diff options
Diffstat (limited to 'tools')
135 files changed, 4447 insertions, 1673 deletions
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 8aa0d276a636..abc418650fec 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -60,6 +60,7 @@ #define ARM_CPU_IMP_FUJITSU 0x46 #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 +#define ARM_CPU_IMP_AMPERE 0xC0 #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -123,6 +124,8 @@ #define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 +#define AMPERE_CPU_PART_AMPERE1 0xAC3 + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -172,6 +175,7 @@ #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) +#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h index 1f5e26aae9fc..01cc27ec4520 100644 --- a/tools/arch/x86/include/asm/atomic.h +++ b/tools/arch/x86/include/asm/atomic.h @@ -8,6 +8,7 @@ #define LOCK_PREFIX "\n\tlock; " +#include <asm/asm.h> #include <asm/cmpxchg.h> /* @@ -70,4 +71,10 @@ static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) return cmpxchg(&v->counter, old, new); } +static inline int atomic_test_and_set_bit(long nr, unsigned long *addr) +{ + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, "Ir", nr, "%0", "c"); + +} + #endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index ef4775c6db01..b71f4f2ecdd5 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -96,7 +96,7 @@ #define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -/* FREE! ( 3*32+17) */ +#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index d0d7b9bc6cad..5418e2f99834 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -27,7 +27,7 @@ * Output: * rax original destination */ -SYM_FUNC_START(__memcpy) +SYM_TYPED_FUNC_START(__memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 57619f240b56..38f8851bd7cb 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -103,6 +103,7 @@ FEATURE_TESTS_EXTRA := \ libbpf-bpf_prog_load \ libbpf-bpf_object__next_program \ libbpf-bpf_object__next_map \ + libbpf-bpf_program__set_insns \ libbpf-bpf_create_map \ libpfm4 \ libdebuginfod \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 04b07ff88234..690fe97be190 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -63,6 +63,7 @@ FILES= \ test-libbpf-bpf_map_create.bin \ test-libbpf-bpf_object__next_program.bin \ test-libbpf-bpf_object__next_map.bin \ + test-libbpf-bpf_program__set_insns.bin \ test-libbpf-btf__raw_data.bin \ test-get_cpuid.bin \ test-sdt.bin \ @@ -316,6 +317,9 @@ $(OUTPUT)test-libbpf-bpf_object__next_program.bin: $(OUTPUT)test-libbpf-bpf_object__next_map.bin: $(BUILD) -lbpf +$(OUTPUT)test-libbpf-bpf_program__set_insns.bin: + $(BUILD) -lbpf + $(OUTPUT)test-libbpf-btf__raw_data.bin: $(BUILD) -lbpf diff --git a/tools/build/feature/test-libbpf-bpf_program__set_insns.c b/tools/build/feature/test-libbpf-bpf_program__set_insns.c new file mode 100644 index 000000000000..f3b7f18c8f49 --- /dev/null +++ b/tools/build/feature/test-libbpf-bpf_program__set_insns.c @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <bpf/libbpf.h> + +int main(void) +{ + bpf_program__set_insns(NULL /* prog */, NULL /* new_insns */, 0 /* new_insn_cnt */); + return 0; +} diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c index aadee6d34c74..8d35893b2fa8 100644 --- a/tools/iio/iio_utils.c +++ b/tools/iio/iio_utils.c @@ -547,6 +547,10 @@ static int calc_digits(int num) { int count = 0; + /* It takes a digit to represent zero */ + if (!num) + return 1; + while (num != 0) { num /= 10; count++; diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h index 4c1966f7c77a..6daa68bf5b9e 100644 --- a/tools/include/asm-generic/atomic-gcc.h +++ b/tools/include/asm-generic/atomic-gcc.h @@ -4,6 +4,7 @@ #include <linux/compiler.h> #include <linux/types.h> +#include <linux/bitops.h> /* * Atomic operations that C can't guarantee us. Useful for @@ -69,4 +70,15 @@ static inline int atomic_cmpxchg(atomic_t *v, int oldval, int newval) return cmpxchg(&(v)->counter, oldval, newval); } +static inline int atomic_test_and_set_bit(long nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + long old; + + addr += BIT_WORD(nr); + + old = __sync_fetch_and_or(addr, mask); + return !!(old & mask); +} + #endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */ diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index bef35bee9c44..ad97c0d522b8 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -19,9 +19,9 @@ static __attribute__((unused)) int memcmp(const void *s1, const void *s2, size_t n) { size_t ofs = 0; - char c1 = 0; + int c1 = 0; - while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { + while (ofs < n && !(c1 = ((unsigned char *)s1)[ofs] - ((unsigned char *)s2)[ofs])) { ofs++; } return c1; @@ -125,14 +125,18 @@ char *strcpy(char *dst, const char *src) } /* this function is only used with arguments that are not constants or when - * it's not known because optimizations are disabled. + * it's not known because optimizations are disabled. Note that gcc 12 + * recognizes an strlen() pattern and replaces it with a jump to strlen(), + * thus itself, hence the asm() statement below that's meant to disable this + * confusing practice. */ static __attribute__((unused)) -size_t nolibc_strlen(const char *str) +size_t strlen(const char *str) { size_t len; - for (len = 0; str[len]; len++); + for (len = 0; str[len]; len++) + asm(""); return len; } @@ -140,13 +144,12 @@ size_t nolibc_strlen(const char *str) * the two branches, then will rely on an external definition of strlen(). */ #if defined(__OPTIMIZE__) +#define nolibc_strlen(x) strlen(x) #define strlen(str) ({ \ __builtin_constant_p((str)) ? \ __builtin_strlen((str)) : \ nolibc_strlen((str)); \ }) -#else -#define strlen(str) nolibc_strlen((str)) #endif static __attribute__((unused)) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 14168225cecd..f243ce665f74 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -68,6 +68,8 @@ enum { #define IPPROTO_PIM IPPROTO_PIM IPPROTO_COMP = 108, /* Compression Header Protocol */ #define IPPROTO_COMP IPPROTO_COMP + IPPROTO_L2TP = 115, /* Layer 2 Tunnelling Protocol */ +#define IPPROTO_L2TP IPPROTO_L2TP IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */ #define IPPROTO_SCTP IPPROTO_SCTP IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */ @@ -188,21 +190,13 @@ struct ip_mreq_source { }; struct ip_msfilter { + __be32 imsf_multiaddr; + __be32 imsf_interface; + __u32 imsf_fmode; + __u32 imsf_numsrc; union { - struct { - __be32 imsf_multiaddr_aux; - __be32 imsf_interface_aux; - __u32 imsf_fmode_aux; - __u32 imsf_numsrc_aux; - __be32 imsf_slist[1]; - }; - struct { - __be32 imsf_multiaddr; - __be32 imsf_interface; - __u32 imsf_fmode; - __u32 imsf_numsrc; - __be32 imsf_slist_flex[]; - }; + __be32 imsf_slist[1]; + __DECLARE_FLEX_ARRAY(__be32, imsf_slist_flex); }; }; diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index ea6defacc1a7..ccb7f5dad59b 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -164,8 +164,6 @@ enum perf_event_sample_format { PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24, PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */ - - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; #define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) @@ -263,6 +261,17 @@ enum { PERF_BR_MAX, }; +/* + * Common branch speculation outcome classification + */ +enum { + PERF_BR_SPEC_NA = 0, /* Not available */ + PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ + PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ + PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ + PERF_BR_SPEC_MAX, +}; + enum { PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ @@ -282,11 +291,11 @@ enum { PERF_BR_PRIV_HV = 3, }; -#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 -#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 -#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 -#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 -#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 +#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 +#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 +#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 +#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 +#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ @@ -1397,6 +1406,7 @@ union perf_mem_data_src { * abort: aborting a hardware transaction * cycles: cycles from last branch (or 0 if not supported) * type: branch type + * spec: branch speculation info (or 0 if not supported) */ struct perf_branch_entry { __u64 from; @@ -1407,9 +1417,10 @@ struct perf_branch_entry { abort:1, /* transaction abort */ cycles:16, /* cycle count to last branch */ type:4, /* branch type */ + spec:2, /* branch speculation info */ new_type:4, /* additional branch type */ priv:3, /* privilege level */ - reserved:33; + reserved:31; }; union perf_sample_weight { diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 1500a0f58041..7cab2c65d3d7 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -124,7 +124,8 @@ struct statx { __u32 stx_dev_minor; /* 0x90 */ __u64 stx_mnt_id; - __u64 __spare2; + __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ + __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ /* 0xa0 */ __u64 __spare3[12]; /* Spare space for future expansion */ /* 0x100 */ @@ -152,6 +153,7 @@ struct statx { #define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ #define STATX_BTIME 0x00000800U /* Want/got stx_btime */ #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ +#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 3974a2a911cc..de6810e94abe 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -3,22 +3,6 @@ * Advanced Linux Sound Architecture - ALSA - Driver * Copyright (c) 1994-2003 by Jaroslav Kysela <perex@perex.cz>, * Abramo Bagnara <abramo@alsa-project.org> - * - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #ifndef _UAPI__SOUND_ASOUND_H diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 9c366b3a676d..6f28180ffeea 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -41,11 +41,14 @@ VMX_EXIT_REASONS = { 'EXCEPTION_NMI': 0, 'EXTERNAL_INTERRUPT': 1, 'TRIPLE_FAULT': 2, - 'PENDING_INTERRUPT': 7, + 'INIT_SIGNAL': 3, + 'SIPI_SIGNAL': 4, + 'INTERRUPT_WINDOW': 7, 'NMI_WINDOW': 8, 'TASK_SWITCH': 9, 'CPUID': 10, 'HLT': 12, + 'INVD': 13, 'INVLPG': 14, 'RDPMC': 15, 'RDTSC': 16, @@ -65,26 +68,48 @@ VMX_EXIT_REASONS = { 'MSR_READ': 31, 'MSR_WRITE': 32, 'INVALID_STATE': 33, + 'MSR_LOAD_FAIL': 34, 'MWAIT_INSTRUCTION': 36, + 'MONITOR_TRAP_FLAG': 37, 'MONITOR_INSTRUCTION': 39, 'PAUSE_INSTRUCTION': 40, 'MCE_DURING_VMENTRY': 41, 'TPR_BELOW_THRESHOLD': 43, 'APIC_ACCESS': 44, + 'EOI_INDUCED': 45, + 'GDTR_IDTR': 46, + 'LDTR_TR': 47, 'EPT_VIOLATION': 48, 'EPT_MISCONFIG': 49, + 'INVEPT': 50, + 'RDTSCP': 51, + 'PREEMPTION_TIMER': 52, + 'INVVPID': 53, 'WBINVD': 54, 'XSETBV': 55, 'APIC_WRITE': 56, + 'RDRAND': 57, 'INVPCID': 58, + 'VMFUNC': 59, + 'ENCLS': 60, + 'RDSEED': 61, + 'PML_FULL': 62, + 'XSAVES': 63, + 'XRSTORS': 64, + 'UMWAIT': 67, + 'TPAUSE': 68, + 'BUS_LOCK': 74, + 'NOTIFY': 75, } SVM_EXIT_REASONS = { 'READ_CR0': 0x000, + 'READ_CR2': 0x002, 'READ_CR3': 0x003, 'READ_CR4': 0x004, 'READ_CR8': 0x008, 'WRITE_CR0': 0x010, + 'WRITE_CR2': 0x012, 'WRITE_CR3': 0x013, 'WRITE_CR4': 0x014, 'WRITE_CR8': 0x018, @@ -105,6 +130,7 @@ SVM_EXIT_REASONS = { 'WRITE_DR6': 0x036, 'WRITE_DR7': 0x037, 'EXCP_BASE': 0x040, + 'LAST_EXCP': 0x05f, 'INTR': 0x060, 'NMI': 0x061, 'SMI': 0x062, @@ -151,21 +177,45 @@ SVM_EXIT_REASONS = { 'MWAIT': 0x08b, 'MWAIT_COND': 0x08c, 'XSETBV': 0x08d, + 'RDPRU': 0x08e, + 'EFER_WRITE_TRAP': 0x08f, + 'CR0_WRITE_TRAP': 0x090, + 'CR1_WRITE_TRAP': 0x091, + 'CR2_WRITE_TRAP': 0x092, + 'CR3_WRITE_TRAP': 0x093, + 'CR4_WRITE_TRAP': 0x094, + 'CR5_WRITE_TRAP': 0x095, + 'CR6_WRITE_TRAP': 0x096, + 'CR7_WRITE_TRAP': 0x097, + 'CR8_WRITE_TRAP': 0x098, + 'CR9_WRITE_TRAP': 0x099, + 'CR10_WRITE_TRAP': 0x09a, + 'CR11_WRITE_TRAP': 0x09b, + 'CR12_WRITE_TRAP': 0x09c, + 'CR13_WRITE_TRAP': 0x09d, + 'CR14_WRITE_TRAP': 0x09e, + 'CR15_WRITE_TRAP': 0x09f, + 'INVPCID': 0x0a2, 'NPF': 0x400, + 'AVIC_INCOMPLETE_IPI': 0x401, + 'AVIC_UNACCELERATED_ACCESS': 0x402, + 'VMGEXIT': 0x403, } -# EC definition of HSR (from arch/arm64/include/asm/kvm_arm.h) +# EC definition of HSR (from arch/arm64/include/asm/esr.h) AARCH64_EXIT_REASONS = { 'UNKNOWN': 0x00, - 'WFI': 0x01, + 'WFx': 0x01, 'CP15_32': 0x03, 'CP15_64': 0x04, 'CP14_MR': 0x05, 'CP14_LS': 0x06, 'FP_ASIMD': 0x07, 'CP10_ID': 0x08, + 'PAC': 0x09, 'CP14_64': 0x0C, - 'ILL_ISS': 0x0E, + 'BTI': 0x0D, + 'ILL': 0x0E, 'SVC32': 0x11, 'HVC32': 0x12, 'SMC32': 0x13, @@ -173,21 +223,26 @@ AARCH64_EXIT_REASONS = { 'HVC64': 0x16, 'SMC64': 0x17, 'SYS64': 0x18, - 'IABT': 0x20, - 'IABT_HYP': 0x21, + 'SVE': 0x19, + 'ERET': 0x1A, + 'FPAC': 0x1C, + 'SME': 0x1D, + 'IMP_DEF': 0x1F, + 'IABT_LOW': 0x20, + 'IABT_CUR': 0x21, 'PC_ALIGN': 0x22, - 'DABT': 0x24, - 'DABT_HYP': 0x25, + 'DABT_LOW': 0x24, + 'DABT_CUR': 0x25, 'SP_ALIGN': 0x26, 'FP_EXC32': 0x28, 'FP_EXC64': 0x2C, 'SERROR': 0x2F, - 'BREAKPT': 0x30, - 'BREAKPT_HYP': 0x31, - 'SOFTSTP': 0x32, - 'SOFTSTP_HYP': 0x33, - 'WATCHPT': 0x34, - 'WATCHPT_HYP': 0x35, + 'BREAKPT_LOW': 0x30, + 'BREAKPT_CUR': 0x31, + 'SOFTSTP_LOW': 0x32, + 'SOFTSTP_CUR': 0x33, + 'WATCHPT_LOW': 0x34, + 'WATCHPT_CUR': 0x35, 'BKPT32': 0x38, 'VECTOR32': 0x3A, 'BRK64': 0x3C, @@ -220,6 +275,19 @@ USERSPACE_EXIT_REASONS = { 'S390_TSCH': 22, 'EPR': 23, 'SYSTEM_EVENT': 24, + 'S390_STSI': 25, + 'IOAPIC_EOI': 26, + 'HYPERV': 27, + 'ARM_NISV': 28, + 'X86_RDMSR': 29, + 'X86_WRMSR': 30, + 'DIRTY_RING_FULL': 31, + 'AP_RESET_HOLD': 32, + 'X86_BUS_LOCK': 33, + 'XEN': 34, + 'RISCV_SBI': 35, + 'RISCV_CSR': 36, + 'NOTIFY': 37, } IOCTL_NUMBERS = { @@ -1756,7 +1824,7 @@ def assign_globals(): debugfs = '' for line in open('/proc/mounts'): - if line.split(' ')[0] == 'debugfs': + if line.split(' ')[2] == 'debugfs': debugfs = line.split(' ')[1] break if debugfs == '': diff --git a/tools/perf/Documentation/perf-arm-coresight.txt b/tools/perf/Documentation/arm-coresight.txt index c117fc50a2a9..c117fc50a2a9 100644 --- a/tools/perf/Documentation/perf-arm-coresight.txt +++ b/tools/perf/Documentation/arm-coresight.txt diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 6fd4b1384b97..898226ea8cad 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -588,6 +588,10 @@ ifndef NO_LIBELF ifeq ($(feature-libbpf-bpf_object__next_map), 1) CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP endif + $(call feature_check,libbpf-bpf_program__set_insns) + ifeq ($(feature-libbpf-bpf_program__set_insns), 1) + CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS + endif $(call feature_check,libbpf-btf__raw_data) ifeq ($(feature-libbpf-btf__raw_data), 1) CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA @@ -604,6 +608,7 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP + CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE endif diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 2bca64f96164..e9e0df4f9a61 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -228,8 +228,10 @@ 176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -179 common pread64 sys_pread64 compat_sys_ppc_pread64 -180 common pwrite64 sys_pwrite64 compat_sys_ppc_pwrite64 +179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 +179 64 pread64 sys_pread64 +180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 +180 64 pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -242,10 +244,11 @@ 188 common putpmsg sys_ni_syscall 189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit -191 common readahead sys_readahead compat_sys_ppc_readahead +191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead +191 64 readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 -193 32 truncate64 sys_truncate64 compat_sys_ppc_truncate64 -194 32 ftruncate64 sys_ftruncate64 compat_sys_ppc_ftruncate64 +193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 +194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 195 32 stat64 sys_stat64 196 32 lstat64 sys_lstat64 197 32 fstat64 sys_fstat64 @@ -288,7 +291,8 @@ 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address -233 common fadvise64 sys_fadvise64 compat_sys_ppc32_fadvise64 +233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 +233 64 fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 236 common epoll_create sys_epoll_create diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 52d254b1530c..e128b855ddde 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -649,7 +649,7 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size) static volatile int signr = -1; static volatile int child_finished; #ifdef HAVE_EVENTFD_SUPPORT -static int done_fd = -1; +static volatile int done_fd = -1; #endif static void sig_handler(int sig) @@ -661,19 +661,24 @@ static void sig_handler(int sig) done = 1; #ifdef HAVE_EVENTFD_SUPPORT -{ - u64 tmp = 1; - /* - * It is possible for this signal handler to run after done is checked - * in the main loop, but before the perf counter fds are polled. If this - * happens, the poll() will continue to wait even though done is set, - * and will only break out if either another signal is received, or the - * counters are ready for read. To ensure the poll() doesn't sleep when - * done is set, use an eventfd (done_fd) to wake up the poll(). - */ - if (write(done_fd, &tmp, sizeof(tmp)) < 0) - pr_err("failed to signal wakeup fd, error: %m\n"); -} + if (done_fd >= 0) { + u64 tmp = 1; + int orig_errno = errno; + + /* + * It is possible for this signal handler to run after done is + * checked in the main loop, but before the perf counter fds are + * polled. If this happens, the poll() will continue to wait + * even though done is set, and will only break out if either + * another signal is received, or the counters are ready for + * read. To ensure the poll() doesn't sleep when done is set, + * use an eventfd (done_fd) to wake up the poll(). + */ + if (write(done_fd, &tmp, sizeof(tmp)) < 0) + pr_err("failed to signal wakeup fd, error: %m\n"); + + errno = orig_errno; + } #endif // HAVE_EVENTFD_SUPPORT } @@ -2834,8 +2839,12 @@ out_free_threads: out_delete_session: #ifdef HAVE_EVENTFD_SUPPORT - if (done_fd >= 0) - close(done_fd); + if (done_fd >= 0) { + fd = done_fd; + done_fd = -1; + + close(fd); + } #endif zstd_fini(&session->zstd_data); perf_session__delete(session); diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 6ee44b18c6b5..eacca9a874e2 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -143,7 +143,7 @@ for i in $SYNC_CHECK_FILES; do done # diff with extra ignore lines -check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"' +check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))" -I"^#include <linux/cfi_types.h>"' check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' check arch/x86/include/asm/amd-ibs.h '-I "^#include [<\"]\(asm/\)*msr-index.h"' check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"' diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json index 6970203cb247..6443a061e22a 100644 --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json @@ -112,21 +112,21 @@ "MetricName": "indirect_branch" }, { - "MetricExpr": "(armv8_pmuv3_0@event\\=0x1014@ + armv8_pmuv3_0@event\\=0x1018@) / BR_MIS_PRED", + "MetricExpr": "(armv8_pmuv3_0@event\\=0x1013@ + armv8_pmuv3_0@event\\=0x1016@) / BR_MIS_PRED", "PublicDescription": "Push branch L3 topdown metric", "BriefDescription": "Push branch L3 topdown metric", "MetricGroup": "TopDownL3", "MetricName": "push_branch" }, { - "MetricExpr": "armv8_pmuv3_0@event\\=0x100c@ / BR_MIS_PRED", + "MetricExpr": "armv8_pmuv3_0@event\\=0x100d@ / BR_MIS_PRED", "PublicDescription": "Pop branch L3 topdown metric", "BriefDescription": "Pop branch L3 topdown metric", "MetricGroup": "TopDownL3", "MetricName": "pop_branch" }, { - "MetricExpr": "(BR_MIS_PRED - armv8_pmuv3_0@event\\=0x1010@ - armv8_pmuv3_0@event\\=0x1014@ - armv8_pmuv3_0@event\\=0x1018@ - armv8_pmuv3_0@event\\=0x100c@) / BR_MIS_PRED", + "MetricExpr": "(BR_MIS_PRED - armv8_pmuv3_0@event\\=0x1010@ - armv8_pmuv3_0@event\\=0x1013@ - armv8_pmuv3_0@event\\=0x1016@ - armv8_pmuv3_0@event\\=0x100d@) / BR_MIS_PRED", "PublicDescription": "Other branch L3 topdown metric", "BriefDescription": "Other branch L3 topdown metric", "MetricGroup": "TopDownL3", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json index 8ba3e81c9808..fe050d44374b 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json @@ -1,13 +1,13 @@ [ { "MetricName": "VEC_GROUP_PUMP_RETRY_RATIO_P01", - "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP01\\,chip\\=?@ / hv_24x7@PM_PB_VG_PUMP01\\,chip\\=?@) * 100", + "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP01\\,chip\\=?@ / (1 + hv_24x7@PM_PB_VG_PUMP01\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "VEC_GROUP_PUMP_RETRY_RATIO_P23", - "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP23\\,chip\\=?@ / hv_24x7@PM_PB_VG_PUMP23\\,chip\\=?@) * 100", + "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP23\\,chip\\=?@ / (1 + hv_24x7@PM_PB_VG_PUMP23\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, @@ -61,13 +61,13 @@ }, { "MetricName": "REMOTE_NODE_PUMPS_RETRIES_RATIO_P01", - "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP01\\,chip\\=?@ / hv_24x7@PM_PB_RNS_PUMP01\\,chip\\=?@) * 100", + "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP01\\,chip\\=?@ / (1 + hv_24x7@PM_PB_RNS_PUMP01\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "REMOTE_NODE_PUMPS_RETRIES_RATIO_P23", - "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP23\\,chip\\=?@ / hv_24x7@PM_PB_RNS_PUMP23\\,chip\\=?@) * 100", + "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP23\\,chip\\=?@ / (1 + hv_24x7@PM_PB_RNS_PUMP23\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, @@ -151,193 +151,193 @@ }, { "MetricName": "XLINK0_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK1_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK2_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK3_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK4_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK5_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK6_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK7_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK0_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK1_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK2_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK3_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK4_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK5_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK6_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "XLINK7_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK0_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK1_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK2_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK3_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK4_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK5_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK6_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK7_OUT_TOTAL_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK0_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK1_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK2_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK3_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK4_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK5_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK6_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, { "MetricName": "ALINK7_OUT_DATA_UTILIZATION", - "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", + "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100", "ScaleUnit": "1.063%", "AggregationMode": "PerChip" }, diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/pai.json b/tools/perf/pmu-events/arch/s390/cf_z16/pai_crypto.json index cf8563d059b9..cf8563d059b9 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z16/pai.json +++ b/tools/perf/pmu-events/arch/s390/cf_z16/pai_crypto.json diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 4c0aabbe33bd..f5ed7b1af419 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -526,6 +526,12 @@ test_kernel_trace() test_virtual_lbr() { echo "--- Test virtual LBR ---" + # Check if python script is supported + libpython=$(perf version --build-options | grep python | grep -cv OFF) + if [ "${libpython}" != "1" ] ; then + echo "SKIP: python scripting is not supported" + return 2 + fi # Python script to determine the maximum size of branch stacks cat << "_end_of_file_" > "${maxbrstack}" diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c index 110f0c609d84..5f5320f7c6e2 100644 --- a/tools/perf/trace/beauty/statx.c +++ b/tools/perf/trace/beauty/statx.c @@ -66,6 +66,7 @@ size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_a P_FLAG(BLOCKS); P_FLAG(BTIME); P_FLAG(MNT_ID); + P_FLAG(DIOALIGN); #undef P_FLAG diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 60d8beb662aa..46ada5ec3f9a 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -2325,11 +2325,19 @@ struct sym_args { bool near; }; +static bool kern_sym_name_match(const char *kname, const char *name) +{ + size_t n = strlen(name); + + return !strcmp(kname, name) || + (!strncmp(kname, name, n) && kname[n] == '\t'); +} + static bool kern_sym_match(struct sym_args *args, const char *name, char type) { /* A function with the same name, and global or the n'th found or any */ return kallsyms__is_function(type) && - !strcmp(name, args->name) && + kern_sym_name_match(name, args->name) && ((args->global && isupper(type)) || (args->selected && ++(args->cnt) == args->idx) || (!args->global && !args->selected)); diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index eee64ddb766d..cc7c1f90cf62 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -36,6 +36,11 @@ struct btf *btf__load_from_kernel_by_id(__u32 id) #endif #ifndef HAVE_LIBBPF_BPF_PROG_LOAD +LIBBPF_API int bpf_load_program(enum bpf_prog_type type, + const struct bpf_insn *insns, size_t insns_cnt, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz); + int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name __maybe_unused, const char *license, diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index d657594894cf..f4adeccdbbcb 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -36,6 +36,24 @@ #include <internal/xyarray.h> +#ifndef HAVE_LIBBPF_BPF_PROGRAM__SET_INSNS +int bpf_program__set_insns(struct bpf_program *prog __maybe_unused, + struct bpf_insn *new_insns __maybe_unused, size_t new_insn_cnt __maybe_unused) +{ + pr_err("%s: not support, update libbpf\n", __func__); + return -ENOTSUP; +} + +int libbpf_register_prog_handler(const char *sec __maybe_unused, + enum bpf_prog_type prog_type __maybe_unused, + enum bpf_attach_type exp_attach_type __maybe_unused, + const struct libbpf_prog_handler_opts *opts __maybe_unused) +{ + pr_err("%s: not support, update libbpf\n", __func__); + return -ENOTSUP; +} +#endif + /* temporarily disable libbpf deprecation warnings */ #pragma GCC diagnostic ignored "-Wdeprecated-declarations" diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h index aa0c5179836d..75e2248416f5 100644 --- a/tools/perf/util/include/linux/linkage.h +++ b/tools/perf/util/include/linux/linkage.h @@ -115,4 +115,17 @@ SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) #endif +// In the kernel sources (include/linux/cfi_types.h), this has a different +// definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang +// definition: +#ifndef SYM_TYPED_START +#define SYM_TYPED_START(name, linkage, align...) \ + SYM_START(name, linkage, align) +#endif + +#ifndef SYM_TYPED_FUNC_START +#define SYM_TYPED_FUNC_START(name) \ + SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + #endif /* PERF_LINUX_LINKAGE_H_ */ diff --git a/tools/power/pm-graph/README b/tools/power/pm-graph/README index e6020c0d59ec..3213dbe63b74 100644 --- a/tools/power/pm-graph/README +++ b/tools/power/pm-graph/README @@ -6,22 +6,22 @@ |_| |___/ |_| pm-graph: suspend/resume/boot timing analysis tools - Version: 5.9 + Version: 5.10 Author: Todd Brandt <todd.e.brandt@intel.com> - Home Page: https://01.org/pm-graph + Home Page: https://www.intel.com/content/www/us/en/developer/topic-technology/open/pm-graph/overview.html Report bugs/issues at bugzilla.kernel.org Tools/pm-graph - https://bugzilla.kernel.org/buglist.cgi?component=pm-graph&product=Tools Full documentation available online & in man pages - Getting Started: - https://01.org/pm-graph/documentation/getting-started + https://www.intel.com/content/www/us/en/developer/articles/technical/usage.html - - Config File Format: - https://01.org/pm-graph/documentation/3-config-file-format + - Feature Summary: + https://www.intel.com/content/www/us/en/developer/topic-technology/open/pm-graph/features.html - upstream version in git: - https://github.com/intel/pm-graph/ + git clone https://github.com/intel/pm-graph/ Table of Contents - Overview diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8 index 5126271de98a..643271b6fc6f 100644 --- a/tools/power/pm-graph/sleepgraph.8 +++ b/tools/power/pm-graph/sleepgraph.8 @@ -78,6 +78,9 @@ This helps maintain the consistency of test data for better comparison. If a wifi connection is available, check that it reconnects after resume. Include the reconnect time in the total resume time calculation and treat wifi timeouts as resume failures. +.TP +\fB-wifitrace\fR +Trace through the wifi reconnect time and include it in the timeline. .SS "advanced" .TP diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index 33981adcdd68..cfe343306e08 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -86,7 +86,7 @@ def ascii(text): # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '5.9' + version = '5.10' ansi = False rs = 0 display = '' @@ -100,6 +100,7 @@ class SystemValues: ftracelog = False acpidebug = True tstat = True + wifitrace = False mindevlen = 0.0001 mincglen = 0.0 cgphase = '' @@ -124,6 +125,7 @@ class SystemValues: epath = '/sys/kernel/debug/tracing/events/power/' pmdpath = '/sys/power/pm_debug_messages' s0ixpath = '/sys/module/intel_pmc_core/parameters/warn_on_s0ix_failures' + s0ixres = '/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us' acpipath='/sys/module/acpi/parameters/debug_level' traceevents = [ 'suspend_resume', @@ -180,6 +182,7 @@ class SystemValues: tmstart = 'SUSPEND START %Y%m%d-%H:%M:%S.%f' tmend = 'RESUME COMPLETE %Y%m%d-%H:%M:%S.%f' tracefuncs = { + 'async_synchronize_full': {}, 'sys_sync': {}, 'ksys_sync': {}, '__pm_notifier_call_chain': {}, @@ -304,6 +307,7 @@ class SystemValues: [2, 'suspendstats', 'sh', '-c', 'grep -v invalid /sys/power/suspend_stats/*'], [2, 'cpuidle', 'sh', '-c', 'grep -v invalid /sys/devices/system/cpu/cpu*/cpuidle/state*/s2idle/*'], [2, 'battery', 'sh', '-c', 'grep -v invalid /sys/class/power_supply/*/*'], + [2, 'thermal', 'sh', '-c', 'grep . /sys/class/thermal/thermal_zone*/temp'], ] cgblacklist = [] kprobes = dict() @@ -777,7 +781,7 @@ class SystemValues: return if not quiet: sysvals.printSystemInfo(False) - pprint('INITIALIZING FTRACE...') + pprint('INITIALIZING FTRACE') # turn trace off self.fsetVal('0', 'tracing_on') self.cleanupFtrace() @@ -841,7 +845,7 @@ class SystemValues: for name in self.dev_tracefuncs: self.defaultKprobe(name, self.dev_tracefuncs[name]) if not quiet: - pprint('INITIALIZING KPROBES...') + pprint('INITIALIZING KPROBES') self.addKprobes(self.verbose) if(self.usetraceevents): # turn trace events on @@ -1133,6 +1137,15 @@ class SystemValues: self.cfgdef[file] = fp.read().strip() fp.write(value) fp.close() + def s0ixSupport(self): + if not os.path.exists(self.s0ixres) or not os.path.exists(self.mempowerfile): + return False + fp = open(sysvals.mempowerfile, 'r') + data = fp.read().strip() + fp.close() + if '[s2idle]' in data: + return True + return False def haveTurbostat(self): if not self.tstat: return False @@ -1146,7 +1159,7 @@ class SystemValues: self.vprint(out) return True return False - def turbostat(self): + def turbostat(self, s0ixready): cmd = self.getExec('turbostat') rawout = keyline = valline = '' fullcmd = '%s -q -S echo freeze > %s' % (cmd, self.powerfile) @@ -1173,6 +1186,8 @@ class SystemValues: for key in keyline: idx = keyline.index(key) val = valline[idx] + if key == 'SYS%LPI' and not s0ixready and re.match('^[0\.]*$', val): + continue out.append('%s=%s' % (key, val)) return '|'.join(out) def netfixon(self, net='both'): @@ -1183,14 +1198,6 @@ class SystemValues: out = ascii(fp.read()).strip() fp.close() return out - def wifiRepair(self): - out = self.netfixon('wifi') - if not out or 'error' in out.lower(): - return '' - m = re.match('WIFI \S* ONLINE (?P<action>\S*)', out) - if not m: - return 'dead' - return m.group('action') def wifiDetails(self, dev): try: info = open('/sys/class/net/%s/device/uevent' % dev, 'r').read().strip() @@ -1220,11 +1227,6 @@ class SystemValues: return '%s reconnected %.2f' % \ (self.wifiDetails(dev), max(0, time.time() - start)) time.sleep(0.01) - if self.netfix: - res = self.wifiRepair() - if res: - timeout = max(0, time.time() - start) - return '%s %s %d' % (self.wifiDetails(dev), res, timeout) return '%s timeout %d' % (self.wifiDetails(dev), timeout) def errorSummary(self, errinfo, msg): found = False @@ -1346,6 +1348,20 @@ class SystemValues: for i in self.rslist: self.setVal(self.rstgt, i) pprint('runtime suspend settings restored on %d devices' % len(self.rslist)) + def start(self, pm): + if self.useftrace: + self.dlog('start ftrace tracing') + self.fsetVal('1', 'tracing_on') + if self.useprocmon: + self.dlog('start the process monitor') + pm.start() + def stop(self, pm): + if self.useftrace: + if self.useprocmon: + self.dlog('stop the process monitor') + pm.stop() + self.dlog('stop ftrace tracing') + self.fsetVal('0', 'tracing_on') sysvals = SystemValues() switchvalues = ['enable', 'disable', 'on', 'off', 'true', 'false', '1', '0'] @@ -1643,19 +1659,20 @@ class Data: ubiquitous = False if kprobename in dtf and 'ub' in dtf[kprobename]: ubiquitous = True - title = cdata+' '+rdata - mstr = '\(.*\) *(?P<args>.*) *\((?P<caller>.*)\+.* arg1=(?P<ret>.*)' - m = re.match(mstr, title) - if m: - c = m.group('caller') - a = m.group('args').strip() - r = m.group('ret') + mc = re.match('\(.*\) *(?P<args>.*)', cdata) + mr = re.match('\((?P<caller>\S*).* arg1=(?P<ret>.*)', rdata) + if mc and mr: + c = mr.group('caller').split('+')[0] + a = mc.group('args').strip() + r = mr.group('ret') if len(r) > 6: r = '' else: r = 'ret=%s ' % r if ubiquitous and c in dtf and 'ub' in dtf[c]: return False + else: + return False color = sysvals.kprobeColor(kprobename) e = DevFunction(displayname, a, c, r, start, end, ubiquitous, proc, pid, color) tgtdev['src'].append(e) @@ -1772,6 +1789,14 @@ class Data: e.time = self.trimTimeVal(e.time, t0, dT, left) e.end = self.trimTimeVal(e.end, t0, dT, left) e.length = e.end - e.time + if('cpuexec' in d): + cpuexec = dict() + for e in d['cpuexec']: + c0, cN = e + c0 = self.trimTimeVal(c0, t0, dT, left) + cN = self.trimTimeVal(cN, t0, dT, left) + cpuexec[(c0, cN)] = d['cpuexec'][e] + d['cpuexec'] = cpuexec for dir in ['suspend', 'resume']: list = [] for e in self.errorinfo[dir]: @@ -2086,75 +2111,43 @@ class Data: return d def addProcessUsageEvent(self, name, times): # get the start and end times for this process - maxC = 0 - tlast = 0 - start = -1 - end = -1 + cpuexec = dict() + tlast = start = end = -1 for t in sorted(times): - if tlast == 0: + if tlast < 0: tlast = t continue - if name in self.pstl[t]: - if start == -1 or tlast < start: + if name in self.pstl[t] and self.pstl[t][name] > 0: + if start < 0: start = tlast - if end == -1 or t > end: - end = t + end, key = t, (tlast, t) + maxj = (t - tlast) * 1024.0 + cpuexec[key] = min(1.0, float(self.pstl[t][name]) / maxj) tlast = t - if start == -1 or end == -1: - return 0 + if start < 0 or end < 0: + return # add a new action for this process and get the object out = self.newActionGlobal(name, start, end, -3) - if not out: - return 0 - phase, devname = out - dev = self.dmesg[phase]['list'][devname] - # get the cpu exec data - tlast = 0 - clast = 0 - cpuexec = dict() - for t in sorted(times): - if tlast == 0 or t <= start or t > end: - tlast = t - continue - list = self.pstl[t] - c = 0 - if name in list: - c = list[name] - if c > maxC: - maxC = c - if c != clast: - key = (tlast, t) - cpuexec[key] = c - tlast = t - clast = c - dev['cpuexec'] = cpuexec - return maxC + if out: + phase, devname = out + dev = self.dmesg[phase]['list'][devname] + dev['cpuexec'] = cpuexec def createProcessUsageEvents(self): - # get an array of process names - proclist = [] - for t in sorted(self.pstl): - pslist = self.pstl[t] - for ps in sorted(pslist): - if ps not in proclist: - proclist.append(ps) - # get a list of data points for suspend and resume - tsus = [] - tres = [] + # get an array of process names and times + proclist = {'sus': dict(), 'res': dict()} + tdata = {'sus': [], 'res': []} for t in sorted(self.pstl): - if t < self.tSuspended: - tsus.append(t) - else: - tres.append(t) + dir = 'sus' if t < self.tSuspended else 'res' + for ps in sorted(self.pstl[t]): + if ps not in proclist[dir]: + proclist[dir][ps] = 0 + tdata[dir].append(t) # process the events for suspend and resume - if len(proclist) > 0: + if len(proclist['sus']) > 0 or len(proclist['res']) > 0: sysvals.vprint('Process Execution:') - for ps in proclist: - c = self.addProcessUsageEvent(ps, tsus) - if c > 0: - sysvals.vprint('%25s (sus): %d' % (ps, c)) - c = self.addProcessUsageEvent(ps, tres) - if c > 0: - sysvals.vprint('%25s (res): %d' % (ps, c)) + for dir in ['sus', 'res']: + for ps in sorted(proclist[dir]): + self.addProcessUsageEvent(ps, tdata[dir]) def handleEndMarker(self, time, msg=''): dm = self.dmesg self.setEnd(time, msg) @@ -3218,7 +3211,7 @@ class ProcessMonitor: # markers, and/or kprobes required for primary parsing. def doesTraceLogHaveTraceEvents(): kpcheck = ['_cal: (', '_ret: ('] - techeck = ['suspend_resume', 'device_pm_callback'] + techeck = ['suspend_resume', 'device_pm_callback', 'tracing_mark_write'] tmcheck = ['SUSPEND START', 'RESUME COMPLETE'] sysvals.usekprobes = False fp = sysvals.openlog(sysvals.ftracefile, 'r') @@ -3241,7 +3234,7 @@ def doesTraceLogHaveTraceEvents(): check.remove(i) tmcheck = check fp.close() - sysvals.usetraceevents = True if len(techeck) < 2 else False + sysvals.usetraceevents = True if len(techeck) < 3 else False sysvals.usetracemarkers = True if len(tmcheck) == 0 else False # Function: appendIncompleteTraceLog @@ -3456,6 +3449,8 @@ def parseTraceLog(live=False): continue # process cpu exec line if t.type == 'tracing_mark_write': + if t.name == 'CMD COMPLETE' and data.tKernRes == 0: + data.tKernRes = t.time m = re.match(tp.procexecfmt, t.name) if(m): parts, msg = 1, m.group('ps') @@ -3674,6 +3669,9 @@ def parseTraceLog(live=False): e = next((x for x in reversed(tp.ktemp[key]) if x['end'] < 0), 0) if not e: continue + if (t.time - e['begin']) * 1000 < sysvals.mindevlen: + tp.ktemp[key].pop() + continue e['end'] = t.time e['rdata'] = kprobedata # end of kernel resume @@ -4213,6 +4211,8 @@ def callgraphHTML(sv, hf, num, cg, title, color, devid): fmt = '<n>(%.3f ms @ '+sv.timeformat+')</n>' flen = fmt % (line.length*1000, line.time) if line.isLeaf(): + if line.length * 1000 < sv.mincglen: + continue hf.write(html_func_leaf.format(line.name, flen)) elif line.freturn: hf.write(html_func_end) @@ -4827,14 +4827,11 @@ def createHTML(testruns, testfail): if('cpuexec' in dev): for t in sorted(dev['cpuexec']): start, end = t - j = float(dev['cpuexec'][t]) / 5 - if j > 1.0: - j = 1.0 height = '%.3f' % (rowheight/3) top = '%.3f' % (rowtop + devtl.scaleH + 2*rowheight/3) left = '%f' % (((start-m0)*100)/mTotal) width = '%f' % ((end-start)*100/mTotal) - color = 'rgba(255, 0, 0, %f)' % j + color = 'rgba(255, 0, 0, %f)' % dev['cpuexec'][t] devtl.html += \ html_cpuexec.format(left, top, height, width, color) if('src' not in dev): @@ -5453,17 +5450,9 @@ def executeSuspend(quiet=False): call('sync', shell=True) sv.dlog('read dmesg') sv.initdmesg() - # start ftrace - if sv.useftrace: - if not quiet: - pprint('START TRACING') - sv.dlog('start ftrace tracing') - sv.fsetVal('1', 'tracing_on') - if sv.useprocmon: - sv.dlog('start the process monitor') - pm.start() - sv.dlog('run the cmdinfo list before') + sv.dlog('cmdinfo before') sv.cmdinfo(True) + sv.start(pm) # execute however many s/r runs requested for count in range(1,sv.execcount+1): # x2delay in between test runs @@ -5500,6 +5489,7 @@ def executeSuspend(quiet=False): if res != 0: tdata['error'] = 'cmd returned %d' % res else: + s0ixready = sv.s0ixSupport() mode = sv.suspendmode if sv.memmode and os.path.exists(sv.mempowerfile): mode = 'mem' @@ -5509,9 +5499,10 @@ def executeSuspend(quiet=False): sv.testVal(sv.diskpowerfile, 'radio', sv.diskmode) if sv.acpidebug: sv.testVal(sv.acpipath, 'acpi', '0xe') - if mode == 'freeze' and sv.haveTurbostat(): + if ((mode == 'freeze') or (sv.memmode == 's2idle')) \ + and sv.haveTurbostat(): # execution will pause here - turbo = sv.turbostat() + turbo = sv.turbostat(s0ixready) if turbo: tdata['turbo'] = turbo else: @@ -5522,7 +5513,8 @@ def executeSuspend(quiet=False): pf.close() except Exception as e: tdata['error'] = str(e) - sv.dlog('system returned from resume') + sv.fsetVal('CMD COMPLETE', 'trace_marker') + sv.dlog('system returned') # reset everything sv.testVal('restoreall') if(sv.rtcwake): @@ -5535,33 +5527,29 @@ def executeSuspend(quiet=False): sv.fsetVal('WAIT END', 'trace_marker') # return from suspend pprint('RESUME COMPLETE') - sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker') + if(count < sv.execcount): + sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker') + elif(not sv.wifitrace): + sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker') + sv.stop(pm) if sv.wifi and wifi: tdata['wifi'] = sv.pollWifi(wifi) sv.dlog('wifi check, %s' % tdata['wifi']) - if sv.netfix: - netfixout = sv.netfixon('wired') - elif sv.netfix: - netfixout = sv.netfixon() - if sv.netfix and netfixout: - tdata['netfix'] = netfixout + if(count == sv.execcount and sv.wifitrace): + sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker') + sv.stop(pm) + if sv.netfix: + tdata['netfix'] = sv.netfixon() sv.dlog('netfix, %s' % tdata['netfix']) if(sv.suspendmode == 'mem' or sv.suspendmode == 'command'): sv.dlog('read the ACPI FPDT') tdata['fw'] = getFPDT(False) testdata.append(tdata) - sv.dlog('run the cmdinfo list after') + sv.dlog('cmdinfo after') cmdafter = sv.cmdinfo(False) - # stop ftrace - if sv.useftrace: - if sv.useprocmon: - sv.dlog('stop the process monitor') - pm.stop() - sv.fsetVal('0', 'tracing_on') # grab a copy of the dmesg output if not quiet: pprint('CAPTURING DMESG') - sysvals.dlog('EXECUTION TRACE END') sv.getdmesg(testdata) # grab a copy of the ftrace output if sv.useftrace: @@ -6350,6 +6338,8 @@ def data_from_html(file, outpath, issues, fulldetail=False): if not m: continue name, time, phase = m.group('n'), m.group('t'), m.group('p') + if name == 'async_synchronize_full': + continue if ' async' in name or ' sync' in name: name = ' '.join(name.split(' ')[:-1]) if phase.startswith('suspend'): @@ -6701,6 +6691,7 @@ def printHelp(): ' -skiphtml Run the test and capture the trace logs, but skip the timeline (default: disabled)\n'\ ' -result fn Export a results table to a text file for parsing.\n'\ ' -wifi If a wifi connection is available, check that it reconnects after resume.\n'\ + ' -wifitrace Trace kernel execution through wifi reconnect.\n'\ ' -netfix Use netfix to reset the network in the event it fails to resume.\n'\ ' [testprep]\n'\ ' -sync Sync the filesystems before starting the test\n'\ @@ -6828,6 +6819,8 @@ if __name__ == '__main__': sysvals.sync = True elif(arg == '-wifi'): sysvals.wifi = True + elif(arg == '-wifitrace'): + sysvals.wifitrace = True elif(arg == '-netfix'): sysvals.netfix = True elif(arg == '-gzip'): diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index a072b2d3e726..7edce12fd2ce 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -12,30 +12,62 @@ #include "mock.h" #define NR_CXL_HOST_BRIDGES 2 +#define NR_CXL_SINGLE_HOST 1 #define NR_CXL_ROOT_PORTS 2 #define NR_CXL_SWITCH_PORTS 2 #define NR_CXL_PORT_DECODERS 8 static struct platform_device *cxl_acpi; static struct platform_device *cxl_host_bridge[NR_CXL_HOST_BRIDGES]; -static struct platform_device - *cxl_root_port[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; -static struct platform_device - *cxl_switch_uport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; -static struct platform_device - *cxl_switch_dport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * - NR_CXL_SWITCH_PORTS]; -struct platform_device - *cxl_mem[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * NR_CXL_SWITCH_PORTS]; +#define NR_MULTI_ROOT (NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS) +static struct platform_device *cxl_root_port[NR_MULTI_ROOT]; +static struct platform_device *cxl_switch_uport[NR_MULTI_ROOT]; +#define NR_MEM_MULTI \ + (NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * NR_CXL_SWITCH_PORTS) +static struct platform_device *cxl_switch_dport[NR_MEM_MULTI]; + +static struct platform_device *cxl_hb_single[NR_CXL_SINGLE_HOST]; +static struct platform_device *cxl_root_single[NR_CXL_SINGLE_HOST]; +static struct platform_device *cxl_swu_single[NR_CXL_SINGLE_HOST]; +#define NR_MEM_SINGLE (NR_CXL_SINGLE_HOST * NR_CXL_SWITCH_PORTS) +static struct platform_device *cxl_swd_single[NR_MEM_SINGLE]; + +struct platform_device *cxl_mem[NR_MEM_MULTI]; +struct platform_device *cxl_mem_single[NR_MEM_SINGLE]; + + +static inline bool is_multi_bridge(struct device *dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++) + if (&cxl_host_bridge[i]->dev == dev) + return true; + return false; +} + +static inline bool is_single_bridge(struct device *dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) + if (&cxl_hb_single[i]->dev == dev) + return true; + return false; +} static struct acpi_device acpi0017_mock; -static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES] = { +static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES + NR_CXL_SINGLE_HOST] = { [0] = { .handle = &host_bridge[0], }, [1] = { .handle = &host_bridge[1], }, + [2] = { + .handle = &host_bridge[2], + }, + }; static bool is_mock_dev(struct device *dev) @@ -45,6 +77,9 @@ static bool is_mock_dev(struct device *dev) for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) if (dev == &cxl_mem[i]->dev) return true; + for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) + if (dev == &cxl_mem_single[i]->dev) + return true; if (dev == &cxl_acpi->dev) return true; return false; @@ -66,7 +101,7 @@ static bool is_mock_adev(struct acpi_device *adev) static struct { struct acpi_table_cedt cedt; - struct acpi_cedt_chbs chbs[NR_CXL_HOST_BRIDGES]; + struct acpi_cedt_chbs chbs[NR_CXL_HOST_BRIDGES + NR_CXL_SINGLE_HOST]; struct { struct acpi_cedt_cfmws cfmws; u32 target[1]; @@ -83,6 +118,10 @@ static struct { struct acpi_cedt_cfmws cfmws; u32 target[2]; } cfmws3; + struct { + struct acpi_cedt_cfmws cfmws; + u32 target[1]; + } cfmws4; } __packed mock_cedt = { .cedt = { .header = { @@ -107,6 +146,14 @@ static struct { .uid = 1, .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, }, + .chbs[2] = { + .header = { + .type = ACPI_CEDT_TYPE_CHBS, + .length = sizeof(mock_cedt.chbs[0]), + }, + .uid = 2, + .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, + }, .cfmws0 = { .cfmws = { .header = { @@ -167,13 +214,29 @@ static struct { }, .target = { 0, 1, }, }, + .cfmws4 = { + .cfmws = { + .header = { + .type = ACPI_CEDT_TYPE_CFMWS, + .length = sizeof(mock_cedt.cfmws4), + }, + .interleave_ways = 0, + .granularity = 4, + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + ACPI_CEDT_CFMWS_RESTRICT_PMEM, + .qtg_id = 4, + .window_size = SZ_256M * 4UL, + }, + .target = { 2 }, + }, }; -struct acpi_cedt_cfmws *mock_cfmws[4] = { +struct acpi_cedt_cfmws *mock_cfmws[] = { [0] = &mock_cedt.cfmws0.cfmws, [1] = &mock_cedt.cfmws1.cfmws, [2] = &mock_cedt.cfmws2.cfmws, [3] = &mock_cedt.cfmws3.cfmws, + [4] = &mock_cedt.cfmws4.cfmws, }; struct cxl_mock_res { @@ -304,6 +367,9 @@ static bool is_mock_bridge(struct device *dev) for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++) if (dev == &cxl_host_bridge[i]->dev) return true; + for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) + if (dev == &cxl_hb_single[i]->dev) + return true; return false; } @@ -326,6 +392,18 @@ static bool is_mock_port(struct device *dev) if (dev == &cxl_switch_dport[i]->dev) return true; + for (i = 0; i < ARRAY_SIZE(cxl_root_single); i++) + if (dev == &cxl_root_single[i]->dev) + return true; + + for (i = 0; i < ARRAY_SIZE(cxl_swu_single); i++) + if (dev == &cxl_swu_single[i]->dev) + return true; + + for (i = 0; i < ARRAY_SIZE(cxl_swd_single); i++) + if (dev == &cxl_swd_single[i]->dev) + return true; + if (is_cxl_memdev(dev)) return is_mock_dev(dev->parent); @@ -561,11 +639,31 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port) int i, array_size; if (port->depth == 1) { - array_size = ARRAY_SIZE(cxl_root_port); - array = cxl_root_port; + if (is_multi_bridge(port->uport)) { + array_size = ARRAY_SIZE(cxl_root_port); + array = cxl_root_port; + } else if (is_single_bridge(port->uport)) { + array_size = ARRAY_SIZE(cxl_root_single); + array = cxl_root_single; + } else { + dev_dbg(&port->dev, "%s: unknown bridge type\n", + dev_name(port->uport)); + return -ENXIO; + } } else if (port->depth == 2) { - array_size = ARRAY_SIZE(cxl_switch_dport); - array = cxl_switch_dport; + struct cxl_port *parent = to_cxl_port(port->dev.parent); + + if (is_multi_bridge(parent->uport)) { + array_size = ARRAY_SIZE(cxl_switch_dport); + array = cxl_switch_dport; + } else if (is_single_bridge(parent->uport)) { + array_size = ARRAY_SIZE(cxl_swd_single); + array = cxl_swd_single; + } else { + dev_dbg(&port->dev, "%s: unknown bridge type\n", + dev_name(port->uport)); + return -ENXIO; + } } else { dev_WARN_ONCE(&port->dev, 1, "unexpected depth %d\n", port->depth); @@ -576,8 +674,12 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port) struct platform_device *pdev = array[i]; struct cxl_dport *dport; - if (pdev->dev.parent != port->uport) + if (pdev->dev.parent != port->uport) { + dev_dbg(&port->dev, "%s: mismatch parent %s\n", + dev_name(port->uport), + dev_name(pdev->dev.parent)); continue; + } dport = devm_cxl_add_dport(port, &pdev->dev, pdev->id, CXL_RESOURCE_NONE); @@ -627,6 +729,157 @@ static void mock_companion(struct acpi_device *adev, struct device *dev) #define SZ_512G (SZ_64G * 8) #endif +static __init int cxl_single_init(void) +{ + int i, rc; + + for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) { + struct acpi_device *adev = + &host_bridge[NR_CXL_HOST_BRIDGES + i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_host_bridge", + NR_CXL_HOST_BRIDGES + i); + if (!pdev) + goto err_bridge; + + mock_companion(adev, &pdev->dev); + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_bridge; + } + + cxl_hb_single[i] = pdev; + rc = sysfs_create_link(&pdev->dev.kobj, &pdev->dev.kobj, + "physical_node"); + if (rc) + goto err_bridge; + } + + for (i = 0; i < ARRAY_SIZE(cxl_root_single); i++) { + struct platform_device *bridge = + cxl_hb_single[i % ARRAY_SIZE(cxl_hb_single)]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_root_port", + NR_MULTI_ROOT + i); + if (!pdev) + goto err_port; + pdev->dev.parent = &bridge->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_port; + } + cxl_root_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_swu_single); i++) { + struct platform_device *root_port = cxl_root_single[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_switch_uport", + NR_MULTI_ROOT + i); + if (!pdev) + goto err_uport; + pdev->dev.parent = &root_port->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_uport; + } + cxl_swu_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_swd_single); i++) { + struct platform_device *uport = + cxl_swu_single[i % ARRAY_SIZE(cxl_swu_single)]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_switch_dport", + i + NR_MEM_MULTI); + if (!pdev) + goto err_dport; + pdev->dev.parent = &uport->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_dport; + } + cxl_swd_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) { + struct platform_device *dport = cxl_swd_single[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_mem", NR_MEM_MULTI + i); + if (!pdev) + goto err_mem; + pdev->dev.parent = &dport->dev; + set_dev_node(&pdev->dev, i % 2); + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_mem; + } + cxl_mem_single[i] = pdev; + } + + return 0; + +err_mem: + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); +err_dport: + for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swd_single[i]); +err_uport: + for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swu_single[i]); +err_port: + for (i = ARRAY_SIZE(cxl_root_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_root_single[i]); +err_bridge: + for (i = ARRAY_SIZE(cxl_hb_single) - 1; i >= 0; i--) { + struct platform_device *pdev = cxl_hb_single[i]; + + if (!pdev) + continue; + sysfs_remove_link(&pdev->dev.kobj, "physical_node"); + platform_device_unregister(cxl_hb_single[i]); + } + + return rc; +} + +static void cxl_single_exit(void) +{ + int i; + + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); + for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swd_single[i]); + for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swu_single[i]); + for (i = ARRAY_SIZE(cxl_root_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_root_single[i]); + for (i = ARRAY_SIZE(cxl_hb_single) - 1; i >= 0; i--) { + struct platform_device *pdev = cxl_hb_single[i]; + + if (!pdev) + continue; + sysfs_remove_link(&pdev->dev.kobj, "physical_node"); + platform_device_unregister(cxl_hb_single[i]); + } +} + static __init int cxl_test_init(void) { int rc, i; @@ -695,7 +948,7 @@ static __init int cxl_test_init(void) pdev = platform_device_alloc("cxl_switch_uport", i); if (!pdev) - goto err_port; + goto err_uport; pdev->dev.parent = &root_port->dev; rc = platform_device_add(pdev); @@ -713,7 +966,7 @@ static __init int cxl_test_init(void) pdev = platform_device_alloc("cxl_switch_dport", i); if (!pdev) - goto err_port; + goto err_dport; pdev->dev.parent = &uport->dev; rc = platform_device_add(pdev); @@ -724,7 +977,6 @@ static __init int cxl_test_init(void) cxl_switch_dport[i] = pdev; } - BUILD_BUG_ON(ARRAY_SIZE(cxl_mem) != ARRAY_SIZE(cxl_switch_dport)); for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) { struct platform_device *dport = cxl_switch_dport[i]; struct platform_device *pdev; @@ -743,9 +995,13 @@ static __init int cxl_test_init(void) cxl_mem[i] = pdev; } + rc = cxl_single_init(); + if (rc) + goto err_mem; + cxl_acpi = platform_device_alloc("cxl_acpi", 0); if (!cxl_acpi) - goto err_mem; + goto err_single; mock_companion(&acpi0017_mock, &cxl_acpi->dev); acpi0017_mock.dev.bus = &platform_bus_type; @@ -758,6 +1014,8 @@ static __init int cxl_test_init(void) err_add: platform_device_put(cxl_acpi); +err_single: + cxl_single_exit(); err_mem: for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) platform_device_unregister(cxl_mem[i]); @@ -793,6 +1051,7 @@ static __exit void cxl_test_exit(void) int i; platform_device_unregister(cxl_acpi); + cxl_single_exit(); for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) platform_device_unregister(cxl_mem[i]); for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 0464b2c6c1e4..f07aef7c592c 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -49,6 +49,7 @@ TARGETS += net TARGETS += net/af_unix TARGETS += net/forwarding TARGETS += net/mptcp +TARGETS += net/openvswitch TARGETS += netfilter TARGETS += nsfs TARGETS += pidfd diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 127b8caa3dc1..24dd6214394e 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3936,6 +3936,19 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid type_id", }, { + .descr = "decl_tag test #16, func proto, return type", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), 2), (-1), /* [3] */ + BTF_FUNC_PROTO_ENC(3, 0), /* [4] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag1"), + .btf_load_err = true, + .err_str = "Invalid return type", +}, +{ .descr = "type_tag test #1", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_success.c b/tools/testing/selftests/bpf/progs/user_ringbuf_success.c index 099c23d9aa21..b39093dd5715 100644 --- a/tools/testing/selftests/bpf/progs/user_ringbuf_success.c +++ b/tools/testing/selftests/bpf/progs/user_ringbuf_success.c @@ -47,14 +47,14 @@ record_sample(struct bpf_dynptr *dynptr, void *context) if (status) { bpf_printk("bpf_dynptr_read() failed: %d\n", status); err = 1; - return 0; + return 1; } } else { sample = bpf_dynptr_data(dynptr, 0, sizeof(*sample)); if (!sample) { bpf_printk("Unexpectedly failed to get sample\n"); err = 2; - return 0; + return 1; } stack_sample = *sample; } diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index e9dab5f9d773..6b8d2e2f23c2 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -7,6 +7,8 @@ TEST_PROGS := \ bond-lladdr-target.sh \ dev_addr_lists.sh -TEST_FILES := lag_lib.sh +TEST_FILES := \ + lag_lib.sh \ + net_forwarding_lib.sh include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh index e6fa24eded5b..5cfe7d8ebc25 100755 --- a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh +++ b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh @@ -14,7 +14,7 @@ ALL_TESTS=" REQUIRE_MZ=no NUM_NETIFS=0 lib_dir=$(dirname "$0") -source "$lib_dir"/../../../net/forwarding/lib.sh +source "$lib_dir"/net_forwarding_lib.sh source "$lib_dir"/lag_lib.sh diff --git a/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh b/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh new file mode 120000 index 000000000000..39c96828c5ef --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh @@ -0,0 +1 @@ +../../../net/forwarding/lib.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh index dca8be6092b9..a1f269ee84da 100755 --- a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh +++ b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh @@ -18,8 +18,8 @@ NUM_NETIFS=1 REQUIRE_JQ="no" REQUIRE_MZ="no" NETIF_CREATE="no" -lib_dir=$(dirname $0)/../../../net/forwarding -source $lib_dir/lib.sh +lib_dir=$(dirname "$0") +source "$lib_dir"/lib.sh cleanup() { echo "Cleaning up" diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile index 642d8df1c137..6a86e61e8bfe 100644 --- a/tools/testing/selftests/drivers/net/team/Makefile +++ b/tools/testing/selftests/drivers/net/team/Makefile @@ -3,4 +3,8 @@ TEST_PROGS := dev_addr_lists.sh +TEST_FILES := \ + lag_lib.sh \ + net_forwarding_lib.sh + include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh index debda7262956..33913112d5ca 100755 --- a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh +++ b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh @@ -11,14 +11,14 @@ ALL_TESTS=" REQUIRE_MZ=no NUM_NETIFS=0 lib_dir=$(dirname "$0") -source "$lib_dir"/../../../net/forwarding/lib.sh +source "$lib_dir"/net_forwarding_lib.sh -source "$lib_dir"/../bonding/lag_lib.sh +source "$lib_dir"/lag_lib.sh destroy() { - local ifnames=(dummy0 dummy1 team0 mv0) + local ifnames=(dummy1 dummy2 team0 mv0) local ifname for ifname in "${ifnames[@]}"; do diff --git a/tools/testing/selftests/drivers/net/team/lag_lib.sh b/tools/testing/selftests/drivers/net/team/lag_lib.sh new file mode 120000 index 000000000000..e1347a10afde --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/lag_lib.sh @@ -0,0 +1 @@ +../bonding/lag_lib.sh
\ No newline at end of file diff --git a/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh b/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh new file mode 120000 index 000000000000..39c96828c5ef --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh @@ -0,0 +1 @@ +../../../net/forwarding/lib.sh
\ No newline at end of file diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc index db522577ff78..d3a79da215c8 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Generic dynamic event - check if duplicate events are caught -# requires: dynamic_events "e[:[<group>/]<event>] <attached-group>.<attached-event> [<args>]":README +# requires: dynamic_events "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README echo 0 > events/enable diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-eprobe.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-eprobe.tc index 914fe2e5d030..6461c375694f 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-eprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-eprobe.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test inter-event histogram trigger eprobe on synthetic event -# requires: dynamic_events synthetic_events events/syscalls/sys_enter_openat/hist "e[:[<group>/]<event>] <attached-group>.<attached-event> [<args>]":README +# requires: dynamic_events synthetic_events events/syscalls/sys_enter_openat/hist "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README echo 0 > events/enable diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 732149011692..5a0e0df8de9b 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -3,11 +3,11 @@ INCLUDES := -I../include -I../../ -I../../../../../usr/include/ CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) $(KHDR_INCLUDES) LDLIBS := -lpthread -lrt -HEADERS := \ +LOCAL_HDRS := \ ../include/futextest.h \ ../include/atomic.h \ ../include/logging.h -TEST_GEN_FILES := \ +TEST_GEN_PROGS := \ futex_wait_timeout \ futex_wait_wouldblock \ futex_requeue_pi \ @@ -24,5 +24,3 @@ TEST_PROGS := run.sh top_srcdir = ../../../../.. DEFAULT_INSTALL_HDR_PATH := 1 include ../../lib.mk - -$(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile index 39f0fa2a8fd6..05d66ef50c97 100644 --- a/tools/testing/selftests/intel_pstate/Makefile +++ b/tools/testing/selftests/intel_pstate/Makefile @@ -2,10 +2,10 @@ CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE LDLIBS += -lm -uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +ARCH ?= $(shell uname -m 2>/dev/null || echo not) +ARCH_PROCESSED := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/) -ifeq (x86,$(ARCH)) +ifeq (x86,$(ARCH_PROCESSED)) TEST_GEN_FILES := msr aperf endif diff --git a/tools/testing/selftests/kexec/Makefile b/tools/testing/selftests/kexec/Makefile index 806a150648c3..67fe7a46cb62 100644 --- a/tools/testing/selftests/kexec/Makefile +++ b/tools/testing/selftests/kexec/Makefile @@ -1,10 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only # Makefile for kexec tests -uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +ARCH ?= $(shell uname -m 2>/dev/null || echo not) +ARCH_PROCESSED := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/) -ifeq ($(ARCH),$(filter $(ARCH),x86 ppc64le)) +ifeq ($(ARCH_PROCESSED),$(filter $(ARCH_PROCESSED),x86 ppc64le)) TEST_PROGS := test_kexec_load.sh test_kexec_file_load.sh TEST_FILES := kexec_common_lib.sh diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 2f0d705db9db..082855d94c72 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -16,16 +16,18 @@ /x86_64/cpuid_test /x86_64/cr4_cpuid_sync_test /x86_64/debug_regs -/x86_64/evmcs_test -/x86_64/emulator_error_test +/x86_64/exit_on_emulation_failure_test /x86_64/fix_hypercall_test /x86_64/get_msr_index_features /x86_64/kvm_clock_test /x86_64/kvm_pv_test /x86_64/hyperv_clock /x86_64/hyperv_cpuid +/x86_64/hyperv_evmcs /x86_64/hyperv_features +/x86_64/hyperv_ipi /x86_64/hyperv_svm_test +/x86_64/hyperv_tlb_flush /x86_64/max_vcpuid_cap_test /x86_64/mmio_warning_test /x86_64/monitor_mwait_test @@ -36,11 +38,13 @@ /x86_64/set_boot_cpu_id /x86_64/set_sregs_test /x86_64/sev_migrate_tests +/x86_64/smaller_maxphyaddr_emulation_test /x86_64/smm_test /x86_64/state_test /x86_64/svm_vmcall_test /x86_64/svm_int_ctl_test /x86_64/svm_nested_soft_inject_test +/x86_64/svm_nested_shutdown_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test /x86_64/tsc_scaling_sync diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 0172eb6cb6ee..2275ba861e0e 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -43,16 +43,18 @@ LIBKVM += lib/elf.c LIBKVM += lib/guest_modes.c LIBKVM += lib/io.c LIBKVM += lib/kvm_util.c -LIBKVM += lib/perf_test_util.c +LIBKVM += lib/memstress.c LIBKVM += lib/rbtree.c LIBKVM += lib/sparsebit.c LIBKVM += lib/test_util.c +LIBKVM += lib/ucall_common.c LIBKVM_STRING += lib/string_override.c LIBKVM_x86_64 += lib/x86_64/apic.c LIBKVM_x86_64 += lib/x86_64/handlers.S -LIBKVM_x86_64 += lib/x86_64/perf_test_util.c +LIBKVM_x86_64 += lib/x86_64/hyperv.c +LIBKVM_x86_64 += lib/x86_64/memstress.c LIBKVM_x86_64 += lib/x86_64/processor.c LIBKVM_x86_64 += lib/x86_64/svm.c LIBKVM_x86_64 += lib/x86_64/ucall.c @@ -80,13 +82,15 @@ TEST_PROGS_x86_64 += x86_64/nx_huge_pages_test.sh TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features -TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test -TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test +TEST_GEN_PROGS_x86_64 += x86_64/exit_on_emulation_failure_test TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_evmcs TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_ipi TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_tlb_flush TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test @@ -96,11 +100,13 @@ TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test +TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_shutdown_test TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c index 6f9c1f19c7f6..b1d2158c0b6d 100644 --- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c +++ b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c @@ -158,12 +158,9 @@ int main(void) TEST_REQUIRE(vcpu_aarch64_only(vcpu)); - ucall_init(vm, NULL); - test_user_raz_wi(vcpu); test_user_raz_invariant(vcpu); test_guest_raz(vcpu); - ucall_uninit(vm); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 574eb73f0e90..f2a96779716a 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -375,7 +375,6 @@ static struct kvm_vm *test_vm_create(void) for (i = 0; i < nr_vcpus; i++) vcpu_init_descriptor_tables(vcpus[i]); - ucall_init(vm, NULL); test_init_timer_irq(vm); gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3"); @@ -414,36 +413,21 @@ static bool parse_args(int argc, char *argv[]) while ((opt = getopt(argc, argv, "hn:i:p:m:")) != -1) { switch (opt) { case 'n': - test_args.nr_vcpus = atoi(optarg); - if (test_args.nr_vcpus <= 0) { - pr_info("Positive value needed for -n\n"); - goto err; - } else if (test_args.nr_vcpus > KVM_MAX_VCPUS) { + test_args.nr_vcpus = atoi_positive("Number of vCPUs", optarg); + if (test_args.nr_vcpus > KVM_MAX_VCPUS) { pr_info("Max allowed vCPUs: %u\n", KVM_MAX_VCPUS); goto err; } break; case 'i': - test_args.nr_iter = atoi(optarg); - if (test_args.nr_iter <= 0) { - pr_info("Positive value needed for -i\n"); - goto err; - } + test_args.nr_iter = atoi_positive("Number of iterations", optarg); break; case 'p': - test_args.timer_period_ms = atoi(optarg); - if (test_args.timer_period_ms <= 0) { - pr_info("Positive value needed for -p\n"); - goto err; - } + test_args.timer_period_ms = atoi_positive("Periodicity", optarg); break; case 'm': - test_args.migration_freq_ms = atoi(optarg); - if (test_args.migration_freq_ms < 0) { - pr_info("0 or positive value needed for -m\n"); - goto err; - } + test_args.migration_freq_ms = atoi_non_negative("Frequency", optarg); break; case 'h': default: @@ -462,9 +446,6 @@ int main(int argc, char *argv[]) { struct kvm_vm *vm; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - if (!parse_args(argc, argv)) exit(KSFT_SKIP); diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c index 947bd201435c..d86c4e4d1c82 100644 --- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c @@ -241,7 +241,6 @@ static void guest_svc_handler(struct ex_regs *regs) enum single_step_op { SINGLE_STEP_ENABLE = 0, - SINGLE_STEP_DISABLE = 1, }; static void guest_code_ss(int test_cnt) @@ -258,7 +257,7 @@ static void guest_code_ss(int test_cnt) GUEST_SYNC(SINGLE_STEP_ENABLE); /* - * The userspace will veriry that the pc is as expected during + * The userspace will verify that the pc is as expected during * single step execution between iter_ss_begin and iter_ss_end. */ asm volatile("iter_ss_begin:nop\n"); @@ -268,11 +267,9 @@ static void guest_code_ss(int test_cnt) bvr = read_sysreg(dbgbvr0_el1); wvr = read_sysreg(dbgwvr0_el1); + /* Userspace disables Single Step when the end is nigh. */ asm volatile("iter_ss_end:\n"); - /* Disable Single Step execution */ - GUEST_SYNC(SINGLE_STEP_DISABLE); - GUEST_ASSERT(bvr == w_bvr); GUEST_ASSERT(wvr == w_wvr); } @@ -295,7 +292,6 @@ static void test_guest_debug_exceptions(void) int stage; vm = vm_create_with_one_vcpu(&vcpu, guest_code); - ucall_init(vm, NULL); vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); @@ -346,7 +342,6 @@ void test_single_step_from_userspace(int test_cnt) struct kvm_guest_debug debug = {}; vm = vm_create_with_one_vcpu(&vcpu, guest_code_ss); - ucall_init(vm, NULL); run = vcpu->run; vcpu_args_set(vcpu, 1, test_cnt); @@ -364,15 +359,12 @@ void test_single_step_from_userspace(int test_cnt) TEST_ASSERT(cmd == UCALL_SYNC, "Unexpected ucall cmd 0x%lx", cmd); - if (uc.args[1] == SINGLE_STEP_ENABLE) { - debug.control = KVM_GUESTDBG_ENABLE | - KVM_GUESTDBG_SINGLESTEP; - ss_enable = true; - } else { - debug.control = SINGLE_STEP_DISABLE; - ss_enable = false; - } + TEST_ASSERT(uc.args[1] == SINGLE_STEP_ENABLE, + "Unexpected ucall action 0x%lx", uc.args[1]); + debug.control = KVM_GUESTDBG_ENABLE | + KVM_GUESTDBG_SINGLESTEP; + ss_enable = true; vcpu_guest_debug_set(vcpu, &debug); continue; } @@ -385,6 +377,14 @@ void test_single_step_from_userspace(int test_cnt) "Unexpected pc 0x%lx (expected 0x%lx)", pc, test_pc); + if ((pc + 4) == (uint64_t)&iter_ss_end) { + test_pc = 0; + debug.control = KVM_GUESTDBG_ENABLE; + ss_enable = false; + vcpu_guest_debug_set(vcpu, &debug); + continue; + } + /* * If the current pc is between iter_ss_bgin and * iter_ss_end, the pc for the next KVM_EXIT_DEBUG should @@ -423,7 +423,7 @@ int main(int argc, char *argv[]) while ((opt = getopt(argc, argv, "i:")) != -1) { switch (opt) { case 'i': - ss_iteration = atoi(optarg); + ss_iteration = atoi_positive("Number of iterations", optarg); break; case 'h': default: diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c index a39da3fe4952..bef1499fb465 100644 --- a/tools/testing/selftests/kvm/aarch64/hypercalls.c +++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c @@ -236,7 +236,6 @@ static struct kvm_vm *test_vm_create(struct kvm_vcpu **vcpu) vm = vm_create_with_one_vcpu(vcpu, guest_code); - ucall_init(vm, NULL); steal_time_init(*vcpu); return vm; @@ -306,8 +305,6 @@ static void test_run(void) int main(void) { - setbuf(stdout, NULL); - test_run(); return 0; } diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c index e0b9e81a3e09..cfa36f387948 100644 --- a/tools/testing/selftests/kvm/aarch64/psci_test.c +++ b/tools/testing/selftests/kvm/aarch64/psci_test.c @@ -79,7 +79,6 @@ static struct kvm_vm *setup_vm(void *guest_code, struct kvm_vcpu **source, struct kvm_vm *vm; vm = vm_create(2); - ucall_init(vm, NULL); vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c index 9c131d977a1b..eef816b80993 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_init.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c @@ -68,8 +68,6 @@ static void guest_code(void) /* we don't want to assert on run execution, hence that helper */ static int run_vcpu(struct kvm_vcpu *vcpu) { - ucall_init(vcpu->vm, NULL); - return __vcpu_run(vcpu) ? -errno : 0; } diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c index 17417220a083..90d854e0fcff 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -756,7 +756,6 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) print_args(&args); vm = vm_create_with_one_vcpu(&vcpu, guest_code); - ucall_init(vm, NULL); vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); @@ -818,22 +817,19 @@ int main(int argc, char **argv) int opt; bool eoi_split = false; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - while ((opt = getopt(argc, argv, "hn:e:l:")) != -1) { switch (opt) { case 'n': - nr_irqs = atoi(optarg); + nr_irqs = atoi_non_negative("Number of IRQs", optarg); if (nr_irqs > 1024 || nr_irqs % 32) help(argv[0]); break; case 'e': - eoi_split = (bool)atoi(optarg); + eoi_split = (bool)atoi_paranoid(optarg); default_args = false; break; case 'l': - level_sensitive = (bool)atoi(optarg); + level_sensitive = (bool)atoi_paranoid(optarg); default_args = false; break; case 'h': diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 76c583a07ea2..02d3587cab0a 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -44,7 +44,7 @@ #include "kvm_util.h" #include "test_util.h" -#include "perf_test_util.h" +#include "memstress.h" #include "guest_modes.h" /* Global variable used to synchronize all of the vCPU threads. */ @@ -126,7 +126,7 @@ static void mark_page_idle(int page_idle_fd, uint64_t pfn) } static void mark_vcpu_memory_idle(struct kvm_vm *vm, - struct perf_test_vcpu_args *vcpu_args) + struct memstress_vcpu_args *vcpu_args) { int vcpu_idx = vcpu_args->vcpu_idx; uint64_t base_gva = vcpu_args->gva; @@ -148,7 +148,7 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm, TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap."); for (page = 0; page < pages; page++) { - uint64_t gva = base_gva + page * perf_test_args.guest_page_size; + uint64_t gva = base_gva + page * memstress_args.guest_page_size; uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva); if (!pfn) { @@ -220,10 +220,10 @@ static bool spin_wait_for_next_iteration(int *current_iteration) return true; } -static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args) +static void vcpu_thread_main(struct memstress_vcpu_args *vcpu_args) { struct kvm_vcpu *vcpu = vcpu_args->vcpu; - struct kvm_vm *vm = perf_test_args.vm; + struct kvm_vm *vm = memstress_args.vm; int vcpu_idx = vcpu_args->vcpu_idx; int current_iteration = 0; @@ -279,7 +279,7 @@ static void run_iteration(struct kvm_vm *vm, int nr_vcpus, const char *descripti static void access_memory(struct kvm_vm *vm, int nr_vcpus, enum access_type access, const char *description) { - perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1); + memstress_set_write_percent(vm, (access == ACCESS_READ) ? 0 : 100); iteration_work = ITERATION_ACCESS_MEMORY; run_iteration(vm, nr_vcpus, description); } @@ -303,10 +303,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct kvm_vm *vm; int nr_vcpus = params->nr_vcpus; - vm = perf_test_create_vm(mode, nr_vcpus, params->vcpu_memory_bytes, 1, + vm = memstress_create_vm(mode, nr_vcpus, params->vcpu_memory_bytes, 1, params->backing_src, !overlap_memory_access); - perf_test_start_vcpu_threads(nr_vcpus, vcpu_thread_main); + memstress_start_vcpu_threads(nr_vcpus, vcpu_thread_main); pr_info("\n"); access_memory(vm, nr_vcpus, ACCESS_WRITE, "Populating memory"); @@ -324,8 +324,8 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Set done to signal the vCPU threads to exit */ done = true; - perf_test_join_vcpu_threads(nr_vcpus); - perf_test_destroy_vm(vm); + memstress_join_vcpu_threads(nr_vcpus); + memstress_destroy_vm(vm); } static void help(char *name) @@ -368,7 +368,7 @@ int main(int argc, char *argv[]) params.vcpu_memory_bytes = parse_size(optarg); break; case 'v': - params.nr_vcpus = atoi(optarg); + params.nr_vcpus = atoi_positive("Number of vCPUs", optarg); break; case 'o': overlap_memory_access = true; diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 779ae54f89c4..3a977ddf07b2 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -20,7 +20,7 @@ #include "kvm_util.h" #include "test_util.h" -#include "perf_test_util.h" +#include "memstress.h" #include "guest_modes.h" #ifdef __NR_userfaultfd @@ -42,7 +42,7 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static size_t demand_paging_size; static char *guest_data_prototype; -static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) +static void vcpu_worker(struct memstress_vcpu_args *vcpu_args) { struct kvm_vcpu *vcpu = vcpu_args->vcpu; int vcpu_idx = vcpu_args->vcpu_idx; @@ -285,7 +285,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct kvm_vm *vm; int r, i; - vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, + vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, p->src_type, p->partition_vcpu_memory_access); demand_paging_size = get_backing_src_pagesz(p->src_type); @@ -307,11 +307,11 @@ static void run_test(enum vm_guest_mode mode, void *arg) TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); for (i = 0; i < nr_vcpus; i++) { - struct perf_test_vcpu_args *vcpu_args; + struct memstress_vcpu_args *vcpu_args; void *vcpu_hva; void *vcpu_alias; - vcpu_args = &perf_test_args.vcpu_args[i]; + vcpu_args = &memstress_args.vcpu_args[i]; /* Cache the host addresses of the region */ vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa); @@ -329,17 +329,17 @@ static void run_test(enum vm_guest_mode mode, void *arg) pipefds[i * 2], p->uffd_mode, p->uffd_delay, &uffd_args[i], vcpu_hva, vcpu_alias, - vcpu_args->pages * perf_test_args.guest_page_size); + vcpu_args->pages * memstress_args.guest_page_size); } } pr_info("Finished creating vCPUs and starting uffd threads\n"); clock_gettime(CLOCK_MONOTONIC, &start); - perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); + memstress_start_vcpu_threads(nr_vcpus, vcpu_worker); pr_info("Started all vCPUs\n"); - perf_test_join_vcpu_threads(nr_vcpus); + memstress_join_vcpu_threads(nr_vcpus); ts_diff = timespec_elapsed(start); pr_info("All vCPU threads joined\n"); @@ -358,10 +358,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("Total guest execution time: %ld.%.9lds\n", ts_diff.tv_sec, ts_diff.tv_nsec); pr_info("Overall demand paging rate: %f pgs/sec\n", - perf_test_args.vcpu_args[0].pages * nr_vcpus / + memstress_args.vcpu_args[0].pages * nr_vcpus / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); - perf_test_destroy_vm(vm); + memstress_destroy_vm(vm); free(guest_data_prototype); if (p->uffd_mode) { @@ -427,8 +427,8 @@ int main(int argc, char *argv[]) p.src_type = parse_backing_src_type(optarg); break; case 'v': - nr_vcpus = atoi(optarg); - TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, + nr_vcpus = atoi_positive("Number of vCPUs", optarg); + TEST_ASSERT(nr_vcpus <= max_vcpus, "Invalid number of vcpus, must be between 1 and %d", max_vcpus); break; case 'o': diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index f99e39a672d3..c33e89012ae6 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -16,7 +16,7 @@ #include "kvm_util.h" #include "test_util.h" -#include "perf_test_util.h" +#include "memstress.h" #include "guest_modes.h" #ifdef __aarch64__ @@ -67,7 +67,7 @@ static bool host_quit; static int iteration; static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; -static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) +static void vcpu_worker(struct memstress_vcpu_args *vcpu_args) { struct kvm_vcpu *vcpu = vcpu_args->vcpu; int vcpu_idx = vcpu_args->vcpu_idx; @@ -128,10 +128,12 @@ static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) struct test_params { unsigned long iterations; uint64_t phys_offset; - int wr_fract; bool partition_vcpu_memory_access; enum vm_mem_backing_src_type backing_src; int slots; + uint32_t write_percent; + uint32_t random_seed; + bool random_access; }; static void toggle_dirty_logging(struct kvm_vm *vm, int slots, bool enable) @@ -139,7 +141,7 @@ static void toggle_dirty_logging(struct kvm_vm *vm, int slots, bool enable) int i; for (i = 0; i < slots; i++) { - int slot = PERF_TEST_MEM_SLOT_INDEX + i; + int slot = MEMSTRESS_MEM_SLOT_INDEX + i; int flags = enable ? KVM_MEM_LOG_DIRTY_PAGES : 0; vm_mem_region_set_flags(vm, slot, flags); @@ -161,7 +163,7 @@ static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots int i; for (i = 0; i < slots; i++) { - int slot = PERF_TEST_MEM_SLOT_INDEX + i; + int slot = MEMSTRESS_MEM_SLOT_INDEX + i; kvm_vm_get_dirty_log(vm, slot, bitmaps[i]); } @@ -173,7 +175,7 @@ static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int i; for (i = 0; i < slots; i++) { - int slot = PERF_TEST_MEM_SLOT_INDEX + i; + int slot = MEMSTRESS_MEM_SLOT_INDEX + i; kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot); } @@ -221,11 +223,13 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct timespec clear_dirty_log_total = (struct timespec){0}; int i; - vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, + vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, p->slots, p->backing_src, p->partition_vcpu_memory_access); - perf_test_set_wr_fract(vm, p->wr_fract); + pr_info("Random seed: %u\n", p->random_seed); + memstress_set_random_seed(vm, p->random_seed); + memstress_set_write_percent(vm, p->write_percent); guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm->page_shift; guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); @@ -248,7 +252,16 @@ static void run_test(enum vm_guest_mode mode, void *arg) for (i = 0; i < nr_vcpus; i++) vcpu_last_completed_iteration[i] = -1; - perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); + /* + * Use 100% writes during the population phase to ensure all + * memory is actually populated and not just mapped to the zero + * page. The prevents expensive copy-on-write faults from + * occurring during the dirty memory iterations below, which + * would pollute the performance results. + */ + memstress_set_write_percent(vm, 100); + memstress_set_random_access(vm, false); + memstress_start_vcpu_threads(nr_vcpus, vcpu_worker); /* Allow the vCPUs to populate memory */ pr_debug("Starting iteration %d - Populating\n", iteration); @@ -269,6 +282,9 @@ static void run_test(enum vm_guest_mode mode, void *arg) pr_info("Enabling dirty logging time: %ld.%.9lds\n\n", ts_diff.tv_sec, ts_diff.tv_nsec); + memstress_set_write_percent(vm, p->write_percent); + memstress_set_random_access(vm, p->random_access); + while (iteration < p->iterations) { /* * Incrementing the iteration number will start the vCPUs @@ -329,7 +345,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) * wait for them to exit. */ host_quit = true; - perf_test_join_vcpu_threads(nr_vcpus); + memstress_join_vcpu_threads(nr_vcpus); avg = timespec_div(get_dirty_log_total, p->iterations); pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", @@ -345,16 +361,17 @@ static void run_test(enum vm_guest_mode mode, void *arg) free_bitmaps(bitmaps, p->slots); arch_cleanup_vm(vm); - perf_test_destroy_vm(vm); + memstress_destroy_vm(vm); } static void help(char *name) { puts(""); - printf("usage: %s [-h] [-i iterations] [-p offset] [-g] " - "[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]" - "[-x memslots]\n", name); + printf("usage: %s [-h] [-a] [-i iterations] [-p offset] [-g] " + "[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-r random seed ] [-s mem type]" + "[-x memslots] [-w percentage] [-c physical cpus to run test on]\n", name); puts(""); + printf(" -a: access memory randomly rather than in order.\n"); printf(" -i: specify iteration counts (default: %"PRIu64")\n", TEST_HOST_LOOP_N); printf(" -g: Do not enable KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2. This\n" @@ -373,16 +390,29 @@ static void help(char *name) printf(" -b: specify the size of the memory region which should be\n" " dirtied by each vCPU. e.g. 10M or 3G.\n" " (default: 1G)\n"); - printf(" -f: specify the fraction of pages which should be written to\n" - " as opposed to simply read, in the form\n" - " 1/<fraction of pages to write>.\n" - " (default: 1 i.e. all pages are written to.)\n"); printf(" -v: specify the number of vCPUs to run.\n"); printf(" -o: Overlap guest memory accesses instead of partitioning\n" " them into a separate region of memory for each vCPU.\n"); + printf(" -r: specify the starting random seed.\n"); backing_src_help("-s"); printf(" -x: Split the memory region into this number of memslots.\n" " (default: 1)\n"); + printf(" -w: specify the percentage of pages which should be written to\n" + " as an integer from 0-100 inclusive. This is probabalistic,\n" + " so -w X means each page has an X%% chance of writing\n" + " and a (100-X)%% chance of reading.\n" + " (default: 100 i.e. all pages are written to.)\n"); + printf(" -c: Pin tasks to physical CPUs. Takes a list of comma separated\n" + " values (target pCPU), one for each vCPU, plus an optional\n" + " entry for the main application task (specified via entry\n" + " <nr_vcpus + 1>). If used, entries must be provided for all\n" + " vCPUs, i.e. pinning vCPUs is all or nothing.\n\n" + " E.g. to create 3 vCPUs, pin vCPU0=>pCPU22, vCPU1=>pCPU23,\n" + " vCPU2=>pCPU24, and pin the application task to pCPU50:\n\n" + " ./dirty_log_perf_test -v 3 -c 22,23,24,50\n\n" + " To leave the application task unpinned, drop the final entry:\n\n" + " ./dirty_log_perf_test -v 3 -c 22,23,24\n\n" + " (default: no pinning)\n"); puts(""); exit(0); } @@ -390,12 +420,14 @@ static void help(char *name) int main(int argc, char *argv[]) { int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); + const char *pcpu_list = NULL; struct test_params p = { .iterations = TEST_HOST_LOOP_N, - .wr_fract = 1, .partition_vcpu_memory_access = true, .backing_src = DEFAULT_VM_MEM_SRC, .slots = 1, + .random_seed = 1, + .write_percent = 100, }; int opt; @@ -406,55 +438,73 @@ int main(int argc, char *argv[]) guest_modes_append_default(); - while ((opt = getopt(argc, argv, "eghi:p:m:nb:f:v:os:x:")) != -1) { + while ((opt = getopt(argc, argv, "ab:c:eghi:m:nop:r:s:v:x:w:")) != -1) { switch (opt) { + case 'a': + p.random_access = true; + break; + case 'b': + guest_percpu_mem_size = parse_size(optarg); + break; + case 'c': + pcpu_list = optarg; + break; case 'e': /* 'e' is for evil. */ run_vcpus_while_disabling_dirty_logging = true; + break; case 'g': dirty_log_manual_caps = 0; break; - case 'i': - p.iterations = atoi(optarg); + case 'h': + help(argv[0]); break; - case 'p': - p.phys_offset = strtoull(optarg, NULL, 0); + case 'i': + p.iterations = atoi_positive("Number of iterations", optarg); break; case 'm': guest_modes_cmdline(optarg); break; case 'n': - perf_test_args.nested = true; - break; - case 'b': - guest_percpu_mem_size = parse_size(optarg); - break; - case 'f': - p.wr_fract = atoi(optarg); - TEST_ASSERT(p.wr_fract >= 1, - "Write fraction cannot be less than one"); - break; - case 'v': - nr_vcpus = atoi(optarg); - TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, - "Invalid number of vcpus, must be between 1 and %d", max_vcpus); + memstress_args.nested = true; break; case 'o': p.partition_vcpu_memory_access = false; break; + case 'p': + p.phys_offset = strtoull(optarg, NULL, 0); + break; + case 'r': + p.random_seed = atoi_positive("Random seed", optarg); + break; case 's': p.backing_src = parse_backing_src_type(optarg); break; + case 'v': + nr_vcpus = atoi_positive("Number of vCPUs", optarg); + TEST_ASSERT(nr_vcpus <= max_vcpus, + "Invalid number of vcpus, must be between 1 and %d", max_vcpus); + break; + case 'w': + p.write_percent = atoi_non_negative("Write percentage", optarg); + TEST_ASSERT(p.write_percent <= 100, + "Write percentage must be between 0 and 100"); + break; case 'x': - p.slots = atoi(optarg); + p.slots = atoi_positive("Number of slots", optarg); break; - case 'h': default: help(argv[0]); break; } } + if (pcpu_list) { + kvm_parse_vcpu_pinning(pcpu_list, memstress_args.vcpu_to_pcpu, + nr_vcpus); + memstress_args.pin_vcpus = true; + } + TEST_ASSERT(p.iterations >= 2, "The test should have at least two iterations"); pr_info("Test iterations: %"PRIu64"\n", p.iterations); diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index b5234d6efbe1..a38c4369fb8e 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -756,8 +756,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Cache the HVA pointer of the region */ host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem); - ucall_init(vm, NULL); - /* Export the shared variables to the guest */ sync_global_to_guest(vm, host_page_size); sync_global_to_guest(vm, guest_page_size); @@ -813,7 +811,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) free(bmap); free(host_bmap_track); - ucall_uninit(vm); kvm_vm_free(vm); } diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index e42a09cd24a0..c7685c7038ff 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -16,6 +16,7 @@ #include <linux/kvm.h> #include "linux/rbtree.h" +#include <asm/atomic.h> #include <sys/ioctl.h> @@ -81,6 +82,7 @@ struct kvm_vm { struct sparsebit *vpages_mapped; bool has_irqchip; bool pgd_created; + vm_paddr_t ucall_mmio_addr; vm_paddr_t pgd; vm_vaddr_t gdt; vm_vaddr_t tss; @@ -383,6 +385,7 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); +vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); @@ -688,6 +691,10 @@ static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); +void kvm_pin_this_task_to_pcpu(uint32_t pcpu); +void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], + int nr_vcpus); + unsigned long vm_compute_max_gfn(struct kvm_vm *vm); unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages); @@ -718,6 +725,19 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, memcpy(&(g), _p, sizeof(g)); \ }) +/* + * Write a global value, but only in the VM's (guest's) domain. Primarily used + * for "globals" that hold per-VM values (VMs always duplicate code and global + * data into their own region of physical memory), but can be used anytime it's + * undesirable to change the host's copy of the global. + */ +#define write_guest_global(vm, g, val) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + typeof(g) _val = val; \ + \ + memcpy(_p, &(_val), sizeof(g)); \ +}) + void assert_on_unhandled_exception(struct kvm_vcpu *vcpu); void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, @@ -838,4 +858,13 @@ static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm) return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0); } +/* + * Arch hook that is invoked via a constructor, i.e. before exeucting main(), + * to allow for arch-specific setup that is common to all tests, e.g. computing + * the default guest "mode". + */ +void kvm_selftest_arch_init(void); + +void kvm_arch_vm_post_create(struct kvm_vm *vm); + #endif /* SELFTEST_KVM_UTIL_BASE_H */ diff --git a/tools/testing/selftests/kvm/include/memstress.h b/tools/testing/selftests/kvm/include/memstress.h new file mode 100644 index 000000000000..bbd2a302df10 --- /dev/null +++ b/tools/testing/selftests/kvm/include/memstress.h @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * tools/testing/selftests/kvm/include/memstress.h + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef SELFTEST_KVM_MEMSTRESS_H +#define SELFTEST_KVM_MEMSTRESS_H + +#include <pthread.h> + +#include "kvm_util.h" + +/* Default guest test virtual memory offset */ +#define DEFAULT_GUEST_TEST_MEM 0xc0000000 + +#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */ + +#define MEMSTRESS_MEM_SLOT_INDEX 1 + +struct memstress_vcpu_args { + uint64_t gpa; + uint64_t gva; + uint64_t pages; + + /* Only used by the host userspace part of the vCPU thread */ + struct kvm_vcpu *vcpu; + int vcpu_idx; +}; + +struct memstress_args { + struct kvm_vm *vm; + /* The starting address and size of the guest test region. */ + uint64_t gpa; + uint64_t size; + uint64_t guest_page_size; + uint32_t random_seed; + uint32_t write_percent; + + /* Run vCPUs in L2 instead of L1, if the architecture supports it. */ + bool nested; + /* Randomize which pages are accessed by the guest. */ + bool random_access; + /* True if all vCPUs are pinned to pCPUs */ + bool pin_vcpus; + /* The vCPU=>pCPU pinning map. Only valid if pin_vcpus is true. */ + uint32_t vcpu_to_pcpu[KVM_MAX_VCPUS]; + + struct memstress_vcpu_args vcpu_args[KVM_MAX_VCPUS]; +}; + +extern struct memstress_args memstress_args; + +struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, + uint64_t vcpu_memory_bytes, int slots, + enum vm_mem_backing_src_type backing_src, + bool partition_vcpu_memory_access); +void memstress_destroy_vm(struct kvm_vm *vm); + +void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent); +void memstress_set_random_seed(struct kvm_vm *vm, uint32_t random_seed); +void memstress_set_random_access(struct kvm_vm *vm, bool random_access); + +void memstress_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct memstress_vcpu_args *)); +void memstress_join_vcpu_threads(int vcpus); +void memstress_guest_code(uint32_t vcpu_id); + +uint64_t memstress_nested_pages(int nr_vcpus); +void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]); + +#endif /* SELFTEST_KVM_MEMSTRESS_H */ diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h deleted file mode 100644 index eaa88df0555a..000000000000 --- a/tools/testing/selftests/kvm/include/perf_test_util.h +++ /dev/null @@ -1,63 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * tools/testing/selftests/kvm/include/perf_test_util.h - * - * Copyright (C) 2020, Google LLC. - */ - -#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H -#define SELFTEST_KVM_PERF_TEST_UTIL_H - -#include <pthread.h> - -#include "kvm_util.h" - -/* Default guest test virtual memory offset */ -#define DEFAULT_GUEST_TEST_MEM 0xc0000000 - -#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */ - -#define PERF_TEST_MEM_SLOT_INDEX 1 - -struct perf_test_vcpu_args { - uint64_t gpa; - uint64_t gva; - uint64_t pages; - - /* Only used by the host userspace part of the vCPU thread */ - struct kvm_vcpu *vcpu; - int vcpu_idx; -}; - -struct perf_test_args { - struct kvm_vm *vm; - /* The starting address and size of the guest test region. */ - uint64_t gpa; - uint64_t size; - uint64_t guest_page_size; - int wr_fract; - - /* Run vCPUs in L2 instead of L1, if the architecture supports it. */ - bool nested; - - struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS]; -}; - -extern struct perf_test_args perf_test_args; - -struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus, - uint64_t vcpu_memory_bytes, int slots, - enum vm_mem_backing_src_type backing_src, - bool partition_vcpu_memory_access); -void perf_test_destroy_vm(struct kvm_vm *vm); - -void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract); - -void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *)); -void perf_test_join_vcpu_threads(int vcpus); -void perf_test_guest_code(uint32_t vcpu_id); - -uint64_t perf_test_nested_pages(int nr_vcpus); -void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]); - -#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index befc754ce9b3..80d6416f3012 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -77,6 +77,13 @@ struct timespec timespec_sub(struct timespec ts1, struct timespec ts2); struct timespec timespec_elapsed(struct timespec start); struct timespec timespec_div(struct timespec ts, int divisor); +struct guest_random_state { + uint32_t seed; +}; + +struct guest_random_state new_guest_random_state(uint32_t seed); +uint32_t guest_random_u32(struct guest_random_state *state); + enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS, VM_MEM_SRC_ANONYMOUS_THP, @@ -152,4 +159,22 @@ static inline void *align_ptr_up(void *x, size_t size) return (void *)align_up((unsigned long)x, size); } +int atoi_paranoid(const char *num_str); + +static inline uint32_t atoi_positive(const char *name, const char *num_str) +{ + int num = atoi_paranoid(num_str); + + TEST_ASSERT(num > 0, "%s must be greater than 0, got '%s'", name, num_str); + return num; +} + +static inline uint32_t atoi_non_negative(const char *name, const char *num_str) +{ + int num = atoi_paranoid(num_str); + + TEST_ASSERT(num >= 0, "%s must be non-negative, got '%s'", name, num_str); + return num; +} + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h index ee79d180e07e..bdd373189a77 100644 --- a/tools/testing/selftests/kvm/include/ucall_common.h +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -22,12 +22,18 @@ enum { struct ucall { uint64_t cmd; uint64_t args[UCALL_MAX_ARGS]; + + /* Host virtual address of this struct. */ + struct ucall *hva; }; -void ucall_init(struct kvm_vm *vm, void *arg); -void ucall_uninit(struct kvm_vm *vm); +void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa); +void ucall_arch_do_ucall(vm_vaddr_t uc); +void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu); + void ucall(uint64_t cmd, int nargs, ...); uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc); +void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa); #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4) diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h index 58db74f68af2..901caf0e0939 100644 --- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h @@ -10,6 +10,7 @@ #define SELFTEST_KVM_EVMCS_H #include <stdint.h> +#include "hyperv.h" #include "vmx.h" #define u16 uint16_t @@ -20,15 +21,6 @@ extern bool enable_evmcs; -struct hv_vp_assist_page { - __u32 apic_assist; - __u32 reserved; - __u64 vtl_control[2]; - __u64 nested_enlightenments_control[2]; - __u32 enlighten_vmentry; - __u64 current_nested_vmcs; -}; - struct hv_enlightened_vmcs { u32 revision_id; u32 abort; @@ -41,6 +33,8 @@ struct hv_enlightened_vmcs { u16 host_gs_selector; u16 host_tr_selector; + u16 padding16_1; + u64 host_ia32_pat; u64 host_ia32_efer; @@ -159,7 +153,7 @@ struct hv_enlightened_vmcs { u64 ept_pointer; u16 virtual_processor_id; - u16 padding16[3]; + u16 padding16_2[3]; u64 padding64_2[5]; u64 guest_physical_address; @@ -195,13 +189,13 @@ struct hv_enlightened_vmcs { u64 guest_rip; u32 hv_clean_fields; - u32 hv_padding_32; + u32 padding32_1; u32 hv_synthetic_controls; struct { u32 nested_flush_hypercall:1; u32 msr_bitmap:1; u32 reserved:30; - } hv_enlightenments_control; + } __packed hv_enlightenments_control; u32 hv_vp_id; u32 padding32_2; u64 hv_vm_id; @@ -222,7 +216,7 @@ struct hv_enlightened_vmcs { u64 host_ssp; u64 host_ia32_int_ssp_table_addr; u64 padding64_6; -}; +} __packed; #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0) @@ -243,29 +237,15 @@ struct hv_enlightened_vmcs { #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL BIT(15) #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF -#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 -#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 -#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 -#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ - (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) +#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031 extern struct hv_enlightened_vmcs *current_evmcs; -extern struct hv_vp_assist_page *current_vp_assist; int vcpu_enable_evmcs(struct kvm_vcpu *vcpu); -static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist) +static inline void evmcs_enable(void) { - u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) | - HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; - - wrmsr(HV_X64_MSR_VP_ASSIST_PAGE, val); - - current_vp_assist = vp_assist; - enable_evmcs = true; - - return 0; } static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs) @@ -278,6 +258,16 @@ static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs) return 0; } +static inline bool load_evmcs(struct hyperv_test_pages *hv) +{ + if (evmcs_vmptrld(hv->enlightened_vmcs_gpa, hv->enlightened_vmcs)) + return false; + + current_evmcs->revision_id = EVMCS_VERSION; + + return true; +} + static inline int evmcs_vmptrst(uint64_t *value) { *value = current_vp_assist->current_nested_vmcs & diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h index b66910702c0a..9218bb5f44bf 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -9,6 +9,8 @@ #ifndef SELFTEST_KVM_HYPERV_H #define SELFTEST_KVM_HYPERV_H +#include "processor.h" + #define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 0x40000000 #define HYPERV_CPUID_INTERFACE 0x40000001 #define HYPERV_CPUID_VERSION 0x40000002 @@ -184,5 +186,106 @@ /* hypercall options */ #define HV_HYPERCALL_FAST_BIT BIT(16) +#define HV_HYPERCALL_VARHEAD_OFFSET 17 +#define HV_HYPERCALL_REP_COMP_OFFSET 32 + +/* + * Issue a Hyper-V hypercall. Returns exception vector raised or 0, 'hv_status' + * is set to the hypercall status (if no exception occurred). + */ +static inline uint8_t __hyperv_hypercall(u64 control, vm_vaddr_t input_address, + vm_vaddr_t output_address, + uint64_t *hv_status) +{ + uint64_t error_code; + uint8_t vector; + + /* Note both the hypercall and the "asm safe" clobber r9-r11. */ + asm volatile("mov %[output_address], %%r8\n\t" + KVM_ASM_SAFE("vmcall") + : "=a" (*hv_status), + "+c" (control), "+d" (input_address), + KVM_ASM_SAFE_OUTPUTS(vector, error_code) + : [output_address] "r"(output_address), + "a" (-EFAULT) + : "cc", "memory", "r8", KVM_ASM_SAFE_CLOBBERS); + return vector; +} + +/* Issue a Hyper-V hypercall and assert that it succeeded. */ +static inline void hyperv_hypercall(u64 control, vm_vaddr_t input_address, + vm_vaddr_t output_address) +{ + uint64_t hv_status; + uint8_t vector; + + vector = __hyperv_hypercall(control, input_address, output_address, &hv_status); + + GUEST_ASSERT(!vector); + GUEST_ASSERT((hv_status & 0xffff) == 0); +} + +/* Write 'Fast' hypercall input 'data' to the first 'n_sse_regs' SSE regs */ +static inline void hyperv_write_xmm_input(void *data, int n_sse_regs) +{ + int i; + + for (i = 0; i < n_sse_regs; i++) + write_sse_reg(i, (sse128_t *)(data + sizeof(sse128_t) * i)); +} + +/* Proper HV_X64_MSR_GUEST_OS_ID value */ +#define HYPERV_LINUX_OS_ID ((u64)0x8100 << 48) + +#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 +#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 +#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 +#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ + (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) + +struct hv_nested_enlightenments_control { + struct { + __u32 directhypercall:1; + __u32 reserved:31; + } features; + struct { + __u32 reserved; + } hypercallControls; +} __packed; + +/* Define virtual processor assist page structure. */ +struct hv_vp_assist_page { + __u32 apic_assist; + __u32 reserved1; + __u64 vtl_control[3]; + struct hv_nested_enlightenments_control nested_control; + __u8 enlighten_vmentry; + __u8 reserved2[7]; + __u64 current_nested_vmcs; +} __packed; + +extern struct hv_vp_assist_page *current_vp_assist; + +int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist); + +struct hyperv_test_pages { + /* VP assist page */ + void *vp_assist_hva; + uint64_t vp_assist_gpa; + void *vp_assist; + + /* Partition assist page */ + void *partition_assist_hva; + uint64_t partition_assist_gpa; + void *partition_assist; + + /* Enlightened VMCS */ + void *enlightened_vmcs_hva; + uint64_t enlightened_vmcs_gpa; + void *enlightened_vmcs; +}; + +struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, + vm_vaddr_t *p_hv_pages_gva); #endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index e8ca0d8a6a7e..5d310abe6c3f 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -63,16 +63,21 @@ struct kvm_x86_cpu_feature { u8 reg; u8 bit; }; -#define KVM_X86_CPU_FEATURE(fn, idx, gpr, __bit) \ -({ \ - struct kvm_x86_cpu_feature feature = { \ - .function = fn, \ - .index = idx, \ - .reg = KVM_CPUID_##gpr, \ - .bit = __bit, \ - }; \ - \ - feature; \ +#define KVM_X86_CPU_FEATURE(fn, idx, gpr, __bit) \ +({ \ + struct kvm_x86_cpu_feature feature = { \ + .function = fn, \ + .index = idx, \ + .reg = KVM_CPUID_##gpr, \ + .bit = __bit, \ + }; \ + \ + static_assert((fn & 0xc0000000) == 0 || \ + (fn & 0xc0000000) == 0x40000000 || \ + (fn & 0xc0000000) == 0x80000000 || \ + (fn & 0xc0000000) == 0xc0000000); \ + static_assert(idx < BIT(sizeof(feature.index) * BITS_PER_BYTE)); \ + feature; \ }) /* @@ -89,6 +94,7 @@ struct kvm_x86_cpu_feature { #define X86_FEATURE_XSAVE KVM_X86_CPU_FEATURE(0x1, 0, ECX, 26) #define X86_FEATURE_OSXSAVE KVM_X86_CPU_FEATURE(0x1, 0, ECX, 27) #define X86_FEATURE_RDRAND KVM_X86_CPU_FEATURE(0x1, 0, ECX, 30) +#define X86_FEATURE_PAE KVM_X86_CPU_FEATURE(0x1, 0, EDX, 6) #define X86_FEATURE_MCE KVM_X86_CPU_FEATURE(0x1, 0, EDX, 7) #define X86_FEATURE_APIC KVM_X86_CPU_FEATURE(0x1, 0, EDX, 9) #define X86_FEATURE_CLFLUSH KVM_X86_CPU_FEATURE(0x1, 0, EDX, 19) @@ -162,6 +168,102 @@ struct kvm_x86_cpu_feature { #define X86_FEATURE_KVM_HC_MAP_GPA_RANGE KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 16) #define X86_FEATURE_KVM_MIGRATION_CONTROL KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 17) +/* + * Same idea as X86_FEATURE_XXX, but X86_PROPERTY_XXX retrieves a multi-bit + * value/property as opposed to a single-bit feature. Again, pack the info + * into a 64-bit value to pass by value with no overhead. + */ +struct kvm_x86_cpu_property { + u32 function; + u8 index; + u8 reg; + u8 lo_bit; + u8 hi_bit; +}; +#define KVM_X86_CPU_PROPERTY(fn, idx, gpr, low_bit, high_bit) \ +({ \ + struct kvm_x86_cpu_property property = { \ + .function = fn, \ + .index = idx, \ + .reg = KVM_CPUID_##gpr, \ + .lo_bit = low_bit, \ + .hi_bit = high_bit, \ + }; \ + \ + static_assert(low_bit < high_bit); \ + static_assert((fn & 0xc0000000) == 0 || \ + (fn & 0xc0000000) == 0x40000000 || \ + (fn & 0xc0000000) == 0x80000000 || \ + (fn & 0xc0000000) == 0xc0000000); \ + static_assert(idx < BIT(sizeof(property.index) * BITS_PER_BYTE)); \ + property; \ +}) + +#define X86_PROPERTY_MAX_BASIC_LEAF KVM_X86_CPU_PROPERTY(0, 0, EAX, 0, 31) +#define X86_PROPERTY_PMU_VERSION KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 0, 7) +#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_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_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_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) +#define X86_PROPERTY_AMX_NR_TILE_REGS KVM_X86_CPU_PROPERTY(0x1d, 1, EBX, 16, 31) +#define X86_PROPERTY_AMX_MAX_ROWS KVM_X86_CPU_PROPERTY(0x1d, 1, ECX, 0, 15) + +#define X86_PROPERTY_MAX_KVM_LEAF KVM_X86_CPU_PROPERTY(0x40000000, 0, EAX, 0, 31) + +#define X86_PROPERTY_MAX_EXT_LEAF KVM_X86_CPU_PROPERTY(0x80000000, 0, EAX, 0, 31) +#define X86_PROPERTY_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 0, 7) +#define X86_PROPERTY_MAX_VIRT_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 8, 15) +#define X86_PROPERTY_PHYS_ADDR_REDUCTION KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11) + +#define X86_PROPERTY_MAX_CENTAUR_LEAF KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31) + +/* + * Intel's architectural PMU events are bizarre. They have a "feature" bit + * that indicates the feature is _not_ supported, and a property that states + * the length of the bit mask of unsupported features. A feature is supported + * if the size of the bit mask is larger than the "unavailable" bit, and said + * bit is not set. + * + * Wrap the "unavailable" feature to simplify checking whether or not a given + * architectural event is supported. + */ +struct kvm_x86_pmu_feature { + struct kvm_x86_cpu_feature anti_feature; +}; +#define KVM_X86_PMU_FEATURE(name, __bit) \ +({ \ + struct kvm_x86_pmu_feature feature = { \ + .anti_feature = KVM_X86_CPU_FEATURE(0xa, 0, EBX, __bit), \ + }; \ + \ + feature; \ +}) + +#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(BRANCH_INSNS_RETIRED, 5) + +static inline unsigned int x86_family(unsigned int eax) +{ + unsigned int x86; + + x86 = (eax >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (eax >> 20) & 0xff; + + return x86; +} + +static inline unsigned int x86_model(unsigned int eax) +{ + return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f); +} + /* Page table bitfield declarations */ #define PTE_PRESENT_MASK BIT_ULL(0) #define PTE_WRITABLE_MASK BIT_ULL(1) @@ -172,12 +274,18 @@ struct kvm_x86_cpu_feature { #define PTE_GLOBAL_MASK BIT_ULL(8) #define PTE_NX_MASK BIT_ULL(63) +#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12) + #define PAGE_SHIFT 12 #define PAGE_SIZE (1ULL << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE-1)) +#define PAGE_MASK (~(PAGE_SIZE-1) & PHYSICAL_PAGE_MASK) -#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12) -#define PTE_GET_PFN(pte) (((pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT) +#define HUGEPAGE_SHIFT(x) (PAGE_SHIFT + (((x) - 1) * 9)) +#define HUGEPAGE_SIZE(x) (1UL << HUGEPAGE_SHIFT(x)) +#define HUGEPAGE_MASK(x) (~(HUGEPAGE_SIZE(x) - 1) & PHYSICAL_PAGE_MASK) + +#define PTE_GET_PA(pte) ((pte) & PHYSICAL_PAGE_MASK) +#define PTE_GET_PFN(pte) (PTE_GET_PA(pte) >> PAGE_SHIFT) /* General Registers in 64-Bit Mode */ struct gpr64_regs { @@ -425,82 +533,143 @@ static inline void cpuid(uint32_t function, return __cpuid(function, 0, eax, ebx, ecx, edx); } -static inline bool this_cpu_has(struct kvm_x86_cpu_feature feature) +static inline uint32_t this_cpu_fms(void) +{ + uint32_t eax, ebx, ecx, edx; + + cpuid(1, &eax, &ebx, &ecx, &edx); + return eax; +} + +static inline uint32_t this_cpu_family(void) +{ + return x86_family(this_cpu_fms()); +} + +static inline uint32_t this_cpu_model(void) +{ + return x86_model(this_cpu_fms()); +} + +static inline uint32_t __this_cpu_has(uint32_t function, uint32_t index, + uint8_t reg, uint8_t lo, uint8_t hi) { uint32_t gprs[4]; - __cpuid(feature.function, feature.index, + __cpuid(function, index, &gprs[KVM_CPUID_EAX], &gprs[KVM_CPUID_EBX], &gprs[KVM_CPUID_ECX], &gprs[KVM_CPUID_EDX]); - return gprs[feature.reg] & BIT(feature.bit); + return (gprs[reg] & GENMASK(hi, lo)) >> lo; +} + +static inline bool this_cpu_has(struct kvm_x86_cpu_feature feature) +{ + return __this_cpu_has(feature.function, feature.index, + feature.reg, feature.bit, feature.bit); } -#define SET_XMM(__var, __xmm) \ - asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm) +static inline uint32_t this_cpu_property(struct kvm_x86_cpu_property property) +{ + return __this_cpu_has(property.function, property.index, + property.reg, property.lo_bit, property.hi_bit); +} -static inline void set_xmm(int n, unsigned long val) +static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property) { - switch (n) { + uint32_t max_leaf; + + switch (property.function & 0xc0000000) { case 0: - SET_XMM(val, xmm0); + max_leaf = this_cpu_property(X86_PROPERTY_MAX_BASIC_LEAF); + break; + case 0x40000000: + max_leaf = this_cpu_property(X86_PROPERTY_MAX_KVM_LEAF); + break; + case 0x80000000: + max_leaf = this_cpu_property(X86_PROPERTY_MAX_EXT_LEAF); + break; + case 0xc0000000: + max_leaf = this_cpu_property(X86_PROPERTY_MAX_CENTAUR_LEAF); + } + return max_leaf >= property.function; +} + +static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) +{ + uint32_t nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + + return nr_bits > feature.anti_feature.bit && + !this_cpu_has(feature.anti_feature); +} + +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]; }) +#define sse128_hi(x) ({ __sse128_u t; t.vec = x; t.as_u64[1]; }) + +static inline void read_sse_reg(int reg, sse128_t *data) +{ + switch (reg) { + case 0: + asm("movdqa %%xmm0, %0" : "=m"(*data)); break; case 1: - SET_XMM(val, xmm1); + asm("movdqa %%xmm1, %0" : "=m"(*data)); break; case 2: - SET_XMM(val, xmm2); + asm("movdqa %%xmm2, %0" : "=m"(*data)); break; case 3: - SET_XMM(val, xmm3); + asm("movdqa %%xmm3, %0" : "=m"(*data)); break; case 4: - SET_XMM(val, xmm4); + asm("movdqa %%xmm4, %0" : "=m"(*data)); break; case 5: - SET_XMM(val, xmm5); + asm("movdqa %%xmm5, %0" : "=m"(*data)); break; case 6: - SET_XMM(val, xmm6); + asm("movdqa %%xmm6, %0" : "=m"(*data)); break; case 7: - SET_XMM(val, xmm7); + asm("movdqa %%xmm7, %0" : "=m"(*data)); break; + default: + BUG(); } } -#define GET_XMM(__xmm) \ -({ \ - unsigned long __val; \ - asm volatile("movq %%"#__xmm", %0" : "=r"(__val)); \ - __val; \ -}) - -static inline unsigned long get_xmm(int n) +static inline void write_sse_reg(int reg, const sse128_t *data) { - assert(n >= 0 && n <= 7); - - switch (n) { + switch (reg) { case 0: - return GET_XMM(xmm0); + asm("movdqa %0, %%xmm0" : : "m"(*data)); + break; case 1: - return GET_XMM(xmm1); + asm("movdqa %0, %%xmm1" : : "m"(*data)); + break; case 2: - return GET_XMM(xmm2); + asm("movdqa %0, %%xmm2" : : "m"(*data)); + break; case 3: - return GET_XMM(xmm3); + asm("movdqa %0, %%xmm3" : : "m"(*data)); + break; case 4: - return GET_XMM(xmm4); + asm("movdqa %0, %%xmm4" : : "m"(*data)); + break; case 5: - return GET_XMM(xmm5); + asm("movdqa %0, %%xmm5" : : "m"(*data)); + break; case 6: - return GET_XMM(xmm6); + asm("movdqa %0, %%xmm6" : : "m"(*data)); + break; case 7: - return GET_XMM(xmm7); + asm("movdqa %0, %%xmm7" : : "m"(*data)); + break; + default: + BUG(); } - - /* never reached */ - return 0; } static inline void cpu_relax(void) @@ -508,11 +677,6 @@ static inline void cpu_relax(void) asm volatile("rep; nop" ::: "memory"); } -#define vmmcall() \ - __asm__ __volatile__( \ - "vmmcall\n" \ - ) - #define ud2() \ __asm__ __volatile__( \ "ud2\n" \ @@ -526,23 +690,6 @@ static inline void cpu_relax(void) bool is_intel_cpu(void); bool is_amd_cpu(void); -static inline unsigned int x86_family(unsigned int eax) -{ - unsigned int x86; - - x86 = (eax >> 8) & 0xf; - - if (x86 == 0xf) - x86 += (eax >> 20) & 0xff; - - return x86; -} - -static inline unsigned int x86_model(unsigned int eax) -{ - return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f); -} - struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu); void vcpu_load_state(struct kvm_vcpu *vcpu, struct kvm_x86_state *state); void kvm_x86_state_cleanup(struct kvm_x86_state *state); @@ -604,10 +751,27 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs) vcpu_ioctl(vcpu, KVM_SET_XCRS, xcrs); } +const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, + uint32_t function, uint32_t index); const struct kvm_cpuid2 *kvm_get_supported_cpuid(void); const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu); +static inline uint32_t kvm_cpu_fms(void) +{ + return get_cpuid_entry(kvm_get_supported_cpuid(), 0x1, 0)->eax; +} + +static inline uint32_t kvm_cpu_family(void) +{ + return x86_family(kvm_cpu_fms()); +} + +static inline uint32_t kvm_cpu_model(void) +{ + return x86_model(kvm_cpu_fms()); +} + bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, struct kvm_x86_cpu_feature feature); @@ -616,6 +780,42 @@ static inline bool kvm_cpu_has(struct kvm_x86_cpu_feature feature) return kvm_cpuid_has(kvm_get_supported_cpuid(), feature); } +uint32_t kvm_cpuid_property(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_property property); + +static inline uint32_t kvm_cpu_property(struct kvm_x86_cpu_property property) +{ + return kvm_cpuid_property(kvm_get_supported_cpuid(), property); +} + +static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property) +{ + uint32_t max_leaf; + + switch (property.function & 0xc0000000) { + case 0: + max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_BASIC_LEAF); + break; + case 0x40000000: + max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_KVM_LEAF); + break; + case 0x80000000: + max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_EXT_LEAF); + break; + case 0xc0000000: + max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_CENTAUR_LEAF); + } + return max_leaf >= property.function; +} + +static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) +{ + uint32_t nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH); + + return nr_bits > feature.anti_feature.bit && + !kvm_cpu_has(feature.anti_feature); +} + static inline size_t kvm_cpuid2_size(int nr_entries) { return sizeof(struct kvm_cpuid2) + @@ -639,8 +839,6 @@ static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries) return cpuid; } -const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, - uint32_t function, uint32_t index); void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid); void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu); @@ -701,17 +899,6 @@ static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu, vcpu_set_or_clear_cpuid_feature(vcpu, feature, false); } -static inline const struct kvm_cpuid_entry2 *__kvm_get_supported_cpuid_entry(uint32_t function, - uint32_t index) -{ - return get_cpuid_entry(kvm_get_supported_cpuid(), function, index); -} - -static inline const struct kvm_cpuid_entry2 *kvm_get_supported_cpuid_entry(uint32_t function) -{ - return __kvm_get_supported_cpuid_entry(function, 0); -} - 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); @@ -723,15 +910,6 @@ static inline void vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, TEST_ASSERT(r == 1, KVM_IOCTL_ERROR(KVM_SET_MSRS, r)); } -static inline uint32_t kvm_get_cpuid_max_basic(void) -{ - return kvm_get_supported_cpuid_entry(0)->eax; -} - -static inline uint32_t kvm_get_cpuid_max_extended(void) -{ - return kvm_get_supported_cpuid_entry(0x80000000)->eax; -} void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); bool vm_is_unrestricted_guest(struct kvm_vm *vm); @@ -748,6 +926,19 @@ struct ex_regs { uint64_t rflags; }; +struct idt_entry { + uint16_t offset0; + uint16_t selector; + uint16_t ist : 3; + uint16_t : 5; + uint16_t type : 4; + uint16_t : 1; + uint16_t dpl : 2; + uint16_t p : 1; + uint16_t offset1; + uint32_t offset2; uint32_t reserved; +}; + void vm_init_descriptor_tables(struct kvm_vm *vm); void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); void vm_install_exception_handler(struct kvm_vm *vm, int vector, @@ -764,7 +955,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, * for recursive faults when accessing memory in the handler. The downside to * using registers is that it restricts what registers can be used by the actual * instruction. But, selftests are 64-bit only, making register* pressure a - * minor concern. Use r9-r11 as they are volatile, i.e. don't need* to be saved + * minor concern. Use r9-r11 as they are volatile, i.e. don't need to be saved * by the callee, and except for r11 are not implicit parameters to any * instructions. Ideally, fixup would use r8-r10 and thus avoid implicit * parameters entirely, but Hyper-V's hypercall ABI uses r8 and testing Hyper-V @@ -780,39 +971,52 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector, * * REGISTER OUTPUTS: * r9 = exception vector (non-zero) + * r10 = error code */ #define KVM_ASM_SAFE(insn) \ "mov $" __stringify(KVM_EXCEPTION_MAGIC) ", %%r9\n\t" \ "lea 1f(%%rip), %%r10\n\t" \ "lea 2f(%%rip), %%r11\n\t" \ "1: " insn "\n\t" \ - "movb $0, %[vector]\n\t" \ - "jmp 3f\n\t" \ + "xor %%r9, %%r9\n\t" \ "2:\n\t" \ "mov %%r9b, %[vector]\n\t" \ - "3:\n\t" + "mov %%r10, %[error_code]\n\t" -#define KVM_ASM_SAFE_OUTPUTS(v) [vector] "=qm"(v) +#define KVM_ASM_SAFE_OUTPUTS(v, ec) [vector] "=qm"(v), [error_code] "=rm"(ec) #define KVM_ASM_SAFE_CLOBBERS "r9", "r10", "r11" -#define kvm_asm_safe(insn, inputs...) \ -({ \ - uint8_t vector; \ - \ - asm volatile(KVM_ASM_SAFE(insn) \ - : KVM_ASM_SAFE_OUTPUTS(vector) \ - : inputs \ - : KVM_ASM_SAFE_CLOBBERS); \ - vector; \ +#define kvm_asm_safe(insn, inputs...) \ +({ \ + uint64_t ign_error_code; \ + uint8_t vector; \ + \ + asm volatile(KVM_ASM_SAFE(insn) \ + : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \ + : inputs \ + : KVM_ASM_SAFE_CLOBBERS); \ + vector; \ +}) + +#define kvm_asm_safe_ec(insn, error_code, inputs...) \ +({ \ + uint8_t vector; \ + \ + asm volatile(KVM_ASM_SAFE(insn) \ + : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \ + : inputs \ + : KVM_ASM_SAFE_CLOBBERS); \ + vector; \ }) static inline uint8_t rdmsr_safe(uint32_t msr, uint64_t *val) { + uint64_t error_code; uint8_t vector; uint32_t a, d; asm volatile(KVM_ASM_SAFE("rdmsr") - : "=a"(a), "=d"(d), KVM_ASM_SAFE_OUTPUTS(vector) + : "=a"(a), "=d"(d), KVM_ASM_SAFE_OUTPUTS(vector, error_code) : "c"(msr) : KVM_ASM_SAFE_CLOBBERS); @@ -827,10 +1031,9 @@ static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val) bool kvm_is_tdp_enabled(void); -uint64_t vm_get_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, - uint64_t vaddr); -void vm_set_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, - uint64_t vaddr, uint64_t pte); +uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, + int *level); +uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr); uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t a3); @@ -882,4 +1085,27 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, #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 +#define PFERR_RSVD_BIT 3 +#define PFERR_FETCH_BIT 4 +#define PFERR_PK_BIT 5 +#define PFERR_SGX_BIT 15 +#define PFERR_GUEST_FINAL_BIT 32 +#define PFERR_GUEST_PAGE_BIT 33 +#define PFERR_IMPLICIT_ACCESS_BIT 48 + +#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT) +#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT) +#define PFERR_USER_MASK BIT(PFERR_USER_BIT) +#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT) +#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT) +#define PFERR_PK_MASK BIT(PFERR_PK_BIT) +#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT) +#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT) +#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT) +#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT) + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h index c8343ff84f7f..4803e1056055 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm.h @@ -58,6 +58,27 @@ enum { INTERCEPT_RDPRU, }; +struct hv_vmcb_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 enlightened_npt_tlb: 1; + u32 reserved:29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB + */ +#define HV_VMCB_NESTED_ENLIGHTENMENTS (1U << 31) + +/* Synthetic VM-Exit */ +#define HV_SVM_EXITCODE_ENL 0xf0000000 +#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1) struct __attribute__ ((__packed__)) vmcb_control_area { u32 intercept_cr; @@ -106,7 +127,10 @@ struct __attribute__ ((__packed__)) vmcb_control_area { * Offset 0x3e0, 32 bytes reserved * for use by hypervisor/software. */ - u8 reserved_sw[32]; + union { + struct hv_vmcb_enlightenments hv_enlightenments; + u8 reserved_sw[32]; + }; }; diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h index 7aee6244ab6a..044f0f872ba9 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -32,6 +32,20 @@ struct svm_test_data { uint64_t msr_gpa; }; +static inline void vmmcall(void) +{ + /* + * Stuff RAX and RCX with "safe" values to make sure L0 doesn't handle + * it as a valid hypercall (e.g. Hyper-V L2 TLB flush) as the intended + * use of this function is to exit to L1 from L2. Clobber all other + * GPRs as L1 doesn't correctly preserve them during vmexits. + */ + __asm__ __volatile__("push %%rbp; vmmcall; pop %%rbp" + : : "a"(0xdeadbeef), "c"(0xbeefdead) + : "rbx", "rdx", "rsi", "rdi", "r8", "r9", + "r10", "r11", "r12", "r13", "r14", "r15"); +} + #define stgi() \ __asm__ __volatile__( \ "stgi\n" \ diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index 71b290b6469d..5f0c0a29c556 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -437,11 +437,16 @@ static inline int vmresume(void) static inline void vmcall(void) { - /* Currently, L1 destroys our GPRs during vmexits. */ - __asm__ __volatile__("push %%rbp; vmcall; pop %%rbp" : : : - "rax", "rbx", "rcx", "rdx", - "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", - "r13", "r14", "r15"); + /* + * Stuff RAX and RCX with "safe" values to make sure L0 doesn't handle + * it as a valid hypercall (e.g. Hyper-V L2 TLB flush) as the intended + * use of this function is to exit to L1 from L2. Clobber all other + * GPRs as L1 doesn't correctly preserve them during vmexits. + */ + __asm__ __volatile__("push %%rbp; vmcall; pop %%rbp" + : : "a"(0xdeadbeef), "c"(0xbeefdead) + : "rbx", "rdx", "rsi", "rdi", "r8", "r9", + "r10", "r11", "r12", "r13", "r14", "r15"); } static inline int vmread(uint64_t encoding, uint64_t *value) @@ -517,14 +522,6 @@ struct vmx_pages { uint64_t vmwrite_gpa; void *vmwrite; - void *vp_assist_hva; - uint64_t vp_assist_gpa; - void *vp_assist; - - void *enlightened_vmcs_hva; - uint64_t enlightened_vmcs_gpa; - void *enlightened_vmcs; - void *eptp_hva; uint64_t eptp_gpa; void *eptp; @@ -572,7 +569,7 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm, uint32_t memslot); void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm, uint64_t addr, uint64_t size); -bool kvm_vm_has_ept(struct kvm_vm *vm); +bool kvm_cpu_has_ept(void); void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, uint32_t eptp_memslot); void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm); diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index f42c6ac6d71d..b3b00be1ef82 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -289,7 +289,6 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem); /* Export shared structure test_args to guest */ - ucall_init(vm, NULL); sync_global_to_guest(vm, test_args); ret = sem_init(&test_stage_updated, 0, 0); @@ -417,7 +416,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) TEST_ASSERT(ret == 0, "Error in sem_destroy"); free(vcpu_threads); - ucall_uninit(vm); kvm_vm_free(vm); } @@ -461,8 +459,8 @@ int main(int argc, char *argv[]) p.test_mem_size = parse_size(optarg); break; case 'v': - nr_vcpus = atoi(optarg); - TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, + nr_vcpus = atoi_positive("Number of vCPUs", optarg); + TEST_ASSERT(nr_vcpus <= max_vcpus, "Invalid number of vcpus, must be between 1 and %d", max_vcpus); break; case 's': diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 6f5551368944..0de4aabc0c76 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -495,15 +495,6 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, close(kvm_fd); } -/* - * arm64 doesn't have a true default mode, so start by computing the - * available IPA space and page sizes early. - */ -void __attribute__((constructor)) init_guest_modes(void) -{ - guest_modes_append_default(); -} - 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) @@ -528,3 +519,12 @@ void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, [arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6) : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7"); } + +void kvm_selftest_arch_init(void) +{ + /* + * arm64 doesn't have a true default mode, so start by computing the + * available IPA space and page sizes early. + */ + guest_modes_append_default(); +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index ed237b744690..562c16dfbb00 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -6,108 +6,36 @@ */ #include "kvm_util.h" +/* + * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each + * VM), it must not be accessed from host code. + */ static vm_vaddr_t *ucall_exit_mmio_addr; -static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa) -{ - if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1)) - return false; - - virt_pg_map(vm, gpa, gpa); - - ucall_exit_mmio_addr = (vm_vaddr_t *)gpa; - sync_global_to_guest(vm, ucall_exit_mmio_addr); - - return true; -} - -void ucall_init(struct kvm_vm *vm, void *arg) +void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) { - vm_paddr_t gpa, start, end, step, offset; - unsigned int bits; - bool ret; + virt_pg_map(vm, mmio_gpa, mmio_gpa); - if (arg) { - gpa = (vm_paddr_t)arg; - ret = ucall_mmio_init(vm, gpa); - TEST_ASSERT(ret, "Can't set ucall mmio address to %lx", gpa); - return; - } + vm->ucall_mmio_addr = mmio_gpa; - /* - * Find an address within the allowed physical and virtual address - * spaces, that does _not_ have a KVM memory region associated with - * it. Identity mapping an address like this allows the guest to - * access it, but as KVM doesn't know what to do with it, it - * will assume it's something userspace handles and exit with - * KVM_EXIT_MMIO. Well, at least that's how it works for AArch64. - * Here we start with a guess that the addresses around 5/8th - * of the allowed space are unmapped and then work both down and - * up from there in 1/16th allowed space sized steps. - * - * Note, we need to use VA-bits - 1 when calculating the allowed - * virtual address space for an identity mapping because the upper - * half of the virtual address space is the two's complement of the - * lower and won't match physical addresses. - */ - bits = vm->va_bits - 1; - bits = min(vm->pa_bits, bits); - end = 1ul << bits; - start = end * 5 / 8; - step = end / 16; - for (offset = 0; offset < end - start; offset += step) { - if (ucall_mmio_init(vm, start - offset)) - return; - if (ucall_mmio_init(vm, start + offset)) - return; - } - TEST_FAIL("Can't find a ucall mmio address"); + write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gpa); } -void ucall_uninit(struct kvm_vm *vm) +void ucall_arch_do_ucall(vm_vaddr_t uc) { - ucall_exit_mmio_addr = 0; - sync_global_to_guest(vm, ucall_exit_mmio_addr); + WRITE_ONCE(*ucall_exit_mmio_addr, uc); } -void ucall(uint64_t cmd, int nargs, ...) -{ - struct ucall uc = {}; - va_list va; - int i; - - WRITE_ONCE(uc.cmd, cmd); - nargs = min(nargs, UCALL_MAX_ARGS); - - va_start(va, nargs); - for (i = 0; i < nargs; ++i) - WRITE_ONCE(uc.args[i], va_arg(va, uint64_t)); - va_end(va); - - WRITE_ONCE(*ucall_exit_mmio_addr, (vm_vaddr_t)&uc); -} - -uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) +void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; - struct ucall ucall = {}; - - if (uc) - memset(uc, 0, sizeof(*uc)); if (run->exit_reason == KVM_EXIT_MMIO && - run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) { - vm_vaddr_t gva; - - TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8, + run->mmio.phys_addr == vcpu->vm->ucall_mmio_addr) { + TEST_ASSERT(run->mmio.is_write && run->mmio.len == sizeof(uint64_t), "Unexpected ucall exit mmio address access"); - memcpy(&gva, run->mmio.data, sizeof(gva)); - memcpy(&ucall, addr_gva2hva(vcpu->vm, gva), sizeof(ucall)); - - vcpu_run_complete_io(vcpu); - if (uc) - memcpy(uc, &ucall, sizeof(ucall)); + return (void *)(*((uint64_t *)run->mmio.data)); } - return ucall.cmd; + return NULL; } diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index 9f54c098d9d0..d71a9a5974de 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -138,7 +138,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename) offset = hdr.e_phoff + (n1 * hdr.e_phentsize); offset_rv = lseek(fd, offset, SEEK_SET); TEST_ASSERT(offset_rv == offset, - "Failed to seek to begining of program header %u,\n" + "Failed to seek to beginning of program header %u,\n" " filename: %s\n" " rv: %jd errno: %i", n1, filename, (intmax_t) offset_rv, errno); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index f1cb1627161f..1d26a2160178 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -11,6 +11,7 @@ #include "processor.h" #include <assert.h> +#include <sched.h> #include <sys/mman.h> #include <sys/types.h> #include <sys/stat.h> @@ -334,15 +335,24 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, { uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus, nr_extra_pages); + struct userspace_mem_region *slot0; struct kvm_vm *vm; vm = ____vm_create(mode, nr_pages); kvm_vm_elf_load(vm, program_invocation_name); -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif + /* + * TODO: Add proper defines to protect the library's memslots, and then + * carve out memslot1 for the ucall MMIO address. KVM treats writes to + * read-only memslots as MMIO, and creating a read-only memslot for the + * MMIO region would prevent silently clobbering the MMIO region. + */ + slot0 = memslot2region(vm, 0); + ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size); + + kvm_arch_vm_post_create(vm); + return vm; } @@ -443,6 +453,59 @@ struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm) return vm_vcpu_recreate(vm, 0); } +void kvm_pin_this_task_to_pcpu(uint32_t pcpu) +{ + cpu_set_t mask; + int r; + + CPU_ZERO(&mask); + CPU_SET(pcpu, &mask); + r = sched_setaffinity(0, sizeof(mask), &mask); + TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.\n", pcpu); +} + +static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask) +{ + uint32_t pcpu = atoi_non_negative("CPU number", cpu_str); + + TEST_ASSERT(CPU_ISSET(pcpu, allowed_mask), + "Not allowed to run on pCPU '%d', check cgroups?\n", pcpu); + return pcpu; +} + +void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], + int nr_vcpus) +{ + cpu_set_t allowed_mask; + char *cpu, *cpu_list; + char delim[2] = ","; + int i, r; + + cpu_list = strdup(pcpus_string); + TEST_ASSERT(cpu_list, "strdup() allocation failed.\n"); + + r = sched_getaffinity(0, sizeof(allowed_mask), &allowed_mask); + TEST_ASSERT(!r, "sched_getaffinity() failed"); + + cpu = strtok(cpu_list, delim); + + /* 1. Get all pcpus for vcpus. */ + for (i = 0; i < nr_vcpus; i++) { + TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'\n", i); + vcpu_to_pcpu[i] = parse_pcpu(cpu, &allowed_mask); + cpu = strtok(NULL, delim); + } + + /* 2. Check if the main worker needs to be pinned. */ + if (cpu) { + kvm_pin_this_task_to_pcpu(parse_pcpu(cpu, &allowed_mask)); + cpu = strtok(NULL, delim); + } + + TEST_ASSERT(!cpu, "pCPU list contains trailing garbage characters '%s'", cpu); + free(cpu_list); +} + /* * Userspace Memory Region Find * @@ -1151,8 +1214,8 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) * TEST_ASSERT failure occurs for invalid input or no area of at least * sz unallocated bytes >= vaddr_min is available. */ -static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, - vm_vaddr_t vaddr_min) +vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min) { uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift; @@ -1256,8 +1319,7 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min) virt_pg_map(vm, vaddr, paddr); - sparsebit_set(vm->vpages_mapped, - vaddr >> vm->page_shift); + sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift); } return vaddr_start; @@ -1330,6 +1392,8 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, virt_pg_map(vm, vaddr, paddr); vaddr += page_size; paddr += page_size; + + sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift); } } @@ -2021,3 +2085,19 @@ void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data, break; } } + +__weak void kvm_arch_vm_post_create(struct kvm_vm *vm) +{ +} + +__weak void kvm_selftest_arch_init(void) +{ +} + +void __attribute((constructor)) kvm_selftest_init(void) +{ + /* Tell stdout not to buffer its content. */ + setbuf(stdout, NULL); + + kvm_selftest_arch_init(); +} diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/memstress.c index 9618b37c66f7..2de8a5d527b3 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/memstress.c @@ -2,13 +2,15 @@ /* * Copyright (C) 2020, Google LLC. */ +#define _GNU_SOURCE + #include <inttypes.h> #include "kvm_util.h" -#include "perf_test_util.h" +#include "memstress.h" #include "processor.h" -struct perf_test_args perf_test_args; +struct memstress_args memstress_args; /* * Guest virtual memory offset of the testing memory slot. @@ -31,7 +33,7 @@ struct vcpu_thread { static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS]; /* The function run by each vCPU thread, as provided by the test. */ -static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *); +static void (*vcpu_thread_fn)(struct memstress_vcpu_args *); /* Set to true once all vCPU threads are up and running. */ static bool all_vcpu_threads_running; @@ -42,14 +44,19 @@ static struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; * Continuously write to the first 8 bytes of each page in the * specified region. */ -void perf_test_guest_code(uint32_t vcpu_idx) +void memstress_guest_code(uint32_t vcpu_idx) { - struct perf_test_args *pta = &perf_test_args; - struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_idx]; + struct memstress_args *args = &memstress_args; + struct memstress_vcpu_args *vcpu_args = &args->vcpu_args[vcpu_idx]; + struct guest_random_state rand_state; uint64_t gva; uint64_t pages; + uint64_t addr; + uint64_t page; int i; + rand_state = new_guest_random_state(args->random_seed + vcpu_idx); + gva = vcpu_args->gva; pages = vcpu_args->pages; @@ -58,9 +65,14 @@ void perf_test_guest_code(uint32_t vcpu_idx) while (true) { for (i = 0; i < pages; i++) { - uint64_t addr = gva + (i * pta->guest_page_size); + if (args->random_access) + page = guest_random_u32(&rand_state) % pages; + else + page = i; - if (i % pta->wr_fract == 0) + addr = gva + (page * args->guest_page_size); + + if (guest_random_u32(&rand_state) % 100 < args->write_percent) *(uint64_t *)addr = 0x0123456789ABCDEF; else READ_ONCE(*(uint64_t *)addr); @@ -70,17 +82,17 @@ void perf_test_guest_code(uint32_t vcpu_idx) } } -void perf_test_setup_vcpus(struct kvm_vm *vm, int nr_vcpus, +void memstress_setup_vcpus(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[], uint64_t vcpu_memory_bytes, bool partition_vcpu_memory_access) { - struct perf_test_args *pta = &perf_test_args; - struct perf_test_vcpu_args *vcpu_args; + struct memstress_args *args = &memstress_args; + struct memstress_vcpu_args *vcpu_args; int i; for (i = 0; i < nr_vcpus; i++) { - vcpu_args = &pta->vcpu_args[i]; + vcpu_args = &args->vcpu_args[i]; vcpu_args->vcpu = vcpus[i]; vcpu_args->vcpu_idx = i; @@ -89,29 +101,29 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int nr_vcpus, vcpu_args->gva = guest_test_virt_mem + (i * vcpu_memory_bytes); vcpu_args->pages = vcpu_memory_bytes / - pta->guest_page_size; - vcpu_args->gpa = pta->gpa + (i * vcpu_memory_bytes); + args->guest_page_size; + vcpu_args->gpa = args->gpa + (i * vcpu_memory_bytes); } else { vcpu_args->gva = guest_test_virt_mem; vcpu_args->pages = (nr_vcpus * vcpu_memory_bytes) / - pta->guest_page_size; - vcpu_args->gpa = pta->gpa; + args->guest_page_size; + vcpu_args->gpa = args->gpa; } vcpu_args_set(vcpus[i], 1, i); pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", i, vcpu_args->gpa, vcpu_args->gpa + - (vcpu_args->pages * pta->guest_page_size)); + (vcpu_args->pages * args->guest_page_size)); } } -struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus, +struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, uint64_t vcpu_memory_bytes, int slots, enum vm_mem_backing_src_type backing_src, bool partition_vcpu_memory_access) { - struct perf_test_args *pta = &perf_test_args; + struct memstress_args *args = &memstress_args; struct kvm_vm *vm; uint64_t guest_num_pages, slot0_pages = 0; uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src); @@ -121,20 +133,20 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus, pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); /* By default vCPUs will write to memory. */ - pta->wr_fract = 1; + args->write_percent = 100; /* * Snapshot the non-huge page size. This is used by the guest code to * access/dirty pages at the logging granularity. */ - pta->guest_page_size = vm_guest_mode_params[mode].page_size; + args->guest_page_size = vm_guest_mode_params[mode].page_size; guest_num_pages = vm_adjust_num_guest_pages(mode, - (nr_vcpus * vcpu_memory_bytes) / pta->guest_page_size); + (nr_vcpus * vcpu_memory_bytes) / args->guest_page_size); TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0, "Guest memory size is not host page size aligned."); - TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0, + TEST_ASSERT(vcpu_memory_bytes % args->guest_page_size == 0, "Guest memory size is not guest page size aligned."); TEST_ASSERT(guest_num_pages % slots == 0, "Guest memory cannot be evenly divided into %d slots.", @@ -144,8 +156,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus, * If using nested, allocate extra pages for the nested page tables and * in-memory data structures. */ - if (pta->nested) - slot0_pages += perf_test_nested_pages(nr_vcpus); + if (args->nested) + slot0_pages += memstress_nested_pages(nr_vcpus); /* * Pass guest_num_pages to populate the page tables for test memory. @@ -153,9 +165,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus, * effect as KVM allows aliasing HVAs in meslots. */ vm = __vm_create_with_vcpus(mode, nr_vcpus, slot0_pages + guest_num_pages, - perf_test_guest_code, vcpus); + memstress_guest_code, vcpus); - pta->vm = vm; + args->vm = vm; /* Put the test region at the top guest physical memory. */ region_end_gfn = vm->max_gfn + 1; @@ -165,8 +177,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus, * When running vCPUs in L2, restrict the test region to 48 bits to * avoid needing 5-level page tables to identity map L2. */ - if (pta->nested) - region_end_gfn = min(region_end_gfn, (1UL << 48) / pta->guest_page_size); + if (args->nested) + region_end_gfn = min(region_end_gfn, (1UL << 48) / args->guest_page_size); #endif /* * If there should be more memory in the guest test region than there @@ -178,63 +190,72 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus, " nr_vcpus: %d wss: %" PRIx64 "]\n", guest_num_pages, region_end_gfn - 1, nr_vcpus, vcpu_memory_bytes); - pta->gpa = (region_end_gfn - guest_num_pages - 1) * pta->guest_page_size; - pta->gpa = align_down(pta->gpa, backing_src_pagesz); + args->gpa = (region_end_gfn - guest_num_pages - 1) * args->guest_page_size; + args->gpa = align_down(args->gpa, backing_src_pagesz); #ifdef __s390x__ /* Align to 1M (segment size) */ - pta->gpa = align_down(pta->gpa, 1 << 20); + args->gpa = align_down(args->gpa, 1 << 20); #endif - pta->size = guest_num_pages * pta->guest_page_size; + args->size = guest_num_pages * args->guest_page_size; pr_info("guest physical test memory: [0x%lx, 0x%lx)\n", - pta->gpa, pta->gpa + pta->size); + args->gpa, args->gpa + args->size); /* Add extra memory slots for testing */ for (i = 0; i < slots; i++) { uint64_t region_pages = guest_num_pages / slots; - vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i; + vm_paddr_t region_start = args->gpa + region_pages * args->guest_page_size * i; vm_userspace_mem_region_add(vm, backing_src, region_start, - PERF_TEST_MEM_SLOT_INDEX + i, + MEMSTRESS_MEM_SLOT_INDEX + i, region_pages, 0); } /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages); + virt_map(vm, guest_test_virt_mem, args->gpa, guest_num_pages); - perf_test_setup_vcpus(vm, nr_vcpus, vcpus, vcpu_memory_bytes, + memstress_setup_vcpus(vm, nr_vcpus, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access); - if (pta->nested) { + if (args->nested) { pr_info("Configuring vCPUs to run in L2 (nested).\n"); - perf_test_setup_nested(vm, nr_vcpus, vcpus); + memstress_setup_nested(vm, nr_vcpus, vcpus); } - ucall_init(vm, NULL); - /* Export the shared variables to the guest. */ - sync_global_to_guest(vm, perf_test_args); + sync_global_to_guest(vm, memstress_args); return vm; } -void perf_test_destroy_vm(struct kvm_vm *vm) +void memstress_destroy_vm(struct kvm_vm *vm) { - ucall_uninit(vm); kvm_vm_free(vm); } -void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract) +void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent) +{ + memstress_args.write_percent = write_percent; + sync_global_to_guest(vm, memstress_args.write_percent); +} + +void memstress_set_random_seed(struct kvm_vm *vm, uint32_t random_seed) +{ + memstress_args.random_seed = random_seed; + sync_global_to_guest(vm, memstress_args.random_seed); +} + +void memstress_set_random_access(struct kvm_vm *vm, bool random_access) { - perf_test_args.wr_fract = wr_fract; - sync_global_to_guest(vm, perf_test_args); + memstress_args.random_access = random_access; + sync_global_to_guest(vm, memstress_args.random_access); } -uint64_t __weak perf_test_nested_pages(int nr_vcpus) +uint64_t __weak memstress_nested_pages(int nr_vcpus) { return 0; } -void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu **vcpus) +void __weak memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu **vcpus) { pr_info("%s() not support on this architecture, skipping.\n", __func__); exit(KSFT_SKIP); @@ -243,6 +264,10 @@ void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_v static void *vcpu_thread_main(void *data) { struct vcpu_thread *vcpu = data; + int vcpu_idx = vcpu->vcpu_idx; + + if (memstress_args.pin_vcpus) + kvm_pin_this_task_to_pcpu(memstress_args.vcpu_to_pcpu[vcpu_idx]); WRITE_ONCE(vcpu->running, true); @@ -255,13 +280,13 @@ static void *vcpu_thread_main(void *data) while (!READ_ONCE(all_vcpu_threads_running)) ; - vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_idx]); + vcpu_thread_fn(&memstress_args.vcpu_args[vcpu_idx]); return NULL; } -void perf_test_start_vcpu_threads(int nr_vcpus, - void (*vcpu_fn)(struct perf_test_vcpu_args *)) +void memstress_start_vcpu_threads(int nr_vcpus, + void (*vcpu_fn)(struct memstress_vcpu_args *)) { int i; @@ -285,7 +310,7 @@ void perf_test_start_vcpu_threads(int nr_vcpus, WRITE_ONCE(all_vcpu_threads_running, true); } -void perf_test_join_vcpu_threads(int nr_vcpus) +void memstress_join_vcpu_threads(int nr_vcpus) { int i; diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c index 087b9740bc8f..9a3476a2dfca 100644 --- a/tools/testing/selftests/kvm/lib/riscv/ucall.c +++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c @@ -10,11 +10,7 @@ #include "kvm_util.h" #include "processor.h" -void ucall_init(struct kvm_vm *vm, void *arg) -{ -} - -void ucall_uninit(struct kvm_vm *vm) +void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) { } @@ -44,47 +40,22 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, return ret; } -void ucall(uint64_t cmd, int nargs, ...) +void ucall_arch_do_ucall(vm_vaddr_t uc) { - struct ucall uc = { - .cmd = cmd, - }; - va_list va; - int i; - - nargs = min(nargs, UCALL_MAX_ARGS); - - va_start(va, nargs); - for (i = 0; i < nargs; ++i) - uc.args[i] = va_arg(va, uint64_t); - va_end(va); - sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, KVM_RISCV_SELFTESTS_SBI_UCALL, - (vm_vaddr_t)&uc, 0, 0, 0, 0, 0); + uc, 0, 0, 0, 0, 0); } -uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) +void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; - struct ucall ucall = {}; - - if (uc) - memset(uc, 0, sizeof(*uc)); if (run->exit_reason == KVM_EXIT_RISCV_SBI && run->riscv_sbi.extension_id == KVM_RISCV_SELFTESTS_SBI_EXT) { switch (run->riscv_sbi.function_id) { case KVM_RISCV_SELFTESTS_SBI_UCALL: - memcpy(&ucall, - addr_gva2hva(vcpu->vm, run->riscv_sbi.args[0]), - sizeof(ucall)); - - vcpu_run_complete_io(vcpu); - if (uc) - memcpy(uc, &ucall, sizeof(ucall)); - - break; + return (void *)run->riscv_sbi.args[0]; case KVM_RISCV_SELFTESTS_SBI_UNEXP: vcpu_dump(stderr, vcpu, 2); TEST_ASSERT(0, "Unexpected trap taken by guest"); @@ -93,6 +64,5 @@ uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) break; } } - - return ucall.cmd; + return NULL; } diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c index 73dc4e21190f..a7f02dc372cf 100644 --- a/tools/testing/selftests/kvm/lib/s390x/ucall.c +++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c @@ -6,40 +6,19 @@ */ #include "kvm_util.h" -void ucall_init(struct kvm_vm *vm, void *arg) +void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) { } -void ucall_uninit(struct kvm_vm *vm) +void ucall_arch_do_ucall(vm_vaddr_t uc) { -} - -void ucall(uint64_t cmd, int nargs, ...) -{ - struct ucall uc = { - .cmd = cmd, - }; - va_list va; - int i; - - nargs = min(nargs, UCALL_MAX_ARGS); - - va_start(va, nargs); - for (i = 0; i < nargs; ++i) - uc.args[i] = va_arg(va, uint64_t); - va_end(va); - /* Exit via DIAGNOSE 0x501 (normally used for breakpoints) */ - asm volatile ("diag 0,%0,0x501" : : "a"(&uc) : "memory"); + asm volatile ("diag 0,%0,0x501" : : "a"(uc) : "memory"); } -uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) +void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; - struct ucall ucall = {}; - - if (uc) - memset(uc, 0, sizeof(*uc)); if (run->exit_reason == KVM_EXIT_S390_SIEIC && run->s390_sieic.icptcode == 4 && @@ -47,13 +26,7 @@ uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) (run->s390_sieic.ipb >> 16) == 0x501) { int reg = run->s390_sieic.ipa & 0xf; - memcpy(&ucall, addr_gva2hva(vcpu->vm, run->s.regs.gprs[reg]), - sizeof(ucall)); - - vcpu_run_complete_io(vcpu); - if (uc) - memcpy(uc, &ucall, sizeof(ucall)); + return (void *)run->s.regs.gprs[reg]; } - - return ucall.cmd; + return NULL; } diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 6d23878bbfe1..5c22fa4c2825 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -18,6 +18,23 @@ #include "test_util.h" /* + * Random number generator that is usable from guest code. This is the + * Park-Miller LCG using standard constants. + */ + +struct guest_random_state new_guest_random_state(uint32_t seed) +{ + struct guest_random_state s = {.seed = seed}; + return s; +} + +uint32_t guest_random_u32(struct guest_random_state *state) +{ + state->seed = (uint64_t)state->seed * 48271 % ((uint32_t)(1 << 31) - 1); + return state->seed; +} + +/* * Parses "[0-9]+[kmgt]?". */ size_t parse_size(const char *size) @@ -334,3 +351,22 @@ long get_run_delay(void) return val[1]; } + +int atoi_paranoid(const char *num_str) +{ + char *end_ptr; + long num; + + errno = 0; + num = strtol(num_str, &end_ptr, 0); + TEST_ASSERT(!errno, "strtol(\"%s\") failed", num_str); + TEST_ASSERT(num_str != end_ptr, + "strtol(\"%s\") didn't find a valid integer.", num_str); + TEST_ASSERT(*end_ptr == '\0', + "strtol(\"%s\") failed to parse trailing characters \"%s\".", + num_str, end_ptr); + TEST_ASSERT(num >= INT_MIN && num <= INT_MAX, + "%ld not in range of [%d, %d]", num, INT_MIN, INT_MAX); + + return num; +} diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c new file mode 100644 index 000000000000..fcae96461e46 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/ucall_common.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "kvm_util.h" +#include "linux/types.h" +#include "linux/bitmap.h" +#include "linux/atomic.h" + +struct ucall_header { + DECLARE_BITMAP(in_use, KVM_MAX_VCPUS); + struct ucall ucalls[KVM_MAX_VCPUS]; +}; + +/* + * ucall_pool holds per-VM values (global data is duplicated by each VM), it + * must not be accessed from host code. + */ +static struct ucall_header *ucall_pool; + +void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) +{ + struct ucall_header *hdr; + struct ucall *uc; + vm_vaddr_t vaddr; + int i; + + vaddr = vm_vaddr_alloc(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR); + hdr = (struct ucall_header *)addr_gva2hva(vm, vaddr); + memset(hdr, 0, sizeof(*hdr)); + + for (i = 0; i < KVM_MAX_VCPUS; ++i) { + uc = &hdr->ucalls[i]; + uc->hva = uc; + } + + write_guest_global(vm, ucall_pool, (struct ucall_header *)vaddr); + + ucall_arch_init(vm, mmio_gpa); +} + +static struct ucall *ucall_alloc(void) +{ + struct ucall *uc; + int i; + + GUEST_ASSERT(ucall_pool); + + for (i = 0; i < KVM_MAX_VCPUS; ++i) { + if (!atomic_test_and_set_bit(i, ucall_pool->in_use)) { + uc = &ucall_pool->ucalls[i]; + memset(uc->args, 0, sizeof(uc->args)); + return uc; + } + } + + GUEST_ASSERT(0); + return NULL; +} + +static void ucall_free(struct ucall *uc) +{ + /* Beware, here be pointer arithmetic. */ + clear_bit(uc - ucall_pool->ucalls, ucall_pool->in_use); +} + +void ucall(uint64_t cmd, int nargs, ...) +{ + struct ucall *uc; + va_list va; + int i; + + uc = ucall_alloc(); + + WRITE_ONCE(uc->cmd, cmd); + + nargs = min(nargs, UCALL_MAX_ARGS); + + va_start(va, nargs); + for (i = 0; i < nargs; ++i) + WRITE_ONCE(uc->args[i], va_arg(va, uint64_t)); + va_end(va); + + ucall_arch_do_ucall((vm_vaddr_t)uc->hva); + + ucall_free(uc); +} + +uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) +{ + struct ucall ucall; + void *addr; + + if (!uc) + uc = &ucall; + + addr = ucall_arch_get_ucall(vcpu); + if (addr) { + memcpy(uc, addr, sizeof(*uc)); + vcpu_run_complete_io(vcpu); + } else { + memset(uc, 0, sizeof(*uc)); + } + + return uc->cmd; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c new file mode 100644 index 000000000000..efb7e7a1354d --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Hyper-V specific functions. + * + * Copyright (C) 2021, Red Hat Inc. + */ +#include <stdint.h> +#include "processor.h" +#include "hyperv.h" + +struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, + vm_vaddr_t *p_hv_pages_gva) +{ + vm_vaddr_t hv_pages_gva = vm_vaddr_alloc_page(vm); + struct hyperv_test_pages *hv = addr_gva2hva(vm, hv_pages_gva); + + /* Setup of a region of guest memory for the VP Assist page. */ + hv->vp_assist = (void *)vm_vaddr_alloc_page(vm); + hv->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)hv->vp_assist); + hv->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)hv->vp_assist); + + /* Setup of a region of guest memory for the partition assist page. */ + hv->partition_assist = (void *)vm_vaddr_alloc_page(vm); + hv->partition_assist_hva = addr_gva2hva(vm, (uintptr_t)hv->partition_assist); + hv->partition_assist_gpa = addr_gva2gpa(vm, (uintptr_t)hv->partition_assist); + + /* Setup of a region of guest memory for the enlightened VMCS. */ + hv->enlightened_vmcs = (void *)vm_vaddr_alloc_page(vm); + hv->enlightened_vmcs_hva = addr_gva2hva(vm, (uintptr_t)hv->enlightened_vmcs); + hv->enlightened_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)hv->enlightened_vmcs); + + *p_hv_pages_gva = hv_pages_gva; + return hv; +} + +int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist) +{ + uint64_t val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) | + HV_X64_MSR_VP_ASSIST_PAGE_ENABLE; + + wrmsr(HV_X64_MSR_VP_ASSIST_PAGE, val); + + current_vp_assist = vp_assist; + + return 0; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c b/tools/testing/selftests/kvm/lib/x86_64/memstress.c index 0f344a7c89c4..d61e623afc8c 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/x86_64/memstress.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * x86_64-specific extensions to perf_test_util.c. + * x86_64-specific extensions to memstress.c. * * Copyright (C) 2022, Google, Inc. */ @@ -11,25 +11,25 @@ #include "test_util.h" #include "kvm_util.h" -#include "perf_test_util.h" +#include "memstress.h" #include "processor.h" #include "vmx.h" -void perf_test_l2_guest_code(uint64_t vcpu_id) +void memstress_l2_guest_code(uint64_t vcpu_id) { - perf_test_guest_code(vcpu_id); + memstress_guest_code(vcpu_id); vmcall(); } -extern char perf_test_l2_guest_entry[]; +extern char memstress_l2_guest_entry[]; __asm__( -"perf_test_l2_guest_entry:" +"memstress_l2_guest_entry:" " mov (%rsp), %rdi;" -" call perf_test_l2_guest_code;" +" call memstress_l2_guest_code;" " ud2;" ); -static void perf_test_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id) +static void memstress_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; @@ -42,14 +42,14 @@ static void perf_test_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id) rsp = &l2_guest_stack[L2_GUEST_STACK_SIZE - 1]; *rsp = vcpu_id; - prepare_vmcs(vmx, perf_test_l2_guest_entry, rsp); + prepare_vmcs(vmx, memstress_l2_guest_entry, rsp); GUEST_ASSERT(!vmlaunch()); GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); GUEST_DONE(); } -uint64_t perf_test_nested_pages(int nr_vcpus) +uint64_t memstress_nested_pages(int nr_vcpus) { /* * 513 page tables is enough to identity-map 256 TiB of L2 with 1G @@ -59,7 +59,7 @@ uint64_t perf_test_nested_pages(int nr_vcpus) return 513 + 10 * nr_vcpus; } -void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm) +void memstress_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm) { uint64_t start, end; @@ -72,12 +72,12 @@ void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm) */ nested_identity_map_1g(vmx, vm, 0, 0x100000000ULL); - start = align_down(perf_test_args.gpa, PG_SIZE_1G); - end = align_up(perf_test_args.gpa + perf_test_args.size, PG_SIZE_1G); + start = align_down(memstress_args.gpa, PG_SIZE_1G); + end = align_up(memstress_args.gpa + memstress_args.size, PG_SIZE_1G); nested_identity_map_1g(vmx, vm, start, end - start); } -void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]) +void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]) { struct vmx_pages *vmx, *vmx0 = NULL; struct kvm_regs regs; @@ -85,12 +85,13 @@ void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vc int vcpu_id; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_cpu_has_ept()); for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { vmx = vcpu_alloc_vmx(vm, &vmx_gva); if (vcpu_id == 0) { - perf_test_setup_ept(vmx, vm); + memstress_setup_ept(vmx, vm); vmx0 = vmx; } else { /* Share the same EPT table across all vCPUs. */ @@ -100,11 +101,11 @@ void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vc } /* - * Override the vCPU to run perf_test_l1_guest_code() which will - * bounce it into L2 before calling perf_test_guest_code(). + * Override the vCPU to run memstress_l1_guest_code() which will + * bounce it into L2 before calling memstress_guest_code(). */ vcpu_regs_get(vcpus[vcpu_id], ®s); - regs.rip = (unsigned long) perf_test_l1_guest_code; + regs.rip = (unsigned long) memstress_l1_guest_code; vcpu_regs_set(vcpus[vcpu_id], ®s); vcpu_args_set(vcpus[vcpu_id], 2, vmx_gva, vcpu_id); } diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 39c4409ef56a..d532c20c74fd 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -131,23 +131,28 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) } } -static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr, - int level) +static void *virt_get_pte(struct kvm_vm *vm, uint64_t *parent_pte, + uint64_t vaddr, int level) { - uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift); + uint64_t pt_gpa = PTE_GET_PA(*parent_pte); + uint64_t *page_table = addr_gpa2hva(vm, pt_gpa); int index = (vaddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu; + TEST_ASSERT((*parent_pte & PTE_PRESENT_MASK) || parent_pte == &vm->pgd, + "Parent PTE (level %d) not PRESENT for gva: 0x%08lx", + level + 1, vaddr); + return &page_table[index]; } static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, - uint64_t pt_pfn, + uint64_t *parent_pte, uint64_t vaddr, uint64_t paddr, int current_level, int target_level) { - uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, current_level); + uint64_t *pte = virt_get_pte(vm, parent_pte, vaddr, current_level); if (!(*pte & PTE_PRESENT_MASK)) { *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK; @@ -197,21 +202,20 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level) * Allocate upper level page tables, if not already present. Return * early if a hugepage was created. */ - pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift, - vaddr, paddr, PG_LEVEL_512G, level); + pml4e = virt_create_upper_pte(vm, &vm->pgd, vaddr, paddr, PG_LEVEL_512G, level); if (*pml4e & PTE_LARGE_MASK) return; - pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, PG_LEVEL_1G, level); + pdpe = virt_create_upper_pte(vm, pml4e, vaddr, paddr, PG_LEVEL_1G, level); if (*pdpe & PTE_LARGE_MASK) return; - pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, PG_LEVEL_2M, level); + pde = virt_create_upper_pte(vm, pdpe, vaddr, paddr, PG_LEVEL_2M, level); if (*pde & PTE_LARGE_MASK) return; /* Fill in page table entry. */ - pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, PG_LEVEL_4K); + pte = virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K); TEST_ASSERT(!(*pte & PTE_PRESENT_MASK), "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr); *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK); @@ -241,30 +245,25 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, } } -static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, - struct kvm_vcpu *vcpu, - uint64_t vaddr) +static bool vm_is_target_pte(uint64_t *pte, int *level, int current_level) { - uint16_t index[4]; - uint64_t *pml4e, *pdpe, *pde; - uint64_t *pte; - struct kvm_sregs sregs; - uint64_t rsvd_mask = 0; + if (*pte & PTE_LARGE_MASK) { + TEST_ASSERT(*level == PG_LEVEL_NONE || + *level == current_level, + "Unexpected hugepage at level %d\n", current_level); + *level = current_level; + } - /* Set the high bits in the reserved mask. */ - if (vm->pa_bits < 52) - rsvd_mask = GENMASK_ULL(51, vm->pa_bits); + return *level == current_level; +} - /* - * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries - * with 4-Level Paging and 5-Level Paging". - * If IA32_EFER.NXE = 0 and the P flag of a paging-structure entry is 1, - * the XD flag (bit 63) is reserved. - */ - vcpu_sregs_get(vcpu, &sregs); - if ((sregs.efer & EFER_NX) == 0) { - rsvd_mask |= PTE_NX_MASK; - } +uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, + int *level) +{ + uint64_t *pml4e, *pdpe, *pde; + + TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM, + "Invalid PG_LEVEL_* '%d'", *level); TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -279,54 +278,26 @@ static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, TEST_ASSERT(vaddr == (((int64_t)vaddr << 16) >> 16), "Canonical check failed. The virtual address is invalid."); - index[0] = (vaddr >> 12) & 0x1ffu; - index[1] = (vaddr >> 21) & 0x1ffu; - index[2] = (vaddr >> 30) & 0x1ffu; - index[3] = (vaddr >> 39) & 0x1ffu; + pml4e = virt_get_pte(vm, &vm->pgd, vaddr, PG_LEVEL_512G); + if (vm_is_target_pte(pml4e, level, PG_LEVEL_512G)) + return pml4e; - pml4e = addr_gpa2hva(vm, vm->pgd); - TEST_ASSERT(pml4e[index[3]] & PTE_PRESENT_MASK, - "Expected pml4e to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT((pml4e[index[3]] & (rsvd_mask | PTE_LARGE_MASK)) == 0, - "Unexpected reserved bits set."); + pdpe = virt_get_pte(vm, pml4e, vaddr, PG_LEVEL_1G); + if (vm_is_target_pte(pdpe, level, PG_LEVEL_1G)) + return pdpe; - pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); - TEST_ASSERT(pdpe[index[2]] & PTE_PRESENT_MASK, - "Expected pdpe to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(!(pdpe[index[2]] & PTE_LARGE_MASK), - "Expected pdpe to map a pde not a 1-GByte page."); - TEST_ASSERT((pdpe[index[2]] & rsvd_mask) == 0, - "Unexpected reserved bits set."); + pde = virt_get_pte(vm, pdpe, vaddr, PG_LEVEL_2M); + if (vm_is_target_pte(pde, level, PG_LEVEL_2M)) + return pde; - pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); - TEST_ASSERT(pde[index[1]] & PTE_PRESENT_MASK, - "Expected pde to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(!(pde[index[1]] & PTE_LARGE_MASK), - "Expected pde to map a pte not a 2-MByte page."); - TEST_ASSERT((pde[index[1]] & rsvd_mask) == 0, - "Unexpected reserved bits set."); - - pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); - TEST_ASSERT(pte[index[0]] & PTE_PRESENT_MASK, - "Expected pte to be present for gva: 0x%08lx", vaddr); - - return &pte[index[0]]; + return virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K); } -uint64_t vm_get_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, - uint64_t vaddr) +uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr) { - uint64_t *pte = _vm_get_page_table_entry(vm, vcpu, vaddr); + int level = PG_LEVEL_4K; - return *(uint64_t *)pte; -} - -void vm_set_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu, - uint64_t vaddr, uint64_t pte) -{ - uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpu, vaddr); - - *(uint64_t *)new_pte = pte; + return __vm_get_page_table_entry(vm, vaddr, &level); } void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) @@ -512,41 +483,17 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { - uint16_t index[4]; - uint64_t *pml4e, *pdpe, *pde; - uint64_t *pte; - - TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " - "unknown or unsupported guest mode, mode: 0x%x", vm->mode); - - index[0] = (gva >> 12) & 0x1ffu; - index[1] = (gva >> 21) & 0x1ffu; - index[2] = (gva >> 30) & 0x1ffu; - index[3] = (gva >> 39) & 0x1ffu; + int level = PG_LEVEL_NONE; + uint64_t *pte = __vm_get_page_table_entry(vm, gva, &level); - if (!vm->pgd_created) - goto unmapped_gva; - pml4e = addr_gpa2hva(vm, vm->pgd); - if (!(pml4e[index[3]] & PTE_PRESENT_MASK)) - goto unmapped_gva; + TEST_ASSERT(*pte & PTE_PRESENT_MASK, + "Leaf PTE not PRESENT for gva: 0x%08lx", gva); - pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); - if (!(pdpe[index[2]] & PTE_PRESENT_MASK)) - goto unmapped_gva; - - pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); - if (!(pde[index[1]] & PTE_PRESENT_MASK)) - goto unmapped_gva; - - pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); - if (!(pte[index[0]] & PTE_PRESENT_MASK)) - goto unmapped_gva; - - return (PTE_GET_PFN(pte[index[0]]) * vm->page_size) + (gva & ~PAGE_MASK); - -unmapped_gva: - TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva); - exit(EXIT_FAILURE); + /* + * No need for a hugepage mask on the PTE, x86-64 requires the "unused" + * address bits to be zero. + */ + return PTE_GET_PA(*pte) | (gva & ~HUGEPAGE_MASK(level)); } static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt) @@ -639,6 +586,11 @@ void __vm_xsave_require_permission(int bit, const char *name) bitmask); } +void kvm_arch_vm_post_create(struct kvm_vm *vm) +{ + vm_create_irqchip(vm); +} + struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, void *guest_code) { @@ -700,8 +652,9 @@ const struct kvm_cpuid2 *kvm_get_supported_cpuid(void) return cpuid; } -bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, - struct kvm_x86_cpu_feature feature) +static uint32_t __kvm_cpu_has(const struct kvm_cpuid2 *cpuid, + uint32_t function, uint32_t index, + uint8_t reg, uint8_t lo, uint8_t hi) { const struct kvm_cpuid_entry2 *entry; int i; @@ -714,12 +667,25 @@ bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, * order, but kvm_x86_cpu_feature matches that mess, so yay * pointer shenanigans! */ - if (entry->function == feature.function && - entry->index == feature.index) - return (&entry->eax)[feature.reg] & BIT(feature.bit); + if (entry->function == function && entry->index == index) + return ((&entry->eax)[reg] & GENMASK(hi, lo)) >> lo; } - return false; + return 0; +} + +bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_feature feature) +{ + return __kvm_cpu_has(cpuid, feature.function, feature.index, + feature.reg, feature.bit, feature.bit); +} + +uint32_t kvm_cpuid_property(const struct kvm_cpuid2 *cpuid, + struct kvm_x86_cpu_property property) +{ + return __kvm_cpu_has(cpuid, property.function, property.index, + property.reg, property.lo_bit, property.hi_bit); } uint64_t kvm_get_feature_msr(uint64_t msr_index) @@ -1059,34 +1025,15 @@ bool is_amd_cpu(void) void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) { - const struct kvm_cpuid_entry2 *entry; - bool pae; - - /* SDM 4.1.4 */ - if (kvm_get_cpuid_max_extended() < 0x80000008) { - pae = kvm_get_supported_cpuid_entry(1)->edx & (1 << 6); - *pa_bits = pae ? 36 : 32; + if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) { + *pa_bits == kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32; *va_bits = 32; } else { - entry = kvm_get_supported_cpuid_entry(0x80000008); - *pa_bits = entry->eax & 0xff; - *va_bits = (entry->eax >> 8) & 0xff; + *pa_bits = kvm_cpu_property(X86_PROPERTY_MAX_PHY_ADDR); + *va_bits = kvm_cpu_property(X86_PROPERTY_MAX_VIRT_ADDR); } } -struct idt_entry { - uint16_t offset0; - uint16_t selector; - uint16_t ist : 3; - uint16_t : 5; - uint16_t type : 4; - uint16_t : 1; - uint16_t dpl : 2; - uint16_t p : 1; - uint16_t offset1; - uint32_t offset2; uint32_t reserved; -}; - static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, int dpl, unsigned short selector) { @@ -1116,6 +1063,7 @@ static bool kvm_fixup_exception(struct ex_regs *regs) regs->rip = regs->r11; regs->r9 = regs->vector; + regs->r10 = regs->error_code; return true; } @@ -1278,7 +1226,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) { const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ unsigned long ht_gfn, max_gfn, max_pfn; - uint32_t eax, ebx, ecx, edx, max_ext_leaf; + uint8_t maxphyaddr; max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; @@ -1292,8 +1240,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) /* Before family 17h, the HyperTransport area is just below 1T. */ ht_gfn = (1 << 28) - num_ht_pages; - cpuid(1, &eax, &ebx, &ecx, &edx); - if (x86_family(eax) < 0x17) + if (this_cpu_family() < 0x17) goto done; /* @@ -1301,17 +1248,14 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX. Use * the old conservative value if MAXPHYADDR is not enumerated. */ - cpuid(0x80000000, &eax, &ebx, &ecx, &edx); - max_ext_leaf = eax; - if (max_ext_leaf < 0x80000008) + if (!this_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) goto done; - cpuid(0x80000008, &eax, &ebx, &ecx, &edx); - max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1; - if (max_ext_leaf >= 0x8000001f) { - cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); - max_pfn >>= (ebx >> 6) & 0x3f; - } + maxphyaddr = this_cpu_property(X86_PROPERTY_MAX_PHY_ADDR); + max_pfn = (1ULL << (maxphyaddr - vm->page_shift)) - 1; + + if (this_cpu_has_p(X86_PROPERTY_PHYS_ADDR_REDUCTION)) + max_pfn >>= this_cpu_property(X86_PROPERTY_PHYS_ADDR_REDUCTION); ht_gfn = max_pfn - num_ht_pages; done: diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c index e5f0f9e0d3ee..4d41dc63cc9e 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -8,52 +8,25 @@ #define UCALL_PIO_PORT ((uint16_t)0x1000) -void ucall_init(struct kvm_vm *vm, void *arg) +void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa) { } -void ucall_uninit(struct kvm_vm *vm) +void ucall_arch_do_ucall(vm_vaddr_t uc) { -} - -void ucall(uint64_t cmd, int nargs, ...) -{ - struct ucall uc = { - .cmd = cmd, - }; - va_list va; - int i; - - nargs = min(nargs, UCALL_MAX_ARGS); - - va_start(va, nargs); - for (i = 0; i < nargs; ++i) - uc.args[i] = va_arg(va, uint64_t); - va_end(va); - asm volatile("in %[port], %%al" - : : [port] "d" (UCALL_PIO_PORT), "D" (&uc) : "rax", "memory"); + : : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax", "memory"); } -uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc) +void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; - struct ucall ucall = {}; - - if (uc) - memset(uc, 0, sizeof(*uc)); if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { struct kvm_regs regs; vcpu_regs_get(vcpu, ®s); - memcpy(&ucall, addr_gva2hva(vcpu->vm, (vm_vaddr_t)regs.rdi), - sizeof(ucall)); - - vcpu_run_complete_io(vcpu); - if (uc) - memcpy(uc, &ucall, sizeof(ucall)); + return (void *)regs.rdi; } - - return ucall.cmd; + return NULL; } diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index d21049c38fc5..59d97531c9b1 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -109,18 +109,6 @@ vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva) vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite); memset(vmx->vmwrite_hva, 0, getpagesize()); - /* Setup of a region of guest memory for the VP Assist page. */ - vmx->vp_assist = (void *)vm_vaddr_alloc_page(vm); - vmx->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)vmx->vp_assist); - vmx->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vp_assist); - - /* Setup of a region of guest memory for the enlightened VMCS. */ - vmx->enlightened_vmcs = (void *)vm_vaddr_alloc_page(vm); - vmx->enlightened_vmcs_hva = - addr_gva2hva(vm, (uintptr_t)vmx->enlightened_vmcs); - vmx->enlightened_vmcs_gpa = - addr_gva2gpa(vm, (uintptr_t)vmx->enlightened_vmcs); - *p_vmx_gva = vmx_gva; return vmx; } @@ -171,26 +159,18 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx) bool load_vmcs(struct vmx_pages *vmx) { - if (!enable_evmcs) { - /* Load a VMCS. */ - *(uint32_t *)(vmx->vmcs) = vmcs_revision(); - if (vmclear(vmx->vmcs_gpa)) - return false; - - if (vmptrld(vmx->vmcs_gpa)) - return false; - - /* Setup shadow VMCS, do not load it yet. */ - *(uint32_t *)(vmx->shadow_vmcs) = - vmcs_revision() | 0x80000000ul; - if (vmclear(vmx->shadow_vmcs_gpa)) - return false; - } else { - if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa, - vmx->enlightened_vmcs)) - return false; - current_evmcs->revision_id = EVMCS_VERSION; - } + /* Load a VMCS. */ + *(uint32_t *)(vmx->vmcs) = vmcs_revision(); + if (vmclear(vmx->vmcs_gpa)) + return false; + + if (vmptrld(vmx->vmcs_gpa)) + return false; + + /* Setup shadow VMCS, do not load it yet. */ + *(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul; + if (vmclear(vmx->shadow_vmcs_gpa)) + return false; return true; } @@ -544,26 +524,22 @@ void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm, __nested_map(vmx, vm, addr, addr, size, PG_LEVEL_1G); } -bool kvm_vm_has_ept(struct kvm_vm *vm) +bool kvm_cpu_has_ept(void) { - struct kvm_vcpu *vcpu; uint64_t ctrl; - vcpu = list_first_entry(&vm->vcpus, struct kvm_vcpu, list); - TEST_ASSERT(vcpu, "Cannot determine EPT support without vCPUs.\n"); - - ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_TRUE_PROCBASED_CTLS) >> 32; + ctrl = kvm_get_feature_msr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) >> 32; if (!(ctrl & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) return false; - ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_PROCBASED_CTLS2) >> 32; + ctrl = kvm_get_feature_msr(MSR_IA32_VMX_PROCBASED_CTLS2) >> 32; return ctrl & SECONDARY_EXEC_ENABLE_EPT; } void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm, uint32_t eptp_memslot) { - TEST_REQUIRE(kvm_vm_has_ept(vm)); + TEST_ASSERT(kvm_cpu_has_ept(), "KVM doesn't support nested EPT"); vmx->eptp = (void *)vm_vaddr_alloc_page(vm); vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp); diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c index 9a6e4f3ad6b5..feaf2be20ff2 100644 --- a/tools/testing/selftests/kvm/max_guest_memory_test.c +++ b/tools/testing/selftests/kvm/max_guest_memory_test.c @@ -11,6 +11,7 @@ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/atomic.h> +#include <linux/sizes.h> #include "kvm_util.h" #include "test_util.h" @@ -162,8 +163,7 @@ int main(int argc, char *argv[]) * just below the 4gb boundary. This test could create memory at * 1gb-3gb,but it's simpler to skip straight to 4gb. */ - const uint64_t size_1gb = (1 << 30); - const uint64_t start_gpa = (4ull * size_1gb); + const uint64_t start_gpa = SZ_4G; const int first_slot = 1; struct timespec time_start, time_run1, time_reset, time_run2; @@ -180,29 +180,26 @@ int main(int argc, char *argv[]) * are quite common for x86, requires changing only max_mem (KVM allows * 32k memslots, 32k * 2gb == ~64tb of guest memory). */ - slot_size = 2 * size_1gb; + slot_size = SZ_2G; max_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS); TEST_ASSERT(max_slots > first_slot, "KVM is broken"); /* All KVM MMUs should be able to survive a 128gb guest. */ - max_mem = 128 * size_1gb; + max_mem = 128ull * SZ_1G; calc_default_nr_vcpus(); while ((opt = getopt(argc, argv, "c:h:m:s:H")) != -1) { switch (opt) { case 'c': - nr_vcpus = atoi(optarg); - TEST_ASSERT(nr_vcpus > 0, "number of vcpus must be >0"); + nr_vcpus = atoi_positive("Number of vCPUs", optarg); break; case 'm': - max_mem = atoi(optarg) * size_1gb; - TEST_ASSERT(max_mem > 0, "memory size must be >0"); + max_mem = 1ull * atoi_positive("Memory size", optarg) * SZ_1G; break; case 's': - slot_size = atoi(optarg) * size_1gb; - TEST_ASSERT(slot_size > 0, "slot size must be >0"); + slot_size = 1ull * atoi_positive("Slot size", optarg) * SZ_1G; break; case 'H': hugepages = true; @@ -245,7 +242,7 @@ int main(int argc, char *argv[]) #ifdef __x86_64__ /* Identity map memory in the guest using 1gb pages. */ - for (i = 0; i < slot_size; i += size_1gb) + for (i = 0; i < slot_size; i += SZ_1G) __virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G); #else for (i = 0; i < slot_size; i += vm->page_size) @@ -260,7 +257,7 @@ int main(int argc, char *argv[]) vcpus = NULL; pr_info("Running with %lugb of guest memory and %u vCPUs\n", - (gpa - start_gpa) / size_1gb, nr_vcpus); + (gpa - start_gpa) / SZ_1G, nr_vcpus); rendezvous_with_vcpus(&time_start, "spawning"); rendezvous_with_vcpus(&time_run1, "run 1"); diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index bb1d17a1171b..d07e921bfcc5 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -21,7 +21,7 @@ #include <linux/bitops.h> #include <linux/userfaultfd.h> -#include "perf_test_util.h" +#include "memstress.h" #include "processor.h" #include "test_util.h" #include "guest_modes.h" @@ -36,7 +36,7 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static bool run_vcpus = true; -static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) +static void vcpu_worker(struct memstress_vcpu_args *vcpu_args) { struct kvm_vcpu *vcpu = vcpu_args->vcpu; struct kvm_run *run; @@ -72,10 +72,10 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, int i; /* - * Add the dummy memslot just below the perf_test_util memslot, which is + * Add the dummy memslot just below the memstress memslot, which is * at the top of the guest physical address space. */ - gpa = perf_test_args.gpa - pages * vm->page_size; + gpa = memstress_args.gpa - pages * vm->page_size; for (i = 0; i < nr_modifications; i++) { usleep(delay); @@ -87,8 +87,8 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, } struct test_params { - useconds_t memslot_modification_delay; - uint64_t nr_memslot_modifications; + useconds_t delay; + uint64_t nr_iterations; bool partition_vcpu_memory_access; }; @@ -97,25 +97,24 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct test_params *p = arg; struct kvm_vm *vm; - vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, + vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, VM_MEM_SRC_ANONYMOUS, p->partition_vcpu_memory_access); pr_info("Finished creating vCPUs\n"); - perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); + memstress_start_vcpu_threads(nr_vcpus, vcpu_worker); pr_info("Started all vCPUs\n"); - add_remove_memslot(vm, p->memslot_modification_delay, - p->nr_memslot_modifications); + add_remove_memslot(vm, p->delay, p->nr_iterations); run_vcpus = false; - perf_test_join_vcpu_threads(nr_vcpus); + memstress_join_vcpu_threads(nr_vcpus); pr_info("All vCPU threads joined\n"); - perf_test_destroy_vm(vm); + memstress_destroy_vm(vm); } static void help(char *name) @@ -144,9 +143,8 @@ int main(int argc, char *argv[]) int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); int opt; struct test_params p = { - .memslot_modification_delay = 0, - .nr_memslot_modifications = - DEFAULT_MEMSLOT_MODIFICATION_ITERATIONS, + .delay = 0, + .nr_iterations = DEFAULT_MEMSLOT_MODIFICATION_ITERATIONS, .partition_vcpu_memory_access = true }; @@ -158,16 +156,14 @@ int main(int argc, char *argv[]) guest_modes_cmdline(optarg); break; case 'd': - p.memslot_modification_delay = strtoul(optarg, NULL, 0); - TEST_ASSERT(p.memslot_modification_delay >= 0, - "A negative delay is not supported."); + p.delay = atoi_non_negative("Delay", optarg); break; case 'b': guest_percpu_mem_size = parse_size(optarg); break; case 'v': - nr_vcpus = atoi(optarg); - TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, + nr_vcpus = atoi_positive("Number of vCPUs", optarg); + TEST_ASSERT(nr_vcpus <= max_vcpus, "Invalid number of vcpus, must be between 1 and %d", max_vcpus); break; @@ -175,7 +171,7 @@ int main(int argc, char *argv[]) p.partition_vcpu_memory_access = false; break; case 'i': - p.nr_memslot_modifications = atoi(optarg); + p.nr_iterations = atoi_positive("Number of iterations", optarg); break; case 'h': default: diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 44995446d942..36b20abfb948 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -277,7 +277,6 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, TEST_ASSERT(data->hva_slots, "malloc() fail"); data->vm = __vm_create_with_one_vcpu(&data->vcpu, mempages, guest_code); - ucall_init(data->vm, NULL); pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", max_mem_slots - 1, data->pages_per_slot, rempages); @@ -885,40 +884,28 @@ static bool parse_args(int argc, char *argv[], map_unmap_verify = true; break; case 's': - targs->nslots = atoi(optarg); + targs->nslots = atoi_paranoid(optarg); if (targs->nslots <= 0 && targs->nslots != -1) { pr_info("Slot count cap has to be positive or -1 for no cap\n"); return false; } break; case 'f': - targs->tfirst = atoi(optarg); - if (targs->tfirst < 0) { - pr_info("First test to run has to be non-negative\n"); - return false; - } + targs->tfirst = atoi_non_negative("First test", optarg); break; case 'e': - targs->tlast = atoi(optarg); - if (targs->tlast < 0 || targs->tlast >= NTESTS) { + targs->tlast = atoi_non_negative("Last test", optarg); + if (targs->tlast >= NTESTS) { pr_info("Last test to run has to be non-negative and less than %zu\n", NTESTS); return false; } break; case 'l': - targs->seconds = atoi(optarg); - if (targs->seconds < 0) { - pr_info("Test length in seconds has to be non-negative\n"); - return false; - } + targs->seconds = atoi_non_negative("Test length", optarg); break; case 'r': - targs->runs = atoi(optarg); - if (targs->runs <= 0) { - pr_info("Runs per test has to be positive\n"); - return false; - } + targs->runs = atoi_positive("Runs per test", optarg); break; } } @@ -1007,9 +994,6 @@ int main(int argc, char *argv[]) struct test_result rbestslottime; int tctr; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - if (!parse_args(argc, argv, &targs)) return -1; diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index 6f88da7e60be..3045fdf9bdf5 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -205,9 +205,6 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; u32 cpu, rseq_cpu; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask); TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno, strerror(errno)); @@ -224,7 +221,6 @@ int main(int argc, char *argv[]) * CPU affinity. */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); - ucall_init(vm, NULL); pthread_create(&migration_thread, NULL, migration_worker, (void *)(unsigned long)syscall(SYS_gettid)); diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index 9113696d5178..3fd81e58f40c 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -760,8 +760,6 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_MEM_OP)); - setbuf(stdout, NULL); /* Tell stdout not to buffer its content */ - ksft_print_header(); ksft_set_plan(ARRAY_SIZE(testlist)); diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c index 19486084eb30..e41e2cb8ffa9 100644 --- a/tools/testing/selftests/kvm/s390x/resets.c +++ b/tools/testing/selftests/kvm/s390x/resets.c @@ -296,8 +296,6 @@ int main(int argc, char *argv[]) bool has_s390_vcpu_resets = kvm_check_cap(KVM_CAP_S390_VCPU_RESETS); int idx; - setbuf(stdout, NULL); /* Tell stdout not to buffer its content */ - ksft_print_header(); ksft_set_plan(ARRAY_SIZE(testlist)); diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c index 3fdb6e2598eb..2ddde41c44ba 100644 --- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c +++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c @@ -231,9 +231,6 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_has_cap(KVM_CAP_SYNC_REGS)); - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - ksft_print_header(); ksft_set_plan(ARRAY_SIZE(testlist)); diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 0d55f508d595..2ef1d1b72ce4 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -392,9 +392,6 @@ int main(int argc, char *argv[]) int i, loops; #endif - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - #ifdef __x86_64__ /* * FIXME: the zero-memslot test fails on aarch64 and s390x because @@ -407,7 +404,7 @@ int main(int argc, char *argv[]) #ifdef __x86_64__ if (argc > 1) - loops = atoi(argv[1]); + loops = atoi_positive("Number of iterations", argv[1]); else loops = 10; diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index db8967f1a17b..c87f38712073 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -266,7 +266,6 @@ int main(int ac, char **av) gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE * NR_VCPUS); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0); virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, gpages); - ucall_init(vm, NULL); TEST_REQUIRE(is_steal_time_supported(vcpus[0])); diff --git a/tools/testing/selftests/kvm/system_counter_offset_test.c b/tools/testing/selftests/kvm/system_counter_offset_test.c index 1c274933912b..7f5b330b6a1b 100644 --- a/tools/testing/selftests/kvm/system_counter_offset_test.c +++ b/tools/testing/selftests/kvm/system_counter_offset_test.c @@ -121,7 +121,6 @@ int main(void) vm = vm_create_with_one_vcpu(&vcpu, guest_main); check_preconditions(vcpu); - ucall_init(vm, NULL); enter_guest(vcpu); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index dadcbad10a1d..21de6ae42086 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -39,11 +39,6 @@ #define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) #define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) -#define TILE_CPUID 0x1d -#define XSTATE_CPUID 0xd -#define TILE_PALETTE_CPUID_SUBLEAVE 0x1 -#define XSTATE_USER_STATE_SUBLEAVE 0x0 - #define XSAVE_HDR_OFFSET 512 struct xsave_data { @@ -129,71 +124,26 @@ static bool check_xsave_supports_xtile(void) return __xgetbv(0) & XFEATURE_MASK_XTILE; } -static bool enum_xtile_config(void) -{ - u32 eax, ebx, ecx, edx; - - __cpuid(TILE_CPUID, TILE_PALETTE_CPUID_SUBLEAVE, &eax, &ebx, &ecx, &edx); - if (!eax || !ebx || !ecx) - return false; - - xtile.max_names = ebx >> 16; - if (xtile.max_names < NUM_TILES) - return false; - - xtile.bytes_per_tile = eax >> 16; - if (xtile.bytes_per_tile < TILE_SIZE) - return false; - - xtile.bytes_per_row = ebx; - xtile.max_rows = ecx; - - return true; -} - -static bool enum_xsave_tile(void) -{ - u32 eax, ebx, ecx, edx; - - __cpuid(XSTATE_CPUID, XFEATURE_XTILEDATA, &eax, &ebx, &ecx, &edx); - if (!eax || !ebx) - return false; - - xtile.xsave_offset = ebx; - xtile.xsave_size = eax; - - return true; -} - -static bool check_xsave_size(void) -{ - u32 eax, ebx, ecx, edx; - bool valid = false; - - __cpuid(XSTATE_CPUID, XSTATE_USER_STATE_SUBLEAVE, &eax, &ebx, &ecx, &edx); - if (ebx && ebx <= XSAVE_SIZE) - valid = true; - - return valid; -} - -static bool check_xtile_info(void) +static void check_xtile_info(void) { - bool ret = false; - - if (!check_xsave_size()) - return ret; - - if (!enum_xsave_tile()) - return ret; - - if (!enum_xtile_config()) - return ret; + GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_XSTATE_MAX_SIZE_XCR0)); + GUEST_ASSERT(this_cpu_property(X86_PROPERTY_XSTATE_MAX_SIZE_XCR0) <= XSAVE_SIZE); - if (sizeof(struct tile_data) >= xtile.xsave_size) - ret = true; + xtile.xsave_offset = this_cpu_property(X86_PROPERTY_XSTATE_TILE_OFFSET); + GUEST_ASSERT(xtile.xsave_offset == 2816); + xtile.xsave_size = this_cpu_property(X86_PROPERTY_XSTATE_TILE_SIZE); + GUEST_ASSERT(xtile.xsave_size == 8192); + GUEST_ASSERT(sizeof(struct tile_data) >= xtile.xsave_size); - return ret; + 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); + xtile.bytes_per_tile = this_cpu_property(X86_PROPERTY_AMX_BYTES_PER_TILE); + GUEST_ASSERT(xtile.bytes_per_tile == 1024); + xtile.bytes_per_row = this_cpu_property(X86_PROPERTY_AMX_BYTES_PER_ROW); + GUEST_ASSERT(xtile.bytes_per_row == 64); + xtile.max_rows = this_cpu_property(X86_PROPERTY_AMX_MAX_ROWS); + GUEST_ASSERT(xtile.max_rows == 16); } static void set_tilecfg(struct tile_config *cfg) @@ -238,16 +188,8 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, { init_regs(); check_cpuid_xsave(); - GUEST_ASSERT(check_xsave_supports_xtile()); - GUEST_ASSERT(check_xtile_info()); - - /* check xtile configs */ - GUEST_ASSERT(xtile.xsave_offset == 2816); - GUEST_ASSERT(xtile.xsave_size == 8192); - GUEST_ASSERT(xtile.max_names == 8); - GUEST_ASSERT(xtile.bytes_per_tile == 1024); - GUEST_ASSERT(xtile.bytes_per_row == 64); - GUEST_ASSERT(xtile.max_rows == 16); + check_xsave_supports_xtile(); + check_xtile_info(); GUEST_SYNC(1); /* xfd=0, enable amx */ @@ -317,8 +259,9 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILECFG)); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILEDATA)); - /* Get xsave/restore max size */ - xsave_restore_size = kvm_get_supported_cpuid_entry(0xd)->ecx; + TEST_ASSERT(kvm_cpu_has_p(X86_PROPERTY_XSTATE_MAX_SIZE), + "KVM should enumerate max XSAVE size when XSAVE is supported"); + xsave_restore_size = kvm_cpu_property(X86_PROPERTY_XSTATE_MAX_SIZE); run = vcpu->run; vcpu_regs_get(vcpu, ®s1); diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c index a6aeee2e62e4..2fc3ad9c887e 100644 --- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c @@ -43,15 +43,6 @@ static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid) } -static void test_cpuid_40000000(struct kvm_cpuid2 *guest_cpuid) -{ - u32 eax, ebx, ecx, edx; - - cpuid(0x40000000, &eax, &ebx, &ecx, &edx); - - GUEST_ASSERT(eax == 0x40000001); -} - static void guest_main(struct kvm_cpuid2 *guest_cpuid) { GUEST_SYNC(1); @@ -60,7 +51,7 @@ static void guest_main(struct kvm_cpuid2 *guest_cpuid) GUEST_SYNC(2); - test_cpuid_40000000(guest_cpuid); + GUEST_ASSERT(this_cpu_property(X86_PROPERTY_MAX_KVM_LEAF) == 0x40000001); GUEST_DONE(); } diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index 4208487652f8..1027a671c7d3 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -57,9 +57,6 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - vm = vm_create_with_one_vcpu(&vcpu, guest_code); run = vcpu->run; diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c deleted file mode 100644 index 236e11755ba6..000000000000 --- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c +++ /dev/null @@ -1,193 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2020, Google LLC. - * - * Tests for KVM_CAP_EXIT_ON_EMULATION_FAILURE capability. - */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ - -#include "test_util.h" -#include "kvm_util.h" -#include "vmx.h" - -#define MAXPHYADDR 36 - -#define MEM_REGION_GVA 0x0000123456789000 -#define MEM_REGION_GPA 0x0000000700000000 -#define MEM_REGION_SLOT 10 -#define MEM_REGION_SIZE PAGE_SIZE - -static void guest_code(void) -{ - __asm__ __volatile__("flds (%[addr])" - :: [addr]"r"(MEM_REGION_GVA)); - - GUEST_DONE(); -} - -/* - * Accessors to get R/M, REG, and Mod bits described in the SDM vol 2, - * figure 2-2 "Table Interpretation of ModR/M Byte (C8H)". - */ -#define GET_RM(insn_byte) (insn_byte & 0x7) -#define GET_REG(insn_byte) ((insn_byte & 0x38) >> 3) -#define GET_MOD(insn_byte) ((insn_byte & 0xc) >> 6) - -/* Ensure we are dealing with a simple 2-byte flds instruction. */ -static bool is_flds(uint8_t *insn_bytes, uint8_t insn_size) -{ - return insn_size >= 2 && - insn_bytes[0] == 0xd9 && - GET_REG(insn_bytes[1]) == 0x0 && - GET_MOD(insn_bytes[1]) == 0x0 && - /* Ensure there is no SIB byte. */ - GET_RM(insn_bytes[1]) != 0x4 && - /* Ensure there is no displacement byte. */ - GET_RM(insn_bytes[1]) != 0x5; -} - -static void process_exit_on_emulation_error(struct kvm_vcpu *vcpu) -{ - struct kvm_run *run = vcpu->run; - struct kvm_regs regs; - uint8_t *insn_bytes; - uint8_t insn_size; - uint64_t flags; - - TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, - "Unexpected exit reason: %u (%s)", - run->exit_reason, - exit_reason_str(run->exit_reason)); - - TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION, - "Unexpected suberror: %u", - run->emulation_failure.suberror); - - if (run->emulation_failure.ndata >= 1) { - flags = run->emulation_failure.flags; - if ((flags & KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES) && - run->emulation_failure.ndata >= 3) { - insn_size = run->emulation_failure.insn_size; - insn_bytes = run->emulation_failure.insn_bytes; - - TEST_ASSERT(insn_size <= 15 && insn_size > 0, - "Unexpected instruction size: %u", - insn_size); - - TEST_ASSERT(is_flds(insn_bytes, insn_size), - "Unexpected instruction. Expected 'flds' (0xd9 /0)"); - - /* - * If is_flds() succeeded then the instruction bytes - * contained an flds instruction that is 2-bytes in - * length (ie: no prefix, no SIB, no displacement). - */ - vcpu_regs_get(vcpu, ®s); - regs.rip += 2; - vcpu_regs_set(vcpu, ®s); - } - } -} - -static void do_guest_assert(struct ucall *uc) -{ - REPORT_GUEST_ASSERT(*uc); -} - -static void check_for_guest_assert(struct kvm_vcpu *vcpu) -{ - struct ucall uc; - - if (vcpu->run->exit_reason == KVM_EXIT_IO && - get_ucall(vcpu, &uc) == UCALL_ABORT) { - do_guest_assert(&uc); - } -} - -static void process_ucall_done(struct kvm_vcpu *vcpu) -{ - struct kvm_run *run = vcpu->run; - struct ucall uc; - - check_for_guest_assert(vcpu); - - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s)", - run->exit_reason, - exit_reason_str(run->exit_reason)); - - TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, - "Unexpected ucall command: %lu, expected UCALL_DONE (%d)", - uc.cmd, UCALL_DONE); -} - -static uint64_t process_ucall(struct kvm_vcpu *vcpu) -{ - struct kvm_run *run = vcpu->run; - struct ucall uc; - - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Unexpected exit reason: %u (%s)", - run->exit_reason, - exit_reason_str(run->exit_reason)); - - switch (get_ucall(vcpu, &uc)) { - case UCALL_SYNC: - break; - case UCALL_ABORT: - do_guest_assert(&uc); - break; - case UCALL_DONE: - process_ucall_done(vcpu); - break; - default: - TEST_ASSERT(false, "Unexpected ucall"); - } - - return uc.cmd; -} - -int main(int argc, char *argv[]) -{ - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - uint64_t gpa, pte; - uint64_t *hva; - int rc; - - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - - TEST_REQUIRE(kvm_has_cap(KVM_CAP_SMALLER_MAXPHYADDR)); - - vm = vm_create_with_one_vcpu(&vcpu, guest_code); - - vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR); - - rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE); - TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable"); - vm_enable_cap(vm, KVM_CAP_EXIT_ON_EMULATION_FAILURE, 1); - - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - MEM_REGION_GPA, MEM_REGION_SLOT, - MEM_REGION_SIZE / PAGE_SIZE, 0); - gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE, - MEM_REGION_GPA, MEM_REGION_SLOT); - TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n"); - virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1); - hva = addr_gpa2hva(vm, MEM_REGION_GPA); - memset(hva, 0, PAGE_SIZE); - pte = vm_get_page_table_entry(vm, vcpu, MEM_REGION_GVA); - vm_set_page_table_entry(vm, vcpu, MEM_REGION_GVA, pte | (1ull << 36)); - - vcpu_run(vcpu); - process_exit_on_emulation_error(vcpu); - vcpu_run(vcpu); - - TEST_ASSERT(process_ucall(vcpu) == UCALL_DONE, "Expected UCALL_DONE"); - - kvm_vm_free(vm); - - return 0; -} diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c new file mode 100644 index 000000000000..37c61f712fd5 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022, Google LLC. + * + * Test for KVM_CAP_EXIT_ON_EMULATION_FAILURE. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ + +#include "flds_emulation.h" + +#include "test_util.h" + +#define MMIO_GPA 0x700000000 +#define MMIO_GVA MMIO_GPA + +static void guest_code(void) +{ + /* Execute flds with an MMIO address to force KVM to emulate it. */ + flds(MMIO_GVA); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vm_enable_cap(vm, KVM_CAP_EXIT_ON_EMULATION_FAILURE, 1); + virt_map(vm, MMIO_GVA, MMIO_GPA, 1); + + vcpu_run(vcpu); + handle_flds_emulation_failure_exit(vcpu); + vcpu_run(vcpu); + ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/flds_emulation.h b/tools/testing/selftests/kvm/x86_64/flds_emulation.h new file mode 100644 index 000000000000..e43a7df25f2c --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/flds_emulation.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_FLDS_EMULATION_H +#define SELFTEST_KVM_FLDS_EMULATION_H + +#include "kvm_util.h" + +#define FLDS_MEM_EAX ".byte 0xd9, 0x00" + +/* + * flds is an instruction that the KVM instruction emulator is known not to + * support. This can be used in guest code along with a mechanism to force + * KVM to emulate the instruction (e.g. by providing an MMIO address) to + * exercise emulation failures. + */ +static inline void flds(uint64_t address) +{ + __asm__ __volatile__(FLDS_MEM_EAX :: "a"(address)); +} + +static inline void handle_flds_emulation_failure_exit(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + struct kvm_regs regs; + uint8_t *insn_bytes; + uint64_t flags; + + TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR, + "Unexpected exit reason: %u (%s)", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION, + "Unexpected suberror: %u", + run->emulation_failure.suberror); + + flags = run->emulation_failure.flags; + TEST_ASSERT(run->emulation_failure.ndata >= 3 && + flags & KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES, + "run->emulation_failure is missing instruction bytes"); + + TEST_ASSERT(run->emulation_failure.insn_size >= 2, + "Expected a 2-byte opcode for 'flds', got %d bytes", + run->emulation_failure.insn_size); + + insn_bytes = run->emulation_failure.insn_bytes; + TEST_ASSERT(insn_bytes[0] == 0xd9 && insn_bytes[1] == 0, + "Expected 'flds [eax]', opcode '0xd9 0x00', got opcode 0x%02x 0x%02x\n", + insn_bytes[0], insn_bytes[1]); + + vcpu_regs_get(vcpu, ®s); + regs.rip += 2; + vcpu_regs_set(vcpu, ®s); +} + +#endif /* !SELFTEST_KVM_FLDS_EMULATION_H */ diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index e804eb08dff9..5c27efbf405e 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -134,9 +134,6 @@ int main(int argc, char *argv[]) const struct kvm_cpuid2 *hv_cpuid_entries; struct kvm_vcpu *vcpu; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c index 99bc202243d2..ba09d300c953 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c @@ -16,6 +16,7 @@ #include "kvm_util.h" +#include "hyperv.h" #include "vmx.h" static int ud_count; @@ -30,24 +31,19 @@ static void guest_nmi_handler(struct ex_regs *regs) { } -/* Exits to L1 destroy GRPs! */ -static inline void rdmsr_fs_base(void) +static inline void rdmsr_from_l2(uint32_t msr) { - __asm__ __volatile__ ("mov $0xc0000100, %%rcx; rdmsr" : : : - "rax", "rbx", "rcx", "rdx", - "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", - "r13", "r14", "r15"); -} -static inline void rdmsr_gs_base(void) -{ - __asm__ __volatile__ ("mov $0xc0000101, %%rcx; rdmsr" : : : - "rax", "rbx", "rcx", "rdx", - "rsi", "rdi", "r8", "r9", "r10", "r11", "r12", - "r13", "r14", "r15"); + /* Currently, L1 doesn't preserve GPRs during vmexits. */ + __asm__ __volatile__ ("rdmsr" : : "c"(msr) : + "rax", "rbx", "rdx", "rsi", "rdi", "r8", "r9", + "r10", "r11", "r12", "r13", "r14", "r15"); } +/* Exit to L1 from L2 with RDMSR instruction */ void l2_guest_code(void) { + u64 unused; + GUEST_SYNC(7); GUEST_SYNC(8); @@ -58,42 +54,58 @@ void l2_guest_code(void) vmcall(); /* MSR-Bitmap tests */ - rdmsr_fs_base(); /* intercepted */ - rdmsr_fs_base(); /* intercepted */ - rdmsr_gs_base(); /* not intercepted */ + rdmsr_from_l2(MSR_FS_BASE); /* intercepted */ + rdmsr_from_l2(MSR_FS_BASE); /* intercepted */ + rdmsr_from_l2(MSR_GS_BASE); /* not intercepted */ vmcall(); - rdmsr_gs_base(); /* intercepted */ + rdmsr_from_l2(MSR_GS_BASE); /* intercepted */ + + /* L2 TLB flush tests */ + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT, 0x0, + HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | HV_FLUSH_ALL_PROCESSORS); + rdmsr_from_l2(MSR_FS_BASE); + /* + * Note: hypercall status (RAX) is not preserved correctly by L1 after + * synthetic vmexit, use unchecked version. + */ + __hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT, 0x0, + HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | HV_FLUSH_ALL_PROCESSORS, + &unused); /* Done, exit to L1 and never come back. */ vmcall(); } -void guest_code(struct vmx_pages *vmx_pages) +void guest_code(struct vmx_pages *vmx_pages, struct hyperv_test_pages *hv_pages, + vm_vaddr_t hv_hcall_page_gpa) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + wrmsr(HV_X64_MSR_HYPERCALL, hv_hcall_page_gpa); + x2apic_enable(); GUEST_SYNC(1); GUEST_SYNC(2); - enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist); + enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist); + evmcs_enable(); - GUEST_ASSERT(vmx_pages->vmcs_gpa); GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); GUEST_SYNC(3); - GUEST_ASSERT(load_vmcs(vmx_pages)); - GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); + GUEST_ASSERT(load_evmcs(hv_pages)); + GUEST_ASSERT(vmptrstz() == hv_pages->enlightened_vmcs_gpa); GUEST_SYNC(4); - GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); + GUEST_ASSERT(vmptrstz() == hv_pages->enlightened_vmcs_gpa); prepare_vmcs(vmx_pages, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); GUEST_SYNC(5); - GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); + GUEST_ASSERT(vmptrstz() == hv_pages->enlightened_vmcs_gpa); current_evmcs->revision_id = -1u; GUEST_ASSERT(vmlaunch()); current_evmcs->revision_id = EVMCS_VERSION; @@ -102,8 +114,18 @@ void guest_code(struct vmx_pages *vmx_pages) vmwrite(PIN_BASED_VM_EXEC_CONTROL, vmreadz(PIN_BASED_VM_EXEC_CONTROL) | PIN_BASED_NMI_EXITING); + /* L2 TLB flush setup */ + current_evmcs->partition_assist_page = hv_pages->partition_assist_gpa; + current_evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; + current_evmcs->hv_vm_id = 1; + current_evmcs->hv_vp_id = 1; + current_vp_assist->nested_control.features.directhypercall = 1; + *(u32 *)(hv_pages->partition_assist) = 0; + GUEST_ASSERT(!vmlaunch()); - GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); + GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_EXCEPTION_NMI); + GUEST_ASSERT_EQ((vmreadz(VM_EXIT_INTR_INFO) & 0xff), NMI_VECTOR); + GUEST_ASSERT(vmptrstz() == hv_pages->enlightened_vmcs_gpa); /* * NMI forces L2->L1 exit, resuming L2 and hope that EVMCS is @@ -146,12 +168,24 @@ void guest_code(struct vmx_pages *vmx_pages) GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); current_evmcs->guest_rip += 2; /* rdmsr */ + /* + * L2 TLB flush test. First VMCALL should be handled directly by L0, + * no VMCALL exit expected. + */ + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ); + current_evmcs->guest_rip += 2; /* rdmsr */ + /* Enable synthetic vmexit */ + *(u32 *)(hv_pages->partition_assist) = 1; + GUEST_ASSERT(!vmresume()); + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH); + GUEST_ASSERT(!vmresume()); GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); GUEST_SYNC(11); /* Try enlightened vmptrld with an incorrect GPA */ - evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs); + evmcs_vmptrld(0xdeadbeef, hv_pages->enlightened_vmcs); GUEST_ASSERT(vmlaunch()); GUEST_ASSERT(ud_count == 1); GUEST_DONE(); @@ -198,7 +232,8 @@ static struct kvm_vcpu *save_restore_vm(struct kvm_vm *vm, int main(int argc, char *argv[]) { - vm_vaddr_t vmx_pages_gva = 0; + vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0; + vm_vaddr_t hcall_page; struct kvm_vcpu *vcpu; struct kvm_vm *vm; @@ -212,11 +247,16 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); + hcall_page = vm_vaddr_alloc_pages(vm, 1); + memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize()); + vcpu_set_hv_cpuid(vcpu); vcpu_enable_evmcs(vcpu); vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vcpu, 1, vmx_pages_gva); + vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva); + vcpu_args_set(vcpu, 3, vmx_pages_gva, hv_pages_gva, addr_gva2gpa(vm, hcall_page)); + vcpu_set_msr(vcpu, HV_X64_MSR_VP_INDEX, vcpu->id); vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 05b32e550a80..3163c3e8db0a 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -13,25 +13,6 @@ #include "processor.h" #include "hyperv.h" -#define LINUX_OS_ID ((u64)0x8100 << 48) - -static inline uint8_t hypercall(u64 control, vm_vaddr_t input_address, - vm_vaddr_t output_address, uint64_t *hv_status) -{ - uint8_t vector; - - /* Note both the hypercall and the "asm safe" clobber r9-r11. */ - asm volatile("mov %[output_address], %%r8\n\t" - KVM_ASM_SAFE("vmcall") - : "=a" (*hv_status), - "+c" (control), "+d" (input_address), - KVM_ASM_SAFE_OUTPUTS(vector) - : [output_address] "r"(output_address), - "a" (-EFAULT) - : "cc", "memory", "r8", KVM_ASM_SAFE_CLOBBERS); - return vector; -} - struct msr_data { uint32_t idx; bool available; @@ -71,7 +52,7 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) GUEST_ASSERT(hcall->control); - wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID); + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) { @@ -81,7 +62,7 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) input = output = 0; } - vector = hypercall(hcall->control, input, output, &res); + vector = __hyperv_hypercall(hcall->control, input, output, &res); if (hcall->ud_expected) { GUEST_ASSERT_2(vector == UD_VECTOR, hcall->control, vector); } else { @@ -169,7 +150,7 @@ static void guest_test_msrs_access(void) */ msr->idx = HV_X64_MSR_GUEST_OS_ID; msr->write = 1; - msr->write_val = LINUX_OS_ID; + msr->write_val = HYPERV_LINUX_OS_ID; msr->available = 1; break; case 3: diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c new file mode 100644 index 000000000000..8b791eac7d5a --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hyper-V HvCallSendSyntheticClusterIpi{,Ex} tests + * + * Copyright (C) 2022, Red Hat, Inc. + * + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <pthread.h> +#include <inttypes.h> + +#include "kvm_util.h" +#include "hyperv.h" +#include "test_util.h" +#include "vmx.h" + +#define RECEIVER_VCPU_ID_1 2 +#define RECEIVER_VCPU_ID_2 65 + +#define IPI_VECTOR 0xfe + +static volatile uint64_t ipis_rcvd[RECEIVER_VCPU_ID_2 + 1]; + +struct hv_vpset { + u64 format; + u64 valid_bank_mask; + u64 bank_contents[2]; +}; + +enum HV_GENERIC_SET_FORMAT { + HV_GENERIC_SET_SPARSE_4K, + HV_GENERIC_SET_ALL, +}; + +/* HvCallSendSyntheticClusterIpi hypercall */ +struct hv_send_ipi { + u32 vector; + u32 reserved; + u64 cpu_mask; +}; + +/* HvCallSendSyntheticClusterIpiEx hypercall */ +struct hv_send_ipi_ex { + u32 vector; + u32 reserved; + struct hv_vpset vp_set; +}; + +static inline void hv_init(vm_vaddr_t pgs_gpa) +{ + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); +} + +static void receiver_code(void *hcall_page, vm_vaddr_t pgs_gpa) +{ + u32 vcpu_id; + + x2apic_enable(); + hv_init(pgs_gpa); + + vcpu_id = rdmsr(HV_X64_MSR_VP_INDEX); + + /* Signal sender vCPU we're ready */ + ipis_rcvd[vcpu_id] = (u64)-1; + + for (;;) + asm volatile("sti; hlt; cli"); +} + +static void guest_ipi_handler(struct ex_regs *regs) +{ + u32 vcpu_id = rdmsr(HV_X64_MSR_VP_INDEX); + + ipis_rcvd[vcpu_id]++; + wrmsr(HV_X64_MSR_EOI, 1); +} + +static inline void nop_loop(void) +{ + int i; + + for (i = 0; i < 100000000; i++) + asm volatile("nop"); +} + +static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa) +{ + struct hv_send_ipi *ipi = (struct hv_send_ipi *)hcall_page; + struct hv_send_ipi_ex *ipi_ex = (struct hv_send_ipi_ex *)hcall_page; + int stage = 1, ipis_expected[2] = {0}; + + hv_init(pgs_gpa); + GUEST_SYNC(stage++); + + /* Wait for receiver vCPUs to come up */ + while (!ipis_rcvd[RECEIVER_VCPU_ID_1] || !ipis_rcvd[RECEIVER_VCPU_ID_2]) + nop_loop(); + ipis_rcvd[RECEIVER_VCPU_ID_1] = ipis_rcvd[RECEIVER_VCPU_ID_2] = 0; + + /* 'Slow' HvCallSendSyntheticClusterIpi to RECEIVER_VCPU_ID_1 */ + ipi->vector = IPI_VECTOR; + ipi->cpu_mask = 1 << RECEIVER_VCPU_ID_1; + hyperv_hypercall(HVCALL_SEND_IPI, pgs_gpa, pgs_gpa + 4096); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]); + GUEST_SYNC(stage++); + /* 'Fast' HvCallSendSyntheticClusterIpi to RECEIVER_VCPU_ID_1 */ + hyperv_hypercall(HVCALL_SEND_IPI | HV_HYPERCALL_FAST_BIT, + IPI_VECTOR, 1 << RECEIVER_VCPU_ID_1); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]); + GUEST_SYNC(stage++); + + /* 'Slow' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_1 */ + memset(hcall_page, 0, 4096); + ipi_ex->vector = IPI_VECTOR; + ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K; + ipi_ex->vp_set.valid_bank_mask = 1 << 0; + ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_1); + hyperv_hypercall(HVCALL_SEND_IPI_EX | (1 << HV_HYPERCALL_VARHEAD_OFFSET), + pgs_gpa, pgs_gpa + 4096); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]); + GUEST_SYNC(stage++); + /* 'XMM Fast' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_1 */ + hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 1); + hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT | + (1 << HV_HYPERCALL_VARHEAD_OFFSET), + IPI_VECTOR, HV_GENERIC_SET_SPARSE_4K); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]); + GUEST_SYNC(stage++); + + /* 'Slow' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_2 */ + memset(hcall_page, 0, 4096); + ipi_ex->vector = IPI_VECTOR; + ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K; + ipi_ex->vp_set.valid_bank_mask = 1 << 1; + ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_2 - 64); + hyperv_hypercall(HVCALL_SEND_IPI_EX | (1 << HV_HYPERCALL_VARHEAD_OFFSET), + pgs_gpa, pgs_gpa + 4096); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]); + GUEST_SYNC(stage++); + /* 'XMM Fast' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_2 */ + hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 1); + hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT | + (1 << HV_HYPERCALL_VARHEAD_OFFSET), + IPI_VECTOR, HV_GENERIC_SET_SPARSE_4K); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]); + GUEST_SYNC(stage++); + + /* 'Slow' HvCallSendSyntheticClusterIpiEx to both RECEIVER_VCPU_ID_{1,2} */ + memset(hcall_page, 0, 4096); + ipi_ex->vector = IPI_VECTOR; + ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K; + ipi_ex->vp_set.valid_bank_mask = 1 << 1 | 1; + ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_1); + ipi_ex->vp_set.bank_contents[1] = BIT(RECEIVER_VCPU_ID_2 - 64); + hyperv_hypercall(HVCALL_SEND_IPI_EX | (2 << HV_HYPERCALL_VARHEAD_OFFSET), + pgs_gpa, pgs_gpa + 4096); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]); + GUEST_SYNC(stage++); + /* 'XMM Fast' HvCallSendSyntheticClusterIpiEx to both RECEIVER_VCPU_ID_{1, 2} */ + hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 2); + hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT | + (2 << HV_HYPERCALL_VARHEAD_OFFSET), + IPI_VECTOR, HV_GENERIC_SET_SPARSE_4K); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]); + GUEST_SYNC(stage++); + + /* 'Slow' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL */ + memset(hcall_page, 0, 4096); + ipi_ex->vector = IPI_VECTOR; + ipi_ex->vp_set.format = HV_GENERIC_SET_ALL; + hyperv_hypercall(HVCALL_SEND_IPI_EX, pgs_gpa, pgs_gpa + 4096); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]); + GUEST_SYNC(stage++); + /* + * 'XMM Fast' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL. + * Nothing to write anything to XMM regs. + */ + hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT, + IPI_VECTOR, HV_GENERIC_SET_ALL); + nop_loop(); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]); + GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]); + GUEST_SYNC(stage++); + + GUEST_DONE(); +} + +static void *vcpu_thread(void *arg) +{ + struct kvm_vcpu *vcpu = (struct kvm_vcpu *)arg; + int old, r; + + r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old); + TEST_ASSERT(!r, "pthread_setcanceltype failed on vcpu_id=%u with errno=%d", + vcpu->id, r); + + vcpu_run(vcpu); + + TEST_FAIL("vCPU %u exited unexpectedly", vcpu->id); + + return NULL; +} + +static void cancel_join_vcpu_thread(pthread_t thread, struct kvm_vcpu *vcpu) +{ + void *retval; + int r; + + r = pthread_cancel(thread); + TEST_ASSERT(!r, "pthread_cancel on vcpu_id=%d failed with errno=%d", + vcpu->id, r); + + r = pthread_join(thread, &retval); + TEST_ASSERT(!r, "pthread_join on vcpu_id=%d failed with errno=%d", + vcpu->id, r); + TEST_ASSERT(retval == PTHREAD_CANCELED, + "expected retval=%p, got %p", PTHREAD_CANCELED, + retval); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu[3]; + unsigned int exit_reason; + vm_vaddr_t hcall_page; + pthread_t threads[2]; + int stage = 1, r; + struct ucall uc; + + vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code); + + /* Hypercall input/output */ + hcall_page = vm_vaddr_alloc_pages(vm, 2); + memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); + + vm_init_descriptor_tables(vm); + + vcpu[1] = vm_vcpu_add(vm, RECEIVER_VCPU_ID_1, receiver_code); + vcpu_init_descriptor_tables(vcpu[1]); + vcpu_args_set(vcpu[1], 2, hcall_page, addr_gva2gpa(vm, hcall_page)); + vcpu_set_msr(vcpu[1], HV_X64_MSR_VP_INDEX, RECEIVER_VCPU_ID_1); + vcpu_set_hv_cpuid(vcpu[1]); + + vcpu[2] = vm_vcpu_add(vm, RECEIVER_VCPU_ID_2, receiver_code); + vcpu_init_descriptor_tables(vcpu[2]); + vcpu_args_set(vcpu[2], 2, hcall_page, addr_gva2gpa(vm, hcall_page)); + vcpu_set_msr(vcpu[2], HV_X64_MSR_VP_INDEX, RECEIVER_VCPU_ID_2); + vcpu_set_hv_cpuid(vcpu[2]); + + vm_install_exception_handler(vm, IPI_VECTOR, guest_ipi_handler); + + vcpu_args_set(vcpu[0], 2, hcall_page, addr_gva2gpa(vm, hcall_page)); + vcpu_set_hv_cpuid(vcpu[0]); + + r = pthread_create(&threads[0], NULL, vcpu_thread, vcpu[1]); + TEST_ASSERT(!r, "pthread_create failed errno=%d", r); + + r = pthread_create(&threads[1], NULL, vcpu_thread, vcpu[2]); + TEST_ASSERT(!r, "pthread_create failed errno=%d", errno); + + while (true) { + vcpu_run(vcpu[0]); + + exit_reason = vcpu[0]->run->exit_reason; + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + exit_reason, exit_reason_str(exit_reason)); + + switch (get_ucall(vcpu[0], &uc)) { + case UCALL_SYNC: + TEST_ASSERT(uc.args[1] == stage, + "Unexpected stage: %ld (%d expected)\n", + uc.args[1], stage); + break; + case UCALL_DONE: + goto done; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + /* NOT REACHED */ + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + stage++; + } + +done: + cancel_join_vcpu_thread(threads[0], vcpu[1]); + cancel_join_vcpu_thread(threads[1], vcpu[2]); + kvm_vm_free(vm); + + return r; +} diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c index a380ad7bb9b3..3b3cc94ba8e4 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -23,59 +23,78 @@ #define L2_GUEST_STACK_SIZE 256 -struct hv_enlightenments { - struct __packed hv_enlightenments_control { - u32 nested_flush_hypercall:1; - u32 msr_bitmap:1; - u32 enlightened_npt_tlb: 1; - u32 reserved:29; - } __packed hv_enlightenments_control; - u32 hv_vp_id; - u64 hv_vm_id; - u64 partition_assist_page; - u64 reserved; -} __packed; - -/* - * Hyper-V uses the software reserved clean bit in VMCB - */ -#define VMCB_HV_NESTED_ENLIGHTENMENTS (1U << 31) +/* Exit to L1 from L2 with RDMSR instruction */ +static inline void rdmsr_from_l2(uint32_t msr) +{ + /* Currently, L1 doesn't preserve GPRs during vmexits. */ + __asm__ __volatile__ ("rdmsr" : : "c"(msr) : + "rax", "rbx", "rdx", "rsi", "rdi", "r8", "r9", + "r10", "r11", "r12", "r13", "r14", "r15"); +} void l2_guest_code(void) { + u64 unused; + GUEST_SYNC(3); /* Exit to L1 */ vmmcall(); /* MSR-Bitmap tests */ - rdmsr(MSR_FS_BASE); /* intercepted */ - rdmsr(MSR_FS_BASE); /* intercepted */ - rdmsr(MSR_GS_BASE); /* not intercepted */ + rdmsr_from_l2(MSR_FS_BASE); /* intercepted */ + rdmsr_from_l2(MSR_FS_BASE); /* intercepted */ + rdmsr_from_l2(MSR_GS_BASE); /* not intercepted */ vmmcall(); - rdmsr(MSR_GS_BASE); /* intercepted */ + rdmsr_from_l2(MSR_GS_BASE); /* intercepted */ GUEST_SYNC(5); + /* L2 TLB flush tests */ + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | + HV_HYPERCALL_FAST_BIT, 0x0, + HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | + HV_FLUSH_ALL_PROCESSORS); + rdmsr_from_l2(MSR_FS_BASE); + /* + * Note: hypercall status (RAX) is not preserved correctly by L1 after + * synthetic vmexit, use unchecked version. + */ + __hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | + HV_HYPERCALL_FAST_BIT, 0x0, + HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | + HV_FLUSH_ALL_PROCESSORS, &unused); + /* Done, exit to L1 and never come back. */ vmmcall(); } -static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm) +static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm, + struct hyperv_test_pages *hv_pages, + vm_vaddr_t pgs_gpa) { unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; struct vmcb *vmcb = svm->vmcb; - struct hv_enlightenments *hve = - (struct hv_enlightenments *)vmcb->control.reserved_sw; + struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments; GUEST_SYNC(1); - wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48); + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); + enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist); GUEST_ASSERT(svm->vmcb_gpa); /* Prepare for L2 execution. */ generic_svm_setup(svm, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + /* L2 TLB flush setup */ + hve->partition_assist_page = hv_pages->partition_assist_gpa; + hve->hv_enlightenments_control.nested_flush_hypercall = 1; + hve->hv_vm_id = 1; + hve->hv_vp_id = 1; + current_vp_assist->nested_control.features.directhypercall = 1; + *(u32 *)(hv_pages->partition_assist) = 0; + GUEST_SYNC(2); run_guest(vmcb, svm->vmcb_gpa); GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); @@ -98,18 +117,32 @@ static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm) /* Intercept RDMSR 0xc0000101 without telling KVM about it */ set_bit(2 * (MSR_GS_BASE & 0x1fff), svm->msr + 0x800); /* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */ - vmcb->control.clean |= VMCB_HV_NESTED_ENLIGHTENMENTS; + vmcb->control.clean |= HV_VMCB_NESTED_ENLIGHTENMENTS; run_guest(vmcb, svm->vmcb_gpa); /* Make sure we don't see SVM_EXIT_MSR here so eMSR bitmap works */ GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); vmcb->save.rip += 3; /* vmcall */ /* Now tell KVM we've changed MSR-Bitmap */ - vmcb->control.clean &= ~VMCB_HV_NESTED_ENLIGHTENMENTS; + vmcb->control.clean &= ~HV_VMCB_NESTED_ENLIGHTENMENTS; run_guest(vmcb, svm->vmcb_gpa); GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); vmcb->save.rip += 2; /* rdmsr */ + + /* + * L2 TLB flush test. First VMCALL should be handled directly by L0, + * no VMCALL exit expected. + */ + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR); + vmcb->save.rip += 2; /* rdmsr */ + /* Enable synthetic vmexit */ + *(u32 *)(hv_pages->partition_assist) = 1; + run_guest(vmcb, svm->vmcb_gpa); + GUEST_ASSERT(vmcb->control.exit_code == HV_SVM_EXITCODE_ENL); + GUEST_ASSERT(vmcb->control.exit_info_1 == HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH); + run_guest(vmcb, svm->vmcb_gpa); GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); GUEST_SYNC(6); @@ -119,8 +152,8 @@ static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm) int main(int argc, char *argv[]) { - vm_vaddr_t nested_gva = 0; - + vm_vaddr_t nested_gva = 0, hv_pages_gva = 0; + vm_vaddr_t hcall_page; struct kvm_vcpu *vcpu; struct kvm_vm *vm; struct kvm_run *run; @@ -134,7 +167,13 @@ int main(int argc, char *argv[]) vcpu_set_hv_cpuid(vcpu); run = vcpu->run; vcpu_alloc_svm(vm, &nested_gva); - vcpu_args_set(vcpu, 1, nested_gva); + vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva); + + hcall_page = vm_vaddr_alloc_pages(vm, 1); + memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize()); + + vcpu_args_set(vcpu, 3, nested_gva, hv_pages_gva, addr_gva2gpa(vm, hcall_page)); + vcpu_set_msr(vcpu, HV_X64_MSR_VP_INDEX, vcpu->id); for (stage = 1;; stage++) { vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c new file mode 100644 index 000000000000..68f97ff720a7 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c @@ -0,0 +1,690 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hyper-V HvFlushVirtualAddress{List,Space}{,Ex} tests + * + * Copyright (C) 2022, Red Hat, Inc. + * + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <asm/barrier.h> +#include <pthread.h> +#include <inttypes.h> + +#include "kvm_util.h" +#include "processor.h" +#include "hyperv.h" +#include "test_util.h" +#include "vmx.h" + +#define WORKER_VCPU_ID_1 2 +#define WORKER_VCPU_ID_2 65 + +#define NTRY 100 +#define NTEST_PAGES 2 + +struct hv_vpset { + u64 format; + u64 valid_bank_mask; + u64 bank_contents[]; +}; + +enum HV_GENERIC_SET_FORMAT { + HV_GENERIC_SET_SPARSE_4K, + HV_GENERIC_SET_ALL, +}; + +#define HV_FLUSH_ALL_PROCESSORS BIT(0) +#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1) +#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2) +#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3) + +/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ +struct hv_tlb_flush { + u64 address_space; + u64 flags; + u64 processor_mask; + u64 gva_list[]; +} __packed; + +/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */ +struct hv_tlb_flush_ex { + u64 address_space; + u64 flags; + struct hv_vpset hv_vp_set; + u64 gva_list[]; +} __packed; + +/* + * Pass the following info to 'workers' and 'sender' + * - Hypercall page's GVA + * - Hypercall page's GPA + * - Test pages GVA + * - GVAs of the test pages' PTEs + */ +struct test_data { + vm_vaddr_t hcall_gva; + vm_paddr_t hcall_gpa; + vm_vaddr_t test_pages; + vm_vaddr_t test_pages_pte[NTEST_PAGES]; +}; + +/* 'Worker' vCPU code checking the contents of the test page */ +static void worker_guest_code(vm_vaddr_t test_data) +{ + struct test_data *data = (struct test_data *)test_data; + u32 vcpu_id = rdmsr(HV_X64_MSR_VP_INDEX); + void *exp_page = (void *)data->test_pages + PAGE_SIZE * NTEST_PAGES; + u64 *this_cpu = (u64 *)(exp_page + vcpu_id * sizeof(u64)); + u64 expected, val; + + x2apic_enable(); + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + + for (;;) { + cpu_relax(); + + expected = READ_ONCE(*this_cpu); + + /* + * Make sure the value in the test page is read after reading + * the expectation for the first time. Pairs with wmb() in + * prepare_to_test(). + */ + rmb(); + + val = READ_ONCE(*(u64 *)data->test_pages); + + /* + * Make sure the value in the test page is read after before + * reading the expectation for the second time. Pairs with wmb() + * post_test(). + */ + rmb(); + + /* + * '0' indicates the sender is between iterations, wait until + * the sender is ready for this vCPU to start checking again. + */ + if (!expected) + continue; + + /* + * Re-read the per-vCPU byte to ensure the sender didn't move + * onto a new iteration. + */ + if (expected != READ_ONCE(*this_cpu)) + continue; + + GUEST_ASSERT(val == expected); + } +} + +/* + * Write per-CPU info indicating what each 'worker' CPU is supposed to see in + * test page. '0' means don't check. + */ +static void set_expected_val(void *addr, u64 val, int vcpu_id) +{ + void *exp_page = addr + PAGE_SIZE * NTEST_PAGES; + + *(u64 *)(exp_page + vcpu_id * sizeof(u64)) = val; +} + +/* + * Update PTEs swapping two test pages. + * TODO: use swap()/xchg() when these are provided. + */ +static void swap_two_test_pages(vm_paddr_t pte_gva1, vm_paddr_t pte_gva2) +{ + uint64_t tmp = *(uint64_t *)pte_gva1; + + *(uint64_t *)pte_gva1 = *(uint64_t *)pte_gva2; + *(uint64_t *)pte_gva2 = tmp; +} + +/* + * TODO: replace the silly NOP loop with a proper udelay() implementation. + */ +static inline void do_delay(void) +{ + int i; + + for (i = 0; i < 1000000; i++) + asm volatile("nop"); +} + +/* + * Prepare to test: 'disable' workers by setting the expectation to '0', + * clear hypercall input page and then swap two test pages. + */ +static inline void prepare_to_test(struct test_data *data) +{ + /* Clear hypercall input page */ + memset((void *)data->hcall_gva, 0, PAGE_SIZE); + + /* 'Disable' workers */ + set_expected_val((void *)data->test_pages, 0x0, WORKER_VCPU_ID_1); + set_expected_val((void *)data->test_pages, 0x0, WORKER_VCPU_ID_2); + + /* Make sure workers are 'disabled' before we swap PTEs. */ + wmb(); + + /* Make sure workers have enough time to notice */ + do_delay(); + + /* Swap test page mappings */ + swap_two_test_pages(data->test_pages_pte[0], data->test_pages_pte[1]); +} + +/* + * Finalize the test: check hypercall resule set the expected val for + * 'worker' CPUs and give them some time to test. + */ +static inline void post_test(struct test_data *data, u64 exp1, u64 exp2) +{ + /* Make sure we change the expectation after swapping PTEs */ + wmb(); + + /* Set the expectation for workers, '0' means don't test */ + set_expected_val((void *)data->test_pages, exp1, WORKER_VCPU_ID_1); + set_expected_val((void *)data->test_pages, exp2, WORKER_VCPU_ID_2); + + /* Make sure workers have enough time to test */ + do_delay(); +} + +#define TESTVAL1 0x0101010101010101 +#define TESTVAL2 0x0202020202020202 + +/* Main vCPU doing the test */ +static void sender_guest_code(vm_vaddr_t test_data) +{ + struct test_data *data = (struct test_data *)test_data; + struct hv_tlb_flush *flush = (struct hv_tlb_flush *)data->hcall_gva; + struct hv_tlb_flush_ex *flush_ex = (struct hv_tlb_flush_ex *)data->hcall_gva; + vm_paddr_t hcall_gpa = data->hcall_gpa; + int i, stage = 1; + + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + wrmsr(HV_X64_MSR_HYPERCALL, data->hcall_gpa); + + /* "Slow" hypercalls */ + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE for WORKER_VCPU_ID_1 */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush->processor_mask = BIT(WORKER_VCPU_ID_1); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE, hcall_gpa, + hcall_gpa + PAGE_SIZE); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, 0x0); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST for WORKER_VCPU_ID_1 */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush->processor_mask = BIT(WORKER_VCPU_ID_1); + flush->gva_list[0] = (u64)data->test_pages; + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), + hcall_gpa, hcall_gpa + PAGE_SIZE); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, 0x0); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE for HV_FLUSH_ALL_PROCESSORS */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | + HV_FLUSH_ALL_PROCESSORS; + flush->processor_mask = 0; + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE, hcall_gpa, + hcall_gpa + PAGE_SIZE); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST for HV_FLUSH_ALL_PROCESSORS */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | + HV_FLUSH_ALL_PROCESSORS; + flush->gva_list[0] = (u64)data->test_pages; + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), + hcall_gpa, hcall_gpa + PAGE_SIZE); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for WORKER_VCPU_ID_2 */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64); + flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_2 % 64); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX | + (1 << HV_HYPERCALL_VARHEAD_OFFSET), + hcall_gpa, hcall_gpa + PAGE_SIZE); + post_test(data, 0x0, i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for WORKER_VCPU_ID_2 */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64); + flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_2 % 64); + /* bank_contents and gva_list occupy the same space, thus [1] */ + flush_ex->gva_list[1] = (u64)data->test_pages; + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX | + (1 << HV_HYPERCALL_VARHEAD_OFFSET) | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), + hcall_gpa, hcall_gpa + PAGE_SIZE); + post_test(data, 0x0, i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for both vCPUs */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64) | + BIT_ULL(WORKER_VCPU_ID_1 / 64); + flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_1 % 64); + flush_ex->hv_vp_set.bank_contents[1] = BIT_ULL(WORKER_VCPU_ID_2 % 64); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX | + (2 << HV_HYPERCALL_VARHEAD_OFFSET), + hcall_gpa, hcall_gpa + PAGE_SIZE); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for both vCPUs */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_1 / 64) | + BIT_ULL(WORKER_VCPU_ID_2 / 64); + flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_1 % 64); + flush_ex->hv_vp_set.bank_contents[1] = BIT_ULL(WORKER_VCPU_ID_2 % 64); + /* bank_contents and gva_list occupy the same space, thus [2] */ + flush_ex->gva_list[2] = (u64)data->test_pages; + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX | + (2 << HV_HYPERCALL_VARHEAD_OFFSET) | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), + hcall_gpa, hcall_gpa + PAGE_SIZE); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for HV_GENERIC_SET_ALL */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush_ex->hv_vp_set.format = HV_GENERIC_SET_ALL; + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, + hcall_gpa, hcall_gpa + PAGE_SIZE); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for HV_GENERIC_SET_ALL */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush_ex->hv_vp_set.format = HV_GENERIC_SET_ALL; + flush_ex->gva_list[0] = (u64)data->test_pages; + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), + hcall_gpa, hcall_gpa + PAGE_SIZE); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + /* "Fast" hypercalls */ + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE for WORKER_VCPU_ID_1 */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush->processor_mask = BIT(WORKER_VCPU_ID_1); + hyperv_write_xmm_input(&flush->processor_mask, 1); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | + HV_HYPERCALL_FAST_BIT, 0x0, + HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, 0x0); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST for WORKER_VCPU_ID_1 */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush->processor_mask = BIT(WORKER_VCPU_ID_1); + flush->gva_list[0] = (u64)data->test_pages; + hyperv_write_xmm_input(&flush->processor_mask, 1); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST | + HV_HYPERCALL_FAST_BIT | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), + 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, 0x0); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE for HV_FLUSH_ALL_PROCESSORS */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + hyperv_write_xmm_input(&flush->processor_mask, 1); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | + HV_HYPERCALL_FAST_BIT, 0x0, + HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | + HV_FLUSH_ALL_PROCESSORS); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST for HV_FLUSH_ALL_PROCESSORS */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush->gva_list[0] = (u64)data->test_pages; + hyperv_write_xmm_input(&flush->processor_mask, 1); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST | + HV_HYPERCALL_FAST_BIT | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), 0x0, + HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | + HV_FLUSH_ALL_PROCESSORS); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for WORKER_VCPU_ID_2 */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64); + flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_2 % 64); + hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX | + HV_HYPERCALL_FAST_BIT | + (1 << HV_HYPERCALL_VARHEAD_OFFSET), + 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES); + post_test(data, 0x0, i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for WORKER_VCPU_ID_2 */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64); + flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_2 % 64); + /* bank_contents and gva_list occupy the same space, thus [1] */ + flush_ex->gva_list[1] = (u64)data->test_pages; + hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX | + HV_HYPERCALL_FAST_BIT | + (1 << HV_HYPERCALL_VARHEAD_OFFSET) | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), + 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES); + post_test(data, 0x0, i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for both vCPUs */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64) | + BIT_ULL(WORKER_VCPU_ID_1 / 64); + flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_1 % 64); + flush_ex->hv_vp_set.bank_contents[1] = BIT_ULL(WORKER_VCPU_ID_2 % 64); + hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX | + HV_HYPERCALL_FAST_BIT | + (2 << HV_HYPERCALL_VARHEAD_OFFSET), + 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES); + post_test(data, i % 2 ? TESTVAL1 : + TESTVAL2, i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for both vCPUs */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_1 / 64) | + BIT_ULL(WORKER_VCPU_ID_2 / 64); + flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_1 % 64); + flush_ex->hv_vp_set.bank_contents[1] = BIT_ULL(WORKER_VCPU_ID_2 % 64); + /* bank_contents and gva_list occupy the same space, thus [2] */ + flush_ex->gva_list[2] = (u64)data->test_pages; + hyperv_write_xmm_input(&flush_ex->hv_vp_set, 3); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX | + HV_HYPERCALL_FAST_BIT | + (2 << HV_HYPERCALL_VARHEAD_OFFSET) | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), + 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for HV_GENERIC_SET_ALL */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush_ex->hv_vp_set.format = HV_GENERIC_SET_ALL; + hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX | + HV_HYPERCALL_FAST_BIT, + 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_SYNC(stage++); + + /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for HV_GENERIC_SET_ALL */ + for (i = 0; i < NTRY; i++) { + prepare_to_test(data); + flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES; + flush_ex->hv_vp_set.format = HV_GENERIC_SET_ALL; + flush_ex->gva_list[0] = (u64)data->test_pages; + hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2); + hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX | + HV_HYPERCALL_FAST_BIT | + (1UL << HV_HYPERCALL_REP_COMP_OFFSET), + 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES); + post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, + i % 2 ? TESTVAL1 : TESTVAL2); + } + + GUEST_DONE(); +} + +static void *vcpu_thread(void *arg) +{ + struct kvm_vcpu *vcpu = (struct kvm_vcpu *)arg; + struct ucall uc; + int old; + int r; + unsigned int exit_reason; + + r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old); + TEST_ASSERT(!r, "pthread_setcanceltype failed on vcpu_id=%u with errno=%d", + vcpu->id, r); + + vcpu_run(vcpu); + exit_reason = vcpu->run->exit_reason; + + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "vCPU %u exited with unexpected exit reason %u-%s, expected KVM_EXIT_IO", + vcpu->id, exit_reason, exit_reason_str(exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + /* NOT REACHED */ + default: + TEST_FAIL("Unexpected ucall %lu, vCPU %d", uc.cmd, vcpu->id); + } + + return NULL; +} + +static void cancel_join_vcpu_thread(pthread_t thread, struct kvm_vcpu *vcpu) +{ + void *retval; + int r; + + r = pthread_cancel(thread); + TEST_ASSERT(!r, "pthread_cancel on vcpu_id=%d failed with errno=%d", + vcpu->id, r); + + r = pthread_join(thread, &retval); + TEST_ASSERT(!r, "pthread_join on vcpu_id=%d failed with errno=%d", + vcpu->id, r); + TEST_ASSERT(retval == PTHREAD_CANCELED, + "expected retval=%p, got %p", PTHREAD_CANCELED, + retval); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu[3]; + unsigned int exit_reason; + pthread_t threads[2]; + vm_vaddr_t test_data_page, gva; + vm_paddr_t gpa; + uint64_t *pte; + struct test_data *data; + struct ucall uc; + int stage = 1, r, i; + + vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code); + + /* Test data page */ + test_data_page = vm_vaddr_alloc_page(vm); + data = (struct test_data *)addr_gva2hva(vm, test_data_page); + + /* Hypercall input/output */ + data->hcall_gva = vm_vaddr_alloc_pages(vm, 2); + data->hcall_gpa = addr_gva2gpa(vm, data->hcall_gva); + memset(addr_gva2hva(vm, data->hcall_gva), 0x0, 2 * PAGE_SIZE); + + /* + * Test pages: the first one is filled with '0x01's, the second with '0x02's + * and the test will swap their mappings. The third page keeps the indication + * about the current state of mappings. + */ + data->test_pages = vm_vaddr_alloc_pages(vm, NTEST_PAGES + 1); + for (i = 0; i < NTEST_PAGES; i++) + memset(addr_gva2hva(vm, data->test_pages + PAGE_SIZE * i), + (u8)(i + 1), PAGE_SIZE); + set_expected_val(addr_gva2hva(vm, data->test_pages), 0x0, WORKER_VCPU_ID_1); + set_expected_val(addr_gva2hva(vm, data->test_pages), 0x0, WORKER_VCPU_ID_2); + + /* + * Get PTE pointers for test pages and map them inside the guest. + * Use separate page for each PTE for simplicity. + */ + gva = vm_vaddr_unused_gap(vm, NTEST_PAGES * PAGE_SIZE, KVM_UTIL_MIN_VADDR); + for (i = 0; i < NTEST_PAGES; i++) { + pte = vm_get_page_table_entry(vm, data->test_pages + i * PAGE_SIZE); + gpa = addr_hva2gpa(vm, pte); + __virt_pg_map(vm, gva + PAGE_SIZE * i, gpa & PAGE_MASK, PG_LEVEL_4K); + data->test_pages_pte[i] = gva + (gpa & ~PAGE_MASK); + } + + /* + * Sender vCPU which performs the test: swaps test pages, sets expectation + * for 'workers' and issues TLB flush hypercalls. + */ + vcpu_args_set(vcpu[0], 1, test_data_page); + vcpu_set_hv_cpuid(vcpu[0]); + + /* Create worker vCPUs which check the contents of the test pages */ + vcpu[1] = vm_vcpu_add(vm, WORKER_VCPU_ID_1, worker_guest_code); + vcpu_args_set(vcpu[1], 1, test_data_page); + vcpu_set_msr(vcpu[1], HV_X64_MSR_VP_INDEX, WORKER_VCPU_ID_1); + vcpu_set_hv_cpuid(vcpu[1]); + + vcpu[2] = vm_vcpu_add(vm, WORKER_VCPU_ID_2, worker_guest_code); + vcpu_args_set(vcpu[2], 1, test_data_page); + vcpu_set_msr(vcpu[2], HV_X64_MSR_VP_INDEX, WORKER_VCPU_ID_2); + vcpu_set_hv_cpuid(vcpu[2]); + + r = pthread_create(&threads[0], NULL, vcpu_thread, vcpu[1]); + TEST_ASSERT(!r, "pthread_create() failed"); + + r = pthread_create(&threads[1], NULL, vcpu_thread, vcpu[2]); + TEST_ASSERT(!r, "pthread_create() failed"); + + while (true) { + vcpu_run(vcpu[0]); + exit_reason = vcpu[0]->run->exit_reason; + + TEST_ASSERT(exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + exit_reason, exit_reason_str(exit_reason)); + + switch (get_ucall(vcpu[0], &uc)) { + case UCALL_SYNC: + TEST_ASSERT(uc.args[1] == stage, + "Unexpected stage: %ld (%d expected)\n", + uc.args[1], stage); + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + /* NOT REACHED */ + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + stage++; + } + +done: + cancel_join_vcpu_thread(threads[0], vcpu[1]); + cancel_join_vcpu_thread(threads[1], vcpu[2]); + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c index 59ffe7fd354f..ea0978f22db8 100644 --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c @@ -241,10 +241,10 @@ int main(int argc, char **argv) while ((opt = getopt(argc, argv, "hp:t:r")) != -1) { switch (opt) { case 'p': - reclaim_period_ms = atoi(optarg); + reclaim_period_ms = atoi_non_negative("Reclaim period", optarg); break; case 't': - token = atoi(optarg); + token = atoi_paranoid(optarg); break; case 'r': reboot_permissions = true; @@ -257,7 +257,6 @@ int main(int argc, char **argv) } TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES)); - TEST_REQUIRE(reclaim_period_ms > 0); __TEST_REQUIRE(token == MAGIC_TOKEN, "This test must be run with the magic token %d.\n" diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index 76417c7d687b..310a104d94f0 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -72,9 +72,6 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; uint64_t msr_platform_info; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_MSR_PLATFORM_INFO)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); 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 ea4e259a1e2e..2de98fce7edd 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 @@ -21,29 +21,6 @@ #define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) #define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) -union cpuid10_eax { - struct { - unsigned int version_id:8; - unsigned int num_counters:8; - unsigned int bit_width:8; - unsigned int mask_length:8; - } split; - unsigned int full; -}; - -union cpuid10_ebx { - struct { - unsigned int no_unhalted_core_cycles:1; - unsigned int no_instructions_retired:1; - unsigned int no_unhalted_reference_cycles:1; - unsigned int no_llc_reference:1; - unsigned int no_llc_misses:1; - unsigned int no_branch_instruction_retired:1; - unsigned int no_branch_misses_retired:1; - } split; - unsigned int full; -}; - /* End of stuff taken from perf_event.h. */ /* Oddly, this isn't in perf_event.h. */ @@ -380,46 +357,31 @@ static void test_pmu_config_disable(void (*guest_code)(void)) } /* - * Check for a non-zero PMU version, at least one general-purpose - * counter per logical processor, an EBX bit vector of length greater - * than 5, and EBX[5] clear. - */ -static bool check_intel_pmu_leaf(const struct kvm_cpuid_entry2 *entry) -{ - union cpuid10_eax eax = { .full = entry->eax }; - union cpuid10_ebx ebx = { .full = entry->ebx }; - - return eax.split.version_id && eax.split.num_counters > 0 && - eax.split.mask_length > ARCH_PERFMON_BRANCHES_RETIRED && - !ebx.split.no_branch_instruction_retired; -} - -/* - * Note that CPUID leaf 0xa is Intel-specific. This leaf should be - * clear on AMD hardware. + * On Intel, check for a non-zero PMU version, at least one general-purpose + * counter per logical processor, and support for counting the number of branch + * instructions retired. */ static bool use_intel_pmu(void) { - const struct kvm_cpuid_entry2 *entry; - - entry = kvm_get_supported_cpuid_entry(0xa); - return is_intel_cpu() && check_intel_pmu_leaf(entry); + return is_intel_cpu() && + kvm_cpu_property(X86_PROPERTY_PMU_VERSION) && + kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS) && + kvm_pmu_has(X86_PMU_FEATURE_BRANCH_INSNS_RETIRED); } -static bool is_zen1(uint32_t eax) +static bool is_zen1(uint32_t family, uint32_t model) { - return x86_family(eax) == 0x17 && x86_model(eax) <= 0x0f; + return family == 0x17 && model <= 0x0f; } -static bool is_zen2(uint32_t eax) +static bool is_zen2(uint32_t family, uint32_t model) { - return x86_family(eax) == 0x17 && - x86_model(eax) >= 0x30 && x86_model(eax) <= 0x3f; + return family == 0x17 && model >= 0x30 && model <= 0x3f; } -static bool is_zen3(uint32_t eax) +static bool is_zen3(uint32_t family, uint32_t model) { - return x86_family(eax) == 0x19 && x86_model(eax) <= 0x0f; + return family == 0x19 && model <= 0x0f; } /* @@ -432,13 +394,13 @@ static bool is_zen3(uint32_t eax) */ static bool use_amd_pmu(void) { - const struct kvm_cpuid_entry2 *entry; + uint32_t family = kvm_cpu_family(); + uint32_t model = kvm_cpu_model(); - entry = kvm_get_supported_cpuid_entry(1); return is_amd_cpu() && - (is_zen1(entry->eax) || - is_zen2(entry->eax) || - is_zen3(entry->eax)); + (is_zen1(family, model) || + is_zen2(family, model) || + is_zen3(family, model)); } int main(int argc, char *argv[]) @@ -447,9 +409,6 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); TEST_REQUIRE(use_intel_pmu() || use_amd_pmu()); diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c index 2bb08bf2125d..a284fcef6ed7 100644 --- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c @@ -82,9 +82,6 @@ int main(int argc, char *argv[]) uint64_t cr4; int rc; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - /* * Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and * use it to verify all supported CR4 bits can be set prior to defining diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c new file mode 100644 index 000000000000..06edf00a97d6 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020, Google LLC. + * + * Test that KVM emulates instructions in response to EPT violations when + * allow_smaller_maxphyaddr is enabled and guest.MAXPHYADDR < host.MAXPHYADDR. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ + +#include "flds_emulation.h" + +#include "test_util.h" +#include "kvm_util.h" +#include "vmx.h" + +#define MAXPHYADDR 36 + +#define MEM_REGION_GVA 0x0000123456789000 +#define MEM_REGION_GPA 0x0000000700000000 +#define MEM_REGION_SLOT 10 +#define MEM_REGION_SIZE PAGE_SIZE + +static void guest_code(bool tdp_enabled) +{ + uint64_t error_code; + uint64_t vector; + + vector = kvm_asm_safe_ec(FLDS_MEM_EAX, error_code, "a"(MEM_REGION_GVA)); + + /* + * When TDP is enabled, flds will trigger an emulation failure, exit to + * userspace, and then the selftest host "VMM" skips the instruction. + * + * When TDP is disabled, no instruction emulation is required so flds + * should generate #PF(RSVD). + */ + if (tdp_enabled) { + GUEST_ASSERT(!vector); + } else { + GUEST_ASSERT_EQ(vector, PF_VECTOR); + GUEST_ASSERT(error_code & PFERR_RSVD_MASK); + } + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + uint64_t *pte; + uint64_t *hva; + uint64_t gpa; + int rc; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_SMALLER_MAXPHYADDR)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vcpu_args_set(vcpu, 1, kvm_is_tdp_enabled()); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR); + + rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE); + TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable"); + vm_enable_cap(vm, KVM_CAP_EXIT_ON_EMULATION_FAILURE, 1); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + MEM_REGION_GPA, MEM_REGION_SLOT, + MEM_REGION_SIZE / PAGE_SIZE, 0); + gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE, + MEM_REGION_GPA, MEM_REGION_SLOT); + TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n"); + virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1); + hva = addr_gpa2hva(vm, MEM_REGION_GPA); + memset(hva, 0, PAGE_SIZE); + + pte = vm_get_page_table_entry(vm, MEM_REGION_GVA); + *pte |= BIT_ULL(MAXPHYADDR); + + vcpu_run(vcpu); + + /* + * When TDP is enabled, KVM must emulate in response the guest physical + * address that is illegal from the guest's perspective, but is legal + * from hardware's perspeective. This should result in an emulation + * failure exit to userspace since KVM doesn't support emulating flds. + */ + if (kvm_is_tdp_enabled()) { + handle_flds_emulation_failure_exit(vcpu); + vcpu_run(vcpu); + } + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unrecognized ucall: %lu\n", uc.cmd); + } + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index 1f136a81858e..cb38a478e1f6 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -137,6 +137,8 @@ int main(int argc, char *argv[]) struct kvm_x86_state *state; int stage, stage_reported; + TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_SMM)); + /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c new file mode 100644 index 000000000000..e73fcdef47bb --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_nested_shutdown_test + * + * Copyright (C) 2022, Red Hat, Inc. + * + * Nested SVM testing: test that unintercepted shutdown in L2 doesn't crash the host + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" + +static void l2_guest_code(struct svm_test_data *svm) +{ + __asm__ __volatile__("ud2"); +} + +static void l1_guest_code(struct svm_test_data *svm, struct idt_entry *idt) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN)); + + idt[6].p = 0; // #UD is intercepted but its injection will cause #NP + idt[11].p = 0; // #NP is not intercepted and will cause another + // #NP that will be converted to #DF + idt[8].p = 0; // #DF will cause #NP which will cause SHUTDOWN + + run_guest(vmcb, svm->vmcb_gpa); + + /* should not reach here */ + GUEST_ASSERT(0); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + vm_vaddr_t svm_gva; + struct kvm_vm *vm; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + vcpu_alloc_svm(vm, &svm_gva); + + vcpu_args_set(vcpu, 2, svm_gva, vm->idt); + run = vcpu->run; + + vcpu_run(vcpu); + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c index e637d7736012..e497ace629c1 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c @@ -194,9 +194,6 @@ done: int main(int argc, char *argv[]) { - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); TEST_ASSERT(kvm_cpu_has(X86_FEATURE_NRIPS), diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index 9b6db0b0b13e..d2f9b5bdfab2 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -90,9 +90,6 @@ int main(int argc, char *argv[]) struct kvm_vcpu_events events; int rv, cap; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - cap = kvm_check_cap(KVM_CAP_SYNC_REGS); TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS); TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD)); diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c index 70b44f0b52fe..ead5d878a71c 100644 --- a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c +++ b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c @@ -3,6 +3,7 @@ #include "kvm_util.h" #include "processor.h" #include "vmx.h" +#include "svm_util.h" #include <string.h> #include <sys/ioctl.h> @@ -20,10 +21,11 @@ static void l2_guest_code(void) : : [port] "d" (ARBITRARY_IO_PORT) : "rax"); } -void l1_guest_code(struct vmx_pages *vmx) -{ #define L2_GUEST_STACK_SIZE 64 - unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; +unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + +void l1_guest_code_vmx(struct vmx_pages *vmx) +{ GUEST_ASSERT(vmx->vmcs_gpa); GUEST_ASSERT(prepare_for_vmx_operation(vmx)); @@ -38,24 +40,53 @@ void l1_guest_code(struct vmx_pages *vmx) GUEST_DONE(); } +void l1_guest_code_svm(struct svm_test_data *svm) +{ + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* don't intercept shutdown to test the case of SVM allowing to do so */ + vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN)); + + run_guest(vmcb, svm->vmcb_gpa); + + /* should not reach here, L1 should crash */ + GUEST_ASSERT(0); +} + int main(void) { struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vcpu_events events; - vm_vaddr_t vmx_pages_gva; struct ucall uc; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + bool has_vmx = kvm_cpu_has(X86_FEATURE_VMX); + bool has_svm = kvm_cpu_has(X86_FEATURE_SVM); + + TEST_REQUIRE(has_vmx || has_svm); TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_TRIPLE_FAULT_EVENT)); - vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1); + if (has_vmx) { + vm_vaddr_t vmx_pages_gva; + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_vmx); + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + } else { + vm_vaddr_t svm_gva; + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_svm); + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vcpu, 1, svm_gva); + } + + vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1); run = vcpu->run; - vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vcpu, 1, vmx_pages_gva); vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, @@ -78,13 +109,21 @@ int main(void) "No triple fault pending"); vcpu_run(vcpu); - switch (get_ucall(vcpu, &uc)) { - case UCALL_DONE: - break; - case UCALL_ABORT: - REPORT_GUEST_ASSERT(uc); - default: - TEST_FAIL("Unexpected ucall: %lu", uc.cmd); - } + if (has_svm) { + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + } else { + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + } + return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c index 7316521428f8..91076c9787b4 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c @@ -56,9 +56,6 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; struct ucall uc; - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - vm = vm_create_with_one_vcpu(&vcpu, guest_code); run = vcpu->run; diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c index a4f06370a245..25fa55344a10 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -733,16 +733,98 @@ static void test_msr_permission_bitmap(void) kvm_vm_free(vm); } -int main(int argc, char *argv[]) +#define test_user_exit_msr_ioctl(vm, cmd, arg, flag, valid_mask) \ +({ \ + int r = __vm_ioctl(vm, cmd, arg); \ + \ + if (flag & valid_mask) \ + TEST_ASSERT(!r, __KVM_IOCTL_ERROR(#cmd, r)); \ + else \ + TEST_ASSERT(r == -1 && errno == EINVAL, \ + "Wanted EINVAL for %s with flag = 0x%llx, got rc: %i errno: %i (%s)", \ + #cmd, flag, r, errno, strerror(errno)); \ +}) + +static void run_user_space_msr_flag_test(struct kvm_vm *vm) { - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); + struct kvm_enable_cap cap = { .cap = KVM_CAP_X86_USER_SPACE_MSR }; + int nflags = sizeof(cap.args[0]) * BITS_PER_BYTE; + int rc; + int i; + + rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); + TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); + + for (i = 0; i < nflags; i++) { + cap.args[0] = BIT_ULL(i); + test_user_exit_msr_ioctl(vm, KVM_ENABLE_CAP, &cap, + BIT_ULL(i), KVM_MSR_EXIT_REASON_VALID_MASK); + } +} + +static void run_msr_filter_flag_test(struct kvm_vm *vm) +{ + u64 deny_bits = 0; + struct kvm_msr_filter filter = { + .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, + .ranges = { + { + .flags = KVM_MSR_FILTER_READ, + .nmsrs = 1, + .base = 0, + .bitmap = (uint8_t *)&deny_bits, + }, + }, + }; + int nflags; + int rc; + int i; + + rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); + TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); + + nflags = sizeof(filter.flags) * BITS_PER_BYTE; + for (i = 0; i < nflags; i++) { + filter.flags = BIT_ULL(i); + test_user_exit_msr_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter, + BIT_ULL(i), KVM_MSR_FILTER_VALID_MASK); + } + filter.flags = KVM_MSR_FILTER_DEFAULT_ALLOW; + nflags = sizeof(filter.ranges[0].flags) * BITS_PER_BYTE; + for (i = 0; i < nflags; i++) { + filter.ranges[0].flags = BIT_ULL(i); + test_user_exit_msr_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter, + BIT_ULL(i), KVM_MSR_FILTER_RANGE_VALID_MASK); + } +} + +/* Test that attempts to write to the unused bits in a flag fails. */ +static void test_user_exit_msr_flags(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + + /* Test flags for KVM_CAP_X86_USER_SPACE_MSR. */ + run_user_space_msr_flag_test(vm); + + /* Test flags and range flags for KVM_X86_SET_MSR_FILTER. */ + run_msr_filter_flag_test(vm); + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ test_msr_filter_allow(); test_msr_filter_deny(); test_msr_permission_bitmap(); + test_user_exit_msr_flags(); + return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index 2d8c23d639f7..f0456fb031b1 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -78,6 +78,7 @@ int main(int argc, char *argv[]) bool done = false; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + TEST_REQUIRE(kvm_cpu_has_ept()); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); 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 069589c52f41..c280ba1e6572 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 @@ -20,16 +20,6 @@ #define PMU_CAP_FW_WRITES (1ULL << 13) #define PMU_CAP_LBR_FMT 0x3f -union cpuid10_eax { - struct { - unsigned int version_id:8; - unsigned int num_counters:8; - unsigned int bit_width:8; - unsigned int mask_length:8; - } split; - unsigned int full; -}; - union perf_capabilities { struct { u64 lbr_format:6; @@ -53,11 +43,9 @@ static void guest_code(void) int main(int argc, char *argv[]) { - const struct kvm_cpuid_entry2 *entry_a_0; struct kvm_vm *vm; struct kvm_vcpu *vcpu; int ret; - union cpuid10_eax eax; union perf_capabilities host_cap; uint64_t val; @@ -69,11 +57,8 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); - TEST_REQUIRE(kvm_get_cpuid_max_basic() >= 0xa); - entry_a_0 = kvm_get_supported_cpuid_entry(0xa); - - eax.full = entry_a_0->eax; - __TEST_REQUIRE(eax.split.version_id, "PMU is not supported by the vCPU"); + TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION)); + TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0); /* testcase 1, set capabilities when we have PDCM bit */ vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index 6f7a5ef66718..d7d37dae3eeb 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -114,7 +114,9 @@ static void test_icr(struct xapic_vcpu *x) * vCPUs, not vcpu.id + 1. Arbitrarily use vector 0xff. */ icr = APIC_INT_ASSERT | 0xff; - for (i = vcpu->id + 1; i < 0xff; i++) { + for (i = 0; i < 0xff; i++) { + if (i == vcpu->id) + continue; for (j = 0; j < 8; j++) __test_icr(x, i << (32 + 24) | icr | (j << 8)); } diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 8a5cb800f50e..2a5727188c8d 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -15,9 +15,13 @@ #include <time.h> #include <sched.h> #include <signal.h> +#include <pthread.h> #include <sys/eventfd.h> +/* Defined in include/linux/kvm_types.h */ +#define GPA_INVALID (~(ulong)0) + #define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 @@ -44,6 +48,8 @@ #define MIN_STEAL_TIME 50000 +#define SHINFO_RACE_TIMEOUT 2 /* seconds */ + #define __HYPERVISOR_set_timer_op 15 #define __HYPERVISOR_sched_op 29 #define __HYPERVISOR_event_channel_op 32 @@ -126,7 +132,7 @@ struct { struct kvm_irq_routing_entry entries[2]; } irq_routes; -bool guest_saw_irq; +static volatile bool guest_saw_irq; static void evtchn_handler(struct ex_regs *regs) { @@ -148,6 +154,7 @@ static void guest_wait_for_irq(void) static void guest_code(void) { struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR; + int i; __asm__ __volatile__( "sti\n" @@ -325,6 +332,49 @@ static void guest_code(void) guest_wait_for_irq(); GUEST_SYNC(21); + /* Racing host ioctls */ + + guest_wait_for_irq(); + + GUEST_SYNC(22); + /* Racing vmcall against host ioctl */ + + ports[0] = 0; + + p = (struct sched_poll) { + .ports = ports, + .nr_ports = 1, + .timeout = 0 + }; + +wait_for_timer: + /* + * Poll for a timer wake event while the worker thread is mucking with + * the shared info. KVM XEN drops timer IRQs if the shared info is + * invalid when the timer expires. Arbitrarily poll 100 times before + * giving up and asking the VMM to re-arm the timer. 100 polls should + * consume enough time to beat on KVM without taking too long if the + * timer IRQ is dropped due to an invalid event channel. + */ + for (i = 0; i < 100 && !guest_saw_irq; i++) + asm volatile("vmcall" + : "=a" (rax) + : "a" (__HYPERVISOR_sched_op), + "D" (SCHEDOP_poll), + "S" (&p) + : "memory"); + + /* + * Re-send the timer IRQ if it was (likely) dropped due to the timer + * expiring while the event channel was invalid. + */ + if (!guest_saw_irq) { + GUEST_SYNC(23); + goto wait_for_timer; + } + guest_saw_irq = false; + + GUEST_SYNC(24); } static int cmp_timespec(struct timespec *a, struct timespec *b) @@ -352,11 +402,36 @@ static void handle_alrm(int sig) TEST_FAIL("IRQ delivery timed out"); } +static void *juggle_shinfo_state(void *arg) +{ + struct kvm_vm *vm = (struct kvm_vm *)arg; + + struct kvm_xen_hvm_attr cache_init = { + .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, + .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE + }; + + struct kvm_xen_hvm_attr cache_destroy = { + .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, + .u.shared_info.gfn = GPA_INVALID + }; + + for (;;) { + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_init); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_destroy); + pthread_testcancel(); + }; + + return NULL; +} + int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; struct kvm_vm *vm; + pthread_t thread; bool verbose; + int ret; verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) || !strncmp(argv[1], "--verbose", 10)); @@ -785,6 +860,71 @@ int main(int argc, char *argv[]) case 21: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); + alarm(0); + + if (verbose) + printf("Testing shinfo lock corruption (KVM_XEN_HVM_EVTCHN_SEND)\n"); + + ret = pthread_create(&thread, NULL, &juggle_shinfo_state, (void *)vm); + TEST_ASSERT(ret == 0, "pthread_create() failed: %s", strerror(ret)); + + struct kvm_irq_routing_xen_evtchn uxe = { + .port = 1, + .vcpu = vcpu->id, + .priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL + }; + + evtchn_irq_expected = true; + for (time_t t = time(NULL) + SHINFO_RACE_TIMEOUT; time(NULL) < t;) + __vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &uxe); + break; + + case 22: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + + if (verbose) + printf("Testing shinfo lock corruption (SCHEDOP_poll)\n"); + + shinfo->evtchn_pending[0] = 1; + + evtchn_irq_expected = true; + tmr.u.timer.expires_ns = rs->state_entry_time + + SHINFO_RACE_TIMEOUT * 1000000000ULL; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + break; + + case 23: + /* + * Optional and possibly repeated sync point. + * Injecting the timer IRQ may fail if the + * shinfo is invalid when the timer expires. + * If the timer has expired but the IRQ hasn't + * been delivered, rearm the timer and retry. + */ + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); + + /* Resume the guest if the timer is still pending. */ + if (tmr.u.timer.expires_ns) + break; + + /* All done if the IRQ was delivered. */ + if (!evtchn_irq_expected) + break; + + tmr.u.timer.expires_ns = rs->state_entry_time + + SHINFO_RACE_TIMEOUT * 1000000000ULL; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + break; + case 24: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + + ret = pthread_cancel(thread); + TEST_ASSERT(ret == 0, "pthread_cancel() failed: %s", strerror(ret)); + + ret = pthread_join(thread, 0); + TEST_ASSERT(ret == 0, "pthread_join() failed: %s", strerror(ret)); goto done; case 0x20: diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index 6632bfff486b..348e2dbdb4e0 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -3,7 +3,6 @@ # First run: make -C ../../../.. headers_install CFLAGS += -Wall -O2 $(KHDR_INCLUDES) -LDLIBS += -lcap LOCAL_HDRS += common.h @@ -13,10 +12,12 @@ TEST_GEN_PROGS := $(src_test:.c=) TEST_GEN_PROGS_EXTENDED := true -# Static linking for short targets: +# Short targets: +$(TEST_GEN_PROGS): LDLIBS += -lcap $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static include ../lib.mk -# Static linking for targets with $(OUTPUT)/ prefix: +# Targets with $(OUTPUT)/ prefix: +$(TEST_GEN_PROGS): LDLIBS += -lcap $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 9d4cb94cf437..a3ea3d4a206d 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -70,7 +70,7 @@ endef run_tests: all ifdef building_out_of_srctree @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ - rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ + rsync -aLq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ fi @if [ "X$(TEST_PROGS)" != "X" ]; then \ $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) \ @@ -84,7 +84,7 @@ endif define INSTALL_SINGLE_RULE $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) - $(if $(INSTALL_LIST),rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),rsync -aL $(INSTALL_LIST) $(INSTALL_PATH)/) endef define INSTALL_RULE diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh index 74ee5067a8ce..611be86eaf3d 100755 --- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh +++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh @@ -138,7 +138,6 @@ online_all_offline_memory() { for memory in `hotpluggable_offline_memory`; do if ! online_memory_expect_success $memory; then - echo "$FUNCNAME $memory: unexpected fail" >&2 retval=1 fi done diff --git a/tools/testing/selftests/net/openvswitch/Makefile b/tools/testing/selftests/net/openvswitch/Makefile new file mode 100644 index 000000000000..2f1508abc826 --- /dev/null +++ b/tools/testing/selftests/net/openvswitch/Makefile @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 + +top_srcdir = ../../../../.. + +CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) + +TEST_PROGS := openvswitch.sh + +TEST_FILES := ovs-dpctl.py + +EXTRA_CLEAN := test_netlink_checks + +include ../../lib.mk diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh new file mode 100755 index 000000000000..7ce46700a3ae --- /dev/null +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -0,0 +1,218 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# OVS kernel module self tests + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +PAUSE_ON_FAIL=no +VERBOSE=0 +TRACING=0 + +tests=" + netlink_checks ovsnl: validate netlink attrs and settings" + +info() { + [ $VERBOSE = 0 ] || echo $* +} + +ovs_base=`pwd` +sbxs= +sbx_add () { + info "adding sandbox '$1'" + + sbxs="$sbxs $1" + + NO_BIN=0 + + # Create sandbox. + local d="$ovs_base"/$1 + if [ -e $d ]; then + info "removing $d" + rm -rf "$d" + fi + mkdir "$d" || return 1 + ovs_setenv $1 +} + +ovs_exit_sig() { + [ -e ${ovs_dir}/cleanup ] && . "$ovs_dir/cleanup" +} + +on_exit() { + echo "$1" > ${ovs_dir}/cleanup.tmp + cat ${ovs_dir}/cleanup >> ${ovs_dir}/cleanup.tmp + mv ${ovs_dir}/cleanup.tmp ${ovs_dir}/cleanup +} + +ovs_setenv() { + sandbox=$1 + + ovs_dir=$ovs_base${1:+/$1}; export ovs_dir + + test -e ${ovs_dir}/cleanup || : > ${ovs_dir}/cleanup +} + +ovs_sbx() { + if test "X$2" != X; then + (ovs_setenv $1; shift; "$@" >> ${ovs_dir}/debug.log) + else + ovs_setenv $1 + fi +} + +ovs_add_dp () { + info "Adding DP/Bridge IF: sbx:$1 dp:$2 {$3, $4, $5}" + sbxname="$1" + shift + ovs_sbx "$sbxname" python3 $ovs_base/ovs-dpctl.py add-dp $* + on_exit "ovs_sbx $sbxname python3 $ovs_base/ovs-dpctl.py del-dp $1;" +} + +usage() { + echo + echo "$0 [OPTIONS] [TEST]..." + echo "If no TEST argument is given, all tests will be run." + echo + echo "Options" + echo " -t: capture traffic via tcpdump" + echo " -v: verbose" + echo " -p: pause on failure" + echo + echo "Available tests${tests}" + exit 1 +} + +# netlink_validation +# - Create a dp +# - check no warning with "old version" simulation +test_netlink_checks () { + sbx_add "test_netlink_checks" || return 1 + + info "setting up new DP" + ovs_add_dp "test_netlink_checks" nv0 || return 1 + # now try again + PRE_TEST=$(dmesg | grep -E "RIP: [0-9a-fA-Fx]+:ovs_dp_cmd_new\+") + ovs_add_dp "test_netlink_checks" nv0 -V 0 || return 1 + POST_TEST=$(dmesg | grep -E "RIP: [0-9a-fA-Fx]+:ovs_dp_cmd_new\+") + if [ "$PRE_TEST" != "$POST_TEST" ]; then + info "failed - gen warning" + return 1 + fi + + return 0 +} + +run_test() { + ( + tname="$1" + tdesc="$2" + + if ! lsmod | grep openvswitch >/dev/null 2>&1; then + stdbuf -o0 printf "TEST: %-60s [NOMOD]\n" "${tdesc}" + return $ksft_skip + fi + + if python3 ovs-dpctl.py -h 2>&1 | \ + grep "Need to install the python" >/dev/null 2>&1; then + stdbuf -o0 printf "TEST: %-60s [PYLIB]\n" "${tdesc}" + return $ksft_skip + fi + printf "TEST: %-60s [START]\n" "${tname}" + + unset IFS + + eval test_${tname} + ret=$? + + if [ $ret -eq 0 ]; then + printf "TEST: %-60s [ OK ]\n" "${tdesc}" + ovs_exit_sig + rm -rf "$ovs_dir" + elif [ $ret -eq 1 ]; then + printf "TEST: %-60s [FAIL]\n" "${tdesc}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "Pausing. Logs in $ovs_dir/. Hit enter to continue" + read a + fi + ovs_exit_sig + [ "${PAUSE_ON_FAIL}" = "yes" ] || rm -rf "$ovs_dir" + exit 1 + elif [ $ret -eq $ksft_skip ]; then + printf "TEST: %-60s [SKIP]\n" "${tdesc}" + elif [ $ret -eq 2 ]; then + rm -rf test_${tname} + run_test "$1" "$2" + fi + + return $ret + ) + ret=$? + case $ret in + 0) + [ $all_skipped = true ] && [ $exitcode=$ksft_skip ] && exitcode=0 + all_skipped=false + ;; + $ksft_skip) + [ $all_skipped = true ] && exitcode=$ksft_skip + ;; + *) + all_skipped=false + exitcode=1 + ;; + esac + + return $ret +} + + +exitcode=0 +desc=0 +all_skipped=true + +while getopts :pvt o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=1;; + t) if which tcpdump > /dev/null 2>&1; then + TRACING=1 + else + echo "=== tcpdump not available, tracing disabled" + fi + ;; + *) usage;; + esac +done +shift $(($OPTIND-1)) + +IFS=" +" + +for arg do + # Check first that all requested tests are available before running any + command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; } +done + +name="" +desc="" +for t in ${tests}; do + [ "${name}" = "" ] && name="${t}" && continue + [ "${desc}" = "" ] && desc="${t}" + + run_this=1 + for arg do + [ "${arg}" != "${arg#--*}" ] && continue + [ "${arg}" = "${name}" ] && run_this=1 && break + run_this=0 + done + if [ $run_this -eq 1 ]; then + run_test "${name}" "${desc}" + fi + name="" + desc="" +done + +exit ${exitcode} diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py new file mode 100644 index 000000000000..3243c90d449e --- /dev/null +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -0,0 +1,351 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +# Controls the openvswitch module. Part of the kselftest suite, but +# can be used for some diagnostic purpose as well. + +import argparse +import errno +import sys + +try: + from pyroute2 import NDB + + from pyroute2.netlink import NLM_F_ACK + from pyroute2.netlink import NLM_F_REQUEST + from pyroute2.netlink import genlmsg + from pyroute2.netlink import nla + from pyroute2.netlink.exceptions import NetlinkError + from pyroute2.netlink.generic import GenericNetlinkSocket +except ModuleNotFoundError: + print("Need to install the python pyroute2 package.") + sys.exit(0) + + +OVS_DATAPATH_FAMILY = "ovs_datapath" +OVS_VPORT_FAMILY = "ovs_vport" +OVS_FLOW_FAMILY = "ovs_flow" +OVS_PACKET_FAMILY = "ovs_packet" +OVS_METER_FAMILY = "ovs_meter" +OVS_CT_LIMIT_FAMILY = "ovs_ct_limit" + +OVS_DATAPATH_VERSION = 2 +OVS_DP_CMD_NEW = 1 +OVS_DP_CMD_DEL = 2 +OVS_DP_CMD_GET = 3 +OVS_DP_CMD_SET = 4 + +OVS_VPORT_CMD_NEW = 1 +OVS_VPORT_CMD_DEL = 2 +OVS_VPORT_CMD_GET = 3 +OVS_VPORT_CMD_SET = 4 + + +class ovs_dp_msg(genlmsg): + # include the OVS version + # We need a custom header rather than just being able to rely on + # genlmsg because fields ends up not expressing everything correctly + # if we use the canonical example of setting fields = (('customfield',),) + fields = genlmsg.fields + (("dpifindex", "I"),) + + +class OvsDatapath(GenericNetlinkSocket): + + OVS_DP_F_VPORT_PIDS = 1 << 1 + OVS_DP_F_DISPATCH_UPCALL_PER_CPU = 1 << 3 + + class dp_cmd_msg(ovs_dp_msg): + """ + Message class that will be used to communicate with the kernel module. + """ + + nla_map = ( + ("OVS_DP_ATTR_UNSPEC", "none"), + ("OVS_DP_ATTR_NAME", "asciiz"), + ("OVS_DP_ATTR_UPCALL_PID", "uint32"), + ("OVS_DP_ATTR_STATS", "dpstats"), + ("OVS_DP_ATTR_MEGAFLOW_STATS", "megaflowstats"), + ("OVS_DP_ATTR_USER_FEATURES", "uint32"), + ("OVS_DP_ATTR_PAD", "none"), + ("OVS_DP_ATTR_MASKS_CACHE_SIZE", "uint32"), + ("OVS_DP_ATTR_PER_CPU_PIDS", "array(uint32)"), + ) + + class dpstats(nla): + fields = ( + ("hit", "=Q"), + ("missed", "=Q"), + ("lost", "=Q"), + ("flows", "=Q"), + ) + + class megaflowstats(nla): + fields = ( + ("mask_hit", "=Q"), + ("masks", "=I"), + ("padding", "=I"), + ("cache_hits", "=Q"), + ("pad1", "=Q"), + ) + + def __init__(self): + GenericNetlinkSocket.__init__(self) + self.bind(OVS_DATAPATH_FAMILY, OvsDatapath.dp_cmd_msg) + + def info(self, dpname, ifindex=0): + msg = OvsDatapath.dp_cmd_msg() + msg["cmd"] = OVS_DP_CMD_GET + msg["version"] = OVS_DATAPATH_VERSION + msg["reserved"] = 0 + msg["dpifindex"] = ifindex + msg["attrs"].append(["OVS_DP_ATTR_NAME", dpname]) + + try: + reply = self.nlm_request( + msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST + ) + reply = reply[0] + except NetlinkError as ne: + if ne.code == errno.ENODEV: + reply = None + else: + raise ne + + return reply + + def create(self, dpname, shouldUpcall=False, versionStr=None): + msg = OvsDatapath.dp_cmd_msg() + msg["cmd"] = OVS_DP_CMD_NEW + if versionStr is None: + msg["version"] = OVS_DATAPATH_VERSION + else: + msg["version"] = int(versionStr.split(":")[0], 0) + msg["reserved"] = 0 + msg["dpifindex"] = 0 + msg["attrs"].append(["OVS_DP_ATTR_NAME", dpname]) + + dpfeatures = 0 + if versionStr is not None and versionStr.find(":") != -1: + dpfeatures = int(versionStr.split(":")[1], 0) + else: + dpfeatures = OvsDatapath.OVS_DP_F_VPORT_PIDS + + msg["attrs"].append(["OVS_DP_ATTR_USER_FEATURES", dpfeatures]) + if not shouldUpcall: + msg["attrs"].append(["OVS_DP_ATTR_UPCALL_PID", 0]) + + try: + reply = self.nlm_request( + msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST | NLM_F_ACK + ) + reply = reply[0] + except NetlinkError as ne: + if ne.code == errno.EEXIST: + reply = None + else: + raise ne + + return reply + + def destroy(self, dpname): + msg = OvsDatapath.dp_cmd_msg() + msg["cmd"] = OVS_DP_CMD_DEL + msg["version"] = OVS_DATAPATH_VERSION + msg["reserved"] = 0 + msg["dpifindex"] = 0 + msg["attrs"].append(["OVS_DP_ATTR_NAME", dpname]) + + try: + reply = self.nlm_request( + msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST | NLM_F_ACK + ) + reply = reply[0] + except NetlinkError as ne: + if ne.code == errno.ENODEV: + reply = None + else: + raise ne + + return reply + + +class OvsVport(GenericNetlinkSocket): + class ovs_vport_msg(ovs_dp_msg): + nla_map = ( + ("OVS_VPORT_ATTR_UNSPEC", "none"), + ("OVS_VPORT_ATTR_PORT_NO", "uint32"), + ("OVS_VPORT_ATTR_TYPE", "uint32"), + ("OVS_VPORT_ATTR_NAME", "asciiz"), + ("OVS_VPORT_ATTR_OPTIONS", "none"), + ("OVS_VPORT_ATTR_UPCALL_PID", "array(uint32)"), + ("OVS_VPORT_ATTR_STATS", "vportstats"), + ("OVS_VPORT_ATTR_PAD", "none"), + ("OVS_VPORT_ATTR_IFINDEX", "uint32"), + ("OVS_VPORT_ATTR_NETNSID", "uint32"), + ) + + class vportstats(nla): + fields = ( + ("rx_packets", "=Q"), + ("tx_packets", "=Q"), + ("rx_bytes", "=Q"), + ("tx_bytes", "=Q"), + ("rx_errors", "=Q"), + ("tx_errors", "=Q"), + ("rx_dropped", "=Q"), + ("tx_dropped", "=Q"), + ) + + def type_to_str(vport_type): + if vport_type == 1: + return "netdev" + elif vport_type == 2: + return "internal" + elif vport_type == 3: + return "gre" + elif vport_type == 4: + return "vxlan" + elif vport_type == 5: + return "geneve" + return "unknown:%d" % vport_type + + def __init__(self): + GenericNetlinkSocket.__init__(self) + self.bind(OVS_VPORT_FAMILY, OvsVport.ovs_vport_msg) + + def info(self, vport_name, dpifindex=0, portno=None): + msg = OvsVport.ovs_vport_msg() + + msg["cmd"] = OVS_VPORT_CMD_GET + msg["version"] = OVS_DATAPATH_VERSION + msg["reserved"] = 0 + msg["dpifindex"] = dpifindex + + if portno is None: + msg["attrs"].append(["OVS_VPORT_ATTR_NAME", vport_name]) + else: + msg["attrs"].append(["OVS_VPORT_ATTR_PORT_NO", portno]) + + try: + reply = self.nlm_request( + msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST + ) + reply = reply[0] + except NetlinkError as ne: + if ne.code == errno.ENODEV: + reply = None + else: + raise ne + return reply + + +def print_ovsdp_full(dp_lookup_rep, ifindex, ndb=NDB()): + dp_name = dp_lookup_rep.get_attr("OVS_DP_ATTR_NAME") + base_stats = dp_lookup_rep.get_attr("OVS_DP_ATTR_STATS") + megaflow_stats = dp_lookup_rep.get_attr("OVS_DP_ATTR_MEGAFLOW_STATS") + user_features = dp_lookup_rep.get_attr("OVS_DP_ATTR_USER_FEATURES") + masks_cache_size = dp_lookup_rep.get_attr("OVS_DP_ATTR_MASKS_CACHE_SIZE") + + print("%s:" % dp_name) + print( + " lookups: hit:%d missed:%d lost:%d" + % (base_stats["hit"], base_stats["missed"], base_stats["lost"]) + ) + print(" flows:%d" % base_stats["flows"]) + pkts = base_stats["hit"] + base_stats["missed"] + avg = (megaflow_stats["mask_hit"] / pkts) if pkts != 0 else 0.0 + print( + " masks: hit:%d total:%d hit/pkt:%f" + % (megaflow_stats["mask_hit"], megaflow_stats["masks"], avg) + ) + print(" caches:") + print(" masks-cache: size:%d" % masks_cache_size) + + if user_features is not None: + print(" features: 0x%X" % user_features) + + # port print out + vpl = OvsVport() + for iface in ndb.interfaces: + rep = vpl.info(iface.ifname, ifindex) + if rep is not None: + print( + " port %d: %s (%s)" + % ( + rep.get_attr("OVS_VPORT_ATTR_PORT_NO"), + rep.get_attr("OVS_VPORT_ATTR_NAME"), + OvsVport.type_to_str(rep.get_attr("OVS_VPORT_ATTR_TYPE")), + ) + ) + + +def main(argv): + parser = argparse.ArgumentParser() + parser.add_argument( + "-v", + "--verbose", + action="count", + help="Increment 'verbose' output counter.", + ) + subparsers = parser.add_subparsers() + + showdpcmd = subparsers.add_parser("show") + showdpcmd.add_argument( + "showdp", metavar="N", type=str, nargs="?", help="Datapath Name" + ) + + adddpcmd = subparsers.add_parser("add-dp") + adddpcmd.add_argument("adddp", help="Datapath Name") + adddpcmd.add_argument( + "-u", + "--upcall", + action="store_true", + help="Leave open a reader for upcalls", + ) + adddpcmd.add_argument( + "-V", + "--versioning", + required=False, + help="Specify a custom version / feature string", + ) + + deldpcmd = subparsers.add_parser("del-dp") + deldpcmd.add_argument("deldp", help="Datapath Name") + + args = parser.parse_args() + + ovsdp = OvsDatapath() + ndb = NDB() + + if hasattr(args, "showdp"): + found = False + for iface in ndb.interfaces: + rep = None + if args.showdp is None: + rep = ovsdp.info(iface.ifname, 0) + elif args.showdp == iface.ifname: + rep = ovsdp.info(iface.ifname, 0) + + if rep is not None: + found = True + print_ovsdp_full(rep, iface.index, ndb) + + if not found: + msg = "No DP found" + if args.showdp is not None: + msg += ":'%s'" % args.showdp + print(msg) + elif hasattr(args, "adddp"): + rep = ovsdp.create(args.adddp, args.upcall, args.versioning) + if rep is None: + print("DP '%s' already exists" % args.adddp) + else: + print("DP '%s' added" % args.adddp) + elif hasattr(args, "deldp"): + ovsdp.destroy(args.deldp) + + return 0 + + +if __name__ == "__main__": + sys.exit(main(sys.argv)) diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index f4a2f28f926b..778b6cdc8aed 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g -I../../../../usr/include/ -pthread +CFLAGS += -g -I../../../../usr/include/ -pthread -Wall TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \ pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 9a2d64901d59..e2dd4ed84984 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -413,7 +413,7 @@ static void poll_pidfd(const char *test_name, int pidfd) c = epoll_wait(epoll_fd, events, MAX_EVENTS, 5000); if (c != 1 || !(events[0].events & EPOLLIN)) - ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) ", + ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) " "(errno %d)\n", test_name, c, events[0].events, errno); @@ -435,6 +435,8 @@ static int child_poll_exec_test(void *args) */ while (1) sleep(1); + + return 0; } static void test_pidfd_poll_exec(int use_waitpid) diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 070c1c876df1..0dcb8365ddc3 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -95,20 +95,28 @@ TEST(wait_states) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; + int pfd[2]; pid_t pid; siginfo_t info = { .si_signo = 0, }; + ASSERT_EQ(pipe(pfd), 0); pid = sys_clone3(&args); ASSERT_GE(pid, 0); if (pid == 0) { + char buf[2]; + + close(pfd[1]); kill(getpid(), SIGSTOP); + ASSERT_EQ(read(pfd[0], buf, 1), 1); + close(pfd[0]); kill(getpid(), SIGSTOP); exit(EXIT_SUCCESS); } + close(pfd[0]); ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_STOPPED); @@ -117,6 +125,8 @@ TEST(wait_states) ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0); ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL), 0); + ASSERT_EQ(write(pfd[1], "C", 1), 1); + close(pfd[1]); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_CONTINUED); ASSERT_EQ(info.si_pid, parent_tid); @@ -138,7 +148,7 @@ TEST(wait_states) TEST(wait_nonblock) { - int pidfd, status = 0; + int pidfd; unsigned int flags = 0; pid_t parent_tid = -1; struct clone_args args = { |