diff options
author | Yonghee Han <onstudy@samsung.com> | 2016-07-27 16:39:12 +0900 |
---|---|---|
committer | Yonghee Han <onstudy@samsung.com> | 2016-07-27 16:47:03 +0900 |
commit | a3b133b0ea0696e42fd876b9a803e28bc6ef5299 (patch) | |
tree | 68d7537fb9ede28b2e4d2b9f44eb70988279b8ba /target-arm | |
parent | 0d6a2f7e595218b5632ba7005128470e65138951 (diff) | |
download | qemu-a3b133b0ea0696e42fd876b9a803e28bc6ef5299.tar.gz qemu-a3b133b0ea0696e42fd876b9a803e28bc6ef5299.tar.bz2 qemu-a3b133b0ea0696e42fd876b9a803e28bc6ef5299.zip |
Imported Upstream version 2.3.1upstream/2.3.1
Change-Id: I2161522ea1d7ff10cd1d697609d473243c05e1df
Diffstat (limited to 'target-arm')
-rw-r--r-- | target-arm/arm-semi.c | 11 | ||||
-rw-r--r-- | target-arm/cpu-qom.h | 2 | ||||
-rw-r--r-- | target-arm/cpu.c | 80 | ||||
-rw-r--r-- | target-arm/cpu.h | 511 | ||||
-rw-r--r-- | target-arm/cpu64.c | 40 | ||||
-rw-r--r-- | target-arm/crypto_helper.c | 114 | ||||
-rw-r--r-- | target-arm/helper-a64.c | 25 | ||||
-rw-r--r-- | target-arm/helper.c | 1833 | ||||
-rw-r--r-- | target-arm/internals.h | 11 | ||||
-rw-r--r-- | target-arm/kvm.c | 159 | ||||
-rw-r--r-- | target-arm/kvm32.c | 104 | ||||
-rw-r--r-- | target-arm/kvm64.c | 189 | ||||
-rw-r--r-- | target-arm/kvm_arm.h | 39 | ||||
-rw-r--r-- | target-arm/machine.c | 26 | ||||
-rw-r--r-- | target-arm/op_helper.c | 10 | ||||
-rw-r--r-- | target-arm/translate-a64.c | 84 | ||||
-rw-r--r-- | target-arm/translate.c | 148 | ||||
-rw-r--r-- | target-arm/translate.h | 8 |
18 files changed, 2586 insertions, 808 deletions
diff --git a/target-arm/arm-semi.c b/target-arm/arm-semi.c index ebb523552..a8b83e691 100644 --- a/target-arm/arm-semi.c +++ b/target-arm/arm-semi.c @@ -58,6 +58,10 @@ #define TARGET_SYS_HEAPINFO 0x16 #define TARGET_SYS_EXIT 0x18 +/* ADP_Stopped_ApplicationExit is used for exit(0), + * anything else is implemented as exit(1) */ +#define ADP_Stopped_ApplicationExit (0x20026) + #ifndef O_BINARY #define O_BINARY 0 #endif @@ -551,8 +555,11 @@ uint32_t do_arm_semihosting(CPUARMState *env) return 0; } case TARGET_SYS_EXIT: - gdb_exit(env, 0); - exit(0); + /* ARM specifies only Stopped_ApplicationExit as normal + * exit, everything else is considered an error */ + ret = (args == ADP_Stopped_ApplicationExit) ? 0 : 1; + gdb_exit(env, ret); + exit(ret); default: fprintf(stderr, "qemu: Unsupported SemiHosting SWI 0x%02x\n", nr); cpu_dump_state(cs, stderr, fprintf, 0); diff --git a/target-arm/cpu-qom.h b/target-arm/cpu-qom.h index dcfda7dfc..ed5a6441b 100644 --- a/target-arm/cpu-qom.h +++ b/target-arm/cpu-qom.h @@ -100,6 +100,8 @@ typedef struct ARMCPU { bool start_powered_off; /* CPU currently in PSCI powered-off state */ bool powered_off; + /* CPU has security extension */ + bool has_el3; /* PSCI conduit used to invoke PSCI methods * 0 - disabled, 1 - smc, 2 - hvc diff --git a/target-arm/cpu.c b/target-arm/cpu.c index 5ce7350ce..986f04cfd 100644 --- a/target-arm/cpu.c +++ b/target-arm/cpu.c @@ -109,11 +109,18 @@ static void arm_cpu_reset(CPUState *s) #if defined(CONFIG_USER_ONLY) env->pstate = PSTATE_MODE_EL0t; /* Userspace expects access to DC ZVA, CTL_EL0 and the cache ops */ - env->cp15.c1_sys |= SCTLR_UCT | SCTLR_UCI | SCTLR_DZE; + env->cp15.sctlr_el[1] |= SCTLR_UCT | SCTLR_UCI | SCTLR_DZE; /* and to the FP/Neon instructions */ env->cp15.c1_coproc = deposit64(env->cp15.c1_coproc, 20, 2, 3); #else - env->pstate = PSTATE_MODE_EL1h; + /* Reset into the highest available EL */ + if (arm_feature(env, ARM_FEATURE_EL3)) { + env->pstate = PSTATE_MODE_EL3h; + } else if (arm_feature(env, ARM_FEATURE_EL2)) { + env->pstate = PSTATE_MODE_EL2h; + } else { + env->pstate = PSTATE_MODE_EL1h; + } env->pc = cpu->rvbar; #endif } else { @@ -167,7 +174,11 @@ static void arm_cpu_reset(CPUState *s) env->thumb = initial_pc & 1; } - if (env->cp15.c1_sys & SCTLR_V) { + /* AArch32 has a hard highvec setting of 0xFFFF0000. If we are currently + * executing as AArch32 then check if highvecs are enabled and + * adjust the PC accordingly. + */ + if (A32_BANKED_CURRENT_REG_GET(env, sctlr) & SCTLR_V) { env->regs[15] = 0xFFFF0000; } @@ -316,6 +327,29 @@ static void arm_cpu_kvm_set_irq(void *opaque, int irq, int level) kvm_set_irq(kvm_state, kvm_irq, level ? 1 : 0); #endif } + +static bool arm_cpu_is_big_endian(CPUState *cs) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + int cur_el; + + cpu_synchronize_state(cs); + + /* In 32bit guest endianness is determined by looking at CPSR's E bit */ + if (!is_a64(env)) { + return (env->uncached_cpsr & CPSR_E) ? 1 : 0; + } + + cur_el = arm_current_el(env); + + if (cur_el == 0) { + return (env->cp15.sctlr_el[1] & SCTLR_E0E) != 0; + } + + return (env->cp15.sctlr_el[cur_el] & SCTLR_EE) != 0; +} + #endif static inline void set_feature(CPUARMState *env, int feature) @@ -323,6 +357,11 @@ static inline void set_feature(CPUARMState *env, int feature) env->features |= 1ULL << feature; } +static inline void unset_feature(CPUARMState *env, int feature) +{ + env->features &= ~(1ULL << feature); +} + static void arm_cpu_initfn(Object *obj) { CPUState *cs = CPU(obj); @@ -379,6 +418,9 @@ static Property arm_cpu_reset_hivecs_property = static Property arm_cpu_rvbar_property = DEFINE_PROP_UINT64("rvbar", ARMCPU, rvbar, 0); +static Property arm_cpu_has_el3_property = + DEFINE_PROP_BOOL("has_el3", ARMCPU, has_el3, true); + static void arm_cpu_post_init(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); @@ -398,6 +440,14 @@ static void arm_cpu_post_init(Object *obj) qdev_property_add_static(DEVICE(obj), &arm_cpu_rvbar_property, &error_abort); } + + if (arm_feature(&cpu->env, ARM_FEATURE_EL3)) { + /* Add the has_el3 state CPU property only if EL3 is allowed. This will + * prevent "has_el3" from existing on CPUs which cannot support EL3. + */ + qdev_property_add_static(DEVICE(obj), &arm_cpu_has_el3_property, + &error_abort); + } } static void arm_cpu_finalizefn(Object *obj) @@ -467,6 +517,18 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) cpu->reset_sctlr |= (1 << 13); } + if (!cpu->has_el3) { + /* If the has_el3 CPU property is disabled then we need to disable the + * feature. + */ + unset_feature(env, ARM_FEATURE_EL3); + + /* Disable the security extension feature bits in the processor feature + * register as well. This is id_pfr1[7:4]. + */ + cpu->id_pfr1 &= ~0xf0; + } + register_cp_regs_for_features(cpu); arm_cpu_register_gdb_regs_for_features(cpu); @@ -482,13 +544,16 @@ static ObjectClass *arm_cpu_class_by_name(const char *cpu_model) { ObjectClass *oc; char *typename; + char **cpuname; if (!cpu_model) { return NULL; } - typename = g_strdup_printf("%s-" TYPE_ARM_CPU, cpu_model); + cpuname = g_strsplit(cpu_model, ",", 1); + typename = g_strdup_printf("%s-" TYPE_ARM_CPU, cpuname[0]); oc = object_class_by_name(typename); + g_strfreev(cpuname); g_free(typename); if (!oc || !object_class_dynamic_cast(oc, TYPE_ARM_CPU) || object_class_is_abstract(oc)) { @@ -548,7 +613,7 @@ static void arm1026_initfn(Object *obj) ARMCPRegInfo ifar = { .name = "IFAR", .cp = 15, .crn = 6, .crm = 0, .opc1 = 0, .opc2 = 1, .access = PL1_RW, - .fieldoffset = offsetofhigh32(CPUARMState, cp15.far_el[1]), + .fieldoffset = offsetof(CPUARMState, cp15.ifar_ns), .resetvalue = 0 }; define_one_arm_cp_reg(cpu, &ifar); @@ -636,6 +701,7 @@ static void arm1176_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG); set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS); + set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->midr = 0x410fb767; cpu->reset_fpsid = 0x410120b5; cpu->mvfr0 = 0x11111111; @@ -724,6 +790,7 @@ static void cortex_a8_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); + set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->midr = 0x410fc080; cpu->reset_fpsid = 0x410330c0; cpu->mvfr0 = 0x11110222; @@ -791,6 +858,7 @@ static void cortex_a9_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_VFP_FP16); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); + set_feature(&cpu->env, ARM_FEATURE_EL3); /* Note that A9 supports the MP extensions even for * A9UP and single-core A9MP (which are both different * and valid configurations; we don't model A9UP). @@ -858,6 +926,7 @@ static void cortex_a15_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_LPAE); + set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->kvm_target = QEMU_KVM_ARM_TARGET_CORTEX_A15; cpu->midr = 0x412fc0f1; cpu->reset_fpsid = 0x410430f0; @@ -1153,6 +1222,7 @@ static void arm_cpu_class_init(ObjectClass *oc, void *data) cc->do_interrupt = arm_cpu_do_interrupt; cc->get_phys_page_debug = arm_cpu_get_phys_page_debug; cc->vmsd = &vmstate_arm_cpu; + cc->virtio_is_big_endian = arm_cpu_is_big_endian; #endif cc->gdb_num_core_regs = 26; cc->gdb_core_xml_file = "arm-core.xml"; diff --git a/target-arm/cpu.h b/target-arm/cpu.h index 7f800908f..083211ce3 100644 --- a/target-arm/cpu.h +++ b/target-arm/cpu.h @@ -32,6 +32,8 @@ # define ELF_MACHINE EM_ARM #endif +#define TARGET_IS_BIENDIAN 1 + #define CPUArchState struct CPUARMState #include "qemu-common.h" @@ -39,8 +41,6 @@ #include "fpu/softfloat.h" -#define TARGET_HAS_ICE 1 - #define EXCP_UDEF 1 /* undefined instruction */ #define EXCP_SWI 2 /* software interrupt */ #define EXCP_PREFETCH_ABORT 3 @@ -100,7 +100,7 @@ typedef uint32_t ARMReadCPFunc(void *opaque, int cp_info, struct arm_boot_info; -#define NB_MMU_MODES 4 +#define NB_MMU_MODES 7 /* We currently assume float and double are IEEE single and double precision respectively. @@ -120,6 +120,12 @@ typedef struct ARMGenericTimer { #define GTIMER_VIRT 1 #define NUM_GTIMERS 2 +typedef struct { + uint64_t raw_tcr; + uint32_t mask; + uint32_t base_mask; +} TCR; + typedef struct CPUARMState { /* Regs for current mode. */ uint32_t regs[16]; @@ -177,28 +183,111 @@ typedef struct CPUARMState { /* System control coprocessor (cp15) */ struct { uint32_t c0_cpuid; - uint64_t c0_cssel; /* Cache size selection. */ - uint64_t c1_sys; /* System control register. */ + union { /* Cache size selection */ + struct { + uint64_t _unused_csselr0; + uint64_t csselr_ns; + uint64_t _unused_csselr1; + uint64_t csselr_s; + }; + uint64_t csselr_el[4]; + }; + union { /* System control register. */ + struct { + uint64_t _unused_sctlr; + uint64_t sctlr_ns; + uint64_t hsctlr; + uint64_t sctlr_s; + }; + uint64_t sctlr_el[4]; + }; uint64_t c1_coproc; /* Coprocessor access register. */ uint32_t c1_xscaleauxcr; /* XScale auxiliary control register. */ - uint64_t ttbr0_el1; /* MMU translation table base 0. */ - uint64_t ttbr1_el1; /* MMU translation table base 1. */ - uint64_t c2_control; /* MMU translation table base control. */ - uint32_t c2_mask; /* MMU translation table base selection mask. */ - uint32_t c2_base_mask; /* MMU translation table base 0 mask. */ + uint64_t sder; /* Secure debug enable register. */ + uint32_t nsacr; /* Non-secure access control register. */ + union { /* MMU translation table base 0. */ + struct { + uint64_t _unused_ttbr0_0; + uint64_t ttbr0_ns; + uint64_t _unused_ttbr0_1; + uint64_t ttbr0_s; + }; + uint64_t ttbr0_el[4]; + }; + union { /* MMU translation table base 1. */ + struct { + uint64_t _unused_ttbr1_0; + uint64_t ttbr1_ns; + uint64_t _unused_ttbr1_1; + uint64_t ttbr1_s; + }; + uint64_t ttbr1_el[4]; + }; + /* MMU translation table base control. */ + TCR tcr_el[4]; uint32_t c2_data; /* MPU data cachable bits. */ uint32_t c2_insn; /* MPU instruction cachable bits. */ - uint32_t c3; /* MMU domain access control register - MPU write buffer control. */ + union { /* MMU domain access control register + * MPU write buffer control. + */ + struct { + uint64_t dacr_ns; + uint64_t dacr_s; + }; + struct { + uint64_t dacr32_el2; + }; + }; uint32_t pmsav5_data_ap; /* PMSAv5 MPU data access permissions */ uint32_t pmsav5_insn_ap; /* PMSAv5 MPU insn access permissions */ uint64_t hcr_el2; /* Hypervisor configuration register */ uint64_t scr_el3; /* Secure configuration register. */ - uint32_t ifsr_el2; /* Fault status registers. */ - uint64_t esr_el[4]; + union { /* Fault status registers. */ + struct { + uint64_t ifsr_ns; + uint64_t ifsr_s; + }; + struct { + uint64_t ifsr32_el2; + }; + }; + union { + struct { + uint64_t _unused_dfsr; + uint64_t dfsr_ns; + uint64_t hsr; + uint64_t dfsr_s; + }; + uint64_t esr_el[4]; + }; uint32_t c6_region[8]; /* MPU base/size registers. */ - uint64_t far_el[4]; /* Fault address registers. */ - uint64_t par_el1; /* Translation result. */ + union { /* Fault address registers. */ + struct { + uint64_t _unused_far0; +#ifdef HOST_WORDS_BIGENDIAN + uint32_t ifar_ns; + uint32_t dfar_ns; + uint32_t ifar_s; + uint32_t dfar_s; +#else + uint32_t dfar_ns; + uint32_t ifar_ns; + uint32_t dfar_s; + uint32_t ifar_s; +#endif + uint64_t _unused_far3; + }; + uint64_t far_el[4]; + }; + union { /* Translation result. */ + struct { + uint64_t _unused_par_0; + uint64_t par_ns; + uint64_t _unused_par_1; + uint64_t par_s; + }; + uint64_t par_el[4]; + }; uint32_t c9_insn; /* Cache lockdown registers. */ uint32_t c9_data; uint64_t c9_pmcr; /* performance monitor control register */ @@ -207,13 +296,67 @@ typedef struct CPUARMState { uint32_t c9_pmxevtyper; /* perf monitor event type */ uint32_t c9_pmuserenr; /* perf monitor user enable */ uint32_t c9_pminten; /* perf monitor interrupt enables */ - uint64_t mair_el1; - uint64_t vbar_el[4]; /* vector base address register */ - uint32_t c13_fcse; /* FCSE PID. */ - uint64_t contextidr_el1; /* Context ID. */ - uint64_t tpidr_el0; /* User RW Thread register. */ - uint64_t tpidrro_el0; /* User RO Thread register. */ - uint64_t tpidr_el1; /* Privileged Thread register. */ + union { /* Memory attribute redirection */ + struct { +#ifdef HOST_WORDS_BIGENDIAN + uint64_t _unused_mair_0; + uint32_t mair1_ns; + uint32_t mair0_ns; + uint64_t _unused_mair_1; + uint32_t mair1_s; + uint32_t mair0_s; +#else + uint64_t _unused_mair_0; + uint32_t mair0_ns; + uint32_t mair1_ns; + uint64_t _unused_mair_1; + uint32_t mair0_s; + uint32_t mair1_s; +#endif + }; + uint64_t mair_el[4]; + }; + union { /* vector base address register */ + struct { + uint64_t _unused_vbar; + uint64_t vbar_ns; + uint64_t hvbar; + uint64_t vbar_s; + }; + uint64_t vbar_el[4]; + }; + uint32_t mvbar; /* (monitor) vector base address register */ + struct { /* FCSE PID. */ + uint32_t fcseidr_ns; + uint32_t fcseidr_s; + }; + union { /* Context ID. */ + struct { + uint64_t _unused_contextidr_0; + uint64_t contextidr_ns; + uint64_t _unused_contextidr_1; + uint64_t contextidr_s; + }; + uint64_t contextidr_el[4]; + }; + union { /* User RW Thread register. */ + struct { + uint64_t tpidrurw_ns; + uint64_t tpidrprw_ns; + uint64_t htpidr; + uint64_t _tpidr_el3; + }; + uint64_t tpidr_el[4]; + }; + /* The secure banks of these registers don't map anywhere */ + uint64_t tpidrurw_s; + uint64_t tpidrprw_s; + uint64_t tpidruro_s; + + union { /* User RO Thread register. */ + uint64_t tpidruro_ns; + uint64_t tpidrro_el[1]; + }; uint64_t c14_cntfrq; /* Counter Frequency register */ uint64_t c14_cntkctl; /* Timer Control register */ ARMGenericTimer c14_timer[NUM_GTIMERS]; @@ -352,6 +495,8 @@ typedef struct CPUARMState { ARMCPU *cpu_arm_init(const char *cpu_model); int cpu_arm_exec(CPUARMState *s); uint32_t do_arm_semihosting(CPUARMState *env); +void aarch64_sync_32_to_64(CPUARMState *env); +void aarch64_sync_64_to_32(CPUARMState *env); static inline bool is_a64(CPUARMState *env) { @@ -817,6 +962,49 @@ static inline bool arm_el_is_aa64(CPUARMState *env, int el) return arm_feature(env, ARM_FEATURE_AARCH64); } +/* Function for determing whether guest cp register reads and writes should + * access the secure or non-secure bank of a cp register. When EL3 is + * operating in AArch32 state, the NS-bit determines whether the secure + * instance of a cp register should be used. When EL3 is AArch64 (or if + * it doesn't exist at all) then there is no register banking, and all + * accesses are to the non-secure version. + */ +static inline bool access_secure_reg(CPUARMState *env) +{ + bool ret = (arm_feature(env, ARM_FEATURE_EL3) && + !arm_el_is_aa64(env, 3) && + !(env->cp15.scr_el3 & SCR_NS)); + + return ret; +} + +/* Macros for accessing a specified CP register bank */ +#define A32_BANKED_REG_GET(_env, _regname, _secure) \ + ((_secure) ? (_env)->cp15._regname##_s : (_env)->cp15._regname##_ns) + +#define A32_BANKED_REG_SET(_env, _regname, _secure, _val) \ + do { \ + if (_secure) { \ + (_env)->cp15._regname##_s = (_val); \ + } else { \ + (_env)->cp15._regname##_ns = (_val); \ + } \ + } while (0) + +/* Macros for automatically accessing a specific CP register bank depending on + * the current secure state of the system. These macros are not intended for + * supporting instruction translation reads/writes as these are dependent + * solely on the SCR.NS bit and not the mode. + */ +#define A32_BANKED_CURRENT_REG_GET(_env, _regname) \ + A32_BANKED_REG_GET((_env), _regname, \ + ((!arm_el_is_aa64((_env), 3) && arm_is_secure(_env)))) + +#define A32_BANKED_CURRENT_REG_SET(_env, _regname, _val) \ + A32_BANKED_REG_SET((_env), _regname, \ + ((!arm_el_is_aa64((_env), 3) && arm_is_secure(_env))), \ + (_val)) + void arm_cpu_list(FILE *f, fprintf_function cpu_fprintf); unsigned int arm_excp_target_el(CPUState *cs, unsigned int excp_idx); @@ -836,6 +1024,7 @@ void armv7m_nvic_complete_irq(void *opaque, int irq); * Crn, Crm, opc1, opc2 fields * 32 or 64 bit register (ie is it accessed via MRC/MCR * or via MRRC/MCRR?) + * non-secure/secure bank (AArch32 only) * We allow 4 bits for opc1 because MRRC/MCRR have a 4 bit field. * (In this case crn and opc2 should be zero.) * For AArch64, there is no 32/64 bit size distinction; @@ -853,9 +1042,16 @@ void armv7m_nvic_complete_irq(void *opaque, int irq); #define CP_REG_AA64_SHIFT 28 #define CP_REG_AA64_MASK (1 << CP_REG_AA64_SHIFT) -#define ENCODE_CP_REG(cp, is64, crn, crm, opc1, opc2) \ - (((cp) << 16) | ((is64) << 15) | ((crn) << 11) | \ - ((crm) << 7) | ((opc1) << 3) | (opc2)) +/* To enable banking of coprocessor registers depending on ns-bit we + * add a bit to distinguish between secure and non-secure cpregs in the + * hashtable. + */ +#define CP_REG_NS_SHIFT 29 +#define CP_REG_NS_MASK (1 << CP_REG_NS_SHIFT) + +#define ENCODE_CP_REG(cp, is64, ns, crn, crm, opc1, opc2) \ + ((ns) << CP_REG_NS_SHIFT | ((cp) << 16) | ((is64) << 15) | \ + ((crn) << 11) | ((crm) << 7) | ((opc1) << 3) | (opc2)) #define ENCODE_AA64_CP_REG(cp, crn, crm, op0, op1, op2) \ (CP_REG_AA64_MASK | \ @@ -874,8 +1070,15 @@ static inline uint32_t kvm_to_cpreg_id(uint64_t kvmid) uint32_t cpregid = kvmid; if ((kvmid & CP_REG_ARCH_MASK) == CP_REG_ARM64) { cpregid |= CP_REG_AA64_MASK; - } else if ((kvmid & CP_REG_SIZE_MASK) == CP_REG_SIZE_U64) { - cpregid |= (1 << 15); + } else { + if ((kvmid & CP_REG_SIZE_MASK) == CP_REG_SIZE_U64) { + cpregid |= (1 << 15); + } + + /* KVM is always non-secure so add the NS flag on AArch32 register + * entries. + */ + cpregid |= 1 << CP_REG_NS_SHIFT; } return cpregid; } @@ -911,8 +1114,14 @@ static inline uint64_t cpreg_to_kvm_id(uint32_t cpregid) * a register definition to override a previous definition for the * same (cp, is64, crn, crm, opc1, opc2) tuple: either the new or the * old must have the OVERRIDE bit set. - * NO_MIGRATE indicates that this register should be ignored for migration; - * (eg because any state is accessed via some other coprocessor register). + * ALIAS indicates that this register is an alias view of some underlying + * state which is also visible via another register, and that the other + * register is handling migration; registers marked ALIAS will not be migrated + * but may have their state set by syncing of register state from KVM. + * NO_RAW indicates that this register has no underlying state and does not + * support raw access for state saving/loading; it will not be used for either + * migration or KVM state synchronization. (Typically this is for "registers" + * which are actually used as instructions for cache maintenance and so on.) * IO indicates that this register does I/O and therefore its accesses * need to be surrounded by gen_io_start()/gen_io_end(). In particular, * registers which implement clocks or timers require this. @@ -922,8 +1131,9 @@ static inline uint64_t cpreg_to_kvm_id(uint32_t cpregid) #define ARM_CP_64BIT 4 #define ARM_CP_SUPPRESS_TB_END 8 #define ARM_CP_OVERRIDE 16 -#define ARM_CP_NO_MIGRATE 32 +#define ARM_CP_ALIAS 32 #define ARM_CP_IO 64 +#define ARM_CP_NO_RAW 128 #define ARM_CP_NOP (ARM_CP_SPECIAL | (1 << 8)) #define ARM_CP_WFI (ARM_CP_SPECIAL | (2 << 8)) #define ARM_CP_NZCV (ARM_CP_SPECIAL | (3 << 8)) @@ -933,7 +1143,7 @@ static inline uint64_t cpreg_to_kvm_id(uint32_t cpregid) /* Used only as a terminator for ARMCPRegInfo lists */ #define ARM_CP_SENTINEL 0xffff /* Mask of only the flag bits in a type field */ -#define ARM_CP_FLAG_MASK 0x7f +#define ARM_CP_FLAG_MASK 0xff /* Valid values for ARMCPRegInfo state field, indicating which of * the AArch32 and AArch64 execution states this register is visible in. @@ -950,6 +1160,21 @@ enum { ARM_CP_STATE_BOTH = 2, }; +/* ARM CP register secure state flags. These flags identify security state + * attributes for a given CP register entry. + * The existence of both or neither secure and non-secure flags indicates that + * the register has both a secure and non-secure hash entry. A single one of + * these flags causes the register to only be hashed for the specified + * security state. + * Although definitions may have any combination of the S/NS bits, each + * registered entry will only have one to identify whether the entry is secure + * or non-secure. + */ +enum { + ARM_CP_SECSTATE_S = (1 << 0), /* bit[0]: Secure state register */ + ARM_CP_SECSTATE_NS = (1 << 1), /* bit[1]: Non-secure state register */ +}; + /* Return true if cptype is a valid type field. This is used to try to * catch errors where the sentinel has been accidentally left off the end * of a list of registers. @@ -997,6 +1222,10 @@ static inline bool cptype_valid(int cptype) */ static inline int arm_current_el(CPUARMState *env) { + if (arm_feature(env, ARM_FEATURE_M)) { + return !((env->v7m.exception == 0) && (env->v7m.control & 1)); + } + if (is_a64(env)) { return extract32(env->pstate, 2, 2); } @@ -1084,6 +1313,8 @@ struct ARMCPRegInfo { int type; /* Access rights: PL*_[RW] */ int access; + /* Security state: ARM_CP_SECSTATE_* bits/values */ + int secure; /* The opaque pointer passed to define_arm_cp_regs_with_opaque() when * this register was defined: can be used to hand data through to the * register read/write functions, since they are passed the ARMCPRegInfo*. @@ -1093,12 +1324,27 @@ struct ARMCPRegInfo { * fieldoffset is non-zero, the reset value of the register. */ uint64_t resetvalue; - /* Offset of the field in CPUARMState for this register. This is not - * needed if either: + /* Offset of the field in CPUARMState for this register. + * + * This is not needed if either: * 1. type is ARM_CP_CONST or one of the ARM_CP_SPECIALs * 2. both readfn and writefn are specified */ ptrdiff_t fieldoffset; /* offsetof(CPUARMState, field) */ + + /* Offsets of the secure and non-secure fields in CPUARMState for the + * register if it is banked. These fields are only used during the static + * registration of a register. During hashing the bank associated + * with a given security state is copied to fieldoffset which is used from + * there on out. + * + * It is expected that register definitions use either fieldoffset or + * bank_fieldoffsets in the definition but not both. It is also expected + * that both bank offsets are set when defining a banked register. This + * use indicates that a register is banked. + */ + ptrdiff_t bank_fieldoffsets[2]; + /* Function for making any access checks for this register in addition to * those specified by the 'access' permissions bits. If NULL, no extra * checks required. The access check is performed at runtime, not at @@ -1247,27 +1493,50 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx) CPUARMState *env = cs->env_ptr; unsigned int cur_el = arm_current_el(env); unsigned int target_el = arm_excp_target_el(cs, excp_idx); - /* FIXME: Use actual secure state. */ - bool secure = false; - /* If in EL1/0, Physical IRQ routing to EL2 only happens from NS state. */ - bool irq_can_hyp = !secure && cur_el < 2 && target_el == 2; - - /* Don't take exceptions if they target a lower EL. */ + bool secure = arm_is_secure(env); + uint32_t scr; + uint32_t hcr; + bool pstate_unmasked; + int8_t unmasked = 0; + + /* Don't take exceptions if they target a lower EL. + * This check should catch any exceptions that would not be taken but left + * pending. + */ if (cur_el > target_el) { return false; } switch (excp_idx) { case EXCP_FIQ: - if (irq_can_hyp && (env->cp15.hcr_el2 & HCR_FMO)) { - return true; - } - return !(env->daif & PSTATE_F); + /* If FIQs are routed to EL3 or EL2 then there are cases where we + * override the CPSR.F in determining if the exception is masked or + * not. If neither of these are set then we fall back to the CPSR.F + * setting otherwise we further assess the state below. + */ + hcr = (env->cp15.hcr_el2 & HCR_FMO); + scr = (env->cp15.scr_el3 & SCR_FIQ); + + /* When EL3 is 32-bit, the SCR.FW bit controls whether the CPSR.F bit + * masks FIQ interrupts when taken in non-secure state. If SCR.FW is + * set then FIQs can be masked by CPSR.F when non-secure but only + * when FIQs are only routed to EL3. + */ + scr &= !((env->cp15.scr_el3 & SCR_FW) && !hcr); + pstate_unmasked = !(env->daif & PSTATE_F); + break; + case EXCP_IRQ: - if (irq_can_hyp && (env->cp15.hcr_el2 & HCR_IMO)) { - return true; - } - return !(env->daif & PSTATE_I); + /* When EL3 execution state is 32-bit, if HCR.IMO is set then we may + * override the CPSR.I masking when in non-secure state. The SCR.IRQ + * setting has already been taken into consideration when setting the + * target EL, so it does not have a further affect here. + */ + hcr = (env->cp15.hcr_el2 & HCR_IMO); + scr = false; + pstate_unmasked = !(env->daif & PSTATE_I); + break; + case EXCP_VFIQ: if (secure || !(env->cp15.hcr_el2 & HCR_FMO)) { /* VFIQs are only taken when hypervized and non-secure. */ @@ -1283,29 +1552,114 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx) default: g_assert_not_reached(); } -} -static inline CPUARMState *cpu_init(const char *cpu_model) -{ - ARMCPU *cpu = cpu_arm_init(cpu_model); - if (cpu) { - return &cpu->env; + /* Use the target EL, current execution state and SCR/HCR settings to + * determine whether the corresponding CPSR bit is used to mask the + * interrupt. + */ + if ((target_el > cur_el) && (target_el != 1)) { + if (arm_el_is_aa64(env, 3) || ((scr || hcr) && (!secure))) { + unmasked = 1; + } } - return NULL; + + /* The PSTATE bits only mask the interrupt if we have not overriden the + * ability above. + */ + return unmasked || pstate_unmasked; } +#define cpu_init(cpu_model) CPU(cpu_arm_init(cpu_model)) + #define cpu_exec cpu_arm_exec #define cpu_gen_code cpu_arm_gen_code #define cpu_signal_handler cpu_arm_signal_handler #define cpu_list arm_cpu_list -/* MMU modes definitions */ -#define MMU_MODE0_SUFFIX _user -#define MMU_MODE1_SUFFIX _kernel +/* ARM has the following "translation regimes" (as the ARM ARM calls them): + * + * If EL3 is 64-bit: + * + NonSecure EL1 & 0 stage 1 + * + NonSecure EL1 & 0 stage 2 + * + NonSecure EL2 + * + Secure EL1 & EL0 + * + Secure EL3 + * If EL3 is 32-bit: + * + NonSecure PL1 & 0 stage 1 + * + NonSecure PL1 & 0 stage 2 + * + NonSecure PL2 + * + Secure PL0 & PL1 + * (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: + * 1. we need to split the "EL1 & 0" regimes into two mmu_idxes, because they + * may differ in access permissions even if the VA->PA map is the same + * 2. we want to cache in our TLB the full VA->IPA->PA lookup for a stage 1+2 + * translation, which means that we have one mmu_idx that deals with two + * concatenated translation regimes [this sort of combined s1+2 TLB is + * architecturally permitted] + * 3. we don't need to allocate an mmu_idx to translations that we won't be + * handling via the TLB. The only way to do a stage 1 translation without + * the immediate stage 2 translation is via the ATS or AT system insns, + * which can be slow-pathed and always do a page table walk. + * 4. we can also safely fold together the "32 bit EL3" and "64 bit EL3" + * translation regimes, because they map reasonably well to each other + * and they can't both be active at the same time. + * This gives us the following list of mmu_idx values: + * + * NS EL0 (aka NS PL0) stage 1+2 + * NS EL1 (aka NS PL1) stage 1+2 + * NS EL2 (aka NS PL2) + * S EL3 (aka S PL1) + * S EL0 (aka S PL0) + * S EL1 (not used if EL3 is 32 bit) + * NS EL0+1 stage 2 + * + * (The last of these is an mmu_idx because we want to be able to use the TLB + * for the accesses done as part of a stage 1 page table walk, rather than + * having to walk the stage 2 page table over and over.) + * + * Our enumeration includes at the end some entries which are not "true" + * mmu_idx values in that they don't have corresponding TLBs and are only + * valid for doing slow path page table walks. + * + * The constant names here are patterned after the general style of the names + * of the AT/ATS operations. + * The values used are carefully arranged to make mmu_idx => EL lookup easy. + */ +typedef enum ARMMMUIdx { + ARMMMUIdx_S12NSE0 = 0, + ARMMMUIdx_S12NSE1 = 1, + ARMMMUIdx_S1E2 = 2, + ARMMMUIdx_S1E3 = 3, + ARMMMUIdx_S1SE0 = 4, + ARMMMUIdx_S1SE1 = 5, + ARMMMUIdx_S2NS = 6, + /* Indexes below here don't have TLBs and are used only for AT system + * instructions or for the first stage of an S12 page table walk. + */ + ARMMMUIdx_S1NSE0 = 7, + ARMMMUIdx_S1NSE1 = 8, +} ARMMMUIdx; + #define MMU_USER_IDX 0 -static inline int cpu_mmu_index (CPUARMState *env) + +/* Return the exception level we're running at if this is our mmu_idx */ +static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) { - return arm_current_el(env); + assert(mmu_idx < ARMMMUIdx_S2NS); + return mmu_idx & 3; +} + +/* Determine the current mmu_idx to use for normal loads/stores */ +static inline int cpu_mmu_index(CPUARMState *env) +{ + int el = arm_current_el(env); + + if (el < 2 && arm_is_secure_below_el3(env)) { + return ARMMMUIdx_S1SE0 + el; + } + return el; } /* Return the Exception Level targeted by debug exceptions; @@ -1372,9 +1726,13 @@ static inline bool arm_singlestep_active(CPUARMState *env) /* Bit usage in the TB flags field: bit 31 indicates whether we are * in 32 or 64 bit mode. The meaning of the other bits depends on that. + * We put flags which are shared between 32 and 64 bit mode at the top + * of the word, and flags which apply to only one mode at the bottom. */ #define ARM_TBFLAG_AARCH64_STATE_SHIFT 31 #define ARM_TBFLAG_AARCH64_STATE_MASK (1U << ARM_TBFLAG_AARCH64_STATE_SHIFT) +#define ARM_TBFLAG_MMUIDX_SHIFT 28 +#define ARM_TBFLAG_MMUIDX_MASK (0x7 << ARM_TBFLAG_MMUIDX_SHIFT) /* Bit usage when in AArch32 state: */ #define ARM_TBFLAG_THUMB_SHIFT 0 @@ -1383,8 +1741,6 @@ static inline bool arm_singlestep_active(CPUARMState *env) #define ARM_TBFLAG_VECLEN_MASK (0x7 << ARM_TBFLAG_VECLEN_SHIFT) #define ARM_TBFLAG_VECSTRIDE_SHIFT 4 #define ARM_TBFLAG_VECSTRIDE_MASK (0x3 << ARM_TBFLAG_VECSTRIDE_SHIFT) -#define ARM_TBFLAG_PRIV_SHIFT 6 -#define ARM_TBFLAG_PRIV_MASK (1 << ARM_TBFLAG_PRIV_SHIFT) #define ARM_TBFLAG_VFPEN_SHIFT 7 #define ARM_TBFLAG_VFPEN_MASK (1 << ARM_TBFLAG_VFPEN_SHIFT) #define ARM_TBFLAG_CONDEXEC_SHIFT 8 @@ -1402,10 +1758,14 @@ static inline bool arm_singlestep_active(CPUARMState *env) */ #define ARM_TBFLAG_XSCALE_CPAR_SHIFT 20 #define ARM_TBFLAG_XSCALE_CPAR_MASK (3 << ARM_TBFLAG_XSCALE_CPAR_SHIFT) +/* Indicates whether cp register reads and writes by guest code should access + * the secure or nonsecure bank of banked registers; note that this is not + * the same thing as the current security state of the processor! + */ +#define ARM_TBFLAG_NS_SHIFT 22 +#define ARM_TBFLAG_NS_MASK (1 << ARM_TBFLAG_NS_SHIFT) /* Bit usage when in AArch64 state */ -#define ARM_TBFLAG_AA64_EL_SHIFT 0 -#define ARM_TBFLAG_AA64_EL_MASK (0x3 << ARM_TBFLAG_AA64_EL_SHIFT) #define ARM_TBFLAG_AA64_FPEN_SHIFT 2 #define ARM_TBFLAG_AA64_FPEN_MASK (1 << ARM_TBFLAG_AA64_FPEN_SHIFT) #define ARM_TBFLAG_AA64_SS_ACTIVE_SHIFT 3 @@ -1416,14 +1776,14 @@ static inline bool arm_singlestep_active(CPUARMState *env) /* some convenience accessor macros */ #define ARM_TBFLAG_AARCH64_STATE(F) \ (((F) & ARM_TBFLAG_AARCH64_STATE_MASK) >> ARM_TBFLAG_AARCH64_STATE_SHIFT) +#define ARM_TBFLAG_MMUIDX(F) \ + (((F) & ARM_TBFLAG_MMUIDX_MASK) >> ARM_TBFLAG_MMUIDX_SHIFT) #define ARM_TBFLAG_THUMB(F) \ (((F) & ARM_TBFLAG_THUMB_MASK) >> ARM_TBFLAG_THUMB_SHIFT) #define ARM_TBFLAG_VECLEN(F) \ (((F) & ARM_TBFLAG_VECLEN_MASK) >> ARM_TBFLAG_VECLEN_SHIFT) #define ARM_TBFLAG_VECSTRIDE(F) \ (((F) & ARM_TBFLAG_VECSTRIDE_MASK) >> ARM_TBFLAG_VECSTRIDE_SHIFT) -#define ARM_TBFLAG_PRIV(F) \ - (((F) & ARM_TBFLAG_PRIV_MASK) >> ARM_TBFLAG_PRIV_SHIFT) #define ARM_TBFLAG_VFPEN(F) \ (((F) & ARM_TBFLAG_VFPEN_MASK) >> ARM_TBFLAG_VFPEN_SHIFT) #define ARM_TBFLAG_CONDEXEC(F) \ @@ -1438,14 +1798,14 @@ static inline bool arm_singlestep_active(CPUARMState *env) (((F) & ARM_TBFLAG_PSTATE_SS_MASK) >> ARM_TBFLAG_PSTATE_SS_SHIFT) #define ARM_TBFLAG_XSCALE_CPAR(F) \ (((F) & ARM_TBFLAG_XSCALE_CPAR_MASK) >> ARM_TBFLAG_XSCALE_CPAR_SHIFT) -#define ARM_TBFLAG_AA64_EL(F) \ - (((F) & ARM_TBFLAG_AA64_EL_MASK) >> ARM_TBFLAG_AA64_EL_SHIFT) #define ARM_TBFLAG_AA64_FPEN(F) \ (((F) & ARM_TBFLAG_AA64_FPEN_MASK) >> ARM_TBFLAG_AA64_FPEN_SHIFT) #define ARM_TBFLAG_AA64_SS_ACTIVE(F) \ (((F) & ARM_TBFLAG_AA64_SS_ACTIVE_MASK) >> ARM_TBFLAG_AA64_SS_ACTIVE_SHIFT) #define ARM_TBFLAG_AA64_PSTATE_SS(F) \ (((F) & ARM_TBFLAG_AA64_PSTATE_SS_MASK) >> ARM_TBFLAG_AA64_PSTATE_SS_SHIFT) +#define ARM_TBFLAG_NS(F) \ + (((F) & ARM_TBFLAG_NS_MASK) >> ARM_TBFLAG_NS_SHIFT) static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, int *flags) @@ -1461,8 +1821,7 @@ static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, if (is_a64(env)) { *pc = env->pc; - *flags = ARM_TBFLAG_AARCH64_STATE_MASK - | (arm_current_el(env) << ARM_TBFLAG_AA64_EL_SHIFT); + *flags = ARM_TBFLAG_AARCH64_STATE_MASK; if (fpen == 3 || (fpen == 1 && arm_current_el(env) != 0)) { *flags |= ARM_TBFLAG_AA64_FPEN_MASK; } @@ -1480,20 +1839,14 @@ static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } } } else { - int privmode; *pc = env->regs[15]; *flags = (env->thumb << ARM_TBFLAG_THUMB_SHIFT) | (env->vfp.vec_len << ARM_TBFLAG_VECLEN_SHIFT) | (env->vfp.vec_stride << ARM_TBFLAG_VECSTRIDE_SHIFT) | (env->condexec_bits << ARM_TBFLAG_CONDEXEC_SHIFT) | (env->bswap_code << ARM_TBFLAG_BSWAP_CODE_SHIFT); - if (arm_feature(env, ARM_FEATURE_M)) { - privmode = !((env->v7m.exception == 0) && (env->v7m.control & 1)); - } else { - privmode = (env->uncached_cpsr & CPSR_M) != ARM_CPU_MODE_USR; - } - if (privmode) { - *flags |= ARM_TBFLAG_PRIV_MASK; + if (!(access_secure_reg(env))) { + *flags |= ARM_TBFLAG_NS_MASK; } if (env->vfp.xregs[ARM_VFP_FPEXC] & (1 << 30) || arm_el_is_aa64(env, 1)) { @@ -1519,6 +1872,8 @@ static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, << ARM_TBFLAG_XSCALE_CPAR_SHIFT); } + *flags |= (cpu_mmu_index(env) << ARM_TBFLAG_MMUIDX_SHIFT); + *cs_base = 0; } diff --git a/target-arm/cpu64.c b/target-arm/cpu64.c index bb778b3d9..270bc2fec 100644 --- a/target-arm/cpu64.c +++ b/target-arm/cpu64.c @@ -32,6 +32,11 @@ static inline void set_feature(CPUARMState *env, int feature) env->features |= 1ULL << feature; } +static inline void unset_feature(CPUARMState *env, int feature) +{ + env->features &= ~(1ULL << feature); +} + #ifndef CONFIG_USER_ONLY static uint64_t a57_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) { @@ -91,6 +96,7 @@ static void aarch64_a57_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); + cpu->dtb_compatible = "arm,cortex-a57"; set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); @@ -170,8 +176,42 @@ static const ARMCPUInfo aarch64_cpus[] = { { .name = NULL } }; +static bool aarch64_cpu_get_aarch64(Object *obj, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + + return arm_feature(&cpu->env, ARM_FEATURE_AARCH64); +} + +static void aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + + /* At this time, this property is only allowed if KVM is enabled. This + * restriction allows us to avoid fixing up functionality that assumes a + * uniform execution state like do_interrupt. + */ + if (!kvm_enabled()) { + error_setg(errp, "'aarch64' feature cannot be disabled " + "unless KVM is enabled"); + return; + } + + if (value == false) { + unset_feature(&cpu->env, ARM_FEATURE_AARCH64); + } else { + set_feature(&cpu->env, ARM_FEATURE_AARCH64); + } +} + static void aarch64_cpu_initfn(Object *obj) { + object_property_add_bool(obj, "aarch64", aarch64_cpu_get_aarch64, + aarch64_cpu_set_aarch64, NULL); + object_property_set_description(obj, "aarch64", + "Set on/off to enable/disable aarch64 " + "execution state ", + NULL); } static void aarch64_cpu_finalizefn(Object *obj) diff --git a/target-arm/crypto_helper.c b/target-arm/crypto_helper.c index dd60d0b81..1fe975d0f 100644 --- a/target-arm/crypto_helper.c +++ b/target-arm/crypto_helper.c @@ -22,6 +22,14 @@ union CRYPTO_STATE { uint64_t l[2]; }; +#ifdef HOST_WORDS_BIGENDIAN +#define CR_ST_BYTE(state, i) (state.bytes[(15 - (i)) ^ 8]) +#define CR_ST_WORD(state, i) (state.words[(3 - (i)) ^ 2]) +#else +#define CR_ST_BYTE(state, i) (state.bytes[i]) +#define CR_ST_WORD(state, i) (state.words[i]) +#endif + void HELPER(crypto_aese)(CPUARMState *env, uint32_t rd, uint32_t rm, uint32_t decrypt) { @@ -46,7 +54,7 @@ void HELPER(crypto_aese)(CPUARMState *env, uint32_t rd, uint32_t rm, /* combine ShiftRows operation and sbox substitution */ for (i = 0; i < 16; i++) { - st.bytes[i] = sbox[decrypt][rk.bytes[shift[decrypt][i]]]; + CR_ST_BYTE(st, i) = sbox[decrypt][CR_ST_BYTE(rk, shift[decrypt][i])]; } env->vfp.regs[rd] = make_float64(st.l[0]); @@ -198,11 +206,11 @@ void HELPER(crypto_aesmc)(CPUARMState *env, uint32_t rd, uint32_t rm, assert(decrypt < 2); for (i = 0; i < 16; i += 4) { - st.words[i >> 2] = cpu_to_le32( - mc[decrypt][st.bytes[i]] ^ - rol32(mc[decrypt][st.bytes[i + 1]], 8) ^ - rol32(mc[decrypt][st.bytes[i + 2]], 16) ^ - rol32(mc[decrypt][st.bytes[i + 3]], 24)); + CR_ST_WORD(st, i >> 2) = + mc[decrypt][CR_ST_BYTE(st, i)] ^ + rol32(mc[decrypt][CR_ST_BYTE(st, i + 1)], 8) ^ + rol32(mc[decrypt][CR_ST_BYTE(st, i + 2)], 16) ^ + rol32(mc[decrypt][CR_ST_BYTE(st, i + 3)], 24); } env->vfp.regs[rd] = make_float64(st.l[0]); @@ -255,24 +263,25 @@ void HELPER(crypto_sha1_3reg)(CPUARMState *env, uint32_t rd, uint32_t rn, switch (op) { case 0: /* sha1c */ - t = cho(d.words[1], d.words[2], d.words[3]); + t = cho(CR_ST_WORD(d, 1), CR_ST_WORD(d, 2), CR_ST_WORD(d, 3)); break; case 1: /* sha1p */ - t = par(d.words[1], d.words[2], d.words[3]); + t = par(CR_ST_WORD(d, 1), CR_ST_WORD(d, 2), CR_ST_WORD(d, 3)); break; case 2: /* sha1m */ - t = maj(d.words[1], d.words[2], d.words[3]); + t = maj(CR_ST_WORD(d, 1), CR_ST_WORD(d, 2), CR_ST_WORD(d, 3)); break; default: g_assert_not_reached(); } - t += rol32(d.words[0], 5) + n.words[0] + m.words[i]; - - n.words[0] = d.words[3]; - d.words[3] = d.words[2]; - d.words[2] = ror32(d.words[1], 2); - d.words[1] = d.words[0]; - d.words[0] = t; + t += rol32(CR_ST_WORD(d, 0), 5) + CR_ST_WORD(n, 0) + + CR_ST_WORD(m, i); + + CR_ST_WORD(n, 0) = CR_ST_WORD(d, 3); + CR_ST_WORD(d, 3) = CR_ST_WORD(d, 2); + CR_ST_WORD(d, 2) = ror32(CR_ST_WORD(d, 1), 2); + CR_ST_WORD(d, 1) = CR_ST_WORD(d, 0); + CR_ST_WORD(d, 0) = t; } } env->vfp.regs[rd] = make_float64(d.l[0]); @@ -286,8 +295,8 @@ void HELPER(crypto_sha1h)(CPUARMState *env, uint32_t rd, uint32_t rm) float64_val(env->vfp.regs[rm + 1]) } }; - m.words[0] = ror32(m.words[0], 2); - m.words[1] = m.words[2] = m.words[3] = 0; + CR_ST_WORD(m, 0) = ror32(CR_ST_WORD(m, 0), 2); + CR_ST_WORD(m, 1) = CR_ST_WORD(m, 2) = CR_ST_WORD(m, 3) = 0; env->vfp.regs[rd] = make_float64(m.l[0]); env->vfp.regs[rd + 1] = make_float64(m.l[1]); @@ -304,10 +313,10 @@ void HELPER(crypto_sha1su1)(CPUARMState *env, uint32_t rd, uint32_t rm) float64_val(env->vfp.regs[rm + 1]) } }; - d.words[0] = rol32(d.words[0] ^ m.words[1], 1); - d.words[1] = rol32(d.words[1] ^ m.words[2], 1); - d.words[2] = rol32(d.words[2] ^ m.words[3], 1); - d.words[3] = rol32(d.words[3] ^ d.words[0], 1); + CR_ST_WORD(d, 0) = rol32(CR_ST_WORD(d, 0) ^ CR_ST_WORD(m, 1), 1); + CR_ST_WORD(d, 1) = rol32(CR_ST_WORD(d, 1) ^ CR_ST_WORD(m, 2), 1); + CR_ST_WORD(d, 2) = rol32(CR_ST_WORD(d, 2) ^ CR_ST_WORD(m, 3), 1); + CR_ST_WORD(d, 3) = rol32(CR_ST_WORD(d, 3) ^ CR_ST_WORD(d, 0), 1); env->vfp.regs[rd] = make_float64(d.l[0]); env->vfp.regs[rd + 1] = make_float64(d.l[1]); @@ -356,20 +365,22 @@ void HELPER(crypto_sha256h)(CPUARMState *env, uint32_t rd, uint32_t rn, int i; for (i = 0; i < 4; i++) { - uint32_t t = cho(n.words[0], n.words[1], n.words[2]) + n.words[3] - + S1(n.words[0]) + m.words[i]; - - n.words[3] = n.words[2]; - n.words[2] = n.words[1]; - n.words[1] = n.words[0]; - n.words[0] = d.words[3] + t; - - t += maj(d.words[0], d.words[1], d.words[2]) + S0(d.words[0]); - - d.words[3] = d.words[2]; - d.words[2] = d.words[1]; - d.words[1] = d.words[0]; - d.words[0] = t; + uint32_t t = cho(CR_ST_WORD(n, 0), CR_ST_WORD(n, 1), CR_ST_WORD(n, 2)) + + CR_ST_WORD(n, 3) + S1(CR_ST_WORD(n, 0)) + + CR_ST_WORD(m, i); + + CR_ST_WORD(n, 3) = CR_ST_WORD(n, 2); + CR_ST_WORD(n, 2) = CR_ST_WORD(n, 1); + CR_ST_WORD(n, 1) = CR_ST_WORD(n, 0); + CR_ST_WORD(n, 0) = CR_ST_WORD(d, 3) + t; + + t += maj(CR_ST_WORD(d, 0), CR_ST_WORD(d, 1), CR_ST_WORD(d, 2)) + + S0(CR_ST_WORD(d, 0)); + + CR_ST_WORD(d, 3) = CR_ST_WORD(d, 2); + CR_ST_WORD(d, 2) = CR_ST_WORD(d, 1); + CR_ST_WORD(d, 1) = CR_ST_WORD(d, 0); + CR_ST_WORD(d, 0) = t; } env->vfp.regs[rd] = make_float64(d.l[0]); @@ -394,13 +405,14 @@ void HELPER(crypto_sha256h2)(CPUARMState *env, uint32_t rd, uint32_t rn, int i; for (i = 0; i < 4; i++) { - uint32_t t = cho(d.words[0], d.words[1], d.words[2]) + d.words[3] - + S1(d.words[0]) + m.words[i]; - - d.words[3] = d.words[2]; - d.words[2] = d.words[1]; - d.words[1] = d.words[0]; - d.words[0] = n.words[3 - i] + t; + uint32_t t = cho(CR_ST_WORD(d, 0), CR_ST_WORD(d, 1), CR_ST_WORD(d, 2)) + + CR_ST_WORD(d, 3) + S1(CR_ST_WORD(d, 0)) + + CR_ST_WORD(m, i); + + CR_ST_WORD(d, 3) = CR_ST_WORD(d, 2); + CR_ST_WORD(d, 2) = CR_ST_WORD(d, 1); + CR_ST_WORD(d, 1) = CR_ST_WORD(d, 0); + CR_ST_WORD(d, 0) = CR_ST_WORD(n, 3 - i) + t; } env->vfp.regs[rd] = make_float64(d.l[0]); @@ -418,10 +430,10 @@ void HELPER(crypto_sha256su0)(CPUARMState *env, uint32_t rd, uint32_t rm) float64_val(env->vfp.regs[rm + 1]) } }; - d.words[0] += s0(d.words[1]); - d.words[1] += s0(d.words[2]); - d.words[2] += s0(d.words[3]); - d.words[3] += s0(m.words[0]); + CR_ST_WORD(d, 0) += s0(CR_ST_WORD(d, 1)); + CR_ST_WORD(d, 1) += s0(CR_ST_WORD(d, 2)); + CR_ST_WORD(d, 2) += s0(CR_ST_WORD(d, 3)); + CR_ST_WORD(d, 3) += s0(CR_ST_WORD(m, 0)); env->vfp.regs[rd] = make_float64(d.l[0]); env->vfp.regs[rd + 1] = make_float64(d.l[1]); @@ -443,10 +455,10 @@ void HELPER(crypto_sha256su1)(CPUARMState *env, uint32_t rd, uint32_t rn, float64_val(env->vfp.regs[rm + 1]) } }; - d.words[0] += s1(m.words[2]) + n.words[1]; - d.words[1] += s1(m.words[3]) + n.words[2]; - d.words[2] += s1(d.words[0]) + n.words[3]; - d.words[3] += s1(d.words[1]) + m.words[0]; + CR_ST_WORD(d, 0) += s1(CR_ST_WORD(m, 2)) + CR_ST_WORD(n, 1); + CR_ST_WORD(d, 1) += s1(CR_ST_WORD(m, 3)) + CR_ST_WORD(n, 2); + CR_ST_WORD(d, 2) += s1(CR_ST_WORD(d, 0)) + CR_ST_WORD(n, 3); + CR_ST_WORD(d, 3) += s1(CR_ST_WORD(d, 1)) + CR_ST_WORD(m, 0); env->vfp.regs[rd] = make_float64(d.l[0]); env->vfp.regs[rd + 1] = make_float64(d.l[1]); diff --git a/target-arm/helper-a64.c b/target-arm/helper-a64.c index 81066ca93..861f6fa69 100644 --- a/target-arm/helper-a64.c +++ b/target-arm/helper-a64.c @@ -135,6 +135,9 @@ float32 HELPER(vfp_mulxs)(float32 a, float32 b, void *fpstp) { float_status *fpst = fpstp; + a = float32_squash_input_denormal(a, fpst); + b = float32_squash_input_denormal(b, fpst); + if ((float32_is_zero(a) && float32_is_infinity(b)) || (float32_is_infinity(a) && float32_is_zero(b))) { /* 2.0 with the sign bit set to sign(A) XOR sign(B) */ @@ -148,6 +151,9 @@ float64 HELPER(vfp_mulxd)(float64 a, float64 b, void *fpstp) { float_status *fpst = fpstp; + a = float64_squash_input_denormal(a, fpst); + b = float64_squash_input_denormal(b, fpst); + if ((float64_is_zero(a) && float64_is_infinity(b)) || (float64_is_infinity(a) && float64_is_zero(b))) { /* 2.0 with the sign bit set to sign(A) XOR sign(B) */ @@ -223,6 +229,9 @@ float32 HELPER(recpsf_f32)(float32 a, float32 b, void *fpstp) { float_status *fpst = fpstp; + a = float32_squash_input_denormal(a, fpst); + b = float32_squash_input_denormal(b, fpst); + a = float32_chs(a); if ((float32_is_infinity(a) && float32_is_zero(b)) || (float32_is_infinity(b) && float32_is_zero(a))) { @@ -235,6 +244,9 @@ float64 HELPER(recpsf_f64)(float64 a, float64 b, void *fpstp) { float_status *fpst = fpstp; + a = float64_squash_input_denormal(a, fpst); + b = float64_squash_input_denormal(b, fpst); + a = float64_chs(a); if ((float64_is_infinity(a) && float64_is_zero(b)) || (float64_is_infinity(b) && float64_is_zero(a))) { @@ -247,6 +259,9 @@ float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, void *fpstp) { float_status *fpst = fpstp; + a = float32_squash_input_denormal(a, fpst); + b = float32_squash_input_denormal(b, fpst); + a = float32_chs(a); if ((float32_is_infinity(a) && float32_is_zero(b)) || (float32_is_infinity(b) && float32_is_zero(a))) { @@ -259,6 +274,9 @@ float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void *fpstp) { float_status *fpst = fpstp; + a = float64_squash_input_denormal(a, fpst); + b = float64_squash_input_denormal(b, fpst); + a = float64_chs(a); if ((float64_is_infinity(a) && float64_is_zero(b)) || (float64_is_infinity(b) && float64_is_zero(a))) { @@ -448,7 +466,6 @@ void aarch64_cpu_do_interrupt(CPUState *cs) unsigned int new_el = arm_excp_target_el(cs, cs->exception_index); target_ulong addr = env->cp15.vbar_el[new_el]; unsigned int new_mode = aarch64_pstate_mode(new_el, true); - int i; if (arm_current_el(env) < new_el) { if (env->aarch64) { @@ -506,15 +523,13 @@ void aarch64_cpu_do_interrupt(CPUState *cs) aarch64_save_sp(env, arm_current_el(env)); env->elr_el[new_el] = env->pc; } else { - env->banked_spsr[0] = cpsr_read(env); + env->banked_spsr[aarch64_banked_spsr_index(new_el)] = cpsr_read(env); if (!env->thumb) { env->cp15.esr_el[new_el] |= 1 << 25; } env->elr_el[new_el] = env->regs[15]; - for (i = 0; i < 15; i++) { - env->xregs[i] = env->regs[i]; - } + aarch64_sync_32_to_64(env); env->condexec_bits = 0; } diff --git a/target-arm/helper.c b/target-arm/helper.c index b74d348a3..d77c6de40 100644 --- a/target-arm/helper.c +++ b/target-arm/helper.c @@ -13,7 +13,7 @@ #ifndef CONFIG_USER_ONLY static inline int get_phys_addr(CPUARMState *env, target_ulong address, - int access_type, int is_user, + int access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, int *prot, target_ulong *page_size); @@ -119,6 +119,7 @@ static int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg) static uint64_t raw_read(CPUARMState *env, const ARMCPRegInfo *ri) { + assert(ri->fieldoffset); if (cpreg_field_is_64bit(ri)) { return CPREG_FIELD64(env, ri); } else { @@ -129,6 +130,7 @@ static uint64_t raw_read(CPUARMState *env, const ARMCPRegInfo *ri) static void raw_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { + assert(ri->fieldoffset); if (cpreg_field_is_64bit(ri)) { CPREG_FIELD64(env, ri) = value; } else { @@ -136,6 +138,11 @@ static void raw_write(CPUARMState *env, const ARMCPRegInfo *ri, } } +static void *raw_ptr(CPUARMState *env, const ARMCPRegInfo *ri) +{ + return (char *)env + ri->fieldoffset; +} + static uint64_t read_raw_cp_reg(CPUARMState *env, const ARMCPRegInfo *ri) { /* Raw read of a coprocessor register (as needed for migration, etc). */ @@ -169,6 +176,27 @@ static void write_raw_cp_reg(CPUARMState *env, const ARMCPRegInfo *ri, } } +static bool raw_accessors_invalid(const ARMCPRegInfo *ri) +{ + /* Return true if the regdef would cause an assertion if you called + * read_raw_cp_reg() or write_raw_cp_reg() on it (ie if it is a + * program bug for it not to have the NO_RAW flag). + * NB that returning false here doesn't necessarily mean that calling + * read/write_raw_cp_reg() is safe, because we can't distinguish "has + * read/write access functions which are safe for raw use" from "has + * read/write access functions which have side effects but has forgotten + * to provide raw access functions". + * The tests here line up with the conditions in read/write_raw_cp_reg() + * and assertions in raw_read()/raw_write(). + */ + if ((ri->type & ARM_CP_CONST) || + ri->fieldoffset || + ((ri->raw_writefn || ri->writefn) && (ri->raw_readfn || ri->readfn))) { + return false; + } + return true; +} + bool write_cpustate_to_list(ARMCPU *cpu) { /* Write the coprocessor state from cpu->env to the (index,value) list. */ @@ -184,7 +212,7 @@ bool write_cpustate_to_list(ARMCPU *cpu) ok = false; continue; } - if (ri->type & ARM_CP_NO_MIGRATE) { + if (ri->type & ARM_CP_NO_RAW) { continue; } cpu->cpreg_values[i] = read_raw_cp_reg(&cpu->env, ri); @@ -207,7 +235,7 @@ bool write_list_to_cpustate(ARMCPU *cpu) ok = false; continue; } - if (ri->type & ARM_CP_NO_MIGRATE) { + if (ri->type & ARM_CP_NO_RAW) { continue; } /* Write value and confirm it reads back as written @@ -231,7 +259,7 @@ static void add_cpreg_to_list(gpointer key, gpointer opaque) regidx = *(uint32_t *)key; ri = get_arm_cp_reginfo(cpu->cp_regs, regidx); - if (!(ri->type & ARM_CP_NO_MIGRATE)) { + if (!(ri->type & (ARM_CP_NO_RAW|ARM_CP_ALIAS))) { cpu->cpreg_indexes[cpu->cpreg_array_len] = cpreg_to_kvm_id(regidx); /* The value array need not be initialized at this point */ cpu->cpreg_array_len++; @@ -247,7 +275,7 @@ static void count_cpreg(gpointer key, gpointer opaque) regidx = *(uint32_t *)key; ri = get_arm_cp_reginfo(cpu->cp_regs, regidx); - if (!(ri->type & ARM_CP_NO_MIGRATE)) { + if (!(ri->type & (ARM_CP_NO_RAW|ARM_CP_ALIAS))) { cpu->cpreg_array_len++; } } @@ -419,13 +447,36 @@ static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri, } static const ARMCPRegInfo cp_reginfo[] = { - { .name = "FCSEIDR", .cp = 15, .crn = 13, .crm = 0, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.c13_fcse), + /* Define the secure and non-secure FCSE identifier CP registers + * separately because there is no secure bank in V8 (no _EL3). This allows + * the secure register to be properly reset and migrated. There is also no + * v8 EL1 version of the register so the non-secure instance stands alone. + */ + { .name = "FCSEIDR(NS)", + .cp = 15, .opc1 = 0, .crn = 13, .crm = 0, .opc2 = 0, + .access = PL1_RW, .secure = ARM_CP_SECSTATE_NS, + .fieldoffset = offsetof(CPUARMState, cp15.fcseidr_ns), .resetvalue = 0, .writefn = fcse_write, .raw_writefn = raw_write, }, - { .name = "CONTEXTIDR", .state = ARM_CP_STATE_BOTH, + { .name = "FCSEIDR(S)", + .cp = 15, .opc1 = 0, .crn = 13, .crm = 0, .opc2 = 0, + .access = PL1_RW, .secure = ARM_CP_SECSTATE_S, + .fieldoffset = offsetof(CPUARMState, cp15.fcseidr_s), + .resetvalue = 0, .writefn = fcse_write, .raw_writefn = raw_write, }, + /* Define the secure and non-secure context identifier CP registers + * separately because there is no secure bank in V8 (no _EL3). This allows + * the secure register to be properly reset and migrated. In the + * non-secure case, the 32-bit register will have reset and migration + * disabled during registration as it is handled by the 64-bit instance. + */ + { .name = "CONTEXTIDR_EL1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 13, .crm = 0, .opc2 = 1, - .access = PL1_RW, - .fieldoffset = offsetof(CPUARMState, cp15.contextidr_el1), + .access = PL1_RW, .secure = ARM_CP_SECSTATE_NS, + .fieldoffset = offsetof(CPUARMState, cp15.contextidr_el[1]), + .resetvalue = 0, .writefn = contextidr_write, .raw_writefn = raw_write, }, + { .name = "CONTEXTIDR(S)", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 0, .crn = 13, .crm = 0, .opc2 = 1, + .access = PL1_RW, .secure = ARM_CP_SECSTATE_S, + .fieldoffset = offsetof(CPUARMState, cp15.contextidr_s), .resetvalue = 0, .writefn = contextidr_write, .raw_writefn = raw_write, }, REGINFO_SENTINEL }; @@ -435,10 +486,12 @@ static const ARMCPRegInfo not_v8_cp_reginfo[] = { * definitions that don't use CP_ANY wildcards (mostly in v8_cp_reginfo[]). */ /* MMU Domain access control / MPU write buffer control */ - { .name = "DACR", .cp = 15, - .crn = 3, .crm = CP_ANY, .opc1 = CP_ANY, .opc2 = CP_ANY, - .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.c3), - .resetvalue = 0, .writefn = dacr_write, .raw_writefn = raw_write, }, + { .name = "DACR", + .cp = 15, .opc1 = CP_ANY, .crn = 3, .crm = CP_ANY, .opc2 = CP_ANY, + .access = PL1_RW, .resetvalue = 0, + .writefn = dacr_write, .raw_writefn = raw_write, + .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.dacr_s), + offsetoflow32(CPUARMState, cp15.dacr_ns) } }, /* ??? This covers not just the impdef TLB lockdown registers but also * some v7VMSA registers relating to TEX remap, so it is overly broad. */ @@ -478,7 +531,7 @@ static const ARMCPRegInfo not_v7_cp_reginfo[] = { .resetvalue = 0 }, /* v6 doesn't have the cache ID registers but Linux reads them anyway */ { .name = "DUMMY", .cp = 15, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = CP_ANY, - .access = PL1_R, .type = ARM_CP_CONST | ARM_CP_NO_MIGRATE, + .access = PL1_R, .type = ARM_CP_CONST | ARM_CP_NO_RAW, .resetvalue = 0 }, /* We don't implement pre-v7 debug but most CPUs had at least a DBGDIDR; * implementing it as RAZ means the "debug architecture version" bits @@ -492,16 +545,16 @@ static const ARMCPRegInfo not_v7_cp_reginfo[] = { */ { .name = "TLBIALL", .cp = 15, .crn = 8, .crm = CP_ANY, .opc1 = CP_ANY, .opc2 = 0, .access = PL1_W, .writefn = tlbiall_write, - .type = ARM_CP_NO_MIGRATE }, + .type = ARM_CP_NO_RAW }, { .name = "TLBIMVA", .cp = 15, .crn = 8, .crm = CP_ANY, .opc1 = CP_ANY, .opc2 = 1, .access = PL1_W, .writefn = tlbimva_write, - .type = ARM_CP_NO_MIGRATE }, + .type = ARM_CP_NO_RAW }, { .name = "TLBIASID", .cp = 15, .crn = 8, .crm = CP_ANY, .opc1 = CP_ANY, .opc2 = 2, .access = PL1_W, .writefn = tlbiasid_write, - .type = ARM_CP_NO_MIGRATE }, + .type = ARM_CP_NO_RAW }, { .name = "TLBIMVAA", .cp = 15, .crn = 8, .crm = CP_ANY, .opc1 = CP_ANY, .opc2 = 3, .access = PL1_W, .writefn = tlbimvaa_write, - .type = ARM_CP_NO_MIGRATE }, + .type = ARM_CP_NO_RAW }, REGINFO_SENTINEL }; @@ -552,7 +605,8 @@ static const ARMCPRegInfo v6_cp_reginfo[] = { .access = PL0_W, .type = ARM_CP_NOP }, { .name = "IFAR", .cp = 15, .crn = 6, .crm = 0, .opc1 = 0, .opc2 = 2, .access = PL1_RW, - .fieldoffset = offsetofhigh32(CPUARMState, cp15.far_el[1]), + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.ifar_s), + offsetof(CPUARMState, cp15.ifar_ns) }, .resetvalue = 0, }, /* Watchpoint Fault Address Register : should actually only be present * for 1136, 1176, 11MPCore. @@ -776,7 +830,14 @@ static void scr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) static uint64_t ccsidr_read(CPUARMState *env, const ARMCPRegInfo *ri) { ARMCPU *cpu = arm_env_get_cpu(env); - return cpu->ccsidr[env->cp15.c0_cssel]; + + /* Acquire the CSSELR index from the bank corresponding to the CCSIDR + * bank + */ + uint32_t index = A32_BANKED_REG_GET(env, csselr, + ri->secure & ARM_CP_SECSTATE_S); + + return cpu->ccsidr[index]; } static void csselr_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -816,7 +877,7 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { * or PL0_RO as appropriate and then check PMUSERENR in the helper fn. */ { .name = "PMCNTENSET", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 1, - .access = PL0_RW, .type = ARM_CP_NO_MIGRATE, + .access = PL0_RW, .type = ARM_CP_ALIAS, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmcnten), .writefn = pmcntenset_write, .accessfn = pmreg_access, @@ -831,11 +892,11 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmcnten), .accessfn = pmreg_access, .writefn = pmcntenclr_write, - .type = ARM_CP_NO_MIGRATE }, + .type = ARM_CP_ALIAS }, { .name = "PMCNTENCLR_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 2, .access = PL0_RW, .accessfn = pmreg_access, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcnten), .writefn = pmcntenclr_write }, { .name = "PMOVSR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 3, @@ -890,24 +951,23 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .resetvalue = 0, .writefn = pmintenset_write, .raw_writefn = raw_write }, { .name = "PMINTENCLR", .cp = 15, .crn = 9, .crm = 14, .opc1 = 0, .opc2 = 2, - .access = PL1_RW, .type = ARM_CP_NO_MIGRATE, + .access = PL1_RW, .type = ARM_CP_ALIAS, .fieldoffset = offsetof(CPUARMState, cp15.c9_pminten), .resetvalue = 0, .writefn = pmintenclr_write, }, { .name = "VBAR", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .crn = 12, .crm = 0, .opc1 = 0, .opc2 = 0, .access = PL1_RW, .writefn = vbar_write, - .fieldoffset = offsetof(CPUARMState, cp15.vbar_el[1]), + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.vbar_s), + offsetof(CPUARMState, cp15.vbar_ns) }, .resetvalue = 0 }, - { .name = "SCR", .cp = 15, .crn = 1, .crm = 1, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .fieldoffset = offsetoflow32(CPUARMState, cp15.scr_el3), - .resetvalue = 0, .writefn = scr_write }, { .name = "CCSIDR", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = 0, - .access = PL1_R, .readfn = ccsidr_read, .type = ARM_CP_NO_MIGRATE }, + .access = PL1_R, .readfn = ccsidr_read, .type = ARM_CP_NO_RAW }, { .name = "CSSELR", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 2, .opc2 = 0, - .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.c0_cssel), - .writefn = csselr_write, .resetvalue = 0 }, + .access = PL1_RW, .writefn = csselr_write, .resetvalue = 0, + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.csselr_s), + offsetof(CPUARMState, cp15.csselr_ns) } }, /* Auxiliary ID register: this actually has an IMPDEF value but for now * just RAZ for all cores: */ @@ -928,61 +988,67 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { */ { .name = "MAIR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 2, .opc2 = 0, - .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.mair_el1), + .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.mair_el[1]), .resetvalue = 0 }, /* For non-long-descriptor page tables these are PRRR and NMRR; * regardless they still act as reads-as-written for QEMU. * The override is necessary because of the overly-broad TLB_LOCKDOWN * definition. */ + /* MAIR0/1 are defined separately from their 64-bit counterpart which + * allows them to assign the correct fieldoffset based on the endianness + * handled in the field definitions. + */ { .name = "MAIR0", .state = ARM_CP_STATE_AA32, .type = ARM_CP_OVERRIDE, .cp = 15, .opc1 = 0, .crn = 10, .crm = 2, .opc2 = 0, .access = PL1_RW, - .fieldoffset = offsetoflow32(CPUARMState, cp15.mair_el1), + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.mair0_s), + offsetof(CPUARMState, cp15.mair0_ns) }, .resetfn = arm_cp_reset_ignore }, { .name = "MAIR1", .state = ARM_CP_STATE_AA32, .type = ARM_CP_OVERRIDE, .cp = 15, .opc1 = 0, .crn = 10, .crm = 2, .opc2 = 1, .access = PL1_RW, - .fieldoffset = offsetofhigh32(CPUARMState, cp15.mair_el1), + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.mair1_s), + offsetof(CPUARMState, cp15.mair1_ns) }, .resetfn = arm_cp_reset_ignore }, { .name = "ISR_EL1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 1, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE, .access = PL1_R, .readfn = isr_read }, + .type = ARM_CP_NO_RAW, .access = PL1_R, .readfn = isr_read }, /* 32 bit ITLB invalidates */ { .name = "ITLBIALL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbiall_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbiall_write }, { .name = "ITLBIMVA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 1, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbimva_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimva_write }, { .name = "ITLBIASID", .cp = 15, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 2, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbiasid_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbiasid_write }, /* 32 bit DTLB invalidates */ { .name = "DTLBIALL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbiall_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbiall_write }, { .name = "DTLBIMVA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 1, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbimva_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimva_write }, { .name = "DTLBIASID", .cp = 15, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 2, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbiasid_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbiasid_write }, /* 32 bit TLB invalidates */ { .name = "TLBIALL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbiall_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbiall_write }, { .name = "TLBIMVA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 1, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbimva_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimva_write }, { .name = "TLBIASID", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 2, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbiasid_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbiasid_write }, { .name = "TLBIMVAA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 3, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbimvaa_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimvaa_write }, REGINFO_SENTINEL }; static const ARMCPRegInfo v7mp_cp_reginfo[] = { /* 32 bit TLB invalidates, Inner Shareable */ { .name = "TLBIALLIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbiall_is_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbiall_is_write }, { .name = "TLBIMVAIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 1, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbimva_is_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimva_is_write }, { .name = "TLBIASIDIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 2, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbiasid_is_write }, { .name = "TLBIMVAAIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 3, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimvaa_is_write }, REGINFO_SENTINEL }; @@ -1017,23 +1083,31 @@ static const ARMCPRegInfo v6k_cp_reginfo[] = { { .name = "TPIDR_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .opc2 = 2, .crn = 13, .crm = 0, .access = PL0_RW, - .fieldoffset = offsetof(CPUARMState, cp15.tpidr_el0), .resetvalue = 0 }, + .fieldoffset = offsetof(CPUARMState, cp15.tpidr_el[0]), .resetvalue = 0 }, { .name = "TPIDRURW", .cp = 15, .crn = 13, .crm = 0, .opc1 = 0, .opc2 = 2, .access = PL0_RW, - .fieldoffset = offsetoflow32(CPUARMState, cp15.tpidr_el0), + .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.tpidrurw_s), + offsetoflow32(CPUARMState, cp15.tpidrurw_ns) }, .resetfn = arm_cp_reset_ignore }, { .name = "TPIDRRO_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .opc2 = 3, .crn = 13, .crm = 0, .access = PL0_R|PL1_W, - .fieldoffset = offsetof(CPUARMState, cp15.tpidrro_el0), .resetvalue = 0 }, + .fieldoffset = offsetof(CPUARMState, cp15.tpidrro_el[0]), + .resetvalue = 0}, { .name = "TPIDRURO", .cp = 15, .crn = 13, .crm = 0, .opc1 = 0, .opc2 = 3, .access = PL0_R|PL1_W, - .fieldoffset = offsetoflow32(CPUARMState, cp15.tpidrro_el0), + .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.tpidruro_s), + offsetoflow32(CPUARMState, cp15.tpidruro_ns) }, .resetfn = arm_cp_reset_ignore }, - { .name = "TPIDR_EL1", .state = ARM_CP_STATE_BOTH, + { .name = "TPIDR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .opc2 = 4, .crn = 13, .crm = 0, .access = PL1_RW, - .fieldoffset = offsetof(CPUARMState, cp15.tpidr_el1), .resetvalue = 0 }, + .fieldoffset = offsetof(CPUARMState, cp15.tpidr_el[1]), .resetvalue = 0 }, + { .name = "TPIDRPRW", .opc1 = 0, .cp = 15, .crn = 13, .crm = 0, .opc2 = 4, + .access = PL1_RW, + .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.tpidrprw_s), + offsetoflow32(CPUARMState, cp15.tpidrprw_ns) }, + .resetvalue = 0 }, REGINFO_SENTINEL }; @@ -1217,7 +1291,7 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { * Our reset value matches the fixed frequency we implement the timer at. */ { .name = "CNTFRQ", .cp = 15, .crn = 14, .crm = 0, .opc1 = 0, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .access = PL1_RW | PL0_R, .accessfn = gt_cntfrq_access, .fieldoffset = offsetoflow32(CPUARMState, cp15.c14_cntfrq), .resetfn = arm_cp_reset_ignore, @@ -1237,7 +1311,7 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { }, /* per-timer control */ { .name = "CNTP_CTL", .cp = 15, .crn = 14, .crm = 2, .opc1 = 0, .opc2 = 1, - .type = ARM_CP_IO | ARM_CP_NO_MIGRATE, .access = PL1_RW | PL0_R, + .type = ARM_CP_IO | ARM_CP_ALIAS, .access = PL1_RW | PL0_R, .accessfn = gt_ptimer_access, .fieldoffset = offsetoflow32(CPUARMState, cp15.c14_timer[GTIMER_PHYS].ctl), @@ -1253,7 +1327,7 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { .writefn = gt_ctl_write, .raw_writefn = raw_write, }, { .name = "CNTV_CTL", .cp = 15, .crn = 14, .crm = 3, .opc1 = 0, .opc2 = 1, - .type = ARM_CP_IO | ARM_CP_NO_MIGRATE, .access = PL1_RW | PL0_R, + .type = ARM_CP_IO | ARM_CP_ALIAS, .access = PL1_RW | PL0_R, .accessfn = gt_vtimer_access, .fieldoffset = offsetoflow32(CPUARMState, cp15.c14_timer[GTIMER_VIRT].ctl), @@ -1270,52 +1344,52 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { }, /* TimerValue views: a 32 bit downcounting view of the underlying state */ { .name = "CNTP_TVAL", .cp = 15, .crn = 14, .crm = 2, .opc1 = 0, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE | ARM_CP_IO, .access = PL1_RW | PL0_R, + .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL1_RW | PL0_R, .accessfn = gt_ptimer_access, .readfn = gt_tval_read, .writefn = gt_tval_write, }, { .name = "CNTP_TVAL_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 2, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE | ARM_CP_IO, .access = PL1_RW | PL0_R, + .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL1_RW | PL0_R, .readfn = gt_tval_read, .writefn = gt_tval_write, }, { .name = "CNTV_TVAL", .cp = 15, .crn = 14, .crm = 3, .opc1 = 0, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE | ARM_CP_IO, .access = PL1_RW | PL0_R, + .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL1_RW | PL0_R, .accessfn = gt_vtimer_access, .readfn = gt_tval_read, .writefn = gt_tval_write, }, { .name = "CNTV_TVAL_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 3, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE | ARM_CP_IO, .access = PL1_RW | PL0_R, + .type = ARM_CP_NO_RAW | ARM_CP_IO, .access = PL1_RW | PL0_R, .readfn = gt_tval_read, .writefn = gt_tval_write, }, /* The counter itself */ { .name = "CNTPCT", .cp = 15, .crm = 14, .opc1 = 0, - .access = PL0_R, .type = ARM_CP_64BIT | ARM_CP_NO_MIGRATE | ARM_CP_IO, + .access = PL0_R, .type = ARM_CP_64BIT | ARM_CP_NO_RAW | ARM_CP_IO, .accessfn = gt_pct_access, .readfn = gt_cnt_read, .resetfn = arm_cp_reset_ignore, }, { .name = "CNTPCT_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 0, .opc2 = 1, - .access = PL0_R, .type = ARM_CP_NO_MIGRATE | ARM_CP_IO, + .access = PL0_R, .type = ARM_CP_NO_RAW | ARM_CP_IO, .accessfn = gt_pct_access, .readfn = gt_cnt_read, .resetfn = gt_cnt_reset, }, { .name = "CNTVCT", .cp = 15, .crm = 14, .opc1 = 1, - .access = PL0_R, .type = ARM_CP_64BIT | ARM_CP_NO_MIGRATE | ARM_CP_IO, + .access = PL0_R, .type = ARM_CP_64BIT | ARM_CP_NO_RAW | ARM_CP_IO, .accessfn = gt_vct_access, .readfn = gt_cnt_read, .resetfn = arm_cp_reset_ignore, }, { .name = "CNTVCT_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 0, .opc2 = 2, - .access = PL0_R, .type = ARM_CP_NO_MIGRATE | ARM_CP_IO, + .access = PL0_R, .type = ARM_CP_NO_RAW | ARM_CP_IO, .accessfn = gt_vct_access, .readfn = gt_cnt_read, .resetfn = gt_cnt_reset, }, /* Comparison value, indicating when the timer goes off */ { .name = "CNTP_CVAL", .cp = 15, .crm = 14, .opc1 = 2, .access = PL1_RW | PL0_R, - .type = ARM_CP_64BIT | ARM_CP_IO | ARM_CP_NO_MIGRATE, + .type = ARM_CP_64BIT | ARM_CP_IO | ARM_CP_ALIAS, .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_PHYS].cval), .accessfn = gt_ptimer_access, .resetfn = arm_cp_reset_ignore, .writefn = gt_cval_write, .raw_writefn = raw_write, @@ -1330,7 +1404,7 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { }, { .name = "CNTV_CVAL", .cp = 15, .crm = 14, .opc1 = 3, .access = PL1_RW | PL0_R, - .type = ARM_CP_64BIT | ARM_CP_IO | ARM_CP_NO_MIGRATE, + .type = ARM_CP_64BIT | ARM_CP_IO | ARM_CP_ALIAS, .fieldoffset = offsetof(CPUARMState, cp15.c14_timer[GTIMER_VIRT].cval), .accessfn = gt_vtimer_access, .resetfn = arm_cp_reset_ignore, .writefn = gt_cval_write, .raw_writefn = raw_write, @@ -1377,29 +1451,30 @@ static CPAccessResult ats_access(CPUARMState *env, const ARMCPRegInfo *ri) /* Other states are only available with TrustZone; in * a non-TZ implementation these registers don't exist * at all, which is an Uncategorized trap. This underdecoding - * is safe because the reginfo is NO_MIGRATE. + * is safe because the reginfo is NO_RAW. */ return CP_ACCESS_TRAP_UNCATEGORIZED; } return CP_ACCESS_OK; } -static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +static uint64_t do_ats_write(CPUARMState *env, uint64_t value, + int access_type, ARMMMUIdx mmu_idx) { hwaddr phys_addr; target_ulong page_size; int prot; - int ret, is_user = ri->opc2 & 2; - int access_type = ri->opc2 & 1; + int ret; + uint64_t par64; - ret = get_phys_addr(env, value, access_type, is_user, + ret = get_phys_addr(env, value, access_type, mmu_idx, &phys_addr, &prot, &page_size); if (extended_addresses_enabled(env)) { /* ret is a DFSR/IFSR value for the long descriptor * translation table format, but with WnR always clear. * Convert it to a 64-bit PAR. */ - uint64_t par64 = (1 << 11); /* LPAE bit always set */ + par64 = (1 << 11); /* LPAE bit always set */ if (ret == 0) { par64 |= phys_addr & ~0xfffULL; /* We don't set the ATTR or SH fields in the PAR. */ @@ -1411,7 +1486,6 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) * fault. */ } - env->cp15.par_el1 = par64; } else { /* ret is a DFSR/IFSR value for the short descriptor * translation table format (with WnR always clear). @@ -1421,28 +1495,126 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) /* We do not set any attribute bits in the PAR */ if (page_size == (1 << 24) && arm_feature(env, ARM_FEATURE_V7)) { - env->cp15.par_el1 = (phys_addr & 0xff000000) | 1 << 1; + par64 = (phys_addr & 0xff000000) | (1 << 1); } else { - env->cp15.par_el1 = phys_addr & 0xfffff000; + par64 = phys_addr & 0xfffff000; } } else { - env->cp15.par_el1 = ((ret & (1 << 10)) >> 5) | - ((ret & (1 << 12)) >> 6) | - ((ret & 0xf) << 1) | 1; + par64 = ((ret & (1 << 10)) >> 5) | ((ret & (1 << 12)) >> 6) | + ((ret & 0xf) << 1) | 1; + } + } + return par64; +} + +static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +{ + int access_type = ri->opc2 & 1; + uint64_t par64; + ARMMMUIdx mmu_idx; + int el = arm_current_el(env); + bool secure = arm_is_secure_below_el3(env); + + switch (ri->opc2 & 6) { + case 0: + /* stage 1 current state PL1: ATS1CPR, ATS1CPW */ + switch (el) { + case 3: + mmu_idx = ARMMMUIdx_S1E3; + break; + case 2: + mmu_idx = ARMMMUIdx_S1NSE1; + break; + case 1: + mmu_idx = secure ? ARMMMUIdx_S1SE1 : ARMMMUIdx_S1NSE1; + break; + default: + g_assert_not_reached(); + } + break; + case 2: + /* stage 1 current state PL0: ATS1CUR, ATS1CUW */ + switch (el) { + case 3: + mmu_idx = ARMMMUIdx_S1SE0; + break; + case 2: + mmu_idx = ARMMMUIdx_S1NSE0; + break; + case 1: + mmu_idx = secure ? ARMMMUIdx_S1SE0 : ARMMMUIdx_S1NSE0; + break; + default: + g_assert_not_reached(); + } + break; + case 4: + /* stage 1+2 NonSecure PL1: ATS12NSOPR, ATS12NSOPW */ + mmu_idx = ARMMMUIdx_S12NSE1; + break; + case 6: + /* stage 1+2 NonSecure PL0: ATS12NSOUR, ATS12NSOUW */ + mmu_idx = ARMMMUIdx_S12NSE0; + break; + default: + g_assert_not_reached(); + } + + par64 = do_ats_write(env, value, access_type, mmu_idx); + + A32_BANKED_CURRENT_REG_SET(env, par, par64); +} + +static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + int access_type = ri->opc2 & 1; + ARMMMUIdx mmu_idx; + int secure = arm_is_secure_below_el3(env); + + switch (ri->opc2 & 6) { + case 0: + switch (ri->opc1) { + case 0: /* AT S1E1R, AT S1E1W */ + mmu_idx = secure ? ARMMMUIdx_S1SE1 : ARMMMUIdx_S1NSE1; + break; + case 4: /* AT S1E2R, AT S1E2W */ + mmu_idx = ARMMMUIdx_S1E2; + break; + case 6: /* AT S1E3R, AT S1E3W */ + mmu_idx = ARMMMUIdx_S1E3; + break; + default: + g_assert_not_reached(); } + break; + case 2: /* AT S1E0R, AT S1E0W */ + mmu_idx = secure ? ARMMMUIdx_S1SE0 : ARMMMUIdx_S1NSE0; + break; + case 4: /* AT S12E1R, AT S12E1W */ + mmu_idx = ARMMMUIdx_S12NSE1; + break; + case 6: /* AT S12E0R, AT S12E0W */ + mmu_idx = ARMMMUIdx_S12NSE0; + break; + default: + g_assert_not_reached(); } + + env->cp15.par_el[1] = do_ats_write(env, value, access_type, mmu_idx); } #endif static const ARMCPRegInfo vapa_cp_reginfo[] = { { .name = "PAR", .cp = 15, .crn = 7, .crm = 4, .opc1 = 0, .opc2 = 0, .access = PL1_RW, .resetvalue = 0, - .fieldoffset = offsetoflow32(CPUARMState, cp15.par_el1), + .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.par_s), + offsetoflow32(CPUARMState, cp15.par_ns) }, .writefn = par_write }, #ifndef CONFIG_USER_ONLY { .name = "ATS", .cp = 15, .crn = 7, .crm = 8, .opc1 = 0, .opc2 = CP_ANY, .access = PL1_W, .accessfn = ats_access, - .writefn = ats_write, .type = ARM_CP_NO_MIGRATE }, + .writefn = ats_write, .type = ARM_CP_NO_RAW }, #endif REGINFO_SENTINEL }; @@ -1501,12 +1673,12 @@ static uint64_t pmsav5_insn_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) static const ARMCPRegInfo pmsav5_cp_reginfo[] = { { .name = "DATA_AP", .cp = 15, .crn = 5, .crm = 0, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_NO_MIGRATE, + .access = PL1_RW, .type = ARM_CP_ALIAS, .fieldoffset = offsetof(CPUARMState, cp15.pmsav5_data_ap), .resetvalue = 0, .readfn = pmsav5_data_ap_read, .writefn = pmsav5_data_ap_write, }, { .name = "INSN_AP", .cp = 15, .crn = 5, .crm = 0, .opc1 = 0, .opc2 = 1, - .access = PL1_RW, .type = ARM_CP_NO_MIGRATE, + .access = PL1_RW, .type = ARM_CP_ALIAS, .fieldoffset = offsetof(CPUARMState, cp15.pmsav5_insn_ap), .resetvalue = 0, .readfn = pmsav5_insn_ap_read, .writefn = pmsav5_insn_ap_write, }, @@ -1555,6 +1727,7 @@ static const ARMCPRegInfo pmsav5_cp_reginfo[] = { static void vmsa_ttbcr_raw_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { + TCR *tcr = raw_ptr(env, ri); int maskshift = extract32(value, 0, 3); if (!arm_feature(env, ARM_FEATURE_V8)) { @@ -1573,14 +1746,15 @@ static void vmsa_ttbcr_raw_write(CPUARMState *env, const ARMCPRegInfo *ri, } } - /* Note that we always calculate c2_mask and c2_base_mask, but + /* Update the masks corresponding to the the TCR bank being written + * Note that we always calculate mask and base_mask, but * they are only used for short-descriptor tables (ie if EAE is 0); - * for long-descriptor tables the TTBCR fields are used differently - * and the c2_mask and c2_base_mask values are meaningless. + * for long-descriptor tables the TCR fields are used differently + * and the mask and base_mask values are meaningless. */ - raw_write(env, ri, value); - env->cp15.c2_mask = ~(((uint32_t)0xffffffffu) >> maskshift); - env->cp15.c2_base_mask = ~((uint32_t)0x3fffu >> maskshift); + tcr->raw_tcr = value; + tcr->mask = ~(((uint32_t)0xffffffffu) >> maskshift); + tcr->base_mask = ~((uint32_t)0x3fffu >> maskshift); } static void vmsa_ttbcr_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -1599,19 +1773,25 @@ static void vmsa_ttbcr_write(CPUARMState *env, const ARMCPRegInfo *ri, static void vmsa_ttbcr_reset(CPUARMState *env, const ARMCPRegInfo *ri) { - env->cp15.c2_base_mask = 0xffffc000u; - raw_write(env, ri, 0); - env->cp15.c2_mask = 0; + TCR *tcr = raw_ptr(env, ri); + + /* Reset both the TCR as well as the masks corresponding to the bank of + * the TCR being reset. + */ + tcr->raw_tcr = 0; + tcr->mask = 0; + tcr->base_mask = 0xffffc000u; } static void vmsa_tcr_el1_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { ARMCPU *cpu = arm_env_get_cpu(env); + TCR *tcr = raw_ptr(env, ri); /* For AArch64 the A1 bit could result in a change of ASID, so TLB flush. */ tlb_flush(CPU(cpu), 1); - raw_write(env, ri, value); + tcr->raw_tcr = value; } static void vmsa_ttbr_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -1630,38 +1810,46 @@ static void vmsa_ttbr_write(CPUARMState *env, const ARMCPRegInfo *ri, static const ARMCPRegInfo vmsa_cp_reginfo[] = { { .name = "DFSR", .cp = 15, .crn = 5, .crm = 0, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_NO_MIGRATE, - .fieldoffset = offsetoflow32(CPUARMState, cp15.esr_el[1]), + .access = PL1_RW, .type = ARM_CP_ALIAS, + .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.dfsr_s), + offsetoflow32(CPUARMState, cp15.dfsr_ns) }, .resetfn = arm_cp_reset_ignore, }, { .name = "IFSR", .cp = 15, .crn = 5, .crm = 0, .opc1 = 0, .opc2 = 1, - .access = PL1_RW, - .fieldoffset = offsetof(CPUARMState, cp15.ifsr_el2), .resetvalue = 0, }, + .access = PL1_RW, .resetvalue = 0, + .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.ifsr_s), + offsetoflow32(CPUARMState, cp15.ifsr_ns) } }, { .name = "ESR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .crn = 5, .crm = 2, .opc1 = 0, .opc2 = 0, .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.esr_el[1]), .resetvalue = 0, }, { .name = "TTBR0_EL1", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .crn = 2, .crm = 0, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.ttbr0_el1), - .writefn = vmsa_ttbr_write, .resetvalue = 0 }, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 0, .opc2 = 0, + .access = PL1_RW, .writefn = vmsa_ttbr_write, .resetvalue = 0, + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.ttbr0_s), + offsetof(CPUARMState, cp15.ttbr0_ns) } }, { .name = "TTBR1_EL1", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .crn = 2, .crm = 0, .opc1 = 0, .opc2 = 1, - .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.ttbr1_el1), - .writefn = vmsa_ttbr_write, .resetvalue = 0 }, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 0, .opc2 = 1, + .access = PL1_RW, .writefn = vmsa_ttbr_write, .resetvalue = 0, + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.ttbr1_s), + offsetof(CPUARMState, cp15.ttbr1_ns) } }, { .name = "TCR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .crn = 2, .crm = 0, .opc1 = 0, .opc2 = 2, .access = PL1_RW, .writefn = vmsa_tcr_el1_write, .resetfn = vmsa_ttbcr_reset, .raw_writefn = raw_write, - .fieldoffset = offsetof(CPUARMState, cp15.c2_control) }, + .fieldoffset = offsetof(CPUARMState, cp15.tcr_el[1]) }, { .name = "TTBCR", .cp = 15, .crn = 2, .crm = 0, .opc1 = 0, .opc2 = 2, - .access = PL1_RW, .type = ARM_CP_NO_MIGRATE, .writefn = vmsa_ttbcr_write, + .access = PL1_RW, .type = ARM_CP_ALIAS, .writefn = vmsa_ttbcr_write, .resetfn = arm_cp_reset_ignore, .raw_writefn = vmsa_ttbcr_raw_write, - .fieldoffset = offsetoflow32(CPUARMState, cp15.c2_control) }, - /* 64-bit FAR; this entry also gives us the AArch32 DFAR */ - { .name = "FAR_EL1", .state = ARM_CP_STATE_BOTH, + .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.tcr_el[3]), + offsetoflow32(CPUARMState, cp15.tcr_el[1])} }, + { .name = "FAR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .crn = 6, .crm = 0, .opc1 = 0, .opc2 = 0, .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.far_el[1]), .resetvalue = 0, }, + { .name = "DFAR", .cp = 15, .opc1 = 0, .crn = 6, .crm = 0, .opc2 = 0, + .access = PL1_RW, .resetvalue = 0, + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.dfar_s), + offsetof(CPUARMState, cp15.dfar_ns) } }, REGINFO_SENTINEL }; @@ -1720,7 +1908,7 @@ static const ARMCPRegInfo omap_cp_reginfo[] = { .writefn = omap_threadid_write }, { .name = "TI925T_STATUS", .cp = 15, .crn = 15, .crm = 8, .opc1 = 0, .opc2 = 0, .access = PL1_RW, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_NO_RAW, .readfn = arm_cp_read_zero, .writefn = omap_wfi_write, }, /* TODO: Peripheral port remap register: * On OMAP2 mcr p15, 0, rn, c15, c2, 4 sets up the interrupt controller @@ -1729,7 +1917,7 @@ static const ARMCPRegInfo omap_cp_reginfo[] = { */ { .name = "OMAP_CACHEMAINT", .cp = 15, .crn = 7, .crm = CP_ANY, .opc1 = 0, .opc2 = CP_ANY, .access = PL1_W, - .type = ARM_CP_OVERRIDE | ARM_CP_NO_MIGRATE, + .type = ARM_CP_OVERRIDE | ARM_CP_NO_RAW, .writefn = omap_cachemaint_write }, { .name = "C9", .cp = 15, .crn = 9, .crm = CP_ANY, .opc1 = CP_ANY, .opc2 = CP_ANY, .access = PL1_RW, @@ -1779,7 +1967,7 @@ static const ARMCPRegInfo dummy_c15_cp_reginfo[] = { { .name = "C15_IMPDEF", .cp = 15, .crn = 15, .crm = CP_ANY, .opc1 = CP_ANY, .opc2 = CP_ANY, .access = PL1_RW, - .type = ARM_CP_CONST | ARM_CP_NO_MIGRATE | ARM_CP_OVERRIDE, + .type = ARM_CP_CONST | ARM_CP_NO_RAW | ARM_CP_OVERRIDE, .resetvalue = 0 }, REGINFO_SENTINEL }; @@ -1787,7 +1975,7 @@ static const ARMCPRegInfo dummy_c15_cp_reginfo[] = { static const ARMCPRegInfo cache_dirty_status_cp_reginfo[] = { /* Cache status: RAZ because we have no cache so it's always clean */ { .name = "CDSR", .cp = 15, .crn = 7, .crm = 10, .opc1 = 0, .opc2 = 6, - .access = PL1_R, .type = ARM_CP_CONST | ARM_CP_NO_MIGRATE, + .access = PL1_R, .type = ARM_CP_CONST | ARM_CP_NO_RAW, .resetvalue = 0 }, REGINFO_SENTINEL }; @@ -1795,7 +1983,7 @@ static const ARMCPRegInfo cache_dirty_status_cp_reginfo[] = { static const ARMCPRegInfo cache_block_ops_cp_reginfo[] = { /* We never have a a block transfer operation in progress */ { .name = "BXSR", .cp = 15, .crn = 7, .crm = 12, .opc1 = 0, .opc2 = 4, - .access = PL0_R, .type = ARM_CP_CONST | ARM_CP_NO_MIGRATE, + .access = PL0_R, .type = ARM_CP_CONST | ARM_CP_NO_RAW, .resetvalue = 0 }, /* The cache ops themselves: these all NOP for QEMU */ { .name = "IICR", .cp = 15, .crm = 5, .opc1 = 0, @@ -1818,10 +2006,10 @@ static const ARMCPRegInfo cache_test_clean_cp_reginfo[] = { * to indicate that there are no dirty cache lines. */ { .name = "TC_DCACHE", .cp = 15, .crn = 7, .crm = 10, .opc1 = 0, .opc2 = 3, - .access = PL0_R, .type = ARM_CP_CONST | ARM_CP_NO_MIGRATE, + .access = PL0_R, .type = ARM_CP_CONST | ARM_CP_NO_RAW, .resetvalue = (1 << 30) }, { .name = "TCI_DCACHE", .cp = 15, .crn = 7, .crm = 14, .opc1 = 0, .opc2 = 3, - .access = PL0_R, .type = ARM_CP_CONST | ARM_CP_NO_MIGRATE, + .access = PL0_R, .type = ARM_CP_CONST | ARM_CP_NO_RAW, .resetvalue = (1 << 30) }, REGINFO_SENTINEL }; @@ -1831,7 +2019,7 @@ static const ARMCPRegInfo strongarm_cp_reginfo[] = { { .name = "C9_READBUFFER", .cp = 15, .crn = 9, .crm = CP_ANY, .opc1 = CP_ANY, .opc2 = CP_ANY, .access = PL1_RW, .resetvalue = 0, - .type = ARM_CP_CONST | ARM_CP_OVERRIDE | ARM_CP_NO_MIGRATE }, + .type = ARM_CP_CONST | ARM_CP_OVERRIDE | ARM_CP_NO_RAW }, REGINFO_SENTINEL }; @@ -1857,7 +2045,7 @@ static uint64_t mpidr_read(CPUARMState *env, const ARMCPRegInfo *ri) static const ARMCPRegInfo mpidr_cp_reginfo[] = { { .name = "MPIDR", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 0, .opc2 = 5, - .access = PL1_R, .readfn = mpidr_read, .type = ARM_CP_NO_MIGRATE }, + .access = PL1_R, .readfn = mpidr_read, .type = ARM_CP_NO_RAW }, REGINFO_SENTINEL }; @@ -1874,15 +2062,18 @@ static const ARMCPRegInfo lpae_cp_reginfo[] = { .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_OVERRIDE, .resetvalue = 0 }, { .name = "PAR", .cp = 15, .crm = 7, .opc1 = 0, - .access = PL1_RW, .type = ARM_CP_64BIT, - .fieldoffset = offsetof(CPUARMState, cp15.par_el1), .resetvalue = 0 }, + .access = PL1_RW, .type = ARM_CP_64BIT, .resetvalue = 0, + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.par_s), + offsetof(CPUARMState, cp15.par_ns)} }, { .name = "TTBR0", .cp = 15, .crm = 2, .opc1 = 0, - .access = PL1_RW, .type = ARM_CP_64BIT | ARM_CP_NO_MIGRATE, - .fieldoffset = offsetof(CPUARMState, cp15.ttbr0_el1), + .access = PL1_RW, .type = ARM_CP_64BIT | ARM_CP_ALIAS, + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.ttbr0_s), + offsetof(CPUARMState, cp15.ttbr0_ns) }, .writefn = vmsa_ttbr_write, .resetfn = arm_cp_reset_ignore }, { .name = "TTBR1", .cp = 15, .crm = 2, .opc1 = 1, - .access = PL1_RW, .type = ARM_CP_64BIT | ARM_CP_NO_MIGRATE, - .fieldoffset = offsetof(CPUARMState, cp15.ttbr1_el1), + .access = PL1_RW, .type = ARM_CP_64BIT | ARM_CP_ALIAS, + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.ttbr1_s), + offsetof(CPUARMState, cp15.ttbr1_ns) }, .writefn = vmsa_ttbr_write, .resetfn = arm_cp_reset_ignore }, REGINFO_SENTINEL }; @@ -1911,7 +2102,7 @@ static void aa64_fpsr_write(CPUARMState *env, const ARMCPRegInfo *ri, static CPAccessResult aa64_daif_access(CPUARMState *env, const ARMCPRegInfo *ri) { - if (arm_current_el(env) == 0 && !(env->cp15.c1_sys & SCTLR_UMA)) { + if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_UMA)) { return CP_ACCESS_TRAP; } return CP_ACCESS_OK; @@ -1929,7 +2120,7 @@ static CPAccessResult aa64_cacheop_access(CPUARMState *env, /* Cache invalidate/clean: NOP, but EL0 must UNDEF unless * SCTLR_EL1.UCI is set. */ - if (arm_current_el(env) == 0 && !(env->cp15.c1_sys & SCTLR_UCI)) { + if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_UCI)) { return CP_ACCESS_TRAP; } return CP_ACCESS_OK; @@ -2006,7 +2197,7 @@ static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri) /* We don't implement EL2, so the only control on DC ZVA is the * bit in the SCTLR which can prohibit access for EL0. */ - if (arm_current_el(env) == 0 && !(env->cp15.c1_sys & SCTLR_DZE)) { + if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_DZE)) { return CP_ACCESS_TRAP; } return CP_ACCESS_OK; @@ -2045,6 +2236,24 @@ static void spsel_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t val) update_spsel(env, val); } +static void sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + ARMCPU *cpu = arm_env_get_cpu(env); + + if (raw_read(env, ri) == value) { + /* Skip the TLB flush if nothing actually changed; Linux likes + * to do a lot of pointless SCTLR writes. + */ + return; + } + + raw_write(env, ri, value); + /* ??? Lots of these bits are not implemented. */ + /* This may enable/disable the MMU, so do a TLB flush. */ + tlb_flush(CPU(cpu), 1); +} + static const ARMCPRegInfo v8_cp_reginfo[] = { /* Minimal set of EL0-visible registers. This will need to be expanded * significantly for system emulation of AArch64 CPUs. @@ -2054,7 +2263,7 @@ static const ARMCPRegInfo v8_cp_reginfo[] = { .access = PL0_RW, .type = ARM_CP_NZCV }, { .name = "DAIF", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .opc2 = 1, .crn = 4, .crm = 2, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_NO_RAW, .access = PL0_RW, .accessfn = aa64_daif_access, .fieldoffset = offsetof(CPUARMState, daif), .writefn = aa64_daif_write, .resetfn = arm_cp_reset_ignore }, @@ -2066,7 +2275,7 @@ static const ARMCPRegInfo v8_cp_reginfo[] = { .access = PL0_RW, .readfn = aa64_fpsr_read, .writefn = aa64_fpsr_write }, { .name = "DCZID_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .opc2 = 7, .crn = 0, .crm = 0, - .access = PL0_R, .type = ARM_CP_NO_MIGRATE, + .access = PL0_R, .type = ARM_CP_NO_RAW, .readfn = aa64_dczid_read }, { .name = "DC_ZVA", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 3, .crn = 7, .crm = 4, .opc2 = 1, @@ -2117,77 +2326,77 @@ static const ARMCPRegInfo v8_cp_reginfo[] = { /* TLBI operations */ { .name = "TLBI_VMALLE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 0, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbiall_is_write }, { .name = "TLBI_VAE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 1, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_va_is_write }, { .name = "TLBI_ASIDE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 2, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_asid_is_write }, { .name = "TLBI_VAAE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 3, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_vaa_is_write }, { .name = "TLBI_VALE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 5, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_va_is_write }, { .name = "TLBI_VAALE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 7, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_vaa_is_write }, { .name = "TLBI_VMALLE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 0, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbiall_write }, { .name = "TLBI_VAE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 1, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_va_write }, { .name = "TLBI_ASIDE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 2, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_asid_write }, { .name = "TLBI_VAAE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 3, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_vaa_write }, { .name = "TLBI_VALE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 5, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_va_write }, { .name = "TLBI_VAALE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 7, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_vaa_write }, #ifndef CONFIG_USER_ONLY /* 64 bit address translation operations */ { .name = "AT_S1E1R", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 7, .crm = 8, .opc2 = 0, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, .writefn = ats_write }, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = ats_write64 }, { .name = "AT_S1E1W", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 7, .crm = 8, .opc2 = 1, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, .writefn = ats_write }, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = ats_write64 }, { .name = "AT_S1E0R", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 7, .crm = 8, .opc2 = 2, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, .writefn = ats_write }, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = ats_write64 }, { .name = "AT_S1E0W", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 7, .crm = 8, .opc2 = 3, - .access = PL1_W, .type = ARM_CP_NO_MIGRATE, .writefn = ats_write }, + .access = PL1_W, .type = ARM_CP_NO_RAW, .writefn = ats_write64 }, #endif /* TLB invalidate last level of translation table walk */ { .name = "TLBIMVALIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 5, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbimva_is_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimva_is_write }, { .name = "TLBIMVAALIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 7, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimvaa_is_write }, { .name = "TLBIMVAL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 5, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbimva_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimva_write }, { .name = "TLBIMVAAL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 7, - .type = ARM_CP_NO_MIGRATE, .access = PL1_W, .writefn = tlbimvaa_write }, + .type = ARM_CP_NO_RAW, .access = PL1_W, .writefn = tlbimvaa_write }, /* 32 bit cache operations */ { .name = "ICIALLUIS", .cp = 15, .opc1 = 0, .crn = 7, .crm = 1, .opc2 = 0, .type = ARM_CP_NOP, .access = PL1_W }, @@ -2216,19 +2425,20 @@ static const ARMCPRegInfo v8_cp_reginfo[] = { { .name = "DCCISW", .cp = 15, .opc1 = 0, .crn = 7, .crm = 14, .opc2 = 2, .type = ARM_CP_NOP, .access = PL1_W }, /* MMU Domain access control / MPU write buffer control */ - { .name = "DACR", .cp = 15, - .opc1 = 0, .crn = 3, .crm = 0, .opc2 = 0, - .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.c3), - .resetvalue = 0, .writefn = dacr_write, .raw_writefn = raw_write, }, + { .name = "DACR", .cp = 15, .opc1 = 0, .crn = 3, .crm = 0, .opc2 = 0, + .access = PL1_RW, .resetvalue = 0, + .writefn = dacr_write, .raw_writefn = raw_write, + .bank_fieldoffsets = { offsetoflow32(CPUARMState, cp15.dacr_s), + offsetoflow32(CPUARMState, cp15.dacr_ns) } }, { .name = "ELR_EL1", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 0, .crn = 4, .crm = 0, .opc2 = 1, .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, elr_el[1]) }, { .name = "SPSR_EL1", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 0, .crn = 4, .crm = 0, .opc2 = 0, - .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, banked_spsr[0]) }, + .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, banked_spsr[1]) }, /* We rely on the access checks not allowing the guest to write to the * state field when SPSel indicates that it's being used as the stack * pointer. @@ -2236,11 +2446,15 @@ static const ARMCPRegInfo v8_cp_reginfo[] = { { .name = "SP_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 4, .crm = 1, .opc2 = 0, .access = PL1_RW, .accessfn = sp_el0_access, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .fieldoffset = offsetof(CPUARMState, sp_el[0]) }, + { .name = "SP_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 4, .crm = 1, .opc2 = 0, + .access = PL2_RW, .type = ARM_CP_ALIAS, + .fieldoffset = offsetof(CPUARMState, sp_el[1]) }, { .name = "SPSel", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 4, .crm = 2, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_NO_RAW, .access = PL1_RW, .readfn = spsel_read, .writefn = spsel_write }, REGINFO_SENTINEL }; @@ -2252,7 +2466,7 @@ static const ARMCPRegInfo v8_el3_no_el2_cp_reginfo[] = { .access = PL2_RW, .readfn = arm_cp_read_zero, .writefn = arm_cp_write_ignore }, { .name = "HCR_EL2", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_NO_RAW, .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0, .access = PL2_RW, .readfn = arm_cp_read_zero, .writefn = arm_cp_write_ignore }, @@ -2289,20 +2503,29 @@ static const ARMCPRegInfo v8_el2_cp_reginfo[] = { .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.hcr_el2), .writefn = hcr_write }, + { .name = "DACR32_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 3, .crm = 0, .opc2 = 0, + .access = PL2_RW, .resetvalue = 0, + .writefn = dacr_write, .raw_writefn = raw_write, + .fieldoffset = offsetof(CPUARMState, cp15.dacr32_el2) }, { .name = "ELR_EL2", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 4, .crn = 4, .crm = 0, .opc2 = 1, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, elr_el[2]) }, { .name = "ESR_EL2", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 2, .opc2 = 0, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.esr_el[2]) }, + { .name = "IFSR32_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 0, .opc2 = 1, + .access = PL2_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.ifsr32_el2) }, { .name = "FAR_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 6, .crm = 0, .opc2 = 0, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.far_el[2]) }, { .name = "SPSR_EL2", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 4, .crn = 4, .crm = 0, .opc2 = 0, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, banked_spsr[6]) }, { .name = "VBAR_EL2", .state = ARM_CP_STATE_AA64, @@ -2310,24 +2533,64 @@ static const ARMCPRegInfo v8_el2_cp_reginfo[] = { .access = PL2_RW, .writefn = vbar_write, .fieldoffset = offsetof(CPUARMState, cp15.vbar_el[2]), .resetvalue = 0 }, + { .name = "SP_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 4, .crm = 1, .opc2 = 0, + .access = PL3_RW, .type = ARM_CP_ALIAS, + .fieldoffset = offsetof(CPUARMState, sp_el[2]) }, REGINFO_SENTINEL }; -static const ARMCPRegInfo v8_el3_cp_reginfo[] = { +static const ARMCPRegInfo el3_cp_reginfo[] = { + { .name = "SCR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 1, .opc2 = 0, + .access = PL3_RW, .fieldoffset = offsetof(CPUARMState, cp15.scr_el3), + .resetvalue = 0, .writefn = scr_write }, + { .name = "SCR", .type = ARM_CP_ALIAS, + .cp = 15, .opc1 = 0, .crn = 1, .crm = 1, .opc2 = 0, + .access = PL3_RW, .fieldoffset = offsetoflow32(CPUARMState, cp15.scr_el3), + .resetfn = arm_cp_reset_ignore, .writefn = scr_write }, + { .name = "SDER32_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 1, .opc2 = 1, + .access = PL3_RW, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.sder) }, + { .name = "SDER", + .cp = 15, .opc1 = 0, .crn = 1, .crm = 1, .opc2 = 1, + .access = PL3_RW, .resetvalue = 0, + .fieldoffset = offsetoflow32(CPUARMState, cp15.sder) }, + /* TODO: Implement NSACR trapping of secure EL1 accesses to EL3 */ + { .name = "NSACR", .cp = 15, .opc1 = 0, .crn = 1, .crm = 1, .opc2 = 2, + .access = PL3_W | PL1_R, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.nsacr) }, + { .name = "MVBAR", .cp = 15, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 1, + .access = PL3_RW, .writefn = vbar_write, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.mvbar) }, + { .name = "SCTLR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 0, .opc2 = 0, + .access = PL3_RW, .raw_writefn = raw_write, .writefn = sctlr_write, + .fieldoffset = offsetof(CPUARMState, cp15.sctlr_el[3]) }, + { .name = "TTBR0_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 2, .crm = 0, .opc2 = 0, + .access = PL3_RW, .writefn = vmsa_ttbr_write, .resetvalue = 0, + .fieldoffset = offsetof(CPUARMState, cp15.ttbr0_el[3]) }, + { .name = "TCR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 2, .crm = 0, .opc2 = 2, + .access = PL3_RW, .writefn = vmsa_tcr_el1_write, + .resetfn = vmsa_ttbcr_reset, .raw_writefn = raw_write, + .fieldoffset = offsetof(CPUARMState, cp15.tcr_el[3]) }, { .name = "ELR_EL3", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 6, .crn = 4, .crm = 0, .opc2 = 1, .access = PL3_RW, .fieldoffset = offsetof(CPUARMState, elr_el[3]) }, { .name = "ESR_EL3", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 6, .crn = 5, .crm = 2, .opc2 = 0, .access = PL3_RW, .fieldoffset = offsetof(CPUARMState, cp15.esr_el[3]) }, { .name = "FAR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 6, .crm = 0, .opc2 = 0, .access = PL3_RW, .fieldoffset = offsetof(CPUARMState, cp15.far_el[3]) }, { .name = "SPSR_EL3", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 6, .crn = 4, .crm = 0, .opc2 = 0, .access = PL3_RW, .fieldoffset = offsetof(CPUARMState, banked_spsr[7]) }, { .name = "VBAR_EL3", .state = ARM_CP_STATE_AA64, @@ -2335,38 +2598,15 @@ static const ARMCPRegInfo v8_el3_cp_reginfo[] = { .access = PL3_RW, .writefn = vbar_write, .fieldoffset = offsetof(CPUARMState, cp15.vbar_el[3]), .resetvalue = 0 }, - { .name = "SCR_EL3", .state = ARM_CP_STATE_AA64, - .type = ARM_CP_NO_MIGRATE, - .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 1, .opc2 = 0, - .access = PL3_RW, .fieldoffset = offsetof(CPUARMState, cp15.scr_el3), - .writefn = scr_write }, REGINFO_SENTINEL }; -static void sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - ARMCPU *cpu = arm_env_get_cpu(env); - - if (raw_read(env, ri) == value) { - /* Skip the TLB flush if nothing actually changed; Linux likes - * to do a lot of pointless SCTLR writes. - */ - return; - } - - raw_write(env, ri, value); - /* ??? Lots of these bits are not implemented. */ - /* This may enable/disable the MMU, so do a TLB flush. */ - tlb_flush(CPU(cpu), 1); -} - static CPAccessResult ctr_el0_access(CPUARMState *env, const ARMCPRegInfo *ri) { /* Only accessible in EL0 if SCTLR.UCT is set (and only in AArch64, * but the AArch32 CTR has its own reginfo struct) */ - if (arm_current_el(env) == 0 && !(env->cp15.c1_sys & SCTLR_UCT)) { + if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_UCT)) { return CP_ACCESS_TRAP; } return CP_ACCESS_OK; @@ -2397,7 +2637,7 @@ static const ARMCPRegInfo debug_cp_reginfo[] = { */ { .name = "MDCCSR_EL0", .state = ARM_CP_STATE_BOTH, .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = 1, .opc2 = 0, - .type = ARM_CP_NO_MIGRATE, + .type = ARM_CP_ALIAS, .access = PL1_R, .fieldoffset = offsetof(CPUARMState, cp15.mdscr_el1), .resetfn = arm_cp_reset_ignore }, @@ -2850,7 +3090,7 @@ void register_cp_regs_for_features(ARMCPU *cpu) ARMCPRegInfo pmcr = { .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0, .access = PL0_RW, - .type = ARM_CP_IO | ARM_CP_NO_MIGRATE, + .type = ARM_CP_IO | ARM_CP_ALIAS, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmcr), .accessfn = pmreg_access, .writefn = pmcr_write, .raw_writefn = raw_write, @@ -2940,17 +3180,30 @@ void register_cp_regs_for_features(ARMCPU *cpu) .resetvalue = cpu->mvfr2 }, REGINFO_SENTINEL }; - ARMCPRegInfo rvbar = { - .name = "RVBAR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 2, - .type = ARM_CP_CONST, .access = PL1_R, .resetvalue = cpu->rvbar - }; - define_one_arm_cp_reg(cpu, &rvbar); + /* RVBAR_EL1 is only implemented if EL1 is the highest EL */ + if (!arm_feature(env, ARM_FEATURE_EL3) && + !arm_feature(env, ARM_FEATURE_EL2)) { + ARMCPRegInfo rvbar = { + .name = "RVBAR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 1, + .type = ARM_CP_CONST, .access = PL1_R, .resetvalue = cpu->rvbar + }; + define_one_arm_cp_reg(cpu, &rvbar); + } define_arm_cp_regs(cpu, v8_idregs); define_arm_cp_regs(cpu, v8_cp_reginfo); } if (arm_feature(env, ARM_FEATURE_EL2)) { define_arm_cp_regs(cpu, v8_el2_cp_reginfo); + /* RVBAR_EL2 is only implemented if EL2 is the highest EL */ + if (!arm_feature(env, ARM_FEATURE_EL3)) { + ARMCPRegInfo rvbar = { + .name = "RVBAR_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 0, .opc2 = 1, + .type = ARM_CP_CONST, .access = PL2_R, .resetvalue = cpu->rvbar + }; + define_one_arm_cp_reg(cpu, &rvbar); + } } else { /* If EL2 is missing but higher ELs are enabled, we need to * register the no_el2 reginfos. @@ -2960,7 +3213,13 @@ void register_cp_regs_for_features(ARMCPU *cpu) } } if (arm_feature(env, ARM_FEATURE_EL3)) { - define_arm_cp_regs(cpu, v8_el3_cp_reginfo); + define_arm_cp_regs(cpu, el3_cp_reginfo); + ARMCPRegInfo rvbar = { + .name = "RVBAR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 12, .crm = 0, .opc2 = 1, + .type = ARM_CP_CONST, .access = PL3_R, .resetvalue = cpu->rvbar + }; + define_one_arm_cp_reg(cpu, &rvbar); } if (arm_feature(env, ARM_FEATURE_MPU)) { /* These are the MPU registers prior to PMSAv6. Any new @@ -3160,8 +3419,10 @@ void register_cp_regs_for_features(ARMCPU *cpu) { ARMCPRegInfo sctlr = { .name = "SCTLR", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .crn = 1, .crm = 0, .opc1 = 0, .opc2 = 0, - .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.c1_sys), + .opc0 = 3, .opc1 = 0, .crn = 1, .crm = 0, .opc2 = 0, + .access = PL1_RW, + .bank_fieldoffsets = { offsetof(CPUARMState, cp15.sctlr_s), + offsetof(CPUARMState, cp15.sctlr_ns) }, .writefn = sctlr_write, .resetvalue = cpu->reset_sctlr, .raw_writefn = raw_write, }; @@ -3287,7 +3548,7 @@ CpuDefinitionInfoList *arch_query_cpu_definitions(Error **errp) } static void add_cpreg_to_hashtable(ARMCPU *cpu, const ARMCPRegInfo *r, - void *opaque, int state, + void *opaque, int state, int secstate, int crm, int opc1, int opc2) { /* Private utility function for define_one_arm_cp_reg_with_opaque(): @@ -3296,22 +3557,59 @@ static void add_cpreg_to_hashtable(ARMCPU *cpu, const ARMCPRegInfo *r, uint32_t *key = g_new(uint32_t, 1); ARMCPRegInfo *r2 = g_memdup(r, sizeof(ARMCPRegInfo)); int is64 = (r->type & ARM_CP_64BIT) ? 1 : 0; - if (r->state == ARM_CP_STATE_BOTH && state == ARM_CP_STATE_AA32) { - /* The AArch32 view of a shared register sees the lower 32 bits - * of a 64 bit backing field. It is not migratable as the AArch64 - * view handles that. AArch64 also handles reset. - * We assume it is a cp15 register if the .cp field is left unset. + int ns = (secstate & ARM_CP_SECSTATE_NS) ? 1 : 0; + + /* Reset the secure state to the specific incoming state. This is + * necessary as the register may have been defined with both states. + */ + r2->secure = secstate; + + if (r->bank_fieldoffsets[0] && r->bank_fieldoffsets[1]) { + /* Register is banked (using both entries in array). + * Overwriting fieldoffset as the array is only used to define + * banked registers but later only fieldoffset is used. */ - if (r2->cp == 0) { - r2->cp = 15; + r2->fieldoffset = r->bank_fieldoffsets[ns]; + } + + if (state == ARM_CP_STATE_AA32) { + if (r->bank_fieldoffsets[0] && r->bank_fieldoffsets[1]) { + /* If the register is banked then we don't need to migrate or + * reset the 32-bit instance in certain cases: + * + * 1) If the register has both 32-bit and 64-bit instances then we + * can count on the 64-bit instance taking care of the + * non-secure bank. + * 2) If ARMv8 is enabled then we can count on a 64-bit version + * taking care of the secure bank. This requires that separate + * 32 and 64-bit definitions are provided. + */ + if ((r->state == ARM_CP_STATE_BOTH && ns) || + (arm_feature(&cpu->env, ARM_FEATURE_V8) && !ns)) { + r2->type |= ARM_CP_ALIAS; + r2->resetfn = arm_cp_reset_ignore; + } + } else if ((secstate != r->secure) && !ns) { + /* The register is not banked so we only want to allow migration of + * the non-secure instance. + */ + r2->type |= ARM_CP_ALIAS; + r2->resetfn = arm_cp_reset_ignore; } - r2->type |= ARM_CP_NO_MIGRATE; - r2->resetfn = arm_cp_reset_ignore; + + if (r->state == ARM_CP_STATE_BOTH) { + /* We assume it is a cp15 register if the .cp field is left unset. + */ + if (r2->cp == 0) { + r2->cp = 15; + } + #ifdef HOST_WORDS_BIGENDIAN - if (r2->fieldoffset) { - r2->fieldoffset += sizeof(uint32_t); - } + if (r2->fieldoffset) { + r2->fieldoffset += sizeof(uint32_t); + } #endif + } } if (state == ARM_CP_STATE_AA64) { /* To allow abbreviation of ARMCPRegInfo @@ -3327,7 +3625,7 @@ static void add_cpreg_to_hashtable(ARMCPU *cpu, const ARMCPRegInfo *r, *key = ENCODE_AA64_CP_REG(r2->cp, r2->crn, crm, r2->opc0, opc1, opc2); } else { - *key = ENCODE_CP_REG(r2->cp, is64, r2->crn, crm, opc1, opc2); + *key = ENCODE_CP_REG(r2->cp, is64, ns, r2->crn, crm, opc1, opc2); } if (opaque) { r2->opaque = opaque; @@ -3344,15 +3642,25 @@ static void add_cpreg_to_hashtable(ARMCPU *cpu, const ARMCPRegInfo *r, r2->opc2 = opc2; /* By convention, for wildcarded registers only the first * entry is used for migration; the others are marked as - * NO_MIGRATE so we don't try to transfer the register + * ALIAS so we don't try to transfer the register * multiple times. Special registers (ie NOP/WFI) are - * never migratable. + * never migratable and not even raw-accessible. */ - if ((r->type & ARM_CP_SPECIAL) || - ((r->crm == CP_ANY) && crm != 0) || + if ((r->type & ARM_CP_SPECIAL)) { + r2->type |= ARM_CP_NO_RAW; + } + if (((r->crm == CP_ANY) && crm != 0) || ((r->opc1 == CP_ANY) && opc1 != 0) || ((r->opc2 == CP_ANY) && opc2 != 0)) { - r2->type |= ARM_CP_NO_MIGRATE; + r2->type |= ARM_CP_ALIAS; + } + + /* Check that raw accesses are either forbidden or handled. Note that + * we can't assert this earlier because the setup of fieldoffset for + * banked registers has to be done first. + */ + if (!(r2->type & ARM_CP_NO_RAW)) { + assert(!raw_accessors_invalid(r2)); } /* Overriding of an existing definition must be explicitly @@ -3460,10 +3768,14 @@ void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu, */ if (!(r->type & (ARM_CP_SPECIAL|ARM_CP_CONST))) { if (r->access & PL3_R) { - assert(r->fieldoffset || r->readfn); + assert((r->fieldoffset || + (r->bank_fieldoffsets[0] && r->bank_fieldoffsets[1])) || + r->readfn); } if (r->access & PL3_W) { - assert(r->fieldoffset || r->writefn); + assert((r->fieldoffset || + (r->bank_fieldoffsets[0] && r->bank_fieldoffsets[1])) || + r->writefn); } } /* Bad type field probably means missing sentinel at end of reg list */ @@ -3476,8 +3788,32 @@ void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu, if (r->state != state && r->state != ARM_CP_STATE_BOTH) { continue; } - add_cpreg_to_hashtable(cpu, r, opaque, state, - crm, opc1, opc2); + if (state == ARM_CP_STATE_AA32) { + /* Under AArch32 CP registers can be common + * (same for secure and non-secure world) or banked. + */ + switch (r->secure) { + case ARM_CP_SECSTATE_S: + case ARM_CP_SECSTATE_NS: + add_cpreg_to_hashtable(cpu, r, opaque, state, + r->secure, crm, opc1, opc2); + break; + default: + add_cpreg_to_hashtable(cpu, r, opaque, state, + ARM_CP_SECSTATE_S, + crm, opc1, opc2); + add_cpreg_to_hashtable(cpu, r, opaque, state, + ARM_CP_SECSTATE_NS, + crm, opc1, opc2); + break; + } + } else { + /* AArch64 registers get mapped to non-secure instance + * of AArch32 */ + add_cpreg_to_hashtable(cpu, r, opaque, state, + ARM_CP_SECSTATE_NS, + crm, opc1, opc2); + } } } } @@ -3551,6 +3887,8 @@ uint32_t cpsr_read(CPUARMState *env) void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask) { + uint32_t changed_daif; + if (mask & CPSR_NZCV) { env->ZF = (~val) & CPSR_Z; env->NF = val; @@ -3573,6 +3911,58 @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask) env->GE = (val >> 16) & 0xf; } + /* In a V7 implementation that includes the security extensions but does + * not include Virtualization Extensions the SCR.FW and SCR.AW bits control + * whether non-secure software is allowed to change the CPSR_F and CPSR_A + * bits respectively. + * + * In a V8 implementation, it is permitted for privileged software to + * change the CPSR A/F bits regardless of the SCR.AW/FW bits. + */ + if (!arm_feature(env, ARM_FEATURE_V8) && + arm_feature(env, ARM_FEATURE_EL3) && + !arm_feature(env, ARM_FEATURE_EL2) && + !arm_is_secure(env)) { + + changed_daif = (env->daif ^ val) & mask; + + if (changed_daif & CPSR_A) { + /* Check to see if we are allowed to change the masking of async + * abort exceptions from a non-secure state. + */ + if (!(env->cp15.scr_el3 & SCR_AW)) { + qemu_log_mask(LOG_GUEST_ERROR, + "Ignoring attempt to switch CPSR_A flag from " + "non-secure world with SCR.AW bit clear\n"); + mask &= ~CPSR_A; + } + } + + if (changed_daif & CPSR_F) { + /* Check to see if we are allowed to change the masking of FIQ + * exceptions from a non-secure state. + */ + if (!(env->cp15.scr_el3 & SCR_FW)) { + qemu_log_mask(LOG_GUEST_ERROR, + "Ignoring attempt to switch CPSR_F flag from " + "non-secure world with SCR.FW bit clear\n"); + mask &= ~CPSR_F; + } + + /* Check whether non-maskable FIQ (NMFI) support is enabled. + * If this bit is set software is not allowed to mask + * FIQs, but is allowed to set CPSR_F to 0. + */ + if ((A32_BANKED_CURRENT_REG_GET(env, sctlr) & SCTLR_NMFI) && + (val & CPSR_F)) { + qemu_log_mask(LOG_GUEST_ERROR, + "Ignoring attempt to enable CPSR_F flag " + "(non-maskable FIQ [NMFI] support enabled)\n"); + mask &= ~CPSR_F; + } + } + } + env->daif &= ~(CPSR_AIF & mask); env->daif |= val & CPSR_AIF & mask; @@ -3706,6 +4096,11 @@ unsigned int arm_excp_target_el(CPUState *cs, unsigned int excp_idx) return 1; } +void aarch64_sync_64_to_32(CPUARMState *env) +{ + g_assert_not_reached(); +} + #else /* Map CPU modes onto saved register banks. */ @@ -3761,6 +4156,101 @@ void switch_mode(CPUARMState *env, int mode) env->spsr = env->banked_spsr[i]; } +/* Physical Interrupt Target EL Lookup Table + * + * [ From ARM ARM section G1.13.4 (Table G1-15) ] + * + * The below multi-dimensional table is used for looking up the target + * exception level given numerous condition criteria. Specifically, the + * target EL is based on SCR and HCR routing controls as well as the + * currently executing EL and secure state. + * + * Dimensions: + * target_el_table[2][2][2][2][2][4] + * | | | | | +--- Current EL + * | | | | +------ Non-secure(0)/Secure(1) + * | | | +--------- HCR mask override + * | | +------------ SCR exec state control + * | +--------------- SCR mask override + * +------------------ 32-bit(0)/64-bit(1) EL3 + * + * The table values are as such: + * 0-3 = EL0-EL3 + * -1 = Cannot occur + * + * The ARM ARM target EL table includes entries indicating that an "exception + * is not taken". The two cases where this is applicable are: + * 1) An exception is taken from EL3 but the SCR does not have the exception + * routed to EL3. + * 2) An exception is taken from EL2 but the HCR does not have the exception + * routed to EL2. + * In these two cases, the below table contain a target of EL1. This value is + * returned as it is expected that the consumer of the table data will check + * for "target EL >= current EL" to ensure the exception is not taken. + * + * SCR HCR + * 64 EA AMO From + * BIT IRQ IMO Non-secure Secure + * EL3 FIQ RW FMO EL0 EL1 EL2 EL3 EL0 EL1 EL2 EL3 + */ +const int8_t target_el_table[2][2][2][2][2][4] = { + {{{{/* 0 0 0 0 */{ 1, 1, 2, -1 },{ 3, -1, -1, 3 },}, + {/* 0 0 0 1 */{ 2, 2, 2, -1 },{ 3, -1, -1, 3 },},}, + {{/* 0 0 1 0 */{ 1, 1, 2, -1 },{ 3, -1, -1, 3 },}, + {/* 0 0 1 1 */{ 2, 2, 2, -1 },{ 3, -1, -1, 3 },},},}, + {{{/* 0 1 0 0 */{ 3, 3, 3, -1 },{ 3, -1, -1, 3 },}, + {/* 0 1 0 1 */{ 3, 3, 3, -1 },{ 3, -1, -1, 3 },},}, + {{/* 0 1 1 0 */{ 3, 3, 3, -1 },{ 3, -1, -1, 3 },}, + {/* 0 1 1 1 */{ 3, 3, 3, -1 },{ 3, -1, -1, 3 },},},},}, + {{{{/* 1 0 0 0 */{ 1, 1, 2, -1 },{ 1, 1, -1, 1 },}, + {/* 1 0 0 1 */{ 2, 2, 2, -1 },{ 1, 1, -1, 1 },},}, + {{/* 1 0 1 0 */{ 1, 1, 1, -1 },{ 1, 1, -1, 1 },}, + {/* 1 0 1 1 */{ 2, 2, 2, -1 },{ 1, 1, -1, 1 },},},}, + {{{/* 1 1 0 0 */{ 3, 3, 3, -1 },{ 3, 3, -1, 3 },}, + {/* 1 1 0 1 */{ 3, 3, 3, -1 },{ 3, 3, -1, 3 },},}, + {{/* 1 1 1 0 */{ 3, 3, 3, -1 },{ 3, 3, -1, 3 },}, + {/* 1 1 1 1 */{ 3, 3, 3, -1 },{ 3, 3, -1, 3 },},},},}, +}; + +/* + * Determine the target EL for physical exceptions + */ +static inline uint32_t arm_phys_excp_target_el(CPUState *cs, uint32_t excp_idx, + uint32_t cur_el, bool secure) +{ + CPUARMState *env = cs->env_ptr; + int rw = ((env->cp15.scr_el3 & SCR_RW) == SCR_RW); + int scr; + int hcr; + int target_el; + int is64 = arm_el_is_aa64(env, 3); + + switch (excp_idx) { + case EXCP_IRQ: + scr = ((env->cp15.scr_el3 & SCR_IRQ) == SCR_IRQ); + hcr = ((env->cp15.hcr_el2 & HCR_IMO) == HCR_IMO); + break; + case EXCP_FIQ: + scr = ((env->cp15.scr_el3 & SCR_FIQ) == SCR_FIQ); + hcr = ((env->cp15.hcr_el2 & HCR_FMO) == HCR_FMO); + break; + default: + scr = ((env->cp15.scr_el3 & SCR_EA) == SCR_EA); + hcr = ((env->cp15.hcr_el2 & HCR_AMO) == HCR_AMO); + break; + }; + + /* If HCR.TGE is set then HCR is treated as being 1 */ + hcr |= ((env->cp15.hcr_el2 & HCR_TGE) == HCR_TGE); + + /* Perform a table-lookup for the target EL given the current state */ + target_el = target_el_table[is64][scr][rw][hcr][secure][cur_el]; + + assert(target_el > 0); + + return target_el; +} + /* * Determine the target EL for a given exception type. */ @@ -3770,13 +4260,7 @@ unsigned int arm_excp_target_el(CPUState *cs, unsigned int excp_idx) CPUARMState *env = &cpu->env; unsigned int cur_el = arm_current_el(env); unsigned int target_el; - /* FIXME: Use actual secure state. */ - bool secure = false; - - if (!env->aarch64) { - /* TODO: Add EL2 and 3 exception handling for AArch32. */ - return 1; - } + bool secure = arm_is_secure(env); switch (excp_idx) { case EXCP_HVC: @@ -3788,19 +4272,8 @@ unsigned int arm_excp_target_el(CPUState *cs, unsigned int excp_idx) break; case EXCP_FIQ: case EXCP_IRQ: - { - const uint64_t hcr_mask = excp_idx == EXCP_FIQ ? HCR_FMO : HCR_IMO; - const uint32_t scr_mask = excp_idx == EXCP_FIQ ? SCR_FIQ : SCR_IRQ; - - target_el = 1; - if (!secure && (env->cp15.hcr_el2 & hcr_mask)) { - target_el = 2; - } - if (env->cp15.scr_el3 & scr_mask) { - target_el = 3; - } + target_el = arm_phys_excp_target_el(cs, excp_idx, cur_el, secure); break; - } case EXCP_VIRQ: case EXCP_VFIQ: target_el = 1; @@ -3861,6 +4334,16 @@ static void do_v7m_exception_exit(CPUARMState *env) env->regs[12] = v7m_pop(env); env->regs[14] = v7m_pop(env); env->regs[15] = v7m_pop(env); + if (env->regs[15] & 1) { + qemu_log_mask(LOG_GUEST_ERROR, + "M profile return from interrupt with misaligned " + "PC is UNPREDICTABLE\n"); + /* Actual hardware seems to ignore the lsbit, and there are several + * RTOSes out there which incorrectly assume the r15 in the stack + * frame should be a Thumb-style "lsbit indicates ARM/Thumb" value. + */ + env->regs[15] &= ~1U; + } xpsr = v7m_pop(env); xpsr_write(env, xpsr, 0xfffffdff); /* Undo stack alignment. */ @@ -3957,6 +4440,212 @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) env->thumb = addr & 1; } +/* Function used to synchronize QEMU's AArch64 register set with AArch32 + * register set. This is necessary when switching between AArch32 and AArch64 + * execution state. + */ +void aarch64_sync_32_to_64(CPUARMState *env) +{ + int i; + uint32_t mode = env->uncached_cpsr & CPSR_M; + + /* We can blanket copy R[0:7] to X[0:7] */ + for (i = 0; i < 8; i++) { + env->xregs[i] = env->regs[i]; + } + + /* Unless we are in FIQ mode, x8-x12 come from the user registers r8-r12. + * Otherwise, they come from the banked user regs. + */ + if (mode == ARM_CPU_MODE_FIQ) { + for (i = 8; i < 13; i++) { + env->xregs[i] = env->usr_regs[i - 8]; + } + } else { + for (i = 8; i < 13; i++) { + env->xregs[i] = env->regs[i]; + } + } + + /* Registers x13-x23 are the various mode SP and FP registers. Registers + * r13 and r14 are only copied if we are in that mode, otherwise we copy + * from the mode banked register. + */ + if (mode == ARM_CPU_MODE_USR || mode == ARM_CPU_MODE_SYS) { + env->xregs[13] = env->regs[13]; + env->xregs[14] = env->regs[14]; + } else { + env->xregs[13] = env->banked_r13[bank_number(ARM_CPU_MODE_USR)]; + /* HYP is an exception in that it is copied from r14 */ + if (mode == ARM_CPU_MODE_HYP) { + env->xregs[14] = env->regs[14]; + } else { + env->xregs[14] = env->banked_r14[bank_number(ARM_CPU_MODE_USR)]; + } + } + + if (mode == ARM_CPU_MODE_HYP) { + env->xregs[15] = env->regs[13]; + } else { + env->xregs[15] = env->banked_r13[bank_number(ARM_CPU_MODE_HYP)]; + } + + if (mode == ARM_CPU_MODE_IRQ) { + env->xregs[16] = env->regs[13]; + env->xregs[17] = env->regs[14]; + } else { + env->xregs[16] = env->banked_r13[bank_number(ARM_CPU_MODE_IRQ)]; + env->xregs[17] = env->banked_r14[bank_number(ARM_CPU_MODE_IRQ)]; + } + + if (mode == ARM_CPU_MODE_SVC) { + env->xregs[18] = env->regs[13]; + env->xregs[19] = env->regs[14]; + } else { + env->xregs[18] = env->banked_r13[bank_number(ARM_CPU_MODE_SVC)]; + env->xregs[19] = env->banked_r14[bank_number(ARM_CPU_MODE_SVC)]; + } + + if (mode == ARM_CPU_MODE_ABT) { + env->xregs[20] = env->regs[13]; + env->xregs[21] = env->regs[14]; + } else { + env->xregs[20] = env->banked_r13[bank_number(ARM_CPU_MODE_ABT)]; + env->xregs[21] = env->banked_r14[bank_number(ARM_CPU_MODE_ABT)]; + } + + if (mode == ARM_CPU_MODE_UND) { + env->xregs[22] = env->regs[13]; + env->xregs[23] = env->regs[14]; + } else { + env->xregs[22] = env->banked_r13[bank_number(ARM_CPU_MODE_UND)]; + env->xregs[23] = env->banked_r14[bank_number(ARM_CPU_MODE_UND)]; + } + + /* Registers x24-x30 are mapped to r8-r14 in FIQ mode. If we are in FIQ + * mode, then we can copy from r8-r14. Otherwise, we copy from the + * FIQ bank for r8-r14. + */ + if (mode == ARM_CPU_MODE_FIQ) { + for (i = 24; i < 31; i++) { + env->xregs[i] = env->regs[i - 16]; /* X[24:30] <- R[8:14] */ + } + } else { + for (i = 24; i < 29; i++) { + env->xregs[i] = env->fiq_regs[i - 24]; + } + env->xregs[29] = env->banked_r13[bank_number(ARM_CPU_MODE_FIQ)]; + env->xregs[30] = env->banked_r14[bank_number(ARM_CPU_MODE_FIQ)]; + } + + env->pc = env->regs[15]; +} + +/* Function used to synchronize QEMU's AArch32 register set with AArch64 + * register set. This is necessary when switching between AArch32 and AArch64 + * execution state. + */ +void aarch64_sync_64_to_32(CPUARMState *env) +{ + int i; + uint32_t mode = env->uncached_cpsr & CPSR_M; + + /* We can blanket copy X[0:7] to R[0:7] */ + for (i = 0; i < 8; i++) { + env->regs[i] = env->xregs[i]; + } + + /* Unless we are in FIQ mode, r8-r12 come from the user registers x8-x12. + * Otherwise, we copy x8-x12 into the banked user regs. + */ + if (mode == ARM_CPU_MODE_FIQ) { + for (i = 8; i < 13; i++) { + env->usr_regs[i - 8] = env->xregs[i]; + } + } else { + for (i = 8; i < 13; i++) { + env->regs[i] = env->xregs[i]; + } + } + + /* Registers r13 & r14 depend on the current mode. + * If we are in a given mode, we copy the corresponding x registers to r13 + * and r14. Otherwise, we copy the x register to the banked r13 and r14 + * for the mode. + */ + if (mode == ARM_CPU_MODE_USR || mode == ARM_CPU_MODE_SYS) { + env->regs[13] = env->xregs[13]; + env->regs[14] = env->xregs[14]; + } else { + env->banked_r13[bank_number(ARM_CPU_MODE_USR)] = env->xregs[13]; + + /* HYP is an exception in that it does not have its own banked r14 but + * shares the USR r14 + */ + if (mode == ARM_CPU_MODE_HYP) { + env->regs[14] = env->xregs[14]; + } else { + env->banked_r14[bank_number(ARM_CPU_MODE_USR)] = env->xregs[14]; + } + } + + if (mode == ARM_CPU_MODE_HYP) { + env->regs[13] = env->xregs[15]; + } else { + env->banked_r13[bank_number(ARM_CPU_MODE_HYP)] = env->xregs[15]; + } + + if (mode == ARM_CPU_MODE_IRQ) { + env->regs[13] = env->xregs[16]; + env->regs[14] = env->xregs[17]; + } else { + env->banked_r13[bank_number(ARM_CPU_MODE_IRQ)] = env->xregs[16]; + env->banked_r14[bank_number(ARM_CPU_MODE_IRQ)] = env->xregs[17]; + } + + if (mode == ARM_CPU_MODE_SVC) { + env->regs[13] = env->xregs[18]; + env->regs[14] = env->xregs[19]; + } else { + env->banked_r13[bank_number(ARM_CPU_MODE_SVC)] = env->xregs[18]; + env->banked_r14[bank_number(ARM_CPU_MODE_SVC)] = env->xregs[19]; + } + + if (mode == ARM_CPU_MODE_ABT) { + env->regs[13] = env->xregs[20]; + env->regs[14] = env->xregs[21]; + } else { + env->banked_r13[bank_number(ARM_CPU_MODE_ABT)] = env->xregs[20]; + env->banked_r14[bank_number(ARM_CPU_MODE_ABT)] = env->xregs[21]; + } + + if (mode == ARM_CPU_MODE_UND) { + env->regs[13] = env->xregs[22]; + env->regs[14] = env->xregs[23]; + } else { + env->banked_r13[bank_number(ARM_CPU_MODE_UND)] = env->xregs[22]; + env->banked_r14[bank_number(ARM_CPU_MODE_UND)] = env->xregs[23]; + } + + /* Registers x24-x30 are mapped to r8-r14 in FIQ mode. If we are in FIQ + * mode, then we can copy to r8-r14. Otherwise, we copy to the + * FIQ bank for r8-r14. + */ + if (mode == ARM_CPU_MODE_FIQ) { + for (i = 24; i < 31; i++) { + env->regs[i - 16] = env->xregs[i]; /* X[24:30] -> R[8:14] */ + } + } else { + for (i = 24; i < 29; i++) { + env->fiq_regs[i - 24] = env->xregs[i]; + } + env->banked_r13[bank_number(ARM_CPU_MODE_FIQ)] = env->xregs[29]; + env->banked_r14[bank_number(ARM_CPU_MODE_FIQ)] = env->xregs[30]; + } + + env->regs[15] = env->pc; +} + /* Handle a CPU exception. */ void arm_cpu_do_interrupt(CPUState *cs) { @@ -4055,22 +4744,20 @@ void arm_cpu_do_interrupt(CPUState *cs) env->exception.fsr = 2; /* Fall through to prefetch abort. */ case EXCP_PREFETCH_ABORT: - env->cp15.ifsr_el2 = env->exception.fsr; - env->cp15.far_el[1] = deposit64(env->cp15.far_el[1], 32, 32, - env->exception.vaddress); + A32_BANKED_CURRENT_REG_SET(env, ifsr, env->exception.fsr); + A32_BANKED_CURRENT_REG_SET(env, ifar, env->exception.vaddress); qemu_log_mask(CPU_LOG_INT, "...with IFSR 0x%x IFAR 0x%x\n", - env->cp15.ifsr_el2, (uint32_t)env->exception.vaddress); + env->exception.fsr, (uint32_t)env->exception.vaddress); new_mode = ARM_CPU_MODE_ABT; addr = 0x0c; mask = CPSR_A | CPSR_I; offset = 4; break; case EXCP_DATA_ABORT: - env->cp15.esr_el[1] = env->exception.fsr; - env->cp15.far_el[1] = deposit64(env->cp15.far_el[1], 0, 32, - env->exception.vaddress); + A32_BANKED_CURRENT_REG_SET(env, dfsr, env->exception.fsr); + A32_BANKED_CURRENT_REG_SET(env, dfar, env->exception.vaddress); qemu_log_mask(CPU_LOG_INT, "...with DFSR 0x%x DFAR 0x%x\n", - (uint32_t)env->cp15.esr_el[1], + env->exception.fsr, (uint32_t)env->exception.vaddress); new_mode = ARM_CPU_MODE_ABT; addr = 0x10; @@ -4083,12 +4770,21 @@ void arm_cpu_do_interrupt(CPUState *cs) /* Disable IRQ and imprecise data aborts. */ mask = CPSR_A | CPSR_I; offset = 4; + if (env->cp15.scr_el3 & SCR_IRQ) { + /* IRQ routed to monitor mode */ + new_mode = ARM_CPU_MODE_MON; + mask |= CPSR_F; + } break; case EXCP_FIQ: new_mode = ARM_CPU_MODE_FIQ; addr = 0x1c; /* Disable FIQ, IRQ and imprecise data aborts. */ mask = CPSR_A | CPSR_I | CPSR_F; + if (env->cp15.scr_el3 & SCR_FIQ) { + /* FIQ routed to monitor mode */ + new_mode = ARM_CPU_MODE_MON; + } offset = 4; break; case EXCP_SMC: @@ -4101,19 +4797,19 @@ void arm_cpu_do_interrupt(CPUState *cs) cpu_abort(cs, "Unhandled exception 0x%x\n", cs->exception_index); return; /* Never happens. Keep compiler happy. */ } - /* High vectors. */ - if (env->cp15.c1_sys & SCTLR_V) { - /* when enabled, base address cannot be remapped. */ + + if (new_mode == ARM_CPU_MODE_MON) { + addr += env->cp15.mvbar; + } else if (A32_BANKED_CURRENT_REG_GET(env, sctlr) & SCTLR_V) { + /* High vectors. When enabled, base address cannot be remapped. */ addr += 0xffff0000; } else { /* ARM v7 architectures provide a vector base address register to remap * the interrupt vector table. - * This register is only followed in non-monitor mode, and has a secure - * and un-secure copy. Since the cpu is always in a un-secure operation - * and is never in monitor mode this feature is always active. + * This register is only followed in non-monitor mode, and is banked. * Note: only bits 31:5 are valid. */ - addr += env->cp15.vbar_el[1]; + addr += A32_BANKED_CURRENT_REG_GET(env, vbar); } if ((env->uncached_cpsr & CPSR_M) == ARM_CPU_MODE_MON) { @@ -4134,91 +4830,280 @@ void arm_cpu_do_interrupt(CPUState *cs) /* this is a lie, as the was no c1_sys on V4T/V5, but who cares * and we should just guard the thumb mode on V4 */ if (arm_feature(env, ARM_FEATURE_V4T)) { - env->thumb = (env->cp15.c1_sys & SCTLR_TE) != 0; + env->thumb = (A32_BANKED_CURRENT_REG_GET(env, sctlr) & SCTLR_TE) != 0; } env->regs[14] = env->regs[15] + offset; env->regs[15] = addr; cs->interrupt_request |= CPU_INTERRUPT_EXITTB; } -/* Check section/page access permissions. - Returns the page protection flags, or zero if the access is not - permitted. */ -static inline int check_ap(CPUARMState *env, int ap, int domain_prot, - int access_type, int is_user) -{ - int prot_ro; - - if (domain_prot == 3) { - return PAGE_READ | PAGE_WRITE; - } - - if (access_type == 1) - prot_ro = 0; - else - prot_ro = PAGE_READ; - - switch (ap) { - case 0: - if (arm_feature(env, ARM_FEATURE_V7)) { - return 0; - } - if (access_type == 1) - return 0; - switch (env->cp15.c1_sys & (SCTLR_S | SCTLR_R)) { - case SCTLR_S: - return is_user ? 0 : PAGE_READ; - case SCTLR_R: - return PAGE_READ; - default: - return 0; - } - case 1: - return is_user ? 0 : PAGE_READ | PAGE_WRITE; - case 2: - if (is_user) - return prot_ro; - else - return PAGE_READ | PAGE_WRITE; - case 3: - return PAGE_READ | PAGE_WRITE; - case 4: /* Reserved. */ - return 0; - case 5: - return is_user ? 0 : prot_ro; - case 6: - return prot_ro; - case 7: - if (!arm_feature (env, ARM_FEATURE_V6K)) - return 0; - return prot_ro; - default: - abort(); - } -} - -static bool get_level1_table_address(CPUARMState *env, uint32_t *table, - uint32_t address) -{ - if (address & env->cp15.c2_mask) { - if ((env->cp15.c2_control & TTBCR_PD1)) { + +/* Return the exception level which controls this address translation regime */ +static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) +{ + switch (mmu_idx) { + case ARMMMUIdx_S2NS: + case ARMMMUIdx_S1E2: + return 2; + case ARMMMUIdx_S1E3: + return 3; + case ARMMMUIdx_S1SE0: + return arm_el_is_aa64(env, 3) ? 1 : 3; + case ARMMMUIdx_S1SE1: + case ARMMMUIdx_S1NSE0: + case ARMMMUIdx_S1NSE1: + return 1; + default: + g_assert_not_reached(); + } +} + +/* Return the SCTLR value which controls this address translation regime */ +static inline uint32_t regime_sctlr(CPUARMState *env, ARMMMUIdx mmu_idx) +{ + return env->cp15.sctlr_el[regime_el(env, mmu_idx)]; +} + +/* Return true if the specified stage of address translation is disabled */ +static inline bool regime_translation_disabled(CPUARMState *env, + ARMMMUIdx mmu_idx) +{ + if (mmu_idx == ARMMMUIdx_S2NS) { + return (env->cp15.hcr_el2 & HCR_VM) == 0; + } + return (regime_sctlr(env, mmu_idx) & SCTLR_M) == 0; +} + +/* Return the TCR controlling this translation regime */ +static inline TCR *regime_tcr(CPUARMState *env, ARMMMUIdx mmu_idx) +{ + if (mmu_idx == ARMMMUIdx_S2NS) { + /* TODO: return VTCR_EL2 */ + g_assert_not_reached(); + } + return &env->cp15.tcr_el[regime_el(env, mmu_idx)]; +} + +/* Return true if the translation regime is using LPAE format page tables */ +static inline bool regime_using_lpae_format(CPUARMState *env, + ARMMMUIdx mmu_idx) +{ + int el = regime_el(env, mmu_idx); + if (el == 2 || arm_el_is_aa64(env, el)) { + return true; + } + if (arm_feature(env, ARM_FEATURE_LPAE) + && (regime_tcr(env, mmu_idx)->raw_tcr & TTBCR_EAE)) { + return true; + } + return false; +} + +static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx) +{ + switch (mmu_idx) { + case ARMMMUIdx_S1SE0: + case ARMMMUIdx_S1NSE0: + return true; + default: + return false; + case ARMMMUIdx_S12NSE0: + case ARMMMUIdx_S12NSE1: + g_assert_not_reached(); + } +} + +/* Translate section/page access permissions to page + * R/W protection flags + * + * @env: CPUARMState + * @mmu_idx: MMU index indicating required translation regime + * @ap: The 3-bit access permissions (AP[2:0]) + * @domain_prot: The 2-bit domain access permissions + */ +static inline int ap_to_rw_prot(CPUARMState *env, ARMMMUIdx mmu_idx, + int ap, int domain_prot) +{ + bool is_user = regime_is_user(env, mmu_idx); + + if (domain_prot == 3) { + return PAGE_READ | PAGE_WRITE; + } + + switch (ap) { + case 0: + if (arm_feature(env, ARM_FEATURE_V7)) { + return 0; + } + switch (regime_sctlr(env, mmu_idx) & (SCTLR_S | SCTLR_R)) { + case SCTLR_S: + return is_user ? 0 : PAGE_READ; + case SCTLR_R: + return PAGE_READ; + default: + return 0; + } + case 1: + return is_user ? 0 : PAGE_READ | PAGE_WRITE; + case 2: + if (is_user) { + return PAGE_READ; + } else { + return PAGE_READ | PAGE_WRITE; + } + case 3: + return PAGE_READ | PAGE_WRITE; + case 4: /* Reserved. */ + return 0; + case 5: + return is_user ? 0 : PAGE_READ; + case 6: + return PAGE_READ; + case 7: + if (!arm_feature(env, ARM_FEATURE_V6K)) { + return 0; + } + return PAGE_READ; + default: + g_assert_not_reached(); + } +} + +/* Translate section/page access permissions to page + * R/W protection flags. + * + * @ap: The 2-bit simple AP (AP[2:1]) + * @is_user: TRUE if accessing from PL0 + */ +static inline int simple_ap_to_rw_prot_is_user(int ap, bool is_user) +{ + switch (ap) { + case 0: + return is_user ? 0 : PAGE_READ | PAGE_WRITE; + case 1: + return PAGE_READ | PAGE_WRITE; + case 2: + return is_user ? 0 : PAGE_READ; + case 3: + return PAGE_READ; + default: + g_assert_not_reached(); + } +} + +static inline int +simple_ap_to_rw_prot(CPUARMState *env, ARMMMUIdx mmu_idx, int ap) +{ + return simple_ap_to_rw_prot_is_user(ap, regime_is_user(env, mmu_idx)); +} + +/* Translate section/page access permissions to protection flags + * + * @env: CPUARMState + * @mmu_idx: MMU index indicating required translation regime + * @is_aa64: TRUE if AArch64 + * @ap: The 2-bit simple AP (AP[2:1]) + * @ns: NS (non-secure) bit + * @xn: XN (execute-never) bit + * @pxn: PXN (privileged execute-never) bit + */ +static int get_S1prot(CPUARMState *env, ARMMMUIdx mmu_idx, bool is_aa64, + int ap, int ns, int xn, int pxn) +{ + bool is_user = regime_is_user(env, mmu_idx); + int prot_rw, user_rw; + bool have_wxn; + int wxn = 0; + + assert(mmu_idx != ARMMMUIdx_S2NS); + + user_rw = simple_ap_to_rw_prot_is_user(ap, true); + if (is_user) { + prot_rw = user_rw; + } else { + prot_rw = simple_ap_to_rw_prot_is_user(ap, false); + } + + if (ns && arm_is_secure(env) && (env->cp15.scr_el3 & SCR_SIF)) { + return prot_rw; + } + + /* TODO have_wxn should be replaced with + * ARM_FEATURE_V8 || (ARM_FEATURE_V7 && ARM_FEATURE_EL2) + * when ARM_FEATURE_EL2 starts getting set. For now we assume all LPAE + * compatible processors have EL2, which is required for [U]WXN. + */ + have_wxn = arm_feature(env, ARM_FEATURE_LPAE); + + if (have_wxn) { + wxn = regime_sctlr(env, mmu_idx) & SCTLR_WXN; + } + + if (is_aa64) { + switch (regime_el(env, mmu_idx)) { + case 1: + if (!is_user) { + xn = pxn || (user_rw & PAGE_WRITE); + } + break; + case 2: + case 3: + break; + } + } else if (arm_feature(env, ARM_FEATURE_V7)) { + switch (regime_el(env, mmu_idx)) { + case 1: + case 3: + if (is_user) { + xn = xn || !(user_rw & PAGE_READ); + } else { + int uwxn = 0; + if (have_wxn) { + uwxn = regime_sctlr(env, mmu_idx) & SCTLR_UWXN; + } + xn = xn || !(prot_rw & PAGE_READ) || pxn || + (uwxn && (user_rw & PAGE_WRITE)); + } + break; + case 2: + break; + } + } else { + xn = wxn = 0; + } + + if (xn || (wxn && (prot_rw & PAGE_WRITE))) { + return prot_rw; + } + return prot_rw | PAGE_EXEC; +} + +static bool get_level1_table_address(CPUARMState *env, ARMMMUIdx mmu_idx, + uint32_t *table, uint32_t address) +{ + /* Note that we can only get here for an AArch32 PL0/PL1 lookup */ + int el = regime_el(env, mmu_idx); + TCR *tcr = regime_tcr(env, mmu_idx); + + if (address & tcr->mask) { + if (tcr->raw_tcr & TTBCR_PD1) { /* Translation table walk disabled for TTBR1 */ return false; } - *table = env->cp15.ttbr1_el1 & 0xffffc000; + *table = env->cp15.ttbr1_el[el] & 0xffffc000; } else { - if ((env->cp15.c2_control & TTBCR_PD0)) { + if (tcr->raw_tcr & TTBCR_PD0) { /* Translation table walk disabled for TTBR0 */ return false; } - *table = env->cp15.ttbr0_el1 & env->cp15.c2_base_mask; + *table = env->cp15.ttbr0_el[el] & tcr->base_mask; } *table |= (address >> 18) & 0x3ffc; return true; } static int get_phys_addr_v5(CPUARMState *env, uint32_t address, int access_type, - int is_user, hwaddr *phys_ptr, + ARMMMUIdx mmu_idx, hwaddr *phys_ptr, int *prot, target_ulong *page_size) { CPUState *cs = CPU(arm_env_get_cpu(env)); @@ -4230,10 +5115,11 @@ static int get_phys_addr_v5(CPUARMState *env, uint32_t address, int access_type, int domain = 0; int domain_prot; hwaddr phys_addr; + uint32_t dacr; /* Pagetable walk. */ /* Lookup l1 descriptor. */ - if (!get_level1_table_address(env, &table, address)) { + if (!get_level1_table_address(env, mmu_idx, &table, address)) { /* Section translation fault if page walk is disabled by PD0 or PD1 */ code = 5; goto do_fault; @@ -4241,7 +5127,12 @@ static int get_phys_addr_v5(CPUARMState *env, uint32_t address, int access_type, desc = ldl_phys(cs->as, table); type = (desc & 3); domain = (desc >> 5) & 0x0f; - domain_prot = (env->cp15.c3 >> (domain * 2)) & 3; + if (regime_el(env, mmu_idx) == 1) { + dacr = env->cp15.dacr_ns; + } else { + dacr = env->cp15.dacr_s; + } + domain_prot = (dacr >> (domain * 2)) & 3; if (type == 0) { /* Section translation fault. */ code = 5; @@ -4262,13 +5153,13 @@ static int get_phys_addr_v5(CPUARMState *env, uint32_t address, int access_type, *page_size = 1024 * 1024; } else { /* Lookup l2 entry. */ - if (type == 1) { - /* Coarse pagetable. */ - table = (desc & 0xfffffc00) | ((address >> 10) & 0x3fc); - } else { - /* Fine pagetable. */ - table = (desc & 0xfffff000) | ((address >> 8) & 0xffc); - } + if (type == 1) { + /* Coarse pagetable. */ + table = (desc & 0xfffffc00) | ((address >> 10) & 0x3fc); + } else { + /* Fine pagetable. */ + table = (desc & 0xfffff000) | ((address >> 8) & 0xffc); + } desc = ldl_phys(cs->as, table); switch (desc & 3) { case 0: /* Page translation fault. */ @@ -4285,17 +5176,17 @@ static int get_phys_addr_v5(CPUARMState *env, uint32_t address, int access_type, *page_size = 0x1000; break; case 3: /* 1k page. */ - if (type == 1) { - if (arm_feature(env, ARM_FEATURE_XSCALE)) { - phys_addr = (desc & 0xfffff000) | (address & 0xfff); - } else { - /* Page translation fault. */ - code = 7; - goto do_fault; - } - } else { - phys_addr = (desc & 0xfffffc00) | (address & 0x3ff); - } + if (type == 1) { + if (arm_feature(env, ARM_FEATURE_XSCALE)) { + phys_addr = (desc & 0xfffff000) | (address & 0xfff); + } else { + /* Page translation fault. */ + code = 7; + goto do_fault; + } + } else { + phys_addr = (desc & 0xfffffc00) | (address & 0x3ff); + } ap = (desc >> 4) & 3; *page_size = 0x400; break; @@ -4305,12 +5196,12 @@ static int get_phys_addr_v5(CPUARMState *env, uint32_t address, int access_type, } code = 15; } - *prot = check_ap(env, ap, domain_prot, access_type, is_user); - if (!*prot) { + *prot = ap_to_rw_prot(env, mmu_idx, ap, domain_prot); + *prot |= *prot ? PAGE_EXEC : 0; + if (!(*prot & (1 << access_type))) { /* Access permission fault. */ goto do_fault; } - *prot |= PAGE_EXEC; *phys_ptr = phys_addr; return 0; do_fault: @@ -4318,7 +5209,7 @@ do_fault: } static int get_phys_addr_v6(CPUARMState *env, uint32_t address, int access_type, - int is_user, hwaddr *phys_ptr, + ARMMMUIdx mmu_idx, hwaddr *phys_ptr, int *prot, target_ulong *page_size) { CPUState *cs = CPU(arm_env_get_cpu(env)); @@ -4332,10 +5223,11 @@ static int get_phys_addr_v6(CPUARMState *env, uint32_t address, int access_type, int domain = 0; int domain_prot; hwaddr phys_addr; + uint32_t dacr; /* Pagetable walk. */ /* Lookup l1 descriptor. */ - if (!get_level1_table_address(env, &table, address)) { + if (!get_level1_table_address(env, mmu_idx, &table, address)) { /* Section translation fault if page walk is disabled by PD0 or PD1 */ code = 5; goto do_fault; @@ -4353,7 +5245,12 @@ static int get_phys_addr_v6(CPUARMState *env, uint32_t address, int access_type, /* Page or Section. */ domain = (desc >> 5) & 0x0f; } - domain_prot = (env->cp15.c3 >> (domain * 2)) & 3; + if (regime_el(env, mmu_idx) == 1) { + dacr = env->cp15.dacr_ns; + } else { + dacr = env->cp15.dacr_s; + } + domain_prot = (dacr >> (domain * 2)) & 3; if (domain_prot == 0 || domain_prot == 2) { if (type != 1) { code = 9; /* Section domain fault. */ @@ -4407,26 +5304,31 @@ static int get_phys_addr_v6(CPUARMState *env, uint32_t address, int access_type, if (domain_prot == 3) { *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; } else { - if (pxn && !is_user) { + if (pxn && !regime_is_user(env, mmu_idx)) { xn = 1; } if (xn && access_type == 2) goto do_fault; - /* The simplified model uses AP[0] as an access control bit. */ - if ((env->cp15.c1_sys & SCTLR_AFE) && (ap & 1) == 0) { - /* Access flag fault. */ - code = (code == 15) ? 6 : 3; - goto do_fault; + if (arm_feature(env, ARM_FEATURE_V6K) && + (regime_sctlr(env, mmu_idx) & SCTLR_AFE)) { + /* The simplified model uses AP[0] as an access control bit. */ + if ((ap & 1) == 0) { + /* Access flag fault. */ + code = (code == 15) ? 6 : 3; + goto do_fault; + } + *prot = simple_ap_to_rw_prot(env, mmu_idx, ap >> 1); + } else { + *prot = ap_to_rw_prot(env, mmu_idx, ap, domain_prot); + } + if (*prot && !xn) { + *prot |= PAGE_EXEC; } - *prot = check_ap(env, ap, domain_prot, access_type, is_user); - if (!*prot) { + if (!(*prot & (1 << access_type))) { /* Access permission fault. */ goto do_fault; } - if (!xn) { - *prot |= PAGE_EXEC; - } } *phys_ptr = phys_addr; return 0; @@ -4444,7 +5346,7 @@ typedef enum { } MMUFaultType; static int get_phys_addr_lpae(CPUARMState *env, target_ulong address, - int access_type, int is_user, + int access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, int *prot, target_ulong *page_size_ptr) { @@ -4464,13 +5366,22 @@ static int get_phys_addr_lpae(CPUARMState *env, target_ulong address, int32_t granule_sz = 9; int32_t va_size = 32; int32_t tbi = 0; - - if (arm_el_is_aa64(env, 1)) { + TCR *tcr = regime_tcr(env, mmu_idx); + int ap, ns, xn, pxn; + + /* TODO: + * This code assumes we're either a 64-bit EL1 or a 32-bit PL1; + * it doesn't handle the different format TCR for TCR_EL2, TCR_EL3, + * and VTCR_EL2, or the fact that those regimes don't have a split + * TTBR0/TTBR1. Attribute and permission bit handling should also + * be checked when adding support for those page table walks. + */ + if (arm_el_is_aa64(env, regime_el(env, mmu_idx))) { va_size = 64; if (extract64(address, 55, 1)) - tbi = extract64(env->cp15.c2_control, 38, 1); + tbi = extract64(tcr->raw_tcr, 38, 1); else - tbi = extract64(env->cp15.c2_control, 37, 1); + tbi = extract64(tcr->raw_tcr, 37, 1); tbi *= 8; } @@ -4479,13 +5390,13 @@ static int get_phys_addr_lpae(CPUARMState *env, target_ulong address, * This is a Non-secure PL0/1 stage 1 translation, so controlled by * TTBCR/TTBR0/TTBR1 in accordance with ARM ARM DDI0406C table B-32: */ - uint32_t t0sz = extract32(env->cp15.c2_control, 0, 6); - if (arm_el_is_aa64(env, 1)) { + uint32_t t0sz = extract32(tcr->raw_tcr, 0, 6); + if (va_size == 64) { t0sz = MIN(t0sz, 39); t0sz = MAX(t0sz, 16); } - uint32_t t1sz = extract32(env->cp15.c2_control, 16, 6); - if (arm_el_is_aa64(env, 1)) { + uint32_t t1sz = extract32(tcr->raw_tcr, 16, 6); + if (va_size == 64) { t1sz = MIN(t1sz, 39); t1sz = MAX(t1sz, 16); } @@ -4515,11 +5426,11 @@ static int get_phys_addr_lpae(CPUARMState *env, target_ulong address, * we will always flush the TLB any time the ASID is changed). */ if (ttbr_select == 0) { - ttbr = env->cp15.ttbr0_el1; - epd = extract32(env->cp15.c2_control, 7, 1); + ttbr = A32_BANKED_CURRENT_REG_GET(env, ttbr0); + epd = extract32(tcr->raw_tcr, 7, 1); tsz = t0sz; - tg = extract32(env->cp15.c2_control, 14, 2); + tg = extract32(tcr->raw_tcr, 14, 2); if (tg == 1) { /* 64KB pages */ granule_sz = 13; } @@ -4527,11 +5438,11 @@ static int get_phys_addr_lpae(CPUARMState *env, target_ulong address, granule_sz = 11; } } else { - ttbr = env->cp15.ttbr1_el1; - epd = extract32(env->cp15.c2_control, 23, 1); + ttbr = A32_BANKED_CURRENT_REG_GET(env, ttbr1); + epd = extract32(tcr->raw_tcr, 23, 1); tsz = t1sz; - tg = extract32(env->cp15.c2_control, 30, 2); + tg = extract32(tcr->raw_tcr, 30, 2); if (tg == 3) { /* 64KB pages */ granule_sz = 13; } @@ -4540,6 +5451,10 @@ static int get_phys_addr_lpae(CPUARMState *env, target_ulong address, } } + /* Here we should have set up all the parameters for the translation: + * va_size, ttbr, epd, tsz, granule_sz, tbi + */ + if (epd) { /* Translation table walk disabled => Translation fault on TLB miss */ goto do_fault; @@ -4613,7 +5528,7 @@ static int get_phys_addr_lpae(CPUARMState *env, target_ulong address, if (extract32(tableattrs, 2, 1)) { attrs &= ~(1 << 4); } - /* Since we're always in the Non-secure state, NSTable is ignored. */ + attrs |= extract32(tableattrs, 4, 1) << 3; /* NS */ break; } /* Here descaddr is the final physical address, and attributes @@ -4624,30 +5539,18 @@ static int get_phys_addr_lpae(CPUARMState *env, target_ulong address, /* Access flag */ goto do_fault; } + + ap = extract32(attrs, 4, 2); + ns = extract32(attrs, 3, 1); + xn = extract32(attrs, 12, 1); + pxn = extract32(attrs, 11, 1); + + *prot = get_S1prot(env, mmu_idx, va_size == 64, ap, ns, xn, pxn); + fault_type = permission_fault; - if (is_user && !(attrs & (1 << 4))) { - /* Unprivileged access not enabled */ + if (!(*prot & (1 << access_type))) { goto do_fault; } - *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; - if ((arm_feature(env, ARM_FEATURE_V8) && is_user && (attrs & (1 << 12))) || - (!arm_feature(env, ARM_FEATURE_V8) && (attrs & (1 << 12))) || - (!is_user && (attrs & (1 << 11)))) { - /* XN/UXN or PXN. Since we only implement EL0/EL1 we unconditionally - * treat XN/UXN as UXN for v8. - */ - if (access_type == 2) { - goto do_fault; - } - *prot &= ~PAGE_EXEC; - } - if (attrs & (1 << 5)) { - /* Write access forbidden */ - if (access_type == 1) { - goto do_fault; - } - *prot &= ~PAGE_WRITE; - } *phys_ptr = descaddr; *page_size_ptr = page_size; @@ -4659,27 +5562,31 @@ do_fault: } static int get_phys_addr_mpu(CPUARMState *env, uint32_t address, - int access_type, int is_user, + int access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, int *prot) { int n; uint32_t mask; uint32_t base; + bool is_user = regime_is_user(env, mmu_idx); *phys_ptr = address; for (n = 7; n >= 0; n--) { - base = env->cp15.c6_region[n]; - if ((base & 1) == 0) - continue; - mask = 1 << ((base >> 1) & 0x1f); - /* Keep this shift separate from the above to avoid an - (undefined) << 32. */ - mask = (mask << 1) - 1; - if (((base ^ address) & ~mask) == 0) - break; - } - if (n < 0) - return 2; + base = env->cp15.c6_region[n]; + if ((base & 1) == 0) { + continue; + } + mask = 1 << ((base >> 1) & 0x1f); + /* Keep this shift separate from the above to avoid an + (undefined) << 32. */ + mask = (mask << 1) - 1; + if (((base ^ address) & ~mask) == 0) { + break; + } + } + if (n < 0) { + return 2; + } if (access_type == 2) { mask = env->cp15.pmsav5_insn_ap; @@ -4689,31 +5596,34 @@ static int get_phys_addr_mpu(CPUARMState *env, uint32_t address, mask = (mask >> (n * 4)) & 0xf; switch (mask) { case 0: - return 1; + return 1; case 1: - if (is_user) - return 1; - *prot = PAGE_READ | PAGE_WRITE; - break; + if (is_user) { + return 1; + } + *prot = PAGE_READ | PAGE_WRITE; + break; case 2: - *prot = PAGE_READ; - if (!is_user) - *prot |= PAGE_WRITE; - break; + *prot = PAGE_READ; + if (!is_user) { + *prot |= PAGE_WRITE; + } + break; case 3: - *prot = PAGE_READ | PAGE_WRITE; - break; + *prot = PAGE_READ | PAGE_WRITE; + break; case 5: - if (is_user) - return 1; - *prot = PAGE_READ; - break; + if (is_user) { + return 1; + } + *prot = PAGE_READ; + break; case 6: - *prot = PAGE_READ; - break; + *prot = PAGE_READ; + break; default: - /* Bad permission. */ - return 1; + /* Bad permission. */ + return 1; } *prot |= PAGE_EXEC; return 0; @@ -4737,38 +5647,60 @@ static int get_phys_addr_mpu(CPUARMState *env, uint32_t address, * @env: CPUARMState * @address: virtual address to get physical address for * @access_type: 0 for read, 1 for write, 2 for execute - * @is_user: 0 for privileged access, 1 for user + * @mmu_idx: MMU index indicating required translation regime * @phys_ptr: set to the physical address corresponding to the virtual address * @prot: set to the permissions for the page containing phys_ptr * @page_size: set to the size of the page containing phys_ptr */ static inline int get_phys_addr(CPUARMState *env, target_ulong address, - int access_type, int is_user, + int access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, int *prot, target_ulong *page_size) { - /* Fast Context Switch Extension. */ - if (address < 0x02000000) - address += env->cp15.c13_fcse; + if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { + /* TODO: when we support EL2 we should here call ourselves recursively + * to do the stage 1 and then stage 2 translations. The ldl_phys + * calls for stage 1 will also need changing. + * For non-EL2 CPUs a stage1+stage2 translation is just stage 1. + */ + assert(!arm_feature(env, ARM_FEATURE_EL2)); + mmu_idx += ARMMMUIdx_S1NSE0; + } + + /* Fast Context Switch Extension. This doesn't exist at all in v8. + * In v7 and earlier it affects all stage 1 translations. + */ + if (address < 0x02000000 && mmu_idx != ARMMMUIdx_S2NS + && !arm_feature(env, ARM_FEATURE_V8)) { + if (regime_el(env, mmu_idx) == 3) { + address += env->cp15.fcseidr_s; + } else { + address += env->cp15.fcseidr_ns; + } + } - if ((env->cp15.c1_sys & SCTLR_M) == 0) { + if (regime_translation_disabled(env, mmu_idx)) { /* MMU/MPU disabled. */ *phys_ptr = address; *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; *page_size = TARGET_PAGE_SIZE; return 0; - } else if (arm_feature(env, ARM_FEATURE_MPU)) { + } + + if (arm_feature(env, ARM_FEATURE_MPU)) { *page_size = TARGET_PAGE_SIZE; - return get_phys_addr_mpu(env, address, access_type, is_user, phys_ptr, - prot); - } else if (extended_addresses_enabled(env)) { - return get_phys_addr_lpae(env, address, access_type, is_user, phys_ptr, + return get_phys_addr_mpu(env, address, access_type, mmu_idx, phys_ptr, + prot); + } + + if (regime_using_lpae_format(env, mmu_idx)) { + return get_phys_addr_lpae(env, address, access_type, mmu_idx, phys_ptr, prot, page_size); - } else if (env->cp15.c1_sys & SCTLR_XP) { - return get_phys_addr_v6(env, address, access_type, is_user, phys_ptr, + } else if (regime_sctlr(env, mmu_idx) & SCTLR_XP) { + return get_phys_addr_v6(env, address, access_type, mmu_idx, phys_ptr, prot, page_size); } else { - return get_phys_addr_v5(env, address, access_type, is_user, phys_ptr, + return get_phys_addr_v5(env, address, access_type, mmu_idx, phys_ptr, prot, page_size); } } @@ -4781,12 +5713,11 @@ int arm_cpu_handle_mmu_fault(CPUState *cs, vaddr address, hwaddr phys_addr; target_ulong page_size; int prot; - int ret, is_user; + int ret; uint32_t syn; bool same_el = (arm_current_el(env) != 0); - is_user = mmu_idx == MMU_USER_IDX; - ret = get_phys_addr(env, address, access_type, is_user, &phys_addr, &prot, + ret = get_phys_addr(env, address, access_type, mmu_idx, &phys_addr, &prot, &page_size); if (ret == 0) { /* Map a single [sub]page. */ @@ -4822,12 +5753,14 @@ int arm_cpu_handle_mmu_fault(CPUState *cs, vaddr address, hwaddr arm_cpu_get_phys_page_debug(CPUState *cs, vaddr addr) { ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; hwaddr phys_addr; target_ulong page_size; int prot; int ret; - ret = get_phys_addr(&cpu->env, addr, 0, 0, &phys_addr, &prot, &page_size); + ret = get_phys_addr(env, addr, 0, cpu_mmu_index(env), &phys_addr, + &prot, &page_size); if (ret != 0) { return -1; @@ -5908,7 +6841,7 @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp) } else { return float64_set_sign(float64_maxnorm, float64_is_neg(f64)); } - } else if (f64_exp >= 1023 && fpst->flush_to_zero) { + } else if (f64_exp >= 2045 && fpst->flush_to_zero) { float_raise(float_flag_underflow, fpst); return float64_set_sign(float64_zero, float64_is_neg(f64)); } diff --git a/target-arm/internals.h b/target-arm/internals.h index 2dff4ffb1..2cc301762 100644 --- a/target-arm/internals.h +++ b/target-arm/internals.h @@ -82,11 +82,14 @@ static inline void arm_log_exception(int idx) /* * For AArch64, map a given EL to an index in the banked_spsr array. + * Note that this mapping and the AArch32 mapping defined in bank_number() + * must agree such that the AArch64<->AArch32 SPSRs have the architecturally + * mandated mapping between each other. */ static inline unsigned int aarch64_banked_spsr_index(unsigned int el) { static const unsigned int map[4] = { - [1] = 0, /* EL1. */ + [1] = 1, /* EL1. */ [2] = 6, /* EL2. */ [3] = 7, /* EL3. */ }; @@ -153,9 +156,9 @@ static inline void update_spsel(CPUARMState *env, uint32_t imm) */ static inline bool extended_addresses_enabled(CPUARMState *env) { - return arm_el_is_aa64(env, 1) - || ((arm_feature(env, ARM_FEATURE_LPAE) - && (env->cp15.c2_control & TTBCR_EAE))); + TCR *tcr = &env->cp15.tcr_el[arm_is_secure(env) ? 3 : 1]; + return arm_el_is_aa64(env, 1) || + (arm_feature(env, ARM_FEATURE_LPAE) && (tcr->raw_tcr & TTBCR_EAE)); } /* Valid Syndrome Register EC field values */ diff --git a/target-arm/kvm.c b/target-arm/kvm.c index 319784d68..fdd9ba3f1 100644 --- a/target-arm/kvm.c +++ b/target-arm/kvm.c @@ -21,12 +21,15 @@ #include "sysemu/kvm.h" #include "kvm_arm.h" #include "cpu.h" +#include "internals.h" #include "hw/arm/arm.h" const KVMCapabilityInfo kvm_arch_required_capabilities[] = { KVM_CAP_LAST_INFO }; +static bool cap_has_mp_state; + int kvm_arm_vcpu_init(CPUState *cs) { ARMCPU *cpu = ARM_CPU(cs); @@ -149,13 +152,15 @@ static const TypeInfo host_arm_cpu_type_info = { .class_size = sizeof(ARMHostCPUClass), }; -int kvm_arch_init(KVMState *s) +int kvm_arch_init(MachineState *ms, KVMState *s) { /* For ARM interrupt delivery is always asynchronous, * whether we are using an in-kernel VGIC or not. */ kvm_async_interrupts_allowed = true; + cap_has_mp_state = kvm_check_extension(s, KVM_CAP_MP_STATE); + type_register_static(&host_arm_cpu_type_info); return 0; @@ -279,6 +284,94 @@ void kvm_arm_register_device(MemoryRegion *mr, uint64_t devid, uint64_t group, memory_region_ref(kd->mr); } +static int compare_u64(const void *a, const void *b) +{ + if (*(uint64_t *)a > *(uint64_t *)b) { + return 1; + } + if (*(uint64_t *)a < *(uint64_t *)b) { + return -1; + } + return 0; +} + +/* Initialize the CPUState's cpreg list according to the kernel's + * definition of what CPU registers it knows about (and throw away + * the previous TCG-created cpreg list). + */ +int kvm_arm_init_cpreg_list(ARMCPU *cpu) +{ + struct kvm_reg_list rl; + struct kvm_reg_list *rlp; + int i, ret, arraylen; + CPUState *cs = CPU(cpu); + + rl.n = 0; + ret = kvm_vcpu_ioctl(cs, KVM_GET_REG_LIST, &rl); + if (ret != -E2BIG) { + return ret; + } + rlp = g_malloc(sizeof(struct kvm_reg_list) + rl.n * sizeof(uint64_t)); + rlp->n = rl.n; + ret = kvm_vcpu_ioctl(cs, KVM_GET_REG_LIST, rlp); + if (ret) { + goto out; + } + /* Sort the list we get back from the kernel, since cpreg_tuples + * must be in strictly ascending order. + */ + qsort(&rlp->reg, rlp->n, sizeof(rlp->reg[0]), compare_u64); + + for (i = 0, arraylen = 0; i < rlp->n; i++) { + if (!kvm_arm_reg_syncs_via_cpreg_list(rlp->reg[i])) { + continue; + } + switch (rlp->reg[i] & KVM_REG_SIZE_MASK) { + case KVM_REG_SIZE_U32: + case KVM_REG_SIZE_U64: + break; + default: + fprintf(stderr, "Can't handle size of register in kernel list\n"); + ret = -EINVAL; + goto out; + } + + arraylen++; + } + + cpu->cpreg_indexes = g_renew(uint64_t, cpu->cpreg_indexes, arraylen); + cpu->cpreg_values = g_renew(uint64_t, cpu->cpreg_values, arraylen); + cpu->cpreg_vmstate_indexes = g_renew(uint64_t, cpu->cpreg_vmstate_indexes, + arraylen); + cpu->cpreg_vmstate_values = g_renew(uint64_t, cpu->cpreg_vmstate_values, + arraylen); + cpu->cpreg_array_len = arraylen; + cpu->cpreg_vmstate_array_len = arraylen; + + for (i = 0, arraylen = 0; i < rlp->n; i++) { + uint64_t regidx = rlp->reg[i]; + if (!kvm_arm_reg_syncs_via_cpreg_list(regidx)) { + continue; + } + cpu->cpreg_indexes[arraylen] = regidx; + arraylen++; + } + assert(cpu->cpreg_array_len == arraylen); + + if (!write_kvmstate_to_list(cpu)) { + /* Shouldn't happen unless kernel is inconsistent about + * what registers exist. + */ + fprintf(stderr, "Initial read of kernel register state failed\n"); + ret = -EINVAL; + goto out; + } + +out: + g_free(rlp); + return ret; +} + bool write_kvmstate_to_list(ARMCPU *cpu) { CPUState *cs = CPU(cpu); @@ -351,6 +444,64 @@ bool write_list_to_kvmstate(ARMCPU *cpu) return ok; } +void kvm_arm_reset_vcpu(ARMCPU *cpu) +{ + int ret; + + /* Re-init VCPU so that all registers are set to + * their respective reset values. + */ + ret = kvm_arm_vcpu_init(CPU(cpu)); + if (ret < 0) { + fprintf(stderr, "kvm_arm_vcpu_init failed: %s\n", strerror(-ret)); + abort(); + } + if (!write_kvmstate_to_list(cpu)) { + fprintf(stderr, "write_kvmstate_to_list failed\n"); + abort(); + } +} + +/* + * Update KVM's MP_STATE based on what QEMU thinks it is + */ +int kvm_arm_sync_mpstate_to_kvm(ARMCPU *cpu) +{ + if (cap_has_mp_state) { + struct kvm_mp_state mp_state = { + .mp_state = + cpu->powered_off ? KVM_MP_STATE_STOPPED : KVM_MP_STATE_RUNNABLE + }; + int ret = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_MP_STATE, &mp_state); + if (ret) { + fprintf(stderr, "%s: failed to set MP_STATE %d/%s\n", + __func__, ret, strerror(-ret)); + return -1; + } + } + + return 0; +} + +/* + * Sync the KVM MP_STATE into QEMU + */ +int kvm_arm_sync_mpstate_to_qemu(ARMCPU *cpu) +{ + if (cap_has_mp_state) { + struct kvm_mp_state mp_state; + int ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_MP_STATE, &mp_state); + if (ret) { + fprintf(stderr, "%s: failed to get MP_STATE %d/%s\n", + __func__, ret, strerror(-ret)); + abort(); + } + cpu->powered_off = (mp_state.mp_state == KVM_MP_STATE_STOPPED); + } + + return 0; +} + void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run) { } @@ -441,3 +592,9 @@ int kvm_arch_irqchip_create(KVMState *s) return 0; } + +int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, + uint64_t address, uint32_t data) +{ + return 0; +} diff --git a/target-arm/kvm32.c b/target-arm/kvm32.c index 5ec4eb1f3..49b6babc0 100644 --- a/target-arm/kvm32.c +++ b/target-arm/kvm32.c @@ -51,17 +51,17 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUClass *ahcc) struct kvm_one_reg idregs[] = { { .id = KVM_REG_ARM | KVM_REG_SIZE_U32 - | ENCODE_CP_REG(15, 0, 0, 0, 0, 0), + | ENCODE_CP_REG(15, 0, 0, 0, 0, 0, 0), .addr = (uintptr_t)&midr, }, { .id = KVM_REG_ARM | KVM_REG_SIZE_U32 - | ENCODE_CP_REG(15, 0, 0, 1, 0, 0), + | ENCODE_CP_REG(15, 0, 0, 0, 1, 0, 0), .addr = (uintptr_t)&id_pfr0, }, { .id = KVM_REG_ARM | KVM_REG_SIZE_U32 - | ENCODE_CP_REG(15, 0, 0, 2, 0, 0), + | ENCODE_CP_REG(15, 0, 0, 0, 2, 0, 0), .addr = (uintptr_t)&id_isar0, }, { @@ -138,7 +138,7 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUClass *ahcc) return true; } -static bool reg_syncs_via_tuple_list(uint64_t regidx) +bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx) { /* Return true if the regidx is a register we should synchronize * via the cpreg_tuples array (ie is not a core reg we sync by @@ -153,24 +153,11 @@ static bool reg_syncs_via_tuple_list(uint64_t regidx) } } -static int compare_u64(const void *a, const void *b) -{ - if (*(uint64_t *)a > *(uint64_t *)b) { - return 1; - } - if (*(uint64_t *)a < *(uint64_t *)b) { - return -1; - } - return 0; -} - int kvm_arch_init_vcpu(CPUState *cs) { - int i, ret, arraylen; + int ret; uint64_t v; struct kvm_one_reg r; - struct kvm_reg_list rl; - struct kvm_reg_list *rlp; ARMCPU *cpu = ARM_CPU(cs); if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE) { @@ -206,73 +193,7 @@ int kvm_arch_init_vcpu(CPUState *cs) return -EINVAL; } - /* Populate the cpreg list based on the kernel's idea - * of what registers exist (and throw away the TCG-created list). - */ - rl.n = 0; - ret = kvm_vcpu_ioctl(cs, KVM_GET_REG_LIST, &rl); - if (ret != -E2BIG) { - return ret; - } - rlp = g_malloc(sizeof(struct kvm_reg_list) + rl.n * sizeof(uint64_t)); - rlp->n = rl.n; - ret = kvm_vcpu_ioctl(cs, KVM_GET_REG_LIST, rlp); - if (ret) { - goto out; - } - /* Sort the list we get back from the kernel, since cpreg_tuples - * must be in strictly ascending order. - */ - qsort(&rlp->reg, rlp->n, sizeof(rlp->reg[0]), compare_u64); - - for (i = 0, arraylen = 0; i < rlp->n; i++) { - if (!reg_syncs_via_tuple_list(rlp->reg[i])) { - continue; - } - switch (rlp->reg[i] & KVM_REG_SIZE_MASK) { - case KVM_REG_SIZE_U32: - case KVM_REG_SIZE_U64: - break; - default: - fprintf(stderr, "Can't handle size of register in kernel list\n"); - ret = -EINVAL; - goto out; - } - - arraylen++; - } - - cpu->cpreg_indexes = g_renew(uint64_t, cpu->cpreg_indexes, arraylen); - cpu->cpreg_values = g_renew(uint64_t, cpu->cpreg_values, arraylen); - cpu->cpreg_vmstate_indexes = g_renew(uint64_t, cpu->cpreg_vmstate_indexes, - arraylen); - cpu->cpreg_vmstate_values = g_renew(uint64_t, cpu->cpreg_vmstate_values, - arraylen); - cpu->cpreg_array_len = arraylen; - cpu->cpreg_vmstate_array_len = arraylen; - - for (i = 0, arraylen = 0; i < rlp->n; i++) { - uint64_t regidx = rlp->reg[i]; - if (!reg_syncs_via_tuple_list(regidx)) { - continue; - } - cpu->cpreg_indexes[arraylen] = regidx; - arraylen++; - } - assert(cpu->cpreg_array_len == arraylen); - - if (!write_kvmstate_to_list(cpu)) { - /* Shouldn't happen unless kernel is inconsistent about - * what registers exist. - */ - fprintf(stderr, "Initial read of kernel register state failed\n"); - ret = -EINVAL; - goto out; - } - -out: - g_free(rlp); - return ret; + return kvm_arm_init_cpreg_list(cpu); } typedef struct Reg { @@ -435,6 +356,8 @@ int kvm_arch_put_registers(CPUState *cs, int level) return EINVAL; } + kvm_arm_sync_mpstate_to_kvm(cpu); + return ret; } @@ -506,14 +429,7 @@ int kvm_arch_get_registers(CPUState *cs) */ write_list_to_cpustate(cpu); - return 0; -} + kvm_arm_sync_mpstate_to_qemu(cpu); -void kvm_arm_reset_vcpu(ARMCPU *cpu) -{ - /* Re-init VCPU so that all registers are set to - * their respective reset values. - */ - kvm_arm_vcpu_init(CPU(cpu)); - write_kvmstate_to_list(cpu); + return 0; } diff --git a/target-arm/kvm64.c b/target-arm/kvm64.c index c61528615..93c1ca8b2 100644 --- a/target-arm/kvm64.c +++ b/target-arm/kvm64.c @@ -15,6 +15,7 @@ #include <linux/kvm.h> +#include "config-host.h" #include "qemu-common.h" #include "qemu/timer.h" #include "sysemu/sysemu.h" @@ -82,7 +83,7 @@ int kvm_arch_init_vcpu(CPUState *cs) ARMCPU *cpu = ARM_CPU(cs); if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE || - !arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { + !object_dynamic_cast(OBJECT(cpu), TYPE_AARCH64_CPU)) { fprintf(stderr, "KVM is not supported for this guest CPU type\n"); return -EINVAL; } @@ -96,6 +97,9 @@ int kvm_arch_init_vcpu(CPUState *cs) cpu->psci_version = 2; cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PSCI_0_2; } + if (!arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { + cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_EL1_32BIT; + } /* Do KVM_ARM_VCPU_INIT ioctl */ ret = kvm_arm_vcpu_init(cs); @@ -103,24 +107,51 @@ int kvm_arch_init_vcpu(CPUState *cs) return ret; } - /* TODO : support for save/restore/reset of system regs via tuple list */ + return kvm_arm_init_cpreg_list(cpu); +} - return 0; +bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx) +{ + /* Return true if the regidx is a register we should synchronize + * via the cpreg_tuples array (ie is not a core reg we sync by + * hand in kvm_arch_get/put_registers()) + */ + switch (regidx & KVM_REG_ARM_COPROC_MASK) { + case KVM_REG_ARM_CORE: + return false; + default: + return true; + } } #define AARCH64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x)) +#define AARCH64_SIMD_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U128 | \ + KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x)) + +#define AARCH64_SIMD_CTRL_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U32 | \ + KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x)) + int kvm_arch_put_registers(CPUState *cs, int level) { struct kvm_one_reg reg; + uint32_t fpr; uint64_t val; int i; int ret; + unsigned int el; ARMCPU *cpu = ARM_CPU(cs); CPUARMState *env = &cpu->env; + /* If we are in AArch32 mode then we need to copy the AArch32 regs to the + * AArch64 registers before pushing them out to 64-bit KVM. + */ + if (!is_a64(env)) { + aarch64_sync_32_to_64(env); + } + for (i = 0; i < 31; i++) { reg.id = AARCH64_CORE_REG(regs.regs[i]); reg.addr = (uintptr_t) &env->xregs[i]; @@ -150,7 +181,11 @@ int kvm_arch_put_registers(CPUState *cs, int level) } /* Note that KVM thinks pstate is 64 bit but we use a uint32_t */ - val = pstate_read(env); + if (is_a64(env)) { + val = pstate_read(env); + } else { + val = cpsr_read(env); + } reg.id = AARCH64_CORE_REG(regs.pstate); reg.addr = (uintptr_t) &val; ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); @@ -172,19 +207,70 @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } + /* Saved Program State Registers + * + * Before we restore from the banked_spsr[] array we need to + * ensure that any modifications to env->spsr are correctly + * reflected in the banks. + */ + el = arm_current_el(env); + if (el > 0 && !is_a64(env)) { + i = bank_number(env->uncached_cpsr & CPSR_M); + env->banked_spsr[i] = env->spsr; + } + + /* KVM 0-4 map to QEMU banks 1-5 */ for (i = 0; i < KVM_NR_SPSR; i++) { reg.id = AARCH64_CORE_REG(spsr[i]); - reg.addr = (uintptr_t) &env->banked_spsr[i - 1]; + reg.addr = (uintptr_t) &env->banked_spsr[i + 1]; ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); if (ret) { return ret; } } - /* TODO: - * FP state - * system registers + /* Advanced SIMD and FP registers + * We map Qn = regs[2n+1]:regs[2n] */ + for (i = 0; i < 32; i++) { + int rd = i << 1; + uint64_t fp_val[2]; +#ifdef HOST_WORDS_BIGENDIAN + fp_val[0] = env->vfp.regs[rd + 1]; + fp_val[1] = env->vfp.regs[rd]; +#else + fp_val[1] = env->vfp.regs[rd + 1]; + fp_val[0] = env->vfp.regs[rd]; +#endif + reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]); + reg.addr = (uintptr_t)(&fp_val); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + if (ret) { + return ret; + } + } + + reg.addr = (uintptr_t)(&fpr); + fpr = vfp_get_fpsr(env); + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + if (ret) { + return ret; + } + + fpr = vfp_get_fpcr(env); + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr); + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + if (ret) { + return ret; + } + + if (!write_list_to_kvmstate(cpu)) { + return EINVAL; + } + + kvm_arm_sync_mpstate_to_kvm(cpu); + return ret; } @@ -192,6 +278,8 @@ int kvm_arch_get_registers(CPUState *cs) { struct kvm_one_reg reg; uint64_t val; + uint32_t fpr; + unsigned int el; int i; int ret; @@ -227,7 +315,14 @@ int kvm_arch_get_registers(CPUState *cs) if (ret) { return ret; } - pstate_write(env, val); + + env->aarch64 = ((val & PSTATE_nRW) == 0); + if (is_a64(env)) { + pstate_write(env, val); + } else { + env->uncached_cpsr = val & CPSR_M; + cpsr_write(env, val, 0xffffffff); + } /* KVM puts SP_EL0 in regs.sp and SP_EL1 in regs.sp_el1. On the * QEMU side we keep the current SP in xregs[31] as well. @@ -241,6 +336,15 @@ int kvm_arch_get_registers(CPUState *cs) return ret; } + /* If we are in AArch32 mode then we need to sync the AArch32 regs with the + * incoming AArch64 regs received from 64-bit KVM. + * We must perform this after all of the registers have been acquired from + * the kernel. + */ + if (!is_a64(env)) { + aarch64_sync_64_to_32(env); + } + reg.id = AARCH64_CORE_REG(elr_el1); reg.addr = (uintptr_t) &env->elr_el[1]; ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); @@ -248,23 +352,72 @@ int kvm_arch_get_registers(CPUState *cs) return ret; } + /* Fetch the SPSR registers + * + * KVM SPSRs 0-4 map to QEMU banks 1-5 + */ for (i = 0; i < KVM_NR_SPSR; i++) { reg.id = AARCH64_CORE_REG(spsr[i]); - reg.addr = (uintptr_t) &env->banked_spsr[i - 1]; + reg.addr = (uintptr_t) &env->banked_spsr[i + 1]; ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); if (ret) { return ret; } } - /* TODO: other registers */ - return ret; -} + el = arm_current_el(env); + if (el > 0 && !is_a64(env)) { + i = bank_number(env->uncached_cpsr & CPSR_M); + env->spsr = env->banked_spsr[i]; + } -void kvm_arm_reset_vcpu(ARMCPU *cpu) -{ - /* Re-init VCPU so that all registers are set to - * their respective reset values. + /* Advanced SIMD and FP registers + * We map Qn = regs[2n+1]:regs[2n] + */ + for (i = 0; i < 32; i++) { + uint64_t fp_val[2]; + reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]); + reg.addr = (uintptr_t)(&fp_val); + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + if (ret) { + return ret; + } else { + int rd = i << 1; +#ifdef HOST_WORDS_BIGENDIAN + env->vfp.regs[rd + 1] = fp_val[0]; + env->vfp.regs[rd] = fp_val[1]; +#else + env->vfp.regs[rd + 1] = fp_val[1]; + env->vfp.regs[rd] = fp_val[0]; +#endif + } + } + + reg.addr = (uintptr_t)(&fpr); + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr); + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + if (ret) { + return ret; + } + vfp_set_fpsr(env, fpr); + + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr); + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + if (ret) { + return ret; + } + vfp_set_fpcr(env, fpr); + + if (!write_kvmstate_to_list(cpu)) { + return EINVAL; + } + /* Note that it's OK to have registers which aren't in CPUState, + * so we can ignore a failure return here. */ - kvm_arm_vcpu_init(CPU(cpu)); + write_list_to_cpustate(cpu); + + kvm_arm_sync_mpstate_to_qemu(cpu); + + /* TODO: other registers */ + return ret; } diff --git a/target-arm/kvm_arm.h b/target-arm/kvm_arm.h index af9310551..5abd5916d 100644 --- a/target-arm/kvm_arm.h +++ b/target-arm/kvm_arm.h @@ -47,6 +47,28 @@ void kvm_arm_register_device(MemoryRegion *mr, uint64_t devid, uint64_t group, uint64_t attr, int dev_fd); /** + * kvm_arm_init_cpreg_list: + * @cs: CPUState + * + * Initialize the CPUState's cpreg list according to the kernel's + * definition of what CPU registers it knows about (and throw away + * the previous TCG-created cpreg list). + * + * Returns: 0 if success, else < 0 error code + */ +int kvm_arm_init_cpreg_list(ARMCPU *cpu); + +/** + * kvm_arm_reg_syncs_via_cpreg_list + * regidx: KVM register index + * + * Return true if this KVM register should be synchronized via the + * cpreg list of arbitrary system registers, false if it is synchronized + * by hand using code in kvm_arch_get/put_registers(). + */ +bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx); + +/** * write_list_to_kvmstate: * @cpu: ARMCPU * @@ -140,6 +162,23 @@ typedef struct ARMHostCPUClass { */ bool kvm_arm_get_host_cpu_features(ARMHostCPUClass *ahcc); + +/** + * kvm_arm_sync_mpstate_to_kvm + * @cpu: ARMCPU + * + * If supported set the KVM MP_STATE based on QEMU's model. + */ +int kvm_arm_sync_mpstate_to_kvm(ARMCPU *cpu); + +/** + * kvm_arm_sync_mpstate_to_qemu + * @cpu: ARMCPU + * + * If supported get the MP_STATE from KVM and store in QEMU's model. + */ +int kvm_arm_sync_mpstate_to_qemu(ARMCPU *cpu); + #endif #endif diff --git a/target-arm/machine.c b/target-arm/machine.c index 6437690af..9446e5a8a 100644 --- a/target-arm/machine.c +++ b/target-arm/machine.c @@ -127,6 +127,13 @@ static int get_cpsr(QEMUFile *f, void *opaque, size_t size) CPUARMState *env = &cpu->env; uint32_t val = qemu_get_be32(f); + env->aarch64 = ((val & PSTATE_nRW) == 0); + + if (is_a64(env)) { + pstate_write(env, val); + return 0; + } + /* Avoid mode switch when restoring CPSR */ env->uncached_cpsr = val & CPSR_M; cpsr_write(env, val, 0xffffffff); @@ -137,8 +144,15 @@ static void put_cpsr(QEMUFile *f, void *opaque, size_t size) { ARMCPU *cpu = opaque; CPUARMState *env = &cpu->env; + uint32_t val; + + if (is_a64(env)) { + val = pstate_read(env); + } else { + val = cpsr_read(env); + } - qemu_put_be32(f, cpsr_read(env)); + qemu_put_be32(f, val); } static const VMStateInfo vmstate_cpsr = { @@ -222,12 +236,14 @@ static int cpu_post_load(void *opaque, int version_id) const VMStateDescription vmstate_arm_cpu = { .name = "cpu", - .version_id = 21, - .minimum_version_id = 21, + .version_id = 22, + .minimum_version_id = 22, .pre_save = cpu_pre_save, .post_load = cpu_post_load, .fields = (VMStateField[]) { VMSTATE_UINT32_ARRAY(env.regs, ARMCPU, 16), + VMSTATE_UINT64_ARRAY(env.xregs, ARMCPU, 32), + VMSTATE_UINT64(env.pc, ARMCPU), { .name = "cpsr", .version_id = 0, @@ -261,8 +277,8 @@ const VMStateDescription vmstate_arm_cpu = { VMSTATE_UINT32(env.exception.syndrome, ARMCPU), VMSTATE_UINT32(env.exception.fsr, ARMCPU), VMSTATE_UINT64(env.exception.vaddress, ARMCPU), - VMSTATE_TIMER(gt_timer[GTIMER_PHYS], ARMCPU), - VMSTATE_TIMER(gt_timer[GTIMER_VIRT], ARMCPU), + VMSTATE_TIMER_PTR(gt_timer[GTIMER_PHYS], ARMCPU), + VMSTATE_TIMER_PTR(gt_timer[GTIMER_VIRT], ARMCPU), VMSTATE_BOOL(powered_off, ARMCPU), VMSTATE_END_OF_LIST() }, diff --git a/target-arm/op_helper.c b/target-arm/op_helper.c index 62012c3a6..771302275 100644 --- a/target-arm/op_helper.c +++ b/target-arm/op_helper.c @@ -361,7 +361,7 @@ void HELPER(msr_i_pstate)(CPUARMState *env, uint32_t op, uint32_t imm) * Note that SPSel is never OK from EL0; we rely on handle_msr_i() * to catch that case at translate time. */ - if (arm_current_el(env) == 0 && !(env->cp15.c1_sys & SCTLR_UMA)) { + if (arm_current_el(env) == 0 && !(env->cp15.sctlr_el[1] & SCTLR_UMA)) { raise_exception(env, EXCP_UDEF); } @@ -465,7 +465,7 @@ void HELPER(exception_return)(CPUARMState *env) int cur_el = arm_current_el(env); unsigned int spsr_idx = aarch64_banked_spsr_index(cur_el); uint32_t spsr = env->banked_spsr[spsr_idx]; - int new_el, i; + int new_el; aarch64_save_sp(env, cur_el); @@ -491,9 +491,7 @@ void HELPER(exception_return)(CPUARMState *env) if (!arm_singlestep_active(env)) { env->uncached_cpsr &= ~PSTATE_SS; } - for (i = 0; i < 15; i++) { - env->regs[i] = env->xregs[i]; - } + aarch64_sync_64_to_32(env); env->regs[15] = env->elr_el[1] & ~0x1; } else { @@ -575,7 +573,7 @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn) * short descriptor format (in which case it holds both PROCID and ASID), * since we don't implement the optional v7 context ID masking. */ - contextidr = extract64(env->cp15.contextidr_el1, 0, 32); + contextidr = extract64(env->cp15.contextidr_el[1], 0, 32); switch (bt) { case 3: /* linked context ID match */ diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c index 80d2c07e8..0b192a1f5 100644 --- a/target-arm/translate-a64.c +++ b/target-arm/translate-a64.c @@ -123,6 +123,23 @@ void a64_translate_init(void) #endif } +static inline ARMMMUIdx get_a64_user_mem_index(DisasContext *s) +{ + /* Return the mmu_idx to use for A64 "unprivileged load/store" insns: + * if EL1, access as if EL0; otherwise access at current EL + */ + switch (s->mmu_idx) { + case ARMMMUIdx_S12NSE1: + return ARMMMUIdx_S12NSE0; + case ARMMMUIdx_S1SE1: + return ARMMMUIdx_S1SE0; + case ARMMMUIdx_S2NS: + g_assert_not_reached(); + default: + return s->mmu_idx; + } +} + void aarch64_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, int flags) { @@ -1060,7 +1077,7 @@ static void disas_uncond_b_imm(DisasContext *s, uint32_t insn) { uint64_t addr = s->pc + sextract32(insn, 0, 26) * 4 - 4; - if (insn & (1 << 31)) { + if (insn & (1U << 31)) { /* C5.6.26 BL Branch with link */ tcg_gen_movi_i64(cpu_reg(s, 30), s->pc); } @@ -1079,7 +1096,7 @@ static void disas_comp_b_imm(DisasContext *s, uint32_t insn) { unsigned int sf, op, rt; uint64_t addr; - int label_match; + TCGLabel *label_match; TCGv_i64 tcg_cmp; sf = extract32(insn, 31, 1); @@ -1108,7 +1125,7 @@ static void disas_test_b_imm(DisasContext *s, uint32_t insn) { unsigned int bit_pos, op, rt; uint64_t addr; - int label_match; + TCGLabel *label_match; TCGv_i64 tcg_cmp; bit_pos = (extract32(insn, 31, 1) << 5) | extract32(insn, 19, 5); @@ -1147,7 +1164,7 @@ static void disas_cond_b_imm(DisasContext *s, uint32_t insn) if (cond < 0x0e) { /* genuinely conditional branches */ - int label_match = gen_new_label(); + TCGLabel *label_match = gen_new_label(); arm_gen_test_cc(cond, label_match); gen_goto_tb(s, 0, s->pc); gen_set_label(label_match); @@ -1254,7 +1271,7 @@ static void gen_get_nzcv(TCGv_i64 tcg_rt) TCGv_i32 nzcv = tcg_temp_new_i32(); /* build bit 31, N */ - tcg_gen_andi_i32(nzcv, cpu_NF, (1 << 31)); + tcg_gen_andi_i32(nzcv, cpu_NF, (1U << 31)); /* build bit 30, Z */ tcg_gen_setcondi_i32(TCG_COND_EQ, tmp, cpu_ZF, 0); tcg_gen_deposit_i32(nzcv, nzcv, tmp, 30, 1); @@ -1279,7 +1296,7 @@ static void gen_set_nzcv(TCGv_i64 tcg_rt) tcg_gen_trunc_i64_i32(nzcv, tcg_rt); /* bit 31, N */ - tcg_gen_andi_i32(cpu_NF, nzcv, (1 << 31)); + tcg_gen_andi_i32(cpu_NF, nzcv, (1U << 31)); /* bit 30, Z */ tcg_gen_andi_i32(cpu_ZF, nzcv, (1 << 30)); tcg_gen_setcondi_i32(TCG_COND_EQ, cpu_ZF, cpu_ZF, 0); @@ -1372,7 +1389,7 @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, break; } - if (use_icount && (ri->type & ARM_CP_IO)) { + if ((s->tb->cflags & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { gen_io_start(); } @@ -1403,7 +1420,7 @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, } } - if (use_icount && (ri->type & ARM_CP_IO)) { + if ((s->tb->cflags & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { /* I/O operations must end the TB here (whether read or write) */ gen_io_end(); s->is_jmp = DISAS_UPDATE; @@ -1694,8 +1711,8 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, * } * env->exclusive_addr = -1; */ - int fail_label = gen_new_label(); - int done_label = gen_new_label(); + TCGLabel *fail_label = gen_new_label(); + TCGLabel *done_label = gen_new_label(); TCGv_i64 addr = tcg_temp_local_new_i64(); TCGv_i64 tmp; @@ -1900,7 +1917,7 @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) int rt = extract32(insn, 0, 5); int rn = extract32(insn, 5, 5); int rt2 = extract32(insn, 10, 5); - int64_t offset = sextract32(insn, 15, 7); + uint64_t offset = sextract64(insn, 15, 7); int index = extract32(insn, 23, 2); bool is_vector = extract32(insn, 26, 1); bool is_load = extract32(insn, 22, 1); @@ -2107,7 +2124,7 @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn) } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); - int memidx = is_unpriv ? 1 : get_mem_index(s); + int memidx = is_unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); if (is_store) { do_gpr_st_memidx(s, tcg_rt, tcg_addr, size, memidx); @@ -2645,11 +2662,12 @@ static void disas_pc_rel_adr(DisasContext *s, uint32_t insn) { unsigned int page, rd; uint64_t base; - int64_t offset; + uint64_t offset; page = extract32(insn, 31, 1); /* SignExtend(immhi:immlo) -> offset */ - offset = ((int64_t)sextract32(insn, 5, 19) << 2) | extract32(insn, 29, 2); + offset = sextract64(insn, 5, 19); + offset = offset << 2 | extract32(insn, 29, 2); rd = extract32(insn, 0, 5); base = s->pc - 4; @@ -2803,7 +2821,10 @@ static bool logic_imm_decode_wmask(uint64_t *result, unsigned int immn, * by r within the element (which is e bits wide)... */ mask = bitmask64(s + 1); - mask = (mask >> r) | (mask << (e - r)); + if (r) { + mask = (mask >> r) | (mask << (e - r)); + mask &= bitmask64(e); + } /* ...then replicate the element over the whole 64 bit value */ mask = bitfield_replicate(mask, e); *result = mask; @@ -3516,7 +3537,7 @@ static void disas_adc_sbc(DisasContext *s, uint32_t insn) static void disas_cc(DisasContext *s, uint32_t insn) { unsigned int sf, op, y, cond, rn, nzcv, is_imm; - int label_continue = -1; + TCGLabel *label_continue = NULL; TCGv_i64 tcg_tmp, tcg_y, tcg_rn; if (!extract32(insn, 29, 1)) { @@ -3536,7 +3557,7 @@ static void disas_cc(DisasContext *s, uint32_t insn) nzcv = extract32(insn, 0, 4); if (cond < 0x0e) { /* not always */ - int label_match = gen_new_label(); + TCGLabel *label_match = gen_new_label(); label_continue = gen_new_label(); arm_gen_test_cc(cond, label_match); /* nomatch: */ @@ -3609,8 +3630,8 @@ static void disas_cond_select(DisasContext *s, uint32_t insn) /* OPTME: we could use movcond here, at the cost of duplicating * a lot of the arm_gen_test_cc() logic. */ - int label_match = gen_new_label(); - int label_continue = gen_new_label(); + TCGLabel *label_match = gen_new_label(); + TCGLabel *label_continue = gen_new_label(); arm_gen_test_cc(cond, label_match); /* nomatch: */ @@ -4083,7 +4104,7 @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) { unsigned int mos, type, rm, cond, rn, op, nzcv; TCGv_i64 tcg_flags; - int label_continue = -1; + TCGLabel *label_continue = NULL; mos = extract32(insn, 29, 3); type = extract32(insn, 22, 2); /* 0 = single, 1 = double */ @@ -4103,7 +4124,7 @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) } if (cond < 0x0e) { /* not always */ - int label_match = gen_new_label(); + TCGLabel *label_match = gen_new_label(); label_continue = gen_new_label(); arm_gen_test_cc(cond, label_match); /* nomatch: */ @@ -4144,7 +4165,7 @@ static void gen_mov_fp2fp(DisasContext *s, int type, int dst, int src) static void disas_fp_csel(DisasContext *s, uint32_t insn) { unsigned int mos, type, rm, cond, rn, rd; - int label_continue = -1; + TCGLabel *label_continue = NULL; mos = extract32(insn, 29, 3); type = extract32(insn, 22, 2); /* 0 = single, 1 = double */ @@ -4163,7 +4184,7 @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) } if (cond < 0x0e) { /* not always */ - int label_match = gen_new_label(); + TCGLabel *label_match = gen_new_label(); label_continue = gen_new_label(); arm_gen_test_cc(cond, label_match); /* nomatch: */ @@ -10899,7 +10920,6 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu, CPUARMState *env = &cpu->env; DisasContext dc1, *dc = &dc1; CPUBreakpoint *bp; - uint16_t *gen_opc_end; int j, lj; target_ulong pc_start; target_ulong next_page_start; @@ -10910,8 +10930,6 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu, dc->tb = tb; - gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE; - dc->is_jmp = DISAS_NEXT; dc->pc = pc_start; dc->singlestep_enabled = cs->singlestep_enabled; @@ -10922,14 +10940,15 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu, dc->bswap_code = 0; dc->condexec_mask = 0; dc->condexec_cond = 0; + dc->mmu_idx = ARM_TBFLAG_MMUIDX(tb->flags); + dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); #if !defined(CONFIG_USER_ONLY) - dc->user = (ARM_TBFLAG_AA64_EL(tb->flags) == 0); + dc->user = (dc->current_el == 0); #endif dc->cpacr_fpen = ARM_TBFLAG_AA64_FPEN(tb->flags); dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = cpu->cp_regs; - dc->current_el = arm_current_el(env); dc->features = env->features; /* Single step state. The code-generation logic here is: @@ -10962,7 +10981,7 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu, max_insns = CF_COUNT_MASK; } - gen_tb_start(); + gen_tb_start(tb); tcg_clear_temp_count(); @@ -10980,7 +10999,7 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu, } if (search_pc) { - j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf; + j = tcg_op_buf_count(); if (lj < j) { lj++; while (lj < j) { @@ -11030,7 +11049,7 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu, * ensures prefetch aborts occur at the right place. */ num_insns++; - } while (!dc->is_jmp && tcg_ctx.gen_opc_ptr < gen_opc_end && + } while (!dc->is_jmp && !tcg_op_buf_full() && !cs->singlestep_enabled && !singlestep && !dc->ss_active && @@ -11090,7 +11109,6 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu, done_generating: gen_tb_end(tb, num_insns); - *tcg_ctx.gen_opc_ptr = INDEX_op_end; #ifdef DEBUG_DISAS if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) { @@ -11102,7 +11120,7 @@ done_generating: } #endif if (search_pc) { - j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf; + j = tcg_op_buf_count(); lj++; while (lj <= j) { tcg_ctx.gen_opc_instr_start[lj++] = 0; diff --git a/target-arm/translate.c b/target-arm/translate.c index af5156857..f8f72bede 100644 --- a/target-arm/translate.c +++ b/target-arm/translate.c @@ -113,6 +113,28 @@ void arm_translate_init(void) a64_translate_init(); } +static inline ARMMMUIdx get_a32_user_mem_index(DisasContext *s) +{ + /* Return the mmu_idx to use for A32/T32 "unprivileged load/store" + * insns: + * if PL2, UNPREDICTABLE (we choose to implement as if PL0) + * otherwise, access as if at PL0. + */ + switch (s->mmu_idx) { + case ARMMMUIdx_S1E2: /* this one is UNPREDICTABLE */ + case ARMMMUIdx_S12NSE0: + case ARMMMUIdx_S12NSE1: + return ARMMMUIdx_S12NSE0; + case ARMMMUIdx_S1E3: + case ARMMMUIdx_S1SE0: + case ARMMMUIdx_S1SE1: + return ARMMMUIdx_S1SE0; + case ARMMMUIdx_S2NS: + default: + g_assert_not_reached(); + } +} + static inline TCGv_i32 load_cpu_offset(int offset) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -714,10 +736,10 @@ static void gen_thumb2_parallel_addsub(int op1, int op2, TCGv_i32 a, TCGv_i32 b) * generate a conditional branch based on ARM condition code cc. * This is common between ARM and Aarch64 targets. */ -void arm_gen_test_cc(int cc, int label) +void arm_gen_test_cc(int cc, TCGLabel *label) { TCGv_i32 tmp; - int inv; + TCGLabel *inv; switch (cc) { case 0: /* eq: Z */ @@ -7091,7 +7113,7 @@ static int disas_coproc_insn(DisasContext *s, uint32_t insn) rt = (insn >> 12) & 0xf; ri = get_arm_cp_reginfo(s->cp_regs, - ENCODE_CP_REG(cpnum, is64, crn, crm, opc1, opc2)); + ENCODE_CP_REG(cpnum, is64, s->ns, crn, crm, opc1, opc2)); if (ri) { /* Check access permissions */ if (!cp_access_ok(s->current_el, ri, isread)) { @@ -7170,7 +7192,7 @@ static int disas_coproc_insn(DisasContext *s, uint32_t insn) break; } - if (use_icount && (ri->type & ARM_CP_IO)) { + if ((s->tb->cflags & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { gen_io_start(); } @@ -7261,7 +7283,7 @@ static int disas_coproc_insn(DisasContext *s, uint32_t insn) } } - if (use_icount && (ri->type & ARM_CP_IO)) { + if ((s->tb->cflags & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { /* I/O operations must end the TB here (whether read or write) */ gen_io_end(); gen_lookup_tb(s); @@ -7281,12 +7303,16 @@ static int disas_coproc_insn(DisasContext *s, uint32_t insn) */ if (is64) { qemu_log_mask(LOG_UNIMP, "%s access to unsupported AArch32 " - "64 bit system register cp:%d opc1: %d crm:%d\n", - isread ? "read" : "write", cpnum, opc1, crm); + "64 bit system register cp:%d opc1: %d crm:%d " + "(%s)\n", + isread ? "read" : "write", cpnum, opc1, crm, + s->ns ? "non-secure" : "secure"); } else { qemu_log_mask(LOG_UNIMP, "%s access to unsupported AArch32 " - "system register cp:%d opc1:%d crn:%d crm:%d opc2:%d\n", - isread ? "read" : "write", cpnum, opc1, crn, crm, opc2); + "system register cp:%d opc1:%d crn:%d crm:%d opc2:%d " + "(%s)\n", + isread ? "read" : "write", cpnum, opc1, crn, crm, opc2, + s->ns ? "non-secure" : "secure"); } return 1; @@ -7414,8 +7440,8 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, { TCGv_i32 tmp; TCGv_i64 val64, extaddr; - int done_label; - int fail_label; + TCGLabel *done_label; + TCGLabel *fail_label; /* if (env->exclusive_addr == addr && env->exclusive_val == [addr]) { [addr] = {Rt}; @@ -8397,34 +8423,30 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } } else { int address_offset; - int load; + bool load = insn & (1 << 20); + bool doubleword = false; /* Misc load/store */ rn = (insn >> 16) & 0xf; rd = (insn >> 12) & 0xf; + + if (!load && (sh & 2)) { + /* doubleword */ + ARCH(5TE); + if (rd & 1) { + /* UNPREDICTABLE; we choose to UNDEF */ + goto illegal_op; + } + load = (sh & 1) == 0; + doubleword = true; + } + addr = load_reg(s, rn); if (insn & (1 << 24)) gen_add_datah_offset(s, insn, 0, addr); address_offset = 0; - if (insn & (1 << 20)) { - /* load */ - tmp = tcg_temp_new_i32(); - switch(sh) { - case 1: - gen_aa32_ld16u(tmp, addr, get_mem_index(s)); - break; - case 2: - gen_aa32_ld8s(tmp, addr, get_mem_index(s)); - break; - default: - case 3: - gen_aa32_ld16s(tmp, addr, get_mem_index(s)); - break; - } - load = 1; - } else if (sh & 2) { - ARCH(5TE); - /* doubleword */ - if (sh & 1) { + + if (doubleword) { + if (!load) { /* store */ tmp = load_reg(s, rd); gen_aa32_st32(tmp, addr, get_mem_index(s)); @@ -8433,7 +8455,6 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) tmp = load_reg(s, rd + 1); gen_aa32_st32(tmp, addr, get_mem_index(s)); tcg_temp_free_i32(tmp); - load = 0; } else { /* load */ tmp = tcg_temp_new_i32(); @@ -8443,15 +8464,28 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) tmp = tcg_temp_new_i32(); gen_aa32_ld32u(tmp, addr, get_mem_index(s)); rd++; - load = 1; } address_offset = -4; + } else if (load) { + /* load */ + tmp = tcg_temp_new_i32(); + switch (sh) { + case 1: + gen_aa32_ld16u(tmp, addr, get_mem_index(s)); + break; + case 2: + gen_aa32_ld8s(tmp, addr, get_mem_index(s)); + break; + default: + case 3: + gen_aa32_ld16s(tmp, addr, get_mem_index(s)); + break; + } } else { /* store */ tmp = load_reg(s, rd); gen_aa32_st16(tmp, addr, get_mem_index(s)); tcg_temp_free_i32(tmp); - load = 0; } /* Perform base writeback before the loaded value to ensure correct behavior with overlapping index registers. @@ -8735,6 +8769,10 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) ARCH(6T2); shift = (insn >> 7) & 0x1f; i = (insn >> 16) & 0x1f; + if (i < shift) { + /* UNPREDICTABLE; we choose to UNDEF */ + goto illegal_op; + } i = i + 1 - shift; if (rm == 15) { tmp = tcg_temp_new_i32(); @@ -8789,7 +8827,7 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) tmp2 = load_reg(s, rn); if ((insn & 0x01200000) == 0x00200000) { /* ldrt/strt */ - i = MMU_USER_IDX; + i = get_a32_user_mem_index(s); } else { i = get_mem_index(s); } @@ -8829,17 +8867,23 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) case 0x08: case 0x09: { - int j, n, user, loaded_base; + int j, n, loaded_base; + bool exc_return = false; + bool is_load = extract32(insn, 20, 1); + bool user = false; TCGv_i32 loaded_var; /* load/store multiple words */ /* XXX: store correct base if write back */ - user = 0; if (insn & (1 << 22)) { + /* LDM (user), LDM (exception return) and STM (user) */ if (IS_USER(s)) goto illegal_op; /* only usable in supervisor mode */ - if ((insn & (1 << 15)) == 0) - user = 1; + if (is_load && extract32(insn, 15, 1)) { + exc_return = true; + } else { + user = true; + } } rn = (insn >> 16) & 0xf; addr = load_reg(s, rn); @@ -8873,7 +8917,7 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) j = 0; for(i=0;i<16;i++) { if (insn & (1 << i)) { - if (insn & (1 << 20)) { + if (is_load) { /* load */ tmp = tcg_temp_new_i32(); gen_aa32_ld32u(tmp, addr, get_mem_index(s)); @@ -8938,7 +8982,7 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) if (loaded_base) { store_reg(s, rn, loaded_var); } - if ((insn & (1 << 22)) && !user) { + if (exc_return) { /* Restore CPSR from SPSR. */ tmp = load_cpu_field(spsr); gen_set_cpsr(tmp, CPSR_ERET_MASK); @@ -10169,7 +10213,7 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw break; case 0xe: /* User privilege. */ tcg_gen_addi_i32(addr, addr, imm); - memidx = MMU_USER_IDX; + memidx = get_a32_user_mem_index(s); break; case 0x9: /* Post-decrement. */ imm = -imm; @@ -10995,7 +11039,6 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu, CPUARMState *env = &cpu->env; DisasContext dc1, *dc = &dc1; CPUBreakpoint *bp; - uint16_t *gen_opc_end; int j, lj; target_ulong pc_start; target_ulong next_page_start; @@ -11016,8 +11059,6 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu, dc->tb = tb; - gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE; - dc->is_jmp = DISAS_NEXT; dc->pc = pc_start; dc->singlestep_enabled = cs->singlestep_enabled; @@ -11028,16 +11069,18 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu, dc->bswap_code = ARM_TBFLAG_BSWAP_CODE(tb->flags); dc->condexec_mask = (ARM_TBFLAG_CONDEXEC(tb->flags) & 0xf) << 1; dc->condexec_cond = ARM_TBFLAG_CONDEXEC(tb->flags) >> 4; + dc->mmu_idx = ARM_TBFLAG_MMUIDX(tb->flags); + dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); #if !defined(CONFIG_USER_ONLY) - dc->user = (ARM_TBFLAG_PRIV(tb->flags) == 0); + dc->user = (dc->current_el == 0); #endif + dc->ns = ARM_TBFLAG_NS(tb->flags); dc->cpacr_fpen = ARM_TBFLAG_CPACR_FPEN(tb->flags); dc->vfp_enabled = ARM_TBFLAG_VFPEN(tb->flags); dc->vec_len = ARM_TBFLAG_VECLEN(tb->flags); dc->vec_stride = ARM_TBFLAG_VECSTRIDE(tb->flags); dc->c15_cpar = ARM_TBFLAG_XSCALE_CPAR(tb->flags); dc->cp_regs = cpu->cp_regs; - dc->current_el = arm_current_el(env); dc->features = env->features; /* Single step state. The code-generation logic here is: @@ -11075,7 +11118,7 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu, if (max_insns == 0) max_insns = CF_COUNT_MASK; - gen_tb_start(); + gen_tb_start(tb); tcg_clear_temp_count(); @@ -11150,7 +11193,7 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu, } } if (search_pc) { - j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf; + j = tcg_op_buf_count(); if (lj < j) { lj++; while (lj < j) @@ -11216,7 +11259,7 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu, * Also stop translation when a page boundary is reached. This * ensures prefetch aborts occur at the right place. */ num_insns ++; - } while (!dc->is_jmp && tcg_ctx.gen_opc_ptr < gen_opc_end && + } while (!dc->is_jmp && !tcg_op_buf_full() && !cs->singlestep_enabled && !singlestep && !dc->ss_active && @@ -11325,7 +11368,6 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu, done_generating: gen_tb_end(tb, num_insns); - *tcg_ctx.gen_opc_ptr = INDEX_op_end; #ifdef DEBUG_DISAS if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) { @@ -11337,7 +11379,7 @@ done_generating: } #endif if (search_pc) { - j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf; + j = tcg_op_buf_count(); lj++; while (lj <= j) tcg_ctx.gen_opc_instr_start[lj++] = 0; diff --git a/target-arm/translate.h b/target-arm/translate.h index 41a907157..9829576ab 100644 --- a/target-arm/translate.h +++ b/target-arm/translate.h @@ -9,7 +9,7 @@ typedef struct DisasContext { /* Nonzero if this instruction has been conditionally skipped. */ int condjmp; /* The label that will be jumped to when the instruction is skipped. */ - int condlabel; + TCGLabel *condlabel; /* Thumb-2 conditional execution bits. */ int condexec_mask; int condexec_cond; @@ -20,6 +20,8 @@ typedef struct DisasContext { #if !defined(CONFIG_USER_ONLY) int user; #endif + ARMMMUIdx mmu_idx; /* MMU index to use for normal loads/stores */ + bool ns; /* Use non-secure CPREG bank on access */ bool cpacr_fpen; /* FP enabled via CPACR.FPEN */ bool vfp_enabled; /* FP enabled via FPSCR.EN */ int vec_len; @@ -68,7 +70,7 @@ static inline int arm_dc_feature(DisasContext *dc, int feature) static inline int get_mem_index(DisasContext *s) { - return s->current_el; + return s->mmu_idx; } /* target-specific extra values for is_jmp */ @@ -117,6 +119,6 @@ static inline void aarch64_cpu_dump_state(CPUState *cs, FILE *f, } #endif -void arm_gen_test_cc(int cc, int label); +void arm_gen_test_cc(int cc, TCGLabel *label); #endif /* TARGET_ARM_TRANSLATE_H */ |