diff mbox series

[v11,13/43] KVM: arm64: nv: Save/Restore vEL2 sysregs

Message ID 20231120131027.854038-14-maz@kernel.org (mailing list archive)
State New, archived
Headers show
Series KVM: arm64: Nested Virtualization support (FEAT_NV2 only) | expand

Commit Message

Marc Zyngier Nov. 20, 2023, 1:09 p.m. UTC 
Whenever we need to restore the guest's system registers to the CPU, we
now need to take care of the EL2 system registers as well. Most of them
are accessed via traps only, but some have an immediate effect and also
a guest running in VHE mode would expect them to be accessible via their
EL1 encoding, which we do not trap.

For vEL2 we write the virtual EL2 registers with an identical format directly
into their EL1 counterpart, and translate the few registers that have a
different format for the same effect on the execution when running a
non-VHE guest guest hypervisor.

Based on an initial patch from Andre Przywara, rewritten many times
since.

Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h |   5 +-
 arch/arm64/kvm/hyp/nvhe/sysreg-sr.c        |   2 +-
 arch/arm64/kvm/hyp/vhe/sysreg-sr.c         | 133 ++++++++++++++++++++-
 3 files changed, 135 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index bb6b571ec627..3472eb6628e6 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -97,9 +97,10 @@  static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0),	tpidrro_el0);
 }
 
-static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt,
+					      u64 mpidr)
 {
-	write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1),	vmpidr_el2);
+	write_sysreg(mpidr,				vmpidr_el2);
 
 	if (has_vhe() ||
 	    !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
index 29305022bc04..dba101565de3 100644
--- a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -28,7 +28,7 @@  void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)
 
 void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
 {
-	__sysreg_restore_el1_state(ctxt);
+	__sysreg_restore_el1_state(ctxt, ctxt_sys_reg(ctxt, MPIDR_EL1));
 	__sysreg_restore_common_state(ctxt);
 	__sysreg_restore_user_state(ctxt);
 	__sysreg_restore_el2_return_state(ctxt);
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index 8e1e0d5033b6..d33f64cd0745 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -15,6 +15,104 @@ 
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_nested.h>
 
+static void __sysreg_save_vel2_state(struct kvm_cpu_context *ctxt)
+{
+	/* These registers are common with EL1 */
+	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg(par_el1);
+	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
+
+	ctxt_sys_reg(ctxt, ESR_EL2)	= read_sysreg_el1(SYS_ESR);
+	ctxt_sys_reg(ctxt, AFSR0_EL2)	= read_sysreg_el1(SYS_AFSR0);
+	ctxt_sys_reg(ctxt, AFSR1_EL2)	= read_sysreg_el1(SYS_AFSR1);
+	ctxt_sys_reg(ctxt, FAR_EL2)	= read_sysreg_el1(SYS_FAR);
+	ctxt_sys_reg(ctxt, MAIR_EL2)	= read_sysreg_el1(SYS_MAIR);
+	ctxt_sys_reg(ctxt, VBAR_EL2)	= read_sysreg_el1(SYS_VBAR);
+	ctxt_sys_reg(ctxt, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR);
+	ctxt_sys_reg(ctxt, AMAIR_EL2)	= read_sysreg_el1(SYS_AMAIR);
+
+	/*
+	 * In VHE mode those registers are compatible between EL1 and EL2,
+	 * and the guest uses the _EL1 versions on the CPU naturally.
+	 * So we save them into their _EL2 versions here.
+	 * For nVHE mode we trap accesses to those registers, so our
+	 * _EL2 copy in sys_regs[] is always up-to-date and we don't need
+	 * to save anything here.
+	 */
+	if (__vcpu_el2_e2h_is_set(ctxt)) {
+		u64 val;
+
+		ctxt_sys_reg(ctxt, SCTLR_EL2)	= read_sysreg_el1(SYS_SCTLR);
+		ctxt_sys_reg(ctxt, CPTR_EL2)	= read_sysreg_el1(SYS_CPACR);
+		ctxt_sys_reg(ctxt, TTBR0_EL2)	= read_sysreg_el1(SYS_TTBR0);
+		ctxt_sys_reg(ctxt, TTBR1_EL2)	= read_sysreg_el1(SYS_TTBR1);
+		ctxt_sys_reg(ctxt, TCR_EL2)	= read_sysreg_el1(SYS_TCR);
+
+		/*
+		 * The EL1 view of CNTKCTL_EL1 has a bunch of RES0 bits where
+		 * the interesting CNTHCTL_EL2 bits live. So preserve these
+		 * bits when reading back the guest-visible value.
+		 */
+		val = read_sysreg_el1(SYS_CNTKCTL);
+		val &= CNTKCTL_VALID_BITS;
+		ctxt_sys_reg(ctxt, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS;
+		ctxt_sys_reg(ctxt, CNTHCTL_EL2) |= val;
+	}
+
+	ctxt_sys_reg(ctxt, SP_EL2)	= read_sysreg(sp_el1);
+	ctxt_sys_reg(ctxt, ELR_EL2)	= read_sysreg_el1(SYS_ELR);
+	ctxt_sys_reg(ctxt, SPSR_EL2)	= read_sysreg_el1(SYS_SPSR);
+}
+
+static void __sysreg_restore_vel2_state(struct kvm_cpu_context *ctxt)
+{
+	u64 val;
+
+	/* These registers are common with EL1 */
+	write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1),	par_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1),	tpidr_el1);
+
+	write_sysreg(read_cpuid_id(),			vpidr_el2);
+	write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1),	vmpidr_el2);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, MAIR_EL2),	SYS_MAIR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, VBAR_EL2),	SYS_VBAR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL2),SYS_CONTEXTIDR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL2),	SYS_AMAIR);
+
+	if (__vcpu_el2_e2h_is_set(ctxt)) {
+		/*
+		 * In VHE mode those registers are compatible between
+		 * EL1 and EL2.
+		 */
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL2),	SYS_SCTLR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, CPTR_EL2),	SYS_CPACR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL2),	SYS_TTBR0);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL2),	SYS_TTBR1);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL2),	SYS_TCR);
+		write_sysreg_el1(ctxt_sys_reg(ctxt, CNTHCTL_EL2), SYS_CNTKCTL);
+	} else {
+		/*
+		 * CNTHCTL_EL2 only affects EL1 when running nVHE, so
+		 * no need to restore it.
+		 */
+		val = translate_sctlr_el2_to_sctlr_el1(ctxt_sys_reg(ctxt, SCTLR_EL2));
+		write_sysreg_el1(val, SYS_SCTLR);
+		val = translate_cptr_el2_to_cpacr_el1(ctxt_sys_reg(ctxt, CPTR_EL2));
+		write_sysreg_el1(val, SYS_CPACR);
+		val = translate_ttbr0_el2_to_ttbr0_el1(ctxt_sys_reg(ctxt, TTBR0_EL2));
+		write_sysreg_el1(val, SYS_TTBR0);
+		val = translate_tcr_el2_to_tcr_el1(ctxt_sys_reg(ctxt, TCR_EL2));
+		write_sysreg_el1(val, SYS_TCR);
+	}
+
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL2),	SYS_ESR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL2),	SYS_AFSR0);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR1_EL2),	SYS_AFSR1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, FAR_EL2),	SYS_FAR);
+	write_sysreg(ctxt_sys_reg(ctxt, SP_EL2),	sp_el1);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL2),	SYS_ELR);
+	write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL2),	SYS_SPSR);
+}
+
 /*
  * 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
@@ -66,6 +164,7 @@  void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
+	u64 mpidr;
 
 	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 	__sysreg_save_user_state(host_ctxt);
@@ -89,7 +188,29 @@  void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 	 */
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_user_state(guest_ctxt);
-	__sysreg_restore_el1_state(guest_ctxt);
+
+	if (unlikely(__is_hyp_ctxt(guest_ctxt))) {
+		__sysreg_restore_vel2_state(guest_ctxt);
+	} else {
+		if (vcpu_has_nv(vcpu)) {
+			/*
+			 * Only set VPIDR_EL2 for nested VMs, as this is the
+			 * only time it changes. We'll restore the MIDR_EL1
+			 * view on put.
+			 */
+			write_sysreg(ctxt_sys_reg(guest_ctxt, VPIDR_EL2), vpidr_el2);
+
+			/*
+			 * As we're restoring a nested guest, set the value
+			 * provided by the guest hypervisor.
+			 */
+			mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2);
+		} else {
+			mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1);
+		}
+
+		__sysreg_restore_el1_state(guest_ctxt, mpidr);
+	}
 
 	vcpu_set_flag(vcpu, SYSREGS_ON_CPU);
 }
@@ -112,12 +233,20 @@  void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu)
 
 	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
 
-	__sysreg_save_el1_state(guest_ctxt);
+	if (unlikely(__is_hyp_ctxt(guest_ctxt)))
+		__sysreg_save_vel2_state(guest_ctxt);
+	else
+		__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);
 
+	/* If leaving a nesting guest, restore MPIDR_EL1 default view */
+	if (vcpu_has_nv(vcpu))
+		write_sysreg(read_cpuid_id(),	vpidr_el2);
+
 	vcpu_clear_flag(vcpu, SYSREGS_ON_CPU);
 }