Merge branch kvm-arm64/misc-6.20 into kvmarm-master/next

* kvm-arm64/misc-6.20:
  : .
  : Misc KVM/arm64 changes for 6.20
  :
  : - Trivial FPSIMD cleanups
  :
  : - Calculate hyp VA size only once, avoiding potential mapping issues when
  :   VA bits is smaller than expected
  :
  : - Silence sparse warning for the HYP stack base
  :
  : - Fix error checking when handling FFA_VERSION
  :
  : - Add missing trap configuration for DBGWCR15_EL1
  :
  : - Don't try to deal with nested S2 when NV isn't enabled for a guest
  :
  : - Various spelling fixes
  : .
  KVM: arm64: nv: Avoid NV stage-2 code when NV is not supported
  KVM: arm64: Fix various comments
  KVM: arm64: nv: Add trap config for DBGWCR<15>_EL1
  KVM: arm64: Fix error checking for FFA_VERSION
  KVM: arm64: Fix missing <asm/stackpage/nvhe.h> include
  KVM: arm64: Calculate hyp VA size only once
  KVM: arm64: Remove ISB after writing FPEXC32_EL2
  KVM: arm64: Shuffle KVM_HOST_DATA_FLAG_* indices
  KVM: arm64: Fix comment in fpsimd_lazy_switch_to_host()

Signed-off-by: Marc Zyngier <maz@kernel.org>

11 files changed, 62 insertions, 46 deletions

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 26c1c3faedc3..5d5a3bbdb95e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -201,7 +201,7 @@ struct kvm_s2_mmu {
 	 * host to parse the guest S2.
 	 * This either contains:
 	 * - the virtual VTTBR programmed by the guest hypervisor with
-         *   CnP cleared
+	 *   CnP cleared
 	 * - The value 1 (VMID=0, BADDR=0, CnP=1) if invalid
 	 *
 	 * We also cache the full VTCR which gets used for TLB invalidation,
@@ -734,11 +734,11 @@ struct cpu_sve_state {
 struct kvm_host_data {
 #define KVM_HOST_DATA_FLAG_HAS_SPE			0
 #define KVM_HOST_DATA_FLAG_HAS_TRBE			1
-#define KVM_HOST_DATA_FLAG_TRBE_ENABLED			4
-#define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED	5
-#define KVM_HOST_DATA_FLAG_VCPU_IN_HYP_CONTEXT		6
-#define KVM_HOST_DATA_FLAG_L1_VNCR_MAPPED		7
-#define KVM_HOST_DATA_FLAG_HAS_BRBE			8
+#define KVM_HOST_DATA_FLAG_TRBE_ENABLED			2
+#define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED	3
+#define KVM_HOST_DATA_FLAG_VCPU_IN_HYP_CONTEXT		4
+#define KVM_HOST_DATA_FLAG_L1_VNCR_MAPPED		5
+#define KVM_HOST_DATA_FLAG_HAS_BRBE			6
 	unsigned long flags;
 
 	struct kvm_cpu_context host_ctxt;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 2dc5e6e742bb..d968aca0461a 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -103,6 +103,7 @@ alternative_cb_end
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);
 void kvm_compute_layout(void);
+u32 kvm_hyp_va_bits(void);
 void kvm_apply_hyp_relocations(void);
 
 #define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset)
@@ -185,7 +186,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
-int __init kvm_mmu_init(u32 *hyp_va_bits);
+int __init kvm_mmu_init(u32 hyp_va_bits);
 
 static inline void *__kvm_vector_slot2addr(void *base,
 					   enum arm64_hyp_spectre_vector slot)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a3729196b91c..0f40d3da0550 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -40,6 +40,7 @@
 #include <asm/kvm_pkvm.h>
 #include <asm/kvm_ptrauth.h>
 #include <asm/sections.h>
+#include <asm/stacktrace/nvhe.h>
 
 #include <kvm/arm_hypercalls.h>
 #include <kvm/arm_pmu.h>
@@ -2623,7 +2624,7 @@ static void pkvm_hyp_init_ptrauth(void)
 /* Inits Hyp-mode on all online CPUs */
 static int __init init_hyp_mode(void)
 {
-	u32 hyp_va_bits;
+	u32 hyp_va_bits = kvm_hyp_va_bits();
 	int cpu;
 	int err = -ENOMEM;
 
@@ -2637,7 +2638,7 @@ static int __init init_hyp_mode(void)
 	/*
 	 * Allocate Hyp PGD and setup Hyp identity mapping
 	 */
-	err = kvm_mmu_init(&hyp_va_bits);
+	err = kvm_mmu_init(hyp_va_bits);
 	if (err)
 		goto out_err;
 
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index bcc553307171..22d497554c94 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -1174,6 +1174,7 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_DBGWCRn_EL1(12),	CGT_MDCR_TDE_TDA),
 	SR_TRAP(SYS_DBGWCRn_EL1(13),	CGT_MDCR_TDE_TDA),
 	SR_TRAP(SYS_DBGWCRn_EL1(14),	CGT_MDCR_TDE_TDA),
+	SR_TRAP(SYS_DBGWCRn_EL1(15),	CGT_MDCR_TDE_TDA),
 	SR_TRAP(SYS_DBGCLAIMSET_EL1,	CGT_MDCR_TDE_TDA),
 	SR_TRAP(SYS_DBGCLAIMCLR_EL1,	CGT_MDCR_TDE_TDA),
 	SR_TRAP(SYS_DBGAUTHSTATUS_EL1,	CGT_MDCR_TDE_TDA),
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index afecbdd3c1e9..2597e8bda867 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -59,10 +59,8 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
 	 * it will cause an exception.
 	 */
-	if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) {
+	if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd())
 		write_sysreg(1 << 30, fpexc32_el2);
-		isb();
-	}
 }
 
 static inline void __activate_cptr_traps_nvhe(struct kvm_vcpu *vcpu)
@@ -495,7 +493,7 @@ static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu)
 	/*
 	 * When the guest owns the FP regs, we know that guest+hyp traps for
 	 * any FPSIMD/SVE/SME features exposed to the guest have been disabled
-	 * by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd()
+	 * by either __activate_cptr_traps() or kvm_hyp_handle_fpsimd()
 	 * prior to __guest_entry(). As __guest_entry() guarantees a context
 	 * synchronization event, we don't need an ISB here to avoid taking
 	 * traps for anything that was exposed to the guest.
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index f731cc4c3f28..94161ea1cd60 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -792,7 +792,7 @@ static void do_ffa_version(struct arm_smccc_1_2_regs *res,
 			.a0 = FFA_VERSION,
 			.a1 = ffa_req_version,
 		}, res);
-		if (res->a0 == FFA_RET_NOT_SUPPORTED)
+		if ((s32)res->a0 == FFA_RET_NOT_SUPPORTED)
 			goto unlock;
 
 		hyp_ffa_version = ffa_req_version;
@@ -943,7 +943,7 @@ int hyp_ffa_init(void *pages)
 		.a0 = FFA_VERSION,
 		.a1 = FFA_VERSION_1_2,
 	}, &res);
-	if (res.a0 == FFA_RET_NOT_SUPPORTED)
+	if ((s32)res.a0 == FFA_RET_NOT_SUPPORTED)
 		return 0;
 
 	/*
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index f28c6cf4fe1b..b254d442e54e 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -205,7 +205,7 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 
 	/*
 	 * When running a normal EL1 guest, we only load a new vcpu
-	 * after a context switch, which imvolves a DSB, so all
+	 * after a context switch, which involves a DSB, so all
 	 * speculative EL1&0 walks will have already completed.
 	 * If running NV, the vcpu may transition between vEL1 and
 	 * vEL2 without a context switch, so make sure we complete
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index e613ec5adc7a..8c5d259810b2 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2294,11 +2294,9 @@ static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = {
 	.virt_to_phys		= kvm_host_pa,
 };
 
-int __init kvm_mmu_init(u32 *hyp_va_bits)
+int __init kvm_mmu_init(u32 hyp_va_bits)
 {
 	int err;
-	u32 idmap_bits;
-	u32 kernel_bits;
 
 	hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start);
 	hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE);
@@ -2312,25 +2310,7 @@ int __init kvm_mmu_init(u32 *hyp_va_bits)
 	 */
 	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);
 
-	/*
-	 * The ID map is always configured for 48 bits of translation, which
-	 * may be fewer than the number of VA bits used by the regular kernel
-	 * stage 1, when VA_BITS=52.
-	 *
-	 * At EL2, there is only one TTBR register, and we can't switch between
-	 * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom
-	 * line: we need to use the extended range with *both* our translation
-	 * tables.
-	 *
-	 * So use the maximum of the idmap VA bits and the regular kernel stage
-	 * 1 VA bits to assure that the hypervisor can both ID map its code page
-	 * and map any kernel memory.
-	 */
-	idmap_bits = IDMAP_VA_BITS;
-	kernel_bits = vabits_actual;
-	*hyp_va_bits = max(idmap_bits, kernel_bits);
-
-	kvm_debug("Using %u-bit virtual addresses at EL2\n", *hyp_va_bits);
+	kvm_debug("Using %u-bit virtual addresses at EL2\n", hyp_va_bits);
 	kvm_debug("IDMAP page: %lx\n", hyp_idmap_start);
 	kvm_debug("HYP VA range: %lx:%lx\n",
 		  kern_hyp_va(PAGE_OFFSET),
@@ -2355,7 +2335,7 @@ int __init kvm_mmu_init(u32 *hyp_va_bits)
 		goto out;
 	}
 
-	err = kvm_pgtable_hyp_init(hyp_pgtable, *hyp_va_bits, &kvm_hyp_mm_ops);
+	err = kvm_pgtable_hyp_init(hyp_pgtable, hyp_va_bits, &kvm_hyp_mm_ops);
 	if (err)
 		goto out_free_pgtable;
 
@@ -2364,7 +2344,7 @@ int __init kvm_mmu_init(u32 *hyp_va_bits)
 		goto out_destroy_pgtable;
 
 	io_map_base = hyp_idmap_start;
-	__hyp_va_bits = *hyp_va_bits;
+	__hyp_va_bits = hyp_va_bits;
 	return 0;
 
 out_destroy_pgtable:
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index ed710228484f..eeea5e692370 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1101,6 +1101,9 @@ void kvm_nested_s2_wp(struct kvm *kvm)
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
+	if (!kvm->arch.nested_mmus_size)
+		return;
+
 	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
 		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
 
@@ -1117,6 +1120,9 @@ void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
+	if (!kvm->arch.nested_mmus_size)
+		return;
+
 	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
 		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
 
@@ -1133,6 +1139,9 @@ void kvm_nested_s2_flush(struct kvm *kvm)
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
+	if (!kvm->arch.nested_mmus_size)
+		return;
+
 	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
 		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
 
@@ -1145,6 +1154,9 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
 	int i;
 
+	if (!kvm->arch.nested_mmus_size)
+		return;
+
 	for (i = 0; i < kvm->arch.nested_mmus_size; i++) {
 		struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
 
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index 91b22a014610..2346f9435a71 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -47,8 +47,30 @@ static void init_hyp_physvirt_offset(void)
 }
 
 /*
+ * Calculate the actual VA size used by the hypervisor
+ */
+__init u32 kvm_hyp_va_bits(void)
+{
+	/*
+	 * The ID map is always configured for 48 bits of translation, which may
+	 * be different from the number of VA bits used by the regular kernel
+	 * stage 1.
+	 *
+	 * At EL2, there is only one TTBR register, and we can't switch between
+	 * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom
+	 * line: we need to use the extended range with *both* our translation
+	 * tables.
+	 *
+	 * So use the maximum of the idmap VA bits and the regular kernel stage
+	 * 1 VA bits as the hypervisor VA size to assure that the hypervisor can
+	 * both ID map its code page and map any kernel memory.
+	 */
+	return max(IDMAP_VA_BITS, vabits_actual);
+}
+
+/*
  * We want to generate a hyp VA with the following format (with V ==
- * vabits_actual):
+ * hypervisor VA bits):
  *
  *  63 ... V |     V-1    | V-2 .. tag_lsb | tag_lsb - 1 .. 0
  *  ---------------------------------------------------------
@@ -61,10 +83,11 @@ __init void kvm_compute_layout(void)
 {
 	phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start);
 	u64 hyp_va_msb;
+	u32 hyp_va_bits = kvm_hyp_va_bits();
 
 	/* Where is my RAM region? */
-	hyp_va_msb  = idmap_addr & BIT(vabits_actual - 1);
-	hyp_va_msb ^= BIT(vabits_actual - 1);
+	hyp_va_msb  = idmap_addr & BIT(hyp_va_bits - 1);
+	hyp_va_msb ^= BIT(hyp_va_bits - 1);
 
 	tag_lsb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^
 			(u64)(high_memory - 1));
@@ -72,9 +95,9 @@ __init void kvm_compute_layout(void)
 	va_mask = GENMASK_ULL(tag_lsb - 1, 0);
 	tag_val = hyp_va_msb;
 
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && tag_lsb != (vabits_actual - 1)) {
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && tag_lsb != (hyp_va_bits - 1)) {
 		/* We have some free bits to insert a random tag. */
-		tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb);
+		tag_val |= get_random_long() & GENMASK_ULL(hyp_va_bits - 2, tag_lsb);
 	}
 	tag_val >>= tag_lsb;
 
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index c9e35ec67117..5c69fa615823 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -57,7 +57,7 @@ static int lr_map_idx_to_shadow_idx(struct shadow_if *shadow_if, int idx)
  * as the L1 guest is in charge of provisioning the interrupts via its own
  * view of the ICH_LR*_EL2 registers, which conveniently live in the VNCR
  * page.  This means that the flow described above does work (there is no
- * state to rebuild in the L0 hypervisor), and that most things happed on L2
+ * state to rebuild in the L0 hypervisor), and that most things happen on L2
  * load/put:
  *
  * - on L2 load: move the in-memory L1 vGIC configuration into a shadow,