aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/arch/arm64/include/asm/cputype.h4
-rw-r--r--tools/arch/arm64/include/uapi/asm/kvm.h15
-rw-r--r--tools/arch/powerpc/include/uapi/asm/kvm.h45
-rw-r--r--tools/arch/s390/include/uapi/asm/kvm.h315
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h17
-rw-r--r--tools/arch/x86/include/asm/disabled-features.h11
-rw-r--r--tools/arch/x86/include/asm/irq_vectors.h2
-rw-r--r--tools/arch/x86/include/asm/msr-index.h74
-rw-r--r--tools/arch/x86/include/asm/required-features.h3
-rw-r--r--tools/arch/x86/include/uapi/asm/kvm.h308
-rw-r--r--tools/hv/hv_kvp_daemon.c213
-rw-r--r--tools/include/asm-generic/bitops/__fls.h8
-rw-r--r--tools/include/asm-generic/bitops/fls.h8
-rw-r--r--tools/include/linux/kernel.h1
-rw-r--r--tools/include/linux/mm.h5
-rw-r--r--tools/include/linux/panic.h19
-rw-r--r--tools/include/uapi/drm/i915_drm.h16
-rw-r--r--tools/include/uapi/linux/fs.h30
-rw-r--r--tools/include/uapi/linux/kvm.h689
-rw-r--r--tools/include/uapi/sound/asound.h4
-rw-r--r--tools/net/ynl/lib/ynl.py1
-rw-r--r--tools/perf/arch/riscv/util/header.c2
-rw-r--r--tools/perf/ui/browsers/annotate.c2
-rw-r--r--tools/perf/util/annotate.c3
-rw-r--r--tools/perf/util/bpf_skel/lock_contention.bpf.c5
-rw-r--r--tools/power/x86/turbostat/turbostat.818
-rw-r--r--tools/power/x86/turbostat/turbostat.c2017
-rw-r--r--tools/testing/cxl/test/cxl.c17
-rw-r--r--tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c3
-rw-r--r--tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc6
-rw-r--r--tools/testing/selftests/iommu/config2
-rw-r--r--tools/testing/selftests/kselftest.h43
-rw-r--r--tools/testing/selftests/kselftest_harness.h19
-rw-r--r--tools/testing/selftests/kvm/Makefile4
-rw-r--r--tools/testing/selftests/kvm/aarch64/arch_timer.c8
-rw-r--r--tools/testing/selftests/kvm/aarch64/page_fault_test.c4
-rw-r--r--tools/testing/selftests/kvm/aarch64/psci_test.c3
-rw-r--r--tools/testing/selftests/kvm/aarch64/set_id_regs.c123
-rw-r--r--tools/testing/selftests/kvm/aarch64/vgic_init.c49
-rw-r--r--tools/testing/selftests/kvm/aarch64/vgic_irq.c15
-rw-r--r--tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c410
-rw-r--r--tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c6
-rw-r--r--tools/testing/selftests/kvm/demand_paging_test.c90
-rw-r--r--tools/testing/selftests/kvm/dirty_log_perf_test.c5
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic.h21
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic_v3.h586
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h19
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/processor.h19
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/vgic.h5
-rw-r--r--tools/testing/selftests/kvm/include/riscv/processor.h49
-rw-r--r--tools/testing/selftests/kvm/include/riscv/sbi.h141
-rw-r--r--tools/testing/selftests/kvm/include/riscv/ucall.h1
-rw-r--r--tools/testing/selftests/kvm/include/userfaultfd_util.h16
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic.c18
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_private.h4
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_v3.c99
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c248
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/vgic.c38
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c8
-rw-r--r--tools/testing/selftests/kvm/lib/riscv/processor.c12
-rw-r--r--tools/testing/selftests/kvm/lib/userfaultfd_util.c153
-rw-r--r--tools/testing/selftests/kvm/max_guest_memory_test.c15
-rw-r--r--tools/testing/selftests/kvm/riscv/arch_timer.c2
-rw-r--r--tools/testing/selftests/kvm/riscv/ebreak_test.c82
-rw-r--r--tools/testing/selftests/kvm/riscv/get-reg-list.c4
-rw-r--r--tools/testing/selftests/kvm/riscv/sbi_pmu_test.c681
-rw-r--r--tools/testing/selftests/kvm/rseq_test.c35
-rw-r--r--tools/testing/selftests/kvm/set_memory_region_test.c2
-rw-r--r--tools/testing/selftests/kvm/steal_time.c51
-rw-r--r--tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c1
-rwxr-xr-xtools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh13
-rw-r--r--tools/testing/selftests/kvm/x86_64/pmu_counters_test.c20
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c60
-rw-r--r--tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c52
-rw-r--r--tools/testing/selftests/mm/mdwe_test.c1
-rw-r--r--tools/testing/selftests/mm/protection_keys.c38
-rwxr-xr-xtools/testing/selftests/mm/run_vmtests.sh2
-rw-r--r--tools/testing/selftests/mm/split_huge_page_test.c2
-rw-r--r--tools/testing/selftests/net/tcp_ao/lib/proc.c2
-rw-r--r--tools/testing/selftests/net/tcp_ao/lib/setup.c12
-rw-r--r--tools/testing/selftests/net/tcp_ao/rst.c23
-rw-r--r--tools/testing/selftests/net/tcp_ao/setsockopt-closed.c2
-rw-r--r--tools/testing/selftests/net/udpgso.c2
-rw-r--r--tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c2
-rw-r--r--tools/testing/selftests/riscv/hwprobe/cbo.c2
-rw-r--r--tools/testing/selftests/riscv/hwprobe/hwprobe.h10
-rw-r--r--tools/testing/selftests/syscall_user_dispatch/sud_test.c14
-rw-r--r--tools/testing/selftests/timers/posix_timers.c105
-rw-r--r--tools/testing/selftests/timers/valid-adjtimex.c73
-rwxr-xr-xtools/testing/selftests/turbostat/defcolumns.py60
90 files changed, 5773 insertions, 1674 deletions
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 7c7493cb571f..52f076afeb96 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -61,6 +61,7 @@
#define ARM_CPU_IMP_HISI 0x48
#define ARM_CPU_IMP_APPLE 0x61
#define ARM_CPU_IMP_AMPERE 0xC0
+#define ARM_CPU_IMP_MICROSOFT 0x6D
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
@@ -135,6 +136,8 @@
#define AMPERE_CPU_PART_AMPERE1 0xAC3
+#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */
+
#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)
@@ -193,6 +196,7 @@
#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)
/* 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/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 89d2fc872d9f..964df31da975 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -37,9 +37,7 @@
#include <asm/ptrace.h>
#include <asm/sve_context.h>
-#define __KVM_HAVE_GUEST_DEBUG
#define __KVM_HAVE_IRQ_LINE
-#define __KVM_HAVE_READONLY_MEM
#define __KVM_HAVE_VCPU_EVENTS
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -76,11 +74,11 @@ struct kvm_regs {
/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
#define KVM_ARM_DEVICE_TYPE_SHIFT 0
-#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
- KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_TYPE_MASK __GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
+ KVM_ARM_DEVICE_TYPE_SHIFT)
#define KVM_ARM_DEVICE_ID_SHIFT 16
-#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
- KVM_ARM_DEVICE_ID_SHIFT)
+#define KVM_ARM_DEVICE_ID_MASK __GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
+ KVM_ARM_DEVICE_ID_SHIFT)
/* Supported device IDs */
#define KVM_ARM_DEVICE_VGIC_V2 0
@@ -162,6 +160,11 @@ struct kvm_sync_regs {
__u64 device_irq_level;
};
+/* Bits for run->s.regs.device_irq_level */
+#define KVM_ARM_DEV_EL1_VTIMER (1 << 0)
+#define KVM_ARM_DEV_EL1_PTIMER (1 << 1)
+#define KVM_ARM_DEV_PMU (1 << 2)
+
/*
* PMU filter structure. Describe a range of events with a particular
* action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 9f18fa090f1f..1691297a766a 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -28,7 +28,6 @@
#define __KVM_HAVE_PPC_SMT
#define __KVM_HAVE_IRQCHIP
#define __KVM_HAVE_IRQ_LINE
-#define __KVM_HAVE_GUEST_DEBUG
/* Not always available, but if it is, this is the correct offset. */
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -733,4 +732,48 @@ struct kvm_ppc_xive_eq {
#define KVM_XIVE_TIMA_PAGE_OFFSET 0
#define KVM_XIVE_ESB_PAGE_OFFSET 4
+/* for KVM_PPC_GET_PVINFO */
+
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
+
+struct kvm_ppc_pvinfo {
+ /* out */
+ __u32 flags;
+ __u32 hcall[4];
+ __u8 pad[108];
+};
+
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ 8
+
+struct kvm_ppc_one_page_size {
+ __u32 page_shift; /* Page shift (or 0) */
+ __u32 pte_enc; /* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+ __u32 page_shift; /* Base page shift of segment (or 0) */
+ __u32 slb_enc; /* SLB encoding for BookS */
+ struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
+#define KVM_PPC_1T_SEGMENTS 0x00000002
+#define KVM_PPC_NO_HASH 0x00000004
+
+struct kvm_ppc_smmu_info {
+ __u64 flags;
+ __u32 slb_size;
+ __u16 data_keys; /* # storage keys supported for data */
+ __u16 instr_keys; /* # storage keys supported for instructions */
+ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
+struct kvm_ppc_resize_hpt {
+ __u64 flags;
+ __u32 shift;
+ __u32 pad;
+};
+
#endif /* __LINUX_KVM_POWERPC_H */
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index abe926d43cbe..05eaf6db3ad4 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -12,7 +12,320 @@
#include <linux/types.h>
#define __KVM_S390
-#define __KVM_HAVE_GUEST_DEBUG
+
+struct kvm_s390_skeys {
+ __u64 start_gfn;
+ __u64 count;
+ __u64 skeydata_addr;
+ __u32 flags;
+ __u32 reserved[9];
+};
+
+#define KVM_S390_CMMA_PEEK (1 << 0)
+
+/**
+ * kvm_s390_cmma_log - Used for CMMA migration.
+ *
+ * Used both for input and output.
+ *
+ * @start_gfn: Guest page number to start from.
+ * @count: Size of the result buffer.
+ * @flags: Control operation mode via KVM_S390_CMMA_* flags
+ * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
+ * pages are still remaining.
+ * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
+ * in the PGSTE.
+ * @values: Pointer to the values buffer.
+ *
+ * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
+ */
+struct kvm_s390_cmma_log {
+ __u64 start_gfn;
+ __u32 count;
+ __u32 flags;
+ union {
+ __u64 remaining;
+ __u64 mask;
+ };
+ __u64 values;
+};
+
+#define KVM_S390_RESET_POR 1
+#define KVM_S390_RESET_CLEAR 2
+#define KVM_S390_RESET_SUBSYSTEM 4
+#define KVM_S390_RESET_CPU_INIT 8
+#define KVM_S390_RESET_IPL 16
+
+/* for KVM_S390_MEM_OP */
+struct kvm_s390_mem_op {
+ /* in */
+ __u64 gaddr; /* the guest address */
+ __u64 flags; /* flags */
+ __u32 size; /* amount of bytes */
+ __u32 op; /* type of operation */
+ __u64 buf; /* buffer in userspace */
+ union {
+ struct {
+ __u8 ar; /* the access register number */
+ __u8 key; /* access key, ignored if flag unset */
+ __u8 pad1[6]; /* ignored */
+ __u64 old_addr; /* ignored if cmpxchg flag unset */
+ };
+ __u32 sida_offset; /* offset into the sida */
+ __u8 reserved[32]; /* ignored */
+ };
+};
+/* types for kvm_s390_mem_op->op */
+#define KVM_S390_MEMOP_LOGICAL_READ 0
+#define KVM_S390_MEMOP_LOGICAL_WRITE 1
+#define KVM_S390_MEMOP_SIDA_READ 2
+#define KVM_S390_MEMOP_SIDA_WRITE 3
+#define KVM_S390_MEMOP_ABSOLUTE_READ 4
+#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5
+#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6
+
+/* flags for kvm_s390_mem_op->flags */
+#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
+#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
+#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2)
+
+/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */
+#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0)
+#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1)
+
+struct kvm_s390_psw {
+ __u64 mask;
+ __u64 addr;
+};
+
+/* valid values for type in kvm_s390_interrupt */
+#define KVM_S390_SIGP_STOP 0xfffe0000u
+#define KVM_S390_PROGRAM_INT 0xfffe0001u
+#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u
+#define KVM_S390_RESTART 0xfffe0003u
+#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u
+#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u
+#define KVM_S390_MCHK 0xfffe1000u
+#define KVM_S390_INT_CLOCK_COMP 0xffff1004u
+#define KVM_S390_INT_CPU_TIMER 0xffff1005u
+#define KVM_S390_INT_VIRTIO 0xffff2603u
+#define KVM_S390_INT_SERVICE 0xffff2401u
+#define KVM_S390_INT_EMERGENCY 0xffff1201u
+#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u
+/* Anything below 0xfffe0000u is taken by INT_IO */
+#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \
+ (((schid)) | \
+ ((ssid) << 16) | \
+ ((cssid) << 18) | \
+ ((ai) << 26))
+#define KVM_S390_INT_IO_MIN 0x00000000u
+#define KVM_S390_INT_IO_MAX 0xfffdffffu
+#define KVM_S390_INT_IO_AI_MASK 0x04000000u
+
+
+struct kvm_s390_interrupt {
+ __u32 type;
+ __u32 parm;
+ __u64 parm64;
+};
+
+struct kvm_s390_io_info {
+ __u16 subchannel_id;
+ __u16 subchannel_nr;
+ __u32 io_int_parm;
+ __u32 io_int_word;
+};
+
+struct kvm_s390_ext_info {
+ __u32 ext_params;
+ __u32 pad;
+ __u64 ext_params2;
+};
+
+struct kvm_s390_pgm_info {
+ __u64 trans_exc_code;
+ __u64 mon_code;
+ __u64 per_address;
+ __u32 data_exc_code;
+ __u16 code;
+ __u16 mon_class_nr;
+ __u8 per_code;
+ __u8 per_atmid;
+ __u8 exc_access_id;
+ __u8 per_access_id;
+ __u8 op_access_id;
+#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01
+#define KVM_S390_PGM_FLAGS_ILC_0 0x02
+#define KVM_S390_PGM_FLAGS_ILC_1 0x04
+#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06
+#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08
+ __u8 flags;
+ __u8 pad[2];
+};
+
+struct kvm_s390_prefix_info {
+ __u32 address;
+};
+
+struct kvm_s390_extcall_info {
+ __u16 code;
+};
+
+struct kvm_s390_emerg_info {
+ __u16 code;
+};
+
+#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01
+struct kvm_s390_stop_info {
+ __u32 flags;
+};
+
+struct kvm_s390_mchk_info {
+ __u64 cr14;
+ __u64 mcic;
+ __u64 failing_storage_address;
+ __u32 ext_damage_code;
+ __u32 pad;
+ __u8 fixed_logout[16];
+};
+
+struct kvm_s390_irq {
+ __u64 type;
+ union {
+ struct kvm_s390_io_info io;
+ struct kvm_s390_ext_info ext;
+ struct kvm_s390_pgm_info pgm;
+ struct kvm_s390_emerg_info emerg;
+ struct kvm_s390_extcall_info extcall;
+ struct kvm_s390_prefix_info prefix;
+ struct kvm_s390_stop_info stop;
+ struct kvm_s390_mchk_info mchk;
+ char reserved[64];
+ } u;
+};
+
+struct kvm_s390_irq_state {
+ __u64 buf;
+ __u32 flags; /* will stay unused for compatibility reasons */
+ __u32 len;
+ __u32 reserved[4]; /* will stay unused for compatibility reasons */
+};
+
+struct kvm_s390_ucas_mapping {
+ __u64 user_addr;
+ __u64 vcpu_addr;
+ __u64 length;
+};
+
+struct kvm_s390_pv_sec_parm {
+ __u64 origin;
+ __u64 length;
+};
+
+struct kvm_s390_pv_unp {
+ __u64 addr;
+ __u64 size;
+ __u64 tweak;
+};
+
+enum pv_cmd_dmp_id {
+ KVM_PV_DUMP_INIT,
+ KVM_PV_DUMP_CONFIG_STOR_STATE,
+ KVM_PV_DUMP_COMPLETE,
+ KVM_PV_DUMP_CPU,
+};
+
+struct kvm_s390_pv_dmp {
+ __u64 subcmd;
+ __u64 buff_addr;
+ __u64 buff_len;
+ __u64 gaddr; /* For dump storage state */
+ __u64 reserved[4];
+};
+
+enum pv_cmd_info_id {
+ KVM_PV_INFO_VM,
+ KVM_PV_INFO_DUMP,
+};
+
+struct kvm_s390_pv_info_dump {
+ __u64 dump_cpu_buffer_len;
+ __u64 dump_config_mem_buffer_per_1m;
+ __u64 dump_config_finalize_len;
+};
+
+struct kvm_s390_pv_info_vm {
+ __u64 inst_calls_list[4];
+ __u64 max_cpus;
+ __u64 max_guests;
+ __u64 max_guest_addr;
+ __u64 feature_indication;
+};
+
+struct kvm_s390_pv_info_header {
+ __u32 id;
+ __u32 len_max;
+ __u32 len_written;
+ __u32 reserved;
+};
+
+struct kvm_s390_pv_info {
+ struct kvm_s390_pv_info_header header;
+ union {
+ struct kvm_s390_pv_info_dump dump;
+ struct kvm_s390_pv_info_vm vm;
+ };
+};
+
+enum pv_cmd_id {
+ KVM_PV_ENABLE,
+ KVM_PV_DISABLE,
+ KVM_PV_SET_SEC_PARMS,
+ KVM_PV_UNPACK,
+ KVM_PV_VERIFY,
+ KVM_PV_PREP_RESET,
+ KVM_PV_UNSHARE_ALL,
+ KVM_PV_INFO,
+ KVM_PV_DUMP,
+ KVM_PV_ASYNC_CLEANUP_PREPARE,
+ KVM_PV_ASYNC_CLEANUP_PERFORM,
+};
+
+struct kvm_pv_cmd {
+ __u32 cmd; /* Command to be executed */
+ __u16 rc; /* Ultravisor return code */
+ __u16 rrc; /* Ultravisor return reason code */
+ __u64 data; /* Data or address */
+ __u32 flags; /* flags for future extensions. Must be 0 for now */
+ __u32 reserved[3];
+};
+
+struct kvm_s390_zpci_op {
+ /* in */
+ __u32 fh; /* target device */
+ __u8 op; /* operation to perform */
+ __u8 pad[3];
+ union {
+ /* for KVM_S390_ZPCIOP_REG_AEN */
+ struct {
+ __u64 ibv; /* Guest addr of interrupt bit vector */
+ __u64 sb; /* Guest addr of summary bit */
+ __u32 flags;
+ __u32 noi; /* Number of interrupts */
+ __u8 isc; /* Guest interrupt subclass */
+ __u8 sbo; /* Offset of guest summary bit vector */
+ __u16 pad;
+ } reg_aen;
+ __u64 reserved[8];
+ } u;
+};
+
+/* types for kvm_s390_zpci_op->op */
+#define KVM_S390_ZPCIOP_REG_AEN 0
+#define KVM_S390_ZPCIOP_DEREG_AEN 1
+
+/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
+#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0)
/* Device control API: s390-specific devices */
#define KVM_DEV_FLIC_GET_ALL_IRQS 1
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 25160d26764b..a38f8f9ba657 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 21 /* N 32-bit words worth of info */
+#define NCAPINTS 22 /* N 32-bit words worth of info */
#define NBUGINTS 2 /* N 32-bit bug flags */
/*
@@ -81,10 +81,8 @@
#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-
-/* CPU types for specific tunings: */
#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */
-/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */
+#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */
#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */
#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */
#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
@@ -97,7 +95,7 @@
#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */
#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */
#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */
#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */
@@ -462,6 +460,14 @@
#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */
/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0x80000022, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */
+
+/*
* BUG word(s)
*/
#define X86_BUG(x) (NCAPINTS*32 + (x))
@@ -508,4 +514,5 @@
/* BUG word 2 */
#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */
#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
+#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 1f23960d2b06..c492bdc97b05 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -123,6 +123,12 @@
# define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31))
#endif
+#ifdef CONFIG_KVM_AMD_SEV
+#define DISABLE_SEV_SNP 0
+#else
+#define DISABLE_SEV_SNP (1 << (X86_FEATURE_SEV_SNP & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -147,8 +153,9 @@
DISABLE_ENQCMD)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 (DISABLE_IBT)
-#define DISABLED_MASK19 0
+#define DISABLED_MASK19 (DISABLE_SEV_SNP)
#define DISABLED_MASK20 0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define DISABLED_MASK21 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h
index 3f73ac3ed3a0..d18bfb238f66 100644
--- a/tools/arch/x86/include/asm/irq_vectors.h
+++ b/tools/arch/x86/include/asm/irq_vectors.h
@@ -84,11 +84,9 @@
#define HYPERVISOR_CALLBACK_VECTOR 0xf3
/* Vector for KVM to deliver posted interrupt IPI */
-#if IS_ENABLED(CONFIG_KVM)
#define POSTED_INTR_VECTOR 0xf2
#define POSTED_INTR_WAKEUP_VECTOR 0xf1
#define POSTED_INTR_NESTED_VECTOR 0xf0
-#endif
#define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 1f9dc9bd13eb..05956bd8bacf 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -176,6 +176,14 @@
* CPU is not vulnerable to Gather
* Data Sampling (GDS).
*/
+#define ARCH_CAP_RFDS_NO BIT(27) /*
+ * Not susceptible to Register
+ * File Data Sampling.
+ */
+#define ARCH_CAP_RFDS_CLEAR BIT(28) /*
+ * VERW clears CPU Register
+ * File.
+ */
#define ARCH_CAP_XAPIC_DISABLE BIT(21) /*
* IA32_XAPIC_DISABLE_STATUS MSR
@@ -605,34 +613,47 @@
#define MSR_AMD64_SEV_ES_GHCB 0xc0010130
#define MSR_AMD64_SEV 0xc0010131
#define MSR_AMD64_SEV_ENABLED_BIT 0
-#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
-#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2
#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
+#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2
#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
-
-/* SNP feature bits enabled by the hypervisor */
-#define MSR_AMD64_SNP_VTOM BIT_ULL(3)
-#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4)
-#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5)
-#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6)
-#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7)
-#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8)
-#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9)
-#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10)
-#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11)
-#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12)
-#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14)
-#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16)
-#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17)
-
-/* SNP feature bits reserved for future use. */
-#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13)
-#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15)
-#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18)
+#define MSR_AMD64_SNP_VTOM_BIT 3
+#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT)
+#define MSR_AMD64_SNP_REFLECT_VC_BIT 4
+#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT)
+#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5
+#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT)
+#define MSR_AMD64_SNP_ALT_INJ_BIT 6
+#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT)
+#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7
+#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT)
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT)
+#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9
+#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT)
+#define MSR_AMD64_SNP_VMPL_SSS_BIT 10
+#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT)
+#define MSR_AMD64_SNP_SECURE_TSC_BIT 11
+#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT)
+#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12
+#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT)
+#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13)
+#define MSR_AMD64_SNP_IBS_VIRT_BIT 14
+#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT)
+#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15)
+#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16
+#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT)
+#define MSR_AMD64_SNP_SMT_PROT_BIT 17
+#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
+#define MSR_AMD64_SNP_RESV_BIT 18
+#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
+#define MSR_AMD64_RMP_BASE 0xc0010132
+#define MSR_AMD64_RMP_END 0xc0010133
+
/* AMD Collaborative Processor Performance Control MSRs */
#define MSR_AMD_CPPC_CAP1 0xc00102b0
#define MSR_AMD_CPPC_ENABLE 0xc00102b1
@@ -719,8 +740,15 @@
#define MSR_K8_TOP_MEM1 0xc001001a
#define MSR_K8_TOP_MEM2 0xc001001d
#define MSR_AMD64_SYSCFG 0xc0010010
-#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23
+#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23
#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT)
+#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24
+#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT)
+#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25
+#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT)
+#define MSR_AMD64_SYSCFG_MFDM_BIT 19
+#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT)
+
#define MSR_K8_INT_PENDING_MSG 0xc0010055
/* C1E active bits in int pending message */
#define K8_INTP_C1E_ACTIVE_MASK 0x18000000
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index 7ba1726b71c7..e9187ddd3d1f 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -99,6 +99,7 @@
#define REQUIRED_MASK18 0
#define REQUIRED_MASK19 0
#define REQUIRED_MASK20 0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define REQUIRED_MASK21 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index a448d0964fc0..ef11aa4cab42 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -7,6 +7,8 @@
*
*/
+#include <linux/const.h>
+#include <linux/bits.h>
#include <linux/types.h>
#include <linux/ioctl.h>
#include <linux/stddef.h>
@@ -40,7 +42,6 @@
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_MSI
#define __KVM_HAVE_USER_NMI
-#define __KVM_HAVE_GUEST_DEBUG
#define __KVM_HAVE_MSIX
#define __KVM_HAVE_MCE
#define __KVM_HAVE_PIT_STATE2
@@ -49,7 +50,6 @@
#define __KVM_HAVE_DEBUGREGS
#define __KVM_HAVE_XSAVE
#define __KVM_HAVE_XCRS
-#define __KVM_HAVE_READONLY_MEM
/* Architectural interrupt line count. */
#define KVM_NR_INTERRUPTS 256
@@ -526,9 +526,301 @@ struct kvm_pmu_event_filter {
#define KVM_PMU_EVENT_ALLOW 0
#define KVM_PMU_EVENT_DENY 1
-#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0)
+#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0)
#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS)
+/* for KVM_CAP_MCE */
+struct kvm_x86_mce {
+ __u64 status;
+ __u64 addr;
+ __u64 misc;
+ __u64 mcg_status;
+ __u8 bank;
+ __u8 pad1[7];
+ __u64 pad2[3];
+};
+
+/* for KVM_CAP_XEN_HVM */
+#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
+#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8)
+
+struct kvm_xen_hvm_config {
+ __u32 flags;
+ __u32 msr;
+ __u64 blob_addr_32;
+ __u64 blob_addr_64;
+ __u8 blob_size_32;
+ __u8 blob_size_64;
+ __u8 pad2[30];
+};
+
+struct kvm_xen_hvm_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u8 long_mode;
+ __u8 vector;
+ __u8 runstate_update_flag;
+ union {
+ __u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
+ __u64 hva;
+ } shared_info;
+ struct {
+ __u32 send_port;
+ __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
+ __u32 flags;
+#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0)
+#define KVM_XEN_EVTCHN_UPDATE (1 << 1)
+#define KVM_XEN_EVTCHN_RESET (1 << 2)
+ /*
+ * Events sent by the guest are either looped back to
+ * the guest itself (potentially on a different port#)
+ * or signalled via an eventfd.
+ */
+ union {
+ struct {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+ } port;
+ struct {
+ __u32 port; /* Zero for eventfd */
+ __s32 fd;
+ } eventfd;
+ __u32 padding[4];
+ } deliver;
+ } evtchn;
+ __u32 xen_version;
+ __u64 pad[8];
+ } u;
+};
+
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3
+#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
+#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 0x6
+
+struct kvm_xen_vcpu_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
+ __u64 hva;
+ __u64 pad[8];
+ struct {
+ __u64 state;
+ __u64 state_entry_time;
+ __u64 time_running;
+ __u64 time_runnable;
+ __u64 time_blocked;
+ __u64 time_offline;
+ } runstate;
+ __u32 vcpu_id;
+ struct {
+ __u32 port;
+ __u32 priority;
+ __u64 expires_ns;
+ } timer;
+ __u8 vector;
+ } u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6
+#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7
+#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 0x9
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+ /* Guest initialization commands */
+ KVM_SEV_INIT = 0,
+ KVM_SEV_ES_INIT,
+ /* Guest launch commands */
+ KVM_SEV_LAUNCH_START,
+ KVM_SEV_LAUNCH_UPDATE_DATA,
+ KVM_SEV_LAUNCH_UPDATE_VMSA,
+ KVM_SEV_LAUNCH_SECRET,
+ KVM_SEV_LAUNCH_MEASURE,
+ KVM_SEV_LAUNCH_FINISH,
+ /* Guest migration commands (outgoing) */
+ KVM_SEV_SEND_START,
+ KVM_SEV_SEND_UPDATE_DATA,
+ KVM_SEV_SEND_UPDATE_VMSA,
+ KVM_SEV_SEND_FINISH,
+ /* Guest migration commands (incoming) */
+ KVM_SEV_RECEIVE_START,
+ KVM_SEV_RECEIVE_UPDATE_DATA,
+ KVM_SEV_RECEIVE_UPDATE_VMSA,
+ KVM_SEV_RECEIVE_FINISH,
+ /* Guest status and debug commands */
+ KVM_SEV_GUEST_STATUS,
+ KVM_SEV_DBG_DECRYPT,
+ KVM_SEV_DBG_ENCRYPT,
+ /* Guest certificates commands */
+ KVM_SEV_CERT_EXPORT,
+ /* Attestation report */
+ KVM_SEV_GET_ATTESTATION_REPORT,
+ /* Guest Migration Extension */
+ KVM_SEV_SEND_CANCEL,
+
+ KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+ __u32 id;
+ __u32 pad0;
+ __u64 data;
+ __u32 error;
+ __u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 dh_uaddr;
+ __u32 dh_len;
+ __u32 pad0;
+ __u64 session_uaddr;
+ __u32 session_len;
+ __u32 pad1;
+};
+
+struct kvm_sev_launch_update_data {
+ __u64 uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+
+struct kvm_sev_launch_secret {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u32 pad0;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u32 pad1;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+ __u32 pad2;
+};
+
+struct kvm_sev_launch_measure {
+ __u64 uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+struct kvm_sev_guest_status {
+ __u32 handle;
+ __u32 policy;
+ __u32 state;
+};
+
+struct kvm_sev_dbg {
+ __u64 src_uaddr;
+ __u64 dst_uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+struct kvm_sev_attestation_report {
+ __u8 mnonce[16];
+ __u64 uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+struct kvm_sev_send_start {
+ __u32 policy;
+ __u32 pad0;
+ __u64 pdh_cert_uaddr;
+ __u32 pdh_cert_len;
+ __u32 pad1;
+ __u64 plat_certs_uaddr;
+ __u32 plat_certs_len;
+ __u32 pad2;
+ __u64 amd_certs_uaddr;
+ __u32 amd_certs_len;
+ __u32 pad3;
+ __u64 session_uaddr;
+ __u32 session_len;
+ __u32 pad4;
+};
+
+struct kvm_sev_send_update_data {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u32 pad0;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u32 pad1;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+ __u32 pad2;
+};
+
+struct kvm_sev_receive_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 pdh_uaddr;
+ __u32 pdh_len;
+ __u32 pad0;
+ __u64 session_uaddr;
+ __u32 session_len;
+ __u32 pad1;
+};
+
+struct kvm_sev_receive_update_data {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u32 pad0;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u32 pad1;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+ __u32 pad2;
+};
+
+#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
+
+struct kvm_hyperv_eventfd {
+ __u32 conn_id;
+ __s32 fd;
+ __u32 flags;
+ __u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
+
/*
* Masked event layout.
* Bits Description
@@ -549,10 +841,10 @@ struct kvm_pmu_event_filter {
((__u64)(!!(exclude)) << 55))
#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \
- (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32))
-#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56))
-#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8))
-#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55))
+ (__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (__GENMASK_ULL(63, 56))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (__GENMASK_ULL(15, 8))
+#define KVM_PMU_MASKED_ENTRY_EXCLUDE (_BITULL(55))
#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56)
/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */
@@ -560,7 +852,7 @@ struct kvm_pmu_event_filter {
#define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
/* x86-specific KVM_EXIT_HYPERCALL flags. */
-#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0)
+#define KVM_EXIT_HYPERCALL_LONG_MODE _BITULL(0)
#define KVM_X86_DEFAULT_VM 0
#define KVM_X86_SW_PROTECTED_VM 1
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 318e2dad27e0..ae57bf69ad4a 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -76,6 +76,12 @@ enum {
DNS
};
+enum {
+ IPV4 = 1,
+ IPV6,
+ IP_TYPE_MAX
+};
+
static int in_hand_shake;
static char *os_name = "";
@@ -102,6 +108,11 @@ static struct utsname uts_buf;
#define MAX_FILE_NAME 100
#define ENTRIES_PER_BLOCK 50
+/*
+ * Change this entry if the number of addresses increases in future
+ */
+#define MAX_IP_ENTRIES 64
+#define OUTSTR_BUF_SIZE ((INET6_ADDRSTRLEN + 1) * MAX_IP_ENTRIES)
struct kvp_record {
char key[HV_KVP_EXCHANGE_MAX_KEY_SIZE];
@@ -1171,6 +1182,18 @@ static int process_ip_string(FILE *f, char *ip_string, int type)
return 0;
}
+int ip_version_check(const char *input_addr)
+{
+ struct in6_addr addr;
+
+ if (inet_pton(AF_INET, input_addr, &addr))
+ return IPV4;
+ else if (inet_pton(AF_INET6, input_addr, &addr))
+ return IPV6;
+
+ return -EINVAL;
+}
+
/*
* Only IPv4 subnet strings needs to be converted to plen
* For IPv6 the subnet is already privided in plen format
@@ -1197,14 +1220,75 @@ static int kvp_subnet_to_plen(char *subnet_addr_str)
return plen;
}
+static int process_dns_gateway_nm(FILE *f, char *ip_string, int type,
+ int ip_sec)
+{
+ char addr[INET6_ADDRSTRLEN], *output_str;
+ int ip_offset = 0, error = 0, ip_ver;
+ char *param_name;
+
+ if (type == DNS)
+ param_name = "dns";
+ else if (type == GATEWAY)
+ param_name = "gateway";
+ else
+ return -EINVAL;
+
+ output_str = (char *)calloc(OUTSTR_BUF_SIZE, sizeof(char));
+ if (!output_str)
+ return -ENOMEM;
+
+ while (1) {
+ memset(addr, 0, sizeof(addr));
+
+ if (!parse_ip_val_buffer(ip_string, &ip_offset, addr,
+ (MAX_IP_ADDR_SIZE * 2)))
+ break;
+
+ ip_ver = ip_version_check(addr);
+ if (ip_ver < 0)
+ continue;
+
+ if ((ip_ver == IPV4 && ip_sec == IPV4) ||
+ (ip_ver == IPV6 && ip_sec == IPV6)) {
+ /*
+ * do a bound check to avoid out-of bound writes
+ */
+ if ((OUTSTR_BUF_SIZE - strlen(output_str)) >
+ (strlen(addr) + 1)) {
+ strncat(output_str, addr,
+ OUTSTR_BUF_SIZE -
+ strlen(output_str) - 1);
+ strncat(output_str, ",",
+ OUTSTR_BUF_SIZE -
+ strlen(output_str) - 1);
+ }
+ } else {
+ continue;
+ }
+ }
+
+ if (strlen(output_str)) {
+ /*
+ * This is to get rid of that extra comma character
+ * in the end of the string
+ */
+ output_str[strlen(output_str) - 1] = '\0';
+ error = fprintf(f, "%s=%s\n", param_name, output_str);
+ }
+
+ free(output_str);
+ return error;
+}
+
static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet,
- int is_ipv6)
+ int ip_sec)
{
char addr[INET6_ADDRSTRLEN];
char subnet_addr[INET6_ADDRSTRLEN];
- int error, i = 0;
+ int error = 0, i = 0;
int ip_offset = 0, subnet_offset = 0;
- int plen;
+ int plen, ip_ver;
memset(addr, 0, sizeof(addr));
memset(subnet_addr, 0, sizeof(subnet_addr));
@@ -1216,10 +1300,16 @@ static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet,
subnet_addr,
(MAX_IP_ADDR_SIZE *
2))) {
- if (!is_ipv6)
+ ip_ver = ip_version_check(addr);
+ if (ip_ver < 0)
+ continue;
+
+ if (ip_ver == IPV4 && ip_sec == IPV4)
plen = kvp_subnet_to_plen((char *)subnet_addr);
- else
+ else if (ip_ver == IPV6 && ip_sec == IPV6)
plen = atoi(subnet_addr);
+ else
+ continue;
if (plen < 0)
return plen;
@@ -1233,17 +1323,16 @@ static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet,
memset(subnet_addr, 0, sizeof(subnet_addr));
}
- return 0;
+ return error;
}
static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
{
- int error = 0;
+ int error = 0, ip_ver;
char if_filename[PATH_MAX];
char nm_filename[PATH_MAX];
FILE *ifcfg_file, *nmfile;
char cmd[PATH_MAX];
- int is_ipv6 = 0;
char *mac_addr;
int str_len;
@@ -1421,52 +1510,94 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
if (error)
goto setval_error;
- if (new_val->addr_family & ADDR_FAMILY_IPV6) {
- error = fprintf(nmfile, "\n[ipv6]\n");
- if (error < 0)
- goto setval_error;
- is_ipv6 = 1;
- } else {
- error = fprintf(nmfile, "\n[ipv4]\n");
- if (error < 0)
- goto setval_error;
- }
-
/*
* Now we populate the keyfile format
+ *
+ * The keyfile format expects the IPv6 and IPv4 configuration in
+ * different sections. Therefore we iterate through the list twice,
+ * once to populate the IPv4 section and the next time for IPv6
*/
+ ip_ver = IPV4;
+ do {
+ if (ip_ver == IPV4) {
+ error = fprintf(nmfile, "\n[ipv4]\n");
+ if (error < 0)
+ goto setval_error;
+ } else {
+ error = fprintf(nmfile, "\n[ipv6]\n");
+ if (error < 0)
+ goto setval_error;
+ }
- if (new_val->dhcp_enabled) {
- error = kvp_write_file(nmfile, "method", "", "auto");
- if (error < 0)
- goto setval_error;
- } else {
- error = kvp_write_file(nmfile, "method", "", "manual");
+ /*
+ * Write the configuration for ipaddress, netmask, gateway and
+ * name services
+ */
+ error = process_ip_string_nm(nmfile, (char *)new_val->ip_addr,
+ (char *)new_val->sub_net,
+ ip_ver);
if (error < 0)
goto setval_error;
- }
- /*
- * Write the configuration for ipaddress, netmask, gateway and
- * name services
- */
- error = process_ip_string_nm(nmfile, (char *)new_val->ip_addr,
- (char *)new_val->sub_net, is_ipv6);
- if (error < 0)
- goto setval_error;
+ /*
+ * As dhcp_enabled is only valid for ipv4, we do not set dhcp
+ * methods for ipv6 based on dhcp_enabled flag.
+ *
+ * For ipv4, set method to manual only when dhcp_enabled is
+ * false and specific ipv4 addresses are configured. If neither
+ * dhcp_enabled is true and no ipv4 addresses are configured,
+ * set method to 'disabled'.
+ *
+ * For ipv6, set method to manual when we configure ipv6
+ * addresses. Otherwise set method to 'auto' so that SLAAC from
+ * RA may be used.
+ */
+ if (ip_ver == IPV4) {
+ if (new_val->dhcp_enabled) {
+ error = kvp_write_file(nmfile, "method", "",
+ "auto");
+ if (error < 0)
+ goto setval_error;
+ } else if (error) {
+ error = kvp_write_file(nmfile, "method", "",
+ "manual");
+ if (error < 0)
+ goto setval_error;
+ } else {
+ error = kvp_write_file(nmfile, "method", "",
+ "disabled");
+ if (error < 0)
+ goto setval_error;
+ }
+ } else if (ip_ver == IPV6) {
+ if (error) {
+ error = kvp_write_file(nmfile, "method", "",
+ "manual");
+ if (error < 0)
+ goto setval_error;
+ } else {
+ error = kvp_write_file(nmfile, "method", "",
+ "auto");
+ if (error < 0)
+ goto setval_error;
+ }
+ }
- /* we do not want ipv4 addresses in ipv6 section and vice versa */
- if (is_ipv6 != is_ipv4((char *)new_val->gate_way)) {
- error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way);
+ error = process_dns_gateway_nm(nmfile,
+ (char *)new_val->gate_way,
+ GATEWAY, ip_ver);
if (error < 0)
goto setval_error;
- }
- if (is_ipv6 != is_ipv4((char *)new_val->dns_addr)) {
- error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr);
+ error = process_dns_gateway_nm(nmfile,
+ (char *)new_val->dns_addr, DNS,
+ ip_ver);
if (error < 0)
goto setval_error;
- }
+
+ ip_ver++;
+ } while (ip_ver < IP_TYPE_MAX);
+
fclose(nmfile);
fclose(ifcfg_file);
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
index 03f721a8a2b1..54ccccf96e21 100644
--- a/tools/include/asm-generic/bitops/__fls.h
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -5,12 +5,12 @@
#include <asm/types.h>
/**
- * __fls - find last (most-significant) set bit in a long word
+ * generic___fls - find last (most-significant) set bit in a long word
* @word: the word to search
*
* Undefined if no set bit exists, so code should check against 0 first.
*/
-static __always_inline unsigned long __fls(unsigned long word)
+static __always_inline unsigned long generic___fls(unsigned long word)
{
int num = BITS_PER_LONG - 1;
@@ -41,4 +41,8 @@ static __always_inline unsigned long __fls(unsigned long word)
return num;
}
+#ifndef __HAVE_ARCH___FLS
+#define __fls(word) generic___fls(word)
+#endif
+
#endif /* _ASM_GENERIC_BITOPS___FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
index b168bb10e1be..26f3ce1dd6e4 100644
--- a/tools/include/asm-generic/bitops/fls.h
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -3,14 +3,14 @@
#define _ASM_GENERIC_BITOPS_FLS_H_
/**
- * fls - find last (most-significant) bit set
+ * generic_fls - find last (most-significant) bit set
* @x: the word to search
*
* This is defined the same way as ffs.
* Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
*/
-static __always_inline int fls(unsigned int x)
+static __always_inline int generic_fls(unsigned int x)
{
int r = 32;
@@ -39,4 +39,8 @@ static __always_inline int fls(unsigned int x)
return r;
}
+#ifndef __HAVE_ARCH_FLS
+#define fls(x) generic_fls(x)
+#endif
+
#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 4b0673bf52c2..07cfad817d53 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -8,6 +8,7 @@
#include <linux/build_bug.h>
#include <linux/compiler.h>
#include <linux/math.h>
+#include <linux/panic.h>
#include <endian.h>
#include <byteswap.h>
diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h
index f3c82ab5b14c..7d73da098047 100644
--- a/tools/include/linux/mm.h
+++ b/tools/include/linux/mm.h
@@ -37,4 +37,9 @@ static inline void totalram_pages_add(long count)
{
}
+static inline int early_pfn_to_nid(unsigned long pfn)
+{
+ return 0;
+}
+
#endif
diff --git a/tools/include/linux/panic.h b/tools/include/linux/panic.h
new file mode 100644
index 000000000000..9c8f17a41ce8
--- /dev/null
+++ b/tools/include/linux/panic.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_PANIC_H
+#define _TOOLS_LINUX_PANIC_H
+
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+static inline void panic(const char *fmt, ...)
+{
+ va_list argp;
+
+ va_start(argp, fmt);
+ vfprintf(stderr, fmt, argp);
+ va_end(argp);
+ exit(-1);
+}
+
+#endif
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index fd4f9574d177..2ee338860b7e 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -3013,6 +3013,7 @@ struct drm_i915_query_item {
* - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions)
* - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`)
* - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info)
+ * - %DRM_I915_QUERY_GUC_SUBMISSION_VERSION (see struct drm_i915_query_guc_submission_version)
*/
__u64 query_id;
#define DRM_I915_QUERY_TOPOLOGY_INFO 1
@@ -3021,6 +3022,7 @@ struct drm_i915_query_item {
#define DRM_I915_QUERY_MEMORY_REGIONS 4
#define DRM_I915_QUERY_HWCONFIG_BLOB 5
#define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6
+#define DRM_I915_QUERY_GUC_SUBMISSION_VERSION 7
/* Must be kept compact -- no holes and well documented */
/**
@@ -3567,6 +3569,20 @@ struct drm_i915_query_memory_regions {
};
/**
+ * struct drm_i915_query_guc_submission_version - query GuC submission interface version
+ */
+struct drm_i915_query_guc_submission_version {
+ /** @branch: Firmware branch version. */
+ __u32 branch;
+ /** @major: Firmware major version. */
+ __u32 major;
+ /** @minor: Firmware minor version. */
+ __u32 minor;
+ /** @patch: Firmware patch version. */
+ __u32 patch;
+};
+
+/**
* DOC: GuC HWCONFIG blob uAPI
*
* The GuC produces a blob with information about the current device.
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index 48ad69f7722e..45e4e64fd664 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -64,6 +64,24 @@ struct fstrim_range {
__u64 minlen;
};
+/*
+ * We include a length field because some filesystems (vfat) have an identifier
+ * that we do want to expose as a UUID, but doesn't have the standard length.
+ *
+ * We use a fixed size buffer beacuse this interface will, by fiat, never
+ * support "UUIDs" longer than 16 bytes; we don't want to force all downstream
+ * users to have to deal with that.
+ */
+struct fsuuid2 {
+ __u8 len;
+ __u8 uuid[16];
+};
+
+struct fs_sysfs_path {
+ __u8 len;
+ __u8 name[128];
+};
+
/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
#define FILE_DEDUPE_RANGE_SAME 0
#define FILE_DEDUPE_RANGE_DIFFERS 1
@@ -215,6 +233,13 @@ struct fsxattr {
#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr)
#define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX])
#define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX])
+/* Returns the external filesystem UUID, the same one blkid returns */
+#define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2)
+/*
+ * Returns the path component under /sys/fs/ that refers to this filesystem;
+ * also /sys/kernel/debug/ for filesystems with debugfs exports
+ */
+#define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path)
/*
* Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
@@ -301,9 +326,12 @@ typedef int __bitwise __kernel_rwf_t;
/* per-IO O_APPEND */
#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010)
+/* per-IO negation of O_APPEND */
+#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020)
+
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
- RWF_APPEND)
+ RWF_APPEND | RWF_NOAPPEND)
/* Pagemap ioctl */
#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index c3308536482b..2190adbe3002 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -16,6 +16,11 @@
#define KVM_API_VERSION 12
+/*
+ * Backwards-compatible definitions.
+ */
+#define __KVM_HAVE_GUEST_DEBUG
+
/* for KVM_SET_USER_MEMORY_REGION */
struct kvm_userspace_memory_region {
__u32 slot;
@@ -85,43 +90,6 @@ struct kvm_pit_config {
#define KVM_PIT_SPEAKER_DUMMY 1
-struct kvm_s390_skeys {
- __u64 start_gfn;
- __u64 count;
- __u64 skeydata_addr;
- __u32 flags;
- __u32 reserved[9];
-};
-
-#define KVM_S390_CMMA_PEEK (1 << 0)
-
-/**
- * kvm_s390_cmma_log - Used for CMMA migration.
- *
- * Used both for input and output.
- *
- * @start_gfn: Guest page number to start from.
- * @count: Size of the result buffer.
- * @flags: Control operation mode via KVM_S390_CMMA_* flags
- * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
- * pages are still remaining.
- * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
- * in the PGSTE.
- * @values: Pointer to the values buffer.
- *
- * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
- */
-struct kvm_s390_cmma_log {
- __u64 start_gfn;
- __u32 count;
- __u32 flags;
- union {
- __u64 remaining;
- __u64 mask;
- };
- __u64 values;
-};
-
struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
@@ -315,11 +283,6 @@ struct kvm_run {
__u32 ipb;
} s390_sieic;
/* KVM_EXIT_S390_RESET */
-#define KVM_S390_RESET_POR 1
-#define KVM_S390_RESET_CLEAR 2
-#define KVM_S390_RESET_SUBSYSTEM 4
-#define KVM_S390_RESET_CPU_INIT 8
-#define KVM_S390_RESET_IPL 16
__u64 s390_reset_flags;
/* KVM_EXIT_S390_UCONTROL */
struct {
@@ -536,43 +499,6 @@ struct kvm_translation {
__u8 pad[5];
};
-/* for KVM_S390_MEM_OP */
-struct kvm_s390_mem_op {
- /* in */
- __u64 gaddr; /* the guest address */
- __u64 flags; /* flags */
- __u32 size; /* amount of bytes */
- __u32 op; /* type of operation */
- __u64 buf; /* buffer in userspace */
- union {
- struct {
- __u8 ar; /* the access register number */
- __u8 key; /* access key, ignored if flag unset */
- __u8 pad1[6]; /* ignored */
- __u64 old_addr; /* ignored if cmpxchg flag unset */
- };
- __u32 sida_offset; /* offset into the sida */
- __u8 reserved[32]; /* ignored */
- };
-};
-/* types for kvm_s390_mem_op->op */
-#define KVM_S390_MEMOP_LOGICAL_READ 0
-#define KVM_S390_MEMOP_LOGICAL_WRITE 1
-#define KVM_S390_MEMOP_SIDA_READ 2
-#define KVM_S390_MEMOP_SIDA_WRITE 3
-#define KVM_S390_MEMOP_ABSOLUTE_READ 4
-#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5
-#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6
-
-/* flags for kvm_s390_mem_op->flags */
-#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
-#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
-#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2)
-
-/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */
-#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0)
-#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1)
-
/* for KVM_INTERRUPT */
struct kvm_interrupt {
/* in */
@@ -637,124 +563,6 @@ struct kvm_mp_state {
__u32 mp_state;
};
-struct kvm_s390_psw {
- __u64 mask;
- __u64 addr;
-};
-
-/* valid values for type in kvm_s390_interrupt */
-#define KVM_S390_SIGP_STOP 0xfffe0000u
-#define KVM_S390_PROGRAM_INT 0xfffe0001u
-#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u
-#define KVM_S390_RESTART 0xfffe0003u
-#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u
-#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u
-#define KVM_S390_MCHK 0xfffe1000u
-#define KVM_S390_INT_CLOCK_COMP 0xffff1004u
-#define KVM_S390_INT_CPU_TIMER 0xffff1005u
-#define KVM_S390_INT_VIRTIO 0xffff2603u
-#define KVM_S390_INT_SERVICE 0xffff2401u
-#define KVM_S390_INT_EMERGENCY 0xffff1201u
-#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u
-/* Anything below 0xfffe0000u is taken by INT_IO */
-#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \
- (((schid)) | \
- ((ssid) << 16) | \
- ((cssid) << 18) | \
- ((ai) << 26))
-#define KVM_S390_INT_IO_MIN 0x00000000u
-#define KVM_S390_INT_IO_MAX 0xfffdffffu
-#define KVM_S390_INT_IO_AI_MASK 0x04000000u
-
-
-struct kvm_s390_interrupt {
- __u32 type;
- __u32 parm;
- __u64 parm64;
-};
-
-struct kvm_s390_io_info {
- __u16 subchannel_id;
- __u16 subchannel_nr;
- __u32 io_int_parm;
- __u32 io_int_word;
-};
-
-struct kvm_s390_ext_info {
- __u32 ext_params;
- __u32 pad;
- __u64 ext_params2;
-};
-
-struct kvm_s390_pgm_info {
- __u64 trans_exc_code;
- __u64 mon_code;
- __u64 per_address;
- __u32 data_exc_code;
- __u16 code;
- __u16 mon_class_nr;
- __u8 per_code;
- __u8 per_atmid;
- __u8 exc_access_id;
- __u8 per_access_id;
- __u8 op_access_id;
-#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01
-#define KVM_S390_PGM_FLAGS_ILC_0 0x02
-#define KVM_S390_PGM_FLAGS_ILC_1 0x04
-#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06
-#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08
- __u8 flags;
- __u8 pad[2];
-};
-
-struct kvm_s390_prefix_info {
- __u32 address;
-};
-
-struct kvm_s390_extcall_info {
- __u16 code;
-};
-
-struct kvm_s390_emerg_info {
- __u16 code;
-};
-
-#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01
-struct kvm_s390_stop_info {
- __u32 flags;
-};
-
-struct kvm_s390_mchk_info {
- __u64 cr14;
- __u64 mcic;
- __u64 failing_storage_address;
- __u32 ext_damage_code;
- __u32 pad;
- __u8 fixed_logout[16];
-};
-
-struct kvm_s390_irq {
- __u64 type;
- union {
- struct kvm_s390_io_info io;
- struct kvm_s390_ext_info ext;
- struct kvm_s390_pgm_info pgm;
- struct kvm_s390_emerg_info emerg;
- struct kvm_s390_extcall_info extcall;
- struct kvm_s390_prefix_info prefix;
- struct kvm_s390_stop_info stop;
- struct kvm_s390_mchk_info mchk;
- char reserved[64];
- } u;
-};
-
-struct kvm_s390_irq_state {
- __u64 buf;
- __u32 flags; /* will stay unused for compatibility reasons */
- __u32 len;
- __u32 reserved[4]; /* will stay unused for compatibility reasons */
-};
-
/* for KVM_SET_GUEST_DEBUG */
#define KVM_GUESTDBG_ENABLE 0x00000001
@@ -810,50 +618,6 @@ struct kvm_enable_cap {
__u8 pad[64];
};
-/* for KVM_PPC_GET_PVINFO */
-
-#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
-
-struct kvm_ppc_pvinfo {
- /* out */
- __u32 flags;
- __u32 hcall[4];
- __u8 pad[108];
-};
-
-/* for KVM_PPC_GET_SMMU_INFO */
-#define KVM_PPC_PAGE_SIZES_MAX_SZ 8
-
-struct kvm_ppc_one_page_size {
- __u32 page_shift; /* Page shift (or 0) */
- __u32 pte_enc; /* Encoding in the HPTE (>>12) */
-};
-
-struct kvm_ppc_one_seg_page_size {
- __u32 page_shift; /* Base page shift of segment (or 0) */
- __u32 slb_enc; /* SLB encoding for BookS */
- struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
-};
-
-#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
-#define KVM_PPC_1T_SEGMENTS 0x00000002
-#define KVM_PPC_NO_HASH 0x00000004
-
-struct kvm_ppc_smmu_info {
- __u64 flags;
- __u32 slb_size;
- __u16 data_keys; /* # storage keys supported for data */
- __u16 instr_keys; /* # storage keys supported for instructions */
- struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
-};
-
-/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
-struct kvm_ppc_resize_hpt {
- __u64 flags;
- __u32 shift;
- __u32 pad;
-};
-
#define KVMIO 0xAE
/* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -923,9 +687,7 @@ struct kvm_ppc_resize_hpt {
/* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
#define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
#define KVM_CAP_USER_NMI 22
-#ifdef __KVM_HAVE_GUEST_DEBUG
#define KVM_CAP_SET_GUEST_DEBUG 23
-#endif
#ifdef __KVM_HAVE_PIT
#define KVM_CAP_REINJECT_CONTROL 24
#endif
@@ -1156,8 +918,6 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_GUEST_MEMFD 234
#define KVM_CAP_VM_TYPES 235
-#ifdef KVM_CAP_IRQ_ROUTING
-
struct kvm_irq_routing_irqchip {
__u32 irqchip;
__u32 pin;
@@ -1222,42 +982,6 @@ struct kvm_irq_routing {
struct kvm_irq_routing_entry entries[];
};
-#endif
-
-#ifdef KVM_CAP_MCE
-/* x86 MCE */
-struct kvm_x86_mce {
- __u64 status;
- __u64 addr;
- __u64 misc;
- __u64 mcg_status;
- __u8 bank;
- __u8 pad1[7];
- __u64 pad2[3];
-};
-#endif
-
-#ifdef KVM_CAP_XEN_HVM
-#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
-#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
-#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
-#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
-#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
-#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5)
-#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6)
-#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7)
-
-struct kvm_xen_hvm_config {
- __u32 flags;
- __u32 msr;
- __u64 blob_addr_32;
- __u64 blob_addr_64;
- __u8 blob_size_32;
- __u8 blob_size_64;
- __u8 pad2[30];
-};
-#endif
-
#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
/*
* Available with KVM_CAP_IRQFD_RESAMPLE
@@ -1442,11 +1166,6 @@ struct kvm_vfio_spapr_tce {
struct kvm_userspace_memory_region2)
/* enable ucontrol for s390 */
-struct kvm_s390_ucas_mapping {
- __u64 user_addr;
- __u64 vcpu_addr;
- __u64 length;
-};
#define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
#define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
#define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long)
@@ -1641,89 +1360,6 @@ struct kvm_enc_region {
#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3)
#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4)
-struct kvm_s390_pv_sec_parm {
- __u64 origin;
- __u64 length;
-};
-
-struct kvm_s390_pv_unp {
- __u64 addr;
- __u64 size;
- __u64 tweak;
-};
-
-enum pv_cmd_dmp_id {
- KVM_PV_DUMP_INIT,
- KVM_PV_DUMP_CONFIG_STOR_STATE,
- KVM_PV_DUMP_COMPLETE,
- KVM_PV_DUMP_CPU,
-};
-
-struct kvm_s390_pv_dmp {
- __u64 subcmd;
- __u64 buff_addr;
- __u64 buff_len;
- __u64 gaddr; /* For dump storage state */
- __u64 reserved[4];
-};
-
-enum pv_cmd_info_id {
- KVM_PV_INFO_VM,
- KVM_PV_INFO_DUMP,
-};
-
-struct kvm_s390_pv_info_dump {
- __u64 dump_cpu_buffer_len;
- __u64 dump_config_mem_buffer_per_1m;
- __u64 dump_config_finalize_len;
-};
-
-struct kvm_s390_pv_info_vm {
- __u64 inst_calls_list[4];
- __u64 max_cpus;
- __u64 max_guests;
- __u64 max_guest_addr;
- __u64 feature_indication;
-};
-
-struct kvm_s390_pv_info_header {
- __u32 id;
- __u32 len_max;
- __u32 len_written;
- __u32 reserved;
-};
-
-struct kvm_s390_pv_info {
- struct kvm_s390_pv_info_header header;
- union {
- struct kvm_s390_pv_info_dump dump;
- struct kvm_s390_pv_info_vm vm;
- };
-};
-
-enum pv_cmd_id {
- KVM_PV_ENABLE,
- KVM_PV_DISABLE,
- KVM_PV_SET_SEC_PARMS,
- KVM_PV_UNPACK,
- KVM_PV_VERIFY,
- KVM_PV_PREP_RESET,
- KVM_PV_UNSHARE_ALL,
- KVM_PV_INFO,
- KVM_PV_DUMP,
- KVM_PV_ASYNC_CLEANUP_PREPARE,
- KVM_PV_ASYNC_CLEANUP_PERFORM,
-};
-
-struct kvm_pv_cmd {
- __u32 cmd; /* Command to be executed */
- __u16 rc; /* Ultravisor return code */
- __u16 rrc; /* Ultravisor return reason code */
- __u64 data; /* Data or address */
- __u32 flags; /* flags for future extensions. Must be 0 for now */
- __u32 reserved[3];
-};
-
/* Available with KVM_CAP_S390_PROTECTED */
#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
@@ -1737,58 +1373,6 @@ struct kvm_pv_cmd {
#define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr)
#define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr)
-struct kvm_xen_hvm_attr {
- __u16 type;
- __u16 pad[3];
- union {
- __u8 long_mode;
- __u8 vector;
- __u8 runstate_update_flag;
- struct {
- __u64 gfn;
-#define KVM_XEN_INVALID_GFN ((__u64)-1)
- } shared_info;
- struct {
- __u32 send_port;
- __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
- __u32 flags;
-#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0)
-#define KVM_XEN_EVTCHN_UPDATE (1 << 1)
-#define KVM_XEN_EVTCHN_RESET (1 << 2)
- /*
- * Events sent by the guest are either looped back to
- * the guest itself (potentially on a different port#)
- * or signalled via an eventfd.
- */
- union {
- struct {
- __u32 port;
- __u32 vcpu;
- __u32 priority;
- } port;
- struct {
- __u32 port; /* Zero for eventfd */
- __s32 fd;
- } eventfd;
- __u32 padding[4];
- } deliver;
- } evtchn;
- __u32 xen_version;
- __u64 pad[8];
- } u;
-};
-
-
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
-#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
-#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
-#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
-#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3
-#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
-#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5
-
/* Per-vCPU Xen attributes */
#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
#define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr)
@@ -1799,242 +1383,6 @@ struct kvm_xen_hvm_attr {
#define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2)
#define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2)
-struct kvm_xen_vcpu_attr {
- __u16 type;
- __u16 pad[3];
- union {
- __u64 gpa;
-#define KVM_XEN_INVALID_GPA ((__u64)-1)
- __u64 pad[8];
- struct {
- __u64 state;
- __u64 state_entry_time;
- __u64 time_running;
- __u64 time_runnable;
- __u64 time_blocked;
- __u64 time_offline;
- } runstate;
- __u32 vcpu_id;
- struct {
- __u32 port;
- __u32 priority;
- __u64 expires_ns;
- } timer;
- __u8 vector;
- } u;
-};
-
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
-#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0
-#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1
-#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2
-#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3
-#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4
-#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
-#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6
-#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7
-#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8
-
-/* Secure Encrypted Virtualization command */
-enum sev_cmd_id {
- /* Guest initialization commands */
- KVM_SEV_INIT = 0,
- KVM_SEV_ES_INIT,
- /* Guest launch commands */
- KVM_SEV_LAUNCH_START,
- KVM_SEV_LAUNCH_UPDATE_DATA,
- KVM_SEV_LAUNCH_UPDATE_VMSA,
- KVM_SEV_LAUNCH_SECRET,
- KVM_SEV_LAUNCH_MEASURE,
- KVM_SEV_LAUNCH_FINISH,
- /* Guest migration commands (outgoing) */
- KVM_SEV_SEND_START,
- KVM_SEV_SEND_UPDATE_DATA,
- KVM_SEV_SEND_UPDATE_VMSA,
- KVM_SEV_SEND_FINISH,
- /* Guest migration commands (incoming) */
- KVM_SEV_RECEIVE_START,
- KVM_SEV_RECEIVE_UPDATE_DATA,
- KVM_SEV_RECEIVE_UPDATE_VMSA,
- KVM_SEV_RECEIVE_FINISH,
- /* Guest status and debug commands */
- KVM_SEV_GUEST_STATUS,
- KVM_SEV_DBG_DECRYPT,
- KVM_SEV_DBG_ENCRYPT,
- /* Guest certificates commands */
- KVM_SEV_CERT_EXPORT,
- /* Attestation report */
- KVM_SEV_GET_ATTESTATION_REPORT,
- /* Guest Migration Extension */
- KVM_SEV_SEND_CANCEL,
-
- KVM_SEV_NR_MAX,
-};
-
-struct kvm_sev_cmd {
- __u32 id;
- __u64 data;
- __u32 error;
- __u32 sev_fd;
-};
-
-struct kvm_sev_launch_start {
- __u32 handle;
- __u32 policy;
- __u64 dh_uaddr;
- __u32 dh_len;
- __u64 session_uaddr;
- __u32 session_len;
-};
-
-struct kvm_sev_launch_update_data {
- __u64 uaddr;
- __u32 len;
-};
-
-
-struct kvm_sev_launch_secret {
- __u64 hdr_uaddr;
- __u32 hdr_len;
- __u64 guest_uaddr;
- __u32 guest_len;
- __u64 trans_uaddr;
- __u32 trans_len;
-};
-
-struct kvm_sev_launch_measure {
- __u64 uaddr;
- __u32 len;
-};
-
-struct kvm_sev_guest_status {
- __u32 handle;
- __u32 policy;
- __u32 state;
-};
-
-struct kvm_sev_dbg {
- __u64 src_uaddr;
- __u64 dst_uaddr;
- __u32 len;
-};
-
-struct kvm_sev_attestation_report {
- __u8 mnonce[16];
- __u64 uaddr;
- __u32 len;
-};
-
-struct kvm_sev_send_start {
- __u32 policy;
- __u64 pdh_cert_uaddr;
- __u32 pdh_cert_len;
- __u64 plat_certs_uaddr;
- __u32 plat_certs_len;
- __u64 amd_certs_uaddr;
- __u32 amd_certs_len;
- __u64 session_uaddr;
- __u32 session_len;
-};
-
-struct kvm_sev_send_update_data {
- __u64 hdr_uaddr;
- __u32 hdr_len;
- __u64 guest_uaddr;
- __u32 guest_len;
- __u64 trans_uaddr;
- __u32 trans_len;
-};
-
-struct kvm_sev_receive_start {
- __u32 handle;
- __u32 policy;
- __u64 pdh_uaddr;
- __u32 pdh_len;
- __u64 session_uaddr;
- __u32 session_len;
-};
-
-struct kvm_sev_receive_update_data {
- __u64 hdr_uaddr;
- __u32 hdr_len;
- __u64 guest_uaddr;
- __u32 guest_len;
- __u64 trans_uaddr;
- __u32 trans_len;
-};
-
-#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
-#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)
-#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2)
-
-struct kvm_assigned_pci_dev {
- __u32 assigned_dev_id;
- __u32 busnr;
- __u32 devfn;
- __u32 flags;
- __u32 segnr;
- union {
- __u32 reserved[11];
- };
-};
-
-#define KVM_DEV_IRQ_HOST_INTX (1 << 0)
-#define KVM_DEV_IRQ_HOST_MSI (1 << 1)
-#define KVM_DEV_IRQ_HOST_MSIX (1 << 2)
-
-#define KVM_DEV_IRQ_GUEST_INTX (1 << 8)
-#define KVM_DEV_IRQ_GUEST_MSI (1 << 9)
-#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10)
-
-#define KVM_DEV_IRQ_HOST_MASK 0x00ff
-#define KVM_DEV_IRQ_GUEST_MASK 0xff00
-
-struct kvm_assigned_irq {
- __u32 assigned_dev_id;
- __u32 host_irq; /* ignored (legacy field) */
- __u32 guest_irq;
- __u32 flags;
- union {
- __u32 reserved[12];
- };
-};
-
-struct kvm_assigned_msix_nr {
- __u32 assigned_dev_id;
- __u16 entry_nr;
- __u16 padding;
-};
-
-#define KVM_MAX_MSIX_PER_DEV 256
-struct kvm_assigned_msix_entry {
- __u32 assigned_dev_id;
- __u32 gsi;
- __u16 entry; /* The index of entry in the MSI-X table */
- __u16 padding[3];
-};
-
-#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
-#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
-
-/* Available with KVM_CAP_ARM_USER_IRQ */
-
-/* Bits for run->s.regs.device_irq_level */
-#define KVM_ARM_DEV_EL1_VTIMER (1 << 0)
-#define KVM_ARM_DEV_EL1_PTIMER (1 << 1)
-#define KVM_ARM_DEV_PMU (1 << 2)
-
-struct kvm_hyperv_eventfd {
- __u32 conn_id;
- __s32 fd;
- __u32 flags;
- __u32 padding[3];
-};
-
-#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
-#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
-
#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
@@ -2180,33 +1528,6 @@ struct kvm_stats_desc {
/* Available with KVM_CAP_S390_ZPCI_OP */
#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op)
-struct kvm_s390_zpci_op {
- /* in */
- __u32 fh; /* target device */
- __u8 op; /* operation to perform */
- __u8 pad[3];
- union {
- /* for KVM_S390_ZPCIOP_REG_AEN */
- struct {
- __u64 ibv; /* Guest addr of interrupt bit vector */
- __u64 sb; /* Guest addr of summary bit */
- __u32 flags;
- __u32 noi; /* Number of interrupts */
- __u8 isc; /* Guest interrupt subclass */
- __u8 sbo; /* Offset of guest summary bit vector */
- __u16 pad;
- } reg_aen;
- __u64 reserved[8];
- } u;
-};
-
-/* types for kvm_s390_zpci_op->op */
-#define KVM_S390_ZPCIOP_REG_AEN 0
-#define KVM_S390_ZPCIOP_DEREG_AEN 1
-
-/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
-#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0)
-
/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
#define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes)
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index d5b9cfbd9cea..628d46a0da92 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image {
* *
*****************************************************************************/
-#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 16)
+#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17)
typedef unsigned long snd_pcm_uframes_t;
typedef signed long snd_pcm_sframes_t;
@@ -416,7 +416,7 @@ struct snd_pcm_hw_params {
unsigned int rmask; /* W: requested masks */
unsigned int cmask; /* R: changed masks */
unsigned int info; /* R: Info flags for returned setup */
- unsigned int msbits; /* R: used most significant bits */
+ unsigned int msbits; /* R: used most significant bits (in sample bit-width) */
unsigned int rate_num; /* R: rate numerator */
unsigned int rate_den; /* R: rate denominator */
snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 5fa7957f6e0f..25810e18b0a7 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -182,6 +182,7 @@ class NlMsg:
self.done = 1
extack_off = 20
elif self.nl_type == Netlink.NLMSG_DONE:
+ self.error = struct.unpack("i", self.raw[0:4])[0]
self.done = 1
extack_off = 4
diff --git a/tools/perf/arch/riscv/util/header.c b/tools/perf/arch/riscv/util/header.c
index 4a41856938a8..1b29030021ee 100644
--- a/tools/perf/arch/riscv/util/header.c
+++ b/tools/perf/arch/riscv/util/header.c
@@ -41,7 +41,7 @@ static char *_get_cpuid(void)
char *mimpid = NULL;
char *cpuid = NULL;
int read;
- unsigned long line_sz;
+ size_t line_sz;
FILE *cpuinfo;
cpuinfo = fopen(CPUINFO, "r");
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ec5e21932876..4790c735599b 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -970,7 +970,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
if (dso->annotate_warned)
return -1;
- if (not_annotated) {
+ if (not_annotated || !sym->annotate2) {
err = symbol__annotate2(ms, evsel, &browser.arch);
if (err) {
char msg[BUFSIZ];
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ac002d907d81..50ca92255ff6 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2461,6 +2461,9 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
if (parch)
*parch = arch;
+ if (!list_empty(&notes->src->source))
+ return 0;
+
args.arch = arch;
args.ms = *ms;
if (annotate_opts.full_addr)
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index fb54bd38e7d0..d931a898c434 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -284,6 +284,7 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags)
struct task_struct *curr;
struct mm_struct___old *mm_old;
struct mm_struct___new *mm_new;
+ struct sighand_struct *sighand;
switch (flags) {
case LCB_F_READ: /* rwsem */
@@ -305,7 +306,9 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags)
break;
case LCB_F_SPIN: /* spinlock */
curr = bpf_get_current_task_btf();
- if (&curr->sighand->siglock == (void *)lock)
+ sighand = curr->sighand;
+
+ if (sighand && &sighand->siglock == (void *)lock)
return LCD_F_SIGHAND_LOCK;
break;
default:
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 8f08c3fd498d..0d3672e5d9ed 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -67,6 +67,10 @@ The column name "all" can be used to enable all disabled-by-default built-in cou
.PP
\fB--quiet\fP Do not decode and print the system configuration header information.
.PP
++\fB--no-msr\fP Disable all the uses of the MSR driver.
++.PP
++\fB--no-perf\fP Disable all the uses of the perf API.
++.PP
\fB--interval seconds\fP overrides the default 5.0 second measurement interval.
.PP
\fB--num_iterations num\fP number of the measurement iterations.
@@ -125,9 +129,17 @@ The system configuration dump (if --quiet is not used) is followed by statistics
.PP
\fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
.PP
-\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
+\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms or /sys/class/drm/card0/gt/gt0/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used.
.PP
-\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
+\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used.
+.PP
+\fBGFXAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used.
+.PP
+\fBSAM%mc6\fP The percentage of time the SA Media is in the "module C6" state, mc6, during the measurement interval. From /sys/class/drm/card0/gt/gt1/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used.
+.PP
+\fBSAMMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used.
+.PP
+\fBSAMAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used.
.PP
\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters.
.PP
@@ -370,7 +382,7 @@ below the processor's base frequency.
Busy% = MPERF_delta/TSC_delta
-Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval
+Bzy_MHz = TSC_delta*APERF_delta/MPERF_delta/measurement_interval
Note that these calculations depend on TSC_delta, so they
are not reliable during intervals when TSC_MHz is not running at the base frequency.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 7a334377f92b..98256468e248 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3,7 +3,7 @@
* turbostat -- show CPU frequency and C-state residency
* on modern Intel and AMD processors.
*
- * Copyright (c) 2023 Intel Corporation.
+ * Copyright (c) 2024 Intel Corporation.
* Len Brown <len.brown@intel.com>
*/
@@ -36,6 +36,8 @@
#include <linux/perf_event.h>
#include <asm/unistd.h>
#include <stdbool.h>
+#include <assert.h>
+#include <linux/kernel.h>
#define UNUSED(x) (void)(x)
@@ -53,9 +55,13 @@
#define NAME_BYTES 20
#define PATH_BYTES 128
+#define MAX_NOFILE 0x8000
+
enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE };
enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC };
enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT };
+enum amperf_source { AMPERF_SOURCE_PERF, AMPERF_SOURCE_MSR };
+enum rapl_source { RAPL_SOURCE_NONE, RAPL_SOURCE_PERF, RAPL_SOURCE_MSR };
struct msr_counter {
unsigned int msr_num;
@@ -127,6 +133,9 @@ struct msr_counter bic[] = {
{ 0x0, "IPC", "", 0, 0, 0, NULL, 0 },
{ 0x0, "CoreThr", "", 0, 0, 0, NULL, 0 },
{ 0x0, "UncMHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SAM%mc6", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SAMMHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SAMAMHz", "", 0, 0, 0, NULL, 0 },
};
#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -185,11 +194,14 @@ struct msr_counter bic[] = {
#define BIC_IPC (1ULL << 52)
#define BIC_CORE_THROT_CNT (1ULL << 53)
#define BIC_UNCORE_MHZ (1ULL << 54)
+#define BIC_SAM_mc6 (1ULL << 55)
+#define BIC_SAMMHz (1ULL << 56)
+#define BIC_SAMACTMHz (1ULL << 57)
#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die )
#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__)
-#define BIC_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_UNCORE_MHZ)
-#define BIC_IDLE ( BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX)
+#define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ)
+#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6)
#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
@@ -204,10 +216,13 @@ unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC
#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
#define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT)
+struct amperf_group_fd;
+
char *proc_stat = "/proc/stat";
FILE *outf;
int *fd_percpu;
int *fd_instr_count_percpu;
+struct amperf_group_fd *fd_amperf_percpu; /* File descriptors for perf group with APERF and MPERF counters. */
struct timeval interval_tv = { 5, 0 };
struct timespec interval_ts = { 5, 0 };
@@ -242,11 +257,8 @@ char *output_buffer, *outp;
unsigned int do_dts;
unsigned int do_ptm;
unsigned int do_ipc;
-unsigned long long gfx_cur_rc6_ms;
unsigned long long cpuidle_cur_cpu_lpi_us;
unsigned long long cpuidle_cur_sys_lpi_us;
-unsigned int gfx_cur_mhz;
-unsigned int gfx_act_mhz;
unsigned int tj_max;
unsigned int tj_max_override;
double rapl_power_units, rapl_time_units;
@@ -263,6 +275,28 @@ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */
unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */
unsigned int first_counter_read = 1;
int ignore_stdin;
+bool no_msr;
+bool no_perf;
+enum amperf_source amperf_source;
+
+enum gfx_sysfs_idx {
+ GFX_rc6,
+ GFX_MHz,
+ GFX_ACTMHz,
+ SAM_mc6,
+ SAM_MHz,
+ SAM_ACTMHz,
+ GFX_MAX
+};
+
+struct gfx_sysfs_info {
+ const char *path;
+ FILE *fp;
+ unsigned int val;
+ unsigned long long val_ull;
+};
+
+static struct gfx_sysfs_info gfx_info[GFX_MAX];
int get_msr(int cpu, off_t offset, unsigned long long *msr);
@@ -652,6 +686,7 @@ static const struct platform_features icx_features = {
.bclk_freq = BCLK_100MHZ,
.supported_cstates = CC1 | CC6 | PC2 | PC6,
.cst_limit = CST_LIMIT_ICX,
+ .has_msr_core_c1_res = 1,
.has_irtl_msrs = 1,
.has_cst_prewake_bit = 1,
.trl_msrs = TRL_BASE | TRL_CORECOUNT,
@@ -948,6 +983,175 @@ size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affi
#define MAX_ADDED_THREAD_COUNTERS 24
#define BITMASK_SIZE 32
+/* Indexes used to map data read from perf and MSRs into global variables */
+enum rapl_rci_index {
+ RAPL_RCI_INDEX_ENERGY_PKG = 0,
+ RAPL_RCI_INDEX_ENERGY_CORES = 1,
+ RAPL_RCI_INDEX_DRAM = 2,
+ RAPL_RCI_INDEX_GFX = 3,
+ RAPL_RCI_INDEX_PKG_PERF_STATUS = 4,
+ RAPL_RCI_INDEX_DRAM_PERF_STATUS = 5,
+ RAPL_RCI_INDEX_CORE_ENERGY = 6,
+ NUM_RAPL_COUNTERS,
+};
+
+enum rapl_unit {
+ RAPL_UNIT_INVALID,
+ RAPL_UNIT_JOULES,
+ RAPL_UNIT_WATTS,
+};
+
+struct rapl_counter_info_t {
+ unsigned long long data[NUM_RAPL_COUNTERS];
+ enum rapl_source source[NUM_RAPL_COUNTERS];
+ unsigned long long flags[NUM_RAPL_COUNTERS];
+ double scale[NUM_RAPL_COUNTERS];
+ enum rapl_unit unit[NUM_RAPL_COUNTERS];
+
+ union {
+ /* Active when source == RAPL_SOURCE_MSR */
+ struct {
+ unsigned long long msr[NUM_RAPL_COUNTERS];
+ unsigned long long msr_mask[NUM_RAPL_COUNTERS];
+ int msr_shift[NUM_RAPL_COUNTERS];
+ };
+ };
+
+ int fd_perf;
+};
+
+/* struct rapl_counter_info_t for each RAPL domain */
+struct rapl_counter_info_t *rapl_counter_info_perdomain;
+
+#define RAPL_COUNTER_FLAG_USE_MSR_SUM (1u << 1)
+
+struct rapl_counter_arch_info {
+ int feature_mask; /* Mask for testing if the counter is supported on host */
+ const char *perf_subsys;
+ const char *perf_name;
+ unsigned long long msr;
+ unsigned long long msr_mask;
+ int msr_shift; /* Positive mean shift right, negative mean shift left */
+ double *platform_rapl_msr_scale; /* Scale applied to values read by MSR (platform dependent, filled at runtime) */
+ unsigned int rci_index; /* Maps data from perf counters to global variables */
+ unsigned long long bic;
+ double compat_scale; /* Some counters require constant scaling to be in the same range as other, similar ones */
+ unsigned long long flags;
+};
+
+static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = {
+ {
+ .feature_mask = RAPL_PKG,
+ .perf_subsys = "power",
+ .perf_name = "energy-pkg",
+ .msr = MSR_PKG_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_ENERGY_PKG,
+ .bic = BIC_PkgWatt | BIC_Pkg_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_AMD_F17H,
+ .perf_subsys = "power",
+ .perf_name = "energy-pkg",
+ .msr = MSR_PKG_ENERGY_STAT,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_ENERGY_PKG,
+ .bic = BIC_PkgWatt | BIC_Pkg_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_CORE_ENERGY_STATUS,
+ .perf_subsys = "power",
+ .perf_name = "energy-cores",
+ .msr = MSR_PP0_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_ENERGY_CORES,
+ .bic = BIC_CorWatt | BIC_Cor_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_DRAM,
+ .perf_subsys = "power",
+ .perf_name = "energy-ram",
+ .msr = MSR_DRAM_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_dram_energy_units,
+ .rci_index = RAPL_RCI_INDEX_DRAM,
+ .bic = BIC_RAMWatt | BIC_RAM_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_GFX,
+ .perf_subsys = "power",
+ .perf_name = "energy-gpu",
+ .msr = MSR_PP1_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_GFX,
+ .bic = BIC_GFXWatt | BIC_GFX_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_PKG_PERF_STATUS,
+ .perf_subsys = NULL,
+ .perf_name = NULL,
+ .msr = MSR_PKG_PERF_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_time_units,
+ .rci_index = RAPL_RCI_INDEX_PKG_PERF_STATUS,
+ .bic = BIC_PKG__,
+ .compat_scale = 100.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_DRAM_PERF_STATUS,
+ .perf_subsys = NULL,
+ .perf_name = NULL,
+ .msr = MSR_DRAM_PERF_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_time_units,
+ .rci_index = RAPL_RCI_INDEX_DRAM_PERF_STATUS,
+ .bic = BIC_RAM__,
+ .compat_scale = 100.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_AMD_F17H,
+ .perf_subsys = NULL,
+ .perf_name = NULL,
+ .msr = MSR_CORE_ENERGY_STAT,
+ .msr_mask = 0xFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_CORE_ENERGY,
+ .bic = BIC_CorWatt | BIC_Cor_J,
+ .compat_scale = 1.0,
+ .flags = 0,
+ },
+};
+
+struct rapl_counter {
+ unsigned long long raw_value;
+ enum rapl_unit unit;
+ double scale;
+};
+
struct thread_data {
struct timeval tv_begin;
struct timeval tv_end;
@@ -974,7 +1178,7 @@ struct core_data {
unsigned long long c7;
unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */
unsigned int core_temp_c;
- unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */
+ struct rapl_counter core_energy; /* MSR_CORE_ENERGY_STAT */
unsigned int core_id;
unsigned long long core_throt_cnt;
unsigned long long counter[MAX_ADDED_COUNTERS];
@@ -989,8 +1193,8 @@ struct pkg_data {
unsigned long long pc8;
unsigned long long pc9;
unsigned long long pc10;
- unsigned long long cpu_lpi;
- unsigned long long sys_lpi;
+ long long cpu_lpi;
+ long long sys_lpi;
unsigned long long pkg_wtd_core_c0;
unsigned long long pkg_any_core_c0;
unsigned long long pkg_any_gfxe_c0;
@@ -998,13 +1202,16 @@ struct pkg_data {
long long gfx_rc6_ms;
unsigned int gfx_mhz;
unsigned int gfx_act_mhz;
+ long long sam_mc6_ms;
+ unsigned int sam_mhz;
+ unsigned int sam_act_mhz;
unsigned int package_id;
- unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */
- unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */
- unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */
- unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */
- unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
- unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
+ struct rapl_counter energy_pkg; /* MSR_PKG_ENERGY_STATUS */
+ struct rapl_counter energy_dram; /* MSR_DRAM_ENERGY_STATUS */
+ struct rapl_counter energy_cores; /* MSR_PP0_ENERGY_STATUS */
+ struct rapl_counter energy_gfx; /* MSR_PP1_ENERGY_STATUS */
+ struct rapl_counter rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
+ struct rapl_counter rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
unsigned int pkg_temp_c;
unsigned int uncore_mhz;
unsigned long long counter[MAX_ADDED_COUNTERS];
@@ -1150,6 +1357,38 @@ struct sys_counters {
struct msr_counter *pp;
} sys;
+void free_sys_counters(void)
+{
+ struct msr_counter *p = sys.tp, *pnext = NULL;
+
+ while (p) {
+ pnext = p->next;
+ free(p);
+ p = pnext;
+ }
+
+ p = sys.cp, pnext = NULL;
+ while (p) {
+ pnext = p->next;
+ free(p);
+ p = pnext;
+ }
+
+ p = sys.pp, pnext = NULL;
+ while (p) {
+ pnext = p->next;
+ free(p);
+ p = pnext;
+ }
+
+ sys.added_thread_counters = 0;
+ sys.added_core_counters = 0;
+ sys.added_package_counters = 0;
+ sys.tp = NULL;
+ sys.cp = NULL;
+ sys.pp = NULL;
+}
+
struct system_summary {
struct thread_data threads;
struct core_data cores;
@@ -1280,34 +1519,60 @@ int get_msr_fd(int cpu)
sprintf(pathname, "/dev/cpu/%d/msr", cpu);
fd = open(pathname, O_RDONLY);
if (fd < 0)
- err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname);
+ err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, "
+ "or run with --no-msr, or run as root", pathname);
fd_percpu[cpu] = fd;
return fd;
}
+static void bic_disable_msr_access(void)
+{
+ const unsigned long bic_msrs =
+ BIC_SMI |
+ BIC_CPU_c1 |
+ BIC_CPU_c3 |
+ BIC_CPU_c6 |
+ BIC_CPU_c7 |
+ BIC_Mod_c6 |
+ BIC_CoreTmp |
+ BIC_Totl_c0 |
+ BIC_Any_c0 |
+ BIC_GFX_c0 |
+ BIC_CPUGFX |
+ BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_PkgTmp;
+
+ bic_enabled &= ~bic_msrs;
+
+ free_sys_counters();
+}
+
static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags)
{
+ assert(!no_perf);
+
return syscall(__NR_perf_event_open, hw_event, pid, cpu, group_fd, flags);
}
-static int perf_instr_count_open(int cpu_num)
+static long open_perf_counter(int cpu, unsigned int type, unsigned int config, int group_fd, __u64 read_format)
{
- struct perf_event_attr pea;
- int fd;
+ struct perf_event_attr attr;
+ const pid_t pid = -1;
+ const unsigned long flags = 0;
- memset(&pea, 0, sizeof(struct perf_event_attr));
- pea.type = PERF_TYPE_HARDWARE;
- pea.size = sizeof(struct perf_event_attr);
- pea.config = PERF_COUNT_HW_INSTRUCTIONS;
+ assert(!no_perf);
- /* counter for cpu_num, including user + kernel and all processes */
- fd = perf_event_open(&pea, -1, cpu_num, -1, 0);
- if (fd == -1) {
- warnx("capget(CAP_PERFMON) failed, try \"# setcap cap_sys_admin=ep %s\"", progname);
- BIC_NOT_PRESENT(BIC_IPC);
- }
+ memset(&attr, 0, sizeof(struct perf_event_attr));
+
+ attr.type = type;
+ attr.size = sizeof(struct perf_event_attr);
+ attr.config = config;
+ attr.disabled = 0;
+ attr.sample_type = PERF_SAMPLE_IDENTIFIER;
+ attr.read_format = read_format;
+
+ const int fd = perf_event_open(&attr, pid, cpu, group_fd, flags);
return fd;
}
@@ -1317,7 +1582,7 @@ int get_instr_count_fd(int cpu)
if (fd_instr_count_percpu[cpu])
return fd_instr_count_percpu[cpu];
- fd_instr_count_percpu[cpu] = perf_instr_count_open(cpu);
+ fd_instr_count_percpu[cpu] = open_perf_counter(cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0);
return fd_instr_count_percpu[cpu];
}
@@ -1326,6 +1591,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
{
ssize_t retval;
+ assert(!no_msr);
+
retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset);
if (retval != sizeof *msr)
@@ -1334,6 +1601,21 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
return 0;
}
+int probe_msr(int cpu, off_t offset)
+{
+ ssize_t retval;
+ unsigned long long dummy;
+
+ assert(!no_msr);
+
+ retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset);
+
+ if (retval != sizeof(dummy))
+ return 1;
+
+ return 0;
+}
+
#define MAX_DEFERRED 16
char *deferred_add_names[MAX_DEFERRED];
char *deferred_skip_names[MAX_DEFERRED];
@@ -1369,6 +1651,8 @@ void help(void)
" Override default 5-second measurement interval\n"
" -J, --Joules displays energy in Joules instead of Watts\n"
" -l, --list list column headers only\n"
+ " -M, --no-msr Disable all uses of the MSR driver\n"
+ " -P, --no-perf Disable all uses of the perf API\n"
" -n, --num_iterations num\n"
" number of the measurement iterations\n"
" -N, --header_iterations num\n"
@@ -1573,6 +1857,15 @@ void print_header(char *delim)
if (DO_BIC(BIC_GFXACTMHz))
outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_SAM_mc6))
+ outp += sprintf(outp, "%sSAM%%mc6", (printed++ ? delim : ""));
+
+ if (DO_BIC(BIC_SAMMHz))
+ outp += sprintf(outp, "%sSAMMHz", (printed++ ? delim : ""));
+
+ if (DO_BIC(BIC_SAMACTMHz))
+ outp += sprintf(outp, "%sSAMAMHz", (printed++ ? delim : ""));
+
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : ""));
if (DO_BIC(BIC_Any_c0))
@@ -1671,26 +1964,35 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p
outp += sprintf(outp, "SMI: %d\n", t->smi_count);
for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
- outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, t->counter[i]);
+ outp +=
+ sprintf(outp, "tADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num,
+ t->counter[i], mp->path);
}
}
- if (c) {
+ if (c && is_cpu_first_thread_in_core(t, c, p)) {
outp += sprintf(outp, "core: %d\n", c->core_id);
outp += sprintf(outp, "c3: %016llX\n", c->c3);
outp += sprintf(outp, "c6: %016llX\n", c->c6);
outp += sprintf(outp, "c7: %016llX\n", c->c7);
outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
outp += sprintf(outp, "cpu_throt_count: %016llX\n", c->core_throt_cnt);
- outp += sprintf(outp, "Joules: %0X\n", c->core_energy);
+
+ const unsigned long long energy_value = c->core_energy.raw_value * c->core_energy.scale;
+ const double energy_scale = c->core_energy.scale;
+
+ if (c->core_energy.unit == RAPL_UNIT_JOULES)
+ outp += sprintf(outp, "Joules: %0llX (scale: %lf)\n", energy_value, energy_scale);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
- outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, c->counter[i]);
+ outp +=
+ sprintf(outp, "cADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num,
+ c->counter[i], mp->path);
}
outp += sprintf(outp, "mc6_us: %016llX\n", c->mc6_us);
}
- if (p) {
+ if (p && is_cpu_first_core_in_package(t, c, p)) {
outp += sprintf(outp, "package: %d\n", p->package_id);
outp += sprintf(outp, "Weighted cores: %016llX\n", p->pkg_wtd_core_c0);
@@ -1710,16 +2012,18 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p
outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
- outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg);
- outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores);
- outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx);
- outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram);
- outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status);
- outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status);
+ outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg.raw_value);
+ outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores.raw_value);
+ outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx.raw_value);
+ outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram.raw_value);
+ outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status.raw_value);
+ outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status.raw_value);
outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
- outp += sprintf(outp, "pADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, p->counter[i]);
+ outp +=
+ sprintf(outp, "pADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num,
+ p->counter[i], mp->path);
}
}
@@ -1728,6 +2032,23 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p
return 0;
}
+double rapl_counter_get_value(const struct rapl_counter *c, enum rapl_unit desired_unit, double interval)
+{
+ assert(desired_unit != RAPL_UNIT_INVALID);
+
+ /*
+ * For now we don't expect anything other than joules,
+ * so just simplify the logic.
+ */
+ assert(c->unit == RAPL_UNIT_JOULES);
+
+ const double scaled = c->raw_value * c->scale;
+
+ if (desired_unit == RAPL_UNIT_WATTS)
+ return scaled / interval;
+ return scaled;
+}
+
/*
* column formatting convention & formats
*/
@@ -1921,9 +2242,11 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl)
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&c->core_energy, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl)
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&c->core_energy, RAPL_UNIT_JOULES, interval_float));
/* print per-package data only for 1st core in package */
if (!is_cpu_first_core_in_package(t, c, p))
@@ -1951,6 +2274,24 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
if (DO_BIC(BIC_GFXACTMHz))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz);
+ /* SAMmc6 */
+ if (DO_BIC(BIC_SAM_mc6)) {
+ if (p->sam_mc6_ms == -1) { /* detect GFX counter reset */
+ outp += sprintf(outp, "%s**.**", (printed++ ? delim : ""));
+ } else {
+ outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+ p->sam_mc6_ms / 10.0 / interval_float);
+ }
+ }
+
+ /* SAMMHz */
+ if (DO_BIC(BIC_SAMMHz))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_mhz);
+
+ /* SAMACTMHz */
+ if (DO_BIC(BIC_SAMACTMHz))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_act_mhz);
+
/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0 / tsc);
@@ -1976,43 +2317,59 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
if (DO_BIC(BIC_Pkgpc10))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10 / tsc);
- if (DO_BIC(BIC_CPU_LPI))
- outp +=
- sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float);
- if (DO_BIC(BIC_SYS_LPI))
- outp +=
- sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
+ if (DO_BIC(BIC_CPU_LPI)) {
+ if (p->cpu_lpi >= 0)
+ outp +=
+ sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+ 100.0 * p->cpu_lpi / 1000000.0 / interval_float);
+ else
+ outp += sprintf(outp, "%s(neg)", (printed++ ? delim : ""));
+ }
+ if (DO_BIC(BIC_SYS_LPI)) {
+ if (p->sys_lpi >= 0)
+ outp +=
+ sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+ 100.0 * p->sys_lpi / 1000000.0 / interval_float);
+ else
+ outp += sprintf(outp, "%s(neg)", (printed++ ? delim : ""));
+ }
if (DO_BIC(BIC_PkgWatt))
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
-
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl)
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_GFXWatt))
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_RAMWatt))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""),
- p->energy_dram * rapl_dram_energy_units / interval_float);
+ rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_Pkg_J))
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl)
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_GFX_J))
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_RAM_J))
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_PKG__))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""),
- 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+ rapl_counter_get_value(&p->rapl_pkg_perf_status, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_RAM__))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""),
- 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+ rapl_counter_get_value(&p->rapl_dram_perf_status, RAPL_UNIT_WATTS, interval_float));
/* UncMHz */
if (DO_BIC(BIC_UNCORE_MHZ))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->uncore_mhz);
@@ -2121,12 +2478,22 @@ int delta_package(struct pkg_data *new, struct pkg_data *old)
old->gfx_mhz = new->gfx_mhz;
old->gfx_act_mhz = new->gfx_act_mhz;
- old->energy_pkg = new->energy_pkg - old->energy_pkg;
- old->energy_cores = new->energy_cores - old->energy_cores;
- old->energy_gfx = new->energy_gfx - old->energy_gfx;
- old->energy_dram = new->energy_dram - old->energy_dram;
- old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status;
- old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status;
+ /* flag an error when mc6 counter resets/wraps */
+ if (old->sam_mc6_ms > new->sam_mc6_ms)
+ old->sam_mc6_ms = -1;
+ else
+ old->sam_mc6_ms = new->sam_mc6_ms - old->sam_mc6_ms;
+
+ old->sam_mhz = new->sam_mhz;
+ old->sam_act_mhz = new->sam_act_mhz;
+
+ old->energy_pkg.raw_value = new->energy_pkg.raw_value - old->energy_pkg.raw_value;
+ old->energy_cores.raw_value = new->energy_cores.raw_value - old->energy_cores.raw_value;
+ old->energy_gfx.raw_value = new->energy_gfx.raw_value - old->energy_gfx.raw_value;
+ old->energy_dram.raw_value = new->energy_dram.raw_value - old->energy_dram.raw_value;
+ old->rapl_pkg_perf_status.raw_value = new->rapl_pkg_perf_status.raw_value - old->rapl_pkg_perf_status.raw_value;
+ old->rapl_dram_perf_status.raw_value =
+ new->rapl_dram_perf_status.raw_value - old->rapl_dram_perf_status.raw_value;
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -2150,7 +2517,7 @@ void delta_core(struct core_data *new, struct core_data *old)
old->core_throt_cnt = new->core_throt_cnt;
old->mc6_us = new->mc6_us - old->mc6_us;
- DELTA_WRAP32(new->core_energy, old->core_energy);
+ DELTA_WRAP32(new->core_energy.raw_value, old->core_energy.raw_value);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -2277,6 +2644,13 @@ int delta_cpu(struct thread_data *t, struct core_data *c,
return retval;
}
+void rapl_counter_clear(struct rapl_counter *c)
+{
+ c->raw_value = 0;
+ c->scale = 0.0;
+ c->unit = RAPL_UNIT_INVALID;
+}
+
void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int i;
@@ -2304,7 +2678,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
c->c7 = 0;
c->mc6_us = 0;
c->core_temp_c = 0;
- c->core_energy = 0;
+ rapl_counter_clear(&c->core_energy);
c->core_throt_cnt = 0;
p->pkg_wtd_core_c0 = 0;
@@ -2325,18 +2699,21 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
p->cpu_lpi = 0;
p->sys_lpi = 0;
- p->energy_pkg = 0;
- p->energy_dram = 0;
- p->energy_cores = 0;
- p->energy_gfx = 0;
- p->rapl_pkg_perf_status = 0;
- p->rapl_dram_perf_status = 0;
+ rapl_counter_clear(&p->energy_pkg);
+ rapl_counter_clear(&p->energy_dram);
+ rapl_counter_clear(&p->energy_cores);
+ rapl_counter_clear(&p->energy_gfx);
+ rapl_counter_clear(&p->rapl_pkg_perf_status);
+ rapl_counter_clear(&p->rapl_dram_perf_status);
p->pkg_temp_c = 0;
p->gfx_rc6_ms = 0;
p->uncore_mhz = 0;
p->gfx_mhz = 0;
p->gfx_act_mhz = 0;
+ p->sam_mc6_ms = 0;
+ p->sam_mhz = 0;
+ p->sam_act_mhz = 0;
for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
t->counter[i] = 0;
@@ -2347,6 +2724,20 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
p->counter[i] = 0;
}
+void rapl_counter_accumulate(struct rapl_counter *dst, const struct rapl_counter *src)
+{
+ /* Copy unit and scale from src if dst is not initialized */
+ if (dst->unit == RAPL_UNIT_INVALID) {
+ dst->unit = src->unit;
+ dst->scale = src->scale;
+ }
+
+ assert(dst->unit == src->unit);
+ assert(dst->scale == src->scale);
+
+ dst->raw_value += src->raw_value;
+}
+
int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int i;
@@ -2393,7 +2784,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
average.cores.core_throt_cnt = MAX(average.cores.core_throt_cnt, c->core_throt_cnt);
- average.cores.core_energy += c->core_energy;
+ rapl_counter_accumulate(&average.cores.core_energy, &c->core_energy);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -2428,25 +2819,29 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
average.packages.cpu_lpi = p->cpu_lpi;
average.packages.sys_lpi = p->sys_lpi;
- average.packages.energy_pkg += p->energy_pkg;
- average.packages.energy_dram += p->energy_dram;
- average.packages.energy_cores += p->energy_cores;
- average.packages.energy_gfx += p->energy_gfx;
+ rapl_counter_accumulate(&average.packages.energy_pkg, &p->energy_pkg);
+ rapl_counter_accumulate(&average.packages.energy_dram, &p->energy_dram);
+ rapl_counter_accumulate(&average.packages.energy_cores, &p->energy_cores);
+ rapl_counter_accumulate(&average.packages.energy_gfx, &p->energy_gfx);
average.packages.gfx_rc6_ms = p->gfx_rc6_ms;
average.packages.uncore_mhz = p->uncore_mhz;
average.packages.gfx_mhz = p->gfx_mhz;
average.packages.gfx_act_mhz = p->gfx_act_mhz;
+ average.packages.sam_mc6_ms = p->sam_mc6_ms;
+ average.packages.sam_mhz = p->sam_mhz;
+ average.packages.sam_act_mhz = p->sam_act_mhz;
average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c);
- average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status;
- average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status;
+ rapl_counter_accumulate(&average.packages.rapl_pkg_perf_status, &p->rapl_pkg_perf_status);
+ rapl_counter_accumulate(&average.packages.rapl_dram_perf_status, &p->rapl_dram_perf_status);
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
- if (mp->format == FORMAT_RAW)
- continue;
- average.packages.counter[i] += p->counter[i];
+ if ((mp->format == FORMAT_RAW) && (topo.num_packages == 0))
+ average.packages.counter[i] = p->counter[i];
+ else
+ average.packages.counter[i] += p->counter[i];
}
return 0;
}
@@ -2578,6 +2973,7 @@ unsigned long long snapshot_sysfs_counter(char *path)
int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
{
if (mp->msr_num != 0) {
+ assert(!no_msr);
if (get_msr(cpu, mp->msr_num, counterp))
return -1;
} else {
@@ -2599,7 +2995,7 @@ unsigned long long get_uncore_mhz(int package, int die)
{
char path[128];
- sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/current_freq_khz", package,
+ sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d/current_freq_khz", package,
die);
return (snapshot_sysfs_counter(path) / 1000);
@@ -2627,6 +3023,9 @@ int get_epb(int cpu)
return epb;
msr_fallback:
+ if (no_msr)
+ return -1;
+
get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr);
return msr & 0xf;
@@ -2700,6 +3099,351 @@ int get_core_throt_cnt(int cpu, unsigned long long *cnt)
return 0;
}
+struct amperf_group_fd {
+ int aperf; /* Also the group descriptor */
+ int mperf;
+};
+
+static int read_perf_counter_info(const char *const path, const char *const parse_format, void *value_ptr)
+{
+ int fdmt;
+ int bytes_read;
+ char buf[64];
+ int ret = -1;
+
+ fdmt = open(path, O_RDONLY, 0);
+ if (fdmt == -1) {
+ if (debug)
+ fprintf(stderr, "Failed to parse perf counter info %s\n", path);
+ ret = -1;
+ goto cleanup_and_exit;
+ }
+
+ bytes_read = read(fdmt, buf, sizeof(buf) - 1);
+ if (bytes_read <= 0 || bytes_read >= (int)sizeof(buf)) {
+ if (debug)
+ fprintf(stderr, "Failed to parse perf counter info %s\n", path);
+ ret = -1;
+ goto cleanup_and_exit;
+ }
+
+ buf[bytes_read] = '\0';
+
+ if (sscanf(buf, parse_format, value_ptr) != 1) {
+ if (debug)
+ fprintf(stderr, "Failed to parse perf counter info %s\n", path);
+ ret = -1;
+ goto cleanup_and_exit;
+ }
+
+ ret = 0;
+
+cleanup_and_exit:
+ close(fdmt);
+ return ret;
+}
+
+static unsigned int read_perf_counter_info_n(const char *const path, const char *const parse_format)
+{
+ unsigned int v;
+ int status;
+
+ status = read_perf_counter_info(path, parse_format, &v);
+ if (status)
+ v = -1;
+
+ return v;
+}
+
+static unsigned int read_msr_type(void)
+{
+ const char *const path = "/sys/bus/event_source/devices/msr/type";
+ const char *const format = "%u";
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_aperf_config(void)
+{
+ const char *const path = "/sys/bus/event_source/devices/msr/events/aperf";
+ const char *const format = "event=%x";
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_mperf_config(void)
+{
+ const char *const path = "/sys/bus/event_source/devices/msr/events/mperf";
+ const char *const format = "event=%x";
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_perf_type(const char *subsys)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/type";
+ const char *const format = "%u";
+ char path[128];
+
+ snprintf(path, sizeof(path), path_format, subsys);
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_rapl_config(const char *subsys, const char *event_name)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s";
+ const char *const format = "event=%x";
+ char path[128];
+
+ snprintf(path, sizeof(path), path_format, subsys, event_name);
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_perf_rapl_unit(const char *subsys, const char *event_name)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.unit";
+ const char *const format = "%s";
+ char path[128];
+ char unit_buffer[16];
+
+ snprintf(path, sizeof(path), path_format, subsys, event_name);
+
+ read_perf_counter_info(path, format, &unit_buffer);
+ if (strcmp("Joules", unit_buffer) == 0)
+ return RAPL_UNIT_JOULES;
+
+ return RAPL_UNIT_INVALID;
+}
+
+static double read_perf_rapl_scale(const char *subsys, const char *event_name)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.scale";
+ const char *const format = "%lf";
+ char path[128];
+ double scale;
+
+ snprintf(path, sizeof(path), path_format, subsys, event_name);
+
+ if (read_perf_counter_info(path, format, &scale))
+ return 0.0;
+
+ return scale;
+}
+
+static struct amperf_group_fd open_amperf_fd(int cpu)
+{
+ const unsigned int msr_type = read_msr_type();
+ const unsigned int aperf_config = read_aperf_config();
+ const unsigned int mperf_config = read_mperf_config();
+ struct amperf_group_fd fds = {.aperf = -1, .mperf = -1 };
+
+ fds.aperf = open_perf_counter(cpu, msr_type, aperf_config, -1, PERF_FORMAT_GROUP);
+ fds.mperf = open_perf_counter(cpu, msr_type, mperf_config, fds.aperf, PERF_FORMAT_GROUP);
+
+ return fds;
+}
+
+static int get_amperf_fd(int cpu)
+{
+ assert(fd_amperf_percpu);
+
+ if (fd_amperf_percpu[cpu].aperf)
+ return fd_amperf_percpu[cpu].aperf;
+
+ fd_amperf_percpu[cpu] = open_amperf_fd(cpu);
+
+ return fd_amperf_percpu[cpu].aperf;
+}
+
+/* Read APERF, MPERF and TSC using the perf API. */
+static int read_aperf_mperf_tsc_perf(struct thread_data *t, int cpu)
+{
+ union {
+ struct {
+ unsigned long nr_entries;
+ unsigned long aperf;
+ unsigned long mperf;
+ };
+
+ unsigned long as_array[3];
+ } cnt;
+
+ const int fd_amperf = get_amperf_fd(cpu);
+
+ /*
+ * Read the TSC with rdtsc, because we want the absolute value and not
+ * the offset from the start of the counter.
+ */
+ t->tsc = rdtsc();
+
+ const int n = read(fd_amperf, &cnt.as_array[0], sizeof(cnt.as_array));
+
+ if (n != sizeof(cnt.as_array))
+ return -2;
+
+ t->aperf = cnt.aperf * aperf_mperf_multiplier;
+ t->mperf = cnt.mperf * aperf_mperf_multiplier;
+
+ return 0;
+}
+
+/* Read APERF, MPERF and TSC using the MSR driver and rdtsc instruction. */
+static int read_aperf_mperf_tsc_msr(struct thread_data *t, int cpu)
+{
+ unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
+ int aperf_mperf_retry_count = 0;
+
+ /*
+ * The TSC, APERF and MPERF must be read together for
+ * APERF/MPERF and MPERF/TSC to give accurate results.
+ *
+ * Unfortunately, APERF and MPERF are read by
+ * individual system call, so delays may occur
+ * between them. If the time to read them
+ * varies by a large amount, we re-read them.
+ */
+
+ /*
+ * This initial dummy APERF read has been seen to
+ * reduce jitter in the subsequent reads.
+ */
+
+ if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
+ return -3;
+
+retry:
+ t->tsc = rdtsc(); /* re-read close to APERF */
+
+ tsc_before = t->tsc;
+
+ if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
+ return -3;
+
+ tsc_between = rdtsc();
+
+ if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
+ return -4;
+
+ tsc_after = rdtsc();
+
+ aperf_time = tsc_between - tsc_before;
+ mperf_time = tsc_after - tsc_between;
+
+ /*
+ * If the system call latency to read APERF and MPERF
+ * differ by more than 2x, then try again.
+ */
+ if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
+ aperf_mperf_retry_count++;
+ if (aperf_mperf_retry_count < 5)
+ goto retry;
+ else
+ warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time);
+ }
+ aperf_mperf_retry_count = 0;
+
+ t->aperf = t->aperf * aperf_mperf_multiplier;
+ t->mperf = t->mperf * aperf_mperf_multiplier;
+
+ return 0;
+}
+
+size_t rapl_counter_info_count_perf(const struct rapl_counter_info_t *rci)
+{
+ size_t ret = 0;
+
+ for (int i = 0; i < NUM_RAPL_COUNTERS; ++i)
+ if (rci->source[i] == RAPL_SOURCE_PERF)
+ ++ret;
+
+ return ret;
+}
+
+void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci, unsigned int idx)
+{
+ rc->raw_value = rci->data[idx];
+ rc->unit = rci->unit[idx];
+ rc->scale = rci->scale[idx];
+}
+
+int get_rapl_counters(int cpu, int domain, struct core_data *c, struct pkg_data *p)
+{
+ unsigned long long perf_data[NUM_RAPL_COUNTERS + 1];
+ struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain];
+
+ if (debug)
+ fprintf(stderr, "%s: cpu%d domain%d\n", __func__, cpu, domain);
+
+ assert(rapl_counter_info_perdomain);
+
+ /*
+ * If we have any perf counters to read, read them all now, in bulk
+ */
+ if (rci->fd_perf != -1) {
+ size_t num_perf_counters = rapl_counter_info_count_perf(rci);
+ const ssize_t expected_read_size = (num_perf_counters + 1) * sizeof(unsigned long long);
+ const ssize_t actual_read_size = read(rci->fd_perf, &perf_data[0], sizeof(perf_data));
+
+ if (actual_read_size != expected_read_size)
+ err(-1, "%s: failed to read perf_data (%zu %zu)", __func__, expected_read_size,
+ actual_read_size);
+ }
+
+ for (unsigned int i = 0, pi = 1; i < NUM_RAPL_COUNTERS; ++i) {
+ switch (rci->source[i]) {
+ case RAPL_SOURCE_NONE:
+ break;
+
+ case RAPL_SOURCE_PERF:
+ assert(pi < ARRAY_SIZE(perf_data));
+ assert(rci->fd_perf != -1);
+
+ if (debug)
+ fprintf(stderr, "Reading rapl counter via perf at %u (%llu %e %lf)\n",
+ i, perf_data[pi], rci->scale[i], perf_data[pi] * rci->scale[i]);
+
+ rci->data[i] = perf_data[pi];
+
+ ++pi;
+ break;
+
+ case RAPL_SOURCE_MSR:
+ if (debug)
+ fprintf(stderr, "Reading rapl counter via msr at %u\n", i);
+
+ assert(!no_msr);
+ if (rci->flags[i] & RAPL_COUNTER_FLAG_USE_MSR_SUM) {
+ if (get_msr_sum(cpu, rci->msr[i], &rci->data[i]))
+ return -13 - i;
+ } else {
+ if (get_msr(cpu, rci->msr[i], &rci->data[i]))
+ return -13 - i;
+ }
+
+ rci->data[i] &= rci->msr_mask[i];
+ if (rci->msr_shift[i] >= 0)
+ rci->data[i] >>= abs(rci->msr_shift[i]);
+ else
+ rci->data[i] <<= abs(rci->msr_shift[i]);
+
+ break;
+ }
+ }
+
+ _Static_assert(NUM_RAPL_COUNTERS == 7);
+ write_rapl_counter(&p->energy_pkg, rci, RAPL_RCI_INDEX_ENERGY_PKG);
+ write_rapl_counter(&p->energy_cores, rci, RAPL_RCI_INDEX_ENERGY_CORES);
+ write_rapl_counter(&p->energy_dram, rci, RAPL_RCI_INDEX_DRAM);
+ write_rapl_counter(&p->energy_gfx, rci, RAPL_RCI_INDEX_GFX);
+ write_rapl_counter(&p->rapl_pkg_perf_status, rci, RAPL_RCI_INDEX_PKG_PERF_STATUS);
+ write_rapl_counter(&p->rapl_dram_perf_status, rci, RAPL_RCI_INDEX_DRAM_PERF_STATUS);
+ write_rapl_counter(&c->core_energy, rci, RAPL_RCI_INDEX_CORE_ENERGY);
+
+ return 0;
+}
+
/*
* get_counters(...)
* migrate to cpu
@@ -2709,12 +3453,12 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int cpu = t->cpu_id;
unsigned long long msr;
- int aperf_mperf_retry_count = 0;
struct msr_counter *mp;
int i;
+ int status;
if (cpu_migrate(cpu)) {
- fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "%s: Could not migrate to CPU %d\n", __func__, cpu);
return -1;
}
@@ -2722,63 +3466,26 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
if (first_counter_read)
get_apic_id(t);
-retry:
+
t->tsc = rdtsc(); /* we are running on local CPU of interest */
if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC)
|| soft_c1_residency_display(BIC_Avg_MHz)) {
- unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
-
- /*
- * The TSC, APERF and MPERF must be read together for
- * APERF/MPERF and MPERF/TSC to give accurate results.
- *
- * Unfortunately, APERF and MPERF are read by
- * individual system call, so delays may occur
- * between them. If the time to read them
- * varies by a large amount, we re-read them.
- */
-
- /*
- * This initial dummy APERF read has been seen to
- * reduce jitter in the subsequent reads.
- */
-
- if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
- return -3;
-
- t->tsc = rdtsc(); /* re-read close to APERF */
-
- tsc_before = t->tsc;
+ int status = -1;
- if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
- return -3;
+ assert(!no_perf || !no_msr);
- tsc_between = rdtsc();
-
- if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
- return -4;
-
- tsc_after = rdtsc();
-
- aperf_time = tsc_between - tsc_before;
- mperf_time = tsc_after - tsc_between;
-
- /*
- * If the system call latency to read APERF and MPERF
- * differ by more than 2x, then try again.
- */
- if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
- aperf_mperf_retry_count++;
- if (aperf_mperf_retry_count < 5)
- goto retry;
- else
- warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time);
+ switch (amperf_source) {
+ case AMPERF_SOURCE_PERF:
+ status = read_aperf_mperf_tsc_perf(t, cpu);
+ break;
+ case AMPERF_SOURCE_MSR:
+ status = read_aperf_mperf_tsc_msr(t, cpu);
+ break;
}
- aperf_mperf_retry_count = 0;
- t->aperf = t->aperf * aperf_mperf_multiplier;
- t->mperf = t->mperf * aperf_mperf_multiplier;
+ if (status != 0)
+ return status;
}
if (DO_BIC(BIC_IPC))
@@ -2806,6 +3513,12 @@ retry:
if (!is_cpu_first_thread_in_core(t, c, p))
goto done;
+ if (platform->has_per_core_rapl) {
+ status = get_rapl_counters(cpu, c->core_id, c, p);
+ if (status != 0)
+ return status;
+ }
+
if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) {
if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
return -6;
@@ -2846,12 +3559,6 @@ retry:
if (DO_BIC(BIC_CORE_THROT_CNT))
get_core_throt_cnt(cpu, &c->core_throt_cnt);
- if (platform->rapl_msrs & RAPL_AMD_F17H) {
- if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
- return -14;
- c->core_energy = msr & 0xFFFFFFFF;
- }
-
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (get_mp(cpu, mp, &c->counter[i]))
return -10;
@@ -2911,59 +3618,39 @@ retry:
if (DO_BIC(BIC_SYS_LPI))
p->sys_lpi = cpuidle_cur_sys_lpi_us;
- if (platform->rapl_msrs & RAPL_PKG) {
- if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr))
- return -13;
- p->energy_pkg = msr;
- }
- if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) {
- if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr))
- return -14;
- p->energy_cores = msr;
- }
- if (platform->rapl_msrs & RAPL_DRAM) {
- if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
- return -15;
- p->energy_dram = msr;
- }
- if (platform->rapl_msrs & RAPL_GFX) {
- if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr))
- return -16;
- p->energy_gfx = msr;
- }
- if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) {
- if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr))
- return -16;
- p->rapl_pkg_perf_status = msr;
- }
- if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) {
- if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr))
- return -16;
- p->rapl_dram_perf_status = msr;
- }
- if (platform->rapl_msrs & RAPL_AMD_F17H) {
- if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr))
- return -13;
- p->energy_pkg = msr;
+ if (!platform->has_per_core_rapl) {
+ status = get_rapl_counters(cpu, p->package_id, c, p);
+ if (status != 0)
+ return status;
}
+
if (DO_BIC(BIC_PkgTmp)) {
if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
return -17;
p->pkg_temp_c = tj_max - ((msr >> 16) & 0x7F);
}
- if (DO_BIC(BIC_GFX_rc6))
- p->gfx_rc6_ms = gfx_cur_rc6_ms;
-
/* n.b. assume die0 uncore frequency applies to whole package */
if (DO_BIC(BIC_UNCORE_MHZ))
p->uncore_mhz = get_uncore_mhz(p->package_id, 0);
+ if (DO_BIC(BIC_GFX_rc6))
+ p->gfx_rc6_ms = gfx_info[GFX_rc6].val_ull;
+
if (DO_BIC(BIC_GFXMHz))
- p->gfx_mhz = gfx_cur_mhz;
+ p->gfx_mhz = gfx_info[GFX_MHz].val;
if (DO_BIC(BIC_GFXACTMHz))
- p->gfx_act_mhz = gfx_act_mhz;
+ p->gfx_act_mhz = gfx_info[GFX_ACTMHz].val;
+
+ if (DO_BIC(BIC_SAM_mc6))
+ p->sam_mc6_ms = gfx_info[SAM_mc6].val_ull;
+
+ if (DO_BIC(BIC_SAMMHz))
+ p->sam_mhz = gfx_info[SAM_MHz].val;
+
+ if (DO_BIC(BIC_SAMACTMHz))
+ p->sam_act_mhz = gfx_info[SAM_ACTMHz].val;
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (get_mp(cpu, mp, &p->counter[i]))
@@ -3053,7 +3740,7 @@ void probe_cst_limit(void)
unsigned long long msr;
int *pkg_cstate_limits;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
switch (platform->cst_limit) {
@@ -3097,7 +3784,7 @@ static void dump_platform_info(void)
unsigned long long msr;
unsigned int ratio;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
@@ -3115,7 +3802,7 @@ static void dump_power_ctl(void)
{
unsigned long long msr;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
@@ -3321,7 +4008,7 @@ static void dump_cst_cfg(void)
{
unsigned long long msr;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
@@ -3393,7 +4080,7 @@ void print_irtl(void)
{
unsigned long long msr;
- if (!platform->has_irtl_msrs)
+ if (!platform->has_irtl_msrs || no_msr)
return;
if (platform->supported_cstates & PC3) {
@@ -3443,12 +4130,64 @@ void free_fd_percpu(void)
{
int i;
+ if (!fd_percpu)
+ return;
+
for (i = 0; i < topo.max_cpu_num + 1; ++i) {
if (fd_percpu[i] != 0)
close(fd_percpu[i]);
}
free(fd_percpu);
+ fd_percpu = NULL;
+}
+
+void free_fd_amperf_percpu(void)
+{
+ int i;
+
+ if (!fd_amperf_percpu)
+ return;
+
+ for (i = 0; i < topo.max_cpu_num + 1; ++i) {
+ if (fd_amperf_percpu[i].mperf != 0)
+ close(fd_amperf_percpu[i].mperf);
+
+ if (fd_amperf_percpu[i].aperf != 0)
+ close(fd_amperf_percpu[i].aperf);
+ }
+
+ free(fd_amperf_percpu);
+ fd_amperf_percpu = NULL;
+}
+
+void free_fd_instr_count_percpu(void)
+{
+ if (!fd_instr_count_percpu)
+ return;
+
+ for (int i = 0; i < topo.max_cpu_num + 1; ++i) {
+ if (fd_instr_count_percpu[i] != 0)
+ close(fd_instr_count_percpu[i]);
+ }
+
+ free(fd_instr_count_percpu);
+ fd_instr_count_percpu = NULL;
+}
+
+void free_fd_rapl_percpu(void)
+{
+ if (!rapl_counter_info_perdomain)
+ return;
+
+ const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages;
+
+ for (int domain_id = 0; domain_id < num_domains; ++domain_id) {
+ if (rapl_counter_info_perdomain[domain_id].fd_perf != -1)
+ close(rapl_counter_info_perdomain[domain_id].fd_perf);
+ }
+
+ free(rapl_counter_info_perdomain);
}
void free_all_buffers(void)
@@ -3492,6 +4231,9 @@ void free_all_buffers(void)
outp = NULL;
free_fd_percpu();
+ free_fd_instr_count_percpu();
+ free_fd_amperf_percpu();
+ free_fd_rapl_percpu();
free(irq_column_2_cpu);
free(irqs_per_cpu);
@@ -3825,11 +4567,17 @@ static void update_effective_set(bool startup)
err(1, "%s: cpu str malformat %s\n", PATH_EFFECTIVE_CPUS, cpu_effective_str);
}
+void linux_perf_init(void);
+void rapl_perf_init(void);
+
void re_initialize(void)
{
free_all_buffers();
setup_all_buffers(false);
- fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus);
+ linux_perf_init();
+ rapl_perf_init();
+ fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus,
+ topo.allowed_cpus);
}
void set_max_cpu_num(void)
@@ -3940,85 +4688,43 @@ int snapshot_proc_interrupts(void)
}
/*
- * snapshot_gfx_rc6_ms()
+ * snapshot_graphics()
*
- * record snapshot of
- * /sys/class/drm/card0/power/rc6_residency_ms
+ * record snapshot of specified graphics sysfs knob
*
* return 1 if config change requires a restart, else return 0
*/
-int snapshot_gfx_rc6_ms(void)
+int snapshot_graphics(int idx)
{
FILE *fp;
int retval;
- fp = fopen_or_die("/sys/class/drm/card0/power/rc6_residency_ms", "r");
-
- retval = fscanf(fp, "%lld", &gfx_cur_rc6_ms);
- if (retval != 1)
- err(1, "GFX rc6");
-
- fclose(fp);
-
- return 0;
-}
-
-/*
- * snapshot_gfx_mhz()
- *
- * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
- * when /sys/class/drm/card0/gt_cur_freq_mhz is not available.
- *
- * return 1 if config change requires a restart, else return 0
- */
-int snapshot_gfx_mhz(void)
-{
- static FILE *fp;
- int retval;
-
- if (fp == NULL) {
- fp = fopen("/sys/class/drm/card0/gt_cur_freq_mhz", "r");
- if (!fp)
- fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
- } else {
- rewind(fp);
- fflush(fp);
- }
-
- retval = fscanf(fp, "%d", &gfx_cur_mhz);
- if (retval != 1)
- err(1, "GFX MHz");
-
- return 0;
-}
-
-/*
- * snapshot_gfx_cur_mhz()
- *
- * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
- * when /sys/class/drm/card0/gt_act_freq_mhz is not available.
- *
- * return 1 if config change requires a restart, else return 0
- */
-int snapshot_gfx_act_mhz(void)
-{
- static FILE *fp;
- int retval;
-
- if (fp == NULL) {
- fp = fopen("/sys/class/drm/card0/gt_act_freq_mhz", "r");
- if (!fp)
- fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
- } else {
- rewind(fp);
- fflush(fp);
+ switch (idx) {
+ case GFX_rc6:
+ case SAM_mc6:
+ fp = fopen_or_die(gfx_info[idx].path, "r");
+ retval = fscanf(fp, "%lld", &gfx_info[idx].val_ull);
+ if (retval != 1)
+ err(1, "rc6");
+ fclose(fp);
+ return 0;
+ case GFX_MHz:
+ case GFX_ACTMHz:
+ case SAM_MHz:
+ case SAM_ACTMHz:
+ if (gfx_info[idx].fp == NULL) {
+ gfx_info[idx].fp = fopen_or_die(gfx_info[idx].path, "r");
+ } else {
+ rewind(gfx_info[idx].fp);
+ fflush(gfx_info[idx].fp);
+ }
+ retval = fscanf(gfx_info[idx].fp, "%d", &gfx_info[idx].val);
+ if (retval != 1)
+ err(1, "MHz");
+ return 0;
+ default:
+ return -EINVAL;
}
-
- retval = fscanf(fp, "%d", &gfx_act_mhz);
- if (retval != 1)
- err(1, "GFX ACT MHz");
-
- return 0;
}
/*
@@ -4083,13 +4789,22 @@ int snapshot_proc_sysfs_files(void)
return 1;
if (DO_BIC(BIC_GFX_rc6))
- snapshot_gfx_rc6_ms();
+ snapshot_graphics(GFX_rc6);
if (DO_BIC(BIC_GFXMHz))
- snapshot_gfx_mhz();
+ snapshot_graphics(GFX_MHz);
if (DO_BIC(BIC_GFXACTMHz))
- snapshot_gfx_act_mhz();
+ snapshot_graphics(GFX_ACTMHz);
+
+ if (DO_BIC(BIC_SAM_mc6))
+ snapshot_graphics(SAM_mc6);
+
+ if (DO_BIC(BIC_SAMMHz))
+ snapshot_graphics(SAM_MHz);
+
+ if (DO_BIC(BIC_SAMACTMHz))
+ snapshot_graphics(SAM_ACTMHz);
if (DO_BIC(BIC_CPU_LPI))
snapshot_cpu_lpi_us();
@@ -4173,6 +4888,8 @@ int get_msr_sum(int cpu, off_t offset, unsigned long long *msr)
int ret, idx;
unsigned long long msr_cur, msr_last;
+ assert(!no_msr);
+
if (!per_cpu_msr_sum)
return 1;
@@ -4201,6 +4918,8 @@ static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg
UNUSED(c);
UNUSED(p);
+ assert(!no_msr);
+
for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) {
unsigned long long msr_cur, msr_last;
off_t offset;
@@ -4280,7 +4999,8 @@ release_msr:
/*
* set_my_sched_priority(pri)
- * return previous
+ * return previous priority on success
+ * return value < -20 on failure
*/
int set_my_sched_priority(int priority)
{
@@ -4290,16 +5010,16 @@ int set_my_sched_priority(int priority)
errno = 0;
original_priority = getpriority(PRIO_PROCESS, 0);
if (errno && (original_priority == -1))
- err(errno, "getpriority");
+ return -21;
retval = setpriority(PRIO_PROCESS, 0, priority);
if (retval)
- errx(retval, "capget(CAP_SYS_NICE) failed,try \"# setcap cap_sys_nice=ep %s\"", progname);
+ return -21;
errno = 0;
retval = getpriority(PRIO_PROCESS, 0);
if (retval != priority)
- err(retval, "getpriority(%d) != setpriority(%d)", retval, priority);
+ return -21;
return original_priority;
}
@@ -4314,6 +5034,9 @@ void turbostat_loop()
/*
* elevate own priority for interval mode
+ *
+ * ignore on error - we probably don't have permission to set it, but
+ * it's not a big deal
*/
set_my_sched_priority(-20);
@@ -4399,10 +5122,13 @@ void check_dev_msr()
struct stat sb;
char pathname[32];
+ if (no_msr)
+ return;
+
sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
if (stat(pathname, &sb))
if (system("/sbin/modprobe msr > /dev/null 2>&1"))
- err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
+ no_msr = 1;
}
/*
@@ -4414,47 +5140,51 @@ int check_for_cap_sys_rawio(void)
{
cap_t caps;
cap_flag_value_t cap_flag_value;
+ int ret = 0;
caps = cap_get_proc();
if (caps == NULL)
- err(-6, "cap_get_proc\n");
+ return 1;
- if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value))
- err(-6, "cap_get\n");
+ if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value)) {
+ ret = 1;
+ goto free_and_exit;
+ }
if (cap_flag_value != CAP_SET) {
- warnx("capget(CAP_SYS_RAWIO) failed," " try \"# setcap cap_sys_rawio=ep %s\"", progname);
- return 1;
+ ret = 1;
+ goto free_and_exit;
}
+free_and_exit:
if (cap_free(caps) == -1)
err(-6, "cap_free\n");
- return 0;
+ return ret;
}
-void check_permissions(void)
+void check_msr_permission(void)
{
- int do_exit = 0;
+ int failed = 0;
char pathname[32];
+ if (no_msr)
+ return;
+
/* check for CAP_SYS_RAWIO */
- do_exit += check_for_cap_sys_rawio();
+ failed += check_for_cap_sys_rawio();
/* test file permissions */
sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
if (euidaccess(pathname, R_OK)) {
- do_exit++;
- warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr");
+ failed++;
}
- /* if all else fails, thell them to be root */
- if (do_exit)
- if (getuid() != 0)
- warnx("... or simply run as root");
-
- if (do_exit)
- exit(-6);
+ if (failed) {
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly", pathname, "--no-msr");
+ no_msr = 1;
+ }
}
void probe_bclk(void)
@@ -4462,7 +5192,7 @@ void probe_bclk(void)
unsigned long long msr;
unsigned int base_ratio;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
if (platform->bclk_freq == BCLK_100MHZ)
@@ -4502,7 +5232,7 @@ static void dump_turbo_ratio_info(void)
if (!has_turbo)
return;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
if (platform->trl_msrs & TRL_LIMIT2)
@@ -4567,20 +5297,15 @@ static void dump_sysfs_file(char *path)
static void probe_intel_uncore_frequency(void)
{
int i, j;
- char path[128];
+ char path[256];
if (!genuine_intel)
return;
- if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00", R_OK))
- return;
-
- /* Cluster level sysfs not supported yet. */
- if (!access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00", R_OK))
- return;
+ if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK))
+ goto probe_cluster;
- if (!access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK))
- BIC_PRESENT(BIC_UNCORE_MHZ);
+ BIC_PRESENT(BIC_UNCORE_MHZ);
if (quiet)
return;
@@ -4588,40 +5313,178 @@ static void probe_intel_uncore_frequency(void)
for (i = 0; i < topo.num_packages; ++i) {
for (j = 0; j < topo.num_die; ++j) {
int k, l;
+ char path_base[128];
+
+ sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d", i,
+ j);
- sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/min_freq_khz",
- i, j);
+ sprintf(path, "%s/min_freq_khz", path_base);
k = read_sysfs_int(path);
- sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/max_freq_khz",
- i, j);
+ sprintf(path, "%s/max_freq_khz", path_base);
l = read_sysfs_int(path);
- fprintf(outf, "Uncore Frequency pkg%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000);
+ fprintf(outf, "Uncore Frequency package%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000);
- sprintf(path,
- "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_min_freq_khz",
- i, j);
+ sprintf(path, "%s/initial_min_freq_khz", path_base);
k = read_sysfs_int(path);
- sprintf(path,
- "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_max_freq_khz",
- i, j);
+ sprintf(path, "%s/initial_max_freq_khz", path_base);
l = read_sysfs_int(path);
- fprintf(outf, "(%d - %d MHz)\n", k / 1000, l / 1000);
+ fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000);
+
+ sprintf(path, "%s/current_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ fprintf(outf, " %d MHz\n", k / 1000);
}
}
+ return;
+
+probe_cluster:
+ if (access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00/current_freq_khz", R_OK))
+ return;
+
+ if (quiet)
+ return;
+
+ for (i = 0;; ++i) {
+ int k, l;
+ char path_base[128];
+ int package_id, domain_id, cluster_id;
+
+ sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/uncore%02d", i);
+
+ if (access(path_base, R_OK))
+ break;
+
+ sprintf(path, "%s/package_id", path_base);
+ package_id = read_sysfs_int(path);
+
+ sprintf(path, "%s/domain_id", path_base);
+ domain_id = read_sysfs_int(path);
+
+ sprintf(path, "%s/fabric_cluster_id", path_base);
+ cluster_id = read_sysfs_int(path);
+
+ sprintf(path, "%s/min_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ sprintf(path, "%s/max_freq_khz", path_base);
+ l = read_sysfs_int(path);
+ fprintf(outf, "Uncore Frequency package%d domain%d cluster%d: %d - %d MHz ", package_id, domain_id,
+ cluster_id, k / 1000, l / 1000);
+
+ sprintf(path, "%s/initial_min_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ sprintf(path, "%s/initial_max_freq_khz", path_base);
+ l = read_sysfs_int(path);
+ fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000);
+
+ sprintf(path, "%s/current_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ fprintf(outf, " %d MHz\n", k / 1000);
+ }
}
static void probe_graphics(void)
{
+ /* Xe graphics sysfs knobs */
+ if (!access("/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms", R_OK)) {
+ FILE *fp;
+ char buf[8];
+ bool gt0_is_gt;
+ int idx;
+
+ fp = fopen("/sys/class/drm/card0/device/tile0/gt0/gtidle/name", "r");
+ if (!fp)
+ goto next;
+
+ if (!fread(buf, sizeof(char), 7, fp)) {
+ fclose(fp);
+ goto next;
+ }
+ fclose(fp);
+
+ if (!strncmp(buf, "gt0-rc", strlen("gt0-rc")))
+ gt0_is_gt = true;
+ else if (!strncmp(buf, "gt0-mc", strlen("gt0-mc")))
+ gt0_is_gt = false;
+ else
+ goto next;
+
+ idx = gt0_is_gt ? GFX_rc6 : SAM_mc6;
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms";
+
+ idx = gt0_is_gt ? GFX_MHz : SAM_MHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq";
+
+ idx = gt0_is_gt ? GFX_ACTMHz : SAM_ACTMHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq";
+
+ idx = gt0_is_gt ? SAM_mc6 : GFX_rc6;
+ if (!access("/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms";
+
+ idx = gt0_is_gt ? SAM_MHz : GFX_MHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq";
+
+ idx = gt0_is_gt ? SAM_ACTMHz : GFX_ACTMHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq";
+
+ goto end;
+ }
+
+next:
+ /* New i915 graphics sysfs knobs */
+ if (!access("/sys/class/drm/card0/gt/gt0/rc6_residency_ms", R_OK)) {
+ gfx_info[GFX_rc6].path = "/sys/class/drm/card0/gt/gt0/rc6_residency_ms";
+
+ if (!access("/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz", R_OK))
+ gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz";
+
+ if (!access("/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz", R_OK))
+ gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz";
+
+ if (!access("/sys/class/drm/card0/gt/gt1/rc6_residency_ms", R_OK))
+ gfx_info[SAM_mc6].path = "/sys/class/drm/card0/gt/gt1/rc6_residency_ms";
+
+ if (!access("/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz", R_OK))
+ gfx_info[SAM_MHz].path = "/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz";
+
+ if (!access("/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz", R_OK))
+ gfx_info[SAM_ACTMHz].path = "/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz";
+
+ goto end;
+ }
+
+ /* Fall back to traditional i915 graphics sysfs knobs */
if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK))
- BIC_PRESENT(BIC_GFX_rc6);
+ gfx_info[GFX_rc6].path = "/sys/class/drm/card0/power/rc6_residency_ms";
+
+ if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK))
+ gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt_cur_freq_mhz";
+ else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
+ gfx_info[GFX_MHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz";
- if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK) ||
- !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
- BIC_PRESENT(BIC_GFXMHz);
- if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK) ||
- !access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+ if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK))
+ gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt_act_freq_mhz";
+ else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+ gfx_info[GFX_ACTMHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz";
+
+end:
+ if (gfx_info[GFX_rc6].path)
+ BIC_PRESENT(BIC_GFX_rc6);
+ if (gfx_info[GFX_MHz].path)
+ BIC_PRESENT(BIC_GFXMHz);
+ if (gfx_info[GFX_ACTMHz].path)
BIC_PRESENT(BIC_GFXACTMHz);
+ if (gfx_info[SAM_mc6].path)
+ BIC_PRESENT(BIC_SAM_mc6);
+ if (gfx_info[SAM_MHz].path)
+ BIC_PRESENT(BIC_SAMMHz);
+ if (gfx_info[SAM_ACTMHz].path)
+ BIC_PRESENT(BIC_SAMACTMHz);
}
static void dump_sysfs_cstate_config(void)
@@ -4783,6 +5646,9 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
UNUSED(c);
UNUSED(p);
+ if (no_msr)
+ return 0;
+
if (!has_hwp)
return 0;
@@ -4869,6 +5735,9 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
UNUSED(c);
UNUSED(p);
+ if (no_msr)
+ return 0;
+
cpu = t->cpu_id;
/* per-package */
@@ -4983,31 +5852,18 @@ void rapl_probe_intel(void)
unsigned long long msr;
unsigned int time_unit;
double tdp;
+ const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt;
+ const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J;
- if (rapl_joules) {
- if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
- BIC_PRESENT(BIC_Pkg_J);
- if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
- BIC_PRESENT(BIC_Cor_J);
- if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
- BIC_PRESENT(BIC_RAM_J);
- if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
- BIC_PRESENT(BIC_GFX_J);
- } else {
- if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
- BIC_PRESENT(BIC_PkgWatt);
- if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
- BIC_PRESENT(BIC_CorWatt);
- if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
- BIC_PRESENT(BIC_RAMWatt);
- if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
- BIC_PRESENT(BIC_GFXWatt);
- }
+ if (rapl_joules)
+ bic_enabled &= ~bic_watt_bits;
+ else
+ bic_enabled &= ~bic_joules_bits;
- if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS)
- BIC_PRESENT(BIC_PKG__);
- if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS)
- BIC_PRESENT(BIC_RAM__);
+ if (!(platform->rapl_msrs & RAPL_PKG_PERF_STATUS))
+ bic_enabled &= ~BIC_PKG__;
+ if (!(platform->rapl_msrs & RAPL_DRAM_PERF_STATUS))
+ bic_enabled &= ~BIC_RAM__;
/* units on package 0, verify later other packages match */
if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr))
@@ -5041,14 +5897,13 @@ void rapl_probe_amd(void)
{
unsigned long long msr;
double tdp;
+ const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt;
+ const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J;
- if (rapl_joules) {
- BIC_PRESENT(BIC_Pkg_J);
- BIC_PRESENT(BIC_Cor_J);
- } else {
- BIC_PRESENT(BIC_PkgWatt);
- BIC_PRESENT(BIC_CorWatt);
- }
+ if (rapl_joules)
+ bic_enabled &= ~bic_watt_bits;
+ else
+ bic_enabled &= ~bic_joules_bits;
if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
return;
@@ -5202,7 +6057,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
*/
void probe_rapl(void)
{
- if (!platform->rapl_msrs)
+ if (!platform->rapl_msrs || no_msr)
return;
if (genuine_intel)
@@ -5258,7 +6113,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
}
/* Temperature Target MSR is Nehalem and newer only */
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
goto guess;
if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
@@ -5305,6 +6160,9 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
UNUSED(c);
UNUSED(p);
+ if (no_msr)
+ return 0;
+
if (!(do_dts || do_ptm))
return 0;
@@ -5402,6 +6260,9 @@ void decode_feature_control_msr(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!get_msr(base_cpu, MSR_IA32_FEAT_CTL, &msr))
fprintf(outf, "cpu%d: MSR_IA32_FEATURE_CONTROL: 0x%08llx (%sLocked %s)\n",
base_cpu, msr, msr & FEAT_CTL_LOCKED ? "" : "UN-", msr & (1 << 18) ? "SGX" : "");
@@ -5411,6 +6272,9 @@ void decode_misc_enable_msr(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!genuine_intel)
return;
@@ -5428,6 +6292,9 @@ void decode_misc_feature_control(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!platform->has_msr_misc_feature_control)
return;
@@ -5449,6 +6316,9 @@ void decode_misc_pwr_mgmt_msr(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!platform->has_msr_misc_pwr_mgmt)
return;
@@ -5468,6 +6338,9 @@ void decode_c6_demotion_policy_msr(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!platform->has_msr_c6_demotion_policy_config)
return;
@@ -5489,7 +6362,8 @@ void print_dev_latency(void)
fd = open(path, O_RDONLY);
if (fd < 0) {
- warnx("capget(CAP_SYS_ADMIN) failed, try \"# setcap cap_sys_admin=ep %s\"", progname);
+ if (debug)
+ warnx("Read %s failed", path);
return;
}
@@ -5504,23 +6378,260 @@ void print_dev_latency(void)
close(fd);
}
+static int has_instr_count_access(void)
+{
+ int fd;
+ int has_access;
+
+ if (no_perf)
+ return 0;
+
+ fd = open_perf_counter(base_cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0);
+ has_access = fd != -1;
+
+ if (fd != -1)
+ close(fd);
+
+ if (!has_access)
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly",
+ "instructions retired perf counter", "--no-perf");
+
+ return has_access;
+}
+
+bool is_aperf_access_required(void)
+{
+ return BIC_IS_ENABLED(BIC_Avg_MHz)
+ || BIC_IS_ENABLED(BIC_Busy)
+ || BIC_IS_ENABLED(BIC_Bzy_MHz)
+ || BIC_IS_ENABLED(BIC_IPC);
+}
+
+int add_rapl_perf_counter_(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai,
+ double *scale_, enum rapl_unit *unit_)
+{
+ if (no_perf)
+ return -1;
+
+ const double scale = read_perf_rapl_scale(cai->perf_subsys, cai->perf_name);
+
+ if (scale == 0.0)
+ return -1;
+
+ const enum rapl_unit unit = read_perf_rapl_unit(cai->perf_subsys, cai->perf_name);
+
+ if (unit == RAPL_UNIT_INVALID)
+ return -1;
+
+ const unsigned int rapl_type = read_perf_type(cai->perf_subsys);
+ const unsigned int rapl_energy_pkg_config = read_rapl_config(cai->perf_subsys, cai->perf_name);
+
+ const int fd_counter =
+ open_perf_counter(cpu, rapl_type, rapl_energy_pkg_config, rci->fd_perf, PERF_FORMAT_GROUP);
+ if (fd_counter == -1)
+ return -1;
+
+ /* If it's the first counter opened, make it a group descriptor */
+ if (rci->fd_perf == -1)
+ rci->fd_perf = fd_counter;
+
+ *scale_ = scale;
+ *unit_ = unit;
+ return fd_counter;
+}
+
+int add_rapl_perf_counter(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai,
+ double *scale, enum rapl_unit *unit)
+{
+ int ret = add_rapl_perf_counter_(cpu, rci, cai, scale, unit);
+
+ if (debug)
+ fprintf(stderr, "%s: %d (cpu: %d)\n", __func__, ret, cpu);
+
+ return ret;
+}
+
/*
* Linux-perf manages the HW instructions-retired counter
* by enabling when requested, and hiding rollover
*/
void linux_perf_init(void)
{
- if (!BIC_IS_ENABLED(BIC_IPC))
- return;
-
if (access("/proc/sys/kernel/perf_event_paranoid", F_OK))
return;
- fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int));
- if (fd_instr_count_percpu == NULL)
- err(-1, "calloc fd_instr_count_percpu");
+ if (BIC_IS_ENABLED(BIC_IPC) && has_aperf) {
+ fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int));
+ if (fd_instr_count_percpu == NULL)
+ err(-1, "calloc fd_instr_count_percpu");
+ }
+
+ const bool aperf_required = is_aperf_access_required();
+
+ if (aperf_required && has_aperf && amperf_source == AMPERF_SOURCE_PERF) {
+ fd_amperf_percpu = calloc(topo.max_cpu_num + 1, sizeof(*fd_amperf_percpu));
+ if (fd_amperf_percpu == NULL)
+ err(-1, "calloc fd_amperf_percpu");
+ }
+}
+
+void rapl_perf_init(void)
+{
+ const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages;
+ bool *domain_visited = calloc(num_domains, sizeof(bool));
+
+ rapl_counter_info_perdomain = calloc(num_domains, sizeof(*rapl_counter_info_perdomain));
+ if (rapl_counter_info_perdomain == NULL)
+ err(-1, "calloc rapl_counter_info_percpu");
+
+ /*
+ * Initialize rapl_counter_info_percpu
+ */
+ for (int domain_id = 0; domain_id < num_domains; ++domain_id) {
+ struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain_id];
+
+ rci->fd_perf = -1;
+ for (size_t i = 0; i < NUM_RAPL_COUNTERS; ++i) {
+ rci->data[i] = 0;
+ rci->source[i] = RAPL_SOURCE_NONE;
+ }
+ }
- BIC_PRESENT(BIC_IPC);
+ /*
+ * Open/probe the counters
+ * If can't get it via perf, fallback to MSR
+ */
+ for (size_t i = 0; i < ARRAY_SIZE(rapl_counter_arch_infos); ++i) {
+
+ const struct rapl_counter_arch_info *const cai = &rapl_counter_arch_infos[i];
+ bool has_counter = 0;
+ double scale;
+ enum rapl_unit unit;
+ int next_domain;
+
+ memset(domain_visited, 0, num_domains * sizeof(*domain_visited));
+
+ for (int cpu = 0; cpu < topo.max_cpu_num + 1; ++cpu) {
+
+ if (cpu_is_not_allowed(cpu))
+ continue;
+
+ /* Skip already seen and handled RAPL domains */
+ next_domain =
+ platform->has_per_core_rapl ? cpus[cpu].physical_core_id : cpus[cpu].physical_package_id;
+
+ if (domain_visited[next_domain])
+ continue;
+
+ domain_visited[next_domain] = 1;
+
+ struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[next_domain];
+
+ /* Check if the counter is enabled and accessible */
+ if (BIC_IS_ENABLED(cai->bic) && (platform->rapl_msrs & cai->feature_mask)) {
+
+ /* Use perf API for this counter */
+ if (!no_perf && cai->perf_name
+ && add_rapl_perf_counter(cpu, rci, cai, &scale, &unit) != -1) {
+ rci->source[cai->rci_index] = RAPL_SOURCE_PERF;
+ rci->scale[cai->rci_index] = scale * cai->compat_scale;
+ rci->unit[cai->rci_index] = unit;
+ rci->flags[cai->rci_index] = cai->flags;
+
+ /* Use MSR for this counter */
+ } else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) {
+ rci->source[cai->rci_index] = RAPL_SOURCE_MSR;
+ rci->msr[cai->rci_index] = cai->msr;
+ rci->msr_mask[cai->rci_index] = cai->msr_mask;
+ rci->msr_shift[cai->rci_index] = cai->msr_shift;
+ rci->unit[cai->rci_index] = RAPL_UNIT_JOULES;
+ rci->scale[cai->rci_index] = *cai->platform_rapl_msr_scale * cai->compat_scale;
+ rci->flags[cai->rci_index] = cai->flags;
+ }
+ }
+
+ if (rci->source[cai->rci_index] != RAPL_SOURCE_NONE)
+ has_counter = 1;
+ }
+
+ /* If any CPU has access to the counter, make it present */
+ if (has_counter)
+ BIC_PRESENT(cai->bic);
+ }
+
+ free(domain_visited);
+}
+
+static int has_amperf_access_via_msr(void)
+{
+ if (no_msr)
+ return 0;
+
+ if (probe_msr(base_cpu, MSR_IA32_APERF))
+ return 0;
+
+ if (probe_msr(base_cpu, MSR_IA32_MPERF))
+ return 0;
+
+ return 1;
+}
+
+static int has_amperf_access_via_perf(void)
+{
+ struct amperf_group_fd fds;
+
+ /*
+ * Cache the last result, so we don't warn the user multiple times
+ *
+ * Negative means cached, no access
+ * Zero means not cached
+ * Positive means cached, has access
+ */
+ static int has_access_cached;
+
+ if (no_perf)
+ return 0;
+
+ if (has_access_cached != 0)
+ return has_access_cached > 0;
+
+ fds = open_amperf_fd(base_cpu);
+ has_access_cached = (fds.aperf != -1) && (fds.mperf != -1);
+
+ if (fds.aperf == -1)
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly",
+ "APERF perf counter", "--no-perf");
+ else
+ close(fds.aperf);
+
+ if (fds.mperf == -1)
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly",
+ "MPERF perf counter", "--no-perf");
+ else
+ close(fds.mperf);
+
+ if (has_access_cached == 0)
+ has_access_cached = -1;
+
+ return has_access_cached > 0;
+}
+
+/* Check if we can access APERF and MPERF */
+static int has_amperf_access(void)
+{
+ if (!is_aperf_access_required())
+ return 0;
+
+ if (!no_msr && has_amperf_access_via_msr())
+ return 1;
+
+ if (!no_perf && has_amperf_access_via_perf())
+ return 1;
+
+ return 0;
}
void probe_cstates(void)
@@ -5563,7 +6674,7 @@ void probe_cstates(void)
if (platform->has_msr_module_c6_res_ms)
BIC_PRESENT(BIC_Mod_c6);
- if (platform->has_ext_cst_msrs) {
+ if (platform->has_ext_cst_msrs && !no_msr) {
BIC_PRESENT(BIC_Totl_c0);
BIC_PRESENT(BIC_Any_c0);
BIC_PRESENT(BIC_GFX_c0);
@@ -5623,6 +6734,7 @@ void process_cpuid()
unsigned int eax, ebx, ecx, edx;
unsigned int fms, family, model, stepping, ecx_flags, edx_flags;
unsigned long long ucode_patch = 0;
+ bool ucode_patch_valid = false;
eax = ebx = ecx = edx = 0;
@@ -5650,8 +6762,12 @@ void process_cpuid()
ecx_flags = ecx;
edx_flags = edx;
- if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch))
- warnx("get_msr(UCODE)");
+ if (!no_msr) {
+ if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch))
+ warnx("get_msr(UCODE)");
+ else
+ ucode_patch_valid = true;
+ }
/*
* check max extended function levels of CPUID.
@@ -5662,9 +6778,12 @@ void process_cpuid()
__cpuid(0x80000000, max_extended_level, ebx, ecx, edx);
if (!quiet) {
- fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d) microcode 0x%x\n",
- family, model, stepping, family, model, stepping,
- (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF));
+ fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d)",
+ family, model, stepping, family, model, stepping);
+ if (ucode_patch_valid)
+ fprintf(outf, " microcode 0x%x", (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF));
+ fputc('\n', outf);
+
fprintf(outf, "CPUID(0x80000000): max_extended_levels: 0x%x\n", max_extended_level);
fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n",
ecx_flags & (1 << 0) ? "SSE3" : "-",
@@ -5700,10 +6819,11 @@ void process_cpuid()
__cpuid(0x6, eax, ebx, ecx, edx);
has_aperf = ecx & (1 << 0);
- if (has_aperf) {
+ if (has_aperf && has_amperf_access()) {
BIC_PRESENT(BIC_Avg_MHz);
BIC_PRESENT(BIC_Busy);
BIC_PRESENT(BIC_Bzy_MHz);
+ BIC_PRESENT(BIC_IPC);
}
do_dts = eax & (1 << 0);
if (do_dts)
@@ -5786,6 +6906,15 @@ void process_cpuid()
base_mhz = max_mhz = bus_mhz = edx = 0;
__cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx);
+
+ bclk = bus_mhz;
+
+ base_hz = base_mhz * 1000000;
+ has_base_hz = 1;
+
+ if (platform->enable_tsc_tweak)
+ tsc_tweak = base_hz / tsc_hz;
+
if (!quiet)
fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n",
base_mhz, max_mhz, bus_mhz);
@@ -5814,7 +6943,7 @@ void probe_pm_features(void)
probe_thermal();
- if (platform->has_nhm_msrs)
+ if (platform->has_nhm_msrs && !no_msr)
BIC_PRESENT(BIC_SMI);
if (!quiet)
@@ -6142,6 +7271,7 @@ void topology_update(void)
topo.allowed_packages = 0;
for_all_cpus(update_topo, ODD_COUNTERS);
}
+
void setup_all_buffers(bool startup)
{
topology_probe(startup);
@@ -6169,21 +7299,129 @@ void set_base_cpu(void)
err(-ENODEV, "No valid cpus found");
}
+static void set_amperf_source(void)
+{
+ amperf_source = AMPERF_SOURCE_PERF;
+
+ const bool aperf_required = is_aperf_access_required();
+
+ if (no_perf || !aperf_required || !has_amperf_access_via_perf())
+ amperf_source = AMPERF_SOURCE_MSR;
+
+ if (quiet || !debug)
+ return;
+
+ fprintf(outf, "aperf/mperf source preference: %s\n", amperf_source == AMPERF_SOURCE_MSR ? "msr" : "perf");
+}
+
+bool has_added_counters(void)
+{
+ /*
+ * It only makes sense to call this after the command line is parsed,
+ * otherwise sys structure is not populated.
+ */
+
+ return sys.added_core_counters | sys.added_thread_counters | sys.added_package_counters;
+}
+
+bool is_msr_access_required(void)
+{
+ if (no_msr)
+ return false;
+
+ if (has_added_counters())
+ return true;
+
+ return BIC_IS_ENABLED(BIC_SMI)
+ || BIC_IS_ENABLED(BIC_CPU_c1)
+ || BIC_IS_ENABLED(BIC_CPU_c3)
+ || BIC_IS_ENABLED(BIC_CPU_c6)
+ || BIC_IS_ENABLED(BIC_CPU_c7)
+ || BIC_IS_ENABLED(BIC_Mod_c6)
+ || BIC_IS_ENABLED(BIC_CoreTmp)
+ || BIC_IS_ENABLED(BIC_Totl_c0)
+ || BIC_IS_ENABLED(BIC_Any_c0)
+ || BIC_IS_ENABLED(BIC_GFX_c0)
+ || BIC_IS_ENABLED(BIC_CPUGFX)
+ || BIC_IS_ENABLED(BIC_Pkgpc3)
+ || BIC_IS_ENABLED(BIC_Pkgpc6)
+ || BIC_IS_ENABLED(BIC_Pkgpc2)
+ || BIC_IS_ENABLED(BIC_Pkgpc7)
+ || BIC_IS_ENABLED(BIC_Pkgpc8)
+ || BIC_IS_ENABLED(BIC_Pkgpc9)
+ || BIC_IS_ENABLED(BIC_Pkgpc10)
+ /* TODO: Multiplex access with perf */
+ || BIC_IS_ENABLED(BIC_CorWatt)
+ || BIC_IS_ENABLED(BIC_Cor_J)
+ || BIC_IS_ENABLED(BIC_PkgWatt)
+ || BIC_IS_ENABLED(BIC_CorWatt)
+ || BIC_IS_ENABLED(BIC_GFXWatt)
+ || BIC_IS_ENABLED(BIC_RAMWatt)
+ || BIC_IS_ENABLED(BIC_Pkg_J)
+ || BIC_IS_ENABLED(BIC_Cor_J)
+ || BIC_IS_ENABLED(BIC_GFX_J)
+ || BIC_IS_ENABLED(BIC_RAM_J)
+ || BIC_IS_ENABLED(BIC_PKG__)
+ || BIC_IS_ENABLED(BIC_RAM__)
+ || BIC_IS_ENABLED(BIC_PkgTmp)
+ || (is_aperf_access_required() && !has_amperf_access_via_perf());
+}
+
+void check_msr_access(void)
+{
+ if (!is_msr_access_required())
+ no_msr = 1;
+
+ check_dev_msr();
+ check_msr_permission();
+
+ if (no_msr)
+ bic_disable_msr_access();
+}
+
+void check_perf_access(void)
+{
+ const bool intrcount_required = BIC_IS_ENABLED(BIC_IPC);
+
+ if (no_perf || !intrcount_required || !has_instr_count_access())
+ bic_enabled &= ~BIC_IPC;
+
+ const bool aperf_required = is_aperf_access_required();
+
+ if (!aperf_required || !has_amperf_access()) {
+ bic_enabled &= ~BIC_Avg_MHz;
+ bic_enabled &= ~BIC_Busy;
+ bic_enabled &= ~BIC_Bzy_MHz;
+ bic_enabled &= ~BIC_IPC;
+ }
+}
+
void turbostat_init()
{
setup_all_buffers(true);
set_base_cpu();
- check_dev_msr();
- check_permissions();
+ check_msr_access();
+ check_perf_access();
process_cpuid();
probe_pm_features();
+ set_amperf_source();
linux_perf_init();
+ rapl_perf_init();
for_all_cpus(get_cpu_type, ODD_COUNTERS);
for_all_cpus(get_cpu_type, EVEN_COUNTERS);
if (DO_BIC(BIC_IPC))
(void)get_instr_count_fd(base_cpu);
+
+ /*
+ * If TSC tweak is needed, but couldn't get it,
+ * disable more BICs, since it can't be reported accurately.
+ */
+ if (platform->enable_tsc_tweak && !has_base_hz) {
+ bic_enabled &= ~BIC_Busy;
+ bic_enabled &= ~BIC_Bzy_MHz;
+ }
}
int fork_it(char **argv)
@@ -6259,7 +7497,7 @@ int get_and_dump_counters(void)
void print_version()
{
- fprintf(outf, "turbostat version 2023.11.07 - Len Brown <lenb@kernel.org>\n");
+ fprintf(outf, "turbostat version 2024.04.08 - Len Brown <lenb@kernel.org>\n");
}
#define COMMAND_LINE_SIZE 2048
@@ -6291,6 +7529,9 @@ int add_counter(unsigned int msr_num, char *path, char *name,
{
struct msr_counter *msrp;
+ if (no_msr && msr_num)
+ errx(1, "Requested MSR counter 0x%x, but in --no-msr mode", msr_num);
+
msrp = calloc(1, sizeof(struct msr_counter));
if (msrp == NULL) {
perror("calloc");
@@ -6595,6 +7836,8 @@ void cmdline(int argc, char **argv)
{ "list", no_argument, 0, 'l' },
{ "out", required_argument, 0, 'o' },
{ "quiet", no_argument, 0, 'q' },
+ { "no-msr", no_argument, 0, 'M' },
+ { "no-perf", no_argument, 0, 'P' },
{ "show", required_argument, 0, 's' },
{ "Summary", no_argument, 0, 'S' },
{ "TCC", required_argument, 0, 'T' },
@@ -6604,7 +7847,25 @@ void cmdline(int argc, char **argv)
progname = argv[0];
- while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qST:v", long_options, &option_index)) != -1) {
+ /*
+ * Parse some options early, because they may make other options invalid,
+ * like adding the MSR counter with --add and at the same time using --no-msr.
+ */
+ while ((opt = getopt_long_only(argc, argv, "MP", long_options, &option_index)) != -1) {
+ switch (opt) {
+ case 'M':
+ no_msr = 1;
+ break;
+ case 'P':
+ no_perf = 1;
+ break;
+ default:
+ break;
+ }
+ }
+ optind = 0;
+
+ while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qMST:v", long_options, &option_index)) != -1) {
switch (opt) {
case 'a':
parse_add_command(optarg);
@@ -6662,6 +7923,10 @@ void cmdline(int argc, char **argv)
case 'q':
quiet = 1;
break;
+ case 'M':
+ case 'P':
+ /* Parsed earlier */
+ break;
case 'n':
num_iterations = strtod(optarg, NULL);
@@ -6704,6 +7969,22 @@ void cmdline(int argc, char **argv)
}
}
+void set_rlimit(void)
+{
+ struct rlimit limit;
+
+ if (getrlimit(RLIMIT_NOFILE, &limit) < 0)
+ err(1, "Failed to get rlimit");
+
+ if (limit.rlim_max < MAX_NOFILE)
+ limit.rlim_max = MAX_NOFILE;
+ if (limit.rlim_cur < MAX_NOFILE)
+ limit.rlim_cur = MAX_NOFILE;
+
+ if (setrlimit(RLIMIT_NOFILE, &limit) < 0)
+ err(1, "Failed to set rlimit");
+}
+
int main(int argc, char **argv)
{
int fd, ret;
@@ -6729,9 +8010,13 @@ skip_cgroup_setting:
probe_sysfs();
+ if (!getuid())
+ set_rlimit();
+
turbostat_init();
- msr_sum_record();
+ if (!no_msr)
+ msr_sum_record();
/* dump counters and exit */
if (dump_only)
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index 908e0d083936..3482248aa344 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -986,10 +986,12 @@ static void dpa_perf_setup(struct cxl_port *endpoint, struct range *range,
{
dpa_perf->qos_class = FAKE_QTG_ID;
dpa_perf->dpa_range = *range;
- dpa_perf->coord.read_latency = 500;
- dpa_perf->coord.write_latency = 500;
- dpa_perf->coord.read_bandwidth = 1000;
- dpa_perf->coord.write_bandwidth = 1000;
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+ dpa_perf->coord[i].read_latency = 500;
+ dpa_perf->coord[i].write_latency = 500;
+ dpa_perf->coord[i].read_bandwidth = 1000;
+ dpa_perf->coord[i].write_bandwidth = 1000;
+ }
}
static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port)
@@ -999,6 +1001,7 @@ static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port)
struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
struct cxl_dev_state *cxlds = cxlmd->cxlds;
struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+ struct access_coordinate ep_c[ACCESS_COORDINATE_MAX];
struct range pmem_range = {
.start = cxlds->pmem_res.start,
.end = cxlds->pmem_res.end,
@@ -1018,6 +1021,12 @@ static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port)
dpa_perf_setup(port, &pmem_range, &mds->pmem_perf);
cxl_memdev_update_perf(cxlmd);
+
+ /*
+ * This function is here to only test the topology iterator. It serves
+ * no other purpose.
+ */
+ cxl_endpoint_get_perf_coordinates(port, ep_c);
}
static struct cxl_mock_ops cxl_mock_ops = {
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 39ad96a18123..edcd26106557 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -205,6 +205,9 @@ __weak noinline struct file *bpf_testmod_return_ptr(int arg)
case 5: return (void *)~(1ull << 30); /* trigger extable */
case 6: return &f; /* valid addr */
case 7: return (void *)((long)&f | 1); /* kernel tricks */
+#ifdef CONFIG_X86_64
+ case 8: return (void *)VSYSCALL_ADDR; /* vsyscall page address */
+#endif
default: return NULL;
}
}
diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
index b1ede6249866..b7c8f29c09a9 100644
--- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -18,7 +18,7 @@ echo 'sched:*' > set_event
yield
-count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
if [ $count -lt 3 ]; then
fail "at least fork, exec and exit events should be recorded"
fi
@@ -29,7 +29,7 @@ echo 1 > events/sched/enable
yield
-count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
if [ $count -lt 3 ]; then
fail "at least fork, exec and exit events should be recorded"
fi
@@ -40,7 +40,7 @@ echo 0 > events/sched/enable
yield
-count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
if [ $count -ne 0 ]; then
fail "any of scheduler events should not be recorded"
fi
diff --git a/tools/testing/selftests/iommu/config b/tools/testing/selftests/iommu/config
index 110d73917615..02a2a1b267c1 100644
--- a/tools/testing/selftests/iommu/config
+++ b/tools/testing/selftests/iommu/config
@@ -1,3 +1,5 @@
CONFIG_IOMMUFD=y
+CONFIG_FAULT_INJECTION_DEBUG_FS=y
CONFIG_FAULT_INJECTION=y
CONFIG_IOMMUFD_TEST=y
+CONFIG_FAILSLAB=y
diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index 541bf192e30e..14bbab0cce13 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -51,6 +51,7 @@
#include <stdarg.h>
#include <string.h>
#include <stdio.h>
+#include <sys/utsname.h>
#endif
#ifndef ARRAY_SIZE
@@ -79,6 +80,9 @@
#define KSFT_XPASS 3
#define KSFT_SKIP 4
+#ifndef __noreturn
+#define __noreturn __attribute__((__noreturn__))
+#endif
#define __printf(a, b) __attribute__((format(printf, a, b)))
/* counters */
@@ -288,24 +292,26 @@ void ksft_test_result_code(int exit_code, const char *test_name,
}
/* Docs seem to call for double space if directive is absent */
- if (!directive[0] && msg[0])
+ if (!directive[0] && msg)
directive = " # ";
- va_start(args, msg);
printf("%s %u %s%s", tap_code, ksft_test_num(), test_name, directive);
errno = saved_errno;
- vprintf(msg, args);
+ if (msg) {
+ va_start(args, msg);
+ vprintf(msg, args);
+ va_end(args);
+ }
printf("\n");
- va_end(args);
}
-static inline int ksft_exit_pass(void)
+static inline __noreturn int ksft_exit_pass(void)
{
ksft_print_cnts();
exit(KSFT_PASS);
}
-static inline int ksft_exit_fail(void)
+static inline __noreturn int ksft_exit_fail(void)
{
ksft_print_cnts();
exit(KSFT_FAIL);
@@ -332,7 +338,7 @@ static inline int ksft_exit_fail(void)
ksft_cnt.ksft_xfail + \
ksft_cnt.ksft_xskip)
-static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...)
+static inline __noreturn __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...)
{
int saved_errno = errno;
va_list args;
@@ -347,19 +353,19 @@ static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...)
exit(KSFT_FAIL);
}
-static inline int ksft_exit_xfail(void)
+static inline __noreturn int ksft_exit_xfail(void)
{
ksft_print_cnts();
exit(KSFT_XFAIL);
}
-static inline int ksft_exit_xpass(void)
+static inline __noreturn int ksft_exit_xpass(void)
{
ksft_print_cnts();
exit(KSFT_XPASS);
}
-static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...)
+static inline __noreturn __printf(1, 2) int ksft_exit_skip(const char *msg, ...)
{
int saved_errno = errno;
va_list args;
@@ -388,4 +394,21 @@ static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...)
exit(KSFT_SKIP);
}
+static inline int ksft_min_kernel_version(unsigned int min_major,
+ unsigned int min_minor)
+{
+#ifdef NOLIBC
+ ksft_print_msg("NOLIBC: Can't check kernel version: Function not implemented\n");
+ return 0;
+#else
+ unsigned int major, minor;
+ struct utsname info;
+
+ if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2)
+ ksft_exit_fail_msg("Can't parse kernel version\n");
+
+ return major > min_major || (major == min_major && minor >= min_minor);
+#endif
+}
+
#endif /* __KSELFTEST_H */
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 4fd735e48ee7..d98702b6955d 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -56,7 +56,6 @@
#include <asm/types.h>
#include <ctype.h>
#include <errno.h>
-#include <limits.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
@@ -383,6 +382,7 @@
FIXTURE_DATA(fixture_name) self; \
pid_t child = 1; \
int status = 0; \
+ bool jmp = false; \
memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \
if (setjmp(_metadata->env) == 0) { \
/* Use the same _metadata. */ \
@@ -399,8 +399,10 @@
_metadata->exit_code = KSFT_FAIL; \
} \
} \
+ else \
+ jmp = true; \
if (child == 0) { \
- if (_metadata->setup_completed && !_metadata->teardown_parent) \
+ if (_metadata->setup_completed && !_metadata->teardown_parent && !jmp) \
fixture_name##_teardown(_metadata, &self, variant->data); \
_exit(0); \
} \
@@ -1156,7 +1158,7 @@ void __run_test(struct __fixture_metadata *f,
struct __test_metadata *t)
{
struct __test_xfail *xfail;
- char test_name[LINE_MAX];
+ char *test_name;
const char *diagnostic;
/* reset test struct */
@@ -1164,8 +1166,12 @@ void __run_test(struct __fixture_metadata *f,
t->trigger = 0;
memset(t->results->reason, 0, sizeof(t->results->reason));
- snprintf(test_name, sizeof(test_name), "%s%s%s.%s",
- f->name, variant->name[0] ? "." : "", variant->name, t->name);
+ if (asprintf(&test_name, "%s%s%s.%s", f->name,
+ variant->name[0] ? "." : "", variant->name, t->name) == -1) {
+ ksft_print_msg("ERROR ALLOCATING MEMORY\n");
+ t->exit_code = KSFT_FAIL;
+ _exit(t->exit_code);
+ }
ksft_print_msg(" RUN %s ...\n", test_name);
@@ -1202,7 +1208,8 @@ void __run_test(struct __fixture_metadata *f,
diagnostic = "unknown";
ksft_test_result_code(t->exit_code, test_name,
- diagnostic ? "%s" : "", diagnostic);
+ diagnostic ? "%s" : NULL, diagnostic);
+ free(test_name);
}
static int test_harness_run(int argc, char **argv)
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 6de9994971c9..ce8ff8e8ce3a 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -45,6 +45,7 @@ LIBKVM_x86_64 += lib/x86_64/vmx.c
LIBKVM_aarch64 += lib/aarch64/gic.c
LIBKVM_aarch64 += lib/aarch64/gic_v3.c
+LIBKVM_aarch64 += lib/aarch64/gic_v3_its.c
LIBKVM_aarch64 += lib/aarch64/handlers.S
LIBKVM_aarch64 += lib/aarch64/processor.c
LIBKVM_aarch64 += lib/aarch64/spinlock.c
@@ -158,6 +159,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/smccc_filter
TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
+TEST_GEN_PROGS_aarch64 += aarch64/vgic_lpi_stress
TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access
TEST_GEN_PROGS_aarch64 += access_tracking_perf_test
TEST_GEN_PROGS_aarch64 += arch_timer
@@ -190,6 +192,8 @@ TEST_GEN_PROGS_s390x += rseq_test
TEST_GEN_PROGS_s390x += set_memory_region_test
TEST_GEN_PROGS_s390x += kvm_binary_stats_test
+TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test
+TEST_GEN_PROGS_riscv += riscv/ebreak_test
TEST_GEN_PROGS_riscv += arch_timer
TEST_GEN_PROGS_riscv += demand_paging_test
TEST_GEN_PROGS_riscv += dirty_log_test
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index 02967318caf4..eeba1cc87ff8 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -13,9 +13,6 @@
#include "ucall_common.h"
#include "vgic.h"
-#define GICD_BASE_GPA 0x8000000ULL
-#define GICR_BASE_GPA 0x80A0000ULL
-
enum guest_stage {
GUEST_STAGE_VTIMER_CVAL = 1,
GUEST_STAGE_VTIMER_TVAL,
@@ -148,8 +145,7 @@ static void guest_code(void)
local_irq_disable();
- gic_init(GIC_V3, test_args.nr_vcpus,
- (void *)GICD_BASE_GPA, (void *)GICR_BASE_GPA);
+ gic_init(GIC_V3, test_args.nr_vcpus);
timer_set_ctl(VIRTUAL, CTL_IMASK);
timer_set_ctl(PHYSICAL, CTL_IMASK);
@@ -208,7 +204,7 @@ struct kvm_vm *test_vm_create(void)
vcpu_init_descriptor_tables(vcpus[i]);
test_init_timer_irq(vm);
- gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+ gic_fd = vgic_v3_setup(vm, nr_vcpus, 64);
__TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3");
/* Make all the test's cmdline args visible to the guest */
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index 79e99f47a9fe..d29b08198b42 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -374,14 +374,14 @@ static void setup_uffd(struct kvm_vm *vm, struct test_params *p,
*pt_uffd = uffd_setup_demand_paging(uffd_mode, 0,
pt_args.hva,
pt_args.paging_size,
- test->uffd_pt_handler);
+ 1, test->uffd_pt_handler);
*data_uffd = NULL;
if (test->uffd_data_handler)
*data_uffd = uffd_setup_demand_paging(uffd_mode, 0,
data_args.hva,
data_args.paging_size,
- test->uffd_data_handler);
+ 1, test->uffd_data_handler);
}
static void free_uffd(struct test_desc *test, struct uffd_desc *pt_uffd,
diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c
index 1c8c6f0c1ca3..61731a950def 100644
--- a/tools/testing/selftests/kvm/aarch64/psci_test.c
+++ b/tools/testing/selftests/kvm/aarch64/psci_test.c
@@ -10,7 +10,10 @@
* - A test for KVM's handling of PSCI SYSTEM_SUSPEND and the associated
* KVM_SYSTEM_EVENT_SUSPEND UAPI.
*/
+
+#include <linux/kernel.h>
#include <linux/psci.h>
+#include <asm/cputype.h>
#include "kvm_util.h"
#include "processor.h"
diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c
index 16e2338686c1..a7de39fa2a0a 100644
--- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c
@@ -327,8 +327,8 @@ uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
return ftr;
}
-static void test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg,
- const struct reg_ftr_bits *ftr_bits)
+static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg,
+ const struct reg_ftr_bits *ftr_bits)
{
uint8_t shift = ftr_bits->shift;
uint64_t mask = ftr_bits->mask;
@@ -346,6 +346,8 @@ static void test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg,
vcpu_set_reg(vcpu, reg, val);
vcpu_get_reg(vcpu, reg, &new_val);
TEST_ASSERT_EQ(new_val, val);
+
+ return new_val;
}
static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg,
@@ -374,7 +376,15 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg,
TEST_ASSERT_EQ(val, old_val);
}
-static void test_user_set_reg(struct kvm_vcpu *vcpu, bool aarch64_only)
+static uint64_t test_reg_vals[KVM_ARM_FEATURE_ID_RANGE_SIZE];
+
+#define encoding_to_range_idx(encoding) \
+ KVM_ARM_FEATURE_ID_RANGE_IDX(sys_reg_Op0(encoding), sys_reg_Op1(encoding), \
+ sys_reg_CRn(encoding), sys_reg_CRm(encoding), \
+ sys_reg_Op2(encoding))
+
+
+static void test_vm_ftr_id_regs(struct kvm_vcpu *vcpu, bool aarch64_only)
{
uint64_t masks[KVM_ARM_FEATURE_ID_RANGE_SIZE];
struct reg_mask_range range = {
@@ -398,9 +408,7 @@ static void test_user_set_reg(struct kvm_vcpu *vcpu, bool aarch64_only)
int idx;
/* Get the index to masks array for the idreg */
- idx = KVM_ARM_FEATURE_ID_RANGE_IDX(sys_reg_Op0(reg_id), sys_reg_Op1(reg_id),
- sys_reg_CRn(reg_id), sys_reg_CRm(reg_id),
- sys_reg_Op2(reg_id));
+ idx = encoding_to_range_idx(reg_id);
for (int j = 0; ftr_bits[j].type != FTR_END; j++) {
/* Skip aarch32 reg on aarch64 only system, since they are RAZ/WI. */
@@ -414,7 +422,9 @@ static void test_user_set_reg(struct kvm_vcpu *vcpu, bool aarch64_only)
TEST_ASSERT_EQ(masks[idx] & ftr_bits[j].mask, ftr_bits[j].mask);
test_reg_set_fail(vcpu, reg, &ftr_bits[j]);
- test_reg_set_success(vcpu, reg, &ftr_bits[j]);
+
+ test_reg_vals[idx] = test_reg_set_success(vcpu, reg,
+ &ftr_bits[j]);
ksft_test_result_pass("%s\n", ftr_bits[j].name);
}
@@ -425,7 +435,6 @@ static void test_guest_reg_read(struct kvm_vcpu *vcpu)
{
bool done = false;
struct ucall uc;
- uint64_t val;
while (!done) {
vcpu_run(vcpu);
@@ -436,8 +445,8 @@ static void test_guest_reg_read(struct kvm_vcpu *vcpu)
break;
case UCALL_SYNC:
/* Make sure the written values are seen by guest */
- vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(uc.args[2]), &val);
- TEST_ASSERT_EQ(val, uc.args[3]);
+ TEST_ASSERT_EQ(test_reg_vals[encoding_to_range_idx(uc.args[2])],
+ uc.args[3]);
break;
case UCALL_DONE:
done = true;
@@ -448,13 +457,85 @@ static void test_guest_reg_read(struct kvm_vcpu *vcpu)
}
}
+/* Politely lifted from arch/arm64/include/asm/cache.h */
+/* Ctypen, bits[3(n - 1) + 2 : 3(n - 1)], for n = 1 to 7 */
+#define CLIDR_CTYPE_SHIFT(level) (3 * (level - 1))
+#define CLIDR_CTYPE_MASK(level) (7 << CLIDR_CTYPE_SHIFT(level))
+#define CLIDR_CTYPE(clidr, level) \
+ (((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
+
+static void test_clidr(struct kvm_vcpu *vcpu)
+{
+ uint64_t clidr;
+ int level;
+
+ vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1), &clidr);
+
+ /* find the first empty level in the cache hierarchy */
+ for (level = 1; level < 7; level++) {
+ if (!CLIDR_CTYPE(clidr, level))
+ break;
+ }
+
+ /*
+ * If you have a mind-boggling 7 levels of cache, congratulations, you
+ * get to fix this.
+ */
+ TEST_ASSERT(level <= 7, "can't find an empty level in cache hierarchy");
+
+ /* stick in a unified cache level */
+ clidr |= BIT(2) << CLIDR_CTYPE_SHIFT(level);
+
+ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1), clidr);
+ test_reg_vals[encoding_to_range_idx(SYS_CLIDR_EL1)] = clidr;
+}
+
+static void test_vcpu_ftr_id_regs(struct kvm_vcpu *vcpu)
+{
+ u64 val;
+
+ test_clidr(vcpu);
+
+ vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &val);
+ val++;
+ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), val);
+
+ test_reg_vals[encoding_to_range_idx(SYS_MPIDR_EL1)] = val;
+ ksft_test_result_pass("%s\n", __func__);
+}
+
+static void test_assert_id_reg_unchanged(struct kvm_vcpu *vcpu, uint32_t encoding)
+{
+ size_t idx = encoding_to_range_idx(encoding);
+ uint64_t observed;
+
+ vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding), &observed);
+ TEST_ASSERT_EQ(test_reg_vals[idx], observed);
+}
+
+static void test_reset_preserves_id_regs(struct kvm_vcpu *vcpu)
+{
+ /*
+ * Calls KVM_ARM_VCPU_INIT behind the scenes, which will do an
+ * architectural reset of the vCPU.
+ */
+ aarch64_vcpu_setup(vcpu, NULL);
+
+ for (int i = 0; i < ARRAY_SIZE(test_regs); i++)
+ test_assert_id_reg_unchanged(vcpu, test_regs[i].reg);
+
+ test_assert_id_reg_unchanged(vcpu, SYS_CLIDR_EL1);
+
+ ksft_test_result_pass("%s\n", __func__);
+}
+
int main(void)
{
struct kvm_vcpu *vcpu;
struct kvm_vm *vm;
bool aarch64_only;
uint64_t val, el0;
- int ftr_cnt;
+ int test_cnt;
TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES));
@@ -467,18 +548,22 @@ int main(void)
ksft_print_header();
- ftr_cnt = ARRAY_SIZE(ftr_id_aa64dfr0_el1) + ARRAY_SIZE(ftr_id_dfr0_el1) +
- ARRAY_SIZE(ftr_id_aa64isar0_el1) + ARRAY_SIZE(ftr_id_aa64isar1_el1) +
- ARRAY_SIZE(ftr_id_aa64isar2_el1) + ARRAY_SIZE(ftr_id_aa64pfr0_el1) +
- ARRAY_SIZE(ftr_id_aa64mmfr0_el1) + ARRAY_SIZE(ftr_id_aa64mmfr1_el1) +
- ARRAY_SIZE(ftr_id_aa64mmfr2_el1) + ARRAY_SIZE(ftr_id_aa64zfr0_el1) -
- ARRAY_SIZE(test_regs);
+ test_cnt = ARRAY_SIZE(ftr_id_aa64dfr0_el1) + ARRAY_SIZE(ftr_id_dfr0_el1) +
+ ARRAY_SIZE(ftr_id_aa64isar0_el1) + ARRAY_SIZE(ftr_id_aa64isar1_el1) +
+ ARRAY_SIZE(ftr_id_aa64isar2_el1) + ARRAY_SIZE(ftr_id_aa64pfr0_el1) +
+ ARRAY_SIZE(ftr_id_aa64mmfr0_el1) + ARRAY_SIZE(ftr_id_aa64mmfr1_el1) +
+ ARRAY_SIZE(ftr_id_aa64mmfr2_el1) + ARRAY_SIZE(ftr_id_aa64zfr0_el1) -
+ ARRAY_SIZE(test_regs) + 2;
- ksft_set_plan(ftr_cnt);
+ ksft_set_plan(test_cnt);
+
+ test_vm_ftr_id_regs(vcpu, aarch64_only);
+ test_vcpu_ftr_id_regs(vcpu);
- test_user_set_reg(vcpu, aarch64_only);
test_guest_reg_read(vcpu);
+ test_reset_preserves_id_regs(vcpu);
+
kvm_vm_free(vm);
ksft_finished();
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c
index e93022870cac..b3b5fb0ff0a9 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_init.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c
@@ -83,6 +83,18 @@ static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type,
return v;
}
+static struct vm_gic vm_gic_create_barebones(uint32_t gic_dev_type)
+{
+ struct vm_gic v;
+
+ v.gic_dev_type = gic_dev_type;
+ v.vm = vm_create_barebones();
+ v.gic_fd = kvm_create_device(v.vm, gic_dev_type);
+
+ return v;
+}
+
+
static void vm_gic_destroy(struct vm_gic *v)
{
close(v->gic_fd);
@@ -356,6 +368,40 @@ static void test_vcpus_then_vgic(uint32_t gic_dev_type)
vm_gic_destroy(&v);
}
+#define KVM_VGIC_V2_ATTR(offset, cpu) \
+ (FIELD_PREP(KVM_DEV_ARM_VGIC_OFFSET_MASK, offset) | \
+ FIELD_PREP(KVM_DEV_ARM_VGIC_CPUID_MASK, cpu))
+
+#define GIC_CPU_CTRL 0x00
+
+static void test_v2_uaccess_cpuif_no_vcpus(void)
+{
+ struct vm_gic v;
+ u64 val = 0;
+ int ret;
+
+ v = vm_gic_create_barebones(KVM_DEV_TYPE_ARM_VGIC_V2);
+ subtest_dist_rdist(&v);
+
+ ret = __kvm_has_device_attr(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS,
+ KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0));
+ TEST_ASSERT(ret && errno == EINVAL,
+ "accessed non-existent CPU interface, want errno: %i",
+ EINVAL);
+ ret = __kvm_device_attr_get(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS,
+ KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0), &val);
+ TEST_ASSERT(ret && errno == EINVAL,
+ "accessed non-existent CPU interface, want errno: %i",
+ EINVAL);
+ ret = __kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS,
+ KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0), &val);
+ TEST_ASSERT(ret && errno == EINVAL,
+ "accessed non-existent CPU interface, want errno: %i",
+ EINVAL);
+
+ vm_gic_destroy(&v);
+}
+
static void test_v3_new_redist_regions(void)
{
struct kvm_vcpu *vcpus[NR_VCPUS];
@@ -674,6 +720,9 @@ void run_tests(uint32_t gic_dev_type)
test_vcpus_then_vgic(gic_dev_type);
test_vgic_then_vcpus(gic_dev_type);
+ if (VGIC_DEV_IS_V2(gic_dev_type))
+ test_v2_uaccess_cpuif_no_vcpus();
+
if (VGIC_DEV_IS_V3(gic_dev_type)) {
test_v3_new_redist_regions();
test_v3_typer_accesses();
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
index 2e64b4856e38..a51dbd2a5f84 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
@@ -19,9 +19,6 @@
#include "gic_v3.h"
#include "vgic.h"
-#define GICD_BASE_GPA 0x08000000ULL
-#define GICR_BASE_GPA 0x080A0000ULL
-
/*
* Stores the user specified args; it's passed to the guest and to every test
* function.
@@ -49,9 +46,6 @@ struct test_args {
#define IRQ_DEFAULT_PRIO (LOWEST_PRIO - 1)
#define IRQ_DEFAULT_PRIO_REG (IRQ_DEFAULT_PRIO << KVM_PRIO_SHIFT) /* 0xf0 */
-static void *dist = (void *)GICD_BASE_GPA;
-static void *redist = (void *)GICR_BASE_GPA;
-
/*
* The kvm_inject_* utilities are used by the guest to ask the host to inject
* interrupts (e.g., using the KVM_IRQ_LINE ioctl).
@@ -152,7 +146,7 @@ static void reset_stats(void)
static uint64_t gic_read_ap1r0(void)
{
- uint64_t reg = read_sysreg_s(SYS_ICV_AP1R0_EL1);
+ uint64_t reg = read_sysreg_s(SYS_ICC_AP1R0_EL1);
dsb(sy);
return reg;
@@ -160,7 +154,7 @@ static uint64_t gic_read_ap1r0(void)
static void gic_write_ap1r0(uint64_t val)
{
- write_sysreg_s(val, SYS_ICV_AP1R0_EL1);
+ write_sysreg_s(val, SYS_ICC_AP1R0_EL1);
isb();
}
@@ -478,7 +472,7 @@ static void guest_code(struct test_args *args)
bool level_sensitive = args->level_sensitive;
struct kvm_inject_desc *f, *inject_fns;
- gic_init(GIC_V3, 1, dist, redist);
+ gic_init(GIC_V3, 1);
for (i = 0; i < nr_irqs; i++)
gic_irq_enable(i);
@@ -764,8 +758,7 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args));
vcpu_args_set(vcpu, 1, args_gva);
- gic_fd = vgic_v3_setup(vm, 1, nr_irqs,
- GICD_BASE_GPA, GICR_BASE_GPA);
+ gic_fd = vgic_v3_setup(vm, 1, nr_irqs);
__TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3, skipping");
vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT,
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c b/tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c
new file mode 100644
index 000000000000..fc4fe52fb6f8
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * vgic_lpi_stress - Stress test for KVM's ITS emulation
+ *
+ * Copyright (c) 2024 Google LLC
+ */
+
+#include <linux/sizes.h>
+#include <pthread.h>
+#include <stdatomic.h>
+#include <sys/sysinfo.h>
+
+#include "kvm_util.h"
+#include "gic.h"
+#include "gic_v3.h"
+#include "gic_v3_its.h"
+#include "processor.h"
+#include "ucall.h"
+#include "vgic.h"
+
+#define TEST_MEMSLOT_INDEX 1
+
+#define GIC_LPI_OFFSET 8192
+
+static size_t nr_iterations = 1000;
+static vm_paddr_t gpa_base;
+
+static struct kvm_vm *vm;
+static struct kvm_vcpu **vcpus;
+static int gic_fd, its_fd;
+
+static struct test_data {
+ bool request_vcpus_stop;
+ u32 nr_cpus;
+ u32 nr_devices;
+ u32 nr_event_ids;
+
+ vm_paddr_t device_table;
+ vm_paddr_t collection_table;
+ vm_paddr_t cmdq_base;
+ void *cmdq_base_va;
+ vm_paddr_t itt_tables;
+
+ vm_paddr_t lpi_prop_table;
+ vm_paddr_t lpi_pend_tables;
+} test_data = {
+ .nr_cpus = 1,
+ .nr_devices = 1,
+ .nr_event_ids = 16,
+};
+
+static void guest_irq_handler(struct ex_regs *regs)
+{
+ u32 intid = gic_get_and_ack_irq();
+
+ if (intid == IAR_SPURIOUS)
+ return;
+
+ GUEST_ASSERT(intid >= GIC_LPI_OFFSET);
+ gic_set_eoi(intid);
+}
+
+static void guest_setup_its_mappings(void)
+{
+ u32 coll_id, device_id, event_id, intid = GIC_LPI_OFFSET;
+ u32 nr_events = test_data.nr_event_ids;
+ u32 nr_devices = test_data.nr_devices;
+ u32 nr_cpus = test_data.nr_cpus;
+
+ for (coll_id = 0; coll_id < nr_cpus; coll_id++)
+ its_send_mapc_cmd(test_data.cmdq_base_va, coll_id, coll_id, true);
+
+ /* Round-robin the LPIs to all of the vCPUs in the VM */
+ coll_id = 0;
+ for (device_id = 0; device_id < nr_devices; device_id++) {
+ vm_paddr_t itt_base = test_data.itt_tables + (device_id * SZ_64K);
+
+ its_send_mapd_cmd(test_data.cmdq_base_va, device_id,
+ itt_base, SZ_64K, true);
+
+ for (event_id = 0; event_id < nr_events; event_id++) {
+ its_send_mapti_cmd(test_data.cmdq_base_va, device_id,
+ event_id, coll_id, intid++);
+
+ coll_id = (coll_id + 1) % test_data.nr_cpus;
+ }
+ }
+}
+
+static void guest_invalidate_all_rdists(void)
+{
+ int i;
+
+ for (i = 0; i < test_data.nr_cpus; i++)
+ its_send_invall_cmd(test_data.cmdq_base_va, i);
+}
+
+static void guest_setup_gic(void)
+{
+ static atomic_int nr_cpus_ready = 0;
+ u32 cpuid = guest_get_vcpuid();
+
+ gic_init(GIC_V3, test_data.nr_cpus);
+ gic_rdist_enable_lpis(test_data.lpi_prop_table, SZ_64K,
+ test_data.lpi_pend_tables + (cpuid * SZ_64K));
+
+ atomic_fetch_add(&nr_cpus_ready, 1);
+
+ if (cpuid > 0)
+ return;
+
+ while (atomic_load(&nr_cpus_ready) < test_data.nr_cpus)
+ cpu_relax();
+
+ its_init(test_data.collection_table, SZ_64K,
+ test_data.device_table, SZ_64K,
+ test_data.cmdq_base, SZ_64K);
+
+ guest_setup_its_mappings();
+ guest_invalidate_all_rdists();
+}
+
+static void guest_code(size_t nr_lpis)
+{
+ guest_setup_gic();
+
+ GUEST_SYNC(0);
+
+ /*
+ * Don't use WFI here to avoid blocking the vCPU thread indefinitely and
+ * never getting the stop signal.
+ */
+ while (!READ_ONCE(test_data.request_vcpus_stop))
+ cpu_relax();
+
+ GUEST_DONE();
+}
+
+static void setup_memslot(void)
+{
+ size_t pages;
+ size_t sz;
+
+ /*
+ * For the ITS:
+ * - A single level device table
+ * - A single level collection table
+ * - The command queue
+ * - An ITT for each device
+ */
+ sz = (3 + test_data.nr_devices) * SZ_64K;
+
+ /*
+ * For the redistributors:
+ * - A shared LPI configuration table
+ * - An LPI pending table for each vCPU
+ */
+ sz += (1 + test_data.nr_cpus) * SZ_64K;
+
+ pages = sz / vm->page_size;
+ gpa_base = ((vm_compute_max_gfn(vm) + 1) * vm->page_size) - sz;
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, gpa_base,
+ TEST_MEMSLOT_INDEX, pages, 0);
+}
+
+#define LPI_PROP_DEFAULT_PRIO 0xa0
+
+static void configure_lpis(void)
+{
+ size_t nr_lpis = test_data.nr_devices * test_data.nr_event_ids;
+ u8 *tbl = addr_gpa2hva(vm, test_data.lpi_prop_table);
+ size_t i;
+
+ for (i = 0; i < nr_lpis; i++) {
+ tbl[i] = LPI_PROP_DEFAULT_PRIO |
+ LPI_PROP_GROUP1 |
+ LPI_PROP_ENABLED;
+ }
+}
+
+static void setup_test_data(void)
+{
+ size_t pages_per_64k = vm_calc_num_guest_pages(vm->mode, SZ_64K);
+ u32 nr_devices = test_data.nr_devices;
+ u32 nr_cpus = test_data.nr_cpus;
+ vm_paddr_t cmdq_base;
+
+ test_data.device_table = vm_phy_pages_alloc(vm, pages_per_64k,
+ gpa_base,
+ TEST_MEMSLOT_INDEX);
+
+ test_data.collection_table = vm_phy_pages_alloc(vm, pages_per_64k,
+ gpa_base,
+ TEST_MEMSLOT_INDEX);
+
+ cmdq_base = vm_phy_pages_alloc(vm, pages_per_64k, gpa_base,
+ TEST_MEMSLOT_INDEX);
+ virt_map(vm, cmdq_base, cmdq_base, pages_per_64k);
+ test_data.cmdq_base = cmdq_base;
+ test_data.cmdq_base_va = (void *)cmdq_base;
+
+ test_data.itt_tables = vm_phy_pages_alloc(vm, pages_per_64k * nr_devices,
+ gpa_base, TEST_MEMSLOT_INDEX);
+
+ test_data.lpi_prop_table = vm_phy_pages_alloc(vm, pages_per_64k,
+ gpa_base, TEST_MEMSLOT_INDEX);
+ configure_lpis();
+
+ test_data.lpi_pend_tables = vm_phy_pages_alloc(vm, pages_per_64k * nr_cpus,
+ gpa_base, TEST_MEMSLOT_INDEX);
+
+ sync_global_to_guest(vm, test_data);
+}
+
+static void setup_gic(void)
+{
+ gic_fd = vgic_v3_setup(vm, test_data.nr_cpus, 64);
+ __TEST_REQUIRE(gic_fd >= 0, "Failed to create GICv3");
+
+ its_fd = vgic_its_setup(vm);
+}
+
+static void signal_lpi(u32 device_id, u32 event_id)
+{
+ vm_paddr_t db_addr = GITS_BASE_GPA + GITS_TRANSLATER;
+
+ struct kvm_msi msi = {
+ .address_lo = db_addr,
+ .address_hi = db_addr >> 32,
+ .data = event_id,
+ .devid = device_id,
+ .flags = KVM_MSI_VALID_DEVID,
+ };
+
+ /*
+ * KVM_SIGNAL_MSI returns 1 if the MSI wasn't 'blocked' by the VM,
+ * which for arm64 implies having a valid translation in the ITS.
+ */
+ TEST_ASSERT(__vm_ioctl(vm, KVM_SIGNAL_MSI, &msi) == 1,
+ "KVM_SIGNAL_MSI ioctl failed");
+}
+
+static pthread_barrier_t test_setup_barrier;
+
+static void *lpi_worker_thread(void *data)
+{
+ u32 device_id = (size_t)data;
+ u32 event_id;
+ size_t i;
+
+ pthread_barrier_wait(&test_setup_barrier);
+
+ for (i = 0; i < nr_iterations; i++)
+ for (event_id = 0; event_id < test_data.nr_event_ids; event_id++)
+ signal_lpi(device_id, event_id);
+
+ return NULL;
+}
+
+static void *vcpu_worker_thread(void *data)
+{
+ struct kvm_vcpu *vcpu = data;
+ struct ucall uc;
+
+ while (true) {
+ vcpu_run(vcpu);
+
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_SYNC:
+ pthread_barrier_wait(&test_setup_barrier);
+ continue;
+ case UCALL_DONE:
+ return NULL;
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ break;
+ default:
+ TEST_FAIL("Unknown ucall: %lu", uc.cmd);
+ }
+ }
+
+ return NULL;
+}
+
+static void report_stats(struct timespec delta)
+{
+ double nr_lpis;
+ double time;
+
+ nr_lpis = test_data.nr_devices * test_data.nr_event_ids * nr_iterations;
+
+ time = delta.tv_sec;
+ time += ((double)delta.tv_nsec) / NSEC_PER_SEC;
+
+ pr_info("Rate: %.2f LPIs/sec\n", nr_lpis / time);
+}
+
+static void run_test(void)
+{
+ u32 nr_devices = test_data.nr_devices;
+ u32 nr_vcpus = test_data.nr_cpus;
+ pthread_t *lpi_threads = malloc(nr_devices * sizeof(pthread_t));
+ pthread_t *vcpu_threads = malloc(nr_vcpus * sizeof(pthread_t));
+ struct timespec start, delta;
+ size_t i;
+
+ TEST_ASSERT(lpi_threads && vcpu_threads, "Failed to allocate pthread arrays");
+
+ pthread_barrier_init(&test_setup_barrier, NULL, nr_vcpus + nr_devices + 1);
+
+ for (i = 0; i < nr_vcpus; i++)
+ pthread_create(&vcpu_threads[i], NULL, vcpu_worker_thread, vcpus[i]);
+
+ for (i = 0; i < nr_devices; i++)
+ pthread_create(&lpi_threads[i], NULL, lpi_worker_thread, (void *)i);
+
+ pthread_barrier_wait(&test_setup_barrier);
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+
+ for (i = 0; i < nr_devices; i++)
+ pthread_join(lpi_threads[i], NULL);
+
+ delta = timespec_elapsed(start);
+ write_guest_global(vm, test_data.request_vcpus_stop, true);
+
+ for (i = 0; i < nr_vcpus; i++)
+ pthread_join(vcpu_threads[i], NULL);
+
+ report_stats(delta);
+}
+
+static void setup_vm(void)
+{
+ int i;
+
+ vcpus = malloc(test_data.nr_cpus * sizeof(struct kvm_vcpu));
+ TEST_ASSERT(vcpus, "Failed to allocate vCPU array");
+
+ vm = vm_create_with_vcpus(test_data.nr_cpus, guest_code, vcpus);
+
+ vm_init_descriptor_tables(vm);
+ for (i = 0; i < test_data.nr_cpus; i++)
+ vcpu_init_descriptor_tables(vcpus[i]);
+
+ vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handler);
+
+ setup_memslot();
+
+ setup_gic();
+
+ setup_test_data();
+}
+
+static void destroy_vm(void)
+{
+ close(its_fd);
+ close(gic_fd);
+ kvm_vm_free(vm);
+ free(vcpus);
+}
+
+static void pr_usage(const char *name)
+{
+ pr_info("%s [-v NR_VCPUS] [-d NR_DEVICES] [-e NR_EVENTS] [-i ITERS] -h\n", name);
+ pr_info(" -v:\tnumber of vCPUs (default: %u)\n", test_data.nr_cpus);
+ pr_info(" -d:\tnumber of devices (default: %u)\n", test_data.nr_devices);
+ pr_info(" -e:\tnumber of event IDs per device (default: %u)\n", test_data.nr_event_ids);
+ pr_info(" -i:\tnumber of iterations (default: %lu)\n", nr_iterations);
+}
+
+int main(int argc, char **argv)
+{
+ u32 nr_threads;
+ int c;
+
+ while ((c = getopt(argc, argv, "hv:d:e:i:")) != -1) {
+ switch (c) {
+ case 'v':
+ test_data.nr_cpus = atoi(optarg);
+ break;
+ case 'd':
+ test_data.nr_devices = atoi(optarg);
+ break;
+ case 'e':
+ test_data.nr_event_ids = atoi(optarg);
+ break;
+ case 'i':
+ nr_iterations = strtoul(optarg, NULL, 0);
+ break;
+ case 'h':
+ default:
+ pr_usage(argv[0]);
+ return 1;
+ }
+ }
+
+ nr_threads = test_data.nr_cpus + test_data.nr_devices;
+ if (nr_threads > get_nprocs())
+ pr_info("WARNING: running %u threads on %d CPUs; performance is degraded.\n",
+ nr_threads, get_nprocs());
+
+ setup_vm();
+
+ run_test();
+
+ destroy_vm();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
index f2fb0e3f14bc..d31b9f64ba14 100644
--- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
@@ -404,9 +404,6 @@ static void guest_code(uint64_t expected_pmcr_n)
GUEST_DONE();
}
-#define GICD_BASE_GPA 0x8000000ULL
-#define GICR_BASE_GPA 0x80A0000ULL
-
/* Create a VM that has one vCPU with PMUv3 configured. */
static void create_vpmu_vm(void *guest_code)
{
@@ -438,8 +435,7 @@ static void create_vpmu_vm(void *guest_code)
init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3);
vpmu_vm.vcpu = aarch64_vcpu_add(vpmu_vm.vm, 0, &init, guest_code);
vcpu_init_descriptor_tables(vpmu_vm.vcpu);
- vpmu_vm.gic_fd = vgic_v3_setup(vpmu_vm.vm, 1, 64,
- GICD_BASE_GPA, GICR_BASE_GPA);
+ vpmu_vm.gic_fd = vgic_v3_setup(vpmu_vm.vm, 1, 64);
__TEST_REQUIRE(vpmu_vm.gic_fd >= 0,
"Failed to create vgic-v3, skipping");
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index e3e56f107f0b..0202b78f8680 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -10,7 +10,6 @@
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
-#include <poll.h>
#include <pthread.h>
#include <linux/userfaultfd.h>
#include <sys/syscall.h>
@@ -75,8 +74,20 @@ static int handle_uffd_page_request(int uffd_mode, int uffd,
copy.mode = 0;
r = ioctl(uffd, UFFDIO_COPY, &copy);
- if (r == -1) {
- pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n",
+ /*
+ * With multiple vCPU threads fault on a single page and there are
+ * multiple readers for the UFFD, at least one of the UFFDIO_COPYs
+ * will fail with EEXIST: handle that case without signaling an
+ * error.
+ *
+ * Note that this also suppress any EEXISTs occurring from,
+ * e.g., the first UFFDIO_COPY/CONTINUEs on a page. That never
+ * happens here, but a realistic VMM might potentially maintain
+ * some external state to correctly surface EEXISTs to userspace
+ * (or prevent duplicate COPY/CONTINUEs in the first place).
+ */
+ if (r == -1 && errno != EEXIST) {
+ pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d, errno = %d\n",
addr, tid, errno);
return r;
}
@@ -87,8 +98,20 @@ static int handle_uffd_page_request(int uffd_mode, int uffd,
cont.range.len = demand_paging_size;
r = ioctl(uffd, UFFDIO_CONTINUE, &cont);
- if (r == -1) {
- pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n",
+ /*
+ * With multiple vCPU threads fault on a single page and there are
+ * multiple readers for the UFFD, at least one of the UFFDIO_COPYs
+ * will fail with EEXIST: handle that case without signaling an
+ * error.
+ *
+ * Note that this also suppress any EEXISTs occurring from,
+ * e.g., the first UFFDIO_COPY/CONTINUEs on a page. That never
+ * happens here, but a realistic VMM might potentially maintain
+ * some external state to correctly surface EEXISTs to userspace
+ * (or prevent duplicate COPY/CONTINUEs in the first place).
+ */
+ if (r == -1 && errno != EEXIST) {
+ pr_info("Failed UFFDIO_CONTINUE in 0x%lx, thread %d, errno = %d\n",
addr, tid, errno);
return r;
}
@@ -108,7 +131,9 @@ static int handle_uffd_page_request(int uffd_mode, int uffd,
struct test_params {
int uffd_mode;
+ bool single_uffd;
useconds_t uffd_delay;
+ int readers_per_uffd;
enum vm_mem_backing_src_type src_type;
bool partition_vcpu_memory_access;
};
@@ -129,10 +154,12 @@ static void run_test(enum vm_guest_mode mode, void *arg)
struct memstress_vcpu_args *vcpu_args;
struct test_params *p = arg;
struct uffd_desc **uffd_descs = NULL;
+ uint64_t uffd_region_size;
struct timespec start;
struct timespec ts_diff;
+ double vcpu_paging_rate;
struct kvm_vm *vm;
- int i;
+ int i, num_uffds = 0;
vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
p->src_type, p->partition_vcpu_memory_access);
@@ -145,7 +172,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
memset(guest_data_prototype, 0xAB, demand_paging_size);
if (p->uffd_mode == UFFDIO_REGISTER_MODE_MINOR) {
- for (i = 0; i < nr_vcpus; i++) {
+ num_uffds = p->single_uffd ? 1 : nr_vcpus;
+ for (i = 0; i < num_uffds; i++) {
vcpu_args = &memstress_args.vcpu_args[i];
prefault_mem(addr_gpa2alias(vm, vcpu_args->gpa),
vcpu_args->pages * memstress_args.guest_page_size);
@@ -153,9 +181,13 @@ static void run_test(enum vm_guest_mode mode, void *arg)
}
if (p->uffd_mode) {
- uffd_descs = malloc(nr_vcpus * sizeof(struct uffd_desc *));
+ num_uffds = p->single_uffd ? 1 : nr_vcpus;
+ uffd_region_size = nr_vcpus * guest_percpu_mem_size / num_uffds;
+
+ uffd_descs = malloc(num_uffds * sizeof(struct uffd_desc *));
TEST_ASSERT(uffd_descs, "Memory allocation failed");
- for (i = 0; i < nr_vcpus; i++) {
+ for (i = 0; i < num_uffds; i++) {
+ struct memstress_vcpu_args *vcpu_args;
void *vcpu_hva;
vcpu_args = &memstress_args.vcpu_args[i];
@@ -168,7 +200,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
*/
uffd_descs[i] = uffd_setup_demand_paging(
p->uffd_mode, p->uffd_delay, vcpu_hva,
- vcpu_args->pages * memstress_args.guest_page_size,
+ uffd_region_size,
+ p->readers_per_uffd,
&handle_uffd_page_request);
}
}
@@ -185,15 +218,19 @@ static void run_test(enum vm_guest_mode mode, void *arg)
if (p->uffd_mode) {
/* Tell the user fault fd handler threads to quit */
- for (i = 0; i < nr_vcpus; i++)
+ for (i = 0; i < num_uffds; i++)
uffd_stop_demand_paging(uffd_descs[i]);
}
- pr_info("Total guest execution time: %ld.%.9lds\n",
+ pr_info("Total guest execution time:\t%ld.%.9lds\n",
ts_diff.tv_sec, ts_diff.tv_nsec);
- pr_info("Overall demand paging rate: %f pgs/sec\n",
- memstress_args.vcpu_args[0].pages * nr_vcpus /
- ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC));
+
+ vcpu_paging_rate = memstress_args.vcpu_args[0].pages /
+ ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC);
+ pr_info("Per-vcpu demand paging rate:\t%f pgs/sec/vcpu\n",
+ vcpu_paging_rate);
+ pr_info("Overall demand paging rate:\t%f pgs/sec\n",
+ vcpu_paging_rate * nr_vcpus);
memstress_destroy_vm(vm);
@@ -205,15 +242,20 @@ static void run_test(enum vm_guest_mode mode, void *arg)
static void help(char *name)
{
puts("");
- printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n"
- " [-b memory] [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name);
+ printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-a]\n"
+ " [-d uffd_delay_usec] [-r readers_per_uffd] [-b memory]\n"
+ " [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name);
guest_modes_help();
printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n"
" UFFD registration mode: 'MISSING' or 'MINOR'.\n");
kvm_print_vcpu_pinning_help();
+ printf(" -a: Use a single userfaultfd for all of guest memory, instead of\n"
+ " creating one for each region paged by a unique vCPU\n"
+ " Set implicitly with -o, and no effect without -u.\n");
printf(" -d: add a delay in usec to the User Fault\n"
" FD handler to simulate demand paging\n"
" overheads. Ignored without -u.\n");
+ printf(" -r: Set the number of reader threads per uffd.\n");
printf(" -b: specify the size of the memory region which should be\n"
" demand paged by each vCPU. e.g. 10M or 3G.\n"
" Default: 1G\n");
@@ -232,12 +274,14 @@ int main(int argc, char *argv[])
struct test_params p = {
.src_type = DEFAULT_VM_MEM_SRC,
.partition_vcpu_memory_access = true,
+ .readers_per_uffd = 1,
+ .single_uffd = false,
};
int opt;
guest_modes_append_default();
- while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:c:o")) != -1) {
+ while ((opt = getopt(argc, argv, "ahom:u:d:b:s:v:c:r:")) != -1) {
switch (opt) {
case 'm':
guest_modes_cmdline(optarg);
@@ -249,6 +293,9 @@ int main(int argc, char *argv[])
p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR;
TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'.");
break;
+ case 'a':
+ p.single_uffd = true;
+ break;
case 'd':
p.uffd_delay = strtoul(optarg, NULL, 0);
TEST_ASSERT(p.uffd_delay >= 0, "A negative UFFD delay is not supported.");
@@ -269,6 +316,13 @@ int main(int argc, char *argv[])
break;
case 'o':
p.partition_vcpu_memory_access = false;
+ p.single_uffd = true;
+ break;
+ case 'r':
+ p.readers_per_uffd = atoi(optarg);
+ TEST_ASSERT(p.readers_per_uffd >= 1,
+ "Invalid number of readers per uffd %d: must be >=1",
+ p.readers_per_uffd);
break;
case 'h':
default:
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 89fdb461aff8..9f24303acb8c 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -23,9 +23,6 @@
#ifdef __aarch64__
#include "aarch64/vgic.h"
-#define GICD_BASE_GPA 0x8000000ULL
-#define GICR_BASE_GPA 0x80A0000ULL
-
static int gic_fd;
static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
@@ -34,7 +31,7 @@ static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
* The test can still run even if hardware does not support GICv3, as it
* is only an optimization to reduce guest exits.
*/
- gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+ gic_fd = vgic_v3_setup(vm, nr_vcpus, 64);
}
static void arch_cleanup_vm(struct kvm_vm *vm)
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/aarch64/gic.h
index b217ea17cac5..baeb3c859389 100644
--- a/tools/testing/selftests/kvm/include/aarch64/gic.h
+++ b/tools/testing/selftests/kvm/include/aarch64/gic.h
@@ -6,11 +6,26 @@
#ifndef SELFTEST_KVM_GIC_H
#define SELFTEST_KVM_GIC_H
+#include <asm/kvm.h>
+
enum gic_type {
GIC_V3,
GIC_TYPE_MAX,
};
+/*
+ * Note that the redistributor frames are at the end, as the range scales
+ * with the number of vCPUs in the VM.
+ */
+#define GITS_BASE_GPA 0x8000000ULL
+#define GICD_BASE_GPA (GITS_BASE_GPA + KVM_VGIC_V3_ITS_SIZE)
+#define GICR_BASE_GPA (GICD_BASE_GPA + KVM_VGIC_V3_DIST_SIZE)
+
+/* The GIC is identity-mapped into the guest at the time of setup. */
+#define GITS_BASE_GVA ((volatile void *)GITS_BASE_GPA)
+#define GICD_BASE_GVA ((volatile void *)GICD_BASE_GPA)
+#define GICR_BASE_GVA ((volatile void *)GICR_BASE_GPA)
+
#define MIN_SGI 0
#define MIN_PPI 16
#define MIN_SPI 32
@@ -21,8 +36,7 @@ enum gic_type {
#define INTID_IS_PPI(intid) (MIN_PPI <= (intid) && (intid) < MIN_SPI)
#define INTID_IS_SPI(intid) (MIN_SPI <= (intid) && (intid) <= MAX_SPI)
-void gic_init(enum gic_type type, unsigned int nr_cpus,
- void *dist_base, void *redist_base);
+void gic_init(enum gic_type type, unsigned int nr_cpus);
void gic_irq_enable(unsigned int intid);
void gic_irq_disable(unsigned int intid);
unsigned int gic_get_and_ack_irq(void);
@@ -44,4 +58,7 @@ void gic_irq_clear_pending(unsigned int intid);
bool gic_irq_get_pending(unsigned int intid);
void gic_irq_set_config(unsigned int intid, bool is_edge);
+void gic_rdist_enable_lpis(vm_paddr_t cfg_table, size_t cfg_table_size,
+ vm_paddr_t pend_table);
+
#endif /* SELFTEST_KVM_GIC_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic_v3.h b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
index ba0886e8a2bb..a76615fa39a1 100644
--- a/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
+++ b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
@@ -1,82 +1,604 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
- * ARM Generic Interrupt Controller (GIC) v3 specific defines
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
*/
-
-#ifndef SELFTEST_KVM_GICV3_H
-#define SELFTEST_KVM_GICV3_H
-
-#include <asm/sysreg.h>
+#ifndef __SELFTESTS_GIC_V3_H
+#define __SELFTESTS_GIC_V3_H
/*
- * Distributor registers
+ * Distributor registers. We assume we're running non-secure, with ARE
+ * being set. Secure-only and non-ARE registers are not described.
*/
#define GICD_CTLR 0x0000
#define GICD_TYPER 0x0004
+#define GICD_IIDR 0x0008
+#define GICD_TYPER2 0x000C
+#define GICD_STATUSR 0x0010
+#define GICD_SETSPI_NSR 0x0040
+#define GICD_CLRSPI_NSR 0x0048
+#define GICD_SETSPI_SR 0x0050
+#define GICD_CLRSPI_SR 0x0058
#define GICD_IGROUPR 0x0080
#define GICD_ISENABLER 0x0100
#define GICD_ICENABLER 0x0180
#define GICD_ISPENDR 0x0200
#define GICD_ICPENDR 0x0280
-#define GICD_ICACTIVER 0x0380
#define GICD_ISACTIVER 0x0300
+#define GICD_ICACTIVER 0x0380
#define GICD_IPRIORITYR 0x0400
#define GICD_ICFGR 0x0C00
+#define GICD_IGRPMODR 0x0D00
+#define GICD_NSACR 0x0E00
+#define GICD_IGROUPRnE 0x1000
+#define GICD_ISENABLERnE 0x1200
+#define GICD_ICENABLERnE 0x1400
+#define GICD_ISPENDRnE 0x1600
+#define GICD_ICPENDRnE 0x1800
+#define GICD_ISACTIVERnE 0x1A00
+#define GICD_ICACTIVERnE 0x1C00
+#define GICD_IPRIORITYRnE 0x2000
+#define GICD_ICFGRnE 0x3000
+#define GICD_IROUTER 0x6000
+#define GICD_IROUTERnE 0x8000
+#define GICD_IDREGS 0xFFD0
+#define GICD_PIDR2 0xFFE8
+
+#define ESPI_BASE_INTID 4096
/*
- * The assumption is that the guest runs in a non-secure mode.
- * The following bits of GICD_CTLR are defined accordingly.
+ * Those registers are actually from GICv2, but the spec demands that they
+ * are implemented as RES0 if ARE is 1 (which we do in KVM's emulated GICv3).
*/
+#define GICD_ITARGETSR 0x0800
+#define GICD_SGIR 0x0F00
+#define GICD_CPENDSGIR 0x0F10
+#define GICD_SPENDSGIR 0x0F20
+
#define GICD_CTLR_RWP (1U << 31)
#define GICD_CTLR_nASSGIreq (1U << 8)
+#define GICD_CTLR_DS (1U << 6)
#define GICD_CTLR_ARE_NS (1U << 4)
#define GICD_CTLR_ENABLE_G1A (1U << 1)
#define GICD_CTLR_ENABLE_G1 (1U << 0)
+#define GICD_IIDR_IMPLEMENTER_SHIFT 0
+#define GICD_IIDR_IMPLEMENTER_MASK (0xfff << GICD_IIDR_IMPLEMENTER_SHIFT)
+#define GICD_IIDR_REVISION_SHIFT 12
+#define GICD_IIDR_REVISION_MASK (0xf << GICD_IIDR_REVISION_SHIFT)
+#define GICD_IIDR_VARIANT_SHIFT 16
+#define GICD_IIDR_VARIANT_MASK (0xf << GICD_IIDR_VARIANT_SHIFT)
+#define GICD_IIDR_PRODUCT_ID_SHIFT 24
+#define GICD_IIDR_PRODUCT_ID_MASK (0xff << GICD_IIDR_PRODUCT_ID_SHIFT)
+
+
+/*
+ * In systems with a single security state (what we emulate in KVM)
+ * the meaning of the interrupt group enable bits is slightly different
+ */
+#define GICD_CTLR_ENABLE_SS_G1 (1U << 1)
+#define GICD_CTLR_ENABLE_SS_G0 (1U << 0)
+
+#define GICD_TYPER_RSS (1U << 26)
+#define GICD_TYPER_LPIS (1U << 17)
+#define GICD_TYPER_MBIS (1U << 16)
+#define GICD_TYPER_ESPI (1U << 8)
+
+#define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1)
+#define GICD_TYPER_NUM_LPIS(typer) ((((typer) >> 11) & 0x1f) + 1)
#define GICD_TYPER_SPIS(typer) ((((typer) & 0x1f) + 1) * 32)
-#define GICD_INT_DEF_PRI_X4 0xa0a0a0a0
+#define GICD_TYPER_ESPIS(typer) \
+ (((typer) & GICD_TYPER_ESPI) ? GICD_TYPER_SPIS((typer) >> 27) : 0)
+
+#define GICD_TYPER2_nASSGIcap (1U << 8)
+#define GICD_TYPER2_VIL (1U << 7)
+#define GICD_TYPER2_VID GENMASK(4, 0)
+
+#define GICD_IROUTER_SPI_MODE_ONE (0U << 31)
+#define GICD_IROUTER_SPI_MODE_ANY (1U << 31)
+
+#define GIC_PIDR2_ARCH_MASK 0xf0
+#define GIC_PIDR2_ARCH_GICv3 0x30
+#define GIC_PIDR2_ARCH_GICv4 0x40
+
+#define GIC_V3_DIST_SIZE 0x10000
+
+#define GIC_PAGE_SIZE_4K 0ULL
+#define GIC_PAGE_SIZE_16K 1ULL
+#define GIC_PAGE_SIZE_64K 2ULL
+#define GIC_PAGE_SIZE_MASK 3ULL
/*
- * Redistributor registers
+ * Re-Distributor registers, offsets from RD_base
*/
-#define GICR_CTLR 0x000
-#define GICR_WAKER 0x014
+#define GICR_CTLR GICD_CTLR
+#define GICR_IIDR 0x0004
+#define GICR_TYPER 0x0008
+#define GICR_STATUSR GICD_STATUSR
+#define GICR_WAKER 0x0014
+#define GICR_SETLPIR 0x0040
+#define GICR_CLRLPIR 0x0048
+#define GICR_PROPBASER 0x0070
+#define GICR_PENDBASER 0x0078
+#define GICR_INVLPIR 0x00A0
+#define GICR_INVALLR 0x00B0
+#define GICR_SYNCR 0x00C0
+#define GICR_IDREGS GICD_IDREGS
+#define GICR_PIDR2 GICD_PIDR2
+
+#define GICR_CTLR_ENABLE_LPIS (1UL << 0)
+#define GICR_CTLR_CES (1UL << 1)
+#define GICR_CTLR_IR (1UL << 2)
+#define GICR_CTLR_RWP (1UL << 3)
-#define GICR_CTLR_RWP (1U << 3)
+#define GICR_TYPER_CPU_NUMBER(r) (((r) >> 8) & 0xffff)
+
+#define EPPI_BASE_INTID 1056
+
+#define GICR_TYPER_NR_PPIS(r) \
+ ({ \
+ unsigned int __ppinum = ((r) >> 27) & 0x1f; \
+ unsigned int __nr_ppis = 16; \
+ if (__ppinum == 1 || __ppinum == 2) \
+ __nr_ppis += __ppinum * 32; \
+ \
+ __nr_ppis; \
+ })
#define GICR_WAKER_ProcessorSleep (1U << 1)
#define GICR_WAKER_ChildrenAsleep (1U << 2)
+#define GIC_BASER_CACHE_nCnB 0ULL
+#define GIC_BASER_CACHE_SameAsInner 0ULL
+#define GIC_BASER_CACHE_nC 1ULL
+#define GIC_BASER_CACHE_RaWt 2ULL
+#define GIC_BASER_CACHE_RaWb 3ULL
+#define GIC_BASER_CACHE_WaWt 4ULL
+#define GIC_BASER_CACHE_WaWb 5ULL
+#define GIC_BASER_CACHE_RaWaWt 6ULL
+#define GIC_BASER_CACHE_RaWaWb 7ULL
+#define GIC_BASER_CACHE_MASK 7ULL
+#define GIC_BASER_NonShareable 0ULL
+#define GIC_BASER_InnerShareable 1ULL
+#define GIC_BASER_OuterShareable 2ULL
+#define GIC_BASER_SHAREABILITY_MASK 3ULL
+
+#define GIC_BASER_CACHEABILITY(reg, inner_outer, type) \
+ (GIC_BASER_CACHE_##type << reg##_##inner_outer##_CACHEABILITY_SHIFT)
+
+#define GIC_BASER_SHAREABILITY(reg, type) \
+ (GIC_BASER_##type << reg##_SHAREABILITY_SHIFT)
+
+/* encode a size field of width @w containing @n - 1 units */
+#define GIC_ENCODE_SZ(n, w) (((unsigned long)(n) - 1) & GENMASK_ULL(((w) - 1), 0))
+
+#define GICR_PROPBASER_SHAREABILITY_SHIFT (10)
+#define GICR_PROPBASER_INNER_CACHEABILITY_SHIFT (7)
+#define GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT (56)
+#define GICR_PROPBASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GICR_PROPBASER, SHAREABILITY_MASK)
+#define GICR_PROPBASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, MASK)
+#define GICR_PROPBASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, MASK)
+#define GICR_PROPBASER_CACHEABILITY_MASK GICR_PROPBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_PROPBASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable)
+
+#define GICR_PROPBASER_nCnB GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nCnB)
+#define GICR_PROPBASER_nC GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nC)
+#define GICR_PROPBASER_RaWt GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWt)
+#define GICR_PROPBASER_RaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWb)
+#define GICR_PROPBASER_WaWt GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWt)
+#define GICR_PROPBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWb)
+#define GICR_PROPBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWt)
+#define GICR_PROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWb)
+
+#define GICR_PROPBASER_IDBITS_MASK (0x1f)
+#define GICR_PROPBASER_ADDRESS(x) ((x) & GENMASK_ULL(51, 12))
+#define GICR_PENDBASER_ADDRESS(x) ((x) & GENMASK_ULL(51, 16))
+
+#define GICR_PENDBASER_SHAREABILITY_SHIFT (10)
+#define GICR_PENDBASER_INNER_CACHEABILITY_SHIFT (7)
+#define GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT (56)
+#define GICR_PENDBASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GICR_PENDBASER, SHAREABILITY_MASK)
+#define GICR_PENDBASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, MASK)
+#define GICR_PENDBASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, MASK)
+#define GICR_PENDBASER_CACHEABILITY_MASK GICR_PENDBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_PENDBASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)
+
+#define GICR_PENDBASER_nCnB GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nCnB)
+#define GICR_PENDBASER_nC GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nC)
+#define GICR_PENDBASER_RaWt GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWt)
+#define GICR_PENDBASER_RaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWb)
+#define GICR_PENDBASER_WaWt GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWt)
+#define GICR_PENDBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWb)
+#define GICR_PENDBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWt)
+#define GICR_PENDBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWb)
+
+#define GICR_PENDBASER_PTZ BIT_ULL(62)
+
/*
- * Redistributor registers, offsets from SGI base
+ * Re-Distributor registers, offsets from SGI_base
*/
#define GICR_IGROUPR0 GICD_IGROUPR
#define GICR_ISENABLER0 GICD_ISENABLER
#define GICR_ICENABLER0 GICD_ICENABLER
#define GICR_ISPENDR0 GICD_ISPENDR
+#define GICR_ICPENDR0 GICD_ICPENDR
#define GICR_ISACTIVER0 GICD_ISACTIVER
#define GICR_ICACTIVER0 GICD_ICACTIVER
-#define GICR_ICENABLER GICD_ICENABLER
-#define GICR_ICACTIVER GICD_ICACTIVER
#define GICR_IPRIORITYR0 GICD_IPRIORITYR
+#define GICR_ICFGR0 GICD_ICFGR
+#define GICR_IGRPMODR0 GICD_IGRPMODR
+#define GICR_NSACR GICD_NSACR
+
+#define GICR_TYPER_PLPIS (1U << 0)
+#define GICR_TYPER_VLPIS (1U << 1)
+#define GICR_TYPER_DIRTY (1U << 2)
+#define GICR_TYPER_DirectLPIS (1U << 3)
+#define GICR_TYPER_LAST (1U << 4)
+#define GICR_TYPER_RVPEID (1U << 7)
+#define GICR_TYPER_COMMON_LPI_AFF GENMASK_ULL(25, 24)
+#define GICR_TYPER_AFFINITY GENMASK_ULL(63, 32)
+
+#define GICR_INVLPIR_INTID GENMASK_ULL(31, 0)
+#define GICR_INVLPIR_VPEID GENMASK_ULL(47, 32)
+#define GICR_INVLPIR_V GENMASK_ULL(63, 63)
+
+#define GICR_INVALLR_VPEID GICR_INVLPIR_VPEID
+#define GICR_INVALLR_V GICR_INVLPIR_V
+
+#define GIC_V3_REDIST_SIZE 0x20000
+
+#define LPI_PROP_GROUP1 (1 << 1)
+#define LPI_PROP_ENABLED (1 << 0)
+
+/*
+ * Re-Distributor registers, offsets from VLPI_base
+ */
+#define GICR_VPROPBASER 0x0070
+
+#define GICR_VPROPBASER_IDBITS_MASK 0x1f
+
+#define GICR_VPROPBASER_SHAREABILITY_SHIFT (10)
+#define GICR_VPROPBASER_INNER_CACHEABILITY_SHIFT (7)
+#define GICR_VPROPBASER_OUTER_CACHEABILITY_SHIFT (56)
+
+#define GICR_VPROPBASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GICR_VPROPBASER, SHAREABILITY_MASK)
+#define GICR_VPROPBASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, MASK)
+#define GICR_VPROPBASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_VPROPBASER, OUTER, MASK)
+#define GICR_VPROPBASER_CACHEABILITY_MASK \
+ GICR_VPROPBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_VPROPBASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GICR_VPROPBASER, InnerShareable)
+
+#define GICR_VPROPBASER_nCnB GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, nCnB)
+#define GICR_VPROPBASER_nC GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, nC)
+#define GICR_VPROPBASER_RaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWt)
+#define GICR_VPROPBASER_RaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWb)
+#define GICR_VPROPBASER_WaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, WaWt)
+#define GICR_VPROPBASER_WaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, WaWb)
+#define GICR_VPROPBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWt)
+#define GICR_VPROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWb)
+
+/*
+ * GICv4.1 VPROPBASER reinvention. A subtle mix between the old
+ * VPROPBASER and ITS_BASER. Just not quite any of the two.
+ */
+#define GICR_VPROPBASER_4_1_VALID (1ULL << 63)
+#define GICR_VPROPBASER_4_1_ENTRY_SIZE GENMASK_ULL(61, 59)
+#define GICR_VPROPBASER_4_1_INDIRECT (1ULL << 55)
+#define GICR_VPROPBASER_4_1_PAGE_SIZE GENMASK_ULL(54, 53)
+#define GICR_VPROPBASER_4_1_Z (1ULL << 52)
+#define GICR_VPROPBASER_4_1_ADDR GENMASK_ULL(51, 12)
+#define GICR_VPROPBASER_4_1_SIZE GENMASK_ULL(6, 0)
+
+#define GICR_VPENDBASER 0x0078
+
+#define GICR_VPENDBASER_SHAREABILITY_SHIFT (10)
+#define GICR_VPENDBASER_INNER_CACHEABILITY_SHIFT (7)
+#define GICR_VPENDBASER_OUTER_CACHEABILITY_SHIFT (56)
+#define GICR_VPENDBASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GICR_VPENDBASER, SHAREABILITY_MASK)
+#define GICR_VPENDBASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, MASK)
+#define GICR_VPENDBASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GICR_VPENDBASER, OUTER, MASK)
+#define GICR_VPENDBASER_CACHEABILITY_MASK \
+ GICR_VPENDBASER_INNER_CACHEABILITY_MASK
+
+#define GICR_VPENDBASER_NonShareable \
+ GIC_BASER_SHAREABILITY(GICR_VPENDBASER, NonShareable)
+
+#define GICR_VPENDBASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GICR_VPENDBASER, InnerShareable)
+
+#define GICR_VPENDBASER_nCnB GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nCnB)
+#define GICR_VPENDBASER_nC GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nC)
+#define GICR_VPENDBASER_RaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWt)
+#define GICR_VPENDBASER_RaWb GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWb)
+#define GICR_VPENDBASER_WaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, WaWt)
+#define GICR_VPENDBASER_WaWb GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, WaWb)
+#define GICR_VPENDBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWaWt)
+#define GICR_VPENDBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWaWb)
+
+#define GICR_VPENDBASER_Dirty (1ULL << 60)
+#define GICR_VPENDBASER_PendingLast (1ULL << 61)
+#define GICR_VPENDBASER_IDAI (1ULL << 62)
+#define GICR_VPENDBASER_Valid (1ULL << 63)
+
+/*
+ * GICv4.1 VPENDBASER, used for VPE residency. On top of these fields,
+ * also use the above Valid, PendingLast and Dirty.
+ */
+#define GICR_VPENDBASER_4_1_DB (1ULL << 62)
+#define GICR_VPENDBASER_4_1_VGRP0EN (1ULL << 59)
+#define GICR_VPENDBASER_4_1_VGRP1EN (1ULL << 58)
+#define GICR_VPENDBASER_4_1_VPEID GENMASK_ULL(15, 0)
+
+#define GICR_VSGIR 0x0080
+
+#define GICR_VSGIR_VPEID GENMASK(15, 0)
+
+#define GICR_VSGIPENDR 0x0088
+
+#define GICR_VSGIPENDR_BUSY (1U << 31)
+#define GICR_VSGIPENDR_PENDING GENMASK(15, 0)
+
+/*
+ * ITS registers, offsets from ITS_base
+ */
+#define GITS_CTLR 0x0000
+#define GITS_IIDR 0x0004
+#define GITS_TYPER 0x0008
+#define GITS_MPIDR 0x0018
+#define GITS_CBASER 0x0080
+#define GITS_CWRITER 0x0088
+#define GITS_CREADR 0x0090
+#define GITS_BASER 0x0100
+#define GITS_IDREGS_BASE 0xffd0
+#define GITS_PIDR0 0xffe0
+#define GITS_PIDR1 0xffe4
+#define GITS_PIDR2 GICR_PIDR2
+#define GITS_PIDR4 0xffd0
+#define GITS_CIDR0 0xfff0
+#define GITS_CIDR1 0xfff4
+#define GITS_CIDR2 0xfff8
+#define GITS_CIDR3 0xfffc
+
+#define GITS_TRANSLATER 0x10040
+
+#define GITS_SGIR 0x20020
+
+#define GITS_SGIR_VPEID GENMASK_ULL(47, 32)
+#define GITS_SGIR_VINTID GENMASK_ULL(3, 0)
+
+#define GITS_CTLR_ENABLE (1U << 0)
+#define GITS_CTLR_ImDe (1U << 1)
+#define GITS_CTLR_ITS_NUMBER_SHIFT 4
+#define GITS_CTLR_ITS_NUMBER (0xFU << GITS_CTLR_ITS_NUMBER_SHIFT)
+#define GITS_CTLR_QUIESCENT (1U << 31)
+
+#define GITS_TYPER_PLPIS (1UL << 0)
+#define GITS_TYPER_VLPIS (1UL << 1)
+#define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4
+#define GITS_TYPER_ITT_ENTRY_SIZE GENMASK_ULL(7, 4)
+#define GITS_TYPER_IDBITS_SHIFT 8
+#define GITS_TYPER_DEVBITS_SHIFT 13
+#define GITS_TYPER_DEVBITS GENMASK_ULL(17, 13)
+#define GITS_TYPER_PTA (1UL << 19)
+#define GITS_TYPER_HCC_SHIFT 24
+#define GITS_TYPER_HCC(r) (((r) >> GITS_TYPER_HCC_SHIFT) & 0xff)
+#define GITS_TYPER_VMOVP (1ULL << 37)
+#define GITS_TYPER_VMAPP (1ULL << 40)
+#define GITS_TYPER_SVPET GENMASK_ULL(42, 41)
-/* CPU interface registers */
-#define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
-#define SYS_ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0)
-#define SYS_ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1)
-#define SYS_ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1)
-#define SYS_ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
-#define SYS_ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
-#define SYS_ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+#define GITS_IIDR_REV_SHIFT 12
+#define GITS_IIDR_REV_MASK (0xf << GITS_IIDR_REV_SHIFT)
+#define GITS_IIDR_REV(r) (((r) >> GITS_IIDR_REV_SHIFT) & 0xf)
+#define GITS_IIDR_PRODUCTID_SHIFT 24
-#define SYS_ICV_AP1R0_EL1 sys_reg(3, 0, 12, 9, 0)
+#define GITS_CBASER_VALID (1ULL << 63)
+#define GITS_CBASER_SHAREABILITY_SHIFT (10)
+#define GITS_CBASER_INNER_CACHEABILITY_SHIFT (59)
+#define GITS_CBASER_OUTER_CACHEABILITY_SHIFT (53)
+#define GITS_CBASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GITS_CBASER, SHAREABILITY_MASK)
+#define GITS_CBASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, MASK)
+#define GITS_CBASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GITS_CBASER, OUTER, MASK)
+#define GITS_CBASER_CACHEABILITY_MASK GITS_CBASER_INNER_CACHEABILITY_MASK
-#define ICC_PMR_DEF_PRIO 0xf0
+#define GITS_CBASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GITS_CBASER, InnerShareable)
+#define GITS_CBASER_nCnB GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nCnB)
+#define GITS_CBASER_nC GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nC)
+#define GITS_CBASER_RaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWt)
+#define GITS_CBASER_RaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWb)
+#define GITS_CBASER_WaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWt)
+#define GITS_CBASER_WaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWb)
+#define GITS_CBASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWt)
+#define GITS_CBASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWb)
+
+#define GITS_CBASER_ADDRESS(cbaser) ((cbaser) & GENMASK_ULL(51, 12))
+
+#define GITS_BASER_NR_REGS 8
+
+#define GITS_BASER_VALID (1ULL << 63)
+#define GITS_BASER_INDIRECT (1ULL << 62)
+
+#define GITS_BASER_INNER_CACHEABILITY_SHIFT (59)
+#define GITS_BASER_OUTER_CACHEABILITY_SHIFT (53)
+#define GITS_BASER_INNER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GITS_BASER, INNER, MASK)
+#define GITS_BASER_CACHEABILITY_MASK GITS_BASER_INNER_CACHEABILITY_MASK
+#define GITS_BASER_OUTER_CACHEABILITY_MASK \
+ GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, MASK)
+#define GITS_BASER_SHAREABILITY_MASK \
+ GIC_BASER_SHAREABILITY(GITS_BASER, SHAREABILITY_MASK)
+
+#define GITS_BASER_nCnB GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nCnB)
+#define GITS_BASER_nC GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nC)
+#define GITS_BASER_RaWt GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWt)
+#define GITS_BASER_RaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb)
+#define GITS_BASER_WaWt GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWt)
+#define GITS_BASER_WaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWb)
+#define GITS_BASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWt)
+#define GITS_BASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWb)
+
+#define GITS_BASER_TYPE_SHIFT (56)
+#define GITS_BASER_TYPE(r) (((r) >> GITS_BASER_TYPE_SHIFT) & 7)
+#define GITS_BASER_ENTRY_SIZE_SHIFT (48)
+#define GITS_BASER_ENTRY_SIZE(r) ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
+#define GITS_BASER_ENTRY_SIZE_MASK GENMASK_ULL(52, 48)
+#define GITS_BASER_PHYS_52_to_48(phys) \
+ (((phys) & GENMASK_ULL(47, 16)) | (((phys) >> 48) & 0xf) << 12)
+#define GITS_BASER_ADDR_48_to_52(baser) \
+ (((baser) & GENMASK_ULL(47, 16)) | (((baser) >> 12) & 0xf) << 48)
+
+#define GITS_BASER_SHAREABILITY_SHIFT (10)
+#define GITS_BASER_InnerShareable \
+ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
+#define GITS_BASER_PAGE_SIZE_SHIFT (8)
+#define __GITS_BASER_PSZ(sz) (GIC_PAGE_SIZE_ ## sz << GITS_BASER_PAGE_SIZE_SHIFT)
+#define GITS_BASER_PAGE_SIZE_4K __GITS_BASER_PSZ(4K)
+#define GITS_BASER_PAGE_SIZE_16K __GITS_BASER_PSZ(16K)
+#define GITS_BASER_PAGE_SIZE_64K __GITS_BASER_PSZ(64K)
+#define GITS_BASER_PAGE_SIZE_MASK __GITS_BASER_PSZ(MASK)
+#define GITS_BASER_PAGES_MAX 256
+#define GITS_BASER_PAGES_SHIFT (0)
+#define GITS_BASER_NR_PAGES(r) (((r) & 0xff) + 1)
+
+#define GITS_BASER_TYPE_NONE 0
+#define GITS_BASER_TYPE_DEVICE 1
+#define GITS_BASER_TYPE_VCPU 2
+#define GITS_BASER_TYPE_RESERVED3 3
+#define GITS_BASER_TYPE_COLLECTION 4
+#define GITS_BASER_TYPE_RESERVED5 5
+#define GITS_BASER_TYPE_RESERVED6 6
+#define GITS_BASER_TYPE_RESERVED7 7
+
+#define GITS_LVL1_ENTRY_SIZE (8UL)
+
+/*
+ * ITS commands
+ */
+#define GITS_CMD_MAPD 0x08
+#define GITS_CMD_MAPC 0x09
+#define GITS_CMD_MAPTI 0x0a
+#define GITS_CMD_MAPI 0x0b
+#define GITS_CMD_MOVI 0x01
+#define GITS_CMD_DISCARD 0x0f
+#define GITS_CMD_INV 0x0c
+#define GITS_CMD_MOVALL 0x0e
+#define GITS_CMD_INVALL 0x0d
+#define GITS_CMD_INT 0x03
+#define GITS_CMD_CLEAR 0x04
+#define GITS_CMD_SYNC 0x05
+
+/*
+ * GICv4 ITS specific commands
+ */
+#define GITS_CMD_GICv4(x) ((x) | 0x20)
+#define GITS_CMD_VINVALL GITS_CMD_GICv4(GITS_CMD_INVALL)
+#define GITS_CMD_VMAPP GITS_CMD_GICv4(GITS_CMD_MAPC)
+#define GITS_CMD_VMAPTI GITS_CMD_GICv4(GITS_CMD_MAPTI)
+#define GITS_CMD_VMOVI GITS_CMD_GICv4(GITS_CMD_MOVI)
+#define GITS_CMD_VSYNC GITS_CMD_GICv4(GITS_CMD_SYNC)
+/* VMOVP, VSGI and INVDB are the odd ones, as they dont have a physical counterpart */
+#define GITS_CMD_VMOVP GITS_CMD_GICv4(2)
+#define GITS_CMD_VSGI GITS_CMD_GICv4(3)
+#define GITS_CMD_INVDB GITS_CMD_GICv4(0xe)
+
+/*
+ * ITS error numbers
+ */
+#define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107
+#define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109
+#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307
+#define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507
+#define E_ITS_MAPD_DEVICE_OOR 0x010801
+#define E_ITS_MAPD_ITTSIZE_OOR 0x010802
+#define E_ITS_MAPC_PROCNUM_OOR 0x010902
+#define E_ITS_MAPC_COLLECTION_OOR 0x010903
+#define E_ITS_MAPTI_UNMAPPED_DEVICE 0x010a04
+#define E_ITS_MAPTI_ID_OOR 0x010a05
+#define E_ITS_MAPTI_PHYSICALID_OOR 0x010a06
+#define E_ITS_INV_UNMAPPED_INTERRUPT 0x010c07
+#define E_ITS_INVALL_UNMAPPED_COLLECTION 0x010d09
+#define E_ITS_MOVALL_PROCNUM_OOR 0x010e01
+#define E_ITS_DISCARD_UNMAPPED_INTERRUPT 0x010f07
+
+/*
+ * CPU interface registers
+ */
+#define ICC_CTLR_EL1_EOImode_SHIFT (1)
+#define ICC_CTLR_EL1_EOImode_drop_dir (0U << ICC_CTLR_EL1_EOImode_SHIFT)
+#define ICC_CTLR_EL1_EOImode_drop (1U << ICC_CTLR_EL1_EOImode_SHIFT)
+#define ICC_CTLR_EL1_EOImode_MASK (1 << ICC_CTLR_EL1_EOImode_SHIFT)
+#define ICC_CTLR_EL1_CBPR_SHIFT 0
+#define ICC_CTLR_EL1_CBPR_MASK (1 << ICC_CTLR_EL1_CBPR_SHIFT)
+#define ICC_CTLR_EL1_PMHE_SHIFT 6
+#define ICC_CTLR_EL1_PMHE_MASK (1 << ICC_CTLR_EL1_PMHE_SHIFT)
+#define ICC_CTLR_EL1_PRI_BITS_SHIFT 8
+#define ICC_CTLR_EL1_PRI_BITS_MASK (0x7 << ICC_CTLR_EL1_PRI_BITS_SHIFT)
+#define ICC_CTLR_EL1_ID_BITS_SHIFT 11
+#define ICC_CTLR_EL1_ID_BITS_MASK (0x7 << ICC_CTLR_EL1_ID_BITS_SHIFT)
+#define ICC_CTLR_EL1_SEIS_SHIFT 14
+#define ICC_CTLR_EL1_SEIS_MASK (0x1 << ICC_CTLR_EL1_SEIS_SHIFT)
+#define ICC_CTLR_EL1_A3V_SHIFT 15
+#define ICC_CTLR_EL1_A3V_MASK (0x1 << ICC_CTLR_EL1_A3V_SHIFT)
+#define ICC_CTLR_EL1_RSS (0x1 << 18)
+#define ICC_CTLR_EL1_ExtRange (0x1 << 19)
+#define ICC_PMR_EL1_SHIFT 0
+#define ICC_PMR_EL1_MASK (0xff << ICC_PMR_EL1_SHIFT)
+#define ICC_BPR0_EL1_SHIFT 0
+#define ICC_BPR0_EL1_MASK (0x7 << ICC_BPR0_EL1_SHIFT)
+#define ICC_BPR1_EL1_SHIFT 0
+#define ICC_BPR1_EL1_MASK (0x7 << ICC_BPR1_EL1_SHIFT)
+#define ICC_IGRPEN0_EL1_SHIFT 0
+#define ICC_IGRPEN0_EL1_MASK (1 << ICC_IGRPEN0_EL1_SHIFT)
+#define ICC_IGRPEN1_EL1_SHIFT 0
+#define ICC_IGRPEN1_EL1_MASK (1 << ICC_IGRPEN1_EL1_SHIFT)
+#define ICC_SRE_EL1_DIB (1U << 2)
+#define ICC_SRE_EL1_DFB (1U << 1)
#define ICC_SRE_EL1_SRE (1U << 0)
-#define ICC_IGRPEN1_EL1_ENABLE (1U << 0)
+/* These are for GICv2 emulation only */
+#define GICH_LR_VIRTUALID (0x3ffUL << 0)
+#define GICH_LR_PHYSID_CPUID_SHIFT (10)
+#define GICH_LR_PHYSID_CPUID (7UL << GICH_LR_PHYSID_CPUID_SHIFT)
+
+#define ICC_IAR1_EL1_SPURIOUS 0x3ff
+
+#define ICC_SRE_EL2_SRE (1 << 0)
+#define ICC_SRE_EL2_ENABLE (1 << 3)
-#define GICV3_MAX_CPUS 512
+#define ICC_SGI1R_TARGET_LIST_SHIFT 0
+#define ICC_SGI1R_TARGET_LIST_MASK (0xffff << ICC_SGI1R_TARGET_LIST_SHIFT)
+#define ICC_SGI1R_AFFINITY_1_SHIFT 16
+#define ICC_SGI1R_AFFINITY_1_MASK (0xff << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_SGI_ID_SHIFT 24
+#define ICC_SGI1R_SGI_ID_MASK (0xfULL << ICC_SGI1R_SGI_ID_SHIFT)
+#define ICC_SGI1R_AFFINITY_2_SHIFT 32
+#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_2_SHIFT)
+#define ICC_SGI1R_IRQ_ROUTING_MODE_BIT 40
+#define ICC_SGI1R_RS_SHIFT 44
+#define ICC_SGI1R_RS_MASK (0xfULL << ICC_SGI1R_RS_SHIFT)
+#define ICC_SGI1R_AFFINITY_3_SHIFT 48
+#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_3_SHIFT)
-#endif /* SELFTEST_KVM_GICV3_H */
+#endif
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h b/tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h
new file mode 100644
index 000000000000..3722ed9c8f96
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SELFTESTS_GIC_V3_ITS_H__
+#define __SELFTESTS_GIC_V3_ITS_H__
+
+#include <linux/sizes.h>
+
+void its_init(vm_paddr_t coll_tbl, size_t coll_tbl_sz,
+ vm_paddr_t device_tbl, size_t device_tbl_sz,
+ vm_paddr_t cmdq, size_t cmdq_size);
+
+void its_send_mapd_cmd(void *cmdq_base, u32 device_id, vm_paddr_t itt_base,
+ size_t itt_size, bool valid);
+void its_send_mapc_cmd(void *cmdq_base, u32 vcpu_id, u32 collection_id, bool valid);
+void its_send_mapti_cmd(void *cmdq_base, u32 device_id, u32 event_id,
+ u32 collection_id, u32 intid);
+void its_send_invall_cmd(void *cmdq_base, u32 collection_id);
+
+#endif // __SELFTESTS_GIC_V3_ITS_H__
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index 1814af7d8567..9b20a355d81a 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -60,8 +60,6 @@
MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) | \
MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
-#define MPIDR_HWID_BITMASK (0xff00fffffful)
-
void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init);
struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
struct kvm_vcpu_init *init, void *guest_code);
@@ -179,11 +177,28 @@ static __always_inline u32 __raw_readl(const volatile void *addr)
return val;
}
+static __always_inline void __raw_writeq(u64 val, volatile void *addr)
+{
+ asm volatile("str %0, [%1]" : : "rZ" (val), "r" (addr));
+}
+
+static __always_inline u64 __raw_readq(const volatile void *addr)
+{
+ u64 val;
+ asm volatile("ldr %0, [%1]" : "=r" (val) : "r" (addr));
+ return val;
+}
+
#define writel_relaxed(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c)))
#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
+#define writeq_relaxed(v,c) ((void)__raw_writeq((__force u64)cpu_to_le64(v),(c)))
+#define readq_relaxed(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; })
#define writel(v,c) ({ __iowmb(); writel_relaxed((v),(c));})
#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(__v); __v; })
+#define writeq(v,c) ({ __iowmb(); writeq_relaxed((v),(c));})
+#define readq(c) ({ u64 __v = readq_relaxed(c); __iormb(__v); __v; })
+
static inline void local_irq_enable(void)
{
diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h
index 0ac6f05c63f9..c481d0c00a5d 100644
--- a/tools/testing/selftests/kvm/include/aarch64/vgic.h
+++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h
@@ -16,8 +16,7 @@
((uint64_t)(flags) << 12) | \
index)
-int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
- uint64_t gicd_base_gpa, uint64_t gicr_base_gpa);
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs);
#define VGIC_MAX_RESERVED 1023
@@ -33,4 +32,6 @@ void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu);
#define KVM_IRQCHIP_NUM_PINS (1020 - 32)
+int vgic_its_setup(struct kvm_vm *vm);
+
#endif // SELFTEST_KVM_VGIC_H
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index ce473fe251dd..5f389166338c 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -50,6 +50,16 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype,
bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext);
+static inline bool __vcpu_has_isa_ext(struct kvm_vcpu *vcpu, uint64_t isa_ext)
+{
+ return __vcpu_has_ext(vcpu, RISCV_ISA_EXT_REG(isa_ext));
+}
+
+static inline bool __vcpu_has_sbi_ext(struct kvm_vcpu *vcpu, uint64_t sbi_ext)
+{
+ return __vcpu_has_ext(vcpu, RISCV_SBI_EXT_REG(sbi_ext));
+}
+
struct ex_regs {
unsigned long ra;
unsigned long sp;
@@ -154,45 +164,6 @@ void vm_install_interrupt_handler(struct kvm_vm *vm, exception_handler_fn handle
#define PGTBL_PAGE_SIZE PGTBL_L0_BLOCK_SIZE
#define PGTBL_PAGE_SIZE_SHIFT PGTBL_L0_BLOCK_SHIFT
-/* SBI return error codes */
-#define SBI_SUCCESS 0
-#define SBI_ERR_FAILURE -1
-#define SBI_ERR_NOT_SUPPORTED -2
-#define SBI_ERR_INVALID_PARAM -3
-#define SBI_ERR_DENIED -4
-#define SBI_ERR_INVALID_ADDRESS -5
-#define SBI_ERR_ALREADY_AVAILABLE -6
-#define SBI_ERR_ALREADY_STARTED -7
-#define SBI_ERR_ALREADY_STOPPED -8
-
-#define SBI_EXT_EXPERIMENTAL_START 0x08000000
-#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF
-
-#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END
-#define KVM_RISCV_SELFTESTS_SBI_UCALL 0
-#define KVM_RISCV_SELFTESTS_SBI_UNEXP 1
-
-enum sbi_ext_id {
- SBI_EXT_BASE = 0x10,
- SBI_EXT_STA = 0x535441,
-};
-
-enum sbi_ext_base_fid {
- SBI_EXT_BASE_PROBE_EXT = 3,
-};
-
-struct sbiret {
- long error;
- long value;
-};
-
-struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
- unsigned long arg1, unsigned long arg2,
- unsigned long arg3, unsigned long arg4,
- unsigned long arg5);
-
-bool guest_sbi_probe_extension(int extid, long *out_val);
-
static inline void local_irq_enable(void)
{
csr_set(CSR_SSTATUS, SR_SIE);
diff --git a/tools/testing/selftests/kvm/include/riscv/sbi.h b/tools/testing/selftests/kvm/include/riscv/sbi.h
new file mode 100644
index 000000000000..046b432ae896
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/riscv/sbi.h
@@ -0,0 +1,141 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * RISC-V SBI specific definitions
+ *
+ * Copyright (C) 2024 Rivos Inc.
+ */
+
+#ifndef SELFTEST_KVM_SBI_H
+#define SELFTEST_KVM_SBI_H
+
+/* SBI spec version fields */
+#define SBI_SPEC_VERSION_DEFAULT 0x1
+#define SBI_SPEC_VERSION_MAJOR_SHIFT 24
+#define SBI_SPEC_VERSION_MAJOR_MASK 0x7f
+#define SBI_SPEC_VERSION_MINOR_MASK 0xffffff
+
+/* SBI return error codes */
+#define SBI_SUCCESS 0
+#define SBI_ERR_FAILURE -1
+#define SBI_ERR_NOT_SUPPORTED -2
+#define SBI_ERR_INVALID_PARAM -3
+#define SBI_ERR_DENIED -4
+#define SBI_ERR_INVALID_ADDRESS -5
+#define SBI_ERR_ALREADY_AVAILABLE -6
+#define SBI_ERR_ALREADY_STARTED -7
+#define SBI_ERR_ALREADY_STOPPED -8
+
+#define SBI_EXT_EXPERIMENTAL_START 0x08000000
+#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF
+
+#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END
+#define KVM_RISCV_SELFTESTS_SBI_UCALL 0
+#define KVM_RISCV_SELFTESTS_SBI_UNEXP 1
+
+enum sbi_ext_id {
+ SBI_EXT_BASE = 0x10,
+ SBI_EXT_STA = 0x535441,
+ SBI_EXT_PMU = 0x504D55,
+};
+
+enum sbi_ext_base_fid {
+ SBI_EXT_BASE_GET_SPEC_VERSION = 0,
+ SBI_EXT_BASE_GET_IMP_ID,
+ SBI_EXT_BASE_GET_IMP_VERSION,
+ SBI_EXT_BASE_PROBE_EXT = 3,
+};
+enum sbi_ext_pmu_fid {
+ SBI_EXT_PMU_NUM_COUNTERS = 0,
+ SBI_EXT_PMU_COUNTER_GET_INFO,
+ SBI_EXT_PMU_COUNTER_CFG_MATCH,
+ SBI_EXT_PMU_COUNTER_START,
+ SBI_EXT_PMU_COUNTER_STOP,
+ SBI_EXT_PMU_COUNTER_FW_READ,
+ SBI_EXT_PMU_COUNTER_FW_READ_HI,
+ SBI_EXT_PMU_SNAPSHOT_SET_SHMEM,
+};
+
+union sbi_pmu_ctr_info {
+ unsigned long value;
+ struct {
+ unsigned long csr:12;
+ unsigned long width:6;
+#if __riscv_xlen == 32
+ unsigned long reserved:13;
+#else
+ unsigned long reserved:45;
+#endif
+ unsigned long type:1;
+ };
+};
+
+struct riscv_pmu_snapshot_data {
+ u64 ctr_overflow_mask;
+ u64 ctr_values[64];
+ u64 reserved[447];
+};
+
+struct sbiret {
+ long error;
+ long value;
+};
+
+/** General pmu event codes specified in SBI PMU extension */
+enum sbi_pmu_hw_generic_events_t {
+ SBI_PMU_HW_NO_EVENT = 0,
+ SBI_PMU_HW_CPU_CYCLES = 1,
+ SBI_PMU_HW_INSTRUCTIONS = 2,
+ SBI_PMU_HW_CACHE_REFERENCES = 3,
+ SBI_PMU_HW_CACHE_MISSES = 4,
+ SBI_PMU_HW_BRANCH_INSTRUCTIONS = 5,
+ SBI_PMU_HW_BRANCH_MISSES = 6,
+ SBI_PMU_HW_BUS_CYCLES = 7,
+ SBI_PMU_HW_STALLED_CYCLES_FRONTEND = 8,
+ SBI_PMU_HW_STALLED_CYCLES_BACKEND = 9,
+ SBI_PMU_HW_REF_CPU_CYCLES = 10,
+
+ SBI_PMU_HW_GENERAL_MAX,
+};
+
+/* SBI PMU counter types */
+enum sbi_pmu_ctr_type {
+ SBI_PMU_CTR_TYPE_HW = 0x0,
+ SBI_PMU_CTR_TYPE_FW,
+};
+
+/* Flags defined for config matching function */
+#define SBI_PMU_CFG_FLAG_SKIP_MATCH BIT(0)
+#define SBI_PMU_CFG_FLAG_CLEAR_VALUE BIT(1)
+#define SBI_PMU_CFG_FLAG_AUTO_START BIT(2)
+#define SBI_PMU_CFG_FLAG_SET_VUINH BIT(3)
+#define SBI_PMU_CFG_FLAG_SET_VSINH BIT(4)
+#define SBI_PMU_CFG_FLAG_SET_UINH BIT(5)
+#define SBI_PMU_CFG_FLAG_SET_SINH BIT(6)
+#define SBI_PMU_CFG_FLAG_SET_MINH BIT(7)
+
+/* Flags defined for counter start function */
+#define SBI_PMU_START_FLAG_SET_INIT_VALUE BIT(0)
+#define SBI_PMU_START_FLAG_INIT_SNAPSHOT BIT(1)
+
+/* Flags defined for counter stop function */
+#define SBI_PMU_STOP_FLAG_RESET BIT(0)
+#define SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT BIT(1)
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+ unsigned long arg1, unsigned long arg2,
+ unsigned long arg3, unsigned long arg4,
+ unsigned long arg5);
+
+bool guest_sbi_probe_extension(int extid, long *out_val);
+
+/* Make SBI version */
+static inline unsigned long sbi_mk_version(unsigned long major,
+ unsigned long minor)
+{
+ return ((major & SBI_SPEC_VERSION_MAJOR_MASK) << SBI_SPEC_VERSION_MAJOR_SHIFT)
+ | (minor & SBI_SPEC_VERSION_MINOR_MASK);
+}
+
+unsigned long get_host_sbi_spec_version(void);
+
+#endif /* SELFTEST_KVM_SBI_H */
diff --git a/tools/testing/selftests/kvm/include/riscv/ucall.h b/tools/testing/selftests/kvm/include/riscv/ucall.h
index be46eb32ec27..a695ae36f3e0 100644
--- a/tools/testing/selftests/kvm/include/riscv/ucall.h
+++ b/tools/testing/selftests/kvm/include/riscv/ucall.h
@@ -3,6 +3,7 @@
#define SELFTEST_KVM_UCALL_H
#include "processor.h"
+#include "sbi.h"
#define UCALL_EXIT_REASON KVM_EXIT_RISCV_SBI
diff --git a/tools/testing/selftests/kvm/include/userfaultfd_util.h b/tools/testing/selftests/kvm/include/userfaultfd_util.h
index a9d97c213584..60f7f9d435dc 100644
--- a/tools/testing/selftests/kvm/include/userfaultfd_util.h
+++ b/tools/testing/selftests/kvm/include/userfaultfd_util.h
@@ -14,17 +14,27 @@
typedef int (*uffd_handler_t)(int uffd_mode, int uffd, struct uffd_msg *msg);
-struct uffd_desc {
+struct uffd_reader_args {
int uffd_mode;
int uffd;
- int pipefds[2];
useconds_t delay;
uffd_handler_t handler;
- pthread_t thread;
+ /* Holds the read end of the pipe for killing the reader. */
+ int pipe;
+};
+
+struct uffd_desc {
+ int uffd;
+ uint64_t num_readers;
+ /* Holds the write ends of the pipes for killing the readers. */
+ int *pipefds;
+ pthread_t *readers;
+ struct uffd_reader_args *reader_args;
};
struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
void *hva, uint64_t len,
+ uint64_t num_readers,
uffd_handler_t handler);
void uffd_stop_demand_paging(struct uffd_desc *uffd);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/aarch64/gic.c
index 55668631d546..7abbf8866512 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic.c
@@ -17,13 +17,12 @@
static const struct gic_common_ops *gic_common_ops;
static struct spinlock gic_lock;
-static void gic_cpu_init(unsigned int cpu, void *redist_base)
+static void gic_cpu_init(unsigned int cpu)
{
- gic_common_ops->gic_cpu_init(cpu, redist_base);
+ gic_common_ops->gic_cpu_init(cpu);
}
-static void
-gic_dist_init(enum gic_type type, unsigned int nr_cpus, void *dist_base)
+static void gic_dist_init(enum gic_type type, unsigned int nr_cpus)
{
const struct gic_common_ops *gic_ops = NULL;
@@ -40,7 +39,7 @@ gic_dist_init(enum gic_type type, unsigned int nr_cpus, void *dist_base)
GUEST_ASSERT(gic_ops);
- gic_ops->gic_init(nr_cpus, dist_base);
+ gic_ops->gic_init(nr_cpus);
gic_common_ops = gic_ops;
/* Make sure that the initialized data is visible to all the vCPUs */
@@ -49,18 +48,15 @@ gic_dist_init(enum gic_type type, unsigned int nr_cpus, void *dist_base)
spin_unlock(&gic_lock);
}
-void gic_init(enum gic_type type, unsigned int nr_cpus,
- void *dist_base, void *redist_base)
+void gic_init(enum gic_type type, unsigned int nr_cpus)
{
uint32_t cpu = guest_get_vcpuid();
GUEST_ASSERT(type < GIC_TYPE_MAX);
- GUEST_ASSERT(dist_base);
- GUEST_ASSERT(redist_base);
GUEST_ASSERT(nr_cpus);
- gic_dist_init(type, nr_cpus, dist_base);
- gic_cpu_init(cpu, redist_base);
+ gic_dist_init(type, nr_cpus);
+ gic_cpu_init(cpu);
}
void gic_irq_enable(unsigned int intid)
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
index 75d07313c893..d24e9ecc96c6 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
@@ -8,8 +8,8 @@
#define SELFTEST_KVM_GIC_PRIVATE_H
struct gic_common_ops {
- void (*gic_init)(unsigned int nr_cpus, void *dist_base);
- void (*gic_cpu_init)(unsigned int cpu, void *redist_base);
+ void (*gic_init)(unsigned int nr_cpus);
+ void (*gic_cpu_init)(unsigned int cpu);
void (*gic_irq_enable)(unsigned int intid);
void (*gic_irq_disable)(unsigned int intid);
uint64_t (*gic_read_iar)(void);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
index 263bf3ed8fd5..66d05506f78b 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
@@ -9,12 +9,21 @@
#include "processor.h"
#include "delay.h"
+#include "gic.h"
#include "gic_v3.h"
#include "gic_private.h"
+#define GICV3_MAX_CPUS 512
+
+#define GICD_INT_DEF_PRI 0xa0
+#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\
+ (GICD_INT_DEF_PRI << 16) |\
+ (GICD_INT_DEF_PRI << 8) |\
+ GICD_INT_DEF_PRI)
+
+#define ICC_PMR_DEF_PRIO 0xf0
+
struct gicv3_data {
- void *dist_base;
- void *redist_base[GICV3_MAX_CPUS];
unsigned int nr_cpus;
unsigned int nr_spis;
};
@@ -35,17 +44,23 @@ static void gicv3_gicd_wait_for_rwp(void)
{
unsigned int count = 100000; /* 1s */
- while (readl(gicv3_data.dist_base + GICD_CTLR) & GICD_CTLR_RWP) {
+ while (readl(GICD_BASE_GVA + GICD_CTLR) & GICD_CTLR_RWP) {
GUEST_ASSERT(count--);
udelay(10);
}
}
-static void gicv3_gicr_wait_for_rwp(void *redist_base)
+static inline volatile void *gicr_base_cpu(uint32_t cpu)
+{
+ /* Align all the redistributors sequentially */
+ return GICR_BASE_GVA + cpu * SZ_64K * 2;
+}
+
+static void gicv3_gicr_wait_for_rwp(uint32_t cpu)
{
unsigned int count = 100000; /* 1s */
- while (readl(redist_base + GICR_CTLR) & GICR_CTLR_RWP) {
+ while (readl(gicr_base_cpu(cpu) + GICR_CTLR) & GICR_CTLR_RWP) {
GUEST_ASSERT(count--);
udelay(10);
}
@@ -56,7 +71,7 @@ static void gicv3_wait_for_rwp(uint32_t cpu_or_dist)
if (cpu_or_dist & DIST_BIT)
gicv3_gicd_wait_for_rwp();
else
- gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu_or_dist]);
+ gicv3_gicr_wait_for_rwp(cpu_or_dist);
}
static enum gicv3_intid_range get_intid_range(unsigned int intid)
@@ -116,15 +131,15 @@ static void gicv3_set_eoi_split(bool split)
uint32_t gicv3_reg_readl(uint32_t cpu_or_dist, uint64_t offset)
{
- void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
- : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+ volatile void *base = cpu_or_dist & DIST_BIT ? GICD_BASE_GVA
+ : sgi_base_from_redist(gicr_base_cpu(cpu_or_dist));
return readl(base + offset);
}
void gicv3_reg_writel(uint32_t cpu_or_dist, uint64_t offset, uint32_t reg_val)
{
- void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
- : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+ volatile void *base = cpu_or_dist & DIST_BIT ? GICD_BASE_GVA
+ : sgi_base_from_redist(gicr_base_cpu(cpu_or_dist));
writel(reg_val, base + offset);
}
@@ -263,7 +278,7 @@ static bool gicv3_irq_get_pending(uint32_t intid)
return gicv3_read_reg(intid, GICD_ISPENDR, 32, 1);
}
-static void gicv3_enable_redist(void *redist_base)
+static void gicv3_enable_redist(volatile void *redist_base)
{
uint32_t val = readl(redist_base + GICR_WAKER);
unsigned int count = 100000; /* 1s */
@@ -278,21 +293,15 @@ static void gicv3_enable_redist(void *redist_base)
}
}
-static inline void *gicr_base_cpu(void *redist_base, uint32_t cpu)
+static void gicv3_cpu_init(unsigned int cpu)
{
- /* Align all the redistributors sequentially */
- return redist_base + cpu * SZ_64K * 2;
-}
-
-static void gicv3_cpu_init(unsigned int cpu, void *redist_base)
-{
- void *sgi_base;
+ volatile void *sgi_base;
unsigned int i;
- void *redist_base_cpu;
+ volatile void *redist_base_cpu;
GUEST_ASSERT(cpu < gicv3_data.nr_cpus);
- redist_base_cpu = gicr_base_cpu(redist_base, cpu);
+ redist_base_cpu = gicr_base_cpu(cpu);
sgi_base = sgi_base_from_redist(redist_base_cpu);
gicv3_enable_redist(redist_base_cpu);
@@ -310,7 +319,7 @@ static void gicv3_cpu_init(unsigned int cpu, void *redist_base)
writel(GICD_INT_DEF_PRI_X4,
sgi_base + GICR_IPRIORITYR0 + i);
- gicv3_gicr_wait_for_rwp(redist_base_cpu);
+ gicv3_gicr_wait_for_rwp(cpu);
/* Enable the GIC system register (ICC_*) access */
write_sysreg_s(read_sysreg_s(SYS_ICC_SRE_EL1) | ICC_SRE_EL1_SRE,
@@ -320,18 +329,15 @@ static void gicv3_cpu_init(unsigned int cpu, void *redist_base)
write_sysreg_s(ICC_PMR_DEF_PRIO, SYS_ICC_PMR_EL1);
/* Enable non-secure Group-1 interrupts */
- write_sysreg_s(ICC_IGRPEN1_EL1_ENABLE, SYS_ICC_GRPEN1_EL1);
-
- gicv3_data.redist_base[cpu] = redist_base_cpu;
+ write_sysreg_s(ICC_IGRPEN1_EL1_MASK, SYS_ICC_IGRPEN1_EL1);
}
static void gicv3_dist_init(void)
{
- void *dist_base = gicv3_data.dist_base;
unsigned int i;
/* Disable the distributor until we set things up */
- writel(0, dist_base + GICD_CTLR);
+ writel(0, GICD_BASE_GVA + GICD_CTLR);
gicv3_gicd_wait_for_rwp();
/*
@@ -339,33 +345,32 @@ static void gicv3_dist_init(void)
* Also, deactivate and disable them.
*/
for (i = 32; i < gicv3_data.nr_spis; i += 32) {
- writel(~0, dist_base + GICD_IGROUPR + i / 8);
- writel(~0, dist_base + GICD_ICACTIVER + i / 8);
- writel(~0, dist_base + GICD_ICENABLER + i / 8);
+ writel(~0, GICD_BASE_GVA + GICD_IGROUPR + i / 8);
+ writel(~0, GICD_BASE_GVA + GICD_ICACTIVER + i / 8);
+ writel(~0, GICD_BASE_GVA + GICD_ICENABLER + i / 8);
}
/* Set a default priority for all the SPIs */
for (i = 32; i < gicv3_data.nr_spis; i += 4)
writel(GICD_INT_DEF_PRI_X4,
- dist_base + GICD_IPRIORITYR + i);
+ GICD_BASE_GVA + GICD_IPRIORITYR + i);
/* Wait for the settings to sync-in */
gicv3_gicd_wait_for_rwp();
/* Finally, enable the distributor globally with ARE */
writel(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A |
- GICD_CTLR_ENABLE_G1, dist_base + GICD_CTLR);
+ GICD_CTLR_ENABLE_G1, GICD_BASE_GVA + GICD_CTLR);
gicv3_gicd_wait_for_rwp();
}
-static void gicv3_init(unsigned int nr_cpus, void *dist_base)
+static void gicv3_init(unsigned int nr_cpus)
{
GUEST_ASSERT(nr_cpus <= GICV3_MAX_CPUS);
gicv3_data.nr_cpus = nr_cpus;
- gicv3_data.dist_base = dist_base;
gicv3_data.nr_spis = GICD_TYPER_SPIS(
- readl(gicv3_data.dist_base + GICD_TYPER));
+ readl(GICD_BASE_GVA + GICD_TYPER));
if (gicv3_data.nr_spis > 1020)
gicv3_data.nr_spis = 1020;
@@ -396,3 +401,27 @@ const struct gic_common_ops gicv3_ops = {
.gic_irq_get_pending = gicv3_irq_get_pending,
.gic_irq_set_config = gicv3_irq_set_config,
};
+
+void gic_rdist_enable_lpis(vm_paddr_t cfg_table, size_t cfg_table_size,
+ vm_paddr_t pend_table)
+{
+ volatile void *rdist_base = gicr_base_cpu(guest_get_vcpuid());
+
+ u32 ctlr;
+ u64 val;
+
+ val = (cfg_table |
+ GICR_PROPBASER_InnerShareable |
+ GICR_PROPBASER_RaWaWb |
+ ((ilog2(cfg_table_size) - 1) & GICR_PROPBASER_IDBITS_MASK));
+ writeq_relaxed(val, rdist_base + GICR_PROPBASER);
+
+ val = (pend_table |
+ GICR_PENDBASER_InnerShareable |
+ GICR_PENDBASER_RaWaWb);
+ writeq_relaxed(val, rdist_base + GICR_PENDBASER);
+
+ ctlr = readl_relaxed(rdist_base + GICR_CTLR);
+ ctlr |= GICR_CTLR_ENABLE_LPIS;
+ writel_relaxed(ctlr, rdist_base + GICR_CTLR);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c
new file mode 100644
index 000000000000..09f270545646
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Guest ITS library, generously donated by drivers/irqchip/irq-gic-v3-its.c
+ * over in the kernel tree.
+ */
+
+#include <linux/kvm.h>
+#include <linux/sizes.h>
+#include <asm/kvm_para.h>
+#include <asm/kvm.h>
+
+#include "kvm_util.h"
+#include "vgic.h"
+#include "gic.h"
+#include "gic_v3.h"
+#include "processor.h"
+
+static u64 its_read_u64(unsigned long offset)
+{
+ return readq_relaxed(GITS_BASE_GVA + offset);
+}
+
+static void its_write_u64(unsigned long offset, u64 val)
+{
+ writeq_relaxed(val, GITS_BASE_GVA + offset);
+}
+
+static u32 its_read_u32(unsigned long offset)
+{
+ return readl_relaxed(GITS_BASE_GVA + offset);
+}
+
+static void its_write_u32(unsigned long offset, u32 val)
+{
+ writel_relaxed(val, GITS_BASE_GVA + offset);
+}
+
+static unsigned long its_find_baser(unsigned int type)
+{
+ int i;
+
+ for (i = 0; i < GITS_BASER_NR_REGS; i++) {
+ u64 baser;
+ unsigned long offset = GITS_BASER + (i * sizeof(baser));
+
+ baser = its_read_u64(offset);
+ if (GITS_BASER_TYPE(baser) == type)
+ return offset;
+ }
+
+ GUEST_FAIL("Couldn't find an ITS BASER of type %u", type);
+ return -1;
+}
+
+static void its_install_table(unsigned int type, vm_paddr_t base, size_t size)
+{
+ unsigned long offset = its_find_baser(type);
+ u64 baser;
+
+ baser = ((size / SZ_64K) - 1) |
+ GITS_BASER_PAGE_SIZE_64K |
+ GITS_BASER_InnerShareable |
+ base |
+ GITS_BASER_RaWaWb |
+ GITS_BASER_VALID;
+
+ its_write_u64(offset, baser);
+}
+
+static void its_install_cmdq(vm_paddr_t base, size_t size)
+{
+ u64 cbaser;
+
+ cbaser = ((size / SZ_4K) - 1) |
+ GITS_CBASER_InnerShareable |
+ base |
+ GITS_CBASER_RaWaWb |
+ GITS_CBASER_VALID;
+
+ its_write_u64(GITS_CBASER, cbaser);
+}
+
+void its_init(vm_paddr_t coll_tbl, size_t coll_tbl_sz,
+ vm_paddr_t device_tbl, size_t device_tbl_sz,
+ vm_paddr_t cmdq, size_t cmdq_size)
+{
+ u32 ctlr;
+
+ its_install_table(GITS_BASER_TYPE_COLLECTION, coll_tbl, coll_tbl_sz);
+ its_install_table(GITS_BASER_TYPE_DEVICE, device_tbl, device_tbl_sz);
+ its_install_cmdq(cmdq, cmdq_size);
+
+ ctlr = its_read_u32(GITS_CTLR);
+ ctlr |= GITS_CTLR_ENABLE;
+ its_write_u32(GITS_CTLR, ctlr);
+}
+
+struct its_cmd_block {
+ union {
+ u64 raw_cmd[4];
+ __le64 raw_cmd_le[4];
+ };
+};
+
+static inline void its_fixup_cmd(struct its_cmd_block *cmd)
+{
+ /* Let's fixup BE commands */
+ cmd->raw_cmd_le[0] = cpu_to_le64(cmd->raw_cmd[0]);
+ cmd->raw_cmd_le[1] = cpu_to_le64(cmd->raw_cmd[1]);
+ cmd->raw_cmd_le[2] = cpu_to_le64(cmd->raw_cmd[2]);
+ cmd->raw_cmd_le[3] = cpu_to_le64(cmd->raw_cmd[3]);
+}
+
+static void its_mask_encode(u64 *raw_cmd, u64 val, int h, int l)
+{
+ u64 mask = GENMASK_ULL(h, l);
+ *raw_cmd &= ~mask;
+ *raw_cmd |= (val << l) & mask;
+}
+
+static void its_encode_cmd(struct its_cmd_block *cmd, u8 cmd_nr)
+{
+ its_mask_encode(&cmd->raw_cmd[0], cmd_nr, 7, 0);
+}
+
+static void its_encode_devid(struct its_cmd_block *cmd, u32 devid)
+{
+ its_mask_encode(&cmd->raw_cmd[0], devid, 63, 32);
+}
+
+static void its_encode_event_id(struct its_cmd_block *cmd, u32 id)
+{
+ its_mask_encode(&cmd->raw_cmd[1], id, 31, 0);
+}
+
+static void its_encode_phys_id(struct its_cmd_block *cmd, u32 phys_id)
+{
+ its_mask_encode(&cmd->raw_cmd[1], phys_id, 63, 32);
+}
+
+static void its_encode_size(struct its_cmd_block *cmd, u8 size)
+{
+ its_mask_encode(&cmd->raw_cmd[1], size, 4, 0);
+}
+
+static void its_encode_itt(struct its_cmd_block *cmd, u64 itt_addr)
+{
+ its_mask_encode(&cmd->raw_cmd[2], itt_addr >> 8, 51, 8);
+}
+
+static void its_encode_valid(struct its_cmd_block *cmd, int valid)
+{
+ its_mask_encode(&cmd->raw_cmd[2], !!valid, 63, 63);
+}
+
+static void its_encode_target(struct its_cmd_block *cmd, u64 target_addr)
+{
+ its_mask_encode(&cmd->raw_cmd[2], target_addr >> 16, 51, 16);
+}
+
+static void its_encode_collection(struct its_cmd_block *cmd, u16 col)
+{
+ its_mask_encode(&cmd->raw_cmd[2], col, 15, 0);
+}
+
+#define GITS_CMDQ_POLL_ITERATIONS 0
+
+static void its_send_cmd(void *cmdq_base, struct its_cmd_block *cmd)
+{
+ u64 cwriter = its_read_u64(GITS_CWRITER);
+ struct its_cmd_block *dst = cmdq_base + cwriter;
+ u64 cbaser = its_read_u64(GITS_CBASER);
+ size_t cmdq_size;
+ u64 next;
+ int i;
+
+ cmdq_size = ((cbaser & 0xFF) + 1) * SZ_4K;
+
+ its_fixup_cmd(cmd);
+
+ WRITE_ONCE(*dst, *cmd);
+ dsb(ishst);
+ next = (cwriter + sizeof(*cmd)) % cmdq_size;
+ its_write_u64(GITS_CWRITER, next);
+
+ /*
+ * Polling isn't necessary considering KVM's ITS emulation at the time
+ * of writing this, as the CMDQ is processed synchronously after a write
+ * to CWRITER.
+ */
+ for (i = 0; its_read_u64(GITS_CREADR) != next; i++) {
+ __GUEST_ASSERT(i < GITS_CMDQ_POLL_ITERATIONS,
+ "ITS didn't process command at offset %lu after %d iterations\n",
+ cwriter, i);
+
+ cpu_relax();
+ }
+}
+
+void its_send_mapd_cmd(void *cmdq_base, u32 device_id, vm_paddr_t itt_base,
+ size_t itt_size, bool valid)
+{
+ struct its_cmd_block cmd = {};
+
+ its_encode_cmd(&cmd, GITS_CMD_MAPD);
+ its_encode_devid(&cmd, device_id);
+ its_encode_size(&cmd, ilog2(itt_size) - 1);
+ its_encode_itt(&cmd, itt_base);
+ its_encode_valid(&cmd, valid);
+
+ its_send_cmd(cmdq_base, &cmd);
+}
+
+void its_send_mapc_cmd(void *cmdq_base, u32 vcpu_id, u32 collection_id, bool valid)
+{
+ struct its_cmd_block cmd = {};
+
+ its_encode_cmd(&cmd, GITS_CMD_MAPC);
+ its_encode_collection(&cmd, collection_id);
+ its_encode_target(&cmd, vcpu_id);
+ its_encode_valid(&cmd, valid);
+
+ its_send_cmd(cmdq_base, &cmd);
+}
+
+void its_send_mapti_cmd(void *cmdq_base, u32 device_id, u32 event_id,
+ u32 collection_id, u32 intid)
+{
+ struct its_cmd_block cmd = {};
+
+ its_encode_cmd(&cmd, GITS_CMD_MAPTI);
+ its_encode_devid(&cmd, device_id);
+ its_encode_event_id(&cmd, event_id);
+ its_encode_phys_id(&cmd, intid);
+ its_encode_collection(&cmd, collection_id);
+
+ its_send_cmd(cmdq_base, &cmd);
+}
+
+void its_send_invall_cmd(void *cmdq_base, u32 collection_id)
+{
+ struct its_cmd_block cmd = {};
+
+ its_encode_cmd(&cmd, GITS_CMD_INVALL);
+ its_encode_collection(&cmd, collection_id);
+
+ its_send_cmd(cmdq_base, &cmd);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index 184378d593e9..4427f43f73ea 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -3,8 +3,10 @@
* ARM Generic Interrupt Controller (GIC) v3 host support
*/
+#include <linux/kernel.h>
#include <linux/kvm.h>
#include <linux/sizes.h>
+#include <asm/cputype.h>
#include <asm/kvm_para.h>
#include <asm/kvm.h>
@@ -19,8 +21,6 @@
* Input args:
* vm - KVM VM
* nr_vcpus - Number of vCPUs supported by this VM
- * gicd_base_gpa - Guest Physical Address of the Distributor region
- * gicr_base_gpa - Guest Physical Address of the Redistributor region
*
* Output args: None
*
@@ -30,11 +30,10 @@
* redistributor regions of the guest. Since it depends on the number of
* vCPUs for the VM, it must be called after all the vCPUs have been created.
*/
-int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
- uint64_t gicd_base_gpa, uint64_t gicr_base_gpa)
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs)
{
int gic_fd;
- uint64_t redist_attr;
+ uint64_t attr;
struct list_head *iter;
unsigned int nr_gic_pages, nr_vcpus_created = 0;
@@ -60,18 +59,19 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
KVM_DEV_ARM_VGIC_CTRL_INIT, NULL);
+ attr = GICD_BASE_GPA;
kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa);
+ KVM_VGIC_V3_ADDR_TYPE_DIST, &attr);
nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_DIST_SIZE);
- virt_map(vm, gicd_base_gpa, gicd_base_gpa, nr_gic_pages);
+ virt_map(vm, GICD_BASE_GPA, GICD_BASE_GPA, nr_gic_pages);
/* Redistributor setup */
- redist_attr = REDIST_REGION_ATTR_ADDR(nr_vcpus, gicr_base_gpa, 0, 0);
+ attr = REDIST_REGION_ATTR_ADDR(nr_vcpus, GICR_BASE_GPA, 0, 0);
kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &redist_attr);
+ KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &attr);
nr_gic_pages = vm_calc_num_guest_pages(vm->mode,
KVM_VGIC_V3_REDIST_SIZE * nr_vcpus);
- virt_map(vm, gicr_base_gpa, gicr_base_gpa, nr_gic_pages);
+ virt_map(vm, GICR_BASE_GPA, GICR_BASE_GPA, nr_gic_pages);
kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
KVM_DEV_ARM_VGIC_CTRL_INIT, NULL);
@@ -168,3 +168,21 @@ void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu)
{
vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISACTIVER);
}
+
+int vgic_its_setup(struct kvm_vm *vm)
+{
+ int its_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_ITS);
+ u64 attr;
+
+ attr = GITS_BASE_GPA;
+ kvm_device_attr_set(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_ITS_ADDR_TYPE, &attr);
+
+ kvm_device_attr_set(its_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+ KVM_DEV_ARM_VGIC_CTRL_INIT, NULL);
+
+ virt_map(vm, GITS_BASE_GPA, GITS_BASE_GPA,
+ vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_ITS_SIZE));
+
+ return its_fd;
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 6b2158655baa..ad00e4761886 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -935,6 +935,10 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
errno, strerror(errno));
}
+#define TEST_REQUIRE_SET_USER_MEMORY_REGION2() \
+ __TEST_REQUIRE(kvm_has_cap(KVM_CAP_USER_MEMORY2), \
+ "KVM selftests now require KVM_SET_USER_MEMORY_REGION2 (introduced in v6.8)")
+
int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
uint64_t gpa, uint64_t size, void *hva,
uint32_t guest_memfd, uint64_t guest_memfd_offset)
@@ -949,6 +953,8 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flag
.guest_memfd_offset = guest_memfd_offset,
};
+ TEST_REQUIRE_SET_USER_MEMORY_REGION2();
+
return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, &region);
}
@@ -975,6 +981,8 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
size_t mem_size = npages * vm->page_size;
size_t alignment;
+ TEST_REQUIRE_SET_USER_MEMORY_REGION2();
+
TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
"Number of guest pages is not compatible with the host. "
"Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages));
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index 79b67e2627cb..6ae47b3d6b25 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -503,3 +503,15 @@ bool guest_sbi_probe_extension(int extid, long *out_val)
return true;
}
+
+unsigned long get_host_sbi_spec_version(void)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_GET_SPEC_VERSION, 0,
+ 0, 0, 0, 0, 0);
+
+ GUEST_ASSERT(!ret.error);
+
+ return ret.value;
+}
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
index bd07568a5240..7c9de8414462 100644
--- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c
+++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
@@ -13,6 +13,7 @@
#include <poll.h>
#include <pthread.h>
#include <linux/userfaultfd.h>
+#include <sys/epoll.h>
#include <sys/syscall.h>
#include "kvm_util.h"
@@ -24,76 +25,69 @@
static void *uffd_handler_thread_fn(void *arg)
{
- struct uffd_desc *uffd_desc = (struct uffd_desc *)arg;
- int uffd = uffd_desc->uffd;
- int pipefd = uffd_desc->pipefds[0];
- useconds_t delay = uffd_desc->delay;
+ struct uffd_reader_args *reader_args = (struct uffd_reader_args *)arg;
+ int uffd = reader_args->uffd;
int64_t pages = 0;
struct timespec start;
struct timespec ts_diff;
+ struct epoll_event evt;
+ int epollfd;
+
+ epollfd = epoll_create(1);
+ TEST_ASSERT(epollfd >= 0, "Failed to create epollfd.");
+
+ evt.events = EPOLLIN | EPOLLEXCLUSIVE;
+ evt.data.u32 = 0;
+ TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, uffd, &evt),
+ "Failed to add uffd to epollfd");
+
+ evt.events = EPOLLIN;
+ evt.data.u32 = 1;
+ TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, reader_args->pipe, &evt),
+ "Failed to add pipe to epollfd");
clock_gettime(CLOCK_MONOTONIC, &start);
while (1) {
struct uffd_msg msg;
- struct pollfd pollfd[2];
- char tmp_chr;
int r;
- pollfd[0].fd = uffd;
- pollfd[0].events = POLLIN;
- pollfd[1].fd = pipefd;
- pollfd[1].events = POLLIN;
-
- r = poll(pollfd, 2, -1);
- switch (r) {
- case -1:
- pr_info("poll err");
- continue;
- case 0:
- continue;
- case 1:
- break;
- default:
- pr_info("Polling uffd returned %d", r);
- return NULL;
- }
+ r = epoll_wait(epollfd, &evt, 1, -1);
+ TEST_ASSERT(r == 1,
+ "Unexpected number of events (%d) from epoll, errno = %d",
+ r, errno);
- if (pollfd[0].revents & POLLERR) {
- pr_info("uffd revents has POLLERR");
- return NULL;
- }
+ if (evt.data.u32 == 1) {
+ char tmp_chr;
- if (pollfd[1].revents & POLLIN) {
- r = read(pollfd[1].fd, &tmp_chr, 1);
+ TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)),
+ "Reader thread received EPOLLERR or EPOLLHUP on pipe.");
+ r = read(reader_args->pipe, &tmp_chr, 1);
TEST_ASSERT(r == 1,
- "Error reading pipefd in UFFD thread");
+ "Error reading pipefd in uffd reader thread");
break;
}
- if (!(pollfd[0].revents & POLLIN))
- continue;
+ TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)),
+ "Reader thread received EPOLLERR or EPOLLHUP on uffd.");
r = read(uffd, &msg, sizeof(msg));
if (r == -1) {
- if (errno == EAGAIN)
- continue;
- pr_info("Read of uffd got errno %d\n", errno);
- return NULL;
+ TEST_ASSERT(errno == EAGAIN,
+ "Error reading from UFFD: errno = %d", errno);
+ continue;
}
- if (r != sizeof(msg)) {
- pr_info("Read on uffd returned unexpected size: %d bytes", r);
- return NULL;
- }
+ TEST_ASSERT(r == sizeof(msg),
+ "Read on uffd returned unexpected number of bytes (%d)", r);
if (!(msg.event & UFFD_EVENT_PAGEFAULT))
continue;
- if (delay)
- usleep(delay);
- r = uffd_desc->handler(uffd_desc->uffd_mode, uffd, &msg);
- if (r < 0)
- return NULL;
+ if (reader_args->delay)
+ usleep(reader_args->delay);
+ r = reader_args->handler(reader_args->uffd_mode, uffd, &msg);
+ TEST_ASSERT(r >= 0,
+ "Reader thread handler fn returned negative value %d", r);
pages++;
}
@@ -107,6 +101,7 @@ static void *uffd_handler_thread_fn(void *arg)
struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
void *hva, uint64_t len,
+ uint64_t num_readers,
uffd_handler_t handler)
{
struct uffd_desc *uffd_desc;
@@ -115,14 +110,25 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
struct uffdio_api uffdio_api;
struct uffdio_register uffdio_register;
uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
- int ret;
+ int ret, i;
PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
is_minor ? "MINOR" : "MISSING",
is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY");
uffd_desc = malloc(sizeof(struct uffd_desc));
- TEST_ASSERT(uffd_desc, "malloc failed");
+ TEST_ASSERT(uffd_desc, "Failed to malloc uffd descriptor");
+
+ uffd_desc->pipefds = calloc(sizeof(int), num_readers);
+ TEST_ASSERT(uffd_desc->pipefds, "Failed to alloc pipes");
+
+ uffd_desc->readers = calloc(sizeof(pthread_t), num_readers);
+ TEST_ASSERT(uffd_desc->readers, "Failed to alloc reader threads");
+
+ uffd_desc->reader_args = calloc(sizeof(struct uffd_reader_args), num_readers);
+ TEST_ASSERT(uffd_desc->reader_args, "Failed to alloc reader_args");
+
+ uffd_desc->num_readers = num_readers;
/* In order to get minor faults, prefault via the alias. */
if (is_minor)
@@ -145,18 +151,28 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) ==
expected_ioctls, "missing userfaultfd ioctls");
- ret = pipe2(uffd_desc->pipefds, O_CLOEXEC | O_NONBLOCK);
- TEST_ASSERT(!ret, "Failed to set up pipefd");
-
- uffd_desc->uffd_mode = uffd_mode;
uffd_desc->uffd = uffd;
- uffd_desc->delay = delay;
- uffd_desc->handler = handler;
- pthread_create(&uffd_desc->thread, NULL, uffd_handler_thread_fn,
- uffd_desc);
+ for (i = 0; i < uffd_desc->num_readers; ++i) {
+ int pipes[2];
+
+ ret = pipe2((int *) &pipes, O_CLOEXEC | O_NONBLOCK);
+ TEST_ASSERT(!ret, "Failed to set up pipefd %i for uffd_desc %p",
+ i, uffd_desc);
- PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
- hva, hva + len);
+ uffd_desc->pipefds[i] = pipes[1];
+
+ uffd_desc->reader_args[i].uffd_mode = uffd_mode;
+ uffd_desc->reader_args[i].uffd = uffd;
+ uffd_desc->reader_args[i].delay = delay;
+ uffd_desc->reader_args[i].handler = handler;
+ uffd_desc->reader_args[i].pipe = pipes[0];
+
+ pthread_create(&uffd_desc->readers[i], NULL, uffd_handler_thread_fn,
+ &uffd_desc->reader_args[i]);
+
+ PER_VCPU_DEBUG("Created uffd thread %i for HVA range [%p, %p)\n",
+ i, hva, hva + len);
+ }
return uffd_desc;
}
@@ -164,19 +180,26 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
void uffd_stop_demand_paging(struct uffd_desc *uffd)
{
char c = 0;
- int ret;
+ int i;
- ret = write(uffd->pipefds[1], &c, 1);
- TEST_ASSERT(ret == 1, "Unable to write to pipefd");
+ for (i = 0; i < uffd->num_readers; ++i)
+ TEST_ASSERT(write(uffd->pipefds[i], &c, 1) == 1,
+ "Unable to write to pipefd %i for uffd_desc %p", i, uffd);
- ret = pthread_join(uffd->thread, NULL);
- TEST_ASSERT(ret == 0, "Pthread_join failed.");
+ for (i = 0; i < uffd->num_readers; ++i)
+ TEST_ASSERT(!pthread_join(uffd->readers[i], NULL),
+ "Pthread_join failed on reader %i for uffd_desc %p", i, uffd);
close(uffd->uffd);
- close(uffd->pipefds[1]);
- close(uffd->pipefds[0]);
+ for (i = 0; i < uffd->num_readers; ++i) {
+ close(uffd->pipefds[i]);
+ close(uffd->reader_args[i].pipe);
+ }
+ free(uffd->pipefds);
+ free(uffd->readers);
+ free(uffd->reader_args);
free(uffd);
}
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 9b7fc3908be6..0b9678858b6d 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -20,10 +20,11 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
{
uint64_t gpa;
- for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
- *((volatile uint64_t *)gpa) = gpa;
-
- GUEST_DONE();
+ for (;;) {
+ for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
+ *((volatile uint64_t *)gpa) = gpa;
+ GUEST_SYNC(0);
+ }
}
struct vcpu_info {
@@ -53,7 +54,7 @@ static void rendezvous_with_boss(void)
static void run_vcpu(struct kvm_vcpu *vcpu)
{
vcpu_run(vcpu);
- TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+ TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC);
}
static void *vcpu_worker(void *data)
@@ -62,17 +63,13 @@ static void *vcpu_worker(void *data)
struct kvm_vcpu *vcpu = info->vcpu;
struct kvm_vm *vm = vcpu->vm;
struct kvm_sregs sregs;
- struct kvm_regs regs;
vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size);
- /* Snapshot regs before the first run. */
- vcpu_regs_get(vcpu, &regs);
rendezvous_with_boss();
run_vcpu(vcpu);
rendezvous_with_boss();
- vcpu_regs_set(vcpu, &regs);
vcpu_sregs_get(vcpu, &sregs);
#ifdef __x86_64__
/* Toggle CR0.WP to trigger a MMU context reset. */
diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c
index 82999e0f0221..2c792228ac0b 100644
--- a/tools/testing/selftests/kvm/riscv/arch_timer.c
+++ b/tools/testing/selftests/kvm/riscv/arch_timer.c
@@ -83,7 +83,7 @@ struct kvm_vm *test_vm_create(void)
int nr_vcpus = test_args.nr_vcpus;
vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus);
- __TEST_REQUIRE(__vcpu_has_ext(vcpus[0], RISCV_ISA_EXT_REG(KVM_RISCV_ISA_EXT_SSTC)),
+ __TEST_REQUIRE(__vcpu_has_isa_ext(vcpus[0], KVM_RISCV_ISA_EXT_SSTC),
"SSTC not available, skipping test\n");
vm_init_vector_tables(vm);
diff --git a/tools/testing/selftests/kvm/riscv/ebreak_test.c b/tools/testing/selftests/kvm/riscv/ebreak_test.c
new file mode 100644
index 000000000000..823c132069b4
--- /dev/null
+++ b/tools/testing/selftests/kvm/riscv/ebreak_test.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RISC-V KVM ebreak test.
+ *
+ * Copyright 2024 Beijing ESWIN Computing Technology Co., Ltd.
+ *
+ */
+#include "kvm_util.h"
+
+#define LABEL_ADDRESS(v) ((uint64_t)&(v))
+
+extern unsigned char sw_bp_1, sw_bp_2;
+static uint64_t sw_bp_addr;
+
+static void guest_code(void)
+{
+ asm volatile(
+ ".option push\n"
+ ".option norvc\n"
+ "sw_bp_1: ebreak\n"
+ "sw_bp_2: ebreak\n"
+ ".option pop\n"
+ );
+ GUEST_ASSERT_EQ(READ_ONCE(sw_bp_addr), LABEL_ADDRESS(sw_bp_2));
+
+ GUEST_DONE();
+}
+
+static void guest_breakpoint_handler(struct ex_regs *regs)
+{
+ WRITE_ONCE(sw_bp_addr, regs->epc);
+ regs->epc += 4;
+}
+
+int main(void)
+{
+ struct kvm_vm *vm;
+ struct kvm_vcpu *vcpu;
+ uint64_t pc;
+ struct kvm_guest_debug debug = {
+ .control = KVM_GUESTDBG_ENABLE,
+ };
+
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_SET_GUEST_DEBUG));
+
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+ vm_init_vector_tables(vm);
+ vcpu_init_vector_tables(vcpu);
+ vm_install_exception_handler(vm, EXC_BREAKPOINT,
+ guest_breakpoint_handler);
+
+ /*
+ * Enable the guest debug.
+ * ebreak should exit to the VMM with KVM_EXIT_DEBUG reason.
+ */
+ vcpu_guest_debug_set(vcpu, &debug);
+ vcpu_run(vcpu);
+
+ TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG);
+
+ vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &pc);
+ TEST_ASSERT_EQ(pc, LABEL_ADDRESS(sw_bp_1));
+
+ /* skip sw_bp_1 */
+ vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), pc + 4);
+
+ /*
+ * Disable all debug controls.
+ * Guest should handle the ebreak without exiting to the VMM.
+ */
+ memset(&debug, 0, sizeof(debug));
+ vcpu_guest_debug_set(vcpu, &debug);
+
+ vcpu_run(vcpu);
+
+ TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index b882b7b9b785..222198dd6d04 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -43,6 +43,7 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_V:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSCOFPMF:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSTC:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT:
@@ -408,6 +409,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(V),
KVM_ISA_EXT_ARR(SMSTATEEN),
KVM_ISA_EXT_ARR(SSAIA),
+ KVM_ISA_EXT_ARR(SSCOFPMF),
KVM_ISA_EXT_ARR(SSTC),
KVM_ISA_EXT_ARR(SVINVAL),
KVM_ISA_EXT_ARR(SVNAPOT),
@@ -931,6 +933,7 @@ KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F);
KVM_ISA_EXT_SUBLIST_CONFIG(fp_d, FP_D);
KVM_ISA_EXT_SIMPLE_CONFIG(h, H);
KVM_ISA_EXT_SUBLIST_CONFIG(smstateen, SMSTATEEN);
+KVM_ISA_EXT_SIMPLE_CONFIG(sscofpmf, SSCOFPMF);
KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC);
KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL);
KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT);
@@ -986,6 +989,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_fp_d,
&config_h,
&config_smstateen,
+ &config_sscofpmf,
&config_sstc,
&config_svinval,
&config_svnapot,
diff --git a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c
new file mode 100644
index 000000000000..69bb94e6b227
--- /dev/null
+++ b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c
@@ -0,0 +1,681 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * sbi_pmu_test.c - Tests the riscv64 SBI PMU functionality.
+ *
+ * Copyright (c) 2024, Rivos Inc.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include "kvm_util.h"
+#include "test_util.h"
+#include "processor.h"
+#include "sbi.h"
+#include "arch_timer.h"
+
+/* Maximum counters(firmware + hardware) */
+#define RISCV_MAX_PMU_COUNTERS 64
+union sbi_pmu_ctr_info ctrinfo_arr[RISCV_MAX_PMU_COUNTERS];
+
+/* Snapshot shared memory data */
+#define PMU_SNAPSHOT_GPA_BASE BIT(30)
+static void *snapshot_gva;
+static vm_paddr_t snapshot_gpa;
+
+static int vcpu_shared_irq_count;
+static int counter_in_use;
+
+/* Cache the available counters in a bitmask */
+static unsigned long counter_mask_available;
+
+static bool illegal_handler_invoked;
+
+#define SBI_PMU_TEST_BASIC BIT(0)
+#define SBI_PMU_TEST_EVENTS BIT(1)
+#define SBI_PMU_TEST_SNAPSHOT BIT(2)
+#define SBI_PMU_TEST_OVERFLOW BIT(3)
+
+static int disabled_tests;
+
+unsigned long pmu_csr_read_num(int csr_num)
+{
+#define switchcase_csr_read(__csr_num, __val) {\
+ case __csr_num: \
+ __val = csr_read(__csr_num); \
+ break; }
+#define switchcase_csr_read_2(__csr_num, __val) {\
+ switchcase_csr_read(__csr_num + 0, __val) \
+ switchcase_csr_read(__csr_num + 1, __val)}
+#define switchcase_csr_read_4(__csr_num, __val) {\
+ switchcase_csr_read_2(__csr_num + 0, __val) \
+ switchcase_csr_read_2(__csr_num + 2, __val)}
+#define switchcase_csr_read_8(__csr_num, __val) {\
+ switchcase_csr_read_4(__csr_num + 0, __val) \
+ switchcase_csr_read_4(__csr_num + 4, __val)}
+#define switchcase_csr_read_16(__csr_num, __val) {\
+ switchcase_csr_read_8(__csr_num + 0, __val) \
+ switchcase_csr_read_8(__csr_num + 8, __val)}
+#define switchcase_csr_read_32(__csr_num, __val) {\
+ switchcase_csr_read_16(__csr_num + 0, __val) \
+ switchcase_csr_read_16(__csr_num + 16, __val)}
+
+ unsigned long ret = 0;
+
+ switch (csr_num) {
+ switchcase_csr_read_32(CSR_CYCLE, ret)
+ switchcase_csr_read_32(CSR_CYCLEH, ret)
+ default :
+ break;
+ }
+
+ return ret;
+#undef switchcase_csr_read_32
+#undef switchcase_csr_read_16
+#undef switchcase_csr_read_8
+#undef switchcase_csr_read_4
+#undef switchcase_csr_read_2
+#undef switchcase_csr_read
+}
+
+static inline void dummy_func_loop(uint64_t iter)
+{
+ int i = 0;
+
+ while (i < iter) {
+ asm volatile("nop");
+ i++;
+ }
+}
+
+static void start_counter(unsigned long counter, unsigned long start_flags,
+ unsigned long ival)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_START, counter, 1, start_flags,
+ ival, 0, 0);
+ __GUEST_ASSERT(ret.error == 0, "Unable to start counter %ld\n", counter);
+}
+
+/* This should be invoked only for reset counter use case */
+static void stop_reset_counter(unsigned long counter, unsigned long stop_flags)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, counter, 1,
+ stop_flags | SBI_PMU_STOP_FLAG_RESET, 0, 0, 0);
+ __GUEST_ASSERT(ret.error == SBI_ERR_ALREADY_STOPPED,
+ "Unable to stop counter %ld\n", counter);
+}
+
+static void stop_counter(unsigned long counter, unsigned long stop_flags)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, counter, 1, stop_flags,
+ 0, 0, 0);
+ __GUEST_ASSERT(ret.error == 0, "Unable to stop counter %ld error %ld\n",
+ counter, ret.error);
+}
+
+static void guest_illegal_exception_handler(struct ex_regs *regs)
+{
+ __GUEST_ASSERT(regs->cause == EXC_INST_ILLEGAL,
+ "Unexpected exception handler %lx\n", regs->cause);
+
+ illegal_handler_invoked = true;
+ /* skip the trapping instruction */
+ regs->epc += 4;
+}
+
+static void guest_irq_handler(struct ex_regs *regs)
+{
+ unsigned int irq_num = regs->cause & ~CAUSE_IRQ_FLAG;
+ struct riscv_pmu_snapshot_data *snapshot_data = snapshot_gva;
+ unsigned long overflown_mask;
+ unsigned long counter_val = 0;
+
+ /* Validate that we are in the correct irq handler */
+ GUEST_ASSERT_EQ(irq_num, IRQ_PMU_OVF);
+
+ /* Stop all counters first to avoid further interrupts */
+ stop_counter(counter_in_use, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT);
+
+ csr_clear(CSR_SIP, BIT(IRQ_PMU_OVF));
+
+ overflown_mask = READ_ONCE(snapshot_data->ctr_overflow_mask);
+ GUEST_ASSERT(overflown_mask & 0x01);
+
+ WRITE_ONCE(vcpu_shared_irq_count, vcpu_shared_irq_count+1);
+
+ counter_val = READ_ONCE(snapshot_data->ctr_values[0]);
+ /* Now start the counter to mimick the real driver behavior */
+ start_counter(counter_in_use, SBI_PMU_START_FLAG_SET_INIT_VALUE, counter_val);
+}
+
+static unsigned long get_counter_index(unsigned long cbase, unsigned long cmask,
+ unsigned long cflags,
+ unsigned long event)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask,
+ cflags, event, 0, 0);
+ __GUEST_ASSERT(ret.error == 0, "config matching failed %ld\n", ret.error);
+ GUEST_ASSERT(ret.value < RISCV_MAX_PMU_COUNTERS);
+ GUEST_ASSERT(BIT(ret.value) & counter_mask_available);
+
+ return ret.value;
+}
+
+static unsigned long get_num_counters(void)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_NUM_COUNTERS, 0, 0, 0, 0, 0, 0);
+
+ __GUEST_ASSERT(ret.error == 0, "Unable to retrieve number of counters from SBI PMU");
+ __GUEST_ASSERT(ret.value < RISCV_MAX_PMU_COUNTERS,
+ "Invalid number of counters %ld\n", ret.value);
+
+ return ret.value;
+}
+
+static void update_counter_info(int num_counters)
+{
+ int i = 0;
+ struct sbiret ret;
+
+ for (i = 0; i < num_counters; i++) {
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_GET_INFO, i, 0, 0, 0, 0, 0);
+
+ /* There can be gaps in logical counter indicies*/
+ if (ret.error)
+ continue;
+ GUEST_ASSERT_NE(ret.value, 0);
+
+ ctrinfo_arr[i].value = ret.value;
+ counter_mask_available |= BIT(i);
+ }
+
+ GUEST_ASSERT(counter_mask_available > 0);
+}
+
+static unsigned long read_fw_counter(int idx, union sbi_pmu_ctr_info ctrinfo)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_FW_READ, idx, 0, 0, 0, 0, 0);
+ GUEST_ASSERT(ret.error == 0);
+ return ret.value;
+}
+
+static unsigned long read_counter(int idx, union sbi_pmu_ctr_info ctrinfo)
+{
+ unsigned long counter_val = 0;
+
+ __GUEST_ASSERT(ctrinfo.type < 2, "Invalid counter type %d", ctrinfo.type);
+
+ if (ctrinfo.type == SBI_PMU_CTR_TYPE_HW)
+ counter_val = pmu_csr_read_num(ctrinfo.csr);
+ else if (ctrinfo.type == SBI_PMU_CTR_TYPE_FW)
+ counter_val = read_fw_counter(idx, ctrinfo);
+
+ return counter_val;
+}
+
+static inline void verify_sbi_requirement_assert(void)
+{
+ long out_val = 0;
+ bool probe;
+
+ probe = guest_sbi_probe_extension(SBI_EXT_PMU, &out_val);
+ GUEST_ASSERT(probe && out_val == 1);
+
+ if (get_host_sbi_spec_version() < sbi_mk_version(2, 0))
+ __GUEST_ASSERT(0, "SBI implementation version doesn't support PMU Snapshot");
+}
+
+static void snapshot_set_shmem(vm_paddr_t gpa, unsigned long flags)
+{
+ unsigned long lo = (unsigned long)gpa;
+#if __riscv_xlen == 32
+ unsigned long hi = (unsigned long)(gpa >> 32);
+#else
+ unsigned long hi = gpa == -1 ? -1 : 0;
+#endif
+ struct sbiret ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_SNAPSHOT_SET_SHMEM,
+ lo, hi, flags, 0, 0, 0);
+
+ GUEST_ASSERT(ret.value == 0 && ret.error == 0);
+}
+
+static void test_pmu_event(unsigned long event)
+{
+ unsigned long counter;
+ unsigned long counter_value_pre, counter_value_post;
+ unsigned long counter_init_value = 100;
+
+ counter = get_counter_index(0, counter_mask_available, 0, event);
+ counter_value_pre = read_counter(counter, ctrinfo_arr[counter]);
+
+ /* Do not set the initial value */
+ start_counter(counter, 0, 0);
+ dummy_func_loop(10000);
+ stop_counter(counter, 0);
+
+ counter_value_post = read_counter(counter, ctrinfo_arr[counter]);
+ __GUEST_ASSERT(counter_value_post > counter_value_pre,
+ "Event update verification failed: post [%lx] pre [%lx]\n",
+ counter_value_post, counter_value_pre);
+
+ /*
+ * We can't just update the counter without starting it.
+ * Do start/stop twice to simulate that by first initializing to a very
+ * high value and a low value after that.
+ */
+ start_counter(counter, SBI_PMU_START_FLAG_SET_INIT_VALUE, ULONG_MAX/2);
+ stop_counter(counter, 0);
+ counter_value_pre = read_counter(counter, ctrinfo_arr[counter]);
+
+ start_counter(counter, SBI_PMU_START_FLAG_SET_INIT_VALUE, counter_init_value);
+ stop_counter(counter, 0);
+ counter_value_post = read_counter(counter, ctrinfo_arr[counter]);
+ __GUEST_ASSERT(counter_value_pre > counter_value_post,
+ "Counter reinitialization verification failed : post [%lx] pre [%lx]\n",
+ counter_value_post, counter_value_pre);
+
+ /* Now set the initial value and compare */
+ start_counter(counter, SBI_PMU_START_FLAG_SET_INIT_VALUE, counter_init_value);
+ dummy_func_loop(10000);
+ stop_counter(counter, 0);
+
+ counter_value_post = read_counter(counter, ctrinfo_arr[counter]);
+ __GUEST_ASSERT(counter_value_post > counter_init_value,
+ "Event update verification failed: post [%lx] pre [%lx]\n",
+ counter_value_post, counter_init_value);
+
+ stop_reset_counter(counter, 0);
+}
+
+static void test_pmu_event_snapshot(unsigned long event)
+{
+ unsigned long counter;
+ unsigned long counter_value_pre, counter_value_post;
+ unsigned long counter_init_value = 100;
+ struct riscv_pmu_snapshot_data *snapshot_data = snapshot_gva;
+
+ counter = get_counter_index(0, counter_mask_available, 0, event);
+ counter_value_pre = read_counter(counter, ctrinfo_arr[counter]);
+
+ /* Do not set the initial value */
+ start_counter(counter, 0, 0);
+ dummy_func_loop(10000);
+ stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT);
+
+ /* The counter value is updated w.r.t relative index of cbase */
+ counter_value_post = READ_ONCE(snapshot_data->ctr_values[0]);
+ __GUEST_ASSERT(counter_value_post > counter_value_pre,
+ "Event update verification failed: post [%lx] pre [%lx]\n",
+ counter_value_post, counter_value_pre);
+
+ /*
+ * We can't just update the counter without starting it.
+ * Do start/stop twice to simulate that by first initializing to a very
+ * high value and a low value after that.
+ */
+ WRITE_ONCE(snapshot_data->ctr_values[0], ULONG_MAX/2);
+ start_counter(counter, SBI_PMU_START_FLAG_INIT_SNAPSHOT, 0);
+ stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT);
+ counter_value_pre = READ_ONCE(snapshot_data->ctr_values[0]);
+
+ WRITE_ONCE(snapshot_data->ctr_values[0], counter_init_value);
+ start_counter(counter, SBI_PMU_START_FLAG_INIT_SNAPSHOT, 0);
+ stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT);
+ counter_value_post = READ_ONCE(snapshot_data->ctr_values[0]);
+ __GUEST_ASSERT(counter_value_pre > counter_value_post,
+ "Counter reinitialization verification failed : post [%lx] pre [%lx]\n",
+ counter_value_post, counter_value_pre);
+
+ /* Now set the initial value and compare */
+ WRITE_ONCE(snapshot_data->ctr_values[0], counter_init_value);
+ start_counter(counter, SBI_PMU_START_FLAG_INIT_SNAPSHOT, 0);
+ dummy_func_loop(10000);
+ stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT);
+
+ counter_value_post = READ_ONCE(snapshot_data->ctr_values[0]);
+ __GUEST_ASSERT(counter_value_post > counter_init_value,
+ "Event update verification failed: post [%lx] pre [%lx]\n",
+ counter_value_post, counter_init_value);
+
+ stop_reset_counter(counter, 0);
+}
+
+static void test_pmu_event_overflow(unsigned long event)
+{
+ unsigned long counter;
+ unsigned long counter_value_post;
+ unsigned long counter_init_value = ULONG_MAX - 10000;
+ struct riscv_pmu_snapshot_data *snapshot_data = snapshot_gva;
+
+ counter = get_counter_index(0, counter_mask_available, 0, event);
+ counter_in_use = counter;
+
+ /* The counter value is updated w.r.t relative index of cbase passed to start/stop */
+ WRITE_ONCE(snapshot_data->ctr_values[0], counter_init_value);
+ start_counter(counter, SBI_PMU_START_FLAG_INIT_SNAPSHOT, 0);
+ dummy_func_loop(10000);
+ udelay(msecs_to_usecs(2000));
+ /* irq handler should have stopped the counter */
+ stop_counter(counter, SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT);
+
+ counter_value_post = READ_ONCE(snapshot_data->ctr_values[0]);
+ /* The counter value after stopping should be less the init value due to overflow */
+ __GUEST_ASSERT(counter_value_post < counter_init_value,
+ "counter_value_post %lx counter_init_value %lx for counter\n",
+ counter_value_post, counter_init_value);
+
+ stop_reset_counter(counter, 0);
+}
+
+static void test_invalid_event(void)
+{
+ struct sbiret ret;
+ unsigned long event = 0x1234; /* A random event */
+
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, 0,
+ counter_mask_available, 0, event, 0, 0);
+ GUEST_ASSERT_EQ(ret.error, SBI_ERR_NOT_SUPPORTED);
+}
+
+static void test_pmu_events(void)
+{
+ int num_counters = 0;
+
+ /* Get the counter details */
+ num_counters = get_num_counters();
+ update_counter_info(num_counters);
+
+ /* Sanity testing for any random invalid event */
+ test_invalid_event();
+
+ /* Only these two events are guaranteed to be present */
+ test_pmu_event(SBI_PMU_HW_CPU_CYCLES);
+ test_pmu_event(SBI_PMU_HW_INSTRUCTIONS);
+
+ GUEST_DONE();
+}
+
+static void test_pmu_basic_sanity(void)
+{
+ long out_val = 0;
+ bool probe;
+ struct sbiret ret;
+ int num_counters = 0, i;
+ union sbi_pmu_ctr_info ctrinfo;
+
+ probe = guest_sbi_probe_extension(SBI_EXT_PMU, &out_val);
+ GUEST_ASSERT(probe && out_val == 1);
+
+ num_counters = get_num_counters();
+
+ for (i = 0; i < num_counters; i++) {
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_GET_INFO, i,
+ 0, 0, 0, 0, 0);
+
+ /* There can be gaps in logical counter indicies*/
+ if (ret.error)
+ continue;
+ GUEST_ASSERT_NE(ret.value, 0);
+
+ ctrinfo.value = ret.value;
+
+ /**
+ * Accessibility check of hardware and read capability of firmware counters.
+ * The spec doesn't mandate any initial value. No need to check any value.
+ */
+ if (ctrinfo.type == SBI_PMU_CTR_TYPE_HW) {
+ pmu_csr_read_num(ctrinfo.csr);
+ GUEST_ASSERT(illegal_handler_invoked);
+ } else if (ctrinfo.type == SBI_PMU_CTR_TYPE_FW) {
+ read_fw_counter(i, ctrinfo);
+ }
+ }
+
+ GUEST_DONE();
+}
+
+static void test_pmu_events_snaphost(void)
+{
+ int num_counters = 0;
+ struct riscv_pmu_snapshot_data *snapshot_data = snapshot_gva;
+ int i;
+
+ /* Verify presence of SBI PMU and minimum requrired SBI version */
+ verify_sbi_requirement_assert();
+
+ snapshot_set_shmem(snapshot_gpa, 0);
+
+ /* Get the counter details */
+ num_counters = get_num_counters();
+ update_counter_info(num_counters);
+
+ /* Validate shared memory access */
+ GUEST_ASSERT_EQ(READ_ONCE(snapshot_data->ctr_overflow_mask), 0);
+ for (i = 0; i < num_counters; i++) {
+ if (counter_mask_available & (BIT(i)))
+ GUEST_ASSERT_EQ(READ_ONCE(snapshot_data->ctr_values[i]), 0);
+ }
+ /* Only these two events are guranteed to be present */
+ test_pmu_event_snapshot(SBI_PMU_HW_CPU_CYCLES);
+ test_pmu_event_snapshot(SBI_PMU_HW_INSTRUCTIONS);
+
+ GUEST_DONE();
+}
+
+static void test_pmu_events_overflow(void)
+{
+ int num_counters = 0;
+
+ /* Verify presence of SBI PMU and minimum requrired SBI version */
+ verify_sbi_requirement_assert();
+
+ snapshot_set_shmem(snapshot_gpa, 0);
+ csr_set(CSR_IE, BIT(IRQ_PMU_OVF));
+ local_irq_enable();
+
+ /* Get the counter details */
+ num_counters = get_num_counters();
+ update_counter_info(num_counters);
+
+ /*
+ * Qemu supports overflow for cycle/instruction.
+ * This test may fail on any platform that do not support overflow for these two events.
+ */
+ test_pmu_event_overflow(SBI_PMU_HW_CPU_CYCLES);
+ GUEST_ASSERT_EQ(vcpu_shared_irq_count, 1);
+
+ test_pmu_event_overflow(SBI_PMU_HW_INSTRUCTIONS);
+ GUEST_ASSERT_EQ(vcpu_shared_irq_count, 2);
+
+ GUEST_DONE();
+}
+
+static void run_vcpu(struct kvm_vcpu *vcpu)
+{
+ struct ucall uc;
+
+ vcpu_run(vcpu);
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ break;
+ case UCALL_DONE:
+ case UCALL_SYNC:
+ break;
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ break;
+ }
+}
+
+void test_vm_destroy(struct kvm_vm *vm)
+{
+ memset(ctrinfo_arr, 0, sizeof(union sbi_pmu_ctr_info) * RISCV_MAX_PMU_COUNTERS);
+ counter_mask_available = 0;
+ kvm_vm_free(vm);
+}
+
+static void test_vm_basic_test(void *guest_code)
+{
+ struct kvm_vm *vm;
+ struct kvm_vcpu *vcpu;
+
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+ __TEST_REQUIRE(__vcpu_has_sbi_ext(vcpu, KVM_RISCV_SBI_EXT_PMU),
+ "SBI PMU not available, skipping test");
+ vm_init_vector_tables(vm);
+ /* Illegal instruction handler is required to verify read access without configuration */
+ vm_install_exception_handler(vm, EXC_INST_ILLEGAL, guest_illegal_exception_handler);
+
+ vcpu_init_vector_tables(vcpu);
+ run_vcpu(vcpu);
+
+ test_vm_destroy(vm);
+}
+
+static void test_vm_events_test(void *guest_code)
+{
+ struct kvm_vm *vm = NULL;
+ struct kvm_vcpu *vcpu = NULL;
+
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+ __TEST_REQUIRE(__vcpu_has_sbi_ext(vcpu, KVM_RISCV_SBI_EXT_PMU),
+ "SBI PMU not available, skipping test");
+ run_vcpu(vcpu);
+
+ test_vm_destroy(vm);
+}
+
+static void test_vm_setup_snapshot_mem(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
+{
+ /* PMU Snapshot requires single page only */
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, PMU_SNAPSHOT_GPA_BASE, 1, 1, 0);
+ /* PMU_SNAPSHOT_GPA_BASE is identity mapped */
+ virt_map(vm, PMU_SNAPSHOT_GPA_BASE, PMU_SNAPSHOT_GPA_BASE, 1);
+
+ snapshot_gva = (void *)(PMU_SNAPSHOT_GPA_BASE);
+ snapshot_gpa = addr_gva2gpa(vcpu->vm, (vm_vaddr_t)snapshot_gva);
+ sync_global_to_guest(vcpu->vm, snapshot_gva);
+ sync_global_to_guest(vcpu->vm, snapshot_gpa);
+}
+
+static void test_vm_events_snapshot_test(void *guest_code)
+{
+ struct kvm_vm *vm = NULL;
+ struct kvm_vcpu *vcpu;
+
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+ __TEST_REQUIRE(__vcpu_has_sbi_ext(vcpu, KVM_RISCV_SBI_EXT_PMU),
+ "SBI PMU not available, skipping test");
+
+ test_vm_setup_snapshot_mem(vm, vcpu);
+
+ run_vcpu(vcpu);
+
+ test_vm_destroy(vm);
+}
+
+static void test_vm_events_overflow(void *guest_code)
+{
+ struct kvm_vm *vm = NULL;
+ struct kvm_vcpu *vcpu;
+
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+ __TEST_REQUIRE(__vcpu_has_sbi_ext(vcpu, KVM_RISCV_SBI_EXT_PMU),
+ "SBI PMU not available, skipping test");
+
+ __TEST_REQUIRE(__vcpu_has_isa_ext(vcpu, KVM_RISCV_ISA_EXT_SSCOFPMF),
+ "Sscofpmf is not available, skipping overflow test");
+
+ test_vm_setup_snapshot_mem(vm, vcpu);
+ vm_init_vector_tables(vm);
+ vm_install_interrupt_handler(vm, guest_irq_handler);
+
+ vcpu_init_vector_tables(vcpu);
+ /* Initialize guest timer frequency. */
+ vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency), &timer_freq);
+ sync_global_to_guest(vm, timer_freq);
+
+ run_vcpu(vcpu);
+
+ test_vm_destroy(vm);
+}
+
+static void test_print_help(char *name)
+{
+ pr_info("Usage: %s [-h] [-d <test name>]\n", name);
+ pr_info("\t-d: Test to disable. Available tests are 'basic', 'events', 'snapshot', 'overflow'\n");
+ pr_info("\t-h: print this help screen\n");
+}
+
+static bool parse_args(int argc, char *argv[])
+{
+ int opt;
+
+ while ((opt = getopt(argc, argv, "hd:")) != -1) {
+ switch (opt) {
+ case 'd':
+ if (!strncmp("basic", optarg, 5))
+ disabled_tests |= SBI_PMU_TEST_BASIC;
+ else if (!strncmp("events", optarg, 6))
+ disabled_tests |= SBI_PMU_TEST_EVENTS;
+ else if (!strncmp("snapshot", optarg, 8))
+ disabled_tests |= SBI_PMU_TEST_SNAPSHOT;
+ else if (!strncmp("overflow", optarg, 8))
+ disabled_tests |= SBI_PMU_TEST_OVERFLOW;
+ else
+ goto done;
+ break;
+ case 'h':
+ default:
+ goto done;
+ }
+ }
+
+ return true;
+done:
+ test_print_help(argv[0]);
+ return false;
+}
+
+int main(int argc, char *argv[])
+{
+ if (!parse_args(argc, argv))
+ exit(KSFT_SKIP);
+
+ if (!(disabled_tests & SBI_PMU_TEST_BASIC)) {
+ test_vm_basic_test(test_pmu_basic_sanity);
+ pr_info("SBI PMU basic test : PASS\n");
+ }
+
+ if (!(disabled_tests & SBI_PMU_TEST_EVENTS)) {
+ test_vm_events_test(test_pmu_events);
+ pr_info("SBI PMU event verification test : PASS\n");
+ }
+
+ if (!(disabled_tests & SBI_PMU_TEST_SNAPSHOT)) {
+ test_vm_events_snapshot_test(test_pmu_events_snaphost);
+ pr_info("SBI PMU event verification with snapshot test : PASS\n");
+ }
+
+ if (!(disabled_tests & SBI_PMU_TEST_OVERFLOW)) {
+ test_vm_events_overflow(test_pmu_events_overflow);
+ pr_info("SBI PMU event verification with overflow test : PASS\n");
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index a44df60cf189..e5898678bfab 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -193,12 +193,35 @@ static void calc_min_max_cpu(void)
"Only one usable CPU, task migration not possible");
}
+static void help(const char *name)
+{
+ puts("");
+ printf("usage: %s [-h] [-u]\n", name);
+ printf(" -u: Don't sanity check the number of successful KVM_RUNs\n");
+ puts("");
+ exit(0);
+}
+
int main(int argc, char *argv[])
{
+ bool skip_sanity_check = false;
int r, i, snapshot;
struct kvm_vm *vm;
struct kvm_vcpu *vcpu;
u32 cpu, rseq_cpu;
+ int opt;
+
+ while ((opt = getopt(argc, argv, "hu")) != -1) {
+ switch (opt) {
+ case 'u':
+ skip_sanity_check = true;
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask);
TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno,
@@ -261,9 +284,17 @@ int main(int argc, char *argv[])
* getcpu() to stabilize. A 2:1 migration:KVM_RUN ratio is a fairly
* conservative ratio on x86-64, which can do _more_ KVM_RUNs than
* migrations given the 1us+ delay in the migration task.
+ *
+ * Another reason why it may have small migration:KVM_RUN ratio is that,
+ * on systems with large low power mode wakeup latency, it may happen
+ * quite often that the scheduler is not able to wake up the target CPU
+ * before the vCPU thread is scheduled to another CPU.
*/
- TEST_ASSERT(i > (NR_TASK_MIGRATIONS / 2),
- "Only performed %d KVM_RUNs, task stalled too much?", i);
+ TEST_ASSERT(skip_sanity_check || i > (NR_TASK_MIGRATIONS / 2),
+ "Only performed %d KVM_RUNs, task stalled too much?\n\n"
+ " Try disabling deep sleep states to reduce CPU wakeup latency,\n"
+ " e.g. via cpuidle.off=1 or setting /dev/cpu_dma_latency to '0',\n"
+ " or run with -u to disable this sanity check.", i);
pthread_join(migration_thread, NULL);
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index ae98cb00da05..bb8002084f52 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -344,7 +344,7 @@ static void test_invalid_memory_region_flags(void)
struct kvm_vm *vm;
int r, i;
-#if defined __aarch64__ || defined __x86_64__
+#if defined __aarch64__ || defined __riscv || defined __x86_64__
supported_flags |= KVM_MEM_READONLY;
#endif
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index d7a70fc191ef..a8d3afa0b86b 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -10,7 +10,9 @@
#include <pthread.h>
#include <linux/kernel.h>
#include <asm/kvm.h>
-#ifndef __riscv
+#ifdef __riscv
+#include "sbi.h"
+#else
#include <asm/kvm_para.h>
#endif
@@ -83,20 +85,18 @@ static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i)
static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx)
{
struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]);
- int i;
- pr_info("VCPU%d:\n", vcpu_idx);
- pr_info(" steal: %lld\n", st->steal);
- pr_info(" version: %d\n", st->version);
- pr_info(" flags: %d\n", st->flags);
- pr_info(" preempted: %d\n", st->preempted);
- pr_info(" u8_pad: ");
- for (i = 0; i < 3; ++i)
- pr_info("%d", st->u8_pad[i]);
- pr_info("\n pad: ");
- for (i = 0; i < 11; ++i)
- pr_info("%d", st->pad[i]);
- pr_info("\n");
+ ksft_print_msg("VCPU%d:\n", vcpu_idx);
+ ksft_print_msg(" steal: %lld\n", st->steal);
+ ksft_print_msg(" version: %d\n", st->version);
+ ksft_print_msg(" flags: %d\n", st->flags);
+ ksft_print_msg(" preempted: %d\n", st->preempted);
+ ksft_print_msg(" u8_pad: %d %d %d\n",
+ st->u8_pad[0], st->u8_pad[1], st->u8_pad[2]);
+ ksft_print_msg(" pad: %d %d %d %d %d %d %d %d %d %d %d\n",
+ st->pad[0], st->pad[1], st->pad[2], st->pad[3],
+ st->pad[4], st->pad[5], st->pad[6], st->pad[7],
+ st->pad[8], st->pad[9], st->pad[10]);
}
#elif defined(__aarch64__)
@@ -199,10 +199,10 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx)
{
struct st_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]);
- pr_info("VCPU%d:\n", vcpu_idx);
- pr_info(" rev: %d\n", st->rev);
- pr_info(" attr: %d\n", st->attr);
- pr_info(" st_time: %ld\n", st->st_time);
+ ksft_print_msg("VCPU%d:\n", vcpu_idx);
+ ksft_print_msg(" rev: %d\n", st->rev);
+ ksft_print_msg(" attr: %d\n", st->attr);
+ ksft_print_msg(" st_time: %ld\n", st->st_time);
}
#elif defined(__riscv)
@@ -366,7 +366,9 @@ int main(int ac, char **av)
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);
+ ksft_print_header();
TEST_REQUIRE(is_steal_time_supported(vcpus[0]));
+ ksft_set_plan(NR_VCPUS);
/* Run test on each VCPU */
for (i = 0; i < NR_VCPUS; ++i) {
@@ -407,14 +409,15 @@ int main(int ac, char **av)
run_delay, stolen_time);
if (verbose) {
- pr_info("VCPU%d: total-stolen-time=%ld test-stolen-time=%ld", i,
- guest_stolen_time[i], stolen_time);
- if (stolen_time == run_delay)
- pr_info(" (BONUS: guest test-stolen-time even exactly matches test-run_delay)");
- pr_info("\n");
+ ksft_print_msg("VCPU%d: total-stolen-time=%ld test-stolen-time=%ld%s\n",
+ i, guest_stolen_time[i], stolen_time,
+ stolen_time == run_delay ?
+ " (BONUS: guest test-stolen-time even exactly matches test-run_delay)" : "");
steal_time_dump(vm, i);
}
+ ksft_test_result_pass("vcpu%d\n", i);
}
- return 0;
+ /* Print results and exit() accordingly */
+ ksft_finished();
}
diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
index 9c8445379d76..2b550eff35f1 100644
--- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
@@ -75,6 +75,7 @@ int main(int argc, char *argv[])
struct ucall uc;
int testcase;
+ TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT));
TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2));
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
index 7cbb409801ee..caad084b8bfd 100755
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
@@ -13,10 +13,21 @@ NX_HUGE_PAGES_RECOVERY_RATIO=$(cat /sys/module/kvm/parameters/nx_huge_pages_reco
NX_HUGE_PAGES_RECOVERY_PERIOD=$(cat /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms)
HUGE_PAGES=$(cat /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages)
+# If we're already root, the host might not have sudo.
+if [ $(whoami) == "root" ]; then
+ function do_sudo () {
+ "$@"
+ }
+else
+ function do_sudo () {
+ sudo "$@"
+ }
+fi
+
set +e
function sudo_echo () {
- echo "$1" | sudo tee -a "$2" > /dev/null
+ echo "$1" | do_sudo tee -a "$2" > /dev/null
}
NXECUTABLE="$(dirname $0)/nx_huge_pages_test"
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
index 2556777c4674..96446134c00b 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
@@ -409,12 +409,30 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters
static void guest_test_gp_counters(void)
{
+ uint8_t pmu_version = guest_get_pmu_version();
uint8_t nr_gp_counters = 0;
uint32_t base_msr;
- if (guest_get_pmu_version())
+ if (pmu_version)
nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
+ /*
+ * For v2+ PMUs, PERF_GLOBAL_CTRL's architectural post-RESET value is
+ * "Sets bits n-1:0 and clears the upper bits", where 'n' is the number
+ * of GP counters. If there are no GP counters, require KVM to leave
+ * PERF_GLOBAL_CTRL '0'. This edge case isn't covered by the SDM, but
+ * follow the spirit of the architecture and only globally enable GP
+ * counters, of which there are none.
+ */
+ if (pmu_version > 1) {
+ uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL);
+
+ if (nr_gp_counters)
+ GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0));
+ else
+ GUEST_ASSERT_EQ(global_ctrl, 0);
+ }
+
if (this_cpu_has(X86_FEATURE_PDCM) &&
rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES)
base_msr = MSR_IA32_PMC0;
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 a39cba19c058..fa512d033205 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
@@ -25,16 +25,16 @@
#define NESTED_TEST_MEM1 0xc0001000
#define NESTED_TEST_MEM2 0xc0002000
-static void l2_guest_code(void)
+static void l2_guest_code(u64 *a, u64 *b)
{
- *(volatile uint64_t *)NESTED_TEST_MEM1;
- *(volatile uint64_t *)NESTED_TEST_MEM1 = 1;
+ READ_ONCE(*a);
+ WRITE_ONCE(*a, 1);
GUEST_SYNC(true);
GUEST_SYNC(false);
- *(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+ WRITE_ONCE(*b, 1);
GUEST_SYNC(true);
- *(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+ WRITE_ONCE(*b, 1);
GUEST_SYNC(true);
GUEST_SYNC(false);
@@ -42,17 +42,33 @@ static void l2_guest_code(void)
vmcall();
}
+static void l2_guest_code_ept_enabled(void)
+{
+ l2_guest_code((u64 *)NESTED_TEST_MEM1, (u64 *)NESTED_TEST_MEM2);
+}
+
+static void l2_guest_code_ept_disabled(void)
+{
+ /* Access the same L1 GPAs as l2_guest_code_ept_enabled() */
+ l2_guest_code((u64 *)GUEST_TEST_MEM, (u64 *)GUEST_TEST_MEM);
+}
+
void l1_guest_code(struct vmx_pages *vmx)
{
#define L2_GUEST_STACK_SIZE 64
unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ void *l2_rip;
GUEST_ASSERT(vmx->vmcs_gpa);
GUEST_ASSERT(prepare_for_vmx_operation(vmx));
GUEST_ASSERT(load_vmcs(vmx));
- prepare_vmcs(vmx, l2_guest_code,
- &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ if (vmx->eptp_gpa)
+ l2_rip = l2_guest_code_ept_enabled;
+ else
+ l2_rip = l2_guest_code_ept_disabled;
+
+ prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
GUEST_SYNC(false);
GUEST_ASSERT(!vmlaunch());
@@ -61,7 +77,7 @@ void l1_guest_code(struct vmx_pages *vmx)
GUEST_DONE();
}
-int main(int argc, char *argv[])
+static void test_vmx_dirty_log(bool enable_ept)
{
vm_vaddr_t vmx_pages_gva = 0;
struct vmx_pages *vmx;
@@ -73,8 +89,7 @@ int main(int argc, char *argv[])
struct ucall uc;
bool done = false;
- TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
- TEST_REQUIRE(kvm_cpu_has_ept());
+ pr_info("Nested EPT: %s\n", enable_ept ? "enabled" : "disabled");
/* Create VM */
vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
@@ -100,11 +115,16 @@ int main(int argc, char *argv[])
*
* Note that prepare_eptp should be called only L1's GPA map is done,
* meaning after the last call to virt_map.
+ *
+ * When EPT is disabled, the L2 guest code will still access the same L1
+ * GPAs as the EPT enabled case.
*/
- prepare_eptp(vmx, vm, 0);
- nested_map_memslot(vmx, vm, 0);
- nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
- nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+ if (enable_ept) {
+ prepare_eptp(vmx, vm, 0);
+ nested_map_memslot(vmx, vm, 0);
+ nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
+ nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+ }
bmap = bitmap_zalloc(TEST_MEM_PAGES);
host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
@@ -145,3 +165,15 @@ int main(int argc, char *argv[])
}
}
}
+
+int main(int argc, char *argv[])
+{
+ TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+
+ test_vmx_dirty_log(/*enable_ept=*/false);
+
+ if (kvm_cpu_has_ept())
+ test_vmx_dirty_log(/*enable_ept=*/true);
+
+ return 0;
+}
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 aa88cc541fe2..a59b3c799bb2 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -125,7 +125,7 @@ struct compat_vcpu_runstate_info {
uint32_t state;
uint64_t state_entry_time;
uint64_t time[5];
-} __attribute__((__packed__));;
+} __attribute__((__packed__));
struct arch_vcpu_info {
unsigned long cr2;
@@ -381,20 +381,6 @@ wait_for_timer:
GUEST_SYNC(TEST_DONE);
}
-static int cmp_timespec(struct timespec *a, struct timespec *b)
-{
- if (a->tv_sec > b->tv_sec)
- return 1;
- else if (a->tv_sec < b->tv_sec)
- return -1;
- else if (a->tv_nsec > b->tv_nsec)
- return 1;
- else if (a->tv_nsec < b->tv_nsec)
- return -1;
- else
- return 0;
-}
-
static struct shared_info *shinfo;
static struct vcpu_info *vinfo;
static struct kvm_vcpu *vcpu;
@@ -450,7 +436,6 @@ static void *juggle_shinfo_state(void *arg)
int main(int argc, char *argv[])
{
- struct timespec min_ts, max_ts, vm_ts;
struct kvm_xen_hvm_attr evt_reset;
struct kvm_vm *vm;
pthread_t thread;
@@ -469,8 +454,6 @@ int main(int argc, char *argv[])
bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND);
bool has_shinfo_hva = !!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA);
- clock_gettime(CLOCK_REALTIME, &min_ts);
-
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
/* Map a region for the shared_info page */
@@ -1009,7 +992,6 @@ int main(int argc, char *argv[])
vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset);
alarm(0);
- clock_gettime(CLOCK_REALTIME, &max_ts);
/*
* Just a *really* basic check that things are being put in the
@@ -1018,6 +1000,8 @@ int main(int argc, char *argv[])
*/
struct pvclock_wall_clock *wc;
struct pvclock_vcpu_time_info *ti, *ti2;
+ struct kvm_clock_data kcdata;
+ long long delta;
wc = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0xc00);
ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20);
@@ -1033,12 +1017,34 @@ int main(int argc, char *argv[])
ti2->tsc_shift, ti2->flags);
}
- vm_ts.tv_sec = wc->sec;
- vm_ts.tv_nsec = wc->nsec;
TEST_ASSERT(wc->version && !(wc->version & 1),
"Bad wallclock version %x", wc->version);
- TEST_ASSERT(cmp_timespec(&min_ts, &vm_ts) <= 0, "VM time too old");
- TEST_ASSERT(cmp_timespec(&max_ts, &vm_ts) >= 0, "VM time too new");
+
+ vm_ioctl(vm, KVM_GET_CLOCK, &kcdata);
+
+ if (kcdata.flags & KVM_CLOCK_REALTIME) {
+ if (verbose) {
+ printf("KVM_GET_CLOCK clock: %lld.%09lld\n",
+ kcdata.clock / NSEC_PER_SEC, kcdata.clock % NSEC_PER_SEC);
+ printf("KVM_GET_CLOCK realtime: %lld.%09lld\n",
+ kcdata.realtime / NSEC_PER_SEC, kcdata.realtime % NSEC_PER_SEC);
+ }
+
+ delta = (wc->sec * NSEC_PER_SEC + wc->nsec) - (kcdata.realtime - kcdata.clock);
+
+ /*
+ * KVM_GET_CLOCK gives CLOCK_REALTIME which jumps on leap seconds updates but
+ * unfortunately KVM doesn't currently offer a CLOCK_TAI alternative. Accept 1s
+ * delta as testing clock accuracy is not the goal here. The test just needs to
+ * check that the value in shinfo is somewhat sane.
+ */
+ TEST_ASSERT(llabs(delta) < NSEC_PER_SEC,
+ "Guest's epoch from shinfo %d.%09d differs from KVM_GET_CLOCK %lld.%lld",
+ wc->sec, wc->nsec, (kcdata.realtime - kcdata.clock) / NSEC_PER_SEC,
+ (kcdata.realtime - kcdata.clock) % NSEC_PER_SEC);
+ } else {
+ pr_info("Missing KVM_CLOCK_REALTIME, skipping shinfo epoch sanity check\n");
+ }
TEST_ASSERT(ti->version && !(ti->version & 1),
"Bad time_info version %x", ti->version);
diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c
index 200bedcdc32e..1e01d3ddc11c 100644
--- a/tools/testing/selftests/mm/mdwe_test.c
+++ b/tools/testing/selftests/mm/mdwe_test.c
@@ -7,6 +7,7 @@
#include <linux/mman.h>
#include <linux/prctl.h>
+#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <sys/auxv.h>
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
index 374a308174d2..48dc151f8fca 100644
--- a/tools/testing/selftests/mm/protection_keys.c
+++ b/tools/testing/selftests/mm/protection_keys.c
@@ -54,7 +54,6 @@ int test_nr;
u64 shadow_pkey_reg;
int dprint_in_signal;
char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
-char buf[256];
void cat_into_file(char *str, char *file)
{
@@ -1745,42 +1744,6 @@ void pkey_setup_shadow(void)
shadow_pkey_reg = __read_pkey_reg();
}
-pid_t parent_pid;
-
-void restore_settings_atexit(void)
-{
- if (parent_pid == getpid())
- cat_into_file(buf, "/proc/sys/vm/nr_hugepages");
-}
-
-void save_settings(void)
-{
- int fd;
- int err;
-
- if (geteuid())
- return;
-
- fd = open("/proc/sys/vm/nr_hugepages", O_RDONLY);
- if (fd < 0) {
- fprintf(stderr, "error opening\n");
- perror("error: ");
- exit(__LINE__);
- }
-
- /* -1 to guarantee leaving the trailing \0 */
- err = read(fd, buf, sizeof(buf)-1);
- if (err < 0) {
- fprintf(stderr, "error reading\n");
- perror("error: ");
- exit(__LINE__);
- }
-
- parent_pid = getpid();
- atexit(restore_settings_atexit);
- close(fd);
-}
-
int main(void)
{
int nr_iterations = 22;
@@ -1788,7 +1751,6 @@ int main(void)
srand((unsigned int)time(NULL));
- save_settings();
setup_handlers();
printf("has pkeys: %d\n", pkeys_supported);
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index c2c542fe7b17..4bdb3a0c7a60 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -385,6 +385,7 @@ CATEGORY="ksm_numa" run_test ./ksm_tests -N -m 0
CATEGORY="ksm" run_test ./ksm_functional_tests
# protection_keys tests
+nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages)
if [ -x ./protection_keys_32 ]
then
CATEGORY="pkey" run_test ./protection_keys_32
@@ -394,6 +395,7 @@ if [ -x ./protection_keys_64 ]
then
CATEGORY="pkey" run_test ./protection_keys_64
fi
+echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages
if [ -x ./soft-dirty ]
then
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index 6c988bd2f335..d3c7f5fb3e7b 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -300,7 +300,7 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
char **addr)
{
size_t i;
- int dummy;
+ int __attribute__((unused)) dummy = 0;
srand(time(NULL));
diff --git a/tools/testing/selftests/net/tcp_ao/lib/proc.c b/tools/testing/selftests/net/tcp_ao/lib/proc.c
index 2fb6dd8adba6..8b984fa04286 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/proc.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/proc.c
@@ -86,7 +86,7 @@ static void netstat_read_type(FILE *fnetstat, struct netstat **dest, char *line)
pos = strchr(line, ' ') + 1;
- if (fscanf(fnetstat, type->header_name) == EOF)
+ if (fscanf(fnetstat, "%[^ :]", type->header_name) == EOF)
test_error("fscanf(%s)", type->header_name);
if (fread(&tmp, 1, 1, fnetstat) != 1 || tmp != ':')
test_error("Unexpected netstat format (%c)", tmp);
diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c
index 92276f916f2f..e408b9243b2c 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/setup.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c
@@ -17,37 +17,37 @@ static pthread_mutex_t ksft_print_lock = PTHREAD_MUTEX_INITIALIZER;
void __test_msg(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_print_msg(buf);
+ ksft_print_msg("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_ok(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_pass(buf);
+ ksft_test_result_pass("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_fail(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_fail(buf);
+ ksft_test_result_fail("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_xfail(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_xfail(buf);
+ ksft_test_result_xfail("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_error(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_error(buf);
+ ksft_test_result_error("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_skip(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_skip(buf);
+ ksft_test_result_skip("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index 7df8b8700e39..a2fe88d35ac0 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -256,8 +256,6 @@ static int test_wait_fds(int sk[], size_t nr, bool is_writable[],
static void test_client_active_rst(unsigned int port)
{
- /* one in queue, another accept()ed */
- unsigned int wait_for = backlog + 2;
int i, sk[3], err;
bool is_writable[ARRAY_SIZE(sk)] = {false};
unsigned int last = ARRAY_SIZE(sk) - 1;
@@ -275,16 +273,20 @@ static void test_client_active_rst(unsigned int port)
for (i = 0; i < last; i++) {
err = _test_connect_socket(sk[i], this_ip_dest, port,
(i == 0) ? TEST_TIMEOUT_SEC : -1);
-
if (err < 0)
test_error("failed to connect()");
}
- synchronize_threads(); /* 2: connection accept()ed, another queued */
- err = test_wait_fds(sk, last, is_writable, wait_for, TEST_TIMEOUT_SEC);
+ synchronize_threads(); /* 2: two connections: one accept()ed, another queued */
+ err = test_wait_fds(sk, last, is_writable, last, TEST_TIMEOUT_SEC);
if (err < 0)
test_error("test_wait_fds(): %d", err);
+ /* async connect() with third sk to get into request_sock_queue */
+ err = _test_connect_socket(sk[last], this_ip_dest, port, -1);
+ if (err < 0)
+ test_error("failed to connect()");
+
synchronize_threads(); /* 3: close listen socket */
if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
test_fail("Failed to send data on connected socket");
@@ -292,13 +294,14 @@ static void test_client_active_rst(unsigned int port)
test_ok("Verified established tcp connection");
synchronize_threads(); /* 4: finishing up */
- err = _test_connect_socket(sk[last], this_ip_dest, port, -1);
- if (err < 0)
- test_error("failed to connect()");
synchronize_threads(); /* 5: closed active sk */
- err = test_wait_fds(sk, ARRAY_SIZE(sk), NULL,
- wait_for, TEST_TIMEOUT_SEC);
+ /*
+ * Wait for 2 connections: one accepted, another in the accept queue,
+ * the one in request_sock_queue won't get fully established, so
+ * doesn't receive an active RST, see inet_csk_listen_stop().
+ */
+ err = test_wait_fds(sk, last, NULL, last, TEST_TIMEOUT_SEC);
if (err < 0)
test_error("select(): %d", err);
diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
index 452de131fa3a..517930f9721b 100644
--- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
+++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
@@ -21,7 +21,7 @@ static void make_listen(int sk)
static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info,
const char *tst)
{
- struct tcp_ao_info_opt tmp;
+ struct tcp_ao_info_opt tmp = {};
socklen_t len = sizeof(tmp);
if (getsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, &tmp, &len))
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index 1d975bf52af3..85b3baa3f7f3 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -34,7 +34,7 @@
#endif
#ifndef UDP_MAX_SEGMENTS
-#define UDP_MAX_SEGMENTS (1 << 6UL)
+#define UDP_MAX_SEGMENTS (1 << 7UL)
#endif
#define CONST_MTU_TEST 1500
diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
index 505294da1b9f..d6f99eb9be65 100644
--- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
+++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
@@ -154,7 +154,7 @@ static int dev_papr_vpd_null_handle(void)
static int papr_vpd_close_handle_without_reading(void)
{
const int devfd = open(DEVPATH, O_RDONLY);
- struct papr_location_code lc;
+ struct papr_location_code lc = { .str = "", };
int fd;
SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c
index c537d52fafc5..a40541bb7c7d 100644
--- a/tools/testing/selftests/riscv/hwprobe/cbo.c
+++ b/tools/testing/selftests/riscv/hwprobe/cbo.c
@@ -19,7 +19,7 @@
#include "hwprobe.h"
#include "../../kselftest.h"
-#define MK_CBO(fn) cpu_to_le32((fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15)
+#define MK_CBO(fn) le32_bswap((uint32_t)(fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15)
static char mem[4096] __aligned(4096) = { [0 ... 4095] = 0xa5 };
diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.h b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
index e3fccb390c4d..f3de970c3222 100644
--- a/tools/testing/selftests/riscv/hwprobe/hwprobe.h
+++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
@@ -4,6 +4,16 @@
#include <stddef.h>
#include <asm/hwprobe.h>
+#if __BYTE_ORDER == __BIG_ENDIAN
+# define le32_bswap(_x) \
+ ((((_x) & 0x000000ffU) << 24) | \
+ (((_x) & 0x0000ff00U) << 8) | \
+ (((_x) & 0x00ff0000U) >> 8) | \
+ (((_x) & 0xff000000U) >> 24))
+#else
+# define le32_bswap(_x) (_x)
+#endif
+
/*
* Rather than relying on having a new enough libc to define this, just do it
* ourselves. This way we don't need to be coupled to a new-enough libc to
diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
index b5d592d4099e..d975a6767329 100644
--- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c
+++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
@@ -158,6 +158,20 @@ static void handle_sigsys(int sig, siginfo_t *info, void *ucontext)
/* In preparation for sigreturn. */
SYSCALL_DISPATCH_OFF(glob_sel);
+
+ /*
+ * The tests for argument handling assume that `syscall(x) == x`. This
+ * is a NOP on x86 because the syscall number is passed in %rax, which
+ * happens to also be the function ABI return register. Other
+ * architectures may need to swizzle the arguments around.
+ */
+#if defined(__riscv)
+/* REG_A7 is not defined in libc headers */
+# define REG_A7 (REG_A0 + 7)
+
+ ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A0] =
+ ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A7];
+#endif
}
TEST(dispatch_and_return)
diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c
index d49dd3ffd0d9..c001dd79179d 100644
--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -66,7 +66,7 @@ static int check_diff(struct timeval start, struct timeval end)
diff = end.tv_usec - start.tv_usec;
diff += (end.tv_sec - start.tv_sec) * USECS_PER_SEC;
- if (abs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) {
+ if (llabs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) {
printf("Diff too high: %lld..", diff);
return -1;
}
@@ -184,80 +184,71 @@ static int check_timer_create(int which)
return 0;
}
-int remain;
-__thread int got_signal;
+static pthread_t ctd_thread;
+static volatile int ctd_count, ctd_failed;
-static void *distribution_thread(void *arg)
+static void ctd_sighandler(int sig)
{
- while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
- return NULL;
+ if (pthread_self() != ctd_thread)
+ ctd_failed = 1;
+ ctd_count--;
}
-static void distribution_handler(int nr)
+static void *ctd_thread_func(void *arg)
{
- if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED))
- __atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED);
-}
-
-/*
- * Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID
- * timer signals. This primarily tests that the kernel does not favour any one.
- */
-static int check_timer_distribution(void)
-{
- int err, i;
- timer_t id;
- const int nthreads = 10;
- pthread_t threads[nthreads];
struct itimerspec val = {
.it_value.tv_sec = 0,
.it_value.tv_nsec = 1000 * 1000,
.it_interval.tv_sec = 0,
.it_interval.tv_nsec = 1000 * 1000,
};
+ timer_t id;
- remain = nthreads + 1; /* worker threads + this thread */
- signal(SIGALRM, distribution_handler);
- err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id);
- if (err < 0) {
- ksft_perror("Can't create timer");
- return -1;
- }
- err = timer_settime(id, 0, &val, NULL);
- if (err < 0) {
- ksft_perror("Can't set timer");
- return -1;
- }
+ /* 1/10 seconds to ensure the leader sleeps */
+ usleep(10000);
- for (i = 0; i < nthreads; i++) {
- err = pthread_create(&threads[i], NULL, distribution_thread,
- NULL);
- if (err) {
- ksft_print_msg("Can't create thread: %s (%d)\n",
- strerror(errno), errno);
- return -1;
- }
- }
+ ctd_count = 100;
+ if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id))
+ return "Can't create timer\n";
+ if (timer_settime(id, 0, &val, NULL))
+ return "Can't set timer\n";
- /* Wait for all threads to receive the signal. */
- while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
+ while (ctd_count > 0 && !ctd_failed)
+ ;
- for (i = 0; i < nthreads; i++) {
- err = pthread_join(threads[i], NULL);
- if (err) {
- ksft_print_msg("Can't join thread: %s (%d)\n",
- strerror(errno), errno);
- return -1;
- }
- }
+ if (timer_delete(id))
+ return "Can't delete timer\n";
- if (timer_delete(id)) {
- ksft_perror("Can't delete timer");
- return -1;
- }
+ return NULL;
+}
+
+/*
+ * Test that only the running thread receives the timer signal.
+ */
+static int check_timer_distribution(void)
+{
+ const char *errmsg;
- ksft_test_result_pass("check_timer_distribution\n");
+ signal(SIGALRM, ctd_sighandler);
+
+ errmsg = "Can't create thread\n";
+ if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL))
+ goto err;
+
+ errmsg = "Can't join thread\n";
+ if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg)
+ goto err;
+
+ if (!ctd_failed)
+ ksft_test_result_pass("check signal distribution\n");
+ else if (ksft_min_kernel_version(6, 3))
+ ksft_test_result_fail("check signal distribution\n");
+ else
+ ksft_test_result_skip("check signal distribution (old kernel)\n");
return 0;
+err:
+ ksft_print_msg("%s", errmsg);
+ return -1;
}
int main(int argc, char **argv)
diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c
index 48b9a803235a..d13ebde20322 100644
--- a/tools/testing/selftests/timers/valid-adjtimex.c
+++ b/tools/testing/selftests/timers/valid-adjtimex.c
@@ -21,9 +21,6 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
-
-
-
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
@@ -62,45 +59,47 @@ int clear_time_state(void)
#define NUM_FREQ_OUTOFRANGE 4
#define NUM_FREQ_INVALID 2
+#define SHIFTED_PPM (1 << 16)
+
long valid_freq[NUM_FREQ_VALID] = {
- -499<<16,
- -450<<16,
- -400<<16,
- -350<<16,
- -300<<16,
- -250<<16,
- -200<<16,
- -150<<16,
- -100<<16,
- -75<<16,
- -50<<16,
- -25<<16,
- -10<<16,
- -5<<16,
- -1<<16,
+ -499 * SHIFTED_PPM,
+ -450 * SHIFTED_PPM,
+ -400 * SHIFTED_PPM,
+ -350 * SHIFTED_PPM,
+ -300 * SHIFTED_PPM,
+ -250 * SHIFTED_PPM,
+ -200 * SHIFTED_PPM,
+ -150 * SHIFTED_PPM,
+ -100 * SHIFTED_PPM,
+ -75 * SHIFTED_PPM,
+ -50 * SHIFTED_PPM,
+ -25 * SHIFTED_PPM,
+ -10 * SHIFTED_PPM,
+ -5 * SHIFTED_PPM,
+ -1 * SHIFTED_PPM,
-1000,
- 1<<16,
- 5<<16,
- 10<<16,
- 25<<16,
- 50<<16,
- 75<<16,
- 100<<16,
- 150<<16,
- 200<<16,
- 250<<16,
- 300<<16,
- 350<<16,
- 400<<16,
- 450<<16,
- 499<<16,
+ 1 * SHIFTED_PPM,
+ 5 * SHIFTED_PPM,
+ 10 * SHIFTED_PPM,
+ 25 * SHIFTED_PPM,
+ 50 * SHIFTED_PPM,
+ 75 * SHIFTED_PPM,
+ 100 * SHIFTED_PPM,
+ 150 * SHIFTED_PPM,
+ 200 * SHIFTED_PPM,
+ 250 * SHIFTED_PPM,
+ 300 * SHIFTED_PPM,
+ 350 * SHIFTED_PPM,
+ 400 * SHIFTED_PPM,
+ 450 * SHIFTED_PPM,
+ 499 * SHIFTED_PPM,
};
long outofrange_freq[NUM_FREQ_OUTOFRANGE] = {
- -1000<<16,
- -550<<16,
- 550<<16,
- 1000<<16,
+ -1000 * SHIFTED_PPM,
+ -550 * SHIFTED_PPM,
+ 550 * SHIFTED_PPM,
+ 1000 * SHIFTED_PPM,
};
#define LONG_MAX (~0UL>>1)
diff --git a/tools/testing/selftests/turbostat/defcolumns.py b/tools/testing/selftests/turbostat/defcolumns.py
new file mode 100755
index 000000000000..d9b042097da7
--- /dev/null
+++ b/tools/testing/selftests/turbostat/defcolumns.py
@@ -0,0 +1,60 @@
+#!/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+from shutil import which
+
+turbostat = which('turbostat')
+if turbostat is None:
+ print('Could not find turbostat binary')
+ exit(1)
+
+timeout = which('timeout')
+if timeout is None:
+ print('Could not find timeout binary')
+ exit(1)
+
+proc_turbostat = subprocess.run([turbostat, '--list'], capture_output = True)
+if proc_turbostat.returncode != 0:
+ print(f'turbostat failed with {proc_turbostat.returncode}')
+ exit(1)
+
+#
+# By default --list reports also "usec" and "Time_Of_Day_Seconds" columns
+# which are only visible when running with --debug.
+#
+expected_columns_debug = proc_turbostat.stdout.replace(b',', b'\t').strip()
+expected_columns = expected_columns_debug.replace(b'usec\t', b'').replace(b'Time_Of_Day_Seconds\t', b'').replace(b'X2APIC\t', b'').replace(b'APIC\t', b'')
+
+#
+# Run turbostat with no options for 10 seconds and send SIGINT
+#
+timeout_argv = [timeout, '--preserve-status', '-s', 'SIGINT', '-k', '3', '1s']
+turbostat_argv = [turbostat, '-i', '0.250']
+
+print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True)
+proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+if proc_turbostat.returncode != 0:
+ print(f'turbostat failed with {proc_turbostat.returncode}')
+ exit(1)
+actual_columns = proc_turbostat.stdout.split(b'\n')[0]
+if expected_columns != actual_columns:
+ print(f'turbostat column check failed\n{expected_columns=}\n{actual_columns=}')
+ exit(1)
+print('OK')
+
+#
+# Same, but with --debug
+#
+turbostat_argv.append('--debug')
+
+print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True)
+proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+if proc_turbostat.returncode != 0:
+ print(f'turbostat failed with {proc_turbostat.returncode}')
+ exit(1)
+actual_columns = proc_turbostat.stdout.split(b'\n')[0]
+if expected_columns_debug != actual_columns:
+ print(f'turbostat column check failed\n{expected_columns_debug=}\n{actual_columns=}')
+ exit(1)
+print('OK')