summaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/acenv.h5
-rw-r--r--arch/x86/include/asm/apic.h5
-rw-r--r--arch/x86/include/asm/cpufeature.h4
-rw-r--r--arch/x86/include/asm/cpufeatures.h21
-rw-r--r--arch/x86/include/asm/fpu/xstate.h1
-rw-r--r--arch/x86/include/asm/hpet.h7
-rw-r--r--arch/x86/include/asm/hw_irq.h5
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h6
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h5
-rw-r--r--arch/x86/include/asm/mem_encrypt.h5
-rw-r--r--arch/x86/include/asm/mshyperv.h81
-rw-r--r--arch/x86/include/asm/msr-index.h9
-rw-r--r--arch/x86/include/asm/mwait.h4
-rw-r--r--arch/x86/include/asm/processor.h3
-rw-r--r--arch/x86/include/asm/pvclock.h2
-rw-r--r--arch/x86/include/asm/time.h1
-rw-r--r--arch/x86/include/asm/vdso/gettimeofday.h261
-rw-r--r--arch/x86/include/asm/vdso/vsyscall.h44
-rw-r--r--arch/x86/include/asm/vgtod.h75
-rw-r--r--arch/x86/include/asm/virtext.h4
-rw-r--r--arch/x86/include/asm/vsyscall.h6
-rw-r--r--arch/x86/include/asm/vvar.h7
-rw-r--r--arch/x86/include/uapi/asm/kvm.h33
-rw-r--r--arch/x86/include/uapi/asm/perf_regs.h3
25 files changed, 406 insertions, 193 deletions
diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h
index 1b010a859b8b..9aff97f0de7f 100644
--- a/arch/x86/include/asm/acenv.h
+++ b/arch/x86/include/asm/acenv.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* X86 specific ACPICA environments and implementation
*
* Copyright (C) 2014, Intel Corporation
* Author: Lv Zheng <lv.zheng@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#ifndef _ASM_X86_ACENV_H
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1340fa53b575..050e5f9ebf81 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -53,7 +53,7 @@ extern unsigned int apic_verbosity;
extern int local_apic_timer_c2_ok;
extern int disable_apic;
-extern unsigned int lapic_timer_frequency;
+extern unsigned int lapic_timer_period;
extern enum apic_intr_mode_id apic_intr_mode;
enum apic_intr_mode_id {
@@ -155,7 +155,6 @@ static inline int apic_force_enable(unsigned long addr)
extern int apic_force_enable(unsigned long addr);
#endif
-extern void apic_bsp_setup(bool upmode);
extern void apic_ap_setup(void);
/*
@@ -175,6 +174,7 @@ extern void lapic_assign_system_vectors(void);
extern void lapic_assign_legacy_vector(unsigned int isairq, bool replace);
extern void lapic_online(void);
extern void lapic_offline(void);
+extern bool apic_needs_pit(void);
#else /* !CONFIG_X86_LOCAL_APIC */
static inline void lapic_shutdown(void) { }
@@ -188,6 +188,7 @@ static inline void init_bsp_APIC(void) { }
static inline void apic_intr_mode_init(void) { }
static inline void lapic_assign_system_vectors(void) { }
static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { }
+static inline bool apic_needs_pit(void) { return true; }
#endif /* !CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_X2APIC
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1d337c51f7e6..58acda503817 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -22,8 +22,8 @@ enum cpuid_leafs
CPUID_LNX_3,
CPUID_7_0_EBX,
CPUID_D_1_EAX,
- CPUID_F_0_EDX,
- CPUID_F_1_EDX,
+ CPUID_LNX_4,
+ CPUID_7_1_EAX,
CPUID_8000_0008_EBX,
CPUID_6_EAX,
CPUID_8000_000A_EDX,
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 75f27ee2c263..998c2cc08363 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -239,12 +239,14 @@
#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */
#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */
#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */
#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */
#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */
#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */
#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */
#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
@@ -269,13 +271,19 @@
#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */
#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
-#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */
+/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0xf, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */
+#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring */
-#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
@@ -322,6 +330,7 @@
#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */
#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 7e42b285c856..c6136d79f8c0 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -47,7 +47,6 @@ extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
extern void __init update_regset_xstate_info(unsigned int size,
u64 xstate_mask);
-void fpu__xstate_clear_all_cpu_caps(void);
void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr);
const void *get_xsave_field_ptr(int xfeature_nr);
int using_compacted_format(void);
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 67385d56d4f4..6352dee37cda 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -75,16 +75,15 @@ extern unsigned int hpet_readl(unsigned int a);
extern void force_hpet_resume(void);
struct irq_data;
-struct hpet_dev;
+struct hpet_channel;
struct irq_domain;
extern void hpet_msi_unmask(struct irq_data *data);
extern void hpet_msi_mask(struct irq_data *data);
-extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
-extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
+extern void hpet_msi_write(struct hpet_channel *hc, struct msi_msg *msg);
extern struct irq_domain *hpet_create_irq_domain(int hpet_id);
extern int hpet_assign_irq(struct irq_domain *domain,
- struct hpet_dev *dev, int dev_num);
+ struct hpet_channel *hc, int dev_num);
#ifdef CONFIG_HPET_EMULATE_RTC
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 32e666e1231e..cbd97e22d2f3 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -150,8 +150,11 @@ extern char irq_entries_start[];
#define trace_irq_entries_start irq_entries_start
#endif
+extern char spurious_entries_start[];
+
#define VECTOR_UNUSED NULL
-#define VECTOR_RETRIGGERED ((void *)~0UL)
+#define VECTOR_SHUTDOWN ((void *)~0UL)
+#define VECTOR_RETRIGGERED ((void *)~1UL)
typedef struct irq_desc* vector_irq_t[NR_VECTORS];
DECLARE_PER_CPU(vector_irq_t, vector_irq);
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index cdf44aa9a501..af78cd72b8f3 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -401,6 +401,12 @@ enum HV_GENERIC_SET_FORMAT {
#define HV_STATUS_INVALID_CONNECTION_ID 18
#define HV_STATUS_INSUFFICIENT_BUFFERS 19
+/*
+ * The Hyper-V TimeRefCount register and the TSC
+ * page provide a guest VM clock with 100ns tick rate
+ */
+#define HV_CLOCK_HZ (NSEC_PER_SEC/100)
+
typedef struct _HV_REFERENCE_TSC_PAGE {
__u32 tsc_sequence;
__u32 res1;
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 310118805f57..0278aa66ef62 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -56,6 +56,7 @@
#define INTEL_FAM6_ICELAKE_XEON_D 0x6C
#define INTEL_FAM6_ICELAKE_DESKTOP 0x7D
#define INTEL_FAM6_ICELAKE_MOBILE 0x7E
+#define INTEL_FAM6_ICELAKE_NNPI 0x9D
/* "Small Core" Processors (Atom) */
@@ -76,6 +77,7 @@
#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */
#define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */
#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */
+
#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */
/* Xeon Phi */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 450d69a1e6fa..26d1eb83f72a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Kernel-based Virtual Machine driver for Linux
*
* This header defines architecture specific interfaces, x86 version
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- *
*/
#ifndef _ASM_X86_KVM_HOST_H
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 616f8e637bc3..0c196c47d621 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* AMD Memory Encryption Support
*
* Copyright (C) 2016 Advanced Micro Devices, Inc.
*
* Author: Tom Lendacky <thomas.lendacky@amd.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
*/
#ifndef __X86_MEM_ENCRYPT_H__
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index cc60e617931c..f4fa8a9d5d0b 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -105,6 +105,17 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
#define hv_get_crash_ctl(val) \
rdmsrl(HV_X64_MSR_CRASH_CTL, val)
+#define hv_get_time_ref_count(val) \
+ rdmsrl(HV_X64_MSR_TIME_REF_COUNT, val)
+
+#define hv_get_reference_tsc(val) \
+ rdmsrl(HV_X64_MSR_REFERENCE_TSC, val)
+#define hv_set_reference_tsc(val) \
+ wrmsrl(HV_X64_MSR_REFERENCE_TSC, val)
+#define hv_set_clocksource_vdso(val) \
+ ((val).archdata.vclock_mode = VCLOCK_HVCLOCK)
+#define hv_get_raw_timer() rdtsc_ordered()
+
void hyperv_callback_vector(void);
void hyperv_reenlightenment_vector(void);
#ifdef CONFIG_TRACING
@@ -133,7 +144,6 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {}
#if IS_ENABLED(CONFIG_HYPERV)
-extern struct clocksource *hyperv_cs;
extern void *hv_hypercall_pg;
extern void __percpu **hyperv_pcpu_input_arg;
@@ -387,73 +397,4 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
}
#endif /* CONFIG_HYPERV */
-#ifdef CONFIG_HYPERV_TSCPAGE
-struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
- u64 *cur_tsc)
-{
- u64 scale, offset;
- u32 sequence;
-
- /*
- * The protocol for reading Hyper-V TSC page is specified in Hypervisor
- * Top-Level Functional Specification ver. 3.0 and above. To get the
- * reference time we must do the following:
- * - READ ReferenceTscSequence
- * A special '0' value indicates the time source is unreliable and we
- * need to use something else. The currently published specification
- * versions (up to 4.0b) contain a mistake and wrongly claim '-1'
- * instead of '0' as the special value, see commit c35b82ef0294.
- * - ReferenceTime =
- * ((RDTSC() * ReferenceTscScale) >> 64) + ReferenceTscOffset
- * - READ ReferenceTscSequence again. In case its value has changed
- * since our first reading we need to discard ReferenceTime and repeat
- * the whole sequence as the hypervisor was updating the page in
- * between.
- */
- do {
- sequence = READ_ONCE(tsc_pg->tsc_sequence);
- if (!sequence)
- return U64_MAX;
- /*
- * Make sure we read sequence before we read other values from
- * TSC page.
- */
- smp_rmb();
-
- scale = READ_ONCE(tsc_pg->tsc_scale);
- offset = READ_ONCE(tsc_pg->tsc_offset);
- *cur_tsc = rdtsc_ordered();
-
- /*
- * Make sure we read sequence after we read all other values
- * from TSC page.
- */
- smp_rmb();
-
- } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
-
- return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
-}
-
-static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
-{
- u64 cur_tsc;
-
- return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
-}
-
-#else
-static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
-{
- return NULL;
-}
-
-static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
- u64 *cur_tsc)
-{
- BUG();
- return U64_MAX;
-}
-#endif
#endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 979ef971cc78..6b4fc2788078 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -61,6 +61,15 @@
#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31
#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
+#define MSR_IA32_UMWAIT_CONTROL 0xe1
+#define MSR_IA32_UMWAIT_CONTROL_C02_DISABLE BIT(0)
+#define MSR_IA32_UMWAIT_CONTROL_RESERVED BIT(1)
+/*
+ * The time field is bit[31:2], but representing a 32bit value with
+ * bit[1:0] zero.
+ */
+#define MSR_IA32_UMWAIT_CONTROL_TIME_MASK (~0x03U)
+
#define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2
#define NHM_C3_AUTO_DEMOTE (1UL << 25)
#define NHM_C1_AUTO_DEMOTE (1UL << 26)
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index eb0f80ce8524..e28f8b723b5c 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -86,9 +86,9 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
{
- mds_idle_clear_cpu_buffers();
-
trace_hardirqs_on();
+
+ mds_idle_clear_cpu_buffers();
/* "mwait %eax, %ecx;" */
asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
:: "a" (eax), "c" (ecx));
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c34a35c78618..e57d2ca2ed87 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -144,7 +144,8 @@ enum cpuid_regs_idx {
#define X86_VENDOR_TRANSMETA 7
#define X86_VENDOR_NSC 8
#define X86_VENDOR_HYGON 9
-#define X86_VENDOR_NUM 10
+#define X86_VENDOR_ZHAOXIN 10
+#define X86_VENDOR_NUM 11
#define X86_VENDOR_UNKNOWN 0xff
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index b6033680d458..19b695ff2c68 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -2,7 +2,7 @@
#ifndef _ASM_X86_PVCLOCK_H
#define _ASM_X86_PVCLOCK_H
-#include <linux/clocksource.h>
+#include <asm/clocksource.h>
#include <asm/pvclock-abi.h>
/* some helper functions for xen and kvm pv clock sources */
diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h
index cef818b16045..8ac563abb567 100644
--- a/arch/x86/include/asm/time.h
+++ b/arch/x86/include/asm/time.h
@@ -7,6 +7,7 @@
extern void hpet_time_init(void);
extern void time_init(void);
+extern bool pit_timer_init(void);
extern struct clock_event_device *global_clock_event;
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
new file mode 100644
index 000000000000..ae91429129a6
--- /dev/null
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -0,0 +1,261 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Fast user context implementation of clock_gettime, gettimeofday, and time.
+ *
+ * Copyright (C) 2019 ARM Limited.
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <uapi/linux/time.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+#include <asm/unistd.h>
+#include <asm/msr.h>
+#include <asm/pvclock.h>
+#include <clocksource/hyperv_timer.h>
+
+#define __vdso_data (VVAR(_vdso_data))
+
+#define VDSO_HAS_TIME 1
+
+#define VDSO_HAS_CLOCK_GETRES 1
+
+/*
+ * Declare the memory-mapped vclock data pages. These come from hypervisors.
+ * If we ever reintroduce something like direct access to an MMIO clock like
+ * the HPET again, it will go here as well.
+ *
+ * A load from any of these pages will segfault if the clock in question is
+ * disabled, so appropriate compiler barriers and checks need to be used
+ * to prevent stray loads.
+ *
+ * These declarations MUST NOT be const. The compiler will assume that
+ * an extern const variable has genuinely constant contents, and the
+ * resulting code won't work, since the whole point is that these pages
+ * change over time, possibly while we're accessing them.
+ */
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+/*
+ * This is the vCPU 0 pvclock page. We only use pvclock from the vDSO
+ * if the hypervisor tells us that all vCPUs can get valid data from the
+ * vCPU 0 page.
+ */
+extern struct pvclock_vsyscall_time_info pvclock_page
+ __attribute__((visibility("hidden")));
+#endif
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+extern struct ms_hyperv_tsc_page hvclock_page
+ __attribute__((visibility("hidden")));
+#endif
+
+#ifndef BUILD_VDSO32
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ long ret;
+
+ asm ("syscall" : "=a" (ret), "=m" (*_ts) :
+ "0" (__NR_clock_gettime), "D" (_clkid), "S" (_ts) :
+ "rcx", "r11");
+
+ return ret;
+}
+
+static __always_inline
+long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+ struct timezone *_tz)
+{
+ long ret;
+
+ asm("syscall" : "=a" (ret) :
+ "0" (__NR_gettimeofday), "D" (_tv), "S" (_tz) : "memory");
+
+ return ret;
+}
+
+static __always_inline
+long clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ long ret;
+
+ asm ("syscall" : "=a" (ret), "=m" (*_ts) :
+ "0" (__NR_clock_getres), "D" (_clkid), "S" (_ts) :
+ "rcx", "r11");
+
+ return ret;
+}
+
+#else
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[clock], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*_ts)
+ : "0" (__NR_clock_gettime64), [clock] "g" (_clkid), "c" (_ts)
+ : "edx");
+
+ return ret;
+}
+
+static __always_inline
+long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+ struct timezone *_tz)
+{
+ long ret;
+
+ asm(
+ "mov %%ebx, %%edx \n"
+ "mov %2, %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret)
+ : "0" (__NR_gettimeofday), "g" (_tv), "c" (_tz)
+ : "memory", "edx");
+
+ return ret;
+}
+
+static __always_inline long
+clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[clock], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*_ts)
+ : "0" (__NR_clock_getres_time64), [clock] "g" (_clkid), "c" (_ts)
+ : "edx");
+
+ return ret;
+}
+
+#endif
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+static u64 vread_pvclock(void)
+{
+ const struct pvclock_vcpu_time_info *pvti = &pvclock_page.pvti;
+ u32 version;
+ u64 ret;
+
+ /*
+ * Note: The kernel and hypervisor must guarantee that cpu ID
+ * number maps 1:1 to per-CPU pvclock time info.
+ *
+ * Because the hypervisor is entirely unaware of guest userspace
+ * preemption, it cannot guarantee that per-CPU pvclock time
+ * info is updated if the underlying CPU changes or that that
+ * version is increased whenever underlying CPU changes.
+ *
+ * On KVM, we are guaranteed that pvti updates for any vCPU are
+ * atomic as seen by *all* vCPUs. This is an even stronger
+ * guarantee than we get with a normal seqlock.
+ *
+ * On Xen, we don't appear to have that guarantee, but Xen still
+ * supplies a valid seqlock using the version field.
+ *
+ * We only do pvclock vdso timing at all if
+ * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
+ * mean that all vCPUs have matching pvti and that the TSC is
+ * synced, so we can just look at vCPU 0's pvti.
+ */
+
+ do {
+ version = pvclock_read_begin(pvti);
+
+ if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT)))
+ return U64_MAX;
+
+ ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
+ } while (pvclock_read_retry(pvti, version));
+
+ return ret;
+}
+#endif
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+static u64 vread_hvclock(void)
+{
+ return hv_read_tsc_page(&hvclock_page);
+}
+#endif
+
+static inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+ if (clock_mode == VCLOCK_TSC)
+ return (u64)rdtsc_ordered();
+ /*
+ * For any memory-mapped vclock type, we need to make sure that gcc
+ * doesn't cleverly hoist a load before the mode check. Otherwise we
+ * might end up touching the memory-mapped page even if the vclock in
+ * question isn't enabled, which will segfault. Hence the barriers.
+ */
+#ifdef CONFIG_PARAVIRT_CLOCK
+ if (clock_mode == VCLOCK_PVCLOCK) {
+ barrier();
+ return vread_pvclock();
+ }
+#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+ if (clock_mode == VCLOCK_HVCLOCK) {
+ barrier();
+ return vread_hvclock();
+ }
+#endif
+ return U64_MAX;
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+ return __vdso_data;
+}
+
+/*
+ * x86 specific delta calculation.
+ *
+ * The regular implementation assumes that clocksource reads are globally
+ * monotonic. The TSC can be slightly off across sockets which can cause
+ * the regular delta calculation (@cycles - @last) to return a huge time
+ * jump.
+ *
+ * Therefore it needs to be verified that @cycles are greater than
+ * @last. If not then use @last, which is the base time of the current
+ * conversion period.
+ *
+ * This variant also removes the masking of the subtraction because the
+ * clocksource mask of all VDSO capable clocksources on x86 is U64_MAX
+ * which would result in a pointless operation. The compiler cannot
+ * optimize it away as the mask comes from the vdso data and is not compile
+ * time constant.
+ */
+static __always_inline
+u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
+{
+ if (cycles > last)
+ return (cycles - last) * mult;
+ return 0;
+}
+#define vdso_calc_delta vdso_calc_delta
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
new file mode 100644
index 000000000000..0026ab2123ce
--- /dev/null
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/hrtimer.h>
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+
+int vclocks_used __read_mostly;
+
+DEFINE_VVAR(struct vdso_data, _vdso_data);
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline
+struct vdso_data *__x86_get_k_vdso_data(void)
+{
+ return _vdso_data;
+}
+#define __arch_get_k_vdso_data __x86_get_k_vdso_data
+
+static __always_inline
+int __x86_get_clock_mode(struct timekeeper *tk)
+{
+ int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
+
+ /* Mark the new vclock used. */
+ BUILD_BUG_ON(VCLOCK_MAX >= 32);
+ WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
+
+ return vclock_mode;
+}
+#define __arch_get_clock_mode __x86_get_clock_mode
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 913a133f8e6f..a2638c6124ed 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -3,7 +3,9 @@
#define _ASM_X86_VGTOD_H
#include <linux/compiler.h>
-#include <linux/clocksource.h>
+#include <asm/clocksource.h>
+#include <vdso/datapage.h>
+#include <vdso/helpers.h>
#include <uapi/linux/time.h>
@@ -13,81 +15,10 @@ typedef u64 gtod_long_t;
typedef unsigned long gtod_long_t;
#endif
-/*
- * There is one of these objects in the vvar page for each
- * vDSO-accelerated clockid. For high-resolution clocks, this encodes
- * the time corresponding to vsyscall_gtod_data.cycle_last. For coarse
- * clocks, this encodes the actual time.
- *
- * To confuse the reader, for high-resolution clocks, nsec is left-shifted
- * by vsyscall_gtod_data.shift.
- */
-struct vgtod_ts {
- u64 sec;
- u64 nsec;
-};
-
-#define VGTOD_BASES (CLOCK_TAI + 1)
-#define VGTOD_HRES (BIT(CLOCK_REALTIME) | BIT(CLOCK_MONOTONIC) | BIT(CLOCK_TAI))
-#define VGTOD_COARSE (BIT(CLOCK_REALTIME_COARSE) | BIT(CLOCK_MONOTONIC_COARSE))
-
-/*
- * vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time
- * so be carefull by modifying this structure.
- */
-struct vsyscall_gtod_data {
- unsigned int seq;
-
- int vclock_mode;
- u64 cycle_last;
- u64 mask;
- u32 mult;
- u32 shift;
-
- struct vgtod_ts basetime[VGTOD_BASES];
-
- int tz_minuteswest;
- int tz_dsttime;
-};
-extern struct vsyscall_gtod_data vsyscall_gtod_data;
-
extern int vclocks_used;
static inline bool vclock_was_used(int vclock)
{
return READ_ONCE(vclocks_used) & (1 << vclock);
}
-static inline unsigned int gtod_read_begin(const struct vsyscall_gtod_data *s)
-{
- unsigned int ret;
-
-repeat:
- ret = READ_ONCE(s->seq);
- if (unlikely(ret & 1)) {
- cpu_relax();
- goto repeat;
- }
- smp_rmb();
- return ret;
-}
-
-static inline int gtod_read_retry(const struct vsyscall_gtod_data *s,
- unsigned int start)
-{
- smp_rmb();
- return unlikely(s->seq != start);
-}
-
-static inline void gtod_write_begin(struct vsyscall_gtod_data *s)
-{
- ++s->seq;
- smp_wmb();
-}
-
-static inline void gtod_write_end(struct vsyscall_gtod_data *s)
-{
- smp_wmb();
- ++s->seq;
-}
-
#endif /* _ASM_X86_VGTOD_H */
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 1fc7a0d1e877..9aad0e0876fb 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/* CPU virtualization extensions handling
*
* This should carry the code for handling CPU virtualization extensions
@@ -8,9 +9,6 @@
* Copyright (C) 2008, Red Hat Inc.
*
* Contains code from KVM, Copyright (C) 2006 Qumranet, Inc.
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
*/
#ifndef _ASM_X86_VIRTEX_H
#define _ASM_X86_VIRTEX_H
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index b986b2ca688a..ab60a71a8dcb 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -13,10 +13,12 @@ extern void set_vsyscall_pgtable_user_bits(pgd_t *root);
* Called on instruction fetch fault in vsyscall page.
* Returns true if handled.
*/
-extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
+extern bool emulate_vsyscall(unsigned long error_code,
+ struct pt_regs *regs, unsigned long address);
#else
static inline void map_vsyscall(void) {}
-static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
+static inline bool emulate_vsyscall(unsigned long error_code,
+ struct pt_regs *regs, unsigned long address)
{
return false;
}
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index e474f5c6e387..32f5d9a0b90e 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -32,19 +32,20 @@
extern char __vvar_page;
#define DECLARE_VVAR(offset, type, name) \
- extern type vvar_ ## name __attribute__((visibility("hidden")));
+ extern type vvar_ ## name[CS_BASES] \
+ __attribute__((visibility("hidden")));
#define VVAR(name) (vvar_ ## name)
#define DEFINE_VVAR(type, name) \
- type name \
+ type name[CS_BASES] \
__attribute__((section(".vvar_" #name), aligned(16))) __visible
#endif
/* DECLARE_VVAR(offset, type, name) */
-DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)
+DECLARE_VVAR(128, struct vdso_data, _vdso_data)
#undef DECLARE_VVAR
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 7a0e64ccd6ff..d6ab5b4d15e5 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -383,6 +383,9 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
+#define KVM_STATE_NESTED_FORMAT_VMX 0
+#define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */
+
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
#define KVM_STATE_NESTED_EVMCS 0x00000004
@@ -390,9 +393,16 @@ struct kvm_sync_regs {
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
-struct kvm_vmx_nested_state {
+#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000
+
+struct kvm_vmx_nested_state_data {
+ __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
+ __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
+};
+
+struct kvm_vmx_nested_state_hdr {
__u64 vmxon_pa;
- __u64 vmcs_pa;
+ __u64 vmcs12_pa;
struct {
__u16 flags;
@@ -401,24 +411,25 @@ struct kvm_vmx_nested_state {
/* for KVM_CAP_NESTED_STATE */
struct kvm_nested_state {
- /* KVM_STATE_* flags */
__u16 flags;
-
- /* 0 for VMX, 1 for SVM. */
__u16 format;
-
- /* 128 for SVM, 128 + VMCS size for VMX. */
__u32 size;
union {
- /* VMXON, VMCS */
- struct kvm_vmx_nested_state vmx;
+ struct kvm_vmx_nested_state_hdr vmx;
/* Pad the header to 128 bytes. */
__u8 pad[120];
- };
+ } hdr;
- __u8 data[0];
+ /*
+ * Define data region as 0 bytes to preserve backwards-compatability
+ * to old definition of kvm_nested_state in order to avoid changing
+ * KVM_{GET,PUT}_NESTED_STATE ioctl values.
+ */
+ union {
+ struct kvm_vmx_nested_state_data vmx[0];
+ } data;
};
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index ac67bbea10ca..7c9d2bb3833b 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -52,4 +52,7 @@ enum perf_event_x86_regs {
/* These include both GPRs and XMMX registers */
PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
};
+
+#define PERF_REG_EXTENDED_MASK (~((1ULL << PERF_REG_X86_XMM0) - 1))
+
#endif /* _ASM_X86_PERF_REGS_H */