Merge tag 'kvmarm-for-v4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/ARM updates for 4.18

- Lazy context-switching of FPSIMD registers on arm64
- Allow virtual redistributors to be part of two or more MMIO ranges

6 files changed, 82 insertions, 49 deletions

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 09b0f2a80c8f..0a6b7133195e 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -11,9 +11,7 @@
 
 #include <asm/cpucaps.h>
 #include <asm/cputype.h>
-#include <asm/fpsimd.h>
 #include <asm/hwcap.h>
-#include <asm/sigcontext.h>
 #include <asm/sysreg.h>
 
 /*
@@ -510,33 +508,6 @@ static inline bool system_supports_sve(void)
 		cpus_have_const_cap(ARM64_SVE);
 }
 
-/*
- * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE
- * vector length.
- *
- * Use only if SVE is present.
- * This function clobbers the SVE vector length.
- */
-static inline u64 read_zcr_features(void)
-{
-	u64 zcr;
-	unsigned int vq_max;
-
-	/*
-	 * Set the maximum possible VL, and write zeroes to all other
-	 * bits to see if they stick.
-	 */
-	sve_kernel_enable(NULL);
-	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);
-
-	zcr = read_sysreg_s(SYS_ZCR_EL1);
-	zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
-	vq_max = sve_vq_from_vl(sve_get_vl());
-	zcr |= vq_max - 1; /* set LEN field to maximum effective value */
-
-	return zcr;
-}
-
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index aa7162ae93e3..fa92747a49c8 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -18,6 +18,8 @@
 
 #include <asm/ptrace.h>
 #include <asm/errno.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
 
 #ifndef __ASSEMBLY__
 
@@ -41,6 +43,8 @@ struct task_struct;
 extern void fpsimd_save_state(struct user_fpsimd_state *state);
 extern void fpsimd_load_state(struct user_fpsimd_state *state);
 
+extern void fpsimd_save(void);
+
 extern void fpsimd_thread_switch(struct task_struct *next);
 extern void fpsimd_flush_thread(void);
 
@@ -49,12 +53,27 @@ 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_bind_task_to_cpu(void);
+extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state);
+
 extern void fpsimd_flush_task_state(struct task_struct *target);
+extern void fpsimd_flush_cpu_state(void);
 extern void sve_flush_cpu_state(void);
 
 /* Maximum VL that SVE VL-agnostic software can transparently support */
 #define SVE_VL_ARCH_MAX 0x100
 
+/* Offset of FFR in the SVE register dump */
+static inline size_t sve_ffr_offset(int vl)
+{
+	return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET;
+}
+
+static inline void *sve_pffr(struct thread_struct *thread)
+{
+	return (char *)thread->sve_state + sve_ffr_offset(thread->sve_vl);
+}
+
 extern void sve_save_state(void *state, u32 *pfpsr);
 extern void sve_load_state(void const *state, u32 const *pfpsr,
 			   unsigned long vq_minus_1);
@@ -63,6 +82,8 @@ extern unsigned int sve_get_vl(void);
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 
+extern u64 read_zcr_features(void);
+
 extern int __ro_after_init sve_max_vl;
 
 #ifdef CONFIG_ARM64_SVE
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index f6648a3e4152..821a7032c0f7 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -30,19 +30,19 @@
 /* The hyp-stub will return this for any kvm_call_hyp() call */
 #define ARM_EXCEPTION_HYP_GONE	  HVC_STUB_ERR
 
-#define KVM_ARM64_DEBUG_DIRTY_SHIFT	0
-#define KVM_ARM64_DEBUG_DIRTY		(1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
+#ifndef __ASSEMBLY__
+
+#include <linux/mm.h>
 
 /* Translate a kernel address of @sym into its equivalent linear mapping */
 #define kvm_ksym_ref(sym)						\
 	({								\
 		void *val = &sym;					\
 		if (!is_kernel_in_hyp_mode())				\
-			val = phys_to_virt((u64)&sym - kimage_voffset);	\
+			val = lm_alias(&sym);				\
 		val;							\
 	 })
 
-#ifndef __ASSEMBLY__
 struct kvm;
 struct kvm_vcpu;
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 469de8acd06f..a4ca202ff3f2 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,6 +30,7 @@
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
+#include <asm/thread_info.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
@@ -216,8 +217,8 @@ struct kvm_vcpu_arch {
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
-	/* Guest debug state */
-	u64 debug_flags;
+	/* Miscellaneous vcpu state flags */
+	u64 flags;
 
 	/*
 	 * We maintain more than a single set of debug registers to support
@@ -238,6 +239,10 @@ struct kvm_vcpu_arch {
 
 	/* Pointer to host CPU context */
 	kvm_cpu_context_t *host_cpu_context;
+
+	struct thread_info *host_thread_info;	/* hyp VA */
+	struct user_fpsimd_state *host_fpsimd_state;	/* hyp VA */
+
 	struct {
 		/* {Break,watch}point registers */
 		struct kvm_guest_debug_arch regs;
@@ -293,6 +298,12 @@ struct kvm_vcpu_arch {
 	bool sysregs_loaded_on_cpu;
 };
 
+/* vcpu_arch flags field values: */
+#define KVM_ARM64_DEBUG_DIRTY		(1 << 0)
+#define KVM_ARM64_FP_ENABLED		(1 << 1) /* guest FP regs loaded */
+#define KVM_ARM64_FP_HOST		(1 << 2) /* host FP regs loaded */
+#define KVM_ARM64_HOST_SVE_IN_USE	(1 << 3) /* backup for host TIF_SVE */
+
 #define vcpu_gp_regs(v)		(&(v)->arch.ctxt.gp_regs)
 
 /*
@@ -394,6 +405,19 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 	kvm_call_hyp(__kvm_set_tpidr_el2, tpidr_el2);
 }
 
+static inline bool kvm_arch_check_sve_has_vhe(void)
+{
+	/*
+	 * The Arm architecture specifies that implementation of SVE
+	 * requires VHE also to be implemented.  The KVM code for arm64
+	 * relies on this when SVE is present:
+	 */
+	if (system_supports_sve())
+		return has_vhe();
+	else
+		return true;
+}
+
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
@@ -420,15 +444,18 @@ static inline void __cpu_init_stage2(void)
 		  "PARange is %d bits, unsupported configuration!", parange);
 }
 
-/*
- * All host FP/SIMD state is restored on guest exit, so nothing needs
- * doing here except in the SVE case:
-*/
-static inline void kvm_fpsimd_flush_cpu_state(void)
+/* Guest/host FPSIMD coordination helpers */
+int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu);
+
+#ifdef CONFIG_KVM /* Avoid conflicts with core headers if CONFIG_KVM=n */
+static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 {
-	if (system_supports_sve())
-		sve_flush_cpu_state();
+	return kvm_arch_vcpu_run_map_fp(vcpu);
 }
+#endif
 
 static inline void kvm_arm_vhe_guest_enter(void)
 {
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 767598932549..c99e657fdd57 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -156,7 +156,9 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
 /* Sync TPIDR_EL0 back to thread_struct for current */
 void tls_preserve_current_state(void);
 
-#define INIT_THREAD  {	}
+#define INIT_THREAD {				\
+	.fpsimd_cpu = NR_CPUS,			\
+}
 
 static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
 {
@@ -244,6 +246,17 @@ void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused);
 void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused);
 void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused);
 
+/*
+ * Not at the top of the file due to a direct #include cycle between
+ * <asm/fpsimd.h> and <asm/processor.h>.  Deferring this #include
+ * ensures that contents of processor.h are visible to fpsimd.h even if
+ * processor.h is included first.
+ *
+ * These prctl helpers are the only things in this file that require
+ * fpsimd.h.  The core code expects them to be in this header.
+ */
+#include <asm/fpsimd.h>
+
 /* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */
 #define SVE_SET_VL(arg)	sve_set_current_vl(arg)
 #define SVE_GET_VL()	sve_get_current_vl()
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 740aa03c5f0d..af271f9a6c9f 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -45,12 +45,6 @@ struct thread_info {
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
 };
 
-#define INIT_THREAD_INFO(tsk)						\
-{									\
-	.preempt_count	= INIT_PREEMPT_COUNT,				\
-	.addr_limit	= KERNEL_DS,					\
-}
-
 #define thread_saved_pc(tsk)	\
 	((unsigned long)(tsk->thread.cpu_context.pc))
 #define thread_saved_sp(tsk)	\
@@ -117,5 +111,12 @@ void arch_release_task_struct(struct task_struct *tsk);
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
 				 _TIF_NOHZ)
 
+#define INIT_THREAD_INFO(tsk)						\
+{									\
+	.flags		= _TIF_FOREIGN_FPSTATE,				\
+	.preempt_count	= INIT_PREEMPT_COUNT,				\
+	.addr_limit	= KERNEL_DS,					\
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_THREAD_INFO_H */