diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 7c721f22bd..7688ceaf8f 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -2699,8 +2699,7 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync); * + NonSecure PL1 & 0 stage 1 * + NonSecure PL1 & 0 stage 2 * + NonSecure PL2 - * + Secure PL0 - * + Secure PL1 + * + Secure PL1 & 0 * (reminder: for 32 bit EL3, Secure PL1 is *EL3*, not EL1.) * * For QEMU, an mmu_idx is not quite the same as a translation regime because: @@ -2735,19 +2734,21 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync); * * This gives us the following list of cases: * - * EL0 EL1&0 stage 1+2 (aka NS PL0) - * EL1 EL1&0 stage 1+2 (aka NS PL1) - * EL1 EL1&0 stage 1+2 +PAN + * EL0 EL1&0 stage 1+2 (aka NS PL0 PL1&0 stage 1+2) + * EL1 EL1&0 stage 1+2 (aka NS PL1 PL1&0 stage 1+2) + * EL1 EL1&0 stage 1+2 +PAN (aka NS PL1 P1&0 stage 1+2 +PAN) * EL0 EL2&0 * EL2 EL2&0 * EL2 EL2&0 +PAN * EL2 (aka NS PL2) - * EL3 (aka S PL1) + * EL3 (aka AArch32 S PL1 PL1&0) + * AArch32 S PL0 PL1&0 (we call this EL30_0) + * AArch32 S PL1 PL1&0 +PAN (we call this EL30_3_PAN) * Stage2 Secure * Stage2 NonSecure * plus one TLB per Physical address space: S, NS, Realm, Root * - * for a total of 14 different mmu_idx. + * for a total of 16 different mmu_idx. * * R profile CPUs have an MPU, but can use the same set of MMU indexes * as A profile. They only need to distinguish EL0 and EL1 (and @@ -2811,6 +2812,8 @@ typedef enum ARMMMUIdx { ARMMMUIdx_E20_2_PAN = 5 | ARM_MMU_IDX_A, ARMMMUIdx_E2 = 6 | ARM_MMU_IDX_A, ARMMMUIdx_E3 = 7 | ARM_MMU_IDX_A, + ARMMMUIdx_E30_0 = 8 | ARM_MMU_IDX_A, + ARMMMUIdx_E30_3_PAN = 9 | ARM_MMU_IDX_A, /* * Used for second stage of an S12 page table walk, or for descriptor @@ -2818,14 +2821,14 @@ typedef enum ARMMMUIdx { * are in use simultaneously for SecureEL2: the security state for * the S2 ptw is selected by the NS bit from the S1 ptw. */ - ARMMMUIdx_Stage2_S = 8 | ARM_MMU_IDX_A, - ARMMMUIdx_Stage2 = 9 | ARM_MMU_IDX_A, + ARMMMUIdx_Stage2_S = 10 | ARM_MMU_IDX_A, + ARMMMUIdx_Stage2 = 11 | ARM_MMU_IDX_A, /* TLBs with 1-1 mapping to the physical address spaces. */ - ARMMMUIdx_Phys_S = 10 | ARM_MMU_IDX_A, - ARMMMUIdx_Phys_NS = 11 | ARM_MMU_IDX_A, - ARMMMUIdx_Phys_Root = 12 | ARM_MMU_IDX_A, - ARMMMUIdx_Phys_Realm = 13 | ARM_MMU_IDX_A, + ARMMMUIdx_Phys_S = 12 | ARM_MMU_IDX_A, + ARMMMUIdx_Phys_NS = 13 | ARM_MMU_IDX_A, + ARMMMUIdx_Phys_Root = 14 | ARM_MMU_IDX_A, + ARMMMUIdx_Phys_Realm = 15 | ARM_MMU_IDX_A, /* * These are not allocated TLBs and are used only for AT system @@ -2864,6 +2867,8 @@ typedef enum ARMMMUIdxBit { TO_CORE_BIT(E20_2), TO_CORE_BIT(E20_2_PAN), TO_CORE_BIT(E3), + TO_CORE_BIT(E30_0), + TO_CORE_BIT(E30_3_PAN), TO_CORE_BIT(Stage2), TO_CORE_BIT(Stage2_S), diff --git a/target/arm/helper.c b/target/arm/helper.c index 42044ae14b..a0b63a1bce 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -444,6 +444,9 @@ static int alle1_tlbmask(CPUARMState *env) * Note that the 'ALL' scope must invalidate both stage 1 and * stage 2 translations, whereas most other scopes only invalidate * stage 1 translations. + * + * For AArch32 this is only used for TLBIALLNSNH and VTTBR + * writes, so only needs to apply to NS PL1&0, not S PL1&0. */ return (ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_1_PAN | @@ -3762,7 +3765,11 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) /* stage 1 current state PL1: ATS1CPR, ATS1CPW, ATS1CPRP, ATS1CPWP */ switch (el) { case 3: - mmu_idx = ARMMMUIdx_E3; + if (ri->crm == 9 && arm_pan_enabled(env)) { + mmu_idx = ARMMMUIdx_E30_3_PAN; + } else { + mmu_idx = ARMMMUIdx_E3; + } break; case 2: g_assert(ss != ARMSS_Secure); /* ARMv8.4-SecEL2 is 64-bit only */ @@ -3782,7 +3789,7 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) /* stage 1 current state PL0: ATS1CUR, ATS1CUW */ switch (el) { case 3: - mmu_idx = ARMMMUIdx_E10_0; + mmu_idx = ARMMMUIdx_E30_0; break; case 2: g_assert(ss != ARMSS_Secure); /* ARMv8.4-SecEL2 is 64-bit only */ @@ -4892,11 +4899,14 @@ static int vae1_tlbmask(CPUARMState *env) uint64_t hcr = arm_hcr_el2_eff(env); uint16_t mask; + assert(arm_feature(env, ARM_FEATURE_AARCH64)); + if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) { mask = ARMMMUIdxBit_E20_2 | ARMMMUIdxBit_E20_2_PAN | ARMMMUIdxBit_E20_0; } else { + /* This is AArch64 only, so we don't need to touch the EL30_x TLBs */ mask = ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_1_PAN | ARMMMUIdxBit_E10_0; @@ -4935,6 +4945,8 @@ static int vae1_tlbbits(CPUARMState *env, uint64_t addr) uint64_t hcr = arm_hcr_el2_eff(env); ARMMMUIdx mmu_idx; + assert(arm_feature(env, ARM_FEATURE_AARCH64)); + /* Only the regime of the mmu_idx below is significant. */ if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) { mmu_idx = ARMMMUIdx_E20_0; @@ -11768,10 +11780,20 @@ void arm_cpu_do_interrupt(CPUState *cs) uint64_t arm_sctlr(CPUARMState *env, int el) { - /* Only EL0 needs to be adjusted for EL1&0 or EL2&0. */ + /* Only EL0 needs to be adjusted for EL1&0 or EL2&0 or EL3&0 */ if (el == 0) { ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, 0); - el = mmu_idx == ARMMMUIdx_E20_0 ? 2 : 1; + switch (mmu_idx) { + case ARMMMUIdx_E20_0: + el = 2; + break; + case ARMMMUIdx_E30_0: + el = 3; + break; + default: + el = 1; + break; + } } return env->cp15.sctlr_el[el]; } @@ -12439,6 +12461,7 @@ int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) switch (mmu_idx) { case ARMMMUIdx_E10_0: case ARMMMUIdx_E20_0: + case ARMMMUIdx_E30_0: return 0; case ARMMMUIdx_E10_1: case ARMMMUIdx_E10_1_PAN: @@ -12448,6 +12471,7 @@ int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) case ARMMMUIdx_E20_2_PAN: return 2; case ARMMMUIdx_E3: + case ARMMMUIdx_E30_3_PAN: return 3; default: g_assert_not_reached(); @@ -12476,6 +12500,9 @@ ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el) hcr = arm_hcr_el2_eff(env); if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) { idx = ARMMMUIdx_E20_0; + } else if (arm_is_secure_below_el3(env) && + !arm_el_is_aa64(env, 3)) { + idx = ARMMMUIdx_E30_0; } else { idx = ARMMMUIdx_E10_0; } @@ -12500,6 +12527,9 @@ ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el) } break; case 3: + if (!arm_el_is_aa64(env, 3) && arm_pan_enabled(env)) { + return ARMMMUIdx_E30_3_PAN; + } return ARMMMUIdx_E3; default: g_assert_not_reached(); diff --git a/target/arm/internals.h b/target/arm/internals.h index f078e5377e..7867778150 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -835,7 +835,16 @@ static inline void arm_call_el_change_hook(ARMCPU *cpu) } } -/* Return true if this address translation regime has two ranges. */ +/* + * Return true if this address translation regime has two ranges. + * Note that this will not return the correct answer for AArch32 + * Secure PL1&0 (i.e. mmu indexes E3, E30_0, E30_3_PAN), but it is + * never called from a context where EL3 can be AArch32. (The + * correct return value for ARMMMUIdx_E3 would be different for + * that case, so we can't just make the function return the + * correct value anyway; we would need an extra "bool e3_is_aarch32" + * argument which all the current callsites would pass as 'false'.) + */ static inline bool regime_has_2_ranges(ARMMMUIdx mmu_idx) { switch (mmu_idx) { @@ -860,6 +869,7 @@ static inline bool regime_is_pan(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_Stage1_E1_PAN: case ARMMMUIdx_E10_1_PAN: case ARMMMUIdx_E20_2_PAN: + case ARMMMUIdx_E30_3_PAN: return true; default: return false; @@ -883,10 +893,11 @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_E2: return 2; case ARMMMUIdx_E3: + case ARMMMUIdx_E30_0: + case ARMMMUIdx_E30_3_PAN: return 3; case ARMMMUIdx_E10_0: case ARMMMUIdx_Stage1_E0: - return arm_el_is_aa64(env, 3) || !arm_is_secure_below_el3(env) ? 1 : 3; case ARMMMUIdx_Stage1_E1: case ARMMMUIdx_Stage1_E1_PAN: case ARMMMUIdx_E10_1: @@ -910,6 +921,7 @@ static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx) switch (mmu_idx) { case ARMMMUIdx_E10_0: case ARMMMUIdx_E20_0: + case ARMMMUIdx_E30_0: case ARMMMUIdx_Stage1_E0: case ARMMMUIdx_MUser: case ARMMMUIdx_MSUser: diff --git a/target/arm/ptw.c b/target/arm/ptw.c index f2c9e5a422..a244db98ee 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -264,6 +264,8 @@ static bool regime_translation_disabled(CPUARMState *env, ARMMMUIdx mmu_idx, case ARMMMUIdx_E20_2_PAN: case ARMMMUIdx_E2: case ARMMMUIdx_E3: + case ARMMMUIdx_E30_0: + case ARMMMUIdx_E30_3_PAN: break; case ARMMMUIdx_Phys_S: @@ -3603,6 +3605,8 @@ bool get_phys_addr(CPUARMState *env, vaddr address, ss = ARMSS_Secure; break; case ARMMMUIdx_E3: + case ARMMMUIdx_E30_0: + case ARMMMUIdx_E30_3_PAN: if (arm_feature(env, ARM_FEATURE_AARCH64) && cpu_isar_feature(aa64_rme, env_archcpu(env))) { ss = ARMSS_Root; diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index c199b69fbf..7d47afff6d 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -858,7 +858,19 @@ void HELPER(tidcp_el0)(CPUARMState *env, uint32_t syndrome) { /* See arm_sctlr(), but we also need the sctlr el. */ ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, 0); - int target_el = mmu_idx == ARMMMUIdx_E20_0 ? 2 : 1; + int target_el; + + switch (mmu_idx) { + case ARMMMUIdx_E20_0: + target_el = 2; + break; + case ARMMMUIdx_E30_0: + target_el = 3; + break; + default: + target_el = 1; + break; + } /* * The bit is not valid unless the target el is aa64, but since the diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index dc49a8d806..9b0decd4e3 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -229,6 +229,9 @@ static inline int get_a32_user_mem_index(DisasContext *s) */ switch (s->mmu_idx) { case ARMMMUIdx_E3: + case ARMMMUIdx_E30_0: + case ARMMMUIdx_E30_3_PAN: + return arm_to_core_mmu_idx(ARMMMUIdx_E30_0); case ARMMMUIdx_E2: /* this one is UNPREDICTABLE */ case ARMMMUIdx_E10_0: case ARMMMUIdx_E10_1: