Merge branch 'kvm-arm64/vtr-patch' into next

* kvm-arm64/vtr-patch:
  : Inline patching of ICH_VTR_EL2 constant, courtesy of Marc Zyngier
  :
  : Unify readers of ICH_VTR_EL2 on an instruction-patched constant value,
  : avoiding system register accesses known to trap under nested
  : virtualization and sharing the implementation between pKVM and 'regular'
  : KVM.
  KVM: arm64: vgic-v3: Kill kvm_vgic_global_state.ich_vtr_el2
  KVM: arm64: vgic-v3: Simplify initial GICv3 configuration sampling
  KVM: arm64: Convert most ICH_VTR_EL2 accesses to inlined literal value
  KVM: arm64: Add a helper providing an inlined literal value for ICH_VTR_EL2
  KVM: arm64: Move GICv3 broken SEIS implementation detection to a CPU errrata
  KVM: arm64: vgic-v3: Make vtr_to_* helpers use architectural field symbols

Signed-off-by: Oliver Upton <oupton@kernel.org>

arch/arm64/include/asm/kvm_asm.h

@@ -282,7 +282,7 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu);
 
-extern u64 __vgic_v3_get_gic_config(void);
+extern bool __vgic_v3_get_gic_config(void);
 extern void __vgic_v3_init_lrs(void);
 
 #define __KVM_EXTABLE(from, to)						\

arch/arm64/kernel/cpu_errata.c

@@ -272,7 +272,7 @@ has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
 	return is_midr_in_range(&range) && has_dic;
 }
 
-static const struct midr_range impdef_pmuv3_cpus[] = {
+static const struct midr_range apple_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM),
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM),
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO),
@@ -301,7 +301,14 @@ static bool has_impdef_pmuv3(const struct arm64_cpu_capabilities *entry, int sco
 	if (pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
 		return false;
 
-	return is_midr_in_range_list(impdef_pmuv3_cpus);
+	return is_midr_in_range_list(apple_cpus);
+}
+
+static bool has_broken_gic_v3_seis(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	return (is_kernel_in_hyp_mode() &&
+		is_midr_in_range_list(apple_cpus) &&
+		(read_sysreg_s(SYS_ICH_VTR_EL2) & ICH_VTR_EL2_SEIS));
 }
 
 static void cpu_enable_impdef_pmuv3_traps(const struct arm64_cpu_capabilities *__unused)
@@ -1009,6 +1016,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.matches = has_impdef_pmuv3,
 		.cpu_enable = cpu_enable_impdef_pmuv3_traps,
 	},
+	{
+		.desc = "Known broken GICv3 SEIS implementation",
+		.capability = ARM64_WORKAROUND_GICv3_BROKEN_SEIS,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_broken_gic_v3_seis,
+	},
 	{
 	}
 };

arch/arm64/kernel/image-vars.h

@@ -93,6 +93,7 @@ KVM_NVHE_ALIAS(spectre_bhb_patch_wa3);
 KVM_NVHE_ALIAS(spectre_bhb_patch_clearbhb);
 KVM_NVHE_ALIAS(alt_cb_patch_nops);
 KVM_NVHE_ALIAS(kvm_compute_ich_hcr_trap_bits);
+KVM_NVHE_ALIAS(kvm_patch_ich_vtr_el2);
 
 /* Global kernel state accessed by nVHE hyp code. */
 KVM_NVHE_ALIAS(kvm_vgic_global_state);

arch/arm64/kvm/hyp/vgic-v3-sr.c

@@ -16,9 +16,9 @@
 
 #include "../../vgic/vgic.h"
 
-#define vtr_to_max_lr_idx(v)		((v) & 0xf)
-#define vtr_to_nr_pre_bits(v)		((((u32)(v) >> 26) & 7) + 1)
-#define vtr_to_nr_apr_regs(v)		(1 << (vtr_to_nr_pre_bits(v) - 5))
+#define vtr_to_max_lr_idx(v)		FIELD_GET(ICH_VTR_EL2_ListRegs, (v))
+#define vtr_to_nr_pre_bits(v)		(FIELD_GET(ICH_VTR_EL2_PREbits, (v)) + 1)
+#define vtr_to_nr_apr_regs(v)		BIT(vtr_to_nr_pre_bits(v) - 5)
 
 u64 __gic_v3_get_lr(unsigned int lr)
 {
@@ -367,7 +367,7 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
 	u64 val;
 	u32 nr_pre_bits;
 
-	val = read_gicreg(ICH_VTR_EL2);
+	val = vgic_ich_vtr();
 	nr_pre_bits = vtr_to_nr_pre_bits(val);
 
 	switch (nr_pre_bits) {
@@ -400,7 +400,7 @@ static void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 	u64 val;
 	u32 nr_pre_bits;
 
-	val = read_gicreg(ICH_VTR_EL2);
+	val = vgic_ich_vtr();
 	nr_pre_bits = vtr_to_nr_pre_bits(val);
 
 	switch (nr_pre_bits) {
@@ -430,33 +430,19 @@ static void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
 
 void __vgic_v3_init_lrs(void)
 {
-	int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2));
+	int max_lr_idx = vtr_to_max_lr_idx(vgic_ich_vtr());
 	int i;
 
 	for (i = 0; i <= max_lr_idx; i++)
 		__gic_v3_set_lr(0, i);
 }
 
-/*
- * Return the GIC CPU configuration:
- * - [31:0]  ICH_VTR_EL2
- * - [62:32] RES0
- * - [63]    MMIO (GICv2) capable
- */
-u64 __vgic_v3_get_gic_config(void)
+/* Return true if GICv3 is MMIO (GICv2) capable, false otherwise */
+bool __vgic_v3_get_gic_config(void)
 {
 	u64 val, sre;
 	unsigned long flags = 0;
 
-	/*
-	 * In compat mode, we cannot access ICC_SRE_EL1 at any EL
-	 * other than EL1 itself; just return the
-	 * ICH_VTR_EL2. ICC_IDR0_EL1 is only implemented on a GICv5
-	 * system, so we first check if we have GICv5 support.
-	 */
-	if (cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF))
-		return read_gicreg(ICH_VTR_EL2);
-
 	sre = read_gicreg(ICC_SRE_EL1);
 	/*
 	 * To check whether we have a MMIO-based (GICv2 compatible)
@@ -497,10 +483,7 @@ u64 __vgic_v3_get_gic_config(void)
 		isb();
 	}
 
-	val  = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
-	val |= read_gicreg(ICH_VTR_EL2);
-
-	return val;
+	return !(val & ICC_SRE_EL1_SRE);
 }
 
 static void __vgic_v3_compat_mode_enable(void)
@@ -540,7 +523,7 @@ void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if)
 static int __vgic_v3_bpr_min(void)
 {
 	/* See Pseudocode for VPriorityGroup */
-	return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2));
+	return 8 - vtr_to_nr_pre_bits(vgic_ich_vtr());
 }
 
 static int __vgic_v3_get_group(struct kvm_vcpu *vcpu)
@@ -614,7 +597,7 @@ static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid,
 
 static int __vgic_v3_get_highest_active_priority(void)
 {
-	u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
+	u8 nr_apr_regs = vtr_to_nr_apr_regs(vgic_ich_vtr());
 	u32 hap = 0;
 	int i;
 
@@ -707,7 +690,7 @@ static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
 
 static int __vgic_v3_clear_highest_active_priority(void)
 {
-	u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
+	u8 nr_apr_regs = vtr_to_nr_apr_regs(vgic_ich_vtr());
 	u32 hap = 0;
 	int i;
 
@@ -1039,7 +1022,7 @@ static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 {
 	u32 vtr, val;
 
-	vtr = read_gicreg(ICH_VTR_EL2);
+	vtr = vgic_ich_vtr();
 	/* PRIbits */
 	val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT;
 	/* IDbits */

arch/arm64/kvm/nested.c

@@ -16,6 +16,7 @@
 #include <asm/sysreg.h>
 
 #include "sys_regs.h"
+#include "vgic/vgic.h"
 
 struct vncr_tlb {
 	/* The guest's VNCR_EL2 */
@@ -1985,7 +1986,7 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
 	/* ICH_HCR_EL2 */
 	resx.res0 = ICH_HCR_EL2_RES0;
 	resx.res1 = ICH_HCR_EL2_RES1;
-	if (!(kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_TDS))
+	if (!(vgic_ich_vtr() & ICH_VTR_EL2_TDS))
 		resx.res0 |= ICH_HCR_EL2_TDIR;
 	/* No GICv4 is presented to the guest */
 	resx.res0 |= ICH_HCR_EL2_DVIM | ICH_HCR_EL2_vSGIEOICount;

arch/arm64/kvm/vgic-sys-reg-v3.c

@@ -35,12 +35,12 @@ static int set_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 
 	vgic_v3_cpu->num_id_bits = host_id_bits;
 
-	host_seis = FIELD_GET(ICH_VTR_EL2_SEIS, kvm_vgic_global_state.ich_vtr_el2);
+	host_seis = FIELD_GET(ICH_VTR_EL2_SEIS, vgic_ich_vtr());
 	seis = FIELD_GET(ICC_CTLR_EL1_SEIS_MASK, val);
 	if (host_seis != seis)
 		return -EINVAL;
 
-	host_a3v = FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2);
+	host_a3v = FIELD_GET(ICH_VTR_EL2_A3V, vgic_ich_vtr());
 	a3v = FIELD_GET(ICC_CTLR_EL1_A3V_MASK, val);
 	if (host_a3v != a3v)
 		return -EINVAL;
@@ -69,9 +69,9 @@ static int get_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 	val |= FIELD_PREP(ICC_CTLR_EL1_ID_BITS_MASK, vgic_v3_cpu->num_id_bits);
 	val |= FIELD_PREP(ICC_CTLR_EL1_SEIS_MASK,
 			  FIELD_GET(ICH_VTR_EL2_SEIS,
-				    kvm_vgic_global_state.ich_vtr_el2));
+				    vgic_ich_vtr()));
 	val |= FIELD_PREP(ICC_CTLR_EL1_A3V_MASK,
-			  FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2));
+			  FIELD_GET(ICH_VTR_EL2_A3V, vgic_ich_vtr()));
 	/*
 	 * The VMCR.CTLR value is in ICC_CTLR_EL1 layout.
 	 * Extract it directly using ICC_CTLR_EL1 reg definitions.

arch/arm64/kvm/vgic/vgic-v3.c

@@ -490,9 +490,9 @@ void vgic_v3_reset(struct kvm_vcpu *vcpu)
 	}
 
 	vcpu->arch.vgic_cpu.num_id_bits = FIELD_GET(ICH_VTR_EL2_IDbits,
-						    kvm_vgic_global_state.ich_vtr_el2);
+						    vgic_ich_vtr());
 	vcpu->arch.vgic_cpu.num_pri_bits = FIELD_GET(ICH_VTR_EL2_PRIbits,
-						     kvm_vgic_global_state.ich_vtr_el2) + 1;
+						     vgic_ich_vtr()) + 1;
 }
 
 void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu)
@@ -809,27 +809,9 @@ static int __init early_gicv4_enable(char *buf)
 }
 early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable);
 
-static const struct midr_range broken_seis[] = {
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX),
-	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX),
-	{},
-};
-
-static bool vgic_v3_broken_seis(void)
+static __always_inline bool vgic_v3_broken_seis(void)
 {
-	return (is_kernel_in_hyp_mode() &&
-		is_midr_in_range_list(broken_seis) &&
-		(read_sysreg_s(SYS_ICH_VTR_EL2) & ICH_VTR_EL2_SEIS));
+	return cpus_have_cap(ARM64_WORKAROUND_GICv3_BROKEN_SEIS);
 }
 
 void noinstr kvm_compute_ich_hcr_trap_bits(struct alt_instr *alt,
@@ -876,6 +858,61 @@ void noinstr kvm_compute_ich_hcr_trap_bits(struct alt_instr *alt,
 	*updptr = cpu_to_le32(insn);
 }
 
+void noinstr kvm_patch_ich_vtr_el2(struct alt_instr *alt,
+				   __le32 *origptr, __le32 *updptr,
+				   int nr_inst)
+{
+	struct arm_smccc_res res = {};
+	u32 insn, oinsn, rd, vtr;
+
+	/* No KVM? Nothing to do */
+	if (!is_hyp_mode_available())
+		return;
+
+	/* No v3, compat, nor the fruity erzatz of a GIC? Bugger off */
+	if (!cpus_have_cap(ARM64_HAS_GICV5_LEGACY) &&
+	    !cpus_have_cap(ARM64_HAS_GICV3_CPUIF) &&
+	    !vgic_v3_broken_seis())
+		return;
+
+	/*
+	 * At the point where this is called, we are guaranteed that if
+	 * we're running at EL1, then the EL2 stubs are still in place.
+	 */
+	if (is_kernel_in_hyp_mode())
+		res.a1 = read_sysreg_s(SYS_ICH_VTR_EL2);
+	else
+		arm_smccc_1_1_hvc(HVC_GET_ICH_VTR_EL2, &res);
+
+	if (res.a0 == HVC_STUB_ERR)
+		return;
+
+	vtr = res.a1;
+
+	if (vgic_v3_broken_seis())
+		vtr &= ~ICH_VTR_EL2_SEIS;
+
+	/* Compute target register */
+	oinsn = le32_to_cpu(*origptr);
+	rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, oinsn);
+
+	/* movz rd, #(vtr & 0xffff) */
+	insn = aarch64_insn_gen_movewide(rd,
+					 (u16)vtr,
+					 0,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_ZERO);
+	*updptr++ = cpu_to_le32(insn);
+
+	/* movk rd, #((vtr >> 16) & 0xffff), lsl #16 */
+	insn = aarch64_insn_gen_movewide(rd,
+					 (u16)(vtr >> 16),
+					 16,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_KEEP);
+	*updptr++ = cpu_to_le32(insn);
+}
+
 void vgic_v3_enable_cpuif_traps(void)
 {
 	u64 traps = vgic_ich_hcr_trap_bits();
@@ -899,12 +936,12 @@ void vgic_v3_enable_cpuif_traps(void)
  */
 int vgic_v3_probe(const struct gic_kvm_info *info)
 {
-	u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config);
+	u64 ich_vtr_el2;
 	bool has_v2;
 	int ret;
 
-	has_v2 = ich_vtr_el2 >> 63;
-	ich_vtr_el2 = (u32)ich_vtr_el2;
+	has_v2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config);
+	ich_vtr_el2 = vgic_ich_vtr();
 
 	/*
 	 * The ListRegs field is 5 bits, but there is an architectural
@@ -912,7 +949,6 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	 */
 	kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1;
 	kvm_vgic_global_state.can_emulate_gicv2 = false;
-	kvm_vgic_global_state.ich_vtr_el2 = ich_vtr_el2;
 
 	/* GICv4 support? */
 	if (info->has_v4) {
@@ -959,11 +995,6 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	if (has_v2)
 		static_branch_enable(&vgic_v3_has_v2_compat);
 
-	if (vgic_v3_broken_seis()) {
-		kvm_info("GICv3 with broken locally generated SEI\n");
-		kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_EL2_SEIS;
-	}
-
 	vgic_v3_enable_cpuif_traps();
 
 	kvm_vgic_global_state.vctrl_base = NULL;

arch/arm64/kvm/vgic/vgic-v5.c

@@ -40,7 +40,6 @@ static void vgic_v5_get_implemented_ppis(void)
 int vgic_v5_probe(const struct gic_kvm_info *info)
 {
 	bool v5_registered = false;
-	u64 ich_vtr_el2;
 	int ret;
 
 	kvm_vgic_global_state.type = VGIC_V5;
@@ -83,14 +82,12 @@ int vgic_v5_probe(const struct gic_kvm_info *info)
 	}
 
 	kvm_vgic_global_state.has_gcie_v3_compat = true;
-	ich_vtr_el2 =  kvm_call_hyp_ret(__vgic_v3_get_gic_config);
-	kvm_vgic_global_state.ich_vtr_el2 = (u32)ich_vtr_el2;
 
 	/*
 	 * The ListRegs field is 5 bits, but there is an architectural
 	 * maximum of 16 list registers. Just ignore bit 4...
 	 */
-	kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1;
+	kvm_vgic_global_state.nr_lr = (vgic_ich_vtr() & 0xf) + 1;
 
 	ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3);
 	if (ret) {

arch/arm64/kvm/vgic/vgic.h

@@ -71,11 +71,28 @@
 				 ICH_VTR_EL2_IDbits)
 #define KVM_ICH_VTR_EL2_RES1	ICH_VTR_EL2_nV4
 
+void kvm_patch_ich_vtr_el2(struct alt_instr *alt,
+			   __le32 *origptr, __le32 *updptr, int nr_inst);
+
+static inline u64 vgic_ich_vtr(void)
+{
+	u64 vtr;
+
+	/* All non-RES0 bits are in the bottom 32bits */
+	asm volatile(ALTERNATIVE_CB("movz %0, #0\n"
+				    "movk %0, #0, lsl #16\n",
+				    ARM64_ALWAYS_SYSTEM,
+				    kvm_patch_ich_vtr_el2)
+		     : "=r" (vtr));
+
+	return vtr;
+}
+
 static inline u64 kvm_get_guest_vtr_el2(void)
 {
 	u64 vtr;
 
-	vtr  = kvm_vgic_global_state.ich_vtr_el2;
+	vtr  = vgic_ich_vtr();
 	vtr &= ~KVM_ICH_VTR_EL2_RES0;
 	vtr |= KVM_ICH_VTR_EL2_RES1;
 

arch/arm64/tools/cpucaps

@@ -123,6 +123,7 @@ WORKAROUND_CAVIUM_TX2_219_TVM
 WORKAROUND_CLEAN_CACHE
 WORKAROUND_DEVICE_LOAD_ACQUIRE
 WORKAROUND_DISABLE_CNP
+WORKAROUND_GICv3_BROKEN_SEIS
 WORKAROUND_PMUV3_IMPDEF_TRAPS
 WORKAROUND_QCOM_FALKOR_E1003
 WORKAROUND_QCOM_ORYON_CNTVOFF

include/kvm/arm_vgic.h

@@ -176,8 +176,6 @@ struct vgic_global {
 	/* GICv3 compat mode on a GICv5 host */
 	bool			has_gcie_v3_compat;
 
-	u32			ich_vtr_el2;
-
 	/* GICv5 PPI capabilities */
 	struct {
 		DECLARE_BITMAP(impl_ppi_mask, VGIC_V5_NR_PRIVATE_IRQS);