From d41571c7097a21a5e188b401a3976b563be3fbe4 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Oct 2024 15:53:09 +0100 Subject: [PATCH 01/16] arm64: Drop SKL0/SKL1 from TCR2_EL2 Despite what the documentation says, TCR2_EL2.{SKL0,SKL1} do not exist, and the corresponding information is in the respective TTBRx_EL2. This is a leftover from a development version of the architecture. This change makes TCR2_EL2 similar to TCR2_EL1 in that respect. Reviewed-by: Joey Gouly Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20241023145345.1613824-2-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/tools/sysreg | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 8d637ac4b7c6..ee3adec6a7c8 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -2819,8 +2819,7 @@ Field 13 AMEC1 Field 12 AMEC0 Field 11 HAFT Field 10 PTTWI -Field 9:8 SKL1 -Field 7:6 SKL0 +Res0 9:6 Field 5 D128 Field 4 AIE Field 3 POE -- 2.51.0 From 5792349d0cce03fa37243a3bbcca78d2338d1f53 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Oct 2024 15:53:10 +0100 Subject: [PATCH 02/16] arm64: Remove VNCR definition for PIRE0_EL2 As of the ARM ARM Known Issues document 102105_K.a_04_en, D22677 fixes a problem with the PIRE0_EL2 register, resulting in its removal from the VNCR page (it had no purpose being there the first place). Follow the architecture update by removing this offset. Reviewed-by: Joey Gouly Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20241023145345.1613824-3-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/include/asm/vncr_mapping.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h index 06f8ec0906a6..4f9bbd4d6c26 100644 --- a/arch/arm64/include/asm/vncr_mapping.h +++ b/arch/arm64/include/asm/vncr_mapping.h @@ -50,7 +50,6 @@ #define VNCR_VBAR_EL1 0x250 #define VNCR_TCR2_EL1 0x270 #define VNCR_PIRE0_EL1 0x290 -#define VNCR_PIRE0_EL2 0x298 #define VNCR_PIR_EL1 0x2A0 #define VNCR_POR_EL1 0x2A8 #define VNCR_ICH_LR0_EL2 0x400 -- 2.51.0 From 4ecda4c67961234e634295334fe69aea574c8e61 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Oct 2024 15:53:11 +0100 Subject: [PATCH 03/16] arm64: Add encoding for PIRE0_EL2 PIRE0_EL2 is the equivalent of PIRE0_EL1 for the EL2&0 translation regime, and it is sorely missing from the sysreg file. Add the sucker. Reviewed-by: Joey Gouly Signed-off-by: Marc Zyngier Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20241023145345.1613824-4-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/tools/sysreg | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index ee3adec6a7c8..3c812fd28eca 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -2882,6 +2882,10 @@ Sysreg PIRE0_EL12 3 5 10 2 2 Fields PIRx_ELx EndSysreg +Sysreg PIRE0_EL2 3 4 10 2 2 +Fields PIRx_ELx +EndSysreg + Sysreg PIR_EL1 3 0 10 2 3 Fields PIRx_ELx EndSysreg -- 2.51.0 From a5c870d0939b7a878edacb70831b8b32cbfed593 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Oct 2024 15:53:12 +0100 Subject: [PATCH 04/16] KVM: arm64: Drop useless struct s2_mmu in __kvm_at_s1e2() __kvm_at_s1e2() contains the definition of an s2_mmu for the current context, but doesn't make any use of it. Drop it. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20241023145345.1613824-5-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/kvm/at.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 39f0e87a340e..f04677127fbc 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -992,12 +992,9 @@ void __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr) * switching context behind everybody's back, disable interrupts... */ scoped_guard(write_lock_irqsave, &vcpu->kvm->mmu_lock) { - struct kvm_s2_mmu *mmu; u64 val, hcr; bool fail; - mmu = &vcpu->kvm->arch.mmu; - val = hcr = read_sysreg(hcr_el2); val &= ~HCR_TGE; val |= HCR_VM; -- 2.51.0 From dfeb91686992f5a973d09b66ddedf458de1acf08 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Oct 2024 15:53:13 +0100 Subject: [PATCH 05/16] KVM: arm64: nv: Add missing EL2->EL1 mappings in get_el2_to_el1_mapping() As KVM has grown a bunch of new system register for NV, it appears that we are missing them in the get_el2_to_el1_mapping() list. Most of them are not crucial as they don't tend to be accessed via vcpu_read_sys_reg() and vcpu_write_sys_reg(). Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20241023145345.1613824-6-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/kvm/sys_regs.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index ff8c4e1b847e..ae0ecd8ae671 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -110,6 +110,14 @@ static bool get_el2_to_el1_mapping(unsigned int reg, PURE_EL2_SYSREG( RVBAR_EL2 ); PURE_EL2_SYSREG( TPIDR_EL2 ); PURE_EL2_SYSREG( HPFAR_EL2 ); + PURE_EL2_SYSREG( HCRX_EL2 ); + PURE_EL2_SYSREG( HFGRTR_EL2 ); + PURE_EL2_SYSREG( HFGWTR_EL2 ); + PURE_EL2_SYSREG( HFGITR_EL2 ); + PURE_EL2_SYSREG( HDFGRTR_EL2 ); + PURE_EL2_SYSREG( HDFGWTR_EL2 ); + PURE_EL2_SYSREG( HAFGRTR_EL2 ); + PURE_EL2_SYSREG( CNTVOFF_EL2 ); PURE_EL2_SYSREG( CNTHCTL_EL2 ); MAPPED_EL2_SYSREG(SCTLR_EL2, SCTLR_EL1, translate_sctlr_el2_to_sctlr_el1 ); @@ -130,6 +138,7 @@ static bool get_el2_to_el1_mapping(unsigned int reg, MAPPED_EL2_SYSREG(ELR_EL2, ELR_EL1, NULL ); MAPPED_EL2_SYSREG(SPSR_EL2, SPSR_EL1, NULL ); MAPPED_EL2_SYSREG(ZCR_EL2, ZCR_EL1, NULL ); + MAPPED_EL2_SYSREG(CONTEXTIDR_EL2, CONTEXTIDR_EL1, NULL ); default: return false; } -- 2.51.0 From 164b5e20cdf6038f1b38867d2f6252ec6f10c356 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Oct 2024 15:53:14 +0100 Subject: [PATCH 06/16] KVM: arm64: nv: Handle CNTHCTL_EL2 specially Accessing CNTHCTL_EL2 is fraught with danger if running with HCR_EL2.E2H=1: half of the bits are held in CNTKCTL_EL1, and thus can be changed behind our back, while the rest lives in the CNTHCTL_EL2 shadow copy that is memory-based. Yes, this is a lot of fun! Make sure that we merge the two on read access, while we can write to CNTKCTL_EL1 in a more straightforward manner. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20241023145345.1613824-7-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/kvm/sys_regs.c | 28 ++++++++++++++++++++++++++++ include/kvm/arm_arch_timer.h | 3 +++ 2 files changed, 31 insertions(+) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index ae0ecd8ae671..9fb2847f5abc 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -157,6 +157,21 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) if (!is_hyp_ctxt(vcpu)) goto memory_read; + /* + * CNTHCTL_EL2 requires some special treatment to + * account for the bits that can be set via CNTKCTL_EL1. + */ + switch (reg) { + case CNTHCTL_EL2: + if (vcpu_el2_e2h_is_set(vcpu)) { + val = read_sysreg_el1(SYS_CNTKCTL); + val &= CNTKCTL_VALID_BITS; + val |= __vcpu_sys_reg(vcpu, reg) & ~CNTKCTL_VALID_BITS; + return val; + } + break; + } + /* * If this register does not have an EL1 counterpart, * then read the stored EL2 version. @@ -207,6 +222,19 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) */ __vcpu_sys_reg(vcpu, reg) = val; + switch (reg) { + case CNTHCTL_EL2: + /* + * If E2H=0, CNHTCTL_EL2 is a pure shadow register. + * Otherwise, some of the bits are backed by + * CNTKCTL_EL1, while the rest is kept in memory. + * Yes, this is fun stuff. + */ + if (vcpu_el2_e2h_is_set(vcpu)) + write_sysreg_el1(val, SYS_CNTKCTL); + return; + } + /* No EL1 counterpart? We're done here.? */ if (reg == el1r) return; diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index c819c5d16613..fd650a8789b9 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -147,6 +147,9 @@ u64 timer_get_cval(struct arch_timer_context *ctxt); void kvm_timer_cpu_up(void); void kvm_timer_cpu_down(void); +/* CNTKCTL_EL1 valid bits as of DDI0487J.a */ +#define CNTKCTL_VALID_BITS (BIT(17) | GENMASK_ULL(9, 0)) + static inline bool has_cntpoff(void) { return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); -- 2.51.0 From b9527b38c66730061c245e353dab42ef7dda33c6 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Oct 2024 15:53:15 +0100 Subject: [PATCH 07/16] KVM: arm64: nv: Save/Restore vEL2 sysregs 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 Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20241023145345.1613824-8-maz@kernel.org Signed-off-by: Oliver Upton --- 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 | 136 ++++++++++++++++++++- 3 files changed, 138 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index 1579a3c08a36..d67628d01bf5 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -152,9 +152,10 @@ 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 e12bd7d6d2dc..922aac39b021 100644 --- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c @@ -15,6 +15,107 @@ #include #include +static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu) +{ + /* These registers are common with EL1 */ + __vcpu_sys_reg(vcpu, PAR_EL1) = read_sysreg(par_el1); + __vcpu_sys_reg(vcpu, TPIDR_EL1) = read_sysreg(tpidr_el1); + + __vcpu_sys_reg(vcpu, ESR_EL2) = read_sysreg_el1(SYS_ESR); + __vcpu_sys_reg(vcpu, AFSR0_EL2) = read_sysreg_el1(SYS_AFSR0); + __vcpu_sys_reg(vcpu, AFSR1_EL2) = read_sysreg_el1(SYS_AFSR1); + __vcpu_sys_reg(vcpu, FAR_EL2) = read_sysreg_el1(SYS_FAR); + __vcpu_sys_reg(vcpu, MAIR_EL2) = read_sysreg_el1(SYS_MAIR); + __vcpu_sys_reg(vcpu, VBAR_EL2) = read_sysreg_el1(SYS_VBAR); + __vcpu_sys_reg(vcpu, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR); + __vcpu_sys_reg(vcpu, 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(vcpu)) { + u64 val; + + /* + * We don't save CPTR_EL2, as accesses to CPACR_EL1 + * are always trapped, ensuring that the in-memory + * copy is always up-to-date. A small blessing... + */ + __vcpu_sys_reg(vcpu, SCTLR_EL2) = read_sysreg_el1(SYS_SCTLR); + __vcpu_sys_reg(vcpu, TTBR0_EL2) = read_sysreg_el1(SYS_TTBR0); + __vcpu_sys_reg(vcpu, TTBR1_EL2) = read_sysreg_el1(SYS_TTBR1); + __vcpu_sys_reg(vcpu, 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; + __vcpu_sys_reg(vcpu, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS; + __vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val; + } + + __vcpu_sys_reg(vcpu, SP_EL2) = read_sysreg(sp_el1); + __vcpu_sys_reg(vcpu, ELR_EL2) = read_sysreg_el1(SYS_ELR); + __vcpu_sys_reg(vcpu, SPSR_EL2) = read_sysreg_el1(SYS_SPSR); +} + +static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu) +{ + u64 val; + + /* These registers are common with EL1 */ + write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1), par_el1); + write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1), tpidr_el1); + + write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1), vmpidr_el2); + write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2), SYS_MAIR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2), SYS_VBAR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2), SYS_CONTEXTIDR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2), SYS_AMAIR); + + if (vcpu_el2_e2h_is_set(vcpu)) { + /* + * In VHE mode those registers are compatible between + * EL1 and EL2. + */ + write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2), SYS_SCTLR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, CPTR_EL2), SYS_CPACR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2), SYS_TTBR0); + write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR1_EL2), SYS_TTBR1); + write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR_EL2), SYS_TCR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, 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(__vcpu_sys_reg(vcpu, SCTLR_EL2)); + write_sysreg_el1(val, SYS_SCTLR); + val = translate_cptr_el2_to_cpacr_el1(__vcpu_sys_reg(vcpu, CPTR_EL2)); + write_sysreg_el1(val, SYS_CPACR); + val = translate_ttbr0_el2_to_ttbr0_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2)); + write_sysreg_el1(val, SYS_TTBR0); + val = translate_tcr_el2_to_tcr_el1(__vcpu_sys_reg(vcpu, TCR_EL2)); + write_sysreg_el1(val, SYS_TCR); + } + + write_sysreg_el1(__vcpu_sys_reg(vcpu, ESR_EL2), SYS_ESR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR0_EL2), SYS_AFSR0); + write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR1_EL2), SYS_AFSR1); + write_sysreg_el1(__vcpu_sys_reg(vcpu, FAR_EL2), SYS_FAR); + write_sysreg(__vcpu_sys_reg(vcpu, SP_EL2), sp_el1); + write_sysreg_el1(__vcpu_sys_reg(vcpu, ELR_EL2), SYS_ELR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, 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 +167,7 @@ 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 = host_data_ptr(host_ctxt); __sysreg_save_user_state(host_ctxt); @@ -89,7 +191,29 @@ 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(vcpu); + } else { + if (vcpu_has_nv(vcpu)) { + /* + * Use the guest hypervisor's VPIDR_EL2 when in a + * nested state. The hardware value of MIDR_EL1 gets + * restored 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 +236,20 @@ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) host_ctxt = host_data_ptr(host_ctxt); - __sysreg_save_el1_state(guest_ctxt); + if (unlikely(__is_hyp_ctxt(guest_ctxt))) + __sysreg_save_vel2_state(vcpu); + 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 MIDR_EL1 default view */ + if (vcpu_has_nv(vcpu)) + write_sysreg(read_cpuid_id(), vpidr_el2); + vcpu_clear_flag(vcpu, SYSREGS_ON_CPU); } -- 2.51.0 From 14ca930d828b6bd0538a0c7e101b52319ae7ad35 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Oct 2024 15:53:16 +0100 Subject: [PATCH 08/16] KVM: arm64: Correctly access TCR2_EL1, PIR_EL1, PIRE0_EL1 with VHE For code that accesses any of the guest registers for emulation purposes, it is crucial to know where the most up-to-date data is. While this is pretty clear for nVHE (memory is the sole repository), things are a lot muddier for VHE, as depending on the SYSREGS_ON_CPU flag, registers can either be loaded on the HW or be in memory. Even worse with NV, where the loaded state is by definition partial. For these reasons, KVM offers the vcpu_read_sys_reg() and vcpu_write_sys_reg() primitives that always do the right thing. However, these primitive must know what register to access, and this is the role of the __vcpu_read_sys_reg_from_cpu() and __vcpu_write_sys_reg_to_cpu() helpers. As it turns out, TCR2_EL1, PIR_EL1, PIRE0_EL1 and not described in the latter helpers, meaning that the AT code cannot use them to emulate S1PIE. Add the three registers to the (long) list. Fixes: 86f9de9db178 ("KVM: arm64: Save/restore PIE registers") Signed-off-by: Marc Zyngier Cc: Joey Gouly Reviewed-by: Joey Gouly Link: https://lore.kernel.org/r/20241023145345.1613824-9-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index bf64fed9820e..b89f19b4195d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1037,6 +1037,9 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val) case TTBR0_EL1: *val = read_sysreg_s(SYS_TTBR0_EL12); break; case TTBR1_EL1: *val = read_sysreg_s(SYS_TTBR1_EL12); break; case TCR_EL1: *val = read_sysreg_s(SYS_TCR_EL12); break; + case TCR2_EL1: *val = read_sysreg_s(SYS_TCR2_EL12); break; + case PIR_EL1: *val = read_sysreg_s(SYS_PIR_EL12); break; + case PIRE0_EL1: *val = read_sysreg_s(SYS_PIRE0_EL12); break; case ESR_EL1: *val = read_sysreg_s(SYS_ESR_EL12); break; case AFSR0_EL1: *val = read_sysreg_s(SYS_AFSR0_EL12); break; case AFSR1_EL1: *val = read_sysreg_s(SYS_AFSR1_EL12); break; @@ -1083,6 +1086,9 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break; case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); break; case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); break; + case TCR2_EL1: write_sysreg_s(val, SYS_TCR2_EL12); break; + case PIR_EL1: write_sysreg_s(val, SYS_PIR_EL12); break; + case PIRE0_EL1: write_sysreg_s(val, SYS_PIRE0_EL12); break; case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); break; case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); break; case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); break; -- 2.51.0 From a0162020095e2a34a59fc64c07183cc039e759f6 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Oct 2024 15:53:17 +0100 Subject: [PATCH 09/16] KVM: arm64: Extend masking facility to arbitrary registers We currently only use the masking (RES0/RES1) facility for VNCR registers, as they are memory-based and thus easy to sanitise. But we could apply the same thing to other registers if we: - split the sanitisation from __VNCR_START__ - apply the sanitisation when reading from a HW register This involves a new "marker" in the vcpu_sysreg enum, which defines the point at which the sanitisation applies (the VNCR registers being of course after this marker). Whle we are at it, rename kvm_vcpu_sanitise_vncr_reg() to kvm_vcpu_apply_reg_masks(), which is vaguely more explicit, and harden set_sysreg_masks() against setting masks for random registers... Signed-off-by: Marc Zyngier Reviewed-by: Joey Gouly Link: https://lore.kernel.org/r/20241023145345.1613824-10-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_host.h | 19 +++++++++++++------ arch/arm64/kvm/nested.c | 12 ++++++++---- arch/arm64/kvm/sys_regs.c | 3 +++ 3 files changed, 24 insertions(+), 10 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index b89f19b4195d..c753ab31dcea 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -374,7 +374,7 @@ struct kvm_arch { u64 ctr_el0; - /* Masks for VNCR-baked sysregs */ + /* Masks for VNCR-backed and general EL2 sysregs */ struct kvm_sysreg_masks *sysreg_masks; /* @@ -408,6 +408,9 @@ struct kvm_vcpu_fault_info { r = __VNCR_START__ + ((VNCR_ ## r) / 8), \ __after_##r = __MAX__(__before_##r - 1, r) +#define MARKER(m) \ + m, __after_##m = m - 1 + enum vcpu_sysreg { __INVALID_SYSREG__, /* 0 is reserved as an invalid value */ MPIDR_EL1, /* MultiProcessor Affinity Register */ @@ -494,7 +497,11 @@ enum vcpu_sysreg { CNTHV_CTL_EL2, CNTHV_CVAL_EL2, - __VNCR_START__, /* Any VNCR-capable reg goes after this point */ + /* Anything from this can be RES0/RES1 sanitised */ + MARKER(__SANITISED_REG_START__), + + /* Any VNCR-capable reg goes after this point */ + MARKER(__VNCR_START__), VNCR(SCTLR_EL1),/* System Control Register */ VNCR(ACTLR_EL1),/* Auxiliary Control Register */ @@ -554,7 +561,7 @@ struct kvm_sysreg_masks { struct { u64 res0; u64 res1; - } mask[NR_SYS_REGS - __VNCR_START__]; + } mask[NR_SYS_REGS - __SANITISED_REG_START__]; }; struct kvm_cpu_context { @@ -1002,13 +1009,13 @@ static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r) #define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r)) -u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg); +u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64); #define __vcpu_sys_reg(v,r) \ (*({ \ const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \ u64 *__r = __ctxt_sys_reg(ctxt, (r)); \ - if (vcpu_has_nv((v)) && (r) >= __VNCR_START__) \ - *__r = kvm_vcpu_sanitise_vncr_reg((v), (r)); \ + if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__) \ + *__r = kvm_vcpu_apply_reg_masks((v), (r), *__r);\ __r; \ })) diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index c4b17d90fc49..26103d6514bd 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -933,15 +933,15 @@ static void limit_nv_id_regs(struct kvm *kvm) kvm_set_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1, val); } -u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg sr) +u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *vcpu, + enum vcpu_sysreg sr, u64 v) { - u64 v = ctxt_sys_reg(&vcpu->arch.ctxt, sr); struct kvm_sysreg_masks *masks; masks = vcpu->kvm->arch.sysreg_masks; if (masks) { - sr -= __VNCR_START__; + sr -= __SANITISED_REG_START__; v &= ~masks->mask[sr].res0; v |= masks->mask[sr].res1; @@ -952,7 +952,11 @@ u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg sr) static void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, u64 res1) { - int i = sr - __VNCR_START__; + int i = sr - __SANITISED_REG_START__; + + BUILD_BUG_ON(!__builtin_constant_p(sr)); + BUILD_BUG_ON(sr < __SANITISED_REG_START__); + BUILD_BUG_ON(sr >= NR_SYS_REGS); kvm->arch.sysreg_masks->mask[i].res0 = res0; kvm->arch.sysreg_masks->mask[i].res1 = res1; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 9fb2847f5abc..9115a75b2c61 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -189,6 +189,9 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) /* Get the current version of the EL1 counterpart. */ WARN_ON(!__vcpu_read_sys_reg_from_cpu(el1r, &val)); + if (reg >= __SANITISED_REG_START__) + val = kvm_vcpu_apply_reg_masks(vcpu, reg, val); + return val; } -- 2.51.0 From 93d7356e4b3044f5165f35a8beb6ef05b1a40b7a Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 25 Oct 2024 18:23:37 +0000 Subject: [PATCH 10/16] arm64: sysreg: Describe ID_AA64DFR2_EL1 fields Describe the new ID register in line with DDI0601 2024-09. Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20241025182354.3364124-3-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/arm64/tools/sysreg | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 3c812fd28eca..98e710aaa620 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1287,6 +1287,32 @@ Field 15:8 BRPs Field 7:0 SYSPMUID EndSysreg +Sysreg ID_AA64DFR2_EL1 3 0 0 5 2 +Res0 63:28 +UnsignedEnum 27:24 TRBE_EXC + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 23:20 SPE_nVM + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 19:16 SPE_EXC + 0b0000 NI + 0b0001 IMP +EndEnum +Res0 15:8 +UnsignedEnum 7:4 BWE + 0b0000 NI + 0b0001 FEAT_BWE + 0b0002 FEAT_BWE2 +EndEnum +UnsignedEnum 3:0 STEP + 0b0000 NI + 0b0001 IMP +EndEnum +EndSysreg + Sysreg ID_AA64AFR0_EL1 3 0 0 5 4 Res0 63:32 Field 31:28 IMPDEF7 -- 2.51.0 From 641630313e9c68b2a889b1aad684f29b9c3e4017 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 25 Oct 2024 18:23:38 +0000 Subject: [PATCH 11/16] arm64: sysreg: Migrate MDCR_EL2 definition to table Migrate MDCR_EL2 over to the sysreg table and align definitions with DDI0601 2024-09. Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20241025182354.3364124-4-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_arm.h | 29 -------------------------- arch/arm64/tools/sysreg | 35 ++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 29 deletions(-) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 109a85ee6910..fb8d15f299a4 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -311,35 +311,6 @@ GENMASK(19, 18) | \ GENMASK(15, 0)) -/* Hyp Debug Configuration Register bits */ -#define MDCR_EL2_E2TB_MASK (UL(0x3)) -#define MDCR_EL2_E2TB_SHIFT (UL(24)) -#define MDCR_EL2_HPMFZS (UL(1) << 36) -#define MDCR_EL2_HPMFZO (UL(1) << 29) -#define MDCR_EL2_MTPME (UL(1) << 28) -#define MDCR_EL2_TDCC (UL(1) << 27) -#define MDCR_EL2_HLP (UL(1) << 26) -#define MDCR_EL2_HCCD (UL(1) << 23) -#define MDCR_EL2_TTRF (UL(1) << 19) -#define MDCR_EL2_HPMD (UL(1) << 17) -#define MDCR_EL2_TPMS (UL(1) << 14) -#define MDCR_EL2_E2PB_MASK (UL(0x3)) -#define MDCR_EL2_E2PB_SHIFT (UL(12)) -#define MDCR_EL2_TDRA (UL(1) << 11) -#define MDCR_EL2_TDOSA (UL(1) << 10) -#define MDCR_EL2_TDA (UL(1) << 9) -#define MDCR_EL2_TDE (UL(1) << 8) -#define MDCR_EL2_HPME (UL(1) << 7) -#define MDCR_EL2_TPM (UL(1) << 6) -#define MDCR_EL2_TPMCR (UL(1) << 5) -#define MDCR_EL2_HPMN_MASK (UL(0x1F)) -#define MDCR_EL2_RES0 (GENMASK(63, 37) | \ - GENMASK(35, 30) | \ - GENMASK(25, 24) | \ - GENMASK(22, 20) | \ - BIT(18) | \ - GENMASK(16, 15)) - /* * FGT register definitions * diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 98e710aaa620..c3117debdc2a 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -2414,6 +2414,41 @@ Field 1 AFSR1_EL1 Field 0 AFSR0_EL1 EndSysregFields +Sysreg MDCR_EL2 3 4 1 1 1 +Res0 63:51 +Field 50 EnSTEPOP +Res0 49:44 +Field 43 EBWE +Res0 42 +Field 41:40 PMEE +Res0 39:37 +Field 36 HPMFZS +Res0 35:32 +Field 31:30 PMSSE +Field 29 HPMFZO +Field 28 MTPME +Field 27 TDCC +Field 26 HLP +Field 25:24 E2TB +Field 23 HCCD +Res0 22:20 +Field 19 TTRF +Res0 18 +Field 17 HPMD +Res0 16 +Field 15 EnSPM +Field 14 TPMS +Field 13:12 E2PB +Field 11 TDRA +Field 10 TDOSA +Field 9 TDA +Field 8 TDE +Field 7 HPME +Field 6 TPM +Field 5 TPMCR +Field 4:0 HPMN +EndSysreg + Sysreg HFGRTR_EL2 3 4 1 1 4 Fields HFGxTR_EL2 EndSysreg -- 2.51.0 From 3ecb1fe3842c8783d8cd94a192aec4225f72b652 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 25 Oct 2024 18:23:39 +0000 Subject: [PATCH 12/16] arm64: sysreg: Add new definitions for ID_AA64DFR0_EL1 Align the field definitions w/ DDI0601 2024-09 and opportunistically declare MTPMU as a signed field. Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20241025182354.3364124-5-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/arm64/tools/sysreg | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index c3117debdc2a..5b28bf157c38 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1200,7 +1200,7 @@ UnsignedEnum 55:52 BRBE 0b0001 IMP 0b0010 BRBE_V1P1 EndEnum -Enum 51:48 MTPMU +SignedEnum 51:48 MTPMU 0b0000 NI_IMPDEF 0b0001 IMP 0b1111 NI @@ -1208,6 +1208,7 @@ EndEnum UnsignedEnum 47:44 TraceBuffer 0b0000 NI 0b0001 IMP + 0b0010 TRBE_V1P1 EndEnum UnsignedEnum 43:40 TraceFilt 0b0000 NI @@ -1224,11 +1225,18 @@ UnsignedEnum 35:32 PMSVer 0b0011 V1P2 0b0100 V1P3 0b0101 V1P4 + 0b0110 V1P5 EndEnum Field 31:28 CTX_CMPs -Res0 27:24 +UnsignedEnum 27:24 SEBEP + 0b0000 NI + 0b0001 IMP +EndEnum Field 23:20 WRPs -Res0 19:16 +UnsignedEnum 19:16 PMSS + 0b0000 NI + 0b0001 IMP +EndEnum Field 15:12 BRPs UnsignedEnum 11:8 PMUVer 0b0000 NI @@ -1238,6 +1246,7 @@ UnsignedEnum 11:8 PMUVer 0b0110 V3P5 0b0111 V3P7 0b1000 V3P8 + 0b1001 V3P9 0b1111 IMP_DEF EndEnum UnsignedEnum 7:4 TraceVer -- 2.51.0 From eb609638da5578c59fd28baf9825f1dd19b61d7a Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 25 Oct 2024 18:23:40 +0000 Subject: [PATCH 13/16] KVM: arm64: Describe RES0/RES1 bits of MDCR_EL2 Add support for sanitising MDCR_EL2 and describe the RES0/RES1 bits according to the feature set exposed to the VM. Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20241025182354.3364124-6-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_host.h | 2 +- arch/arm64/kvm/nested.c | 37 +++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index c753ab31dcea..725b5cd18ee0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -471,7 +471,6 @@ enum vcpu_sysreg { /* EL2 registers */ SCTLR_EL2, /* System Control Register (EL2) */ ACTLR_EL2, /* Auxiliary Control Register (EL2) */ - MDCR_EL2, /* Monitor Debug Configuration Register (EL2) */ CPTR_EL2, /* Architectural Feature Trap Register (EL2) */ HACR_EL2, /* Hypervisor Auxiliary Control Register */ ZCR_EL2, /* SVE Control Register (EL2) */ @@ -499,6 +498,7 @@ enum vcpu_sysreg { /* Anything from this can be RES0/RES1 sanitised */ MARKER(__SANITISED_REG_START__), + MDCR_EL2, /* Monitor Debug Configuration Register (EL2) */ /* Any VNCR-capable reg goes after this point */ MARKER(__VNCR_START__), diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 26103d6514bd..676e2de78fdd 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -1211,6 +1211,43 @@ int kvm_init_nv_sysregs(struct kvm *kvm) res0 |= SCTLR_EL1_EPAN; set_sysreg_masks(kvm, SCTLR_EL1, res0, res1); + /* MDCR_EL2 */ + res0 = MDCR_EL2_RES0; + res1 = MDCR_EL2_RES1; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) + res0 |= (MDCR_EL2_HPMN | MDCR_EL2_TPMCR | + MDCR_EL2_TPM | MDCR_EL2_HPME); + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP)) + res0 |= MDCR_EL2_E2PB | MDCR_EL2_TPMS; + if (!kvm_has_feat(kvm, ID_AA64DFR1_EL1, SPMU, IMP)) + res0 |= MDCR_EL2_EnSPM; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, V3P1)) + res0 |= MDCR_EL2_HPMD; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP)) + res0 |= MDCR_EL2_TTRF; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) + res0 |= MDCR_EL2_HCCD | MDCR_EL2_HLP; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, IMP)) + res0 |= MDCR_EL2_E2TB; + if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, FGT, IMP)) + res0 |= MDCR_EL2_TDCC; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, MTPMU, IMP) || + kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL3, IMP)) + res0 |= MDCR_EL2_MTPME; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, V3P7)) + res0 |= MDCR_EL2_HPMFZO; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSS, IMP)) + res0 |= MDCR_EL2_PMSSE; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P2)) + res0 |= MDCR_EL2_HPMFZS; + if (!kvm_has_feat(kvm, ID_AA64DFR1_EL1, EBEP, IMP)) + res0 |= MDCR_EL2_PMEE; + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DebugVer, V8P9)) + res0 |= MDCR_EL2_EBWE; + if (!kvm_has_feat(kvm, ID_AA64DFR2_EL1, STEP, IMP)) + res0 |= MDCR_EL2_EnSTEPOP; + set_sysreg_masks(kvm, MDCR_EL2, res0, res1); + return 0; } -- 2.51.0 From 18aeeeb57b93f5038ad9b1bac2102640e786b1d1 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 25 Oct 2024 18:23:41 +0000 Subject: [PATCH 14/16] KVM: arm64: nv: Allow coarse-grained trap combos to use complex traps KVM uses a sanity-check to avoid infinite recursion in trap combinations that could potentially depend on itself. Narrow the scope of this sanity check to the exact CGT IDs that correspond w/ trap combos, opening the door to using 'complex' traps as part of a combination. Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20241025182354.3364124-7-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/arm64/kvm/emulate-nested.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 05b6435d02a9..da7ab14e036d 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -2021,7 +2021,8 @@ check_mcb: cgids = coarse_control_combo[id - __MULTIPLE_CONTROL_BITS__]; for (int i = 0; cgids[i] != __RESERVED__; i++) { - if (cgids[i] >= __MULTIPLE_CONTROL_BITS__) { + if (cgids[i] >= __MULTIPLE_CONTROL_BITS__ && + cgids[i] < __COMPLEX_CONDITIONS__) { kvm_err("Recursive MCB %d/%d\n", id, cgids[i]); ret = -EINVAL; } -- 2.51.0 From a4063b5aa0bd7abc31c8044d897cff606cc8b74b Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 25 Oct 2024 18:23:42 +0000 Subject: [PATCH 15/16] KVM: arm64: nv: Rename BEHAVE_FORWARD_ANY BEHAVE_FORWARD_ANY is slightly ambiguous, especially since we're about to cram some more information into the enum. Rephrase it. Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20241025182354.3364124-8-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/arm64/kvm/emulate-nested.c | 93 +++++++++++++++++---------------- 1 file changed, 47 insertions(+), 46 deletions(-) diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index da7ab14e036d..e1a30d1bcd06 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -16,9 +16,10 @@ enum trap_behaviour { BEHAVE_HANDLE_LOCALLY = 0, + BEHAVE_FORWARD_READ = BIT(0), BEHAVE_FORWARD_WRITE = BIT(1), - BEHAVE_FORWARD_ANY = BEHAVE_FORWARD_READ | BEHAVE_FORWARD_WRITE, + BEHAVE_FORWARD_RW = BEHAVE_FORWARD_READ | BEHAVE_FORWARD_WRITE, }; struct trap_bits { @@ -138,7 +139,7 @@ static const struct trap_bits coarse_trap_bits[] = { .index = HCR_EL2, .value = HCR_TID2, .mask = HCR_TID2, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TID3] = { .index = HCR_EL2, @@ -162,37 +163,37 @@ static const struct trap_bits coarse_trap_bits[] = { .index = HCR_EL2, .value = HCR_TIDCP, .mask = HCR_TIDCP, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TACR] = { .index = HCR_EL2, .value = HCR_TACR, .mask = HCR_TACR, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TSW] = { .index = HCR_EL2, .value = HCR_TSW, .mask = HCR_TSW, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TPC] = { /* Also called TCPC when FEAT_DPB is implemented */ .index = HCR_EL2, .value = HCR_TPC, .mask = HCR_TPC, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TPU] = { .index = HCR_EL2, .value = HCR_TPU, .mask = HCR_TPU, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TTLB] = { .index = HCR_EL2, .value = HCR_TTLB, .mask = HCR_TTLB, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TVM] = { .index = HCR_EL2, @@ -204,7 +205,7 @@ static const struct trap_bits coarse_trap_bits[] = { .index = HCR_EL2, .value = HCR_TDZ, .mask = HCR_TDZ, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TRVM] = { .index = HCR_EL2, @@ -216,205 +217,205 @@ static const struct trap_bits coarse_trap_bits[] = { .index = HCR_EL2, .value = HCR_TLOR, .mask = HCR_TLOR, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TERR] = { .index = HCR_EL2, .value = HCR_TERR, .mask = HCR_TERR, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_APK] = { .index = HCR_EL2, .value = 0, .mask = HCR_APK, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_NV] = { .index = HCR_EL2, .value = HCR_NV, .mask = HCR_NV, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_NV_nNV2] = { .index = HCR_EL2, .value = HCR_NV, .mask = HCR_NV | HCR_NV2, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_NV1_nNV2] = { .index = HCR_EL2, .value = HCR_NV | HCR_NV1, .mask = HCR_NV | HCR_NV1 | HCR_NV2, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_AT] = { .index = HCR_EL2, .value = HCR_AT, .mask = HCR_AT, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_nFIEN] = { .index = HCR_EL2, .value = 0, .mask = HCR_FIEN, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TID4] = { .index = HCR_EL2, .value = HCR_TID4, .mask = HCR_TID4, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TICAB] = { .index = HCR_EL2, .value = HCR_TICAB, .mask = HCR_TICAB, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TOCU] = { .index = HCR_EL2, .value = HCR_TOCU, .mask = HCR_TOCU, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_ENSCXT] = { .index = HCR_EL2, .value = 0, .mask = HCR_ENSCXT, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TTLBIS] = { .index = HCR_EL2, .value = HCR_TTLBIS, .mask = HCR_TTLBIS, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TTLBOS] = { .index = HCR_EL2, .value = HCR_TTLBOS, .mask = HCR_TTLBOS, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TPMCR] = { .index = MDCR_EL2, .value = MDCR_EL2_TPMCR, .mask = MDCR_EL2_TPMCR, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TPM] = { .index = MDCR_EL2, .value = MDCR_EL2_TPM, .mask = MDCR_EL2_TPM, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TDE] = { .index = MDCR_EL2, .value = MDCR_EL2_TDE, .mask = MDCR_EL2_TDE, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TDA] = { .index = MDCR_EL2, .value = MDCR_EL2_TDA, .mask = MDCR_EL2_TDA, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TDOSA] = { .index = MDCR_EL2, .value = MDCR_EL2_TDOSA, .mask = MDCR_EL2_TDOSA, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TDRA] = { .index = MDCR_EL2, .value = MDCR_EL2_TDRA, .mask = MDCR_EL2_TDRA, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_E2PB] = { .index = MDCR_EL2, .value = 0, .mask = BIT(MDCR_EL2_E2PB_SHIFT), - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TPMS] = { .index = MDCR_EL2, .value = MDCR_EL2_TPMS, .mask = MDCR_EL2_TPMS, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TTRF] = { .index = MDCR_EL2, .value = MDCR_EL2_TTRF, .mask = MDCR_EL2_TTRF, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_E2TB] = { .index = MDCR_EL2, .value = 0, .mask = BIT(MDCR_EL2_E2TB_SHIFT), - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TDCC] = { .index = MDCR_EL2, .value = MDCR_EL2_TDCC, .mask = MDCR_EL2_TDCC, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_CPACR_E0POE] = { .index = CPTR_EL2, .value = CPACR_ELx_E0POE, .mask = CPACR_ELx_E0POE, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_CPTR_TAM] = { .index = CPTR_EL2, .value = CPTR_EL2_TAM, .mask = CPTR_EL2_TAM, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_CPTR_TCPAC] = { .index = CPTR_EL2, .value = CPTR_EL2_TCPAC, .mask = CPTR_EL2_TCPAC, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCRX_EnFPM] = { .index = HCRX_EL2, .value = 0, .mask = HCRX_EL2_EnFPM, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCRX_TCR2En] = { .index = HCRX_EL2, .value = 0, .mask = HCRX_EL2_TCR2En, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TC] = { .index = ICH_HCR_EL2, .value = ICH_HCR_TC, .mask = ICH_HCR_TC, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TALL0] = { .index = ICH_HCR_EL2, .value = ICH_HCR_TALL0, .mask = ICH_HCR_TALL0, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TALL1] = { .index = ICH_HCR_EL2, .value = ICH_HCR_TALL1, .mask = ICH_HCR_TALL1, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TDIR] = { .index = ICH_HCR_EL2, .value = ICH_HCR_TDIR, .mask = ICH_HCR_TDIR, - .behaviour = BEHAVE_FORWARD_ANY, + .behaviour = BEHAVE_FORWARD_RW, }, }; @@ -474,7 +475,7 @@ static enum trap_behaviour check_cnthctl_el1pcten(struct kvm_vcpu *vcpu) if (get_sanitized_cnthctl(vcpu) & (CNTHCTL_EL1PCTEN << 10)) return BEHAVE_HANDLE_LOCALLY; - return BEHAVE_FORWARD_ANY; + return BEHAVE_FORWARD_RW; } static enum trap_behaviour check_cnthctl_el1pten(struct kvm_vcpu *vcpu) @@ -482,7 +483,7 @@ static enum trap_behaviour check_cnthctl_el1pten(struct kvm_vcpu *vcpu) if (get_sanitized_cnthctl(vcpu) & (CNTHCTL_EL1PCEN << 10)) return BEHAVE_HANDLE_LOCALLY; - return BEHAVE_FORWARD_ANY; + return BEHAVE_FORWARD_RW; } static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu) @@ -493,7 +494,7 @@ static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu) val = translate_cptr_el2_to_cpacr_el1(val); if (val & CPACR_ELx_TTA) - return BEHAVE_FORWARD_ANY; + return BEHAVE_FORWARD_RW; return BEHAVE_HANDLE_LOCALLY; } -- 2.51.0 From d97e66fbcba796bb986e2097c352afae896b7942 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 25 Oct 2024 18:23:43 +0000 Subject: [PATCH 16/16] KVM: arm64: nv: Reinject traps that take effect in Host EL0 Wire up the other end of traps that affect host EL0 by actually injecting them into the guest hypervisor. Skip over FGT entirely, as a cursory glance suggests no FGT is effective in host EL0. Note that kvm_inject_nested() is already equipped for handling exceptions while the VM is already in a host context. Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/20241025182354.3364124-9-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_emulate.h | 5 +++++ arch/arm64/kvm/emulate-nested.c | 29 ++++++++++++++++++++++++---- 2 files changed, 30 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index a601a9305b10..bf0c48403f59 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -225,6 +225,11 @@ static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu) return vcpu_has_nv(vcpu) && __is_hyp_ctxt(&vcpu->arch.ctxt); } +static inline bool vcpu_is_host_el0(const struct kvm_vcpu *vcpu) +{ + return is_hyp_ctxt(vcpu) && !vcpu_is_el2(vcpu); +} + /* * The layout of SPSR for an AArch32 state is different when observed from an * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32 diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index e1a30d1bcd06..b072098ee44e 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -20,6 +20,9 @@ enum trap_behaviour { BEHAVE_FORWARD_READ = BIT(0), BEHAVE_FORWARD_WRITE = BIT(1), BEHAVE_FORWARD_RW = BEHAVE_FORWARD_READ | BEHAVE_FORWARD_WRITE, + + /* Traps that take effect in Host EL0, this is rare! */ + BEHAVE_FORWARD_IN_HOST_EL0 = BIT(2), }; struct trap_bits { @@ -2128,11 +2131,19 @@ static u64 kvm_get_sysreg_res0(struct kvm *kvm, enum vcpu_sysreg sr) return masks->mask[sr - __VNCR_START__].res0; } -static bool check_fgt_bit(struct kvm *kvm, bool is_read, +static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read, u64 val, const union trap_config tc) { + struct kvm *kvm = vcpu->kvm; enum vcpu_sysreg sr; + /* + * KVM doesn't know about any FGTs that apply to the host, and hopefully + * that'll remain the case. + */ + if (is_hyp_ctxt(vcpu)) + return false; + if (tc.pol) return (val & BIT(tc.bit)); @@ -2209,7 +2220,15 @@ bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index) * If we're not nesting, immediately return to the caller, with the * sysreg index, should we have it. */ - if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu)) + if (!vcpu_has_nv(vcpu)) + goto local; + + /* + * There are a few traps that take effect InHost, but are constrained + * to EL0. Don't bother with computing the trap behaviour if the vCPU + * isn't in EL0. + */ + if (is_hyp_ctxt(vcpu) && !vcpu_is_host_el0(vcpu)) goto local; switch ((enum fgt_group_id)tc.fgt) { @@ -2255,12 +2274,14 @@ bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index) goto local; } - if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu->kvm, is_read, - val, tc)) + if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu, is_read, val, tc)) goto inject; b = compute_trap_behaviour(vcpu, tc); + if (!(b & BEHAVE_FORWARD_IN_HOST_EL0) && vcpu_is_host_el0(vcpu)) + goto local; + if (((b & BEHAVE_FORWARD_READ) && is_read) || ((b & BEHAVE_FORWARD_WRITE) && !is_read)) goto inject; -- 2.51.0