'insn->entry' encounter UNRET_END - * before RET. + * Validate that all branches starting at VALIDATE_UNRET_BEGIN encounter + * VALIDATE_UNRET_END before RET. */ -static int validate_unret(struct objtool_file *file) +static int validate_unrets(struct objtool_file *file) { struct instruction *insn; int ret, warnings = 0; for_each_insn(file, insn) { - if (!insn->entry) + if (!insn->unret) continue; - ret = validate_entry(file, insn); + ret = validate_unret(file, insn); if (ret < 0) { - WARN_FUNC("Failed UNRET validation", insn->sec, insn->offset); + WARN_INSN(insn, "Failed UNRET validation"); return ret; } warnings += ret; @@ -4018,13 +3989,11 @@ static int validate_retpoline(struct objtool_file *file) if (insn->type == INSN_RETURN) { if (opts.rethunk) { - WARN_FUNC("'naked' return found in RETHUNK build", - insn->sec, insn->offset); + WARN_INSN(insn, "'naked' return found in RETHUNK build"); } else continue; } else { - WARN_FUNC("indirect %s found in RETPOLINE build", - insn->sec, insn->offset, + WARN_INSN(insn, "indirect %s found in RETPOLINE build", insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); } @@ -4121,8 +4090,7 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio * It may also insert a UD2 after calling a __noreturn function. */ prev_insn = prev_insn_same_sec(file, insn); - if ((prev_insn->dead_end || - dead_end_function(file, insn_call_dest(prev_insn))) && + if (prev_insn->dead_end && (insn->type == INSN_BUG || (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest && insn->jump_dest->type == INSN_BUG))) @@ -4158,54 +4126,75 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio return false; } -static int add_prefix_symbol(struct objtool_file *file, struct symbol *func, - struct instruction *insn) +static int add_prefix_symbol(struct objtool_file *file, struct symbol *func) { - if (!opts.prefix) - return 0; + struct instruction *insn, *prev; + struct cfi_state *cfi; - for (;;) { - struct instruction *prev = prev_insn_same_sec(file, insn); - u64 offset; + insn = find_insn(file, func->sec, func->offset); + if (!insn) + return -1; - if (!prev) - break; + for (prev = prev_insn_same_sec(file, insn); + prev; + prev = prev_insn_same_sec(file, prev)) { + u64 offset; if (prev->type != INSN_NOP) - break; + return -1; offset = func->offset - prev->offset; - if (offset >= opts.prefix) { - if (offset == opts.prefix) { - /* - * Since the sec->symbol_list is ordered by - * offset (see elf_add_symbol()) the added - * symbol will not be seen by the iteration in - * validate_section(). - * - * Hence the lack of list_for_each_entry_safe() - * there. - * - * The direct concequence is that prefix symbols - * don't get visited (because pointless), except - * for the logic in ignore_unreachable_insn() - * that needs the terminating insn to be visited - * otherwise it will report the hole. - * - * Hence mark the first instruction of the - * prefix symbol as visisted. - */ - prev->visited |= VISITED_BRANCH; - elf_create_prefix_symbol(file->elf, func, opts.prefix); - } - break; - } - insn = prev; + + if (offset > opts.prefix) + return -1; + + if (offset < opts.prefix) + continue; + + elf_create_prefix_symbol(file->elf, func, opts.prefix); + break; } + if (!prev) + return -1; + + if (!insn->cfi) { + /* + * This can happen if stack validation isn't enabled or the + * function is annotated with STACK_FRAME_NON_STANDARD. + */ + return 0; + } + + /* Propagate insn->cfi to the prefix code */ + cfi = cfi_hash_find_or_add(insn->cfi); + for (; prev != insn; prev = next_insn_same_sec(file, prev)) + prev->cfi = cfi; + return 0; } +static int add_prefix_symbols(struct objtool_file *file) +{ + struct section *sec; + struct symbol *func; + int warnings = 0; + + for_each_sec(file, sec) { + if (!(sec->sh.sh_flags & SHF_EXECINSTR)) + continue; + + sec_for_each_sym(sec, func) { + if (func->type != STT_FUNC) + continue; + + add_prefix_symbol(file, func); + } + } + + return warnings; +} + static int validate_symbol(struct objtool_file *file, struct section *sec, struct symbol *sym, struct insn_state *state) { @@ -4224,8 +4213,6 @@ static int validate_symbol(struct objtool_file *file, struct section *sec, if (!insn || insn->ignore || insn->visited) return 0; - add_prefix_symbol(file, sym, insn); - state->uaccess = sym->uaccess_safe; ret = validate_branch(file, insn_func(insn), insn, *state); @@ -4240,7 +4227,7 @@ static int validate_section(struct objtool_file *file, struct section *sec) struct symbol *func; int warnings = 0; - list_for_each_entry(func, &sec->symbol_list, list) { + sec_for_each_sym(sec, func) { if (func->type != STT_FUNC) continue; @@ -4403,9 +4390,7 @@ static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn if (noendbr_range(file, dest)) continue; - WARN_FUNC("relocation to !ENDBR: %s", - insn->sec, insn->offset, - offstr(dest->sec, dest->offset)); + WARN_INSN(insn, "relocation to !ENDBR: %s", offstr(dest->sec, dest->offset)); warnings++; } @@ -4507,16 +4492,14 @@ static int validate_sls(struct objtool_file *file) switch (insn->type) { case INSN_RETURN: if (!next_insn || next_insn->type != INSN_TRAP) { - WARN_FUNC("missing int3 after ret", - insn->sec, insn->offset); + WARN_INSN(insn, "missing int3 after ret"); warnings++; } break; case INSN_JUMP_DYNAMIC: if (!next_insn || next_insn->type != INSN_TRAP) { - WARN_FUNC("missing int3 after indirect jump", - insn->sec, insn->offset); + WARN_INSN(insn, "missing int3 after indirect jump"); warnings++; } break; @@ -4539,7 +4522,7 @@ static int validate_reachable_instructions(struct objtool_file *file) if (insn->visited || ignore_unreachable_insn(file, insn)) continue; - WARN_FUNC("unreachable instruction", insn->sec, insn->offset); + WARN_INSN(insn, "unreachable instruction"); return 1; } @@ -4607,7 +4590,7 @@ int check(struct objtool_file *file) * Must be after validate_branch() and friends, it plays * further games with insn->visited. */ - ret = validate_unret(file); + ret = validate_unrets(file); if (ret < 0) return ret; warnings += ret; @@ -4669,6 +4652,13 @@ int check(struct objtool_file *file) warnings += ret; } + if (opts.prefix) { + ret = add_prefix_symbols(file); + if (ret < 0) + return ret; + warnings += ret; + } + if (opts.ibt) { ret = create_ibt_endbr_seal_sections(file); if (ret < 0) diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 6806ce01d933..500e92979a31 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -474,7 +474,7 @@ static int read_symbols(struct elf *elf) /* Create parent/child links for any cold subfunctions */ list_for_each_entry(sec, &elf->sections, list) { - list_for_each_entry(sym, &sec->symbol_list, list) { + sec_for_each_sym(sec, sym) { char pname[MAX_NAME_LEN + 1]; size_t pnamelen; if (sym->type != STT_FUNC) diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index 3e7c7004f7df..daa46f1f0965 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -61,7 +61,7 @@ struct instruction { restore : 1, retpoline_safe : 1, noendbr : 1, - entry : 1, + unret : 1, visited : 4, no_reloc : 1; /* 10 bit hole */ @@ -92,7 +92,7 @@ static inline struct symbol *insn_func(struct instruction *insn) #define VISITED_BRANCH 0x01 #define VISITED_BRANCH_UACCESS 0x02 #define VISITED_BRANCH_MASK 0x03 -#define VISITED_ENTRY 0x04 +#define VISITED_UNRET 0x04 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 ad0024da262b..e1ca588eb69d 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -188,4 +188,13 @@ struct symbol *find_func_containing(struct section *sec, unsigned long offset); #define for_each_sec(file, sec) \ list_for_each_entry(sec, &file->elf->sections, list) +#define sec_for_each_sym(sec, sym) \ + list_for_each_entry(sym, &sec->symbol_list, list) + +#define for_each_sym(file, sym) \ + for (struct section *__sec, *__fake = (struct section *)1; \ + __fake; __fake = NULL) \ + for_each_sec(file, __sec) \ + sec_for_each_sym(__sec, sym) + #endif /* _OBJTOOL_ELF_H */ diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index a3e79ae75f2e..b1c920dc9516 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -53,6 +53,11 @@ static inline char *offstr(struct section *sec, unsigned long offset) free(_str); \ }) +#define WARN_INSN(insn, format, ...) \ +({ \ + WARN_FUNC(format, insn->sec, insn->offset, ##__VA_ARGS__); \ +}) + #define BT_FUNC(format, insn, ...) \ ({ \ struct instruction *_insn = (insn); \ diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index 2d8ebdcd1db3..0e183bb1c720 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -4,7 +4,6 @@ */ #include <unistd.h> -#include <linux/objtool.h> #include <asm/orc_types.h> #include <objtool/objtool.h> #include <objtool/warn.h> @@ -39,11 +38,15 @@ static const char *reg_name(unsigned int reg) static const char *orc_type_name(unsigned int type) { switch (type) { - case UNWIND_HINT_TYPE_CALL: + case ORC_TYPE_UNDEFINED: + return "(und)"; + case ORC_TYPE_END_OF_STACK: + return "end"; + case ORC_TYPE_CALL: return "call"; - case UNWIND_HINT_TYPE_REGS: + case ORC_TYPE_REGS: return "regs"; - case UNWIND_HINT_TYPE_REGS_PARTIAL: + case ORC_TYPE_REGS_PARTIAL: return "regs (partial)"; default: return "?"; @@ -202,6 +205,7 @@ int orc_dump(const char *_objname) printf("%llx:", (unsigned long long)(orc_ip_addr + (i * sizeof(int)) + orc_ip[i])); } + printf("type:%s", orc_type_name(orc[i].type)); printf(" sp:"); @@ -211,8 +215,7 @@ int orc_dump(const char *_objname) print_reg(orc[i].bp_reg, bswap_if_needed(&dummy_elf, orc[i].bp_offset)); - printf(" type:%s signal:%d end:%d\n", - orc_type_name(orc[i].type), orc[i].signal, orc[i].end); + printf(" signal:%d\n", orc[i].signal); } elf_end(elf); diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 57a4527d5988..48efd1e2f00d 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -6,7 +6,7 @@ #include <stdlib.h> #include <string.h> -#include <linux/objtool.h> +#include <linux/objtool_types.h> #include <asm/orc_types.h> #include <objtool/check.h> @@ -21,19 +21,38 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, memset(orc, 0, sizeof(*orc)); if (!cfi) { - orc->end = 0; - orc->sp_reg = ORC_REG_UNDEFINED; + /* + * This is usually either unreachable nops/traps (which don't + * trigger unreachable instruction warnings), or + * STACK_FRAME_NON_STANDARD functions. + */ + orc->type = ORC_TYPE_UNDEFINED; return 0; } - orc->end = cfi->end; - orc->signal = cfi->signal; - - if (cfi->cfa.base == CFI_UNDEFINED) { - orc->sp_reg = ORC_REG_UNDEFINED; + switch (cfi->type) { + case UNWIND_HINT_TYPE_UNDEFINED: + orc->type = ORC_TYPE_UNDEFINED; + return 0; + case UNWIND_HINT_TYPE_END_OF_STACK: + orc->type = ORC_TYPE_END_OF_STACK; return 0; + case UNWIND_HINT_TYPE_CALL: + orc->type = ORC_TYPE_CALL; + break; + case UNWIND_HINT_TYPE_REGS: + orc->type = ORC_TYPE_REGS; + break; + case UNWIND_HINT_TYPE_REGS_PARTIAL: + orc->type = ORC_TYPE_REGS_PARTIAL; + break; + default: + WARN_INSN(insn, "unknown unwind hint type %d", cfi->type); + return -1; } + orc->signal = cfi->signal; + switch (cfi->cfa.base) { case CFI_SP: orc->sp_reg = ORC_REG_SP; @@ -60,8 +79,7 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, orc->sp_reg = ORC_REG_DX; break; default: - WARN_FUNC("unknown CFA base reg %d", - insn->sec, insn->offset, cfi->cfa.base); + WARN_INSN(insn, "unknown CFA base reg %d", cfi->cfa.base); return -1; } @@ -76,14 +94,12 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, orc->bp_reg = ORC_REG_BP; break; default: - WARN_FUNC("unknown BP base reg %d", - insn->sec, insn->offset, bp->base); + WARN_INSN(insn, "unknown BP base reg %d", bp->base); return -1; } orc->sp_offset = cfi->cfa.offset; orc->bp_offset = bp->offset; - orc->type = cfi->type; return 0; } @@ -148,11 +164,7 @@ int orc_create(struct objtool_file *file) struct orc_list_entry *entry; struct list_head orc_list; - struct orc_entry null = { - .sp_reg = ORC_REG_UNDEFINED, - .bp_reg = ORC_REG_UNDEFINED, - .type = UNWIND_HINT_TYPE_CALL, - }; + struct orc_entry null = { .type = ORC_TYPE_UNDEFINED }; /* Build a deduplicated list of ORC entries: */ INIT_LIST_HEAD(&orc_list); diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh index 105a291ff8e7..81d120d05442 100755 --- a/tools/objtool/sync-check.sh +++ b/tools/objtool/sync-check.sh @@ -6,7 +6,7 @@ if [ -z "$SRCARCH" ]; then exit 1 fi -FILES="include/linux/objtool.h" +FILES="include/linux/objtool_types.h" if [ "$SRCARCH" = "x86" ]; then FILES="$FILES diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 3519a0139026..c0a208f9b67b 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -38,7 +38,7 @@ ifneq ($(NO_SYSCALL_TABLE),1) NO_SYSCALL_TABLE := 0 endif else - ifeq ($(SRCARCH),$(filter $(SRCARCH),powerpc arm64 s390 mips)) + ifeq ($(SRCARCH),$(filter $(SRCARCH),powerpc arm64 s390 mips loongarch)) NO_SYSCALL_TABLE := 0 endif endif @@ -80,6 +80,12 @@ ifeq ($(SRCARCH),arm64) LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif +ifeq ($(SRCARCH),loongarch) + NO_PERF_REGS := 0 + CFLAGS += -I$(OUTPUT)arch/loongarch/include/generated + LIBUNWIND_LIBS = -lunwind -lunwind-loongarch64 +endif + ifeq ($(SRCARCH),riscv) NO_PERF_REGS := 0 endif @@ -107,7 +113,7 @@ endif # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures # to the check. -ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky riscv)) +ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky riscv loongarch)) NO_LIBDW_DWARF_UNWIND := 1 endif @@ -129,7 +135,7 @@ endef ifdef LIBUNWIND_DIR LIBUNWIND_CFLAGS = -I$(LIBUNWIND_DIR)/include LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib - LIBUNWIND_ARCHS = x86 x86_64 arm aarch64 debug-frame-arm debug-frame-aarch64 + LIBUNWIND_ARCHS = x86 x86_64 arm aarch64 debug-frame-arm debug-frame-aarch64 loongarch $(foreach libunwind_arch,$(LIBUNWIND_ARCHS),$(call libunwind_arch_set_flags,$(libunwind_arch))) endif diff --git a/tools/perf/arch/loongarch/Build b/tools/perf/arch/loongarch/Build new file mode 100644 index 000000000000..e4e5f33c84d8 --- /dev/null +++ b/tools/perf/arch/loongarch/Build @@ -0,0 +1 @@ +perf-y += util/ diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile new file mode 100644 index 000000000000..c392e7af4743 --- /dev/null +++ b/tools/perf/arch/loongarch/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 +ifndef NO_DWARF +PERF_HAVE_DWARF_REGS := 1 +endif +PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 +PERF_HAVE_JITDUMP := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/loongarch/include/generated/asm +header := $(out)/syscalls.c +incpath := $(srctree)/tools +sysdef := $(srctree)/tools/arch/loongarch/include/uapi/asm/unistd.h +sysprf := $(srctree)/tools/perf/arch/loongarch/entry/syscalls/ +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, loongarch) $(RM) $(header) + +archheaders: $(header) diff --git a/tools/perf/arch/loongarch/annotate/instructions.c b/tools/perf/arch/loongarch/annotate/instructions.c new file mode 100644 index 000000000000..ab21bf122135 --- /dev/null +++ b/tools/perf/arch/loongarch/annotate/instructions.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Perf annotate functions. + * + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +static +struct ins_ops *loongarch__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + if (!strncmp(name, "beqz", 4) || + !strncmp(name, "bnez", 4) || + !strncmp(name, "beq", 3) || + !strncmp(name, "bne", 3) || + !strncmp(name, "blt", 3) || + !strncmp(name, "bge", 3) || + !strncmp(name, "bltu", 4) || + !strncmp(name, "bgeu", 4) || + !strncmp(name, "bl", 2)) + ops = &call_ops; + else if (!strncmp(name, "jirl", 4)) + ops = &ret_ops; + else if (name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +static +int loongarch__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + if (!arch->initialized) { + arch->associate_instruction_ops = loongarch__associate_ins_ops; + arch->initialized = true; + arch->objdump.comment_char = '#'; + } + + return 0; +} diff --git a/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl b/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000000..c52156f7204d --- /dev/null +++ b/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl @@ -0,0 +1,61 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# powerpc script. +# +# Author(s): Ming Wang <wangming01@loongson.cn> +# Author(s): Huacai Chen <chenhuacai@loongson.cn> +# Copyright (C) 2020-2023 Loongson Technology Corporation Limited + +gcc=$1 +hostcc=$2 +incpath=$3 +input=$4 + +if ! test -r $input; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table_from_c() +{ + local sc nr last_sc + + create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX` + + { + + cat <<-_EoHEADER + #include <stdio.h> + #include "$input" + int main(int argc, char *argv[]) + { + _EoHEADER + + while read sc nr; do + printf "%s\n" " printf(\"\\t[%d] = \\\"$sc\\\",\\n\", $nr);" + last_sc=$nr + done + + printf "%s\n" " printf(\"#define SYSCALLTBL_LOONGARCH_MAX_ID %d\\n\", $last_sc);" + printf "}\n" + + } | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c - + + $create_table_exe + + rm -f $create_table_exe +} + +create_table() +{ + echo "static const char *syscalltbl_loongarch[] = {" + create_table_from_c + echo "};" +} + +$gcc -E -dM -x c -I $incpath/include/uapi $input \ + |sed -ne 's/^#define __NR_//p' \ + |sort -t' ' -k2 -n \ + |create_table diff --git a/tools/perf/arch/loongarch/include/dwarf-regs-table.h b/tools/perf/arch/loongarch/include/dwarf-regs-table.h new file mode 100644 index 000000000000..bb3944f5764a --- /dev/null +++ b/tools/perf/arch/loongarch/include/dwarf-regs-table.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * dwarf-regs-table.h : Mapping of DWARF debug register numbers into + * register names. + * + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#ifdef DEFINE_DWARF_REGSTR_TABLE +static const char * const loongarch_regstr_tbl[] = { + "%r0", "%r1", "%r2", "%r3", "%r4", "%r5", "%r6", "%r7", + "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", + "%r16", "%r17", "%r18", "%r19", "%r20", "%r21", "%r22", "%r23", + "%r24", "%r25", "%r26", "%r27", "%r28", "%r29", "%r30", "%r31", +}; +#endif diff --git a/tools/perf/arch/loongarch/include/perf_regs.h b/tools/perf/arch/loongarch/include/perf_regs.h new file mode 100644 index 000000000000..7833c7dbd38d --- /dev/null +++ b/tools/perf/arch/loongarch/include/perf_regs.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include <stdlib.h> +#include <linux/types.h> +#include <asm/perf_regs.h> + +#define PERF_REGS_MAX PERF_REG_LOONGARCH_MAX +#define PERF_REG_IP PERF_REG_LOONGARCH_PC +#define PERF_REG_SP PERF_REG_LOONGARCH_R3 + +#define PERF_REGS_MASK ((1ULL << PERF_REG_LOONGARCH_MAX) - 1) + +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/loongarch/util/Build b/tools/perf/arch/loongarch/util/Build new file mode 100644 index 000000000000..d776125a2d06 --- /dev/null +++ b/tools/perf/arch/loongarch/util/Build @@ -0,0 +1,5 @@ +perf-y += perf_regs.o + +perf-$(CONFIG_DWARF) += dwarf-regs.o +perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o +perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/loongarch/util/dwarf-regs.c b/tools/perf/arch/loongarch/util/dwarf-regs.c new file mode 100644 index 000000000000..0f6ebc387463 --- /dev/null +++ b/tools/perf/arch/loongarch/util/dwarf-regs.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * dwarf-regs.c : Mapping of DWARF debug register numbers into register names. + * + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#include <stdio.h> +#include <errno.h> /* for EINVAL */ +#include <string.h> /* for strcmp */ +#include <dwarf-regs.h> + +struct pt_regs_dwarfnum { + const char *name; + unsigned int dwarfnum; +}; + +static struct pt_regs_dwarfnum loongarch_gpr_table[] = { + {"%r0", 0}, {"%r1", 1}, {"%r2", 2}, {"%r3", 3}, + {"%r4", 4}, {"%r5", 5}, {"%r6", 6}, {"%r7", 7}, + {"%r8", 8}, {"%r9", 9}, {"%r10", 10}, {"%r11", 11}, + {"%r12", 12}, {"%r13", 13}, {"%r14", 14}, {"%r15", 15}, + {"%r16", 16}, {"%r17", 17}, {"%r18", 18}, {"%r19", 19}, + {"%r20", 20}, {"%r21", 21}, {"%r22", 22}, {"%r23", 23}, + {"%r24", 24}, {"%r25", 25}, {"%r26", 26}, {"%r27", 27}, + {"%r28", 28}, {"%r29", 29}, {"%r30", 30}, {"%r31", 31}, + {NULL, 0} +}; + +const char *get_arch_regstr(unsigned int n) +{ + n %= 32; + return loongarch_gpr_table[n].name; +} + +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_dwarfnum *roff; + + for (roff = loongarch_gpr_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->dwarfnum; + return -EINVAL; +} diff --git a/tools/perf/arch/loongarch/util/perf_regs.c b/tools/perf/arch/loongarch/util/perf_regs.c new file mode 100644 index 000000000000..2833e101a7c6 --- /dev/null +++ b/tools/perf/arch/loongarch/util/perf_regs.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "../../../util/perf_regs.h" + +const struct sample_reg sample_reg_masks[] = { + SMPL_REG_END +}; diff --git a/tools/perf/arch/loongarch/util/unwind-libdw.c b/tools/perf/arch/loongarch/util/unwind-libdw.c new file mode 100644 index 000000000000..a9415385230a --- /dev/null +++ b/tools/perf/arch/loongarch/util/unwind-libdw.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2020-2023 Loongson Technology Corporation Limited */ + +#include <elfutils/libdwfl.h> +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" +#include "../../util/sample.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[PERF_REG_LOONGARCH_MAX]; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_LOONGARCH_##r); \ + val; \ +}) + + dwarf_regs[0] = 0; + dwarf_regs[1] = REG(R1); + dwarf_regs[2] = REG(R2); + dwarf_regs[3] = REG(R3); + dwarf_regs[4] = REG(R4); + dwarf_regs[5] = REG(R5); + dwarf_regs[6] = REG(R6); + dwarf_regs[7] = REG(R7); + dwarf_regs[8] = REG(R8); + dwarf_regs[9] = REG(R9); + dwarf_regs[10] = REG(R10); + dwarf_regs[11] = REG(R11); + dwarf_regs[12] = REG(R12); + dwarf_regs[13] = REG(R13); + dwarf_regs[14] = REG(R14); + dwarf_regs[15] = REG(R15); + dwarf_regs[16] = REG(R16); + dwarf_regs[17] = REG(R17); + dwarf_regs[18] = REG(R18); + dwarf_regs[19] = REG(R19); + dwarf_regs[20] = REG(R20); + dwarf_regs[21] = REG(R21); + dwarf_regs[22] = REG(R22); + dwarf_regs[23] = REG(R23); + dwarf_regs[24] = REG(R24); + dwarf_regs[25] = REG(R25); + dwarf_regs[26] = REG(R26); + dwarf_regs[27] = REG(R27); + dwarf_regs[28] = REG(R28); + dwarf_regs[29] = REG(R29); + dwarf_regs[30] = REG(R30); + dwarf_regs[31] = REG(R31); + dwfl_thread_state_register_pc(thread, REG(PC)); + + return dwfl_thread_state_registers(thread, 0, PERF_REG_LOONGARCH_MAX, dwarf_regs); +} diff --git a/tools/perf/arch/loongarch/util/unwind-libunwind.c b/tools/perf/arch/loongarch/util/unwind-libunwind.c new file mode 100644 index 000000000000..f693167b86ef --- /dev/null +++ b/tools/perf/arch/loongarch/util/unwind-libunwind.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <errno.h> +#include <libunwind.h> +#include "perf_regs.h" +#include "../../util/unwind.h" +#include "util/debug.h" + +int libunwind__arch_reg_id(int regnum) +{ + switch (regnum) { + case UNW_LOONGARCH64_R1: + return PERF_REG_LOONGARCH_R1; + case UNW_LOONGARCH64_R2: + return PERF_REG_LOONGARCH_R2; + case UNW_LOONGARCH64_R3: + return PERF_REG_LOONGARCH_R3; + case UNW_LOONGARCH64_R4: + return PERF_REG_LOONGARCH_R4; + case UNW_LOONGARCH64_R5: + return PERF_REG_LOONGARCH_R5; + case UNW_LOONGARCH64_R6: + return PERF_REG_LOONGARCH_R6; + case UNW_LOONGARCH64_R7: + return PERF_REG_LOONGARCH_R7; + case UNW_LOONGARCH64_R8: + return PERF_REG_LOONGARCH_R8; + case UNW_LOONGARCH64_R9: + return PERF_REG_LOONGARCH_R9; + case UNW_LOONGARCH64_R10: + return PERF_REG_LOONGARCH_R10; + case UNW_LOONGARCH64_R11: + return PERF_REG_LOONGARCH_R11; + case UNW_LOONGARCH64_R12: + return PERF_REG_LOONGARCH_R12; + case UNW_LOONGARCH64_R13: + return PERF_REG_LOONGARCH_R13; + case UNW_LOONGARCH64_R14: + return PERF_REG_LOONGARCH_R14; + case UNW_LOONGARCH64_R15: + return PERF_REG_LOONGARCH_R15; + case UNW_LOONGARCH64_R16: + return PERF_REG_LOONGARCH_R16; + case UNW_LOONGARCH64_R17: + return PERF_REG_LOONGARCH_R17; + case UNW_LOONGARCH64_R18: + return PERF_REG_LOONGARCH_R18; + case UNW_LOONGARCH64_R19: + return PERF_REG_LOONGARCH_R19; + case UNW_LOONGARCH64_R20: + return PERF_REG_LOONGARCH_R20; + case UNW_LOONGARCH64_R21: + return PERF_REG_LOONGARCH_R21; + case UNW_LOONGARCH64_R22: + return PERF_REG_LOONGARCH_R22; + case UNW_LOONGARCH64_R23: + return PERF_REG_LOONGARCH_R23; + case UNW_LOONGARCH64_R24: + return PERF_REG_LOONGARCH_R24; + case UNW_LOONGARCH64_R25: + return PERF_REG_LOONGARCH_R25; + case UNW_LOONGARCH64_R26: + return PERF_REG_LOONGARCH_R26; + case UNW_LOONGARCH64_R27: + return PERF_REG_LOONGARCH_R27; + case UNW_LOONGARCH64_R28: + return PERF_REG_LOONGARCH_R28; + case UNW_LOONGARCH64_R29: + return PERF_REG_LOONGARCH_R29; + case UNW_LOONGARCH64_R30: + return PERF_REG_LOONGARCH_R30; + case UNW_LOONGARCH64_R31: + return PERF_REG_LOONGARCH_R31; + case UNW_LOONGARCH64_PC: + return PERF_REG_LOONGARCH_PC; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + + return -EINVAL; +} diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index eacca9a874e2..9d6232f681ce 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -40,6 +40,7 @@ arch/x86/lib/x86-opcode-map.txt arch/x86/tools/gen-insn-attr-x86.awk arch/arm/include/uapi/asm/perf_regs.h arch/arm64/include/uapi/asm/perf_regs.h +arch/loongarch/include/uapi/asm/perf_regs.h arch/mips/include/uapi/asm/perf_regs.h arch/powerpc/include/uapi/asm/perf_regs.h arch/s390/include/uapi/asm/perf_regs.h diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index db475e44f42f..0cc7710f32da 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -149,6 +149,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/arm/annotate/instructions.c" #include "arch/arm64/annotate/instructions.c" #include "arch/csky/annotate/instructions.c" +#include "arch/loongarch/annotate/instructions.c" #include "arch/mips/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" @@ -211,6 +212,13 @@ static struct arch architectures[] = { .comment_char = '#', }, }, + { + .name = "loongarch", + .init = loongarch__annotate_init, + .objdump = { + .comment_char = '#', + }, + }, }; static void ins__delete(struct ins_operands *ops) diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c index 3fa4486742cd..69cfaa5953bf 100644 --- a/tools/perf/util/dwarf-regs.c +++ b/tools/perf/util/dwarf-regs.c @@ -14,6 +14,10 @@ #define EM_AARCH64 183 /* ARM 64 bit */ #endif +#ifndef EM_LOONGARCH +#define EM_LOONGARCH 258 /* LoongArch */ +#endif + /* Define const char * {arch}_register_tbl[] */ #define DEFINE_DWARF_REGSTR_TABLE #include "../arch/x86/include/dwarf-regs-table.h" @@ -25,6 +29,7 @@ #include "../arch/sparc/include/dwarf-regs-table.h" #include "../arch/xtensa/include/dwarf-regs-table.h" #include "../arch/mips/include/dwarf-regs-table.h" +#include "../arch/loongarch/include/dwarf-regs-table.h" #define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL) @@ -56,6 +61,8 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine) return __get_dwarf_regstr(xtensa_regstr_tbl, n); case EM_MIPS: return __get_dwarf_regstr(mips_regstr_tbl, n); + case EM_LOONGARCH: + return __get_dwarf_regstr(loongarch_regstr_tbl, n); default: pr_err("ELF MACHINE %x is not supported.\n", machine); } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 5b8cf6a421a4..0d5d40cb997b 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -435,6 +435,8 @@ static const char *normalize_arch(char *arch) return "mips"; if (!strncmp(arch, "sh", 2) && isdigit(arch[2])) return "sh"; + if (!strncmp(arch, "loongarch", 9)) + return "loongarch"; return arch; } diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index 6af062d1c452..5f18d20ea903 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -43,6 +43,9 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #elif defined(__riscv) && __riscv_xlen == 64 #define GEN_ELF_ARCH EM_RISCV #define GEN_ELF_CLASS ELFCLASS64 +#elif defined(__loongarch__) +#define GEN_ELF_ARCH EM_LOONGARCH +#define GEN_ELF_CLASS ELFCLASS64 #else #error "unsupported architecture" #endif diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 57a567ee2cea..9bdbaa37f813 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -28,6 +28,7 @@ uint64_t __weak arch__user_reg_mask(void) #include "../../arch/arm/include/uapi/asm/perf_regs.h" #include "../../arch/csky/include/uapi/asm/perf_regs.h" +#include "../../arch/loongarch/include/uapi/asm/perf_regs.h" #include "../../arch/mips/include/uapi/asm/perf_regs.h" #include "../../arch/powerpc/include/uapi/asm/perf_regs.h" #include "../../arch/riscv/include/uapi/asm/perf_regs.h" @@ -236,6 +237,79 @@ static const char *__perf_reg_name_csky(int id) return NULL; } +static inline const char *__perf_reg_name_loongarch(int id) +{ + switch (id) { + case PERF_REG_LOONGARCH_PC: + return "PC"; + case PERF_REG_LOONGARCH_R1: + return "%r1"; + case PERF_REG_LOONGARCH_R2: + return "%r2"; + case PERF_REG_LOONGARCH_R3: + return "%r3"; + case PERF_REG_LOONGARCH_R4: + return "%r4"; + case PERF_REG_LOONGARCH_R5: + return "%r5"; + case PERF_REG_LOONGARCH_R6: + return "%r6"; + case PERF_REG_LOONGARCH_R7: + return "%r7"; + case PERF_REG_LOONGARCH_R8: + return "%r8"; + case PERF_REG_LOONGARCH_R9: + return "%r9"; + case PERF_REG_LOONGARCH_R10: + return "%r10"; + case PERF_REG_LOONGARCH_R11: + return "%r11"; + case PERF_REG_LOONGARCH_R12: + return "%r12"; + case PERF_REG_LOONGARCH_R13: + return "%r13"; + case PERF_REG_LOONGARCH_R14: + return "%r14"; + case PERF_REG_LOONGARCH_R15: + return "%r15"; + case PERF_REG_LOONGARCH_R16: + return "%r16"; + case PERF_REG_LOONGARCH_R17: + return "%r17"; + case PERF_REG_LOONGARCH_R18: + return "%r18"; + case PERF_REG_LOONGARCH_R19: + return "%r19"; + case PERF_REG_LOONGARCH_R20: + return "%r20"; + case PERF_REG_LOONGARCH_R21: + return "%r21"; + case PERF_REG_LOONGARCH_R22: + return "%r22"; + case PERF_REG_LOONGARCH_R23: + return "%r23"; + case PERF_REG_LOONGARCH_R24: + return "%r24"; + case PERF_REG_LOONGARCH_R25: + return "%r25"; + case PERF_REG_LOONGARCH_R26: + return "%r26"; + case PERF_REG_LOONGARCH_R27: + return "%r27"; + case PERF_REG_LOONGARCH_R28: + return "%r28"; + case PERF_REG_LOONGARCH_R29: + return "%r29"; + case PERF_REG_LOONGARCH_R30: + return "%r30"; + case PERF_REG_LOONGARCH_R31: + return "%r31"; + default: + break; + } + return NULL; +} + static const char *__perf_reg_name_mips(int id) { switch (id) { @@ -670,6 +744,8 @@ const char *perf_reg_name(int id, const char *arch) if (!strcmp(arch, "csky")) reg_name = __perf_reg_name_csky(id); + else if (!strcmp(arch, "loongarch")) + reg_name = __perf_reg_name_loongarch(id); else if (!strcmp(arch, "mips")) reg_name = __perf_reg_name_mips(id); else if (!strcmp(arch, "powerpc")) diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index a2e906858891..313eccef6cb4 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_arm64; #include <asm/syscalls_n64.c> const int syscalltbl_native_max_id = SYSCALLTBL_MIPS_N64_MAX_ID; static const char **syscalltbl_native = syscalltbl_mips_n64; +#elif defined(__loongarch__) +#include <asm/syscalls.c> +const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID; +static const char **syscalltbl_native = syscalltbl_loongarch; #endif struct syscall { diff --git a/tools/testing/cxl/config_check.c b/tools/testing/cxl/config_check.c index 99b56b5f6edf..0902c5d6e410 100644 --- a/tools/testing/cxl/config_check.c +++ b/tools/testing/cxl/config_check.c @@ -13,4 +13,5 @@ void check(void) BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_PMEM)); BUILD_BUG_ON(!IS_ENABLED(CONFIG_CXL_REGION_INVALIDATION_TEST)); BUILD_BUG_ON(!IS_ENABLED(CONFIG_NVDIMM_SECURITY_TEST)); + BUILD_BUG_ON(!IS_ENABLED(CONFIG_DEBUG_FS)); } diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 9263b04d35f7..ba572d03c687 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -7,6 +7,7 @@ #include <linux/delay.h> #include <linux/sizes.h> #include <linux/bits.h> +#include <asm/unaligned.h> #include <cxlmem.h> #include "trace.h" @@ -15,6 +16,11 @@ #define DEV_SIZE SZ_2G #define EFFECT(x) (1U << x) +#define MOCK_INJECT_DEV_MAX 8 +#define MOCK_INJECT_TEST_MAX 128 + +static unsigned int poison_inject_dev_max = MOCK_INJECT_DEV_MAX; + static struct cxl_cel_entry mock_cel[] = { { .opcode = cpu_to_le16(CXL_MBOX_OP_GET_SUPPORTED_LOGS), @@ -40,6 +46,18 @@ static struct cxl_cel_entry mock_cel[] = { .opcode = cpu_to_le16(CXL_MBOX_OP_GET_HEALTH_INFO), .effect = cpu_to_le16(0), }, + { + .opcode = cpu_to_le16(CXL_MBOX_OP_GET_POISON), + .effect = cpu_to_le16(0), + }, + { + .opcode = cpu_to_le16(CXL_MBOX_OP_INJECT_POISON), + .effect = cpu_to_le16(0), + }, + { + .opcode = cpu_to_le16(CXL_MBOX_OP_CLEAR_POISON), + .effect = cpu_to_le16(0), + }, }; /* See CXL 2.0 Table 181 Get Health Info Output Payload */ @@ -98,6 +116,7 @@ struct cxl_mockmem_data { int master_limit; struct mock_event_store mes; u8 event_buf[SZ_4K]; + u64 timestamp; }; static struct mock_event_log *event_find_log(struct device *dev, int log_type) @@ -361,6 +380,22 @@ struct cxl_event_mem_module mem_module = { } }; +static int mock_set_timestamp(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mockmem_data *mdata = dev_get_drvdata(cxlds->dev); + struct cxl_mbox_set_timestamp_in *ts = cmd->payload_in; + + if (cmd->size_in != sizeof(*ts)) + return -EINVAL; + + if (cmd->size_out != 0) + return -EINVAL; + + mdata->timestamp = le64_to_cpu(ts->timestamp); + return 0; +} + static void cxl_mock_add_event_logs(struct mock_event_store *mes) { put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, @@ -469,8 +504,11 @@ static int mock_id(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) cpu_to_le64(SZ_256M / CXL_CAPACITY_MULTIPLIER), .total_capacity = cpu_to_le64(DEV_SIZE / CXL_CAPACITY_MULTIPLIER), + .inject_poison_limit = cpu_to_le16(MOCK_INJECT_TEST_MAX), }; + put_unaligned_le24(CXL_POISON_LIST_MAX, id.poison_list_max_mer); + if (cmd->size_out < sizeof(id)) return -EINVAL; @@ -888,12 +926,203 @@ static int mock_health_info(struct cxl_dev_state *cxlds, return 0; } +static struct mock_poison { + struct cxl_dev_state *cxlds; + u64 dpa; +} mock_poison_list[MOCK_INJECT_TEST_MAX]; + +static struct cxl_mbox_poison_out * +cxl_get_injected_po(struct cxl_dev_state *cxlds, u64 offset, u64 length) +{ + struct cxl_mbox_poison_out *po; + int nr_records = 0; + u64 dpa; + + po = kzalloc(struct_size(po, record, poison_inject_dev_max), GFP_KERNEL); + if (!po) + return NULL; + + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds != cxlds) + continue; + if (mock_poison_list[i].dpa < offset || + mock_poison_list[i].dpa > offset + length - 1) + continue; + + dpa = mock_poison_list[i].dpa + CXL_POISON_SOURCE_INJECTED; + po->record[nr_records].address = cpu_to_le64(dpa); + po->record[nr_records].length = cpu_to_le32(1); + nr_records++; + if (nr_records == poison_inject_dev_max) + break; + } + + /* Always return count, even when zero */ + po->count = cpu_to_le16(nr_records); + + return po; +} + +static int mock_get_poison(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_poison_in *pi = cmd->payload_in; + struct cxl_mbox_poison_out *po; + u64 offset = le64_to_cpu(pi->offset); + u64 length = le64_to_cpu(pi->length); + int nr_records; + + po = cxl_get_injected_po(cxlds, offset, length); + if (!po) + return -ENOMEM; + nr_records = le16_to_cpu(po->count); + memcpy(cmd->payload_out, po, struct_size(po, record, nr_records)); + cmd->size_out = struct_size(po, record, nr_records); + kfree(po); + + return 0; +} + +static bool mock_poison_dev_max_injected(struct cxl_dev_state *cxlds) +{ + int count = 0; + + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds == cxlds) + count++; + } + return (count >= poison_inject_dev_max); +} + +static bool mock_poison_add(struct cxl_dev_state *cxlds, u64 dpa) +{ + if (mock_poison_dev_max_injected(cxlds)) { + dev_dbg(cxlds->dev, + "Device poison injection limit has been reached: %d\n", + MOCK_INJECT_DEV_MAX); + return false; + } + + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (!mock_poison_list[i].cxlds) { + mock_poison_list[i].cxlds = cxlds; + mock_poison_list[i].dpa = dpa; + return true; + } + } + dev_dbg(cxlds->dev, + "Mock test poison injection limit has been reached: %d\n", + MOCK_INJECT_TEST_MAX); + + return false; +} + +static bool mock_poison_found(struct cxl_dev_state *cxlds, u64 dpa) +{ + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds == cxlds && + mock_poison_list[i].dpa == dpa) + return true; + } + return false; +} + +static int mock_inject_poison(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_inject_poison *pi = cmd->payload_in; + u64 dpa = le64_to_cpu(pi->address); + + if (mock_poison_found(cxlds, dpa)) { + /* Not an error to inject poison if already poisoned */ + dev_dbg(cxlds->dev, "DPA: 0x%llx already poisoned\n", dpa); + return 0; + } + if (!mock_poison_add(cxlds, dpa)) + return -ENXIO; + + return 0; +} + +static bool mock_poison_del(struct cxl_dev_state *cxlds, u64 dpa) +{ + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds == cxlds && + mock_poison_list[i].dpa == dpa) { + mock_poison_list[i].cxlds = NULL; + return true; + } + } + return false; +} + +static int mock_clear_poison(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_clear_poison *pi = cmd->payload_in; + u64 dpa = le64_to_cpu(pi->address); + + /* + * A real CXL device will write pi->write_data to the address + * being cleared. In this mock, just delete this address from + * the mock poison list. + */ + if (!mock_poison_del(cxlds, dpa)) + dev_dbg(cxlds->dev, "DPA: 0x%llx not in poison list\n", dpa); + + return 0; +} + +static bool mock_poison_list_empty(void) +{ + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds) + return false; + } + return true; +} + +static ssize_t poison_inject_max_show(struct device_driver *drv, char *buf) +{ + return sysfs_emit(buf, "%u\n", poison_inject_dev_max); +} + +static ssize_t poison_inject_max_store(struct device_driver *drv, + const char *buf, size_t len) +{ + int val; + + if (kstrtoint(buf, 0, &val) < 0) + return -EINVAL; + + if (!mock_poison_list_empty()) + return -EBUSY; + + if (val <= MOCK_INJECT_TEST_MAX) + poison_inject_dev_max = val; + else + return -EINVAL; + + return len; +} + +static DRIVER_ATTR_RW(poison_inject_max); + +static struct attribute *cxl_mock_mem_core_attrs[] = { + &driver_attr_poison_inject_max.attr, + NULL +}; +ATTRIBUTE_GROUPS(cxl_mock_mem_core); + static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) { struct device *dev = cxlds->dev; int rc = -EIO; switch (cmd->opcode) { + case CXL_MBOX_OP_SET_TIMESTAMP: + rc = mock_set_timestamp(cxlds, cmd); + break; case CXL_MBOX_OP_GET_SUPPORTED_LOGS: rc = mock_gsl(cmd); break; @@ -942,6 +1171,15 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd * case CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE: rc = mock_passphrase_secure_erase(cxlds, cmd); break; + case CXL_MBOX_OP_GET_POISON: + rc = mock_get_poison(cxlds, cmd); + break; + case CXL_MBOX_OP_INJECT_POISON: + rc = mock_inject_poison(cxlds, cmd); + break; + case CXL_MBOX_OP_CLEAR_POISON: + rc = mock_clear_poison(cxlds, cmd); + break; default: break; } @@ -1010,6 +1248,14 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + rc = cxl_poison_state_init(cxlds); + if (rc) + return rc; + + rc = cxl_set_timestamp(cxlds); + if (rc) + return rc; + rc = cxl_dev_state_identify(cxlds); if (rc) return rc; @@ -1083,6 +1329,7 @@ static struct platform_driver cxl_mock_mem_driver = { .driver = { .name = KBUILD_MODNAME, .dev_groups = cxl_mock_mem_groups, + .groups = cxl_mock_mem_core_groups, }, }; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 97dcdaa656f6..90a62cf75008 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -64,6 +64,7 @@ TARGETS += pstore TARGETS += ptrace TARGETS += openat2 TARGETS += resctrl +TARGETS += riscv TARGETS += rlimits TARGETS += rseq TARGETS += rtc diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 75c100de90ff..2b5215cc599f 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -15,13 +15,6 @@ skip_test() { [[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!" -# Set sched verbose flag, if available -if [[ -d /sys/kernel/debug/sched ]] -then - # Used to restore the original setting during cleanup - SCHED_DEBUG=$(cat /sys/kernel/debug/sched/verbose) - echo Y > /sys/kernel/debug/sched/verbose -fi # Get wait_inotify location WAIT_INOTIFY=$(cd $(dirname $0); pwd)/wait_inotify @@ -37,10 +30,14 @@ CPUS=$(lscpu | grep "^CPU(s):" | sed -e "s/.*:[[:space:]]*//") PROG=$1 VERBOSE= DELAY_FACTOR=1 +SCHED_DEBUG= while [[ "$1" = -* ]] do case "$1" in -v) VERBOSE=1 + # Enable sched/verbose can slow thing down + [[ $DELAY_FACTOR -eq 1 ]] && + DELAY_FACTOR=2 break ;; -d) DELAY_FACTOR=$2 @@ -54,6 +51,14 @@ do shift done +# Set sched verbose flag if available when "-v" option is specified +if [[ -n "$VERBOSE" && -d /sys/kernel/debug/sched ]] +then + # Used to restore the original setting during cleanup + SCHED_DEBUG=$(cat /sys/kernel/debug/sched/verbose) + echo Y > /sys/kernel/debug/sched/verbose +fi + cd $CGROUP2 echo +cpuset > cgroup.subtree_control [[ -d test ]] || mkdir test @@ -65,7 +70,8 @@ cleanup() rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1 cd .. rmdir test > /dev/null 2>&1 - echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose + [[ -n "$SCHED_DEBUG" ]] && + echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose } # Pause in ms @@ -571,7 +577,6 @@ run_state_test() echo "Test $TEST[$I] failed result check!" eval echo \"\${$TEST[$I]}\" dump_states - online_cpus exit 1 } @@ -582,7 +587,6 @@ run_state_test() eval echo \"\${$TEST[$I]}\" echo dump_states - online_cpus exit 1 } } @@ -594,7 +598,6 @@ run_state_test() eval echo \"\${$TEST[$I]}\" echo dump_states - online_cpus exit 1 } } diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 84a627c43795..7a5ff646e7e7 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -105,6 +105,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test +TEST_GEN_PROGS_x86_64 += x86_64/xcr0_cpuid_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test @@ -141,6 +142,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list TEST_GEN_PROGS_aarch64 += aarch64/hypercalls TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test TEST_GEN_PROGS_aarch64 += aarch64/psci_test +TEST_GEN_PROGS_aarch64 += aarch64/smccc_filter TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config TEST_GEN_PROGS_aarch64 += aarch64/vgic_init TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 26556a266021..8ef370924a02 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -47,6 +47,7 @@ struct test_args { int nr_iter; int timer_period_ms; int migration_freq_ms; + struct kvm_arm_counter_offset offset; }; static struct test_args test_args = { @@ -54,6 +55,7 @@ static struct test_args test_args = { .nr_iter = NR_TEST_ITERS_DEF, .timer_period_ms = TIMER_TEST_PERIOD_MS_DEF, .migration_freq_ms = TIMER_TEST_MIGRATION_FREQ_MS, + .offset = { .reserved = 1 }, }; #define msecs_to_usecs(msec) ((msec) * 1000LL) @@ -121,25 +123,35 @@ static void guest_validate_irq(unsigned int intid, uint64_t xcnt = 0, xcnt_diff_us, cval = 0; unsigned long xctl = 0; unsigned int timer_irq = 0; + unsigned int accessor; - if (stage == GUEST_STAGE_VTIMER_CVAL || - stage == GUEST_STAGE_VTIMER_TVAL) { - xctl = timer_get_ctl(VIRTUAL); - timer_set_ctl(VIRTUAL, CTL_IMASK); - xcnt = timer_get_cntct(VIRTUAL); - cval = timer_get_cval(VIRTUAL); + if (intid == IAR_SPURIOUS) + return; + + switch (stage) { + case GUEST_STAGE_VTIMER_CVAL: + case GUEST_STAGE_VTIMER_TVAL: + accessor = VIRTUAL; timer_irq = vtimer_irq; - } else if (stage == GUEST_STAGE_PTIMER_CVAL || - stage == GUEST_STAGE_PTIMER_TVAL) { - xctl = timer_get_ctl(PHYSICAL); - timer_set_ctl(PHYSICAL, CTL_IMASK); - xcnt = timer_get_cntct(PHYSICAL); - cval = timer_get_cval(PHYSICAL); + break; + case GUEST_STAGE_PTIMER_CVAL: + case GUEST_STAGE_PTIMER_TVAL: + accessor = PHYSICAL; timer_irq = ptimer_irq; - } else { + break; + default: GUEST_ASSERT(0); + return; } + xctl = timer_get_ctl(accessor); + if ((xctl & CTL_IMASK) || !(xctl & CTL_ENABLE)) + return; + + timer_set_ctl(accessor, CTL_IMASK); + xcnt = timer_get_cntct(accessor); + cval = timer_get_cval(accessor); + xcnt_diff_us = cycles_to_usec(xcnt - shared_data->xcnt); /* Make sure we are dealing with the correct timer IRQ */ @@ -148,6 +160,8 @@ static void guest_validate_irq(unsigned int intid, /* Basic 'timer condition met' check */ GUEST_ASSERT_3(xcnt >= cval, xcnt, cval, xcnt_diff_us); GUEST_ASSERT_1(xctl & CTL_ISTATUS, xctl); + + WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1); } static void guest_irq_handler(struct ex_regs *regs) @@ -158,8 +172,6 @@ static void guest_irq_handler(struct ex_regs *regs) guest_validate_irq(intid, shared_data); - WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1); - gic_set_eoi(intid); } @@ -372,6 +384,13 @@ static struct kvm_vm *test_vm_create(void) vm_init_descriptor_tables(vm); vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handler); + if (!test_args.offset.reserved) { + if (kvm_has_cap(KVM_CAP_COUNTER_OFFSET)) + vm_ioctl(vm, KVM_ARM_SET_COUNTER_OFFSET, &test_args.offset); + else + TEST_FAIL("no support for global offset\n"); + } + for (i = 0; i < nr_vcpus; i++) vcpu_init_descriptor_tables(vcpus[i]); @@ -403,6 +422,7 @@ static void test_print_help(char *name) TIMER_TEST_PERIOD_MS_DEF); pr_info("\t-m: Frequency (in ms) of vCPUs to migrate to different pCPU. 0 to turn off (default: %u)\n", TIMER_TEST_MIGRATION_FREQ_MS); + pr_info("\t-o: Counter offset (in counter cycles, default: 0)\n"); pr_info("\t-h: print this help screen\n"); } @@ -410,7 +430,7 @@ static bool parse_args(int argc, char *argv[]) { int opt; - while ((opt = getopt(argc, argv, "hn:i:p:m:")) != -1) { + while ((opt = getopt(argc, argv, "hn:i:p:m:o:")) != -1) { switch (opt) { case 'n': test_args.nr_vcpus = atoi_positive("Number of vCPUs", optarg); @@ -429,6 +449,10 @@ static bool parse_args(int argc, char *argv[]) case 'm': test_args.migration_freq_ms = atoi_non_negative("Frequency", optarg); break; + case 'o': + test_args.offset.counter_offset = strtol(optarg, NULL, 0); + test_args.offset.reserved = 0; + break; case 'h': default: goto err; diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index d287dd2cac0a..d4e1f4af29d6 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -651,7 +651,7 @@ int main(int ac, char **av) * The current blessed list was primed with the output of kernel version * v4.15 with --core-reg-fixup and then later updated with new registers. * - * The blessed list is up to date with kernel version v5.13-rc3 + * The blessed list is up to date with kernel version v6.4 (or so we hope) */ static __u64 base_regs[] = { KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]), @@ -807,10 +807,10 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 0, 3, 7), ARM64_SYS_REG(3, 0, 0, 4, 0), /* ID_AA64PFR0_EL1 */ ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ - ARM64_SYS_REG(3, 0, 0, 4, 2), + ARM64_SYS_REG(3, 0, 0, 4, 2), /* ID_AA64PFR2_EL1 */ ARM64_SYS_REG(3, 0, 0, 4, 3), ARM64_SYS_REG(3, 0, 0, 4, 4), /* ID_AA64ZFR0_EL1 */ - ARM64_SYS_REG(3, 0, 0, 4, 5), + ARM64_SYS_REG(3, 0, 0, 4, 5), /* ID_AA64SMFR0_EL1 */ ARM64_SYS_REG(3, 0, 0, 4, 6), ARM64_SYS_REG(3, 0, 0, 4, 7), ARM64_SYS_REG(3, 0, 0, 5, 0), /* ID_AA64DFR0_EL1 */ @@ -823,7 +823,7 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 0, 5, 7), ARM64_SYS_REG(3, 0, 0, 6, 0), /* ID_AA64ISAR0_EL1 */ ARM64_SYS_REG(3, 0, 0, 6, 1), /* ID_AA64ISAR1_EL1 */ - ARM64_SYS_REG(3, 0, 0, 6, 2), + ARM64_SYS_REG(3, 0, 0, 6, 2), /* ID_AA64ISAR2_EL1 */ ARM64_SYS_REG(3, 0, 0, 6, 3), ARM64_SYS_REG(3, 0, 0, 6, 4), ARM64_SYS_REG(3, 0, 0, 6, 5), @@ -832,8 +832,8 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 0, 7, 0), /* ID_AA64MMFR0_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 1), /* ID_AA64MMFR1_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 2), /* ID_AA64MMFR2_EL1 */ - ARM64_SYS_REG(3, 0, 0, 7, 3), - ARM64_SYS_REG(3, 0, 0, 7, 4), + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 4), /* ID_AA64MMFR4_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 5), ARM64_SYS_REG(3, 0, 0, 7, 6), ARM64_SYS_REG(3, 0, 0, 7, 7), @@ -858,6 +858,9 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */ ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */ ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */ + ARM64_SYS_REG(3, 3, 14, 0, 1), /* CNTPCT_EL0 */ + ARM64_SYS_REG(3, 3, 14, 2, 1), /* CNTP_CTL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 2, 2), /* CNTP_CVAL_EL0 */ ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */ ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */ ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */ diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/aarch64/smccc_filter.c new file mode 100644 index 000000000000..f4ceae9c8925 --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/smccc_filter.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * smccc_filter - Tests for the SMCCC filter UAPI. + * + * Copyright (c) 2023 Google LLC + * + * This test includes: + * - Tests that the UAPI constraints are upheld by KVM. For example, userspace + * is prevented from filtering the architecture range of SMCCC calls. + * - Test that the filter actions (DENIED, FWD_TO_USER) work as intended. + */ + +#include <linux/arm-smccc.h> +#include <linux/psci.h> +#include <stdint.h> + +#include "processor.h" +#include "test_util.h" + +enum smccc_conduit { + HVC_INSN, + SMC_INSN, +}; + +#define for_each_conduit(conduit) \ + for (conduit = HVC_INSN; conduit <= SMC_INSN; conduit++) + +static void guest_main(uint32_t func_id, enum smccc_conduit conduit) +{ + struct arm_smccc_res res; + + if (conduit == SMC_INSN) + smccc_smc(func_id, 0, 0, 0, 0, 0, 0, 0, &res); + else + smccc_hvc(func_id, 0, 0, 0, 0, 0, 0, 0, &res); + + GUEST_SYNC(res.a0); +} + +static int __set_smccc_filter(struct kvm_vm *vm, uint32_t start, uint32_t nr_functions, + enum kvm_smccc_filter_action action) +{ + struct kvm_smccc_filter filter = { + .base = start, + .nr_functions = nr_functions, + .action = action, + }; + + return __kvm_device_attr_set(vm->fd, KVM_ARM_VM_SMCCC_CTRL, + KVM_ARM_VM_SMCCC_FILTER, &filter); +} + +static void set_smccc_filter(struct kvm_vm *vm, uint32_t start, uint32_t nr_functions, + enum kvm_smccc_filter_action action) +{ + int ret = __set_smccc_filter(vm, start, nr_functions, action); + + TEST_ASSERT(!ret, "failed to configure SMCCC filter: %d", ret); +} + +static struct kvm_vm *setup_vm(struct kvm_vcpu **vcpu) +{ + struct kvm_vcpu_init init; + struct kvm_vm *vm; + + vm = vm_create(1); + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + + /* + * Enable in-kernel emulation of PSCI to ensure that calls are denied + * due to the SMCCC filter, not because of KVM. + */ + init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); + + *vcpu = aarch64_vcpu_add(vm, 0, &init, guest_main); + return vm; +} + +static void test_pad_must_be_zero(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + struct kvm_smccc_filter filter = { + .base = PSCI_0_2_FN_PSCI_VERSION, + .nr_functions = 1, + .action = KVM_SMCCC_FILTER_DENY, + .pad = { -1 }, + }; + int r; + + r = __kvm_device_attr_set(vm->fd, KVM_ARM_VM_SMCCC_CTRL, + KVM_ARM_VM_SMCCC_FILTER, &filter); + TEST_ASSERT(r < 0 && errno == EINVAL, + "Setting filter with nonzero padding should return EINVAL"); +} + +/* Ensure that userspace cannot filter the Arm Architecture SMCCC range */ +static void test_filter_reserved_range(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + uint32_t smc64_fn; + int r; + + r = __set_smccc_filter(vm, ARM_SMCCC_ARCH_WORKAROUND_1, + 1, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EEXIST, + "Attempt to filter reserved range should return EEXIST"); + + smc64_fn = ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, + 0, 0); + + r = __set_smccc_filter(vm, smc64_fn, 1, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EEXIST, + "Attempt to filter reserved range should return EEXIST"); + + kvm_vm_free(vm); +} + +static void test_invalid_nr_functions(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + int r; + + r = __set_smccc_filter(vm, PSCI_0_2_FN64_CPU_ON, 0, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EINVAL, + "Attempt to filter 0 functions should return EINVAL"); + + kvm_vm_free(vm); +} + +static void test_overflow_nr_functions(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + int r; + + r = __set_smccc_filter(vm, ~0, ~0, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EINVAL, + "Attempt to overflow filter range should return EINVAL"); + + kvm_vm_free(vm); +} + +static void test_reserved_action(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + int r; + + r = __set_smccc_filter(vm, PSCI_0_2_FN64_CPU_ON, 1, -1); + TEST_ASSERT(r < 0 && errno == EINVAL, + "Attempt to use reserved filter action should return EINVAL"); + + kvm_vm_free(vm); +} + + +/* Test that overlapping configurations of the SMCCC filter are rejected */ +static void test_filter_overlap(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + int r; + + set_smccc_filter(vm, PSCI_0_2_FN64_CPU_ON, 1, KVM_SMCCC_FILTER_DENY); + + r = __set_smccc_filter(vm, PSCI_0_2_FN64_CPU_ON, 1, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EEXIST, + "Attempt to filter already configured range should return EEXIST"); + + kvm_vm_free(vm); +} + +static void expect_call_denied(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + if (get_ucall(vcpu, &uc) != UCALL_SYNC) + TEST_FAIL("Unexpected ucall: %lu\n", uc.cmd); + + TEST_ASSERT(uc.args[1] == SMCCC_RET_NOT_SUPPORTED, + "Unexpected SMCCC return code: %lu", uc.args[1]); +} + +/* Denied SMCCC calls have a return code of SMCCC_RET_NOT_SUPPORTED */ +static void test_filter_denied(void) +{ + enum smccc_conduit conduit; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + for_each_conduit(conduit) { + vm = setup_vm(&vcpu); + + set_smccc_filter(vm, PSCI_0_2_FN_PSCI_VERSION, 1, KVM_SMCCC_FILTER_DENY); + vcpu_args_set(vcpu, 2, PSCI_0_2_FN_PSCI_VERSION, conduit); + + vcpu_run(vcpu); + expect_call_denied(vcpu); + + kvm_vm_free(vm); + } +} + +static void expect_call_fwd_to_user(struct kvm_vcpu *vcpu, uint32_t func_id, + enum smccc_conduit conduit) +{ + struct kvm_run *run = vcpu->run; + + TEST_ASSERT(run->exit_reason == KVM_EXIT_HYPERCALL, + "Unexpected exit reason: %u", run->exit_reason); + TEST_ASSERT(run->hypercall.nr == func_id, + "Unexpected SMCCC function: %llu", run->hypercall.nr); + + if (conduit == SMC_INSN) + TEST_ASSERT(run->hypercall.flags & KVM_HYPERCALL_EXIT_SMC, + "KVM_HYPERCALL_EXIT_SMC is not set"); + else + TEST_ASSERT(!(run->hypercall.flags & KVM_HYPERCALL_EXIT_SMC), + "KVM_HYPERCALL_EXIT_SMC is set"); +} + +/* SMCCC calls forwarded to userspace cause KVM_EXIT_HYPERCALL exits */ +static void test_filter_fwd_to_user(void) +{ + enum smccc_conduit conduit; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + for_each_conduit(conduit) { + vm = setup_vm(&vcpu); + + set_smccc_filter(vm, PSCI_0_2_FN_PSCI_VERSION, 1, KVM_SMCCC_FILTER_FWD_TO_USER); + vcpu_args_set(vcpu, 2, PSCI_0_2_FN_PSCI_VERSION, conduit); + + vcpu_run(vcpu); + expect_call_fwd_to_user(vcpu, PSCI_0_2_FN_PSCI_VERSION, conduit); + + kvm_vm_free(vm); + } +} + +static bool kvm_supports_smccc_filter(void) +{ + struct kvm_vm *vm = vm_create_barebones(); + int r; + + r = __kvm_has_device_attr(vm->fd, KVM_ARM_VM_SMCCC_CTRL, KVM_ARM_VM_SMCCC_FILTER); + + kvm_vm_free(vm); + return !r; +} + +int main(void) +{ + TEST_REQUIRE(kvm_supports_smccc_filter()); + + test_pad_must_be_zero(); + test_invalid_nr_functions(); + test_overflow_nr_functions(); + test_reserved_action(); + test_filter_reserved_range(); + test_filter_overlap(); + test_filter_denied(); + test_filter_fwd_to_user(); +} diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config index d011b38e259e..8835fed09e9f 100644 --- a/tools/testing/selftests/kvm/config +++ b/tools/testing/selftests/kvm/config @@ -2,3 +2,4 @@ CONFIG_KVM=y CONFIG_KVM_INTEL=y CONFIG_KVM_AMD=y CONFIG_USERFAULTFD=y +CONFIG_IDLE_PAGE_TRACKING=y diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index b0e1fc4de9e2..2439c4043fed 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -194,7 +194,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) ts_diff.tv_sec, ts_diff.tv_nsec); pr_info("Overall demand paging rate: %f pgs/sec\n", memstress_args.vcpu_args[0].pages * nr_vcpus / - ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); + ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC)); memstress_destroy_vm(vm); diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 5f977528e09c..cb537253a6b9 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -214,6 +214,19 @@ void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, uint64_t arg6, struct arm_smccc_res *res); +/** + * smccc_smc - Invoke a SMCCC function using the smc conduit + * @function_id: the SMCCC function to be called + * @arg0-arg6: SMCCC function arguments, corresponding to registers x1-x7 + * @res: pointer to write the return values from registers x0-x3 + * + */ +void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, + uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, + uint64_t arg6, struct arm_smccc_res *res); + + + uint32_t guest_get_vcpuid(void); #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index fbc2a79369b8..a089c356f354 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -213,6 +213,7 @@ extern const struct vm_guest_mode_params vm_guest_mode_params[]; int open_path_or_exit(const char *path, int flags); int open_kvm_dev_path_or_exit(void); +bool get_kvm_param_bool(const char *param); bool get_kvm_intel_param_bool(const char *param); bool get_kvm_amd_param_bool(const char *param); diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 90387ddcb2a9..aa434c8f19c5 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -48,6 +48,35 @@ extern bool host_cpu_is_amd; #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) +struct xstate_header { + u64 xstate_bv; + u64 xcomp_bv; + u64 reserved[6]; +} __attribute__((packed)); + +struct xstate { + u8 i387[512]; + struct xstate_header header; + u8 extended_state_area[0]; +} __attribute__ ((packed, aligned (64))); + +#define XFEATURE_MASK_FP BIT_ULL(0) +#define XFEATURE_MASK_SSE BIT_ULL(1) +#define XFEATURE_MASK_YMM BIT_ULL(2) +#define XFEATURE_MASK_BNDREGS BIT_ULL(3) +#define XFEATURE_MASK_BNDCSR BIT_ULL(4) +#define XFEATURE_MASK_OPMASK BIT_ULL(5) +#define XFEATURE_MASK_ZMM_Hi256 BIT_ULL(6) +#define XFEATURE_MASK_Hi16_ZMM BIT_ULL(7) +#define XFEATURE_MASK_XTILE_CFG BIT_ULL(17) +#define XFEATURE_MASK_XTILE_DATA BIT_ULL(18) + +#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_ZMM_Hi256 | \ + XFEATURE_MASK_Hi16_ZMM) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILE_DATA | \ + XFEATURE_MASK_XTILE_CFG) + /* Note, these are ordered alphabetically to match kvm_cpuid_entry2. Eww. */ enum cpuid_output_regs { KVM_CPUID_EAX, @@ -131,6 +160,7 @@ struct kvm_x86_cpu_feature { #define X86_FEATURE_XTILEDATA KVM_X86_CPU_FEATURE(0xD, 0, EAX, 18) #define X86_FEATURE_XSAVES KVM_X86_CPU_FEATURE(0xD, 1, EAX, 3) #define X86_FEATURE_XFD KVM_X86_CPU_FEATURE(0xD, 1, EAX, 4) +#define X86_FEATURE_XTILEDATA_XFD KVM_X86_CPU_FEATURE(0xD, 18, ECX, 2) /* * Extended Leafs, a.k.a. AMD defined @@ -211,10 +241,14 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_PMU_NR_GP_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15) #define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31) +#define X86_PROPERTY_SUPPORTED_XCR0_LO KVM_X86_CPU_PROPERTY(0xd, 0, EAX, 0, 31) #define X86_PROPERTY_XSTATE_MAX_SIZE_XCR0 KVM_X86_CPU_PROPERTY(0xd, 0, EBX, 0, 31) #define X86_PROPERTY_XSTATE_MAX_SIZE KVM_X86_CPU_PROPERTY(0xd, 0, ECX, 0, 31) +#define X86_PROPERTY_SUPPORTED_XCR0_HI KVM_X86_CPU_PROPERTY(0xd, 0, EDX, 0, 31) + #define X86_PROPERTY_XSTATE_TILE_SIZE KVM_X86_CPU_PROPERTY(0xd, 18, EAX, 0, 31) #define X86_PROPERTY_XSTATE_TILE_OFFSET KVM_X86_CPU_PROPERTY(0xd, 18, EBX, 0, 31) +#define X86_PROPERTY_AMX_MAX_PALETTE_TABLES KVM_X86_CPU_PROPERTY(0x1d, 0, EAX, 0, 31) #define X86_PROPERTY_AMX_TOTAL_TILE_BYTES KVM_X86_CPU_PROPERTY(0x1d, 1, EAX, 0, 15) #define X86_PROPERTY_AMX_BYTES_PER_TILE KVM_X86_CPU_PROPERTY(0x1d, 1, EAX, 16, 31) #define X86_PROPERTY_AMX_BYTES_PER_ROW KVM_X86_CPU_PROPERTY(0x1d, 1, EBX, 0, 15) @@ -496,6 +530,24 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } +static inline u64 xgetbv(u32 index) +{ + u32 eax, edx; + + __asm__ __volatile__("xgetbv;" + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax | ((u64)edx << 32); +} + +static inline void xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + __asm__ __volatile__("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); +} + static inline struct desc_ptr get_gdt(void) { struct desc_ptr gdt; @@ -632,6 +684,15 @@ static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) !this_cpu_has(feature.anti_feature); } +static __always_inline uint64_t this_cpu_supported_xcr0(void) +{ + if (!this_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO)) + return 0; + + return this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) | + ((uint64_t)this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); +} + typedef u32 __attribute__((vector_size(16))) sse128_t; #define __sse128_u union { sse128_t vec; u64 as_u64[2]; u32 as_u32[4]; } #define sse128_lo(x) ({ __sse128_u t; t.vec = x; t.as_u64[0]; }) @@ -928,14 +989,45 @@ static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu, uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index); int _vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, uint64_t msr_value); -static inline void vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, - uint64_t msr_value) -{ - int r = _vcpu_set_msr(vcpu, msr_index, msr_value); +/* + * Assert on an MSR access(es) and pretty print the MSR name when possible. + * Note, the caller provides the stringified name so that the name of macro is + * printed, not the value the macro resolves to (due to macro expansion). + */ +#define TEST_ASSERT_MSR(cond, fmt, msr, str, args...) \ +do { \ + if (__builtin_constant_p(msr)) { \ + TEST_ASSERT(cond, fmt, str, args); \ + } else if (!(cond)) { \ + char buf[16]; \ + \ + snprintf(buf, sizeof(buf), "MSR 0x%x", msr); \ + TEST_ASSERT(cond, fmt, buf, args); \ + } \ +} while (0) - TEST_ASSERT(r == 1, KVM_IOCTL_ERROR(KVM_SET_MSRS, r)); +/* + * Returns true if KVM should return the last written value when reading an MSR + * from userspace, e.g. the MSR isn't a command MSR, doesn't emulate state that + * is changing, etc. This is NOT an exhaustive list! The intent is to filter + * out MSRs that are not durable _and_ that a selftest wants to write. + */ +static inline bool is_durable_msr(uint32_t msr) +{ + return msr != MSR_IA32_TSC; } +#define vcpu_set_msr(vcpu, msr, val) \ +do { \ + uint64_t r, v = val; \ + \ + TEST_ASSERT_MSR(_vcpu_set_msr(vcpu, msr, v) == 1, \ + "KVM_SET_MSRS failed on %s, value = 0x%lx", msr, #msr, v); \ + if (!is_durable_msr(msr)) \ + break; \ + r = vcpu_get_msr(vcpu, msr); \ + TEST_ASSERT_MSR(r == v, "Set %s to '0x%lx', got back '0x%lx'", msr, #msr, v, r);\ +} while (0) void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); bool vm_is_unrestricted_guest(struct kvm_vm *vm); @@ -1055,6 +1147,14 @@ static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val) return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr)); } +static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value) +{ + u32 eax = value; + u32 edx = value >> 32; + + return kvm_asm_safe("xsetbv", "a" (eax), "d" (edx), "c" (index)); +} + bool kvm_is_tdp_enabled(void); uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, @@ -1066,10 +1166,10 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1); void xen_hypercall(uint64_t nr, uint64_t a0, void *a1); -void __vm_xsave_require_permission(int bit, const char *name); +void __vm_xsave_require_permission(uint64_t xfeature, const char *name); -#define vm_xsave_require_permission(perm) \ - __vm_xsave_require_permission(perm, #perm) +#define vm_xsave_require_permission(xfeature) \ + __vm_xsave_require_permission(xfeature, #xfeature) enum pg_level { PG_LEVEL_NONE, @@ -1106,14 +1206,6 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, #define X86_CR0_CD (1UL<<30) /* Cache Disable */ #define X86_CR0_PG (1UL<<31) /* Paging */ -#define XSTATE_XTILE_CFG_BIT 17 -#define XSTATE_XTILE_DATA_BIT 18 - -#define XSTATE_XTILE_CFG_MASK (1ULL << XSTATE_XTILE_CFG_BIT) -#define XSTATE_XTILE_DATA_MASK (1ULL << XSTATE_XTILE_DATA_BIT) -#define XFEATURE_XTILE_MASK (XSTATE_XTILE_CFG_MASK | \ - XSTATE_XTILE_DATA_MASK) - #define PFERR_PRESENT_BIT 0 #define PFERR_WRITE_BIT 1 #define PFERR_USER_BIT 2 diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 5972a23b2765..3a0259e25335 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -58,10 +58,27 @@ static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva) return (gva >> vm->page_shift) & mask; } -static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry) +static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs) { - uint64_t mask = ((1UL << (vm->va_bits - vm->page_shift)) - 1) << vm->page_shift; - return entry & mask; + uint64_t pte; + + pte = pa & GENMASK(47, vm->page_shift); + if (vm->page_shift == 16) + pte |= FIELD_GET(GENMASK(51, 48), pa) << 12; + pte |= attrs; + + return pte; +} + +static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte) +{ + uint64_t pa; + + pa = pte & GENMASK(47, vm->page_shift); + if (vm->page_shift == 16) + pa |= FIELD_GET(GENMASK(15, 12), pte) << 48; + + return pa; } static uint64_t ptrs_per_pgd(struct kvm_vm *vm) @@ -110,18 +127,18 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8; if (!*ptep) - *ptep = vm_alloc_page_table(vm) | 3; + *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3); switch (vm->pgtable_levels) { case 4: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8; if (!*ptep) - *ptep = vm_alloc_page_table(vm) | 3; + *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3); /* fall through */ case 3: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8; if (!*ptep) - *ptep = vm_alloc_page_table(vm) | 3; + *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3); /* fall through */ case 2: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8; @@ -130,8 +147,7 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, TEST_FAIL("Page table levels must be 2, 3, or 4"); } - *ptep = paddr | 3; - *ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */; + *ptep = addr_pte(vm, paddr, (attr_idx << 2) | (1 << 10) | 3); /* AF */ } void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) @@ -226,7 +242,7 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) { struct kvm_vcpu_init default_init = { .target = -1, }; struct kvm_vm *vm = vcpu->vm; - uint64_t sctlr_el1, tcr_el1; + uint64_t sctlr_el1, tcr_el1, ttbr0_el1; if (!init) init = &default_init; @@ -277,10 +293,13 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); } + ttbr0_el1 = vm->pgd & GENMASK(47, vm->page_shift); + /* Configure output size */ switch (vm->mode) { case VM_MODE_P52V48_64K: tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2; break; case VM_MODE_P48V48_4K: case VM_MODE_P48V48_16K: @@ -310,7 +329,7 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MAIR_EL1), DEFAULT_MAIR_EL1); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), vm->pgd); + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), ttbr0_el1); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TPIDR_EL1), vcpu->id); } @@ -508,29 +527,43 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, close(kvm_fd); } +#define __smccc_call(insn, function_id, arg0, arg1, arg2, arg3, arg4, arg5, \ + arg6, res) \ + asm volatile("mov w0, %w[function_id]\n" \ + "mov x1, %[arg0]\n" \ + "mov x2, %[arg1]\n" \ + "mov x3, %[arg2]\n" \ + "mov x4, %[arg3]\n" \ + "mov x5, %[arg4]\n" \ + "mov x6, %[arg5]\n" \ + "mov x7, %[arg6]\n" \ + #insn "#0\n" \ + "mov %[res0], x0\n" \ + "mov %[res1], x1\n" \ + "mov %[res2], x2\n" \ + "mov %[res3], x3\n" \ + : [res0] "=r"(res->a0), [res1] "=r"(res->a1), \ + [res2] "=r"(res->a2), [res3] "=r"(res->a3) \ + : [function_id] "r"(function_id), [arg0] "r"(arg0), \ + [arg1] "r"(arg1), [arg2] "r"(arg2), [arg3] "r"(arg3), \ + [arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6) \ + : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7") + + void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, uint64_t arg6, struct arm_smccc_res *res) { - asm volatile("mov w0, %w[function_id]\n" - "mov x1, %[arg0]\n" - "mov x2, %[arg1]\n" - "mov x3, %[arg2]\n" - "mov x4, %[arg3]\n" - "mov x5, %[arg4]\n" - "mov x6, %[arg5]\n" - "mov x7, %[arg6]\n" - "hvc #0\n" - "mov %[res0], x0\n" - "mov %[res1], x1\n" - "mov %[res2], x2\n" - "mov %[res3], x3\n" - : [res0] "=r"(res->a0), [res1] "=r"(res->a1), - [res2] "=r"(res->a2), [res3] "=r"(res->a3) - : [function_id] "r"(function_id), [arg0] "r"(arg0), - [arg1] "r"(arg1), [arg2] "r"(arg2), [arg3] "r"(arg3), - [arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6) - : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7"); + __smccc_call(hvc, function_id, arg0, arg1, arg2, arg3, arg4, arg5, + arg6, res); +} + +void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, + uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, + uint64_t arg6, struct arm_smccc_res *res) +{ + __smccc_call(smc, function_id, arg0, arg1, arg2, arg3, arg4, arg5, + arg6, res); } void kvm_selftest_arch_init(void) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 8ec20ac33de0..298c4372fb1a 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -80,6 +80,11 @@ static bool get_module_param_bool(const char *module_name, const char *param) TEST_FAIL("Unrecognized value '%c' for boolean module param", value); } +bool get_kvm_param_bool(const char *param) +{ + return get_module_param_bool("kvm", param); +} + bool get_kvm_intel_param_bool(const char *param) { return get_module_param_bool("kvm_intel", param); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c39a4353ba19..d4a0b504b1e0 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -5,6 +5,7 @@ * Copyright (C) 2018, Google LLC. */ +#include "linux/bitmap.h" #include "test_util.h" #include "kvm_util.h" #include "processor.h" @@ -573,6 +574,21 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, DEFAULT_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA); + stack_vaddr += DEFAULT_STACK_PGS * getpagesize(); + + /* + * Align stack to match calling sequence requirements in section "The + * Stack Frame" of the System V ABI AMD64 Architecture Processor + * Supplement, which requires the value (%rsp + 8) to be a multiple of + * 16 when control is transferred to the function entry point. + * + * If this code is ever used to launch a vCPU with 32-bit entry point it + * may need to subtract 4 bytes instead of 8 bytes. + */ + TEST_ASSERT(IS_ALIGNED(stack_vaddr, PAGE_SIZE), + "__vm_vaddr_alloc() did not provide a page-aligned address"); + stack_vaddr -= 8; + vcpu = __vm_vcpu_add(vm, vcpu_id); vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); vcpu_setup(vm, vcpu); @@ -580,7 +596,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, /* Setup guest general purpose registers */ vcpu_regs_get(vcpu, ®s); regs.rflags = regs.rflags | 0x2; - regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()); + regs.rsp = stack_vaddr; regs.rip = (unsigned long) guest_code; vcpu_regs_set(vcpu, ®s); @@ -681,7 +697,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) return buffer.entry.data; } -void __vm_xsave_require_permission(int bit, const char *name) +void __vm_xsave_require_permission(uint64_t xfeature, const char *name) { int kvm_fd; u64 bitmask; @@ -689,12 +705,15 @@ void __vm_xsave_require_permission(int bit, const char *name) struct kvm_device_attr attr = { .group = 0, .attr = KVM_X86_XCOMP_GUEST_SUPP, - .addr = (unsigned long) &bitmask + .addr = (unsigned long) &bitmask, }; TEST_ASSERT(!kvm_supported_cpuid, "kvm_get_supported_cpuid() cannot be used before ARCH_REQ_XCOMP_GUEST_PERM"); + TEST_ASSERT(is_power_of_2(xfeature), + "Dynamic XFeatures must be enabled one at a time"); + kvm_fd = open_kvm_dev_path_or_exit(); rc = __kvm_ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr); close(kvm_fd); @@ -704,16 +723,16 @@ void __vm_xsave_require_permission(int bit, const char *name) TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc); - __TEST_REQUIRE(bitmask & (1ULL << bit), + __TEST_REQUIRE(bitmask & xfeature, "Required XSAVE feature '%s' not supported", name); - TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit)); + TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, ilog2(xfeature))); rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask); TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc); - TEST_ASSERT(bitmask & (1ULL << bit), - "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx", - bitmask); + TEST_ASSERT(bitmask & xfeature, + "'%s' (0x%lx) not permitted after prctl(ARCH_REQ_XCOMP_GUEST_PERM) permitted=0x%lx", + name, xfeature, bitmask); } void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid) @@ -954,6 +973,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu) vcpu_run_complete_io(vcpu); state = malloc(sizeof(*state) + msr_list->nmsrs * sizeof(state->msrs.entries[0])); + TEST_ASSERT(state, "-ENOMEM when allocating kvm state"); vcpu_events_get(vcpu, &state->events); vcpu_mp_state_get(vcpu, &state->mp_state); diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index b646cdb5055a..11329e5ff945 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -30,21 +30,12 @@ #define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE) /* Tile configuration associated: */ +#define PALETTE_TABLE_INDEX 1 #define MAX_TILES 16 #define RESERVED_BYTES 14 -#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 XSAVE_HDR_OFFSET 512 -struct xsave_data { - u8 area[XSAVE_SIZE]; -} __aligned(64); - struct tile_config { u8 palette_id; u8 start_row; @@ -68,24 +59,6 @@ struct xtile_info { static struct xtile_info xtile; -static inline u64 __xgetbv(u32 index) -{ - u32 eax, edx; - - asm volatile("xgetbv;" - : "=a" (eax), "=d" (edx) - : "c" (index)); - return eax + ((u64)edx << 32); -} - -static inline void __xsetbv(u32 index, u64 value) -{ - u32 eax = value; - u32 edx = value >> 32; - - asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); -} - static inline void __ldtilecfg(void *cfg) { asm volatile(".byte 0xc4,0xe2,0x78,0x49,0x00" @@ -103,27 +76,16 @@ static inline void __tilerelease(void) asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::); } -static inline void __xsavec(struct xsave_data *data, uint64_t rfbm) +static inline void __xsavec(struct xstate *xstate, uint64_t rfbm) { uint32_t rfbm_lo = rfbm; uint32_t rfbm_hi = rfbm >> 32; asm volatile("xsavec (%%rdi)" - : : "D" (data), "a" (rfbm_lo), "d" (rfbm_hi) + : : "D" (xstate), "a" (rfbm_lo), "d" (rfbm_hi) : "memory"); } -static inline void check_cpuid_xsave(void) -{ - GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE)); - GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE)); -} - -static bool check_xsave_supports_xtile(void) -{ - return __xgetbv(0) & XFEATURE_MASK_XTILE; -} - static void check_xtile_info(void) { GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_XSTATE_MAX_SIZE_XCR0)); @@ -135,6 +97,10 @@ static void check_xtile_info(void) GUEST_ASSERT(xtile.xsave_size == 8192); GUEST_ASSERT(sizeof(struct tile_data) >= xtile.xsave_size); + GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_AMX_MAX_PALETTE_TABLES)); + GUEST_ASSERT(this_cpu_property(X86_PROPERTY_AMX_MAX_PALETTE_TABLES) >= + PALETTE_TABLE_INDEX); + GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_AMX_NR_TILE_REGS)); xtile.max_names = this_cpu_property(X86_PROPERTY_AMX_NR_TILE_REGS); GUEST_ASSERT(xtile.max_names == 8); @@ -158,37 +124,29 @@ static void set_tilecfg(struct tile_config *cfg) } } -static void set_xstatebv(void *data, uint64_t bv) -{ - *(uint64_t *)(data + XSAVE_HDR_OFFSET) = bv; -} - -static u64 get_xstatebv(void *data) -{ - return *(u64 *)(data + XSAVE_HDR_OFFSET); -} - static void init_regs(void) { uint64_t cr4, xcr0; + GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE)); + /* turn on CR4.OSXSAVE */ cr4 = get_cr4(); cr4 |= X86_CR4_OSXSAVE; set_cr4(cr4); + GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE)); - xcr0 = __xgetbv(0); + xcr0 = xgetbv(0); xcr0 |= XFEATURE_MASK_XTILE; - __xsetbv(0x0, xcr0); + xsetbv(0x0, xcr0); + GUEST_ASSERT((xgetbv(0) & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE); } static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, struct tile_data *tiledata, - struct xsave_data *xsave_data) + struct xstate *xstate) { init_regs(); - check_cpuid_xsave(); - check_xsave_supports_xtile(); check_xtile_info(); GUEST_SYNC(1); @@ -204,15 +162,29 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_SYNC(4); __tilerelease(); GUEST_SYNC(5); - /* bit 18 not in the XCOMP_BV after xsavec() */ - set_xstatebv(xsave_data, XFEATURE_MASK_XTILEDATA); - __xsavec(xsave_data, XFEATURE_MASK_XTILEDATA); - GUEST_ASSERT((get_xstatebv(xsave_data) & XFEATURE_MASK_XTILEDATA) == 0); + /* + * After XSAVEC, XTILEDATA is cleared in the xstate_bv but is set in + * the xcomp_bv. + */ + xstate->header.xstate_bv = XFEATURE_MASK_XTILE_DATA; + __xsavec(xstate, XFEATURE_MASK_XTILE_DATA); + GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); + GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA); /* xfd=0x40000, disable amx tiledata */ - wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA); + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); + + /* + * XTILEDATA is cleared in xstate_bv but set in xcomp_bv, this property + * remains the same even when amx tiledata is disabled by IA32_XFD. + */ + xstate->header.xstate_bv = XFEATURE_MASK_XTILE_DATA; + __xsavec(xstate, XFEATURE_MASK_XTILE_DATA); + GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); + GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA)); + GUEST_SYNC(6); - GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); /* Trigger #NM exception */ @@ -224,11 +196,14 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, void guest_nm_handler(struct ex_regs *regs) { - /* Check if #NM is triggered by XFEATURE_MASK_XTILEDATA */ + /* Check if #NM is triggered by XFEATURE_MASK_XTILE_DATA */ GUEST_SYNC(7); - GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(!(get_cr0() & X86_CR0_TS)); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); GUEST_SYNC(8); - GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); /* Clear xfd_err */ wrmsr(MSR_IA32_XFD_ERR, 0); /* xfd=0, enable amx */ @@ -243,7 +218,7 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; struct kvm_x86_state *state; int xsave_restore_size; - vm_vaddr_t amx_cfg, tiledata, xsavedata; + vm_vaddr_t amx_cfg, tiledata, xstate; struct ucall uc; u32 amx_offset; int stage, ret; @@ -252,13 +227,14 @@ int main(int argc, char *argv[]) * Note, all off-by-default features must be enabled before anything * caches KVM_GET_SUPPORTED_CPUID, e.g. before using kvm_cpu_has(). */ - vm_xsave_require_permission(XSTATE_XTILE_DATA_BIT); + vm_xsave_require_permission(XFEATURE_MASK_XTILE_DATA); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XFD)); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_AMX_TILE)); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILECFG)); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILEDATA)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILEDATA_XFD)); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); @@ -282,10 +258,10 @@ int main(int argc, char *argv[]) tiledata = vm_vaddr_alloc_pages(vm, 2); memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize()); - /* xsave data for guest_code */ - xsavedata = vm_vaddr_alloc_pages(vm, 3); - memset(addr_gva2hva(vm, xsavedata), 0, 3 * getpagesize()); - vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xsavedata); + /* XSAVE state for guest_code */ + xstate = vm_vaddr_alloc_pages(vm, DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); + memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); + vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate); for (stage = 1; ; stage++) { vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 2feef25ba691..40507ed9fe8a 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -54,6 +54,21 @@ #define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0) + +/* + * "Retired instructions", from Processor Programming Reference + * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, + * Preliminary Processor Programming Reference (PPR) for AMD Family + * 17h Model 31h, Revision B0 Processors, and Preliminary Processor + * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision + * B1 Processors Volume 1 of 2. + * --- and --- + * "Instructions retired", from the Intel SDM, volume 3, + * "Pre-defined Architectural Performance Events." + */ + +#define INST_RETIRED EVENT(0xc0, 0) + /* * This event list comprises Intel's eight architectural events plus * AMD's "retired branch instructions" for Zen[123] (and possibly @@ -61,7 +76,7 @@ */ static const uint64_t event_list[] = { EVENT(0x3c, 0), - EVENT(0xc0, 0), + INST_RETIRED, EVENT(0x3c, 1), EVENT(0x2e, 0x4f), EVENT(0x2e, 0x41), @@ -71,13 +86,21 @@ static const uint64_t event_list[] = { AMD_ZEN_BR_RETIRED, }; +struct { + uint64_t loads; + uint64_t stores; + uint64_t loads_stores; + uint64_t branches_retired; + uint64_t instructions_retired; +} pmc_results; + /* * If we encounter a #GP during the guest PMU sanity check, then the guest * PMU is not functional. Inform the hypervisor via GUEST_SYNC(0). */ static void guest_gp_handler(struct ex_regs *regs) { - GUEST_SYNC(0); + GUEST_SYNC(-EFAULT); } /* @@ -92,12 +115,23 @@ static void check_msr(uint32_t msr, uint64_t bits_to_flip) wrmsr(msr, v); if (rdmsr(msr) != v) - GUEST_SYNC(0); + GUEST_SYNC(-EIO); v ^= bits_to_flip; wrmsr(msr, v); if (rdmsr(msr) != v) - GUEST_SYNC(0); + GUEST_SYNC(-EIO); +} + +static void run_and_measure_loop(uint32_t msr_base) +{ + const uint64_t branches_retired = rdmsr(msr_base + 0); + const uint64_t insn_retired = rdmsr(msr_base + 1); + + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + + pmc_results.branches_retired = rdmsr(msr_base + 0) - branches_retired; + pmc_results.instructions_retired = rdmsr(msr_base + 1) - insn_retired; } static void intel_guest_code(void) @@ -105,19 +139,18 @@ static void intel_guest_code(void) check_msr(MSR_CORE_PERF_GLOBAL_CTRL, 1); check_msr(MSR_P6_EVNTSEL0, 0xffff); check_msr(MSR_IA32_PMC0, 0xffff); - GUEST_SYNC(1); + GUEST_SYNC(0); for (;;) { - uint64_t br0, br1; - wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED); - wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 1); - br0 = rdmsr(MSR_IA32_PMC0); - __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); - br1 = rdmsr(MSR_IA32_PMC0); - GUEST_SYNC(br1 - br0); + wrmsr(MSR_P6_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x3); + + run_and_measure_loop(MSR_IA32_PMC0); + GUEST_SYNC(0); } } @@ -130,18 +163,17 @@ static void amd_guest_code(void) { check_msr(MSR_K7_EVNTSEL0, 0xffff); check_msr(MSR_K7_PERFCTR0, 0xffff); - GUEST_SYNC(1); + GUEST_SYNC(0); for (;;) { - uint64_t br0, br1; - wrmsr(MSR_K7_EVNTSEL0, 0); wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED); - br0 = rdmsr(MSR_K7_PERFCTR0); - __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); - br1 = rdmsr(MSR_K7_PERFCTR0); - GUEST_SYNC(br1 - br0); + wrmsr(MSR_K7_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED); + + run_and_measure_loop(MSR_K7_PERFCTR0); + GUEST_SYNC(0); } } @@ -161,6 +193,19 @@ static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) return uc.args[1]; } +static void run_vcpu_and_sync_pmc_results(struct kvm_vcpu *vcpu) +{ + uint64_t r; + + memset(&pmc_results, 0, sizeof(pmc_results)); + sync_global_to_guest(vcpu->vm, pmc_results); + + r = run_vcpu_to_sync(vcpu); + TEST_ASSERT(!r, "Unexpected sync value: 0x%lx", r); + + sync_global_from_guest(vcpu->vm, pmc_results); +} + /* * In a nested environment or if the vPMU is disabled, the guest PMU * might not work as architected (accessing the PMU MSRs may raise @@ -171,13 +216,13 @@ static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) */ static bool sanity_check_pmu(struct kvm_vcpu *vcpu) { - bool success; + uint64_t r; vm_install_exception_handler(vcpu->vm, GP_VECTOR, guest_gp_handler); - success = run_vcpu_to_sync(vcpu); + r = run_vcpu_to_sync(vcpu); vm_install_exception_handler(vcpu->vm, GP_VECTOR, NULL); - return success; + return !r; } static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents) @@ -237,91 +282,101 @@ static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, return f; } +#define ASSERT_PMC_COUNTING_INSTRUCTIONS() \ +do { \ + uint64_t br = pmc_results.branches_retired; \ + uint64_t ir = pmc_results.instructions_retired; \ + \ + if (br && br != NUM_BRANCHES) \ + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", \ + __func__, br, NUM_BRANCHES); \ + TEST_ASSERT(br, "%s: Branch instructions retired = %lu (expected > 0)", \ + __func__, br); \ + TEST_ASSERT(ir, "%s: Instructions retired = %lu (expected > 0)", \ + __func__, ir); \ +} while (0) + +#define ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS() \ +do { \ + uint64_t br = pmc_results.branches_retired; \ + uint64_t ir = pmc_results.instructions_retired; \ + \ + TEST_ASSERT(!br, "%s: Branch instructions retired = %lu (expected 0)", \ + __func__, br); \ + TEST_ASSERT(!ir, "%s: Instructions retired = %lu (expected 0)", \ + __func__, ir); \ +} while (0) + static void test_without_filter(struct kvm_vcpu *vcpu) { - uint64_t count = run_vcpu_to_sync(vcpu); + run_vcpu_and_sync_pmc_results(vcpu); - if (count != NUM_BRANCHES) - pr_info("%s: Branch instructions retired = %lu (expected %u)\n", - __func__, count, NUM_BRANCHES); - TEST_ASSERT(count, "Allowed PMU event is not counting"); + ASSERT_PMC_COUNTING_INSTRUCTIONS(); } -static uint64_t test_with_filter(struct kvm_vcpu *vcpu, - struct kvm_pmu_event_filter *f) +static void test_with_filter(struct kvm_vcpu *vcpu, + struct kvm_pmu_event_filter *f) { vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); - return run_vcpu_to_sync(vcpu); + run_vcpu_and_sync_pmc_results(vcpu); } static void test_amd_deny_list(struct kvm_vcpu *vcpu) { uint64_t event = EVENT(0x1C2, 0); struct kvm_pmu_event_filter *f; - uint64_t count; f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY, 0); - count = test_with_filter(vcpu, f); - + test_with_filter(vcpu, f); free(f); - if (count != NUM_BRANCHES) - pr_info("%s: Branch instructions retired = %lu (expected %u)\n", - __func__, count, NUM_BRANCHES); - TEST_ASSERT(count, "Allowed PMU event is not counting"); + + ASSERT_PMC_COUNTING_INSTRUCTIONS(); } static void test_member_deny_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); - uint64_t count = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - if (count) - pr_info("%s: Branch instructions retired = %lu (expected 0)\n", - __func__, count); - TEST_ASSERT(!count, "Disallowed PMU Event is counting"); + + ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(); } static void test_member_allow_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); - uint64_t count = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - if (count != NUM_BRANCHES) - pr_info("%s: Branch instructions retired = %lu (expected %u)\n", - __func__, count, NUM_BRANCHES); - TEST_ASSERT(count, "Allowed PMU event is not counting"); + + ASSERT_PMC_COUNTING_INSTRUCTIONS(); } static void test_not_member_deny_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); - uint64_t count; + remove_event(f, INST_RETIRED); remove_event(f, INTEL_BR_RETIRED); remove_event(f, AMD_ZEN_BR_RETIRED); - count = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - if (count != NUM_BRANCHES) - pr_info("%s: Branch instructions retired = %lu (expected %u)\n", - __func__, count, NUM_BRANCHES); - TEST_ASSERT(count, "Allowed PMU event is not counting"); + + ASSERT_PMC_COUNTING_INSTRUCTIONS(); } static void test_not_member_allow_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); - uint64_t count; + remove_event(f, INST_RETIRED); remove_event(f, INTEL_BR_RETIRED); remove_event(f, AMD_ZEN_BR_RETIRED); - count = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - if (count) - pr_info("%s: Branch instructions retired = %lu (expected 0)\n", - __func__, count); - TEST_ASSERT(!count, "Disallowed PMU Event is counting"); + + ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(); } /* @@ -450,51 +505,30 @@ static bool supports_event_mem_inst_retired(void) #define EXCLUDE_MASKED_ENTRY(event_select, mask, match) \ KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, true) -struct perf_counter { - union { - uint64_t raw; - struct { - uint64_t loads:22; - uint64_t stores:22; - uint64_t loads_stores:20; - }; - }; -}; - -static uint64_t masked_events_guest_test(uint32_t msr_base) +static void masked_events_guest_test(uint32_t msr_base) { - uint64_t ld0, ld1, st0, st1, ls0, ls1; - struct perf_counter c; - int val; - /* - * The acutal value of the counters don't determine the outcome of + * The actual value of the counters don't determine the outcome of * the test. Only that they are zero or non-zero. */ - ld0 = rdmsr(msr_base + 0); - st0 = rdmsr(msr_base + 1); - ls0 = rdmsr(msr_base + 2); + const uint64_t loads = rdmsr(msr_base + 0); + const uint64_t stores = rdmsr(msr_base + 1); + const uint64_t loads_stores = rdmsr(msr_base + 2); + int val; + __asm__ __volatile__("movl $0, %[v];" "movl %[v], %%eax;" "incl %[v];" : [v]"+m"(val) :: "eax"); - ld1 = rdmsr(msr_base + 0); - st1 = rdmsr(msr_base + 1); - ls1 = rdmsr(msr_base + 2); - - c.loads = ld1 - ld0; - c.stores = st1 - st0; - c.loads_stores = ls1 - ls0; - - return c.raw; + pmc_results.loads = rdmsr(msr_base + 0) - loads; + pmc_results.stores = rdmsr(msr_base + 1) - stores; + pmc_results.loads_stores = rdmsr(msr_base + 2) - loads_stores; } static void intel_masked_events_guest_code(void) { - uint64_t r; - for (;;) { wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); @@ -507,16 +541,13 @@ static void intel_masked_events_guest_code(void) wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x7); - r = masked_events_guest_test(MSR_IA32_PMC0); - - GUEST_SYNC(r); + masked_events_guest_test(MSR_IA32_PMC0); + GUEST_SYNC(0); } } static void amd_masked_events_guest_code(void) { - uint64_t r; - for (;;) { wrmsr(MSR_K7_EVNTSEL0, 0); wrmsr(MSR_K7_EVNTSEL1, 0); @@ -529,26 +560,22 @@ static void amd_masked_events_guest_code(void) wrmsr(MSR_K7_EVNTSEL2, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_LOAD_STORE); - r = masked_events_guest_test(MSR_K7_PERFCTR0); - - GUEST_SYNC(r); + masked_events_guest_test(MSR_K7_PERFCTR0); + GUEST_SYNC(0); } } -static struct perf_counter run_masked_events_test(struct kvm_vcpu *vcpu, - const uint64_t masked_events[], - const int nmasked_events) +static void run_masked_events_test(struct kvm_vcpu *vcpu, + const uint64_t masked_events[], + const int nmasked_events) { struct kvm_pmu_event_filter *f; - struct perf_counter r; f = create_pmu_event_filter(masked_events, nmasked_events, KVM_PMU_EVENT_ALLOW, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); - r.raw = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - - return r; } /* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */ @@ -673,7 +700,6 @@ static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, int nevents) { int ntests = ARRAY_SIZE(test_cases); - struct perf_counter c; int i, n; for (i = 0; i < ntests; i++) { @@ -685,13 +711,15 @@ static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, n = append_test_events(test, events, nevents); - c = run_masked_events_test(vcpu, events, n); - TEST_ASSERT(bool_eq(c.loads, test->flags & ALLOW_LOADS) && - bool_eq(c.stores, test->flags & ALLOW_STORES) && - bool_eq(c.loads_stores, + run_masked_events_test(vcpu, events, n); + + TEST_ASSERT(bool_eq(pmc_results.loads, test->flags & ALLOW_LOADS) && + bool_eq(pmc_results.stores, test->flags & ALLOW_STORES) && + bool_eq(pmc_results.loads_stores, test->flags & ALLOW_LOADS_STORES), - "%s loads: %u, stores: %u, loads + stores: %u", - test->msg, c.loads, c.stores, c.loads_stores); + "%s loads: %lu, stores: %lu, loads + stores: %lu", + test->msg, pmc_results.loads, pmc_results.stores, + pmc_results.loads_stores); } } @@ -764,6 +792,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu, *vcpu2 = NULL; struct kvm_vm *vm; + TEST_REQUIRE(get_kvm_param_bool("enable_pmu")); TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_MASKED_EVENTS)); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c index d427eb146bc5..fa03c8d1ce4e 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c @@ -126,12 +126,16 @@ static void stable_tsc_check_supported(void) goto skip_test; if (fgets(buf, sizeof(buf), fp) == NULL) - goto skip_test; + goto close_fp; if (strncmp(buf, "tsc", sizeof(buf))) - goto skip_test; + goto close_fp; + fclose(fp); return; + +close_fp: + fclose(fp); skip_test: print_skip("Kernel does not use TSC clocksource - assuming that host TSC is not stable"); exit(KSFT_SKIP); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index c280ba1e6572..4c90f76930f9 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -14,12 +14,11 @@ #define _GNU_SOURCE /* for program_invocation_short_name */ #include <sys/ioctl.h> +#include <linux/bitmap.h> + #include "kvm_util.h" #include "vmx.h" -#define PMU_CAP_FW_WRITES (1ULL << 13) -#define PMU_CAP_LBR_FMT 0x3f - union perf_capabilities { struct { u64 lbr_format:6; @@ -36,59 +35,221 @@ union perf_capabilities { u64 capabilities; }; -static void guest_code(void) +/* + * The LBR format and most PEBS features are immutable, all other features are + * fungible (if supported by the host and KVM). + */ +static const union perf_capabilities immutable_caps = { + .lbr_format = -1, + .pebs_trap = 1, + .pebs_arch_reg = 1, + .pebs_format = -1, + .pebs_baseline = 1, +}; + +static const union perf_capabilities format_caps = { + .lbr_format = -1, + .pebs_format = -1, +}; + +static void guest_code(uint64_t current_val) { - wrmsr(MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); + uint8_t vector; + int i; + + vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, current_val); + GUEST_ASSERT_2(vector == GP_VECTOR, current_val, vector); + + vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, 0); + GUEST_ASSERT_2(vector == GP_VECTOR, 0, vector); + + for (i = 0; i < 64; i++) { + vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, + current_val ^ BIT_ULL(i)); + GUEST_ASSERT_2(vector == GP_VECTOR, + current_val ^ BIT_ULL(i), vector); + } + + GUEST_DONE(); } -int main(int argc, char *argv[]) +/* + * Verify that guest WRMSRs to PERF_CAPABILITIES #GP regardless of the value + * written, that the guest always sees the userspace controlled value, and that + * PERF_CAPABILITIES is immutable after KVM_RUN. + */ +static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap) { - struct kvm_vm *vm; struct kvm_vcpu *vcpu; - int ret; - union perf_capabilities host_cap; - uint64_t val; + struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, guest_code); + struct ucall uc; + int r, i; - host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); - host_cap.capabilities &= (PMU_CAP_FW_WRITES | PMU_CAP_LBR_FMT); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); - /* Create VM */ - vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); + vcpu_args_set(vcpu, 1, host_cap.capabilities); + vcpu_run(vcpu); - TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION)); - TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0); + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT_2(uc, "val = 0x%lx, vector = %lu"); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } - /* testcase 1, set capabilities when we have PDCM bit */ - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), host_cap.capabilities); - /* check capabilities can be retrieved with KVM_GET_MSR */ - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - /* check whatever we write with KVM_SET_MSR is _not_ modified */ - vcpu_run(vcpu); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); + TEST_ASSERT(!r, "Post-KVM_RUN write '0' didn't fail"); + + for (i = 0; i < 64; i++) { + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, + host_cap.capabilities ^ BIT_ULL(i)); + TEST_ASSERT(!r, "Post-KVM_RUN write '0x%llx'didn't fail", + host_cap.capabilities ^ BIT_ULL(i)); + } + + kvm_vm_free(vm); +} + +/* + * Verify KVM allows writing PERF_CAPABILITIES with all KVM-supported features + * enabled, as well as '0' (to disable all features). + */ +static void test_basic_perf_capabilities(union perf_capabilities host_cap) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); - /* testcase 2, check valid LBR formats are accepted */ vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), 0); + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); + + kvm_vm_free(vm); +} - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.lbr_format); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), (u64)host_cap.lbr_format); +static void test_fungible_perf_capabilities(union perf_capabilities host_cap) +{ + const uint64_t fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities; + + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); + int bit; + + for_each_set_bit(bit, &fungible_caps, 64) { + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, BIT_ULL(bit)); + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, + host_cap.capabilities & ~BIT_ULL(bit)); + } + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); + + kvm_vm_free(vm); +} + +/* + * Verify KVM rejects attempts to set unsupported and/or immutable features in + * PERF_CAPABILITIES. Note, LBR format and PEBS format need to be validated + * separately as they are multi-bit values, e.g. toggling or setting a single + * bit can generate a false positive without dedicated safeguards. + */ +static void test_immutable_perf_capabilities(union perf_capabilities host_cap) +{ + const uint64_t reserved_caps = (~host_cap.capabilities | + immutable_caps.capabilities) & + ~format_caps.capabilities; + + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); + union perf_capabilities val = host_cap; + int r, bit; + + for_each_set_bit(bit, &reserved_caps, 64) { + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, + host_cap.capabilities ^ BIT_ULL(bit)); + TEST_ASSERT(!r, "%s immutable feature 0x%llx (bit %d) didn't fail", + host_cap.capabilities & BIT_ULL(bit) ? "Setting" : "Clearing", + BIT_ULL(bit), bit); + } /* - * Testcase 3, check that an "invalid" LBR format is rejected. Only an - * exact match of the host's format (and 0/disabled) is allowed. + * KVM only supports the host's native LBR format, as well as '0' (to + * disable LBR support). Verify KVM rejects all other LBR formats. */ - for (val = 1; val <= PMU_CAP_LBR_FMT; val++) { - if (val == (host_cap.capabilities & PMU_CAP_LBR_FMT)) + for (val.lbr_format = 1; val.lbr_format; val.lbr_format++) { + if (val.lbr_format == host_cap.lbr_format) continue; - ret = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val); - TEST_ASSERT(!ret, "Bad LBR FMT = 0x%lx didn't fail", val); + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val.capabilities); + TEST_ASSERT(!r, "Bad LBR FMT = 0x%x didn't fail, host = 0x%x", + val.lbr_format, host_cap.lbr_format); } - printf("Completed perf capability tests.\n"); + /* Ditto for the PEBS format. */ + for (val.pebs_format = 1; val.pebs_format; val.pebs_format++) { + if (val.pebs_format == host_cap.pebs_format) + continue; + + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val.capabilities); + TEST_ASSERT(!r, "Bad PEBS FMT = 0x%x didn't fail, host = 0x%x", + val.pebs_format, host_cap.pebs_format); + } + + kvm_vm_free(vm); +} + +/* + * Test that LBR MSRs are writable when LBRs are enabled, and then verify that + * disabling the vPMU via CPUID also disables LBR support. Set bits 2:0 of + * LBR_TOS as those bits are writable across all uarch implementations (arch + * LBRs will need to poke a different MSR). + */ +static void test_lbr_perf_capabilities(union perf_capabilities host_cap) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int r; + + if (!host_cap.lbr_format) + return; + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); + vcpu_set_msr(vcpu, MSR_LBR_TOS, 7); + + vcpu_clear_cpuid_entry(vcpu, X86_PROPERTY_PMU_VERSION.function); + + r = _vcpu_set_msr(vcpu, MSR_LBR_TOS, 7); + TEST_ASSERT(!r, "Writing LBR_TOS should fail after disabling vPMU"); + kvm_vm_free(vm); } + +int main(int argc, char *argv[]) +{ + union perf_capabilities host_cap; + + TEST_REQUIRE(get_kvm_param_bool("enable_pmu")); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); + + TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION)); + TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0); + + host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); + + TEST_ASSERT(host_cap.full_width_write, + "Full-width writes should always be supported"); + + test_basic_perf_capabilities(host_cap); + test_fungible_perf_capabilities(host_cap); + test_immutable_perf_capabilities(host_cap); + test_guest_wrmsr_perf_capabilities(host_cap); + test_lbr_perf_capabilities(host_cap); +} diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c new file mode 100644 index 000000000000..905bd5ae4431 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * XCR0 cpuid test + * + * Copyright (C) 2022, Google LLC. + */ + +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" + +/* + * Assert that architectural dependency rules are satisfied, e.g. that AVX is + * supported if and only if SSE is supported. + */ +#define ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, xfeatures, dependencies) \ +do { \ + uint64_t __supported = (supported_xcr0) & ((xfeatures) | (dependencies)); \ + \ + GUEST_ASSERT_3((__supported & (xfeatures)) != (xfeatures) || \ + __supported == ((xfeatures) | (dependencies)), \ + __supported, (xfeatures), (dependencies)); \ +} while (0) + +/* + * Assert that KVM reports a sane, usable as-is XCR0. Architecturally, a CPU + * isn't strictly required to _support_ all XFeatures related to a feature, but + * at the same time XSETBV will #GP if bundled XFeatures aren't enabled and + * disabled coherently. E.g. a CPU can technically enumerate supported for + * XTILE_CFG but not XTILE_DATA, but attempting to enable XTILE_CFG without + * XTILE_DATA will #GP. + */ +#define ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, xfeatures) \ +do { \ + uint64_t __supported = (supported_xcr0) & (xfeatures); \ + \ + GUEST_ASSERT_2(!__supported || __supported == (xfeatures), \ + __supported, (xfeatures)); \ +} while (0) + +static void guest_code(void) +{ + uint64_t xcr0_reset; + uint64_t supported_xcr0; + int i, vector; + + set_cr4(get_cr4() | X86_CR4_OSXSAVE); + + xcr0_reset = xgetbv(0); + supported_xcr0 = this_cpu_supported_xcr0(); + + GUEST_ASSERT(xcr0_reset == XFEATURE_MASK_FP); + + /* Check AVX */ + ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, + XFEATURE_MASK_YMM, + XFEATURE_MASK_SSE); + + /* Check MPX */ + ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, + XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); + + /* Check AVX-512 */ + ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, + XFEATURE_MASK_AVX512, + XFEATURE_MASK_SSE | XFEATURE_MASK_YMM); + ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, + XFEATURE_MASK_AVX512); + + /* Check AMX */ + ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, + XFEATURE_MASK_XTILE); + + vector = xsetbv_safe(0, supported_xcr0); + GUEST_ASSERT_2(!vector, supported_xcr0, vector); + + for (i = 0; i < 64; i++) { + if (supported_xcr0 & BIT_ULL(i)) + continue; + + vector = xsetbv_safe(0, supported_xcr0 | BIT_ULL(i)); + GUEST_ASSERT_3(vector == GP_VECTOR, supported_xcr0, vector, BIT_ULL(i)); + } + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + while (1) { + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT_3(uc, "0x%lx 0x%lx 0x%lx"); + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index 7bc9fc17c9f0..26853badae70 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -91,9 +91,10 @@ static int ksm_merge(void) return 0; } -static char *mmap_and_merge_range(char val, unsigned long size) +static char *mmap_and_merge_range(char val, unsigned long size, bool use_prctl) { char *map; + int ret; map = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0); @@ -110,7 +111,17 @@ static char *mmap_and_merge_range(char val, unsigned long size) /* Make sure each page contains the same values to merge them. */ memset(map, val, size); - if (madvise(map, size, MADV_MERGEABLE)) { + + if (use_prctl) { + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) { + ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + goto unmap; + } else if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + goto unmap; + } + } else if (madvise(map, size, MADV_MERGEABLE)) { ksft_test_result_fail("MADV_MERGEABLE failed\n"); goto unmap; } @@ -133,7 +144,7 @@ static void test_unmerge(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size); + map = mmap_and_merge_range(0xcf, size, false); if (map == MAP_FAILED) return; @@ -155,7 +166,7 @@ static void test_unmerge_discarded(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size); + map = mmap_and_merge_range(0xcf, size, false); if (map == MAP_FAILED) return; @@ -187,7 +198,7 @@ static void test_unmerge_uffd_wp(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size); + map = mmap_and_merge_range(0xcf, size, false); if (map == MAP_FAILED) return; @@ -323,9 +334,31 @@ static void test_prctl_fork(void) ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n"); } +static void test_prctl_unmerge(void) +{ + const unsigned int size = 2 * MiB; + char *map; + + ksft_print_msg("[RUN] %s\n", __func__); + + map = mmap_and_merge_range(0xcf, size, true); + if (map == MAP_FAILED) + return; + + if (prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0)) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n"); + goto unmap; + } + + ksft_test_result(!range_maps_duplicates(map, size), + "Pages were unmerged\n"); +unmap: + munmap(map, size); +} + int main(int argc, char **argv) { - unsigned int tests = 4; + unsigned int tests = 5; int err; #ifdef __NR_userfaultfd @@ -355,6 +388,7 @@ int main(int argc, char **argv) test_prctl(); test_prctl_fork(); + test_prctl_unmerge(); err = ksft_get_fail_cnt(); if (err) diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 95f403a0c46d..0381c34fdd56 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -98,7 +98,7 @@ int tracing_root_ok(void) void tracing_on(void) { #if CONTROL_TRACING > 0 -#define TRACEDIR "/sys/kernel/debug/tracing" +#define TRACEDIR "/sys/kernel/tracing" char pidstr[32]; if (!tracing_root_ok()) @@ -124,7 +124,7 @@ void tracing_off(void) #if CONTROL_TRACING > 0 if (!tracing_root_ok()) return; - cat_into_file("0", "/sys/kernel/debug/tracing/tracing_on"); + cat_into_file("0", "/sys/kernel/tracing/tracing_on"); #endif } diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 6ba95cd19e42..ae2bfc0d822f 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -45,28 +45,28 @@ $(SUB_DIRS): include ../lib.mk override define RUN_TESTS - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; endef override define INSTALL_RULE - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\ done; endef override define EMIT_TESTS - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\ done; endef override define CLEAN - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \ done; diff --git a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h index 003e1b3d9300..a89f1fbf86ec 100644 --- a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h +++ b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h @@ -27,6 +27,7 @@ #define _GLOBAL_TOC(A) _GLOBAL(A) #define _GLOBAL_TOC_KASAN(A) _GLOBAL(A) #define _GLOBAL_KASAN(A) _GLOBAL(A) +#define CFUNC(name) name #define PPC_MTOCRF(A, B) mtocrf A, B diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile index 845db6273a1b..9289d5febe1e 100644 --- a/tools/testing/selftests/powerpc/dscr/Makefile +++ b/tools/testing/selftests/powerpc/dscr/Makefile @@ -3,11 +3,10 @@ TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test \ dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test \ dscr_sysfs_thread_test -TEST_FILES := settings - top_srcdir = ../../../../.. include ../../lib.mk $(OUTPUT)/dscr_default_test: LDLIBS += -lpthread +$(OUTPUT)/dscr_explicit_test: LDLIBS += -lpthread $(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/dscr/dscr.h b/tools/testing/selftests/powerpc/dscr/dscr.h index 2c54998d4715..b281659071e8 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr.h +++ b/tools/testing/selftests/powerpc/dscr/dscr.h @@ -86,8 +86,4 @@ void set_default_dscr(unsigned long val) } } -double uniform_deviate(int seed) -{ - return seed * (1.0 / (RAND_MAX + 1.0)); -} #endif /* _SELFTESTS_POWERPC_DSCR_DSCR_H */ diff --git a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c index e76611e608af..60ab02525b79 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c @@ -9,118 +9,161 @@ * Copyright 2012, Anton Blanchard, IBM Corporation. * Copyright 2015, Anshuman Khandual, IBM Corporation. */ -#include "dscr.h" - -static unsigned long dscr; /* System DSCR default */ -static unsigned long sequence; -static unsigned long result[THREADS]; - -static void *do_test(void *in) -{ - unsigned long thread = (unsigned long)in; - unsigned long i; - for (i = 0; i < COUNT; i++) { - unsigned long d, cur_dscr, cur_dscr_usr; - unsigned long s1, s2; +#define _GNU_SOURCE - s1 = READ_ONCE(sequence); - if (s1 & 1) - continue; - rmb(); +#include "dscr.h" - d = dscr; - cur_dscr = get_dscr(); - cur_dscr_usr = get_dscr_usr(); +#include <pthread.h> +#include <semaphore.h> +#include <unistd.h> - rmb(); - s2 = sequence; +static void *dscr_default_lockstep_writer(void *arg) +{ + sem_t *reader_sem = (sem_t *)arg; + sem_t *writer_sem = (sem_t *)arg + 1; + unsigned long expected_dscr = 0; - if (s1 != s2) - continue; + for (int i = 0; i < COUNT; i++) { + FAIL_IF_EXIT(sem_wait(writer_sem)); - if (cur_dscr != d) { - fprintf(stderr, "thread %ld kernel DSCR should be %ld " - "but is %ld\n", thread, d, cur_dscr); - result[thread] = 1; - pthread_exit(&result[thread]); - } + set_default_dscr(expected_dscr); + expected_dscr = (expected_dscr + 1) % DSCR_MAX; - if (cur_dscr_usr != d) { - fprintf(stderr, "thread %ld user DSCR should be %ld " - "but is %ld\n", thread, d, cur_dscr_usr); - result[thread] = 1; - pthread_exit(&result[thread]); - } + FAIL_IF_EXIT(sem_post(reader_sem)); } - result[thread] = 0; - pthread_exit(&result[thread]); + + return NULL; } -int dscr_default(void) +int dscr_default_lockstep_test(void) { - pthread_t threads[THREADS]; - unsigned long i, *status[THREADS]; - unsigned long orig_dscr_default; + pthread_t writer; + sem_t rw_semaphores[2]; + sem_t *reader_sem = &rw_semaphores[0]; + sem_t *writer_sem = &rw_semaphores[1]; + unsigned long expected_dscr = 0; SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); - orig_dscr_default = get_default_dscr(); + FAIL_IF(sem_init(reader_sem, 0, 0)); + FAIL_IF(sem_init(writer_sem, 0, 1)); /* writer starts first */ + FAIL_IF(bind_to_cpu(BIND_CPU_ANY) < 0); + FAIL_IF(pthread_create(&writer, NULL, dscr_default_lockstep_writer, (void *)rw_semaphores)); - /* Initial DSCR default */ - dscr = 1; - set_default_dscr(dscr); + for (int i = 0; i < COUNT ; i++) { + FAIL_IF(sem_wait(reader_sem)); - /* Spawn all testing threads */ - for (i = 0; i < THREADS; i++) { - if (pthread_create(&threads[i], NULL, do_test, (void *)i)) { - perror("pthread_create() failed"); - goto fail; - } - } + FAIL_IF(get_dscr() != expected_dscr); + FAIL_IF(get_dscr_usr() != expected_dscr); - srand(getpid()); + expected_dscr = (expected_dscr + 1) % DSCR_MAX; - /* Keep changing the DSCR default */ - for (i = 0; i < COUNT; i++) { - double ret = uniform_deviate(rand()); + FAIL_IF(sem_post(writer_sem)); + } - if (ret < 0.0001) { - sequence++; - wmb(); + FAIL_IF(pthread_join(writer, NULL)); + FAIL_IF(sem_destroy(reader_sem)); + FAIL_IF(sem_destroy(writer_sem)); - dscr++; - if (dscr > DSCR_MAX) - dscr = 0; + return 0; +} - set_default_dscr(dscr); +struct random_thread_args { + pthread_t thread_id; + unsigned long *expected_system_dscr; + pthread_rwlock_t *rw_lock; + pthread_barrier_t *barrier; +}; - wmb(); - sequence++; +static void *dscr_default_random_thread(void *in) +{ + struct random_thread_args *args = (struct random_thread_args *)in; + unsigned long *expected_dscr_p = args->expected_system_dscr; + pthread_rwlock_t *rw_lock = args->rw_lock; + int err; + + srand(gettid()); + + err = pthread_barrier_wait(args->barrier); + FAIL_IF_EXIT(err != 0 && err != PTHREAD_BARRIER_SERIAL_THREAD); + + for (int i = 0; i < COUNT; i++) { + unsigned long expected_dscr; + unsigned long current_dscr; + unsigned long current_dscr_usr; + + FAIL_IF_EXIT(pthread_rwlock_rdlock(rw_lock)); + expected_dscr = *expected_dscr_p; + current_dscr = get_dscr(); + current_dscr_usr = get_dscr_usr(); + FAIL_IF_EXIT(pthread_rwlock_unlock(rw_lock)); + + FAIL_IF_EXIT(current_dscr != expected_dscr); + FAIL_IF_EXIT(current_dscr_usr != expected_dscr); + + if (rand() % 10 == 0) { + unsigned long next_dscr; + + FAIL_IF_EXIT(pthread_rwlock_wrlock(rw_lock)); + next_dscr = (*expected_dscr_p + 1) % DSCR_MAX; + set_default_dscr(next_dscr); + *expected_dscr_p = next_dscr; + FAIL_IF_EXIT(pthread_rwlock_unlock(rw_lock)); } } - /* Individual testing thread exit status */ - for (i = 0; i < THREADS; i++) { - if (pthread_join(threads[i], (void **)&(status[i]))) { - perror("pthread_join() failed"); - goto fail; - } + pthread_exit((void *)0); +} - if (*status[i]) { - printf("%ldth thread failed to join with %ld status\n", - i, *status[i]); - goto fail; - } +int dscr_default_random_test(void) +{ + struct random_thread_args threads[THREADS]; + unsigned long expected_system_dscr = 0; + pthread_rwlockattr_t rwlock_attr; + pthread_rwlock_t rw_lock; + pthread_barrier_t barrier; + + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + + FAIL_IF(pthread_rwlockattr_setkind_np(&rwlock_attr, + PTHREAD_RWLOCK_PREFER_WRITER_NONRECURSIVE_NP)); + FAIL_IF(pthread_rwlock_init(&rw_lock, &rwlock_attr)); + FAIL_IF(pthread_barrier_init(&barrier, NULL, THREADS)); + + set_default_dscr(expected_system_dscr); + + for (int i = 0; i < THREADS; i++) { + threads[i].expected_system_dscr = &expected_system_dscr; + threads[i].rw_lock = &rw_lock; + threads[i].barrier = &barrier; + + FAIL_IF(pthread_create(&threads[i].thread_id, NULL, + dscr_default_random_thread, (void *)&threads[i])); } - set_default_dscr(orig_dscr_default); + + for (int i = 0; i < THREADS; i++) + FAIL_IF(pthread_join(threads[i].thread_id, NULL)); + + FAIL_IF(pthread_barrier_destroy(&barrier)); + FAIL_IF(pthread_rwlock_destroy(&rw_lock)); + return 0; -fail: - set_default_dscr(orig_dscr_default); - return 1; } int main(int argc, char *argv[]) { - return test_harness(dscr_default, "dscr_default_test"); + unsigned long orig_dscr_default = 0; + int err = 0; + + if (have_hwcap2(PPC_FEATURE2_DSCR)) + orig_dscr_default = get_default_dscr(); + + err |= test_harness(dscr_default_lockstep_test, "dscr_default_lockstep_test"); + err |= test_harness(dscr_default_random_test, "dscr_default_random_test"); + + if (have_hwcap2(PPC_FEATURE2_DSCR)) + set_default_dscr(orig_dscr_default); + + return err; } diff --git a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c index 32fcf2b324b1..e2268e9183a8 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c @@ -7,64 +7,167 @@ * privilege state SPR and the problem state SPR for this purpose. * * When using the privilege state SPR, the instructions such as - * mfspr or mtspr are priviledged and the kernel emulates them - * for us. Instructions using problem state SPR can be exuecuted + * mfspr or mtspr are privileged and the kernel emulates them + * for us. Instructions using problem state SPR can be executed * directly without any emulation if the HW supports them. Else * they also get emulated by the kernel. * * Copyright 2012, Anton Blanchard, IBM Corporation. * Copyright 2015, Anshuman Khandual, IBM Corporation. */ + +#define _GNU_SOURCE + #include "dscr.h" +#include "utils.h" + +#include <pthread.h> +#include <sched.h> +#include <semaphore.h> -int dscr_explicit(void) +void *dscr_explicit_lockstep_thread(void *args) { - unsigned long i, dscr = 0; + sem_t *prev = (sem_t *)args; + sem_t *next = (sem_t *)args + 1; + unsigned long expected_dscr = 0; + + set_dscr(expected_dscr); + srand(gettid()); + + for (int i = 0; i < COUNT; i++) { + FAIL_IF_EXIT(sem_wait(prev)); + + FAIL_IF_EXIT(expected_dscr != get_dscr()); + FAIL_IF_EXIT(expected_dscr != get_dscr_usr()); + + expected_dscr = (expected_dscr + 1) % DSCR_MAX; + set_dscr(expected_dscr); + + FAIL_IF_EXIT(sem_post(next)); + } + + return NULL; +} + +int dscr_explicit_lockstep_test(void) +{ + pthread_t thread; + sem_t semaphores[2]; + sem_t *prev = &semaphores[1]; /* reversed prev/next than for the other thread */ + sem_t *next = &semaphores[0]; + unsigned long expected_dscr = 0; SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); - srand(getpid()); - set_dscr(dscr); + srand(gettid()); + set_dscr(expected_dscr); - for (i = 0; i < COUNT; i++) { - unsigned long cur_dscr, cur_dscr_usr; - double ret = uniform_deviate(rand()); + FAIL_IF(sem_init(prev, 0, 0)); + FAIL_IF(sem_init(next, 0, 1)); /* other thread starts first */ + FAIL_IF(bind_to_cpu(BIND_CPU_ANY) < 0); + FAIL_IF(pthread_create(&thread, NULL, dscr_explicit_lockstep_thread, (void *)semaphores)); - if (ret < 0.001) { - dscr++; - if (dscr > DSCR_MAX) - dscr = 0; + for (int i = 0; i < COUNT; i++) { + FAIL_IF(sem_wait(prev)); - set_dscr(dscr); - } + FAIL_IF(expected_dscr != get_dscr()); + FAIL_IF(expected_dscr != get_dscr_usr()); - cur_dscr = get_dscr(); - if (cur_dscr != dscr) { - fprintf(stderr, "Kernel DSCR should be %ld but " - "is %ld\n", dscr, cur_dscr); - return 1; - } + expected_dscr = (expected_dscr - 1) % DSCR_MAX; + set_dscr(expected_dscr); + + FAIL_IF(sem_post(next)); + } + + FAIL_IF(pthread_join(thread, NULL)); + FAIL_IF(sem_destroy(prev)); + FAIL_IF(sem_destroy(next)); + + return 0; +} + +struct random_thread_args { + pthread_t thread_id; + bool do_yields; + pthread_barrier_t *barrier; +}; + +void *dscr_explicit_random_thread(void *in) +{ + struct random_thread_args *args = (struct random_thread_args *)in; + unsigned long expected_dscr = 0; + int err; + + srand(gettid()); + + err = pthread_barrier_wait(args->barrier); + FAIL_IF_EXIT(err != 0 && err != PTHREAD_BARRIER_SERIAL_THREAD); - ret = uniform_deviate(rand()); - if (ret < 0.001) { - dscr++; - if (dscr > DSCR_MAX) - dscr = 0; + for (int i = 0; i < COUNT; i++) { + expected_dscr = rand() % DSCR_MAX; + set_dscr(expected_dscr); - set_dscr_usr(dscr); + for (int j = rand() % 5; j > 0; --j) { + FAIL_IF_EXIT(get_dscr() != expected_dscr); + FAIL_IF_EXIT(get_dscr_usr() != expected_dscr); + + if (args->do_yields && rand() % 2) + sched_yield(); } - cur_dscr_usr = get_dscr_usr(); - if (cur_dscr_usr != dscr) { - fprintf(stderr, "User DSCR should be %ld but " - "is %ld\n", dscr, cur_dscr_usr); - return 1; + expected_dscr = rand() % DSCR_MAX; + set_dscr_usr(expected_dscr); + + for (int j = rand() % 5; j > 0; --j) { + FAIL_IF_EXIT(get_dscr() != expected_dscr); + FAIL_IF_EXIT(get_dscr_usr() != expected_dscr); + + if (args->do_yields && rand() % 2) + sched_yield(); } } + + return NULL; +} + +int dscr_explicit_random_test(void) +{ + struct random_thread_args threads[THREADS]; + pthread_barrier_t barrier; + + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + + FAIL_IF(pthread_barrier_init(&barrier, NULL, THREADS)); + + for (int i = 0; i < THREADS; i++) { + threads[i].do_yields = i % 2 == 0; + threads[i].barrier = &barrier; + + FAIL_IF(pthread_create(&threads[i].thread_id, NULL, + dscr_explicit_random_thread, (void *)&threads[i])); + } + + for (int i = 0; i < THREADS; i++) + FAIL_IF(pthread_join(threads[i].thread_id, NULL)); + + FAIL_IF(pthread_barrier_destroy(&barrier)); + return 0; } int main(int argc, char *argv[]) { - return test_harness(dscr_explicit, "dscr_explicit_test"); + unsigned long orig_dscr_default = 0; + int err = 0; + + if (have_hwcap2(PPC_FEATURE2_DSCR)) + orig_dscr_default = get_default_dscr(); + + err |= test_harness(dscr_explicit_lockstep_test, "dscr_explicit_lockstep_test"); + err |= test_harness(dscr_explicit_random_test, "dscr_explicit_random_test"); + + if (have_hwcap2(PPC_FEATURE2_DSCR)) + set_default_dscr(orig_dscr_default); + + return err; } diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c index f9dfd3d3c2d5..68ce328e813e 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c @@ -7,8 +7,8 @@ * value using mfspr. * * When using the privilege state SPR, the instructions such as - * mfspr or mtspr are priviledged and the kernel emulates them - * for us. Instructions using problem state SPR can be exuecuted + * mfspr or mtspr are privileged and the kernel emulates them + * for us. Instructions using problem state SPR can be executed * directly without any emulation if the HW supports them. Else * they also get emulated by the kernel. * diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c index 4f1fef6198fc..e7cd0d6b1fad 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c @@ -67,17 +67,14 @@ static int check_all_cpu_dscr_defaults(unsigned long val) int dscr_sysfs(void) { unsigned long orig_dscr_default; - int i, j; SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); orig_dscr_default = get_default_dscr(); - for (i = 0; i < COUNT; i++) { - for (j = 0; j < DSCR_MAX; j++) { - set_default_dscr(j); - if (check_all_cpu_dscr_defaults(j)) - goto fail; - } + for (int i = 0; i < DSCR_MAX; i++) { + set_default_dscr(i); + if (check_all_cpu_dscr_defaults(i)) + goto fail; } set_default_dscr(orig_dscr_default); return 0; diff --git a/tools/testing/selftests/powerpc/dscr/dscr_user_test.c b/tools/testing/selftests/powerpc/dscr/dscr_user_test.c index e09072446dd3..67bb872a246a 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_user_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_user_test.c @@ -8,8 +8,8 @@ * numbers. * * When using the privilege state SPR, the instructions such as - * mfspr or mtspr are priviledged and the kernel emulates them - * for us. Instructions using problem state SPR can be exuecuted + * mfspr or mtspr are privileged and the kernel emulates them + * for us. Instructions using problem state SPR can be executed * directly without any emulation if the HW supports them. Else * they also get emulated by the kernel. * diff --git a/tools/testing/selftests/powerpc/dscr/settings b/tools/testing/selftests/powerpc/dscr/settings deleted file mode 100644 index e7b9417537fb..000000000000 --- a/tools/testing/selftests/powerpc/dscr/settings +++ /dev/null @@ -1 +0,0 @@ -timeout=0 diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index eed7dd7582b2..44bfd48b93d6 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -31,7 +31,10 @@ int read_auxv(char *buf, ssize_t buf_size); void *find_auxv_entry(int type, char *auxv); void *get_auxv_entry(int type); +#define BIND_CPU_ANY (-1) + int pick_online_cpu(void); +int bind_to_cpu(int cpu); int parse_intmax(const char *buffer, size_t count, intmax_t *result, int base); int parse_uintmax(const char *buffer, size_t count, uintmax_t *result, int base); diff --git a/tools/testing/selftests/powerpc/math/vmx_signal.c b/tools/testing/selftests/powerpc/math/vmx_signal.c index b340a5c4e79d..c307dff19c12 100644 --- a/tools/testing/selftests/powerpc/math/vmx_signal.c +++ b/tools/testing/selftests/powerpc/math/vmx_signal.c @@ -151,5 +151,6 @@ int test_signal_vmx(void) int main(int argc, char *argv[]) { + test_harness_set_timeout(360); return test_harness(test_signal_vmx, "vmx_signal"); } diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index 19dd0b2ea397..4a6608beef0e 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -32,7 +32,7 @@ $(OUTPUT)/stack_expansion_ldst: CFLAGS += -fno-stack-protector $(OUTPUT)/stack_expansion_ldst: ../utils.c $(OUTPUT)/tempfile: - dd if=/dev/zero of=$@ bs=64k count=1 + dd if=/dev/zero of=$@ bs=64k count=1 status=none $(OUTPUT)/tlbie_test: LDLIBS += -lpthread $(OUTPUT)/pkey_siginfo: LDLIBS += -lpthread diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index 30803353bd7c..2b95e44d20ff 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -25,32 +25,35 @@ $(OUTPUT)/per_event_excludes: ../utils.c DEFAULT_RUN_TESTS := $(RUN_TESTS) override define RUN_TESTS $(DEFAULT_RUN_TESTS) - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests endef DEFAULT_EMIT_TESTS := $(EMIT_TESTS) override define EMIT_TESTS $(DEFAULT_EMIT_TESTS) - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests endef DEFAULT_INSTALL_RULE := $(INSTALL_RULE) override define INSTALL_RULE $(DEFAULT_INSTALL_RULE) - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install endef -clean: +DEFAULT_CLEAN := $(CLEAN) +override define CLEAN + $(DEFAULT_CLEAN) $(RM) $(TEST_GEN_PROGS) $(OUTPUT)/loop.o - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean +endef ebb: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all @@ -61,4 +64,4 @@ sampling_tests: event_code_tests: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all -.PHONY: all run_tests clean ebb sampling_tests event_code_tests +.PHONY: all run_tests ebb sampling_tests event_code_tests diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c index 3cd33eb51e5e..fab7f34d7ce1 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c @@ -45,9 +45,8 @@ int cpu_event_pinned_vs_ebb(void) SKIP_IF(!ebb_is_supported()); - cpu = pick_online_cpu(); + cpu = bind_to_cpu(BIND_CPU_ANY); FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); FAIL_IF(pipe(read_pipe.fds) == -1); FAIL_IF(pipe(write_pipe.fds) == -1); diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c index 8466ef9d7de8..7c54c262036e 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c @@ -43,9 +43,8 @@ int cpu_event_vs_ebb(void) SKIP_IF(!ebb_is_supported()); - cpu = pick_online_cpu(); + cpu = bind_to_cpu(BIND_CPU_ANY); FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); FAIL_IF(pipe(read_pipe.fds) == -1); FAIL_IF(pipe(write_pipe.fds) == -1); diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c index 4d822cb3589c..d7064b54c64f 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c @@ -43,9 +43,8 @@ int ebb_vs_cpu_event(void) SKIP_IF(!ebb_is_supported()); - cpu = pick_online_cpu(); + cpu = bind_to_cpu(BIND_CPU_ANY); FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); FAIL_IF(pipe(read_pipe.fds) == -1); FAIL_IF(pipe(write_pipe.fds) == -1); diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c index 9b0f70d59702..4ac22b2e774f 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c @@ -75,13 +75,11 @@ static int cycles_child(void) int multi_ebb_procs(void) { pid_t pids[NR_CHILDREN]; - int cpu, rc, i; + int rc, i; SKIP_IF(!ebb_is_supported()); - cpu = pick_online_cpu(); - FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); + FAIL_IF(bind_to_cpu(BIND_CPU_ANY) < 0); for (i = 0; i < NR_CHILDREN; i++) { pids[i] = fork(); diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index 719f94f10d41..321357987408 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -14,19 +14,6 @@ #include "utils.h" #include "lib.h" - -int bind_to_cpu(int cpu) -{ - cpu_set_t mask; - - printf("Binding to cpu %d\n", cpu); - - CPU_ZERO(&mask); - CPU_SET(cpu, &mask); - - return sched_setaffinity(0, sizeof(mask), &mask); -} - #define PARENT_TOKEN 0xAA #define CHILD_TOKEN 0x55 @@ -116,12 +103,10 @@ static int eat_cpu_child(union pipe read_pipe, union pipe write_pipe) pid_t eat_cpu(int (test_function)(void)) { union pipe read_pipe, write_pipe; - int cpu, rc; + int rc; pid_t pid; - cpu = pick_online_cpu(); - FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); + FAIL_IF(bind_to_cpu(BIND_CPU_ANY) < 0); if (pipe(read_pipe.fds) == -1) return -1; diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h index bf1bec013bbb..1d62403ae6ea 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.h +++ b/tools/testing/selftests/powerpc/pmu/lib.h @@ -20,7 +20,6 @@ union pipe { int fds[2]; }; -extern int bind_to_cpu(int cpu); extern int kill_child_and_wait(pid_t child_pid); extern int wait_for_child(pid_t child_pid); extern int sync_with_child(union pipe read_pipe, union pipe write_pipe); diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c index 022cc1655eb5..75527876ad3c 100644 --- a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c @@ -63,9 +63,9 @@ static int mmcra_thresh_marked_sample(void) get_mmcra_thd_stop(get_reg_value(intr_regs, "MMCRA"), 4)); FAIL_IF(EV_CODE_EXTRACT(event.attr.config, marked) != get_mmcra_marked(get_reg_value(intr_regs, "MMCRA"), 4)); - FAIL_IF(EV_CODE_EXTRACT(event.attr.config, sample >> 2) != + FAIL_IF((EV_CODE_EXTRACT(event.attr.config, sample) >> 2) != get_mmcra_rand_samp_elig(get_reg_value(intr_regs, "MMCRA"), 4)); - FAIL_IF(EV_CODE_EXTRACT(event.attr.config, sample & 0x3) != + FAIL_IF((EV_CODE_EXTRACT(event.attr.config, sample) & 0x3) != get_mmcra_sample_mode(get_reg_value(intr_regs, "MMCRA"), 4)); FAIL_IF(EV_CODE_EXTRACT(event.attr.config, sm) != get_mmcra_sm(get_reg_value(intr_regs, "MMCRA"), 4)); diff --git a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h index 2b488b78c4f2..e713b69d694a 100644 --- a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h +++ b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h @@ -9,6 +9,7 @@ #define _GLOBAL(A) FUNC_START(test_ ## A) #define _GLOBAL_TOC(A) FUNC_START(test_ ## A) +#define CFUNC(name) name #define CONFIG_ALTIVEC diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index 7c8cfedb012a..252fb4a95e90 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -452,6 +452,29 @@ done: return cpu; } +int bind_to_cpu(int cpu) +{ + cpu_set_t mask; + int err; + + if (cpu == BIND_CPU_ANY) { + cpu = pick_online_cpu(); + if (cpu < 0) + return cpu; + } + + printf("Binding to cpu %d\n", cpu); + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + + err = sched_setaffinity(0, sizeof(mask), &mask); + if (err) + return err; + + return cpu; +} + bool is_ppc64le(void) { struct utsname uts; diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile new file mode 100644 index 000000000000..32a72902d045 --- /dev/null +++ b/tools/testing/selftests/riscv/Makefile @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: GPL-2.0 +# Originally tools/testing/arm64/Makefile + +# When ARCH not overridden for crosscompiling, lookup machine +ARCH ?= $(shell uname -m 2>/dev/null || echo not) + +ifneq (,$(filter $(ARCH),riscv)) +RISCV_SUBTARGETS ?= hwprobe +else +RISCV_SUBTARGETS := +endif + +CFLAGS := -Wall -O2 -g + +# A proper top_srcdir is needed by KSFT(lib.mk) +top_srcdir = $(realpath ../../../../) + +# Additional include paths needed by kselftest.h and local headers +CFLAGS += -I$(top_srcdir)/tools/testing/selftests/ + +CFLAGS += $(KHDR_INCLUDES) + +export CFLAGS +export top_srcdir + +all: + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + mkdir -p $$BUILD_TARGET; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +install: all + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +run_tests: all + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +# Avoid any output on non riscv on emit_tests +emit_tests: all + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +clean: + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +.PHONY: all clean install run_tests emit_tests diff --git a/tools/testing/selftests/riscv/hwprobe/Makefile b/tools/testing/selftests/riscv/hwprobe/Makefile new file mode 100644 index 000000000000..ebdbb3c22e54 --- /dev/null +++ b/tools/testing/selftests/riscv/hwprobe/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2021 ARM Limited +# Originally tools/testing/arm64/abi/Makefile + +TEST_GEN_PROGS := hwprobe + +include ../../lib.mk + +$(OUTPUT)/hwprobe: hwprobe.c sys_hwprobe.S + $(CC) -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.c b/tools/testing/selftests/riscv/hwprobe/hwprobe.c new file mode 100644 index 000000000000..09f290a67420 --- /dev/null +++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stddef.h> +#include <asm/hwprobe.h> + +/* + * Rather than relying on having a new enough libc to define this, just do it + * ourselves. This way we don't need to be coupled to a new-enough libc to + * contain the call. + */ +long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpu_count, unsigned long *cpus, unsigned int flags); + +int main(int argc, char **argv) +{ + struct riscv_hwprobe pairs[8]; + unsigned long cpus; + long out; + + /* Fake the CPU_SET ops. */ + cpus = -1; + + /* + * Just run a basic test: pass enough pairs to get up to the base + * behavior, and then check to make sure it's sane. + */ + for (long i = 0; i < 8; i++) + pairs[i].key = i; + out = riscv_hwprobe(pairs, 8, 1, &cpus, 0); + if (out != 0) + return -1; + for (long i = 0; i < 4; ++i) { + /* Fail if the kernel claims not to recognize a base key. */ + if ((i < 4) && (pairs[i].key != i)) + return -2; + + if (pairs[i].key != RISCV_HWPROBE_KEY_BASE_BEHAVIOR) + continue; + + if (pairs[i].value & RISCV_HWPROBE_BASE_BEHAVIOR_IMA) + continue; + + return -3; + } + + /* + * This should also work with a NULL CPU set, but should not work + * with an improperly supplied CPU set. + */ + out = riscv_hwprobe(pairs, 8, 0, 0, 0); + if (out != 0) + return -4; + + out = riscv_hwprobe(pairs, 8, 0, &cpus, 0); + if (out == 0) + return -5; + + out = riscv_hwprobe(pairs, 8, 1, 0, 0); + if (out == 0) + return -6; + + /* + * Check that keys work by providing one that we know exists, and + * checking to make sure the resultig pair is what we asked for. + */ + pairs[0].key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR; + out = riscv_hwprobe(pairs, 1, 1, &cpus, 0); + if (out != 0) + return -7; + if (pairs[0].key != RISCV_HWPROBE_KEY_BASE_BEHAVIOR) + return -8; + + /* + * Check that an unknown key gets overwritten with -1, + * but doesn't block elements after it. + */ + pairs[0].key = 0x5555; + pairs[1].key = 1; + pairs[1].value = 0xAAAA; + out = riscv_hwprobe(pairs, 2, 0, 0, 0); + if (out != 0) + return -9; + + if (pairs[0].key != -1) + return -10; + + if ((pairs[1].key != 1) || (pairs[1].value == 0xAAAA)) + return -11; + + return 0; +} diff --git a/tools/testing/selftests/riscv/hwprobe/sys_hwprobe.S b/tools/testing/selftests/riscv/hwprobe/sys_hwprobe.S new file mode 100644 index 000000000000..a4773c88d267 --- /dev/null +++ b/tools/testing/selftests/riscv/hwprobe/sys_hwprobe.S @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023 Rivos, Inc */ + +.text +.global riscv_hwprobe +riscv_hwprobe: + # Put __NR_riscv_hwprobe in the syscall number register, then just shim + # back the kernel's return. This doesn't do any sort of errno + # handling, the caller can deal with it. + li a7, 258 + ecall + ret diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile index 6b512b86aec3..9e95bd41b0b4 100644 --- a/tools/testing/selftests/user_events/Makefile +++ b/tools/testing/selftests/user_events/Makefile @@ -10,7 +10,7 @@ LDLIBS += -lrt -lpthread -lm # This test will not compile until user_events.h is added # back to uapi. -TEST_GEN_PROGS = ftrace_test dyn_test perf_test +TEST_GEN_PROGS = ftrace_test dyn_test perf_test abi_test TEST_FILES := settings diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c new file mode 100644 index 000000000000..5125c42efe65 --- /dev/null +++ b/tools/testing/selftests/user_events/abi_test.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * User Events ABI Test Program + * + * Copyright (c) 2022 Beau Belgrave <beaub@linux.microsoft.com> + */ + +#define _GNU_SOURCE +#include <sched.h> + +#include <errno.h> +#include <linux/user_events.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <unistd.h> +#include <asm/unistd.h> + +#include "../kselftest_harness.h" + +const char *data_file = "/sys/kernel/tracing/user_events_data"; +const char *enable_file = "/sys/kernel/tracing/events/user_events/__abi_event/enable"; + +static int change_event(bool enable) +{ + int fd = open(enable_file, O_RDWR); + int ret; + + if (fd < 0) + return -1; + + if (enable) + ret = write(fd, "1", 1); + else + ret = write(fd, "0", 1); + + close(fd); + + if (ret == 1) + ret = 0; + else + ret = -1; + + return ret; +} + +static int reg_enable(long *enable, int size, int bit) +{ + struct user_reg reg = {0}; + int fd = open(data_file, O_RDWR); + int ret; + + if (fd < 0) + return -1; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__abi_event"; + reg.enable_bit = bit; + reg.enable_addr = (__u64)enable; + reg.enable_size = size; + + ret = ioctl(fd, DIAG_IOCSREG, ®); + + close(fd); + + return ret; +} + +static int reg_disable(long *enable, int bit) +{ + struct user_unreg reg = {0}; + int fd = open(data_file, O_RDWR); + int ret; + + if (fd < 0) + return -1; + + reg.size = sizeof(reg); + reg.disable_bit = bit; + reg.disable_addr = (__u64)enable; + + ret = ioctl(fd, DIAG_IOCSUNREG, ®); + + close(fd); + + return ret; +} + +FIXTURE(user) { + long check; +}; + +FIXTURE_SETUP(user) { + change_event(false); + self->check = 0; +} + +FIXTURE_TEARDOWN(user) { +} + +TEST_F(user, enablement) { + /* Changes should be reflected immediately */ + ASSERT_EQ(0, self->check); + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 0)); + ASSERT_EQ(0, change_event(true)); + ASSERT_EQ(1, self->check); + ASSERT_EQ(0, change_event(false)); + ASSERT_EQ(0, self->check); + + /* Ensure kernel clears bit after disable */ + ASSERT_EQ(0, change_event(true)); + ASSERT_EQ(1, self->check); + ASSERT_EQ(0, reg_disable(&self->check, 0)); + ASSERT_EQ(0, self->check); + + /* Ensure doesn't change after unreg */ + ASSERT_EQ(0, change_event(true)); + ASSERT_EQ(0, self->check); + ASSERT_EQ(0, change_event(false)); +} + +TEST_F(user, bit_sizes) { + /* Allow 0-31 bits for 32-bit */ + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 0)); + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 31)); + ASSERT_NE(0, reg_enable(&self->check, sizeof(int), 32)); + ASSERT_EQ(0, reg_disable(&self->check, 0)); + ASSERT_EQ(0, reg_disable(&self->check, 31)); + +#if BITS_PER_LONG == 8 + /* Allow 0-64 bits for 64-bit */ + ASSERT_EQ(0, reg_enable(&self->check, sizeof(long), 63)); + ASSERT_NE(0, reg_enable(&self->check, sizeof(long), 64)); + ASSERT_EQ(0, reg_disable(&self->check, 63)); +#endif + + /* Disallowed sizes (everything beside 4 and 8) */ + ASSERT_NE(0, reg_enable(&self->check, 1, 0)); + ASSERT_NE(0, reg_enable(&self->check, 2, 0)); + ASSERT_NE(0, reg_enable(&self->check, 3, 0)); + ASSERT_NE(0, reg_enable(&self->check, 5, 0)); + ASSERT_NE(0, reg_enable(&self->check, 6, 0)); + ASSERT_NE(0, reg_enable(&self->check, 7, 0)); + ASSERT_NE(0, reg_enable(&self->check, 9, 0)); + ASSERT_NE(0, reg_enable(&self->check, 128, 0)); +} + +TEST_F(user, forks) { + int i; + + /* Ensure COW pages get updated after fork */ + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 0)); + ASSERT_EQ(0, self->check); + + if (fork() == 0) { + /* Force COW */ + self->check = 0; + + /* Up to 1 sec for enablement */ + for (i = 0; i < 10; ++i) { + usleep(100000); + + if (self->check) + exit(0); + } + + exit(1); + } + + /* Allow generous time for COW, then enable */ + usleep(100000); + ASSERT_EQ(0, change_event(true)); + + ASSERT_NE(-1, wait(&i)); + ASSERT_EQ(0, WEXITSTATUS(i)); + + /* Ensure child doesn't disable parent */ + if (fork() == 0) + exit(reg_disable(&self->check, 0)); + + ASSERT_NE(-1, wait(&i)); + ASSERT_EQ(0, WEXITSTATUS(i)); + ASSERT_EQ(1, self->check); + ASSERT_EQ(0, change_event(false)); + ASSERT_EQ(0, self->check); +} + +/* Waits up to 1 sec for enablement */ +static int clone_check(void *check) +{ + int i; + + for (i = 0; i < 10; ++i) { + usleep(100000); + + if (*(long *)check) + return 0; + } + + return 1; +} + +TEST_F(user, clones) { + int i, stack_size = 4096; + void *stack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, + -1, 0); + + ASSERT_NE(MAP_FAILED, stack); + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 0)); + ASSERT_EQ(0, self->check); + + /* Shared VM should see enablements */ + ASSERT_NE(-1, clone(&clone_check, stack + stack_size, + CLONE_VM | SIGCHLD, &self->check)); + + ASSERT_EQ(0, change_event(true)); + ASSERT_NE(-1, wait(&i)); + ASSERT_EQ(0, WEXITSTATUS(i)); + munmap(stack, stack_size); + ASSERT_EQ(0, change_event(false)); +} + +int main(int argc, char **argv) +{ + return test_harness_run(argc, argv); +} diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index d6265d14cd51..8879a7b04c6a 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -16,7 +16,7 @@ #include "../kselftest_harness.h" -const char *dyn_file = "/sys/kernel/debug/tracing/dynamic_events"; +const char *dyn_file = "/sys/kernel/tracing/dynamic_events"; const char *clear = "!u:__test_event"; static int Append(const char *value) diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 404a2713dcae..7c99cef94a65 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -12,20 +12,16 @@ #include <fcntl.h> #include <sys/ioctl.h> #include <sys/stat.h> +#include <sys/uio.h> #include <unistd.h> #include "../kselftest_harness.h" -const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; -const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; -const char *enable_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/enable"; -const char *trace_file = "/sys/kernel/debug/tracing/trace"; -const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format"; - -static inline int status_check(char *status_page, int status_bit) -{ - return status_page[status_bit >> 3] & (1 << (status_bit & 7)); -} +const char *data_file = "/sys/kernel/tracing/user_events_data"; +const char *status_file = "/sys/kernel/tracing/user_events_status"; +const char *enable_file = "/sys/kernel/tracing/events/user_events/__test_event/enable"; +const char *trace_file = "/sys/kernel/tracing/trace"; +const char *fmt_file = "/sys/kernel/tracing/events/user_events/__test_event/format"; static int trace_bytes(void) { @@ -106,13 +102,23 @@ err: return -1; } -static int clear(void) +static int clear(int *check) { + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = 31; + unreg.disable_addr = (__u64)check; + int fd = open(data_file, O_RDWR); if (fd == -1) return -1; + if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) + if (errno != ENOENT) + return -1; + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) if (errno != ENOENT) return -1; @@ -122,7 +128,7 @@ static int clear(void) return 0; } -static int check_print_fmt(const char *event, const char *expected) +static int check_print_fmt(const char *event, const char *expected, int *check) { struct user_reg reg = {0}; char print_fmt[256]; @@ -130,7 +136,7 @@ static int check_print_fmt(const char *event, const char *expected) int fd; /* Ensure cleared */ - ret = clear(); + ret = clear(check); if (ret != 0) return ret; @@ -142,14 +148,19 @@ static int check_print_fmt(const char *event, const char *expected) reg.size = sizeof(reg); reg.name_args = (__u64)event; + reg.enable_bit = 31; + reg.enable_addr = (__u64)check; + reg.enable_size = sizeof(*check); /* Register should work */ ret = ioctl(fd, DIAG_IOCSREG, ®); close(fd); - if (ret != 0) + if (ret != 0) { + printf("Reg failed in fmt\n"); return ret; + } /* Ensure correct print_fmt */ ret = get_print_fmt(print_fmt, sizeof(print_fmt)); @@ -164,6 +175,7 @@ FIXTURE(user) { int status_fd; int data_fd; int enable_fd; + int check; }; FIXTURE_SETUP(user) { @@ -185,59 +197,63 @@ FIXTURE_TEARDOWN(user) { close(self->enable_fd); } - ASSERT_EQ(0, clear()); + if (clear(&self->check) != 0) + printf("WARNING: Clear didn't work!\n"); } TEST_F(user, register_events) { struct user_reg reg = {0}; - int page_size = sysconf(_SC_PAGESIZE); - char *status_page; + struct user_unreg unreg = {0}; reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); - status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, - self->status_fd, 0); + unreg.size = sizeof(unreg); + unreg.disable_bit = 31; + unreg.disable_addr = (__u64)&self->check; /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); - /* Multiple registers should result in same index */ + /* Multiple registers to the same addr + bit should fail */ + ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(EADDRINUSE, errno); + + /* Multiple registers to same name should result in same index */ + reg.enable_bit = 30; ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); /* Ensure disabled */ self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, self->enable_fd); ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0"))) - /* MMAP should work and be zero'd */ - ASSERT_NE(MAP_FAILED, status_page); - ASSERT_NE(NULL, status_page); - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); - /* Enable event and ensure bits updated in status */ ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) - ASSERT_NE(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(1 << reg.enable_bit, self->check); /* Disable event and ensure bits updated in status */ ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0"))) - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(0, self->check); /* File still open should return -EBUSY for delete */ ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); ASSERT_EQ(EBUSY, errno); - /* Delete should work only after close */ + /* Unregister */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); + unreg.disable_bit = 30; + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); + + /* Delete should work only after close and unregister */ close(self->data_fd); self->data_fd = open(data_file, O_RDWR); ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); - - /* Unmap should work */ - ASSERT_EQ(0, munmap(status_page, page_size)); } TEST_F(user, write_events) { @@ -245,11 +261,12 @@ TEST_F(user, write_events) { struct iovec io[3]; __u32 field1, field2; int before = 0, after = 0; - int page_size = sysconf(_SC_PAGESIZE); - char *status_page; reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); field1 = 1; field2 = 2; @@ -261,18 +278,10 @@ TEST_F(user, write_events) { io[2].iov_base = &field2; io[2].iov_len = sizeof(field2); - status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, - self->status_fd, 0); - /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); - - /* MMAP should work and be zero'd */ - ASSERT_NE(MAP_FAILED, status_page); - ASSERT_NE(NULL, status_page); - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(0, self->check); /* Write should fail on invalid slot with ENOENT */ io[0].iov_base = &field2; @@ -287,13 +296,18 @@ TEST_F(user, write_events) { ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) /* Event should now be enabled */ - ASSERT_NE(0, status_check(status_page, reg.status_bit)); + ASSERT_NE(1 << reg.enable_bit, self->check); /* Write should make it out to ftrace buffers */ before = trace_bytes(); ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3)); after = trace_bytes(); ASSERT_GT(after, before); + + /* Negative index should fail with EINVAL */ + reg.write_index = -1; + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EINVAL, errno); } TEST_F(user, write_fault) { @@ -304,6 +318,9 @@ TEST_F(user, write_fault) { reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event u64 anon"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); anon = mmap(NULL, l, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); ASSERT_NE(MAP_FAILED, anon); @@ -316,7 +333,6 @@ TEST_F(user, write_fault) { /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); /* Write should work normally */ ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2)); @@ -333,24 +349,17 @@ TEST_F(user, write_validator) { int loc, bytes; char data[8]; int before = 0, after = 0; - int page_size = sysconf(_SC_PAGESIZE); - char *status_page; - - status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, - self->status_fd, 0); reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event __rel_loc char[] data"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); - - /* MMAP should work and be zero'd */ - ASSERT_NE(MAP_FAILED, status_page); - ASSERT_NE(NULL, status_page); - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(0, self->check); io[0].iov_base = ®.write_index; io[0].iov_len = sizeof(reg.write_index); @@ -369,7 +378,7 @@ TEST_F(user, write_validator) { ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) /* Event should now be enabled */ - ASSERT_NE(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(1 << reg.enable_bit, self->check); /* Full in-bounds write should work */ before = trace_bytes(); @@ -409,71 +418,88 @@ TEST_F(user, print_fmt) { int ret; ret = check_print_fmt("__test_event __rel_loc char[] data", - "print fmt: \"data=%s\", __get_rel_str(data)"); + "print fmt: \"data=%s\", __get_rel_str(data)", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event __data_loc char[] data", - "print fmt: \"data=%s\", __get_str(data)"); + "print fmt: \"data=%s\", __get_str(data)", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event s64 data", - "print fmt: \"data=%lld\", REC->data"); + "print fmt: \"data=%lld\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event u64 data", - "print fmt: \"data=%llu\", REC->data"); + "print fmt: \"data=%llu\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event s32 data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event u32 data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event int data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event unsigned int data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event s16 data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event u16 data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event short data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event unsigned short data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event s8 data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event u8 data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event char data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event unsigned char data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event char[4] data", - "print fmt: \"data=%s\", REC->data"); + "print fmt: \"data=%s\", REC->data", + &self->check); ASSERT_EQ(0, ret); } diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index 8b4c7879d5a7..a070258d4449 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -18,10 +18,9 @@ #include "../kselftest_harness.h" -const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; -const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; -const char *id_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/id"; -const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format"; +const char *data_file = "/sys/kernel/tracing/user_events_data"; +const char *id_file = "/sys/kernel/tracing/events/user_events/__test_event/id"; +const char *fmt_file = "/sys/kernel/tracing/events/user_events/__test_event/format"; struct event { __u32 index; @@ -35,11 +34,6 @@ static long perf_event_open(struct perf_event_attr *pe, pid_t pid, return syscall(__NR_perf_event_open, pe, pid, cpu, group_fd, flags); } -static inline int status_check(char *status_page, int status_bit) -{ - return status_page[status_bit >> 3] & (1 << (status_bit & 7)); -} - static int get_id(void) { FILE *fp = fopen(id_file, "r"); @@ -88,45 +82,38 @@ static int get_offset(void) } FIXTURE(user) { - int status_fd; int data_fd; + int check; }; FIXTURE_SETUP(user) { - self->status_fd = open(status_file, O_RDONLY); - ASSERT_NE(-1, self->status_fd); - self->data_fd = open(data_file, O_RDWR); ASSERT_NE(-1, self->data_fd); } FIXTURE_TEARDOWN(user) { - close(self->status_fd); close(self->data_fd); } TEST_F(user, perf_write) { struct perf_event_attr pe = {0}; struct user_reg reg = {0}; - int page_size = sysconf(_SC_PAGESIZE); - char *status_page; struct event event; struct perf_event_mmap_page *perf_page; + int page_size = sysconf(_SC_PAGESIZE); int id, fd, offset; __u32 *val; reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; - - status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, - self->status_fd, 0); - ASSERT_NE(MAP_FAILED, status_page); + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(0, self->check); /* Id should be there */ id = get_id(); @@ -149,7 +136,7 @@ TEST_F(user, perf_write) { ASSERT_NE(MAP_FAILED, perf_page); /* Status should be updated */ - ASSERT_NE(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(1 << reg.enable_bit, self->check); event.index = reg.write_index; event.field1 = 0xc001; @@ -165,6 +152,12 @@ TEST_F(user, perf_write) { /* Ensure correct */ ASSERT_EQ(event.field1, *val++); ASSERT_EQ(event.field2, *val++); + + munmap(perf_page, page_size * 2); + close(fd); + + /* Status should be updated */ + ASSERT_EQ(0, self->check); } int main(int argc, char **argv) diff --git a/tools/tracing/rtla/.gitignore b/tools/tracing/rtla/.gitignore new file mode 100644 index 000000000000..e9df32419b2b --- /dev/null +++ b/tools/tracing/rtla/.gitignore @@ -0,0 +1 @@ +/rtla diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c index ec4e0f4b0e6c..1843fff66da5 100644 --- a/tools/tracing/rtla/src/timerlat_aa.c +++ b/tools/tracing/rtla/src/timerlat_aa.c @@ -548,7 +548,7 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, exp_irq_ts = taa_data->timer_irq_start_time - taa_data->timer_irq_start_delay; if (exp_irq_ts < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) - printf(" Previous IRQ interference: \t up to %9.2f us", + printf(" Previous IRQ interference: \t\t up to %9.2f us\n", ns_to_usf(taa_data->prev_irq_duration)); /* diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index eea5b3357e27..92c658c64f28 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -33,6 +33,7 @@ struct timerlat_top_params { int set_sched; int dma_latency; int no_aa; + int aa_only; int dump_tasks; struct sched_attr sched_param; struct trace_events *events; @@ -142,10 +143,12 @@ timerlat_top_handler(struct trace_seq *s, struct tep_record *record, top = container_of(trace, struct osnoise_tool, trace); params = top->params; - tep_get_field_val(s, event, "context", record, &thread, 1); - tep_get_field_val(s, event, "timer_latency", record, &latency, 1); + if (!params->aa_only) { + tep_get_field_val(s, event, "context", record, &thread, 1); + tep_get_field_val(s, event, "timer_latency", record, &latency, 1); - timerlat_top_update(top, cpu, thread, latency); + timerlat_top_update(top, cpu, thread, latency); + } if (!params->no_aa) timerlat_aa_handler(s, record, event, context); @@ -250,6 +253,9 @@ timerlat_print_stats(struct timerlat_top_params *params, struct osnoise_tool *to static int nr_cpus = -1; int i; + if (params->aa_only) + return; + if (nr_cpus == -1) nr_cpus = sysconf(_SC_NPROCESSORS_CONF); @@ -279,10 +285,11 @@ static void timerlat_top_usage(char *usage) "", " usage: rtla timerlat [top] [-h] [-q] [-a us] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] \\", " [[-t[=file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] [-c cpu-list] \\", - " [-P priority] [--dma-latency us]", + " [-P priority] [--dma-latency us] [--aa-only us]", "", " -h/--help: print this menu", " -a/--auto: set automatic trace mode, stopping the session if argument in us latency is hit", + " --aa-only us: stop if <us> latency is hit, only printing the auto analysis (reduces CPU usage)", " -p/--period us: timerlat period in us", " -i/--irq us: stop trace if the irq latency is higher than the argument in us", " -T/--thread us: stop trace if the thread latency is higher than the argument in us", @@ -362,13 +369,14 @@ static struct timerlat_top_params {"dma-latency", required_argument, 0, '2'}, {"no-aa", no_argument, 0, '3'}, {"dump-tasks", no_argument, 0, '4'}, + {"aa-only", required_argument, 0, '5'}, {0, 0, 0, 0} }; /* getopt_long stores the option index here. */ int option_index = 0; - c = getopt_long(argc, argv, "a:c:d:De:hi:np:P:qs:t::T:0:1:2:34", + c = getopt_long(argc, argv, "a:c:d:De:hi:np:P:qs:t::T:0:1:2:345:", long_options, &option_index); /* detect the end of the options. */ @@ -389,6 +397,20 @@ static struct timerlat_top_params /* set trace */ params->trace_output = "timerlat_trace.txt"; break; + case '5': + /* it is here because it is similar to -a */ + auto_thresh = get_llong_from_str(optarg); + + /* set thread stop to auto_thresh */ + params->stop_total_us = auto_thresh; + params->stop_us = auto_thresh; + + /* get stack trace */ + params->print_stack = auto_thresh; + + /* set aa_only to avoid parsing the trace */ + params->aa_only = 1; + break; case 'c': retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); if (retval) @@ -503,6 +525,9 @@ static struct timerlat_top_params if (!params->stop_us && !params->stop_total_us) params->no_aa = 1; + if (params->no_aa && params->aa_only) + timerlat_top_usage("--no-aa and --aa-only are mutually exclusive!"); + return params; } @@ -634,6 +659,7 @@ int timerlat_top_main(int argc, char *argv[]) struct trace_instance *trace; int dma_latency_fd = -1; int return_value = 1; + char *max_lat; int retval; params = timerlat_top_parse_args(argc, argv); @@ -700,6 +726,9 @@ int timerlat_top_main(int argc, char *argv[]) while (!stop_tracing) { sleep(params->sleep_time); + if (params->aa_only && !trace_is_off(&top->trace, &record->trace)) + continue; + retval = tracefs_iterate_raw_events(trace->tep, trace->inst, NULL, @@ -733,6 +762,16 @@ int timerlat_top_main(int argc, char *argv[]) printf(" Saving trace to %s\n", params->trace_output); save_trace_to_file(record->trace.inst, params->trace_output); } + } else if (params->aa_only) { + /* + * If the trace did not stop with --aa-only, at least print the + * max known latency. + */ + max_lat = tracefs_instance_file_read(trace->inst, "tracing_max_latency", NULL); + if (max_lat) { + printf(" Max latency was %s\n", max_lat); + free(max_lat); + } } out_top: diff --git a/tools/verification/rv/src/rv.c b/tools/verification/rv/src/rv.c index e601cd9c411e..1ddb85532816 100644 --- a/tools/verification/rv/src/rv.c +++ b/tools/verification/rv/src/rv.c @@ -74,7 +74,7 @@ static void rv_list(int argc, char **argv) static void rv_mon(int argc, char **argv) { char *monitor_name; - int i, run; + int i, run = 0; static const char *const usage[] = { "", |