Merge tag 'kvmarm-fixes-6.14-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 fixes for 6.14, take #2

- Large set of fixes for vector handling, specially in the interactions
  between host and guest state. This fixes a number of bugs affecting
  actual deployments, and greatly simplifies the FP/SIMD/SVE handling.
  Thanks to Mark Rutland for dealing with this thankless task.

- Fix an ugly race between vcpu and vgic creation/init, resulting in
  unexpected behaviours.

- Fix use of kernel VAs at EL2 when emulating timers with nVHE.

- Small set of pKVM improvements and cleanups.

Author: bonzini

Diff for: arch/arm64/include/asm/kvm_emulate.h

@@ -605,48 +605,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 					 __cpacr_to_cptr_set(clr, set));\
 	} while (0)
 
-static __always_inline void kvm_write_cptr_el2(u64 val)
-{
-	if (has_vhe() || has_hvhe())
-		write_sysreg(val, cpacr_el1);
-	else
-		write_sysreg(val, cptr_el2);
-}
-
-/* Resets the value of cptr_el2 when returning to the host. */
-static __always_inline void __kvm_reset_cptr_el2(struct kvm *kvm)
-{
-	u64 val;
-
-	if (has_vhe()) {
-		val = (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN);
-		if (cpus_have_final_cap(ARM64_SME))
-			val |= CPACR_EL1_SMEN_EL1EN;
-	} else if (has_hvhe()) {
-		val = CPACR_EL1_FPEN;
-
-		if (!kvm_has_sve(kvm) || !guest_owns_fp_regs())
-			val |= CPACR_EL1_ZEN;
-		if (cpus_have_final_cap(ARM64_SME))
-			val |= CPACR_EL1_SMEN;
-	} else {
-		val = CPTR_NVHE_EL2_RES1;
-
-		if (kvm_has_sve(kvm) && guest_owns_fp_regs())
-			val |= CPTR_EL2_TZ;
-		if (!cpus_have_final_cap(ARM64_SME))
-			val |= CPTR_EL2_TSM;
-	}
-
-	kvm_write_cptr_el2(val);
-}
-
-#ifdef __KVM_NVHE_HYPERVISOR__
-#define kvm_reset_cptr_el2(v)	__kvm_reset_cptr_el2(kern_hyp_va((v)->kvm))
-#else
-#define kvm_reset_cptr_el2(v)	__kvm_reset_cptr_el2((v)->kvm)
-#endif
-
 /*
  * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE
  * format if E2H isn't set.

Diff for: arch/arm64/include/asm/kvm_host.h

@@ -100,7 +100,7 @@ static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc,
 static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc,
 				     void *(*to_va)(phys_addr_t phys))
 {
-	phys_addr_t *p = to_va(mc->head);
+	phys_addr_t *p = to_va(mc->head & PAGE_MASK);
 
 	if (!mc->nr_pages)
 		return NULL;
@@ -615,32 +615,20 @@ 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_HOST_SVE_ENABLED		2
-#define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED		3
 #define KVM_HOST_DATA_FLAG_TRBE_ENABLED			4
 #define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED	5
 	unsigned long flags;
 
 	struct kvm_cpu_context host_ctxt;
 
 	/*
-	 * All pointers in this union are hyp VA.
+	 * Hyp VA.
 	 * sve_state is only used in pKVM and if system_supports_sve().
 	 */
-	union {
-		struct user_fpsimd_state *fpsimd_state;
-		struct cpu_sve_state *sve_state;
-	};
-
-	union {
-		/* HYP VA pointer to the host storage for FPMR */
-		u64	*fpmr_ptr;
-		/*
-		 * Used by pKVM only, as it needs to provide storage
-		 * for the host
-		 */
-		u64	fpmr;
-	};
+	struct cpu_sve_state *sve_state;
+
+	/* Used by pKVM only. */
+	u64	fpmr;
 
 	/* Ownership of the FP regs */
 	enum {

Diff for: arch/arm64/kernel/fpsimd.c

@@ -1694,31 +1694,6 @@ void fpsimd_signal_preserve_current_state(void)
 		sve_to_fpsimd(current);
 }
 
-/*
- * Called by KVM when entering the guest.
- */
-void fpsimd_kvm_prepare(void)
-{
-	if (!system_supports_sve())
-		return;
-
-	/*
-	 * KVM does not save host SVE state since we can only enter
-	 * the guest from a syscall so the ABI means that only the
-	 * non-saved SVE state needs to be saved.  If we have left
-	 * SVE enabled for performance reasons then update the task
-	 * state to be FPSIMD only.
-	 */
-	get_cpu_fpsimd_context();
-
-	if (test_and_clear_thread_flag(TIF_SVE)) {
-		sve_to_fpsimd(current);
-		current->thread.fp_type = FP_STATE_FPSIMD;
-	}
-
-	put_cpu_fpsimd_context();
-}
-
 /*
  * Associate current's FPSIMD context with this cpu
  * The caller must have ownership of the cpu FPSIMD context before calling

Diff for: arch/arm64/kvm/arch_timer.c

@@ -447,21 +447,19 @@ static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level)
 static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 				 struct arch_timer_context *timer_ctx)
 {
-	int ret;
-
 	kvm_timer_update_status(timer_ctx, new_level);
 
 	timer_ctx->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx),
 				   timer_ctx->irq.level);
 
-	if (!userspace_irqchip(vcpu->kvm)) {
-		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu,
-					  timer_irq(timer_ctx),
-					  timer_ctx->irq.level,
-					  timer_ctx);
-		WARN_ON(ret);
-	}
+	if (userspace_irqchip(vcpu->kvm))
+		return;
+
+	kvm_vgic_inject_irq(vcpu->kvm, vcpu,
+			    timer_irq(timer_ctx),
+			    timer_ctx->irq.level,
+			    timer_ctx);
 }
 
 /* Only called for a fully emulated timer */

Diff for: arch/arm64/kvm/arm.c

@@ -2481,14 +2481,6 @@ static void finalize_init_hyp_mode(void)
 			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state =
 				kern_hyp_va(sve_state);
 		}
-	} else {
-		for_each_possible_cpu(cpu) {
-			struct user_fpsimd_state *fpsimd_state;
-
-			fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs;
-			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state =
-				kern_hyp_va(fpsimd_state);
-		}
 	}
 }
 

Diff for: arch/arm64/kvm/fpsimd.c

@@ -54,50 +54,18 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	if (!system_supports_fpsimd())
 		return;
 
-	fpsimd_kvm_prepare();
-
 	/*
-	 * We will check TIF_FOREIGN_FPSTATE just before entering the
-	 * guest in kvm_arch_vcpu_ctxflush_fp() and override this to
-	 * FP_STATE_FREE if the flag set.
+	 * Ensure that any host FPSIMD/SVE/SME state is saved and unbound such
+	 * that the host kernel is responsible for restoring this state upon
+	 * return to userspace, and the hyp code doesn't need to save anything.
+	 *
+	 * When the host may use SME, fpsimd_save_and_flush_cpu_state() ensures
+	 * that PSTATE.{SM,ZA} == {0,0}.
 	 */
-	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
-	*host_data_ptr(fpsimd_state) = kern_hyp_va(&current->thread.uw.fpsimd_state);
-	*host_data_ptr(fpmr_ptr) = kern_hyp_va(&current->thread.uw.fpmr);
-
-	host_data_clear_flag(HOST_SVE_ENABLED);
-	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
-		host_data_set_flag(HOST_SVE_ENABLED);
-
-	if (system_supports_sme()) {
-		host_data_clear_flag(HOST_SME_ENABLED);
-		if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
-			host_data_set_flag(HOST_SME_ENABLED);
-
-		/*
-		 * If PSTATE.SM is enabled then save any pending FP
-		 * state and disable PSTATE.SM. If we leave PSTATE.SM
-		 * enabled and the guest does not enable SME via
-		 * CPACR_EL1.SMEN then operations that should be valid
-		 * may generate SME traps from EL1 to EL1 which we
-		 * can't intercept and which would confuse the guest.
-		 *
-		 * Do the same for PSTATE.ZA in the case where there
-		 * is state in the registers which has not already
-		 * been saved, this is very unlikely to happen.
-		 */
-		if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) {
-			*host_data_ptr(fp_owner) = FP_STATE_FREE;
-			fpsimd_save_and_flush_cpu_state();
-		}
-	}
+	fpsimd_save_and_flush_cpu_state();
+	*host_data_ptr(fp_owner) = FP_STATE_FREE;
 
-	/*
-	 * If normal guests gain SME support, maintain this behavior for pKVM
-	 * guests, which don't support SME.
-	 */
-	WARN_ON(is_protected_kvm_enabled() && system_supports_sme() &&
-		read_sysreg_s(SYS_SVCR));
+	WARN_ON_ONCE(system_supports_sme() && read_sysreg_s(SYS_SVCR));
 }
 
 /*
@@ -162,52 +130,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 
 	local_irq_save(flags);
 
-	/*
-	 * If we have VHE then the Hyp code will reset CPACR_EL1 to
-	 * the default value and we need to reenable SME.
-	 */
-	if (has_vhe() && system_supports_sme()) {
-		/* Also restore EL0 state seen on entry */
-		if (host_data_test_flag(HOST_SME_ENABLED))
-			sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN);
-		else
-			sysreg_clear_set(CPACR_EL1,
-					 CPACR_EL1_SMEN_EL0EN,
-					 CPACR_EL1_SMEN_EL1EN);
-		isb();
-	}
-
 	if (guest_owns_fp_regs()) {
-		if (vcpu_has_sve(vcpu)) {
-			u64 zcr = read_sysreg_el1(SYS_ZCR);
-
-			/*
-			 * If the vCPU is in the hyp context then ZCR_EL1 is
-			 * loaded with its vEL2 counterpart.
-			 */
-			__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr;
-
-			/*
-			 * Restore the VL that was saved when bound to the CPU,
-			 * which is the maximum VL for the guest. Because the
-			 * layout of the data when saving the sve state depends
-			 * on the VL, we need to use a consistent (i.e., the
-			 * maximum) VL.
-			 * Note that this means that at guest exit ZCR_EL1 is
-			 * not necessarily the same as on guest entry.
-			 *
-			 * ZCR_EL2 holds the guest hypervisor's VL when running
-			 * a nested guest, which could be smaller than the
-			 * max for the vCPU. Similar to above, we first need to
-			 * switch to a VL consistent with the layout of the
-			 * vCPU's SVE state. KVM support for NV implies VHE, so
-			 * using the ZCR_EL1 alias is safe.
-			 */
-			if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)))
-				sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1,
-						       SYS_ZCR_EL1);
-		}
-
 		/*
 		 * Flush (save and invalidate) the fpsimd/sve state so that if
 		 * the host tries to use fpsimd/sve, it's not using stale data
@@ -219,18 +142,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 		 * when needed.
 		 */
 		fpsimd_save_and_flush_cpu_state();
-	} else if (has_vhe() && system_supports_sve()) {
-		/*
-		 * The FPSIMD/SVE state in the CPU has not been touched, and we
-		 * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been
-		 * reset by kvm_reset_cptr_el2() in the Hyp code, disabling SVE
-		 * for EL0.  To avoid spurious traps, restore the trap state
-		 * seen by kvm_arch_vcpu_load_fp():
-		 */
-		if (host_data_test_flag(HOST_SVE_ENABLED))
-			sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN);
-		else
-			sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
 	}
 
 	local_irq_restore(flags);

Diff for: arch/arm64/kvm/hyp/entry.S

@@ -44,6 +44,11 @@ alternative_if ARM64_HAS_RAS_EXTN
 alternative_else_nop_endif
 	mrs	x1, isr_el1
 	cbz	x1,  1f
+
+	// Ensure that __guest_enter() always provides a context
+	// synchronization event so that callers don't need ISBs for anything
+	// that would usually be synchonized by the ERET.
+	isb
 	mov	x0, #ARM_EXCEPTION_IRQ
 	ret