Commit 77ee70a0 authored by Oliver Upton's avatar Oliver Upton
Browse files

KVM: arm64: nv: Honor SError exception routing / masking 



To date KVM has used HCR_EL2.VSE to track the state of a pending SError
for the guest. With this bit set, hardware respects the EL1 exception
routing / masking rules and injects the vSError when appropriate.

This isn't correct for NV guests as hardware is oblivious to vEL2's
intentions for SErrors. Better yet, with FEAT_NV2 the guest can change
the routing behind our back as HCR_EL2 is redirected to memory. Cope
with this mess by:

 - Using a flag (instead of HCR_EL2.VSE) to track the pending SError
   state when SErrors are unconditionally masked for the current context

 - Resampling the routing / masking of a pending SError on every guest
   entry/exit

 - Emulating exception entry when SError routing implies a translation
   regime change

Reviewed-by: default avatarMarc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250708172532.1699409-7-oliver.upton@linux.dev


Signed-off-by: default avatarOliver Upton <oliver.upton@linux.dev>
parent 9aba641b

arch/arm64/include/asm/kvm_emulate.h

+19 −1
Original line number Diff line number Diff line
@@ -45,7 +45,7 @@ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu); 
void kvm_skip_instr32(struct kvm_vcpu *vcpu);



void kvm_inject_undefined(struct kvm_vcpu *vcpu);

void kvm_inject_vabt(struct kvm_vcpu *vcpu);

int kvm_inject_serror_esr(struct kvm_vcpu *vcpu, u64 esr);

int kvm_inject_sea(struct kvm_vcpu *vcpu, bool iabt, u64 addr);

void kvm_inject_size_fault(struct kvm_vcpu *vcpu);
@@ -59,12 +59,25 @@ static inline int kvm_inject_sea_iabt(struct kvm_vcpu *vcpu, u64 addr) 
	return kvm_inject_sea(vcpu, true, addr);

}



static inline int kvm_inject_serror(struct kvm_vcpu *vcpu)

{

	/*

	 * ESR_ELx.ISV (later renamed to IDS) indicates whether or not

	 * ESR_ELx.ISS contains IMPLEMENTATION DEFINED syndrome information.

	 *

	 * Set the bit when injecting an SError w/o an ESR to indicate ISS

	 * does not follow the architected format.

	 */

	return kvm_inject_serror_esr(vcpu, ESR_ELx_ISV);

}



void kvm_vcpu_wfi(struct kvm_vcpu *vcpu);



void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);

int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);

int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);

int kvm_inject_nested_sea(struct kvm_vcpu *vcpu, bool iabt, u64 addr);

int kvm_inject_nested_serror(struct kvm_vcpu *vcpu, u64 esr);



static inline void kvm_inject_nested_sve_trap(struct kvm_vcpu *vcpu)

{
@@ -205,6 +218,11 @@ static inline bool vcpu_el2_tge_is_set(const struct kvm_vcpu *vcpu) 
	return ctxt_sys_reg(&vcpu->arch.ctxt, HCR_EL2) & HCR_TGE;

}



static inline bool vcpu_el2_amo_is_set(const struct kvm_vcpu *vcpu)

{

	return ctxt_sys_reg(&vcpu->arch.ctxt, HCR_EL2) & HCR_AMO;

}



static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)

{

	bool e2h, tge;

arch/arm64/include/asm/kvm_host.h

+15 −3
Original line number Diff line number Diff line
@@ -817,7 +817,7 @@ struct kvm_vcpu_arch { 
	u8 iflags;



	/* State flags for kernel bookkeeping, unused by the hypervisor code */

	u8 sflags;

	u16 sflags;



	/*

	 * Don't run the guest (internal implementation need).
@@ -953,9 +953,21 @@ struct kvm_vcpu_arch { 
		__vcpu_flags_preempt_enable();			\

	} while (0)



#define __vcpu_test_and_clear_flag(v, flagset, f, m)		\

	({							\

		typeof(v->arch.flagset) set;			\

								\

		set = __vcpu_get_flag(v, flagset, f, m);	\

		__vcpu_clear_flag(v, flagset, f, m);		\

								\

		set;						\

	})



#define vcpu_get_flag(v, ...)	__vcpu_get_flag((v), __VA_ARGS__)

#define vcpu_set_flag(v, ...)	__vcpu_set_flag((v), __VA_ARGS__)

#define vcpu_clear_flag(v, ...)	__vcpu_clear_flag((v), __VA_ARGS__)

#define vcpu_test_and_clear_flag(v, ...)			\

	__vcpu_test_and_clear_flag((v), __VA_ARGS__)



/* KVM_ARM_VCPU_INIT completed */

#define VCPU_INITIALIZED	__vcpu_single_flag(cflags, BIT(0))
@@ -1015,6 +1027,8 @@ struct kvm_vcpu_arch { 
#define IN_WFI			__vcpu_single_flag(sflags, BIT(6))

/* KVM is currently emulating a nested ERET */

#define IN_NESTED_ERET		__vcpu_single_flag(sflags, BIT(7))

/* SError pending for nested guest */

#define NESTED_SERROR_PENDING	__vcpu_single_flag(sflags, BIT(8))





/* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -1387,8 +1401,6 @@ static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) 
	return (vcpu_arch->steal.base != INVALID_GPA);

}



void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);



struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);



DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data);

arch/arm64/include/asm/kvm_nested.h

+2 −0
Original line number Diff line number Diff line
@@ -80,6 +80,8 @@ extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu); 
extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);



extern void check_nested_vcpu_requests(struct kvm_vcpu *vcpu);

extern void kvm_nested_flush_hwstate(struct kvm_vcpu *vcpu);

extern void kvm_nested_sync_hwstate(struct kvm_vcpu *vcpu);



struct kvm_s2_trans {

	phys_addr_t output;

arch/arm64/kvm/arm.c

+4 −0
Original line number Diff line number Diff line
@@ -1188,6 +1188,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) 
		 */

		preempt_disable();



		kvm_nested_flush_hwstate(vcpu);



		if (kvm_vcpu_has_pmu(vcpu))

			kvm_pmu_flush_hwstate(vcpu);
@@ -1287,6 +1289,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) 
		/* Exit types that need handling before we can be preempted */

		handle_exit_early(vcpu, ret);



		kvm_nested_sync_hwstate(vcpu);



		preempt_enable();



		/*

arch/arm64/kvm/emulate-nested.c

+14 −0
Original line number Diff line number Diff line
@@ -2714,6 +2714,9 @@ static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2, 
	case except_type_irq:

		kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_IRQ);

		break;

	case except_type_serror:

		kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SERR);

		break;

	default:

		WARN_ONCE(1, "Unsupported EL2 exception injection %d\n", type);

	}
@@ -2821,3 +2824,14 @@ int kvm_inject_nested_sea(struct kvm_vcpu *vcpu, bool iabt, u64 addr) 
	vcpu_write_sys_reg(vcpu, FAR_EL2, addr);

	return kvm_inject_nested_sync(vcpu, esr);

}



int kvm_inject_nested_serror(struct kvm_vcpu *vcpu, u64 esr)

{

	/*

	 * Hardware sets up the EC field when propagating ESR as a result of

	 * vSError injection. Manually populate EC for an emulated SError

	 * exception.

	 */

	esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SERROR);

	return kvm_inject_nested(vcpu, esr, except_type_serror);

}