Intel-SIG: DiamondRapids (DMR) new ISAs enabling

arch/x86/include/asm/cpufeatures.h

@@ -331,6 +331,7 @@
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* Support for VPMADD52[H,L]UQ */
 #define X86_FEATURE_LAM			(12*32+26) /* "lam" Linear Address Masking */
+#define X86_FEATURE_MOVRS		(12*32+31) /* MOVRS instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_AMD_IBPB_RET	(13*32+30) /* "" IBPB clears return address predictor */
@@ -476,6 +477,7 @@
 #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 */
 #define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32 + 5) /* "" Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_APX			(21*32 + 9) /* Advanced Performance Extensions */
 
 #define X86_FEATURE_TSA_SQ_NO          (21*32+11) /* "" AMD CPU not vulnerable to TSA-SQ */
 #define X86_FEATURE_TSA_L1_NO          (21*32+12) /* "" AMD CPU not vulnerable to TSA-L1 */

arch/x86/include/asm/cpuid.h

@@ -180,6 +180,7 @@ static __always_inline bool cpuid_function_is_indexed(u32 function)
 	case 0x1d:
 	case 0x1e:
 	case 0x1f:
+	case 0x24:
 	case 0x8000001d:
 		return true;
 	}

arch/x86/include/asm/fpu/types.h

@@ -123,6 +123,7 @@ enum xfeature {
 	XFEATURE_RSRVD_COMP_16,
 	XFEATURE_XTILE_CFG,
 	XFEATURE_XTILE_DATA,
+	XFEATURE_APX,
 
 	XFEATURE_MAX,
 };
@@ -143,6 +144,7 @@ enum xfeature {
 #define XFEATURE_MASK_LBR		(1 << XFEATURE_LBR)
 #define XFEATURE_MASK_XTILE_CFG		(1 << XFEATURE_XTILE_CFG)
 #define XFEATURE_MASK_XTILE_DATA	(1 << XFEATURE_XTILE_DATA)
+#define XFEATURE_MASK_APX		(1 << XFEATURE_APX)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
 #define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK \
@@ -301,6 +303,13 @@ struct xtile_data {
 	struct reg_1024_byte		tmm;
 } __packed;
 
+/*
+ * State component 19: 8B extended general purpose register.
+ */
+struct apx_state {
+	u64				egpr[16];
+} __packed;
+
 /*
  * State component 10 is supervisor state used for context-switching the
  * PASID state.

arch/x86/include/asm/fpu/xstate.h

@@ -36,7 +36,8 @@
 				      XFEATURE_MASK_PKRU | \
 				      XFEATURE_MASK_BNDREGS | \
 				      XFEATURE_MASK_BNDCSR | \
-				      XFEATURE_MASK_XTILE)
+				      XFEATURE_MASK_XTILE | \
+				      XFEATURE_MASK_APX)
 
 /*
  * Features which are restored when returning to user space.

arch/x86/include/asm/kvm_host.h

@@ -712,6 +712,26 @@ struct kvm_queued_exception {
 	bool has_payload;
 };
 
+/*
+ * Hardware-defined CPUID leafs that are either scattered by the kernel or are
+ * unknown to the kernel, but need to be directly used by KVM.  Note, these
+ * word values conflict with the kernel's "bug" caps, but KVM doesn't use those.
+ */
+enum kvm_only_cpuid_leafs {
+	CPUID_12_EAX	 = NCAPINTS,
+	CPUID_7_1_EDX,
+	CPUID_8000_0007_EDX,
+	CPUID_8000_0022_EAX,
+	CPUID_7_2_EDX,
+	CPUID_8000_0021_ECX,
+	CPUID_24_0_EBX,
+	CPUID_1E_1_EAX,
+	CPUID_24_1_ECX,
+	NR_KVM_CPU_CAPS,
+
+	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through

arch/x86/kernel/cpu/cpuid-deps.c

@@ -28,6 +28,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_PKU,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_MPX,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_XGETBV1,			X86_FEATURE_XSAVE     },
+	{ X86_FEATURE_APX,			X86_FEATURE_XSAVE     },
 	{ X86_FEATURE_CMOV,			X86_FEATURE_FXSR      },
 	{ X86_FEATURE_MMX,			X86_FEATURE_FXSR      },
 	{ X86_FEATURE_MMXEXT,			X86_FEATURE_MMX       },

arch/x86/kernel/cpu/scattered.c

@@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
 	{ X86_FEATURE_INTEL_PPIN,	CPUID_EBX,  0, 0x00000007, 1 },
+	{ X86_FEATURE_APX,		CPUID_EDX, 21, 0x00000007, 1 },
 	{ X86_FEATURE_RRSBA_CTRL,	CPUID_EDX,  2, 0x00000007, 2 },
 	{ X86_FEATURE_BHI_CTRL,		CPUID_EDX,  4, 0x00000007, 2 },
 	{ X86_FEATURE_CQM_LLC,		CPUID_EDX,  1, 0x0000000f, 0 },

arch/x86/kernel/fpu/core.c

@@ -735,7 +735,7 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
 /*
  * Reset current->fpu memory state to the init values.
  */
-static void fpu_reset_fpregs(void)
+static void fpu_reset_fpstate_regs(void)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
@@ -770,7 +770,7 @@ void fpu__clear_user_states(struct fpu *fpu)
 
 	fpregs_lock();
 	if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
-		fpu_reset_fpregs();
+		fpu_reset_fpstate_regs();
 		fpregs_unlock();
 		return;
 	}
@@ -803,7 +803,7 @@ void fpu__clear_user_states(struct fpu *fpu)
 void fpu_flush_thread(void)
 {
 	fpstate_reset(&current->thread.fpu);
-	fpu_reset_fpregs();
+	fpu_reset_fpstate_regs();
 }
 /*
  * Load FPU context before returning to userspace.

arch/x86/kernel/fpu/init.c

@@ -94,7 +94,6 @@ static void __init fpu__init_system_early_generic(void)
  * Boot time FPU feature detection code:
  */
 unsigned int mxcsr_feature_mask __ro_after_init = 0xffffffffu;
-EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
 
 static void __init fpu__init_system_mxcsr(void)
 {

arch/x86/kernel/fpu/signal.c

@@ -119,7 +119,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 {
 	struct xregs_state __user *x = buf;
 	struct _fpx_sw_bytes sw_bytes = {};
-	u32 xfeatures;
 	int err;
 
 	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
@@ -132,12 +131,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 	err |= __put_user(FP_XSTATE_MAGIC2,
 			  (__u32 __user *)(buf + fpstate->user_size));
 
-	/*
-	 * Read the xfeatures which we copied (directly from the cpu or
-	 * from the state in task struct) to the user buffers.
-	 */
-	err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
-
 	/*
 	 * For legacy compatible, we always set FP/SSE bits in the bit
 	 * vector while saving the state to the user context. This will
@@ -149,17 +142,16 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 	 * header as well as change any contents in the memory layout.
 	 * xrestore as part of sigreturn will capture all the changes.
 	 */
-	xfeatures |= XFEATURE_MASK_FPSSE;
-
-	err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
+	err |= set_xfeature_in_sigframe(x, XFEATURE_MASK_FPSSE);
 
 	return !err;
 }
 
 static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
 	if (use_xsave())
-		return xsave_to_user_sigframe(buf);
+		return xsave_to_user_sigframe(buf, pkru);
+
 	if (use_fxsr())
 		return fxsave_to_user_sigframe((struct fxregs_state __user *) buf);
 	else