From: Oliver Upton oliver.upton@linux.dev

Add flags to kvm_host_data to track if SPE/TRBE is present + programmable on a per-CPU basis. Set the flags up at init rather than vcpu_load() as the programmability of these buffers is unlikely to change.

Signed-off-by: Oliver Upton oliver.upton@linux.dev Reviewed-by: James Clark james.clark@linaro.org Signed-off-by: James Clark james.clark@linaro.org --- arch/arm64/include/asm/kvm_host.h | 19 +++++++++------- arch/arm64/kvm/arm.c | 3 --- arch/arm64/kvm/debug.c | 36 ++++++++---------------------- arch/arm64/kvm/hyp/nvhe/debug-sr.c | 8 +++---- 4 files changed, 24 insertions(+), 42 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index ad514434f3fe..7e3478386351 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -610,6 +610,10 @@ struct cpu_sve_state { * field. */ struct kvm_host_data { +#define KVM_HOST_DATA_FLAG_HAS_SPE 0 +#define KVM_HOST_DATA_FLAG_HAS_TRBE 1 + unsigned long flags; + struct kvm_cpu_context host_ctxt;

/* @@ -911,10 +915,6 @@ struct kvm_vcpu_arch { #define EXCEPT_AA64_EL2_SERR __vcpu_except_flags(7) /* Guest debug is live */ #define DEBUG_DIRTY __vcpu_single_flag(iflags, BIT(4)) -/* Save SPE context if active */ -#define DEBUG_STATE_SAVE_SPE __vcpu_single_flag(iflags, BIT(5)) -/* Save TRBE context if active */ -#define DEBUG_STATE_SAVE_TRBE __vcpu_single_flag(iflags, BIT(6))

/* SVE enabled for host EL0 */ #define HOST_SVE_ENABLED __vcpu_single_flag(sflags, BIT(0)) @@ -1310,6 +1310,13 @@ DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data); &this_cpu_ptr_hyp_sym(kvm_host_data)->f) #endif

+#define host_data_test_flag(flag) \ + (test_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags))) +#define host_data_set_flag(flag) \ + set_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)) +#define host_data_clear_flag(flag) \ + clear_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)) + /* Check whether the FP regs are owned by the guest */ static inline bool guest_owns_fp_regs(void) { @@ -1370,10 +1377,6 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) return (!has_vhe() && attr->exclude_host); }

-/* Flags for host debug state */ -void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu); -void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu); - #ifdef CONFIG_KVM void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u64 clr); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index ab1bf9ccf385..3822774840e1 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -617,15 +617,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)

vcpu_set_pauth_traps(vcpu);

- kvm_arch_vcpu_load_debug_state_flags(vcpu); - if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus)) vcpu_set_on_unsupported_cpu(vcpu); }

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { - kvm_arch_vcpu_put_debug_state_flags(vcpu); kvm_arch_vcpu_put_fp(vcpu); if (has_vhe()) kvm_vcpu_put_vhe(vcpu); diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 0dbabb6e1108..dd9e139dfd13 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -299,40 +299,22 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) } }

-void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu) +void kvm_init_host_debug_data(void) { - u64 dfr0; + u64 dfr0 = read_sysreg(id_aa64dfr0_el1); + + if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0) + *host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N, + read_sysreg(pmcr_el0));

- /* For VHE, there is nothing to do */ if (has_vhe()) return;

- dfr0 = read_sysreg(id_aa64dfr0_el1); - /* - * If SPE is present on this CPU and is available at current EL, - * we may need to check if the host state needs to be saved. - */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && - !(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(PMBIDR_EL1_P_SHIFT))) - vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_SPE); + !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P)) + host_data_set_flag(HAS_SPE);

- /* Check if we have TRBE implemented and available at the host */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) - vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_TRBE); -} - -void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu) -{ - vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_SPE); - vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_TRBE); -} - -void kvm_init_host_debug_data(void) -{ - u64 dfr0 = read_sysreg(id_aa64dfr0_el1); - - if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0) - *host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N, - read_sysreg(pmcr_el0)); + host_data_set_flag(HAS_TRBE); } diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c index 1e2a26d0196e..858bb38e273f 100644 --- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c @@ -82,10 +82,10 @@ static void __debug_restore_trace(u64 trfcr_el1) void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu) { /* Disable and flush SPE data generation */ - if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE)) + if (host_data_test_flag(HAS_SPE)) __debug_save_spe(host_data_ptr(host_debug_state.pmscr_el1)); /* Disable and flush Self-Hosted Trace generation */ - if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE)) + if (host_data_test_flag(HAS_TRBE)) __debug_save_trace(host_data_ptr(host_debug_state.trfcr_el1)); }

@@ -96,9 +96,9 @@ void __debug_switch_to_guest(struct kvm_vcpu *vcpu)

void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu) { - if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE)) + if (host_data_test_flag(HAS_SPE)) __debug_restore_spe(*host_data_ptr(host_debug_state.pmscr_el1)); - if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE)) + if (host_data_test_flag(HAS_TRBE)) __debug_restore_trace(*host_data_ptr(host_debug_state.trfcr_el1)); }

From: James Clark james.clark@arm.com

Created with the following:

cp include/linux/kasan-tags.h tools/include/linux/ cp arch/arm64/include/asm/sysreg.h tools/arch/arm64/include/asm/

Update the tools copy of sysreg.h so that the next commit to add a new register doesn't have unrelated changes in it. Because the new version of sysreg.h includes kasan-tags.h, that file also now needs to be copied into tools.

Acked-by: Mark Brown broonie@kernel.org Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: James Clark james.clark@arm.com Signed-off-by: James Clark james.clark@linaro.org --- tools/arch/arm64/include/asm/sysreg.h | 398 +++++++++++++++++++++++++- tools/include/linux/kasan-tags.h | 15 + 2 files changed, 405 insertions(+), 8 deletions(-) create mode 100644 tools/include/linux/kasan-tags.h

diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h index cd8420e8c3ad..345e81e0d2b3 100644 --- a/tools/arch/arm64/include/asm/sysreg.h +++ b/tools/arch/arm64/include/asm/sysreg.h @@ -11,6 +11,7 @@

#include <linux/bits.h> #include <linux/stringify.h> +#include <linux/kasan-tags.h>

#include <asm/gpr-num.h>

@@ -108,6 +109,9 @@ #define set_pstate_ssbs(x) asm volatile(SET_PSTATE_SSBS(x)) #define set_pstate_dit(x) asm volatile(SET_PSTATE_DIT(x))

+/* Register-based PAN access, for save/restore purposes */ +#define SYS_PSTATE_PAN sys_reg(3, 0, 4, 2, 3) + #define __SYS_BARRIER_INSN(CRm, op2, Rt) \ __emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))

@@ -123,6 +127,37 @@ #define SYS_DC_CIGSW sys_insn(1, 0, 7, 14, 4) #define SYS_DC_CIGDSW sys_insn(1, 0, 7, 14, 6)

+#define SYS_IC_IALLUIS sys_insn(1, 0, 7, 1, 0) +#define SYS_IC_IALLU sys_insn(1, 0, 7, 5, 0) +#define SYS_IC_IVAU sys_insn(1, 3, 7, 5, 1) + +#define SYS_DC_IVAC sys_insn(1, 0, 7, 6, 1) +#define SYS_DC_IGVAC sys_insn(1, 0, 7, 6, 3) +#define SYS_DC_IGDVAC sys_insn(1, 0, 7, 6, 5) + +#define SYS_DC_CVAC sys_insn(1, 3, 7, 10, 1) +#define SYS_DC_CGVAC sys_insn(1, 3, 7, 10, 3) +#define SYS_DC_CGDVAC sys_insn(1, 3, 7, 10, 5) + +#define SYS_DC_CVAU sys_insn(1, 3, 7, 11, 1) + +#define SYS_DC_CVAP sys_insn(1, 3, 7, 12, 1) +#define SYS_DC_CGVAP sys_insn(1, 3, 7, 12, 3) +#define SYS_DC_CGDVAP sys_insn(1, 3, 7, 12, 5) + +#define SYS_DC_CVADP sys_insn(1, 3, 7, 13, 1) +#define SYS_DC_CGVADP sys_insn(1, 3, 7, 13, 3) +#define SYS_DC_CGDVADP sys_insn(1, 3, 7, 13, 5) + +#define SYS_DC_CIVAC sys_insn(1, 3, 7, 14, 1) +#define SYS_DC_CIGVAC sys_insn(1, 3, 7, 14, 3) +#define SYS_DC_CIGDVAC sys_insn(1, 3, 7, 14, 5) + +/* Data cache zero operations */ +#define SYS_DC_ZVA sys_insn(1, 3, 7, 4, 1) +#define SYS_DC_GVA sys_insn(1, 3, 7, 4, 3) +#define SYS_DC_GZVA sys_insn(1, 3, 7, 4, 4) + /* * Automatically generated definitions for system registers, the * manual encodings below are in the process of being converted to @@ -162,6 +197,84 @@ #define SYS_DBGDTRTX_EL0 sys_reg(2, 3, 0, 5, 0) #define SYS_DBGVCR32_EL2 sys_reg(2, 4, 0, 7, 0)

+#define SYS_BRBINF_EL1(n) sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 0)) +#define SYS_BRBINFINJ_EL1 sys_reg(2, 1, 9, 1, 0) +#define SYS_BRBSRC_EL1(n) sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 1)) +#define SYS_BRBSRCINJ_EL1 sys_reg(2, 1, 9, 1, 1) +#define SYS_BRBTGT_EL1(n) sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 2)) +#define SYS_BRBTGTINJ_EL1 sys_reg(2, 1, 9, 1, 2) +#define SYS_BRBTS_EL1 sys_reg(2, 1, 9, 0, 2) + +#define SYS_BRBCR_EL1 sys_reg(2, 1, 9, 0, 0) +#define SYS_BRBFCR_EL1 sys_reg(2, 1, 9, 0, 1) +#define SYS_BRBIDR0_EL1 sys_reg(2, 1, 9, 2, 0) + +#define SYS_TRCITECR_EL1 sys_reg(3, 0, 1, 2, 3) +#define SYS_TRCACATR(m) sys_reg(2, 1, 2, ((m & 7) << 1), (2 | (m >> 3))) +#define SYS_TRCACVR(m) sys_reg(2, 1, 2, ((m & 7) << 1), (0 | (m >> 3))) +#define SYS_TRCAUTHSTATUS sys_reg(2, 1, 7, 14, 6) +#define SYS_TRCAUXCTLR sys_reg(2, 1, 0, 6, 0) +#define SYS_TRCBBCTLR sys_reg(2, 1, 0, 15, 0) +#define SYS_TRCCCCTLR sys_reg(2, 1, 0, 14, 0) +#define SYS_TRCCIDCCTLR0 sys_reg(2, 1, 3, 0, 2) +#define SYS_TRCCIDCCTLR1 sys_reg(2, 1, 3, 1, 2) +#define SYS_TRCCIDCVR(m) sys_reg(2, 1, 3, ((m & 7) << 1), 0) +#define SYS_TRCCLAIMCLR sys_reg(2, 1, 7, 9, 6) +#define SYS_TRCCLAIMSET sys_reg(2, 1, 7, 8, 6) +#define SYS_TRCCNTCTLR(m) sys_reg(2, 1, 0, (4 | (m & 3)), 5) +#define SYS_TRCCNTRLDVR(m) sys_reg(2, 1, 0, (0 | (m & 3)), 5) +#define SYS_TRCCNTVR(m) sys_reg(2, 1, 0, (8 | (m & 3)), 5) +#define SYS_TRCCONFIGR sys_reg(2, 1, 0, 4, 0) +#define SYS_TRCDEVARCH sys_reg(2, 1, 7, 15, 6) +#define SYS_TRCDEVID sys_reg(2, 1, 7, 2, 7) +#define SYS_TRCEVENTCTL0R sys_reg(2, 1, 0, 8, 0) +#define SYS_TRCEVENTCTL1R sys_reg(2, 1, 0, 9, 0) +#define SYS_TRCEXTINSELR(m) sys_reg(2, 1, 0, (8 | (m & 3)), 4) +#define SYS_TRCIDR0 sys_reg(2, 1, 0, 8, 7) +#define SYS_TRCIDR10 sys_reg(2, 1, 0, 2, 6) +#define SYS_TRCIDR11 sys_reg(2, 1, 0, 3, 6) +#define SYS_TRCIDR12 sys_reg(2, 1, 0, 4, 6) +#define SYS_TRCIDR13 sys_reg(2, 1, 0, 5, 6) +#define SYS_TRCIDR1 sys_reg(2, 1, 0, 9, 7) +#define SYS_TRCIDR2 sys_reg(2, 1, 0, 10, 7) +#define SYS_TRCIDR3 sys_reg(2, 1, 0, 11, 7) +#define SYS_TRCIDR4 sys_reg(2, 1, 0, 12, 7) +#define SYS_TRCIDR5 sys_reg(2, 1, 0, 13, 7) +#define SYS_TRCIDR6 sys_reg(2, 1, 0, 14, 7) +#define SYS_TRCIDR7 sys_reg(2, 1, 0, 15, 7) +#define SYS_TRCIDR8 sys_reg(2, 1, 0, 0, 6) +#define SYS_TRCIDR9 sys_reg(2, 1, 0, 1, 6) +#define SYS_TRCIMSPEC(m) sys_reg(2, 1, 0, (m & 7), 7) +#define SYS_TRCITEEDCR sys_reg(2, 1, 0, 2, 1) +#define SYS_TRCOSLSR sys_reg(2, 1, 1, 1, 4) +#define SYS_TRCPRGCTLR sys_reg(2, 1, 0, 1, 0) +#define SYS_TRCQCTLR sys_reg(2, 1, 0, 1, 1) +#define SYS_TRCRSCTLR(m) sys_reg(2, 1, 1, (m & 15), (0 | (m >> 4))) +#define SYS_TRCRSR sys_reg(2, 1, 0, 10, 0) +#define SYS_TRCSEQEVR(m) sys_reg(2, 1, 0, (m & 3), 4) +#define SYS_TRCSEQRSTEVR sys_reg(2, 1, 0, 6, 4) +#define SYS_TRCSEQSTR sys_reg(2, 1, 0, 7, 4) +#define SYS_TRCSSCCR(m) sys_reg(2, 1, 1, (m & 7), 2) +#define SYS_TRCSSCSR(m) sys_reg(2, 1, 1, (8 | (m & 7)), 2) +#define SYS_TRCSSPCICR(m) sys_reg(2, 1, 1, (m & 7), 3) +#define SYS_TRCSTALLCTLR sys_reg(2, 1, 0, 11, 0) +#define SYS_TRCSTATR sys_reg(2, 1, 0, 3, 0) +#define SYS_TRCSYNCPR sys_reg(2, 1, 0, 13, 0) +#define SYS_TRCTRACEIDR sys_reg(2, 1, 0, 0, 1) +#define SYS_TRCTSCTLR sys_reg(2, 1, 0, 12, 0) +#define SYS_TRCVICTLR sys_reg(2, 1, 0, 0, 2) +#define SYS_TRCVIIECTLR sys_reg(2, 1, 0, 1, 2) +#define SYS_TRCVIPCSSCTLR sys_reg(2, 1, 0, 3, 2) +#define SYS_TRCVISSCTLR sys_reg(2, 1, 0, 2, 2) +#define SYS_TRCVMIDCCTLR0 sys_reg(2, 1, 3, 2, 2) +#define SYS_TRCVMIDCCTLR1 sys_reg(2, 1, 3, 3, 2) +#define SYS_TRCVMIDCVR(m) sys_reg(2, 1, 3, ((m & 7) << 1), 1) + +/* ETM */ +#define SYS_TRCOSLAR sys_reg(2, 1, 1, 0, 4) + +#define SYS_BRBCR_EL2 sys_reg(2, 4, 9, 0, 0) + #define SYS_MIDR_EL1 sys_reg(3, 0, 0, 0, 0) #define SYS_MPIDR_EL1 sys_reg(3, 0, 0, 0, 5) #define SYS_REVIDR_EL1 sys_reg(3, 0, 0, 0, 6) @@ -202,15 +315,38 @@ #define SYS_ERXCTLR_EL1 sys_reg(3, 0, 5, 4, 1) #define SYS_ERXSTATUS_EL1 sys_reg(3, 0, 5, 4, 2) #define SYS_ERXADDR_EL1 sys_reg(3, 0, 5, 4, 3) +#define SYS_ERXPFGF_EL1 sys_reg(3, 0, 5, 4, 4) +#define SYS_ERXPFGCTL_EL1 sys_reg(3, 0, 5, 4, 5) +#define SYS_ERXPFGCDN_EL1 sys_reg(3, 0, 5, 4, 6) #define SYS_ERXMISC0_EL1 sys_reg(3, 0, 5, 5, 0) #define SYS_ERXMISC1_EL1 sys_reg(3, 0, 5, 5, 1) +#define SYS_ERXMISC2_EL1 sys_reg(3, 0, 5, 5, 2) +#define SYS_ERXMISC3_EL1 sys_reg(3, 0, 5, 5, 3) #define SYS_TFSR_EL1 sys_reg(3, 0, 5, 6, 0) #define SYS_TFSRE0_EL1 sys_reg(3, 0, 5, 6, 1)

#define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0)

#define SYS_PAR_EL1_F BIT(0) +/* When PAR_EL1.F == 1 */ #define SYS_PAR_EL1_FST GENMASK(6, 1) +#define SYS_PAR_EL1_PTW BIT(8) +#define SYS_PAR_EL1_S BIT(9) +#define SYS_PAR_EL1_AssuredOnly BIT(12) +#define SYS_PAR_EL1_TopLevel BIT(13) +#define SYS_PAR_EL1_Overlay BIT(14) +#define SYS_PAR_EL1_DirtyBit BIT(15) +#define SYS_PAR_EL1_F1_IMPDEF GENMASK_ULL(63, 48) +#define SYS_PAR_EL1_F1_RES0 (BIT(7) | BIT(10) | GENMASK_ULL(47, 16)) +#define SYS_PAR_EL1_RES1 BIT(11) +/* When PAR_EL1.F == 0 */ +#define SYS_PAR_EL1_SH GENMASK_ULL(8, 7) +#define SYS_PAR_EL1_NS BIT(9) +#define SYS_PAR_EL1_F0_IMPDEF BIT(10) +#define SYS_PAR_EL1_NSE BIT(11) +#define SYS_PAR_EL1_PA GENMASK_ULL(51, 12) +#define SYS_PAR_EL1_ATTR GENMASK_ULL(63, 56) +#define SYS_PAR_EL1_F0_RES0 (GENMASK_ULL(6, 1) | GENMASK_ULL(55, 52))

/*** Statistical Profiling Extension ***/ #define PMSEVFR_EL1_RES0_IMP \ @@ -274,6 +410,8 @@ #define SYS_ICC_IGRPEN0_EL1 sys_reg(3, 0, 12, 12, 6) #define SYS_ICC_IGRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)

+#define SYS_ACCDATA_EL1 sys_reg(3, 0, 13, 0, 5) + #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0)

#define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7) @@ -286,7 +424,6 @@ #define SYS_PMCNTENCLR_EL0 sys_reg(3, 3, 9, 12, 2) #define SYS_PMOVSCLR_EL0 sys_reg(3, 3, 9, 12, 3) #define SYS_PMSWINC_EL0 sys_reg(3, 3, 9, 12, 4) -#define SYS_PMSELR_EL0 sys_reg(3, 3, 9, 12, 5) #define SYS_PMCEID0_EL0 sys_reg(3, 3, 9, 12, 6) #define SYS_PMCEID1_EL0 sys_reg(3, 3, 9, 12, 7) #define SYS_PMCCNTR_EL0 sys_reg(3, 3, 9, 13, 0) @@ -369,6 +506,7 @@

#define SYS_SCTLR_EL2 sys_reg(3, 4, 1, 0, 0) #define SYS_ACTLR_EL2 sys_reg(3, 4, 1, 0, 1) +#define SYS_SCTLR2_EL2 sys_reg(3, 4, 1, 0, 3) #define SYS_HCR_EL2 sys_reg(3, 4, 1, 1, 0) #define SYS_MDCR_EL2 sys_reg(3, 4, 1, 1, 1) #define SYS_CPTR_EL2 sys_reg(3, 4, 1, 1, 2) @@ -382,12 +520,15 @@ #define SYS_VTCR_EL2 sys_reg(3, 4, 2, 1, 2)

#define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) -#define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4) -#define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5) +#define SYS_VNCR_EL2 sys_reg(3, 4, 2, 2, 0) #define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6) #define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0) #define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1) #define SYS_SP_EL1 sys_reg(3, 4, 4, 1, 0) +#define SYS_SPSR_irq sys_reg(3, 4, 4, 3, 0) +#define SYS_SPSR_abt sys_reg(3, 4, 4, 3, 1) +#define SYS_SPSR_und sys_reg(3, 4, 4, 3, 2) +#define SYS_SPSR_fiq sys_reg(3, 4, 4, 3, 3) #define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1) #define SYS_AFSR0_EL2 sys_reg(3, 4, 5, 1, 0) #define SYS_AFSR1_EL2 sys_reg(3, 4, 5, 1, 1) @@ -449,24 +590,49 @@

#define SYS_CONTEXTIDR_EL2 sys_reg(3, 4, 13, 0, 1) #define SYS_TPIDR_EL2 sys_reg(3, 4, 13, 0, 2) +#define SYS_SCXTNUM_EL2 sys_reg(3, 4, 13, 0, 7) + +#define __AMEV_op2(m) (m & 0x7) +#define __AMEV_CRm(n, m) (n | ((m & 0x8) >> 3)) +#define __SYS__AMEVCNTVOFF0n_EL2(m) sys_reg(3, 4, 13, __AMEV_CRm(0x8, m), __AMEV_op2(m)) +#define SYS_AMEVCNTVOFF0n_EL2(m) __SYS__AMEVCNTVOFF0n_EL2(m) +#define __SYS__AMEVCNTVOFF1n_EL2(m) sys_reg(3, 4, 13, __AMEV_CRm(0xA, m), __AMEV_op2(m)) +#define SYS_AMEVCNTVOFF1n_EL2(m) __SYS__AMEVCNTVOFF1n_EL2(m)

#define SYS_CNTVOFF_EL2 sys_reg(3, 4, 14, 0, 3) #define SYS_CNTHCTL_EL2 sys_reg(3, 4, 14, 1, 0) +#define SYS_CNTHP_TVAL_EL2 sys_reg(3, 4, 14, 2, 0) +#define SYS_CNTHP_CTL_EL2 sys_reg(3, 4, 14, 2, 1) +#define SYS_CNTHP_CVAL_EL2 sys_reg(3, 4, 14, 2, 2) +#define SYS_CNTHV_TVAL_EL2 sys_reg(3, 4, 14, 3, 0) +#define SYS_CNTHV_CTL_EL2 sys_reg(3, 4, 14, 3, 1) +#define SYS_CNTHV_CVAL_EL2 sys_reg(3, 4, 14, 3, 2)

/* VHE encodings for architectural EL0/1 system registers */ +#define SYS_BRBCR_EL12 sys_reg(2, 5, 9, 0, 0) #define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0) +#define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2) +#define SYS_SCTLR2_EL12 sys_reg(3, 5, 1, 0, 3) +#define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0) +#define SYS_TRFCR_EL12 sys_reg(3, 5, 1, 2, 1) +#define SYS_SMCR_EL12 sys_reg(3, 5, 1, 2, 6) #define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0) #define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1) #define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2) +#define SYS_TCR2_EL12 sys_reg(3, 5, 2, 0, 3) #define SYS_SPSR_EL12 sys_reg(3, 5, 4, 0, 0) #define SYS_ELR_EL12 sys_reg(3, 5, 4, 0, 1) #define SYS_AFSR0_EL12 sys_reg(3, 5, 5, 1, 0) #define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1) #define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0) #define SYS_TFSR_EL12 sys_reg(3, 5, 5, 6, 0) +#define SYS_FAR_EL12 sys_reg(3, 5, 6, 0, 0) +#define SYS_PMSCR_EL12 sys_reg(3, 5, 9, 9, 0) #define SYS_MAIR_EL12 sys_reg(3, 5, 10, 2, 0) #define SYS_AMAIR_EL12 sys_reg(3, 5, 10, 3, 0) #define SYS_VBAR_EL12 sys_reg(3, 5, 12, 0, 0) +#define SYS_CONTEXTIDR_EL12 sys_reg(3, 5, 13, 0, 1) +#define SYS_SCXTNUM_EL12 sys_reg(3, 5, 13, 0, 7) #define SYS_CNTKCTL_EL12 sys_reg(3, 5, 14, 1, 0) #define SYS_CNTP_TVAL_EL02 sys_reg(3, 5, 14, 2, 0) #define SYS_CNTP_CTL_EL02 sys_reg(3, 5, 14, 2, 1) @@ -477,6 +643,183 @@

#define SYS_SP_EL2 sys_reg(3, 6, 4, 1, 0)

+/* AT instructions */ +#define AT_Op0 1 +#define AT_CRn 7 + +#define OP_AT_S1E1R sys_insn(AT_Op0, 0, AT_CRn, 8, 0) +#define OP_AT_S1E1W sys_insn(AT_Op0, 0, AT_CRn, 8, 1) +#define OP_AT_S1E0R sys_insn(AT_Op0, 0, AT_CRn, 8, 2) +#define OP_AT_S1E0W sys_insn(AT_Op0, 0, AT_CRn, 8, 3) +#define OP_AT_S1E1RP sys_insn(AT_Op0, 0, AT_CRn, 9, 0) +#define OP_AT_S1E1WP sys_insn(AT_Op0, 0, AT_CRn, 9, 1) +#define OP_AT_S1E1A sys_insn(AT_Op0, 0, AT_CRn, 9, 2) +#define OP_AT_S1E2R sys_insn(AT_Op0, 4, AT_CRn, 8, 0) +#define OP_AT_S1E2W sys_insn(AT_Op0, 4, AT_CRn, 8, 1) +#define OP_AT_S12E1R sys_insn(AT_Op0, 4, AT_CRn, 8, 4) +#define OP_AT_S12E1W sys_insn(AT_Op0, 4, AT_CRn, 8, 5) +#define OP_AT_S12E0R sys_insn(AT_Op0, 4, AT_CRn, 8, 6) +#define OP_AT_S12E0W sys_insn(AT_Op0, 4, AT_CRn, 8, 7) +#define OP_AT_S1E2A sys_insn(AT_Op0, 4, AT_CRn, 9, 2) + +/* TLBI instructions */ +#define TLBI_Op0 1 + +#define TLBI_Op1_EL1 0 /* Accessible from EL1 or higher */ +#define TLBI_Op1_EL2 4 /* Accessible from EL2 or higher */ + +#define TLBI_CRn_XS 8 /* Extra Slow (the common one) */ +#define TLBI_CRn_nXS 9 /* not Extra Slow (which nobody uses)*/ + +#define TLBI_CRm_IPAIS 0 /* S2 Inner-Shareable */ +#define TLBI_CRm_nROS 1 /* non-Range, Outer-Sharable */ +#define TLBI_CRm_RIS 2 /* Range, Inner-Sharable */ +#define TLBI_CRm_nRIS 3 /* non-Range, Inner-Sharable */ +#define TLBI_CRm_IPAONS 4 /* S2 Outer and Non-Shareable */ +#define TLBI_CRm_ROS 5 /* Range, Outer-Sharable */ +#define TLBI_CRm_RNS 6 /* Range, Non-Sharable */ +#define TLBI_CRm_nRNS 7 /* non-Range, Non-Sharable */ + +#define OP_TLBI_VMALLE1OS sys_insn(1, 0, 8, 1, 0) +#define OP_TLBI_VAE1OS sys_insn(1, 0, 8, 1, 1) +#define OP_TLBI_ASIDE1OS sys_insn(1, 0, 8, 1, 2) +#define OP_TLBI_VAAE1OS sys_insn(1, 0, 8, 1, 3) +#define OP_TLBI_VALE1OS sys_insn(1, 0, 8, 1, 5) +#define OP_TLBI_VAALE1OS sys_insn(1, 0, 8, 1, 7) +#define OP_TLBI_RVAE1IS sys_insn(1, 0, 8, 2, 1) +#define OP_TLBI_RVAAE1IS sys_insn(1, 0, 8, 2, 3) +#define OP_TLBI_RVALE1IS sys_insn(1, 0, 8, 2, 5) +#define OP_TLBI_RVAALE1IS sys_insn(1, 0, 8, 2, 7) +#define OP_TLBI_VMALLE1IS sys_insn(1, 0, 8, 3, 0) +#define OP_TLBI_VAE1IS sys_insn(1, 0, 8, 3, 1) +#define OP_TLBI_ASIDE1IS sys_insn(1, 0, 8, 3, 2) +#define OP_TLBI_VAAE1IS sys_insn(1, 0, 8, 3, 3) +#define OP_TLBI_VALE1IS sys_insn(1, 0, 8, 3, 5) +#define OP_TLBI_VAALE1IS sys_insn(1, 0, 8, 3, 7) +#define OP_TLBI_RVAE1OS sys_insn(1, 0, 8, 5, 1) +#define OP_TLBI_RVAAE1OS sys_insn(1, 0, 8, 5, 3) +#define OP_TLBI_RVALE1OS sys_insn(1, 0, 8, 5, 5) +#define OP_TLBI_RVAALE1OS sys_insn(1, 0, 8, 5, 7) +#define OP_TLBI_RVAE1 sys_insn(1, 0, 8, 6, 1) +#define OP_TLBI_RVAAE1 sys_insn(1, 0, 8, 6, 3) +#define OP_TLBI_RVALE1 sys_insn(1, 0, 8, 6, 5) +#define OP_TLBI_RVAALE1 sys_insn(1, 0, 8, 6, 7) +#define OP_TLBI_VMALLE1 sys_insn(1, 0, 8, 7, 0) +#define OP_TLBI_VAE1 sys_insn(1, 0, 8, 7, 1) +#define OP_TLBI_ASIDE1 sys_insn(1, 0, 8, 7, 2) +#define OP_TLBI_VAAE1 sys_insn(1, 0, 8, 7, 3) +#define OP_TLBI_VALE1 sys_insn(1, 0, 8, 7, 5) +#define OP_TLBI_VAALE1 sys_insn(1, 0, 8, 7, 7) +#define OP_TLBI_VMALLE1OSNXS sys_insn(1, 0, 9, 1, 0) +#define OP_TLBI_VAE1OSNXS sys_insn(1, 0, 9, 1, 1) +#define OP_TLBI_ASIDE1OSNXS sys_insn(1, 0, 9, 1, 2) +#define OP_TLBI_VAAE1OSNXS sys_insn(1, 0, 9, 1, 3) +#define OP_TLBI_VALE1OSNXS sys_insn(1, 0, 9, 1, 5) +#define OP_TLBI_VAALE1OSNXS sys_insn(1, 0, 9, 1, 7) +#define OP_TLBI_RVAE1ISNXS sys_insn(1, 0, 9, 2, 1) +#define OP_TLBI_RVAAE1ISNXS sys_insn(1, 0, 9, 2, 3) +#define OP_TLBI_RVALE1ISNXS sys_insn(1, 0, 9, 2, 5) +#define OP_TLBI_RVAALE1ISNXS sys_insn(1, 0, 9, 2, 7) +#define OP_TLBI_VMALLE1ISNXS sys_insn(1, 0, 9, 3, 0) +#define OP_TLBI_VAE1ISNXS sys_insn(1, 0, 9, 3, 1) +#define OP_TLBI_ASIDE1ISNXS sys_insn(1, 0, 9, 3, 2) +#define OP_TLBI_VAAE1ISNXS sys_insn(1, 0, 9, 3, 3) +#define OP_TLBI_VALE1ISNXS sys_insn(1, 0, 9, 3, 5) +#define OP_TLBI_VAALE1ISNXS sys_insn(1, 0, 9, 3, 7) +#define OP_TLBI_RVAE1OSNXS sys_insn(1, 0, 9, 5, 1) +#define OP_TLBI_RVAAE1OSNXS sys_insn(1, 0, 9, 5, 3) +#define OP_TLBI_RVALE1OSNXS sys_insn(1, 0, 9, 5, 5) +#define OP_TLBI_RVAALE1OSNXS sys_insn(1, 0, 9, 5, 7) +#define OP_TLBI_RVAE1NXS sys_insn(1, 0, 9, 6, 1) +#define OP_TLBI_RVAAE1NXS sys_insn(1, 0, 9, 6, 3) +#define OP_TLBI_RVALE1NXS sys_insn(1, 0, 9, 6, 5) +#define OP_TLBI_RVAALE1NXS sys_insn(1, 0, 9, 6, 7) +#define OP_TLBI_VMALLE1NXS sys_insn(1, 0, 9, 7, 0) +#define OP_TLBI_VAE1NXS sys_insn(1, 0, 9, 7, 1) +#define OP_TLBI_ASIDE1NXS sys_insn(1, 0, 9, 7, 2) +#define OP_TLBI_VAAE1NXS sys_insn(1, 0, 9, 7, 3) +#define OP_TLBI_VALE1NXS sys_insn(1, 0, 9, 7, 5) +#define OP_TLBI_VAALE1NXS sys_insn(1, 0, 9, 7, 7) +#define OP_TLBI_IPAS2E1IS sys_insn(1, 4, 8, 0, 1) +#define OP_TLBI_RIPAS2E1IS sys_insn(1, 4, 8, 0, 2) +#define OP_TLBI_IPAS2LE1IS sys_insn(1, 4, 8, 0, 5) +#define OP_TLBI_RIPAS2LE1IS sys_insn(1, 4, 8, 0, 6) +#define OP_TLBI_ALLE2OS sys_insn(1, 4, 8, 1, 0) +#define OP_TLBI_VAE2OS sys_insn(1, 4, 8, 1, 1) +#define OP_TLBI_ALLE1OS sys_insn(1, 4, 8, 1, 4) +#define OP_TLBI_VALE2OS sys_insn(1, 4, 8, 1, 5) +#define OP_TLBI_VMALLS12E1OS sys_insn(1, 4, 8, 1, 6) +#define OP_TLBI_RVAE2IS sys_insn(1, 4, 8, 2, 1) +#define OP_TLBI_RVALE2IS sys_insn(1, 4, 8, 2, 5) +#define OP_TLBI_ALLE2IS sys_insn(1, 4, 8, 3, 0) +#define OP_TLBI_VAE2IS sys_insn(1, 4, 8, 3, 1) +#define OP_TLBI_ALLE1IS sys_insn(1, 4, 8, 3, 4) +#define OP_TLBI_VALE2IS sys_insn(1, 4, 8, 3, 5) +#define OP_TLBI_VMALLS12E1IS sys_insn(1, 4, 8, 3, 6) +#define OP_TLBI_IPAS2E1OS sys_insn(1, 4, 8, 4, 0) +#define OP_TLBI_IPAS2E1 sys_insn(1, 4, 8, 4, 1) +#define OP_TLBI_RIPAS2E1 sys_insn(1, 4, 8, 4, 2) +#define OP_TLBI_RIPAS2E1OS sys_insn(1, 4, 8, 4, 3) +#define OP_TLBI_IPAS2LE1OS sys_insn(1, 4, 8, 4, 4) +#define OP_TLBI_IPAS2LE1 sys_insn(1, 4, 8, 4, 5) +#define OP_TLBI_RIPAS2LE1 sys_insn(1, 4, 8, 4, 6) +#define OP_TLBI_RIPAS2LE1OS sys_insn(1, 4, 8, 4, 7) +#define OP_TLBI_RVAE2OS sys_insn(1, 4, 8, 5, 1) +#define OP_TLBI_RVALE2OS sys_insn(1, 4, 8, 5, 5) +#define OP_TLBI_RVAE2 sys_insn(1, 4, 8, 6, 1) +#define OP_TLBI_RVALE2 sys_insn(1, 4, 8, 6, 5) +#define OP_TLBI_ALLE2 sys_insn(1, 4, 8, 7, 0) +#define OP_TLBI_VAE2 sys_insn(1, 4, 8, 7, 1) +#define OP_TLBI_ALLE1 sys_insn(1, 4, 8, 7, 4) +#define OP_TLBI_VALE2 sys_insn(1, 4, 8, 7, 5) +#define OP_TLBI_VMALLS12E1 sys_insn(1, 4, 8, 7, 6) +#define OP_TLBI_IPAS2E1ISNXS sys_insn(1, 4, 9, 0, 1) +#define OP_TLBI_RIPAS2E1ISNXS sys_insn(1, 4, 9, 0, 2) +#define OP_TLBI_IPAS2LE1ISNXS sys_insn(1, 4, 9, 0, 5) +#define OP_TLBI_RIPAS2LE1ISNXS sys_insn(1, 4, 9, 0, 6) +#define OP_TLBI_ALLE2OSNXS sys_insn(1, 4, 9, 1, 0) +#define OP_TLBI_VAE2OSNXS sys_insn(1, 4, 9, 1, 1) +#define OP_TLBI_ALLE1OSNXS sys_insn(1, 4, 9, 1, 4) +#define OP_TLBI_VALE2OSNXS sys_insn(1, 4, 9, 1, 5) +#define OP_TLBI_VMALLS12E1OSNXS sys_insn(1, 4, 9, 1, 6) +#define OP_TLBI_RVAE2ISNXS sys_insn(1, 4, 9, 2, 1) +#define OP_TLBI_RVALE2ISNXS sys_insn(1, 4, 9, 2, 5) +#define OP_TLBI_ALLE2ISNXS sys_insn(1, 4, 9, 3, 0) +#define OP_TLBI_VAE2ISNXS sys_insn(1, 4, 9, 3, 1) +#define OP_TLBI_ALLE1ISNXS sys_insn(1, 4, 9, 3, 4) +#define OP_TLBI_VALE2ISNXS sys_insn(1, 4, 9, 3, 5) +#define OP_TLBI_VMALLS12E1ISNXS sys_insn(1, 4, 9, 3, 6) +#define OP_TLBI_IPAS2E1OSNXS sys_insn(1, 4, 9, 4, 0) +#define OP_TLBI_IPAS2E1NXS sys_insn(1, 4, 9, 4, 1) +#define OP_TLBI_RIPAS2E1NXS sys_insn(1, 4, 9, 4, 2) +#define OP_TLBI_RIPAS2E1OSNXS sys_insn(1, 4, 9, 4, 3) +#define OP_TLBI_IPAS2LE1OSNXS sys_insn(1, 4, 9, 4, 4) +#define OP_TLBI_IPAS2LE1NXS sys_insn(1, 4, 9, 4, 5) +#define OP_TLBI_RIPAS2LE1NXS sys_insn(1, 4, 9, 4, 6) +#define OP_TLBI_RIPAS2LE1OSNXS sys_insn(1, 4, 9, 4, 7) +#define OP_TLBI_RVAE2OSNXS sys_insn(1, 4, 9, 5, 1) +#define OP_TLBI_RVALE2OSNXS sys_insn(1, 4, 9, 5, 5) +#define OP_TLBI_RVAE2NXS sys_insn(1, 4, 9, 6, 1) +#define OP_TLBI_RVALE2NXS sys_insn(1, 4, 9, 6, 5) +#define OP_TLBI_ALLE2NXS sys_insn(1, 4, 9, 7, 0) +#define OP_TLBI_VAE2NXS sys_insn(1, 4, 9, 7, 1) +#define OP_TLBI_ALLE1NXS sys_insn(1, 4, 9, 7, 4) +#define OP_TLBI_VALE2NXS sys_insn(1, 4, 9, 7, 5) +#define OP_TLBI_VMALLS12E1NXS sys_insn(1, 4, 9, 7, 6) + +/* Misc instructions */ +#define OP_GCSPUSHX sys_insn(1, 0, 7, 7, 4) +#define OP_GCSPOPCX sys_insn(1, 0, 7, 7, 5) +#define OP_GCSPOPX sys_insn(1, 0, 7, 7, 6) +#define OP_GCSPUSHM sys_insn(1, 3, 7, 7, 0) + +#define OP_BRB_IALL sys_insn(1, 1, 7, 2, 4) +#define OP_BRB_INJ sys_insn(1, 1, 7, 2, 5) +#define OP_CFP_RCTX sys_insn(1, 3, 7, 3, 4) +#define OP_DVP_RCTX sys_insn(1, 3, 7, 3, 5) +#define OP_COSP_RCTX sys_insn(1, 3, 7, 3, 6) +#define OP_CPP_RCTX sys_insn(1, 3, 7, 3, 7) + /* Common SCTLR_ELx flags. */ #define SCTLR_ELx_ENTP2 (BIT(60)) #define SCTLR_ELx_DSSBS (BIT(44)) @@ -555,16 +898,14 @@ /* Position the attr at the correct index */ #define MAIR_ATTRIDX(attr, idx) ((attr) << ((idx) * 8))

-/* id_aa64pfr0 */ -#define ID_AA64PFR0_EL1_ELx_64BIT_ONLY 0x1 -#define ID_AA64PFR0_EL1_ELx_32BIT_64BIT 0x2 - /* id_aa64mmfr0 */ #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN 0x0 +#define ID_AA64MMFR0_EL1_TGRAN4_LPA2 ID_AA64MMFR0_EL1_TGRAN4_52_BIT #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX 0x7 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN 0x0 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX 0x7 #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN 0x1 +#define ID_AA64MMFR0_EL1_TGRAN16_LPA2 ID_AA64MMFR0_EL1_TGRAN16_52_BIT #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX 0xf

#define ARM64_MIN_PARANGE_BITS 32 @@ -572,6 +913,7 @@ #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT 0x0 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE 0x1 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN 0x2 +#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2 0x3 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX 0x7

#ifdef CONFIG_ARM64_PA_BITS_52 @@ -582,11 +924,13 @@

#if defined(CONFIG_ARM64_4K_PAGES) #define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN4_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_LPA2 ID_AA64MMFR0_EL1_TGRAN4_52_BIT #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT #elif defined(CONFIG_ARM64_16K_PAGES) #define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN16_SHIFT +#define ID_AA64MMFR0_EL1_TGRAN_LPA2 ID_AA64MMFR0_EL1_TGRAN16_52_BIT #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT @@ -610,6 +954,19 @@ #define SYS_GCR_EL1_RRND (BIT(16)) #define SYS_GCR_EL1_EXCL_MASK 0xffffUL

+#ifdef CONFIG_KASAN_HW_TAGS +/* + * KASAN always uses a whole byte for its tags. With CONFIG_KASAN_HW_TAGS it + * only uses tags in the range 0xF0-0xFF, which we map to MTE tags 0x0-0xF. + */ +#define __MTE_TAG_MIN (KASAN_TAG_MIN & 0xf) +#define __MTE_TAG_MAX (KASAN_TAG_MAX & 0xf) +#define __MTE_TAG_INCL GENMASK(__MTE_TAG_MAX, __MTE_TAG_MIN) +#define KERNEL_GCR_EL1_EXCL (SYS_GCR_EL1_EXCL_MASK & ~__MTE_TAG_INCL) +#else +#define KERNEL_GCR_EL1_EXCL SYS_GCR_EL1_EXCL_MASK +#endif + #define KERNEL_GCR_EL1 (SYS_GCR_EL1_RRND | KERNEL_GCR_EL1_EXCL)

/* RGSR_EL1 Definitions */ @@ -716,6 +1073,22 @@

#define PIRx_ELx_PERM(idx, perm) ((perm) << ((idx) * 4))

+/* + * Permission Overlay Extension (POE) permission encodings. + */ +#define POE_NONE UL(0x0) +#define POE_R UL(0x1) +#define POE_X UL(0x2) +#define POE_RX UL(0x3) +#define POE_W UL(0x4) +#define POE_RW UL(0x5) +#define POE_XW UL(0x6) +#define POE_RXW UL(0x7) +#define POE_MASK UL(0xf) + +/* Initial value for Permission Overlay Extension for EL0 */ +#define POR_EL0_INIT POE_RXW + #define ARM64_FEATURE_FIELD_BITS 4

/* Defined for compatibility only, do not add new users. */ @@ -789,15 +1162,21 @@ /* * For registers without architectural names, or simply unsupported by * GAS. + * + * __check_r forces warnings to be generated by the compiler when + * evaluating r which wouldn't normally happen due to being passed to + * the assembler via __stringify(r). */ #define read_sysreg_s(r) ({ \ u64 __val; \ + u32 __maybe_unused __check_r = (u32)(r); \ asm volatile(__mrs_s("%0", r) : "=r" (__val)); \ __val; \ })

#define write_sysreg_s(v, r) do { \ u64 __val = (u64)(v); \ + u32 __maybe_unused __check_r = (u32)(r); \ asm volatile(__msr_s(r, "%x0") : : "rZ" (__val)); \ } while (0)

@@ -827,6 +1206,8 @@ par; \ })

+#define SYS_FIELD_VALUE(reg, field, val) reg##_##field##_##val + #define SYS_FIELD_GET(reg, field, val) \ FIELD_GET(reg##_##field##_MASK, val)

@@ -834,7 +1215,8 @@ FIELD_PREP(reg##_##field##_MASK, val)

#define SYS_FIELD_PREP_ENUM(reg, field, val) \ - FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val) + FIELD_PREP(reg##_##field##_MASK, \ + SYS_FIELD_VALUE(reg, field, val))

#endif

diff --git a/tools/include/linux/kasan-tags.h b/tools/include/linux/kasan-tags.h new file mode 100644 index 000000000000..4f85f562512c --- /dev/null +++ b/tools/include/linux/kasan-tags.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KASAN_TAGS_H +#define _LINUX_KASAN_TAGS_H + +#define KASAN_TAG_KERNEL 0xFF /* native kernel pointers tag */ +#define KASAN_TAG_INVALID 0xFE /* inaccessible memory tag */ +#define KASAN_TAG_MAX 0xFD /* maximum value for random tags */ + +#ifdef CONFIG_KASAN_HW_TAGS +#define KASAN_TAG_MIN 0xF0 /* minimum value for random tags */ +#else +#define KASAN_TAG_MIN 0x00 /* minimum value for random tags */ +#endif + +#endif /* LINUX_KASAN_TAGS_H */

Currently in nVHE, KVM has to check if TRBE is enabled on every guest switch even if it was never used. Because it's a debug feature and is more likely to not be used than used, give KVM the TRBE buffer status to allow a much simpler and faster do-nothing path in the hyp.

This is always called with preemption disabled except for probe/hotplug which gets wrapped with preempt_disable().

Protected mode disables trace regardless of TRBE (because guest_trfcr_el1 is always 0), which was not previously done. HAS_TRBE becomes redundant, but HAS_TRF is now required for this.

Signed-off-by: James Clark james.clark@linaro.org --- arch/arm64/include/asm/kvm_host.h | 10 +++- arch/arm64/kvm/debug.c | 25 ++++++++-- arch/arm64/kvm/hyp/nvhe/debug-sr.c | 51 +++++++++++--------- drivers/hwtracing/coresight/coresight-trbe.c | 5 ++ 4 files changed, 65 insertions(+), 26 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7e3478386351..ba251caa593b 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -611,7 +611,8 @@ struct cpu_sve_state { */ struct kvm_host_data { #define KVM_HOST_DATA_FLAG_HAS_SPE 0 -#define KVM_HOST_DATA_FLAG_HAS_TRBE 1 +#define KVM_HOST_DATA_FLAG_HAS_TRF 1 +#define KVM_HOST_DATA_FLAG_TRBE_ENABLED 2 unsigned long flags;

struct kvm_cpu_context host_ctxt; @@ -657,6 +658,9 @@ struct kvm_host_data { u64 mdcr_el2; } host_debug_state;

+ /* Guest trace filter value */ + u64 guest_trfcr_el1; + /* Number of programmable event counters (PMCR_EL0.N) for this CPU */ unsigned int nr_event_counters; }; @@ -1381,6 +1385,8 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u64 clr); bool kvm_set_pmuserenr(u64 val); +void kvm_enable_trbe(void); +void kvm_disable_trbe(void); #else static inline void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u64 clr) {} @@ -1388,6 +1394,8 @@ static inline bool kvm_set_pmuserenr(u64 val) { return false; } +static inline void kvm_enable_trbe(void) {} +static inline void kvm_disable_trbe(void) {} #endif

void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index dd9e139dfd13..0c340ae7b5d1 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -314,7 +314,26 @@ void kvm_init_host_debug_data(void) !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P)) host_data_set_flag(HAS_SPE);

- if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && - !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) - host_data_set_flag(HAS_TRBE); + if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceFilt_SHIFT)) + host_data_set_flag(HAS_TRF); } + +void kvm_enable_trbe(void) +{ + if (has_vhe() || is_protected_kvm_enabled() || + WARN_ON_ONCE(preemptible())) + return; + + host_data_set_flag(TRBE_ENABLED); +} +EXPORT_SYMBOL_GPL(kvm_enable_trbe); + +void kvm_disable_trbe(void) +{ + if (has_vhe() || is_protected_kvm_enabled() || + WARN_ON_ONCE(preemptible())) + return; + + host_data_clear_flag(TRBE_ENABLED); +} +EXPORT_SYMBOL_GPL(kvm_disable_trbe); diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c index 858bb38e273f..9479bee41801 100644 --- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c @@ -51,32 +51,39 @@ static void __debug_restore_spe(u64 pmscr_el1) write_sysreg_el1(pmscr_el1, SYS_PMSCR); }

-static void __debug_save_trace(u64 *trfcr_el1) +static void __trace_do_switch(u64 *saved_trfcr, u64 new_trfcr) { - *trfcr_el1 = 0; + *saved_trfcr = read_sysreg_el1(SYS_TRFCR); + write_sysreg_el1(new_trfcr, SYS_TRFCR);

- /* Check if the TRBE is enabled */ - if (!(read_sysreg_s(SYS_TRBLIMITR_EL1) & TRBLIMITR_EL1_E)) + /* No need to drain if going to an enabled state or from disabled state */ + if (new_trfcr || !*saved_trfcr) return; - /* - * Prohibit trace generation while we are in guest. - * Since access to TRFCR_EL1 is trapped, the guest can't - * modify the filtering set by the host. - */ - *trfcr_el1 = read_sysreg_el1(SYS_TRFCR); - write_sysreg_el1(0, SYS_TRFCR); + isb(); - /* Drain the trace buffer to memory */ tsb_csync(); }

-static void __debug_restore_trace(u64 trfcr_el1) +static bool __trace_needs_switch(void) { - if (!trfcr_el1) - return; + return host_data_test_flag(TRBE_ENABLED) || + (is_protected_kvm_enabled() && host_data_test_flag(HAS_TRF)); +}

- /* Restore trace filter controls */ - write_sysreg_el1(trfcr_el1, SYS_TRFCR); +static void __trace_switch_to_guest(void) +{ + /* Unsupported with TRBE so disable */ + if (host_data_test_flag(TRBE_ENABLED)) + *host_data_ptr(guest_trfcr_el1) = 0; + + __trace_do_switch(host_data_ptr(host_debug_state.trfcr_el1), + *host_data_ptr(guest_trfcr_el1)); +} + +static void __trace_switch_to_host(void) +{ + __trace_do_switch(host_data_ptr(guest_trfcr_el1), + *host_data_ptr(host_debug_state.trfcr_el1)); }

void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu) @@ -84,9 +91,9 @@ void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu) /* Disable and flush SPE data generation */ if (host_data_test_flag(HAS_SPE)) __debug_save_spe(host_data_ptr(host_debug_state.pmscr_el1)); - /* Disable and flush Self-Hosted Trace generation */ - if (host_data_test_flag(HAS_TRBE)) - __debug_save_trace(host_data_ptr(host_debug_state.trfcr_el1)); + + if (__trace_needs_switch()) + __trace_switch_to_guest(); }

void __debug_switch_to_guest(struct kvm_vcpu *vcpu) @@ -98,8 +105,8 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu) { if (host_data_test_flag(HAS_SPE)) __debug_restore_spe(*host_data_ptr(host_debug_state.pmscr_el1)); - if (host_data_test_flag(HAS_TRBE)) - __debug_restore_trace(*host_data_ptr(host_debug_state.trfcr_el1)); + if (__trace_needs_switch()) + __trace_switch_to_host(); }

void __debug_switch_to_host(struct kvm_vcpu *vcpu) diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c index 96a32b213669..9c0f8c43e6fe 100644 --- a/drivers/hwtracing/coresight/coresight-trbe.c +++ b/drivers/hwtracing/coresight/coresight-trbe.c @@ -18,6 +18,7 @@ #include <asm/barrier.h> #include <asm/cpufeature.h> #include <linux/vmalloc.h> +#include <linux/kvm_host.h>

#include "coresight-self-hosted-trace.h" #include "coresight-trbe.h" @@ -221,6 +222,7 @@ static inline void set_trbe_enabled(struct trbe_cpudata *cpudata, u64 trblimitr) */ trblimitr |= TRBLIMITR_EL1_E; write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); + kvm_enable_trbe();

/* Synchronize the TRBE enable event */ isb(); @@ -239,6 +241,7 @@ static inline void set_trbe_disabled(struct trbe_cpudata *cpudata) */ trblimitr &= ~TRBLIMITR_EL1_E; write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); + kvm_disable_trbe();

if (trbe_needs_drain_after_disable(cpudata)) trbe_drain_buffer(); @@ -253,8 +256,10 @@ static void trbe_drain_and_disable_local(struct trbe_cpudata *cpudata)

static void trbe_reset_local(struct trbe_cpudata *cpudata) { + preempt_disable(); trbe_drain_and_disable_local(cpudata); write_sysreg_s(0, SYS_TRBLIMITR_EL1); + preempt_enable(); write_sysreg_s(0, SYS_TRBPTR_EL1); write_sysreg_s(0, SYS_TRBBASER_EL1); write_sysreg_s(0, SYS_TRBSR_EL1);

From: James Clark james.clark@arm.com

Currently the userspace and kernel filters for guests are never set, so no trace will be generated for them. Add support for tracing guests by passing the desired TRFCR value to KVM so it can be applied to the guest.

By writing either E1TRE or E0TRE, filtering on either guest kernel or guest userspace is also supported. And if both E1TRE and E0TRE are cleared when exclude_guest is set, that option is supported too. This change also brings exclude_host support which is difficult to add as a separate commit without excess churn and resulting in no trace at all.

Testing =======

The addresses were counted with the following:

$ perf report -D | grep -Eo 'EL2|EL1|EL0' | sort | uniq -c

Guest kernel only:

$ perf record -e cs_etm//Gk -a -- true 535 EL1 1 EL2

Guest user only (only 5 addresses because the guest runs slowly in the model):

$ perf record -e cs_etm//Gu -a -- true 5 EL0

Host kernel only:

$ perf record -e cs_etm//Hk -a -- true 3501 EL2

Host userspace only:

$ perf record -e cs_etm//Hu -a -- true 408 EL0 1 EL2

Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: James Clark james.clark@arm.com --- .../coresight/coresight-etm4x-core.c | 43 ++++++++++++++++--- drivers/hwtracing/coresight/coresight-etm4x.h | 2 +- drivers/hwtracing/coresight/coresight-priv.h | 3 ++ 3 files changed, 41 insertions(+), 7 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 66d44a404ad0..afe56e1b9364 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -6,6 +6,7 @@ #include <linux/acpi.h> #include <linux/bitops.h> #include <linux/kernel.h> +#include <linux/kvm_host.h> #include <linux/moduleparam.h> #include <linux/init.h> #include <linux/types.h> @@ -271,9 +272,23 @@ static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata) /* If the CPU doesn't support FEAT_TRF, nothing to do */ if (!drvdata->trfcr) return; + + kvm_clear_trfcr(); cpu_prohibit_trace(); }

+static u64 etm4x_get_kern_user_filter(struct etmv4_drvdata *drvdata) +{ + u64 trfcr = drvdata->trfcr; + + if (drvdata->config.mode & ETM_MODE_EXCL_KERN) + trfcr &= ~TRFCR_ELx_ExTRE; + if (drvdata->config.mode & ETM_MODE_EXCL_USER) + trfcr &= ~TRFCR_ELx_E0TRE; + + return trfcr; +} + /* * etm4x_allow_trace - Allow CPU tracing in the respective ELs, * as configured by the drvdata->config.mode for the current @@ -286,18 +301,28 @@ static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata) */ static void etm4x_allow_trace(struct etmv4_drvdata *drvdata) { - u64 trfcr = drvdata->trfcr; + u64 trfcr, guest_trfcr;

/* If the CPU doesn't support FEAT_TRF, nothing to do */ - if (!trfcr) + if (!drvdata->trfcr) return;

- if (drvdata->config.mode & ETM_MODE_EXCL_KERN) - trfcr &= ~TRFCR_ELx_ExTRE; - if (drvdata->config.mode & ETM_MODE_EXCL_USER) - trfcr &= ~TRFCR_ELx_E0TRE; + if (drvdata->config.mode & ETM_MODE_EXCL_HOST) + trfcr = drvdata->trfcr & ~(TRFCR_ELx_ExTRE | TRFCR_ELx_E0TRE); + else + trfcr = etm4x_get_kern_user_filter(drvdata);

write_trfcr(trfcr); + + /* Set filters for guests and pass to KVM */ + if (drvdata->config.mode & ETM_MODE_EXCL_GUEST) + guest_trfcr = drvdata->trfcr & ~(TRFCR_ELx_ExTRE | TRFCR_ELx_E0TRE); + else + guest_trfcr = etm4x_get_kern_user_filter(drvdata); + + /* TRFCR_EL1 doesn't have CX so mask it out. */ + guest_trfcr &= ~TRFCR_EL2_CX; + kvm_set_trfcr(guest_trfcr); }

#ifdef CONFIG_ETM4X_IMPDEF_FEATURE @@ -655,6 +680,12 @@ static int etm4_parse_event_config(struct coresight_device *csdev, if (attr->exclude_user) config->mode = ETM_MODE_EXCL_USER;

+ if (attr->exclude_host) + config->mode |= ETM_MODE_EXCL_HOST; + + if (attr->exclude_guest) + config->mode |= ETM_MODE_EXCL_GUEST; + /* Always start from the default config */ etm4_set_default_config(config);

diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 9e9165f62e81..1119762b5cec 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -817,7 +817,7 @@ enum etm_impdef_type { * @s_ex_level: Secure ELs where tracing is supported. */ struct etmv4_config { - u32 mode; + u64 mode; u32 pe_sel; u32 cfg; u32 eventctrl0; diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 05f891ca6b5c..76403530f33e 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -42,6 +42,9 @@ extern const struct device_type coresight_dev_type[];

#define ETM_MODE_EXCL_KERN BIT(30) #define ETM_MODE_EXCL_USER BIT(31) +#define ETM_MODE_EXCL_HOST BIT(32) +#define ETM_MODE_EXCL_GUEST BIT(33) + struct cs_pair_attribute { struct device_attribute attr; u32 lo_off;