[PATCH 0/4] KVM: arm64: nv: Add CPTR_EL2 handling

[PATCH 0/4] KVM: arm64: nv: Add CPTR_EL2 handling

[Marc Zyngier]

Building on top of Oliver's NV+SVE series[1], I've put together a
small set of patches handling CPTR_EL2, as the two are pretty closely
related.

This series adds:

- the description on the CPTR_EL2-driven traps in the exception
  routing tables

- the merging of the L1 guest's CPTR_EL2 traps with the host's

- the handling of L1's CPTR_EL2 access via the CPACR_EL1 accessor as a
  trap so that we can emulate writing to the TCPAC/TTA bits

Overall, this is pretty straightforward (for NV, that is...).

[1] https://lore.kernel.org/r/20240531231358.1000039-1-oliver.upton@linux.dev

Marc Zyngier (4):
  KVM: arm64: nv: Add TCPAC/TTA to CPTR->CPACR conversion helper
  KVM: arm64: nv: Add trap description for CPTR_EL2
  KVM: arm64: nv: Add additional trap setup for CPTR_EL2
  KVM: arm64: nv: Handle CPACR_EL1 traps

 arch/arm64/include/asm/kvm_emulate.h |  2 +-
 arch/arm64/include/asm/kvm_nested.h  |  4 +-
 arch/arm64/kvm/emulate-nested.c      | 91 ++++++++++++++++++++++++++++
 arch/arm64/kvm/hyp/vhe/switch.c      | 55 ++++++++++++++++-
 4 files changed, 148 insertions(+), 4 deletions(-)

-- 
2.39.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 1/4] KVM: arm64: nv: Add TCPAC/TTA to CPTR->CPACR conversion helper

[Marc Zyngier]

We are missing the propagation of CPTR_EL2.{TCPAC,TTA} into
the CPACR format. Make sure we preserve these bits.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 5d55f76254c3..07cf6c64f0d0 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -32,7 +32,7 @@ static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr)
 
 static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
 {
-	u64 cpacr_el1 = 0;
+	u64 cpacr_el1 = CPACR_ELx_RES1;
 
 	if (cptr_el2 & CPTR_EL2_TTA)
 		cpacr_el1 |= CPACR_ELx_TTA;
@@ -41,6 +41,8 @@ static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2)
 	if (!(cptr_el2 & CPTR_EL2_TZ))
 		cpacr_el1 |= CPACR_ELx_ZEN;
 
+	cpacr_el1 |= cptr_el2 & (CPTR_EL2_TCPAC | CPTR_EL2_TAM);
+
 	return cpacr_el1;
 }
 
-- 
2.39.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 2/4] KVM: arm64: nv: Add trap description for CPTR_EL2

[Marc Zyngier]

Add trap description for CPTR_EL2.{TCPAC,TAM,E0POE,TTA}.

TTA is a bit annoying as it changes location depending on E2H.
This forces us to add yet another "complex" trap condition.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/emulate-nested.c | 91 +++++++++++++++++++++++++++++++++
 1 file changed, 91 insertions(+)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 72d733c74a38..61e6b97c3e25 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -79,6 +79,10 @@ enum cgt_group_id {
 	CGT_MDCR_E2TB,
 	CGT_MDCR_TDCC,
 
+	CGT_CPACR_E0POE,
+	CGT_CPTR_TAM,
+	CGT_CPTR_TCPAC,
+
 	/*
 	 * Anything after this point is a combination of coarse trap
 	 * controls, which must all be evaluated to decide what to do.
@@ -106,6 +110,8 @@ enum cgt_group_id {
 	CGT_CNTHCTL_EL1PCTEN = __COMPLEX_CONDITIONS__,
 	CGT_CNTHCTL_EL1PTEN,
 
+	CGT_CPTR_TTA,
+
 	/* Must be last */
 	__NR_CGT_GROUP_IDS__
 };
@@ -345,6 +351,24 @@ static const struct trap_bits coarse_trap_bits[] = {
 		.mask		= MDCR_EL2_TDCC,
 		.behaviour	= BEHAVE_FORWARD_ANY,
 	},
+	[CGT_CPACR_E0POE] = {
+		.index		= CPTR_EL2,
+		.value		= CPACR_ELx_E0POE,
+		.mask		= CPACR_ELx_E0POE,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_CPTR_TAM] = {
+		.index		= CPTR_EL2,
+		.value		= CPTR_EL2_TAM,
+		.mask		= CPTR_EL2_TAM,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_CPTR_TCPAC] = {
+		.index		= CPTR_EL2,
+		.value		= CPTR_EL2_TCPAC,
+		.mask		= CPTR_EL2_TCPAC,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
 };
 
 #define MCB(id, ...)						\
@@ -410,12 +434,26 @@ static enum trap_behaviour check_cnthctl_el1pten(struct kvm_vcpu *vcpu)
 	return BEHAVE_FORWARD_ANY;
 }
 
+static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu)
+{
+	u64 val = __vcpu_sys_reg(vcpu, CPTR_EL2);
+
+	if (!vcpu_el2_e2h_is_set(vcpu))
+		val = translate_cptr_el2_to_cpacr_el1(val);
+
+	if (val & CPACR_ELx_TTA)
+		return BEHAVE_FORWARD_ANY;
+
+	return BEHAVE_HANDLE_LOCALLY;
+}
+
 #define CCC(id, fn)				\
 	[id - __COMPLEX_CONDITIONS__] = fn
 
 static const complex_condition_check ccc[] = {
 	CCC(CGT_CNTHCTL_EL1PCTEN, check_cnthctl_el1pcten),
 	CCC(CGT_CNTHCTL_EL1PTEN, check_cnthctl_el1pten),
+	CCC(CGT_CPTR_TTA, check_cptr_tta),
 };
 
 /*
@@ -1000,6 +1038,59 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_TRBPTR_EL1, 	CGT_MDCR_E2TB),
 	SR_TRAP(SYS_TRBSR_EL1, 		CGT_MDCR_E2TB),
 	SR_TRAP(SYS_TRBTRG_EL1,		CGT_MDCR_E2TB),
+	SR_TRAP(SYS_CPACR_EL1,		CGT_CPTR_TCPAC),
+	SR_TRAP(SYS_AMUSERENR_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCFGR_EL0,		CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCGCR_EL0,		CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENCLR0_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENCLR1_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENSET0_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCNTENSET1_EL0,	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMCR_EL0,		CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR0_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(4),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(5),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(6),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(7),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(8),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(9),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(10),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(11),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(12),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(13),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(14),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVCNTR1_EL0(15),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER0_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(0),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(1),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(2),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(3),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(4),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(5),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(6),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(7),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(8),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(9),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(10),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(11),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(12),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(13),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(14),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_AMEVTYPER1_EL0(15),	CGT_CPTR_TAM),
+	SR_TRAP(SYS_POR_EL0,		CGT_CPACR_E0POE),
+	/* op0=2, op1=1, and CRn<0b1000 */
+	SR_RANGE_TRAP(sys_reg(2, 1, 0, 0, 0),
+		      sys_reg(2, 1, 7, 15, 7), CGT_CPTR_TTA),
 	SR_TRAP(SYS_CNTP_TVAL_EL0,	CGT_CNTHCTL_EL1PTEN),
 	SR_TRAP(SYS_CNTP_CVAL_EL0,	CGT_CNTHCTL_EL1PTEN),
 	SR_TRAP(SYS_CNTP_CTL_EL0,	CGT_CNTHCTL_EL1PTEN),
-- 
2.39.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 3/4] KVM: arm64: nv: Add additional trap setup for CPTR_EL2

[Marc Zyngier]

We need to teach KVM a couple of new tricks. CPTR_EL2 and its
VHE accessor CPACR_EL1 need to be handled specially:

- CPACR_EL1 is trapped on VHE so that we can track the TCPAC
  and TTA bits

- CPTR_EL2.{TCPAC,E0POE} are propagated from L1 to L2

As a consequence of CPTR_EL2 being always trapped, we update
vcpu_sanitised_cptr_el2() so that it doesn't try to read from
the CPU registers, but from the shadow copy (ensuring that we
always have up-to-date TCPAC and TTA bits).

This helper will also be used when handling the CPTR_EL1 trap.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h |  2 +-
 arch/arm64/kvm/hyp/vhe/switch.c      | 23 ++++++++++++++++++++++-
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index e86de04ba1c4..cc5c93b46e6f 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -607,7 +607,7 @@ static __always_inline void kvm_reset_cptr_el2(struct kvm_vcpu *vcpu)
  */
 static inline u64 vcpu_sanitised_cptr_el2(const struct kvm_vcpu *vcpu)
 {
-	u64 cptr = vcpu_read_sys_reg(vcpu, CPTR_EL2);
+	u64 cptr = __vcpu_sys_reg(vcpu, CPTR_EL2);
 
 	if (!vcpu_el2_e2h_is_set(vcpu))
 		cptr = translate_cptr_el2_to_cpacr_el1(cptr);
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index d07b4f4be5e5..b4ba236526d6 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -67,6 +67,8 @@ static u64 __compute_hcr(struct kvm_vcpu *vcpu)
 
 static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
 {
+	u64 cptr;
+
 	/*
 	 * 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,
@@ -85,11 +87,23 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
 		__activate_traps_fpsimd32(vcpu);
 	}
 
+	if (!vcpu_has_nv(vcpu))
+		goto write;
+
+	/*
+	 * The architecture is a bit crap (what a surprise): an EL2 guest
+	 * writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA,
+	 * as they are RES0 in the guest's view. To work around it, trap the
+	 * sucker using the very same bit it can't set...
+	 */
+	if (vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu))
+		val |= CPTR_EL2_TCPAC;
+
 	/*
 	 * Layer the guest hypervisor's trap configuration on top of our own if
 	 * we're in a nested context.
 	 */
-	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
+	if (is_hyp_ctxt(vcpu))
 		goto write;
 
 	if (guest_hyp_fpsimd_traps_enabled(vcpu))
@@ -97,6 +111,13 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
 	if (guest_hyp_sve_traps_enabled(vcpu))
 		val &= ~CPACR_ELx_ZEN;
 
+	cptr = vcpu_sanitised_cptr_el2(vcpu);
+
+	if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
+		val |= cptr & CPACR_ELx_E0POE;
+
+	val |= cptr & CPTR_EL2_TCPAC;
+
 write:
 	write_sysreg(val, cpacr_el1);
 }
-- 
2.39.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH 4/4] KVM: arm64: nv: Handle CPACR_EL1 traps

[Marc Zyngier]

Handle CPACR_EL1 accesses when running a VHE guest. In order to
limit the cost of the emulation, implement it ass a shallow exit.

In the other cases:

- this is a nVHE L1 which will write to memory, and we don't trap

- this is a L2 guest:

  * the L1 has CPTR_EL2.TCPAC==0, and the L2 has direct register
   access

  * the L1 has CPTR_EL2.TCPAC==1, and the L2 will trap, but the
    handling is defered to the general handling for forwarding

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/vhe/switch.c | 32 +++++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index b4ba236526d6..c1711f2b92b8 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -295,10 +295,40 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return true;
 }
 
+static bool kvm_hyp_handle_cpacr_el1(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	int rt;
+
+	if (!is_hyp_ctxt(vcpu) || esr_sys64_to_sysreg(esr) != SYS_CPACR_EL1)
+		return false;
+
+	rt = kvm_vcpu_sys_get_rt(vcpu);
+
+	if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ) {
+		vcpu_set_reg(vcpu, rt, __vcpu_sys_reg(vcpu, CPTR_EL2));
+	} else {
+		vcpu_write_sys_reg(vcpu, vcpu_get_reg(vcpu, rt), CPTR_EL2);
+		__activate_cptr_traps(vcpu);
+	}
+
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
+static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (kvm_hyp_handle_cpacr_el1(vcpu, exit_code))
+		return true;
+
+	return kvm_hyp_handle_sysreg(vcpu, exit_code);
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
-	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg,
+	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg_vhe,
 	[ESR_ELx_EC_SVE]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
-- 
2.39.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH 0/4] KVM: arm64: nv: Add CPTR_EL2 handling

[Oliver Upton]

On Tue, Jun 04, 2024 at 02:05:49PM +0100, Marc Zyngier wrote:
> Building on top of Oliver's NV+SVE series[1], I've put together a
> small set of patches handling CPTR_EL2, as the two are pretty closely
> related.

Thanks for posting this, overall looks good. I'll probably pick this up
and repost a combined series that eliminates some of the incidental
churn that I've forced upon your patches.

-- 
Best,
Oliver

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel