Commit 08b3f08a authored by Nicholas Piggin's avatar Nicholas Piggin Committed by Michael Ellerman
Browse files

KVM: PPC: Book3S HV P9: Move nested guest entry into its own function 



Move the part of the guest entry which is specific to nested HV into its
own function. This is just refactoring.

Signed-off-by: default avatarNicholas Piggin <npiggin@gmail.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211123095231.1036501-31-npiggin@gmail.com
parent aabcaf6a

arch/powerpc/kvm/book3s_hv.c

+67 −58
Original line number Diff line number Diff line
@@ -3822,6 +3822,72 @@ static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu) 
	}

}



/* call our hypervisor to load up HV regs and go */

static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb)

{

	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	unsigned long host_psscr;

	struct hv_guest_state hvregs;

	int trap;

	s64 dec;



	/*

	 * We need to save and restore the guest visible part of the

	 * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor

	 * doesn't do this for us. Note only required if pseries since

	 * this is done in kvmhv_vcpu_entry_p9() below otherwise.

	 */

	host_psscr = mfspr(SPRN_PSSCR_PR);

	mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr);

	kvmhv_save_hv_regs(vcpu, &hvregs);

	hvregs.lpcr = lpcr;

	vcpu->arch.regs.msr = vcpu->arch.shregs.msr;

	hvregs.version = HV_GUEST_STATE_VERSION;

	if (vcpu->arch.nested) {

		hvregs.lpid = vcpu->arch.nested->shadow_lpid;

		hvregs.vcpu_token = vcpu->arch.nested_vcpu_id;

	} else {

		hvregs.lpid = vcpu->kvm->arch.lpid;

		hvregs.vcpu_token = vcpu->vcpu_id;

	}

	hvregs.hdec_expiry = time_limit;



	/*

	 * When setting DEC, we must always deal with irq_work_raise

	 * via NMI vs setting DEC. The problem occurs right as we

	 * switch into guest mode if a NMI hits and sets pending work

	 * and sets DEC, then that will apply to the guest and not

	 * bring us back to the host.

	 *

	 * irq_work_raise could check a flag (or possibly LPCR[HDICE]

	 * for example) and set HDEC to 1? That wouldn't solve the

	 * nested hv case which needs to abort the hcall or zero the

	 * time limit.

	 *

	 * XXX: Another day's problem.

	 */

	mtspr(SPRN_DEC, kvmppc_dec_expires_host_tb(vcpu) - *tb);



	mtspr(SPRN_DAR, vcpu->arch.shregs.dar);

	mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);

	trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs),

				  __pa(&vcpu->arch.regs));

	kvmhv_restore_hv_return_state(vcpu, &hvregs);

	vcpu->arch.shregs.msr = vcpu->arch.regs.msr;

	vcpu->arch.shregs.dar = mfspr(SPRN_DAR);

	vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);

	vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR);

	mtspr(SPRN_PSSCR_PR, host_psscr);



	dec = mfspr(SPRN_DEC);

	if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */

		dec = (s32) dec;

	*tb = mftb();

	vcpu->arch.dec_expires = dec + (*tb + vc->tb_offset);



	return trap;

}



/*

 * Guest entry for POWER9 and later CPUs.

 */
@@ -3830,7 +3896,6 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, 
{

	struct kvmppc_vcore *vc = vcpu->arch.vcore;

	struct p9_host_os_sprs host_os_sprs;

	s64 dec;

	u64 next_timer;

	unsigned long msr;

	int trap;
@@ -3883,63 +3948,7 @@ static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit, 
	switch_pmu_to_guest(vcpu, &host_os_sprs);



	if (kvmhv_on_pseries()) {

		/*

		 * We need to save and restore the guest visible part of the

		 * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor

		 * doesn't do this for us. Note only required if pseries since

		 * this is done in kvmhv_vcpu_entry_p9() below otherwise.

		 */

		unsigned long host_psscr;

		/* call our hypervisor to load up HV regs and go */

		struct hv_guest_state hvregs;



		host_psscr = mfspr(SPRN_PSSCR_PR);

		mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr);

		kvmhv_save_hv_regs(vcpu, &hvregs);

		hvregs.lpcr = lpcr;

		vcpu->arch.regs.msr = vcpu->arch.shregs.msr;

		hvregs.version = HV_GUEST_STATE_VERSION;

		if (vcpu->arch.nested) {

			hvregs.lpid = vcpu->arch.nested->shadow_lpid;

			hvregs.vcpu_token = vcpu->arch.nested_vcpu_id;

		} else {

			hvregs.lpid = vcpu->kvm->arch.lpid;

			hvregs.vcpu_token = vcpu->vcpu_id;

		}

		hvregs.hdec_expiry = time_limit;



		/*

		 * When setting DEC, we must always deal with irq_work_raise

		 * via NMI vs setting DEC. The problem occurs right as we

		 * switch into guest mode if a NMI hits and sets pending work

		 * and sets DEC, then that will apply to the guest and not

		 * bring us back to the host.

		 *

		 * irq_work_raise could check a flag (or possibly LPCR[HDICE]

		 * for example) and set HDEC to 1? That wouldn't solve the

		 * nested hv case which needs to abort the hcall or zero the

		 * time limit.

		 *

		 * XXX: Another day's problem.

		 */

		mtspr(SPRN_DEC, kvmppc_dec_expires_host_tb(vcpu) - *tb);



		mtspr(SPRN_DAR, vcpu->arch.shregs.dar);

		mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);

		trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs),

					  __pa(&vcpu->arch.regs));

		kvmhv_restore_hv_return_state(vcpu, &hvregs);

		vcpu->arch.shregs.msr = vcpu->arch.regs.msr;

		vcpu->arch.shregs.dar = mfspr(SPRN_DAR);

		vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);

		vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR);

		mtspr(SPRN_PSSCR_PR, host_psscr);



		dec = mfspr(SPRN_DEC);

		if (!(lpcr & LPCR_LD)) /* Sign extend if not using large decrementer */

			dec = (s32) dec;

		*tb = mftb();

		vcpu->arch.dec_expires = dec + (*tb + vc->tb_offset);

		trap = kvmhv_vcpu_entry_p9_nested(vcpu, time_limit, lpcr, tb);



		/* H_CEDE has to be handled now, not later */

		if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&