Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

7 files changed, 82 insertions, 197 deletions

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index a38f8f9ba6..3c74343296 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -461,11 +461,15 @@
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various
- * CPUID levels like 0x80000022, etc.
+ * CPUID levels like 0x80000022, etc and Linux defined features.
  *
  * Reuse free bits when adding new feature flags!
  */
 #define X86_FEATURE_AMD_LBR_PMC_FREEZE	(21*32+ 0) /* AMD LBR and PMC Freeze */
+#define X86_FEATURE_CLEAR_BHB_LOOP	(21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
+#define X86_FEATURE_BHI_CTRL		(21*32+ 2) /* "" BHI_DIS_S HW control available */
+#define X86_FEATURE_CLEAR_BHB_HW	(21*32+ 3) /* "" BHI_DIS_S HW control enabled */
+#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */
 
 /*
  * BUG word(s)
@@ -515,4 +519,5 @@
 #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 */
+#define X86_BUG_BHI			X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/inat.h b/tools/arch/x86/include/asm/inat.h
index a610514003..253690eb3c 100644
--- a/tools/arch/x86/include/asm/inat.h
+++ b/tools/arch/x86/include/asm/inat.h
@@ -35,6 +35,8 @@
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
 #define INAT_PFX_EVEX	15	/* EVEX prefix */
+/* x86-64 REX2 prefix */
+#define INAT_PFX_REX2	16	/* 0xD5 */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -50,7 +52,7 @@
 
 /* Legacy prefix */
 #define INAT_PFX_OFFS	0
-#define INAT_PFX_BITS	4
+#define INAT_PFX_BITS	5
 #define INAT_PFX_MAX    ((1 << INAT_PFX_BITS) - 1)
 #define INAT_PFX_MASK	(INAT_PFX_MAX << INAT_PFX_OFFS)
 /* Escape opcodes */
@@ -77,6 +79,9 @@
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
 #define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
+#define INAT_NO_REX2	(1 << (INAT_FLAG_OFFS + 8))
+#define INAT_REX2_VARIANT	(1 << (INAT_FLAG_OFFS + 9))
+#define INAT_EVEX_SCALABLE	(1 << (INAT_FLAG_OFFS + 10))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -128,6 +133,11 @@ static inline int inat_is_rex_prefix(insn_attr_t attr)
 	return (attr & INAT_PFX_MASK) == INAT_PFX_REX;
 }
 
+static inline int inat_is_rex2_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_REX2;
+}
+
 static inline int inat_last_prefix_id(insn_attr_t attr)
 {
 	if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX)
@@ -227,4 +237,9 @@ static inline int inat_must_evex(insn_attr_t attr)
 {
 	return attr & INAT_EVEXONLY;
 }
+
+static inline int inat_evex_scalable(insn_attr_t attr)
+{
+	return attr & INAT_EVEX_SCALABLE;
+}
 #endif
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index 65c0d9ce1e..0e5abd896a 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -112,10 +112,15 @@ struct insn {
 #define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3)
 #define X86_SIB_BASE(sib) ((sib) & 0x07)
 
-#define X86_REX_W(rex) ((rex) & 8)
-#define X86_REX_R(rex) ((rex) & 4)
-#define X86_REX_X(rex) ((rex) & 2)
-#define X86_REX_B(rex) ((rex) & 1)
+#define X86_REX2_M(rex) ((rex) & 0x80)	/* REX2 M0 */
+#define X86_REX2_R(rex) ((rex) & 0x40)	/* REX2 R4 */
+#define X86_REX2_X(rex) ((rex) & 0x20)	/* REX2 X4 */
+#define X86_REX2_B(rex) ((rex) & 0x10)	/* REX2 B4 */
+
+#define X86_REX_W(rex) ((rex) & 8)	/* REX or REX2 W */
+#define X86_REX_R(rex) ((rex) & 4)	/* REX or REX2 R3 */
+#define X86_REX_X(rex) ((rex) & 2)	/* REX or REX2 X3 */
+#define X86_REX_B(rex) ((rex) & 1)	/* REX or REX2 B3 */
 
 /* VEX bit flags  */
 #define X86_VEX_W(vex)	((vex) & 0x80)	/* VEX3 Byte2 */
@@ -161,6 +166,18 @@ static inline void insn_get_attribute(struct insn *insn)
 /* Instruction uses RIP-relative addressing */
 extern int insn_rip_relative(struct insn *insn);
 
+static inline int insn_is_rex2(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return insn->rex_prefix.nbytes == 2;
+}
+
+static inline insn_byte_t insn_rex2_m_bit(struct insn *insn)
+{
+	return X86_REX2_M(insn->rex_prefix.bytes[1]);
+}
+
 static inline int insn_is_avx(struct insn *insn)
 {
 	if (!insn->prefixes.got)
@@ -198,6 +215,13 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
 		return X86_VEX_P(insn->vex_prefix.bytes[2]);
 }
 
+static inline insn_byte_t insn_vex_w_bit(struct insn *insn)
+{
+	if (insn->vex_prefix.nbytes < 3)
+		return 0;
+	return X86_VEX_W(insn->vex_prefix.bytes[2]);
+}
+
 /* Get the last prefix id from last prefix or VEX prefix */
 static inline int insn_last_prefix_id(struct insn *insn)
 {
diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h
deleted file mode 100644
index d18bfb238f..0000000000
--- a/tools/arch/x86/include/asm/irq_vectors.h
+++ /dev/null
@@ -1,140 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_IRQ_VECTORS_H
-#define _ASM_X86_IRQ_VECTORS_H
-
-#include <linux/threads.h>
-/*
- * Linux IRQ vector layout.
- *
- * There are 256 IDT entries (per CPU - each entry is 8 bytes) which can
- * be defined by Linux. They are used as a jump table by the CPU when a
- * given vector is triggered - by a CPU-external, CPU-internal or
- * software-triggered event.
- *
- * Linux sets the kernel code address each entry jumps to early during
- * bootup, and never changes them. This is the general layout of the
- * IDT entries:
- *
- *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
- *  Vectors  32 ... 127 : device interrupts
- *  Vector  128         : legacy int80 syscall interface
- *  Vectors 129 ... LOCAL_TIMER_VECTOR-1
- *  Vectors LOCAL_TIMER_VECTOR ... 255 : special interrupts
- *
- * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
- *
- * This file enumerates the exact layout of them:
- */
-
-/* This is used as an interrupt vector when programming the APIC. */
-#define NMI_VECTOR			0x02
-
-/*
- * IDT vectors usable for external interrupt sources start at 0x20.
- * (0x80 is the syscall vector, 0x30-0x3f are for ISA)
- */
-#define FIRST_EXTERNAL_VECTOR		0x20
-
-#define IA32_SYSCALL_VECTOR		0x80
-
-/*
- * Vectors 0x30-0x3f are used for ISA interrupts.
- *   round up to the next 16-vector boundary
- */
-#define ISA_IRQ_VECTOR(irq)		(((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq)
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- */
-
-#define SPURIOUS_APIC_VECTOR		0xff
-/*
- * Sanity check
- */
-#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F)
-# error SPURIOUS_APIC_VECTOR definition error
-#endif
-
-#define ERROR_APIC_VECTOR		0xfe
-#define RESCHEDULE_VECTOR		0xfd
-#define CALL_FUNCTION_VECTOR		0xfc
-#define CALL_FUNCTION_SINGLE_VECTOR	0xfb
-#define THERMAL_APIC_VECTOR		0xfa
-#define THRESHOLD_APIC_VECTOR		0xf9
-#define REBOOT_VECTOR			0xf8
-
-/*
- * Generic system vector for platform specific use
- */
-#define X86_PLATFORM_IPI_VECTOR		0xf7
-
-/*
- * IRQ work vector:
- */
-#define IRQ_WORK_VECTOR			0xf6
-
-/* 0xf5 - unused, was UV_BAU_MESSAGE */
-#define DEFERRED_ERROR_VECTOR		0xf4
-
-/* Vector on which hypervisor callbacks will be delivered */
-#define HYPERVISOR_CALLBACK_VECTOR	0xf3
-
-/* Vector for KVM to deliver posted interrupt IPI */
-#define POSTED_INTR_VECTOR		0xf2
-#define POSTED_INTR_WAKEUP_VECTOR	0xf1
-#define POSTED_INTR_NESTED_VECTOR	0xf0
-
-#define MANAGED_IRQ_SHUTDOWN_VECTOR	0xef
-
-#if IS_ENABLED(CONFIG_HYPERV)
-#define HYPERV_REENLIGHTENMENT_VECTOR	0xee
-#define HYPERV_STIMER0_VECTOR		0xed
-#endif
-
-#define LOCAL_TIMER_VECTOR		0xec
-
-#define NR_VECTORS			 256
-
-#ifdef CONFIG_X86_LOCAL_APIC
-#define FIRST_SYSTEM_VECTOR		LOCAL_TIMER_VECTOR
-#else
-#define FIRST_SYSTEM_VECTOR		NR_VECTORS
-#endif
-
-#define NR_EXTERNAL_VECTORS		(FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
-#define NR_SYSTEM_VECTORS		(NR_VECTORS - FIRST_SYSTEM_VECTOR)
-
-/*
- * Size the maximum number of interrupts.
- *
- * If the irq_desc[] array has a sparse layout, we can size things
- * generously - it scales up linearly with the maximum number of CPUs,
- * and the maximum number of IO-APICs, whichever is higher.
- *
- * In other cases we size more conservatively, to not create too large
- * static arrays.
- */
-
-#define NR_IRQS_LEGACY			16
-
-#define CPU_VECTOR_LIMIT		(64 * NR_CPUS)
-#define IO_APIC_VECTOR_LIMIT		(32 * MAX_IO_APICS)
-
-#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI)
-#define NR_IRQS						\
-	(CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ?	\
-		(NR_VECTORS + CPU_VECTOR_LIMIT)  :	\
-		(NR_VECTORS + IO_APIC_VECTOR_LIMIT))
-#elif defined(CONFIG_X86_IO_APIC)
-#define	NR_IRQS				(NR_VECTORS + IO_APIC_VECTOR_LIMIT)
-#elif defined(CONFIG_PCI_MSI)
-#define NR_IRQS				(NR_VECTORS + CPU_VECTOR_LIMIT)
-#else
-#define NR_IRQS				NR_IRQS_LEGACY
-#endif
-
-#endif /* _ASM_X86_IRQ_VECTORS_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 05956bd8ba..e022e6eb76 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -61,10 +61,13 @@
 #define SPEC_CTRL_SSBD			BIT(SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
 #define SPEC_CTRL_RRSBA_DIS_S_SHIFT	6	   /* Disable RRSBA behavior */
 #define SPEC_CTRL_RRSBA_DIS_S		BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
+#define SPEC_CTRL_BHI_DIS_S_SHIFT	10	   /* Disable Branch History Injection behavior */
+#define SPEC_CTRL_BHI_DIS_S		BIT(SPEC_CTRL_BHI_DIS_S_SHIFT)
 
 /* A mask for bits which the kernel toggles when controlling mitigations */
 #define SPEC_CTRL_MITIGATIONS_MASK	(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \
-							| SPEC_CTRL_RRSBA_DIS_S)
+							| SPEC_CTRL_RRSBA_DIS_S \
+							| SPEC_CTRL_BHI_DIS_S)
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
@@ -163,6 +166,14 @@
 						 * are restricted to targets in
 						 * kernel.
 						 */
+#define ARCH_CAP_BHI_NO			BIT(20)	/*
+						 * CPU is not affected by Branch
+						 * History Injection.
+						 */
+#define ARCH_CAP_XAPIC_DISABLE		BIT(21)	/*
+						 * IA32_XAPIC_DISABLE_STATUS MSR
+						 * supported
+						 */
 #define ARCH_CAP_PBRSB_NO		BIT(24)	/*
 						 * Not susceptible to Post-Barrier
 						 * Return Stack Buffer Predictions.
@@ -185,11 +196,6 @@
 						 * File.
 						 */
 
-#define ARCH_CAP_XAPIC_DISABLE		BIT(21)	/*
-						 * IA32_XAPIC_DISABLE_STATUS MSR
-						 * supported
-						 */
-
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
 						 * Writeback and invalidate the
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index ef11aa4cab..9fae1b73b5 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -457,8 +457,13 @@ struct kvm_sync_regs {
 
 #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE	0x00000001
 
-/* attributes for system fd (group 0) */
-#define KVM_X86_XCOMP_GUEST_SUPP	0
+/* vendor-independent attributes for system fd (group 0) */
+#define KVM_X86_GRP_SYSTEM		0
+#  define KVM_X86_XCOMP_GUEST_SUPP	0
+
+/* vendor-specific groups and attributes for system fd */
+#define KVM_X86_GRP_SEV			1
+#  define KVM_X86_SEV_VMSA_FEATURES	0
 
 struct kvm_vmx_nested_state_data {
 	__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
@@ -689,6 +694,9 @@ enum sev_cmd_id {
 	/* Guest Migration Extension */
 	KVM_SEV_SEND_CANCEL,
 
+	/* Second time is the charm; improved versions of the above ioctls.  */
+	KVM_SEV_INIT2,
+
 	KVM_SEV_NR_MAX,
 };
 
@@ -700,6 +708,14 @@ struct kvm_sev_cmd {
 	__u32 sev_fd;
 };
 
+struct kvm_sev_init {
+	__u64 vmsa_features;
+	__u32 flags;
+	__u16 ghcb_version;
+	__u16 pad1;
+	__u32 pad2[8];
+};
+
 struct kvm_sev_launch_start {
 	__u32 handle;
 	__u32 policy;
@@ -856,5 +872,7 @@ struct kvm_hyperv_eventfd {
 
 #define KVM_X86_DEFAULT_VM	0
 #define KVM_X86_SW_PROTECTED_VM	1
+#define KVM_X86_SEV_VM		2
+#define KVM_X86_SEV_ES_VM	3
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h
deleted file mode 100644
index 384e2cc6ac..0000000000
--- a/tools/arch/x86/include/uapi/asm/prctl.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_X86_PRCTL_H
-#define _ASM_X86_PRCTL_H
-
-#define ARCH_SET_GS			0x1001
-#define ARCH_SET_FS			0x1002
-#define ARCH_GET_FS			0x1003
-#define ARCH_GET_GS			0x1004
-
-#define ARCH_GET_CPUID			0x1011
-#define ARCH_SET_CPUID			0x1012
-
-#define ARCH_GET_XCOMP_SUPP		0x1021
-#define ARCH_GET_XCOMP_PERM		0x1022
-#define ARCH_REQ_XCOMP_PERM		0x1023
-#define ARCH_GET_XCOMP_GUEST_PERM	0x1024
-#define ARCH_REQ_XCOMP_GUEST_PERM	0x1025
-
-#define ARCH_XCOMP_TILECFG		17
-#define ARCH_XCOMP_TILEDATA		18
-
-#define ARCH_MAP_VDSO_X32		0x2001
-#define ARCH_MAP_VDSO_32		0x2002
-#define ARCH_MAP_VDSO_64		0x2003
-
-/* Don't use 0x3001-0x3004 because of old glibcs */
-
-#define ARCH_GET_UNTAG_MASK		0x4001
-#define ARCH_ENABLE_TAGGED_ADDR		0x4002
-#define ARCH_GET_MAX_TAG_BITS		0x4003
-#define ARCH_FORCE_TAGGED_SVA		0x4004
-
-#define ARCH_SHSTK_ENABLE		0x5001
-#define ARCH_SHSTK_DISABLE		0x5002
-#define ARCH_SHSTK_LOCK			0x5003
-#define ARCH_SHSTK_UNLOCK		0x5004
-#define ARCH_SHSTK_STATUS		0x5005
-
-/* ARCH_SHSTK_ features bits */
-#define ARCH_SHSTK_SHSTK		(1ULL <<  0)
-#define ARCH_SHSTK_WRSS			(1ULL <<  1)
-
-#endif /* _ASM_X86_PRCTL_H */