Expose c0 and SW encap ICM for RDMA

These two series from Mark and Shun extend RDMA mlx5 API.

Mark's series provides c0 register used to match egress
traffic sent by local device.

Shun's series adds new type for ICM area.

Link: https://lore.kernel.org/all/cover.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>

77 files changed, 2769 insertions, 1841 deletions

diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 5f6f84837a49..7c7493cb571f 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -79,13 +79,15 @@
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_A520	0xD80
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_A715	0xD4D
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
 #define ARM_CPU_PART_CORTEX_A78C	0xD4B
 
-#define APM_CPU_PART_POTENZA		0x000
+#define APM_CPU_PART_XGENE		0x000
+#define APM_CPU_VAR_POTENZA		0x00
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
 #define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
@@ -148,6 +150,7 @@
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index f7ddd73a8c0f..89d2fc872d9f 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -505,6 +505,38 @@ struct kvm_smccc_filter {
 #define KVM_HYPERCALL_EXIT_SMC		(1U << 0)
 #define KVM_HYPERCALL_EXIT_16BIT	(1U << 1)
 
+/*
+ * Get feature ID registers userspace writable mask.
+ *
+ * From DDI0487J.a, D19.2.66 ("ID_AA64MMFR2_EL1, AArch64 Memory Model
+ * Feature Register 2"):
+ *
+ * "The Feature ID space is defined as the System register space in
+ * AArch64 with op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7},
+ * op2=={0-7}."
+ *
+ * This covers all currently known R/O registers that indicate
+ * anything useful feature wise, including the ID registers.
+ *
+ * If we ever need to introduce a new range, it will be described as
+ * such in the range field.
+ */
+#define KVM_ARM_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2)		\
+	({								\
+		__u64 __op1 = (op1) & 3;				\
+		__op1 -= (__op1 == 3);					\
+		(__op1 << 6 | ((crm) & 7) << 3 | (op2));		\
+	})
+
+#define KVM_ARM_FEATURE_ID_RANGE	0
+#define KVM_ARM_FEATURE_ID_RANGE_SIZE	(3 * 8 * 8)
+
+struct reg_mask_range {
+	__u64 addr;		/* Pointer to mask array */
+	__u32 range;		/* Requested range */
+	__u32 reserved[13];
+};
+
 #endif
 
 #endif /* __ARM_KVM_H__ */
diff --git a/tools/arch/arm64/include/uapi/asm/perf_regs.h b/tools/arch/arm64/include/uapi/asm/perf_regs.h
index fd157f46727e..86e556429e0e 100644
--- a/tools/arch/arm64/include/uapi/asm/perf_regs.h
+++ b/tools/arch/arm64/include/uapi/asm/perf_regs.h
@@ -36,11 +36,13 @@ enum perf_event_arm_regs {
 	PERF_REG_ARM64_LR,
 	PERF_REG_ARM64_SP,
 	PERF_REG_ARM64_PC,
+	PERF_REG_ARM64_MAX,
 
 	/* Extended/pseudo registers */
-	PERF_REG_ARM64_VG = 46, // SVE Vector Granule
-
-	PERF_REG_ARM64_MAX = PERF_REG_ARM64_PC + 1,
-	PERF_REG_ARM64_EXTENDED_MAX = PERF_REG_ARM64_VG + 1
+	PERF_REG_ARM64_VG = 46,				/* SVE Vector Granule */
+	PERF_REG_ARM64_EXTENDED_MAX
 };
+
+#define PERF_REG_EXTENDED_MASK	(1ULL << PERF_REG_ARM64_VG)
+
 #endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/tools/arch/arm64/tools/Makefile b/tools/arch/arm64/tools/Makefile
index 7f64b8bb5107..7b42feedf647 100644
--- a/tools/arch/arm64/tools/Makefile
+++ b/tools/arch/arm64/tools/Makefile
@@ -22,7 +22,7 @@ endif
 arm64_tools_dir = $(top_srcdir)/arch/arm64/tools
 arm64_sysreg_tbl = $(arm64_tools_dir)/sysreg
 arm64_gen_sysreg = $(arm64_tools_dir)/gen-sysreg.awk
-arm64_generated_dir = $(top_srcdir)/tools/arch/arm64/include/generated
+arm64_generated_dir = $(OUTPUT)arch/arm64/include/generated
 arm64_sysreg_defs = $(arm64_generated_dir)/asm/sysreg-defs.h
 
 all: $(arm64_sysreg_defs)
diff --git a/tools/arch/parisc/include/uapi/asm/errno.h b/tools/arch/parisc/include/uapi/asm/errno.h
index 87245c584784..8d94739d75c6 100644
--- a/tools/arch/parisc/include/uapi/asm/errno.h
+++ b/tools/arch/parisc/include/uapi/asm/errno.h
@@ -75,7 +75,6 @@
 
 /* We now return you to your regularly scheduled HPUX. */
 
-#define ENOSYM		215	/* symbol does not exist in executable */
 #define	ENOTSOCK	216	/* Socket operation on non-socket */
 #define	EDESTADDRREQ	217	/* Destination address required */
 #define	EMSGSIZE	218	/* Message too long */
@@ -101,7 +100,6 @@
 #define	ETIMEDOUT	238	/* Connection timed out */
 #define	ECONNREFUSED	239	/* Connection refused */
 #define	EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
-#define	EREMOTERELEASE	240	/* Remote peer released connection */
 #define	EHOSTDOWN	241	/* Host is down */
 #define	EHOSTUNREACH	242	/* No route to host */
 
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index a73cf01a1606..abe926d43cbe 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -159,6 +159,22 @@ struct kvm_s390_vm_cpu_subfunc {
 	__u8 reserved[1728];
 };
 
+#define KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST	6
+#define KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST	7
+
+#define KVM_S390_VM_CPU_UV_FEAT_NR_BITS	64
+struct kvm_s390_vm_cpu_uv_feat {
+	union {
+		struct {
+			__u64 : 4;
+			__u64 ap : 1;		/* bit 4 */
+			__u64 ap_intr : 1;	/* bit 5 */
+			__u64 : 58;
+		};
+		__u64 feat;
+	};
+};
+
 /* kvm attributes for crypto */
 #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW	0
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW	1
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 798e60b5454b..4af140cf5719 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -198,7 +198,6 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
-#define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_XCOMPACTED		( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */
@@ -308,6 +307,11 @@
 #define X86_FEATURE_MSR_TSX_CTRL	(11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
+#define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
+
+#define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
+#define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
+#define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -380,6 +384,7 @@
 #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_SHSTK		(16*32+ 7) /* "" Shadow stack */
 #define X86_FEATURE_GFNI		(16*32+ 8) /* Galois Field New Instructions */
 #define X86_FEATURE_VAES		(16*32+ 9) /* Vector AES */
 #define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
@@ -438,11 +443,16 @@
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */
+#define X86_FEATURE_WRMSR_XX_BASE_NS	(20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
 #define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* "" Null Selector Clears Base */
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* "" Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* "" SMM_CTL MSR is not present */
 
+#define X86_FEATURE_SBPB		(20*32+27) /* "" Selective Branch Prediction Barrier */
+#define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */
+#define X86_FEATURE_SRSO_NO		(20*32+29) /* "" CPU is not affected by SRSO */
+
 /*
  * BUG word(s)
  */
@@ -484,5 +494,9 @@
 #define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
+#define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
 
+/* 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 */
 #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 fafe9be7a6f4..702d93fdd10e 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -105,6 +105,18 @@
 # define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
 #endif
 
+#ifdef CONFIG_X86_USER_SHADOW_STACK
+#define DISABLE_USER_SHSTK	0
+#else
+#define DISABLE_USER_SHSTK	(1 << (X86_FEATURE_USER_SHSTK & 31))
+#endif
+
+#ifdef CONFIG_X86_KERNEL_IBT
+#define DISABLE_IBT	0
+#else
+#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -120,7 +132,7 @@
 #define DISABLED_MASK9	(DISABLE_SGX)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
-			 DISABLE_CALL_DEPTH_TRACKING)
+			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
 #define DISABLED_MASK12	(DISABLE_LAM)
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
@@ -128,7 +140,7 @@
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
 			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK18	0
+#define DISABLED_MASK18	(DISABLE_IBT)
 #define DISABLED_MASK19	0
 #define DISABLED_MASK20	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 1d111350197f..1d51e1850ed0 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -222,6 +222,7 @@
 #define MSR_INTEGRITY_CAPS_ARRAY_BIST          BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT)
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT	4
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST	BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
+#define MSR_INTEGRITY_CAPS_SAF_GEN_MASK	GENMASK_ULL(10, 9)
 
 #define MSR_LBR_NHM_FROM		0x00000680
 #define MSR_LBR_NHM_TO			0x000006c0
@@ -553,6 +554,7 @@
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
+#define MSR_AMD64_TW_CFG		0xc0011023
 
 #define MSR_AMD64_DE_CFG		0xc0011029
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1
@@ -637,12 +639,21 @@
 /* AMD Last Branch Record MSRs */
 #define MSR_AMD64_LBR_SELECT			0xc000010e
 
+/* Zen4 */
+#define MSR_ZEN4_BP_CFG                 0xc001102e
+#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
+
+/* Fam 19h MSRs */
+#define MSR_F19H_UMC_PERF_CTL           0xc0010800
+#define MSR_F19H_UMC_PERF_CTR           0xc0010801
+
+/* Zen 2 */
+#define MSR_ZEN2_SPECTRAL_CHICKEN       0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT   BIT_ULL(1)
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
-#define MSR_ZEN2_SPECTRAL_CHICKEN	0xc00110e3
-#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT	BIT_ULL(1)
-
 /* Fam 16h MSRs */
 #define MSR_F16H_L2I_PERF_CTL		0xc0010230
 #define MSR_F16H_L2I_PERF_CTR		0xc0010231
@@ -1112,12 +1123,16 @@
 #define MSR_IA32_VMX_MISC_INTEL_PT                 (1ULL << 14)
 #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
 #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
-/* AMD-V MSRs */
 
+/* AMD-V MSRs */
 #define MSR_VM_CR                       0xc0010114
 #define MSR_VM_IGNNE                    0xc0010115
 #define MSR_VM_HSAVE_PA                 0xc0010117
 
+#define SVM_VM_CR_VALID_MASK		0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK		0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK		0x0010ULL
+
 /* Hardware Feedback Interface */
 #define MSR_IA32_HW_FEEDBACK_PTR        0x17d0
 #define MSR_IA32_HW_FEEDBACK_CONFIG     0x17d1
diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h
index e8d7ebbca1a4..384e2cc6ac19 100644
--- a/tools/arch/x86/include/uapi/asm/prctl.h
+++ b/tools/arch/x86/include/uapi/asm/prctl.h
@@ -23,9 +23,21 @@
 #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