Merge branch 'for-next/sve-state' into for-next/core

* for-next/sve-state:
  arm64/fp: Use a struct to pass data to fpsimd_bind_state_to_cpu()
  arm64/sve: Leave SVE enabled on syscall if we don't context switch
  arm64/fpsimd: SME no longer requires SVE register state
  arm64/fpsimd: Load FP state based on recorded data type
  arm64/fpsimd: Stop using TIF_SVE to manage register saving in KVM
  arm64/fpsimd: Have KVM explicitly say which FP registers to save
  arm64/fpsimd: Track the saved FPSIMD state type separately to TIF_SVE
  KVM: arm64: Discard any SVE state when entering KVM guests

arch/arm64/include/asm/fpsimd.h

@@ -56,11 +56,20 @@ extern void fpsimd_signal_preserve_current_state(void);
 extern void fpsimd_preserve_current_state(void);
 extern void fpsimd_restore_current_state(void);
 extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
+extern void fpsimd_kvm_prepare(void);
+
+struct cpu_fp_state {
+	struct user_fpsimd_state *st;
+	void *sve_state;
+	void *za_state;
+	u64 *svcr;
+	unsigned int sve_vl;
+	unsigned int sme_vl;
+	enum fp_type *fp_type;
+	enum fp_type to_save;
+};
 
-extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
-				     void *sve_state, unsigned int sve_vl,
-				     void *za_state, unsigned int sme_vl,
-				     u64 *svcr);
+extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state);
 
 extern void fpsimd_flush_task_state(struct task_struct *target);
 extern void fpsimd_save_and_flush_cpu_state(void);

arch/arm64/include/asm/kvm_host.h

@@ -306,8 +306,18 @@ struct vcpu_reset_state {
 struct kvm_vcpu_arch {
 	struct kvm_cpu_context ctxt;
 
-	/* Guest floating point state */
+	/*
+	 * Guest floating point state
+	 *
+	 * The architecture has two main floating point extensions,
+	 * the original FPSIMD and SVE.  These have overlapping
+	 * register views, with the FPSIMD V registers occupying the
+	 * low 128 bits of the SVE Z registers.  When the core
+	 * floating point code saves the register state of a task it
+	 * records which view it saved in fp_type.
+	 */
 	void *sve_state;
+	enum fp_type fp_type;
 	unsigned int sve_max_vl;
 	u64 svcr;
 

arch/arm64/include/asm/processor.h

@@ -122,6 +122,12 @@ enum vec_type {
 	ARM64_VEC_MAX,
 };
 
+enum fp_type {
+	FP_STATE_CURRENT,	/* Save based on current task state. */
+	FP_STATE_FPSIMD,
+	FP_STATE_SVE,
+};
+
 struct cpu_context {
 	unsigned long x19;
 	unsigned long x20;
@@ -152,6 +158,7 @@ struct thread_struct {
 		struct user_fpsimd_state fpsimd_state;
 	} uw;
 
+	enum fp_type		fp_type;	/* registers FPSIMD or SVE? */
 	unsigned int		fpsimd_cpu;
 	void			*sve_state;	/* SVE registers, if any */
 	void			*za_state;	/* ZA register, if any */

arch/arm64/kernel/process.c

@@ -331,6 +331,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 		clear_tsk_thread_flag(dst, TIF_SME);
 	}
 
+	dst->thread.fp_type = FP_STATE_FPSIMD;
+
 	/* clear any pending asynchronous tag fault raised by the parent */
 	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
 

arch/arm64/kernel/ptrace.c

@@ -907,8 +907,7 @@ static int sve_set_common(struct task_struct *target,
 		ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
 				SVE_PT_FPSIMD_OFFSET);
 		clear_tsk_thread_flag(target, TIF_SVE);
-		if (type == ARM64_VEC_SME)
-			fpsimd_force_sync_to_sve(target);
+		target->thread.fp_type = FP_STATE_FPSIMD;
 		goto out;
 	}
 
@@ -931,6 +930,7 @@ static int sve_set_common(struct task_struct *target,
 	if (!target->thread.sve_state) {
 		ret = -ENOMEM;
 		clear_tsk_thread_flag(target, TIF_SVE);
+		target->thread.fp_type = FP_STATE_FPSIMD;
 		goto out;
 	}
 
@@ -942,6 +942,7 @@ static int sve_set_common(struct task_struct *target,
 	 */
 	fpsimd_sync_to_sve(target);
 	set_tsk_thread_flag(target, TIF_SVE);
+	target->thread.fp_type = FP_STATE_SVE;
 
 	BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
 	start = SVE_PT_SVE_OFFSET;

arch/arm64/kernel/signal.c

@@ -207,6 +207,7 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
 
 	clear_thread_flag(TIF_SVE);
+	current->thread.fp_type = FP_STATE_FPSIMD;
 
 	/* load the hardware registers from the fpsimd_state structure */
 	if (!err)
@@ -292,6 +293,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 	if (sve.head.size <= sizeof(*user->sve)) {
 		clear_thread_flag(TIF_SVE);
 		current->thread.svcr &= ~SVCR_SM_MASK;
+		current->thread.fp_type = FP_STATE_FPSIMD;
 		goto fpsimd_only;
 	}
 
@@ -327,6 +329,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
 		current->thread.svcr |= SVCR_SM_MASK;
 	else
 		set_thread_flag(TIF_SVE);
+	current->thread.fp_type = FP_STATE_SVE;
 
 fpsimd_only:
 	/* copy the FP and status/control registers */
@@ -932,9 +935,11 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		 * FPSIMD register state - flush the saved FPSIMD
 		 * register state in case it gets loaded.
 		 */
-		if (current->thread.svcr & SVCR_SM_MASK)
+		if (current->thread.svcr & SVCR_SM_MASK) {
 			memset(&current->thread.uw.fpsimd_state, 0,
 			       sizeof(current->thread.uw.fpsimd_state));
+			current->thread.fp_type = FP_STATE_FPSIMD;
+		}
 
 		current->thread.svcr &= ~(SVCR_ZA_MASK |
 					  SVCR_SM_MASK);

arch/arm64/kernel/syscall.c

@@ -183,21 +183,12 @@ static inline void fp_user_discard(void)
 	if (!system_supports_sve())
 		return;
 
-	/*
-	 * If SME is not active then disable SVE, the registers will
-	 * be cleared when userspace next attempts to access them and
-	 * we do not need to track the SVE register state until then.
-	 */
-	clear_thread_flag(TIF_SVE);
+	if (test_thread_flag(TIF_SVE)) {
+		unsigned int sve_vq_minus_one;
 
-	/*
-	 * task_fpsimd_load() won't be called to update CPACR_EL1 in
-	 * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
-	 * happens if a context switch or kernel_neon_begin() or context
-	 * modification (sigreturn, ptrace) intervenes.
-	 * So, ensure that CPACR_EL1 is already correct for the fast-path case.
-	 */
-	sve_user_disable();
+		sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1;
+		sve_flush_live(true, sve_vq_minus_one);
+	}
 }
 
 void do_el0_svc(struct pt_regs *regs)

arch/arm64/kvm/fpsimd.c

@@ -75,11 +75,12 @@ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 {
 	BUG_ON(!current->mm);
-	BUG_ON(test_thread_flag(TIF_SVE));
 
 	if (!system_supports_fpsimd())
 		return;
 
+	fpsimd_kvm_prepare();
+
 	vcpu->arch.fp_state = FP_STATE_HOST_OWNED;
 
 	vcpu_clear_flag(vcpu, HOST_SVE_ENABLED);
@@ -129,20 +130,31 @@ void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu)
  */
 void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 {
+	struct cpu_fp_state fp_state;
+
 	WARN_ON_ONCE(!irqs_disabled());
 
 	if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) {
+
 		/*
 		 * Currently we do not support SME guests so SVCR is
 		 * always 0 and we just need a variable to point to.
 		 */
-		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
-					 vcpu->arch.sve_state,
-					 vcpu->arch.sve_max_vl,
-					 NULL, 0, &vcpu->arch.svcr);
+		fp_state.st = &vcpu->arch.ctxt.fp_regs;
+		fp_state.sve_state = vcpu->arch.sve_state;
+		fp_state.sve_vl = vcpu->arch.sve_max_vl;
+		fp_state.za_state = NULL;
+		fp_state.svcr = &vcpu->arch.svcr;
+		fp_state.fp_type = &vcpu->arch.fp_type;
+
+		if (vcpu_has_sve(vcpu))
+			fp_state.to_save = FP_STATE_SVE;
+		else
+			fp_state.to_save = FP_STATE_FPSIMD;
+
+		fpsimd_bind_state_to_cpu(&fp_state);
 
 		clear_thread_flag(TIF_FOREIGN_FPSTATE);
-		update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
 	}
 }
 
@@ -199,7 +211,5 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 			sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
 	}
 
-	update_thread_flag(TIF_SVE, 0);
-
 	local_irq_restore(flags);
 }