summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--arch/arm64/include/asm/kvm_asm.h66
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h2
-rw-r--r--arch/arm64/include/asm/kvm_host.h23
-rw-r--r--arch/arm64/include/asm/kvm_hyp.h15
-rw-r--r--arch/arm64/include/asm/mmu.h7
-rw-r--r--arch/arm64/include/asm/virt.h13
-rw-r--r--arch/arm64/kernel/image-vars.h54
-rw-r--r--arch/arm64/kvm/Makefile2
-rw-r--r--arch/arm64/kvm/arm.c16
-rw-r--r--arch/arm64/kvm/hyp/Makefile24
-rw-r--r--arch/arm64/kvm/hyp/aarch32.c6
-rw-r--r--arch/arm64/kvm/hyp/entry.S1
-rw-r--r--arch/arm64/kvm/hyp/fpsimd.S1
-rw-r--r--arch/arm64/kvm/hyp/hyp-entry.S21
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/debug-sr.h (renamed from arch/arm64/kvm/hyp/debug-sr.c)78
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h509
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h (renamed from arch/arm64/kvm/hyp/sysreg-sr.c)162
-rw-r--r--arch/arm64/kvm/hyp/nvhe/Makefile42
-rw-r--r--arch/arm64/kvm/hyp/nvhe/debug-sr.c77
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-init.S (renamed from arch/arm64/kvm/hyp-init.S)0
-rw-r--r--arch/arm64/kvm/hyp/nvhe/switch.c272
-rw-r--r--arch/arm64/kvm/hyp/nvhe/sysreg-sr.c46
-rw-r--r--arch/arm64/kvm/hyp/nvhe/timer-sr.c (renamed from arch/arm64/kvm/hyp/timer-sr.c)6
-rw-r--r--arch/arm64/kvm/hyp/nvhe/tlb.c (renamed from arch/arm64/kvm/hyp/tlb.c)102
-rw-r--r--arch/arm64/kvm/hyp/smccc_wa.S32
-rw-r--r--arch/arm64/kvm/hyp/switch.c936
-rw-r--r--arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c4
-rw-r--r--arch/arm64/kvm/hyp/vgic-v3-sr.c130
-rw-r--r--arch/arm64/kvm/hyp/vhe/Makefile11
-rw-r--r--arch/arm64/kvm/hyp/vhe/debug-sr.c26
-rw-r--r--arch/arm64/kvm/hyp/vhe/switch.c219
-rw-r--r--arch/arm64/kvm/hyp/vhe/sysreg-sr.c114
-rw-r--r--arch/arm64/kvm/hyp/vhe/timer-sr.c12
-rw-r--r--arch/arm64/kvm/hyp/vhe/tlb.c161
-rw-r--r--scripts/kallsyms.c1
35 files changed, 1793 insertions, 1398 deletions
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 352aaebf4198..1a66815ea01b 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -42,22 +42,70 @@
#include <linux/mm.h>
-/* Translate a kernel address of @sym into its equivalent linear mapping */
-#define kvm_ksym_ref(sym) \
+/*
+ * Translate name of a symbol defined in nVHE hyp to the name seen
+ * by kernel proper. All nVHE symbols are prefixed by the build system
+ * to avoid clashes with the VHE variants.
+ */
+#define kvm_nvhe_sym(sym) __kvm_nvhe_##sym
+
+#define DECLARE_KVM_VHE_SYM(sym) extern char sym[]
+#define DECLARE_KVM_NVHE_SYM(sym) extern char kvm_nvhe_sym(sym)[]
+
+/*
+ * Define a pair of symbols sharing the same name but one defined in
+ * VHE and the other in nVHE hyp implementations.
+ */
+#define DECLARE_KVM_HYP_SYM(sym) \
+ DECLARE_KVM_VHE_SYM(sym); \
+ DECLARE_KVM_NVHE_SYM(sym)
+
+#define CHOOSE_VHE_SYM(sym) sym
+#define CHOOSE_NVHE_SYM(sym) kvm_nvhe_sym(sym)
+
+#ifndef __KVM_NVHE_HYPERVISOR__
+/*
+ * BIG FAT WARNINGS:
+ *
+ * - Don't be tempted to change the following is_kernel_in_hyp_mode()
+ * to has_vhe(). has_vhe() is implemented as a *final* capability,
+ * while this is used early at boot time, when the capabilities are
+ * not final yet....
+ *
+ * - Don't let the nVHE hypervisor have access to this, as it will
+ * pick the *wrong* symbol (yes, it runs at EL2...).
+ */
+#define CHOOSE_HYP_SYM(sym) (is_kernel_in_hyp_mode() ? CHOOSE_VHE_SYM(sym) \
+ : CHOOSE_NVHE_SYM(sym))
+#else
+/* The nVHE hypervisor shouldn't even try to access anything */
+extern void *__nvhe_undefined_symbol;
+#define CHOOSE_HYP_SYM(sym) __nvhe_undefined_symbol
+#endif
+
+/* Translate a kernel address @ptr into its equivalent linear mapping */
+#define kvm_ksym_ref(ptr) \
({ \
- void *val = &sym; \
+ void *val = (ptr); \
if (!is_kernel_in_hyp_mode()) \
- val = lm_alias(&sym); \
+ val = lm_alias((ptr)); \
val; \
})
+#define kvm_ksym_ref_nvhe(sym) kvm_ksym_ref(kvm_nvhe_sym(sym))
struct kvm;
struct kvm_vcpu;
-extern char __kvm_hyp_init[];
-extern char __kvm_hyp_init_end[];
+DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
+DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
+#define __kvm_hyp_init CHOOSE_NVHE_SYM(__kvm_hyp_init)
+#define __kvm_hyp_vector CHOOSE_HYP_SYM(__kvm_hyp_vector)
-extern char __kvm_hyp_vector[];
+#ifdef CONFIG_KVM_INDIRECT_VECTORS
+extern atomic_t arm64_el2_vector_last_slot;
+DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
+#define __bp_harden_hyp_vecs CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
+#endif
extern void __kvm_flush_vm_context(void);
extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
@@ -66,9 +114,7 @@ extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
extern void __kvm_timer_set_cntvoff(u64 cntvoff);
-extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu);
-
-extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu);
+extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
extern void __kvm_enable_ssbs(void);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 4d0f8ea600ba..269a76cd51ff 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -516,7 +516,7 @@ static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_i
* Skip an instruction which has been emulated at hyp while most guest sysregs
* are live.
*/
-static __always_inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
+static __always_inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
{
*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index c3e6fcc664b1..e0920df1d0c1 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -338,7 +338,7 @@ struct kvm_vcpu_arch {
struct vcpu_reset_state reset_state;
/* True when deferrable sysregs are loaded on the physical CPU,
- * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
+ * see kvm_vcpu_load_sysregs_vhe and kvm_vcpu_put_sysregs_vhe. */
bool sysregs_loaded_on_cpu;
/* Guest PV state */
@@ -448,6 +448,18 @@ void kvm_arm_resume_guest(struct kvm *kvm);
u64 __kvm_call_hyp(void *hypfn, ...);
+#define kvm_call_hyp_nvhe(f, ...) \
+ do { \
+ DECLARE_KVM_NVHE_SYM(f); \
+ __kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__); \
+ } while(0)
+
+#define kvm_call_hyp_nvhe_ret(f, ...) \
+ ({ \
+ DECLARE_KVM_NVHE_SYM(f); \
+ __kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__); \
+ })
+
/*
* The couple of isb() below are there to guarantee the same behaviour
* on VHE as on !VHE, where the eret to EL1 acts as a context
@@ -459,7 +471,7 @@ u64 __kvm_call_hyp(void *hypfn, ...);
f(__VA_ARGS__); \
isb(); \
} else { \
- __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \
+ kvm_call_hyp_nvhe(f, ##__VA_ARGS__); \
} \
} while(0)
@@ -471,8 +483,7 @@ u64 __kvm_call_hyp(void *hypfn, ...);
ret = f(__VA_ARGS__); \
isb(); \
} else { \
- ret = __kvm_call_hyp(kvm_ksym_ref(f), \
- ##__VA_ARGS__); \
+ ret = kvm_call_hyp_nvhe_ret(f, ##__VA_ARGS__); \
} \
\
ret; \
@@ -628,8 +639,8 @@ static inline int kvm_arm_have_ssbd(void)
}
}
-void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
-void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
+void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
+void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
int kvm_set_ipa_limit(void);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index ce3080834bfa..46689e7db46c 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -12,8 +12,6 @@
#include <asm/alternative.h>
#include <asm/sysreg.h>
-#define __hyp_text __section(.hyp.text) notrace __noscs
-
#define read_sysreg_elx(r,nvh,vh) \
({ \
u64 reg; \
@@ -63,17 +61,20 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if);
void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if);
int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu);
+#ifdef __KVM_NVHE_HYPERVISOR__
void __timer_enable_traps(struct kvm_vcpu *vcpu);
void __timer_disable_traps(struct kvm_vcpu *vcpu);
+#endif
+#ifdef __KVM_NVHE_HYPERVISOR__
void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt);
+#else
void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt);
void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt);
void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt);
void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt);
-void __sysreg32_save_state(struct kvm_vcpu *vcpu);
-void __sysreg32_restore_state(struct kvm_vcpu *vcpu);
+#endif
void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
void __debug_switch_to_host(struct kvm_vcpu *vcpu);
@@ -81,11 +82,17 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu);
void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
+#ifndef __KVM_NVHE_HYPERVISOR__
void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
void deactivate_traps_vhe_put(void);
+#endif
u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt);
+#ifdef __KVM_NVHE_HYPERVISOR__
void __noreturn __hyp_do_panic(unsigned long, ...);
+#endif
#endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 8444df000181..a7a5ecaa2e83 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -45,13 +45,6 @@ struct bp_hardening_data {
bp_hardening_cb_t fn;
};
-#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) || \
- defined(CONFIG_HARDEN_EL2_VECTORS))
-
-extern char __bp_harden_hyp_vecs[];
-extern atomic_t arm64_el2_vector_last_slot;
-#endif /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
-
#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 5051b388c654..09977acc007d 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -85,10 +85,17 @@ static inline bool is_kernel_in_hyp_mode(void)
static __always_inline bool has_vhe(void)
{
- if (cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN))
+ /*
+ * The following macros are defined for code specic to VHE/nVHE.
+ * If has_vhe() is inlined into those compilation units, it can
+ * be determined statically. Otherwise fall back to caps.
+ */
+ if (__is_defined(__KVM_VHE_HYPERVISOR__))
return true;
-
- return false;
+ else if (__is_defined(__KVM_NVHE_HYPERVISOR__))
+ return false;
+ else
+ return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN);
}
#endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index be0a63ffed23..9e897c500237 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -51,4 +51,58 @@ __efistub__ctype = _ctype;
#endif
+#ifdef CONFIG_KVM
+
+/*
+ * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_, to
+ * separate it from the kernel proper. The following symbols are legally
+ * accessed by it, therefore provide aliases to make them linkable.
+ * Do not include symbols which may not be safely accessed under hypervisor
+ * memory mappings.
+ */
+
+#define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym;
+
+/* Alternative callbacks for init-time patching of nVHE hyp code. */
+KVM_NVHE_ALIAS(arm64_enable_wa2_handling);
+KVM_NVHE_ALIAS(kvm_patch_vector_branch);
+KVM_NVHE_ALIAS(kvm_update_va_mask);
+
+/* Global kernel state accessed by nVHE hyp code. */
+KVM_NVHE_ALIAS(arm64_ssbd_callback_required);
+KVM_NVHE_ALIAS(kvm_host_data);
+KVM_NVHE_ALIAS(kvm_vgic_global_state);
+
+/* Kernel constant needed to compute idmap addresses. */
+KVM_NVHE_ALIAS(kimage_voffset);
+
+/* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
+KVM_NVHE_ALIAS(__hyp_panic_string);
+KVM_NVHE_ALIAS(panic);
+
+/* Vectors installed by hyp-init on reset HVC. */
+KVM_NVHE_ALIAS(__hyp_stub_vectors);
+
+/* IDMAP TCR_EL1.T0SZ as computed by the EL1 init code */
+KVM_NVHE_ALIAS(idmap_t0sz);
+
+/* Kernel symbol used by icache_is_vpipt(). */
+KVM_NVHE_ALIAS(__icache_flags);
+
+/* Kernel symbols needed for cpus_have_final/const_caps checks. */
+KVM_NVHE_ALIAS(arm64_const_caps_ready);
+KVM_NVHE_ALIAS(cpu_hwcap_keys);
+KVM_NVHE_ALIAS(cpu_hwcaps);
+
+/* Static keys which are set if a vGIC trap should be handled in hyp. */
+KVM_NVHE_ALIAS(vgic_v2_cpuif_trap);
+KVM_NVHE_ALIAS(vgic_v3_cpuif_trap);
+
+/* Static key checked in pmr_sync(). */
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+KVM_NVHE_ALIAS(gic_pmr_sync);
+#endif
+
+#endif /* CONFIG_KVM */
+
#endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 8d3d9513cbfe..152d8845a1a2 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_KVM) += hyp/
kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
$(KVM)/vfio.o $(KVM)/irqchip.o \
arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \
- inject_fault.o regmap.o va_layout.o hyp.o hyp-init.o handle_exit.o \
+ inject_fault.o regmap.o va_layout.o hyp.o handle_exit.o \
guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o \
vgic-sys-reg-v3.o fpsimd.o pmu.o \
aarch32.o arch_timer.o \
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 90cb90561446..0bf2cf5614c6 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -351,7 +351,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
kvm_vgic_load(vcpu);
kvm_timer_vcpu_load(vcpu);
- kvm_vcpu_load_sysregs(vcpu);
+ if (has_vhe())
+ kvm_vcpu_load_sysregs_vhe(vcpu);
kvm_arch_vcpu_load_fp(vcpu);
kvm_vcpu_pmu_restore_guest(vcpu);
if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
@@ -369,7 +370,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
kvm_arch_vcpu_put_fp(vcpu);
- kvm_vcpu_put_sysregs(vcpu);
+ if (has_vhe())
+ kvm_vcpu_put_sysregs_vhe(vcpu);
kvm_timer_vcpu_put(vcpu);
kvm_vgic_put(vcpu);
kvm_vcpu_pmu_restore_host(vcpu);
@@ -748,11 +750,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
trace_kvm_entry(*vcpu_pc(vcpu));
guest_enter_irqoff();
- if (has_vhe()) {
- ret = kvm_vcpu_run_vhe(vcpu);
- } else {
- ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu);
- }
+ ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu);
vcpu->mode = OUTSIDE_GUEST_MODE;
vcpu->stat.exits++;
@@ -1285,7 +1283,7 @@ static void cpu_init_hyp_mode(void)
* so that we can use adr_l to access per-cpu variables in EL2.
*/
tpidr_el2 = ((unsigned long)this_cpu_ptr(&kvm_host_data) -
- (unsigned long)kvm_ksym_ref(kvm_host_data));
+ (unsigned long)kvm_ksym_ref(&kvm_host_data));
pgd_ptr = kvm_mmu_get_httbr();
hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE;
@@ -1306,7 +1304,7 @@ static void cpu_init_hyp_mode(void)
*/
if (this_cpu_has_cap(ARM64_SSBS) &&
arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
- kvm_call_hyp(__kvm_enable_ssbs);
+ kvm_call_hyp_nvhe(__kvm_enable_ssbs);
}
}
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 8c9880783839..f54f0e89a71c 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -3,18 +3,12 @@
# Makefile for Kernel-based Virtual Machine module, HYP part
#
-ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
- $(DISABLE_STACKLEAK_PLUGIN)
-
-obj-$(CONFIG_KVM) += hyp.o
-
-hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
- debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o
-
-# KVM code is run at a different exception code with a different map, so
-# compiler instrumentation that inserts callbacks or checks into the code may
-# cause crashes. Just disable it.
-GCOV_PROFILE := n
-KASAN_SANITIZE := n
-UBSAN_SANITIZE := n
-KCOV_INSTRUMENT := n
+incdir := $(srctree)/$(src)/include
+subdir-asflags-y := -I$(incdir)
+subdir-ccflags-y := -I$(incdir) \
+ -fno-stack-protector \
+ -DDISABLE_BRANCH_PROFILING \
+ $(DISABLE_STACKLEAK_PLUGIN)
+
+obj-$(CONFIG_KVM) += vhe/ nvhe/
+obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c
index 25c0e47d57cb..f9ff67dfbf0b 100644
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@@ -44,7 +44,7 @@ static const unsigned short cc_map[16] = {
/*
* Check if a trapped instruction should have been executed or not.
*/
-bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
{
unsigned long cpsr;
u32 cpsr_cond;
@@ -93,7 +93,7 @@ bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
*
* IT[7:0] -> CPSR[26:25],CPSR[15:10]
*/
-static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
+static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
{
unsigned long itbits, cond;
unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -123,7 +123,7 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
* kvm_skip_instr - skip a trapped instruction and proceed to the next
* @vcpu: The vcpu pointer
*/
-void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
+void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
{
u32 pc = *vcpu_pc(vcpu);
bool is_thumb;
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 90186cf6473e..dfb4e6d359ab 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -21,7 +21,6 @@
#define CPU_SP_EL0_OFFSET (CPU_XREG_OFFSET(30) + 8)
.text
- .pushsection .hyp.text, "ax"
/*
* We treat x18 as callee-saved as the host may use it as a platform
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
index 5b8ff517ff10..01f114aa47b0 100644
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -9,7 +9,6 @@
#include <asm/fpsimdmacros.h>
.text
- .pushsection .hyp.text, "ax"
SYM_FUNC_START(__fpsimd_save_state)
fpsimd_save x0, 1
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 9c5cfb04170e..689fccbc9de7 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -16,7 +16,6 @@
#include <asm/mmu.h>
.text
- .pushsection .hyp.text, "ax"
.macro do_el2_call
/*
@@ -40,6 +39,7 @@ el1_sync: // Guest trapped into EL2
ccmp x0, #ESR_ELx_EC_HVC32, #4, ne
b.ne el1_trap
+#ifdef __KVM_NVHE_HYPERVISOR__
mrs x1, vttbr_el2 // If vttbr is valid, the guest
cbnz x1, el1_hvc_guest // called HVC
@@ -74,6 +74,7 @@ el1_sync: // Guest trapped into EL2
eret
sb
+#endif /* __KVM_NVHE_HYPERVISOR__ */
el1_hvc_guest:
/*
@@ -180,6 +181,7 @@ el2_error:
eret
sb
+#ifdef __KVM_NVHE_HYPERVISOR__
SYM_FUNC_START(__hyp_do_panic)
mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
PSR_MODE_EL1h)
@@ -189,6 +191,7 @@ SYM_FUNC_START(__hyp_do_panic)
eret
sb
SYM_FUNC_END(__hyp_do_panic)
+#endif
SYM_CODE_START(__hyp_panic)
get_host_ctxt x0, x1
@@ -318,20 +321,4 @@ SYM_CODE_START(__bp_harden_hyp_vecs)
1: .org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
.org 1b
SYM_CODE_END(__bp_harden_hyp_vecs)
-
- .popsection
-
-SYM_CODE_START(__smccc_workaround_1_smc)
- esb
- sub sp, sp, #(8 * 4)
- stp x2, x3, [sp, #(8 * 0)]
- stp x0, x1, [sp, #(8 * 2)]
- mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1
- smc #0
- ldp x2, x3, [sp, #(8 * 0)]
- ldp x0, x1, [sp, #(8 * 2)]
- add sp, sp, #(8 * 4)
-1: .org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
- .org 1b
-SYM_CODE_END(__smccc_workaround_1_smc)
#endif
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index e95af204fec7..24e8acf9ec10 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -4,6 +4,9 @@
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
+#ifndef __ARM64_KVM_HYP_DEBUG_SR_H__
+#define __ARM64_KVM_HYP_DEBUG_SR_H__
+
#include <linux/compiler.h>
#include <linux/kvm_host.h>
@@ -85,53 +88,9 @@
default: write_debug(ptr[0], reg, 0); \
}
-static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
-{
- u64 reg;
-
- /* Clear pmscr in case of early return */
- *pmscr_el1 = 0;
-
- /* SPE present on this CPU? */
- if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
- ID_AA64DFR0_PMSVER_SHIFT))
- return;
-
- /* Yes; is it owned by EL3? */
- reg = read_sysreg_s(SYS_PMBIDR_EL1);
- if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
- return;
-
- /* No; is the host actually using the thing? */
- reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
- if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
- return;
-
- /* Yes; save the control register and disable data generation */
- *pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
- write_sysreg_s(0, SYS_PMSCR_EL1);
- isb();
-
- /* Now drain all buffered data to memory */
- psb_csync();
- dsb(nsh);
-}
-
-static void __hyp_text __debug_restore_spe_nvhe(u64 pmscr_el1)
-{
- if (!pmscr_el1)
- return;
-
- /* The host page table is installed, but not yet synchronised */
- isb();
-
- /* Re-enable data generation */
- write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
-}
-
-static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
- struct kvm_guest_debug_arch *dbg,
- struct kvm_cpu_context *ctxt)
+static inline void __debug_save_state(struct kvm_vcpu *vcpu,
+ struct kvm_guest_debug_arch *dbg,
+ struct kvm_cpu_context *ctxt)
{
u64 aa64dfr0;
int brps, wrps;
@@ -148,9 +107,9 @@ static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
}
-static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
- struct kvm_guest_debug_arch *dbg,
- struct kvm_cpu_context *ctxt)
+static inline void __debug_restore_state(struct kvm_vcpu *vcpu,
+ struct kvm_guest_debug_arch *dbg,
+ struct kvm_cpu_context *ctxt)
{
u64 aa64dfr0;
int brps, wrps;
@@ -168,20 +127,13 @@ static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
}
-void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *host_ctxt;
struct kvm_cpu_context *guest_ctxt;
struct kvm_guest_debug_arch *host_dbg;
struct kvm_guest_debug_arch *guest_dbg;
- /*
- * Non-VHE: Disable and flush SPE data generation
- * VHE: The vcpu can run, but it can't hide.
- */
- if (!has_vhe())
- __debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1);
-
if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
return;
@@ -194,16 +146,13 @@ void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
}
-void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *host_ctxt;
struct kvm_cpu_context *guest_ctxt;
struct kvm_guest_debug_arch *host_dbg;
struct kvm_guest_debug_arch *guest_dbg;
- if (!has_vhe())
- __debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1);
-
if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
return;
@@ -218,7 +167,4 @@ void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY;
}
-u32 __hyp_text __kvm_get_mdcr_el2(void)
-{
- return read_sysreg(mdcr_el2);
-}
+#endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
new file mode 100644
index 000000000000..8f622688fa64
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_SWITCH_H__
+#define __ARM64_KVM_HYP_SWITCH_H__
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+extern const char __hyp_panic_string[];
+
+/* Check whether the FP regs were dirtied while in the host-side run loop: */
+static inline bool update_fp_enabled(struct kvm_vcpu *vcpu)
+{
+ /*
+ * When the system doesn't support FP/SIMD, we cannot rely on
+ * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
+ * abort on the very first access to FP and thus we should never
+ * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
+ * trap the accesses.
+ */
+ if (!system_supports_fpsimd() ||
+ vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
+ vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
+ KVM_ARM64_FP_HOST);
+
+ return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
+}
+
+/* Save the 32-bit only FPSIMD system register state */
+static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
+{
+ if (!vcpu_el1_is_32bit(vcpu))
+ return;
+
+ vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
+}
+
+static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
+{
+ /*
+ * We are about to set CPTR_EL2.TFP to trap all floating point
+ * register accesses to EL2, however, the ARM ARM clearly states that
+ * traps are only taken to EL2 if the operation would not otherwise
+ * trap to EL1. Therefore, always make sure that for 32-bit guests,
+ * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
+ * 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()) {
+ write_sysreg(1 << 30, fpexc32_el2);
+ isb();
+ }
+}
+
+static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
+{
+ /* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
+ write_sysreg(1 << 15, hstr_el2);
+
+ /*
+ * Make sure we trap PMU access from EL0 to EL2. Also sanitize
+ * PMSELR_EL0 to make sure it never contains the cycle
+ * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
+ * EL1 instead of being trapped to EL2.
+ */
+ write_sysreg(0, pmselr_el0);
+ write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+ write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+}
+
+static inline void __deactivate_traps_common(void)
+{
+ write_sysreg(0, hstr_el2);
+ write_sysreg(0, pmuserenr_el0);
+}
+
+static inline void ___activate_traps(struct kvm_vcpu *vcpu)
+{
+ u64 hcr = vcpu->arch.hcr_el2;
+
+ if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+ hcr |= HCR_TVM;
+
+ write_sysreg(hcr, hcr_el2);
+
+ if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
+ write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
+}
+
+static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
+{
+ /*
+ * If we pended a virtual abort, preserve it until it gets
+ * cleared. See D1.14.3 (Virtual Interrupts) for details, but
+ * the crucial bit is "On taking a vSError interrupt,
+ * HCR_EL2.VSE is cleared to 0."
+ */
+ if (vcpu->arch.hcr_el2 & HCR_VSE) {
+ vcpu->arch.hcr_el2 &= ~HCR_VSE;
+ vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
+ }
+}
+
+static inline void __activate_vm(struct kvm *kvm)
+{
+ __load_guest_stage2(kvm);
+}
+
+static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+ u64 par, tmp;
+
+ /*
+ * Resolve the IPA the hard way using the guest VA.
+ *
+ * Stage-1 translation already validated the memory access
+ * rights. As such, we can use the EL1 translation regime, and
+ * don't have to distinguish between EL0 and EL1 access.
+ *
+ * We do need to save/restore PAR_EL1 though, as we haven't
+ * saved the guest context yet, and we may return early...
+ */
+ par = read_sysreg(par_el1);
+ asm volatile("at s1e1r, %0" : : "r" (far));
+ isb();
+
+ tmp = read_sysreg(par_el1);
+ write_sysreg(par, par_el1);
+
+ if (unlikely(tmp & SYS_PAR_EL1_F))
+ return false; /* Translation failed, back to guest */
+
+ /* Convert PAR to HPFAR format */
+ *hpfar = PAR_TO_HPFAR(tmp);
+ return true;
+}
+
+static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+ u8 ec;
+ u64 esr;
+ u64 hpfar, far;
+
+ esr = vcpu->arch.fault.esr_el2;
+ ec = ESR_ELx_EC(esr);
+
+ if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
+ return true;
+
+ far = read_sysreg_el2(SYS_FAR);
+
+ /*
+ * The HPFAR can be invalid if the stage 2 fault did not
+ * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+ * bit is clear) and one of the two following cases are true:
+ * 1. The fault was due to a permission fault
+ * 2. The processor carries errata 834220
+ *
+ * Therefore, for all non S1PTW faults where we either have a
+ * permission fault or the errata workaround is enabled, we
+ * resolve the IPA using the AT instruction.
+ */
+ if (!(esr & ESR_ELx_S1PTW) &&
+ (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
+ (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+ if (!__translate_far_to_hpfar(far, &hpfar))
+ return false;
+ } else {
+ hpfar = read_sysreg(hpfar_el2);
+ }
+
+ vcpu->arch.fault.far_el2 = far;
+ vcpu->arch.fault.hpfar_el2 = hpfar;
+ return true;
+}
+
+/* Check for an FPSIMD/SVE trap and handle as appropriate */
+static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+{
+ bool vhe, sve_guest, sve_host;
+ u8 hsr_ec;
+
+ if (!system_supports_fpsimd())
+ return false;
+
+ /*
+ * Currently system_supports_sve() currently implies has_vhe(),
+ * so the check is redundant. However, has_vhe() can be determined
+ * statically and helps the compiler remove dead code.
+ */
+ if (has_vhe() && system_supports_sve()) {
+ sve_guest = vcpu_has_sve(vcpu);
+ sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
+ vhe = true;
+ } else {
+ sve_guest = false;
+ sve_host = false;
+ vhe = has_vhe();
+ }
+
+ hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+ if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
+ hsr_ec != ESR_ELx_EC_SVE)
+ return false;
+
+ /* Don't handle SVE traps for non-SVE vcpus here: */
+ if (!sve_guest)
+ if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
+ return false;
+
+ /* Valid trap. Switch the context: */
+
+ if (vhe) {
+ u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;
+
+ if (sve_guest)
+ reg |= CPACR_EL1_ZEN;
+
+ write_sysreg(reg, cpacr_el1);
+ } else {
+ write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
+ cptr_el2);
+ }
+
+ isb();
+
+ if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
+ /*
+ * In the SVE case, VHE is assumed: it is enforced by
+ * Kconfig and kvm_arch_init().
+ */
+ if (sve_host) {
+ struct thread_struct *thread = container_of(
+ vcpu->arch.host_fpsimd_state,
+ struct thread_struct, uw.fpsimd_state);
+
+ sve_save_state(sve_pffr(thread),
+ &vcpu->arch.host_fpsimd_state->fpsr);
+ } else {
+ __fpsimd_save_state(vcpu->arch.host_fpsimd_state);
+ }
+
+ vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
+ }
+
+ if (sve_guest) {
+ sve_load_state(vcpu_sve_pffr(vcpu),
+ &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
+ sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
+ write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
+ } else {
+ __fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
+ }
+
+ /* Skip restoring fpexc32 for AArch64 guests */
+ if (!(read_sysreg(hcr_el2) & HCR_RW))
+ write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
+ fpexc32_el2);
+
+ vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
+
+ return true;
+}
+
+static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
+{
+ u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
+ int rt = kvm_vcpu_sys_get_rt(vcpu);
+ u64 val = vcpu_get_reg(vcpu, rt);
+
+ /*
+ * The normal sysreg handling code expects to see the traps,
+ * let's not do anything here.
+ */
+ if (vcpu->arch.hcr_el2 & HCR_TVM)
+ return false;
+
+ switch (sysreg) {
+ case SYS_SCTLR_EL1:
+ write_sysreg_el1(val, SYS_SCTLR);
+ break;
+ case SYS_TTBR0_EL1:
+ write_sysreg_el1(val, SYS_TTBR0);
+ break;
+ case SYS_TTBR1_EL1:
+ write_sysreg_el1(val, SYS_TTBR1);
+ break;
+ case SYS_TCR_EL1:
+ write_sysreg_el1(val, SYS_TCR);
+ break;
+ case SYS_ESR_EL1:
+ write_sysreg_el1(val, SYS_ESR);
+ break;
+ case SYS_FAR_EL1:
+ write_sysreg_el1(val, SYS_FAR);
+ break;
+ case SYS_AFSR0_EL1:
+ write_sysreg_el1(val, SYS_AFSR0);
+ break;
+ case SYS_AFSR1_EL1:
+ write_sysreg_el1(val, SYS_AFSR1);
+ break;
+ case SYS_MAIR_EL1:
+ write_sysreg_el1(val, SYS_MAIR);
+ break;
+ case SYS_AMAIR_EL1:
+ write_sysreg_el1(val, SYS_AMAIR);
+ break;
+ case SYS_CONTEXTIDR_EL1:
+ write_sysreg_el1(val, SYS_CONTEXTIDR);
+ break;
+ default:
+ return false;
+ }
+
+ __kvm_skip_instr(vcpu);
+ return true;
+}
+
+static inline bool esr_is_ptrauth_trap(u32 esr)
+{
+ u32 ec = ESR_ELx_EC(esr);
+
+ if (ec == ESR_ELx_EC_PAC)
+ return true;
+
+ if (ec != ESR_ELx_EC_SYS64)
+ return false;
+
+ switch (esr_sys64_to_sysreg(esr)) {
+ case SYS_APIAKEYLO_EL1:
+ case SYS_APIAKEYHI_EL1:
+ case SYS_APIBKEYLO_EL1:
+ case SYS_APIBKEYHI_EL1:
+ case SYS_APDAKEYLO_EL1:
+ case SYS_APDAKEYHI_EL1:
+ case SYS_APDBKEYLO_EL1:
+ case SYS_APDBKEYHI_EL1:
+ case SYS_APGAKEYLO_EL1:
+ case SYS_APGAKEYHI_EL1:
+ return true;
+ }
+
+ return false;
+}
+
+#define __ptrauth_save_key(regs, key) \
+({ \
+ regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \
+ regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \
+})
+
+static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpu_context *ctxt;
+ u64 val;
+
+ if (!vcpu_has_ptrauth(vcpu) ||
+ !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu)))
+ return false;
+
+ ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+ __ptrauth_save_key(ctxt->sys_regs, APIA);
+ __ptrauth_save_key(ctxt->sys_regs, APIB);
+ __ptrauth_save_key(ctxt->sys_regs, APDA);
+ __ptrauth_save_key(ctxt->sys_regs, APDB);
+ __ptrauth_save_key(ctxt->sys_regs, APGA);
+
+ vcpu_ptrauth_enable(vcpu);
+
+ val = read_sysreg(hcr_el2);
+ val |= (HCR_API | HCR_APK);
+ write_sysreg(val, hcr_el2);
+
+ return true;
+}
+
+/*
+ * Return true when we were able to fixup the guest exit and should return to
+ * the guest, false when we should restore the host state and return to the
+ * main run loop.
+ */
+static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
+ vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
+
+ /*
+ * We're using the raw exception code in order to only process
+ * the trap if no SError is pending. We will come back to the
+ * same PC once the SError has been injected, and replay the
+ * trapping instruction.
+ */
+ if (*exit_code != ARM_EXCEPTION_TRAP)
+ goto exit;
+
+ if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+ kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
+ handle_tx2_tvm(vcpu))
+ return true;
+
+ /*
+ * We trap the first access to the FP/SIMD to save the host context
+ * and restore the guest context lazily.
+ * If FP/SIMD is not implemented, handle the trap and inject an
+ * undefined instruction exception to the guest.
+ * Similarly for trapped SVE accesses.
+ */
+ if (__hyp_handle_fpsimd(vcpu))
+ return true;
+
+ if (__hyp_handle_ptrauth(vcpu))
+ return true;
+
+ if (!__populate_fault_info(vcpu))
+ return true;
+
+ if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
+ bool valid;
+
+ valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
+ kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+ kvm_vcpu_dabt_isvalid(vcpu) &&
+ !kvm_vcpu_dabt_isextabt(vcpu) &&
+ !kvm_vcpu_dabt_iss1tw(vcpu);
+
+ if (valid) {
+ int ret = __vgic_v2_perform_cpuif_access(vcpu);
+
+ if (ret == 1)
+ return true;
+
+ /* Promote an illegal access to an SError.*/
+ if (ret == -1)
+ *exit_code = ARM_EXCEPTION_EL1_SERROR;
+
+ goto exit;
+ }
+ }
+
+ if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+ (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
+ kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
+ int ret = __vgic_v3_perform_cpuif_access(vcpu);
+
+ if (ret == 1)
+ return true;
+ }
+
+exit:
+ /* Return to the host kernel and handle the exit */
+ return false;
+}
+
+static inline bool __needs_ssbd_off(struct kvm_vcpu *vcpu)
+{
+ if (!cpus_have_final_cap(ARM64_SSBD))
+ return false;
+
+ return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
+}
+
+static inline void __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+ /*
+ * The host runs with the workaround always present. If the
+ * guest wants it disabled, so be it...
+ */
+ if (__needs_ssbd_off(vcpu) &&
+ __hyp_this_cpu_read(arm64_ssbd_callback_required))
+ arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
+#endif
+}
+
+static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+ /*
+ * If the guest has disabled the workaround, bring it back on.
+ */
+ if (__needs_ssbd_off(vcpu) &&
+ __hyp_this_cpu_read(arm64_ssbd_callback_required))
+ arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
+#endif
+}
+
+#endif /* __ARM64_KVM_HYP_SWITCH_H__ */
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index cc7e957f5b2c..6e04e061f762 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -4,6 +4,9 @@
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
+#ifndef __ARM64_KVM_HYP_SYSREG_SR_H__
+#define __ARM64_KVM_HYP_SYSREG_SR_H__
+
#include <linux/compiler.h>
#include <linux/kvm_host.h>
@@ -12,30 +15,18 @@
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
-/*
- * Non-VHE: Both host and guest must save everything.
- *
- * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
- * pstate, which are handled as part of the el2 return state) on every
- * switch (sp_el0 is being dealt with in the assembly code).
- * tpidr_el0 and tpidrro_el0 only need to be switched when going
- * to host userspace or a different VCPU. EL1 registers only need to be
- * switched when potentially going to run a different VCPU. The latter two
- * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put.
- */
-
-static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
{
ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1);
}
-static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
{
ctxt->sys_regs[TPIDR_EL0] = read_sysreg(tpidr_el0);
ctxt->sys_regs[TPIDRRO_EL0] = read_sysreg(tpidrro_el0);
}
-static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
{
ctxt->sys_regs[CSSELR_EL1] = read_sysreg(csselr_el1);
ctxt->sys_regs[SCTLR_EL1] = read_sysreg_el1(SYS_SCTLR);
@@ -60,7 +51,7 @@ static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR);
}
-static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
{
ctxt->gp_regs.regs.pc = read_sysreg_el2(SYS_ELR);
ctxt->gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
@@ -69,39 +60,18 @@ static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ct
ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
}
-void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
-{
- __sysreg_save_el1_state(ctxt);
- __sysreg_save_common_state(ctxt);
- __sysreg_save_user_state(ctxt);
- __sysreg_save_el2_return_state(ctxt);
-}
-
-void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
-{
- __sysreg_save_common_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_save_host_state_vhe);
-
-void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
-{
- __sysreg_save_common_state(ctxt);
- __sysreg_save_el2_return_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
-
-static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
{
write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1);
}
-static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
{
write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0);
write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
}
-static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
{
write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2);
write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1);
@@ -114,7 +84,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
/*
* Must only be done for guest registers, hence the context
* test. We're coming from the host, so SCTLR.M is already
- * set. Pairs with __activate_traps_nvhe().
+ * set. Pairs with nVHE's __activate_traps().
*/
write_sysreg_el1((ctxt->sys_regs[TCR_EL1] |
TCR_EPD1_MASK | TCR_EPD0_MASK),
@@ -142,7 +112,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
ctxt->__hyp_running_vcpu) {
/*
* Must only be done for host registers, hence the context
- * test. Pairs with __deactivate_traps_nvhe().
+ * test. Pairs with nVHE's __deactivate_traps().
*/
isb();
/*
@@ -160,8 +130,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
}
-static void __hyp_text
-__sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
{
u64 pstate = ctxt->gp_regs.regs.pstate;
u64 mode = pstate & PSR_AA32_MODE_MASK;
@@ -187,28 +156,7 @@ __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
}
-void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
-{
- __sysreg_restore_el1_state(ctxt);
- __sysreg_restore_common_state(ctxt);
- __sysreg_restore_user_state(ctxt);
- __sysreg_restore_el2_return_state(ctxt);
-}
-
-void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
-{
- __sysreg_restore_common_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe);
-
-void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
-{
- __sysreg_restore_common_state(ctxt);
- __sysreg_restore_el2_return_state(ctxt);
-}
-NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
-
-void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
+static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
{
u64 *spsr, *sysreg;
@@ -230,7 +178,7 @@ void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
}
-void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
+static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
{
u64 *spsr, *sysreg;
@@ -252,82 +200,4 @@ void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2);
}
-/**
- * kvm_vcpu_load_sysregs - Load guest system registers to the physical CPU
- *
- * @vcpu: The VCPU pointer
- *
- * Load system registers that do not affect the host's execution, for
- * example EL1 system registers on a VHE system where the host kernel
- * runs at EL2. This function is called from KVM's vcpu_load() function
- * and loading system register state early avoids having to load them on
- * every entry to the VM.
- */
-void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
- struct kvm_cpu_context *host_ctxt;
-
- if (!has_vhe())
- return;
-
- host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
- __sysreg_save_user_state(host_ctxt);
-
- /*
- * Load guest EL1 and user state
- *
- * We must restore the 32-bit state before the sysregs, thanks
- * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
- */
- __sysreg32_restore_state(vcpu);
- __sysreg_restore_user_state(guest_ctxt);
- __sysreg_restore_el1_state(guest_ctxt);
-
- vcpu->arch.sysregs_loaded_on_cpu = true;
-
- activate_traps_vhe_load(vcpu);
-}
-
-/**
- * kvm_vcpu_put_sysregs - Restore host system registers to the physical CPU
- *
- * @vcpu: The VCPU pointer
- *
- * Save guest system registers that do not affect the host's execution, for
- * example EL1 system registers on a VHE system where the host kernel
- * runs at EL2. This function is called from KVM's vcpu_put() function
- * and deferring saving system register state until we're no longer running the
- * VCPU avoids having to save them on every exit from the VM.
- */
-void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
- struct kvm_cpu_context *host_ctxt;
-
- if (!has_vhe())
- return;
-
- host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
- deactivate_traps_vhe_put();
-
- __sysreg_save_el1_state(guest_ctxt);
- __sysreg_save_user_state(guest_ctxt);
- __sysreg32_save_state(vcpu);
-
- /* Restore host user state */
- __sysreg_restore_user_state(host_ctxt);
-
- vcpu->arch.sysregs_loaded_on_cpu = false;
-}
-
-void __hyp_text __kvm_enable_ssbs(void)
-{
- u64 tmp;
-
- asm volatile(
- "mrs %0, sctlr_el2\n"
- "orr %0, %0, %1\n"
- "msr sctlr_el2, %0"
- : "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
-}
+#endif /* __ARM64_KVM_HYP_SYSREG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
new file mode 100644
index 000000000000..0b34414557d6
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part
+#
+
+asflags-y := -D__KVM_NVHE_HYPERVISOR__
+ccflags-y := -D__KVM_NVHE_HYPERVISOR__
+
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o
+obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
+ ../fpsimd.o ../hyp-entry.o
+
+obj-y := $(patsubst %.o,%.hyp.o,$(obj-y))
+extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y))
+
+$(obj)/%.hyp.tmp.o: $(src)/%.c FORCE
+ $(call if_changed_rule,cc_o_c)
+$(obj)/%.hyp.tmp.o: $(src)/%.S FORCE
+ $(call if_changed_rule,as_o_S)
+$(obj)/%.hyp.o: $(obj)/%.hyp.tmp.o FORCE
+ $(call if_changed,hypcopy)
+
+quiet_cmd_hypcopy = HYPCOPY $@
+ cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ \
+ --rename-section=.text=.hyp.text \
+ $< $@
+
+# Remove ftrace and Shadow Call Stack CFLAGS.
+# This is equivalent to the 'notrace' and '__noscs' annotations.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
+
+# KVM nVHE code is run at a different exception code with a different map, so
+# compiler instrumentation that inserts callbacks or checks into the code may
+# cause crashes. Just disable it.
+GCOV_PROFILE := n
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+
+# Skip objtool checking for this directory because nVHE code is compiled with
+# non-standard build rules.
+OBJECT_FILES_NON_STANDARD := y
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
new file mode 100644
index 000000000000..91a711aa8382
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/debug-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/debug-monitors.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+static void __debug_save_spe(u64 *pmscr_el1)
+{
+ u64 reg;
+
+ /* Clear pmscr in case of early return */
+ *pmscr_el1 = 0;
+
+ /* SPE present on this CPU? */
+ if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
+ ID_AA64DFR0_PMSVER_SHIFT))
+ return;
+
+ /* Yes; is it owned by EL3? */
+ reg = read_sysreg_s(SYS_PMBIDR_EL1);
+ if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
+ return;
+
+ /* No; is the host actually using the thing? */
+ reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
+ if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
+ return;
+
+ /* Yes; save the control register and disable data generation */
+ *pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
+ write_sysreg_s(0, SYS_PMSCR_EL1);
+ isb();
+
+ /* Now drain all buffered data to memory */
+ psb_csync();
+ dsb(nsh);
+}
+
+static void __debug_restore_spe(u64 pmscr_el1)
+{
+ if (!pmscr_el1)
+ return;
+
+ /* The host page table is installed, but not yet synchronised */
+ isb();
+
+ /* Re-enable data generation */
+ write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
+}
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+ /* Disable and flush SPE data generation */
+ __debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+ __debug_switch_to_guest_common(vcpu);
+}
+
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
+ __debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+ __debug_switch_to_host_common(vcpu);
+}
+
+u32 __kvm_get_mdcr_el2(void)
+{
+ return read_sysreg(mdcr_el2);
+}
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 6e6ed5581eed..6e6ed5581eed 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
new file mode 100644
index 000000000000..a1dcf59bd45e
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/switch.h>
+#include <hyp/sysreg-sr.h>
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+static void __activate_traps(struct kvm_vcpu *vcpu)
+{
+ u64 val;
+
+ ___activate_traps(vcpu);
+ __activate_traps_common(vcpu);
+
+ val = CPTR_EL2_DEFAULT;
+ val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
+ if (!update_fp_enabled(vcpu)) {
+ val |= CPTR_EL2_TFP;
+ __activate_traps_fpsimd32(vcpu);
+ }
+
+ write_sysreg(val, cptr_el2);
+
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+ struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+
+ isb();
+ /*
+ * At this stage, and thanks to the above isb(), S2 is
+ * configured and enabled. We can now restore the guest's S1
+ * configuration: SCTLR, and only then TCR.
+ */
+ write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR);
+ isb();
+ write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR);
+ }
+}
+
+static void __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+ u64 mdcr_el2;
+
+ ___deactivate_traps(vcpu);
+
+ mdcr_el2 = read_sysreg(mdcr_el2);
+
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+ u64 val;
+
+ /*
+ * Set the TCR and SCTLR registers in the exact opposite
+ * sequence as __activate_traps (first prevent walks,
+ * then force the MMU on). A generous sprinkling of isb()
+ * ensure that things happen in this exact order.
+ */
+ val = read_sysreg_el1(SYS_TCR);
+ write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
+ isb();
+ val = read_sysreg_el1(SYS_SCTLR);
+ write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
+ isb();
+ }
+
+ __deactivate_traps_common();
+
+ mdcr_el2 &= MDCR_EL2_HPMN_MASK;
+ mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+
+ write_sysreg(mdcr_el2, mdcr_el2);
+ write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
+ write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
+}
+
+static void __deactivate_vm(struct kvm_vcpu *vcpu)
+{
+ write_sysreg(0, vttbr_el2);
+}
+
+/* Save VGICv3 state on non-VHE systems */
+static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
+{
+ if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+ __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
+ __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
+ }
+}
+
+/* Restore VGICv3 state on non_VEH systems */
+static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
+{
+ if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
+ __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
+ __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
+ }
+}
+
+/**
+ * Disable host events, enable guest events
+ */
+static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
+{
+ struct kvm_host_data *host;
+ struct kvm_pmu_events *pmu;
+
+ host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+ pmu = &host->pmu_events;
+
+ if (pmu->events_host)
+ write_sysreg(pmu->events_host, pmcntenclr_el0);
+
+ if (pmu->events_guest)
+ write_sysreg(pmu->events_guest, pmcntenset_el0);
+
+ return (pmu->events_host || pmu->events_guest);
+}
+
+/**
+ * Disable guest events, enable host events
+ */
+static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
+{
+ struct kvm_host_data *host;
+ struct kvm_pmu_events *pmu;
+
+ host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
+ pmu = &host->pmu_events;
+
+ if (pmu->events_guest)
+ write_sysreg(pmu->events_guest, pmcntenclr_el0);
+
+ if (pmu->events_host)
+ write_sysreg(pmu->events_host, pmcntenset_el0);
+}
+
+/* Switch to the guest for legacy non-VHE systems */
+int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpu_context *host_ctxt;
+ struct kvm_cpu_context *guest_ctxt;
+ bool pmu_switch_needed;
+ u64 exit_code;
+
+ /*
+ * Having IRQs masked via PMR when entering the guest means the GIC
+ * will not signal the CPU of interrupts of lower priority, and the
+ * only way to get out will be via guest exceptions.
+ * Naturally, we want to avoid this.
+ */
+ if (system_uses_irq_prio_masking()) {
+ gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+ pmr_sync();
+ }
+
+ vcpu = kern_hyp_va(vcpu);
+
+ host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+ host_ctxt->__hyp_running_vcpu = vcpu;
+ guest_ctxt = &vcpu->arch.ctxt;
+
+ pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
+
+ __sysreg_save_state_nvhe(host_ctxt);
+
+ /*
+ * We must restore the 32-bit state before the sysregs, thanks
+ * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+ *
+ * Also, and in order to be able to deal with erratum #1319537 (A57)
+ * and #1319367 (A72), we must ensure that all VM-related sysreg are
+ * restored before we enable S2 translation.
+ */
+ __sysreg32_restore_state(vcpu);
+ __sysreg_restore_state_nvhe(guest_ctxt);
+
+ __activate_vm(kern_hyp_va(vcpu->kvm));
+ __activate_traps(vcpu);
+
+ __hyp_vgic_restore_state(vcpu);
+ __timer_enable_traps(vcpu);
+
+ __debug_switch_to_guest(vcpu);
+
+ __set_guest_arch_workaround_state(vcpu);
+
+ do {
+ /* Jump in the fire! */
+ exit_code = __guest_enter(vcpu, host_ctxt);
+
+ /* And we're baaack! */
+ } while (fixup_guest_exit(vcpu, &exit_code));
+
+ __set_host_arch_workaround_state(vcpu);
+
+ __sysreg_save_state_nvhe(guest_ctxt);
+ __sysreg32_save_state(vcpu);
+ __timer_disable_traps(vcpu);
+ __hyp_vgic_save_state(vcpu);
+
+ __deactivate_traps(vcpu);
+ __deactivate_vm(vcpu);
+
+ __sysreg_restore_state_nvhe(host_ctxt);
+
+ if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
+ __fpsimd_save_fpexc32(vcpu);
+
+ /*
+ * This must come after restoring the host sysregs, since a non-VHE
+ * system may enable SPE here and make use of the TTBRs.
+ */
+ __debug_switch_to_host(vcpu);
+
+ if (pmu_switch_needed)
+ __pmu_switch_to_host(host_ctxt);
+
+ /* Returning to host will clear PSR.I, remask PMR if needed */
+ if (system_uses_irq_prio_masking())
+ gic_write_pmr(GIC_PRIO_IRQOFF);
+
+ return exit_code;
+}
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+{
+ u64 spsr = read_sysreg_el2(SYS_SPSR);
+ u64 elr = read_sysreg_el2(SYS_ELR);
+ u64 par = read_sysreg(par_el1);
+ struct kvm_vcpu *vcpu = host_ctxt->__hyp_running_vcpu;
+ unsigned long str_va;
+
+ if (read_sysreg(vttbr_el2)) {
+ __timer_disable_traps(vcpu);
+ __deactivate_traps(vcpu);
+ __deactivate_vm(vcpu);
+ __sysreg_restore_state_nvhe(host_ctxt);
+ }
+
+ /*
+ * Force the panic string to be loaded from the literal pool,
+ * making sure it is a kernel address and not a PC-relative
+ * reference.
+ */
+ asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string));
+
+ __hyp_do_panic(str_va,
+ spsr, elr,
+ read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
+ read_sysreg(hpfar_el2), par, vcpu);
+ unreachable();
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
new file mode 100644
index 000000000000..88a25fc8fcd3
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/sysreg-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * Non-VHE: Both host and guest must save everything.
+ */
+
+void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+ __sysreg_save_el1_state(ctxt);
+ __sysreg_save_common_state(ctxt);
+ __sysreg_save_user_state(ctxt);
+ __sysreg_save_el2_return_state(ctxt);
+}
+
+void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
+{
+ __sysreg_restore_el1_state(ctxt);
+ __sysreg_restore_common_state(ctxt);
+ __sysreg_restore_user_state(ctxt);
+ __sysreg_restore_el2_return_state(ctxt);
+}
+
+void __kvm_enable_ssbs(void)
+{
+ u64 tmp;
+
+ asm volatile(
+ "mrs %0, sctlr_el2\n"
+ "orr %0, %0, %1\n"
+ "msr sctlr_el2, %0"
+ : "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
+}
diff --git a/arch/arm64/kvm/hyp/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
index fb5c0be33223..9072e71693ba 100644
--- a/arch/arm64/kvm/hyp/timer-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
@@ -10,7 +10,7 @@
#include <asm/kvm_hyp.h>
-void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff)
+void __kvm_timer_set_cntvoff(u64 cntvoff)
{
write_sysreg(cntvoff, cntvoff_el2);
}
@@ -19,7 +19,7 @@ void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff)
* Should only be called on non-VHE systems.
* VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
*/
-void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
+void __timer_disable_traps(struct kvm_vcpu *vcpu)
{
u64 val;
@@ -33,7 +33,7 @@ void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
* Should only be called on non-VHE systems.
* VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
*/
-void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu)
+void __timer_enable_traps(struct kvm_vcpu *vcpu)
{
u64 val;
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index d063a576d511..d4475f8340c4 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -4,64 +4,15 @@
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
-#include <linux/irqflags.h>
-
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
#include <asm/tlbflush.h>
struct tlb_inv_context {
- unsigned long flags;
u64 tcr;
- u64 sctlr;
};
-static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
- struct tlb_inv_context *cxt)
-{
- u64 val;
-
- local_irq_save(cxt->flags);
-
- if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
- /*
- * For CPUs that are affected by ARM errata 1165522 or 1530923,
- * we cannot trust stage-1 to be in a correct state at that
- * point. Since we do not want to force a full load of the
- * vcpu state, we prevent the EL1 page-table walker to
- * allocate new TLBs. This is done by setting the EPD bits
- * in the TCR_EL1 register. We also need to prevent it to
- * allocate IPA->PA walks, so we enable the S1 MMU...
- */
- val = cxt->tcr = read_sysreg_el1(SYS_TCR);
- val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
- write_sysreg_el1(val, SYS_TCR);
- val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR);
- val |= SCTLR_ELx_M;
- write_sysreg_el1(val, SYS_SCTLR);
- }
-
- /*
- * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
- * most TLB operations target EL2/EL0. In order to affect the
- * guest TLBs (EL1/EL0), we need to change one of these two
- * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
- * let's flip TGE before executing the TLB operation.
- *
- * ARM erratum 1165522 requires some special handling (again),
- * as we need to make sure both stages of translation are in
- * place before clearing TGE. __load_guest_stage2() already
- * has an ISB in order to deal with this.
- */
- __load_guest_stage2(kvm);
- val = read_sysreg(hcr_el2);
- val &= ~HCR_TGE;
- write_sysreg(val, hcr_el2);
- isb();
-}
-
-static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
- struct tlb_inv_context *cxt)
+static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
{
if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
u64 val;
@@ -84,37 +35,7 @@ static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
}
-static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
- struct tlb_inv_context *cxt)
-{
- if (has_vhe())
- __tlb_switch_to_guest_vhe(kvm, cxt);
- else
- __tlb_switch_to_guest_nvhe(kvm, cxt);
-}
-
-static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
- struct tlb_inv_context *cxt)
-{
- /*
- * We're done with the TLB operation, let's restore the host's
- * view of HCR_EL2.
- */
- write_sysreg(0, vttbr_el2);
- write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
- isb();
-
- if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
- /* Restore the registers to what they were */
- write_sysreg_el1(cxt->tcr, SYS_TCR);
- write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
- }
-
- local_irq_restore(cxt->flags);
-}
-
-static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
- struct tlb_inv_context *cxt)
+static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
{
write_sysreg(0, vttbr_el2);
@@ -126,16 +47,7 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
}
}
-static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
- struct tlb_inv_context *cxt)
-{
- if (has_vhe())
- __tlb_switch_to_host_vhe(kvm, cxt);
- else
- __tlb_switch_to_host_nvhe(kvm, cxt);
-}
-
-void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
{
struct tlb_inv_context cxt;
@@ -183,13 +95,13 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
* The moral of this story is: if you have a VPIPT I-cache, then
* you should be running with VHE enabled.
*/
- if (!has_vhe() && icache_is_vpipt())
+ if (icache_is_vpipt())
__flush_icache_all();
__tlb_switch_to_host(kvm, &cxt);
}
-void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
+void __kvm_tlb_flush_vmid(struct kvm *kvm)
{
struct tlb_inv_context cxt;
@@ -206,7 +118,7 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
__tlb_switch_to_host(kvm, &cxt);
}
-void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
struct tlb_inv_context cxt;
@@ -221,7 +133,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
__tlb_switch_to_host(kvm, &cxt);
}
-void __hyp_text __kvm_flush_vm_context(void)
+void __kvm_flush_vm_context(void)
{
dsb(ishst);
__tlbi(alle1is);
diff --git a/arch/arm64/kvm/hyp/smccc_wa.S b/arch/arm64/kvm/hyp/smccc_wa.S
new file mode 100644
index 000000000000..b0441dbdf68b
--- /dev/null
+++ b/arch/arm64/kvm/hyp/smccc_wa.S
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2015-2018 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/linkage.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+ /*
+ * This is not executed directly and is instead copied into the vectors
+ * by install_bp_hardening_cb().
+ */
+ .data
+ .pushsection .rodata
+ .global __smccc_workaround_1_smc
+SYM_DATA_START(__smccc_workaround_1_smc)
+ esb
+ sub sp, sp, #(8 * 4)
+ stp x2, x3, [sp, #(8 * 0)]
+ stp x0, x1, [sp, #(8 * 2)]
+ mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1
+ smc #0
+ ldp x2, x3, [sp, #(8 * 0)]
+ ldp x0, x1, [sp, #(8 * 2)]
+ add sp, sp, #(8 * 4)
+1: .org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
+ .org 1b
+SYM_DATA_END(__smccc_workaround_1_smc)
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
deleted file mode 100644
index db1c4487d95d..000000000000
--- a/arch/arm64/kvm/hyp/switch.c
+++ /dev/null
@@ -1,936 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2015 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <linux/arm-smccc.h>
-#include <linux/kvm_host.h>
-#include <linux/types.h>
-#include <linux/jump_label.h>
-#include <uapi/linux/psci.h>
-
-#include <kvm/arm_psci.h>
-
-#include <asm/barrier.h>
-#include <asm/cpufeature.h>
-#include <asm/kprobes.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_hyp.h>
-#include <asm/kvm_mmu.h>
-#include <asm/fpsimd.h>
-#include <asm/debug-monitors.h>
-#include <asm/processor.h>
-#include <asm/thread_info.h>
-
-/* Check whether the FP regs were dirtied while in the host-side run loop: */
-static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
-{
- /*
- * When the system doesn't support FP/SIMD, we cannot rely on
- * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
- * abort on the very first access to FP and thus we should never
- * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
- * trap the accesses.
- */
- if (!system_supports_fpsimd() ||
- vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
- vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
- KVM_ARM64_FP_HOST);
-
- return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
-}
-
-/* Save the 32-bit only FPSIMD system register state */
-static void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
-{
- if (!vcpu_el1_is_32bit(vcpu))
- return;
-
- vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2);
-}
-
-static void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
-{
- /*
- * We are about to set CPTR_EL2.TFP to trap all floating point
- * register accesses to EL2, however, the ARM ARM clearly states that
- * traps are only taken to EL2 if the operation would not otherwise
- * trap to EL1. Therefore, always make sure that for 32-bit guests,
- * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
- * 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()) {
- write_sysreg(1 << 30, fpexc32_el2);
- isb();
- }
-}
-
-static void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu)
-{
- /* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
- write_sysreg(1 << 15, hstr_el2);
-
- /*
- * Make sure we trap PMU access from EL0 to EL2. Also sanitize
- * PMSELR_EL0 to make sure it never contains the cycle
- * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
- * EL1 instead of being trapped to EL2.
- */
- write_sysreg(0, pmselr_el0);
- write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
- write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
-}
-
-static void __hyp_text __deactivate_traps_common(void)
-{
- write_sysreg(0, hstr_el2);
- write_sysreg(0, pmuserenr_el0);
-}
-
-static void activate_traps_vhe(struct kvm_vcpu *vcpu)
-{
- u64 val;
-
- val = read_sysreg(cpacr_el1);
- val |= CPACR_EL1_TTA;
- val &= ~CPACR_EL1_ZEN;
-
- /*
- * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
- * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
- * except for some missing controls, such as TAM.
- * In this case, CPTR_EL2.TAM has the same position with or without
- * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
- * shift value for trapping the AMU accesses.
- */
-
- val |= CPTR_EL2_TAM;
-
- if (update_fp_enabled(vcpu)) {
- if (vcpu_has_sve(vcpu))
- val |= CPACR_EL1_ZEN;
- } else {
- val &= ~CPACR_EL1_FPEN;
- __activate_traps_fpsimd32(vcpu);
- }
-
- write_sysreg(val, cpacr_el1);
-
- write_sysreg(kvm_get_hyp_vector(), vbar_el1);
-}
-NOKPROBE_SYMBOL(activate_traps_vhe);
-
-static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
-{
- u64 val;
-
- __activate_traps_common(vcpu);
-
- val = CPTR_EL2_DEFAULT;
- val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
- if (!update_fp_enabled(vcpu)) {
- val |= CPTR_EL2_TFP;
- __activate_traps_fpsimd32(vcpu);
- }
-
- write_sysreg(val, cptr_el2);
-
- if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
- struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
-
- isb();
- /*
- * At this stage, and thanks to the above isb(), S2 is
- * configured and enabled. We can now restore the guest's S1
- * configuration: SCTLR, and only then TCR.
- */
- write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR);
- isb();
- write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR);
- }
-}
-
-static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
-{
- u64 hcr = vcpu->arch.hcr_el2;
-
- if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
- hcr |= HCR_TVM;
-
- write_sysreg(hcr, hcr_el2);
-
- if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
- write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
-
- if (has_vhe())
- activate_traps_vhe(vcpu);
- else
- __activate_traps_nvhe(vcpu);
-}
-
-static void deactivate_traps_vhe(void)
-{
- extern char vectors[]; /* kernel exception vectors */
- write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
-
- /*
- * ARM errata 1165522 and 1530923 require the actual execution of the
- * above before we can switch to the EL2/EL0 translation regime used by
- * the host.
- */
- asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
-
- write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
- write_sysreg(vectors, vbar_el1);
-}
-NOKPROBE_SYMBOL(deactivate_traps_vhe);
-
-static void __hyp_text __deactivate_traps_nvhe(void)
-{
- u64 mdcr_el2 = read_sysreg(mdcr_el2);
-
- if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
- u64 val;
-
- /*
- * Set the TCR and SCTLR registers in the exact opposite
- * sequence as __activate_traps_nvhe (first prevent walks,
- * then force the MMU on). A generous sprinkling of isb()
- * ensure that things happen in this exact order.
- */
- val = read_sysreg_el1(SYS_TCR);
- write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR);
- isb();
- val = read_sysreg_el1(SYS_SCTLR);
- write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR);
- isb();
- }
-
- __deactivate_traps_common();
-
- mdcr_el2 &= MDCR_EL2_HPMN_MASK;
- mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
-
- write_sysreg(mdcr_el2, mdcr_el2);
- write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
- write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
-}
-
-static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
-{
- /*
- * If we pended a virtual abort, preserve it until it gets
- * cleared. See D1.14.3 (Virtual Interrupts) for details, but
- * the crucial bit is "On taking a vSError interrupt,
- * HCR_EL2.VSE is cleared to 0."
- */
- if (vcpu->arch.hcr_el2 & HCR_VSE) {
- vcpu->arch.hcr_el2 &= ~HCR_VSE;
- vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
- }
-
- if (has_vhe())
- deactivate_traps_vhe();
- else
- __deactivate_traps_nvhe();
-}
-
-void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
-{
- __activate_traps_common(vcpu);
-}
-
-void deactivate_traps_vhe_put(void)
-{
- u64 mdcr_el2 = read_sysreg(mdcr_el2);
-
- mdcr_el2 &= MDCR_EL2_HPMN_MASK |
- MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
- MDCR_EL2_TPMS;
-
- write_sysreg(mdcr_el2, mdcr_el2);
-
- __deactivate_traps_common();
-}
-
-static void __hyp_text __activate_vm(struct kvm *kvm)
-{
- __load_guest_stage2(kvm);
-}
-
-static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
-{
- write_sysreg(0, vttbr_el2);
-}
-
-/* Save VGICv3 state on non-VHE systems */
-static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu)
-{
- if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
- __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3);
- __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
- }
-}
-
-/* Restore VGICv3 state on non_VEH systems */
-static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
-{
- if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) {
- __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3);
- __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3);
- }
-}
-
-static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
-{
- u64 par, tmp;
-
- /*
- * Resolve the IPA the hard way using the guest VA.
- *
- * Stage-1 translation already validated the memory access
- * rights. As such, we can use the EL1 translation regime, and
- * don't have to distinguish between EL0 and EL1 access.
- *
- * We do need to save/restore PAR_EL1 though, as we haven't
- * saved the guest context yet, and we may return early...
- */
- par = read_sysreg(par_el1);
- asm volatile("at s1e1r, %0" : : "r" (far));
- isb();
-
- tmp = read_sysreg(par_el1);
- write_sysreg(par, par_el1);
-
- if (unlikely(tmp & SYS_PAR_EL1_F))
- return false; /* Translation failed, back to guest */
-
- /* Convert PAR to HPFAR format */
- *hpfar = PAR_TO_HPFAR(tmp);
- return true;
-}
-
-static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
-{
- u8 ec;
- u64 esr;
- u64 hpfar, far;
-
- esr = vcpu->arch.fault.esr_el2;
- ec = ESR_ELx_EC(esr);
-
- if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
- return true;
-
- far = read_sysreg_el2(SYS_FAR);
-
- /*
- * The HPFAR can be invalid if the stage 2 fault did not
- * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
- * bit is clear) and one of the two following cases are true:
- * 1. The fault was due to a permission fault
- * 2. The processor carries errata 834220
- *
- * Therefore, for all non S1PTW faults where we either have a
- * permission fault or the errata workaround is enabled, we
- * resolve the IPA using the AT instruction.
- */
- if (!(esr & ESR_ELx_S1PTW) &&
- (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
- (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
- if (!__translate_far_to_hpfar(far, &hpfar))
- return false;
- } else {
- hpfar = read_sysreg(hpfar_el2);
- }
-
- vcpu->arch.fault.far_el2 = far;
- vcpu->arch.fault.hpfar_el2 = hpfar;
- return true;
-}
-
-/* Check for an FPSIMD/SVE trap and handle as appropriate */
-static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
-{
- bool vhe, sve_guest, sve_host;
- u8 hsr_ec;
-
- if (!system_supports_fpsimd())
- return false;
-
- if (system_supports_sve()) {
- sve_guest = vcpu_has_sve(vcpu);
- sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
- vhe = true;
- } else {
- sve_guest = false;
- sve_host = false;
- vhe = has_vhe();
- }
-
- hsr_ec = kvm_vcpu_trap_get_class(vcpu);
- if (hsr_ec != ESR_ELx_EC_FP_ASIMD &&
- hsr_ec != ESR_ELx_EC_SVE)
- return false;
-
- /* Don't handle SVE traps for non-SVE vcpus here: */
- if (!sve_guest)
- if (hsr_ec != ESR_ELx_EC_FP_ASIMD)
- return false;
-
- /* Valid trap. Switch the context: */
-
- if (vhe) {
- u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;
-
- if (sve_guest)
- reg |= CPACR_EL1_ZEN;
-
- write_sysreg(reg, cpacr_el1);
- } else {
- write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
- cptr_el2);
- }
-
- isb();
-
- if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
- /*
- * In the SVE case, VHE is assumed: it is enforced by
- * Kconfig and kvm_arch_init().
- */
- if (sve_host) {
- struct thread_struct *thread = container_of(
- vcpu->arch.host_fpsimd_state,
- struct thread_struct, uw.fpsimd_state);
-
- sve_save_state(sve_pffr(thread),
- &vcpu->arch.host_fpsimd_state->fpsr);
- } else {
- __fpsimd_save_state(vcpu->arch.host_fpsimd_state);
- }
-
- vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
- }
-
- if (sve_guest) {
- sve_load_state(vcpu_sve_pffr(vcpu),
- &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr,
- sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
- write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12);
- } else {
- __fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
- }
-
- /* Skip restoring fpexc32 for AArch64 guests */
- if (!(read_sysreg(hcr_el2) & HCR_RW))
- write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
- fpexc32_el2);
-
- vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
-
- return true;
-}
-
-static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
-{
- u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
- int rt = kvm_vcpu_sys_get_rt(vcpu);
- u64 val = vcpu_get_reg(vcpu, rt);
-
- /*
- * The normal sysreg handling code expects to see the traps,
- * let's not do anything here.
- */
- if (vcpu->arch.hcr_el2 & HCR_TVM)
- return false;
-
- switch (sysreg) {
- case SYS_SCTLR_EL1:
- write_sysreg_el1(val, SYS_SCTLR);
- break;
- case SYS_TTBR0_EL1:
- write_sysreg_el1(val, SYS_TTBR0);
- break;
- case SYS_TTBR1_EL1:
- write_sysreg_el1(val, SYS_TTBR1);
- break;
- case SYS_TCR_EL1:
- write_sysreg_el1(val, SYS_TCR);
- break;
- case SYS_ESR_EL1:
- write_sysreg_el1(val, SYS_ESR);
- break;
- case SYS_FAR_EL1:
- write_sysreg_el1(val, SYS_FAR);
- break;
- case SYS_AFSR0_EL1:
- write_sysreg_el1(val, SYS_AFSR0);
- break;
- case SYS_AFSR1_EL1:
- write_sysreg_el1(val, SYS_AFSR1);
- break;
- case SYS_MAIR_EL1:
- write_sysreg_el1(val, SYS_MAIR);
- break;
- case SYS_AMAIR_EL1:
- write_sysreg_el1(val, SYS_AMAIR);
- break;
- case SYS_CONTEXTIDR_EL1:
- write_sysreg_el1(val, SYS_CONTEXTIDR);
- break;
- default:
- return false;
- }
-
- __kvm_skip_instr(vcpu);
- return true;
-}
-
-static bool __hyp_text esr_is_ptrauth_trap(u32 esr)
-{
- u32 ec = ESR_ELx_EC(esr);
-
- if (ec == ESR_ELx_EC_PAC)
- return true;
-
- if (ec != ESR_ELx_EC_SYS64)
- return false;
-
- switch (esr_sys64_to_sysreg(esr)) {
- case SYS_APIAKEYLO_EL1:
- case SYS_APIAKEYHI_EL1:
- case SYS_APIBKEYLO_EL1:
- case SYS_APIBKEYHI_EL1:
- case SYS_APDAKEYLO_EL1:
- case SYS_APDAKEYHI_EL1:
- case SYS_APDBKEYLO_EL1:
- case SYS_APDBKEYHI_EL1:
- case SYS_APGAKEYLO_EL1:
- case SYS_APGAKEYHI_EL1:
- return true;
- }
-
- return false;
-}
-
-#define __ptrauth_save_key(regs, key) \
-({ \
- regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \
- regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \
-})
-
-static bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpu_context *ctxt;
- u64 val;
-
- if (!vcpu_has_ptrauth(vcpu) ||
- !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu)))
- return false;
-
- ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
- __ptrauth_save_key(ctxt->sys_regs, APIA);
- __ptrauth_save_key(ctxt->sys_regs, APIB);
- __ptrauth_save_key(ctxt->sys_regs, APDA);
- __ptrauth_save_key(ctxt->sys_regs, APDB);
- __ptrauth_save_key(ctxt->sys_regs, APGA);
-
- vcpu_ptrauth_enable(vcpu);
-
- val = read_sysreg(hcr_el2);
- val |= (HCR_API | HCR_APK);
- write_sysreg(val, hcr_el2);
-
- return true;
-}
-
-/*
- * Return true when we were able to fixup the guest exit and should return to
- * the guest, false when we should restore the host state and return to the
- * main run loop.
- */
-static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
-{
- if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
- vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
-
- /*
- * We're using the raw exception code in order to only process
- * the trap if no SError is pending. We will come back to the
- * same PC once the SError has been injected, and replay the
- * trapping instruction.
- */
- if (*exit_code != ARM_EXCEPTION_TRAP)
- goto exit;
-
- if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
- kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
- handle_tx2_tvm(vcpu))
- return true;
-
- /*
- * We trap the first access to the FP/SIMD to save the host context
- * and restore the guest context lazily.
- * If FP/SIMD is not implemented, handle the trap and inject an
- * undefined instruction exception to the guest.
- * Similarly for trapped SVE accesses.
- */
- if (__hyp_handle_fpsimd(vcpu))
- return true;
-
- if (__hyp_handle_ptrauth(vcpu))
- return true;
-
- if (!__populate_fault_info(vcpu))
- return true;
-
- if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
- bool valid;
-
- valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
- kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
- kvm_vcpu_dabt_isvalid(vcpu) &&
- !kvm_vcpu_dabt_isextabt(vcpu) &&
- !kvm_vcpu_dabt_iss1tw(vcpu);
-
- if (valid) {
- int ret = __vgic_v2_perform_cpuif_access(vcpu);
-
- if (ret == 1)
- return true;
-
- /* Promote an illegal access to an SError.*/
- if (ret == -1)
- *exit_code = ARM_EXCEPTION_EL1_SERROR;
-
- goto exit;
- }
- }
-
- if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
- (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
- kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
- int ret = __vgic_v3_perform_cpuif_access(vcpu);
-
- if (ret == 1)
- return true;
- }
-
-exit:
- /* Return to the host kernel and handle the exit */
- return false;
-}
-
-static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
-{
- if (!cpus_have_final_cap(ARM64_SSBD))
- return false;
-
- return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
-}
-
-static void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_ARM64_SSBD
- /*
- * The host runs with the workaround always present. If the
- * guest wants it disabled, so be it...
- */
- if (__needs_ssbd_off(vcpu) &&
- __hyp_this_cpu_read(arm64_ssbd_callback_required))
- arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
-#endif
-}
-
-static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_ARM64_SSBD
- /*
- * If the guest has disabled the workaround, bring it back on.
- */
- if (__needs_ssbd_off(vcpu) &&
- __hyp_this_cpu_read(arm64_ssbd_callback_required))
- arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
-#endif
-}
-
-/**
- * Disable host events, enable guest events
- */
-static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt)
-{
- struct kvm_host_data *host;
- struct kvm_pmu_events *pmu;
-
- host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
- pmu = &host->pmu_events;
-
- if (pmu->events_host)
- write_sysreg(pmu->events_host, pmcntenclr_el0);
-
- if (pmu->events_guest)
- write_sysreg(pmu->events_guest, pmcntenset_el0);
-
- return (pmu->events_host || pmu->events_guest);
-}
-
-/**
- * Disable guest events, enable host events
- */
-static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
-{
- struct kvm_host_data *host;
- struct kvm_pmu_events *pmu;
-
- host = container_of(host_ctxt, struct kvm_host_data, host_ctxt);
- pmu = &host->pmu_events;
-
- if (pmu->events_guest)
- write_sysreg(pmu->events_guest, pmcntenclr_el0);
-
- if (pmu->events_host)
- write_sysreg(pmu->events_host, pmcntenset_el0);
-}
-
-/* Switch to the guest for VHE systems running in EL2 */
-static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpu_context *host_ctxt;
- struct kvm_cpu_context *guest_ctxt;
- u64 exit_code;
-
- host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
- host_ctxt->__hyp_running_vcpu = vcpu;
- guest_ctxt = &vcpu->arch.ctxt;
-
- sysreg_save_host_state_vhe(host_ctxt);
-
- /*
- * ARM erratum 1165522 requires us to configure both stage 1 and
- * stage 2 translation for the guest context before we clear
- * HCR_EL2.TGE.
- *
- * We have already configured the guest's stage 1 translation in
- * kvm_vcpu_load_sysregs above. We must now call __activate_vm
- * before __activate_traps, because __activate_vm configures
- * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
- * (among other things).
- */
- __activate_vm(vcpu->kvm);
- __activate_traps(vcpu);
-
- sysreg_restore_guest_state_vhe(guest_ctxt);
- __debug_switch_to_guest(vcpu);
-
- __set_guest_arch_workaround_state(vcpu);
-
- do {
- /* Jump in the fire! */
- exit_code = __guest_enter(vcpu, host_ctxt);
-
- /* And we're baaack! */
- } while (fixup_guest_exit(vcpu, &exit_code));
-
- __set_host_arch_workaround_state(vcpu);
-
- sysreg_save_guest_state_vhe(guest_ctxt);
-
- __deactivate_traps(vcpu);
-
- sysreg_restore_host_state_vhe(host_ctxt);
-
- if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
- __fpsimd_save_fpexc32(vcpu);
-
- __debug_switch_to_host(vcpu);
-
- return exit_code;
-}
-NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
-
-int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
-{
- int ret;
-
- local_daif_mask();
-
- /*
- * Having IRQs masked via PMR when entering the guest means the GIC
- * will not signal the CPU of interrupts of lower priority, and the
- * only way to get out will be via guest exceptions.
- * Naturally, we want to avoid this.
- *
- * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
- * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
- */
- pmr_sync();
-
- ret = __kvm_vcpu_run_vhe(vcpu);
-
- /*
- * local_daif_restore() takes care to properly restore PSTATE.DAIF
- * and the GIC PMR if the host is using IRQ priorities.
- */
- local_daif_restore(DAIF_PROCCTX_NOIRQ);
-
- /*
- * When we exit from the guest we change a number of CPU configuration
- * parameters, such as traps. Make sure these changes take effect
- * before running the host or additional guests.
- */
- isb();
-
- return ret;
-}
-
-/* Switch to the guest for legacy non-VHE systems */
-int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpu_context *host_ctxt;
- struct kvm_cpu_context *guest_ctxt;
- bool pmu_switch_needed;
- u64 exit_code;
-
- /*
- * Having IRQs masked via PMR when entering the guest means the GIC
- * will not signal the CPU of interrupts of lower priority, and the
- * only way to get out will be via guest exceptions.
- * Naturally, we want to avoid this.
- */
- if (system_uses_irq_prio_masking()) {
- gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
- pmr_sync();
- }
-
- vcpu = kern_hyp_va(vcpu);
-
- host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
- host_ctxt->__hyp_running_vcpu = vcpu;
- guest_ctxt = &vcpu->arch.ctxt;
-
- pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
-
- __sysreg_save_state_nvhe(host_ctxt);
-
- /*
- * We must restore the 32-bit state before the sysregs, thanks
- * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
- *
- * Also, and in order to be able to deal with erratum #1319537 (A57)
- * and #1319367 (A72), we must ensure that all VM-related sysreg are
- * restored before we enable S2 translation.
- */
- __sysreg32_restore_state(vcpu);
- __sysreg_restore_state_nvhe(guest_ctxt);
-
- __activate_vm(kern_hyp_va(vcpu->kvm));
- __activate_traps(vcpu);
-
- __hyp_vgic_restore_state(vcpu);
- __timer_enable_traps(vcpu);
-
- __debug_switch_to_guest(vcpu);
-
- __set_guest_arch_workaround_state(vcpu);
-
- do {
- /* Jump in the fire! */
- exit_code = __guest_enter(vcpu, host_ctxt);
-
- /* And we're baaack! */
- } while (fixup_guest_exit(vcpu, &exit_code));
-
- __set_host_arch_workaround_state(vcpu);
-
- __sysreg_save_state_nvhe(guest_ctxt);
- __sysreg32_save_state(vcpu);
- __timer_disable_traps(vcpu);
- __hyp_vgic_save_state(vcpu);
-
- __deactivate_traps(vcpu);
- __deactivate_vm(vcpu);
-
- __sysreg_restore_state_nvhe(host_ctxt);
-
- if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
- __fpsimd_save_fpexc32(vcpu);
-
- /*
- * This must come after restoring the host sysregs, since a non-VHE
- * system may enable SPE here and make use of the TTBRs.
- */
- __debug_switch_to_host(vcpu);
-
- if (pmu_switch_needed)
- __pmu_switch_to_host(host_ctxt);
-
- /* Returning to host will clear PSR.I, remask PMR if needed */
- if (system_uses_irq_prio_masking())
- gic_write_pmr(GIC_PRIO_IRQOFF);
-
- return exit_code;
-}
-
-static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
-
-static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
- struct kvm_cpu_context *__host_ctxt)
-{
- struct kvm_vcpu *vcpu;
- unsigned long str_va;
-
- vcpu = __host_ctxt->__hyp_running_vcpu;
-
- if (read_sysreg(vttbr_el2)) {
- __timer_disable_traps(vcpu);
- __deactivate_traps(vcpu);
- __deactivate_vm(vcpu);
- __sysreg_restore_state_nvhe(__host_ctxt);
- }
-
- /*
- * Force the panic string to be loaded from the literal pool,
- * making sure it is a kernel address and not a PC-relative
- * reference.
- */
- asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));
-
- __hyp_do_panic(str_va,
- spsr, elr,
- read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
- read_sysreg(hpfar_el2), par, vcpu);
-}
-
-static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
- struct kvm_cpu_context *host_ctxt)
-{
- struct kvm_vcpu *vcpu;
- vcpu = host_ctxt->__hyp_running_vcpu;
-
- __deactivate_traps(vcpu);
- sysreg_restore_host_state_vhe(host_ctxt);
-
- panic(__hyp_panic_string,
- spsr, elr,
- read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR),
- read_sysreg(hpfar_el2), par, vcpu);
-}
-NOKPROBE_SYMBOL(__hyp_call_panic_vhe);
-
-void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
-{
- u64 spsr = read_sysreg_el2(SYS_SPSR);
- u64 elr = read_sysreg_el2(SYS_ELR);
- u64 par = read_sysreg(par_el1);
-
- if (!has_vhe())
- __hyp_call_panic_nvhe(spsr, elr, par, host_ctxt);
- else
- __hyp_call_panic_vhe(spsr, elr, par, host_ctxt);
-
- unreachable();
-}
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 4f3a087e36d5..bd1bab551d48 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -13,7 +13,7 @@
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
-static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
+static bool __is_be(struct kvm_vcpu *vcpu)
{
if (vcpu_mode_is_32bit(vcpu))
return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT);
@@ -32,7 +32,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
* 0: Not a GICV access
* -1: Illegal GICV access successfully performed
*/
-int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
+int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = kern_hyp_va(vcpu->kvm);
struct vgic_dist *vgic = &kvm->arch.vgic;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 10ed539835c1..d31eb6266f2e 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -16,7 +16,7 @@
#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))
-static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
+static u64 __gic_v3_get_lr(unsigned int lr)
{
switch (lr & 0xf) {
case 0:
@@ -56,7 +56,7 @@ static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
unreachable();
}
-static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
+static void __gic_v3_set_lr(u64 val, int lr)
{
switch (lr & 0xf) {
case 0:
@@ -110,7 +110,7 @@ static void __hyp_text __gic_v3_set_lr(u64 val, int lr)
}
}
-static void __hyp_text __vgic_v3_write_ap0rn(u32 val, int n)
+static void __vgic_v3_write_ap0rn(u32 val, int n)
{
switch (n) {
case 0:
@@ -128,7 +128,7 @@ static void __hyp_text __vgic_v3_write_ap0rn(u32 val, int n)
}
}
-static void __hyp_text __vgic_v3_write_ap1rn(u32 val, int n)
+static void __vgic_v3_write_ap1rn(u32 val, int n)
{
switch (n) {
case 0:
@@ -146,7 +146,7 @@ static void __hyp_text __vgic_v3_write_ap1rn(u32 val, int n)
}
}
-static u32 __hyp_text __vgic_v3_read_ap0rn(int n)
+static u32 __vgic_v3_read_ap0rn(int n)
{
u32 val;
@@ -170,7 +170,7 @@ static u32 __hyp_text __vgic_v3_read_ap0rn(int n)
return val;
}
-static u32 __hyp_text __vgic_v3_read_ap1rn(int n)
+static u32 __vgic_v3_read_ap1rn(int n)
{
u32 val;
@@ -194,7 +194,7 @@ static u32 __hyp_text __vgic_v3_read_ap1rn(int n)
return val;
}
-void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
{
u64 used_lrs = cpu_if->used_lrs;
@@ -229,7 +229,7 @@ void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if)
}
}
-void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
{
u64 used_lrs = cpu_if->used_lrs;
int i;
@@ -255,7 +255,7 @@ void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if)
}
}
-void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
{
/*
* VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a
@@ -302,7 +302,7 @@ void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
}
-void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
{
u64 val;
@@ -328,7 +328,7 @@ void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
write_gicreg(0, ICH_HCR_EL2);
}
-void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
{
u64 val;
u32 nr_pre_bits;
@@ -361,7 +361,7 @@ void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if)
}
}
-void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
+void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
{
u64 val;
u32 nr_pre_bits;
@@ -394,7 +394,7 @@ void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if)
}
}
-void __hyp_text __vgic_v3_init_lrs(void)
+void __vgic_v3_init_lrs(void)
{
int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2));
int i;
@@ -403,28 +403,28 @@ void __hyp_text __vgic_v3_init_lrs(void)
__gic_v3_set_lr(0, i);
}
-u64 __hyp_text __vgic_v3_get_ich_vtr_el2(void)
+u64 __vgic_v3_get_ich_vtr_el2(void)
{
return read_gicreg(ICH_VTR_EL2);
}
-u64 __hyp_text __vgic_v3_read_vmcr(void)
+u64 __vgic_v3_read_vmcr(void)
{
return read_gicreg(ICH_VMCR_EL2);
}
-void __hyp_text __vgic_v3_write_vmcr(u32 vmcr)
+void __vgic_v3_write_vmcr(u32 vmcr)
{
write_gicreg(vmcr, ICH_VMCR_EL2);
}
-static int __hyp_text __vgic_v3_bpr_min(void)
+static int __vgic_v3_bpr_min(void)
{
/* See Pseudocode for VPriorityGroup */
return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2));
}
-static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu)
+static int __vgic_v3_get_group(struct kvm_vcpu *vcpu)
{
u32 esr = kvm_vcpu_get_hsr(vcpu);
u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
@@ -434,9 +434,8 @@ static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu)
#define GICv3_IDLE_PRIORITY 0xff
-static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu,
- u32 vmcr,
- u64 *lr_val)
+static int __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, u32 vmcr,
+ u64 *lr_val)
{
unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
u8 priority = GICv3_IDLE_PRIORITY;
@@ -474,8 +473,8 @@ static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu,
return lr;
}
-static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu,
- int intid, u64 *lr_val)
+static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid,
+ u64 *lr_val)
{
unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs;
int i;
@@ -494,7 +493,7 @@ static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu,
return -1;
}
-static int __hyp_text __vgic_v3_get_highest_active_priority(void)
+static int __vgic_v3_get_highest_active_priority(void)
{
u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
u32 hap = 0;
@@ -526,12 +525,12 @@ static int __hyp_text __vgic_v3_get_highest_active_priority(void)
return GICv3_IDLE_PRIORITY;
}
-static unsigned int __hyp_text __vgic_v3_get_bpr0(u32 vmcr)
+static unsigned int __vgic_v3_get_bpr0(u32 vmcr)
{
return (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
}
-static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr)
+static unsigned int __vgic_v3_get_bpr1(u32 vmcr)
{
unsigned int bpr;
@@ -550,7 +549,7 @@ static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr)
* Convert a priority to a preemption level, taking the relevant BPR
* into account by zeroing the sub-priority bits.
*/
-static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
+static u8 __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
{
unsigned int bpr;
@@ -568,7 +567,7 @@ static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp)
* matter what the guest does with its BPR, we can always set/get the
* same value of a priority.
*/
-static void __hyp_text __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
+static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
{
u8 pre, ap;
u32 val;
@@ -587,7 +586,7 @@ static void __hyp_text __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp)
}
}
-static int __hyp_text __vgic_v3_clear_highest_active_priority(void)
+static int __vgic_v3_clear_highest_active_priority(void)
{
u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2));
u32 hap = 0;
@@ -625,7 +624,7 @@ static int __hyp_text __vgic_v3_clear_highest_active_priority(void)
return GICv3_IDLE_PRIORITY;
}
-static void __hyp_text __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 lr_val;
u8 lr_prio, pmr;
@@ -661,7 +660,7 @@ spurious:
vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS);
}
-static void __hyp_text __vgic_v3_clear_active_lr(int lr, u64 lr_val)
+static void __vgic_v3_clear_active_lr(int lr, u64 lr_val)
{
lr_val &= ~ICH_LR_ACTIVE_BIT;
if (lr_val & ICH_LR_HW) {
@@ -674,7 +673,7 @@ static void __hyp_text __vgic_v3_clear_active_lr(int lr, u64 lr_val)
__gic_v3_set_lr(lr_val, lr);
}
-static void __hyp_text __vgic_v3_bump_eoicount(void)
+static void __vgic_v3_bump_eoicount(void)
{
u32 hcr;
@@ -683,8 +682,7 @@ static void __hyp_text __vgic_v3_bump_eoicount(void)
write_gicreg(hcr, ICH_HCR_EL2);
}
-static void __hyp_text __vgic_v3_write_dir(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 vid = vcpu_get_reg(vcpu, rt);
u64 lr_val;
@@ -707,7 +705,7 @@ static void __hyp_text __vgic_v3_write_dir(struct kvm_vcpu *vcpu,
__vgic_v3_clear_active_lr(lr, lr_val);
}
-static void __hyp_text __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 vid = vcpu_get_reg(vcpu, rt);
u64 lr_val;
@@ -744,17 +742,17 @@ static void __hyp_text __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int
__vgic_v3_clear_active_lr(lr, lr_val);
}
-static void __hyp_text __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG0_MASK));
}
-static void __hyp_text __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG1_MASK));
}
-static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 val = vcpu_get_reg(vcpu, rt);
@@ -766,7 +764,7 @@ static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr,
__vgic_v3_write_vmcr(vmcr);
}
-static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 val = vcpu_get_reg(vcpu, rt);
@@ -778,17 +776,17 @@ static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr,
__vgic_v3_write_vmcr(vmcr);
}
-static void __hyp_text __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr));
}
-static void __hyp_text __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr));
}
-static void __hyp_text __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 val = vcpu_get_reg(vcpu, rt);
u8 bpr_min = __vgic_v3_bpr_min() - 1;
@@ -805,7 +803,7 @@ static void __hyp_text __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int
__vgic_v3_write_vmcr(vmcr);
}
-static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
+static void __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 val = vcpu_get_reg(vcpu, rt);
u8 bpr_min = __vgic_v3_bpr_min();
@@ -825,7 +823,7 @@ static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int
__vgic_v3_write_vmcr(vmcr);
}
-static void __hyp_text __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
+static void __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
{
u32 val;
@@ -837,7 +835,7 @@ static void __hyp_text __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n
vcpu_set_reg(vcpu, rt, val);
}
-static void __hyp_text __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
+static void __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n)
{
u32 val = vcpu_get_reg(vcpu, rt);
@@ -847,56 +845,49 @@ static void __hyp_text __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int
__vgic_v3_write_ap1rn(val, n);
}
-static void __hyp_text __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu,
+static void __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu,
u32 vmcr, int rt)
{
__vgic_v3_read_apxrn(vcpu, rt, 0);
}
-static void __hyp_text __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu,
+static void __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu,
u32 vmcr, int rt)
{
__vgic_v3_read_apxrn(vcpu, rt, 1);
}
-static void __hyp_text __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_read_apxrn(vcpu, rt, 2);
}
-static void __hyp_text __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_read_apxrn(vcpu, rt, 3);
}
-static void __hyp_text __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_write_apxrn(vcpu, rt, 0);
}
-static void __hyp_text __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_write_apxrn(vcpu, rt, 1);
}
-static void __hyp_text __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_write_apxrn(vcpu, rt, 2);
}
-static void __hyp_text __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
__vgic_v3_write_apxrn(vcpu, rt, 3);
}
-static void __hyp_text __vgic_v3_read_hppir(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u64 lr_val;
int lr, lr_grp, grp;
@@ -915,16 +906,14 @@ spurious:
vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK);
}
-static void __hyp_text __vgic_v3_read_pmr(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
vmcr &= ICH_VMCR_PMR_MASK;
vmcr >>= ICH_VMCR_PMR_SHIFT;
vcpu_set_reg(vcpu, rt, vmcr);
}
-static void __hyp_text __vgic_v3_write_pmr(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 val = vcpu_get_reg(vcpu, rt);
@@ -936,15 +925,13 @@ static void __hyp_text __vgic_v3_write_pmr(struct kvm_vcpu *vcpu,
write_gicreg(vmcr, ICH_VMCR_EL2);
}
-static void __hyp_text __vgic_v3_read_rpr(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 val = __vgic_v3_get_highest_active_priority();
vcpu_set_reg(vcpu, rt, val);
}
-static void __hyp_text __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 vtr, val;
@@ -965,8 +952,7 @@ static void __hyp_text __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu,
vcpu_set_reg(vcpu, rt, val);
}
-static void __hyp_text __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu,
- u32 vmcr, int rt)
+static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
{
u32 val = vcpu_get_reg(vcpu, rt);
@@ -983,7 +969,7 @@ static void __hyp_text __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu,
write_gicreg(vmcr, ICH_VMCR_EL2);
}
-int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
+int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
{
int rt;
u32 esr;
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
new file mode 100644
index 000000000000..461e97c375cc
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part
+#
+
+asflags-y := -D__KVM_VHE_HYPERVISOR__
+ccflags-y := -D__KVM_VHE_HYPERVISOR__
+
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
+obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
+ ../fpsimd.o ../hyp-entry.o
diff --git a/arch/arm64/kvm/hyp/vhe/debug-sr.c b/arch/arm64/kvm/hyp/vhe/debug-sr.c
new file mode 100644
index 000000000000..f1e2e5a00933
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/debug-sr.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/debug-sr.h>
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_hyp.h>
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+ __debug_switch_to_guest_common(vcpu);
+}
+
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
+ __debug_switch_to_host_common(vcpu);
+}
+
+u32 __kvm_get_mdcr_el2(void)
+{
+ return read_sysreg(mdcr_el2);
+}
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
new file mode 100644
index 000000000000..c0d33deba77e
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/switch.h>
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
+
+static void __activate_traps(struct kvm_vcpu *vcpu)
+{
+ u64 val;
+
+ ___activate_traps(vcpu);
+
+ val = read_sysreg(cpacr_el1);
+ val |= CPACR_EL1_TTA;
+ val &= ~CPACR_EL1_ZEN;
+
+ /*
+ * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+ * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+ * except for some missing controls, such as TAM.
+ * In this case, CPTR_EL2.TAM has the same position with or without
+ * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+ * shift value for trapping the AMU accesses.
+ */
+
+ val |= CPTR_EL2_TAM;
+
+ if (update_fp_enabled(vcpu)) {
+ if (vcpu_has_sve(vcpu))
+ val |= CPACR_EL1_ZEN;
+ } else {
+ val &= ~CPACR_EL1_FPEN;
+ __activate_traps_fpsimd32(vcpu);
+ }
+
+ write_sysreg(val, cpacr_el1);
+
+ write_sysreg(kvm_get_hyp_vector(), vbar_el1);
+}
+NOKPROBE_SYMBOL(__activate_traps);
+
+static void __deactivate_traps(struct kvm_vcpu *vcpu)
+{
+ extern char vectors[]; /* kernel exception vectors */
+
+ ___deactivate_traps(vcpu);
+
+ write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+
+ /*
+ * ARM errata 1165522 and 1530923 require the actual execution of the
+ * above before we can switch to the EL2/EL0 translation regime used by
+ * the host.
+ */
+ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
+
+ write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
+ write_sysreg(vectors, vbar_el1);
+}
+NOKPROBE_SYMBOL(__deactivate_traps);
+
+void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
+{
+ __activate_traps_common(vcpu);
+}
+
+void deactivate_traps_vhe_put(void)
+{
+ u64 mdcr_el2 = read_sysreg(mdcr_el2);
+
+ mdcr_el2 &= MDCR_EL2_HPMN_MASK |
+ MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
+ MDCR_EL2_TPMS;
+
+ write_sysreg(mdcr_el2, mdcr_el2);
+
+ __deactivate_traps_common();
+}
+
+/* Switch to the guest for VHE systems running in EL2 */
+static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpu_context *host_ctxt;
+ struct kvm_cpu_context *guest_ctxt;
+ u64 exit_code;
+
+ host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+ host_ctxt->__hyp_running_vcpu = vcpu;
+ guest_ctxt = &vcpu->arch.ctxt;
+
+ sysreg_save_host_state_vhe(host_ctxt);
+
+ /*
+ * ARM erratum 1165522 requires us to configure both stage 1 and
+ * stage 2 translation for the guest context before we clear
+ * HCR_EL2.TGE.
+ *
+ * We have already configured the guest's stage 1 translation in
+ * kvm_vcpu_load_sysregs_vhe above. We must now call __activate_vm
+ * before __activate_traps, because __activate_vm configures
+ * stage 2 translation, and __activate_traps clear HCR_EL2.TGE
+ * (among other things).
+ */
+ __activate_vm(vcpu->kvm);
+ __activate_traps(vcpu);
+
+ sysreg_restore_guest_state_vhe(guest_ctxt);
+ __debug_switch_to_guest(vcpu);
+
+ __set_guest_arch_workaround_state(vcpu);
+
+ do {
+ /* Jump in the fire! */
+ exit_code = __guest_enter(vcpu, host_ctxt);
+
+ /* And we're baaack! */
+ } while (fixup_guest_exit(vcpu, &exit_code));
+
+ __set_host_arch_workaround_state(vcpu);
+
+ sysreg_save_guest_state_vhe(guest_ctxt);
+
+ __deactivate_traps(vcpu);
+
+ sysreg_restore_host_state_vhe(host_ctxt);
+
+ if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
+ __fpsimd_save_fpexc32(vcpu);
+
+ __debug_switch_to_host(vcpu);
+
+ return exit_code;
+}
+NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
+
+int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
+{
+ int ret;
+
+ local_daif_mask();
+
+ /*
+ * Having IRQs masked via PMR when entering the guest means the GIC
+ * will not signal the CPU of interrupts of lower priority, and the
+ * only way to get out will be via guest exceptions.
+ * Naturally, we want to avoid this.
+ *
+ * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a
+ * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU.
+ */
+ pmr_sync();
+
+ ret = __kvm_vcpu_run_vhe(vcpu);
+
+ /*
+ * local_daif_restore() takes care to properly restore PSTATE.DAIF
+ * and the GIC PMR if the host is using IRQ priorities.
+ */
+ local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
+ /*
+ * When we exit from the guest we change a number of CPU configuration
+ * parameters, such as traps. Make sure these changes take effect
+ * before running the host or additional guests.
+ */
+ isb();
+
+ return ret;
+}
+
+static void __hyp_call_panic(u64 spsr, u64 elr, u64 par,
+ struct kvm_cpu_context *host_ctxt)
+{
+ struct kvm_vcpu *vcpu;
+ vcpu = host_ctxt->__hyp_running_vcpu;
+
+ __deactivate_traps(vcpu);
+ sysreg_restore_host_state_vhe(host_ctxt);
+
+ panic(__hyp_panic_string,
+ spsr, elr,
+ read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR),
+ read_sysreg(hpfar_el2), par, vcpu);
+}
+NOKPROBE_SYMBOL(__hyp_call_panic);
+
+void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
+{
+ u64 spsr = read_sysreg_el2(SYS_SPSR);
+ u64 elr = read_sysreg_el2(SYS_ELR);
+ u64 par = read_sysreg(par_el1);
+
+ __hyp_call_panic(spsr, elr, par, host_ctxt);
+ unreachable();
+}
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
new file mode 100644
index 000000000000..996471e4c138
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <hyp/sysreg-sr.h>
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+/*
+ * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
+ * pstate, which are handled as part of the el2 return state) on every
+ * switch (sp_el0 is being dealt with in the assembly code).
+ * tpidr_el0 and tpidrro_el0 only need to be switched when going
+ * to host userspace or a different VCPU. EL1 registers only need to be
+ * switched when potentially going to run a different VCPU. The latter two
+ * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put.
+ */
+
+void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt)
+{
+ __sysreg_save_common_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_save_host_state_vhe);
+
+void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt)
+{
+ __sysreg_save_common_state(ctxt);
+ __sysreg_save_el2_return_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe);
+
+void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt)
+{
+ __sysreg_restore_common_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe);
+
+void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt)
+{
+ __sysreg_restore_common_state(ctxt);
+ __sysreg_restore_el2_return_state(ctxt);
+}
+NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe);
+
+/**
+ * kvm_vcpu_load_sysregs_vhe - Load guest system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Load system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2. This function is called from KVM's vcpu_load() function
+ * and loading system register state early avoids having to load them on
+ * every entry to the VM.
+ */
+void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+ struct kvm_cpu_context *host_ctxt;
+
+ host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+ __sysreg_save_user_state(host_ctxt);
+
+ /*
+ * Load guest EL1 and user state
+ *
+ * We must restore the 32-bit state before the sysregs, thanks
+ * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
+ */
+ __sysreg32_restore_state(vcpu);
+ __sysreg_restore_user_state(guest_ctxt);
+ __sysreg_restore_el1_state(guest_ctxt);
+
+ vcpu->arch.sysregs_loaded_on_cpu = true;
+
+ activate_traps_vhe_load(vcpu);
+}
+
+/**
+ * kvm_vcpu_put_sysregs_vhe - Restore host system registers to the physical CPU
+ *
+ * @vcpu: The VCPU pointer
+ *
+ * Save guest system registers that do not affect the host's execution, for
+ * example EL1 system registers on a VHE system where the host kernel
+ * runs at EL2. This function is called from KVM's vcpu_put() function
+ * and deferring saving system register state until we're no longer running the
+ * VCPU avoids having to save them on every exit from the VM.
+ */
+void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
+ struct kvm_cpu_context *host_ctxt;
+
+ host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+ deactivate_traps_vhe_put();
+
+ __sysreg_save_el1_state(guest_ctxt);
+ __sysreg_save_user_state(guest_ctxt);
+ __sysreg32_save_state(vcpu);
+
+ /* Restore host user state */
+ __sysreg_restore_user_state(host_ctxt);
+
+ vcpu->arch.sysregs_loaded_on_cpu = false;
+}
diff --git a/arch/arm64/kvm/hyp/vhe/timer-sr.c b/arch/arm64/kvm/hyp/vhe/timer-sr.c
new file mode 100644
index 000000000000..4cda674a8be6
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/timer-sr.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <asm/kvm_hyp.h>
+
+void __kvm_timer_set_cntvoff(u64 cntvoff)
+{
+ write_sysreg(cntvoff, cntvoff_el2);
+}
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
new file mode 100644
index 000000000000..b275101e9c9c
--- /dev/null
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#include <linux/irqflags.h>
+
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/tlbflush.h>
+
+struct tlb_inv_context {
+ unsigned long flags;
+ u64 tcr;
+ u64 sctlr;
+};
+
+static void __tlb_switch_to_guest(struct kvm *kvm, struct tlb_inv_context *cxt)
+{
+ u64 val;
+
+ local_irq_save(cxt->flags);
+
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+ /*
+ * For CPUs that are affected by ARM errata 1165522 or 1530923,
+ * we cannot trust stage-1 to be in a correct state at that
+ * point. Since we do not want to force a full load of the
+ * vcpu state, we prevent the EL1 page-table walker to
+ * allocate new TLBs. This is done by setting the EPD bits
+ * in the TCR_EL1 register. We also need to prevent it to
+ * allocate IPA->PA walks, so we enable the S1 MMU...
+ */
+ val = cxt->tcr = read_sysreg_el1(SYS_TCR);
+ val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
+ write_sysreg_el1(val, SYS_TCR);
+ val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR);
+ val |= SCTLR_ELx_M;
+ write_sysreg_el1(val, SYS_SCTLR);
+ }
+
+ /*
+ * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
+ * most TLB operations target EL2/EL0. In order to affect the
+ * guest TLBs (EL1/EL0), we need to change one of these two
+ * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
+ * let's flip TGE before executing the TLB operation.
+ *
+ * ARM erratum 1165522 requires some special handling (again),
+ * as we need to make sure both stages of translation are in
+ * place before clearing TGE. __load_guest_stage2() already
+ * has an ISB in order to deal with this.
+ */
+ __load_guest_stage2(kvm);
+ val = read_sysreg(hcr_el2);
+ val &= ~HCR_TGE;
+ write_sysreg(val, hcr_el2);
+ isb();
+}
+
+static void __tlb_switch_to_host(struct kvm *kvm, struct tlb_inv_context *cxt)
+{
+ /*
+ * We're done with the TLB operation, let's restore the host's
+ * view of HCR_EL2.
+ */
+ write_sysreg(0, vttbr_el2);
+ write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+ isb();
+
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
+ /* Restore the registers to what they were */
+ write_sysreg_el1(cxt->tcr, SYS_TCR);
+ write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
+ }
+
+ local_irq_restore(cxt->flags);
+}
+
+void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
+{
+ struct tlb_inv_context cxt;
+
+ dsb(ishst);
+
+ /* Switch to requested VMID */
+ __tlb_switch_to_guest(kvm, &cxt);
+
+ /*
+ * We could do so much better if we had the VA as well.
+ * Instead, we invalidate Stage-2 for this IPA, and the
+ * whole of Stage-1. Weep...
+ */
+ ipa >>= 12;
+ __tlbi(ipas2e1is, ipa);
+
+ /*
+ * We have to ensure completion of the invalidation at Stage-2,
+ * since a table walk on another CPU could refill a TLB with a
+ * complete (S1 + S2) walk based on the old Stage-2 mapping if
+ * the Stage-1 invalidation happened first.
+ */
+ dsb(ish);
+ __tlbi(vmalle1is);
+ dsb(ish);
+ isb();
+
+ __tlb_switch_to_host(kvm, &cxt);
+}
+
+void __kvm_tlb_flush_vmid(struct kvm *kvm)
+{
+ struct tlb_inv_context cxt;
+
+ dsb(ishst);
+
+ /* Switch to requested VMID */
+ __tlb_switch_to_guest(kvm, &cxt);
+
+ __tlbi(vmalls12e1is);
+ dsb(ish);
+ isb();
+
+ __tlb_switch_to_host(kvm, &cxt);
+}
+
+void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct tlb_inv_context cxt;
+
+ /* Switch to requested VMID */
+ __tlb_switch_to_guest(kvm, &cxt);
+
+ __tlbi(vmalle1);
+ dsb(nsh);
+ isb();
+
+ __tlb_switch_to_host(kvm, &cxt);
+}
+
+void __kvm_flush_vm_context(void)
+{
+ dsb(ishst);
+ __tlbi(alle1is);
+
+ /*
+ * VIPT and PIPT caches are not affected by VMID, so no maintenance
+ * is necessary across a VMID rollover.
+ *
+ * VPIPT caches constrain lookup and maintenance to the active VMID,
+ * so we need to invalidate lines with a stale VMID to avoid an ABA
+ * race after multiple rollovers.
+ *
+ */
+ if (icache_is_vpipt())
+ asm volatile("ic ialluis");
+
+ dsb(ish);
+}
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 6dc3078649fa..0096cd965332 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -109,6 +109,7 @@ static bool is_ignored_symbol(const char *name, char type)
".LASANPC", /* s390 kasan local symbols */
"__crc_", /* modversions */
"__efistub_", /* arm64 EFI stub namespace */
+ "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */
NULL
};