diff options
Diffstat (limited to 'tools')
42 files changed, 1629 insertions, 313 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/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/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/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/net/srv6_end_dt46_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh index aebaab8ce44c..441eededa031 100755 --- a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh @@ -292,6 +292,11 @@ setup_hs() ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} ip -netns ${hsname} link set ${rtveth} netns ${rtname} ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad @@ -316,11 +321,6 @@ setup_hs() ip netns exec ${rtname} sysctl -wq net.ipv6.conf.${rtveth}.proxy_ndp=1 ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 - # disable the rp_filter otherwise the kernel gets confused about how - # to route decap ipv4 packets. - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 - ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" } diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 4504ee07be08..3686bfa6c58d 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -8,8 +8,11 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ conntrack_vrf.sh nft_synproxy.sh rpath.sh -CFLAGS += $(shell pkg-config --cflags libmnl 2>/dev/null || echo "-I/usr/include/libmnl") -LDLIBS = -lmnl +HOSTPKG_CONFIG := pkg-config + +CFLAGS += $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) +LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) + TEST_GEN_FILES = nf-queue connect_close include ../lib.mk |